diff --git a/Makefile b/Makefile index 5f3e285d9812..611d7de2e3a2 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 6 -SUBLEVEL = 62 +SUBLEVEL = 63 EXTRAVERSION = NAME = Pinguïn Aangedreven diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 1ec35f065617..28873cda464f 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -252,11 +252,15 @@ __create_page_tables: */ add r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ENTRY_ORDER) ldr r6, =(_end - 1) + + /* For XIP, kernel_sec_start/kernel_sec_end are currently in RO memory */ +#ifndef CONFIG_XIP_KERNEL adr_l r5, kernel_sec_start @ _pa(kernel_sec_start) #if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32 str r8, [r5, #4] @ Save physical start of kernel (BE) #else str r8, [r5] @ Save physical start of kernel (LE) +#endif #endif orr r3, r8, r7 @ Add the MMU flags add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ENTRY_ORDER) @@ -264,6 +268,7 @@ __create_page_tables: add r3, r3, #1 << SECTION_SHIFT cmp r0, r6 bls 1b +#ifndef CONFIG_XIP_KERNEL eor r3, r3, r7 @ Remove the MMU flags adr_l r5, kernel_sec_end @ _pa(kernel_sec_end) #if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32 @@ -271,8 +276,7 @@ __create_page_tables: #else str r3, [r5] @ Save physical end of kernel (LE) #endif - -#ifdef CONFIG_XIP_KERNEL +#else /* * Map the kernel image separately as it is not located in RAM. */ diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 674ed71573a8..073de5b24560 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1402,18 +1402,6 @@ static void __init devicemaps_init(const struct machine_desc *mdesc) create_mapping(&map); } - /* - * Map the kernel if it is XIP. - * It is always first in the modulearea. - */ -#ifdef CONFIG_XIP_KERNEL - map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK); - map.virtual = MODULES_VADDR; - map.length = ((unsigned long)_exiprom - map.virtual + ~SECTION_MASK) & SECTION_MASK; - map.type = MT_ROM; - create_mapping(&map); -#endif - /* * Map the cache flushing regions. */ @@ -1603,12 +1591,27 @@ static void __init map_kernel(void) * This will only persist until we turn on proper memory management later on * and we remap the whole kernel with page granularity. */ +#ifdef CONFIG_XIP_KERNEL + phys_addr_t kernel_nx_start = kernel_sec_start; +#else phys_addr_t kernel_x_start = kernel_sec_start; phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE); phys_addr_t kernel_nx_start = kernel_x_end; +#endif phys_addr_t kernel_nx_end = kernel_sec_end; struct map_desc map; + /* + * Map the kernel if it is XIP. + * It is always first in the modulearea. + */ +#ifdef CONFIG_XIP_KERNEL + map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK); + map.virtual = MODULES_VADDR; + map.length = ((unsigned long)_exiprom - map.virtual + ~SECTION_MASK) & SECTION_MASK; + map.type = MT_ROM; + create_mapping(&map); +#else map.pfn = __phys_to_pfn(kernel_x_start); map.virtual = __phys_to_virt(kernel_x_start); map.length = kernel_x_end - kernel_x_start; @@ -1618,7 +1621,7 @@ static void __init map_kernel(void) /* If the nx part is small it may end up covered by the tail of the RWX section */ if (kernel_x_end == kernel_nx_end) return; - +#endif map.pfn = __phys_to_pfn(kernel_nx_start); map.virtual = __phys_to_virt(kernel_nx_start); map.length = kernel_nx_end - kernel_nx_start; @@ -1763,6 +1766,11 @@ void __init paging_init(const struct machine_desc *mdesc) { void *zero_page; +#ifdef CONFIG_XIP_KERNEL + /* Store the kernel RW RAM region start/end in these variables */ + kernel_sec_start = CONFIG_PHYS_OFFSET & SECTION_MASK; + kernel_sec_end = round_up(__pa(_end), SECTION_SIZE); +#endif pr_debug("physical kernel sections: 0x%08llx-0x%08llx\n", kernel_sec_start, kernel_sec_end); diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h index 5966ee4a6154..ef35c52aabd6 100644 --- a/arch/arm64/include/asm/mman.h +++ b/arch/arm64/include/asm/mman.h @@ -3,6 +3,8 @@ #define __ASM_MMAN_H__ #include <linux/compiler.h> +#include <linux/fs.h> +#include <linux/shmem_fs.h> #include <linux/types.h> #include <uapi/asm/mman.h> @@ -21,19 +23,21 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) -static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) +static inline unsigned long arch_calc_vm_flag_bits(struct file *file, + unsigned long flags) { /* * Only allow MTE on anonymous mappings as these are guaranteed to be * backed by tags-capable memory. The vm_flags may be overridden by a * filesystem supporting MTE (RAM-based). */ - if (system_supports_mte() && (flags & MAP_ANONYMOUS)) + if (system_supports_mte() && + ((flags & MAP_ANONYMOUS) || shmem_file(file))) return VM_MTE_ALLOWED; return 0; } -#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) +#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags) static inline bool arch_validate_prot(unsigned long prot, unsigned long addr __always_unused) diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h index c6bce5fbff57..cb74a47f620e 100644 --- a/arch/loongarch/include/asm/kasan.h +++ b/arch/loongarch/include/asm/kasan.h @@ -51,7 +51,7 @@ /* KAsan shadow memory start right after vmalloc. */ #define KASAN_SHADOW_START round_up(KFENCE_AREA_END, PGDIR_SIZE) #define KASAN_SHADOW_SIZE (XKVRANGE_VC_SHADOW_END - XKPRANGE_CC_KASAN_OFFSET) -#define KASAN_SHADOW_END round_up(KASAN_SHADOW_START + KASAN_SHADOW_SIZE, PGDIR_SIZE) +#define KASAN_SHADOW_END (round_up(KASAN_SHADOW_START + KASAN_SHADOW_SIZE, PGDIR_SIZE) - 1) #define XKPRANGE_CC_SHADOW_OFFSET (KASAN_SHADOW_START + XKPRANGE_CC_KASAN_OFFSET) #define XKPRANGE_UC_SHADOW_OFFSET (KASAN_SHADOW_START + XKPRANGE_UC_KASAN_OFFSET) diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index d74dfe1206ed..9dbe7907a961 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -272,7 +272,7 @@ static void __init fdt_smp_setup(void) __cpu_number_map[cpuid] = cpu; __cpu_logical_map[cpu] = cpuid; - early_numa_add_cpu(cpu, 0); + early_numa_add_cpu(cpuid, 0); set_cpuid_to_node(cpuid, 0); } diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c index c608adc99845..082cb2a6f1ef 100644 --- a/arch/loongarch/mm/kasan_init.c +++ b/arch/loongarch/mm/kasan_init.c @@ -13,6 +13,13 @@ static pgd_t kasan_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); +#ifdef __PAGETABLE_P4D_FOLDED +#define __pgd_none(early, pgd) (0) +#else +#define __pgd_none(early, pgd) (early ? (pgd_val(pgd) == 0) : \ +(__pa(pgd_val(pgd)) == (unsigned long)__pa(kasan_early_shadow_p4d))) +#endif + #ifdef __PAGETABLE_PUD_FOLDED #define __p4d_none(early, p4d) (0) #else @@ -142,6 +149,19 @@ static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, return pud_offset(p4dp, addr); } +static p4d_t *__init kasan_p4d_offset(pgd_t *pgdp, unsigned long addr, int node, bool early) +{ + if (__pgd_none(early, pgdp_get(pgdp))) { + phys_addr_t p4d_phys = early ? + __pa_symbol(kasan_early_shadow_p4d) : kasan_alloc_zeroed_page(node); + if (!early) + memcpy(__va(p4d_phys), kasan_early_shadow_p4d, sizeof(kasan_early_shadow_p4d)); + pgd_populate(&init_mm, pgdp, (p4d_t *)__va(p4d_phys)); + } + + return p4d_offset(pgdp, addr); +} + static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, unsigned long end, int node, bool early) { @@ -178,19 +198,19 @@ static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr, do { next = pud_addr_end(addr, end); kasan_pmd_populate(pudp, addr, next, node, early); - } while (pudp++, addr = next, addr != end); + } while (pudp++, addr = next, addr != end && __pud_none(early, READ_ONCE(*pudp))); } static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - p4d_t *p4dp = p4d_offset(pgdp, addr); + p4d_t *p4dp = kasan_p4d_offset(pgdp, addr, node, early); do { next = p4d_addr_end(addr, end); kasan_pud_populate(p4dp, addr, next, node, early); - } while (p4dp++, addr = next, addr != end); + } while (p4dp++, addr = next, addr != end && __p4d_none(early, READ_ONCE(*p4dp))); } static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, @@ -218,7 +238,7 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end, asmlinkage void __init kasan_early_init(void) { BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE)); - BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END + 1, PGDIR_SIZE)); } static inline void kasan_set_pgd(pgd_t *pgdp, pgd_t pgdval) @@ -233,7 +253,7 @@ static void __init clear_pgds(unsigned long start, unsigned long end) * swapper_pg_dir. pgd_clear() can't be used * here because it's nop on 2,3-level pagetable setups */ - for (; start < end; start += PGDIR_SIZE) + for (; start < end; start = pgd_addr_end(start, end)) kasan_set_pgd((pgd_t *)pgd_offset_k(start), __pgd(0)); } @@ -242,6 +262,17 @@ void __init kasan_init(void) u64 i; phys_addr_t pa_start, pa_end; + /* + * If PGDIR_SIZE is too large for cpu_vabits, KASAN_SHADOW_END will + * overflow UINTPTR_MAX and then looks like a user space address. + * For example, PGDIR_SIZE of CONFIG_4KB_4LEVEL is 2^39, which is too + * large for Loongson-2K series whose cpu_vabits = 39. + */ + if (KASAN_SHADOW_END < vm_map_base) { + pr_warn("PGDIR_SIZE too large for cpu_vabits, KernelAddressSanitizer disabled.\n"); + return; + } + /* * PGD was populated as invalid_pmd_table or invalid_pud_table * in pagetable_init() which depends on how many levels of page diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h index 89b6beeda0b8..663f587dc789 100644 --- a/arch/parisc/include/asm/mman.h +++ b/arch/parisc/include/asm/mman.h @@ -2,6 +2,7 @@ #ifndef __ASM_MMAN_H__ #define __ASM_MMAN_H__ +#include <linux/fs.h> #include <uapi/asm/mman.h> /* PARISC cannot allow mdwe as it needs writable stacks */ @@ -11,7 +12,7 @@ static inline bool arch_memory_deny_write_exec_supported(void) } #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported -static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) +static inline unsigned long arch_calc_vm_flag_bits(struct file *file, unsigned long flags) { /* * The stack on parisc grows upwards, so if userspace requests memory @@ -23,6 +24,6 @@ static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) return 0; } -#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) +#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags) #endif /* __ASM_MMAN_H__ */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 1380f3489777..34766abbabd8 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2603,19 +2603,26 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - if (apic->apicv_active) { - /* irr_pending is always true when apicv is activated. */ - apic->irr_pending = true; + /* + * When APICv is enabled, KVM must always search the IRR for a pending + * IRQ, as other vCPUs and devices can set IRR bits even if the vCPU + * isn't running. If APICv is disabled, KVM _should_ search the IRR + * for a pending IRQ. But KVM currently doesn't ensure *all* hardware, + * e.g. CPUs and IOMMUs, has seen the change in state, i.e. searching + * the IRR at this time could race with IRQ delivery from hardware that + * still sees APICv as being enabled. + * + * FIXME: Ensure other vCPUs and devices observe the change in APICv + * state prior to updating KVM's metadata caches, so that KVM + * can safely search the IRR and set irr_pending accordingly. + */ + apic->irr_pending = true; + + if (apic->apicv_active) apic->isr_count = 1; - } else { - /* - * Don't clear irr_pending, searching the IRR can race with - * updates from the CPU as APICv is still active from hardware's - * perspective. The flag will be cleared as appropriate when - * KVM injects the interrupt. - */ + else apic->isr_count = count_vectors(apic->regs + APIC_ISR); - } + apic->highest_isr_cache = -1; } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0ad66b9207e8..d3e346a574f1 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -1150,11 +1150,14 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); /* - * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings - * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a - * full TLB flush from the guest's perspective. This is required even - * if VPID is disabled in the host as KVM may need to synchronize the - * MMU in response to the guest TLB flush. + * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the + * same VPID as the host, and so architecturally, linear and combined + * mappings for VPID=0 must be flushed at VM-Enter and VM-Exit. KVM + * emulates L2 sharing L1's VPID=0 by using vpid01 while running L2, + * and so KVM must also emulate TLB flush of VPID=0, i.e. vpid01. This + * is required if VPID is disabled in KVM, as a TLB flush (there are no + * VPIDs) still occurs from L1's perspective, and KVM may need to + * synchronize the MMU in response to the guest TLB flush. * * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use. * EPT is a special snowflake, as guest-physical mappings aren't @@ -2229,6 +2232,17 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); + /* + * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the + * same VPID as the host. Emulate this behavior by using vpid01 for L2 + * if VPID is disabled in vmcs12. Note, if VPID is disabled, VM-Enter + * and VM-Exit are architecturally required to flush VPID=0, but *only* + * VPID=0. I.e. using vpid02 would be ok (so long as KVM emulates the + * required flushes), but doing so would cause KVM to over-flush. E.g. + * if L1 runs L2 X with VPID12=1, then runs L2 Y with VPID12 disabled, + * and then runs L2 X again, then KVM can and should retain TLB entries + * for VPID12=1. + */ if (enable_vpid) { if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); @@ -5827,6 +5841,12 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + /* + * Always flush the effective vpid02, i.e. never flush the current VPID + * and never explicitly flush vpid01. INVVPID targets a VPID, not a + * VMCS, and so whether or not the current vmcs12 has VPID enabled is + * irrelevant (and there may not be a loaded vmcs12). + */ vpid02 = nested_get_vpid02(vcpu); switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 2e0106d9d371..479ef26626f2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -212,9 +212,11 @@ module_param(ple_window_shrink, uint, 0444); static unsigned int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX; module_param(ple_window_max, uint, 0444); -/* Default is SYSTEM mode, 1 for host-guest mode */ +/* Default is SYSTEM mode, 1 for host-guest mode (which is BROKEN) */ int __read_mostly pt_mode = PT_MODE_SYSTEM; +#ifdef CONFIG_BROKEN module_param(pt_mode, int, S_IRUGO); +#endif static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); @@ -3193,7 +3195,7 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu)) + if (is_guest_mode(vcpu) && nested_cpu_has_vpid(get_vmcs12(vcpu))) return nested_get_vpid02(vcpu); return to_vmx(vcpu)->vpid; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index aa7d279321ea..2c102dc164e1 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -655,7 +655,8 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, paddr_next = data->next; len = data->len; - if ((phys_addr > paddr) && (phys_addr < (paddr + len))) { + if ((phys_addr > paddr) && + (phys_addr < (paddr + sizeof(struct setup_data) + len))) { memunmap(data); return true; } @@ -717,7 +718,8 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, paddr_next = data->next; len = data->len; - if ((phys_addr > paddr) && (phys_addr < (paddr + len))) { + if ((phys_addr > paddr) && + (phys_addr < (paddr + sizeof(struct setup_data) + len))) { early_memunmap(data, sizeof(*data)); return true; } diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index a936219aebb8..3773cd9d998d 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -2928,13 +2928,12 @@ static int btintel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb) case INTEL_TLV_TEST_EXCEPTION: /* Generate devcoredump from exception */ if (!hci_devcd_init(hdev, skb->len)) { - hci_devcd_append(hdev, skb); + hci_devcd_append(hdev, skb_clone(skb, GFP_ATOMIC)); hci_devcd_complete(hdev); } else { bt_dev_err(hdev, "Failed to generate devcoredump"); - kfree_skb(skb); } - return 0; + break; default: bt_dev_err(hdev, "Invalid exception type %02X", tlv->val[0]); } diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c index def89379b51a..d23e7391c6f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c @@ -247,6 +247,12 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_SOC15(NBIO, 0, regBIF0_PCIE_MST_CTRL_3, data); + switch (adev->ip_versions[NBIO_HWIP][0]) { + case IP_VERSION(7, 7, 0): + data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4) & ~BIT(23); + WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4, data); + break; + } } static void nbio_v7_7_update_medium_grain_clock_gating(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index a3f17c572bf0..8a152f4974d3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -10725,7 +10725,7 @@ static int parse_amd_vsdb(struct amdgpu_dm_connector *aconnector, break; } - while (j < EDID_LENGTH) { + while (j < EDID_LENGTH - sizeof(struct amd_vsdb_block)) { struct amd_vsdb_block *amd_vsdb = (struct amd_vsdb_block *)&edid_ext[j]; unsigned int ieeeId = (amd_vsdb->ieee_id[2] << 16) | (amd_vsdb->ieee_id[1] << 8) | (amd_vsdb->ieee_id[0]); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index f46cda889483..454216bd6f1d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -256,10 +256,9 @@ static int vangogh_tables_init(struct smu_context *smu) goto err0_out; smu_table->metrics_time = 0; - if (smu_version >= 0x043F3E00) - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_3); - else - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2); + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2); + smu_table->gpu_metrics_table_size = max(smu_table->gpu_metrics_table_size, sizeof(struct gpu_metrics_v2_3)); + smu_table->gpu_metrics_table_size = max(smu_table->gpu_metrics_table_size, sizeof(struct gpu_metrics_v2_4)); smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL); if (!smu_table->gpu_metrics_table) goto err1_out; diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index c72d5fbbb0ec..5d5834a286f0 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -125,6 +125,9 @@ #define TC358768_DSI_CONFW_MODE_CLR (6 << 29) #define TC358768_DSI_CONFW_ADDR_DSI_CONTROL (0x3 << 24) +/* TC358768_DSICMD_TX (0x0600) register */ +#define TC358768_DSI_CMDTX_DC_START BIT(0) + static const char * const tc358768_supplies[] = { "vddc", "vddmipi", "vddio" }; @@ -229,6 +232,21 @@ static void tc358768_update_bits(struct tc358768_priv *priv, u32 reg, u32 mask, tc358768_write(priv, reg, tmp); } +static void tc358768_dsicmd_tx(struct tc358768_priv *priv) +{ + u32 val; + + /* start transfer */ + tc358768_write(priv, TC358768_DSICMD_TX, TC358768_DSI_CMDTX_DC_START); + if (priv->error) + return; + + /* wait transfer completion */ + priv->error = regmap_read_poll_timeout(priv->regmap, TC358768_DSICMD_TX, val, + (val & TC358768_DSI_CMDTX_DC_START) == 0, + 100, 100000); +} + static int tc358768_sw_reset(struct tc358768_priv *priv) { /* Assert Reset */ @@ -516,8 +534,7 @@ static ssize_t tc358768_dsi_host_transfer(struct mipi_dsi_host *host, } } - /* start transfer */ - tc358768_write(priv, TC358768_DSICMD_TX, 1); + tc358768_dsicmd_tx(priv); ret = tc358768_clear_error(priv); if (ret) diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c index a1c8545f1249..cac6d64ab67d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c @@ -89,11 +89,6 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user, nvkm_falcon_fw_dtor_sigs(fw); } - /* after last write to the img, sync dma mappings */ - dma_sync_single_for_device(fw->fw.device->dev, - fw->fw.phys, - sg_dma_len(&fw->fw.mem.sgl), - DMA_TO_DEVICE); FLCNFW_DBG(fw, "resetting"); fw->func->reset(fw); @@ -105,6 +100,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user, goto done; } + /* after last write to the img, sync dma mappings */ + dma_sync_single_for_device(fw->fw.device->dev, + fw->fw.phys, + sg_dma_len(&fw->fw.mem.sgl), + DMA_TO_DEVICE); + ret = fw->func->load(fw); if (ret) goto done; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index ee72e8c6ad69..a34d3fc66248 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -1076,10 +1076,10 @@ static int vop_plane_atomic_async_check(struct drm_plane *plane, if (!plane->state->fb) return -EINVAL; - if (state) - crtc_state = drm_atomic_get_existing_crtc_state(state, - new_plane_state->crtc); - else /* Special case for asynchronous cursor updates. */ + crtc_state = drm_atomic_get_existing_crtc_state(state, new_plane_state->crtc); + + /* Special case for asynchronous cursor updates. */ + if (!crtc_state) crtc_state = plane->crtc->state; return drm_atomic_helper_check_plane_state(plane->state, crtc_state, diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index fd78d678877c..f253295795f0 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -269,8 +269,6 @@ rdma_find_ndev_for_src_ip_rcu(struct net *net, const struct sockaddr *src_in) break; #endif } - if (!ret && dev && is_vlan_dev(dev)) - dev = vlan_dev_real_dev(dev); return ret ? ERR_PTR(ret) : dev; } diff --git a/drivers/leds/leds-mlxreg.c b/drivers/leds/leds-mlxreg.c index 39210653acf7..b1510cd32e47 100644 --- a/drivers/leds/leds-mlxreg.c +++ b/drivers/leds/leds-mlxreg.c @@ -257,6 +257,7 @@ static int mlxreg_led_probe(struct platform_device *pdev) { struct mlxreg_core_platform_data *led_pdata; struct mlxreg_led_priv_data *priv; + int err; led_pdata = dev_get_platdata(&pdev->dev); if (!led_pdata) { @@ -268,28 +269,21 @@ static int mlxreg_led_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - mutex_init(&priv->access_lock); + err = devm_mutex_init(&pdev->dev, &priv->access_lock); + if (err) + return err; + priv->pdev = pdev; priv->pdata = led_pdata; return mlxreg_led_config(priv); } -static int mlxreg_led_remove(struct platform_device *pdev) -{ - struct mlxreg_led_priv_data *priv = dev_get_drvdata(&pdev->dev); - - mutex_destroy(&priv->access_lock); - - return 0; -} - static struct platform_driver mlxreg_led_driver = { .driver = { .name = "leds-mlxreg", }, .probe = mlxreg_led_probe, - .remove = mlxreg_led_remove, }; module_platform_driver(mlxreg_led_driver); diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index 14f323fbada7..9df7c213716a 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -530,6 +530,9 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, for (minor = 0; minor < MAX_DVB_MINORS; minor++) if (!dvb_minors[minor]) break; +#else + minor = nums2minor(adap->num, type, id); +#endif if (minor >= MAX_DVB_MINORS) { if (new_node) { list_del(&new_node->list_head); @@ -543,17 +546,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, mutex_unlock(&dvbdev_register_lock); return -EINVAL; } -#else - minor = nums2minor(adap->num, type, id); - if (minor >= MAX_DVB_MINORS) { - dvb_media_device_free(dvbdev); - list_del(&dvbdev->list_head); - kfree(dvbdev); - *pdvbdev = NULL; - mutex_unlock(&dvbdev_register_lock); - return ret; - } -#endif + dvbdev->minor = minor; dvb_minors[minor] = dvb_device_get(dvbdev); up_write(&minor_rwsem); diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 2f0bc79ef856..02bee7afab37 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -2952,8 +2952,8 @@ static int dw_mci_init_slot(struct dw_mci *host) if (host->use_dma == TRANS_MODE_IDMAC) { mmc->max_segs = host->ring_size; mmc->max_blk_size = 65535; - mmc->max_req_size = DW_MCI_DESC_DATA_LENGTH * host->ring_size; - mmc->max_seg_size = mmc->max_req_size; + mmc->max_seg_size = 0x1000; + mmc->max_req_size = mmc->max_seg_size * host->ring_size; mmc->max_blk_count = mmc->max_req_size / 512; } else if (host->use_dma == TRANS_MODE_EDMAC) { mmc->max_segs = 64; diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index d3bd0ac99ec4..e0ab5fd635e6 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -1191,10 +1191,9 @@ static const struct sunxi_mmc_cfg sun50i_a64_emmc_cfg = { .needs_new_timings = true, }; -static const struct sunxi_mmc_cfg sun50i_a100_cfg = { +static const struct sunxi_mmc_cfg sun50i_h616_cfg = { .idma_des_size_bits = 16, .idma_des_shift = 2, - .clk_delays = NULL, .can_calibrate = true, .mask_data0 = true, .needs_new_timings = true, @@ -1217,8 +1216,9 @@ static const struct of_device_id sunxi_mmc_of_match[] = { { .compatible = "allwinner,sun20i-d1-mmc", .data = &sun20i_d1_cfg }, { .compatible = "allwinner,sun50i-a64-mmc", .data = &sun50i_a64_cfg }, { .compatible = "allwinner,sun50i-a64-emmc", .data = &sun50i_a64_emmc_cfg }, - { .compatible = "allwinner,sun50i-a100-mmc", .data = &sun50i_a100_cfg }, + { .compatible = "allwinner,sun50i-a100-mmc", .data = &sun20i_d1_cfg }, { .compatible = "allwinner,sun50i-a100-emmc", .data = &sun50i_a100_emmc_cfg }, + { .compatible = "allwinner,sun50i-h616-mmc", .data = &sun50i_h616_cfg }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, sunxi_mmc_of_match); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 14b4780b73c7..bee93a437f99 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -934,6 +934,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_UP) bond_hw_addr_flush(bond->dev, old_active->dev); + + bond_slave_ns_maddrs_add(bond, old_active); } if (new_active) { @@ -950,6 +952,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, dev_mc_sync(new_active->dev, bond->dev); netif_addr_unlock_bh(bond->dev); } + + bond_slave_ns_maddrs_del(bond, new_active); } } @@ -2267,6 +2271,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, bond_compute_features(bond); bond_set_carrier(bond); + /* Needs to be called before bond_select_active_slave(), which will + * remove the maddrs if the slave is selected as active slave. + */ + bond_slave_ns_maddrs_add(bond, new_slave); + if (bond_uses_primary(bond)) { block_netpoll_tx(); bond_select_active_slave(bond); @@ -2276,7 +2285,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); - if (!slave_dev->netdev_ops->ndo_bpf || !slave_dev->netdev_ops->ndo_xdp_xmit) { if (bond->xdp_prog) { @@ -2474,6 +2482,12 @@ static int __bond_release_one(struct net_device *bond_dev, if (oldcurrent == slave) bond_change_active_slave(bond, NULL); + /* Must be called after bond_change_active_slave () as the slave + * might change from an active slave to a backup slave. Then it is + * necessary to clear the maddrs on the backup slave. + */ + bond_slave_ns_maddrs_del(bond, slave); + if (bond_is_lb(bond)) { /* Must be called only after the slave has been * detached from the list and the curr_active_slave diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index d1208d058eea..8c326e41b8d6 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -15,6 +15,7 @@ #include <linux/sched/signal.h> #include <net/bonding.h> +#include <net/ndisc.h> static int bond_option_active_slave_set(struct bonding *bond, const struct bond_opt_value *newval); @@ -1218,6 +1219,68 @@ static int bond_option_arp_ip_targets_set(struct bonding *bond, } #if IS_ENABLED(CONFIG_IPV6) +static bool slave_can_set_ns_maddr(const struct bonding *bond, struct slave *slave) +{ + return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && + !bond_is_active_slave(slave) && + slave->dev->flags & IFF_MULTICAST; +} + +static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add) +{ + struct in6_addr *targets = bond->params.ns_targets; + char slot_maddr[MAX_ADDR_LEN]; + int i; + + if (!slave_can_set_ns_maddr(bond, slave)) + return; + + for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { + if (ipv6_addr_any(&targets[i])) + break; + + if (!ndisc_mc_map(&targets[i], slot_maddr, slave->dev, 0)) { + if (add) + dev_mc_add(slave->dev, slot_maddr); + else + dev_mc_del(slave->dev, slot_maddr); + } + } +} + +void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave) +{ + if (!bond->params.arp_validate) + return; + slave_set_ns_maddrs(bond, slave, true); +} + +void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave) +{ + if (!bond->params.arp_validate) + return; + slave_set_ns_maddrs(bond, slave, false); +} + +static void slave_set_ns_maddr(struct bonding *bond, struct slave *slave, + struct in6_addr *target, struct in6_addr *slot) +{ + char target_maddr[MAX_ADDR_LEN], slot_maddr[MAX_ADDR_LEN]; + + if (!bond->params.arp_validate || !slave_can_set_ns_maddr(bond, slave)) + return; + + /* remove the previous maddr from slave */ + if (!ipv6_addr_any(slot) && + !ndisc_mc_map(slot, slot_maddr, slave->dev, 0)) + dev_mc_del(slave->dev, slot_maddr); + + /* add new maddr on slave if target is set */ + if (!ipv6_addr_any(target) && + !ndisc_mc_map(target, target_maddr, slave->dev, 0)) + dev_mc_add(slave->dev, target_maddr); +} + static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot, struct in6_addr *target, unsigned long last_rx) @@ -1227,8 +1290,10 @@ static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot, struct slave *slave; if (slot >= 0 && slot < BOND_MAX_NS_TARGETS) { - bond_for_each_slave(bond, slave, iter) + bond_for_each_slave(bond, slave, iter) { slave->target_last_arp_rx[slot] = last_rx; + slave_set_ns_maddr(bond, slave, target, &targets[slot]); + } targets[slot] = *target; } } @@ -1280,15 +1345,30 @@ static int bond_option_ns_ip6_targets_set(struct bonding *bond, { return -EPERM; } + +static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add) {} + +void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave) {} + +void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave) {} #endif static int bond_option_arp_validate_set(struct bonding *bond, const struct bond_opt_value *newval) { + bool changed = !!bond->params.arp_validate != !!newval->value; + struct list_head *iter; + struct slave *slave; + netdev_dbg(bond->dev, "Setting arp_validate to %s (%llu)\n", newval->string, newval->value); bond->params.arp_validate = newval->value; + if (changed) { + bond_for_each_slave(bond, slave, iter) + slave_set_ns_maddrs(bond, slave, !!bond->params.arp_validate); + } + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 8c4e3ecef590..65cee5c6f1dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -854,7 +854,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, return 0; err_rule: - mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, zone_rule->mh); + mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, attr, zone_rule->mh); mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); err_mod_hdr: kfree(attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index d61be26a4df1..3db31cc10719 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -660,7 +660,7 @@ tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx, while (remaining > 0) { skb_frag_t *frag = &record->frags[i]; - get_page(skb_frag_page(frag)); + page_ref_inc(skb_frag_page(frag)); remaining -= skb_frag_size(frag); info->frags[i++] = *frag; } @@ -763,7 +763,7 @@ void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq, stats = sq->stats; mlx5e_tx_dma_unmap(sq->pdev, dma); - put_page(wi->resync_dump_frag_page); + page_ref_dec(wi->resync_dump_frag_page); stats->tls_dump_packets++; stats->tls_dump_bytes += wi->num_bytes; } @@ -816,12 +816,12 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, err_out: for (; i < info.nr_frags; i++) - /* The put_page() here undoes the page ref obtained in tx_sync_info_get(). + /* The page_ref_dec() here undoes the page ref obtained in tx_sync_info_get(). * Page refs obtained for the DUMP WQEs above (by page_ref_add) will be * released only upon their completions (or in mlx5e_free_txqsq_descs, * if channel closes). */ - put_page(skb_frag_page(&info.frags[i])); + page_ref_dec(skb_frag_page(&info.frags[i])); return MLX5E_KTLS_SYNC_FAIL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index a65c407aa60b..6e431f587c23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4067,7 +4067,8 @@ void mlx5e_set_xdp_feature(struct net_device *netdev) struct mlx5e_params *params = &priv->channels.params; xdp_features_t val; - if (params->packet_merge.type != MLX5E_PACKET_MERGE_NONE) { + if (!netdev->netdev_ops->ndo_bpf || + params->packet_merge.type != MLX5E_PACKET_MERGE_NONE) { xdp_clear_features_flag(netdev); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index e2f7cecce6f1..991250f44c2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1946,13 +1946,22 @@ lookup_fte_locked(struct mlx5_flow_group *g, fte_tmp = NULL; goto out; } + + nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); + if (!fte_tmp->node.active) { + up_write_ref_node(&fte_tmp->node, false); + + if (take_write) + up_write_ref_node(&g->node, false); + else + up_read_ref_node(&g->node); + tree_put_node(&fte_tmp->node, false); - fte_tmp = NULL; - goto out; + + return NULL; } - nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); out: if (take_write) up_write_ref_node(&g->node, false); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c index d352a14f9d48..134f6506df99 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -85,17 +85,15 @@ static int intel_eth_plat_probe(struct platform_device *pdev) if (ret) return ret; - plat_dat = stmmac_probe_config_dt(pdev, stmmac_res.mac); + plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac); if (IS_ERR(plat_dat)) { dev_err(&pdev->dev, "dt configuration failed\n"); return PTR_ERR(plat_dat); } dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) { - ret = -ENOMEM; - goto err_remove_config_dt; - } + if (!dwmac) + return -ENOMEM; dwmac->dev = &pdev->dev; dwmac->tx_clk = NULL; @@ -110,12 +108,15 @@ static int intel_eth_plat_probe(struct platform_device *pdev) /* Enable TX clock */ if (dwmac->data->tx_clk_en) { dwmac->tx_clk = devm_clk_get(&pdev->dev, "tx_clk"); - if (IS_ERR(dwmac->tx_clk)) { - ret = PTR_ERR(dwmac->tx_clk); - goto err_remove_config_dt; - } + if (IS_ERR(dwmac->tx_clk)) + return PTR_ERR(dwmac->tx_clk); - clk_prepare_enable(dwmac->tx_clk); + ret = clk_prepare_enable(dwmac->tx_clk); + if (ret) { + dev_err(&pdev->dev, + "Failed to enable tx_clk\n"); + return ret; + } /* Check and configure TX clock rate */ rate = clk_get_rate(dwmac->tx_clk); @@ -126,7 +127,7 @@ static int intel_eth_plat_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Failed to set tx_clk\n"); - goto err_remove_config_dt; + goto err_tx_clk_disable; } } } @@ -140,7 +141,7 @@ static int intel_eth_plat_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Failed to set clk_ptp_ref\n"); - goto err_remove_config_dt; + goto err_tx_clk_disable; } } } @@ -156,16 +157,14 @@ static int intel_eth_plat_probe(struct platform_device *pdev) } ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); - if (ret) { - clk_disable_unprepare(dwmac->tx_clk); - goto err_remove_config_dt; - } + if (ret) + goto err_tx_clk_disable; return 0; -err_remove_config_dt: - stmmac_remove_config_dt(pdev, plat_dat); - +err_tx_clk_disable: + if (dwmac->data->tx_clk_en) + clk_disable_unprepare(dwmac->tx_clk); return ret; } @@ -174,7 +173,8 @@ static void intel_eth_plat_remove(struct platform_device *pdev) struct intel_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev); stmmac_pltfr_remove(pdev); - clk_disable_unprepare(dwmac->tx_clk); + if (dwmac->data->tx_clk_en) + clk_disable_unprepare(dwmac->tx_clk); } static struct platform_driver intel_eth_plat_driver = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index cd796ec04132..634ea6b33ea3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -589,9 +589,9 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev, plat->mac_interface = priv_plat->phy_mode; if (priv_plat->mac_wol) - plat->flags |= STMMAC_FLAG_USE_PHY_WOL; - else plat->flags &= ~STMMAC_FLAG_USE_PHY_WOL; + else + plat->flags |= STMMAC_FLAG_USE_PHY_WOL; plat->riwt_off = 1; plat->maxmtu = ETH_DATA_LEN; plat->host_dma_width = priv_plat->variant->dma_bit_mask; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c index 22d113fb8e09..a5a5cfa989c6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c @@ -220,15 +220,13 @@ static int visconti_eth_dwmac_probe(struct platform_device *pdev) if (ret) return ret; - plat_dat = stmmac_probe_config_dt(pdev, stmmac_res.mac); + plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac); if (IS_ERR(plat_dat)) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) { - ret = -ENOMEM; - goto remove_config; - } + if (!dwmac) + return -ENOMEM; spin_lock_init(&dwmac->lock); dwmac->reg = stmmac_res.addr; @@ -238,7 +236,7 @@ static int visconti_eth_dwmac_probe(struct platform_device *pdev) ret = visconti_eth_clock_probe(pdev, plat_dat); if (ret) - goto remove_config; + return ret; visconti_eth_init_hw(pdev, plat_dat); @@ -252,22 +250,14 @@ static int visconti_eth_dwmac_probe(struct platform_device *pdev) remove: visconti_eth_clock_remove(pdev); -remove_config: - stmmac_remove_config_dt(pdev, plat_dat); return ret; } static void visconti_eth_dwmac_remove(struct platform_device *pdev) { - struct net_device *ndev = platform_get_drvdata(pdev); - struct stmmac_priv *priv = netdev_priv(ndev); - stmmac_pltfr_remove(pdev); - visconti_eth_clock_remove(pdev); - - stmmac_remove_config_dt(pdev, priv->plat); } static const struct of_device_id visconti_eth_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 30d5e635190e..b4fdd40be63c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -810,7 +810,7 @@ static void devm_stmmac_pltfr_remove(void *data) { struct platform_device *pdev = data; - stmmac_pltfr_remove_no_dt(pdev); + stmmac_pltfr_remove(pdev); } /** @@ -837,12 +837,12 @@ int devm_stmmac_pltfr_probe(struct platform_device *pdev, EXPORT_SYMBOL_GPL(devm_stmmac_pltfr_probe); /** - * stmmac_pltfr_remove_no_dt + * stmmac_pltfr_remove * @pdev: pointer to the platform device * Description: This undoes the effects of stmmac_pltfr_probe() by removing the * driver and calling the platform's exit() callback. */ -void stmmac_pltfr_remove_no_dt(struct platform_device *pdev) +void stmmac_pltfr_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct stmmac_priv *priv = netdev_priv(ndev); @@ -851,23 +851,6 @@ void stmmac_pltfr_remove_no_dt(struct platform_device *pdev) stmmac_dvr_remove(&pdev->dev); stmmac_pltfr_exit(pdev, plat); } -EXPORT_SYMBOL_GPL(stmmac_pltfr_remove_no_dt); - -/** - * stmmac_pltfr_remove - * @pdev: platform device pointer - * Description: this function calls the main to free the net resources - * and calls the platforms hook and release the resources (e.g. mem). - */ -void stmmac_pltfr_remove(struct platform_device *pdev) -{ - struct net_device *ndev = platform_get_drvdata(pdev); - struct stmmac_priv *priv = netdev_priv(ndev); - struct plat_stmmacenet_data *plat = priv->plat; - - stmmac_pltfr_remove_no_dt(pdev); - stmmac_remove_config_dt(pdev, plat); -} EXPORT_SYMBOL_GPL(stmmac_pltfr_remove); /** diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h index c5565b2a70ac..bb07a99e1248 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h @@ -32,7 +32,6 @@ int stmmac_pltfr_probe(struct platform_device *pdev, int devm_stmmac_pltfr_probe(struct platform_device *pdev, struct plat_stmmacenet_data *plat, struct stmmac_resources *res); -void stmmac_pltfr_remove_no_dt(struct platform_device *pdev); void stmmac_pltfr_remove(struct platform_device *pdev); extern const struct dev_pm_ops stmmac_pltfr_pm_ops; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index fb120baee553..7efb3e347c04 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -15,6 +15,7 @@ #include <linux/genalloc.h> #include <linux/if_vlan.h> #include <linux/interrupt.h> +#include <linux/io-64-nonatomic-hi-lo.h> #include <linux/kernel.h> #include <linux/mfd/syscon.h> #include <linux/module.h> @@ -1245,6 +1246,8 @@ static int prueth_perout_enable(void *clockops_data, struct prueth_emac *emac = clockops_data; u32 reduction_factor = 0, offset = 0; struct timespec64 ts; + u64 current_cycle; + u64 start_offset; u64 ns_period; if (!on) @@ -1283,8 +1286,14 @@ static int prueth_perout_enable(void *clockops_data, writel(reduction_factor, emac->prueth->shram.va + TIMESYNC_FW_WC_SYNCOUT_REDUCTION_FACTOR_OFFSET); - writel(0, emac->prueth->shram.va + - TIMESYNC_FW_WC_SYNCOUT_START_TIME_CYCLECOUNT_OFFSET); + current_cycle = icssg_read_time(emac->prueth->shram.va + + TIMESYNC_FW_WC_CYCLECOUNT_OFFSET); + + /* Rounding of current_cycle count to next second */ + start_offset = roundup(current_cycle, MSEC_PER_SEC); + + hi_lo_writeq(start_offset, emac->prueth->shram.va + + TIMESYNC_FW_WC_SYNCOUT_START_TIME_CYCLECOUNT_OFFSET); return 0; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index 3fe80a8758d3..0713ad7897b6 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -257,6 +257,18 @@ static inline int prueth_emac_slice(struct prueth_emac *emac) extern const struct ethtool_ops icssg_ethtool_ops; +static inline u64 icssg_read_time(const void __iomem *addr) +{ + u32 low, high; + + do { + high = readl(addr + 4); + low = readl(addr); + } while (high != readl(addr + 4)); + + return low + ((u64)high << 32); +} + /* Classifier helpers */ void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac); void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac); diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c index dd766e175f7d..8f67c39f479e 100644 --- a/drivers/net/ethernet/vertexcom/mse102x.c +++ b/drivers/net/ethernet/vertexcom/mse102x.c @@ -437,13 +437,15 @@ static void mse102x_tx_work(struct work_struct *work) mse = &mses->mse102x; while ((txb = skb_dequeue(&mse->txq))) { + unsigned int len = max_t(unsigned int, txb->len, ETH_ZLEN); + mutex_lock(&mses->lock); ret = mse102x_tx_pkt_spi(mse, txb, work_timeout); mutex_unlock(&mses->lock); if (ret) { mse->ndev->stats.tx_dropped++; } else { - mse->ndev->stats.tx_bytes += txb->len; + mse->ndev->stats.tx_bytes += len; mse->ndev->stats.tx_packets++; } diff --git a/drivers/pmdomain/imx/imx93-blk-ctrl.c b/drivers/pmdomain/imx/imx93-blk-ctrl.c index 40bd90f8b977..ec6198e35eb7 100644 --- a/drivers/pmdomain/imx/imx93-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx93-blk-ctrl.c @@ -313,7 +313,9 @@ static int imx93_blk_ctrl_remove(struct platform_device *pdev) of_genpd_del_provider(pdev->dev.of_node); - for (i = 0; bc->onecell_data.num_domains; i++) { + pm_runtime_disable(&pdev->dev); + + for (i = 0; i < bc->onecell_data.num_domains; i++) { struct imx93_blk_ctrl_domain *domain = &bc->domains[i]; pm_genpd_remove(&domain->genpd); diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index aa2313f3bcab..92aa98bbdc66 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -115,11 +115,6 @@ struct vchiq_arm_state { int first_connect; }; -struct vchiq_2835_state { - int inited; - struct vchiq_arm_state arm_state; -}; - struct vchiq_pagelist_info { struct pagelist *pagelist; size_t pagelist_buffer_size; @@ -580,29 +575,21 @@ vchiq_arm_init_state(struct vchiq_state *state, int vchiq_platform_init_state(struct vchiq_state *state) { - struct vchiq_2835_state *platform_state; + struct vchiq_arm_state *platform_state; - state->platform_state = kzalloc(sizeof(*platform_state), GFP_KERNEL); - if (!state->platform_state) + platform_state = devm_kzalloc(state->dev, sizeof(*platform_state), GFP_KERNEL); + if (!platform_state) return -ENOMEM; - platform_state = (struct vchiq_2835_state *)state->platform_state; - - platform_state->inited = 1; - vchiq_arm_init_state(state, &platform_state->arm_state); + vchiq_arm_init_state(state, platform_state); + state->platform_state = (struct opaque_platform_state *)platform_state; return 0; } static struct vchiq_arm_state *vchiq_platform_get_arm_state(struct vchiq_state *state) { - struct vchiq_2835_state *platform_state; - - platform_state = (struct vchiq_2835_state *)state->platform_state; - - WARN_ON_ONCE(!platform_state->inited); - - return &platform_state->arm_state; + return (struct vchiq_arm_state *)state->platform_state; } void diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index 5a1971fcd87b..59fa9f3d5ec8 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -232,7 +232,7 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr struct page *pg; unsigned int nsg; int sglen; - u64 pa; + u64 pa, offset; u64 paend; struct scatterlist *sg; struct device *dma = mvdev->vdev.dma_dev; @@ -255,8 +255,10 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr sg = mr->sg_head.sgl; for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1); map; map = vhost_iotlb_itree_next(map, mr->start, mr->end - 1)) { - paend = map->addr + maplen(map, mr); - for (pa = map->addr; pa < paend; pa += sglen) { + offset = mr->start > map->start ? mr->start - map->start : 0; + pa = map->addr + offset; + paend = map->addr + offset + maplen(map, mr); + for (; pa < paend; pa += sglen) { pg = pfn_to_page(__phys_to_pfn(pa)); if (!sg) { mlx5_vdpa_warn(mvdev, "sg null. start 0x%llx, end 0x%llx\n", diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index 99428a04068d..c8b74980dbd1 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -555,7 +555,7 @@ static const struct vdpa_config_ops snet_config_ops = { static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) { - char name[50]; + char *name; int ret, i, mask = 0; /* We don't know which BAR will be used to communicate.. * We will map every bar with len > 0. @@ -573,7 +573,10 @@ static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) return -ENODEV; } - snprintf(name, sizeof(name), "psnet[%s]-bars", pci_name(pdev)); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev)); + if (!name) + return -ENOMEM; + ret = pcim_iomap_regions(pdev, mask, name); if (ret) { SNET_ERR(pdev, "Failed to request and map PCI BARs\n"); @@ -590,10 +593,13 @@ static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) static int snet_open_vf_bar(struct pci_dev *pdev, struct snet *snet) { - char name[50]; + char *name; int ret; - snprintf(name, sizeof(name), "snet[%s]-bar", pci_name(pdev)); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "snet[%s]-bars", pci_name(pdev)); + if (!name) + return -ENOMEM; + /* Request and map BAR */ ret = pcim_iomap_regions(pdev, BIT(snet->psnet->cfg.vf_bar), name); if (ret) { diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index 281287fae89f..1d6d89c08e6e 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -591,7 +591,11 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto mdev_err; } - mdev_id = kzalloc(sizeof(struct virtio_device_id), GFP_KERNEL); + /* + * id_table should be a null terminated array, so allocate one additional + * entry here, see vdpa_mgmtdev_get_classes(). + */ + mdev_id = kcalloc(2, sizeof(struct virtio_device_id), GFP_KERNEL); if (!mdev_id) { err = -ENOMEM; goto mdev_id_err; @@ -611,8 +615,8 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto probe_err; } - mdev_id->device = mdev->id.device; - mdev_id->vendor = mdev->id.vendor; + mdev_id[0].device = mdev->id.device; + mdev_id[0].vendor = mdev->id.vendor; mgtdev->id_table = mdev_id; mgtdev->max_supported_vqs = vp_modern_get_num_queues(mdev); mgtdev->supported_features = vp_modern_get_features(mdev); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 853c63b83681..aba0625de48a 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -374,20 +374,23 @@ void v9fs_evict_inode(struct inode *inode) struct v9fs_inode __maybe_unused *v9inode = V9FS_I(inode); __le32 __maybe_unused version; - truncate_inode_pages_final(&inode->i_data); + if (!is_bad_inode(inode)) { + truncate_inode_pages_final(&inode->i_data); #ifdef CONFIG_9P_FSCACHE - version = cpu_to_le32(v9inode->qid.version); - fscache_clear_inode_writeback(v9fs_inode_cookie(v9inode), inode, + version = cpu_to_le32(v9inode->qid.version); + fscache_clear_inode_writeback(v9fs_inode_cookie(v9inode), inode, &version); #endif - - clear_inode(inode); - filemap_fdatawrite(&inode->i_data); + clear_inode(inode); + filemap_fdatawrite(&inode->i_data); #ifdef CONFIG_9P_FSCACHE - fscache_relinquish_cookie(v9fs_inode_cookie(v9inode), false); + if (v9fs_inode_cookie(v9inode)) + fscache_relinquish_cookie(v9fs_inode_cookie(v9inode), false); #endif + } else + clear_inode(inode); } static int v9fs_test_inode(struct inode *inode, void *data) diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 9bfca3dda63d..77d4f82096c9 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -153,6 +153,7 @@ struct nfsd_net { u32 s2s_cp_cl_id; struct idr s2s_cp_stateids; spinlock_t s2s_cp_lock; + atomic_t pending_async_copies; /* * Version information diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ae0057c54ef4..d64f792964e1 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -751,15 +751,6 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &access->ac_supported); } -static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net) -{ - __be32 *verf = (__be32 *)verifier->data; - - BUILD_BUG_ON(2*sizeof(*verf) != sizeof(verifier->data)); - - nfsd_copy_write_verifier(verf, net_generic(net, nfsd_net_id)); -} - static __be32 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -1282,6 +1273,7 @@ static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) return; + atomic_dec(©->cp_nn->pending_async_copies); kfree(copy->cp_src); kfree(copy); } @@ -1623,7 +1615,6 @@ static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync) test_bit(NFSD4_COPY_F_COMMITTED, ©->cp_flags) ? NFS_FILE_SYNC : NFS_UNSTABLE; nfsd4_copy_set_sync(copy, sync); - gen_boot_verifier(©->cp_res.wr_verifier, copy->cp_clp->net); } static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, @@ -1794,10 +1785,16 @@ static __be32 nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct nfsd4_copy *async_copy = NULL; struct nfsd4_copy *copy = &u->copy; + struct nfsd42_write_res *result; __be32 status; - struct nfsd4_copy *async_copy = NULL; + result = ©->cp_res; + nfsd_copy_write_verifier((__be32 *)&result->wr_verifier.data, nn); + + copy->cp_clp = cstate->clp; if (nfsd4_ssc_is_inter(copy)) { if (!inter_copy_offload_enable || nfsd4_copy_is_sync(copy)) { status = nfserr_notsupp; @@ -1812,25 +1809,26 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status; } - copy->cp_clp = cstate->clp; memcpy(©->fh, &cstate->current_fh.fh_handle, sizeof(struct knfsd_fh)); if (nfsd4_copy_is_async(copy)) { - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - - status = nfserrno(-ENOMEM); async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!async_copy) goto out_err; + async_copy->cp_nn = nn; INIT_LIST_HEAD(&async_copy->copies); refcount_set(&async_copy->refcount, 1); + /* Arbitrary cap on number of pending async copy operations */ + if (atomic_inc_return(&nn->pending_async_copies) > + (int)rqstp->rq_pool->sp_nrthreads) + goto out_err; async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) goto out_err; if (!nfs4_init_copy_state(nn, copy)) goto out_err; - memcpy(©->cp_res.cb_stateid, ©->cp_stateid.cs_stid, - sizeof(copy->cp_res.cb_stateid)); + memcpy(&result->cb_stateid, ©->cp_stateid.cs_stid, + sizeof(result->cb_stateid)); dup_copy_fields(copy, async_copy); async_copy->copy_task = kthread_create(nfsd4_do_async_copy, async_copy, "%s", "copy thread"); @@ -1860,7 +1858,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } if (async_copy) cleanup_async_copy(async_copy); - status = nfserrno(-ENOMEM); + status = nfserr_jukebox; goto out; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 975dd74a7a4d..901fc68636cd 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -8142,6 +8142,7 @@ static int nfs4_state_create_net(struct net *net) spin_lock_init(&nn->client_lock); spin_lock_init(&nn->s2s_cp_lock); idr_init(&nn->s2s_cp_stateids); + atomic_set(&nn->pending_async_copies, 0); spin_lock_init(&nn->blocked_locks_lock); INIT_LIST_HEAD(&nn->blocked_locks_lru); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 9d918a79dc16..144e05efd14c 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -574,6 +574,7 @@ struct nfsd4_copy { struct nfsd4_ssc_umount_item *ss_nsui; struct nfs_fh c_fh; nfs4_stateid stateid; + struct nfsd_net *cp_nn; }; static inline void nfsd4_copy_set_sync(struct nfsd4_copy *copy, bool sync) diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 8fe348bceabe..eaf646b45cc9 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -68,7 +68,6 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) goto failed; } memset(bh->b_data, 0, i_blocksize(inode)); - bh->b_bdev = inode->i_sb->s_bdev; bh->b_blocknr = blocknr; set_buffer_mapped(bh); set_buffer_uptodate(bh); @@ -133,7 +132,6 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr, goto found; } set_buffer_mapped(bh); - bh->b_bdev = inode->i_sb->s_bdev; bh->b_blocknr = pblocknr; /* set block address for read */ bh->b_end_io = end_buffer_read_sync; get_bh(bh); diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 8beb2730929d..c5a119f3cb0d 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -83,10 +83,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, goto out; } - if (!buffer_mapped(bh)) { - bh->b_bdev = inode->i_sb->s_bdev; + if (!buffer_mapped(bh)) set_buffer_mapped(bh); - } bh->b_blocknr = pbn; bh->b_end_io = end_buffer_read_sync; get_bh(bh); diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 19c8158605ed..75a2ed5ee6e0 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -89,7 +89,6 @@ static int nilfs_mdt_create_block(struct inode *inode, unsigned long block, if (buffer_uptodate(bh)) goto failed_bh; - bh->b_bdev = sb->s_bdev; err = nilfs_mdt_insert_new_block(inode, block, bh, init_block); if (likely(!err)) { get_bh(bh); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 956c90700e15..144e200c4909 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -39,7 +39,6 @@ __nilfs_get_page_block(struct page *page, unsigned long block, pgoff_t index, first_block = (unsigned long)index << (PAGE_SHIFT - blkbits); bh = nilfs_page_get_nth_block(page, block - first_block); - touch_buffer(bh); wait_on_buffer(bh); return bh; } @@ -64,6 +63,7 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode, put_page(page); return NULL; } + bh->b_bdev = inode->i_sb->s_bdev; return bh; } diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index d65d43c61857..b2b47bb79529 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -566,6 +566,8 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) ocfs2_commit_trans(osb, handle); out_free_group_bh: + if (ret < 0) + ocfs2_remove_from_cache(INODE_CACHE(inode), group_bh); brelse(group_bh); out_unlock: diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index cfc093937a17..9f6bbb4a0844 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -2322,6 +2322,7 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di, struct ocfs2_blockcheck_stats *stats) { int status = -EAGAIN; + u32 blksz_bits; if (memcmp(di->i_signature, OCFS2_SUPER_BLOCK_SIGNATURE, strlen(OCFS2_SUPER_BLOCK_SIGNATURE)) == 0) { @@ -2336,11 +2337,15 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di, goto out; } status = -EINVAL; - if ((1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits)) != blksz) { + /* Acceptable block sizes are 512 bytes, 1K, 2K and 4K. */ + blksz_bits = le32_to_cpu(di->id2.i_super.s_blocksize_bits); + if (blksz_bits < 9 || blksz_bits > 12) { mlog(ML_ERROR, "found superblock with incorrect block " - "size: found %u, should be %u\n", - 1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits), - blksz); + "size bits: found %u, should be 9, 10, 11, or 12\n", + blksz_bits); + } else if ((1 << le32_to_cpu(blksz_bits)) != blksz) { + mlog(ML_ERROR, "found superblock with incorrect block " + "size: found %u, should be %u\n", 1 << blksz_bits, blksz); } else if (le16_to_cpu(di->id2.i_super.s_major_rev_level) != OCFS2_MAJOR_REV_LEVEL || le16_to_cpu(di->id2.i_super.s_minor_rev_level) != diff --git a/include/linux/damon.h b/include/linux/damon.h index a953d7083cd5..343132a146cf 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -298,16 +298,19 @@ struct damos_access_pattern { * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @pattern: Access pattern of target regions. * @action: &damo_action to be applied to the target regions. + * @apply_interval_us: The time between applying the @action. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. * @filters: Additional set of &struct damos_filter for &action. * @stat: Statistics of this scheme. * @list: List head for siblings. * - * For each aggregation interval, DAMON finds regions which fit in the + * For each @apply_interval_us, DAMON finds regions which fit in the * &pattern and applies &action to those. To avoid consuming too much * CPU time or IO resources for the &action, "a is used. * + * If @apply_interval_us is zero, &damon_attrs->aggr_interval is used instead. + * * To do the work only when needed, schemes can be activated for specific * system situations using &wmarks. If all schemes that registered to the * monitoring context are inactive, DAMON stops monitoring either, and just @@ -327,6 +330,14 @@ struct damos_access_pattern { struct damos { struct damos_access_pattern pattern; enum damos_action action; + unsigned long apply_interval_us; +/* private: internal use only */ + /* + * number of sample intervals that should be passed before applying + * @action + */ + unsigned long next_apply_sis; +/* public: */ struct damos_quota quota; struct damos_watermarks wmarks; struct list_head filters; @@ -627,7 +638,9 @@ void damos_add_filter(struct damos *s, struct damos_filter *f); void damos_destroy_filter(struct damos_filter *f); struct damos *damon_new_scheme(struct damos_access_pattern *pattern, - enum damos_action action, struct damos_quota *quota, + enum damos_action action, + unsigned long apply_interval_us, + struct damos_quota *quota, struct damos_watermarks *wmarks); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); diff --git a/include/linux/mman.h b/include/linux/mman.h index db4741007bef..b2e2677ea156 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H +#include <linux/fs.h> #include <linux/mm.h> #include <linux/percpu_counter.h> @@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long pages) #endif #ifndef arch_calc_vm_flag_bits -#define arch_calc_vm_flag_bits(flags) 0 +#define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_validate_prot @@ -151,12 +152,12 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey) * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long -calc_vm_flag_bits(unsigned long flags) +calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | - arch_calc_vm_flag_bits(flags); + arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); @@ -187,16 +188,31 @@ static inline bool arch_memory_deny_write_exec_supported(void) * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. */ -static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { + /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; - if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) return true; - if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) return true; return false; diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 1c1a5d926b17..0eb3a2b1f81f 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -77,7 +77,9 @@ static inline int copy_safe_from_sockptr(void *dst, size_t ksize, { if (optlen < ksize) return -EINVAL; - return copy_from_sockptr(dst, optval, ksize); + if (copy_from_sockptr(dst, optval, ksize)) + return -EFAULT; + return 0; } static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 69292ecc0325..f631d9f09941 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -160,5 +160,7 @@ void bond_option_arp_ip_targets_clear(struct bonding *bond); #if IS_ENABLED(CONFIG_IPV6) void bond_option_ns_ip6_targets_clear(struct bonding *bond); #endif +void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave); +void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave); #endif /* _NET_BOND_OPTIONS_H */ diff --git a/lib/buildid.c b/lib/buildid.c index d3bc3d0528d5..9fc46366597e 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -40,7 +40,7 @@ static int parse_build_id_buf(unsigned char *build_id, name_sz == note_name_sz && memcmp(nhdr + 1, note_name, note_name_sz) == 0 && desc_sz > 0 && desc_sz <= BUILD_ID_SIZE_MAX) { - data = note_start + note_off + ALIGN(note_name_sz, 4); + data = note_start + note_off + sizeof(Elf32_Nhdr) + ALIGN(note_name_sz, 4); memcpy(build_id, data, desc_sz); memset(build_id + desc_sz, 0, BUILD_ID_SIZE_MAX - desc_sz); if (size) diff --git a/mm/damon/core.c b/mm/damon/core.c index ae55f20835b0..43e4fe7ef17e 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -312,7 +312,9 @@ static struct damos_quota *damos_quota_init_priv(struct damos_quota *quota) } struct damos *damon_new_scheme(struct damos_access_pattern *pattern, - enum damos_action action, struct damos_quota *quota, + enum damos_action action, + unsigned long apply_interval_us, + struct damos_quota *quota, struct damos_watermarks *wmarks) { struct damos *scheme; @@ -322,6 +324,13 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern, return NULL; scheme->pattern = *pattern; scheme->action = action; + scheme->apply_interval_us = apply_interval_us; + /* + * next_apply_sis will be set when kdamond starts. While kdamond is + * running, it will also updated when it is added to the DAMON context, + * or damon_attrs are updated. + */ + scheme->next_apply_sis = 0; INIT_LIST_HEAD(&scheme->filters); scheme->stat = (struct damos_stat){}; INIT_LIST_HEAD(&scheme->list); @@ -334,9 +343,21 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern, return scheme; } +static void damos_set_next_apply_sis(struct damos *s, struct damon_ctx *ctx) +{ + unsigned long sample_interval = ctx->attrs.sample_interval ? + ctx->attrs.sample_interval : 1; + unsigned long apply_interval = s->apply_interval_us ? + s->apply_interval_us : ctx->attrs.aggr_interval; + + s->next_apply_sis = ctx->passed_sample_intervals + + apply_interval / sample_interval; +} + void damon_add_scheme(struct damon_ctx *ctx, struct damos *s) { list_add_tail(&s->list, &ctx->schemes); + damos_set_next_apply_sis(s, ctx); } static void damon_del_scheme(struct damos *s) @@ -548,6 +569,7 @@ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) { unsigned long sample_interval = attrs->sample_interval ? attrs->sample_interval : 1; + struct damos *s; if (attrs->min_nr_regions < 3) return -EINVAL; @@ -563,6 +585,10 @@ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) damon_update_monitoring_results(ctx, attrs); ctx->attrs = *attrs; + + damon_for_each_scheme(s, ctx) + damos_set_next_apply_sis(s, ctx); + return 0; } @@ -963,6 +989,9 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; + if (c->passed_sample_intervals < s->next_apply_sis) + continue; + if (!s->wmarks.activated) continue; @@ -1055,18 +1084,37 @@ static void kdamond_apply_schemes(struct damon_ctx *c) struct damon_target *t; struct damon_region *r, *next_r; struct damos *s; + unsigned long sample_interval = c->attrs.sample_interval ? + c->attrs.sample_interval : 1; + bool has_schemes_to_apply = false; damon_for_each_scheme(s, c) { + if (c->passed_sample_intervals < s->next_apply_sis) + continue; + if (!s->wmarks.activated) continue; + has_schemes_to_apply = true; + damos_adjust_quota(c, s); } + if (!has_schemes_to_apply) + return; + damon_for_each_target(t, c) { damon_for_each_region_safe(r, next_r, t) damon_do_apply_schemes(c, t, r); } + + damon_for_each_scheme(s, c) { + if (c->passed_sample_intervals < s->next_apply_sis) + continue; + s->next_apply_sis = c->passed_sample_intervals + + (s->apply_interval_us ? s->apply_interval_us : + c->attrs.aggr_interval) / sample_interval; + } } /* @@ -1167,6 +1215,7 @@ static void damon_split_region_at(struct damon_target *t, new->age = r->age; new->last_nr_accesses = r->last_nr_accesses; + new->nr_accesses = r->nr_accesses; damon_insert_region(new, r, damon_next_region(r), t); } @@ -1348,11 +1397,19 @@ static void kdamond_init_intervals_sis(struct damon_ctx *ctx) { unsigned long sample_interval = ctx->attrs.sample_interval ? ctx->attrs.sample_interval : 1; + unsigned long apply_interval; + struct damos *scheme; ctx->passed_sample_intervals = 0; ctx->next_aggregation_sis = ctx->attrs.aggr_interval / sample_interval; ctx->next_ops_update_sis = ctx->attrs.ops_update_interval / sample_interval; + + damon_for_each_scheme(scheme, ctx) { + apply_interval = scheme->apply_interval_us ? + scheme->apply_interval_us : ctx->attrs.aggr_interval; + scheme->next_apply_sis = apply_interval / sample_interval; + } } /* @@ -1405,26 +1462,35 @@ static int kdamond_fn(void *data) if (ctx->ops.check_accesses) max_nr_accesses = ctx->ops.check_accesses(ctx); - sample_interval = ctx->attrs.sample_interval ? - ctx->attrs.sample_interval : 1; - if (ctx->passed_sample_intervals == next_aggregation_sis) { - ctx->next_aggregation_sis = next_aggregation_sis + - ctx->attrs.aggr_interval / sample_interval; + if (ctx->passed_sample_intervals >= next_aggregation_sis) { kdamond_merge_regions(ctx, max_nr_accesses / 10, sz_limit); if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) break; - if (!list_empty(&ctx->schemes)) - kdamond_apply_schemes(ctx); + } + + /* + * do kdamond_apply_schemes() after kdamond_merge_regions() if + * possible, to reduce overhead + */ + if (!list_empty(&ctx->schemes)) + kdamond_apply_schemes(ctx); + + sample_interval = ctx->attrs.sample_interval ? + ctx->attrs.sample_interval : 1; + if (ctx->passed_sample_intervals >= next_aggregation_sis) { + ctx->next_aggregation_sis = next_aggregation_sis + + ctx->attrs.aggr_interval / sample_interval; + kdamond_reset_aggregated(ctx); kdamond_split_regions(ctx); if (ctx->ops.reset_aggregated) ctx->ops.reset_aggregated(ctx); } - if (ctx->passed_sample_intervals == next_ops_update_sis) { + if (ctx->passed_sample_intervals >= next_ops_update_sis) { ctx->next_ops_update_sis = next_ops_update_sis + ctx->attrs.ops_update_interval / sample_interval; diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 124f0f8c97b7..dc0ea1fc30ca 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -278,7 +278,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, goto fail; pos += parsed; - scheme = damon_new_scheme(&pattern, action, "a, &wmarks); + scheme = damon_new_scheme(&pattern, action, 0, "a, + &wmarks); if (!scheme) goto fail; diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index e84495ab92cf..3de2916a65c3 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -158,6 +158,8 @@ static struct damos *damon_lru_sort_new_scheme( pattern, /* (de)prioritize on LRU-lists */ action, + /* for each aggregation interval */ + 0, /* under the quota. */ "a, /* (De)activate this according to the watermarks. */ diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index eca9d000ecc5..66e190f0374a 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -142,6 +142,8 @@ static struct damos *damon_reclaim_new_scheme(void) &pattern, /* page out those, as soon as found */ DAMOS_PAGEOUT, + /* for each aggregation interval */ + 0, /* under the quota. */ &damon_reclaim_quota, /* (De)activate this according to the watermarks. */ diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 36dcd881a19c..26c948f87489 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -1613,7 +1613,7 @@ static struct damos *damon_sysfs_mk_scheme( .low = sysfs_wmarks->low, }; - scheme = damon_new_scheme(&pattern, sysfs_scheme->action, "a, + scheme = damon_new_scheme(&pattern, sysfs_scheme->action, 0, "a, &wmarks); if (!scheme) return NULL; diff --git a/mm/internal.h b/mm/internal.h index b30907537801..a0b24d005579 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -83,6 +83,51 @@ static inline void *folio_raw_mapping(struct folio *folio) return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } +/* + * This is a file-backed mapping, and is about to be memory mapped - invoke its + * mmap hook and safely handle error conditions. On error, VMA hooks will be + * mutated. + * + * @file: File which backs the mapping. + * @vma: VMA which we are mapping. + * + * Returns: 0 if success, error otherwise. + */ +static inline int mmap_file(struct file *file, struct vm_area_struct *vma) +{ + int err = call_mmap(file, vma); + + if (likely(!err)) + return 0; + + /* + * OK, we tried to call the file hook for mmap(), but an error + * arose. The mapping is in an inconsistent state and we most not invoke + * any further hooks on it. + */ + vma->vm_ops = &vma_dummy_vm_ops; + + return err; +} + +/* + * If the VMA has a close hook then close it, and since closing it might leave + * it in an inconsistent state which makes the use of any hooks suspect, clear + * them down by installing dummy empty hooks. + */ +static inline void vma_close(struct vm_area_struct *vma) +{ + if (vma->vm_ops && vma->vm_ops->close) { + vma->vm_ops->close(vma); + + /* + * The mapping is in an inconsistent state, and no further hooks + * may be invoked upon it. + */ + vma->vm_ops = &vma_dummy_vm_ops; + } +} + void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) diff --git a/mm/mmap.c b/mm/mmap.c index 6530e9cac458..e4dfeaef668a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -137,8 +137,7 @@ void unlink_file_vma(struct vm_area_struct *vma) static void remove_vma(struct vm_area_struct *vma, bool unreachable) { might_sleep(); - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); @@ -1274,7 +1273,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ - vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | + vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(file, flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; if (flags & MAP_LOCKED) @@ -2667,14 +2666,14 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, return do_vmi_munmap(&vmi, mm, start, len, uf, false); } -unsigned long mmap_region(struct file *file, unsigned long addr, +static unsigned long __mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct vm_area_struct *next, *prev, *merge; - pgoff_t pglen = len >> PAGE_SHIFT; + pgoff_t pglen = PHYS_PFN(len); unsigned long charged = 0; unsigned long end = addr + len; unsigned long merge_start = addr, merge_end = end; @@ -2771,29 +2770,30 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; - if (file) { - if (vm_flags & VM_SHARED) { - error = mapping_map_writable(file->f_mapping); - if (error) - goto free_vma; - } + if (vma_iter_prealloc(&vmi, vma)) { + error = -ENOMEM; + goto free_vma; + } + if (file) { vma->vm_file = get_file(file); - error = call_mmap(file, vma); + error = mmap_file(file, vma); if (error) - goto unmap_and_free_vma; + goto unmap_and_free_file_vma; + /* Drivers cannot alter the address of the VMA. */ + WARN_ON_ONCE(addr != vma->vm_start); /* - * Expansion is handled above, merging is handled below. - * Drivers should not alter the address of the VMA. + * Drivers should not permit writability when previously it was + * disallowed. */ - error = -EINVAL; - if (WARN_ON((addr != vma->vm_start))) - goto close_and_free_vma; + VM_WARN_ON_ONCE(vm_flags != vma->vm_flags && + !(vm_flags & VM_MAYWRITE) && + (vma->vm_flags & VM_MAYWRITE)); vma_iter_config(&vmi, addr, end); /* - * If vm_flags changed after call_mmap(), we should try merge + * If vm_flags changed after mmap_file(), we should try merge * vma again as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && prev)) { @@ -2801,6 +2801,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma->vm_end, vma->vm_flags, NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX, NULL); + if (merge) { /* * ->mmap() can change vma->vm_file and fput @@ -2814,7 +2815,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma = merge; /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; - goto unmap_writable; + goto file_expanded; } } @@ -2822,24 +2823,15 @@ unsigned long mmap_region(struct file *file, unsigned long addr, } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) - goto free_vma; + goto free_iter_vma; } else { vma_set_anonymous(vma); } - if (map_deny_write_exec(vma, vma->vm_flags)) { - error = -EACCES; - goto close_and_free_vma; - } - - /* Allow architectures to sanity-check the vm_flags */ - error = -EINVAL; - if (!arch_validate_flags(vma->vm_flags)) - goto close_and_free_vma; - - error = -ENOMEM; - if (vma_iter_prealloc(&vmi, vma)) - goto close_and_free_vma; +#ifdef CONFIG_SPARC64 + /* TODO: Fix SPARC ADI! */ + WARN_ON_ONCE(!arch_validate_flags(vm_flags)); +#endif /* Lock the VMA since it is modified after insertion into VMA tree */ vma_start_write(vma); @@ -2862,10 +2854,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, */ khugepaged_enter_vma(vma, vma->vm_flags); - /* Once vma denies write, undo our temporary denial count */ -unmap_writable: - if (file && vm_flags & VM_SHARED) - mapping_unmap_writable(file->f_mapping); +file_expanded: file = vma->vm_file; ksm_add_vma(vma); expanded: @@ -2895,34 +2884,60 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma_set_page_prot(vma); - validate_mm(mm); return addr; -close_and_free_vma: - if (file && vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); - - if (file || vma->vm_file) { -unmap_and_free_vma: - fput(vma->vm_file); - vma->vm_file = NULL; +unmap_and_free_file_vma: + fput(vma->vm_file); + vma->vm_file = NULL; - vma_iter_set(&vmi, vma->vm_end); - /* Undo any partial mapping done by a device driver. */ - unmap_region(mm, &vmi.mas, vma, prev, next, vma->vm_start, - vma->vm_end, vma->vm_end, true); - } - if (file && (vm_flags & VM_SHARED)) - mapping_unmap_writable(file->f_mapping); + vma_iter_set(&vmi, vma->vm_end); + /* Undo any partial mapping done by a device driver. */ + unmap_region(mm, &vmi.mas, vma, prev, next, vma->vm_start, + vma->vm_end, vma->vm_end, true); +free_iter_vma: + vma_iter_free(&vmi); free_vma: vm_area_free(vma); unacct_error: if (charged) vm_unacct_memory(charged); - validate_mm(mm); return error; } +unsigned long mmap_region(struct file *file, unsigned long addr, + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf) +{ + unsigned long ret; + bool writable_file_mapping = false; + + /* Check to see if MDWE is applicable. */ + if (map_deny_write_exec(vm_flags, vm_flags)) + return -EACCES; + + /* Allow architectures to sanity-check the vm_flags. */ + if (!arch_validate_flags(vm_flags)) + return -EINVAL; + + /* Map writable and ensure this isn't a sealed memfd. */ + if (file && (vm_flags & VM_SHARED)) { + int error = mapping_map_writable(file->f_mapping); + + if (error) + return error; + writable_file_mapping = true; + } + + ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf); + + /* Clear our write mapping regardless of error. */ + if (writable_file_mapping) + mapping_unmap_writable(file->f_mapping); + + validate_mm(current->mm); + return ret; +} + static int __vm_munmap(unsigned long start, size_t len, bool unlock) { int ret; @@ -3392,8 +3407,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_vma_link: - if (new_vma->vm_ops && new_vma->vm_ops->close) - new_vma->vm_ops->close(new_vma); + vma_close(new_vma); if (new_vma->vm_file) fput(new_vma->vm_file); diff --git a/mm/mprotect.c b/mm/mprotect.c index b94fbb45d5c7..7e870a8c9402 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -791,7 +791,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, break; } - if (map_deny_write_exec(vma, newflags)) { + if (map_deny_write_exec(vma->vm_flags, newflags)) { error = -EACCES; break; } diff --git a/mm/nommu.c b/mm/nommu.c index 7f9e9e5a0e12..f848d98e8997 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -584,7 +584,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma) VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_start); vma_iter_config(&vmi, vma->vm_start, vma->vm_end); - if (vma_iter_prealloc(&vmi, vma)) { + if (vma_iter_prealloc(&vmi, NULL)) { pr_warn("Allocation of vma tree for process %d failed\n", current->pid); return -ENOMEM; @@ -600,8 +600,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma) */ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) { - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (vma->vm_file) fput(vma->vm_file); put_nommu_region(vma->vm_region); @@ -854,7 +853,7 @@ static unsigned long determine_vm_flags(struct file *file, { unsigned long vm_flags; - vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(flags); + vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(file, flags); if (!file) { /* @@ -896,7 +895,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) { int ret; - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); if (ret == 0) { vma->vm_region->vm_top = vma->vm_region->vm_end; return 0; @@ -929,7 +928,7 @@ static int do_mmap_private(struct vm_area_struct *vma, * happy. */ if (capabilities & NOMMU_MAP_DIRECT) { - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); /* shouldn't return success if we're not sharing */ if (WARN_ON_ONCE(!is_nommu_shared_mapping(vma->vm_flags))) ret = -ENOSYS; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7272a922b838..3bda3f4570a2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4301,7 +4301,8 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, gfp = alloc_gfp; /* Find an allowed local zone that meets the low watermark. */ - for_each_zone_zonelist_nodemask(zone, z, ac.zonelist, ac.highest_zoneidx, ac.nodemask) { + z = ac.preferred_zoneref; + for_next_zone_zonelist_nodemask(zone, z, ac.highest_zoneidx, ac.nodemask) { unsigned long mark; if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) && diff --git a/mm/shmem.c b/mm/shmem.c index 5d076022da24..db7dd45c9181 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1158,9 +1158,7 @@ static int shmem_getattr(struct mnt_idmap *idmap, stat->attributes_mask |= (STATX_ATTR_APPEND | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); - inode_lock_shared(inode); generic_fillattr(idmap, request_mask, inode, stat); - inode_unlock_shared(inode); if (shmem_is_huge(inode, 0, false, NULL, 0)) stat->blksize = HPAGE_PMD_SIZE; @@ -2402,9 +2400,6 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) if (ret) return ret; - /* arm64 - allow memory tagging on RAM-based files */ - vm_flags_set(vma, VM_MTE_ALLOWED); - file_accessed(file); /* This is anonymous shared memory if it is unlinked at the time of mmap */ if (inode->i_nlink) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index d4e607bf35ba..3cf4dd9cad8a 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3752,8 +3752,6 @@ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, handle); - if (conn && hci_dev_test_flag(hdev, HCI_MGMT)) - mgmt_device_connected(hdev, conn, NULL, 0); hci_dev_unlock(hdev); if (conn) { diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d8c47ca86de4..2cf4393e48dc 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -521,15 +521,13 @@ __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id) } static struct mptcp_pm_addr_entry * -__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info, - bool lookup_by_id) +__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) { struct mptcp_pm_addr_entry *entry; - list_for_each_entry(entry, &pernet->local_addr_list, list) { - if ((!lookup_by_id && - mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) || - (lookup_by_id && entry->addr.id == info->id)) + list_for_each_entry_rcu(entry, &pernet->local_addr_list, list, + lockdep_is_held(&pernet->lock)) { + if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) return entry; } return NULL; @@ -560,7 +558,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) mptcp_local_address((struct sock_common *)msk->first, &mpc_addr); rcu_read_lock(); - entry = __lookup_addr(pernet, &mpc_addr, false); + entry = __lookup_addr(pernet, &mpc_addr); if (entry) { __clear_bit(entry->addr.id, msk->pm.id_avail_bitmap); msk->mpc_endpoint_id = entry->addr.id; @@ -2064,7 +2062,8 @@ int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 } spin_lock_bh(&pernet->lock); - entry = __lookup_addr(pernet, &addr->addr, lookup_by_id); + entry = lookup_by_id ? __lookup_addr_by_id(pernet, addr->addr.id) : + __lookup_addr(pernet, &addr->addr); if (!entry) { spin_unlock_bh(&pernet->lock); return -EINVAL; diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index e097b6a7b816..8faf776cb977 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -107,19 +107,26 @@ static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk, return -EINVAL; } +static struct mptcp_pm_addr_entry * +mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id) +{ + struct mptcp_pm_addr_entry *entry; + + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (entry->addr.id == id) + return entry; + } + return NULL; +} + int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex) { - struct mptcp_pm_addr_entry *entry, *match = NULL; + struct mptcp_pm_addr_entry *match; spin_lock_bh(&msk->pm.lock); - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { - if (id == entry->addr.id) { - match = entry; - break; - } - } + match = mptcp_userspace_pm_lookup_addr_by_id(msk, id); spin_unlock_bh(&msk->pm.lock); if (match) { *flags = match->flags; @@ -183,6 +190,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) struct mptcp_pm_addr_entry addr_val; struct mptcp_sock *msk; int err = -EINVAL; + struct sock *sk; u32 token_val; if (!addr || !token) { @@ -198,6 +206,8 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) return err; } + sk = (struct sock *)msk; + if (!mptcp_pm_is_userspace(msk)) { GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); goto announce_err; @@ -221,7 +231,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) goto announce_err; } - lock_sock((struct sock *)msk); + lock_sock(sk); spin_lock_bh(&msk->pm.lock); if (mptcp_pm_alloc_anno_list(msk, &addr_val.addr)) { @@ -231,11 +241,11 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) } spin_unlock_bh(&msk->pm.lock); - release_sock((struct sock *)msk); + release_sock(sk); err = 0; announce_err: - sock_put((struct sock *)msk); + sock_put(sk); return err; } @@ -277,11 +287,12 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *id = info->attrs[MPTCP_PM_ATTR_LOC_ID]; - struct mptcp_pm_addr_entry *match = NULL; + struct mptcp_pm_addr_entry *match; struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; LIST_HEAD(free_list); int err = -EINVAL; + struct sock *sk; u32 token_val; u8 id_val; @@ -299,6 +310,8 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) return err; } + sk = (struct sock *)msk; + if (!mptcp_pm_is_userspace(msk)) { GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); goto remove_err; @@ -309,34 +322,31 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) goto remove_err; } - lock_sock((struct sock *)msk); - - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { - if (entry->addr.id == id_val) { - match = entry; - break; - } - } + lock_sock(sk); + spin_lock_bh(&msk->pm.lock); + match = mptcp_userspace_pm_lookup_addr_by_id(msk, id_val); if (!match) { GENL_SET_ERR_MSG(info, "address with specified id not found"); - release_sock((struct sock *)msk); + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); goto remove_err; } list_move(&match->list, &free_list); + spin_unlock_bh(&msk->pm.lock); mptcp_pm_remove_addrs(msk, &free_list); - release_sock((struct sock *)msk); + release_sock(sk); list_for_each_entry_safe(match, entry, &free_list, list) { - sock_kfree_s((struct sock *)msk, match, sizeof(*match)); + sock_kfree_s(sk, match, sizeof(*match)); } err = 0; remove_err: - sock_put((struct sock *)msk); + sock_put(sk); return err; } @@ -556,8 +566,10 @@ int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, struct mptcp_pm_addr_entry *loc, struct mptcp_pm_addr_entry *rem, u8 bkup) { + struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; int ret = -EINVAL; + struct sock *sk; u32 token_val; token_val = nla_get_u32(token); @@ -566,6 +578,8 @@ int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, if (!msk) return ret; + sk = (struct sock *)msk; + if (!mptcp_pm_is_userspace(msk)) goto set_flags_err; @@ -573,11 +587,22 @@ int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, rem->addr.family == AF_UNSPEC) goto set_flags_err; - lock_sock((struct sock *)msk); + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, &loc->addr, false)) { + if (bkup) + entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; + else + entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; + } + } + spin_unlock_bh(&msk->pm.lock); + + lock_sock(sk); ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc->addr, &rem->addr, bkup); - release_sock((struct sock *)msk); + release_sock(sk); set_flags_err: - sock_put((struct sock *)msk); + sock_put(sk); return ret; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index cd6f8d655c18..b8357d7c6b3a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2045,7 +2045,8 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) slow = lock_sock_fast(ssk); WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf); WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp); - tcp_cleanup_rbuf(ssk, 1); + if (tcp_can_send_ack(ssk)) + tcp_cleanup_rbuf(ssk, 1); unlock_sock_fast(ssk, slow); } } @@ -2168,7 +2169,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, cmsg_flags = MPTCP_CMSG_INQ; while (copied < len) { - int bytes_read; + int err, bytes_read; bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { @@ -2230,9 +2231,16 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } pr_debug("block timeout %ld\n", timeo); - sk_wait_data(sk, &timeo, NULL); + mptcp_rcv_space_adjust(msk, copied); + err = sk_wait_data(sk, &timeo, NULL); + if (err < 0) { + err = copied ? : err; + goto out_err; + } } + mptcp_rcv_space_adjust(msk, copied); + out_err: if (cmsg_flags && copied >= 0) { if (cmsg_flags & MPTCP_CMSG_TS) @@ -2248,8 +2256,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n", msk, skb_queue_empty_lockless(&sk->sk_receive_queue), skb_queue_empty(&msk->receive_queue), copied); - if (!(flags & MSG_PEEK)) - mptcp_rcv_space_adjust(msk, copied); release_sock(sk); return copied; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 50e13207a05a..4aa2cbe9d6fa 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -393,15 +393,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) static void netlink_sock_destruct(struct sock *sk) { - struct netlink_sock *nlk = nlk_sk(sk); - - if (nlk->cb_running) { - if (nlk->cb.done) - nlk->cb.done(&nlk->cb); - module_put(nlk->cb.module); - kfree_skb(nlk->cb.skb); - } - skb_queue_purge(&sk->sk_receive_queue); if (!sock_flag(sk, SOCK_DEAD)) { @@ -414,14 +405,6 @@ static void netlink_sock_destruct(struct sock *sk) WARN_ON(nlk_sk(sk)->groups); } -static void netlink_sock_destruct_work(struct work_struct *work) -{ - struct netlink_sock *nlk = container_of(work, struct netlink_sock, - work); - - sk_free(&nlk->sk); -} - /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on * SMP. Look, when several writers sleep and reader wakes them up, all but one * immediately hit write lock and grab all the cpus. Exclusive sleep solves @@ -735,12 +718,6 @@ static void deferred_put_nlk_sk(struct rcu_head *head) if (!refcount_dec_and_test(&sk->sk_refcnt)) return; - if (nlk->cb_running && nlk->cb.done) { - INIT_WORK(&nlk->work, netlink_sock_destruct_work); - schedule_work(&nlk->work); - return; - } - sk_free(sk); } @@ -792,6 +769,14 @@ static int netlink_release(struct socket *sock) NETLINK_URELEASE, &n); } + /* Terminate any outstanding dump */ + if (nlk->cb_running) { + if (nlk->cb.done) + nlk->cb.done(&nlk->cb); + module_put(nlk->cb.module); + kfree_skb(nlk->cb.skb); + } + module_put(nlk->module); if (netlink_is_kernel(sk)) { diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 9751e29d4bbb..b1a17c0d97a1 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -4,7 +4,6 @@ #include <linux/rhashtable.h> #include <linux/atomic.h> -#include <linux/workqueue.h> #include <net/sock.h> /* flags */ @@ -51,7 +50,6 @@ struct netlink_sock { struct rhash_head node; struct rcu_head rcu; - struct work_struct work; }; static inline struct netlink_sock *nlk_sk(struct sock *sk) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 6663e971a13e..67f27be13848 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -71,7 +71,7 @@ struct tc_u_hnode { struct tc_u_hnode __rcu *next; u32 handle; u32 prio; - int refcnt; + refcount_t refcnt; unsigned int divisor; struct idr handle_idr; bool is_root; @@ -86,12 +86,22 @@ struct tc_u_hnode { struct tc_u_common { struct tc_u_hnode __rcu *hlist; void *ptr; - int refcnt; + refcount_t refcnt; struct idr handle_idr; struct hlist_node hnode; long knodes; }; +static u32 handle2id(u32 h) +{ + return ((h & 0x80000000) ? ((h >> 20) & 0x7FF) : h); +} + +static u32 id2handle(u32 id) +{ + return (id | 0x800U) << 20; +} + static inline unsigned int u32_hash_fold(__be32 key, const struct tc_u32_sel *sel, u8 fshift) @@ -310,7 +320,7 @@ static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr) int id = idr_alloc_cyclic(&tp_c->handle_idr, ptr, 1, 0x7FF, GFP_KERNEL); if (id < 0) return 0; - return (id | 0x800U) << 20; + return id2handle(id); } static struct hlist_head *tc_u_common_hash; @@ -359,8 +369,8 @@ static int u32_init(struct tcf_proto *tp) if (root_ht == NULL) return -ENOBUFS; - root_ht->refcnt++; - root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000; + refcount_set(&root_ht->refcnt, 1); + root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : id2handle(0); root_ht->prio = tp->prio; root_ht->is_root = true; idr_init(&root_ht->handle_idr); @@ -371,18 +381,20 @@ static int u32_init(struct tcf_proto *tp) kfree(root_ht); return -ENOBUFS; } + refcount_set(&tp_c->refcnt, 1); tp_c->ptr = key; INIT_HLIST_NODE(&tp_c->hnode); idr_init(&tp_c->handle_idr); hlist_add_head(&tp_c->hnode, tc_u_hash(key)); + } else { + refcount_inc(&tp_c->refcnt); } - tp_c->refcnt++; RCU_INIT_POINTER(root_ht->next, tp_c->hlist); rcu_assign_pointer(tp_c->hlist, root_ht); - root_ht->refcnt++; + /* root_ht must be destroyed when tcf_proto is destroyed */ rcu_assign_pointer(tp->root, root_ht); tp->data = tp_c; return 0; @@ -393,7 +405,7 @@ static void __u32_destroy_key(struct tc_u_knode *n) struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); tcf_exts_destroy(&n->exts); - if (ht && --ht->refcnt == 0) + if (ht && refcount_dec_and_test(&ht->refcnt)) kfree(ht); kfree(n); } @@ -601,8 +613,6 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, struct tc_u_hnode __rcu **hn; struct tc_u_hnode *phn; - WARN_ON(--ht->refcnt); - u32_clear_hnode(tp, ht, extack); hn = &tp_c->hlist; @@ -612,7 +622,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, if (phn == ht) { u32_clear_hw_hnode(tp, ht, extack); idr_destroy(&ht->handle_idr); - idr_remove(&tp_c->handle_idr, ht->handle); + idr_remove(&tp_c->handle_idr, handle2id(ht->handle)); RCU_INIT_POINTER(*hn, ht->next); kfree_rcu(ht, rcu); return 0; @@ -630,10 +640,10 @@ static void u32_destroy(struct tcf_proto *tp, bool rtnl_held, WARN_ON(root_ht == NULL); - if (root_ht && --root_ht->refcnt == 1) + if (root_ht && refcount_dec_and_test(&root_ht->refcnt)) u32_destroy_hnode(tp, root_ht, extack); - if (--tp_c->refcnt == 0) { + if (refcount_dec_and_test(&tp_c->refcnt)) { struct tc_u_hnode *ht; hlist_del(&tp_c->hnode); @@ -645,7 +655,7 @@ static void u32_destroy(struct tcf_proto *tp, bool rtnl_held, /* u32_destroy_key() will later free ht for us, if it's * still referenced by some knode */ - if (--ht->refcnt == 0) + if (refcount_dec_and_test(&ht->refcnt)) kfree_rcu(ht, rcu); } @@ -674,7 +684,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, return -EINVAL; } - if (ht->refcnt == 1) { + if (refcount_dec_if_one(&ht->refcnt)) { u32_destroy_hnode(tp, ht, extack); } else { NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter"); @@ -682,7 +692,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, } out: - *last = tp_c->refcnt == 1 && tp_c->knodes == 0; + *last = refcount_read(&tp_c->refcnt) == 1 && tp_c->knodes == 0; return ret; } @@ -766,14 +776,14 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, NL_SET_ERR_MSG_MOD(extack, "Not linking to root node"); return -EINVAL; } - ht_down->refcnt++; + refcount_inc(&ht_down->refcnt); } ht_old = rtnl_dereference(n->ht_down); rcu_assign_pointer(n->ht_down, ht_down); if (ht_old) - ht_old->refcnt--; + refcount_dec(&ht_old->refcnt); } if (ifindex >= 0) @@ -852,7 +862,7 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, /* bump reference count as long as we hold pointer to structure */ if (ht) - ht->refcnt++; + refcount_inc(&ht->refcnt); return new; } @@ -932,7 +942,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, ht_old = rtnl_dereference(n->ht_down); if (ht_old) - ht_old->refcnt++; + refcount_inc(&ht_old->refcnt); } __u32_destroy_key(new); return err; @@ -980,7 +990,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return err; } } - ht->refcnt = 1; + refcount_set(&ht->refcnt, 1); ht->divisor = divisor; ht->handle = handle; ht->prio = tp->prio; @@ -989,7 +999,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, err = u32_replace_hw_hnode(tp, ht, userflags, extack); if (err) { - idr_remove(&tp_c->handle_idr, handle); + idr_remove(&tp_c->handle_idr, handle2id(handle)); kfree(ht); return err; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 43f2731bf590..08acda9ecdf5 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -684,7 +684,7 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) struct sock *sk = &sp->inet.sk; struct net *net = sock_net(sk); struct net_device *dev = NULL; - int type; + int type, res, bound_dev_if; type = ipv6_addr_type(in6); if (IPV6_ADDR_ANY == type) @@ -698,14 +698,21 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) if (!(type & IPV6_ADDR_UNICAST)) return 0; - if (sk->sk_bound_dev_if) { - dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + rcu_read_lock(); + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + if (bound_dev_if) { + res = 0; + dev = dev_get_by_index_rcu(net, bound_dev_if); if (!dev) - return 0; + goto out; } - return ipv6_can_nonlocal_bind(net, &sp->inet) || - ipv6_chk_addr(net, in6, dev, 0); + res = ipv6_can_nonlocal_bind(net, &sp->inet) || + ipv6_chk_addr(net, in6, dev, 0); + +out: + rcu_read_unlock(); + return res; } /* This function checks if the address is a valid address to be used for diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 2a44505f4a22..43495820b64f 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1314,6 +1314,14 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb, return -ENOMEM; } + /* __vsock_release() might have already flushed accept_queue. + * Subsequent enqueues would lead to a memory leak. + */ + if (sk->sk_shutdown == SHUTDOWN_MASK) { + virtio_transport_reset_no_sock(t, skb); + return -ESHUTDOWN; + } + child = vsock_create_connected(sk); if (!child) { virtio_transport_reset_no_sock(t, skb); diff --git a/samples/pktgen/pktgen_sample01_simple.sh b/samples/pktgen/pktgen_sample01_simple.sh index cdb9f497f87d..66cb707479e6 100755 --- a/samples/pktgen/pktgen_sample01_simple.sh +++ b/samples/pktgen/pktgen_sample01_simple.sh @@ -76,7 +76,7 @@ if [ -n "$DST_PORT" ]; then pg_set $DEV "udp_dst_max $UDP_DST_MAX" fi -[ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM" +[ ! -z "$UDP_CSUM" ] && pg_set $DEV "flag UDPCSUM" # Setup random UDP port src range pg_set $DEV "flag UDPSRC_RND" diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index 3b2cb8f1002e..e474f6a2cc85 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -318,15 +318,21 @@ static int ima_eventdigest_init_common(const u8 *digest, u32 digestsize, hash_algo_name[hash_algo]); } - if (digest) + if (digest) { memcpy(buffer + offset, digest, digestsize); - else + } else { /* * If digest is NULL, the event being recorded is a violation. * Make room for the digest by increasing the offset by the - * hash algorithm digest size. + * hash algorithm digest size. If the hash algorithm is not + * specified increase the offset by IMA_DIGEST_SIZE which + * fits SHA1 or MD5 */ - offset += hash_digest_size[hash_algo]; + if (hash_algo < HASH_ALGO__LAST) + offset += hash_digest_size[hash_algo]; + else + offset += IMA_DIGEST_SIZE; + } return ima_write_template_field_data(buffer, offset + digestsize, fmt, field_data); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3c48036fdf0b..ffe298eb7b36 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9996,6 +9996,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b59, "HP Elite mt645 G7 Mobile Thin Client U89", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b5f, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b65, "HP ProBook 455 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b66, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), @@ -11064,6 +11065,8 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = { {0x1a, 0x40000000}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC2XX_FIXUP_HEADSET_MIC, {0x19, 0x40000000}), + SND_HDA_PIN_QUIRK(0x10ec0255, 0x1558, "Clevo", ALC2XX_FIXUP_HEADSET_MIC, + {0x19, 0x40000000}), {} }; diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c index 2a4ca4dd2da8..69f00eab1b8c 100644 --- a/tools/mm/page-types.c +++ b/tools/mm/page-types.c @@ -421,7 +421,7 @@ static void show_page(unsigned long voffset, unsigned long offset, if (opt_file) printf("%lx\t", voffset); if (opt_list_cgroup) - printf("@%" PRIu64 "\t", cgroup) + printf("@%" PRIu64 "\t", cgroup); if (opt_list_mapcnt) printf("%" PRIu64 "\t", mapcnt);