diff options
100 files changed, 1061 insertions, 494 deletions
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index a1f28a54f23a..60c4c342316c 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -244,6 +244,17 @@ ENTRY(__switch_to_asm) movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset #endif +#ifdef CONFIG_RETPOLINE + /* + * When switching from a shallower to a deeper call stack + * the RSB may either underflow or use entries populated + * with userspace addresses. On CPUs where those concerns + * exist, overwrite the RSB with entries which capture + * speculative execution to prevent attack. + */ + FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW +#endif + /* restore callee-saved registers */ popl %esi popl %edi diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4f8e1d35a97c..aa15b4c0e3d1 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -491,6 +491,17 @@ ENTRY(__switch_to_asm) movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset #endif +#ifdef CONFIG_RETPOLINE + /* + * When switching from a shallower to a deeper call stack + * the RSB may either underflow or use entries populated + * with userspace addresses. On CPUs where those concerns + * exist, overwrite the RSB with entries which capture + * speculative execution to prevent attack. + */ + FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW +#endif + /* restore callee-saved registers */ popq %r15 popq %r14 diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 005908ee9333..a2efb490f743 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -755,14 +755,14 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsx_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsx_rapl_init), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsx_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init), diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a9e57f08bfa6..98722773391d 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -136,6 +136,7 @@ extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); extern void lapic_shutdown(void); extern void sync_Arb_IDs(void); +extern void init_bsp_APIC(void); extern void apic_intr_mode_init(void); extern void setup_local_APIC(void); extern void init_apic_mappings(void); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index f275447862f4..25b9375c1484 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -206,11 +206,11 @@ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ #define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -245,6 +245,7 @@ #define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ #define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index c9459a4c3c68..22c5f3e6f820 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -39,7 +39,7 @@ void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); -void __init sme_encrypt_kernel(void); +void __init sme_encrypt_kernel(struct boot_params *bp); void __init sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); @@ -67,7 +67,7 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } -static inline void __init sme_encrypt_kernel(void) { } +static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } static inline void __init sme_enable(struct boot_params *bp) { } static inline bool sme_active(void) { return false; } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 402a11c803c3..7b45d8424150 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -11,7 +11,7 @@ * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; jmp' loop to capture speculative execution. + * infinite 'pause; lfence; jmp' loop to capture speculative execution. * * This is required in various cases for retpoline and IBRS-based * mitigations for the Spectre variant 2 vulnerability. Sometimes to @@ -38,11 +38,13 @@ call 772f; \ 773: /* speculation trap */ \ pause; \ + lfence; \ jmp 773b; \ 772: \ call 774f; \ 775: /* speculation trap */ \ pause; \ + lfence; \ jmp 775b; \ 774: \ dec reg; \ @@ -73,6 +75,7 @@ call .Ldo_rop_\@ .Lspec_trap_\@: pause + lfence jmp .Lspec_trap_\@ .Ldo_rop_\@: mov \reg, (%_ASM_SP) @@ -165,6 +168,7 @@ " .align 16\n" \ "901: call 903f;\n" \ "902: pause;\n" \ + " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ "903: addl $4, %%esp;\n" \ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 880441f24146..25ddf02598d2 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1286,6 +1286,55 @@ static int __init apic_intr_mode_select(void) return APIC_SYMMETRIC_IO; } +/* + * An initial setup of the virtual wire mode. + */ +void __init init_bsp_APIC(void) +{ + unsigned int value; + + /* + * Don't do the setup now if we have a SMP BIOS as the + * through-I/O-APIC virtual wire mode might be active. + */ + if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC)) + return; + + /* + * Do not trust the local APIC being empty at bootup. + */ + clear_local_APIC(); + + /* + * Enable APIC. + */ + value = apic_read(APIC_SPIV); + value &= ~APIC_VECTOR_MASK; + value |= APIC_SPIV_APIC_ENABLED; + +#ifdef CONFIG_X86_32 + /* This bit is reserved on P4/Xeon and should be cleared */ + if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && + (boot_cpu_data.x86 == 15)) + value &= ~APIC_SPIV_FOCUS_DISABLED; + else +#endif + value |= APIC_SPIV_FOCUS_DISABLED; + value |= SPURIOUS_APIC_VECTOR; + apic_write(APIC_SPIV, value); + + /* + * Set up the virtual wire mode. + */ + apic_write(APIC_LVT0, APIC_DM_EXTINT); + value = APIC_DM_NMI; + if (!lapic_is_integrated()) /* 82489DX */ + value |= APIC_LVT_LEVEL_TRIGGER; + if (apic_extnmi == APIC_EXTNMI_NONE) + value |= APIC_LVT_MASKED; + apic_write(APIC_LVT1, value); +} + /* Init the interrupt delivery mode for the BSP */ void __init apic_intr_mode_init(void) { diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index f8b03bb8e725..3cc471beb50b 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -542,14 +542,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, err = assign_irq_vector_policy(irqd, info); trace_vector_setup(virq + i, false, err); - if (err) + if (err) { + irqd->chip_data = NULL; + free_apic_chip_data(apicd); goto error; + } } return 0; error: - x86_vector_free_irqs(domain, virq, i + 1); + x86_vector_free_irqs(domain, virq, i); return err; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index e4dc26185aa7..390b3dc3d438 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -23,6 +23,7 @@ #include <asm/alternative.h> #include <asm/pgtable.h> #include <asm/set_memory.h> +#include <asm/intel-family.h> static void __init spectre_v2_select_mitigation(void); @@ -155,6 +156,23 @@ disable: return SPECTRE_V2_CMD_NONE; } +/* Check for Skylake-like CPUs (for RSB handling) */ +static bool __init is_skylake_era(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + boot_cpu_data.x86 == 6) { + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + return true; + } + } + return false; +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -213,6 +231,24 @@ retpoline_auto: spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); + + /* + * If neither SMEP or KPTI are available, there is a risk of + * hitting userspace addresses in the RSB after a context switch + * from a shallow call stack to a deeper one. To prevent this fill + * the entire RSB, even when using IBRS. + * + * Skylake era CPUs have a separate issue with *underflow* of the + * RSB, when they will predict 'ret' targets from the generic BTB. + * The proper mitigation for this is IBRS. If IBRS is not supported + * or deactivated in favour of retpolines the RSB fill on context + * switch is required. + */ + if ((!boot_cpu_has(X86_FEATURE_PTI) && + !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { + setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); + pr_info("Filling RSB on context switch\n"); + } } #undef pr_fmt diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 88dcf8479013..99442370de40 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -525,10 +525,6 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) */ if (static_branch_unlikely(&rdt_mon_enable_key)) rmdir_mondata_subdir_allrdtgrp(r, d->id); - kfree(d->ctrl_val); - kfree(d->rmid_busy_llc); - kfree(d->mbm_total); - kfree(d->mbm_local); list_del(&d->list); if (is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); @@ -545,6 +541,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cancel_delayed_work(&d->cqm_limbo); } + kfree(d->ctrl_val); + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + kfree(d->mbm_local); kfree(d); return; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 05459ad3db46..d0e69769abfd 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -21,7 +21,6 @@ struct cpuid_bit { static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 }, { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 }, { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 6a5d757b9cfd..7ba5d819ebe3 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -157,8 +157,8 @@ unsigned long __head __startup_64(unsigned long physaddr, p = fixup_pointer(&phys_base, physaddr); *p += load_delta - sme_get_me_mask(); - /* Encrypt the kernel (if SME is active) */ - sme_encrypt_kernel(); + /* Encrypt the kernel and related (if SME is active) */ + sme_encrypt_kernel(bp); /* * Return the SME encryption mask (if SME is active) to be used as a diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index d985cef3984f..56d99be3706a 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -56,7 +56,7 @@ struct idt_data { * Early traps running on the DEFAULT_STACK because the other interrupt * stacks work only after cpu_init(). */ -static const __initdata struct idt_data early_idts[] = { +static const __initconst struct idt_data early_idts[] = { INTG(X86_TRAP_DB, debug), SYSG(X86_TRAP_BP, int3), #ifdef CONFIG_X86_32 @@ -70,7 +70,7 @@ static const __initdata struct idt_data early_idts[] = { * the traps which use them are reinitialized with IST after cpu_init() has * set up TSS. */ -static const __initdata struct idt_data def_idts[] = { +static const __initconst struct idt_data def_idts[] = { INTG(X86_TRAP_DE, divide_error), INTG(X86_TRAP_NMI, nmi), INTG(X86_TRAP_BR, bounds), @@ -108,7 +108,7 @@ static const __initdata struct idt_data def_idts[] = { /* * The APIC and SMP idt entries */ -static const __initdata struct idt_data apic_idts[] = { +static const __initconst struct idt_data apic_idts[] = { #ifdef CONFIG_SMP INTG(RESCHEDULE_VECTOR, reschedule_interrupt), INTG(CALL_FUNCTION_VECTOR, call_function_interrupt), @@ -150,7 +150,7 @@ static const __initdata struct idt_data apic_idts[] = { * Early traps running on the DEFAULT_STACK because the other interrupt * stacks work only after cpu_init(). */ -static const __initdata struct idt_data early_pf_idts[] = { +static const __initconst struct idt_data early_pf_idts[] = { INTG(X86_TRAP_PF, page_fault), }; @@ -158,7 +158,7 @@ static const __initdata struct idt_data early_pf_idts[] = { * Override for the debug_idt. Same as the default, but with interrupt * stack set to DEFAULT_STACK (0). Required for NMI trap handling. */ -static const __initdata struct idt_data dbg_idts[] = { +static const __initconst struct idt_data dbg_idts[] = { INTG(X86_TRAP_DB, debug), INTG(X86_TRAP_BP, int3), }; @@ -180,7 +180,7 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss; * The exceptions which use Interrupt stacks. They are setup after * cpu_init() when the TSS has been initialized. */ -static const __initdata struct idt_data ist_idts[] = { +static const __initconst struct idt_data ist_idts[] = { ISTG(X86_TRAP_DB, debug, DEBUG_STACK), ISTG(X86_TRAP_NMI, nmi, NMI_STACK), SISTG(X86_TRAP_BP, int3, DEBUG_STACK), diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 8da3e909e967..a539410c4ea9 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -61,6 +61,9 @@ void __init init_ISA_irqs(void) struct irq_chip *chip = legacy_pic->chip; int i; +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) + init_bsp_APIC(); +#endif legacy_pic->init(0); for (i = 0; i < nr_legacy_irqs(); i++) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 145810b0edf6..68d7ab81c62f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -364,16 +364,6 @@ static void __init reserve_initrd(void) !ramdisk_image || !ramdisk_size) return; /* No initrd provided by bootloader */ - /* - * If SME is active, this memory will be marked encrypted by the - * kernel when it is accessed (including relocation). However, the - * ramdisk image was loaded decrypted by the bootloader, so make - * sure that it is encrypted before accessing it. For SEV the - * ramdisk will already be encrypted, so only do this for SME. - */ - if (sme_active()) - sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image); - initrd_start = 0; mapped_size = memblock_mem_size(max_pfn_mapped); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 8ea117f8142e..e169e85db434 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -602,7 +602,6 @@ unsigned long native_calibrate_tsc(void) case INTEL_FAM6_KABYLAKE_DESKTOP: crystal_khz = 24000; /* 24.0 MHz */ break; - case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ATOM_DENVERTON: crystal_khz = 25000; /* 25.0 MHz */ break; @@ -612,6 +611,8 @@ unsigned long native_calibrate_tsc(void) } } + if (crystal_khz == 0) + return 0; /* * TSC frequency determined by CPUID is a "hardware reported" * frequency and is the most accurate one so far we have. This @@ -1315,6 +1316,12 @@ void __init tsc_init(void) (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); + if (cpu_khz != tsc_khz) { + pr_info("Detected %lu.%03lu MHz TSC", + (unsigned long)tsc_khz / 1000, + (unsigned long)tsc_khz % 1000); + } + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ tsc_store_and_check_tsc_adjust(true); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 06fe3d51d385..b3e40773dce0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -172,14 +172,15 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ -static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) +static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info, + u32 *pkey) { /* This is effectively an #ifdef */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return; /* Fault not from Protection Keys: nothing to do */ - if (si_code != SEGV_PKUERR) + if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV)) return; /* * force_sig_info_fault() is called from a number of @@ -218,7 +219,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, lsb = PAGE_SHIFT; info.si_addr_lsb = lsb; - fill_sig_info_pkey(si_code, &info, pkey); + fill_sig_info_pkey(si_signo, si_code, &info, pkey); force_sig_info(si_signo, &info, tsk); } diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 47388f0c0e59..af6f2f9c6a26 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -21,10 +21,14 @@ extern struct range pfn_mapped[E820_MAX_ENTRIES]; static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); -static __init void *early_alloc(size_t size, int nid) +static __init void *early_alloc(size_t size, int nid, bool panic) { - return memblock_virt_alloc_try_nid_nopanic(size, size, - __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + if (panic) + return memblock_virt_alloc_try_nid(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + else + return memblock_virt_alloc_try_nid_nopanic(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); } static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, @@ -38,14 +42,14 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, if (boot_cpu_has(X86_FEATURE_PSE) && ((end - addr) == PMD_SIZE) && IS_ALIGNED(addr, PMD_SIZE)) { - p = early_alloc(PMD_SIZE, nid); + p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; else if (p) memblock_free(__pa(p), PMD_SIZE); } - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pmd_populate_kernel(&init_mm, pmd, p); } @@ -57,7 +61,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, if (!pte_none(*pte)) continue; - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL); set_pte_at(&init_mm, addr, pte, entry); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -75,14 +79,14 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, if (boot_cpu_has(X86_FEATURE_GBPAGES) && ((end - addr) == PUD_SIZE) && IS_ALIGNED(addr, PUD_SIZE)) { - p = early_alloc(PUD_SIZE, nid); + p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; else if (p) memblock_free(__pa(p), PUD_SIZE); } - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pud_populate(&init_mm, pud, p); } @@ -101,7 +105,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, unsigned long next; if (p4d_none(*p4d)) { - void *p = early_alloc(PAGE_SIZE, nid); + void *p = early_alloc(PAGE_SIZE, nid, true); p4d_populate(&init_mm, p4d, p); } @@ -122,7 +126,7 @@ static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr, unsigned long next; if (pgd_none(*pgd)) { - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pgd_populate(&init_mm, pgd, p); } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 391b13402e40..3ef362f598e3 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -464,37 +464,62 @@ void swiotlb_set_mem_attributes(void *vaddr, unsigned long size) set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT); } -static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start, - unsigned long end) +struct sme_populate_pgd_data { + void *pgtable_area; + pgd_t *pgd; + + pmdval_t pmd_flags; + pteval_t pte_flags; + unsigned long paddr; + + unsigned long vaddr; + unsigned long vaddr_end; +}; + +static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) { unsigned long pgd_start, pgd_end, pgd_size; pgd_t *pgd_p; - pgd_start = start & PGDIR_MASK; - pgd_end = end & PGDIR_MASK; + pgd_start = ppd->vaddr & PGDIR_MASK; + pgd_end = ppd->vaddr_end & PGDIR_MASK; - pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1); - pgd_size *= sizeof(pgd_t); + pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t); - pgd_p = pgd_base + pgd_index(start); + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); memset(pgd_p, 0, pgd_size); } -#define PGD_FLAGS _KERNPG_TABLE_NOENC -#define P4D_FLAGS _KERNPG_TABLE_NOENC -#define PUD_FLAGS _KERNPG_TABLE_NOENC -#define PMD_FLAGS (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) +#define PGD_FLAGS _KERNPG_TABLE_NOENC +#define P4D_FLAGS _KERNPG_TABLE_NOENC +#define PUD_FLAGS _KERNPG_TABLE_NOENC +#define PMD_FLAGS _KERNPG_TABLE_NOENC + +#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) + +#define PMD_FLAGS_DEC PMD_FLAGS_LARGE +#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) + +#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL) + +#define PTE_FLAGS_DEC PTE_FLAGS +#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC) -static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, - unsigned long vaddr, pmdval_t pmd_val) +static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) { pgd_t *pgd_p; p4d_t *p4d_p; pud_t *pud_p; pmd_t *pmd_p; - pgd_p = pgd_base + pgd_index(vaddr); + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); if (native_pgd_val(*pgd_p)) { if (IS_ENABLED(CONFIG_X86_5LEVEL)) p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); @@ -504,15 +529,15 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, pgd_t pgd; if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p = pgtable_area; + p4d_p = ppd->pgtable_area; memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); - pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; + ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS); } else { - pud_p = pgtable_area; + pud_p = ppd->pgtable_area; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS); } @@ -520,58 +545,160 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, } if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p += p4d_index(vaddr); + p4d_p += p4d_index(ppd->vaddr); if (native_p4d_val(*p4d_p)) { pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK); } else { p4d_t p4d; - pud_p = pgtable_area; + pud_p = ppd->pgtable_area; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS); native_set_p4d(p4d_p, p4d); } } - pud_p += pud_index(vaddr); + pud_p += pud_index(ppd->vaddr); if (native_pud_val(*pud_p)) { if (native_pud_val(*pud_p) & _PAGE_PSE) - goto out; + return NULL; pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK); } else { pud_t pud; - pmd_p = pgtable_area; + pmd_p = ppd->pgtable_area; memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); - pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; + ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS); native_set_pud(pud_p, pud); } - pmd_p += pmd_index(vaddr); + return pmd_p; +} + +static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +{ + pmd_t *pmd_p; + + pmd_p = sme_prepare_pgd(ppd); + if (!pmd_p) + return; + + pmd_p += pmd_index(ppd->vaddr); if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE)) - native_set_pmd(pmd_p, native_make_pmd(pmd_val)); + native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags)); +} -out: - return pgtable_area; +static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +{ + pmd_t *pmd_p; + pte_t *pte_p; + + pmd_p = sme_prepare_pgd(ppd); + if (!pmd_p) + return; + + pmd_p += pmd_index(ppd->vaddr); + if (native_pmd_val(*pmd_p)) { + if (native_pmd_val(*pmd_p) & _PAGE_PSE) + return; + + pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK); + } else { + pmd_t pmd; + + pte_p = ppd->pgtable_area; + memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE); + ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE; + + pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS); + native_set_pmd(pmd_p, pmd); + } + + pte_p += pte_index(ppd->vaddr); + if (!native_pte_val(*pte_p)) + native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags)); +} + +static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd_large(ppd); + + ppd->vaddr += PMD_PAGE_SIZE; + ppd->paddr += PMD_PAGE_SIZE; + } +} + +static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd(ppd); + + ppd->vaddr += PAGE_SIZE; + ppd->paddr += PAGE_SIZE; + } +} + +static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, + pmdval_t pmd_flags, pteval_t pte_flags) +{ + unsigned long vaddr_end; + + ppd->pmd_flags = pmd_flags; + ppd->pte_flags = pte_flags; + + /* Save original end value since we modify the struct value */ + vaddr_end = ppd->vaddr_end; + + /* If start is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE); + __sme_map_range_pte(ppd); + + /* Create PMD entries */ + ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK; + __sme_map_range_pmd(ppd); + + /* If end is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = vaddr_end; + __sme_map_range_pte(ppd); +} + +static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); +} + +static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); +} + +static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); } static unsigned long __init sme_pgtable_calc(unsigned long len) { - unsigned long p4d_size, pud_size, pmd_size; + unsigned long p4d_size, pud_size, pmd_size, pte_size; unsigned long total; /* * Perform a relatively simplistic calculation of the pagetable - * entries that are needed. That mappings will be covered by 2MB - * PMD entries so we can conservatively calculate the required + * entries that are needed. Those mappings will be covered mostly + * by 2MB PMD entries so we can conservatively calculate the required * number of P4D, PUD and PMD structures needed to perform the - * mappings. Incrementing the count for each covers the case where - * the addresses cross entries. + * mappings. For mappings that are not 2MB aligned, PTE mappings + * would be needed for the start and end portion of the address range + * that fall outside of the 2MB alignment. This results in, at most, + * two extra pages to hold PTE entries for each range that is mapped. + * Incrementing the count for each covers the case where the addresses + * cross entries. */ if (IS_ENABLED(CONFIG_X86_5LEVEL)) { p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; @@ -585,8 +712,9 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) } pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1; pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; + pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE; - total = p4d_size + pud_size + pmd_size; + total = p4d_size + pud_size + pmd_size + pte_size; /* * Now calculate the added pagetable structures needed to populate @@ -610,29 +738,29 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) return total; } -void __init sme_encrypt_kernel(void) +void __init sme_encrypt_kernel(struct boot_params *bp) { unsigned long workarea_start, workarea_end, workarea_len; unsigned long execute_start, execute_end, execute_len; unsigned long kernel_start, kernel_end, kernel_len; + unsigned long initrd_start, initrd_end, initrd_len; + struct sme_populate_pgd_data ppd; unsigned long pgtable_area_len; - unsigned long paddr, pmd_flags; unsigned long decrypted_base; - void *pgtable_area; - pgd_t *pgd; if (!sme_active()) return; /* - * Prepare for encrypting the kernel by building new pagetables with - * the necessary attributes needed to encrypt the kernel in place. + * Prepare for encrypting the kernel and initrd by building new + * pagetables with the necessary attributes needed to encrypt the + * kernel in place. * * One range of virtual addresses will map the memory occupied - * by the kernel as encrypted. + * by the kernel and initrd as encrypted. * * Another range of virtual addresses will map the memory occupied - * by the kernel as decrypted and write-protected. + * by the kernel and initrd as decrypted and write-protected. * * The use of write-protect attribute will prevent any of the * memory from being cached. @@ -643,6 +771,20 @@ void __init sme_encrypt_kernel(void) kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE); kernel_len = kernel_end - kernel_start; + initrd_start = 0; + initrd_end = 0; + initrd_len = 0; +#ifdef CONFIG_BLK_DEV_INITRD + initrd_len = (unsigned long)bp->hdr.ramdisk_size | + ((unsigned long)bp->ext_ramdisk_size << 32); + if (initrd_len) { + initrd_start = (unsigned long)bp->hdr.ramdisk_image | + ((unsigned long)bp->ext_ramdisk_image << 32); + initrd_end = PAGE_ALIGN(initrd_start + initrd_len); + initrd_len = initrd_end - initrd_start; + } +#endif + /* Set the encryption workarea to be immediately after the kernel */ workarea_start = kernel_end; @@ -665,16 +807,21 @@ void __init sme_encrypt_kernel(void) */ pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD; pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2; + if (initrd_len) + pgtable_area_len += sme_pgtable_calc(initrd_len) * 2; /* PUDs and PMDs needed in the current pagetables for the workarea */ pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len); /* * The total workarea includes the executable encryption area and - * the pagetable area. + * the pagetable area. The start of the workarea is already 2MB + * aligned, align the end of the workarea on a 2MB boundary so that + * we don't try to create/allocate PTE entries from the workarea + * before it is mapped. */ workarea_len = execute_len + pgtable_area_len; - workarea_end = workarea_start + workarea_len; + workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE); /* * Set the address to the start of where newly created pagetable @@ -683,45 +830,30 @@ void __init sme_encrypt_kernel(void) * pagetables and when the new encrypted and decrypted kernel * mappings are populated. */ - pgtable_area = (void *)execute_end; + ppd.pgtable_area = (void *)execute_end; /* * Make sure the current pagetable structure has entries for * addressing the workarea. */ - pgd = (pgd_t *)native_read_cr3_pa(); - paddr = workarea_start; - while (paddr < workarea_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + PMD_FLAGS); - - paddr += PMD_PAGE_SIZE; - } + ppd.pgd = (pgd_t *)native_read_cr3_pa(); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); /* * A new pagetable structure is being built to allow for the kernel - * to be encrypted. It starts with an empty PGD that will then be - * populated with new PUDs and PMDs as the encrypted and decrypted - * kernel mappings are created. + * and initrd to be encrypted. It starts with an empty PGD that will + * then be populated with new PUDs and PMDs as the encrypted and + * decrypted kernel mappings are created. */ - pgd = pgtable_area; - memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD); - pgtable_area += sizeof(*pgd) * PTRS_PER_PGD; - - /* Add encrypted kernel (identity) mappings */ - pmd_flags = PMD_FLAGS | _PAGE_ENC; - paddr = kernel_start; - while (paddr < kernel_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + pmd_flags); - - paddr += PMD_PAGE_SIZE; - } + ppd.pgd = ppd.pgtable_area; + memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD); + ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD; /* * A different PGD index/entry must be used to get different @@ -730,47 +862,79 @@ void __init sme_encrypt_kernel(void) * the base of the mapping. */ decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1); + if (initrd_len) { + unsigned long check_base; + + check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1); + decrypted_base = max(decrypted_base, check_base); + } decrypted_base <<= PGDIR_SHIFT; + /* Add encrypted kernel (identity) mappings */ + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start; + ppd.vaddr_end = kernel_end; + sme_map_range_encrypted(&ppd); + /* Add decrypted, write-protected kernel (non-identity) mappings */ - pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT); - paddr = kernel_start; - while (paddr < kernel_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr + decrypted_base, - paddr + pmd_flags); - - paddr += PMD_PAGE_SIZE; + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); + + if (initrd_len) { + /* Add encrypted initrd (identity) mappings */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start; + ppd.vaddr_end = initrd_end; + sme_map_range_encrypted(&ppd); + /* + * Add decrypted, write-protected initrd (non-identity) mappings + */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); } /* Add decrypted workarea mappings to both kernel mappings */ - paddr = workarea_start; - while (paddr < workarea_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + PMD_FLAGS); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr + decrypted_base, - paddr + PMD_FLAGS); - - paddr += PMD_PAGE_SIZE; - } + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_map_range_decrypted(&ppd); /* Perform the encryption */ sme_encrypt_execute(kernel_start, kernel_start + decrypted_base, - kernel_len, workarea_start, (unsigned long)pgd); + kernel_len, workarea_start, (unsigned long)ppd.pgd); + + if (initrd_len) + sme_encrypt_execute(initrd_start, initrd_start + decrypted_base, + initrd_len, workarea_start, + (unsigned long)ppd.pgd); /* * At this point we are running encrypted. Remove the mappings for * the decrypted areas - all that is needed for this is to remove * the PGD entry/entries. */ - sme_clear_pgd(pgd, kernel_start + decrypted_base, - kernel_end + decrypted_base); + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_clear_pgd(&ppd); + + if (initrd_len) { + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_clear_pgd(&ppd); + } - sme_clear_pgd(pgd, workarea_start + decrypted_base, - workarea_end + decrypted_base); + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_clear_pgd(&ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 730e6d541df1..01f682cf77a8 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -22,9 +22,9 @@ ENTRY(sme_encrypt_execute) /* * Entry parameters: - * RDI - virtual address for the encrypted kernel mapping - * RSI - virtual address for the decrypted kernel mapping - * RDX - length of kernel + * RDI - virtual address for the encrypted mapping + * RSI - virtual address for the decrypted mapping + * RDX - length to encrypt * RCX - virtual address of the encryption workarea, including: * - stack page (PAGE_SIZE) * - encryption routine page (PAGE_SIZE) @@ -41,9 +41,9 @@ ENTRY(sme_encrypt_execute) addq $PAGE_SIZE, %rax /* Workarea encryption routine */ push %r12 - movq %rdi, %r10 /* Encrypted kernel */ - movq %rsi, %r11 /* Decrypted kernel */ - movq %rdx, %r12 /* Kernel length */ + movq %rdi, %r10 /* Encrypted area */ + movq %rsi, %r11 /* Decrypted area */ + movq %rdx, %r12 /* Area length */ /* Copy encryption routine into the workarea */ movq %rax, %rdi /* Workarea encryption routine */ @@ -52,10 +52,10 @@ ENTRY(sme_encrypt_execute) rep movsb /* Setup registers for call */ - movq %r10, %rdi /* Encrypted kernel */ - movq %r11, %rsi /* Decrypted kernel */ + movq %r10, %rdi /* Encrypted area */ + movq %r11, %rsi /* Decrypted area */ movq %r8, %rdx /* Pagetables used for encryption */ - movq %r12, %rcx /* Kernel length */ + movq %r12, %rcx /* Area length */ movq %rax, %r8 /* Workarea encryption routine */ addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ @@ -71,7 +71,7 @@ ENDPROC(sme_encrypt_execute) ENTRY(__enc_copy) /* - * Routine used to encrypt kernel. + * Routine used to encrypt memory in place. * This routine must be run outside of the kernel proper since * the kernel will be encrypted during the process. So this * routine is defined here and then copied to an area outside @@ -79,19 +79,19 @@ ENTRY(__enc_copy) * during execution. * * On entry the registers must be: - * RDI - virtual address for the encrypted kernel mapping - * RSI - virtual address for the decrypted kernel mapping + * RDI - virtual address for the encrypted mapping + * RSI - virtual address for the decrypted mapping * RDX - address of the pagetables to use for encryption - * RCX - length of kernel + * RCX - length of area * R8 - intermediate copy buffer * * RAX - points to this routine * - * The kernel will be encrypted by copying from the non-encrypted - * kernel space to an intermediate buffer and then copying from the - * intermediate buffer back to the encrypted kernel space. The physical - * addresses of the two kernel space mappings are the same which - * results in the kernel being encrypted "in place". + * The area will be encrypted by copying from the non-encrypted + * memory space to an intermediate buffer and then copying from the + * intermediate buffer back to the encrypted memory space. The physical + * addresses of the two mappings are the same which results in the area + * being encrypted "in place". */ /* Enable the new page tables */ mov %rdx, %cr3 @@ -103,47 +103,55 @@ ENTRY(__enc_copy) orq $X86_CR4_PGE, %rdx mov %rdx, %cr4 + push %r15 + push %r12 + + movq %rcx, %r9 /* Save area length */ + movq %rdi, %r10 /* Save encrypted area address */ + movq %rsi, %r11 /* Save decrypted area address */ + /* Set the PAT register PA5 entry to write-protect */ - push %rcx movl $MSR_IA32_CR_PAT, %ecx rdmsr - push %rdx /* Save original PAT value */ + mov %rdx, %r15 /* Save original PAT value */ andl $0xffff00ff, %edx /* Clear PA5 */ orl $0x00000500, %edx /* Set PA5 to WP */ wrmsr - pop %rdx /* RDX contains original PAT value */ - pop %rcx - - movq %rcx, %r9 /* Save kernel length */ - movq %rdi, %r10 /* Save encrypted kernel address */ - movq %rsi, %r11 /* Save decrypted kernel address */ wbinvd /* Invalidate any cache entries */ - /* Copy/encrypt 2MB at a time */ + /* Copy/encrypt up to 2MB at a time */ + movq $PMD_PAGE_SIZE, %r12 1: - movq %r11, %rsi /* Source - decrypted kernel */ + cmpq %r12, %r9 + jnb 2f + movq %r9, %r12 + +2: + movq %r11, %rsi /* Source - decrypted area */ movq %r8, %rdi /* Dest - intermediate copy buffer */ - movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + movq %r12, %rcx rep movsb movq %r8, %rsi /* Source - intermediate copy buffer */ - movq %r10, %rdi /* Dest - encrypted kernel */ - movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + movq %r10, %rdi /* Dest - encrypted area */ + movq %r12, %rcx rep movsb - addq $PMD_PAGE_SIZE, %r11 - addq $PMD_PAGE_SIZE, %r10 - subq $PMD_PAGE_SIZE, %r9 /* Kernel length decrement */ + addq %r12, %r11 + addq %r12, %r10 + subq %r12, %r9 /* Kernel length decrement */ jnz 1b /* Kernel length not zero? */ /* Restore PAT register */ - push %rdx /* Save original PAT value */ movl $MSR_IA32_CR_PAT, %ecx rdmsr - pop %rdx /* Restore original PAT value */ + mov %r15, %rdx /* Restore original PAT value */ wrmsr + pop %r12 + pop %r15 + ret .L__enc_copy_end: ENDPROC(__enc_copy) diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 7750a9c38b06..1df7da47f431 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -763,11 +763,11 @@ static int complete_subctxt(struct hfi1_filedata *fd) } if (ret) { - hfi1_rcd_put(fd->uctxt); - fd->uctxt = NULL; spin_lock_irqsave(&fd->dd->uctxt_lock, flags); __clear_bit(fd->subctxt, fd->uctxt->in_use_ctxts); spin_unlock_irqrestore(&fd->dd->uctxt_lock, flags); + hfi1_rcd_put(fd->uctxt); + fd->uctxt = NULL; } return ret; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 8ac50de2b242..262c1aa2e028 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1324,7 +1324,8 @@ static int mlx5_ib_alloc_transport_domain(struct mlx5_ib_dev *dev, u32 *tdn) return err; if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) || - !MLX5_CAP_GEN(dev->mdev, disable_local_lb)) + (!MLX5_CAP_GEN(dev->mdev, disable_local_lb_uc) && + !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc))) return err; mutex_lock(&dev->lb_mutex); @@ -1342,7 +1343,8 @@ static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn) mlx5_core_dealloc_transport_domain(dev->mdev, tdn); if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) || - !MLX5_CAP_GEN(dev->mdev, disable_local_lb)) + (!MLX5_CAP_GEN(dev->mdev, disable_local_lb_uc) && + !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc))) return; mutex_lock(&dev->lb_mutex); @@ -4158,7 +4160,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) goto err_cnt; dev->mdev->priv.uar = mlx5_get_uars_page(dev->mdev); - if (!dev->mdev->priv.uar) + if (IS_ERR(dev->mdev->priv.uar)) goto err_cong; err = mlx5_alloc_bfreg(dev->mdev, &dev->bfreg, false, false); @@ -4187,7 +4189,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) } if ((MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && - MLX5_CAP_GEN(mdev, disable_local_lb)) + (MLX5_CAP_GEN(mdev, disable_local_lb_uc) || + MLX5_CAP_GEN(mdev, disable_local_lb_mc))) mutex_init(&dev->lb_mutex); dev->ib_active = true; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 31ad28853efa..cffe5966aef9 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -4362,12 +4362,11 @@ static void to_rdma_ah_attr(struct mlx5_ib_dev *ibdev, memset(ah_attr, 0, sizeof(*ah_attr)); - ah_attr->type = rdma_ah_find_type(&ibdev->ib_dev, path->port); - rdma_ah_set_port_num(ah_attr, path->port); - if (rdma_ah_get_port_num(ah_attr) == 0 || - rdma_ah_get_port_num(ah_attr) > MLX5_CAP_GEN(dev, num_ports)) + if (!path->port || path->port > MLX5_CAP_GEN(dev, num_ports)) return; + ah_attr->type = rdma_ah_find_type(&ibdev->ib_dev, path->port); + rdma_ah_set_port_num(ah_attr, path->port); rdma_ah_set_sl(ah_attr, path->dci_cfi_prio_sl & 0xf); diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 720dfb3a1ac2..1b02283ce20e 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -741,6 +741,7 @@ isert_connect_error(struct rdma_cm_id *cma_id) { struct isert_conn *isert_conn = cma_id->qp->qp_context; + ib_drain_qp(isert_conn->qp); list_del_init(&isert_conn->node); isert_conn->cm_id = NULL; isert_put_conn(isert_conn); diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index 410a0a95130b..b3e7fafee3df 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -1913,3 +1913,7 @@ static struct platform_driver cs89x0_driver = { module_platform_driver_probe(cs89x0_driver, cs89x0_platform_probe); #endif /* CONFIG_CS89x0_PLATFORM */ + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Crystal Semiconductor (Now Cirrus Logic) CS89[02]0 network driver"); +MODULE_AUTHOR("Russell Nelson <nelson@crynwr.com>"); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 1dc4aef37d3a..4b3df17c7a45 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -756,6 +756,12 @@ static int ibmvnic_login(struct net_device *netdev) } } while (adapter->renegotiate); + /* handle pending MAC address changes after successful login */ + if (adapter->mac_change_pending) { + __ibmvnic_set_mac(netdev, &adapter->desired.mac); + adapter->mac_change_pending = false; + } + return 0; } @@ -993,11 +999,6 @@ static int ibmvnic_open(struct net_device *netdev) mutex_lock(&adapter->reset_lock); - if (adapter->mac_change_pending) { - __ibmvnic_set_mac(netdev, &adapter->desired.mac); - adapter->mac_change_pending = false; - } - if (adapter->state != VNIC_CLOSED) { rc = ibmvnic_login(netdev); if (rc) { @@ -1527,7 +1528,7 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p) struct ibmvnic_adapter *adapter = netdev_priv(netdev); struct sockaddr *addr = p; - if (adapter->state != VNIC_OPEN) { + if (adapter->state == VNIC_PROBED) { memcpy(&adapter->desired.mac, addr, sizeof(struct sockaddr)); adapter->mac_change_pending = true; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 543060c305a0..c2d89bfa1a70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -895,7 +895,7 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, u16 vid); void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); -void mlx5e_timestamp_set(struct mlx5e_priv *priv); +void mlx5e_timestamp_init(struct mlx5e_priv *priv); struct mlx5e_redirect_rqt_param { bool is_rss; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 9bcf38f4123b..3d46ef48d5b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -922,8 +922,9 @@ static void mlx5e_dcbnl_query_dcbx_mode(struct mlx5e_priv *priv, static void mlx5e_ets_init(struct mlx5e_priv *priv) { - int i; struct ieee_ets ets; + int err; + int i; if (!MLX5_CAP_GEN(priv->mdev, ets)) return; @@ -936,11 +937,16 @@ static void mlx5e_ets_init(struct mlx5e_priv *priv) ets.prio_tc[i] = i; } - /* tclass[prio=0]=1, tclass[prio=1]=0, tclass[prio=i]=i (for i>1) */ - ets.prio_tc[0] = 1; - ets.prio_tc[1] = 0; + if (ets.ets_cap > 1) { + /* tclass[prio=0]=1, tclass[prio=1]=0, tclass[prio=i]=i (for i>1) */ + ets.prio_tc[0] = 1; + ets.prio_tc[1] = 0; + } - mlx5e_dcbnl_ieee_setets_core(priv, &ets); + err = mlx5e_dcbnl_ieee_setets_core(priv, &ets); + if (err) + netdev_err(priv->netdev, + "%s, Failed to init ETS: %d\n", __func__, err); } enum { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 8f05efa5c829..ea5fff2c3143 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -207,8 +207,7 @@ void mlx5e_ethtool_get_ethtool_stats(struct mlx5e_priv *priv, return; mutex_lock(&priv->state_lock); - if (test_bit(MLX5E_STATE_OPENED, &priv->state)) - mlx5e_update_stats(priv, true); + mlx5e_update_stats(priv, true); mutex_unlock(&priv->state_lock); for (i = 0; i < mlx5e_num_stats_grps; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d9d8227f195f..d8aefeed124d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2669,7 +2669,7 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, netif_carrier_on(netdev); } -void mlx5e_timestamp_set(struct mlx5e_priv *priv) +void mlx5e_timestamp_init(struct mlx5e_priv *priv) { priv->tstamp.tx_type = HWTSTAMP_TX_OFF; priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE; @@ -2690,7 +2690,6 @@ int mlx5e_open_locked(struct net_device *netdev) mlx5e_activate_priv_channels(priv); if (priv->profile->update_carrier) priv->profile->update_carrier(priv); - mlx5e_timestamp_set(priv); if (priv->profile->update_stats) queue_delayed_work(priv->wq, &priv->update_stats_work, 0); @@ -3219,12 +3218,12 @@ static int mlx5e_set_mac(struct net_device *netdev, void *addr) return 0; } -#define MLX5E_SET_FEATURE(netdev, feature, enable) \ +#define MLX5E_SET_FEATURE(features, feature, enable) \ do { \ if (enable) \ - netdev->features |= feature; \ + *features |= feature; \ else \ - netdev->features &= ~feature; \ + *features &= ~feature; \ } while (0) typedef int (*mlx5e_feature_handler)(struct net_device *netdev, bool enable); @@ -3347,6 +3346,7 @@ static int set_feature_arfs(struct net_device *netdev, bool enable) #endif static int mlx5e_handle_feature(struct net_device *netdev, + netdev_features_t *features, netdev_features_t wanted_features, netdev_features_t feature, mlx5e_feature_handler feature_handler) @@ -3365,34 +3365,40 @@ static int mlx5e_handle_feature(struct net_device *netdev, return err; } - MLX5E_SET_FEATURE(netdev, feature, enable); + MLX5E_SET_FEATURE(features, feature, enable); return 0; } static int mlx5e_set_features(struct net_device *netdev, netdev_features_t features) { + netdev_features_t oper_features = netdev->features; int err; - err = mlx5e_handle_feature(netdev, features, NETIF_F_LRO, - set_feature_lro); - err |= mlx5e_handle_feature(netdev, features, + err = mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_LRO, set_feature_lro); + err |= mlx5e_handle_feature(netdev, &oper_features, features, NETIF_F_HW_VLAN_CTAG_FILTER, set_feature_cvlan_filter); - err |= mlx5e_handle_feature(netdev, features, NETIF_F_HW_TC, - set_feature_tc_num_filters); - err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXALL, - set_feature_rx_all); - err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXFCS, - set_feature_rx_fcs); - err |= mlx5e_handle_feature(netdev, features, NETIF_F_HW_VLAN_CTAG_RX, - set_feature_rx_vlan); + err |= mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_HW_TC, set_feature_tc_num_filters); + err |= mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_RXALL, set_feature_rx_all); + err |= mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_RXFCS, set_feature_rx_fcs); + err |= mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan); #ifdef CONFIG_RFS_ACCEL - err |= mlx5e_handle_feature(netdev, features, NETIF_F_NTUPLE, - set_feature_arfs); + err |= mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_NTUPLE, set_feature_arfs); #endif - return err ? -EINVAL : 0; + if (err) { + netdev->features = oper_features; + return -EINVAL; + } + + return 0; } static netdev_features_t mlx5e_fix_features(struct net_device *netdev, @@ -4139,6 +4145,8 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev, INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work); INIT_WORK(&priv->tx_timeout_work, mlx5e_tx_timeout_work); INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work); + + mlx5e_timestamp_init(priv); } static void mlx5e_set_netdev_dev_addr(struct net_device *netdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 2c43606c26b5..3409d86eb06b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -877,6 +877,8 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev, mlx5e_build_rep_params(mdev, &priv->channels.params); mlx5e_build_rep_netdev(netdev); + + mlx5e_timestamp_init(priv); } static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 1f1f8af87d4d..5a4608281f38 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -238,15 +238,19 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv, int err = 0; /* Temporarily enable local_lb */ - if (MLX5_CAP_GEN(priv->mdev, disable_local_lb)) { - mlx5_nic_vport_query_local_lb(priv->mdev, &lbtp->local_lb); - if (!lbtp->local_lb) - mlx5_nic_vport_update_local_lb(priv->mdev, true); + err = mlx5_nic_vport_query_local_lb(priv->mdev, &lbtp->local_lb); + if (err) + return err; + + if (!lbtp->local_lb) { + err = mlx5_nic_vport_update_local_lb(priv->mdev, true); + if (err) + return err; } err = mlx5e_refresh_tirs(priv, true); if (err) - return err; + goto out; lbtp->loopback_ok = false; init_completion(&lbtp->comp); @@ -256,16 +260,21 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv, lbtp->pt.dev = priv->netdev; lbtp->pt.af_packet_priv = lbtp; dev_add_pack(&lbtp->pt); + + return 0; + +out: + if (!lbtp->local_lb) + mlx5_nic_vport_update_local_lb(priv->mdev, false); + return err; } static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv, struct mlx5e_lbt_priv *lbtp) { - if (MLX5_CAP_GEN(priv->mdev, disable_local_lb)) { - if (!lbtp->local_lb) - mlx5_nic_vport_update_local_lb(priv->mdev, false); - } + if (!lbtp->local_lb) + mlx5_nic_vport_update_local_lb(priv->mdev, false); dev_remove_pack(&lbtp->pt); mlx5e_refresh_tirs(priv, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 8812d7208e8f..ee2f378c5030 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -86,6 +86,8 @@ void mlx5i_init(struct mlx5_core_dev *mdev, mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev)); mlx5i_build_nic_params(mdev, &priv->channels.params); + mlx5e_timestamp_init(priv); + /* netdev init */ netdev->hw_features |= NETIF_F_SG; netdev->hw_features |= NETIF_F_IP_CSUM; @@ -450,7 +452,6 @@ static int mlx5i_open(struct net_device *netdev) mlx5e_refresh_tirs(epriv, false); mlx5e_activate_priv_channels(epriv); - mlx5e_timestamp_set(epriv); mutex_unlock(&epriv->state_lock); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index fa8aed62b231..5701f125e99c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -423,9 +423,13 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev, switch (clock->ptp_info.pin_config[pin].func) { case PTP_PF_EXTTS: + ptp_event.index = pin; + ptp_event.timestamp = timecounter_cyc2time(&clock->tc, + be64_to_cpu(eqe->data.pps.time_stamp)); if (clock->pps_info.enabled) { ptp_event.type = PTP_CLOCK_PPSUSR; - ptp_event.pps_times.ts_real = ns_to_timespec64(eqe->data.pps.time_stamp); + ptp_event.pps_times.ts_real = + ns_to_timespec64(ptp_event.timestamp); } else { ptp_event.type = PTP_CLOCK_EXTTS; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8a89c7e8cd63..0f88fd30a09a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -319,6 +319,7 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) struct mlx5_eq_table *table = &priv->eq_table; int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq); int nvec; + int err; nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + MLX5_EQ_VEC_COMP_BASE; @@ -328,21 +329,23 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL); if (!priv->irq_info) - goto err_free_msix; + return -ENOMEM; nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1, nvec, PCI_IRQ_MSIX); - if (nvec < 0) - return nvec; + if (nvec < 0) { + err = nvec; + goto err_free_irq_info; + } table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE; return 0; -err_free_msix: +err_free_irq_info: kfree(priv->irq_info); - return -ENOMEM; + return err; } static void mlx5_free_irq_vectors(struct mlx5_core_dev *dev) @@ -578,8 +581,7 @@ static int mlx5_core_set_hca_defaults(struct mlx5_core_dev *dev) int ret = 0; /* Disable local_lb by default */ - if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && - MLX5_CAP_GEN(dev, disable_local_lb)) + if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) ret = mlx5_nic_vport_update_local_lb(dev, false); return ret; @@ -1121,9 +1123,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_stop_poll; } - if (boot && mlx5_init_once(dev, priv)) { - dev_err(&pdev->dev, "sw objs init failed\n"); - goto err_stop_poll; + if (boot) { + err = mlx5_init_once(dev, priv); + if (err) { + dev_err(&pdev->dev, "sw objs init failed\n"); + goto err_stop_poll; + } } err = mlx5_alloc_irq_vectors(dev); @@ -1133,8 +1138,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, } dev->priv.uar = mlx5_get_uars_page(dev); - if (!dev->priv.uar) { + if (IS_ERR(dev->priv.uar)) { dev_err(&pdev->dev, "Failed allocating uar, aborting\n"); + err = PTR_ERR(dev->priv.uar); goto err_disable_msix; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index 222b25908d01..8b97066dd1f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -168,18 +168,16 @@ struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev) struct mlx5_uars_page *ret; mutex_lock(&mdev->priv.bfregs.reg_head.lock); - if (list_empty(&mdev->priv.bfregs.reg_head.list)) { - ret = alloc_uars_page(mdev, false); - if (IS_ERR(ret)) { - ret = NULL; - goto out; - } - list_add(&ret->list, &mdev->priv.bfregs.reg_head.list); - } else { + if (!list_empty(&mdev->priv.bfregs.reg_head.list)) { ret = list_first_entry(&mdev->priv.bfregs.reg_head.list, struct mlx5_uars_page, list); kref_get(&ret->ref_count); + goto out; } + ret = alloc_uars_page(mdev, false); + if (IS_ERR(ret)) + goto out; + list_add(&ret->list, &mdev->priv.bfregs.reg_head.list); out: mutex_unlock(&mdev->priv.bfregs.reg_head.lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index d653b0025b13..a1296a62497d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -908,23 +908,33 @@ int mlx5_nic_vport_update_local_lb(struct mlx5_core_dev *mdev, bool enable) void *in; int err; - mlx5_core_dbg(mdev, "%s local_lb\n", enable ? "enable" : "disable"); + if (!MLX5_CAP_GEN(mdev, disable_local_lb_mc) && + !MLX5_CAP_GEN(mdev, disable_local_lb_uc)) + return 0; + in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; MLX5_SET(modify_nic_vport_context_in, in, - field_select.disable_mc_local_lb, 1); - MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.disable_mc_local_lb, !enable); - - MLX5_SET(modify_nic_vport_context_in, in, - field_select.disable_uc_local_lb, 1); MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.disable_uc_local_lb, !enable); + if (MLX5_CAP_GEN(mdev, disable_local_lb_mc)) + MLX5_SET(modify_nic_vport_context_in, in, + field_select.disable_mc_local_lb, 1); + + if (MLX5_CAP_GEN(mdev, disable_local_lb_uc)) + MLX5_SET(modify_nic_vport_context_in, in, + field_select.disable_uc_local_lb, 1); + err = mlx5_modify_nic_vport_context(mdev, in, inlen); + if (!err) + mlx5_core_dbg(mdev, "%s local_lb\n", + enable ? "enable" : "disable"); + kvfree(in); return err; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 2801ecd09eab..6c02b2d6ba06 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -333,7 +333,7 @@ nfp_net_get_link_ksettings(struct net_device *netdev, ls >= ARRAY_SIZE(ls_to_ethtool)) return 0; - cmd->base.speed = ls_to_ethtool[sts]; + cmd->base.speed = ls_to_ethtool[ls]; cmd->base.duplex = DUPLEX_FULL; return 0; diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index be48d9abd001..3588081b2e27 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -776,6 +776,7 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, int rc = 0; struct qed_spq *p_spq = p_hwfn ? p_hwfn->p_spq : NULL; bool b_ret_ent = true; + bool eblock; if (!p_hwfn) return -EINVAL; @@ -794,6 +795,11 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, if (rc) goto spq_post_fail; + /* Check if entry is in block mode before qed_spq_add_entry, + * which might kfree p_ent. + */ + eblock = (p_ent->comp_mode == QED_SPQ_MODE_EBLOCK); + /* Add the request to the pending queue */ rc = qed_spq_add_entry(p_hwfn, p_ent, p_ent->priority); if (rc) @@ -811,7 +817,7 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, spin_unlock_bh(&p_spq->lock); - if (p_ent->comp_mode == QED_SPQ_MODE_EBLOCK) { + if (eblock) { /* For entries in QED BLOCK mode, the completion code cannot * perform the necessary cleanup - if it did, we couldn't * access p_ent here to see whether it's successful or not. diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index b9e2846589f8..53924a4fc31c 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2089,8 +2089,8 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf) add_reg(CSMR); if (cd->select_mii) add_reg(RMII_MII); - add_reg(ARSTR); if (cd->tsu) { + add_tsu_reg(ARSTR); add_tsu_reg(TSU_CTRST); add_tsu_reg(TSU_FWEN0); add_tsu_reg(TSU_FWEN1); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index d8e5747ff4e3..264d4af0bf69 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1006,17 +1006,18 @@ static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) if (!ifname_is_set) snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ppp->file.index); + mutex_unlock(&pn->all_ppp_mutex); + ret = register_netdevice(ppp->dev); if (ret < 0) goto err_unit; atomic_inc(&ppp_unit_count); - mutex_unlock(&pn->all_ppp_mutex); - return 0; err_unit: + mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); err: mutex_unlock(&pn->all_ppp_mutex); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 94c7804903c4..ec56ff29aac4 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2396,6 +2396,7 @@ static int lan78xx_reset(struct lan78xx_net *dev) buf = DEFAULT_BURST_CAP_SIZE / FS_USB_PKT_SIZE; dev->rx_urb_size = DEFAULT_BURST_CAP_SIZE; dev->rx_qlen = 4; + dev->tx_qlen = 4; } ret = lan78xx_write_reg(dev, BURST_CAP, buf); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index e8189c07b41f..f6d4a50f1bdb 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -489,6 +489,7 @@ static const struct ieee80211_iface_combination hwsim_if_comb_p2p_dev[] = { static spinlock_t hwsim_radio_lock; static LIST_HEAD(hwsim_radios); +static struct workqueue_struct *hwsim_wq; static int hwsim_radio_idx; static struct platform_driver mac80211_hwsim_driver = { @@ -3120,6 +3121,11 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) if (info->attrs[HWSIM_ATTR_CHANNELS]) param.channels = nla_get_u32(info->attrs[HWSIM_ATTR_CHANNELS]); + if (param.channels > CFG80211_MAX_NUM_DIFFERENT_CHANNELS) { + GENL_SET_ERR_MSG(info, "too many channels specified"); + return -EINVAL; + } + if (info->attrs[HWSIM_ATTR_NO_VIF]) param.no_vif = true; @@ -3342,7 +3348,7 @@ static void remove_user_radios(u32 portid) if (entry->destroy_on_close && entry->portid == portid) { list_del(&entry->list); INIT_WORK(&entry->destroy_work, destroy_radio); - schedule_work(&entry->destroy_work); + queue_work(hwsim_wq, &entry->destroy_work); } } spin_unlock_bh(&hwsim_radio_lock); @@ -3417,7 +3423,7 @@ static void __net_exit hwsim_exit_net(struct net *net) list_del(&data->list); INIT_WORK(&data->destroy_work, destroy_radio); - schedule_work(&data->destroy_work); + queue_work(hwsim_wq, &data->destroy_work); } spin_unlock_bh(&hwsim_radio_lock); } @@ -3449,6 +3455,10 @@ static int __init init_mac80211_hwsim(void) spin_lock_init(&hwsim_radio_lock); + hwsim_wq = alloc_workqueue("hwsim_wq",WQ_MEM_RECLAIM,0); + if (!hwsim_wq) + return -ENOMEM; + err = register_pernet_device(&hwsim_net_ops); if (err) return err; @@ -3587,8 +3597,11 @@ static void __exit exit_mac80211_hwsim(void) hwsim_exit_netlink(); mac80211_hwsim_free(); + flush_workqueue(hwsim_wq); + unregister_netdev(hwsim_mon); platform_driver_unregister(&mac80211_hwsim_driver); unregister_pernet_device(&hwsim_net_ops); + destroy_workqueue(hwsim_wq); } module_exit(exit_mac80211_hwsim); diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 4178d2493547..5e335b6203f4 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -71,7 +71,7 @@ extern void delayacct_init(void); extern void __delayacct_tsk_init(struct task_struct *); extern void __delayacct_tsk_exit(struct task_struct *); extern void __delayacct_blkio_start(void); -extern void __delayacct_blkio_end(void); +extern void __delayacct_blkio_end(struct task_struct *); extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); @@ -122,10 +122,10 @@ static inline void delayacct_blkio_start(void) __delayacct_blkio_start(); } -static inline void delayacct_blkio_end(void) +static inline void delayacct_blkio_end(struct task_struct *p) { if (current->delays) - __delayacct_blkio_end(); + __delayacct_blkio_end(p); delayacct_clear_flag(DELAYACCT_PF_BLKIO); } @@ -169,7 +169,7 @@ static inline void delayacct_tsk_free(struct task_struct *tsk) {} static inline void delayacct_blkio_start(void) {} -static inline void delayacct_blkio_end(void) +static inline void delayacct_blkio_end(struct task_struct *p) {} static inline int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1f509d072026..a0610427e168 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -36,6 +36,7 @@ #include <linux/kernel.h> #include <linux/completion.h> #include <linux/pci.h> +#include <linux/irq.h> #include <linux/spinlock_types.h> #include <linux/semaphore.h> #include <linux/slab.h> @@ -1231,7 +1232,23 @@ enum { static inline const struct cpumask * mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector) { - return pci_irq_get_affinity(dev->pdev, MLX5_EQ_VEC_COMP_BASE + vector); + const struct cpumask *mask; + struct irq_desc *desc; + unsigned int irq; + int eqn; + int err; + + err = mlx5_vector2eqn(dev, vector, &eqn, &irq); + if (err) + return NULL; + + desc = irq_to_desc(irq); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + mask = irq_data_get_effective_affinity_mask(&desc->irq_data); +#else + mask = desc->irq_common_data.affinity; +#endif + return mask; } #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index d44ec5f41d4a..1391a82da98e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1027,8 +1027,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_wq_sz[0x5]; u8 nic_vport_change_event[0x1]; - u8 disable_local_lb[0x1]; - u8 reserved_at_3e2[0x9]; + u8 disable_local_lb_uc[0x1]; + u8 disable_local_lb_mc[0x1]; + u8 reserved_at_3e3[0x8]; u8 log_max_vlan_list[0x5]; u8 reserved_at_3f0[0x3]; u8 log_max_current_mc_list[0x5]; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 49b4257ce1ea..f3075d6c7e82 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -85,7 +85,7 @@ struct netlink_ext_ack { * to the lack of an output buffer.) */ #define NL_SET_ERR_MSG(extack, msg) do { \ - static const char __msg[] = (msg); \ + static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) \ @@ -101,7 +101,7 @@ struct netlink_ext_ack { } while (0) #define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do { \ - static const char __msg[] = (msg); \ + static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) { \ diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 6866df4f31b5..d72b2e7dd500 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -174,6 +174,15 @@ static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr) * if they dereference the pointer - see e.g. PTR_RING_PEEK_CALL. * If ring is never resized, and if the pointer is merely * tested, there's no need to take the lock - see e.g. __ptr_ring_empty. + * However, if called outside the lock, and if some other CPU + * consumes ring entries at the same time, the value returned + * is not guaranteed to be correct. + * In this case - to avoid incorrectly detecting the ring + * as empty - the CPU consuming the ring entries is responsible + * for either consuming all ring entries until the ring is empty, + * or synchronizing with some other CPU and causing it to + * execute __ptr_ring_peek and/or consume the ring enteries + * after the synchronization point. */ static inline void *__ptr_ring_peek(struct ptr_ring *r) { @@ -182,10 +191,7 @@ static inline void *__ptr_ring_peek(struct ptr_ring *r) return NULL; } -/* Note: callers invoking this in a loop must use a compiler barrier, - * for example cpu_relax(). Callers must take consumer_lock - * if the ring is ever resized - see e.g. ptr_ring_empty. - */ +/* See __ptr_ring_peek above for locking rules. */ static inline bool __ptr_ring_empty(struct ptr_ring *r) { return !__ptr_ring_peek(r); diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index bae807eb2933..853291714ae0 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -31,11 +31,17 @@ #else #define MODULE_RANDSTRUCT_PLUGIN #endif +#ifdef RETPOLINE +#define MODULE_VERMAGIC_RETPOLINE "retpoline " +#else +#define MODULE_VERMAGIC_RETPOLINE "" +#endif #define VERMAGIC_STRING \ UTS_RELEASE " " \ MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \ MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \ MODULE_ARCH_VERMAGIC \ - MODULE_RANDSTRUCT_PLUGIN + MODULE_RANDSTRUCT_PLUGIN \ + MODULE_VERMAGIC_RETPOLINE diff --git a/include/net/arp.h b/include/net/arp.h index dc8cd47f883b..977aabfcdc03 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -20,6 +20,9 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + key = INADDR_ANY; + return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cb4d92b79cd9..fb94a8bd8ab5 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -815,6 +815,8 @@ struct cfg80211_csa_settings { u8 count; }; +#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 + /** * struct iface_combination_params - input parameters for interface combinations * diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 83a3e47d5845..becf86aa4ac6 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -179,6 +179,7 @@ struct Qdisc_ops { const struct Qdisc_class_ops *cl_ops; char id[IFNAMSIZ]; int priv_size; + unsigned int static_flags; int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, @@ -444,6 +445,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, unsigned int len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops); +void qdisc_free(struct Qdisc *qdisc); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid); void __qdisc_calculate_pkt_len(struct sk_buff *skb, diff --git a/include/net/tls.h b/include/net/tls.h index 936cfc5cab7d..9185e53a743c 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -170,7 +170,7 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) static inline void tls_err_abort(struct sock *sk) { - sk->sk_err = -EBADMSG; + sk->sk_err = EBADMSG; sk->sk_error_report(sk); } diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 4265d7f9e1f2..dcfab5e3b55c 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -363,7 +363,6 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ OVS_TUNNEL_KEY_ATTR_PAD, - OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* be32 ERSPAN index. */ __OVS_TUNNEL_KEY_ATTR_MAX }; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index aaa319848e7d..ab94d304a634 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -56,7 +56,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) u32 elem_size, index_mask, max_entries; bool unpriv = !capable(CAP_SYS_ADMIN); struct bpf_array *array; - u64 array_size; + u64 array_size, mask64; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -74,13 +74,25 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) elem_size = round_up(attr->value_size, 8); max_entries = attr->max_entries; - index_mask = roundup_pow_of_two(max_entries) - 1; - if (unpriv) + /* On 32 bit archs roundup_pow_of_two() with max_entries that has + * upper most bit set in u32 space is undefined behavior due to + * resulting 1U << 32, so do it manually here in u64 space. + */ + mask64 = fls_long(max_entries - 1); + mask64 = 1ULL << mask64; + mask64 -= 1; + + index_mask = mask64; + if (unpriv) { /* round up array size to nearest power of 2, * since cpu will speculate within index_mask limits */ max_entries = index_mask + 1; + /* Check for overflows. */ + if (max_entries < attr->max_entries) + return ERR_PTR(-E2BIG); + } array_size = sizeof(*array); if (percpu) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b414d6b2d470..20eb04fd155e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2493,6 +2493,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } + if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) { + verbose(env, "BPF_ARSH not supported for 32 bit ALU\n"); + return -EINVAL; + } + if ((opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; @@ -4472,7 +4477,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) */ map_ptr = env->insn_aux_data[i + delta].map_ptr; if (map_ptr == BPF_MAP_PTR_POISON) { - verbose(env, "tail_call obusing map_ptr\n"); + verbose(env, "tail_call abusing map_ptr\n"); return -EINVAL; } if (!map_ptr->unpriv_array) diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 4a1c33416b6a..e2764d767f18 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -51,16 +51,16 @@ void __delayacct_tsk_init(struct task_struct *tsk) * Finish delay accounting for a statistic using its timestamps (@start), * accumalator (@total) and @count */ -static void delayacct_end(u64 *start, u64 *total, u32 *count) +static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count) { s64 ns = ktime_get_ns() - *start; unsigned long flags; if (ns > 0) { - spin_lock_irqsave(¤t->delays->lock, flags); + spin_lock_irqsave(lock, flags); *total += ns; (*count)++; - spin_unlock_irqrestore(¤t->delays->lock, flags); + spin_unlock_irqrestore(lock, flags); } } @@ -69,17 +69,25 @@ void __delayacct_blkio_start(void) current->delays->blkio_start = ktime_get_ns(); } -void __delayacct_blkio_end(void) +/* + * We cannot rely on the `current` macro, as we haven't yet switched back to + * the process being woken. + */ +void __delayacct_blkio_end(struct task_struct *p) { - if (current->delays->flags & DELAYACCT_PF_SWAPIN) - /* Swapin block I/O */ - delayacct_end(¤t->delays->blkio_start, - ¤t->delays->swapin_delay, - ¤t->delays->swapin_count); - else /* Other block I/O */ - delayacct_end(¤t->delays->blkio_start, - ¤t->delays->blkio_delay, - ¤t->delays->blkio_count); + struct task_delay_info *delays = p->delays; + u64 *total; + u32 *count; + + if (p->delays->flags & DELAYACCT_PF_SWAPIN) { + total = &delays->swapin_delay; + count = &delays->swapin_count; + } else { + total = &delays->blkio_delay; + count = &delays->blkio_count; + } + + delayacct_end(&delays->lock, &delays->blkio_start, total, count); } int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) @@ -153,8 +161,10 @@ void __delayacct_freepages_start(void) void __delayacct_freepages_end(void) { - delayacct_end(¤t->delays->freepages_start, - ¤t->delays->freepages_delay, - ¤t->delays->freepages_count); + delayacct_end( + ¤t->delays->lock, + ¤t->delays->freepages_start, + ¤t->delays->freepages_delay, + ¤t->delays->freepages_count); } diff --git a/kernel/futex.c b/kernel/futex.c index 57d0b3657e16..8c5424dd5924 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1878,6 +1878,9 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, struct futex_q *this, *next; DEFINE_WAKE_Q(wake_q); + if (nr_wake < 0 || nr_requeue < 0) + return -EINVAL; + /* * When PI not supported: return -ENOSYS if requeue_pi is true, * consequently the compiler knows requeue_pi is always false past @@ -2294,21 +2297,17 @@ static void unqueue_me_pi(struct futex_q *q) spin_unlock(q->lock_ptr); } -/* - * Fixup the pi_state owner with the new owner. - * - * Must be called with hash bucket lock held and mm->sem held for non - * private futexes. - */ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *newowner) + struct task_struct *argowner) { - u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; u32 uval, uninitialized_var(curval), newval; - struct task_struct *oldowner; + struct task_struct *oldowner, *newowner; + u32 newtid; int ret; + lockdep_assert_held(q->lock_ptr); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); oldowner = pi_state->owner; @@ -2317,11 +2316,17 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, newtid |= FUTEX_OWNER_DIED; /* - * We are here either because we stole the rtmutex from the - * previous highest priority waiter or we are the highest priority - * waiter but have failed to get the rtmutex the first time. + * We are here because either: + * + * - we stole the lock and pi_state->owner needs updating to reflect + * that (@argowner == current), + * + * or: + * + * - someone stole our lock and we need to fix things to point to the + * new owner (@argowner == NULL). * - * We have to replace the newowner TID in the user space variable. + * Either way, we have to replace the TID in the user space variable. * This must be atomic as we have to preserve the owner died bit here. * * Note: We write the user space value _before_ changing the pi_state @@ -2334,6 +2339,42 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, * in the PID check in lookup_pi_state. */ retry: + if (!argowner) { + if (oldowner != current) { + /* + * We raced against a concurrent self; things are + * already fixed up. Nothing to do. + */ + ret = 0; + goto out_unlock; + } + + if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) { + /* We got the lock after all, nothing to fix. */ + ret = 0; + goto out_unlock; + } + + /* + * Since we just failed the trylock; there must be an owner. + */ + newowner = rt_mutex_owner(&pi_state->pi_mutex); + BUG_ON(!newowner); + } else { + WARN_ON_ONCE(argowner != current); + if (oldowner == current) { + /* + * We raced against a concurrent self; things are + * already fixed up. Nothing to do. + */ + ret = 0; + goto out_unlock; + } + newowner = argowner; + } + + newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; + if (get_futex_value_locked(&uval, uaddr)) goto handle_fault; @@ -2434,9 +2475,9 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * Got the lock. We might not be the anticipated owner if we * did a lock-steal - fix up the PI-state in that case: * - * We can safely read pi_state->owner without holding wait_lock - * because we now own the rt_mutex, only the owner will attempt - * to change it. + * Speculative pi_state->owner read (we don't hold wait_lock); + * since we own the lock pi_state->owner == current is the + * stable state, anything else needs more attention. */ if (q->pi_state->owner != current) ret = fixup_pi_state_owner(uaddr, q, current); @@ -2444,6 +2485,19 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) } /* + * If we didn't get the lock; check if anybody stole it from us. In + * that case, we need to fix up the uval to point to them instead of + * us, otherwise bad things happen. [10] + * + * Another speculative read; pi_state->owner == current is unstable + * but needs our attention. + */ + if (q->pi_state->owner == current) { + ret = fixup_pi_state_owner(uaddr, q, NULL); + goto out; + } + + /* * Paranoia check. If we did not take the lock, then we should not be * the owner of the rt_mutex. */ diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 6f3dba6e4e9e..65cc0cb984e6 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1290,6 +1290,19 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, return ret; } +static inline int __rt_mutex_slowtrylock(struct rt_mutex *lock) +{ + int ret = try_to_take_rt_mutex(lock, current, NULL); + + /* + * try_to_take_rt_mutex() sets the lock waiters bit + * unconditionally. Clean this up. + */ + fixup_rt_mutex_waiters(lock); + + return ret; +} + /* * Slow path try-lock function: */ @@ -1312,13 +1325,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) */ raw_spin_lock_irqsave(&lock->wait_lock, flags); - ret = try_to_take_rt_mutex(lock, current, NULL); - - /* - * try_to_take_rt_mutex() sets the lock waiters bit - * unconditionally. Clean this up. - */ - fixup_rt_mutex_waiters(lock); + ret = __rt_mutex_slowtrylock(lock); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); @@ -1505,6 +1512,11 @@ int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) return rt_mutex_slowtrylock(lock); } +int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) +{ + return __rt_mutex_slowtrylock(lock); +} + /** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 124e98ca0b17..68686b3ec3c1 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -148,6 +148,7 @@ extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter); extern int rt_mutex_futex_trylock(struct rt_mutex *l); +extern int __rt_mutex_futex_trylock(struct rt_mutex *l); extern void rt_mutex_futex_unlock(struct rt_mutex *lock); extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 644fa2e3d993..a7bf32aabfda 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2056,7 +2056,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) p->state = TASK_WAKING; if (p->in_iowait) { - delayacct_blkio_end(); + delayacct_blkio_end(p); atomic_dec(&task_rq(p)->nr_iowait); } @@ -2069,7 +2069,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) #else /* CONFIG_SMP */ if (p->in_iowait) { - delayacct_blkio_end(); + delayacct_blkio_end(p); atomic_dec(&task_rq(p)->nr_iowait); } @@ -2122,7 +2122,7 @@ static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf) if (!task_on_rq_queued(p)) { if (p->in_iowait) { - delayacct_blkio_end(); + delayacct_blkio_end(p); atomic_dec(&rq->nr_iowait); } ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 89a9e1b4264a..0bcf00e3ce48 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1696,7 +1696,7 @@ void run_local_timers(void) hrtimer_run_queues(); /* Raise the softirq only if required. */ if (time_before(jiffies, base->clk)) { - if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active) + if (!IS_ENABLED(CONFIG_NO_HZ_COMMON)) return; /* CPU is awake, so check the deferrable base. */ base++; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 904c952ac383..f54dc62b599c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -355,7 +355,7 @@ config PROFILE_ANNOTATED_BRANCHES on if you need to profile the system's use of these macros. config PROFILE_ALL_BRANCHES - bool "Profile all if conditionals" + bool "Profile all if conditionals" if !FORTIFY_SOURCE select TRACE_BRANCH_PROFILING help This tracer profiles all branch conditions. Every if () diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9ab18995ff1e..0cddf60186da 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2534,29 +2534,59 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * The lock and unlock are done within a preempt disable section. * The current_context per_cpu variable can only be modified * by the current task between lock and unlock. But it can - * be modified more than once via an interrupt. There are four - * different contexts that we need to consider. + * be modified more than once via an interrupt. To pass this + * information from the lock to the unlock without having to + * access the 'in_interrupt()' functions again (which do show + * a bit of overhead in something as critical as function tracing, + * we use a bitmask trick. * - * Normal context. - * SoftIRQ context - * IRQ context - * NMI context + * bit 0 = NMI context + * bit 1 = IRQ context + * bit 2 = SoftIRQ context + * bit 3 = normal context. * - * If for some reason the ring buffer starts to recurse, we - * only allow that to happen at most 4 times (one for each - * context). If it happens 5 times, then we consider this a - * recusive loop and do not let it go further. + * This works because this is the order of contexts that can + * preempt other contexts. A SoftIRQ never preempts an IRQ + * context. + * + * When the context is determined, the corresponding bit is + * checked and set (if it was set, then a recursion of that context + * happened). + * + * On unlock, we need to clear this bit. To do so, just subtract + * 1 from the current_context and AND it to itself. + * + * (binary) + * 101 - 1 = 100 + * 101 & 100 = 100 (clearing bit zero) + * + * 1010 - 1 = 1001 + * 1010 & 1001 = 1000 (clearing bit 1) + * + * The least significant bit can be cleared this way, and it + * just so happens that it is the same bit corresponding to + * the current context. */ static __always_inline int trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) { - if (cpu_buffer->current_context >= 4) + unsigned int val = cpu_buffer->current_context; + unsigned long pc = preempt_count(); + int bit; + + if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) + bit = RB_CTX_NORMAL; + else + bit = pc & NMI_MASK ? RB_CTX_NMI : + pc & HARDIRQ_MASK ? RB_CTX_IRQ : + pc & SOFTIRQ_OFFSET ? 2 : RB_CTX_SOFTIRQ; + + if (unlikely(val & (1 << bit))) return 1; - cpu_buffer->current_context++; - /* Interrupts must see this update */ - barrier(); + val |= (1 << bit); + cpu_buffer->current_context = val; return 0; } @@ -2564,9 +2594,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) static __always_inline void trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) { - /* Don't let the dec leak out */ - barrier(); - cpu_buffer->current_context--; + cpu_buffer->current_context &= cpu_buffer->current_context - 1; } /** diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 325c56043007..086a4abdfa7c 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -543,3 +543,7 @@ static void p9_trans_xen_exit(void) return xenbus_unregister_driver(&xen_9pfs_front_driver); } module_exit(p9_trans_xen_exit); + +MODULE_AUTHOR("Stefano Stabellini <stefano@aporeto.com>"); +MODULE_DESCRIPTION("Xen Transport for 9P"); +MODULE_LICENSE("GPL"); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index d1f5fe986edd..7f831711b6e0 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -532,7 +532,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, if (atomic_read(&tbl->entries) > (1 << nht->hash_shift)) nht = neigh_hash_grow(tbl, nht->hash_shift + 1); - hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); + hash_val = tbl->hash(n->primary_key, dev, nht->hash_rnd) >> (32 - nht->hash_shift); if (n->parms->dead) { rc = ERR_PTR(-EINVAL); @@ -544,7 +544,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, n1 != NULL; n1 = rcu_dereference_protected(n1->next, lockdep_is_held(&tbl->lock))) { - if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) { + if (dev == n1->dev && !memcmp(n1->primary_key, n->primary_key, key_len)) { if (want_ref) neigh_hold(n1); rc = n1; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index a8d7c5a9fb05..6c231b43974d 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -223,11 +223,16 @@ static bool arp_key_eq(const struct neighbour *neigh, const void *pkey) static int arp_constructor(struct neighbour *neigh) { - __be32 addr = *(__be32 *)neigh->primary_key; + __be32 addr; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; + u32 inaddr_any = INADDR_ANY; + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len); + + addr = *(__be32 *)neigh->primary_key; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index d57aa64fa7c7..61fe6e4d23fc 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -981,6 +981,7 @@ static int esp_init_state(struct xfrm_state *x) switch (encap->encap_type) { default: + err = -EINVAL; goto error; case UDP_ENCAP_ESPINUDP: x->props.header_len += sizeof(struct udphdr); diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index f8b918c766b0..b1338e576d00 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -38,7 +38,8 @@ static struct sk_buff **esp4_gro_receive(struct sk_buff **head, __be32 spi; int err; - skb_pull(skb, offset); + if (!pskb_pull(skb, offset)) + return NULL; if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0) goto out; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 43b69af242e1..4e153b23bcec 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2762,6 +2762,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { + fl4.flowi4_iif = LOOPBACK_IFINDEX; rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb); err = 0; if (IS_ERR(rt)) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index a902ff8f59be..1a7f00cd4803 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -890,13 +890,12 @@ static int esp6_init_state(struct xfrm_state *x) x->props.header_len += IPV4_BEET_PHMAXLEN + (sizeof(struct ipv6hdr) - sizeof(struct iphdr)); break; + default: case XFRM_MODE_TRANSPORT: break; case XFRM_MODE_TUNNEL: x->props.header_len += sizeof(struct ipv6hdr); break; - default: - goto error; } align = ALIGN(crypto_aead_blocksize(aead), 4); diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 333a478aa161..dd9627490c7c 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -60,7 +60,8 @@ static struct sk_buff **esp6_gro_receive(struct sk_buff **head, int nhoff; int err; - skb_pull(skb, offset); + if (!pskb_pull(skb, offset)) + return NULL; if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0) goto out; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 688ba5f7516b..4f7d8de56611 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1206,14 +1206,16 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, v6_cork->tclass = ipc6->tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(&rt->dst); + READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst); else mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(rt->dst.path); + READ_ONCE(rt->dst.dev->mtu) : dst_mtu(rt->dst.path); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } + if (mtu < IPV6_MIN_MTU) + return -EINVAL; cork->base.fragsize = mtu; if (dst_allfrag(rt->dst.path)) cork->base.flags |= IPCORK_ALLFRAG; @@ -1733,6 +1735,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, cork.base.flags = 0; cork.base.addr = 0; cork.base.opt = NULL; + cork.base.dst = NULL; v6_cork.opt = NULL; err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6); if (err) { diff --git a/net/key/af_key.c b/net/key/af_key.c index 3dffb892d52c..7e2e7188e7f4 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -401,6 +401,11 @@ static int verify_address_len(const void *p) #endif int len; + if (sp->sadb_address_len < + DIV_ROUND_UP(sizeof(*sp) + offsetofend(typeof(*addr), sa_family), + sizeof(uint64_t))) + return -EINVAL; + switch (addr->sa_family) { case AF_INET: len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin), sizeof(uint64_t)); @@ -511,6 +516,9 @@ static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void * uint16_t ext_type; int ext_len; + if (len < sizeof(*ehdr)) + return -EINVAL; + ext_len = ehdr->sadb_ext_len; ext_len *= sizeof(uint64_t); ext_type = ehdr->sadb_ext_type; @@ -2194,8 +2202,10 @@ static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_ev return PTR_ERR(out_skb); err = pfkey_xfrm_policy2msg(out_skb, xp, dir); - if (err < 0) + if (err < 0) { + kfree_skb(out_skb); return err; + } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = PF_KEY_V2; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 79cc1bf36e4a..47ef2d8683d6 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2384,7 +2384,7 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)) { - struct netlink_ext_ack extack = {}; + struct netlink_ext_ack extack; struct nlmsghdr *nlh; int err; @@ -2405,6 +2405,7 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, if (nlh->nlmsg_type < NLMSG_MIN_TYPE) goto ack; + memset(&extack, 0, sizeof(extack)); err = cb(skb, nlh, &extack); if (err == -EINTR) goto skip; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 624ea74353dd..f143908b651d 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -49,7 +49,6 @@ #include <net/mpls.h> #include <net/vxlan.h> #include <net/tun_proto.h> -#include <net/erspan.h> #include "flow_netlink.h" @@ -334,8 +333,7 @@ size_t ovs_tun_key_attr_size(void) * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it. */ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */ - + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_DST */ - + nla_total_size(4); /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */ + + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */ } static size_t ovs_nsh_key_attr_size(void) @@ -402,7 +400,6 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] .next = ovs_vxlan_ext_key_lens }, [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, - [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = sizeof(u32) }, }; static const struct ovs_len_tbl @@ -634,33 +631,6 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, return 0; } -static int erspan_tun_opt_from_nlattr(const struct nlattr *attr, - struct sw_flow_match *match, bool is_mask, - bool log) -{ - unsigned long opt_key_offset; - struct erspan_metadata opts; - - BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); - - memset(&opts, 0, sizeof(opts)); - opts.index = nla_get_be32(attr); - - /* Index has only 20-bit */ - if (ntohl(opts.index) & ~INDEX_MASK) { - OVS_NLERR(log, "ERSPAN index number %x too large.", - ntohl(opts.index)); - return -EINVAL; - } - - SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), is_mask); - opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts)); - SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts), - is_mask); - - return 0; -} - static int ip_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) @@ -768,19 +738,6 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_PAD: break; - case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: - if (opts_type) { - OVS_NLERR(log, "Multiple metadata blocks provided"); - return -EINVAL; - } - - err = erspan_tun_opt_from_nlattr(a, match, is_mask, log); - if (err) - return err; - - tun_flags |= TUNNEL_ERSPAN_OPT; - opts_type = type; - break; default: OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); @@ -905,10 +862,6 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, else if (output->tun_flags & TUNNEL_VXLAN_OPT && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; - else if (output->tun_flags & TUNNEL_ERSPAN_OPT && - nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, - ((struct erspan_metadata *)tun_opts)->index)) - return -EMSGSIZE; } return 0; @@ -2533,8 +2486,6 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: break; - case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: - break; } }; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 0f1eab99ff4e..52529b7f8d96 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1063,17 +1063,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, } if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) { - if (qdisc_is_percpu_stats(sch)) { - sch->cpu_bstats = - netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); - if (!sch->cpu_bstats) - goto err_out4; - - sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); - if (!sch->cpu_qstats) - goto err_out4; - } - if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB]); if (IS_ERR(stab)) { @@ -1115,7 +1104,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, ops->destroy(sch); err_out3: dev_put(dev); - kfree((char *) sch - sch->padded); + qdisc_free(sch); err_out2: module_put(ops->owner); err_out: @@ -1123,8 +1112,6 @@ err_out: return NULL; err_out4: - free_percpu(sch->cpu_bstats); - free_percpu(sch->cpu_qstats); /* * Any broken qdiscs that would require a ops->reset() here? * The qdisc was never in action so it shouldn't be necessary. diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 661c7144b53a..cac003fddf3e 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -633,6 +633,19 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, qdisc_skb_head_init(&sch->q); spin_lock_init(&sch->q.lock); + if (ops->static_flags & TCQ_F_CPUSTATS) { + sch->cpu_bstats = + netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + if (!sch->cpu_bstats) + goto errout1; + + sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); + if (!sch->cpu_qstats) { + free_percpu(sch->cpu_bstats); + goto errout1; + } + } + spin_lock_init(&sch->busylock); lockdep_set_class(&sch->busylock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); @@ -642,6 +655,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, dev->qdisc_running_key ?: &qdisc_running_key); sch->ops = ops; + sch->flags = ops->static_flags; sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; @@ -649,6 +663,8 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, refcount_set(&sch->refcnt, 1); return sch; +errout1: + kfree(p); errout: return ERR_PTR(err); } @@ -698,7 +714,7 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -static void qdisc_free(struct Qdisc *qdisc) +void qdisc_free(struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index fc1286f499c1..003e1b063447 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -66,7 +66,6 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) { struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - int err; net_inc_ingress_queue(); @@ -76,13 +75,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) q->block_info.chain_head_change = clsact_chain_head_change; q->block_info.chain_head_change_priv = &q->miniqp; - err = tcf_block_get_ext(&q->block, sch, &q->block_info); - if (err) - return err; - - sch->flags |= TCQ_F_CPUSTATS; - - return 0; + return tcf_block_get_ext(&q->block, sch, &q->block_info); } static void ingress_destroy(struct Qdisc *sch) @@ -121,6 +114,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", .priv_size = sizeof(struct ingress_sched_data), + .static_flags = TCQ_F_CPUSTATS, .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, @@ -192,13 +186,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) q->egress_block_info.chain_head_change = clsact_chain_head_change; q->egress_block_info.chain_head_change_priv = &q->miniqp_egress; - err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info); - if (err) - return err; - - sch->flags |= TCQ_F_CPUSTATS; - - return 0; + return tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info); } static void clsact_destroy(struct Qdisc *sch) @@ -225,6 +213,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", .priv_size = sizeof(struct clsact_sched_data), + .static_flags = TCQ_F_CPUSTATS, .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 3b18085e3b10..5d4c15bf66d2 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -826,6 +826,7 @@ static int sctp_inet6_af_supported(sa_family_t family, struct sctp_sock *sp) case AF_INET: if (!__ipv6_only_sock(sctp_opt2sk(sp))) return 1; + /* fallthru */ default: return 0; } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 7d67feeeffc1..c4ec99b20150 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -918,9 +918,9 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) break; case SCTP_CID_ABORT: - if (sctp_test_T_bit(chunk)) { + if (sctp_test_T_bit(chunk)) packet->vtag = asoc->c.my_vtag; - } + /* fallthru */ /* The following chunks are "response" chunks, i.e. * they are generated in response to something we * received. If we are sending these, then we can diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9b01e994f661..039fcb618c34 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -85,7 +85,7 @@ static int sctp_writeable(struct sock *sk); static void sctp_wfree(struct sk_buff *skb); static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len, struct sock **orig_sk); + size_t msg_len); static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p); static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p); static int sctp_wait_for_accept(struct sock *sk, long timeo); @@ -335,16 +335,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, if (len < sizeof (struct sockaddr)) return NULL; + if (!opt->pf->af_supported(addr->sa.sa_family, opt)) + return NULL; + /* V4 mapped address are really of AF_INET family */ if (addr->sa.sa_family == AF_INET6 && - ipv6_addr_v4mapped(&addr->v6.sin6_addr)) { - if (!opt->pf->af_supported(AF_INET, opt)) - return NULL; - } else { - /* Does this PF support this AF? */ - if (!opt->pf->af_supported(addr->sa.sa_family, opt)) - return NULL; - } + ipv6_addr_v4mapped(&addr->v6.sin6_addr) && + !opt->pf->af_supported(AF_INET, opt)) + return NULL; /* If we get this far, af is valid. */ af = sctp_get_af_specific(addr->sa.sa_family); @@ -1883,8 +1881,14 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) */ if (sinit) { if (sinit->sinit_num_ostreams) { - asoc->c.sinit_num_ostreams = - sinit->sinit_num_ostreams; + __u16 outcnt = sinit->sinit_num_ostreams; + + asoc->c.sinit_num_ostreams = outcnt; + /* outcnt has been changed, so re-init stream */ + err = sctp_stream_init(&asoc->stream, outcnt, 0, + GFP_KERNEL); + if (err) + goto out_free; } if (sinit->sinit_max_instreams) { asoc->c.sinit_max_instreams = @@ -1971,7 +1975,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); if (!sctp_wspace(asoc)) { /* sk can be changed by peel off when waiting for buf. */ - err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len, &sk); + err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) { if (err == -ESRCH) { /* asoc is already dead. */ @@ -8016,12 +8020,12 @@ void sctp_sock_rfree(struct sk_buff *skb) /* Helper function to wait for space in the sndbuf. */ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len, struct sock **orig_sk) + size_t msg_len) { struct sock *sk = asoc->base.sk; - int err = 0; long current_timeo = *timeo_p; DEFINE_WAIT(wait); + int err = 0; pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc, *timeo_p, msg_len); @@ -8050,17 +8054,13 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, release_sock(sk); current_timeo = schedule_timeout(current_timeo); lock_sock(sk); - if (sk != asoc->base.sk) { - release_sock(sk); - sk = asoc->base.sk; - lock_sock(sk); - } + if (sk != asoc->base.sk) + goto do_error; *timeo_p = current_timeo; } out: - *orig_sk = sk; finish_wait(&asoc->wait, &wait); /* Release the association's refcnt. */ diff --git a/net/tipc/node.c b/net/tipc/node.c index 507017fe0f1b..9036d8756e73 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1880,36 +1880,38 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info) if (strcmp(name, tipc_bclink_name) == 0) { err = tipc_nl_add_bc_link(net, &msg); - if (err) { - nlmsg_free(msg.skb); - return err; - } + if (err) + goto err_free; } else { int bearer_id; struct tipc_node *node; struct tipc_link *link; node = tipc_node_find_by_name(net, name, &bearer_id); - if (!node) - return -EINVAL; + if (!node) { + err = -EINVAL; + goto err_free; + } tipc_node_read_lock(node); link = node->links[bearer_id].link; if (!link) { tipc_node_read_unlock(node); - nlmsg_free(msg.skb); - return -EINVAL; + err = -EINVAL; + goto err_free; } err = __tipc_nl_add_link(net, &msg, link, 0); tipc_node_read_unlock(node); - if (err) { - nlmsg_free(msg.skb); - return err; - } + if (err) + goto err_free; } return genlmsg_reply(msg.skb, info); + +err_free: + nlmsg_free(msg.skb); + return err; } int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 73d19210dd49..9773571b6a34 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -391,7 +391,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) while (msg_data_left(msg)) { if (sk->sk_err) { - ret = sk->sk_err; + ret = -sk->sk_err; goto send_end; } @@ -544,7 +544,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, size_t copy, required_size; if (sk->sk_err) { - ret = sk->sk_err; + ret = -sk->sk_err; goto sendpage_end; } diff --git a/net/wireless/core.c b/net/wireless/core.c index fdde0d98fde1..a6f3cac8c640 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -439,6 +439,8 @@ struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv, if (rv) goto use_default_name; } else { + int rv; + use_default_name: /* NOTE: This is *probably* safe w/out holding rtnl because of * the restrictions on phy names. Probably this call could @@ -446,7 +448,11 @@ use_default_name: * phyX. But, might should add some locking and check return * value, and use a different name if this one exists? */ - dev_set_name(&rdev->wiphy.dev, PHY_NAME "%d", rdev->wiphy_idx); + rv = dev_set_name(&rdev->wiphy.dev, PHY_NAME "%d", rdev->wiphy_idx); + if (rv < 0) { + kfree(rdev); + return NULL; + } } INIT_LIST_HEAD(&rdev->wiphy.wdev_list); diff --git a/net/wireless/core.h b/net/wireless/core.h index d2f7e8b8a097..eaff636169c2 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -507,8 +507,6 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, void cfg80211_stop_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); -#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 - #ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS #define CFG80211_DEV_WARN_ON(cond) WARN_ON(cond) #else diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2b3dbcd40e46..ed87a97fcb0b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2618,12 +2618,13 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag const u8 *ssid_ie; if (!wdev->current_bss) break; + rcu_read_lock(); ssid_ie = ieee80211_bss_get_ie(&wdev->current_bss->pub, WLAN_EID_SSID); - if (!ssid_ie) - break; - if (nla_put(msg, NL80211_ATTR_SSID, ssid_ie[1], ssid_ie + 2)) - goto nla_put_failure_locked; + if (ssid_ie && + nla_put(msg, NL80211_ATTR_SSID, ssid_ie[1], ssid_ie + 2)) + goto nla_put_failure_rcu_locked; + rcu_read_unlock(); break; } default: @@ -2635,6 +2636,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag genlmsg_end(msg, hdr); return 0; + nla_put_failure_rcu_locked: + rcu_read_unlock(); nla_put_failure_locked: wdev_unlock(wdev); nla_put_failure: diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 78e71b0390be..7b42f0bacfd8 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1769,8 +1769,7 @@ static void handle_reg_beacon(struct wiphy *wiphy, unsigned int chan_idx, if (wiphy->regulatory_flags & REGULATORY_DISABLE_BEACON_HINTS) return; - chan_before.center_freq = chan->center_freq; - chan_before.flags = chan->flags; + chan_before = *chan; if (chan->flags & IEEE80211_CHAN_NO_IR) { chan->flags &= ~IEEE80211_CHAN_NO_IR; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 3f6f6f8c9fa5..5b2409746ae0 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -518,7 +518,7 @@ int xfrm_trans_queue(struct sk_buff *skb, return -ENOBUFS; XFRM_TRANS_SKB_CB(skb)->finish = finish; - skb_queue_tail(&trans->queue, skb); + __skb_queue_tail(&trans->queue, skb); tasklet_schedule(&trans->tasklet); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 70aa5cb0c659..bd6b0e7a0ee4 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -609,7 +609,8 @@ static void xfrm_hash_rebuild(struct work_struct *work) /* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { - if (xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) { + if (policy->walk.dead || + xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) { /* skip socket policies */ continue; } @@ -974,8 +975,6 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) } if (!cnt) err = -ESRCH; - else - xfrm_policy_cache_flush(); out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; @@ -1743,6 +1742,8 @@ void xfrm_policy_cache_flush(void) bool found = 0; int cpu; + might_sleep(); + local_bh_disable(); rcu_read_lock(); for_each_possible_cpu(cpu) { @@ -2062,8 +2063,11 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, if (num_xfrms <= 0) goto make_dummy_bundle; + local_bh_disable(); xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, - xflo->dst_orig); + xflo->dst_orig); + local_bh_enable(); + if (IS_ERR(xdst)) { err = PTR_ERR(xdst); if (err != -EAGAIN) @@ -2150,9 +2154,12 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, goto no_transform; } + local_bh_disable(); xdst = xfrm_resolve_and_create_bundle( pols, num_pols, fl, family, dst_orig); + local_bh_enable(); + if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 500b3391f474..429957412633 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -313,13 +313,14 @@ retry: if ((type && !try_module_get(type->owner))) type = NULL; + rcu_read_unlock(); + if (!type && try_load) { request_module("xfrm-offload-%d-%d", family, proto); try_load = 0; goto retry; } - rcu_read_unlock(); return type; } @@ -1534,8 +1535,12 @@ out: err = -EINVAL; spin_lock_bh(&x1->lock); if (likely(x1->km.state == XFRM_STATE_VALID)) { - if (x->encap && x1->encap) + if (x->encap && x1->encap && + x->encap->encap_type == x1->encap->encap_type) memcpy(x1->encap, x->encap, sizeof(*x1->encap)); + else if (x->encap || x1->encap) + goto fail; + if (x->coaddr && x1->coaddr) { memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr)); } @@ -1552,6 +1557,8 @@ out: x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); } + +fail: spin_unlock_bh(&x1->lock); xfrm_state_put(x1); diff --git a/scripts/Makefile.build b/scripts/Makefile.build index cb8997ed0149..47cddf32aeba 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -265,12 +265,18 @@ else objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable) endif +ifdef CONFIG_MODVERSIONS +objtool_o = $(@D)/.tmp_$(@F) +else +objtool_o = $(@) +endif + # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file # 'OBJECT_FILES_NON_STANDARD_foo.o := 'n': override directory skip for a file cmd_objtool = $(if $(patsubst y%,, \ $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \ - $(__objtool_obj) $(objtool_args) "$(@)";) + $(__objtool_obj) $(objtool_args) "$(objtool_o)";) objtool_obj = $(if $(patsubst y%,, \ $(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \ $(__objtool_obj)) @@ -286,16 +292,16 @@ objtool_dep = $(objtool_obj) \ define rule_cc_o_c $(call echo-cmd,checksrc) $(cmd_checksrc) \ $(call cmd_and_fixdep,cc_o_c) \ - $(cmd_modversions_c) \ $(cmd_checkdoc) \ $(call echo-cmd,objtool) $(cmd_objtool) \ + $(cmd_modversions_c) \ $(call echo-cmd,record_mcount) $(cmd_record_mcount) endef define rule_as_o_S $(call cmd_and_fixdep,as_o_S) \ - $(cmd_modversions_S) \ - $(call echo-cmd,objtool) $(cmd_objtool) + $(call echo-cmd,objtool) $(cmd_objtool) \ + $(cmd_modversions_S) endef # List module undefined symbols (or empty line if not enabled) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index db7894bb028c..faa67861cbc1 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -560,7 +560,6 @@ static inline unsigned int muldiv32(unsigned int a, unsigned int b, { u_int64_t n = (u_int64_t) a * b; if (c == 0) { - snd_BUG_ON(!n); *r = 0; return UINT_MAX; } diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 6e22eea72654..d01913404581 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -221,6 +221,7 @@ static struct snd_seq_client *seq_create_client1(int client_index, int poolsize) rwlock_init(&client->ports_lock); mutex_init(&client->ports_mutex); INIT_LIST_HEAD(&client->ports_list_head); + mutex_init(&client->ioctl_mutex); /* find free slot in the client table */ spin_lock_irqsave(&clients_lock, flags); @@ -2130,7 +2131,9 @@ static long snd_seq_ioctl(struct file *file, unsigned int cmd, return -EFAULT; } + mutex_lock(&client->ioctl_mutex); err = handler->func(client, &buf); + mutex_unlock(&client->ioctl_mutex); if (err >= 0) { /* Some commands includes a bug in 'dir' field. */ if (handler->cmd == SNDRV_SEQ_IOCTL_SET_QUEUE_CLIENT || diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h index c6614254ef8a..0611e1e0ed5b 100644 --- a/sound/core/seq/seq_clientmgr.h +++ b/sound/core/seq/seq_clientmgr.h @@ -61,6 +61,7 @@ struct snd_seq_client { struct list_head ports_list_head; rwlock_t ports_lock; struct mutex ports_mutex; + struct mutex ioctl_mutex; int convert32; /* convert 32->64bit */ /* output pool */ diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index 80bbadc83721..d6e079f4ec09 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -408,6 +408,7 @@ static const struct snd_pci_quirk cs420x_fixup_tbl[] = { /*SND_PCI_QUIRK(0x8086, 0x7270, "IMac 27 Inch", CS420X_IMAC27),*/ /* codec SSID */ + SND_PCI_QUIRK(0x106b, 0x0600, "iMac 14,1", CS420X_IMAC27_122), SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81), SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122), SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8fd2d9c62c96..9aafc6c86132 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6196,6 +6196,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), + SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 24460155c82c..c1c338661699 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -26,6 +26,7 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> +#include <errno.h> #include "elf.h" #include "warn.h" @@ -358,7 +359,8 @@ struct elf *elf_open(const char *name, int flags) elf->fd = open(name, flags); if (elf->fd == -1) { - perror("open"); + fprintf(stderr, "objtool: Can't open '%s': %s\n", + name, strerror(errno)); goto err; } diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index b51017404c62..6bafa5456568 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -273,6 +273,46 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "arsh32 on imm", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 5), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "BPF_ARSH not supported for 32 bit ALU", + }, + { + "arsh32 on reg", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU32_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "BPF_ARSH not supported for 32 bit ALU", + }, + { + "arsh64 on imm", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_0, 5), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "arsh64 on reg", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU64_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { "no bpf_exit", .insns = { BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2), |