diff options
303 files changed, 4147 insertions, 1671 deletions
@@ -41,7 +41,8 @@ Andrew Murray <[email protected]> <[email protected]> Andrew Vasquez <[email protected]> Andrey Ryabinin <[email protected]> <[email protected]> Andy Adamson <[email protected]> -Antoine Tenart <[email protected]> +Antoine Tenart <[email protected]> <[email protected]> +Antoine Tenart <[email protected]> <[email protected]> Antonio Ospite <[email protected]> <[email protected]> Archit Taneja <[email protected]> Ard Biesheuvel <[email protected]> <[email protected]> @@ -188,6 +189,7 @@ Leon Romanovsky <[email protected]> <[email protected]> Linas Vepstas <[email protected]> Linus Lüssing <[email protected]> <[email protected]> Linus Lüssing <[email protected]> <[email protected]> Li Yang <[email protected]> <[email protected]> Li Yang <[email protected]> <[email protected]> Lukasz Luba <[email protected]> <[email protected]> diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst index a96a423e3779..6ebe163f9dfe 100644 --- a/Documentation/admin-guide/pm/cpuidle.rst +++ b/Documentation/admin-guide/pm/cpuidle.rst @@ -690,7 +690,7 @@ which of the two parameters is added to the kernel command line. In the instruction of the CPUs (which, as a rule, suspends the execution of the program and causes the hardware to attempt to enter the shallowest available idle state) for this purpose, and if ``idle=poll`` is used, idle CPUs will execute a -more or less ``lightweight'' sequence of instructions in a tight loop. [Note +more or less "lightweight" sequence of instructions in a tight loop. [Note that using ``idle=poll`` is somewhat drastic in many cases, as preventing idle CPUs from saving almost any energy at all may not be the only effect of it. For example, on Intel hardware it effectively prevents CPUs from using diff --git a/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt b/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt index d4d83916c09d..be329ea4794f 100644 --- a/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt +++ b/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt @@ -20,8 +20,9 @@ Required properties: - gpio-controller : Marks the device node as a GPIO controller - interrupts : Interrupt specifier, see interrupt-controller/interrupts.txt - interrupt-controller : Mark the GPIO controller as an interrupt-controller -- ngpios : number of GPIO lines, see gpio.txt - (should be multiple of 8, up to 80 pins) +- ngpios : number of *hardware* GPIO lines, see gpio.txt. This will expose + 2 software GPIOs per hardware GPIO: one for hardware input, one for hardware + output. Up to 80 pins, must be a multiple of 8. - clocks : A phandle to the APB clock for SGPM clock division - bus-frequency : SGPM CLK frequency diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt index 032b76f14f4f..9119f1caf391 100644 --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt @@ -21,6 +21,7 @@ Required properties: - "renesas,etheravb-r8a774a1" for the R8A774A1 SoC. - "renesas,etheravb-r8a774b1" for the R8A774B1 SoC. - "renesas,etheravb-r8a774c0" for the R8A774C0 SoC. + - "renesas,etheravb-r8a774e1" for the R8A774E1 SoC. - "renesas,etheravb-r8a7795" for the R8A7795 SoC. - "renesas,etheravb-r8a7796" for the R8A77960 SoC. - "renesas,etheravb-r8a77961" for the R8A77961 SoC. diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst index 7fafc7ac00d7..abb9fc164657 100644 --- a/Documentation/x86/boot.rst +++ b/Documentation/x86/boot.rst @@ -1342,8 +1342,8 @@ follow:: In addition to read/modify/write the setup header of the struct boot_params as that of 16-bit boot protocol, the boot loader should -also fill the additional fields of the struct boot_params as that -described in zero-page.txt. +also fill the additional fields of the struct boot_params as +described in chapter :doc:`zero-page`. After setting up the struct boot_params, the boot loader can load the 32/64-bit kernel in the same way as that of 16-bit boot protocol. @@ -1379,7 +1379,7 @@ can be calculated as follows:: In addition to read/modify/write the setup header of the struct boot_params as that of 16-bit boot protocol, the boot loader should also fill the additional fields of the struct boot_params as described -in zero-page.txt. +in chapter :doc:`zero-page`. After setting up the struct boot_params, the boot loader can load 64-bit kernel in the same way as that of 16-bit boot protocol, but diff --git a/MAINTAINERS b/MAINTAINERS index 48aff80d1f29..d61d45daa31b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1460,6 +1460,11 @@ S: Odd Fixes F: drivers/amba/ F: include/linux/amba/bus.h +ARM PRIMECELL CLCD PL110 DRIVER +M: Russell King <[email protected]> +S: Odd Fixes +F: drivers/video/fbdev/amba-clcd.* + ARM PRIMECELL KMI PL050 DRIVER M: Russell King <[email protected]> S: Odd Fixes @@ -1623,7 +1628,7 @@ N: meson ARM/Annapurna Labs ALPINE ARCHITECTURE M: Tsahee Zidenberg <[email protected]> -M: Antoine Tenart <[email protected]> +M: Antoine Tenart <[email protected]> L: [email protected] (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/alpine* @@ -7235,7 +7240,7 @@ F: drivers/staging/gasket/ GCC PLUGINS M: Kees Cook <[email protected]> R: Emese Revfy <[email protected]> S: Maintained F: Documentation/kbuild/gcc-plugins.rst F: scripts/Makefile.gcc-plugins @@ -8673,7 +8678,7 @@ F: drivers/input/input-mt.c K: \b(ABS|SYN)_MT_ INSIDE SECURE CRYPTO DRIVER -M: Antoine Tenart <[email protected]> +M: Antoine Tenart <[email protected]> S: Maintained F: drivers/crypto/inside-secure/ @@ -8752,7 +8757,8 @@ F: include/drm/i915* F: include/uapi/drm/i915_drm.h INTEL ETHERNET DRIVERS -M: Jeff Kirsher <[email protected]> +M: Jesse Brandeburg <[email protected]> +M: Tony Nguyen <[email protected]> L: [email protected] (moderated for non-subscribers) S: Supported W: http://www.intel.com/support/feedback.htm @@ -9796,7 +9802,7 @@ F: drivers/scsi/53c700* LEAKING_ADDRESSES M: Tobin C. Harding <[email protected]> M: Tycho Andersen <[email protected]> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tobin/leaks.git F: scripts/leaking_addresses.pl @@ -12077,6 +12083,7 @@ NETWORKING [DSA] M: Andrew Lunn <[email protected]> M: Vivien Didelot <[email protected]> M: Florian Fainelli <[email protected]> +M: Vladimir Oltean <[email protected]> S: Maintained F: Documentation/devicetree/bindings/net/dsa/ F: drivers/net/dsa/ @@ -13182,6 +13189,7 @@ F: drivers/firmware/pcdp.* PCI DRIVER FOR AARDVARK (Marvell Armada 3700) M: Thomas Petazzoni <[email protected]> +M: Pali Rohár <[email protected]> L: [email protected] (moderated for non-subscribers) S: Maintained @@ -16724,6 +16732,13 @@ S: Maintained F: Documentation/devicetree/bindings/gpio/snps,dw-apb-gpio.yaml F: drivers/gpio/gpio-dwapb.c +SYNOPSYS DESIGNWARE APB SSI DRIVER +M: Serge Semin <[email protected]> +S: Supported +F: Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml +F: drivers/spi/spi-dw* + SYNOPSYS DESIGNWARE AXI DMAC DRIVER M: Eugeniy Paltsev <[email protected]> S: Maintained @@ -18281,7 +18296,8 @@ F: drivers/gpu/vga/vga_switcheroo.c F: include/linux/vga_switcheroo.h VIA RHINE NETWORK DRIVER -S: Orphan +S: Maintained +M: Kevin Brace <[email protected]> F: drivers/net/ethernet/via/via-rhine.c VIA SD/MMC CARD CONTROLLER DRIVER @@ -18886,10 +18902,10 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/mm F: arch/x86/mm/ X86 PLATFORM DRIVERS -M: Darren Hart <[email protected]> -M: Andy Shevchenko <[email protected]> +M: Hans de Goede <[email protected]> +M: Mark Gross <[email protected]> -S: Odd Fixes +S: Maintained T: git git://git.infradead.org/linux-platform-drivers-x86.git F: drivers/platform/olpc/ F: drivers/platform/x86/ @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c index 24dd5bbe60e4..094337dc1bc7 100644 --- a/arch/arm/mach-imx/cpuidle-imx6q.c +++ b/arch/arm/mach-imx/cpuidle-imx6q.c @@ -24,7 +24,9 @@ static int imx6q_enter_wait(struct cpuidle_device *dev, imx6_set_lpm(WAIT_UNCLOCKED); raw_spin_unlock(&cpuidle_lock); + rcu_idle_enter(); cpu_do_idle(); + rcu_idle_exit(); raw_spin_lock(&cpuidle_lock); if (num_idle_cpus-- == num_online_cpus()) @@ -44,7 +46,7 @@ static struct cpuidle_driver imx6q_cpuidle_driver = { { .exit_latency = 50, .target_residency = 75, - .flags = CPUIDLE_FLAG_TIMER_STOP, + .flags = CPUIDLE_FLAG_TIMER_STOP | CPUIDLE_FLAG_RCU_IDLE, .enter = imx6q_enter_wait, .name = "WAIT", .desc = "Clock off", diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index e93145d72c26..a6ab3689b2f4 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -150,7 +150,7 @@ static int xen_starting_cpu(unsigned int cpu) pr_info("Xen: initializing cpu%d\n", cpu); vcpup = per_cpu_ptr(xen_vcpu_info, cpu); - info.mfn = virt_to_gfn(vcpup); + info.mfn = percpu_to_gfn(vcpup); info.offset = xen_offset_in_page(vcpup); err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu), diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S index b357164379f6..63a52ad9a75c 100644 --- a/arch/arm64/crypto/aes-neonbs-core.S +++ b/arch/arm64/crypto/aes-neonbs-core.S @@ -788,7 +788,7 @@ SYM_FUNC_START_LOCAL(__xts_crypt8) 0: mov bskey, x21 mov rounds, x22 - br x7 + br x16 SYM_FUNC_END(__xts_crypt8) .macro __xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7 @@ -806,7 +806,7 @@ SYM_FUNC_END(__xts_crypt8) uzp1 v30.4s, v30.4s, v25.4s ld1 {v25.16b}, [x24] -99: adr x7, \do8 +99: adr x16, \do8 bl __xts_crypt8 ldp q16, q17, [sp, #.Lframe_local_offset] diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index a85174d05473..cada0b816c8a 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -298,8 +298,21 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: case EFI_PERSISTENT_MEMORY: - pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys); - return NULL; + if (memblock_is_map_memory(phys) || + !memblock_is_region_memory(phys, size)) { + pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys); + return NULL; + } + /* + * Mapping kernel memory is permitted if the region in + * question is covered by a single memblock with the + * NOMAP attribute set: this enables the use of ACPI + * table overrides passed via initramfs, which are + * reserved in memory using arch_reserve_mem_area() + * below. As this particular use case only requires + * read access, fall through to the R/O mapping case. + */ + fallthrough; case EFI_RUNTIME_SERVICES_CODE: /* @@ -388,3 +401,8 @@ int apei_claim_sea(struct pt_regs *regs) return err; } + +void arch_reserve_mem_area(acpi_physical_address addr, size_t size) +{ + memblock_mark_nomap(addr, size); +} diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c index 69eae608d670..b15d65a42042 100644 --- a/arch/arm64/kvm/hyp/nvhe/tlb.c +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -31,7 +31,14 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu, isb(); } + /* + * __load_guest_stage2() includes an ISB only when the AT + * workaround is applied. Take care of the opposite condition, + * ensuring that we always have an ISB, but not two ISBs back + * to back. + */ __load_guest_stage2(mmu); + asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT)); } static void __tlb_switch_to_host(struct tlb_inv_context *cxt) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 78d61f97371e..e809cb5a1631 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -475,7 +475,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: true_cond = COND_NE; - fallthrough; cond_branch: /* same targets, can avoid doing the test :) */ if (filter[i].jt == filter[i].jf) { diff --git a/arch/riscv/include/asm/stackprotector.h b/arch/riscv/include/asm/stackprotector.h index d95f7b2a7f37..5962f8891f06 100644 --- a/arch/riscv/include/asm/stackprotector.h +++ b/arch/riscv/include/asm/stackprotector.h @@ -5,7 +5,6 @@ #include <linux/random.h> #include <linux/version.h> -#include <asm/timex.h> extern unsigned long __stack_chk_guard; @@ -18,12 +17,9 @@ extern unsigned long __stack_chk_guard; static __always_inline void boot_init_stack_canary(void) { unsigned long canary; - unsigned long tsc; /* Try to get a semi random initial value. */ get_random_bytes(&canary, sizeof(canary)); - tsc = get_cycles(); - canary += tsc + (tsc << BITS_PER_LONG/2); canary ^= LINUX_VERSION_CODE; canary &= CANARY_MASK; diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index 7f659dda0032..ab104905d4db 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -33,6 +33,19 @@ static inline u32 get_cycles_hi(void) #define get_cycles_hi get_cycles_hi #endif /* CONFIG_64BIT */ +/* + * Much like MIPS, we may not have a viable counter to use at an early point + * in the boot process. Unfortunately we don't have a fallback, so instead + * we just return 0. + */ +static inline unsigned long random_get_entropy(void) +{ + if (unlikely(clint_time_val == NULL)) + return 0; + return get_cycles(); +} +#define random_get_entropy() random_get_entropy() + #else /* CONFIG_RISCV_M_MODE */ static inline cycles_t get_cycles(void) diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index f3586e31ed1e..34d00d9e6eac 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -22,13 +22,11 @@ SECTIONS /* Beginning of code and text segment */ . = LOAD_OFFSET; _start = .; - _stext = .; HEAD_TEXT_SECTION . = ALIGN(PAGE_SIZE); __init_begin = .; INIT_TEXT_SECTION(PAGE_SIZE) - INIT_DATA_SECTION(16) . = ALIGN(8); __soc_early_init_table : { __soc_early_init_table_start = .; @@ -55,6 +53,7 @@ SECTIONS . = ALIGN(SECTION_ALIGN); .text : { _text = .; + _stext = .; TEXT_TEXT SCHED_TEXT CPUIDLE_TEXT @@ -67,6 +66,8 @@ SECTIONS _etext = .; } + INIT_DATA_SECTION(16) + /* Start of data section */ _sdata = .; RO_DATA(SECTION_ALIGN) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ca03762a3733..f750e012dbe5 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -515,6 +515,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) #else dtb_early_va = (void *)dtb_pa; #endif + dtb_early_pa = dtb_pa; } static inline void setup_vm_final(void) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index f43a78bde670..fc4f8c04bdb5 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1904,6 +1904,8 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check; static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) { + bool irq_state; + WARN_ON_ONCE(user_mode(regs)); /* @@ -1914,7 +1916,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) mce_check_crashing_cpu()) return; - nmi_enter(); + irq_state = idtentry_enter_nmi(regs); /* * The call targets are marked noinstr, but objtool can't figure * that out because it's an indirect call. Annotate it. @@ -1925,7 +1927,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) if (regs->flags & X86_EFLAGS_IF) trace_hardirqs_on_prepare(); instrumentation_end(); - nmi_exit(); + idtentry_exit_nmi(regs, irq_state); } static __always_inline void exc_machine_check_user(struct pt_regs *regs) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7b2a068f08c1..96979c09ebd1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -794,6 +794,18 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu) */ if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; + else { + /* + * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched + * between guest and host. In that case we only care about present + * faults. For vmcs02, however, PFEC_MASK and PFEC_MATCH are set in + * prepare_vmcs02_rare. + */ + bool selective_pf_trap = enable_ept && (eb & (1u << PF_VECTOR)); + int mask = selective_pf_trap ? PFERR_PRESENT_MASK : 0; + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, mask); + } vmcs_write32(EXCEPTION_BITMAP, eb); } @@ -4355,16 +4367,6 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmx->pt_desc.guest.output_mask = 0x7F; vmcs_write64(GUEST_IA32_RTIT_CTL, 0); } - - /* - * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched - * between guest and host. In that case we only care about present - * faults. - */ - if (enable_ept) { - vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, PFERR_PRESENT_MASK); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, PFERR_PRESENT_MASK); - } } static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) diff --git a/block/blk-mq.c b/block/blk-mq.c index b3d2785eefe9..cdced4aca2e8 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1412,6 +1412,11 @@ out: hctx->dispatched[queued_to_index(queued)]++; + /* If we didn't flush the entire list, we could have told the driver + * there was more coming, but that turned out to be a lie. + */ + if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued) + q->mq_ops->commit_rqs(hctx); /* * Any items that need requeuing? Stuff them into hctx->dispatch, * that is where we will continue on next queue run. @@ -1425,14 +1430,6 @@ out: blk_mq_release_budgets(q, nr_budgets); - /* - * If we didn't flush the entire list, we could have told - * the driver there was more coming, but that turned out to - * be a lie. - */ - if (q->mq_ops->commit_rqs && queued) - q->mq_ops->commit_rqs(hctx); - spin_lock(&hctx->lock); list_splice_tail_init(list, &hctx->dispatch); spin_unlock(&hctx->lock); @@ -2079,6 +2076,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list) { int queued = 0; + int errors = 0; while (!list_empty(list)) { blk_status_t ret; @@ -2095,6 +2093,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, break; } blk_mq_end_request(rq, ret); + errors++; } else queued++; } @@ -2104,7 +2103,8 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, * the driver there was more coming, but that turned out to * be a lie. */ - if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs && queued) + if ((!list_empty(list) || errors) && + hctx->queue->mq_ops->commit_rqs && queued) hctx->queue->mq_ops->commit_rqs(hctx); } diff --git a/block/partitions/ibm.c b/block/partitions/ibm.c index d6e18df9c53c..4b044e620d35 100644 --- a/block/partitions/ibm.c +++ b/block/partitions/ibm.c @@ -305,8 +305,6 @@ int ibm_partition(struct parsed_partitions *state) if (!disk->fops->getgeo) goto out_exit; fn = symbol_get(dasd_biodasdinfo); - if (!fn) - goto out_exit; blocksize = bdev_logical_block_size(bdev); if (blocksize <= 0) goto out_symbol; @@ -326,7 +324,7 @@ int ibm_partition(struct parsed_partitions *state) geo->start = get_start_sect(bdev); if (disk->fops->getgeo(bdev, geo)) goto out_freeall; - if (fn(disk, info)) { + if (!fn || fn(disk, info)) { kfree(info); info = NULL; } @@ -370,7 +368,8 @@ out_nolab: out_nogeo: kfree(info); out_symbol: - symbol_put(dasd_biodasdinfo); + if (fn) + symbol_put(dasd_biodasdinfo); out_exit: return res; } diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index ef722f04f88a..72108404718f 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -651,6 +651,7 @@ struct compat_cdrom_generic_command { compat_int_t stat; compat_caddr_t sense; unsigned char data_direction; + unsigned char pad[3]; compat_int_t quiet; compat_int_t timeout; compat_caddr_t reserved[1]; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 04b6bde9419d..573dbf6f0c31 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -1553,7 +1553,7 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa * put_page(); and would cause either a VM_BUG directly, or * __page_cache_release a page that would actually still be referenced * by someone, leading to some obscure delayed Oops somewhere else. */ - if (drbd_disable_sendpage || (page_count(page) < 1) || PageSlab(page)) + if (drbd_disable_sendpage || !sendpage_ok(page)) return _drbd_no_send_page(peer_device, page, offset, size, msg_flags); msg_flags |= MSG_NOSIGNAL; diff --git a/drivers/clocksource/timer-clint.c b/drivers/clocksource/timer-clint.c index d17367dee02c..6cfe2ab73eb0 100644 --- a/drivers/clocksource/timer-clint.c +++ b/drivers/clocksource/timer-clint.c @@ -38,6 +38,7 @@ static unsigned int clint_timer_irq; #ifdef CONFIG_RISCV_M_MODE u64 __iomem *clint_time_val; +EXPORT_SYMBOL(clint_time_val); #endif static void clint_send_ipi(const struct cpumask *target) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index a827b000ef51..9a515c460a00 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2781,6 +2781,7 @@ static int intel_pstate_update_status(const char *buf, size_t size) cpufreq_unregister_driver(intel_pstate_driver); intel_pstate_driver_cleanup(); + return 0; } if (size == 6 && !strncmp(buf, "active", size)) { diff --git a/drivers/gpio/gpio-amd-fch.c b/drivers/gpio/gpio-amd-fch.c index 4e44ba4d7423..2a21354ed6a0 100644 --- a/drivers/gpio/gpio-amd-fch.c +++ b/drivers/gpio/gpio-amd-fch.c @@ -92,7 +92,7 @@ static int amd_fch_gpio_get_direction(struct gpio_chip *gc, unsigned int gpio) ret = (readl_relaxed(ptr) & AMD_FCH_GPIO_FLAG_DIRECTION); spin_unlock_irqrestore(&priv->lock, flags); - return ret ? GPIO_LINE_DIRECTION_IN : GPIO_LINE_DIRECTION_OUT; + return ret ? GPIO_LINE_DIRECTION_OUT : GPIO_LINE_DIRECTION_IN; } static void amd_fch_gpio_set(struct gpio_chip *gc, diff --git a/drivers/gpio/gpio-aspeed-sgpio.c b/drivers/gpio/gpio-aspeed-sgpio.c index 3aa45934d60c..64e54f8c30d2 100644 --- a/drivers/gpio/gpio-aspeed-sgpio.c +++ b/drivers/gpio/gpio-aspeed-sgpio.c @@ -17,7 +17,17 @@ #include <linux/spinlock.h> #include <linux/string.h> -#define MAX_NR_SGPIO 80 +/* + * MAX_NR_HW_GPIO represents the number of actual hardware-supported GPIOs (ie, + * slots within the clocked serial GPIO data). Since each HW GPIO is both an + * input and an output, we provide MAX_NR_HW_GPIO * 2 lines on our gpiochip + * device. + * + * We use SGPIO_OUTPUT_OFFSET to define the split between the inputs and + * outputs; the inputs start at line 0, the outputs start at OUTPUT_OFFSET. + */ +#define MAX_NR_HW_SGPIO 80 +#define SGPIO_OUTPUT_OFFSET MAX_NR_HW_SGPIO #define ASPEED_SGPIO_CTRL 0x54 @@ -30,8 +40,8 @@ struct aspeed_sgpio { struct clk *pclk; spinlock_t lock; void __iomem *base; - uint32_t dir_in[3]; int irq; + int n_sgpio; }; struct aspeed_sgpio_bank { @@ -111,31 +121,69 @@ static void __iomem *bank_reg(struct aspeed_sgpio *gpio, } } -#define GPIO_BANK(x) ((x) >> 5) -#define GPIO_OFFSET(x) ((x) & 0x1f) +#define GPIO_BANK(x) ((x % SGPIO_OUTPUT_OFFSET) >> 5) +#define GPIO_OFFSET(x) ((x % SGPIO_OUTPUT_OFFSET) & 0x1f) #define GPIO_BIT(x) BIT(GPIO_OFFSET(x)) static const struct aspeed_sgpio_bank *to_bank(unsigned int offset) { - unsigned int bank = GPIO_BANK(offset); + unsigned int bank; + + bank = GPIO_BANK(offset); WARN_ON(bank >= ARRAY_SIZE(aspeed_sgpio_banks)); return &aspeed_sgpio_banks[bank]; } +static int aspeed_sgpio_init_valid_mask(struct gpio_chip *gc, + unsigned long *valid_mask, unsigned int ngpios) +{ + struct aspeed_sgpio *sgpio = gpiochip_get_data(gc); + int n = sgpio->n_sgpio; + int c = SGPIO_OUTPUT_OFFSET - n; + + WARN_ON(ngpios < MAX_NR_HW_SGPIO * 2); + + /* input GPIOs in the lower range */ + bitmap_set(valid_mask, 0, n); + bitmap_clear(valid_mask, n, c); + + /* output GPIOS above SGPIO_OUTPUT_OFFSET */ + bitmap_set(valid_mask, SGPIO_OUTPUT_OFFSET, n); + bitmap_clear(valid_mask, SGPIO_OUTPUT_OFFSET + n, c); + + return 0; +} + +static void aspeed_sgpio_irq_init_valid_mask(struct gpio_chip *gc, + unsigned long *valid_mask, unsigned int ngpios) +{ + struct aspeed_sgpio *sgpio = gpiochip_get_data(gc); + int n = sgpio->n_sgpio; + + WARN_ON(ngpios < MAX_NR_HW_SGPIO * 2); + + /* input GPIOs in the lower range */ + bitmap_set(valid_mask, 0, n); + bitmap_clear(valid_mask, n, ngpios - n); +} + +static bool aspeed_sgpio_is_input(unsigned int offset) +{ + return offset < SGPIO_OUTPUT_OFFSET; +} + static int aspeed_sgpio_get(struct gpio_chip *gc, unsigned int offset) { struct aspeed_sgpio *gpio = gpiochip_get_data(gc); const struct aspeed_sgpio_bank *bank = to_bank(offset); unsigned long flags; enum aspeed_sgpio_reg reg; - bool is_input; int rc = 0; spin_lock_irqsave(&gpio->lock, flags); - is_input = gpio->dir_in[GPIO_BANK(offset)] & GPIO_BIT(offset); - reg = is_input ? reg_val : reg_rdata; + reg = aspeed_sgpio_is_input(offset) ? reg_val : reg_rdata; rc = !!(ioread32(bank_reg(gpio, bank, reg)) & GPIO_BIT(offset)); spin_unlock_irqrestore(&gpio->lock, flags); @@ -143,22 +191,31 @@ static int aspeed_sgpio_get(struct gpio_chip *gc, unsigned int offset) return rc; } -static void sgpio_set_value(struct gpio_chip *gc, unsigned int offset, int val) +static int sgpio_set_value(struct gpio_chip *gc, unsigned int offset, int val) { struct aspeed_sgpio *gpio = gpiochip_get_data(gc); const struct aspeed_sgpio_bank *bank = to_bank(offset); - void __iomem *addr; + void __iomem *addr_r, *addr_w; u32 reg = 0; - addr = bank_reg(gpio, bank, reg_val); - reg = ioread32(addr); + if (aspeed_sgpio_is_input(offset)) + return -EINVAL; + + /* Since this is an output, read the cached value from rdata, then + * update val. */ + addr_r = bank_reg(gpio, bank, reg_rdata); + addr_w = bank_reg(gpio, bank, reg_val); + + reg = ioread32(addr_r); if (val) reg |= GPIO_BIT(offset); else reg &= ~GPIO_BIT(offset); - iowrite32(reg, addr); + iowrite32(reg, addr_w); + + return 0; } static void aspeed_sgpio_set(struct gpio_chip *gc, unsigned int offset, int val) @@ -175,43 +232,28 @@ static void aspeed_sgpio_set(struct gpio_chip *gc, unsigned int offset, int val) static int aspeed_sgpio_dir_in(struct gpio_chip *gc, unsigned int offset) { - struct aspeed_sgpio *gpio = gpiochip_get_data(gc); - unsigned long flags; - - spin_lock_irqsave(&gpio->lock, flags); - gpio->dir_in[GPIO_BANK(offset)] |= GPIO_BIT(offset); - spin_unlock_irqrestore(&gpio->lock, flags); - - return 0; + return aspeed_sgpio_is_input(offset) ? 0 : -EINVAL; } static int aspeed_sgpio_dir_out(struct gpio_chip *gc, unsigned int offset, int val) { struct aspeed_sgpio *gpio = gpiochip_get_data(gc); unsigned long flags; + int rc; - spin_lock_irqsave(&gpio->lock, flags); - - gpio->dir_in[GPIO_BANK(offset)] &= ~GPIO_BIT(offset); - sgpio_set_value(gc, offset, val); + /* No special action is required for setting the direction; we'll + * error-out in sgpio_set_value if this isn't an output GPIO */ + spin_lock_irqsave(&gpio->lock, flags); + rc = sgpio_set_value(gc, offset, val); spin_unlock_irqrestore(&gpio->lock, flags); - return 0; + return rc; } static int aspeed_sgpio_get_direction(struct gpio_chip *gc, unsigned int offset) { - int dir_status; - struct aspeed_sgpio *gpio = gpiochip_get_data(gc); - unsigned long flags; - - spin_lock_irqsave(&gpio->lock, flags); - dir_status = gpio->dir_in[GPIO_BANK(offset)] & GPIO_BIT(offset); - spin_unlock_irqrestore(&gpio->lock, flags); - - return dir_status; - + return !!aspeed_sgpio_is_input(offset); } static void irqd_to_aspeed_sgpio_data(struct irq_data *d, @@ -402,6 +444,7 @@ static int aspeed_sgpio_setup_irqs(struct aspeed_sgpio *gpio, irq = &gpio->chip.irq; irq->chip = &aspeed_sgpio_irqchip; + irq->init_valid_mask = aspeed_sgpio_irq_init_valid_mask; irq->handler = handle_bad_irq; irq->default_type = IRQ_TYPE_NONE; irq->parent_handler = aspeed_sgpio_irq_handler; @@ -409,17 +452,15 @@ static int aspeed_sgpio_setup_irqs(struct aspeed_sgpio *gpio, irq->parents = &gpio->irq; irq->num_parents = 1; - /* set IRQ settings and Enable Interrupt */ + /* Apply default IRQ settings */ for (i = 0; i < ARRAY_SIZE(aspeed_sgpio_banks); i++) { bank = &aspeed_sgpio_banks[i]; /* set falling or level-low irq */ iowrite32(0x00000000, bank_reg(gpio, bank, reg_irq_type0)); /* trigger type is edge */ iowrite32(0x00000000, bank_reg(gpio, bank, reg_irq_type1)); - /* dual edge trigger mode. */ - iowrite32(0xffffffff, bank_reg(gpio, bank, reg_irq_type2)); - /* enable irq */ - iowrite32(0xffffffff, bank_reg(gpio, bank, reg_irq_enable)); + /* single edge trigger */ + iowrite32(0x00000000, bank_reg(gpio, bank, reg_irq_type2)); } return 0; @@ -452,11 +493,12 @@ static int __init aspeed_sgpio_probe(struct platform_device *pdev) if (rc < 0) { dev_err(&pdev->dev, "Could not read ngpios property\n"); return -EINVAL; - } else if (nr_gpios > MAX_NR_SGPIO) { + } else if (nr_gpios > MAX_NR_HW_SGPIO) { dev_err(&pdev->dev, "Number of GPIOs exceeds the maximum of %d: %d\n", - MAX_NR_SGPIO, nr_gpios); + MAX_NR_HW_SGPIO, nr_gpios); return -EINVAL; } + gpio->n_sgpio = nr_gpios; rc = of_property_read_u32(pdev->dev.of_node, "bus-frequency", &sgpio_freq); if (rc < 0) { @@ -497,7 +539,8 @@ static int __init aspeed_sgpio_probe(struct platform_device *pdev) spin_lock_init(&gpio->lock); gpio->chip.parent = &pdev->dev; - gpio->chip.ngpio = nr_gpios; + gpio->chip.ngpio = MAX_NR_HW_SGPIO * 2; + gpio->chip.init_valid_mask = aspeed_sgpio_init_valid_mask; gpio->chip.direction_input = aspeed_sgpio_dir_in; gpio->chip.direction_output = aspeed_sgpio_dir_out; gpio->chip.get_direction = aspeed_sgpio_get_direction; @@ -509,9 +552,6 @@ static int __init aspeed_sgpio_probe(struct platform_device *pdev) gpio->chip.label = dev_name(&pdev->dev); gpio->chip.base = -1; - /* set all SGPIO pins as input (1). */ - memset(gpio->dir_in, 0xff, sizeof(gpio->dir_in)); - aspeed_sgpio_setup_irqs(gpio, pdev); rc = devm_gpiochip_add_data(&pdev->dev, &gpio->chip, gpio); diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index bf08b4561f36..e44d5de2a120 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -1114,8 +1114,8 @@ static const struct aspeed_gpio_config ast2500_config = static const struct aspeed_bank_props ast2600_bank_props[] = { /* input output */ - {5, 0xffffffff, 0x0000ffff}, /* U/V/W/X */ - {6, 0xffff0000, 0x0fff0000}, /* Y/Z */ + {5, 0xffffffff, 0xffffff00}, /* U/V/W/X */ + {6, 0x0000ffff, 0x0000ffff}, /* Y/Z */ { }, }; diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index bc345185db26..1652897fdf90 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -552,6 +552,7 @@ static int __init gpio_mockup_init(void) err = platform_driver_register(&gpio_mockup_driver); if (err) { gpio_mockup_err("error registering platform driver\n"); + debugfs_remove_recursive(gpio_mockup_dbg_dir); return err; } @@ -582,6 +583,7 @@ static int __init gpio_mockup_init(void) gpio_mockup_err("error registering device"); platform_driver_unregister(&gpio_mockup_driver); gpio_mockup_unregister_pdevs(); + debugfs_remove_recursive(gpio_mockup_dbg_dir); return PTR_ERR(pdev); } diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 7fbe0c9e1fc1..0ea640fb636c 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -1516,7 +1516,7 @@ static int __maybe_unused omap_gpio_runtime_resume(struct device *dev) return 0; } -static int omap_gpio_suspend(struct device *dev) +static int __maybe_unused omap_gpio_suspend(struct device *dev) { struct gpio_bank *bank = dev_get_drvdata(dev); @@ -1528,7 +1528,7 @@ static int omap_gpio_suspend(struct device *dev) return omap_gpio_runtime_suspend(dev); } -static int omap_gpio_resume(struct device *dev) +static int __maybe_unused omap_gpio_resume(struct device *dev) { struct gpio_bank *bank = dev_get_drvdata(dev); diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index bd2e96c34f82..c2d6121c48c9 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -818,12 +818,27 @@ static irqreturn_t pca953x_irq_handler(int irq, void *devid) int level; bool ret; + bitmap_zero(pending, MAX_LINE); + mutex_lock(&chip->i2c_lock); ret = pca953x_irq_pending(chip, pending); mutex_unlock(&chip->i2c_lock); - for_each_set_bit(level, pending, gc->ngpio) - handle_nested_irq(irq_find_mapping(gc->irq.domain, level)); + if (ret) { + ret = 0; + + for_each_set_bit(level, pending, gc->ngpio) { + int nested_irq = irq_find_mapping(gc->irq.domain, level); + + if (unlikely(nested_irq <= 0)) { + dev_warn_ratelimited(gc->parent, "unmapped interrupt %d\n", level); + continue; + } + + handle_nested_irq(nested_irq); + ret = 1; + } + } return IRQ_RETVAL(ret); } @@ -940,6 +955,7 @@ out: static int device_pca957x_init(struct pca953x_chip *chip, u32 invert) { DECLARE_BITMAP(val, MAX_LINE); + unsigned int i; int ret; ret = device_pca95xx_init(chip, invert); @@ -947,7 +963,9 @@ static int device_pca957x_init(struct pca953x_chip *chip, u32 invert) goto out; /* To enable register 6, 7 to control pull up and pull down */ - memset(val, 0x02, NBANK(chip)); + for (i = 0; i < NBANK(chip); i++) + bitmap_set_value8(val, 0x02, i * BANK_SZ); + ret = pca953x_write_regs(chip, PCA957X_BKEN, val); if (ret) goto out; diff --git a/drivers/gpio/gpio-siox.c b/drivers/gpio/gpio-siox.c index 26e1fe092304..f8c5e9fc4bac 100644 --- a/drivers/gpio/gpio-siox.c +++ b/drivers/gpio/gpio-siox.c @@ -245,6 +245,7 @@ static int gpio_siox_probe(struct siox_device *sdevice) girq->chip = &ddata->ichip; girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_level_irq; + girq->threaded = true; ret = devm_gpiochip_add_data(dev, &ddata->gchip, NULL); if (ret) diff --git a/drivers/gpio/gpio-sprd.c b/drivers/gpio/gpio-sprd.c index d7314d39ab65..36ea8a3bd451 100644 --- a/drivers/gpio/gpio-sprd.c +++ b/drivers/gpio/gpio-sprd.c @@ -149,17 +149,20 @@ static int sprd_gpio_irq_set_type(struct irq_data *data, sprd_gpio_update(chip, offset, SPRD_GPIO_IS, 0); sprd_gpio_update(chip, offset, SPRD_GPIO_IBE, 0); sprd_gpio_update(chip, offset, SPRD_GPIO_IEV, 1); + sprd_gpio_update(chip, offset, SPRD_GPIO_IC, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_FALLING: sprd_gpio_update(chip, offset, SPRD_GPIO_IS, 0); sprd_gpio_update(chip, offset, SPRD_GPIO_IBE, 0); sprd_gpio_update(chip, offset, SPRD_GPIO_IEV, 0); + sprd_gpio_update(chip, offset, SPRD_GPIO_IC, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: sprd_gpio_update(chip, offset, SPRD_GPIO_IS, 0); sprd_gpio_update(chip, offset, SPRD_GPIO_IBE, 1); + sprd_gpio_update(chip, offset, SPRD_GPIO_IC, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_LEVEL_HIGH: diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c index 58b0da9eb76f..ea3f68a28fea 100644 --- a/drivers/gpio/gpio-tc3589x.c +++ b/drivers/gpio/gpio-tc3589x.c @@ -212,7 +212,7 @@ static void tc3589x_gpio_irq_sync_unlock(struct irq_data *d) continue; tc3589x_gpio->oldregs[i][j] = new; - tc3589x_reg_write(tc3589x, regmap[i] + j * 8, new); + tc3589x_reg_write(tc3589x, regmap[i] + j, new); } } diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index e6c9b78adfc2..fed5a3b2172f 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -423,6 +423,21 @@ static __poll_t lineevent_poll(struct file *file, return events; } +static ssize_t lineevent_get_size(void) +{ +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) + /* i386 has no padding after 'id' */ + if (in_ia32_syscall()) { + struct compat_gpioeevent_data { + compat_u64 timestamp; + u32 id; + }; + + return sizeof(struct compat_gpioeevent_data); + } +#endif + return sizeof(struct gpioevent_data); +} static ssize_t lineevent_read(struct file *file, char __user *buf, @@ -432,9 +447,20 @@ static ssize_t lineevent_read(struct file *file, struct lineevent_state *le = file->private_data; struct gpioevent_data ge; ssize_t bytes_read = 0; + ssize_t ge_size; int ret; - if (count < sizeof(ge)) + /* + * When compatible system call is being used the struct gpioevent_data, + * in case of at least ia32, has different size due to the alignment + * differences. Because we have first member 64 bits followed by one of + * 32 bits there is no gap between them. The only difference is the + * padding at the end of the data structure. Hence, we calculate the + * actual sizeof() and pass this as an argument to copy_to_user() to + * drop unneeded bytes from the output. + */ + ge_size = lineevent_get_size(); + if (count < ge_size) return -EINVAL; do { @@ -470,10 +496,10 @@ static ssize_t lineevent_read(struct file *file, break; } - if (copy_to_user(buf + bytes_read, &ge, sizeof(ge))) + if (copy_to_user(buf + bytes_read, &ge, ge_size)) return -EFAULT; - bytes_read += sizeof(ge); - } while (count >= bytes_read + sizeof(ge)); + bytes_read += ge_size; + } while (count >= bytes_read + ge_size); return bytes_read; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 84d811b6e48b..c28ebf41530a 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -694,12 +694,12 @@ static void soc15_reg_base_init(struct amdgpu_device *adev) * it doesn't support SRIOV. */ if (amdgpu_discovery) { r = amdgpu_discovery_reg_base_init(adev); - if (r) { - DRM_WARN("failed to init reg base from ip discovery table, " - "fallback to legacy init method\n"); - vega10_reg_base_init(adev); - } + if (r == 0) + break; + DRM_WARN("failed to init reg base from ip discovery table, " + "fallback to legacy init method\n"); } + vega10_reg_base_init(adev); break; case CHIP_VEGA20: vega20_reg_base_init(adev); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 4ba8b54a2695..a717a4904268 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1409,7 +1409,7 @@ static int dm_late_init(void *handle) if (dmcu) ret = dmcu_load_iram(dmcu, params); else if (adev->dm.dc->ctx->dmub_srv) - ret = dmub_init_abm_config(adev->dm.dc->res_pool->abm, params); + ret = dmub_init_abm_config(adev->dm.dc->res_pool, params); if (!ret) return -EINVAL; diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 859724771a75..61497954e67e 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -657,7 +657,7 @@ void fill_iram_v_2_3(struct iram_table_v_2_2 *ram_table, struct dmcu_iram_parame params, ram_table, big_endian); } -bool dmub_init_abm_config(struct abm *abm, +bool dmub_init_abm_config(struct resource_pool *res_pool, struct dmcu_iram_parameters params) { struct iram_table_v_2_2 ram_table; @@ -665,8 +665,13 @@ bool dmub_init_abm_config(struct abm *abm, bool result = false; uint32_t i, j = 0; - if (abm == NULL) +#if defined(CONFIG_DRM_AMD_DC_DCN3_0) + if (res_pool->abm == NULL && res_pool->multiple_abms[0] == NULL) return false; +#else + if (res_pool->abm == NULL) + return false; +#endif memset(&ram_table, 0, sizeof(ram_table)); memset(&config, 0, sizeof(config)); @@ -707,8 +712,14 @@ bool dmub_init_abm_config(struct abm *abm, config.min_abm_backlight = ram_table.min_abm_backlight; - result = abm->funcs->init_abm_config( - abm, (char *)(&config), sizeof(struct abm_config_table)); +#if defined(CONFIG_DRM_AMD_DC_DCN3_0) + if (res_pool->multiple_abms[0]) { + result = res_pool->multiple_abms[0]->funcs->init_abm_config( + res_pool->multiple_abms[0], (char *)(&config), sizeof(struct abm_config_table)); + } else +#endif + result = res_pool->abm->funcs->init_abm_config( + res_pool->abm, (char *)(&config), sizeof(struct abm_config_table)); return result; } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h index 46fbca2e2cd1..fa4728d88092 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h @@ -28,6 +28,8 @@ #include "dc/inc/hw/dmcu.h" #include "dc/inc/hw/abm.h" +struct resource_pool; + enum abm_defines { abm_defines_max_level = 4, @@ -45,7 +47,7 @@ struct dmcu_iram_parameters { bool dmcu_load_iram(struct dmcu *dmcu, struct dmcu_iram_parameters params); -bool dmub_init_abm_config(struct abm *abm, +bool dmub_init_abm_config(struct resource_pool *res_pool, struct dmcu_iram_parameters params); #endif /* MODULES_POWER_POWER_HELPERS_H_ */ diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 3d5eae956a23..b1547a83e721 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -2265,8 +2265,6 @@ static void navi10_fill_i2c_req(SwI2cRequest_t *req, bool write, { int i; - BUG_ON(numbytes > MAX_SW_I2C_COMMANDS); - req->I2CcontrollerPort = 0; req->I2CSpeed = 2; req->SlaveAddress = address; @@ -2304,6 +2302,12 @@ static int navi10_i2c_read_data(struct i2c_adapter *control, struct smu_table_context *smu_table = &adev->smu.smu_table; struct smu_table *table = &smu_table->driver_table; + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); navi10_fill_i2c_req(&req, false, address, numbytes, data); @@ -2340,6 +2344,12 @@ static int navi10_i2c_write_data(struct i2c_adapter *control, SwI2cRequest_t req; struct amdgpu_device *adev = to_amdgpu_device(control); + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); navi10_fill_i2c_req(&req, true, address, numbytes, data); diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c index 61f4ddae262d..ace682fde22f 100644 --- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c @@ -2445,8 +2445,6 @@ static void sienna_cichlid_fill_i2c_req(SwI2cRequest_t *req, bool write, { int i; - BUG_ON(numbytes > MAX_SW_I2C_COMMANDS); - req->I2CcontrollerPort = 0; req->I2CSpeed = 2; req->SlaveAddress = address; @@ -2484,6 +2482,12 @@ static int sienna_cichlid_i2c_read_data(struct i2c_adapter *control, struct smu_table_context *smu_table = &adev->smu.smu_table; struct smu_table *table = &smu_table->driver_table; + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); sienna_cichlid_fill_i2c_req(&req, false, address, numbytes, data); @@ -2520,6 +2524,12 @@ static int sienna_cichlid_i2c_write_data(struct i2c_adapter *control, SwI2cRequest_t req; struct amdgpu_device *adev = to_amdgpu_device(control); + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); sienna_cichlid_fill_i2c_req(&req, true, address, numbytes, data); diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index b1bb542d3115..e5fae57fffbd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -176,6 +176,8 @@ void nouveau_mem_del(struct ttm_mem_reg *reg) { struct nouveau_mem *mem = nouveau_mem(reg); + if (!mem) + return; nouveau_mem_fini(mem); kfree(reg->mm_node); reg->mm_node = NULL; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 9f4ac2672cf2..dcb70677d0ac 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -3149,6 +3149,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func, case 0x168: device->chip = &nv168_chipset; break; default: nvdev_error(device, "unknown chipset (%08x)\n", boot0); + ret = -ENODEV; goto done; } diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c index 1213e1932ccb..24d584a1c9a7 100644 --- a/drivers/i2c/busses/i2c-cpm.c +++ b/drivers/i2c/busses/i2c-cpm.c @@ -65,6 +65,9 @@ struct i2c_ram { char res1[4]; /* Reserved */ ushort rpbase; /* Relocation pointer */ char res2[2]; /* Reserved */ + /* The following elements are only for CPM2 */ + char res3[4]; /* Reserved */ + uint sdmatmp; /* Internal */ }; #define I2COM_START 0x80 diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index ebb4c0b03057..bffca729e1c7 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1917,6 +1917,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) pci_set_drvdata(dev, priv); + dev_pm_set_driver_flags(&dev->dev, DPM_FLAG_NO_DIRECT_COMPLETE); pm_runtime_set_autosuspend_delay(&dev->dev, 1000); pm_runtime_use_autosuspend(&dev->dev); pm_runtime_put_autosuspend(&dev->dev); diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c index c5dec572fc48..ef73a42577cc 100644 --- a/drivers/i2c/busses/i2c-meson.c +++ b/drivers/i2c/busses/i2c-meson.c @@ -5,6 +5,7 @@ * Copyright (C) 2014 Beniamino Galvani <[email protected]> */ +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/completion.h> #include <linux/i2c.h> @@ -33,12 +34,17 @@ #define REG_CTRL_ACK_IGNORE BIT(1) #define REG_CTRL_STATUS BIT(2) #define REG_CTRL_ERROR BIT(3) -#define REG_CTRL_CLKDIV_SHIFT 12 -#define REG_CTRL_CLKDIV_MASK GENMASK(21, 12) -#define REG_CTRL_CLKDIVEXT_SHIFT 28 -#define REG_CTRL_CLKDIVEXT_MASK GENMASK(29, 28) +#define REG_CTRL_CLKDIV GENMASK(21, 12) +#define REG_CTRL_CLKDIVEXT GENMASK(29, 28) + +#define REG_SLV_ADDR GENMASK(7, 0) +#define REG_SLV_SDA_FILTER GENMASK(10, 8) +#define REG_SLV_SCL_FILTER GENMASK(13, 11) +#define REG_SLV_SCL_LOW GENMASK(27, 16) +#define REG_SLV_SCL_LOW_EN BIT(28) #define I2C_TIMEOUT_MS 500 +#define FILTER_DELAY 15 enum { TOKEN_END = 0, @@ -133,19 +139,24 @@ static void meson_i2c_set_clk_div(struct meson_i2c *i2c, unsigned int freq) unsigned long clk_rate = clk_get_rate(i2c->clk); unsigned int div; - div = DIV_ROUND_UP(clk_rate, freq * i2c->data->div_factor); + div = DIV_ROUND_UP(clk_rate, freq); + div -= FILTER_DELAY; + div = DIV_ROUND_UP(div, i2c->data->div_factor); /* clock divider has 12 bits */ - if (div >= (1 << 12)) { + if (div > GENMASK(11, 0)) { dev_err(i2c->dev, "requested bus frequency too low\n"); - div = (1 << 12) - 1; + div = GENMASK(11, 0); } - meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIV_MASK, - (div & GENMASK(9, 0)) << REG_CTRL_CLKDIV_SHIFT); + meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIV, + FIELD_PREP(REG_CTRL_CLKDIV, div & GENMASK(9, 0))); + + meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIVEXT, + FIELD_PREP(REG_CTRL_CLKDIVEXT, div >> 10)); - meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIVEXT_MASK, - (div >> 10) << REG_CTRL_CLKDIVEXT_SHIFT); + /* Disable HIGH/LOW mode */ + meson_i2c_set_mask(i2c, REG_SLAVE_ADDR, REG_SLV_SCL_LOW_EN, 0); dev_dbg(i2c->dev, "%s: clk %lu, freq %u, div %u\n", __func__, clk_rate, freq, div); @@ -280,7 +291,10 @@ static void meson_i2c_do_start(struct meson_i2c *i2c, struct i2c_msg *msg) token = (msg->flags & I2C_M_RD) ? TOKEN_SLAVE_ADDR_READ : TOKEN_SLAVE_ADDR_WRITE; - writel(msg->addr << 1, i2c->regs + REG_SLAVE_ADDR); + + meson_i2c_set_mask(i2c, REG_SLAVE_ADDR, REG_SLV_ADDR, + FIELD_PREP(REG_SLV_ADDR, msg->addr << 1)); + meson_i2c_add_token(i2c, TOKEN_START); meson_i2c_add_token(i2c, token); } @@ -357,16 +371,12 @@ static int meson_i2c_xfer_messages(struct i2c_adapter *adap, struct meson_i2c *i2c = adap->algo_data; int i, ret = 0; - clk_enable(i2c->clk); - for (i = 0; i < num; i++) { ret = meson_i2c_xfer_msg(i2c, msgs + i, i == num - 1, atomic); if (ret) break; } - clk_disable(i2c->clk); - return ret ?: i; } @@ -435,7 +445,7 @@ static int meson_i2c_probe(struct platform_device *pdev) return ret; } - ret = clk_prepare(i2c->clk); + ret = clk_prepare_enable(i2c->clk); if (ret < 0) { dev_err(&pdev->dev, "can't prepare clock\n"); return ret; @@ -457,10 +467,14 @@ static int meson_i2c_probe(struct platform_device *pdev) ret = i2c_add_adapter(&i2c->adap); if (ret < 0) { - clk_unprepare(i2c->clk); + clk_disable_unprepare(i2c->clk); return ret; } + /* Disable filtering */ + meson_i2c_set_mask(i2c, REG_SLAVE_ADDR, + REG_SLV_SDA_FILTER | REG_SLV_SCL_FILTER, 0); + meson_i2c_set_clk_div(i2c, timings.bus_freq_hz); return 0; @@ -471,7 +485,7 @@ static int meson_i2c_remove(struct platform_device *pdev) struct meson_i2c *i2c = platform_get_drvdata(pdev); i2c_del_adapter(&i2c->adap); - clk_unprepare(i2c->clk); + clk_disable_unprepare(i2c->clk); return 0; } diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c index dfcf04e1967f..2ad166355ec9 100644 --- a/drivers/i2c/busses/i2c-npcm7xx.c +++ b/drivers/i2c/busses/i2c-npcm7xx.c @@ -2163,6 +2163,15 @@ static int npcm_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, if (bus->cmd_err == -EAGAIN) ret = i2c_recover_bus(adap); + /* + * After any type of error, check if LAST bit is still set, + * due to a HW issue. + * It cannot be cleared without resetting the module. + */ + if (bus->cmd_err && + (NPCM_I2CRXF_CTL_LAST_PEC & ioread8(bus->reg + NPCM_I2CRXF_CTL))) + npcm_i2c_reset(bus); + #if IS_ENABLED(CONFIG_I2C_SLAVE) /* reenable slave if it was enabled */ if (bus->slave) diff --git a/drivers/i2c/busses/i2c-owl.c b/drivers/i2c/busses/i2c-owl.c index 672f1f239bd6..a163b8f308c1 100644 --- a/drivers/i2c/busses/i2c-owl.c +++ b/drivers/i2c/busses/i2c-owl.c @@ -176,6 +176,9 @@ static irqreturn_t owl_i2c_interrupt(int irq, void *_dev) fifostat = readl(i2c_dev->base + OWL_I2C_REG_FIFOSTAT); if (fifostat & OWL_I2C_FIFOSTAT_RNB) { i2c_dev->err = -ENXIO; + /* Clear NACK error bit by writing "1" */ + owl_i2c_update_reg(i2c_dev->base + OWL_I2C_REG_FIFOSTAT, + OWL_I2C_FIFOSTAT_RNB, true); goto stop; } @@ -183,6 +186,9 @@ static irqreturn_t owl_i2c_interrupt(int irq, void *_dev) stat = readl(i2c_dev->base + OWL_I2C_REG_STAT); if (stat & OWL_I2C_STAT_BEB) { i2c_dev->err = -EIO; + /* Clear BUS error bit by writing "1" */ + owl_i2c_update_reg(i2c_dev->base + OWL_I2C_REG_STAT, + OWL_I2C_STAT_BEB, true); goto stop; } diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index 8dce06e9e69c..766c73333604 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -177,12 +177,12 @@ static const struct iio_chan_spec ad7124_channel_template = { static struct ad7124_chip_info ad7124_chip_info_tbl[] = { [ID_AD7124_4] = { - .name = "ad7127-4", + .name = "ad7124-4", .chip_id = CHIPID_AD7124_4, .num_inputs = 8, }, [ID_AD7124_8] = { - .name = "ad7127-8", + .name = "ad7124-8", .chip_id = CHIPID_AD7124_8, .num_inputs = 16, }, diff --git a/drivers/iio/adc/qcom-spmi-adc5.c b/drivers/iio/adc/qcom-spmi-adc5.c index b4b73c9920b4..c10aa28be70a 100644 --- a/drivers/iio/adc/qcom-spmi-adc5.c +++ b/drivers/iio/adc/qcom-spmi-adc5.c @@ -982,7 +982,7 @@ static int adc5_probe(struct platform_device *pdev) static struct platform_driver adc5_driver = { .driver = { - .name = "qcom-spmi-adc5.c", + .name = "qcom-spmi-adc5", .of_match_table = adc5_match_table, }, .probe = adc5_probe, diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index ffad73bb40ff..5a76611e684a 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -1320,9 +1320,10 @@ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr) } EXPORT_SYMBOL(rdma_read_gid_attr_ndev_rcu); -static int get_lower_dev_vlan(struct net_device *lower_dev, void *data) +static int get_lower_dev_vlan(struct net_device *lower_dev, + struct netdev_nested_priv *priv) { - u16 *vlan_id = data; + u16 *vlan_id = (u16 *)priv->data; if (is_vlan_dev(lower_dev)) *vlan_id = vlan_dev_vlan_id(lower_dev); @@ -1348,6 +1349,9 @@ static int get_lower_dev_vlan(struct net_device *lower_dev, void *data) int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr, u16 *vlan_id, u8 *smac) { + struct netdev_nested_priv priv = { + .data = (void *)vlan_id, + }; struct net_device *ndev; rcu_read_lock(); @@ -1368,7 +1372,7 @@ int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr, * the lower vlan device for this gid entry. */ netdev_walk_all_lower_dev_rcu(attr->ndev, - get_lower_dev_vlan, vlan_id); + get_lower_dev_vlan, &priv); } } rcu_read_unlock(); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 7f0e91e92968..5888311b2119 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2865,9 +2865,10 @@ struct iboe_prio_tc_map { bool found; }; -static int get_lower_vlan_dev_tc(struct net_device *dev, void *data) +static int get_lower_vlan_dev_tc(struct net_device *dev, + struct netdev_nested_priv *priv) { - struct iboe_prio_tc_map *map = data; + struct iboe_prio_tc_map *map = (struct iboe_prio_tc_map *)priv->data; if (is_vlan_dev(dev)) map->output_tc = get_vlan_ndev_tc(dev, map->input_prio); @@ -2886,16 +2887,18 @@ static int iboe_tos_to_sl(struct net_device *ndev, int tos) { struct iboe_prio_tc_map prio_tc_map = {}; int prio = rt_tos2priority(tos); + struct netdev_nested_priv priv; /* If VLAN device, get it directly from the VLAN netdev */ if (is_vlan_dev(ndev)) return get_vlan_ndev_tc(ndev, prio); prio_tc_map.input_prio = prio; + priv.data = (void *)&prio_tc_map; rcu_read_lock(); netdev_walk_all_lower_dev_rcu(ndev, get_lower_vlan_dev_tc, - &prio_tc_map); + &priv); rcu_read_unlock(); /* If map is found from lower device, use it; Otherwise * continue with the current netdevice to get priority to tc map. diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c index 2860def84f4d..6b8364bb032d 100644 --- a/drivers/infiniband/core/roce_gid_mgmt.c +++ b/drivers/infiniband/core/roce_gid_mgmt.c @@ -531,10 +531,11 @@ struct upper_list { struct net_device *upper; }; -static int netdev_upper_walk(struct net_device *upper, void *data) +static int netdev_upper_walk(struct net_device *upper, + struct netdev_nested_priv *priv) { struct upper_list *entry = kmalloc(sizeof(*entry), GFP_ATOMIC); - struct list_head *upper_list = data; + struct list_head *upper_list = (struct list_head *)priv->data; if (!entry) return 0; @@ -553,12 +554,14 @@ static void handle_netdev_upper(struct ib_device *ib_dev, u8 port, struct net_device *ndev)) { struct net_device *ndev = cookie; + struct netdev_nested_priv priv; struct upper_list *upper_iter; struct upper_list *upper_temp; LIST_HEAD(upper_list); + priv.data = &upper_list; rcu_read_lock(); - netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &upper_list); + netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &priv); rcu_read_unlock(); handle_netdev(ib_dev, port, ndev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index ab75b7f745d4..f772fe8c5b66 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -342,9 +342,10 @@ struct ipoib_walk_data { struct net_device *result; }; -static int ipoib_upper_walk(struct net_device *upper, void *_data) +static int ipoib_upper_walk(struct net_device *upper, + struct netdev_nested_priv *priv) { - struct ipoib_walk_data *data = _data; + struct ipoib_walk_data *data = (struct ipoib_walk_data *)priv->data; int ret = 0; if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) { @@ -368,10 +369,12 @@ static int ipoib_upper_walk(struct net_device *upper, void *_data) static struct net_device *ipoib_get_net_dev_match_addr( const struct sockaddr *addr, struct net_device *dev) { + struct netdev_nested_priv priv; struct ipoib_walk_data data = { .addr = addr, }; + priv.data = (void *)&data; rcu_read_lock(); if (ipoib_is_dev_match_addr_rcu(addr, dev)) { dev_hold(dev); @@ -379,7 +382,7 @@ static struct net_device *ipoib_get_net_dev_match_addr( goto out; } - netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &data); + netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &priv); out: rcu_read_unlock(); return data.result; diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c index 854d5e758724..ef2fa0905208 100644 --- a/drivers/input/mouse/trackpoint.c +++ b/drivers/input/mouse/trackpoint.c @@ -282,6 +282,8 @@ static int trackpoint_start_protocol(struct psmouse *psmouse, case TP_VARIANT_ALPS: case TP_VARIANT_ELAN: case TP_VARIANT_NXP: + case TP_VARIANT_JYT_SYNAPTICS: + case TP_VARIANT_SYNAPTICS: if (variant_id) *variant_id = param[0]; if (firmware_id) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 37fb9aa88f9c..a4c9b9652560 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -721,6 +721,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nopnp_table[] = { DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), }, }, + { + /* Acer Aspire 5 A515 */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "Grumpy_PK"), + DMI_MATCH(DMI_BOARD_VENDOR, "PK"), + }, + }, { } }; diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 445a08d23fed..1ba6b4cc56e8 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1104,25 +1104,6 @@ static int __init add_early_maps(void) } /* - * Reads the device exclusion range from ACPI and initializes the IOMMU with - * it - */ -static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m) -{ - if (!(m->flags & IVMD_FLAG_EXCL_RANGE)) - return; - - /* - * Treat per-device exclusion ranges as r/w unity-mapped regions - * since some buggy BIOSes might lead to the overwritten exclusion - * range (exclusion_start and exclusion_length members). This - * happens when there are multiple exclusion ranges (IVMD entries) - * defined in ACPI table. - */ - m->flags = (IVMD_FLAG_IW | IVMD_FLAG_IR | IVMD_FLAG_UNITY_MAP); -} - -/* * Takes a pointer to an AMD IOMMU entry in the ACPI table and * initializes the hardware and our data structures with it. */ @@ -2073,30 +2054,6 @@ static void __init free_unity_maps(void) } } -/* called when we find an exclusion range definition in ACPI */ -static int __init init_exclusion_range(struct ivmd_header *m) -{ - int i; - - switch (m->type) { - case ACPI_IVMD_TYPE: - set_device_exclusion_range(m->devid, m); - break; - case ACPI_IVMD_TYPE_ALL: - for (i = 0; i <= amd_iommu_last_bdf; ++i) - set_device_exclusion_range(i, m); - break; - case ACPI_IVMD_TYPE_RANGE: - for (i = m->devid; i <= m->aux; ++i) - set_device_exclusion_range(i, m); - break; - default: - break; - } - - return 0; -} - /* called for unity map ACPI definition */ static int __init init_unity_map_range(struct ivmd_header *m) { @@ -2107,9 +2064,6 @@ static int __init init_unity_map_range(struct ivmd_header *m) if (e == NULL) return -ENOMEM; - if (m->flags & IVMD_FLAG_EXCL_RANGE) - init_exclusion_range(m); - switch (m->type) { default: kfree(e); @@ -2133,6 +2087,16 @@ static int __init init_unity_map_range(struct ivmd_header *m) e->address_end = e->address_start + PAGE_ALIGN(m->range_length); e->prot = m->flags >> 1; + /* + * Treat per-device exclusion ranges as r/w unity-mapped regions + * since some buggy BIOSes might lead to the overwritten exclusion + * range (exclusion_start and exclusion_length members). This + * happens when there are multiple exclusion ranges (IVMD entries) + * defined in ACPI table. + */ + if (m->flags & IVMD_FLAG_EXCL_RANGE) + e->prot = (IVMD_FLAG_IW | IVMD_FLAG_IR) >> 1; + DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x" " range_start: %016llx range_end: %016llx flags: %x\n", s, PCI_BUS_NUM(e->devid_start), PCI_SLOT(e->devid_start), diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index bad3c0ce10cb..de324b4eedfe 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1295,13 +1295,17 @@ static int exynos_iommu_of_xlate(struct device *dev, return -ENODEV; data = platform_get_drvdata(sysmmu); - if (!data) + if (!data) { + put_device(&sysmmu->dev); return -ENODEV; + } if (!owner) { owner = kzalloc(sizeof(*owner), GFP_KERNEL); - if (!owner) + if (!owner) { + put_device(&sysmmu->dev); return -ENOMEM; + } INIT_LIST_HEAD(&owner->controllers); mutex_init(&owner->rpm_lock); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 87b17bac04c2..2239c211178b 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2664,7 +2664,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, } /* Setup the PASID entry for requests without PASID: */ - spin_lock(&iommu->lock); + spin_lock_irqsave(&iommu->lock, flags); if (hw_pass_through && domain_type_is_si(domain)) ret = intel_pasid_setup_pass_through(iommu, domain, dev, PASID_RID2PASID); @@ -2674,7 +2674,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, else ret = intel_pasid_setup_second_level(iommu, domain, dev, PASID_RID2PASID); - spin_unlock(&iommu->lock); + spin_unlock_irqrestore(&iommu->lock, flags); if (ret) { dev_err(dev, "Setup RID2PASID failed\n"); dmar_remove_one_dev_info(dev); diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index 693ee73eb291..ef03d6fafc5c 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -441,6 +441,9 @@ static void memstick_check(struct work_struct *work) } else if (host->card->stop) host->card->stop(host->card); + if (host->removing) + goto out_power_off; + card = memstick_alloc_card(host); if (!card) { @@ -545,6 +548,7 @@ EXPORT_SYMBOL(memstick_add_host); */ void memstick_remove_host(struct memstick_host *host) { + host->removing = 1; flush_workqueue(workqueue); mutex_lock(&host->lock); if (host->card) diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 6c022ef0f84d..350d0cc4ee62 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -190,7 +190,7 @@ static void mmc_queue_setup_discard(struct request_queue *q, q->limits.discard_granularity = card->pref_erase << 9; /* granularity must not be greater than max. discard */ if (card->pref_erase > max_discard) - q->limits.discard_granularity = 0; + q->limits.discard_granularity = SECTOR_SIZE; if (mmc_can_secure_erase_trim(card)) blk_queue_flag_set(QUEUE_FLAG_SECERASE, q); } diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index af413805bbf1..914f5184295f 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -794,7 +794,8 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot) static bool glk_broken_cqhci(struct sdhci_pci_slot *slot) { return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_GLK_EMMC && - dmi_match(DMI_BIOS_VENDOR, "LENOVO"); + (dmi_match(DMI_BIOS_VENDOR, "LENOVO") || + dmi_match(DMI_SYS_VENDOR, "IRBIS")); } static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 4e1b7deb724b..c3091e00dd5f 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -942,9 +942,10 @@ struct alb_walk_data { bool strict_match; }; -static int alb_upper_dev_walk(struct net_device *upper, void *_data) +static int alb_upper_dev_walk(struct net_device *upper, + struct netdev_nested_priv *priv) { - struct alb_walk_data *data = _data; + struct alb_walk_data *data = (struct alb_walk_data *)priv->data; bool strict_match = data->strict_match; struct bonding *bond = data->bond; struct slave *slave = data->slave; @@ -983,6 +984,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], bool strict_match) { struct bonding *bond = bond_get_bond_by_slave(slave); + struct netdev_nested_priv priv; struct alb_walk_data data = { .strict_match = strict_match, .mac_addr = mac_addr, @@ -990,6 +992,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], .bond = bond, }; + priv.data = (void *)&data; /* send untagged */ alb_send_lp_vid(slave, mac_addr, 0, 0); @@ -997,7 +1000,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], * for that device. */ rcu_read_lock(); - netdev_walk_all_upper_dev_rcu(bond->dev, alb_upper_dev_walk, &data); + netdev_walk_all_upper_dev_rcu(bond->dev, alb_upper_dev_walk, &priv); rcu_read_unlock(); } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 42ef25ec0af5..84ecbc6fa0ff 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1315,6 +1315,7 @@ static void bond_setup_by_slave(struct net_device *bond_dev, bond_dev->type = slave_dev->type; bond_dev->hard_header_len = slave_dev->hard_header_len; + bond_dev->needed_headroom = slave_dev->needed_headroom; bond_dev->addr_len = slave_dev->addr_len; memcpy(bond_dev->broadcast, slave_dev->broadcast, @@ -2510,22 +2511,26 @@ re_arm: } } -static int bond_upper_dev_walk(struct net_device *upper, void *data) +static int bond_upper_dev_walk(struct net_device *upper, + struct netdev_nested_priv *priv) { - __be32 ip = *((__be32 *)data); + __be32 ip = *(__be32 *)priv->data; return ip == bond_confirm_addr(upper, 0, ip); } static bool bond_has_this_ip(struct bonding *bond, __be32 ip) { + struct netdev_nested_priv priv = { + .data = (void *)&ip, + }; bool ret = false; if (ip == bond_confirm_addr(bond->dev, 0, ip)) return true; rcu_read_lock(); - if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &ip)) + if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &priv)) ret = true; rcu_read_unlock(); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 8e755b50c9c1..c796d42730ba 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -387,8 +387,8 @@ EXPORT_SYMBOL(ksz_switch_alloc); int ksz_switch_register(struct ksz_device *dev, const struct ksz_dev_ops *ops) { + struct device_node *port, *ports; phy_interface_t interface; - struct device_node *port; unsigned int port_num; int ret; @@ -429,13 +429,17 @@ int ksz_switch_register(struct ksz_device *dev, ret = of_get_phy_mode(dev->dev->of_node, &interface); if (ret == 0) dev->compat_interface = interface; - for_each_available_child_of_node(dev->dev->of_node, port) { - if (of_property_read_u32(port, "reg", &port_num)) - continue; - if (port_num >= dev->port_cnt) - return -EINVAL; - of_get_phy_mode(port, &dev->ports[port_num].interface); - } + ports = of_get_child_by_name(dev->dev->of_node, "ports"); + if (ports) + for_each_available_child_of_node(ports, port) { + if (of_property_read_u32(port, "reg", + &port_num)) + continue; + if (port_num >= dev->port_cnt) + return -EINVAL; + of_get_phy_mode(port, + &dev->ports[port_num].interface); + } dev->synclko_125 = of_property_read_bool(dev->dev->of_node, "microchip,synclko-125"); } diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 6855c94256f8..3a9637496407 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -685,12 +685,12 @@ static struct vcap_field vsc9959_vcap_is2_actions[] = { [VCAP_IS2_ACT_POLICE_ENA] = { 9, 1}, [VCAP_IS2_ACT_POLICE_IDX] = { 10, 9}, [VCAP_IS2_ACT_POLICE_VCAP_ONLY] = { 19, 1}, - [VCAP_IS2_ACT_PORT_MASK] = { 20, 11}, - [VCAP_IS2_ACT_REW_OP] = { 31, 9}, - [VCAP_IS2_ACT_SMAC_REPLACE_ENA] = { 40, 1}, - [VCAP_IS2_ACT_RSV] = { 41, 2}, - [VCAP_IS2_ACT_ACL_ID] = { 43, 6}, - [VCAP_IS2_ACT_HIT_CNT] = { 49, 32}, + [VCAP_IS2_ACT_PORT_MASK] = { 20, 6}, + [VCAP_IS2_ACT_REW_OP] = { 26, 9}, + [VCAP_IS2_ACT_SMAC_REPLACE_ENA] = { 35, 1}, + [VCAP_IS2_ACT_RSV] = { 36, 2}, + [VCAP_IS2_ACT_ACL_ID] = { 38, 6}, + [VCAP_IS2_ACT_HIT_CNT] = { 44, 32}, }; static const struct vcap_props vsc9959_vcap_props[] = { @@ -1171,6 +1171,8 @@ static int vsc9959_prevalidate_phy_mode(struct ocelot *ocelot, int port, */ static u16 vsc9959_wm_enc(u16 value) { + WARN_ON(value >= 16 * BIT(8)); + if (value >= BIT(8)) return BIT(8) | (value / 16); @@ -1284,8 +1286,28 @@ void vsc9959_mdio_bus_free(struct ocelot *ocelot) static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port, u32 speed) { + u8 tas_speed; + + switch (speed) { + case SPEED_10: + tas_speed = OCELOT_SPEED_10; + break; + case SPEED_100: + tas_speed = OCELOT_SPEED_100; + break; + case SPEED_1000: + tas_speed = OCELOT_SPEED_1000; + break; + case SPEED_2500: + tas_speed = OCELOT_SPEED_2500; + break; + default: + tas_speed = OCELOT_SPEED_1000; + break; + } + ocelot_rmw_rix(ocelot, - QSYS_TAG_CONFIG_LINK_SPEED(speed), + QSYS_TAG_CONFIG_LINK_SPEED(tas_speed), QSYS_TAG_CONFIG_LINK_SPEED_M, QSYS_TAG_CONFIG, port); } diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 29df0797ecf5..9e9fd19e1d00 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -706,7 +706,7 @@ static const struct vcap_props vsc9953_vcap_props[] = { .action_type_width = 1, .action_table = { [IS2_ACTION_TYPE_NORMAL] = { - .width = 44, + .width = 50, /* HIT_CNT not included */ .count = 2 }, [IS2_ACTION_TYPE_SMAC_SIP] = { @@ -911,6 +911,8 @@ static int vsc9953_prevalidate_phy_mode(struct ocelot *ocelot, int port, */ static u16 vsc9953_wm_enc(u16 value) { + WARN_ON(value >= 16 * BIT(9)); + if (value >= BIT(9)) return BIT(9) | (value / 16); diff --git a/drivers/net/ethernet/3com/typhoon.h b/drivers/net/ethernet/3com/typhoon.h index 2f634c64d5d1..38e6dcab4e94 100644 --- a/drivers/net/ethernet/3com/typhoon.h +++ b/drivers/net/ethernet/3com/typhoon.h @@ -33,7 +33,7 @@ struct basic_ring { u32 lastWrite; }; -/* The Typoon transmit ring -- same as a basic ring, plus: +/* The Typhoon transmit ring -- same as a basic ring, plus: * lastRead: where we're at in regard to cleaning up the ring * writeRegister: register to use for writing (different for Hi & Lo rings) */ diff --git a/drivers/net/ethernet/aquantia/atlantic/Makefile b/drivers/net/ethernet/aquantia/atlantic/Makefile index 130a105d03f3..8ebcc68e807f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/Makefile +++ b/drivers/net/ethernet/aquantia/atlantic/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_AQTION) += atlantic.o -ccflags-y += -I$(src) +ccflags-y += -I$(srctree)/$(src) atlantic-objs := aq_main.o \ aq_nic.o \ @@ -33,4 +33,4 @@ atlantic-objs := aq_main.o \ atlantic-$(CONFIG_MACSEC) += aq_macsec.o -atlantic-$(CONFIG_PTP_1588_CLOCK) += aq_ptp.o
\ No newline at end of file +atlantic-$(CONFIG_PTP_1588_CLOCK) += aq_ptp.o diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h index bfc0e45d4a2b..5caa75b41b73 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h @@ -284,12 +284,12 @@ #define CCM_REG_GR_ARB_TYPE 0xd015c /* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed; that the Store channel priority is - the compliment to 4 of the rest priorities - Aggregation channel; Load + the complement to 4 of the rest priorities - Aggregation channel; Load (FIC0) channel and Load (FIC1). */ #define CCM_REG_GR_LD0_PR 0xd0164 /* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed; that the Store channel priority is - the compliment to 4 of the rest priorities - Aggregation channel; Load + the complement to 4 of the rest priorities - Aggregation channel; Load (FIC0) channel and Load (FIC1). */ #define CCM_REG_GR_LD1_PR 0xd0168 /* [RW 2] General flags index. */ @@ -4489,11 +4489,11 @@ #define TCM_REG_GR_ARB_TYPE 0x50114 /* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Store channel is the - compliment of the other 3 groups. */ + complement of the other 3 groups. */ #define TCM_REG_GR_LD0_PR 0x5011c /* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Store channel is the - compliment of the other 3 groups. */ + complement of the other 3 groups. */ #define TCM_REG_GR_LD1_PR 0x50120 /* [RW 4] The number of double REG-pairs; loaded from the STORM context and sent to STORM; for a specific connection type. The double REG-pairs are @@ -5020,11 +5020,11 @@ #define UCM_REG_GR_ARB_TYPE 0xe0144 /* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Store channel group is - compliment to the others. */ + complement to the others. */ #define UCM_REG_GR_LD0_PR 0xe014c /* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Store channel group is - compliment to the others. */ + complement to the others. */ #define UCM_REG_GR_LD1_PR 0xe0150 /* [RW 2] The queue index for invalidate counter flag decision. */ #define UCM_REG_INV_CFLG_Q 0xe00e4 @@ -5523,11 +5523,11 @@ #define XCM_REG_GR_ARB_TYPE 0x2020c /* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Channel group is the - compliment of the other 3 groups. */ + complement of the other 3 groups. */ #define XCM_REG_GR_LD0_PR 0x20214 /* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Channel group is the - compliment of the other 3 groups. */ + complement of the other 3 groups. */ #define XCM_REG_GR_LD1_PR 0x20218 /* [RW 1] Input nig0 Interface enable. If 0 - the valid input is disregarded; acknowledge output is deasserted; all other signals are diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 3e17ce0d2314..6cb2162a75d4 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -1219,7 +1219,7 @@ static int octeon_mgmt_open(struct net_device *netdev) */ if (netdev->phydev) { netif_carrier_off(netdev); - phy_start_aneg(netdev->phydev); + phy_start(netdev->phydev); } netif_wake_queue(netdev); @@ -1247,8 +1247,10 @@ static int octeon_mgmt_stop(struct net_device *netdev) napi_disable(&p->napi); netif_stop_queue(netdev); - if (netdev->phydev) + if (netdev->phydev) { + phy_stop(netdev->phydev); phy_disconnect(netdev->phydev); + } netif_carrier_off(netdev); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h index 593e3812af93..3c06f5fb5759 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h @@ -11,9 +11,11 @@ #define DPNI_VER_MAJOR 7 #define DPNI_VER_MINOR 0 #define DPNI_CMD_BASE_VERSION 1 +#define DPNI_CMD_2ND_VERSION 2 #define DPNI_CMD_ID_OFFSET 4 #define DPNI_CMD(id) (((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_BASE_VERSION) +#define DPNI_CMD_V2(id) (((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_2ND_VERSION) #define DPNI_CMDID_OPEN DPNI_CMD(0x801) #define DPNI_CMDID_CLOSE DPNI_CMD(0x800) @@ -45,7 +47,7 @@ #define DPNI_CMDID_SET_MAX_FRAME_LENGTH DPNI_CMD(0x216) #define DPNI_CMDID_GET_MAX_FRAME_LENGTH DPNI_CMD(0x217) #define DPNI_CMDID_SET_LINK_CFG DPNI_CMD(0x21A) -#define DPNI_CMDID_SET_TX_SHAPING DPNI_CMD(0x21B) +#define DPNI_CMDID_SET_TX_SHAPING DPNI_CMD_V2(0x21B) #define DPNI_CMDID_SET_MCAST_PROMISC DPNI_CMD(0x220) #define DPNI_CMDID_GET_MCAST_PROMISC DPNI_CMD(0x221) diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index 98be51d8b08c..bfa2826c5545 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -229,7 +229,7 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) /* Return all Fs if nothing was there */ if ((xgmac_read32(®s->mdio_stat, endian) & MDIO_STAT_RD_ER) && !priv->has_a011043) { - dev_err(&bus->dev, + dev_dbg(&bus->dev, "Error while reading PHY%d reg at %d.%hhu\n", phy_id, dev_addr, regnum); return 0xffff; diff --git a/drivers/net/ethernet/huawei/hinic/Kconfig b/drivers/net/ethernet/huawei/hinic/Kconfig index 936e2dd3bb13..b47bd5440c5f 100644 --- a/drivers/net/ethernet/huawei/hinic/Kconfig +++ b/drivers/net/ethernet/huawei/hinic/Kconfig @@ -6,6 +6,7 @@ config HINIC tristate "Huawei Intelligent PCIE Network Interface Card" depends on (PCI_MSI && (X86 || ARM64)) + select NET_DEVLINK help This driver supports HiNIC PCIE Ethernet cards. To compile this driver as part of the kernel, choose Y here. diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c index 02cd635d6914..eb97f2d6b1ad 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c @@ -58,9 +58,9 @@ static int change_mac(struct hinic_dev *nic_dev, const u8 *addr, sizeof(port_mac_cmd), &port_mac_cmd, &out_size); if (err || out_size != sizeof(port_mac_cmd) || - (port_mac_cmd.status && - port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY && - port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) { + (port_mac_cmd.status && + (port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY || !HINIC_IS_VF(hwif)) && + port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) { dev_err(&pdev->dev, "Failed to change MAC, err: %d, status: 0x%x, out size: 0x%x\n", err, port_mac_cmd.status, out_size); return -EFAULT; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c index 4d63680f2143..f8a26459ff65 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -38,8 +38,7 @@ static int hinic_set_mac(struct hinic_hwdev *hwdev, const u8 *mac_addr, err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_MAC, &mac_info, sizeof(mac_info), &mac_info, &out_size); if (err || out_size != sizeof(mac_info) || - (mac_info.status && mac_info.status != HINIC_PF_SET_VF_ALREADY && - mac_info.status != HINIC_MGMT_STATUS_EXIST)) { + (mac_info.status && mac_info.status != HINIC_MGMT_STATUS_EXIST)) { dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to set MAC, err: %d, status: 0x%x, out size: 0x%x\n", err, mac_info.status, out_size); return -EIO; @@ -503,8 +502,7 @@ struct hinic_sriov_info *hinic_get_sriov_info_by_pcidev(struct pci_dev *pdev) static int hinic_check_mac_info(u8 status, u16 vlan_id) { - if ((status && status != HINIC_MGMT_STATUS_EXIST && - status != HINIC_PF_SET_VF_ALREADY) || + if ((status && status != HINIC_MGMT_STATUS_EXIST) || (vlan_id & CHECK_IPSU_15BIT && status == HINIC_MGMT_STATUS_EXIST)) return -EINVAL; @@ -546,12 +544,6 @@ static int hinic_update_mac(struct hinic_hwdev *hwdev, u8 *old_mac, return -EINVAL; } - if (mac_info.status == HINIC_PF_SET_VF_ALREADY) { - dev_warn(&hwdev->hwif->pdev->dev, - "PF has already set VF MAC. Ignore update operation\n"); - return HINIC_PF_SET_VF_ALREADY; - } - if (mac_info.status == HINIC_MGMT_STATUS_EXIST) dev_warn(&hwdev->hwif->pdev->dev, "MAC is repeated. Ignore update operation\n"); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index d870343cf689..cf539db79af9 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3806,8 +3806,8 @@ static int __maybe_unused iavf_suspend(struct device *dev_d) static int __maybe_unused iavf_resume(struct device *dev_d) { struct pci_dev *pdev = to_pci_dev(dev_d); - struct iavf_adapter *adapter = pci_get_drvdata(pdev); - struct net_device *netdev = adapter->netdev; + struct net_device *netdev = pci_get_drvdata(pdev); + struct iavf_adapter *adapter = netdev_priv(netdev); u32 err; pci_set_master(pdev); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 34abfcea9858..7db5fd977367 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -2288,26 +2288,28 @@ void ice_set_safe_mode_caps(struct ice_hw *hw) { struct ice_hw_func_caps *func_caps = &hw->func_caps; struct ice_hw_dev_caps *dev_caps = &hw->dev_caps; - u32 valid_func, rxq_first_id, txq_first_id; - u32 msix_vector_first_id, max_mtu; + struct ice_hw_common_caps cached_caps; u32 num_funcs; /* cache some func_caps values that should be restored after memset */ - valid_func = func_caps->common_cap.valid_functions; - txq_first_id = func_caps->common_cap.txq_first_id; - rxq_first_id = func_caps->common_cap.rxq_first_id; - msix_vector_first_id = func_caps->common_cap.msix_vector_first_id; - max_mtu = func_caps->common_cap.max_mtu; + cached_caps = func_caps->common_cap; /* unset func capabilities */ memset(func_caps, 0, sizeof(*func_caps)); +#define ICE_RESTORE_FUNC_CAP(name) \ + func_caps->common_cap.name = cached_caps.name + /* restore cached values */ - func_caps->common_cap.valid_functions = valid_func; - func_caps->common_cap.txq_first_id = txq_first_id; - func_caps->common_cap.rxq_first_id = rxq_first_id; - func_caps->common_cap.msix_vector_first_id = msix_vector_first_id; - func_caps->common_cap.max_mtu = max_mtu; + ICE_RESTORE_FUNC_CAP(valid_functions); + ICE_RESTORE_FUNC_CAP(txq_first_id); + ICE_RESTORE_FUNC_CAP(rxq_first_id); + ICE_RESTORE_FUNC_CAP(msix_vector_first_id); + ICE_RESTORE_FUNC_CAP(max_mtu); + ICE_RESTORE_FUNC_CAP(nvm_unified_update); + ICE_RESTORE_FUNC_CAP(nvm_update_pending_nvm); + ICE_RESTORE_FUNC_CAP(nvm_update_pending_orom); + ICE_RESTORE_FUNC_CAP(nvm_update_pending_netlist); /* one Tx and one Rx queue in safe mode */ func_caps->common_cap.num_rxq = 1; @@ -2318,22 +2320,25 @@ void ice_set_safe_mode_caps(struct ice_hw *hw) func_caps->guar_num_vsi = 1; /* cache some dev_caps values that should be restored after memset */ - valid_func = dev_caps->common_cap.valid_functions; - txq_first_id = dev_caps->common_cap.txq_first_id; - rxq_first_id = dev_caps->common_cap.rxq_first_id; - msix_vector_first_id = dev_caps->common_cap.msix_vector_first_id; - max_mtu = dev_caps->common_cap.max_mtu; + cached_caps = dev_caps->common_cap; num_funcs = dev_caps->num_funcs; /* unset dev capabilities */ memset(dev_caps, 0, sizeof(*dev_caps)); +#define ICE_RESTORE_DEV_CAP(name) \ + dev_caps->common_cap.name = cached_caps.name + /* restore cached values */ - dev_caps->common_cap.valid_functions = valid_func; - dev_caps->common_cap.txq_first_id = txq_first_id; - dev_caps->common_cap.rxq_first_id = rxq_first_id; - dev_caps->common_cap.msix_vector_first_id = msix_vector_first_id; - dev_caps->common_cap.max_mtu = max_mtu; + ICE_RESTORE_DEV_CAP(valid_functions); + ICE_RESTORE_DEV_CAP(txq_first_id); + ICE_RESTORE_DEV_CAP(rxq_first_id); + ICE_RESTORE_DEV_CAP(msix_vector_first_id); + ICE_RESTORE_DEV_CAP(max_mtu); + ICE_RESTORE_DEV_CAP(nvm_unified_update); + ICE_RESTORE_DEV_CAP(nvm_update_pending_nvm); + ICE_RESTORE_DEV_CAP(nvm_update_pending_orom); + ICE_RESTORE_DEV_CAP(nvm_update_pending_netlist); dev_caps->num_funcs = num_funcs; /* one Tx and one Rx queue per function in safe mode */ diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index deaefe00c9c0..8968fdd4816b 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -289,7 +289,13 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, return -EIO; } - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, HZ, &event); + /* In most cases, firmware reports a write completion within a few + * milliseconds. However, it has been observed that a completion might + * take more than a second to complete in some cases. The timeout here + * is conservative and is intended to prevent failure to update when + * firmware is slow to respond. + */ + err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, 15 * HZ, &event); if (err) { dev_err(dev, "Timed out waiting for firmware write completion for module 0x%02x, err %d\n", module, err); @@ -513,7 +519,7 @@ static int ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, return -EIO; } - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, HZ, + err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, 30 * HZ, &event); if (err) { dev_err(dev, "Timed out waiting for firmware to switch active flash banks, err %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index f2682776f8c8..ebbb8f54871c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -246,7 +246,7 @@ static int ice_get_free_slot(void *array, int size, int curr) * ice_vsi_delete - delete a VSI from the switch * @vsi: pointer to VSI being removed */ -void ice_vsi_delete(struct ice_vsi *vsi) +static void ice_vsi_delete(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct ice_vsi_ctx *ctxt; @@ -313,7 +313,7 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) * * Returns 0 on success, negative on failure */ -int ice_vsi_clear(struct ice_vsi *vsi) +static int ice_vsi_clear(struct ice_vsi *vsi) { struct ice_pf *pf = NULL; struct device *dev; @@ -563,7 +563,7 @@ static int ice_vsi_get_qs(struct ice_vsi *vsi) * ice_vsi_put_qs - Release queues from VSI to PF * @vsi: the VSI that is going to release queues */ -void ice_vsi_put_qs(struct ice_vsi *vsi) +static void ice_vsi_put_qs(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; int i; @@ -1196,6 +1196,18 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi) { int i; + /* Avoid stale references by clearing map from vector to ring */ + if (vsi->q_vectors) { + ice_for_each_q_vector(vsi, i) { + struct ice_q_vector *q_vector = vsi->q_vectors[i]; + + if (q_vector) { + q_vector->tx.ring = NULL; + q_vector->rx.ring = NULL; + } + } + } + if (vsi->tx_rings) { for (i = 0; i < vsi->alloc_txq; i++) { if (vsi->tx_rings[i]) { @@ -2291,7 +2303,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (status) { dev_err(dev, "VSI %d failed lan queue config, error %s\n", vsi->vsi_num, ice_stat_str(status)); - goto unroll_vector_base; + goto unroll_clear_rings; } /* Add switch rule to drop all Tx Flow Control Frames, of look up diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 981f3a156c24..3da17895a2b1 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -45,10 +45,6 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc); void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); -void ice_vsi_delete(struct ice_vsi *vsi); - -int ice_vsi_clear(struct ice_vsi *vsi); - #ifdef CONFIG_DCB int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc); #endif /* CONFIG_DCB */ @@ -79,8 +75,6 @@ bool ice_is_reset_in_progress(unsigned long *state); void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio); -void ice_vsi_put_qs(struct ice_vsi *vsi); - void ice_vsi_dis_irq(struct ice_vsi *vsi); void ice_vsi_free_irq(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4634b48949bb..54a7f55eb8c1 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3169,10 +3169,8 @@ static int ice_setup_pf_sw(struct ice_pf *pf) return -EBUSY; vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); - if (!vsi) { - status = -ENOMEM; - goto unroll_vsi_setup; - } + if (!vsi) + return -ENOMEM; status = ice_cfg_netdev(vsi); if (status) { @@ -3219,12 +3217,7 @@ unroll_napi_add: } unroll_vsi_setup: - if (vsi) { - ice_vsi_free_q_vectors(vsi); - ice_vsi_delete(vsi); - ice_vsi_put_qs(vsi); - ice_vsi_clear(vsi); - } + ice_vsi_release(vsi); return status; } @@ -4522,6 +4515,7 @@ static int __maybe_unused ice_suspend(struct device *dev) } ice_clear_interrupt_scheme(pf); + pci_save_state(pdev); pci_wake_from_d3(pdev, pf->wol_ena); pci_set_power_state(pdev, PCI_D3hot); return 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 2f8a4cfc5fa1..86ca8b9ea1b8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5396,9 +5396,10 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter, return err; } -static int ixgbe_macvlan_up(struct net_device *vdev, void *data) +static int ixgbe_macvlan_up(struct net_device *vdev, + struct netdev_nested_priv *priv) { - struct ixgbe_adapter *adapter = data; + struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data; struct ixgbe_fwd_adapter *accel; if (!netif_is_macvlan(vdev)) @@ -5415,8 +5416,12 @@ static int ixgbe_macvlan_up(struct net_device *vdev, void *data) static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter) { + struct netdev_nested_priv priv = { + .data = (void *)adapter, + }; + netdev_walk_all_upper_dev_rcu(adapter->netdev, - ixgbe_macvlan_up, adapter); + ixgbe_macvlan_up, &priv); } static void ixgbe_configure(struct ixgbe_adapter *adapter) @@ -9023,9 +9028,10 @@ static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter) } #endif /* CONFIG_IXGBE_DCB */ -static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data) +static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, + struct netdev_nested_priv *priv) { - struct ixgbe_adapter *adapter = data; + struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data; struct ixgbe_fwd_adapter *accel; int pool; @@ -9062,13 +9068,16 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data) static void ixgbe_defrag_macvlan_pools(struct net_device *dev) { struct ixgbe_adapter *adapter = netdev_priv(dev); + struct netdev_nested_priv priv = { + .data = (void *)adapter, + }; /* flush any stale bits out of the fwd bitmask */ bitmap_clear(adapter->fwd_bitmask, 1, 63); /* walk through upper devices reassigning pools */ netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool, - adapter); + &priv); } /** @@ -9242,14 +9251,18 @@ struct upper_walk_data { u8 queue; }; -static int get_macvlan_queue(struct net_device *upper, void *_data) +static int get_macvlan_queue(struct net_device *upper, + struct netdev_nested_priv *priv) { if (netif_is_macvlan(upper)) { struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper); - struct upper_walk_data *data = _data; - struct ixgbe_adapter *adapter = data->adapter; - int ifindex = data->ifindex; + struct ixgbe_adapter *adapter; + struct upper_walk_data *data; + int ifindex; + data = (struct upper_walk_data *)priv->data; + ifindex = data->ifindex; + adapter = data->adapter; if (vadapter && upper->ifindex == ifindex) { data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx; data->action = data->queue; @@ -9265,6 +9278,7 @@ static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex, { struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; unsigned int num_vfs = adapter->num_vfs, vf; + struct netdev_nested_priv priv; struct upper_walk_data data; struct net_device *upper; @@ -9284,8 +9298,9 @@ static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex, data.ifindex = ifindex; data.action = 0; data.queue = 0; + priv.data = (void *)&data; if (netdev_walk_all_upper_dev_rcu(adapter->netdev, - get_macvlan_queue, &data)) { + get_macvlan_queue, &priv)) { *action = data.action; *queue = data.queue; diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 635ff3a5dcfb..51ed8a54d380 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -245,6 +245,7 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget) int pkts = 0; int bytes = 0; + netif_tx_lock(net_dev); while (pkts < budget) { struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->tx_free]; @@ -268,6 +269,7 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget) net_dev->stats.tx_bytes += bytes; netdev_completed_queue(ch->priv->net_dev, pkts, bytes); + netif_tx_unlock(net_dev); if (netif_queue_stopped(net_dev)) netif_wake_queue(net_dev); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index c4345e3d616f..5bf0409f5d42 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3400,24 +3400,15 @@ static int mvneta_txq_sw_init(struct mvneta_port *pp, txq->last_desc = txq->size - 1; txq->buf = kmalloc_array(txq->size, sizeof(*txq->buf), GFP_KERNEL); - if (!txq->buf) { - dma_free_coherent(pp->dev->dev.parent, - txq->size * MVNETA_DESC_ALIGNED_SIZE, - txq->descs, txq->descs_phys); + if (!txq->buf) return -ENOMEM; - } /* Allocate DMA buffers for TSO MAC/IP/TCP headers */ txq->tso_hdrs = dma_alloc_coherent(pp->dev->dev.parent, txq->size * TSO_HEADER_SIZE, &txq->tso_hdrs_phys, GFP_KERNEL); - if (!txq->tso_hdrs) { - kfree(txq->buf); - dma_free_coherent(pp->dev->dev.parent, - txq->size * MVNETA_DESC_ALIGNED_SIZE, - txq->descs, txq->descs_phys); + if (!txq->tso_hdrs) return -ENOMEM; - } /* Setup XPS mapping */ if (txq_number > 1) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c index 387e33fa417a..2718fe201c14 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c @@ -17,7 +17,7 @@ static const u16 msgs_offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN); -void otx2_mbox_reset(struct otx2_mbox *mbox, int devid) +void __otx2_mbox_reset(struct otx2_mbox *mbox, int devid) { void *hw_mbase = mbox->hwbase + (devid * MBOX_SIZE); struct otx2_mbox_dev *mdev = &mbox->dev[devid]; @@ -26,13 +26,21 @@ void otx2_mbox_reset(struct otx2_mbox *mbox, int devid) tx_hdr = hw_mbase + mbox->tx_start; rx_hdr = hw_mbase + mbox->rx_start; - spin_lock(&mdev->mbox_lock); mdev->msg_size = 0; mdev->rsp_size = 0; tx_hdr->num_msgs = 0; tx_hdr->msg_size = 0; rx_hdr->num_msgs = 0; rx_hdr->msg_size = 0; +} +EXPORT_SYMBOL(__otx2_mbox_reset); + +void otx2_mbox_reset(struct otx2_mbox *mbox, int devid) +{ + struct otx2_mbox_dev *mdev = &mbox->dev[devid]; + + spin_lock(&mdev->mbox_lock); + __otx2_mbox_reset(mbox, devid); spin_unlock(&mdev->mbox_lock); } EXPORT_SYMBOL(otx2_mbox_reset); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 6dfd0f90cd70..ab433789d2c3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -93,6 +93,7 @@ struct mbox_msghdr { }; void otx2_mbox_reset(struct otx2_mbox *mbox, int devid); +void __otx2_mbox_reset(struct otx2_mbox *mbox, int devid); void otx2_mbox_destroy(struct otx2_mbox *mbox); int otx2_mbox_init(struct otx2_mbox *mbox, void __force *hwbase, struct pci_dev *pdev, void __force *reg_base, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index dcf25a092008..b89dde2c8b08 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -463,6 +463,7 @@ void rvu_nix_freemem(struct rvu *rvu); int rvu_get_nixlf_count(struct rvu *rvu); void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf); int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr); +int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add); /* NPC APIs */ int rvu_npc_init(struct rvu *rvu); @@ -477,7 +478,7 @@ void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan); -void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc); +void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable); int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 01a793105599..0fc70824fd6b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -17,7 +17,6 @@ #include "npc.h" #include "cgx.h" -static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add); static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req, int type, int chan_id); @@ -2020,7 +2019,7 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list, return 0; } -static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) +int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) { int err = 0, idx, next_idx, last_idx; struct nix_mce_list *mce_list; @@ -2065,7 +2064,7 @@ static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) /* Disable MCAM entry in NPC */ if (!mce_list->count) { - rvu_npc_disable_bcast_entry(rvu, pcifunc); + rvu_npc_enable_bcast_entry(rvu, pcifunc, false); goto end; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 0a214084406a..fbaf9bcd83f2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -530,7 +530,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, NIX_INTF_RX, &entry, true); } -void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc) +void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable) { struct npc_mcam *mcam = &rvu->hw->mcam; int blkaddr, index; @@ -543,7 +543,7 @@ void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc) pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; index = npc_get_nixlf_mcam_index(mcam, pcifunc, 0, NIXLF_BCAST_ENTRY); - npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); } void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, @@ -622,23 +622,35 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc, nixlf, NIXLF_UCAST_ENTRY); npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); - /* For PF, ena/dis promisc and bcast MCAM match entries */ - if (pcifunc & RVU_PFVF_FUNC_MASK) + /* For PF, ena/dis promisc and bcast MCAM match entries. + * For VFs add/delete from bcast list when RX multicast + * feature is present. + */ + if (pcifunc & RVU_PFVF_FUNC_MASK && !rvu->hw->cap.nix_rx_multicast) return; /* For bcast, enable/disable only if it's action is not * packet replication, incase if action is replication - * then this PF's nixlf is removed from bcast replication + * then this PF/VF's nixlf is removed from bcast replication * list. */ - index = npc_get_nixlf_mcam_index(mcam, pcifunc, + index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK, nixlf, NIXLF_BCAST_ENTRY); bank = npc_get_bank(mcam, index); *(u64 *)&action = rvu_read64(rvu, blkaddr, NPC_AF_MCAMEX_BANKX_ACTION(index & (mcam->banksize - 1), bank)); - if (action.op != NIX_RX_ACTIONOP_MCAST) + + /* VFs will not have BCAST entry */ + if (action.op != NIX_RX_ACTIONOP_MCAST && + !(pcifunc & RVU_PFVF_FUNC_MASK)) { npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); + } else { + nix_update_bcast_mce_list(rvu, pcifunc, enable); + /* Enable PF's BCAST entry for packet replication */ + rvu_npc_enable_bcast_entry(rvu, pcifunc, enable); + } + if (enable) rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf); else diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 75a8c407e815..2fb45670aca4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -370,8 +370,8 @@ static int otx2_forward_vf_mbox_msgs(struct otx2_nic *pf, dst_mbox = &pf->mbox; dst_size = dst_mbox->mbox.tx_size - ALIGN(sizeof(*mbox_hdr), MBOX_MSG_ALIGN); - /* Check if msgs fit into destination area */ - if (mbox_hdr->msg_size > dst_size) + /* Check if msgs fit into destination area and has valid size */ + if (mbox_hdr->msg_size > dst_size || !mbox_hdr->msg_size) return -EINVAL; dst_mdev = &dst_mbox->mbox.dev[0]; @@ -526,10 +526,10 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work) end: offset = mbox->rx_start + msg->next_msgoff; + if (mdev->msgs_acked == (vf_mbox->up_num_msgs - 1)) + __otx2_mbox_reset(mbox, 0); mdev->msgs_acked++; } - - otx2_mbox_reset(mbox, vf_idx); } static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) @@ -803,10 +803,11 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work) msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2_process_pfaf_mbox_msg(pf, msg); offset = mbox->rx_start + msg->next_msgoff; + if (mdev->msgs_acked == (af_mbox->num_msgs - 1)) + __otx2_mbox_reset(mbox, 0); mdev->msgs_acked++; } - otx2_mbox_reset(mbox, 0); } static void otx2_handle_link_event(struct otx2_nic *pf) @@ -1560,10 +1561,13 @@ int otx2_open(struct net_device *netdev) err = otx2_rxtx_enable(pf, true); if (err) - goto err_free_cints; + goto err_tx_stop_queues; return 0; +err_tx_stop_queues: + netif_tx_stop_all_queues(netdev); + netif_carrier_off(netdev); err_free_cints: otx2_free_cints(pf, qidx); vec = pci_irq_vector(pf->pdev, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 3a5b34a2a7a6..e46834e043be 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -524,6 +524,7 @@ static void otx2_sqe_add_hdr(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, sqe_hdr->ol3type = NIX_SENDL3TYPE_IP4_CKSUM; } else if (skb->protocol == htons(ETH_P_IPV6)) { proto = ipv6_hdr(skb)->nexthdr; + sqe_hdr->ol3type = NIX_SENDL3TYPE_IP6; } if (proto == IPPROTO_TCP) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 92a3db69a6cd..2f90f1721441 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -99,10 +99,10 @@ static void otx2vf_vfaf_mbox_handler(struct work_struct *work) msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2vf_process_vfaf_mbox_msg(af_mbox->pfvf, msg); offset = mbox->rx_start + msg->next_msgoff; + if (mdev->msgs_acked == (af_mbox->num_msgs - 1)) + __otx2_mbox_reset(mbox, 0); mdev->msgs_acked++; } - - otx2_mbox_reset(mbox, 0); } static int otx2vf_process_mbox_msg_up(struct otx2_nic *vf, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1d91a0d0ab1d..2d1f4b3be9bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -69,12 +69,10 @@ enum { MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR = 0x10, }; -static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd, - struct mlx5_cmd_msg *in, - struct mlx5_cmd_msg *out, - void *uout, int uout_size, - mlx5_cmd_cbk_t cbk, - void *context, int page_queue) +static struct mlx5_cmd_work_ent * +cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in, + struct mlx5_cmd_msg *out, void *uout, int uout_size, + mlx5_cmd_cbk_t cbk, void *context, int page_queue) { gfp_t alloc_flags = cbk ? GFP_ATOMIC : GFP_KERNEL; struct mlx5_cmd_work_ent *ent; @@ -83,6 +81,7 @@ static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd, if (!ent) return ERR_PTR(-ENOMEM); + ent->idx = -EINVAL; ent->in = in; ent->out = out; ent->uout = uout; @@ -91,10 +90,16 @@ static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd, ent->context = context; ent->cmd = cmd; ent->page_queue = page_queue; + refcount_set(&ent->refcnt, 1); return ent; } +static void cmd_free_ent(struct mlx5_cmd_work_ent *ent) +{ + kfree(ent); +} + static u8 alloc_token(struct mlx5_cmd *cmd) { u8 token; @@ -109,7 +114,7 @@ static u8 alloc_token(struct mlx5_cmd *cmd) return token; } -static int alloc_ent(struct mlx5_cmd *cmd) +static int cmd_alloc_index(struct mlx5_cmd *cmd) { unsigned long flags; int ret; @@ -123,7 +128,7 @@ static int alloc_ent(struct mlx5_cmd *cmd) return ret < cmd->max_reg_cmds ? ret : -ENOMEM; } -static void free_ent(struct mlx5_cmd *cmd, int idx) +static void cmd_free_index(struct mlx5_cmd *cmd, int idx) { unsigned long flags; @@ -132,6 +137,22 @@ static void free_ent(struct mlx5_cmd *cmd, int idx) spin_unlock_irqrestore(&cmd->alloc_lock, flags); } +static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) +{ + refcount_inc(&ent->refcnt); +} + +static void cmd_ent_put(struct mlx5_cmd_work_ent *ent) +{ + if (!refcount_dec_and_test(&ent->refcnt)) + return; + + if (ent->idx >= 0) + cmd_free_index(ent->cmd, ent->idx); + + cmd_free_ent(ent); +} + static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) { return cmd->cmd_buf + (idx << cmd->log_stride); @@ -219,11 +240,6 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent) ent->ret = -ETIMEDOUT; } -static void free_cmd(struct mlx5_cmd_work_ent *ent) -{ - kfree(ent); -} - static int verify_signature(struct mlx5_cmd_work_ent *ent) { struct mlx5_cmd_mailbox *next = ent->out->next; @@ -837,11 +853,22 @@ static void cb_timeout_handler(struct work_struct *work) struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev, cmd); + mlx5_cmd_eq_recover(dev); + + /* Maybe got handled by eq recover ? */ + if (!test_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state)) { + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, recovered after timeout\n", ent->idx, + mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + goto out; /* phew, already handled */ + } + ent->ret = -ETIMEDOUT; - mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n", - mlx5_command_str(msg_to_opcode(ent->in)), - msg_to_opcode(ent->in)); + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n", + ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + +out: + cmd_ent_put(ent); /* for the cmd_ent_get() took on schedule delayed work */ } static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg); @@ -856,6 +883,32 @@ static bool opcode_allowed(struct mlx5_cmd *cmd, u16 opcode) return cmd->allowed_opcode == opcode; } +static int cmd_alloc_index_retry(struct mlx5_cmd *cmd) +{ + unsigned long alloc_end = jiffies + msecs_to_jiffies(1000); + int idx; + +retry: + idx = cmd_alloc_index(cmd); + if (idx < 0 && time_before(jiffies, alloc_end)) { + /* Index allocation can fail on heavy load of commands. This is a temporary + * situation as the current command already holds the semaphore, meaning that + * another command completion is being handled and it is expected to release + * the entry index soon. + */ + cpu_relax(); + goto retry; + } + return idx; +} + +bool mlx5_cmd_is_down(struct mlx5_core_dev *dev) +{ + return pci_channel_offline(dev->pdev) || + dev->cmd.state != MLX5_CMDIF_STATE_UP || + dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR; +} + static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); @@ -873,14 +926,14 @@ static void cmd_work_handler(struct work_struct *work) sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); if (!ent->page_queue) { - alloc_ret = alloc_ent(cmd); + alloc_ret = cmd_alloc_index_retry(cmd); if (alloc_ret < 0) { mlx5_core_err_rl(dev, "failed to allocate command entry\n"); if (ent->callback) { ent->callback(-EAGAIN, ent->context); mlx5_free_cmd_msg(dev, ent->out); free_msg(dev, ent->in); - free_cmd(ent); + cmd_ent_put(ent); } else { ent->ret = -EAGAIN; complete(&ent->done); @@ -916,15 +969,12 @@ static void cmd_work_handler(struct work_struct *work) ent->ts1 = ktime_get_ns(); cmd_mode = cmd->mode; - if (ent->callback) - schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); + if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, cb_timeout)) + cmd_ent_get(ent); set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); /* Skip sending command to fw if internal error */ - if (pci_channel_offline(dev->pdev) || - dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR || - cmd->state != MLX5_CMDIF_STATE_UP || - !opcode_allowed(&dev->cmd, ent->op)) { + if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, ent->op)) { u8 status = 0; u32 drv_synd; @@ -933,13 +983,10 @@ static void cmd_work_handler(struct work_struct *work) MLX5_SET(mbox_out, ent->out, syndrome, drv_synd); mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); - /* no doorbell, no need to keep the entry */ - free_ent(cmd, ent->idx); - if (ent->callback) - free_cmd(ent); return; } + cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* ring doorbell after the descriptor is valid */ mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); @@ -983,6 +1030,35 @@ static const char *deliv_status_to_str(u8 status) } } +enum { + MLX5_CMD_TIMEOUT_RECOVER_MSEC = 5 * 1000, +}; + +static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, + struct mlx5_cmd_work_ent *ent) +{ + unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_RECOVER_MSEC); + + mlx5_cmd_eq_recover(dev); + + /* Re-wait on the ent->done after executing the recovery flow. If the + * recovery flow (or any other recovery flow running simultaneously) + * has recovered an EQE, it should cause the entry to be completed by + * the command interface. + */ + if (wait_for_completion_timeout(&ent->done, timeout)) { + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) recovered after timeout\n", ent->idx, + mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + return; + } + + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) No done completion\n", ent->idx, + mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + + ent->ret = -ETIMEDOUT; + mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); +} + static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) { unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); @@ -994,12 +1070,10 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) ent->ret = -ECANCELED; goto out_err; } - if (cmd->mode == CMD_MODE_POLLING || ent->polling) { + if (cmd->mode == CMD_MODE_POLLING || ent->polling) wait_for_completion(&ent->done); - } else if (!wait_for_completion_timeout(&ent->done, timeout)) { - ent->ret = -ETIMEDOUT; - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); - } + else if (!wait_for_completion_timeout(&ent->done, timeout)) + wait_func_handle_exec_timeout(dev, ent); out_err: err = ent->ret; @@ -1039,11 +1113,16 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, if (callback && page_queue) return -EINVAL; - ent = alloc_cmd(cmd, in, out, uout, uout_size, callback, context, - page_queue); + ent = cmd_alloc_ent(cmd, in, out, uout, uout_size, + callback, context, page_queue); if (IS_ERR(ent)) return PTR_ERR(ent); + /* put for this ent is when consumed, depending on the use case + * 1) (!callback) blocking flow: by caller after wait_func completes + * 2) (callback) flow: by mlx5_cmd_comp_handler() when ent is handled + */ + ent->token = token; ent->polling = force_polling; @@ -1062,12 +1141,10 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, } if (callback) - goto out; + goto out; /* mlx5_cmd_comp_handler() will put(ent) */ err = wait_func(dev, ent); - if (err == -ETIMEDOUT) - goto out; - if (err == -ECANCELED) + if (err == -ETIMEDOUT || err == -ECANCELED) goto out_free; ds = ent->ts2 - ent->ts1; @@ -1085,7 +1162,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, *status = ent->status; out_free: - free_cmd(ent); + cmd_ent_put(ent); out: return err; } @@ -1516,14 +1593,19 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force if (!forced) { mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n", ent->idx); - free_ent(cmd, ent->idx); - free_cmd(ent); + cmd_ent_put(ent); } continue; } - if (ent->callback) - cancel_delayed_work(&ent->cb_timeout_work); + if (ent->callback && cancel_delayed_work(&ent->cb_timeout_work)) + cmd_ent_put(ent); /* timeout work was canceled */ + + if (!forced || /* Real FW completion */ + pci_channel_offline(dev->pdev) || /* FW is inaccessible */ + dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + cmd_ent_put(ent); + if (ent->page_queue) sem = &cmd->pages_sem; else @@ -1545,10 +1627,6 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force ent->ret, deliv_status_to_str(ent->status), ent->status); } - /* only real completion will free the entry slot */ - if (!forced) - free_ent(cmd, ent->idx); - if (ent->callback) { ds = ent->ts2 - ent->ts1; if (ent->op < MLX5_CMD_OP_MAX) { @@ -1576,10 +1654,13 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force free_msg(dev, ent->in); err = err ? err : ent->status; - if (!forced) - free_cmd(ent); + /* final consumer is done, release ent */ + cmd_ent_put(ent); callback(err, context); } else { + /* release wait_func() so mlx5_cmd_invoke() + * can make the final ent_put() + */ complete(&ent->done); } up(sem); @@ -1589,8 +1670,11 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) { + struct mlx5_cmd *cmd = &dev->cmd; + unsigned long bitmask; unsigned long flags; u64 vector; + int i; /* wait for pending handlers to complete */ mlx5_eq_synchronize_cmd_irq(dev); @@ -1599,11 +1683,20 @@ void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) if (!vector) goto no_trig; + bitmask = vector; + /* we must increment the allocated entries refcount before triggering the completions + * to guarantee pending commands will not get freed in the meanwhile. + * For that reason, it also has to be done inside the alloc_lock. + */ + for_each_set_bit(i, &bitmask, (1 << cmd->log_sz)) + cmd_ent_get(cmd->ent_arr[i]); vector |= MLX5_TRIGGERED_CMD_COMP; spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); mlx5_core_dbg(dev, "vector 0x%llx\n", vector); mlx5_cmd_comp_handler(dev, vector, true); + for_each_set_bit(i, &bitmask, (1 << cmd->log_sz)) + cmd_ent_put(cmd->ent_arr[i]); return; no_trig: @@ -1711,10 +1804,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, u8 token; opcode = MLX5_GET(mbox_in, in, opcode); - if (pci_channel_offline(dev->pdev) || - dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR || - dev->cmd.state != MLX5_CMDIF_STATE_UP || - !opcode_allowed(&dev->cmd, opcode)) { + if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode)) { err = mlx5_internal_err_ret_value(dev, opcode, &drv_synd, &status); MLX5_SET(mbox_out, out, status, status); MLX5_SET(mbox_out, out, syndrome, drv_synd); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 90d5caabd6af..356f5852955f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -91,7 +91,12 @@ struct page_pool; #define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER) #define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2) -#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8)) +/* Add another page to MLX5E_REQUIRED_WQE_MTTS as a buffer between + * WQEs, This page will absorb write overflow by the hardware, when + * receiving packets larger than MTU. These oversize packets are + * dropped by the driver at a later stage. + */ +#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE + 1, 8)) #define MLX5E_LOG_ALIGNED_MPWQE_PPW (ilog2(MLX5E_REQUIRED_WQE_MTTS)) #define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS) #define MLX5E_MAX_RQ_NUM_MTTS \ @@ -617,6 +622,7 @@ struct mlx5e_rq { u32 rqn; struct mlx5_core_dev *mdev; struct mlx5_core_mkey umr_mkey; + struct mlx5e_dma_info wqe_overflow; /* XDP read-mostly */ struct xdp_rxq_info xdp_rxq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 96608dbb9314..308fd279669e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -569,6 +569,9 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy) if (fec_policy >= (1 << MLX5E_FEC_LLRS_272_257_1) && !fec_50g_per_lane) return -EOPNOTSUPP; + if (fec_policy && !mlx5e_fec_in_caps(dev, fec_policy)) + return -EOPNOTSUPP; + MLX5_SET(pplm_reg, in, local_port, 1); err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c index 906292035088..58e27038c947 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c @@ -110,11 +110,25 @@ static void mlx5e_rep_neigh_stats_work(struct work_struct *work) rtnl_unlock(); } +struct neigh_update_work { + struct work_struct work; + struct neighbour *n; + struct mlx5e_neigh_hash_entry *nhe; +}; + +static void mlx5e_release_neigh_update_work(struct neigh_update_work *update_work) +{ + neigh_release(update_work->n); + mlx5e_rep_neigh_entry_release(update_work->nhe); + kfree(update_work); +} + static void mlx5e_rep_neigh_update(struct work_struct *work) { - struct mlx5e_neigh_hash_entry *nhe = - container_of(work, struct mlx5e_neigh_hash_entry, neigh_update_work); - struct neighbour *n = nhe->n; + struct neigh_update_work *update_work = container_of(work, struct neigh_update_work, + work); + struct mlx5e_neigh_hash_entry *nhe = update_work->nhe; + struct neighbour *n = update_work->n; struct mlx5e_encap_entry *e; unsigned char ha[ETH_ALEN]; struct mlx5e_priv *priv; @@ -146,30 +160,42 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) mlx5e_rep_update_flows(priv, e, neigh_connected, ha); mlx5e_encap_put(priv, e); } - mlx5e_rep_neigh_entry_release(nhe); rtnl_unlock(); - neigh_release(n); + mlx5e_release_neigh_update_work(update_work); } -static void mlx5e_rep_queue_neigh_update_work(struct mlx5e_priv *priv, - struct mlx5e_neigh_hash_entry *nhe, - struct neighbour *n) +static struct neigh_update_work *mlx5e_alloc_neigh_update_work(struct mlx5e_priv *priv, + struct neighbour *n) { - /* Take a reference to ensure the neighbour and mlx5 encap - * entry won't be destructed until we drop the reference in - * delayed work. - */ - neigh_hold(n); + struct neigh_update_work *update_work; + struct mlx5e_neigh_hash_entry *nhe; + struct mlx5e_neigh m_neigh = {}; - /* This assignment is valid as long as the the neigh reference - * is taken - */ - nhe->n = n; + update_work = kzalloc(sizeof(*update_work), GFP_ATOMIC); + if (WARN_ON(!update_work)) + return NULL; - if (!queue_work(priv->wq, &nhe->neigh_update_work)) { - mlx5e_rep_neigh_entry_release(nhe); - neigh_release(n); + m_neigh.dev = n->dev; + m_neigh.family = n->ops->family; + memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len); + + /* Obtain reference to nhe as last step in order not to release it in + * atomic context. + */ + rcu_read_lock(); + nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh); + rcu_read_unlock(); + if (!nhe) { + kfree(update_work); + return NULL; } + + INIT_WORK(&update_work->work, mlx5e_rep_neigh_update); + neigh_hold(n); + update_work->n = n; + update_work->nhe = nhe; + + return update_work; } static int mlx5e_rep_netevent_event(struct notifier_block *nb, @@ -181,7 +207,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb, struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_neigh_hash_entry *nhe = NULL; - struct mlx5e_neigh m_neigh = {}; + struct neigh_update_work *update_work; struct neigh_parms *p; struct neighbour *n; bool found = false; @@ -196,17 +222,11 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb, #endif return NOTIFY_DONE; - m_neigh.dev = n->dev; - m_neigh.family = n->ops->family; - memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len); - - rcu_read_lock(); - nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh); - rcu_read_unlock(); - if (!nhe) + update_work = mlx5e_alloc_neigh_update_work(priv, n); + if (!update_work) return NOTIFY_DONE; - mlx5e_rep_queue_neigh_update_work(priv, nhe, n); + queue_work(priv->wq, &update_work->work); break; case NETEVENT_DELAY_PROBE_TIME_UPDATE: @@ -352,7 +372,6 @@ int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv, (*nhe)->priv = priv; memcpy(&(*nhe)->m_neigh, &e->m_neigh, sizeof(e->m_neigh)); - INIT_WORK(&(*nhe)->neigh_update_work, mlx5e_rep_neigh_update); spin_lock_init(&(*nhe)->encap_list_lock); INIT_LIST_HEAD(&(*nhe)->encap_list); refcount_set(&(*nhe)->refcnt, 1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index bc5f72ec3623..a8be40cbe325 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -246,8 +246,10 @@ mlx5_tc_ct_rule_to_tuple_nat(struct mlx5_ct_tuple *tuple, case FLOW_ACT_MANGLE_HDR_TYPE_IP6: ip6_offset = (offset - offsetof(struct ipv6hdr, saddr)); ip6_offset /= 4; - if (ip6_offset < 8) + if (ip6_offset < 4) tuple->ip.src_v6.s6_addr32[ip6_offset] = cpu_to_be32(val); + else if (ip6_offset < 8) + tuple->ip.dst_v6.s6_addr32[ip6_offset - 4] = cpu_to_be32(val); else return -EOPNOTSUPP; break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 64d002d92250..1f48f99c0997 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -217,6 +217,9 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv, break; } + if (WARN_ONCE(*rule_p, "VLAN rule already exists type %d", rule_type)) + return 0; + *rule_p = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(*rule_p)) { @@ -397,8 +400,7 @@ static void mlx5e_add_vlan_rules(struct mlx5e_priv *priv) for_each_set_bit(i, priv->fs.vlan.active_svlans, VLAN_N_VID) mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, i); - if (priv->fs.vlan.cvlan_filter_disabled && - !(priv->netdev->flags & IFF_PROMISC)) + if (priv->fs.vlan.cvlan_filter_disabled) mlx5e_add_any_vid_rules(priv); } @@ -415,8 +417,12 @@ static void mlx5e_del_vlan_rules(struct mlx5e_priv *priv) for_each_set_bit(i, priv->fs.vlan.active_svlans, VLAN_N_VID) mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, i); - if (priv->fs.vlan.cvlan_filter_disabled && - !(priv->netdev->flags & IFF_PROMISC)) + WARN_ON_ONCE(!(test_bit(MLX5E_STATE_DESTROYING, &priv->state))); + + /* must be called after DESTROY bit is set and + * set_rx_mode is called and flushed + */ + if (priv->fs.vlan.cvlan_filter_disabled) mlx5e_del_any_vid_rules(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b3cda7b6e5e1..42ec28e29834 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -246,12 +246,17 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, u64 npages, u8 page_shift, - struct mlx5_core_mkey *umr_mkey) + struct mlx5_core_mkey *umr_mkey, + dma_addr_t filler_addr) { - int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); + struct mlx5_mtt *mtt; + int inlen; void *mkc; u32 *in; int err; + int i; + + inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + sizeof(*mtt) * npages; in = kvzalloc(inlen, GFP_KERNEL); if (!in) @@ -271,6 +276,18 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, MLX5_SET(mkc, mkc, translations_octword_size, MLX5_MTT_OCTW(npages)); MLX5_SET(mkc, mkc, log_page_size, page_shift); + MLX5_SET(create_mkey_in, in, translations_octword_actual_size, + MLX5_MTT_OCTW(npages)); + + /* Initialize the mkey with all MTTs pointing to a default + * page (filler_addr). When the channels are activated, UMR + * WQEs will redirect the RX WQEs to the actual memory from + * the RQ's pool, while the gaps (wqe_overflow) remain mapped + * to the default page. + */ + mtt = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); + for (i = 0 ; i < npages ; i++) + mtt[i].ptag = cpu_to_be64(filler_addr); err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen); @@ -282,7 +299,8 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq { u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->mpwqe.wq)); - return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey); + return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey, + rq->wqe_overflow.addr); } static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix) @@ -350,6 +368,28 @@ static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work) mlx5e_reporter_rq_cqe_err(rq); } +static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq) +{ + rq->wqe_overflow.page = alloc_page(GFP_KERNEL); + if (!rq->wqe_overflow.page) + return -ENOMEM; + + rq->wqe_overflow.addr = dma_map_page(rq->pdev, rq->wqe_overflow.page, 0, + PAGE_SIZE, rq->buff.map_dir); + if (dma_mapping_error(rq->pdev, rq->wqe_overflow.addr)) { + __free_page(rq->wqe_overflow.page); + return -ENOMEM; + } + return 0; +} + +static void mlx5e_free_mpwqe_rq_drop_page(struct mlx5e_rq *rq) +{ + dma_unmap_page(rq->pdev, rq->wqe_overflow.addr, PAGE_SIZE, + rq->buff.map_dir); + __free_page(rq->wqe_overflow.page); +} + static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, @@ -396,7 +436,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq_xdp_ix += params->num_channels * MLX5E_RQ_GROUP_XSK; err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix); if (err < 0) - goto err_rq_wq_destroy; + goto err_rq_xdp_prog; rq->buff.map_dir = params->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk); @@ -407,6 +447,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq, &rq->wq_ctrl); if (err) + goto err_rq_xdp; + + err = mlx5e_alloc_mpwqe_rq_drop_page(rq); + if (err) goto err_rq_wq_destroy; rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR]; @@ -424,18 +468,18 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5e_create_rq_umr_mkey(mdev, rq); if (err) - goto err_rq_wq_destroy; + goto err_rq_drop_page; rq->mkey_be = cpu_to_be32(rq->umr_mkey.key); err = mlx5e_rq_alloc_mpwqe_info(rq, c); if (err) - goto err_free; + goto err_rq_mkey; break; default: /* MLX5_WQ_TYPE_CYCLIC */ err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq, &rq->wq_ctrl); if (err) - goto err_rq_wq_destroy; + goto err_rq_xdp; rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR]; @@ -450,19 +494,19 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->wqe.frags) { err = -ENOMEM; - goto err_free; + goto err_rq_wq_destroy; } err = mlx5e_init_di_list(rq, wq_sz, c->cpu); if (err) - goto err_free; + goto err_rq_frags; rq->mkey_be = c->mkey_be; } err = mlx5e_rq_set_handlers(rq, params, xsk); if (err) - goto err_free; + goto err_free_by_rq_type; if (xsk) { err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, @@ -486,13 +530,13 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (IS_ERR(rq->page_pool)) { err = PTR_ERR(rq->page_pool); rq->page_pool = NULL; - goto err_free; + goto err_free_by_rq_type; } err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_POOL, rq->page_pool); } if (err) - goto err_free; + goto err_free_by_rq_type; for (i = 0; i < wq_sz; i++) { if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { @@ -542,23 +586,27 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, return 0; -err_free: +err_free_by_rq_type: switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kvfree(rq->mpwqe.info); +err_rq_mkey: mlx5_core_destroy_mkey(mdev, &rq->umr_mkey); +err_rq_drop_page: + mlx5e_free_mpwqe_rq_drop_page(rq); break; default: /* MLX5_WQ_TYPE_CYCLIC */ - kvfree(rq->wqe.frags); mlx5e_free_di_list(rq); +err_rq_frags: + kvfree(rq->wqe.frags); } - err_rq_wq_destroy: + mlx5_wq_destroy(&rq->wq_ctrl); +err_rq_xdp: + xdp_rxq_info_unreg(&rq->xdp_rxq); +err_rq_xdp_prog: if (params->xdp_prog) bpf_prog_put(params->xdp_prog); - xdp_rxq_info_unreg(&rq->xdp_rxq); - page_pool_destroy(rq->page_pool); - mlx5_wq_destroy(&rq->wq_ctrl); return err; } @@ -580,6 +628,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kvfree(rq->mpwqe.info); mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey); + mlx5e_free_mpwqe_rq_drop_page(rq); break; default: /* MLX5_WQ_TYPE_CYCLIC */ kvfree(rq->wqe.frags); @@ -4177,6 +4226,21 @@ int mlx5e_get_vf_stats(struct net_device *dev, } #endif +static bool mlx5e_gre_tunnel_inner_proto_offload_supported(struct mlx5_core_dev *mdev, + struct sk_buff *skb) +{ + switch (skb->inner_protocol) { + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + case htons(ETH_P_TEB): + return true; + case htons(ETH_P_MPLS_UC): + case htons(ETH_P_MPLS_MC): + return MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_gre); + } + return false; +} + static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, struct sk_buff *skb, netdev_features_t features) @@ -4199,7 +4263,9 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, switch (proto) { case IPPROTO_GRE: - return features; + if (mlx5e_gre_tunnel_inner_proto_offload_supported(priv->mdev, skb)) + return features; + break; case IPPROTO_IPIP: case IPPROTO_IPV6: if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 622c27ae4ac7..0d1562e20118 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -135,12 +135,6 @@ struct mlx5e_neigh_hash_entry { /* encap list sharing the same neigh */ struct list_head encap_list; - /* valid only when the neigh reference is taken during - * neigh_update_work workqueue callback. - */ - struct neighbour *n; - struct work_struct neigh_update_work; - /* neigh hash entry can be deleted only when the refcount is zero. * refcount is needed to avoid neigh hash entry removal by TC, while * it's used by the neigh notification call. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 31ef9f8420c8..22a19d391e17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -189,6 +189,29 @@ u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq) return count_eqe; } +static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, unsigned long *flags) + __acquires(&eq->lock) +{ + if (in_irq()) + spin_lock(&eq->lock); + else + spin_lock_irqsave(&eq->lock, *flags); +} + +static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, unsigned long *flags) + __releases(&eq->lock) +{ + if (in_irq()) + spin_unlock(&eq->lock); + else + spin_unlock_irqrestore(&eq->lock, *flags); +} + +enum async_eq_nb_action { + ASYNC_EQ_IRQ_HANDLER = 0, + ASYNC_EQ_RECOVER = 1, +}; + static int mlx5_eq_async_int(struct notifier_block *nb, unsigned long action, void *data) { @@ -198,11 +221,14 @@ static int mlx5_eq_async_int(struct notifier_block *nb, struct mlx5_eq_table *eqt; struct mlx5_core_dev *dev; struct mlx5_eqe *eqe; + unsigned long flags; int num_eqes = 0; dev = eq->dev; eqt = dev->priv.eq_table; + mlx5_eq_async_int_lock(eq_async, &flags); + eqe = next_eqe_sw(eq); if (!eqe) goto out; @@ -223,8 +249,19 @@ static int mlx5_eq_async_int(struct notifier_block *nb, out: eq_update_ci(eq, 1); + mlx5_eq_async_int_unlock(eq_async, &flags); - return 0; + return unlikely(action == ASYNC_EQ_RECOVER) ? num_eqes : 0; +} + +void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev) +{ + struct mlx5_eq_async *eq = &dev->priv.eq_table->cmd_eq; + int eqes; + + eqes = mlx5_eq_async_int(&eq->irq_nb, ASYNC_EQ_RECOVER, NULL); + if (eqes) + mlx5_core_warn(dev, "Recovered %d EQEs on cmd_eq\n", eqes); } static void init_eq_buf(struct mlx5_eq *eq) @@ -569,6 +606,7 @@ setup_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq_async *eq, int err; eq->irq_nb.notifier_call = mlx5_eq_async_int; + spin_lock_init(&eq->lock); err = create_async_eq(dev, &eq->core, param); if (err) { @@ -656,8 +694,10 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev) cleanup_async_eq(dev, &table->pages_eq, "pages"); cleanup_async_eq(dev, &table->async_eq, "async"); + mlx5_cmd_allowed_opcode(dev, MLX5_CMD_OP_DESTROY_EQ); mlx5_cmd_use_polling(dev); cleanup_async_eq(dev, &table->cmd_eq, "cmd"); + mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL); mlx5_eq_notifier_unregister(dev, &table->cq_err_nb); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 4aaca7400fb2..5c681e31983b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -37,6 +37,7 @@ struct mlx5_eq { struct mlx5_eq_async { struct mlx5_eq core; struct notifier_block irq_nb; + spinlock_t lock; /* To avoid irq EQ handle races with resiliency flows */ }; struct mlx5_eq_comp { @@ -81,6 +82,7 @@ void mlx5_cq_tasklet_cb(unsigned long data); struct cpumask *mlx5_eq_comp_cpumask(struct mlx5_core_dev *dev, int ix); u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq); +void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev); void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev); void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index f9b798af6335..c0e18f2ade99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -432,7 +432,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, u32 npages; u32 i = 0; - if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR) + if (!mlx5_cmd_is_down(dev)) return mlx5_cmd_exec(dev, in, in_size, out, out_size); /* No hard feelings, we want our pages back! */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 373981a659c7..6fd974920394 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -115,7 +115,7 @@ static int request_irqs(struct mlx5_core_dev *dev, int nvec) return 0; err_request_irq: - for (; i >= 0; i--) { + while (i--) { struct mlx5_irq *irq = mlx5_irq_get(dev, i); int irqn = pci_irq_vector(dev->pdev, i); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 4186e29119c2..f3c0e241e1b4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3690,13 +3690,13 @@ bool mlxsw_sp_port_dev_check(const struct net_device *dev) return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; } -static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data) +static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) { - struct mlxsw_sp_port **p_mlxsw_sp_port = data; int ret = 0; if (mlxsw_sp_port_dev_check(lower_dev)) { - *p_mlxsw_sp_port = netdev_priv(lower_dev); + priv->data = (void *)netdev_priv(lower_dev); ret = 1; } @@ -3705,15 +3705,16 @@ static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data) struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev) { - struct mlxsw_sp_port *mlxsw_sp_port; + struct netdev_nested_priv priv = { + .data = NULL, + }; if (mlxsw_sp_port_dev_check(dev)) return netdev_priv(dev); - mlxsw_sp_port = NULL; - netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &mlxsw_sp_port); + netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &priv); - return mlxsw_sp_port; + return (struct mlxsw_sp_port *)priv.data; } struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) @@ -3726,16 +3727,17 @@ struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev) { - struct mlxsw_sp_port *mlxsw_sp_port; + struct netdev_nested_priv priv = { + .data = NULL, + }; if (mlxsw_sp_port_dev_check(dev)) return netdev_priv(dev); - mlxsw_sp_port = NULL; netdev_walk_all_lower_dev_rcu(dev, mlxsw_sp_lower_dev_walk, - &mlxsw_sp_port); + &priv); - return mlxsw_sp_port; + return (struct mlxsw_sp_port *)priv.data; } struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 5c020403342f..7cccc41dd69c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -292,13 +292,14 @@ mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp_acl_tcam *tcam, int err; group->tcam = tcam; - mutex_init(&group->lock); INIT_LIST_HEAD(&group->region_list); err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id); if (err) return err; + mutex_init(&group->lock); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 24f1fd1f8d56..460cb523312f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -7351,9 +7351,10 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, return err; } -static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, void *data) +static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, + struct netdev_nested_priv *priv) { - struct mlxsw_sp_rif *rif = data; + struct mlxsw_sp_rif *rif = (struct mlxsw_sp_rif *)priv->data; if (!netif_is_macvlan(dev)) return 0; @@ -7364,12 +7365,16 @@ static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, void *data) static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif) { + struct netdev_nested_priv priv = { + .data = (void *)rif, + }; + if (!netif_is_macvlan_port(rif->dev)) return 0; netdev_warn(rif->dev, "Router interface is deleted. Upper macvlans will not work\n"); return netdev_walk_all_upper_dev_rcu(rif->dev, - __mlxsw_sp_rif_macvlan_flush, rif); + __mlxsw_sp_rif_macvlan_flush, &priv); } static void mlxsw_sp_rif_subport_setup(struct mlxsw_sp_rif *rif, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 72912afa6f72..6501ce94ace5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -136,9 +136,9 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_bridge_device_upper_rif_destroy(struct net_device *dev, - void *data) + struct netdev_nested_priv *priv) { - struct mlxsw_sp *mlxsw_sp = data; + struct mlxsw_sp *mlxsw_sp = priv->data; mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev); return 0; @@ -147,10 +147,14 @@ static int mlxsw_sp_bridge_device_upper_rif_destroy(struct net_device *dev, static void mlxsw_sp_bridge_device_rifs_destroy(struct mlxsw_sp *mlxsw_sp, struct net_device *dev) { + struct netdev_nested_priv priv = { + .data = (void *)mlxsw_sp, + }; + mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev); netdev_walk_all_upper_dev_rcu(dev, mlxsw_sp_bridge_device_upper_rif_destroy, - mlxsw_sp); + &priv); } static int mlxsw_sp_bridge_device_vxlan_init(struct mlxsw_sp_bridge *bridge, diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 8518e1d60da4..aa002db04250 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1253,7 +1253,7 @@ void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu) struct ocelot_port *ocelot_port = ocelot->ports[port]; int maxlen = sdu + ETH_HLEN + ETH_FCS_LEN; int pause_start, pause_stop; - int atop_wm; + int atop, atop_tot; if (port == ocelot->npi) { maxlen += OCELOT_TAG_LEN; @@ -1274,12 +1274,12 @@ void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu) ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_STOP, pause_stop); - /* Tail dropping watermark */ - atop_wm = (ocelot->shared_queue_sz - 9 * maxlen) / + /* Tail dropping watermarks */ + atop_tot = (ocelot->shared_queue_sz - 9 * maxlen) / OCELOT_BUFFER_CELL_SZ; - ocelot_write_rix(ocelot, ocelot->ops->wm_enc(9 * maxlen), - SYS_ATOP, port); - ocelot_write(ocelot, ocelot->ops->wm_enc(atop_wm), SYS_ATOP_TOT_CFG); + atop = (9 * maxlen) / OCELOT_BUFFER_CELL_SZ; + ocelot_write_rix(ocelot, ocelot->ops->wm_enc(atop), SYS_ATOP, port); + ocelot_write(ocelot, ocelot->ops->wm_enc(atop_tot), SYS_ATOP_TOT_CFG); } EXPORT_SYMBOL(ocelot_port_set_maxlen); diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index dfb1535f26f2..8a6917691ba6 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -745,6 +745,8 @@ static int ocelot_reset(struct ocelot *ocelot) */ static u16 ocelot_wm_enc(u16 value) { + WARN_ON(value >= 16 * BIT(8)); + if (value >= BIT(8)) return BIT(8) | (value / 16); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index fc9e6626db55..11e6962a18e4 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2058,11 +2058,18 @@ static void rtl_release_firmware(struct rtl8169_private *tp) void r8169_apply_firmware(struct rtl8169_private *tp) { + int val; + /* TODO: release firmware if rtl_fw_write_firmware signals failure. */ if (tp->rtl_fw) { rtl_fw_write_firmware(tp, tp->rtl_fw); /* At least one firmware doesn't reset tp->ocp_base. */ tp->ocp_base = OCP_STD_PHY_BASE; + + /* PHY soft reset may still be in progress */ + phy_read_poll_timeout(tp->phydev, MII_BMCR, val, + !(val & BMCR_RESET), + 50000, 600000, true); } } @@ -2239,14 +2246,10 @@ static void rtl_pll_power_down(struct rtl8169_private *tp) default: break; } - - clk_disable_unprepare(tp->clk); } static void rtl_pll_power_up(struct rtl8169_private *tp) { - clk_prepare_enable(tp->clk); - switch (tp->mac_version) { case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33: case RTL_GIGA_MAC_VER_37: @@ -2904,7 +2907,7 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp) { 0x08, 0x0001, 0x0002 }, { 0x09, 0x0000, 0x0080 }, { 0x19, 0x0000, 0x0224 }, - { 0x00, 0x0000, 0x0004 }, + { 0x00, 0x0000, 0x0008 }, { 0x0c, 0x3df0, 0x0200 }, }; @@ -2921,7 +2924,7 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp) { 0x06, 0x00c0, 0x0020 }, { 0x0f, 0xffff, 0x5200 }, { 0x19, 0x0000, 0x0224 }, - { 0x00, 0x0000, 0x0004 }, + { 0x00, 0x0000, 0x0008 }, { 0x0c, 0x3df0, 0x0200 }, }; @@ -4826,29 +4829,43 @@ static void rtl8169_net_suspend(struct rtl8169_private *tp) #ifdef CONFIG_PM +static int rtl8169_net_resume(struct rtl8169_private *tp) +{ + rtl_rar_set(tp, tp->dev->dev_addr); + + if (tp->TxDescArray) + rtl8169_up(tp); + + netif_device_attach(tp->dev); + + return 0; +} + static int __maybe_unused rtl8169_suspend(struct device *device) { struct rtl8169_private *tp = dev_get_drvdata(device); rtnl_lock(); rtl8169_net_suspend(tp); + if (!device_may_wakeup(tp_to_dev(tp))) + clk_disable_unprepare(tp->clk); rtnl_unlock(); return 0; } -static int rtl8169_resume(struct device *device) +static int __maybe_unused rtl8169_resume(struct device *device) { struct rtl8169_private *tp = dev_get_drvdata(device); - rtl_rar_set(tp, tp->dev->dev_addr); + if (!device_may_wakeup(tp_to_dev(tp))) + clk_prepare_enable(tp->clk); - if (tp->TxDescArray) - rtl8169_up(tp); + /* Reportedly at least Asus X453MA truncates packets otherwise */ + if (tp->mac_version == RTL_GIGA_MAC_VER_37) + rtl_init_rxcfg(tp); - netif_device_attach(tp->dev); - - return 0; + return rtl8169_net_resume(tp); } static int rtl8169_runtime_suspend(struct device *device) @@ -4874,7 +4891,7 @@ static int rtl8169_runtime_resume(struct device *device) __rtl8169_set_wol(tp, tp->saved_wolopts); - return rtl8169_resume(device); + return rtl8169_net_resume(tp); } static int rtl8169_runtime_idle(struct device *device) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index df89d09b253e..99f7aae102ce 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1342,51 +1342,6 @@ static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler, return error; } -/* MDIO bus init function */ -static int ravb_mdio_init(struct ravb_private *priv) -{ - struct platform_device *pdev = priv->pdev; - struct device *dev = &pdev->dev; - int error; - - /* Bitbang init */ - priv->mdiobb.ops = &bb_ops; - - /* MII controller setting */ - priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb); - if (!priv->mii_bus) - return -ENOMEM; - - /* Hook up MII support for ethtool */ - priv->mii_bus->name = "ravb_mii"; - priv->mii_bus->parent = dev; - snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", - pdev->name, pdev->id); - - /* Register MDIO bus */ - error = of_mdiobus_register(priv->mii_bus, dev->of_node); - if (error) - goto out_free_bus; - - return 0; - -out_free_bus: - free_mdio_bitbang(priv->mii_bus); - return error; -} - -/* MDIO bus release function */ -static int ravb_mdio_release(struct ravb_private *priv) -{ - /* Unregister mdio bus */ - mdiobus_unregister(priv->mii_bus); - - /* Free bitbang info */ - free_mdio_bitbang(priv->mii_bus); - - return 0; -} - /* Network device open function for Ethernet AVB */ static int ravb_open(struct net_device *ndev) { @@ -1395,13 +1350,6 @@ static int ravb_open(struct net_device *ndev) struct device *dev = &pdev->dev; int error; - /* MDIO bus init */ - error = ravb_mdio_init(priv); - if (error) { - netdev_err(ndev, "failed to initialize MDIO\n"); - return error; - } - napi_enable(&priv->napi[RAVB_BE]); napi_enable(&priv->napi[RAVB_NC]); @@ -1479,7 +1427,6 @@ out_free_irq: out_napi_off: napi_disable(&priv->napi[RAVB_NC]); napi_disable(&priv->napi[RAVB_BE]); - ravb_mdio_release(priv); return error; } @@ -1789,8 +1736,6 @@ static int ravb_close(struct net_device *ndev) ravb_ring_free(ndev, RAVB_BE); ravb_ring_free(ndev, RAVB_NC); - ravb_mdio_release(priv); - return 0; } @@ -1942,6 +1887,51 @@ static const struct net_device_ops ravb_netdev_ops = { .ndo_set_features = ravb_set_features, }; +/* MDIO bus init function */ +static int ravb_mdio_init(struct ravb_private *priv) +{ + struct platform_device *pdev = priv->pdev; + struct device *dev = &pdev->dev; + int error; + + /* Bitbang init */ + priv->mdiobb.ops = &bb_ops; + + /* MII controller setting */ + priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb); + if (!priv->mii_bus) + return -ENOMEM; + + /* Hook up MII support for ethtool */ + priv->mii_bus->name = "ravb_mii"; + priv->mii_bus->parent = dev; + snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", + pdev->name, pdev->id); + + /* Register MDIO bus */ + error = of_mdiobus_register(priv->mii_bus, dev->of_node); + if (error) + goto out_free_bus; + + return 0; + +out_free_bus: + free_mdio_bitbang(priv->mii_bus); + return error; +} + +/* MDIO bus release function */ +static int ravb_mdio_release(struct ravb_private *priv) +{ + /* Unregister mdio bus */ + mdiobus_unregister(priv->mii_bus); + + /* Free bitbang info */ + free_mdio_bitbang(priv->mii_bus); + + return 0; +} + static const struct of_device_id ravb_match_table[] = { { .compatible = "renesas,etheravb-r8a7790", .data = (void *)RCAR_GEN2 }, { .compatible = "renesas,etheravb-r8a7794", .data = (void *)RCAR_GEN2 }, @@ -2184,6 +2174,13 @@ static int ravb_probe(struct platform_device *pdev) eth_hw_addr_random(ndev); } + /* MDIO bus init */ + error = ravb_mdio_init(priv); + if (error) { + dev_err(&pdev->dev, "failed to initialize MDIO\n"); + goto out_dma_free; + } + netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64); netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64); @@ -2205,6 +2202,8 @@ static int ravb_probe(struct platform_device *pdev) out_napi_del: netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); + ravb_mdio_release(priv); +out_dma_free: dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat, priv->desc_bat_dma); @@ -2236,6 +2235,7 @@ static int ravb_remove(struct platform_device *pdev) unregister_netdev(ndev); netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); + ravb_mdio_release(priv); pm_runtime_disable(&pdev->dev); free_netdev(ndev); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 42458a46ffaf..9cc31f7e0df1 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -3099,9 +3099,10 @@ struct rocker_walk_data { struct rocker_port *port; }; -static int rocker_lower_dev_walk(struct net_device *lower_dev, void *_data) +static int rocker_lower_dev_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) { - struct rocker_walk_data *data = _data; + struct rocker_walk_data *data = (struct rocker_walk_data *)priv->data; int ret = 0; if (rocker_port_dev_check_under(lower_dev, data->rocker)) { @@ -3115,6 +3116,7 @@ static int rocker_lower_dev_walk(struct net_device *lower_dev, void *_data) struct rocker_port *rocker_port_dev_lower_find(struct net_device *dev, struct rocker *rocker) { + struct netdev_nested_priv priv; struct rocker_walk_data data; if (rocker_port_dev_check_under(dev, rocker)) @@ -3122,7 +3124,8 @@ struct rocker_port *rocker_port_dev_lower_find(struct net_device *dev, data.rocker = rocker; data.port = NULL; - netdev_walk_all_lower_dev(dev, rocker_lower_dev_walk, &data); + priv.data = (void *)&data; + netdev_walk_all_lower_dev(dev, rocker_lower_dev_walk, &priv); return data.port; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 2ac9dfb3462c..9e6d60e75f85 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -653,7 +653,6 @@ static void intel_eth_pci_remove(struct pci_dev *pdev) pci_free_irq_vectors(pdev); - clk_disable_unprepare(priv->plat->stmmac_clk); clk_unregister_fixed_rate(priv->plat->stmmac_clk); pcim_iounmap_regions(pdev, BIT(0)); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 9c02fc754bf1..545696971f65 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -203,6 +203,8 @@ struct stmmac_priv { int eee_enabled; int eee_active; int tx_lpi_timer; + int tx_lpi_enabled; + int eee_tw_timer; unsigned int mode; unsigned int chain_mode; int extend_desc; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index ac5e8cc5fb9f..814879f91f76 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -665,6 +665,7 @@ static int stmmac_ethtool_op_get_eee(struct net_device *dev, edata->eee_enabled = priv->eee_enabled; edata->eee_active = priv->eee_active; edata->tx_lpi_timer = priv->tx_lpi_timer; + edata->tx_lpi_enabled = priv->tx_lpi_enabled; return phylink_ethtool_get_eee(priv->phylink, edata); } @@ -675,24 +676,26 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, struct stmmac_priv *priv = netdev_priv(dev); int ret; - if (!edata->eee_enabled) { + if (!priv->dma_cap.eee) + return -EOPNOTSUPP; + + if (priv->tx_lpi_enabled != edata->tx_lpi_enabled) + netdev_warn(priv->dev, + "Setting EEE tx-lpi is not supported\n"); + + if (!edata->eee_enabled) stmmac_disable_eee_mode(priv); - } else { - /* We are asking for enabling the EEE but it is safe - * to verify all by invoking the eee_init function. - * In case of failure it will return an error. - */ - edata->eee_enabled = stmmac_eee_init(priv); - if (!edata->eee_enabled) - return -EOPNOTSUPP; - } ret = phylink_ethtool_set_eee(priv->phylink, edata); if (ret) return ret; - priv->eee_enabled = edata->eee_enabled; - priv->tx_lpi_timer = edata->tx_lpi_timer; + if (edata->eee_enabled && + priv->tx_lpi_timer != edata->tx_lpi_timer) { + priv->tx_lpi_timer = edata->tx_lpi_timer; + stmmac_eee_init(priv); + } + return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 89b2b3472852..b56b13d64ab4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -94,7 +94,7 @@ static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE | static int eee_timer = STMMAC_DEFAULT_LPI_TIMER; module_param(eee_timer, int, 0644); MODULE_PARM_DESC(eee_timer, "LPI tx expiration time in msec"); -#define STMMAC_LPI_T(x) (jiffies + msecs_to_jiffies(x)) +#define STMMAC_LPI_T(x) (jiffies + usecs_to_jiffies(x)) /* By default the driver will use the ring mode to manage tx and rx descriptors, * but allow user to force to use the chain instead of the ring @@ -370,7 +370,7 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t) struct stmmac_priv *priv = from_timer(priv, t, eee_ctrl_timer); stmmac_enable_eee_mode(priv); - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer)); + mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); } /** @@ -383,7 +383,7 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t) */ bool stmmac_eee_init(struct stmmac_priv *priv) { - int tx_lpi_timer = priv->tx_lpi_timer; + int eee_tw_timer = priv->eee_tw_timer; /* Using PCS we cannot dial with the phy registers at this stage * so we do not support extra feature like EEE. @@ -403,7 +403,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv) if (priv->eee_enabled) { netdev_dbg(priv->dev, "disable EEE\n"); del_timer_sync(&priv->eee_ctrl_timer); - stmmac_set_eee_timer(priv, priv->hw, 0, tx_lpi_timer); + stmmac_set_eee_timer(priv, priv->hw, 0, eee_tw_timer); } mutex_unlock(&priv->lock); return false; @@ -411,11 +411,12 @@ bool stmmac_eee_init(struct stmmac_priv *priv) if (priv->eee_active && !priv->eee_enabled) { timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0); - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer)); stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS, - tx_lpi_timer); + eee_tw_timer); } + mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); + mutex_unlock(&priv->lock); netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n"); return true; @@ -930,6 +931,7 @@ static void stmmac_mac_link_down(struct phylink_config *config, stmmac_mac_set(priv, priv->ioaddr, false); priv->eee_active = false; + priv->tx_lpi_enabled = false; stmmac_eee_init(priv); stmmac_set_eee_pls(priv, priv->hw, false); } @@ -1027,6 +1029,7 @@ static void stmmac_mac_link_up(struct phylink_config *config, if (phy && priv->dma_cap.eee) { priv->eee_active = phy_init_eee(phy, 1) >= 0; priv->eee_enabled = stmmac_eee_init(priv); + priv->tx_lpi_enabled = priv->eee_enabled; stmmac_set_eee_pls(priv, priv->hw, true); } } @@ -2061,7 +2064,7 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) { stmmac_enable_eee_mode(priv); - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer)); + mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); } /* We still have pending packets, let's call for a new scheduling */ @@ -2694,7 +2697,11 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) netdev_warn(priv->dev, "PTP init failed\n"); } - priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS; + priv->eee_tw_timer = STMMAC_DEFAULT_TWT_LS; + + /* Convert the timer from msec to usec */ + if (!priv->tx_lpi_timer) + priv->tx_lpi_timer = eee_timer * 1000; if (priv->use_riwt) { if (!priv->rx_riwt) diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 803247d51fe9..55b0ddab1776 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -2,7 +2,7 @@ /* Written 1998-2001 by Donald Becker. - Current Maintainer: Roger Luethi <[email protected]> + Current Maintainer: Kevin Brace <[email protected]> This software may be used and distributed according to the terms of the GNU General Public License (GPL), incorporated herein by reference. @@ -32,8 +32,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "via-rhine" -#define DRV_VERSION "1.5.1" -#define DRV_RELDATE "2010-10-09" #include <linux/types.h> @@ -117,10 +115,6 @@ static const int multicast_filter_limit = 32; #include <linux/uaccess.h> #include <linux/dmi.h> -/* These identify the driver base version and may not be removed. */ -static const char version[] = - "v1.10-LK" DRV_VERSION " " DRV_RELDATE " Written by Donald Becker"; - MODULE_AUTHOR("Donald Becker <[email protected]>"); MODULE_DESCRIPTION("VIA Rhine PCI Fast Ethernet driver"); MODULE_LICENSE("GPL"); @@ -243,7 +237,7 @@ enum rhine_revs { VT8233 = 0x60, /* Integrated MAC */ VT8235 = 0x74, /* Integrated MAC */ VT8237 = 0x78, /* Integrated MAC */ - VTunknown1 = 0x7C, + VT8251 = 0x7C, /* Integrated MAC */ VT6105 = 0x80, VT6105_B0 = 0x83, VT6105L = 0x8A, @@ -1051,11 +1045,6 @@ static int rhine_init_one_pci(struct pci_dev *pdev, u32 quirks = 0; #endif -/* when built into the kernel, we only print version if device is found */ -#ifndef MODULE - pr_info_once("%s\n", version); -#endif - rc = pci_enable_device(pdev); if (rc) goto err_out; @@ -1706,6 +1695,8 @@ static int rhine_open(struct net_device *dev) goto out_free_ring; alloc_tbufs(dev); + enable_mmio(rp->pioaddr, rp->quirks); + rhine_power_init(dev); rhine_chip_reset(dev); rhine_task_enable(rp); init_registers(dev); @@ -2294,7 +2285,6 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i struct device *hwdev = dev->dev.parent; strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, dev_name(hwdev), sizeof(info->bus_info)); } @@ -2616,9 +2606,6 @@ static int __init rhine_init(void) int ret_pci, ret_platform; /* when a module, this is printed whether or not devices are found in probe */ -#ifdef MODULE - pr_info("%s\n", version); -#endif if (dmi_check_system(rhine_dmi_table)) { /* these BIOSes fail at PXE boot if chip is in D3 */ avoid_D3 = true; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 9159846b8b93..787ac2c8e74e 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1077,6 +1077,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) struct macsec_rx_sa *rx_sa; struct macsec_rxh_data *rxd; struct macsec_dev *macsec; + unsigned int len; sci_t sci; u32 hdr_pn; bool cbit; @@ -1232,9 +1233,10 @@ deliver: macsec_rxsc_put(rx_sc); skb_orphan(skb); + len = skb->len; ret = gro_cells_receive(&macsec->gro_cells, skb); if (ret == NET_RX_SUCCESS) - count_rx(dev, skb->len); + count_rx(dev, len); else macsec->secy.netdev->stats.rx_dropped++; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 726e4b240e7e..1c5a10b672fc 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -222,6 +222,7 @@ config MDIO_THUNDER depends on 64BIT depends on PCI select MDIO_CAVIUM + select MDIO_DEVRES help This driver supports the MDIO interfaces found on Cavium ThunderX SoCs when the MDIO bus device appears as a PCI diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 95dbe5e8e1d8..0f0960971800 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0+ -/* - * drivers/net/phy/realtek.c +/* drivers/net/phy/realtek.c * * Driver for Realtek PHYs * @@ -32,9 +31,9 @@ #define RTL8211F_TX_DELAY BIT(8) #define RTL8211F_RX_DELAY BIT(3) -#define RTL8211E_TX_DELAY BIT(1) -#define RTL8211E_RX_DELAY BIT(2) -#define RTL8211E_MODE_MII_GMII BIT(3) +#define RTL8211E_CTRL_DELAY BIT(13) +#define RTL8211E_TX_DELAY BIT(12) +#define RTL8211E_RX_DELAY BIT(11) #define RTL8201F_ISR 0x1e #define RTL8201F_IER 0x13 @@ -246,16 +245,16 @@ static int rtl8211e_config_init(struct phy_device *phydev) /* enable TX/RX delay for rgmii-* modes, and disable them for rgmii. */ switch (phydev->interface) { case PHY_INTERFACE_MODE_RGMII: - val = 0; + val = RTL8211E_CTRL_DELAY | 0; break; case PHY_INTERFACE_MODE_RGMII_ID: - val = RTL8211E_TX_DELAY | RTL8211E_RX_DELAY; + val = RTL8211E_CTRL_DELAY | RTL8211E_TX_DELAY | RTL8211E_RX_DELAY; break; case PHY_INTERFACE_MODE_RGMII_RXID: - val = RTL8211E_RX_DELAY; + val = RTL8211E_CTRL_DELAY | RTL8211E_RX_DELAY; break; case PHY_INTERFACE_MODE_RGMII_TXID: - val = RTL8211E_TX_DELAY; + val = RTL8211E_CTRL_DELAY | RTL8211E_TX_DELAY; break; default: /* the rest of the modes imply leaving delays as is. */ return 0; @@ -263,11 +262,12 @@ static int rtl8211e_config_init(struct phy_device *phydev) /* According to a sample driver there is a 0x1c config register on the * 0xa4 extension page (0x7) layout. It can be used to disable/enable - * the RX/TX delays otherwise controlled by RXDLY/TXDLY pins. It can - * also be used to customize the whole configuration register: - * 8:6 = PHY Address, 5:4 = Auto-Negotiation, 3 = Interface Mode Select, - * 2 = RX Delay, 1 = TX Delay, 0 = SELRGV (see original PHY datasheet - * for details). + * the RX/TX delays otherwise controlled by RXDLY/TXDLY pins. + * The configuration register definition: + * 14 = reserved + * 13 = Force Tx RX Delay controlled by bit12 bit11, + * 12 = RX Delay, 11 = TX Delay + * 10:0 = Test && debug settings reserved by realtek */ oldpage = phy_select_page(phydev, 0x7); if (oldpage < 0) @@ -277,7 +277,8 @@ static int rtl8211e_config_init(struct phy_device *phydev) if (ret) goto err_restore_page; - ret = __phy_modify(phydev, 0x1c, RTL8211E_TX_DELAY | RTL8211E_RX_DELAY, + ret = __phy_modify(phydev, 0x1c, RTL8211E_CTRL_DELAY + | RTL8211E_TX_DELAY | RTL8211E_RX_DELAY, val); err_restore_page: diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 8c1e02752ff6..bcc4a4c011f1 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -287,7 +287,7 @@ inst_rollback: for (i--; i >= 0; i--) __team_option_inst_del_option(team, dst_opts[i]); - i = option_count - 1; + i = option_count; alloc_rollback: for (i--; i >= 0; i--) kfree(dst_opts[i]); @@ -2112,6 +2112,7 @@ static void team_setup_by_port(struct net_device *dev, dev->header_ops = port_dev->header_ops; dev->type = port_dev->type; dev->hard_header_len = port_dev->hard_header_len; + dev->needed_headroom = port_dev->needed_headroom; dev->addr_len = port_dev->addr_len; dev->mtu = port_dev->mtu; memcpy(dev->broadcast, port_dev->broadcast, port_dev->addr_len); diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index a38e868e44d4..5541f3faedbc 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1823,6 +1823,33 @@ static const struct driver_info belkin_info = { .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_reset, + .stop = ax88179_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + +static const struct driver_info toshiba_info = { + .description = "Toshiba USB Ethernet Adapter", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .stop = ax88179_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + +static const struct driver_info mct_info = { + .description = "MCT USB 3.0 Gigabit Ethernet Adapter", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, @@ -1861,6 +1888,14 @@ static const struct usb_device_id products[] = { /* Belkin B2B128 USB 3.0 Hub + Gigabit Ethernet Adapter */ USB_DEVICE(0x050d, 0x0128), .driver_info = (unsigned long)&belkin_info, +}, { + /* Toshiba USB 3.0 GBit Ethernet Adapter */ + USB_DEVICE(0x0930, 0x0a13), + .driver_info = (unsigned long)&toshiba_info, +}, { + /* Magic Control Technology U3-A9003 USB 3.0 Gigabit Ethernet Adapter */ + USB_DEVICE(0x0711, 0x0179), + .driver_info = (unsigned long)&mct_info, }, { }, }; diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index e92cb51a2c77..060a8a03e6c4 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -360,28 +360,47 @@ fail: } #endif /* PEGASUS_WRITE_EEPROM */ -static inline void get_node_id(pegasus_t *pegasus, __u8 *id) +static inline int get_node_id(pegasus_t *pegasus, u8 *id) { - int i; - __u16 w16; + int i, ret; + u16 w16; for (i = 0; i < 3; i++) { - read_eprom_word(pegasus, i, &w16); + ret = read_eprom_word(pegasus, i, &w16); + if (ret < 0) + return ret; ((__le16 *) id)[i] = cpu_to_le16(w16); } + + return 0; } static void set_ethernet_addr(pegasus_t *pegasus) { - __u8 node_id[6]; + int ret; + u8 node_id[6]; if (pegasus->features & PEGASUS_II) { - get_registers(pegasus, 0x10, sizeof(node_id), node_id); + ret = get_registers(pegasus, 0x10, sizeof(node_id), node_id); + if (ret < 0) + goto err; } else { - get_node_id(pegasus, node_id); - set_registers(pegasus, EthID, sizeof(node_id), node_id); + ret = get_node_id(pegasus, node_id); + if (ret < 0) + goto err; + ret = set_registers(pegasus, EthID, sizeof(node_id), node_id); + if (ret < 0) + goto err; } + memcpy(pegasus->net->dev_addr, node_id, sizeof(node_id)); + + return; +err: + eth_hw_addr_random(pegasus->net); + dev_info(&pegasus->intf->dev, "software assigned MAC address.\n"); + + return; } static inline int reset_mac(pegasus_t *pegasus) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 07c42c0719f5..5ca1356b8656 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1375,6 +1375,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ + {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 733f120c852b..9d079dc2a535 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -274,12 +274,20 @@ static int write_mii_word(rtl8150_t * dev, u8 phy, __u8 indx, u16 reg) return 1; } -static inline void set_ethernet_addr(rtl8150_t * dev) +static void set_ethernet_addr(rtl8150_t *dev) { - u8 node_id[6]; + u8 node_id[ETH_ALEN]; + int ret; + + ret = get_registers(dev, IDR, sizeof(node_id), node_id); - get_registers(dev, IDR, sizeof(node_id), node_id); - memcpy(dev->netdev->dev_addr, node_id, sizeof(node_id)); + if (ret == sizeof(node_id)) { + ether_addr_copy(dev->netdev->dev_addr, node_id); + } else { + eth_hw_addr_random(dev->netdev); + netdev_notice(dev->netdev, "Assigned a random MAC address: %pM\n", + dev->netdev->dev_addr); + } } static int rtl8150_set_mac_address(struct net_device *netdev, void *p) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 263b005981bd..668685c09e65 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -63,6 +63,11 @@ static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_CSUM }; +#define GUEST_OFFLOAD_LRO_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \ + (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \ + (1ULL << VIRTIO_NET_F_GUEST_ECN) | \ + (1ULL << VIRTIO_NET_F_GUEST_UFO)) + struct virtnet_stat_desc { char desc[ETH_GSTRING_LEN]; size_t offset; @@ -2531,7 +2536,8 @@ static int virtnet_set_features(struct net_device *dev, if (features & NETIF_F_LRO) offloads = vi->guest_offloads_capable; else - offloads = 0; + offloads = vi->guest_offloads_capable & + ~GUEST_OFFLOAD_LRO_MASK; err = virtnet_set_guest_offloads(vi, offloads); if (err) diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 2818015324b8..336504b7531d 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1032,7 +1032,6 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, /* Use temporary descriptor to avoid touching bits multiple times */ union Vmxnet3_GenericDesc tempTxDesc; #endif - struct udphdr *udph; count = txd_estimate(skb); @@ -1135,8 +1134,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, gdesc->txd.om = VMXNET3_OM_ENCAP; gdesc->txd.msscof = ctx.mss; - udph = udp_hdr(skb); - if (udph->check) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) gdesc->txd.oco = 1; } else { gdesc->txd.hlen = ctx.l4_offset + ctx.l4_hdr_size; @@ -3371,6 +3369,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, .ndo_change_mtu = vmxnet3_change_mtu, .ndo_fix_features = vmxnet3_fix_features, .ndo_set_features = vmxnet3_set_features, + .ndo_features_check = vmxnet3_features_check, .ndo_get_stats64 = vmxnet3_get_stats64, .ndo_tx_timeout = vmxnet3_tx_timeout, .ndo_set_rx_mode = vmxnet3_set_mc, diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index 1014693a5ceb..7ec8652f2c26 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -267,6 +267,34 @@ netdev_features_t vmxnet3_fix_features(struct net_device *netdev, return features; } +netdev_features_t vmxnet3_features_check(struct sk_buff *skb, + struct net_device *netdev, + netdev_features_t features) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + /* Validate if the tunneled packet is being offloaded by the device */ + if (VMXNET3_VERSION_GE_4(adapter) && + skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) { + u8 l4_proto = 0; + + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_IP): + l4_proto = ip_hdr(skb)->protocol; + break; + case htons(ETH_P_IPV6): + l4_proto = ipv6_hdr(skb)->nexthdr; + break; + default: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + + if (l4_proto != IPPROTO_UDP) + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + return features; +} + static void vmxnet3_enable_encap_offloads(struct net_device *netdev) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 5d2b062215a2..d958b92c9429 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -470,6 +470,10 @@ vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter); netdev_features_t vmxnet3_fix_features(struct net_device *netdev, netdev_features_t features); +netdev_features_t +vmxnet3_features_check(struct sk_buff *skb, + struct net_device *netdev, netdev_features_t features); + int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features); diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index 7ee980575208..c418767a890a 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -464,7 +464,6 @@ static int x25_asy_open(struct net_device *dev) { struct x25_asy *sl = netdev_priv(dev); unsigned long len; - int err; if (sl->tty == NULL) return -ENODEV; @@ -490,14 +489,7 @@ static int x25_asy_open(struct net_device *dev) sl->xleft = 0; sl->flags &= (1 << SLF_INUSE); /* Clear ESCAPE & ERROR flags */ - netif_start_queue(dev); - - /* - * Now attach LAPB - */ - err = lapb_register(dev, &x25_asy_callbacks); - if (err == LAPB_OK) - return 0; + return 0; /* Cleanup */ kfree(sl->xbuff); @@ -519,7 +511,6 @@ static int x25_asy_close(struct net_device *dev) if (sl->tty) clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags); - netif_stop_queue(dev); sl->rcount = 0; sl->xleft = 0; spin_unlock(&sl->lock); @@ -604,7 +595,6 @@ static int x25_asy_open_tty(struct tty_struct *tty) static void x25_asy_close_tty(struct tty_struct *tty) { struct x25_asy *sl = tty->disc_data; - int err; /* First make sure we're connected. */ if (!sl || sl->magic != X25_ASY_MAGIC) @@ -615,11 +605,6 @@ static void x25_asy_close_tty(struct tty_struct *tty) dev_close(sl->dev); rtnl_unlock(); - err = lapb_unregister(sl->dev); - if (err != LAPB_OK) - pr_err("%s: lapb_unregister error: %d\n", - __func__, err); - tty->disc_data = NULL; sl->tty = NULL; x25_asy_free(sl); @@ -722,15 +707,39 @@ static int x25_asy_ioctl(struct tty_struct *tty, struct file *file, static int x25_asy_open_dev(struct net_device *dev) { + int err; struct x25_asy *sl = netdev_priv(dev); if (sl->tty == NULL) return -ENODEV; + + err = lapb_register(dev, &x25_asy_callbacks); + if (err != LAPB_OK) + return -ENOMEM; + + netif_start_queue(dev); + + return 0; +} + +static int x25_asy_close_dev(struct net_device *dev) +{ + int err; + + netif_stop_queue(dev); + + err = lapb_unregister(dev); + if (err != LAPB_OK) + pr_err("%s: lapb_unregister error: %d\n", + __func__, err); + + x25_asy_close(dev); + return 0; } static const struct net_device_ops x25_asy_netdev_ops = { .ndo_open = x25_asy_open_dev, - .ndo_stop = x25_asy_close, + .ndo_stop = x25_asy_close_dev, .ndo_start_xmit = x25_asy_xmit, .ndo_tx_timeout = x25_asy_timeout, .ndo_change_mtu = x25_asy_change_mtu, diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c index fc1ebabfebac..1f57b43693bc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c @@ -460,7 +460,7 @@ void mt7615_init_device(struct mt7615_dev *dev) dev->mphy.sband_2g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING; dev->mphy.sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING; dev->mphy.sband_5g.sband.vht_cap.cap |= - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | + IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 | IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; mt7615_cap_dbdc_disable(dev); dev->phy.dfs_state = -1; diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.c b/drivers/net/wireless/quantenna/qtnfmac/core.c index 6aafff9d4231..e013ebe3079c 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/core.c +++ b/drivers/net/wireless/quantenna/qtnfmac/core.c @@ -671,9 +671,10 @@ bool qtnf_netdev_is_qtn(const struct net_device *ndev) return ndev->netdev_ops == &qtnf_netdev_ops; } -static int qtnf_check_br_ports(struct net_device *dev, void *data) +static int qtnf_check_br_ports(struct net_device *dev, + struct netdev_nested_priv *priv) { - struct net_device *ndev = data; + struct net_device *ndev = (struct net_device *)priv->data; if (dev != ndev && netdev_port_same_parent_id(dev, ndev)) return -ENOTSUPP; @@ -686,6 +687,9 @@ static int qtnf_core_netdevice_event(struct notifier_block *nb, { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); const struct netdev_notifier_changeupper_info *info; + struct netdev_nested_priv priv = { + .data = (void *)ndev, + }; struct net_device *brdev; struct qtnf_vif *vif; struct qtnf_bus *bus; @@ -725,7 +729,7 @@ static int qtnf_core_netdevice_event(struct notifier_block *nb, } else { ret = netdev_walk_all_lower_dev(brdev, qtnf_check_br_ports, - ndev); + &priv); } break; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 8f9d61e0729f..893e29624c16 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3265,8 +3265,10 @@ static int nvme_dev_open(struct inode *inode, struct file *file) } nvme_get_ctrl(ctrl); - if (!try_module_get(ctrl->ops->module)) + if (!try_module_get(ctrl->ops->module)) { + nvme_put_ctrl(ctrl); return -EINVAL; + } file->private_data = ctrl; return 0; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 8f4f29f18b8c..d6a3e1487354 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -913,12 +913,11 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) else flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST; - /* can't zcopy slab pages */ - if (unlikely(PageSlab(page))) { - ret = sock_no_sendpage(queue->sock, page, offset, len, + if (sendpage_ok(page)) { + ret = kernel_sendpage(queue->sock, page, offset, len, flags); } else { - ret = kernel_sendpage(queue->sock, page, offset, len, + ret = sock_no_sendpage(queue->sock, page, offset, len, flags); } if (ret <= 0) diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c index 0bb2fb3e8a0b..9705059523a6 100644 --- a/drivers/pci/controller/pcie-rockchip-host.c +++ b/drivers/pci/controller/pcie-rockchip-host.c @@ -71,16 +71,13 @@ static void rockchip_pcie_update_txcredit_mui(struct rockchip_pcie *rockchip) static int rockchip_pcie_valid_device(struct rockchip_pcie *rockchip, struct pci_bus *bus, int dev) { - /* access only one slot on each root port */ - if (pci_is_root_bus(bus) && dev > 0) - return 0; - /* - * do not read more than one device on the bus directly attached + * Access only one slot on each root port. + * Do not read more than one device on the bus directly attached * to RC's downstream side. */ - if (pci_is_root_bus(bus->parent) && dev > 0) - return 0; + if (pci_is_root_bus(bus) || pci_is_root_bus(bus->parent)) + return dev == 0; return 1; } diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c index a174b3c3f010..819c49af169a 100644 --- a/drivers/phy/ti/phy-am654-serdes.c +++ b/drivers/phy/ti/phy-am654-serdes.c @@ -725,8 +725,10 @@ static int serdes_am654_probe(struct platform_device *pdev) pm_runtime_enable(dev); phy = devm_phy_create(dev, NULL, &ops); - if (IS_ERR(phy)) - return PTR_ERR(phy); + if (IS_ERR(phy)) { + ret = PTR_ERR(phy); + goto clk_err; + } phy_set_drvdata(phy, am654_phy); phy_provider = devm_of_phy_provider_register(dev, serdes_am654_xlate); diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 9ef246145bde..06521097513a 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -58,6 +58,7 @@ #define CHV_PADCTRL1_CFGLOCK BIT(31) #define CHV_PADCTRL1_INVRXTX_SHIFT 4 #define CHV_PADCTRL1_INVRXTX_MASK GENMASK(7, 4) +#define CHV_PADCTRL1_INVRXTX_TXDATA BIT(7) #define CHV_PADCTRL1_INVRXTX_RXDATA BIT(6) #define CHV_PADCTRL1_INVRXTX_TXENABLE BIT(5) #define CHV_PADCTRL1_ODEN BIT(3) @@ -792,11 +793,22 @@ static int chv_pinmux_set_mux(struct pinctrl_dev *pctldev, static void chv_gpio_clear_triggering(struct chv_pinctrl *pctrl, unsigned int offset) { + u32 invrxtx_mask = CHV_PADCTRL1_INVRXTX_MASK; u32 value; + /* + * One some devices the GPIO should output the inverted value from what + * device-drivers / ACPI code expects (inverted external buffer?). The + * BIOS makes this work by setting the CHV_PADCTRL1_INVRXTX_TXDATA flag, + * preserve this flag if the pin is already setup as GPIO. + */ + value = chv_readl(pctrl, offset, CHV_PADCTRL0); + if (value & CHV_PADCTRL0_GPIOEN) + invrxtx_mask &= ~CHV_PADCTRL1_INVRXTX_TXDATA; + value = chv_readl(pctrl, offset, CHV_PADCTRL1); value &= ~CHV_PADCTRL1_INTWAKECFG_MASK; - value &= ~CHV_PADCTRL1_INVRXTX_MASK; + value &= ~invrxtx_mask; chv_writel(pctrl, offset, CHV_PADCTRL1, value); } diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c index 2f3dfb56c3fa..35bbe5935708 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c @@ -259,6 +259,10 @@ bool mtk_is_virt_gpio(struct mtk_pinctrl *hw, unsigned int gpio_n) desc = (const struct mtk_pin_desc *)&hw->soc->pins[gpio_n]; + /* if the GPIO is not supported for eint mode */ + if (desc->eint.eint_m == NO_EINT_SUPPORT) + return virt_gpio; + if (desc->funcs && !desc->funcs[desc->eint.eint_m].name) virt_gpio = true; diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-xp.c b/drivers/pinctrl/mvebu/pinctrl-armada-xp.c index a767a05fa3a0..48e2a6c56a83 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-xp.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-xp.c @@ -414,7 +414,7 @@ static struct mvebu_mpp_mode mv98dx3236_mpp_modes[] = { MPP_VAR_FUNCTION(0x1, "i2c0", "sck", V_98DX3236_PLUS)), MPP_MODE(15, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_98DX3236_PLUS), - MPP_VAR_FUNCTION(0x4, "i2c0", "sda", V_98DX3236_PLUS)), + MPP_VAR_FUNCTION(0x1, "i2c0", "sda", V_98DX3236_PLUS)), MPP_MODE(16, MPP_VAR_FUNCTION(0x0, "gpo", NULL, V_98DX3236_PLUS), MPP_VAR_FUNCTION(0x4, "dev", "oe", V_98DX3236_PLUS)), diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c index a660f1274b66..826df0d637ea 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm8250.c +++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c @@ -1308,7 +1308,7 @@ static const struct msm_pingroup sm8250_groups[] = { [178] = PINGROUP(178, WEST, _, _, _, _, _, _, _, _, _), [179] = PINGROUP(179, WEST, _, _, _, _, _, _, _, _, _), [180] = UFS_RESET(ufs_reset, 0xb8000), - [181] = SDC_PINGROUP(sdc2_clk, 0x7000, 14, 6), + [181] = SDC_PINGROUP(sdc2_clk, 0xb7000, 14, 6), [182] = SDC_PINGROUP(sdc2_cmd, 0xb7000, 11, 3), [183] = SDC_PINGROUP(sdc2_data, 0xb7000, 9, 0), }; diff --git a/drivers/platform/olpc/olpc-ec.c b/drivers/platform/olpc/olpc-ec.c index 190e4a6186ef..f64b82824db2 100644 --- a/drivers/platform/olpc/olpc-ec.c +++ b/drivers/platform/olpc/olpc-ec.c @@ -439,7 +439,9 @@ static int olpc_ec_probe(struct platform_device *pdev) &config); if (IS_ERR(ec->dcon_rdev)) { dev_err(&pdev->dev, "failed to register DCON regulator\n"); - return PTR_ERR(ec->dcon_rdev); + err = PTR_ERR(ec->dcon_rdev); + kfree(ec); + return err; } ec->dbgfs_dir = olpc_ec_setup_debugfs(); diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 40219bba6801..0d91d136bc3b 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -469,6 +469,7 @@ config FUJITSU_LAPTOP depends on BACKLIGHT_CLASS_DEVICE depends on ACPI_VIDEO || ACPI_VIDEO = n select INPUT_SPARSEKMAP + select NEW_LEDS select LEDS_CLASS help This is a driver for laptops built by Fujitsu: @@ -1112,6 +1113,7 @@ config LG_LAPTOP depends on ACPI_WMI depends on INPUT select INPUT_SPARSEKMAP + select NEW_LEDS select LEDS_CLASS help This driver adds support for hotkeys as well as control of keyboard diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index b2e3d1e3b3e9..1d9fbabd02fb 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -115,6 +115,10 @@ static struct quirk_entry quirk_asus_vendor_backlight = { .wmi_backlight_set_devstate = true, }; +static struct quirk_entry quirk_asus_use_kbd_dock_devid = { + .use_kbd_dock_devid = true, +}; + static int dmi_matched(const struct dmi_system_id *dmi) { pr_info("Identified laptop model '%s'\n", dmi->ident); @@ -488,6 +492,34 @@ static const struct dmi_system_id asus_quirks[] = { }, .driver_data = &quirk_asus_vendor_backlight, }, + { + .callback = dmi_matched, + .ident = "Asus Transformer T100TA / T100HA / T100CHI", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + /* Match *T100* */ + DMI_MATCH(DMI_PRODUCT_NAME, "T100"), + }, + .driver_data = &quirk_asus_use_kbd_dock_devid, + }, + { + .callback = dmi_matched, + .ident = "Asus Transformer T101HA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "T101HA"), + }, + .driver_data = &quirk_asus_use_kbd_dock_devid, + }, + { + .callback = dmi_matched, + .ident = "Asus Transformer T200TA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"), + }, + .driver_data = &quirk_asus_use_kbd_dock_devid, + }, {}, }; @@ -593,33 +625,9 @@ static struct asus_wmi_driver asus_nb_wmi_driver = { .detect_quirks = asus_nb_wmi_quirks, }; -static const struct dmi_system_id asus_nb_wmi_blacklist[] __initconst = { - { - /* - * asus-nb-wm adds no functionality. The T100TA has a detachable - * USB kbd, so no hotkeys and it has no WMI rfkill; and loading - * asus-nb-wm causes the camera LED to turn and _stay_ on. - */ - .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"), - }, - }, - { - /* The Asus T200TA has the same issue as the T100TA */ - .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T200TA"), - }, - }, - {} /* Terminating entry */ -}; static int __init asus_nb_wmi_init(void) { - if (dmi_check_system(asus_nb_wmi_blacklist)) - return -ENODEV; - return asus_wmi_register_driver(&asus_nb_wmi_driver); } diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 8f4acdc06b13..39e1a6396e08 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -365,12 +365,14 @@ static int asus_wmi_input_init(struct asus_wmi *asus) if (err) goto err_free_dev; - result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_KBD_DOCK); - if (result >= 0) { - input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE); - input_report_switch(asus->inputdev, SW_TABLET_MODE, !result); - } else if (result != -ENODEV) { - pr_err("Error checking for keyboard-dock: %d\n", result); + if (asus->driver->quirks->use_kbd_dock_devid) { + result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_KBD_DOCK); + if (result >= 0) { + input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE); + input_report_switch(asus->inputdev, SW_TABLET_MODE, !result); + } else if (result != -ENODEV) { + pr_err("Error checking for keyboard-dock: %d\n", result); + } } err = input_register_device(asus->inputdev); @@ -442,6 +444,7 @@ static int asus_wmi_battery_add(struct power_supply *battery) */ if (strcmp(battery->desc->name, "BAT0") != 0 && strcmp(battery->desc->name, "BAT1") != 0 && + strcmp(battery->desc->name, "BATC") != 0 && strcmp(battery->desc->name, "BATT") != 0) return -ENODEV; @@ -2114,7 +2117,7 @@ static void asus_wmi_handle_event_code(int code, struct asus_wmi *asus) return; } - if (code == NOTIFY_KBD_DOCK_CHANGE) { + if (asus->driver->quirks->use_kbd_dock_devid && code == NOTIFY_KBD_DOCK_CHANGE) { result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_KBD_DOCK); if (result >= 0) { diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h index 4f31b68642a0..1a95c172f94b 100644 --- a/drivers/platform/x86/asus-wmi.h +++ b/drivers/platform/x86/asus-wmi.h @@ -33,6 +33,7 @@ struct quirk_entry { bool wmi_backlight_native; bool wmi_backlight_set_devstate; bool wmi_force_als_set; + bool use_kbd_dock_devid; int wapf; /* * For machines with AMD graphic chips, it will send out WMI event diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index e85d8e58320c..f5901b0b07cd 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -167,20 +167,54 @@ static bool intel_vbtn_has_buttons(acpi_handle handle) return ACPI_SUCCESS(status); } +/* + * There are several laptops (non 2-in-1) models out there which support VGBS, + * but simply always return 0, which we translate to SW_TABLET_MODE=1. This in + * turn causes userspace (libinput) to suppress events from the builtin + * keyboard and touchpad, making the laptop essentially unusable. + * + * Since the problem of wrongly reporting SW_TABLET_MODE=1 in combination + * with libinput, leads to a non-usable system. Where as OTOH many people will + * not even notice when SW_TABLET_MODE is not being reported, a DMI based allow + * list is used here. This list mainly matches on the chassis-type of 2-in-1s. + * + * There are also some 2-in-1s which use the intel-vbtn ACPI interface to report + * SW_TABLET_MODE with a chassis-type of 8 ("Portable") or 10 ("Notebook"), + * these are matched on a per model basis, since many normal laptops with a + * possible broken VGBS ACPI-method also use these chassis-types. + */ +static const struct dmi_system_id dmi_switches_allow_list[] = { + { + .matches = { + DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "31" /* Convertible */), + }, + }, + { + .matches = { + DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "32" /* Detachable */), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Stream x360 Convertible PC 11"), + }, + }, + {} /* Array terminator */ +}; + static bool intel_vbtn_has_switches(acpi_handle handle) { - const char *chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE); unsigned long long vgbs; acpi_status status; - /* - * Some normal laptops have a VGBS method despite being non-convertible - * and their VGBS method always returns 0, causing detect_tablet_mode() - * to report SW_TABLET_MODE=1 to userspace, which causes issues. - * These laptops have a DMI chassis_type of 9 ("Laptop"), do not report - * switches on any devices with a DMI chassis_type of 9. - */ - if (chassis_type && strcmp(chassis_type, "9") == 0) + if (!dmi_check_system(dmi_switches_allow_list)) return false; status = acpi_evaluate_integer(handle, "VGBS", NULL, &vgbs); diff --git a/drivers/platform/x86/intel_pmc_core_pltdrv.c b/drivers/platform/x86/intel_pmc_core_pltdrv.c index 731281855cc8..73797680b895 100644 --- a/drivers/platform/x86/intel_pmc_core_pltdrv.c +++ b/drivers/platform/x86/intel_pmc_core_pltdrv.c @@ -20,15 +20,10 @@ static void intel_pmc_core_release(struct device *dev) { - /* Nothing to do. */ + kfree(dev); } -static struct platform_device pmc_core_device = { - .name = "intel_pmc_core", - .dev = { - .release = intel_pmc_core_release, - }, -}; +static struct platform_device *pmc_core_device; /* * intel_pmc_core_platform_ids is the list of platforms where we want to @@ -52,6 +47,8 @@ MODULE_DEVICE_TABLE(x86cpu, intel_pmc_core_platform_ids); static int __init pmc_core_platform_init(void) { + int retval; + /* Skip creating the platform device if ACPI already has a device */ if (acpi_dev_present("INT33A1", NULL, -1)) return -ENODEV; @@ -59,12 +56,23 @@ static int __init pmc_core_platform_init(void) if (!x86_match_cpu(intel_pmc_core_platform_ids)) return -ENODEV; - return platform_device_register(&pmc_core_device); + pmc_core_device = kzalloc(sizeof(*pmc_core_device), GFP_KERNEL); + if (!pmc_core_device) + return -ENOMEM; + + pmc_core_device->name = "intel_pmc_core"; + pmc_core_device->dev.release = intel_pmc_core_release; + + retval = platform_device_register(pmc_core_device); + if (retval) + kfree(pmc_core_device); + + return retval; } static void __exit pmc_core_platform_exit(void) { - platform_device_unregister(&pmc_core_device); + platform_device_unregister(pmc_core_device); } module_init(pmc_core_platform_init); diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index 8cf8c1be2666..1506ec0a4777 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -171,7 +171,6 @@ #define MLXPLAT_CPLD_NR_NONE -1 #define MLXPLAT_CPLD_PSU_DEFAULT_NR 10 #define MLXPLAT_CPLD_PSU_MSNXXXX_NR 4 -#define MLXPLAT_CPLD_PSU_MSNXXXX_NR2 3 #define MLXPLAT_CPLD_FAN1_DEFAULT_NR 11 #define MLXPLAT_CPLD_FAN2_DEFAULT_NR 12 #define MLXPLAT_CPLD_FAN3_DEFAULT_NR 13 @@ -347,6 +346,15 @@ static struct i2c_board_info mlxplat_mlxcpld_pwr[] = { }, }; +static struct i2c_board_info mlxplat_mlxcpld_ext_pwr[] = { + { + I2C_BOARD_INFO("dps460", 0x5b), + }, + { + I2C_BOARD_INFO("dps460", 0x5a), + }, +}; + static struct i2c_board_info mlxplat_mlxcpld_fan[] = { { I2C_BOARD_INFO("24c32", 0x50), @@ -921,15 +929,15 @@ static struct mlxreg_core_data mlxplat_mlxcpld_ext_pwr_items_data[] = { .label = "pwr3", .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, .mask = BIT(2), - .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[0], - .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR2, + .hpdev.brdinfo = &mlxplat_mlxcpld_ext_pwr[0], + .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, }, { .label = "pwr4", .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, .mask = BIT(3), - .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[1], - .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR2, + .hpdev.brdinfo = &mlxplat_mlxcpld_ext_pwr[1], + .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, }, }; diff --git a/drivers/platform/x86/pcengines-apuv2.c b/drivers/platform/x86/pcengines-apuv2.c index 6aff6cf41414..c37349f97bb8 100644 --- a/drivers/platform/x86/pcengines-apuv2.c +++ b/drivers/platform/x86/pcengines-apuv2.c @@ -32,7 +32,7 @@ #define APU2_GPIO_REG_LED3 AMD_FCH_GPIO_REG_GPIO59_DEVSLP1 #define APU2_GPIO_REG_MODESW AMD_FCH_GPIO_REG_GPIO32_GE1 #define APU2_GPIO_REG_SIMSWAP AMD_FCH_GPIO_REG_GPIO33_GE2 -#define APU2_GPIO_REG_MPCIE2 AMD_FCH_GPIO_REG_GPIO59_DEVSLP0 +#define APU2_GPIO_REG_MPCIE2 AMD_FCH_GPIO_REG_GPIO55_DEVSLP0 #define APU2_GPIO_REG_MPCIE3 AMD_FCH_GPIO_REG_GPIO51 /* Order in which the GPIO lines are defined in the register list */ diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 9c4df41687a3..eae3579f106f 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -2569,7 +2569,7 @@ static void hotkey_compare_and_issue_event(struct tp_nvram_state *oldn, */ static int hotkey_kthread(void *data) { - struct tp_nvram_state s[2]; + struct tp_nvram_state s[2] = { 0 }; u32 poll_mask, event_mask; unsigned int si, so; unsigned long t; @@ -6829,8 +6829,10 @@ static int __init tpacpi_query_bcl_levels(acpi_handle handle) list_for_each_entry(child, &device->children, node) { acpi_status status = acpi_evaluate_object(child->handle, "_BCL", NULL, &buffer); - if (ACPI_FAILURE(status)) + if (ACPI_FAILURE(status)) { + buffer.length = ACPI_ALLOCATE_BUFFER; continue; + } obj = (union acpi_object *)buffer.pointer; if (!obj || (obj->type != ACPI_TYPE_PACKAGE)) { diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 5c223015ee71..dda60f89c951 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -373,6 +373,23 @@ static const struct ts_dmi_data jumper_ezpad_mini3_data = { .properties = jumper_ezpad_mini3_props, }; +static const struct property_entry mpman_converter9_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 8), + PROPERTY_ENTRY_U32("touchscreen-min-y", 8), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1664), + PROPERTY_ENTRY_U32("touchscreen-size-y", 880), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-mpman-converter9.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data mpman_converter9_data = { + .acpi_name = "MSSL1680:00", + .properties = mpman_converter9_props, +}; + static const struct property_entry mpman_mpwin895cl_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 3), PROPERTY_ENTRY_U32("touchscreen-min-y", 9), @@ -977,6 +994,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* MP Man Converter 9 */ + .driver_data = (void *)&mpman_converter9_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MPMAN"), + DMI_MATCH(DMI_PRODUCT_NAME, "Converter9"), + }, + }, + { /* MP Man MPWIN895CL */ .driver_data = (void *)&mpman_mpwin895cl_data, .matches = { diff --git a/drivers/power/supply/sbs-battery.c b/drivers/power/supply/sbs-battery.c index 49c3508a6b79..7439753fac87 100644 --- a/drivers/power/supply/sbs-battery.c +++ b/drivers/power/supply/sbs-battery.c @@ -280,6 +280,12 @@ static int sbs_update_presence(struct sbs_info *chip, bool is_present) else client->flags &= ~I2C_CLIENT_PEC; + if (of_device_is_compatible(client->dev.parent->of_node, "google,cros-ec-i2c-tunnel") + && client->flags & I2C_CLIENT_PEC) { + dev_info(&client->dev, "Disabling PEC because of broken Cros-EC implementation\n"); + client->flags &= ~I2C_CLIENT_PEC; + } + dev_dbg(&client->dev, "PEC: %s\n", (client->flags & I2C_CLIENT_PEC) ? "enabled" : "disabled"); diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index b5dd1caae5e9..d10efb66cf19 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -736,6 +736,7 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data; struct sockaddr_in6 addr; + struct socket *sock; int rc; switch(param) { @@ -747,13 +748,17 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, spin_unlock_bh(&conn->session->frwd_lock); return -ENOTCONN; } + sock = tcp_sw_conn->sock; + sock_hold(sock->sk); + spin_unlock_bh(&conn->session->frwd_lock); + if (param == ISCSI_PARAM_LOCAL_PORT) - rc = kernel_getsockname(tcp_sw_conn->sock, + rc = kernel_getsockname(sock, (struct sockaddr *)&addr); else - rc = kernel_getpeername(tcp_sw_conn->sock, + rc = kernel_getpeername(sock, (struct sockaddr *)&addr); - spin_unlock_bh(&conn->session->frwd_lock); + sock_put(sock->sk); if (rc < 0) return rc; @@ -775,6 +780,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, struct iscsi_tcp_conn *tcp_conn; struct iscsi_sw_tcp_conn *tcp_sw_conn; struct sockaddr_in6 addr; + struct socket *sock; int rc; switch (param) { @@ -789,16 +795,18 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, return -ENOTCONN; } tcp_conn = conn->dd_data; - tcp_sw_conn = tcp_conn->dd_data; - if (!tcp_sw_conn->sock) { + sock = tcp_sw_conn->sock; + if (!sock) { spin_unlock_bh(&session->frwd_lock); return -ENOTCONN; } + sock_hold(sock->sk); + spin_unlock_bh(&session->frwd_lock); - rc = kernel_getsockname(tcp_sw_conn->sock, + rc = kernel_getsockname(sock, (struct sockaddr *)&addr); - spin_unlock_bh(&session->frwd_lock); + sock_put(sock->sk); if (rc < 0) return rc; diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index 37e5d4e48c2f..83f14b2c8804 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -128,7 +128,7 @@ static void iscsi_tcp_segment_map(struct iscsi_segment *segment, int recv) * coalescing neighboring slab objects into a single frag which * triggers one of hardened usercopy checks. */ - if (!recv && page_count(sg_page(sg)) >= 1 && !PageSlab(sg_page(sg))) + if (!recv && sendpage_ok(sg_page(sg))) return; if (recv) { diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 127323a4b27c..108a7d50d2c3 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -1281,6 +1281,9 @@ static int dspi_probe(struct platform_device *pdev) if (!ctlr) return -ENOMEM; + spi_controller_set_devdata(ctlr, dspi); + platform_set_drvdata(pdev, dspi); + dspi->pdev = pdev; dspi->ctlr = ctlr; @@ -1417,8 +1420,6 @@ poll_mode: if (dspi->devtype_data->trans_mode != DSPI_DMA_MODE) ctlr->ptp_sts_supported = true; - platform_set_drvdata(pdev, dspi); - ret = spi_register_controller(ctlr); if (ret != 0) { dev_err(&pdev->dev, "Problem registering DSPI ctlr\n"); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 590eac2df909..ff26ab0a5f60 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1840,7 +1840,8 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess, * out unpacked_lun for the original se_cmd. */ if (tm_type == TMR_ABORT_TASK && (flags & TARGET_SCF_LOOKUP_LUN_FROM_TAG)) { - if (!target_lookup_lun_from_tag(se_sess, tag, &unpacked_lun)) + if (!target_lookup_lun_from_tag(se_sess, tag, + &se_cmd->orig_fe_lun)) goto failure; } diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index 7e73e989645b..b351962279e4 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -269,8 +269,30 @@ static int usb_probe_device(struct device *dev) if (error) return error; + /* Probe the USB device with the driver in hand, but only + * defer to a generic driver in case the current USB + * device driver has an id_table or a match function; i.e., + * when the device driver was explicitly matched against + * a device. + * + * If the device driver does not have either of these, + * then we assume that it can bind to any device and is + * not truly a more specialized/non-generic driver, so a + * return value of -ENODEV should not force the device + * to be handled by the generic USB driver, as there + * can still be another, more specialized, device driver. + * + * This accommodates the usbip driver. + * + * TODO: What if, in the future, there are multiple + * specialized USB device drivers for a particular device? + * In such cases, there is a need to try all matching + * specialised device drivers prior to setting the + * use_generic_driver bit. + */ error = udriver->probe(udev); - if (error == -ENODEV && udriver != &usb_generic_driver) { + if (error == -ENODEV && udriver != &usb_generic_driver && + (udriver->id_table || udriver->match)) { udev->use_generic_driver = 1; return -EPROBE_DEFER; } @@ -831,14 +853,17 @@ static int usb_device_match(struct device *dev, struct device_driver *drv) udev = to_usb_device(dev); udrv = to_usb_device_driver(drv); - if (udrv->id_table && - usb_device_match_id(udev, udrv->id_table) != NULL) { - return 1; - } + if (udrv->id_table) + return usb_device_match_id(udev, udrv->id_table) != NULL; if (udrv->match) return udrv->match(udev); - return 0; + + /* If the device driver under consideration does not have a + * id_table or a match function, then let the driver's probe + * function decide. + */ + return 1; } else if (is_usb_interface(dev)) { struct usb_interface *intf; @@ -905,26 +930,19 @@ static int usb_uevent(struct device *dev, struct kobj_uevent_env *env) return 0; } -static bool is_dev_usb_generic_driver(struct device *dev) -{ - struct usb_device_driver *udd = dev->driver ? - to_usb_device_driver(dev->driver) : NULL; - - return udd == &usb_generic_driver; -} - static int __usb_bus_reprobe_drivers(struct device *dev, void *data) { struct usb_device_driver *new_udriver = data; struct usb_device *udev; int ret; - if (!is_dev_usb_generic_driver(dev)) + /* Don't reprobe if current driver isn't usb_generic_driver */ + if (dev->driver != &usb_generic_driver.drvwrap.driver) return 0; udev = to_usb_device(dev); if (usb_device_match_id(udev, new_udriver->id_table) == NULL && - (!new_udriver->match || new_udriver->match(udev) != 0)) + (!new_udriver->match || new_udriver->match(udev) == 0)) return 0; ret = device_reprobe(dev); diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index b4206b0dede5..1f638759a953 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1189,7 +1189,6 @@ static int ncm_unwrap_ntb(struct gether *port, const struct ndp_parser_opts *opts = ncm->parser_opts; unsigned crc_len = ncm->is_crc ? sizeof(uint32_t) : 0; int dgram_counter; - bool ndp_after_header; /* dwSignature */ if (get_unaligned_le32(tmp) != opts->nth_sign) { @@ -1216,7 +1215,6 @@ static int ncm_unwrap_ntb(struct gether *port, } ndp_index = get_ncm(&tmp, opts->ndp_index); - ndp_after_header = false; /* Run through all the NDP's in the NTB */ do { @@ -1232,8 +1230,6 @@ static int ncm_unwrap_ntb(struct gether *port, ndp_index); goto err; } - if (ndp_index == opts->nth_size) - ndp_after_header = true; /* * walk through NDP @@ -1312,37 +1308,13 @@ static int ncm_unwrap_ntb(struct gether *port, index2 = get_ncm(&tmp, opts->dgram_item_len); dg_len2 = get_ncm(&tmp, opts->dgram_item_len); - if (index2 == 0 || dg_len2 == 0) - break; - /* wDatagramIndex[1] */ - if (ndp_after_header) { - if (index2 < opts->nth_size + opts->ndp_size) { - INFO(port->func.config->cdev, - "Bad index: %#X\n", index2); - goto err; - } - } else { - if (index2 < opts->nth_size + opts->dpe_size) { - INFO(port->func.config->cdev, - "Bad index: %#X\n", index2); - goto err; - } - } if (index2 > block_len - opts->dpe_size) { INFO(port->func.config->cdev, "Bad index: %#X\n", index2); goto err; } - /* wDatagramLength[1] */ - if ((dg_len2 < 14 + crc_len) || - (dg_len2 > frame_max)) { - INFO(port->func.config->cdev, - "Bad dgram length: %#X\n", dg_len); - goto err; - } - /* * Copy the data into a new skb. * This ensures the truesize is correct @@ -1359,6 +1331,8 @@ static int ncm_unwrap_ntb(struct gether *port, ndp_len -= 2 * (opts->dgram_item_len * 2); dgram_counter++; + if (index2 == 0 || dg_len2 == 0) + break; } while (ndp_len > 2 * (opts->dgram_item_len * 2)); } while (ndp_index); diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c index 9d7d642022d1..2305d425e6c9 100644 --- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -461,11 +461,6 @@ static void stub_disconnect(struct usb_device *udev) return; } -static bool usbip_match(struct usb_device *udev) -{ - return true; -} - #ifdef CONFIG_PM /* These functions need usb_port_suspend and usb_port_resume, @@ -491,7 +486,6 @@ struct usb_device_driver stub_driver = { .name = "usbip-host", .probe = stub_probe, .disconnect = stub_disconnect, - .match = usbip_match, #ifdef CONFIG_PM .suspend = stub_suspend, .resume = stub_resume, diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index 4271c408103e..d7d32b656102 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -30,9 +30,7 @@ config IFCVF be called ifcvf. config MLX5_VDPA - bool "MLX5 VDPA support library for ConnectX devices" - depends on MLX5_CORE - default n + bool help Support library for Mellanox VDPA drivers. Provides code that is common for all types of VDPA drivers. The following drivers are planned: @@ -40,7 +38,8 @@ config MLX5_VDPA config MLX5_VDPA_NET tristate "vDPA driver for ConnectX devices" - depends on MLX5_VDPA + select MLX5_VDPA + depends on MLX5_CORE default n help VDPA network driver for ConnectX6 and newer. Provides offloading diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 70676a6d1691..74264e590695 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1133,15 +1133,17 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m if (!mvq->initialized) return; - if (query_virtqueue(ndev, mvq, &attr)) { - mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n"); - return; - } if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY) return; if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND)) mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n"); + + if (query_virtqueue(ndev, mvq, &attr)) { + mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n"); + return; + } + mvq->avail_idx = attr.available_index; } static void suspend_vqs(struct mlx5_vdpa_net *ndev) @@ -1411,8 +1413,14 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa struct mlx5_virtq_attr attr; int err; - if (!mvq->initialized) - return -EAGAIN; + /* If the virtq object was destroyed, use the value saved at + * the last minute of suspend_vq. This caters for userspace + * that cares about emulating the index after vq is stopped. + */ + if (!mvq->initialized) { + state->avail_index = mvq->avail_idx; + return 0; + } err = query_virtqueue(ndev, mvq, &attr); if (err) { diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 796fe979f997..62a9bb0efc55 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -565,6 +565,9 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, perm_to_iommu_flags(perm)); } + if (r) + vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1); + return r; } @@ -592,21 +595,19 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, struct vhost_dev *dev = &v->vdev; struct vhost_iotlb *iotlb = dev->iotlb; struct page **page_list; - unsigned long list_size = PAGE_SIZE / sizeof(struct page *); + struct vm_area_struct **vmas; unsigned int gup_flags = FOLL_LONGTERM; - unsigned long npages, cur_base, map_pfn, last_pfn = 0; - unsigned long locked, lock_limit, pinned, i; + unsigned long map_pfn, last_pfn = 0; + unsigned long npages, lock_limit; + unsigned long i, nmap = 0; u64 iova = msg->iova; + long pinned; int ret = 0; if (vhost_iotlb_itree_first(iotlb, msg->iova, msg->iova + msg->size - 1)) return -EEXIST; - page_list = (struct page **) __get_free_page(GFP_KERNEL); - if (!page_list) - return -ENOMEM; - if (msg->perm & VHOST_ACCESS_WO) gup_flags |= FOLL_WRITE; @@ -614,61 +615,86 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, if (!npages) return -EINVAL; + page_list = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); + vmas = kvmalloc_array(npages, sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!page_list || !vmas) { + ret = -ENOMEM; + goto free; + } + mmap_read_lock(dev->mm); - locked = atomic64_add_return(npages, &dev->mm->pinned_vm); lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - - if (locked > lock_limit) { + if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) { ret = -ENOMEM; - goto out; + goto unlock; } - cur_base = msg->uaddr & PAGE_MASK; - iova &= PAGE_MASK; + pinned = pin_user_pages(msg->uaddr & PAGE_MASK, npages, gup_flags, + page_list, vmas); + if (npages != pinned) { + if (pinned < 0) { + ret = pinned; + } else { + unpin_user_pages(page_list, pinned); + ret = -ENOMEM; + } + goto unlock; + } - while (npages) { - pinned = min_t(unsigned long, npages, list_size); - ret = pin_user_pages(cur_base, pinned, - gup_flags, page_list, NULL); - if (ret != pinned) - goto out; - - if (!last_pfn) - map_pfn = page_to_pfn(page_list[0]); - - for (i = 0; i < ret; i++) { - unsigned long this_pfn = page_to_pfn(page_list[i]); - u64 csize; - - if (last_pfn && (this_pfn != last_pfn + 1)) { - /* Pin a contiguous chunk of memory */ - csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT; - if (vhost_vdpa_map(v, iova, csize, - map_pfn << PAGE_SHIFT, - msg->perm)) - goto out; - map_pfn = this_pfn; - iova += csize; + iova &= PAGE_MASK; + map_pfn = page_to_pfn(page_list[0]); + + /* One more iteration to avoid extra vdpa_map() call out of loop. */ + for (i = 0; i <= npages; i++) { + unsigned long this_pfn; + u64 csize; + + /* The last chunk may have no valid PFN next to it */ + this_pfn = i < npages ? page_to_pfn(page_list[i]) : -1UL; + + if (last_pfn && (this_pfn == -1UL || + this_pfn != last_pfn + 1)) { + /* Pin a contiguous chunk of memory */ + csize = last_pfn - map_pfn + 1; + ret = vhost_vdpa_map(v, iova, csize << PAGE_SHIFT, + map_pfn << PAGE_SHIFT, + msg->perm); + if (ret) { + /* + * Unpin the rest chunks of memory on the + * flight with no corresponding vdpa_map() + * calls having been made yet. On the other + * hand, vdpa_unmap() in the failure path + * is in charge of accounting the number of + * pinned pages for its own. + * This asymmetrical pattern of accounting + * is for efficiency to pin all pages at + * once, while there is no other callsite + * of vdpa_map() than here above. + */ + unpin_user_pages(&page_list[nmap], + npages - nmap); + goto out; } - - last_pfn = this_pfn; + atomic64_add(csize, &dev->mm->pinned_vm); + nmap += csize; + iova += csize << PAGE_SHIFT; + map_pfn = this_pfn; } - - cur_base += ret << PAGE_SHIFT; - npages -= ret; + last_pfn = this_pfn; } - /* Pin the rest chunk */ - ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT, - map_pfn << PAGE_SHIFT, msg->perm); + WARN_ON(nmap != npages); out: - if (ret) { + if (ret) vhost_vdpa_unmap(v, msg->iova, msg->size); - atomic64_sub(npages, &dev->mm->pinned_vm); - } +unlock: mmap_read_unlock(dev->mm); - free_page((unsigned long)page_list); +free: + kvfree(vmas); + kvfree(page_list); return ret; } @@ -810,6 +836,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) err_init_iotlb: vhost_dev_cleanup(&v->vdev); + kfree(vqs); err: atomic_dec(&v->opened); return r; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index b45519ca66a7..9ad45e1d27f0 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1290,6 +1290,11 @@ static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, vring_used_t __user *used) { + /* If an IOTLB device is present, the vring addresses are + * GIOVAs. Access validation occurs at prefetch time. */ + if (vq->iotlb) + return true; + return access_ok(desc, vhost_get_desc_size(vq, num)) && access_ok(avail, vhost_get_avail_size(vq, num)) && access_ok(used, vhost_get_used_size(vq, num)); @@ -1365,6 +1370,20 @@ bool vhost_log_access_ok(struct vhost_dev *dev) } EXPORT_SYMBOL_GPL(vhost_log_access_ok); +static bool vq_log_used_access_ok(struct vhost_virtqueue *vq, + void __user *log_base, + bool log_used, + u64 log_addr) +{ + /* If an IOTLB device is present, log_addr is a GIOVA that + * will never be logged by log_used(). */ + if (vq->iotlb) + return true; + + return !log_used || log_access_ok(log_base, log_addr, + vhost_get_used_size(vq, vq->num)); +} + /* Verify access for write logging. */ /* Caller should have vq mutex and device mutex */ static bool vq_log_access_ok(struct vhost_virtqueue *vq, @@ -1372,8 +1391,7 @@ static bool vq_log_access_ok(struct vhost_virtqueue *vq, { return vq_memory_access_ok(log_base, vq->umem, vhost_has_feature(vq, VHOST_F_LOG_ALL)) && - (!vq->log_used || log_access_ok(log_base, vq->log_addr, - vhost_get_used_size(vq, vq->num))); + vq_log_used_access_ok(vq, log_base, vq->log_used, vq->log_addr); } /* Can we start vq? */ @@ -1383,10 +1401,6 @@ bool vhost_vq_access_ok(struct vhost_virtqueue *vq) if (!vq_log_access_ok(vq, vq->log_base)) return false; - /* Access validation occurs at prefetch time with IOTLB */ - if (vq->iotlb) - return true; - return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used); } EXPORT_SYMBOL_GPL(vhost_vq_access_ok); @@ -1516,10 +1530,9 @@ static long vhost_vring_set_addr(struct vhost_dev *d, return -EINVAL; /* Also validate log access for used ring if enabled. */ - if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) && - !log_access_ok(vq->log_base, a.log_guest_addr, - sizeof *vq->used + - vq->num * sizeof *vq->used->ring)) + if (!vq_log_used_access_ok(vq, vq->log_base, + a.flags & (0x1 << VHOST_VRING_F_LOG), + a.log_guest_addr)) return -EINVAL; } diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c index 72f146d047d9..cd51b7a17a21 100644 --- a/drivers/video/console/newport_con.c +++ b/drivers/video/console/newport_con.c @@ -35,12 +35,6 @@ #define FONT_DATA ((unsigned char *)font_vga_8x16.data) -/* borrowed from fbcon.c */ -#define REFCOUNT(fd) (((int *)(fd))[-1]) -#define FNTSIZE(fd) (((int *)(fd))[-2]) -#define FNTCHARCNT(fd) (((int *)(fd))[-3]) -#define FONT_EXTRA_WORDS 3 - static unsigned char *font_data[MAX_NR_CONSOLES]; static struct newport_regs *npregs; @@ -522,6 +516,7 @@ static int newport_set_font(int unit, struct console_font *op) FNTSIZE(new_data) = size; FNTCHARCNT(new_data) = op->charcount; REFCOUNT(new_data) = 0; /* usage counter */ + FNTSUM(new_data) = 0; p = new_data; for (i = 0; i < op->charcount; i++) { diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index b2c9dd4f0cb5..402e85450bb5 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -272,6 +272,26 @@ config FB_PM2_FIFO_DISCONNECT help Support the Permedia2 FIFO disconnect feature. +config FB_ARMCLCD + tristate "ARM PrimeCell PL110 support" + depends on ARM || ARM64 || COMPILE_TEST + depends on FB && ARM_AMBA && HAS_IOMEM + select FB_CFB_FILLRECT + select FB_CFB_COPYAREA + select FB_CFB_IMAGEBLIT + select FB_MODE_HELPERS if OF + select VIDEOMODE_HELPERS if OF + select BACKLIGHT_CLASS_DEVICE if OF + help + This framebuffer device driver is for the ARM PrimeCell PL110 + Colour LCD controller. ARM PrimeCells provide the building + blocks for System on a Chip devices. + + If you want to compile this as a module (=code which can be + inserted into and removed from the running kernel), say M + here and read <file:Documentation/kbuild/modules.rst>. The module + will be called amba-clcd. + config FB_ACORN bool "Acorn VIDC support" depends on (FB = y) && ARM && ARCH_ACORN diff --git a/drivers/video/fbdev/Makefile b/drivers/video/fbdev/Makefile index cad4fb64442a..a0705b99e643 100644 --- a/drivers/video/fbdev/Makefile +++ b/drivers/video/fbdev/Makefile @@ -75,6 +75,7 @@ obj-$(CONFIG_FB_HIT) += hitfb.o obj-$(CONFIG_FB_ATMEL) += atmel_lcdfb.o obj-$(CONFIG_FB_PVR2) += pvr2fb.o obj-$(CONFIG_FB_VOODOO1) += sstfb.o +obj-$(CONFIG_FB_ARMCLCD) += amba-clcd.o obj-$(CONFIG_FB_GOLDFISH) += goldfishfb.o obj-$(CONFIG_FB_68328) += 68328fb.o obj-$(CONFIG_FB_GBE) += gbefb.o diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c new file mode 100644 index 000000000000..b7682de412d8 --- /dev/null +++ b/drivers/video/fbdev/amba-clcd.c @@ -0,0 +1,986 @@ +/* + * linux/drivers/video/amba-clcd.c + * + * Copyright (C) 2001 ARM Limited, by David A Rusling + * Updated to 2.5, Deep Blue Solutions Ltd. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + * + * ARM PrimeCell PL110 Color LCD Controller + */ +#include <linux/amba/bus.h> +#include <linux/amba/clcd.h> +#include <linux/backlight.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/fb.h> +#include <linux/init.h> +#include <linux/ioport.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_graph.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <video/display_timing.h> +#include <video/of_display_timing.h> +#include <video/videomode.h> + +#define to_clcd(info) container_of(info, struct clcd_fb, fb) + +/* This is limited to 16 characters when displayed by X startup */ +static const char *clcd_name = "CLCD FB"; + +/* + * Unfortunately, the enable/disable functions may be called either from + * process or IRQ context, and we _need_ to delay. This is _not_ good. + */ +static inline void clcdfb_sleep(unsigned int ms) +{ + if (in_atomic()) { + mdelay(ms); + } else { + msleep(ms); + } +} + +static inline void clcdfb_set_start(struct clcd_fb *fb) +{ + unsigned long ustart = fb->fb.fix.smem_start; + unsigned long lstart; + + ustart += fb->fb.var.yoffset * fb->fb.fix.line_length; + lstart = ustart + fb->fb.var.yres * fb->fb.fix.line_length / 2; + + writel(ustart, fb->regs + CLCD_UBAS); + writel(lstart, fb->regs + CLCD_LBAS); +} + +static void clcdfb_disable(struct clcd_fb *fb) +{ + u32 val; + + if (fb->board->disable) + fb->board->disable(fb); + + if (fb->panel->backlight) { + fb->panel->backlight->props.power = FB_BLANK_POWERDOWN; + backlight_update_status(fb->panel->backlight); + } + + val = readl(fb->regs + fb->off_cntl); + if (val & CNTL_LCDPWR) { + val &= ~CNTL_LCDPWR; + writel(val, fb->regs + fb->off_cntl); + + clcdfb_sleep(20); + } + if (val & CNTL_LCDEN) { + val &= ~CNTL_LCDEN; + writel(val, fb->regs + fb->off_cntl); + } + + /* + * Disable CLCD clock source. + */ + if (fb->clk_enabled) { + fb->clk_enabled = false; + clk_disable(fb->clk); + } +} + +static void clcdfb_enable(struct clcd_fb *fb, u32 cntl) +{ + /* + * Enable the CLCD clock source. + */ + if (!fb->clk_enabled) { + fb->clk_enabled = true; + clk_enable(fb->clk); + } + + /* + * Bring up by first enabling.. + */ + cntl |= CNTL_LCDEN; + writel(cntl, fb->regs + fb->off_cntl); + + clcdfb_sleep(20); + + /* + * and now apply power. + */ + cntl |= CNTL_LCDPWR; + writel(cntl, fb->regs + fb->off_cntl); + + /* + * Turn on backlight + */ + if (fb->panel->backlight) { + fb->panel->backlight->props.power = FB_BLANK_UNBLANK; + backlight_update_status(fb->panel->backlight); + } + + /* + * finally, enable the interface. + */ + if (fb->board->enable) + fb->board->enable(fb); +} + +static int +clcdfb_set_bitfields(struct clcd_fb *fb, struct fb_var_screeninfo *var) +{ + u32 caps; + int ret = 0; + + if (fb->panel->caps && fb->board->caps) + caps = fb->panel->caps & fb->board->caps; + else { + /* Old way of specifying what can be used */ + caps = fb->panel->cntl & CNTL_BGR ? + CLCD_CAP_BGR : CLCD_CAP_RGB; + /* But mask out 444 modes as they weren't supported */ + caps &= ~CLCD_CAP_444; + } + + /* Only TFT panels can do RGB888/BGR888 */ + if (!(fb->panel->cntl & CNTL_LCDTFT)) + caps &= ~CLCD_CAP_888; + + memset(&var->transp, 0, sizeof(var->transp)); + + var->red.msb_right = 0; + var->green.msb_right = 0; + var->blue.msb_right = 0; + + switch (var->bits_per_pixel) { + case 1: + case 2: + case 4: + case 8: + /* If we can't do 5551, reject */ + caps &= CLCD_CAP_5551; + if (!caps) { + ret = -EINVAL; + break; + } + + var->red.length = var->bits_per_pixel; + var->red.offset = 0; + var->green.length = var->bits_per_pixel; + var->green.offset = 0; + var->blue.length = var->bits_per_pixel; + var->blue.offset = 0; + break; + + case 16: + /* If we can't do 444, 5551 or 565, reject */ + if (!(caps & (CLCD_CAP_444 | CLCD_CAP_5551 | CLCD_CAP_565))) { + ret = -EINVAL; + break; + } + + /* + * Green length can be 4, 5 or 6 depending whether + * we're operating in 444, 5551 or 565 mode. + */ + if (var->green.length == 4 && caps & CLCD_CAP_444) + caps &= CLCD_CAP_444; + if (var->green.length == 5 && caps & CLCD_CAP_5551) + caps &= CLCD_CAP_5551; + else if (var->green.length == 6 && caps & CLCD_CAP_565) + caps &= CLCD_CAP_565; + else { + /* + * PL110 officially only supports RGB555, + * but may be wired up to allow RGB565. + */ + if (caps & CLCD_CAP_565) { + var->green.length = 6; + caps &= CLCD_CAP_565; + } else if (caps & CLCD_CAP_5551) { + var->green.length = 5; + caps &= CLCD_CAP_5551; + } else { + var->green.length = 4; + caps &= CLCD_CAP_444; + } + } + + if (var->green.length >= 5) { + var->red.length = 5; + var->blue.length = 5; + } else { + var->red.length = 4; + var->blue.length = 4; + } + break; + case 32: + /* If we can't do 888, reject */ + caps &= CLCD_CAP_888; + if (!caps) { + ret = -EINVAL; + break; + } + + var->red.length = 8; + var->green.length = 8; + var->blue.length = 8; + break; + default: + ret = -EINVAL; + break; + } + + /* + * >= 16bpp displays have separate colour component bitfields + * encoded in the pixel data. Calculate their position from + * the bitfield length defined above. + */ + if (ret == 0 && var->bits_per_pixel >= 16) { + bool bgr, rgb; + + bgr = caps & CLCD_CAP_BGR && var->blue.offset == 0; + rgb = caps & CLCD_CAP_RGB && var->red.offset == 0; + + if (!bgr && !rgb) + /* + * The requested format was not possible, try just + * our capabilities. One of BGR or RGB must be + * supported. + */ + bgr = caps & CLCD_CAP_BGR; + + if (bgr) { + var->blue.offset = 0; + var->green.offset = var->blue.offset + var->blue.length; + var->red.offset = var->green.offset + var->green.length; + } else { + var->red.offset = 0; + var->green.offset = var->red.offset + var->red.length; + var->blue.offset = var->green.offset + var->green.length; + } + } + + return ret; +} + +static int clcdfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) +{ + struct clcd_fb *fb = to_clcd(info); + int ret = -EINVAL; + + if (fb->board->check) + ret = fb->board->check(fb, var); + + if (ret == 0 && + var->xres_virtual * var->bits_per_pixel / 8 * + var->yres_virtual > fb->fb.fix.smem_len) + ret = -EINVAL; + + if (ret == 0) + ret = clcdfb_set_bitfields(fb, var); + + return ret; +} + +static int clcdfb_set_par(struct fb_info *info) +{ + struct clcd_fb *fb = to_clcd(info); + struct clcd_regs regs; + + fb->fb.fix.line_length = fb->fb.var.xres_virtual * + fb->fb.var.bits_per_pixel / 8; + + if (fb->fb.var.bits_per_pixel <= 8) + fb->fb.fix.visual = FB_VISUAL_PSEUDOCOLOR; + else + fb->fb.fix.visual = FB_VISUAL_TRUECOLOR; + + fb->board->decode(fb, ®s); + + clcdfb_disable(fb); + + writel(regs.tim0, fb->regs + CLCD_TIM0); + writel(regs.tim1, fb->regs + CLCD_TIM1); + writel(regs.tim2, fb->regs + CLCD_TIM2); + writel(regs.tim3, fb->regs + CLCD_TIM3); + + clcdfb_set_start(fb); + + clk_set_rate(fb->clk, (1000000000 / regs.pixclock) * 1000); + + fb->clcd_cntl = regs.cntl; + + clcdfb_enable(fb, regs.cntl); + +#ifdef DEBUG + printk(KERN_INFO + "CLCD: Registers set to\n" + " %08x %08x %08x %08x\n" + " %08x %08x %08x %08x\n", + readl(fb->regs + CLCD_TIM0), readl(fb->regs + CLCD_TIM1), + readl(fb->regs + CLCD_TIM2), readl(fb->regs + CLCD_TIM3), + readl(fb->regs + CLCD_UBAS), readl(fb->regs + CLCD_LBAS), + readl(fb->regs + fb->off_ienb), readl(fb->regs + fb->off_cntl)); +#endif + + return 0; +} + +static inline u32 convert_bitfield(int val, struct fb_bitfield *bf) +{ + unsigned int mask = (1 << bf->length) - 1; + + return (val >> (16 - bf->length) & mask) << bf->offset; +} + +/* + * Set a single color register. The values supplied have a 16 bit + * magnitude. Return != 0 for invalid regno. + */ +static int +clcdfb_setcolreg(unsigned int regno, unsigned int red, unsigned int green, + unsigned int blue, unsigned int transp, struct fb_info *info) +{ + struct clcd_fb *fb = to_clcd(info); + + if (regno < 16) + fb->cmap[regno] = convert_bitfield(transp, &fb->fb.var.transp) | + convert_bitfield(blue, &fb->fb.var.blue) | + convert_bitfield(green, &fb->fb.var.green) | + convert_bitfield(red, &fb->fb.var.red); + + if (fb->fb.fix.visual == FB_VISUAL_PSEUDOCOLOR && regno < 256) { + int hw_reg = CLCD_PALETTE + ((regno * 2) & ~3); + u32 val, mask, newval; + + newval = (red >> 11) & 0x001f; + newval |= (green >> 6) & 0x03e0; + newval |= (blue >> 1) & 0x7c00; + + /* + * 3.2.11: if we're configured for big endian + * byte order, the palette entries are swapped. + */ + if (fb->clcd_cntl & CNTL_BEBO) + regno ^= 1; + + if (regno & 1) { + newval <<= 16; + mask = 0x0000ffff; + } else { + mask = 0xffff0000; + } + + val = readl(fb->regs + hw_reg) & mask; + writel(val | newval, fb->regs + hw_reg); + } + + return regno > 255; +} + +/* + * Blank the screen if blank_mode != 0, else unblank. If blank == NULL + * then the caller blanks by setting the CLUT (Color Look Up Table) to all + * black. Return 0 if blanking succeeded, != 0 if un-/blanking failed due + * to e.g. a video mode which doesn't support it. Implements VESA suspend + * and powerdown modes on hardware that supports disabling hsync/vsync: + * blank_mode == 2: suspend vsync + * blank_mode == 3: suspend hsync + * blank_mode == 4: powerdown + */ +static int clcdfb_blank(int blank_mode, struct fb_info *info) +{ + struct clcd_fb *fb = to_clcd(info); + + if (blank_mode != 0) { + clcdfb_disable(fb); + } else { + clcdfb_enable(fb, fb->clcd_cntl); + } + return 0; +} + +static int clcdfb_mmap(struct fb_info *info, + struct vm_area_struct *vma) +{ + struct clcd_fb *fb = to_clcd(info); + unsigned long len, off = vma->vm_pgoff << PAGE_SHIFT; + int ret = -EINVAL; + + len = info->fix.smem_len; + + if (off <= len && vma->vm_end - vma->vm_start <= len - off && + fb->board->mmap) + ret = fb->board->mmap(fb, vma); + + return ret; +} + +static const struct fb_ops clcdfb_ops = { + .owner = THIS_MODULE, + .fb_check_var = clcdfb_check_var, + .fb_set_par = clcdfb_set_par, + .fb_setcolreg = clcdfb_setcolreg, + .fb_blank = clcdfb_blank, + .fb_fillrect = cfb_fillrect, + .fb_copyarea = cfb_copyarea, + .fb_imageblit = cfb_imageblit, + .fb_mmap = clcdfb_mmap, +}; + +static int clcdfb_register(struct clcd_fb *fb) +{ + int ret; + + /* + * ARM PL111 always has IENB at 0x1c; it's only PL110 + * which is reversed on some platforms. + */ + if (amba_manf(fb->dev) == 0x41 && amba_part(fb->dev) == 0x111) { + fb->off_ienb = CLCD_PL111_IENB; + fb->off_cntl = CLCD_PL111_CNTL; + } else { + fb->off_ienb = CLCD_PL110_IENB; + fb->off_cntl = CLCD_PL110_CNTL; + } + + fb->clk = clk_get(&fb->dev->dev, NULL); + if (IS_ERR(fb->clk)) { + ret = PTR_ERR(fb->clk); + goto out; + } + + ret = clk_prepare(fb->clk); + if (ret) + goto free_clk; + + fb->fb.device = &fb->dev->dev; + + fb->fb.fix.mmio_start = fb->dev->res.start; + fb->fb.fix.mmio_len = resource_size(&fb->dev->res); + + fb->regs = ioremap(fb->fb.fix.mmio_start, fb->fb.fix.mmio_len); + if (!fb->regs) { + printk(KERN_ERR "CLCD: unable to remap registers\n"); + ret = -ENOMEM; + goto clk_unprep; + } + + fb->fb.fbops = &clcdfb_ops; + fb->fb.flags = FBINFO_FLAG_DEFAULT; + fb->fb.pseudo_palette = fb->cmap; + + strncpy(fb->fb.fix.id, clcd_name, sizeof(fb->fb.fix.id)); + fb->fb.fix.type = FB_TYPE_PACKED_PIXELS; + fb->fb.fix.type_aux = 0; + fb->fb.fix.xpanstep = 0; + fb->fb.fix.ypanstep = 0; + fb->fb.fix.ywrapstep = 0; + fb->fb.fix.accel = FB_ACCEL_NONE; + + fb->fb.var.xres = fb->panel->mode.xres; + fb->fb.var.yres = fb->panel->mode.yres; + fb->fb.var.xres_virtual = fb->panel->mode.xres; + fb->fb.var.yres_virtual = fb->panel->mode.yres; + fb->fb.var.bits_per_pixel = fb->panel->bpp; + fb->fb.var.grayscale = fb->panel->grayscale; + fb->fb.var.pixclock = fb->panel->mode.pixclock; + fb->fb.var.left_margin = fb->panel->mode.left_margin; + fb->fb.var.right_margin = fb->panel->mode.right_margin; + fb->fb.var.upper_margin = fb->panel->mode.upper_margin; + fb->fb.var.lower_margin = fb->panel->mode.lower_margin; + fb->fb.var.hsync_len = fb->panel->mode.hsync_len; + fb->fb.var.vsync_len = fb->panel->mode.vsync_len; + fb->fb.var.sync = fb->panel->mode.sync; + fb->fb.var.vmode = fb->panel->mode.vmode; + fb->fb.var.activate = FB_ACTIVATE_NOW; + fb->fb.var.nonstd = 0; + fb->fb.var.height = fb->panel->height; + fb->fb.var.width = fb->panel->width; + fb->fb.var.accel_flags = 0; + + fb->fb.monspecs.hfmin = 0; + fb->fb.monspecs.hfmax = 100000; + fb->fb.monspecs.vfmin = 0; + fb->fb.monspecs.vfmax = 400; + fb->fb.monspecs.dclkmin = 1000000; + fb->fb.monspecs.dclkmax = 100000000; + + /* + * Make sure that the bitfields are set appropriately. + */ + clcdfb_set_bitfields(fb, &fb->fb.var); + + /* + * Allocate colourmap. + */ + ret = fb_alloc_cmap(&fb->fb.cmap, 256, 0); + if (ret) + goto unmap; + + /* + * Ensure interrupts are disabled. + */ + writel(0, fb->regs + fb->off_ienb); + + fb_set_var(&fb->fb, &fb->fb.var); + + dev_info(&fb->dev->dev, "%s hardware, %s display\n", + fb->board->name, fb->panel->mode.name); + + ret = register_framebuffer(&fb->fb); + if (ret == 0) + goto out; + + printk(KERN_ERR "CLCD: cannot register framebuffer (%d)\n", ret); + + fb_dealloc_cmap(&fb->fb.cmap); + unmap: + iounmap(fb->regs); + clk_unprep: + clk_unprepare(fb->clk); + free_clk: + clk_put(fb->clk); + out: + return ret; +} + +#ifdef CONFIG_OF +static int clcdfb_of_get_dpi_panel_mode(struct device_node *node, + struct clcd_panel *clcd_panel) +{ + int err; + struct display_timing timing; + struct videomode video; + + err = of_get_display_timing(node, "panel-timing", &timing); + if (err) { + pr_err("%pOF: problems parsing panel-timing (%d)\n", node, err); + return err; + } + + videomode_from_timing(&timing, &video); + + err = fb_videomode_from_videomode(&video, &clcd_panel->mode); + if (err) + return err; + + /* Set up some inversion flags */ + if (timing.flags & DISPLAY_FLAGS_PIXDATA_NEGEDGE) + clcd_panel->tim2 |= TIM2_IPC; + else if (!(timing.flags & DISPLAY_FLAGS_PIXDATA_POSEDGE)) + /* + * To preserve backwards compatibility, the IPC (inverted + * pixel clock) flag needs to be set on any display that + * doesn't explicitly specify that the pixel clock is + * active on the negative or positive edge. + */ + clcd_panel->tim2 |= TIM2_IPC; + + if (timing.flags & DISPLAY_FLAGS_HSYNC_LOW) + clcd_panel->tim2 |= TIM2_IHS; + + if (timing.flags & DISPLAY_FLAGS_VSYNC_LOW) + clcd_panel->tim2 |= TIM2_IVS; + + if (timing.flags & DISPLAY_FLAGS_DE_LOW) + clcd_panel->tim2 |= TIM2_IOE; + + return 0; +} + +static int clcdfb_snprintf_mode(char *buf, int size, struct fb_videomode *mode) +{ + return snprintf(buf, size, "%ux%u@%u", mode->xres, mode->yres, + mode->refresh); +} + +static int clcdfb_of_get_backlight(struct device *dev, + struct clcd_panel *clcd_panel) +{ + struct backlight_device *backlight; + + /* Look up the optional backlight device */ + backlight = devm_of_find_backlight(dev); + if (IS_ERR(backlight)) + return PTR_ERR(backlight); + + clcd_panel->backlight = backlight; + return 0; +} + +static int clcdfb_of_get_mode(struct device *dev, struct device_node *panel, + struct clcd_panel *clcd_panel) +{ + int err; + struct fb_videomode *mode; + char *name; + int len; + + /* Only directly connected DPI panels supported for now */ + if (of_device_is_compatible(panel, "panel-dpi")) + err = clcdfb_of_get_dpi_panel_mode(panel, clcd_panel); + else + err = -ENOENT; + if (err) + return err; + mode = &clcd_panel->mode; + + len = clcdfb_snprintf_mode(NULL, 0, mode); + name = devm_kzalloc(dev, len + 1, GFP_KERNEL); + if (!name) + return -ENOMEM; + + clcdfb_snprintf_mode(name, len + 1, mode); + mode->name = name; + + return 0; +} + +static int clcdfb_of_init_tft_panel(struct clcd_fb *fb, u32 r0, u32 g0, u32 b0) +{ + static struct { + unsigned int part; + u32 r0, g0, b0; + u32 caps; + } panels[] = { + { 0x110, 1, 7, 13, CLCD_CAP_5551 }, + { 0x110, 0, 8, 16, CLCD_CAP_888 }, + { 0x110, 16, 8, 0, CLCD_CAP_888 }, + { 0x111, 4, 14, 20, CLCD_CAP_444 }, + { 0x111, 3, 11, 19, CLCD_CAP_444 | CLCD_CAP_5551 }, + { 0x111, 3, 10, 19, CLCD_CAP_444 | CLCD_CAP_5551 | + CLCD_CAP_565 }, + { 0x111, 0, 8, 16, CLCD_CAP_444 | CLCD_CAP_5551 | + CLCD_CAP_565 | CLCD_CAP_888 }, + }; + int i; + + /* Bypass pixel clock divider */ + fb->panel->tim2 |= TIM2_BCD; + + /* TFT display, vert. comp. interrupt at the start of the back porch */ + fb->panel->cntl |= CNTL_LCDTFT | CNTL_LCDVCOMP(1); + + fb->panel->caps = 0; + + /* Match the setup with known variants */ + for (i = 0; i < ARRAY_SIZE(panels) && !fb->panel->caps; i++) { + if (amba_part(fb->dev) != panels[i].part) + continue; + if (g0 != panels[i].g0) + continue; + if (r0 == panels[i].r0 && b0 == panels[i].b0) + fb->panel->caps = panels[i].caps; + } + + /* + * If we actually physically connected the R lines to B and + * vice versa + */ + if (r0 != 0 && b0 == 0) + fb->panel->bgr_connection = true; + + return fb->panel->caps ? 0 : -EINVAL; +} + +static int clcdfb_of_init_display(struct clcd_fb *fb) +{ + struct device_node *endpoint, *panel; + int err; + unsigned int bpp; + u32 max_bandwidth; + u32 tft_r0b0g0[3]; + + fb->panel = devm_kzalloc(&fb->dev->dev, sizeof(*fb->panel), GFP_KERNEL); + if (!fb->panel) + return -ENOMEM; + + /* + * Fetch the panel endpoint. + */ + endpoint = of_graph_get_next_endpoint(fb->dev->dev.of_node, NULL); + if (!endpoint) + return -ENODEV; + + panel = of_graph_get_remote_port_parent(endpoint); + if (!panel) + return -ENODEV; + + err = clcdfb_of_get_backlight(&fb->dev->dev, fb->panel); + if (err) + return err; + + err = clcdfb_of_get_mode(&fb->dev->dev, panel, fb->panel); + if (err) + return err; + + err = of_property_read_u32(fb->dev->dev.of_node, "max-memory-bandwidth", + &max_bandwidth); + if (!err) { + /* + * max_bandwidth is in bytes per second and pixclock in + * pico-seconds, so the maximum allowed bits per pixel is + * 8 * max_bandwidth / (PICOS2KHZ(pixclock) * 1000) + * Rearrange this calculation to avoid overflow and then ensure + * result is a valid format. + */ + bpp = max_bandwidth / (1000 / 8) + / PICOS2KHZ(fb->panel->mode.pixclock); + bpp = rounddown_pow_of_two(bpp); + if (bpp > 32) + bpp = 32; + } else + bpp = 32; + fb->panel->bpp = bpp; + +#ifdef CONFIG_CPU_BIG_ENDIAN + fb->panel->cntl |= CNTL_BEBO; +#endif + fb->panel->width = -1; + fb->panel->height = -1; + + if (of_property_read_u32_array(endpoint, + "arm,pl11x,tft-r0g0b0-pads", + tft_r0b0g0, ARRAY_SIZE(tft_r0b0g0)) != 0) + return -ENOENT; + + return clcdfb_of_init_tft_panel(fb, tft_r0b0g0[0], + tft_r0b0g0[1], tft_r0b0g0[2]); +} + +static int clcdfb_of_vram_setup(struct clcd_fb *fb) +{ + int err; + struct device_node *memory; + u64 size; + + err = clcdfb_of_init_display(fb); + if (err) + return err; + + memory = of_parse_phandle(fb->dev->dev.of_node, "memory-region", 0); + if (!memory) + return -ENODEV; + + fb->fb.screen_base = of_iomap(memory, 0); + if (!fb->fb.screen_base) + return -ENOMEM; + + fb->fb.fix.smem_start = of_translate_address(memory, + of_get_address(memory, 0, &size, NULL)); + fb->fb.fix.smem_len = size; + + return 0; +} + +static int clcdfb_of_vram_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) +{ + unsigned long off, user_size, kernel_size; + + + off = vma->vm_pgoff << PAGE_SHIFT; + user_size = vma->vm_end - vma->vm_start; + kernel_size = fb->fb.fix.smem_len; + + if (off >= kernel_size || user_size > (kernel_size - off)) + return -ENXIO; + + return remap_pfn_range(vma, vma->vm_start, + __phys_to_pfn(fb->fb.fix.smem_start) + vma->vm_pgoff, + user_size, + pgprot_writecombine(vma->vm_page_prot)); +} + +static void clcdfb_of_vram_remove(struct clcd_fb *fb) +{ + iounmap(fb->fb.screen_base); +} + +static int clcdfb_of_dma_setup(struct clcd_fb *fb) +{ + unsigned long framesize; + dma_addr_t dma; + int err; + + err = clcdfb_of_init_display(fb); + if (err) + return err; + + framesize = PAGE_ALIGN(fb->panel->mode.xres * fb->panel->mode.yres * + fb->panel->bpp / 8); + fb->fb.screen_base = dma_alloc_coherent(&fb->dev->dev, framesize, + &dma, GFP_KERNEL); + if (!fb->fb.screen_base) + return -ENOMEM; + + fb->fb.fix.smem_start = dma; + fb->fb.fix.smem_len = framesize; + + return 0; +} + +static int clcdfb_of_dma_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) +{ + return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, + fb->fb.fix.smem_start, fb->fb.fix.smem_len); +} + +static void clcdfb_of_dma_remove(struct clcd_fb *fb) +{ + dma_free_coherent(&fb->dev->dev, fb->fb.fix.smem_len, + fb->fb.screen_base, fb->fb.fix.smem_start); +} + +static struct clcd_board *clcdfb_of_get_board(struct amba_device *dev) +{ + struct clcd_board *board = devm_kzalloc(&dev->dev, sizeof(*board), + GFP_KERNEL); + struct device_node *node = dev->dev.of_node; + + if (!board) + return NULL; + + board->name = of_node_full_name(node); + board->caps = CLCD_CAP_ALL; + board->check = clcdfb_check; + board->decode = clcdfb_decode; + if (of_find_property(node, "memory-region", NULL)) { + board->setup = clcdfb_of_vram_setup; + board->mmap = clcdfb_of_vram_mmap; + board->remove = clcdfb_of_vram_remove; + } else { + board->setup = clcdfb_of_dma_setup; + board->mmap = clcdfb_of_dma_mmap; + board->remove = clcdfb_of_dma_remove; + } + + return board; +} +#else +static struct clcd_board *clcdfb_of_get_board(struct amba_device *dev) +{ + return NULL; +} +#endif + +static int clcdfb_probe(struct amba_device *dev, const struct amba_id *id) +{ + struct clcd_board *board = dev_get_platdata(&dev->dev); + struct clcd_fb *fb; + int ret; + + if (!board) + board = clcdfb_of_get_board(dev); + + if (!board) + return -EINVAL; + + ret = dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32)); + if (ret) + goto out; + + ret = amba_request_regions(dev, NULL); + if (ret) { + printk(KERN_ERR "CLCD: unable to reserve regs region\n"); + goto out; + } + + fb = kzalloc(sizeof(*fb), GFP_KERNEL); + if (!fb) { + ret = -ENOMEM; + goto free_region; + } + + fb->dev = dev; + fb->board = board; + + dev_info(&fb->dev->dev, "PL%03x designer %02x rev%u at 0x%08llx\n", + amba_part(dev), amba_manf(dev), amba_rev(dev), + (unsigned long long)dev->res.start); + + ret = fb->board->setup(fb); + if (ret) + goto free_fb; + + ret = clcdfb_register(fb); + if (ret == 0) { + amba_set_drvdata(dev, fb); + goto out; + } + + fb->board->remove(fb); + free_fb: + kfree(fb); + free_region: + amba_release_regions(dev); + out: + return ret; +} + +static int clcdfb_remove(struct amba_device *dev) +{ + struct clcd_fb *fb = amba_get_drvdata(dev); + + clcdfb_disable(fb); + unregister_framebuffer(&fb->fb); + if (fb->fb.cmap.len) + fb_dealloc_cmap(&fb->fb.cmap); + iounmap(fb->regs); + clk_unprepare(fb->clk); + clk_put(fb->clk); + + fb->board->remove(fb); + + kfree(fb); + + amba_release_regions(dev); + + return 0; +} + +static const struct amba_id clcdfb_id_table[] = { + { + .id = 0x00041110, + .mask = 0x000ffffe, + }, + { 0, 0 }, +}; + +MODULE_DEVICE_TABLE(amba, clcdfb_id_table); + +static struct amba_driver clcd_driver = { + .drv = { + .name = "clcd-pl11x", + }, + .probe = clcdfb_probe, + .remove = clcdfb_remove, + .id_table = clcdfb_id_table, +}; + +static int __init amba_clcdfb_init(void) +{ + if (fb_get_options("ambafb", NULL)) + return -ENODEV; + + return amba_driver_register(&clcd_driver); +} + +module_init(amba_clcdfb_init); + +static void __exit amba_clcdfb_exit(void) +{ + amba_driver_unregister(&clcd_driver); +} + +module_exit(amba_clcdfb_exit); + +MODULE_DESCRIPTION("ARM PrimeCell PL110 CLCD core driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 41f3fa3db6d4..8c7bd0a29eaa 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2299,6 +2299,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) if (font->width <= 8) { j = vc->vc_font.height; + if (font->charcount * j > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 32 - j); @@ -2307,6 +2310,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) } } else if (font->width <= 16) { j = vc->vc_font.height * 2; + if (font->charcount * j > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 64 - j); @@ -2314,6 +2320,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) fontdata += j; } } else if (font->width <= 24) { + if (font->charcount * (vc->vc_font.height * sizeof(u32)) > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { for (j = 0; j < vc->vc_font.height; j++) { *data++ = fontdata[0]; @@ -2326,6 +2335,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) } } else { j = vc->vc_font.height * 4; + if (font->charcount * j > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 128 - j); diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h index 78bb14c03643..9315b360c898 100644 --- a/drivers/video/fbdev/core/fbcon.h +++ b/drivers/video/fbdev/core/fbcon.h @@ -152,13 +152,6 @@ static inline int attr_col_ec(int shift, struct vc_data *vc, #define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0) #define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1) -/* Font */ -#define REFCOUNT(fd) (((int *)(fd))[-1]) -#define FNTSIZE(fd) (((int *)(fd))[-2]) -#define FNTCHARCNT(fd) (((int *)(fd))[-3]) -#define FNTSUM(fd) (((int *)(fd))[-4]) -#define FONT_EXTRA_WORDS 4 - /* * Scroll Method */ diff --git a/drivers/video/fbdev/core/fbcon_rotate.c b/drivers/video/fbdev/core/fbcon_rotate.c index c0d445294aa7..ac72d4f85f7d 100644 --- a/drivers/video/fbdev/core/fbcon_rotate.c +++ b/drivers/video/fbdev/core/fbcon_rotate.c @@ -14,6 +14,7 @@ #include <linux/fb.h> #include <linux/vt_kern.h> #include <linux/console.h> +#include <linux/font.h> #include <asm/types.h> #include "fbcon.h" #include "fbcon_rotate.h" diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c index 31b85b71cc37..628fe5e010c0 100644 --- a/drivers/video/fbdev/core/tileblit.c +++ b/drivers/video/fbdev/core/tileblit.c @@ -13,6 +13,7 @@ #include <linux/fb.h> #include <linux/vt_kern.h> #include <linux/console.h> +#include <linux/font.h> #include <asm/types.h> #include "fbcon.h" diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 90b8f56fbadb..6f02c18fa65c 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -92,6 +92,8 @@ static bool (*pirq_needs_eoi)(unsigned irq); /* Xen will never allocate port zero for any purpose. */ #define VALID_EVTCHN(chn) ((chn) != 0) +static struct irq_info *legacy_info_ptrs[NR_IRQS_LEGACY]; + static struct irq_chip xen_dynamic_chip; static struct irq_chip xen_percpu_chip; static struct irq_chip xen_pirq_chip; @@ -156,7 +158,18 @@ int get_evtchn_to_irq(evtchn_port_t evtchn) /* Get info for IRQ */ struct irq_info *info_for_irq(unsigned irq) { - return irq_get_chip_data(irq); + if (irq < nr_legacy_irqs()) + return legacy_info_ptrs[irq]; + else + return irq_get_chip_data(irq); +} + +static void set_info_for_irq(unsigned int irq, struct irq_info *info) +{ + if (irq < nr_legacy_irqs()) + legacy_info_ptrs[irq] = info; + else + irq_set_chip_data(irq, info); } /* Constructors for packed IRQ information. */ @@ -377,7 +390,7 @@ static void xen_irq_init(unsigned irq) info->type = IRQT_UNBOUND; info->refcnt = -1; - irq_set_chip_data(irq, info); + set_info_for_irq(irq, info); list_add_tail(&info->list, &xen_irq_list_head); } @@ -426,14 +439,14 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi) static void xen_free_irq(unsigned irq) { - struct irq_info *info = irq_get_chip_data(irq); + struct irq_info *info = info_for_irq(irq); if (WARN_ON(!info)) return; list_del(&info->list); - irq_set_chip_data(irq, NULL); + set_info_for_irq(irq, NULL); WARN_ON(info->refcnt > 0); @@ -603,7 +616,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi); static void __unbind_from_irq(unsigned int irq) { evtchn_port_t evtchn = evtchn_from_irq(irq); - struct irq_info *info = irq_get_chip_data(irq); + struct irq_info *info = info_for_irq(irq); if (info->refcnt > 0) { info->refcnt--; @@ -1108,7 +1121,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, void unbind_from_irqhandler(unsigned int irq, void *dev_id) { - struct irq_info *info = irq_get_chip_data(irq); + struct irq_info *info = info_for_irq(irq); if (WARN_ON(!info)) return; @@ -1142,7 +1155,7 @@ int evtchn_make_refcounted(evtchn_port_t evtchn) if (irq == -1) return -ENOENT; - info = irq_get_chip_data(irq); + info = info_for_irq(irq); if (!info) return -ENOENT; @@ -1170,7 +1183,7 @@ int evtchn_get(evtchn_port_t evtchn) if (irq == -1) goto done; - info = irq_get_chip_data(irq); + info = info_for_irq(irq); if (!info) goto done; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 1d13d2e882ad..0fe8844b4bee 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -810,14 +810,32 @@ void afs_evict_inode(struct inode *inode) static void afs_setattr_success(struct afs_operation *op) { - struct inode *inode = &op->file[0].vnode->vfs_inode; + struct afs_vnode_param *vp = &op->file[0]; + struct inode *inode = &vp->vnode->vfs_inode; + loff_t old_i_size = i_size_read(inode); + + op->setattr.old_i_size = old_i_size; + afs_vnode_commit_status(op, vp); + /* inode->i_size has now been changed. */ + + if (op->setattr.attr->ia_valid & ATTR_SIZE) { + loff_t size = op->setattr.attr->ia_size; + if (size > old_i_size) + pagecache_isize_extended(inode, old_i_size, size); + } +} + +static void afs_setattr_edit_file(struct afs_operation *op) +{ + struct afs_vnode_param *vp = &op->file[0]; + struct inode *inode = &vp->vnode->vfs_inode; - afs_vnode_commit_status(op, &op->file[0]); if (op->setattr.attr->ia_valid & ATTR_SIZE) { - loff_t i_size = inode->i_size, size = op->setattr.attr->ia_size; - if (size > i_size) - pagecache_isize_extended(inode, i_size, size); - truncate_pagecache(inode, size); + loff_t size = op->setattr.attr->ia_size; + loff_t i_size = op->setattr.old_i_size; + + if (size < i_size) + truncate_pagecache(inode, size); } } @@ -825,6 +843,7 @@ static const struct afs_operation_ops afs_setattr_operation = { .issue_afs_rpc = afs_fs_setattr, .issue_yfs_rpc = yfs_fs_setattr, .success = afs_setattr_success, + .edit_dir = afs_setattr_edit_file, }; /* @@ -863,11 +882,16 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) if (S_ISREG(vnode->vfs_inode.i_mode)) filemap_write_and_wait(vnode->vfs_inode.i_mapping); + /* Prevent any new writebacks from starting whilst we do this. */ + down_write(&vnode->validate_lock); + op = afs_alloc_operation(((attr->ia_valid & ATTR_FILE) ? afs_file_key(attr->ia_file) : NULL), vnode->volume); - if (IS_ERR(op)) - return PTR_ERR(op); + if (IS_ERR(op)) { + ret = PTR_ERR(op); + goto out_unlock; + } afs_op_set_vnode(op, 0, vnode); op->setattr.attr = attr; @@ -880,5 +904,10 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) op->file[0].update_ctime = 1; op->ops = &afs_setattr_operation; - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + +out_unlock: + up_write(&vnode->validate_lock); + _leave(" = %d", ret); + return ret; } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 18042b7dab6a..e5f0446f27e5 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -812,6 +812,7 @@ struct afs_operation { } store; struct { struct iattr *attr; + loff_t old_i_size; } setattr; struct afs_acl *acl; struct yfs_acl *yacl; diff --git a/fs/afs/write.c b/fs/afs/write.c index 4b2265cb1891..da12abd6db21 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -738,11 +738,21 @@ static int afs_writepages_region(struct address_space *mapping, int afs_writepages(struct address_space *mapping, struct writeback_control *wbc) { + struct afs_vnode *vnode = AFS_FS_I(mapping->host); pgoff_t start, end, next; int ret; _enter(""); + /* We have to be careful as we can end up racing with setattr() + * truncating the pagecache since the caller doesn't take a lock here + * to prevent it. + */ + if (wbc->sync_mode == WB_SYNC_ALL) + down_read(&vnode->validate_lock); + else if (!down_read_trylock(&vnode->validate_lock)) + return 0; + if (wbc->range_cyclic) { start = mapping->writeback_index; end = -1; @@ -762,6 +772,7 @@ int afs_writepages(struct address_space *mapping, ret = afs_writepages_region(mapping, wbc, start, end, &next); } + up_read(&vnode->validate_lock); _leave(" = %d", ret); return ret; } diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index db93909b25e0..e4a1c6afe35d 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -599,6 +599,37 @@ static void btrfs_rm_dev_replace_unblocked(struct btrfs_fs_info *fs_info) wake_up(&fs_info->dev_replace.replace_wait); } +/* + * When finishing the device replace, before swapping the source device with the + * target device we must update the chunk allocation state in the target device, + * as it is empty because replace works by directly copying the chunks and not + * through the normal chunk allocation path. + */ +static int btrfs_set_target_alloc_state(struct btrfs_device *srcdev, + struct btrfs_device *tgtdev) +{ + struct extent_state *cached_state = NULL; + u64 start = 0; + u64 found_start; + u64 found_end; + int ret = 0; + + lockdep_assert_held(&srcdev->fs_info->chunk_mutex); + + while (!find_first_extent_bit(&srcdev->alloc_state, start, + &found_start, &found_end, + CHUNK_ALLOCATED, &cached_state)) { + ret = set_extent_bits(&tgtdev->alloc_state, found_start, + found_end, CHUNK_ALLOCATED); + if (ret) + break; + start = found_end + 1; + } + + free_extent_state(cached_state); + return ret; +} + static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, int scrub_ret) { @@ -673,8 +704,14 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, dev_replace->time_stopped = ktime_get_real_seconds(); dev_replace->item_needs_writeback = 1; - /* replace old device with new one in mapping tree */ + /* + * Update allocation state in the new device and replace the old device + * with the new one in the mapping tree. + */ if (!scrub_ret) { + scrub_ret = btrfs_set_target_alloc_state(src_device, tgt_device); + if (scrub_ret) + goto error; btrfs_dev_replace_update_device_in_mapping_tree(fs_info, src_device, tgt_device); @@ -685,6 +722,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, btrfs_dev_name(src_device), src_device->devid, rcu_str_deref(tgt_device->name), scrub_ret); +error: up_write(&dev_replace->rwsem); mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&fs_info->fs_devices->device_list_mutex); @@ -745,7 +783,9 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, /* replace the sysfs entry */ btrfs_sysfs_remove_devices_dir(fs_info->fs_devices, src_device); btrfs_sysfs_update_devid(tgt_device); - btrfs_rm_dev_replace_free_srcdev(src_device); + if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &src_device->dev_state)) + btrfs_scratch_superblocks(fs_info, src_device->bdev, + src_device->name->str); /* write back the superblocks */ trans = btrfs_start_transaction(root, 0); @@ -754,6 +794,8 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); + btrfs_rm_dev_replace_free_srcdev(src_device); + return 0; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 117b43367629..1997a7d67f22 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1999,9 +1999,9 @@ static u64 btrfs_num_devices(struct btrfs_fs_info *fs_info) return num_devices; } -static void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, - struct block_device *bdev, - const char *device_path) +void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, + struct block_device *bdev, + const char *device_path) { struct btrfs_super_block *disk_super; int copy_num; @@ -2224,11 +2224,7 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev) struct btrfs_fs_info *fs_info = srcdev->fs_info; struct btrfs_fs_devices *fs_devices = srcdev->fs_devices; - if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &srcdev->dev_state)) { - /* zero out the old super if it is writable */ - btrfs_scratch_superblocks(fs_info, srcdev->bdev, - srcdev->name->str); - } + mutex_lock(&uuid_mutex); btrfs_close_bdev(srcdev); synchronize_rcu(); @@ -2258,6 +2254,7 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev) close_fs_devices(fs_devices); free_fs_devices(fs_devices); } + mutex_unlock(&uuid_mutex); } void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev) diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 5eea93916fbf..302c9234f7d0 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -573,6 +573,9 @@ void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info); void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info); bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info, struct btrfs_device *failing_dev); +void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, + struct block_device *bdev, + const char *device_path); int btrfs_bg_type_to_factor(u64 flags); const char *btrfs_bg_type_to_raid_name(u64 flags); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 32f90dc82c84..d44df8f95bcd 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1208,7 +1208,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_iov = si_iov; rqst[1].rq_nvec = 1; - len = sizeof(ea) + ea_name_len + ea_value_len + 1; + len = sizeof(*ea) + ea_name_len + ea_value_len + 1; ea = kzalloc(len, GFP_KERNEL); if (ea == NULL) { rc = -ENOMEM; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 8107e06d7f6f..4df61129566d 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -218,8 +218,7 @@ struct eventpoll { struct file *file; /* used to optimize loop detection check */ - struct list_head visited_list_link; - int visited; + u64 gen; #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ @@ -274,6 +273,8 @@ static long max_user_watches __read_mostly; */ static DEFINE_MUTEX(epmutex); +static u64 loop_check_gen = 0; + /* Used to check for epoll file descriptor inclusion loops */ static struct nested_calls poll_loop_ncalls; @@ -283,9 +284,6 @@ static struct kmem_cache *epi_cache __read_mostly; /* Slab cache used to allocate "struct eppoll_entry" */ static struct kmem_cache *pwq_cache __read_mostly; -/* Visited nodes during ep_loop_check(), so we can unset them when we finish */ -static LIST_HEAD(visited_list); - /* * List of files with newly added links, where we may need to limit the number * of emanating paths. Protected by the epmutex. @@ -1450,7 +1448,7 @@ static int reverse_path_check(void) static int ep_create_wakeup_source(struct epitem *epi) { - const char *name; + struct name_snapshot n; struct wakeup_source *ws; if (!epi->ep->ws) { @@ -1459,8 +1457,9 @@ static int ep_create_wakeup_source(struct epitem *epi) return -ENOMEM; } - name = epi->ffd.file->f_path.dentry->d_name.name; - ws = wakeup_source_register(NULL, name); + take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry); + ws = wakeup_source_register(NULL, n.name.name); + release_dentry_name_snapshot(&n); if (!ws) return -ENOMEM; @@ -1522,6 +1521,22 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, RCU_INIT_POINTER(epi->ws, NULL); } + /* Add the current item to the list of active epoll hook for this file */ + spin_lock(&tfile->f_lock); + list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); + spin_unlock(&tfile->f_lock); + + /* + * Add the current item to the RB tree. All RB tree operations are + * protected by "mtx", and ep_insert() is called with "mtx" held. + */ + ep_rbtree_insert(ep, epi); + + /* now check if we've created too many backpaths */ + error = -EINVAL; + if (full_check && reverse_path_check()) + goto error_remove_epi; + /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); @@ -1544,22 +1559,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, if (epi->nwait < 0) goto error_unregister; - /* Add the current item to the list of active epoll hook for this file */ - spin_lock(&tfile->f_lock); - list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); - spin_unlock(&tfile->f_lock); - - /* - * Add the current item to the RB tree. All RB tree operations are - * protected by "mtx", and ep_insert() is called with "mtx" held. - */ - ep_rbtree_insert(ep, epi); - - /* now check if we've created too many backpaths */ - error = -EINVAL; - if (full_check && reverse_path_check()) - goto error_remove_epi; - /* We have to drop the new item inside our item list to keep track of it */ write_lock_irq(&ep->lock); @@ -1588,6 +1587,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, return 0; +error_unregister: + ep_unregister_pollwait(ep, epi); error_remove_epi: spin_lock(&tfile->f_lock); list_del_rcu(&epi->fllink); @@ -1595,9 +1596,6 @@ error_remove_epi: rb_erase_cached(&epi->rbn, &ep->rbr); -error_unregister: - ep_unregister_pollwait(ep, epi); - /* * We need to do this because an event could have been arrived on some * allocated wait queue. Note that we don't care about the ep->ovflist @@ -1972,13 +1970,12 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) struct epitem *epi; mutex_lock_nested(&ep->mtx, call_nests + 1); - ep->visited = 1; - list_add(&ep->visited_list_link, &visited_list); + ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { ep_tovisit = epi->ffd.file->private_data; - if (ep_tovisit->visited) + if (ep_tovisit->gen == loop_check_gen) continue; error = ep_call_nested(&poll_loop_ncalls, ep_loop_check_proc, epi->ffd.file, @@ -2019,18 +2016,8 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) */ static int ep_loop_check(struct eventpoll *ep, struct file *file) { - int ret; - struct eventpoll *ep_cur, *ep_next; - - ret = ep_call_nested(&poll_loop_ncalls, + return ep_call_nested(&poll_loop_ncalls, ep_loop_check_proc, file, ep, current); - /* clear visited list */ - list_for_each_entry_safe(ep_cur, ep_next, &visited_list, - visited_list_link) { - ep_cur->visited = 0; - list_del(&ep_cur->visited_list_link); - } - return ret; } static void clear_tfile_check_list(void) @@ -2195,11 +2182,13 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, goto error_tgt_fput; if (op == EPOLL_CTL_ADD) { if (!list_empty(&f.file->f_ep_links) || + ep->gen == loop_check_gen || is_file_epoll(tf.file)) { mutex_unlock(&ep->mtx); error = epoll_mutex_lock(&epmutex, 0, nonblock); if (error) goto error_tgt_fput; + loop_check_gen++; full_check = 1; if (is_file_epoll(tf.file)) { error = -ELOOP; @@ -2263,6 +2252,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, error_tgt_fput: if (full_check) { clear_tfile_check_list(); + loop_check_gen++; mutex_unlock(&epmutex); } diff --git a/fs/exfat/cache.c b/fs/exfat/cache.c index 03d0824fc368..5a2f119b7e8c 100644 --- a/fs/exfat/cache.c +++ b/fs/exfat/cache.c @@ -17,7 +17,6 @@ #include "exfat_raw.h" #include "exfat_fs.h" -#define EXFAT_CACHE_VALID 0 #define EXFAT_MAX_CACHE 16 struct exfat_cache { @@ -61,16 +60,6 @@ void exfat_cache_shutdown(void) kmem_cache_destroy(exfat_cachep); } -void exfat_cache_init_inode(struct inode *inode) -{ - struct exfat_inode_info *ei = EXFAT_I(inode); - - spin_lock_init(&ei->cache_lru_lock); - ei->nr_caches = 0; - ei->cache_valid_id = EXFAT_CACHE_VALID + 1; - INIT_LIST_HEAD(&ei->cache_lru); -} - static inline struct exfat_cache *exfat_cache_alloc(void) { return kmem_cache_alloc(exfat_cachep, GFP_NOFS); diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index 95d717f8620c..c013fe931d9c 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -248,6 +248,8 @@ struct exfat_sb_info { struct rcu_head rcu; }; +#define EXFAT_CACHE_VALID 0 + /* * EXFAT file system inode in-memory data */ @@ -428,7 +430,6 @@ extern const struct dentry_operations exfat_utf8_dentry_ops; /* cache.c */ int exfat_cache_init(void); void exfat_cache_shutdown(void); -void exfat_cache_init_inode(struct inode *inode); void exfat_cache_inval_inode(struct inode *inode); int exfat_get_cluster(struct inode *inode, unsigned int cluster, unsigned int *fclus, unsigned int *dclus, diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index 7f90204adef5..a6de17cac3df 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -611,8 +611,6 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) ei->i_crtime = info->crtime; inode->i_atime = info->atime; - exfat_cache_init_inode(inode); - return 0; } diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index e73f20f66cb2..c94ac239f740 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -578,7 +578,8 @@ static int exfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, i_pos = exfat_make_i_pos(&info); inode = exfat_build_inode(sb, &info, i_pos); - if (IS_ERR(inode)) + err = PTR_ERR_OR_ZERO(inode); + if (err) goto unlock; inode_inc_iversion(inode); @@ -745,10 +746,9 @@ static struct dentry *exfat_lookup(struct inode *dir, struct dentry *dentry, i_pos = exfat_make_i_pos(&info); inode = exfat_build_inode(sb, &info, i_pos); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); + err = PTR_ERR_OR_ZERO(inode); + if (err) goto unlock; - } i_mode = inode->i_mode; alias = d_find_alias(inode); @@ -890,10 +890,9 @@ static int exfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) i_pos = exfat_make_i_pos(&info); inode = exfat_build_inode(sb, &info, i_pos); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); + err = PTR_ERR_OR_ZERO(inode); + if (err) goto unlock; - } inode_inc_iversion(inode); inode->i_mtime = inode->i_atime = inode->i_ctime = diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 3b6a1659892f..60b941ba557b 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -376,7 +376,6 @@ static int exfat_read_root(struct inode *inode) inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime = current_time(inode); exfat_truncate_atime(&inode->i_atime); - exfat_cache_init_inode(inode); return 0; } @@ -763,6 +762,10 @@ static void exfat_inode_init_once(void *foo) { struct exfat_inode_info *ei = (struct exfat_inode_info *)foo; + spin_lock_init(&ei->cache_lru_lock); + ei->nr_caches = 0; + ei->cache_valid_id = EXFAT_CACHE_VALID + 1; + INIT_LIST_HEAD(&ei->cache_lru); INIT_HLIST_NODE(&ei->i_hash_fat); inode_init_once(&ei->vfs_inode); } diff --git a/fs/io_uring.c b/fs/io_uring.c index eed0d068904c..aae0ef2ec34d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3049,6 +3049,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, if (!wake_page_match(wpq, key)) return 0; + req->rw.kiocb.ki_flags &= ~IOCB_WAITQ; list_del_init(&wait->entry); init_task_work(&req->task_work, io_req_task_submit); @@ -3106,6 +3107,7 @@ static bool io_rw_should_retry(struct io_kiocb *req) wait->wait.flags = 0; INIT_LIST_HEAD(&wait->wait.entry); kiocb->ki_flags |= IOCB_WAITQ; + kiocb->ki_flags &= ~IOCB_NOWAIT; kiocb->ki_waitq = wait; io_get_req_task(req); @@ -4743,6 +4745,8 @@ static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode, if (mask && !(mask & poll->events)) return 0; + list_del_init(&wait->entry); + if (poll && poll->head) { bool done; @@ -8412,11 +8416,19 @@ static int io_uring_show_cred(int id, void *p, void *data) static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) { + bool has_lock; int i; - mutex_lock(&ctx->uring_lock); + /* + * Avoid ABBA deadlock between the seq lock and the io_uring mutex, + * since fdinfo case grabs it in the opposite direction of normal use + * cases. If we fail to get the lock, we just don't iterate any + * structures that could be going away outside the io_uring mutex. + */ + has_lock = mutex_trylock(&ctx->uring_lock); + seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); - for (i = 0; i < ctx->nr_user_files; i++) { + for (i = 0; has_lock && i < ctx->nr_user_files; i++) { struct fixed_file_table *table; struct file *f; @@ -8428,13 +8440,13 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) seq_printf(m, "%5u: <none>\n", i); } seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); - for (i = 0; i < ctx->nr_user_bufs; i++) { + for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { struct io_mapped_ubuf *buf = &ctx->user_bufs[i]; seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, (unsigned int) buf->len); } - if (!idr_is_empty(&ctx->personality_idr)) { + if (has_lock && !idr_is_empty(&ctx->personality_idr)) { seq_printf(m, "Personalities:\n"); idr_for_each(&ctx->personality_idr, io_uring_show_cred, m); } @@ -8449,7 +8461,8 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) req->task->task_works != NULL); } spin_unlock_irq(&ctx->completion_lock); - mutex_unlock(&ctx->uring_lock); + if (has_lock) + mutex_unlock(&ctx->uring_lock); } static void io_uring_show_fdinfo(struct seq_file *m, struct file *f) diff --git a/fs/pipe.c b/fs/pipe.c index 60dbee457143..0ac197658a2d 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -106,25 +106,6 @@ void pipe_double_lock(struct pipe_inode_info *pipe1, } } -/* Drop the inode semaphore and wait for a pipe event, atomically */ -void pipe_wait(struct pipe_inode_info *pipe) -{ - DEFINE_WAIT(rdwait); - DEFINE_WAIT(wrwait); - - /* - * Pipes are system-local resources, so sleeping on them - * is considered a noninteractive wait: - */ - prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); - prepare_to_wait(&pipe->wr_wait, &wrwait, TASK_INTERRUPTIBLE); - pipe_unlock(pipe); - schedule(); - finish_wait(&pipe->rd_wait, &rdwait); - finish_wait(&pipe->wr_wait, &wrwait); - pipe_lock(pipe); -} - static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { @@ -913,19 +894,18 @@ int create_pipe_files(struct file **res, int flags) { struct inode *inode = get_pipe_inode(); struct file *f; + int error; if (!inode) return -ENFILE; if (flags & O_NOTIFICATION_PIPE) { -#ifdef CONFIG_WATCH_QUEUE - if (watch_queue_init(inode->i_pipe) < 0) { + error = watch_queue_init(inode->i_pipe); + if (error) { + free_pipe_info(inode->i_pipe); iput(inode); - return -ENOMEM; + return error; } -#else - return -ENOPKG; -#endif } f = alloc_file_pseudo(inode, pipe_mnt, "", @@ -1035,12 +1015,52 @@ SYSCALL_DEFINE1(pipe, int __user *, fildes) return do_pipe2(fildes, 0); } +/* + * This is the stupid "wait for pipe to be readable or writable" + * model. + * + * See pipe_read/write() for the proper kind of exclusive wait, + * but that requires that we wake up any other readers/writers + * if we then do not end up reading everything (ie the whole + * "wake_next_reader/writer" logic in pipe_read/write()). + */ +void pipe_wait_readable(struct pipe_inode_info *pipe) +{ + pipe_unlock(pipe); + wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe)); + pipe_lock(pipe); +} + +void pipe_wait_writable(struct pipe_inode_info *pipe) +{ + pipe_unlock(pipe); + wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe)); + pipe_lock(pipe); +} + +/* + * This depends on both the wait (here) and the wakeup (wake_up_partner) + * holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot + * race with the count check and waitqueue prep. + * + * Normally in order to avoid races, you'd do the prepare_to_wait() first, + * then check the condition you're waiting for, and only then sleep. But + * because of the pipe lock, we can check the condition before being on + * the wait queue. + * + * We use the 'rd_wait' waitqueue for pipe partner waiting. + */ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { + DEFINE_WAIT(rdwait); int cur = *cnt; while (cur == *cnt) { - pipe_wait(pipe); + prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); + pipe_unlock(pipe); + schedule(); + finish_wait(&pipe->rd_wait, &rdwait); + pipe_lock(pipe); if (signal_pending(current)) break; } @@ -1050,7 +1070,6 @@ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible_all(&pipe->rd_wait); - wake_up_interruptible_all(&pipe->wr_wait); } static int fifo_open(struct inode *inode, struct file *filp) diff --git a/fs/splice.c b/fs/splice.c index d7c8a7c4db07..ce75aec52274 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -526,6 +526,22 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des return 1; } +/* We know we have a pipe buffer, but maybe it's empty? */ +static inline bool eat_empty_buffer(struct pipe_inode_info *pipe) +{ + unsigned int tail = pipe->tail; + unsigned int mask = pipe->ring_size - 1; + struct pipe_buffer *buf = &pipe->bufs[tail & mask]; + + if (unlikely(!buf->len)) { + pipe_buf_release(pipe, buf); + pipe->tail = tail+1; + return true; + } + + return false; +} + /** * splice_from_pipe_next - wait for some data to splice from * @pipe: pipe to splice from @@ -545,6 +561,7 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des if (signal_pending(current)) return -ERESTARTSYS; +repeat: while (pipe_empty(pipe->head, pipe->tail)) { if (!pipe->writers) return 0; @@ -563,9 +580,12 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des sd->need_wakeup = false; } - pipe_wait(pipe); + pipe_wait_readable(pipe); } + if (eat_empty_buffer(pipe)) + goto repeat; + return 1; } @@ -1077,7 +1097,7 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) return -EAGAIN; if (signal_pending(current)) return -ERESTARTSYS; - pipe_wait(pipe); + pipe_wait_writable(pipe); } } @@ -1454,7 +1474,7 @@ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) ret = -EAGAIN; break; } - pipe_wait(pipe); + pipe_wait_readable(pipe); } pipe_unlock(pipe); @@ -1493,7 +1513,7 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) ret = -ERESTARTSYS; break; } - pipe_wait(pipe); + pipe_wait_writable(pipe); } pipe_unlock(pipe); diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 5430febd34be..7636bc71c71f 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -661,7 +661,7 @@ #define BTF \ .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { \ __start_BTF = .; \ - *(.BTF) \ + KEEP(*(.BTF)) \ __stop_BTF = .; \ } \ . = ALIGN(4); \ diff --git a/include/drm/drm_dsc.h b/include/drm/drm_dsc.h index 887954cbfc60..732f32740c86 100644 --- a/include/drm/drm_dsc.h +++ b/include/drm/drm_dsc.h @@ -588,7 +588,7 @@ struct drm_dsc_picture_parameter_set { * This structure represents the DSC PPS infoframe required to send the Picture * Parameter Set metadata required before enabling VESA Display Stream * Compression. This is based on the DP Secondary Data Packet structure and - * comprises of SDP Header as defined &struct struct dp_sdp_header in drm_dp_helper.h + * comprises of SDP Header as defined &struct dp_sdp_header in drm_dp_helper.h * and PPS payload defined in &struct drm_dsc_picture_parameter_set. * * @pps_header: Header for PPS as per DP SDP header format of type diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1e4cdc6c7ae2..64ae25c59d55 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -958,7 +958,7 @@ void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); -#ifdef CONFIG_X86 +#ifndef CONFIG_IA64 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else static inline void arch_reserve_mem_area(acpi_physical_address addr, diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h new file mode 100644 index 000000000000..421b0fa90d6a --- /dev/null +++ b/include/linux/amba/clcd-regs.h @@ -0,0 +1,87 @@ +/* + * David A Rusling + * + * Copyright (C) 2001 ARM Limited + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ + +#ifndef AMBA_CLCD_REGS_H +#define AMBA_CLCD_REGS_H + +/* + * CLCD Controller Internal Register addresses + */ +#define CLCD_TIM0 0x00000000 +#define CLCD_TIM1 0x00000004 +#define CLCD_TIM2 0x00000008 +#define CLCD_TIM3 0x0000000c +#define CLCD_UBAS 0x00000010 +#define CLCD_LBAS 0x00000014 + +#define CLCD_PL110_IENB 0x00000018 +#define CLCD_PL110_CNTL 0x0000001c +#define CLCD_PL110_STAT 0x00000020 +#define CLCD_PL110_INTR 0x00000024 +#define CLCD_PL110_UCUR 0x00000028 +#define CLCD_PL110_LCUR 0x0000002C + +#define CLCD_PL111_CNTL 0x00000018 +#define CLCD_PL111_IENB 0x0000001c +#define CLCD_PL111_RIS 0x00000020 +#define CLCD_PL111_MIS 0x00000024 +#define CLCD_PL111_ICR 0x00000028 +#define CLCD_PL111_UCUR 0x0000002c +#define CLCD_PL111_LCUR 0x00000030 + +#define CLCD_PALL 0x00000200 +#define CLCD_PALETTE 0x00000200 + +#define TIM2_PCD_LO_MASK GENMASK(4, 0) +#define TIM2_PCD_LO_BITS 5 +#define TIM2_CLKSEL (1 << 5) +#define TIM2_ACB_MASK GENMASK(10, 6) +#define TIM2_IVS (1 << 11) +#define TIM2_IHS (1 << 12) +#define TIM2_IPC (1 << 13) +#define TIM2_IOE (1 << 14) +#define TIM2_BCD (1 << 26) +#define TIM2_PCD_HI_MASK GENMASK(31, 27) +#define TIM2_PCD_HI_BITS 5 +#define TIM2_PCD_HI_SHIFT 27 + +#define CNTL_LCDEN (1 << 0) +#define CNTL_LCDBPP1 (0 << 1) +#define CNTL_LCDBPP2 (1 << 1) +#define CNTL_LCDBPP4 (2 << 1) +#define CNTL_LCDBPP8 (3 << 1) +#define CNTL_LCDBPP16 (4 << 1) +#define CNTL_LCDBPP16_565 (6 << 1) +#define CNTL_LCDBPP16_444 (7 << 1) +#define CNTL_LCDBPP24 (5 << 1) +#define CNTL_LCDBW (1 << 4) +#define CNTL_LCDTFT (1 << 5) +#define CNTL_LCDMONO8 (1 << 6) +#define CNTL_LCDDUAL (1 << 7) +#define CNTL_BGR (1 << 8) +#define CNTL_BEBO (1 << 9) +#define CNTL_BEPO (1 << 10) +#define CNTL_LCDPWR (1 << 11) +#define CNTL_LCDVCOMP(x) ((x) << 12) +#define CNTL_LDMAFIFOTIME (1 << 15) +#define CNTL_WATERMARK (1 << 16) + +/* ST Microelectronics variant bits */ +#define CNTL_ST_1XBPP_444 0x0 +#define CNTL_ST_1XBPP_5551 (1 << 17) +#define CNTL_ST_1XBPP_565 (1 << 18) +#define CNTL_ST_CDWID_12 0x0 +#define CNTL_ST_CDWID_16 (1 << 19) +#define CNTL_ST_CDWID_18 (1 << 20) +#define CNTL_ST_CDWID_24 ((1 << 19)|(1 << 20)) +#define CNTL_ST_CEAEN (1 << 21) +#define CNTL_ST_LCDBPP24_PACKED (6 << 1) + +#endif /* AMBA_CLCD_REGS_H */ diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h new file mode 100644 index 000000000000..b6e0cbeaf533 --- /dev/null +++ b/include/linux/amba/clcd.h @@ -0,0 +1,290 @@ +/* + * linux/include/asm-arm/hardware/amba_clcd.h -- Integrator LCD panel. + * + * David A Rusling + * + * Copyright (C) 2001 ARM Limited + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ +#include <linux/fb.h> +#include <linux/amba/clcd-regs.h> + +enum { + /* individual formats */ + CLCD_CAP_RGB444 = (1 << 0), + CLCD_CAP_RGB5551 = (1 << 1), + CLCD_CAP_RGB565 = (1 << 2), + CLCD_CAP_RGB888 = (1 << 3), + CLCD_CAP_BGR444 = (1 << 4), + CLCD_CAP_BGR5551 = (1 << 5), + CLCD_CAP_BGR565 = (1 << 6), + CLCD_CAP_BGR888 = (1 << 7), + + /* connection layouts */ + CLCD_CAP_444 = CLCD_CAP_RGB444 | CLCD_CAP_BGR444, + CLCD_CAP_5551 = CLCD_CAP_RGB5551 | CLCD_CAP_BGR5551, + CLCD_CAP_565 = CLCD_CAP_RGB565 | CLCD_CAP_BGR565, + CLCD_CAP_888 = CLCD_CAP_RGB888 | CLCD_CAP_BGR888, + + /* red/blue ordering */ + CLCD_CAP_RGB = CLCD_CAP_RGB444 | CLCD_CAP_RGB5551 | + CLCD_CAP_RGB565 | CLCD_CAP_RGB888, + CLCD_CAP_BGR = CLCD_CAP_BGR444 | CLCD_CAP_BGR5551 | + CLCD_CAP_BGR565 | CLCD_CAP_BGR888, + + CLCD_CAP_ALL = CLCD_CAP_BGR | CLCD_CAP_RGB, +}; + +struct backlight_device; + +struct clcd_panel { + struct fb_videomode mode; + signed short width; /* width in mm */ + signed short height; /* height in mm */ + u32 tim2; + u32 tim3; + u32 cntl; + u32 caps; + unsigned int bpp:8, + fixedtimings:1, + grayscale:1; + unsigned int connector; + struct backlight_device *backlight; + /* + * If the B/R lines are switched between the CLCD + * and the panel we need to know this and not try to + * compensate with the BGR bit in the control register. + */ + bool bgr_connection; +}; + +struct clcd_regs { + u32 tim0; + u32 tim1; + u32 tim2; + u32 tim3; + u32 cntl; + unsigned long pixclock; +}; + +struct clcd_fb; + +/* + * the board-type specific routines + */ +struct clcd_board { + const char *name; + + /* + * Optional. Hardware capability flags. + */ + u32 caps; + + /* + * Optional. Check whether the var structure is acceptable + * for this display. + */ + int (*check)(struct clcd_fb *fb, struct fb_var_screeninfo *var); + + /* + * Compulsory. Decode fb->fb.var into regs->*. In the case of + * fixed timing, set regs->* to the register values required. + */ + void (*decode)(struct clcd_fb *fb, struct clcd_regs *regs); + + /* + * Optional. Disable any extra display hardware. + */ + void (*disable)(struct clcd_fb *); + + /* + * Optional. Enable any extra display hardware. + */ + void (*enable)(struct clcd_fb *); + + /* + * Setup platform specific parts of CLCD driver + */ + int (*setup)(struct clcd_fb *); + + /* + * mmap the framebuffer memory + */ + int (*mmap)(struct clcd_fb *, struct vm_area_struct *); + + /* + * Remove platform specific parts of CLCD driver + */ + void (*remove)(struct clcd_fb *); +}; + +struct amba_device; +struct clk; + +/* this data structure describes each frame buffer device we find */ +struct clcd_fb { + struct fb_info fb; + struct amba_device *dev; + struct clk *clk; + struct clcd_panel *panel; + struct clcd_board *board; + void *board_data; + void __iomem *regs; + u16 off_ienb; + u16 off_cntl; + u32 clcd_cntl; + u32 cmap[16]; + bool clk_enabled; +}; + +static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs) +{ + struct fb_var_screeninfo *var = &fb->fb.var; + u32 val, cpl; + + /* + * Program the CLCD controller registers and start the CLCD + */ + val = ((var->xres / 16) - 1) << 2; + val |= (var->hsync_len - 1) << 8; + val |= (var->right_margin - 1) << 16; + val |= (var->left_margin - 1) << 24; + regs->tim0 = val; + + val = var->yres; + if (fb->panel->cntl & CNTL_LCDDUAL) + val /= 2; + val -= 1; + val |= (var->vsync_len - 1) << 10; + val |= var->lower_margin << 16; + val |= var->upper_margin << 24; + regs->tim1 = val; + + val = fb->panel->tim2; + val |= var->sync & FB_SYNC_HOR_HIGH_ACT ? 0 : TIM2_IHS; + val |= var->sync & FB_SYNC_VERT_HIGH_ACT ? 0 : TIM2_IVS; + + cpl = var->xres_virtual; + if (fb->panel->cntl & CNTL_LCDTFT) /* TFT */ + /* / 1 */; + else if (!var->grayscale) /* STN color */ + cpl = cpl * 8 / 3; + else if (fb->panel->cntl & CNTL_LCDMONO8) /* STN monochrome, 8bit */ + cpl /= 8; + else /* STN monochrome, 4bit */ + cpl /= 4; + + regs->tim2 = val | ((cpl - 1) << 16); + + regs->tim3 = fb->panel->tim3; + + val = fb->panel->cntl; + if (var->grayscale) + val |= CNTL_LCDBW; + + if (fb->panel->caps && fb->board->caps && var->bits_per_pixel >= 16) { + /* + * if board and panel supply capabilities, we can support + * changing BGR/RGB depending on supplied parameters. Here + * we switch to what the framebuffer is providing if need + * be, so if the framebuffer is BGR but the display connection + * is RGB (first case) we switch it around. Vice versa mutatis + * mutandis if the framebuffer is RGB but the display connection + * is BGR, we flip it around. + */ + if (var->red.offset == 0) + val &= ~CNTL_BGR; + else + val |= CNTL_BGR; + if (fb->panel->bgr_connection) + val ^= CNTL_BGR; + } + + switch (var->bits_per_pixel) { + case 1: + val |= CNTL_LCDBPP1; + break; + case 2: + val |= CNTL_LCDBPP2; + break; + case 4: + val |= CNTL_LCDBPP4; + break; + case 8: + val |= CNTL_LCDBPP8; + break; + case 16: + /* + * PL110 cannot choose between 5551 and 565 modes in its + * control register. It is possible to use 565 with + * custom external wiring. + */ + if (amba_part(fb->dev) == 0x110 || + var->green.length == 5) + val |= CNTL_LCDBPP16; + else if (var->green.length == 6) + val |= CNTL_LCDBPP16_565; + else + val |= CNTL_LCDBPP16_444; + break; + case 32: + val |= CNTL_LCDBPP24; + break; + } + + regs->cntl = val; + regs->pixclock = var->pixclock; +} + +static inline int clcdfb_check(struct clcd_fb *fb, struct fb_var_screeninfo *var) +{ + var->xres_virtual = var->xres = (var->xres + 15) & ~15; + var->yres_virtual = var->yres = (var->yres + 1) & ~1; + +#define CHECK(e,l,h) (var->e < l || var->e > h) + if (CHECK(right_margin, (5+1), 256) || /* back porch */ + CHECK(left_margin, (5+1), 256) || /* front porch */ + CHECK(hsync_len, (5+1), 256) || + var->xres > 4096 || + var->lower_margin > 255 || /* back porch */ + var->upper_margin > 255 || /* front porch */ + var->vsync_len > 32 || + var->yres > 1024) + return -EINVAL; +#undef CHECK + + /* single panel mode: PCD = max(PCD, 1) */ + /* dual panel mode: PCD = max(PCD, 5) */ + + /* + * You can't change the grayscale setting, and + * we can only do non-interlaced video. + */ + if (var->grayscale != fb->fb.var.grayscale || + (var->vmode & FB_VMODE_MASK) != FB_VMODE_NONINTERLACED) + return -EINVAL; + +#define CHECK(e) (var->e != fb->fb.var.e) + if (fb->panel->fixedtimings && + (CHECK(xres) || + CHECK(yres) || + CHECK(bits_per_pixel) || + CHECK(pixclock) || + CHECK(left_margin) || + CHECK(right_margin) || + CHECK(upper_margin) || + CHECK(lower_margin) || + CHECK(hsync_len) || + CHECK(vsync_len) || + CHECK(sync))) + return -EINVAL; +#undef CHECK + + var->nonstd = 0; + var->accel_flags = 0; + + return 0; +} diff --git a/include/linux/font.h b/include/linux/font.h index 51b91c8b69d5..59faa80f586d 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -59,4 +59,17 @@ extern const struct font_desc *get_default_font(int xres, int yres, /* Max. length for the name of a predefined font */ #define MAX_FONT_NAME 32 +/* Extra word getters */ +#define REFCOUNT(fd) (((int *)(fd))[-1]) +#define FNTSIZE(fd) (((int *)(fd))[-2]) +#define FNTCHARCNT(fd) (((int *)(fd))[-3]) +#define FNTSUM(fd) (((int *)(fd))[-4]) + +#define FONT_EXTRA_WORDS 4 + +struct font_data { + unsigned int extra[FONT_EXTRA_WORDS]; + const unsigned char data[]; +} __packed; + #endif /* _VIDEO_FONT_H */ diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index bc45ea1efbf7..c941b7377321 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -15,6 +15,7 @@ extern int __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma, unsigned long vm_flags); +extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); #else @@ -85,6 +86,10 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) { } + +static inline void khugepaged_min_free_kbytes_update(void) +{ +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_KHUGEPAGED_H */ diff --git a/include/linux/memstick.h b/include/linux/memstick.h index da4c65f9435f..ebf73d4ee969 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -281,6 +281,7 @@ struct memstick_host { struct memstick_dev *card; unsigned int retries; + bool removing; /* Notify the host that some requests are pending. */ void (*request)(struct memstick_host *host); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c145de0473bc..372100c755e7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -767,6 +767,8 @@ struct mlx5_cmd_work_ent { u64 ts2; u16 op; bool polling; + /* Track the max comp handlers */ + refcount_t refcnt; }; struct mlx5_pas { @@ -933,6 +935,7 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); +bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); diff --git a/include/linux/net.h b/include/linux/net.h index d48ff1180879..ae713c851342 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -21,6 +21,7 @@ #include <linux/rcupdate.h> #include <linux/once.h> #include <linux/fs.h> +#include <linux/mm.h> #include <linux/sockptr.h> #include <uapi/linux/net.h> @@ -286,6 +287,21 @@ do { \ #define net_get_random_once_wait(buf, nbytes) \ get_random_once_wait((buf), (nbytes)) +/* + * E.g. XFS meta- & log-data is in slab pages, or bcache meta + * data pages, or other high order pages allocated by + * __get_free_pages() without __GFP_COMP, which have a page_count + * of 0 and/or have PageSlab() set. We cannot use send_page for + * those, as that does get_page(); put_page(); and would cause + * either a VM_BUG directly, or __page_cache_release a page that + * would actually still be referenced by someone, leading to some + * obscure delayed Oops somewhere else. + */ +static inline bool sendpage_ok(struct page *page) +{ + return !PageSlab(page) && page_count(page) >= 1; +} + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7bd4fcdd0738..18dec08439f9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1851,6 +1851,11 @@ enum netdev_priv_flags { * @udp_tunnel_nic: UDP tunnel offload state * @xdp_state: stores info on attached XDP BPF programs * + * @nested_level: Used as as a parameter of spin_lock_nested() of + * dev->addr_list_lock. + * @unlink_list: As netif_addr_lock() can be called recursively, + * keep a list of interfaces to be deleted. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -1955,6 +1960,7 @@ struct net_device { unsigned short type; unsigned short hard_header_len; unsigned char min_header_len; + unsigned char name_assign_type; unsigned short needed_headroom; unsigned short needed_tailroom; @@ -1965,12 +1971,12 @@ struct net_device { unsigned char addr_len; unsigned char upper_level; unsigned char lower_level; + unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; spinlock_t addr_list_lock; - unsigned char name_assign_type; - bool uc_promisc; + struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; struct netdev_hw_addr_list dev_addrs; @@ -1978,8 +1984,15 @@ struct net_device { #ifdef CONFIG_SYSFS struct kset *queues_kset; #endif +#ifdef CONFIG_LOCKDEP + struct list_head unlink_list; +#endif unsigned int promiscuity; unsigned int allmulti; + bool uc_promisc; +#ifdef CONFIG_LOCKDEP + unsigned char nested_level; +#endif /* Protocol-specific pointers */ @@ -4260,17 +4273,23 @@ static inline void netif_tx_disable(struct net_device *dev) static inline void netif_addr_lock(struct net_device *dev) { - spin_lock(&dev->addr_list_lock); -} + unsigned char nest_level = 0; -static inline void netif_addr_lock_nested(struct net_device *dev) -{ - spin_lock_nested(&dev->addr_list_lock, dev->lower_level); +#ifdef CONFIG_LOCKDEP + nest_level = dev->nested_level; +#endif + spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_lock_bh(struct net_device *dev) { - spin_lock_bh(&dev->addr_list_lock); + unsigned char nest_level = 0; + +#ifdef CONFIG_LOCKDEP + nest_level = dev->nested_level; +#endif + local_bh_disable(); + spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_unlock(struct net_device *dev) @@ -4455,12 +4474,38 @@ extern int dev_rx_weight; extern int dev_tx_weight; extern int gro_normal_batch; +enum { + NESTED_SYNC_IMM_BIT, + NESTED_SYNC_TODO_BIT, +}; + +#define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit)) +#define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT) + +#define NESTED_SYNC_IMM __NESTED_SYNC(IMM) +#define NESTED_SYNC_TODO __NESTED_SYNC(TODO) + +struct netdev_nested_priv { + unsigned char flags; + void *data; +}; + bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); +#ifdef CONFIG_LOCKDEP +static LIST_HEAD(net_unlink_list); + +static inline void net_unlink_todo(struct net_device *dev) +{ + if (list_empty(&dev->unlink_list)) + list_add_tail(&dev->unlink_list, &net_unlink_list); +} +#endif + /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->adj_list.upper, \ @@ -4470,8 +4515,8 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *upper_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev); @@ -4508,12 +4553,12 @@ struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *lower_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 7de11dcd534d..434c9c34aeb6 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -54,7 +54,8 @@ static inline void mapping_set_error(struct address_space *mapping, int error) __filemap_set_wb_err(mapping, error); /* Record it in superblock */ - errseq_set(&mapping->host->i_sb->s_wb_err, error); + if (mapping->host) + errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 50afd0d0084c..5d2705f1d01c 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -240,8 +240,9 @@ extern unsigned int pipe_max_size; extern unsigned long pipe_user_pages_hard; extern unsigned long pipe_user_pages_soft; -/* Drop the inode semaphore and wait for a pipe event, atomically */ -void pipe_wait(struct pipe_inode_info *pipe); +/* Wait for a pipe to be readable/writable while dropping the pipe lock */ +void pipe_wait_readable(struct pipe_inode_info *); +void pipe_wait_writable(struct pipe_inode_info *); struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); diff --git a/include/linux/platform_data/gpio/gpio-amd-fch.h b/include/linux/platform_data/gpio/gpio-amd-fch.h index 9e46678edb2a..255d51c9d36d 100644 --- a/include/linux/platform_data/gpio/gpio-amd-fch.h +++ b/include/linux/platform_data/gpio/gpio-amd-fch.h @@ -19,7 +19,7 @@ #define AMD_FCH_GPIO_REG_GPIO49 0x40 #define AMD_FCH_GPIO_REG_GPIO50 0x41 #define AMD_FCH_GPIO_REG_GPIO51 0x42 -#define AMD_FCH_GPIO_REG_GPIO59_DEVSLP0 0x43 +#define AMD_FCH_GPIO_REG_GPIO55_DEVSLP0 0x43 #define AMD_FCH_GPIO_REG_GPIO57 0x44 #define AMD_FCH_GPIO_REG_GPIO58 0x45 #define AMD_FCH_GPIO_REG_GPIO59_DEVSLP1 0x46 diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 91220ace31da..7557c1070fd7 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -312,6 +312,11 @@ static inline void __mod_zone_page_state(struct zone *zone, static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { + if (vmstat_item_in_bytes(item)) { + VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); + delta >>= PAGE_SHIFT; + } + node_page_state_add(delta, pgdat, item); } diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h index 5e08db2adc31..c994d1b2cdba 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -122,6 +122,12 @@ static inline void remove_watch_list(struct watch_list *wlist, u64 id) */ #define watch_sizeof(STRUCT) (sizeof(STRUCT) << WATCH_INFO_LENGTH__SHIFT) +#else +static inline int watch_queue_init(struct pipe_inode_info *pipe) +{ + return -ENOPKG; +} + #endif #endif /* _LINUX_WATCH_QUEUE_H */ diff --git a/include/net/act_api.h b/include/net/act_api.h index cb382a89ea58..87214927314a 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -166,8 +166,6 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, u32 flags); -void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a); - void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tc_action **a, int bind); diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 6e5f1e1aa822..8899d7429ccb 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -138,6 +138,7 @@ genl_dumpit_info(struct netlink_callback *cb) * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags + * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers diff --git a/include/net/ip.h b/include/net/ip.h index b09c48d862cc..2a52787db64a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -436,12 +436,18 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { struct net *net = dev_net(dst->dev); + unsigned int mtu; if (net->ipv4.sysctl_ip_fwd_use_pmtu || ip_mtu_locked(dst) || !forwarding) return dst_mtu(dst); + /* 'forwarding = true' case should always honour route mtu */ + mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + return mtu; + return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); } diff --git a/include/net/netlink.h b/include/net/netlink.h index 8e0eb2c9c528..271620f6bc7f 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1934,7 +1934,8 @@ void nla_get_range_signed(const struct nla_policy *pt, int netlink_policy_dump_start(const struct nla_policy *policy, unsigned int maxtype, unsigned long *state); -bool netlink_policy_dump_loop(unsigned long *state); +bool netlink_policy_dump_loop(unsigned long state); int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state); +void netlink_policy_dump_free(unsigned long state); #endif diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 2737d24ec244..9e806c781025 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1773,21 +1773,17 @@ static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_es static inline int xfrm_replay_clone(struct xfrm_state *x, struct xfrm_state *orig) { - x->replay_esn = kzalloc(xfrm_replay_state_esn_len(orig->replay_esn), + + x->replay_esn = kmemdup(orig->replay_esn, + xfrm_replay_state_esn_len(orig->replay_esn), GFP_KERNEL); if (!x->replay_esn) return -ENOMEM; - - x->replay_esn->bmp_len = orig->replay_esn->bmp_len; - x->replay_esn->replay_window = orig->replay_esn->replay_window; - - x->preplay_esn = kmemdup(x->replay_esn, - xfrm_replay_state_esn_len(x->replay_esn), + x->preplay_esn = kmemdup(orig->preplay_esn, + xfrm_replay_state_esn_len(orig->preplay_esn), GFP_KERNEL); - if (!x->preplay_esn) { - kfree(x->replay_esn); + if (!x->preplay_esn) return -ENOMEM; - } return 0; } diff --git a/include/soc/mscc/ocelot_ana.h b/include/soc/mscc/ocelot_ana.h index 841c6ec22b64..1669481d9779 100644 --- a/include/soc/mscc/ocelot_ana.h +++ b/include/soc/mscc/ocelot_ana.h @@ -252,10 +252,10 @@ #define ANA_SG_CONFIG_REG_3_LIST_LENGTH_M GENMASK(18, 16) #define ANA_SG_CONFIG_REG_3_LIST_LENGTH_X(x) (((x) & GENMASK(18, 16)) >> 16) #define ANA_SG_CONFIG_REG_3_GATE_ENABLE BIT(20) -#define ANA_SG_CONFIG_REG_3_INIT_IPS(x) (((x) << 24) & GENMASK(27, 24)) -#define ANA_SG_CONFIG_REG_3_INIT_IPS_M GENMASK(27, 24) -#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x) (((x) & GENMASK(27, 24)) >> 24) -#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(28) +#define ANA_SG_CONFIG_REG_3_INIT_IPS(x) (((x) << 21) & GENMASK(24, 21)) +#define ANA_SG_CONFIG_REG_3_INIT_IPS_M GENMASK(24, 21) +#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x) (((x) & GENMASK(24, 21)) >> 21) +#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(25) #define ANA_SG_GCL_GS_CONFIG_RSZ 0x4 diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h index 4accfa7e266d..8f8dc7a937a4 100644 --- a/include/uapi/linux/rxrpc.h +++ b/include/uapi/linux/rxrpc.h @@ -51,11 +51,11 @@ enum rxrpc_cmsg_type { RXRPC_BUSY = 6, /* -r: server busy received [terminal] */ RXRPC_LOCAL_ERROR = 7, /* -r: local error generated [terminal] */ RXRPC_NEW_CALL = 8, /* -r: [Service] new incoming call notification */ - RXRPC_ACCEPT = 9, /* s-: [Service] accept request */ RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */ RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */ RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */ RXRPC_SET_CALL_TIMEOUT = 13, /* s-: Set one or more call timeouts */ + RXRPC_CHARGE_ACCEPT = 14, /* s-: Charge the accept pool with a user call ID */ RXRPC__SUPPORTED }; diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index cee9f8e6fce3..f84e7bcad6de 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -288,6 +288,7 @@ enum LINUX_MIB_TCPTIMEOUTREHASH, /* TCPTimeoutRehash */ LINUX_MIB_TCPDUPLICATEDATAREHASH, /* TCPDuplicateDataRehash */ LINUX_MIB_TCPDSACKRECVSEGS, /* TCPDSACKRecvSegs */ + LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */ __LINUX_MIB_MAX }; diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index 39df751d0dc4..ac1b65470563 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -83,6 +83,9 @@ static inline unsigned long bfn_to_pfn(unsigned long bfn) }) #define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT)) +#define percpu_to_gfn(v) \ + (pfn_to_gfn(per_cpu_ptr_to_phys(v) >> XEN_PAGE_SHIFT)) + /* Only used in PV code. But ARM guests are always HVM. */ static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr) { diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c index 3b495773de5a..11b3380887fa 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -30,15 +30,15 @@ static struct kobject *btf_kobj; static int __init btf_vmlinux_init(void) { - if (!__start_BTF) + bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF; + + if (!__start_BTF || bin_attr_btf_vmlinux.size == 0) return 0; btf_kobj = kobject_create_and_add("btf", kernel_kobj); if (!btf_kobj) return -ENOMEM; - bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF; - return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 47e74f09fa37..fba52d9ec8fc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5667,8 +5667,8 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); - s32 smin_val = src_reg->smin_value; - u32 umin_val = src_reg->umin_value; + s32 smin_val = src_reg->s32_min_value; + u32 umin_val = src_reg->u32_min_value; /* Assuming scalar64_min_max_or will be called so it is safe * to skip updating register for known case. @@ -5691,8 +5691,8 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, /* ORing two positives gives a positive, so safe to * cast result into s64. */ - dst_reg->s32_min_value = dst_reg->umin_value; - dst_reg->s32_max_value = dst_reg->umax_value; + dst_reg->s32_min_value = dst_reg->u32_min_value; + dst_reg->s32_max_value = dst_reg->u32_max_value; } } diff --git a/kernel/events/core.c b/kernel/events/core.c index 7ed5248f0445..e8bf92202542 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -99,7 +99,7 @@ static void remote_function(void *data) * retry due to any failures in smp_call_function_single(), such as if the * task_cpu() goes offline concurrently. * - * returns @func return value or -ESRCH when the process isn't running + * returns @func return value or -ESRCH or -ENXIO when the process isn't running */ static int task_function_call(struct task_struct *p, remote_function_f func, void *info) @@ -115,7 +115,8 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info) for (;;) { ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1); - ret = !ret ? data.ret : -EAGAIN; + if (!ret) + ret = data.ret; if (ret != -EAGAIN) break; diff --git a/kernel/umh.c b/kernel/umh.c index fcf3ee803630..3f646613a9d3 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -14,6 +14,7 @@ #include <linux/cred.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/fs_struct.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> @@ -72,6 +73,14 @@ static int call_usermodehelper_exec_async(void *data) spin_unlock_irq(¤t->sighand->siglock); /* + * Initial kernel threads share ther FS with init, in order to + * get the init root directory. But we've now created a new + * thread that is going to execve a user process and has its own + * 'struct fs_struct'. Reset umask to the default. + */ + current->fs->umask = 0022; + + /* * Our parent (unbound workqueue) runs with elevated scheduling * priority. Avoid propagating that into the userspace child. */ diff --git a/lib/fonts/font_10x18.c b/lib/fonts/font_10x18.c index 532f0ff89a96..0e2deac97da0 100644 --- a/lib/fonts/font_10x18.c +++ b/lib/fonts/font_10x18.c @@ -8,8 +8,8 @@ #define FONTDATAMAX 9216 -static const unsigned char fontdata_10x18[FONTDATAMAX] = { - +static struct font_data fontdata_10x18 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, 0x00, /* 0000000000 */ 0x00, 0x00, /* 0000000000 */ @@ -5129,8 +5129,7 @@ static const unsigned char fontdata_10x18[FONTDATAMAX] = { 0x00, 0x00, /* 0000000000 */ 0x00, 0x00, /* 0000000000 */ 0x00, 0x00, /* 0000000000 */ - -}; +} }; const struct font_desc font_10x18 = { @@ -5138,7 +5137,7 @@ const struct font_desc font_10x18 = { .name = "10x18", .width = 10, .height = 18, - .data = fontdata_10x18, + .data = fontdata_10x18.data, #ifdef __sparc__ .pref = 5, #else diff --git a/lib/fonts/font_6x10.c b/lib/fonts/font_6x10.c index 09b2cc03435b..87da8acd07db 100644 --- a/lib/fonts/font_6x10.c +++ b/lib/fonts/font_6x10.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/font.h> -static const unsigned char fontdata_6x10[] = { +#define FONTDATAMAX 2560 +static struct font_data fontdata_6x10 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -3074,14 +3076,13 @@ static const unsigned char fontdata_6x10[] = { 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} }; const struct font_desc font_6x10 = { .idx = FONT6x10_IDX, .name = "6x10", .width = 6, .height = 10, - .data = fontdata_6x10, + .data = fontdata_6x10.data, .pref = 0, }; diff --git a/lib/fonts/font_6x11.c b/lib/fonts/font_6x11.c index d7136c33f1f0..5e975dfa10a5 100644 --- a/lib/fonts/font_6x11.c +++ b/lib/fonts/font_6x11.c @@ -9,8 +9,8 @@ #define FONTDATAMAX (11*256) -static const unsigned char fontdata_6x11[FONTDATAMAX] = { - +static struct font_data fontdata_6x11 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -3338,8 +3338,7 @@ static const unsigned char fontdata_6x11[FONTDATAMAX] = { 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} }; const struct font_desc font_vga_6x11 = { @@ -3347,7 +3346,7 @@ const struct font_desc font_vga_6x11 = { .name = "ProFont6x11", .width = 6, .height = 11, - .data = fontdata_6x11, + .data = fontdata_6x11.data, /* Try avoiding this font if possible unless on MAC */ .pref = -2000, }; diff --git a/lib/fonts/font_7x14.c b/lib/fonts/font_7x14.c index 89752d0b23e8..86d298f38505 100644 --- a/lib/fonts/font_7x14.c +++ b/lib/fonts/font_7x14.c @@ -8,8 +8,8 @@ #define FONTDATAMAX 3584 -static const unsigned char fontdata_7x14[FONTDATAMAX] = { - +static struct font_data fontdata_7x14 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 0000000 */ 0x00, /* 0000000 */ @@ -4105,8 +4105,7 @@ static const unsigned char fontdata_7x14[FONTDATAMAX] = { 0x00, /* 0000000 */ 0x00, /* 0000000 */ 0x00, /* 0000000 */ - -}; +} }; const struct font_desc font_7x14 = { @@ -4114,6 +4113,6 @@ const struct font_desc font_7x14 = { .name = "7x14", .width = 7, .height = 14, - .data = fontdata_7x14, + .data = fontdata_7x14.data, .pref = 0, }; diff --git a/lib/fonts/font_8x16.c b/lib/fonts/font_8x16.c index b7ab1f5fbdb8..37cedd36ca5e 100644 --- a/lib/fonts/font_8x16.c +++ b/lib/fonts/font_8x16.c @@ -10,8 +10,8 @@ #define FONTDATAMAX 4096 -static const unsigned char fontdata_8x16[FONTDATAMAX] = { - +static struct font_data fontdata_8x16 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -4619,8 +4619,7 @@ static const unsigned char fontdata_8x16[FONTDATAMAX] = { 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} }; const struct font_desc font_vga_8x16 = { @@ -4628,7 +4627,7 @@ const struct font_desc font_vga_8x16 = { .name = "VGA8x16", .width = 8, .height = 16, - .data = fontdata_8x16, + .data = fontdata_8x16.data, .pref = 0, }; EXPORT_SYMBOL(font_vga_8x16); diff --git a/lib/fonts/font_8x8.c b/lib/fonts/font_8x8.c index 2328ebc8bab5..8ab695538395 100644 --- a/lib/fonts/font_8x8.c +++ b/lib/fonts/font_8x8.c @@ -9,8 +9,8 @@ #define FONTDATAMAX 2048 -static const unsigned char fontdata_8x8[FONTDATAMAX] = { - +static struct font_data fontdata_8x8 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -2570,8 +2570,7 @@ static const unsigned char fontdata_8x8[FONTDATAMAX] = { 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} }; const struct font_desc font_vga_8x8 = { @@ -2579,6 +2578,6 @@ const struct font_desc font_vga_8x8 = { .name = "VGA8x8", .width = 8, .height = 8, - .data = fontdata_8x8, + .data = fontdata_8x8.data, .pref = 0, }; diff --git a/lib/fonts/font_acorn_8x8.c b/lib/fonts/font_acorn_8x8.c index 0ff0e85d4481..069b3e80c434 100644 --- a/lib/fonts/font_acorn_8x8.c +++ b/lib/fonts/font_acorn_8x8.c @@ -3,7 +3,10 @@ #include <linux/font.h> -static const unsigned char acorndata_8x8[] = { +#define FONTDATAMAX 2048 + +static struct font_data acorndata_8x8 = { +{ 0, 0, FONTDATAMAX, 0 }, { /* 00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* ^@ */ /* 01 */ 0x7e, 0x81, 0xa5, 0x81, 0xbd, 0x99, 0x81, 0x7e, /* ^A */ /* 02 */ 0x7e, 0xff, 0xbd, 0xff, 0xc3, 0xe7, 0xff, 0x7e, /* ^B */ @@ -260,14 +263,14 @@ static const unsigned char acorndata_8x8[] = { /* FD */ 0x38, 0x04, 0x18, 0x20, 0x3c, 0x00, 0x00, 0x00, /* FE */ 0x00, 0x00, 0x3c, 0x3c, 0x3c, 0x3c, 0x00, 0x00, /* FF */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 -}; +} }; const struct font_desc font_acorn_8x8 = { .idx = ACORN8x8_IDX, .name = "Acorn8x8", .width = 8, .height = 8, - .data = acorndata_8x8, + .data = acorndata_8x8.data, #ifdef CONFIG_ARCH_ACORN .pref = 20, #else diff --git a/lib/fonts/font_mini_4x6.c b/lib/fonts/font_mini_4x6.c index 838caa1cfef7..1449876c6a27 100644 --- a/lib/fonts/font_mini_4x6.c +++ b/lib/fonts/font_mini_4x6.c @@ -43,8 +43,8 @@ __END__; #define FONTDATAMAX 1536 -static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = { - +static struct font_data fontdata_mini_4x6 = { + { 0, 0, FONTDATAMAX, 0 }, { /*{*/ /* Char 0: ' ' */ 0xee, /*= [*** ] */ @@ -2145,14 +2145,14 @@ static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = { 0xee, /*= [*** ] */ 0x00, /*= [ ] */ /*}*/ -}; +} }; const struct font_desc font_mini_4x6 = { .idx = MINI4x6_IDX, .name = "MINI4x6", .width = 4, .height = 6, - .data = fontdata_mini_4x6, + .data = fontdata_mini_4x6.data, .pref = 3, }; diff --git a/lib/fonts/font_pearl_8x8.c b/lib/fonts/font_pearl_8x8.c index b15d3c342c5b..32d65551e7ed 100644 --- a/lib/fonts/font_pearl_8x8.c +++ b/lib/fonts/font_pearl_8x8.c @@ -14,8 +14,8 @@ #define FONTDATAMAX 2048 -static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = { - +static struct font_data fontdata_pearl8x8 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -2575,14 +2575,13 @@ static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = { 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} }; const struct font_desc font_pearl_8x8 = { .idx = PEARL8x8_IDX, .name = "PEARL8x8", .width = 8, .height = 8, - .data = fontdata_pearl8x8, + .data = fontdata_pearl8x8.data, .pref = 2, }; diff --git a/lib/fonts/font_sun12x22.c b/lib/fonts/font_sun12x22.c index 955d6eee3959..641a6b4dca42 100644 --- a/lib/fonts/font_sun12x22.c +++ b/lib/fonts/font_sun12x22.c @@ -3,8 +3,8 @@ #define FONTDATAMAX 11264 -static const unsigned char fontdata_sun12x22[FONTDATAMAX] = { - +static struct font_data fontdata_sun12x22 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, 0x00, /* 000000000000 */ 0x00, 0x00, /* 000000000000 */ @@ -6148,8 +6148,7 @@ static const unsigned char fontdata_sun12x22[FONTDATAMAX] = { 0x00, 0x00, /* 000000000000 */ 0x00, 0x00, /* 000000000000 */ 0x00, 0x00, /* 000000000000 */ - -}; +} }; const struct font_desc font_sun_12x22 = { @@ -6157,7 +6156,7 @@ const struct font_desc font_sun_12x22 = { .name = "SUN12x22", .width = 12, .height = 22, - .data = fontdata_sun12x22, + .data = fontdata_sun12x22.data, #ifdef __sparc__ .pref = 5, #else diff --git a/lib/fonts/font_sun8x16.c b/lib/fonts/font_sun8x16.c index 03d71e53954a..193fe6d988e0 100644 --- a/lib/fonts/font_sun8x16.c +++ b/lib/fonts/font_sun8x16.c @@ -3,7 +3,8 @@ #define FONTDATAMAX 4096 -static const unsigned char fontdata_sun8x16[FONTDATAMAX] = { +static struct font_data fontdata_sun8x16 = { +{ 0, 0, FONTDATAMAX, 0 }, { /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x7e,0x81,0xa5,0x81,0x81,0xbd,0x99,0x81,0x81,0x7e,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x7e,0xff,0xdb,0xff,0xff,0xc3,0xe7,0xff,0xff,0x7e,0x00,0x00,0x00,0x00, @@ -260,14 +261,14 @@ static const unsigned char fontdata_sun8x16[FONTDATAMAX] = { /* */ 0x00,0x70,0xd8,0x30,0x60,0xc8,0xf8,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x00,0x00,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x00,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, -}; +} }; const struct font_desc font_sun_8x16 = { .idx = SUN8x16_IDX, .name = "SUN8x16", .width = 8, .height = 16, - .data = fontdata_sun8x16, + .data = fontdata_sun8x16.data, #ifdef __sparc__ .pref = 10, #else diff --git a/lib/fonts/font_ter16x32.c b/lib/fonts/font_ter16x32.c index 3f0cf1ccdf3a..91b9c283bd9c 100644 --- a/lib/fonts/font_ter16x32.c +++ b/lib/fonts/font_ter16x32.c @@ -4,8 +4,8 @@ #define FONTDATAMAX 16384 -static const unsigned char fontdata_ter16x32[FONTDATAMAX] = { - +static struct font_data fontdata_ter16x32 = { + { 0, 0, FONTDATAMAX, 0 }, { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0xfc, 0x7f, 0xfc, 0x70, 0x1c, 0x70, 0x1c, 0x70, 0x1c, 0x70, 0x1c, @@ -2054,8 +2054,7 @@ static const unsigned char fontdata_ter16x32[FONTDATAMAX] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 255 */ - -}; +} }; const struct font_desc font_ter_16x32 = { @@ -2063,7 +2062,7 @@ const struct font_desc font_ter_16x32 = { .name = "TER16x32", .width = 16, .height = 32, - .data = fontdata_ter16x32, + .data = fontdata_ter16x32.data, #ifdef __sparc__ .pref = 5, #else diff --git a/lib/random32.c b/lib/random32.c index 932345323af0..dfb9981ab798 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -49,7 +49,7 @@ static inline void prandom_state_selftest(void) } #endif -DEFINE_PER_CPU(struct rnd_state, net_rand_state); +DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; /** * prandom_u32_state - seeded pseudo-random number generator. diff --git a/mm/filemap.c b/mm/filemap.c index 5202e38ab79e..99c49eeae71b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2365,7 +2365,11 @@ readpage: } if (!PageUptodate(page)) { - error = lock_page_killable(page); + if (iocb->ki_flags & IOCB_WAITQ) + error = lock_page_async(page, iocb->ki_waitq); + else + error = lock_page_killable(page); + if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { diff --git a/mm/khugepaged.c b/mm/khugepaged.c index cfa0dba5fd3b..58b0d9c502a1 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -56,6 +56,9 @@ enum scan_result { #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> +static struct task_struct *khugepaged_thread __read_mostly; +static DEFINE_MUTEX(khugepaged_mutex); + /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; @@ -914,6 +917,18 @@ static struct page *khugepaged_alloc_hugepage(bool *wait) static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { + /* + * If the hpage allocated earlier was briefly exposed in page cache + * before collapse_file() failed, it is possible that racing lookups + * have not yet completed, and would then be unpleasantly surprised by + * finding the hpage reused for the same mapping at a different offset. + * Just release the previous allocation if there is any danger of that. + */ + if (*hpage && page_count(*hpage) > 1) { + put_page(*hpage); + *hpage = NULL; + } + if (!*hpage) *hpage = khugepaged_alloc_hugepage(wait); @@ -2292,8 +2307,6 @@ static void set_recommended_min_free_kbytes(void) int start_stop_khugepaged(void) { - static struct task_struct *khugepaged_thread __read_mostly; - static DEFINE_MUTEX(khugepaged_mutex); int err = 0; mutex_lock(&khugepaged_mutex); @@ -2320,3 +2333,11 @@ fail: mutex_unlock(&khugepaged_mutex); return err; } + +void khugepaged_min_free_kbytes_update(void) +{ + mutex_lock(&khugepaged_mutex); + if (khugepaged_enabled() && khugepaged_thread) + set_recommended_min_free_kbytes(); + mutex_unlock(&khugepaged_mutex); +} diff --git a/mm/memory.c b/mm/memory.c index fcfc4ca36eba..eeae590e526a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -806,8 +806,6 @@ copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm, return 1; /* - * The trick starts. - * * What we want to do is to check whether this page may * have been pinned by the parent process. If so, * instead of wrprotect the pte on both sides, we copy @@ -815,47 +813,16 @@ copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm, * the pinned page won't be randomly replaced in the * future. * - * To achieve this, we do the following: - * - * 1. Write-protect the pte if it's writable. This is - * to protect concurrent write fast-gup with - * FOLL_PIN, so that we'll fail the fast-gup with - * the write bit removed. - * - * 2. Check page_maybe_dma_pinned() to see whether this - * page may have been pinned. - * - * The order of these steps is important to serialize - * against the fast-gup code (gup_pte_range()) on the - * pte check and try_grab_compound_head(), so that - * we'll make sure either we'll capture that fast-gup - * so we'll copy the pinned page here, or we'll fail - * that fast-gup. - * - * NOTE! Even if we don't end up copying the page, - * we won't undo this wrprotect(), because the normal - * reference copy will need it anyway. - */ - if (pte_write(pte)) - ptep_set_wrprotect(src_mm, addr, src_pte); - - /* - * These are the "normally we can just copy by reference" - * checks. + * The page pinning checks are just "has this mm ever + * seen pinning", along with the (inexact) check of + * the page count. That might give false positives for + * for pinning, but it will work correctly. */ if (likely(!atomic_read(&src_mm->has_pinned))) return 1; if (likely(!page_maybe_dma_pinned(page))) return 1; - /* - * Uhhuh. It looks like the page might be a pinned page, - * and we actually need to copy it. Now we can set the - * source pte back to being writable. - */ - if (pte_write(pte)) - set_pte_at(src_mm, addr, src_pte, pte); - new_page = *prealloc; if (!new_page) return -EAGAIN; diff --git a/mm/mmap.c b/mm/mmap.c index 40248d84ad5f..bdd19f5b994e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1781,7 +1781,11 @@ unsigned long mmap_region(struct file *file, unsigned long addr, merge = vma_merge(mm, prev, vma->vm_start, vma->vm_end, vma->vm_flags, NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX); if (merge) { - fput(file); + /* ->mmap() can change vma->vm_file and fput the original file. So + * fput the vma->vm_file here or we would add an extra fput for file + * and cause general protection fault ultimately. + */ + fput(vma->vm_file); vm_area_free(vma); vma = merge; /* Update vm_flags and possible addr to pick up the change. We don't diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5661fa164f13..780c8f023b28 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -69,6 +69,7 @@ #include <linux/nmi.h> #include <linux/psi.h> #include <linux/padata.h> +#include <linux/khugepaged.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -3367,9 +3368,16 @@ struct page *rmqueue(struct zone *preferred_zone, struct page *page; if (likely(order == 0)) { - page = rmqueue_pcplist(preferred_zone, zone, gfp_flags, + /* + * MIGRATE_MOVABLE pcplist could have the pages on CMA area and + * we need to skip it when CMA area isn't allowed. + */ + if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA || + migratetype != MIGRATE_MOVABLE) { + page = rmqueue_pcplist(preferred_zone, zone, gfp_flags, migratetype, alloc_flags); - goto out; + goto out; + } } /* @@ -3381,7 +3389,13 @@ struct page *rmqueue(struct zone *preferred_zone, do { page = NULL; - if (alloc_flags & ALLOC_HARDER) { + /* + * order-0 request can reach here when the pcplist is skipped + * due to non-CMA allocation context. HIGHATOMIC area is + * reserved for high-order atomic allocation, so order-0 + * request should skip it. + */ + if (order > 0 && alloc_flags & ALLOC_HARDER) { page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); if (page) trace_mm_page_alloc_zone_locked(page, order, migratetype); @@ -7891,6 +7905,8 @@ int __meminit init_per_zone_wmark_min(void) setup_min_slab_ratio(); #endif + khugepaged_min_free_kbytes_update(); + return 0; } postcore_initcall(init_per_zone_wmark_min) diff --git a/mm/slub.c b/mm/slub.c index d4177aecedf6..6d3574013b2f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1413,10 +1413,6 @@ slab_flags_t kmem_cache_flags(unsigned int object_size, char *next_block; slab_flags_t block_flags; - /* If slub_debug = 0, it folds into the if conditional. */ - if (!slub_debug_string) - return flags | slub_debug; - len = strlen(name); next_block = slub_debug_string; /* Go through all blocks of debug options, see if any matches our slab's name */ @@ -1450,7 +1446,7 @@ slab_flags_t kmem_cache_flags(unsigned int object_size, } } - return slub_debug; + return flags | slub_debug; } #else /* !CONFIG_SLUB_DEBUG */ static inline void setup_object_debug(struct kmem_cache *s, diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index b18cdf03edb3..dfec65eca8a6 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -88,9 +88,10 @@ static void br_arp_send(struct net_bridge *br, struct net_bridge_port *p, } } -static int br_chk_addr_ip(struct net_device *dev, void *data) +static int br_chk_addr_ip(struct net_device *dev, + struct netdev_nested_priv *priv) { - __be32 ip = *(__be32 *)data; + __be32 ip = *(__be32 *)priv->data; struct in_device *in_dev; __be32 addr = 0; @@ -107,11 +108,15 @@ static int br_chk_addr_ip(struct net_device *dev, void *data) static bool br_is_local_ip(struct net_device *dev, __be32 ip) { - if (br_chk_addr_ip(dev, &ip)) + struct netdev_nested_priv priv = { + .data = (void *)&ip, + }; + + if (br_chk_addr_ip(dev, &priv)) return true; /* check if ip is configured on upper dev */ - if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &ip)) + if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &priv)) return true; return false; @@ -361,9 +366,10 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p, } } -static int br_chk_addr_ip6(struct net_device *dev, void *data) +static int br_chk_addr_ip6(struct net_device *dev, + struct netdev_nested_priv *priv) { - struct in6_addr *addr = (struct in6_addr *)data; + struct in6_addr *addr = (struct in6_addr *)priv->data; if (ipv6_chk_addr(dev_net(dev), addr, dev, 0)) return 1; @@ -374,11 +380,15 @@ static int br_chk_addr_ip6(struct net_device *dev, void *data) static bool br_is_local_ip6(struct net_device *dev, struct in6_addr *addr) { - if (br_chk_addr_ip6(dev, addr)) + struct netdev_nested_priv priv = { + .data = (void *)addr, + }; + + if (br_chk_addr_ip6(dev, &priv)) return true; /* check if ip is configured on upper dev */ - if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, addr)) + if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, &priv)) return true; return false; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 9db504baa094..32ac8343b0ba 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -413,6 +413,8 @@ void br_fdb_delete_by_port(struct net_bridge *br, if (!do_all) if (test_bit(BR_FDB_STATIC, &f->flags) || + (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags) && + !test_bit(BR_FDB_OFFLOADED, &f->flags)) || (vid && f->key.vlan_id != vid)) continue; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 147d52596e17..da310f0ca725 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -380,6 +380,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, u32 filter_mask, const struct net_device *dev) { u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + struct nlattr *af = NULL; struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; @@ -423,11 +424,18 @@ static int br_fill_ifinfo(struct sk_buff *skb, nla_nest_end(skb, nest); } + if (filter_mask & (RTEXT_FILTER_BRVLAN | + RTEXT_FILTER_BRVLAN_COMPRESSED | + RTEXT_FILTER_MRP)) { + af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); + if (!af) + goto nla_put_failure; + } + /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { struct net_bridge_vlan_group *vg; - struct nlattr *af; int err; /* RCU needed because of the VLAN locking rules (rcu || rtnl) */ @@ -441,11 +449,6 @@ static int br_fill_ifinfo(struct sk_buff *skb, rcu_read_unlock(); goto done; } - af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); - if (!af) { - rcu_read_unlock(); - goto nla_put_failure; - } if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) err = br_fill_ifvlaninfo_compressed(skb, vg); else @@ -456,32 +459,25 @@ static int br_fill_ifinfo(struct sk_buff *skb, rcu_read_unlock(); if (err) goto nla_put_failure; - - nla_nest_end(skb, af); } if (filter_mask & RTEXT_FILTER_MRP) { - struct nlattr *af; int err; if (!br_mrp_enabled(br) || port) goto done; - af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); - if (!af) - goto nla_put_failure; - rcu_read_lock(); err = br_mrp_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; - - nla_nest_end(skb, af); } done: + if (af) + nla_nest_end(skb, af); nlmsg_end(skb, nlh); return 0; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 61c94cefa843..ee8780080be5 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1360,7 +1360,7 @@ static int br_vlan_is_bind_vlan_dev(const struct net_device *dev) } static int br_vlan_is_bind_vlan_dev_fn(struct net_device *dev, - __always_unused void *data) + __always_unused struct netdev_nested_priv *priv) { return br_vlan_is_bind_vlan_dev(dev); } @@ -1383,9 +1383,9 @@ struct br_vlan_bind_walk_data { }; static int br_vlan_match_bind_vlan_dev_fn(struct net_device *dev, - void *data_in) + struct netdev_nested_priv *priv) { - struct br_vlan_bind_walk_data *data = data_in; + struct br_vlan_bind_walk_data *data = priv->data; int found = 0; if (br_vlan_is_bind_vlan_dev(dev) && @@ -1403,10 +1403,13 @@ br_vlan_get_upper_bind_vlan_dev(struct net_device *dev, u16 vid) struct br_vlan_bind_walk_data data = { .vid = vid, }; + struct netdev_nested_priv priv = { + .data = (void *)&data, + }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_match_bind_vlan_dev_fn, - &data); + &priv); rcu_read_unlock(); return data.result; @@ -1487,9 +1490,9 @@ struct br_vlan_link_state_walk_data { }; static int br_vlan_link_state_change_fn(struct net_device *vlan_dev, - void *data_in) + struct netdev_nested_priv *priv) { - struct br_vlan_link_state_walk_data *data = data_in; + struct br_vlan_link_state_walk_data *data = priv->data; if (br_vlan_is_bind_vlan_dev(vlan_dev)) br_vlan_set_vlan_dev_state(data->br, vlan_dev); @@ -1503,10 +1506,13 @@ static void br_vlan_link_state_change(struct net_device *dev, struct br_vlan_link_state_walk_data data = { .br = br }; + struct netdev_nested_priv priv = { + .data = (void *)&data, + }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_link_state_change_fn, - &data); + &priv); rcu_read_unlock(); } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index bdfd66ba3843..d4d7a0e52491 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -575,7 +575,7 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, * coalescing neighboring slab objects into a single frag which * triggers one of hardened usercopy checks. */ - if (page_count(page) >= 1 && !PageSlab(page)) + if (sendpage_ok(page)) sendpage = sock->ops->sendpage; else sendpage = sock_no_sendpage; diff --git a/net/core/dev.c b/net/core/dev.c index 266073e300b5..4906b44af850 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6812,9 +6812,10 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, return NULL; } -static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data) +static int ____netdev_has_upper_dev(struct net_device *upper_dev, + struct netdev_nested_priv *priv) { - struct net_device *dev = data; + struct net_device *dev = (struct net_device *)priv->data; return upper_dev == dev; } @@ -6831,10 +6832,14 @@ static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data) bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { + struct netdev_nested_priv priv = { + .data = (void *)upper_dev, + }; + ASSERT_RTNL(); return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, - upper_dev); + &priv); } EXPORT_SYMBOL(netdev_has_upper_dev); @@ -6851,8 +6856,12 @@ EXPORT_SYMBOL(netdev_has_upper_dev); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { + struct netdev_nested_priv priv = { + .data = (void *)upper_dev, + }; + return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, - upper_dev); + &priv); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); @@ -6997,8 +7006,8 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, static int __netdev_walk_all_upper_dev(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7010,7 +7019,7 @@ static int __netdev_walk_all_upper_dev(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7046,8 +7055,8 @@ static int __netdev_walk_all_upper_dev(struct net_device *dev, int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7058,7 +7067,7 @@ int netdev_walk_all_upper_dev_rcu(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7094,10 +7103,15 @@ EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); static bool __netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { + struct netdev_nested_priv priv = { + .flags = 0, + .data = (void *)upper_dev, + }; + ASSERT_RTNL(); return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, - upper_dev); + &priv); } /** @@ -7215,8 +7229,8 @@ static struct net_device *__netdev_next_lower_dev(struct net_device *dev, int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7227,7 +7241,7 @@ int netdev_walk_all_lower_dev(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7262,8 +7276,8 @@ EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); static int __netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7275,7 +7289,7 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7364,22 +7378,34 @@ static u8 __netdev_lower_depth(struct net_device *dev) return max_depth; } -static int __netdev_update_upper_level(struct net_device *dev, void *data) +static int __netdev_update_upper_level(struct net_device *dev, + struct netdev_nested_priv *__unused) { dev->upper_level = __netdev_upper_depth(dev) + 1; return 0; } -static int __netdev_update_lower_level(struct net_device *dev, void *data) +static int __netdev_update_lower_level(struct net_device *dev, + struct netdev_nested_priv *priv) { dev->lower_level = __netdev_lower_depth(dev) + 1; + +#ifdef CONFIG_LOCKDEP + if (!priv) + return 0; + + if (priv->flags & NESTED_SYNC_IMM) + dev->nested_level = dev->lower_level - 1; + if (priv->flags & NESTED_SYNC_TODO) + net_unlink_todo(dev); +#endif return 0; } int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7390,7 +7416,7 @@ int netdev_walk_all_lower_dev_rcu(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7650,6 +7676,7 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *upper_priv, void *upper_info, + struct netdev_nested_priv *priv, struct netlink_ext_ack *extack) { struct netdev_notifier_changeupper_info changeupper_info = { @@ -7706,9 +7733,9 @@ static int __netdev_upper_dev_link(struct net_device *dev, __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); - __netdev_update_lower_level(upper_dev, NULL); + __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, - NULL); + priv); return 0; @@ -7733,8 +7760,13 @@ int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack) { + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, + .data = NULL, + }; + return __netdev_upper_dev_link(dev, upper_dev, false, - NULL, NULL, extack); + NULL, NULL, &priv, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); @@ -7757,21 +7789,19 @@ int netdev_master_upper_dev_link(struct net_device *dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack) { + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, + .data = NULL, + }; + return __netdev_upper_dev_link(dev, upper_dev, true, - upper_priv, upper_info, extack); + upper_priv, upper_info, &priv, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); -/** - * netdev_upper_dev_unlink - Removes a link to upper device - * @dev: device - * @upper_dev: new upper device - * - * Removes a link to device which is upper to this one. The caller must hold - * the RTNL lock. - */ -void netdev_upper_dev_unlink(struct net_device *dev, - struct net_device *upper_dev) +static void __netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev, + struct netdev_nested_priv *priv) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { @@ -7796,9 +7826,28 @@ void netdev_upper_dev_unlink(struct net_device *dev, __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); - __netdev_update_lower_level(upper_dev, NULL); + __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, - NULL); + priv); +} + +/** + * netdev_upper_dev_unlink - Removes a link to upper device + * @dev: device + * @upper_dev: new upper device + * + * Removes a link to device which is upper to this one. The caller must hold + * the RTNL lock. + */ +void netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) +{ + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_TODO, + .data = NULL, + }; + + __netdev_upper_dev_unlink(dev, upper_dev, &priv); } EXPORT_SYMBOL(netdev_upper_dev_unlink); @@ -7834,6 +7883,10 @@ int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *dev, struct netlink_ext_ack *extack) { + struct netdev_nested_priv priv = { + .flags = 0, + .data = NULL, + }; int err; if (!new_dev) @@ -7841,8 +7894,8 @@ int netdev_adjacent_change_prepare(struct net_device *old_dev, if (old_dev && new_dev != old_dev) netdev_adjacent_dev_disable(dev, old_dev); - - err = netdev_upper_dev_link(new_dev, dev, extack); + err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv, + extack); if (err) { if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); @@ -7857,6 +7910,11 @@ void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, + .data = NULL, + }; + if (!new_dev || !old_dev) return; @@ -7864,7 +7922,7 @@ void netdev_adjacent_change_commit(struct net_device *old_dev, return; netdev_adjacent_dev_enable(dev, old_dev); - netdev_upper_dev_unlink(old_dev, dev); + __netdev_upper_dev_unlink(old_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_commit); @@ -7872,13 +7930,18 @@ void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { + struct netdev_nested_priv priv = { + .flags = 0, + .data = NULL, + }; + if (!new_dev) return; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); - netdev_upper_dev_unlink(new_dev, dev); + __netdev_upper_dev_unlink(new_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_abort); @@ -10062,6 +10125,19 @@ static void netdev_wait_allrefs(struct net_device *dev) void netdev_run_todo(void) { struct list_head list; +#ifdef CONFIG_LOCKDEP + struct list_head unlink_list; + + list_replace_init(&net_unlink_list, &unlink_list); + + while (!list_empty(&unlink_list)) { + struct net_device *dev = list_first_entry(&unlink_list, + struct net_device, + unlink_list); + list_del(&dev->unlink_list); + dev->nested_level = dev->lower_level - 1; + } +#endif /* Snapshot list, allow later requests */ list_replace_init(&net_todo_list, &list); @@ -10274,6 +10350,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_segs = GSO_MAX_SEGS; dev->upper_level = 1; dev->lower_level = 1; +#ifdef CONFIG_LOCKDEP + dev->nested_level = 0; + INIT_LIST_HEAD(&dev->unlink_list); +#endif INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 54cd568e7c2f..fa1c37ec40c9 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -700,7 +700,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from) * larger. */ netif_addr_lock_bh(from); - netif_addr_lock_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); @@ -867,7 +867,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -897,7 +897,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -922,7 +922,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) /* See the above comments inside dev_uc_unsync(). */ netif_addr_lock_bh(from); - netif_addr_lock_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); diff --git a/net/core/filter.c b/net/core/filter.c index 21eaf3b182f2..b5f3faac5e3b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -9558,6 +9558,12 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk) { + /* BTF types for tcp_timewait_sock and inet_timewait_sock are not + * generated if CONFIG_INET=n. Trigger an explicit generation here. + */ + BTF_TYPE_EMIT(struct inet_timewait_sock); + BTF_TYPE_EMIT(struct tcp_timewait_sock); + #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6faf73d6a0f7..2b48cb0cc684 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5622,7 +5622,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); - if (ethernet) + if (ethernet && mac_len >= ETH_HLEN) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; @@ -5662,7 +5662,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); - if (ethernet) { + if (ethernet && mac_len >= ETH_HLEN) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 5c2072765be7..0c3f54baec4e 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -866,7 +866,7 @@ static const struct genl_multicast_group ethtool_nl_mcgrps[] = { [ETHNL_MCGRP_MONITOR] = { .name = ETHTOOL_MCGRP_MONITOR_NAME }, }; -static struct genl_family ethtool_genl_family = { +static struct genl_family ethtool_genl_family __ro_after_init = { .name = ETHTOOL_GENL_NAME, .version = ETHTOOL_GENL_VERSION, .netnsok = true, diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 49daaed89764..f687abb069fa 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -490,6 +490,7 @@ static struct xfrm_tunnel vti_ipip_handler __read_mostly = { .priority = 0, }; +#if IS_ENABLED(CONFIG_IPV6) static struct xfrm_tunnel vti_ipip6_handler __read_mostly = { .handler = vti_rcv_tunnel, .cb_handler = vti_rcv_cb, @@ -497,6 +498,7 @@ static struct xfrm_tunnel vti_ipip6_handler __read_mostly = { .priority = 0, }; #endif +#endif static int __net_init vti_init_net(struct net *net) { diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 1074df726ec0..8d5e1695b9aa 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -293,6 +293,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TcpTimeoutRehash", LINUX_MIB_TCPTIMEOUTREHASH), SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH), SNMP_MIB_ITEM("TCPDSACKRecvSegs", LINUX_MIB_TCPDSACKRECVSEGS), + SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index f0794f0232ba..e03756631541 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -214,7 +214,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, sock_rps_save_rxhash(child, skb); if (rsk_drop_req(req)) { - refcount_set(&req->rsk_refcnt, 2); + reqsk_put(req); return child; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 31f3b858db81..2135ee7c806d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -970,7 +970,8 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); if (IS_ENABLED(CONFIG_DEBUG_VM) && - WARN_ONCE(PageSlab(page), "page must not be a Slab one")) + WARN_ONCE(!sendpage_ok(page), + "page must not be a Slab one and have page_count > 0")) return -EINVAL; /* Wait for a connection to finish. One exception is TCP Fast Open diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 184ea556f50e..b1ce2054291d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -885,21 +885,34 @@ struct tcp_sacktag_state { struct rate_sample *rate; }; -/* Take a notice that peer is sending D-SACKs */ +/* Take a notice that peer is sending D-SACKs. Skip update of data delivery + * and spurious retransmission information if this DSACK is unlikely caused by + * sender's action: + * - DSACKed sequence range is larger than maximum receiver's window. + * - Total no. of DSACKed segments exceed the total no. of retransmitted segs. + */ static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq, u32 end_seq, struct tcp_sacktag_state *state) { u32 seq_len, dup_segs = 1; - if (before(start_seq, end_seq)) { - seq_len = end_seq - start_seq; - if (seq_len > tp->mss_cache) - dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache); - } + if (!before(start_seq, end_seq)) + return 0; + + seq_len = end_seq - start_seq; + /* Dubious DSACK: DSACKed range greater than maximum advertised rwnd */ + if (seq_len > tp->max_window) + return 0; + if (seq_len > tp->mss_cache) + dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache); + + tp->dsack_dups += dup_segs; + /* Skip the DSACK if dup segs weren't retransmitted by sender */ + if (tp->dsack_dups > tp->total_retrans) + return 0; tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; tp->rack.dsack_seen = 1; - tp->dsack_dups += dup_segs; state->flag |= FLAG_DSACKING_ACK; /* A spurious retransmission is delivered */ @@ -1153,6 +1166,11 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, } dup_segs = tcp_dsack_seen(tp, start_seq_0, end_seq_0, state); + if (!dup_segs) { /* Skip dubious DSACK */ + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKIGNOREDDUBIOUS); + return false; + } + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECVSEGS, dup_segs); /* D-SACK for already forgotten data... Do dumb counting. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5084333b5ab6..592c73962723 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1788,12 +1788,12 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, hdrlen); if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) { - thtail->window = th->window; - TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq; - if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq)) + if (likely(!before(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))) { TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq; + thtail->window = th->window; + } /* We have to update both TCP_SKB_CB(tail)->tcp_flags and * thtail->fin, so that the fast path in tcp_rcv_established() diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 7fa822b55c34..888bbbbb3e8a 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -451,7 +451,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, struct sk_buff *skb, struct mptcp_ext *ext) { - u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq); + /* The write_seq value has already been incremented, so the actual + * sequence number for the DATA_FIN is one less. + */ + u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq) - 1; if (!ext->use_map || !skb->len) { /* RFC6824 requires a DSS mapping with specific values @@ -460,10 +463,7 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, ext->data_fin = 1; ext->use_map = 1; ext->dsn64 = 1; - /* The write_seq value has already been incremented, so - * the actual sequence number for the DATA_FIN is one less. - */ - ext->data_seq = data_fin_tx_seq - 1; + ext->data_seq = data_fin_tx_seq; ext->subflow_seq = 0; ext->data_len = 1; } else if (ext->data_seq + ext->data_len == data_fin_tx_seq) { @@ -518,11 +518,11 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, if (subflow->use_64bit_ack) { ack_size = TCPOLEN_MPTCP_DSS_ACK64; - opts->ext_copy.data_ack = msk->ack_seq; + opts->ext_copy.data_ack = READ_ONCE(msk->ack_seq); opts->ext_copy.ack64 = 1; } else { ack_size = TCPOLEN_MPTCP_DSS_ACK32; - opts->ext_copy.data_ack32 = (uint32_t)(msk->ack_seq); + opts->ext_copy.data_ack32 = (uint32_t)READ_ONCE(msk->ack_seq); opts->ext_copy.ack64 = 0; } opts->ext_copy.use_ack = 1; @@ -782,7 +782,7 @@ static void update_una(struct mptcp_sock *msk, } } -bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq) +bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit) { /* Skip if DATA_FIN was already received. * If updating simultaneously with the recvmsg loop, values @@ -792,7 +792,8 @@ bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq) if (READ_ONCE(msk->rcv_data_fin) || !READ_ONCE(msk->first)) return false; - WRITE_ONCE(msk->rcv_data_fin_seq, data_fin_seq); + WRITE_ONCE(msk->rcv_data_fin_seq, + expand_ack(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit)); WRITE_ONCE(msk->rcv_data_fin, 1); return true; @@ -875,7 +876,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, */ if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { if (mp_opt.data_fin && mp_opt.data_len == 1 && - mptcp_update_rcv_data_fin(msk, mp_opt.data_seq) && + mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) && schedule_work(&msk->work)) sock_hold(subflow->conn); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 365ba96c84b0..5d747c6a610e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -123,7 +123,7 @@ static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, skb_ext_reset(skb); skb_orphan(skb); - msk->ack_seq += copy_len; + WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len); tail = skb_peek_tail(&sk->sk_receive_queue); if (offset == 0 && tail) { @@ -261,7 +261,7 @@ static void mptcp_check_data_fin(struct sock *sk) if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) { struct mptcp_subflow_context *subflow; - msk->ack_seq++; + WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1); WRITE_ONCE(msk->rcv_data_fin, 0); sk->sk_shutdown |= RCV_SHUTDOWN; @@ -1720,7 +1720,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->remote_key = mp_opt->sndr_key; mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq); ack_seq++; - msk->ack_seq = ack_seq; + WRITE_ONCE(msk->ack_seq, ack_seq); } sock_reset_flag(nsk, SOCK_RCU_FREE); @@ -2072,7 +2072,7 @@ bool mptcp_finish_join(struct sock *sk) parent_sock = READ_ONCE(parent->sk_socket); if (parent_sock && !sk->sk_socket) mptcp_sock_graft(sk, parent_sock); - subflow->map_seq = msk->ack_seq; + subflow->map_seq = READ_ONCE(msk->ack_seq); return true; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 60b27d44c184..20f04ac85409 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -387,7 +387,7 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk); bool mptcp_finish_join(struct sock *sk); void mptcp_data_acked(struct sock *sk); void mptcp_subflow_eof(struct sock *sk); -bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq); +bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit); void __init mptcp_token_init(void); static inline void mptcp_token_init_request(struct request_sock *req) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9ead43f79023..6f035af1c9d2 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -731,7 +731,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (mpext->data_fin == 1) { if (data_len == 1) { - mptcp_update_rcv_data_fin(msk, mpext->data_seq); + bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq, + mpext->dsn64); pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq); if (subflow->map_valid) { /* A DATA_FIN might arrive in a DSS @@ -742,11 +743,23 @@ static enum mapping_status get_mapping_status(struct sock *ssk, skb_ext_del(skb, SKB_EXT_MPTCP); return MAPPING_OK; } else { + if (updated && schedule_work(&msk->work)) + sock_hold((struct sock *)msk); + return MAPPING_DATA_FIN; } } else { - mptcp_update_rcv_data_fin(msk, mpext->data_seq + data_len); - pr_debug("DATA_FIN with mapping seq=%llu", mpext->data_seq + data_len); + u64 data_fin_seq = mpext->data_seq + data_len - 1; + + /* If mpext->data_seq is a 32-bit value, data_fin_seq + * must also be limited to 32 bits. + */ + if (!mpext->dsn64) + data_fin_seq &= GENMASK_ULL(31, 0); + + mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64); + pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d", + data_fin_seq, mpext->dsn64); } /* Adjust for DATA_FIN using 1 byte of sequence space */ diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 1eb65a7a27fd..c4b4d3376227 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1079,7 +1079,7 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; - while (netlink_policy_dump_loop(&cb->args[1])) { + while (netlink_policy_dump_loop(cb->args[1])) { void *hdr; struct nlattr *nest; @@ -1113,6 +1113,12 @@ nla_put_failure: return skb->len; } +static int ctrl_dumppolicy_done(struct netlink_callback *cb) +{ + netlink_policy_dump_free(cb->args[1]); + return 0; +} + static const struct genl_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETFAMILY, @@ -1123,6 +1129,7 @@ static const struct genl_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETPOLICY, .dumpit = ctrl_dumppolicy, + .done = ctrl_dumppolicy_done, }, }; diff --git a/net/netlink/policy.c b/net/netlink/policy.c index 641ffbdd977a..0176b59ce530 100644 --- a/net/netlink/policy.c +++ b/net/netlink/policy.c @@ -84,7 +84,6 @@ int netlink_policy_dump_start(const struct nla_policy *policy, unsigned int policy_idx; int err; - /* also returns 0 if "*_state" is our ERR_PTR() end marker */ if (*_state) return 0; @@ -140,21 +139,11 @@ static bool netlink_policy_dump_finished(struct nl_policy_dump *state) !state->policies[state->policy_idx].policy; } -bool netlink_policy_dump_loop(unsigned long *_state) +bool netlink_policy_dump_loop(unsigned long _state) { - struct nl_policy_dump *state = (void *)*_state; - - if (IS_ERR(state)) - return false; - - if (netlink_policy_dump_finished(state)) { - kfree(state); - /* store end marker instead of freed state */ - *_state = (unsigned long)ERR_PTR(-ENOENT); - return false; - } + struct nl_policy_dump *state = (void *)_state; - return true; + return !netlink_policy_dump_finished(state); } int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state) @@ -309,3 +298,10 @@ nla_put_failure: nla_nest_cancel(skb, policy); return -ENOBUFS; } + +void netlink_policy_dump_free(unsigned long _state) +{ + struct nl_policy_dump *state = (void *)_state; + + kfree(state); +} diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index a3f1204f1ed2..12d42ab0193b 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -905,15 +905,19 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, } err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype); - if (err == NF_ACCEPT && - ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; - - err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, - maniptype); + if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { + if (ct->status & IPS_SRC_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, + maniptype); + } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL, + NF_NAT_MANIP_SRC); + } } /* Mark NAT done if successful and update the flow key. */ diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index d8252fdab851..b8559c882431 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -199,17 +199,30 @@ static int announce_servers(struct sockaddr_qrtr *sq) if (!node) return 0; + rcu_read_lock(); /* Announce the list of servers registered in this node */ radix_tree_for_each_slot(slot, &node->servers, &iter, 0) { srv = radix_tree_deref_slot(slot); + if (!srv) + continue; + if (radix_tree_deref_retry(srv)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); ret = service_announce_new(sq, srv); if (ret < 0) { pr_err("failed to announce new service\n"); return ret; } + + rcu_read_lock(); } + rcu_read_unlock(); + return 0; } @@ -344,11 +357,22 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) if (!node) return 0; + rcu_read_lock(); /* Advertise removal of this client to all servers of remote node */ radix_tree_for_each_slot(slot, &node->servers, &iter, 0) { srv = radix_tree_deref_slot(slot); + if (!srv) + continue; + if (radix_tree_deref_retry(srv)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); server_del(node, srv->port); + rcu_read_lock(); } + rcu_read_unlock(); /* Advertise the removal of this client to all local servers */ local_node = node_get(qrtr_ns.local_node); @@ -359,8 +383,17 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) pkt.cmd = cpu_to_le32(QRTR_TYPE_BYE); pkt.client.node = cpu_to_le32(from->sq_node); + rcu_read_lock(); radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) { srv = radix_tree_deref_slot(slot); + if (!srv) + continue; + if (radix_tree_deref_retry(srv)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); sq.sq_family = AF_QIPCRTR; sq.sq_node = srv->node; @@ -374,8 +407,11 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) pr_err("failed to send bye cmd\n"); return ret; } + rcu_read_lock(); } + rcu_read_unlock(); + return 0; } @@ -434,8 +470,17 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, pkt.client.node = cpu_to_le32(node_id); pkt.client.port = cpu_to_le32(port); + rcu_read_lock(); radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) { srv = radix_tree_deref_slot(slot); + if (!srv) + continue; + if (radix_tree_deref_retry(srv)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); sq.sq_family = AF_QIPCRTR; sq.sq_node = srv->node; @@ -449,8 +494,11 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, pr_err("failed to send del client cmd\n"); return ret; } + rcu_read_lock(); } + rcu_read_unlock(); + return 0; } @@ -554,20 +602,40 @@ static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, filter.service = service; filter.instance = instance; + rcu_read_lock(); radix_tree_for_each_slot(node_slot, &nodes, &node_iter, 0) { node = radix_tree_deref_slot(node_slot); + if (!node) + continue; + if (radix_tree_deref_retry(node)) { + node_slot = radix_tree_iter_retry(&node_iter); + continue; + } + node_slot = radix_tree_iter_resume(node_slot, &node_iter); radix_tree_for_each_slot(srv_slot, &node->servers, &srv_iter, 0) { struct qrtr_server *srv; srv = radix_tree_deref_slot(srv_slot); + if (!srv) + continue; + if (radix_tree_deref_retry(srv)) { + srv_slot = radix_tree_iter_retry(&srv_iter); + continue; + } + if (!server_match(srv, &filter)) continue; + srv_slot = radix_tree_iter_resume(srv_slot, &srv_iter); + + rcu_read_unlock(); lookup_notify(from, srv, true); + rcu_read_lock(); } } + rcu_read_unlock(); /* Empty notification, to indicate end of listing */ lookup_notify(from, NULL, true); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 884cff7bb169..97aebb5d19db 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -518,7 +518,6 @@ enum rxrpc_call_state { RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */ RXRPC_CALL_SERVER_PREALLOC, /* - service preallocation */ RXRPC_CALL_SERVER_SECURING, /* - server securing request connection */ - RXRPC_CALL_SERVER_ACCEPTING, /* - server accepting request */ RXRPC_CALL_SERVER_RECV_REQUEST, /* - server receiving request */ RXRPC_CALL_SERVER_ACK_REQUEST, /* - server pending ACK of request */ RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */ @@ -714,8 +713,8 @@ struct rxrpc_ack_summary { enum rxrpc_command { RXRPC_CMD_SEND_DATA, /* send data message */ RXRPC_CMD_SEND_ABORT, /* request abort generation */ - RXRPC_CMD_ACCEPT, /* [server] accept incoming call */ RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */ + RXRPC_CMD_CHARGE_ACCEPT, /* [server] charge accept preallocation */ }; struct rxrpc_call_params { @@ -755,9 +754,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_sock *, struct sk_buff *); void rxrpc_accept_incoming_calls(struct rxrpc_local *); -struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long, - rxrpc_notify_rx_t); -int rxrpc_reject_call(struct rxrpc_sock *); +int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* * call_event.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index ef160566aa9a..8df1964db333 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -39,8 +39,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, unsigned int debug_id) { const void *here = __builtin_return_address(0); - struct rxrpc_call *call; + struct rxrpc_call *call, *xcall; struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); + struct rb_node *parent, **pp; int max, tmp; unsigned int size = RXRPC_BACKLOG_MAX; unsigned int head, tail, call_head, call_tail; @@ -94,7 +95,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, } /* Now it gets complicated, because calls get registered with the - * socket here, particularly if a user ID is preassigned by the user. + * socket here, with a user ID preassigned by the user. */ call = rxrpc_alloc_call(rx, gfp, debug_id); if (!call) @@ -107,34 +108,33 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, here, (const void *)user_call_ID); write_lock(&rx->call_lock); - if (user_attach_call) { - struct rxrpc_call *xcall; - struct rb_node *parent, **pp; - - /* Check the user ID isn't already in use */ - pp = &rx->calls.rb_node; - parent = NULL; - while (*pp) { - parent = *pp; - xcall = rb_entry(parent, struct rxrpc_call, sock_node); - if (user_call_ID < xcall->user_call_ID) - pp = &(*pp)->rb_left; - else if (user_call_ID > xcall->user_call_ID) - pp = &(*pp)->rb_right; - else - goto id_in_use; - } - call->user_call_ID = user_call_ID; - call->notify_rx = notify_rx; + /* Check the user ID isn't already in use */ + pp = &rx->calls.rb_node; + parent = NULL; + while (*pp) { + parent = *pp; + xcall = rb_entry(parent, struct rxrpc_call, sock_node); + if (user_call_ID < xcall->user_call_ID) + pp = &(*pp)->rb_left; + else if (user_call_ID > xcall->user_call_ID) + pp = &(*pp)->rb_right; + else + goto id_in_use; + } + + call->user_call_ID = user_call_ID; + call->notify_rx = notify_rx; + if (user_attach_call) { rxrpc_get_call(call, rxrpc_call_got_kernel); user_attach_call(call, user_call_ID); - rxrpc_get_call(call, rxrpc_call_got_userid); - rb_link_node(&call->sock_node, parent, pp); - rb_insert_color(&call->sock_node, &rx->calls); - set_bit(RXRPC_CALL_HAS_USERID, &call->flags); } + rxrpc_get_call(call, rxrpc_call_got_userid); + rb_link_node(&call->sock_node, parent, pp); + rb_insert_color(&call->sock_node, &rx->calls); + set_bit(RXRPC_CALL_HAS_USERID, &call->flags); + list_add(&call->sock_link, &rx->sock_calls); write_unlock(&rx->call_lock); @@ -157,11 +157,8 @@ id_in_use: } /* - * Preallocate sufficient service connections, calls and peers to cover the - * entire backlog of a socket. When a new call comes in, if we don't have - * sufficient of each available, the call gets rejected as busy or ignored. - * - * The backlog is replenished when a connection is accepted or rejected. + * Allocate the preallocation buffers for incoming service calls. These must + * be charged manually. */ int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp) { @@ -174,13 +171,6 @@ int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp) rx->backlog = b; } - if (rx->discard_new_call) - return 0; - - while (rxrpc_service_prealloc_one(rx, b, NULL, NULL, 0, gfp, - atomic_inc_return(&rxrpc_debug_id)) == 0) - ; - return 0; } @@ -333,6 +323,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, rxrpc_see_call(call); call->conn = conn; call->security = conn->security; + call->security_ix = conn->security_ix; call->peer = rxrpc_get_peer(conn->params.peer); call->cong_cwnd = call->peer->cong_cwnd; return call; @@ -402,8 +393,6 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, if (rx->notify_new_call) rx->notify_new_call(&rx->sk, call, call->user_call_ID); - else - sk_acceptq_added(&rx->sk); spin_lock(&conn->state_lock); switch (conn->state) { @@ -415,12 +404,8 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, case RXRPC_CONN_SERVICE: write_lock(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) { - if (rx->discard_new_call) - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; - else - call->state = RXRPC_CALL_SERVER_ACCEPTING; - } + if (call->state < RXRPC_CALL_COMPLETE) + call->state = RXRPC_CALL_SERVER_RECV_REQUEST; write_unlock(&call->state_lock); break; @@ -440,9 +425,6 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, rxrpc_send_ping(call, skb); - if (call->state == RXRPC_CALL_SERVER_ACCEPTING) - rxrpc_notify_socket(call); - /* We have to discard the prealloc queue's ref here and rely on a * combination of the RCU read lock and refs held either by the socket * (recvmsg queue, to-be-accepted queue or user ID tree) or the kernel @@ -460,187 +442,18 @@ no_call: } /* - * handle acceptance of a call by userspace - * - assign the user call ID to the call at the front of the queue - * - called with the socket locked. + * Charge up socket with preallocated calls, attaching user call IDs. */ -struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, - unsigned long user_call_ID, - rxrpc_notify_rx_t notify_rx) - __releases(&rx->sk.sk_lock.slock) - __acquires(call->user_mutex) +int rxrpc_user_charge_accept(struct rxrpc_sock *rx, unsigned long user_call_ID) { - struct rxrpc_call *call; - struct rb_node *parent, **pp; - int ret; - - _enter(",%lx", user_call_ID); - - ASSERT(!irqs_disabled()); - - write_lock(&rx->call_lock); - - if (list_empty(&rx->to_be_accepted)) { - write_unlock(&rx->call_lock); - release_sock(&rx->sk); - kleave(" = -ENODATA [empty]"); - return ERR_PTR(-ENODATA); - } - - /* check the user ID isn't already in use */ - pp = &rx->calls.rb_node; - parent = NULL; - while (*pp) { - parent = *pp; - call = rb_entry(parent, struct rxrpc_call, sock_node); - - if (user_call_ID < call->user_call_ID) - pp = &(*pp)->rb_left; - else if (user_call_ID > call->user_call_ID) - pp = &(*pp)->rb_right; - else - goto id_in_use; - } - - /* Dequeue the first call and check it's still valid. We gain - * responsibility for the queue's reference. - */ - call = list_entry(rx->to_be_accepted.next, - struct rxrpc_call, accept_link); - write_unlock(&rx->call_lock); - - /* We need to gain the mutex from the interrupt handler without - * upsetting lockdep, so we have to release it there and take it here. - * We are, however, still holding the socket lock, so other accepts - * must wait for us and no one can add the user ID behind our backs. - */ - if (mutex_lock_interruptible(&call->user_mutex) < 0) { - release_sock(&rx->sk); - kleave(" = -ERESTARTSYS"); - return ERR_PTR(-ERESTARTSYS); - } - - write_lock(&rx->call_lock); - list_del_init(&call->accept_link); - sk_acceptq_removed(&rx->sk); - rxrpc_see_call(call); - - /* Find the user ID insertion point. */ - pp = &rx->calls.rb_node; - parent = NULL; - while (*pp) { - parent = *pp; - call = rb_entry(parent, struct rxrpc_call, sock_node); - - if (user_call_ID < call->user_call_ID) - pp = &(*pp)->rb_left; - else if (user_call_ID > call->user_call_ID) - pp = &(*pp)->rb_right; - else - BUG(); - } - - write_lock_bh(&call->state_lock); - switch (call->state) { - case RXRPC_CALL_SERVER_ACCEPTING: - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; - break; - case RXRPC_CALL_COMPLETE: - ret = call->error; - goto out_release; - default: - BUG(); - } - - /* formalise the acceptance */ - call->notify_rx = notify_rx; - call->user_call_ID = user_call_ID; - rxrpc_get_call(call, rxrpc_call_got_userid); - rb_link_node(&call->sock_node, parent, pp); - rb_insert_color(&call->sock_node, &rx->calls); - if (test_and_set_bit(RXRPC_CALL_HAS_USERID, &call->flags)) - BUG(); - - write_unlock_bh(&call->state_lock); - write_unlock(&rx->call_lock); - rxrpc_notify_socket(call); - rxrpc_service_prealloc(rx, GFP_KERNEL); - release_sock(&rx->sk); - _leave(" = %p{%d}", call, call->debug_id); - return call; - -out_release: - _debug("release %p", call); - write_unlock_bh(&call->state_lock); - write_unlock(&rx->call_lock); - rxrpc_release_call(rx, call); - rxrpc_put_call(call, rxrpc_call_put); - goto out; - -id_in_use: - ret = -EBADSLT; - write_unlock(&rx->call_lock); -out: - rxrpc_service_prealloc(rx, GFP_KERNEL); - release_sock(&rx->sk); - _leave(" = %d", ret); - return ERR_PTR(ret); -} - -/* - * Handle rejection of a call by userspace - * - reject the call at the front of the queue - */ -int rxrpc_reject_call(struct rxrpc_sock *rx) -{ - struct rxrpc_call *call; - bool abort = false; - int ret; - - _enter(""); - - ASSERT(!irqs_disabled()); - - write_lock(&rx->call_lock); - - if (list_empty(&rx->to_be_accepted)) { - write_unlock(&rx->call_lock); - return -ENODATA; - } - - /* Dequeue the first call and check it's still valid. We gain - * responsibility for the queue's reference. - */ - call = list_entry(rx->to_be_accepted.next, - struct rxrpc_call, accept_link); - list_del_init(&call->accept_link); - sk_acceptq_removed(&rx->sk); - rxrpc_see_call(call); + struct rxrpc_backlog *b = rx->backlog; - write_lock_bh(&call->state_lock); - switch (call->state) { - case RXRPC_CALL_SERVER_ACCEPTING: - __rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, -ECONNABORTED); - abort = true; - fallthrough; - case RXRPC_CALL_COMPLETE: - ret = call->error; - goto out_discard; - default: - BUG(); - } + if (rx->sk.sk_state == RXRPC_CLOSE) + return -ESHUTDOWN; -out_discard: - write_unlock_bh(&call->state_lock); - write_unlock(&rx->call_lock); - if (abort) { - rxrpc_send_abort_packet(call); - rxrpc_release_call(rx, call); - rxrpc_put_call(call, rxrpc_call_put); - } - rxrpc_service_prealloc(rx, GFP_KERNEL); - _leave(" = %d", ret); - return ret; + return rxrpc_service_prealloc_one(rx, b, NULL, NULL, user_call_ID, + GFP_KERNEL, + atomic_inc_return(&rxrpc_debug_id)); } /* diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index a40fae013942..ed49769b459d 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -23,7 +23,6 @@ const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = { [RXRPC_CALL_CLIENT_RECV_REPLY] = "ClRcvRpl", [RXRPC_CALL_SERVER_PREALLOC] = "SvPrealc", [RXRPC_CALL_SERVER_SECURING] = "SvSecure", - [RXRPC_CALL_SERVER_ACCEPTING] = "SvAccept", [RXRPC_CALL_SERVER_RECV_REQUEST] = "SvRcvReq", [RXRPC_CALL_SERVER_ACK_REQUEST] = "SvAckReq", [RXRPC_CALL_SERVER_SEND_REPLY] = "SvSndRpl", @@ -352,9 +351,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, call->call_id = sp->hdr.callNumber; call->service_id = sp->hdr.serviceId; call->cid = sp->hdr.cid; - call->state = RXRPC_CALL_SERVER_ACCEPTING; - if (sp->hdr.securityIndex > 0) - call->state = RXRPC_CALL_SERVER_SECURING; + call->state = RXRPC_CALL_SERVER_SECURING; call->cong_tstamp = skb->tstamp; /* Set the channel for this call. We don't get channel_lock as we're diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 447f55ca6886..64ace2960ecc 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -269,7 +269,7 @@ static void rxrpc_call_is_secure(struct rxrpc_call *call) if (call) { write_lock_bh(&call->state_lock); if (call->state == RXRPC_CALL_SERVER_SECURING) { - call->state = RXRPC_CALL_SERVER_ACCEPTING; + call->state = RXRPC_CALL_SERVER_RECV_REQUEST; rxrpc_notify_socket(call); } write_unlock_bh(&call->state_lock); @@ -340,18 +340,18 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return ret; spin_lock(&conn->channel_lock); - spin_lock(&conn->state_lock); + spin_lock_bh(&conn->state_lock); if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { conn->state = RXRPC_CONN_SERVICE; - spin_unlock(&conn->state_lock); + spin_unlock_bh(&conn->state_lock); for (loop = 0; loop < RXRPC_MAXCALLS; loop++) rxrpc_call_is_secure( rcu_dereference_protected( conn->channels[loop].call, lockdep_is_held(&conn->channel_lock))); } else { - spin_unlock(&conn->state_lock); + spin_unlock_bh(&conn->state_lock); } spin_unlock(&conn->channel_lock); diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index 94c3df392651..2e8bd3b97301 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -903,7 +903,7 @@ int rxrpc_request_key(struct rxrpc_sock *rx, sockptr_t optval, int optlen) _enter(""); - if (optlen <= 0 || optlen > PAGE_SIZE - 1) + if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->securities) return -EINVAL; description = memdup_sockptr_nul(optval, optlen); @@ -940,7 +940,7 @@ int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen) if (IS_ERR(description)) return PTR_ERR(description); - key = request_key_net(&key_type_keyring, description, sock_net(&rx->sk), NULL); + key = request_key(&key_type_keyring, description, NULL); if (IS_ERR(key)) { kfree(description); _leave(" = %ld", PTR_ERR(key)); @@ -1072,7 +1072,7 @@ static long rxrpc_read(const struct key *key, switch (token->security_index) { case RXRPC_SECURITY_RXKAD: - toksize += 9 * 4; /* viceid, kvno, key*2 + len, begin, + toksize += 8 * 4; /* viceid, kvno, key*2, begin, * end, primary, tktlen */ toksize += RND(token->kad->ticket_len); break; @@ -1107,7 +1107,8 @@ static long rxrpc_read(const struct key *key, break; default: /* we have a ticket we can't encode */ - BUG(); + pr_err("Unsupported key token type (%u)\n", + token->security_index); continue; } @@ -1138,6 +1139,14 @@ static long rxrpc_read(const struct key *key, memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \ xdr += (_l + 3) >> 2; \ } while(0) +#define ENCODE_BYTES(l, s) \ + do { \ + u32 _l = (l); \ + memcpy(xdr, (s), _l); \ + if (_l & 3) \ + memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \ + xdr += (_l + 3) >> 2; \ + } while(0) #define ENCODE64(x) \ do { \ __be64 y = cpu_to_be64(x); \ @@ -1165,7 +1174,7 @@ static long rxrpc_read(const struct key *key, case RXRPC_SECURITY_RXKAD: ENCODE(token->kad->vice_id); ENCODE(token->kad->kvno); - ENCODE_DATA(8, token->kad->session_key); + ENCODE_BYTES(8, token->kad->session_key); ENCODE(token->kad->start); ENCODE(token->kad->expiry); ENCODE(token->kad->primary_flag); @@ -1215,7 +1224,6 @@ static long rxrpc_read(const struct key *key, break; default: - BUG(); break; } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index c4684dde1f16..2c842851d72e 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -179,37 +179,6 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) } /* - * Pass back notification of a new call. The call is added to the - * to-be-accepted list. This means that the next call to be accepted might not - * be the last call seen awaiting acceptance, but unless we leave this on the - * front of the queue and block all other messages until someone gives us a - * user_ID for it, there's not a lot we can do. - */ -static int rxrpc_recvmsg_new_call(struct rxrpc_sock *rx, - struct rxrpc_call *call, - struct msghdr *msg, int flags) -{ - int tmp = 0, ret; - - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NEW_CALL, 0, &tmp); - - if (ret == 0 && !(flags & MSG_PEEK)) { - _debug("to be accepted"); - write_lock_bh(&rx->recvmsg_lock); - list_del_init(&call->recvmsg_link); - write_unlock_bh(&rx->recvmsg_lock); - - rxrpc_get_call(call, rxrpc_call_got); - write_lock(&rx->call_lock); - list_add_tail(&call->accept_link, &rx->to_be_accepted); - write_unlock(&rx->call_lock); - } - - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_to_be_accepted, 1, 0, 0, ret); - return ret; -} - -/* * End the packet reception phase. */ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) @@ -630,9 +599,6 @@ try_again: } switch (READ_ONCE(call->state)) { - case RXRPC_CALL_SERVER_ACCEPTING: - ret = rxrpc_recvmsg_new_call(rx, call, msg, flags); - break; case RXRPC_CALL_CLIENT_RECV_REPLY: case RXRPC_CALL_SERVER_RECV_REQUEST: case RXRPC_CALL_SERVER_ACK_REQUEST: @@ -728,7 +694,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, call->debug_id, rxrpc_call_states[call->state], iov_iter_count(iter), want_more); - ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_ACCEPTING); + ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_SECURING); mutex_lock(&call->user_mutex); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 0824e103d037..d27140c836cc 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -530,10 +530,10 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p) return -EINVAL; break; - case RXRPC_ACCEPT: + case RXRPC_CHARGE_ACCEPT: if (p->command != RXRPC_CMD_SEND_DATA) return -EINVAL; - p->command = RXRPC_CMD_ACCEPT; + p->command = RXRPC_CMD_CHARGE_ACCEPT; if (len != 0) return -EINVAL; break; @@ -659,16 +659,12 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (ret < 0) goto error_release_sock; - if (p.command == RXRPC_CMD_ACCEPT) { + if (p.command == RXRPC_CMD_CHARGE_ACCEPT) { ret = -EINVAL; if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) goto error_release_sock; - call = rxrpc_accept_call(rx, p.call.user_call_ID, NULL); - /* The socket is now unlocked. */ - if (IS_ERR(call)) - return PTR_ERR(call); - ret = 0; - goto out_put_unlock; + ret = rxrpc_user_charge_accept(rx, p.call.user_call_ID); + goto error_release_sock; } call = rxrpc_find_call_by_user_ID(rx, p.call.user_call_ID); @@ -690,7 +686,6 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) case RXRPC_CALL_CLIENT_AWAIT_CONN: case RXRPC_CALL_SERVER_PREALLOC: case RXRPC_CALL_SERVER_SECURING: - case RXRPC_CALL_SERVER_ACCEPTING: rxrpc_put_call(call, rxrpc_call_put); ret = -EBUSY; goto error_release_sock; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 063d8aaf2900..798430e1a79f 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -235,6 +235,8 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, index++; if (index < s_i) continue; + if (IS_ERR(p)) + continue; if (jiffy_since && time_after(jiffy_since, @@ -307,6 +309,8 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, mutex_lock(&idrinfo->lock); idr_for_each_entry_ul(idr, p, tmp, id) { + if (IS_ERR(p)) + continue; ret = tcf_idr_release_unsafe(p); if (ret == ACT_P_DELETED) { module_put(ops->owner); @@ -467,17 +471,6 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, } EXPORT_SYMBOL(tcf_idr_create_from_flags); -void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a) -{ - struct tcf_idrinfo *idrinfo = tn->idrinfo; - - mutex_lock(&idrinfo->lock); - /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ - WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index))); - mutex_unlock(&idrinfo->lock); -} -EXPORT_SYMBOL(tcf_idr_insert); - /* Cleanup idr index that was allocated but not initialized. */ void tcf_idr_cleanup(struct tc_action_net *tn, u32 index) @@ -731,13 +724,6 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) return ret; } -static int tcf_action_destroy_1(struct tc_action *a, int bind) -{ - struct tc_action *actions[] = { a, NULL }; - - return tcf_action_destroy(actions, bind); -} - static int tcf_action_put(struct tc_action *p) { return __tcf_action_put(p, false); @@ -902,6 +888,26 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { [TCA_ACT_HW_STATS] = NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY), }; +static void tcf_idr_insert_many(struct tc_action *actions[]) +{ + int i; + + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { + struct tc_action *a = actions[i]; + struct tcf_idrinfo *idrinfo; + + if (!a) + continue; + idrinfo = a->idrinfo; + mutex_lock(&idrinfo->lock); + /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if + * it is just created, otherwise this is just a nop. + */ + idr_replace(&idrinfo->action_idr, a, a->tcfa_index); + mutex_unlock(&idrinfo->lock); + } +} + struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, @@ -1002,13 +1008,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (err != ACT_P_CREATED) module_put(a_o->owner); - if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN) && - !rcu_access_pointer(a->goto_chain)) { - tcf_action_destroy_1(a, bind); - NL_SET_ERR_MSG(extack, "can't use goto chain with NULL chain"); - return ERR_PTR(-EINVAL); - } - return a; err_mod: @@ -1051,6 +1050,11 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, actions[i - 1] = act; } + /* We have to commit them all together, because if any error happened in + * between, we could not handle the failure gracefully. + */ + tcf_idr_insert_many(actions); + *attr_size = tcf_action_full_attrs_size(sz); return i - 1; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 54d5652cfe6c..a4c7ba35a343 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -365,9 +365,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (res == ACT_P_CREATED) { - tcf_idr_insert(tn, *act); - } else { + if (res != ACT_P_CREATED) { /* make sure the program being replaced is no longer executing */ synchronize_rcu(); tcf_bpf_cfg_cleanup(&old); diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index f901421b0634..e19885d7fe2c 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -139,7 +139,6 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, ci->net = net; ci->zone = parm->zone; - tcf_idr_insert(tn, *a); ret = ACT_P_CREATED; } else if (ret > 0) { ci = to_connmark(*a); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index f5826e457679..4fa4fcb842ba 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -110,9 +110,6 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, if (params_new) kfree_rcu(params_new, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 2c3619165680..a780afdf570d 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1297,8 +1297,6 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, tcf_chain_put_by_act(goto_ch); if (params) call_rcu(¶ms->rcu, tcf_ct_params_free); - if (res == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return res; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index b5042f3ea079..6084300e51ad 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -269,9 +269,6 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, if (cp_new) kfree_rcu(cp_new, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; put_chain: diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 410e3bbfb9ca..73c3926358a0 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -140,8 +140,6 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; release_idr: tcf_idr_release(*a, bind); diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 1fb8d428d2c1..7c0771dd77a3 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -437,9 +437,6 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; chain_put: diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 5c568757643b..a2ddea04183a 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -627,9 +627,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (p) kfree_rcu(p, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; metadata_parse_err: if (goto_ch) diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 400a2cfe8452..8dc3bec0d325 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -189,8 +189,6 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, ipt->tcfi_t = t; ipt->tcfi_hook = hook; spin_unlock_bh(&ipt->tcf_lock); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; err3: diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index b2705318993b..e24b7e2331cd 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -194,8 +194,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, spin_lock(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); spin_unlock(&mirred_list_lock); - - tcf_idr_insert(tn, *a); } return ret; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 8118e2640979..e298ec3b3c9e 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -273,8 +273,6 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, if (p) kfree_rcu(p, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 855a6fa16a62..1ebd2a86d980 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -93,9 +93,6 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; release_idr: tcf_idr_release(*a, bind); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index c158bfed86d5..b45304446e13 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -238,8 +238,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&p->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 0b431d493768..8d8452b1cdd4 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -201,8 +201,6 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (new) kfree_rcu(new, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; failure: diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 5e2df590bb58..3ebf9ede3cf1 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -116,8 +116,6 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 9813ca4006dd..a4f3d0f0daa9 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -157,8 +157,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, goto release_idr; } - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index d0652386c6e2..e5f3fb8b00e3 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -225,8 +225,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 39e6d94cfafb..81a1c67335be 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -190,8 +190,6 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 37f1e10f35e0..a229751ee8c4 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -537,9 +537,6 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; put_chain: diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index a5ff9f68ab02..163b0385fd4c 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -229,8 +229,6 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (p) kfree_rcu(p, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 9e289c770574..7e59d8a18f3e 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -494,6 +494,7 @@ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp) out_err: /* Clean up any successful allocations */ sctp_auth_destroy_hmacs(ep->auth_hmacs); + ep->auth_hmacs = NULL; return -ENOMEM; } diff --git a/net/socket.c b/net/socket.c index 0c0144604f81..58cac2da5f66 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3638,9 +3638,11 @@ EXPORT_SYMBOL(kernel_getpeername); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { - if (sock->ops->sendpage) + if (sock->ops->sendpage) { + /* Warn in case the improper page to zero-copy send */ + WARN_ONCE(!sendpage_ok(page), "improper page for zero-copy send"); return sock->ops->sendpage(sock, page, offset, size, flags); - + } return sock_no_sendpage(sock, page, offset, size, flags); } EXPORT_SYMBOL(kernel_sendpage); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 865f3e037425..23d868545362 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -404,7 +404,7 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); * @val: value passed unmodified to notifier function * @dev: port device * @info: notifier information data - * + * @extack: netlink extended ack * Call all network notifier blocks. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9a3d9fedd7aa..95ab5545a931 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2143,10 +2143,15 @@ void tls_sw_release_resources_tx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec, *tmp; + int pending; /* Wait for any pending async encryptions to complete */ - smp_store_mb(ctx->async_notify, true); - if (atomic_read(&ctx->encrypt_pending)) + spin_lock_bh(&ctx->encrypt_compl_lock); + ctx->async_notify = true; + pending = atomic_read(&ctx->encrypt_pending); + spin_unlock_bh(&ctx->encrypt_compl_lock); + + if (pending) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); tls_tx_records(sk, -1); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2c9e9a2d1688..7fd45f6ddb05 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4172,6 +4172,9 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) if (err) return err; + if (key.idx < 0) + return -EINVAL; + if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index c3231620d210..6c5e09e7440a 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -377,15 +377,30 @@ static int xsk_generic_xmit(struct sock *sk) skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr; skb->destructor = xsk_destruct_skb; + /* Hinder dev_direct_xmit from freeing the packet and + * therefore completing it in the destructor + */ + refcount_inc(&skb->users); err = dev_direct_xmit(skb, xs->queue_id); + if (err == NETDEV_TX_BUSY) { + /* Tell user-space to retry the send */ + skb->destructor = sock_wfree; + /* Free skb without triggering the perf drop trace */ + consume_skb(skb); + err = -EAGAIN; + goto out; + } + xskq_cons_release(xs->tx); /* Ignore NET_XMIT_CN as packet might have been sent */ - if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) { + if (err == NET_XMIT_DROP) { /* SKB completed but not sent */ + kfree_skb(skb); err = -EBUSY; goto out; } + consume_skb(skb); sent_frame = true; } diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index 827ccdf2db57..1f08ebf7d80c 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -29,8 +29,12 @@ static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, static void handle_esp(struct sk_buff *skb, struct sock *sk) { + struct tcp_skb_cb *tcp_cb = (struct tcp_skb_cb *)skb->cb; + skb_reset_transport_header(skb); - memset(skb->cb, 0, sizeof(skb->cb)); + + /* restore IP CB, we need at least IP6CB->nhoff */ + memmove(skb->cb, &tcp_cb->header, sizeof(tcp_cb->header)); rcu_read_lock(); skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index eb8181987620..a8f66112c52b 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -303,7 +303,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } mtu = dst_mtu(dst); - if (!skb->ignore_df && skb->len > mtu) { + if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 69520ad3d83b..efc89a92961d 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1019,7 +1019,8 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, */ if (x->km.state == XFRM_STATE_VALID) { if ((x->sel.family && - !xfrm_selector_match(&x->sel, fl, x->sel.family)) || + (x->sel.family != family || + !xfrm_selector_match(&x->sel, fl, family))) || !security_xfrm_state_pol_flow_match(x, pol, fl)) return; @@ -1032,7 +1033,9 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, *acq_in_progress = 1; } else if (x->km.state == XFRM_STATE_ERROR || x->km.state == XFRM_STATE_EXPIRED) { - if (xfrm_selector_match(&x->sel, fl, x->sel.family) && + if ((!x->sel.family || + (x->sel.family == family && + xfrm_selector_match(&x->sel, fl, family))) && security_xfrm_state_pol_flow_match(x, pol, fl)) *error = -ESRCH; } @@ -1072,7 +1075,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, encap_family, + xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error); } if (best || acquire_in_progress) @@ -1089,7 +1092,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, encap_family, + xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error); } @@ -1441,6 +1444,30 @@ out: EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE +static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security) +{ + struct xfrm_user_sec_ctx *uctx; + int size = sizeof(*uctx) + security->ctx_len; + int err; + + uctx = kmalloc(size, GFP_KERNEL); + if (!uctx) + return -ENOMEM; + + uctx->exttype = XFRMA_SEC_CTX; + uctx->len = size; + uctx->ctx_doi = security->ctx_doi; + uctx->ctx_alg = security->ctx_alg; + uctx->ctx_len = security->ctx_len; + memcpy(uctx + 1, security->ctx_str, security->ctx_len); + err = security_xfrm_state_alloc(x, uctx); + kfree(uctx); + if (err) + return err; + + return 0; +} + static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, struct xfrm_encap_tmpl *encap) { @@ -1497,6 +1524,10 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, goto error; } + if (orig->security) + if (clone_security(x, orig->security)) + goto error; + if (orig->coaddr) { x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr), GFP_KERNEL); @@ -1510,6 +1541,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, } memcpy(&x->mark, &orig->mark, sizeof(x->mark)); + memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark)); if (xfrm_init_state(x) < 0) goto error; @@ -1521,7 +1553,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->tfcpad = orig->tfcpad; x->replay_maxdiff = orig->replay_maxdiff; x->replay_maxage = orig->replay_maxage; - x->curlft.add_time = orig->curlft.add_time; + memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft)); x->km.state = orig->km.state; x->km.seq = orig->km.seq; x->replay = orig->replay; diff --git a/scripts/spelling.txt b/scripts/spelling.txt index f253681e7e2a..feb2efaaa5e6 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -589,7 +589,7 @@ explictly||explicitly expresion||expression exprimental||experimental extened||extended -exteneded||extended||extended +exteneded||extended extensability||extensibility extention||extension extenstion||extension diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 8462690a039b..4828913703b6 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -25,7 +25,7 @@ endif LIBBPF = $(LIBBPF_PATH)libbpf.a -BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion) +BPFTOOL_VERSION ?= $(shell make -rR --no-print-directory -sC ../../.. kernelversion) $(LIBBPF): FORCE $(if $(LIBBPF_OUTPUT),@mkdir -p $(LIBBPF_OUTPUT)) diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 7dfca7016aaa..6bdbc389b493 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -659,6 +659,12 @@ struct btf *btf__parse_raw(const char *path) err = -EIO; goto err_out; } + if (magic == __bswap_16(BTF_MAGIC)) { + /* non-native endian raw BTF */ + pr_warn("non-native BTF endianness is not supported\n"); + err = -LIBBPF_ERRNO__ENDIAN; + goto err_out; + } if (magic != BTF_MAGIC) { /* definitely not a raw BTF */ err = -EPROTO; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 7253b833576c..e493d6048143 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -6925,7 +6925,7 @@ static const struct bpf_sec_def section_defs[] = { BPF_XDP_DEVMAP), BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, BPF_XDP_CPUMAP), - BPF_EAPROG_SEC("xdp", BPF_PROG_TYPE_XDP, + BPF_APROG_SEC("xdp", BPF_PROG_TYPE_XDP, BPF_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), |