diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index eacf8983e230..dcbb6f6caf6d 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2170,6 +2170,12 @@ nexthop_compat_mode - BOOLEAN understands the new API, this sysctl can be disabled to achieve full performance benefits of the new API by disabling the nexthop expansion and extraneous notifications. + + Note that as a backward-compatible mode, dumping of modern features + might be incomplete or wrong. For example, resilient groups will not be + shown as such, but rather as just a list of next hops. Also weights that + do not fit into 8 bits will show incorrectly. + Default: true (backward compat mode) fib_notify_on_flag_change - INTEGER diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst index 53d1996460ab..12f429359a82 100644 --- a/Documentation/power/runtime_pm.rst +++ b/Documentation/power/runtime_pm.rst @@ -347,7 +347,9 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: `int pm_runtime_resume_and_get(struct device *dev);` - run pm_runtime_resume(dev) and if successful, increment the device's - usage counter; return the result of pm_runtime_resume + usage counter; returns 0 on success (whether or not the device's + runtime PM status was already 'active') or the error code from + pm_runtime_resume() on failure. `int pm_request_idle(struct device *dev);` - submit a request to execute the subsystem-level idle callback for the diff --git a/Makefile b/Makefile index f158bfe6407a..c10952585c14 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 12 -SUBLEVEL = 5 +SUBLEVEL = 6 EXTRAVERSION = NAME = Baby Opossum Posse diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index ff8c4e1b847e..fbed433283c9 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1535,6 +1535,7 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_DF2); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR); + val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MPAM_frac); break; case SYS_ID_AA64PFR2_EL1: /* We only expose FPMR */ @@ -1724,6 +1725,13 @@ static u64 read_sanitised_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, val &= ~ID_AA64PFR0_EL1_AMU_MASK; + /* + * MPAM is disabled by default as KVM also needs a set of PARTID to + * program the MPAMVPMx_EL2 PARTID remapping registers with. But some + * older kernels let the guest see the ID bit. + */ + val &= ~ID_AA64PFR0_EL1_MPAM_MASK; + return val; } @@ -1834,6 +1842,42 @@ static int set_id_dfr0_el1(struct kvm_vcpu *vcpu, return set_id_reg(vcpu, rd, val); } +static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, u64 user_val) +{ + u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + u64 mpam_mask = ID_AA64PFR0_EL1_MPAM_MASK; + + /* + * Commit 011e5f5bf529f ("arm64/cpufeature: Add remaining feature bits + * in ID_AA64PFR0 register") exposed the MPAM field of AA64PFR0_EL1 to + * guests, but didn't add trap handling. KVM doesn't support MPAM and + * always returns an UNDEF for these registers. The guest must see 0 + * for this field. + * + * But KVM must also accept values from user-space that were provided + * by KVM. On CPUs that support MPAM, permit user-space to write + * the sanitizied value to ID_AA64PFR0_EL1.MPAM, but ignore this field. + */ + if ((hw_val & mpam_mask) == (user_val & mpam_mask)) + user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK; + + return set_id_reg(vcpu, rd, user_val); +} + +static int set_id_aa64pfr1_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, u64 user_val) +{ + u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); + u64 mpam_mask = ID_AA64PFR1_EL1_MPAM_frac_MASK; + + /* See set_id_aa64pfr0_el1 for comment about MPAM */ + if ((hw_val & mpam_mask) == (user_val & mpam_mask)) + user_val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK; + + return set_id_reg(vcpu, rd, user_val); +} + /* * cpufeature ID register user accessors * @@ -2377,7 +2421,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ID_AA64PFR0_EL1), .access = access_id_reg, .get_user = get_id_reg, - .set_user = set_id_reg, + .set_user = set_id_aa64pfr0_el1, .reset = read_sanitised_id_aa64pfr0_el1, .val = ~(ID_AA64PFR0_EL1_AMU | ID_AA64PFR0_EL1_MPAM | @@ -2385,7 +2429,12 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_AA64PFR0_EL1_RAS | ID_AA64PFR0_EL1_AdvSIMD | ID_AA64PFR0_EL1_FP), }, - ID_WRITABLE(ID_AA64PFR1_EL1, ~(ID_AA64PFR1_EL1_PFAR | + { SYS_DESC(SYS_ID_AA64PFR1_EL1), + .access = access_id_reg, + .get_user = get_id_reg, + .set_user = set_id_aa64pfr1_el1, + .reset = kvm_read_sanitised_id_reg, + .val = ~(ID_AA64PFR1_EL1_PFAR | ID_AA64PFR1_EL1_DF2 | ID_AA64PFR1_EL1_MTEX | ID_AA64PFR1_EL1_THE | @@ -2397,7 +2446,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_AA64PFR1_EL1_RES0 | ID_AA64PFR1_EL1_MPAM_frac | ID_AA64PFR1_EL1_RAS_frac | - ID_AA64PFR1_EL1_MTE)), + ID_AA64PFR1_EL1_MTE), }, ID_WRITABLE(ID_AA64PFR2_EL1, ID_AA64PFR2_EL1_FPMR), ID_UNALLOCATED(4,3), ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0), diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h index 7388edd88986..d08bf7fb3aee 100644 --- a/arch/riscv/include/asm/kfence.h +++ b/arch/riscv/include/asm/kfence.h @@ -22,7 +22,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) else set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT)); - flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_disable(); + local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_enable(); return true; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 26c886db4fb3..2b3c152d3c91 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -227,7 +227,7 @@ static void __init init_resources(void) static void __init parse_dtb(void) { /* Early scan of device tree from init memory */ - if (early_init_dt_scan(dtb_early_va, __pa(dtb_early_va))) { + if (early_init_dt_scan(dtb_early_va, dtb_early_pa)) { const char *name = of_flat_dt_get_machine_name(); if (name) { diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 0e8c20adcd98..fc53ce748c80 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1566,7 +1566,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) pmd_clear(pmd); } -static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, bool is_vmemmap) { struct page *page = pud_page(*pud); struct ptdesc *ptdesc = page_ptdesc(page); @@ -1579,7 +1579,8 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) return; } - pagetable_pmd_dtor(ptdesc); + if (!is_vmemmap) + pagetable_pmd_dtor(ptdesc); if (PageReserved(page)) free_reserved_page(page); else @@ -1703,7 +1704,7 @@ static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, un remove_pmd_mapping(pmd_base, addr, next, is_vmemmap, altmap); if (pgtable_l4_enabled) - free_pmd_table(pmd_base, pudp); + free_pmd_table(pmd_base, pudp, is_vmemmap); } } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index fa5ea65de0d0..6188650707ab 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1468,7 +1468,7 @@ void intel_pmu_pebs_enable(struct perf_event *event) * hence we need to drain when changing said * size. */ - intel_pmu_drain_large_pebs(cpuc); + intel_pmu_drain_pebs_buffer(); adaptive_pebs_record_size_update(); wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg); cpuc->active_pebs_data_cfg = pebs_data_cfg; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 4a686f0e5dbf..2d776635aa53 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -212,6 +212,8 @@ static inline unsigned long long l1tf_pfn_limit(void) return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } +void init_cpu_devs(void); +void get_cpu_vendor(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 125c407e2abe..41502bd2afd6 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -65,4 +65,19 @@ extern bool __static_call_fixup(void *tramp, u8 op, void *dest); +extern void __static_call_update_early(void *tramp, void *func); + +#define static_call_update_early(name, _func) \ +({ \ + typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \ + if (static_call_initialized) { \ + __static_call_update(&STATIC_CALL_KEY(name), \ + STATIC_CALL_TRAMP_ADDR(name), __F);\ + } else { \ + WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \ + __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\ + __F); \ + } \ +}) + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index ab7382f92aff..96bda43538ee 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -8,7 +8,7 @@ #include #ifdef CONFIG_X86_32 -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { asm volatile ( "pushfl\n\t" @@ -19,7 +19,7 @@ static inline void iret_to_self(void) : ASM_CALL_CONSTRAINT : : "memory"); } #else -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { unsigned int tmp; @@ -55,7 +55,7 @@ static inline void iret_to_self(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ -static inline void sync_core(void) +static __always_inline void sync_core(void) { /* * The SERIALIZE instruction is the most straightforward way to diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a2dd24947eb8..97771b9d33af 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -39,9 +39,11 @@ #include #include #include +#include #include +#include #include #include #include @@ -86,11 +88,20 @@ struct xen_dm_op_buf; * there aren't more than 5 arguments...) */ -extern struct { char _entry[32]; } hypercall_page[]; +void xen_hypercall_func(void); +DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); -#define __HYPERCALL "call hypercall_page+%c[offset]" -#define __HYPERCALL_ENTRY(x) \ - [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0])) +#ifdef MODULE +#define __ADDRESSABLE_xen_hypercall +#else +#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall) +#endif + +#define __HYPERCALL \ + __ADDRESSABLE_xen_hypercall \ + "call __SCT__xen_hypercall" + +#define __HYPERCALL_ENTRY(x) "a" (x) #ifdef CONFIG_X86_32 #define __HYPERCALL_RETREG "eax" @@ -148,7 +159,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_0ARG(); \ asm volatile (__HYPERCALL \ : __HYPERCALL_0PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER0); \ (type)__res; \ }) @@ -159,7 +170,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_1ARG(a1); \ asm volatile (__HYPERCALL \ : __HYPERCALL_1PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER1); \ (type)__res; \ }) @@ -170,7 +181,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_2ARG(a1, a2); \ asm volatile (__HYPERCALL \ : __HYPERCALL_2PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER2); \ (type)__res; \ }) @@ -181,7 +192,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_3ARG(a1, a2, a3); \ asm volatile (__HYPERCALL \ : __HYPERCALL_3PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER3); \ (type)__res; \ }) @@ -192,7 +203,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_4ARG(a1, a2, a3, a4); \ asm volatile (__HYPERCALL \ : __HYPERCALL_4PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER4); \ (type)__res; \ }) @@ -206,12 +217,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); - if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) - return -EINVAL; - - asm volatile(CALL_NOSPEC + asm volatile(__HYPERCALL : __HYPERCALL_5PARAM - : [thunk_target] "a" (&hypercall_page[call]) + : __HYPERCALL_ENTRY(call) : __HYPERCALL_CLOBBER5); return (long)__res; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 465647456753..f17d16607882 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -142,11 +142,6 @@ static bool skip_addr(void *dest) if (dest >= (void *)relocate_kernel && dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE) return true; -#endif -#ifdef CONFIG_XEN - if (dest >= (void *)hypercall_page && - dest < (void*)hypercall_page + PAGE_SIZE) - return true; #endif return false; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b17bcf9b67ee..f439763f45ae 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -868,7 +868,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -static void get_cpu_vendor(struct cpuinfo_x86 *c) +void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; int i; @@ -1652,15 +1652,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) detect_nopl(); } -void __init early_cpu_init(void) +void __init init_cpu_devs(void) { const struct cpu_dev *const *cdev; int count = 0; -#ifdef CONFIG_PROCESSOR_SELECT - pr_info("KERNEL supported cpus:\n"); -#endif - for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { const struct cpu_dev *cpudev = *cdev; @@ -1668,20 +1664,30 @@ void __init early_cpu_init(void) break; cpu_devs[count] = cpudev; count++; + } +} + +void __init early_cpu_init(void) +{ +#ifdef CONFIG_PROCESSOR_SELECT + unsigned int i, j; + + pr_info("KERNEL supported cpus:\n"); +#endif + + init_cpu_devs(); #ifdef CONFIG_PROCESSOR_SELECT - { - unsigned int j; - - for (j = 0; j < 2; j++) { - if (!cpudev->c_ident[j]) - continue; - pr_info(" %s %s\n", cpudev->c_vendor, - cpudev->c_ident[j]); - } + for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) { + for (j = 0; j < 2; j++) { + if (!cpu_devs[i]->c_ident[j]) + continue; + pr_info(" %s %s\n", cpu_devs[i]->c_vendor, + cpu_devs[i]->c_ident[j]); } -#endif } +#endif + early_identify_cpu(&boot_cpu_data); } diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 4eefaac64c6c..9eed0c144dad 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,6 +172,15 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); +noinstr void __static_call_update_early(void *tramp, void *func) +{ + BUG_ON(system_state != SYSTEM_BOOTING); + BUG_ON(!early_boot_irqs_disabled); + BUG_ON(static_call_initialized); + __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE); + sync_core(); +} + #ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 84e5adbd0925..b4f3784f27e9 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -2,6 +2,7 @@ #include #include +#include #include #include #include @@ -21,7 +22,8 @@ #include "xen-ops.h" -EXPORT_SYMBOL_GPL(hypercall_page); +DEFINE_STATIC_CALL(xen_hypercall, xen_hypercall_hvm); +EXPORT_STATIC_CALL_TRAMP(xen_hypercall); /* * Pointer to the xen_vcpu_info structure or @@ -68,6 +70,66 @@ EXPORT_SYMBOL(xen_start_flags); */ struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; +static __ref void xen_get_vendor(void) +{ + init_cpu_devs(); + cpu_detect(&boot_cpu_data); + get_cpu_vendor(&boot_cpu_data); +} + +void xen_hypercall_setfunc(void) +{ + if (static_call_query(xen_hypercall) != xen_hypercall_hvm) + return; + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + static_call_update(xen_hypercall, xen_hypercall_amd); + else + static_call_update(xen_hypercall, xen_hypercall_intel); +} + +/* + * Evaluate processor vendor in order to select the correct hypercall + * function for HVM/PVH guests. + * Might be called very early in boot before vendor has been set by + * early_cpu_init(). + */ +noinstr void *__xen_hypercall_setfunc(void) +{ + void (*func)(void); + + /* + * Xen is supported only on CPUs with CPUID, so testing for + * X86_FEATURE_CPUID is a test for early_cpu_init() having been + * run. + * + * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty + * dependency chain: it is being called via the xen_hypercall static + * call when running as a PVH or HVM guest. Hypercalls need to be + * noinstr due to PV guests using hypercalls in noinstr code. So we + * the PV guest requirement is not of interest here (xen_get_vendor() + * calls noinstr functions, and static_call_update_early() might do + * so, too). + */ + instrumentation_begin(); + + if (!boot_cpu_has(X86_FEATURE_CPUID)) + xen_get_vendor(); + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + func = xen_hypercall_amd; + else + func = xen_hypercall_intel; + + static_call_update_early(xen_hypercall, func); + + instrumentation_end(); + + return func; +} + static int xen_cpu_up_online(unsigned int cpu) { xen_init_lock_cpu(cpu); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 24d2957a4726..fe57ff85d004 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -106,15 +106,8 @@ static void __init init_hvm_pv_info(void) /* PVH set up hypercall page in xen_prepare_pvh(). */ if (xen_pvh_domain()) pv_info.name = "Xen PVH"; - else { - u64 pfn; - uint32_t msr; - + else pv_info.name = "Xen HVM"; - msr = cpuid_ebx(base + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - } xen_setup_features(); @@ -300,6 +293,10 @@ static uint32_t __init xen_platform_hvm(void) if (xen_pv_domain()) return 0; + /* Set correct hypercall function. */ + if (xen_domain) + xen_hypercall_setfunc(); + if (xen_pvh_domain() && nopv) { /* Guest booting via the Xen-PVH boot entry goes here */ pr_info("\"nopv\" parameter is ignored in PVH guest\n"); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index d6818c6cafda..a8eb7e0c473c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1341,6 +1341,9 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) xen_domain_type = XEN_PV_DOMAIN; xen_start_flags = xen_start_info->flags; + /* Interrupts are guaranteed to be off initially. */ + early_boot_irqs_disabled = true; + static_call_update_early(xen_hypercall, xen_hypercall_pv); xen_setup_features(); @@ -1431,7 +1434,6 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv)); local_irq_disable(); - early_boot_irqs_disabled = true; xen_raw_console_write("mapping kernel into physical memory\n"); xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index bf68c329fc01..0e3d930bcb89 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -129,17 +129,10 @@ static void __init pvh_arch_setup(void) void __init xen_pvh_init(struct boot_params *boot_params) { - u32 msr; - u64 pfn; - xen_pvh = 1; xen_domain_type = XEN_HVM_DOMAIN; xen_start_flags = pvh_start_info.flags; - msr = cpuid_ebx(xen_cpuid_base() + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - x86_init.oem.arch_setup = pvh_arch_setup; x86_init.oem.banner = xen_banner; diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 83189cf5cdce..b518f36d1ca2 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,9 +20,32 @@ #include #include +#include #include <../entry/calling.h> .pushsection .noinstr.text, "ax" +/* + * PV hypercall interface to the hypervisor. + * + * Called via inline asm(), so better preserve %rcx and %r11. + * + * Input: + * %eax: hypercall number + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %rax + */ +SYM_FUNC_START(xen_hypercall_pv) + ANNOTATE_NOENDBR + push %rcx + push %r11 + UNWIND_HINT_SAVE + syscall + UNWIND_HINT_RESTORE + pop %r11 + pop %rcx + RET +SYM_FUNC_END(xen_hypercall_pv) + /* * Disabling events is simply a matter of making the event mask * non-zero. @@ -176,7 +199,6 @@ SYM_CODE_START(xen_early_idt_handler_array) SYM_CODE_END(xen_early_idt_handler_array) __FINIT -hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* * Xen64 iret frame: * @@ -186,17 +208,28 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * cs * rip <-- standard iret frame * - * flags + * flags <-- xen_iret must push from here on * - * rcx } - * r11 }<-- pushed by hypercall page - * rsp->rax } + * rcx + * r11 + * rsp->rax */ +.macro xen_hypercall_iret + pushq $0 /* Flags */ + push %rcx + push %r11 + push %rax + mov $__HYPERVISOR_iret, %eax + syscall /* Do the IRET. */ +#ifdef CONFIG_MITIGATION_SLS + int3 +#endif +.endm + SYM_CODE_START(xen_iret) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_iret) /* @@ -301,8 +334,7 @@ SYM_CODE_START(xen_entry_SYSENTER_compat) ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_entry_SYSENTER_compat) SYM_CODE_END(xen_entry_SYSCALL_compat) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 758bcd47b72d..721a57700a3b 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -6,9 +6,11 @@ #include #include +#include #include #include +#include #include #include #include @@ -20,28 +22,6 @@ #include #include -.pushsection .noinstr.text, "ax" - .balign PAGE_SIZE -SYM_CODE_START(hypercall_page) - .rept (PAGE_SIZE / 32) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret - /* - * Xen will write the hypercall page, and sort out ENDBR. - */ - .skip 31, 0xcc - .endr - -#define HYPERCALL(n) \ - .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ - .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 -#include -#undef HYPERCALL -SYM_CODE_END(hypercall_page) -.popsection - #ifdef CONFIG_XEN_PV __INIT SYM_CODE_START(startup_xen) @@ -87,6 +67,87 @@ SYM_CODE_END(xen_cpu_bringup_again) #endif #endif + .pushsection .noinstr.text, "ax" +/* + * Xen hypercall interface to the hypervisor. + * + * Input: + * %eax: hypercall number + * 32-bit: + * %ebx, %ecx, %edx, %esi, %edi: args 1..5 for the hypercall + * 64-bit: + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %[er]ax + */ +SYM_FUNC_START(xen_hypercall_hvm) + ENDBR + FRAME_BEGIN + /* Save all relevant registers (caller save and arguments). */ +#ifdef CONFIG_X86_32 + push %eax + push %ebx + push %ecx + push %edx + push %esi + push %edi +#else + push %rax + push %rcx + push %rdx + push %rdi + push %rsi + push %r11 + push %r10 + push %r9 + push %r8 +#ifdef CONFIG_FRAME_POINTER + pushq $0 /* Dummy push for stack alignment. */ +#endif +#endif + /* Set the vendor specific function. */ + call __xen_hypercall_setfunc + /* Set ZF = 1 if AMD, Restore saved registers. */ +#ifdef CONFIG_X86_32 + lea xen_hypercall_amd, %ebx + cmp %eax, %ebx + pop %edi + pop %esi + pop %edx + pop %ecx + pop %ebx + pop %eax +#else + lea xen_hypercall_amd(%rip), %rbx + cmp %rax, %rbx +#ifdef CONFIG_FRAME_POINTER + pop %rax /* Dummy pop. */ +#endif + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %rsi + pop %rdi + pop %rdx + pop %rcx + pop %rax +#endif + /* Use correct hypercall function. */ + jz xen_hypercall_amd + jmp xen_hypercall_intel +SYM_FUNC_END(xen_hypercall_hvm) + +SYM_FUNC_START(xen_hypercall_amd) + vmmcall + RET +SYM_FUNC_END(xen_hypercall_amd) + +SYM_FUNC_START(xen_hypercall_intel) + vmcall + RET +SYM_FUNC_END(xen_hypercall_intel) + .popsection + ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6") ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0") @@ -115,7 +176,6 @@ SYM_CODE_END(xen_cpu_bringup_again) #else # define FEATURES_DOM0 0 #endif - ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page) ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long FEATURES_PV | FEATURES_PVH | FEATURES_DOM0) ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index e1b782e823e6..63c13a2ccf55 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -326,4 +326,13 @@ static inline void xen_smp_intr_free_pv(unsigned int cpu) {} static inline void xen_smp_count_cpus(void) { } #endif /* CONFIG_SMP */ +#ifdef CONFIG_XEN_PV +void xen_hypercall_pv(void); +#endif +void xen_hypercall_hvm(void); +void xen_hypercall_amd(void); +void xen_hypercall_intel(void); +void xen_hypercall_setfunc(void); +void *__xen_hypercall_setfunc(void); + #endif /* XEN_OPS_H */ diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index e68c725cf8d9..45a395862fbc 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1324,10 +1324,14 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { + struct blkcg *parent; + if (!refcount_dec_and_test(&blkcg->online_pin)) break; + + parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); + blkcg = parent; } while (blkcg); } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 384aa15e8260..a5894ec9696e 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1098,7 +1098,14 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum, iocg->child_active_sum); } else { - inuse = clamp_t(u32, inuse, 1, active); + /* + * It may be tempting to turn this into a clamp expression with + * a lower limit of 1 but active may be 0, which cannot be used + * as an upper limit in that situation. This expression allows + * active to clamp inuse unless it is 0, in which case inuse + * becomes 1. + */ + inuse = min(inuse, active) ?: 1; } iocg->last_inuse = iocg->inuse; diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 156e9bb07abf..cd5ea6eaa76b 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -275,15 +275,13 @@ void blk_mq_sysfs_unregister_hctxs(struct request_queue *q) struct blk_mq_hw_ctx *hctx; unsigned long i; - mutex_lock(&q->sysfs_dir_lock); + lockdep_assert_held(&q->sysfs_dir_lock); + if (!q->mq_sysfs_init_done) - goto unlock; + return; queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); - -unlock: - mutex_unlock(&q->sysfs_dir_lock); } int blk_mq_sysfs_register_hctxs(struct request_queue *q) @@ -292,9 +290,10 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q) unsigned long i; int ret = 0; - mutex_lock(&q->sysfs_dir_lock); + lockdep_assert_held(&q->sysfs_dir_lock); + if (!q->mq_sysfs_init_done) - goto unlock; + return ret; queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); @@ -302,8 +301,5 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q) break; } -unlock: - mutex_unlock(&q->sysfs_dir_lock); - return ret; } diff --git a/block/blk-mq.c b/block/blk-mq.c index b4fba7b398e5..cc1b32023838 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -43,6 +43,7 @@ static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd); +static DEFINE_MUTEX(blk_mq_cpuhp_lock); static void blk_mq_insert_request(struct request *rq, blk_insert_t flags); static void blk_mq_request_bypass_insert(struct request *rq, @@ -3740,13 +3741,91 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) return 0; } -static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) +static void __blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { - if (!(hctx->flags & BLK_MQ_F_STACKING)) + lockdep_assert_held(&blk_mq_cpuhp_lock); + + if (!(hctx->flags & BLK_MQ_F_STACKING) && + !hlist_unhashed(&hctx->cpuhp_online)) { cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, &hctx->cpuhp_online); - cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, - &hctx->cpuhp_dead); + INIT_HLIST_NODE(&hctx->cpuhp_online); + } + + if (!hlist_unhashed(&hctx->cpuhp_dead)) { + cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, + &hctx->cpuhp_dead); + INIT_HLIST_NODE(&hctx->cpuhp_dead); + } +} + +static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) +{ + mutex_lock(&blk_mq_cpuhp_lock); + __blk_mq_remove_cpuhp(hctx); + mutex_unlock(&blk_mq_cpuhp_lock); +} + +static void __blk_mq_add_cpuhp(struct blk_mq_hw_ctx *hctx) +{ + lockdep_assert_held(&blk_mq_cpuhp_lock); + + if (!(hctx->flags & BLK_MQ_F_STACKING) && + hlist_unhashed(&hctx->cpuhp_online)) + cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, + &hctx->cpuhp_online); + + if (hlist_unhashed(&hctx->cpuhp_dead)) + cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, + &hctx->cpuhp_dead); +} + +static void __blk_mq_remove_cpuhp_list(struct list_head *head) +{ + struct blk_mq_hw_ctx *hctx; + + lockdep_assert_held(&blk_mq_cpuhp_lock); + + list_for_each_entry(hctx, head, hctx_list) + __blk_mq_remove_cpuhp(hctx); +} + +/* + * Unregister cpuhp callbacks from exited hw queues + * + * Safe to call if this `request_queue` is live + */ +static void blk_mq_remove_hw_queues_cpuhp(struct request_queue *q) +{ + LIST_HEAD(hctx_list); + + spin_lock(&q->unused_hctx_lock); + list_splice_init(&q->unused_hctx_list, &hctx_list); + spin_unlock(&q->unused_hctx_lock); + + mutex_lock(&blk_mq_cpuhp_lock); + __blk_mq_remove_cpuhp_list(&hctx_list); + mutex_unlock(&blk_mq_cpuhp_lock); + + spin_lock(&q->unused_hctx_lock); + list_splice(&hctx_list, &q->unused_hctx_list); + spin_unlock(&q->unused_hctx_lock); +} + +/* + * Register cpuhp callbacks from all hw queues + * + * Safe to call if this `request_queue` is live + */ +static void blk_mq_add_hw_queues_cpuhp(struct request_queue *q) +{ + struct blk_mq_hw_ctx *hctx; + unsigned long i; + + mutex_lock(&blk_mq_cpuhp_lock); + queue_for_each_hw_ctx(q, hctx, i) + __blk_mq_add_cpuhp(hctx); + mutex_unlock(&blk_mq_cpuhp_lock); } /* @@ -3797,8 +3876,6 @@ static void blk_mq_exit_hctx(struct request_queue *q, if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); - blk_mq_remove_cpuhp(hctx); - xa_erase(&q->hctx_table, hctx_idx); spin_lock(&q->unused_hctx_lock); @@ -3815,6 +3892,7 @@ static void blk_mq_exit_hw_queues(struct request_queue *q, queue_for_each_hw_ctx(q, hctx, i) { if (i == nr_queue) break; + blk_mq_remove_cpuhp(hctx); blk_mq_exit_hctx(q, set, hctx, i); } } @@ -3878,6 +3956,8 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn); spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); + INIT_HLIST_NODE(&hctx->cpuhp_dead); + INIT_HLIST_NODE(&hctx->cpuhp_online); hctx->queue = q; hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED; @@ -4382,7 +4462,8 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, unsigned long i, j; /* protect against switching io scheduler */ - mutex_lock(&q->sysfs_lock); + lockdep_assert_held(&q->sysfs_lock); + for (i = 0; i < set->nr_hw_queues; i++) { int old_node; int node = blk_mq_get_hctx_node(set, i); @@ -4415,7 +4496,12 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, xa_for_each_start(&q->hctx_table, j, hctx, j) blk_mq_exit_hctx(q, set, hctx, j); - mutex_unlock(&q->sysfs_lock); + + /* unregister cpuhp callbacks for exited hctxs */ + blk_mq_remove_hw_queues_cpuhp(q); + + /* register cpuhp for new initialized hctxs */ + blk_mq_add_hw_queues_cpuhp(q); } int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, @@ -4441,10 +4527,14 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, xa_init(&q->hctx_table); + mutex_lock(&q->sysfs_lock); + blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; + mutex_unlock(&q->sysfs_lock); + INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); @@ -4463,6 +4553,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, return 0; err_hctxs: + mutex_unlock(&q->sysfs_lock); blk_mq_release(q); err_exit: q->mq_ops = NULL; @@ -4843,12 +4934,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head, return false; /* q->elevator needs protection from ->sysfs_lock */ - mutex_lock(&q->sysfs_lock); + lockdep_assert_held(&q->sysfs_lock); /* the check has to be done with holding sysfs_lock */ if (!q->elevator) { kfree(qe); - goto unlock; + goto out; } INIT_LIST_HEAD(&qe->node); @@ -4858,9 +4949,7 @@ static bool blk_mq_elv_switch_none(struct list_head *head, __elevator_get(qe->type); list_add(&qe->node, head); elevator_disable(q); -unlock: - mutex_unlock(&q->sysfs_lock); - +out: return true; } @@ -4889,11 +4978,9 @@ static void blk_mq_elv_switch_back(struct list_head *head, list_del(&qe->node); kfree(qe); - mutex_lock(&q->sysfs_lock); elevator_switch(q, t); /* drop the reference acquired in blk_mq_elv_switch_none */ elevator_put(t); - mutex_unlock(&q->sysfs_lock); } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, @@ -4913,8 +5000,11 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues) return; - list_for_each_entry(q, &set->tag_list, tag_set_list) + list_for_each_entry(q, &set->tag_list, tag_set_list) { + mutex_lock(&q->sysfs_dir_lock); + mutex_lock(&q->sysfs_lock); blk_mq_freeze_queue(q); + } /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done @@ -4970,8 +5060,11 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_elv_switch_back(&head, q); - list_for_each_entry(q, &set->tag_list, tag_set_list) + list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_unfreeze_queue(q); + mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->sysfs_dir_lock); + } /* Free the excess tags when nr_hw_queues shrink. */ for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 207577145c54..42c2cb97d778 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -690,11 +690,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, return res; } - blk_mq_freeze_queue(q); mutex_lock(&q->sysfs_lock); + blk_mq_freeze_queue(q); res = entry->store(disk, page, length); - mutex_unlock(&q->sysfs_lock); blk_mq_unfreeze_queue(q); + mutex_unlock(&q->sysfs_lock); return res; } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 0b1184176ce7..767bcbce74fa 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include "blk.h" @@ -41,7 +41,6 @@ static const char *const zone_cond_name[] = { /* * Per-zone write plug. * @node: hlist_node structure for managing the plug using a hash table. - * @link: To list the plug in the zone write plug error list of the disk. * @ref: Zone write plug reference counter. A zone write plug reference is * always at least 1 when the plug is hashed in the disk plug hash table. * The reference is incremented whenever a new BIO needing plugging is @@ -63,8 +62,7 @@ static const char *const zone_cond_name[] = { */ struct blk_zone_wplug { struct hlist_node node; - struct list_head link; - atomic_t ref; + refcount_t ref; spinlock_t lock; unsigned int flags; unsigned int zone_no; @@ -80,8 +78,8 @@ struct blk_zone_wplug { * - BLK_ZONE_WPLUG_PLUGGED: Indicates that the zone write plug is plugged, * that is, that write BIOs are being throttled due to a write BIO already * being executed or the zone write plug bio list is not empty. - * - BLK_ZONE_WPLUG_ERROR: Indicates that a write error happened which will be - * recovered with a report zone to update the zone write pointer offset. + * - BLK_ZONE_WPLUG_NEED_WP_UPDATE: Indicates that we lost track of a zone + * write pointer offset and need to update it. * - BLK_ZONE_WPLUG_UNHASHED: Indicates that the zone write plug was removed * from the disk hash table and that the initial reference to the zone * write plug set when the plug was first added to the hash table has been @@ -91,11 +89,9 @@ struct blk_zone_wplug { * freed once all remaining references from BIOs or functions are dropped. */ #define BLK_ZONE_WPLUG_PLUGGED (1U << 0) -#define BLK_ZONE_WPLUG_ERROR (1U << 1) +#define BLK_ZONE_WPLUG_NEED_WP_UPDATE (1U << 1) #define BLK_ZONE_WPLUG_UNHASHED (1U << 2) -#define BLK_ZONE_WPLUG_BUSY (BLK_ZONE_WPLUG_PLUGGED | BLK_ZONE_WPLUG_ERROR) - /** * blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX. * @zone_cond: BLK_ZONE_COND_XXX. @@ -115,6 +111,30 @@ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond) } EXPORT_SYMBOL_GPL(blk_zone_cond_str); +struct disk_report_zones_cb_args { + struct gendisk *disk; + report_zones_cb user_cb; + void *user_data; +}; + +static void disk_zone_wplug_sync_wp_offset(struct gendisk *disk, + struct blk_zone *zone); + +static int disk_report_zones_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct disk_report_zones_cb_args *args = data; + struct gendisk *disk = args->disk; + + if (disk->zone_wplugs_hash) + disk_zone_wplug_sync_wp_offset(disk, zone); + + if (!args->user_cb) + return 0; + + return args->user_cb(zone, idx, args->user_data); +} + /** * blkdev_report_zones - Get zones information * @bdev: Target block device @@ -139,6 +159,11 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, { struct gendisk *disk = bdev->bd_disk; sector_t capacity = get_capacity(disk); + struct disk_report_zones_cb_args args = { + .disk = disk, + .user_cb = cb, + .user_data = data, + }; if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones)) return -EOPNOTSUPP; @@ -146,7 +171,8 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, if (!nr_zones || sector >= capacity) return 0; - return disk->fops->report_zones(disk, sector, nr_zones, cb, data); + return disk->fops->report_zones(disk, sector, nr_zones, + disk_report_zones_cb, &args); } EXPORT_SYMBOL_GPL(blkdev_report_zones); @@ -417,7 +443,7 @@ static struct blk_zone_wplug *disk_get_zone_wplug(struct gendisk *disk, hlist_for_each_entry_rcu(zwplug, &disk->zone_wplugs_hash[idx], node) { if (zwplug->zone_no == zno && - atomic_inc_not_zero(&zwplug->ref)) { + refcount_inc_not_zero(&zwplug->ref)) { rcu_read_unlock(); return zwplug; } @@ -438,9 +464,9 @@ static void disk_free_zone_wplug_rcu(struct rcu_head *rcu_head) static inline void disk_put_zone_wplug(struct blk_zone_wplug *zwplug) { - if (atomic_dec_and_test(&zwplug->ref)) { + if (refcount_dec_and_test(&zwplug->ref)) { WARN_ON_ONCE(!bio_list_empty(&zwplug->bio_list)); - WARN_ON_ONCE(!list_empty(&zwplug->link)); + WARN_ON_ONCE(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED); WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_UNHASHED)); call_rcu(&zwplug->rcu_head, disk_free_zone_wplug_rcu); @@ -454,8 +480,8 @@ static inline bool disk_should_remove_zone_wplug(struct gendisk *disk, if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) return false; - /* If the zone write plug is still busy, it cannot be removed. */ - if (zwplug->flags & BLK_ZONE_WPLUG_BUSY) + /* If the zone write plug is still plugged, it cannot be removed. */ + if (zwplug->flags & BLK_ZONE_WPLUG_PLUGGED) return false; /* @@ -469,7 +495,7 @@ static inline bool disk_should_remove_zone_wplug(struct gendisk *disk, * taken when the plug was allocated and another reference taken by the * caller context). */ - if (atomic_read(&zwplug->ref) > 2) + if (refcount_read(&zwplug->ref) > 2) return false; /* We can remove zone write plugs for zones that are empty or full. */ @@ -538,12 +564,11 @@ static struct blk_zone_wplug *disk_get_and_lock_zone_wplug(struct gendisk *disk, return NULL; INIT_HLIST_NODE(&zwplug->node); - INIT_LIST_HEAD(&zwplug->link); - atomic_set(&zwplug->ref, 2); + refcount_set(&zwplug->ref, 2); spin_lock_init(&zwplug->lock); zwplug->flags = 0; zwplug->zone_no = zno; - zwplug->wp_offset = sector & (disk->queue->limits.chunk_sectors - 1); + zwplug->wp_offset = bdev_offset_from_zone_start(disk->part0, sector); bio_list_init(&zwplug->bio_list); INIT_WORK(&zwplug->bio_work, blk_zone_wplug_bio_work); zwplug->disk = disk; @@ -587,115 +612,22 @@ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug) } /* - * Abort (fail) all plugged BIOs of a zone write plug that are not aligned - * with the assumed write pointer location of the zone when the BIO will - * be unplugged. - */ -static void disk_zone_wplug_abort_unaligned(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - unsigned int wp_offset = zwplug->wp_offset; - struct bio_list bl = BIO_EMPTY_LIST; - struct bio *bio; - - while ((bio = bio_list_pop(&zwplug->bio_list))) { - if (disk_zone_is_full(disk, zwplug->zone_no, wp_offset) || - (bio_op(bio) != REQ_OP_ZONE_APPEND && - bio_offset_from_zone_start(bio) != wp_offset)) { - blk_zone_wplug_bio_io_error(zwplug, bio); - continue; - } - - wp_offset += bio_sectors(bio); - bio_list_add(&bl, bio); - } - - bio_list_merge(&zwplug->bio_list, &bl); -} - -static inline void disk_zone_wplug_set_error(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - unsigned long flags; - - if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) - return; - - /* - * At this point, we already have a reference on the zone write plug. - * However, since we are going to add the plug to the disk zone write - * plugs work list, increase its reference count. This reference will - * be dropped in disk_zone_wplugs_work() once the error state is - * handled, or in disk_zone_wplug_clear_error() if the zone is reset or - * finished. - */ - zwplug->flags |= BLK_ZONE_WPLUG_ERROR; - atomic_inc(&zwplug->ref); - - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - list_add_tail(&zwplug->link, &disk->zone_wplugs_err_list); - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); -} - -static inline void disk_zone_wplug_clear_error(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - unsigned long flags; - - if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR)) - return; - - /* - * We are racing with the error handling work which drops the reference - * on the zone write plug after handling the error state. So remove the - * plug from the error list and drop its reference count only if the - * error handling has not yet started, that is, if the zone write plug - * is still listed. - */ - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - if (!list_empty(&zwplug->link)) { - list_del_init(&zwplug->link); - zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR; - disk_put_zone_wplug(zwplug); - } - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); -} - -/* - * Set a zone write plug write pointer offset to either 0 (zone reset case) - * or to the zone size (zone finish case). This aborts all plugged BIOs, which - * is fine to do as doing a zone reset or zone finish while writes are in-flight - * is a mistake from the user which will most likely cause all plugged BIOs to - * fail anyway. + * Set a zone write plug write pointer offset to the specified value. + * This aborts all plugged BIOs, which is fine as this function is called for + * a zone reset operation, a zone finish operation or if the zone needs a wp + * update from a report zone after a write error. */ static void disk_zone_wplug_set_wp_offset(struct gendisk *disk, struct blk_zone_wplug *zwplug, unsigned int wp_offset) { - unsigned long flags; - - spin_lock_irqsave(&zwplug->lock, flags); - - /* - * Make sure that a BIO completion or another zone reset or finish - * operation has not already removed the plug from the hash table. - */ - if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) { - spin_unlock_irqrestore(&zwplug->lock, flags); - return; - } + lockdep_assert_held(&zwplug->lock); /* Update the zone write pointer and abort all plugged BIOs. */ + zwplug->flags &= ~BLK_ZONE_WPLUG_NEED_WP_UPDATE; zwplug->wp_offset = wp_offset; disk_zone_wplug_abort(zwplug); - /* - * Updating the write pointer offset puts back the zone - * in a good state. So clear the error flag and decrement the - * error count if we were in error state. - */ - disk_zone_wplug_clear_error(disk, zwplug); - /* * The zone write plug now has no BIO plugged: remove it from the * hash table so that it cannot be seen. The plug will be freed @@ -703,8 +635,58 @@ static void disk_zone_wplug_set_wp_offset(struct gendisk *disk, */ if (disk_should_remove_zone_wplug(disk, zwplug)) disk_remove_zone_wplug(disk, zwplug); +} +static unsigned int blk_zone_wp_offset(struct blk_zone *zone) +{ + switch (zone->cond) { + case BLK_ZONE_COND_IMP_OPEN: + case BLK_ZONE_COND_EXP_OPEN: + case BLK_ZONE_COND_CLOSED: + return zone->wp - zone->start; + case BLK_ZONE_COND_FULL: + return zone->len; + case BLK_ZONE_COND_EMPTY: + return 0; + case BLK_ZONE_COND_NOT_WP: + case BLK_ZONE_COND_OFFLINE: + case BLK_ZONE_COND_READONLY: + default: + /* + * Conventional, offline and read-only zones do not have a valid + * write pointer. + */ + return UINT_MAX; + } +} + +static void disk_zone_wplug_sync_wp_offset(struct gendisk *disk, + struct blk_zone *zone) +{ + struct blk_zone_wplug *zwplug; + unsigned long flags; + + zwplug = disk_get_zone_wplug(disk, zone->start); + if (!zwplug) + return; + + spin_lock_irqsave(&zwplug->lock, flags); + if (zwplug->flags & BLK_ZONE_WPLUG_NEED_WP_UPDATE) + disk_zone_wplug_set_wp_offset(disk, zwplug, + blk_zone_wp_offset(zone)); spin_unlock_irqrestore(&zwplug->lock, flags); + + disk_put_zone_wplug(zwplug); +} + +static int disk_zone_sync_wp_offset(struct gendisk *disk, sector_t sector) +{ + struct disk_report_zones_cb_args args = { + .disk = disk, + }; + + return disk->fops->report_zones(disk, sector, 1, + disk_report_zones_cb, &args); } static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, @@ -713,6 +695,7 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, struct gendisk *disk = bio->bi_bdev->bd_disk; sector_t sector = bio->bi_iter.bi_sector; struct blk_zone_wplug *zwplug; + unsigned long flags; /* Conventional zones cannot be reset nor finished. */ if (disk_zone_is_conv(disk, sector)) { @@ -720,6 +703,15 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, return true; } + /* + * No-wait reset or finish BIOs do not make much sense as the callers + * issue these as blocking operations in most cases. To avoid issues + * the BIO execution potentially failing with BLK_STS_AGAIN, warn about + * REQ_NOWAIT being set and ignore that flag. + */ + if (WARN_ON_ONCE(bio->bi_opf & REQ_NOWAIT)) + bio->bi_opf &= ~REQ_NOWAIT; + /* * If we have a zone write plug, set its write pointer offset to 0 * (reset case) or to the zone size (finish case). This will abort all @@ -729,7 +721,9 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, */ zwplug = disk_get_zone_wplug(disk, sector); if (zwplug) { + spin_lock_irqsave(&zwplug->lock, flags); disk_zone_wplug_set_wp_offset(disk, zwplug, wp_offset); + spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); } @@ -740,6 +734,7 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; struct blk_zone_wplug *zwplug; + unsigned long flags; sector_t sector; /* @@ -751,7 +746,9 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio) sector += disk->queue->limits.chunk_sectors) { zwplug = disk_get_zone_wplug(disk, sector); if (zwplug) { + spin_lock_irqsave(&zwplug->lock, flags); disk_zone_wplug_set_wp_offset(disk, zwplug, 0); + spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); } } @@ -759,9 +756,25 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio) return false; } -static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug, - struct bio *bio, unsigned int nr_segs) +static void disk_zone_wplug_schedule_bio_work(struct gendisk *disk, + struct blk_zone_wplug *zwplug) { + /* + * Take a reference on the zone write plug and schedule the submission + * of the next plugged BIO. blk_zone_wplug_bio_work() will release the + * reference we take here. + */ + WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED)); + refcount_inc(&zwplug->ref); + queue_work(disk->zone_wplugs_wq, &zwplug->bio_work); +} + +static inline void disk_zone_wplug_add_bio(struct gendisk *disk, + struct blk_zone_wplug *zwplug, + struct bio *bio, unsigned int nr_segs) +{ + bool schedule_bio_work = false; + /* * Grab an extra reference on the BIO request queue usage counter. * This reference will be reused to submit a request for the BIO for @@ -777,6 +790,16 @@ static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug, */ bio_clear_polled(bio); + /* + * REQ_NOWAIT BIOs are always handled using the zone write plug BIO + * work, which can block. So clear the REQ_NOWAIT flag and schedule the + * work if this is the first BIO we are plugging. + */ + if (bio->bi_opf & REQ_NOWAIT) { + schedule_bio_work = !(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED); + bio->bi_opf &= ~REQ_NOWAIT; + } + /* * Reuse the poll cookie field to store the number of segments when * split to the hardware limits. @@ -790,6 +813,11 @@ static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug, * at the tail of the list to preserve the sequential write order. */ bio_list_add(&zwplug->bio_list, bio); + + zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; + + if (schedule_bio_work) + disk_zone_wplug_schedule_bio_work(disk, zwplug); } /* @@ -902,13 +930,23 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug, { struct gendisk *disk = bio->bi_bdev->bd_disk; + /* + * If we lost track of the zone write pointer due to a write error, + * the user must either execute a report zones, reset the zone or finish + * the to recover a reliable write pointer position. Fail BIOs if the + * user did not do that as we cannot handle emulated zone append + * otherwise. + */ + if (zwplug->flags & BLK_ZONE_WPLUG_NEED_WP_UPDATE) + return false; + /* * Check that the user is not attempting to write to a full zone. * We know such BIO will fail, and that would potentially overflow our * write pointer offset beyond the end of the zone. */ if (disk_zone_wplug_is_full(disk, zwplug)) - goto err; + return false; if (bio_op(bio) == REQ_OP_ZONE_APPEND) { /* @@ -927,24 +965,18 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug, bio_set_flag(bio, BIO_EMULATES_ZONE_APPEND); } else { /* - * Check for non-sequential writes early because we avoid a - * whole lot of error handling trouble if we don't send it off - * to the driver. + * Check for non-sequential writes early as we know that BIOs + * with a start sector not unaligned to the zone write pointer + * will fail. */ if (bio_offset_from_zone_start(bio) != zwplug->wp_offset) - goto err; + return false; } /* Advance the zone write pointer offset. */ zwplug->wp_offset += bio_sectors(bio); return true; - -err: - /* We detected an invalid write BIO: schedule error recovery. */ - disk_zone_wplug_set_error(disk, zwplug); - kblockd_schedule_work(&disk->zone_wplugs_work); - return false; } static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) @@ -983,7 +1015,10 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) zwplug = disk_get_and_lock_zone_wplug(disk, sector, gfp_mask, &flags); if (!zwplug) { - bio_io_error(bio); + if (bio->bi_opf & REQ_NOWAIT) + bio_wouldblock_error(bio); + else + bio_io_error(bio); return true; } @@ -991,18 +1026,20 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) bio_set_flag(bio, BIO_ZONE_WRITE_PLUGGING); /* - * If the zone is already plugged or has a pending error, add the BIO - * to the plug BIO list. Otherwise, plug and let the BIO execute. + * If the zone is already plugged, add the BIO to the plug BIO list. + * Do the same for REQ_NOWAIT BIOs to ensure that we will not see a + * BLK_STS_AGAIN failure if we let the BIO execute. + * Otherwise, plug and let the BIO execute. */ - if (zwplug->flags & BLK_ZONE_WPLUG_BUSY) + if ((zwplug->flags & BLK_ZONE_WPLUG_PLUGGED) || + (bio->bi_opf & REQ_NOWAIT)) goto plug; - /* - * If an error is detected when preparing the BIO, add it to the BIO - * list so that error recovery can deal with it. - */ - if (!blk_zone_wplug_prepare_bio(zwplug, bio)) - goto plug; + if (!blk_zone_wplug_prepare_bio(zwplug, bio)) { + spin_unlock_irqrestore(&zwplug->lock, flags); + bio_io_error(bio); + return true; + } zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; @@ -1011,8 +1048,7 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) return false; plug: - zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; - blk_zone_wplug_add_bio(zwplug, bio, nr_segs); + disk_zone_wplug_add_bio(disk, zwplug, bio, nr_segs); spin_unlock_irqrestore(&zwplug->lock, flags); @@ -1096,19 +1132,6 @@ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) } EXPORT_SYMBOL_GPL(blk_zone_plug_bio); -static void disk_zone_wplug_schedule_bio_work(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - /* - * Take a reference on the zone write plug and schedule the submission - * of the next plugged BIO. blk_zone_wplug_bio_work() will release the - * reference we take here. - */ - WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED)); - atomic_inc(&zwplug->ref); - queue_work(disk->zone_wplugs_wq, &zwplug->bio_work); -} - static void disk_zone_wplug_unplug_bio(struct gendisk *disk, struct blk_zone_wplug *zwplug) { @@ -1116,16 +1139,6 @@ static void disk_zone_wplug_unplug_bio(struct gendisk *disk, spin_lock_irqsave(&zwplug->lock, flags); - /* - * If we had an error, schedule error recovery. The recovery work - * will restart submission of plugged BIOs. - */ - if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) { - spin_unlock_irqrestore(&zwplug->lock, flags); - kblockd_schedule_work(&disk->zone_wplugs_work); - return; - } - /* Schedule submission of the next plugged BIO if we have one. */ if (!bio_list_empty(&zwplug->bio_list)) { disk_zone_wplug_schedule_bio_work(disk, zwplug); @@ -1168,12 +1181,13 @@ void blk_zone_write_plug_bio_endio(struct bio *bio) } /* - * If the BIO failed, mark the plug as having an error to trigger - * recovery. + * If the BIO failed, abort all plugged BIOs and mark the plug as + * needing a write pointer update. */ if (bio->bi_status != BLK_STS_OK) { spin_lock_irqsave(&zwplug->lock, flags); - disk_zone_wplug_set_error(disk, zwplug); + disk_zone_wplug_abort(zwplug); + zwplug->flags |= BLK_ZONE_WPLUG_NEED_WP_UPDATE; spin_unlock_irqrestore(&zwplug->lock, flags); } @@ -1229,6 +1243,7 @@ static void blk_zone_wplug_bio_work(struct work_struct *work) */ spin_lock_irqsave(&zwplug->lock, flags); +again: bio = bio_list_pop(&zwplug->bio_list); if (!bio) { zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; @@ -1237,10 +1252,8 @@ static void blk_zone_wplug_bio_work(struct work_struct *work) } if (!blk_zone_wplug_prepare_bio(zwplug, bio)) { - /* Error recovery will decide what to do with the BIO. */ - bio_list_add_head(&zwplug->bio_list, bio); - spin_unlock_irqrestore(&zwplug->lock, flags); - goto put_zwplug; + blk_zone_wplug_bio_io_error(zwplug, bio); + goto again; } spin_unlock_irqrestore(&zwplug->lock, flags); @@ -1262,120 +1275,6 @@ static void blk_zone_wplug_bio_work(struct work_struct *work) disk_put_zone_wplug(zwplug); } -static unsigned int blk_zone_wp_offset(struct blk_zone *zone) -{ - switch (zone->cond) { - case BLK_ZONE_COND_IMP_OPEN: - case BLK_ZONE_COND_EXP_OPEN: - case BLK_ZONE_COND_CLOSED: - return zone->wp - zone->start; - case BLK_ZONE_COND_FULL: - return zone->len; - case BLK_ZONE_COND_EMPTY: - return 0; - case BLK_ZONE_COND_NOT_WP: - case BLK_ZONE_COND_OFFLINE: - case BLK_ZONE_COND_READONLY: - default: - /* - * Conventional, offline and read-only zones do not have a valid - * write pointer. - */ - return UINT_MAX; - } -} - -static int blk_zone_wplug_report_zone_cb(struct blk_zone *zone, - unsigned int idx, void *data) -{ - struct blk_zone *zonep = data; - - *zonep = *zone; - return 0; -} - -static void disk_zone_wplug_handle_error(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - sector_t zone_start_sector = - bdev_zone_sectors(disk->part0) * zwplug->zone_no; - unsigned int noio_flag; - struct blk_zone zone; - unsigned long flags; - int ret; - - /* Get the current zone information from the device. */ - noio_flag = memalloc_noio_save(); - ret = disk->fops->report_zones(disk, zone_start_sector, 1, - blk_zone_wplug_report_zone_cb, &zone); - memalloc_noio_restore(noio_flag); - - spin_lock_irqsave(&zwplug->lock, flags); - - /* - * A zone reset or finish may have cleared the error already. In such - * case, do nothing as the report zones may have seen the "old" write - * pointer value before the reset/finish operation completed. - */ - if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR)) - goto unlock; - - zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR; - - if (ret != 1) { - /* - * We failed to get the zone information, meaning that something - * is likely really wrong with the device. Abort all remaining - * plugged BIOs as otherwise we could endup waiting forever on - * plugged BIOs to complete if there is a queue freeze on-going. - */ - disk_zone_wplug_abort(zwplug); - goto unplug; - } - - /* Update the zone write pointer offset. */ - zwplug->wp_offset = blk_zone_wp_offset(&zone); - disk_zone_wplug_abort_unaligned(disk, zwplug); - - /* Restart BIO submission if we still have any BIO left. */ - if (!bio_list_empty(&zwplug->bio_list)) { - disk_zone_wplug_schedule_bio_work(disk, zwplug); - goto unlock; - } - -unplug: - zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; - if (disk_should_remove_zone_wplug(disk, zwplug)) - disk_remove_zone_wplug(disk, zwplug); - -unlock: - spin_unlock_irqrestore(&zwplug->lock, flags); -} - -static void disk_zone_wplugs_work(struct work_struct *work) -{ - struct gendisk *disk = - container_of(work, struct gendisk, zone_wplugs_work); - struct blk_zone_wplug *zwplug; - unsigned long flags; - - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - - while (!list_empty(&disk->zone_wplugs_err_list)) { - zwplug = list_first_entry(&disk->zone_wplugs_err_list, - struct blk_zone_wplug, link); - list_del_init(&zwplug->link); - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); - - disk_zone_wplug_handle_error(disk, zwplug); - disk_put_zone_wplug(zwplug); - - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - } - - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); -} - static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk) { return 1U << disk->zone_wplugs_hash_bits; @@ -1384,8 +1283,6 @@ static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk) void disk_init_zone_resources(struct gendisk *disk) { spin_lock_init(&disk->zone_wplugs_lock); - INIT_LIST_HEAD(&disk->zone_wplugs_err_list); - INIT_WORK(&disk->zone_wplugs_work, disk_zone_wplugs_work); } /* @@ -1450,7 +1347,7 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk) while (!hlist_empty(&disk->zone_wplugs_hash[i])) { zwplug = hlist_entry(disk->zone_wplugs_hash[i].first, struct blk_zone_wplug, node); - atomic_inc(&zwplug->ref); + refcount_inc(&zwplug->ref); disk_remove_zone_wplug(disk, zwplug); disk_put_zone_wplug(zwplug); } @@ -1484,8 +1381,6 @@ void disk_free_zone_resources(struct gendisk *disk) if (!disk->zone_wplugs_pool) return; - cancel_work_sync(&disk->zone_wplugs_work); - if (disk->zone_wplugs_wq) { destroy_workqueue(disk->zone_wplugs_wq); disk->zone_wplugs_wq = NULL; @@ -1682,6 +1577,8 @@ static int blk_revalidate_seq_zone(struct blk_zone *zone, unsigned int idx, if (!disk->zone_wplugs_hash) return 0; + disk_zone_wplug_sync_wp_offset(disk, zone); + wp_offset = blk_zone_wp_offset(zone); if (!wp_offset || wp_offset >= zone->capacity) return 0; @@ -1818,6 +1715,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) memalloc_noio_restore(noio_flag); return ret; } + ret = disk->fops->report_zones(disk, 0, UINT_MAX, blk_revalidate_zone_cb, &args); if (!ret) { @@ -1854,6 +1752,48 @@ int blk_revalidate_disk_zones(struct gendisk *disk) } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); +/** + * blk_zone_issue_zeroout - zero-fill a block range in a zone + * @bdev: blockdev to write + * @sector: start sector + * @nr_sects: number of sectors to write + * @gfp_mask: memory allocation flags (for bio_alloc) + * + * Description: + * Zero-fill a block range in a zone (@sector must be equal to the zone write + * pointer), handling potential errors due to the (initially unknown) lack of + * hardware offload (See blkdev_issue_zeroout()). + */ +int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask) +{ + int ret; + + if (WARN_ON_ONCE(!bdev_is_zoned(bdev))) + return -EIO; + + ret = blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, + BLKDEV_ZERO_NOFALLBACK); + if (ret != -EOPNOTSUPP) + return ret; + + /* + * The failed call to blkdev_issue_zeroout() advanced the zone write + * pointer. Undo this using a report zone to update the zone write + * pointer to the correct current value. + */ + ret = disk_zone_sync_wp_offset(bdev->bd_disk, sector); + if (ret != 1) + return ret < 0 ? ret : -EIO; + + /* + * Retry without BLKDEV_ZERO_NOFALLBACK to force the fallback to a + * regular write with zero-pages. + */ + return blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, 0); +} +EXPORT_SYMBOL_GPL(blk_zone_issue_zeroout); + #ifdef CONFIG_BLK_DEBUG_FS int queue_zone_wplugs_show(void *data, struct seq_file *m) @@ -1876,7 +1816,7 @@ int queue_zone_wplugs_show(void *data, struct seq_file *m) spin_lock_irqsave(&zwplug->lock, flags); zwp_zone_no = zwplug->zone_no; zwp_flags = zwplug->flags; - zwp_ref = atomic_read(&zwplug->ref); + zwp_ref = refcount_read(&zwplug->ref); zwp_wp_offset = zwplug->wp_offset; zwp_bio_list_size = bio_list_size(&zwplug->bio_list); spin_unlock_irqrestore(&zwplug->lock, flags); diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 95f78383bbdb..bff2d099f469 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -232,8 +232,6 @@ acpi_remove_address_space_handler(acpi_handle device, /* Now we can delete the handler object */ - acpi_os_release_mutex(handler_obj->address_space. - context_mutex); acpi_ut_remove_reference(handler_obj); goto unlock_and_exit; } diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 5429ec9ef06f..a5d47819b3a4 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -454,8 +454,13 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, if (cmd_rc) *cmd_rc = -EINVAL; - if (cmd == ND_CMD_CALL) + if (cmd == ND_CMD_CALL) { + if (!buf || buf_len < sizeof(*call_pkg)) + return -EINVAL; + call_pkg = buf; + } + func = cmd_to_func(nfit_mem, cmd, call_pkg, &family); if (func < 0) return func; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 7fe842dae1ec..821867de43be 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -250,6 +250,9 @@ static bool acpi_decode_space(struct resource_win *win, switch (addr->resource_type) { case ACPI_MEMORY_RANGE: acpi_dev_memresource_flags(res, len, wp); + + if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY) + res->flags |= IORESOURCE_PREFETCH; break; case ACPI_IO_RANGE: acpi_dev_ioresource_flags(res, len, iodec, @@ -265,9 +268,6 @@ static bool acpi_decode_space(struct resource_win *win, if (addr->producer_consumer == ACPI_PRODUCER) res->flags |= IORESOURCE_WINDOW; - if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY) - res->flags |= IORESOURCE_PREFETCH; - return !(res->flags & IORESOURCE_DISABLED); } diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c index 63ef7bb073ce..596c6d294da9 100644 --- a/drivers/ata/sata_highbank.c +++ b/drivers/ata/sata_highbank.c @@ -348,6 +348,7 @@ static int highbank_initialize_phys(struct device *dev, void __iomem *addr) phy_nodes[phy] = phy_data.np; cphy_base[phy] = of_iomap(phy_nodes[phy], 0); if (cphy_base[phy] == NULL) { + of_node_put(phy_data.np); return 0; } phy_count += 1; diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 480e4adba9fa..85e99641eaae 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -395,6 +395,7 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) { struct btmtk_data *data = hci_get_priv(hdev); int err; + bool complete = false; if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) { kfree_skb(skb); @@ -416,19 +417,22 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) fallthrough; case HCI_DEVCOREDUMP_ACTIVE: default: + /* Mediatek coredump data would be more than MTK_COREDUMP_NUM */ + if (data->cd_info.cnt >= MTK_COREDUMP_NUM && + skb->len > MTK_COREDUMP_END_LEN) + if (!memcmp((char *)&skb->data[skb->len - MTK_COREDUMP_END_LEN], + MTK_COREDUMP_END, MTK_COREDUMP_END_LEN - 1)) + complete = true; + err = hci_devcd_append(hdev, skb); if (err < 0) break; data->cd_info.cnt++; - /* Mediatek coredump data would be more than MTK_COREDUMP_NUM */ - if (data->cd_info.cnt > MTK_COREDUMP_NUM && - skb->len > MTK_COREDUMP_END_LEN) - if (!memcmp((char *)&skb->data[skb->len - MTK_COREDUMP_END_LEN], - MTK_COREDUMP_END, MTK_COREDUMP_END_LEN - 1)) { - bt_dev_info(hdev, "Mediatek coredump end"); - hci_devcd_complete(hdev); - } + if (complete) { + bt_dev_info(hdev, "Mediatek coredump end"); + hci_devcd_complete(hdev); + } break; } diff --git a/drivers/clk/clk-en7523.c b/drivers/clk/clk-en7523.c index bc21b2921449..62a62eaba2aa 100644 --- a/drivers/clk/clk-en7523.c +++ b/drivers/clk/clk-en7523.c @@ -92,6 +92,7 @@ static const u32 slic_base[] = { 100000000, 3125000 }; static const u32 npu_base[] = { 333000000, 400000000, 500000000 }; /* EN7581 */ static const u32 emi7581_base[] = { 540000000, 480000000, 400000000, 300000000 }; +static const u32 bus7581_base[] = { 600000000, 540000000 }; static const u32 npu7581_base[] = { 800000000, 750000000, 720000000, 600000000 }; static const u32 crypto_base[] = { 540000000, 480000000 }; @@ -227,8 +228,8 @@ static const struct en_clk_desc en7581_base_clks[] = { .base_reg = REG_BUS_CLK_DIV_SEL, .base_bits = 1, .base_shift = 8, - .base_values = bus_base, - .n_base_values = ARRAY_SIZE(bus_base), + .base_values = bus7581_base, + .n_base_values = ARRAY_SIZE(bus7581_base), .div_bits = 3, .div_shift = 0, diff --git a/drivers/crypto/hisilicon/debugfs.c b/drivers/crypto/hisilicon/debugfs.c index 1b9b7bccdeff..45e130b901eb 100644 --- a/drivers/crypto/hisilicon/debugfs.c +++ b/drivers/crypto/hisilicon/debugfs.c @@ -192,7 +192,7 @@ static int qm_sqc_dump(struct hisi_qm *qm, char *s, char *name) down_read(&qm->qps_lock); if (qm->sqc) { - memcpy(&sqc, qm->sqc + qp_id * sizeof(struct qm_sqc), sizeof(struct qm_sqc)); + memcpy(&sqc, qm->sqc + qp_id, sizeof(struct qm_sqc)); sqc.base_h = cpu_to_le32(QM_XQC_ADDR_MASK); sqc.base_l = cpu_to_le32(QM_XQC_ADDR_MASK); dump_show(qm, &sqc, sizeof(struct qm_sqc), "SOFT SQC"); @@ -229,7 +229,7 @@ static int qm_cqc_dump(struct hisi_qm *qm, char *s, char *name) down_read(&qm->qps_lock); if (qm->cqc) { - memcpy(&cqc, qm->cqc + qp_id * sizeof(struct qm_cqc), sizeof(struct qm_cqc)); + memcpy(&cqc, qm->cqc + qp_id, sizeof(struct qm_cqc)); cqc.base_h = cpu_to_le32(QM_XQC_ADDR_MASK); cqc.base_l = cpu_to_le32(QM_XQC_ADDR_MASK); dump_show(qm, &cqc, sizeof(struct qm_cqc), "SOFT CQC"); diff --git a/drivers/gpio/gpio-graniterapids.c b/drivers/gpio/gpio-graniterapids.c index f2e911a3d2ca..ad6a045fd3d2 100644 --- a/drivers/gpio/gpio-graniterapids.c +++ b/drivers/gpio/gpio-graniterapids.c @@ -32,12 +32,14 @@ #define GNR_PINS_PER_REG 32 #define GNR_NUM_REGS DIV_ROUND_UP(GNR_NUM_PINS, GNR_PINS_PER_REG) -#define GNR_CFG_BAR 0x00 +#define GNR_CFG_PADBAR 0x00 #define GNR_CFG_LOCK_OFFSET 0x04 -#define GNR_GPI_STATUS_OFFSET 0x20 +#define GNR_GPI_STATUS_OFFSET 0x14 #define GNR_GPI_ENABLE_OFFSET 0x24 -#define GNR_CFG_DW_RX_MASK GENMASK(25, 22) +#define GNR_CFG_DW_HOSTSW_MODE BIT(27) +#define GNR_CFG_DW_RX_MASK GENMASK(23, 22) +#define GNR_CFG_DW_INTSEL_MASK GENMASK(21, 14) #define GNR_CFG_DW_RX_DISABLE FIELD_PREP(GNR_CFG_DW_RX_MASK, 2) #define GNR_CFG_DW_RX_EDGE FIELD_PREP(GNR_CFG_DW_RX_MASK, 1) #define GNR_CFG_DW_RX_LEVEL FIELD_PREP(GNR_CFG_DW_RX_MASK, 0) @@ -50,6 +52,7 @@ * struct gnr_gpio - Intel Granite Rapids-D vGPIO driver state * @gc: GPIO controller interface * @reg_base: base address of the GPIO registers + * @pad_base: base address of the vGPIO pad configuration registers * @ro_bitmap: bitmap of read-only pins * @lock: guard the registers * @pad_backup: backup of the register state for suspend @@ -57,6 +60,7 @@ struct gnr_gpio { struct gpio_chip gc; void __iomem *reg_base; + void __iomem *pad_base; DECLARE_BITMAP(ro_bitmap, GNR_NUM_PINS); raw_spinlock_t lock; u32 pad_backup[]; @@ -65,7 +69,7 @@ struct gnr_gpio { static void __iomem *gnr_gpio_get_padcfg_addr(const struct gnr_gpio *priv, unsigned int gpio) { - return priv->reg_base + gpio * sizeof(u32); + return priv->pad_base + gpio * sizeof(u32); } static int gnr_gpio_configure_line(struct gpio_chip *gc, unsigned int gpio, @@ -88,6 +92,20 @@ static int gnr_gpio_configure_line(struct gpio_chip *gc, unsigned int gpio, return 0; } +static int gnr_gpio_request(struct gpio_chip *gc, unsigned int gpio) +{ + struct gnr_gpio *priv = gpiochip_get_data(gc); + u32 dw; + + dw = readl(gnr_gpio_get_padcfg_addr(priv, gpio)); + if (!(dw & GNR_CFG_DW_HOSTSW_MODE)) { + dev_warn(gc->parent, "GPIO %u is not owned by host", gpio); + return -EBUSY; + } + + return 0; +} + static int gnr_gpio_get(struct gpio_chip *gc, unsigned int gpio) { const struct gnr_gpio *priv = gpiochip_get_data(gc); @@ -139,6 +157,7 @@ static int gnr_gpio_direction_output(struct gpio_chip *gc, unsigned int gpio, in static const struct gpio_chip gnr_gpio_chip = { .owner = THIS_MODULE, + .request = gnr_gpio_request, .get = gnr_gpio_get, .set = gnr_gpio_set, .get_direction = gnr_gpio_get_direction, @@ -166,7 +185,7 @@ static void gnr_gpio_irq_ack(struct irq_data *d) guard(raw_spinlock_irqsave)(&priv->lock); reg = readl(addr); - reg &= ~BIT(bit_idx); + reg |= BIT(bit_idx); writel(reg, addr); } @@ -209,10 +228,18 @@ static void gnr_gpio_irq_unmask(struct irq_data *d) static int gnr_gpio_irq_set_type(struct irq_data *d, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - irq_hw_number_t pin = irqd_to_hwirq(d); - u32 mask = GNR_CFG_DW_RX_MASK; + struct gnr_gpio *priv = gpiochip_get_data(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); + u32 reg; u32 set; + /* Allow interrupts only if Interrupt Select field is non-zero */ + reg = readl(gnr_gpio_get_padcfg_addr(priv, hwirq)); + if (!(reg & GNR_CFG_DW_INTSEL_MASK)) { + dev_dbg(gc->parent, "GPIO %lu cannot be used as IRQ", hwirq); + return -EPERM; + } + /* Falling edge and level low triggers not supported by the GPIO controller */ switch (type) { case IRQ_TYPE_NONE: @@ -230,10 +257,11 @@ static int gnr_gpio_irq_set_type(struct irq_data *d, unsigned int type) return -EINVAL; } - return gnr_gpio_configure_line(gc, pin, mask, set); + return gnr_gpio_configure_line(gc, hwirq, GNR_CFG_DW_RX_MASK, set); } static const struct irq_chip gnr_gpio_irq_chip = { + .name = "gpio-graniterapids", .irq_ack = gnr_gpio_irq_ack, .irq_mask = gnr_gpio_irq_mask, .irq_unmask = gnr_gpio_irq_unmask, @@ -291,6 +319,7 @@ static int gnr_gpio_probe(struct platform_device *pdev) struct gnr_gpio *priv; void __iomem *regs; int irq, ret; + u32 offset; priv = devm_kzalloc(dev, struct_size(priv, pad_backup, num_backup_pins), GFP_KERNEL); if (!priv) @@ -302,6 +331,10 @@ static int gnr_gpio_probe(struct platform_device *pdev) if (IS_ERR(regs)) return PTR_ERR(regs); + priv->reg_base = regs; + offset = readl(priv->reg_base + GNR_CFG_PADBAR); + priv->pad_base = priv->reg_base + offset; + irq = platform_get_irq(pdev, 0); if (irq < 0) return irq; @@ -311,8 +344,6 @@ static int gnr_gpio_probe(struct platform_device *pdev) if (ret) return dev_err_probe(dev, ret, "failed to request interrupt\n"); - priv->reg_base = regs + readl(regs + GNR_CFG_BAR); - gnr_gpio_init_pin_ro_bits(dev, priv->reg_base + GNR_CFG_LOCK_OFFSET, priv->ro_bitmap); @@ -324,7 +355,6 @@ static int gnr_gpio_probe(struct platform_device *pdev) girq = &priv->gc.irq; gpio_irq_chip_set_chip(girq, &gnr_gpio_irq_chip); - girq->chip->name = dev_name(dev); girq->parent_handler = NULL; girq->num_parents = 0; girq->parents = NULL; diff --git a/drivers/gpio/gpio-ljca.c b/drivers/gpio/gpio-ljca.c index dfec9fbfc7a9..c2a9b4253974 100644 --- a/drivers/gpio/gpio-ljca.c +++ b/drivers/gpio/gpio-ljca.c @@ -82,9 +82,9 @@ static int ljca_gpio_config(struct ljca_gpio_dev *ljca_gpio, u8 gpio_id, int ret; mutex_lock(&ljca_gpio->trans_lock); + packet->num = 1; packet->item[0].index = gpio_id; packet->item[0].value = config | ljca_gpio->connect_mode[gpio_id]; - packet->num = 1; ret = ljca_transfer(ljca_gpio->ljca, LJCA_GPIO_CONFIG, (u8 *)packet, struct_size(packet, item, packet->num), NULL, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index d891ab779ca7..5df21529b3b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1801,13 +1801,18 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser, if (dma_resv_locking_ctx((*bo)->tbo.base.resv) != &parser->exec.ticket) return -EINVAL; + /* Make sure VRAM is allocated contigiously */ (*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; - amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains); - for (i = 0; i < (*bo)->placement.num_placement; i++) - (*bo)->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; - r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx); - if (r) - return r; + if ((*bo)->tbo.resource->mem_type == TTM_PL_VRAM && + !((*bo)->tbo.resource->placement & TTM_PL_FLAG_CONTIGUOUS)) { + + amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains); + for (i = 0; i < (*bo)->placement.num_placement; i++) + (*bo)->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; + r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx); + if (r) + return r; + } return amdgpu_ttm_alloc_gart(&(*bo)->tbo); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 31fd30dcd593..65bb26215e86 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -551,6 +551,8 @@ static void amdgpu_uvd_force_into_uvd_segment(struct amdgpu_bo *abo) for (i = 0; i < abo->placement.num_placement; ++i) { abo->placements[i].fpfn = 0 >> PAGE_SHIFT; abo->placements[i].lpfn = (256 * 1024 * 1024) >> PAGE_SHIFT; + if (abo->placements[i].mem_type == TTM_PL_VRAM) + abo->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 6005280f5f38..8d2562d0f143 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -674,12 +674,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, pasid_mapping_needed &= adev->gmc.gmc_funcs->emit_pasid_mapping && ring->funcs->emit_wreg; - if (adev->gfx.enable_cleaner_shader && - ring->funcs->emit_cleaner_shader && - job->enforce_isolation) - ring->funcs->emit_cleaner_shader(ring); - - if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync) + if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync && + !(job->enforce_isolation && !job->vmid)) return 0; amdgpu_ring_ib_begin(ring); @@ -690,6 +686,11 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, if (need_pipe_sync) amdgpu_ring_emit_pipeline_sync(ring); + if (adev->gfx.enable_cleaner_shader && + ring->funcs->emit_cleaner_shader && + job->enforce_isolation) + ring->funcs->emit_cleaner_shader(ring); + if (vm_flush_needed) { trace_amdgpu_vm_flush(ring, job->vmid, job->vm_pd_addr); amdgpu_ring_emit_vm_flush(ring, job->vmid, job->vm_pd_addr); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index 6068b784dc69..9a30b8c10838 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -1289,7 +1289,7 @@ static int uvd_v7_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_job *job, struct amdgpu_ib *ib) { - struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched); + struct amdgpu_ring *ring = amdgpu_job_ring(job); unsigned i; /* No patching necessary for the first instance */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 8de61cc524c9..d2993594c848 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -1422,6 +1422,7 @@ int kfd_parse_crat_table(void *crat_image, struct list_head *device_list, static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, + bool cache_line_size_missing, struct kfd_gpu_cache_info *pcache_info) { struct amdgpu_device *adev = kdev->adev; @@ -1436,6 +1437,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_tcp_per_wpg / 2; pcache_info[i].cache_line_size = adev->gfx.config.gc_tcp_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 128; i++; } /* Scalar L1 Instruction Cache per SQC */ @@ -1448,6 +1451,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_sqc_per_wgp * 2; pcache_info[i].cache_line_size = adev->gfx.config.gc_instruction_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 128; i++; } /* Scalar L1 Data Cache per SQC */ @@ -1459,6 +1464,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_sqc_per_wgp * 2; pcache_info[i].cache_line_size = adev->gfx.config.gc_scalar_data_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 64; i++; } /* GL1 Data Cache per SA */ @@ -1471,7 +1478,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_DATA_CACHE | CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; - pcache_info[i].cache_line_size = 0; + if (cache_line_size_missing) + pcache_info[i].cache_line_size = 128; i++; } /* L2 Data Cache per GPU (Total Tex Cache) */ @@ -1483,6 +1491,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; pcache_info[i].cache_line_size = adev->gfx.config.gc_tcc_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 128; i++; } /* L3 Data Cache per GPU */ @@ -1493,7 +1503,7 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_DATA_CACHE | CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; - pcache_info[i].cache_line_size = 0; + pcache_info[i].cache_line_size = 64; i++; } return i; @@ -1568,6 +1578,7 @@ static int kfd_fill_gpu_cache_info_from_gfx_config_v2(struct kfd_dev *kdev, int kfd_get_gpu_cache_info(struct kfd_node *kdev, struct kfd_gpu_cache_info **pcache_info) { int num_of_cache_types = 0; + bool cache_line_size_missing = false; switch (kdev->adev->asic_type) { case CHIP_KAVERI: @@ -1691,10 +1702,17 @@ int kfd_get_gpu_cache_info(struct kfd_node *kdev, struct kfd_gpu_cache_info **pc case IP_VERSION(11, 5, 0): case IP_VERSION(11, 5, 1): case IP_VERSION(11, 5, 2): + /* Cacheline size not available in IP discovery for gc11. + * kfd_fill_gpu_cache_info_from_gfx_config to hard code it + */ + cache_line_size_missing = true; + fallthrough; case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): num_of_cache_types = - kfd_fill_gpu_cache_info_from_gfx_config(kdev->kfd, *pcache_info); + kfd_fill_gpu_cache_info_from_gfx_config(kdev->kfd, + cache_line_size_missing, + *pcache_info); break; default: *pcache_info = dummy_cache_info; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 648f40091aa3..f5b3ed20e891 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -205,6 +205,21 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, if (!down_read_trylock(&adev->reset_domain->sem)) return -EIO; + if (!pdd->proc_ctx_cpu_ptr) { + r = amdgpu_amdkfd_alloc_gtt_mem(adev, + AMDGPU_MES_PROC_CTX_SIZE, + &pdd->proc_ctx_bo, + &pdd->proc_ctx_gpu_addr, + &pdd->proc_ctx_cpu_ptr, + false); + if (r) { + dev_err(adev->dev, + "failed to allocate process context bo\n"); + return r; + } + memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); + } + memset(&queue_input, 0x0, sizeof(struct mes_add_queue_input)); queue_input.process_id = qpd->pqm->process->pasid; queue_input.page_table_base_addr = qpd->page_table_base; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index ff34bb1ac9db..3139987b82b1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1076,7 +1076,8 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) kfd_free_process_doorbells(pdd->dev->kfd, pdd); - if (pdd->dev->kfd->shared_resources.enable_mes) + if (pdd->dev->kfd->shared_resources.enable_mes && + pdd->proc_ctx_cpu_ptr) amdgpu_amdkfd_free_gtt_mem(pdd->dev->adev, &pdd->proc_ctx_bo); /* @@ -1610,7 +1611,6 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev, struct kfd_process *p) { struct kfd_process_device *pdd = NULL; - int retval = 0; if (WARN_ON_ONCE(p->n_pdds >= MAX_GPU_INSTANCE)) return NULL; @@ -1634,21 +1634,6 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev, pdd->user_gpu_id = dev->id; atomic64_set(&pdd->evict_duration_counter, 0); - if (dev->kfd->shared_resources.enable_mes) { - retval = amdgpu_amdkfd_alloc_gtt_mem(dev->adev, - AMDGPU_MES_PROC_CTX_SIZE, - &pdd->proc_ctx_bo, - &pdd->proc_ctx_gpu_addr, - &pdd->proc_ctx_cpu_ptr, - false); - if (retval) { - dev_err(dev->adev->dev, - "failed to allocate process context bo\n"); - goto err_free_pdd; - } - memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); - } - p->pdds[p->n_pdds++] = pdd; if (kfd_dbg_is_per_vmid_supported(pdd->dev)) pdd->spi_dbg_override = pdd->dev->kfd2kgd->disable_debug_trap( @@ -1660,10 +1645,6 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev, idr_init(&pdd->alloc_idr); return pdd; - -err_free_pdd: - kfree(pdd); - return NULL; } /** diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 01b960b15274..ead4317a2168 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -212,13 +212,17 @@ static void pqm_clean_queue_resource(struct process_queue_manager *pqm, void pqm_uninit(struct process_queue_manager *pqm) { struct process_queue_node *pqn, *next; - struct kfd_process_device *pdd; list_for_each_entry_safe(pqn, next, &pqm->queues, process_queue_list) { if (pqn->q) { - pdd = kfd_get_process_device_data(pqn->q->device, pqm->process); - kfd_queue_unref_bo_vas(pdd, &pqn->q->properties); - kfd_queue_release_buffers(pdd, &pqn->q->properties); + struct kfd_process_device *pdd = kfd_get_process_device_data(pqn->q->device, + pqm->process); + if (pdd) { + kfd_queue_unref_bo_vas(pdd, &pqn->q->properties); + kfd_queue_release_buffers(pdd, &pqn->q->properties); + } else { + WARN_ON(!pdd); + } pqm_clean_queue_resource(pqm, pqn); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index d0e6d051e9cf..1aedfafa507f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2717,4 +2717,5 @@ void smu_v13_0_7_set_ppt_funcs(struct smu_context *smu) smu->workload_map = smu_v13_0_7_workload_map; smu->smc_driver_if_version = SMU13_0_7_DRIVER_IF_VERSION; smu_v13_0_set_smu_mailbox_registers(smu); + smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; } diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index 1ef56cb07dfb..447740d79d3d 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -929,7 +929,6 @@ fn draw_all(&mut self, data: impl Iterator) { /// * `tmp` must be valid for reading and writing for `tmp_size` bytes. /// /// They must remain valid for the duration of the function call. - #[no_mangle] pub unsafe extern "C" fn drm_panic_qr_generate( url: *const i8, diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index 5d701f48351b..ec55cb651d44 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -1333,19 +1333,29 @@ static void ilk_load_lut_8(const struct intel_crtc_state *crtc_state, lut = blob->data; /* - * DSB fails to correctly load the legacy LUT - * unless we either write each entry twice, - * or use non-posted writes + * DSB fails to correctly load the legacy LUT unless + * we either write each entry twice when using posted + * writes, or we use non-posted writes. + * + * If palette anti-collision is active during LUT + * register writes: + * - posted writes simply get dropped and thus the LUT + * contents may not be correctly updated + * - non-posted writes are blocked and thus the LUT + * contents are always correct, but simultaneous CPU + * MMIO access will start to fail + * + * Choose the lesser of two evils and use posted writes. + * Using posted writes is also faster, even when having + * to write each register twice. */ - if (crtc_state->dsb_color_vblank) - intel_dsb_nonpost_start(crtc_state->dsb_color_vblank); - - for (i = 0; i < 256; i++) + for (i = 0; i < 256; i++) { ilk_lut_write(crtc_state, LGC_PALETTE(pipe, i), i9xx_lut_8(&lut[i])); - - if (crtc_state->dsb_color_vblank) - intel_dsb_nonpost_end(crtc_state->dsb_color_vblank); + if (crtc_state->dsb_color_vblank) + ilk_lut_write(crtc_state, LGC_PALETTE(pipe, i), + i9xx_lut_8(&lut[i])); + } } static void ilk_load_lut_10(const struct intel_crtc_state *crtc_state, diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 6469b9bcf2ec..082ac72c757a 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1652,9 +1652,21 @@ capture_engine(struct intel_engine_cs *engine, return NULL; intel_engine_get_hung_entity(engine, &ce, &rq); - if (rq && !i915_request_started(rq)) - drm_info(&engine->gt->i915->drm, "Got hung context on %s with active request %lld:%lld [0x%04X] not yet started\n", - engine->name, rq->fence.context, rq->fence.seqno, ce->guc_id.id); + if (rq && !i915_request_started(rq)) { + /* + * We want to know also what is the guc_id of the context, + * but if we don't have the context reference, then skip + * printing it. + */ + if (ce) + drm_info(&engine->gt->i915->drm, + "Got hung context on %s with active request %lld:%lld [0x%04X] not yet started\n", + engine->name, rq->fence.context, rq->fence.seqno, ce->guc_id.id); + else + drm_info(&engine->gt->i915->drm, + "Got hung context on %s with active request %lld:%lld not yet started\n", + engine->name, rq->fence.context, rq->fence.seqno); + } if (rq) { capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL); diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 762127dd56c5..70a854557e6e 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -506,6 +506,6 @@ int __init i915_scheduler_module_init(void) return 0; err_priorities: - kmem_cache_destroy(slab_priorities); + kmem_cache_destroy(slab_dependencies); return -ENOMEM; } diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c index 1a192a2a941b..3bbdb362d6f0 100644 --- a/drivers/gpu/drm/xe/tests/xe_migrate.c +++ b/drivers/gpu/drm/xe/tests/xe_migrate.c @@ -224,8 +224,8 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test) XE_BO_FLAG_VRAM_IF_DGFX(tile) | XE_BO_FLAG_PINNED); if (IS_ERR(tiny)) { - KUNIT_FAIL(test, "Failed to allocate fake pt: %li\n", - PTR_ERR(pt)); + KUNIT_FAIL(test, "Failed to allocate tiny fake pt: %li\n", + PTR_ERR(tiny)); goto free_pt; } diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 9d82ea30f4df..7e385940df08 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -65,6 +65,14 @@ invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fe __invalidation_fence_signal(xe, fence); } +void xe_gt_tlb_invalidation_fence_signal(struct xe_gt_tlb_invalidation_fence *fence) +{ + if (WARN_ON_ONCE(!fence->gt)) + return; + + __invalidation_fence_signal(gt_to_xe(fence->gt), fence); +} + static void xe_gt_tlb_fence_timeout(struct work_struct *work) { struct xe_gt *gt = container_of(work, struct xe_gt, diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index f430d5797af7..00b1c6c01e8d 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -28,6 +28,7 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len); void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, bool stack); +void xe_gt_tlb_invalidation_fence_signal(struct xe_gt_tlb_invalidation_fence *fence); static inline void xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence) diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index f27f579f4d85..797576690356 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -1333,8 +1333,7 @@ static void invalidation_fence_cb(struct dma_fence *fence, queue_work(system_wq, &ifence->work); } else { ifence->base.base.error = ifence->fence->error; - dma_fence_signal(&ifence->base.base); - dma_fence_put(&ifence->base.base); + xe_gt_tlb_invalidation_fence_signal(&ifence->base); } dma_fence_put(ifence->fence); } diff --git a/drivers/gpu/drm/xe/xe_reg_sr.c b/drivers/gpu/drm/xe/xe_reg_sr.c index 440ac572f6e5..52969c090965 100644 --- a/drivers/gpu/drm/xe/xe_reg_sr.c +++ b/drivers/gpu/drm/xe/xe_reg_sr.c @@ -26,46 +26,27 @@ #include "xe_reg_whitelist.h" #include "xe_rtp_types.h" -#define XE_REG_SR_GROW_STEP_DEFAULT 16 - static void reg_sr_fini(struct drm_device *drm, void *arg) { struct xe_reg_sr *sr = arg; + struct xe_reg_sr_entry *entry; + unsigned long reg; + + xa_for_each(&sr->xa, reg, entry) + kfree(entry); xa_destroy(&sr->xa); - kfree(sr->pool.arr); - memset(&sr->pool, 0, sizeof(sr->pool)); } int xe_reg_sr_init(struct xe_reg_sr *sr, const char *name, struct xe_device *xe) { xa_init(&sr->xa); - memset(&sr->pool, 0, sizeof(sr->pool)); - sr->pool.grow_step = XE_REG_SR_GROW_STEP_DEFAULT; sr->name = name; return drmm_add_action_or_reset(&xe->drm, reg_sr_fini, sr); } EXPORT_SYMBOL_IF_KUNIT(xe_reg_sr_init); -static struct xe_reg_sr_entry *alloc_entry(struct xe_reg_sr *sr) -{ - if (sr->pool.used == sr->pool.allocated) { - struct xe_reg_sr_entry *arr; - - arr = krealloc_array(sr->pool.arr, - ALIGN(sr->pool.allocated + 1, sr->pool.grow_step), - sizeof(*arr), GFP_KERNEL); - if (!arr) - return NULL; - - sr->pool.arr = arr; - sr->pool.allocated += sr->pool.grow_step; - } - - return &sr->pool.arr[sr->pool.used++]; -} - static bool compatible_entries(const struct xe_reg_sr_entry *e1, const struct xe_reg_sr_entry *e2) { @@ -111,7 +92,7 @@ int xe_reg_sr_add(struct xe_reg_sr *sr, return 0; } - pentry = alloc_entry(sr); + pentry = kmalloc(sizeof(*pentry), GFP_KERNEL); if (!pentry) { ret = -ENOMEM; goto fail; diff --git a/drivers/gpu/drm/xe/xe_reg_sr_types.h b/drivers/gpu/drm/xe/xe_reg_sr_types.h index ad48a52b824a..ebe11f237fa2 100644 --- a/drivers/gpu/drm/xe/xe_reg_sr_types.h +++ b/drivers/gpu/drm/xe/xe_reg_sr_types.h @@ -20,12 +20,6 @@ struct xe_reg_sr_entry { }; struct xe_reg_sr { - struct { - struct xe_reg_sr_entry *arr; - unsigned int used; - unsigned int allocated; - unsigned int grow_step; - } pool; struct xarray xa; const char *name; diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index c8ec74f089f3..6e41ddaa24d6 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -339,7 +339,7 @@ tegra241_cmdqv_get_cmdq(struct arm_smmu_device *smmu, * one CPU at a time can enter the process, while the others * will be spinning at the same lock. */ - lidx = smp_processor_id() % cmdqv->num_lvcmdqs_per_vintf; + lidx = raw_smp_processor_id() % cmdqv->num_lvcmdqs_per_vintf; vcmdq = vintf->lvcmdqs[lidx]; if (!vcmdq || !READ_ONCE(vcmdq->enabled)) return NULL; diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c index e5b89f728ad3..09694cca8752 100644 --- a/drivers/iommu/intel/cache.c +++ b/drivers/iommu/intel/cache.c @@ -105,12 +105,35 @@ static void cache_tag_unassign(struct dmar_domain *domain, u16 did, spin_unlock_irqrestore(&domain->cache_lock, flags); } +/* domain->qi_batch will be freed in iommu_free_domain() path. */ +static int domain_qi_batch_alloc(struct dmar_domain *domain) +{ + unsigned long flags; + int ret = 0; + + spin_lock_irqsave(&domain->cache_lock, flags); + if (domain->qi_batch) + goto out_unlock; + + domain->qi_batch = kzalloc(sizeof(*domain->qi_batch), GFP_ATOMIC); + if (!domain->qi_batch) + ret = -ENOMEM; +out_unlock: + spin_unlock_irqrestore(&domain->cache_lock, flags); + + return ret; +} + static int __cache_tag_assign_domain(struct dmar_domain *domain, u16 did, struct device *dev, ioasid_t pasid) { struct device_domain_info *info = dev_iommu_priv_get(dev); int ret; + ret = domain_qi_batch_alloc(domain); + if (ret) + return ret; + ret = cache_tag_assign(domain, did, dev, pasid, CACHE_TAG_IOTLB); if (ret || !info->ats_enabled) return ret; @@ -139,6 +162,10 @@ static int __cache_tag_assign_parent_domain(struct dmar_domain *domain, u16 did, struct device_domain_info *info = dev_iommu_priv_get(dev); int ret; + ret = domain_qi_batch_alloc(domain); + if (ret) + return ret; + ret = cache_tag_assign(domain, did, dev, pasid, CACHE_TAG_NESTING_IOTLB); if (ret || !info->ats_enabled) return ret; @@ -190,13 +217,6 @@ int cache_tag_assign_domain(struct dmar_domain *domain, u16 did = domain_get_id_for_dev(domain, dev); int ret; - /* domain->qi_bach will be freed in iommu_free_domain() path. */ - if (!domain->qi_batch) { - domain->qi_batch = kzalloc(sizeof(*domain->qi_batch), GFP_KERNEL); - if (!domain->qi_batch) - return -ENOMEM; - } - ret = __cache_tag_assign_domain(domain, did, dev, pasid); if (ret || domain->domain.type != IOMMU_DOMAIN_NESTED) return ret; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index a167d59101ae..cc23cfcdeb2d 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3372,6 +3372,9 @@ void device_block_translation(struct device *dev) struct intel_iommu *iommu = info->iommu; unsigned long flags; + if (info->domain) + cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID); + iommu_disable_pci_caps(info); if (!dev_is_real_dma_subdevice(dev)) { if (sm_supported(iommu)) @@ -3388,7 +3391,6 @@ void device_block_translation(struct device *dev) list_del(&info->link); spin_unlock_irqrestore(&info->domain->lock, flags); - cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID); domain_detach_iommu(info->domain, iommu); info->domain = NULL; } diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index d58db9a27e6c..76e2c6868548 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -76,9 +76,9 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone, * pointer and the requested position. */ nr_blocks = block - wp_block; - ret = blkdev_issue_zeroout(dev->bdev, - dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block), - dmz_blk2sect(nr_blocks), GFP_NOIO, 0); + ret = blk_zone_issue_zeroout(dev->bdev, + dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block), + dmz_blk2sect(nr_blocks), GFP_NOIO); if (ret) { dmz_dev_err(dev, "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d", diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 15e0f14d0d49..4d73abae503d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1520,9 +1520,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev, struct slave *slave; mask = features; - - features &= ~NETIF_F_ONE_FOR_ALL; - features |= NETIF_F_ALL_FOR_ALL; + features = netdev_base_features(features); bond_for_each_slave(bond, slave, iter) { features = netdev_increment_features(features, @@ -1536,6 +1534,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev, #define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ + NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HIGHDMA | NETIF_F_LRO) #define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ @@ -1564,8 +1563,9 @@ static void bond_compute_features(struct bonding *bond) if (!bond_has_slaves(bond)) goto done; - vlan_features &= NETIF_F_ALL_FOR_ALL; - mpls_features &= NETIF_F_ALL_FOR_ALL; + + vlan_features = netdev_base_features(vlan_features); + mpls_features = netdev_base_features(mpls_features); bond_for_each_slave(bond, slave, iter) { vlan_features = netdev_increment_features(vlan_features, diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 5290f5ad98f3..bf26cd0abf6d 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1098,10 +1098,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x1030, 0x1030), regmap_reg_range(0x1100, 0x1115), regmap_reg_range(0x111a, 0x111f), - regmap_reg_range(0x1122, 0x1127), - regmap_reg_range(0x112a, 0x112b), - regmap_reg_range(0x1136, 0x1139), - regmap_reg_range(0x113e, 0x113f), + regmap_reg_range(0x1120, 0x112b), + regmap_reg_range(0x1134, 0x113b), + regmap_reg_range(0x113c, 0x113f), regmap_reg_range(0x1400, 0x1401), regmap_reg_range(0x1403, 0x1403), regmap_reg_range(0x1410, 0x1417), @@ -1128,10 +1127,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x2030, 0x2030), regmap_reg_range(0x2100, 0x2115), regmap_reg_range(0x211a, 0x211f), - regmap_reg_range(0x2122, 0x2127), - regmap_reg_range(0x212a, 0x212b), - regmap_reg_range(0x2136, 0x2139), - regmap_reg_range(0x213e, 0x213f), + regmap_reg_range(0x2120, 0x212b), + regmap_reg_range(0x2134, 0x213b), + regmap_reg_range(0x213c, 0x213f), regmap_reg_range(0x2400, 0x2401), regmap_reg_range(0x2403, 0x2403), regmap_reg_range(0x2410, 0x2417), @@ -1158,10 +1156,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x3030, 0x3030), regmap_reg_range(0x3100, 0x3115), regmap_reg_range(0x311a, 0x311f), - regmap_reg_range(0x3122, 0x3127), - regmap_reg_range(0x312a, 0x312b), - regmap_reg_range(0x3136, 0x3139), - regmap_reg_range(0x313e, 0x313f), + regmap_reg_range(0x3120, 0x312b), + regmap_reg_range(0x3134, 0x313b), + regmap_reg_range(0x313c, 0x313f), regmap_reg_range(0x3400, 0x3401), regmap_reg_range(0x3403, 0x3403), regmap_reg_range(0x3410, 0x3417), @@ -1188,10 +1185,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x4030, 0x4030), regmap_reg_range(0x4100, 0x4115), regmap_reg_range(0x411a, 0x411f), - regmap_reg_range(0x4122, 0x4127), - regmap_reg_range(0x412a, 0x412b), - regmap_reg_range(0x4136, 0x4139), - regmap_reg_range(0x413e, 0x413f), + regmap_reg_range(0x4120, 0x412b), + regmap_reg_range(0x4134, 0x413b), + regmap_reg_range(0x413c, 0x413f), regmap_reg_range(0x4400, 0x4401), regmap_reg_range(0x4403, 0x4403), regmap_reg_range(0x4410, 0x4417), @@ -1218,10 +1214,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x5030, 0x5030), regmap_reg_range(0x5100, 0x5115), regmap_reg_range(0x511a, 0x511f), - regmap_reg_range(0x5122, 0x5127), - regmap_reg_range(0x512a, 0x512b), - regmap_reg_range(0x5136, 0x5139), - regmap_reg_range(0x513e, 0x513f), + regmap_reg_range(0x5120, 0x512b), + regmap_reg_range(0x5134, 0x513b), + regmap_reg_range(0x513c, 0x513f), regmap_reg_range(0x5400, 0x5401), regmap_reg_range(0x5403, 0x5403), regmap_reg_range(0x5410, 0x5417), @@ -1248,10 +1243,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x6030, 0x6030), regmap_reg_range(0x6100, 0x6115), regmap_reg_range(0x611a, 0x611f), - regmap_reg_range(0x6122, 0x6127), - regmap_reg_range(0x612a, 0x612b), - regmap_reg_range(0x6136, 0x6139), - regmap_reg_range(0x613e, 0x613f), + regmap_reg_range(0x6120, 0x612b), + regmap_reg_range(0x6134, 0x613b), + regmap_reg_range(0x613c, 0x613f), regmap_reg_range(0x6300, 0x6301), regmap_reg_range(0x6400, 0x6401), regmap_reg_range(0x6403, 0x6403), diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 0102a82e88cc..940f1b71226d 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -24,7 +24,7 @@ #define VSC9959_NUM_PORTS 6 #define VSC9959_TAS_GCL_ENTRY_MAX 63 -#define VSC9959_TAS_MIN_GATE_LEN_NS 33 +#define VSC9959_TAS_MIN_GATE_LEN_NS 35 #define VSC9959_VCAP_POLICER_BASE 63 #define VSC9959_VCAP_POLICER_MAX 383 #define VSC9959_SWITCH_PCI_BAR 4 @@ -1056,11 +1056,15 @@ static void vsc9959_mdio_bus_free(struct ocelot *ocelot) mdiobus_free(felix->imdio); } -/* The switch considers any frame (regardless of size) as eligible for - * transmission if the traffic class gate is open for at least 33 ns. +/* The switch considers any frame (regardless of size) as eligible + * for transmission if the traffic class gate is open for at least + * VSC9959_TAS_MIN_GATE_LEN_NS. + * * Overruns are prevented by cropping an interval at the end of the gate time - * slot for which egress scheduling is blocked, but we need to still keep 33 ns - * available for one packet to be transmitted, otherwise the port tc will hang. + * slot for which egress scheduling is blocked, but we need to still keep + * VSC9959_TAS_MIN_GATE_LEN_NS available for one packet to be transmitted, + * otherwise the port tc will hang. + * * This function returns the size of a gate interval that remains available for * setting the guard band, after reserving the space for one egress frame. */ @@ -1303,7 +1307,8 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) * per-tc static guard band lengths, so it reduces the * useful gate interval length. Therefore, be careful * to calculate a guard band (and therefore max_sdu) - * that still leaves 33 ns available in the time slot. + * that still leaves VSC9959_TAS_MIN_GATE_LEN_NS + * available in the time slot. */ max_sdu = div_u64(remaining_gate_len_ps, picos_per_byte); /* A TC gate may be completely closed, which is a diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 3d9ee91e1f8b..dafc5a4039cd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1518,7 +1518,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, if (TPA_START_IS_IPV6(tpa_start1)) tpa_info->gso_type = SKB_GSO_TCPV6; /* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */ - else if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP && + else if (!BNXT_CHIP_P4_PLUS(bp) && TPA_START_HASH_TYPE(tpa_start) == 3) tpa_info->gso_type = SKB_GSO_TCPV6; tpa_info->rss_hash = @@ -2212,15 +2212,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, if (cmp_type == CMP_TYPE_RX_L2_V3_CMP) { type = bnxt_rss_ext_op(bp, rxcmp); } else { - u32 hash_type = RX_CMP_HASH_TYPE(rxcmp); + u32 itypes = RX_CMP_ITYPES(rxcmp); - /* RSS profiles 1 and 3 with extract code 0 for inner - * 4-tuple - */ - if (hash_type != 1 && hash_type != 3) - type = PKT_HASH_TYPE_L3; - else + if (itypes == RX_CMP_FLAGS_ITYPE_TCP || + itypes == RX_CMP_FLAGS_ITYPE_UDP) type = PKT_HASH_TYPE_L4; + else + type = PKT_HASH_TYPE_L3; } skb_set_hash(skb, le32_to_cpu(rxcmp->rx_cmp_rss_hash), type); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 69231e85140b..9e05704d9445 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -267,6 +267,9 @@ struct rx_cmp { (((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_RSS_HASH_TYPE) >>\ RX_CMP_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK) +#define RX_CMP_ITYPES(rxcmp) \ + (le32_to_cpu((rxcmp)->rx_cmp_len_flags_type) & RX_CMP_FLAGS_ITYPES_MASK) + #define RX_CMP_V3_HASH_TYPE_LEGACY(rxcmp) \ ((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_V3_RSS_EXT_OP_LEGACY) >>\ RX_CMP_V3_RSS_EXT_OP_LEGACY_SHIFT) @@ -378,7 +381,7 @@ struct rx_agg_cmp { u32 rx_agg_cmp_opaque; __le32 rx_agg_cmp_v; #define RX_AGG_CMP_V (1 << 0) - #define RX_AGG_CMP_AGG_ID (0xffff << 16) + #define RX_AGG_CMP_AGG_ID (0x0fff << 16) #define RX_AGG_CMP_AGG_ID_SHIFT 16 __le32 rx_agg_cmp_unused; }; @@ -416,7 +419,7 @@ struct rx_tpa_start_cmp { #define RX_TPA_START_CMP_V3_RSS_HASH_TYPE_SHIFT 7 #define RX_TPA_START_CMP_AGG_ID (0x7f << 25) #define RX_TPA_START_CMP_AGG_ID_SHIFT 25 - #define RX_TPA_START_CMP_AGG_ID_P5 (0xffff << 16) + #define RX_TPA_START_CMP_AGG_ID_P5 (0x0fff << 16) #define RX_TPA_START_CMP_AGG_ID_SHIFT_P5 16 #define RX_TPA_START_CMP_METADATA1 (0xf << 28) #define RX_TPA_START_CMP_METADATA1_SHIFT 28 @@ -540,7 +543,7 @@ struct rx_tpa_end_cmp { #define RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT 16 #define RX_TPA_END_CMP_AGG_ID (0x7f << 25) #define RX_TPA_END_CMP_AGG_ID_SHIFT 25 - #define RX_TPA_END_CMP_AGG_ID_P5 (0xffff << 16) + #define RX_TPA_END_CMP_AGG_ID_P5 (0x0fff << 16) #define RX_TPA_END_CMP_AGG_ID_SHIFT_P5 16 __le32 rx_tpa_end_cmp_tsdelta; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index bbf7641a0fc7..7e13cd69f68a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -2077,7 +2077,7 @@ void t4_idma_monitor(struct adapter *adapter, struct sge_idma_monitor_state *idma, int hz, int ticks); int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf, - unsigned int naddr, u8 *addr); + u8 start, unsigned int naddr, u8 *addr); void t4_tp_pio_read(struct adapter *adap, u32 *buff, u32 nregs, u32 start_index, bool sleep_ok); void t4_tp_tm_pio_read(struct adapter *adap, u32 *buff, u32 nregs, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 2418645c8823..fb3933fbb842 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3246,7 +3246,7 @@ static int cxgb4_mgmt_set_vf_mac(struct net_device *dev, int vf, u8 *mac) dev_info(pi->adapter->pdev_dev, "Setting MAC %pM on VF %d\n", mac, vf); - ret = t4_set_vf_mac_acl(adap, vf + 1, 1, mac); + ret = t4_set_vf_mac_acl(adap, vf + 1, pi->lport, 1, mac); if (!ret) ether_addr_copy(adap->vfinfo[vf].vf_mac_addr, mac); return ret; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 76de55306c4d..175bf9b13058 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -10215,11 +10215,12 @@ int t4_load_cfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) * t4_set_vf_mac_acl - Set MAC address for the specified VF * @adapter: The adapter * @vf: one of the VFs instantiated by the specified PF + * @start: The start port id associated with specified VF * @naddr: the number of MAC addresses * @addr: the MAC address(es) to be set to the specified VF */ int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf, - unsigned int naddr, u8 *addr) + u8 start, unsigned int naddr, u8 *addr) { struct fw_acl_mac_cmd cmd; @@ -10234,7 +10235,7 @@ int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf, cmd.en_to_len16 = cpu_to_be32((unsigned int)FW_LEN16(cmd)); cmd.nmac = naddr; - switch (adapter->pf) { + switch (start) { case 3: memcpy(cmd.macaddr3, addr, sizeof(cmd.macaddr3)); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 3d74109f8230..49f22cad92bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -297,7 +297,9 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) if (ret) { mlx5dr_dbg(dmn, "Couldn't insert new vport into xarray (%d)\n", ret); kvfree(vport_caps); - return ERR_PTR(ret); + if (ret == -EBUSY) + return ERR_PTR(-EBUSY); + return NULL; } return vport_caps; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index b64c814eac11..0c4c75b3682f 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -693,12 +693,11 @@ static int sparx5_start(struct sparx5 *sparx5) err = -ENXIO; if (sparx5->fdma_irq >= 0) { if (GCB_CHIP_ID_REV_ID_GET(sparx5->chip_id) > 0) - err = devm_request_threaded_irq(sparx5->dev, - sparx5->fdma_irq, - NULL, - sparx5_fdma_handler, - IRQF_ONESHOT, - "sparx5-fdma", sparx5); + err = devm_request_irq(sparx5->dev, + sparx5->fdma_irq, + sparx5_fdma_handler, + 0, + "sparx5-fdma", sparx5); if (!err) err = sparx5_fdma_start(sparx5); if (err) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c index 062e486c002c..672508efce5c 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -1119,7 +1119,7 @@ int sparx5_port_init(struct sparx5 *sparx5, spx5_inst_rmw(DEV10G_MAC_MAXLEN_CFG_MAX_LEN_SET(ETH_MAXLEN), DEV10G_MAC_MAXLEN_CFG_MAX_LEN, devinst, - DEV10G_MAC_ENA_CFG(0)); + DEV10G_MAC_MAXLEN_CFG(0)); /* Handle Signal Detect in 10G PCS */ spx5_inst_wr(PCS10G_BR_PCS_SD_CFG_SD_POL_SET(sd_pol) | diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index ca4ed58f1206..0c2ba2fa88c4 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1315,7 +1315,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) GFP_KERNEL); if (!gc->irq_contexts) { err = -ENOMEM; - goto free_irq_vector; + goto free_irq_array; } for (i = 0; i < nvec; i++) { @@ -1372,6 +1372,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) gc->max_num_msix = nvec; gc->num_msix_usable = nvec; cpus_read_unlock(); + kfree(irqs); return 0; free_irq: @@ -1384,8 +1385,9 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) } kfree(gc->irq_contexts); - kfree(irqs); gc->irq_contexts = NULL; +free_irq_array: + kfree(irqs); free_irq_vector: cpus_read_unlock(); pci_free_irq_vectors(pdev); diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c index e172638b0601..808ce8e68d39 100644 --- a/drivers/net/ethernet/mscc/ocelot_ptp.c +++ b/drivers/net/ethernet/mscc/ocelot_ptp.c @@ -14,6 +14,8 @@ #include #include "ocelot.h" +#define OCELOT_PTP_TX_TSTAMP_TIMEOUT (5 * HZ) + int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); @@ -495,6 +497,28 @@ static int ocelot_traps_to_ptp_rx_filter(unsigned int proto) return HWTSTAMP_FILTER_NONE; } +static int ocelot_ptp_tx_type_to_cmd(int tx_type, int *ptp_cmd) +{ + switch (tx_type) { + case HWTSTAMP_TX_ON: + *ptp_cmd = IFH_REW_OP_TWO_STEP_PTP; + break; + case HWTSTAMP_TX_ONESTEP_SYNC: + /* IFH_REW_OP_ONE_STEP_PTP updates the correctionField, + * what we need to update is the originTimestamp. + */ + *ptp_cmd = IFH_REW_OP_ORIGIN_PTP; + break; + case HWTSTAMP_TX_OFF: + *ptp_cmd = 0; + break; + default: + return -ERANGE; + } + + return 0; +} + int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr) { struct ocelot_port *ocelot_port = ocelot->ports[port]; @@ -521,30 +545,19 @@ EXPORT_SYMBOL(ocelot_hwstamp_get); int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + int ptp_cmd, old_ptp_cmd = ocelot_port->ptp_cmd; bool l2 = false, l4 = false; struct hwtstamp_config cfg; + bool old_l2, old_l4; int err; if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; /* Tx type sanity check */ - switch (cfg.tx_type) { - case HWTSTAMP_TX_ON: - ocelot_port->ptp_cmd = IFH_REW_OP_TWO_STEP_PTP; - break; - case HWTSTAMP_TX_ONESTEP_SYNC: - /* IFH_REW_OP_ONE_STEP_PTP updates the correctional field, we - * need to update the origin time. - */ - ocelot_port->ptp_cmd = IFH_REW_OP_ORIGIN_PTP; - break; - case HWTSTAMP_TX_OFF: - ocelot_port->ptp_cmd = 0; - break; - default: - return -ERANGE; - } + err = ocelot_ptp_tx_type_to_cmd(cfg.tx_type, &ptp_cmd); + if (err) + return err; switch (cfg.rx_filter) { case HWTSTAMP_FILTER_NONE: @@ -569,13 +582,27 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) return -ERANGE; } + old_l2 = ocelot_port->trap_proto & OCELOT_PROTO_PTP_L2; + old_l4 = ocelot_port->trap_proto & OCELOT_PROTO_PTP_L4; + err = ocelot_setup_ptp_traps(ocelot, port, l2, l4); if (err) return err; + ocelot_port->ptp_cmd = ptp_cmd; + cfg.rx_filter = ocelot_traps_to_ptp_rx_filter(ocelot_port->trap_proto); - return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; + if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) { + err = -EFAULT; + goto out_restore_ptp_traps; + } + + return 0; +out_restore_ptp_traps: + ocelot_setup_ptp_traps(ocelot, port, old_l2, old_l4); + ocelot_port->ptp_cmd = old_ptp_cmd; + return err; } EXPORT_SYMBOL(ocelot_hwstamp_set); @@ -603,34 +630,87 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, } EXPORT_SYMBOL(ocelot_get_ts_info); -static int ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port, +static struct sk_buff *ocelot_port_dequeue_ptp_tx_skb(struct ocelot *ocelot, + int port, u8 ts_id, + u32 seqid) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct ptp_header *hdr; + + spin_lock(&ocelot->ts_id_lock); + + skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) { + if (OCELOT_SKB_CB(skb)->ts_id != ts_id) + continue; + + /* Check that the timestamp ID is for the expected PTP + * sequenceId. We don't have to test ptp_parse_header() against + * NULL, because we've pre-validated the packet's ptp_class. + */ + hdr = ptp_parse_header(skb, OCELOT_SKB_CB(skb)->ptp_class); + if (seqid != ntohs(hdr->sequence_id)) + continue; + + __skb_unlink(skb, &ocelot_port->tx_skbs); + ocelot->ptp_skbs_in_flight--; + skb_match = skb; + break; + } + + spin_unlock(&ocelot->ts_id_lock); + + return skb_match; +} + +static int ocelot_port_queue_ptp_tx_skb(struct ocelot *ocelot, int port, struct sk_buff *clone) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - unsigned long flags; + DECLARE_BITMAP(ts_id_in_flight, OCELOT_MAX_PTP_ID); + struct sk_buff *skb, *skb_tmp; + unsigned long n; - spin_lock_irqsave(&ocelot->ts_id_lock, flags); + spin_lock(&ocelot->ts_id_lock); - if (ocelot_port->ptp_skbs_in_flight == OCELOT_MAX_PTP_ID || - ocelot->ptp_skbs_in_flight == OCELOT_PTP_FIFO_SIZE) { - spin_unlock_irqrestore(&ocelot->ts_id_lock, flags); + /* To get a better chance of acquiring a timestamp ID, first flush the + * stale packets still waiting in the TX timestamping queue. They are + * probably lost. + */ + skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) { + if (time_before(OCELOT_SKB_CB(skb)->ptp_tx_time + + OCELOT_PTP_TX_TSTAMP_TIMEOUT, jiffies)) { + dev_warn_ratelimited(ocelot->dev, + "port %d invalidating stale timestamp ID %u which seems lost\n", + port, OCELOT_SKB_CB(skb)->ts_id); + __skb_unlink(skb, &ocelot_port->tx_skbs); + kfree_skb(skb); + ocelot->ptp_skbs_in_flight--; + } else { + __set_bit(OCELOT_SKB_CB(skb)->ts_id, ts_id_in_flight); + } + } + + if (ocelot->ptp_skbs_in_flight == OCELOT_PTP_FIFO_SIZE) { + spin_unlock(&ocelot->ts_id_lock); return -EBUSY; } - skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS; - /* Store timestamp ID in OCELOT_SKB_CB(clone)->ts_id */ - OCELOT_SKB_CB(clone)->ts_id = ocelot_port->ts_id; + n = find_first_zero_bit(ts_id_in_flight, OCELOT_MAX_PTP_ID); + if (n == OCELOT_MAX_PTP_ID) { + spin_unlock(&ocelot->ts_id_lock); + return -EBUSY; + } - ocelot_port->ts_id++; - if (ocelot_port->ts_id == OCELOT_MAX_PTP_ID) - ocelot_port->ts_id = 0; - - ocelot_port->ptp_skbs_in_flight++; + /* Found an available timestamp ID, use it */ + OCELOT_SKB_CB(clone)->ts_id = n; + OCELOT_SKB_CB(clone)->ptp_tx_time = jiffies; ocelot->ptp_skbs_in_flight++; + __skb_queue_tail(&ocelot_port->tx_skbs, clone); - skb_queue_tail(&ocelot_port->tx_skbs, clone); + spin_unlock(&ocelot->ts_id_lock); - spin_unlock_irqrestore(&ocelot->ts_id_lock, flags); + dev_dbg_ratelimited(ocelot->dev, "port %d timestamp id %lu\n", port, n); return 0; } @@ -687,10 +767,14 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port, if (!(*clone)) return -ENOMEM; - err = ocelot_port_add_txtstamp_skb(ocelot, port, *clone); - if (err) + /* Store timestamp ID in OCELOT_SKB_CB(clone)->ts_id */ + err = ocelot_port_queue_ptp_tx_skb(ocelot, port, *clone); + if (err) { + kfree_skb(*clone); return err; + } + skb_shinfo(*clone)->tx_flags |= SKBTX_IN_PROGRESS; OCELOT_SKB_CB(skb)->ptp_cmd = ptp_cmd; OCELOT_SKB_CB(*clone)->ptp_class = ptp_class; } @@ -726,28 +810,15 @@ static void ocelot_get_hwtimestamp(struct ocelot *ocelot, spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); } -static bool ocelot_validate_ptp_skb(struct sk_buff *clone, u16 seqid) -{ - struct ptp_header *hdr; - - hdr = ptp_parse_header(clone, OCELOT_SKB_CB(clone)->ptp_class); - if (WARN_ON(!hdr)) - return false; - - return seqid == ntohs(hdr->sequence_id); -} - void ocelot_get_txtstamp(struct ocelot *ocelot) { int budget = OCELOT_PTP_QUEUE_SZ; while (budget--) { - struct sk_buff *skb, *skb_tmp, *skb_match = NULL; struct skb_shared_hwtstamps shhwtstamps; u32 val, id, seqid, txport; - struct ocelot_port *port; + struct sk_buff *skb_match; struct timespec64 ts; - unsigned long flags; val = ocelot_read(ocelot, SYS_PTP_STATUS); @@ -762,36 +833,14 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) txport = SYS_PTP_STATUS_PTP_MESS_TXPORT_X(val); seqid = SYS_PTP_STATUS_PTP_MESS_SEQ_ID(val); - port = ocelot->ports[txport]; - - spin_lock(&ocelot->ts_id_lock); - port->ptp_skbs_in_flight--; - ocelot->ptp_skbs_in_flight--; - spin_unlock(&ocelot->ts_id_lock); - /* Retrieve its associated skb */ -try_again: - spin_lock_irqsave(&port->tx_skbs.lock, flags); - - skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) { - if (OCELOT_SKB_CB(skb)->ts_id != id) - continue; - __skb_unlink(skb, &port->tx_skbs); - skb_match = skb; - break; - } - - spin_unlock_irqrestore(&port->tx_skbs.lock, flags); - - if (WARN_ON(!skb_match)) - continue; - - if (!ocelot_validate_ptp_skb(skb_match, seqid)) { - dev_err_ratelimited(ocelot->dev, - "port %d received stale TX timestamp for seqid %d, discarding\n", - txport, seqid); - dev_kfree_skb_any(skb); - goto try_again; + skb_match = ocelot_port_dequeue_ptp_tx_skb(ocelot, txport, id, + seqid); + if (!skb_match) { + dev_warn_ratelimited(ocelot->dev, + "port %d received TX timestamp (seqid %d, ts id %u) for packet previously declared stale\n", + txport, seqid, id); + goto next_ts; } /* Get the h/w timestamp */ @@ -802,7 +851,7 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); skb_complete_tx_timestamp(skb_match, &shhwtstamps); - /* Next ts */ +next_ts: ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT); } } diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 8f7ce6b51a1c..6b4b40c6e1fe 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -53,7 +53,7 @@ MODULE_PARM_DESC(qcaspi_burst_len, "Number of data bytes per burst. Use 1-5000." #define QCASPI_PLUGGABLE_MIN 0 #define QCASPI_PLUGGABLE_MAX 1 -static int qcaspi_pluggable = QCASPI_PLUGGABLE_MIN; +static int qcaspi_pluggable = QCASPI_PLUGGABLE_MAX; module_param(qcaspi_pluggable, int, 0); MODULE_PARM_DESC(qcaspi_pluggable, "Pluggable SPI connection (yes/no)."); @@ -812,7 +812,6 @@ qcaspi_netdev_init(struct net_device *dev) dev->mtu = QCAFRM_MAX_MTU; dev->type = ARPHRD_ETHER; - qca->clkspeed = qcaspi_clkspeed; qca->burst_len = qcaspi_burst_len; qca->spi_thread = NULL; qca->buffer_size = (QCAFRM_MAX_MTU + VLAN_ETH_HLEN + QCAFRM_HEADER_LEN + @@ -903,17 +902,15 @@ qca_spi_probe(struct spi_device *spi) legacy_mode = of_property_read_bool(spi->dev.of_node, "qca,legacy-mode"); - if (qcaspi_clkspeed == 0) { - if (spi->max_speed_hz) - qcaspi_clkspeed = spi->max_speed_hz; - else - qcaspi_clkspeed = QCASPI_CLK_SPEED; - } + if (qcaspi_clkspeed) + spi->max_speed_hz = qcaspi_clkspeed; + else if (!spi->max_speed_hz) + spi->max_speed_hz = QCASPI_CLK_SPEED; - if ((qcaspi_clkspeed < QCASPI_CLK_SPEED_MIN) || - (qcaspi_clkspeed > QCASPI_CLK_SPEED_MAX)) { - dev_err(&spi->dev, "Invalid clkspeed: %d\n", - qcaspi_clkspeed); + if (spi->max_speed_hz < QCASPI_CLK_SPEED_MIN || + spi->max_speed_hz > QCASPI_CLK_SPEED_MAX) { + dev_err(&spi->dev, "Invalid clkspeed: %u\n", + spi->max_speed_hz); return -EINVAL; } @@ -938,14 +935,13 @@ qca_spi_probe(struct spi_device *spi) return -EINVAL; } - dev_info(&spi->dev, "ver=%s, clkspeed=%d, burst_len=%d, pluggable=%d\n", + dev_info(&spi->dev, "ver=%s, clkspeed=%u, burst_len=%d, pluggable=%d\n", QCASPI_DRV_VERSION, - qcaspi_clkspeed, + spi->max_speed_hz, qcaspi_burst_len, qcaspi_pluggable); spi->mode = SPI_MODE_3; - spi->max_speed_hz = qcaspi_clkspeed; if (spi_setup(spi) < 0) { dev_err(&spi->dev, "Unable to setup SPI device\n"); return -EFAULT; diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index 8f4808695e82..0831cefc58b8 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -89,7 +89,6 @@ struct qcaspi { #endif /* user configurable options */ - u32 clkspeed; u8 legacy_mode; u16 burst_len; }; diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index b80aa27a7214..09117110e3dd 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -862,13 +862,10 @@ static void rswitch_tx_free(struct net_device *ndev) struct rswitch_ext_desc *desc; struct sk_buff *skb; - for (; rswitch_get_num_cur_queues(gq) > 0; - gq->dirty = rswitch_next_queue_index(gq, false, 1)) { - desc = &gq->tx_ring[gq->dirty]; - if ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY) - break; - + desc = &gq->tx_ring[gq->dirty]; + while ((desc->desc.die_dt & DT_MASK) == DT_FEMPTY) { dma_rmb(); + skb = gq->skbs[gq->dirty]; if (skb) { rdev->ndev->stats.tx_packets++; @@ -879,7 +876,10 @@ static void rswitch_tx_free(struct net_device *ndev) dev_kfree_skb_any(gq->skbs[gq->dirty]); gq->skbs[gq->dirty] = NULL; } + desc->desc.die_dt = DT_EEMPTY; + gq->dirty = rswitch_next_queue_index(gq, false, 1); + desc = &gq->tx_ring[gq->dirty]; } } @@ -908,8 +908,10 @@ static int rswitch_poll(struct napi_struct *napi, int budget) if (napi_complete_done(napi, budget - quota)) { spin_lock_irqsave(&priv->lock, flags); - rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true); - rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true); + if (test_bit(rdev->port, priv->opened_ports)) { + rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true); + rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true); + } spin_unlock_irqrestore(&priv->lock, flags); } @@ -1114,25 +1116,40 @@ static int rswitch_etha_wait_link_verification(struct rswitch_etha *etha) static void rswitch_rmac_setting(struct rswitch_etha *etha, const u8 *mac) { - u32 val; + u32 pis, lsc; rswitch_etha_write_mac_address(etha, mac); - switch (etha->speed) { - case 100: - val = MPIC_LSC_100M; + switch (etha->phy_interface) { + case PHY_INTERFACE_MODE_SGMII: + pis = MPIC_PIS_GMII; break; - case 1000: - val = MPIC_LSC_1G; - break; - case 2500: - val = MPIC_LSC_2_5G; + case PHY_INTERFACE_MODE_USXGMII: + case PHY_INTERFACE_MODE_5GBASER: + pis = MPIC_PIS_XGMII; break; default: - return; + pis = FIELD_GET(MPIC_PIS, ioread32(etha->addr + MPIC)); + break; } - iowrite32(MPIC_PIS_GMII | val, etha->addr + MPIC); + switch (etha->speed) { + case 100: + lsc = MPIC_LSC_100M; + break; + case 1000: + lsc = MPIC_LSC_1G; + break; + case 2500: + lsc = MPIC_LSC_2_5G; + break; + default: + lsc = FIELD_GET(MPIC_LSC, ioread32(etha->addr + MPIC)); + break; + } + + rswitch_modify(etha->addr, MPIC, MPIC_PIS | MPIC_LSC, + FIELD_PREP(MPIC_PIS, pis) | FIELD_PREP(MPIC_LSC, lsc)); } static void rswitch_etha_enable_mii(struct rswitch_etha *etha) @@ -1538,20 +1555,20 @@ static int rswitch_open(struct net_device *ndev) struct rswitch_device *rdev = netdev_priv(ndev); unsigned long flags; - phy_start(ndev->phydev); + if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) + iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDIE); napi_enable(&rdev->napi); - netif_start_queue(ndev); spin_lock_irqsave(&rdev->priv->lock, flags); + bitmap_set(rdev->priv->opened_ports, rdev->port, 1); rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, true); rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, true); spin_unlock_irqrestore(&rdev->priv->lock, flags); - if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) - iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDIE); + phy_start(ndev->phydev); - bitmap_set(rdev->priv->opened_ports, rdev->port, 1); + netif_start_queue(ndev); return 0; }; @@ -1563,7 +1580,16 @@ static int rswitch_stop(struct net_device *ndev) unsigned long flags; netif_tx_stop_all_queues(ndev); + + phy_stop(ndev->phydev); + + spin_lock_irqsave(&rdev->priv->lock, flags); + rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, false); + rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, false); bitmap_clear(rdev->priv->opened_ports, rdev->port, 1); + spin_unlock_irqrestore(&rdev->priv->lock, flags); + + napi_disable(&rdev->napi); if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID); @@ -1576,14 +1602,6 @@ static int rswitch_stop(struct net_device *ndev) kfree(ts_info); } - spin_lock_irqsave(&rdev->priv->lock, flags); - rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, false); - rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, false); - spin_unlock_irqrestore(&rdev->priv->lock, flags); - - phy_stop(ndev->phydev); - napi_disable(&rdev->napi); - return 0; }; @@ -1681,8 +1699,11 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd if (dma_mapping_error(ndev->dev.parent, dma_addr_orig)) goto err_kfree; - gq->skbs[gq->cur] = skb; - gq->unmap_addrs[gq->cur] = dma_addr_orig; + /* Stored the skb at the last descriptor to avoid skb free before hardware completes send */ + gq->skbs[(gq->cur + nr_desc - 1) % gq->ring_size] = skb; + gq->unmap_addrs[(gq->cur + nr_desc - 1) % gq->ring_size] = dma_addr_orig; + + dma_wmb(); /* DT_FSTART should be set at last. So, this is reverse order. */ for (i = nr_desc; i-- > 0; ) { @@ -1694,14 +1715,13 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd goto err_unmap; } - wmb(); /* gq->cur must be incremented after die_dt was set */ - gq->cur = rswitch_next_queue_index(gq, true, nr_desc); rswitch_modify(rdev->addr, GWTRC(gq->index), 0, BIT(gq->index % 32)); return ret; err_unmap: + gq->skbs[(gq->cur + nr_desc - 1) % gq->ring_size] = NULL; dma_unmap_single(ndev->dev.parent, dma_addr_orig, skb->len, DMA_TO_DEVICE); err_kfree: @@ -1889,7 +1909,6 @@ static int rswitch_device_alloc(struct rswitch_private *priv, unsigned int index rdev->np_port = rswitch_get_port_node(rdev); rdev->disabled = !rdev->np_port; err = of_get_ethdev_address(rdev->np_port, ndev); - of_node_put(rdev->np_port); if (err) { if (is_valid_ether_addr(rdev->etha->mac_addr)) eth_hw_addr_set(ndev, rdev->etha->mac_addr); @@ -1919,6 +1938,7 @@ static int rswitch_device_alloc(struct rswitch_private *priv, unsigned int index out_rxdmac: out_get_params: + of_node_put(rdev->np_port); netif_napi_del(&rdev->napi); free_netdev(ndev); @@ -1932,6 +1952,7 @@ static void rswitch_device_free(struct rswitch_private *priv, unsigned int index rswitch_txdmac_free(ndev); rswitch_rxdmac_free(ndev); + of_node_put(rdev->np_port); netif_napi_del(&rdev->napi); free_netdev(ndev); } diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index 72e3ff596d31..e020800dcc57 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -724,13 +724,13 @@ enum rswitch_etha_mode { #define EAVCC_VEM_SC_TAG (0x3 << 16) -#define MPIC_PIS_MII 0x00 -#define MPIC_PIS_GMII 0x02 -#define MPIC_PIS_XGMII 0x04 -#define MPIC_LSC_SHIFT 3 -#define MPIC_LSC_100M (1 << MPIC_LSC_SHIFT) -#define MPIC_LSC_1G (2 << MPIC_LSC_SHIFT) -#define MPIC_LSC_2_5G (3 << MPIC_LSC_SHIFT) +#define MPIC_PIS GENMASK(2, 0) +#define MPIC_PIS_GMII 2 +#define MPIC_PIS_XGMII 4 +#define MPIC_LSC GENMASK(5, 3) +#define MPIC_LSC_100M 1 +#define MPIC_LSC_1G 2 +#define MPIC_LSC_2_5G 3 #define MDIO_READ_C45 0x03 #define MDIO_WRITE_C45 0x01 diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 18191d5a8bd4..6ace5a74cddb 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -983,7 +983,8 @@ static void team_port_disable(struct team *team, #define TEAM_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ - NETIF_F_HIGHDMA | NETIF_F_LRO) + NETIF_F_HIGHDMA | NETIF_F_LRO | \ + NETIF_F_GSO_ENCAP_ALL) #define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE) @@ -991,13 +992,14 @@ static void team_port_disable(struct team *team, static void __team_compute_features(struct team *team) { struct team_port *port; - netdev_features_t vlan_features = TEAM_VLAN_FEATURES & - NETIF_F_ALL_FOR_ALL; + netdev_features_t vlan_features = TEAM_VLAN_FEATURES; netdev_features_t enc_features = TEAM_ENC_FEATURES; unsigned short max_hard_header_len = ETH_HLEN; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; + vlan_features = netdev_base_features(vlan_features); + rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, @@ -2012,8 +2014,7 @@ static netdev_features_t team_fix_features(struct net_device *dev, netdev_features_t mask; mask = features; - features &= ~NETIF_F_ONE_FOR_ALL; - features |= NETIF_F_ALL_FOR_ALL; + features = netdev_base_features(features); rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index c897afef0b41..60027b439021 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -502,6 +502,7 @@ struct virtio_net_common_hdr { }; static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf); +static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq); static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp, struct net_device *dev, unsigned int *xdp_xmit, @@ -2898,7 +2899,6 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) if (err < 0) goto err_xdp_reg_mem_model; - netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index)); virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); @@ -3166,7 +3166,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi, virtnet_rx_pause(vi, rq); - err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf); + err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf, NULL); if (err) netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err); @@ -3229,7 +3229,8 @@ static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq, virtnet_tx_pause(vi, sq); - err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf); + err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf, + virtnet_sq_free_unused_buf_done); if (err) netdev_err(vi->dev, "resize tx fail: tx queue index: %d err: %d\n", qindex, err); @@ -5997,6 +5998,14 @@ static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf) xdp_return_frame(ptr_to_xdp(buf)); } +static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq) +{ + struct virtnet_info *vi = vq->vdev->priv; + int i = vq2txq(vq); + + netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i)); +} + static void free_unused_bufs(struct virtnet_info *vi) { void *buf; @@ -6728,11 +6737,20 @@ static int virtnet_probe(struct virtio_device *vdev) static void remove_vq_common(struct virtnet_info *vi) { + int i; + virtio_reset_device(vi->vdev); /* Free unused buffers in both send and recv, if any. */ free_unused_bufs(vi); + /* + * Rule of thumb is netdev_tx_reset_queue() should follow any + * skb freeing not followed by netdev_tx_completed_queue() + */ + for (i = 0; i < vi->max_queue_pairs; i++) + netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i)); + free_receive_bufs(vi); free_receive_page_frags(vi); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index a7a10e716e65..e96ddaeeeeff 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -1967,7 +1967,7 @@ void iwl_mvm_channel_switch_error_notif(struct iwl_mvm *mvm, if (csa_err_mask & (CS_ERR_COUNT_ERROR | CS_ERR_LONG_DELAY_AFTER_CS | CS_ERR_TX_BLOCK_TIMER_EXPIRED)) - ieee80211_channel_switch_disconnect(vif, true); + ieee80211_channel_switch_disconnect(vif); rcu_read_unlock(); } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 4265c1cd0ff7..63fe51d0e64d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -867,7 +867,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev static int xennet_close(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); - unsigned int num_queues = dev->real_num_tx_queues; + unsigned int num_queues = np->queues ? dev->real_num_tx_queues : 0; unsigned int i; struct netfront_queue *queue; netif_tx_stop_all_queues(np->netdev); @@ -882,6 +882,9 @@ static void xennet_destroy_queues(struct netfront_info *info) { unsigned int i; + if (!info->queues) + return; + for (i = 0; i < info->netdev->real_num_tx_queues; i++) { struct netfront_queue *queue = &info->queues[i]; diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c index 617c8d6706d3..6cea4fe39bcf 100644 --- a/drivers/ptp/ptp_kvm_x86.c +++ b/drivers/ptp/ptp_kvm_x86.c @@ -26,7 +26,7 @@ int kvm_arch_ptp_init(void) long ret; if (!kvm_para_available()) - return -ENODEV; + return -EOPNOTSUPP; if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { p = alloc_page(GFP_KERNEL | __GFP_ZERO); @@ -46,14 +46,14 @@ int kvm_arch_ptp_init(void) clock_pair_gpa = slow_virt_to_phys(clock_pair); if (!pvclock_get_pvti_cpu0_va()) { - ret = -ENODEV; + ret = -EOPNOTSUPP; goto err; } ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa, KVM_CLOCK_PAIRING_WALLCLOCK); if (ret == -KVM_ENOSYS) { - ret = -ENODEV; + ret = -EOPNOTSUPP; goto err; } diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index a8e91d9d028b..945d2917b91b 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -371,8 +371,8 @@ .ops = &axp20x_ops, \ } -#define AXP_DESC(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ - _vmask, _ereg, _emask) \ +#define AXP_DESC_DELAY(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ + _vmask, _ereg, _emask, _ramp_delay) \ [_family##_##_id] = { \ .name = (_match), \ .supply_name = (_supply), \ @@ -388,9 +388,15 @@ .vsel_mask = (_vmask), \ .enable_reg = (_ereg), \ .enable_mask = (_emask), \ + .ramp_delay = (_ramp_delay), \ .ops = &axp20x_ops, \ } +#define AXP_DESC(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ + _vmask, _ereg, _emask) \ + AXP_DESC_DELAY(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ + _vmask, _ereg, _emask, 0) + #define AXP_DESC_SW(_family, _id, _match, _supply, _ereg, _emask) \ [_family##_##_id] = { \ .name = (_match), \ @@ -419,8 +425,8 @@ .ops = &axp20x_ops_fixed \ } -#define AXP_DESC_RANGES(_family, _id, _match, _supply, _ranges, _n_voltages, \ - _vreg, _vmask, _ereg, _emask) \ +#define AXP_DESC_RANGES_DELAY(_family, _id, _match, _supply, _ranges, _n_voltages, \ + _vreg, _vmask, _ereg, _emask, _ramp_delay) \ [_family##_##_id] = { \ .name = (_match), \ .supply_name = (_supply), \ @@ -436,9 +442,15 @@ .enable_mask = (_emask), \ .linear_ranges = (_ranges), \ .n_linear_ranges = ARRAY_SIZE(_ranges), \ + .ramp_delay = (_ramp_delay), \ .ops = &axp20x_ops_range, \ } +#define AXP_DESC_RANGES(_family, _id, _match, _supply, _ranges, _n_voltages, \ + _vreg, _vmask, _ereg, _emask) \ + AXP_DESC_RANGES_DELAY(_family, _id, _match, _supply, _ranges, \ + _n_voltages, _vreg, _vmask, _ereg, _emask, 0) + static const int axp209_dcdc2_ldo3_slew_rates[] = { 1600, 800, @@ -781,21 +793,21 @@ static const struct linear_range axp717_dcdc3_ranges[] = { }; static const struct regulator_desc axp717_regulators[] = { - AXP_DESC_RANGES(AXP717, DCDC1, "dcdc1", "vin1", + AXP_DESC_RANGES_DELAY(AXP717, DCDC1, "dcdc1", "vin1", axp717_dcdc1_ranges, AXP717_DCDC1_NUM_VOLTAGES, AXP717_DCDC1_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(0)), - AXP_DESC_RANGES(AXP717, DCDC2, "dcdc2", "vin2", + AXP717_DCDC_OUTPUT_CONTROL, BIT(0), 640), + AXP_DESC_RANGES_DELAY(AXP717, DCDC2, "dcdc2", "vin2", axp717_dcdc2_ranges, AXP717_DCDC2_NUM_VOLTAGES, AXP717_DCDC2_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(1)), - AXP_DESC_RANGES(AXP717, DCDC3, "dcdc3", "vin3", + AXP717_DCDC_OUTPUT_CONTROL, BIT(1), 640), + AXP_DESC_RANGES_DELAY(AXP717, DCDC3, "dcdc3", "vin3", axp717_dcdc3_ranges, AXP717_DCDC3_NUM_VOLTAGES, AXP717_DCDC3_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(2)), - AXP_DESC(AXP717, DCDC4, "dcdc4", "vin4", 1000, 3700, 100, + AXP717_DCDC_OUTPUT_CONTROL, BIT(2), 640), + AXP_DESC_DELAY(AXP717, DCDC4, "dcdc4", "vin4", 1000, 3700, 100, AXP717_DCDC4_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(3)), + AXP717_DCDC_OUTPUT_CONTROL, BIT(3), 6400), AXP_DESC(AXP717, ALDO1, "aldo1", "aldoin", 500, 3500, 100, AXP717_ALDO1_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(0)), diff --git a/drivers/spi/spi-aspeed-smc.c b/drivers/spi/spi-aspeed-smc.c index bbd417c55e7f..b0e3f307b283 100644 --- a/drivers/spi/spi-aspeed-smc.c +++ b/drivers/spi/spi-aspeed-smc.c @@ -239,7 +239,7 @@ static ssize_t aspeed_spi_read_user(struct aspeed_spi_chip *chip, ret = aspeed_spi_send_cmd_addr(chip, op->addr.nbytes, offset, op->cmd.opcode); if (ret < 0) - return ret; + goto stop_user; if (op->dummy.buswidth && op->dummy.nbytes) { for (i = 0; i < op->dummy.nbytes / op->dummy.buswidth; i++) @@ -249,8 +249,9 @@ static ssize_t aspeed_spi_read_user(struct aspeed_spi_chip *chip, aspeed_spi_set_io_mode(chip, io_mode); aspeed_spi_read_from_ahb(buf, chip->ahb_base, len); +stop_user: aspeed_spi_stop_user(chip); - return 0; + return ret; } static ssize_t aspeed_spi_write_user(struct aspeed_spi_chip *chip, @@ -261,10 +262,11 @@ static ssize_t aspeed_spi_write_user(struct aspeed_spi_chip *chip, aspeed_spi_start_user(chip); ret = aspeed_spi_send_cmd_addr(chip, op->addr.nbytes, op->addr.val, op->cmd.opcode); if (ret < 0) - return ret; + goto stop_user; aspeed_spi_write_to_ahb(chip->ahb_base, op->data.buf.out, op->data.nbytes); +stop_user: aspeed_spi_stop_user(chip); - return 0; + return ret; } /* support for 1-1-1, 1-1-2 or 1-1-4 */ diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 0bb33c43b1b4..40a64a598a74 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -241,6 +241,20 @@ static void rockchip_spi_set_cs(struct spi_device *spi, bool enable) struct spi_controller *ctlr = spi->controller; struct rockchip_spi *rs = spi_controller_get_devdata(ctlr); bool cs_asserted = spi->mode & SPI_CS_HIGH ? enable : !enable; + bool cs_actual; + + /* + * SPI subsystem tries to avoid no-op calls that would break the PM + * refcount below. It can't however for the first time it is used. + * To detect this case we read it here and bail out early for no-ops. + */ + if (spi_get_csgpiod(spi, 0)) + cs_actual = !!(readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & 1); + else + cs_actual = !!(readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & + BIT(spi_get_chipselect(spi, 0))); + if (unlikely(cs_actual == cs_asserted)) + return; if (cs_asserted) { /* Keep things powered as long as CS is asserted */ diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index b80e9a528e17..bdf17eafd359 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -157,6 +157,7 @@ struct sci_port { bool has_rtscts; bool autorts; + bool tx_occurred; }; #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS @@ -850,6 +851,7 @@ static void sci_transmit_chars(struct uart_port *port) { struct tty_port *tport = &port->state->port; unsigned int stopped = uart_tx_stopped(port); + struct sci_port *s = to_sci_port(port); unsigned short status; unsigned short ctrl; int count; @@ -885,6 +887,7 @@ static void sci_transmit_chars(struct uart_port *port) } sci_serial_out(port, SCxTDR, c); + s->tx_occurred = true; port->icount.tx++; } while (--count > 0); @@ -1241,6 +1244,8 @@ static void sci_dma_tx_complete(void *arg) if (kfifo_len(&tport->xmit_fifo) < WAKEUP_CHARS) uart_write_wakeup(port); + s->tx_occurred = true; + if (!kfifo_is_empty(&tport->xmit_fifo)) { s->cookie_tx = 0; schedule_work(&s->work_tx); @@ -1731,6 +1736,19 @@ static void sci_flush_buffer(struct uart_port *port) s->cookie_tx = -EINVAL; } } + +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ + struct dma_tx_state state; + enum dma_status status; + + if (!s->chan_tx) + return; + + status = dmaengine_tx_status(s->chan_tx, s->cookie_tx, &state); + if (status == DMA_COMPLETE || status == DMA_IN_PROGRESS) + s->tx_occurred = true; +} #else /* !CONFIG_SERIAL_SH_SCI_DMA */ static inline void sci_request_dma(struct uart_port *port) { @@ -1740,6 +1758,10 @@ static inline void sci_free_dma(struct uart_port *port) { } +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ +} + #define sci_flush_buffer NULL #endif /* !CONFIG_SERIAL_SH_SCI_DMA */ @@ -2076,6 +2098,12 @@ static unsigned int sci_tx_empty(struct uart_port *port) { unsigned short status = sci_serial_in(port, SCxSR); unsigned short in_tx_fifo = sci_txfill(port); + struct sci_port *s = to_sci_port(port); + + sci_dma_check_tx_occurred(s); + + if (!s->tx_occurred) + return TIOCSER_TEMT; return (status & SCxSR_TEND(port)) && !in_tx_fifo ? TIOCSER_TEMT : 0; } @@ -2247,6 +2275,7 @@ static int sci_startup(struct uart_port *port) dev_dbg(port->dev, "%s(%d)\n", __func__, port->line); + s->tx_occurred = false; sci_request_dma(port); ret = sci_request_irq(s); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index cfebe4a1af9e..bc13133efaa5 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -5566,6 +5566,7 @@ void ufshcd_compl_one_cqe(struct ufs_hba *hba, int task_tag, lrbp = &hba->lrb[task_tag]; lrbp->compl_time_stamp = ktime_get(); + lrbp->compl_time_stamp_local_clock = local_clock(); cmd = lrbp->cmd; if (cmd) { if (unlikely(ufshcd_should_inform_monitor(hba, lrbp))) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 500dc35e6477..0b2490347b9f 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2794,8 +2794,14 @@ int usb_add_hcd(struct usb_hcd *hcd, int retval; struct usb_device *rhdev; struct usb_hcd *shared_hcd; + int skip_phy_initialization; - if (!hcd->skip_phy_initialization) { + if (usb_hcd_is_primary_hcd(hcd)) + skip_phy_initialization = hcd->skip_phy_initialization; + else + skip_phy_initialization = hcd->primary_hcd->skip_phy_initialization; + + if (!skip_phy_initialization) { if (usb_hcd_is_primary_hcd(hcd)) { hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev); if (IS_ERR(hcd->phy_roothub)) diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index cb54390e7de4..8c3941ecaaf5 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -3546,11 +3546,9 @@ static int dwc2_hcd_hub_control(struct dwc2_hsotg *hsotg, u16 typereq, port_status |= USB_PORT_STAT_C_OVERCURRENT << 16; } - if (!hsotg->flags.b.port_connect_status) { + if (dwc2_is_device_mode(hsotg)) { /* - * The port is disconnected, which means the core is - * either in device mode or it soon will be. Just - * return 0's for the remainder of the port status + * Just return 0's for the remainder of the port status * since the port register can't be read if the core * is in device mode. */ @@ -3620,13 +3618,11 @@ static int dwc2_hcd_hub_control(struct dwc2_hsotg *hsotg, u16 typereq, if (wvalue != USB_PORT_FEAT_TEST && (!windex || windex > 1)) goto error; - if (!hsotg->flags.b.port_connect_status) { + if (dwc2_is_device_mode(hsotg)) { /* - * The port is disconnected, which means the core is - * either in device mode or it soon will be. Just - * return without doing anything since the port - * register can't be written if the core is in device - * mode. + * Just return 0's for the remainder of the port status + * since the port register can't be read if the core + * is in device mode. */ break; } @@ -4349,7 +4345,7 @@ static int _dwc2_hcd_suspend(struct usb_hcd *hcd) if (hsotg->bus_suspended) goto skip_power_saving; - if (hsotg->flags.b.port_connect_status == 0) + if (!(dwc2_read_hprt0(hsotg) & HPRT0_CONNSTS)) goto skip_power_saving; switch (hsotg->params.power_down) { @@ -4431,6 +4427,7 @@ static int _dwc2_hcd_resume(struct usb_hcd *hcd) * Power Down mode. */ if (hprt0 & HPRT0_CONNSTS) { + set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags); hsotg->lx_state = DWC2_L0; goto unlock; } diff --git a/drivers/usb/dwc3/dwc3-imx8mp.c b/drivers/usb/dwc3/dwc3-imx8mp.c index 64c0cd1995aa..e99faf014c78 100644 --- a/drivers/usb/dwc3/dwc3-imx8mp.c +++ b/drivers/usb/dwc3/dwc3-imx8mp.c @@ -129,6 +129,16 @@ static void dwc3_imx8mp_wakeup_disable(struct dwc3_imx8mp *dwc3_imx) writel(val, dwc3_imx->hsio_blk_base + USB_WAKEUP_CTRL); } +static const struct property_entry dwc3_imx8mp_properties[] = { + PROPERTY_ENTRY_BOOL("xhci-missing-cas-quirk"), + PROPERTY_ENTRY_BOOL("xhci-skip-phy-init-quirk"), + {}, +}; + +static const struct software_node dwc3_imx8mp_swnode = { + .properties = dwc3_imx8mp_properties, +}; + static irqreturn_t dwc3_imx8mp_interrupt(int irq, void *_dwc3_imx) { struct dwc3_imx8mp *dwc3_imx = _dwc3_imx; @@ -148,17 +158,6 @@ static irqreturn_t dwc3_imx8mp_interrupt(int irq, void *_dwc3_imx) return IRQ_HANDLED; } -static int dwc3_imx8mp_set_software_node(struct device *dev) -{ - struct property_entry props[3] = { 0 }; - int prop_idx = 0; - - props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-missing-cas-quirk"); - props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-skip-phy-init-quirk"); - - return device_create_managed_software_node(dev, props, NULL); -} - static int dwc3_imx8mp_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -221,17 +220,17 @@ static int dwc3_imx8mp_probe(struct platform_device *pdev) if (err < 0) goto disable_rpm; - err = dwc3_imx8mp_set_software_node(dev); + err = device_add_software_node(dev, &dwc3_imx8mp_swnode); if (err) { err = -ENODEV; - dev_err(dev, "failed to create software node\n"); + dev_err(dev, "failed to add software node\n"); goto disable_rpm; } err = of_platform_populate(node, NULL, NULL, dev); if (err) { dev_err(&pdev->dev, "failed to create dwc3 core\n"); - goto disable_rpm; + goto remove_swnode; } dwc3_imx->dwc3 = of_find_device_by_node(dwc3_np); @@ -255,6 +254,8 @@ static int dwc3_imx8mp_probe(struct platform_device *pdev) depopulate: of_platform_depopulate(dev); +remove_swnode: + device_remove_software_node(dev); disable_rpm: pm_runtime_disable(dev); pm_runtime_put_noidle(dev); @@ -268,6 +269,7 @@ static void dwc3_imx8mp_remove(struct platform_device *pdev) pm_runtime_get_sync(dev); of_platform_depopulate(dev); + device_remove_software_node(dev); pm_runtime_disable(dev); pm_runtime_put_noidle(dev); diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c index b5e5be424ce9..96c87dc4757f 100644 --- a/drivers/usb/dwc3/dwc3-xilinx.c +++ b/drivers/usb/dwc3/dwc3-xilinx.c @@ -121,8 +121,11 @@ static int dwc3_xlnx_init_zynqmp(struct dwc3_xlnx *priv_data) * in use but the usb3-phy entry is missing from the device tree. * Therefore, skip these operations in this case. */ - if (!priv_data->usb3_phy) + if (!priv_data->usb3_phy) { + /* Deselect the PIPE Clock Select bit in FPD PIPE Clock register */ + writel(PIPE_CLK_DESELECT, priv_data->regs + XLNX_USB_FPD_PIPE_CLK); goto skip_usb3_phy; + } crst = devm_reset_control_get_exclusive(dev, "usb_crst"); if (IS_ERR(crst)) { diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index 8285df9ed6fd..8c9d0074db58 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -1593,7 +1593,11 @@ static int f_midi2_create_card(struct f_midi2 *midi2) fb->info.midi_ci_version = b->midi_ci_version; fb->info.ui_hint = reverse_dir(b->ui_hint); fb->info.sysex8_streams = b->sysex8_streams; - fb->info.flags |= b->is_midi1; + if (b->is_midi1 < 2) + fb->info.flags |= b->is_midi1; + else + fb->info.flags |= SNDRV_UMP_BLOCK_IS_MIDI1 | + SNDRV_UMP_BLOCK_IS_LOWSPEED; strscpy(fb->info.name, ump_fb_name(b), sizeof(fb->info.name)); } diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 0a8c05b2746b..53d9fc41acc5 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -579,9 +579,12 @@ static int gs_start_io(struct gs_port *port) * we didn't in gs_start_tx() */ tty_wakeup(port->port.tty); } else { - gs_free_requests(ep, head, &port->read_allocated); - gs_free_requests(port->port_usb->in, &port->write_pool, - &port->write_allocated); + /* Free reqs only if we are still connected */ + if (port->port_usb) { + gs_free_requests(ep, head, &port->read_allocated); + gs_free_requests(port->port_usb->in, &port->write_pool, + &port->write_allocated); + } status = -EIO; } diff --git a/drivers/usb/host/ehci-sh.c b/drivers/usb/host/ehci-sh.c index d31d9506e41a..7c2b2339e674 100644 --- a/drivers/usb/host/ehci-sh.c +++ b/drivers/usb/host/ehci-sh.c @@ -119,8 +119,12 @@ static int ehci_hcd_sh_probe(struct platform_device *pdev) if (IS_ERR(priv->iclk)) priv->iclk = NULL; - clk_enable(priv->fclk); - clk_enable(priv->iclk); + ret = clk_enable(priv->fclk); + if (ret) + goto fail_request_resource; + ret = clk_enable(priv->iclk); + if (ret) + goto fail_iclk; ret = usb_add_hcd(hcd, irq, IRQF_SHARED); if (ret != 0) { @@ -136,6 +140,7 @@ static int ehci_hcd_sh_probe(struct platform_device *pdev) fail_add_hcd: clk_disable(priv->iclk); +fail_iclk: clk_disable(priv->fclk); fail_request_resource: diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c index 9fe4f48b1898..0881fdd1823e 100644 --- a/drivers/usb/host/max3421-hcd.c +++ b/drivers/usb/host/max3421-hcd.c @@ -779,11 +779,17 @@ max3421_check_unlink(struct usb_hcd *hcd) retval = 1; dev_dbg(&spi->dev, "%s: URB %p unlinked=%d", __func__, urb, urb->unlinked); - usb_hcd_unlink_urb_from_ep(hcd, urb); - spin_unlock_irqrestore(&max3421_hcd->lock, - flags); - usb_hcd_giveback_urb(hcd, urb, 0); - spin_lock_irqsave(&max3421_hcd->lock, flags); + if (urb == max3421_hcd->curr_urb) { + max3421_hcd->urb_done = 1; + max3421_hcd->hien &= ~(BIT(MAX3421_HI_HXFRDN_BIT) | + BIT(MAX3421_HI_RCVDAV_BIT)); + } else { + usb_hcd_unlink_urb_from_ep(hcd, urb); + spin_unlock_irqrestore(&max3421_hcd->lock, + flags); + usb_hcd_giveback_urb(hcd, urb, 0); + spin_lock_irqsave(&max3421_hcd->lock, flags); + } } } } diff --git a/drivers/usb/misc/onboard_usb_dev.c b/drivers/usb/misc/onboard_usb_dev.c index 75dfdca04ff1..27b0a6e18267 100644 --- a/drivers/usb/misc/onboard_usb_dev.c +++ b/drivers/usb/misc/onboard_usb_dev.c @@ -407,8 +407,10 @@ static int onboard_dev_probe(struct platform_device *pdev) } if (of_device_is_compatible(pdev->dev.of_node, "usb424,2744") || - of_device_is_compatible(pdev->dev.of_node, "usb424,5744")) + of_device_is_compatible(pdev->dev.of_node, "usb424,5744")) { err = onboard_dev_5744_i2c_init(client); + onboard_dev->always_powered_in_suspend = true; + } put_device(&client->dev); if (err < 0) diff --git a/drivers/usb/typec/anx7411.c b/drivers/usb/typec/anx7411.c index d1e7c487ddfb..0ae0a5ee3fae 100644 --- a/drivers/usb/typec/anx7411.c +++ b/drivers/usb/typec/anx7411.c @@ -290,6 +290,8 @@ struct anx7411_data { struct power_supply *psy; struct power_supply_desc psy_desc; struct device *dev; + struct fwnode_handle *switch_node; + struct fwnode_handle *mux_node; }; static u8 snk_identity[] = { @@ -1021,6 +1023,16 @@ static void anx7411_port_unregister_altmodes(struct typec_altmode **adev) } } +static void anx7411_port_unregister(struct typec_params *typecp) +{ + fwnode_handle_put(typecp->caps.fwnode); + anx7411_port_unregister_altmodes(typecp->port_amode); + if (typecp->port) + typec_unregister_port(typecp->port); + if (typecp->role_sw) + usb_role_switch_put(typecp->role_sw); +} + static int anx7411_usb_mux_set(struct typec_mux_dev *mux, struct typec_mux_state *state) { @@ -1089,6 +1101,7 @@ static void anx7411_unregister_mux(struct anx7411_data *ctx) if (ctx->typec.typec_mux) { typec_mux_unregister(ctx->typec.typec_mux); ctx->typec.typec_mux = NULL; + fwnode_handle_put(ctx->mux_node); } } @@ -1097,6 +1110,7 @@ static void anx7411_unregister_switch(struct anx7411_data *ctx) if (ctx->typec.typec_switch) { typec_switch_unregister(ctx->typec.typec_switch); ctx->typec.typec_switch = NULL; + fwnode_handle_put(ctx->switch_node); } } @@ -1104,28 +1118,29 @@ static int anx7411_typec_switch_probe(struct anx7411_data *ctx, struct device *dev) { int ret; - struct device_node *node; - node = of_get_child_by_name(dev->of_node, "orientation_switch"); - if (!node) + ctx->switch_node = device_get_named_child_node(dev, "orientation_switch"); + if (!ctx->switch_node) return 0; - ret = anx7411_register_switch(ctx, dev, &node->fwnode); + ret = anx7411_register_switch(ctx, dev, ctx->switch_node); if (ret) { dev_err(dev, "failed register switch"); + fwnode_handle_put(ctx->switch_node); return ret; } - node = of_get_child_by_name(dev->of_node, "mode_switch"); - if (!node) { + ctx->mux_node = device_get_named_child_node(dev, "mode_switch"); + if (!ctx->mux_node) { dev_err(dev, "no typec mux exist"); ret = -ENODEV; goto unregister_switch; } - ret = anx7411_register_mux(ctx, dev, &node->fwnode); + ret = anx7411_register_mux(ctx, dev, ctx->mux_node); if (ret) { dev_err(dev, "failed register mode switch"); + fwnode_handle_put(ctx->mux_node); ret = -ENODEV; goto unregister_switch; } @@ -1154,34 +1169,34 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, ret = fwnode_property_read_string(fwnode, "power-role", &buf); if (ret) { dev_err(dev, "power-role not found: %d\n", ret); - return ret; + goto put_fwnode; } ret = typec_find_port_power_role(buf); if (ret < 0) - return ret; + goto put_fwnode; cap->type = ret; ret = fwnode_property_read_string(fwnode, "data-role", &buf); if (ret) { dev_err(dev, "data-role not found: %d\n", ret); - return ret; + goto put_fwnode; } ret = typec_find_port_data_role(buf); if (ret < 0) - return ret; + goto put_fwnode; cap->data = ret; ret = fwnode_property_read_string(fwnode, "try-power-role", &buf); if (ret) { dev_err(dev, "try-power-role not found: %d\n", ret); - return ret; + goto put_fwnode; } ret = typec_find_power_role(buf); if (ret < 0) - return ret; + goto put_fwnode; cap->prefer_role = ret; /* Get source pdos */ @@ -1193,7 +1208,7 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, typecp->src_pdo_nr); if (ret < 0) { dev_err(dev, "source cap validate failed: %d\n", ret); - return -EINVAL; + goto put_fwnode; } typecp->caps_flags |= HAS_SOURCE_CAP; @@ -1207,7 +1222,7 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, typecp->sink_pdo_nr); if (ret < 0) { dev_err(dev, "sink cap validate failed: %d\n", ret); - return -EINVAL; + goto put_fwnode; } for (i = 0; i < typecp->sink_pdo_nr; i++) { @@ -1251,13 +1266,21 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, ret = PTR_ERR(ctx->typec.port); ctx->typec.port = NULL; dev_err(dev, "Failed to register type c port %d\n", ret); - return ret; + goto put_usb_role_switch; } typec_port_register_altmodes(ctx->typec.port, NULL, ctx, ctx->typec.port_amode, MAX_ALTMODE); return 0; + +put_usb_role_switch: + if (ctx->typec.role_sw) + usb_role_switch_put(ctx->typec.role_sw); +put_fwnode: + fwnode_handle_put(fwnode); + + return ret; } static int anx7411_typec_check_connection(struct anx7411_data *ctx) @@ -1523,8 +1546,7 @@ static int anx7411_i2c_probe(struct i2c_client *client) destroy_workqueue(plat->workqueue); free_typec_port: - typec_unregister_port(plat->typec.port); - anx7411_port_unregister_altmodes(plat->typec.port_amode); + anx7411_port_unregister(&plat->typec); free_typec_switch: anx7411_unregister_switch(plat); @@ -1548,17 +1570,11 @@ static void anx7411_i2c_remove(struct i2c_client *client) i2c_unregister_device(plat->spi_client); - if (plat->typec.role_sw) - usb_role_switch_put(plat->typec.role_sw); - anx7411_unregister_mux(plat); anx7411_unregister_switch(plat); - if (plat->typec.port) - typec_unregister_port(plat->typec.port); - - anx7411_port_unregister_altmodes(plat->typec.port_amode); + anx7411_port_unregister(&plat->typec); } static const struct i2c_device_id anx7411_id[] = { diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index e0f3925e401b..7a3f0f5af38f 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -46,11 +46,11 @@ void ucsi_notify_common(struct ucsi *ucsi, u32 cci) ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci)); if (cci & UCSI_CCI_ACK_COMPLETE && - test_bit(ACK_PENDING, &ucsi->flags)) + test_and_clear_bit(ACK_PENDING, &ucsi->flags)) complete(&ucsi->complete); if (cci & UCSI_CCI_COMMAND_COMPLETE && - test_bit(COMMAND_PENDING, &ucsi->flags)) + test_and_clear_bit(COMMAND_PENDING, &ucsi->flags)) complete(&ucsi->complete); } EXPORT_SYMBOL_GPL(ucsi_notify_common); @@ -65,6 +65,8 @@ int ucsi_sync_control_common(struct ucsi *ucsi, u64 command) else set_bit(COMMAND_PENDING, &ucsi->flags); + reinit_completion(&ucsi->complete); + ret = ucsi->ops->async_control(ucsi, command); if (ret) goto out_clear_bit; diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 98374ed7c577..0112742e4504 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2716,6 +2716,7 @@ EXPORT_SYMBOL_GPL(vring_create_virtqueue_dma); * @_vq: the struct virtqueue we're talking about. * @num: new ring num * @recycle: callback to recycle unused buffers + * @recycle_done: callback to be invoked when recycle for all unused buffers done * * When it is really necessary to create a new vring, it will set the current vq * into the reset state. Then call the passed callback to recycle the buffer @@ -2736,7 +2737,8 @@ EXPORT_SYMBOL_GPL(vring_create_virtqueue_dma); * */ int virtqueue_resize(struct virtqueue *_vq, u32 num, - void (*recycle)(struct virtqueue *vq, void *buf)) + void (*recycle)(struct virtqueue *vq, void *buf), + void (*recycle_done)(struct virtqueue *vq)) { struct vring_virtqueue *vq = to_vvq(_vq); int err; @@ -2753,6 +2755,8 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num, err = virtqueue_disable_and_recycle(_vq, recycle); if (err) return err; + if (recycle_done) + recycle_done(_vq); if (vq->packed_ring) err = virtqueue_resize_packed(_vq, num); diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index b35fe1075503..fafc07e38663 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1925,6 +1925,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) goto unlink_out; } + netfs_wait_for_outstanding_io(inode); cifs_close_deferred_file_under_dentry(tcon, full_path); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -2442,8 +2443,10 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, } cifs_close_deferred_file_under_dentry(tcon, from_name); - if (d_inode(target_dentry) != NULL) + if (d_inode(target_dentry) != NULL) { + netfs_wait_for_outstanding_io(d_inode(target_dentry)); cifs_close_deferred_file_under_dentry(tcon, to_name); + } rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 611716bc8f27..8892177e500f 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -1016,6 +1016,8 @@ static int ksmbd_get_encryption_key(struct ksmbd_work *work, __u64 ses_id, ses_enc_key = enc ? sess->smb3encryptionkey : sess->smb3decryptionkey; + if (enc) + ksmbd_user_session_get(sess); memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); return 0; diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index ad02fe555fda..d960ddcbba16 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -263,8 +263,10 @@ struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, down_read(&conn->session_lock); sess = xa_load(&conn->sessions, id); - if (sess) + if (sess) { sess->last_active = jiffies; + ksmbd_user_session_get(sess); + } up_read(&conn->session_lock); return sess; } @@ -275,6 +277,8 @@ struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id) down_read(&sessions_table_lock); sess = __session_lookup(id); + if (sess) + ksmbd_user_session_get(sess); up_read(&sessions_table_lock); return sess; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index c8cc6fa6fc3e..698af37e988d 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -241,14 +241,14 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, if (work->tcon) ksmbd_tree_connect_put(work->tcon); smb3_preauth_hash_rsp(work); - if (work->sess) - ksmbd_user_session_put(work->sess); if (work->sess && work->sess->enc && work->encrypted && conn->ops->encrypt_resp) { rc = conn->ops->encrypt_resp(work); if (rc < 0) conn->ops->set_rsp_status(work, STATUS_DATA_ERROR); } + if (work->sess) + ksmbd_user_session_put(work->sess); ksmbd_conn_write(work); } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index d0836d710f18..7d01dd313351 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -67,8 +67,10 @@ static inline bool check_session_id(struct ksmbd_conn *conn, u64 id) return false; sess = ksmbd_session_lookup_all(conn, id); - if (sess) + if (sess) { + ksmbd_user_session_put(sess); return true; + } pr_err("Invalid user session id: %llu\n", id); return false; } @@ -605,10 +607,8 @@ int smb2_check_user_session(struct ksmbd_work *work) /* Check for validity of user session */ work->sess = ksmbd_session_lookup_all(conn, sess_id); - if (work->sess) { - ksmbd_user_session_get(work->sess); + if (work->sess) return 1; - } ksmbd_debug(SMB, "Invalid user session, Uid %llu\n", sess_id); return -ENOENT; } @@ -1701,29 +1701,35 @@ int smb2_sess_setup(struct ksmbd_work *work) if (conn->dialect != sess->dialect) { rc = -EINVAL; + ksmbd_user_session_put(sess); goto out_err; } if (!(req->hdr.Flags & SMB2_FLAGS_SIGNED)) { rc = -EINVAL; + ksmbd_user_session_put(sess); goto out_err; } if (strncmp(conn->ClientGUID, sess->ClientGUID, SMB2_CLIENT_GUID_SIZE)) { rc = -ENOENT; + ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_IN_PROGRESS) { rc = -EACCES; + ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_EXPIRED) { rc = -EFAULT; + ksmbd_user_session_put(sess); goto out_err; } + ksmbd_user_session_put(sess); if (ksmbd_conn_need_reconnect(conn)) { rc = -EFAULT; @@ -1731,7 +1737,8 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } - if (ksmbd_session_lookup(conn, sess_id)) { + sess = ksmbd_session_lookup(conn, sess_id); + if (!sess) { rc = -EACCES; goto out_err; } @@ -1742,7 +1749,6 @@ int smb2_sess_setup(struct ksmbd_work *work) } conn->binding = true; - ksmbd_user_session_get(sess); } else if ((conn->dialect < SMB30_PROT_ID || server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) && (req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { @@ -1769,7 +1775,6 @@ int smb2_sess_setup(struct ksmbd_work *work) } conn->binding = false; - ksmbd_user_session_get(sess); } work->sess = sess; @@ -2195,9 +2200,9 @@ int smb2_tree_disconnect(struct ksmbd_work *work) int smb2_session_logoff(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + struct ksmbd_session *sess = work->sess; struct smb2_logoff_req *req; struct smb2_logoff_rsp *rsp; - struct ksmbd_session *sess; u64 sess_id; int err; @@ -2219,11 +2224,6 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_close_session_fds(work); ksmbd_conn_wait_idle(conn); - /* - * Re-lookup session to validate if session is deleted - * while waiting request complete - */ - sess = ksmbd_session_lookup_all(conn, sess_id); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -8962,6 +8962,7 @@ int smb3_decrypt_req(struct ksmbd_work *work) le64_to_cpu(tr_hdr->SessionId)); return -ECONNABORTED; } + ksmbd_user_session_put(sess); iov[0].iov_base = buf; iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index a5c4af148853..134d87b3489a 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -3569,14 +3569,31 @@ xfs_btree_insrec( xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS); /* - * If we just inserted into a new tree block, we have to - * recalculate nkey here because nkey is out of date. + * Update btree keys to reflect the newly added record or keyptr. + * There are three cases here to be aware of. Normally, all we have to + * do is walk towards the root, updating keys as necessary. * - * Otherwise we're just updating an existing block (having shoved - * some records into the new tree block), so use the regular key - * update mechanism. + * If the caller had us target a full block for the insertion, we dealt + * with that by calling the _make_block_unfull function. If the + * "make unfull" function splits the block, it'll hand us back the key + * and pointer of the new block. We haven't yet added the new block to + * the next level up, so if we decide to add the new record to the new + * block (bp->b_bn != old_bn), we have to update the caller's pointer + * so that the caller adds the new block with the correct key. + * + * However, there is a third possibility-- if the selected block is the + * root block of an inode-rooted btree and cannot be expanded further, + * the "make unfull" function moves the root block contents to a new + * block and updates the root block to point to the new block. In this + * case, no block pointer is passed back because the block has already + * been added to the btree. In this case, we need to use the regular + * key update function, just like the first case. This is critical for + * overlapping btrees, because the high key must be updated to reflect + * the entire tree, not just the subtree accessible through the first + * child of the root (which is now two levels down from the root). */ - if (bp && xfs_buf_daddr(bp) != old_bn) { + if (!xfs_btree_ptr_is_null(cur, &nptr) && + bp && xfs_buf_daddr(bp) != old_bn) { xfs_btree_get_keys(cur, block, lkey); } else if (xfs_btree_needs_key_update(cur, optr)) { error = xfs_btree_update_keys(cur, level); @@ -5156,7 +5173,7 @@ xfs_btree_count_blocks_helper( int level, void *data) { - xfs_extlen_t *blocks = data; + xfs_filblks_t *blocks = data; (*blocks)++; return 0; @@ -5166,7 +5183,7 @@ xfs_btree_count_blocks_helper( int xfs_btree_count_blocks( struct xfs_btree_cur *cur, - xfs_extlen_t *blocks) + xfs_filblks_t *blocks) { *blocks = 0; return xfs_btree_visit_blocks(cur, xfs_btree_count_blocks_helper, diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 10b7ddc3b2b3..91e0b6dac31e 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -485,7 +485,7 @@ typedef int (*xfs_btree_visit_blocks_fn)(struct xfs_btree_cur *cur, int level, int xfs_btree_visit_blocks(struct xfs_btree_cur *cur, xfs_btree_visit_blocks_fn fn, unsigned int flags, void *data); -int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_extlen_t *blocks); +int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_filblks_t *blocks); union xfs_btree_rec *xfs_btree_rec_addr(struct xfs_btree_cur *cur, int n, struct xfs_btree_block *block); diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 401b42d52af6..6aa43f3fc68e 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -743,6 +743,7 @@ xfs_finobt_count_blocks( { struct xfs_buf *agbp = NULL; struct xfs_btree_cur *cur; + xfs_filblks_t blocks; int error; error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); @@ -750,9 +751,10 @@ xfs_finobt_count_blocks( return error; cur = xfs_finobt_init_cursor(pag, tp, agbp); - error = xfs_btree_count_blocks(cur, tree_blocks); + error = xfs_btree_count_blocks(cur, &blocks); xfs_btree_del_cursor(cur, error); xfs_trans_brelse(tp, agbp); + *tree_blocks = blocks; return error; } diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index f228127a88ff..fb47a76ead18 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -92,8 +92,10 @@ xfs_symlink_verify( struct xfs_mount *mp = bp->b_mount; struct xfs_dsymlink_hdr *dsl = bp->b_addr; + /* no verification of non-crc buffers */ if (!xfs_has_crc(mp)) - return __this_address; + return NULL; + if (!xfs_verify_magic(bp, dsl->sl_magic)) return __this_address; if (!uuid_equal(&dsl->sl_uuid, &mp->m_sb.sb_meta_uuid)) diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index f8e5b67128d2..da30f926cbe6 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -434,7 +434,7 @@ xchk_agf_xref_btreeblks( { struct xfs_agf *agf = sc->sa.agf_bp->b_addr; struct xfs_mount *mp = sc->mp; - xfs_agblock_t blocks; + xfs_filblks_t blocks; xfs_agblock_t btreeblks; int error; @@ -483,7 +483,7 @@ xchk_agf_xref_refcblks( struct xfs_scrub *sc) { struct xfs_agf *agf = sc->sa.agf_bp->b_addr; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error; if (!sc->sa.refc_cur) @@ -816,7 +816,7 @@ xchk_agi_xref_fiblocks( struct xfs_scrub *sc) { struct xfs_agi *agi = sc->sa.agi_bp->b_addr; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error = 0; if (!xfs_has_inobtcounts(sc->mp)) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 2f98d90d7fd6..69b003259784 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -256,7 +256,7 @@ xrep_agf_calc_from_btrees( struct xfs_agf *agf = agf_bp->b_addr; struct xfs_mount *mp = sc->mp; xfs_agblock_t btreeblks; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error; /* Update the AGF counters from the bnobt. */ @@ -946,7 +946,7 @@ xrep_agi_calc_from_btrees( if (error) goto err; if (xfs_has_inobtcounts(mp)) { - xfs_agblock_t blocks; + xfs_filblks_t blocks; error = xfs_btree_count_blocks(cur, &blocks); if (error) @@ -959,7 +959,7 @@ xrep_agi_calc_from_btrees( agi->agi_freecount = cpu_to_be32(freecount); if (xfs_has_finobt(mp) && xfs_has_inobtcounts(mp)) { - xfs_agblock_t blocks; + xfs_filblks_t blocks; cur = xfs_finobt_init_cursor(sc->sa.pag, sc->tp, agi_bp); error = xfs_btree_count_blocks(cur, &blocks); diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index 1d3e98346933..454f17595c9c 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -261,7 +261,7 @@ xchk_fscount_btreeblks( struct xchk_fscounters *fsc, xfs_agnumber_t agno) { - xfs_extlen_t blocks; + xfs_filblks_t blocks; int error; error = xchk_ag_init_existing(sc, agno, &sc->sa); diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 750d7b0cd25a..a59c44e5903a 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -652,8 +652,8 @@ xchk_iallocbt_xref_rmap_btreeblks( struct xfs_scrub *sc) { xfs_filblks_t blocks; - xfs_extlen_t inobt_blocks = 0; - xfs_extlen_t finobt_blocks = 0; + xfs_filblks_t inobt_blocks = 0; + xfs_filblks_t finobt_blocks = 0; int error; if (!sc->sa.ino_cur || !sc->sa.rmap_cur || diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index d0c7d4a29c0f..cccf39d917a0 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -490,7 +490,7 @@ xchk_refcount_xref_rmap( struct xfs_scrub *sc, xfs_filblks_t cow_blocks) { - xfs_extlen_t refcbt_blocks = 0; + xfs_filblks_t refcbt_blocks = 0; xfs_filblks_t blocks; int error; diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c index d015a86ef460..953ce7be78dc 100644 --- a/fs/xfs/scrub/symlink_repair.c +++ b/fs/xfs/scrub/symlink_repair.c @@ -36,6 +36,7 @@ #include "scrub/tempfile.h" #include "scrub/tempexch.h" #include "scrub/reap.h" +#include "scrub/health.h" /* * Symbolic Link Repair @@ -233,7 +234,7 @@ xrep_symlink_salvage( * target zapped flag. */ if (buflen == 0) { - sc->sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED; + xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_SYMLINK_ZAPPED); sprintf(target_buf, DUMMY_TARGET); } diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index c886d5d0eb02..da773fee8638 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -601,7 +601,7 @@ TRACE_EVENT(xchk_ifork_btree_op_error, TP_fast_assign( xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level); __entry->dev = sc->mp->m_super->s_dev; - __entry->ino = sc->ip->i_ino; + __entry->ino = cur->bc_ino.ip->i_ino; __entry->whichfork = cur->bc_ino.whichfork; __entry->type = sc->sm->sm_type; __assign_str(name); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index edaf193dbd5c..95f8a09f96ae 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -111,7 +111,7 @@ xfs_bmap_count_blocks( struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur; - xfs_extlen_t btblocks = 0; + xfs_filblks_t btblocks = 0; int error; *nextents = 0; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index b19916b11fd5..aba54e3c5836 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1228,6 +1228,14 @@ xfs_file_remap_range( xfs_iunlock2_remapping(src, dest); if (ret) trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); + /* + * If the caller did not set CAN_SHORTEN, then it is not prepared to + * handle partial results -- either the whole remap succeeds, or we + * must say why it did not. In this case, any error should be returned + * to the caller. + */ + if (ret && remapped < len && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) + return ret; return remapped > 0 ? remapped : ret; } diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 3a2005a1e673..8caa55b81674 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1295,7 +1295,7 @@ xfs_rtallocate( * For an allocation to an empty file at offset 0, pick an extent that * will space things out in the rt area. */ - if (bno_hint) + if (bno_hint != NULLFSBLOCK) start = xfs_rtb_to_rtx(args.mp, bno_hint); else if (initial_user_data) start = xfs_rtpick_extent(args.mp, tp, maxlen); diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index bdf3704dc301..30e03342287a 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -834,13 +834,6 @@ __xfs_trans_commit( trace_xfs_trans_commit(tp, _RET_IP_); - error = xfs_trans_run_precommits(tp); - if (error) { - if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) - xfs_defer_cancel(tp); - goto out_unreserve; - } - /* * Finish deferred items on final commit. Only permanent transactions * should ever have deferred ops. @@ -851,13 +844,12 @@ __xfs_trans_commit( error = xfs_defer_finish_noroll(&tp); if (error) goto out_unreserve; - - /* Run precommits from final tx in defer chain. */ - error = xfs_trans_run_precommits(tp); - if (error) - goto out_unreserve; } + error = xfs_trans_run_precommits(tp); + if (error) + goto out_unreserve; + /* * If there is nothing to be logged by the transaction, * then unlock all of the items associated with the @@ -1382,5 +1374,8 @@ xfs_trans_alloc_dir( out_cancel: xfs_trans_cancel(tp); + xfs_iunlock(dp, XFS_ILOCK_EXCL); + if (dp != ip) + xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6b4bc85f4999..b7f327ce797e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -200,8 +200,6 @@ struct gendisk { spinlock_t zone_wplugs_lock; struct mempool_s *zone_wplugs_pool; struct hlist_head *zone_wplugs_hash; - struct list_head zone_wplugs_err_list; - struct work_struct zone_wplugs_work; struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ @@ -1386,6 +1384,9 @@ static inline bool bdev_is_zone_start(struct block_device *bdev, return bdev_offset_from_zone_start(bdev, sector) == 0; } +int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); + static inline int queue_dma_alignment(const struct request_queue *q) { return q->limits.dma_alignment; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cbe235091246..a7af13f550e0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2157,26 +2157,25 @@ bpf_prog_run_array(const struct bpf_prog_array *array, * rcu-protected dynamically sized maps. */ static __always_inline u32 -bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, +bpf_prog_run_array_uprobe(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; - const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; might_fault(); + RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held"); + + if (unlikely(!array)) + return ret; - rcu_read_lock_trace(); migrate_disable(); run_ctx.is_uprobe = true; - array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); - if (unlikely(!array)) - goto out; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { @@ -2191,9 +2190,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); -out: migrate_enable(); - rcu_read_unlock_trace(); return ret; } @@ -3471,10 +3468,4 @@ static inline bool bpf_is_subprog(const struct bpf_prog *prog) return prog->aux->func_idx != 0; } -static inline bool bpf_prog_is_raw_tp(const struct bpf_prog *prog) -{ - return prog->type == BPF_PROG_TYPE_TRACING && - prog->expected_attach_type == BPF_TRACE_RAW_TP; -} - #endif /* _LINUX_BPF_H */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4d4e23b6e3e7..2d962dade9fa 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -216,18 +216,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* __KERNEL__ */ -/* - * Force the compiler to emit 'sym' as a symbol, so that we can reference - * it from inline assembler. Necessary in case 'sym' could be inlined - * otherwise, or eliminated entirely due to lack of references that are - * visible to the compiler. - */ -#define ___ADDRESSABLE(sym, __attrs) \ - static void * __used __attrs \ - __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; -#define __ADDRESSABLE(sym) \ - ___ADDRESSABLE(sym, __section(".discard.addressable")) - /** * offset_to_ptr - convert a relative memory offset to an absolute pointer * @off: the address of the 32-bit offset value @@ -239,6 +227,33 @@ static inline void *offset_to_ptr(const int *off) #endif /* __ASSEMBLY__ */ +#ifdef CONFIG_64BIT +#define ARCH_SEL(a,b) a +#else +#define ARCH_SEL(a,b) b +#endif + +/* + * Force the compiler to emit 'sym' as a symbol, so that we can reference + * it from inline assembler. Necessary in case 'sym' could be inlined + * otherwise, or eliminated entirely due to lack of references that are + * visible to the compiler. + */ +#define ___ADDRESSABLE(sym, __attrs) \ + static void * __used __attrs \ + __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; + +#define __ADDRESSABLE(sym) \ + ___ADDRESSABLE(sym, __section(".discard.addressable")) + +#define __ADDRESSABLE_ASM(sym) \ + .pushsection .discard.addressable,"aw"; \ + .align ARCH_SEL(8,4); \ + ARCH_SEL(.quad, .long) __stringify(sym); \ + .popsection; + +#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) + /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 6fbfbde68a37..620a3260fc08 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -15,6 +15,7 @@ struct ocelot_skb_cb { struct sk_buff *clone; unsigned int ptp_class; /* valid only for clones */ + unsigned long ptp_tx_time; /* valid only for clones */ u32 tstamp_lo; u8 ptp_cmd; u8 ts_id; diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 66e7d26b70a4..11be70a7929f 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -253,4 +253,11 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) +static inline netdev_features_t netdev_base_features(netdev_features_t features) +{ + features &= ~NETIF_F_ONE_FOR_ALL; + features |= NETIF_F_ALL_FOR_ALL; + return features; +} + #endif /* _LINUX_NETDEV_FEATURES_H */ diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 141e6b176a1b..78a77a4ae0ea 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -160,6 +160,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool #ifdef CONFIG_HAVE_STATIC_CALL_INLINE +extern int static_call_initialized; + extern int __init static_call_init(void); extern void static_call_force_reinit(void); @@ -225,6 +227,8 @@ extern long __static_call_return0(void); #elif defined(CONFIG_HAVE_STATIC_CALL) +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } #define DEFINE_STATIC_CALL(name, _func) \ @@ -281,6 +285,8 @@ extern long __static_call_return0(void); #else /* Generic implementation */ +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } static inline long __static_call_return0(void) diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 306137a15d07..73c8922e69e0 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -100,7 +100,8 @@ dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *vq); dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq); int virtqueue_resize(struct virtqueue *vq, u32 num, - void (*recycle)(struct virtqueue *vq, void *buf)); + void (*recycle)(struct virtqueue *vq, void *buf), + void (*recycle_done)(struct virtqueue *vq)); int virtqueue_reset(struct virtqueue *vq, void (*recycle)(struct virtqueue *vq, void *buf)); diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index f66bc85c6411..435250c72d56 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -123,6 +123,7 @@ struct bt_voice { #define BT_VOICE_TRANSPARENT 0x0003 #define BT_VOICE_CVSD_16BIT 0x0060 +#define BT_VOICE_TRANSPARENT_16BIT 0x0063 #define BT_SNDMTU 12 #define BT_RCVMTU 13 @@ -590,15 +591,6 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, return skb; } -static inline int bt_copy_from_sockptr(void *dst, size_t dst_size, - sockptr_t src, size_t src_size) -{ - if (dst_size > src_size) - return -EINVAL; - - return copy_from_sockptr(dst, src, dst_size); -} - int bt_to_errno(u16 code); __u8 bt_status(int err); diff --git a/include/net/lapb.h b/include/net/lapb.h index 124ee122f2c8..6c07420644e4 100644 --- a/include/net/lapb.h +++ b/include/net/lapb.h @@ -4,7 +4,7 @@ #include #include -#define LAPB_HEADER_LEN 20 /* LAPB over Ethernet + a bit more */ +#define LAPB_HEADER_LEN MAX_HEADER /* LAPB over Ethernet + a bit more */ #define LAPB_ACK_PENDING_CONDITION 0x01 #define LAPB_REJECT_CONDITION 0x02 diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 333e0fae6796..5b712582f9a9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6770,14 +6770,12 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success, /** * ieee80211_channel_switch_disconnect - disconnect due to channel switch error * @vif: &struct ieee80211_vif pointer from the add_interface callback. - * @block_tx: if %true, do not send deauth frame. * * Instruct mac80211 to disconnect due to a channel switch error. The channel * switch can request to block the tx and so, we need to make sure we do not send * a deauth frame in this case. */ -void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, - bool block_tx); +void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif); /** * ieee80211_request_smps - request SM PS transition diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index e67b483cc8bb..9398c8f49953 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -80,6 +80,7 @@ struct net { * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ + struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ #ifdef CONFIG_KEYS diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 066a3ea33b12..91ae20cb7648 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1103,7 +1103,6 @@ struct nft_rule_blob { * @name: name of the chain * @udlen: user data length * @udata: user data in the chain - * @rcu_head: rcu head for deferred release * @blob_next: rule blob pointer to the next in the chain */ struct nft_chain { @@ -1121,7 +1120,6 @@ struct nft_chain { char *name; u16 udlen; u8 *udata; - struct rcu_head rcu_head; /* Only used during control plane commit phase: */ struct nft_rule_blob *blob_next; @@ -1265,7 +1263,6 @@ static inline void nft_use_inc_restore(u32 *use) * @sets: sets in the table * @objects: stateful objects in the table * @flowtables: flow tables in the table - * @net: netnamespace this table belongs to * @hgenerator: handle generator state * @handle: table handle * @use: number of chain references to this table @@ -1285,7 +1282,6 @@ struct nft_table { struct list_head sets; struct list_head objects; struct list_head flowtables; - possible_net_t net; u64 hgenerator; u64 handle; u32 use; diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 462c653e1017..2db9ae0575b6 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -778,7 +778,6 @@ struct ocelot_port { phy_interface_t phy_mode; - unsigned int ptp_skbs_in_flight; struct sk_buff_head tx_skbs; unsigned int trap_proto; @@ -786,7 +785,6 @@ struct ocelot_port { u16 mrp_ring_id; u8 ptp_cmd; - u8 ts_id; u8 index; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 346826e3c933..41d20b7199c4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6415,6 +6415,101 @@ int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, return off; } +struct bpf_raw_tp_null_args { + const char *func; + u64 mask; +}; + +static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { + /* sched */ + { "sched_pi_setprio", 0x10 }, + /* ... from sched_numa_pair_template event class */ + { "sched_stick_numa", 0x100 }, + { "sched_swap_numa", 0x100 }, + /* afs */ + { "afs_make_fs_call", 0x10 }, + { "afs_make_fs_calli", 0x10 }, + { "afs_make_fs_call1", 0x10 }, + { "afs_make_fs_call2", 0x10 }, + { "afs_protocol_error", 0x1 }, + { "afs_flock_ev", 0x10 }, + /* cachefiles */ + { "cachefiles_lookup", 0x1 | 0x200 }, + { "cachefiles_unlink", 0x1 }, + { "cachefiles_rename", 0x1 }, + { "cachefiles_prep_read", 0x1 }, + { "cachefiles_mark_active", 0x1 }, + { "cachefiles_mark_failed", 0x1 }, + { "cachefiles_mark_inactive", 0x1 }, + { "cachefiles_vfs_error", 0x1 }, + { "cachefiles_io_error", 0x1 }, + { "cachefiles_ondemand_open", 0x1 }, + { "cachefiles_ondemand_copen", 0x1 }, + { "cachefiles_ondemand_close", 0x1 }, + { "cachefiles_ondemand_read", 0x1 }, + { "cachefiles_ondemand_cread", 0x1 }, + { "cachefiles_ondemand_fd_write", 0x1 }, + { "cachefiles_ondemand_fd_release", 0x1 }, + /* ext4, from ext4__mballoc event class */ + { "ext4_mballoc_discard", 0x10 }, + { "ext4_mballoc_free", 0x10 }, + /* fib */ + { "fib_table_lookup", 0x100 }, + /* filelock */ + /* ... from filelock_lock event class */ + { "posix_lock_inode", 0x10 }, + { "fcntl_setlk", 0x10 }, + { "locks_remove_posix", 0x10 }, + { "flock_lock_inode", 0x10 }, + /* ... from filelock_lease event class */ + { "break_lease_noblock", 0x10 }, + { "break_lease_block", 0x10 }, + { "break_lease_unblock", 0x10 }, + { "generic_delete_lease", 0x10 }, + { "time_out_leases", 0x10 }, + /* host1x */ + { "host1x_cdma_push_gather", 0x10000 }, + /* huge_memory */ + { "mm_khugepaged_scan_pmd", 0x10 }, + { "mm_collapse_huge_page_isolate", 0x1 }, + { "mm_khugepaged_scan_file", 0x10 }, + { "mm_khugepaged_collapse_file", 0x10 }, + /* kmem */ + { "mm_page_alloc", 0x1 }, + { "mm_page_pcpu_drain", 0x1 }, + /* .. from mm_page event class */ + { "mm_page_alloc_zone_locked", 0x1 }, + /* netfs */ + { "netfs_failure", 0x10 }, + /* power */ + { "device_pm_callback_start", 0x10 }, + /* qdisc */ + { "qdisc_dequeue", 0x1000 }, + /* rxrpc */ + { "rxrpc_recvdata", 0x1 }, + { "rxrpc_resend", 0x10 }, + /* sunrpc */ + { "xs_stream_read_data", 0x1 }, + /* ... from xprt_cong_event event class */ + { "xprt_reserve_cong", 0x10 }, + { "xprt_release_cong", 0x10 }, + { "xprt_get_cong", 0x10 }, + { "xprt_put_cong", 0x10 }, + /* tcp */ + { "tcp_send_reset", 0x11 }, + /* tegra_apb_dma */ + { "tegra_dma_tx_status", 0x100 }, + /* timer_migration */ + { "tmigr_update_events", 0x1 }, + /* writeback, from writeback_folio_template event class */ + { "writeback_dirty_folio", 0x10 }, + { "folio_wait_writeback", 0x10 }, + /* rdma */ + { "mr_integ_alloc", 0x2000 }, + /* bpf_testmod */ + { "bpf_testmod_test_read", 0x0 }, +}; + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -6425,6 +6520,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, const char *tname = prog->aux->attach_func_name; struct bpf_verifier_log *log = info->log; const struct btf_param *args; + bool ptr_err_raw_tp = false; const char *tag_value; u32 nr_args, arg; int i, ret; @@ -6519,6 +6615,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, return false; } + if (size != sizeof(u64)) { + bpf_log(log, "func '%s' size %d must be 8\n", + tname, size); + return false; + } + /* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; @@ -6564,12 +6666,42 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (prog_args_trusted(prog)) info->reg_type |= PTR_TRUSTED; - /* Raw tracepoint arguments always get marked as maybe NULL */ - if (bpf_prog_is_raw_tp(prog)) - info->reg_type |= PTR_MAYBE_NULL; - else if (btf_param_match_suffix(btf, &args[arg], "__nullable")) + if (btf_param_match_suffix(btf, &args[arg], "__nullable")) info->reg_type |= PTR_MAYBE_NULL; + if (prog->expected_attach_type == BPF_TRACE_RAW_TP) { + struct btf *btf = prog->aux->attach_btf; + const struct btf_type *t; + const char *tname; + + /* BTF lookups cannot fail, return false on error */ + t = btf_type_by_id(btf, prog->aux->attach_btf_id); + if (!t) + return false; + tname = btf_name_by_offset(btf, t->name_off); + if (!tname) + return false; + /* Checked by bpf_check_attach_target */ + tname += sizeof("btf_trace_") - 1; + for (i = 0; i < ARRAY_SIZE(raw_tp_null_args); i++) { + /* Is this a func with potential NULL args? */ + if (strcmp(tname, raw_tp_null_args[i].func)) + continue; + if (raw_tp_null_args[i].mask & (0x1 << (arg * 4))) + info->reg_type |= PTR_MAYBE_NULL; + /* Is the current arg IS_ERR? */ + if (raw_tp_null_args[i].mask & (0x2 << (arg * 4))) + ptr_err_raw_tp = true; + break; + } + /* If we don't know NULL-ness specification and the tracepoint + * is coming from a loadable module, be conservative and mark + * argument as PTR_MAYBE_NULL. + */ + if (i == ARRAY_SIZE(raw_tp_null_args) && btf_is_module(btf)) + info->reg_type |= PTR_MAYBE_NULL; + } + if (tgt_prog) { enum bpf_prog_type tgt_type; @@ -6614,6 +6746,15 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n", tname, arg, info->btf_id, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); + + /* Perform all checks on the validity of type for this argument, but if + * we know it can be IS_ERR at runtime, scrub pointer type and mark as + * scalar. + */ + if (ptr_err_raw_tp) { + bpf_log(log, "marking pointer arg%d as scalar as it may encode error", arg); + info->reg_type = SCALAR_VALUE; + } return true; } EXPORT_SYMBOL_GPL(btf_ctx_access); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b2008076df9c..4c486a0bfcc4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -418,25 +418,6 @@ static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) return rec; } -static bool mask_raw_tp_reg_cond(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - return reg->type == (PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL) && - bpf_prog_is_raw_tp(env->prog) && !reg->ref_obj_id; -} - -static bool mask_raw_tp_reg(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) -{ - if (!mask_raw_tp_reg_cond(env, reg)) - return false; - reg->type &= ~PTR_MAYBE_NULL; - return true; -} - -static void unmask_raw_tp_reg(struct bpf_reg_state *reg, bool result) -{ - if (result) - reg->type |= PTR_MAYBE_NULL; -} - static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog) { struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux; @@ -6618,7 +6599,6 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, const char *field_name = NULL; enum bpf_type_flag flag = 0; u32 btf_id = 0; - bool mask; int ret; if (!env->allow_ptr_leaks) { @@ -6690,21 +6670,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (ret < 0) return ret; - /* For raw_tp progs, we allow dereference of PTR_MAYBE_NULL - * trusted PTR_TO_BTF_ID, these are the ones that are possibly - * arguments to the raw_tp. Since internal checks in for trusted - * reg in check_ptr_to_btf_access would consider PTR_MAYBE_NULL - * modifier as problematic, mask it out temporarily for the - * check. Don't apply this to pointers with ref_obj_id > 0, as - * those won't be raw_tp args. - * - * We may end up applying this relaxation to other trusted - * PTR_TO_BTF_ID with maybe null flag, since we cannot - * distinguish PTR_MAYBE_NULL tagged for arguments vs normal - * tagging, but that should expand allowed behavior, and not - * cause regression for existing behavior. - */ - mask = mask_raw_tp_reg(env, reg); + if (ret != PTR_TO_BTF_ID) { /* just mark; */ @@ -6765,13 +6731,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, clear_trusted_flags(&flag); } - if (atype == BPF_READ && value_regno >= 0) { + if (atype == BPF_READ && value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); - /* We've assigned a new type to regno, so don't undo masking. */ - if (regno == value_regno) - mask = false; - } - unmask_raw_tp_reg(reg, mask); return 0; } @@ -7146,7 +7107,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (base_type(reg->type) == PTR_TO_BTF_ID && - (mask_raw_tp_reg_cond(env, reg) || !type_may_be_null(reg->type))) { + !type_may_be_null(reg->type)) { err = check_ptr_to_btf_access(env, regs, regno, off, size, t, value_regno); } else if (reg->type == CONST_PTR_TO_MAP) { @@ -8844,7 +8805,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, enum bpf_reg_type type = reg->type; u32 *arg_btf_id = NULL; int err = 0; - bool mask; if (arg_type == ARG_DONTCARE) return 0; @@ -8885,11 +8845,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, base_type(arg_type) == ARG_PTR_TO_SPIN_LOCK) arg_btf_id = fn->arg_btf_id[arg]; - mask = mask_raw_tp_reg(env, reg); err = check_reg_type(env, regno, arg_type, arg_btf_id, meta); + if (err) + return err; - err = err ?: check_func_arg_reg_off(env, reg, regno, arg_type); - unmask_raw_tp_reg(reg, mask); + err = check_func_arg_reg_off(env, reg, regno, arg_type); if (err) return err; @@ -9684,17 +9644,14 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, return ret; } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { struct bpf_call_arg_meta meta; - bool mask; int err; if (register_is_null(reg) && type_may_be_null(arg->arg_type)) continue; memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */ - mask = mask_raw_tp_reg(env, reg); err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta); err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type); - unmask_raw_tp_reg(reg, mask); if (err) return err; } else { @@ -12009,7 +11966,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ enum bpf_arg_type arg_type = ARG_DONTCARE; u32 regno = i + 1, ref_id, type_size; bool is_ret_buf_sz = false; - bool mask = false; int kf_arg_type; t = btf_type_skip_modifiers(btf, args[i].type, NULL); @@ -12068,15 +12024,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return -EINVAL; } - mask = mask_raw_tp_reg(env, reg); if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) && (register_is_null(reg) || type_may_be_null(reg->type)) && !is_kfunc_arg_nullable(meta->btf, &args[i])) { verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); - unmask_raw_tp_reg(reg, mask); return -EACCES; } - unmask_raw_tp_reg(reg, mask); if (reg->ref_obj_id) { if (is_kfunc_release(meta) && meta->ref_obj_id) { @@ -12134,24 +12087,16 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) break; - /* Allow passing maybe NULL raw_tp arguments to - * kfuncs for compatibility. Don't apply this to - * arguments with ref_obj_id > 0. - */ - mask = mask_raw_tp_reg(env, reg); if (!is_trusted_reg(reg)) { if (!is_kfunc_rcu(meta)) { verbose(env, "R%d must be referenced or trusted\n", regno); - unmask_raw_tp_reg(reg, mask); return -EINVAL; } if (!is_rcu_reg(reg)) { verbose(env, "R%d must be a rcu pointer\n", regno); - unmask_raw_tp_reg(reg, mask); return -EINVAL; } } - unmask_raw_tp_reg(reg, mask); fallthrough; case KF_ARG_PTR_TO_CTX: case KF_ARG_PTR_TO_DYNPTR: @@ -12174,9 +12119,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (is_kfunc_release(meta) && reg->ref_obj_id) arg_type |= OBJ_RELEASE; - mask = mask_raw_tp_reg(env, reg); ret = check_func_arg_reg_off(env, reg, regno, arg_type); - unmask_raw_tp_reg(reg, mask); if (ret < 0) return ret; @@ -12353,7 +12296,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ ref_tname = btf_name_by_offset(btf, ref_t->name_off); fallthrough; case KF_ARG_PTR_TO_BTF_ID: - mask = mask_raw_tp_reg(env, reg); /* Only base_type is checked, further checks are done here */ if ((base_type(reg->type) != PTR_TO_BTF_ID || (bpf_type_has_unsafe_modifiers(reg->type) && !is_rcu_reg(reg))) && @@ -12362,11 +12304,9 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ verbose(env, "expected %s or socket\n", reg_type_str(env, base_type(reg->type) | (type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS))); - unmask_raw_tp_reg(reg, mask); return -EINVAL; } ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); - unmask_raw_tp_reg(reg, mask); if (ret < 0) return ret; break; @@ -13336,7 +13276,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env, */ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, - struct bpf_reg_state *ptr_reg, + const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg) { struct bpf_verifier_state *vstate = env->cur_state; @@ -13350,7 +13290,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; - bool mask; int ret; dst_reg = ®s[dst]; @@ -13377,14 +13316,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } - mask = mask_raw_tp_reg(env, ptr_reg); if (ptr_reg->type & PTR_MAYBE_NULL) { verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", dst, reg_type_str(env, ptr_reg->type)); - unmask_raw_tp_reg(ptr_reg, mask); return -EACCES; } - unmask_raw_tp_reg(ptr_reg, mask); switch (base_type(ptr_reg->type)) { case PTR_TO_CTX: @@ -19934,7 +19870,6 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) * for this case. */ case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: - case PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL: if (type == BPF_READ) { if (BPF_MODE(insn->code) == BPF_MEM) insn->code = BPF_LDX | BPF_PROBE_MEM | diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 40a1ad4493b4..fc6f41ac33eb 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -781,7 +781,7 @@ static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se, * If it is a deferred reservation, and the server * is not handling an starvation case, defer it. */ - if (dl_se->dl_defer & !dl_se->dl_defer_running) { + if (dl_se->dl_defer && !dl_se->dl_defer_running) { dl_se->dl_throttled = 1; dl_se->dl_defer_armed = 1; } diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c index 5259cda486d0..bb7d066a7c39 100644 --- a/kernel/static_call_inline.c +++ b/kernel/static_call_inline.c @@ -15,7 +15,7 @@ extern struct static_call_site __start_static_call_sites[], extern struct static_call_tramp_key __start_static_call_tramp_key[], __stop_static_call_tramp_key[]; -static int static_call_initialized; +int static_call_initialized; /* * Must be called before early_initcall() to be effective. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 792dc35414a3..50881898e758 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2215,6 +2215,9 @@ void perf_event_detach_bpf_prog(struct perf_event *event) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); + if (!old_array) + goto put; + ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array); if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); @@ -2223,6 +2226,14 @@ void perf_event_detach_bpf_prog(struct perf_event *event) bpf_prog_array_free_sleepable(old_array); } +put: + /* + * It could be that the bpf_prog is not sleepable (and will be freed + * via normal RCU), but is called from a point that supports sleepable + * programs and uses tasks-trace-RCU. + */ + synchronize_rcu_tasks_trace(); + bpf_prog_put(event->prog); event->prog = NULL; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index b30fc8fcd095..b085a8a164ea 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1400,9 +1400,13 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, #ifdef CONFIG_BPF_EVENTS if (bpf_prog_array_valid(call)) { + const struct bpf_prog_array *array; u32 ret; - ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run); + rcu_read_lock_trace(); + array = rcu_dereference_check(call->prog_array, rcu_read_lock_trace_held()); + ret = bpf_prog_run_array_uprobe(array, regs, bpf_prog_run); + rcu_read_unlock_trace(); if (!ret) return; } diff --git a/mm/slub.c b/mm/slub.c index 15ba89fef89a..b9447a955f61 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2199,9 +2199,24 @@ bool memcg_slab_post_charge(void *p, gfp_t flags) folio = virt_to_folio(p); if (!folio_test_slab(folio)) { - return folio_memcg_kmem(folio) || - (__memcg_kmem_charge_page(folio_page(folio, 0), flags, - folio_order(folio)) == 0); + int size; + + if (folio_memcg_kmem(folio)) + return true; + + if (__memcg_kmem_charge_page(folio_page(folio, 0), flags, + folio_order(folio))) + return false; + + /* + * This folio has already been accounted in the global stats but + * not in the memcg stats. So, subtract from the global and use + * the interface which adds to both global and memcg stats. + */ + size = folio_size(folio); + node_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B, -size); + lruvec_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B, size); + return true; } slab = folio_slab(folio); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 2243cec18ecc..53dea8ae96e4 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -990,16 +990,25 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) int tt_diff_len, tt_change_len = 0; int tt_diff_entries_num = 0; int tt_diff_entries_count = 0; + bool drop_changes = false; + size_t tt_extra_len = 0; u16 tvlv_len; tt_diff_entries_num = atomic_read(&bat_priv->tt.local_changes); tt_diff_len = batadv_tt_len(tt_diff_entries_num); /* if we have too many changes for one packet don't send any - * and wait for the tt table request which will be fragmented + * and wait for the tt table request so we can reply with the full + * (fragmented) table. + * + * The local change history should still be cleaned up so the next + * TT round can start again with a clean state. */ - if (tt_diff_len > bat_priv->soft_iface->mtu) + if (tt_diff_len > bat_priv->soft_iface->mtu) { tt_diff_len = 0; + tt_diff_entries_num = 0; + drop_changes = true; + } tvlv_len = batadv_tt_prepare_tvlv_local_data(bat_priv, &tt_data, &tt_change, &tt_diff_len); @@ -1008,7 +1017,7 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) tt_data->flags = BATADV_TT_OGM_DIFF; - if (tt_diff_len == 0) + if (!drop_changes && tt_diff_len == 0) goto container_register; spin_lock_bh(&bat_priv->tt.changes_list_lock); @@ -1027,6 +1036,9 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) } spin_unlock_bh(&bat_priv->tt.changes_list_lock); + tt_extra_len = batadv_tt_len(tt_diff_entries_num - + tt_diff_entries_count); + /* Keep the buffer for possible tt_request */ spin_lock_bh(&bat_priv->tt.last_changeset_lock); kfree(bat_priv->tt.last_changeset); @@ -1035,6 +1047,7 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) tt_change_len = batadv_tt_len(tt_diff_entries_count); /* check whether this new OGM has no changes due to size problems */ if (tt_diff_entries_count > 0) { + tt_diff_len -= tt_extra_len; /* if kmalloc() fails we will reply with the full table * instead of providing the diff */ @@ -1047,6 +1060,8 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) } spin_unlock_bh(&bat_priv->tt.last_changeset_lock); + /* Remove extra packet space for OGM */ + tvlv_len -= tt_extra_len; container_register: batadv_tvlv_container_register(bat_priv, BATADV_TVLV_TT, 1, tt_data, tvlv_len); @@ -2747,14 +2762,16 @@ static bool batadv_tt_global_valid(const void *entry_ptr, * * Fills the tvlv buff with the tt entries from the specified hash. If valid_cb * is not provided then this becomes a no-op. + * + * Return: Remaining unused length in tvlv_buff. */ -static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, - struct batadv_hashtable *hash, - void *tvlv_buff, u16 tt_len, - bool (*valid_cb)(const void *, - const void *, - u8 *flags), - void *cb_data) +static u16 batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, + struct batadv_hashtable *hash, + void *tvlv_buff, u16 tt_len, + bool (*valid_cb)(const void *, + const void *, + u8 *flags), + void *cb_data) { struct batadv_tt_common_entry *tt_common_entry; struct batadv_tvlv_tt_change *tt_change; @@ -2768,7 +2785,7 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, tt_change = tvlv_buff; if (!valid_cb) - return; + return tt_len; rcu_read_lock(); for (i = 0; i < hash->size; i++) { @@ -2794,6 +2811,8 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, } } rcu_read_unlock(); + + return batadv_tt_len(tt_tot - tt_num_entries); } /** @@ -3069,10 +3088,11 @@ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv, goto out; /* fill the rest of the tvlv with the real TT entries */ - batadv_tt_tvlv_generate(bat_priv, bat_priv->tt.global_hash, - tt_change, tt_len, - batadv_tt_global_valid, - req_dst_orig_node); + tvlv_len -= batadv_tt_tvlv_generate(bat_priv, + bat_priv->tt.global_hash, + tt_change, tt_len, + batadv_tt_global_valid, + req_dst_orig_node); } /* Don't send the response, if larger than fragmented packet. */ @@ -3196,9 +3216,11 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, goto out; /* fill the rest of the tvlv with the real TT entries */ - batadv_tt_tvlv_generate(bat_priv, bat_priv->tt.local_hash, - tt_change, tt_len, - batadv_tt_local_valid, NULL); + tvlv_len -= batadv_tt_tvlv_generate(bat_priv, + bat_priv->tt.local_hash, + tt_change, tt_len, + batadv_tt_local_valid, + NULL); } tvlv_tt_data->flags = BATADV_TT_RESPONSE; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 2b5ba8acd1d8..388d46c6a043 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6872,38 +6872,27 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, return; hci_dev_lock(hdev); - rcu_read_lock(); /* Connect all BISes that are bound to the BIG */ - list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { - if (bacmp(&conn->dst, BDADDR_ANY) || - conn->type != ISO_LINK || - conn->iso_qos.bcast.big != ev->handle) + while ((conn = hci_conn_hash_lookup_big_state(hdev, ev->handle, + BT_BOUND))) { + if (ev->status) { + hci_connect_cfm(conn, ev->status); + hci_conn_del(conn); continue; + } if (hci_conn_set_handle(conn, __le16_to_cpu(ev->bis_handle[i++]))) continue; - if (!ev->status) { - conn->state = BT_CONNECTED; - set_bit(HCI_CONN_BIG_CREATED, &conn->flags); - rcu_read_unlock(); - hci_debugfs_create_conn(conn); - hci_conn_add_sysfs(conn); - hci_iso_setup_path(conn); - rcu_read_lock(); - continue; - } - - hci_connect_cfm(conn, ev->status); - rcu_read_unlock(); - hci_conn_del(conn); - rcu_read_lock(); + conn->state = BT_CONNECTED; + set_bit(HCI_CONN_BIG_CREATED, &conn->flags); + hci_debugfs_create_conn(conn); + hci_conn_add_sysfs(conn); + hci_iso_setup_path(conn); } - rcu_read_unlock(); - if (!ev->status && !i) /* If no BISes have been connected for the BIG, * terminate. This is in case all bound connections diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 2272e1849ebd..022b86797acd 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1926,7 +1926,7 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg, } static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int len) + sockptr_t optval, unsigned int optlen) { struct hci_ufilter uf = { .opcode = 0 }; struct sock *sk = sock->sk; @@ -1943,7 +1943,7 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, switch (optname) { case HCI_DATA_DIR: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1954,7 +1954,7 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, break; case HCI_TIME_STAMP: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1974,7 +1974,7 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, uf.event_mask[1] = *((u32 *) f->event_mask + 1); } - err = bt_copy_from_sockptr(&uf, sizeof(uf), optval, len); + err = copy_safe_from_sockptr(&uf, sizeof(uf), optval, optlen); if (err) break; @@ -2005,7 +2005,7 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, } static int hci_sock_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int len) + sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; @@ -2015,7 +2015,7 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname, if (level == SOL_HCI) return hci_sock_setsockopt_old(sock, level, optname, optval, - len); + optlen); if (level != SOL_BLUETOOTH) return -ENOPROTOOPT; @@ -2035,7 +2035,7 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname, goto done; } - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 5e2d9758bd3c..644b606743e2 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1129,6 +1129,7 @@ static int iso_listen_bis(struct sock *sk) return -EHOSTUNREACH; hci_dev_lock(hdev); + lock_sock(sk); /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_bcast_qos(&iso_pi(sk)->qos)) { @@ -1158,10 +1159,10 @@ static int iso_listen_bis(struct sock *sk) goto unlock; } - hci_dev_put(hdev); - unlock: + release_sock(sk); hci_dev_unlock(hdev); + hci_dev_put(hdev); return err; } @@ -1188,6 +1189,7 @@ static int iso_sock_listen(struct socket *sock, int backlog) BT_DBG("sk %p backlog %d", sk, backlog); + sock_hold(sk); lock_sock(sk); if (sk->sk_state != BT_BOUND) { @@ -1200,10 +1202,16 @@ static int iso_sock_listen(struct socket *sock, int backlog) goto done; } - if (!bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) + if (!bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) { err = iso_listen_cis(sk); - else + } else { + /* Drop sock lock to avoid potential + * deadlock with the hdev lock. + */ + release_sock(sk); err = iso_listen_bis(sk); + lock_sock(sk); + } if (err) goto done; @@ -1215,6 +1223,7 @@ static int iso_sock_listen(struct socket *sock, int backlog) done: release_sock(sk); + sock_put(sk); return err; } @@ -1226,7 +1235,11 @@ static int iso_sock_accept(struct socket *sock, struct socket *newsock, long timeo; int err = 0; - lock_sock(sk); + /* Use explicit nested locking to avoid lockdep warnings generated + * because the parent socket and the child socket are locked on the + * same thread. + */ + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); @@ -1257,7 +1270,7 @@ static int iso_sock_accept(struct socket *sock, struct socket *newsock, release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); } remove_wait_queue(sk_sleep(sk), &wait); @@ -1398,6 +1411,7 @@ static void iso_conn_big_sync(struct sock *sk) * change. */ hci_dev_lock(hdev); + lock_sock(sk); if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { err = hci_le_big_create_sync(hdev, iso_pi(sk)->conn->hcon, @@ -1410,6 +1424,7 @@ static void iso_conn_big_sync(struct sock *sk) err); } + release_sock(sk); hci_dev_unlock(hdev); } @@ -1418,39 +1433,57 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct iso_pinfo *pi = iso_pi(sk); + bool early_ret = false; + int err = 0; BT_DBG("sk %p", sk); if (test_and_clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + sock_hold(sk); lock_sock(sk); + switch (sk->sk_state) { case BT_CONNECT2: if (test_bit(BT_SK_PA_SYNC, &pi->flags)) { + release_sock(sk); iso_conn_big_sync(sk); + lock_sock(sk); + sk->sk_state = BT_LISTEN; } else { iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; } - release_sock(sk); - return 0; + + early_ret = true; + break; case BT_CONNECTED: if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) { - iso_conn_big_sync(sk); - sk->sk_state = BT_LISTEN; release_sock(sk); - return 0; + iso_conn_big_sync(sk); + lock_sock(sk); + + sk->sk_state = BT_LISTEN; + early_ret = true; } - release_sock(sk); break; case BT_CONNECT: release_sock(sk); - return iso_connect_cis(sk); + err = iso_connect_cis(sk); + lock_sock(sk); + + early_ret = true; + break; default: - release_sock(sk); break; } + + release_sock(sk); + sock_put(sk); + + if (early_ret) + return err; } return bt_sock_recvmsg(sock, msg, len, flags); @@ -1566,7 +1599,7 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1577,7 +1610,7 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1596,7 +1629,7 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&qos, sizeof(qos), optval, optlen); + err = copy_safe_from_sockptr(&qos, sizeof(qos), optval, optlen); if (err) break; @@ -1617,8 +1650,8 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(iso_pi(sk)->base, optlen, optval, - optlen); + err = copy_safe_from_sockptr(iso_pi(sk)->base, optlen, optval, + optlen); if (err) break; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 18e89e764f3b..3d2553dcdb1b 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -755,7 +755,8 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, opts.max_tx = chan->max_tx; opts.txwin_size = chan->tx_win; - err = bt_copy_from_sockptr(&opts, sizeof(opts), optval, optlen); + err = copy_safe_from_sockptr(&opts, sizeof(opts), optval, + optlen); if (err) break; @@ -800,7 +801,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, break; case L2CAP_LM: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -909,7 +910,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + err = copy_safe_from_sockptr(&sec, sizeof(sec), optval, optlen); if (err) break; @@ -956,7 +957,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -970,7 +971,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_FLUSHABLE: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1004,7 +1005,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, pwr.force_active = BT_POWER_FORCE_ACTIVE_ON; - err = bt_copy_from_sockptr(&pwr, sizeof(pwr), optval, optlen); + err = copy_safe_from_sockptr(&pwr, sizeof(pwr), optval, optlen); if (err) break; @@ -1015,7 +1016,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_CHANNEL_POLICY: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1046,7 +1047,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&mtu, sizeof(mtu), optval, optlen); + err = copy_safe_from_sockptr(&mtu, sizeof(mtu), optval, optlen); if (err) break; @@ -1076,7 +1077,8 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&mode, sizeof(mode), optval, optlen); + err = copy_safe_from_sockptr(&mode, sizeof(mode), optval, + optlen); if (err) break; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 40766f8119ed..913402806fa0 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -629,10 +629,9 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, switch (optname) { case RFCOMM_LM: - if (bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen)) { - err = -EFAULT; + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt & RFCOMM_LM_FIPS) { err = -EINVAL; @@ -685,7 +684,7 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + err = copy_safe_from_sockptr(&sec, sizeof(sec), optval, optlen); if (err) break; @@ -703,7 +702,7 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 1c7252a36866..b872a2ca3ff3 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -267,10 +267,13 @@ static int sco_connect(struct sock *sk) else type = SCO_LINK; - if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && - (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) { - err = -EOPNOTSUPP; - goto unlock; + switch (sco_pi(sk)->setting & SCO_AIRMODE_MASK) { + case SCO_AIRMODE_TRANSP: + if (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev)) { + err = -EOPNOTSUPP; + goto unlock; + } + break; } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, @@ -853,7 +856,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -872,18 +875,11 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, voice.setting = sco_pi(sk)->setting; - err = bt_copy_from_sockptr(&voice, sizeof(voice), optval, - optlen); + err = copy_safe_from_sockptr(&voice, sizeof(voice), optval, + optlen); if (err) break; - /* Explicitly check for these values */ - if (voice.setting != BT_VOICE_TRANSPARENT && - voice.setting != BT_VOICE_CVSD_16BIT) { - err = -EINVAL; - break; - } - sco_pi(sk)->setting = voice.setting; hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); @@ -891,14 +887,19 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, err = -EBADFD; break; } - if (enhanced_sync_conn_capable(hdev) && - voice.setting == BT_VOICE_TRANSPARENT) - sco_pi(sk)->codec.id = BT_CODEC_TRANSPARENT; + + switch (sco_pi(sk)->setting & SCO_AIRMODE_MASK) { + case SCO_AIRMODE_TRANSP: + if (enhanced_sync_conn_capable(hdev)) + sco_pi(sk)->codec.id = BT_CODEC_TRANSPARENT; + break; + } + hci_dev_put(hdev); break; case BT_PKT_STATUS: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -941,7 +942,8 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(buffer, optlen, optval, optlen); + err = copy_struct_from_sockptr(buffer, sizeof(buffer), optval, + optlen); if (err) { hci_dev_put(hdev); break; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index e39479f1c9a4..70fea7c1a4b0 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -443,6 +443,21 @@ static struct net *net_alloc(void) goto out; } +static LLIST_HEAD(defer_free_list); + +static void net_complete_free(void) +{ + struct llist_node *kill_list; + struct net *net, *next; + + /* Get the list of namespaces to free from last round. */ + kill_list = llist_del_all(&defer_free_list); + + llist_for_each_entry_safe(net, next, kill_list, defer_free_list) + kmem_cache_free(net_cachep, net); + +} + static void net_free(struct net *net) { if (refcount_dec_and_test(&net->passive)) { @@ -451,7 +466,8 @@ static void net_free(struct net *net) /* There should not be any trackers left there. */ ref_tracker_dir_exit(&net->notrefcnt_tracker); - kmem_cache_free(net_cachep, net); + /* Wait for an extra rcu_barrier() before final free. */ + llist_add(&net->defer_free_list, &defer_free_list); } } @@ -636,6 +652,8 @@ static void cleanup_net(struct work_struct *work) */ rcu_barrier(); + net_complete_free(); + /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 78347d7d25ef..f1b9b3958792 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -159,6 +159,7 @@ static void sock_map_del_link(struct sock *sk, verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); + break; } } spin_unlock_bh(&psock->link_lock); @@ -411,12 +412,11 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key) static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock **psk) { - struct sock *sk; + struct sock *sk = NULL; int err = 0; spin_lock_bh(&stab->lock); - sk = *psk; - if (!sk_test || sk_test == sk) + if (!sk_test || sk_test == *psk) sk = xchg(psk, NULL); if (likely(sk)) diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 8e8b1bef6af6..11ea8cfd6266 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -79,7 +79,7 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct net_device *netdev) { - int src_port, switch_id; + int src_port = -1, switch_id = -1; dsa_8021q_rcv(skb, &src_port, &switch_id, NULL, NULL); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 68804fd01daf..8efc58716ce9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -883,8 +883,10 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, unsigned int size; if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) { - opts->options |= OPTION_MPTCP; - remaining -= size; + if (remaining >= size) { + opts->options |= OPTION_MPTCP; + remaining -= size; + } } } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 6dfc61a9acd4..1b1bf044378d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1061,13 +1061,13 @@ ieee80211_copy_mbssid_beacon(u8 *pos, struct cfg80211_mbssid_elems *dst, { int i, offset = 0; + dst->cnt = src->cnt; for (i = 0; i < src->cnt; i++) { memcpy(pos + offset, src->elem[i].data, src->elem[i].len); dst->elem[i].len = src->elem[i].len; dst->elem[i].data = pos + offset; offset += dst->elem[i].len; } - dst->cnt = src->cnt; return offset; } @@ -1911,6 +1911,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, params->eht_capa_len, link_sta); + ieee80211_sta_init_nss(link_sta); + if (params->opmode_notif_used) { /* returned value is only needed for rc update, but the * rc isn't initialized here yet, so ignore it @@ -1920,8 +1922,6 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, sband->band); } - ieee80211_sta_init_nss(link_sta); - return 0; } @@ -3674,13 +3674,12 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id) } EXPORT_SYMBOL(ieee80211_csa_finish); -void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, bool block_tx) +void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - sdata->csa_blocked_queues = block_tx; sdata_info(sdata, "channel switch failed, disconnecting\n"); wiphy_work_queue(local->hw.wiphy, &ifmgd->csa_connection_drop_work); } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 3d3c9139ff5e..7a0242e937d3 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1106,8 +1106,6 @@ struct ieee80211_sub_if_data { unsigned long state; - bool csa_blocked_queues; - char name[IFNAMSIZ]; struct ieee80211_fragment_cache frags; @@ -2411,17 +2409,13 @@ void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr, bool ack, u16 tx_time); - +unsigned int +ieee80211_get_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata); void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw, unsigned long queues, enum queue_stop_reason reason, bool refcounted); -void ieee80211_stop_vif_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - enum queue_stop_reason reason); -void ieee80211_wake_vif_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - enum queue_stop_reason reason); void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, unsigned long queues, enum queue_stop_reason reason, @@ -2432,6 +2426,43 @@ void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason, bool refcounted); +static inline void +ieee80211_stop_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason) +{ + ieee80211_stop_queues_by_reason(&local->hw, + ieee80211_get_vif_queues(local, sdata), + reason, true); +} + +static inline void +ieee80211_wake_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason) +{ + ieee80211_wake_queues_by_reason(&local->hw, + ieee80211_get_vif_queues(local, sdata), + reason, true); +} +static inline void +ieee80211_stop_vif_queues_norefcount(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason) +{ + ieee80211_stop_queues_by_reason(&local->hw, + ieee80211_get_vif_queues(local, sdata), + reason, false); +} +static inline void +ieee80211_wake_vif_queues_norefcount(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason) +{ + ieee80211_wake_queues_by_reason(&local->hw, + ieee80211_get_vif_queues(local, sdata), + reason, false); +} void ieee80211_add_pending_skb(struct ieee80211_local *local, struct sk_buff *skb); void ieee80211_add_pending_skbs(struct ieee80211_local *local, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 6ef0990d3d29..af9055252e6d 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -2364,18 +2364,14 @@ void ieee80211_vif_block_queues_csa(struct ieee80211_sub_if_data *sdata) if (ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) return; - ieee80211_stop_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = true; + ieee80211_stop_vif_queues_norefcount(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); } void ieee80211_vif_unblock_queues_csa(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; - if (sdata->csa_blocked_queues) { - ieee80211_wake_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = false; - } + ieee80211_wake_vif_queues_norefcount(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0303972c23e4..111066928b96 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2636,8 +2636,6 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, */ link->conf->csa_active = true; link->u.mgd.csa.blocked_tx = csa_ie.mode; - sdata->csa_blocked_queues = - csa_ie.mode && !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA); wiphy_work_queue(sdata->local->hw.wiphy, &ifmgd->csa_connection_drop_work); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index f94faa86ba8a..b4814e97cf74 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -657,7 +657,7 @@ void ieee80211_wake_queues(struct ieee80211_hw *hw) } EXPORT_SYMBOL(ieee80211_wake_queues); -static unsigned int +unsigned int ieee80211_get_vif_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { @@ -669,7 +669,8 @@ ieee80211_get_vif_queues(struct ieee80211_local *local, queues = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) - queues |= BIT(sdata->vif.hw_queue[ac]); + if (sdata->vif.hw_queue[ac] != IEEE80211_INVAL_HW_QUEUE) + queues |= BIT(sdata->vif.hw_queue[ac]); if (sdata->vif.cab_queue != IEEE80211_INVAL_HW_QUEUE) queues |= BIT(sdata->vif.cab_queue); } else { @@ -724,24 +725,6 @@ void ieee80211_flush_queues(struct ieee80211_local *local, __ieee80211_flush_queues(local, sdata, 0, drop); } -void ieee80211_stop_vif_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - enum queue_stop_reason reason) -{ - ieee80211_stop_queues_by_reason(&local->hw, - ieee80211_get_vif_queues(local, sdata), - reason, true); -} - -void ieee80211_wake_vif_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - enum queue_stop_reason reason) -{ - ieee80211_wake_queues_by_reason(&local->hw, - ieee80211_get_vif_queues(local, sdata), - reason, true); -} - static void __iterate_interfaces(struct ieee80211_local *local, u32 iter_flags, void (*iterator)(void *data, u8 *mac, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4a137afaf0b8..0c5ff4afc370 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1495,7 +1495,6 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, INIT_LIST_HEAD(&table->sets); INIT_LIST_HEAD(&table->objects); INIT_LIST_HEAD(&table->flowtables); - write_pnet(&table->net, net); table->family = family; table->flags = flags; table->handle = ++nft_net->table_handle; @@ -3884,8 +3883,11 @@ void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) kfree(rule); } +/* can only be used if rule is no longer visible to dumps */ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { + lockdep_commit_lock_is_held(ctx->net); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } @@ -5650,6 +5652,8 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase) { + lockdep_commit_lock_is_held(ctx->net); + switch (phase) { case NFT_TRANS_PREPARE_ERROR: nft_set_trans_unbind(ctx, set); @@ -11456,19 +11460,6 @@ static void __nft_release_basechain_now(struct nft_ctx *ctx) nf_tables_chain_destroy(ctx->chain); } -static void nft_release_basechain_rcu(struct rcu_head *head) -{ - struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head); - struct nft_ctx ctx = { - .family = chain->table->family, - .chain = chain, - .net = read_pnet(&chain->table->net), - }; - - __nft_release_basechain_now(&ctx); - put_net(ctx.net); -} - int __nft_release_basechain(struct nft_ctx *ctx) { struct nft_rule *rule; @@ -11483,11 +11474,18 @@ int __nft_release_basechain(struct nft_ctx *ctx) nft_chain_del(ctx->chain); nft_use_dec(&ctx->table->use); - if (maybe_get_net(ctx->net)) - call_rcu(&ctx->chain->rcu_head, nft_release_basechain_rcu); - else + if (!maybe_get_net(ctx->net)) { __nft_release_basechain_now(ctx); + return 0; + } + /* wait for ruleset dumps to complete. Owning chain is no longer in + * lists, so new dumps can't find any of these rules anymore. + */ + synchronize_rcu(); + + __nft_release_basechain_now(ctx); + put_net(ctx->net); return 0; } EXPORT_SYMBOL_GPL(__nft_release_basechain); diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index f8b25b6f5da7..9869ef3c2ab3 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -409,21 +409,23 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par) mutex_lock(&list_mutex); - if (--info->timer->refcnt == 0) { - pr_debug("deleting timer %s\n", info->label); - - list_del(&info->timer->entry); - timer_shutdown_sync(&info->timer->timer); - cancel_work_sync(&info->timer->work); - sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); - kfree(info->timer->attr.attr.name); - kfree(info->timer); - } else { + if (--info->timer->refcnt > 0) { pr_debug("decreased refcnt of timer %s to %u\n", info->label, info->timer->refcnt); + mutex_unlock(&list_mutex); + return; } + pr_debug("deleting timer %s\n", info->label); + + list_del(&info->timer->entry); mutex_unlock(&list_mutex); + + timer_shutdown_sync(&info->timer->timer); + cancel_work_sync(&info->timer->work); + sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); + kfree(info->timer->attr.attr.name); + kfree(info->timer); } static void idletimer_tg_destroy_v1(const struct xt_tgdtor_param *par) @@ -434,25 +436,27 @@ static void idletimer_tg_destroy_v1(const struct xt_tgdtor_param *par) mutex_lock(&list_mutex); - if (--info->timer->refcnt == 0) { - pr_debug("deleting timer %s\n", info->label); - - list_del(&info->timer->entry); - if (info->timer->timer_type & XT_IDLETIMER_ALARM) { - alarm_cancel(&info->timer->alarm); - } else { - timer_shutdown_sync(&info->timer->timer); - } - cancel_work_sync(&info->timer->work); - sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); - kfree(info->timer->attr.attr.name); - kfree(info->timer); - } else { + if (--info->timer->refcnt > 0) { pr_debug("decreased refcnt of timer %s to %u\n", info->label, info->timer->refcnt); + mutex_unlock(&list_mutex); + return; } + pr_debug("deleting timer %s\n", info->label); + + list_del(&info->timer->entry); mutex_unlock(&list_mutex); + + if (info->timer->timer_type & XT_IDLETIMER_ALARM) { + alarm_cancel(&info->timer->alarm); + } else { + timer_shutdown_sync(&info->timer->timer); + } + cancel_work_sync(&info->timer->work); + sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); + kfree(info->timer->attr.attr.name); + kfree(info->timer); } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 39382ee1e331..3b519adc0125 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -78,6 +78,8 @@ struct netem_sched_data { struct sk_buff *t_head; struct sk_buff *t_tail; + u32 t_len; + /* optional qdisc for classful handling (NULL at netem init) */ struct Qdisc *qdisc; @@ -382,6 +384,7 @@ static void tfifo_reset(struct Qdisc *sch) rtnl_kfree_skbs(q->t_head, q->t_tail); q->t_head = NULL; q->t_tail = NULL; + q->t_len = 0; } static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) @@ -411,6 +414,7 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) rb_link_node(&nskb->rbnode, parent, p); rb_insert_color(&nskb->rbnode, &q->t_root); } + q->t_len++; sch->q.qlen++; } @@ -517,7 +521,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, 1<q.qlen >= sch->limit)) { + if (unlikely(q->t_len >= sch->limit)) { /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); @@ -701,8 +705,8 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) tfifo_dequeue: skb = __qdisc_dequeue_head(&sch->q); if (skb) { - qdisc_qstats_backlog_dec(sch, skb); deliver: + qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); return skb; } @@ -718,8 +722,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) if (time_to_send <= now && q->slot.slot_next <= now) { netem_erase_head(q, skb); - sch->q.qlen--; - qdisc_qstats_backlog_dec(sch, skb); + q->t_len--; skb->next = NULL; skb->prev = NULL; /* skb->dev shares skb->rbnode area, @@ -746,16 +749,21 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) if (net_xmit_drop_count(err)) qdisc_qstats_drop(sch); qdisc_tree_reduce_backlog(sch, 1, pkt_len); + sch->qstats.backlog -= pkt_len; + sch->q.qlen--; } goto tfifo_dequeue; } + sch->q.qlen--; goto deliver; } if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); - if (skb) + if (skb) { + sch->q.qlen--; goto deliver; + } } qdisc_watchdog_schedule_ns(&q->watchdog, @@ -765,8 +773,10 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); - if (skb) + if (skb) { + sch->q.qlen--; goto deliver; + } } return NULL; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index b7e25e7e9933..108a4cc2e001 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -807,6 +807,7 @@ static void cleanup_bearer(struct work_struct *work) { struct udp_bearer *ub = container_of(work, struct udp_bearer, work); struct udp_replicast *rcast, *tmp; + struct tipc_net *tn; list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { dst_cache_destroy(&rcast->dst_cache); @@ -814,10 +815,14 @@ static void cleanup_bearer(struct work_struct *work) kfree_rcu(rcast, rcu); } + tn = tipc_net(sock_net(ub->ubsock->sk)); + dst_cache_destroy(&ub->rcast.dst_cache); udp_tunnel_sock_release(ub->ubsock); + + /* Note: could use a call_rcu() to avoid another synchronize_net() */ synchronize_net(); - atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); + atomic_dec(&tn->wq_count); kfree(ub); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 001ccc55ef0f..6b1762300443 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2313,6 +2313,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, fds_sent = true; if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; err = skb_splice_from_iter(skb, &msg->msg_iter, size, sk->sk_allocation); if (err < 0) { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9b1b9dc5a7eb..1e78f575fb56 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -814,7 +814,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MLO_LINKS] = NLA_POLICY_NESTED_ARRAY(nl80211_policy), [NL80211_ATTR_MLO_LINK_ID] = - NLA_POLICY_RANGE(NLA_U8, 0, IEEE80211_MLD_MAX_NUM_LINKS), + NLA_POLICY_RANGE(NLA_U8, 0, IEEE80211_MLD_MAX_NUM_LINKS - 1), [NL80211_ATTR_MLD_ADDR] = NLA_POLICY_EXACT_LEN(ETH_ALEN), [NL80211_ATTR_MLO_SUPPORT] = { .type = NLA_FLAG }, [NL80211_ATTR_MAX_NUM_AKM_SUITES] = { .type = NLA_REJECT }, diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 431da30817a6..268171600087 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -83,6 +83,7 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) if (!request) return -ENOMEM; + request->n_channels = n_channels; if (wdev->conn->params.channel) { enum nl80211_band band = wdev->conn->params.channel->band; struct ieee80211_supported_band *sband = diff --git a/rust/Makefile b/rust/Makefile index b5e0a73b78f3..9f59baacaf77 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -267,9 +267,22 @@ endif bindgen_c_flags_final = $(bindgen_c_flags_lto) -D__BINDGEN__ +# Each `bindgen` release may upgrade the list of Rust target versions. By +# default, the highest stable release in their list is used. Thus we need to set +# a `--rust-target` to avoid future `bindgen` releases emitting code that +# `rustc` may not understand. On top of that, `bindgen` does not support passing +# an unknown Rust target version. +# +# Therefore, the Rust target for `bindgen` can be only as high as the minimum +# Rust version the kernel supports and only as high as the greatest stable Rust +# target supported by the minimum `bindgen` version the kernel supports (that +# is, if we do not test the actual `rustc`/`bindgen` versions running). +# +# Starting with `bindgen` 0.71.0, we will be able to set any future Rust version +# instead, i.e. we will be able to set here our minimum supported Rust version. quiet_cmd_bindgen = BINDGEN $@ cmd_bindgen = \ - $(BINDGEN) $< $(bindgen_target_flags) \ + $(BINDGEN) $< $(bindgen_target_flags) --rust-target 1.68 \ --use-core --with-derive-default --ctypes-prefix core::ffi --no-layout-tests \ --no-debug '.*' --enable-function-attribute-detection \ -o $@ -- $(bindgen_c_flags_final) -DMODULE \ diff --git a/sound/core/control_led.c b/sound/core/control_led.c index 65a1ebe87776..e33dfcf863cf 100644 --- a/sound/core/control_led.c +++ b/sound/core/control_led.c @@ -668,10 +668,16 @@ static void snd_ctl_led_sysfs_add(struct snd_card *card) goto cerr; led->cards[card->number] = led_card; snprintf(link_name, sizeof(link_name), "led-%s", led->name); - WARN(sysfs_create_link(&card->ctl_dev->kobj, &led_card->dev.kobj, link_name), - "can't create symlink to controlC%i device\n", card->number); - WARN(sysfs_create_link(&led_card->dev.kobj, &card->card_dev.kobj, "card"), - "can't create symlink to card%i\n", card->number); + if (sysfs_create_link(&card->ctl_dev->kobj, &led_card->dev.kobj, + link_name)) + dev_err(card->dev, + "%s: can't create symlink to controlC%i device\n", + __func__, card->number); + if (sysfs_create_link(&led_card->dev.kobj, &card->card_dev.kobj, + "card")) + dev_err(card->dev, + "%s: can't create symlink to card%i\n", + __func__, card->number); continue; cerr: diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 973671e0cdb0..192fc75b51e6 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -10127,6 +10127,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), SND_PCI_QUIRK(0x1025, 0x1534, "Acer Predator PH315-54", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1025, 0x159c, "Acer Nitro 5 AN515-58", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x053c, "Dell Latitude E5430", ALC292_FIXUP_DELL_E7X), diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index e38c5885dadf..ecf57a6cb7c3 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -578,14 +578,19 @@ static int acp6x_probe(struct platform_device *pdev) handle = ACPI_HANDLE(pdev->dev.parent); ret = acpi_evaluate_integer(handle, "_WOV", NULL, &dmic_status); - if (!ACPI_FAILURE(ret)) + if (!ACPI_FAILURE(ret)) { wov_en = dmic_status; + if (!wov_en) + return -ENODEV; + } else { + /* Incase of ACPI method read failure then jump to check_dmi_entry */ + goto check_dmi_entry; + } - if (is_dmic_enable && wov_en) + if (is_dmic_enable) platform_set_drvdata(pdev, &acp6x_card); - else - return 0; +check_dmi_entry: /* check for any DMI overrides */ dmi_id = dmi_first_match(yc_acp_quirk_table); if (dmi_id) diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index 12d093437ba9..1b2f55030c39 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -370,7 +370,7 @@ static void sngl_calib_start(struct tasdevice_priv *tas_priv, int i, tasdevice_dev_read(tas_priv, i, p[j].reg, (int *)&p[j].val[0]); } else { - switch (p[j].reg) { + switch (tas2781_cali_start_reg[j].reg) { case 0: { if (!reg[0]) continue; diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c index b6ff04f7138a..ee946e0d3f49 100644 --- a/sound/soc/fsl/fsl_spdif.c +++ b/sound/soc/fsl/fsl_spdif.c @@ -1204,7 +1204,7 @@ static struct snd_kcontrol_new fsl_spdif_ctrls[] = { }, /* DPLL lock info get controller */ { - .iface = SNDRV_CTL_ELEM_IFACE_PCM, + .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = RX_SAMPLE_RATE_KCONTROL, .access = SNDRV_CTL_ELEM_ACCESS_READ | SNDRV_CTL_ELEM_ACCESS_VOLATILE, diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index beede7344efd..4341269eb977 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -169,7 +169,7 @@ static int fsl_xcvr_capds_put(struct snd_kcontrol *kcontrol, } static struct snd_kcontrol_new fsl_xcvr_earc_capds_kctl = { - .iface = SNDRV_CTL_ELEM_IFACE_PCM, + .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = "Capabilities Data Structure", .access = SNDRV_CTL_ELEM_ACCESS_READWRITE, .info = fsl_xcvr_type_capds_bytes_info, diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index a58842a8c8a6..db57292c00ca 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -1003,8 +1003,12 @@ static int sof_card_dai_links_create(struct snd_soc_card *card) return ret; } - /* One per DAI link, worst case is a DAI link for every endpoint */ - sof_dais = kcalloc(num_ends, sizeof(*sof_dais), GFP_KERNEL); + /* + * One per DAI link, worst case is a DAI link for every endpoint, also + * add one additional to act as a terminator such that code can iterate + * until it hits an uninitialised DAI. + */ + sof_dais = kcalloc(num_ends + 1, sizeof(*sof_dais), GFP_KERNEL); if (!sof_dais) return -ENOMEM; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 00101875d9a8..a0767de7f1b7 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2179,6 +2179,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_MIC_RES_384), DEVICE_FLG(0x046d, 0x09a4, /* Logitech QuickCam E 3500 */ QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_IGNORE_CTL_ERROR), + DEVICE_FLG(0x0499, 0x1506, /* Yamaha THR5 */ + QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0499, 0x1509, /* Steinberg UR22 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0499, 0x3108, /* Yamaha YIT-W12TX */ diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index c6d67fc9e57e..83c43dc13313 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -47,6 +47,20 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, */ perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus); + + /* + * Empty cpu lists would eventually get opened as "any" so remove + * genuinely empty ones before they're opened in the wrong place. + */ + if (perf_cpu_map__is_empty(evsel->cpus)) { + struct perf_evsel *next = perf_evlist__next(evlist, evsel); + + perf_evlist__remove(evlist, evsel); + /* Keep idx contiguous */ + if (next) + list_for_each_entry_from(next, &evlist->entries, node) + next->idx--; + } } else if (!evsel->own_cpus || evlist->has_user_cpus || (!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) { /* @@ -80,11 +94,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, static void perf_evlist__propagate_maps(struct perf_evlist *evlist) { - struct perf_evsel *evsel; + struct perf_evsel *evsel, *n; evlist->needs_map_propagation = true; - perf_evlist__for_each_evsel(evlist, evsel) + list_for_each_entry_safe(evsel, n, &evlist->entries, node) __perf_evlist__propagate_maps(evlist, evsel); } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 6604f5d038aa..f0d8796b984a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3820,9 +3820,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break; case INSN_CONTEXT_SWITCH: - if (func && (!next_insn || !next_insn->hint)) { - WARN_INSN(insn, "unsupported instruction in callable function"); - return 1; + if (func) { + if (!next_insn || !next_insn->hint) { + WARN_INSN(insn, "unsupported instruction in callable function"); + return 1; + } + break; } return 0; diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 272d3c70810e..a56cf8b0a7d4 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1151,8 +1151,9 @@ static int cmp_profile_data(const void *a, const void *b) if (v1 > v2) return -1; - else + if (v1 < v2) return 1; + return 0; } static void print_profile_result(struct perf_ftrace *ftrace) diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 8982f68e7230..e763e8d99a43 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -277,7 +277,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid struct perf_record_header_build_id b; size_t len; - len = sizeof(b) + name_len + 1; + len = name_len + 1; len = PERF_ALIGN(len, sizeof(u64)); memset(&b, 0, sizeof(b)); @@ -286,7 +286,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid misc |= PERF_RECORD_MISC_BUILD_ID_SIZE; b.pid = pid; b.header.misc = misc; - b.header.size = len; + b.header.size = sizeof(b) + len; err = do_write(fd, &b, sizeof(b)); if (err < 0) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 4f0ac998b0cc..27d5345d2b30 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -134,6 +134,8 @@ struct machine *machine__new_host(void) if (machine__create_kernel_maps(machine) < 0) goto out_delete; + + machine->env = &perf_env; } return machine; diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S index df3230fdac39..66ab2e0bae5f 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S +++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S @@ -81,32 +81,31 @@ do_syscall: stp x27, x28, [sp, #96] // Set SVCR if we're doing SME - cbz x1, 1f + cbz x1, load_gpr adrp x2, svcr_in ldr x2, [x2, :lo12:svcr_in] msr S3_3_C4_C2_2, x2 -1: // Load ZA and ZT0 if enabled - uses x12 as scratch due to SME LDR - tbz x2, #SVCR_ZA_SHIFT, 1f + tbz x2, #SVCR_ZA_SHIFT, load_gpr mov w12, #0 ldr x2, =za_in -2: _ldr_za 12, 2 +1: _ldr_za 12, 2 add x2, x2, x1 add x12, x12, #1 cmp x1, x12 - bne 2b + bne 1b // ZT0 mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1 ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \ #ID_AA64SMFR0_EL1_SMEver_WIDTH - cbz x2, 1f + cbz x2, load_gpr adrp x2, zt_in add x2, x2, :lo12:zt_in _ldr_zt 2 -1: +load_gpr: // Load GPRs x8-x28, and save our SP/FP for later comparison ldr x2, =gpr_in add x2, x2, #64 @@ -125,9 +124,9 @@ do_syscall: str x30, [x2], #8 // LR // Load FPRs if we're not doing neither SVE nor streaming SVE - cbnz x0, 1f + cbnz x0, check_sve_in ldr x2, =svcr_in - tbnz x2, #SVCR_SM_SHIFT, 1f + tbnz x2, #SVCR_SM_SHIFT, check_sve_in ldr x2, =fpr_in ldp q0, q1, [x2] @@ -148,8 +147,8 @@ do_syscall: ldp q30, q31, [x2, #16 * 30] b 2f -1: +check_sve_in: // Load the SVE registers if we're doing SVE/SME ldr x2, =z_in @@ -256,32 +255,31 @@ do_syscall: stp q30, q31, [x2, #16 * 30] // Save SVCR if we're doing SME - cbz x1, 1f + cbz x1, check_sve_out mrs x2, S3_3_C4_C2_2 adrp x3, svcr_out str x2, [x3, :lo12:svcr_out] -1: // Save ZA if it's enabled - uses x12 as scratch due to SME STR - tbz x2, #SVCR_ZA_SHIFT, 1f + tbz x2, #SVCR_ZA_SHIFT, check_sve_out mov w12, #0 ldr x2, =za_out -2: _str_za 12, 2 +1: _str_za 12, 2 add x2, x2, x1 add x12, x12, #1 cmp x1, x12 - bne 2b + bne 1b // ZT0 mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1 ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \ #ID_AA64SMFR0_EL1_SMEver_WIDTH - cbz x2, 1f + cbz x2, check_sve_out adrp x2, zt_out add x2, x2, :lo12:zt_out _str_zt 2 -1: +check_sve_out: // Save the SVE state if we have some cbz x0, 1f diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c index 5aaf2b065f86..bba3e37f749b 100644 --- a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c +++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c @@ -7,11 +7,7 @@ #include "bpf_misc.h" SEC("tp_btf/bpf_testmod_test_nullable_bare") -/* This used to be a failure test, but raw_tp nullable arguments can now - * directly be dereferenced, whether they have nullable annotation or not, - * and don't need to be explicitly checked. - */ -__success +__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx) { return nullable_ctx->len; diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c index a570e48b917a..bfc3bf18fed4 100644 --- a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c @@ -11,7 +11,7 @@ __success __retval(0) __naked void btf_ctx_access_accept(void) { asm volatile (" \ - r2 = *(u32*)(r1 + 8); /* load 2nd argument value (int pointer) */\ + r2 = *(u64 *)(r1 + 8); /* load 2nd argument value (int pointer) */\ r0 = 0; \ exit; \ " ::: __clobber_all); @@ -23,7 +23,7 @@ __success __retval(0) __naked void ctx_access_u32_pointer_accept(void) { asm volatile (" \ - r2 = *(u32*)(r1 + 0); /* load 1nd argument value (u32 pointer) */\ + r2 = *(u64 *)(r1 + 0); /* load 1nd argument value (u32 pointer) */\ r0 = 0; \ exit; \ " ::: __clobber_all); diff --git a/tools/testing/selftests/bpf/progs/verifier_d_path.c b/tools/testing/selftests/bpf/progs/verifier_d_path.c index ec79cbcfde91..87e51a215558 100644 --- a/tools/testing/selftests/bpf/progs/verifier_d_path.c +++ b/tools/testing/selftests/bpf/progs/verifier_d_path.c @@ -11,7 +11,7 @@ __success __retval(0) __naked void d_path_accept(void) { asm volatile (" \ - r1 = *(u32*)(r1 + 0); \ + r1 = *(u64 *)(r1 + 0); \ r2 = r10; \ r2 += -8; \ r6 = 0; \ @@ -31,7 +31,7 @@ __failure __msg("helper call is not allowed in probe") __naked void d_path_reject(void) { asm volatile (" \ - r1 = *(u32*)(r1 + 0); \ + r1 = *(u64 *)(r1 + 0); \ r2 = r10; \ r2 += -8; \ r6 = 0; \ diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh index 0c47faff9274..c068e6c2a580 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh @@ -22,20 +22,34 @@ SB_ITC=0 h1_create() { simple_if_init $h1 192.0.1.1/24 + tc qdisc add dev $h1 clsact + + # Add egress filter on $h1 that will guarantee that the packet sent, + # will be the only packet being passed to the device. + tc filter add dev $h1 egress pref 2 handle 102 matchall action drop } h1_destroy() { + tc filter del dev $h1 egress pref 2 handle 102 matchall action drop + tc qdisc del dev $h1 clsact simple_if_fini $h1 192.0.1.1/24 } h2_create() { simple_if_init $h2 192.0.1.2/24 + tc qdisc add dev $h2 clsact + + # Add egress filter on $h2 that will guarantee that the packet sent, + # will be the only packet being passed to the device. + tc filter add dev $h2 egress pref 1 handle 101 matchall action drop } h2_destroy() { + tc filter del dev $h2 egress pref 1 handle 101 matchall action drop + tc qdisc del dev $h2 clsact simple_if_fini $h2 192.0.1.2/24 } @@ -101,6 +115,11 @@ port_pool_test() local exp_max_occ=$(devlink_cell_size_get) local max_occ + tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass + devlink sb occupancy clearmax $DEVLINK_DEV $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ @@ -108,11 +127,6 @@ port_pool_test() devlink sb occupancy snapshot $DEVLINK_DEV - RET=0 - max_occ=$(sb_occ_pool_check $dl_port1 $SB_POOL_ING $exp_max_occ) - check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ" - log_test "physical port's($h1) ingress pool" - RET=0 max_occ=$(sb_occ_pool_check $dl_port2 $SB_POOL_ING $exp_max_occ) check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ" @@ -122,6 +136,11 @@ port_pool_test() max_occ=$(sb_occ_pool_check $cpu_dl_port $SB_POOL_EGR_CPU $exp_max_occ) check_err $? "Expected ePool($SB_POOL_EGR_CPU) max occupancy to be $exp_max_occ, but got $max_occ" log_test "CPU port's egress pool" + + tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass } port_tc_ip_test() @@ -129,6 +148,11 @@ port_tc_ip_test() local exp_max_occ=$(devlink_cell_size_get) local max_occ + tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass + devlink sb occupancy clearmax $DEVLINK_DEV $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ @@ -136,11 +160,6 @@ port_tc_ip_test() devlink sb occupancy snapshot $DEVLINK_DEV - RET=0 - max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) - check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" - log_test "physical port's($h1) ingress TC - IP packet" - RET=0 max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" @@ -150,6 +169,11 @@ port_tc_ip_test() max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_IP $exp_max_occ) check_err $? "Expected egress TC($SB_ITC_CPU_IP) max occupancy to be $exp_max_occ, but got $max_occ" log_test "CPU port's egress TC - IP packet" + + tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass } port_tc_arp_test() @@ -157,17 +181,15 @@ port_tc_arp_test() local exp_max_occ=$(devlink_cell_size_get) local max_occ + tc filter add dev $h1 egress protocol arp pref 1 handle 101 flower \ + src_mac $h1mac action pass + devlink sb occupancy clearmax $DEVLINK_DEV $MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q devlink sb occupancy snapshot $DEVLINK_DEV - RET=0 - max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) - check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" - log_test "physical port's($h1) ingress TC - ARP packet" - RET=0 max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" @@ -177,6 +199,9 @@ port_tc_arp_test() max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_ARP $exp_max_occ) check_err $? "Expected egress TC($SB_ITC_IP2ME) max occupancy to be $exp_max_occ, but got $max_occ" log_test "CPU port's egress TC - ARP packet" + + tc filter del dev $h1 egress protocol arp pref 1 handle 101 flower \ + src_mac $h1mac action pass } setup_prepare() diff --git a/tools/testing/selftests/net/netfilter/rpath.sh b/tools/testing/selftests/net/netfilter/rpath.sh index 4485fd7675ed..86ec4e68594d 100755 --- a/tools/testing/selftests/net/netfilter/rpath.sh +++ b/tools/testing/selftests/net/netfilter/rpath.sh @@ -61,9 +61,20 @@ ip -net "$ns2" a a 192.168.42.1/24 dev d0 ip -net "$ns1" a a fec0:42::2/64 dev v0 nodad ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad +# avoid neighbor lookups and enable martian IPv6 pings +ns2_hwaddr=$(ip -net "$ns2" link show dev v0 | \ + sed -n 's, *link/ether \([^ ]*\) .*,\1,p') +ns1_hwaddr=$(ip -net "$ns1" link show dev v0 | \ + sed -n 's, *link/ether \([^ ]*\) .*,\1,p') +ip -net "$ns1" neigh add fec0:42::1 lladdr "$ns2_hwaddr" nud permanent dev v0 +ip -net "$ns1" neigh add fec0:23::1 lladdr "$ns2_hwaddr" nud permanent dev v0 +ip -net "$ns2" neigh add fec0:42::2 lladdr "$ns1_hwaddr" nud permanent dev d0 +ip -net "$ns2" neigh add fec0:23::2 lladdr "$ns1_hwaddr" nud permanent dev v0 + # firewall matches to test [ -n "$iptables" ] && { common='-t raw -A PREROUTING -s 192.168.0.0/16' + common+=' -p icmp --icmp-type echo-request' if ! ip netns exec "$ns2" "$iptables" $common -m rpfilter;then echo "Cannot add rpfilter rule" exit $ksft_skip @@ -72,6 +83,7 @@ ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad } [ -n "$ip6tables" ] && { common='-t raw -A PREROUTING -s fec0::/16' + common+=' -p icmpv6 --icmpv6-type echo-request' if ! ip netns exec "$ns2" "$ip6tables" $common -m rpfilter;then echo "Cannot add rpfilter rule" exit $ksft_skip @@ -82,8 +94,10 @@ ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad table inet t { chain c { type filter hook prerouting priority raw; - ip saddr 192.168.0.0/16 fib saddr . iif oif exists counter - ip6 saddr fec0::/16 fib saddr . iif oif exists counter + ip saddr 192.168.0.0/16 icmp type echo-request \ + fib saddr . iif oif exists counter + ip6 saddr fec0::/16 icmpv6 type echo-request \ + fib saddr . iif oif exists counter } } EOF