diff options
472 files changed, 4105 insertions, 2384 deletions
diff --git a/Documentation/ABI/testing/dev-kmsg b/Documentation/ABI/testing/dev-kmsg index 1e6c28b1942b..f307506eb54c 100644 --- a/Documentation/ABI/testing/dev-kmsg +++ b/Documentation/ABI/testing/dev-kmsg @@ -56,11 +56,6 @@ Description: The /dev/kmsg character device node provides userspace access seek after the last record available at the time the last SYSLOG_ACTION_CLEAR was issued. - Due to the record nature of this interface with a "read all" - behavior and the specific positions each seek operation sets, - SEEK_CUR is not supported, returning -ESPIPE (invalid seek) to - errno whenever requested. - The output format consists of a prefix carrying the syslog prefix including priority and facility, the 64 bit message sequence number and the monotonic timestamp in microseconds, diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index ce3e05e41724..d09471aa7443 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1356,8 +1356,8 @@ PAGE_SIZE multiple when read back. thp_fault_alloc Number of transparent hugepages which were allocated to satisfy - a page fault, including COW faults. This counter is not present - when CONFIG_TRANSPARENT_HUGEPAGE is not set. + a page fault. This counter is not present when CONFIG_TRANSPARENT_HUGEPAGE + is not set. thp_collapse_alloc Number of transparent hugepages which were allocated to allow diff --git a/Documentation/admin-guide/device-mapper/index.rst b/Documentation/admin-guide/device-mapper/index.rst index ec62fcc8eece..6cf8adc86fa8 100644 --- a/Documentation/admin-guide/device-mapper/index.rst +++ b/Documentation/admin-guide/device-mapper/index.rst @@ -11,6 +11,7 @@ Device Mapper dm-clone dm-crypt dm-dust + dm-ebs dm-flakey dm-init dm-integrity diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 6a233e42be08..b2acd0d395ca 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -305,8 +305,7 @@ monitor how successfully the system is providing huge pages for use. thp_fault_alloc is incremented every time a huge page is successfully - allocated to handle a page fault. This applies to both the - first time a page is faulted and for COW faults. + allocated to handle a page fault. thp_collapse_alloc is incremented by khugepaged when it has found diff --git a/Documentation/bpf/prog_cgroup_sockopt.rst b/Documentation/bpf/prog_cgroup_sockopt.rst index c47d974629ae..172f957204bf 100644 --- a/Documentation/bpf/prog_cgroup_sockopt.rst +++ b/Documentation/bpf/prog_cgroup_sockopt.rst @@ -86,6 +86,20 @@ then the next program in the chain (A) will see those changes, *not* the original input ``setsockopt`` arguments. The potentially modified values will be then passed down to the kernel. +Large optval +============ +When the ``optval`` is greater than the ``PAGE_SIZE``, the BPF program +can access only the first ``PAGE_SIZE`` of that data. So it has to options: + +* Set ``optlen`` to zero, which indicates that the kernel should + use the original buffer from the userspace. Any modifications + done by the BPF program to the ``optval`` are ignored. +* Set ``optlen`` to the value less than ``PAGE_SIZE``, which + indicates that the kernel should use BPF's trimmed ``optval``. + +When the BPF program returns with the ``optlen`` greater than +``PAGE_SIZE``, the userspace will receive ``EFAULT`` errno. + Example ======= diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst index 6068266dd303..7ca8c7bac650 100644 --- a/Documentation/core-api/pin_user_pages.rst +++ b/Documentation/core-api/pin_user_pages.rst @@ -33,7 +33,7 @@ all combinations of get*(), pin*(), FOLL_LONGTERM, and more. Also, the pin_user_pages*() APIs are clearly distinct from the get_user_pages*() APIs, so that's a natural dividing line, and a good point to make separate wrapper calls. In other words, use pin_user_pages*() for DMA-pinned pages, and -get_user_pages*() for other cases. There are four cases described later on in +get_user_pages*() for other cases. There are five cases described later on in this document, to further clarify that concept. FOLL_PIN and FOLL_GET are mutually exclusive for a given gup call. However, diff --git a/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml b/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml index 9147df29022a..38efb50081e3 100644 --- a/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml +++ b/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml @@ -34,12 +34,15 @@ properties: maxItems: 1 clocks: - maxItems: 1 + minItems: 1 + maxItems: 2 + items: + - description: controller register bus clock + - description: baud rate generator and delay control clock clock-names: - description: input clock for the baud rate generator - items: - - const: core + minItems: 1 + maxItems: 2 if: properties: @@ -51,17 +54,22 @@ if: then: properties: clocks: - contains: - items: - - description: controller register bus clock - - description: baud rate generator and delay control clock + minItems: 2 clock-names: - minItems: 2 items: - const: core - const: pclk +else: + properties: + clocks: + maxItems: 1 + + clock-names: + items: + - const: core + required: - compatible - reg diff --git a/Documentation/networking/ieee802154.rst b/Documentation/networking/ieee802154.rst index 36ca823a1122..6f4bf8447a21 100644 --- a/Documentation/networking/ieee802154.rst +++ b/Documentation/networking/ieee802154.rst @@ -30,8 +30,8 @@ Socket API The address family, socket addresses etc. are defined in the include/net/af_ieee802154.h header or in the special header -in the userspace package (see either http://wpan.cakelab.org/ or the -git tree at https://github.com/linux-wpan/wpan-tools). +in the userspace package (see either https://linux-wpan.org/wpan-tools.html +or the git tree at https://github.com/linux-wpan/wpan-tools). 6LoWPAN Linux implementation ============================ diff --git a/MAINTAINERS b/MAINTAINERS index 7b5ffd646c6b..28bd4715ebd5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8333,7 +8333,7 @@ M: Alexander Aring <alex.aring@gmail.com> M: Stefan Schmidt <stefan@datenfreihafen.org> L: linux-wpan@vger.kernel.org S: Maintained -W: http://wpan.cakelab.org/ +W: https://linux-wpan.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan-next.git F: Documentation/networking/ieee802154.rst @@ -10808,7 +10808,7 @@ F: Documentation/devicetree/bindings/dma/mtk-* F: drivers/dma/mediatek/ MEDIATEK ETHERNET DRIVER -M: Felix Fietkau <nbd@openwrt.org> +M: Felix Fietkau <nbd@nbd.name> M: John Crispin <john@phrozen.org> M: Sean Wang <sean.wang@mediatek.com> M: Mark Lee <Mark-MC.Lee@mediatek.com> @@ -16058,8 +16058,10 @@ SPARSE CHECKER M: "Luc Van Oostenryck" <luc.vanoostenryck@gmail.com> L: linux-sparse@vger.kernel.org S: Maintained -W: https://sparse.wiki.kernel.org/ +W: https://sparse.docs.kernel.org/ T: git git://git.kernel.org/pub/scm/devel/sparse/sparse.git +Q: https://patchwork.kernel.org/project/linux-sparse/list/ +B: https://bugzilla.kernel.org/enter_bug.cgi?component=Sparse&product=Tools F: include/linux/compiler.h SPEAR CLOCK FRAMEWORK SUPPORT diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a4a094bedcb2..66dc41fd49f2 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1518,9 +1518,9 @@ config ARM64_PTR_AUTH default y depends on !KVM || ARM64_VHE depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC - # GCC 9.1 and later inserts a .note.gnu.property section note for PAC + # Modern compilers insert a .note.gnu.property section note for PAC # which is only understood by binutils starting with version 2.33.1. - depends on !CC_IS_GCC || GCC_VERSION < 90100 || LD_VERSION >= 233010000 + depends on LD_IS_LLD || LD_VERSION >= 233010000 || (CC_IS_GCC && GCC_VERSION < 90100) depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h index 81fefd2a1d02..ba89a9af820a 100644 --- a/arch/arm64/include/asm/linkage.h +++ b/arch/arm64/include/asm/linkage.h @@ -12,7 +12,6 @@ * instead. */ #define BTI_C hint 34 ; -#define BTI_J hint 36 ; /* * When using in-kernel BTI we need to ensure that PCS-conformant assembly @@ -43,11 +42,6 @@ SYM_START(name, SYM_L_WEAK, SYM_A_NONE) \ BTI_C -#define SYM_INNER_LABEL(name, linkage) \ - .type name SYM_T_NONE ASM_NL \ - SYM_ENTRY(name, linkage, SYM_A_NONE) \ - BTI_J - #endif /* diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 68140fdd89d6..8444df000181 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -19,6 +19,9 @@ typedef struct { atomic64_t id; +#ifdef CONFIG_COMPAT + void *sigpage; +#endif void *vdso; unsigned long flags; } mm_context_t; diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 151f28521f1e..a561cbb91d4d 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -29,9 +29,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ sys_compat.o -ifneq ($(CONFIG_COMPAT_VDSO), y) obj-$(CONFIG_COMPAT) += sigreturn32.o -endif obj-$(CONFIG_KUSER_HELPERS) += kuser32.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o obj-$(CONFIG_MODULES) += module.o diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index ad06d6802d2e..cf50c53e9357 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -460,6 +460,8 @@ static const struct midr_range arm64_ssb_cpus[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), {}, }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 4ae41670c2e6..9f63053a63a9 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1290,6 +1290,8 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } }; char const *str = "kpti command line option"; diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 0bbac612146e..666b225aeb3a 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) return 0; /* - * Compat (i.e. 32 bit) mode: - * - PC has been set in the pt_regs struct in kernel_entry, - * - Handle SP and LR here. + * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but + * we're stuck with it for ABI compatability reasons. + * + * For a 32-bit consumer inspecting a 32-bit task, then it will look at + * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h). + * These correspond directly to a prefix of the registers saved in our + * 'struct pt_regs', with the exception of the PC, so we copy that down + * (x15 corresponds to SP_hyp in the architecture). + * + * So far, so good. + * + * The oddity arises when a 64-bit consumer looks at a 32-bit task and + * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return + * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and + * PC registers would normally live. The initial idea was to allow a + * 64-bit unwinder to unwind a 32-bit task and, although it's not clear + * how well that works in practice, somebody might be relying on it. + * + * At the time we make a sample, we don't know whether the consumer is + * 32-bit or 64-bit, so we have to cater for both possibilities. */ if (compat_user_mode(regs)) { if ((u32)idx == PERF_REG_ARM64_SP) return regs->compat_sp; if ((u32)idx == PERF_REG_ARM64_LR) return regs->compat_lr; + if (idx == 15) + return regs->pc; } if ((u32)idx == PERF_REG_ARM64_SP) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index d1c95dcf1d78..cbe49cd117cf 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -120,15 +120,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) void *alloc_insn_page(void) { - void *page; - - page = vmalloc_exec(PAGE_SIZE); - if (page) { - set_memory_ro((unsigned long)page, 1); - set_vm_flush_reset_perms(page); - } - - return page; + return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __func__); } /* arm kprobe: install breakpoint in text */ diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 82feca6f7052..2f507f565c48 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -342,38 +342,13 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka, retcode = ptr_to_compat(ka->sa.sa_restorer); } else { /* Set up sigreturn pointer */ -#ifdef CONFIG_COMPAT_VDSO - void *vdso_base = current->mm->context.vdso; - void *vdso_trampoline; - - if (ka->sa.sa_flags & SA_SIGINFO) { - if (thumb) { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_rt_sigreturn_thumb); - } else { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_rt_sigreturn_arm); - } - } else { - if (thumb) { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_sigreturn_thumb); - } else { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_sigreturn_arm); - } - } - - retcode = ptr_to_compat(vdso_trampoline) + thumb; -#else unsigned int idx = thumb << 1; if (ka->sa.sa_flags & SA_SIGINFO) idx += 3; - retcode = (unsigned long)current->mm->context.vdso + + retcode = (unsigned long)current->mm->context.sigpage + (idx << 2) + thumb; -#endif } regs->regs[0] = usig; diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 4e016574bd91..e546df0efefb 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -191,15 +191,12 @@ enum aarch32_map { #ifdef CONFIG_COMPAT_VDSO AA32_MAP_VVAR, AA32_MAP_VDSO, -#else - AA32_MAP_SIGPAGE #endif + AA32_MAP_SIGPAGE }; static struct page *aarch32_vectors_page __ro_after_init; -#ifndef CONFIG_COMPAT_VDSO static struct page *aarch32_sig_page __ro_after_init; -#endif static struct vm_special_mapping aarch32_vdso_maps[] = { [AA32_MAP_VECTORS] = { @@ -214,12 +211,11 @@ static struct vm_special_mapping aarch32_vdso_maps[] = { .name = "[vdso]", .mremap = aarch32_vdso_mremap, }, -#else +#endif /* CONFIG_COMPAT_VDSO */ [AA32_MAP_SIGPAGE] = { .name = "[sigpage]", /* ABI */ .pages = &aarch32_sig_page, }, -#endif /* CONFIG_COMPAT_VDSO */ }; static int aarch32_alloc_kuser_vdso_page(void) @@ -242,27 +238,11 @@ static int aarch32_alloc_kuser_vdso_page(void) return 0; } -#ifdef CONFIG_COMPAT_VDSO -static int __aarch32_alloc_vdso_pages(void) -{ - int ret; - - vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR]; - vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO]; - - ret = __vdso_init(VDSO_ABI_AA32); - if (ret) - return ret; - - return aarch32_alloc_kuser_vdso_page(); -} -#else -static int __aarch32_alloc_vdso_pages(void) +static int aarch32_alloc_sigpage(void) { extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[]; int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start; unsigned long sigpage; - int ret; sigpage = get_zeroed_page(GFP_ATOMIC); if (!sigpage) @@ -271,18 +251,34 @@ static int __aarch32_alloc_vdso_pages(void) memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz); aarch32_sig_page = virt_to_page(sigpage); flush_dcache_page(aarch32_sig_page); + return 0; +} - ret = aarch32_alloc_kuser_vdso_page(); - if (ret) - free_page(sigpage); +#ifdef CONFIG_COMPAT_VDSO +static int __aarch32_alloc_vdso_pages(void) +{ + vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR]; + vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO]; - return ret; + return __vdso_init(VDSO_ABI_AA32); } #endif /* CONFIG_COMPAT_VDSO */ static int __init aarch32_alloc_vdso_pages(void) { - return __aarch32_alloc_vdso_pages(); + int ret; + +#ifdef CONFIG_COMPAT_VDSO + ret = __aarch32_alloc_vdso_pages(); + if (ret) + return ret; +#endif + + ret = aarch32_alloc_sigpage(); + if (ret) + return ret; + + return aarch32_alloc_kuser_vdso_page(); } arch_initcall(aarch32_alloc_vdso_pages); @@ -305,7 +301,6 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm) return PTR_ERR_OR_ZERO(ret); } -#ifndef CONFIG_COMPAT_VDSO static int aarch32_sigreturn_setup(struct mm_struct *mm) { unsigned long addr; @@ -328,12 +323,11 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm) if (IS_ERR(ret)) goto out; - mm->context.vdso = (void *)addr; + mm->context.sigpage = (void *)addr; out: return PTR_ERR_OR_ZERO(ret); } -#endif /* !CONFIG_COMPAT_VDSO */ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { @@ -352,10 +346,11 @@ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) mm, bprm, uses_interp); -#else - ret = aarch32_sigreturn_setup(mm); + if (ret) + goto out; #endif /* CONFIG_COMPAT_VDSO */ + ret = aarch32_sigreturn_setup(mm); out: mmap_write_unlock(mm); return ret; diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 556d424c6f52..45d5cfe46429 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -23,13 +23,14 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti # potential future proofing if we end up with internal calls to the exported # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so # preparation in build-time C")). -ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ - -Bsymbolic --eh-frame-hdr --build-id -n $(btildflags-y) -T +ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ + -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id -n \ + $(btildflags-y) -T ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 ccflags-y += -DDISABLE_BRANCH_PROFILING -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) KBUILD_CFLAGS += $(DISABLE_LTO) KASAN_SANITIZE := n UBSAN_SANITIZE := n diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S index 620a3ef837b7..0e18729abc3b 100644 --- a/arch/arm64/kernel/vdso/sigreturn.S +++ b/arch/arm64/kernel/vdso/sigreturn.S @@ -18,29 +18,40 @@ .text +/* + * NOTE!!! You may notice that all of the .cfi directives in this file have + * been commented out. This is because they have been shown to trigger segfaults + * in libgcc when unwinding out of a SIGCANCEL handler to invoke pthread + * cleanup handlers during the thread cancellation dance. By omitting the + * directives, we trigger an arm64-specific fallback path in the unwinder which + * recognises the signal frame and restores many of the registers directly from + * the sigcontext. Re-enabling the cfi directives here therefore needs to be + * much more comprehensive to reduce the risk of further regressions. + */ + /* Ensure that the mysterious NOP can be associated with a function. */ - .cfi_startproc +// .cfi_startproc /* - * .cfi_signal_frame causes the corresponding Frame Description Entry in the - * .eh_frame section to be annotated as a signal frame. This allows DWARF - * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo(), which permits - * unwinding out of the signal trampoline without the need for the mysterious - * NOP. + * .cfi_signal_frame causes the corresponding Frame Description Entry (FDE) in + * the .eh_frame section to be annotated as a signal frame. This allows DWARF + * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo() and identify + * the next frame using the unmodified return address instead of subtracting 1, + * which may yield the wrong FDE. */ - .cfi_signal_frame +// .cfi_signal_frame /* * Tell the unwinder where to locate the frame record linking back to the - * interrupted context. We don't provide unwind info for registers other - * than the frame pointer and the link register here; in practice, this - * is sufficient for unwinding in C/C++ based runtimes and the values in - * the sigcontext may have been modified by this point anyway. Debuggers + * interrupted context. We don't provide unwind info for registers other than + * the frame pointer and the link register here; in practice, this is likely to + * be insufficient for unwinding in C/C++ based runtimes, especially without a + * means to restore the stack pointer. Thankfully, unwinders and debuggers * already have baked-in strategies for attempting to unwind out of signals. */ - .cfi_def_cfa x29, 0 - .cfi_offset x29, 0 * 8 - .cfi_offset x30, 1 * 8 +// .cfi_def_cfa x29, 0 +// .cfi_offset x29, 0 * 8 +// .cfi_offset x30, 1 * 8 /* * This mysterious NOP is required for some unwinders (e.g. libc++) that @@ -51,16 +62,19 @@ nop // Mysterious NOP /* - * GDB relies on being able to identify the sigreturn instruction sequence to - * unwind from signal handlers. We cannot, therefore, use SYM_FUNC_START() - * here, as it will emit a BTI C instruction and break the unwinder. Thankfully, - * this function is only ever called from a RET and so omitting the landing pad - * is perfectly fine. + * GDB, libgcc and libunwind rely on being able to identify the sigreturn + * instruction sequence to unwind from signal handlers. We cannot, therefore, + * use SYM_FUNC_START() here, as it will emit a BTI C instruction and break the + * unwinder. Thankfully, this function is only ever called from a RET and so + * omitting the landing pad is perfectly fine. */ SYM_CODE_START(__kernel_rt_sigreturn) +// PLEASE DO NOT MODIFY mov x8, #__NR_rt_sigreturn +// PLEASE DO NOT MODIFY svc #0 - .cfi_endproc +// PLEASE DO NOT MODIFY +// .cfi_endproc SYM_CODE_END(__kernel_rt_sigreturn) emit_aarch64_feature_1_and diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 7ea1e827e505..d88148bef6b0 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -140,7 +140,6 @@ hostprogs := $(munge) c-obj-vdso := note.o c-obj-vdso-gettimeofday := vgettimeofday.o -asm-obj-vdso := sigreturn.o ifneq ($(c-gettimeofday-y),) VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y) diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S deleted file mode 100644 index b0091064c3d6..000000000000 --- a/arch/arm64/kernel/vdso32/sigreturn.S +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This file provides both A32 and T32 versions, in accordance with the - * arm sigreturn code. - * - * Please read the comments in arch/arm64/kernel/vdso/sigreturn.S to - * understand some of the craziness in here. - * - * Copyright (C) 2018 ARM Limited - */ - -#include <linux/linkage.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> - - .text - - .arm - .fnstart - .save {r0-r15} - .pad #COMPAT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_sigreturn_arm) - mov r7, #__NR_compat_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_sigreturn_arm) - - .fnstart - .save {r0-r15} - .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_rt_sigreturn_arm) - mov r7, #__NR_compat_rt_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_rt_sigreturn_arm) - - .thumb - .fnstart - .save {r0-r15} - .pad #COMPAT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_sigreturn_thumb) - mov r7, #__NR_compat_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_sigreturn_thumb) - - .fnstart - .save {r0-r15} - .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_rt_sigreturn_thumb) - mov r7, #__NR_compat_rt_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_rt_sigreturn_thumb) diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S index a3944927eaeb..337d03522048 100644 --- a/arch/arm64/kernel/vdso32/vdso.lds.S +++ b/arch/arm64/kernel/vdso32/vdso.lds.S @@ -64,19 +64,7 @@ VERSION __vdso_clock_gettime; __vdso_gettimeofday; __vdso_clock_getres; - __kernel_sigreturn_arm; - __kernel_sigreturn_thumb; - __kernel_rt_sigreturn_arm; - __kernel_rt_sigreturn_thumb; __vdso_clock_gettime64; local: *; }; } - -/* - * Make the sigreturn code visible to the kernel. - */ -VDSO_compat_sigreturn_arm = __kernel_sigreturn_arm; -VDSO_compat_sigreturn_thumb = __kernel_sigreturn_thumb; -VDSO_compat_rt_sigreturn_arm = __kernel_rt_sigreturn_arm; -VDSO_compat_rt_sigreturn_thumb = __kernel_rt_sigreturn_thumb; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 521bd5891e84..666d3350b4ac 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -67,8 +67,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("vz_ghfc", vz_ghfc_exits), VCPU_STAT("vz_gpa", vz_gpa_exits), VCPU_STAT("vz_resvd", vz_resvd_exits), +#ifdef CONFIG_CPU_LOONGSON64 VCPU_STAT("vz_cpucfg", vz_cpucfg_exits), #endif +#endif VCPU_STAT("halt_successful_poll", halt_successful_poll), VCPU_STAT("halt_attempted_poll", halt_attempted_poll), VCPU_STAT("halt_poll_invalid", halt_poll_invalid), diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index c152a68811dd..345727638d52 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -74,8 +74,11 @@ void *arch_dma_set_uncached(void *cpu_addr, size_t size) * We need to iterate through the pages, clearing the dcache for * them and setting the cache-inhibit bit. */ + mmap_read_lock(&init_mm); error = walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops, NULL); + mmap_read_unlock(&init_mm); + if (error) return ERR_PTR(error); return cpu_addr; @@ -85,9 +88,11 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size) { unsigned long va = (unsigned long)cpu_addr; + mmap_read_lock(&init_mm); /* walk_page_range shouldn't be able to fail here */ WARN_ON(walk_page_range(&init_mm, va, va + size, &clear_nocache_walk_ops, NULL)); + mmap_read_unlock(&init_mm); } void arch_sync_dma_for_device(phys_addr_t addr, size_t size, diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index e738ea652192..6a73714759ba 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -40,7 +40,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, /* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */ if (kvmhv_on_pseries()) return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr, - __pa(to), __pa(from), n); + (to != NULL) ? __pa(to): 0, + (from != NULL) ? __pa(from): 0, n); quadrant = 1; if (!pid) diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index 4a75f2d9bf0e..bce0e5349978 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -14,6 +14,7 @@ #include <linux/memblock.h> #include <linux/libfdt.h> #include <linux/crash_core.h> +#include <asm/cacheflush.h> #include <asm/pgalloc.h> #include <asm/prom.h> #include <asm/kdump.h> diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 38ba55b0eb9d..e4c7c2c8a02f 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -17,7 +17,7 @@ vdso-syms += flush_icache obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o ifneq ($(c-gettimeofday-y),) - CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) + CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) endif # Build rules @@ -27,6 +27,9 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) obj-y += vdso.o vdso-syms.o CPPFLAGS_vdso.lds += -P -C -U$(ARCH) +# Disable -pg to prevent insert call site +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os + # Disable gcov profiling for VDSO code GCOV_PROFILE := n diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c index d264943e2e47..cc0d80699c31 100644 --- a/arch/riscv/kernel/vdso/vgettimeofday.c +++ b/arch/riscv/kernel/vdso/vgettimeofday.c @@ -9,16 +9,22 @@ #include <linux/time.h> #include <linux/types.h> +extern +int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts); int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) { return __cvdso_clock_gettime(clock, ts); } +extern +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { return __cvdso_gettimeofday(tv, tz); } +extern +int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res); int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res) { return __cvdso_clock_getres(clock_id, res); diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 636446003a06..263075a1af36 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -198,9 +198,10 @@ static debug_entry_t ***debug_areas_alloc(int pages_per_area, int nr_areas) if (!areas) goto fail_malloc_areas; for (i = 0; i < nr_areas; i++) { + /* GFP_NOWARN to avoid user triggerable WARN, we handle fails */ areas[i] = kmalloc_array(pages_per_area, sizeof(debug_entry_t *), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!areas[i]) goto fail_malloc_areas2; for (j = 0; j < pages_per_area; j++) { diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index cd241ee66eff..078277231858 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -170,6 +170,8 @@ static noinline __init void setup_lowcore_early(void) psw_t psw; psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA; + if (IS_ENABLED(CONFIG_KASAN)) + psw.mask |= PSW_MASK_DAT; psw.addr = (unsigned long) s390_base_ext_handler; S390_lowcore.external_new_psw = psw; psw.addr = (unsigned long) s390_base_pgm_handler; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 496f74d98473..969b35b177dd 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -378,9 +378,9 @@ ENTRY(system_call) stmg %r8,%r15,__LC_SAVE_AREA_SYNC BPOFF lg %r12,__LC_CURRENT - lghi %r13,__TASK_thread lghi %r14,_PIF_SYSCALL .Lsysc_per: + lghi %r13,__TASK_thread lg %r15,__LC_KERNEL_STACK la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index a54c6a401581..2bdc72e6890e 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -375,7 +375,9 @@ void __init hyperv_init(void) guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); - hv_hypercall_pg = vmalloc_exec(PAGE_SIZE); + hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, + VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __func__); if (hv_hypercall_pg == NULL) { wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); goto remove_cpuhp_state; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f8998e97457f..be5363b21540 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -943,7 +943,7 @@ struct kvm_arch { atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map *apic_map; - bool apic_map_dirty; + atomic_t apic_map_dirty; bool apic_access_page_done; unsigned long apicv_inhibit_reasons; @@ -1220,7 +1220,7 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); - int (*write_log_dirty)(struct kvm_vcpu *vcpu); + int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 73d997aa2966..e039a933aca3 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -25,8 +25,6 @@ #define TPAUSE_C01_STATE 1 #define TPAUSE_C02_STATE 0 -u32 get_umwait_control_msr(void); - static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) { diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 2da1f95b88d7..816b31c68550 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -194,6 +194,7 @@ enum page_cache_mode { #define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0) #define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC) #define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_ROX (__PP| 0| 0|___A| 0|___D| 0|___G) #define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) #define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G) #define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G) @@ -219,6 +220,7 @@ enum page_cache_mode { #define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC) #define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC) #define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0) +#define PAGE_KERNEL_ROX __pgprot_mask(__PAGE_KERNEL_ROX | _ENC) #define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC) #define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC) diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c index 300e3fd5ade3..ec8064c0ae03 100644 --- a/arch/x86/kernel/cpu/umwait.c +++ b/arch/x86/kernel/cpu/umwait.c @@ -18,12 +18,6 @@ */ static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE); -u32 get_umwait_control_msr(void) -{ - return umwait_control_cached; -} -EXPORT_SYMBOL_GPL(get_umwait_control_msr); - /* * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by * hardware or BIOS before kernel boot. diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 34a7e0533dad..5bf72fc86a8e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -169,6 +169,18 @@ static void kvm_apic_map_free(struct rcu_head *rcu) kvfree(map); } +/* + * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock. + * + * DIRTY -> UPDATE_IN_PROGRESS and UPDATE_IN_PROGRESS -> CLEAN happen with + * apic_map_lock_held. + */ +enum { + CLEAN, + UPDATE_IN_PROGRESS, + DIRTY +}; + void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; @@ -176,17 +188,17 @@ void kvm_recalculate_apic_map(struct kvm *kvm) int i; u32 max_id = 255; /* enough space for any xAPIC ID */ - if (!kvm->arch.apic_map_dirty) { - /* - * Read kvm->arch.apic_map_dirty before - * kvm->arch.apic_map - */ - smp_rmb(); + /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ + if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN) return; - } mutex_lock(&kvm->arch.apic_map_lock); - if (!kvm->arch.apic_map_dirty) { + /* + * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map + * (if clean) or the APIC registers (if dirty). + */ + if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty, + DIRTY, UPDATE_IN_PROGRESS) == CLEAN) { /* Someone else has updated the map. */ mutex_unlock(&kvm->arch.apic_map_lock); return; @@ -256,11 +268,11 @@ out: lockdep_is_held(&kvm->arch.apic_map_lock)); rcu_assign_pointer(kvm->arch.apic_map, new); /* - * Write kvm->arch.apic_map before - * clearing apic->apic_map_dirty + * Write kvm->arch.apic_map before clearing apic->apic_map_dirty. + * If another update has come in, leave it DIRTY. */ - smp_wmb(); - kvm->arch.apic_map_dirty = false; + atomic_cmpxchg_release(&kvm->arch.apic_map_dirty, + UPDATE_IN_PROGRESS, CLEAN); mutex_unlock(&kvm->arch.apic_map_lock); if (old) @@ -282,20 +294,20 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) else static_key_slow_inc(&apic_sw_disabled.key); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) { kvm_lapic_set_reg(apic, APIC_ID, id << 24); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) { kvm_lapic_set_reg(apic, APIC_LDR, id); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) @@ -311,7 +323,7 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) kvm_lapic_set_reg(apic, APIC_ID, id); kvm_lapic_set_reg(apic, APIC_LDR, ldr); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) @@ -1976,7 +1988,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_DFR: if (!apic_x2apic_mode(apic)) { kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } else ret = 1; break; @@ -2232,7 +2244,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) static_key_slow_dec_deferred(&apic_hw_disabled); } else { static_key_slow_inc(&apic_hw_disabled.key); - vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } } @@ -2273,7 +2285,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) if (!apic) return; - vcpu->kvm->arch.apic_map_dirty = false; /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); @@ -2567,6 +2578,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 0ad06bfe2c2c..444bb9c54548 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -222,7 +222,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index fdd05c233308..76817d13c86e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1745,10 +1745,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, * Emulate arch specific page modification logging for the * nested hypervisor */ -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu) +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa) { if (kvm_x86_ops.write_log_dirty) - return kvm_x86_ops.write_log_dirty(vcpu); + return kvm_x86_ops.write_log_dirty(vcpu, l2_gpa); return 0; } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index a6d484ea110b..bd70ece1ef8b 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -235,7 +235,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte) static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, struct guest_walker *walker, - int write_fault) + gpa_t addr, int write_fault) { unsigned level, index; pt_element_t pte, orig_pte; @@ -260,7 +260,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, !(pte & PT_GUEST_DIRTY_MASK)) { trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); #if PTTYPE == PTTYPE_EPT - if (kvm_arch_write_log_dirty(vcpu)) + if (kvm_arch_write_log_dirty(vcpu, addr)) return -EINVAL; #endif pte |= PT_GUEST_DIRTY_MASK; @@ -360,7 +360,6 @@ retry_walk: ++walker->level; do { - gfn_t real_gfn; unsigned long host_addr; pt_access = pte_access; @@ -375,7 +374,7 @@ retry_walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), + real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), nested_access, &walker->fault); @@ -389,12 +388,10 @@ retry_walk: * information to fix the exit_qualification or exit_info_1 * fields. */ - if (unlikely(real_gfn == UNMAPPED_GVA)) + if (unlikely(real_gpa == UNMAPPED_GVA)) return 0; - real_gfn = gpa_to_gfn(real_gfn); - - host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn, + host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa), &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; @@ -457,7 +454,8 @@ retry_walk: (PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT); if (unlikely(!accessed_dirty)) { - ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault); + ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, + addr, write_fault); if (unlikely(ret < 0)) goto error; else if (ret) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8ccfa4197d9c..c0da4dd78ac5 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3344,7 +3344,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); -static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) +static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) { fastpath_t exit_fastpath; struct vcpu_svm *svm = to_svm(vcpu); diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 5c0ff80b85c0..7a3675fddec2 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -72,11 +72,24 @@ struct loaded_vmcs { struct vmcs_controls_shadow controls_shadow; }; +static inline bool is_intr_type(u32 intr_info, u32 type) +{ + const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK; + + return (intr_info & mask) == (INTR_INFO_VALID_MASK | type); +} + +static inline bool is_intr_type_n(u32 intr_info, u32 type, u8 vector) +{ + const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK | + INTR_INFO_VECTOR_MASK; + + return (intr_info & mask) == (INTR_INFO_VALID_MASK | type | vector); +} + static inline bool is_exception_n(u32 intr_info, u8 vector) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK); + return is_intr_type_n(intr_info, INTR_TYPE_HARD_EXCEPTION, vector); } static inline bool is_debug(u32 intr_info) @@ -106,28 +119,23 @@ static inline bool is_gp_fault(u32 intr_info) static inline bool is_machine_check(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK); + return is_exception_n(intr_info, MC_VECTOR); } /* Undocumented: icebp/int1 */ static inline bool is_icebp(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) - == (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK); + return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION); } static inline bool is_nmi(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) - == (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK); + return is_intr_type(intr_info, INTR_TYPE_NMI_INTR); } static inline bool is_external_intr(u32 intr_info) { - return (intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) - == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR); + return is_intr_type(intr_info, INTR_TYPE_EXT_INTR); } enum vmcs_field_width { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 36c771728c8c..cb22f33bf1d8 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6606,23 +6606,6 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx) -{ - u32 host_umwait_control; - - if (!vmx_has_waitpkg(vmx)) - return; - - host_umwait_control = get_umwait_control_msr(); - - if (vmx->msr_ia32_umwait_control != host_umwait_control) - add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL, - vmx->msr_ia32_umwait_control, - host_umwait_control, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL); -} - static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6728,9 +6711,7 @@ reenter_guest: pt_guest_enter(vmx); - if (vcpu_to_pmu(vcpu)->version) - atomic_switch_perf_msrs(vmx); - atomic_switch_umwait_control_msr(vmx); + atomic_switch_perf_msrs(vmx); if (enable_preemption_timer) vmx_update_hv_timer(vcpu); @@ -7501,11 +7482,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm) kvm_flush_pml_buffers(kvm); } -static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) +static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) { struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); - gpa_t gpa, dst; + gpa_t dst; if (is_guest_mode(vcpu)) { WARN_ON_ONCE(vmx->nested.pml_full); @@ -7524,7 +7505,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) return 1; } - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull; + gpa &= ~0xFFFull; dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index; if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 8a83b5edc820..639798e4a6ca 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -288,8 +288,6 @@ struct vcpu_vmx { u64 current_tsc_ratio; - u32 host_pkru; - unsigned long host_debugctlmsr; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 00c88c2f34e4..3b92db412335 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2856,7 +2856,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSCDEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); @@ -3196,7 +3196,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_APICBASE: msr_info->data = kvm_get_apic_base(vcpu); break; - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); case MSR_IA32_TSCDEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); @@ -4603,7 +4603,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; user_tsc_khz = (u32)arg; - if (user_tsc_khz >= kvm_max_guest_tsc_khz) + if (kvm_has_tsc_control && + user_tsc_khz >= kvm_max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 23632a33ed39..4707e90b8ee5 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -24,6 +24,18 @@ void blk_flush_integrity(void) flush_workqueue(kintegrityd_wq); } +void __bio_integrity_free(struct bio_set *bs, struct bio_integrity_payload *bip) +{ + if (bs && mempool_initialized(&bs->bio_integrity_pool)) { + if (bip->bip_vec) + bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, + bip->bip_slab); + mempool_free(bip, &bs->bio_integrity_pool); + } else { + kfree(bip); + } +} + /** * bio_integrity_alloc - Allocate integrity payload and attach it to bio * @bio: bio to attach integrity metadata to @@ -78,7 +90,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, return bip; err: - mempool_free(bip, &bs->bio_integrity_pool); + __bio_integrity_free(bs, bip); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(bio_integrity_alloc); @@ -99,14 +111,7 @@ void bio_integrity_free(struct bio *bio) kfree(page_address(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset); - if (bs && mempool_initialized(&bs->bio_integrity_pool)) { - bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab); - - mempool_free(bip, &bs->bio_integrity_pool); - } else { - kfree(bip); - } - + __bio_integrity_free(bs, bip); bio->bi_integrity = NULL; bio->bi_opf &= ~REQ_INTEGRITY; } diff --git a/drivers/acpi/acpi_configfs.c b/drivers/acpi/acpi_configfs.c index ece8c1a921cc..88c8af455ea3 100644 --- a/drivers/acpi/acpi_configfs.c +++ b/drivers/acpi/acpi_configfs.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/configfs.h> #include <linux/acpi.h> +#include <linux/security.h> #include "acpica/accommon.h" #include "acpica/actables.h" @@ -28,7 +29,10 @@ static ssize_t acpi_table_aml_write(struct config_item *cfg, { const struct acpi_table_header *header = data; struct acpi_table *table; - int ret; + int ret = security_locked_down(LOCKDOWN_ACPI_TABLES); + + if (ret) + return ret; table = container_of(cfg, struct acpi_table, cfg); diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index 3a89909b50a6..76c668c05fa0 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -938,13 +938,13 @@ static void __exit interrupt_stats_exit(void) } static ssize_t -acpi_show_profile(struct device *dev, struct device_attribute *attr, +acpi_show_profile(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%d\n", acpi_gbl_FADT.preferred_profile); } -static const struct device_attribute pm_profile_attr = +static const struct kobj_attribute pm_profile_attr = __ATTR(pm_profile, S_IRUGO, acpi_show_profile, NULL); static ssize_t hotplug_enabled_show(struct kobject *kobj, diff --git a/drivers/android/binder.c b/drivers/android/binder.c index e47c8a4c83db..f50c5f182bb5 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -4686,8 +4686,15 @@ static struct binder_thread *binder_get_thread(struct binder_proc *proc) static void binder_free_proc(struct binder_proc *proc) { + struct binder_device *device; + BUG_ON(!list_empty(&proc->todo)); BUG_ON(!list_empty(&proc->delivered_death)); + device = container_of(proc->context, struct binder_device, context); + if (refcount_dec_and_test(&device->ref)) { + kfree(proc->context->name); + kfree(device); + } binder_alloc_deferred_release(&proc->alloc); put_task_struct(proc->tsk); binder_stats_deleted(BINDER_STAT_PROC); @@ -5406,7 +5413,6 @@ static int binder_node_release(struct binder_node *node, int refs) static void binder_deferred_release(struct binder_proc *proc) { struct binder_context *context = proc->context; - struct binder_device *device; struct rb_node *n; int threads, nodes, incoming_refs, outgoing_refs, active_transactions; @@ -5423,12 +5429,6 @@ static void binder_deferred_release(struct binder_proc *proc) context->binder_context_mgr_node = NULL; } mutex_unlock(&context->context_mgr_node_lock); - device = container_of(proc->context, struct binder_device, context); - if (refcount_dec_and_test(&device->ref)) { - kfree(context->name); - kfree(device); - } - proc->context = NULL; binder_inner_proc_lock(proc); /* * Make sure proc stays alive after we diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index 977d27bd1a22..a97f33d0c59f 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -265,14 +265,14 @@ static struct notifier_block pm_trace_nb = { .notifier_call = pm_trace_notify, }; -static int early_resume_init(void) +static int __init early_resume_init(void) { hash_value_early_read = read_magic_time(); register_pm_notifier(&pm_trace_nb); return 0; } -static int late_resume_init(void) +static int __init late_resume_init(void) { unsigned int val = hash_value_early_read; unsigned int user, file, dev; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index c472f624382d..06a796821e8b 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -17,6 +17,7 @@ #include <linux/delay.h> #include <linux/log2.h> #include <linux/hwspinlock.h> +#include <asm/unaligned.h> #define CREATE_TRACE_POINTS #include "trace.h" @@ -249,22 +250,20 @@ static void regmap_format_8(void *buf, unsigned int val, unsigned int shift) static void regmap_format_16_be(void *buf, unsigned int val, unsigned int shift) { - __be16 *b = buf; - - b[0] = cpu_to_be16(val << shift); + put_unaligned_be16(val << shift, buf); } static void regmap_format_16_le(void *buf, unsigned int val, unsigned int shift) { - __le16 *b = buf; - - b[0] = cpu_to_le16(val << shift); + put_unaligned_le16(val << shift, buf); } static void regmap_format_16_native(void *buf, unsigned int val, unsigned int shift) { - *(u16 *)buf = val << shift; + u16 v = val << shift; + + memcpy(buf, &v, sizeof(v)); } static void regmap_format_24(void *buf, unsigned int val, unsigned int shift) @@ -280,43 +279,39 @@ static void regmap_format_24(void *buf, unsigned int val, unsigned int shift) static void regmap_format_32_be(void *buf, unsigned int val, unsigned int shift) { - __be32 *b = buf; - - b[0] = cpu_to_be32(val << shift); + put_unaligned_be32(val << shift, buf); } static void regmap_format_32_le(void *buf, unsigned int val, unsigned int shift) { - __le32 *b = buf; - - b[0] = cpu_to_le32(val << shift); + put_unaligned_le32(val << shift, buf); } static void regmap_format_32_native(void *buf, unsigned int val, unsigned int shift) { - *(u32 *)buf = val << shift; + u32 v = val << shift; + + memcpy(buf, &v, sizeof(v)); } #ifdef CONFIG_64BIT static void regmap_format_64_be(void *buf, unsigned int val, unsigned int shift) { - __be64 *b = buf; - - b[0] = cpu_to_be64((u64)val << shift); + put_unaligned_be64((u64) val << shift, buf); } static void regmap_format_64_le(void *buf, unsigned int val, unsigned int shift) { - __le64 *b = buf; - - b[0] = cpu_to_le64((u64)val << shift); + put_unaligned_le64((u64) val << shift, buf); } static void regmap_format_64_native(void *buf, unsigned int val, unsigned int shift) { - *(u64 *)buf = (u64)val << shift; + u64 v = (u64) val << shift; + + memcpy(buf, &v, sizeof(v)); } #endif @@ -333,35 +328,34 @@ static unsigned int regmap_parse_8(const void *buf) static unsigned int regmap_parse_16_be(const void *buf) { - const __be16 *b = buf; - - return be16_to_cpu(b[0]); + return get_unaligned_be16(buf); } static unsigned int regmap_parse_16_le(const void *buf) { - const __le16 *b = buf; - - return le16_to_cpu(b[0]); + return get_unaligned_le16(buf); } static void regmap_parse_16_be_inplace(void *buf) { - __be16 *b = buf; + u16 v = get_unaligned_be16(buf); - b[0] = be16_to_cpu(b[0]); + memcpy(buf, &v, sizeof(v)); } static void regmap_parse_16_le_inplace(void *buf) { - __le16 *b = buf; + u16 v = get_unaligned_le16(buf); - b[0] = le16_to_cpu(b[0]); + memcpy(buf, &v, sizeof(v)); } static unsigned int regmap_parse_16_native(const void *buf) { - return *(u16 *)buf; + u16 v; + + memcpy(&v, buf, sizeof(v)); + return v; } static unsigned int regmap_parse_24(const void *buf) @@ -376,69 +370,67 @@ static unsigned int regmap_parse_24(const void *buf) static unsigned int regmap_parse_32_be(const void *buf) { - const __be32 *b = buf; - - return be32_to_cpu(b[0]); + return get_unaligned_be32(buf); } static unsigned int regmap_parse_32_le(const void *buf) { - const __le32 *b = buf; - - return le32_to_cpu(b[0]); + return get_unaligned_le32(buf); } static void regmap_parse_32_be_inplace(void *buf) { - __be32 *b = buf; + u32 v = get_unaligned_be32(buf); - b[0] = be32_to_cpu(b[0]); + memcpy(buf, &v, sizeof(v)); } static void regmap_parse_32_le_inplace(void *buf) { - __le32 *b = buf; + u32 v = get_unaligned_le32(buf); - b[0] = le32_to_cpu(b[0]); + memcpy(buf, &v, sizeof(v)); } static unsigned int regmap_parse_32_native(const void *buf) { - return *(u32 *)buf; + u32 v; + + memcpy(&v, buf, sizeof(v)); + return v; } #ifdef CONFIG_64BIT static unsigned int regmap_parse_64_be(const void *buf) { - const __be64 *b = buf; - - return be64_to_cpu(b[0]); + return get_unaligned_be64(buf); } static unsigned int regmap_parse_64_le(const void *buf) { - const __le64 *b = buf; - - return le64_to_cpu(b[0]); + return get_unaligned_le64(buf); } static void regmap_parse_64_be_inplace(void *buf) { - __be64 *b = buf; + u64 v = get_unaligned_be64(buf); - b[0] = be64_to_cpu(b[0]); + memcpy(buf, &v, sizeof(v)); } static void regmap_parse_64_le_inplace(void *buf) { - __le64 *b = buf; + u64 v = get_unaligned_le64(buf); - b[0] = le64_to_cpu(b[0]); + memcpy(buf, &v, sizeof(v)); } static unsigned int regmap_parse_64_native(const void *buf) { - return *(u64 *)buf; + u64 v; + + memcpy(&v, buf, sizeof(v)); + return v; } #endif @@ -1357,6 +1349,7 @@ void regmap_exit(struct regmap *map) if (map->hwlock) hwspin_lock_free(map->hwlock); kfree_const(map->name); + kfree(map->patch); kfree(map); } EXPORT_SYMBOL_GPL(regmap_exit); @@ -2944,8 +2937,9 @@ EXPORT_SYMBOL_GPL(regmap_update_bits_base); * @reg: Register to read from * @bits: Bits to test * - * Returns -1 if the underlying regmap_read() fails, 0 if at least one of the - * tested bits is not set and 1 if all tested bits are set. + * Returns 0 if at least one of the tested bits is not set, 1 if all tested + * bits are set and a negative error number if the underlying regmap_read() + * fails. */ int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits) { diff --git a/drivers/clk/sifive/fu540-prci.c b/drivers/clk/sifive/fu540-prci.c index 6282ee2f361c..a8901f90a61a 100644 --- a/drivers/clk/sifive/fu540-prci.c +++ b/drivers/clk/sifive/fu540-prci.c @@ -586,7 +586,10 @@ static int sifive_fu540_prci_probe(struct platform_device *pdev) struct __prci_data *pd; int r; - pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL); + pd = devm_kzalloc(dev, + struct_size(pd, hw_clks.hws, + ARRAY_SIZE(__prci_init_clocks)), + GFP_KERNEL); if (!pd) return -ENOMEM; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 8e23a698ce04..e771e8b4f99f 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2677,6 +2677,8 @@ static struct acpi_platform_list plat_info[] __initdata = { { } /* End */ }; +#define BITMASK_OOB (BIT(8) | BIT(18)) + static bool __init intel_pstate_platform_pwr_mgmt_exists(void) { const struct x86_cpu_id *id; @@ -2686,8 +2688,9 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void) id = x86_match_cpu(intel_pstate_cpu_oob_ids); if (id) { rdmsrl(MSR_MISC_PWR_MGMT, misc_pwr); - if (misc_pwr & (1 << 8)) { - pr_debug("Bit 8 in the MISC_PWR_MGMT MSR set\n"); + if (misc_pwr & BITMASK_OOB) { + pr_debug("Bit 8 or 18 in the MISC_PWR_MGMT MSR set\n"); + pr_debug("P states are controlled in Out of Band mode by the firmware/hardware\n"); return true; } } diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index c149d9e20dfd..87197319ab06 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -186,9 +186,10 @@ int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev) * be frozen safely. */ index = find_deepest_state(drv, dev, U64_MAX, 0, true); - if (index > 0) + if (index > 0) { enter_s2idle_proper(drv, dev, index); - + local_irq_enable(); + } return index; } #endif /* CONFIG_SUSPEND */ diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index ef90070a9194..6262f6370c5d 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -269,6 +269,8 @@ static int get_scrub_rate(struct mem_ctl_info *mci) if (pvt->model == 0x60) amd64_read_pci_cfg(pvt->F2, F15H_M60H_SCRCTRL, &scrubval); + else + amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval); } else { amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval); } diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig index b2408a710662..7cd5a29fc437 100644 --- a/drivers/fpga/Kconfig +++ b/drivers/fpga/Kconfig @@ -208,7 +208,7 @@ config FPGA_DFL_PCI config FPGA_MGR_ZYNQMP_FPGA tristate "Xilinx ZynqMP FPGA" - depends on ARCH_ZYNQMP || COMPILE_TEST + depends on ZYNQMP_FIRMWARE || (!ZYNQMP_FIRMWARE && COMPILE_TEST) help FPGA manager driver support for Xilinx ZynqMP FPGAs. This driver uses the processor configuration port(PCAP) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index b544baf306f2..5d71c23e2640 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1298,8 +1298,12 @@ static int sdma_v5_0_sw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int i; - for (i = 0; i < adev->sdma.num_instances; i++) + for (i = 0; i < adev->sdma.num_instances; i++) { + if (adev->sdma.instance[i].fw != NULL) + release_firmware(adev->sdma.instance[i].fw); + amdgpu_ring_fini(&adev->sdma.instance[i].ring); + } return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index d27221ddcdeb..0e0c42e9f6a3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -428,6 +428,7 @@ struct kfd_process *kfd_create_process(struct file *filep) (int)process->lead_thread->pid); if (ret) { pr_warn("Creating procfs pid directory failed"); + kobject_put(process->kobj); goto out; } 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 7ced9f87be97..10ac8076d4f2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5024,7 +5024,8 @@ create_validate_stream_for_sink(struct amdgpu_dm_connector *aconnector, struct drm_connector *connector = &aconnector->base; struct amdgpu_device *adev = connector->dev->dev_private; struct dc_stream_state *stream; - int requested_bpc = connector->state ? connector->state->max_requested_bpc : 8; + const struct drm_connector_state *drm_state = dm_state ? &dm_state->base : NULL; + int requested_bpc = drm_state ? drm_state->max_requested_bpc : 8; enum dc_status dc_result = DC_OK; do { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 076af267b488..1d692f4f42f3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -1058,7 +1058,6 @@ static const struct { {"link_settings", &dp_link_settings_debugfs_fops}, {"phy_settings", &dp_phy_settings_debugfs_fop}, {"test_pattern", &dp_phy_test_pattern_fops}, - {"output_bpc", &output_bpc_fops}, {"vrr_range", &vrr_range_fops}, #ifdef CONFIG_DRM_AMD_DC_HDCP {"hdcp_sink_capability", &hdcp_sink_capability_fops}, @@ -1142,6 +1141,9 @@ void connector_debugfs_init(struct amdgpu_dm_connector *connector) debugfs_create_file_unsafe("force_yuv420_output", 0644, dir, connector, &force_yuv420_output_fops); + debugfs_create_file("output_bpc", 0644, dir, connector, + &output_bpc_fops); + connector->debugfs_dpcd_address = 0; connector->debugfs_dpcd_size = 0; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index dcf84a61de37..949d10ef8304 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -510,8 +510,10 @@ static ssize_t srm_data_read(struct file *filp, struct kobject *kobj, struct bin srm = psp_get_srm(work->hdcp.config.psp.handle, &srm_version, &srm_size); - if (!srm) - return -EINVAL; + if (!srm) { + ret = -EINVAL; + goto ret; + } if (pos >= srm_size) ret = 0; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 170aa7689110..5609e164805f 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -227,18 +227,9 @@ int drm_fb_helper_debug_leave(struct fb_info *info) } EXPORT_SYMBOL(drm_fb_helper_debug_leave); -/** - * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration - * @fb_helper: driver-allocated fbdev helper, can be NULL - * - * This should be called from driver's drm &drm_driver.lastclose callback - * when implementing an fbcon on top of kms using this helper. This ensures that - * the user isn't greeted with a black screen when e.g. X dies. - * - * RETURNS: - * Zero if everything went ok, negative error code otherwise. - */ -int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) +static int +__drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper, + bool force) { bool do_delayed; int ret; @@ -250,7 +241,16 @@ int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) return 0; mutex_lock(&fb_helper->lock); - ret = drm_client_modeset_commit(&fb_helper->client); + if (force) { + /* + * Yes this is the _locked version which expects the master lock + * to be held. But for forced restores we're intentionally + * racing here, see drm_fb_helper_set_par(). + */ + ret = drm_client_modeset_commit_locked(&fb_helper->client); + } else { + ret = drm_client_modeset_commit(&fb_helper->client); + } do_delayed = fb_helper->delayed_hotplug; if (do_delayed) @@ -262,6 +262,22 @@ int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) return ret; } + +/** + * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration + * @fb_helper: driver-allocated fbdev helper, can be NULL + * + * This should be called from driver's drm &drm_driver.lastclose callback + * when implementing an fbcon on top of kms using this helper. This ensures that + * the user isn't greeted with a black screen when e.g. X dies. + * + * RETURNS: + * Zero if everything went ok, negative error code otherwise. + */ +int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) +{ + return __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, false); +} EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked); #ifdef CONFIG_MAGIC_SYSRQ @@ -1318,6 +1334,7 @@ int drm_fb_helper_set_par(struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct fb_var_screeninfo *var = &info->var; + bool force; if (oops_in_progress) return -EBUSY; @@ -1327,7 +1344,25 @@ int drm_fb_helper_set_par(struct fb_info *info) return -EINVAL; } - drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper); + /* + * Normally we want to make sure that a kms master takes precedence over + * fbdev, to avoid fbdev flickering and occasionally stealing the + * display status. But Xorg first sets the vt back to text mode using + * the KDSET IOCTL with KD_TEXT, and only after that drops the master + * status when exiting. + * + * In the past this was caught by drm_fb_helper_lastclose(), but on + * modern systems where logind always keeps a drm fd open to orchestrate + * the vt switching, this doesn't work. + * + * To not break the userspace ABI we have this special case here, which + * is only used for the above case. Everything else uses the normal + * commit function, which ensures that we never steal the display from + * an active drm master. + */ + force = var->activate & FB_ACTIVATE_KD_TEXT; + + __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, force); return 0; } diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index ffd95bfeaa94..d00ea384dcbf 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -30,12 +30,6 @@ struct drm_dmi_panel_orientation_data { int orientation; }; -static const struct drm_dmi_panel_orientation_data acer_s1003 = { - .width = 800, - .height = 1280, - .orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP, -}; - static const struct drm_dmi_panel_orientation_data asus_t100ha = { .width = 800, .height = 1280, @@ -114,13 +108,19 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"), }, - .driver_data = (void *)&acer_s1003, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* Asus T100HA */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100HAN"), }, .driver_data = (void *)&asus_t100ha, + }, { /* Asus T101HA */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T101HA"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* GPD MicroPC (generic strings, also match on bios date) */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"), diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c index 04e1d38d41f7..08802e5177f6 100644 --- a/drivers/gpu/drm/mcde/mcde_display.c +++ b/drivers/gpu/drm/mcde/mcde_display.c @@ -812,7 +812,7 @@ static void mcde_display_enable(struct drm_simple_display_pipe *pipe, struct drm_crtc *crtc = &pipe->crtc; struct drm_plane *plane = &pipe->plane; struct drm_device *drm = crtc->dev; - struct mcde *mcde = drm->dev_private; + struct mcde *mcde = to_mcde(drm); const struct drm_display_mode *mode = &cstate->mode; struct drm_framebuffer *fb = plane->state->fb; u32 format = fb->format->format; diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index 84f3e2dbd77b..80082d6dce3a 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -209,7 +209,6 @@ static int mcde_modeset_init(struct drm_device *drm) drm_mode_config_reset(drm); drm_kms_helper_poll_init(drm); - drm_fbdev_generic_setup(drm, 32); return 0; } @@ -264,6 +263,8 @@ static int mcde_drm_bind(struct device *dev) if (ret < 0) goto unbind; + drm_fbdev_generic_setup(drm, 32); + return 0; unbind: diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index b6ecd1552132..5178f87d6574 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2495,6 +2495,7 @@ static const struct panel_desc logicpd_type_28 = { .bus_format = MEDIA_BUS_FMT_RGB888_1X24, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE | DRM_BUS_FLAG_SYNC_DRIVE_NEGEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, }; static const struct panel_desc mitsubishi_aa070mc01 = { @@ -2663,6 +2664,7 @@ static const struct panel_desc newhaven_nhd_43_480272ef_atxl = { .bus_format = MEDIA_BUS_FMT_RGB888_1X24, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE | DRM_BUS_FLAG_SYNC_DRIVE_POSEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, }; static const struct display_timing nlt_nl192108ac18_02d_timing = { diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c index b57c37ddd164..c7fbb7932f37 100644 --- a/drivers/gpu/drm/radeon/ni_dpm.c +++ b/drivers/gpu/drm/radeon/ni_dpm.c @@ -2127,7 +2127,7 @@ static int ni_init_smc_spll_table(struct radeon_device *rdev) if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT)) ret = -EINVAL; - if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT)) + if (fb_div & ~(SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_SHIFT)) ret = -EINVAL; if (clk_v & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_SHIFT)) diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig index 0919f1f159a4..f65d1489dc50 100644 --- a/drivers/gpu/drm/rcar-du/Kconfig +++ b/drivers/gpu/drm/rcar-du/Kconfig @@ -31,6 +31,7 @@ config DRM_RCAR_DW_HDMI config DRM_RCAR_LVDS tristate "R-Car DU LVDS Encoder Support" depends on DRM && DRM_BRIDGE && OF + select DRM_KMS_HELPER select DRM_PANEL select OF_FLATTREE select OF_OVERLAY diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c index 56cc037fd312..cc4fb916318f 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.c +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c @@ -363,6 +363,19 @@ static int sun8i_mixer_bind(struct device *dev, struct device *master, mixer->engine.ops = &sun8i_engine_ops; mixer->engine.node = dev->of_node; + if (of_find_property(dev->of_node, "iommus", NULL)) { + /* + * This assume we have the same DMA constraints for + * all our the mixers in our pipeline. This sounds + * bad, but it has always been the case for us, and + * DRM doesn't do per-device allocation either, so we + * would need to fix DRM first... + */ + ret = of_dma_configure(drm->dev, dev->of_node, true); + if (ret) + return ret; + } + /* * While this function can fail, we shouldn't do anything * if this happens. Some early DE2 DT entries don't provide diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 83f31c6e891c..04d6848d19fc 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -957,6 +957,7 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm, } drm_plane_helper_add(&plane->base, &tegra_cursor_plane_helper_funcs); + drm_plane_create_zpos_immutable_property(&plane->base, 255); return &plane->base; } diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c index 8183e617bf6b..22a03f7ffdc1 100644 --- a/drivers/gpu/drm/tegra/hub.c +++ b/drivers/gpu/drm/tegra/hub.c @@ -149,7 +149,9 @@ int tegra_display_hub_prepare(struct tegra_display_hub *hub) for (i = 0; i < hub->soc->num_wgrps; i++) { struct tegra_windowgroup *wgrp = &hub->wgrps[i]; - tegra_windowgroup_enable(wgrp); + /* Skip orphaned window group whose parent DC is disabled */ + if (wgrp->parent) + tegra_windowgroup_enable(wgrp); } return 0; @@ -166,7 +168,9 @@ void tegra_display_hub_cleanup(struct tegra_display_hub *hub) for (i = 0; i < hub->soc->num_wgrps; i++) { struct tegra_windowgroup *wgrp = &hub->wgrps[i]; - tegra_windowgroup_disable(wgrp); + /* Skip orphaned window group whose parent DC is disabled */ + if (wgrp->parent) + tegra_windowgroup_disable(wgrp); } } @@ -944,6 +948,15 @@ static int tegra_display_hub_probe(struct platform_device *pdev) dev_err(&pdev->dev, "failed to register host1x client: %d\n", err); + err = devm_of_platform_populate(&pdev->dev); + if (err < 0) + goto unregister; + + return err; + +unregister: + host1x_client_unregister(&hub->client); + pm_runtime_disable(&pdev->dev); return err; } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index f73b81c2576e..0f20e14a4cfd 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -883,8 +883,10 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, if (!fence) return 0; - if (no_wait_gpu) + if (no_wait_gpu) { + dma_fence_put(fence); return -EBUSY; + } dma_resv_add_shared_fence(bo->base.resv, fence); diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index a43aa7275f12..fa03fab02076 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -300,8 +300,10 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, break; case -EBUSY: case -ERESTARTSYS: + dma_fence_put(moving); return VM_FAULT_NOPAGE; default: + dma_fence_put(moving); return VM_FAULT_SIGBUS; } diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index 6a995db51d6d..e201f62d62c0 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -686,8 +686,17 @@ EXPORT_SYMBOL(host1x_driver_register_full); */ void host1x_driver_unregister(struct host1x_driver *driver) { + struct host1x *host1x; + driver_unregister(&driver->driver); + mutex_lock(&devices_lock); + + list_for_each_entry(host1x, &devices, list) + host1x_detach_driver(host1x, driver); + + mutex_unlock(&devices_lock); + mutex_lock(&drivers_lock); list_del_init(&driver->list); mutex_unlock(&drivers_lock); diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index d24344e91922..d0ebb70e2fdd 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -468,11 +468,18 @@ static int host1x_probe(struct platform_device *pdev) err = host1x_register(host); if (err < 0) - goto deinit_intr; + goto deinit_debugfs; + + err = devm_of_platform_populate(&pdev->dev); + if (err < 0) + goto unregister; return 0; -deinit_intr: +unregister: + host1x_unregister(host); +deinit_debugfs: + host1x_debug_deinit(host); host1x_intr_deinit(host); deinit_syncpt: host1x_syncpt_deinit(host); diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 9ce787e37e22..0d1377232933 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -918,6 +918,7 @@ static void cm_free_work(struct cm_work *work) static void cm_queue_work_unlock(struct cm_id_private *cm_id_priv, struct cm_work *work) + __releases(&cm_id_priv->lock) { bool immediate; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 3d7cc9f0f3d4..c30cf5307ce3 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1624,6 +1624,8 @@ static struct rdma_id_private *cma_find_listener( { struct rdma_id_private *id_priv, *id_priv_dev; + lockdep_assert_held(&lock); + if (!bind_list) return ERR_PTR(-EINVAL); @@ -1670,6 +1672,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id, } } + mutex_lock(&lock); /* * Net namespace might be getting deleted while route lookup, * cm_id lookup is in progress. Therefore, perform netdevice @@ -1711,6 +1714,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id, id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev); err: rcu_read_unlock(); + mutex_unlock(&lock); if (IS_ERR(id_priv) && *net_dev) { dev_put(*net_dev); *net_dev = NULL; @@ -2492,6 +2496,8 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv, struct net *net = id_priv->id.route.addr.dev_addr.net; int ret; + lockdep_assert_held(&lock); + if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) return; @@ -3342,6 +3348,8 @@ static void cma_bind_port(struct rdma_bind_list *bind_list, u64 sid, mask; __be16 port; + lockdep_assert_held(&lock); + addr = cma_src_addr(id_priv); port = htons(bind_list->port); @@ -3370,6 +3378,8 @@ static int cma_alloc_port(enum rdma_ucm_port_space ps, struct rdma_bind_list *bind_list; int ret; + lockdep_assert_held(&lock); + bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL); if (!bind_list) return -ENOMEM; @@ -3396,6 +3406,8 @@ static int cma_port_is_unique(struct rdma_bind_list *bind_list, struct sockaddr *saddr = cma_src_addr(id_priv); __be16 dport = cma_port(daddr); + lockdep_assert_held(&lock); + hlist_for_each_entry(cur_id, &bind_list->owners, node) { struct sockaddr *cur_daddr = cma_dst_addr(cur_id); struct sockaddr *cur_saddr = cma_src_addr(cur_id); @@ -3435,6 +3447,8 @@ static int cma_alloc_any_port(enum rdma_ucm_port_space ps, unsigned int rover; struct net *net = id_priv->id.route.addr.dev_addr.net; + lockdep_assert_held(&lock); + inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rover = prandom_u32() % remaining + low; @@ -3482,6 +3496,8 @@ static int cma_check_port(struct rdma_bind_list *bind_list, struct rdma_id_private *cur_id; struct sockaddr *addr, *cur_addr; + lockdep_assert_held(&lock); + addr = cma_src_addr(id_priv); hlist_for_each_entry(cur_id, &bind_list->owners, node) { if (id_priv == cur_id) @@ -3512,6 +3528,8 @@ static int cma_use_port(enum rdma_ucm_port_space ps, unsigned short snum; int ret; + lockdep_assert_held(&lock); + snum = ntohs(cma_port(cma_src_addr(id_priv))); if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c index 2257d7f7810f..738d1faf4bba 100644 --- a/drivers/infiniband/core/counters.c +++ b/drivers/infiniband/core/counters.c @@ -202,7 +202,7 @@ static int __rdma_counter_unbind_qp(struct ib_qp *qp) return ret; } -static void counter_history_stat_update(const struct rdma_counter *counter) +static void counter_history_stat_update(struct rdma_counter *counter) { struct ib_device *dev = counter->device; struct rdma_port_counter *port_counter; @@ -212,6 +212,8 @@ static void counter_history_stat_update(const struct rdma_counter *counter) if (!port_counter->hstats) return; + rdma_counter_query_stats(counter); + for (i = 0; i < counter->stats->num_counters; i++) port_counter->hstats->value[i] += counter->stats->value[i]; } diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 186e0d652e8b..a09f8e3c7f3f 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -509,10 +509,10 @@ static void unregister_mad_agent(struct ib_mad_agent_private *mad_agent_priv) xa_erase(&ib_mad_clients, mad_agent_priv->agent.hi_tid); flush_workqueue(port_priv->wq); - ib_cancel_rmpp_recvs(mad_agent_priv); deref_mad_agent(mad_agent_priv); wait_for_completion(&mad_agent_priv->comp); + ib_cancel_rmpp_recvs(mad_agent_priv); ib_mad_agent_security_cleanup(&mad_agent_priv->agent); @@ -2718,6 +2718,7 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info, DMA_FROM_DEVICE); if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device, sg_list.addr))) { + kfree(mad_priv); ret = -ENOMEM; break; } diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 38de4942c682..3027cd2fb247 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -470,40 +470,46 @@ static struct ib_uobject * alloc_begin_fd_uobject(const struct uverbs_api_object *obj, struct uverbs_attr_bundle *attrs) { - const struct uverbs_obj_fd_type *fd_type = - container_of(obj->type_attrs, struct uverbs_obj_fd_type, type); + const struct uverbs_obj_fd_type *fd_type; int new_fd; - struct ib_uobject *uobj; + struct ib_uobject *uobj, *ret; struct file *filp; + uobj = alloc_uobj(attrs, obj); + if (IS_ERR(uobj)) + return uobj; + + fd_type = + container_of(obj->type_attrs, struct uverbs_obj_fd_type, type); if (WARN_ON(fd_type->fops->release != &uverbs_uobject_fd_release && - fd_type->fops->release != &uverbs_async_event_release)) - return ERR_PTR(-EINVAL); + fd_type->fops->release != &uverbs_async_event_release)) { + ret = ERR_PTR(-EINVAL); + goto err_fd; + } new_fd = get_unused_fd_flags(O_CLOEXEC); - if (new_fd < 0) - return ERR_PTR(new_fd); - - uobj = alloc_uobj(attrs, obj); - if (IS_ERR(uobj)) + if (new_fd < 0) { + ret = ERR_PTR(new_fd); goto err_fd; + } /* Note that uverbs_uobject_fd_release() is called during abort */ filp = anon_inode_getfile(fd_type->name, fd_type->fops, NULL, fd_type->flags); if (IS_ERR(filp)) { - uverbs_uobject_put(uobj); - uobj = ERR_CAST(filp); - goto err_fd; + ret = ERR_CAST(filp); + goto err_getfile; } uobj->object = filp; uobj->id = new_fd; return uobj; -err_fd: +err_getfile: put_unused_fd(new_fd); - return uobj; +err_fd: + uverbs_uobject_put(uobj); + return ret; } struct ib_uobject *rdma_alloc_begin_uobject(const struct uverbs_api_object *obj, diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 08313f7c73bc..7dd082441333 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -212,6 +212,7 @@ int efa_query_device(struct ib_device *ibdev, props->max_send_sge = dev_attr->max_sq_sge; props->max_recv_sge = dev_attr->max_rq_sge; props->max_sge_rd = dev_attr->max_wr_rdma_sge; + props->max_pkeys = 1; if (udata && udata->outlen) { resp.max_sq_sge = dev_attr->max_sq_sge; diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c index 4633a0ce1a8c..2ced236e1553 100644 --- a/drivers/infiniband/hw/hfi1/debugfs.c +++ b/drivers/infiniband/hw/hfi1/debugfs.c @@ -985,15 +985,10 @@ static ssize_t qsfp2_debugfs_read(struct file *file, char __user *buf, static int __i2c_debugfs_open(struct inode *in, struct file *fp, u32 target) { struct hfi1_pportdata *ppd; - int ret; ppd = private2ppd(fp); - ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0); - if (ret) /* failed - release the module */ - module_put(THIS_MODULE); - - return ret; + return acquire_chip_resource(ppd->dd, i2c_target(target), 0); } static int i2c1_debugfs_open(struct inode *in, struct file *fp) @@ -1013,7 +1008,6 @@ static int __i2c_debugfs_release(struct inode *in, struct file *fp, u32 target) ppd = private2ppd(fp); release_chip_resource(ppd->dd, i2c_target(target)); - module_put(THIS_MODULE); return 0; } @@ -1031,18 +1025,10 @@ static int i2c2_debugfs_release(struct inode *in, struct file *fp) static int __qsfp_debugfs_open(struct inode *in, struct file *fp, u32 target) { struct hfi1_pportdata *ppd; - int ret; - - if (!try_module_get(THIS_MODULE)) - return -ENODEV; ppd = private2ppd(fp); - ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0); - if (ret) /* failed - release the module */ - module_put(THIS_MODULE); - - return ret; + return acquire_chip_resource(ppd->dd, i2c_target(target), 0); } static int qsfp1_debugfs_open(struct inode *in, struct file *fp) @@ -1062,7 +1048,6 @@ static int __qsfp_debugfs_release(struct inode *in, struct file *fp, u32 target) ppd = private2ppd(fp); release_chip_resource(ppd->dd, i2c_target(target)); - module_put(THIS_MODULE); return 0; } diff --git a/drivers/infiniband/hw/hfi1/iowait.h b/drivers/infiniband/hw/hfi1/iowait.h index 07847cb72169..d580aa17ae37 100644 --- a/drivers/infiniband/hw/hfi1/iowait.h +++ b/drivers/infiniband/hw/hfi1/iowait.h @@ -399,7 +399,7 @@ static inline void iowait_get_priority(struct iowait *w) * @wait_head: the wait queue * * This function is called to insert an iowait struct into a - * wait queue after a resource (eg, sdma decriptor or pio + * wait queue after a resource (eg, sdma descriptor or pio * buffer) is run out. */ static inline void iowait_queue(bool pkts_sent, struct iowait *w, diff --git a/drivers/infiniband/hw/hfi1/ipoib.h b/drivers/infiniband/hw/hfi1/ipoib.h index 185c9b02c974..b8c9d0a003fb 100644 --- a/drivers/infiniband/hw/hfi1/ipoib.h +++ b/drivers/infiniband/hw/hfi1/ipoib.h @@ -67,6 +67,9 @@ struct hfi1_ipoib_circ_buf { * @sde: sdma engine * @tx_list: tx request list * @sent_txreqs: count of txreqs posted to sdma + * @stops: count of stops of queue + * @ring_full: ring has been filled + * @no_desc: descriptor shortage seen * @flow: tracks when list needs to be flushed for a flow change * @q_idx: ipoib Tx queue index * @pkts_sent: indicator packets have been sent from this queue @@ -80,6 +83,9 @@ struct hfi1_ipoib_txq { struct sdma_engine *sde; struct list_head tx_list; u64 sent_txreqs; + atomic_t stops; + atomic_t ring_full; + atomic_t no_desc; union hfi1_ipoib_flow flow; u8 q_idx; bool pkts_sent; diff --git a/drivers/infiniband/hw/hfi1/ipoib_tx.c b/drivers/infiniband/hw/hfi1/ipoib_tx.c index 883cb9d48022..9df292b51a05 100644 --- a/drivers/infiniband/hw/hfi1/ipoib_tx.c +++ b/drivers/infiniband/hw/hfi1/ipoib_tx.c @@ -55,23 +55,48 @@ static u64 hfi1_ipoib_txreqs(const u64 sent, const u64 completed) return sent - completed; } -static void hfi1_ipoib_check_queue_depth(struct hfi1_ipoib_txq *txq) +static u64 hfi1_ipoib_used(struct hfi1_ipoib_txq *txq) { - if (unlikely(hfi1_ipoib_txreqs(++txq->sent_txreqs, - atomic64_read(&txq->complete_txreqs)) >= - min_t(unsigned int, txq->priv->netdev->tx_queue_len, - txq->tx_ring.max_items - 1))) + return hfi1_ipoib_txreqs(txq->sent_txreqs, + atomic64_read(&txq->complete_txreqs)); +} + +static void hfi1_ipoib_stop_txq(struct hfi1_ipoib_txq *txq) +{ + if (atomic_inc_return(&txq->stops) == 1) netif_stop_subqueue(txq->priv->netdev, txq->q_idx); } +static void hfi1_ipoib_wake_txq(struct hfi1_ipoib_txq *txq) +{ + if (atomic_dec_and_test(&txq->stops)) + netif_wake_subqueue(txq->priv->netdev, txq->q_idx); +} + +static uint hfi1_ipoib_ring_hwat(struct hfi1_ipoib_txq *txq) +{ + return min_t(uint, txq->priv->netdev->tx_queue_len, + txq->tx_ring.max_items - 1); +} + +static uint hfi1_ipoib_ring_lwat(struct hfi1_ipoib_txq *txq) +{ + return min_t(uint, txq->priv->netdev->tx_queue_len, + txq->tx_ring.max_items) >> 1; +} + +static void hfi1_ipoib_check_queue_depth(struct hfi1_ipoib_txq *txq) +{ + ++txq->sent_txreqs; + if (hfi1_ipoib_used(txq) >= hfi1_ipoib_ring_hwat(txq) && + !atomic_xchg(&txq->ring_full, 1)) + hfi1_ipoib_stop_txq(txq); +} + static void hfi1_ipoib_check_queue_stopped(struct hfi1_ipoib_txq *txq) { struct net_device *dev = txq->priv->netdev; - /* If the queue is already running just return */ - if (likely(!__netif_subqueue_stopped(dev, txq->q_idx))) - return; - /* If shutting down just return as queue state is irrelevant */ if (unlikely(dev->reg_state != NETREG_REGISTERED)) return; @@ -86,11 +111,9 @@ static void hfi1_ipoib_check_queue_stopped(struct hfi1_ipoib_txq *txq) * Use the minimum of the current tx_queue_len or the rings max txreqs * to protect against ring overflow. */ - if (hfi1_ipoib_txreqs(txq->sent_txreqs, - atomic64_read(&txq->complete_txreqs)) - < min_t(unsigned int, dev->tx_queue_len, - txq->tx_ring.max_items) >> 1) - netif_wake_subqueue(dev, txq->q_idx); + if (hfi1_ipoib_used(txq) < hfi1_ipoib_ring_lwat(txq) && + atomic_xchg(&txq->ring_full, 0)) + hfi1_ipoib_wake_txq(txq); } static void hfi1_ipoib_free_tx(struct ipoib_txreq *tx, int budget) @@ -364,11 +387,12 @@ static struct ipoib_txreq *hfi1_ipoib_send_dma_common(struct net_device *dev, if (unlikely(!tx)) return ERR_PTR(-ENOMEM); - /* so that we can test if the sdma decriptors are there */ + /* so that we can test if the sdma descriptors are there */ tx->txreq.num_desc = 0; tx->priv = priv; tx->txq = txp->txq; tx->skb = skb; + INIT_LIST_HEAD(&tx->txreq.list); hfi1_ipoib_build_ib_tx_headers(tx, txp); @@ -469,6 +493,7 @@ static int hfi1_ipoib_send_dma_single(struct net_device *dev, ret = hfi1_ipoib_submit_tx(txq, tx); if (likely(!ret)) { +tx_ok: trace_sdma_output_ibhdr(tx->priv->dd, &tx->sdma_hdr.hdr, ib_is_sc5(txp->flow.sc5)); @@ -478,20 +503,8 @@ static int hfi1_ipoib_send_dma_single(struct net_device *dev, txq->pkts_sent = false; - if (ret == -EBUSY) { - list_add_tail(&tx->txreq.list, &txq->tx_list); - - trace_sdma_output_ibhdr(tx->priv->dd, - &tx->sdma_hdr.hdr, - ib_is_sc5(txp->flow.sc5)); - hfi1_ipoib_check_queue_depth(txq); - return NETDEV_TX_OK; - } - - if (ret == -ECOMM) { - hfi1_ipoib_check_queue_depth(txq); - return NETDEV_TX_OK; - } + if (ret == -EBUSY || ret == -ECOMM) + goto tx_ok; sdma_txclean(priv->dd, &tx->txreq); dev_kfree_skb_any(skb); @@ -509,9 +522,17 @@ static int hfi1_ipoib_send_dma_list(struct net_device *dev, struct ipoib_txreq *tx; /* Has the flow change ? */ - if (txq->flow.as_int != txp->flow.as_int) - (void)hfi1_ipoib_flush_tx_list(dev, txq); - + if (txq->flow.as_int != txp->flow.as_int) { + int ret; + + ret = hfi1_ipoib_flush_tx_list(dev, txq); + if (unlikely(ret)) { + if (ret == -EBUSY) + ++dev->stats.tx_dropped; + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + } tx = hfi1_ipoib_send_dma_common(dev, skb, txp); if (IS_ERR(tx)) { int ret = PTR_ERR(tx); @@ -610,10 +631,14 @@ static int hfi1_ipoib_sdma_sleep(struct sdma_engine *sde, return -EAGAIN; } - netif_stop_subqueue(txq->priv->netdev, txq->q_idx); - - if (list_empty(&txq->wait.list)) + if (list_empty(&txreq->list)) + /* came from non-list submit */ + list_add_tail(&txreq->list, &txq->tx_list); + if (list_empty(&txq->wait.list)) { + if (!atomic_xchg(&txq->no_desc, 1)) + hfi1_ipoib_stop_txq(txq); iowait_queue(pkts_sent, wait->iow, &sde->dmawait); + } write_sequnlock(&sde->waitlock); return -EBUSY; @@ -648,9 +673,9 @@ static void hfi1_ipoib_flush_txq(struct work_struct *work) struct net_device *dev = txq->priv->netdev; if (likely(dev->reg_state == NETREG_REGISTERED) && - likely(__netif_subqueue_stopped(dev, txq->q_idx)) && likely(!hfi1_ipoib_flush_tx_list(dev, txq))) - netif_wake_subqueue(dev, txq->q_idx); + if (atomic_xchg(&txq->no_desc, 0)) + hfi1_ipoib_wake_txq(txq); } int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv) @@ -704,6 +729,9 @@ int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv) txq->sde = NULL; INIT_LIST_HEAD(&txq->tx_list); atomic64_set(&txq->complete_txreqs, 0); + atomic_set(&txq->stops, 0); + atomic_set(&txq->ring_full, 0); + atomic_set(&txq->no_desc, 0); txq->q_idx = i; txq->flow.tx_queue = 0xff; txq->flow.sc5 = 0xff; @@ -769,7 +797,7 @@ static void hfi1_ipoib_drain_tx_list(struct hfi1_ipoib_txq *txq) atomic64_inc(complete_txreqs); } - if (hfi1_ipoib_txreqs(txq->sent_txreqs, atomic64_read(complete_txreqs))) + if (hfi1_ipoib_used(txq)) dd_dev_warn(txq->priv->dd, "txq %d not empty found %llu requests\n", txq->q_idx, diff --git a/drivers/infiniband/hw/hfi1/netdev_rx.c b/drivers/infiniband/hw/hfi1/netdev_rx.c index 63688e85e8da..6d263c9749b3 100644 --- a/drivers/infiniband/hw/hfi1/netdev_rx.c +++ b/drivers/infiniband/hw/hfi1/netdev_rx.c @@ -373,7 +373,7 @@ void hfi1_netdev_free(struct hfi1_devdata *dd) { if (dd->dummy_netdev) { dd_dev_info(dd, "hfi1 netdev freed\n"); - free_netdev(dd->dummy_netdev); + kfree(dd->dummy_netdev); dd->dummy_netdev = NULL; } } diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h index bfa6e081cb56..d2d526c5a756 100644 --- a/drivers/infiniband/hw/hfi1/verbs_txreq.h +++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h @@ -91,7 +91,7 @@ static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev, tx->mr = NULL; tx->sde = priv->s_sde; tx->psc = priv->s_sendcontext; - /* so that we can test if the sdma decriptors are there */ + /* so that we can test if the sdma descriptors are there */ tx->txreq.num_desc = 0; /* Set the header type */ tx->phdr.hdr.hdr_type = priv->hdr_type; diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index a77fa6730b2d..479fa557993e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -898,13 +898,14 @@ struct hns_roce_hw { int (*set_mac)(struct hns_roce_dev *hr_dev, u8 phy_port, u8 *addr); void (*set_mtu)(struct hns_roce_dev *hr_dev, u8 phy_port, enum ib_mtu mtu); - int (*write_mtpt)(void *mb_buf, struct hns_roce_mr *mr, - unsigned long mtpt_idx); + int (*write_mtpt)(struct hns_roce_dev *hr_dev, void *mb_buf, + struct hns_roce_mr *mr, unsigned long mtpt_idx); int (*rereg_write_mtpt)(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr, int flags, u32 pdn, int mr_access_flags, u64 iova, u64 size, void *mb_buf); - int (*frmr_write_mtpt)(void *mb_buf, struct hns_roce_mr *mr); + int (*frmr_write_mtpt)(struct hns_roce_dev *hr_dev, void *mb_buf, + struct hns_roce_mr *mr); int (*mw_write_mtpt)(void *mb_buf, struct hns_roce_mw *mw); void (*write_cqc)(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq, void *mb_buf, u64 *mtts, diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index d02207cd30df..cf39f560b800 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -1756,10 +1756,10 @@ static void hns_roce_v1_set_mtu(struct hns_roce_dev *hr_dev, u8 phy_port, val); } -static int hns_roce_v1_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, +static int hns_roce_v1_write_mtpt(struct hns_roce_dev *hr_dev, void *mb_buf, + struct hns_roce_mr *mr, unsigned long mtpt_idx) { - struct hns_roce_dev *hr_dev = to_hr_dev(mr->ibmr.device); u64 pages[HNS_ROCE_MAX_INNER_MTPT_NUM] = { 0 }; struct ib_device *ibdev = &hr_dev->ib_dev; struct hns_roce_v1_mpt_entry *mpt_entry; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index c597d7281629..dd01a51816cc 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -910,7 +910,7 @@ static int hns_roce_v2_rst_process_cmd(struct hns_roce_dev *hr_dev) instance_stage = handle->rinfo.instance_state; reset_stage = handle->rinfo.reset_state; reset_cnt = ops->ae_dev_reset_cnt(handle); - hw_resetting = ops->get_hw_reset_stat(handle); + hw_resetting = ops->get_cmdq_stat(handle); sw_resetting = ops->ae_dev_resetting(handle); if (reset_cnt != hr_dev->reset_cnt) @@ -2529,10 +2529,10 @@ static int hns_roce_v2_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port, return hns_roce_cmq_send(hr_dev, &desc, 1); } -static int set_mtpt_pbl(struct hns_roce_v2_mpt_entry *mpt_entry, +static int set_mtpt_pbl(struct hns_roce_dev *hr_dev, + struct hns_roce_v2_mpt_entry *mpt_entry, struct hns_roce_mr *mr) { - struct hns_roce_dev *hr_dev = to_hr_dev(mr->ibmr.device); u64 pages[HNS_ROCE_V2_MAX_INNER_MTPT_NUM] = { 0 }; struct ib_device *ibdev = &hr_dev->ib_dev; dma_addr_t pbl_ba; @@ -2571,7 +2571,8 @@ static int set_mtpt_pbl(struct hns_roce_v2_mpt_entry *mpt_entry, return 0; } -static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, +static int hns_roce_v2_write_mtpt(struct hns_roce_dev *hr_dev, + void *mb_buf, struct hns_roce_mr *mr, unsigned long mtpt_idx) { struct hns_roce_v2_mpt_entry *mpt_entry; @@ -2620,7 +2621,7 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, if (mr->type == MR_TYPE_DMA) return 0; - ret = set_mtpt_pbl(mpt_entry, mr); + ret = set_mtpt_pbl(hr_dev, mpt_entry, mr); return ret; } @@ -2666,15 +2667,15 @@ static int hns_roce_v2_rereg_write_mtpt(struct hns_roce_dev *hr_dev, mr->iova = iova; mr->size = size; - ret = set_mtpt_pbl(mpt_entry, mr); + ret = set_mtpt_pbl(hr_dev, mpt_entry, mr); } return ret; } -static int hns_roce_v2_frmr_write_mtpt(void *mb_buf, struct hns_roce_mr *mr) +static int hns_roce_v2_frmr_write_mtpt(struct hns_roce_dev *hr_dev, + void *mb_buf, struct hns_roce_mr *mr) { - struct hns_roce_dev *hr_dev = to_hr_dev(mr->ibmr.device); struct ib_device *ibdev = &hr_dev->ib_dev; struct hns_roce_v2_mpt_entry *mpt_entry; dma_addr_t pbl_ba = 0; diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 4c0bbb12770d..0e71ebee9e52 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -180,9 +180,10 @@ static int hns_roce_mr_enable(struct hns_roce_dev *hr_dev, } if (mr->type != MR_TYPE_FRMR) - ret = hr_dev->hw->write_mtpt(mailbox->buf, mr, mtpt_idx); + ret = hr_dev->hw->write_mtpt(hr_dev, mailbox->buf, mr, + mtpt_idx); else - ret = hr_dev->hw->frmr_write_mtpt(mailbox->buf, mr); + ret = hr_dev->hw->frmr_write_mtpt(hr_dev, mailbox->buf, mr); if (ret) { dev_err(dev, "Write mtpt fail!\n"); goto err_page; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 81bf6b975e0e..f939c9b769f0 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1862,7 +1862,7 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, if (!in) return -ENOMEM; - if (MLX5_CAP_GEN(mdev, ece_support)) + if (MLX5_CAP_GEN(mdev, ece_support) && ucmd) MLX5_SET(create_qp_in, in, ece, ucmd->ece_options); qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); @@ -2341,18 +2341,18 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, unsigned long flags; int err; - if (qp->ibqp.rwq_ind_tbl) { + if (qp->is_rss) { destroy_rss_raw_qp_tir(dev, qp); return; } - base = (qp->ibqp.qp_type == IB_QPT_RAW_PACKET || + base = (qp->type == IB_QPT_RAW_PACKET || qp->flags & IB_QP_CREATE_SOURCE_QPN) ? - &qp->raw_packet_qp.rq.base : - &qp->trans_qp.base; + &qp->raw_packet_qp.rq.base : + &qp->trans_qp.base; if (qp->state != IB_QPS_RESET) { - if (qp->ibqp.qp_type != IB_QPT_RAW_PACKET && + if (qp->type != IB_QPT_RAW_PACKET && !(qp->flags & IB_QP_CREATE_SOURCE_QPN)) { err = mlx5_core_qp_modify(dev, MLX5_CMD_OP_2RST_QP, 0, NULL, &base->mqp, NULL); @@ -2368,8 +2368,8 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, base->mqp.qpn); } - get_cqs(qp->ibqp.qp_type, qp->ibqp.send_cq, qp->ibqp.recv_cq, - &send_cq, &recv_cq); + get_cqs(qp->type, qp->ibqp.send_cq, qp->ibqp.recv_cq, &send_cq, + &recv_cq); spin_lock_irqsave(&dev->reset_flow_resource_lock, flags); mlx5_ib_lock_cqs(send_cq, recv_cq); @@ -2391,7 +2391,7 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, mlx5_ib_unlock_cqs(send_cq, recv_cq); spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags); - if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET || + if (qp->type == IB_QPT_RAW_PACKET || qp->flags & IB_QP_CREATE_SOURCE_QPN) { destroy_raw_packet_qp(dev, qp); } else { @@ -2669,6 +2669,9 @@ static int process_create_flags(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, return (create_flags) ? -EINVAL : 0; process_create_flag(dev, &create_flags, + IB_QP_CREATE_INTEGRITY_EN, + MLX5_CAP_GEN(mdev, sho), qp); + process_create_flag(dev, &create_flags, IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK, MLX5_CAP_GEN(mdev, block_lb_mc), qp); process_create_flag(dev, &create_flags, IB_QP_CREATE_CROSS_CHANNEL, @@ -2873,7 +2876,6 @@ static int mlx5_ib_destroy_dct(struct mlx5_ib_qp *mqp) static int check_ucmd_data(struct mlx5_ib_dev *dev, struct mlx5_create_qp_params *params) { - struct ib_qp_init_attr *attr = params->attr; struct ib_udata *udata = params->udata; size_t size, last; int ret; @@ -2885,14 +2887,7 @@ static int check_ucmd_data(struct mlx5_ib_dev *dev, */ last = sizeof(struct mlx5_ib_create_qp_rss); else - /* IB_QPT_RAW_PACKET doesn't have ECE data */ - switch (attr->qp_type) { - case IB_QPT_RAW_PACKET: - last = offsetof(struct mlx5_ib_create_qp, ece_options); - break; - default: - last = offsetof(struct mlx5_ib_create_qp, reserved); - } + last = offsetof(struct mlx5_ib_create_qp, reserved); if (udata->inlen <= last) return 0; @@ -2907,7 +2902,7 @@ static int check_ucmd_data(struct mlx5_ib_dev *dev, if (!ret) mlx5_ib_dbg( dev, - "udata is not cleared, inlen = %lu, ucmd = %lu, last = %lu, size = %lu\n", + "udata is not cleared, inlen = %zu, ucmd = %zu, last = %zu, size = %zu\n", udata->inlen, params->ucmd_size, last, size); return ret ? 0 : -EINVAL; } @@ -3002,10 +2997,18 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attr, return &qp->ibqp; destroy_qp: - if (qp->type == MLX5_IB_QPT_DCT) + if (qp->type == MLX5_IB_QPT_DCT) { mlx5_ib_destroy_dct(qp); - else + } else { + /* + * The two lines below are temp solution till QP allocation + * will be moved to be under IB/core responsiblity. + */ + qp->ibqp.send_cq = attr->send_cq; + qp->ibqp.recv_cq = attr->recv_cq; destroy_qp_common(dev, qp, udata); + } + qp = NULL; free_qp: kfree(qp); @@ -4162,8 +4165,6 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr, if (udata->outlen < min_resp_len) return -EINVAL; - resp.response_length = min_resp_len; - /* * If we don't have enough space for the ECE options, * simply indicate it with resp.response_length. @@ -4384,8 +4385,7 @@ static void to_rdma_ah_attr(struct mlx5_ib_dev *ibdev, MLX5_GET(ads, path, src_addr_index), MLX5_GET(ads, path, hop_limit), MLX5_GET(ads, path, tclass)); - memcpy(ah_attr, MLX5_ADDR_OF(ads, path, rgid_rip), - MLX5_FLD_SZ_BYTES(ads, rgid_rip)); + rdma_ah_set_dgid_raw(ah_attr, MLX5_ADDR_OF(ads, path, rgid_rip)); } } diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c index c19d91d6dce8..7c3968ef9cd1 100644 --- a/drivers/infiniband/hw/mlx5/qpc.c +++ b/drivers/infiniband/hw/mlx5/qpc.c @@ -346,6 +346,9 @@ static int get_ece_from_mbox(void *out, u16 opcode) int ece = 0; switch (opcode) { + case MLX5_CMD_OP_INIT2INIT_QP: + ece = MLX5_GET(init2init_qp_out, out, ece); + break; case MLX5_CMD_OP_INIT2RTR_QP: ece = MLX5_GET(init2rtr_qp_out, out, ece); break; @@ -355,6 +358,9 @@ static int get_ece_from_mbox(void *out, u16 opcode) case MLX5_CMD_OP_RTS2RTS_QP: ece = MLX5_GET(rts2rts_qp_out, out, ece); break; + case MLX5_CMD_OP_RST2INIT_QP: + ece = MLX5_GET(rst2init_qp_out, out, ece); + break; default: break; } @@ -406,6 +412,7 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn, return -ENOMEM; MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn, opt_param_mask, qpc, uid); + MLX5_SET(rst2init_qp_in, mbox->in, ece, ece); break; case MLX5_CMD_OP_INIT2RTR_QP: if (MBOX_ALLOC(mbox, init2rtr_qp)) @@ -439,6 +446,7 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn, return -ENOMEM; MOD_QP_IN_SET_QPC(init2init_qp, mbox->in, opcode, qpn, opt_param_mask, qpc, uid); + MLX5_SET(init2init_qp_in, mbox->in, ece, ece); break; default: return -EINVAL; diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index 792eecd206b6..97fc7dd353b0 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -150,8 +150,17 @@ qedr_iw_issue_event(void *context, if (params->cm_info) { event.ird = params->cm_info->ird; event.ord = params->cm_info->ord; - event.private_data_len = params->cm_info->private_data_len; - event.private_data = (void *)params->cm_info->private_data; + /* Only connect_request and reply have valid private data + * the rest of the events this may be left overs from + * connection establishment. CONNECT_REQUEST is issued via + * qedr_iw_mpa_request + */ + if (event_type == IW_CM_EVENT_CONNECT_REPLY) { + event.private_data_len = + params->cm_info->private_data_len; + event.private_data = + (void *)params->cm_info->private_data; + } } if (ep->cm_id) diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 511b72809e14..7db35dd6ad74 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -1204,7 +1204,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, err = alloc_ud_wq_attr(qp, rdi->dparms.node); if (err) { ret = (ERR_PTR(err)); - goto bail_driver_priv; + goto bail_rq_rvt; } if (init_attr->create_flags & IB_QP_CREATE_NETDEV_USE) @@ -1314,9 +1314,11 @@ bail_qpn: rvt_free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num); bail_rq_wq: - rvt_free_rq(&qp->r_rq); free_ud_wq_attr(qp); +bail_rq_rvt: + rvt_free_rq(&qp->r_rq); + bail_driver_priv: rdi->driver_f.qp_priv_free(rdi, qp); diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c index 650520244ed0..7271d705f4b0 100644 --- a/drivers/infiniband/sw/siw/siw_qp_rx.c +++ b/drivers/infiniband/sw/siw/siw_qp_rx.c @@ -139,7 +139,8 @@ static int siw_rx_pbl(struct siw_rx_stream *srx, int *pbl_idx, break; bytes = min(bytes, len); - if (siw_rx_kva(srx, (void *)buf_addr, bytes) == bytes) { + if (siw_rx_kva(srx, (void *)(uintptr_t)buf_addr, bytes) == + bytes) { copied += bytes; offset += bytes; len -= bytes; diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index b510f67dfa49..6dc49ed8377a 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -211,7 +211,7 @@ config INTEL_IOMMU_DEBUGFS config INTEL_IOMMU_SVM bool "Support for Shared Virtual Memory with Intel IOMMU" - depends on INTEL_IOMMU && X86 + depends on INTEL_IOMMU && X86_64 select PCI_PASID select PCI_PRI select MMU_NOTIFIER diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index cc46dff98fa0..683b812c5c47 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -898,7 +898,8 @@ int __init detect_intel_iommu(void) if (!ret) ret = dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl, &validate_drhd_cb); - if (!ret && !no_iommu && !iommu_detected && !dmar_disabled) { + if (!ret && !no_iommu && !iommu_detected && + (!dmar_disabled || dmar_platform_optin())) { iommu_detected = 1; /* Make sure ACS will be enabled */ pci_request_acs(); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 9129663a7406..d759e7234e98 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -612,6 +612,12 @@ struct intel_iommu *domain_get_iommu(struct dmar_domain *domain) return g_iommus[iommu_id]; } +static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu) +{ + return sm_supported(iommu) ? + ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap); +} + static void domain_update_iommu_coherency(struct dmar_domain *domain) { struct dmar_drhd_unit *drhd; @@ -623,7 +629,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain) for_each_domain_iommu(i, domain) { found = true; - if (!ecap_coherent(g_iommus[i]->ecap)) { + if (!iommu_paging_structure_coherency(g_iommus[i])) { domain->iommu_coherency = 0; break; } @@ -634,7 +640,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain) /* No hardware attached; use lowest common denominator */ rcu_read_lock(); for_each_active_iommu(iommu, drhd) { - if (!ecap_coherent(iommu->ecap)) { + if (!iommu_paging_structure_coherency(iommu)) { domain->iommu_coherency = 0; break; } @@ -921,7 +927,7 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE); pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE; if (domain_use_first_level(domain)) - pteval |= DMA_FL_PTE_XD; + pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US; if (cmpxchg64(&pte->val, 0ULL, pteval)) /* Someone else set it while we were thinking; use theirs. */ free_pgtable_page(tmp_page); @@ -1951,7 +1957,6 @@ static inline void context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid) { context->hi |= pasid & ((1 << 20) - 1); - context->hi |= (1 << 20); } /* @@ -2095,7 +2100,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain, context_set_fault_enable(context); context_set_present(context); - domain_flush_cache(domain, context, sizeof(*context)); + if (!ecap_coherent(iommu->ecap)) + clflush_cache_range(context, sizeof(*context)); /* * It's a non-present to present mapping. If hardware doesn't cache @@ -2243,7 +2249,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP); if (domain_use_first_level(domain)) - attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD; + attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD | DMA_FL_PTE_US; if (!sg) { sg_res = nr_pages; @@ -2695,7 +2701,9 @@ static int __init si_domain_init(int hw) end >> agaw_to_width(si_domain->agaw))) continue; - ret = iommu_domain_identity_map(si_domain, start, end); + ret = iommu_domain_identity_map(si_domain, + mm_to_dma_pfn(start >> PAGE_SHIFT), + mm_to_dma_pfn(end >> PAGE_SHIFT)); if (ret) return ret; } @@ -6021,6 +6029,23 @@ intel_iommu_domain_set_attr(struct iommu_domain *domain, return ret; } +/* + * Check that the device does not live on an external facing PCI port that is + * marked as untrusted. Such devices should not be able to apply quirks and + * thus not be able to bypass the IOMMU restrictions. + */ +static bool risky_device(struct pci_dev *pdev) +{ + if (pdev->untrusted) { + pci_info(pdev, + "Skipping IOMMU quirk for dev [%04X:%04X] on untrusted PCI link\n", + pdev->vendor, pdev->device); + pci_info(pdev, "Please check with your BIOS/Platform vendor about this\n"); + return true; + } + return false; +} + const struct iommu_ops intel_iommu_ops = { .capable = intel_iommu_capable, .domain_alloc = intel_iommu_domain_alloc, @@ -6060,6 +6085,9 @@ const struct iommu_ops intel_iommu_ops = { static void quirk_iommu_igfx(struct pci_dev *dev) { + if (risky_device(dev)) + return; + pci_info(dev, "Disabling IOMMU for graphics on this chipset\n"); dmar_map_gfx = 0; } @@ -6101,6 +6129,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163D, quirk_iommu_igfx); static void quirk_iommu_rwbf(struct pci_dev *dev) { + if (risky_device(dev)) + return; + /* * Mobile 4 Series Chipset neglects to set RWBF capability, * but needs it. Same seems to hold for the desktop versions. @@ -6131,6 +6162,9 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev) { unsigned short ggc; + if (risky_device(dev)) + return; + if (pci_read_config_word(dev, GGC, &ggc)) return; @@ -6164,6 +6198,12 @@ static void __init check_tylersburg_isoch(void) pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3a3e, NULL); if (!pdev) return; + + if (risky_device(pdev)) { + pci_dev_put(pdev); + return; + } + pci_dev_put(pdev); /* System Management Registers. Might be hidden, in which case @@ -6173,6 +6213,11 @@ static void __init check_tylersburg_isoch(void) if (!pdev) return; + if (risky_device(pdev)) { + pci_dev_put(pdev); + return; + } + if (pci_read_config_dword(pdev, 0x188, &vtisochctrl)) { pci_dev_put(pdev); return; diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index ac83f5002ce5..489935d5f22d 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1471,7 +1471,7 @@ static void retrieve_deps(struct dm_table *table, /* * Check we have enough space. */ - needed = sizeof(*deps) + (sizeof(*deps->dev) * count); + needed = struct_size(deps, dev, count); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; return; diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 74f3c506f084..30505d70f423 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -282,6 +282,8 @@ static int persistent_memory_claim(struct dm_writecache *wc) while (daa-- && i < p) { pages[i++] = pfn_t_to_page(pfn); pfn.val++; + if (!(i & 15)) + cond_resched(); } } while (i < p); wc->memory_map = vmap(pages, p, VM_MAP, PAGE_KERNEL); @@ -849,10 +851,14 @@ static void writecache_discard(struct dm_writecache *wc, sector_t start, sector_ if (likely(!e->write_in_progress)) { if (!discarded_something) { - writecache_wait_for_ios(wc, READ); - writecache_wait_for_ios(wc, WRITE); + if (!WC_MODE_PMEM(wc)) { + writecache_wait_for_ios(wc, READ); + writecache_wait_for_ios(wc, WRITE); + } discarded_something = true; } + if (!writecache_entry_is_committed(wc, e)) + wc->uncommitted_blocks--; writecache_free_entry(wc, e); } diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 130b5a6d9f12..5cf6f5f552e0 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1078,7 +1078,8 @@ static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_sb *dsb, nr_meta_zones = (le32_to_cpu(sb->nr_meta_blocks) + zmd->zone_nr_blocks - 1) >> zmd->zone_nr_blocks_shift; if (!nr_meta_zones || - nr_meta_zones >= zmd->nr_rnd_zones) { + (zmd->nr_devs <= 1 && nr_meta_zones >= zmd->nr_rnd_zones) || + (zmd->nr_devs > 1 && nr_meta_zones >= zmd->nr_cache_zones)) { dmz_dev_err(dev, "Invalid number of metadata blocks"); return -ENXIO; } @@ -1949,7 +1950,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd, unsigned int idx, bool idle) { struct dm_zone *dzone = NULL; - struct dm_zone *zone, *last = NULL; + struct dm_zone *zone, *maxw_z = NULL; struct list_head *zone_list; /* If we have cache zones select from the cache zone list */ @@ -1961,18 +1962,37 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd, } else zone_list = &zmd->dev[idx].map_rnd_list; + /* + * Find the buffer zone with the heaviest weight or the first (oldest) + * data zone that can be reclaimed. + */ list_for_each_entry(zone, zone_list, link) { if (dmz_is_buf(zone)) { dzone = zone->bzone; - if (dzone->dev->dev_idx != idx) - continue; - if (!last) { - last = dzone; + if (dmz_is_rnd(dzone) && dzone->dev->dev_idx != idx) continue; - } - if (last->weight < dzone->weight) + if (!maxw_z || maxw_z->weight < dzone->weight) + maxw_z = dzone; + } else { + dzone = zone; + if (dmz_lock_zone_reclaim(dzone)) + return dzone; + } + } + + if (maxw_z && dmz_lock_zone_reclaim(maxw_z)) + return maxw_z; + + /* + * If we come here, none of the zones inspected could be locked for + * reclaim. Try again, being more aggressive, that is, find the + * first zone that can be reclaimed regardless of its weitght. + */ + list_for_each_entry(zone, zone_list, link) { + if (dmz_is_buf(zone)) { + dzone = zone->bzone; + if (dmz_is_rnd(dzone) && dzone->dev->dev_idx != idx) continue; - dzone = last; } else dzone = zone; if (dmz_lock_zone_reclaim(dzone)) @@ -2006,7 +2026,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd, struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd, unsigned int dev_idx, bool idle) { - struct dm_zone *zone; + struct dm_zone *zone = NULL; /* * Search for a zone candidate to reclaim: 2 cases are possible. @@ -2019,7 +2039,7 @@ struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd, dmz_lock_map(zmd); if (list_empty(&zmd->reserved_seq_zones_list)) zone = dmz_get_seq_zone_for_reclaim(zmd, dev_idx); - else + if (!zone) zone = dmz_get_rnd_zone_for_reclaim(zmd, dev_idx, idle); dmz_unlock_map(zmd); diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index 2261b4dd60b7..dd1eebf6e50f 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -377,6 +377,7 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc) dmz_metadata_label(zmd), zrc->dev_idx); return -EBUSY; } + rzone = dzone; start = jiffies; if (dmz_is_cache(dzone) || dmz_is_rnd(dzone)) { @@ -391,8 +392,6 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc) */ ret = dmz_reclaim_rnd_data(zrc, dzone); } - rzone = dzone; - } else { struct dm_zone *bzone = dzone->bzone; sector_t chunk_block = 0; @@ -415,7 +414,6 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc) * be later reclaimed. */ ret = dmz_reclaim_seq_data(zrc, dzone); - rzone = dzone; } } out: diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index a907a9446c0b..cf915009c306 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -890,7 +890,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) } /* Set target (no write same support) */ - ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata) << 9; + ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata); ti->num_flush_bios = 1; ti->num_discard_bios = 1; ti->num_write_zeroes_bios = 1; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 109e81f33edb..e6807792fec8 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1009,6 +1009,7 @@ static void clone_endio(struct bio *bio) struct dm_io *io = tio->io; struct mapped_device *md = tio->io->md; dm_endio_fn endio = tio->ti->type->end_io; + struct bio *orig_bio = io->orig_bio; if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) { if (bio_op(bio) == REQ_OP_DISCARD && @@ -1022,6 +1023,18 @@ static void clone_endio(struct bio *bio) disable_write_zeroes(md); } + /* + * For zone-append bios get offset in zone of the written + * sector and add that to the original bio sector pos. + */ + if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) { + sector_t written_sector = bio->bi_iter.bi_sector; + struct request_queue *q = orig_bio->bi_disk->queue; + u64 mask = (u64)blk_queue_zone_sectors(q) - 1; + + orig_bio->bi_iter.bi_sector += written_sector & mask; + } + if (endio) { int r = endio(tio->ti, bio, &error); switch (r) { diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c index a4ee6b86663e..b91e472ee764 100644 --- a/drivers/media/platform/omap3isp/isp.c +++ b/drivers/media/platform/omap3isp/isp.c @@ -39,8 +39,6 @@ * Troy Laramy <t-laramy@ti.com> */ -#include <asm/cacheflush.h> - #include <linux/clk.h> #include <linux/clkdev.h> #include <linux/delay.h> diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c index 10c214bd0903..1ac9aef70dff 100644 --- a/drivers/media/platform/omap3isp/ispvideo.c +++ b/drivers/media/platform/omap3isp/ispvideo.c @@ -18,7 +18,6 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/vmalloc.h> -#include <asm/cacheflush.h> #include <media/v4l2-dev.h> #include <media/v4l2-ioctl.h> diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index f82974a916c3..b0f62cbbdc87 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -62,6 +62,12 @@ static void hl_fence_release(struct dma_fence *fence) container_of(fence, struct hl_cs_compl, base_fence); struct hl_device *hdev = hl_cs_cmpl->hdev; + /* EBUSY means the CS was never submitted and hence we don't have + * an attached hw_sob object that we should handle here + */ + if (fence->error == -EBUSY) + goto free; + if ((hl_cs_cmpl->type == CS_TYPE_SIGNAL) || (hl_cs_cmpl->type == CS_TYPE_WAIT)) { @@ -92,6 +98,7 @@ static void hl_fence_release(struct dma_fence *fence) kref_put(&hl_cs_cmpl->hw_sob->kref, hl_sob_reset); } +free: kfree_rcu(hl_cs_cmpl, base_fence.rcu); } @@ -328,10 +335,16 @@ static void cs_do_release(struct kref *ref) hl_ctx_put(cs->ctx); + /* We need to mark an error for not submitted because in that case + * the dma fence release flow is different. Mainly, we don't need + * to handle hw_sob for signal/wait + */ if (cs->timedout) dma_fence_set_error(cs->fence, -ETIMEDOUT); else if (cs->aborted) dma_fence_set_error(cs->fence, -EIO); + else if (!cs->submitted) + dma_fence_set_error(cs->fence, -EBUSY); dma_fence_signal(cs->fence); dma_fence_put(cs->fence); diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c index 3c8dcdfba20c..fc4372c18ce2 100644 --- a/drivers/misc/habanalabs/debugfs.c +++ b/drivers/misc/habanalabs/debugfs.c @@ -480,7 +480,7 @@ out: return 0; } -static ssize_t mmu_write(struct file *file, const char __user *buf, +static ssize_t mmu_asid_va_write(struct file *file, const char __user *buf, size_t count, loff_t *f_pos) { struct seq_file *s = file->private_data; @@ -1125,7 +1125,7 @@ static const struct hl_info_list hl_debugfs_list[] = { {"command_submission_jobs", command_submission_jobs_show, NULL}, {"userptr", userptr_show, NULL}, {"vm", vm_show, NULL}, - {"mmu", mmu_show, mmu_write}, + {"mmu", mmu_show, mmu_asid_va_write}, {"engines", engines_show, NULL} }; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 61f88e9884ce..834470d10b46 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -96,7 +96,7 @@ #define GAUDI_NUM_OF_QM_ARB_ERR_CAUSE 3 -#define GAUDI_ARB_WDT_TIMEOUT 0x400000 +#define GAUDI_ARB_WDT_TIMEOUT 0x1000000 static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = { "gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3", @@ -1893,6 +1893,8 @@ static void gaudi_init_pci_dma_qman(struct hl_device *hdev, int dma_id, WREG32(mmDMA0_QM_CP_MSG_BASE3_ADDR_LO_0 + q_off, so_base_ws_lo); WREG32(mmDMA0_QM_CP_MSG_BASE3_ADDR_HI_0 + q_off, so_base_ws_hi); + WREG32(mmDMA0_QM_CP_BARRIER_CFG_0 + q_off, 0x100); + /* The following configuration is needed only once per QMAN */ if (qman_id == 0) { /* Configure RAZWI IRQ */ @@ -2725,6 +2727,12 @@ static int gaudi_mmu_init(struct hl_device *hdev) WREG32(mmSTLB_HOP_CONFIGURATION, hdev->mmu_huge_page_opt ? 0x30440 : 0x40440); + /* + * The H/W expects the first PI after init to be 1. After wraparound + * we'll write 0. + */ + gaudi->mmu_cache_inv_pi = 1; + gaudi->hw_cap_initialized |= HW_CAP_MMU; return 0; @@ -3790,6 +3798,25 @@ static int gaudi_validate_dma_pkt_no_mmu(struct hl_device *hdev, src_in_host); } +static int gaudi_validate_load_and_exe_pkt(struct hl_device *hdev, + struct hl_cs_parser *parser, + struct packet_load_and_exe *user_pkt) +{ + u32 cfg; + + cfg = le32_to_cpu(user_pkt->cfg); + + if (cfg & GAUDI_PKT_LOAD_AND_EXE_CFG_DST_MASK) { + dev_err(hdev->dev, + "User not allowed to use Load and Execute\n"); + return -EPERM; + } + + parser->patched_cb_size += sizeof(struct packet_load_and_exe); + + return 0; +} + static int gaudi_validate_cb(struct hl_device *hdev, struct hl_cs_parser *parser, bool is_mmu) { @@ -3838,6 +3865,11 @@ static int gaudi_validate_cb(struct hl_device *hdev, rc = -EPERM; break; + case PACKET_LOAD_AND_EXE: + rc = gaudi_validate_load_and_exe_pkt(hdev, parser, + (struct packet_load_and_exe *) user_pkt); + break; + case PACKET_LIN_DMA: parser->contains_dma_pkt = true; if (is_mmu) @@ -3855,7 +3887,6 @@ static int gaudi_validate_cb(struct hl_device *hdev, case PACKET_FENCE: case PACKET_NOP: case PACKET_ARB_POINT: - case PACKET_LOAD_AND_EXE: parser->patched_cb_size += pkt_size; break; @@ -5994,6 +6025,8 @@ static int gaudi_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard, mutex_lock(&hdev->mmu_cache_lock); /* L0 & L1 invalidation */ + WREG32(mmSTLB_INV_PS, 3); + WREG32(mmSTLB_CACHE_INV, gaudi->mmu_cache_inv_pi++); WREG32(mmSTLB_INV_PS, 2); rc = hl_poll_timeout( diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h index a46530d375fa..41a8d9bff6bf 100644 --- a/drivers/misc/habanalabs/gaudi/gaudiP.h +++ b/drivers/misc/habanalabs/gaudi/gaudiP.h @@ -229,6 +229,8 @@ struct gaudi_internal_qman_info { * @multi_msi_mode: whether we are working in multi MSI single MSI mode. * Multi MSI is possible only with IOMMU enabled. * @ext_queue_idx: helper index for external queues initialization. + * @mmu_cache_inv_pi: PI for MMU cache invalidation flow. The H/W expects an + * 8-bit value so use u8. */ struct gaudi_device { int (*armcp_info_get)(struct hl_device *hdev); @@ -248,6 +250,7 @@ struct gaudi_device { u32 hw_cap_initialized; u8 multi_msi_mode; u8 ext_queue_idx; + u8 mmu_cache_inv_pi; }; void gaudi_init_security(struct hl_device *hdev); diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_packets.h b/drivers/misc/habanalabs/include/gaudi/gaudi_packets.h index 9a5800b0086b..0f0cd067bb43 100644 --- a/drivers/misc/habanalabs/include/gaudi/gaudi_packets.h +++ b/drivers/misc/habanalabs/include/gaudi/gaudi_packets.h @@ -197,6 +197,9 @@ struct packet_wait { __le32 ctl; }; +#define GAUDI_PKT_LOAD_AND_EXE_CFG_DST_SHIFT 0 +#define GAUDI_PKT_LOAD_AND_EXE_CFG_DST_MASK 0x00000001 + struct packet_load_and_exe { __le32 cfg; __le32 ctl; diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 9392934e3a06..7becfc768bbc 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -94,6 +94,7 @@ #define MEI_DEV_ID_JSP_N 0x4DE0 /* Jasper Lake Point N */ #define MEI_DEV_ID_TGP_LP 0xA0E0 /* Tiger Lake Point LP */ +#define MEI_DEV_ID_TGP_H 0x43E0 /* Tiger Lake Point H */ #define MEI_DEV_ID_MCC 0x4B70 /* Mule Creek Canyon (EHL) */ #define MEI_DEV_ID_MCC_4 0x4B75 /* Mule Creek Canyon 4 (EHL) */ @@ -107,6 +108,8 @@ # define PCI_CFG_HFS_1_D0I3_MSK 0x80000000 #define PCI_CFG_HFS_2 0x48 #define PCI_CFG_HFS_3 0x60 +# define PCI_CFG_HFS_3_FW_SKU_MSK 0x00000070 +# define PCI_CFG_HFS_3_FW_SKU_SPS 0x00000060 #define PCI_CFG_HFS_4 0x64 #define PCI_CFG_HFS_5 0x68 #define PCI_CFG_HFS_6 0x6C diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index f620442addf5..7649710a2ab9 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1366,7 +1366,7 @@ static bool mei_me_fw_type_nm(struct pci_dev *pdev) #define MEI_CFG_FW_NM \ .quirk_probe = mei_me_fw_type_nm -static bool mei_me_fw_type_sps(struct pci_dev *pdev) +static bool mei_me_fw_type_sps_4(struct pci_dev *pdev) { u32 reg; unsigned int devfn; @@ -1382,7 +1382,36 @@ static bool mei_me_fw_type_sps(struct pci_dev *pdev) return (reg & 0xf0000) == 0xf0000; } -#define MEI_CFG_FW_SPS \ +#define MEI_CFG_FW_SPS_4 \ + .quirk_probe = mei_me_fw_type_sps_4 + +/** + * mei_me_fw_sku_sps() - check for sps sku + * + * Read ME FW Status register to check for SPS Firmware. + * The SPS FW is only signaled in pci function 0 + * + * @pdev: pci device + * + * Return: true in case of SPS firmware + */ +static bool mei_me_fw_type_sps(struct pci_dev *pdev) +{ + u32 reg; + u32 fw_type; + unsigned int devfn; + + devfn = PCI_DEVFN(PCI_SLOT(pdev->devfn), 0); + pci_bus_read_config_dword(pdev->bus, devfn, PCI_CFG_HFS_3, ®); + trace_mei_pci_cfg_read(&pdev->dev, "PCI_CFG_HFS_3", PCI_CFG_HFS_3, reg); + fw_type = (reg & PCI_CFG_HFS_3_FW_SKU_MSK); + + dev_dbg(&pdev->dev, "fw type is %d\n", fw_type); + + return fw_type == PCI_CFG_HFS_3_FW_SKU_SPS; +} + +#define MEI_CFG_FW_SPS \ .quirk_probe = mei_me_fw_type_sps #define MEI_CFG_FW_VER_SUPP \ @@ -1452,10 +1481,17 @@ static const struct mei_cfg mei_me_pch8_cfg = { }; /* PCH8 Lynx Point with quirk for SPS Firmware exclusion */ -static const struct mei_cfg mei_me_pch8_sps_cfg = { +static const struct mei_cfg mei_me_pch8_sps_4_cfg = { MEI_CFG_PCH8_HFS, MEI_CFG_FW_VER_SUPP, - MEI_CFG_FW_SPS, + MEI_CFG_FW_SPS_4, +}; + +/* LBG with quirk for SPS (4.0) Firmware exclusion */ +static const struct mei_cfg mei_me_pch12_sps_4_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, + MEI_CFG_FW_SPS_4, }; /* Cannon Lake and newer devices */ @@ -1465,10 +1501,20 @@ static const struct mei_cfg mei_me_pch12_cfg = { MEI_CFG_DMA_128, }; -/* LBG with quirk for SPS Firmware exclusion */ +/* Cannon Lake with quirk for SPS 5.0 and newer Firmware exclusion */ static const struct mei_cfg mei_me_pch12_sps_cfg = { MEI_CFG_PCH8_HFS, MEI_CFG_FW_VER_SUPP, + MEI_CFG_DMA_128, + MEI_CFG_FW_SPS, +}; + +/* Cannon Lake with quirk for SPS 5.0 and newer Firmware exclusion + * w/o DMA support + */ +static const struct mei_cfg mei_me_pch12_nodma_sps_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, MEI_CFG_FW_SPS, }; @@ -1480,6 +1526,15 @@ static const struct mei_cfg mei_me_pch15_cfg = { MEI_CFG_TRC, }; +/* Tiger Lake with quirk for SPS 5.0 and newer Firmware exclusion */ +static const struct mei_cfg mei_me_pch15_sps_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, + MEI_CFG_DMA_128, + MEI_CFG_TRC, + MEI_CFG_FW_SPS, +}; + /* * mei_cfg_list - A list of platform platform specific configurations. * Note: has to be synchronized with enum mei_cfg_idx. @@ -1492,10 +1547,13 @@ static const struct mei_cfg *const mei_cfg_list[] = { [MEI_ME_PCH7_CFG] = &mei_me_pch7_cfg, [MEI_ME_PCH_CPT_PBG_CFG] = &mei_me_pch_cpt_pbg_cfg, [MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg, - [MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg, + [MEI_ME_PCH8_SPS_4_CFG] = &mei_me_pch8_sps_4_cfg, [MEI_ME_PCH12_CFG] = &mei_me_pch12_cfg, + [MEI_ME_PCH12_SPS_4_CFG] = &mei_me_pch12_sps_4_cfg, [MEI_ME_PCH12_SPS_CFG] = &mei_me_pch12_sps_cfg, + [MEI_ME_PCH12_SPS_NODMA_CFG] = &mei_me_pch12_nodma_sps_cfg, [MEI_ME_PCH15_CFG] = &mei_me_pch15_cfg, + [MEI_ME_PCH15_SPS_CFG] = &mei_me_pch15_sps_cfg, }; const struct mei_cfg *mei_me_get_cfg(kernel_ulong_t idx) diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h index b6b94e211464..6a8973649c49 100644 --- a/drivers/misc/mei/hw-me.h +++ b/drivers/misc/mei/hw-me.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Copyright (c) 2012-2019, Intel Corporation. All rights reserved. + * Copyright (c) 2012-2020, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver */ @@ -76,14 +76,20 @@ struct mei_me_hw { * with quirk for Node Manager exclusion. * @MEI_ME_PCH8_CFG: Platform Controller Hub Gen8 and newer * client platforms. - * @MEI_ME_PCH8_SPS_CFG: Platform Controller Hub Gen8 and newer + * @MEI_ME_PCH8_SPS_4_CFG: Platform Controller Hub Gen8 and newer * servers platforms with quirk for * SPS firmware exclusion. * @MEI_ME_PCH12_CFG: Platform Controller Hub Gen12 and newer - * @MEI_ME_PCH12_SPS_CFG: Platform Controller Hub Gen12 and newer + * @MEI_ME_PCH12_SPS_4_CFG:Platform Controller Hub Gen12 up to 4.0 + * servers platforms with quirk for + * SPS firmware exclusion. + * @MEI_ME_PCH12_SPS_CFG: Platform Controller Hub Gen12 5.0 and newer * servers platforms with quirk for * SPS firmware exclusion. * @MEI_ME_PCH15_CFG: Platform Controller Hub Gen15 and newer + * @MEI_ME_PCH15_SPS_CFG: Platform Controller Hub Gen15 and newer + * servers platforms with quirk for + * SPS firmware exclusion. * @MEI_ME_NUM_CFG: Upper Sentinel. */ enum mei_cfg_idx { @@ -94,10 +100,13 @@ enum mei_cfg_idx { MEI_ME_PCH7_CFG, MEI_ME_PCH_CPT_PBG_CFG, MEI_ME_PCH8_CFG, - MEI_ME_PCH8_SPS_CFG, + MEI_ME_PCH8_SPS_4_CFG, MEI_ME_PCH12_CFG, + MEI_ME_PCH12_SPS_4_CFG, MEI_ME_PCH12_SPS_CFG, + MEI_ME_PCH12_SPS_NODMA_CFG, MEI_ME_PCH15_CFG, + MEI_ME_PCH15_SPS_CFG, MEI_ME_NUM_CFG, }; diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 71f795b510ce..2a3f2fd5df50 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -59,18 +59,18 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_1, MEI_ME_PCH7_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_2, MEI_ME_PCH7_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_3, MEI_ME_PCH7_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_H, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_W, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_H, MEI_ME_PCH8_SPS_4_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_W, MEI_ME_PCH8_SPS_4_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_LP, MEI_ME_PCH8_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_HR, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_HR, MEI_ME_PCH8_SPS_4_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_WPT_LP, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_WPT_LP_2, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, MEI_ME_PCH8_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_4_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_4_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_4_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)}, @@ -84,8 +84,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_LP, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_LP_3, MEI_ME_PCH8_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH12_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_3, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH12_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_3, MEI_ME_PCH12_SPS_NODMA_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP_3, MEI_ME_PCH8_CFG)}, @@ -96,6 +96,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_TGP_LP, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_TGP_H, MEI_ME_PCH15_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_JSP_N, MEI_ME_PCH15_CFG)}, diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 5d3c691a1c66..3dd46cd55114 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -572,6 +572,9 @@ static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf, if (data[IFLA_BAREUDP_SRCPORT_MIN]) conf->sport_min = nla_get_u16(data[IFLA_BAREUDP_SRCPORT_MIN]); + if (data[IFLA_BAREUDP_MULTIPROTO_MODE]) + conf->multi_proto_mode = true; + return 0; } diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index c7ac63f41918..946e41f020a5 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1147,6 +1147,8 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) set_bit(0, priv->cfp.used); set_bit(0, priv->cfp.unique); + /* Balance of_node_put() done by of_find_node_by_name() */ + of_node_get(dn); ports = of_find_node_by_name(dn, "ports"); if (ports) { bcm_sf2_identify_ports(priv, ports); diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c index bdfd6c4e190d..af3565160db6 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.c +++ b/drivers/net/dsa/sja1105/sja1105_vl.c @@ -7,6 +7,165 @@ #define SJA1105_SIZE_VL_STATUS 8 +/* Insert into the global gate list, sorted by gate action time. */ +static int sja1105_insert_gate_entry(struct sja1105_gating_config *gating_cfg, + struct sja1105_rule *rule, + u8 gate_state, s64 entry_time, + struct netlink_ext_ack *extack) +{ + struct sja1105_gate_entry *e; + int rc; + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) + return -ENOMEM; + + e->rule = rule; + e->gate_state = gate_state; + e->interval = entry_time; + + if (list_empty(&gating_cfg->entries)) { + list_add(&e->list, &gating_cfg->entries); + } else { + struct sja1105_gate_entry *p; + + list_for_each_entry(p, &gating_cfg->entries, list) { + if (p->interval == e->interval) { + NL_SET_ERR_MSG_MOD(extack, + "Gate conflict"); + rc = -EBUSY; + goto err; + } + + if (e->interval < p->interval) + break; + } + list_add(&e->list, p->list.prev); + } + + gating_cfg->num_entries++; + + return 0; +err: + kfree(e); + return rc; +} + +/* The gate entries contain absolute times in their e->interval field. Convert + * that to proper intervals (i.e. "0, 5, 10, 15" to "5, 5, 5, 5"). + */ +static void +sja1105_gating_cfg_time_to_interval(struct sja1105_gating_config *gating_cfg, + u64 cycle_time) +{ + struct sja1105_gate_entry *last_e; + struct sja1105_gate_entry *e; + struct list_head *prev; + + list_for_each_entry(e, &gating_cfg->entries, list) { + struct sja1105_gate_entry *p; + + prev = e->list.prev; + + if (prev == &gating_cfg->entries) + continue; + + p = list_entry(prev, struct sja1105_gate_entry, list); + p->interval = e->interval - p->interval; + } + last_e = list_last_entry(&gating_cfg->entries, + struct sja1105_gate_entry, list); + last_e->interval = cycle_time - last_e->interval; +} + +static void sja1105_free_gating_config(struct sja1105_gating_config *gating_cfg) +{ + struct sja1105_gate_entry *e, *n; + + list_for_each_entry_safe(e, n, &gating_cfg->entries, list) { + list_del(&e->list); + kfree(e); + } +} + +static int sja1105_compose_gating_subschedule(struct sja1105_private *priv, + struct netlink_ext_ack *extack) +{ + struct sja1105_gating_config *gating_cfg = &priv->tas_data.gating_cfg; + struct sja1105_rule *rule; + s64 max_cycle_time = 0; + s64 its_base_time = 0; + int i, rc = 0; + + sja1105_free_gating_config(gating_cfg); + + list_for_each_entry(rule, &priv->flow_block.rules, list) { + if (rule->type != SJA1105_RULE_VL) + continue; + if (rule->vl.type != SJA1105_VL_TIME_TRIGGERED) + continue; + + if (max_cycle_time < rule->vl.cycle_time) { + max_cycle_time = rule->vl.cycle_time; + its_base_time = rule->vl.base_time; + } + } + + if (!max_cycle_time) + return 0; + + dev_dbg(priv->ds->dev, "max_cycle_time %lld its_base_time %lld\n", + max_cycle_time, its_base_time); + + gating_cfg->base_time = its_base_time; + gating_cfg->cycle_time = max_cycle_time; + gating_cfg->num_entries = 0; + + list_for_each_entry(rule, &priv->flow_block.rules, list) { + s64 time; + s64 rbt; + + if (rule->type != SJA1105_RULE_VL) + continue; + if (rule->vl.type != SJA1105_VL_TIME_TRIGGERED) + continue; + + /* Calculate the difference between this gating schedule's + * base time, and the base time of the gating schedule with the + * longest cycle time. We call it the relative base time (rbt). + */ + rbt = future_base_time(rule->vl.base_time, rule->vl.cycle_time, + its_base_time); + rbt -= its_base_time; + + time = rbt; + + for (i = 0; i < rule->vl.num_entries; i++) { + u8 gate_state = rule->vl.entries[i].gate_state; + s64 entry_time = time; + + while (entry_time < max_cycle_time) { + rc = sja1105_insert_gate_entry(gating_cfg, rule, + gate_state, + entry_time, + extack); + if (rc) + goto err; + + entry_time += rule->vl.cycle_time; + } + time += rule->vl.entries[i].interval; + } + } + + sja1105_gating_cfg_time_to_interval(gating_cfg, max_cycle_time); + + return 0; +err: + sja1105_free_gating_config(gating_cfg); + return rc; +} + /* The switch flow classification core implements TTEthernet, which 'thinks' in * terms of Virtual Links (VL), a concept borrowed from ARINC 664 part 7. * However it also has one other operating mode (VLLUPFORMAT=0) where it acts @@ -342,7 +501,9 @@ int sja1105_vl_redirect(struct sja1105_private *priv, int port, NL_SET_ERR_MSG_MOD(extack, "Can only redirect based on DMAC"); return -EOPNOTSUPP; - } else if (key->type != SJA1105_KEY_VLAN_AWARE_VL) { + } else if ((priv->vlan_state == SJA1105_VLAN_BEST_EFFORT || + priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) && + key->type != SJA1105_KEY_VLAN_AWARE_VL) { NL_SET_ERR_MSG_MOD(extack, "Can only redirect based on {DMAC, VID, PCP}"); return -EOPNOTSUPP; @@ -388,171 +549,19 @@ int sja1105_vl_delete(struct sja1105_private *priv, int port, kfree(rule); } - rc = sja1105_init_virtual_links(priv, extack); + rc = sja1105_compose_gating_subschedule(priv, extack); if (rc) return rc; - return sja1105_static_config_reload(priv, SJA1105_VIRTUAL_LINKS); -} - -/* Insert into the global gate list, sorted by gate action time. */ -static int sja1105_insert_gate_entry(struct sja1105_gating_config *gating_cfg, - struct sja1105_rule *rule, - u8 gate_state, s64 entry_time, - struct netlink_ext_ack *extack) -{ - struct sja1105_gate_entry *e; - int rc; - - e = kzalloc(sizeof(*e), GFP_KERNEL); - if (!e) - return -ENOMEM; - - e->rule = rule; - e->gate_state = gate_state; - e->interval = entry_time; - - if (list_empty(&gating_cfg->entries)) { - list_add(&e->list, &gating_cfg->entries); - } else { - struct sja1105_gate_entry *p; - - list_for_each_entry(p, &gating_cfg->entries, list) { - if (p->interval == e->interval) { - NL_SET_ERR_MSG_MOD(extack, - "Gate conflict"); - rc = -EBUSY; - goto err; - } - - if (e->interval < p->interval) - break; - } - list_add(&e->list, p->list.prev); - } - - gating_cfg->num_entries++; - - return 0; -err: - kfree(e); - return rc; -} - -/* The gate entries contain absolute times in their e->interval field. Convert - * that to proper intervals (i.e. "0, 5, 10, 15" to "5, 5, 5, 5"). - */ -static void -sja1105_gating_cfg_time_to_interval(struct sja1105_gating_config *gating_cfg, - u64 cycle_time) -{ - struct sja1105_gate_entry *last_e; - struct sja1105_gate_entry *e; - struct list_head *prev; - - list_for_each_entry(e, &gating_cfg->entries, list) { - struct sja1105_gate_entry *p; - - prev = e->list.prev; - - if (prev == &gating_cfg->entries) - continue; - - p = list_entry(prev, struct sja1105_gate_entry, list); - p->interval = e->interval - p->interval; - } - last_e = list_last_entry(&gating_cfg->entries, - struct sja1105_gate_entry, list); - if (last_e->list.prev != &gating_cfg->entries) - last_e->interval = cycle_time - last_e->interval; -} - -static void sja1105_free_gating_config(struct sja1105_gating_config *gating_cfg) -{ - struct sja1105_gate_entry *e, *n; - - list_for_each_entry_safe(e, n, &gating_cfg->entries, list) { - list_del(&e->list); - kfree(e); - } -} - -static int sja1105_compose_gating_subschedule(struct sja1105_private *priv, - struct netlink_ext_ack *extack) -{ - struct sja1105_gating_config *gating_cfg = &priv->tas_data.gating_cfg; - struct sja1105_rule *rule; - s64 max_cycle_time = 0; - s64 its_base_time = 0; - int i, rc = 0; - - list_for_each_entry(rule, &priv->flow_block.rules, list) { - if (rule->type != SJA1105_RULE_VL) - continue; - if (rule->vl.type != SJA1105_VL_TIME_TRIGGERED) - continue; - - if (max_cycle_time < rule->vl.cycle_time) { - max_cycle_time = rule->vl.cycle_time; - its_base_time = rule->vl.base_time; - } - } - - if (!max_cycle_time) - return 0; - - dev_dbg(priv->ds->dev, "max_cycle_time %lld its_base_time %lld\n", - max_cycle_time, its_base_time); - - sja1105_free_gating_config(gating_cfg); - - gating_cfg->base_time = its_base_time; - gating_cfg->cycle_time = max_cycle_time; - gating_cfg->num_entries = 0; - - list_for_each_entry(rule, &priv->flow_block.rules, list) { - s64 time; - s64 rbt; - - if (rule->type != SJA1105_RULE_VL) - continue; - if (rule->vl.type != SJA1105_VL_TIME_TRIGGERED) - continue; - - /* Calculate the difference between this gating schedule's - * base time, and the base time of the gating schedule with the - * longest cycle time. We call it the relative base time (rbt). - */ - rbt = future_base_time(rule->vl.base_time, rule->vl.cycle_time, - its_base_time); - rbt -= its_base_time; - - time = rbt; - - for (i = 0; i < rule->vl.num_entries; i++) { - u8 gate_state = rule->vl.entries[i].gate_state; - s64 entry_time = time; - - while (entry_time < max_cycle_time) { - rc = sja1105_insert_gate_entry(gating_cfg, rule, - gate_state, - entry_time, - extack); - if (rc) - goto err; - - entry_time += rule->vl.cycle_time; - } - time += rule->vl.entries[i].interval; - } - } + rc = sja1105_init_virtual_links(priv, extack); + if (rc) + return rc; - sja1105_gating_cfg_time_to_interval(gating_cfg, max_cycle_time); + rc = sja1105_init_scheduling(priv); + if (rc < 0) + return rc; - return 0; -err: - sja1105_free_gating_config(gating_cfg); - return rc; + return sja1105_static_config_reload(priv, SJA1105_VIRTUAL_LINKS); } int sja1105_vl_gate(struct sja1105_private *priv, int port, @@ -588,14 +597,12 @@ int sja1105_vl_gate(struct sja1105_private *priv, int port, if (priv->vlan_state == SJA1105_VLAN_UNAWARE && key->type != SJA1105_KEY_VLAN_UNAWARE_VL) { - dev_err(priv->ds->dev, "1: vlan state %d key type %d\n", - priv->vlan_state, key->type); NL_SET_ERR_MSG_MOD(extack, "Can only gate based on DMAC"); return -EOPNOTSUPP; - } else if (key->type != SJA1105_KEY_VLAN_AWARE_VL) { - dev_err(priv->ds->dev, "2: vlan state %d key type %d\n", - priv->vlan_state, key->type); + } else if ((priv->vlan_state == SJA1105_VLAN_BEST_EFFORT || + priv->vlan_state == SJA1105_VLAN_FILTERING_FULL) && + key->type != SJA1105_KEY_VLAN_AWARE_VL) { NL_SET_ERR_MSG_MOD(extack, "Can only gate based on {DMAC, VID, PCP}"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b93e05f91d77..6a884df44612 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6292,6 +6292,7 @@ int bnxt_hwrm_set_coal(struct bnxt *bp) static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp) { + struct hwrm_stat_ctx_clr_stats_input req0 = {0}; struct hwrm_stat_ctx_free_input req = {0}; int i; @@ -6301,6 +6302,7 @@ static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp) if (BNXT_CHIP_TYPE_NITRO_A0(bp)) return; + bnxt_hwrm_cmd_hdr_init(bp, &req0, HWRM_STAT_CTX_CLR_STATS, -1, -1); bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_FREE, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); @@ -6310,7 +6312,11 @@ static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp) if (cpr->hw_stats_ctx_id != INVALID_STATS_CTX_ID) { req.stat_ctx_id = cpu_to_le32(cpr->hw_stats_ctx_id); - + if (BNXT_FW_MAJ(bp) <= 20) { + req0.stat_ctx_id = req.stat_ctx_id; + _hwrm_send_message(bp, &req0, sizeof(req0), + HWRM_CMD_TIMEOUT); + } _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -6976,7 +6982,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->fw_cap |= BNXT_FW_CAP_ERR_RECOVER_RELOAD; bp->tx_push_thresh = 0; - if (flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) + if ((flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) && + BNXT_FW_MAJ(bp) > 217) bp->tx_push_thresh = BNXT_TX_PUSH_THRESH; hw_resc->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx); @@ -7240,8 +7247,9 @@ static int __bnxt_hwrm_ver_get(struct bnxt *bp, bool silent) static int bnxt_hwrm_ver_get(struct bnxt *bp) { struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr; + u16 fw_maj, fw_min, fw_bld, fw_rsv; u32 dev_caps_cfg, hwrm_ver; - int rc; + int rc, len; bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN; mutex_lock(&bp->hwrm_cmd_lock); @@ -7273,9 +7281,22 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp) resp->hwrm_intf_maj_8b, resp->hwrm_intf_min_8b, resp->hwrm_intf_upd_8b); - snprintf(bp->fw_ver_str, BC_HWRM_STR_LEN, "%d.%d.%d.%d", - resp->hwrm_fw_maj_8b, resp->hwrm_fw_min_8b, - resp->hwrm_fw_bld_8b, resp->hwrm_fw_rsvd_8b); + fw_maj = le16_to_cpu(resp->hwrm_fw_major); + if (bp->hwrm_spec_code > 0x10803 && fw_maj) { + fw_min = le16_to_cpu(resp->hwrm_fw_minor); + fw_bld = le16_to_cpu(resp->hwrm_fw_build); + fw_rsv = le16_to_cpu(resp->hwrm_fw_patch); + len = FW_VER_STR_LEN; + } else { + fw_maj = resp->hwrm_fw_maj_8b; + fw_min = resp->hwrm_fw_min_8b; + fw_bld = resp->hwrm_fw_bld_8b; + fw_rsv = resp->hwrm_fw_rsvd_8b; + len = BC_HWRM_STR_LEN; + } + bp->fw_ver_code = BNXT_FW_VER_CODE(fw_maj, fw_min, fw_bld, fw_rsv); + snprintf(bp->fw_ver_str, len, "%d.%d.%d.%d", fw_maj, fw_min, fw_bld, + fw_rsv); if (strlen(resp->active_pkg_name)) { int fw_ver_len = strlen(bp->fw_ver_str); @@ -11892,7 +11913,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->ethtool_ops = &bnxt_ethtool_ops; pci_set_drvdata(pdev, dev); - bnxt_vpd_read_info(bp); + if (BNXT_PF(bp)) + bnxt_vpd_read_info(bp); rc = bnxt_alloc_hwrm_resources(bp); if (rc) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 9e173d74b72a..78e2fd63ac3d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1746,6 +1746,11 @@ struct bnxt { #define PHY_VER_STR_LEN (FW_VER_STR_LEN - BC_HWRM_STR_LEN) char fw_ver_str[FW_VER_STR_LEN]; char hwrm_ver_supp[FW_VER_STR_LEN]; + u64 fw_ver_code; +#define BNXT_FW_VER_CODE(maj, min, bld, rsv) \ + ((u64)(maj) << 48 | (u64)(min) << 32 | (u64)(bld) << 16 | (rsv)) +#define BNXT_FW_MAJ(bp) ((bp)->fw_ver_code >> 48) + __be16 vxlan_port; u8 vxlan_port_cnt; __le16 vxlan_fw_dst_port_id; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 0eef4f5e4a46..4a11c1e7cc02 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1889,7 +1889,8 @@ static void bnxt_tc_setup_indr_rel(void *cb_priv) } static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp, - struct flow_block_offload *f) + struct flow_block_offload *f, void *data, + void (*cleanup)(struct flow_block_cb *block_cb)) { struct bnxt_flower_indr_block_cb_priv *cb_priv; struct flow_block_cb *block_cb; @@ -1907,9 +1908,10 @@ static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp, cb_priv->bp = bp; list_add(&cb_priv->list, &bp->tc_indr_block_list); - block_cb = flow_block_cb_alloc(bnxt_tc_setup_indr_block_cb, - cb_priv, cb_priv, - bnxt_tc_setup_indr_rel); + block_cb = flow_indr_block_cb_alloc(bnxt_tc_setup_indr_block_cb, + cb_priv, cb_priv, + bnxt_tc_setup_indr_rel, f, + netdev, data, bp, cleanup); if (IS_ERR(block_cb)) { list_del(&cb_priv->list); kfree(cb_priv); @@ -1930,7 +1932,7 @@ static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp, if (!block_cb) return -ENOENT; - flow_block_cb_remove(block_cb, f); + flow_indr_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); break; default: @@ -1945,14 +1947,17 @@ static bool bnxt_is_netdev_indr_offload(struct net_device *netdev) } static int bnxt_tc_setup_indr_cb(struct net_device *netdev, void *cb_priv, - enum tc_setup_type type, void *type_data) + enum tc_setup_type type, void *type_data, + void *data, + void (*cleanup)(struct flow_block_cb *block_cb)) { if (!bnxt_is_netdev_indr_offload(netdev)) return -EOPNOTSUPP; switch (type) { case TC_SETUP_BLOCK: - return bnxt_tc_setup_indr_block(netdev, cb_priv, type_data); + return bnxt_tc_setup_indr_block(netdev, cb_priv, type_data, data, + cleanup); default: break; } @@ -2074,7 +2079,7 @@ void bnxt_shutdown_tc(struct bnxt *bp) return; flow_indr_dev_unregister(bnxt_tc_setup_indr_cb, bp, - bnxt_tc_setup_indr_block_cb); + bnxt_tc_setup_indr_rel); rhashtable_destroy(&tc_info->flow_table); rhashtable_destroy(&tc_info->l2_table); rhashtable_destroy(&tc_info->decap_l2_table); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index ff31da0ed846..af924a8b885f 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -459,17 +459,6 @@ static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv, genet_dma_ring_regs[r]); } -static bool bcmgenet_hfb_is_filter_enabled(struct bcmgenet_priv *priv, - u32 f_index) -{ - u32 offset; - u32 reg; - - offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32); - reg = bcmgenet_hfb_reg_readl(priv, offset); - return !!(reg & (1 << (f_index % 32))); -} - static void bcmgenet_hfb_enable_filter(struct bcmgenet_priv *priv, u32 f_index) { u32 offset; @@ -533,19 +522,6 @@ static void bcmgenet_hfb_set_filter_length(struct bcmgenet_priv *priv, bcmgenet_hfb_reg_writel(priv, reg, offset); } -static int bcmgenet_hfb_find_unused_filter(struct bcmgenet_priv *priv) -{ - u32 f_index; - - /* First MAX_NUM_OF_FS_RULES are reserved for Rx NFC filters */ - for (f_index = MAX_NUM_OF_FS_RULES; - f_index < priv->hw_params->hfb_filter_cnt; f_index++) - if (!bcmgenet_hfb_is_filter_enabled(priv, f_index)) - return f_index; - - return -ENOMEM; -} - static int bcmgenet_hfb_validate_mask(void *mask, size_t size) { while (size) { @@ -634,8 +610,9 @@ static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv, { struct ethtool_rx_flow_spec *fs = &rule->fs; int err = 0, offset = 0, f_length = 0; - u16 val_16, mask_16; u8 val_8, mask_8; + __be16 val_16; + u16 mask_16; size_t size; u32 *f_data; @@ -744,59 +721,6 @@ static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv, return err; } -/* bcmgenet_hfb_add_filter - * - * Add new filter to Hardware Filter Block to match and direct Rx traffic to - * desired Rx queue. - * - * f_data is an array of unsigned 32-bit integers where each 32-bit integer - * provides filter data for 2 bytes (4 nibbles) of Rx frame: - * - * bits 31:20 - unused - * bit 19 - nibble 0 match enable - * bit 18 - nibble 1 match enable - * bit 17 - nibble 2 match enable - * bit 16 - nibble 3 match enable - * bits 15:12 - nibble 0 data - * bits 11:8 - nibble 1 data - * bits 7:4 - nibble 2 data - * bits 3:0 - nibble 3 data - * - * Example: - * In order to match: - * - Ethernet frame type = 0x0800 (IP) - * - IP version field = 4 - * - IP protocol field = 0x11 (UDP) - * - * The following filter is needed: - * u32 hfb_filter_ipv4_udp[] = { - * Rx frame offset 0x00: 0x00000000, 0x00000000, 0x00000000, 0x00000000, - * Rx frame offset 0x08: 0x00000000, 0x00000000, 0x000F0800, 0x00084000, - * Rx frame offset 0x10: 0x00000000, 0x00000000, 0x00000000, 0x00030011, - * }; - * - * To add the filter to HFB and direct the traffic to Rx queue 0, call: - * bcmgenet_hfb_add_filter(priv, hfb_filter_ipv4_udp, - * ARRAY_SIZE(hfb_filter_ipv4_udp), 0); - */ -int bcmgenet_hfb_add_filter(struct bcmgenet_priv *priv, u32 *f_data, - u32 f_length, u32 rx_queue) -{ - int f_index; - - f_index = bcmgenet_hfb_find_unused_filter(priv); - if (f_index < 0) - return -ENOMEM; - - if (f_length > priv->hw_params->hfb_filter_size) - return -EINVAL; - - bcmgenet_hfb_set_filter(priv, f_data, f_length, rx_queue, f_index); - bcmgenet_hfb_enable_filter(priv, f_index); - - return 0; -} - /* bcmgenet_hfb_clear * * Clear Hardware Filter Block and disable all filtering. @@ -2118,11 +2042,6 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) goto out; } - if (skb_padto(skb, ETH_ZLEN)) { - ret = NETDEV_TX_OK; - goto out; - } - /* Retain how many bytes will be sent on the wire, without TSB inserted * by transmit checksum offload */ @@ -2169,6 +2088,9 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) len_stat = (size << DMA_BUFLENGTH_SHIFT) | (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT); + /* Note: if we ever change from DMA_TX_APPEND_CRC below we + * will need to restore software padding of "runt" packets + */ if (!i) { len_stat |= DMA_TX_APPEND_CRC | DMA_SOP; if (skb->ip_summed == CHECKSUM_PARTIAL) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 7a3b22b35238..ebff1fc0d8ce 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -18168,8 +18168,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, rtnl_lock(); - /* We probably don't have netdev yet */ - if (!netdev || !netif_running(netdev)) + /* Could be second call or maybe we don't have netdev yet */ + if (!netdev || tp->pcierr_recovery || !netif_running(netdev)) goto done; /* We needn't recover from permanent error */ diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 67933079aeea..52582e8ed90e 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2558,7 +2558,7 @@ static int macb_open(struct net_device *dev) err = macb_phylink_connect(bp); if (err) - goto napi_exit; + goto reset_hw; netif_tx_start_all_queues(dev); @@ -2567,9 +2567,11 @@ static int macb_open(struct net_device *dev) return 0; -napi_exit: +reset_hw: + macb_reset_hw(bp); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) napi_disable(&queue->napi); + macb_free_consistent(bp); pm_exit: pm_runtime_put_sync(&bp->pdev->dev); return err; @@ -3760,15 +3762,9 @@ static int macb_init(struct platform_device *pdev) static struct sifive_fu540_macb_mgmt *mgmt; -/* Initialize and start the Receiver and Transmit subsystems */ -static int at91ether_start(struct net_device *dev) +static int at91ether_alloc_coherent(struct macb *lp) { - struct macb *lp = netdev_priv(dev); struct macb_queue *q = &lp->queues[0]; - struct macb_dma_desc *desc; - dma_addr_t addr; - u32 ctl; - int i; q->rx_ring = dma_alloc_coherent(&lp->pdev->dev, (AT91ETHER_MAX_RX_DESCR * @@ -3790,6 +3786,43 @@ static int at91ether_start(struct net_device *dev) return -ENOMEM; } + return 0; +} + +static void at91ether_free_coherent(struct macb *lp) +{ + struct macb_queue *q = &lp->queues[0]; + + if (q->rx_ring) { + dma_free_coherent(&lp->pdev->dev, + AT91ETHER_MAX_RX_DESCR * + macb_dma_desc_get_size(lp), + q->rx_ring, q->rx_ring_dma); + q->rx_ring = NULL; + } + + if (q->rx_buffers) { + dma_free_coherent(&lp->pdev->dev, + AT91ETHER_MAX_RX_DESCR * + AT91ETHER_MAX_RBUFF_SZ, + q->rx_buffers, q->rx_buffers_dma); + q->rx_buffers = NULL; + } +} + +/* Initialize and start the Receiver and Transmit subsystems */ +static int at91ether_start(struct macb *lp) +{ + struct macb_queue *q = &lp->queues[0]; + struct macb_dma_desc *desc; + dma_addr_t addr; + u32 ctl; + int i, ret; + + ret = at91ether_alloc_coherent(lp); + if (ret) + return ret; + addr = q->rx_buffers_dma; for (i = 0; i < AT91ETHER_MAX_RX_DESCR; i++) { desc = macb_rx_desc(q, i); @@ -3811,9 +3844,39 @@ static int at91ether_start(struct net_device *dev) ctl = macb_readl(lp, NCR); macb_writel(lp, NCR, ctl | MACB_BIT(RE) | MACB_BIT(TE)); + /* Enable MAC interrupts */ + macb_writel(lp, IER, MACB_BIT(RCOMP) | + MACB_BIT(RXUBR) | + MACB_BIT(ISR_TUND) | + MACB_BIT(ISR_RLE) | + MACB_BIT(TCOMP) | + MACB_BIT(ISR_ROVR) | + MACB_BIT(HRESP)); + return 0; } +static void at91ether_stop(struct macb *lp) +{ + u32 ctl; + + /* Disable MAC interrupts */ + macb_writel(lp, IDR, MACB_BIT(RCOMP) | + MACB_BIT(RXUBR) | + MACB_BIT(ISR_TUND) | + MACB_BIT(ISR_RLE) | + MACB_BIT(TCOMP) | + MACB_BIT(ISR_ROVR) | + MACB_BIT(HRESP)); + + /* Disable Receiver and Transmitter */ + ctl = macb_readl(lp, NCR); + macb_writel(lp, NCR, ctl & ~(MACB_BIT(TE) | MACB_BIT(RE))); + + /* Free resources. */ + at91ether_free_coherent(lp); +} + /* Open the ethernet interface */ static int at91ether_open(struct net_device *dev) { @@ -3833,63 +3896,36 @@ static int at91ether_open(struct net_device *dev) macb_set_hwaddr(lp); - ret = at91ether_start(dev); + ret = at91ether_start(lp); if (ret) - return ret; - - /* Enable MAC interrupts */ - macb_writel(lp, IER, MACB_BIT(RCOMP) | - MACB_BIT(RXUBR) | - MACB_BIT(ISR_TUND) | - MACB_BIT(ISR_RLE) | - MACB_BIT(TCOMP) | - MACB_BIT(ISR_ROVR) | - MACB_BIT(HRESP)); + goto pm_exit; ret = macb_phylink_connect(lp); if (ret) - return ret; + goto stop; netif_start_queue(dev); return 0; + +stop: + at91ether_stop(lp); +pm_exit: + pm_runtime_put_sync(&lp->pdev->dev); + return ret; } /* Close the interface */ static int at91ether_close(struct net_device *dev) { struct macb *lp = netdev_priv(dev); - struct macb_queue *q = &lp->queues[0]; - u32 ctl; - - /* Disable Receiver and Transmitter */ - ctl = macb_readl(lp, NCR); - macb_writel(lp, NCR, ctl & ~(MACB_BIT(TE) | MACB_BIT(RE))); - - /* Disable MAC interrupts */ - macb_writel(lp, IDR, MACB_BIT(RCOMP) | - MACB_BIT(RXUBR) | - MACB_BIT(ISR_TUND) | - MACB_BIT(ISR_RLE) | - MACB_BIT(TCOMP) | - MACB_BIT(ISR_ROVR) | - MACB_BIT(HRESP)); netif_stop_queue(dev); phylink_stop(lp->phylink); phylink_disconnect_phy(lp->phylink); - dma_free_coherent(&lp->pdev->dev, - AT91ETHER_MAX_RX_DESCR * - macb_dma_desc_get_size(lp), - q->rx_ring, q->rx_ring_dma); - q->rx_ring = NULL; - - dma_free_coherent(&lp->pdev->dev, - AT91ETHER_MAX_RX_DESCR * AT91ETHER_MAX_RBUFF_SZ, - q->rx_buffers, q->rx_buffers_dma); - q->rx_buffers = NULL; + at91ether_stop(lp); return pm_runtime_put(&lp->pdev->dev); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 7b9cd69f9844..d8ab8e366818 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -1975,7 +1975,6 @@ int cudbg_collect_dump_context(struct cudbg_init *pdbg_init, u8 mem_type[CTXT_INGRESS + 1] = { 0 }; struct cudbg_buffer temp_buff = { 0 }; struct cudbg_ch_cntxt *buff; - u64 *dst_off, *src_off; u8 *ctx_buf; u8 i, k; int rc; @@ -2044,8 +2043,11 @@ int cudbg_collect_dump_context(struct cudbg_init *pdbg_init, } for (j = 0; j < max_ctx_qid; j++) { + __be64 *dst_off; + u64 *src_off; + src_off = (u64 *)(ctx_buf + j * SGE_CTXT_SIZE); - dst_off = (u64 *)buff->data; + dst_off = (__be64 *)buff->data; /* The data is stored in 64-bit cpu order. Convert it * to big endian before parsing. diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h index d3c654b9989b..80c6627fe981 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h @@ -136,6 +136,9 @@ static inline __u8 bitswap_1(unsigned char val) ((val & 0x02) << 5) | ((val & 0x01) << 7); } + +extern const char * const dcb_ver_array[]; + #define CXGB4_DCB_ENABLED true #else /* !CONFIG_CHELSIO_T4_DCB */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 828499256004..b477b8842905 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -2379,7 +2379,6 @@ static const struct file_operations rss_vf_config_debugfs_fops = { }; #ifdef CONFIG_CHELSIO_T4_DCB -extern char *dcb_ver_array[]; /* Data Center Briging information for each port. */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 9fd496732b2c..f27be1132d37 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -588,7 +588,7 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, /** * lmm_to_fw_caps - translate ethtool Link Mode Mask to Firmware * capabilities - * @et_lmm: ethtool Link Mode Mask + * @link_mode_mask: ethtool Link Mode Mask * * Translate ethtool Link Mode Mask into a Firmware Port capabilities * value. diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 796555255207..7a7f61a8cdf4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -165,6 +165,9 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f, unsigned int tid, bool dip, bool sip, bool dp, bool sp) { + u8 *nat_lp = (u8 *)&f->fs.nat_lport; + u8 *nat_fp = (u8 *)&f->fs.nat_fport; + if (dip) { if (f->fs.type) { set_tcb_field(adap, f, tid, TCB_SND_UNA_RAW_W, @@ -236,8 +239,9 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f, } set_tcb_field(adap, f, tid, TCB_PDU_HDR_LEN_W, WORD_MASK, - (dp ? f->fs.nat_lport : 0) | - (sp ? f->fs.nat_fport << 16 : 0), 1); + (dp ? (nat_lp[1] | nat_lp[0] << 8) : 0) | + (sp ? (nat_fp[1] << 16 | nat_fp[0] << 24) : 0), + 1); } /* Validate filter spec against configuration done on the card. */ @@ -909,6 +913,9 @@ int set_filter_wr(struct adapter *adapter, int fidx) fwr->fpm = htons(f->fs.mask.fport); if (adapter->params.filter2_wr_support) { + u8 *nat_lp = (u8 *)&f->fs.nat_lport; + u8 *nat_fp = (u8 *)&f->fs.nat_fport; + fwr->natmode_to_ulp_type = FW_FILTER2_WR_ULP_TYPE_V(f->fs.nat_mode ? ULP_MODE_TCPDDP : @@ -916,8 +923,8 @@ int set_filter_wr(struct adapter *adapter, int fidx) FW_FILTER2_WR_NATMODE_V(f->fs.nat_mode); memcpy(fwr->newlip, f->fs.nat_lip, sizeof(fwr->newlip)); memcpy(fwr->newfip, f->fs.nat_fip, sizeof(fwr->newfip)); - fwr->newlport = htons(f->fs.nat_lport); - fwr->newfport = htons(f->fs.nat_fport); + fwr->newlport = htons(nat_lp[1] | nat_lp[0] << 8); + fwr->newfport = htons(nat_fp[1] | nat_fp[0] << 8); } /* Mark the filter as "pending" and ship off the Filter Work Request. @@ -1105,16 +1112,16 @@ static bool is_addr_all_mask(u8 *ipmask, int family) struct in_addr *addr; addr = (struct in_addr *)ipmask; - if (addr->s_addr == 0xffffffff) + if (ntohl(addr->s_addr) == 0xffffffff) return true; } else if (family == AF_INET6) { struct in6_addr *addr6; addr6 = (struct in6_addr *)ipmask; - if (addr6->s6_addr32[0] == 0xffffffff && - addr6->s6_addr32[1] == 0xffffffff && - addr6->s6_addr32[2] == 0xffffffff && - addr6->s6_addr32[3] == 0xffffffff) + if (ntohl(addr6->s6_addr32[0]) == 0xffffffff && + ntohl(addr6->s6_addr32[1]) == 0xffffffff && + ntohl(addr6->s6_addr32[2]) == 0xffffffff && + ntohl(addr6->s6_addr32[3]) == 0xffffffff) return true; } return false; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 854b1717a70d..0329a6b52087 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -449,7 +449,7 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok) * or -1 * @addr: the new MAC address value * @persist: whether a new MAC allocation should be persistent - * @add_smt: if true also add the address to the HW SMT + * @smt_idx: the destination to store the new SMT index. * * Modifies an MPS filter and sets it to the new MAC address if * @tcam_idx >= 0, or adds the MAC address to a new filter if @@ -1615,6 +1615,7 @@ static int tid_init(struct tid_info *t) * @stid: the server TID * @sip: local IP address to bind server to * @sport: the server's TCP port + * @vlan: the VLAN header information * @queue: queue to direct messages from this server to * * Create an IP server for the given port and address. @@ -2609,7 +2610,7 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid, /* Clear out filter specifications */ memset(&f->fs, 0, sizeof(struct ch_filter_specification)); - f->fs.val.lport = cpu_to_be16(sport); + f->fs.val.lport = be16_to_cpu(sport); f->fs.mask.lport = ~0; val = (u8 *)&sip; if ((val[0] | val[1] | val[2] | val[3]) != 0) { @@ -5377,10 +5378,10 @@ static inline bool is_x_10g_port(const struct link_config *lc) static int cfg_queues(struct adapter *adap) { u32 avail_qsets, avail_eth_qsets, avail_uld_qsets; - u32 i, n10g = 0, qidx = 0, n1g = 0; u32 ncpus = num_online_cpus(); u32 niqflint, neq, num_ulds; struct sge *s = &adap->sge; + u32 i, n10g = 0, qidx = 0; u32 q10g = 0, q1g; /* Reduce memory usage in kdump environment, disable all offload. */ @@ -5426,7 +5427,6 @@ static int cfg_queues(struct adapter *adap) if (n10g) q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g; - n1g = adap->params.nports - n10g; #ifdef CONFIG_CHELSIO_T4_DCB /* For Data Center Bridging support we need to be able to support up * to 8 Traffic Priorities; each of which will be assigned to its @@ -5444,7 +5444,8 @@ static int cfg_queues(struct adapter *adap) else q10g = max(8U, q10g); - while ((q10g * n10g) > (avail_eth_qsets - n1g * q1g)) + while ((q10g * n10g) > + (avail_eth_qsets - (adap->params.nports - n10g) * q1g)) q10g--; #else /* !CONFIG_CHELSIO_T4_DCB */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c index f5bc996ac77d..70dbee89118e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c @@ -194,6 +194,7 @@ int cxgb4_ptp_redirect_rx_packet(struct adapter *adapter, struct port_info *pi) } /** + * cxgb4_ptp_adjfreq - Adjust frequency of PHC cycle counter * @ptp: ptp clock structure * @ppb: Desired frequency change in parts per billion * @@ -229,7 +230,7 @@ static int cxgb4_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) /** * cxgb4_ptp_fineadjtime - Shift the time of the hardware clock - * @ptp: ptp clock structure + * @adapter: board private structure * @delta: Desired change in nanoseconds * * Adjust the timer by resetting the timecounter structure. diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 4a5fa9eba0b6..59b65d4db086 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -58,10 +58,6 @@ static struct ch_tc_pedit_fields pedits[] = { PEDIT_FIELDS(IP6_, DST_63_32, 4, nat_lip, 4), PEDIT_FIELDS(IP6_, DST_95_64, 4, nat_lip, 8), PEDIT_FIELDS(IP6_, DST_127_96, 4, nat_lip, 12), - PEDIT_FIELDS(TCP_, SPORT, 2, nat_fport, 0), - PEDIT_FIELDS(TCP_, DPORT, 2, nat_lport, 0), - PEDIT_FIELDS(UDP_, SPORT, 2, nat_fport, 0), - PEDIT_FIELDS(UDP_, DPORT, 2, nat_lport, 0), }; static struct ch_tc_flower_entry *allocate_flower_entry(void) @@ -156,14 +152,14 @@ static void cxgb4_process_flow_match(struct net_device *dev, struct flow_match_ports match; flow_rule_match_ports(rule, &match); - fs->val.lport = cpu_to_be16(match.key->dst); - fs->mask.lport = cpu_to_be16(match.mask->dst); - fs->val.fport = cpu_to_be16(match.key->src); - fs->mask.fport = cpu_to_be16(match.mask->src); + fs->val.lport = be16_to_cpu(match.key->dst); + fs->mask.lport = be16_to_cpu(match.mask->dst); + fs->val.fport = be16_to_cpu(match.key->src); + fs->mask.fport = be16_to_cpu(match.mask->src); /* also initialize nat_lport/fport to same values */ - fs->nat_lport = cpu_to_be16(match.key->dst); - fs->nat_fport = cpu_to_be16(match.key->src); + fs->nat_lport = fs->val.lport; + fs->nat_fport = fs->val.fport; } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { @@ -354,12 +350,9 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val, switch (offset) { case PEDIT_TCP_SPORT_DPORT: if (~mask & PEDIT_TCP_UDP_SPORT_MASK) - offload_pedit(fs, cpu_to_be32(val) >> 16, - cpu_to_be32(mask) >> 16, - TCP_SPORT); + fs->nat_fport = val; else - offload_pedit(fs, cpu_to_be32(val), - cpu_to_be32(mask), TCP_DPORT); + fs->nat_lport = val >> 16; } fs->nat_mode = NAT_MODE_ALL; break; @@ -367,12 +360,9 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val, switch (offset) { case PEDIT_UDP_SPORT_DPORT: if (~mask & PEDIT_TCP_UDP_SPORT_MASK) - offload_pedit(fs, cpu_to_be32(val) >> 16, - cpu_to_be32(mask) >> 16, - UDP_SPORT); + fs->nat_fport = val; else - offload_pedit(fs, cpu_to_be32(val), - cpu_to_be32(mask), UDP_DPORT); + fs->nat_lport = val >> 16; } fs->nat_mode = NAT_MODE_ALL; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c index 3f3c11e54d97..dede02505ceb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c @@ -48,7 +48,7 @@ static int fill_match_fields(struct adapter *adap, bool next_header) { unsigned int i, j; - u32 val, mask; + __be32 val, mask; int off, err; bool found; @@ -228,7 +228,7 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls) const struct cxgb4_next_header *next; bool found = false; unsigned int i, j; - u32 val, mask; + __be32 val, mask; int off; if (t->table[link_uhtid - 1].link_handle) { @@ -242,10 +242,10 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls) /* Try to find matches that allow jumps to next header. */ for (i = 0; next[i].jump; i++) { - if (next[i].offoff != cls->knode.sel->offoff || - next[i].shift != cls->knode.sel->offshift || - next[i].mask != cls->knode.sel->offmask || - next[i].offset != cls->knode.sel->off) + if (next[i].sel.offoff != cls->knode.sel->offoff || + next[i].sel.offshift != cls->knode.sel->offshift || + next[i].sel.offmask != cls->knode.sel->offmask || + next[i].sel.off != cls->knode.sel->off) continue; /* Found a possible candidate. Find a key that @@ -257,9 +257,9 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls) val = cls->knode.sel->keys[j].val; mask = cls->knode.sel->keys[j].mask; - if (next[i].match_off == off && - next[i].match_val == val && - next[i].match_mask == mask) { + if (next[i].key.off == off && + next[i].key.val == val && + next[i].key.mask == mask) { found = true; break; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h index 125868c6770a..f59dd4b2ae6f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h @@ -38,12 +38,12 @@ struct cxgb4_match_field { int off; /* Offset from the beginning of the header to match */ /* Fill the value/mask pair in the spec if matched */ - int (*val)(struct ch_filter_specification *f, u32 val, u32 mask); + int (*val)(struct ch_filter_specification *f, __be32 val, __be32 mask); }; /* IPv4 match fields */ static inline int cxgb4_fill_ipv4_tos(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { f->val.tos = (ntohl(val) >> 16) & 0x000000FF; f->mask.tos = (ntohl(mask) >> 16) & 0x000000FF; @@ -52,7 +52,7 @@ static inline int cxgb4_fill_ipv4_tos(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv4_frag(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { u32 mask_val; u8 frag_val; @@ -74,7 +74,7 @@ static inline int cxgb4_fill_ipv4_frag(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv4_proto(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { f->val.proto = (ntohl(val) >> 16) & 0x000000FF; f->mask.proto = (ntohl(mask) >> 16) & 0x000000FF; @@ -83,7 +83,7 @@ static inline int cxgb4_fill_ipv4_proto(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv4_src_ip(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { memcpy(&f->val.fip[0], &val, sizeof(u32)); memcpy(&f->mask.fip[0], &mask, sizeof(u32)); @@ -92,7 +92,7 @@ static inline int cxgb4_fill_ipv4_src_ip(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv4_dst_ip(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { memcpy(&f->val.lip[0], &val, sizeof(u32)); memcpy(&f->mask.lip[0], &mask, sizeof(u32)); @@ -111,7 +111,7 @@ static const struct cxgb4_match_field cxgb4_ipv4_fields[] = { /* IPv6 match fields */ static inline int cxgb4_fill_ipv6_tos(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { f->val.tos = (ntohl(val) >> 20) & 0x000000FF; f->mask.tos = (ntohl(mask) >> 20) & 0x000000FF; @@ -120,7 +120,7 @@ static inline int cxgb4_fill_ipv6_tos(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv6_proto(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { f->val.proto = (ntohl(val) >> 8) & 0x000000FF; f->mask.proto = (ntohl(mask) >> 8) & 0x000000FF; @@ -129,7 +129,7 @@ static inline int cxgb4_fill_ipv6_proto(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv6_src_ip0(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { memcpy(&f->val.fip[0], &val, sizeof(u32)); memcpy(&f->mask.fip[0], &mask, sizeof(u32)); @@ -138,7 +138,7 @@ static inline int cxgb4_fill_ipv6_src_ip0(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv6_src_ip1(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { memcpy(&f->val.fip[4], &val, sizeof(u32)); memcpy(&f->mask.fip[4], &mask, sizeof(u32)); @@ -147,7 +147,7 @@ static inline int cxgb4_fill_ipv6_src_ip1(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv6_src_ip2(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { memcpy(&f->val.fip[8], &val, sizeof(u32)); memcpy(&f->mask.fip[8], &mask, sizeof(u32)); @@ -156,7 +156,7 @@ static inline int cxgb4_fill_ipv6_src_ip2(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv6_src_ip3(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { memcpy(&f->val.fip[12], &val, sizeof(u32)); memcpy(&f->mask.fip[12], &mask, sizeof(u32)); @@ -165,7 +165,7 @@ static inline int cxgb4_fill_ipv6_src_ip3(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv6_dst_ip0(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { memcpy(&f->val.lip[0], &val, sizeof(u32)); memcpy(&f->mask.lip[0], &mask, sizeof(u32)); @@ -174,7 +174,7 @@ static inline int cxgb4_fill_ipv6_dst_ip0(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv6_dst_ip1(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { memcpy(&f->val.lip[4], &val, sizeof(u32)); memcpy(&f->mask.lip[4], &mask, sizeof(u32)); @@ -183,7 +183,7 @@ static inline int cxgb4_fill_ipv6_dst_ip1(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv6_dst_ip2(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { memcpy(&f->val.lip[8], &val, sizeof(u32)); memcpy(&f->mask.lip[8], &mask, sizeof(u32)); @@ -192,7 +192,7 @@ static inline int cxgb4_fill_ipv6_dst_ip2(struct ch_filter_specification *f, } static inline int cxgb4_fill_ipv6_dst_ip3(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { memcpy(&f->val.lip[12], &val, sizeof(u32)); memcpy(&f->mask.lip[12], &mask, sizeof(u32)); @@ -216,7 +216,7 @@ static const struct cxgb4_match_field cxgb4_ipv6_fields[] = { /* TCP/UDP match */ static inline int cxgb4_fill_l4_ports(struct ch_filter_specification *f, - u32 val, u32 mask) + __be32 val, __be32 mask) { f->val.fport = ntohl(val) >> 16; f->mask.fport = ntohl(mask) >> 16; @@ -237,19 +237,13 @@ static const struct cxgb4_match_field cxgb4_udp_fields[] = { }; struct cxgb4_next_header { - unsigned int offset; /* Offset to next header */ - /* offset, shift, and mask added to offset above + /* Offset, shift, and mask added to beginning of the header * to get to next header. Useful when using a header * field's value to jump to next header such as IHL field * in IPv4 header. */ - unsigned int offoff; - u32 shift; - u32 mask; - /* match criteria to make this jump */ - unsigned int match_off; - u32 match_val; - u32 match_mask; + struct tc_u32_sel sel; + struct tc_u32_key key; /* location of jump to make */ const struct cxgb4_match_field *jump; }; @@ -258,26 +252,74 @@ struct cxgb4_next_header { * IPv4 header. */ static const struct cxgb4_next_header cxgb4_ipv4_jumps[] = { - { .offset = 0, .offoff = 0, .shift = 6, .mask = 0xF, - .match_off = 8, .match_val = 0x600, .match_mask = 0xFF00, - .jump = cxgb4_tcp_fields }, - { .offset = 0, .offoff = 0, .shift = 6, .mask = 0xF, - .match_off = 8, .match_val = 0x1100, .match_mask = 0xFF00, - .jump = cxgb4_udp_fields }, - { .jump = NULL } + { + /* TCP Jump */ + .sel = { + .off = 0, + .offoff = 0, + .offshift = 6, + .offmask = cpu_to_be16(0x0f00), + }, + .key = { + .off = 8, + .val = cpu_to_be32(0x00060000), + .mask = cpu_to_be32(0x00ff0000), + }, + .jump = cxgb4_tcp_fields, + }, + { + /* UDP Jump */ + .sel = { + .off = 0, + .offoff = 0, + .offshift = 6, + .offmask = cpu_to_be16(0x0f00), + }, + .key = { + .off = 8, + .val = cpu_to_be32(0x00110000), + .mask = cpu_to_be32(0x00ff0000), + }, + .jump = cxgb4_udp_fields, + }, + { .jump = NULL }, }; /* Accept a rule with a jump directly past the 40 Bytes of IPv6 fixed header * to get to transport layer header. */ static const struct cxgb4_next_header cxgb4_ipv6_jumps[] = { - { .offset = 0x28, .offoff = 0, .shift = 0, .mask = 0, - .match_off = 4, .match_val = 0x60000, .match_mask = 0xFF0000, - .jump = cxgb4_tcp_fields }, - { .offset = 0x28, .offoff = 0, .shift = 0, .mask = 0, - .match_off = 4, .match_val = 0x110000, .match_mask = 0xFF0000, - .jump = cxgb4_udp_fields }, - { .jump = NULL } + { + /* TCP Jump */ + .sel = { + .off = 40, + .offoff = 0, + .offshift = 0, + .offmask = 0, + }, + .key = { + .off = 4, + .val = cpu_to_be32(0x00000600), + .mask = cpu_to_be32(0x0000ff00), + }, + .jump = cxgb4_tcp_fields, + }, + { + /* UDP Jump */ + .sel = { + .off = 40, + .offoff = 0, + .offshift = 0, + .offmask = 0, + }, + .key = { + .off = 4, + .val = cpu_to_be32(0x00001100), + .mask = cpu_to_be32(0x0000ff00), + }, + .jump = cxgb4_udp_fields, + }, + { .jump = NULL }, }; struct cxgb4_link { diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c index 72b37a66c7d8..c4864125fe02 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c @@ -503,40 +503,19 @@ u64 cxgb4_select_ntuple(struct net_device *dev, EXPORT_SYMBOL(cxgb4_select_ntuple); /* - * Called when address resolution fails for an L2T entry to handle packets - * on the arpq head. If a packet specifies a failure handler it is invoked, - * otherwise the packet is sent to the device. - */ -static void handle_failed_resolution(struct adapter *adap, struct l2t_entry *e) -{ - struct sk_buff *skb; - - while ((skb = __skb_dequeue(&e->arpq)) != NULL) { - const struct l2t_skb_cb *cb = L2T_SKB_CB(skb); - - spin_unlock(&e->lock); - if (cb->arp_err_handler) - cb->arp_err_handler(cb->handle, skb); - else - t4_ofld_send(adap, skb); - spin_lock(&e->lock); - } -} - -/* * Called when the host's neighbor layer makes a change to some entry that is * loaded into the HW L2 table. */ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh) { - struct l2t_entry *e; - struct sk_buff_head *arpq = NULL; - struct l2t_data *d = adap->l2t; unsigned int addr_len = neigh->tbl->key_len; u32 *addr = (u32 *) neigh->primary_key; - int ifidx = neigh->dev->ifindex; - int hash = addr_hash(d, addr, addr_len, ifidx); + int hash, ifidx = neigh->dev->ifindex; + struct sk_buff_head *arpq = NULL; + struct l2t_data *d = adap->l2t; + struct l2t_entry *e; + hash = addr_hash(d, addr, addr_len, ifidx); read_lock_bh(&d->lock); for (e = d->l2tab[hash].first; e; e = e->next) if (!addreq(e, addr) && e->ifindex == ifidx) { @@ -569,8 +548,25 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh) write_l2e(adap, e, 0); } - if (arpq) - handle_failed_resolution(adap, e); + if (arpq) { + struct sk_buff *skb; + + /* Called when address resolution fails for an L2T + * entry to handle packets on the arpq head. If a + * packet specifies a failure handler it is invoked, + * otherwise the packet is sent to the device. + */ + while ((skb = __skb_dequeue(&e->arpq)) != NULL) { + const struct l2t_skb_cb *cb = L2T_SKB_CB(skb); + + spin_unlock(&e->lock); + if (cb->arp_err_handler) + cb->arp_err_handler(cb->handle, skb); + else + t4_ofld_send(adap, skb); + spin_lock(&e->lock); + } + } spin_unlock_bh(&e->lock); } @@ -613,6 +609,7 @@ struct l2t_entry *t4_l2t_alloc_switching(struct adapter *adap, u16 vlan, } /** + * cxgb4_l2t_alloc_switching - Allocates an L2T entry for switch filters * @dev: net_device pointer * @vlan: VLAN Id * @port: Associated port diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c index fde93c50cfec..a1b14468d1ff 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c @@ -598,7 +598,7 @@ struct sched_class *cxgb4_sched_class_alloc(struct net_device *dev, /** * cxgb4_sched_class_free - free a scheduling class * @dev: net_device pointer - * @e: scheduling class + * @classid: scheduling class id to free * * Frees a scheduling class if there are no users. */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 1359158652b7..32a45dc51ed7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -302,7 +302,7 @@ static void deferred_unmap_destructor(struct sk_buff *skb) /** * free_tx_desc - reclaims Tx descriptors and their buffers - * @adapter: the adapter + * @adap: the adapter * @q: the Tx queue to reclaim descriptors from * @n: the number of descriptors to reclaim * @unmap: whether the buffers should be unmapped for DMA @@ -722,6 +722,7 @@ static inline unsigned int flits_to_desc(unsigned int n) /** * is_eth_imm - can an Ethernet packet be sent as immediate data? * @skb: the packet + * @chip_ver: chip version * * Returns whether an Ethernet packet is small enough to fit as * immediate data. Return value corresponds to headroom required. @@ -749,6 +750,7 @@ static inline int is_eth_imm(const struct sk_buff *skb, unsigned int chip_ver) /** * calc_tx_flits - calculate the number of flits for a packet Tx WR * @skb: the packet + * @chip_ver: chip version * * Returns the number of flits needed for a Tx WR for the given Ethernet * packet, including the needed WR and CPL headers. @@ -804,6 +806,7 @@ static inline unsigned int calc_tx_flits(const struct sk_buff *skb, /** * calc_tx_descs - calculate the number of Tx descriptors for a packet * @skb: the packet + * @chip_ver: chip version * * Returns the number of Tx descriptors needed for the given Ethernet * packet, including the needed WR and CPL headers. @@ -1425,12 +1428,10 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) qidx = skb_get_queue_mapping(skb); if (ptp_enabled) { - spin_lock(&adap->ptp_lock); if (!(adap->ptp_tx_skb)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; adap->ptp_tx_skb = skb_get(skb); } else { - spin_unlock(&adap->ptp_lock); goto out_free; } q = &adap->sge.ptptxq; @@ -1444,11 +1445,8 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) #ifdef CONFIG_CHELSIO_T4_FCOE ret = cxgb_fcoe_offload(skb, adap, pi, &cntrl); - if (unlikely(ret == -ENOTSUPP)) { - if (ptp_enabled) - spin_unlock(&adap->ptp_lock); + if (unlikely(ret == -EOPNOTSUPP)) goto out_free; - } #endif /* CONFIG_CHELSIO_T4_FCOE */ chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip); @@ -1461,8 +1459,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) dev_err(adap->pdev_dev, "%s: Tx ring %u full while queue awake!\n", dev->name, qidx); - if (ptp_enabled) - spin_unlock(&adap->ptp_lock); return NETDEV_TX_BUSY; } @@ -1481,8 +1477,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) unlikely(cxgb4_map_skb(adap->pdev_dev, skb, sgl_sdesc->addr) < 0)) { memset(sgl_sdesc->addr, 0, sizeof(sgl_sdesc->addr)); q->mapping_err++; - if (ptp_enabled) - spin_unlock(&adap->ptp_lock); goto out_free; } @@ -1533,8 +1527,7 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) if (iph->version == 4) { iph->check = 0; iph->tot_len = 0; - iph->check = (u16)(~ip_fast_csum((u8 *)iph, - iph->ihl)); + iph->check = ~ip_fast_csum((u8 *)iph, iph->ihl); } if (skb->ip_summed == CHECKSUM_PARTIAL) cntrl = hwcsum(adap->params.chip, skb); @@ -1630,8 +1623,6 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) txq_advance(&q->q, ndesc); cxgb4_ring_tx_db(adap, &q->q, ndesc); - if (ptp_enabled) - spin_unlock(&adap->ptp_lock); return NETDEV_TX_OK; out_free: @@ -2377,6 +2368,16 @@ netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(qid >= pi->nqsets)) return cxgb4_ethofld_xmit(skb, dev); + if (is_ptp_enabled(skb, dev)) { + struct adapter *adap = netdev2adap(dev); + netdev_tx_t ret; + + spin_lock(&adap->ptp_lock); + ret = cxgb4_eth_xmit(skb, dev); + spin_unlock(&adap->ptp_lock); + return ret; + } + return cxgb4_eth_xmit(skb, dev); } @@ -2410,9 +2411,9 @@ static void eosw_txq_flush_pending_skbs(struct sge_eosw_txq *eosw_txq) /** * cxgb4_ethofld_send_flowc - Send ETHOFLD flowc request to bind eotid to tc. - * @dev - netdevice - * @eotid - ETHOFLD tid to bind/unbind - * @tc - traffic class. If set to FW_SCHED_CLS_NONE, then unbinds the @eotid + * @dev: netdevice + * @eotid: ETHOFLD tid to bind/unbind + * @tc: traffic class. If set to FW_SCHED_CLS_NONE, then unbinds the @eotid * * Send a FLOWC work request to bind an ETHOFLD TID to a traffic class. * If @tc is set to FW_SCHED_CLS_NONE, then the @eotid is unbound from @@ -2691,7 +2692,6 @@ static inline unsigned int calc_tx_flits_ofld(const struct sk_buff *skb) /** * txq_stop_maperr - stop a Tx queue due to I/O MMU exhaustion - * @adap: the adapter * @q: the queue to stop * * Mark a Tx queue stopped due to I/O MMU exhaustion and resulting @@ -3286,7 +3286,7 @@ enum { /** * t4_systim_to_hwstamp - read hardware time stamp - * @adap: the adapter + * @adapter: the adapter * @skb: the packet * * Read Time Stamp from MPS packet and insert in skb which @@ -3313,15 +3313,16 @@ static noinline int t4_systim_to_hwstamp(struct adapter *adapter, hwtstamps = skb_hwtstamps(skb); memset(hwtstamps, 0, sizeof(*hwtstamps)); - hwtstamps->hwtstamp = ns_to_ktime(be64_to_cpu(*((u64 *)data))); + hwtstamps->hwtstamp = ns_to_ktime(get_unaligned_be64(data)); return RX_PTP_PKT_SUC; } /** * t4_rx_hststamp - Recv PTP Event Message - * @adap: the adapter + * @adapter: the adapter * @rsp: the response queue descriptor holding the RX_PKT message + * @rxq: the response queue holding the RX_PKT message * @skb: the packet * * PTP enabled and MPS packet, read HW timestamp @@ -3345,7 +3346,7 @@ static int t4_rx_hststamp(struct adapter *adapter, const __be64 *rsp, /** * t4_tx_hststamp - Loopback PTP Transmit Event Message - * @adap: the adapter + * @adapter: the adapter * @skb: the packet * @dev: the ingress net device * diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.c b/drivers/net/ethernet/chelsio/cxgb4/smt.c index 01c65d13fc0e..cbe72ed27b1e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/smt.c +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.c @@ -103,6 +103,7 @@ static void t4_smte_free(struct smt_entry *e) } /** + * cxgb4_smt_release - Release SMT entry * @e: smt entry to release * * Releases ref count and frees up an smt entry from SMT table @@ -231,6 +232,7 @@ static struct smt_entry *t4_smt_alloc_switching(struct adapter *adap, u16 pfvf, } /** + * cxgb4_smt_alloc_switching - Allocates an SMT entry for switch filters. * @dev: net_device pointer * @smac: MAC address to add to SMT * Returns pointer to the SMT entry created diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 1c8068c02728..1aa6dc10dc0b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3163,7 +3163,7 @@ int t4_get_tp_version(struct adapter *adapter, u32 *vers) /** * t4_get_exprom_version - return the Expansion ROM version (if any) - * @adapter: the adapter + * @adap: the adapter * @vers: where to place the version * * Reads the Expansion ROM header from FLASH and returns the version @@ -5310,7 +5310,7 @@ static unsigned int t4_use_ldst(struct adapter *adap) * @cmd: TP fw ldst address space type * @vals: where the indirect register values are stored/written * @nregs: how many indirect registers to read/write - * @start_idx: index of first indirect register to read/write + * @start_index: index of first indirect register to read/write * @rw: Read (1) or Write (0) * @sleep_ok: if true we may sleep while awaiting command completion * @@ -6115,7 +6115,7 @@ void t4_pmrx_get_stats(struct adapter *adap, u32 cnt[], u64 cycles[]) /** * compute_mps_bg_map - compute the MPS Buffer Group Map for a Port - * @adap: the adapter + * @adapter: the adapter * @pidx: the port index * * Computes and returns a bitmap indicating which MPS buffer groups are @@ -6252,7 +6252,7 @@ static unsigned int t4_get_tp_e2c_map(struct adapter *adapter, int pidx) /** * t4_get_tp_ch_map - return TP ingress channels associated with a port - * @adapter: the adapter + * @adap: the adapter * @pidx: the port index * * Returns a bitmap indicating which TP Ingress Channels are associated @@ -6589,7 +6589,7 @@ int t4_mdio_rd(struct adapter *adap, unsigned int mbox, unsigned int phy_addr, * @phy_addr: the PHY address * @mmd: the PHY MMD to access (0 for clause 22 PHYs) * @reg: the register to write - * @valp: value to write + * @val: value to write * * Issues a FW command through the given mailbox to write a PHY register. */ @@ -6615,7 +6615,7 @@ int t4_mdio_wr(struct adapter *adap, unsigned int mbox, unsigned int phy_addr, /** * t4_sge_decode_idma_state - decode the idma state - * @adap: the adapter + * @adapter: the adapter * @state: the state idma is stuck in */ void t4_sge_decode_idma_state(struct adapter *adapter, int state) @@ -6782,7 +6782,7 @@ void t4_sge_decode_idma_state(struct adapter *adapter, int state) * t4_sge_ctxt_flush - flush the SGE context cache * @adap: the adapter * @mbox: mailbox to use for the FW command - * @ctx_type: Egress or Ingress + * @ctxt_type: Egress or Ingress * * Issues a FW command through the given mailbox to flush the * SGE context cache. @@ -6809,7 +6809,7 @@ int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type) /** * t4_read_sge_dbqtimers - read SGE Doorbell Queue Timer values - * @adap - the adapter + * @adap: the adapter * @ndbqtimers: size of the provided SGE Doorbell Queue Timer table * @dbqtimers: SGE Doorbell Queue Timer table * @@ -7092,6 +7092,7 @@ static int t4_fw_halt(struct adapter *adap, unsigned int mbox, int force) /** * t4_fw_restart - restart the firmware by taking the uP out of RESET * @adap: the adapter + * @mbox: mailbox to use for the FW command * @reset: if we want to do a RESET to restart things * * Restart firmware previously halted by t4_fw_halt(). On successful @@ -7630,6 +7631,8 @@ int t4_cfg_pfvf(struct adapter *adap, unsigned int mbox, unsigned int pf, * @nmac: number of MAC addresses needed (1 to 5) * @mac: the MAC addresses of the VI * @rss_size: size of RSS table slice associated with this VI + * @vivld: the destination to store the VI Valid value. + * @vin: the destination to store the VIN value. * * Allocates a virtual interface for the given physical port. If @mac is * not %NULL it contains the MAC addresses of the VI as assigned by FW. @@ -7848,7 +7851,7 @@ int t4_free_raw_mac_filt(struct adapter *adap, unsigned int viid, * t4_alloc_encap_mac_filt - Adds a mac entry in mps tcam with VNI support * @adap: the adapter * @viid: the VI id - * @mac: the MAC address + * @addr: the MAC address * @mask: the mask * @vni: the VNI id for the tunnel protocol * @vni_mask: mask for the VNI id @@ -7897,11 +7900,11 @@ int t4_alloc_encap_mac_filt(struct adapter *adap, unsigned int viid, * t4_alloc_raw_mac_filt - Adds a mac entry in mps tcam * @adap: the adapter * @viid: the VI id - * @mac: the MAC address + * @addr: the MAC address * @mask: the mask * @idx: index at which to add this entry - * @port_id: the port index * @lookup_type: MAC address for inner (1) or outer (0) header + * @port_id: the port index * @sleep_ok: call is allowed to sleep * * Adds the mac entry at the specified index using raw mac interface. @@ -8126,7 +8129,7 @@ int t4_free_mac_filt(struct adapter *adap, unsigned int mbox, * @idx: index of existing filter for old value of MAC address, or -1 * @addr: the new MAC address value * @persist: whether a new MAC allocation should be persistent - * @add_smt: if true also add the address to the HW SMT + * @smt_idx: the destination to store the new SMT index. * * Modifies an exact-match filter and sets it to the new MAC address. * Note that in general it is not possible to modify the value of a given @@ -8448,7 +8451,6 @@ int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf, /** * t4_link_down_rc_str - return a string for a Link Down Reason Code - * @adap: the adapter * @link_down_rc: Link Down Reason Code * * Returns a string representation of the Link Down Reason Code. @@ -8472,9 +8474,7 @@ static const char *t4_link_down_rc_str(unsigned char link_down_rc) return reason[link_down_rc]; } -/** - * Return the highest speed set in the port capabilities, in Mb/s. - */ +/* Return the highest speed set in the port capabilities, in Mb/s. */ static unsigned int fwcap_to_speed(fw_port_cap32_t caps) { #define TEST_SPEED_RETURN(__caps_speed, __speed) \ @@ -9110,7 +9110,6 @@ found: /** * t4_prep_adapter - prepare SW and HW for operation * @adapter: the adapter - * @reset: if true perform a HW reset * * Initialize adapter SW state for the various HW modules, set initial * values for some adapter tunables, take PHYs out of reset, and @@ -10395,6 +10394,7 @@ int t4_sched_params(struct adapter *adapter, u8 type, u8 level, u8 mode, /** * t4_i2c_rd - read I2C data from adapter * @adap: the adapter + * @mbox: mailbox to use for the FW command * @port: Port number if per-port device; <0 if not * @devid: per-port device ID or absolute device ID * @offset: byte offset into device I2C space @@ -10450,7 +10450,7 @@ int t4_i2c_rd(struct adapter *adap, unsigned int mbox, int port, /** * t4_set_vlan_acl - Set a VLAN id for the specified VF - * @adapter: the adapter + * @adap: the adapter * @mbox: mailbox to use for the FW command * @vf: one of the VFs instantiated by the specified PF * @vlan: The vlanid to be set diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index cec865a97464..a7641be9094f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -260,8 +260,7 @@ static int cxgb4vf_set_addr_hash(struct port_info *pi) * @tcam_idx: TCAM index of existing filter for old value of MAC address, * or -1 * @addr: the new MAC address value - * @persist: whether a new MAC allocation should be persistent - * @add_smt: if true also add the address to the HW SMT + * @persistent: whether a new MAC allocation should be persistent * * Modifies an MPS filter and sets it to the new MAC address if * @tcam_idx >= 0, or adds the MAC address to a new filter if diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index f71c973398ec..8c3d6e11a4bf 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -1692,7 +1692,7 @@ static inline bool is_new_response(const struct rsp_ctrl *rc, * restore_rx_bufs - put back a packet's RX buffers * @gl: the packet gather list * @fl: the SGE Free List - * @nfrags: how many fragments in @si + * @frags: how many fragments in @si * * Called when we find out that the current packet, @si, can't be * processed right away for some reason. This is a very rare event and @@ -2054,7 +2054,7 @@ irq_handler_t t4vf_intr_handler(struct adapter *adapter) /** * sge_rx_timer_cb - perform periodic maintenance of SGE RX queues - * @data: the adapter + * @t: Rx timer * * Runs periodically from a timer to perform maintenance of SGE RX queues. * @@ -2113,7 +2113,7 @@ static void sge_rx_timer_cb(struct timer_list *t) /** * sge_tx_timer_cb - perform periodic maintenance of SGE Tx queues - * @data: the adapter + * @t: Tx timer * * Runs periodically from a timer to perform maintenance of SGE TX queues. * @@ -2405,6 +2405,7 @@ err: * t4vf_sge_alloc_eth_txq - allocate an SGE Ethernet TX Queue * @adapter: the adapter * @txq: pointer to the new txq to be filled in + * @dev: the network device * @devq: the network TX queue associated with the new txq * @iqid: the relative ingress queue ID to which events relating to * the new txq should be directed diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index 9d49ff211cc1..a31b87390b50 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -389,9 +389,7 @@ static inline enum cc_fec fwcap_to_cc_fec(fw_port_cap32_t fw_fec) return cc_fec; } -/** - * Return the highest speed set in the port capabilities, in Mb/s. - */ +/* Return the highest speed set in the port capabilities, in Mb/s. */ static unsigned int fwcap_to_speed(fw_port_cap32_t caps) { #define TEST_SPEED_RETURN(__caps_speed, __speed) \ @@ -1467,6 +1465,7 @@ int t4vf_identify_port(struct adapter *adapter, unsigned int viid, * @bcast: 1 to enable broadcast Rx, 0 to disable it, -1 no change * @vlanex: 1 to enable hardware VLAN Tag extraction, 0 to disable it, * -1 no change + * @sleep_ok: call is allowed to sleep * * Sets Rx properties of a virtual interface. */ @@ -1906,7 +1905,7 @@ static const char *t4vf_link_down_rc_str(unsigned char link_down_rc) /** * t4vf_handle_get_port_info - process a FW reply message * @pi: the port info - * @rpl: start of the FW message + * @cmd: start of the FW message * * Processes a GET_PORT_INFO FW reply message. */ @@ -2137,8 +2136,6 @@ int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl) return 0; } -/** - */ int t4vf_prep_adapter(struct adapter *adapter) { int err; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 298c55786fd9..96831f49925c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1595,6 +1595,24 @@ static int enetc_set_psfp(struct net_device *ndev, int en) return 0; } +static void enetc_enable_rxvlan(struct net_device *ndev, bool en) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + int i; + + for (i = 0; i < priv->num_rx_rings; i++) + enetc_bdr_enable_rxvlan(&priv->si->hw, i, en); +} + +static void enetc_enable_txvlan(struct net_device *ndev, bool en) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + int i; + + for (i = 0; i < priv->num_tx_rings; i++) + enetc_bdr_enable_txvlan(&priv->si->hw, i, en); +} + int enetc_set_features(struct net_device *ndev, netdev_features_t features) { @@ -1604,6 +1622,14 @@ int enetc_set_features(struct net_device *ndev, if (changed & NETIF_F_RXHASH) enetc_set_rss(ndev, !!(features & NETIF_F_RXHASH)); + if (changed & NETIF_F_HW_VLAN_CTAG_RX) + enetc_enable_rxvlan(ndev, + !!(features & NETIF_F_HW_VLAN_CTAG_RX)); + + if (changed & NETIF_F_HW_VLAN_CTAG_TX) + enetc_enable_txvlan(ndev, + !!(features & NETIF_F_HW_VLAN_CTAG_TX)); + if (changed & NETIF_F_HW_TC) err = enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC)); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 6314051bc6c1..ce0d321c0639 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -531,22 +531,22 @@ struct enetc_msg_cmd_header { /* Common H/W utility functions */ -static inline void enetc_enable_rxvlan(struct enetc_hw *hw, int si_idx, - bool en) +static inline void enetc_bdr_enable_rxvlan(struct enetc_hw *hw, int idx, + bool en) { - u32 val = enetc_rxbdr_rd(hw, si_idx, ENETC_RBMR); + u32 val = enetc_rxbdr_rd(hw, idx, ENETC_RBMR); val = (val & ~ENETC_RBMR_VTE) | (en ? ENETC_RBMR_VTE : 0); - enetc_rxbdr_wr(hw, si_idx, ENETC_RBMR, val); + enetc_rxbdr_wr(hw, idx, ENETC_RBMR, val); } -static inline void enetc_enable_txvlan(struct enetc_hw *hw, int si_idx, - bool en) +static inline void enetc_bdr_enable_txvlan(struct enetc_hw *hw, int idx, + bool en) { - u32 val = enetc_txbdr_rd(hw, si_idx, ENETC_TBMR); + u32 val = enetc_txbdr_rd(hw, idx, ENETC_TBMR); val = (val & ~ENETC_TBMR_VIH) | (en ? ENETC_TBMR_VIH : 0); - enetc_txbdr_wr(hw, si_idx, ENETC_TBMR, val); + enetc_txbdr_wr(hw, idx, ENETC_TBMR, val); } static inline void enetc_set_bdr_prio(struct enetc_hw *hw, int bdr_idx, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 824d211ec00f..4fac57dbb3c8 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -649,14 +649,6 @@ static int enetc_pf_set_features(struct net_device *ndev, netdev_features_t changed = ndev->features ^ features; struct enetc_ndev_priv *priv = netdev_priv(ndev); - if (changed & NETIF_F_HW_VLAN_CTAG_RX) - enetc_enable_rxvlan(&priv->si->hw, 0, - !!(features & NETIF_F_HW_VLAN_CTAG_RX)); - - if (changed & NETIF_F_HW_VLAN_CTAG_TX) - enetc_enable_txvlan(&priv->si->hw, 0, - !!(features & NETIF_F_HW_VLAN_CTAG_TX)); - if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) { struct enetc_pf *pf = enetc_si_priv(priv->si); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index c117074c16e3..23f278e46975 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -699,7 +699,7 @@ static void hns_nic_rx_up_pro(struct hns_nic_ring_data *ring_data, struct net_device *ndev = ring_data->napi.dev; skb->protocol = eth_type_trans(skb, ndev); - (void)napi_gro_receive(&ring_data->napi, skb); + napi_gro_receive(&ring_data->napi, skb); } static int hns_desc_unused(struct hnae_ring *ring) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 96d36ae5049e..c5c732601e35 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1715,7 +1715,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) } netdev->min_mtu = IBMVETH_MIN_MTU; - netdev->max_mtu = ETH_MAX_MTU; + netdev->max_mtu = ETH_MAX_MTU - IBMVETH_BUFF_OH; memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 2baf7b3ff4cb..0fd7eae25fe9 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1971,13 +1971,18 @@ static int do_reset(struct ibmvnic_adapter *adapter, release_sub_crqs(adapter, 1); } else { rc = ibmvnic_reset_crq(adapter); - if (!rc) + if (rc == H_CLOSED || rc == H_SUCCESS) { rc = vio_enable_interrupts(adapter->vdev); + if (rc) + netdev_err(adapter->netdev, + "Reset failed to enable interrupts. rc=%d\n", + rc); + } } if (rc) { netdev_err(adapter->netdev, - "Couldn't initialize crq. rc=%d\n", rc); + "Reset couldn't initialize crq. rc=%d\n", rc); goto out; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index aa8026b1eb81..67806b7b2f49 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2072,6 +2072,9 @@ static int i40e_set_ringparam(struct net_device *netdev, err = i40e_setup_rx_descriptors(&rx_rings[i]); if (err) goto rx_unwind; + err = i40e_alloc_rx_bi(&rx_rings[i]); + if (err) + goto rx_unwind; /* now allocate the Rx buffers to make sure the OS * has enough memory, any failure here means abort diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 5d807c8004f8..56ecd6c3f236 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -439,11 +439,15 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev, i40e_get_netdev_stats_struct_tx(ring, stats); if (i40e_enabled_xdp_vsi(vsi)) { - ring++; + ring = READ_ONCE(vsi->xdp_rings[i]); + if (!ring) + continue; i40e_get_netdev_stats_struct_tx(ring, stats); } - ring++; + ring = READ_ONCE(vsi->rx_rings[i]); + if (!ring) + continue; do { start = u64_stats_fetch_begin_irq(&ring->syncp); packets = ring->stats.packets; @@ -787,6 +791,8 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) for (q = 0; q < vsi->num_queue_pairs; q++) { /* locate Tx ring */ p = READ_ONCE(vsi->tx_rings[q]); + if (!p) + continue; do { start = u64_stats_fetch_begin_irq(&p->syncp); @@ -800,8 +806,11 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) tx_linearize += p->tx_stats.tx_linearize; tx_force_wb += p->tx_stats.tx_force_wb; - /* Rx queue is part of the same block as Tx queue */ - p = &p[1]; + /* locate Rx ring */ + p = READ_ONCE(vsi->rx_rings[q]); + if (!p) + continue; + do { start = u64_stats_fetch_begin_irq(&p->syncp); packets = p->stats.packets; @@ -10824,10 +10833,10 @@ static void i40e_vsi_clear_rings(struct i40e_vsi *vsi) if (vsi->tx_rings && vsi->tx_rings[0]) { for (i = 0; i < vsi->alloc_queue_pairs; i++) { kfree_rcu(vsi->tx_rings[i], rcu); - vsi->tx_rings[i] = NULL; - vsi->rx_rings[i] = NULL; + WRITE_ONCE(vsi->tx_rings[i], NULL); + WRITE_ONCE(vsi->rx_rings[i], NULL); if (vsi->xdp_rings) - vsi->xdp_rings[i] = NULL; + WRITE_ONCE(vsi->xdp_rings[i], NULL); } } } @@ -10861,7 +10870,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; ring->itr_setting = pf->tx_itr_default; - vsi->tx_rings[i] = ring++; + WRITE_ONCE(vsi->tx_rings[i], ring++); if (!i40e_enabled_xdp_vsi(vsi)) goto setup_rx; @@ -10879,7 +10888,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; set_ring_xdp(ring); ring->itr_setting = pf->tx_itr_default; - vsi->xdp_rings[i] = ring++; + WRITE_ONCE(vsi->xdp_rings[i], ring++); setup_rx: ring->queue_index = i; @@ -10892,7 +10901,7 @@ setup_rx: ring->size = 0; ring->dcb_tc = 0; ring->itr_setting = pf->rx_itr_default; - vsi->rx_rings[i] = ring; + WRITE_ONCE(vsi->rx_rings[i], ring); } return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 28b46cc9f5cb..2e3a39cea2c0 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1194,7 +1194,7 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi) for (i = 0; i < vsi->alloc_txq; i++) { if (vsi->tx_rings[i]) { kfree_rcu(vsi->tx_rings[i], rcu); - vsi->tx_rings[i] = NULL; + WRITE_ONCE(vsi->tx_rings[i], NULL); } } } @@ -1202,7 +1202,7 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi) for (i = 0; i < vsi->alloc_rxq; i++) { if (vsi->rx_rings[i]) { kfree_rcu(vsi->rx_rings[i], rcu); - vsi->rx_rings[i] = NULL; + WRITE_ONCE(vsi->rx_rings[i], NULL); } } } @@ -1235,7 +1235,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->vsi = vsi; ring->dev = dev; ring->count = vsi->num_tx_desc; - vsi->tx_rings[i] = ring; + WRITE_ONCE(vsi->tx_rings[i], ring); } /* Allocate Rx rings */ @@ -1254,7 +1254,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->netdev = vsi->netdev; ring->dev = dev; ring->count = vsi->num_rx_desc; - vsi->rx_rings[i] = ring; + WRITE_ONCE(vsi->rx_rings[i], ring); } return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 082825e3cb39..4cbd49c87568 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1702,7 +1702,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) xdp_ring->netdev = NULL; xdp_ring->dev = dev; xdp_ring->count = vsi->num_tx_desc; - vsi->xdp_rings[i] = xdp_ring; + WRITE_ONCE(vsi->xdp_rings[i], xdp_ring); if (ice_setup_tx_ring(xdp_ring)) goto free_xdp_rings; ice_set_ring_xdp(xdp_ring); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index fd9f5d41b594..2e35c5706cf1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -921,7 +921,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, ring->queue_index = txr_idx; /* assign ring to adapter */ - adapter->tx_ring[txr_idx] = ring; + WRITE_ONCE(adapter->tx_ring[txr_idx], ring); /* update count and index */ txr_count--; @@ -948,7 +948,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, set_ring_xdp(ring); /* assign ring to adapter */ - adapter->xdp_ring[xdp_idx] = ring; + WRITE_ONCE(adapter->xdp_ring[xdp_idx], ring); /* update count and index */ xdp_count--; @@ -991,7 +991,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, ring->queue_index = rxr_idx; /* assign ring to adapter */ - adapter->rx_ring[rxr_idx] = ring; + WRITE_ONCE(adapter->rx_ring[rxr_idx], ring); /* update count and index */ rxr_count--; @@ -1020,13 +1020,13 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx) ixgbe_for_each_ring(ring, q_vector->tx) { if (ring_is_xdp(ring)) - adapter->xdp_ring[ring->queue_index] = NULL; + WRITE_ONCE(adapter->xdp_ring[ring->queue_index], NULL); else - adapter->tx_ring[ring->queue_index] = NULL; + WRITE_ONCE(adapter->tx_ring[ring->queue_index], NULL); } ixgbe_for_each_ring(ring, q_vector->rx) - adapter->rx_ring[ring->queue_index] = NULL; + WRITE_ONCE(adapter->rx_ring[ring->queue_index], NULL); adapter->q_vector[v_idx] = NULL; napi_hash_del(&q_vector->napi); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index f162b8b8f345..97a423ecf808 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7051,7 +7051,10 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) } for (i = 0; i < adapter->num_rx_queues; i++) { - struct ixgbe_ring *rx_ring = adapter->rx_ring[i]; + struct ixgbe_ring *rx_ring = READ_ONCE(adapter->rx_ring[i]); + + if (!rx_ring) + continue; non_eop_descs += rx_ring->rx_stats.non_eop_descs; alloc_rx_page += rx_ring->rx_stats.alloc_rx_page; alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed; @@ -7072,15 +7075,20 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) packets = 0; /* gather some stats to the adapter struct that are per queue */ for (i = 0; i < adapter->num_tx_queues; i++) { - struct ixgbe_ring *tx_ring = adapter->tx_ring[i]; + struct ixgbe_ring *tx_ring = READ_ONCE(adapter->tx_ring[i]); + + if (!tx_ring) + continue; restart_queue += tx_ring->tx_stats.restart_queue; tx_busy += tx_ring->tx_stats.tx_busy; bytes += tx_ring->stats.bytes; packets += tx_ring->stats.packets; } for (i = 0; i < adapter->num_xdp_queues; i++) { - struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i]; + struct ixgbe_ring *xdp_ring = READ_ONCE(adapter->xdp_ring[i]); + if (!xdp_ring) + continue; restart_queue += xdp_ring->tx_stats.restart_queue; tx_busy += xdp_ring->tx_stats.tx_busy; bytes += xdp_ring->stats.bytes; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 946925bbcb2d..c639e3a29302 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -106,9 +106,11 @@ #define MVNETA_TX_IN_PRGRS BIT(1) #define MVNETA_TX_FIFO_EMPTY BIT(8) #define MVNETA_RX_MIN_FRAME_SIZE 0x247c +/* Only exists on Armada XP and Armada 370 */ #define MVNETA_SERDES_CFG 0x24A0 #define MVNETA_SGMII_SERDES_PROTO 0x0cc7 #define MVNETA_QSGMII_SERDES_PROTO 0x0667 +#define MVNETA_HSGMII_SERDES_PROTO 0x1107 #define MVNETA_TYPE_PRIO 0x24bc #define MVNETA_FORCE_UNI BIT(21) #define MVNETA_TXQ_CMD_1 0x24e4 @@ -3529,26 +3531,60 @@ static int mvneta_setup_txqs(struct mvneta_port *pp) return 0; } -static int mvneta_comphy_init(struct mvneta_port *pp) +static int mvneta_comphy_init(struct mvneta_port *pp, phy_interface_t interface) { int ret; - if (!pp->comphy) - return 0; - - ret = phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET, - pp->phy_interface); + ret = phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET, interface); if (ret) return ret; return phy_power_on(pp->comphy); } +static int mvneta_config_interface(struct mvneta_port *pp, + phy_interface_t interface) +{ + int ret = 0; + + if (pp->comphy) { + if (interface == PHY_INTERFACE_MODE_SGMII || + interface == PHY_INTERFACE_MODE_1000BASEX || + interface == PHY_INTERFACE_MODE_2500BASEX) { + ret = mvneta_comphy_init(pp, interface); + } + } else { + switch (interface) { + case PHY_INTERFACE_MODE_QSGMII: + mvreg_write(pp, MVNETA_SERDES_CFG, + MVNETA_QSGMII_SERDES_PROTO); + break; + + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + mvreg_write(pp, MVNETA_SERDES_CFG, + MVNETA_SGMII_SERDES_PROTO); + break; + + case PHY_INTERFACE_MODE_2500BASEX: + mvreg_write(pp, MVNETA_SERDES_CFG, + MVNETA_HSGMII_SERDES_PROTO); + break; + default: + break; + } + } + + pp->phy_interface = interface; + + return ret; +} + static void mvneta_start_dev(struct mvneta_port *pp) { int cpu; - WARN_ON(mvneta_comphy_init(pp)); + WARN_ON(mvneta_config_interface(pp, pp->phy_interface)); mvneta_max_rx_size_set(pp, pp->pkt_size); mvneta_txq_max_tx_size_set(pp, pp->pkt_size); @@ -3926,14 +3962,10 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, if (state->speed == SPEED_2500) new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE; - if (pp->comphy && pp->phy_interface != state->interface && - (state->interface == PHY_INTERFACE_MODE_SGMII || - state->interface == PHY_INTERFACE_MODE_1000BASEX || - state->interface == PHY_INTERFACE_MODE_2500BASEX)) { - pp->phy_interface = state->interface; - - WARN_ON(phy_power_off(pp->comphy)); - WARN_ON(mvneta_comphy_init(pp)); + if (pp->phy_interface != state->interface) { + if (pp->comphy) + WARN_ON(phy_power_off(pp->comphy)); + WARN_ON(mvneta_config_interface(pp, state->interface)); } if (new_ctrl0 != gmac_ctrl0) @@ -4982,12 +5014,10 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) /* MAC Cause register should be cleared */ mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0); - if (phy_mode == PHY_INTERFACE_MODE_QSGMII) - mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_QSGMII_SERDES_PROTO); - else if (phy_mode == PHY_INTERFACE_MODE_SGMII || - phy_interface_mode_is_8023z(phy_mode)) - mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO); - else if (!phy_interface_mode_is_rgmii(phy_mode)) + if (phy_mode != PHY_INTERFACE_MODE_QSGMII && + phy_mode != PHY_INTERFACE_MODE_SGMII && + !phy_interface_mode_is_8023z(phy_mode) && + !phy_interface_mode_is_rgmii(phy_mode)) return -EINVAL; return 0; @@ -5176,10 +5206,10 @@ static int mvneta_probe(struct platform_device *pdev) if (err < 0) goto err_netdev; - err = mvneta_port_power_up(pp, phy_mode); + err = mvneta_port_power_up(pp, pp->phy_interface); if (err < 0) { dev_err(&pdev->dev, "can't power up port\n"); - goto err_netdev; + return err; } /* Armada3700 network controller does not support per-cpu diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 80713123de5c..eefeb1cdc2ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -407,7 +407,9 @@ static int mlx5e_rep_indr_setup_block(struct net_device *netdev, struct mlx5e_rep_priv *rpriv, struct flow_block_offload *f, - flow_setup_cb_t *setup_cb) + flow_setup_cb_t *setup_cb, + void *data, + void (*cleanup)(struct flow_block_cb *block_cb)) { struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); struct mlx5e_rep_indr_block_priv *indr_priv; @@ -438,8 +440,10 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, list_add(&indr_priv->list, &rpriv->uplink_priv.tc_indr_block_priv_list); - block_cb = flow_block_cb_alloc(setup_cb, indr_priv, indr_priv, - mlx5e_rep_indr_block_unbind); + block_cb = flow_indr_block_cb_alloc(setup_cb, indr_priv, indr_priv, + mlx5e_rep_indr_block_unbind, + f, netdev, data, rpriv, + cleanup); if (IS_ERR(block_cb)) { list_del(&indr_priv->list); kfree(indr_priv); @@ -458,7 +462,7 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, if (!block_cb) return -ENOENT; - flow_block_cb_remove(block_cb, f); + flow_indr_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); return 0; default: @@ -469,15 +473,19 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, static int mlx5e_rep_indr_setup_cb(struct net_device *netdev, void *cb_priv, - enum tc_setup_type type, void *type_data) + enum tc_setup_type type, void *type_data, + void *data, + void (*cleanup)(struct flow_block_cb *block_cb)) { switch (type) { case TC_SETUP_BLOCK: return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data, - mlx5e_rep_indr_setup_tc_cb); + mlx5e_rep_indr_setup_tc_cb, + data, cleanup); case TC_SETUP_FT: return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data, - mlx5e_rep_indr_setup_ft_cb); + mlx5e_rep_indr_setup_ft_cb, + data, cleanup); default: return -EOPNOTSUPP; } @@ -496,7 +504,7 @@ int mlx5e_rep_tc_netdevice_event_register(struct mlx5e_rep_priv *rpriv) void mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv) { flow_indr_dev_unregister(mlx5e_rep_indr_setup_cb, rpriv, - mlx5e_rep_indr_setup_tc_cb); + mlx5e_rep_indr_block_unbind); } #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 55af877763ed..029ea344ad65 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -978,10 +978,10 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, lossy = !(pfc || pause_en); thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); - mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &thres_cells); + thres_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, thres_cells); delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc, pause_en); - mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &delay_cells); + delay_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, delay_cells); total_cells = thres_cells + delay_cells; taken_headroom_cells += total_cells; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 6e87457dd635..3abe3e7d89bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -374,17 +374,15 @@ mlxsw_sp_port_vlan_find_by_vid(const struct mlxsw_sp_port *mlxsw_sp_port, return NULL; } -static inline void +static inline u32 mlxsw_sp_port_headroom_8x_adjust(const struct mlxsw_sp_port *mlxsw_sp_port, - u16 *p_size) + u32 size_cells) { /* Ports with eight lanes use two headroom buffers between which the * configured headroom size is split. Therefore, multiply the calculated * headroom size by two. */ - if (mlxsw_sp_port->mapping.width != 8) - return; - *p_size *= 2; + return mlxsw_sp_port->mapping.width == 8 ? 2 * size_cells : size_cells; } enum mlxsw_sp_flood_type { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index f25a8b084b4b..6f84557a5a6f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -312,7 +312,7 @@ static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port) if (i == MLXSW_SP_PB_UNUSED) continue; - mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &size); + size = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, size); mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, size); } mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index f843545d3478..92351a79addc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -782,7 +782,7 @@ mlxsw_sp_span_port_buffer_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu) speed = 0; buffsize = mlxsw_sp_span_buffsize_get(mlxsw_sp, speed, mtu); - mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, (u16 *) &buffsize); + buffsize = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, buffsize); mlxsw_reg_sbib_pack(sbib_pl, mlxsw_sp_port->local_port, buffsize); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); } diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.h b/drivers/net/ethernet/neterion/vxge/vxge-config.h index 628fa9b2f741..373165119850 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.h +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.h @@ -297,7 +297,7 @@ struct vxge_hw_fifo_config { * @greedy_return: If Set it forces the device to return absolutely all RxD * that are consumed and still on board when a timer interrupt * triggers. If Clear, then if the device has already returned - * RxD before current timer interrupt trigerred and after the + * RxD before current timer interrupt triggered and after the * previous timer interrupt triggered, then the device is not * forced to returned the rest of the consumed RxD that it has * on board which account for a byte count less than the one diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index c39327677a7d..bb448c82cdc2 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -861,7 +861,7 @@ static void nfp_flower_clean(struct nfp_app *app) flush_work(&app_priv->cmsg_work); flow_indr_dev_unregister(nfp_flower_indr_setup_tc_cb, app, - nfp_flower_setup_indr_block_cb); + nfp_flower_setup_indr_tc_release); if (app_priv->flower_ext_feats & NFP_FL_FEATS_VF_RLIM) nfp_flower_qos_cleanup(app); diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 6c3dc3baf387..7f54a620acad 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -459,9 +459,10 @@ int nfp_flower_setup_qos_offload(struct nfp_app *app, struct net_device *netdev, struct tc_cls_matchall_offload *flow); void nfp_flower_stats_rlim_reply(struct nfp_app *app, struct sk_buff *skb); int nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv, - enum tc_setup_type type, void *type_data); -int nfp_flower_setup_indr_block_cb(enum tc_setup_type type, void *type_data, - void *cb_priv); + enum tc_setup_type type, void *type_data, + void *data, + void (*cleanup)(struct flow_block_cb *block_cb)); +void nfp_flower_setup_indr_tc_release(void *cb_priv); void __nfp_flower_non_repr_priv_get(struct nfp_flower_non_repr_priv *non_repr_priv); diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 695d24b9dd92..d7340dc09b4c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -1619,8 +1619,8 @@ nfp_flower_indr_block_cb_priv_lookup(struct nfp_app *app, return NULL; } -int nfp_flower_setup_indr_block_cb(enum tc_setup_type type, - void *type_data, void *cb_priv) +static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type, + void *type_data, void *cb_priv) { struct nfp_flower_indr_block_cb_priv *priv = cb_priv; struct flow_cls_offload *flower = type_data; @@ -1637,7 +1637,7 @@ int nfp_flower_setup_indr_block_cb(enum tc_setup_type type, } } -static void nfp_flower_setup_indr_tc_release(void *cb_priv) +void nfp_flower_setup_indr_tc_release(void *cb_priv) { struct nfp_flower_indr_block_cb_priv *priv = cb_priv; @@ -1647,7 +1647,8 @@ static void nfp_flower_setup_indr_tc_release(void *cb_priv) static int nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, - struct flow_block_offload *f) + struct flow_block_offload *f, void *data, + void (*cleanup)(struct flow_block_cb *block_cb)) { struct nfp_flower_indr_block_cb_priv *cb_priv; struct nfp_flower_priv *priv = app->priv; @@ -1676,9 +1677,10 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, cb_priv->app = app; list_add(&cb_priv->list, &priv->indr_block_cb_priv); - block_cb = flow_block_cb_alloc(nfp_flower_setup_indr_block_cb, - cb_priv, cb_priv, - nfp_flower_setup_indr_tc_release); + block_cb = flow_indr_block_cb_alloc(nfp_flower_setup_indr_block_cb, + cb_priv, cb_priv, + nfp_flower_setup_indr_tc_release, + f, netdev, data, app, cleanup); if (IS_ERR(block_cb)) { list_del(&cb_priv->list); kfree(cb_priv); @@ -1699,7 +1701,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, if (!block_cb) return -ENOENT; - flow_block_cb_remove(block_cb, f); + flow_indr_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); return 0; default: @@ -1710,7 +1712,9 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, int nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv, - enum tc_setup_type type, void *type_data) + enum tc_setup_type type, void *type_data, + void *data, + void (*cleanup)(struct flow_block_cb *block_cb)) { if (!nfp_fl_is_netdev_to_offload(netdev)) return -EOPNOTSUPP; @@ -1718,7 +1722,7 @@ nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv, switch (type) { case TC_SETUP_BLOCK: return nfp_flower_setup_indr_tc_block(netdev, cb_priv, - type_data); + type_data, data, cleanup); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h index 32b9d7705404..55cef5b16aa5 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h @@ -147,7 +147,7 @@ struct pch_gbe_regs { #define PCH_GBE_RH_ALM_FULL_8 0x00001000 /* 8 words */ #define PCH_GBE_RH_ALM_FULL_16 0x00002000 /* 16 words */ #define PCH_GBE_RH_ALM_FULL_32 0x00003000 /* 32 words */ -/* RX FIFO Read Triger Threshold */ +/* RX FIFO Read Trigger Threshold */ #define PCH_GBE_RH_RD_TRG_4 0x00000000 /* 4 words */ #define PCH_GBE_RH_RD_TRG_8 0x00000200 /* 8 words */ #define PCH_GBE_RH_RD_TRG_16 0x00000400 /* 16 words */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 9d8c969f21cb..aaa00edd9d5b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -96,7 +96,8 @@ static void ionic_link_status_check(struct ionic_lif *lif) u16 link_status; bool link_up; - if (!test_bit(IONIC_LIF_F_LINK_CHECK_REQUESTED, lif->state)) + if (!test_bit(IONIC_LIF_F_LINK_CHECK_REQUESTED, lif->state) || + test_bit(IONIC_LIF_F_QUEUE_RESET, lif->state)) return; link_status = le16_to_cpu(lif->info->status.link_status); @@ -1245,6 +1246,7 @@ static int ionic_init_nic_features(struct ionic_lif *lif) netdev->hw_features |= netdev->hw_enc_features; netdev->features |= netdev->hw_features; + netdev->vlan_features |= netdev->features & ~NETIF_F_VLAN_FEATURES; netdev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE; @@ -1692,15 +1694,15 @@ static void ionic_stop_queues(struct ionic_lif *lif) if (!test_and_clear_bit(IONIC_LIF_F_UP, lif->state)) return; - ionic_txrx_disable(lif); netif_tx_disable(lif->netdev); + ionic_txrx_disable(lif); } int ionic_stop(struct net_device *netdev) { struct ionic_lif *lif = netdev_priv(netdev); - if (!netif_device_present(netdev)) + if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) return 0; ionic_stop_queues(lif); @@ -1983,18 +1985,19 @@ int ionic_reset_queues(struct ionic_lif *lif) bool running; int err = 0; - /* Put off the next watchdog timeout */ - netif_trans_update(lif->netdev); - err = ionic_wait_for_bit(lif, IONIC_LIF_F_QUEUE_RESET); if (err) return err; running = netif_running(lif->netdev); - if (running) + if (running) { + netif_device_detach(lif->netdev); err = ionic_stop(lif->netdev); - if (!err && running) + } + if (!err && running) { ionic_open(lif->netdev); + netif_device_attach(lif->netdev); + } clear_bit(IONIC_LIF_F_QUEUE_RESET, lif->state); diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 7b76667acaba..08ba9d54ab63 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -271,7 +271,7 @@ static void qed_cxt_qm_iids(struct qed_hwfn *p_hwfn, vf_tids += segs[NUM_TASK_PF_SEGMENTS].count; } - iids->vf_cids += vf_cids * p_mngr->vf_count; + iids->vf_cids = vf_cids; iids->tids += vf_tids * p_mngr->vf_count; DP_VERBOSE(p_hwfn, QED_MSG_ILT, @@ -465,6 +465,20 @@ static struct qed_ilt_cli_blk *qed_cxt_set_blk(struct qed_ilt_cli_blk *p_blk) return p_blk; } +static void qed_cxt_ilt_blk_reset(struct qed_hwfn *p_hwfn) +{ + struct qed_ilt_client_cfg *clients = p_hwfn->p_cxt_mngr->clients; + u32 cli_idx, blk_idx; + + for (cli_idx = 0; cli_idx < MAX_ILT_CLIENTS; cli_idx++) { + for (blk_idx = 0; blk_idx < ILT_CLI_PF_BLOCKS; blk_idx++) + clients[cli_idx].pf_blks[blk_idx].total_size = 0; + + for (blk_idx = 0; blk_idx < ILT_CLI_VF_BLOCKS; blk_idx++) + clients[cli_idx].vf_blks[blk_idx].total_size = 0; + } +} + int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count) { struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr; @@ -484,6 +498,11 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count) p_mngr->pf_start_line = RESC_START(p_hwfn, QED_ILT); + /* Reset all ILT blocks at the beginning of ILT computing in order + * to prevent memory allocation for irrelevant blocks afterwards. + */ + qed_cxt_ilt_blk_reset(p_hwfn); + DP_VERBOSE(p_hwfn, QED_MSG_ILT, "hwfn [%d] - Set context manager starting line to be 0x%08x\n", p_hwfn->my_id, p_hwfn->p_cxt_mngr->pf_start_line); diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 57a0dab88431..81e8fbe4a05b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -5568,7 +5568,8 @@ static const char * const s_status_str[] = { /* DBG_STATUS_INVALID_FILTER_TRIGGER_DWORDS */ "The filter/trigger constraint dword offsets are not enabled for recording", - + /* DBG_STATUS_NO_MATCHING_FRAMING_MODE */ + "No matching framing mode", /* DBG_STATUS_VFC_READ_ERROR */ "Error reading from VFC", diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 1eebf30fa798..3aa51374e727 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -980,7 +980,7 @@ int qed_llh_add_mac_filter(struct qed_dev *cdev, struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn); union qed_llh_filter filter = {}; - u8 filter_idx, abs_ppfid; + u8 filter_idx, abs_ppfid = 0; u32 high, low, ref_cnt; int rc = 0; @@ -1368,6 +1368,8 @@ static void qed_dbg_user_data_free(struct qed_hwfn *p_hwfn) void qed_resc_free(struct qed_dev *cdev) { + struct qed_rdma_info *rdma_info; + struct qed_hwfn *p_hwfn; int i; if (IS_VF(cdev)) { @@ -1385,7 +1387,8 @@ void qed_resc_free(struct qed_dev *cdev) qed_llh_free(cdev); for_each_hwfn(cdev, i) { - struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; + p_hwfn = cdev->hwfns + i; + rdma_info = p_hwfn->p_rdma_info; qed_cxt_mngr_free(p_hwfn); qed_qm_info_free(p_hwfn); @@ -1404,8 +1407,10 @@ void qed_resc_free(struct qed_dev *cdev) qed_ooo_free(p_hwfn); } - if (QED_IS_RDMA_PERSONALITY(p_hwfn)) + if (QED_IS_RDMA_PERSONALITY(p_hwfn) && rdma_info) { + qed_spq_unregister_async_cb(p_hwfn, rdma_info->proto); qed_rdma_info_free(p_hwfn); + } qed_iov_free(p_hwfn); qed_l2_free(p_hwfn); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index d2fe61a5cf56..5409a2da6106 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -2836,8 +2836,6 @@ int qed_iwarp_stop(struct qed_hwfn *p_hwfn) if (rc) return rc; - qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_IWARP); - return qed_iwarp_ll2_stop(p_hwfn); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index 4566815f7b87..7271dd7166e5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -113,7 +113,6 @@ void qed_roce_stop(struct qed_hwfn *p_hwfn) break; } } - qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_ROCE); } static void qed_rdma_copy_gids(struct qed_rdma_qp *qp, __le32 *src_gid, diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 856051f50eb7..adc2c8f3d48e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -81,12 +81,17 @@ static void qed_vf_pf_req_end(struct qed_hwfn *p_hwfn, int req_status) mutex_unlock(&(p_hwfn->vf_iov_info->mutex)); } +#define QED_VF_CHANNEL_USLEEP_ITERATIONS 90 +#define QED_VF_CHANNEL_USLEEP_DELAY 100 +#define QED_VF_CHANNEL_MSLEEP_ITERATIONS 10 +#define QED_VF_CHANNEL_MSLEEP_DELAY 25 + static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size) { union vfpf_tlvs *p_req = p_hwfn->vf_iov_info->vf2pf_request; struct ustorm_trigger_vf_zone trigger; struct ustorm_vf_zone *zone_data; - int rc = 0, time = 100; + int iter, rc = 0; zone_data = (struct ustorm_vf_zone *)PXP_VF_BAR0_START_USDM_ZONE_B; @@ -126,11 +131,19 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size) REG_WR(p_hwfn, (uintptr_t)&zone_data->trigger, *((u32 *)&trigger)); /* When PF would be done with the response, it would write back to the - * `done' address. Poll until then. + * `done' address from a coherent DMA zone. Poll until then. */ - while ((!*done) && time) { - msleep(25); - time--; + + iter = QED_VF_CHANNEL_USLEEP_ITERATIONS; + while (!*done && iter--) { + udelay(QED_VF_CHANNEL_USLEEP_DELAY); + dma_rmb(); + } + + iter = QED_VF_CHANNEL_MSLEEP_ITERATIONS; + while (!*done && iter--) { + msleep(QED_VF_CHANNEL_MSLEEP_DELAY); + dma_rmb(); } if (!*done) { diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 756c05eb96f3..29e285430f99 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1229,7 +1229,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, /* PTP not supported on VFs */ if (!is_vf) - qede_ptp_enable(edev, (mode == QEDE_PROBE_NORMAL)); + qede_ptp_enable(edev); edev->ops->register_ops(cdev, &qede_ll_ops, edev); @@ -1318,6 +1318,7 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) if (system_state == SYSTEM_POWER_OFF) return; qed_ops->common->remove(cdev); + edev->cdev = NULL; /* Since this can happen out-of-sync with other flows, * don't release the netdevice until after slowpath stop diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 4c7f7a7fc151..cd5841a9415e 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -412,6 +412,7 @@ void qede_ptp_disable(struct qede_dev *edev) if (ptp->tx_skb) { dev_kfree_skb_any(ptp->tx_skb); ptp->tx_skb = NULL; + clear_bit_unlock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags); } /* Disable PTP in HW */ @@ -423,7 +424,7 @@ void qede_ptp_disable(struct qede_dev *edev) edev->ptp = NULL; } -static int qede_ptp_init(struct qede_dev *edev, bool init_tc) +static int qede_ptp_init(struct qede_dev *edev) { struct qede_ptp *ptp; int rc; @@ -444,25 +445,19 @@ static int qede_ptp_init(struct qede_dev *edev, bool init_tc) /* Init work queue for Tx timestamping */ INIT_WORK(&ptp->work, qede_ptp_task); - /* Init cyclecounter and timecounter. This is done only in the first - * load. If done in every load, PTP application will fail when doing - * unload / load (e.g. MTU change) while it is running. - */ - if (init_tc) { - memset(&ptp->cc, 0, sizeof(ptp->cc)); - ptp->cc.read = qede_ptp_read_cc; - ptp->cc.mask = CYCLECOUNTER_MASK(64); - ptp->cc.shift = 0; - ptp->cc.mult = 1; - - timecounter_init(&ptp->tc, &ptp->cc, - ktime_to_ns(ktime_get_real())); - } + /* Init cyclecounter and timecounter */ + memset(&ptp->cc, 0, sizeof(ptp->cc)); + ptp->cc.read = qede_ptp_read_cc; + ptp->cc.mask = CYCLECOUNTER_MASK(64); + ptp->cc.shift = 0; + ptp->cc.mult = 1; - return rc; + timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real())); + + return 0; } -int qede_ptp_enable(struct qede_dev *edev, bool init_tc) +int qede_ptp_enable(struct qede_dev *edev) { struct qede_ptp *ptp; int rc; @@ -483,7 +478,7 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc) edev->ptp = ptp; - rc = qede_ptp_init(edev, init_tc); + rc = qede_ptp_init(edev); if (rc) goto err1; diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.h b/drivers/net/ethernet/qlogic/qede/qede_ptp.h index 691a14c4b2c5..89c7f3cf3ee2 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.h +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.h @@ -41,7 +41,7 @@ void qede_ptp_rx_ts(struct qede_dev *edev, struct sk_buff *skb); void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb); int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *req); void qede_ptp_disable(struct qede_dev *edev); -int qede_ptp_enable(struct qede_dev *edev, bool init_tc); +int qede_ptp_enable(struct qede_dev *edev); int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *ts); static inline void qede_ptp_record_rx_ts(struct qede_dev *edev, diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c index 2d873ae8a234..668ccc9d49f8 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c +++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c @@ -105,6 +105,7 @@ static void qede_rdma_destroy_wq(struct qede_dev *edev) qede_rdma_cleanup_event(edev); destroy_workqueue(edev->rdma_info.rdma_wq); + edev->rdma_info.rdma_wq = NULL; } int qede_rdma_dev_add(struct qede_dev *edev, bool recovery) @@ -325,7 +326,7 @@ static void qede_rdma_add_event(struct qede_dev *edev, if (edev->rdma_info.exp_recovery) return; - if (!edev->rdma_info.qedr_dev) + if (!edev->rdma_info.qedr_dev || !edev->rdma_info.rdma_wq) return; /* We don't want the cleanup flow to start while we're allocating and diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index dad84ecf5a77..b660ddbe4025 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2114,8 +2114,11 @@ static void rtl_release_firmware(struct rtl8169_private *tp) void r8169_apply_firmware(struct rtl8169_private *tp) { /* TODO: release firmware if rtl_fw_write_firmware signals failure. */ - if (tp->rtl_fw) + 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; + } } static void rtl8168_config_eee_mac(struct rtl8169_private *tp) diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 328bc38848bb..0f366cc50b74 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1044,8 +1044,9 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget) skb->ip_summed = CHECKSUM_UNNECESSARY; next: - if ((skb && napi_gro_receive(&priv->napi, skb) != GRO_DROP) || - xdp_result) { + if (skb) + napi_gro_receive(&priv->napi, skb); + if (skb || xdp_result) { ndev->stats.rx_packets++; ndev->stats.rx_bytes += xdp.data_end - xdp.data; } diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 75266580b586..4661ef865807 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1649,6 +1649,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], geneve->collect_md = metadata; geneve->use_udp6_rx_checksums = use_udp6_rx_checksums; geneve->ttl_inherit = ttl_inherit; + geneve->df = df; geneve_unquiesce(geneve, gs4, gs6); return 0; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index f25702386d83..e351d65533aa 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -480,8 +480,7 @@ config MICROCHIP_T1_PHY config MICROSEMI_PHY tristate "Microsemi PHYs" depends on MACSEC || MACSEC=n - select CRYPTO_AES - select CRYPTO_ECB + select CRYPTO_LIB_AES if MACSEC help Currently supports VSC8514, VSC8530, VSC8531, VSC8540 and VSC8541 PHYs diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c index b4d3dc4068e2..d53ca884b5c9 100644 --- a/drivers/net/phy/mscc/mscc_macsec.c +++ b/drivers/net/phy/mscc/mscc_macsec.c @@ -10,7 +10,7 @@ #include <linux/phy.h> #include <dt-bindings/net/mscc-phy-vsc8531.h> -#include <crypto/skcipher.h> +#include <crypto/aes.h> #include <net/macsec.h> @@ -500,39 +500,17 @@ static u32 vsc8584_macsec_flow_context_id(struct macsec_flow *flow) static int vsc8584_macsec_derive_key(const u8 key[MACSEC_KEYID_LEN], u16 key_len, u8 hkey[16]) { - struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0); - struct skcipher_request *req = NULL; - struct scatterlist src, dst; - DECLARE_CRYPTO_WAIT(wait); - u32 input[4] = {0}; + const u8 input[AES_BLOCK_SIZE] = {0}; + struct crypto_aes_ctx ctx; int ret; - if (IS_ERR(tfm)) - return PTR_ERR(tfm); - - req = skcipher_request_alloc(tfm, GFP_KERNEL); - if (!req) { - ret = -ENOMEM; - goto out; - } - - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | - CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, - &wait); - ret = crypto_skcipher_setkey(tfm, key, key_len); - if (ret < 0) - goto out; - - sg_init_one(&src, input, 16); - sg_init_one(&dst, hkey, 16); - skcipher_request_set_crypt(req, &src, &dst, 16, NULL); - - ret = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); + ret = aes_expandkey(&ctx, key, key_len); + if (ret) + return ret; -out: - skcipher_request_free(req); - crypto_free_skcipher(tfm); - return ret; + aes_encrypt(&ctx, hkey, input); + memzero_explicit(&ctx, sizeof(ctx)); + return 0; } static int vsc8584_macsec_transformation(struct phy_device *phydev, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 1de3938628f4..56cfae950472 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -840,7 +840,7 @@ static void phy_error(struct phy_device *phydev) * phy_disable_interrupts - Disable the PHY interrupts from the PHY side * @phydev: target phy_device struct */ -static int phy_disable_interrupts(struct phy_device *phydev) +int phy_disable_interrupts(struct phy_device *phydev) { int err; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 04946de74fa0..b4978c5fb2ca 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -794,8 +794,10 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id, /* Grab the bits from PHYIR2, and put them in the lower half */ phy_reg = mdiobus_read(bus, addr, MII_PHYSID2); - if (phy_reg < 0) - return -EIO; + if (phy_reg < 0) { + /* returning -ENODEV doesn't stop bus scanning */ + return (phy_reg == -EIO || phy_reg == -ENODEV) ? -ENODEV : -EIO; + } *phy_id |= phy_reg; @@ -1090,6 +1092,10 @@ int phy_init_hw(struct phy_device *phydev) if (ret < 0) return ret; + ret = phy_disable_interrupts(phydev); + if (ret) + return ret; + if (phydev->drv->config_init) ret = phydev->drv->config_init(phydev); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 0ab65fb75258..3b7c70e6c5dd 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1463,6 +1463,8 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, struct ethtool_pauseparam *pause) { struct phylink_link_state *config = &pl->link_config; + bool manual_changed; + int pause_state; ASSERT_RTNL(); @@ -1477,15 +1479,15 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, !pause->autoneg && pause->rx_pause != pause->tx_pause) return -EINVAL; - mutex_lock(&pl->state_mutex); - config->pause = 0; + pause_state = 0; if (pause->autoneg) - config->pause |= MLO_PAUSE_AN; + pause_state |= MLO_PAUSE_AN; if (pause->rx_pause) - config->pause |= MLO_PAUSE_RX; + pause_state |= MLO_PAUSE_RX; if (pause->tx_pause) - config->pause |= MLO_PAUSE_TX; + pause_state |= MLO_PAUSE_TX; + mutex_lock(&pl->state_mutex); /* * See the comments for linkmode_set_pause(), wrt the deficiencies * with the current implementation. A solution to this issue would @@ -1502,18 +1504,35 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, linkmode_set_pause(config->advertising, pause->tx_pause, pause->rx_pause); - /* If we have a PHY, phylib will call our link state function if the - * mode has changed, which will trigger a resolve and update the MAC - * configuration. + manual_changed = (config->pause ^ pause_state) & MLO_PAUSE_AN || + (!(pause_state & MLO_PAUSE_AN) && + (config->pause ^ pause_state) & MLO_PAUSE_TXRX_MASK); + + config->pause = pause_state; + + if (!pl->phydev && !test_bit(PHYLINK_DISABLE_STOPPED, + &pl->phylink_disable_state)) + phylink_pcs_config(pl, true, &pl->link_config); + + mutex_unlock(&pl->state_mutex); + + /* If we have a PHY, a change of the pause frame advertisement will + * cause phylib to renegotiate (if AN is enabled) which will in turn + * call our phylink_phy_change() and trigger a resolve. Note that + * we can't hold our state mutex while calling phy_set_asym_pause(). */ - if (pl->phydev) { + if (pl->phydev) phy_set_asym_pause(pl->phydev, pause->rx_pause, pause->tx_pause); - } else if (!test_bit(PHYLINK_DISABLE_STOPPED, - &pl->phylink_disable_state)) { - phylink_pcs_config(pl, true, &pl->link_config); + + /* If the manual pause settings changed, make sure we trigger a + * resolve to update their state; we can not guarantee that the + * link will cycle. + */ + if (manual_changed) { + pl->mac_link_dropped = true; + phylink_run_resolve(pl); } - mutex_unlock(&pl->state_mutex); return 0; } diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 93da7d3d0954..74568ae16125 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -122,10 +122,13 @@ static int lan87xx_read_status(struct phy_device *phydev) if (rc < 0) return rc; - /* Wait max 640 ms to detect energy */ - phy_read_poll_timeout(phydev, MII_LAN83C185_CTRL_STATUS, rc, - rc & MII_LAN83C185_ENERGYON, 10000, - 640000, true); + /* Wait max 640 ms to detect energy and the timeout is not + * an actual error. + */ + read_poll_timeout(phy_read, rc, + rc & MII_LAN83C185_ENERGYON || rc < 0, + 10000, 640000, true, phydev, + MII_LAN83C185_CTRL_STATUS); if (rc < 0) return rc; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 950711448f39..a38e868e44d4 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1491,10 +1491,10 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) } if (pkt_cnt == 0) { - /* Skip IP alignment psudo header */ - skb_pull(skb, 2); skb->len = pkt_len; - skb_set_tail_pointer(skb, pkt_len); + /* Skip IP alignment pseudo header */ + skb_pull(skb, 2); + skb_set_tail_pointer(skb, skb->len); skb->truesize = pkt_len + sizeof(struct sk_buff); ax88179_rx_checksum(skb, pkt_hdr); return 1; @@ -1503,8 +1503,9 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) ax_skb = skb_clone(skb, GFP_ATOMIC); if (ax_skb) { ax_skb->len = pkt_len; - ax_skb->data = skb->data + 2; - skb_set_tail_pointer(ax_skb, pkt_len); + /* Skip IP alignment pseudo header */ + skb_pull(ax_skb, 2); + skb_set_tail_pointer(ax_skb, ax_skb->len); ax_skb->truesize = pkt_len + sizeof(struct sk_buff); ax88179_rx_checksum(ax_skb, pkt_hdr); usbnet_skb_return(dev, ax_skb); diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 355be77f4241..3cf4dc3433f9 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1324,7 +1324,7 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf) struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); if (pdata) { - cancel_delayed_work(&pdata->carrier_check); + cancel_delayed_work_sync(&pdata->carrier_check); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); pdata = NULL; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index e8085ab6d484..89d85dcb200e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1380,6 +1380,8 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct vxlan_rdst *rd; if (rcu_access_pointer(f->nh)) { + if (*idx < cb->args[2]) + goto skip_nh; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, @@ -1387,6 +1389,8 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, NLM_F_MULTI, NULL); if (err < 0) goto out; +skip_nh: + *idx += 1; continue; } diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 3ac3f8570ca1..a8f151b1b5fa 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -45,17 +45,18 @@ static int wg_open(struct net_device *dev) if (dev_v6) dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE; + mutex_lock(&wg->device_update_lock); ret = wg_socket_init(wg, wg->incoming_port); if (ret < 0) - return ret; - mutex_lock(&wg->device_update_lock); + goto out; list_for_each_entry(peer, &wg->peer_list, peer_list) { wg_packet_send_staged_packets(peer); if (peer->persistent_keepalive_interval) wg_packet_send_keepalive(peer); } +out: mutex_unlock(&wg->device_update_lock); - return 0; + return ret; } #ifdef CONFIG_PM_SLEEP @@ -225,6 +226,7 @@ static void wg_destruct(struct net_device *dev) list_del(&wg->device_list); rtnl_unlock(); mutex_lock(&wg->device_update_lock); + rcu_assign_pointer(wg->creating_net, NULL); wg->incoming_port = 0; wg_socket_reinit(wg, NULL, NULL); /* The final references are cleared in the below calls to destroy_workqueue. */ @@ -240,13 +242,11 @@ static void wg_destruct(struct net_device *dev) skb_queue_purge(&wg->incoming_handshakes); free_percpu(dev->tstats); free_percpu(wg->incoming_handshakes_worker); - if (wg->have_creating_net_ref) - put_net(wg->creating_net); kvfree(wg->index_hashtable); kvfree(wg->peer_hashtable); mutex_unlock(&wg->device_update_lock); - pr_debug("%s: Interface deleted\n", dev->name); + pr_debug("%s: Interface destroyed\n", dev->name); free_netdev(dev); } @@ -292,7 +292,7 @@ static int wg_newlink(struct net *src_net, struct net_device *dev, struct wg_device *wg = netdev_priv(dev); int ret = -ENOMEM; - wg->creating_net = src_net; + rcu_assign_pointer(wg->creating_net, src_net); init_rwsem(&wg->static_identity.lock); mutex_init(&wg->socket_update_lock); mutex_init(&wg->device_update_lock); @@ -393,30 +393,26 @@ static struct rtnl_link_ops link_ops __read_mostly = { .newlink = wg_newlink, }; -static int wg_netdevice_notification(struct notifier_block *nb, - unsigned long action, void *data) +static void wg_netns_pre_exit(struct net *net) { - struct net_device *dev = ((struct netdev_notifier_info *)data)->dev; - struct wg_device *wg = netdev_priv(dev); - - ASSERT_RTNL(); - - if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops) - return 0; + struct wg_device *wg; - if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) { - put_net(wg->creating_net); - wg->have_creating_net_ref = false; - } else if (dev_net(dev) != wg->creating_net && - !wg->have_creating_net_ref) { - wg->have_creating_net_ref = true; - get_net(wg->creating_net); + rtnl_lock(); + list_for_each_entry(wg, &device_list, device_list) { + if (rcu_access_pointer(wg->creating_net) == net) { + pr_debug("%s: Creating namespace exiting\n", wg->dev->name); + netif_carrier_off(wg->dev); + mutex_lock(&wg->device_update_lock); + rcu_assign_pointer(wg->creating_net, NULL); + wg_socket_reinit(wg, NULL, NULL); + mutex_unlock(&wg->device_update_lock); + } } - return 0; + rtnl_unlock(); } -static struct notifier_block netdevice_notifier = { - .notifier_call = wg_netdevice_notification +static struct pernet_operations pernet_ops = { + .pre_exit = wg_netns_pre_exit }; int __init wg_device_init(void) @@ -429,18 +425,18 @@ int __init wg_device_init(void) return ret; #endif - ret = register_netdevice_notifier(&netdevice_notifier); + ret = register_pernet_device(&pernet_ops); if (ret) goto error_pm; ret = rtnl_link_register(&link_ops); if (ret) - goto error_netdevice; + goto error_pernet; return 0; -error_netdevice: - unregister_netdevice_notifier(&netdevice_notifier); +error_pernet: + unregister_pernet_device(&pernet_ops); error_pm: #ifdef CONFIG_PM_SLEEP unregister_pm_notifier(&pm_notifier); @@ -451,7 +447,7 @@ error_pm: void wg_device_uninit(void) { rtnl_link_unregister(&link_ops); - unregister_netdevice_notifier(&netdevice_notifier); + unregister_pernet_device(&pernet_ops); #ifdef CONFIG_PM_SLEEP unregister_pm_notifier(&pm_notifier); #endif diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h index b15a8be9d816..4d0144e16947 100644 --- a/drivers/net/wireguard/device.h +++ b/drivers/net/wireguard/device.h @@ -40,7 +40,7 @@ struct wg_device { struct net_device *dev; struct crypt_queue encrypt_queue, decrypt_queue; struct sock __rcu *sock4, *sock6; - struct net *creating_net; + struct net __rcu *creating_net; struct noise_static_identity static_identity; struct workqueue_struct *handshake_receive_wq, *handshake_send_wq; struct workqueue_struct *packet_crypt_wq; @@ -56,7 +56,6 @@ struct wg_device { unsigned int num_peers, device_update_gen; u32 fwmark; u16 incoming_port; - bool have_creating_net_ref; }; int wg_device_init(void); diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index 802099c8828a..20a4f3c0a0a1 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -511,11 +511,15 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info) if (flags & ~__WGDEVICE_F_ALL) goto out; - ret = -EPERM; - if ((info->attrs[WGDEVICE_A_LISTEN_PORT] || - info->attrs[WGDEVICE_A_FWMARK]) && - !ns_capable(wg->creating_net->user_ns, CAP_NET_ADMIN)) - goto out; + if (info->attrs[WGDEVICE_A_LISTEN_PORT] || info->attrs[WGDEVICE_A_FWMARK]) { + struct net *net; + rcu_read_lock(); + net = rcu_dereference(wg->creating_net); + ret = !net || !ns_capable(net->user_ns, CAP_NET_ADMIN) ? -EPERM : 0; + rcu_read_unlock(); + if (ret) + goto out; + } ++wg->device_update_gen; diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c index 626433690abb..201a22681945 100644 --- a/drivers/net/wireguard/noise.c +++ b/drivers/net/wireguard/noise.c @@ -617,8 +617,8 @@ wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src, memcpy(handshake->hash, hash, NOISE_HASH_LEN); memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN); handshake->remote_index = src->sender_index; - if ((s64)(handshake->last_initiation_consumption - - (initiation_consumption = ktime_get_coarse_boottime_ns())) < 0) + initiation_consumption = ktime_get_coarse_boottime_ns(); + if ((s64)(handshake->last_initiation_consumption - initiation_consumption) < 0) handshake->last_initiation_consumption = initiation_consumption; handshake->state = HANDSHAKE_CONSUMED_INITIATION; up_write(&handshake->lock); diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 91438144e4f7..9b2ab6fc91cd 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -414,14 +414,8 @@ static void wg_packet_consume_data_done(struct wg_peer *peer, if (unlikely(routed_peer != peer)) goto dishonest_packet_peer; - if (unlikely(napi_gro_receive(&peer->napi, skb) == GRO_DROP)) { - ++dev->stats.rx_dropped; - net_dbg_ratelimited("%s: Failed to give packet to userspace from peer %llu (%pISpfsc)\n", - dev->name, peer->internal_id, - &peer->endpoint.addr); - } else { - update_rx_stats(peer, message_data_len(len_before_trim)); - } + napi_gro_receive(&peer->napi, skb); + update_rx_stats(peer, message_data_len(len_before_trim)); return; dishonest_packet_peer: diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index f9018027fc13..c33e2c81635f 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -347,6 +347,7 @@ static void set_sock_opts(struct socket *sock) int wg_socket_init(struct wg_device *wg, u16 port) { + struct net *net; int ret; struct udp_tunnel_sock_cfg cfg = { .sk_user_data = wg, @@ -371,37 +372,47 @@ int wg_socket_init(struct wg_device *wg, u16 port) }; #endif + rcu_read_lock(); + net = rcu_dereference(wg->creating_net); + net = net ? maybe_get_net(net) : NULL; + rcu_read_unlock(); + if (unlikely(!net)) + return -ENONET; + #if IS_ENABLED(CONFIG_IPV6) retry: #endif - ret = udp_sock_create(wg->creating_net, &port4, &new4); + ret = udp_sock_create(net, &port4, &new4); if (ret < 0) { pr_err("%s: Could not create IPv4 socket\n", wg->dev->name); - return ret; + goto out; } set_sock_opts(new4); - setup_udp_tunnel_sock(wg->creating_net, new4, &cfg); + setup_udp_tunnel_sock(net, new4, &cfg); #if IS_ENABLED(CONFIG_IPV6) if (ipv6_mod_enabled()) { port6.local_udp_port = inet_sk(new4->sk)->inet_sport; - ret = udp_sock_create(wg->creating_net, &port6, &new6); + ret = udp_sock_create(net, &port6, &new6); if (ret < 0) { udp_tunnel_sock_release(new4); if (ret == -EADDRINUSE && !port && retries++ < 100) goto retry; pr_err("%s: Could not create IPv6 socket\n", wg->dev->name); - return ret; + goto out; } set_sock_opts(new6); - setup_udp_tunnel_sock(wg->creating_net, new6, &cfg); + setup_udp_tunnel_sock(net, new6, &cfg); } #endif wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL); - return 0; + ret = 0; +out: + put_net(net); + return ret; } void wg_socket_reinit(struct wg_device *wg, struct sock *new4, diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c index bc8c15fb609d..080e5aa60bea 100644 --- a/drivers/net/wireless/ath/wil6210/txrx.c +++ b/drivers/net/wireless/ath/wil6210/txrx.c @@ -897,7 +897,6 @@ static void wil_rx_handle_eapol(struct wil6210_vif *vif, struct sk_buff *skb) void wil_netif_rx(struct sk_buff *skb, struct net_device *ndev, int cid, struct wil_net_stats *stats, bool gro) { - gro_result_t rc = GRO_NORMAL; struct wil6210_vif *vif = ndev_to_vif(ndev); struct wil6210_priv *wil = ndev_to_wil(ndev); struct wireless_dev *wdev = vif_to_wdev(vif); @@ -908,22 +907,16 @@ void wil_netif_rx(struct sk_buff *skb, struct net_device *ndev, int cid, */ int mcast = is_multicast_ether_addr(da); struct sk_buff *xmit_skb = NULL; - static const char * const gro_res_str[] = { - [GRO_MERGED] = "GRO_MERGED", - [GRO_MERGED_FREE] = "GRO_MERGED_FREE", - [GRO_HELD] = "GRO_HELD", - [GRO_NORMAL] = "GRO_NORMAL", - [GRO_DROP] = "GRO_DROP", - [GRO_CONSUMED] = "GRO_CONSUMED", - }; if (wdev->iftype == NL80211_IFTYPE_STATION) { sa = wil_skb_get_sa(skb); if (mcast && ether_addr_equal(sa, ndev->dev_addr)) { /* mcast packet looped back to us */ - rc = GRO_DROP; dev_kfree_skb(skb); - goto stats; + ndev->stats.rx_dropped++; + stats->rx_dropped++; + wil_dbg_txrx(wil, "Rx drop %d bytes\n", len); + return; } } else if (wdev->iftype == NL80211_IFTYPE_AP && !vif->ap_isolate) { if (mcast) { @@ -967,26 +960,16 @@ void wil_netif_rx(struct sk_buff *skb, struct net_device *ndev, int cid, wil_rx_handle_eapol(vif, skb); if (gro) - rc = napi_gro_receive(&wil->napi_rx, skb); + napi_gro_receive(&wil->napi_rx, skb); else netif_rx_ni(skb); - wil_dbg_txrx(wil, "Rx complete %d bytes => %s\n", - len, gro_res_str[rc]); - } -stats: - /* statistics. rc set to GRO_NORMAL for AP bridging */ - if (unlikely(rc == GRO_DROP)) { - ndev->stats.rx_dropped++; - stats->rx_dropped++; - wil_dbg_txrx(wil, "Rx drop %d bytes\n", len); - } else { - ndev->stats.rx_packets++; - stats->rx_packets++; - ndev->stats.rx_bytes += len; - stats->rx_bytes += len; - if (mcast) - ndev->stats.multicast++; } + ndev->stats.rx_packets++; + stats->rx_packets++; + ndev->stats.rx_bytes += len; + stats->rx_bytes += len; + if (mcast) + ndev->stats.multicast++; } void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c2c5bc4fb702..28f4388c1337 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1974,7 +1974,6 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->head->disk) { nvme_update_disk_info(ns->head->disk, ns, id); blk_queue_stack_limits(ns->head->disk->queue, ns->queue); - revalidate_disk(ns->head->disk); } #endif return 0; @@ -4174,6 +4173,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->dev = dev; ctrl->ops = ops; ctrl->quirks = quirks; + ctrl->numa_node = NUMA_NO_NODE; INIT_WORK(&ctrl->scan_work, nvme_scan_work); INIT_WORK(&ctrl->async_event_work, nvme_async_event_work); INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index da78e499947a..18d084ed497e 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -409,15 +409,14 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) { struct nvme_ns_head *head = ns->head; - lockdep_assert_held(&ns->head->lock); - if (!head->disk) return; - if (!(head->disk->flags & GENHD_FL_UP)) + if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) device_add_disk(&head->subsys->dev, head->disk, nvme_ns_id_attr_groups); + mutex_lock(&head->lock); if (nvme_path_is_optimized(ns)) { int node, srcu_idx; @@ -426,9 +425,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) __nvme_find_path(head, node); srcu_read_unlock(&head->srcu, srcu_idx); } + mutex_unlock(&head->lock); - synchronize_srcu(&ns->head->srcu); - kblockd_schedule_work(&ns->head->requeue_work); + synchronize_srcu(&head->srcu); + kblockd_schedule_work(&head->requeue_work); } static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data, @@ -483,14 +483,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state) static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc, struct nvme_ns *ns) { - mutex_lock(&ns->head->lock); ns->ana_grpid = le32_to_cpu(desc->grpid); ns->ana_state = desc->state; clear_bit(NVME_NS_ANA_PENDING, &ns->flags); if (nvme_state_is_live(ns->ana_state)) nvme_mpath_set_live(ns); - mutex_unlock(&ns->head->lock); } static int nvme_update_ana_state(struct nvme_ctrl *ctrl, @@ -640,31 +638,37 @@ static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr, } DEVICE_ATTR_RO(ana_state); -static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl, +static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl, struct nvme_ana_group_desc *desc, void *data) { - struct nvme_ns *ns = data; + struct nvme_ana_group_desc *dst = data; - if (ns->ana_grpid == le32_to_cpu(desc->grpid)) { - nvme_update_ns_ana_state(desc, ns); - return -ENXIO; /* just break out of the loop */ - } + if (desc->grpid != dst->grpid) + return 0; - return 0; + *dst = *desc; + return -ENXIO; /* just break out of the loop */ } void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id) { if (nvme_ctrl_use_ana(ns->ctrl)) { + struct nvme_ana_group_desc desc = { + .grpid = id->anagrpid, + .state = 0, + }; + mutex_lock(&ns->ctrl->ana_lock); ns->ana_grpid = le32_to_cpu(id->anagrpid); - nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state); + nvme_parse_ana_log(ns->ctrl, &desc, nvme_lookup_ana_group_desc); mutex_unlock(&ns->ctrl->ana_lock); + if (desc.state) { + /* found the group desc: update */ + nvme_update_ns_ana_state(&desc, ns); + } } else { - mutex_lock(&ns->head->lock); ns->ana_state = NVME_ANA_OPTIMIZED; nvme_mpath_set_live(ns); - mutex_unlock(&ns->head->lock); } if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) { @@ -686,6 +690,14 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) kblockd_schedule_work(&head->requeue_work); flush_work(&head->requeue_work); blk_cleanup_queue(head->disk->queue); + if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) { + /* + * if device_add_disk wasn't called, prevent + * disk release to put a bogus reference on the + * request queue + */ + head->disk->queue = NULL; + } put_disk(head->disk); } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index c0f4226d3299..2ef8d501e2a8 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -364,6 +364,8 @@ struct nvme_ns_head { spinlock_t requeue_lock; struct work_struct requeue_work; struct mutex lock; + unsigned long flags; +#define NVME_NSHEAD_DISK_LIVE 0 struct nvme_ns __rcu *current_path[]; #endif }; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index e2bacd369a88..b1d18f0633c7 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1593,7 +1593,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev) dev->admin_tagset.queue_depth = NVME_AQ_MQ_TAG_DEPTH; dev->admin_tagset.timeout = ADMIN_TIMEOUT; - dev->admin_tagset.numa_node = dev_to_node(dev->dev); + dev->admin_tagset.numa_node = dev->ctrl.numa_node; dev->admin_tagset.cmd_size = sizeof(struct nvme_iod); dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED; dev->admin_tagset.driver_data = dev; @@ -1669,6 +1669,8 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev) if (result) return result; + dev->ctrl.numa_node = dev_to_node(dev->dev); + nvmeq = &dev->queues[0]; aqa = nvmeq->q_depth - 1; aqa |= aqa << 16; @@ -2257,7 +2259,7 @@ static void nvme_dev_add(struct nvme_dev *dev) if (dev->io_queues[HCTX_TYPE_POLL]) dev->tagset.nr_maps++; dev->tagset.timeout = NVME_IO_TIMEOUT; - dev->tagset.numa_node = dev_to_node(dev->dev); + dev->tagset.numa_node = dev->ctrl.numa_node; dev->tagset.queue_depth = min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1; dev->tagset.cmd_size = sizeof(struct nvme_iod); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index f8f856dc0c67..13506a87a444 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -470,7 +470,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) * Spread I/O queues completion vectors according their queue index. * Admin queues can always go on completion vector 0. */ - comp_vector = idx == 0 ? idx : idx - 1; + comp_vector = (idx == 0 ? idx : idx - 1) % ibdev->num_comp_vectors; /* Polling queues need direct cq polling context */ if (nvme_rdma_poll_queue(queue)) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 3345ec7efaff..79ef2b8e2b3c 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1532,7 +1532,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, set->ops = &nvme_tcp_admin_mq_ops; set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; set->reserved_tags = 2; /* connect + keep-alive */ - set->numa_node = NUMA_NO_NODE; + set->numa_node = nctrl->numa_node; set->flags = BLK_MQ_F_BLOCKING; set->cmd_size = sizeof(struct nvme_tcp_request); set->driver_data = ctrl; @@ -1544,7 +1544,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, set->ops = &nvme_tcp_mq_ops; set->queue_depth = nctrl->sqsize + 1; set->reserved_tags = 1; /* fabric connect */ - set->numa_node = NUMA_NO_NODE; + set->numa_node = nctrl->numa_node; set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; set->cmd_size = sizeof(struct nvme_tcp_request); set->driver_data = ctrl; diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 0d54e730cbf2..6344e73c9354 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -340,7 +340,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops; ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */ - ctrl->admin_tag_set.numa_node = NUMA_NO_NODE; + ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node; ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) + NVME_INLINE_SG_CNT * sizeof(struct scatterlist); ctrl->admin_tag_set.driver_data = ctrl; @@ -512,7 +512,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) ctrl->tag_set.ops = &nvme_loop_mq_ops; ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; ctrl->tag_set.reserved_tags = 1; /* fabric connect */ - ctrl->tag_set.numa_node = NUMA_NO_NODE; + ctrl->tag_set.numa_node = ctrl->ctrl.numa_node; ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) + NVME_INLINE_SG_CNT * sizeof(struct scatterlist); diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index a04afe79529c..ef6f818ce5b3 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -314,10 +314,15 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) child, addr); if (of_mdiobus_child_is_phy(child)) { + /* -ENODEV is the return code that PHYLIB has + * standardized on to indicate that bus + * scanning should continue. + */ rc = of_mdiobus_register_phy(mdio, child, addr); - if (rc && rc != -ENODEV) + if (!rc) + break; + if (rc != -ENODEV) goto unregister; - break; } } } diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index 8f677f5d79b4..edb1c4f8b496 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -684,7 +684,7 @@ config REGULATOR_MT6323 config REGULATOR_MT6358 tristate "MediaTek MT6358 PMIC" - depends on MFD_MT6397 && BROKEN + depends on MFD_MT6397 help Say y here to select this option to enable the power regulator of MediaTek MT6358 PMIC. diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c index e1d6c8f6d40b..fe65b5acaf28 100644 --- a/drivers/regulator/da9063-regulator.c +++ b/drivers/regulator/da9063-regulator.c @@ -512,7 +512,6 @@ static const struct da9063_regulator_info da9063_regulator_info[] = { }, { DA9063_LDO(DA9063, LDO9, 950, 50, 3600), - .suspend = BFIELD(DA9063_REG_LDO9_CONT, DA9063_VLDO9_SEL), }, { DA9063_LDO(DA9063, LDO11, 900, 50, 3600), diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c index e970e9d2f8be..e4bb09bbd3fa 100644 --- a/drivers/regulator/helpers.c +++ b/drivers/regulator/helpers.c @@ -486,7 +486,7 @@ int regulator_map_voltage_pickable_linear_range(struct regulator_dev *rdev, continue; } - ret = selector + sel; + ret = selector + sel - range->min_sel; voltage = rdev->desc->ops->list_voltage(rdev, ret); diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c index 689537927f6f..4c8e8b472287 100644 --- a/drivers/regulator/pfuze100-regulator.c +++ b/drivers/regulator/pfuze100-regulator.c @@ -209,6 +209,19 @@ static const struct regulator_ops pfuze100_swb_regulator_ops = { }; +static const struct regulator_ops pfuze3000_sw_regulator_ops = { + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .list_voltage = regulator_list_voltage_table, + .map_voltage = regulator_map_voltage_ascend, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .set_ramp_delay = pfuze100_set_ramp_delay, + +}; + #define PFUZE100_FIXED_REG(_chip, _name, base, voltage) \ [_chip ## _ ## _name] = { \ .desc = { \ @@ -318,23 +331,28 @@ static const struct regulator_ops pfuze100_swb_regulator_ops = { .stby_mask = 0x20, \ } - -#define PFUZE3000_SW2_REG(_chip, _name, base, min, max, step) { \ - .desc = { \ - .name = #_name,\ - .n_voltages = ((max) - (min)) / (step) + 1, \ - .ops = &pfuze100_sw_regulator_ops, \ - .type = REGULATOR_VOLTAGE, \ - .id = _chip ## _ ## _name, \ - .owner = THIS_MODULE, \ - .min_uV = (min), \ - .uV_step = (step), \ - .vsel_reg = (base) + PFUZE100_VOL_OFFSET, \ - .vsel_mask = 0x7, \ - }, \ - .stby_reg = (base) + PFUZE100_STANDBY_OFFSET, \ - .stby_mask = 0x7, \ -} +/* No linar case for the some switches of PFUZE3000 */ +#define PFUZE3000_SW_REG(_chip, _name, base, mask, voltages) \ + [_chip ## _ ## _name] = { \ + .desc = { \ + .name = #_name, \ + .n_voltages = ARRAY_SIZE(voltages), \ + .ops = &pfuze3000_sw_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = _chip ## _ ## _name, \ + .owner = THIS_MODULE, \ + .volt_table = voltages, \ + .vsel_reg = (base) + PFUZE100_VOL_OFFSET, \ + .vsel_mask = (mask), \ + .enable_reg = (base) + PFUZE100_MODE_OFFSET, \ + .enable_mask = 0xf, \ + .enable_val = 0x8, \ + .enable_time = 500, \ + }, \ + .stby_reg = (base) + PFUZE100_STANDBY_OFFSET, \ + .stby_mask = (mask), \ + .sw_reg = true, \ + } #define PFUZE3000_SW3_REG(_chip, _name, base, min, max, step) { \ .desc = { \ @@ -391,9 +409,9 @@ static struct pfuze_regulator pfuze200_regulators[] = { }; static struct pfuze_regulator pfuze3000_regulators[] = { - PFUZE100_SWB_REG(PFUZE3000, SW1A, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a), + PFUZE3000_SW_REG(PFUZE3000, SW1A, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a), PFUZE100_SW_REG(PFUZE3000, SW1B, PFUZE100_SW1CVOL, 700000, 1475000, 25000), - PFUZE100_SWB_REG(PFUZE3000, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo), + PFUZE3000_SW_REG(PFUZE3000, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo), PFUZE3000_SW3_REG(PFUZE3000, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000), PFUZE100_SWB_REG(PFUZE3000, SWBST, PFUZE100_SWBSTCON1, 0x3, pfuze100_swbst), PFUZE100_SWB_REG(PFUZE3000, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs), @@ -407,8 +425,8 @@ static struct pfuze_regulator pfuze3000_regulators[] = { }; static struct pfuze_regulator pfuze3001_regulators[] = { - PFUZE100_SWB_REG(PFUZE3001, SW1, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a), - PFUZE100_SWB_REG(PFUZE3001, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo), + PFUZE3000_SW_REG(PFUZE3001, SW1, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a), + PFUZE3000_SW_REG(PFUZE3001, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo), PFUZE3000_SW3_REG(PFUZE3001, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000), PFUZE100_SWB_REG(PFUZE3001, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs), PFUZE100_VGEN_REG(PFUZE3001, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000), diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 18a0fb75a710..88e998de2d03 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -4544,9 +4544,6 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, int fallback = *(int *)reply->param; QETH_CARD_TEXT(card, 4, "setaccb"); - if (cmd->hdr.return_code) - return -EIO; - qeth_setadpparms_inspect_rc(cmd); access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl; QETH_CARD_TEXT_(card, 2, "rc=%d", @@ -4556,7 +4553,7 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, QETH_DBF_MESSAGE(3, "ERR:SET_ACCESS_CTRL(%#x) on device %x: %#x\n", access_ctrl_req->subcmd_code, CARD_DEVID(card), cmd->data.setadapterparms.hdr.return_code); - switch (cmd->data.setadapterparms.hdr.return_code) { + switch (qeth_setadpparms_inspect_rc(cmd)) { case SET_ACCESS_CTRL_RC_SUCCESS: if (card->options.isolation == ISOLATION_MODE_NONE) { dev_info(&card->gdev->dev, @@ -6840,9 +6837,11 @@ netdev_features_t qeth_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { + struct qeth_card *card = dev->ml_priv; + /* Traffic with local next-hop is not eligible for some offloads: */ - if (skb->ip_summed == CHECKSUM_PARTIAL) { - struct qeth_card *card = dev->ml_priv; + if (skb->ip_summed == CHECKSUM_PARTIAL && + card->options.isolation != ISOLATION_MODE_FWD) { netdev_features_t restricted = 0; if (skb_is_gso(skb) && !netif_needs_gso(skb, features)) diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index a35faced0456..58190c94561f 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -588,14 +588,14 @@ static void dspi_release_dma(struct fsl_dspi *dspi) return; if (dma->chan_tx) { - dma_unmap_single(dma->chan_tx->device->dev, dma->tx_dma_phys, - dma_bufsize, DMA_TO_DEVICE); + dma_free_coherent(dma->chan_tx->device->dev, dma_bufsize, + dma->tx_dma_buf, dma->tx_dma_phys); dma_release_channel(dma->chan_tx); } if (dma->chan_rx) { - dma_unmap_single(dma->chan_rx->device->dev, dma->rx_dma_phys, - dma_bufsize, DMA_FROM_DEVICE); + dma_free_coherent(dma->chan_rx->device->dev, dma_bufsize, + dma->rx_dma_buf, dma->rx_dma_phys); dma_release_channel(dma->chan_rx); } } diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index 06192c9ea813..cbc2387d450c 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -179,7 +179,7 @@ struct rspi_data { void __iomem *addr; - u32 max_speed_hz; + u32 speed_hz; struct spi_controller *ctlr; struct platform_device *pdev; wait_queue_head_t wait; @@ -258,8 +258,7 @@ static int rspi_set_config_register(struct rspi_data *rspi, int access_size) rspi_write8(rspi, rspi->sppcr, RSPI_SPPCR); /* Sets transfer bit rate */ - spbr = DIV_ROUND_UP(clk_get_rate(rspi->clk), - 2 * rspi->max_speed_hz) - 1; + spbr = DIV_ROUND_UP(clk_get_rate(rspi->clk), 2 * rspi->speed_hz) - 1; rspi_write8(rspi, clamp(spbr, 0, 255), RSPI_SPBR); /* Disable dummy transmission, set 16-bit word access, 1 frame */ @@ -299,14 +298,14 @@ static int rspi_rz_set_config_register(struct rspi_data *rspi, int access_size) clksrc = clk_get_rate(rspi->clk); while (div < 3) { - if (rspi->max_speed_hz >= clksrc/4) /* 4=(CLK/2)/2 */ + if (rspi->speed_hz >= clksrc/4) /* 4=(CLK/2)/2 */ break; div++; clksrc /= 2; } /* Sets transfer bit rate */ - spbr = DIV_ROUND_UP(clksrc, 2 * rspi->max_speed_hz) - 1; + spbr = DIV_ROUND_UP(clksrc, 2 * rspi->speed_hz) - 1; rspi_write8(rspi, clamp(spbr, 0, 255), RSPI_SPBR); rspi->spcmd |= div << 2; @@ -341,7 +340,7 @@ static int qspi_set_config_register(struct rspi_data *rspi, int access_size) rspi_write8(rspi, rspi->sppcr, RSPI_SPPCR); /* Sets transfer bit rate */ - spbr = DIV_ROUND_UP(clk_get_rate(rspi->clk), 2 * rspi->max_speed_hz); + spbr = DIV_ROUND_UP(clk_get_rate(rspi->clk), 2 * rspi->speed_hz); rspi_write8(rspi, clamp(spbr, 0, 255), RSPI_SPBR); /* Disable dummy transmission, set byte access */ @@ -949,9 +948,24 @@ static int rspi_prepare_message(struct spi_controller *ctlr, { struct rspi_data *rspi = spi_controller_get_devdata(ctlr); struct spi_device *spi = msg->spi; + const struct spi_transfer *xfer; int ret; - rspi->max_speed_hz = spi->max_speed_hz; + /* + * As the Bit Rate Register must not be changed while the device is + * active, all transfers in a message must use the same bit rate. + * In theory, the sequencer could be enabled, and each Command Register + * could divide the base bit rate by a different value. + * However, most RSPI variants do not have Transfer Data Length + * Multiplier Setting Registers, so each sequence step would be limited + * to a single word, making this feature unsuitable for large + * transfers, which would gain most from it. + */ + rspi->speed_hz = spi->max_speed_hz; + list_for_each_entry(xfer, &msg->transfers, transfer_list) { + if (xfer->speed_hz < rspi->speed_hz) + rspi->speed_hz = xfer->speed_hz; + } rspi->spcmd = SPCMD_SSLKP; if (spi->mode & SPI_CPOL) diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c index 88e6543648cb..bd23c4689b46 100644 --- a/drivers/spi/spi-sprd-adi.c +++ b/drivers/spi/spi-sprd-adi.c @@ -389,9 +389,9 @@ static int sprd_adi_restart_handler(struct notifier_block *this, sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_CTRL, val); /* Load the watchdog timeout value, 50ms is always enough. */ + sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_HIGH, 0); sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_LOW, WDG_LOAD_VAL & WDG_LOAD_MASK); - sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_HIGH, 0); /* Start the watchdog to reset system */ sprd_adi_read(sadi, sadi->slave_pbase + REG_WDG_CTRL, &val); diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c index 3c44bb2fd9b1..a900962b4336 100644 --- a/drivers/spi/spi-stm32-qspi.c +++ b/drivers/spi/spi-stm32-qspi.c @@ -553,20 +553,6 @@ static const struct spi_controller_mem_ops stm32_qspi_mem_ops = { .exec_op = stm32_qspi_exec_op, }; -static void stm32_qspi_release(struct stm32_qspi *qspi) -{ - pm_runtime_get_sync(qspi->dev); - /* disable qspi */ - writel_relaxed(0, qspi->io_base + QSPI_CR); - stm32_qspi_dma_free(qspi); - mutex_destroy(&qspi->lock); - pm_runtime_put_noidle(qspi->dev); - pm_runtime_disable(qspi->dev); - pm_runtime_set_suspended(qspi->dev); - pm_runtime_dont_use_autosuspend(qspi->dev); - clk_disable_unprepare(qspi->clk); -} - static int stm32_qspi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -642,7 +628,7 @@ static int stm32_qspi_probe(struct platform_device *pdev) if (IS_ERR(rstc)) { ret = PTR_ERR(rstc); if (ret == -EPROBE_DEFER) - goto err_qspi_release; + goto err_clk_disable; } else { reset_control_assert(rstc); udelay(2); @@ -653,7 +639,7 @@ static int stm32_qspi_probe(struct platform_device *pdev) platform_set_drvdata(pdev, qspi); ret = stm32_qspi_dma_setup(qspi); if (ret) - goto err_qspi_release; + goto err_dma_free; mutex_init(&qspi->lock); @@ -673,15 +659,26 @@ static int stm32_qspi_probe(struct platform_device *pdev) ret = devm_spi_register_master(dev, ctrl); if (ret) - goto err_qspi_release; + goto err_pm_runtime_free; pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); return 0; -err_qspi_release: - stm32_qspi_release(qspi); +err_pm_runtime_free: + pm_runtime_get_sync(qspi->dev); + /* disable qspi */ + writel_relaxed(0, qspi->io_base + QSPI_CR); + mutex_destroy(&qspi->lock); + pm_runtime_put_noidle(qspi->dev); + pm_runtime_disable(qspi->dev); + pm_runtime_set_suspended(qspi->dev); + pm_runtime_dont_use_autosuspend(qspi->dev); +err_dma_free: + stm32_qspi_dma_free(qspi); +err_clk_disable: + clk_disable_unprepare(qspi->clk); err_master_put: spi_master_put(qspi->ctrl); @@ -692,7 +689,16 @@ static int stm32_qspi_remove(struct platform_device *pdev) { struct stm32_qspi *qspi = platform_get_drvdata(pdev); - stm32_qspi_release(qspi); + pm_runtime_get_sync(qspi->dev); + /* disable qspi */ + writel_relaxed(0, qspi->io_base + QSPI_CR); + stm32_qspi_dma_free(qspi); + mutex_destroy(&qspi->lock); + pm_runtime_put_noidle(qspi->dev); + pm_runtime_disable(qspi->dev); + pm_runtime_set_suspended(qspi->dev); + pm_runtime_dont_use_autosuspend(qspi->dev); + clk_disable_unprepare(qspi->clk); return 0; } diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index d753df700e9e..59e07675ef86 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -609,15 +609,20 @@ err_find_dev: static int spidev_release(struct inode *inode, struct file *filp) { struct spidev_data *spidev; + int dofree; mutex_lock(&device_list_lock); spidev = filp->private_data; filp->private_data = NULL; + spin_lock_irq(&spidev->spi_lock); + /* ... after we unbound from the underlying device? */ + dofree = (spidev->spi == NULL); + spin_unlock_irq(&spidev->spi_lock); + /* last close? */ spidev->users--; if (!spidev->users) { - int dofree; kfree(spidev->tx_buffer); spidev->tx_buffer = NULL; @@ -625,19 +630,14 @@ static int spidev_release(struct inode *inode, struct file *filp) kfree(spidev->rx_buffer); spidev->rx_buffer = NULL; - spin_lock_irq(&spidev->spi_lock); - if (spidev->spi) - spidev->speed_hz = spidev->spi->max_speed_hz; - - /* ... after we unbound from the underlying device? */ - dofree = (spidev->spi == NULL); - spin_unlock_irq(&spidev->spi_lock); - if (dofree) kfree(spidev); + else + spidev->speed_hz = spidev->spi->max_speed_hz; } #ifdef CONFIG_SPI_SLAVE - spi_slave_abort(spidev->spi); + if (!dofree) + spi_slave_abort(spidev->spi); #endif mutex_unlock(&device_list_lock); @@ -787,13 +787,13 @@ static int spidev_remove(struct spi_device *spi) { struct spidev_data *spidev = spi_get_drvdata(spi); + /* prevent new opens */ + mutex_lock(&device_list_lock); /* make sure ops on existing fds can abort cleanly */ spin_lock_irq(&spidev->spi_lock); spidev->spi = NULL; spin_unlock_irq(&spidev->spi_lock); - /* prevent new opens */ - mutex_lock(&device_list_lock); list_del(&spidev->device_entry); device_destroy(spidev_class, spidev->devt); clear_bit(MINOR(spidev->devt), minors); diff --git a/drivers/tty/serial/kgdb_nmi.c b/drivers/tty/serial/kgdb_nmi.c index 5022447afa23..6004c0c1d173 100644 --- a/drivers/tty/serial/kgdb_nmi.c +++ b/drivers/tty/serial/kgdb_nmi.c @@ -50,7 +50,7 @@ static int kgdb_nmi_console_setup(struct console *co, char *options) * I/O utilities that messages sent to the console will automatically * be displayed on the dbg_io. */ - dbg_io_ops->is_console = true; + dbg_io_ops->cons = co; return 0; } diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c index 41396982e9e0..84ffede27f23 100644 --- a/drivers/tty/serial/kgdboc.c +++ b/drivers/tty/serial/kgdboc.c @@ -45,7 +45,6 @@ static struct platform_device *kgdboc_pdev; #if IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) static struct kgdb_io kgdboc_earlycon_io_ops; -static struct console *earlycon; static int (*earlycon_orig_exit)(struct console *con); #endif /* IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) */ @@ -145,7 +144,7 @@ static void kgdboc_unregister_kbd(void) #if IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) static void cleanup_earlycon(void) { - if (earlycon) + if (kgdboc_earlycon_io_ops.cons) kgdb_unregister_io_module(&kgdboc_earlycon_io_ops); } #else /* !IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) */ @@ -178,7 +177,7 @@ static int configure_kgdboc(void) goto noconfig; } - kgdboc_io_ops.is_console = 0; + kgdboc_io_ops.cons = NULL; kgdb_tty_driver = NULL; kgdboc_use_kms = 0; @@ -198,7 +197,7 @@ static int configure_kgdboc(void) int idx; if (cons->device && cons->device(cons, &idx) == p && idx == tty_line) { - kgdboc_io_ops.is_console = 1; + kgdboc_io_ops.cons = cons; break; } } @@ -433,7 +432,8 @@ static int kgdboc_earlycon_get_char(void) { char c; - if (!earlycon->read(earlycon, &c, 1)) + if (!kgdboc_earlycon_io_ops.cons->read(kgdboc_earlycon_io_ops.cons, + &c, 1)) return NO_POLL_CHAR; return c; @@ -441,7 +441,8 @@ static int kgdboc_earlycon_get_char(void) static void kgdboc_earlycon_put_char(u8 chr) { - earlycon->write(earlycon, &chr, 1); + kgdboc_earlycon_io_ops.cons->write(kgdboc_earlycon_io_ops.cons, &chr, + 1); } static void kgdboc_earlycon_pre_exp_handler(void) @@ -461,7 +462,7 @@ static void kgdboc_earlycon_pre_exp_handler(void) * boot if we detect this case. */ for_each_console(con) - if (con == earlycon) + if (con == kgdboc_earlycon_io_ops.cons) return; already_warned = true; @@ -484,25 +485,25 @@ static int kgdboc_earlycon_deferred_exit(struct console *con) static void kgdboc_earlycon_deinit(void) { - if (!earlycon) + if (!kgdboc_earlycon_io_ops.cons) return; - if (earlycon->exit == kgdboc_earlycon_deferred_exit) + if (kgdboc_earlycon_io_ops.cons->exit == kgdboc_earlycon_deferred_exit) /* * kgdboc_earlycon is exiting but original boot console exit * was never called (AKA kgdboc_earlycon_deferred_exit() * didn't ever run). Undo our trap. */ - earlycon->exit = earlycon_orig_exit; - else if (earlycon->exit) + kgdboc_earlycon_io_ops.cons->exit = earlycon_orig_exit; + else if (kgdboc_earlycon_io_ops.cons->exit) /* * We skipped calling the exit() routine so we could try to * keep using the boot console even after it went away. We're * finally done so call the function now. */ - earlycon->exit(earlycon); + kgdboc_earlycon_io_ops.cons->exit(kgdboc_earlycon_io_ops.cons); - earlycon = NULL; + kgdboc_earlycon_io_ops.cons = NULL; } static struct kgdb_io kgdboc_earlycon_io_ops = { @@ -511,7 +512,6 @@ static struct kgdb_io kgdboc_earlycon_io_ops = { .write_char = kgdboc_earlycon_put_char, .pre_exception = kgdboc_earlycon_pre_exp_handler, .deinit = kgdboc_earlycon_deinit, - .is_console = true, }; #define MAX_CONSOLE_NAME_LEN (sizeof((struct console *) 0)->name) @@ -557,10 +557,10 @@ static int __init kgdboc_earlycon_init(char *opt) goto unlock; } - earlycon = con; + kgdboc_earlycon_io_ops.cons = con; pr_info("Going to register kgdb with earlycon '%s'\n", con->name); if (kgdb_register_io_module(&kgdboc_earlycon_io_ops) != 0) { - earlycon = NULL; + kgdboc_earlycon_io_ops.cons = NULL; pr_info("Failed to register kgdb with earlycon\n"); } else { /* Trap exit so we can keep earlycon longer if needed. */ diff --git a/drivers/usb/early/ehci-dbgp.c b/drivers/usb/early/ehci-dbgp.c index ea0d531c63e2..775cf70cfb3e 100644 --- a/drivers/usb/early/ehci-dbgp.c +++ b/drivers/usb/early/ehci-dbgp.c @@ -1058,7 +1058,8 @@ static int __init kgdbdbgp_parse_config(char *str) kgdbdbgp_wait_time = simple_strtoul(ptr, &ptr, 10); } kgdb_register_io_module(&kgdbdbgp_io_ops); - kgdbdbgp_io_ops.is_console = early_dbgp_console.index != -1; + if (early_dbgp_console.index != -1) + kgdbdbgp_io_ops.cons = &early_dbgp_console; return 0; } diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index ff6562f602e0..de211ef3738c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -63,7 +63,7 @@ static void vdpa_release_dev(struct device *d) * @config: the bus operations that is supported by this device * @size: size of the parent structure that contains private data * - * Drvier should use vdap_alloc_device() wrapper macro instead of + * Driver should use vdpa_alloc_device() wrapper macro instead of * using this directly. * * Returns an error when parent/config/dma_dev is not set or fail to get diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index 0466921f4772..a09dedc79f68 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -263,9 +263,62 @@ static int vhost_test_set_features(struct vhost_test *n, u64 features) return 0; } +static long vhost_test_set_backend(struct vhost_test *n, unsigned index, int fd) +{ + static void *backend; + + const bool enable = fd != -1; + struct vhost_virtqueue *vq; + int r; + + mutex_lock(&n->dev.mutex); + r = vhost_dev_check_owner(&n->dev); + if (r) + goto err; + + if (index >= VHOST_TEST_VQ_MAX) { + r = -ENOBUFS; + goto err; + } + vq = &n->vqs[index]; + mutex_lock(&vq->mutex); + + /* Verify that ring has been setup correctly. */ + if (!vhost_vq_access_ok(vq)) { + r = -EFAULT; + goto err_vq; + } + if (!enable) { + vhost_poll_stop(&vq->poll); + backend = vhost_vq_get_backend(vq); + vhost_vq_set_backend(vq, NULL); + } else { + vhost_vq_set_backend(vq, backend); + r = vhost_vq_init_access(vq); + if (r == 0) + r = vhost_poll_start(&vq->poll, vq->kick); + } + + mutex_unlock(&vq->mutex); + + if (enable) { + vhost_test_flush_vq(n, index); + } + + mutex_unlock(&n->dev.mutex); + return 0; + +err_vq: + mutex_unlock(&vq->mutex); +err: + mutex_unlock(&n->dev.mutex); + return r; +} + static long vhost_test_ioctl(struct file *f, unsigned int ioctl, unsigned long arg) { + struct vhost_vring_file backend; struct vhost_test *n = f->private_data; void __user *argp = (void __user *)arg; u64 __user *featurep = argp; @@ -277,6 +330,10 @@ static long vhost_test_ioctl(struct file *f, unsigned int ioctl, if (copy_from_user(&test, argp, sizeof test)) return -EFAULT; return vhost_test_run(n, test); + case VHOST_TEST_SET_BACKEND: + if (copy_from_user(&backend, argp, sizeof backend)) + return -EFAULT; + return vhost_test_set_backend(n, backend.index, backend.fd); case VHOST_GET_FEATURES: features = VHOST_FEATURES; if (copy_to_user(featurep, &features, sizeof features)) diff --git a/drivers/vhost/test.h b/drivers/vhost/test.h index 7dd265bfdf81..822bc4bee03a 100644 --- a/drivers/vhost/test.h +++ b/drivers/vhost/test.h @@ -4,5 +4,6 @@ /* Start a given test on the virtio null device. 0 stops all tests. */ #define VHOST_TEST_RUN _IOW(VHOST_VIRTIO, 0x31, int) +#define VHOST_TEST_SET_BACKEND _IOW(VHOST_VIRTIO, 0x32, int) #endif diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 7580e34f76c1..a54b60d6623f 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -818,7 +818,7 @@ static int vhost_vdpa_mmap(struct file *file, struct vm_area_struct *vma) struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; struct vdpa_notification_area notify; - int index = vma->vm_pgoff; + unsigned long index = vma->vm_pgoff; if (vma->vm_end - vma->vm_start != PAGE_SIZE) return -EINVAL; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 9d28a8e3328f..e2a490c5ae08 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2402,7 +2402,8 @@ static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch) ops->graphics = 1; if (!blank) { - var.activate = FB_ACTIVATE_NOW | FB_ACTIVATE_FORCE; + var.activate = FB_ACTIVATE_NOW | FB_ACTIVATE_FORCE | + FB_ACTIVATE_KD_TEXT; fb_set_var(info, &var); ops->graphics = 0; ops->var = info->var; diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index bee29aadc646..def14ac0ebe1 100644 --- a/drivers/video/fbdev/uvesafb.c +++ b/drivers/video/fbdev/uvesafb.c @@ -1836,7 +1836,7 @@ static int uvesafb_setup(char *options) else if (!strcmp(this_opt, "noedid")) noedid = true; else if (!strcmp(this_opt, "noblank")) - blank = true; + blank = false; else if (!strncmp(this_opt, "vtotal:", 7)) vram_total = simple_strtoul(this_opt + 7, NULL, 0); else if (!strncmp(this_opt, "vremap:", 7)) diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 50c689f25045..f26f5f64ae82 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -101,6 +101,11 @@ struct virtio_mem { /* The parent resource for all memory added via this device. */ struct resource *parent_resource; + /* + * Copy of "System RAM (virtio_mem)" to be used for + * add_memory_driver_managed(). + */ + const char *resource_name; /* Summary of all memory block states. */ unsigned long nb_mb_state[VIRTIO_MEM_MB_STATE_COUNT]; @@ -414,8 +419,20 @@ static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id) if (nid == NUMA_NO_NODE) nid = memory_add_physaddr_to_nid(addr); + /* + * When force-unloading the driver and we still have memory added to + * Linux, the resource name has to stay. + */ + if (!vm->resource_name) { + vm->resource_name = kstrdup_const("System RAM (virtio_mem)", + GFP_KERNEL); + if (!vm->resource_name) + return -ENOMEM; + } + dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id); - return add_memory(nid, addr, memory_block_size_bytes()); + return add_memory_driver_managed(nid, addr, memory_block_size_bytes(), + vm->resource_name); } /* @@ -1192,7 +1209,7 @@ static int virtio_mem_mb_plug_any_sb(struct virtio_mem *vm, unsigned long mb_id, VIRTIO_MEM_MB_STATE_OFFLINE); } - return rc; + return 0; } /* @@ -1890,10 +1907,12 @@ static void virtio_mem_remove(struct virtio_device *vdev) vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL] || vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE] || vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL] || - vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE]) + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE]) { dev_warn(&vdev->dev, "device still has system memory added\n"); - else + } else { virtio_mem_delete_resource(vm); + kfree_const(vm->resource_name); + } /* remove all tracking data - no locking needed */ vfree(vm->mb_state); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 176e8a292fd1..c037ef514b64 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -940,7 +940,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; - goto out_put_group; + goto out; } /* @@ -978,7 +978,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = btrfs_orphan_add(trans, BTRFS_I(inode)); if (ret) { btrfs_add_delayed_iput(inode); - goto out_put_group; + goto out; } clear_nlink(inode); /* One for the block groups ref */ @@ -1001,13 +1001,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); if (ret < 0) - goto out_put_group; + goto out; if (ret > 0) btrfs_release_path(path); if (ret == 0) { ret = btrfs_del_item(trans, tree_root, path); if (ret) - goto out_put_group; + goto out; btrfs_release_path(path); } @@ -1016,6 +1016,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, &fs_info->block_group_cache_tree); RB_CLEAR_NODE(&block_group->cache_node); + /* Once for the block groups rbtree */ + btrfs_put_block_group(block_group); + if (fs_info->first_logical_byte == block_group->start) fs_info->first_logical_byte = (u64)-1; spin_unlock(&fs_info->block_group_cache_lock); @@ -1089,6 +1092,25 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, spin_unlock(&block_group->space_info->lock); + /* + * Remove the free space for the block group from the free space tree + * and the block group's item from the extent tree before marking the + * block group as removed. This is to prevent races with tasks that + * freeze and unfreeze a block group, this task and another task + * allocating a new block group - the unfreeze task ends up removing + * the block group's extent map before the task calling this function + * deletes the block group item from the extent tree, allowing for + * another task to attempt to create another block group with the same + * item key (and failing with -EEXIST and a transaction abort). + */ + ret = remove_block_group_free_space(trans, block_group); + if (ret) + goto out; + + ret = remove_block_group_item(trans, path, block_group); + if (ret < 0) + goto out; + mutex_lock(&fs_info->chunk_mutex); spin_lock(&block_group->lock); block_group->removed = 1; @@ -1123,17 +1145,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, mutex_unlock(&fs_info->chunk_mutex); - ret = remove_block_group_free_space(trans, block_group); - if (ret) - goto out_put_group; - - /* Once for the block groups rbtree */ - btrfs_put_block_group(block_group); - - ret = remove_block_group_item(trans, path, block_group); - if (ret < 0) - goto out; - if (remove_em) { struct extent_map_tree *em_tree; @@ -1145,10 +1156,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, free_extent_map(em); } -out_put_group: +out: /* Once for the lookup reference */ btrfs_put_block_group(block_group); -out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1); btrfs_free_path(path); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 30ce7039bc27..d404cce8ae40 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1009,6 +1009,8 @@ enum { BTRFS_ROOT_DEAD_RELOC_TREE, /* Mark dead root stored on device whose cleanup needs to be resumed */ BTRFS_ROOT_DEAD_TREE, + /* The root has a log tree. Used only for subvolume roots. */ + BTRFS_ROOT_HAS_LOG_TREE, }; /* diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 2c14312b05e8..2520605afc25 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1533,7 +1533,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, } static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes) + size_t *write_bytes, bool nowait) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; @@ -1541,27 +1541,43 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, u64 num_bytes; int ret; - if (!btrfs_drew_try_write_lock(&root->snapshot_lock)) + if (!nowait && !btrfs_drew_try_write_lock(&root->snapshot_lock)) return -EAGAIN; lockstart = round_down(pos, fs_info->sectorsize); lockend = round_up(pos + *write_bytes, fs_info->sectorsize) - 1; + num_bytes = lockend - lockstart + 1; - btrfs_lock_and_flush_ordered_range(inode, lockstart, - lockend, NULL); + if (nowait) { + struct btrfs_ordered_extent *ordered; + + if (!try_lock_extent(&inode->io_tree, lockstart, lockend)) + return -EAGAIN; + + ordered = btrfs_lookup_ordered_range(inode, lockstart, + num_bytes); + if (ordered) { + btrfs_put_ordered_extent(ordered); + ret = -EAGAIN; + goto out_unlock; + } + } else { + btrfs_lock_and_flush_ordered_range(inode, lockstart, + lockend, NULL); + } - num_bytes = lockend - lockstart + 1; ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, NULL, NULL, NULL); if (ret <= 0) { ret = 0; - btrfs_drew_write_unlock(&root->snapshot_lock); + if (!nowait) + btrfs_drew_write_unlock(&root->snapshot_lock); } else { *write_bytes = min_t(size_t, *write_bytes , num_bytes - pos + lockstart); } - +out_unlock: unlock_extent(&inode->io_tree, lockstart, lockend); return ret; @@ -1633,7 +1649,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) && check_can_nocow(BTRFS_I(inode), pos, - &write_bytes) > 0) { + &write_bytes, false) > 0) { /* * For nodata cow case, no need to reserve * data space. @@ -1904,13 +1920,25 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, pos = iocb->ki_pos; count = iov_iter_count(from); if (iocb->ki_flags & IOCB_NOWAIT) { + size_t nocow_bytes = count; + /* * We will allocate space in case nodatacow is not set, * so bail */ if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) || - check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { + check_can_nocow(BTRFS_I(inode), pos, &nocow_bytes, + true) <= 0) { + inode_unlock(inode); + return -EAGAIN; + } + /* + * There are holes in the range or parts of the range that must + * be COWed (shared extents, RO block groups, etc), so just bail + * out. + */ + if (nocow_bytes < count) { inode_unlock(inode); return -EAGAIN; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d04c82c88418..18d384f4af54 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -985,6 +985,7 @@ static noinline int cow_file_range(struct inode *inode, u64 num_bytes; unsigned long ram_size; u64 cur_alloc_size = 0; + u64 min_alloc_size; u64 blocksize = fs_info->sectorsize; struct btrfs_key ins; struct extent_map *em; @@ -1035,10 +1036,26 @@ static noinline int cow_file_range(struct inode *inode, btrfs_drop_extent_cache(BTRFS_I(inode), start, start + num_bytes - 1, 0); + /* + * Relocation relies on the relocated extents to have exactly the same + * size as the original extents. Normally writeback for relocation data + * extents follows a NOCOW path because relocation preallocates the + * extents. However, due to an operation such as scrub turning a block + * group to RO mode, it may fallback to COW mode, so we must make sure + * an extent allocated during COW has exactly the requested size and can + * not be split into smaller extents, otherwise relocation breaks and + * fails during the stage where it updates the bytenr of file extent + * items. + */ + if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID) + min_alloc_size = num_bytes; + else + min_alloc_size = fs_info->sectorsize; + while (num_bytes > 0) { cur_alloc_size = num_bytes; ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size, - fs_info->sectorsize, 0, alloc_hint, + min_alloc_size, 0, alloc_hint, &ins, 1, 1); if (ret < 0) goto out_unlock; @@ -1361,6 +1378,8 @@ static int fallback_to_cow(struct inode *inode, struct page *locked_page, int *page_started, unsigned long *nr_written) { const bool is_space_ino = btrfs_is_free_space_inode(BTRFS_I(inode)); + const bool is_reloc_ino = (BTRFS_I(inode)->root->root_key.objectid == + BTRFS_DATA_RELOC_TREE_OBJECTID); const u64 range_bytes = end + 1 - start; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; u64 range_start = start; @@ -1391,18 +1410,23 @@ static int fallback_to_cow(struct inode *inode, struct page *locked_page, * data space info, which we incremented in the step above. * * If we need to fallback to cow and the inode corresponds to a free - * space cache inode, we must also increment bytes_may_use of the data - * space_info for the same reason. Space caches always get a prealloc + * space cache inode or an inode of the data relocation tree, we must + * also increment bytes_may_use of the data space_info for the same + * reason. Space caches and relocated data extents always get a prealloc * extent for them, however scrub or balance may have set the block - * group that contains that extent to RO mode. + * group that contains that extent to RO mode and therefore force COW + * when starting writeback. */ count = count_range_bits(io_tree, &range_start, end, range_bytes, EXTENT_NORESERVE, 0); - if (count > 0 || is_space_ino) { - const u64 bytes = is_space_ino ? range_bytes : count; + if (count > 0 || is_space_ino || is_reloc_ino) { + u64 bytes = count; struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; struct btrfs_space_info *sinfo = fs_info->data_sinfo; + if (is_space_ino || is_reloc_ino) + bytes = range_bytes; + spin_lock(&sinfo->lock); btrfs_space_info_update_bytes_may_use(fs_info, sinfo, bytes); spin_unlock(&sinfo->lock); @@ -7865,9 +7889,6 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) dio_data.overwrite = 1; inode_unlock(inode); relock = true; - } else if (iocb->ki_flags & IOCB_NOWAIT) { - ret = -EAGAIN; - goto out; } ret = btrfs_delalloc_reserve_space(inode, &data_reserved, offset, count); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 168deb8ef68a..e8f7c5f00894 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2692,7 +2692,7 @@ out: btrfs_put_root(root); out_free: btrfs_free_path(path); - kzfree(subvol_info); + kfree(subvol_info); return ret; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 920cee312f4e..cd5348f352dd 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -169,6 +169,7 @@ static int start_log_trans(struct btrfs_trans_handle *trans, if (ret) goto out; + set_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; } @@ -195,6 +196,9 @@ static int join_running_log_trans(struct btrfs_root *root) { int ret = -ENOENT; + if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state)) + return ret; + mutex_lock(&root->log_mutex); if (root->log_root) { ret = 0; @@ -3303,6 +3307,7 @@ int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root) if (root->log_root) { free_log_tree(trans, root->log_root); root->log_root = NULL; + clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); } return 0; } diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index 7824f5563a55..9b66c28b3ae9 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -144,22 +144,22 @@ static inline void z_erofs_onlinepage_init(struct page *page) static inline void z_erofs_onlinepage_fixup(struct page *page, uintptr_t index, bool down) { - unsigned long *p, o, v, id; -repeat: - p = &page_private(page); - o = READ_ONCE(*p); + union z_erofs_onlinepage_converter u = { .v = &page_private(page) }; + int orig, orig_index, val; - id = o >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT; - if (id) { +repeat: + orig = atomic_read(u.o); + orig_index = orig >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT; + if (orig_index) { if (!index) return; - DBG_BUGON(id != index); + DBG_BUGON(orig_index != index); } - v = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) | - ((o & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down); - if (cmpxchg(p, o, v) != o) + val = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) | + ((orig & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down); + if (atomic_cmpxchg(u.o, orig, val) != orig) goto repeat; } diff --git a/fs/file_table.c b/fs/file_table.c index 656647f9575a..65603502fed6 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -230,7 +230,7 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, d_set_d_op(path.dentry, &anon_ops); path.mnt = mntget(mnt); d_instantiate(path.dentry, inode); - file = alloc_file(&path, flags, fops); + file = alloc_file(&path, flags | FMODE_NONOTIFY, fops); if (IS_ERR(file)) { ihold(inode); path_put(&path); diff --git a/fs/io_uring.c b/fs/io_uring.c index a78201b96179..e507737f044e 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -890,6 +890,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, struct io_uring_files_update *ip, unsigned nr_args); static int io_grab_files(struct io_kiocb *req); +static void io_complete_rw_common(struct kiocb *kiocb, long res); static void io_cleanup_req(struct io_kiocb *req); static int io_file_get(struct io_submit_state *state, struct io_kiocb *req, int fd, struct file **out_file, bool fixed); @@ -1749,6 +1750,14 @@ static void io_iopoll_queue(struct list_head *again) do { req = list_first_entry(again, struct io_kiocb, list); list_del(&req->list); + + /* shouldn't happen unless io_uring is dying, cancel reqs */ + if (unlikely(!current->mm)) { + io_complete_rw_common(&req->rw.kiocb, -EAGAIN); + io_put_req(req); + continue; + } + refcount_inc(&req->refs); io_queue_async_work(req); } while (!list_empty(again)); @@ -1994,10 +2003,8 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) WRITE_ONCE(req->result, res); /* order with io_poll_complete() checking ->result */ - if (res != -EAGAIN) { - smp_wmb(); - WRITE_ONCE(req->iopoll_completed, 1); - } + smp_wmb(); + WRITE_ONCE(req->iopoll_completed, 1); } /* @@ -5353,9 +5360,6 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) { const bool in_async = io_wq_current_is_worker(); - if (req->result == -EAGAIN) - return -EAGAIN; - /* workqueue context doesn't hold uring_lock, grab it now */ if (in_async) mutex_lock(&ctx->uring_lock); @@ -6011,7 +6015,7 @@ static int io_sq_thread(void *data) * If submit got -EBUSY, flag us as needing the application * to enter the kernel to reap and flush events. */ - if (!to_submit || ret == -EBUSY) { + if (!to_submit || ret == -EBUSY || need_resched()) { /* * Drop cur_mm before scheduling, we can't hold it for * long periods (or over schedule()). Do this before @@ -6027,7 +6031,7 @@ static int io_sq_thread(void *data) * more IO, we should wait for the application to * reap events and wake us up. */ - if (!list_empty(&ctx->poll_list) || + if (!list_empty(&ctx->poll_list) || need_resched() || (!time_after(jiffies, timeout) && ret != -EBUSY && !percpu_ref_is_dying(&ctx->refs))) { if (current->task_works) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1b79dd5cf661..3d113cf8908a 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -267,8 +267,6 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) { struct inode *inode = dreq->inode; - inode_dio_end(inode); - if (dreq->iocb) { long res = (long) dreq->error; if (dreq->count != 0) { @@ -280,7 +278,10 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) complete(&dreq->completion); + igrab(inode); nfs_direct_req_release(dreq); + inode_dio_end(inode); + iput(inode); } static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) @@ -410,8 +411,10 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * generic layer handle the completion. */ if (requested_bytes == 0) { - inode_dio_end(inode); + igrab(inode); nfs_direct_req_release(dreq); + inode_dio_end(inode); + iput(inode); return result < 0 ? result : -EIO; } @@ -864,8 +867,10 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * generic layer handle the completion. */ if (requested_bytes == 0) { - inode_dio_end(inode); + igrab(inode); nfs_direct_req_release(dreq); + inode_dio_end(inode); + iput(inode); return result < 0 ? result : -EIO; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index f96367a2463e..ccd6c1637b27 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -83,6 +83,7 @@ nfs_file_release(struct inode *inode, struct file *filp) dprintk("NFS: release(%pD2)\n", filp); nfs_inc_stats(inode, NFSIOS_VFSRELEASE); + inode_dio_wait(inode); nfs_file_clear_open_context(filp); return 0; } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 7d399f72ebbb..de03e440b7ee 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -907,9 +907,8 @@ retry: goto out_mds; /* Use a direct mapping of ds_idx to pgio mirror_idx */ - if (WARN_ON_ONCE(pgio->pg_mirror_count != - FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))) - goto out_mds; + if (pgio->pg_mirror_count != FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg)) + goto out_eagain; for (i = 0; i < pgio->pg_mirror_count; i++) { mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); @@ -931,7 +930,10 @@ retry: (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)) pgio->pg_maxretrans = io_maxretrans; return; - +out_eagain: + pnfs_generic_pg_cleanup(pgio); + pgio->pg_error = -EAGAIN; + return; out_mds: trace_pnfs_mds_fallback_pg_init_write(pgio->pg_inode, 0, NFS4_MAX_UINT64, IOMODE_RW, @@ -941,6 +943,7 @@ out_mds: pgio->pg_lseg = NULL; pgio->pg_maxretrans = 0; nfs_pageio_reset_write_mds(pgio); + pgio->pg_error = -EAGAIN; } static unsigned int diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index a3ab6e219061..873342308dc0 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -308,6 +308,7 @@ static int try_location(struct fs_context *fc, if (IS_ERR(export_path)) return PTR_ERR(export_path); + kfree(ctx->nfs_server.export_path); ctx->nfs_server.export_path = export_path; source = kmalloc(len + 1 + ctx->nfs_server.export_path_len + 1, diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 152a0fc4e905..751bc4dc7466 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -689,6 +689,12 @@ static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res, &ocfs2_nfs_sync_lops, osb); } +static void ocfs2_nfs_sync_lock_init(struct ocfs2_super *osb) +{ + ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb); + init_rwsem(&osb->nfs_sync_rwlock); +} + void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb) { struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres; @@ -2855,6 +2861,11 @@ int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex) if (ocfs2_is_hard_readonly(osb)) return -EROFS; + if (ex) + down_write(&osb->nfs_sync_rwlock); + else + down_read(&osb->nfs_sync_rwlock); + if (ocfs2_mount_local(osb)) return 0; @@ -2873,6 +2884,10 @@ void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex) if (!ocfs2_mount_local(osb)) ocfs2_cluster_unlock(osb, lockres, ex ? LKM_EXMODE : LKM_PRMODE); + if (ex) + up_write(&osb->nfs_sync_rwlock); + else + up_read(&osb->nfs_sync_rwlock); } int ocfs2_trim_fs_lock(struct ocfs2_super *osb, @@ -3340,7 +3355,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb) local: ocfs2_super_lock_res_init(&osb->osb_super_lockres, osb); ocfs2_rename_lock_res_init(&osb->osb_rename_lockres, osb); - ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb); + ocfs2_nfs_sync_lock_init(osb); ocfs2_orphan_scan_lock_res_init(&osb->osb_orphan_scan.os_lockres, osb); osb->cconn = conn; diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index ee5d98516212..2dd71d626196 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -395,6 +395,7 @@ struct ocfs2_super struct ocfs2_lock_res osb_super_lockres; struct ocfs2_lock_res osb_rename_lockres; struct ocfs2_lock_res osb_nfs_sync_lockres; + struct rw_semaphore nfs_sync_rwlock; struct ocfs2_lock_res osb_trim_fs_lockres; struct mutex obs_trim_fs_mutex; struct ocfs2_dlm_debug *osb_dlm_debug; diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 0dd8c41bafd4..19137c6d087b 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -290,7 +290,7 @@ #define OCFS2_MAX_SLOTS 255 /* Slot map indicator for an empty slot */ -#define OCFS2_INVALID_SLOT -1 +#define OCFS2_INVALID_SLOT ((u16)-1) #define OCFS2_VOL_UUID_LEN 16 #define OCFS2_MAX_VOL_LABEL_LEN 64 @@ -326,8 +326,8 @@ struct ocfs2_system_inode_info { enum { BAD_BLOCK_SYSTEM_INODE = 0, GLOBAL_INODE_ALLOC_SYSTEM_INODE, +#define OCFS2_FIRST_ONLINE_SYSTEM_INODE GLOBAL_INODE_ALLOC_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE, -#define OCFS2_FIRST_ONLINE_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE HEARTBEAT_SYSTEM_INODE, GLOBAL_BITMAP_SYSTEM_INODE, USER_QUOTA_SYSTEM_INODE, diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 4836becb7578..45745cc3408a 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -2825,9 +2825,12 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res) goto bail; } - inode_alloc_inode = - ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE, - suballoc_slot); + if (suballoc_slot == (u16)OCFS2_INVALID_SLOT) + inode_alloc_inode = ocfs2_get_system_file_inode(osb, + GLOBAL_INODE_ALLOC_SYSTEM_INODE, suballoc_slot); + else + inode_alloc_inode = ocfs2_get_system_file_inode(osb, + INODE_ALLOC_SYSTEM_INODE, suballoc_slot); if (!inode_alloc_inode) { /* the error code could be inaccurate, but we are not able to * get the correct one. */ diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index 907fa5d16494..4a674db4e1fa 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -2,6 +2,11 @@ #ifndef _ASM_GENERIC_CACHEFLUSH_H #define _ASM_GENERIC_CACHEFLUSH_H +struct mm_struct; +struct vm_area_struct; +struct page; +struct address_space; + /* * The cache doesn't need to be flushed when TLB entries change when * the cache is mapped to physical memory, not virtual memory diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 136f984df0d9..cdfa400f89b3 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -77,8 +77,6 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); -struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, - gfp_t gfp, unsigned long attrs); int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); diff --git a/include/linux/host1x.h b/include/linux/host1x.h index c230b4e70d75..a3a568bf9686 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -48,6 +48,9 @@ struct host1x_client_ops { * @channel: host1x channel associated with this client * @syncpts: array of syncpoints requested for this client * @num_syncpts: number of syncpoints requested for this client + * @parent: pointer to parent structure + * @usecount: reference count for this structure + * @lock: mutex for mutually exclusive concurrency */ struct host1x_client { struct list_head list; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4100bd224f5c..3e8fa1c7a1e6 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -41,6 +41,7 @@ #define DMA_PTE_SNP BIT_ULL(11) #define DMA_FL_PTE_PRESENT BIT_ULL(0) +#define DMA_FL_PTE_US BIT_ULL(2) #define DMA_FL_PTE_XD BIT_ULL(63) #define ADDR_WIDTH_5LEVEL (57) diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index c62d76478adc..529116b0cabe 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -276,8 +276,7 @@ struct kgdb_arch { * the I/O driver. * @post_exception: Pointer to a function that will do any cleanup work * for the I/O driver. - * @is_console: 1 if the end device is a console 0 if the I/O device is - * not a console + * @cons: valid if the I/O device is a console; else NULL. */ struct kgdb_io { const char *name; @@ -288,7 +287,7 @@ struct kgdb_io { void (*deinit) (void); void (*pre_exception) (void); void (*post_exception) (void); - int is_console; + struct console *cons; }; extern const struct kgdb_arch arch_kgdb_ops; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 116bd9bb347f..ca1887dd0423 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4283,7 +4283,8 @@ struct mlx5_ifc_rst2init_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_rst2init_qp_in_bits { @@ -4300,7 +4301,7 @@ struct mlx5_ifc_rst2init_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; @@ -6619,7 +6620,8 @@ struct mlx5_ifc_init2init_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_init2init_qp_in_bits { @@ -6636,7 +6638,7 @@ struct mlx5_ifc_init2init_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c4c37fd12104..f6f884970511 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -257,8 +257,8 @@ struct lruvec { */ unsigned long anon_cost; unsigned long file_cost; - /* Evictions & activations on the inactive file list */ - atomic_long_t inactive_age; + /* Non-resident age, driven by LRU movement */ + atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults; /* Various lruvec state flags (enum lruvec_flags) */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6fc613ed8eae..39e28e11863c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3157,7 +3157,7 @@ static inline int dev_recursion_level(void) return this_cpu_read(softnet_data.xmit.recursion); } -#define XMIT_RECURSION_LIMIT 10 +#define XMIT_RECURSION_LIMIT 8 static inline bool dev_xmit_recursion(void) { return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index b394bd4f68a3..c4676d6feeff 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -25,6 +25,12 @@ int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); + +void ipt_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); + +void ipt_unregister_table_exit(struct net *net, struct xt_table *table); + void ipt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops); diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 8225f7821a29..1547d5f9ae06 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -29,6 +29,9 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, const struct nf_hook_ops *ops, struct xt_table **res); void ip6t_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops); +void ip6t_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); +void ip6t_unregister_table_exit(struct net *net, struct xt_table *table); extern unsigned int ip6t_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/phy.h b/include/linux/phy.h index 8c05d0fb5c00..b693b609b2f5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1416,6 +1416,7 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev, int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd); +int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 733fad7dfbed..6d15040c642c 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -207,28 +207,34 @@ static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain) static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) { + u16 elem_per_page = p_chain->elem_per_page; + u32 prod = p_chain->u.chain16.prod_idx; + u32 cons = p_chain->u.chain16.cons_idx; u16 used; - used = (u16) (((u32)0x10000 + - (u32)p_chain->u.chain16.prod_idx) - - (u32)p_chain->u.chain16.cons_idx); + if (prod < cons) + prod += (u32)U16_MAX + 1; + + used = (u16)(prod - cons); if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= p_chain->u.chain16.prod_idx / p_chain->elem_per_page - - p_chain->u.chain16.cons_idx / p_chain->elem_per_page; + used -= prod / elem_per_page - cons / elem_per_page; return (u16)(p_chain->capacity - used); } static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain) { + u16 elem_per_page = p_chain->elem_per_page; + u64 prod = p_chain->u.chain32.prod_idx; + u64 cons = p_chain->u.chain32.cons_idx; u32 used; - used = (u32) (((u64)0x100000000ULL + - (u64)p_chain->u.chain32.prod_idx) - - (u64)p_chain->u.chain32.cons_idx); + if (prod < cons) + prod += (u64)U32_MAX + 1; + + used = (u32)(prod - cons); if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= p_chain->u.chain32.prod_idx / p_chain->elem_per_page - - p_chain->u.chain32.cons_idx / p_chain->elem_per_page; + used -= (u32)(prod / elem_per_page - cons / elem_per_page); return p_chain->capacity - used; } diff --git a/include/linux/swap.h b/include/linux/swap.h index 4c5974bb9ba9..5b3216ba39a9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -313,6 +313,7 @@ struct vma_swap_readahead { }; /* linux/mm/workingset.c */ +void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 48bb681e6c2a..0221f852a7e1 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -106,7 +106,6 @@ extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); extern void *vzalloc_node(unsigned long size, int node); -extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index f2c8311a0433..6315324b9dc2 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -450,6 +450,7 @@ struct flow_block_indr { struct net_device *dev; enum flow_block_binder_type binder_type; void *data; + void *cb_priv; void (*cleanup)(struct flow_block_cb *block_cb); }; @@ -467,6 +468,13 @@ struct flow_block_cb { struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)); +struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb, + void *cb_ident, void *cb_priv, + void (*release)(void *cb_priv), + struct flow_block_offload *bo, + struct net_device *dev, void *data, + void *indr_cb_priv, + void (*cleanup)(struct flow_block_cb *block_cb)); void flow_block_cb_free(struct flow_block_cb *block_cb); struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block, @@ -488,6 +496,13 @@ static inline void flow_block_cb_remove(struct flow_block_cb *block_cb, list_move(&block_cb->list, &offload->cb_list); } +static inline void flow_indr_block_cb_remove(struct flow_block_cb *block_cb, + struct flow_block_offload *offload) +{ + list_del(&block_cb->indr.list); + list_move(&block_cb->list, &offload->cb_list); +} + bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident, struct list_head *driver_block_list); @@ -532,11 +547,13 @@ static inline void flow_block_init(struct flow_block *flow_block) } typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, - enum tc_setup_type type, void *type_data); + enum tc_setup_type type, void *type_data, + void *data, + void (*cleanup)(struct flow_block_cb *block_cb)); int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv); void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv, - flow_setup_cb_t *setup_cb); + void (*release)(void *cb_priv)); int flow_indr_dev_setup_offload(struct net_device *dev, enum tc_setup_type type, void *data, struct flow_block_offload *bo, diff --git a/include/net/gue.h b/include/net/gue.h index 3a6595bfa641..e42402f180b7 100644 --- a/include/net/gue.h +++ b/include/net/gue.h @@ -21,7 +21,7 @@ * | | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * - * C bit indicates contol message when set, data message when unset. + * C bit indicates control message when set, data message when unset. * For a control message, proto/ctype is interpreted as a type of * control message. For data messages, proto/ctype is the IP protocol * of the next header. diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 15b4d9aec7ff..122d9e2d8dfd 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -353,11 +353,13 @@ enum { ipv4_is_anycast_6to4(a)) /* Flags used for the bind address copy functions. */ -#define SCTP_ADDR6_ALLOWED 0x00000001 /* IPv6 address is allowed by +#define SCTP_ADDR4_ALLOWED 0x00000001 /* IPv4 address is allowed by local sock family */ -#define SCTP_ADDR4_PEERSUPP 0x00000002 /* IPv4 address is supported by +#define SCTP_ADDR6_ALLOWED 0x00000002 /* IPv6 address is allowed by + local sock family */ +#define SCTP_ADDR4_PEERSUPP 0x00000004 /* IPv4 address is supported by peer */ -#define SCTP_ADDR6_PEERSUPP 0x00000004 /* IPv6 address is supported by +#define SCTP_ADDR6_PEERSUPP 0x00000008 /* IPv6 address is supported by peer */ /* Reasons to retransmit. */ diff --git a/include/net/sock.h b/include/net/sock.h index c53cc42b5ab9..3428619faae4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1848,7 +1848,6 @@ static inline int sk_rx_queue_get(const struct sock *sk) static inline void sk_set_socket(struct sock *sk, struct socket *sock) { - sk_tx_queue_clear(sk); sk->sk_socket = sock; } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 094fe682f5d7..c7d213c9f9d8 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1008,6 +1008,7 @@ struct xfrm_offload { #define XFRM_GRO 32 #define XFRM_ESP_NO_TRAILER 64 #define XFRM_DEV_RESUME 128 +#define XFRM_XMIT 256 __u32 status; #define CRYPTO_SUCCESS 1 diff --git a/include/sound/dmaengine_pcm.h b/include/sound/dmaengine_pcm.h index b65220685920..8c5e38180fb0 100644 --- a/include/sound/dmaengine_pcm.h +++ b/include/sound/dmaengine_pcm.h @@ -161,4 +161,15 @@ int snd_dmaengine_pcm_prepare_slave_config(struct snd_pcm_substream *substream, #define SND_DMAENGINE_PCM_DRV_NAME "snd_dmaengine_pcm" +struct dmaengine_pcm { + struct dma_chan *chan[SNDRV_PCM_STREAM_LAST + 1]; + const struct snd_dmaengine_pcm_config *config; + struct snd_soc_component component; + unsigned int flags; +}; + +static inline struct dmaengine_pcm *soc_component_to_pcm(struct snd_soc_component *p) +{ + return container_of(p, struct dmaengine_pcm, component); +} #endif diff --git a/include/sound/soc.h b/include/sound/soc.h index ef5dd28e10a9..2756f9bcac3e 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -444,6 +444,8 @@ int devm_snd_soc_register_component(struct device *dev, const struct snd_soc_component_driver *component_driver, struct snd_soc_dai_driver *dai_drv, int num_dai); void snd_soc_unregister_component(struct device *dev); +struct snd_soc_component *snd_soc_lookup_component_nolocked(struct device *dev, + const char *driver_name); struct snd_soc_component *snd_soc_lookup_component(struct device *dev, const char *driver_name); @@ -1361,6 +1363,10 @@ void snd_soc_remove_pcm_runtime(struct snd_soc_card *card, struct snd_soc_dai *snd_soc_register_dai(struct snd_soc_component *component, struct snd_soc_dai_driver *dai_drv, bool legacy_dai_naming); +struct snd_soc_dai *devm_snd_soc_register_dai(struct device *dev, + struct snd_soc_component *component, + struct snd_soc_dai_driver *dai_drv, + bool legacy_dai_naming); void snd_soc_unregister_dai(struct snd_soc_dai *dai); struct snd_soc_dai *snd_soc_find_dai( diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index ba9efdc848f9..059b6e45a028 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -400,7 +400,7 @@ enum rxrpc_tx_point { EM(rxrpc_cong_begin_retransmission, " Retrans") \ EM(rxrpc_cong_cleared_nacks, " Cleared") \ EM(rxrpc_cong_new_low_nack, " NewLowN") \ - EM(rxrpc_cong_no_change, "") \ + EM(rxrpc_cong_no_change, " -") \ EM(rxrpc_cong_progress, " Progres") \ EM(rxrpc_cong_retransmit_again, " ReTxAgn") \ EM(rxrpc_cong_rtt_window_end, " RttWinE") \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 19684813faae..974a71342aea 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3168,7 +3168,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) + * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) * Description * Copy *size* bytes from *data* into a ring buffer *ringbuf*. * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index b6aac7ee1f67..4c14e8be7267 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -205,6 +205,7 @@ struct fb_bitfield { #define FB_ACTIVATE_ALL 64 /* change all VCs on this fb */ #define FB_ACTIVATE_FORCE 128 /* force apply even when no change*/ #define FB_ACTIVATE_INV_MODE 256 /* invalidate videomode */ +#define FB_ACTIVATE_KD_TEXT 512 /* for KDSET vt ioctl */ #define FB_ACCELF_TEXT 1 /* (OBSOLETE) see fb_info.flags and vc_mode */ diff --git a/include/uapi/linux/mrp_bridge.h b/include/uapi/linux/mrp_bridge.h index 84f15f48a7cb..bee366540212 100644 --- a/include/uapi/linux/mrp_bridge.h +++ b/include/uapi/linux/mrp_bridge.h @@ -36,7 +36,6 @@ enum br_mrp_port_state_type { enum br_mrp_port_role_type { BR_MRP_PORT_ROLE_PRIMARY, BR_MRP_PORT_ROLE_SECONDARY, - BR_MRP_PORT_ROLE_NONE, }; enum br_mrp_tlv_header_type { diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index cba368e55863..c21edb966c19 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -64,10 +64,12 @@ /* supported values for SO_RDS_TRANSPORT */ #define RDS_TRANS_IB 0 -#define RDS_TRANS_IWARP 1 +#define RDS_TRANS_GAP 1 #define RDS_TRANS_TCP 2 #define RDS_TRANS_COUNT 3 #define RDS_TRANS_NONE (~0) +/* don't use RDS_TRANS_IWARP - it is deprecated */ +#define RDS_TRANS_IWARP RDS_TRANS_GAP /* IOCTLS commands for SOL_RDS */ #define SIOCRDSSETTOS (SIOCPROTOPRIVATE) diff --git a/include/uapi/linux/spi/spidev.h b/include/uapi/linux/spi/spidev.h index ee0f2460bff6..d56427c0b3e0 100644 --- a/include/uapi/linux/spi/spidev.h +++ b/include/uapi/linux/spi/spidev.h @@ -48,6 +48,10 @@ #define SPI_TX_QUAD 0x200 #define SPI_RX_DUAL 0x400 #define SPI_RX_QUAD 0x800 +#define SPI_CS_WORD 0x1000 +#define SPI_TX_OCTAL 0x2000 +#define SPI_RX_OCTAL 0x4000 +#define SPI_3WIRE_HIZ 0x8000 /*---------------------------------------------------------------------------*/ diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4d76f16524cc..ac53102e244a 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1276,16 +1276,23 @@ static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp, static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) { - if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0) + if (unlikely(max_optlen < 0)) return -EINVAL; + if (unlikely(max_optlen > PAGE_SIZE)) { + /* We don't expose optvals that are greater than PAGE_SIZE + * to the BPF program. + */ + max_optlen = PAGE_SIZE; + } + ctx->optval = kzalloc(max_optlen, GFP_USER); if (!ctx->optval) return -ENOMEM; ctx->optval_end = ctx->optval + max_optlen; - return 0; + return max_optlen; } static void sockopt_free_buf(struct bpf_sockopt_kern *ctx) @@ -1319,13 +1326,13 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, */ max_optlen = max_t(int, 16, *optlen); - ret = sockopt_alloc_buf(&ctx, max_optlen); - if (ret) - return ret; + max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + if (max_optlen < 0) + return max_optlen; ctx.optlen = *optlen; - if (copy_from_user(ctx.optval, optval, *optlen) != 0) { + if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) { ret = -EFAULT; goto out; } @@ -1353,8 +1360,14 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, /* export any potential modifications */ *level = ctx.level; *optname = ctx.optname; - *optlen = ctx.optlen; - *kernel_optval = ctx.optval; + + /* optlen == 0 from BPF indicates that we should + * use original userspace data. + */ + if (ctx.optlen != 0) { + *optlen = ctx.optlen; + *kernel_optval = ctx.optval; + } } out: @@ -1385,12 +1398,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT)) return retval; - ret = sockopt_alloc_buf(&ctx, max_optlen); - if (ret) - return ret; - ctx.optlen = max_optlen; + max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + if (max_optlen < 0) + return max_optlen; + if (!retval) { /* If kernel getsockopt finished successfully, * copy whatever was returned to the user back @@ -1404,10 +1417,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } - if (ctx.optlen > max_optlen) - ctx.optlen = max_optlen; - - if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) { + if (copy_from_user(ctx.optval, optval, + min(ctx.optlen, max_optlen)) != 0) { ret = -EFAULT; goto out; } @@ -1436,10 +1447,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } - if (copy_to_user(optval, ctx.optval, ctx.optlen) || - put_user(ctx.optlen, optlen)) { - ret = -EFAULT; - goto out; + if (ctx.optlen != 0) { + if (copy_to_user(optval, ctx.optval, ctx.optlen) || + put_user(ctx.optlen, optlen)) { + ret = -EFAULT; + goto out; + } } ret = ctx.retval; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 0cbb72cdaf63..5fdbc776a760 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -86,12 +86,13 @@ static DEFINE_PER_CPU(struct list_head, dev_flush_list); static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); -static struct hlist_head *dev_map_create_hash(unsigned int entries) +static struct hlist_head *dev_map_create_hash(unsigned int entries, + int numa_node) { int i; struct hlist_head *hash; - hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL); + hash = bpf_map_area_alloc(entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); @@ -145,7 +146,8 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) return -EINVAL; if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { - dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets); + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, + dtab->map.numa_node); if (!dtab->dev_index_head) goto free_charge; @@ -232,7 +234,7 @@ static void dev_map_free(struct bpf_map *map) } } - kfree(dtab->dev_index_head); + bpf_map_area_free(dtab->dev_index_head); } else { for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index bc8d25f2ac8a..9e5934780f41 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -587,6 +587,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs, arch_kgdb_ops.disable_hw_break(regs); acquirelock: + rcu_read_lock(); /* * Interrupts will be restored by the 'trap return' code, except when * single stepping. @@ -646,6 +647,7 @@ return_normal: atomic_dec(&slaves_in_kgdb); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); return 0; } cpu_relax(); @@ -664,6 +666,7 @@ return_normal: raw_spin_unlock(&dbg_master_lock); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); goto acquirelock; } @@ -787,6 +790,7 @@ kgdb_restore: raw_spin_unlock(&dbg_master_lock); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); return kgdb_info[cpu].ret_state; } diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 924bc9298a42..683a799618ad 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -542,6 +542,44 @@ static int kdb_search_string(char *searched, char *searchfor) return 0; } +static void kdb_msg_write(const char *msg, int msg_len) +{ + struct console *c; + + if (msg_len == 0) + return; + + if (dbg_io_ops) { + const char *cp = msg; + int len = msg_len; + + while (len--) { + dbg_io_ops->write_char(*cp); + cp++; + } + } + + for_each_console(c) { + if (!(c->flags & CON_ENABLED)) + continue; + if (c == dbg_io_ops->cons) + continue; + /* + * Set oops_in_progress to encourage the console drivers to + * disregard their internal spin locks: in the current calling + * context the risk of deadlock is a bigger problem than risks + * due to re-entering the console driver. We operate directly on + * oops_in_progress rather than using bust_spinlocks() because + * the calls bust_spinlocks() makes on exit are not appropriate + * for this calling context. + */ + ++oops_in_progress; + c->write(c, msg, msg_len); + --oops_in_progress; + touch_nmi_watchdog(); + } +} + int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) { int diag; @@ -553,7 +591,6 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) int this_cpu, old_cpu; char *cp, *cp2, *cphold = NULL, replaced_byte = ' '; char *moreprompt = "more> "; - struct console *c; unsigned long uninitialized_var(flags); /* Serialize kdb_printf if multiple cpus try to write at once. @@ -687,22 +724,11 @@ kdb_printit: */ retlen = strlen(kdb_buffer); cp = (char *) printk_skip_headers(kdb_buffer); - if (!dbg_kdb_mode && kgdb_connected) { + if (!dbg_kdb_mode && kgdb_connected) gdbstub_msg_write(cp, retlen - (cp - kdb_buffer)); - } else { - if (dbg_io_ops && !dbg_io_ops->is_console) { - len = retlen - (cp - kdb_buffer); - cp2 = cp; - while (len--) { - dbg_io_ops->write_char(*cp2); - cp2++; - } - } - for_each_console(c) { - c->write(c, cp, retlen - (cp - kdb_buffer)); - touch_nmi_watchdog(); - } - } + else + kdb_msg_write(cp, retlen - (cp - kdb_buffer)); + if (logging) { saved_loglevel = console_loglevel; console_loglevel = CONSOLE_LOGLEVEL_SILENT; @@ -751,19 +777,7 @@ kdb_printit: moreprompt = "more> "; kdb_input_flush(); - - if (dbg_io_ops && !dbg_io_ops->is_console) { - len = strlen(moreprompt); - cp = moreprompt; - while (len--) { - dbg_io_ops->write_char(*cp); - cp++; - } - } - for_each_console(c) { - c->write(c, moreprompt, strlen(moreprompt)); - touch_nmi_watchdog(); - } + kdb_msg_write(moreprompt, strlen(moreprompt)); if (logging) printk("%s", moreprompt); diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index a0ce3c1494fd..1da3f44f2565 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -71,15 +71,16 @@ config SWIOTLB # in the pagetables # config DMA_NONCOHERENT_MMAP + default y if !MMU bool config DMA_COHERENT_POOL + select GENERIC_ALLOCATOR bool config DMA_REMAP bool depends on MMU - select GENERIC_ALLOCATOR select DMA_NONCOHERENT_MMAP config DMA_DIRECT_REMAP diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 0a4881e59aa7..93f578a8e613 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -109,14 +109,15 @@ static inline bool dma_should_free_from_pool(struct device *dev, return false; } -struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, +static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp_t gfp, unsigned long attrs) { - size_t alloc_size = PAGE_ALIGN(size); int node = dev_to_node(dev); struct page *page = NULL; u64 phys_limit; + WARN_ON_ONCE(!PAGE_ALIGNED(size)); + if (attrs & DMA_ATTR_NO_WARN) gfp |= __GFP_NOWARN; @@ -124,14 +125,14 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp &= ~__GFP_ZERO; gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, &phys_limit); - page = dma_alloc_contiguous(dev, alloc_size, gfp); + page = dma_alloc_contiguous(dev, size, gfp); if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { - dma_free_contiguous(dev, page, alloc_size); + dma_free_contiguous(dev, page, size); page = NULL; } again: if (!page) - page = alloc_pages_node(node, gfp, get_order(alloc_size)); + page = alloc_pages_node(node, gfp, get_order(size)); if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { dma_free_contiguous(dev, page, size); page = NULL; @@ -157,9 +158,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, { struct page *page; void *ret; + int err; + + size = PAGE_ALIGN(size); if (dma_should_alloc_from_pool(dev, gfp, attrs)) { - ret = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &page, gfp); + ret = dma_alloc_from_pool(dev, size, &page, gfp); if (!ret) return NULL; goto done; @@ -183,14 +187,20 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, dma_alloc_need_uncached(dev, attrs)) || (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) { /* remove any dirty cache lines on the kernel alias */ - arch_dma_prep_coherent(page, PAGE_ALIGN(size)); + arch_dma_prep_coherent(page, size); /* create a coherent mapping */ - ret = dma_common_contiguous_remap(page, PAGE_ALIGN(size), + ret = dma_common_contiguous_remap(page, size, dma_pgprot(dev, PAGE_KERNEL, attrs), __builtin_return_address(0)); if (!ret) goto out_free_pages; + if (force_dma_unencrypted(dev)) { + err = set_memory_decrypted((unsigned long)ret, + 1 << get_order(size)); + if (err) + goto out_free_pages; + } memset(ret, 0, size); goto done; } @@ -207,8 +217,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, } ret = page_address(page); - if (force_dma_unencrypted(dev)) - set_memory_decrypted((unsigned long)ret, 1 << get_order(size)); + if (force_dma_unencrypted(dev)) { + err = set_memory_decrypted((unsigned long)ret, + 1 << get_order(size)); + if (err) + goto out_free_pages; + } memset(ret, 0, size); @@ -217,7 +231,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, arch_dma_prep_coherent(page, size); ret = arch_dma_set_uncached(ret, size); if (IS_ERR(ret)) - goto out_free_pages; + goto out_encrypt_pages; } done: if (force_dma_unencrypted(dev)) @@ -225,6 +239,15 @@ done: else *dma_handle = phys_to_dma(dev, page_to_phys(page)); return ret; + +out_encrypt_pages: + if (force_dma_unencrypted(dev)) { + err = set_memory_encrypted((unsigned long)page_address(page), + 1 << get_order(size)); + /* If memory cannot be re-encrypted, it must be leaked */ + if (err) + return NULL; + } out_free_pages: dma_free_contiguous(dev, page, size); return NULL; @@ -459,7 +482,6 @@ int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, return ret; } -#ifdef CONFIG_MMU bool dma_direct_can_mmap(struct device *dev) { return dev_is_dma_coherent(dev) || @@ -485,19 +507,6 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff, user_count << PAGE_SHIFT, vma->vm_page_prot); } -#else /* CONFIG_MMU */ -bool dma_direct_can_mmap(struct device *dev) -{ - return false; -} - -int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - return -ENXIO; -} -#endif /* CONFIG_MMU */ int dma_direct_supported(struct device *dev, u64 mask) { diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index e739a6eea6e7..78b23f089cf1 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -24,7 +24,8 @@ void *dma_common_pages_remap(struct page **pages, size_t size, { void *vaddr; - vaddr = vmap(pages, size >> PAGE_SHIFT, VM_DMA_COHERENT, prot); + vaddr = vmap(pages, PAGE_ALIGN(size) >> PAGE_SHIFT, + VM_DMA_COHERENT, prot); if (vaddr) find_vm_area(vaddr)->pages = pages; return vaddr; @@ -37,7 +38,7 @@ void *dma_common_pages_remap(struct page **pages, size_t size, void *dma_common_contiguous_remap(struct page *page, size_t size, pgprot_t prot, const void *caller) { - int count = size >> PAGE_SHIFT; + int count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct page **pages; void *vaddr; int i; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index bb05fd52de85..09cc78df53c6 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -181,34 +181,19 @@ void kimage_file_post_load_cleanup(struct kimage *image) static int kimage_validate_signature(struct kimage *image) { - const char *reason; int ret; ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf, image->kernel_buf_len); - switch (ret) { - case 0: - break; + if (ret) { - /* Certain verification errors are non-fatal if we're not - * checking errors, provided we aren't mandating that there - * must be a valid signature. - */ - case -ENODATA: - reason = "kexec of unsigned image"; - goto decide; - case -ENOPKG: - reason = "kexec of image with unsupported crypto"; - goto decide; - case -ENOKEY: - reason = "kexec of image with unavailable key"; - decide: if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) { - pr_notice("%s rejected\n", reason); + pr_notice("Enforced kernel signature verification failed (%d).\n", ret); return ret; } - /* If IMA is guaranteed to appraise a signature on the kexec + /* + * If IMA is guaranteed to appraise a signature on the kexec * image, permit it even if the kernel is otherwise locked * down. */ @@ -216,17 +201,10 @@ kimage_validate_signature(struct kimage *image) security_locked_down(LOCKDOWN_KEXEC)) return -EPERM; - return 0; - - /* All other errors are fatal, including nomem, unparseable - * signatures and signature check failures - even if signatures - * aren't required. - */ - default: - pr_notice("kernel signature verification failed (%d).\n", ret); + pr_debug("kernel signature verification failed (%d).\n", ret); } - return ret; + return 0; } #endif diff --git a/kernel/module.c b/kernel/module.c index e8a198588f26..0c6573b98c36 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2783,7 +2783,9 @@ static void dynamic_debug_remove(struct module *mod, struct _ddebug *debug) void * __weak module_alloc(unsigned long size) { - return vmalloc_exec(size); + return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __func__); } bool __weak module_init_section(const char *name) diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index b03df67621d0..cd356630a311 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -531,7 +531,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags) } else if (!IS_ERR(pidfd_pid(file))) { err = check_setns_flags(flags); } else { - err = -EBADF; + err = -EINVAL; } if (err) goto out; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 8c14835be46c..b71eaf5f5a86 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -974,16 +974,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) user->idx = log_next_idx; user->seq = log_next_seq; break; - case SEEK_CUR: - /* - * It isn't supported due to the record nature of this - * interface: _SET _DATA and _END point to very specific - * record positions, while _CUR would be more useful in case - * of a byte-based log. Because of that, return the default - * errno value for invalid seek operation. - */ - ret = -ESPIPE; - break; default: ret = -EINVAL; } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 05deb81bb3e3..1ae95b9150d3 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -96,6 +96,15 @@ void __cpuidle default_idle_call(void) } } +static int call_cpuidle_s2idle(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + if (current_clr_polling_and_test()) + return -EBUSY; + + return cpuidle_enter_s2idle(drv, dev); +} + static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev, int next_state) { @@ -171,11 +180,9 @@ static void cpuidle_idle_call(void) if (idle_should_enter_s2idle()) { rcu_idle_enter(); - entered_state = cpuidle_enter_s2idle(drv, dev); - if (entered_state > 0) { - local_irq_enable(); + entered_state = call_cpuidle_s2idle(drv, dev); + if (entered_state > 0) goto exit_idle; - } rcu_idle_exit(); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index dc05626979b8..7bc3d6175868 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -241,7 +241,7 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) if (unlikely(ret < 0)) goto fail; - return 0; + return ret; fail: memset(dst, 0, size); return ret; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b8e1ca48be50..00867ff82412 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2427,7 +2427,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, if (unlikely(info->add_timestamp)) { bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer); - event = rb_add_time_stamp(event, info->delta, abs); + event = rb_add_time_stamp(event, abs ? info->delta : delta, abs); length -= RB_LEN_TIME_EXTEND; delta = 0; } diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index 9de29bb45a27..fa0fc08c6ef8 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -101,12 +101,16 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event) kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN); ret = kprobe_event_gen_cmd_start(&cmd, event, val); - if (ret) + if (ret) { + pr_err("Failed to generate probe: %s\n", buf); break; + } ret = kprobe_event_gen_cmd_end(&cmd); - if (ret) + if (ret) { pr_err("Failed to add probe: %s\n", buf); + break; + } } return ret; @@ -120,7 +124,7 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event) } #endif -#ifdef CONFIG_HIST_TRIGGERS +#ifdef CONFIG_SYNTH_EVENTS static int __init trace_boot_add_synth_event(struct xbc_node *node, const char *event) { diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 3a74736da363..f725802160c0 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -216,11 +216,17 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) int trigger_process_regex(struct trace_event_file *file, char *buff) { - char *command, *next = buff; + char *command, *next; struct event_command *p; int ret = -EINVAL; + next = buff = skip_spaces(buff); command = strsep(&next, ": \t"); + if (next) { + next = skip_spaces(next); + if (!*next) + next = NULL; + } command = (command[0] != '!') ? command : command + 1; mutex_lock(&trigger_cmd_mutex); @@ -630,8 +636,14 @@ event_trigger_callback(struct event_command *cmd_ops, int ret; /* separate the trigger from the filter (t:n [if filter]) */ - if (param && isdigit(param[0])) + if (param && isdigit(param[0])) { trigger = strsep(¶m, " \t"); + if (param) { + param = skip_spaces(param); + if (!*param) + param = NULL; + } + } trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger); @@ -1368,6 +1380,11 @@ int event_enable_trigger_func(struct event_command *cmd_ops, trigger = strsep(¶m, " \t"); if (!trigger) return -EINVAL; + if (param) { + param = skip_spaces(param); + if (!*param) + param = NULL; + } system = strsep(&trigger, ":"); if (!trigger) diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 28528285942c..a2a82262b97b 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -520,8 +520,7 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice, err_free: kfree(devmem); err_release: - release_mem_region(devmem->pagemap.res.start, - resource_size(&devmem->pagemap.res)); + release_mem_region(res->start, resource_size(res)); err: mutex_unlock(&mdevice->devmem_lock); return false; diff --git a/mm/compaction.c b/mm/compaction.c index fd988b7e5f2b..86375605faa9 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2316,15 +2316,26 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, .page = NULL, }; - current->capture_control = &capc; + /* + * Make sure the structs are really initialized before we expose the + * capture control, in case we are interrupted and the interrupt handler + * frees a page. + */ + barrier(); + WRITE_ONCE(current->capture_control, &capc); ret = compact_zone(&cc, &capc); VM_BUG_ON(!list_empty(&cc.freepages)); VM_BUG_ON(!list_empty(&cc.migratepages)); - *capture = capc.page; - current->capture_control = NULL; + /* + * Make sure we hide capture control first before we read the captured + * page pointer, otherwise an interrupt could free and capture a page + * and we would leak it. + */ + WRITE_ONCE(current->capture_control, NULL); + *capture = READ_ONCE(capc.page); return ret; } diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index e45623016aea..61ab16fb2e36 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -246,13 +246,13 @@ static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp, static void __init pte_clear_tests(struct mm_struct *mm, pte_t *ptep, unsigned long vaddr) { - pte_t pte = READ_ONCE(*ptep); + pte_t pte = ptep_get(ptep); pte = __pte(pte_val(pte) | RANDOM_ORVALUE); set_pte_at(mm, vaddr, ptep, pte); barrier(); pte_clear(mm, vaddr, ptep); - pte = READ_ONCE(*ptep); + pte = ptep_get(ptep); WARN_ON(!pte_none(pte)); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0b38b6ad547d..19622328e4b5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2772,8 +2772,10 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, return; cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN); - if (!cw) + if (!cw) { + css_put(&memcg->css); return; + } cw->memcg = memcg; cw->cachep = cachep; @@ -6360,11 +6362,16 @@ static unsigned long effective_protection(unsigned long usage, * We're using unprotected memory for the weight so that if * some cgroups DO claim explicit protection, we don't protect * the same bytes twice. + * + * Check both usage and parent_usage against the respective + * protected values. One should imply the other, but they + * aren't read atomically - make sure the division is sane. */ if (!(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)) return ep; - - if (parent_effective > siblings_protected && usage > protected) { + if (parent_effective > siblings_protected && + parent_usage > siblings_protected && + usage > protected) { unsigned long unclaimed; unclaimed = parent_effective - siblings_protected; @@ -6416,7 +6423,7 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, if (parent == root) { memcg->memory.emin = READ_ONCE(memcg->memory.min); - memcg->memory.elow = memcg->memory.low; + memcg->memory.elow = READ_ONCE(memcg->memory.low); goto out; } @@ -6428,7 +6435,8 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, atomic_long_read(&parent->memory.children_min_usage))); WRITE_ONCE(memcg->memory.elow, effective_protection(usage, parent_usage, - memcg->memory.low, READ_ONCE(parent->memory.elow), + READ_ONCE(memcg->memory.low), + READ_ONCE(parent->memory.elow), atomic_long_read(&parent->memory.children_low_usage))); out: diff --git a/mm/memory.c b/mm/memory.c index dc7f3543b1fd..87ec87cdc1ff 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1498,7 +1498,7 @@ out: } #ifdef pte_index -static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd, +static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; @@ -1506,8 +1506,9 @@ static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd, if (!page_count(page)) return -EINVAL; err = validate_page_before_insert(page); - return err ? err : insert_page_into_pte_locked( - mm, pte_offset_map(pmd, addr), addr, page, prot); + if (err) + return err; + return insert_page_into_pte_locked(mm, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations @@ -1517,7 +1518,8 @@ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; - spinlock_t *pte_lock = NULL; + pte_t *start_pte, *pte; + spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; @@ -1536,18 +1538,17 @@ more: ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; - pte_lock = pte_lockptr(mm, pmd); while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); - spin_lock(pte_lock); - for (; pte_idx < batch_size; ++pte_idx) { - int err = insert_page_in_batch_locked(mm, pmd, + start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); + for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { + int err = insert_page_in_batch_locked(mm, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { - spin_unlock(pte_lock); + pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; @@ -1555,7 +1556,7 @@ more: addr += PAGE_SIZE; ++curr_page_idx; } - spin_unlock(pte_lock); + pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } @@ -3140,8 +3141,18 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) err = mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL); ClearPageSwapCache(page); - if (err) + if (err) { + ret = VM_FAULT_OOM; goto out_page; + } + + /* + * XXX: Move to lru_cache_add() when it + * supports new vs putback + */ + spin_lock_irq(&page_pgdat(page)->lru_lock); + lru_note_cost_page(page); + spin_unlock_irq(&page_pgdat(page)->lru_lock); lru_cache_add(page); swap_readpage(page, true); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9b34e03e730a..da374cd3d45b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -471,11 +471,20 @@ void __ref remove_pfn_range_from_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { + const unsigned long end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; - unsigned long flags; + unsigned long pfn, cur_nr_pages, flags; /* Poison struct pages because they are now uninitialized again. */ - page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages); + for (pfn = start_pfn; pfn < end_pfn; pfn += cur_nr_pages) { + cond_resched(); + + /* Select all remaining pages up to the next section boundary */ + cur_nr_pages = + min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn); + page_init_poison(pfn_to_page(pfn), + sizeof(struct page) * cur_nr_pages); + } #ifdef CONFIG_ZONE_DEVICE /* diff --git a/mm/nommu.c b/mm/nommu.c index cdcad5d61dd1..f32a69095d50 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -291,23 +291,6 @@ void *vzalloc_node(unsigned long size, int node) EXPORT_SYMBOL(vzalloc_node); /** - * vmalloc_exec - allocate virtually contiguous, executable memory - * @size: allocation size - * - * Kernel-internal function to allocate enough pages to cover @size - * the page level allocator and map them into contiguous and - * executable kernel virtual space. - * - * For tight control over page level allocator and protection flags - * use __vmalloc() instead. - */ - -void *vmalloc_exec(unsigned long size) -{ - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM); -} - -/** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) * @size: allocation size * diff --git a/mm/slab.h b/mm/slab.h index 207c83ef6e06..74f7e09a7cfd 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -348,7 +348,7 @@ static __always_inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order, struct kmem_cache *s) { - unsigned int nr_pages = 1 << order; + int nr_pages = 1 << order; struct mem_cgroup *memcg; struct lruvec *lruvec; int ret; @@ -388,7 +388,7 @@ out: static __always_inline void memcg_uncharge_slab(struct page *page, int order, struct kmem_cache *s) { - unsigned int nr_pages = 1 << order; + int nr_pages = 1 << order; struct mem_cgroup *memcg; struct lruvec *lruvec; diff --git a/mm/slab_common.c b/mm/slab_common.c index 9e72ba224175..37d48a56431d 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1726,7 +1726,7 @@ void kzfree(const void *p) if (unlikely(ZERO_OR_NULL_PTR(mem))) return; ks = ksize(mem); - memset(mem, 0, ks); + memzero_explicit(mem, ks); kfree(mem); } EXPORT_SYMBOL(kzfree); diff --git a/mm/slub.c b/mm/slub.c index fe81773fd97e..ef303070d175 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3766,15 +3766,13 @@ error: } static void list_slab_objects(struct kmem_cache *s, struct page *page, - const char *text, unsigned long *map) + const char *text) { #ifdef CONFIG_SLUB_DEBUG void *addr = page_address(page); + unsigned long *map; void *p; - if (!map) - return; - slab_err(s, page, text, s->name); slab_lock(page); @@ -3786,6 +3784,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, print_tracking(s, p); } } + put_map(map); slab_unlock(page); #endif } @@ -3799,11 +3798,6 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) { LIST_HEAD(discard); struct page *page, *h; - unsigned long *map = NULL; - -#ifdef CONFIG_SLUB_DEBUG - map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL); -#endif BUG_ON(irqs_disabled()); spin_lock_irq(&n->list_lock); @@ -3813,16 +3807,11 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) list_add(&page->slab_list, &discard); } else { list_slab_objects(s, page, - "Objects remaining in %s on __kmem_cache_shutdown()", - map); + "Objects remaining in %s on __kmem_cache_shutdown()"); } } spin_unlock_irq(&n->list_lock); -#ifdef CONFIG_SLUB_DEBUG - bitmap_free(map); -#endif - list_for_each_entry_safe(page, h, &discard, slab_list) discard_slab(s, page); } diff --git a/mm/swap.c b/mm/swap.c index dbcab84c6fce..a82efc33411f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -443,8 +443,7 @@ void mark_page_accessed(struct page *page) else __lru_cache_activate_page(page); ClearPageReferenced(page); - if (page_is_file_lru(page)) - workingset_activation(page); + workingset_activation(page); } if (page_is_idle(page)) clear_page_idle(page); diff --git a/mm/swap_state.c b/mm/swap_state.c index e98ff460e9e9..05889e8e3c97 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -21,7 +21,7 @@ #include <linux/vmalloc.h> #include <linux/swap_slots.h> #include <linux/huge_mm.h> - +#include "internal.h" /* * swapper_space is a fiction, retained to simplify the path through @@ -429,7 +429,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, __SetPageSwapBacked(page); /* May fail (-ENOMEM) if XArray node allocation failed. */ - if (add_to_swap_cache(page, entry, gfp_mask & GFP_KERNEL)) { + if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK)) { put_swap_page(page, entry); goto fail_unlock; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 3091c2ca60df..5a2b55c8dd9a 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1862,7 +1862,6 @@ EXPORT_SYMBOL(vm_unmap_ram); * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node - * @prot: memory protection to use. PAGE_KERNEL for regular RAM * * If you use this function for less than VMAP_MAX_ALLOC pages, it could be * faster than vmap so it's good. But if you mix long-life and short-life @@ -2696,26 +2695,6 @@ void *vzalloc_node(unsigned long size, int node) } EXPORT_SYMBOL(vzalloc_node); -/** - * vmalloc_exec - allocate virtually contiguous, executable memory - * @size: allocation size - * - * Kernel-internal function to allocate enough pages to cover @size - * the page level allocator and map them into contiguous and - * executable kernel virtual space. - * - * For tight control over page level allocator and protection flags - * use __vmalloc() instead. - * - * Return: pointer to the allocated memory or %NULL on error - */ -void *vmalloc_exec(unsigned long size) -{ - return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, - GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, - NUMA_NO_NODE, __builtin_return_address(0)); -} - #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) diff --git a/mm/vmscan.c b/mm/vmscan.c index b6d84326bdf2..749d239c62b2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -904,6 +904,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, __delete_from_swap_cache(page, swap); xa_unlock_irqrestore(&mapping->i_pages, flags); put_swap_page(page, swap); + workingset_eviction(page, target_memcg); } else { void (*freepage)(struct page *); void *shadow = NULL; @@ -1884,6 +1885,8 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, list_add(&page->lru, &pages_to_free); } else { nr_moved += nr_pages; + if (PageActive(page)) + workingset_age_nonresident(lruvec, nr_pages); } } diff --git a/mm/workingset.c b/mm/workingset.c index d481ea452eeb..50b7937bab32 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -156,8 +156,8 @@ * * Implementation * - * For each node's file LRU lists, a counter for inactive evictions - * and activations is maintained (node->inactive_age). + * For each node's LRU lists, a counter for inactive evictions and + * activations is maintained (node->nonresident_age). * * On eviction, a snapshot of this counter (along with some bits to * identify the node) is stored in the now empty page cache @@ -213,7 +213,17 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, *workingsetp = workingset; } -static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat) +/** + * workingset_age_nonresident - age non-resident entries as LRU ages + * @memcg: the lruvec that was aged + * @nr_pages: the number of pages to count + * + * As in-memory pages are aged, non-resident pages need to be aged as + * well, in order for the refault distances later on to be comparable + * to the in-memory dimensions. This function allows reclaim and LRU + * operations to drive the non-resident aging along in parallel. + */ +void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) { /* * Reclaiming a cgroup means reclaiming all its children in a @@ -227,11 +237,8 @@ static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat) * the root cgroup's, age as well. */ do { - struct lruvec *lruvec; - - lruvec = mem_cgroup_lruvec(memcg, pgdat); - atomic_long_inc(&lruvec->inactive_age); - } while (memcg && (memcg = parent_mem_cgroup(memcg))); + atomic_long_add(nr_pages, &lruvec->nonresident_age); + } while ((lruvec = parent_lruvec(lruvec))); } /** @@ -254,12 +261,11 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); - advance_inactive_age(page_memcg(page), pgdat); - lruvec = mem_cgroup_lruvec(target_memcg, pgdat); + workingset_age_nonresident(lruvec, hpage_nr_pages(page)); /* XXX: target_memcg can be NULL, go through lruvec */ memcgid = mem_cgroup_id(lruvec_memcg(lruvec)); - eviction = atomic_long_read(&lruvec->inactive_age); + eviction = atomic_long_read(&lruvec->nonresident_age); return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } @@ -309,20 +315,20 @@ void workingset_refault(struct page *page, void *shadow) if (!mem_cgroup_disabled() && !eviction_memcg) goto out; eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat); - refault = atomic_long_read(&eviction_lruvec->inactive_age); + refault = atomic_long_read(&eviction_lruvec->nonresident_age); /* * Calculate the refault distance * * The unsigned subtraction here gives an accurate distance - * across inactive_age overflows in most cases. There is a + * across nonresident_age overflows in most cases. There is a * special case: usually, shadow entries have a short lifetime * and are either refaulted or reclaimed along with the inode * before they get too old. But it is not impossible for the - * inactive_age to lap a shadow entry in the field, which can - * then result in a false small refault distance, leading to a - * false activation should this old entry actually refault - * again. However, earlier kernels used to deactivate + * nonresident_age to lap a shadow entry in the field, which + * can then result in a false small refault distance, leading + * to a false activation should this old entry actually + * refault again. However, earlier kernels used to deactivate * unconditionally with *every* reclaim invocation for the * longest time, so the occasional inappropriate activation * leading to pressure on the active list is not a problem. @@ -359,7 +365,7 @@ void workingset_refault(struct page *page, void *shadow) goto out; SetPageActive(page); - advance_inactive_age(memcg, pgdat); + workingset_age_nonresident(lruvec, hpage_nr_pages(page)); inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); /* Page was active prior to eviction */ @@ -382,6 +388,7 @@ out: void workingset_activation(struct page *page) { struct mem_cgroup *memcg; + struct lruvec *lruvec; rcu_read_lock(); /* @@ -394,7 +401,8 @@ void workingset_activation(struct page *page) memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; - advance_inactive_age(memcg, page_pgdat(page)); + lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); + workingset_age_nonresident(lruvec, hpage_nr_pages(page)); out: rcu_read_unlock(); } diff --git a/net/9p/mod.c b/net/9p/mod.c index c1b62428da7b..5126566850bd 100644 --- a/net/9p/mod.c +++ b/net/9p/mod.c @@ -189,3 +189,4 @@ MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>"); MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>"); MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Plan 9 Resource Sharing Support (9P2000)"); diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 24986ec7d38c..779e1eb75443 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -411,10 +411,16 @@ int br_mrp_set_port_role(struct net_bridge_port *p, if (!mrp) return -EINVAL; - if (role == BR_MRP_PORT_ROLE_PRIMARY) + switch (role) { + case BR_MRP_PORT_ROLE_PRIMARY: rcu_assign_pointer(mrp->p_port, p); - else + break; + case BR_MRP_PORT_ROLE_SECONDARY: rcu_assign_pointer(mrp->s_port, p); + break; + default: + return -EINVAL; + } br_mrp_port_switchdev_set_role(p, role); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 7501be4eeba0..2130fe0194e6 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -217,8 +217,8 @@ struct net_bridge_port_group { struct rcu_head rcu; struct timer_list timer; struct br_ip addr; + unsigned char eth_addr[ETH_ALEN] __aligned(2); unsigned char flags; - unsigned char eth_addr[ETH_ALEN]; }; struct net_bridge_mdb_entry { diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index 7c9e92b2f806..8e8ffac037cd 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -155,3 +155,4 @@ module_exit(nft_meta_bridge_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("wenxu <wenxu@ucloud.cn>"); MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta"); +MODULE_DESCRIPTION("Support for bridge dedicated meta key"); diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index f48cf4cfb80f..deae2c9a0f69 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -455,3 +455,4 @@ module_exit(nft_reject_bridge_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "reject"); +MODULE_DESCRIPTION("Reject packets from bridge via nftables"); diff --git a/net/core/dev.c b/net/core/dev.c index 6bc2388141f6..90b59fc50dc9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4192,10 +4192,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) local_bh_disable(); + dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); + dev_xmit_recursion_dec(); local_bh_enable(); @@ -9547,6 +9549,13 @@ int register_netdevice(struct net_device *dev) rcu_barrier(); dev->reg_state = NETREG_UNREGISTERED; + /* We should put the kobject that hold in + * netdev_unregister_kobject(), otherwise + * the net device cannot be freed when + * driver calls free_netdev(), because the + * kobject is being hold. + */ + kobject_put(&dev->dev.kobj); } /* * Prevent userspace races by waiting until the network diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 2ee7bc4c9e03..b09bebeadf0b 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1721,3 +1721,4 @@ module_exit(exit_net_drop_monitor); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); MODULE_ALIAS_GENL_FAMILY("NET_DM"); +MODULE_DESCRIPTION("Monitoring code for network dropped packet alerts"); diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 0cfc35e6be28..b739cfab796e 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -372,14 +372,15 @@ int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv) } EXPORT_SYMBOL(flow_indr_dev_register); -static void __flow_block_indr_cleanup(flow_setup_cb_t *setup_cb, void *cb_priv, +static void __flow_block_indr_cleanup(void (*release)(void *cb_priv), + void *cb_priv, struct list_head *cleanup_list) { struct flow_block_cb *this, *next; list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) { - if (this->cb == setup_cb && - this->cb_priv == cb_priv) { + if (this->release == release && + this->indr.cb_priv == cb_priv) { list_move(&this->indr.list, cleanup_list); return; } @@ -397,7 +398,7 @@ static void flow_block_indr_notify(struct list_head *cleanup_list) } void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv, - flow_setup_cb_t *setup_cb) + void (*release)(void *cb_priv)) { struct flow_indr_dev *this, *next, *indr_dev = NULL; LIST_HEAD(cleanup_list); @@ -418,7 +419,7 @@ void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv, return; } - __flow_block_indr_cleanup(setup_cb, cb_priv, &cleanup_list); + __flow_block_indr_cleanup(release, cb_priv, &cleanup_list); mutex_unlock(&flow_indr_block_lock); flow_block_indr_notify(&cleanup_list); @@ -429,32 +430,37 @@ EXPORT_SYMBOL(flow_indr_dev_unregister); static void flow_block_indr_init(struct flow_block_cb *flow_block, struct flow_block_offload *bo, struct net_device *dev, void *data, + void *cb_priv, void (*cleanup)(struct flow_block_cb *block_cb)) { flow_block->indr.binder_type = bo->binder_type; flow_block->indr.data = data; + flow_block->indr.cb_priv = cb_priv; flow_block->indr.dev = dev; flow_block->indr.cleanup = cleanup; } -static void __flow_block_indr_binding(struct flow_block_offload *bo, - struct net_device *dev, void *data, - void (*cleanup)(struct flow_block_cb *block_cb)) +struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb, + void *cb_ident, void *cb_priv, + void (*release)(void *cb_priv), + struct flow_block_offload *bo, + struct net_device *dev, void *data, + void *indr_cb_priv, + void (*cleanup)(struct flow_block_cb *block_cb)) { struct flow_block_cb *block_cb; - list_for_each_entry(block_cb, &bo->cb_list, list) { - switch (bo->command) { - case FLOW_BLOCK_BIND: - flow_block_indr_init(block_cb, bo, dev, data, cleanup); - list_add(&block_cb->indr.list, &flow_block_indr_list); - break; - case FLOW_BLOCK_UNBIND: - list_del(&block_cb->indr.list); - break; - } - } + block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, release); + if (IS_ERR(block_cb)) + goto out; + + flow_block_indr_init(block_cb, bo, dev, data, indr_cb_priv, cleanup); + list_add(&block_cb->indr.list, &flow_block_indr_list); + +out: + return block_cb; } +EXPORT_SYMBOL(flow_indr_block_cb_alloc); int flow_indr_dev_setup_offload(struct net_device *dev, enum tc_setup_type type, void *data, @@ -465,9 +471,8 @@ int flow_indr_dev_setup_offload(struct net_device *dev, mutex_lock(&flow_indr_block_lock); list_for_each_entry(this, &flow_block_indr_dev_list, list) - this->cb(dev, this->cb_priv, type, bo); + this->cb(dev, this->cb_priv, type, bo, data, cleanup); - __flow_block_indr_binding(bo, dev, data, cleanup); mutex_unlock(&flow_indr_block_lock); return list_empty(&bo->cb_list) ? -EOPNOTSUPP : 0; diff --git a/net/core/sock.c b/net/core/sock.c index 6c4acf1f0220..d832c650287c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -718,7 +718,7 @@ bool sk_mc_loop(struct sock *sk) return inet6_sk(sk)->mc_loop; #endif } - WARN_ON(1); + WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); @@ -1767,6 +1767,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); + sk_tx_queue_clear(sk); } return sk; @@ -1990,6 +1991,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) */ sk_refcnt_debug_inc(newsk); sk_set_socket(newsk, NULL); + sk_tx_queue_clear(newsk); RCU_INIT_POINTER(newsk->sk_wq, NULL); if (newsk->sk_prot->sockets_allocated) diff --git a/net/core/xdp.c b/net/core/xdp.c index 90f44f382115..3c45f99e26d5 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -462,6 +462,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) xdpf->len = totsize - metasize; xdpf->headroom = 0; xdpf->metasize = metasize; + xdpf->frame_sz = PAGE_SIZE; xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; xsk_buff_free(xdp); diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index e8eaa804ccb9..d6200ff98200 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -13,6 +13,16 @@ #define DSA_HLEN 4 #define EDSA_HLEN 8 +#define FRAME_TYPE_TO_CPU 0x00 +#define FRAME_TYPE_FORWARD 0x03 + +#define TO_CPU_CODE_MGMT_TRAP 0x00 +#define TO_CPU_CODE_FRAME2REG 0x01 +#define TO_CPU_CODE_IGMP_MLD_TRAP 0x02 +#define TO_CPU_CODE_POLICY_TRAP 0x03 +#define TO_CPU_CODE_ARP_MIRROR 0x04 +#define TO_CPU_CODE_POLICY_MIRROR 0x05 + static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); @@ -77,6 +87,8 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { u8 *edsa_header; + int frame_type; + int code; int source_device; int source_port; @@ -91,8 +103,29 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, /* * Check that frame type is either TO_CPU or FORWARD. */ - if ((edsa_header[0] & 0xc0) != 0x00 && (edsa_header[0] & 0xc0) != 0xc0) + frame_type = edsa_header[0] >> 6; + + switch (frame_type) { + case FRAME_TYPE_TO_CPU: + code = (edsa_header[1] & 0x6) | ((edsa_header[2] >> 4) & 1); + + /* + * Mark the frame to never egress on any port of the same switch + * unless it's a trapped IGMP/MLD packet, in which case the + * bridge might want to forward it. + */ + if (code != TO_CPU_CODE_IGMP_MLD_TRAP) + skb->offload_fwd_mark = 1; + + break; + + case FRAME_TYPE_FORWARD: + skb->offload_fwd_mark = 1; + break; + + default: return NULL; + } /* * Determine source device and port. @@ -156,8 +189,6 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, 2 * ETH_ALEN); } - skb->offload_fwd_mark = 1; - return skb; } diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index 7b7a0456c15c..7194956aa09e 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -234,6 +234,14 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, struct nlattr *tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX + 1]; int ret; + cfg->first = 100; + cfg->step = 100; + cfg->last = MAX_CABLE_LENGTH_CM; + cfg->pair = PHY_PAIR_ALL; + + if (!nest) + return 0; + ret = nla_parse_nested(tb, ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX, nest, cable_test_tdr_act_cfg_policy, info->extack); if (ret < 0) @@ -242,17 +250,12 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]) cfg->first = nla_get_u32( tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]); - else - cfg->first = 100; + if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST]) cfg->last = nla_get_u32(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST]); - else - cfg->last = MAX_CABLE_LENGTH_CM; if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP]) cfg->step = nla_get_u32(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP]); - else - cfg->step = 100; if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR]) { cfg->pair = nla_get_u8(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR]); @@ -263,8 +266,6 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, "invalid pair parameter"); return -EINVAL; } - } else { - cfg->pair = PHY_PAIR_ALL; } if (cfg->first > MAX_CABLE_LENGTH_CM) { diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 423e640e3876..aaecfc916a4d 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -40,9 +40,11 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", + [NETIF_F_GSO_TUNNEL_REMCSUM_BIT] = "tx-tunnel-remcsum-segmentation", [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", [NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation", [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation", + [NETIF_F_GSO_FRAGLIST_BIT] = "tx-gso-list", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index b5df90c981c2..21d5fc0f6bb3 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2978,7 +2978,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) sizeof(match->mask.ipv6.dst)); } if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) || - memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { + memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) { match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] = diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index 7f47ba89054e..afe5ac8a0f00 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -78,19 +78,18 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, ret = linkstate_get_sqi(dev); if (ret < 0 && ret != -EOPNOTSUPP) - return ret; - + goto out; data->sqi = ret; ret = linkstate_get_sqi_max(dev); if (ret < 0 && ret != -EOPNOTSUPP) - return ret; - + goto out; data->sqi_max = ret; + ret = 0; +out: ethnl_ops_complete(dev); - - return 0; + return ret; } static int linkstate_reply_size(const struct ethnl_req_info *req_base, diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index cd99f548e440..478852ef98ef 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -339,7 +339,7 @@ static void hsr_announce(struct timer_list *t) rcu_read_unlock(); } -static void hsr_del_ports(struct hsr_priv *hsr) +void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; @@ -356,31 +356,12 @@ static void hsr_del_ports(struct hsr_priv *hsr) hsr_del_port(port); } -/* This has to be called after all the readers are gone. - * Otherwise we would have to check the return value of - * hsr_port_get_hsr(). - */ -static void hsr_dev_destroy(struct net_device *hsr_dev) -{ - struct hsr_priv *hsr = netdev_priv(hsr_dev); - - hsr_debugfs_term(hsr); - hsr_del_ports(hsr); - - del_timer_sync(&hsr->prune_timer); - del_timer_sync(&hsr->announce_timer); - - hsr_del_self_node(hsr); - hsr_del_nodes(&hsr->node_db); -} - static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_fix_features = hsr_fix_features, - .ndo_uninit = hsr_dev_destroy, }; static struct device_type hsr_type = { diff --git a/net/hsr/hsr_device.h b/net/hsr/hsr_device.h index a099d7de7e79..b8f9262ed101 100644 --- a/net/hsr/hsr_device.h +++ b/net/hsr/hsr_device.h @@ -11,6 +11,7 @@ #include <linux/netdevice.h> #include "hsr_main.h" +void hsr_del_ports(struct hsr_priv *hsr); void hsr_dev_setup(struct net_device *dev); int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], unsigned char multicast_spec, u8 protocol_version, @@ -18,5 +19,4 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], void hsr_check_carrier_and_operstate(struct hsr_priv *hsr); bool is_hsr_master(struct net_device *dev); int hsr_get_max_mtu(struct hsr_priv *hsr); - #endif /* __HSR_DEVICE_H */ diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index e2564de67603..144da15f0a81 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -6,6 +6,7 @@ */ #include <linux/netdevice.h> +#include <net/rtnetlink.h> #include <linux/rculist.h> #include <linux/timer.h> #include <linux/etherdevice.h> @@ -100,8 +101,10 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, master = hsr_port_get_hsr(port->hsr, HSR_PT_MASTER); hsr_del_port(port); if (hsr_slave_empty(master->hsr)) { - unregister_netdevice_queue(master->dev, - &list_kill); + const struct rtnl_link_ops *ops; + + ops = master->dev->rtnl_link_ops; + ops->dellink(master->dev, &list_kill); unregister_netdevice_many(&list_kill); } } @@ -144,9 +147,9 @@ static int __init hsr_init(void) static void __exit hsr_exit(void) { - unregister_netdevice_notifier(&hsr_nb); hsr_netlink_exit(); hsr_debugfs_remove_root(); + unregister_netdevice_notifier(&hsr_nb); } module_init(hsr_init); diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 1decb25f6764..6e14b7d22639 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -83,6 +83,22 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, return hsr_dev_finalize(dev, link, multicast_spec, hsr_version, extack); } +static void hsr_dellink(struct net_device *dev, struct list_head *head) +{ + struct hsr_priv *hsr = netdev_priv(dev); + + del_timer_sync(&hsr->prune_timer); + del_timer_sync(&hsr->announce_timer); + + hsr_debugfs_term(hsr); + hsr_del_ports(hsr); + + hsr_del_self_node(hsr); + hsr_del_nodes(&hsr->node_db); + + unregister_netdevice_queue(dev, head); +} + static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); @@ -118,6 +134,7 @@ static struct rtnl_link_ops hsr_link_ops __read_mostly = { .priv_size = sizeof(struct hsr_priv), .setup = hsr_dev_setup, .newlink = hsr_newlink, + .dellink = hsr_dellink, .fill_info = hsr_fill_info, }; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 6ecbb0ced177..e64e59b536d3 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -340,29 +340,31 @@ config NET_FOU_IP_TUNNELS config INET_AH tristate "IP: AH transformation" - select XFRM_ALGO - select CRYPTO - select CRYPTO_HMAC - select CRYPTO_MD5 - select CRYPTO_SHA1 + select XFRM_AH help - Support for IPsec AH. + Support for IPsec AH (Authentication Header). + + AH can be used with various authentication algorithms. Besides + enabling AH support itself, this option enables the generic + implementations of the algorithms that RFC 8221 lists as MUST be + implemented. If you need any other algorithms, you'll need to enable + them in the crypto API. You should also enable accelerated + implementations of any needed algorithms when available. If unsure, say Y. config INET_ESP tristate "IP: ESP transformation" - select XFRM_ALGO - select CRYPTO - select CRYPTO_AUTHENC - select CRYPTO_HMAC - select CRYPTO_MD5 - select CRYPTO_CBC - select CRYPTO_SHA1 - select CRYPTO_DES - select CRYPTO_ECHAINIV + select XFRM_ESP help - Support for IPsec ESP. + Support for IPsec ESP (Encapsulating Security Payload). + + ESP can be used with various encryption and authentication algorithms. + Besides enabling ESP support itself, this option enables the generic + implementations of the algorithms that RFC 8221 lists as MUST be + implemented. If you need any other algorithms, you'll need to enable + them in the crypto API. You should also enable accelerated + implementations of any needed algorithms when available. If unsure, say Y. diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index d14133eac476..5bda5aeda579 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -361,3 +361,4 @@ module_exit(esp4_offload_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>"); MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET, XFRM_PROTO_ESP); +MODULE_DESCRIPTION("IPV4 GSO/GRO offload support"); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e53871e4a097..1f75dc686b6b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1109,7 +1109,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table, if (fl4.flowi4_scope < RT_SCOPE_LINK) fl4.flowi4_scope = RT_SCOPE_LINK; - if (table) + if (table && table != RT_TABLE_MAIN) tbl = fib_get_table(net, table); if (tbl) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index dcc79ff54b41..abd083415f89 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -1304,3 +1304,4 @@ module_init(fou_init); module_exit(fou_fini); MODULE_AUTHOR("Tom Herbert <therbert@google.com>"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Foo over UDP"); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index f4f1d11eab50..0c1f36404471 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -85,9 +85,10 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, __be32 remote, __be32 local, __be32 key) { - unsigned int hash; struct ip_tunnel *t, *cand = NULL; struct hlist_head *head; + struct net_device *ndev; + unsigned int hash; hash = ip_tunnel_hash(key, remote); head = &itn->tunnels[hash]; @@ -162,8 +163,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (t && t->dev->flags & IFF_UP) return t; - if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP) - return netdev_priv(itn->fb_tunnel_dev); + ndev = READ_ONCE(itn->fb_tunnel_dev); + if (ndev && ndev->flags & IFF_UP) + return netdev_priv(ndev); return NULL; } @@ -1259,9 +1261,9 @@ void ip_tunnel_uninit(struct net_device *dev) struct ip_tunnel_net *itn; itn = net_generic(net, tunnel->ip_tnl_net_id); - /* fb_tunnel_dev will be unregisted in net-exit call. */ - if (itn->fb_tunnel_dev != dev) - ip_tunnel_del(itn, netdev_priv(dev)); + ip_tunnel_del(itn, netdev_priv(dev)); + if (itn->fb_tunnel_dev == dev) + WRITE_ONCE(itn->fb_tunnel_dev, NULL); dst_cache_reset(&tunnel->dst_cache); } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index c2670eaa74e6..5bf9fa06aee0 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1797,11 +1797,22 @@ out_free: return ret; } +void ipt_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) +{ + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); +} + +void ipt_unregister_table_exit(struct net *net, struct xt_table *table) +{ + __ipt_unregister_table(net, table); +} + void ipt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { if (ops) - nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + ipt_unregister_table_pre_exit(net, table, ops); __ipt_unregister_table(net, table); } @@ -1958,6 +1969,8 @@ static void __exit ip_tables_fini(void) EXPORT_SYMBOL(ipt_register_table); EXPORT_SYMBOL(ipt_unregister_table); +EXPORT_SYMBOL(ipt_unregister_table_pre_exit); +EXPORT_SYMBOL(ipt_unregister_table_exit); EXPORT_SYMBOL(ipt_do_table); module_init(ip_tables_init); module_exit(ip_tables_fini); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 748dc3ce58d3..f2984c7eef40 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -118,3 +118,4 @@ module_exit(synproxy_tg4_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Intercept TCP connections and establish them using syncookies"); diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 9d54b4017e50..8f7bc1ee7453 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -72,16 +72,24 @@ static int __net_init iptable_filter_net_init(struct net *net) return 0; } +static void __net_exit iptable_filter_net_pre_exit(struct net *net) +{ + if (net->ipv4.iptable_filter) + ipt_unregister_table_pre_exit(net, net->ipv4.iptable_filter, + filter_ops); +} + static void __net_exit iptable_filter_net_exit(struct net *net) { if (!net->ipv4.iptable_filter) return; - ipt_unregister_table(net, net->ipv4.iptable_filter, filter_ops); + ipt_unregister_table_exit(net, net->ipv4.iptable_filter); net->ipv4.iptable_filter = NULL; } static struct pernet_operations iptable_filter_net_ops = { .init = iptable_filter_net_init, + .pre_exit = iptable_filter_net_pre_exit, .exit = iptable_filter_net_exit, }; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index bb9266ea3785..f703a717ab1d 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -100,15 +100,23 @@ static int __net_init iptable_mangle_table_init(struct net *net) return ret; } +static void __net_exit iptable_mangle_net_pre_exit(struct net *net) +{ + if (net->ipv4.iptable_mangle) + ipt_unregister_table_pre_exit(net, net->ipv4.iptable_mangle, + mangle_ops); +} + static void __net_exit iptable_mangle_net_exit(struct net *net) { if (!net->ipv4.iptable_mangle) return; - ipt_unregister_table(net, net->ipv4.iptable_mangle, mangle_ops); + ipt_unregister_table_exit(net, net->ipv4.iptable_mangle); net->ipv4.iptable_mangle = NULL; } static struct pernet_operations iptable_mangle_net_ops = { + .pre_exit = iptable_mangle_net_pre_exit, .exit = iptable_mangle_net_exit, }; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index ad33687b7444..b0143b109f25 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -113,16 +113,22 @@ static int __net_init iptable_nat_table_init(struct net *net) return ret; } +static void __net_exit iptable_nat_net_pre_exit(struct net *net) +{ + if (net->ipv4.nat_table) + ipt_nat_unregister_lookups(net); +} + static void __net_exit iptable_nat_net_exit(struct net *net) { if (!net->ipv4.nat_table) return; - ipt_nat_unregister_lookups(net); - ipt_unregister_table(net, net->ipv4.nat_table, NULL); + ipt_unregister_table_exit(net, net->ipv4.nat_table); net->ipv4.nat_table = NULL; } static struct pernet_operations iptable_nat_net_ops = { + .pre_exit = iptable_nat_net_pre_exit, .exit = iptable_nat_net_exit, }; diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 69697eb4bfc6..9abfe6bf2cb9 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -67,15 +67,23 @@ static int __net_init iptable_raw_table_init(struct net *net) return ret; } +static void __net_exit iptable_raw_net_pre_exit(struct net *net) +{ + if (net->ipv4.iptable_raw) + ipt_unregister_table_pre_exit(net, net->ipv4.iptable_raw, + rawtable_ops); +} + static void __net_exit iptable_raw_net_exit(struct net *net) { if (!net->ipv4.iptable_raw) return; - ipt_unregister_table(net, net->ipv4.iptable_raw, rawtable_ops); + ipt_unregister_table_exit(net, net->ipv4.iptable_raw); net->ipv4.iptable_raw = NULL; } static struct pernet_operations iptable_raw_net_ops = { + .pre_exit = iptable_raw_net_pre_exit, .exit = iptable_raw_net_exit, }; diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index ac633c1db97e..415c1975d770 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -62,16 +62,23 @@ static int __net_init iptable_security_table_init(struct net *net) return ret; } +static void __net_exit iptable_security_net_pre_exit(struct net *net) +{ + if (net->ipv4.iptable_security) + ipt_unregister_table_pre_exit(net, net->ipv4.iptable_security, + sectbl_ops); +} + static void __net_exit iptable_security_net_exit(struct net *net) { if (!net->ipv4.iptable_security) return; - - ipt_unregister_table(net, net->ipv4.iptable_security, sectbl_ops); + ipt_unregister_table_exit(net, net->ipv4.iptable_security); net->ipv4.iptable_security = NULL; } static struct pernet_operations iptable_security_net_ops = { + .pre_exit = iptable_security_net_pre_exit, .exit = iptable_security_net_exit, }; diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index e32e41b99f0f..aba65fe90345 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -34,3 +34,4 @@ module_exit(nf_flow_ipv4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NF_FLOWTABLE(AF_INET); +MODULE_DESCRIPTION("Netfilter flow table support"); diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index abf89b972094..bcdb37f86a94 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -107,3 +107,4 @@ module_exit(nft_dup_ipv4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "dup"); +MODULE_DESCRIPTION("IPv4 nftables packet duplication support"); diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index ce294113dbcd..03df986217b7 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -210,3 +210,4 @@ module_exit(nft_fib4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_ALIAS_NFT_AF_EXPR(2, "fib"); +MODULE_DESCRIPTION("nftables fib / ip route lookup support"); diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index 7e6fd5cde50f..e408f813f5d8 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -71,3 +71,4 @@ module_exit(nft_reject_ipv4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject"); +MODULE_DESCRIPTION("IPv4 packet rejection for nftables"); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 8f8eefd3a3ce..c7bf5b26bf0c 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -432,10 +432,9 @@ static void hystart_update(struct sock *sk, u32 delay) if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ + if (ca->curr_rtt > delay) + ca->curr_rtt = delay; if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { - if (ca->curr_rtt > delay) - ca->curr_rtt = delay; - ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min + diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 12fda8f27b08..f3a0eb139b76 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -261,7 +261,8 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb) * cwnd may be very low (even just 1 packet), so we should ACK * immediately. */ - inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } } @@ -3665,6 +3666,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_in_ack_event(sk, ack_ev_flags); } + /* This is a deviation from RFC3168 since it states that: + * "When the TCP data sender is ready to set the CWR bit after reducing + * the congestion window, it SHOULD set the CWR bit only on the first + * new data packet that it transmits." + * We accept CWR on pure ACKs to be more robust + * with widely-deployed TCP implementations that do this. + */ + tcp_ecn_accept_cwr(sk, skb); + /* We passed data and got it acked, remove any soft error * log. Something worked... */ @@ -4800,8 +4810,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) skb_dst_drop(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); - tcp_ecn_accept_cwr(sk, skb); - tp->rx_opt.dsack = 0; /* Queue data for delivery to the user. diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 992cf45fb4f6..f4f19e89af5e 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -49,29 +49,31 @@ config IPV6_OPTIMISTIC_DAD config INET6_AH tristate "IPv6: AH transformation" - select XFRM_ALGO - select CRYPTO - select CRYPTO_HMAC - select CRYPTO_MD5 - select CRYPTO_SHA1 + select XFRM_AH help - Support for IPsec AH. + Support for IPsec AH (Authentication Header). + + AH can be used with various authentication algorithms. Besides + enabling AH support itself, this option enables the generic + implementations of the algorithms that RFC 8221 lists as MUST be + implemented. If you need any other algorithms, you'll need to enable + them in the crypto API. You should also enable accelerated + implementations of any needed algorithms when available. If unsure, say Y. config INET6_ESP tristate "IPv6: ESP transformation" - select XFRM_ALGO - select CRYPTO - select CRYPTO_AUTHENC - select CRYPTO_HMAC - select CRYPTO_MD5 - select CRYPTO_CBC - select CRYPTO_SHA1 - select CRYPTO_DES - select CRYPTO_ECHAINIV + select XFRM_ESP help - Support for IPsec ESP. + Support for IPsec ESP (Encapsulating Security Payload). + + ESP can be used with various encryption and authentication algorithms. + Besides enabling ESP support itself, this option enables the generic + implementations of the algorithms that RFC 8221 lists as MUST be + implemented. If you need any other algorithms, you'll need to enable + them in the crypto API. You should also enable accelerated + implementations of any needed algorithms when available. If unsure, say Y. diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 55addea1948f..1ca516fb30e1 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -395,3 +395,4 @@ module_exit(esp6_offload_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>"); MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET6, XFRM_PROTO_ESP); +MODULE_DESCRIPTION("IPV6 GSO/GRO offload support"); diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c index 091f94184dc1..430518ae26fa 100644 --- a/net/ipv6/fou6.c +++ b/net/ipv6/fou6.c @@ -224,3 +224,4 @@ module_init(fou6_init); module_exit(fou6_fini); MODULE_AUTHOR("Tom Herbert <therbert@google.com>"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Foo over UDP (IPv6)"); diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c index 257d2b681246..36c58aa257e8 100644 --- a/net/ipv6/ila/ila_main.c +++ b/net/ipv6/ila/ila_main.c @@ -120,3 +120,4 @@ module_init(ila_init); module_exit(ila_fini); MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("IPv6: Identifier Locator Addressing (ILA)"); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 781ca8c07a0d..6532bde82b40 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -127,6 +127,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; + struct net_device *ndev; for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || @@ -238,9 +239,9 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, if (t && t->dev->flags & IFF_UP) return t; - dev = ign->fb_tunnel_dev; - if (dev && dev->flags & IFF_UP) - return netdev_priv(dev); + ndev = READ_ONCE(ign->fb_tunnel_dev); + if (ndev && ndev->flags & IFF_UP) + return netdev_priv(ndev); return NULL; } @@ -413,6 +414,8 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); + if (ign->fb_tunnel_dev == dev) + WRITE_ONCE(ign->fb_tunnel_dev, NULL); dst_cache_reset(&t->dst_cache); dev_put(dev); } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index e27393498ecb..e96a431549bc 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1807,11 +1807,22 @@ out_free: return ret; } +void ip6t_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) +{ + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); +} + +void ip6t_unregister_table_exit(struct net *net, struct xt_table *table) +{ + __ip6t_unregister_table(net, table); +} + void ip6t_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { if (ops) - nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + ip6t_unregister_table_pre_exit(net, table, ops); __ip6t_unregister_table(net, table); } @@ -1969,6 +1980,8 @@ static void __exit ip6_tables_fini(void) EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table); +EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); +EXPORT_SYMBOL(ip6t_unregister_table_exit); EXPORT_SYMBOL(ip6t_do_table); module_init(ip6_tables_init); diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index fd1f52a21bf1..d51d0c3e5fe9 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -121,3 +121,4 @@ module_exit(synproxy_tg6_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Intercept IPv6 TCP connections and establish them using syncookies"); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 32667f5d5a33..88337b51ffbf 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -73,16 +73,24 @@ static int __net_init ip6table_filter_net_init(struct net *net) return 0; } +static void __net_exit ip6table_filter_net_pre_exit(struct net *net) +{ + if (net->ipv6.ip6table_filter) + ip6t_unregister_table_pre_exit(net, net->ipv6.ip6table_filter, + filter_ops); +} + static void __net_exit ip6table_filter_net_exit(struct net *net) { if (!net->ipv6.ip6table_filter) return; - ip6t_unregister_table(net, net->ipv6.ip6table_filter, filter_ops); + ip6t_unregister_table_exit(net, net->ipv6.ip6table_filter); net->ipv6.ip6table_filter = NULL; } static struct pernet_operations ip6table_filter_net_ops = { .init = ip6table_filter_net_init, + .pre_exit = ip6table_filter_net_pre_exit, .exit = ip6table_filter_net_exit, }; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 070afb97fa2b..1a2748611e00 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -93,16 +93,24 @@ static int __net_init ip6table_mangle_table_init(struct net *net) return ret; } +static void __net_exit ip6table_mangle_net_pre_exit(struct net *net) +{ + if (net->ipv6.ip6table_mangle) + ip6t_unregister_table_pre_exit(net, net->ipv6.ip6table_mangle, + mangle_ops); +} + static void __net_exit ip6table_mangle_net_exit(struct net *net) { if (!net->ipv6.ip6table_mangle) return; - ip6t_unregister_table(net, net->ipv6.ip6table_mangle, mangle_ops); + ip6t_unregister_table_exit(net, net->ipv6.ip6table_mangle); net->ipv6.ip6table_mangle = NULL; } static struct pernet_operations ip6table_mangle_net_ops = { + .pre_exit = ip6table_mangle_net_pre_exit, .exit = ip6table_mangle_net_exit, }; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 0f4875952efc..0a23265e3caa 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -114,16 +114,22 @@ static int __net_init ip6table_nat_table_init(struct net *net) return ret; } +static void __net_exit ip6table_nat_net_pre_exit(struct net *net) +{ + if (net->ipv6.ip6table_nat) + ip6t_nat_unregister_lookups(net); +} + static void __net_exit ip6table_nat_net_exit(struct net *net) { if (!net->ipv6.ip6table_nat) return; - ip6t_nat_unregister_lookups(net); - ip6t_unregister_table(net, net->ipv6.ip6table_nat, NULL); + ip6t_unregister_table_exit(net, net->ipv6.ip6table_nat); net->ipv6.ip6table_nat = NULL; } static struct pernet_operations ip6table_nat_net_ops = { + .pre_exit = ip6table_nat_net_pre_exit, .exit = ip6table_nat_net_exit, }; diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index a22100b1cf2c..8f9e742226f7 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -66,15 +66,23 @@ static int __net_init ip6table_raw_table_init(struct net *net) return ret; } +static void __net_exit ip6table_raw_net_pre_exit(struct net *net) +{ + if (net->ipv6.ip6table_raw) + ip6t_unregister_table_pre_exit(net, net->ipv6.ip6table_raw, + rawtable_ops); +} + static void __net_exit ip6table_raw_net_exit(struct net *net) { if (!net->ipv6.ip6table_raw) return; - ip6t_unregister_table(net, net->ipv6.ip6table_raw, rawtable_ops); + ip6t_unregister_table_exit(net, net->ipv6.ip6table_raw); net->ipv6.ip6table_raw = NULL; } static struct pernet_operations ip6table_raw_net_ops = { + .pre_exit = ip6table_raw_net_pre_exit, .exit = ip6table_raw_net_exit, }; diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index a74335fe2bd9..5e8c48fed032 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -61,15 +61,23 @@ static int __net_init ip6table_security_table_init(struct net *net) return ret; } +static void __net_exit ip6table_security_net_pre_exit(struct net *net) +{ + if (net->ipv6.ip6table_security) + ip6t_unregister_table_pre_exit(net, net->ipv6.ip6table_security, + sectbl_ops); +} + static void __net_exit ip6table_security_net_exit(struct net *net) { if (!net->ipv6.ip6table_security) return; - ip6t_unregister_table(net, net->ipv6.ip6table_security, sectbl_ops); + ip6t_unregister_table_exit(net, net->ipv6.ip6table_security); net->ipv6.ip6table_security = NULL; } static struct pernet_operations ip6table_security_net_ops = { + .pre_exit = ip6table_security_net_pre_exit, .exit = ip6table_security_net_exit, }; diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index a8566ee12e83..667b8af2546a 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -35,3 +35,4 @@ module_exit(nf_flow_ipv6_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NF_FLOWTABLE(AF_INET6); +MODULE_DESCRIPTION("Netfilter flow table IPv6 module"); diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index 2af32200507d..8b5193efb1f1 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -105,3 +105,4 @@ module_exit(nft_dup_ipv6_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "dup"); +MODULE_DESCRIPTION("IPv6 nftables packet duplication support"); diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 7ece86afd079..e204163c7036 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -255,3 +255,4 @@ module_exit(nft_fib6_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_ALIAS_NFT_AF_EXPR(10, "fib"); +MODULE_DESCRIPTION("nftables fib / ipv6 route lookup support"); diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c index 680a28ce29fd..c1098a1968e1 100644 --- a/net/ipv6/netfilter/nft_reject_ipv6.c +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -72,3 +72,4 @@ module_exit(nft_reject_ipv6_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject"); +MODULE_DESCRIPTION("IPv6 packet rejection for nftables"); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 490b92534afc..df9a51425c6f 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -336,9 +336,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, */ subflow->snd_isn = TCP_SKB_CB(skb)->end_seq; if (subflow->request_mptcp) { - pr_debug("local_key=%llu", subflow->local_key); opts->suboptions = OPTION_MPTCP_MPC_SYN; - opts->sndr_key = subflow->local_key; *size = TCPOLEN_MPTCP_MPC_SYN; return true; } else if (subflow->request_join) { diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index db56535dfc29..c6eeaf3e8dcb 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -249,6 +249,7 @@ struct mptcp_subflow_request_sock { u64 thmac; u32 local_nonce; u32 remote_nonce; + struct mptcp_sock *msk; }; static inline struct mptcp_subflow_request_sock * diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index bbdb74b8bc3c..3838a0b3a21f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -69,6 +69,9 @@ static void subflow_req_destructor(struct request_sock *req) pr_debug("subflow_req=%p", subflow_req); + if (subflow_req->msk) + sock_put((struct sock *)subflow_req->msk); + if (subflow_req->mp_capable) mptcp_token_destroy_request(subflow_req->token); tcp_request_sock_ops.destructor(req); @@ -86,8 +89,8 @@ static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2, } /* validate received token and create truncated hmac and nonce for SYN-ACK */ -static bool subflow_token_join_request(struct request_sock *req, - const struct sk_buff *skb) +static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, + const struct sk_buff *skb) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); u8 hmac[SHA256_DIGEST_SIZE]; @@ -97,13 +100,13 @@ static bool subflow_token_join_request(struct request_sock *req, msk = mptcp_token_get_sock(subflow_req->token); if (!msk) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN); - return false; + return NULL; } local_id = mptcp_pm_get_local_id(msk, (struct sock_common *)req); if (local_id < 0) { sock_put((struct sock *)msk); - return false; + return NULL; } subflow_req->local_id = local_id; @@ -114,9 +117,7 @@ static bool subflow_token_join_request(struct request_sock *req, subflow_req->remote_nonce, hmac); subflow_req->thmac = get_unaligned_be64(hmac); - - sock_put((struct sock *)msk); - return true; + return msk; } static void subflow_init_req(struct request_sock *req, @@ -133,6 +134,7 @@ static void subflow_init_req(struct request_sock *req, subflow_req->mp_capable = 0; subflow_req->mp_join = 0; + subflow_req->msk = NULL; #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of @@ -166,12 +168,9 @@ static void subflow_init_req(struct request_sock *req, subflow_req->remote_id = mp_opt.join_id; subflow_req->token = mp_opt.token; subflow_req->remote_nonce = mp_opt.nonce; - pr_debug("token=%u, remote_nonce=%u", subflow_req->token, - subflow_req->remote_nonce); - if (!subflow_token_join_request(req, skb)) { - subflow_req->mp_join = 0; - // @@ need to trigger RST - } + subflow_req->msk = subflow_token_join_request(req, skb); + pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, + subflow_req->remote_nonce, subflow_req->msk); } } @@ -354,10 +353,9 @@ static bool subflow_hmac_valid(const struct request_sock *req, const struct mptcp_subflow_request_sock *subflow_req; u8 hmac[SHA256_DIGEST_SIZE]; struct mptcp_sock *msk; - bool ret; subflow_req = mptcp_subflow_rsk(req); - msk = mptcp_token_get_sock(subflow_req->token); + msk = subflow_req->msk; if (!msk) return false; @@ -365,12 +363,7 @@ static bool subflow_hmac_valid(const struct request_sock *req, subflow_req->remote_nonce, subflow_req->local_nonce, hmac); - ret = true; - if (crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN)) - ret = false; - - sock_put((struct sock *)msk); - return ret; + return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN); } static void mptcp_sock_destruct(struct sock *sk) @@ -438,22 +431,25 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk); struct mptcp_subflow_request_sock *subflow_req; struct mptcp_options_received mp_opt; - bool fallback_is_fatal = false; + bool fallback, fallback_is_fatal; struct sock *new_msk = NULL; - bool fallback = false; struct sock *child; pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); - /* we need later a valid 'mp_capable' value even when options are not - * parsed + /* After child creation we must look for 'mp_capable' even when options + * are not parsed */ mp_opt.mp_capable = 0; - if (tcp_rsk(req)->is_mptcp == 0) + + /* hopefully temporary handling for MP_JOIN+syncookie */ + subflow_req = mptcp_subflow_rsk(req); + fallback_is_fatal = subflow_req->mp_join; + fallback = !tcp_rsk(req)->is_mptcp; + if (fallback) goto create_child; /* if the sk is MP_CAPABLE, we try to fetch the client key */ - subflow_req = mptcp_subflow_rsk(req); if (subflow_req->mp_capable) { if (TCP_SKB_CB(skb)->seq != subflow_req->ssn_offset + 1) { /* here we can receive and accept an in-window, @@ -474,12 +470,11 @@ create_msk: if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { - fallback_is_fatal = true; mptcp_get_options(skb, &mp_opt); if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); - return NULL; + fallback = true; } } @@ -522,10 +517,12 @@ create_child: } else if (ctx->mp_join) { struct mptcp_sock *owner; - owner = mptcp_token_get_sock(ctx->token); + owner = subflow_req->msk; if (!owner) goto dispose_child; + /* move the msk reference ownership to the subflow */ + subflow_req->msk = NULL; ctx->conn = (struct sock *)owner; if (!mptcp_finish_join(child)) goto dispose_child; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 340cb955af25..56621d6bfd29 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -460,6 +460,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len, for (id = 0; id < IPSET_EXT_ID_MAX; id++) { if (!add_extension(id, cadt_flags, tb)) continue; + if (align < ip_set_extensions[id].align) + align = ip_set_extensions[id].align; len = ALIGN(len, ip_set_extensions[id].align); set->offset[id] = len; set->extensions |= ip_set_extensions[id].type; diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index f108a76925dd..2b01a151eaa8 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -73,3 +73,4 @@ EXPORT_SYMBOL_GPL(nft_fwd_dup_netdev_offload); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_DESCRIPTION("Netfilter packet duplication support"); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index afa85171df38..b1eb5272b379 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -594,3 +594,4 @@ module_exit(nf_flow_table_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_DESCRIPTION("Netfilter flow table module"); diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 88bedf1ff1ae..bc4126d8ef65 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -72,3 +72,4 @@ module_exit(nf_flow_inet_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NF_FLOWTABLE(1); /* NFPROTO_INET */ +MODULE_DESCRIPTION("Netfilter flow table mixed IPv4/IPv6 module"); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 62651e6683f6..5fff1e040168 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -950,6 +950,7 @@ static void nf_flow_table_indr_cleanup(struct flow_block_cb *block_cb) nf_flow_table_gc_cleanup(flowtable, dev); down_write(&flowtable->flow_block_lock); list_del(&block_cb->list); + list_del(&block_cb->driver_list); flow_block_cb_free(block_cb); up_write(&flowtable->flow_block_lock); } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b9cbe1e2453e..ebcdc8e54476 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -1237,3 +1237,4 @@ EXPORT_SYMBOL_GPL(nf_synproxy_ipv6_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("nftables SYNPROXY expression support"); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 185fc82c99aa..c7cf1cde46de 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -296,6 +296,7 @@ static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); mutex_lock(&net->nft.commit_mutex); + list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); mutex_unlock(&net->nft.commit_mutex); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 99127e2d95a8..5f24edf95830 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -33,6 +33,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER); +MODULE_DESCRIPTION("Netfilter messages via netlink socket"); #define nfnl_dereference_protected(id) \ rcu_dereference_protected(table[(id)].subsys, \ diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index f9adca62ccb3..aa1a066cb74b 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -902,3 +902,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("match"); MODULE_ALIAS_NFT_EXPR("target"); +MODULE_DESCRIPTION("x_tables over nftables support"); diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 69d6173f91e2..7d0761fad37e 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -280,3 +280,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso"); MODULE_ALIAS_NFT_EXPR("connlimit"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CONNLIMIT); +MODULE_DESCRIPTION("nftables connlimit rule support"); diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index f6d4d0fa23a6..85ed461ec24e 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -303,3 +303,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_EXPR("counter"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_COUNTER); +MODULE_DESCRIPTION("nftables counter rule support"); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index faea72c2df32..77258af1fce0 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1345,3 +1345,4 @@ MODULE_ALIAS_NFT_EXPR("notrack"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_HELPER); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_TIMEOUT); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_EXPECT); +MODULE_DESCRIPTION("Netfilter nf_tables conntrack module"); diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index c2e78c160fd7..40788b3f1071 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -102,3 +102,4 @@ module_exit(nft_dup_netdev_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_AF_EXPR(5, "dup"); +MODULE_DESCRIPTION("nftables netdev packet duplication support"); diff --git a/net/netfilter/nft_fib_inet.c b/net/netfilter/nft_fib_inet.c index 465432e0531b..a88d44e163d1 100644 --- a/net/netfilter/nft_fib_inet.c +++ b/net/netfilter/nft_fib_inet.c @@ -76,3 +76,4 @@ module_exit(nft_fib_inet_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_ALIAS_NFT_AF_EXPR(1, "fib"); +MODULE_DESCRIPTION("nftables fib inet support"); diff --git a/net/netfilter/nft_fib_netdev.c b/net/netfilter/nft_fib_netdev.c index a2e726ae7f07..3f3478abd845 100644 --- a/net/netfilter/nft_fib_netdev.c +++ b/net/netfilter/nft_fib_netdev.c @@ -85,3 +85,4 @@ module_exit(nft_fib_netdev_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo M. Bermudo Garay <pablombg@gmail.com>"); MODULE_ALIAS_NFT_AF_EXPR(5, "fib"); +MODULE_DESCRIPTION("nftables netdev fib lookups support"); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index b70b48996801..3b9b97aa4b32 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -286,3 +286,4 @@ module_exit(nft_flow_offload_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("flow_offload"); +MODULE_DESCRIPTION("nftables hardware flow offload module"); diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index b836d550b919..96371d878e7e 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -248,3 +248,4 @@ module_exit(nft_hash_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Laura Garcia <nevola@gmail.com>"); MODULE_ALIAS_NFT_EXPR("hash"); +MODULE_DESCRIPTION("Netfilter nftables hash module"); diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 35b67d7e3694..0e2c315c3b5e 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -372,3 +372,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_EXPR("limit"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_LIMIT); +MODULE_DESCRIPTION("nftables limit expression support"); diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index fe4831f2258f..57899454a530 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -298,3 +298,4 @@ module_exit(nft_log_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_EXPR("log"); +MODULE_DESCRIPTION("Netfilter nf_tables log module"); diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index bc9fd98c5d6d..71390b727040 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -305,3 +305,4 @@ module_exit(nft_masq_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); MODULE_ALIAS_NFT_EXPR("masq"); +MODULE_DESCRIPTION("Netfilter nftables masquerade expression support"); diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 23a7bfd10521..4bcf33b049c4 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -402,3 +402,4 @@ module_exit(nft_nat_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>"); MODULE_ALIAS_NFT_EXPR("nat"); +MODULE_DESCRIPTION("Network Address Translation support"); diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 48edb9d5f012..f1fc824f9737 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -217,3 +217,4 @@ module_exit(nft_ng_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Laura Garcia <nevola@gmail.com>"); MODULE_ALIAS_NFT_EXPR("numgen"); +MODULE_DESCRIPTION("nftables number generator module"); diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index bfd18d2b65a2..5f9207a9f485 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -252,3 +252,4 @@ module_exit(nft_objref_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("objref"); +MODULE_DESCRIPTION("nftables stateful object reference module"); diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index b42247aa48a9..c261d57a666a 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -149,3 +149,4 @@ module_exit(nft_osf_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Fernando Fernandez <ffmancera@riseup.net>"); MODULE_ALIAS_NFT_EXPR("osf"); +MODULE_DESCRIPTION("nftables passive OS fingerprint support"); diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index 5ece0a6aa8c3..23265d757acb 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -216,3 +216,4 @@ module_exit(nft_queue_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Eric Leblond <eric@regit.org>"); MODULE_ALIAS_NFT_EXPR("queue"); +MODULE_DESCRIPTION("Netfilter nftables queue module"); diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 4413690591f2..0363f533a42b 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -254,3 +254,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("quota"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_QUOTA); +MODULE_DESCRIPTION("Netfilter nftables quota module"); diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 5b779171565c..2056051c0af0 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -292,3 +292,4 @@ module_exit(nft_redir_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); MODULE_ALIAS_NFT_EXPR("redir"); +MODULE_DESCRIPTION("Netfilter nftables redirect support"); diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 00f865fb80ca..86eafbb0fdd0 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -119,3 +119,4 @@ EXPORT_SYMBOL_GPL(nft_reject_icmpv6_code); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Netfilter x_tables over nftables module"); diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index f41f414b72d1..cf8f2646e93c 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -149,3 +149,4 @@ module_exit(nft_reject_inet_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_AF_EXPR(1, "reject"); +MODULE_DESCRIPTION("Netfilter nftables reject inet support"); diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index e2c1fc608841..4fda8b3f1762 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -388,3 +388,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Fernando Fernandez <ffmancera@riseup.net>"); MODULE_ALIAS_NFT_EXPR("synproxy"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_SYNPROXY); +MODULE_DESCRIPTION("nftables SYNPROXY expression support"); diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 30be5787fbde..d3eb953d0333 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -719,3 +719,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("tunnel"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_TUNNEL); +MODULE_DESCRIPTION("nftables tunnel expression support"); diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c index a8e5f6c8db7a..b4f7bbc3f3ca 100644 --- a/net/netfilter/xt_nat.c +++ b/net/netfilter/xt_nat.c @@ -244,3 +244,4 @@ MODULE_ALIAS("ipt_SNAT"); MODULE_ALIAS("ipt_DNAT"); MODULE_ALIAS("ip6t_SNAT"); MODULE_ALIAS("ip6t_DNAT"); +MODULE_DESCRIPTION("SNAT and DNAT targets support"); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index fc0efd8833c8..2611657f40ca 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1169,9 +1169,10 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, bool last) { + struct ovs_skb_cb *ovs_cb = OVS_CB(skb); const struct nlattr *actions, *cpl_arg; + int len, max_len, rem = nla_len(attr); const struct check_pkt_len_arg *arg; - int rem = nla_len(attr); bool clone_flow_key; /* The first netlink attribute in 'attr' is always @@ -1180,7 +1181,11 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, cpl_arg = nla_data(attr); arg = nla_data(cpl_arg); - if (skb->len <= arg->pkt_len) { + len = ovs_cb->mru ? ovs_cb->mru + skb->mac_len : skb->len; + max_len = arg->pkt_len; + + if ((skb_is_gso(skb) && skb_gso_validate_mac_len(skb, max_len)) || + len <= max_len) { /* Second netlink attribute in 'attr' is always * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'. */ diff --git a/net/rds/transport.c b/net/rds/transport.c index 46f709a4b577..f8001ec80867 100644 --- a/net/rds/transport.c +++ b/net/rds/transport.c @@ -38,6 +38,12 @@ #include "rds.h" #include "loop.h" +static char * const rds_trans_modules[] = { + [RDS_TRANS_IB] = "rds_rdma", + [RDS_TRANS_GAP] = NULL, + [RDS_TRANS_TCP] = "rds_tcp", +}; + static struct rds_transport *transports[RDS_TRANS_COUNT]; static DECLARE_RWSEM(rds_trans_sem); @@ -110,18 +116,20 @@ struct rds_transport *rds_trans_get(int t_type) { struct rds_transport *ret = NULL; struct rds_transport *trans; - unsigned int i; down_read(&rds_trans_sem); - for (i = 0; i < RDS_TRANS_COUNT; i++) { - trans = transports[i]; - - if (trans && trans->t_type == t_type && - (!trans->t_owner || try_module_get(trans->t_owner))) { - ret = trans; - break; - } + trans = transports[t_type]; + if (!trans) { + up_read(&rds_trans_sem); + if (rds_trans_modules[t_type]) + request_module(rds_trans_modules[t_type]); + down_read(&rds_trans_sem); + trans = transports[t_type]; } + if (trans && trans->t_type == t_type && + (!trans->t_owner || try_module_get(trans->t_owner))) + ret = trans; + up_read(&rds_trans_sem); return ret; diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index b7611cc159e5..032ed76c0166 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -22,6 +22,11 @@ #include <net/ip.h> #include "ar-internal.h" +static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call, + unsigned long user_call_ID) +{ +} + /* * Preallocate a single service call, connection and peer and, if possible, * give them a user ID and attach the user's side of the ID to them. @@ -228,6 +233,8 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) if (rx->discard_new_call) { _debug("discard %lx", call->user_call_ID); rx->discard_new_call(call, call->user_call_ID); + if (call->notify_rx) + call->notify_rx = rxrpc_dummy_notify; rxrpc_put_call(call, rxrpc_call_put_kernel); } rxrpc_call_completed(call); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index aa1c8eee6557..6be2672a65ea 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -253,7 +253,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) * confuse things */ annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_RESENT; + annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT; call->rxtx_annotations[ix] = annotation; skb = call->rxtx_buffer[ix]; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 299ac98e9754..767579328a06 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -722,13 +722,12 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max)); + if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) + rwind = RXRPC_RXTX_BUFF_SIZE - 1; if (call->tx_winsize != rwind) { - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; if (rwind > call->tx_winsize) wake = true; - trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, - ntohl(ackinfo->rwind), wake); + trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, rwind, wake); call->tx_winsize = rwind; } diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 9c628591f452..323ae7f6315d 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -32,7 +32,7 @@ static ktime_t gate_get_time(struct tcf_gate *gact) return KTIME_MAX; } -static int gate_get_start_time(struct tcf_gate *gact, ktime_t *start) +static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start) { struct tcf_gate_params *param = &gact->param; ktime_t now, base, cycle; @@ -43,18 +43,13 @@ static int gate_get_start_time(struct tcf_gate *gact, ktime_t *start) if (ktime_after(base, now)) { *start = base; - return 0; + return; } cycle = param->tcfg_cycletime; - /* cycle time should not be zero */ - if (!cycle) - return -EFAULT; - n = div64_u64(ktime_sub_ns(now, base), cycle); *start = ktime_add_ns(base, (n + 1) * cycle); - return 0; } static void gate_start_timer(struct tcf_gate *gact, ktime_t start) @@ -277,6 +272,27 @@ release_list: return err; } +static void gate_setup_timer(struct tcf_gate *gact, u64 basetime, + enum tk_offsets tko, s32 clockid, + bool do_init) +{ + if (!do_init) { + if (basetime == gact->param.tcfg_basetime && + tko == gact->tk_offset && + clockid == gact->param.tcfg_clockid) + return; + + spin_unlock_bh(&gact->tcf_lock); + hrtimer_cancel(&gact->hitimer); + spin_lock_bh(&gact->tcf_lock); + } + gact->param.tcfg_basetime = basetime; + gact->param.tcfg_clockid = clockid; + gact->tk_offset = tko; + hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT); + gact->hitimer.function = gate_timer_func; +} + static int tcf_gate_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, @@ -287,12 +303,12 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, enum tk_offsets tk_offset = TK_OFFS_TAI; struct nlattr *tb[TCA_GATE_MAX + 1]; struct tcf_chain *goto_ch = NULL; + u64 cycletime = 0, basetime = 0; struct tcf_gate_params *p; s32 clockid = CLOCK_TAI; struct tcf_gate *gact; struct tc_gate *parm; int ret = 0, err; - u64 basetime = 0; u32 gflags = 0; s32 prio = -1; ktime_t start; @@ -308,6 +324,27 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (!tb[TCA_GATE_PARMS]) return -EINVAL; + if (tb[TCA_GATE_CLOCKID]) { + clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); + switch (clockid) { + case CLOCK_REALTIME: + tk_offset = TK_OFFS_REAL; + break; + case CLOCK_MONOTONIC: + tk_offset = TK_OFFS_MAX; + break; + case CLOCK_BOOTTIME: + tk_offset = TK_OFFS_BOOT; + break; + case CLOCK_TAI: + tk_offset = TK_OFFS_TAI; + break; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + return -EINVAL; + } + } + parm = nla_data(tb[TCA_GATE_PARMS]); index = parm->index; @@ -331,10 +368,6 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } - if (ret == ACT_P_CREATED) { - to_gate(*a)->param.tcfg_clockid = -1; - INIT_LIST_HEAD(&(to_gate(*a)->param.entries)); - } if (tb[TCA_GATE_PRIORITY]) prio = nla_get_s32(tb[TCA_GATE_PRIORITY]); @@ -345,41 +378,19 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (tb[TCA_GATE_FLAGS]) gflags = nla_get_u32(tb[TCA_GATE_FLAGS]); - if (tb[TCA_GATE_CLOCKID]) { - clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); - switch (clockid) { - case CLOCK_REALTIME: - tk_offset = TK_OFFS_REAL; - break; - case CLOCK_MONOTONIC: - tk_offset = TK_OFFS_MAX; - break; - case CLOCK_BOOTTIME: - tk_offset = TK_OFFS_BOOT; - break; - case CLOCK_TAI: - tk_offset = TK_OFFS_TAI; - break; - default: - NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); - goto release_idr; - } - } + gact = to_gate(*a); + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&gact->param.entries); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; - gact = to_gate(*a); - spin_lock_bh(&gact->tcf_lock); p = &gact->param; - if (tb[TCA_GATE_CYCLE_TIME]) { - p->tcfg_cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); - if (!p->tcfg_cycletime_ext) - goto chain_put; - } + if (tb[TCA_GATE_CYCLE_TIME]) + cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); if (tb[TCA_GATE_ENTRY_LIST]) { err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); @@ -387,35 +398,29 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, goto chain_put; } - if (!p->tcfg_cycletime) { + if (!cycletime) { struct tcfg_gate_entry *entry; ktime_t cycle = 0; list_for_each_entry(entry, &p->entries, list) cycle = ktime_add_ns(cycle, entry->interval); - p->tcfg_cycletime = cycle; + cycletime = cycle; + if (!cycletime) { + err = -EINVAL; + goto chain_put; + } } + p->tcfg_cycletime = cycletime; if (tb[TCA_GATE_CYCLE_TIME_EXT]) p->tcfg_cycletime_ext = nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); + gate_setup_timer(gact, basetime, tk_offset, clockid, + ret == ACT_P_CREATED); p->tcfg_priority = prio; - p->tcfg_basetime = basetime; - p->tcfg_clockid = clockid; p->tcfg_flags = gflags; - - gact->tk_offset = tk_offset; - hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT); - gact->hitimer.function = gate_timer_func; - - err = gate_get_start_time(gact, &start); - if (err < 0) { - NL_SET_ERR_MSG(extack, - "Internal error: failed get start time"); - release_entry_list(&p->entries); - goto chain_put; - } + gate_get_start_time(gact, &start); gact->current_close_time = start; gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING; @@ -443,6 +448,13 @@ chain_put: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: + /* action is not inserted in any list: it's safe to init hitimer + * without taking tcf_lock. + */ + if (ret == ACT_P_CREATED) + gate_setup_timer(gact, gact->param.tcfg_basetime, + gact->tk_offset, gact->param.tcfg_clockid, + true); tcf_idr_release(*a, bind); return err; } @@ -453,9 +465,7 @@ static void tcf_gate_cleanup(struct tc_action *a) struct tcf_gate_params *p; p = &gact->param; - if (p->tcfg_clockid != -1) - hrtimer_cancel(&gact->hitimer); - + hrtimer_cancel(&gact->hitimer); release_entry_list(&p->entries); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index a00a203b2ef5..faa78b7dd962 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -652,6 +652,7 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb) &block->flow_block, tcf_block_shared(block), &extack); down_write(&block->cb_lock); + list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); up_write(&block->cb_lock); rtnl_lock(); @@ -671,25 +672,29 @@ static int tcf_block_offload_cmd(struct tcf_block *block, struct netlink_ext_ack *extack) { struct flow_block_offload bo = {}; - int err; tcf_block_offload_init(&bo, dev, command, ei->binder_type, &block->flow_block, tcf_block_shared(block), extack); - if (dev->netdev_ops->ndo_setup_tc) + if (dev->netdev_ops->ndo_setup_tc) { + int err; + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); - else - err = flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block, - &bo, tc_block_indr_cleanup); + if (err < 0) { + if (err != -EOPNOTSUPP) + NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed"); + return err; + } - if (err < 0) { - if (err != -EOPNOTSUPP) - NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed"); - return err; + return tcf_block_setup(block, &bo); } - return tcf_block_setup(block, &bo); + flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block, &bo, + tc_block_indr_cleanup); + tcf_block_setup(block, &bo); + + return -EOPNOTSUPP; } static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 60f8ae578819..ca813697728e 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1551,32 +1551,51 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) return idx + (tin << 16); } -static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash) +static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) { - int wlen = skb_network_offset(skb); + const int offset = skb_network_offset(skb); + u16 *buf, buf_; u8 dscp; switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0; - dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; - if (wash && dscp) + /* ToS is in the second byte of iphdr */ + dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct iphdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); + } + return dscp; case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0; - dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; - if (wash && dscp) + /* Traffic class is in the first and second bytes of ipv6hdr */ + dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct ipv6hdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); + } + return dscp; case htons(ETH_P_ARP): @@ -1593,14 +1612,17 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, { struct cake_sched_data *q = qdisc_priv(sch); u32 tin, mark; + bool wash; u8 dscp; /* Tin selection: Default to diffserv-based selection, allow overriding - * using firewall marks or skb->priority. + * using firewall marks or skb->priority. Call DSCP parsing early if + * wash is enabled, otherwise defer to below to skip unneeded parsing. */ - dscp = cake_handle_diffserv(skb, - q->rate_flags & CAKE_FLAG_WASH); mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; + wash = !!(q->rate_flags & CAKE_FLAG_WASH); + if (wash) + dscp = cake_handle_diffserv(skb, wash); if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) tin = 0; @@ -1614,6 +1636,8 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, tin = q->tin_order[TC_H_MIN(skb->priority) - 1]; else { + if (!wash) + dscp = cake_handle_diffserv(skb, wash); tin = q->tin_index[dscp]; if (unlikely(tin >= q->tin_cnt)) @@ -2691,7 +2715,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, qdisc_watchdog_init(&q->watchdog, sch); if (opt) { - int err = cake_change(sch, opt, extack); + err = cake_change(sch, opt, extack); if (err) return err; @@ -3008,7 +3032,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, PUT_STAT_S32(BLUE_TIMER_US, ktime_to_us( ktime_sub(now, - flow->cvars.blue_timer))); + flow->cvars.blue_timer))); } if (flow->cvars.dropping) { PUT_STAT_S32(DROP_NEXT_US, diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 8f06a808c59a..2fb76fc0cc31 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -1075,3 +1075,4 @@ module_init(fq_module_init) module_exit(fq_module_exit) MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Fair Queue Packet Scheduler"); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 436160be9c18..459a784056c0 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -721,3 +721,4 @@ module_init(fq_codel_module_init) module_exit(fq_codel_module_exit) MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Fair Queue CoDel discipline"); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index be35f03b657b..420ede875322 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -721,3 +721,4 @@ module_exit(hhf_module_exit) MODULE_AUTHOR("Terry Lam"); MODULE_AUTHOR("Nandita Dukkipati"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Heavy-Hitter Filter (HHF)"); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 72315137d7e7..8d735461fa19 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1565,12 +1565,15 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, enum sctp_scope scope, gfp_t gfp) { + struct sock *sk = asoc->base.sk; int flags; /* Use scoping rules to determine the subset of addresses from * the endpoint. */ - flags = (PF_INET6 == asoc->base.sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; + flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; + if (!inet_v6_ipv6only(sk)) + flags |= SCTP_ADDR4_ALLOWED; if (asoc->peer.ipv4_address) flags |= SCTP_ADDR4_PEERSUPP; if (asoc->peer.ipv6_address) diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 53bc61537f44..701c5a4e441d 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -461,6 +461,7 @@ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest, * well as the remote peer. */ if ((((AF_INET == addr->sa.sa_family) && + (flags & SCTP_ADDR4_ALLOWED) && (flags & SCTP_ADDR4_PEERSUPP))) || (((AF_INET6 == addr->sa.sa_family) && (flags & SCTP_ADDR6_ALLOWED) && diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 092d1afdee0d..cde29f3c7fb3 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -148,7 +148,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp, * sock as well as the remote peer. */ if (addr->a.sa.sa_family == AF_INET && - !(copy_flags & SCTP_ADDR4_PEERSUPP)) + (!(copy_flags & SCTP_ADDR4_ALLOWED) || + !(copy_flags & SCTP_ADDR4_PEERSUPP))) continue; if (addr->a.sa.sa_family == AF_INET6 && (!(copy_flags & SCTP_ADDR6_ALLOWED) || diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 39e14d5edaf1..e9d0953522f0 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1317,6 +1317,7 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) q.len = strlen(gssd_dummy_clnt_dir[0].name); clnt_dentry = d_hash_and_lookup(gssd_dentry, &q); if (!clnt_dentry) { + __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); pipe_dentry = ERR_PTR(-ENOENT); goto out; } diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 6f7d82fb1eb0..be11d672b5b9 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1118,6 +1118,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->head[0].iov_len; + subbuf->head[0].iov_base = buf->head[0].iov_base; subbuf->head[0].iov_len = 0; } @@ -1130,6 +1131,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->page_len; + subbuf->pages = buf->pages; + subbuf->page_base = 0; subbuf->page_len = 0; } @@ -1141,6 +1144,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->tail[0].iov_len; + subbuf->tail[0].iov_base = buf->tail[0].iov_base; subbuf->tail[0].iov_len = 0; } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index ef997880e17a..b647562a26dd 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -367,7 +367,7 @@ static void frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc) trace_xprtrdma_wc_fastreg(wc, frwr); /* The MR will get recycled when the associated req is retransmitted */ - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** @@ -452,7 +452,7 @@ static void frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc) trace_xprtrdma_wc_li(wc, frwr); __frwr_release_mr(wc, mr); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** @@ -474,7 +474,7 @@ static void frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) __frwr_release_mr(wc, mr); complete(&frwr->fr_linv_done); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** @@ -582,7 +582,7 @@ static void frwr_wc_localinv_done(struct ib_cq *cq, struct ib_wc *wc) smp_rmb(); rpcrdma_complete_rqst(rep); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 2081c8fbfa48..935bbef2f7be 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1349,8 +1349,7 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep, be32_to_cpup(p), be32_to_cpu(rep->rr_xid)); } - r_xprt->rx_stats.bad_reply_count++; - return -EREMOTEIO; + return -EIO; } /* Perform XID lookup, reconstruction of the RPC reply, and @@ -1387,13 +1386,11 @@ out: spin_unlock(&xprt->queue_lock); return; -/* If the incoming reply terminated a pending RPC, the next - * RPC call will post a replacement receive buffer as it is - * being marshaled. - */ out_badheader: trace_xprtrdma_reply_hdr(rep); r_xprt->rx_stats.bad_reply_count++; + rqst->rq_task->tk_status = status; + status = 0; goto out; } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 0c4af7f5e241..14165b673b20 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -242,7 +242,7 @@ xprt_rdma_connect_worker(struct work_struct *work) rc = rpcrdma_xprt_connect(r_xprt); xprt_clear_connecting(xprt); - if (r_xprt->rx_ep && r_xprt->rx_ep->re_connect_status > 0) { + if (!rc) { xprt->connect_cookie++; xprt->stat.connect_count++; xprt->stat.connect_time += (long)jiffies - diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 2ae348377806..2198c8ec8dff 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -84,7 +84,8 @@ static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep); static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_destroy(struct rpcrdma_xprt *r_xprt); -static int rpcrdma_ep_destroy(struct rpcrdma_ep *ep); +static void rpcrdma_ep_get(struct rpcrdma_ep *ep); +static int rpcrdma_ep_put(struct rpcrdma_ep *ep); static struct rpcrdma_regbuf * rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction, gfp_t flags); @@ -97,7 +98,8 @@ static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb); */ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt) { - struct rdma_cm_id *id = r_xprt->rx_ep->re_id; + struct rpcrdma_ep *ep = r_xprt->rx_ep; + struct rdma_cm_id *id = ep->re_id; /* Flush Receives, then wait for deferred Reply work * to complete. @@ -108,6 +110,8 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt) * local invalidations. */ ib_drain_sq(id->qp); + + rpcrdma_ep_put(ep); } /** @@ -126,23 +130,27 @@ static void rpcrdma_qp_event_handler(struct ib_event *event, void *context) trace_xprtrdma_qp_event(ep, event); } +/* Ensure xprt_force_disconnect() is invoked exactly once when a + * connection is closed or lost. (The important thing is it needs + * to be invoked "at least" once). + */ +static void rpcrdma_force_disconnect(struct rpcrdma_ep *ep) +{ + if (atomic_add_unless(&ep->re_force_disconnect, 1, 1)) + xprt_force_disconnect(ep->re_xprt); +} + /** * rpcrdma_flush_disconnect - Disconnect on flushed completion - * @cq: completion queue + * @r_xprt: transport to disconnect * @wc: work completion entry * * Must be called in process context. */ -void rpcrdma_flush_disconnect(struct ib_cq *cq, struct ib_wc *wc) +void rpcrdma_flush_disconnect(struct rpcrdma_xprt *r_xprt, struct ib_wc *wc) { - struct rpcrdma_xprt *r_xprt = cq->cq_context; - struct rpc_xprt *xprt = &r_xprt->rx_xprt; - - if (wc->status != IB_WC_SUCCESS && - r_xprt->rx_ep->re_connect_status == 1) { - r_xprt->rx_ep->re_connect_status = -ECONNABORTED; - xprt_force_disconnect(xprt); - } + if (wc->status != IB_WC_SUCCESS) + rpcrdma_force_disconnect(r_xprt->rx_ep); } /** @@ -156,11 +164,12 @@ static void rpcrdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) struct ib_cqe *cqe = wc->wr_cqe; struct rpcrdma_sendctx *sc = container_of(cqe, struct rpcrdma_sendctx, sc_cqe); + struct rpcrdma_xprt *r_xprt = cq->cq_context; /* WARNING: Only wr_cqe and status are reliable at this point */ trace_xprtrdma_wc_send(sc, wc); - rpcrdma_sendctx_put_locked((struct rpcrdma_xprt *)cq->cq_context, sc); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_sendctx_put_locked(r_xprt, sc); + rpcrdma_flush_disconnect(r_xprt, wc); } /** @@ -195,7 +204,7 @@ static void rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) return; out_flushed: - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(r_xprt, wc); rpcrdma_rep_destroy(rep); } @@ -239,7 +248,6 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) { struct sockaddr *sap = (struct sockaddr *)&id->route.addr.dst_addr; struct rpcrdma_ep *ep = id->context; - struct rpc_xprt *xprt = ep->re_xprt; might_sleep(); @@ -263,10 +271,9 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) /* fall through */ case RDMA_CM_EVENT_ADDR_CHANGE: ep->re_connect_status = -ENODEV; - xprt_force_disconnect(xprt); goto disconnected; case RDMA_CM_EVENT_ESTABLISHED: - kref_get(&ep->re_kref); + rpcrdma_ep_get(ep); ep->re_connect_status = 1; rpcrdma_update_cm_private(ep, &event->param.conn); trace_xprtrdma_inline_thresh(ep); @@ -288,8 +295,8 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_DISCONNECTED: ep->re_connect_status = -ECONNABORTED; disconnected: - xprt_force_disconnect(xprt); - return rpcrdma_ep_destroy(ep); + rpcrdma_force_disconnect(ep); + return rpcrdma_ep_put(ep); default: break; } @@ -345,7 +352,7 @@ out: return ERR_PTR(rc); } -static void rpcrdma_ep_put(struct kref *kref) +static void rpcrdma_ep_destroy(struct kref *kref) { struct rpcrdma_ep *ep = container_of(kref, struct rpcrdma_ep, re_kref); @@ -369,13 +376,18 @@ static void rpcrdma_ep_put(struct kref *kref) module_put(THIS_MODULE); } +static noinline void rpcrdma_ep_get(struct rpcrdma_ep *ep) +{ + kref_get(&ep->re_kref); +} + /* Returns: * %0 if @ep still has a positive kref count, or * %1 if @ep was destroyed successfully. */ -static int rpcrdma_ep_destroy(struct rpcrdma_ep *ep) +static noinline int rpcrdma_ep_put(struct rpcrdma_ep *ep) { - return kref_put(&ep->re_kref, rpcrdma_ep_put); + return kref_put(&ep->re_kref, rpcrdma_ep_destroy); } static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) @@ -492,7 +504,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) return 0; out_destroy: - rpcrdma_ep_destroy(ep); + rpcrdma_ep_put(ep); rdma_destroy_id(id); out_free: kfree(ep); @@ -519,10 +531,13 @@ retry: return rc; ep = r_xprt->rx_ep; - ep->re_connect_status = 0; xprt_clear_connected(xprt); - rpcrdma_reset_cwnd(r_xprt); + + /* Bump the ep's reference count while there are + * outstanding Receives. + */ + rpcrdma_ep_get(ep); rpcrdma_post_recvs(r_xprt, true); rc = rpcrdma_sendctxs_create(r_xprt); @@ -552,8 +567,6 @@ retry: rpcrdma_mrs_create(r_xprt); out: - if (rc) - ep->re_connect_status = rc; trace_xprtrdma_connect(r_xprt, rc); return rc; } @@ -587,7 +600,7 @@ void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt) rpcrdma_mrs_destroy(r_xprt); rpcrdma_sendctxs_destroy(r_xprt); - if (rpcrdma_ep_destroy(ep)) + if (rpcrdma_ep_put(ep)) rdma_destroy_id(id); r_xprt->rx_ep = NULL; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 0a16fdb09b2c..43974ef39a50 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -82,6 +82,7 @@ struct rpcrdma_ep { unsigned int re_max_inline_recv; int re_async_rc; int re_connect_status; + atomic_t re_force_disconnect; struct ib_qp_init_attr re_attr; wait_queue_head_t re_connect_wait; struct rpc_xprt *re_xprt; @@ -446,7 +447,7 @@ extern unsigned int xprt_rdma_memreg_strategy; /* * Endpoint calls - xprtrdma/verbs.c */ -void rpcrdma_flush_disconnect(struct ib_cq *cq, struct ib_wc *wc); +void rpcrdma_flush_disconnect(struct rpcrdma_xprt *r_xprt, struct ib_wc *wc); int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt); void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt); diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index b5d4a1ef04b9..5b9a5ab48111 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -67,6 +67,30 @@ config XFRM_STATISTICS If unsure, say N. +# This option selects XFRM_ALGO along with the AH authentication algorithms that +# RFC 8221 lists as MUST be implemented. +config XFRM_AH + tristate + select XFRM_ALGO + select CRYPTO + select CRYPTO_HMAC + select CRYPTO_SHA256 + +# This option selects XFRM_ALGO along with the ESP encryption and authentication +# algorithms that RFC 8221 lists as MUST be implemented. +config XFRM_ESP + tristate + select XFRM_ALGO + select CRYPTO + select CRYPTO_AES + select CRYPTO_AUTHENC + select CRYPTO_CBC + select CRYPTO_ECHAINIV + select CRYPTO_GCM + select CRYPTO_HMAC + select CRYPTO_SEQIV + select CRYPTO_SHA256 + config XFRM_IPCOMP tristate select XFRM_ALGO diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index f50d1f97cf8e..626096bd0d29 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -108,7 +108,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp; - if (!xo) + if (!xo || (xo->flags & XFRM_XMIT)) return skb; if (!(features & NETIF_F_HW_ESP)) @@ -129,6 +129,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } + xo->flags |= XFRM_XMIT; + if (skb_is_gso(skb)) { struct net_device *dev = skb->dev; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index e4c23f69f69f..a7ab19353313 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -574,16 +574,12 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) switch (x->outer_mode.family) { case AF_INET: memset(IPCB(skb), 0, sizeof(*IPCB(skb))); -#ifdef CONFIG_NETFILTER IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; -#endif break; case AF_INET6: memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); -#ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; -#endif break; } diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c index dd558cbb2309..ef53b93db573 100644 --- a/samples/bpf/xdp_monitor_user.c +++ b/samples/bpf/xdp_monitor_user.c @@ -509,11 +509,8 @@ static void *alloc_rec_per_cpu(int record_size) { unsigned int nr_cpus = bpf_num_possible_cpus(); void *array; - size_t size; - size = record_size * nr_cpus; - array = malloc(size); - memset(array, 0, size); + array = calloc(nr_cpus, record_size); if (!array) { fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); exit(EXIT_FAIL_MEM); @@ -528,8 +525,7 @@ static struct stats_record *alloc_stats_record(void) int i; /* Alloc main stats_record structure */ - rec = malloc(sizeof(*rec)); - memset(rec, 0, sizeof(*rec)); + rec = calloc(1, sizeof(*rec)); if (!rec) { fprintf(stderr, "Mem alloc error\n"); exit(EXIT_FAIL_MEM); diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index f3468168982e..f4e755e0dd73 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -207,11 +207,8 @@ static struct datarec *alloc_record_per_cpu(void) { unsigned int nr_cpus = bpf_num_possible_cpus(); struct datarec *array; - size_t size; - size = sizeof(struct datarec) * nr_cpus; - array = malloc(size); - memset(array, 0, size); + array = calloc(nr_cpus, sizeof(struct datarec)); if (!array) { fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); exit(EXIT_FAIL_MEM); @@ -226,11 +223,11 @@ static struct stats_record *alloc_stats_record(void) size = sizeof(*rec) + n_cpus * sizeof(struct record); rec = malloc(size); - memset(rec, 0, size); if (!rec) { fprintf(stderr, "Mem alloc error\n"); exit(EXIT_FAIL_MEM); } + memset(rec, 0, size); rec->rx_cnt.cpu = alloc_record_per_cpu(); rec->redir_err.cpu = alloc_record_per_cpu(); rec->kthread.cpu = alloc_record_per_cpu(); diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index 4fe47502ebed..caa4e7ffcfc7 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -198,11 +198,8 @@ static struct datarec *alloc_record_per_cpu(void) { unsigned int nr_cpus = bpf_num_possible_cpus(); struct datarec *array; - size_t size; - size = sizeof(struct datarec) * nr_cpus; - array = malloc(size); - memset(array, 0, size); + array = calloc(nr_cpus, sizeof(struct datarec)); if (!array) { fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); exit(EXIT_FAIL_MEM); @@ -214,11 +211,8 @@ static struct record *alloc_record_per_rxq(void) { unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; struct record *array; - size_t size; - size = sizeof(struct record) * nr_rxqs; - array = malloc(size); - memset(array, 0, size); + array = calloc(nr_rxqs, sizeof(struct record)); if (!array) { fprintf(stderr, "Mem alloc error (nr_rxqs:%u)\n", nr_rxqs); exit(EXIT_FAIL_MEM); @@ -232,8 +226,7 @@ static struct stats_record *alloc_stats_record(void) struct stats_record *rec; int i; - rec = malloc(sizeof(*rec)); - memset(rec, 0, sizeof(*rec)); + rec = calloc(1, sizeof(struct stats_record)); if (!rec) { fprintf(stderr, "Mem alloc error\n"); exit(EXIT_FAIL_MEM); diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 20b8f6cb3ff8..99aec7349167 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -208,8 +208,8 @@ static const struct config_entry config_table[] = { }, #endif +#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE) /* Cometlake-LP */ -#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_LP) { .flags = FLAG_SOF, .device = 0x02c8, @@ -240,9 +240,7 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x02c8, }, -#endif /* Cometlake-H */ -#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_H) { .flags = FLAG_SOF, .device = 0x06c8, diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index d20aedd103c6..3565e2ab0965 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2470,6 +2470,9 @@ static const struct pci_device_id azx_ids[] = { /* Icelake */ { PCI_DEVICE(0x8086, 0x34c8), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Icelake-H */ + { PCI_DEVICE(0x8086, 0x3dc8), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Jasperlake */ { PCI_DEVICE(0x8086, 0x38c8), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, @@ -2478,9 +2481,14 @@ static const struct pci_device_id azx_ids[] = { /* Tigerlake */ { PCI_DEVICE(0x8086, 0xa0c8), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Tigerlake-H */ + { PCI_DEVICE(0x8086, 0x43c8), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Elkhart Lake */ { PCI_DEVICE(0x8086, 0x4b55), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + { PCI_DEVICE(0x8086, 0x4b58), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Broxton-P(Apollolake) */ { PCI_DEVICE(0x8086, 0x5a98), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON }, diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index fbd7cc6026d8..e2b21ef5d7d1 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4145,6 +4145,11 @@ HDA_CODEC_ENTRY(0x10de0095, "GPU 95 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0097, "GPU 97 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0098, "GPU 98 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0099, "GPU 99 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de009a, "GPU 9a HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP", patch_via_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 6d73f8beadb6..737ef82a75fd 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2461,6 +2461,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), SND_PCI_QUIRK(0x1458, 0xa0cd, "Gigabyte X570 Aorus Master", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1458, 0xa0ce, "Gigabyte X570 Aorus Xtreme", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1462, 0x11f7, "MSI-GE63", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x1275, "MSI-GL63", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950), @@ -7470,6 +7471,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED), diff --git a/sound/soc/amd/raven/acp3x-pcm-dma.c b/sound/soc/amd/raven/acp3x-pcm-dma.c index d8f554f369a8..e6386de20ac7 100644 --- a/sound/soc/amd/raven/acp3x-pcm-dma.c +++ b/sound/soc/amd/raven/acp3x-pcm-dma.c @@ -342,11 +342,34 @@ static int acp3x_dma_close(struct snd_soc_component *component, { struct snd_soc_pcm_runtime *prtd; struct i2s_dev_data *adata; + struct i2s_stream_instance *ins; prtd = substream->private_data; component = snd_soc_rtdcom_lookup(prtd, DRV_NAME); adata = dev_get_drvdata(component->dev); + ins = substream->runtime->private_data; + if (!ins) + return -EINVAL; + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + switch (ins->i2s_instance) { + case I2S_BT_INSTANCE: + adata->play_stream = NULL; + break; + case I2S_SP_INSTANCE: + default: + adata->i2ssp_play_stream = NULL; + } + } else { + switch (ins->i2s_instance) { + case I2S_BT_INSTANCE: + adata->capture_stream = NULL; + break; + case I2S_SP_INSTANCE: + default: + adata->i2ssp_capture_stream = NULL; + } + } /* Disable ACP irq, when the current stream is being closed and * another stream is also not active. @@ -354,13 +377,6 @@ static int acp3x_dma_close(struct snd_soc_component *component, if (!adata->play_stream && !adata->capture_stream && !adata->i2ssp_play_stream && !adata->i2ssp_capture_stream) rv_writel(0, adata->acp3x_base + mmACP_EXTERNAL_INTR_ENB); - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { - adata->play_stream = NULL; - adata->i2ssp_play_stream = NULL; - } else { - adata->capture_stream = NULL; - adata->i2ssp_capture_stream = NULL; - } return 0; } diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c index de003acb1951..473efe9ef998 100644 --- a/sound/soc/codecs/hdac_hda.c +++ b/sound/soc/codecs/hdac_hda.c @@ -441,13 +441,13 @@ static int hdac_hda_codec_probe(struct snd_soc_component *component) ret = snd_hda_codec_set_name(hcodec, hcodec->preset->name); if (ret < 0) { dev_err(&hdev->dev, "name failed %s\n", hcodec->preset->name); - goto error; + goto error_pm; } ret = snd_hdac_regmap_init(&hcodec->core); if (ret < 0) { dev_err(&hdev->dev, "regmap init failed\n"); - goto error; + goto error_pm; } patch = (hda_codec_patch_t)hcodec->preset->driver_data; @@ -455,7 +455,7 @@ static int hdac_hda_codec_probe(struct snd_soc_component *component) ret = patch(hcodec); if (ret < 0) { dev_err(&hdev->dev, "patch failed %d\n", ret); - goto error; + goto error_regmap; } } else { dev_dbg(&hdev->dev, "no patch file found\n"); @@ -467,7 +467,7 @@ static int hdac_hda_codec_probe(struct snd_soc_component *component) ret = snd_hda_codec_parse_pcms(hcodec); if (ret < 0) { dev_err(&hdev->dev, "unable to map pcms to dai %d\n", ret); - goto error; + goto error_regmap; } /* HDMI controls need to be created in machine drivers */ @@ -476,7 +476,7 @@ static int hdac_hda_codec_probe(struct snd_soc_component *component) if (ret < 0) { dev_err(&hdev->dev, "unable to create controls %d\n", ret); - goto error; + goto error_regmap; } } @@ -496,7 +496,9 @@ static int hdac_hda_codec_probe(struct snd_soc_component *component) return 0; -error: +error_regmap: + snd_hdac_regmap_exit(hdev); +error_pm: pm_runtime_put(&hdev->dev); error_no_pm: snd_hdac_ext_bus_link_put(hdev->bus, hlink); @@ -518,6 +520,8 @@ static void hdac_hda_codec_remove(struct snd_soc_component *component) pm_runtime_disable(&hdev->dev); snd_hdac_ext_bus_link_put(hdev->bus, hlink); + + snd_hdac_regmap_exit(hdev); } static const struct snd_soc_dapm_route hdac_hda_dapm_routes[] = { diff --git a/sound/soc/codecs/max98390.c b/sound/soc/codecs/max98390.c index 0d63ebfbff2f..e6613b52bd78 100644 --- a/sound/soc/codecs/max98390.c +++ b/sound/soc/codecs/max98390.c @@ -700,8 +700,8 @@ static bool max98390_readable_register(struct device *dev, unsigned int reg) case MAX98390_IRQ_CTRL ... MAX98390_WDOG_CTRL: case MAX98390_MEAS_ADC_THERM_WARN_THRESH ... MAX98390_BROWNOUT_INFINITE_HOLD: - case MAX98390_BROWNOUT_LVL_HOLD ... THERMAL_COILTEMP_RD_BACK_BYTE0: - case DSMIG_DEBUZZER_THRESHOLD ... MAX98390_R24FF_REV_ID: + case MAX98390_BROWNOUT_LVL_HOLD ... DSMIG_DEBUZZER_THRESHOLD: + case DSM_VOL_ENA ... MAX98390_R24FF_REV_ID: return true; default: return false; @@ -717,7 +717,7 @@ static bool max98390_volatile_reg(struct device *dev, unsigned int reg) case MAX98390_BROWNOUT_LOWEST_STATUS: case MAX98390_ENV_TRACK_BOOST_VOUT_READ: case DSM_STBASS_HPF_B0_BYTE0 ... DSM_DEBUZZER_ATTACK_TIME_BYTE2: - case THERMAL_RDC_RD_BACK_BYTE1 ... THERMAL_COILTEMP_RD_BACK_BYTE0: + case THERMAL_RDC_RD_BACK_BYTE1 ... DSMIG_DEBUZZER_THRESHOLD: case DSM_THERMAL_GAIN ... DSM_WBDRC_GAIN: return true; default: diff --git a/sound/soc/codecs/rt1015.c b/sound/soc/codecs/rt1015.c index 67e2e944d21b..2cccb310fa96 100644 --- a/sound/soc/codecs/rt1015.c +++ b/sound/soc/codecs/rt1015.c @@ -34,30 +34,32 @@ static const struct reg_default rt1015_reg[] = { { 0x0000, 0x0000 }, { 0x0004, 0xa000 }, { 0x0006, 0x0003 }, - { 0x000a, 0x0802 }, - { 0x000c, 0x0020 }, + { 0x000a, 0x081e }, + { 0x000c, 0x0006 }, { 0x000e, 0x0000 }, { 0x0010, 0x0000 }, { 0x0012, 0x0000 }, + { 0x0014, 0x0000 }, + { 0x0016, 0x0000 }, + { 0x0018, 0x0000 }, { 0x0020, 0x8000 }, - { 0x0022, 0x471b }, - { 0x006a, 0x0000 }, - { 0x006c, 0x4020 }, + { 0x0022, 0x8043 }, { 0x0076, 0x0000 }, { 0x0078, 0x0000 }, - { 0x007a, 0x0000 }, + { 0x007a, 0x0002 }, { 0x007c, 0x10ec }, { 0x007d, 0x1015 }, { 0x00f0, 0x5000 }, - { 0x00f2, 0x0774 }, - { 0x00f3, 0x8400 }, + { 0x00f2, 0x004c }, + { 0x00f3, 0xecfe }, { 0x00f4, 0x0000 }, + { 0x00f6, 0x0400 }, { 0x0100, 0x0028 }, { 0x0102, 0xff02 }, - { 0x0104, 0x8232 }, + { 0x0104, 0xa213 }, { 0x0106, 0x200c }, - { 0x010c, 0x002f }, - { 0x010e, 0xc000 }, + { 0x010c, 0x0000 }, + { 0x010e, 0x0058 }, { 0x0111, 0x0200 }, { 0x0112, 0x0400 }, { 0x0114, 0x0022 }, @@ -65,38 +67,46 @@ static const struct reg_default rt1015_reg[] = { { 0x0118, 0x0000 }, { 0x011a, 0x0123 }, { 0x011c, 0x4567 }, - { 0x0300, 0xdddd }, - { 0x0302, 0x0000 }, - { 0x0311, 0x9330 }, - { 0x0313, 0x0000 }, - { 0x0314, 0x0000 }, + { 0x0300, 0x203d }, + { 0x0302, 0x001e }, + { 0x0311, 0x0000 }, + { 0x0313, 0x6014 }, + { 0x0314, 0x00a2 }, { 0x031a, 0x00a0 }, { 0x031c, 0x001f }, { 0x031d, 0xffff }, { 0x031e, 0x0000 }, { 0x031f, 0x0000 }, + { 0x0320, 0x0000 }, { 0x0321, 0x0000 }, - { 0x0322, 0x0000 }, - { 0x0328, 0x0000 }, - { 0x0329, 0x0000 }, - { 0x032a, 0x0000 }, - { 0x032b, 0x0000 }, - { 0x032c, 0x0000 }, - { 0x032d, 0x0000 }, - { 0x032e, 0x030e }, - { 0x0330, 0x0080 }, + { 0x0322, 0xd7df }, + { 0x0328, 0x10b2 }, + { 0x0329, 0x0175 }, + { 0x032a, 0x36ad }, + { 0x032b, 0x7e55 }, + { 0x032c, 0x0520 }, + { 0x032d, 0xaa00 }, + { 0x032e, 0x570e }, + { 0x0330, 0xe180 }, { 0x0332, 0x0034 }, - { 0x0334, 0x0000 }, - { 0x0336, 0x0000 }, + { 0x0334, 0x0001 }, + { 0x0336, 0x0010 }, + { 0x0338, 0x0000 }, + { 0x04fa, 0x0030 }, + { 0x04fc, 0x35c8 }, + { 0x04fe, 0x0800 }, + { 0x0500, 0x0400 }, + { 0x0502, 0x1000 }, + { 0x0504, 0x0000 }, { 0x0506, 0x04ff }, - { 0x0508, 0x0030 }, - { 0x050a, 0x0018 }, - { 0x0519, 0x307f }, - { 0x051a, 0xffff }, - { 0x051b, 0x4000 }, + { 0x0508, 0x0010 }, + { 0x050a, 0x001a }, + { 0x0519, 0x1c68 }, + { 0x051a, 0x0ccc }, + { 0x051b, 0x0666 }, { 0x051d, 0x0000 }, { 0x051f, 0x0000 }, - { 0x0536, 0x1000 }, + { 0x0536, 0x061c }, { 0x0538, 0x0000 }, { 0x053a, 0x0000 }, { 0x053c, 0x0000 }, @@ -110,19 +120,18 @@ static const struct reg_default rt1015_reg[] = { { 0x0544, 0x0000 }, { 0x0568, 0x0000 }, { 0x056a, 0x0000 }, - { 0x1000, 0x0000 }, - { 0x1002, 0x6505 }, + { 0x1000, 0x0040 }, + { 0x1002, 0x5405 }, { 0x1006, 0x5515 }, - { 0x1007, 0x003f }, - { 0x1009, 0x770f }, - { 0x100a, 0x01ff }, - { 0x100c, 0x0000 }, + { 0x1007, 0x05f7 }, + { 0x1009, 0x0b0a }, + { 0x100a, 0x00ef }, { 0x100d, 0x0003 }, { 0x1010, 0xa433 }, { 0x1020, 0x0000 }, - { 0x1200, 0x3d02 }, - { 0x1202, 0x0813 }, - { 0x1204, 0x0211 }, + { 0x1200, 0x5a01 }, + { 0x1202, 0x6524 }, + { 0x1204, 0x1f00 }, { 0x1206, 0x0000 }, { 0x1208, 0x0000 }, { 0x120a, 0x0000 }, @@ -130,16 +139,16 @@ static const struct reg_default rt1015_reg[] = { { 0x120e, 0x0000 }, { 0x1210, 0x0000 }, { 0x1212, 0x0000 }, - { 0x1300, 0x0701 }, - { 0x1302, 0x12f9 }, - { 0x1304, 0x3405 }, + { 0x1300, 0x10a1 }, + { 0x1302, 0x12ff }, + { 0x1304, 0x0400 }, { 0x1305, 0x0844 }, - { 0x1306, 0x1611 }, + { 0x1306, 0x4611 }, { 0x1308, 0x555e }, { 0x130a, 0x0000 }, - { 0x130c, 0x2400}, - { 0x130e, 0x7700 }, - { 0x130f, 0x0000 }, + { 0x130c, 0x2000 }, + { 0x130e, 0x0100 }, + { 0x130f, 0x0001 }, { 0x1310, 0x0000 }, { 0x1312, 0x0000 }, { 0x1314, 0x0000 }, @@ -209,6 +218,9 @@ static bool rt1015_volatile_register(struct device *dev, unsigned int reg) case RT1015_DC_CALIB_CLSD7: case RT1015_DC_CALIB_CLSD8: case RT1015_S_BST_TIMING_INTER1: + case RT1015_OSCK_STA: + case RT1015_MONO_DYNA_CTRL1: + case RT1015_MONO_DYNA_CTRL5: return true; default: @@ -224,6 +236,12 @@ static bool rt1015_readable_register(struct device *dev, unsigned int reg) case RT1015_CLK3: case RT1015_PLL1: case RT1015_PLL2: + case RT1015_DUM_RW1: + case RT1015_DUM_RW2: + case RT1015_DUM_RW3: + case RT1015_DUM_RW4: + case RT1015_DUM_RW5: + case RT1015_DUM_RW6: case RT1015_CLK_DET: case RT1015_SIL_DET: case RT1015_CUSTOMER_ID: @@ -235,6 +253,7 @@ static bool rt1015_readable_register(struct device *dev, unsigned int reg) case RT1015_PAD_DRV2: case RT1015_GAT_BOOST: case RT1015_PRO_ALT: + case RT1015_OSCK_STA: case RT1015_MAN_I2C: case RT1015_DAC1: case RT1015_DAC2: @@ -272,6 +291,13 @@ static bool rt1015_readable_register(struct device *dev, unsigned int reg) case RT1015_SMART_BST_CTRL2: case RT1015_ANA_CTRL1: case RT1015_ANA_CTRL2: + case RT1015_PWR_STATE_CTRL: + case RT1015_MONO_DYNA_CTRL: + case RT1015_MONO_DYNA_CTRL1: + case RT1015_MONO_DYNA_CTRL2: + case RT1015_MONO_DYNA_CTRL3: + case RT1015_MONO_DYNA_CTRL4: + case RT1015_MONO_DYNA_CTRL5: case RT1015_SPK_VOL: case RT1015_SHORT_DETTOP1: case RT1015_SHORT_DETTOP2: diff --git a/sound/soc/codecs/rt1015.h b/sound/soc/codecs/rt1015.h index 6fbe802082c4..8169962935a5 100644 --- a/sound/soc/codecs/rt1015.h +++ b/sound/soc/codecs/rt1015.h @@ -21,6 +21,12 @@ #define RT1015_CLK3 0x0006 #define RT1015_PLL1 0x000a #define RT1015_PLL2 0x000c +#define RT1015_DUM_RW1 0x000e +#define RT1015_DUM_RW2 0x0010 +#define RT1015_DUM_RW3 0x0012 +#define RT1015_DUM_RW4 0x0014 +#define RT1015_DUM_RW5 0x0016 +#define RT1015_DUM_RW6 0x0018 #define RT1015_CLK_DET 0x0020 #define RT1015_SIL_DET 0x0022 #define RT1015_CUSTOMER_ID 0x0076 @@ -32,6 +38,7 @@ #define RT1015_PAD_DRV2 0x00f2 #define RT1015_GAT_BOOST 0x00f3 #define RT1015_PRO_ALT 0x00f4 +#define RT1015_OSCK_STA 0x00f6 #define RT1015_MAN_I2C 0x0100 #define RT1015_DAC1 0x0102 #define RT1015_DAC2 0x0104 @@ -70,7 +77,13 @@ #define RT1015_ANA_CTRL1 0x0334 #define RT1015_ANA_CTRL2 0x0336 #define RT1015_PWR_STATE_CTRL 0x0338 -#define RT1015_SPK_VOL 0x0506 +#define RT1015_MONO_DYNA_CTRL 0x04fa +#define RT1015_MONO_DYNA_CTRL1 0x04fc +#define RT1015_MONO_DYNA_CTRL2 0x04fe +#define RT1015_MONO_DYNA_CTRL3 0x0500 +#define RT1015_MONO_DYNA_CTRL4 0x0502 +#define RT1015_MONO_DYNA_CTRL5 0x0504 +#define RT1015_SPK_VOL 0x0506 #define RT1015_SHORT_DETTOP1 0x0508 #define RT1015_SHORT_DETTOP2 0x050a #define RT1015_SPK_DC_DETECT1 0x0519 diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index d3245123101d..3e9d2c6c51f9 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -2829,12 +2829,13 @@ static int rt5682_probe(struct snd_soc_component *component) return ret; } rt5682->mclk = NULL; - } else { - /* Register CCF DAI clock control */ - ret = rt5682_register_dai_clks(component); - if (ret) - return ret; } + + /* Register CCF DAI clock control */ + ret = rt5682_register_dai_clks(component); + if (ret) + return ret; + /* Initial setup for CCF */ rt5682->lrck[RT5682_AIF1] = CLK_48; #endif diff --git a/sound/soc/fsl/fsl_asrc_common.h b/sound/soc/fsl/fsl_asrc_common.h index 77665b15c8db..7e1c13ca37f1 100644 --- a/sound/soc/fsl/fsl_asrc_common.h +++ b/sound/soc/fsl/fsl_asrc_common.h @@ -32,6 +32,7 @@ enum asrc_pair_index { * @dma_chan: inputer and output DMA channels * @dma_data: private dma data * @pos: hardware pointer position + * @req_dma_chan: flag to release dev_to_dev chan * @private: pair private area */ struct fsl_asrc_pair { @@ -45,6 +46,7 @@ struct fsl_asrc_pair { struct dma_chan *dma_chan[2]; struct imx_dma_data dma_data; unsigned int pos; + bool req_dma_chan; void *private; }; diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c index d6a3fc5f87e5..5f01a58f422a 100644 --- a/sound/soc/fsl/fsl_asrc_dma.c +++ b/sound/soc/fsl/fsl_asrc_dma.c @@ -135,6 +135,8 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component, struct snd_dmaengine_dai_dma_data *dma_params_be = NULL; struct snd_pcm_runtime *runtime = substream->runtime; struct fsl_asrc_pair *pair = runtime->private_data; + struct dma_chan *tmp_chan = NULL, *be_chan = NULL; + struct snd_soc_component *component_be = NULL; struct fsl_asrc *asrc = pair->asrc; struct dma_slave_config config_fe, config_be; enum asrc_pair_index index = pair->index; @@ -142,7 +144,6 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component, int stream = substream->stream; struct imx_dma_data *tmp_data; struct snd_soc_dpcm *dpcm; - struct dma_chan *tmp_chan; struct device *dev_be; u8 dir = tx ? OUT : IN; dma_cap_mask_t mask; @@ -198,17 +199,29 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component, dma_cap_set(DMA_CYCLIC, mask); /* + * The Back-End device might have already requested a DMA channel, + * so try to reuse it first, and then request a new one upon NULL. + */ + component_be = snd_soc_lookup_component_nolocked(dev_be, SND_DMAENGINE_PCM_DRV_NAME); + if (component_be) { + be_chan = soc_component_to_pcm(component_be)->chan[substream->stream]; + tmp_chan = be_chan; + } + if (!tmp_chan) + tmp_chan = dma_request_slave_channel(dev_be, tx ? "tx" : "rx"); + + /* * An EDMA DEV_TO_DEV channel is fixed and bound with DMA event of each * peripheral, unlike SDMA channel that is allocated dynamically. So no - * need to configure dma_request and dma_request2, but get dma_chan via - * dma_request_slave_channel directly with dma name of Front-End device + * need to configure dma_request and dma_request2, but get dma_chan of + * Back-End device directly via dma_request_slave_channel. */ if (!asrc->use_edma) { /* Get DMA request of Back-End */ - tmp_chan = dma_request_slave_channel(dev_be, tx ? "tx" : "rx"); tmp_data = tmp_chan->private; pair->dma_data.dma_request = tmp_data->dma_request; - dma_release_channel(tmp_chan); + if (!be_chan) + dma_release_channel(tmp_chan); /* Get DMA request of Front-End */ tmp_chan = asrc->get_dma_channel(pair, dir); @@ -220,9 +233,11 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component, pair->dma_chan[dir] = dma_request_channel(mask, filter, &pair->dma_data); + pair->req_dma_chan = true; } else { - pair->dma_chan[dir] = - asrc->get_dma_channel(pair, dir); + pair->dma_chan[dir] = tmp_chan; + /* Do not flag to release if we are reusing the Back-End one */ + pair->req_dma_chan = !be_chan; } if (!pair->dma_chan[dir]) { @@ -261,7 +276,8 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component, ret = dmaengine_slave_config(pair->dma_chan[dir], &config_be); if (ret) { dev_err(dev, "failed to config DMA channel for Back-End\n"); - dma_release_channel(pair->dma_chan[dir]); + if (pair->req_dma_chan) + dma_release_channel(pair->dma_chan[dir]); return ret; } @@ -273,19 +289,22 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component, static int fsl_asrc_dma_hw_free(struct snd_soc_component *component, struct snd_pcm_substream *substream) { + bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; struct snd_pcm_runtime *runtime = substream->runtime; struct fsl_asrc_pair *pair = runtime->private_data; + u8 dir = tx ? OUT : IN; snd_pcm_set_runtime_buffer(substream, NULL); - if (pair->dma_chan[IN]) - dma_release_channel(pair->dma_chan[IN]); + if (pair->dma_chan[!dir]) + dma_release_channel(pair->dma_chan[!dir]); - if (pair->dma_chan[OUT]) - dma_release_channel(pair->dma_chan[OUT]); + /* release dev_to_dev chan if we aren't reusing the Back-End one */ + if (pair->dma_chan[dir] && pair->req_dma_chan) + dma_release_channel(pair->dma_chan[dir]); - pair->dma_chan[IN] = NULL; - pair->dma_chan[OUT] = NULL; + pair->dma_chan[!dir] = NULL; + pair->dma_chan[dir] = NULL; return 0; } diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index bad89b0d129e..1a2fa7f18142 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -678,8 +678,9 @@ static int fsl_ssi_set_bclk(struct snd_pcm_substream *substream, struct regmap *regs = ssi->regs; u32 pm = 999, div2, psr, stccr, mask, afreq, factor, i; unsigned long clkrate, baudrate, tmprate; - unsigned int slots = params_channels(hw_params); - unsigned int slot_width = 32; + unsigned int channels = params_channels(hw_params); + unsigned int slot_width = params_width(hw_params); + unsigned int slots = 2; u64 sub, savesub = 100000; unsigned int freq; bool baudclk_is_used; @@ -688,10 +689,14 @@ static int fsl_ssi_set_bclk(struct snd_pcm_substream *substream, /* Override slots and slot_width if being specifically set... */ if (ssi->slots) slots = ssi->slots; - /* ...but keep 32 bits if slots is 2 -- I2S Master mode */ - if (ssi->slot_width && slots != 2) + if (ssi->slot_width) slot_width = ssi->slot_width; + /* ...but force 32 bits for stereo audio using I2S Master Mode */ + if (channels == 2 && + (ssi->i2s_net & SSI_SCR_I2S_MODE_MASK) == SSI_SCR_I2S_MODE_MASTER) + slot_width = 32; + /* Generate bit clock based on the slot number and slot width */ freq = slots * slot_width * params_rate(hw_params); diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig index a2a5798c9139..5dc489a79454 100644 --- a/sound/soc/intel/boards/Kconfig +++ b/sound/soc/intel/boards/Kconfig @@ -492,7 +492,7 @@ config SND_SOC_INTEL_SOF_PCM512x_MACH endif ## SND_SOC_SOF_HDA_LINK || SND_SOC_SOF_BAYTRAIL -if (SND_SOC_SOF_COMETLAKE_LP && SND_SOC_SOF_HDA_LINK) +if (SND_SOC_SOF_COMETLAKE && SND_SOC_SOF_HDA_LINK) config SND_SOC_INTEL_CML_LP_DA7219_MAX98357A_MACH tristate "CML_LP with DA7219 and MAX98357A in I2S Mode" @@ -520,7 +520,7 @@ config SND_SOC_INTEL_SOF_CML_RT1011_RT5682_MACH Say Y if you have such a device. If unsure select "N". -endif ## SND_SOC_SOF_COMETLAKE_LP && SND_SOC_SOF_HDA_LINK +endif ## SND_SOC_SOF_COMETLAKE && SND_SOC_SOF_HDA_LINK if SND_SOC_SOF_JASPERLAKE diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c index 6c20bdd850f3..8ada4ecba847 100644 --- a/sound/soc/qcom/common.c +++ b/sound/soc/qcom/common.c @@ -4,6 +4,7 @@ #include <linux/module.h> #include "common.h" +#include "qdsp6/q6afe.h" int qcom_snd_parse_of(struct snd_soc_card *card) { @@ -101,6 +102,15 @@ int qcom_snd_parse_of(struct snd_soc_card *card) } link->no_pcm = 1; link->ignore_pmdown_time = 1; + + if (q6afe_is_rx_port(link->id)) { + link->dpcm_playback = 1; + link->dpcm_capture = 0; + } else { + link->dpcm_playback = 0; + link->dpcm_capture = 1; + } + } else { dlc = devm_kzalloc(dev, sizeof(*dlc), GFP_KERNEL); if (!dlc) @@ -113,12 +123,12 @@ int qcom_snd_parse_of(struct snd_soc_card *card) link->codecs->dai_name = "snd-soc-dummy-dai"; link->codecs->name = "snd-soc-dummy"; link->dynamic = 1; + link->dpcm_playback = 1; + link->dpcm_capture = 1; } link->ignore_suspend = 1; link->nonatomic = 1; - link->dpcm_playback = 1; - link->dpcm_capture = 1; link->stream_name = link->name; link++; diff --git a/sound/soc/qcom/qdsp6/q6afe.c b/sound/soc/qcom/qdsp6/q6afe.c index e0945f7a58c8..0ce4eb60f984 100644 --- a/sound/soc/qcom/qdsp6/q6afe.c +++ b/sound/soc/qcom/qdsp6/q6afe.c @@ -800,6 +800,14 @@ int q6afe_get_port_id(int index) } EXPORT_SYMBOL_GPL(q6afe_get_port_id); +int q6afe_is_rx_port(int index) +{ + if (index < 0 || index >= AFE_PORT_MAX) + return -EINVAL; + + return port_maps[index].is_rx; +} +EXPORT_SYMBOL_GPL(q6afe_is_rx_port); static int afe_apr_send_pkt(struct q6afe *afe, struct apr_pkt *pkt, struct q6afe_port *port) { diff --git a/sound/soc/qcom/qdsp6/q6afe.h b/sound/soc/qcom/qdsp6/q6afe.h index c7ed5422baff..1a0f80a14afe 100644 --- a/sound/soc/qcom/qdsp6/q6afe.h +++ b/sound/soc/qcom/qdsp6/q6afe.h @@ -198,6 +198,7 @@ int q6afe_port_start(struct q6afe_port *port); int q6afe_port_stop(struct q6afe_port *port); void q6afe_port_put(struct q6afe_port *port); int q6afe_get_port_id(int index); +int q6afe_is_rx_port(int index); void q6afe_hdmi_port_prepare(struct q6afe_port *port, struct q6afe_hdmi_cfg *cfg); void q6afe_slim_port_prepare(struct q6afe_port *port, diff --git a/sound/soc/qcom/qdsp6/q6asm.c b/sound/soc/qcom/qdsp6/q6asm.c index 0e0e8f7a460a..ae4b2cabdf2d 100644 --- a/sound/soc/qcom/qdsp6/q6asm.c +++ b/sound/soc/qcom/qdsp6/q6asm.c @@ -25,6 +25,7 @@ #define ASM_STREAM_CMD_FLUSH 0x00010BCE #define ASM_SESSION_CMD_PAUSE 0x00010BD3 #define ASM_DATA_CMD_EOS 0x00010BDB +#define ASM_DATA_EVENT_RENDERED_EOS 0x00010C1C #define ASM_NULL_POPP_TOPOLOGY 0x00010C68 #define ASM_STREAM_CMD_FLUSH_READBUFS 0x00010C09 #define ASM_STREAM_CMD_SET_ENCDEC_PARAM 0x00010C10 @@ -622,9 +623,6 @@ static int32_t q6asm_stream_callback(struct apr_device *adev, case ASM_SESSION_CMD_SUSPEND: client_event = ASM_CLIENT_EVENT_CMD_SUSPEND_DONE; break; - case ASM_DATA_CMD_EOS: - client_event = ASM_CLIENT_EVENT_CMD_EOS_DONE; - break; case ASM_STREAM_CMD_FLUSH: client_event = ASM_CLIENT_EVENT_CMD_FLUSH_DONE; break; @@ -728,6 +726,9 @@ static int32_t q6asm_stream_callback(struct apr_device *adev, } break; + case ASM_DATA_EVENT_RENDERED_EOS: + client_event = ASM_CLIENT_EVENT_CMD_EOS_DONE; + break; } if (ac->cb) diff --git a/sound/soc/rockchip/rockchip_pdm.c b/sound/soc/rockchip/rockchip_pdm.c index 7cd42fcfcf38..1707414cfa92 100644 --- a/sound/soc/rockchip/rockchip_pdm.c +++ b/sound/soc/rockchip/rockchip_pdm.c @@ -590,8 +590,10 @@ static int rockchip_pdm_resume(struct device *dev) int ret; ret = pm_runtime_get_sync(dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put(dev); return ret; + } ret = regcache_sync(pdm->regmap); diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 7b387202c5db..0f30f5aabaa8 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -310,7 +310,7 @@ struct snd_soc_component *snd_soc_rtdcom_lookup(struct snd_soc_pcm_runtime *rtd, } EXPORT_SYMBOL_GPL(snd_soc_rtdcom_lookup); -static struct snd_soc_component +struct snd_soc_component *snd_soc_lookup_component_nolocked(struct device *dev, const char *driver_name) { struct snd_soc_component *component; @@ -329,6 +329,7 @@ static struct snd_soc_component return found_component; } +EXPORT_SYMBOL_GPL(snd_soc_lookup_component_nolocked); struct snd_soc_component *snd_soc_lookup_component(struct device *dev, const char *driver_name) diff --git a/sound/soc/soc-devres.c b/sound/soc/soc-devres.c index a9ea172a66a7..11e5d7962370 100644 --- a/sound/soc/soc-devres.c +++ b/sound/soc/soc-devres.c @@ -9,6 +9,43 @@ #include <sound/soc.h> #include <sound/dmaengine_pcm.h> +static void devm_dai_release(struct device *dev, void *res) +{ + snd_soc_unregister_dai(*(struct snd_soc_dai **)res); +} + +/** + * devm_snd_soc_register_dai - resource-managed dai registration + * @dev: Device used to manage component + * @component: The component the DAIs are registered for + * @dai_drv: DAI driver to use for the DAI + * @legacy_dai_naming: if %true, use legacy single-name format; + * if %false, use multiple-name format; + */ +struct snd_soc_dai *devm_snd_soc_register_dai(struct device *dev, + struct snd_soc_component *component, + struct snd_soc_dai_driver *dai_drv, + bool legacy_dai_naming) +{ + struct snd_soc_dai **ptr; + struct snd_soc_dai *dai; + + ptr = devres_alloc(devm_dai_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return NULL; + + dai = snd_soc_register_dai(component, dai_drv, legacy_dai_naming); + if (dai) { + *ptr = dai; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return dai; +} +EXPORT_SYMBOL_GPL(devm_snd_soc_register_dai); + static void devm_component_release(struct device *dev, void *res) { snd_soc_unregister_component(*(struct device **)res); diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c index f728309a0833..80a4e71f2d95 100644 --- a/sound/soc/soc-generic-dmaengine-pcm.c +++ b/sound/soc/soc-generic-dmaengine-pcm.c @@ -21,18 +21,6 @@ */ #define SND_DMAENGINE_PCM_FLAG_NO_RESIDUE BIT(31) -struct dmaengine_pcm { - struct dma_chan *chan[SNDRV_PCM_STREAM_LAST + 1]; - const struct snd_dmaengine_pcm_config *config; - struct snd_soc_component component; - unsigned int flags; -}; - -static struct dmaengine_pcm *soc_component_to_pcm(struct snd_soc_component *p) -{ - return container_of(p, struct dmaengine_pcm, component); -} - static struct device *dmaengine_dma_dev(struct dmaengine_pcm *pcm, struct snd_pcm_substream *substream) { diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 2c114b4542ce..c517064f5391 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -2630,15 +2630,15 @@ static int soc_dpcm_fe_runtime_update(struct snd_soc_pcm_runtime *fe, int new) int count, paths; int ret; + if (!fe->dai_link->dynamic) + return 0; + if (fe->num_cpus > 1) { dev_err(fe->dev, "%s doesn't support Multi CPU yet\n", __func__); return -EINVAL; } - if (!fe->dai_link->dynamic) - return 0; - /* only check active links */ if (!snd_soc_dai_active(asoc_rtd_to_cpu(fe, 0))) return 0; diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 9e89633676b7..43e5745b06aa 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1851,7 +1851,7 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg, list_add(&dai_drv->dobj.list, &tplg->comp->dobj_list); /* register the DAI to the component */ - dai = snd_soc_register_dai(tplg->comp, dai_drv, false); + dai = devm_snd_soc_register_dai(tplg->comp->dev, tplg->comp, dai_drv, false); if (!dai) return -ENOMEM; @@ -1859,7 +1859,6 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg, ret = snd_soc_dapm_new_dai_widgets(dapm, dai); if (ret != 0) { dev_err(dai->dev, "Failed to create DAI widgets %d\n", ret); - snd_soc_unregister_dai(dai); return ret; } diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig index c9a2bee4b55c..3aaf25e4f766 100644 --- a/sound/soc/sof/intel/Kconfig +++ b/sound/soc/sof/intel/Kconfig @@ -25,8 +25,7 @@ config SND_SOC_SOF_INTEL_PCI select SND_SOC_SOF_CANNONLAKE if SND_SOC_SOF_CANNONLAKE_SUPPORT select SND_SOC_SOF_COFFEELAKE if SND_SOC_SOF_COFFEELAKE_SUPPORT select SND_SOC_SOF_ICELAKE if SND_SOC_SOF_ICELAKE_SUPPORT - select SND_SOC_SOF_COMETLAKE_LP if SND_SOC_SOF_COMETLAKE_LP_SUPPORT - select SND_SOC_SOF_COMETLAKE_H if SND_SOC_SOF_COMETLAKE_H_SUPPORT + select SND_SOC_SOF_COMETLAKE if SND_SOC_SOF_COMETLAKE_SUPPORT select SND_SOC_SOF_TIGERLAKE if SND_SOC_SOF_TIGERLAKE_SUPPORT select SND_SOC_SOF_ELKHARTLAKE if SND_SOC_SOF_ELKHARTLAKE_SUPPORT select SND_SOC_SOF_JASPERLAKE if SND_SOC_SOF_JASPERLAKE_SUPPORT @@ -201,34 +200,22 @@ config SND_SOC_SOF_ICELAKE This option is not user-selectable but automagically handled by 'select' statements at a higher level -config SND_SOC_SOF_COMETLAKE_LP +config SND_SOC_SOF_COMETLAKE tristate select SND_SOC_SOF_HDA_COMMON help This option is not user-selectable but automagically handled by 'select' statements at a higher level -config SND_SOC_SOF_COMETLAKE_LP_SUPPORT - bool "SOF support for CometLake-LP" - help - This adds support for Sound Open Firmware for Intel(R) platforms - using the Cometlake-LP processors. - Say Y if you have such a device. - If unsure select "N". +config SND_SOC_SOF_COMETLAKE_SUPPORT + bool -config SND_SOC_SOF_COMETLAKE_H - tristate - select SND_SOC_SOF_HDA_COMMON - help - This option is not user-selectable but automagically handled by - 'select' statements at a higher level - -config SND_SOC_SOF_COMETLAKE_H_SUPPORT - bool "SOF support for CometLake-H" +config SND_SOC_SOF_COMETLAKE_LP_SUPPORT + bool "SOF support for CometLake" + select SND_SOC_SOF_COMETLAKE_SUPPORT help This adds support for Sound Open Firmware for Intel(R) platforms - using the Cometlake-H processors. - Say Y if you have such a device. + using the Cometlake processors. If unsure select "N". config SND_SOC_SOF_TIGERLAKE_SUPPORT diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c index 7f65dcc95811..1bda14c3590c 100644 --- a/sound/soc/sof/intel/hda-stream.c +++ b/sound/soc/sof/intel/hda-stream.c @@ -653,11 +653,16 @@ irqreturn_t hda_dsp_stream_threaded_handler(int irq, void *context) if (status & AZX_INT_CTRL_EN) { rirb_status = snd_hdac_chip_readb(bus, RIRBSTS); if (rirb_status & RIRB_INT_MASK) { + /* + * Clearing the interrupt status here ensures + * that no interrupt gets masked after the RIRB + * wp is read in snd_hdac_bus_update_rirb. + */ + snd_hdac_chip_writeb(bus, RIRBSTS, + RIRB_INT_MASK); active = true; if (rirb_status & RIRB_INT_RESPONSE) snd_hdac_bus_update_rirb(bus); - snd_hdac_chip_writeb(bus, RIRBSTS, - RIRB_INT_MASK); } } #endif diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c index b13697dab7c0..aa3532ba1434 100644 --- a/sound/soc/sof/sof-pci-dev.c +++ b/sound/soc/sof/sof-pci-dev.c @@ -151,9 +151,7 @@ static const struct sof_dev_desc cfl_desc = { }; #endif -#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_LP) || \ - IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_H) - +#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE) static const struct sof_dev_desc cml_desc = { .machines = snd_soc_acpi_intel_cml_machines, .alt_machines = snd_soc_acpi_intel_cml_sdw_machines, @@ -411,8 +409,11 @@ static const struct pci_device_id sof_pci_ids[] = { .driver_data = (unsigned long)&cfl_desc}, #endif #if IS_ENABLED(CONFIG_SND_SOC_SOF_ICELAKE) - { PCI_DEVICE(0x8086, 0x34C8), + { PCI_DEVICE(0x8086, 0x34C8), /* ICL-LP */ + .driver_data = (unsigned long)&icl_desc}, + { PCI_DEVICE(0x8086, 0x3dc8), /* ICL-H */ .driver_data = (unsigned long)&icl_desc}, + #endif #if IS_ENABLED(CONFIG_SND_SOC_SOF_JASPERLAKE) { PCI_DEVICE(0x8086, 0x38c8), @@ -420,17 +421,20 @@ static const struct pci_device_id sof_pci_ids[] = { { PCI_DEVICE(0x8086, 0x4dc8), .driver_data = (unsigned long)&jsl_desc}, #endif -#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_LP) - { PCI_DEVICE(0x8086, 0x02c8), +#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE) + { PCI_DEVICE(0x8086, 0x02c8), /* CML-LP */ .driver_data = (unsigned long)&cml_desc}, -#endif -#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_H) - { PCI_DEVICE(0x8086, 0x06c8), + { PCI_DEVICE(0x8086, 0x06c8), /* CML-H */ + .driver_data = (unsigned long)&cml_desc}, + { PCI_DEVICE(0x8086, 0xa3f0), /* CML-S */ .driver_data = (unsigned long)&cml_desc}, #endif #if IS_ENABLED(CONFIG_SND_SOC_SOF_TIGERLAKE) - { PCI_DEVICE(0x8086, 0xa0c8), + { PCI_DEVICE(0x8086, 0xa0c8), /* TGL-LP */ + .driver_data = (unsigned long)&tgl_desc}, + { PCI_DEVICE(0x8086, 0x43c8), /* TGL-H */ .driver_data = (unsigned long)&tgl_desc}, + #endif #if IS_ENABLED(CONFIG_SND_SOC_SOF_ELKHARTLAKE) { PCI_DEVICE(0x8086, 0x4b55), diff --git a/sound/usb/format.c b/sound/usb/format.c index 5ffb457cc88c..1b28d01d1f4c 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -394,8 +394,9 @@ skip_rate: return nr_rates; } -/* Line6 Helix series don't support the UAC2_CS_RANGE usb function - * call. Return a static table of known clock rates. +/* Line6 Helix series and the Rode Rodecaster Pro don't support the + * UAC2_CS_RANGE usb function call. Return a static table of known + * clock rates. */ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, struct audioformat *fp) @@ -408,6 +409,7 @@ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */ case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */ case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */ + case USB_ID(0x19f7, 0x0011): /* Rode Rodecaster Pro */ return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000); } diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 15769f266790..eab0fd4fd7c3 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -581,8 +581,9 @@ static int check_matrix_bitmap(unsigned char *bmap, * if failed, give up and free the control instance. */ -int snd_usb_mixer_add_control(struct usb_mixer_elem_list *list, - struct snd_kcontrol *kctl) +int snd_usb_mixer_add_list(struct usb_mixer_elem_list *list, + struct snd_kcontrol *kctl, + bool is_std_info) { struct usb_mixer_interface *mixer = list->mixer; int err; @@ -596,6 +597,7 @@ int snd_usb_mixer_add_control(struct usb_mixer_elem_list *list, return err; } list->kctl = kctl; + list->is_std_info = is_std_info; list->next_id_elem = mixer->id_elems[list->id]; mixer->id_elems[list->id] = list; return 0; @@ -3234,8 +3236,11 @@ void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid) unitid = delegate_notify(mixer, unitid, NULL, NULL); for_each_mixer_elem(list, mixer, unitid) { - struct usb_mixer_elem_info *info = - mixer_elem_list_to_info(list); + struct usb_mixer_elem_info *info; + + if (!list->is_std_info) + continue; + info = mixer_elem_list_to_info(list); /* invalidate cache, so the value is read from the device */ info->cached = 0; snd_ctl_notify(mixer->chip->card, SNDRV_CTL_EVENT_MASK_VALUE, @@ -3315,6 +3320,8 @@ static void snd_usb_mixer_interrupt_v2(struct usb_mixer_interface *mixer, if (!list->kctl) continue; + if (!list->is_std_info) + continue; info = mixer_elem_list_to_info(list); if (count > 1 && info->control != control) diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h index 41ec9dc4139b..c29e27ac43a7 100644 --- a/sound/usb/mixer.h +++ b/sound/usb/mixer.h @@ -66,6 +66,7 @@ struct usb_mixer_elem_list { struct usb_mixer_elem_list *next_id_elem; /* list of controls with same id */ struct snd_kcontrol *kctl; unsigned int id; + bool is_std_info; usb_mixer_elem_dump_func_t dump; usb_mixer_elem_resume_func_t resume; }; @@ -103,8 +104,12 @@ void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid); int snd_usb_mixer_set_ctl_value(struct usb_mixer_elem_info *cval, int request, int validx, int value_set); -int snd_usb_mixer_add_control(struct usb_mixer_elem_list *list, - struct snd_kcontrol *kctl); +int snd_usb_mixer_add_list(struct usb_mixer_elem_list *list, + struct snd_kcontrol *kctl, + bool is_std_info); + +#define snd_usb_mixer_add_control(list, kctl) \ + snd_usb_mixer_add_list(list, kctl, true) void snd_usb_mixer_elem_init_std(struct usb_mixer_elem_list *list, struct usb_mixer_interface *mixer, diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index b6bcf2f92383..cec1cfd7edb7 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -158,7 +158,8 @@ static int add_single_ctl_with_resume(struct usb_mixer_interface *mixer, return -ENOMEM; } kctl->private_free = snd_usb_mixer_elem_free; - return snd_usb_mixer_add_control(list, kctl); + /* don't use snd_usb_mixer_add_control() here, this is a special list element */ + return snd_usb_mixer_add_list(list, kctl, false); } /* diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 8a05dcb1344f..a777d36c4f5a 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -367,6 +367,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, ifnum = 0; goto add_sync_ep_from_ifnum; case USB_ID(0x07fd, 0x0008): /* MOTU M Series */ + case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */ ep = 0x81; ifnum = 2; goto add_sync_ep_from_ifnum; @@ -1786,6 +1787,7 @@ static int snd_usb_substream_capture_trigger(struct snd_pcm_substream *substream return 0; case SNDRV_PCM_TRIGGER_STOP: stop_endpoints(subs); + subs->data_endpoint->retire_data_urb = NULL; subs->running = 0; return 0; case SNDRV_PCM_TRIGGER_PAUSE_PUSH: diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index bca0179a0ef8..fca72730a802 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1532,6 +1532,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) static bool is_itf_usb_dsd_dac(unsigned int id) { switch (id) { + case USB_ID(0x154e, 0x1002): /* Denon DCD-1500RE */ case USB_ID(0x154e, 0x1003): /* Denon DA-300USB */ case USB_ID(0x154e, 0x3005): /* Marantz HD-DAC1 */ case USB_ID(0x154e, 0x3006): /* Marantz SA-14S1 */ @@ -1673,6 +1674,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) usleep_range(1000, 2000); + + /* + * Samsung USBC Headset (AKG) need a tiny delay after each + * class compliant request. (Model number: AAM625R or AAM627R) + */ + if (chip->usb_id == USB_ID(0x04e8, 0xa051) && + (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) + usleep_range(5000, 6000); } /* @@ -1856,6 +1865,7 @@ struct registration_quirk { static const struct registration_quirk registration_quirks[] = { REG_QUIRK_ENTRY(0x0951, 0x16d8, 2), /* Kingston HyperX AMP */ REG_QUIRK_ENTRY(0x0951, 0x16ed, 2), /* Kingston HyperX Cloud Alpha S */ + REG_QUIRK_ENTRY(0x0951, 0x16ea, 2), /* Kingston HyperX Cloud Flight S */ { 0 } /* terminator */ }; diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 31101643e57c..70c78faa47ab 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -49,7 +49,7 @@ MAP COMMANDS | | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** | | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** -| | **queue** | **stack** | **sk_storage** | **struct_ops** } +| | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** } DESCRIPTION =========== diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index c5fac8068ba1..1d3b60651078 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -49,6 +49,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_STACK] = "stack", [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_MAP_TYPE_RINGBUF] = "ringbuf", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); @@ -1590,7 +1591,7 @@ static int do_help(int argc, char **argv) " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" - " queue | stack | sk_storage | struct_ops }\n" + " queue | stack | sk_storage | struct_ops | ringbuf }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2]); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 19684813faae..974a71342aea 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3168,7 +3168,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) + * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) * Description * Copy *size* bytes from *data* into a ring buffer *ringbuf*. * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of diff --git a/tools/spi/spidev_test.c b/tools/spi/spidev_test.c index eec23fa693bd..83844f8b862a 100644 --- a/tools/spi/spidev_test.c +++ b/tools/spi/spidev_test.c @@ -47,7 +47,7 @@ static int transfer_size; static int iterations; static int interval = 5; /* interval in seconds for showing transfer rate */ -uint8_t default_tx[] = { +static uint8_t default_tx[] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x40, 0x00, 0x00, 0x00, 0x00, 0x95, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, @@ -56,8 +56,8 @@ uint8_t default_tx[] = { 0xF0, 0x0D, }; -uint8_t default_rx[ARRAY_SIZE(default_tx)] = {0, }; -char *input_tx; +static uint8_t default_rx[ARRAY_SIZE(default_tx)] = {0, }; +static char *input_tx; static void hex_dump(const void *src, size_t length, size_t line_size, char *prefix) @@ -461,8 +461,8 @@ int main(int argc, char *argv[]) pabort("can't get max speed hz"); printf("spi mode: 0x%x\n", mode); - printf("bits per word: %d\n", bits); - printf("max speed: %d Hz (%d KHz)\n", speed, speed/1000); + printf("bits per word: %u\n", bits); + printf("max speed: %u Hz (%u kHz)\n", speed, speed/1000); if (input_tx) transfer_escaped_string(fd, input_tx); diff --git a/tools/testing/selftests/arm64/signal/Makefile b/tools/testing/selftests/arm64/signal/Makefile index b497cfea4643..ac4ad0005715 100644 --- a/tools/testing/selftests/arm64/signal/Makefile +++ b/tools/testing/selftests/arm64/signal/Makefile @@ -21,10 +21,6 @@ include ../../lib.mk $(TEST_GEN_PROGS): $(PROGS) cp $(PROGS) $(OUTPUT)/ -clean: - $(CLEAN) - rm -f $(PROGS) - # Common test-unit targets to build common-layout test-cases executables # Needs secondary expansion to properly include the testcase c-file in pre-reqs .SECONDEXPANSION: diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 2061a6beac0f..5f54c6aec7f0 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -13,6 +13,7 @@ static int getsetsockopt(void) char cc[16]; /* TCP_CA_NAME_MAX */ } buf = {}; socklen_t optlen; + char *big_buf = NULL; fd = socket(AF_INET, SOCK_STREAM, 0); if (fd < 0) { @@ -22,24 +23,31 @@ static int getsetsockopt(void) /* IP_TOS - BPF bypass */ - buf.u8[0] = 0x08; - err = setsockopt(fd, SOL_IP, IP_TOS, &buf, 1); + optlen = getpagesize() * 2; + big_buf = calloc(1, optlen); + if (!big_buf) { + log_err("Couldn't allocate two pages"); + goto err; + } + + *(int *)big_buf = 0x08; + err = setsockopt(fd, SOL_IP, IP_TOS, big_buf, optlen); if (err) { log_err("Failed to call setsockopt(IP_TOS)"); goto err; } - buf.u8[0] = 0x00; + memset(big_buf, 0, optlen); optlen = 1; - err = getsockopt(fd, SOL_IP, IP_TOS, &buf, &optlen); + err = getsockopt(fd, SOL_IP, IP_TOS, big_buf, &optlen); if (err) { log_err("Failed to call getsockopt(IP_TOS)"); goto err; } - if (buf.u8[0] != 0x08) { - log_err("Unexpected getsockopt(IP_TOS) buf[0] 0x%02x != 0x08", - buf.u8[0]); + if (*(int *)big_buf != 0x08) { + log_err("Unexpected getsockopt(IP_TOS) optval 0x%x != 0x08", + *(int *)big_buf); goto err; } @@ -78,6 +86,28 @@ static int getsetsockopt(void) goto err; } + /* IP_FREEBIND - BPF can't access optval past PAGE_SIZE */ + + optlen = getpagesize() * 2; + memset(big_buf, 0, optlen); + + err = setsockopt(fd, SOL_IP, IP_FREEBIND, big_buf, optlen); + if (err != 0) { + log_err("Failed to call setsockopt, ret=%d", err); + goto err; + } + + err = getsockopt(fd, SOL_IP, IP_FREEBIND, big_buf, &optlen); + if (err != 0) { + log_err("Failed to call getsockopt, ret=%d", err); + goto err; + } + + if (optlen != 1 || *(__u8 *)big_buf != 0x55) { + log_err("Unexpected IP_FREEBIND getsockopt, optlen=%d, optval=0x%x", + optlen, *(__u8 *)big_buf); + } + /* SO_SNDBUF is overwritten */ buf.u32 = 0x01010101; @@ -124,9 +154,11 @@ static int getsetsockopt(void) goto err; } + free(big_buf); close(fd); return 0; err: + free(big_buf); close(fd); return -1; } diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index 7897c8f4d363..ef574087f1e1 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -480,10 +480,9 @@ static __always_inline void hystart_update(struct sock *sk, __u32 delay) if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ + if (ca->curr_rtt > delay) + ca->curr_rtt = delay; if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { - if (ca->curr_rtt > delay) - ca->curr_rtt = delay; - ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min + diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index d5a5eeb5fb52..712df7b49cb1 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -8,6 +8,10 @@ char _license[] SEC("license") = "GPL"; __u32 _version SEC("version") = 1; +#ifndef PAGE_SIZE +#define PAGE_SIZE 4096 +#endif + #define SOL_CUSTOM 0xdeadbeef struct sockopt_sk { @@ -28,12 +32,14 @@ int _getsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; struct sockopt_sk *storage; - if (ctx->level == SOL_IP && ctx->optname == IP_TOS) + if (ctx->level == SOL_IP && ctx->optname == IP_TOS) { /* Not interested in SOL_IP:IP_TOS; * let next BPF program in the cgroup chain or kernel * handle it. */ + ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ return 1; + } if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { /* Not interested in SOL_SOCKET:SO_SNDBUF; @@ -51,6 +57,26 @@ int _getsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + ctx->retval = 0; /* Reset system call return value to zero */ + + /* Always export 0x55 */ + optval[0] = 0x55; + ctx->optlen = 1; + + /* Userspace buffer is PAGE_SIZE * 2, but BPF + * program can only see the first PAGE_SIZE + * bytes of data. + */ + if (optval_end - optval != PAGE_SIZE) + return 0; /* EPERM, unexpected data size */ + + return 1; + } + if (ctx->level != SOL_CUSTOM) return 0; /* EPERM, deny everything except custom level */ @@ -81,12 +107,14 @@ int _setsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; struct sockopt_sk *storage; - if (ctx->level == SOL_IP && ctx->optname == IP_TOS) + if (ctx->level == SOL_IP && ctx->optname == IP_TOS) { /* Not interested in SOL_IP:IP_TOS; * let next BPF program in the cgroup chain or kernel * handle it. */ + ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ return 1; + } if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { /* Overwrite SO_SNDBUF value */ @@ -112,6 +140,28 @@ int _setsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { + /* Original optlen is larger than PAGE_SIZE. */ + if (ctx->optlen != PAGE_SIZE * 2) + return 0; /* EPERM, unexpected data size */ + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + /* Make sure we can trim the buffer. */ + optval[0] = 0; + ctx->optlen = 1; + + /* Usepace buffer is PAGE_SIZE * 2, but BPF + * program can only see the first PAGE_SIZE + * bytes of data. + */ + if (optval_end - optval != PAGE_SIZE) + return 0; /* EPERM, unexpected data size */ + + return 1; + } + if (ctx->level != SOL_CUSTOM) return 0; /* EPERM, deny everything except custom level */ diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 383bac05ac32..ceaad78e9667 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -15,8 +15,9 @@ #include <inttypes.h> #include <linux/net_tstamp.h> #include <linux/errqueue.h> +#include <linux/if_ether.h> #include <linux/ipv6.h> -#include <linux/tcp.h> +#include <linux/udp.h> #include <stdbool.h> #include <stdlib.h> #include <stdio.h> @@ -140,8 +141,8 @@ static void do_recv_errqueue_timeout(int fdt) { char control[CMSG_SPACE(sizeof(struct sock_extended_err)) + CMSG_SPACE(sizeof(struct sockaddr_in6))] = {0}; - char data[sizeof(struct ipv6hdr) + - sizeof(struct tcphdr) + 1]; + char data[sizeof(struct ethhdr) + sizeof(struct ipv6hdr) + + sizeof(struct udphdr) + 1]; struct sock_extended_err *err; struct msghdr msg = {0}; struct iovec iov = {0}; @@ -159,6 +160,8 @@ static void do_recv_errqueue_timeout(int fdt) msg.msg_controllen = sizeof(control); while (1) { + const char *reason; + ret = recvmsg(fdt, &msg, MSG_ERRQUEUE); if (ret == -1 && errno == EAGAIN) break; @@ -176,14 +179,30 @@ static void do_recv_errqueue_timeout(int fdt) err = (struct sock_extended_err *)CMSG_DATA(cm); if (err->ee_origin != SO_EE_ORIGIN_TXTIME) error(1, 0, "errqueue: origin 0x%x\n", err->ee_origin); - if (err->ee_code != ECANCELED) - error(1, 0, "errqueue: code 0x%x\n", err->ee_code); + + switch (err->ee_errno) { + case ECANCELED: + if (err->ee_code != SO_EE_CODE_TXTIME_MISSED) + error(1, 0, "errqueue: unknown ECANCELED %u\n", + err->ee_code); + reason = "missed txtime"; + break; + case EINVAL: + if (err->ee_code != SO_EE_CODE_TXTIME_INVALID_PARAM) + error(1, 0, "errqueue: unknown EINVAL %u\n", + err->ee_code); + reason = "invalid txtime"; + break; + default: + error(1, 0, "errqueue: errno %u code %u\n", + err->ee_errno, err->ee_code); + }; tstamp = ((int64_t) err->ee_data) << 32 | err->ee_info; tstamp -= (int64_t) glob_tstart; tstamp /= 1000 * 1000; - fprintf(stderr, "send: pkt %c at %" PRId64 "ms dropped\n", - data[ret - 1], tstamp); + fprintf(stderr, "send: pkt %c at %" PRId64 "ms dropped: %s\n", + data[ret - 1], tstamp, reason); msg.msg_flags = 0; msg.msg_controllen = sizeof(control); diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 9c0f758310fe..a179f0dca8ce 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -3,7 +3,7 @@ TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ - nft_concat_range.sh \ + nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh LDLIBS = -lmnl diff --git a/tools/testing/selftests/netfilter/nft_conntrack_helper.sh b/tools/testing/selftests/netfilter/nft_conntrack_helper.sh new file mode 100755 index 000000000000..edf0a48da6bf --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_conntrack_helper.sh @@ -0,0 +1,175 @@ +#!/bin/bash +# +# This tests connection tracking helper assignment: +# 1. can attach ftp helper to a connection from nft ruleset. +# 2. auto-assign still works. +# +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +sfx=$(mktemp -u "XXXXXXXX") +ns1="ns1-$sfx" +ns2="ns2-$sfx" +testipv6=1 + +cleanup() +{ + ip netns del ${ns1} + ip netns del ${ns2} +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +conntrack -V > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without conntrack tool" + exit $ksft_skip +fi + +which nc >/dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without netcat tool" + exit $ksft_skip +fi + +trap cleanup EXIT + +ip netns add ${ns1} +ip netns add ${ns2} + +ip link add veth0 netns ${ns1} type veth peer name veth0 netns ${ns2} > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: No virtual ethernet pair device support in kernel" + exit $ksft_skip +fi + +ip -net ${ns1} link set lo up +ip -net ${ns1} link set veth0 up + +ip -net ${ns2} link set lo up +ip -net ${ns2} link set veth0 up + +ip -net ${ns1} addr add 10.0.1.1/24 dev veth0 +ip -net ${ns1} addr add dead:1::1/64 dev veth0 + +ip -net ${ns2} addr add 10.0.1.2/24 dev veth0 +ip -net ${ns2} addr add dead:1::2/64 dev veth0 + +load_ruleset_family() { + local family=$1 + local ns=$2 + +ip netns exec ${ns} nft -f - <<EOF +table $family raw { + ct helper ftp { + type "ftp" protocol tcp + } + chain pre { + type filter hook prerouting priority 0; policy accept; + tcp dport 2121 ct helper set "ftp" + } + chain output { + type filter hook output priority 0; policy accept; + tcp dport 2121 ct helper set "ftp" + } +} +EOF + return $? +} + +check_for_helper() +{ + local netns=$1 + local message=$2 + local port=$3 + + ip netns exec ${netns} conntrack -L -p tcp --dport $port 2> /dev/null |grep -q 'helper=ftp' + if [ $? -ne 0 ] ; then + echo "FAIL: ${netns} did not show attached helper $message" 1>&2 + ret=1 + fi + + echo "PASS: ${netns} connection on port $port has ftp helper attached" 1>&2 + return 0 +} + +test_helper() +{ + local port=$1 + local msg=$2 + + sleep 3 | ip netns exec ${ns2} nc -w 2 -l -p $port > /dev/null & + + sleep 1 + sleep 1 | ip netns exec ${ns1} nc -w 2 10.0.1.2 $port > /dev/null & + + check_for_helper "$ns1" "ip $msg" $port + check_for_helper "$ns2" "ip $msg" $port + + wait + + if [ $testipv6 -eq 0 ] ;then + return 0 + fi + + ip netns exec ${ns1} conntrack -F 2> /dev/null + ip netns exec ${ns2} conntrack -F 2> /dev/null + + sleep 3 | ip netns exec ${ns2} nc -w 2 -6 -l -p $port > /dev/null & + + sleep 1 + sleep 1 | ip netns exec ${ns1} nc -w 2 -6 dead:1::2 $port > /dev/null & + + check_for_helper "$ns1" "ipv6 $msg" $port + check_for_helper "$ns2" "ipv6 $msg" $port + + wait +} + +load_ruleset_family ip ${ns1} +if [ $? -ne 0 ];then + echo "FAIL: ${ns1} cannot load ip ruleset" 1>&2 + exit 1 +fi + +load_ruleset_family ip6 ${ns1} +if [ $? -ne 0 ];then + echo "SKIP: ${ns1} cannot load ip6 ruleset" 1>&2 + testipv6=0 +fi + +load_ruleset_family inet ${ns2} +if [ $? -ne 0 ];then + echo "SKIP: ${ns1} cannot load inet ruleset" 1>&2 + load_ruleset_family ip ${ns2} + if [ $? -ne 0 ];then + echo "FAIL: ${ns2} cannot load ip ruleset" 1>&2 + exit 1 + fi + + if [ $testipv6 -eq 1 ] ;then + load_ruleset_family ip6 ${ns2} + if [ $? -ne 0 ];then + echo "FAIL: ${ns2} cannot load ip6 ruleset" 1>&2 + exit 1 + fi + fi +fi + +test_helper 2121 "set via ruleset" +ip netns exec ${ns1} sysctl -q 'net.netfilter.nf_conntrack_helper=1' +ip netns exec ${ns2} sysctl -q 'net.netfilter.nf_conntrack_helper=1' +test_helper 21 "auto-assign" + +exit $ret diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index c1921a53dbed..8d728eda783d 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -95,4 +95,9 @@ static inline int sys_pidfd_getfd(int pidfd, int fd, int flags) return syscall(__NR_pidfd_getfd, pidfd, fd, flags); } +static inline int sys_memfd_create(const char *name, unsigned int flags) +{ + return syscall(__NR_memfd_create, name, flags); +} + #endif /* __PIDFD_H */ diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c index 401a7c1d0312..84b65ecccb04 100644 --- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c @@ -34,11 +34,6 @@ static int sys_kcmp(pid_t pid1, pid_t pid2, int type, unsigned long idx1, return syscall(__NR_kcmp, pid1, pid2, type, idx1, idx2); } -static int sys_memfd_create(const char *name, unsigned int flags) -{ - return syscall(__NR_memfd_create, name, flags); -} - static int __child(int sk, int memfd) { int ret; diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c index 133ec5b6cda8..9418108eae13 100644 --- a/tools/testing/selftests/pidfd/pidfd_setns_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c @@ -470,4 +470,16 @@ TEST_F(current_nsset, no_foul_play) } } +TEST(setns_einval) +{ + int fd; + + fd = sys_memfd_create("rostock", 0); + EXPECT_GT(fd, 0); + + ASSERT_NE(setns(fd, 0), 0); + EXPECT_EQ(errno, EINVAL); + close(fd); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index ca35dd8848b0..af3df79d8163 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -7,7 +7,7 @@ noarg: # The EBB handler is 64-bit code and everything links against it CFLAGS += -m64 -TMPOUT = $(OUTPUT)/ +TMPOUT = $(OUTPUT)/TMPDIR/ # Toolchains may build PIE by default which breaks the assembly no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 47a3082b6661..503982b8f295 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -260,10 +260,10 @@ 255 ] ], - "cmdUnderTest": "$TC action add action bpf bytecode '4,40 0 0 12,21 0 1 2054,6 0 0 262144,6 0 0 0' index 4294967296 cookie 12345", + "cmdUnderTest": "$TC action add action bpf bytecode '4,40 0 0 12,21 0 1 2054,6 0 0 262144,6 0 0 0' index 4294967296 cookie 123456", "expExitCode": "255", "verifyCmd": "$TC action ls action bpf", - "matchPattern": "action order [0-9]*: bpf bytecode '4,40 0 0 12,21 0 1 2048,6 0 0 262144,6 0 0 0' default-action pipe.*cookie 12345", + "matchPattern": "action order [0-9]*: bpf bytecode '4,40 0 0 12,21 0 1 2048,6 0 0 262144,6 0 0 0' default-action pipe.*cookie 123456", "matchCount": "0", "teardown": [ "$TC action flush action bpf" diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json index 88ec134872e4..072febf25f55 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json @@ -469,7 +469,7 @@ 255 ] ], - "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie 123456789abcde \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", "expExitCode": "0", "verifyCmd": "$TC actions ls action csum", "matchPattern": "^[ \t]+index [0-9]* ref", @@ -492,7 +492,7 @@ 1, 255 ], - "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"" + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie 123456789abcde \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"" ], "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", "expExitCode": "0", diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json index fbeb9197697d..d06346968bcb 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json @@ -629,7 +629,7 @@ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022 index 1", "expExitCode": "0", "verifyCmd": "$TC actions get action tunnel_key index 1", - "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022.*index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt[s]? 0102:80:00880022.*index 1", "matchCount": "1", "teardown": [ "$TC actions flush action tunnel_key" @@ -653,7 +653,7 @@ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022,0408:42:0040007611223344,0111:02:1020304011223344 index 1", "expExitCode": "0", "verifyCmd": "$TC actions get action tunnel_key index 1", - "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022,0408:42:0040007611223344,0111:02:1020304011223344.*index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt[s]? 0102:80:00880022,0408:42:0040007611223344,0111:02:1020304011223344.*index 1", "matchCount": "1", "teardown": [ "$TC actions flush action tunnel_key" @@ -677,7 +677,7 @@ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 824212:80:00880022 index 1", "expExitCode": "255", "verifyCmd": "$TC actions get action tunnel_key index 1", - "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 824212:80:00880022.*index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt[s]? 824212:80:00880022.*index 1", "matchCount": "0", "teardown": [ "$TC actions flush action tunnel_key" @@ -701,7 +701,7 @@ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:4224:00880022 index 1", "expExitCode": "255", "verifyCmd": "$TC actions get action tunnel_key index 1", - "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:4224:00880022.*index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt[s]? 0102:4224:00880022.*index 1", "matchCount": "0", "teardown": [ "$TC actions flush action tunnel_key" @@ -725,7 +725,7 @@ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:4288 index 1", "expExitCode": "255", "verifyCmd": "$TC actions get action tunnel_key index 1", - "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:4288.*index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt[s]? 0102:80:4288.*index 1", "matchCount": "0", "teardown": [ "$TC actions flush action tunnel_key" @@ -749,7 +749,7 @@ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:4288428822 index 1", "expExitCode": "255", "verifyCmd": "$TC actions get action tunnel_key index 1", - "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:4288428822.*index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt[s]? 0102:80:4288428822.*index 1", "matchCount": "0", "teardown": [ "$TC actions flush action tunnel_key" @@ -773,7 +773,7 @@ "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022,0408:42: index 1", "expExitCode": "255", "verifyCmd": "$TC actions get action tunnel_key index 1", - "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022,0408:42:.*index 1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt[s]? 0102:80:00880022,0408:42:.*index 1", "matchCount": "0", "teardown": [ "$TC actions flush action tunnel_key" @@ -818,12 +818,12 @@ 1, 255 ], - "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 index 1 cookie aabbccddeeff112233445566778800a" + "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 index 1 cookie 123456" ], - "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 11.11.11.1 dst_ip 21.21.21.2 dst_port 3129 id 11 csum reclassify index 1 cookie a1b1c1d1", + "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 11.11.11.1 dst_ip 21.21.21.2 dst_port 3129 id 11 csum reclassify index 1 cookie 123456", "expExitCode": "0", "verifyCmd": "$TC actions get action tunnel_key index 1", - "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 11.11.11.1.*dst_ip 21.21.21.2.*key_id 11.*dst_port 3129.*csum reclassify.*index 1.*cookie a1b1c1d1", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 11.11.11.1.*dst_ip 21.21.21.2.*key_id 11.*dst_port 3129.*csum reclassify.*index 1.*cookie 123456", "matchCount": "1", "teardown": [ "$TC actions flush action tunnel_key" diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 17a1f53ceba0..d77f4829f1e0 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -587,9 +587,20 @@ ip0 link set wg0 up kill $ncat_pid ip0 link del wg0 +# Ensure there aren't circular reference loops +ip1 link add wg1 type wireguard +ip2 link add wg2 type wireguard +ip1 link set wg1 netns $netns2 +ip2 link set wg2 netns $netns1 +pp ip netns delete $netns1 +pp ip netns delete $netns2 +pp ip netns add $netns1 +pp ip netns add $netns2 + +sleep 2 # Wait for cleanup and grace periods declare -A objects while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do - [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue + [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ ?[0-9]*)\ .*(created|destroyed).* ]] || continue objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}" done < /dev/kmsg alldeleted=1 diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 6683b4a70b05..caab980211a6 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -11,6 +11,7 @@ #include <linux/compiler.h> #include <linux/types.h> +#include <linux/list.h> #include <linux/printk.h> #include <linux/bug.h> #include <errno.h> @@ -135,10 +136,4 @@ static inline void free_page(unsigned long addr) (void) (&_min1 == &_min2); \ _min1 < _min2 ? _min1 : _min2; }) -/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */ -#define list_add_tail(a, b) do {} while (0) -#define list_del(a) do {} while (0) -#define list_for_each_entry(a, b, c) while (0) -/* end of stubs */ - #endif /* KERNEL_H */ diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index b751350d4ce8..5d90254ddae4 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -11,12 +11,11 @@ struct device { struct virtio_device { struct device dev; u64 features; + struct list_head vqs; }; struct virtqueue { - /* TODO: commented as list macros are empty stubs for now. - * Broken but enough for virtio_ring.c - * struct list_head list; */ + struct list_head list; void (*callback)(struct virtqueue *vq); const char *name; struct virtio_device *vdev; diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index b427def67e7e..cb3f29c09aff 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #define _GNU_SOURCE #include <getopt.h> +#include <limits.h> #include <string.h> #include <poll.h> #include <sys/eventfd.h> @@ -18,6 +19,8 @@ #include <linux/virtio_ring.h> #include "../../drivers/vhost/test.h" +#define RANDOM_BATCH -1 + /* Unused */ void *__kmalloc_fake, *__kfree_ignore_start, *__kfree_ignore_end; @@ -43,6 +46,10 @@ struct vdev_info { struct vhost_memory *mem; }; +static const struct vhost_vring_file no_backend = { .fd = -1 }, + backend = { .fd = 1 }; +static const struct vhost_vring_state null_state = {}; + bool vq_notify(struct virtqueue *vq) { struct vq_info *info = vq->priv; @@ -88,6 +95,19 @@ void vhost_vq_setup(struct vdev_info *dev, struct vq_info *info) assert(r >= 0); } +static void vq_reset(struct vq_info *info, int num, struct virtio_device *vdev) +{ + if (info->vq) + vring_del_virtqueue(info->vq); + + memset(info->ring, 0, vring_size(num, 4096)); + vring_init(&info->vring, num, info->ring, 4096); + info->vq = __vring_new_virtqueue(info->idx, info->vring, vdev, true, + false, vq_notify, vq_callback, "test"); + assert(info->vq); + info->vq->priv = info; +} + static void vq_info_add(struct vdev_info *dev, int num) { struct vq_info *info = &dev->vqs[dev->nvqs]; @@ -97,14 +117,7 @@ static void vq_info_add(struct vdev_info *dev, int num) info->call = eventfd(0, EFD_NONBLOCK); r = posix_memalign(&info->ring, 4096, vring_size(num, 4096)); assert(r >= 0); - memset(info->ring, 0, vring_size(num, 4096)); - vring_init(&info->vring, num, info->ring, 4096); - info->vq = vring_new_virtqueue(info->idx, - info->vring.num, 4096, &dev->vdev, - true, false, info->ring, - vq_notify, vq_callback, "test"); - assert(info->vq); - info->vq->priv = info; + vq_reset(info, num, &dev->vdev); vhost_vq_setup(dev, info); dev->fds[info->idx].fd = info->call; dev->fds[info->idx].events = POLLIN; @@ -116,6 +129,7 @@ static void vdev_info_init(struct vdev_info* dev, unsigned long long features) int r; memset(dev, 0, sizeof *dev); dev->vdev.features = features; + INIT_LIST_HEAD(&dev->vdev.vqs); dev->buf_size = 1024; dev->buf = malloc(dev->buf_size); assert(dev->buf); @@ -152,41 +166,93 @@ static void wait_for_interrupt(struct vdev_info *dev) } static void run_test(struct vdev_info *dev, struct vq_info *vq, - bool delayed, int bufs) + bool delayed, int batch, int reset_n, int bufs) { struct scatterlist sl; - long started = 0, completed = 0; - long completed_before; + long started = 0, completed = 0, next_reset = reset_n; + long completed_before, started_before; int r, test = 1; unsigned len; long long spurious = 0; + const bool random_batch = batch == RANDOM_BATCH; + r = ioctl(dev->control, VHOST_TEST_RUN, &test); assert(r >= 0); + if (!reset_n) { + next_reset = INT_MAX; + } + for (;;) { virtqueue_disable_cb(vq->vq); completed_before = completed; + started_before = started; do { - if (started < bufs) { + const bool reset = completed > next_reset; + if (random_batch) + batch = (random() % vq->vring.num) + 1; + + while (started < bufs && + (started - completed) < batch) { sg_init_one(&sl, dev->buf, dev->buf_size); r = virtqueue_add_outbuf(vq->vq, &sl, 1, dev->buf + started, GFP_ATOMIC); - if (likely(r == 0)) { - ++started; - if (unlikely(!virtqueue_kick(vq->vq))) + if (unlikely(r != 0)) { + if (r == -ENOSPC && + started > started_before) + r = 0; + else r = -1; + break; } - } else + + ++started; + + if (unlikely(!virtqueue_kick(vq->vq))) { + r = -1; + break; + } + } + + if (started >= bufs) r = -1; + if (reset) { + r = ioctl(dev->control, VHOST_TEST_SET_BACKEND, + &no_backend); + assert(!r); + } + /* Flush out completed bufs if any */ - if (virtqueue_get_buf(vq->vq, &len)) { + while (virtqueue_get_buf(vq->vq, &len)) { ++completed; r = 0; } + if (reset) { + struct vhost_vring_state s = { .index = 0 }; + + vq_reset(vq, vq->vring.num, &dev->vdev); + + r = ioctl(dev->control, VHOST_GET_VRING_BASE, + &s); + assert(!r); + + s.num = 0; + r = ioctl(dev->control, VHOST_SET_VRING_BASE, + &null_state); + assert(!r); + + r = ioctl(dev->control, VHOST_TEST_SET_BACKEND, + &backend); + assert(!r); + + started = completed; + while (completed > next_reset) + next_reset += completed; + } } while (r == 0); - if (completed == completed_before) + if (completed == completed_before && started == started_before) ++spurious; assert(completed <= bufs); assert(started <= bufs); @@ -203,7 +269,9 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq, test = 0; r = ioctl(dev->control, VHOST_TEST_RUN, &test); assert(r >= 0); - fprintf(stderr, "spurious wakeups: 0x%llx\n", spurious); + fprintf(stderr, + "spurious wakeups: 0x%llx started=0x%lx completed=0x%lx\n", + spurious, started, completed); } const char optstring[] = "h"; @@ -245,6 +313,16 @@ const struct option longopts[] = { .val = 'd', }, { + .name = "batch", + .val = 'b', + .has_arg = required_argument, + }, + { + .name = "reset", + .val = 'r', + .has_arg = optional_argument, + }, + { } }; @@ -255,6 +333,8 @@ static void help(void) " [--no-event-idx]" " [--no-virtio-1]" " [--delayed-interrupt]" + " [--batch=random/N]" + " [--reset=N]" "\n"); } @@ -263,6 +343,7 @@ int main(int argc, char **argv) struct vdev_info dev; unsigned long long features = (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | (1ULL << VIRTIO_RING_F_EVENT_IDX) | (1ULL << VIRTIO_F_VERSION_1); + long batch = 1, reset = 0; int o; bool delayed = false; @@ -289,6 +370,24 @@ int main(int argc, char **argv) case 'D': delayed = true; break; + case 'b': + if (0 == strcmp(optarg, "random")) { + batch = RANDOM_BATCH; + } else { + batch = strtol(optarg, NULL, 10); + assert(batch > 0); + assert(batch < (long)INT_MAX + 1); + } + break; + case 'r': + if (!optarg) { + reset = 1; + } else { + reset = strtol(optarg, NULL, 10); + assert(reset > 0); + assert(reset < (long)INT_MAX + 1); + } + break; default: assert(0); break; @@ -298,6 +397,6 @@ int main(int argc, char **argv) done: vdev_info_init(&dev, features); vq_info_add(&dev, 256); - run_test(&dev, &dev.vqs[0], delayed, 0x100000); + run_test(&dev, &dev.vqs[0], delayed, batch, reset, 0x100000); return 0; } diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c index 293653463303..fa87b58bd5fa 100644 --- a/tools/virtio/vringh_test.c +++ b/tools/virtio/vringh_test.c @@ -307,6 +307,7 @@ static int parallel_test(u64 features, close(to_host[0]); gvdev.vdev.features = features; + INIT_LIST_HEAD(&gvdev.vdev.vqs); gvdev.to_host_fd = to_host[1]; gvdev.notifies = 0; @@ -453,6 +454,7 @@ int main(int argc, char *argv[]) getrange = getrange_iov; vdev.features = 0; + INIT_LIST_HEAD(&vdev.vqs); while (argv[1]) { if (strcmp(argv[1], "--indirect") == 0) |