diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 0380a45ecf4b..d6d7669e667f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3997,6 +3997,23 @@ expediting. Set to zero to disable automatic expediting. + ssbd= [ARM64,HW] + Speculative Store Bypass Disable control + + On CPUs that are vulnerable to the Speculative + Store Bypass vulnerability and offer a + firmware based mitigation, this parameter + indicates how the mitigation should be used: + + force-on: Unconditionally enable mitigation for + for both kernel and userspace + force-off: Unconditionally disable mitigation for + for both kernel and userspace + kernel: Always enable mitigation in the + kernel, and offer a prctl interface + to allow userspace to register its + interest in being mitigated too. + stack_guard_gap= [MM] override the default stack gap protection. The value is in page units and it defines how many pages prior diff --git a/Makefile b/Makefile index acbb0e3d29c9..a44d6b2adb76 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 56 +SUBLEVEL = 57 EXTRAVERSION = NAME = Petit Gorille diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 8f973e3b7348..65572e14306c 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -302,4 +302,16 @@ static inline bool kvm_arm_harden_branch_predictor(void) return false; } +#define KVM_SSBD_UNKNOWN -1 +#define KVM_SSBD_FORCE_DISABLE 0 +#define KVM_SSBD_KERNEL 1 +#define KVM_SSBD_FORCE_ENABLE 2 +#define KVM_SSBD_MITIGATED 3 + +static inline int kvm_arm_have_ssbd(void) +{ + /* No way to detect it yet, pretend it is not there. */ + return KVM_SSBD_UNKNOWN; +} + #endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 08cd720eae01..8a098e65f5f8 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -28,6 +28,13 @@ */ #define kern_hyp_va(kva) (kva) +/* Contrary to arm64, there is no need to generate a PC-relative address */ +#define hyp_symbol_addr(s) \ + ({ \ + typeof(s) *addr = &(s); \ + addr; \ + }) + /* * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels. */ @@ -247,6 +254,11 @@ static inline int kvm_map_vectors(void) return 0; } +static inline int hyp_map_aux_data(void) +{ + return 0; +} + #endif /* !__ASSEMBLY__ */ #endif /* __ARM_KVM_MMU_H__ */ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 2d5f7aca156d..1bbb89d37f57 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -849,6 +849,15 @@ config HARDEN_BRANCH_PREDICTOR If unsure, say Y. +config ARM64_SSBD + bool "Speculative Store Bypass Disable" if EXPERT + default y + help + This enables mitigation of the bypassing of previous stores + by speculative loads. + + If unsure, say Y. + menuconfig ARMV8_DEPRECATED bool "Emulate deprecated/obsolete ARMv8 instructions" depends on COMPAT diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 4a85c6952a22..a91933b1e2e6 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -5,6 +5,8 @@ #include #include +#define ARM64_CB_PATCH ARM64_NCAPS + #ifndef __ASSEMBLY__ #include @@ -12,6 +14,8 @@ #include #include +extern int alternatives_applied; + struct alt_instr { s32 orig_offset; /* offset to original instruction */ s32 alt_offset; /* offset to replacement instruction */ @@ -20,12 +24,19 @@ struct alt_instr { u8 alt_len; /* size of new instruction(s), <= orig_len */ }; +typedef void (*alternative_cb_t)(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst); + void __init apply_alternatives_all(void); void apply_alternatives(void *start, size_t length); -#define ALTINSTR_ENTRY(feature) \ +#define ALTINSTR_ENTRY(feature,cb) \ " .word 661b - .\n" /* label */ \ + " .if " __stringify(cb) " == 0\n" \ " .word 663f - .\n" /* new instruction */ \ + " .else\n" \ + " .word " __stringify(cb) "- .\n" /* callback */ \ + " .endif\n" \ " .hword " __stringify(feature) "\n" /* feature bit */ \ " .byte 662b-661b\n" /* source len */ \ " .byte 664f-663f\n" /* replacement len */ @@ -43,15 +54,18 @@ void apply_alternatives(void *start, size_t length); * but most assemblers die if insn1 or insn2 have a .inst. This should * be fixed in a binutils release posterior to 2.25.51.0.2 (anything * containing commit 4e4d08cf7399b606 or c1baaddf8861). + * + * Alternatives with callbacks do not generate replacement instructions. */ -#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled) \ +#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled, cb) \ ".if "__stringify(cfg_enabled)" == 1\n" \ "661:\n\t" \ oldinstr "\n" \ "662:\n" \ ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY(feature) \ + ALTINSTR_ENTRY(feature,cb) \ ".popsection\n" \ + " .if " __stringify(cb) " == 0\n" \ ".pushsection .altinstr_replacement, \"a\"\n" \ "663:\n\t" \ newinstr "\n" \ @@ -59,11 +73,17 @@ void apply_alternatives(void *start, size_t length); ".popsection\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ ".org . - (662b-661b) + (664b-663b)\n" \ + ".else\n\t" \ + "663:\n\t" \ + "664:\n\t" \ + ".endif\n" \ ".endif\n" #define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...) \ - __ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg)) + __ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg), 0) +#define ALTERNATIVE_CB(oldinstr, cb) \ + __ALTERNATIVE_CFG(oldinstr, "NOT_AN_INSTRUCTION", ARM64_CB_PATCH, 1, cb) #else #include @@ -130,6 +150,14 @@ void apply_alternatives(void *start, size_t length); 661: .endm +.macro alternative_cb cb + .set .Lasm_alt_mode, 0 + .pushsection .altinstructions, "a" + altinstruction_entry 661f, \cb, ARM64_CB_PATCH, 662f-661f, 0 + .popsection +661: +.endm + /* * Provide the other half of the alternative code sequence. */ @@ -155,6 +183,13 @@ void apply_alternatives(void *start, size_t length); .org . - (662b-661b) + (664b-663b) .endm +/* + * Callback-based alternative epilogue + */ +.macro alternative_cb_end +662: +.endm + /* * Provides a trivial alternative or default sequence consisting solely * of NOPs. The number of NOPs is chosen automatically to match the diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 25b2a4161c7a..66aea4aa455d 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -260,7 +260,11 @@ lr .req x30 // link register #else adr_l \dst, \sym #endif +alternative_if_not ARM64_HAS_VIRT_HOST_EXTN mrs \tmp, tpidr_el1 +alternative_else + mrs \tmp, tpidr_el2 +alternative_endif add \dst, \dst, \tmp .endm @@ -271,7 +275,11 @@ lr .req x30 // link register */ .macro ldr_this_cpu dst, sym, tmp adr_l \dst, \sym +alternative_if_not ARM64_HAS_VIRT_HOST_EXTN mrs \tmp, tpidr_el1 +alternative_else + mrs \tmp, tpidr_el2 +alternative_endif ldr \dst, [\dst, \tmp] .endm diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index 2e7b236bc596..76c0d23ca161 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -43,7 +43,8 @@ #define ARM64_UNMAP_KERNEL_AT_EL0 23 #define ARM64_HARDEN_BRANCH_PREDICTOR 24 #define ARM64_HARDEN_BP_POST_GUEST_EXIT 25 +#define ARM64_SSBD 26 -#define ARM64_NCAPS 26 +#define ARM64_NCAPS 27 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 428ee1f2468c..c5bc80a03515 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -262,6 +262,28 @@ static inline bool system_uses_ttbr0_pan(void) !cpus_have_const_cap(ARM64_HAS_PAN); } +#define ARM64_SSBD_UNKNOWN -1 +#define ARM64_SSBD_FORCE_DISABLE 0 +#define ARM64_SSBD_KERNEL 1 +#define ARM64_SSBD_FORCE_ENABLE 2 +#define ARM64_SSBD_MITIGATED 3 + +static inline int arm64_get_ssbd_state(void) +{ +#ifdef CONFIG_ARM64_SSBD + extern int ssbd_state; + return ssbd_state; +#else + return ARM64_SSBD_UNKNOWN; +#endif +} + +#ifdef CONFIG_ARM64_SSBD +void arm64_set_ssbd_mitigation(bool state); +#else +static inline void arm64_set_ssbd_mitigation(bool state) {} +#endif + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index a7ef5a051911..1a6d02350fc6 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -33,6 +33,10 @@ #define KVM_ARM64_DEBUG_DIRTY_SHIFT 0 #define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT) +#define VCPU_WORKAROUND_2_FLAG_SHIFT 0 +#define VCPU_WORKAROUND_2_FLAG (_AC(1, UL) << VCPU_WORKAROUND_2_FLAG_SHIFT) + +/* Translate a kernel address of @sym into its equivalent linear mapping */ #define kvm_ksym_ref(sym) \ ({ \ void *val = &sym; \ @@ -68,6 +72,43 @@ extern u32 __init_stage2_translation(void); extern void __qcom_hyp_sanitize_btac_predictors(void); +/* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */ +#define __hyp_this_cpu_ptr(sym) \ + ({ \ + void *__ptr = hyp_symbol_addr(sym); \ + __ptr += read_sysreg(tpidr_el2); \ + (typeof(&sym))__ptr; \ + }) + +#define __hyp_this_cpu_read(sym) \ + ({ \ + *__hyp_this_cpu_ptr(sym); \ + }) + +#else /* __ASSEMBLY__ */ + +.macro hyp_adr_this_cpu reg, sym, tmp + adr_l \reg, \sym + mrs \tmp, tpidr_el2 + add \reg, \reg, \tmp +.endm + +.macro hyp_ldr_this_cpu reg, sym, tmp + adr_l \reg, \sym + mrs \tmp, tpidr_el2 + ldr \reg, [\reg, \tmp] +.endm + +.macro get_host_ctxt reg, tmp + hyp_adr_this_cpu \reg, kvm_host_cpu_state, \tmp +.endm + +.macro get_vcpu_ptr vcpu, ctxt + get_host_ctxt \ctxt, \vcpu + ldr \vcpu, [\ctxt, #HOST_CONTEXT_VCPU] + kern_hyp_va \vcpu +.endm + #endif #endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 8abec9f7f430..b01ad3489bd8 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -194,6 +194,8 @@ struct kvm_cpu_context { u64 sys_regs[NR_SYS_REGS]; u32 copro[NR_COPRO_REGS]; }; + + struct kvm_vcpu *__hyp_running_vcpu; }; typedef struct kvm_cpu_context kvm_cpu_context_t; @@ -208,6 +210,9 @@ struct kvm_vcpu_arch { /* Exception Information */ struct kvm_vcpu_fault_info fault; + /* State of various workarounds, see kvm_asm.h for bit assignment */ + u64 workaround_flags; + /* Guest debug state */ u64 debug_flags; @@ -348,10 +353,15 @@ int kvm_perf_teardown(void); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); +void __kvm_set_tpidr_el2(u64 tpidr_el2); +DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state); + static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, unsigned long hyp_stack_ptr, unsigned long vector_ptr) { + u64 tpidr_el2; + /* * Call initialization code, and switch to the full blown HYP code. * If the cpucaps haven't been finalized yet, something has gone very @@ -360,6 +370,16 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, */ BUG_ON(!static_branch_likely(&arm64_const_caps_ready)); __kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr); + + /* + * Calculate the raw per-cpu offset without a translation from the + * kernel's mapping to the linear mapping, and store it in tpidr_el2 + * so that we can use adr_l to access per-cpu variables in EL2. + */ + tpidr_el2 = (u64)this_cpu_ptr(&kvm_host_cpu_state) + - (u64)kvm_ksym_ref(kvm_host_cpu_state); + + kvm_call_hyp(__kvm_set_tpidr_el2, tpidr_el2); } static inline void kvm_arch_hardware_unsetup(void) {} @@ -392,4 +412,27 @@ static inline bool kvm_arm_harden_branch_predictor(void) return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR); } +#define KVM_SSBD_UNKNOWN -1 +#define KVM_SSBD_FORCE_DISABLE 0 +#define KVM_SSBD_KERNEL 1 +#define KVM_SSBD_FORCE_ENABLE 2 +#define KVM_SSBD_MITIGATED 3 + +static inline int kvm_arm_have_ssbd(void) +{ + switch (arm64_get_ssbd_state()) { + case ARM64_SSBD_FORCE_DISABLE: + return KVM_SSBD_FORCE_DISABLE; + case ARM64_SSBD_KERNEL: + return KVM_SSBD_KERNEL; + case ARM64_SSBD_FORCE_ENABLE: + return KVM_SSBD_FORCE_ENABLE; + case ARM64_SSBD_MITIGATED: + return KVM_SSBD_MITIGATED; + case ARM64_SSBD_UNKNOWN: + default: + return KVM_SSBD_UNKNOWN; + } +} + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index fe55b516f018..e42c1f0ae6cf 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -130,6 +130,26 @@ static inline unsigned long __kern_hyp_va(unsigned long v) #define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v)))) +/* + * Obtain the PC-relative address of a kernel symbol + * s: symbol + * + * The goal of this macro is to return a symbol's address based on a + * PC-relative computation, as opposed to a loading the VA from a + * constant pool or something similar. This works well for HYP, as an + * absolute VA is guaranteed to be wrong. Only use this if trying to + * obtain the address of a symbol (i.e. not something you obtained by + * following a pointer). + */ +#define hyp_symbol_addr(s) \ + ({ \ + typeof(s) *addr; \ + asm("adrp %0, %1\n" \ + "add %0, %0, :lo12:%1\n" \ + : "=r" (addr) : "S" (&s)); \ + addr; \ + }) + /* * We currently only support a 40bit IPA. */ @@ -363,5 +383,29 @@ static inline int kvm_map_vectors(void) } #endif +#ifdef CONFIG_ARM64_SSBD +DECLARE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required); + +static inline int hyp_map_aux_data(void) +{ + int cpu, err; + + for_each_possible_cpu(cpu) { + u64 *ptr; + + ptr = per_cpu_ptr(&arm64_ssbd_callback_required, cpu); + err = create_hyp_mappings(ptr, ptr + 1, PAGE_HYP); + if (err) + return err; + } + return 0; +} +#else +static inline int hyp_map_aux_data(void) +{ + return 0; +} +#endif + #endif /* __ASSEMBLY__ */ #endif /* __ARM64_KVM_MMU_H__ */ diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 3bd498e4de4c..43393208229e 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -16,11 +16,15 @@ #ifndef __ASM_PERCPU_H #define __ASM_PERCPU_H +#include #include static inline void set_my_cpu_offset(unsigned long off) { - asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory"); + asm volatile(ALTERNATIVE("msr tpidr_el1, %0", + "msr tpidr_el2, %0", + ARM64_HAS_VIRT_HOST_EXTN) + :: "r" (off) : "memory"); } static inline unsigned long __my_cpu_offset(void) @@ -31,7 +35,10 @@ static inline unsigned long __my_cpu_offset(void) * We want to allow caching the value, so avoid using volatile and * instead use a fake stack read to hazard against barrier(). */ - asm("mrs %0, tpidr_el1" : "=r" (off) : + asm(ALTERNATIVE("mrs %0, tpidr_el1", + "mrs %0, tpidr_el2", + ARM64_HAS_VIRT_HOST_EXTN) + : "=r" (off) : "Q" (*(const unsigned long *)current_stack_pointer)); return off; diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index ddded6497a8a..fc786d344e46 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -92,6 +92,7 @@ void arch_setup_new_exec(void); #define TIF_RESTORE_SIGMASK 20 #define TIF_SINGLESTEP 21 #define TIF_32BIT 22 /* 32bit process */ +#define TIF_SSBD 23 /* Wants SSB mitigation */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index def8d5623fd1..714fe90dbf66 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -54,6 +54,7 @@ arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +arm64-obj-$(CONFIG_ARM64_SSBD) += ssbd.o ifeq ($(CONFIG_KVM),y) arm64-obj-$(CONFIG_HARDEN_BRANCH_PREDICTOR) += bpi.o diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 6dd0a3a3e5c9..5c4bce4ac381 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -32,6 +32,8 @@ #define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset) #define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset) +int alternatives_applied; + struct alt_region { struct alt_instr *begin; struct alt_instr *end; @@ -105,32 +107,53 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp return insn; } +static void patch_alternative(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + __le32 *replptr; + int i; + + replptr = ALT_REPL_PTR(alt); + for (i = 0; i < nr_inst; i++) { + u32 insn; + + insn = get_alt_insn(alt, origptr + i, replptr + i); + updptr[i] = cpu_to_le32(insn); + } +} + static void __apply_alternatives(void *alt_region, bool use_linear_alias) { struct alt_instr *alt; struct alt_region *region = alt_region; - __le32 *origptr, *replptr, *updptr; + __le32 *origptr, *updptr; + alternative_cb_t alt_cb; for (alt = region->begin; alt < region->end; alt++) { - u32 insn; - int i, nr_inst; + int nr_inst; - if (!cpus_have_cap(alt->cpufeature)) + /* Use ARM64_CB_PATCH as an unconditional patch */ + if (alt->cpufeature < ARM64_CB_PATCH && + !cpus_have_cap(alt->cpufeature)) continue; - BUG_ON(alt->alt_len != alt->orig_len); + if (alt->cpufeature == ARM64_CB_PATCH) + BUG_ON(alt->alt_len != 0); + else + BUG_ON(alt->alt_len != alt->orig_len); pr_info_once("patching kernel code\n"); origptr = ALT_ORIG_PTR(alt); - replptr = ALT_REPL_PTR(alt); updptr = use_linear_alias ? lm_alias(origptr) : origptr; - nr_inst = alt->alt_len / sizeof(insn); + nr_inst = alt->orig_len / AARCH64_INSN_SIZE; - for (i = 0; i < nr_inst; i++) { - insn = get_alt_insn(alt, origptr + i, replptr + i); - updptr[i] = cpu_to_le32(insn); - } + if (alt->cpufeature < ARM64_CB_PATCH) + alt_cb = patch_alternative; + else + alt_cb = ALT_REPL_PTR(alt); + + alt_cb(alt, origptr, updptr, nr_inst); flush_icache_range((uintptr_t)origptr, (uintptr_t)(origptr + nr_inst)); @@ -143,7 +166,6 @@ static void __apply_alternatives(void *alt_region, bool use_linear_alias) */ static int __apply_alternatives_multi_stop(void *unused) { - static int patched = 0; struct alt_region region = { .begin = (struct alt_instr *)__alt_instructions, .end = (struct alt_instr *)__alt_instructions_end, @@ -151,14 +173,14 @@ static int __apply_alternatives_multi_stop(void *unused) /* We always have a CPU 0 at this point (__init) */ if (smp_processor_id()) { - while (!READ_ONCE(patched)) + while (!READ_ONCE(alternatives_applied)) cpu_relax(); isb(); } else { - BUG_ON(patched); + BUG_ON(alternatives_applied); __apply_alternatives(®ion, true); /* Barriers provided by the cache flushing */ - WRITE_ONCE(patched, 1); + WRITE_ONCE(alternatives_applied, 1); } return 0; diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index af247d10252f..b5e43b01b396 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -131,11 +131,13 @@ int main(void) BLANK(); #ifdef CONFIG_KVM_ARM_HOST DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt)); + DEFINE(VCPU_WORKAROUND_FLAGS, offsetof(struct kvm_vcpu, arch.workaround_flags)); DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs)); DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_regs, regs)); DEFINE(CPU_FP_REGS, offsetof(struct kvm_regs, fp_regs)); DEFINE(VCPU_FPEXC32_EL2, offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2])); DEFINE(VCPU_HOST_CONTEXT, offsetof(struct kvm_vcpu, arch.host_cpu_context)); + DEFINE(HOST_CONTEXT_VCPU, offsetof(struct kvm_cpu_context, __hyp_running_vcpu)); #endif #ifdef CONFIG_CPU_PM DEFINE(CPU_SUSPEND_SZ, sizeof(struct cpu_suspend_ctx)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index b5a28336c077..eccdb28b4a39 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -228,6 +228,178 @@ static int qcom_enable_link_stack_sanitization(void *data) } #endif /* CONFIG_HARDEN_BRANCH_PREDICTOR */ +#ifdef CONFIG_ARM64_SSBD +DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required); + +int ssbd_state __read_mostly = ARM64_SSBD_KERNEL; + +static const struct ssbd_options { + const char *str; + int state; +} ssbd_options[] = { + { "force-on", ARM64_SSBD_FORCE_ENABLE, }, + { "force-off", ARM64_SSBD_FORCE_DISABLE, }, + { "kernel", ARM64_SSBD_KERNEL, }, +}; + +static int __init ssbd_cfg(char *buf) +{ + int i; + + if (!buf || !buf[0]) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(ssbd_options); i++) { + int len = strlen(ssbd_options[i].str); + + if (strncmp(buf, ssbd_options[i].str, len)) + continue; + + ssbd_state = ssbd_options[i].state; + return 0; + } + + return -EINVAL; +} +early_param("ssbd", ssbd_cfg); + +void __init arm64_update_smccc_conduit(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, + int nr_inst) +{ + u32 insn; + + BUG_ON(nr_inst != 1); + + switch (psci_ops.conduit) { + case PSCI_CONDUIT_HVC: + insn = aarch64_insn_get_hvc_value(); + break; + case PSCI_CONDUIT_SMC: + insn = aarch64_insn_get_smc_value(); + break; + default: + return; + } + + *updptr = cpu_to_le32(insn); +} + +void __init arm64_enable_wa2_handling(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, + int nr_inst) +{ + BUG_ON(nr_inst != 1); + /* + * Only allow mitigation on EL1 entry/exit and guest + * ARCH_WORKAROUND_2 handling if the SSBD state allows it to + * be flipped. + */ + if (arm64_get_ssbd_state() == ARM64_SSBD_KERNEL) + *updptr = cpu_to_le32(aarch64_insn_gen_nop()); +} + +void arm64_set_ssbd_mitigation(bool state) +{ + switch (psci_ops.conduit) { + case PSCI_CONDUIT_HVC: + arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); + break; + + case PSCI_CONDUIT_SMC: + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); + break; + + default: + WARN_ON_ONCE(1); + break; + } +} + +static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, + int scope) +{ + struct arm_smccc_res res; + bool required = true; + s32 val; + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + + if (psci_ops.smccc_version == SMCCC_VERSION_1_0) { + ssbd_state = ARM64_SSBD_UNKNOWN; + return false; + } + + switch (psci_ops.conduit) { + case PSCI_CONDUIT_HVC: + arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_2, &res); + break; + + case PSCI_CONDUIT_SMC: + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_2, &res); + break; + + default: + ssbd_state = ARM64_SSBD_UNKNOWN; + return false; + } + + val = (s32)res.a0; + + switch (val) { + case SMCCC_RET_NOT_SUPPORTED: + ssbd_state = ARM64_SSBD_UNKNOWN; + return false; + + case SMCCC_RET_NOT_REQUIRED: + pr_info_once("%s mitigation not required\n", entry->desc); + ssbd_state = ARM64_SSBD_MITIGATED; + return false; + + case SMCCC_RET_SUCCESS: + required = true; + break; + + case 1: /* Mitigation not required on this CPU */ + required = false; + break; + + default: + WARN_ON(1); + return false; + } + + switch (ssbd_state) { + case ARM64_SSBD_FORCE_DISABLE: + pr_info_once("%s disabled from command-line\n", entry->desc); + arm64_set_ssbd_mitigation(false); + required = false; + break; + + case ARM64_SSBD_KERNEL: + if (required) { + __this_cpu_write(arm64_ssbd_callback_required, 1); + arm64_set_ssbd_mitigation(true); + } + break; + + case ARM64_SSBD_FORCE_ENABLE: + pr_info_once("%s forced from command-line\n", entry->desc); + arm64_set_ssbd_mitigation(true); + required = true; + break; + + default: + WARN_ON(1); + break; + } + + return required; +} +#endif /* CONFIG_ARM64_SSBD */ + #define MIDR_RANGE(model, min, max) \ .def_scope = SCOPE_LOCAL_CPU, \ .matches = is_affected_midr_range, \ @@ -425,6 +597,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), .enable = enable_smccc_arch_workaround_1, }, +#endif +#ifdef CONFIG_ARM64_SSBD + { + .desc = "Speculative Store Bypass Disable", + .def_scope = SCOPE_LOCAL_CPU, + .capability = ARM64_SSBD, + .matches = has_ssbd_mitigation, + }, #endif { } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 718822ab6e4b..376cf12edf0c 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -880,6 +880,22 @@ static int __init parse_kpti(char *str) early_param("kpti", parse_kpti); #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ +static int cpu_copy_el2regs(void *__unused) +{ + /* + * Copy register values that aren't redirected by hardware. + * + * Before code patching, we only set tpidr_el1, all CPUs need to copy + * this value to tpidr_el2 before we patch the code. Once we've done + * that, freshly-onlined CPUs will set tpidr_el2, so we don't need to + * do anything here. + */ + if (!alternatives_applied) + write_sysreg(read_sysreg(tpidr_el1), tpidr_el2); + + return 0; +} + static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "GIC system register CPU interface", @@ -949,6 +965,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_VIRT_HOST_EXTN, .def_scope = SCOPE_SYSTEM, .matches = runs_at_el2, + .enable = cpu_copy_el2regs, }, { .desc = "32-bit EL0 Support", diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 93958d1341bb..c1ffa95c0ad2 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -18,6 +18,7 @@ * along with this program. If not, see . */ +#include #include #include @@ -137,6 +138,25 @@ alternative_else_nop_endif add \dst, \dst, #(\sym - .entry.tramp.text) .endm + // This macro corrupts x0-x3. It is the caller's duty + // to save/restore them if required. + .macro apply_ssbd, state, targ, tmp1, tmp2 +#ifdef CONFIG_ARM64_SSBD +alternative_cb arm64_enable_wa2_handling + b \targ +alternative_cb_end + ldr_this_cpu \tmp2, arm64_ssbd_callback_required, \tmp1 + cbz \tmp2, \targ + ldr \tmp2, [tsk, #TSK_TI_FLAGS] + tbnz \tmp2, #TIF_SSBD, \targ + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_2 + mov w1, #\state +alternative_cb arm64_update_smccc_conduit + nop // Patched to SMC/HVC #0 +alternative_cb_end +#endif + .endm + .macro kernel_entry, el, regsize = 64 .if \regsize == 32 mov w0, w0 // zero upper 32 bits of x0 @@ -163,6 +183,14 @@ alternative_else_nop_endif ldr x19, [tsk, #TSK_TI_FLAGS] // since we can unmask debug disable_step_tsk x19, x20 // exceptions when scheduling. + apply_ssbd 1, 1f, x22, x23 + +#ifdef CONFIG_ARM64_SSBD + ldp x0, x1, [sp, #16 * 0] + ldp x2, x3, [sp, #16 * 1] +#endif +1: + mov x29, xzr // fp pointed to user-space .else add x21, sp, #S_FRAME_SIZE @@ -301,6 +329,8 @@ alternative_if ARM64_WORKAROUND_845719 alternative_else_nop_endif #endif 3: + apply_ssbd 0, 5f, x0, x1 +5: .endif msr elr_el1, x21 // set up the return data diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 095d3c170f5d..a028cc95afe1 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -313,6 +313,17 @@ int swsusp_arch_suspend(void) sleep_cpu = -EINVAL; __cpu_suspend_exit(); + + /* + * Just in case the boot kernel did turn the SSBD + * mitigation off behind our back, let's set the state + * to what we expect it to be. + */ + switch (arm64_get_ssbd_state()) { + case ARM64_SSBD_FORCE_ENABLE: + case ARM64_SSBD_KERNEL: + arm64_set_ssbd_mitigation(true); + } } local_dbg_restore(flags); diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c new file mode 100644 index 000000000000..0560738c1d5c --- /dev/null +++ b/arch/arm64/kernel/ssbd.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018 ARM Ltd, All Rights Reserved. + */ + +#include +#include +#include +#include + +#include + +/* + * prctl interface for SSBD + */ +static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + int state = arm64_get_ssbd_state(); + + /* Unsupported */ + if (state == ARM64_SSBD_UNKNOWN) + return -EINVAL; + + /* Treat the unaffected/mitigated state separately */ + if (state == ARM64_SSBD_MITIGATED) { + switch (ctrl) { + case PR_SPEC_ENABLE: + return -EPERM; + case PR_SPEC_DISABLE: + case PR_SPEC_FORCE_DISABLE: + return 0; + } + } + + /* + * Things are a bit backward here: the arm64 internal API + * *enables the mitigation* when the userspace API *disables + * speculation*. So much fun. + */ + switch (ctrl) { + case PR_SPEC_ENABLE: + /* If speculation is force disabled, enable is not allowed */ + if (state == ARM64_SSBD_FORCE_ENABLE || + task_spec_ssb_force_disable(task)) + return -EPERM; + task_clear_spec_ssb_disable(task); + clear_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_DISABLE: + if (state == ARM64_SSBD_FORCE_DISABLE) + return -EPERM; + task_set_spec_ssb_disable(task); + set_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_FORCE_DISABLE: + if (state == ARM64_SSBD_FORCE_DISABLE) + return -EPERM; + task_set_spec_ssb_disable(task); + task_set_spec_ssb_force_disable(task); + set_tsk_thread_flag(task, TIF_SSBD); + break; + default: + return -ERANGE; + } + + return 0; +} + +int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, + unsigned long ctrl) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssbd_prctl_set(task, ctrl); + default: + return -ENODEV; + } +} + +static int ssbd_prctl_get(struct task_struct *task) +{ + switch (arm64_get_ssbd_state()) { + case ARM64_SSBD_UNKNOWN: + return -EINVAL; + case ARM64_SSBD_FORCE_ENABLE: + return PR_SPEC_DISABLE; + case ARM64_SSBD_KERNEL: + if (task_spec_ssb_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ssb_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + case ARM64_SSBD_FORCE_DISABLE: + return PR_SPEC_ENABLE; + default: + return PR_SPEC_NOT_AFFECTED; + } +} + +int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssbd_prctl_get(task); + default: + return -ENODEV; + } +} diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 77cd655e6eb7..7a655e60cf4b 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -62,6 +62,14 @@ void notrace __cpu_suspend_exit(void) */ if (hw_breakpoint_restore) hw_breakpoint_restore(cpu); + + /* + * On resume, firmware implementing dynamic mitigation will + * have turned the mitigation on. If the user has forcefully + * disabled it, make sure their wishes are obeyed. + */ + if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) + arm64_set_ssbd_mitigation(false); } /* diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index 870828c364c5..dea20651a5f1 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -122,6 +122,10 @@ CPU_BE( orr x4, x4, #SCTLR_ELx_EE) kern_hyp_va x2 msr vbar_el2, x2 + /* copy tpidr_el1 into tpidr_el2 for use by HYP */ + mrs x1, tpidr_el1 + msr tpidr_el2, x1 + /* Hello, World! */ eret ENDPROC(__kvm_hyp_init) diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index 9c45c6af1f58..a7b3c198d4de 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -62,9 +62,6 @@ ENTRY(__guest_enter) // Store the host regs save_callee_saved_regs x1 - // Store the host_ctxt for use at exit time - str x1, [sp, #-16]! - add x18, x0, #VCPU_CONTEXT // Restore guest regs x0-x17 @@ -118,8 +115,7 @@ ENTRY(__guest_exit) // Store the guest regs x19-x29, lr save_callee_saved_regs x1 - // Restore the host_ctxt from the stack - ldr x2, [sp], #16 + get_host_ctxt x2, x3 // Now restore the host regs restore_callee_saved_regs x2 @@ -159,6 +155,10 @@ abort_guest_exit_end: ENDPROC(__guest_exit) ENTRY(__fpsimd_guest_restore) + // x0: esr + // x1: vcpu + // x2-x29,lr: vcpu regs + // vcpu x0-x1 on the stack stp x2, x3, [sp, #-16]! stp x4, lr, [sp, #-16]! @@ -173,7 +173,7 @@ alternative_else alternative_endif isb - mrs x3, tpidr_el2 + mov x3, x1 ldr x0, [x3, #VCPU_HOST_CONTEXT] kern_hyp_va x0 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index f49b53331d28..3c283fd8c8f5 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -57,13 +57,8 @@ ENDPROC(__vhe_hyp_call) el1_sync: // Guest trapped into EL2 stp x0, x1, [sp, #-16]! -alternative_if_not ARM64_HAS_VIRT_HOST_EXTN - mrs x1, esr_el2 -alternative_else - mrs x1, esr_el1 -alternative_endif - lsr x0, x1, #ESR_ELx_EC_SHIFT - + mrs x0, esr_el2 + lsr x0, x0, #ESR_ELx_EC_SHIFT cmp x0, #ESR_ELx_EC_HVC64 ccmp x0, #ESR_ELx_EC_HVC32, #4, ne b.ne el1_trap @@ -111,14 +106,55 @@ el1_hvc_guest: */ ldr x1, [sp] // Guest's x0 eor w1, w1, #ARM_SMCCC_ARCH_WORKAROUND_1 + cbz w1, wa_epilogue + + /* ARM_SMCCC_ARCH_WORKAROUND_2 handling */ + eor w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_1 ^ \ + ARM_SMCCC_ARCH_WORKAROUND_2) cbnz w1, el1_trap - mov x0, x1 + +#ifdef CONFIG_ARM64_SSBD +alternative_cb arm64_enable_wa2_handling + b wa2_end +alternative_cb_end + get_vcpu_ptr x2, x0 + ldr x0, [x2, #VCPU_WORKAROUND_FLAGS] + + // Sanitize the argument and update the guest flags + ldr x1, [sp, #8] // Guest's x1 + clz w1, w1 // Murphy's device: + lsr w1, w1, #5 // w1 = !!w1 without using + eor w1, w1, #1 // the flags... + bfi x0, x1, #VCPU_WORKAROUND_2_FLAG_SHIFT, #1 + str x0, [x2, #VCPU_WORKAROUND_FLAGS] + + /* Check that we actually need to perform the call */ + hyp_ldr_this_cpu x0, arm64_ssbd_callback_required, x2 + cbz x0, wa2_end + + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_2 + smc #0 + + /* Don't leak data from the SMC call */ + mov x3, xzr +wa2_end: + mov x2, xzr + mov x1, xzr +#endif + +wa_epilogue: + mov x0, xzr add sp, sp, #16 eret el1_trap: + get_vcpu_ptr x1, x0 + + mrs x0, esr_el2 + lsr x0, x0, #ESR_ELx_EC_SHIFT /* * x0: ESR_EC + * x1: vcpu pointer */ /* @@ -132,19 +168,18 @@ alternative_if_not ARM64_HAS_NO_FPSIMD b.eq __fpsimd_guest_restore alternative_else_nop_endif - mrs x1, tpidr_el2 mov x0, #ARM_EXCEPTION_TRAP b __guest_exit el1_irq: stp x0, x1, [sp, #-16]! - mrs x1, tpidr_el2 + get_vcpu_ptr x1, x0 mov x0, #ARM_EXCEPTION_IRQ b __guest_exit el1_error: stp x0, x1, [sp, #-16]! - mrs x1, tpidr_el2 + get_vcpu_ptr x1, x0 mov x0, #ARM_EXCEPTION_EL1_SERROR b __guest_exit @@ -179,6 +214,11 @@ ENTRY(__hyp_do_panic) eret ENDPROC(__hyp_do_panic) +ENTRY(__hyp_panic) + get_host_ctxt x0, x1 + b hyp_panic +ENDPROC(__hyp_panic) + .macro invalid_vector label, target = __hyp_panic .align 2 \label: diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index e08ae6b6b63e..b2f1992c6234 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -15,6 +15,7 @@ * along with this program. If not, see . */ +#include #include #include #include @@ -281,6 +282,39 @@ static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu) write_sysreg_el2(*vcpu_pc(vcpu), elr); } +static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu) +{ + if (!cpus_have_const_cap(ARM64_SSBD)) + return false; + + return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG); +} + +static void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_ARM64_SSBD + /* + * The host runs with the workaround always present. If the + * guest wants it disabled, so be it... + */ + if (__needs_ssbd_off(vcpu) && + __hyp_this_cpu_read(arm64_ssbd_callback_required)) + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL); +#endif +} + +static void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_ARM64_SSBD + /* + * If the guest has disabled the workaround, bring it back on. + */ + if (__needs_ssbd_off(vcpu) && + __hyp_this_cpu_read(arm64_ssbd_callback_required)) + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL); +#endif +} + int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; @@ -289,9 +323,9 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu) u64 exit_code; vcpu = kern_hyp_va(vcpu); - write_sysreg(vcpu, tpidr_el2); host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); + host_ctxt->__hyp_running_vcpu = vcpu; guest_ctxt = &vcpu->arch.ctxt; __sysreg_save_host_state(host_ctxt); @@ -311,6 +345,8 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu) __sysreg_restore_guest_state(guest_ctxt); __debug_restore_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt); + __set_guest_arch_workaround_state(vcpu); + /* Jump in the fire! */ again: exit_code = __guest_enter(vcpu, host_ctxt); @@ -367,6 +403,8 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu) /* 0 falls through to be handled out of EL2 */ } + __set_host_arch_workaround_state(vcpu); + if (cpus_have_const_cap(ARM64_HARDEN_BP_POST_GUEST_EXIT)) { u32 midr = read_cpuid_id(); @@ -406,7 +444,8 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu) static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n"; -static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par) +static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par, + struct kvm_vcpu *vcpu) { unsigned long str_va; @@ -420,35 +459,32 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par) __hyp_do_panic(str_va, spsr, elr, read_sysreg(esr_el2), read_sysreg_el2(far), - read_sysreg(hpfar_el2), par, - (void *)read_sysreg(tpidr_el2)); + read_sysreg(hpfar_el2), par, vcpu); } -static void __hyp_text __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par) +static void __hyp_text __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par, + struct kvm_vcpu *vcpu) { panic(__hyp_panic_string, spsr, elr, read_sysreg_el2(esr), read_sysreg_el2(far), - read_sysreg(hpfar_el2), par, - (void *)read_sysreg(tpidr_el2)); + read_sysreg(hpfar_el2), par, vcpu); } static hyp_alternate_select(__hyp_call_panic, __hyp_call_panic_nvhe, __hyp_call_panic_vhe, ARM64_HAS_VIRT_HOST_EXTN); -void __hyp_text __noreturn __hyp_panic(void) +void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) { + struct kvm_vcpu *vcpu = NULL; + u64 spsr = read_sysreg_el2(spsr); u64 elr = read_sysreg_el2(elr); u64 par = read_sysreg(par_el1); if (read_sysreg(vttbr_el2)) { - struct kvm_vcpu *vcpu; - struct kvm_cpu_context *host_ctxt; - - vcpu = (struct kvm_vcpu *)read_sysreg(tpidr_el2); - host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); + vcpu = host_ctxt->__hyp_running_vcpu; __timer_save_state(vcpu); __deactivate_traps(vcpu); __deactivate_vm(vcpu); @@ -456,7 +492,7 @@ void __hyp_text __noreturn __hyp_panic(void) } /* Call panic for real */ - __hyp_call_panic()(spsr, elr, par); + __hyp_call_panic()(spsr, elr, par, vcpu); unreachable(); } diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 934137647837..e19d89cabf2a 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -27,8 +27,8 @@ static void __hyp_text __sysreg_do_nothing(struct kvm_cpu_context *ctxt) { } /* * Non-VHE: Both host and guest must save everything. * - * VHE: Host must save tpidr*_el[01], actlr_el1, mdscr_el1, sp0, pc, - * pstate, and guest must save everything. + * VHE: Host must save tpidr*_el0, actlr_el1, mdscr_el1, sp_el0, + * and guest must save everything. */ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt) @@ -36,11 +36,8 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt) ctxt->sys_regs[ACTLR_EL1] = read_sysreg(actlr_el1); ctxt->sys_regs[TPIDR_EL0] = read_sysreg(tpidr_el0); ctxt->sys_regs[TPIDRRO_EL0] = read_sysreg(tpidrro_el0); - ctxt->sys_regs[TPIDR_EL1] = read_sysreg(tpidr_el1); ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1); ctxt->gp_regs.regs.sp = read_sysreg(sp_el0); - ctxt->gp_regs.regs.pc = read_sysreg_el2(elr); - ctxt->gp_regs.regs.pstate = read_sysreg_el2(spsr); } static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt) @@ -62,10 +59,13 @@ static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt) ctxt->sys_regs[AMAIR_EL1] = read_sysreg_el1(amair); ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg_el1(cntkctl); ctxt->sys_regs[PAR_EL1] = read_sysreg(par_el1); + ctxt->sys_regs[TPIDR_EL1] = read_sysreg(tpidr_el1); ctxt->gp_regs.sp_el1 = read_sysreg(sp_el1); ctxt->gp_regs.elr_el1 = read_sysreg_el1(elr); ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(spsr); + ctxt->gp_regs.regs.pc = read_sysreg_el2(elr); + ctxt->gp_regs.regs.pstate = read_sysreg_el2(spsr); } static hyp_alternate_select(__sysreg_call_save_host_state, @@ -89,11 +89,8 @@ static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctx write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1); write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0); write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0); - write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1); write_sysreg(ctxt->gp_regs.regs.sp, sp_el0); - write_sysreg_el2(ctxt->gp_regs.regs.pc, elr); - write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr); } static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt) @@ -115,10 +112,13 @@ static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt) write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1], amair); write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], cntkctl); write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1); + write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); write_sysreg(ctxt->gp_regs.sp_el1, sp_el1); write_sysreg_el1(ctxt->gp_regs.elr_el1, elr); write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],spsr); + write_sysreg_el2(ctxt->gp_regs.regs.pc, elr); + write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr); } static hyp_alternate_select(__sysreg_call_restore_host_state, @@ -183,3 +183,8 @@ void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu) if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY) write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2); } + +void __hyp_text __kvm_set_tpidr_el2(u64 tpidr_el2) +{ + asm("msr tpidr_el2, %0": : "r" (tpidr_el2)); +} diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 3256b9228e75..a74311beda35 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -122,6 +122,10 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) /* Reset PMU */ kvm_pmu_vcpu_reset(vcpu); + /* Default workaround setup is enabled (if supported) */ + if (kvm_arm_have_ssbd() == KVM_SSBD_KERNEL) + vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG; + /* Reset timer */ return kvm_timer_vcpu_reset(vcpu); } diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index bf0821b7b1ab..10c835f13f62 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -70,7 +70,11 @@ ENTRY(cpu_do_suspend) mrs x8, mdscr_el1 mrs x9, oslsr_el1 mrs x10, sctlr_el1 +alternative_if_not ARM64_HAS_VIRT_HOST_EXTN mrs x11, tpidr_el1 +alternative_else + mrs x11, tpidr_el2 +alternative_endif mrs x12, sp_el0 stp x2, x3, [x0] stp x4, xzr, [x0, #16] @@ -116,7 +120,11 @@ ENTRY(cpu_do_resume) msr mdscr_el1, x10 msr sctlr_el1, x12 +alternative_if_not ARM64_HAS_VIRT_HOST_EXTN msr tpidr_el1, x13 +alternative_else + msr tpidr_el2, x13 +alternative_endif msr sp_el0, x14 /* * Restore oslsr_el1 by writing oslar_el1 diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 386a6900e206..3bf87f92b932 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -46,6 +46,65 @@ #define _ASM_SI __ASM_REG(si) #define _ASM_DI __ASM_REG(di) +#ifndef __x86_64__ +/* 32 bit */ + +#define _ASM_ARG1 _ASM_AX +#define _ASM_ARG2 _ASM_DX +#define _ASM_ARG3 _ASM_CX + +#define _ASM_ARG1L eax +#define _ASM_ARG2L edx +#define _ASM_ARG3L ecx + +#define _ASM_ARG1W ax +#define _ASM_ARG2W dx +#define _ASM_ARG3W cx + +#define _ASM_ARG1B al +#define _ASM_ARG2B dl +#define _ASM_ARG3B cl + +#else +/* 64 bit */ + +#define _ASM_ARG1 _ASM_DI +#define _ASM_ARG2 _ASM_SI +#define _ASM_ARG3 _ASM_DX +#define _ASM_ARG4 _ASM_CX +#define _ASM_ARG5 r8 +#define _ASM_ARG6 r9 + +#define _ASM_ARG1Q rdi +#define _ASM_ARG2Q rsi +#define _ASM_ARG3Q rdx +#define _ASM_ARG4Q rcx +#define _ASM_ARG5Q r8 +#define _ASM_ARG6Q r9 + +#define _ASM_ARG1L edi +#define _ASM_ARG2L esi +#define _ASM_ARG3L edx +#define _ASM_ARG4L ecx +#define _ASM_ARG5L r8d +#define _ASM_ARG6L r9d + +#define _ASM_ARG1W di +#define _ASM_ARG2W si +#define _ASM_ARG3W dx +#define _ASM_ARG4W cx +#define _ASM_ARG5W r8w +#define _ASM_ARG6W r9w + +#define _ASM_ARG1B dil +#define _ASM_ARG2B sil +#define _ASM_ARG3B dl +#define _ASM_ARG4B cl +#define _ASM_ARG5B r8b +#define _ASM_ARG6B r9b + +#endif + /* * Macros to generate condition code outputs from inline assembly, * The output operand must be type "bool". diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 89f08955fff7..c4fc17220df9 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -13,7 +13,7 @@ * Interrupt control: */ -static inline unsigned long native_save_fl(void) +extern inline unsigned long native_save_fl(void) { unsigned long flags; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 295abaa58add..4137f7ba0f88 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -58,6 +58,7 @@ obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o obj-y += tsc.o tsc_msr.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o +obj-y += irqflags.o obj-y += process.o obj-y += fpu/ diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S new file mode 100644 index 000000000000..ddeeaac8adda --- /dev/null +++ b/arch/x86/kernel/irqflags.S @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include +#include +#include + +/* + * unsigned long native_save_fl(void) + */ +ENTRY(native_save_fl) + pushf + pop %_ASM_AX + ret +ENDPROC(native_save_fl) +EXPORT_SYMBOL(native_save_fl) + +/* + * void native_restore_fl(unsigned long flags) + * %eax/%rdi: flags + */ +ENTRY(native_restore_fl) + push %_ASM_ARG1 + popf + ret +ENDPROC(native_restore_fl) +EXPORT_SYMBOL(native_restore_fl) diff --git a/block/blk-core.c b/block/blk-core.c index 6f6e21821d2d..68bae6338ad4 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -779,7 +779,6 @@ EXPORT_SYMBOL(blk_alloc_queue); int blk_queue_enter(struct request_queue *q, bool nowait) { while (true) { - int ret; if (percpu_ref_tryget_live(&q->q_usage_counter)) return 0; @@ -796,13 +795,11 @@ int blk_queue_enter(struct request_queue *q, bool nowait) */ smp_rmb(); - ret = wait_event_interruptible(q->mq_freeze_wq, - !atomic_read(&q->mq_freeze_depth) || - blk_queue_dying(q)); + wait_event(q->mq_freeze_wq, + !atomic_read(&q->mq_freeze_depth) || + blk_queue_dying(q)); if (blk_queue_dying(q)) return -ENODEV; - if (ret) - return ret; } } diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 815ee1075574..42dfdd1fd6d8 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1183,8 +1183,10 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags, /* make one iovec available as scatterlist */ err = af_alg_make_sg(&rsgl->sgl, &msg->msg_iter, seglen); - if (err < 0) + if (err < 0) { + rsgl->sg_num_bytes = 0; return err; + } /* chain the new scatterlist with previous one */ if (areq->last_rsgl) diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index a8d2eb0ceb8d..2c288d1f42bb 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1483,6 +1483,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg) return -EFAULT; if (pool < 0 || pool > ZATM_LAST_POOL) return -EINVAL; + pool = array_index_nospec(pool, + ZATM_LAST_POOL + 1); if (copy_from_user(&info, &((struct zatm_pool_req __user *) arg)->info, sizeof(info))) return -EFAULT; diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 8b432d6e846d..c9ce716247c1 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -126,6 +126,49 @@ static void cppc_cpufreq_stop_cpu(struct cpufreq_policy *policy) cpu->perf_caps.lowest_perf, cpu_num, ret); } +/* + * The PCC subspace describes the rate at which platform can accept commands + * on the shared PCC channel (including READs which do not count towards freq + * trasition requests), so ideally we need to use the PCC values as a fallback + * if we don't have a platform specific transition_delay_us + */ +#ifdef CONFIG_ARM64 +#include + +static unsigned int cppc_cpufreq_get_transition_delay_us(int cpu) +{ + unsigned long implementor = read_cpuid_implementor(); + unsigned long part_num = read_cpuid_part_number(); + unsigned int delay_us = 0; + + switch (implementor) { + case ARM_CPU_IMP_QCOM: + switch (part_num) { + case QCOM_CPU_PART_FALKOR_V1: + case QCOM_CPU_PART_FALKOR: + delay_us = 10000; + break; + default: + delay_us = cppc_get_transition_latency(cpu) / NSEC_PER_USEC; + break; + } + break; + default: + delay_us = cppc_get_transition_latency(cpu) / NSEC_PER_USEC; + break; + } + + return delay_us; +} + +#else + +static unsigned int cppc_cpufreq_get_transition_delay_us(int cpu) +{ + return cppc_get_transition_latency(cpu) / NSEC_PER_USEC; +} +#endif + static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) { struct cppc_cpudata *cpu; @@ -163,8 +206,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.max_freq = cppc_dmi_max_khz; policy->cpuinfo.transition_latency = cppc_get_transition_latency(cpu_num); - policy->transition_delay_us = cppc_get_transition_latency(cpu_num) / - NSEC_PER_USEC; + policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu_num); policy->shared_type = cpu->shared_type; if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) { diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c index 65dc78b91dea..3f9eee7e555f 100644 --- a/drivers/crypto/amcc/crypto4xx_core.c +++ b/drivers/crypto/amcc/crypto4xx_core.c @@ -207,7 +207,7 @@ static u32 crypto4xx_build_pdr(struct crypto4xx_device *dev) dev->pdr_pa); return -ENOMEM; } - memset(dev->pdr, 0, sizeof(struct ce_pd) * PPC4XX_NUM_PD); + memset(dev->pdr, 0, sizeof(struct ce_pd) * PPC4XX_NUM_PD); dev->shadow_sa_pool = dma_alloc_coherent(dev->core_dev->device, 256 * PPC4XX_NUM_PD, &dev->shadow_sa_pool_pa, @@ -240,13 +240,15 @@ static u32 crypto4xx_build_pdr(struct crypto4xx_device *dev) static void crypto4xx_destroy_pdr(struct crypto4xx_device *dev) { - if (dev->pdr != NULL) + if (dev->pdr) dma_free_coherent(dev->core_dev->device, sizeof(struct ce_pd) * PPC4XX_NUM_PD, dev->pdr, dev->pdr_pa); + if (dev->shadow_sa_pool) dma_free_coherent(dev->core_dev->device, 256 * PPC4XX_NUM_PD, dev->shadow_sa_pool, dev->shadow_sa_pool_pa); + if (dev->shadow_sr_pool) dma_free_coherent(dev->core_dev->device, sizeof(struct sa_state_record) * PPC4XX_NUM_PD, @@ -416,12 +418,12 @@ static u32 crypto4xx_build_sdr(struct crypto4xx_device *dev) static void crypto4xx_destroy_sdr(struct crypto4xx_device *dev) { - if (dev->sdr != NULL) + if (dev->sdr) dma_free_coherent(dev->core_dev->device, sizeof(struct ce_sd) * PPC4XX_NUM_SD, dev->sdr, dev->sdr_pa); - if (dev->scatter_buffer_va != NULL) + if (dev->scatter_buffer_va) dma_free_coherent(dev->core_dev->device, dev->scatter_buffer_size * PPC4XX_NUM_SD, dev->scatter_buffer_va, @@ -1033,12 +1035,10 @@ int crypto4xx_register_alg(struct crypto4xx_device *sec_dev, break; } - if (rc) { - list_del(&alg->entry); + if (rc) kfree(alg); - } else { + else list_add_tail(&alg->entry, &sec_dev->alg_list); - } } return 0; @@ -1193,7 +1193,7 @@ static int crypto4xx_probe(struct platform_device *ofdev) rc = crypto4xx_build_gdr(core_dev->dev); if (rc) - goto err_build_gdr; + goto err_build_pdr; rc = crypto4xx_build_sdr(core_dev->dev); if (rc) @@ -1236,12 +1236,11 @@ static int crypto4xx_probe(struct platform_device *ofdev) err_request_irq: irq_dispose_mapping(core_dev->irq); tasklet_kill(&core_dev->tasklet); - crypto4xx_destroy_sdr(core_dev->dev); err_build_sdr: + crypto4xx_destroy_sdr(core_dev->dev); crypto4xx_destroy_gdr(core_dev->dev); -err_build_gdr: - crypto4xx_destroy_pdr(core_dev->dev); err_build_pdr: + crypto4xx_destroy_pdr(core_dev->dev); kfree(core_dev->dev); err_alloc_dev: kfree(core_dev); diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 72f381522cb2..a22828713c1c 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -1824,11 +1824,11 @@ void rc_unregister_device(struct rc_dev *dev) if (!dev) return; - del_timer_sync(&dev->timer_keyup); - if (dev->driver_type == RC_DRIVER_IR_RAW) ir_raw_event_unregister(dev); + del_timer_sync(&dev->timer_keyup); + rc_free_rx_device(dev); device_del(&dev->dev); diff --git a/drivers/mtd/nand/denali_dt.c b/drivers/mtd/nand/denali_dt.c index 56e2e177644d..3f4f4aea0e8b 100644 --- a/drivers/mtd/nand/denali_dt.c +++ b/drivers/mtd/nand/denali_dt.c @@ -122,7 +122,11 @@ static int denali_dt_probe(struct platform_device *pdev) if (ret) return ret; - denali->clk_x_rate = clk_get_rate(dt->clk); + /* + * Hardcode the clock rate for the backward compatibility. + * This works for both SOCFPGA and UniPhier. + */ + denali->clk_x_rate = 200000000; ret = denali_init(denali); if (ret) diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 567ee54504bc..5e5022fa1d04 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1897,13 +1897,19 @@ static int alx_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct alx_priv *alx = pci_get_drvdata(pdev); struct alx_hw *hw = &alx->hw; + int err; alx_reset_phy(hw); if (!netif_running(alx->dev)) return 0; netif_device_attach(alx->dev); - return __alx_open(alx, true); + + rtnl_lock(); + err = __alx_open(alx, true); + rtnl_unlock(); + + return err; } static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume); diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 4f3845a58126..68470c7c630a 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1062,7 +1062,8 @@ static int bcm_enet_open(struct net_device *dev) val = enet_readl(priv, ENET_CTL_REG); val |= ENET_CTL_ENABLE_MASK; enet_writel(priv, val, ENET_CTL_REG); - enet_dma_writel(priv, ENETDMA_CFG_EN_MASK, ENETDMA_CFG_REG); + if (priv->dma_has_sram) + enet_dma_writel(priv, ENETDMA_CFG_EN_MASK, ENETDMA_CFG_REG); enet_dmac_writel(priv, priv->dma_chan_en_mask, ENETDMAC_CHANCFG, priv->rx_chan); @@ -1773,7 +1774,9 @@ static int bcm_enet_probe(struct platform_device *pdev) ret = PTR_ERR(priv->mac_clk); goto out; } - clk_prepare_enable(priv->mac_clk); + ret = clk_prepare_enable(priv->mac_clk); + if (ret) + goto out_put_clk_mac; /* initialize default and fetch platform data */ priv->rx_ring_size = BCMENET_DEF_RX_DESC; @@ -1805,9 +1808,11 @@ static int bcm_enet_probe(struct platform_device *pdev) if (IS_ERR(priv->phy_clk)) { ret = PTR_ERR(priv->phy_clk); priv->phy_clk = NULL; - goto out_put_clk_mac; + goto out_disable_clk_mac; } - clk_prepare_enable(priv->phy_clk); + ret = clk_prepare_enable(priv->phy_clk); + if (ret) + goto out_put_clk_phy; } /* do minimal hardware init to be able to probe mii bus */ @@ -1901,13 +1906,16 @@ static int bcm_enet_probe(struct platform_device *pdev) out_uninit_hw: /* turn off mdc clock */ enet_writel(priv, 0, ENET_MIISC_REG); - if (priv->phy_clk) { + if (priv->phy_clk) clk_disable_unprepare(priv->phy_clk); + +out_put_clk_phy: + if (priv->phy_clk) clk_put(priv->phy_clk); - } -out_put_clk_mac: +out_disable_clk_mac: clk_disable_unprepare(priv->mac_clk); +out_put_clk_mac: clk_put(priv->mac_clk); out: free_netdev(dev); @@ -2752,7 +2760,9 @@ static int bcm_enetsw_probe(struct platform_device *pdev) ret = PTR_ERR(priv->mac_clk); goto out_unmap; } - clk_enable(priv->mac_clk); + ret = clk_prepare_enable(priv->mac_clk); + if (ret) + goto out_put_clk; priv->rx_chan = 0; priv->tx_chan = 1; @@ -2773,7 +2783,7 @@ static int bcm_enetsw_probe(struct platform_device *pdev) ret = register_netdev(dev); if (ret) - goto out_put_clk; + goto out_disable_clk; netif_carrier_off(dev); platform_set_drvdata(pdev, dev); @@ -2782,6 +2792,9 @@ static int bcm_enetsw_probe(struct platform_device *pdev) return 0; +out_disable_clk: + clk_disable_unprepare(priv->mac_clk); + out_put_clk: clk_put(priv->mac_clk); @@ -2813,6 +2826,9 @@ static int bcm_enetsw_remove(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); release_mem_region(res->start, resource_size(res)); + clk_disable_unprepare(priv->mac_clk); + clk_put(priv->mac_clk); + free_netdev(dev); return 0; } diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index 2220c771092b..678835136bf8 100755 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -170,10 +170,7 @@ static int gem_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) if (delta > TSU_NSEC_MAX_VAL) { gem_tsu_get_time(&bp->ptp_clock_info, &now); - if (sign) - now = timespec64_sub(now, then); - else - now = timespec64_add(now, then); + now = timespec64_add(now, then); gem_tsu_set_time(&bp->ptp_clock_info, (const struct timespec64 *)&now); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 6a015362c340..bf291e90cdb0 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -51,6 +51,7 @@ #include #include #include +#include #include "common.h" #include "cxgb3_ioctl.h" @@ -2268,6 +2269,7 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (t.qset_idx >= nqsets) return -EINVAL; + t.qset_idx = array_index_nospec(t.qset_idx, nqsets); q = &adapter->params.sge.qset[q1 + t.qset_idx]; t.rspq_size = q->rspq_size; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 20a8018d41ef..b68d94b49a8a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2211,9 +2211,10 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } -#define IXGBE_XDP_PASS 0 -#define IXGBE_XDP_CONSUMED 1 -#define IXGBE_XDP_TX 2 +#define IXGBE_XDP_PASS 0 +#define IXGBE_XDP_CONSUMED BIT(0) +#define IXGBE_XDP_TX BIT(1) +#define IXGBE_XDP_REDIR BIT(2) static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, struct xdp_buff *xdp); @@ -2242,7 +2243,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); if (!err) - result = IXGBE_XDP_TX; + result = IXGBE_XDP_REDIR; else result = IXGBE_XDP_CONSUMED; break; @@ -2302,7 +2303,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, unsigned int mss = 0; #endif /* IXGBE_FCOE */ u16 cleaned_count = ixgbe_desc_unused(rx_ring); - bool xdp_xmit = false; + unsigned int xdp_xmit = 0; while (likely(total_rx_packets < budget)) { union ixgbe_adv_rx_desc *rx_desc; @@ -2342,8 +2343,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } if (IS_ERR(skb)) { - if (PTR_ERR(skb) == -IXGBE_XDP_TX) { - xdp_xmit = true; + unsigned int xdp_res = -PTR_ERR(skb); + + if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { + xdp_xmit |= xdp_res; ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); } else { rx_buffer->pagecnt_bias++; @@ -2415,7 +2418,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, total_rx_packets++; } - if (xdp_xmit) { + if (xdp_xmit & IXGBE_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & IXGBE_XDP_TX) { struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; /* Force memory writes to complete before letting h/w @@ -2423,8 +2429,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ wmb(); writel(ring->next_to_use, ring->tail); - - xdp_do_flush_map(); } u64_stats_update_begin(&rx_ring->syncp); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index d28f873169a9..3deaa3413313 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1959,7 +1959,7 @@ static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo, rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE); index = rx_desc - rxq->descs; data = rxq->buf_virt_addr[index]; - phys_addr = rx_desc->buf_phys_addr; + phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction; if (!mvneta_rxq_desc_is_first_last(rx_status) || (rx_status & MVNETA_RXD_ERR_SUMMARY)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 3efe45bc2471..cf94fdf25155 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -801,6 +801,7 @@ static void cmd_work_handler(struct work_struct *work) unsigned long flags; bool poll_cmd = ent->polling; int alloc_ret; + int cmd_mode; sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); @@ -847,6 +848,7 @@ static void cmd_work_handler(struct work_struct *work) set_signature(ent, !cmd->checksum_disabled); dump_command(dev, ent, 1); ent->ts1 = ktime_get_ns(); + cmd_mode = cmd->mode; if (ent->callback) schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); @@ -871,7 +873,7 @@ static void cmd_work_handler(struct work_struct *work) iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell); mmiowb(); /* if not in polling don't use ent after this point */ - if (cmd->mode == CMD_MODE_POLLING || poll_cmd) { + if (cmd_mode == CMD_MODE_POLLING || poll_cmd) { poll_timeout(ent); /* make sure we read the descriptor after ownership is SW */ rmb(); @@ -1272,7 +1274,7 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf, { struct mlx5_core_dev *dev = filp->private_data; struct mlx5_cmd_debug *dbg = &dev->cmd.dbg; - char outlen_str[8]; + char outlen_str[8] = {0}; int outlen; void *ptr; int err; @@ -1287,8 +1289,6 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf, if (copy_from_user(outlen_str, buf, count)) return -EFAULT; - outlen_str[7] = 0; - err = sscanf(outlen_str, "%d", &outlen); if (err < 0) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 337ce9423794..bf34264c734b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2626,7 +2626,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_activate_channels(&priv->channels); netif_tx_start_all_queues(priv->netdev); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_add_sqs_fwd_rules(priv); mlx5e_wait_channels_min_rx_wqes(&priv->channels); @@ -2637,7 +2637,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { mlx5e_redirect_rqts_to_drop(priv); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_remove_sqs_fwd_rules(priv); /* FIXME: This is a W/A only for tx timeout watch dog false alarm when @@ -4127,7 +4127,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) mlx5e_set_netdev_dev_addr(netdev); #if IS_ENABLED(CONFIG_MLX5_ESWITCH) - if (MLX5_VPORT_MANAGER(mdev)) + if (MLX5_ESWITCH_MANAGER(mdev)) netdev->switchdev_ops = &mlx5e_switchdev_ops; #endif @@ -4273,7 +4273,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) mlx5e_enable_async_events(priv); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_register_vport_reps(priv); if (netdev->reg_state != NETREG_REGISTERED) @@ -4300,7 +4300,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) queue_work(priv->wq, &priv->set_rx_mode_work); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_unregister_vport_reps(priv); mlx5e_disable_async_events(priv); @@ -4483,7 +4483,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) return NULL; #ifdef CONFIG_MLX5_ESWITCH - if (MLX5_VPORT_MANAGER(mdev)) { + if (MLX5_ESWITCH_MANAGER(mdev)) { rpriv = mlx5e_alloc_nic_rep_priv(mdev); if (!rpriv) { mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 4727e7390834..281911698f72 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -710,7 +710,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep; - if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager)) + if (!MLX5_ESWITCH_MANAGER(priv->mdev)) return false; rep = rpriv->rep; @@ -724,8 +724,12 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5_eswitch_rep *rep = rpriv->rep; + struct mlx5_eswitch_rep *rep; + if (!MLX5_ESWITCH_MANAGER(priv->mdev)) + return false; + + rep = rpriv->rep; if (rep && rep->vport != FDB_UPLINK_VPORT) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 82e37250ed01..667415301066 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1535,7 +1535,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) if (!ESW_ALLOWED(esw)) return 0; - if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) || + if (!MLX5_ESWITCH_MANAGER(esw->dev) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 565c8b7a399a..10bf770675f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -39,6 +39,8 @@ #include #include "lib/mpfs.h" +#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) + enum { SRIOV_NONE, SRIOV_LEGACY, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d9fd8570b07c..c699055c0ffd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -912,8 +912,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink) if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) return -EOPNOTSUPP; - if (!MLX5_CAP_GEN(dev, vport_group_manager)) - return -EOPNOTSUPP; + if(!MLX5_ESWITCH_MANAGER(dev)) + return -EPERM; if (dev->priv.eswitch->mode == SRIOV_NONE) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 33e5ff081e36..dd05cf148845 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -36,6 +36,7 @@ #include "mlx5_core.h" #include "fs_core.h" #include "fs_cmd.h" +#include "eswitch.h" #include "diag/fs_tracepoint.h" #define INIT_TREE_NODE_ARRAY_SIZE(...) (sizeof((struct init_tree_node[]){__VA_ARGS__}) /\ @@ -2211,7 +2212,7 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } - if (MLX5_CAP_GEN(dev, eswitch_flow_table)) { + if (MLX5_ESWITCH_MANAGER(dev)) { if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) { err = init_fdb_root_ns(steering); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 2c71557d1cee..d69897a1e2ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -34,6 +34,7 @@ #include #include #include "mlx5_core.h" +#include "eswitch.h" #include "../../mlxfw/mlxfw.h" static int mlx5_cmd_query_adapter(struct mlx5_core_dev *dev, u32 *out, @@ -152,13 +153,13 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) } if (MLX5_CAP_GEN(dev, vport_group_manager) && - MLX5_CAP_GEN(dev, eswitch_flow_table)) { + MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE); if (err) return err; } - if (MLX5_CAP_GEN(dev, eswitch_flow_table)) { + if (MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index 7cb67122e8b5..22811ecd8fcd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -34,6 +34,7 @@ #include #include #include "mlx5_core.h" +#include "eswitch.h" #include "lib/mpfs.h" /* HW L2 Table (MPFS) management */ @@ -98,7 +99,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev) int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table); struct mlx5_mpfs *mpfs; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL); @@ -122,7 +123,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) { struct mlx5_mpfs *mpfs = dev->priv.mpfs; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return; WARN_ON(!hlist_empty(mpfs->hash)); @@ -137,7 +138,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) u32 index; int err; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mutex_lock(&mpfs->lock); @@ -179,7 +180,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) int err = 0; u32 index; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mutex_lock(&mpfs->lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index e07061f565d6..ccb6287aeeb7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -641,7 +641,7 @@ EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc); static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, int inlen) { - u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + u32 out[MLX5_ST_SZ_DW(qetc_reg)]; if (!MLX5_CAP_GEN(mdev, ets)) return -EOPNOTSUPP; @@ -653,7 +653,7 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out, int outlen) { - u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; if (!MLX5_CAP_GEN(mdev, ets)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 2a8b529ce6dd..a0674962f02c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -88,6 +88,9 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return -EBUSY; } + if (!MLX5_ESWITCH_MANAGER(dev)) + goto enable_vfs_hca; + err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY); if (err) { mlx5_core_warn(dev, @@ -95,6 +98,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return err; } +enable_vfs_hca: for (vf = 0; vf < num_vfs; vf++) { err = mlx5_core_enable_hca(dev, vf + 1); if (err) { @@ -140,7 +144,8 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev) } out: - mlx5_eswitch_disable_sriov(dev->priv.eswitch); + if (MLX5_ESWITCH_MANAGER(dev)) + mlx5_eswitch_disable_sriov(dev->priv.eswitch); if (mlx5_wait_for_vf_pages(dev)) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 8f6ccc0c39e5..b306961b02fd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -700,9 +700,9 @@ qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn, p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE]; memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id, - ARRAY_SIZE(p_local->local_chassis_id)); + sizeof(p_local->local_chassis_id)); memcpy(params->lldp_local.local_port_id, p_local->local_port_id, - ARRAY_SIZE(p_local->local_port_id)); + sizeof(p_local->local_port_id)); } static void @@ -714,9 +714,9 @@ qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn, p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE]; memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id, - ARRAY_SIZE(p_remote->peer_chassis_id)); + sizeof(p_remote->peer_chassis_id)); memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id, - ARRAY_SIZE(p_remote->peer_port_id)); + sizeof(p_remote->peer_port_id)); } static int diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 58a689fb04db..ef2374699726 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1782,7 +1782,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) DP_INFO(p_hwfn, "Failed to update driver state\n"); rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt, - QED_OV_ESWITCH_VEB); + QED_OV_ESWITCH_NONE); if (rc) DP_INFO(p_hwfn, "Failed to update eswitch mode\n"); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 27832885a87f..2c958921dfb3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -779,6 +779,14 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev, /* We want a minimum of one slowpath and one fastpath vector per hwfn */ cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2; + if (is_kdump_kernel()) { + DP_INFO(cdev, + "Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n", + cdev->int_params.in.min_msix_cnt); + cdev->int_params.in.num_vectors = + cdev->int_params.in.min_msix_cnt; + } + rc = qed_set_int_mode(cdev, false); if (rc) { DP_ERR(cdev, "qed_slowpath_setup_int ERR\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 3f40b1de7957..d08fe350ab6c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -4396,6 +4396,8 @@ static void qed_sriov_enable_qid_config(struct qed_hwfn *hwfn, static int qed_sriov_enable(struct qed_dev *cdev, int num) { struct qed_iov_vf_init_params params; + struct qed_hwfn *hwfn; + struct qed_ptt *ptt; int i, j, rc; if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) { @@ -4408,8 +4410,8 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num) /* Initialize HW for VF access */ for_each_hwfn(cdev, j) { - struct qed_hwfn *hwfn = &cdev->hwfns[j]; - struct qed_ptt *ptt = qed_ptt_acquire(hwfn); + hwfn = &cdev->hwfns[j]; + ptt = qed_ptt_acquire(hwfn); /* Make sure not to use more than 16 queues per VF */ params.num_queues = min_t(int, @@ -4445,6 +4447,19 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num) goto err; } + hwfn = QED_LEADING_HWFN(cdev); + ptt = qed_ptt_acquire(hwfn); + if (!ptt) { + DP_ERR(hwfn, "Failed to acquire ptt\n"); + rc = -EBUSY; + goto err; + } + + rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB); + if (rc) + DP_INFO(cdev, "Failed to update eswitch mode\n"); + qed_ptt_release(hwfn, ptt); + return num; err: diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 9b2280badaf7..475f6ae5d4b3 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -337,8 +337,14 @@ int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *info) { struct qede_ptp *ptp = edev->ptp; - if (!ptp) - return -EIO; + if (!ptp) { + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info->phc_index = -1; + + return 0; + } info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE | diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 9866d2e34cdd..27f2e650e27b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -914,6 +914,7 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv) static int stmmac_init_phy(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + u32 tx_cnt = priv->plat->tx_queues_to_use; struct phy_device *phydev; char phy_id_fmt[MII_BUS_ID_SIZE + 3]; char bus_id[MII_BUS_ID_SIZE]; @@ -954,6 +955,15 @@ static int stmmac_init_phy(struct net_device *dev) phydev->advertising &= ~(SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full); + /* + * Half-duplex mode not supported with multiqueue + * half-duplex can only works with single queue + */ + if (tx_cnt > 1) + phydev->supported &= ~(SUPPORTED_1000baseT_Half | + SUPPORTED_100baseT_Half | + SUPPORTED_10baseT_Half); + /* * Broken HW is sometimes missing the pull-up resistor on the * MDIO line, which results in reads to non-existent devices returning diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index fa607d062cb3..15cd086e3f47 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -59,8 +59,7 @@ #include #include "sungem.h" -/* Stripping FCS is causing problems, disabled for now */ -#undef STRIP_FCS +#define STRIP_FCS #define DEFAULT_MSG (NETIF_MSG_DRV | \ NETIF_MSG_PROBE | \ @@ -434,7 +433,7 @@ static int gem_rxmac_reset(struct gem *gp) writel(desc_dma & 0xffffffff, gp->regs + RXDMA_DBLOW); writel(RX_RING_SIZE - 4, gp->regs + RXDMA_KICK); val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) | - ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128); + (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128); writel(val, gp->regs + RXDMA_CFG); if (readl(gp->regs + GREG_BIFCFG) & GREG_BIFCFG_M66EN) writel(((5 & RXDMA_BLANK_IPKTS) | @@ -759,7 +758,6 @@ static int gem_rx(struct gem *gp, int work_to_do) struct net_device *dev = gp->dev; int entry, drops, work_done = 0; u32 done; - __sum16 csum; if (netif_msg_rx_status(gp)) printk(KERN_DEBUG "%s: rx interrupt, done: %d, rx_new: %d\n", @@ -854,9 +852,13 @@ static int gem_rx(struct gem *gp, int work_to_do) skb = copy_skb; } - csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff); - skb->csum = csum_unfold(csum); - skb->ip_summed = CHECKSUM_COMPLETE; + if (likely(dev->features & NETIF_F_RXCSUM)) { + __sum16 csum; + + csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff); + skb->csum = csum_unfold(csum); + skb->ip_summed = CHECKSUM_COMPLETE; + } skb->protocol = eth_type_trans(skb, gp->dev); napi_gro_receive(&gp->napi, skb); @@ -1760,7 +1762,7 @@ static void gem_init_dma(struct gem *gp) writel(0, gp->regs + TXDMA_KICK); val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) | - ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128); + (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128); writel(val, gp->regs + RXDMA_CFG); writel(desc_dma >> 32, gp->regs + RXDMA_DBHI); @@ -2986,8 +2988,8 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, dev); /* We can do scatter/gather and HW checksum */ - dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM; - dev->features |= dev->hw_features | NETIF_F_RXCSUM; + dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM; + dev->features = dev->hw_features; if (pci_using_dac) dev->features |= NETIF_F_HIGHDMA; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index fbc825ac97ab..cb51448389a1 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -474,7 +474,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 01017dd88802..cb250cacf721 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -207,7 +207,7 @@ int netvsc_recv_callback(struct net_device *net, void netvsc_channel_cb(void *context); int netvsc_poll(struct napi_struct *napi, int budget); -void rndis_set_subchannel(struct work_struct *w); +int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev); int rndis_filter_open(struct netvsc_device *nvdev); int rndis_filter_close(struct netvsc_device *nvdev); struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 4647ecbe6f36..701be5d81062 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -62,6 +62,41 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf) VM_PKT_DATA_INBAND, 0); } +/* Worker to setup sub channels on initial setup + * Initial hotplug event occurs in softirq context + * and can't wait for channels. + */ +static void netvsc_subchan_work(struct work_struct *w) +{ + struct netvsc_device *nvdev = + container_of(w, struct netvsc_device, subchan_work); + struct rndis_device *rdev; + int i, ret; + + /* Avoid deadlock with device removal already under RTNL */ + if (!rtnl_trylock()) { + schedule_work(w); + return; + } + + rdev = nvdev->extension; + if (rdev) { + ret = rndis_set_subchannel(rdev->ndev, nvdev); + if (ret == 0) { + netif_device_attach(rdev->ndev); + } else { + /* fallback to only primary channel */ + for (i = 1; i < nvdev->num_chn; i++) + netif_napi_del(&nvdev->chan_table[i].napi); + + nvdev->max_chn = 1; + nvdev->num_chn = 1; + } + } + + rtnl_unlock(); +} + static struct netvsc_device *alloc_net_device(void) { struct netvsc_device *net_device; @@ -78,7 +113,7 @@ static struct netvsc_device *alloc_net_device(void) init_completion(&net_device->channel_init_wait); init_waitqueue_head(&net_device->subchan_open); - INIT_WORK(&net_device->subchan_work, rndis_set_subchannel); + INIT_WORK(&net_device->subchan_work, netvsc_subchan_work); return net_device; } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 6890478a0851..aeabeb107fed 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -911,8 +911,20 @@ static int netvsc_attach(struct net_device *ndev, if (IS_ERR(nvdev)) return PTR_ERR(nvdev); - /* Note: enable and attach happen when sub-channels setup */ + if (nvdev->num_chn > 1) { + ret = rndis_set_subchannel(ndev, nvdev); + + /* if unavailable, just proceed with one queue */ + if (ret) { + nvdev->max_chn = 1; + nvdev->num_chn = 1; + } + } + + /* In any case device is now ready */ + netif_device_attach(ndev); + /* Note: enable and attach happen when sub-channels setup */ netif_carrier_off(ndev); if (netif_running(ndev)) { @@ -2035,6 +2047,9 @@ static int netvsc_probe(struct hv_device *dev, memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN); + if (nvdev->num_chn > 1) + schedule_work(&nvdev->subchan_work); + /* hw_features computed in rndis_netdev_set_hwcaps() */ net->features = net->hw_features | NETIF_F_HIGHDMA | NETIF_F_SG | diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index d1ae184008b4..cb03a6ea076a 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1055,29 +1055,15 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) * This breaks overlap of processing the host message for the * new primary channel with the initialization of sub-channels. */ -void rndis_set_subchannel(struct work_struct *w) +int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev) { - struct netvsc_device *nvdev - = container_of(w, struct netvsc_device, subchan_work); struct nvsp_message *init_packet = &nvdev->channel_init_pkt; - struct net_device_context *ndev_ctx; - struct rndis_device *rdev; - struct net_device *ndev; - struct hv_device *hv_dev; + struct net_device_context *ndev_ctx = netdev_priv(ndev); + struct hv_device *hv_dev = ndev_ctx->device_ctx; + struct rndis_device *rdev = nvdev->extension; int i, ret; - if (!rtnl_trylock()) { - schedule_work(w); - return; - } - - rdev = nvdev->extension; - if (!rdev) - goto unlock; /* device was removed */ - - ndev = rdev->ndev; - ndev_ctx = netdev_priv(ndev); - hv_dev = ndev_ctx->device_ctx; + ASSERT_RTNL(); memset(init_packet, 0, sizeof(struct nvsp_message)); init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL; @@ -1091,13 +1077,13 @@ void rndis_set_subchannel(struct work_struct *w) VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret) { netdev_err(ndev, "sub channel allocate send failed: %d\n", ret); - goto failed; + return ret; } wait_for_completion(&nvdev->channel_init_wait); if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) { netdev_err(ndev, "sub channel request failed\n"); - goto failed; + return -EIO; } nvdev->num_chn = 1 + @@ -1116,21 +1102,7 @@ void rndis_set_subchannel(struct work_struct *w) for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) ndev_ctx->tx_table[i] = i % nvdev->num_chn; - netif_device_attach(ndev); - rtnl_unlock(); - return; - -failed: - /* fallback to only primary channel */ - for (i = 1; i < nvdev->num_chn; i++) - netif_napi_del(&nvdev->chan_table[i].napi); - - nvdev->max_chn = 1; - nvdev->num_chn = 1; - - netif_device_attach(ndev); -unlock: - rtnl_unlock(); + return 0; } static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, @@ -1321,21 +1293,12 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, netif_napi_add(net, &net_device->chan_table[i].napi, netvsc_poll, NAPI_POLL_WEIGHT); - if (net_device->num_chn > 1) - schedule_work(&net_device->subchan_work); + return net_device; out: - /* if unavailable, just proceed with one queue */ - if (ret) { - net_device->max_chn = 1; - net_device->num_chn = 1; - } - - /* No sub channels, device is ready */ - if (net_device->num_chn == 1) - netif_device_attach(net); - - return net_device; + /* setting up multiple channels failed */ + net_device->max_chn = 1; + net_device->num_chn = 1; err_dev_remv: rndis_filter_device_remove(dev, net_device); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index c74893c1e620..e7f7a1a002ee 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -546,7 +546,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, ipvlan->dev = dev; ipvlan->port = port; ipvlan->sfeatures = IPVLAN_FEATURES; - ipvlan_adjust_mtu(ipvlan, phy_dev); + if (!tb[IFLA_MTU]) + ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); /* If the port-id base is at the MAX value, then wrap it around and diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 9881edc568ba..0aa91ab9a0fb 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3197,6 +3197,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) pkt_cnt = 0; count = 0; length = 0; + spin_lock_irqsave(&tqp->lock, flags); for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) { if (skb_is_gso(skb)) { if (pkt_cnt) { @@ -3205,7 +3206,8 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) } count = 1; length = skb->len - TX_OVERHEAD; - skb2 = skb_dequeue(tqp); + __skb_unlink(skb, tqp); + spin_unlock_irqrestore(&tqp->lock, flags); goto gso_skb; } @@ -3214,6 +3216,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) skb_totallen = skb->len + roundup(skb_totallen, sizeof(u32)); pkt_cnt++; } + spin_unlock_irqrestore(&tqp->lock, flags); /* copy to a single skb */ skb = alloc_skb(skb_totallen, GFP_ATOMIC); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index b23ee948e7c9..0db500bf86d9 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1245,6 +1245,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ + {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index aa88b640cb6c..0fa64cc1a011 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3959,7 +3959,8 @@ static int rtl8152_close(struct net_device *netdev) #ifdef CONFIG_PM_SLEEP unregister_pm_notifier(&tp->pm_notifier); #endif - napi_disable(&tp->napi); + if (!test_bit(RTL8152_UNPLUG, &tp->flags)) + napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 3d9c5b35a4a7..bbdb46916dc3 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -623,9 +623,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk, flush = 0; out: - skb_gro_remcsum_cleanup(skb, &grc); - skb->remcsum_offload = 0; - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index 93256f8bc0b5..ec82c1c3f12e 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -483,18 +483,21 @@ static void _rtl_init_deferred_work(struct ieee80211_hw *hw) } -void rtl_deinit_deferred_work(struct ieee80211_hw *hw) +void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq) { struct rtl_priv *rtlpriv = rtl_priv(hw); del_timer_sync(&rtlpriv->works.watchdog_timer); - cancel_delayed_work(&rtlpriv->works.watchdog_wq); - cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); - cancel_delayed_work(&rtlpriv->works.ps_work); - cancel_delayed_work(&rtlpriv->works.ps_rfon_wq); - cancel_delayed_work(&rtlpriv->works.fwevt_wq); - cancel_delayed_work(&rtlpriv->works.c2hcmd_wq); + cancel_delayed_work_sync(&rtlpriv->works.watchdog_wq); + if (ips_wq) + cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); + else + cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq); + cancel_delayed_work_sync(&rtlpriv->works.ps_work); + cancel_delayed_work_sync(&rtlpriv->works.ps_rfon_wq); + cancel_delayed_work_sync(&rtlpriv->works.fwevt_wq); + cancel_delayed_work_sync(&rtlpriv->works.c2hcmd_wq); } EXPORT_SYMBOL_GPL(rtl_deinit_deferred_work); diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h index b56d1b7f5567..cbbb5be36a09 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.h +++ b/drivers/net/wireless/realtek/rtlwifi/base.h @@ -121,7 +121,7 @@ void rtl_init_rfkill(struct ieee80211_hw *hw); void rtl_deinit_rfkill(struct ieee80211_hw *hw); void rtl_watch_dog_timer_callback(unsigned long data); -void rtl_deinit_deferred_work(struct ieee80211_hw *hw); +void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq); bool rtl_action_proc(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx); int rtlwifi_rate_mapping(struct ieee80211_hw *hw, bool isht, diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c index c53cbf3d52bd..b01123138797 100644 --- a/drivers/net/wireless/realtek/rtlwifi/core.c +++ b/drivers/net/wireless/realtek/rtlwifi/core.c @@ -130,7 +130,6 @@ static void rtl_fw_do_work(const struct firmware *firmware, void *context, firmware->size); rtlpriv->rtlhal.wowlan_fwsize = firmware->size; } - rtlpriv->rtlhal.fwsize = firmware->size; release_firmware(firmware); } @@ -196,7 +195,7 @@ static void rtl_op_stop(struct ieee80211_hw *hw) /* reset sec info */ rtl_cam_reset_sec_info(hw); - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); } rtlpriv->intf_ops->adapter_stop(hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index d7331225c5f3..457a0f725c8a 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -2359,7 +2359,7 @@ void rtl_pci_disconnect(struct pci_dev *pdev) ieee80211_unregister_hw(hw); rtlmac->mac80211_registered = 0; } else { - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); rtlpriv->intf_ops->adapter_stop(hw); } rtlpriv->cfg->ops->disable_interrupt(hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.c b/drivers/net/wireless/realtek/rtlwifi/ps.c index 07ee3096f50e..f6d00613c53d 100644 --- a/drivers/net/wireless/realtek/rtlwifi/ps.c +++ b/drivers/net/wireless/realtek/rtlwifi/ps.c @@ -66,7 +66,7 @@ bool rtl_ps_disable_nic(struct ieee80211_hw *hw) struct rtl_priv *rtlpriv = rtl_priv(hw); /*<1> Stop all timer */ - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, true); /*<2> Disable Interrupt */ rtlpriv->cfg->ops->disable_interrupt(hw); @@ -287,7 +287,7 @@ void rtl_ips_nic_on(struct ieee80211_hw *hw) struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); enum rf_pwrstate rtstate; - cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); + cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq); spin_lock(&rtlpriv->locks.ips_lock); if (ppsc->inactiveps) { diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index 5590d07d0918..820c42ff5384 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -1150,7 +1150,7 @@ void rtl_usb_disconnect(struct usb_interface *intf) ieee80211_unregister_hw(hw); rtlmac->mac80211_registered = 0; } else { - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); rtlpriv->intf_ops->adapter_stop(hw); } /*deinit rfkill */ diff --git a/drivers/pci/dwc/pci-exynos.c b/drivers/pci/dwc/pci-exynos.c index 5596fdedbb94..ea03f1ec12a4 100644 --- a/drivers/pci/dwc/pci-exynos.c +++ b/drivers/pci/dwc/pci-exynos.c @@ -695,7 +695,8 @@ static int __init exynos_pcie_probe(struct platform_device *pdev) return ret; } - if (ep->ops && ep->ops->get_clk_resources) { + if (ep->ops && ep->ops->get_clk_resources && + ep->ops->init_clk_resources) { ret = ep->ops->get_clk_resources(ep); if (ret) return ret; diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c index caea7c618207..4523d7e1bcb9 100644 --- a/drivers/pci/host/pci-hyperv.c +++ b/drivers/pci/host/pci-hyperv.c @@ -1091,6 +1091,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_bus *pbus; struct pci_dev *pdev; struct cpumask *dest; + unsigned long flags; struct compose_comp_ctxt comp; struct tran_int_desc *int_desc; struct { @@ -1182,14 +1183,15 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) * the channel callback directly when channel->target_cpu is * the current CPU. When the higher level interrupt code * calls us with interrupt enabled, let's add the - * local_bh_disable()/enable() to avoid race. + * local_irq_save()/restore() to avoid race: + * hv_pci_onchannelcallback() can also run in tasklet. */ - local_bh_disable(); + local_irq_save(flags); if (hbus->hdev->channel->target_cpu == smp_processor_id()) hv_pci_onchannelcallback(hbus); - local_bh_enable(); + local_irq_restore(flags); if (hpdev->state == hv_pcichild_ejecting) { dev_err_once(&hbus->hdev->device, diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 00b8d4cdcac3..c01d1f3a1c7d 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -366,7 +366,7 @@ int xhci_find_slot_id_by_port(struct usb_hcd *hcd, struct xhci_hcd *xhci, slot_id = 0; for (i = 0; i < MAX_HC_SLOTS; i++) { - if (!xhci->devs[i]) + if (!xhci->devs[i] || !xhci->devs[i]->udev) continue; speed = xhci->devs[i]->udev->speed; if (((speed >= USB_SPEED_SUPER) == (hcd->speed >= HCD_USB3)) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index b0d606b2d06c..6123b4dd8638 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1186,7 +1186,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) if (ubufs) vhost_net_ubuf_put_wait_and_free(ubufs); err_ubufs: - sockfd_put(sock); + if (sock) + sockfd_put(sock); err_vq: mutex_unlock(&vq->mutex); err: diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index b7c816f39404..6dd63981787a 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -148,6 +148,15 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) cmd); goto out; } + } else { + unsigned int inr = _IOC_NR(cmd); + + if (inr == AUTOFS_DEV_IOCTL_OPENMOUNT_CMD || + inr == AUTOFS_DEV_IOCTL_REQUESTER_CMD || + inr == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) { + err = -EINVAL; + goto out; + } } err = 0; @@ -284,7 +293,8 @@ static int autofs_dev_ioctl_openmount(struct file *fp, dev_t devid; int err, fd; - /* param->path has already been checked */ + /* param->path has been checked in validate_dev_ioctl() */ + if (!param->openmount.devid) return -EINVAL; @@ -446,10 +456,7 @@ static int autofs_dev_ioctl_requester(struct file *fp, dev_t devid; int err = -ENOENT; - if (param->size <= AUTOFS_DEV_IOCTL_SIZE) { - err = -EINVAL; - goto out; - } + /* param->path has been checked in validate_dev_ioctl() */ devid = sbi->sb->s_dev; @@ -534,10 +541,7 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp, unsigned int devid, magic; int err = -ENOENT; - if (param->size <= AUTOFS_DEV_IOCTL_SIZE) { - err = -EINVAL; - goto out; - } + /* param->path has been checked in validate_dev_ioctl() */ name = param->path; type = param->ismountpoint.in.type; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fc4c14a72366..bf4e22df7c97 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4214,6 +4214,110 @@ static int log_one_extent(struct btrfs_trans_handle *trans, return ret; } +/* + * Log all prealloc extents beyond the inode's i_size to make sure we do not + * lose them after doing a fast fsync and replaying the log. We scan the + * subvolume's root instead of iterating the inode's extent map tree because + * otherwise we can log incorrect extent items based on extent map conversion. + * That can happen due to the fact that extent maps are merged when they + * are not in the extent map tree's list of modified extents. + */ +static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode, + struct btrfs_path *path) +{ + struct btrfs_root *root = inode->root; + struct btrfs_key key; + const u64 i_size = i_size_read(&inode->vfs_inode); + const u64 ino = btrfs_ino(inode); + struct btrfs_path *dst_path = NULL; + u64 last_extent = (u64)-1; + int ins_nr = 0; + int start_slot; + int ret; + + if (!(inode->flags & BTRFS_INODE_PREALLOC)) + return 0; + + key.objectid = ino; + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = i_size; + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out; + + while (true) { + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + + if (slot >= btrfs_header_nritems(leaf)) { + if (ins_nr > 0) { + ret = copy_items(trans, inode, dst_path, path, + &last_extent, start_slot, + ins_nr, 1, 0); + if (ret < 0) + goto out; + ins_nr = 0; + } + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto out; + if (ret > 0) { + ret = 0; + break; + } + continue; + } + + btrfs_item_key_to_cpu(leaf, &key, slot); + if (key.objectid > ino) + break; + if (WARN_ON_ONCE(key.objectid < ino) || + key.type < BTRFS_EXTENT_DATA_KEY || + key.offset < i_size) { + path->slots[0]++; + continue; + } + if (last_extent == (u64)-1) { + last_extent = key.offset; + /* + * Avoid logging extent items logged in past fsync calls + * and leading to duplicate keys in the log tree. + */ + do { + ret = btrfs_truncate_inode_items(trans, + root->log_root, + &inode->vfs_inode, + i_size, + BTRFS_EXTENT_DATA_KEY); + } while (ret == -EAGAIN); + if (ret) + goto out; + } + if (ins_nr == 0) + start_slot = slot; + ins_nr++; + path->slots[0]++; + if (!dst_path) { + dst_path = btrfs_alloc_path(); + if (!dst_path) { + ret = -ENOMEM; + goto out; + } + } + } + if (ins_nr > 0) { + ret = copy_items(trans, inode, dst_path, path, &last_extent, + start_slot, ins_nr, 1, 0); + if (ret > 0) + ret = 0; + } +out: + btrfs_release_path(path); + btrfs_free_path(dst_path); + return ret; +} + static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_inode *inode, @@ -4256,6 +4360,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, if (em->generation <= test_gen) continue; + /* We log prealloc extents beyond eof later. */ + if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) && + em->start >= i_size_read(&inode->vfs_inode)) + continue; + if (em->start < logged_start) logged_start = em->start; if ((em->start + em->len - 1) > logged_end) @@ -4268,31 +4377,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, num++; } - /* - * Add all prealloc extents beyond the inode's i_size to make sure we - * don't lose them after doing a fast fsync and replaying the log. - */ - if (inode->flags & BTRFS_INODE_PREALLOC) { - struct rb_node *node; - - for (node = rb_last(&tree->map); node; node = rb_prev(node)) { - em = rb_entry(node, struct extent_map, rb_node); - if (em->start < i_size_read(&inode->vfs_inode)) - break; - if (!list_empty(&em->list)) - continue; - /* Same as above loop. */ - if (++num > 32768) { - list_del_init(&tree->modified_extents); - ret = -EFBIG; - goto process; - } - refcount_inc(&em->refs); - set_bit(EXTENT_FLAG_LOGGING, &em->flags); - list_add_tail(&em->list, &extents); - } - } - list_sort(NULL, &extents, extent_cmp); btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end); /* @@ -4337,6 +4421,9 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, up_write(&inode->dio_sem); btrfs_release_path(path); + if (!ret) + ret = btrfs_log_prealloc_extents(trans, inode, path); + return ret; } diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 88a31e9340a0..d1516327b787 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -134,6 +134,19 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock, return err; } +static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + int ret = 0; + struct ocfs2_inode_info *oi = OCFS2_I(inode); + + down_read(&oi->ip_alloc_sem); + ret = ocfs2_get_block(inode, iblock, bh_result, create); + up_read(&oi->ip_alloc_sem); + + return ret; +} + int ocfs2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -2128,7 +2141,7 @@ static void ocfs2_dio_free_write_ctx(struct inode *inode, * called like this: dio->get_blocks(dio->inode, fs_startblk, * fs_count, map_bh, dio->rw == WRITE); */ -static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock, +static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); @@ -2154,12 +2167,9 @@ static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock, * while file size will be changed. */ if (pos + total_len <= i_size_read(inode)) { - down_read(&oi->ip_alloc_sem); - /* This is the fast path for re-write. */ - ret = ocfs2_get_block(inode, iblock, bh_result, create); - - up_read(&oi->ip_alloc_sem); + /* This is the fast path for re-write. */ + ret = ocfs2_lock_get_block(inode, iblock, bh_result, create); if (buffer_mapped(bh_result) && !buffer_new(bh_result) && ret == 0) @@ -2424,9 +2434,9 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) return 0; if (iov_iter_rw(iter) == READ) - get_block = ocfs2_get_block; + get_block = ocfs2_lock_get_block; else - get_block = ocfs2_dio_get_block; + get_block = ocfs2_dio_wr_get_block; return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index b17d180bdc16..c204ac9b49e5 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -40,6 +40,9 @@ char *o2nm_fence_method_desc[O2NM_FENCE_METHODS] = { "panic", /* O2NM_FENCE_PANIC */ }; +static inline void o2nm_lock_subsystem(void); +static inline void o2nm_unlock_subsystem(void); + struct o2nm_node *o2nm_get_node_by_num(u8 node_num) { struct o2nm_node *node = NULL; @@ -181,7 +184,10 @@ static struct o2nm_cluster *to_o2nm_cluster_from_node(struct o2nm_node *node) { /* through the first node_set .parent * mycluster/nodes/mynode == o2nm_cluster->o2nm_node_group->o2nm_node */ - return to_o2nm_cluster(node->nd_item.ci_parent->ci_parent); + if (node->nd_item.ci_parent) + return to_o2nm_cluster(node->nd_item.ci_parent->ci_parent); + else + return NULL; } enum { @@ -194,7 +200,7 @@ static ssize_t o2nm_node_num_store(struct config_item *item, const char *page, size_t count) { struct o2nm_node *node = to_o2nm_node(item); - struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node); + struct o2nm_cluster *cluster; unsigned long tmp; char *p = (char *)page; int ret = 0; @@ -214,6 +220,13 @@ static ssize_t o2nm_node_num_store(struct config_item *item, const char *page, !test_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes)) return -EINVAL; /* XXX */ + o2nm_lock_subsystem(); + cluster = to_o2nm_cluster_from_node(node); + if (!cluster) { + o2nm_unlock_subsystem(); + return -EINVAL; + } + write_lock(&cluster->cl_nodes_lock); if (cluster->cl_nodes[tmp]) ret = -EEXIST; @@ -226,6 +239,8 @@ static ssize_t o2nm_node_num_store(struct config_item *item, const char *page, set_bit(tmp, cluster->cl_nodes_bitmap); } write_unlock(&cluster->cl_nodes_lock); + o2nm_unlock_subsystem(); + if (ret) return ret; @@ -269,7 +284,7 @@ static ssize_t o2nm_node_ipv4_address_store(struct config_item *item, size_t count) { struct o2nm_node *node = to_o2nm_node(item); - struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node); + struct o2nm_cluster *cluster; int ret, i; struct rb_node **p, *parent; unsigned int octets[4]; @@ -286,6 +301,13 @@ static ssize_t o2nm_node_ipv4_address_store(struct config_item *item, be32_add_cpu(&ipv4_addr, octets[i] << (i * 8)); } + o2nm_lock_subsystem(); + cluster = to_o2nm_cluster_from_node(node); + if (!cluster) { + o2nm_unlock_subsystem(); + return -EINVAL; + } + ret = 0; write_lock(&cluster->cl_nodes_lock); if (o2nm_node_ip_tree_lookup(cluster, ipv4_addr, &p, &parent)) @@ -298,6 +320,8 @@ static ssize_t o2nm_node_ipv4_address_store(struct config_item *item, rb_insert_color(&node->nd_ip_node, &cluster->cl_node_ip_tree); } write_unlock(&cluster->cl_nodes_lock); + o2nm_unlock_subsystem(); + if (ret) return ret; @@ -315,7 +339,7 @@ static ssize_t o2nm_node_local_store(struct config_item *item, const char *page, size_t count) { struct o2nm_node *node = to_o2nm_node(item); - struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node); + struct o2nm_cluster *cluster; unsigned long tmp; char *p = (char *)page; ssize_t ret; @@ -333,17 +357,26 @@ static ssize_t o2nm_node_local_store(struct config_item *item, const char *page, !test_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes)) return -EINVAL; /* XXX */ + o2nm_lock_subsystem(); + cluster = to_o2nm_cluster_from_node(node); + if (!cluster) { + ret = -EINVAL; + goto out; + } + /* the only failure case is trying to set a new local node * when a different one is already set */ if (tmp && tmp == cluster->cl_has_local && - cluster->cl_local_node != node->nd_num) - return -EBUSY; + cluster->cl_local_node != node->nd_num) { + ret = -EBUSY; + goto out; + } /* bring up the rx thread if we're setting the new local node. */ if (tmp && !cluster->cl_has_local) { ret = o2net_start_listening(node); if (ret) - return ret; + goto out; } if (!tmp && cluster->cl_has_local && @@ -358,7 +391,11 @@ static ssize_t o2nm_node_local_store(struct config_item *item, const char *page, cluster->cl_local_node = node->nd_num; } - return count; + ret = count; + +out: + o2nm_unlock_subsystem(); + return ret; } CONFIGFS_ATTR(o2nm_node_, num); @@ -738,6 +775,16 @@ static struct o2nm_cluster_group o2nm_cluster_group = { }, }; +static inline void o2nm_lock_subsystem(void) +{ + mutex_lock(&o2nm_cluster_group.cs_subsys.su_mutex); +} + +static inline void o2nm_unlock_subsystem(void) +{ + mutex_unlock(&o2nm_cluster_group.cs_subsys.su_mutex); +} + int o2nm_depend_item(struct config_item *item) { return configfs_depend_item(&o2nm_cluster_group.cs_subsys, item); diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index 64f49cafbc5b..cfb0c9ac2de4 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -76,83 +76,99 @@ static char *le_type(struct reiserfs_key *key) } /* %k */ -static void sprintf_le_key(char *buf, struct reiserfs_key *key) +static int scnprintf_le_key(char *buf, size_t size, struct reiserfs_key *key) { if (key) - sprintf(buf, "[%d %d %s %s]", le32_to_cpu(key->k_dir_id), - le32_to_cpu(key->k_objectid), le_offset(key), - le_type(key)); + return scnprintf(buf, size, "[%d %d %s %s]", + le32_to_cpu(key->k_dir_id), + le32_to_cpu(key->k_objectid), le_offset(key), + le_type(key)); else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } /* %K */ -static void sprintf_cpu_key(char *buf, struct cpu_key *key) +static int scnprintf_cpu_key(char *buf, size_t size, struct cpu_key *key) { if (key) - sprintf(buf, "[%d %d %s %s]", key->on_disk_key.k_dir_id, - key->on_disk_key.k_objectid, reiserfs_cpu_offset(key), - cpu_type(key)); + return scnprintf(buf, size, "[%d %d %s %s]", + key->on_disk_key.k_dir_id, + key->on_disk_key.k_objectid, + reiserfs_cpu_offset(key), cpu_type(key)); else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } -static void sprintf_de_head(char *buf, struct reiserfs_de_head *deh) +static int scnprintf_de_head(char *buf, size_t size, + struct reiserfs_de_head *deh) { if (deh) - sprintf(buf, - "[offset=%d dir_id=%d objectid=%d location=%d state=%04x]", - deh_offset(deh), deh_dir_id(deh), deh_objectid(deh), - deh_location(deh), deh_state(deh)); + return scnprintf(buf, size, + "[offset=%d dir_id=%d objectid=%d location=%d state=%04x]", + deh_offset(deh), deh_dir_id(deh), + deh_objectid(deh), deh_location(deh), + deh_state(deh)); else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } -static void sprintf_item_head(char *buf, struct item_head *ih) +static int scnprintf_item_head(char *buf, size_t size, struct item_head *ih) { if (ih) { - strcpy(buf, - (ih_version(ih) == KEY_FORMAT_3_6) ? "*3.6* " : "*3.5*"); - sprintf_le_key(buf + strlen(buf), &(ih->ih_key)); - sprintf(buf + strlen(buf), ", item_len %d, item_location %d, " - "free_space(entry_count) %d", - ih_item_len(ih), ih_location(ih), ih_free_space(ih)); + char *p = buf; + char * const end = buf + size; + + p += scnprintf(p, end - p, "%s", + (ih_version(ih) == KEY_FORMAT_3_6) ? + "*3.6* " : "*3.5*"); + + p += scnprintf_le_key(p, end - p, &ih->ih_key); + + p += scnprintf(p, end - p, + ", item_len %d, item_location %d, free_space(entry_count) %d", + ih_item_len(ih), ih_location(ih), + ih_free_space(ih)); + return p - buf; } else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } -static void sprintf_direntry(char *buf, struct reiserfs_dir_entry *de) +static int scnprintf_direntry(char *buf, size_t size, + struct reiserfs_dir_entry *de) { char name[20]; memcpy(name, de->de_name, de->de_namelen > 19 ? 19 : de->de_namelen); name[de->de_namelen > 19 ? 19 : de->de_namelen] = 0; - sprintf(buf, "\"%s\"==>[%d %d]", name, de->de_dir_id, de->de_objectid); + return scnprintf(buf, size, "\"%s\"==>[%d %d]", + name, de->de_dir_id, de->de_objectid); } -static void sprintf_block_head(char *buf, struct buffer_head *bh) +static int scnprintf_block_head(char *buf, size_t size, struct buffer_head *bh) { - sprintf(buf, "level=%d, nr_items=%d, free_space=%d rdkey ", - B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh)); + return scnprintf(buf, size, + "level=%d, nr_items=%d, free_space=%d rdkey ", + B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh)); } -static void sprintf_buffer_head(char *buf, struct buffer_head *bh) +static int scnprintf_buffer_head(char *buf, size_t size, struct buffer_head *bh) { - sprintf(buf, - "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)", - bh->b_bdev, bh->b_size, - (unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)), - bh->b_state, bh->b_page, - buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE", - buffer_dirty(bh) ? "DIRTY" : "CLEAN", - buffer_locked(bh) ? "LOCKED" : "UNLOCKED"); + return scnprintf(buf, size, + "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)", + bh->b_bdev, bh->b_size, + (unsigned long long)bh->b_blocknr, + atomic_read(&(bh->b_count)), + bh->b_state, bh->b_page, + buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE", + buffer_dirty(bh) ? "DIRTY" : "CLEAN", + buffer_locked(bh) ? "LOCKED" : "UNLOCKED"); } -static void sprintf_disk_child(char *buf, struct disk_child *dc) +static int scnprintf_disk_child(char *buf, size_t size, struct disk_child *dc) { - sprintf(buf, "[dc_number=%d, dc_size=%u]", dc_block_number(dc), - dc_size(dc)); + return scnprintf(buf, size, "[dc_number=%d, dc_size=%u]", + dc_block_number(dc), dc_size(dc)); } static char *is_there_reiserfs_struct(char *fmt, int *what) @@ -189,55 +205,60 @@ static void prepare_error_buf(const char *fmt, va_list args) char *fmt1 = fmt_buf; char *k; char *p = error_buf; + char * const end = &error_buf[sizeof(error_buf)]; int what; spin_lock(&error_lock); - strcpy(fmt1, fmt); + if (WARN_ON(strscpy(fmt_buf, fmt, sizeof(fmt_buf)) < 0)) { + strscpy(error_buf, "format string too long", end - error_buf); + goto out_unlock; + } while ((k = is_there_reiserfs_struct(fmt1, &what)) != NULL) { *k = 0; - p += vsprintf(p, fmt1, args); + p += vscnprintf(p, end - p, fmt1, args); switch (what) { case 'k': - sprintf_le_key(p, va_arg(args, struct reiserfs_key *)); + p += scnprintf_le_key(p, end - p, + va_arg(args, struct reiserfs_key *)); break; case 'K': - sprintf_cpu_key(p, va_arg(args, struct cpu_key *)); + p += scnprintf_cpu_key(p, end - p, + va_arg(args, struct cpu_key *)); break; case 'h': - sprintf_item_head(p, va_arg(args, struct item_head *)); + p += scnprintf_item_head(p, end - p, + va_arg(args, struct item_head *)); break; case 't': - sprintf_direntry(p, - va_arg(args, - struct reiserfs_dir_entry *)); + p += scnprintf_direntry(p, end - p, + va_arg(args, struct reiserfs_dir_entry *)); break; case 'y': - sprintf_disk_child(p, - va_arg(args, struct disk_child *)); + p += scnprintf_disk_child(p, end - p, + va_arg(args, struct disk_child *)); break; case 'z': - sprintf_block_head(p, - va_arg(args, struct buffer_head *)); + p += scnprintf_block_head(p, end - p, + va_arg(args, struct buffer_head *)); break; case 'b': - sprintf_buffer_head(p, - va_arg(args, struct buffer_head *)); + p += scnprintf_buffer_head(p, end - p, + va_arg(args, struct buffer_head *)); break; case 'a': - sprintf_de_head(p, - va_arg(args, - struct reiserfs_de_head *)); + p += scnprintf_de_head(p, end - p, + va_arg(args, struct reiserfs_de_head *)); break; } - p += strlen(p); fmt1 = k + 2; } - vsprintf(p, fmt1, args); + p += vscnprintf(p, end - p, fmt1, args); +out_unlock: spin_unlock(&error_lock); } diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index a031897fca76..ca1d2cc2cdfa 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -80,6 +80,11 @@ ARM_SMCCC_SMC_32, \ 0, 0x8000) +#define ARM_SMCCC_ARCH_WORKAROUND_2 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x7fff) + #ifndef __ASSEMBLY__ #include @@ -291,5 +296,10 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, */ #define arm_smccc_1_1_hvc(...) __arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__) +/* Return codes defined in ARM DEN 0070A */ +#define SMCCC_RET_SUCCESS 0 +#define SMCCC_RET_NOT_SUPPORTED -1 +#define SMCCC_RET_NOT_REQUIRED -2 + #endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 0c27515d2cf6..8124815eb121 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -214,6 +214,7 @@ struct atmphy_ops { struct atm_skb_data { struct atm_vcc *vcc; /* ATM VCC */ unsigned long atm_options; /* ATM layer options */ + unsigned int acct_truesize; /* truesize accounted to vcc */ }; #define VCC_HTABLE_SIZE 32 @@ -241,6 +242,20 @@ void vcc_insert_socket(struct sock *sk); void atm_dev_release_vccs(struct atm_dev *dev); +static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb) +{ + /* + * Because ATM skbs may not belong to a sock (and we don't + * necessarily want to), skb->truesize may be adjusted, + * escaping the hack in pskb_expand_head() which avoids + * doing so for some cases. So stash the value of truesize + * at the time we accounted it, and atm_pop_raw() can use + * that value later, in case it changes. + */ + refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + ATM_SKB(skb)->acct_truesize = skb->truesize; + ATM_SKB(skb)->atm_options = vcc->atm_options; +} static inline void atm_force_charge(struct atm_vcc *vcc,int truesize) { diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index eac387a3bfef..3c1beffc861a 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -22,7 +22,6 @@ struct dentry; */ enum wb_state { WB_registered, /* bdi_register() was done */ - WB_shutting_down, /* wb_shutdown() in progress */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ }; @@ -165,6 +164,7 @@ struct backing_dev_info { #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ + struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ #else struct bdi_writeback_congested *wb_congested; #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index f43113b8890b..c11032b06d68 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -65,6 +65,18 @@ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #endif +/* + * Feature detection for gnu_inline (gnu89 extern inline semantics). Either + * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics, + * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not + * defined so the gnu89 semantics are the default. + */ +#ifdef __GNUC_STDC_INLINE__ +# define __gnu_inline __attribute__((gnu_inline)) +#else +# define __gnu_inline +#endif + /* * Force always-inline if the user requests it so via the .config, * or if gcc is too old. @@ -72,19 +84,22 @@ * -Wunused-function. This turns out to avoid the need for complex #ifdef * directives. Suppress the warning in clang as well by using "unused" * function attribute, which is redundant but not harmful for gcc. + * Prefer gnu_inline, so that extern inline functions do not emit an + * externally visible function. This makes extern inline behave as per gnu89 + * semantics rather than c99. This prevents multiple symbol definition errors + * of extern inline functions at link time. + * A lot of inline functions can cause havoc with function tracing. */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) -#define inline inline __attribute__((always_inline,unused)) notrace -#define __inline__ __inline__ __attribute__((always_inline,unused)) notrace -#define __inline __inline __attribute__((always_inline,unused)) notrace +#define inline \ + inline __attribute__((always_inline, unused)) notrace __gnu_inline #else -/* A lot of inline functions can cause havoc with function tracing */ -#define inline inline __attribute__((unused)) notrace -#define __inline__ __inline__ __attribute__((unused)) notrace -#define __inline __inline __attribute__((unused)) notrace +#define inline inline __attribute__((unused)) notrace __gnu_inline #endif +#define __inline__ inline +#define __inline inline #define __always_inline inline __attribute__((always_inline)) #define noinline __attribute__((noinline)) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f3765155fa4d..1d793d86d55f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -857,7 +857,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_1a4[0x1]; u8 ets[0x1]; u8 nic_flow_table[0x1]; - u8 eswitch_flow_table[0x1]; + u8 eswitch_manager[0x1]; u8 early_vf_enable[0x1]; u8 mcam_reg[0x1]; u8 pcam_reg[0x1]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 46bf7cc7d5d5..2ea7ee1fb495 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2668,11 +2668,31 @@ static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff **pp, + int flush, + struct gro_remcsum *grc) +{ + if (PTR_ERR(pp) != -EINPROGRESS) { + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; + } +} #else static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff **pp, + int flush, + struct gro_remcsum *grc) +{ + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; +} #endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, diff --git a/include/linux/string.h b/include/linux/string.h index cfd83eb2f926..96115bf561b4 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -28,7 +28,7 @@ extern char * strncpy(char *,const char *, __kernel_size_t); size_t strlcpy(char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRSCPY -ssize_t __must_check strscpy(char *, const char *, size_t); +ssize_t strscpy(char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRCAT extern char * strcat(char *, const char *); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 03918a19cf2d..3b71d859ee38 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -322,6 +322,8 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) { unsigned long flags; + INIT_LIST_HEAD(&cs->wd_list); + spin_lock_irqsave(&watchdog_lock, flags); if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { /* cs is a clocksource to be watched. */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6774e0369ebe..9386c98dac12 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -356,15 +356,8 @@ static void wb_shutdown(struct bdi_writeback *wb) spin_lock_bh(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_bh(&wb->work_lock); - /* - * Wait for wb shutdown to finish if someone else is just - * running wb_shutdown(). Otherwise we could proceed to wb / - * bdi destruction before wb_shutdown() is finished. - */ - wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE); return; } - set_bit(WB_shutting_down, &wb->state); spin_unlock_bh(&wb->work_lock); cgwb_remove_from_bdi_list(wb); @@ -376,12 +369,6 @@ static void wb_shutdown(struct bdi_writeback *wb) mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); - /* - * Make sure bit gets cleared after shutdown is finished. Matches with - * the barrier provided by test_and_clear_bit() above. - */ - smp_wmb(); - clear_and_wake_up_bit(WB_shutting_down, &wb->state); } static void wb_exit(struct bdi_writeback *wb) @@ -505,10 +492,12 @@ static void cgwb_release_workfn(struct work_struct *work) struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); + mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); css_put(wb->memcg_css); css_put(wb->blkcg_css); + mutex_unlock(&wb->bdi->cgwb_release_mutex); fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); @@ -694,6 +683,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); bdi->cgwb_congested_tree = RB_ROOT; + mutex_init(&bdi->cgwb_release_mutex); ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (!ret) { @@ -714,7 +704,10 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi) spin_lock_irq(&cgwb_lock); radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); + spin_unlock_irq(&cgwb_lock); + mutex_lock(&bdi->cgwb_release_mutex); + spin_lock_irq(&cgwb_lock); while (!list_empty(&bdi->wb_list)) { wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); @@ -723,6 +716,7 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi) spin_lock_irq(&cgwb_lock); } spin_unlock_irq(&cgwb_lock); + mutex_unlock(&bdi->cgwb_release_mutex); } /** diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index cf2e70003a53..cf82d970b0e4 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -664,7 +664,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 4e111196f902..bc21f8e8daf2 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -252,8 +252,7 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev); - refcount_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = atmvcc->atm_options; + atm_account_tx(atmvcc, skb); dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; diff --git a/net/atm/clip.c b/net/atm/clip.c index 65f706e4344c..60920a42f640 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -381,8 +381,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, memcpy(here, llc_oui, sizeof(llc_oui)); ((__be16 *) here)[3] = skb->protocol; } - refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = vcc->atm_options; + atm_account_tx(vcc, skb); entry->vccs->last_use = jiffies; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, vcc, vcc->dev); old = xchg(&entry->vccs->xoff, 1); /* assume XOFF ... */ diff --git a/net/atm/common.c b/net/atm/common.c index 8a4f99114cd2..9e812c782a37 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -630,10 +630,9 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) goto out; } pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); - refcount_add(skb->truesize, &sk->sk_wmem_alloc); + atm_account_tx(vcc, skb); skb->dev = NULL; /* for paths shared with net_device interfaces */ - ATM_SKB(skb)->atm_options = vcc->atm_options; if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) { kfree_skb(skb); error = -EFAULT; diff --git a/net/atm/lec.c b/net/atm/lec.c index 5741b6474dd9..9f2365694ad4 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -182,9 +182,8 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb) struct net_device *dev = skb->dev; ATM_SKB(skb)->vcc = vcc; - ATM_SKB(skb)->atm_options = vcc->atm_options; + atm_account_tx(vcc, skb); - refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); if (vcc->send(vcc, skb) < 0) { dev->stats.tx_dropped++; return; diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 5677147209e8..db9a1838687c 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -555,8 +555,7 @@ static int send_via_shortcut(struct sk_buff *skb, struct mpoa_client *mpc) sizeof(struct llc_snap_hdr)); } - refcount_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = entry->shortcut->atm_options; + atm_account_tx(entry->shortcut, skb); entry->shortcut->send(entry->shortcut, skb); entry->packets_fwded++; mpc->in_ops->put(entry); diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index 21d9d341a619..af8c4b38b746 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -350,8 +350,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) return 1; } - refcount_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options; + atm_account_tx(vcc, skb); pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev); ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb) diff --git a/net/atm/raw.c b/net/atm/raw.c index ee10e8d46185..b3ba44aab0ee 100644 --- a/net/atm/raw.c +++ b/net/atm/raw.c @@ -35,8 +35,8 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb) struct sock *sk = sk_atm(vcc); pr_debug("(%d) %d -= %d\n", - vcc->vci, sk_wmem_alloc_get(sk), skb->truesize); - WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); + vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize); + WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc)); dev_kfree_skb_any(skb); sk->sk_write_space(sk); } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 25738b20676d..54c7fe68040f 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -398,6 +398,12 @@ ebt_check_watcher(struct ebt_entry_watcher *w, struct xt_tgchk_param *par, watcher = xt_request_find_target(NFPROTO_BRIDGE, w->u.name, 0); if (IS_ERR(watcher)) return PTR_ERR(watcher); + + if (watcher->family != NFPROTO_BRIDGE) { + module_put(watcher->me); + return -ENOENT; + } + w->u.watcher = watcher; par->target = watcher; @@ -719,6 +725,13 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, goto cleanup_watchers; } + /* Reject UNSPEC, xtables verdicts/return values are incompatible */ + if (target->family != NFPROTO_BRIDGE) { + module_put(target->me); + ret = -ENOENT; + goto cleanup_watchers; + } + t->u.target = target; if (t->u.target == &ebt_standard_target) { if (gap < sizeof(struct ebt_standard_target)) { diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 119c04317d48..03fcf3ee1534 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -599,7 +599,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); struct dccp_sock *dp = dccp_sk(sk); - ktime_t now = ktime_get_real(); + ktime_t now = ktime_get(); s64 delta = 0; switch (fbtype) { @@ -624,15 +624,14 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, case CCID3_FBACK_PERIODIC: delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback); if (delta <= 0) - DCCP_BUG("delta (%ld) <= 0", (long)delta); - else - hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta); + delta = 1; + hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta); break; default: return; } - ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n", (long)delta, + ccid3_pr_debug("Interval %lldusec, X_recv=%u, 1/p=%u\n", delta, hc->rx_x_recv, hc->rx_pinv); hc->rx_tstamp_last_feedback = now; @@ -679,7 +678,8 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) static u32 ccid3_first_li(struct sock *sk) { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); - u32 x_recv, p, delta; + u32 x_recv, p; + s64 delta; u64 fval; if (hc->rx_rtt == 0) { @@ -687,7 +687,9 @@ static u32 ccid3_first_li(struct sock *sk) hc->rx_rtt = DCCP_FALLBACK_RTT; } - delta = ktime_to_us(net_timedelta(hc->rx_tstamp_last_feedback)); + delta = ktime_us_delta(ktime_get(), hc->rx_tstamp_last_feedback); + if (delta <= 0) + delta = 1; x_recv = scaled_div32(hc->rx_bytes_recv, delta); if (x_recv == 0) { /* would also trigger divide-by-zero */ DCCP_WARN("X_recv==0\n"); diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index f0252768ecf4..5f5d9eafccf5 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -87,35 +87,39 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) opt++; kdebug("options: '%s'", opt); do { + int opt_len, opt_nlen; const char *eq; - int opt_len, opt_nlen, opt_vlen, tmp; + char optval[128]; next_opt = memchr(opt, '#', end - opt) ?: end; opt_len = next_opt - opt; - if (opt_len <= 0 || opt_len > 128) { + if (opt_len <= 0 || opt_len > sizeof(optval)) { pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n", opt_len); return -EINVAL; } - eq = memchr(opt, '=', opt_len) ?: end; - opt_nlen = eq - opt; - eq++; - opt_vlen = next_opt - eq; /* will be -1 if no value */ + eq = memchr(opt, '=', opt_len); + if (eq) { + opt_nlen = eq - opt; + eq++; + memcpy(optval, eq, next_opt - eq); + optval[next_opt - eq] = '\0'; + } else { + opt_nlen = opt_len; + optval[0] = '\0'; + } - tmp = opt_vlen >= 0 ? opt_vlen : 0; - kdebug("option '%*.*s' val '%*.*s'", - opt_nlen, opt_nlen, opt, tmp, tmp, eq); + kdebug("option '%*.*s' val '%s'", + opt_nlen, opt_nlen, opt, optval); /* see if it's an error number representing a DNS error * that's to be recorded as the result in this key */ if (opt_nlen == sizeof(DNS_ERRORNO_OPTION) - 1 && memcmp(opt, DNS_ERRORNO_OPTION, opt_nlen) == 0) { kdebug("dns error number option"); - if (opt_vlen <= 0) - goto bad_option_value; - ret = kstrtoul(eq, 10, &derrno); + ret = kstrtoul(optval, 10, &derrno); if (ret < 0) goto bad_option_value; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 1540db65241a..c9ec1603666b 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -448,9 +448,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, &grc); - skb->remcsum_offload = 0; + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 1859c473b21a..6a7d980105f6 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -223,7 +223,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e7d15fb0d94d..24b066c32e06 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -188,9 +188,9 @@ static inline int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score += 4; } if (sk->sk_incoming_cpu == raw_smp_processor_id()) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0989e739d098..5a29dc5083a3 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -258,8 +258,9 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, { struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; - int ret; u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */ + __le32 key[4]; + int ret, i; tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); if (!tbl.data) @@ -268,11 +269,14 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, rcu_read_lock(); ctxt = rcu_dereference(tcp_fastopen_ctx); if (ctxt) - memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); + memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); else - memset(user_key, 0, sizeof(user_key)); + memset(key, 0, sizeof(key)); rcu_read_unlock(); + for (i = 0; i < ARRAY_SIZE(key); i++) + user_key[i] = le32_to_cpu(key[i]); + snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x", user_key[0], user_key[1], user_key[2], user_key[3]); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); @@ -288,12 +292,16 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, * first invocation of tcp_fastopen_cookie_gen */ tcp_fastopen_init_key_once(false); - tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH); + + for (i = 0; i < ARRAY_SIZE(user_key); i++) + key[i] = cpu_to_le32(user_key[i]); + + tcp_fastopen_reset_cipher(key, TCP_FASTOPEN_KEY_LENGTH); } bad_key: pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", - user_key[0], user_key[1], user_key[2], user_key[3], + user_key[0], user_key[1], user_key[2], user_key[3], (char *)tbl.data, ret); kfree(tbl.data); return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f0caff3139ed..5711b1b12d28 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3194,6 +3194,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (tcp_is_reno(tp)) { tcp_remove_reno_sacks(sk, pkts_acked); + + /* If any of the cumulatively ACKed segments was + * retransmitted, non-SACK case cannot confirm that + * progress was due to original transmission due to + * lack of TCPCB_SACKED_ACKED bits even if some of + * the packets may have been never retransmitted. + */ + if (flag & FLAG_RETRANS_DATA_ACKED) + flag &= ~FLAG_ORIG_SACK_ACKED; } else { int delta; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index ea6e6e7df0ee..cde2719fcb89 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -295,7 +295,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b01858f5deb1..6dc93ac28261 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -113,9 +113,9 @@ static inline int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score++; } if (sk->sk_incoming_cpu == raw_smp_processor_id()) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 64ec23388450..722a9db8c6a7 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -618,6 +618,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) fq->q.meat == fq->q.len && nf_ct_frag6_reasm(fq, skb, dev)) ret = 0; + else + skb_dst_drop(skb); out_unlock: spin_unlock_bh(&fq->q.lock); diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 33fb35cbfac1..558fe8cc6d43 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -373,7 +373,7 @@ static int seg6_hmac_init_algo(void) return -ENOMEM; for_each_possible_cpu(cpu) { - tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL); + tfm = crypto_alloc_shash(algo->name, 0, 0); if (IS_ERR(tfm)) return PTR_ERR(tfm); p_tfm = per_cpu_ptr(algo->tfms, cpu); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 2ceefa183cee..6a196e438b6c 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -752,11 +752,14 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); - pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT, + pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, 0, frag_len + LLCP_HEADER_SIZE, &err); if (pdu == NULL) { - pr_err("Could not allocate PDU\n"); - continue; + pr_err("Could not allocate PDU (error=%d)\n", err); + len -= remaining_len; + if (len == 0) + len = err; + break; } pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI); diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 6df6f58a8103..5647905c88d6 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -42,7 +42,7 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, __skb_pull(skb, nsh_len); skb_reset_mac_header(skb); - skb_reset_mac_len(skb); + skb->mac_len = proto == htons(ETH_P_TEB) ? ETH_HLEN : 0; skb->protocol = proto; features &= NETIF_F_SG; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4fe2e34522d6..27dafe36f29c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2303,6 +2303,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (po->stats.stats1.tp_drops) status |= TP_STATUS_LOSING; } + + if (do_vnet && + virtio_net_hdr_from_skb(skb, h.raw + macoff - + sizeof(struct virtio_net_hdr), + vio_le(), true, 0)) + goto drop_n_account; + po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; @@ -2310,15 +2317,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } spin_unlock(&sk->sk_receive_queue.lock); - if (do_vnet) { - if (virtio_net_hdr_from_skb(skb, h.raw + macoff - - sizeof(struct virtio_net_hdr), - vio_le(), true, 0)) { - spin_lock(&sk->sk_receive_queue.lock); - goto drop_n_account; - } - } - skb_copy_bits(skb, 0, h.raw + macoff, snaplen); if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp))) diff --git a/net/rds/loop.c b/net/rds/loop.c index f2bf78de5688..dac6218a460e 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.c @@ -193,4 +193,5 @@ struct rds_transport rds_loop_transport = { .inc_copy_to_user = rds_message_inc_copy_to_user, .inc_free = rds_loop_inc_free, .t_name = "loopback", + .t_type = RDS_TRANS_LOOP, }; diff --git a/net/rds/rds.h b/net/rds/rds.h index d09f6c1facb4..f685d8b514e5 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -454,6 +454,11 @@ struct rds_notifier { int n_status; }; +/* Available as part of RDS core, so doesn't need to participate + * in get_preferred transport etc + */ +#define RDS_TRANS_LOOP 3 + /** * struct rds_transport - transport specific behavioural hooks * diff --git a/net/rds/recv.c b/net/rds/recv.c index 555f07ccf0dc..c27cceae52e1 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -103,6 +103,11 @@ static void rds_recv_rcvbuf_delta(struct rds_sock *rs, struct sock *sk, rds_stats_add(s_recv_bytes_added_to_socket, delta); else rds_stats_add(s_recv_bytes_removed_from_socket, -delta); + + /* loop transport doesn't send/recv congestion updates */ + if (rs->rs_transport->t_type == RDS_TRANS_LOOP) + return; + now_congested = rs->rs_rcv_bytes > rds_sk_rcvbuf(rs); rdsdebug("rs %p (%pI4:%u) recv bytes %d buf %d " diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c index c98a61e980ba..9c4c2bb547d7 100644 --- a/net/sched/sch_blackhole.c +++ b/net/sched/sch_blackhole.c @@ -21,7 +21,7 @@ static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { qdisc_drop(skb, sch, to_free); - return NET_XMIT_SUCCESS; + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } static struct sk_buff *blackhole_dequeue(struct Qdisc *sch) diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index c741365f77da..a68c754e84ea 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -35,7 +35,6 @@ struct _strp_msg { */ struct strp_msg strp; int accum_len; - int early_eaten; }; static inline struct _strp_msg *_strp_msg(struct sk_buff *skb) @@ -115,20 +114,6 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, head = strp->skb_head; if (head) { /* Message already in progress */ - - stm = _strp_msg(head); - if (unlikely(stm->early_eaten)) { - /* Already some number of bytes on the receive sock - * data saved in skb_head, just indicate they - * are consumed. - */ - eaten = orig_len <= stm->early_eaten ? - orig_len : stm->early_eaten; - stm->early_eaten -= eaten; - - return eaten; - } - if (unlikely(orig_offset)) { /* Getting data with a non-zero offset when a message is * in progress is not expected. If it does happen, we @@ -297,9 +282,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, } stm->accum_len += cand_len; + eaten += cand_len; strp->need_bytes = stm->strp.full_len - stm->accum_len; - stm->early_eaten = cand_len; STRP_STATS_ADD(strp->stats.bytes, cand_len); desc->count = 0; /* Stop reading socket */ break; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 97b9d4f671ac..2aaf46599126 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -270,7 +270,6 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) wait_for_completion(&ia->ri_remove_done); ia->ri_id = NULL; - ia->ri_pd = NULL; ia->ri_device = NULL; /* Return 1 to ensure the core destroys the id. */ return 1; @@ -464,7 +463,9 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) ia->ri_id->qp = NULL; } ib_free_cq(ep->rep_attr.recv_cq); + ep->rep_attr.recv_cq = NULL; ib_free_cq(ep->rep_attr.send_cq); + ep->rep_attr.send_cq = NULL; /* The ULP is responsible for ensuring all DMA * mappings and MRs are gone. @@ -477,6 +478,8 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) rpcrdma_dma_unmap_regbuf(req->rl_recvbuf); } rpcrdma_destroy_mrs(buf); + ib_dealloc_pd(ia->ri_pd); + ia->ri_pd = NULL; /* Allow waiters to continue */ complete(&ia->ri_remove_done); @@ -650,14 +653,16 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) cancel_delayed_work_sync(&ep->rep_connect_worker); - if (ia->ri_id->qp) { + if (ia->ri_id && ia->ri_id->qp) { rpcrdma_ep_disconnect(ep, ia); rdma_destroy_qp(ia->ri_id); ia->ri_id->qp = NULL; } - ib_free_cq(ep->rep_attr.recv_cq); - ib_free_cq(ep->rep_attr.send_cq); + if (ep->rep_attr.recv_cq) + ib_free_cq(ep->rep_attr.recv_cq); + if (ep->rep_attr.send_cq) + ib_free_cq(ep->rep_attr.send_cq); } /* Re-establish a connection after a device removal event. diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 3c86614462f6..8ee4e667a414 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -449,7 +449,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) ret = tls_push_record(sk, msg->msg_flags, record_type); if (!ret) continue; - if (ret == -EAGAIN) + if (ret < 0) goto send_end; copied -= try_to_copy; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 403d86e80162..fdb294441682 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -201,7 +201,7 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt) return -ENODEV; } - if (le32_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) + if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) return virtio_transport_send_pkt_loopback(vsock, pkt); if (pkt->reply) diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 9bee849db682..d5f1d8364571 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -51,8 +51,8 @@ __asm__(".arch_extension virt"); #endif +DEFINE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state); static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); -static kvm_cpu_context_t __percpu *kvm_host_cpu_state; /* Per-CPU variable containing the currently running vcpu. */ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu); @@ -351,7 +351,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } vcpu->cpu = cpu; - vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state); + vcpu->arch.host_cpu_context = this_cpu_ptr(&kvm_host_cpu_state); kvm_arm_set_running_vcpu(vcpu); @@ -1259,19 +1259,8 @@ static inline void hyp_cpu_pm_exit(void) } #endif -static void teardown_common_resources(void) -{ - free_percpu(kvm_host_cpu_state); -} - static int init_common_resources(void) { - kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t); - if (!kvm_host_cpu_state) { - kvm_err("Cannot allocate host CPU state\n"); - return -ENOMEM; - } - /* set size of VMID supported by CPU */ kvm_vmid_bits = kvm_get_vmid_bits(); kvm_info("%d-bit VMID\n", kvm_vmid_bits); @@ -1413,7 +1402,7 @@ static int init_hyp_mode(void) for_each_possible_cpu(cpu) { kvm_cpu_context_t *cpu_ctxt; - cpu_ctxt = per_cpu_ptr(kvm_host_cpu_state, cpu); + cpu_ctxt = per_cpu_ptr(&kvm_host_cpu_state, cpu); err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1, PAGE_HYP); if (err) { @@ -1422,6 +1411,10 @@ static int init_hyp_mode(void) } } + err = hyp_map_aux_data(); + if (err) + kvm_err("Cannot map host auxilary data: %d\n", err); + return 0; out_err: @@ -1497,7 +1490,6 @@ int kvm_arch_init(void *opaque) if (!in_hyp_mode) teardown_hyp_mode(); out_err: - teardown_common_resources(); return err; } diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c index d7fd46fe9efb..4b4221b0d4ba 100644 --- a/virt/kvm/arm/hyp/vgic-v2-sr.c +++ b/virt/kvm/arm/hyp/vgic-v2-sr.c @@ -139,7 +139,7 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) return -1; rd = kvm_vcpu_dabt_get_rd(vcpu); - addr = kern_hyp_va((kern_hyp_va(&kvm_vgic_global_state))->vcpu_base_va); + addr = kern_hyp_va(hyp_symbol_addr(kvm_vgic_global_state)->vcpu_base_va); addr += fault_ipa - vgic->vgic_cpu_base; if (kvm_vcpu_dabt_iswrite(vcpu)) { diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index c4762bef13c6..c95ab4c5a475 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -405,7 +405,7 @@ static int kvm_psci_call(struct kvm_vcpu *vcpu) int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) { u32 func_id = smccc_get_function(vcpu); - u32 val = PSCI_RET_NOT_SUPPORTED; + u32 val = SMCCC_RET_NOT_SUPPORTED; u32 feature; switch (func_id) { @@ -417,7 +417,21 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) switch(feature) { case ARM_SMCCC_ARCH_WORKAROUND_1: if (kvm_arm_harden_branch_predictor()) - val = 0; + val = SMCCC_RET_SUCCESS; + break; + case ARM_SMCCC_ARCH_WORKAROUND_2: + switch (kvm_arm_have_ssbd()) { + case KVM_SSBD_FORCE_DISABLE: + case KVM_SSBD_UNKNOWN: + break; + case KVM_SSBD_KERNEL: + val = SMCCC_RET_SUCCESS; + break; + case KVM_SSBD_FORCE_ENABLE: + case KVM_SSBD_MITIGATED: + val = SMCCC_RET_NOT_REQUIRED; + break; + } break; } break;