Re: Linux 6.18.44
Greg Kroah-Hartman <[email protected]>
| Newsgroups | org.kernel.vger.stable,org.kernel.vger.linux-kernel |
|---|---|
| Message-ID | <2026080951-etching-strut-6914@gregkh> |
diff --git a/Documentation/hwmon/ina2xx.rst b/Documentation/hwmon/ina2xx.rst index a3860aae444c..d64e7af46a12 100644 --- a/Documentation/hwmon/ina2xx.rst +++ b/Documentation/hwmon/ina2xx.rst @@ -74,6 +74,16 @@ Supported chips: https://us1.silergy.com/ + * Texas Instruments INA234 + + Prefix: 'ina234' + + Addresses: I2C 0x40 - 0x43 + + Datasheet: Publicly available at the Texas Instruments website + + https://www.ti.com/ + Author: Lothar Felten <[email protected]> Description @@ -89,7 +99,7 @@ interface. The INA220 monitors both shunt drop and supply voltage. The INA226 is a current shunt and power monitor with an I2C interface. The INA226 monitors both a shunt voltage drop and bus supply voltage. -INA230 and INA231 are high or low side current shunt and power monitors +INA230, INA231, and INA234 are high or low side current shunt and power monitors with an I2C interface. The chips monitor both a shunt voltage drop and bus supply voltage. @@ -124,8 +134,17 @@ power1_input Power(uW) measurement channel shunt_resistor Shunt resistance(uOhm) channel (not for ina260) ======================= =============================================== -Additional sysfs entries for ina226, ina230, ina231, ina260, and sy24655 ------------------------------------------------------------------------- +Additional sysfs entries +------------------------ + +Additional entries are available for the following chips: + + * ina226 + * ina230 + * ina231 + * ina234 + * ina260 + * sy24655 ======================= ==================================================== curr1_lcrit Critical low current diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9f835f68b4fb..10d8a366b207 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8259,6 +8259,12 @@ When this capability is enabled all memory in memslots must be mapped as attempts to create a memslot with an invalid mmap will result in an -EINVAL return. +``guest_memfd``, even though it is an anonymous file, is not supported with MTE. +Attempting to create a memslot backed by ``guest_memfd`` when the MTE capability +is enabled, or attempting to enable the MTE capability after +``guest_memfd``-backed memslots have been created, will result in an -EINVAL +return. + When enabled the VMM may make use of the ``KVM_ARM_MTE_COPY_TAGS`` ioctl to perform a bulk copy of tags to/from the guest. diff --git a/Makefile b/Makefile index 5976ab6f0128..93ae28a0b88b 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 18 -SUBLEVEL = 43 +SUBLEVEL = 44 EXTRAVERSION = NAME = Baby Opossum Posse diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 10fc6783cd60..5d2435dd76f3 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -96,14 +96,27 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, set_bit(KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER, &kvm->arch.flags); break; - case KVM_CAP_ARM_MTE: - mutex_lock(&kvm->lock); - if (system_supports_mte() && !kvm->created_vcpus) { - r = 0; - set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags); + case KVM_CAP_ARM_MTE: { + struct kvm_memory_slot *memslot; + int bkt; + + guard(mutex)(&kvm->lock); + if (!system_supports_mte() || kvm->created_vcpus) + break; + + r = 0; + guard(mutex)(&kvm->slots_lock); + kvm_for_each_memslot(memslot, bkt, kvm_memslots(kvm)) { + if (kvm_slot_has_gmem(memslot)) { + r = -EINVAL; + break; + } } - mutex_unlock(&kvm->lock); + if (r == 0) + set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags); break; + + } case KVM_CAP_ARM_SYSTEM_SUSPEND: r = 0; set_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 403a63548351..b4237699705b 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -2323,6 +2323,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (kvm_slot_has_gmem(new) && !kvm_memslot_is_gmem_only(new)) return -EINVAL; + /* guest_memfd is incompatible with MTE. */ + if (kvm_slot_has_gmem(new) && kvm_has_mte(kvm)) + return -EINVAL; + hva = new->userspace_addr; reg_end = hva + (new->npages << PAGE_SHIFT); diff --git a/arch/powerpc/boot/simpleboot.c b/arch/powerpc/boot/simpleboot.c index c80691d83880..27591df41e9e 100644 --- a/arch/powerpc/boot/simpleboot.c +++ b/arch/powerpc/boot/simpleboot.c @@ -68,7 +68,7 @@ void platform_init(unsigned long r3, unsigned long r4, unsigned long r5, /* finally, setup the timebase */ node = fdt_node_offset_by_prop_value(_dtb_start, -1, "device_type", "cpu", sizeof("cpu")); - if (!node) + if (node < 0) fatal("Cannot find cpu node\n"); timebase = fdt_getprop(_dtb_start, node, "timebase-frequency", &size); if (timebase && (size == 4)) diff --git a/arch/powerpc/boot/treeboot-akebono.c b/arch/powerpc/boot/treeboot-akebono.c index e3cc2599869c..1b529037480f 100644 --- a/arch/powerpc/boot/treeboot-akebono.c +++ b/arch/powerpc/boot/treeboot-akebono.c @@ -146,7 +146,7 @@ void platform_init(char *userdata) node = fdt_node_offset_by_prop_value(_dtb_start, -1, "device_type", "cpu", sizeof("cpu")); - if (!node) + if (node < 0) fatal("Cannot find cpu node\n"); timebase = fdt_getprop(_dtb_start, node, "timebase-frequency", &size); if (timebase && (size == 4)) diff --git a/arch/powerpc/boot/treeboot-currituck.c b/arch/powerpc/boot/treeboot-currituck.c index d53e8a592f81..5b5363b74f9f 100644 --- a/arch/powerpc/boot/treeboot-currituck.c +++ b/arch/powerpc/boot/treeboot-currituck.c @@ -102,7 +102,7 @@ void platform_init(void) node = fdt_node_offset_by_prop_value(_dtb_start, -1, "device_type", "cpu", sizeof("cpu")); - if (!node) + if (node < 0) fatal("Cannot find cpu node\n"); timebase = fdt_getprop(_dtb_start, node, "timebase-frequency", &size); if (timebase && (size == 4)) diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c index 1326de55fda6..e04952bb4360 100644 --- a/arch/powerpc/platforms/ps3/mm.c +++ b/arch/powerpc/platforms/ps3/mm.c @@ -615,6 +615,7 @@ static int dma_ioc0_map_pages(struct ps3_dma_region *r, unsigned long phys_addr, fail_map: for (iopage--; 0 <= iopage; iopage--) { + offset = (1 << r->page_size) * iopage; lv1_put_iopte(0, c->bus_addr + offset, c->lpar_addr + offset, diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index 70b5e6927620..78fc74a41678 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -376,7 +376,7 @@ static void check_vector_unaligned_access(struct work_struct *work __always_unus } /* Measure unaligned access speed on all CPUs present at boot in parallel. */ -static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) +static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) { schedule_on_each_cpu(check_vector_unaligned_access); riscv_hwprobe_complete_async_probe(); @@ -384,7 +384,7 @@ static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __alway return 0; } #else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */ -static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) +static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) { return 0; } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ee40ca01ac66..557bf160b503 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1738,7 +1738,7 @@ static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, un for (; addr < end; addr = next) { next = pud_addr_end(addr, end); - pudp = pud_base + pud_index(addr); + pudp = pgtable_l4_enabled ? pud_base + pud_index(addr) : pud_base; pud = pudp_get(pudp); if (!pud_present(pud)) continue; @@ -1769,7 +1769,7 @@ static void __meminit remove_p4d_mapping(p4d_t *p4d_base, unsigned long addr, un for (; addr < end; addr = next) { next = p4d_addr_end(addr, end); - p4dp = p4d_base + p4d_index(addr); + p4dp = pgtable_l5_enabled ? p4d_base + p4d_index(addr) : p4d_base; p4d = p4dp_get(p4dp); if (!p4d_present(p4d)) continue; diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 20f738fa6556..4cc554c9d328 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -191,40 +191,61 @@ static int kvm_zpci_clear_airq(struct zpci_dev *zdev) return cc ? -EIO : 0; } -static inline void unaccount_mem(unsigned long nr_pages) +static inline void unaccount_mem(struct kvm_zdev *kzdev, unsigned long nr_pages) { - struct user_struct *user = get_uid(current_user()); + struct user_struct *user = kzdev->user_account; + struct mm_struct *mm_account = kzdev->mm_account; - if (user) + if (user) { atomic_long_sub(nr_pages, &user->locked_vm); - if (current->mm) - atomic64_sub(nr_pages, ¤t->mm->pinned_vm); + free_uid(user); + kzdev->user_account = NULL; + } + + if (mm_account) { + atomic64_sub(nr_pages, &mm_account->pinned_vm); + mmdrop(mm_account); + kzdev->mm_account = NULL; + } } -static inline int account_mem(unsigned long nr_pages) +static inline int account_mem(struct kvm_zdev *kzdev, unsigned long nr_pages) { struct user_struct *user = get_uid(current_user()); unsigned long page_limit, cur_pages, new_pages; + int rc = 0; page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; cur_pages = atomic_long_read(&user->locked_vm); do { new_pages = cur_pages + nr_pages; - if (new_pages > page_limit) - return -ENOMEM; + if (new_pages > page_limit) { + rc = -ENOMEM; + goto out; + } } while (!atomic_long_try_cmpxchg(&user->locked_vm, &cur_pages, new_pages)); - atomic64_add(nr_pages, ¤t->mm->pinned_vm); + if (current->mm) { + mmgrab(current->mm); + atomic64_add(nr_pages, ¤t->mm->pinned_vm); + } + + kzdev->user_account = user; + kzdev->mm_account = current->mm; return 0; + +out: + free_uid(user); + return rc; } static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, bool assist) { struct page *pages[1], *aibv_page, *aisb_page = NULL; - unsigned int msi_vecs, idx; + unsigned int msi_vecs, idx, size; struct zpci_gaite *gaite; unsigned long hva, bit; struct kvm *kvm; @@ -238,6 +259,10 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, if (zdev->gisa == 0) return -EINVAL; + /* AIF already enabled for the device */ + if (zdev->kzdev->fib.fmt0.aibv != 0) + return -EINVAL; + kvm = zdev->kzdev->kvm; msi_vecs = min_t(unsigned int, fib->fmt0.noi, zdev->max_msi); @@ -247,6 +272,14 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, return gisc; /* Replace AIBV address */ + size = BITS_TO_LONGS(msi_vecs + fib->fmt0.aibvo) * sizeof(unsigned long); + npages = DIV_ROUND_UP((fib->fmt0.aibv & ~PAGE_MASK) + size, PAGE_SIZE); + /* AIBV cannot span more than 1 page */ + if (npages > 1) { + rc = -EINVAL; + goto out; + } + idx = srcu_read_lock(&kvm->srcu); hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aibv)); npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, pages); @@ -262,6 +295,12 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, /* Pin the guest AISB if one was specified */ if (fib->fmt0.sum == 1) { + /* AISB must be dword aligned */ + if (fib->fmt0.aisb & 0x7) { + rc = -EINVAL; + goto unpin1; + } + idx = srcu_read_lock(&kvm->srcu); hva = gfn_to_hva(kvm, gpa_to_gfn((gpa_t)fib->fmt0.aisb)); npages = pin_user_pages_fast(hva, 1, FOLL_WRITE | FOLL_LONGTERM, @@ -276,20 +315,28 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, } /* Account for pinned pages, roll back on failure */ - if (account_mem(pcount)) + rc = account_mem(zdev->kzdev, pcount); + if (rc) goto unpin2; /* AISB must be allocated before we can fill in GAITE */ mutex_lock(&aift->aift_lock); bit = airq_iv_alloc_bit(aift->sbv); - if (bit == -1UL) + if (bit == -1UL) { + rc = -ENOMEM; goto unlock; + } zdev->aisb = bit; /* store the summary bit number */ zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK | AIRQ_IV_GUESTVEC, phys_to_virt(fib->fmt0.aibv)); + if (!zdev->aibv) { + rc = -ENOMEM; + goto free_aisb; + } + spin_lock_irq(&aift->gait_lock); gaite = aift->gait + zdev->aisb; @@ -326,7 +373,12 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, rc = kvm_zpci_set_airq(zdev); return rc; +free_aisb: + airq_iv_free_bit(aift->sbv, zdev->aisb); + zdev->aisb = 0; unlock: + if (pcount > 0) + unaccount_mem(zdev->kzdev, pcount); mutex_unlock(&aift->aift_lock); unpin2: if (fib->fmt0.sum == 1) @@ -397,7 +449,7 @@ static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force) pcount++; } if (pcount > 0) - unaccount_mem(pcount); + unaccount_mem(kzdev, pcount); out: mutex_unlock(&aift->aift_lock); diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index ff0972dd5e71..fdf8c7bf4ed0 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -22,6 +22,8 @@ struct kvm_zdev { struct kvm *kvm; struct zpci_fib fib; struct list_head entry; + struct user_struct *user_account; + struct mm_struct *mm_account; }; struct zpci_gaite { diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 51e7a28af899..f3f79ba78410 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -188,6 +188,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, goto out_unlock_mmap; } + ret = -EFAULT; io_addr = (void __iomem *)((args.pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 25d9258fa592..02d1ad3052f1 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1000,6 +1000,9 @@ static int vector_mmsg_rx(struct vector_private *vp, int budget) */ dev_kfree_skb_irq(skb); vp->estats.rx_encaps_errors++; + (*skbuff_vector) = NULL; + mmsg_vector++; + skbuff_vector++; continue; } if (header_check > 0) { diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index b25c6a9303b7..3a2bba7c25e9 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -32,8 +32,15 @@ int memcmp(const void *s1, const void *s2, size_t len) { bool diff; - asm("repe cmpsb" - : "=@ccnz" (diff), "+D" (s1), "+S" (s2), "+c" (len)); + + /* + * Make sure ZF is properly set in the len==0 case because in it, + * RCX==0 and the REPE; CMPSB won't get executed. + */ + asm volatile("test %3, %3\n\t" + "repe cmpsb" + : "=@ccnz" (diff), "+D" (s1), "+S" (s2), "+c" (len) + : : "cc", "memory"); return diff; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index c4febdbcfe4d..cae0dcd9006b 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -440,7 +440,7 @@ EXPORT_SYMBOL_GPL(hv_get_hypervisor_version); static void __init ms_hyperv_init_platform(void) { - int hv_max_functions_eax; + int hv_max_functions_eax, eax; #ifdef CONFIG_PARAVIRT pv_info.name = "Hyper-V"; @@ -475,6 +475,19 @@ static void __init ms_hyperv_init_platform(void) pr_info("Hyper-V: running on a nested hypervisor\n"); } + /* + * There is no check against the max function for HYPERV_CPUID_VIRT_STACK_* CPUID + * leaves as the hypervisor doesn't handle them. Even a nested root partition (L2 + * root) will not get them because the nested (L1) hypervisor filters them out. + * These are handled through intercept processing by the Windows Hyper-V stack + * or the paravisor. + */ + eax = cpuid_eax(HYPERV_CPUID_VIRT_STACK_PROPERTIES); + ms_hyperv.confidential_vmbus_available = + eax & HYPERV_VS_PROPERTIES_EAX_CONFIDENTIAL_VMBUS_AVAILABLE; + ms_hyperv.msi_ext_dest_id = + eax & HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE; + if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { x86_platform.calibrate_tsc = hv_get_tsc_khz; @@ -675,21 +688,10 @@ static bool __init ms_hyperv_x2apic_available(void) * pci-hyperv host bridge. * * Note: for a Hyper-V root partition, this will always return false. - * The hypervisor doesn't expose these HYPERV_CPUID_VIRT_STACK_* cpuids by - * default, they are implemented as intercepts by the Windows Hyper-V stack. - * Even a nested root partition (L2 root) will not get them because the - * nested (L1) hypervisor filters them out. */ static bool __init ms_hyperv_msi_ext_dest_id(void) { - u32 eax; - - eax = cpuid_eax(HYPERV_CPUID_VIRT_STACK_INTERFACE); - if (eax != HYPERV_VS_INTERFACE_EAX_SIGNATURE) - return false; - - eax = cpuid_eax(HYPERV_CPUID_VIRT_STACK_PROPERTIES); - return eax & HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE; + return ms_hyperv.msi_ext_dest_id; } #ifdef CONFIG_AMD_MEM_ENCRYPT diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index a700f3795c17..62eb7b871a84 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -220,14 +220,6 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm) if (!sev_es_guest(svm->vcpu.kvm)) svm_set_intercept(svm, INTERCEPT_CR8_WRITE); - /* - * If running nested and the guest uses its own MSR bitmap, there - * is no need to update L0's msr bitmap - */ - if (is_guest_mode(&svm->vcpu) && - vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)) - return; - /* Enabling MSR intercept for x2APIC registers */ avic_set_x2apic_msr_interception(svm, true); } diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 96677576c836..e131c7b555dc 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -101,7 +101,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) : [output] "=r" (value) : [field] "r" (field) - : "cc" + : "cc", "memory" : do_fail, do_exception); return value; @@ -146,7 +146,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) : ASM_CALL_CONSTRAINT, [output] "=&r" (value) : [field] "r" (field) - : "cc"); + : "cc", "memory"); return value; #endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ @@ -194,7 +194,7 @@ do { \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ - : : op1 : "cc" : error, fault); \ + : : op1 : "cc", "memory" : error, fault); \ return; \ error: \ instrumentation_begin(); \ @@ -211,7 +211,7 @@ do { \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ - : : op1, op2 : "cc" : error, fault); \ + : : op1, op2 : "cc", "memory" : error, fault);\ return; \ error: \ instrumentation_begin(); \ diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c index 8eae30fe14f9..8759b53ba38e 100644 --- a/drivers/accel/qaic/qaic_control.c +++ b/drivers/accel/qaic/qaic_control.c @@ -782,7 +782,7 @@ static int encode_message(struct qaic_device *qdev, struct manage_msg *user_msg, break; } trans_hdr = (struct qaic_manage_trans_hdr *)(user_msg->data + user_len); - if (trans_hdr->len < sizeof(trans_hdr) || + if (trans_hdr->len < sizeof(*trans_hdr) || size_add(user_len, trans_hdr->len) > user_msg->len) { ret = -EINVAL; break; diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c index 2d6a08c23d6a..2961e53288f4 100644 --- a/drivers/ata/ahci_ceva.c +++ b/drivers/ata/ahci_ceva.c @@ -211,7 +211,7 @@ static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv) rc = phy_init(hpriv->phys[i]); if (rc) - goto disable_rsts; + goto exit_phys; } /* De-assert the controller reset */ @@ -230,14 +230,24 @@ static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv) return 0; -disable_rsts: - ahci_platform_deassert_rsts(hpriv); - disable_phys: while (--i >= 0) { + if (ahci_ignore_port(hpriv, i)) + continue; + phy_power_off(hpriv->phys[i]); phy_exit(hpriv->phys[i]); } + ahci_platform_assert_rsts(hpriv); + goto disable_clks; + +exit_phys: + while (--i >= 0) { + if (ahci_ignore_port(hpriv, i)) + continue; + + phy_exit(hpriv->phys[i]); + } disable_clks: ahci_platform_disable_clks(hpriv); diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 5e8a63206108..44daae8f378a 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -106,6 +106,12 @@ static const unsigned int ata_eh_flush_timeouts[] = { UINT_MAX, }; +static const unsigned int ata_eh_standby_timeouts[] = { + 15000, /* Some drives may be slow to standby */ + /* but don't hold up a suspend too long waiting for them */ + UINT_MAX, +}; + static const unsigned int ata_eh_other_timeouts[] = { 5000, /* same rationale as identify timeout */ 10000, /* ditto */ @@ -147,6 +153,8 @@ ata_eh_cmd_timeout_table[ATA_EH_CMD_TIMEOUT_TABLE_SIZE] = { .timeouts = ata_eh_other_timeouts, }, { .commands = CMDS(ATA_CMD_FLUSH, ATA_CMD_FLUSH_EXT), .timeouts = ata_eh_flush_timeouts }, + { .commands = CMDS(ATA_CMD_STANDBYNOW1), + .timeouts = ata_eh_standby_timeouts }, { .commands = CMDS(ATA_CMD_VERIFY), .timeouts = ata_eh_reset_timeouts }, }; diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 04e1e774645e..9b374e8f9938 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -913,7 +913,7 @@ static bool ata_scsi_lpm_supported(struct ata_port *ap) return false; ata_for_each_link(link, ap, EDGE) { - ata_for_each_dev(dev, &ap->link, ENABLED) { + ata_for_each_dev(dev, link, ENABLED) { if (dev->quirks & ATA_QUIRK_NOLPM) return false; } diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index ffb396f61731..1d8ca95fb732 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -4026,7 +4026,7 @@ static int mv_platform_probe(struct platform_device *pdev) /* * Simple resource validation .. */ - if (unlikely(pdev->num_resources != 1)) { + if (unlikely(pdev->num_resources != 1 && pdev->num_resources != 2)) { dev_err(&pdev->dev, "invalid number of resources\n"); return -EINVAL; } diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index cb31e96f01cd..615d3d28e7c6 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -3287,6 +3287,15 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) /* update device id */ ub->dev_info.dev_id = ub->ub_number; + /* + * ->state and ->ublksrv_pid are owned by the driver and only read back + * by userspace, but they come from the copied-in dev_info, so reset + * them. Otherwise a device added with ->state != DEAD looks live while + * ->ub_disk is still NULL. + */ + ub->dev_info.state = UBLK_S_DEV_DEAD; + ub->dev_info.ublksrv_pid = -1; + /* * 64bit flags will be copied back to userspace as feature * negotiation result, so have to clear flags which driver diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 5e0a05edcbfd..4d6b6bbb4267 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -3694,6 +3694,9 @@ static int btintel_diagnostics(struct hci_dev *hdev, struct sk_buff *skb) { struct intel_tlv *tlv = (void *)&skb->data[5]; + if (skb->len < 5 + sizeof(*tlv) + sizeof(tlv->val[0])) + goto recv_frame; + /* The first event is always an event type TLV */ if (tlv->type != INTEL_TLV_TYPE_ID) goto recv_frame; diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index a908e7b46eca..df0b59e6f968 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -763,30 +763,24 @@ static int btmtk_usb_uhw_reg_write(struct hci_dev *hdev, u32 reg, u32 val) static int btmtk_usb_uhw_reg_read(struct hci_dev *hdev, u32 reg, u32 *val) { struct btmtk_data *data = hci_get_priv(hdev); - int pipe, err; - void *buf; - - buf = kzalloc(4, GFP_KERNEL); - if (!buf) - return -ENOMEM; + u8 buf[sizeof(u32)]; + int err; - pipe = usb_rcvctrlpipe(data->udev, 0); - err = usb_control_msg(data->udev, pipe, 0x01, - 0xDE, - reg >> 16, reg & 0xffff, - buf, 4, USB_CTRL_GET_TIMEOUT); - if (err < 0) { + *val = 0; + err = usb_control_msg_recv(data->udev, 0, 0x01, + 0xDE, + reg >> 16, reg & 0xffff, + buf, sizeof(buf), USB_CTRL_GET_TIMEOUT, + GFP_KERNEL); + if (err) { bt_dev_err(hdev, "Failed to read uhw reg(%d)", err); - goto err_free_buf; + return err; } *val = get_unaligned_le32(buf); bt_dev_dbg(hdev, "reg=%x, value=0x%08x", reg, *val); -err_free_buf: - kfree(buf); - - return err; + return 0; } static int btmtk_usb_reg_read(struct hci_dev *hdev, u32 reg, u32 *val) @@ -836,7 +830,7 @@ int btmtk_usb_subsys_reset(struct hci_dev *hdev, u32 dev_id) if (dev_id == 0x7922) { err = btmtk_usb_uhw_reg_read(hdev, MTK_BT_SUBSYS_RST, &val); - if (err < 0) + if (err) return err; val |= 0x00002020; err = btmtk_usb_uhw_reg_write(hdev, MTK_BT_SUBSYS_RST, val); @@ -846,7 +840,7 @@ int btmtk_usb_subsys_reset(struct hci_dev *hdev, u32 dev_id) if (err < 0) return err; err = btmtk_usb_uhw_reg_read(hdev, MTK_BT_SUBSYS_RST, &val); - if (err < 0) + if (err) return err; val |= BIT(0); err = btmtk_usb_uhw_reg_write(hdev, MTK_BT_SUBSYS_RST, val); @@ -855,14 +849,14 @@ int btmtk_usb_subsys_reset(struct hci_dev *hdev, u32 dev_id) msleep(100); } else if (dev_id == 0x7925) { err = btmtk_usb_uhw_reg_read(hdev, MTK_BT_RESET_REG_CONNV3, &val); - if (err < 0) + if (err) return err; val |= (1 << 5); err = btmtk_usb_uhw_reg_write(hdev, MTK_BT_RESET_REG_CONNV3, val); if (err < 0) return err; err = btmtk_usb_uhw_reg_read(hdev, MTK_BT_RESET_REG_CONNV3, &val); - if (err < 0) + if (err) return err; val &= 0xFFFF00FF; val |= (1 << 13); @@ -873,7 +867,7 @@ int btmtk_usb_subsys_reset(struct hci_dev *hdev, u32 dev_id) if (err < 0) return err; err = btmtk_usb_uhw_reg_read(hdev, MTK_BT_RESET_REG_CONNV3, &val); - if (err < 0) + if (err) return err; val |= (1 << 0); err = btmtk_usb_uhw_reg_write(hdev, MTK_BT_RESET_REG_CONNV3, val); @@ -883,13 +877,13 @@ int btmtk_usb_subsys_reset(struct hci_dev *hdev, u32 dev_id) if (err < 0) return err; err = btmtk_usb_uhw_reg_read(hdev, MTK_UDMA_INT_STA_BT, &val); - if (err < 0) + if (err) return err; err = btmtk_usb_uhw_reg_write(hdev, MTK_UDMA_INT_STA_BT1, 0x000000FF); if (err < 0) return err; err = btmtk_usb_uhw_reg_read(hdev, MTK_UDMA_INT_STA_BT1, &val); - if (err < 0) + if (err) return err; msleep(100); } else { @@ -899,7 +893,7 @@ int btmtk_usb_subsys_reset(struct hci_dev *hdev, u32 dev_id) if (err < 0) return err; err = btmtk_usb_uhw_reg_read(hdev, MTK_BT_WDT_STATUS, &val); - if (err < 0) + if (err) return err; /* Reset the bluetooth chip via USB interface. */ err = btmtk_usb_uhw_reg_write(hdev, MTK_BT_SUBSYS_RST, 1); @@ -909,13 +903,13 @@ int btmtk_usb_subsys_reset(struct hci_dev *hdev, u32 dev_id) if (err < 0) return err; err = btmtk_usb_uhw_reg_read(hdev, MTK_UDMA_INT_STA_BT, &val); - if (err < 0) + if (err) return err; err = btmtk_usb_uhw_reg_write(hdev, MTK_UDMA_INT_STA_BT1, 0x000000FF); if (err < 0) return err; err = btmtk_usb_uhw_reg_read(hdev, MTK_UDMA_INT_STA_BT1, &val); - if (err < 0) + if (err) return err; /* MT7921 need to delay 20ms between toggle reset bit */ msleep(20); @@ -923,7 +917,7 @@ int btmtk_usb_subsys_reset(struct hci_dev *hdev, u32 dev_id) if (err < 0) return err; err = btmtk_usb_uhw_reg_read(hdev, MTK_BT_SUBSYS_RST, &val); - if (err < 0) + if (err) return err; } diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index fea3cb502a4e..cb8f14b9cae8 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -3345,28 +3345,16 @@ static const char *qca_get_fw_subdirectory(const struct qca_version *ver) static int btusb_qca_send_vendor_req(struct usb_device *udev, u8 request, void *data, u16 size) { - int pipe, err; - u8 *buf; - - buf = kmalloc(size, GFP_KERNEL); - if (!buf) - return -ENOMEM; + int err; /* Found some of USB hosts have IOT issues with ours so that we should * not wait until HCI layer is ready. */ - pipe = usb_rcvctrlpipe(udev, 0); - err = usb_control_msg(udev, pipe, request, USB_TYPE_VENDOR | USB_DIR_IN, - 0, 0, buf, size, USB_CTRL_GET_TIMEOUT); - if (err < 0) { + err = usb_control_msg_recv(udev, 0, request, USB_TYPE_VENDOR | USB_DIR_IN, + 0, 0, data, size, USB_CTRL_GET_TIMEOUT, + GFP_KERNEL); + if (err) dev_err(&udev->dev, "Failed to access otp area (%d)", err); - goto done; - } - - memcpy(data, buf, size); - -done: - kfree(buf); return err; } @@ -3573,7 +3561,7 @@ static bool btusb_qca_need_patch(struct usb_device *udev) struct qca_version ver; if (btusb_qca_send_vendor_req(udev, QCA_GET_TARGET_VERSION, &ver, - sizeof(ver)) < 0) + sizeof(ver))) return false; /* only low ROM versions need patches */ return !(le32_to_cpu(ver.rom_version) & ~0xffffU); @@ -3591,7 +3579,7 @@ static int btusb_setup_qca(struct hci_dev *hdev) err = btusb_qca_send_vendor_req(udev, QCA_GET_TARGET_VERSION, &ver, sizeof(ver)); - if (err < 0) + if (err) return err; ver_rom = le32_to_cpu(ver.rom_version); @@ -3614,7 +3602,7 @@ static int btusb_setup_qca(struct hci_dev *hdev) err = btusb_qca_send_vendor_req(udev, QCA_CHECK_STATUS, &status, sizeof(status)); - if (err < 0) + if (err) return err; if (!(status & QCA_PATCH_UPDATED)) { @@ -3625,7 +3613,7 @@ static int btusb_setup_qca(struct hci_dev *hdev) err = btusb_qca_send_vendor_req(udev, QCA_GET_TARGET_VERSION, &ver, sizeof(ver)); - if (err < 0) + if (err) return err; btdata->qca_dump.fw_version = le32_to_cpu(ver.patch_version); diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c index f7512b4e923e..0012c3e3a915 100644 --- a/drivers/cpufreq/powernow-k8.c +++ b/drivers/cpufreq/powernow-k8.c @@ -1083,6 +1083,7 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol) err_out_exit_acpi: powernow_k8_cpu_exit_acpi(data); + kfree(data->powernow_table); err_out: kfree(data); diff --git a/drivers/dibs/dibs_loopback.c b/drivers/dibs/dibs_loopback.c index 8e165bdedb33..73ca4fbca097 100644 --- a/drivers/dibs/dibs_loopback.c +++ b/drivers/dibs/dibs_loopback.c @@ -118,14 +118,9 @@ static int dibs_lo_register_dmb(struct dibs_dev *dibs, struct dibs_dmb *dmb, return rc; } -static void __dibs_lo_unregister_dmb(struct dibs_lo_dev *ldev, - struct dibs_lo_dmb_node *dmb_node) +static void dibs_lo_free_dmb(struct dibs_lo_dev *ldev, + struct dibs_lo_dmb_node *dmb_node) { - /* remove dmb from hash table */ - write_lock_bh(&ldev->dmb_ht_lock); - hash_del(&dmb_node->list); - write_unlock_bh(&ldev->dmb_ht_lock); - clear_bit(dmb_node->sba_idx, ldev->sba_idx_mask); folio_put(virt_to_folio(dmb_node->cpu_addr)); kfree(dmb_node); @@ -139,27 +134,33 @@ static int dibs_lo_unregister_dmb(struct dibs_dev *dibs, struct dibs_dmb *dmb) struct dibs_lo_dmb_node *dmb_node = NULL, *tmp_node; struct dibs_lo_dev *ldev; unsigned long flags; + bool last; ldev = dibs->drv_priv; /* find dmb from hash table */ - read_lock_bh(&ldev->dmb_ht_lock); + write_lock_bh(&ldev->dmb_ht_lock); hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb->dmb_tok) { if (tmp_node->token == dmb->dmb_tok) { dmb_node = tmp_node; break; } } - read_unlock_bh(&ldev->dmb_ht_lock); - if (!dmb_node) + if (!dmb_node) { + write_unlock_bh(&ldev->dmb_ht_lock); return -EINVAL; + } + last = refcount_dec_and_test(&dmb_node->refcnt); + if (last) + hash_del(&dmb_node->list); + write_unlock_bh(&ldev->dmb_ht_lock); - if (refcount_dec_and_test(&dmb_node->refcnt)) { + if (last) { spin_lock_irqsave(&dibs->lock, flags); dibs->dmb_clientid_arr[dmb_node->sba_idx] = NO_DIBS_CLIENT; spin_unlock_irqrestore(&dibs->lock, flags); - __dibs_lo_unregister_dmb(ldev, dmb_node); + dibs_lo_free_dmb(ldev, dmb_node); } return 0; } @@ -188,14 +189,9 @@ static int dibs_lo_attach_dmb(struct dibs_dev *dibs, struct dibs_dmb *dmb) read_unlock_bh(&ldev->dmb_ht_lock); return -EINVAL; } + refcount_inc(&dmb_node->refcnt); read_unlock_bh(&ldev->dmb_ht_lock); - if (!refcount_inc_not_zero(&dmb_node->refcnt)) - /* the dmb is being unregistered, but has - * not been removed from the hash table. - */ - return -EINVAL; - /* provide dmb information */ dmb->idx = dmb_node->sba_idx; dmb->dmb_tok = dmb_node->token; @@ -209,11 +205,12 @@ static int dibs_lo_detach_dmb(struct dibs_dev *dibs, u64 token) { struct dibs_lo_dmb_node *dmb_node = NULL, *tmp_node; struct dibs_lo_dev *ldev; + bool last; ldev = dibs->drv_priv; /* find dmb_node according to dmb->dmb_tok */ - read_lock_bh(&ldev->dmb_ht_lock); + write_lock_bh(&ldev->dmb_ht_lock); hash_for_each_possible(ldev->dmb_ht, tmp_node, list, token) { if (tmp_node->token == token) { dmb_node = tmp_node; @@ -221,13 +218,17 @@ static int dibs_lo_detach_dmb(struct dibs_dev *dibs, u64 token) } } if (!dmb_node) { - read_unlock_bh(&ldev->dmb_ht_lock); + write_unlock_bh(&ldev->dmb_ht_lock); return -EINVAL; } - read_unlock_bh(&ldev->dmb_ht_lock); + last = refcount_dec_and_test(&dmb_node->refcnt); + if (last) + hash_del(&dmb_node->list); + write_unlock_bh(&ldev->dmb_ht_lock); + + if (last) + dibs_lo_free_dmb(ldev, dmb_node); - if (refcount_dec_and_test(&dmb_node->refcnt)) - __dibs_lo_unregister_dmb(ldev, dmb_node); return 0; } diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 4105688cf3f0..37addcdc10bc 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -288,6 +288,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) fdev->parent = cdev_dev(idxd_cdev); fdev->bus = &dsa_bus_type; fdev->type = &idxd_cdev_file_type; + idxd_wq_get(wq); rc = dev_set_name(fdev, "file%d", ctx->id); if (rc < 0) { @@ -301,13 +302,14 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) goto failed_dev_add; } - idxd_wq_get(wq); mutex_unlock(&wq->wq_lock); return 0; failed_dev_add: failed_dev_name: + mutex_unlock(&wq->wq_lock); put_device(fdev); + return rc; failed_ida: failed_set_pasid: if (device_user_pasid_enabled(idxd)) diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c index f9d876deb1f0..ae362a2f7c40 100644 --- a/drivers/dma/sun6i-dma.c +++ b/drivers/dma/sun6i-dma.c @@ -935,16 +935,13 @@ static int sun6i_dma_terminate_all(struct dma_chan *chan) spin_lock_irqsave(&vchan->vc.lock, flags); - if (vchan->cyclic) { - vchan->cyclic = false; - if (pchan && pchan->desc) { - struct virt_dma_desc *vd = &pchan->desc->vd; - struct virt_dma_chan *vc = &vchan->vc; + if (pchan && pchan->desc && pchan->desc != pchan->done) { + struct virt_dma_desc *vd = &pchan->desc->vd; - list_add_tail(&vd->node, &vc->desc_completed); - } + vchan_terminate_vdesc(vd); } + vchan->cyclic = false; vchan_get_all_descriptors(&vchan->vc, &head); if (pchan) { diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index f7daeadaea57..b18a2d0f6984 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -1370,9 +1370,20 @@ static int pca953x_restore_context(struct pca953x_chip *chip) regcache_mark_dirty(chip->regmap); ret = pca953x_regcache_sync(chip); if (ret) - return ret; + goto err; + + ret = regcache_sync(chip->regmap); + if (ret) + goto err; + + return 0; - return regcache_sync(chip->regmap); +err: + if (chip->client->irq > 0) + disable_irq(chip->client->irq); + regcache_cache_only(chip->regmap, true); + + return ret; } static void pca953x_save_context(struct pca953x_chip *chip) diff --git a/drivers/gpio/gpio-pch.c b/drivers/gpio/gpio-pch.c index 9925687e05fb..1a7e42267529 100644 --- a/drivers/gpio/gpio-pch.c +++ b/drivers/gpio/gpio-pch.c @@ -96,7 +96,7 @@ struct pch_gpio { struct pch_gpio_reg_data pch_gpio_reg; int irq_base; enum pch_type_t ioh; - spinlock_t spinlock; + raw_spinlock_t spinlock; }; static int pch_gpio_set(struct gpio_chip *gpio, unsigned int nr, int val) @@ -105,7 +105,7 @@ static int pch_gpio_set(struct gpio_chip *gpio, unsigned int nr, int val) struct pch_gpio *chip = gpiochip_get_data(gpio); unsigned long flags; - spin_lock_irqsave(&chip->spinlock, flags); + raw_spin_lock_irqsave(&chip->spinlock, flags); reg_val = ioread32(&chip->reg->po); if (val) reg_val |= BIT(nr); @@ -113,7 +113,7 @@ static int pch_gpio_set(struct gpio_chip *gpio, unsigned int nr, int val) reg_val &= ~BIT(nr); iowrite32(reg_val, &chip->reg->po); - spin_unlock_irqrestore(&chip->spinlock, flags); + raw_spin_unlock_irqrestore(&chip->spinlock, flags); return 0; } @@ -133,7 +133,7 @@ static int pch_gpio_direction_output(struct gpio_chip *gpio, unsigned int nr, u32 reg_val; unsigned long flags; - spin_lock_irqsave(&chip->spinlock, flags); + raw_spin_lock_irqsave(&chip->spinlock, flags); reg_val = ioread32(&chip->reg->po); if (val) @@ -147,7 +147,7 @@ static int pch_gpio_direction_output(struct gpio_chip *gpio, unsigned int nr, pm |= BIT(nr); iowrite32(pm, &chip->reg->pm); - spin_unlock_irqrestore(&chip->spinlock, flags); + raw_spin_unlock_irqrestore(&chip->spinlock, flags); return 0; } @@ -158,12 +158,12 @@ static int pch_gpio_direction_input(struct gpio_chip *gpio, unsigned int nr) u32 pm; unsigned long flags; - spin_lock_irqsave(&chip->spinlock, flags); + raw_spin_lock_irqsave(&chip->spinlock, flags); pm = ioread32(&chip->reg->pm); pm &= BIT(gpio_pins[chip->ioh]) - 1; pm &= ~BIT(nr); iowrite32(pm, &chip->reg->pm); - spin_unlock_irqrestore(&chip->spinlock, flags); + raw_spin_unlock_irqrestore(&chip->spinlock, flags); return 0; } @@ -265,7 +265,7 @@ static int pch_irq_type(struct irq_data *d, unsigned int type) return 0; } - spin_lock_irqsave(&chip->spinlock, flags); + raw_spin_lock_irqsave(&chip->spinlock, flags); /* Set interrupt mode */ im = ioread32(im_reg) & ~(PCH_IM_MASK << (im_pos * 4)); @@ -277,7 +277,7 @@ static int pch_irq_type(struct irq_data *d, unsigned int type) else if (type & IRQ_TYPE_EDGE_BOTH) irq_set_handler_locked(d, handle_edge_irq); - spin_unlock_irqrestore(&chip->spinlock, flags); + raw_spin_unlock_irqrestore(&chip->spinlock, flags); return 0; } @@ -374,7 +374,7 @@ static int pch_gpio_probe(struct pci_dev *pdev, chip->ioh = id->driver_data; chip->reg = chip->base; pci_set_drvdata(pdev, chip); - spin_lock_init(&chip->spinlock); + raw_spin_lock_init(&chip->spinlock); pch_gpio_setup(chip); ret = devm_gpiochip_add_data(dev, &chip->gpio, chip); @@ -407,9 +407,9 @@ static int __maybe_unused pch_gpio_suspend(struct device *dev) struct pch_gpio *chip = dev_get_drvdata(dev); unsigned long flags; - spin_lock_irqsave(&chip->spinlock, flags); + raw_spin_lock_irqsave(&chip->spinlock, flags); pch_gpio_save_reg_conf(chip); - spin_unlock_irqrestore(&chip->spinlock, flags); + raw_spin_unlock_irqrestore(&chip->spinlock, flags); return 0; } @@ -419,11 +419,11 @@ static int __maybe_unused pch_gpio_resume(struct device *dev) struct pch_gpio *chip = dev_get_drvdata(dev); unsigned long flags; - spin_lock_irqsave(&chip->spinlock, flags); + raw_spin_lock_irqsave(&chip->spinlock, flags); iowrite32(0x01, &chip->reg->reset); iowrite32(0x00, &chip->reg->reset); pch_gpio_restore_reg_conf(chip); - spin_unlock_irqrestore(&chip->spinlock, flags); + raw_spin_unlock_irqrestore(&chip->spinlock, flags); return 0; } diff --git a/drivers/gpio/gpio-sloppy-logic-analyzer.c b/drivers/gpio/gpio-sloppy-logic-analyzer.c index 969dddd3d6fa..0f4a6228a748 100644 --- a/drivers/gpio/gpio-sloppy-logic-analyzer.c +++ b/drivers/gpio/gpio-sloppy-logic-analyzer.c @@ -161,6 +161,13 @@ static int fops_buf_size_get(void *data, u64 *val) return 0; } +static void fops_buf_release(void *data) +{ + struct gpio_la_poll_priv *priv = data; + + vfree(priv->blob.data); +} + static int fops_buf_size_set(void *data, u64 val) { struct gpio_la_poll_priv *priv = data; @@ -239,6 +246,9 @@ static int gpio_la_poll_probe(struct platform_device *pdev) return ret; fops_buf_size_set(priv, GPIO_LA_DEFAULT_BUF_SIZE); + ret = devm_add_action_or_reset(dev, fops_buf_release, priv); + if (ret) + return ret; priv->descs = devm_gpiod_get_array(dev, "probe", GPIOD_IN); if (IS_ERR(priv->descs)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 4b449b58d907..752b34cffdc5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -864,7 +864,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, struct amdgpu_vm *vm = &fpriv->vm; struct amdgpu_bo_list_entry *e; struct drm_gem_object *obj; - unsigned long index; unsigned int i; int r; @@ -969,7 +968,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, goto out_free_user_pages; } - drm_exec_for_each_locked_object(&p->exec, index, obj) { + drm_exec_for_each_locked_object(&p->exec, obj) { r = amdgpu_cs_bo_validate(p, gem_to_amdgpu_bo(obj)); if (unlikely(r)) goto out_free_user_pages; @@ -1187,19 +1186,6 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.bo); } - if (adev->debug_vm) { - /* Invalidate all BOs to test for userspace bugs */ - amdgpu_bo_list_for_each_entry(e, p->bo_list) { - struct amdgpu_bo *bo = e->bo; - - /* ignore duplicates */ - if (!bo) - continue; - - amdgpu_vm_bo_invalidate(bo, false); - } - } - return 0; } @@ -1209,7 +1195,6 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) struct drm_gpu_scheduler *sched; struct drm_gem_object *obj; struct dma_fence *fence; - unsigned long index; unsigned int i; int r; @@ -1220,7 +1205,7 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) return r; } - drm_exec_for_each_locked_object(&p->exec, index, obj) { + drm_exec_for_each_locked_object(&p->exec, obj) { struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); struct dma_resv *resv = bo->tbo.base.resv; @@ -1289,7 +1274,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, struct amdgpu_vm *vm = &fpriv->vm; struct amdgpu_bo_list_entry *e; struct drm_gem_object *gobj; - unsigned long index; unsigned int i; uint64_t seq; int r; @@ -1340,7 +1324,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, } p->fence = dma_fence_get(&leader->base.s_fence->finished); - drm_exec_for_each_locked_object(&p->exec, index, gobj) { + drm_exec_for_each_locked_object(&p->exec, gobj) { ttm_bo_move_to_lru_tail_unlocked(&gem_to_amdgpu_bo(gobj)->tbo); @@ -1389,6 +1373,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, /* Cleanup the parser structure */ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser) { + struct amdgpu_device *adev = parser->adev; + struct amdgpu_bo_list_entry *e; unsigned int i; amdgpu_sync_free(&parser->sync); @@ -1404,8 +1390,21 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser) if (parser->ctx) amdgpu_ctx_put(parser->ctx); - if (parser->bo_list) + if (parser->bo_list) { + if (adev->debug_vm) { + /* Invalidate all BOs to test for userspace bugs */ + amdgpu_bo_list_for_each_entry(e, parser->bo_list) { + struct amdgpu_bo *bo = e->bo; + + /* ignore duplicates */ + if (!bo) + continue; + + amdgpu_vm_bo_invalidate(bo, false); + } + } amdgpu_bo_list_put(parser->bo_list); + } for (i = 0; i < parser->nchunks; i++) kvfree(parser->chunks[i].kdata); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index afedea02188d..32f3d7c49e1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -321,7 +321,6 @@ static int amdgpu_ctx_init(struct amdgpu_ctx_mgr *mgr, int32_t priority, struct drm_file *filp, struct amdgpu_ctx *ctx) { struct amdgpu_fpriv *fpriv = filp->driver_priv; - u32 current_stable_pstate; int r; r = amdgpu_ctx_priority_permit(filp, priority); @@ -339,37 +338,22 @@ static int amdgpu_ctx_init(struct amdgpu_ctx_mgr *mgr, int32_t priority, ctx->generation = amdgpu_vm_generation(mgr->adev, &fpriv->vm); ctx->init_priority = priority; ctx->override_priority = AMDGPU_CTX_PRIORITY_UNSET; - - r = amdgpu_ctx_get_stable_pstate(ctx, ¤t_stable_pstate); - if (r) - return r; - - if (mgr->adev->pm.stable_pstate_ctx) - ctx->stable_pstate = mgr->adev->pm.stable_pstate_ctx->stable_pstate; - else - ctx->stable_pstate = current_stable_pstate; + ctx->stable_pstate = AMDGPU_CTX_STABLE_PSTATE_NONE; ctx->ctx_mgr = &(fpriv->ctx_mgr); return 0; } -static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, - u32 stable_pstate) +static int __amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, + u32 stable_pstate) { struct amdgpu_device *adev = ctx->mgr->adev; enum amd_dpm_forced_level level; + struct amdgpu_ctx *current_ctx; u32 current_stable_pstate; - int r; + int r = 0; - mutex_lock(&adev->pm.stable_pstate_ctx_lock); - if (adev->pm.stable_pstate_ctx && adev->pm.stable_pstate_ctx != ctx) { - r = -EBUSY; - goto done; - } - - r = amdgpu_ctx_get_stable_pstate(ctx, ¤t_stable_pstate); - if (r || (stable_pstate == current_stable_pstate)) - goto done; + lockdep_assert_held(&adev->pm.stable_pstate_ctx_lock); switch (stable_pstate) { case AMDGPU_CTX_STABLE_PSTATE_NONE: @@ -388,17 +372,41 @@ static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, level = AMD_DPM_FORCED_LEVEL_PROFILE_PEAK; break; default: - r = -EINVAL; - goto done; + return -EINVAL; } + current_ctx = adev->pm.stable_pstate_ctx; + if (current_ctx && current_ctx != ctx) + return -EBUSY; + + r = amdgpu_ctx_get_stable_pstate(ctx, ¤t_stable_pstate); + if (r || current_stable_pstate == stable_pstate) + return r; + r = amdgpu_dpm_force_performance_level(adev, level); + if (r) + return r; - if (level == AMD_DPM_FORCED_LEVEL_AUTO) - adev->pm.stable_pstate_ctx = NULL; - else + if (!current_ctx) { adev->pm.stable_pstate_ctx = ctx; -done: + /* + * Serialized by context taking ownership for the first time + * while holding adev->pm.stable_pstate_ctx_lock). + */ + WRITE_ONCE(ctx->stable_pstate, current_stable_pstate); + } + + return 0; +} + +static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, + u32 stable_pstate) +{ + struct amdgpu_device *adev = ctx->mgr->adev; + int r; + + mutex_lock(&adev->pm.stable_pstate_ctx_lock); + r = __amdgpu_ctx_set_stable_pstate(ctx, stable_pstate); mutex_unlock(&adev->pm.stable_pstate_ctx_lock); return r; @@ -424,7 +432,12 @@ static void amdgpu_ctx_fini(struct kref *ref) } if (drm_dev_enter(adev_to_drm(adev), &idx)) { - amdgpu_ctx_set_stable_pstate(ctx, ctx->stable_pstate); + mutex_lock(&adev->pm.stable_pstate_ctx_lock); + if (adev->pm.stable_pstate_ctx == ctx) { + __amdgpu_ctx_set_stable_pstate(ctx, ctx->stable_pstate); + adev->pm.stable_pstate_ctx = NULL; + } + mutex_unlock(&adev->pm.stable_pstate_ctx_lock); drm_dev_exit(idx); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 7248947835f1..99f22633abf5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2891,6 +2891,19 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) return 0; } +static void amdgpu_restore_umd_profile_pstate_after_runpm(struct amdgpu_device *adev) +{ + enum amd_dpm_forced_level level; + uint32_t profile_mode_mask = AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD | + AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK | + AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK | + AMD_DPM_FORCED_LEVEL_PROFILE_PEAK; + + level = amdgpu_dpm_get_performance_level(adev); + if (level & profile_mode_mask) + amdgpu_asic_update_umd_stable_pstate(adev, true); +} + static int amdgpu_pmops_runtime_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); @@ -2935,6 +2948,8 @@ static int amdgpu_pmops_runtime_resume(struct device *dev) if (adev->pm.rpm_mode == AMDGPU_RUNPM_PX) drm_dev->switch_power_state = DRM_SWITCH_POWER_ON; + + amdgpu_restore_umd_profile_pstate_after_runpm(adev); adev->in_runpm = false; return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_eviction_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_eviction_fence.c index 23d7d0b0d625..83fad3a37184 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_eviction_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_eviction_fence.c @@ -49,7 +49,6 @@ amdgpu_eviction_fence_replace_fence(struct amdgpu_eviction_fence_mgr *evf_mgr, { struct amdgpu_eviction_fence *old_ef, *new_ef; struct drm_gem_object *obj; - unsigned long index; int ret; if (evf_mgr->ev_fence && @@ -77,7 +76,7 @@ amdgpu_eviction_fence_replace_fence(struct amdgpu_eviction_fence_mgr *evf_mgr, spin_unlock(&evf_mgr->ev_fence_lock); /* Attach the new fence */ - drm_exec_for_each_locked_object(exec, index, obj) { + drm_exec_for_each_locked_object(exec, obj) { struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); if (!bo) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index 0760e70402ec..52ed0fa000d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -217,7 +217,20 @@ static bool amdgpu_gtt_mgr_intersects(struct ttm_resource_manager *man, const struct ttm_place *place, size_t size) { - return !place->lpfn || amdgpu_gtt_mgr_has_gart_addr(res); + const struct drm_mm_node *const node = &to_ttm_range_mgr_node(res)->mm_nodes[0]; + const u32 num_pages = PFN_UP(size); + + if (!place->lpfn) + return true; + + if (!amdgpu_gtt_mgr_has_gart_addr(res)) + return false; + + if (place->fpfn >= (node->start + num_pages) || + (place->lpfn && place->lpfn <= node->start)) + return false; + + return true; } /** @@ -235,7 +248,20 @@ static bool amdgpu_gtt_mgr_compatible(struct ttm_resource_manager *man, const struct ttm_place *place, size_t size) { - return !place->lpfn || amdgpu_gtt_mgr_has_gart_addr(res); + const struct drm_mm_node *const node = &to_ttm_range_mgr_node(res)->mm_nodes[0]; + const u32 num_pages = PFN_UP(size); + + if (!place->lpfn) + return true; + + if (!amdgpu_gtt_mgr_has_gart_addr(res)) + return false; + + if (node->start < place->fpfn || + (place->lpfn && (node->start + num_pages) > place->lpfn)) + return false; + + return true; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index a4b5fe35c3cd..d6d463c93fdd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -2078,6 +2078,18 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) gtt_size = configured_size; } + /* Cap GTT so that it does not exceed total physical RAM. */ + if (adev->flags & AMD_IS_APU) { + u64 phys_ram = (u64)totalram_pages() << PAGE_SHIFT; + + if (gtt_size > phys_ram) { + gtt_size = phys_ram; + dev_info(adev->dev, + "Capping GTT to %uM to not exceed available system memory\n", + (unsigned int)(gtt_size / (1024 * 1024))); + } + } + /* Initialize GTT memory pool */ r = amdgpu_gtt_mgr_init(adev, gtt_size); if (r) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index c4fd83ae1762..d3190c3bb1ae 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -2971,10 +2971,14 @@ static int kfd_ioctl_set_debug_trap(struct file *filep, struct kfd_process *p, v goto out; } - /* Check if target is still PTRACED. */ + /* + * Verify debugger has permission to debug target process. + * For cross-process debugging, require active ptrace relationship. + * This applies to ALL operations to prevent unauthorized interference. + */ rcu_read_lock(); - if (target != p && args->op != KFD_IOC_DBG_TRAP_DISABLE - && ptrace_parent(target->lead_thread) != current) { + if (target != p && ptrace_parent(target->lead_thread) != current + && target->debugger_process != p) { pr_err("PID %i is not PTRACED and cannot be debugged\n", args->pid); r = -EPERM; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 2fdee34ae543..b033c3a9ce54 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -521,6 +521,9 @@ int kfd_criu_restore_event(struct file *devkfd, ret = create_other_event(p, ev, &ev_priv->event_id); break; + default: + ret = -EINVAL; + break; } mutex_unlock(&p->event_mutex); @@ -542,15 +545,27 @@ int kfd_criu_checkpoint_events(struct kfd_process *p, int ret = 0; struct kfd_event *ev; uint32_t ev_id; + uint32_t num_events; - uint32_t num_events = kfd_get_num_events(p); + /* Serialize the count and the walk below against concurrent event + * create/destroy. Those paths take only p->event_mutex, not the + * p->mutex held by the CRIU checkpoint caller, so without this the + * event_idr can grow between kfd_get_num_events() and the loop and the + * walk writes past the ev_privs allocation. + */ + mutex_lock(&p->event_mutex); - if (!num_events) + num_events = kfd_get_num_events(p); + if (!num_events) { + mutex_unlock(&p->event_mutex); return 0; + } ev_privs = kvzalloc(num_events * sizeof(*ev_privs), GFP_KERNEL); - if (!ev_privs) + if (!ev_privs) { + mutex_unlock(&p->event_mutex); return -ENOMEM; + } idr_for_each_entry(&p->event_idr, ev, ev_id) { @@ -591,6 +606,8 @@ int kfd_criu_checkpoint_events(struct kfd_process *p, i++; } + mutex_unlock(&p->event_mutex); + ret = copy_to_user(user_priv_data + *priv_data_offset, ev_privs, num_events * sizeof(*ev_privs)); if (ret) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 0bfe64cdabe6..e96488f6b02d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -375,7 +375,7 @@ int pqm_create_queue(struct process_queue_manager *pqm, false); if (retval) { dev_err(dev->adev->dev, "failed to allocate process context bo\n"); - return retval; + goto err_allocate_pqn; } memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c index 8e74e2bae590..6f06516da32a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c @@ -285,7 +285,7 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope } err = kfd_queue_buffer_get(vm, (void *)properties->eop_ring_buffer_address, &properties->eop_buf_bo, - ALIGN(properties->eop_ring_buffer_size, PAGE_SIZE)); + ALIGN((u64)properties->eop_ring_buffer_size, PAGE_SIZE)); if (err) goto out_err_unreserve; } 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 99759559cc0f..4f5329778662 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -676,13 +676,30 @@ static void dm_crtc_high_irq_handler(struct amdgpu_device *adev, * Deliver pageflip completion events (DCN only). * * Since GRPH_PFLIP is not used, VUPDATE_NO_LOCK is the flip latch - * point. Deliver any pending pageflip completion event from here. + * point. Deliver any pending pageflip completion event from here, + * once HW has consumed the new address (the OTG no longer reports a + * pending flip). * - * NOTE: This can deliver an event for a flip that was armed but not yet - * programmed into HW; that race is closed in a follow-up change by - * checking the programmed flip status. + * Also handle the case here where there aren't any active planes and + * DCN HUBP may be clock-gated, so the flip-pending status may be + * undefined. */ - if (is_dcn && acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED) { + if (is_dcn && acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && + acrtc->event) { + + if (!dc_get_flip_pending_on_otg(adev->dm.dc, acrtc->otg_inst)) { + drm_crtc_send_vblank_event(&acrtc->base, acrtc->event); + acrtc->event = NULL; + drm_crtc_vblank_put(&acrtc->base); + acrtc->pflip_status = AMDGPU_FLIP_NONE; + } + /* + * If the flip is still pending, leave it armed and + * retry on the next vupdate. + */ + } else if (is_dcn && acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && + acrtc->dm_irq_params.active_planes == 0) { + if (acrtc->event) { drm_crtc_send_vblank_event(&acrtc->base, acrtc->event); acrtc->event = NULL; @@ -9309,25 +9326,6 @@ static void remove_stream(struct amdgpu_device *adev, acrtc->enabled = false; } -static void prepare_flip_isr(struct amdgpu_crtc *acrtc) -{ - - assert_spin_locked(&acrtc->base.dev->event_lock); - WARN_ON(acrtc->event); - - acrtc->event = acrtc->base.state->event; - - /* Set the flip status */ - acrtc->pflip_status = AMDGPU_FLIP_SUBMITTED; - - /* Mark this event as consumed */ - acrtc->base.state->event = NULL; - - drm_dbg_state(acrtc->base.dev, - "crtc:%d, pflip_stat:AMDGPU_FLIP_SUBMITTED\n", - acrtc->crtc_id); -} - static void update_freesync_state_on_stream( struct amdgpu_display_manager *dm, struct dm_crtc_state *new_crtc_state, @@ -9664,6 +9662,58 @@ static void amdgpu_dm_enable_self_refresh(struct amdgpu_crtc *acrtc_attach, } } +static void dm_arm_vblank_event(struct amdgpu_crtc *acrtc, + struct dm_crtc_state *acrtc_state, + bool pflip_update, + bool cursor_update) +{ + assert_spin_locked(&acrtc->base.dev->event_lock); + + if (!acrtc->base.state->event || acrtc_state->active_planes == 0) + return; + + if (pflip_update) { + WARN_ON(acrtc->pflip_status != AMDGPU_FLIP_NONE); + WARN_ON(acrtc->event); + + acrtc->pflip_status = AMDGPU_FLIP_SUBMITTED; + acrtc->event = acrtc->base.state->event; + acrtc->base.state->event = NULL; + + drm_dbg_state(acrtc->base.dev, + "crtc:%d, pflip_stat:AMDGPU_FLIP_SUBMITTED\n", + acrtc->crtc_id); + } else if (cursor_update) { + acrtc->event = acrtc->base.state->event; + acrtc->base.state->event = NULL; + } +} + +/** + * dm_arm_vblank_event_pre_programming - Prepare for programming + * @acrtc: The amdgpu CRTC to prepare + * @acrtc_state: The new CRTC state + * @pflip_update: Whether a page flip is being programmed + * @cursor_update: Whether a cursor update is being programmed + * + * Grab a reference on the vblank counter if a page flip or cursor update is to + * be programmed. Do this before programming so the HW is not in any + * idle-optimized state (such as PSR). + */ +static void dm_arm_vblank_event_pre_programming(struct amdgpu_crtc *acrtc, + struct dm_crtc_state *acrtc_state, + bool pflip_update, + bool cursor_update) +{ + assert_spin_locked(&acrtc->base.dev->event_lock); + + if (!acrtc->base.state->event || acrtc_state->active_planes == 0) + return; + + if (pflip_update || cursor_update) + drm_crtc_vblank_get(&acrtc->base); +} + static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, struct drm_device *dev, struct amdgpu_display_manager *dm, @@ -9687,6 +9737,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bool cursor_update = false; bool pflip_present = false; bool immediate_flip = false; + bool flip_latched_during_prog = false; bool dirty_rects_changed = false; bool updated_planes_and_streams = false; struct { @@ -9922,39 +9973,27 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, usleep_range(1000, 1100); } - /** - * Prepare the flip event for the pageflip interrupt to handle. - * - * This only works in the case where we've already turned on the - * appropriate hardware blocks (eg. HUBP) so in the transition case - * from 0 -> n planes we have to skip a hardware generated event - * and rely on sending it from software. - */ - if (acrtc_attach->base.state->event && - acrtc_state->active_planes > 0) { - drm_crtc_vblank_get(pcrtc); - - spin_lock_irqsave(&pcrtc->dev->event_lock, flags); - - WARN_ON(acrtc_attach->pflip_status != AMDGPU_FLIP_NONE); - prepare_flip_isr(acrtc_attach); - - spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); - } - if (acrtc_state->stream) { if (acrtc_state->freesync_vrr_info_changed) bundle->stream_update.vrr_infopacket = &acrtc_state->stream->vrr_infopacket; } - } else if (cursor_update && acrtc_state->active_planes > 0) { - spin_lock_irqsave(&pcrtc->dev->event_lock, flags); - if (acrtc_attach->base.state->event) { - drm_crtc_vblank_get(pcrtc); - acrtc_attach->event = acrtc_attach->base.state->event; - acrtc_attach->base.state->event = NULL; + } + + scoped_guard(spinlock_irqsave, &pcrtc->dev->event_lock) { + dm_arm_vblank_event_pre_programming(acrtc_attach, acrtc_state, + pflip_present, + cursor_update); + /* + * DCE depends on a combination of GRPH_FLIP, VLINE0, and + * VUPDATE for event delivery. Only GRPH_FLIP handler can send + * pflip events, and it only fires if HW latched to the flip. + * Maintain legacy behavior by arming event before programming. + */ + if (amdgpu_ip_version(dm->adev, DCE_HWIP, 0) == 0) { + dm_arm_vblank_event(acrtc_attach, acrtc_state, + pflip_present, cursor_update); } - spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); } /* Update the planes if changed or disable if we don't have any. */ @@ -10056,17 +10095,103 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, amdgpu_dm_commit_cursors(state); /* - * On DCN, flip completion is normally delivered from VUPDATE_NO_LOCK. - * However, an immediate (tearing / async) flip is latched by HW right - * away and does not wait for the next vupdate, so deliver its - * completion event here after programming. + * DCN specific vblank handling + * ============================ + * + * With the event_lock held, arm the vblank event, and determine whether + * deliver it immediately, or in VUPDATE_NO_LOCK IRQ (i.e. HW latch + * point) handler. Do this *after* programming so that the IRQ handler + * will not deliver the event before HW laches onto the programmed + * values: + * + * Commit thread IRQ handler HW + * ----------------------------------------------------------------- + * arm_vblank_event() + * vupdate() + * vupdate_handler() + * cook_timestamp() + * # prev flip already latched, + * # so flip_latched == true. + * if event_armed && flip_latched: + * send_vblank_event() + * # sent before latch, **BAD!** + * hw_program() + * vupdate() + * **latch** + * + * There's a consequence of arming after: it's possible for HW to latch + * between start of HW programming and acrtc->event/pflip_status arming. + * When this happens, the IRQ handler will send the event on the next + * immediate latch point, even though HW has already latched. This is + * handled by optimistically checking for HW latch after programming, + * and if latched, send the event immediately: + * + * Commit thread IRQ handler HW + * ----------------------------------------------------------------- + * hw_program() + * vupdate() + * **latch** + * vupdate_handler() + * cook_timestamp() + * # event_armed == false + * # **no event sent!** + * arm_vblank_event() + * if flip_latched: + * **send_vblank_event()** + * disarm_vblank_event() + * + * The IRQ handler is expected to cook the timestamp, but we need to + * cook the timestamp before optimistic sending as well. That's because + * the following sequence is possible: + * + * Commit thread IRQ handler HW + * ----------------------------------------------------------------- + * hw_program() + * arm_vblank_event() + * vupdate() + * **latch** + * if flip_latched: + * # Need cook before send! + * **cook_timestamp()** + * send_vblank_event() + * disarm_vblank_event() + * vupdate_handler() + * cook_timestamp() + * # event_armed == false + * # no event sent! * - * On DCE, GRPH_PFLIP already fires immediately for immediate flips, so - * this is DCN-only. + * Cooking twice is OK, since DRM scanout accurate timestamps report A) + * the previous vactive start if currently in vactive, or B) the next + * vactive start if currently in vblank (see &get_vblank_counter). 'A)' + * is what we want for the optimistic send, and for 'B)', we'll cook a + * timestamp no later than the next IRQ handler run. + * + * The more correct fix is to wrap programming and arming with the + * event_lock and thus serializing it with the IRQ handler. However, + * there are various sleep-waits within + * update_planes_and_stream_adapter() that makes spin locking illegal. + * And on full updates, it can take 1-2 frame-times to return (see + * commit_planes_for_stream). + * + * On DCE, GRPH_PFLIP IRQ is used and takes care of this. */ - if (immediate_flip && amdgpu_ip_version(dm->adev, DCE_HWIP, 0) != 0) { + if (amdgpu_ip_version(dm->adev, DCE_HWIP, 0) != 0) { spin_lock_irqsave(&pcrtc->dev->event_lock, flags); - if (acrtc_attach->pflip_status == AMDGPU_FLIP_SUBMITTED && + + if (updated_planes_and_streams) { + flip_latched_during_prog = + !dc_get_flip_pending_on_otg(dm->dc, acrtc_attach->otg_inst); + } + + dm_arm_vblank_event(acrtc_attach, acrtc_state, + pflip_present, cursor_update); + + /* + * Deliver the event immediately on immediate flip, or on a + * update that has already latched. + */ + if ((immediate_flip || flip_latched_during_prog) && + acrtc_attach->pflip_status == AMDGPU_FLIP_SUBMITTED && acrtc_attach->event) { drm_crtc_accurate_vblank_count(&acrtc_attach->base); drm_crtc_send_vblank_event(&acrtc_attach->base, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 0347174173f3..927837249479 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -5427,6 +5427,51 @@ void dc_interrupt_ack(struct dc *dc, enum dc_irq_source src) dal_irq_service_ack(dc->res_pool->irqs, src); } +/* + * dc_get_flip_pending_on_otg() - Check if a GRPH_FLIP is still pending on OTG + * + * @dc: display core context @otg_inst: OTG instance to query + * + * Reads the HUBP flip-pending status for the pipe(s) bound to @otg_inst, + * returning true if any of them has not yet latched its programmed surface + * address. + * + * Unlike dc_plane_get_status(), this does not take or mutate a dc_plane_state, + * so it is safe to call from interrupt context without racing a concurrent + * commit that may be updating plane state. + * + * Return: true if a flip is still pending on the OTG, false otherwise. + */ +bool dc_get_flip_pending_on_otg(struct dc *dc, int otg_inst) +{ + bool flip_pending = false; + int i; + + if (!dc || !dc->current_state) + return false; + + dc_exit_ips_for_hw_access(dc); + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; + struct hubp *hubp = pipe_ctx->plane_res.hubp; + + if (!pipe_ctx->plane_state || !pipe_ctx->stream_res.tg) + continue; + + if (pipe_ctx->stream_res.tg->inst != otg_inst) + continue; + + if (hubp && hubp->funcs->hubp_is_flip_pending && + hubp->funcs->hubp_is_flip_pending(hubp)) { + flip_pending = true; + break; + } + } + + return flip_pending; +} + void dc_power_down_on_boot(struct dc *dc) { if (dc->ctx->dce_environment != DCE_ENV_VIRTUAL_HW && diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 98f0b6b3c213..390f948dad39 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -2611,6 +2611,7 @@ enum dc_irq_source dc_interrupt_to_irq_source( uint32_t ext_id); bool dc_interrupt_set(struct dc *dc, enum dc_irq_source src, bool enable); void dc_interrupt_ack(struct dc *dc, enum dc_irq_source src); +bool dc_get_flip_pending_on_otg(struct dc *dc, int otg_inst); enum dc_irq_source dc_get_hpd_irq_source_at_index( struct dc *dc, uint32_t link_index); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c index b4f5b4a6331a..20c52b0038d1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c @@ -45,9 +45,7 @@ clk_src->base.ctx #define DC_LOGGER \ - calc_pll_cs->ctx->logger -#define DC_LOGGER_INIT() \ - struct calc_pll_clock_source *calc_pll_cs = &clk_src->calc_pll + CTX->logger #undef FN #define FN(reg_name, field_name) \ @@ -291,6 +289,7 @@ static bool calc_pll_dividers_in_range( } static uint32_t calculate_pixel_clock_pll_dividers( + struct dce110_clk_src *clk_src, struct calc_pll_clock_source *calc_pll_cs, struct pll_settings *pll_settings) { @@ -479,7 +478,7 @@ static uint32_t dce110_get_pix_clk_dividers_helper ( { uint32_t field = 0; uint32_t pll_calc_error = MAX_PLL_CALC_ERROR; - DC_LOGGER_INIT(); + /* Check if reference clock is external (not pcie/xtalin) * HW Dce80 spec: * 00 - PCIE_REFCLK, 01 - XTALIN, 02 - GENERICA, 03 - GENERICB @@ -522,12 +521,14 @@ static uint32_t dce110_get_pix_clk_dividers_helper ( /*Calculate Dividers by HDMI object, no SS case or SS case */ pll_calc_error = calculate_pixel_clock_pll_dividers( + clk_src, &clk_src->calc_pll_hdmi, pll_settings); else /*Calculate Dividers by default object, no SS case or SS case */ pll_calc_error = calculate_pixel_clock_pll_dividers( + clk_src, &clk_src->calc_pll, pll_settings); @@ -572,7 +573,6 @@ static uint32_t dce110_get_pix_clk_dividers( { struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(cs); uint32_t pll_calc_error = MAX_PLL_CALC_ERROR; - DC_LOGGER_INIT(); if (pix_clk_params == NULL || pll_settings == NULL || pix_clk_params->requested_pix_clk_100hz == 0) { @@ -604,7 +604,6 @@ static uint32_t dce112_get_pix_clk_dividers( struct pll_settings *pll_settings) { struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(cs); - DC_LOGGER_INIT(); if (pix_clk_params == NULL || pll_settings == NULL || pix_clk_params->requested_pix_clk_100hz == 0) { @@ -1370,8 +1369,6 @@ static uint32_t dcn3_get_pix_clk_dividers( unsigned long long actual_pix_clk_100Hz = pix_clk_params ? pix_clk_params->requested_pix_clk_100hz : 0; struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(cs); - DC_LOGGER_INIT(); - if (pix_clk_params == NULL || pll_settings == NULL || pix_clk_params->requested_pix_clk_100hz == 0) { DC_LOG_ERROR( @@ -1441,7 +1438,6 @@ static const struct clock_source_funcs dce110_clk_src_funcs = { .get_pixel_clk_frequency_100hz = get_pixel_clk_frequency_100hz }; - static void get_ss_info_from_atombios( struct dce110_clk_src *clk_src, enum as_signal_type as_signal, @@ -1454,7 +1450,7 @@ static void get_ss_info_from_atombios( struct spread_spectrum_info *ss_info_cur; struct spread_spectrum_data *ss_data_cur; uint32_t i; - DC_LOGGER_INIT(); + if (ss_entries_num == NULL) { DC_LOG_SYNC( "Invalid entry !!!\n"); @@ -1589,6 +1585,7 @@ static void ss_info_from_atombios_create( } static bool calc_pll_max_vco_construct( + struct dce110_clk_src *clk_src, struct calc_pll_clock_source *calc_pll_cs, struct calc_pll_clock_source_init_data *init_data) { @@ -1740,6 +1737,7 @@ bool dce110_clk_src_construct( ss_info_from_atombios_create(clk_src); if (!calc_pll_max_vco_construct( + clk_src, &clk_src->calc_pll, &calc_pll_cs_init_data)) { ASSERT_CRITICAL(false); @@ -1754,7 +1752,7 @@ bool dce110_clk_src_construct( if (!calc_pll_max_vco_construct( - &clk_src->calc_pll_hdmi, &calc_pll_cs_init_data_hdmi)) { + clk_src, &clk_src->calc_pll_hdmi, &calc_pll_cs_init_data_hdmi)) { ASSERT_CRITICAL(false); goto unexpected_failure; } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c index 731645a2ab9a..20b408b68824 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c @@ -837,13 +837,19 @@ void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable) pipe_ctx->stream_res.stream_enc, enable); - /* Wait for two frame to make sure AV mute is sent out */ + /* Wait for three frames to make sure AV mute is sent out. + * Some HDMI sinks need additional GCP packets to properly + * process the mute state, especially after link re-establishment + * with HDMI 2.0 scrambling enabled. + */ if (enable && pipe_ctx->stream_res.tg->funcs->is_tg_enabled(pipe_ctx->stream_res.tg)) { + int i; + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); - pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); - pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); - pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); - pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + for (i = 0; i < 3; i++) { + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + } } } } diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 8253d2977408..caf2cabeca6d 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -1442,17 +1442,23 @@ int amdgpu_dpm_set_power_profile_mode(struct amdgpu_device *adev, return ret; } -int amdgpu_dpm_get_gpu_metrics(struct amdgpu_device *adev, void **table) +ssize_t amdgpu_dpm_get_gpu_metrics(struct amdgpu_device *adev, void *buf, + size_t size) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - int ret = 0; + void *table; + ssize_t ret; if (!pp_funcs->get_gpu_metrics) return 0; mutex_lock(&adev->pm.mutex); ret = pp_funcs->get_gpu_metrics(adev->powerplay.pp_handle, - table); + &table); + if (ret > 0) { + ret = min_t(ssize_t, ret, size); + memcpy(buf, table, ret); + } mutex_unlock(&adev->pm.mutex); return ret; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 7c9e2003e2a0..94c534c1d0be 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -1754,7 +1754,6 @@ static ssize_t amdgpu_get_gpu_metrics(struct device *dev, { struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - void *gpu_metrics; ssize_t size = 0; int ret; @@ -1762,15 +1761,10 @@ static ssize_t amdgpu_get_gpu_metrics(struct device *dev, if (ret) return ret; - size = amdgpu_dpm_get_gpu_metrics(adev, &gpu_metrics); + size = amdgpu_dpm_get_gpu_metrics(adev, buf, PAGE_SIZE - 1); if (size <= 0) goto out; - if (size >= PAGE_SIZE) - size = PAGE_SIZE - 1; - - memcpy(buf, gpu_metrics, size); - out: amdgpu_pm_put_access(adev); diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index af48aead12f7..b0bbb23929bf 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -517,7 +517,8 @@ int amdgpu_dpm_get_power_profile_mode(struct amdgpu_device *adev, char *buf); int amdgpu_dpm_set_power_profile_mode(struct amdgpu_device *adev, long *input, uint32_t size); -int amdgpu_dpm_get_gpu_metrics(struct amdgpu_device *adev, void **table); +ssize_t amdgpu_dpm_get_gpu_metrics(struct amdgpu_device *adev, void *buf, + size_t size); ssize_t amdgpu_dpm_get_xcp_metrics(struct amdgpu_device *adev, int xcp_id, void *table); ssize_t amdgpu_dpm_get_temp_metrics(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c index cb53cc91bafb..4a8c432e311e 100644 --- a/drivers/gpu/drm/armada/armada_fbdev.c +++ b/drivers/gpu/drm/armada/armada_fbdev.c @@ -45,10 +45,10 @@ int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh, struct drm_fb_helper_surface_size *sizes) { struct drm_device *dev = fbh->dev; + struct fb_info *info = fbh->info; struct drm_mode_fb_cmd2 mode; struct armada_framebuffer *dfb; struct armada_gem_object *obj; - struct fb_info *info; int size, ret; void *ptr; @@ -92,12 +92,6 @@ int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh, if (IS_ERR(dfb)) return PTR_ERR(dfb); - info = drm_fb_helper_alloc_info(fbh); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_fballoc; - } - info->fbops = &armada_fb_ops; info->fix.smem_start = obj->phys_addr; info->fix.smem_len = obj->obj.size; @@ -113,8 +107,4 @@ int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh, (unsigned long long)obj->phys_addr); return 0; - - err_fballoc: - dfb->fb.funcs->destroy(&dfb->fb); - return ret; } diff --git a/drivers/gpu/drm/bridge/display-connector.c b/drivers/gpu/drm/bridge/display-connector.c index e9f16dbc9535..9a64fefbc903 100644 --- a/drivers/gpu/drm/bridge/display-connector.c +++ b/drivers/gpu/drm/bridge/display-connector.c @@ -40,6 +40,13 @@ static int display_connector_attach(struct drm_bridge *bridge, return flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR ? 0 : -EINVAL; } +static void display_connector_destroy(struct drm_bridge *bridge) +{ + struct display_connector *conn = to_display_connector(bridge); + + i2c_put_adapter(conn->bridge.ddc); +} + static enum drm_connector_status display_connector_detect(struct drm_bridge *bridge) { struct display_connector *conn = to_display_connector(bridge); @@ -177,6 +184,7 @@ static u32 *display_connector_get_input_bus_fmts(struct drm_bridge *bridge, static const struct drm_bridge_funcs display_connector_bridge_funcs = { .attach = display_connector_attach, + .destroy = display_connector_destroy, .detect = display_connector_bridge_detect, .edid_read = display_connector_edid_read, .atomic_get_output_bus_fmts = display_connector_get_output_bus_fmts, @@ -403,9 +411,6 @@ static void display_connector_remove(struct platform_device *pdev) regulator_disable(conn->supply); drm_bridge_remove(&conn->bridge); - - if (!IS_ERR(conn->bridge.ddc)) - i2c_put_adapter(conn->bridge.ddc); } static const struct of_device_id display_connector_match[] = { diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index 4aaeae4fa03c..8c858ba40c6c 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -3457,6 +3457,18 @@ int drm_dp_get_pcon_max_frl_bw(const u8 dpcd[DP_RECEIVER_CAP_SIZE], int bw; u8 buf; + if (!drm_dp_is_branch(dpcd)) + return 0; + + if (dpcd[DP_DPCD_REV] < 0x11) + return 0; + + if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0) + return 0; + + if ((port_cap[0] & DP_DS_PORT_TYPE_MASK) != DP_DS_PORT_TYPE_HDMI) + return 0; + buf = port_cap[2]; bw = buf & DP_PCON_MAX_FRL_BW; diff --git a/drivers/gpu/drm/drm_exec.c b/drivers/gpu/drm/drm_exec.c index 8d0601400182..746210f3f6c2 100644 --- a/drivers/gpu/drm/drm_exec.c +++ b/drivers/gpu/drm/drm_exec.c @@ -24,7 +24,6 @@ * * struct drm_gem_object *obj; * struct drm_exec exec; - * unsigned long index; * int ret; * * drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); @@ -40,7 +39,7 @@ * goto error; * } * - * drm_exec_for_each_locked_object(&exec, index, obj) { + * drm_exec_for_each_locked_object(&exec, obj) { * dma_resv_add_fence(obj->resv, fence, DMA_RESV_USAGE_READ); * ... * } @@ -56,9 +55,8 @@ static void drm_exec_unlock_all(struct drm_exec *exec) { struct drm_gem_object *obj; - unsigned long index; - drm_exec_for_each_locked_object_reverse(exec, index, obj) { + drm_exec_for_each_locked_object_reverse(exec, obj) { dma_resv_unlock(obj->resv); drm_gem_object_put(obj); } diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 0b3ee008523d..df73433b4652 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -489,20 +489,7 @@ int drm_fb_helper_init(struct drm_device *dev, } EXPORT_SYMBOL(drm_fb_helper_init); -/** - * drm_fb_helper_alloc_info - allocate fb_info and some of its members - * @fb_helper: driver-allocated fbdev helper - * - * A helper to alloc fb_info and the member cmap. Called by the driver - * within the struct &drm_driver.fbdev_probe callback function. Drivers do - * not need to release the allocated fb_info structure themselves, this is - * automatically done when calling drm_fb_helper_fini(). - * - * RETURNS: - * fb_info pointer if things went okay, pointer containing error code - * otherwise - */ -struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) +static struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) { struct device *dev = fb_helper->dev->dev; struct fb_info *info; @@ -529,17 +516,8 @@ struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) framebuffer_release(info); return ERR_PTR(ret); } -EXPORT_SYMBOL(drm_fb_helper_alloc_info); -/** - * drm_fb_helper_release_info - release fb_info and its members - * @fb_helper: driver-allocated fbdev helper - * - * A helper to release fb_info and the member cmap. Drivers do not - * need to release the allocated fb_info structure themselves, this is - * automatically done when calling drm_fb_helper_fini(). - */ -void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper) +static void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper) { struct fb_info *info = fb_helper->info; @@ -552,7 +530,6 @@ void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper) fb_dealloc_cmap(&info->cmap); framebuffer_release(info); } -EXPORT_SYMBOL(drm_fb_helper_release_info); /** * drm_fb_helper_unregister_info - unregister fb_info framebuffer device @@ -1813,6 +1790,13 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper) height = dev->mode_config.max_height; drm_client_modeset_probe(&fb_helper->client, width, height); + + info = drm_fb_helper_alloc_info(fb_helper); + if (IS_ERR(info)) { + mutex_unlock(&fb_helper->lock); + return PTR_ERR(info); + } + ret = drm_fb_helper_single_fb_probe(fb_helper); if (ret < 0) { if (ret == -EAGAIN) { @@ -1821,13 +1805,12 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper) } mutex_unlock(&fb_helper->lock); - return ret; + goto err_drm_fb_helper_release_info; } drm_setup_crtcs_fb(fb_helper); fb_helper->deferred_setup = false; - info = fb_helper->info; info->var.pixclock = 0; /* Need to drop locks to avoid recursive deadlock in @@ -1850,6 +1833,10 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper) mutex_unlock(&kernel_fb_helper_lock); return 0; + +err_drm_fb_helper_release_info: + drm_fb_helper_release_info(fb_helper); + return ret; } /** diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c index 8bd626ef16c7..7b77c801a63a 100644 --- a/drivers/gpu/drm/drm_fbdev_dma.c +++ b/drivers/gpu/drm/drm_fbdev_dma.c @@ -272,9 +272,9 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper, { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; + struct fb_info *info = fb_helper->info; struct drm_client_buffer *buffer; struct drm_framebuffer *fb; - struct fb_info *info; u32 format; struct iosys_map map; int ret; @@ -304,12 +304,6 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper, fb_helper->buffer = buffer; fb_helper->fb = fb; - info = drm_fb_helper_alloc_info(fb_helper); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_drm_client_buffer_vunmap; - } - drm_fb_helper_fill_info(info, fb_helper, sizes); if (fb->funcs->dirty) @@ -317,12 +311,10 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper, else ret = drm_fbdev_dma_driver_fbdev_probe_tail(fb_helper, sizes); if (ret) - goto err_drm_fb_helper_release_info; + goto err_drm_client_buffer_vunmap; return 0; -err_drm_fb_helper_release_info: - drm_fb_helper_release_info(fb_helper); err_drm_client_buffer_vunmap: fb_helper->fb = NULL; fb_helper->buffer = NULL; diff --git a/drivers/gpu/drm/drm_fbdev_shmem.c b/drivers/gpu/drm/drm_fbdev_shmem.c index 1e827bf8b815..77f350700818 100644 --- a/drivers/gpu/drm/drm_fbdev_shmem.c +++ b/drivers/gpu/drm/drm_fbdev_shmem.c @@ -136,10 +136,10 @@ int drm_fbdev_shmem_driver_fbdev_probe(struct drm_fb_helper *fb_helper, { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; + struct fb_info *info = fb_helper->info; struct drm_client_buffer *buffer; struct drm_gem_shmem_object *shmem; struct drm_framebuffer *fb; - struct fb_info *info; u32 format; struct iosys_map map; int ret; @@ -169,12 +169,6 @@ int drm_fbdev_shmem_driver_fbdev_probe(struct drm_fb_helper *fb_helper, fb_helper->buffer = buffer; fb_helper->fb = fb; - info = drm_fb_helper_alloc_info(fb_helper); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_drm_client_buffer_vunmap; - } - drm_fb_helper_fill_info(info, fb_helper, sizes); info->fbops = &drm_fbdev_shmem_fb_ops; @@ -195,12 +189,10 @@ int drm_fbdev_shmem_driver_fbdev_probe(struct drm_fb_helper *fb_helper, info->fbdefio = &fb_helper->fbdefio; ret = fb_deferred_io_init(info); if (ret) - goto err_drm_fb_helper_release_info; + goto err_drm_client_buffer_vunmap; return 0; -err_drm_fb_helper_release_info: - drm_fb_helper_release_info(fb_helper); err_drm_client_buffer_vunmap: fb_helper->fb = NULL; fb_helper->buffer = NULL; diff --git a/drivers/gpu/drm/drm_fbdev_ttm.c b/drivers/gpu/drm/drm_fbdev_ttm.c index 85feb55bba11..1ba258f3c854 100644 --- a/drivers/gpu/drm/drm_fbdev_ttm.c +++ b/drivers/gpu/drm/drm_fbdev_ttm.c @@ -176,8 +176,8 @@ int drm_fbdev_ttm_driver_fbdev_probe(struct drm_fb_helper *fb_helper, { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; + struct fb_info *info = fb_helper->info; struct drm_client_buffer *buffer; - struct fb_info *info; size_t screen_size; void *screen_buffer; u32 format; @@ -205,12 +205,6 @@ int drm_fbdev_ttm_driver_fbdev_probe(struct drm_fb_helper *fb_helper, goto err_drm_client_framebuffer_delete; } - info = drm_fb_helper_alloc_info(fb_helper); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_vfree; - } - drm_fb_helper_fill_info(info, fb_helper, sizes); info->fbops = &drm_fbdev_ttm_fb_ops; @@ -227,12 +221,10 @@ int drm_fbdev_ttm_driver_fbdev_probe(struct drm_fb_helper *fb_helper, info->fbdefio = &fb_helper->fbdefio; ret = fb_deferred_io_init(info); if (ret) - goto err_drm_fb_helper_release_info; + goto err_vfree; return 0; -err_drm_fb_helper_release_info: - drm_fb_helper_release_info(fb_helper); err_vfree: vfree(screen_buffer); err_drm_client_framebuffer_delete: diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index 781cd4e5b704..e5c7befe3108 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -1390,6 +1390,14 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm, err = -EAGAIN; goto err_unmap; } + + /* + * Set the dpagemap as soon as the first + * device page is mapped so the err_unmap path + * can device_unmap() the device mappings that + * have already been created. + */ + svm_pages->dpagemap = dpagemap; } svm_pages->dma_addr[j] = dpagemap->ops->device_map(dpagemap, @@ -1432,10 +1440,8 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm, flags.has_dma_mapping = true; } - if (pagemap) { + if (pagemap) flags.has_devmem_pages = true; - svm_pages->dpagemap = dpagemap; - } /* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */ WRITE_ONCE(svm_pages->flags.__flags, flags.__flags); diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c index 5c8bf010cd96..61c3df0711a3 100644 --- a/drivers/gpu/drm/drm_gpuvm.c +++ b/drivers/gpu/drm/drm_gpuvm.c @@ -1521,9 +1521,8 @@ drm_gpuvm_resv_add_fence(struct drm_gpuvm *gpuvm, enum dma_resv_usage extobj_usage) { struct drm_gem_object *obj; - unsigned long index; - drm_exec_for_each_locked_object(exec, index, obj) { + drm_exec_for_each_locked_object(exec, obj) { dma_resv_assert_held(obj->resv); dma_resv_add_fence(obj->resv, fence, drm_gpuvm_is_extobj(gpuvm, obj) ? diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 93de25b77e68..b0bd0697910e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -59,18 +59,11 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper, struct drm_fb_helper_surface_size *sizes, struct exynos_drm_gem *exynos_gem) { - struct fb_info *fbi; + struct fb_info *fbi = helper->info; struct drm_framebuffer *fb = helper->fb; unsigned int size = fb->width * fb->height * fb->format->cpp[0]; unsigned long offset; - fbi = drm_fb_helper_alloc_info(helper); - if (IS_ERR(fbi)) { - DRM_DEV_ERROR(to_dma_dev(helper->dev), - "failed to allocate fb info.\n"); - return PTR_ERR(fbi); - } - fbi->fbops = &exynos_drm_fb_ops; drm_fb_helper_fill_info(fbi, helper, sizes); diff --git a/drivers/gpu/drm/gma500/fbdev.c b/drivers/gpu/drm/gma500/fbdev.c index a6af21514cff..dacc118b1242 100644 --- a/drivers/gpu/drm/gma500/fbdev.c +++ b/drivers/gpu/drm/gma500/fbdev.c @@ -111,7 +111,7 @@ int psb_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, struct drm_device *dev = fb_helper->dev; struct drm_psb_private *dev_priv = to_drm_psb_private(dev); struct pci_dev *pdev = to_pci_dev(dev->dev); - struct fb_info *info; + struct fb_info *info = fb_helper->info; struct drm_framebuffer *fb; struct drm_mode_fb_cmd2 mode_cmd = { }; int size; @@ -170,12 +170,6 @@ int psb_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, fb_helper->funcs = &psb_fbdev_fb_helper_funcs; fb_helper->fb = fb; - info = drm_fb_helper_alloc_info(fb_helper); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_drm_framebuffer_unregister_private; - } - info->fbops = &psb_fbdev_fb_ops; /* Accessed stolen memory directly */ @@ -199,10 +193,6 @@ int psb_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, return 0; -err_drm_framebuffer_unregister_private: - drm_framebuffer_unregister_private(fb); - drm_framebuffer_cleanup(fb); - kfree(fb); err_drm_gem_object_put: drm_gem_object_put(obj); return ret; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index c09aa759f4d4..3de3e9167d0d 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -3502,6 +3502,8 @@ static void intel_ddi_enable_hdmi(struct intel_atomic_state *state, } intel_ddi_buf_enable(encoder, buf_ctl); + + intel_hdmi_poll_for_scrambling_enable(crtc_state, connector); } static void intel_ddi_enable(struct intel_atomic_state *state, diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 2a0750acf205..84fca860c93e 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -3859,7 +3859,14 @@ static int intel_dp_hdmi_sink_max_frl(struct intel_dp *intel_dp) rate_per_lane = info->hdmi.max_frl_rate_per_lane; max_frl_rate = max_lanes * rate_per_lane; - if (info->hdmi.dsc_cap.v_1p2) { + /* + * The sink's DSC max FRL rate only applies to compressed video + * transport, which requires a DSC 1.2 encoder in the PCON. Without + * one the HDMI link always carries uncompressed video, for which + * the regular max FRL rate is the limit. + */ + if (drm_dp_pcon_enc_is_dsc_1_2(intel_dp->pcon_dsc_dpcd) && + info->hdmi.dsc_cap.v_1p2) { max_dsc_lanes = info->hdmi.dsc_cap.max_lanes; dsc_rate_per_lane = info->hdmi.dsc_cap.max_frl_rate_per_lane; if (max_dsc_lanes && dsc_rate_per_lane) diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index 7daf72b69bae..a42b0943ed95 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -242,8 +242,8 @@ int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, struct intel_display *display = to_intel_display(helper->dev); struct intel_fbdev *ifbdev = to_intel_fbdev(helper); struct intel_framebuffer *fb = ifbdev->fb; + struct fb_info *info = helper->info; struct ref_tracker *wakeref; - struct fb_info *info; struct i915_vma *vma; unsigned long flags = 0; bool prealloc = false; @@ -296,13 +296,6 @@ int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, goto out_unlock; } - info = drm_fb_helper_alloc_info(helper); - if (IS_ERR(info)) { - drm_err(display->drm, "Failed to allocate fb_info (%pe)\n", info); - ret = PTR_ERR(info); - goto out_unpin; - } - helper->funcs = &intel_fb_helper_funcs; helper->fb = &fb->base; diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index 4ab7e2e3bfd4..e77c6422b001 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -2680,6 +2680,32 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *_ drm_connector_attach_max_bpc_property(&connector->base, 8, 12); } +/* + * HDMI 2.0 spec, section 6.1.3.1 (Scrambling Control): after + * enabling Scrambling_Enable and starting scrambled video + * transmission, poll Scrambling_Status for up to 200 ms. + */ +void +intel_hdmi_poll_for_scrambling_enable(const struct intel_crtc_state *crtc_state, + struct drm_connector *_connector) +{ + struct intel_connector *connector = to_intel_connector(_connector); + struct intel_display *display = to_intel_display(crtc_state); + bool scrambling_enabled = false; + int ret; + + if (!crtc_state->hdmi_scrambling) + return; + + /* Poll for a max of 200 msec as per HDMI spec */ + ret = poll_timeout_us(scrambling_enabled = drm_scdc_get_scrambling_status(&connector->base), + scrambling_enabled, 1000, 200 * 1000, false); + if (ret) + drm_dbg_kms(display->drm, + "[CONNECTOR:%d:%s] Timed out waiting for scrambling enable\n", + connector->base.base.id, connector->base.name); +} + /* * intel_hdmi_handle_sink_scrambling: handle sink scrambling/clock ratio setup * @encoder: intel_encoder diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h index dec2ad7dd8a2..2de905636791 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.h +++ b/drivers/gpu/drm/i915/display/intel_hdmi.h @@ -69,5 +69,7 @@ void hsw_read_infoframe(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, unsigned int type, void *frame, ssize_t len); +void intel_hdmi_poll_for_scrambling_enable(const struct intel_crtc_state *crtc_state, + struct drm_connector *_connector); #endif /* __INTEL_HDMI_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index 04a2ea086fb2..3ac6cd74ae15 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -22,6 +22,9 @@ bool intel_vrr_is_capable(struct intel_connector *connector) const struct drm_display_info *info = &connector->base.display_info; struct intel_dp *intel_dp; + if (!HAS_VRR(display)) + return false; + /* * DP Sink is capable of VRR video timings if * Ignore MSA bit is set in DPCD. @@ -46,8 +49,11 @@ bool intel_vrr_is_capable(struct intel_connector *connector) return false; } - return HAS_VRR(display) && - info->monitor_range.max_vfreq - info->monitor_range.min_vfreq > 10; + if (!info->monitor_range.min_vfreq || !info->monitor_range.max_vfreq || + info->monitor_range.min_vfreq > info->monitor_range.max_vfreq) + return false; + + return info->monitor_range.max_vfreq - info->monitor_range.min_vfreq > 10; } bool intel_vrr_is_in_range(struct intel_connector *connector, int vrefresh) diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index c4c6d0249df5..aa8e6f6ddcd3 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -153,10 +153,10 @@ static void mtk_crtc_reset(struct drm_crtc *crtc) { struct mtk_crtc_state *state; - if (crtc->state) + if (crtc->state) { __drm_atomic_helper_crtc_destroy_state(crtc->state); - - kfree(to_mtk_crtc_state(crtc->state)); + kfree(to_mtk_crtc_state(crtc->state)); + } crtc->state = NULL; state = kzalloc(sizeof(*state), GFP_KERNEL); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c index c0af3e3b51d5..6a259872b0a9 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c @@ -625,6 +625,7 @@ static void mtk_disp_ovl_adaptor_master_unbind(struct device *dev) struct mtk_disp_ovl_adaptor *priv = dev_get_drvdata(dev); priv->children_bound = false; + component_unbind_all(dev, priv->mmsys_dev); } static const struct component_master_ops mtk_disp_ovl_adaptor_master_ops = { @@ -651,12 +652,15 @@ static int mtk_disp_ovl_adaptor_probe(struct platform_device *pdev) priv->mmsys_dev = pdev->dev.platform_data; - component_master_add_with_match(dev, &mtk_disp_ovl_adaptor_master_ops, match); + ret = component_master_add_with_match(dev, &mtk_disp_ovl_adaptor_master_ops, match); + if (ret) + return dev_err_probe(dev, ret, "Failed to add component master\n"); pm_runtime_enable(dev); ret = component_add(dev, &mtk_disp_ovl_adaptor_comp_ops); if (ret != 0) { + component_master_del(dev, &mtk_disp_ovl_adaptor_master_ops); pm_runtime_disable(dev); return dev_err_probe(dev, ret, "Failed to add component\n"); } @@ -666,6 +670,7 @@ static int mtk_disp_ovl_adaptor_probe(struct platform_device *pdev) static void mtk_disp_ovl_adaptor_remove(struct platform_device *pdev) { + component_del(&pdev->dev, &mtk_disp_ovl_adaptor_comp_ops); component_master_del(&pdev->dev, &mtk_disp_ovl_adaptor_master_ops); pm_runtime_disable(&pdev->dev); } diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index b5969374d53f..d86c89d03f4b 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -93,9 +93,9 @@ int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, { struct drm_device *dev = helper->dev; struct msm_drm_private *priv = dev->dev_private; + struct fb_info *fbi = helper->info; struct drm_framebuffer *fb = NULL; struct drm_gem_object *bo; - struct fb_info *fbi = NULL; uint64_t paddr; uint32_t format; int ret, pitch; @@ -128,13 +128,6 @@ int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, goto fail; } - fbi = drm_fb_helper_alloc_info(helper); - if (IS_ERR(fbi)) { - DRM_DEV_ERROR(dev->dev, "failed to allocate fb info\n"); - ret = PTR_ERR(fbi); - goto fail; - } - DBG("fbi=%p, dev=%p", fbi, dev); helper->funcs = &msm_fbdev_helper_funcs; diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c index 948af7ec1130..2b435c05bdb1 100644 --- a/drivers/gpu/drm/omapdrm/omap_fbdev.c +++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c @@ -155,9 +155,9 @@ int omap_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, struct drm_device *dev = helper->dev; struct omap_drm_private *priv = dev->dev_private; struct omap_fbdev *fbdev = priv->fbdev; + struct fb_info *fbi = helper->info; struct drm_framebuffer *fb = NULL; union omap_gem_size gsize; - struct fb_info *fbi = NULL; struct drm_mode_fb_cmd2 mode_cmd = {0}; struct drm_gem_object *bo; dma_addr_t dma_addr; @@ -226,13 +226,6 @@ int omap_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, goto fail; } - fbi = drm_fb_helper_alloc_info(helper); - if (IS_ERR(fbi)) { - dev_err(dev->dev, "failed to allocate fb info\n"); - ret = PTR_ERR(fbi); - goto fail; - } - DBG("fbi=%p, dev=%p", fbi, dev); helper->funcs = &omap_fbdev_helper_funcs; diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c index a8a5a8e26024..470e41297764 100644 --- a/drivers/gpu/drm/panthor/panthor_fw.c +++ b/drivers/gpu/drm/panthor/panthor_fw.c @@ -495,6 +495,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev, struct panthor_fw_binary_section_entry_hdr hdr; struct panthor_fw_section *section; u32 section_size; + u32 data_size; u32 name_len; int ret; @@ -545,6 +546,13 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev, return -EINVAL; } + section_size = hdr.va.end - hdr.va.start; + data_size = hdr.data.end - hdr.data.start; + if (data_size > section_size) { + drm_err(&ptdev->base, "Firmware corrupted, section data exceeds section size\n"); + return -EINVAL; + } + name_len = iter->size - iter->offset; section = drmm_kzalloc(&ptdev->base, sizeof(*section), GFP_KERNEL); @@ -553,7 +561,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev, list_add_tail(§ion->node, &ptdev->fw->sections); section->flags = hdr.flags; - section->data.size = hdr.data.end - hdr.data.start; + section->data.size = data_size; if (section->data.size > 0) { void *data = drmm_kmalloc(&ptdev->base, section->data.size, GFP_KERNEL); @@ -576,7 +584,6 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev, section->name = name; } - section_size = hdr.va.end - hdr.va.start; if (section_size) { u32 cache_mode = hdr.flags & CSF_FW_BINARY_IFACE_ENTRY_CACHE_MODE_MASK; struct panthor_gem_object *bo; @@ -805,18 +812,24 @@ static int panthor_fw_load(struct panthor_device *ptdev) * iface_fw_to_cpu_addr() - Turn an MCU address into a CPU address * @ptdev: Device. * @mcu_va: MCU address. + * @size: Size of the object pointed to by @mcu_va. * - * Return: NULL if the address is not part of the shared section, non-NULL otherwise. + * Return: NULL if the object is not part of the shared section, non-NULL otherwise. */ -static void *iface_fw_to_cpu_addr(struct panthor_device *ptdev, u32 mcu_va) +static void *iface_fw_to_cpu_addr(struct panthor_device *ptdev, u32 mcu_va, size_t size) { u64 shared_mem_start = panthor_kernel_bo_gpuva(ptdev->fw->shared_section->mem); - u64 shared_mem_end = shared_mem_start + - panthor_kernel_bo_size(ptdev->fw->shared_section->mem); - if (mcu_va < shared_mem_start || mcu_va >= shared_mem_end) + size_t shared_mem_size = panthor_kernel_bo_size(ptdev->fw->shared_section->mem); + u64 offset; + + if (mcu_va < shared_mem_start) + return NULL; + + offset = mcu_va - shared_mem_start; + if (offset > shared_mem_size || size > shared_mem_size - offset) return NULL; - return ptdev->fw->shared_section->mem->kmap + (mcu_va - shared_mem_start); + return ptdev->fw->shared_section->mem->kmap + offset; } static int panthor_init_cs_iface(struct panthor_device *ptdev, @@ -838,8 +851,10 @@ static int panthor_init_cs_iface(struct panthor_device *ptdev, spin_lock_init(&cs_iface->lock); cs_iface->control = ptdev->fw->shared_section->mem->kmap + iface_offset; - cs_iface->input = iface_fw_to_cpu_addr(ptdev, cs_iface->control->input_va); - cs_iface->output = iface_fw_to_cpu_addr(ptdev, cs_iface->control->output_va); + cs_iface->input = iface_fw_to_cpu_addr(ptdev, cs_iface->control->input_va, + sizeof(*cs_iface->input)); + cs_iface->output = iface_fw_to_cpu_addr(ptdev, cs_iface->control->output_va, + sizeof(*cs_iface->output)); if (!cs_iface->input || !cs_iface->output) { drm_err(&ptdev->base, "Invalid stream control interface input/output VA"); @@ -889,8 +904,10 @@ static int panthor_init_csg_iface(struct panthor_device *ptdev, spin_lock_init(&csg_iface->lock); csg_iface->control = ptdev->fw->shared_section->mem->kmap + iface_offset; - csg_iface->input = iface_fw_to_cpu_addr(ptdev, csg_iface->control->input_va); - csg_iface->output = iface_fw_to_cpu_addr(ptdev, csg_iface->control->output_va); + csg_iface->input = iface_fw_to_cpu_addr(ptdev, csg_iface->control->input_va, + sizeof(*csg_iface->input)); + csg_iface->output = iface_fw_to_cpu_addr(ptdev, csg_iface->control->output_va, + sizeof(*csg_iface->output)); if (csg_iface->control->stream_num < MIN_CS_PER_CSG || csg_iface->control->stream_num > MAX_CS_PER_CSG) @@ -947,8 +964,10 @@ static int panthor_fw_init_ifaces(struct panthor_device *ptdev) return -EINVAL; } - glb_iface->input = iface_fw_to_cpu_addr(ptdev, glb_iface->control->input_va); - glb_iface->output = iface_fw_to_cpu_addr(ptdev, glb_iface->control->output_va); + glb_iface->input = iface_fw_to_cpu_addr(ptdev, glb_iface->control->input_va, + sizeof(*glb_iface->input)); + glb_iface->output = iface_fw_to_cpu_addr(ptdev, glb_iface->control->output_va, + sizeof(*glb_iface->output)); if (!glb_iface->input || !glb_iface->output) { drm_err(&ptdev->base, "Invalid global control interface input/output VA"); return -EINVAL; diff --git a/drivers/gpu/drm/radeon/radeon_fbdev.c b/drivers/gpu/drm/radeon/radeon_fbdev.c index dc81b0c2dbff..d5c621d48e20 100644 --- a/drivers/gpu/drm/radeon/radeon_fbdev.c +++ b/drivers/gpu/drm/radeon/radeon_fbdev.c @@ -206,7 +206,7 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, struct radeon_device *rdev = fb_helper->dev->dev_private; const struct drm_format_info *format_info; struct drm_mode_fb_cmd2 mode_cmd = { }; - struct fb_info *info; + struct fb_info *info = fb_helper->info; struct drm_gem_object *gobj; struct radeon_bo *rbo; struct drm_framebuffer *fb; @@ -247,13 +247,6 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, fb_helper->funcs = &radeon_fbdev_fb_helper_funcs; fb_helper->fb = fb; - /* okay we have an object now allocate the framebuffer */ - info = drm_fb_helper_alloc_info(fb_helper); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_drm_framebuffer_unregister_private; - } - info->fbops = &radeon_fbdev_fb_ops; /* radeon resume is fragile and needs a vt switch to help it along */ @@ -279,10 +272,6 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, return 0; -err_drm_framebuffer_unregister_private: - fb_helper->fb = NULL; - drm_framebuffer_unregister_private(fb); - drm_framebuffer_cleanup(fb); err_kfree: kfree(fb); err_radeon_fbdev_destroy_pinned_object: diff --git a/drivers/gpu/drm/tegra/fbdev.c b/drivers/gpu/drm/tegra/fbdev.c index 1b70f5e164af..50d3186241c6 100644 --- a/drivers/gpu/drm/tegra/fbdev.c +++ b/drivers/gpu/drm/tegra/fbdev.c @@ -75,10 +75,9 @@ int tegra_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, struct tegra_drm *tegra = helper->dev->dev_private; struct drm_device *drm = helper->dev; struct drm_mode_fb_cmd2 cmd = { 0 }; + struct fb_info *info = helper->info; unsigned int bytes_per_pixel; struct drm_framebuffer *fb; - unsigned long offset; - struct fb_info *info; struct tegra_bo *bo; size_t size; int err; @@ -99,13 +98,6 @@ int tegra_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, if (IS_ERR(bo)) return PTR_ERR(bo); - info = drm_fb_helper_alloc_info(helper); - if (IS_ERR(info)) { - dev_err(drm->dev, "failed to allocate framebuffer info\n"); - drm_gem_object_put(&bo->gem); - return PTR_ERR(info); - } - fb = tegra_fb_alloc(drm, drm_get_format_info(drm, cmd.pixel_format, cmd.modifier[0]), &cmd, &bo, 1); @@ -119,15 +111,11 @@ int tegra_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, helper->funcs = &tegra_fbdev_helper_funcs; helper->fb = fb; - helper->info = info; info->fbops = &tegra_fb_ops; drm_fb_helper_fill_info(info, helper, sizes); - offset = info->var.xoffset * bytes_per_pixel + - info->var.yoffset * fb->pitches[0]; - if (bo->pages) { bo->vaddr = vmap(bo->pages, bo->num_pages, VM_MAP, pgprot_writecombine(PAGE_KERNEL)); @@ -139,9 +127,9 @@ int tegra_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, } info->flags |= FBINFO_VIRTFB; - info->screen_buffer = bo->vaddr + offset; + info->screen_buffer = bo->vaddr; info->screen_size = size; - info->fix.smem_start = (unsigned long)(bo->iova + offset); + info->fix.smem_start = (unsigned long)(bo->iova); info->fix.smem_len = size; return 0; diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c index 69b399f3b802..4fdad88e53e1 100644 --- a/drivers/gpu/drm/vc4/vc4_irq.c +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -104,7 +104,7 @@ vc4_overflow_mem_work(struct work_struct *work) vc4->bin_alloc_overflow = BIT(bin_bo_slot); V3D_WRITE(V3D_BPOA, bo->base.dma_addr + bin_bo_slot * vc4->bin_alloc_size); - V3D_WRITE(V3D_BPOS, bo->base.base.size); + V3D_WRITE(V3D_BPOS, vc4->bin_alloc_size); V3D_WRITE(V3D_INTCTL, V3D_INT_OUTOMEM); V3D_WRITE(V3D_INTENA, V3D_INT_OUTOMEM); spin_unlock_irqrestore(&vc4->job_lock, irqflags); diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c index 1e7bdda55698..205d360a007a 100644 --- a/drivers/gpu/drm/vc4/vc4_validate.c +++ b/drivers/gpu/drm/vc4/vc4_validate.c @@ -384,6 +384,23 @@ validate_tile_binning_config(VALIDATE_ARGS) return -EINVAL; } + /* The tile state data array is 48 bytes per tile, and we put it at + * the start of a BO containing both it and the tile alloc. + */ + tile_state_size = 48 * tile_count; + + /* Since the tile alloc array will follow us, align. */ + tile_state_size = roundup(tile_state_size, 4096); + + /* Reject configurations whose tile state would leave no room for + * the tile alloc pool that follows it in the slot. + */ + if (tile_state_size >= vc4->bin_alloc_size) { + DRM_DEBUG("Tile binning config of %dx%d too large\n", + exec->bin_tiles_x, exec->bin_tiles_y); + return -EINVAL; + } + bin_slot = vc4_v3d_get_bin_slot(vc4); if (bin_slot < 0) { if (bin_slot != -EINTR && bin_slot != -ERESTARTSYS) { @@ -399,13 +416,13 @@ validate_tile_binning_config(VALIDATE_ARGS) exec->bin_slots |= BIT(bin_slot); bin_addr = vc4->bin_bo->base.dma_addr + bin_slot * vc4->bin_alloc_size; - /* The tile state data array is 48 bytes per tile, and we put it at - * the start of a BO containing both it and the tile alloc. - */ - tile_state_size = 48 * tile_count; + exec->tile_alloc_offset = bin_addr + tile_state_size; - /* Since the tile alloc array will follow us, align. */ - exec->tile_alloc_offset = bin_addr + roundup(tile_state_size, 4096); + /* The TSDA area must be zeroed out before use, otherwise the PTB might + * consume a stale tile state. + */ + memset(vc4->bin_bo->base.vaddr + bin_slot * vc4->bin_alloc_size, 0, + tile_state_size); *(uint8_t *)(validated + 14) = ((flags & ~(VC4_BIN_CONFIG_ALLOC_INIT_BLOCK_SIZE_MASK | diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.c b/drivers/gpu/drm/vmwgfx/ttm_object.c index 36d46b79562a..95f7c5820aab 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_object.c +++ b/drivers/gpu/drm/vmwgfx/ttm_object.c @@ -547,14 +547,17 @@ int ttm_prime_fd_to_handle(struct ttm_object_file *tfile, if (IS_ERR(dma_buf)) return PTR_ERR(dma_buf); - if (dma_buf->ops != &tdev->ops) - return -ENOSYS; + if (dma_buf->ops != &tdev->ops) { + ret = -ENOSYS; + goto out; + } prime = (struct ttm_prime_object *) dma_buf->priv; base = &prime->base; *handle = base->handle; ret = ttm_ref_object_add(tfile, base, NULL, false); +out: dma_buf_put(dma_buf); return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c index fa5841fda659..d78874e7f5c7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c @@ -30,6 +30,7 @@ #include "vmwgfx_bo.h" #include <linux/highmem.h> +#include <linux/overflow.h> /* * Template that implements find_first_diff() for a generic @@ -463,19 +464,42 @@ static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset, container_of(dst->tbo.bdev, struct vmw_private, bdev); size_t dst_size = dst->tbo.resource->size; size_t src_size = src->tbo.resource->size; + size_t dst_end, src_end; struct iosys_map dst_map = {0}; struct iosys_map src_map = {0}; + bool dst_mapped = false; + bool src_mapped = false; int ret, i; int x_in_bytes; u8 *vsrc; u8 *vdst; + if (!height || !width_in_bytes) + return 0; + + if (!dst_stride || !src_stride) + return -EINVAL; + if (dst_stride < width_in_bytes || src_stride < width_in_bytes) + return -EINVAL; + if (check_mul_overflow((size_t)dst_stride, (size_t)height - 1, &dst_end) || + check_add_overflow(dst_end, (size_t)width_in_bytes, &dst_end) || + check_add_overflow((size_t)dst_offset, dst_end, &dst_end) || + dst_end > dst_size || + check_mul_overflow((size_t)src_stride, (size_t)height - 1, &src_end) || + check_add_overflow(src_end, (size_t)width_in_bytes, &src_end) || + check_add_overflow((size_t)src_offset, src_end, &src_end) || + src_end > src_size) { + drm_dbg_driver(&vmw->drm, "Out-of-bounds external BO copy\n"); + return -EINVAL; + } + vsrc = map_external(src, &src_map); if (!vsrc) { drm_dbg_driver(&vmw->drm, "Wasn't able to map src\n"); ret = -ENOMEM; goto out; } + src_mapped = true; vdst = map_external(dst, &dst_map); if (!vdst) { @@ -483,16 +507,13 @@ static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset, ret = -ENOMEM; goto out; } + dst_mapped = true; vsrc += src_offset; vdst += dst_offset; - if (src_stride == dst_stride) { - dst_size -= dst_offset; - src_size -= src_offset; - memcpy(vdst, vsrc, - min(dst_stride * height, min(dst_size, src_size))); + if (src_stride == dst_stride && width_in_bytes == dst_stride) { + memcpy(vdst, vsrc, dst_stride * (size_t)height); } else { - WARN_ON(dst_stride < width_in_bytes); for (i = 0; i < height; ++i) { memcpy(vdst, vsrc, width_in_bytes); vsrc += src_stride; @@ -508,8 +529,10 @@ static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset, ret = 0; out: - unmap_external(src, &src_map); - unmap_external(dst, &dst_map); + if (src_mapped) + unmap_external(src, &src_map); + if (dst_mapped) + unmap_external(dst, &dst_map); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c index c46f17ba7236..c53bb9376b36 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c @@ -432,6 +432,7 @@ vmw_cursor_mob_map(struct vmw_plane_state *vps) u32 size = vmw_cursor_mob_size(vps->cursor.update_type, vps->base.crtc_w, vps->base.crtc_h); struct vmw_bo *vbo = vps->cursor.mob; + void *map; if (!vbo) return -EINVAL; @@ -446,11 +447,15 @@ vmw_cursor_mob_map(struct vmw_plane_state *vps) if (unlikely(ret != 0)) return -ENOMEM; - vmw_bo_map_and_cache(vbo); + map = vmw_bo_map_and_cache(vbo); + if (!map) { + vmw_bo_unmap(vbo); + ret = -ENOMEM; + } ttm_bo_unreserve(&vbo->tbo); - return 0; + return ret; } /** @@ -663,9 +668,15 @@ int vmw_cursor_plane_prepare_fb(struct drm_plane *plane, !vmw_cursor_buffer_changed(vps, old_vps)) { vps->cursor.update_type = VMW_CURSOR_UPDATE_NONE; - } else { - vmw_cursor_mob_get(vcp, vps); - vmw_cursor_mob_map(vps); + } else if (vps->cursor.update_type == + VMW_CURSOR_UPDATE_MOB && + (vmw_cursor_mob_get(vcp, vps) || + vmw_cursor_mob_map(vps))) { + /* + * Reset the cursor to avoid crashes later. + */ + vps->cursor.update_type = + VMW_CURSOR_UPDATE_NONE; } } } @@ -732,6 +743,34 @@ int vmw_cursor_plane_atomic_check(struct drm_plane *plane, "surface not suitable for cursor\n"); return -EINVAL; } + } else if (update_type == VMW_CURSOR_UPDATE_GB_ONLY || + update_type == VMW_CURSOR_UPDATE_MOB) { + u32 cursor_max_dim = + vmw_read(vmw, SVGA_REG_CURSOR_MAX_DIMENSION); + + if (new_state->crtc_w > cursor_max_dim || + new_state->crtc_h > cursor_max_dim) { + drm_warn(&vmw->drm, + "Cursor dimensions (%d, %d) exceed device max %u\n", + new_state->crtc_w, new_state->crtc_h, + cursor_max_dim); + return -EINVAL; + } + + if (update_type == VMW_CURSOR_UPDATE_MOB) { + u32 mob_max_size = + vmw_read(vmw, SVGA_REG_MOB_MAX_SIZE); + u64 mob_size = (u64)new_state->crtc_w * + new_state->crtc_h * sizeof(u32) + + sizeof(SVGAGBCursorHeader); + + if (mob_size > mob_max_size) { + drm_warn(&vmw->drm, + "Cursor MOB size %llu exceeds device max %u\n", + mob_size, mob_max_size); + return -EINVAL; + } + } } return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index e1f18020170a..a9136a6523cb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1272,9 +1272,13 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv, SVGA3dCmdHeader *header) { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXBindQuery); + struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context); struct vmw_bo *vmw_bo; int ret; + if (!ctx_node) + return -EINVAL; + cmd = container_of(header, typeof(*cmd), header); /* @@ -1288,7 +1292,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv, return ret; sw_context->dx_query_mob = vmw_bo; - sw_context->dx_query_ctx = sw_context->dx_ctx_node->ctx; + sw_context->dx_query_ctx = ctx_node->ctx; return 0; } @@ -1506,6 +1510,12 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv, bool dirty; cmd = container_of(header, typeof(*cmd), header); + + if (unlikely(header->size < sizeof(cmd->body) + sizeof(*suffix))) { + VMW_DEBUG_USER("Illegal SVGA_3D_CMD_SURFACE_DMA size.\n"); + return -EINVAL; + } + suffix = (SVGA3dCmdSurfaceDMASuffix *)((unsigned long) &cmd->body + header->size - sizeof(*suffix)); @@ -1567,11 +1577,17 @@ static int vmw_cmd_draw(struct vmw_private *dev_priv, uint32_t maxnum; int ret; + cmd = container_of(header, typeof(*cmd), header); + + if (unlikely(header->size < sizeof(cmd->body))) { + VMW_DEBUG_USER("Illegal DRAW_PRIMITIVES header size.\n"); + return -EINVAL; + } + ret = vmw_cmd_cid_check(dev_priv, sw_context, header); if (unlikely(ret != 0)) return ret; - cmd = container_of(header, typeof(*cmd), header); maxnum = (header->size - sizeof(cmd->body)) / sizeof(*decl); if (unlikely(cmd->body.numVertexDecls > maxnum)) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 00be92da5509..fe59a613e1d0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -366,13 +366,24 @@ void vmw_fence_fifo_down(struct vmw_fence_manager *fman) ret = vmw_fence_obj_wait(fence, false, false, VMW_FENCE_WAIT_TIMEOUT); + spin_lock(&fman->lock); if (unlikely(ret != 0)) { + bool cookie = dma_fence_begin_signalling(); + list_del_init(&fence->head); - dma_fence_signal(&fence->base); + if (fence->waiter_added) { + vmw_seqno_waiter_remove(fman->dev_priv); + fence->waiter_added = false; + } + dma_fence_signal_locked(&fence->base); + dma_fence_end_signalling(cookie); } BUG_ON(!list_empty(&fence->head)); + spin_unlock(&fman->lock); + dma_fence_put(&fence->base); + spin_lock(&fman->lock); } spin_unlock(&fman->lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index 45561bc1c9ef..8ab88f388652 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -311,7 +311,7 @@ void vmw_bo_dirty_transfer_to_res(struct vmw_resource *res) return; cur = max(res_start, dirty->start); - res_end = max(res_end, dirty->end); + res_end = min(res_end, dirty->end); while (cur < res_end) { unsigned long num; @@ -347,7 +347,7 @@ void vmw_bo_dirty_clear(struct vmw_bo *vbo) return; cur = max(res_start, dirty->start); - res_end = max(res_end, dirty->end); + res_end = min(res_end, dirty->end); while (cur < res_end) { unsigned long num; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 388011696941..e3a187a2c7a1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -136,7 +136,7 @@ static void vmw_resource_release(struct kref *kref) val_buf.num_shared = 0; res->func->unbind(res, false, &val_buf); } - res->guest_memory_size = false; + res->guest_memory_dirty = false; vmw_resource_mob_detach(res); if (res->dirty) res->func->dirty_free(res); @@ -773,7 +773,7 @@ void vmw_resource_unbind_list(struct vmw_bo *vbo) if (!WARN_ON_ONCE(!res->func->unbind)) (void) res->func->unbind(res, res->res_dirty, &val_buf); - res->guest_memory_size = true; + res->guest_memory_dirty = true; res->res_dirty = false; vmw_resource_mob_detach(res); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index a8c8c9375d29..bc89a137ab6d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -25,6 +25,8 @@ * **************************************************************************/ +#include <linux/overflow.h> + #include <drm/ttm/ttm_placement.h> #include "vmwgfx_binding.h" @@ -685,7 +687,7 @@ int vmw_shader_destroy_ioctl(struct drm_device *dev, void *data, static int vmw_user_shader_alloc(struct vmw_private *dev_priv, struct vmw_bo *buffer, size_t shader_size, - size_t offset, + u64 offset, SVGA3dShaderType shader_type, uint8_t num_input_sig, uint8_t num_output_sig, @@ -739,7 +741,7 @@ static int vmw_user_shader_alloc(struct vmw_private *dev_priv, static struct vmw_resource *vmw_shader_alloc(struct vmw_private *dev_priv, struct vmw_bo *buffer, size_t shader_size, - size_t offset, + u64 offset, SVGA3dShaderType shader_type) { struct vmw_shader *shader; @@ -768,7 +770,7 @@ static struct vmw_resource *vmw_shader_alloc(struct vmw_private *dev_priv, static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv, enum drm_vmw_shader_type shader_type_drm, - u32 buffer_handle, size_t size, size_t offset, + u32 buffer_handle, size_t size, u64 offset, uint8_t num_input_sig, uint8_t num_output_sig, uint32_t *shader_handle) { @@ -779,13 +781,16 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv, int ret; if (buffer_handle != SVGA3D_INVALID_ID) { + u64 end; + ret = vmw_user_bo_lookup(file_priv, buffer_handle, &buffer); if (unlikely(ret != 0)) { VMW_DEBUG_USER("Couldn't find buffer for shader creation.\n"); return ret; } - if ((u64)buffer->tbo.base.size < (u64)size + (u64)offset) { + if (check_add_overflow((u64)size, (u64)offset, &end) || + end > buffer->tbo.base.size) { VMW_DEBUG_USER("Illegal buffer- or shader size.\n"); ret = -EINVAL; goto out_bad_arg; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c index aec774fa4d7b..87de8e43667d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c @@ -214,14 +214,14 @@ vmw_vkms_init(struct vmw_private *vmw) vmw->vkms_enabled = false; ret = vmw_host_get_guestinfo(GUESTINFO_VBLANK, buffer, &buf_len); - if (ret || buf_len > max_buf_len) - return; - buffer[buf_len] = '\0'; + if (!ret && buf_len <= max_buf_len) { + buffer[buf_len] = '\0'; - ret = kstrtobool(buffer, &vmw->vkms_enabled); - if (!ret && vmw->vkms_enabled) { - ret = drm_vblank_init(&vmw->drm, VMWGFX_NUM_DISPLAY_UNITS); - vmw->vkms_enabled = (ret == 0); + ret = kstrtobool(buffer, &vmw->vkms_enabled); + if (!ret && vmw->vkms_enabled) { + ret = drm_vblank_init(&vmw->drm, VMWGFX_NUM_DISPLAY_UNITS); + vmw->vkms_enabled = (ret == 0); + } } vmw->crc_workq = alloc_ordered_workqueue("vmwgfx_crc_generator", 0); @@ -236,7 +236,8 @@ vmw_vkms_init(struct vmw_private *vmw) void vmw_vkms_cleanup(struct vmw_private *vmw) { - destroy_workqueue(vmw->crc_workq); + if (vmw->crc_workq) + destroy_workqueue(vmw->crc_workq); } bool diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index ee52b751623f..c5fc8cc71149 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -94,6 +94,7 @@ xe-y += xe_bb.o \ xe_nvm.o \ xe_oa.o \ xe_observation.o \ + xe_pagefault.o \ xe_pat.o \ xe_pci.o \ xe_pcode.o \ diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 9c1ba37983d9..fef60c8a4e5b 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -84,6 +84,28 @@ #define XE_PCI_BARRIER_MMAP_OFFSET (0x50 << XE_PTE_SHIFT) +/** + * enum xe_madv_purgeable_state - Buffer object purgeable state enumeration + * + * This enum defines the possible purgeable states for a buffer object, + * allowing userspace to provide memory usage hints to the kernel for + * better memory management under pressure. + * + * @XE_MADV_PURGEABLE_WILLNEED: The buffer object is needed and should not be purged. + * This is the default state. + * @XE_MADV_PURGEABLE_DONTNEED: The buffer object is not currently needed and can be + * purged by the kernel under memory pressure. + * @XE_MADV_PURGEABLE_PURGED: The buffer object has been purged by the kernel. + * + * Accessing a purged buffer will result in an error. Per i915 semantics, + * once purged, a BO remains permanently invalid and must be destroyed and recreated. + */ +enum xe_madv_purgeable_state { + XE_MADV_PURGEABLE_WILLNEED, + XE_MADV_PURGEABLE_DONTNEED, + XE_MADV_PURGEABLE_PURGED, +}; + struct sg_table; struct xe_bo *xe_bo_alloc(void); @@ -213,6 +235,40 @@ static inline bool xe_bo_is_protected(const struct xe_bo *bo) return bo->pxp_key_instance; } +/** + * xe_bo_is_purged() - Check if buffer object has been purged + * @bo: The buffer object to check + * + * Checks if the buffer object's backing store has been discarded by the + * kernel due to memory pressure after being marked as purgeable (DONTNEED). + * Once purged, the BO cannot be restored and any attempt to use it will fail. + * + * Context: Caller must hold the BO's dma-resv lock + * Return: true if the BO has been purged, false otherwise + */ +static inline bool xe_bo_is_purged(struct xe_bo *bo) +{ + xe_bo_assert_held(bo); + return bo->madv_purgeable == XE_MADV_PURGEABLE_PURGED; +} + +/** + * xe_bo_madv_is_dontneed() - Check if BO is marked as DONTNEED + * @bo: The buffer object to check + * + * Checks if userspace has marked this BO as DONTNEED (i.e., its contents + * are not currently needed and can be discarded under memory pressure). + * This is used internally to decide whether a BO is eligible for purging. + * + * Context: Caller must hold the BO's dma-resv lock + * Return: true if the BO is marked DONTNEED, false otherwise + */ +static inline bool xe_bo_madv_is_dontneed(struct xe_bo *bo) +{ + xe_bo_assert_held(bo); + return bo->madv_purgeable == XE_MADV_PURGEABLE_DONTNEED; +} + static inline void xe_bo_unpin_map_no_vm(struct xe_bo *bo) { if (likely(bo)) { diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index 88e3d8b33c53..efff5519fc58 100644 --- a/drivers/gpu/drm/xe/xe_bo_types.h +++ b/drivers/gpu/drm/xe/xe_bo_types.h @@ -110,6 +110,12 @@ struct xe_bo { * from default */ u64 min_align; + + /** + * @madv_purgeable: user space advise on BO purgeability, protected + * by BO's dma-resv lock. + */ + u32 madv_purgeable; }; #endif diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 0e80f2940c99..2ed03fd074ff 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -305,6 +305,8 @@ struct xe_device { * pcode mailbox commands. */ u8 has_mbx_power_limits:1; + /** @info.has_page_reclaim_hw_assist: Device supports page reclamation feature */ + u8 has_page_reclaim_hw_assist:1; /** @info.has_pxp: Device has PXP support */ u8 has_pxp:1; /** @info.has_range_tlb_inval: Has range based TLB invalidations */ diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 87a32b61bece..c156cf4661f2 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -286,13 +286,23 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto err_exec; } - /* Wait behind rebinds */ + /* + * Wait behind rebinds and any kernel operations (evictions, defrag + * moves, ...) on the VM and all external BOs. The VM's private BOs + * carry their kernel ops in the VM dma-resv KERNEL slot, while each + * external BO carries them in its own dma-resv KERNEL slot; both are + * covered by iterating every object locked by the exec, mirroring the + * drm_gpuvm_resv_add_fence() below. + */ if (!xe_vm_in_lr_mode(vm)) { - err = xe_sched_job_add_deps(job, - xe_vm_resv(vm), - DMA_RESV_USAGE_KERNEL); - if (err) - goto err_put_job; + struct drm_gem_object *obj; + + drm_exec_for_each_locked_object(exec, obj) { + err = xe_sched_job_add_deps(job, obj->resv, + DMA_RESV_USAGE_KERNEL); + if (err) + goto err_put_job; + } } for (i = 0; i < num_syncs && !err; i++) diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c index f253e2df4907..1a4d8d4f44b4 100644 --- a/drivers/gpu/drm/xe/xe_gt_debugfs.c +++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c @@ -174,8 +174,10 @@ static int register_save_restore(struct xe_gt *gt, struct drm_printer *p) drm_printf(p, "\n"); drm_printf(p, "Whitelist\n"); - for_each_hw_engine(hwe, gt, id) + for_each_hw_engine(hwe, gt, id) { xe_reg_whitelist_dump(&hwe->reg_whitelist, p); + xe_reg_whitelist_dump(&hwe->oa_whitelist, p); + } xe_pm_runtime_put(gt_to_xe(gt)); diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c index 243dad3e2418..3a1613886495 100644 --- a/drivers/gpu/drm/xe/xe_guc_capture.c +++ b/drivers/gpu/drm/xe/xe_guc_capture.c @@ -437,8 +437,15 @@ static void guc_capture_alloc_steered_lists(struct xe_guc *guc) if (!list || guc->capture->extlists) return; - total = bitmap_weight(gt->fuse_topo.g_dss_mask, sizeof(gt->fuse_topo.g_dss_mask) * 8) * - guc_capture_get_steer_reg_num(guc_to_xe(guc)); + { + xe_dss_mask_t all_dss; + + bitmap_or(all_dss, gt->fuse_topo.g_dss_mask, gt->fuse_topo.c_dss_mask, + XE_MAX_DSS_FUSE_BITS); + + total = bitmap_weight(all_dss, XE_MAX_DSS_FUSE_BITS) * + guc_capture_get_steer_reg_num(guc_to_xe(guc)); + } if (!total) return; diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c index d88770370eeb..66a738f17a3b 100644 --- a/drivers/gpu/drm/xe/xe_hw_engine.c +++ b/drivers/gpu/drm/xe/xe_hw_engine.c @@ -565,6 +565,8 @@ static void hw_engine_init_early(struct xe_gt *gt, struct xe_hw_engine *hwe, hw_engine_setup_default_state(hwe); xe_reg_sr_init(&hwe->reg_whitelist, hwe->name, gt_to_xe(gt)); + xe_reg_sr_init(&hwe->oa_whitelist, hwe->name, gt_to_xe(gt)); + xe_reg_sr_init(&hwe->oa_sr, hwe->name, gt_to_xe(gt)); xe_reg_whitelist_process_engine(hwe); } diff --git a/drivers/gpu/drm/xe/xe_hw_engine_types.h b/drivers/gpu/drm/xe/xe_hw_engine_types.h index e4191a7a2c31..04ca7545d22c 100644 --- a/drivers/gpu/drm/xe/xe_hw_engine_types.h +++ b/drivers/gpu/drm/xe/xe_hw_engine_types.h @@ -128,6 +128,14 @@ struct xe_hw_engine { * @reg_whitelist: table with registers to be whitelisted */ struct xe_reg_sr reg_whitelist; + /** + * @oa_whitelist: oa registers to be whitelisted + */ + struct xe_reg_sr oa_whitelist; + /** + * @oa_sr: oa nonpriv whitelist registers, changed on oa stream open/close + */ + struct xe_reg_sr oa_sr; /** * @reg_lrc: LRC workaround registers */ diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index e0a14360d312..1e8c0b92d712 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -765,31 +765,13 @@ static u32 xe_migrate_ccs_copy(struct xe_migrate *m, return flush_flags; } -/** - * xe_migrate_copy() - Copy content of TTM resources. - * @m: The migration context. - * @src_bo: The buffer object @src is currently bound to. - * @dst_bo: If copying between resources created for the same bo, set this to - * the same value as @src_bo. If copying between buffer objects, set it to - * the buffer object @dst is currently bound to. - * @src: The source TTM resource. - * @dst: The dst TTM resource. - * @copy_only_ccs: If true copy only CCS metadata - * - * Copies the contents of @src to @dst: On flat CCS devices, - * the CCS metadata is copied as well if needed, or if not present, - * the CCS metadata of @dst is cleared for security reasons. - * - * Return: Pointer to a dma_fence representing the last copy batch, or - * an error pointer on failure. If there is a failure, any copy operation - * started by the function call has been synced. - */ -struct dma_fence *xe_migrate_copy(struct xe_migrate *m, - struct xe_bo *src_bo, - struct xe_bo *dst_bo, - struct ttm_resource *src, - struct ttm_resource *dst, - bool copy_only_ccs) +static struct dma_fence *__xe_migrate_copy(struct xe_migrate *m, + struct xe_bo *src_bo, + struct xe_bo *dst_bo, + struct ttm_resource *src, + struct ttm_resource *dst, + bool copy_only_ccs, + bool is_vram_resolve) { struct xe_gt *gt = m->tile->primary_gt; struct xe_device *xe = gt_to_xe(gt); @@ -810,8 +792,15 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, bool copy_ccs = xe_device_has_flat_ccs(xe) && xe_bo_needs_ccs_pages(src_bo) && xe_bo_needs_ccs_pages(dst_bo); bool copy_system_ccs = copy_ccs && (!src_is_vram || !dst_is_vram); - bool use_comp_pat = type_device && xe_device_has_flat_ccs(xe) && - GRAPHICS_VER(xe) >= 20 && src_is_vram && !dst_is_vram; + + /* + * For decompression operation, always use the compression PAT index. + * Otherwise, only use the compression PAT index for device memory + * when copying from VRAM to system memory. + */ + bool use_comp_pat = is_vram_resolve || (type_device && + xe_device_has_flat_ccs(xe) && + GRAPHICS_VER(xe) >= 20 && src_is_vram && !dst_is_vram); /* Copying CCS between two different BOs is not supported yet. */ if (XE_WARN_ON(copy_ccs && src_bo != dst_bo)) @@ -970,6 +959,53 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, return fence; } +/** + * xe_migrate_copy() - Copy content of TTM resources. + * @m: The migration context. + * @src_bo: The buffer object @src is currently bound to. + * @dst_bo: If copying between resources created for the same bo, set this to + * the same value as @src_bo. If copying between buffer objects, set it to + * the buffer object @dst is currently bound to. + * @src: The source TTM resource. + * @dst: The dst TTM resource. + * @copy_only_ccs: If true copy only CCS metadata + * + * Copies the contents of @src to @dst: On flat CCS devices, + * the CCS metadata is copied as well if needed, or if not present, + * the CCS metadata of @dst is cleared for security reasons. + * + * Return: Pointer to a dma_fence representing the last copy batch, or + * an error pointer on failure. If there is a failure, any copy operation + * started by the function call has been synced. + */ +struct dma_fence *xe_migrate_copy(struct xe_migrate *m, + struct xe_bo *src_bo, + struct xe_bo *dst_bo, + struct ttm_resource *src, + struct ttm_resource *dst, + bool copy_only_ccs) +{ + return __xe_migrate_copy(m, src_bo, dst_bo, src, dst, copy_only_ccs, false); +} + +/** + * xe_migrate_resolve() - Resolve and decompress a buffer object if required. + * @m: The migrate context + * @bo: The buffer object to resolve + * @res: The reservation object + * + * Wrapper around __xe_migrate_copy() with is_vram_resolve set to true + * to trigger decompression if needed. + * + * Return: A dma_fence that signals on completion, or an ERR_PTR on failure. + */ +struct dma_fence *xe_migrate_resolve(struct xe_migrate *m, + struct xe_bo *bo, + struct ttm_resource *res) +{ + return __xe_migrate_copy(m, bo, bo, res, res, false, true); +} + /** * xe_migrate_lrc() - Get the LRC from migrate context. * @migrate: Migrate context. diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h index 8bac669685ee..9665a0aff547 100644 --- a/drivers/gpu/drm/xe/xe_migrate.h +++ b/drivers/gpu/drm/xe/xe_migrate.h @@ -127,6 +127,10 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, struct ttm_resource *dst, bool copy_only_ccs); +struct dma_fence *xe_migrate_resolve(struct xe_migrate *m, + struct xe_bo *bo, + struct ttm_resource *res); + int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q, struct xe_bo *src_bo, struct ttm_resource *new_mem, diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 7d04591e297a..98df9ee1cac3 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -35,6 +35,7 @@ #include "xe_oa.h" #include "xe_observation.h" #include "xe_pm.h" +#include "xe_reg_whitelist.h" #include "xe_sched_job.h" #include "xe_sriov.h" #include "xe_sync.h" @@ -863,6 +864,9 @@ static void xe_oa_stream_destroy(struct xe_oa_stream *stream) mutex_destroy(&stream->stream_lock); + if (stream->sample) + xe_reg_dewhitelist_oa_regs(stream->gt); + xe_oa_disable_metric_set(stream); xe_exec_queue_put(stream->k_exec_q); @@ -1887,6 +1891,9 @@ static int xe_oa_stream_open_ioctl_locked(struct xe_oa *oa, goto err_disable; } + if (stream->sample) + xe_reg_whitelist_oa_regs(stream->gt); + /* Hold a reference on the drm device till stream_fd is released */ drm_dev_get(&stream->oa->xe->drm); diff --git a/drivers/gpu/drm/xe/xe_oa_types.h b/drivers/gpu/drm/xe/xe_oa_types.h index daf701b5d48b..48f9520f560c 100644 --- a/drivers/gpu/drm/xe/xe_oa_types.h +++ b/drivers/gpu/drm/xe/xe_oa_types.h @@ -125,6 +125,9 @@ struct xe_oa_gt { /** @oa_unit: array of oa_units */ struct xe_oa_unit *oa_unit; + + /** @whitelist_count: number of open streams for which oa registers are whitelisted */ + u32 whitelist_count; }; /** diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c new file mode 100644 index 000000000000..d509a80cb1f3 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_pagefault.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2025 Intel Corporation + */ + +#include "xe_pagefault.h" +#include "xe_pagefault_types.h" + +/** + * DOC: Xe page faults + * + * Xe page faults are handled in two layers. The producer layer interacts with + * hardware or firmware to receive and parse faults into struct xe_pagefault, + * then forwards them to the consumer. The consumer layer services the faults + * (e.g., memory migration, page table updates) and acknowledges the result back + * to the producer, which then forwards the results to the hardware or firmware. + * The consumer uses a page fault queue sized to absorb all potential faults and + * a multi-threaded worker to process them. Multiple producers are supported, + * with a single shared consumer. + * + * xe_pagefault.c implements the consumer layer. + */ + +/** + * xe_pagefault_init() - Page fault init + * @xe: xe device instance + * + * Initialize Xe page fault state. Must be done after reading fuses. + * + * Return: 0 on Success, errno on failure + */ +int xe_pagefault_init(struct xe_device *xe) +{ + /* TODO - implement */ + return 0; +} + +/** + * xe_pagefault_reset() - Page fault reset for a GT + * @xe: xe device instance + * @gt: GT being reset + * + * Reset the Xe page fault state for a GT; that is, squash any pending faults on + * the GT. + */ +void xe_pagefault_reset(struct xe_device *xe, struct xe_gt *gt) +{ + /* TODO - implement */ +} + +/** + * xe_pagefault_handler() - Page fault handler + * @xe: xe device instance + * @pf: Page fault + * + * Sink the page fault to a queue (i.e., a memory buffer) and queue a worker to + * service it. Safe to be called from IRQ or process context. Reclaim safe. + * + * Return: 0 on success, errno on failure + */ +int xe_pagefault_handler(struct xe_device *xe, struct xe_pagefault *pf) +{ + /* TODO - implement */ + return 0; +} diff --git a/drivers/gpu/drm/xe/xe_pagefault.h b/drivers/gpu/drm/xe/xe_pagefault.h new file mode 100644 index 000000000000..bd0cdf9ed37f --- /dev/null +++ b/drivers/gpu/drm/xe/xe_pagefault.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _XE_PAGEFAULT_H_ +#define _XE_PAGEFAULT_H_ + +struct xe_device; +struct xe_gt; +struct xe_pagefault; + +int xe_pagefault_init(struct xe_device *xe); + +void xe_pagefault_reset(struct xe_device *xe, struct xe_gt *gt); + +int xe_pagefault_handler(struct xe_device *xe, struct xe_pagefault *pf); + +#endif diff --git a/drivers/gpu/drm/xe/xe_pagefault_types.h b/drivers/gpu/drm/xe/xe_pagefault_types.h new file mode 100644 index 000000000000..d3b516407d60 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_pagefault_types.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2025 Intel Corporation + */ + +#ifndef _XE_PAGEFAULT_TYPES_H_ +#define _XE_PAGEFAULT_TYPES_H_ + +#include <linux/workqueue.h> + +struct xe_gt; +struct xe_pagefault; + +/** enum xe_pagefault_access_type - Xe page fault access type */ +enum xe_pagefault_access_type { + /** @XE_PAGEFAULT_ACCESS_TYPE_READ: Read access type */ + XE_PAGEFAULT_ACCESS_TYPE_READ = 0, + /** @XE_PAGEFAULT_ACCESS_TYPE_WRITE: Write access type */ + XE_PAGEFAULT_ACCESS_TYPE_WRITE = 1, + /** @XE_PAGEFAULT_ACCESS_TYPE_ATOMIC: Atomic access type */ + XE_PAGEFAULT_ACCESS_TYPE_ATOMIC = 2, +}; + +/** enum xe_pagefault_type - Xe page fault type */ +enum xe_pagefault_type { + /** @XE_PAGEFAULT_TYPE_NOT_PRESENT: Not present */ + XE_PAGEFAULT_TYPE_NOT_PRESENT = 0, + /** @XE_PAGEFAULT_TYPE_WRITE_ACCESS_VIOLATION: Write access violation */ + XE_PAGEFAULT_TYPE_WRITE_ACCESS_VIOLATION = 1, + /** @XE_PAGEFAULT_TYPE_ATOMIC_ACCESS_VIOLATION: Atomic access violation */ + XE_PAGEFAULT_TYPE_ATOMIC_ACCESS_VIOLATION = 2, +}; + +/** struct xe_pagefault_ops - Xe pagefault ops (producer) */ +struct xe_pagefault_ops { + /** + * @ack_fault: Ack fault + * @pf: Page fault + * @err: Error state of fault + * + * Page fault producer receives acknowledgment from the consumer and + * sends the result to the HW/FW interface. + */ + void (*ack_fault)(struct xe_pagefault *pf, int err); +}; + +/** + * struct xe_pagefault - Xe page fault + * + * Generic page fault structure for communication between producer and consumer. + * Carefully sized to be 64 bytes. Upon a device page fault, the producer + * populates this structure, and the consumer copies it into the page-fault + * queue for deferred handling. + */ +struct xe_pagefault { + /** + * @gt: GT of fault + */ + struct xe_gt *gt; + /** + * @consumer: State for the software handling the fault. Populated by + * the producer and may be modified by the consumer to communicate + * information back to the producer upon fault acknowledgment. + */ + struct { + /** @consumer.page_addr: address of page fault */ + u64 page_addr; + /** @consumer.asid: address space ID */ + u32 asid; + /** + * @consumer.access_type: access type, u8 rather than enum to + * keep size compact + */ + u8 access_type; + /** + * @consumer.fault_type: fault type, u8 rather than enum to + * keep size compact + */ + u8 fault_type; +#define XE_PAGEFAULT_LEVEL_NACK 0xff /* Producer indicates nack fault */ + /** @consumer.fault_level: fault level */ + u8 fault_level; + /** @consumer.engine_class: engine class */ + u8 engine_class; + /** @consumer.engine_instance: engine instance */ + u8 engine_instance; + /** consumer.reserved: reserved bits for future expansion */ + u8 reserved[7]; + } consumer; + /** + * @producer: State for the producer (i.e., HW/FW interface). Populated + * by the producer and should not be modified—or even inspected—by the + * consumer, except for calling operations. + */ + struct { + /** @producer.private: private pointer */ + void *private; + /** @producer.ops: operations */ + const struct xe_pagefault_ops *ops; +#define XE_PAGEFAULT_PRODUCER_MSG_LEN_DW 4 + /** + * @producer.msg: page fault message, used by producer in fault + * acknowledgment to formulate response to HW/FW interface. + * Included in the page-fault message because the producer + * typically receives the fault in a context where memory cannot + * be allocated (e.g., atomic context or the reclaim path). + */ + u32 msg[XE_PAGEFAULT_PRODUCER_MSG_LEN_DW]; + } producer; +}; + +/** + * struct xe_pagefault_queue: Xe pagefault queue (consumer) + * + * Used to capture all device page faults for deferred processing. Size this + * queue to absorb the device’s worst-case number of outstanding faults. + */ +struct xe_pagefault_queue { + /** + * @data: Data in queue containing struct xe_pagefault, protected by + * @lock + */ + void *data; + /** @size: Size of queue in bytes */ + u32 size; + /** @head: Head pointer in bytes, moved by producer, protected by @lock */ + u32 head; + /** @tail: Tail pointer in bytes, moved by consumer, protected by @lock */ + u32 tail; + /** @lock: protects page fault queue */ + spinlock_t lock; + /** @worker: to process page faults */ + struct work_struct worker; +}; + +#endif diff --git a/drivers/gpu/drm/xe/xe_pat.c b/drivers/gpu/drm/xe/xe_pat.c index 2e7cb99ae87a..9a321384b73d 100644 --- a/drivers/gpu/drm/xe/xe_pat.c +++ b/drivers/gpu/drm/xe/xe_pat.c @@ -160,6 +160,12 @@ u16 xe_pat_index_get_coh_mode(struct xe_device *xe, u16 pat_index) return xe->pat.table[pat_index].coh_mode; } +bool xe_pat_index_get_comp_en(struct xe_device *xe, u16 pat_index) +{ + WARN_ON(pat_index >= xe->pat.n_entries); + return !!(xe->pat.table[pat_index].value & XE2_COMP_EN); +} + static void program_pat(struct xe_gt *gt, const struct xe_pat_table_entry table[], int n_entries) { diff --git a/drivers/gpu/drm/xe/xe_pat.h b/drivers/gpu/drm/xe/xe_pat.h index fa0dfbe525cd..12cb6ec39d34 100644 --- a/drivers/gpu/drm/xe/xe_pat.h +++ b/drivers/gpu/drm/xe/xe_pat.h @@ -58,4 +58,14 @@ void xe_pat_dump(struct xe_gt *gt, struct drm_printer *p); */ u16 xe_pat_index_get_coh_mode(struct xe_device *xe, u16 pat_index); +/** + * xe_pat_index_get_comp_en - Extract the compression enable flag for + * the given pat_index. + * @xe: xe device + * @pat_index: The pat_index to query + * + * Return: true if compression is enabled for this pat_index, false otherwise. + */ +bool xe_pat_index_get_comp_en(struct xe_device *xe, u16 pat_index); + #endif diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index 89cc6d32f041..b78729211790 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -591,6 +591,7 @@ static int xe_info_init_early(struct xe_device *xe, xe->info.has_heci_cscfi = desc->has_heci_cscfi; xe->info.has_late_bind = desc->has_late_bind; xe->info.has_llc = desc->has_llc; + xe->info.has_page_reclaim_hw_assist = desc->has_page_reclaim_hw_assist; xe->info.has_pxp = desc->has_pxp; xe->info.has_sriov = desc->has_sriov; xe->info.skip_guc_pc = desc->skip_guc_pc; diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h index 9b9766a3baa3..a7b6576725ed 100644 --- a/drivers/gpu/drm/xe/xe_pci_types.h +++ b/drivers/gpu/drm/xe/xe_pci_types.h @@ -42,6 +42,7 @@ struct xe_device_desc { u8 has_late_bind:1; u8 has_llc:1; u8 has_mbx_power_limits:1; + u8 has_page_reclaim_hw_assist:1; u8 has_pxp:1; u8 has_sriov:1; u8 needs_scratch:1; diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index de0d104fc8b6..1d22af2145bf 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -715,7 +715,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, .vm = vm, .tile = tile, .curs = &curs, - .va_curs_start = range ? range->base.itree.start : + .va_curs_start = range ? xe_svm_range_start(range) : xe_vma_start(vma), .vma = vma, .wupd.entries = entries, @@ -734,7 +734,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, } if (xe_svm_range_has_dma_mapping(range)) { xe_res_first_dma(range->base.pages.dma_addr, 0, - range->base.itree.last + 1 - range->base.itree.start, + xe_svm_range_size(range), &curs); xe_svm_range_debug(range, "BIND PREPARE - MIXED"); } else { @@ -778,8 +778,8 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, walk_pt: ret = xe_pt_walk_range(&pt->base, pt->level, - range ? range->base.itree.start : xe_vma_start(vma), - range ? range->base.itree.last + 1 : xe_vma_end(vma), + range ? xe_svm_range_start(range) : xe_vma_start(vma), + range ? xe_svm_range_end(range) : xe_vma_end(vma), &xe_walk.base); *num_entries = xe_walk.wupd.num_used_entries; @@ -983,8 +983,8 @@ bool xe_pt_zap_ptes_range(struct xe_tile *tile, struct xe_vm *vm, if (!(pt_mask & BIT(tile->id))) return false; - (void)xe_pt_walk_shared(&pt->base, pt->level, range->base.itree.start, - range->base.itree.last + 1, &xe_walk.base); + (void)xe_pt_walk_shared(&pt->base, pt->level, xe_svm_range_start(range), + xe_svm_range_end(range), &xe_walk.base); return xe_walk.needs_invalidate; } @@ -1711,8 +1711,8 @@ static unsigned int xe_pt_stage_unbind(struct xe_tile *tile, struct xe_svm_range *range, struct xe_vm_pgtable_update *entries) { - u64 start = range ? range->base.itree.start : xe_vma_start(vma); - u64 end = range ? range->base.itree.last + 1 : xe_vma_end(vma); + u64 start = range ? xe_svm_range_start(range) : xe_vma_start(vma); + u64 end = range ? xe_svm_range_end(range) : xe_vma_end(vma); struct xe_pt_stage_unbind_walk xe_walk = { .base = { .ops = &xe_pt_stage_unbind_ops, @@ -1922,7 +1922,7 @@ static int bind_range_prepare(struct xe_vm *vm, struct xe_tile *tile, vm_dbg(&xe_vma_vm(vma)->xe->drm, "Preparing bind, with range [%lx...%lx)\n", - range->base.itree.start, range->base.itree.last); + xe_svm_range_start(range), xe_svm_range_end(range) - 1); pt_op->vma = NULL; pt_op->bind = true; @@ -1937,8 +1937,8 @@ static int bind_range_prepare(struct xe_vm *vm, struct xe_tile *tile, pt_op->num_entries, true); xe_pt_update_ops_rfence_interval(pt_update_ops, - range->base.itree.start, - range->base.itree.last + 1); + xe_svm_range_start(range), + xe_svm_range_end(range)); ++pt_update_ops->current_op; pt_update_ops->needs_svm_lock = true; @@ -2033,7 +2033,7 @@ static int unbind_range_prepare(struct xe_vm *vm, vm_dbg(&vm->xe->drm, "Preparing unbind, with range [%lx...%lx)\n", - range->base.itree.start, range->base.itree.last); + xe_svm_range_start(range), xe_svm_range_end(range) - 1); pt_op->vma = XE_INVALID_VMA; pt_op->bind = false; @@ -2044,8 +2044,8 @@ static int unbind_range_prepare(struct xe_vm *vm, xe_vm_dbg_print_entries(tile_to_xe(tile), pt_op->entries, pt_op->num_entries, false); - xe_pt_update_ops_rfence_interval(pt_update_ops, range->base.itree.start, - range->base.itree.last + 1); + xe_pt_update_ops_rfence_interval(pt_update_ops, xe_svm_range_start(range), + xe_svm_range_end(range)); ++pt_update_ops->current_op; pt_update_ops->needs_svm_lock = true; pt_update_ops->needs_invalidation |= xe_vm_has_scratch(vm) || @@ -2153,8 +2153,11 @@ static void xe_pt_update_ops_init(struct xe_vm_pgtable_update_ops *pt_update_ops) { init_llist_head(&pt_update_ops->deferred); + pt_update_ops->current_op = 0; pt_update_ops->start = ~0x0ull; pt_update_ops->last = 0x0ull; + pt_update_ops->needs_svm_lock = false; + pt_update_ops->needs_invalidation = false; } /** diff --git a/drivers/gpu/drm/xe/xe_reg_whitelist.c b/drivers/gpu/drm/xe/xe_reg_whitelist.c index 21763dc51150..eb1d6f52f75f 100644 --- a/drivers/gpu/drm/xe/xe_reg_whitelist.c +++ b/drivers/gpu/drm/xe/xe_reg_whitelist.c @@ -9,7 +9,8 @@ #include "regs/xe_gt_regs.h" #include "regs/xe_oa_regs.h" #include "regs/xe_regs.h" -#include "xe_gt_types.h" +#include "xe_assert.h" +#include "xe_gt.h" #include "xe_gt_printk.h" #include "xe_platform_types.h" #include "xe_reg_sr.h" @@ -66,33 +67,36 @@ static const struct xe_rtp_entry_sr register_whitelist[] = { ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(WHITELIST(CSBE_DEBUG_STATUS(RENDER_RING_BASE), 0)) }, - { XE_RTP_NAME("oa_reg_render"), +}; + +static const struct xe_rtp_entry_sr oa_whitelist[] = { + +#define WHITELIST_DENY(r, f) WHITELIST(r, (f) | RING_FORCE_TO_NONPRIV_DENY) + +#define WHITELIST_OA_MMIO_TRG(trg, status, head) \ + WHITELIST_DENY(trg, RING_FORCE_TO_NONPRIV_ACCESS_RW), \ + WHITELIST_DENY(status, RING_FORCE_TO_NONPRIV_ACCESS_RD), \ + WHITELIST_DENY(head, RING_FORCE_TO_NONPRIV_ACCESS_RD | RING_FORCE_TO_NONPRIV_RANGE_4) + +#define WHITELIST_OAG_MMIO_TRG \ + WHITELIST_OA_MMIO_TRG(OAG_MMIOTRIGGER, OAG_OASTATUS, OAG_OAHEADPTR) + + { XE_RTP_NAME("oag_mmio_trg_rcs"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, XE_RTP_END_VERSION_UNDEFINED), ENGINE_CLASS(RENDER)), - XE_RTP_ACTIONS(WHITELIST(OAG_MMIOTRIGGER, - RING_FORCE_TO_NONPRIV_ACCESS_RW), - WHITELIST(OAG_OASTATUS, - RING_FORCE_TO_NONPRIV_ACCESS_RD), - WHITELIST(OAG_OAHEADPTR, - RING_FORCE_TO_NONPRIV_ACCESS_RD | - RING_FORCE_TO_NONPRIV_RANGE_4)) + XE_RTP_ACTIONS(WHITELIST_OAG_MMIO_TRG) }, - { XE_RTP_NAME("oa_reg_compute"), + { XE_RTP_NAME("oag_mmio_trg_ccs"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, XE_RTP_END_VERSION_UNDEFINED), ENGINE_CLASS(COMPUTE)), - XE_RTP_ACTIONS(WHITELIST(OAG_MMIOTRIGGER, - RING_FORCE_TO_NONPRIV_ACCESS_RW), - WHITELIST(OAG_OASTATUS, - RING_FORCE_TO_NONPRIV_ACCESS_RD), - WHITELIST(OAG_OAHEADPTR, - RING_FORCE_TO_NONPRIV_ACCESS_RD | - RING_FORCE_TO_NONPRIV_RANGE_4)) + XE_RTP_ACTIONS(WHITELIST_OAG_MMIO_TRG) }, }; -static void whitelist_apply_to_hwe(struct xe_hw_engine *hwe) +static int whitelist_apply_to_hwe(struct xe_hw_engine *hwe, struct xe_reg_sr *in, + struct xe_reg_sr *out, int first_slot) { - struct xe_reg_sr *sr = &hwe->reg_whitelist; + struct xe_reg_sr *sr = in; struct xe_reg_sr_entry *entry; struct drm_printer p; unsigned long reg; @@ -101,7 +105,7 @@ static void whitelist_apply_to_hwe(struct xe_hw_engine *hwe) xe_gt_dbg(hwe->gt, "Add %s whitelist to engine\n", sr->name); p = xe_gt_dbg_printer(hwe->gt); - slot = 0; + slot = first_slot; xa_for_each(&sr->xa, reg, entry) { struct xe_reg_sr_entry hwe_entry = { .reg = RING_FORCE_TO_NONPRIV(hwe->mmio_base, slot), @@ -118,10 +122,12 @@ static void whitelist_apply_to_hwe(struct xe_hw_engine *hwe) } xe_reg_whitelist_print_entry(&p, 0, reg, entry); - xe_reg_sr_add(&hwe->reg_sr, &hwe_entry, hwe->gt); + xe_reg_sr_add(out, &hwe_entry, hwe->gt); slot++; } + + return slot; } /** @@ -135,10 +141,79 @@ static void whitelist_apply_to_hwe(struct xe_hw_engine *hwe) void xe_reg_whitelist_process_engine(struct xe_hw_engine *hwe) { struct xe_rtp_process_ctx ctx = XE_RTP_PROCESS_CTX_INITIALIZER(hwe); + int first_oa_slot; xe_rtp_process_to_sr(&ctx, register_whitelist, ARRAY_SIZE(register_whitelist), &hwe->reg_whitelist); - whitelist_apply_to_hwe(hwe); + first_oa_slot = whitelist_apply_to_hwe(hwe, &hwe->reg_whitelist, &hwe->reg_sr, 0); + + xe_rtp_process_to_sr(&ctx, oa_whitelist, ARRAY_SIZE(oa_whitelist), + &hwe->oa_whitelist); + /* + * Save oa nonpriv registers to hwe->oa_sr, from which oa registers are whitelisted + * or de-whitelisted, by toggling the 'deny' bit on oa stream open/close + */ + whitelist_apply_to_hwe(hwe, &hwe->oa_whitelist, &hwe->oa_sr, first_oa_slot); + + /* + * Also save oa nonpriv registers to hwe->reg_sr, to ensure oa registers are not + * whitelisted by default after probe, gt reset, resume and engine reset + */ + whitelist_apply_to_hwe(hwe, &hwe->oa_whitelist, &hwe->reg_sr, first_oa_slot); +} + +static void __whitelist_oa_regs(struct xe_hw_engine *hwe, bool whitelist) +{ + struct xe_reg_sr_entry *entry; + unsigned long reg; + + xa_for_each(&hwe->oa_sr.xa, reg, entry) { + if (whitelist) + entry->set_bits &= ~RING_FORCE_TO_NONPRIV_DENY; + else + entry->set_bits |= RING_FORCE_TO_NONPRIV_DENY; + } + + xe_reg_sr_apply_mmio(&hwe->oa_sr, hwe->gt); +} + +/** + * xe_reg_whitelist_oa_regs - whitelist oa registers for gt + * @gt: gt to whitelist oa registers for + * + * Whitelist OA registers by resetting RING_FORCE_TO_NONPRIV_DENY + */ +void xe_reg_whitelist_oa_regs(struct xe_gt *gt) +{ + struct xe_hw_engine *hwe; + enum xe_hw_engine_id id; + + lockdep_assert_held(>->oa.gt_lock); + if (gt->oa.whitelist_count++) + return; + + for_each_hw_engine(hwe, gt, id) + __whitelist_oa_regs(hwe, true); +} + +/** + * xe_reg_dewhitelist_oa_regs - dewhitelist oa registers for gt + * @gt: gt to dewhitelist oa registers for + * + * Dewhitelist OA registers by setting RING_FORCE_TO_NONPRIV_DENY + */ +void xe_reg_dewhitelist_oa_regs(struct xe_gt *gt) +{ + struct xe_hw_engine *hwe; + enum xe_hw_engine_id id; + + lockdep_assert_held(>->oa.gt_lock); + xe_assert(gt_to_xe(gt), gt->oa.whitelist_count); + if (--gt->oa.whitelist_count) + return; + + for_each_hw_engine(hwe, gt, id) + __whitelist_oa_regs(hwe, false); } /** diff --git a/drivers/gpu/drm/xe/xe_reg_whitelist.h b/drivers/gpu/drm/xe/xe_reg_whitelist.h index 69b121d377da..f243b6ac60b7 100644 --- a/drivers/gpu/drm/xe/xe_reg_whitelist.h +++ b/drivers/gpu/drm/xe/xe_reg_whitelist.h @@ -9,12 +9,16 @@ #include <linux/types.h> struct drm_printer; +struct xe_gt; struct xe_hw_engine; struct xe_reg_sr; struct xe_reg_sr_entry; void xe_reg_whitelist_process_engine(struct xe_hw_engine *hwe); +void xe_reg_whitelist_oa_regs(struct xe_gt *gt); +void xe_reg_dewhitelist_oa_regs(struct xe_gt *gt); + void xe_reg_whitelist_print_entry(struct drm_printer *p, unsigned int indent, u32 reg, struct xe_reg_sr_entry *entry); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index ed0c8acd0fe2..423705bcd94c 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -355,7 +355,6 @@ int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec, unsigned int num_fences) { struct drm_gem_object *obj; - unsigned long index; int ret; do { @@ -368,7 +367,7 @@ int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec, return ret; } while (!list_empty(&vm->gpuvm.evict.list)); - drm_exec_for_each_locked_object(exec, index, obj) { + drm_exec_for_each_locked_object(exec, obj) { ret = dma_resv_reserve_fences(obj->resv, num_fences); if (ret) return ret; @@ -2834,8 +2833,22 @@ static void vm_bind_ioctl_ops_unwind(struct xe_vm *vm, } } +/** + * struct xe_vma_lock_and_validate_flags - Flags for vma_lock_and_validate() + * @res_evict: Allow evicting resources during validation + * @validate: Perform BO validation + * @request_decompress: Request BO decompression + * @check_purged: Reject operation if BO is purged + */ +struct xe_vma_lock_and_validate_flags { + u32 res_evict : 1; + u32 validate : 1; + u32 request_decompress : 1; + u32 check_purged : 1; +}; + static int vma_lock_and_validate(struct drm_exec *exec, struct xe_vma *vma, - bool res_evict, bool validate) + struct xe_vma_lock_and_validate_flags flags) { struct xe_bo *bo = xe_vma_bo(vma); struct xe_vm *vm = xe_vma_vm(vma); @@ -2844,10 +2857,19 @@ static int vma_lock_and_validate(struct drm_exec *exec, struct xe_vma *vma, if (bo) { if (!bo->vm) err = drm_exec_lock_obj(exec, &bo->ttm.base); - if (!err && validate) + + /* Reject new mappings to DONTNEED/purged BOs; allow cleanup operations */ + if (!err && flags.check_purged) { + if (xe_bo_madv_is_dontneed(bo)) + err = -EBUSY; /* BO marked purgeable */ + else if (xe_bo_is_purged(bo)) + err = -EINVAL; /* BO already purged */ + } + + if (!err && flags.validate) err = xe_bo_validate(bo, vm, !xe_vm_in_preempt_fence_mode(vm) && - res_evict, exec); + flags.res_evict, exec); } return err; @@ -2933,9 +2955,13 @@ static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm, case DRM_GPUVA_OP_MAP: if (!op->map.invalidate_on_bind) err = vma_lock_and_validate(exec, op->map.vma, - res_evict, - !xe_vm_in_fault_mode(vm) || - op->map.immediate); + (struct xe_vma_lock_and_validate_flags) { + .res_evict = res_evict, + .validate = !xe_vm_in_fault_mode(vm) || + op->map.immediate, + .request_decompress = false, + .check_purged = true, + }); break; case DRM_GPUVA_OP_REMAP: err = check_ufence(gpuva_to_vma(op->base.remap.unmap->va)); @@ -2944,13 +2970,28 @@ static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm, err = vma_lock_and_validate(exec, gpuva_to_vma(op->base.remap.unmap->va), - res_evict, false); + (struct xe_vma_lock_and_validate_flags) { + .res_evict = res_evict, + .validate = false, + .request_decompress = false, + .check_purged = false, + }); if (!err && op->remap.prev) err = vma_lock_and_validate(exec, op->remap.prev, - res_evict, true); + (struct xe_vma_lock_and_validate_flags) { + .res_evict = res_evict, + .validate = true, + .request_decompress = false, + .check_purged = true, + }); if (!err && op->remap.next) err = vma_lock_and_validate(exec, op->remap.next, - res_evict, true); + (struct xe_vma_lock_and_validate_flags) { + .res_evict = res_evict, + .validate = true, + .request_decompress = false, + .check_purged = true, + }); break; case DRM_GPUVA_OP_UNMAP: err = check_ufence(gpuva_to_vma(op->base.unmap.va)); @@ -2959,7 +3000,12 @@ static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm, err = vma_lock_and_validate(exec, gpuva_to_vma(op->base.unmap.va), - res_evict, false); + (struct xe_vma_lock_and_validate_flags) { + .res_evict = res_evict, + .validate = false, + .request_decompress = false, + .check_purged = false, + }); break; case DRM_GPUVA_OP_PREFETCH: { @@ -2972,14 +3018,39 @@ static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm, region <= ARRAY_SIZE(region_to_mem_type)); } + /* + * Prefetch attempts to migrate BO's backing store without + * repopulating it first. Purged BOs have no backing store + * to migrate, so reject the operation. + */ err = vma_lock_and_validate(exec, gpuva_to_vma(op->base.prefetch.va), - res_evict, false); - if (!err && !xe_vma_has_no_bo(vma)) - err = xe_bo_migrate(xe_vma_bo(vma), - region_to_mem_type[region], - NULL, - exec); + (struct xe_vma_lock_and_validate_flags) { + .res_evict = res_evict, + .validate = false, + .request_decompress = false, + .check_purged = true, + }); + if (!err && !xe_vma_has_no_bo(vma)) { + struct xe_bo *bo = xe_vma_bo(vma); + u32 mem_type; + + if (region == DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC) { + unsigned int i; + + mem_type = XE_PL_TT; + for (i = 0; i < bo->placement.num_placement; i++) { + if (mem_type_is_vram(bo->placements[i].mem_type)) { + mem_type = bo->placements[i].mem_type; + break; + } + } + } else { + mem_type = region_to_mem_type[region]; + } + + err = xe_bo_migrate(bo, mem_type, NULL, exec); + } break; } default: diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 3b5412541c92..7895f27c9135 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1749,7 +1749,8 @@ static int logi_dj_raw_event(struct hid_device *hdev, static int logi_dj_probe(struct hid_device *hdev, const struct hid_device_id *id) { - struct hid_report_enum *rep_enum; + struct hid_report_enum *input_report_enum; + struct hid_report_enum *output_report_enum; struct hid_report *rep; struct dj_receiver_dev *djrcv_dev; struct usb_interface *intf; @@ -1793,10 +1794,25 @@ static int logi_dj_probe(struct hid_device *hdev, } } - rep_enum = &hdev->report_enum[HID_INPUT_REPORT]; + output_report_enum = &hdev->report_enum[HID_OUTPUT_REPORT]; + rep = output_report_enum->report_id_hash[REPORT_ID_DJ_SHORT]; + + if (rep && rep->maxfield < 1) { + hid_err(hdev, "Expected size of DJ short report is %d, but got 0", + DJREPORT_SHORT_LENGTH - 1); + return -EINVAL; + } + + if (rep && rep->field[0]->report_count != DJREPORT_SHORT_LENGTH - 1) { + hid_err(hdev, "Expected size of DJ short report is %d, but got %d", + DJREPORT_SHORT_LENGTH - 1, rep->field[0]->report_count); + return -EINVAL; + } + + input_report_enum = &hdev->report_enum[HID_INPUT_REPORT]; /* no input reports, bail out */ - if (list_empty(&rep_enum->report_list)) + if (list_empty(&input_report_enum->report_list)) return -ENODEV; /* @@ -1804,7 +1820,7 @@ static int logi_dj_probe(struct hid_device *hdev, * Note: we should theoretically check for HID++ and DJ * collections, but this will do. */ - list_for_each_entry(rep, &rep_enum->report_list, list) { + list_for_each_entry(rep, &input_report_enum->report_list, list) { if (rep->application == 0xff000001) has_hidpp = true; } @@ -1817,7 +1833,7 @@ static int logi_dj_probe(struct hid_device *hdev, return -ENODEV; /* get the current application attached to the node */ - rep = list_first_entry(&rep_enum->report_list, struct hid_report, list); + rep = list_first_entry(&input_report_enum->report_list, struct hid_report, list); djrcv_dev = dj_get_receiver_dev(hdev, id->driver_data, rep->application, has_hidpp); if (!djrcv_dev) { @@ -1825,7 +1841,7 @@ static int logi_dj_probe(struct hid_device *hdev, return -ENOMEM; } - if (!rep_enum->numbered) + if (!input_report_enum->numbered) djrcv_dev->unnumbered_application = rep->application; /* Starts the usb device and connects to upper interfaces hiddev and diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index fd1d675ae37a..d5348195e4fb 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -844,14 +844,14 @@ static void vmbus_wait_for_unload(void) = per_cpu_ptr(hv_context.cpu_context, cpu); /* - * In a CoCo VM the synic_message_page is not allocated + * In a CoCo VM the hyp_synic_message_page is not allocated * in hv_synic_alloc(). Instead it is set/cleared in * hv_synic_enable_regs() and hv_synic_disable_regs() * such that it is set only when the CPU is online. If * not all present CPUs are online, the message page * might be NULL, so skip such CPUs. */ - page_addr = hv_cpu->synic_message_page; + page_addr = hv_cpu->hyp_synic_message_page; if (!page_addr) continue; @@ -892,7 +892,7 @@ static void vmbus_wait_for_unload(void) struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); - page_addr = hv_cpu->synic_message_page; + page_addr = hv_cpu->hyp_synic_message_page; if (!page_addr) continue; diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index b14c5f9e0ef2..90db1e17582d 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -96,10 +96,70 @@ int hv_post_message(union hv_connection_id connection_id, return hv_result(status); } +static int hv_alloc_page(void **page, bool decrypt, const char *note) +{ + int ret = 0; + + /* + * After the page changes its encryption status, its contents might + * appear scrambled on some hardware. Thus `get_zeroed_page` would + * zero the page out in vain, so do that explicitly exactly once. + * + * By default, the page is allocated encrypted in a CoCo VM. + */ + *page = (void *)__get_free_page(GFP_KERNEL); + if (!*page) + return -ENOMEM; + + if (decrypt) + ret = set_memory_decrypted((unsigned long)*page, 1); + if (ret) + goto failed; + + memset(*page, 0, PAGE_SIZE); + return 0; + +failed: + /* + * Report the failure but don't put the page back on the free list as + * its encryption status is unknown. + */ + pr_err("allocation failed for %s page, error %d, decrypted %d\n", + note, ret, decrypt); + *page = NULL; + return ret; +} + +static int hv_free_page(void **page, bool encrypt, const char *note) +{ + int ret = 0; + + if (!*page) + return 0; + + if (encrypt) + ret = set_memory_encrypted((unsigned long)*page, 1); + + /* + * In the case of the failure, the page is leaked. Something is wrong, + * prefer to lose the page with the unknown encryption status and stay afloat. + */ + if (ret) + pr_err("deallocation failed for %s page, error %d, encrypt %d\n", + note, ret, encrypt); + else + free_page((unsigned long)*page); + + *page = NULL; + + return ret; +} + int hv_synic_alloc(void) { int cpu, ret = -ENOMEM; struct hv_per_cpu_context *hv_cpu; + const bool decrypt = !vmbus_is_confidential(); /* * First, zero all per-cpu memory areas so hv_synic_free() can @@ -125,73 +185,37 @@ int hv_synic_alloc(void) vmbus_on_msg_dpc, (unsigned long)hv_cpu); if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) { - hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (!hv_cpu->post_msg_page) { - pr_err("Unable to allocate post msg page\n"); + ret = hv_alloc_page(&hv_cpu->post_msg_page, + decrypt, "post msg"); + if (ret) goto err; - } - - ret = set_memory_decrypted((unsigned long)hv_cpu->post_msg_page, 1); - if (ret) { - pr_err("Failed to decrypt post msg page: %d\n", ret); - /* Just leak the page, as it's unsafe to free the page. */ - hv_cpu->post_msg_page = NULL; - goto err; - } - - memset(hv_cpu->post_msg_page, 0, PAGE_SIZE); } /* - * Synic message and event pages are allocated by paravisor. - * Skip these pages allocation here. + * If these SynIC pages are not allocated, SIEF and SIM pages + * are configured using what the root partition or the paravisor + * provides upon reading the SIEFP and SIMP registers. */ if (!ms_hyperv.paravisor_present && !hv_root_partition()) { - hv_cpu->synic_message_page = - (void *)get_zeroed_page(GFP_ATOMIC); - if (!hv_cpu->synic_message_page) { - pr_err("Unable to allocate SYNIC message page\n"); + ret = hv_alloc_page(&hv_cpu->hyp_synic_message_page, + decrypt, "hypervisor SynIC msg"); + if (ret) goto err; - } - - hv_cpu->synic_event_page = - (void *)get_zeroed_page(GFP_ATOMIC); - if (!hv_cpu->synic_event_page) { - pr_err("Unable to allocate SYNIC event page\n"); - - free_page((unsigned long)hv_cpu->synic_message_page); - hv_cpu->synic_message_page = NULL; + ret = hv_alloc_page(&hv_cpu->hyp_synic_event_page, + decrypt, "hypervisor SynIC event"); + if (ret) goto err; - } } - if (!ms_hyperv.paravisor_present && - (hv_isolation_type_snp() || hv_isolation_type_tdx())) { - ret = set_memory_decrypted((unsigned long) - hv_cpu->synic_message_page, 1); - if (ret) { - pr_err("Failed to decrypt SYNIC msg page: %d\n", ret); - hv_cpu->synic_message_page = NULL; - - /* - * Free the event page here so that hv_synic_free() - * won't later try to re-encrypt it. - */ - free_page((unsigned long)hv_cpu->synic_event_page); - hv_cpu->synic_event_page = NULL; + if (vmbus_is_confidential()) { + ret = hv_alloc_page(&hv_cpu->para_synic_message_page, + false, "paravisor SynIC msg"); + if (ret) goto err; - } - - ret = set_memory_decrypted((unsigned long) - hv_cpu->synic_event_page, 1); - if (ret) { - pr_err("Failed to decrypt SYNIC event page: %d\n", ret); - hv_cpu->synic_event_page = NULL; + ret = hv_alloc_page(&hv_cpu->para_synic_event_page, + false, "paravisor SynIC event"); + if (ret) goto err; - } - - memset(hv_cpu->synic_message_page, 0, PAGE_SIZE); - memset(hv_cpu->synic_event_page, 0, PAGE_SIZE); } } @@ -207,48 +231,28 @@ int hv_synic_alloc(void) void hv_synic_free(void) { - int cpu, ret; + int cpu; + const bool encrypt = !vmbus_is_confidential(); for_each_present_cpu(cpu) { struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); - /* It's better to leak the page if the encryption fails. */ - if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) { - if (hv_cpu->post_msg_page) { - ret = set_memory_encrypted((unsigned long) - hv_cpu->post_msg_page, 1); - if (ret) { - pr_err("Failed to encrypt post msg page: %d\n", ret); - hv_cpu->post_msg_page = NULL; - } - } + if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) + hv_free_page(&hv_cpu->post_msg_page, + encrypt, "post msg"); + if (!ms_hyperv.paravisor_present && !hv_root_partition()) { + hv_free_page(&hv_cpu->hyp_synic_event_page, + encrypt, "hypervisor SynIC event"); + hv_free_page(&hv_cpu->hyp_synic_message_page, + encrypt, "hypervisor SynIC msg"); } - - if (!ms_hyperv.paravisor_present && - (hv_isolation_type_snp() || hv_isolation_type_tdx())) { - if (hv_cpu->synic_message_page) { - ret = set_memory_encrypted((unsigned long) - hv_cpu->synic_message_page, 1); - if (ret) { - pr_err("Failed to encrypt SYNIC msg page: %d\n", ret); - hv_cpu->synic_message_page = NULL; - } - } - - if (hv_cpu->synic_event_page) { - ret = set_memory_encrypted((unsigned long) - hv_cpu->synic_event_page, 1); - if (ret) { - pr_err("Failed to encrypt SYNIC event page: %d\n", ret); - hv_cpu->synic_event_page = NULL; - } - } + if (vmbus_is_confidential()) { + hv_free_page(&hv_cpu->para_synic_event_page, + false, "paravisor SynIC event"); + hv_free_page(&hv_cpu->para_synic_message_page, + false, "paravisor SynIC msg"); } - - free_page((unsigned long)hv_cpu->post_msg_page); - free_page((unsigned long)hv_cpu->synic_event_page); - free_page((unsigned long)hv_cpu->synic_message_page); } kfree(hv_context.hv_numa_map); @@ -278,12 +282,12 @@ void hv_synic_enable_regs(unsigned int cpu) /* Mask out vTOM bit. ioremap_cache() maps decrypted */ u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) & ~ms_hyperv.shared_gpa_boundary; - hv_cpu->synic_message_page = + hv_cpu->hyp_synic_message_page = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); - if (!hv_cpu->synic_message_page) + if (!hv_cpu->hyp_synic_message_page) pr_err("Fail to map synic message page.\n"); } else { - simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page) + simp.base_simp_gpa = virt_to_phys(hv_cpu->hyp_synic_message_page) >> HV_HYP_PAGE_SHIFT; } @@ -297,12 +301,12 @@ void hv_synic_enable_regs(unsigned int cpu) /* Mask out vTOM bit. ioremap_cache() maps decrypted */ u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) & ~ms_hyperv.shared_gpa_boundary; - hv_cpu->synic_event_page = + hv_cpu->hyp_synic_event_page = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); - if (!hv_cpu->synic_event_page) + if (!hv_cpu->hyp_synic_event_page) pr_err("Fail to map synic event page.\n"); } else { - siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page) + siefp.base_siefp_gpa = virt_to_phys(hv_cpu->hyp_synic_event_page) >> HV_HYP_PAGE_SHIFT; } @@ -360,8 +364,8 @@ void hv_synic_disable_regs(unsigned int cpu) */ simp.simp_enabled = 0; if (ms_hyperv.paravisor_present || hv_root_partition()) { - iounmap(hv_cpu->synic_message_page); - hv_cpu->synic_message_page = NULL; + iounmap(hv_cpu->hyp_synic_message_page); + hv_cpu->hyp_synic_message_page = NULL; } else { simp.base_simp_gpa = 0; } @@ -372,8 +376,8 @@ void hv_synic_disable_regs(unsigned int cpu) siefp.siefp_enabled = 0; if (ms_hyperv.paravisor_present || hv_root_partition()) { - iounmap(hv_cpu->synic_event_page); - hv_cpu->synic_event_page = NULL; + iounmap(hv_cpu->hyp_synic_event_page); + hv_cpu->hyp_synic_event_page = NULL; } else { siefp.base_siefp_gpa = 0; } @@ -403,7 +407,7 @@ static bool hv_synic_event_pending(void) { struct hv_per_cpu_context *hv_cpu = this_cpu_ptr(hv_context.cpu_context); union hv_synic_event_flags *event = - (union hv_synic_event_flags *)hv_cpu->synic_event_page + VMBUS_MESSAGE_SINT; + (union hv_synic_event_flags *)hv_cpu->hyp_synic_event_page + VMBUS_MESSAGE_SINT; unsigned long *recv_int_page = event->flags; /* assumes VMBus version >= VERSION_WIN8 */ bool pending; u32 relid; diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 34943de7d6ac..39cdded062e8 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -120,8 +120,26 @@ enum { * Per cpu state for channel handling */ struct hv_per_cpu_context { - void *synic_message_page; - void *synic_event_page; + /* + * SynIC pages for communicating with the host. + * + * These pages are accessible to the host partition and the hypervisor. + * They may be used for exchanging data with the host partition and the + * hypervisor even when they aren't trusted yet the guest partition + * must be prepared to handle the malicious behavior. + */ + void *hyp_synic_message_page; + void *hyp_synic_event_page; + /* + * SynIC pages for communicating with the paravisor. + * + * These pages may be accessed from within the guest partition only in + * CoCo VMs. Neither the host partition nor the hypervisor can access + * these pages in that case; they are used for exchanging data with the + * paravisor. + */ + void *para_synic_message_page; + void *para_synic_event_page; /* * The page is only used in hv_post_message() for a TDX VM (with the diff --git a/drivers/hv/mshv_eventfd.c b/drivers/hv/mshv_eventfd.c index 40b7179fee80..161a9655aa0b 100644 --- a/drivers/hv/mshv_eventfd.c +++ b/drivers/hv/mshv_eventfd.c @@ -164,10 +164,19 @@ static int mshv_try_assert_irq_fast(struct mshv_irqfd *irqfd) if (hv_scheduler_type != HV_SCHEDULER_TYPE_ROOT) return -EOPNOTSUPP; +#if IS_ENABLED(CONFIG_X86) if (irq->lapic_control.logical_dest_mode) return -EOPNOTSUPP; +#endif - vp = partition->pt_vp_array[irq->lapic_apic_id]; + /* + * Pairs with smp_store_release() in mshv_partition_ioctl_create_vp(). + * MSHV_IRQFD does not require the target lapic_apic_id to refer to an + * existing VP, so this read can race a concurrent VP creation; the + * acquire ensures that a non-NULL pointer implies the VP's + * initialising stores are visible. + */ + vp = smp_load_acquire(&partition->pt_vp_array[irq->lapic_apic_id]); if (!vp->vp_register_page) return -EOPNOTSUPP; @@ -197,8 +206,10 @@ static void mshv_assert_irq_slow(struct mshv_irqfd *irqfd) unsigned int seq; int idx; +#if IS_ENABLED(CONFIG_X86) WARN_ON(irqfd->irqfd_resampler && !irq->lapic_control.level_triggered); +#endif idx = srcu_read_lock(&partition->pt_irq_srcu); if (irqfd->irqfd_girq_ent.guest_irq_num) { @@ -280,7 +291,7 @@ static void mshv_irqfd_deactivate(struct mshv_irqfd *irqfd) if (!mshv_irqfd_is_active(irqfd)) return; - hlist_del(&irqfd->irqfd_hnode); + hlist_del_init(&irqfd->irqfd_hnode); queue_work(irqfd_cleanup_wq, &irqfd->irqfd_shutdown); } @@ -469,16 +480,6 @@ static int mshv_irqfd_assign(struct mshv_partition *pt, init_poll_funcptr(&irqfd->irqfd_polltbl, mshv_irqfd_queue_proc); spin_lock_irq(&pt->pt_irqfds_lock); - if (args->flags & BIT(MSHV_IRQFD_BIT_RESAMPLE) && - !irqfd->irqfd_lapic_irq.lapic_control.level_triggered) { - /* - * Resample Fd must be for level triggered interrupt - * Otherwise return with failure - */ - spin_unlock_irq(&pt->pt_irqfds_lock); - ret = -EINVAL; - goto fail; - } ret = 0; hlist_for_each_entry(tmp, &pt->pt_irqfds_list, irqfd_hnode) { if (irqfd->irqfd_eventfd_ctx != tmp->irqfd_eventfd_ctx) @@ -491,6 +492,21 @@ static int mshv_irqfd_assign(struct mshv_partition *pt, idx = srcu_read_lock(&pt->pt_irq_srcu); mshv_irqfd_update(pt, irqfd); + +#if IS_ENABLED(CONFIG_X86) + if (args->flags & BIT(MSHV_IRQFD_BIT_RESAMPLE) && + !irqfd->irqfd_lapic_irq.lapic_control.level_triggered) { + /* + * Resample Fd must be for level triggered interrupt + * Otherwise return with failure + */ + spin_unlock_irq(&pt->pt_irqfds_lock); + srcu_read_unlock(&pt->pt_irq_srcu, idx); + ret = -EINVAL; + goto fail; + } +#endif + hlist_add_head(&irqfd->irqfd_hnode, &pt->pt_irqfds_list); spin_unlock_irq(&pt->pt_irqfds_lock); @@ -535,13 +551,14 @@ static int mshv_irqfd_deassign(struct mshv_partition *pt, if (IS_ERR(eventfd)) return PTR_ERR(eventfd); + spin_lock_irq(&pt->pt_irqfds_lock); hlist_for_each_entry_safe(irqfd, n, &pt->pt_irqfds_list, irqfd_hnode) { if (irqfd->irqfd_eventfd_ctx == eventfd && irqfd->irqfd_irqnum == args->gsi) - mshv_irqfd_deactivate(irqfd); } + spin_unlock_irq(&pt->pt_irqfds_lock); eventfd_ctx_put(eventfd); diff --git a/drivers/hv/mshv_irq.c b/drivers/hv/mshv_irq.c index d0fb9ef734f4..7422a36199b4 100644 --- a/drivers/hv/mshv_irq.c +++ b/drivers/hv/mshv_irq.c @@ -51,7 +51,7 @@ int mshv_update_routing_table(struct mshv_partition *partition, /* * Allow only one to one mapping between GSI and MSI routing. */ - if (girq->guest_irq_num != 0) { + if (girq->girq_entry_valid) { r = -EINVAL; goto out; } @@ -119,6 +119,10 @@ void mshv_copy_girq_info(struct mshv_guest_irq_ent *ent, lirq->lapic_vector = ent->girq_irq_data & 0xFF; lirq->lapic_apic_id = (ent->girq_addr_lo >> 12) & 0xFF; lirq->lapic_control.interrupt_type = (ent->girq_irq_data & 0x700) >> 8; +#if IS_ENABLED(CONFIG_X86) lirq->lapic_control.level_triggered = (ent->girq_irq_data >> 15) & 0x1; lirq->lapic_control.logical_dest_mode = (ent->girq_addr_lo >> 2) & 0x1; +#elif IS_ENABLED(CONFIG_ARM64) + lirq->lapic_control.asserted = 1; +#endif } diff --git a/drivers/hv/mshv_portid_table.c b/drivers/hv/mshv_portid_table.c index c349af1f0aaa..6f59b3e37624 100644 --- a/drivers/hv/mshv_portid_table.c +++ b/drivers/hv/mshv_portid_table.c @@ -40,12 +40,14 @@ mshv_port_table_fini(void) int mshv_portid_alloc(struct port_table_info *info) { - int ret = 0; + int ret; + idr_preload(GFP_KERNEL); idr_lock(&port_table_idr); ret = idr_alloc(&port_table_idr, info, PORTID_MIN, - PORTID_MAX, GFP_KERNEL); + PORTID_MAX, GFP_NOWAIT); idr_unlock(&port_table_idr); + idr_preload_end(); return ret; } diff --git a/drivers/hv/mshv_root.h b/drivers/hv/mshv_root.h index e3931b0f1269..db6b42db2fdc 100644 --- a/drivers/hv/mshv_root.h +++ b/drivers/hv/mshv_root.h @@ -169,7 +169,7 @@ struct mshv_girq_routing_table { }; struct hv_synic_pages { - struct hv_message_page *synic_message_page; + struct hv_message_page *hyp_synic_message_page; struct hv_synic_event_flags_page *synic_event_flags_page; struct hv_synic_event_ring_page *synic_event_ring_page; }; diff --git a/drivers/hv/mshv_root_hv_call.c b/drivers/hv/mshv_root_hv_call.c index c9c274f29c3c..a23b5ba09fb4 100644 --- a/drivers/hv/mshv_root_hv_call.c +++ b/drivers/hv/mshv_root_hv_call.c @@ -388,7 +388,13 @@ int hv_call_assert_virtual_interrupt(u64 partition_id, u32 vector, memset(input, 0, sizeof(*input)); input->partition_id = partition_id; input->vector = vector; + /* + * NOTE: dest_addr only needs to be provided while asserting an + * interrupt on x86 platform + */ +#if IS_ENABLED(CONFIG_X86) input->dest_addr = dest_addr; +#endif input->control = control; status = hv_do_hypercall(HVCALL_ASSERT_VIRTUAL_INTERRUPT, input, NULL); local_irq_restore(flags); diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c index 4e04bef54437..3a356b34774b 100644 --- a/drivers/hv/mshv_root_main.c +++ b/drivers/hv/mshv_root_main.c @@ -979,7 +979,13 @@ mshv_partition_ioctl_create_vp(struct mshv_partition *partition, /* already exclusive with the partition mutex for all ioctls */ partition->pt_vp_count++; - partition->pt_vp_array[args.vp_index] = vp; + /* + * Pairs with smp_load_acquire() in mshv_try_assert_irq_fast(), which + * can run concurrently from an irqfd waker without holding pt_mutex. + * The release ensures the VP's initialising stores are visible to any + * reader that observes a non-NULL pointer in pt_vp_array. + */ + smp_store_release(&partition->pt_vp_array[args.vp_index], vp); return ret; diff --git a/drivers/hv/mshv_synic.c b/drivers/hv/mshv_synic.c index 1a822beae239..3c65b1c4abbe 100644 --- a/drivers/hv/mshv_synic.c +++ b/drivers/hv/mshv_synic.c @@ -399,7 +399,7 @@ mshv_intercept_isr(struct hv_message *msg) void mshv_isr(void) { struct hv_synic_pages *spages = this_cpu_ptr(mshv_root.synic_pages); - struct hv_message_page **msg_page = &spages->synic_message_page; + struct hv_message_page **msg_page = &spages->hyp_synic_message_page; struct hv_message *msg; bool handled; @@ -461,7 +461,7 @@ int mshv_synic_init(unsigned int cpu) #endif union hv_synic_scontrol sctrl; struct hv_synic_pages *spages = this_cpu_ptr(mshv_root.synic_pages); - struct hv_message_page **msg_page = &spages->synic_message_page; + struct hv_message_page **msg_page = &spages->hyp_synic_message_page; struct hv_synic_event_flags_page **event_flags_page = &spages->synic_event_flags_page; struct hv_synic_event_ring_page **event_ring_page = @@ -555,7 +555,7 @@ int mshv_synic_cleanup(unsigned int cpu) union hv_synic_sirbp sirbp; union hv_synic_scontrol sctrl; struct hv_synic_pages *spages = this_cpu_ptr(mshv_root.synic_pages); - struct hv_message_page **msg_page = &spages->synic_message_page; + struct hv_message_page **msg_page = &spages->hyp_synic_message_page; struct hv_synic_event_flags_page **event_flags_page = &spages->synic_event_flags_page; struct hv_synic_event_ring_page **event_ring_page = diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 1a0e350c1940..4f1f5f294a73 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1048,7 +1048,7 @@ static void vmbus_onmessage_work(struct work_struct *work) void vmbus_on_msg_dpc(unsigned long data) { struct hv_per_cpu_context *hv_cpu = (void *)data; - void *page_addr = hv_cpu->synic_message_page; + void *page_addr = hv_cpu->hyp_synic_message_page; struct hv_message msg_copy, *msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT; struct vmbus_channel_message_header *hdr; @@ -1232,7 +1232,7 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu) * The event page can be directly checked to get the id of * the channel that has the interrupt pending. */ - void *page_addr = hv_cpu->synic_event_page; + void *page_addr = hv_cpu->hyp_synic_event_page; union hv_synic_event_flags *event = (union hv_synic_event_flags *)page_addr + VMBUS_MESSAGE_SINT; @@ -1315,7 +1315,7 @@ static void __vmbus_isr(void) vmbus_chan_sched(hv_cpu); - page_addr = hv_cpu->synic_message_page; + page_addr = hv_cpu->hyp_synic_message_page; msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT; /* Check if there are actual msgs to be processed */ @@ -1372,8 +1372,19 @@ static void vmbus_isr(void) if (IS_ENABLED(CONFIG_PREEMPT_RT)) { vmbus_irqd_wake(); } else { - lockdep_hardirq_threaded(); + static DEFINE_WAIT_OVERRIDE_MAP(vmbus_map, LD_WAIT_CONFIG); + + /* + * vmbus_isr is never force-threaded and always invoked at hard + * IRQ level. __vmbus_isr() below can acquire a spinlock_t + * which becomes a sleeping lock and must not be acquired in + * this context. Therefore on PREEMPT_RT this will be threaded + * via vmbus_irqd_wake(). On non-PREEMPT the annotation lets + * lockdep know that acquiring a spinlock_t is not an issue. + */ + lock_map_acquire_try(&vmbus_map); __vmbus_isr(); + lock_map_release(&vmbus_map); } } diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index c8a7e45e8006..4d852e68b474 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -2275,7 +2275,7 @@ config SENSORS_INA2XX select REGMAP_I2C help If you say yes here you get support for INA219, INA220, INA226, - INA230, INA231, INA260, and SY24655 power monitor chips. + INA230, INA231, INA234, INA260, and SY24655 power monitor chips. The INA2xx driver is configured for the default configuration of the part as described in the datasheet. diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c index dbee6926fa05..0fad4bfe53df 100644 --- a/drivers/hwmon/adt7470.c +++ b/drivers/hwmon/adt7470.c @@ -70,8 +70,8 @@ static const unsigned short normal_i2c[] = { 0x2C, 0x2E, 0x2F, I2C_CLIENT_END }; #define ADT7470_PWM1_AUTO_MASK 0x80 #define ADT7470_PWM_AUTO_MASK 0xC0 #define ADT7470_REG_PWM34_CFG 0x69 -#define ADT7470_PWM3_AUTO_MASK 0x40 -#define ADT7470_PWM4_AUTO_MASK 0x80 +#define ADT7470_PWM4_AUTO_MASK 0x40 +#define ADT7470_PWM3_AUTO_MASK 0x80 #define ADT7470_REG_PWM_MIN_BASE_ADDR 0x6A #define ADT7470_REG_PWM_MIN_MAX_ADDR 0x6D #define ADT7470_REG_PWM_TEMP_MIN_BASE_ADDR 0x6E @@ -110,6 +110,21 @@ static const unsigned short normal_i2c[] = { 0x2C, 0x2E, 0x2F, I2C_CLIENT_END }; #define ALARM2(x) ((x) << 8) +/* TEMP1..TEMP7 (ch 0..6) are, respectively BIT(0)..BIT(6) of reg 0x41 and + * 0x72, or BIT(0)..BIT(6) of data->alarm. + * TEMP8..TEMP9 (ch 7..9) are, respectively BIT(0)..BIT(2) of reg 0x42 and + * 0x73, or BIT(8)..BIT(10) of data->alarm. + */ +#define TEMP_ALARM_BIT(ch) ({ \ + typeof(ch) _ch = (ch); \ + (1 << (_ch < 7 ? _ch : _ch + 1)); \ +}) + +/* FAN1..FAN4 (ch 0..3) are respectively BIT(4)..BIT(7) in + * reg 0x42 and 0x73 or BIT(12)..BIT(15) in data->alarm. + */ +#define FAN_ALARM_BIT(ch) (1 << (12 + (ch))) + #define ADT7470_VENDOR 0x41 #define ADT7470_DEVICE 0x70 /* datasheet only mentions a revision 2 */ @@ -167,6 +182,7 @@ struct adt7470_data { u8 pwm_min[ADT7470_PWM_COUNT]; s8 pwm_tmin[ADT7470_PWM_COUNT]; u8 pwm_auto_temp[ADT7470_PWM_COUNT]; + u32 pwm_freq; struct task_struct *auto_update; unsigned int auto_update_interval; @@ -205,11 +221,12 @@ static inline int adt7470_write_word_data(struct adt7470_data *data, unsigned in /* Probe for temperature sensors. Assumes lock is held */ static int adt7470_read_temperatures(struct adt7470_data *data) { - unsigned long res; + struct device *dev = regmap_get_device(data->regmap); + u8 pwm[ADT7470_FAN_COUNT]; unsigned int pwm_cfg[2]; - int err; + unsigned long res; + int err, err2; int i; - u8 pwm[ADT7470_FAN_COUNT]; /* save pwm[1-4] config register */ err = regmap_read(data->regmap, ADT7470_REG_PWM_CFG(0), &pwm_cfg[0]); @@ -233,19 +250,19 @@ static int adt7470_read_temperatures(struct adt7470_data *data) err = regmap_update_bits(data->regmap, ADT7470_REG_PWM_CFG(2), ADT7470_PWM_AUTO_MASK, 0); if (err < 0) - return err; + goto out_restore; /* write pwm control to whatever it was */ err = regmap_bulk_write(data->regmap, ADT7470_REG_PWM(0), &pwm[0], ADT7470_PWM_COUNT); if (err < 0) - return err; + goto out_restore; /* start reading temperature sensors */ err = regmap_update_bits(data->regmap, ADT7470_REG_CFG, ADT7470_T05_STB_MASK, ADT7470_T05_STB_MASK); if (err < 0) - return err; + goto out_restore; /* Delay is 200ms * number of temp sensors. */ res = msleep_interruptible((data->num_temp_sensors >= 0 ? @@ -256,13 +273,30 @@ static int adt7470_read_temperatures(struct adt7470_data *data) err = regmap_update_bits(data->regmap, ADT7470_REG_CFG, ADT7470_T05_STB_MASK, 0); if (err < 0) - return err; + goto out_restore; +out_restore: /* restore pwm[1-4] config registers */ - err = regmap_write(data->regmap, ADT7470_REG_PWM_CFG(0), pwm_cfg[0]); - if (err < 0) - return err; - err = regmap_write(data->regmap, ADT7470_REG_PWM_CFG(2), pwm_cfg[1]); + err2 = regmap_write(data->regmap, ADT7470_REG_PWM_CFG(0), pwm_cfg[0]); + if (err2 < 0) { + dev_warn_ratelimited(dev, + "failed to restore PWM{1,2} config (%d)\n", + err2); + + if (!err) + err = err2; + } + + err2 = regmap_write(data->regmap, ADT7470_REG_PWM_CFG(2), pwm_cfg[1]); + if (err2 < 0) { + dev_warn_ratelimited(dev, + "failed to restore PWM{3,4} config (%d)\n", + err2); + + if (!err) + err = err2; + } + if (err < 0) return err; @@ -491,7 +525,7 @@ static ssize_t auto_update_interval_store(struct device *dev, if (kstrtol(buf, 10, &temp)) return -EINVAL; - temp = clamp_val(temp, 0, 60000); + temp = clamp_val(temp, 500, 60000); mutex_lock(&data->lock); data->auto_update_interval = temp; @@ -551,7 +585,7 @@ static int adt7470_temp_read(struct device *dev, u32 attr, int channel, long *va *val = 1000 * data->temp_max[channel]; break; case hwmon_temp_alarm: - *val = !!(data->alarm & channel); + *val = !!(data->alarm & TEMP_ALARM_BIT(channel)); break; default: return -EOPNOTSUPP; @@ -571,14 +605,16 @@ static int adt7470_temp_write(struct device *dev, u32 attr, int channel, long va switch (attr) { case hwmon_temp_min: mutex_lock(&data->lock); - data->temp_min[channel] = val; err = regmap_write(data->regmap, ADT7470_TEMP_MIN_REG(channel), val); + if (!err) + data->temp_min[channel] = val; mutex_unlock(&data->lock); break; case hwmon_temp_max: mutex_lock(&data->lock); - data->temp_max[channel] = val; err = regmap_write(data->regmap, ADT7470_TEMP_MAX_REG(channel), val); + if (!err) + data->temp_max[channel] = val; mutex_unlock(&data->lock); break; default: @@ -624,36 +660,33 @@ static ssize_t alarm_mask_store(struct device *dev, static int adt7470_fan_read(struct device *dev, u32 attr, int channel, long *val) { struct adt7470_data *data = adt7470_update_device(dev); + u16 fan_data; if (IS_ERR(data)) return PTR_ERR(data); switch (attr) { case hwmon_fan_input: - if (FAN_DATA_VALID(data->fan[channel])) - *val = FAN_PERIOD_TO_RPM(data->fan[channel]); - else - *val = 0; + fan_data = READ_ONCE(data->fan[channel]); break; case hwmon_fan_min: - if (FAN_DATA_VALID(data->fan_min[channel])) - *val = FAN_PERIOD_TO_RPM(data->fan_min[channel]); - else - *val = 0; + fan_data = READ_ONCE(data->fan_min[channel]); break; case hwmon_fan_max: - if (FAN_DATA_VALID(data->fan_max[channel])) - *val = FAN_PERIOD_TO_RPM(data->fan_max[channel]); - else - *val = 0; + fan_data = READ_ONCE(data->fan_max[channel]); break; case hwmon_fan_alarm: - *val = !!(data->alarm & (1 << (12 + channel))); - break; + *val = !!(data->alarm & FAN_ALARM_BIT(channel)); + return 0; default: return -EOPNOTSUPP; } + if (FAN_DATA_VALID(fan_data)) + *val = FAN_PERIOD_TO_RPM(fan_data); + else + *val = 0; + return 0; } @@ -721,7 +754,7 @@ static ssize_t force_pwm_max_store(struct device *dev, } /* These are the valid PWM frequencies to the nearest Hz */ -static const int adt7470_freq_map[] = { +static const u32 adt7470_freq_map[] = { 11, 15, 22, 29, 35, 44, 59, 88, 1400, 22500 }; @@ -761,7 +794,7 @@ static int adt7470_pwm_read(struct device *dev, u32 attr, int channel, long *val *val = 1 + data->pwm_automatic[channel]; break; case hwmon_pwm_freq: - *val = pwm1_freq_get(dev); + *val = data->pwm_freq; break; default: return -EOPNOTSUPP; @@ -774,12 +807,14 @@ static int pwm1_freq_set(struct device *dev, long freq) { struct adt7470_data *data = dev_get_drvdata(dev); unsigned int low_freq = ADT7470_CFG_LF; + u32 closest_freq; int index; int err; /* Round the user value given to the closest available frequency */ index = find_closest(freq, adt7470_freq_map, ARRAY_SIZE(adt7470_freq_map)); + closest_freq = adt7470_freq_map[index]; if (index >= 8) { index -= 8; @@ -797,6 +832,10 @@ static int pwm1_freq_set(struct device *dev, long freq) err = regmap_update_bits(data->regmap, ADT7470_REG_CFG_2, ADT7470_FREQ_MASK, index << ADT7470_FREQ_SHIFT); + if (err < 0) + goto out; + + data->pwm_freq = closest_freq; out: mutex_unlock(&data->lock); @@ -813,9 +852,10 @@ static int adt7470_pwm_write(struct device *dev, u32 attr, int channel, long val case hwmon_pwm_input: val = clamp_val(val, 0, 255); mutex_lock(&data->lock); - data->pwm[channel] = val; err = regmap_write(data->regmap, ADT7470_REG_PWM(channel), - data->pwm[channel]); + val); + if (!err) + data->pwm[channel] = val; mutex_unlock(&data->lock); break; case hwmon_pwm_enable: @@ -829,10 +869,11 @@ static int adt7470_pwm_write(struct device *dev, u32 attr, int channel, long val val--; mutex_lock(&data->lock); - data->pwm_automatic[channel] = val; err = regmap_update_bits(data->regmap, ADT7470_REG_PWM_CFG(channel), pwm_auto_reg_mask, val ? pwm_auto_reg_mask : 0); + if (!err) + data->pwm_automatic[channel] = val; mutex_unlock(&data->lock); break; case hwmon_pwm_freq: @@ -1008,8 +1049,10 @@ static ssize_t pwm_auto_temp_store(struct device *dev, if (temp < 0) return temp; + if (temp > 0xF) + return -EINVAL; + mutex_lock(&data->lock); - data->pwm_automatic[attr->index] = temp; if (!(attr->index % 2)) { mask = 0xF0; @@ -1020,6 +1063,9 @@ static ssize_t pwm_auto_temp_store(struct device *dev, } err = regmap_update_bits(data->regmap, pwm_auto_reg, mask, val); + if (!err) + data->pwm_auto_temp[attr->index] = temp; + mutex_unlock(&data->lock); return err < 0 ? err : count; @@ -1248,6 +1294,7 @@ static int adt7470_probe(struct i2c_client *client) struct device *dev = &client->dev; struct adt7470_data *data; struct device *hwmon_dev; + int freq_val; int err; data = devm_kzalloc(dev, sizeof(struct adt7470_data), GFP_KERNEL); @@ -1272,6 +1319,14 @@ static int adt7470_probe(struct i2c_client *client) if (err < 0) return err; + freq_val = pwm1_freq_get(dev); + if (freq_val <= 0) { + err = freq_val < 0 ? freq_val : -EINVAL; + return err; + } + + data->pwm_freq = (u32)freq_val; + /* Register sysfs hooks */ hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, data, &adt7470_chip_info, diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index bc3c1f7314b3..9c2dc9c0fd4d 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -31,6 +31,7 @@ #include <linux/i2c.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/limits.h> #include <linux/module.h> #include <linux/property.h> #include <linux/regmap.h> @@ -135,18 +136,27 @@ static const struct regmap_config ina2xx_regmap_config = { .writeable_reg = ina2xx_writeable_reg, }; -enum ina2xx_ids { ina219, ina226, ina260, sy24655 }; +enum ina2xx_ids { + ina219, + ina226, + ina234, + ina260, + sy24655 +}; struct ina2xx_config { u16 config_default; bool has_alerts; /* chip supports alerts and limits */ bool has_ishunt; /* chip has internal shunt resistor */ - bool has_power_average; /* chip has internal shunt resistor */ + bool has_power_average; /* chip supports average power */ + bool has_update_interval; int calibration_value; int shunt_div; + int shunt_voltage_shift; int bus_voltage_shift; int bus_voltage_lsb; /* uV */ int power_lsb_factor; + int current_shift; }; struct ina2xx_data { @@ -166,44 +176,70 @@ static const struct ina2xx_config ina2xx_config[] = { .config_default = INA219_CONFIG_DEFAULT, .calibration_value = 4096, .shunt_div = 100, + .shunt_voltage_shift = 0, .bus_voltage_shift = 3, .bus_voltage_lsb = 4000, .power_lsb_factor = 20, .has_alerts = false, .has_ishunt = false, .has_power_average = false, + .current_shift = 0, + .has_update_interval = false, }, [ina226] = { .config_default = INA226_CONFIG_DEFAULT, .calibration_value = 2048, .shunt_div = 400, + .shunt_voltage_shift = 0, .bus_voltage_shift = 0, .bus_voltage_lsb = 1250, .power_lsb_factor = 25, .has_alerts = true, .has_ishunt = false, .has_power_average = false, + .current_shift = 0, + .has_update_interval = true, + }, + [ina234] = { + .config_default = INA226_CONFIG_DEFAULT, + .calibration_value = 2048, + .shunt_div = 25, /* 2.5 µV/LSB raw ADC reading from INA2XX_SHUNT_VOLTAGE */ + .shunt_voltage_shift = 4, + .bus_voltage_shift = 4, + .bus_voltage_lsb = 25600, + .power_lsb_factor = 32, + .has_alerts = true, + .has_ishunt = false, + .has_power_average = false, + .current_shift = 4, + .has_update_interval = true, }, [ina260] = { .config_default = INA260_CONFIG_DEFAULT, .shunt_div = 400, + .shunt_voltage_shift = 0, .bus_voltage_shift = 0, .bus_voltage_lsb = 1250, .power_lsb_factor = 8, .has_alerts = true, .has_ishunt = true, .has_power_average = false, + .current_shift = 0, + .has_update_interval = true, }, [sy24655] = { .config_default = SY24655_CONFIG_DEFAULT, .calibration_value = 4096, .shunt_div = 400, + .shunt_voltage_shift = 0, .bus_voltage_shift = 0, .bus_voltage_lsb = 1250, .power_lsb_factor = 25, .has_alerts = true, .has_ishunt = false, .has_power_average = true, + .current_shift = 0, + .has_update_interval = false, }, }; @@ -248,28 +284,34 @@ static u16 ina226_interval_to_reg(long interval) return FIELD_PREP(INA226_AVG_RD_MASK, avg_bits); } -static int ina2xx_get_value(struct ina2xx_data *data, u8 reg, - unsigned int regval) +static long ina2xx_get_value(struct ina2xx_data *data, u8 reg, + unsigned int regval) { - int val; + s64 val64; + long val; switch (reg) { case INA2XX_SHUNT_VOLTAGE: /* signed register */ - val = DIV_ROUND_CLOSEST((s16)regval, data->config->shunt_div); + val = DIV_ROUND_CLOSEST((s16)regval >> data->config->shunt_voltage_shift, + data->config->shunt_div); break; case INA2XX_BUS_VOLTAGE: - val = (regval >> data->config->bus_voltage_shift) * - data->config->bus_voltage_lsb; - val = DIV_ROUND_CLOSEST(val, 1000); + val = DIV_ROUND_CLOSEST((regval >> data->config->bus_voltage_shift) * + data->config->bus_voltage_lsb, 1000); break; case INA2XX_POWER: - val = regval * data->power_lsb_uW; + val = min_t(u64, (u64)regval * data->power_lsb_uW, LONG_MAX); break; case INA2XX_CURRENT: /* signed register, result in mA */ - val = (s16)regval * data->current_lsb_uA; - val = DIV_ROUND_CLOSEST(val, 1000); + val64 = (s64)((s16)regval >> data->config->current_shift) * + data->current_lsb_uA; + if (val64 < 0) + val64 = -DIV_ROUND_CLOSEST_ULL(-val64, 1000); + else + val64 = DIV_ROUND_CLOSEST_ULL(val64, 1000); + val = clamp_val(val64, LONG_MIN, LONG_MAX); break; case INA2XX_CALIBRATION: val = regval; @@ -358,25 +400,29 @@ static int ina2xx_read_init(struct device *dev, int reg, long *val) */ static u16 ina226_alert_to_reg(struct ina2xx_data *data, int reg, long val) { + long limit; + switch (reg) { case INA2XX_SHUNT_VOLTAGE: - val = clamp_val(val, 0, SHRT_MAX * data->config->shunt_div); - val *= data->config->shunt_div; - return clamp_val(val, 0, SHRT_MAX); + val = min_t(long, val, DIV_ROUND_CLOSEST(SHRT_MAX, data->config->shunt_div)); + return min_t(long, (val * data->config->shunt_div) << data->config->shunt_voltage_shift, + SHRT_MAX); case INA2XX_BUS_VOLTAGE: - val = clamp_val(val, 0, 200000); - val = (val * 1000) << data->config->bus_voltage_shift; - val = DIV_ROUND_CLOSEST(val, data->config->bus_voltage_lsb); - return clamp_val(val, 0, USHRT_MAX); + val = min_t(long, val, 130000); + return min_t(long, + DIV_ROUND_CLOSEST((val * 1000) << data->config->bus_voltage_shift, + data->config->bus_voltage_lsb), + USHRT_MAX); case INA2XX_POWER: - val = clamp_val(val, 0, UINT_MAX - data->power_lsb_uW); - val = DIV_ROUND_CLOSEST(val, data->power_lsb_uW); - return clamp_val(val, 0, USHRT_MAX); + val = min_t(long, val, LONG_MAX - data->power_lsb_uW); + return min_t(long, DIV_ROUND_CLOSEST(val, data->power_lsb_uW), USHRT_MAX); case INA2XX_CURRENT: - val = clamp_val(val, INT_MIN / 1000, INT_MAX / 1000); + limit = (LONG_MAX - (data->current_lsb_uA / 2)) / 1000; + val = min_t(long, val, limit); /* signed register, result in mA */ val = DIV_ROUND_CLOSEST(val * 1000, data->current_lsb_uA); - return clamp_val(val, SHRT_MIN, SHRT_MAX); + limit = SHRT_MAX >> data->config->current_shift; + return (u16)(min_t(long, val, limit) << data->config->current_shift); default: /* programmer goofed */ WARN_ON_ONCE(1); @@ -521,6 +567,7 @@ static int sy24655_average_power_read(struct ina2xx_data *data, u8 reg, long *va u8 template[6]; int ret; long accumulator_24, sample_count; + u64 val64; /* 48-bit register read */ ret = i2c_smbus_read_i2c_block_data(data->client, reg, 6, template); @@ -539,7 +586,8 @@ static int sy24655_average_power_read(struct ina2xx_data *data, u8 reg, long *va return 0; } - *val = DIV_ROUND_CLOSEST(accumulator_24, sample_count) * data->power_lsb_uW; + val64 = (u64)DIV_ROUND_CLOSEST(accumulator_24, sample_count) * data->power_lsb_uW; + *val = min_t(u64, val64, LONG_MAX); return 0; } @@ -713,7 +761,7 @@ static umode_t ina2xx_is_visible(const void *_data, enum hwmon_sensor_types type const struct ina2xx_data *data = _data; bool has_alerts = data->config->has_alerts; bool has_power_average = data->config->has_power_average; - enum ina2xx_ids chip = data->chip; + bool has_update_interval = data->config->has_update_interval; switch (type) { case hwmon_in: @@ -775,7 +823,7 @@ static umode_t ina2xx_is_visible(const void *_data, enum hwmon_sensor_types type case hwmon_chip: switch (attr) { case hwmon_chip_update_interval: - if (chip == ina226 || chip == ina260) + if (has_update_interval) return 0644; break; default: @@ -990,6 +1038,7 @@ static const struct i2c_device_id ina2xx_id[] = { { "ina226", ina226 }, { "ina230", ina226 }, { "ina231", ina226 }, + { "ina234", ina234 }, { "ina260", ina260 }, { "sy24655", sy24655 }, { } @@ -1021,6 +1070,10 @@ static const struct of_device_id __maybe_unused ina2xx_of_match[] = { .compatible = "ti,ina231", .data = (void *)ina226 }, + { + .compatible = "ti,ina234", + .data = (void *)ina234 + }, { .compatible = "ti,ina260", .data = (void *)ina260 diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c index a465a8a7ef5a..e1795ccde876 100644 --- a/drivers/hwmon/lm90.c +++ b/drivers/hwmon/lm90.c @@ -1196,7 +1196,7 @@ static int lm90_update_alarms_locked(struct lm90_data *data, bool force) check_enable = (client->irq || !(data->config_orig & 0x80)) && (data->config & 0x80); - if (force || check_enable) + if (data->hwmon_dev && (force || check_enable)) schedule_work(&data->report_work); /* @@ -1204,7 +1204,7 @@ static int lm90_update_alarms_locked(struct lm90_data *data, bool force) * alarms are all clear, and alerts are currently disabled. * Otherwise (re)schedule worker if needed. */ - if (check_enable) { + if (check_enable && data->hwmon_dev) { if (!(data->current_alarms & data->alert_alarms)) { dev_dbg(&client->dev, "Re-enabling ALERT#\n"); lm90_update_confreg(data, data->config & ~0x80); diff --git a/drivers/hwmon/ltc4282.c b/drivers/hwmon/ltc4282.c index 58c2d3a62432..4000bcbc7353 100644 --- a/drivers/hwmon/ltc4282.c +++ b/drivers/hwmon/ltc4282.c @@ -384,8 +384,8 @@ static int ltc4282_read_in(struct ltc4282_state *st, u32 attr, long *val, channel, val); case hwmon_in_min_alarm: if (channel == LTC4282_CHAN_VGPIO) - ltc4282_read_alarm(st, LTC4282_ADC_ALERT_LOG, - LTC4282_GPIO_ALARM_L_MASK, val); + return ltc4282_read_alarm(st, LTC4282_ADC_ALERT_LOG, + LTC4282_GPIO_ALARM_L_MASK, val); return ltc4282_vdd_source_read_alm(st, LTC4282_VSOURCE_ALARM_L_MASK, diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c index 79bc67ffb998..ce2cf1f22900 100644 --- a/drivers/hwmon/nct6775-core.c +++ b/drivers/hwmon/nct6775-core.c @@ -791,12 +791,12 @@ static const u16 NCT6106_REG_TOLERANCE_H[] = { 0x112, 0x122, 0x132 }; static const u16 NCT6106_REG_TARGET[] = { 0x111, 0x121, 0x131 }; -static const u16 NCT6106_REG_WEIGHT_TEMP_SEL[] = { 0x168, 0x178, 0x188 }; -static const u16 NCT6106_REG_WEIGHT_TEMP_STEP[] = { 0x169, 0x179, 0x189 }; -static const u16 NCT6106_REG_WEIGHT_TEMP_STEP_TOL[] = { 0x16a, 0x17a, 0x18a }; -static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x18b }; -static const u16 NCT6106_REG_WEIGHT_TEMP_BASE[] = { 0x16c, 0x17c, 0x18c }; -static const u16 NCT6106_REG_WEIGHT_DUTY_BASE[] = { 0x16d, 0x17d, 0x18d }; +static const u16 NCT6106_REG_WEIGHT_TEMP_SEL[] = { 0x168, 0x178, 0x188, 0, 0 }; +static const u16 NCT6106_REG_WEIGHT_TEMP_STEP[] = { 0x169, 0x179, 0x189, 0, 0 }; +static const u16 NCT6106_REG_WEIGHT_TEMP_STEP_TOL[] = { 0x16a, 0x17a, 0x18a, 0, 0 }; +static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x18b, 0, 0 }; +static const u16 NCT6106_REG_WEIGHT_TEMP_BASE[] = { 0x16c, 0x17c, 0x18c, 0, 0 }; +static const u16 NCT6106_REG_WEIGHT_DUTY_BASE[] = { 0x16d, 0x17d, 0x18d, 0, 0 }; static const u16 NCT6106_REG_AUTO_TEMP[] = { 0x160, 0x170, 0x180 }; static const u16 NCT6106_REG_AUTO_PWM[] = { 0x164, 0x174, 0x184 }; @@ -846,8 +846,6 @@ static const u16 NCT6116_FAN_PULSE_SHIFT[] = { 0, 2, 4, 6, 6 }; static const u16 NCT6116_REG_PWM[] = { 0x119, 0x129, 0x139, 0x199, 0x1a9 }; static const u16 NCT6116_REG_FAN_MODE[] = { 0x113, 0x123, 0x133, 0x193, 0x1a3 }; static const u16 NCT6116_REG_TEMP_SEL[] = { 0x110, 0x120, 0x130, 0x190, 0x1a0 }; -static const u16 NCT6116_REG_TEMP_SOURCE[] = { - 0xb0, 0xb1, 0xb2 }; static const u16 NCT6116_REG_CRITICAL_TEMP[] = { 0x11a, 0x12a, 0x13a, 0x19a, 0x1aa }; @@ -3650,7 +3648,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, = NCT6106_CRITICAL_PWM_ENABLE_MASK; data->REG_CRITICAL_PWM = NCT6116_REG_CRITICAL_PWM; data->REG_TEMP_OFFSET = NCT6106_REG_TEMP_OFFSET; - data->REG_TEMP_SOURCE = NCT6116_REG_TEMP_SOURCE; + data->REG_TEMP_SOURCE = NCT6106_REG_TEMP_SOURCE; data->REG_TEMP_SEL = NCT6116_REG_TEMP_SEL; data->REG_WEIGHT_TEMP_SEL = NCT6106_REG_WEIGHT_TEMP_SEL; data->REG_WEIGHT_TEMP[0] = NCT6106_REG_WEIGHT_TEMP_STEP; @@ -3664,13 +3662,13 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, reg_temp = NCT6106_REG_TEMP; reg_temp_mon = NCT6106_REG_TEMP_MON; - num_reg_temp = ARRAY_SIZE(NCT6106_REG_TEMP); + num_reg_temp = 3; num_reg_temp_mon = ARRAY_SIZE(NCT6106_REG_TEMP_MON); num_reg_tsi_temp = ARRAY_SIZE(NCT6116_REG_TSI_TEMP); reg_temp_over = NCT6106_REG_TEMP_OVER; reg_temp_hyst = NCT6106_REG_TEMP_HYST; reg_temp_config = NCT6106_REG_TEMP_CONFIG; - num_reg_temp_config = ARRAY_SIZE(NCT6106_REG_TEMP_CONFIG); + num_reg_temp_config = 3; reg_temp_alternate = NCT6106_REG_TEMP_ALTERNATE; reg_temp_crit = NCT6106_REG_TEMP_CRIT; reg_temp_crit_l = NCT6106_REG_TEMP_CRIT_L; diff --git a/drivers/hwmon/npcm750-pwm-fan.c b/drivers/hwmon/npcm750-pwm-fan.c index 802c73def428..bb390f6c7c3f 100644 --- a/drivers/hwmon/npcm750-pwm-fan.c +++ b/drivers/hwmon/npcm750-pwm-fan.c @@ -364,6 +364,11 @@ static void npcm7xx_fan_polling(struct timer_list *t) add_timer(&data->fan_timer); } +static void npcm7xx_fan_cleanup(void *timer) +{ + timer_shutdown_sync(timer); +} + static inline void npcm7xx_fan_compute(struct npcm7xx_pwm_fan_data *data, u8 fan, u8 cmp, u8 fan_id, u8 flag_int, u8 flag_mode, u8 flag_clear) @@ -1027,6 +1032,12 @@ static int npcm7xx_pwm_fan_probe(struct platform_device *pdev) msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS); timer_setup(&data->fan_timer, npcm7xx_fan_polling, 0); + ret = devm_add_action_or_reset(dev, + npcm7xx_fan_cleanup, + &data->fan_timer); + if (ret) + return ret; + add_timer(&data->fan_timer); break; } diff --git a/drivers/hwmon/nzxt-smart2.c b/drivers/hwmon/nzxt-smart2.c index e2316c46629d..ff0c0bee0e83 100644 --- a/drivers/hwmon/nzxt-smart2.c +++ b/drivers/hwmon/nzxt-smart2.c @@ -203,7 +203,7 @@ struct drvdata { */ struct mutex mutex; long update_interval; - u8 output_buffer[OUTPUT_REPORT_SIZE]; + u8 output_buffer[OUTPUT_REPORT_SIZE] __aligned(ARCH_DMA_MINALIGN); }; static long scale_pwm_value(long val, long orig_max, long new_max) diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index ddf64e72751c..c9e3ec4552ef 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -512,7 +512,7 @@ int pmbus_update_byte_data(struct i2c_client *client, int page, u8 reg, if (tmp != rv) rv = _pmbus_write_byte_data(client, page, reg, tmp); - return rv; + return rv < 0 ? rv : 0; } EXPORT_SYMBOL_NS_GPL(pmbus_update_byte_data, "PMBUS"); @@ -2977,8 +2977,9 @@ static void pmbus_notify(struct pmbus_data *data, int page, int reg, int flags) if (reg == sreg && page == spage && (smask & flags)) { dev_dbg(data->dev, "sysfs notify: %s", da->attr.name); - sysfs_notify(&data->dev->kobj, NULL, da->attr.name); - kobject_uevent(&data->dev->kobj, KOBJ_CHANGE); + sysfs_notify(&data->hwmon_dev->kobj, NULL, + da->attr.name); + kobject_uevent(&data->hwmon_dev->kobj, KOBJ_CHANGE); flags &= ~smask; } diff --git a/drivers/hwmon/sht3x.c b/drivers/hwmon/sht3x.c index f36c0229328f..5d04013efb52 100644 --- a/drivers/hwmon/sht3x.c +++ b/drivers/hwmon/sht3x.c @@ -21,6 +21,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/jiffies.h> +#include <linux/unaligned.h> /* commands (high repeatability mode) */ static const unsigned char sht3x_cmd_measure_single_hpm[] = { 0x24, 0x00 }; @@ -276,9 +277,9 @@ static struct sht3x_data *sht3x_update_client(struct device *dev) if (ret) goto out; - val = be16_to_cpup((__be16 *)buf); + val = get_unaligned_be16(buf); data->temperature = sht3x_extract_temperature(val); - val = be16_to_cpup((__be16 *)(buf + 3)); + val = get_unaligned_be16(buf + 3); data->humidity = sht3x_extract_humidity(val); data->last_update = jiffies; } @@ -336,7 +337,7 @@ static int limits_update(struct sht3x_data *data) if (ret) return ret; - raw = be16_to_cpup((__be16 *)buffer); + raw = get_unaligned_be16(buffer); temperature = sht3x_extract_temperature((raw & 0x01ff) << 7); humidity = sht3x_extract_humidity(raw & 0xfe00); data->temperature_limits[index] = temperature; @@ -389,7 +390,7 @@ static size_t limit_write(struct device *dev, raw = ((u32)(temperature + 45000) * 24543) >> (16 + 7); raw |= ((humidity * 42950) >> 16) & 0xfe00; - *((__be16 *)position) = cpu_to_be16(raw); + put_unaligned_be16(raw, position); position += SHT3X_WORD_LEN; *position = crc8(sht3x_crc8_table, position - SHT3X_WORD_LEN, diff --git a/drivers/i2c/busses/i2c-amd-mp2-plat.c b/drivers/i2c/busses/i2c-amd-mp2-plat.c index 188e24cc4d35..9fdd6a5fb8b6 100644 --- a/drivers/i2c/busses/i2c-amd-mp2-plat.c +++ b/drivers/i2c/busses/i2c-amd-mp2-plat.c @@ -316,8 +316,10 @@ static int i2c_amd_probe(struct platform_device *pdev) amd_mp2_pm_runtime_put(mp2_dev); - if (ret < 0) + if (ret < 0) { dev_err(&pdev->dev, "i2c add adapter failed = %d\n", ret); + amd_mp2_unregister_cb(&i2c_dev->common); + } return ret; } diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index e418a4f23f15..19300c098af8 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -803,6 +803,17 @@ static int bcm_iproc_i2c_xfer_wait(struct bcm_iproc_i2c_dev *iproc_i2c, } if (!time_left && !iproc_i2c->xfer_is_done) { + /* + * The controller may fail to clear START_BUSY after a timeout, + * reset the controller to recover in that case. + */ + if (!!(iproc_i2c_rd_reg(iproc_i2c, M_CMD_OFFSET) & + BIT(M_CMD_START_BUSY_SHIFT))) { + bcm_iproc_i2c_enable_disable(iproc_i2c, false); + bcm_iproc_i2c_init(iproc_i2c); + bcm_iproc_i2c_enable_disable(iproc_i2c, true); + } + /* flush both TX/RX FIFOs */ val = BIT(M_FIFO_RX_FLUSH_SHIFT) | BIT(M_FIFO_TX_FLUSH_SHIFT); iproc_i2c_wr_reg(iproc_i2c, M_FIFO_CTRL_OFFSET, val); diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index d5e6e2eca3b3..9477d814fde9 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -930,9 +930,6 @@ static int i2c_imx_reg_slave(struct i2c_client *client) if (i2c_imx->slave) return -EBUSY; - i2c_imx->slave = client; - i2c_imx->last_slave_event = I2C_SLAVE_STOP; - /* Resume */ ret = pm_runtime_resume_and_get(i2c_imx->adapter.dev.parent); if (ret < 0) { @@ -940,6 +937,11 @@ static int i2c_imx_reg_slave(struct i2c_client *client) return ret; } + scoped_guard(spinlock_irqsave, &i2c_imx->slave_lock) { + i2c_imx->slave = client; + i2c_imx->last_slave_event = I2C_SLAVE_STOP; + } + i2c_imx_slave_init(i2c_imx); return 0; @@ -958,6 +960,7 @@ static int i2c_imx_unreg_slave(struct i2c_client *client) i2c_imx_reset_regs(i2c_imx); + hrtimer_cancel(&i2c_imx->slave_timer); i2c_imx->slave = NULL; /* Suspend */ @@ -1952,6 +1955,47 @@ static int i2c_imx_runtime_resume(struct device *dev) return 0; } +static int __maybe_unused i2c_imx_suspend_noirq(struct device *dev) +{ + struct imx_i2c_struct *i2c_imx = dev_get_drvdata(dev); + int ret; + + i2c_mark_adapter_suspended(&i2c_imx->adapter); + + /* + * Cancel the slave timer before powering down to prevent + * i2c_imx_slave_timeout() from accessing hardware registers + * while the clock is disabled. + */ + hrtimer_cancel(&i2c_imx->slave_timer); + + ret = pm_runtime_force_suspend(dev); + if (ret) { + i2c_mark_adapter_resumed(&i2c_imx->adapter); + if (i2c_imx->slave) { + hrtimer_forward_now(&i2c_imx->slave_timer, I2C_IMX_CHECK_DELAY); + hrtimer_restart(&i2c_imx->slave_timer); + } + return ret; + } + + return 0; +} + +static int __maybe_unused i2c_imx_resume_noirq(struct device *dev) +{ + struct imx_i2c_struct *i2c_imx = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + i2c_mark_adapter_resumed(&i2c_imx->adapter); + + return 0; +} + static int i2c_imx_suspend(struct device *dev) { /* @@ -1985,8 +2029,8 @@ static int i2c_imx_resume(struct device *dev) } static const struct dev_pm_ops i2c_imx_pm_ops = { - NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + NOIRQ_SYSTEM_SLEEP_PM_OPS(i2c_imx_suspend_noirq, + i2c_imx_resume_noirq) SYSTEM_SLEEP_PM_OPS(i2c_imx_suspend, i2c_imx_resume) RUNTIME_PM_OPS(i2c_imx_runtime_suspend, i2c_imx_runtime_resume, NULL) }; diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c index 664a5471d933..695be3b21460 100644 --- a/drivers/i2c/busses/i2c-jz4780.c +++ b/drivers/i2c/busses/i2c-jz4780.c @@ -141,6 +141,7 @@ struct jz4780_i2c { void __iomem *iomem; int irq; struct clk *clk; + unsigned long clk_rate_khz; struct i2c_adapter adap; const struct ingenic_i2c_config *cdata; @@ -246,7 +247,7 @@ static int jz4780_i2c_set_target(struct jz4780_i2c *i2c, unsigned char address) static int jz4780_i2c_set_speed(struct jz4780_i2c *i2c) { - int dev_clk_khz = clk_get_rate(i2c->clk) / 1000; + int dev_clk_khz = i2c->clk_rate_khz; int cnt_high = 0; /* HIGH period count of the SCL clock */ int cnt_low = 0; /* LOW period count of the SCL clock */ int cnt_period = 0; /* period count of the SCL clock */ @@ -796,6 +797,8 @@ static int jz4780_i2c_probe(struct platform_device *pdev) if (IS_ERR(i2c->clk)) return PTR_ERR(i2c->clk); + i2c->clk_rate_khz = clk_get_rate(i2c->clk) / 1000; + ret = of_property_read_u32(pdev->dev.of_node, "clock-frequency", &clk_freq); if (ret) { diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c index 1c58c39b9279..f2bb04a1b493 100644 --- a/drivers/i2c/busses/i2c-k1.c +++ b/drivers/i2c/busses/i2c-k1.c @@ -565,11 +565,6 @@ static int spacemit_i2c_probe(struct platform_device *pdev) if (i2c->irq < 0) return dev_err_probe(dev, i2c->irq, "failed to get irq resource"); - ret = devm_request_irq(i2c->dev, i2c->irq, spacemit_i2c_irq_handler, - IRQF_NO_SUSPEND, dev_name(i2c->dev), i2c); - if (ret) - return dev_err_probe(dev, ret, "failed to request irq"); - clk = devm_clk_get_enabled(dev, "func"); if (IS_ERR(clk)) return dev_err_probe(dev, PTR_ERR(clk), "failed to enable func clock"); @@ -592,6 +587,11 @@ static int spacemit_i2c_probe(struct platform_device *pdev) init_completion(&i2c->complete); + ret = devm_request_irq(i2c->dev, i2c->irq, spacemit_i2c_irq_handler, + IRQF_NO_SUSPEND, dev_name(i2c->dev), i2c); + if (ret) + return dev_err_probe(dev, ret, "failed to request irq"); + platform_set_drvdata(pdev, i2c); ret = i2c_add_numbered_adapter(&i2c->adapt); diff --git a/drivers/i2c/busses/i2c-qcom-cci.c b/drivers/i2c/busses/i2c-qcom-cci.c index 9d83358f2ae2..791e1a9fd1ba 100644 --- a/drivers/i2c/busses/i2c-qcom-cci.c +++ b/drivers/i2c/busses/i2c-qcom-cci.c @@ -496,24 +496,8 @@ static int __maybe_unused cci_resume_runtime(struct device *dev) return 0; } -static int __maybe_unused cci_suspend(struct device *dev) -{ - if (!pm_runtime_suspended(dev)) - return cci_suspend_runtime(dev); - - return 0; -} - -static int __maybe_unused cci_resume(struct device *dev) -{ - cci_resume_runtime(dev); - pm_request_autosuspend(dev); - - return 0; -} - static const struct dev_pm_ops qcom_cci_pm = { - SET_SYSTEM_SLEEP_PM_OPS(cci_suspend, cci_resume) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) SET_RUNTIME_PM_OPS(cci_suspend_runtime, cci_resume_runtime, NULL) }; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c index 9ec559156508..a52f86454f77 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -285,6 +285,20 @@ static int arm_vsmmu_vsid_to_sid(struct arm_vsmmu *vsmmu, u32 vsid, u32 *sid) return ret; } +static int arm_vsmmu_vdevice_init(struct iommufd_vdevice *vdev) +{ + struct device *dev = iommufd_vdevice_to_device(vdev); + struct arm_smmu_master *master = dev_iommu_priv_get(dev); + + /* + * arm_vsmmu_vsid_to_sid() maps a vSID to master->streams[0] alone, so + * more streams would leave the rest stale and none reads out of bounds. + */ + if (master->num_streams != 1) + return -EOPNOTSUPP; + return 0; +} + /* This is basically iommu_viommu_arm_smmuv3_invalidate in u64 for conversion */ struct arm_vsmmu_invalidation_cmd { union { @@ -391,6 +405,7 @@ int arm_vsmmu_cache_invalidate(struct iommufd_viommu *viommu, static const struct iommufd_viommu_ops arm_vsmmu_ops = { .alloc_domain_nested = arm_vsmmu_alloc_domain_nested, .cache_invalidate = arm_vsmmu_cache_invalidate, + .vdevice_init = arm_vsmmu_vdevice_init, }; size_t arm_smmu_get_viommu_size(struct device *dev, diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index 8b5926c1452e..afe977235d72 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -332,16 +332,30 @@ void iopf_group_response(struct iopf_group *group, .code = status, }; - /* Only send response if there is a fault report pending */ mutex_lock(&fault_param->lock); - if (!list_empty(&group->pending_node)) { - ops->page_response(dev, &group->last_fault, &resp); - list_del_init(&group->pending_node); - } + ops->page_response(dev, &group->last_fault, &resp); + list_del_init(&group->pending_node); mutex_unlock(&fault_param->lock); } EXPORT_SYMBOL_GPL(iopf_group_response); +/** + * iopf_group_dequeue - Dequeue a page fault group from the pending list + * @group: the group to dequeue + * + * The fault handler is responsible for responding to the group after + * this function returns. + */ +void iopf_group_dequeue(struct iopf_group *group) +{ + struct iommu_fault_param *fault_param = group->fault_param; + + mutex_lock(&fault_param->lock); + list_del_init(&group->pending_node); + mutex_unlock(&fault_param->lock); +} +EXPORT_SYMBOL_GPL(iopf_group_dequeue); + /** * iopf_queue_discard_partial - Remove all pending partial fault * @queue: the queue whose partial faults need to be discarded diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 4c842368289f..5c7ead633edd 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -589,7 +589,7 @@ static int iommufd_hwpt_replace_device(struct iommufd_device *idev, if (rc) goto out_free_handle; - iommufd_auto_response_faults(hwpt, old_handle); + iommufd_auto_response_faults(old, old_handle); kfree(old_handle); return 0; diff --git a/drivers/iommu/iommufd/eventq.c b/drivers/iommu/iommufd/eventq.c index a934f02528b0..8971360c955a 100644 --- a/drivers/iommu/iommufd/eventq.c +++ b/drivers/iommu/iommufd/eventq.c @@ -484,6 +484,8 @@ int iommufd_fault_iopf_handler(struct iopf_group *group) hwpt = group->attach_handle->domain->iommufd_hwpt; fault = hwpt->fault; + iopf_group_dequeue(group); + spin_lock(&fault->common.lock); list_add_tail(&group->node, &fault->common.deliver); spin_unlock(&fault->common.lock); diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index 462b457ffd0c..f80582f25e1e 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -143,7 +143,7 @@ void iommufd_vdevice_destroy(struct iommufd_object *obj) int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) { struct iommu_vdevice_alloc *cmd = ucmd->cmd; - struct iommufd_vdevice *vdev, *curr; + struct iommufd_vdevice *vdev; size_t vdev_size = sizeof(*vdev); struct iommufd_viommu *viommu; struct iommufd_device *idev; @@ -189,7 +189,7 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) if (WARN_ON_ONCE(viommu->ops->vdevice_size < vdev_size || !viommu->ops->vdevice_init)) { rc = -EOPNOTSUPP; - goto out_put_idev; + goto out_unlock_igroup; } vdev_size = viommu->ops->vdevice_size; } @@ -218,18 +218,28 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) */ idev->vdev = vdev; - curr = xa_cmpxchg(&viommu->vdevs, virt_id, NULL, vdev, GFP_KERNEL); - if (curr) { - rc = xa_err(curr) ?: -EEXIST; + /* + * Reserve the slot with a zero entry (reads back as NULL) until the + * vdevice_init() op accepts the vDEVICE. Only the xa_* helpers hide a + * reserved entry, so never use a raw xas_* iterator on this xarray. + */ + rc = xa_insert(&viommu->vdevs, virt_id, NULL, GFP_KERNEL); + if (rc) { + if (rc == -EBUSY) + rc = -EEXIST; goto out_abort; } if (viommu->ops && viommu->ops->vdevice_init) { rc = viommu->ops->vdevice_init(vdev); - if (rc) + if (rc) { + xa_release(&viommu->vdevs, virt_id); goto out_abort; + } } + xa_store(&viommu->vdevs, virt_id, vdev, GFP_KERNEL); + cmd->out_vdevice_id = vdev->obj.id; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); if (rc) diff --git a/drivers/media/platform/chips-media/wave5/wave5-hw.c b/drivers/media/platform/chips-media/wave5/wave5-hw.c index d94cf84c3ee5..fd3c3c216815 100644 --- a/drivers/media/platform/chips-media/wave5/wave5-hw.c +++ b/drivers/media/platform/chips-media/wave5/wave5-hw.c @@ -1762,6 +1762,9 @@ int wave5_vpu_enc_init_seq(struct vpu_instance *inst) (p_param->skip_intra_trans << 25) | (p_param->strong_intra_smooth_enable << 27) | (p_param->en_still_picture << 30); + else if (inst->std == W_AVC_ENC) + reg_val |= (p_param->constraint_set1_flag << 29); + vpu_write_reg(inst->dev, W5_CMD_ENC_SEQ_SPS_PARAM, reg_val); reg_val = (p_param->lossless_enable) | diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c index 50cba21fdcdc..03687a1e23c7 100644 --- a/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c +++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c @@ -915,6 +915,8 @@ static int wave5_vpu_enc_s_ctrl(struct v4l2_ctrl *ctrl) case V4L2_MPEG_VIDEO_H264_PROFILE_CONSTRAINED_BASELINE: inst->enc_param.profile = H264_PROFILE_BP; inst->bit_depth = 8; + if (ctrl->val == V4L2_MPEG_VIDEO_H264_PROFILE_CONSTRAINED_BASELINE) + inst->enc_param.constraint_set1_flag = 1; break; case V4L2_MPEG_VIDEO_H264_PROFILE_MAIN: inst->enc_param.profile = H264_PROFILE_MP; @@ -1190,6 +1192,7 @@ static int wave5_set_enc_openparam(struct enc_open_param *open_param, open_param->wave_param.intra_period = input.avc_idr_period; } } else { + open_param->wave_param.constraint_set1_flag = input.constraint_set1_flag; open_param->wave_param.avc_idr_period = input.avc_idr_period; } open_param->wave_param.entropy_coding_mode = input.entropy_coding_mode; @@ -1662,7 +1665,7 @@ static int wave5_vpu_open_enc(struct file *filp) -6, 6, 1, 0); v4l2_ctrl_new_std(v4l2_ctrl_hdl, &wave5_vpu_enc_ctrl_ops, V4L2_CID_MPEG_VIDEO_H264_8X8_TRANSFORM, - 0, 1, 1, 1); + 0, 1, 1, 0); v4l2_ctrl_new_std(v4l2_ctrl_hdl, &wave5_vpu_enc_ctrl_ops, V4L2_CID_MPEG_VIDEO_H264_CONSTRAINED_INTRA_PREDICTION, 0, 1, 1, 0); diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpuapi.h b/drivers/media/platform/chips-media/wave5/wave5-vpuapi.h index bc101397204d..8112d4899ce4 100644 --- a/drivers/media/platform/chips-media/wave5/wave5-vpuapi.h +++ b/drivers/media/platform/chips-media/wave5/wave5-vpuapi.h @@ -570,6 +570,7 @@ struct enc_wave_param { u32 transform8x8_enable: 1; /* enable 8x8 intra prediction and 8x8 transform */ u32 mb_level_rc_enable: 1; /* enable MB-level rate control */ u32 forced_idr_header_enable: 1; /* enable header encoding before IDR frame */ + u32 constraint_set1_flag: 1; /* enable CBP */ }; struct enc_open_param { diff --git a/drivers/media/platform/qcom/camss/camss-csid-340.c b/drivers/media/platform/qcom/camss/camss-csid-340.c index 22a30510fb79..0231985746ed 100644 --- a/drivers/media/platform/qcom/camss/camss-csid-340.c +++ b/drivers/media/platform/qcom/camss/camss-csid-340.c @@ -55,8 +55,7 @@ #define CSID_RDI_CTRL_HALT_AT_FRAME_BOUNDARY 0 #define CSID_RDI_CTRL_RESUME_AT_FRAME_BOUNDARY 1 -static void __csid_configure_rx(struct csid_device *csid, - struct csid_phy_config *phy, int vc) +static void __csid_configure_rx(struct csid_device *csid, struct csid_phy_config *phy) { u32 val; @@ -75,32 +74,28 @@ static void __csid_ctrl_rdi(struct csid_device *csid, int enable, u8 rdi) writel_relaxed(!!enable, csid->base + CSID_RDI_CTRL(rdi)); } -static void __csid_configure_rdi_stream(struct csid_device *csid, u8 enable, u8 vc) +static void __csid_configure_rdi_stream(struct csid_device *csid, u8 enable, u8 port, u8 vc) { - struct v4l2_mbus_framefmt *input_format = &csid->fmt[MSM_CSID_PAD_FIRST_SRC + vc]; + struct v4l2_mbus_framefmt *input_format = &csid->fmt[MSM_CSID_PAD_FIRST_SRC + port]; const struct csid_format_info *format = csid_get_fmt_entry(csid->res->formats->formats, csid->res->formats->nformats, input_format->code); - u8 lane_cnt = csid->phy.lane_cnt; u8 dt_id; u32 val; - if (!lane_cnt) - lane_cnt = 4; - /* * DT_ID is a two bit bitfield that is concatenated with * the four least significant bits of the five bit VC * bitfield to generate an internal CID value. * - * CSID_RDI_CFG0(vc) + * CSID_RDI_CFG0(port) * DT_ID : 28:27 * VC : 26:22 * DT : 21:16 * * CID : VC 3:0 << 2 | DT_ID 1:0 */ - dt_id = vc & 0x03; + dt_id = port & 0x03; val = CSID_RDI_CFG0_DECODE_FORMAT_NOP; /* only for RDI path */ val |= FIELD_PREP(CSID_RDI_CFG0_DT_MASK, format->data_type); @@ -110,20 +105,23 @@ static void __csid_configure_rdi_stream(struct csid_device *csid, u8 enable, u8 if (enable) val |= CSID_RDI_CFG0_ENABLE; - dev_dbg(csid->camss->dev, "CSID%u: Stream %s (dt:0x%x vc=%u)\n", - csid->id, enable ? "enable" : "disable", format->data_type, vc); + dev_dbg(csid->camss->dev, "CSID%u: Stream %s (dt:0x%x port=%u vc=%u)\n", + csid->id, enable ? "enable" : "disable", format->data_type, + port, vc); - writel_relaxed(val, csid->base + CSID_RDI_CFG0(vc)); + writel_relaxed(val, csid->base + CSID_RDI_CFG0(port)); } static void csid_configure_stream(struct csid_device *csid, u8 enable) { int i; + __csid_configure_rx(csid, &csid->phy); + + /* Loop through all enabled ports and configure a stream for each */ for (i = 0; i < MSM_CSID_MAX_SRC_STREAMS; i++) { if (csid->phy.en_vc & BIT(i)) { - __csid_configure_rdi_stream(csid, enable, i); - __csid_configure_rx(csid, &csid->phy, i); + __csid_configure_rdi_stream(csid, enable, i, 0); __csid_ctrl_rdi(csid, enable, i); } } diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c index cc371d0c9f3c..2ea5224ebfcb 100644 --- a/drivers/net/can/c_can/c_can_main.c +++ b/drivers/net/can/c_can/c_can_main.c @@ -597,20 +597,20 @@ static int c_can_chip_config(struct net_device *dev) return err; /* enable automatic retransmission */ - priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_ENABLE_AR); + priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_ENABLE_AR | CONTROL_INIT); if ((priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) && (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)) { /* loopback + silent mode : useful for hot self-test */ - priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_TEST); + priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_TEST | CONTROL_INIT); priv->write_reg(priv, C_CAN_TEST_REG, TEST_LBACK | TEST_SILENT); } else if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) { /* loopback mode : useful for self-test function */ - priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_TEST); + priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_TEST | CONTROL_INIT); priv->write_reg(priv, C_CAN_TEST_REG, TEST_LBACK); } else if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) { /* silent mode : bus-monitoring mode */ - priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_TEST); + priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_TEST | CONTROL_INIT); priv->write_reg(priv, C_CAN_TEST_REG, TEST_SILENT); } diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c index 33a5ec434627..178fa05bac66 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_base.c +++ b/drivers/net/can/ctucanfd/ctucanfd_base.c @@ -340,8 +340,8 @@ static void ctucan_set_mode(struct ctucan_priv *priv, const struct can_ctrlmode (mode_reg & ~REG_MODE_FDE); mode_reg = (mode->flags & CAN_CTRLMODE_PRESUME_ACK) ? - (mode_reg | REG_MODE_ACF) : - (mode_reg & ~REG_MODE_ACF); + (mode_reg | REG_MODE_STM) : + (mode_reg & ~REG_MODE_STM); mode_reg = (mode->flags & CAN_CTRLMODE_FD_NON_ISO) ? (mode_reg | REG_MODE_NISOFD) : @@ -869,7 +869,7 @@ static void ctucan_err_interrupt(struct net_device *ndev, u32 isr) break; case CAN_STATE_ERROR_ACTIVE: if (skb) { - cf->can_id |= CAN_ERR_CNT; + cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT; cf->data[1] = CAN_ERR_CRTL_ACTIVE; cf->data[6] = bec.txerr; cf->data[7] = bec.rxerr; @@ -1136,8 +1136,12 @@ static irqreturn_t ctucan_interrupt(int irq, void *dev_id) /* Error interrupts */ if (FIELD_GET(REG_INT_STAT_EWLI, isr) || FIELD_GET(REG_INT_STAT_FCSI, isr) || - FIELD_GET(REG_INT_STAT_ALI, isr)) { - icr = isr & (REG_INT_STAT_EWLI | REG_INT_STAT_FCSI | REG_INT_STAT_ALI); + FIELD_GET(REG_INT_STAT_ALI, isr) || + FIELD_GET(REG_INT_STAT_BEI, isr)) { + icr = isr & (REG_INT_STAT_EWLI | + REG_INT_STAT_FCSI | + REG_INT_STAT_ALI | + REG_INT_STAT_BEI); ctucan_netdev_dbg(ndev, "some ERR interrupt: clearing 0x%08x\n", icr); ctucan_write32(priv, CTUCANFD_INT_STAT, icr); diff --git a/drivers/net/can/ctucanfd/ctucanfd_pci.c b/drivers/net/can/ctucanfd/ctucanfd_pci.c index 9da09e7dd63a..8cc995649287 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_pci.c +++ b/drivers/net/can/ctucanfd/ctucanfd_pci.c @@ -202,7 +202,7 @@ static int ctucan_pci_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, NULL); kfree(bdata); err_pci_iounmap_bar0: - pci_iounmap(pdev, cra_addr); + pci_iounmap(pdev, bar0_base); err_pci_iounmap_bar1: pci_iounmap(pdev, addr); err_release_regions: @@ -274,6 +274,7 @@ static const struct pci_device_id ctucan_pci_tbl[] = { CTUCAN_WITH_CTUCAN_ID)}, {}, }; +MODULE_DEVICE_TABLE(pci, ctucan_pci_tbl); static struct pci_driver ctucan_pci_driver = { .name = KBUILD_MODNAME, diff --git a/drivers/net/can/dev/skb.c b/drivers/net/can/dev/skb.c index 3ebd4f779b9b..0da615afa04d 100644 --- a/drivers/net/can/dev/skb.c +++ b/drivers/net/can/dev/skb.c @@ -202,7 +202,6 @@ static void init_can_skb_reserve(struct sk_buff *skb) skb_reset_transport_header(skb); can_skb_reserve(skb); - can_skb_prv(skb)->skbcnt = 0; } struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf) @@ -312,7 +311,6 @@ static bool can_skb_headroom_valid(struct net_device *dev, struct sk_buff *skb) if (skb->ip_summed == CHECKSUM_NONE) { /* init headroom */ can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/drivers/net/can/softing/softing_fw.c b/drivers/net/can/softing/softing_fw.c index 721df91cdbfb..282570daf3ef 100644 --- a/drivers/net/can/softing/softing_fw.c +++ b/drivers/net/can/softing/softing_fw.c @@ -91,12 +91,12 @@ int softing_bootloader_command(struct softing *card, int16_t cmd, return ret; } -static int fw_parse(const uint8_t **pmem, uint16_t *ptype, uint32_t *paddr, - uint16_t *plen, const uint8_t **pdat) +static int fw_parse(const u8 **pmem, const u8 *limit, u16 *ptype, + u32 *paddr, u16 *plen, const u8 **pdat) { uint16_t checksum[2]; - const uint8_t *mem; - const uint8_t *end; + const u8 *mem; + const u8 *record_end; /* * firmware records are a binary, unaligned stream composed of: @@ -114,14 +114,21 @@ static int fw_parse(const uint8_t **pmem, uint16_t *ptype, uint32_t *paddr, * endianness & alignment. */ mem = *pmem; + /* A record needs an 8-byte prefix and a 2-byte checksum. */ + if (mem > limit || limit - mem < 10) + return -EINVAL; + *ptype = le16_to_cpup((void *)&mem[0]); *paddr = le32_to_cpup((void *)&mem[2]); *plen = le16_to_cpup((void *)&mem[6]); + if (*plen > limit - mem - 10) + return -EINVAL; + *pdat = &mem[8]; /* verify checksum */ - end = &mem[8 + *plen]; - checksum[0] = le16_to_cpup((void *)end); - for (checksum[1] = 0; mem < end; ++mem) + record_end = &mem[8 + *plen]; + checksum[0] = le16_to_cpup((void *)record_end); + for (checksum[1] = 0; mem < record_end; ++mem) checksum[1] += *mem; if (checksum[0] != checksum[1]) return -EINVAL; @@ -139,6 +146,7 @@ int softing_load_fw(const char *file, struct softing *card, uint16_t type, len; uint32_t addr; uint8_t *buf = NULL, *new_buf; + s64 dpram_offset; int buflen = 0; int8_t type_end = 0; @@ -153,7 +161,7 @@ int softing_load_fw(const char *file, struct softing *card, mem = fw->data; end = &mem[fw->size]; /* look for header record */ - ret = fw_parse(&mem, &type, &addr, &len, &dat); + ret = fw_parse(&mem, end, &type, &addr, &len, &dat); if (ret < 0) goto failed; if (type != 0xffff) @@ -164,7 +172,7 @@ int softing_load_fw(const char *file, struct softing *card, } /* ok, we had a header */ while (mem < end) { - ret = fw_parse(&mem, &type, &addr, &len, &dat); + ret = fw_parse(&mem, end, &type, &addr, &len, &dat); if (ret < 0) goto failed; if (type == 3) { @@ -179,9 +187,13 @@ int softing_load_fw(const char *file, struct softing *card, goto failed; } - if ((addr + len + offset) > size) + dpram_offset = (s64)addr + offset; + if (dpram_offset < 0 || dpram_offset > size || + len > size - dpram_offset) { + ret = -EINVAL; goto failed; - memcpy_toio(&dpram[addr + offset], dat, len); + } + memcpy_toio(&dpram[dpram_offset], dat, len); /* be sure to flush caches from IO space */ mb(); if (len > buflen) { @@ -195,7 +207,7 @@ int softing_load_fw(const char *file, struct softing *card, buf = new_buf; } /* verify record data */ - memcpy_fromio(buf, &dpram[addr + offset], len); + memcpy_fromio(buf, &dpram[dpram_offset], len); if (memcmp(buf, dat, len)) { /* is not ok */ dev_alert(&card->pdev->dev, "DPRAM readback failed\n"); @@ -237,7 +249,7 @@ int softing_load_app_fw(const char *file, struct softing *card) mem = fw->data; end = &mem[fw->size]; /* look for header record */ - ret = fw_parse(&mem, &type, &addr, &len, &dat); + ret = fw_parse(&mem, end, &type, &addr, &len, &dat); if (ret) goto failed; ret = -EINVAL; @@ -253,7 +265,7 @@ int softing_load_app_fw(const char *file, struct softing *card) } /* ok, we had a header */ while (mem < end) { - ret = fw_parse(&mem, &type, &addr, &len, &dat); + ret = fw_parse(&mem, end, &type, &addr, &len, &dat); if (ret) goto failed; @@ -279,6 +291,12 @@ int softing_load_app_fw(const char *file, struct softing *card) /* work in 16bit (target) */ sum &= 0xffff; + if (card->pdat->app.offs > card->dpram_size || + len > card->dpram_size - card->pdat->app.offs) { + ret = -EINVAL; + goto failed; + } + memcpy_toio(&card->dpram[card->pdat->app.offs], dat, len); iowrite32(card->pdat->app.offs + card->pdat->app.addr, &card->dpram[DPRAM_COMMAND + 2]); diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index d8c881130e90..4b130c96c9ab 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -409,6 +409,40 @@ static void ems_usb_rx_err(struct ems_usb *dev, struct ems_cpc_msg *msg) netif_rx(skb); } +static bool ems_usb_rx_msg_len_valid(struct ems_cpc_msg *msg) +{ + size_t len = msg->length; + size_t can_len; + + switch (msg->type) { + case CPC_MSG_TYPE_CAN_STATE: + return len >= sizeof(msg->msg.can_state); + + case CPC_MSG_TYPE_CAN_FRAME: + case CPC_MSG_TYPE_EXT_CAN_FRAME: + case CPC_MSG_TYPE_RTR_FRAME: + case CPC_MSG_TYPE_EXT_RTR_FRAME: + if (len < CPC_CAN_MSG_MIN_SIZE) + return false; + + if (msg->type == CPC_MSG_TYPE_RTR_FRAME || + msg->type == CPC_MSG_TYPE_EXT_RTR_FRAME) + return true; + + can_len = can_cc_dlc2len(msg->msg.can_msg.length & 0xf); + return len >= CPC_CAN_MSG_MIN_SIZE + can_len; + + case CPC_MSG_TYPE_CAN_FRAME_ERROR: + return len >= sizeof(msg->msg.error); + + case CPC_MSG_TYPE_OVERRUN: + return len >= sizeof(msg->msg.overrun); + + default: + return true; + } +} + /* * callback for bulk IN urb */ @@ -451,6 +485,15 @@ static void ems_usb_read_bulk_callback(struct urb *urb) } msg = (struct ems_cpc_msg *)&ibuf[start]; + if (msg->length > + urb->actual_length - start - CPC_MSG_HEADER_LEN) { + netdev_err(netdev, "format error\n"); + break; + } + if (!ems_usb_rx_msg_len_valid(msg)) { + netdev_err(netdev, "format error\n"); + break; + } switch (msg->type) { case CPC_MSG_TYPE_CAN_STATE: diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index 1e44bd1dfee9..70d9cd11cb85 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -1476,7 +1476,6 @@ static void es58x_read_bulk_callback(struct urb *urb) dev_err_ratelimited(dev, "Failed resubmitting read bulk urb: %pe\n", ERR_PTR(ret)); - return; free_urb: usb_free_coherent(urb->dev, urb->transfer_buffer_length, diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index e336703b941e..241ffa8daaee 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -674,7 +674,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) if (hf->flags & GS_CAN_FLAG_FD) { skb = alloc_canfd_skb(netdev, &cfd); if (!skb) - return; + goto resubmit_urb; cfd->can_id = le32_to_cpu(hf->can_id); cfd->len = data_length; @@ -687,7 +687,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) } else { skb = alloc_can_skb(netdev, &cf); if (!skb) - return; + goto resubmit_urb; cf->can_id = le32_to_cpu(hf->can_id); can_frame_set_cc_len(cf, hf->can_dlc, dev->can.ctrlmode); diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index a59f20dad692..6f8d3bc42733 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -1626,6 +1626,7 @@ static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv, reinit_completion(&priv->get_busparams_comp); err = kvaser_usb_send_cmd(dev, cmd, cmd_len); + kfree(cmd); if (err) return err; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 1167d38344f1..c9322f279e3e 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -691,13 +691,22 @@ static int kvaser_usb_leaf_wait_cmd(const struct kvaser_usb *dev, u8 id, continue; } - if (pos + tmp->len > actual_len) { + if (tmp->len < CMD_HEADER_LEN || + tmp->len > actual_len - pos) { dev_err_ratelimited(&dev->intf->dev, "Format error\n"); break; } if (tmp->id == id) { + if (tmp->len > sizeof(*cmd)) { + dev_err_ratelimited(&dev->intf->dev, + "Received command %u too large (%u)\n", + tmp->id, tmp->len); + err = -EIO; + goto end; + } + memcpy(cmd, tmp, tmp->len); goto end; } @@ -1737,7 +1746,7 @@ static void kvaser_usb_leaf_read_bulk_callback(struct kvaser_usb *dev, continue; } - if (pos + cmd->len > len) { + if (cmd->len < CMD_HEADER_LEN || cmd->len > len - pos) { dev_err_ratelimited(&dev->intf->dev, "Format error\n"); break; } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index c74302ca7cee..529e9cb2570f 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -470,7 +470,6 @@ static int peak_usb_start(struct peak_usb_device *dev) netif_device_detach(dev->netdev); usb_unanchor_urb(urb); - kfree(buf); usb_free_urb(urb); break; } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index be84191cde56..f92a3b404ec1 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -566,6 +566,13 @@ static int pcan_usb_fd_decode_canmsg(struct pcan_usb_fd_if *usb_if, dev->can.ctrlmode); } + if (!(rx_msg_flags & PUCAN_MSG_RTR) && + le16_to_cpu(rx_msg->size) - offsetof(struct pucan_rx_msg, d) < + cfd->len) { + kfree_skb(skb); + return -EBADMSG; + } + cfd->can_id = le32_to_cpu(rm->can_id); if (rx_msg_flags & PUCAN_MSG_EXT_ID) @@ -714,6 +721,24 @@ static void pcan_usb_fd_decode_ts(struct pcan_usb_fd_if *usb_if, peak_usb_set_ts_now(&usb_if->time_ref, le32_to_cpu(ts->ts_low)); } +static size_t pcan_usb_fd_rx_msg_min_size(u16 rx_msg_type) +{ + switch (rx_msg_type) { + case PUCAN_MSG_CAN_RX: + return offsetof(struct pucan_rx_msg, d); + case PCAN_UFD_MSG_CALIBRATION: + return sizeof(struct pcan_ufd_ts_msg); + case PUCAN_MSG_ERROR: + return sizeof(struct pucan_error_msg); + case PUCAN_MSG_STATUS: + return sizeof(struct pucan_status_msg); + case PCAN_UFD_MSG_OVERRUN: + return sizeof(struct pcan_ufd_ovr_msg); + default: + return sizeof(struct pucan_msg); + } +} + /* callback for bulk IN urb */ static int pcan_usb_fd_decode_buf(struct peak_usb_device *dev, struct urb *urb) { @@ -728,6 +753,12 @@ static int pcan_usb_fd_decode_buf(struct peak_usb_device *dev, struct urb *urb) msg_end = urb->transfer_buffer + urb->actual_length; for (; msg_ptr < msg_end;) { u16 rx_msg_type, rx_msg_size; + size_t rx_msg_min_size; + + if (msg_end - msg_ptr < sizeof(*rx_msg)) { + err = -EBADMSG; + break; + } rx_msg = (struct pucan_msg *)msg_ptr; if (!rx_msg->size) { @@ -739,13 +770,20 @@ static int pcan_usb_fd_decode_buf(struct peak_usb_device *dev, struct urb *urb) rx_msg_type = le16_to_cpu(rx_msg->type); /* check if the record goes out of current packet */ - if (msg_ptr + rx_msg_size > msg_end) { + if (rx_msg_size > msg_end - msg_ptr) { netdev_err(netdev, "got frag rec: should inc usb rx buf sze\n"); err = -EBADMSG; break; } + rx_msg_min_size = pcan_usb_fd_rx_msg_min_size(rx_msg_type); + if (rx_msg_size < rx_msg_min_size) { + netdev_err(netdev, "got short rec\n"); + err = -EBADMSG; + break; + } + switch (rx_msg_type) { case PUCAN_MSG_CAN_RX: err = pcan_usb_fd_decode_canmsg(usb_if, rx_msg); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 7be286293b1a..c6023acd05e5 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -534,12 +534,18 @@ static int pcan_usb_pro_handle_canmsg(struct pcan_usb_pro_interface *usb_if, struct pcan_usb_pro_rxmsg *rx) { const unsigned int ctrl_idx = (rx->len >> 4) & 0x0f; - struct peak_usb_device *dev = usb_if->dev[ctrl_idx]; - struct net_device *netdev = dev->netdev; + struct peak_usb_device *dev; + struct net_device *netdev; struct can_frame *can_frame; struct sk_buff *skb; struct skb_shared_hwtstamps *hwts; + if (ctrl_idx >= ARRAY_SIZE(usb_if->dev)) + return -EINVAL; + + dev = usb_if->dev[ctrl_idx]; + netdev = dev->netdev; + skb = alloc_can_skb(netdev, &can_frame); if (!skb) return -ENOMEM; @@ -573,14 +579,20 @@ static int pcan_usb_pro_handle_error(struct pcan_usb_pro_interface *usb_if, { const u16 raw_status = le16_to_cpu(er->status); const unsigned int ctrl_idx = (er->channel >> 4) & 0x0f; - struct peak_usb_device *dev = usb_if->dev[ctrl_idx]; - struct net_device *netdev = dev->netdev; + struct peak_usb_device *dev; + struct net_device *netdev; struct can_frame *can_frame; enum can_state new_state = CAN_STATE_ERROR_ACTIVE; u8 err_mask = 0; struct sk_buff *skb; struct skb_shared_hwtstamps *hwts; + if (ctrl_idx >= ARRAY_SIZE(usb_if->dev)) + return -EINVAL; + + dev = usb_if->dev[ctrl_idx]; + netdev = dev->netdev; + /* nothing should be sent while in BUS_OFF state */ if (dev->can.state == CAN_STATE_BUS_OFF) return 0; diff --git a/drivers/net/dsa/mt7530-mdio.c b/drivers/net/dsa/mt7530-mdio.c index 0286a6cecb6f..6cc2c8975af6 100644 --- a/drivers/net/dsa/mt7530-mdio.c +++ b/drivers/net/dsa/mt7530-mdio.c @@ -55,8 +55,15 @@ mt7530_regmap_read(void *context, unsigned int reg, unsigned int *val) if (ret < 0) return ret; - lo = bus->read(bus, priv->mdiodev->addr, r); - hi = bus->read(bus, priv->mdiodev->addr, 0x10); + ret = bus->read(bus, priv->mdiodev->addr, r); + if (ret < 0) + return ret; + lo = ret; + + ret = bus->read(bus, priv->mdiodev->addr, 0x10); + if (ret < 0) + return ret; + hi = ret; *val = (hi << 16) | (lo & 0xffff); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 4571da0d7a8f..2a70fa4b5fa3 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -188,12 +188,6 @@ mt7530_write(struct mt7530_priv *priv, u32 reg, u32 val) mt7530_mutex_unlock(priv); } -static u32 -_mt7530_unlocked_read(struct mt7530_dummy_poll *p) -{ - return mt7530_mii_read(p->priv, p->reg); -} - static u32 _mt7530_read(struct mt7530_dummy_poll *p) { @@ -546,16 +540,13 @@ static int mt7531_ind_c45_phy_read(struct mt7530_priv *priv, int port, int devad, int regnum) { - struct mt7530_dummy_poll p; u32 reg, val; int ret; - INIT_MT7530_DUMMY_POLL(&p, priv, MT7531_PHY_IAC); - mt7530_mutex_lock(priv); - ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val, - !(val & MT7531_PHY_ACS_ST), 20, 100000); + ret = regmap_read_poll_timeout(priv->regmap, MT7531_PHY_IAC, val, + !(val & MT7531_PHY_ACS_ST), 20, 100000); if (ret < 0) { dev_err(priv->dev, "poll timeout\n"); goto out; @@ -565,8 +556,8 @@ mt7531_ind_c45_phy_read(struct mt7530_priv *priv, int port, int devad, MT7531_MDIO_DEV_ADDR(devad) | regnum; mt7530_mii_write(priv, MT7531_PHY_IAC, reg | MT7531_PHY_ACS_ST); - ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val, - !(val & MT7531_PHY_ACS_ST), 20, 100000); + ret = regmap_read_poll_timeout(priv->regmap, MT7531_PHY_IAC, val, + !(val & MT7531_PHY_ACS_ST), 20, 100000); if (ret < 0) { dev_err(priv->dev, "poll timeout\n"); goto out; @@ -576,8 +567,8 @@ mt7531_ind_c45_phy_read(struct mt7530_priv *priv, int port, int devad, MT7531_MDIO_DEV_ADDR(devad); mt7530_mii_write(priv, MT7531_PHY_IAC, reg | MT7531_PHY_ACS_ST); - ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val, - !(val & MT7531_PHY_ACS_ST), 20, 100000); + ret = regmap_read_poll_timeout(priv->regmap, MT7531_PHY_IAC, val, + !(val & MT7531_PHY_ACS_ST), 20, 100000); if (ret < 0) { dev_err(priv->dev, "poll timeout\n"); goto out; @@ -594,16 +585,13 @@ static int mt7531_ind_c45_phy_write(struct mt7530_priv *priv, int port, int devad, int regnum, u16 data) { - struct mt7530_dummy_poll p; u32 val, reg; int ret; - INIT_MT7530_DUMMY_POLL(&p, priv, MT7531_PHY_IAC); - mt7530_mutex_lock(priv); - ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val, - !(val & MT7531_PHY_ACS_ST), 20, 100000); + ret = regmap_read_poll_timeout(priv->regmap, MT7531_PHY_IAC, val, + !(val & MT7531_PHY_ACS_ST), 20, 100000); if (ret < 0) { dev_err(priv->dev, "poll timeout\n"); goto out; @@ -613,8 +601,8 @@ mt7531_ind_c45_phy_write(struct mt7530_priv *priv, int port, int devad, MT7531_MDIO_DEV_ADDR(devad) | regnum; mt7530_mii_write(priv, MT7531_PHY_IAC, reg | MT7531_PHY_ACS_ST); - ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val, - !(val & MT7531_PHY_ACS_ST), 20, 100000); + ret = regmap_read_poll_timeout(priv->regmap, MT7531_PHY_IAC, val, + !(val & MT7531_PHY_ACS_ST), 20, 100000); if (ret < 0) { dev_err(priv->dev, "poll timeout\n"); goto out; @@ -624,8 +612,8 @@ mt7531_ind_c45_phy_write(struct mt7530_priv *priv, int port, int devad, MT7531_MDIO_DEV_ADDR(devad) | data; mt7530_mii_write(priv, MT7531_PHY_IAC, reg | MT7531_PHY_ACS_ST); - ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val, - !(val & MT7531_PHY_ACS_ST), 20, 100000); + ret = regmap_read_poll_timeout(priv->regmap, MT7531_PHY_IAC, val, + !(val & MT7531_PHY_ACS_ST), 20, 100000); if (ret < 0) { dev_err(priv->dev, "poll timeout\n"); goto out; @@ -640,16 +628,13 @@ mt7531_ind_c45_phy_write(struct mt7530_priv *priv, int port, int devad, static int mt7531_ind_c22_phy_read(struct mt7530_priv *priv, int port, int regnum) { - struct mt7530_dummy_poll p; int ret; u32 val; - INIT_MT7530_DUMMY_POLL(&p, priv, MT7531_PHY_IAC); - mt7530_mutex_lock(priv); - ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val, - !(val & MT7531_PHY_ACS_ST), 20, 100000); + ret = regmap_read_poll_timeout(priv->regmap, MT7531_PHY_IAC, val, + !(val & MT7531_PHY_ACS_ST), 20, 100000); if (ret < 0) { dev_err(priv->dev, "poll timeout\n"); goto out; @@ -660,8 +645,8 @@ mt7531_ind_c22_phy_read(struct mt7530_priv *priv, int port, int regnum) mt7530_mii_write(priv, MT7531_PHY_IAC, val | MT7531_PHY_ACS_ST); - ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val, - !(val & MT7531_PHY_ACS_ST), 20, 100000); + ret = regmap_read_poll_timeout(priv->regmap, MT7531_PHY_IAC, val, + !(val & MT7531_PHY_ACS_ST), 20, 100000); if (ret < 0) { dev_err(priv->dev, "poll timeout\n"); goto out; @@ -678,16 +663,13 @@ static int mt7531_ind_c22_phy_write(struct mt7530_priv *priv, int port, int regnum, u16 data) { - struct mt7530_dummy_poll p; int ret; u32 reg; - INIT_MT7530_DUMMY_POLL(&p, priv, MT7531_PHY_IAC); - mt7530_mutex_lock(priv); - ret = readx_poll_timeout(_mt7530_unlocked_read, &p, reg, - !(reg & MT7531_PHY_ACS_ST), 20, 100000); + ret = regmap_read_poll_timeout(priv->regmap, MT7531_PHY_IAC, reg, + !(reg & MT7531_PHY_ACS_ST), 20, 100000); if (ret < 0) { dev_err(priv->dev, "poll timeout\n"); goto out; @@ -698,8 +680,8 @@ mt7531_ind_c22_phy_write(struct mt7530_priv *priv, int port, int regnum, mt7530_mii_write(priv, MT7531_PHY_IAC, reg | MT7531_PHY_ACS_ST); - ret = readx_poll_timeout(_mt7530_unlocked_read, &p, reg, - !(reg & MT7531_PHY_ACS_ST), 20, 100000); + ret = regmap_read_poll_timeout(priv->regmap, MT7531_PHY_IAC, reg, + !(reg & MT7531_PHY_ACS_ST), 20, 100000); if (ret < 0) { dev_err(priv->dev, "poll timeout\n"); goto out; diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 15160427c8b3..a668afc18393 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -1222,11 +1222,11 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (hw->flash_address) iounmap(hw->flash_address); +err_mdio_ioremap: kfree(adapter->tx_ring); kfree(adapter->rx_ring); err_dma: err_sw_init: -err_mdio_ioremap: iounmap(hw->ce4100_gbe_mdio_base_virt); iounmap(hw->hw_addr); err_ioremap: diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 023d0de12670..2a47d9f3cf7e 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -703,7 +703,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, ret, libie_aq_str(pf->hw.adminq.sq_last_status), pin_type_name[pin_type], pin->idx); - else + else if (pf->hw.adminq.sq_last_status != LIBIE_AQ_RC_EBUSY) dev_err_ratelimited(ice_pf_to_dev(pf), "err:%d %s failed to update %s pin:%u\n", ret, @@ -2669,7 +2669,8 @@ static int ice_dpll_pps_update_phase_offsets(struct ice_pf *pf, *phase_offset_pins_updated = 0; ret = ice_aq_get_cgu_input_pin_measure(&pf->hw, DPLL_TYPE_PPS, meas, ARRAY_SIZE(meas)); - if (ret && pf->hw.adminq.sq_last_status == LIBIE_AQ_RC_EAGAIN) { + if (ret && (pf->hw.adminq.sq_last_status == LIBIE_AQ_RC_EAGAIN || + pf->hw.adminq.sq_last_status == LIBIE_AQ_RC_EBUSY)) { return 0; } else if (ret) { dev_err(ice_pf_to_dev(pf), @@ -2731,10 +2732,12 @@ ice_dpll_update_state(struct ice_pf *pf, struct ice_dpll *d, bool init) d->dpll_idx, d->prev_input_idx, d->input_idx, d->dpll_state, d->prev_dpll_state, d->mode); if (ret) { - dev_err(ice_pf_to_dev(pf), - "update dpll=%d state failed, ret=%d %s\n", - d->dpll_idx, ret, - libie_aq_str(pf->hw.adminq.sq_last_status)); + /* EBUSY is expected during reset recovery, don't log error */ + if (pf->hw.adminq.sq_last_status != LIBIE_AQ_RC_EBUSY) + dev_err(ice_pf_to_dev(pf), + "update dpll=%d state failed, ret=%d %s\n", + d->dpll_idx, ret, + libie_aq_str(pf->hw.adminq.sq_last_status)); return ret; } if (init) { @@ -2803,7 +2806,9 @@ static void ice_dpll_periodic_work(struct kthread_work *work) d->periodic_counter % dp->phase_offset_monitor_period == 0) ret = ice_dpll_pps_update_phase_offsets(pf, &phase_offset_ntf); if (ret) { - d->cgu_state_acq_err_num++; + /* EBUSY is expected during reset recovery */ + if (pf->hw.adminq.sq_last_status != LIBIE_AQ_RC_EBUSY) + d->cgu_state_acq_err_num++; /* stop rescheduling this worker */ if (d->cgu_state_acq_err_num > ICE_CGU_STATE_ACQ_ERR_THRESHOLD) { diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index ce0f8106dcd4..5944ab6efd44 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1077,18 +1077,18 @@ static int ice_lbtest_prepare_rings(struct ice_vsi *vsi) status = ice_vsi_cfg_lan(vsi); if (status) - goto err_setup_rx_ring; + goto err_cfg_lan; status = ice_vsi_start_all_rx_rings(vsi); if (status) - goto err_start_rx_ring; + goto err_cfg_lan; return 0; -err_start_rx_ring: - ice_vsi_free_rx_rings(vsi); -err_setup_rx_ring: +err_cfg_lan: ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0); +err_setup_rx_ring: + ice_vsi_free_rx_rings(vsi); err_setup_tx_ring: ice_vsi_free_tx_rings(vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index b89041743f6f..2f1dd9eea2b2 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5713,6 +5713,16 @@ static int ice_resume(struct device *dev) /* Restart the service task */ mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); + /* Best-effort wait for the scheduled reset to finish so that the + * device is operational before returning. Without this, userspace + * (e.g. NetworkManager) may try to open the net device while the + * asynchronous reset is still in progress, hitting -EBUSY. + */ + ret = ice_wait_for_reset(pf, secs_to_jiffies(10)); + if (ret) + dev_err(dev, "Wait for reset timed out (10s) during resume: %d\n", + ret); + return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index bab968b05540..54f59bed9645 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -848,6 +848,30 @@ static void ice_notify_vf_reset(struct ice_vf *vf) NULL); } +/** + * ice_reset_interrupts - clear all queue interrupt configuration for a VSI + * @vsi: the VSI whose interrupt registers should be cleared + * + * Zero the QINT_RQCTL and QINT_TQCTL registers for all allocated queues + * in the VSI. This clears the entire register including MSIX_INDX, ITR_INDX, + * CAUSE_ENA and NEXTQ fields, unlike ice_vf_dis_rxq_interrupt() which only + * clears the CAUSE_ENA bit. + */ +void ice_reset_interrupts(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + int i; + + ice_for_each_alloc_rxq(vsi, i) + wr32(hw, QINT_RQCTL(vsi->rxq_map[i]), 0); + + ice_for_each_alloc_txq(vsi, i) + wr32(hw, QINT_TQCTL(vsi->txq_map[i]), 0); + + ice_flush(hw); +} + /** * ice_reset_vf - Reset a particular VF * @vf: pointer to the VF structure @@ -919,6 +943,9 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) ice_dis_vf_qs(vf); + /* cleanup interrupt registers */ + ice_reset_interrupts(vsi); + /* Call Disable LAN Tx queue AQ whether or not queues are * enabled. This is needed for successful completion of VFR. */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h index 5392b0404986..321d29c25b7c 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -26,6 +26,7 @@ void ice_initialize_vf_entry(struct ice_vf *vf); void ice_deinitialize_vf_entry(struct ice_vf *vf); void ice_dis_vf_qs(struct ice_vf *vf); +void ice_reset_interrupts(struct ice_vsi *vsi); int ice_check_vf_init(struct ice_vf *vf); enum virtchnl_status_code ice_err_to_virt_err(int err); struct ice_port_info *ice_vf_get_port_info(struct ice_vf *vf); diff --git a/drivers/net/ethernet/intel/ice/virt/queues.c b/drivers/net/ethernet/intel/ice/virt/queues.c index a82024bf388b..0765ee901b7c 100644 --- a/drivers/net/ethernet/intel/ice/virt/queues.c +++ b/drivers/net/ethernet/intel/ice/virt/queues.c @@ -224,6 +224,24 @@ void ice_vf_ena_rxq_interrupt(struct ice_vsi *vsi, u32 q_idx) wr32(hw, QINT_RQCTL(pfq), reg | QINT_RQCTL_CAUSE_ENA_M); } +/** + * ice_vf_dis_rxq_interrupt - disable Rx queue interrupt via QINT_RQCTL + * @vsi: VSI of the VF to configure + * @q_idx: VF queue index used to determine the queue in the PF's space + */ +static void ice_vf_dis_rxq_interrupt(struct ice_vsi *vsi, u32 q_idx) +{ + struct ice_hw *hw = &vsi->back->hw; + u32 pfq = vsi->rxq_map[q_idx]; + u32 reg; + + reg = rd32(hw, QINT_RQCTL(pfq)); + reg &= ~QINT_RQCTL_CAUSE_ENA_M; + wr32(hw, QINT_RQCTL(pfq), reg); + + ice_flush(hw); +} + /** * ice_vc_ena_qs_msg * @vf: pointer to the VF info @@ -416,6 +434,8 @@ int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } + for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) + ice_vf_dis_rxq_interrupt(vsi, vf_q_id); bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); } else if (q_map) { for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { @@ -436,6 +456,7 @@ int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } + ice_vf_dis_rxq_interrupt(vsi, vf_q_id); /* Clear enabled queues flag */ clear_bit(vf_q_id, vf->rxq_ena); } diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 131a8121839b..590119f4097d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -139,7 +139,7 @@ static int idpf_mb_intr_req_irq(struct idpf_adapter *adapter) if (err) { dev_err(&adapter->pdev->dev, "IRQ request for mailbox failed, error: %d\n", err); - + kfree(name); return err; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index c859665b2dc8..e6563ad31f5c 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3075,10 +3075,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb, tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE; tx_params.eop_cmd = IDPF_TXD_FLEX_FLOW_CMD_EOP; - /* Set the RE bit to periodically "clean" the descriptor ring. - * MIN_GAP is set to MIN_RING size to ensure it will be set at - * least once each time around the ring. - */ + /* Set the RE bit periodically to "clean" the descriptor ring */ if (idpf_tx_splitq_need_re(tx_q)) { tx_params.eop_cmd |= IDPF_TXD_FLEX_FLOW_CMD_RE; tx_q->txq_grp->num_completions_pending++; diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 423cc9486dce..aa0b93b5c859 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -21,7 +21,7 @@ /* Mailbox Queue */ #define IDPF_MAX_MBXQ 1 -#define IDPF_MIN_TXQ_DESC 64 +#define IDPF_MIN_TXQ_DESC 128 #define IDPF_MIN_RXQ_DESC 64 #define IDPF_MIN_TXQ_COMPLQ_DESC 256 #define IDPF_MAX_QIDS 256 diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 61dfcd8cb370..c1f2eff615f1 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2191,8 +2191,6 @@ static inline int igbvf_tx_map_adv(struct igbvf_adapter *adapter, buffer_info->time_stamp = 0; buffer_info->length = 0; buffer_info->mapped_as_page = false; - if (count) - count--; /* clear timestamp and dma mappings for remaining portion of packet */ while (count--) { diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index ebc00ce2e3a6..4ca242ebf3e3 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5354,9 +5354,8 @@ void igc_down(struct igc_adapter *adapter) for (i = 0; i < adapter->num_q_vectors; i++) { if (adapter->q_vector[i]) { - napi_synchronize(&adapter->q_vector[i]->napi); - igc_set_queue_napi(adapter, i, NULL); napi_disable(&adapter->q_vector[i]->napi); + igc_set_queue_napi(adapter, i, NULL); } } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index ae7bded77768..7e42d3291a9f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -889,8 +889,8 @@ static void otx2_handle_link_event(struct otx2_nic *pf) netif_carrier_on(netdev); netif_tx_start_all_queues(netdev); } else { - netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); } } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 065f969ee44e..98cf11a706e1 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3446,7 +3446,7 @@ static void mtk_poll_controller(struct net_device *dev) mtk_tx_irq_disable(eth, MTK_TX_DONE_INT); mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask); - mtk_handle_irq_rx(eth->irq[MTK_FE_IRQ_RX], dev); + mtk_handle_irq_rx(eth->irq[MTK_FE_IRQ_RX], eth); mtk_tx_irq_enable(eth, MTK_TX_DONE_INT); mtk_rx_irq_enable(eth, eth->soc->rx.irq_done_mask); } diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 19aa1f1538aa..c09fb7694fac 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -6187,10 +6187,10 @@ static void nv_remove(struct pci_dev *pci_dev) struct net_device *dev = pci_get_drvdata(pci_dev); struct fe_priv *np = netdev_priv(dev); - free_percpu(np->txrx_stats); - unregister_netdev(dev); + free_percpu(np->txrx_stats); + nv_restore_mac_addr(pci_dev); /* restore any phy related changes */ diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index b5d744d2586f..59a80f719372 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -107,7 +107,7 @@ static void qede_remove(struct pci_dev *pdev); static void qede_shutdown(struct pci_dev *pdev); static void qede_link_update(void *dev, struct qed_link_output *link); static void qede_schedule_recovery_handler(void *dev); -static void qede_recovery_handler(struct qede_dev *edev); +static bool qede_recovery_handler(struct qede_dev *edev); static void qede_schedule_hw_err_handler(void *dev, enum qed_hw_err_type err_type); static void qede_get_eth_tlv_data(void *edev, void *data); @@ -1065,21 +1065,6 @@ void __qede_unlock(struct qede_dev *edev) mutex_unlock(&edev->qede_lock); } -/* This version of the lock should be used when acquiring the RTNL lock is also - * needed in addition to the internal qede lock. - */ -static void qede_lock(struct qede_dev *edev) -{ - rtnl_lock(); - __qede_lock(edev); -} - -static void qede_unlock(struct qede_dev *edev) -{ - __qede_unlock(edev); - rtnl_unlock(); -} - static void qede_periodic_task(struct work_struct *work) { struct qede_dev *edev = container_of(work, struct qede_dev, @@ -1116,6 +1101,8 @@ static void qede_sp_task(struct work_struct *work) */ if (test_and_clear_bit(QEDE_SP_RECOVERY, &edev->sp_flags)) { + bool reloaded; + cancel_delayed_work_sync(&edev->periodic_task); #ifdef CONFIG_QED_SRIOV /* SRIOV must be disabled outside the lock to avoid a deadlock. @@ -1124,9 +1111,17 @@ static void qede_sp_task(struct work_struct *work) if (pci_num_vf(edev->pdev)) qede_sriov_configure(edev->pdev, 0); #endif - qede_lock(edev); - qede_recovery_handler(edev); - qede_unlock(edev); + rtnl_lock(); + __qede_lock(edev); + reloaded = qede_recovery_handler(edev); + __qede_unlock(edev); + + /* The udp_tunnel core synchronously calls back into + * qede_udp_tunnel_sync(), which takes the qede lock. + */ + if (reloaded) + udp_tunnel_nic_reset_ntf(edev->ndev); + rtnl_unlock(); } __qede_lock(edev); @@ -2667,9 +2662,13 @@ static void qede_recovery_failed(struct qede_dev *edev) edev->ops->common->set_power_state(edev->cdev, PCI_D3hot); } -static void qede_recovery_handler(struct qede_dev *edev) +/* Returns true if an open device was successfully reloaded and its + * udp_tunnel ports need to be re-synced by the caller. + */ +static bool qede_recovery_handler(struct qede_dev *edev) { u32 curr_state = edev->state; + bool reloaded = false; int rc; DP_NOTICE(edev, "Starting a recovery process\n"); @@ -2699,17 +2698,18 @@ static void qede_recovery_handler(struct qede_dev *edev) goto err; qede_config_rx_mode(edev->ndev); - udp_tunnel_nic_reset_ntf(edev->ndev); + reloaded = true; } edev->state = curr_state; DP_NOTICE(edev, "Recovery handling is done\n"); - return; + return reloaded; err: qede_recovery_failed(edev); + return false; } static void qede_atomic_hw_err_handler(struct qede_dev *edev) diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c index a57a525327a3..bc9b14614f7a 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase_main.c +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -1620,6 +1620,9 @@ static netdev_tx_t rtase_start_xmit(struct sk_buff *skb, err_dma_1: ring->skbuff[entry] = NULL; rtase_tx_clear_range(ring, ring->cur_idx + 1, frags); + if (frags) + /* the frags were cleared above, along with the skb */ + return NETDEV_TX_OK; err_dma_0: tp->stats.tx_dropped++; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 849c5a6c2af1..848a0578cea1 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -599,14 +599,13 @@ static int init_dma_desc_rings(struct net_device *netd) return 0; -txalloc_err: - while (queue_num--) - free_tx_ring(priv->device, priv->txq[queue_num], tx_rsize); - return ret; - rxalloc_err: while (queue_num--) free_rx_ring(priv->device, priv->rxq[queue_num], rx_rsize); + queue_num = SXGBE_TX_QUEUES; +txalloc_err: + while (queue_num--) + free_tx_ring(priv->device, priv->txq[queue_num], tx_rsize); return ret; } @@ -1081,7 +1080,9 @@ static int sxgbe_open(struct net_device *dev) priv->dma_buf_sz = SXGBE_ALIGN(DMA_BUFFER_SIZE); priv->tx_tc = TC_DEFAULT; priv->rx_tc = TC_DEFAULT; - init_dma_desc_rings(dev); + ret = init_dma_desc_rings(dev); + if (ret) + goto init_phy_error; /* DMA initialization and SW reset */ ret = sxgbe_init_dma_engine(priv); @@ -1190,6 +1191,7 @@ static int sxgbe_open(struct net_device *dev) init_error: free_dma_desc_resources(priv); +init_phy_error: if (dev->phydev) phy_disconnect(dev->phydev); phy_error: diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 678dce480f15..380edc64e45e 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -1549,6 +1549,8 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, if (skb_vlan_tag_present(skb)) { tx_flags |= skb_vlan_tag_get(skb) << WX_TX_FLAGS_VLAN_SHIFT; tx_flags |= WX_TX_FLAGS_HW_VLAN; + } else if (eth_type_vlan(skb->protocol)) { + tx_flags |= WX_TX_FLAGS_SW_VLAN; } if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 918244308215..1b7fc17bf391 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1861,8 +1861,8 @@ struct phylink *phylink_create(struct phylink_config *config, } else if (config->type == PHYLINK_DEV) { pl->dev = config->dev; } else { - kfree(pl); - return ERR_PTR(-EINVAL); + ret = -EINVAL; + goto free_pl; } pl->mac_supports_eee_ops = phylink_mac_implements_lpi(mac_ops); @@ -1895,28 +1895,29 @@ struct phylink *phylink_create(struct phylink_config *config, phylink_validate(pl, pl->supported, &pl->link_config); ret = phylink_parse_mode(pl, fwnode); - if (ret < 0) { - kfree(pl); - return ERR_PTR(ret); - } + if (ret < 0) + goto free_pl; if (pl->cfg_link_an_mode == MLO_AN_FIXED) { ret = phylink_parse_fixedlink(pl, fwnode); - if (ret < 0) { - kfree(pl); - return ERR_PTR(ret); - } + if (ret < 0) + goto release_link_gpio; } pl->req_link_an_mode = pl->cfg_link_an_mode; ret = phylink_register_sfp(pl, fwnode); - if (ret < 0) { - kfree(pl); - return ERR_PTR(ret); - } + if (ret < 0) + goto release_link_gpio; return pl; + +release_link_gpio: + if (pl->link_gpio) + gpiod_put(pl->link_gpio); +free_pl: + kfree(pl); + return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(phylink_create); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 4595c61c0790..a72b9504b8e6 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -756,7 +756,7 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, u32 frame_sz; if (skb_shared(skb) || skb_head_is_locked(skb) || - skb_shinfo(skb)->nr_frags || + skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { if (skb_pp_cow_data(rq->page_pool, pskb, XDP_PACKET_HEADROOM)) goto drop; @@ -771,7 +771,7 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, xdp_prepare_buff(xdp, skb->head, skb_headroom(skb), skb_headlen(skb), true); - if (skb_is_nonlinear(skb)) { + if (skb_shinfo(skb)->nr_frags) { skb_shinfo(skb)->xdp_frags_size = skb->data_len; xdp_buff_set_frags_flag(xdp); } else { diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index cb7b01e492fa..4527d2d653b1 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1852,7 +1852,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) if (dev->flags & IFF_NOARP) goto out; - if (!pskb_may_pull(skb, arp_hdr_len(dev))) { + if (!pskb_network_may_pull(skb, arp_hdr_len(dev))) { dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); @@ -2115,7 +2115,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) { struct iphdr *pip; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) return false; pip = ip_hdr(skb); n = neigh_lookup(&arp_tbl, &pip->daddr, dev); @@ -2141,7 +2141,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) */ if (!ipv6_stub->nd_tbl) return false; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) return false; pip6 = ipv6_hdr(skb); n = neigh_lookup(ipv6_stub->nd_tbl, &pip6->daddr, dev); @@ -2163,13 +2163,19 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) } if (n) { + u8 haddr[ETH_ALEN]; bool diff; - diff = !ether_addr_equal(eth_hdr(skb)->h_dest, n->ha); + neigh_ha_snapshot(haddr, n, dev); + diff = !ether_addr_equal_unaligned(eth_hdr(skb)->h_dest, haddr); if (diff) { + if (skb_cow_head(skb, 0)) { + neigh_release(n); + return false; + } memcpy(eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, dev->addr_len); - memcpy(eth_hdr(skb)->h_dest, n->ha, dev->addr_len); + memcpy(eth_hdr(skb)->h_dest, haddr, dev->addr_len); } neigh_release(n); return diff; @@ -2759,8 +2765,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) return arp_reduce(dev, skb, vni); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(eth->h_proto) == ETH_P_IPV6 && - pskb_may_pull(skb, sizeof(struct ipv6hdr) + - sizeof(struct nd_msg)) && + pskb_network_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1); @@ -2798,6 +2804,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) (ntohs(eth->h_proto) == ETH_P_IP || ntohs(eth->h_proto) == ETH_P_IPV6)) { did_rsc = route_shortcircuit(dev, skb); + eth = eth_hdr(skb); if (did_rsc) f = vxlan_find_mac_tx(vxlan, eth->h_dest, vni); } diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c index 4e02a669d045..2ddcbf102b89 100644 --- a/drivers/net/vxlan/vxlan_mdb.c +++ b/drivers/net/vxlan/vxlan_mdb.c @@ -1631,7 +1631,7 @@ struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan, switch (skb->protocol) { case htons(ETH_P_IP): - if (!pskb_may_pull(skb, sizeof(struct iphdr))) + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) return NULL; group.dst.sa.sa_family = AF_INET; group.dst.sin.sin_addr.s_addr = ip_hdr(skb)->daddr; @@ -1640,7 +1640,7 @@ struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan, break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) return NULL; group.dst.sa.sa_family = AF_INET6; group.dst.sin6.sin6_addr = ipv6_hdr(skb)->daddr; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index 0beb38047df5..20b890f7ae7f 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -1070,6 +1070,7 @@ static int brcmf_ops_sdio_probe(struct sdio_func *func, bus_if = kzalloc(sizeof(*bus_if), GFP_KERNEL); if (!bus_if) return -ENOMEM; + mutex_init(&bus_if->bus_reset_lock); sdiodev = kzalloc(sizeof(*sdiodev), GFP_KERNEL); if (!sdiodev) { kfree(bus_if); @@ -1131,6 +1132,14 @@ static void brcmf_ops_sdio_remove(struct sdio_func *func) if (func->num != 1) return; + /* Drain bus_reset before the shared brcmf_sdiod_remove() + * teardown, which the SDIO reset callback also reaches. The + * data worker can arm bus_reset via brcmf_fw_crashed(); cancel + * it first. + */ + brcmf_sdio_cancel_datawork(sdiodev->bus); + brcmf_bus_cancel_reset_work(bus_if); + /* only proceed with rest of cleanup if func 1 */ brcmf_sdiod_remove(sdiodev); @@ -1205,6 +1214,8 @@ static int brcmf_ops_sdio_suspend(struct device *dev) } else { /* power will be cut so remove device, probe again in resume */ brcmf_sdiod_intr_unregister(sdiodev); + brcmf_sdio_cancel_datawork(sdiodev->bus); + brcmf_bus_cancel_reset_work(bus_if); ret = brcmf_sdiod_remove(sdiodev); if (ret) brcmf_err("Failed to remove device on suspend\n"); @@ -1230,6 +1241,8 @@ static int brcmf_ops_sdio_resume(struct device *dev) ret = brcmf_sdiod_probe(sdiodev); if (ret) brcmf_err("Failed to probe device on resume\n"); + else + brcmf_bus_allow_reset_work(bus_if); } else { if (sdiodev->wowl_enabled && sdiodev->settings->bus.sdio.oob_irq_supported) disable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h index fe31051a9e11..9371c1489948 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/firmware.h> #include <linux/device.h> +#include <linux/mutex.h> #include "debug.h" /* IDs of the 6 default common rings of msgbuf protocol */ @@ -179,6 +180,8 @@ struct brcmf_bus { enum brcmf_fwvendor fwvid; bool always_use_fws_queue; bool wowl_supported; + bool removing; /* device removal in progress; quiesce async work */ + struct mutex bus_reset_lock; const struct brcmf_bus_ops *ops; struct brcmf_bus_msgbuf *msgbuf; @@ -186,6 +189,9 @@ struct brcmf_bus { struct list_head list; }; +void brcmf_bus_cancel_reset_work(struct brcmf_bus *bus_if); +void brcmf_bus_allow_reset_work(struct brcmf_bus *bus_if); + /* * callback wrappers */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index 862a0336a0b5..169e62b9d773 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -1167,6 +1167,35 @@ static int brcmf_revinfo_read(struct seq_file *s, void *data) return 0; } +/* + * Serialize arming from debugfs reset and brcmf_fw_crashed() against + * teardown. The remove path sets ->removing and drains the work while + * holding bus_reset_lock, so a racing armer is either drained or skips it. + */ +static void brcmf_bus_schedule_reset(struct brcmf_bus *bus_if) +{ + mutex_lock(&bus_if->bus_reset_lock); + if (bus_if->drvr && bus_if->drvr->bus_reset.func && !bus_if->removing) + schedule_work(&bus_if->drvr->bus_reset); + mutex_unlock(&bus_if->bus_reset_lock); +} + +void brcmf_bus_cancel_reset_work(struct brcmf_bus *bus_if) +{ + mutex_lock(&bus_if->bus_reset_lock); + bus_if->removing = true; + if (bus_if->drvr) + cancel_work_sync(&bus_if->drvr->bus_reset); + mutex_unlock(&bus_if->bus_reset_lock); +} + +void brcmf_bus_allow_reset_work(struct brcmf_bus *bus_if) +{ + mutex_lock(&bus_if->bus_reset_lock); + bus_if->removing = false; + mutex_unlock(&bus_if->bus_reset_lock); +} + static void brcmf_core_bus_reset(struct work_struct *work) { struct brcmf_pub *drvr = container_of(work, struct brcmf_pub, @@ -1187,7 +1216,7 @@ static ssize_t bus_reset_write(struct file *file, const char __user *user_buf, if (value != 1) return -EINVAL; - schedule_work(&drvr->bus_reset); + brcmf_bus_schedule_reset(drvr->bus_if); return count; } @@ -1417,14 +1446,23 @@ void brcmf_dev_coredump(struct device *dev) void brcmf_fw_crashed(struct device *dev) { struct brcmf_bus *bus_if = dev_get_drvdata(dev); - struct brcmf_pub *drvr = bus_if->drvr; + struct brcmf_pub *drvr; + + /* May fire before brcmf_attach() wires up drvr, or after removal + * has cleared it; guard the derefs below (and the arming gate in + * brcmf_bus_schedule_reset() already checks drvr/->removing). + */ + if (!bus_if) + return; + drvr = bus_if->drvr; + if (!drvr) + return; bphy_err(drvr, "Firmware has halted or crashed\n"); brcmf_dev_coredump(dev); - if (drvr->bus_reset.func) - schedule_work(&drvr->bus_reset); + brcmf_bus_schedule_reset(bus_if); } void brcmf_detach(struct device *dev) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index fe4f23decc70..d2a1770540b0 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -2504,6 +2504,7 @@ brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = -ENOMEM; goto fail; } + mutex_init(&bus->bus_reset_lock); bus->msgbuf = kzalloc(sizeof(*bus->msgbuf), GFP_KERNEL); if (!bus->msgbuf) { ret = -ENOMEM; @@ -2599,6 +2600,11 @@ brcmf_pcie_remove(struct pci_dev *pdev) if (devinfo->ci) brcmf_pcie_intr_disable(devinfo); + if (devinfo->irq_allocated) + synchronize_irq(pdev->irq); + + brcmf_bus_cancel_reset_work(bus); + brcmf_detach(&pdev->dev); brcmf_free(&pdev->dev); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 9ab62a2667c7..936df04504ec 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -4560,6 +4560,12 @@ int brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev) return ret; } +void brcmf_sdio_cancel_datawork(struct brcmf_sdio *bus) +{ + if (bus) + cancel_work_sync(&bus->datawork); +} + /* Detach and free everything */ void brcmf_sdio_remove(struct brcmf_sdio *bus) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h index 80180d5c6c87..b93d153a8963 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h @@ -361,6 +361,7 @@ int brcmf_sdiod_remove(struct brcmf_sdio_dev *sdiodev); int brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev); void brcmf_sdio_remove(struct brcmf_sdio *bus); void brcmf_sdio_isr(struct brcmf_sdio *bus, bool in_isr); +void brcmf_sdio_cancel_datawork(struct brcmf_sdio *bus); void brcmf_sdio_wd_timer(struct brcmf_sdio *bus, bool active); void brcmf_sdio_wowl_config(struct device *dev, bool enabled); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c index f0129d10d2b9..b6b5f130c439 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c @@ -1260,6 +1260,7 @@ static int brcmf_usb_probe_cb(struct brcmf_usbdev_info *devinfo, ret = -ENOMEM; goto fail; } + mutex_init(&bus->bus_reset_lock); bus->dev = dev; bus_pub->bus = bus; @@ -1329,6 +1330,8 @@ brcmf_usb_disconnect_cb(struct brcmf_usbdev_info *devinfo) return; brcmf_dbg(USB, "Enter, bus_pub %p\n", devinfo); + brcmf_bus_cancel_reset_work(devinfo->bus_pub.bus); + brcmf_detach(devinfo->dev); brcmf_free(devinfo->dev); kfree(devinfo->bus_pub.bus); diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c index f3397dc6c422..c27814c1ccb1 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c +++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c @@ -44,7 +44,7 @@ static int mwifiex_11n_dispatch_amsdu_pkt(struct mwifiex_private *priv, ntohs(rx_hdr->eth803_hdr.h_proto) == ETH_P_TDLS) { mwifiex_process_tdls_action_frame(priv, (u8 *)rx_hdr, - skb->len); + rx_skb->len); } if (priv->bss_role == MWIFIEX_BSS_ROLE_UAP) diff --git a/drivers/of/address.c b/drivers/of/address.c index f0f8f0dd191c..07d90831dec0 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -757,6 +757,7 @@ EXPORT_SYMBOL(of_property_read_reg); static int parser_init(struct of_pci_range_parser *parser, struct device_node *node, const char *name) { + const __be32 *range; int rlen; parser->node = node; @@ -765,12 +766,20 @@ static int parser_init(struct of_pci_range_parser *parser, parser->ns = of_bus_n_size_cells(node); parser->dma = !strcmp(name, "dma-ranges"); parser->bus = of_match_bus(node); + parser->range = NULL; + parser->end = NULL; - parser->range = of_get_property(node, name, &rlen); - if (parser->range == NULL) + range = of_get_property(node, name, &rlen); + if (!range) return -ENOENT; - parser->end = parser->range + rlen / sizeof(__be32); + if (!parser->bus || + !OF_CHECK_COUNTS(parser->na, parser->ns) || + !OF_CHECK_ADDR_COUNT(parser->pna)) + return -EINVAL; + + parser->range = range; + parser->end = range + rlen / sizeof(__be32); return 0; } @@ -796,7 +805,7 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser, int na = parser->na; int ns = parser->ns; int np = parser->pna + na + ns; - int busflag_na = parser->bus->flag_cells; + int busflag_na; if (!range) return NULL; @@ -804,6 +813,8 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser, if (!parser->range || parser->range + np > parser->end) return NULL; + busflag_na = parser->bus->flag_cells; + range->flags = parser->bus->get_flags(parser->range); range->bus_addr = of_read_number(parser->range + busflag_na, na - busflag_na); @@ -980,8 +991,7 @@ phys_addr_t __init of_dma_get_max_cpu_address(struct device_node *np) np = of_root; ranges = of_get_property(np, "dma-ranges", &len); - if (ranges && len) { - of_dma_range_parser_init(&parser, np); + if (ranges && len && !of_dma_range_parser_init(&parser, np)) { for_each_of_range(&parser, &range) if (range.cpu_addr + range.size > cpu_end) cpu_end = range.cpu_addr + range.size - 1; diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 39d8305a1680..56c2a1e4e86c 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -326,6 +326,7 @@ int __init fdt_scan_reserved_mem(void) err = __reserved_mem_reserve_reg(child, uname); if (!err) count++; + /* * Save the nodes for the dynamically-placed regions * into an array which will be used for allocation right @@ -333,10 +334,17 @@ int __init fdt_scan_reserved_mem(void) * or marked as no-map. This is done to avoid dynamically * allocating from one of the statically-placed regions. */ - if (err == -ENOENT && of_get_flat_dt_prop(child, "size", NULL)) { - dynamic_nodes[dynamic_nodes_cnt] = child; - dynamic_nodes_cnt++; + if (err != -ENOENT || !of_get_flat_dt_prop(child, "size", NULL)) + continue; + + if (dynamic_nodes_cnt == MAX_RESERVED_REGIONS) { + pr_err("too many defined dynamic regions, skip '%s'\n", + uname); + continue; } + + dynamic_nodes[dynamic_nodes_cnt] = child; + dynamic_nodes_cnt++; } for (int i = 0; i < dynamic_nodes_cnt; i++) { const char *uname; diff --git a/drivers/phy/qualcomm/phy-qcom-m31-eusb2.c b/drivers/phy/qualcomm/phy-qcom-m31-eusb2.c index 68f1ba8fec4a..9434bd22ef32 100644 --- a/drivers/phy/qualcomm/phy-qcom-m31-eusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-m31-eusb2.c @@ -221,7 +221,7 @@ static int m31eusb2_phy_init(struct phy *uphy) disable_vreg: regulator_bulk_disable(M31_EUSB_NUM_VREGS, phy->vregs); - return 0; + return ret; } static int m31eusb2_phy_exit(struct phy *uphy) diff --git a/drivers/phy/xilinx/phy-zynqmp.c b/drivers/phy/xilinx/phy-zynqmp.c index fe6b4925d166..240626b55475 100644 --- a/drivers/phy/xilinx/phy-zynqmp.c +++ b/drivers/phy/xilinx/phy-zynqmp.c @@ -53,7 +53,7 @@ #define L0_TM_DIG_6 0x106c #define L0_TM_DIS_DESCRAMBLE_DECODER 0x0f #define L0_TX_DIG_61 0x00f4 -#define L0_TM_DISABLE_SCRAMBLE_ENCODER 0x0f +#define L0_TM_DISABLE_SCRAMBLE_ENCODER (BIT(3) | GENMASK(1, 0)) /* PLL Test Mode register parameters */ #define L0_TM_PLL_DIG_37 0x2094 @@ -502,11 +502,30 @@ static void xpsgtr_lane_set_protocol(struct xpsgtr_phy *gtr_phy) } } -/* Bypass (de)scrambler and 8b/10b decoder and encoder. */ -static void xpsgtr_bypass_scrambler_8b10b(struct xpsgtr_phy *gtr_phy) +/** + * xpsgtr_bypass_scrambler_8b10b - Configure scrambler/encoder behavior + * @gtr_phy: pointer to lane context + * @bypass: true to enable scrambler/encoder bypass (SATA/SGMII), + * false to disable scrambler/encoder bypass (USB3) + * + * Uses RMW to preserve reserved and unrelated register fields. + */ +static void xpsgtr_bypass_scrambler_8b10b(struct xpsgtr_phy *gtr_phy, + bool bypass) { - xpsgtr_write_phy(gtr_phy, L0_TM_DIG_6, L0_TM_DIS_DESCRAMBLE_DECODER); - xpsgtr_write_phy(gtr_phy, L0_TX_DIG_61, L0_TM_DISABLE_SCRAMBLE_ENCODER); + if (bypass) { + xpsgtr_clr_set_phy(gtr_phy, L0_TM_DIG_6, + L0_TM_DIS_DESCRAMBLE_DECODER, + L0_TM_DIS_DESCRAMBLE_DECODER); + xpsgtr_clr_set_phy(gtr_phy, L0_TX_DIG_61, + L0_TM_DISABLE_SCRAMBLE_ENCODER, + L0_TM_DISABLE_SCRAMBLE_ENCODER); + } else { + xpsgtr_clr_set_phy(gtr_phy, L0_TM_DIG_6, + L0_TM_DIS_DESCRAMBLE_DECODER, 0); + xpsgtr_clr_set_phy(gtr_phy, L0_TX_DIG_61, + L0_TM_DISABLE_SCRAMBLE_ENCODER, 0); + } } /* DP-specific initialization. */ @@ -527,7 +546,7 @@ static void xpsgtr_phy_init_sata(struct xpsgtr_phy *gtr_phy) { struct xpsgtr_dev *gtr_dev = gtr_phy->dev; - xpsgtr_bypass_scrambler_8b10b(gtr_phy); + xpsgtr_bypass_scrambler_8b10b(gtr_phy, true); writel(gtr_phy->lane, gtr_dev->siou + SATA_CONTROL_OFFSET); } @@ -543,7 +562,7 @@ static void xpsgtr_phy_init_sgmii(struct xpsgtr_phy *gtr_phy) xpsgtr_clr_set(gtr_dev, TX_PROT_BUS_WIDTH, mask, val); xpsgtr_clr_set(gtr_dev, RX_PROT_BUS_WIDTH, mask, val); - xpsgtr_bypass_scrambler_8b10b(gtr_phy); + xpsgtr_bypass_scrambler_8b10b(gtr_phy, true); } /* Configure TX de-emphasis and margining for DP. */ @@ -658,12 +677,13 @@ static int xpsgtr_phy_init(struct phy *phy) { struct xpsgtr_phy *gtr_phy = phy_get_drvdata(phy); struct xpsgtr_dev *gtr_dev = gtr_phy->dev; - int ret = 0; + int ret; mutex_lock(>r_dev->gtr_mutex); /* Configure and enable the clock when peripheral phy_init call */ - if (clk_prepare_enable(gtr_dev->clk[gtr_phy->refclk])) + ret = clk_prepare_enable(gtr_dev->clk[gtr_phy->refclk]); + if (ret) goto out; /* Skip initialization if not required. */ @@ -673,7 +693,7 @@ static int xpsgtr_phy_init(struct phy *phy) if (gtr_dev->tx_term_fix) { ret = xpsgtr_phy_tx_term_fix(gtr_phy); if (ret < 0) - goto out; + goto out_disable_clk; gtr_dev->tx_term_fix = false; } @@ -687,7 +707,7 @@ static int xpsgtr_phy_init(struct phy *phy) */ ret = xpsgtr_configure_pll(gtr_phy); if (ret) - goto out; + goto out_disable_clk; xpsgtr_lane_set_protocol(gtr_phy); @@ -703,8 +723,16 @@ static int xpsgtr_phy_init(struct phy *phy) case ICM_PROTOCOL_SGMII: xpsgtr_phy_init_sgmii(gtr_phy); break; + + case ICM_PROTOCOL_USB: + xpsgtr_bypass_scrambler_8b10b(gtr_phy, false); + break; } + goto out; + +out_disable_clk: + clk_disable_unprepare(gtr_dev->clk[gtr_phy->refclk]); out: mutex_unlock(>r_dev->gtr_mutex); return ret; @@ -1039,6 +1067,12 @@ static int xpsgtr_probe(struct platform_device *pdev) return PTR_ERR(provider); } + gtr_dev->saved_regs = devm_kmalloc(gtr_dev->dev, + sizeof(save_reg_address), + GFP_KERNEL); + if (!gtr_dev->saved_regs) + return -ENOMEM; + pm_runtime_set_active(gtr_dev->dev); pm_runtime_enable(gtr_dev->dev); @@ -1048,12 +1082,6 @@ static int xpsgtr_probe(struct platform_device *pdev) return ret; } - gtr_dev->saved_regs = devm_kmalloc(gtr_dev->dev, - sizeof(save_reg_address), - GFP_KERNEL); - if (!gtr_dev->saved_regs) - return -ENOMEM; - return 0; } diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index 4f8507ebbdac..80db4195a559 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -162,6 +162,7 @@ config PINCTRL_BM1880 depends on OF && (ARCH_BITMAIN || COMPILE_TEST) default ARCH_BITMAIN select PINMUX + select GENERIC_PINCONF help Pinctrl driver for Bitmain BM1880 SoC. @@ -414,6 +415,7 @@ config PINCTRL_MICROCHIP_SGPIO select GENERIC_PINCTRL_GROUPS select GENERIC_PINMUX_FUNCTIONS select OF_GPIO + select REGMAP_MMIO help Support for the serial GPIO interface used on Microsemi and Microchip SoCs. By using a serial interface, the SIO diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index 0b7f74beb6a6..fdb5ff0e4b0b 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -69,6 +69,10 @@ static int dt_remember_or_free_map(struct pinctrl *p, const char *statename, int i; struct pinctrl_dt_map *dt_map; + /* Initialize dev_name before any allocation can fail */ + for (i = 0; i < num_maps; i++) + map[i].dev_name = NULL; + /* Initialize common mapping table entry fields */ for (i = 0; i < num_maps; i++) { const char *devname; diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 2dac5c71eb00..d962f2e1d2ac 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -886,8 +886,7 @@ static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) u32 pin_reg, mask; int i; - mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | - BIT(WAKE_CNTRL_OFF_S4); + mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3); for (i = 0; i < desc->npins; i++) { int pin = desc->pins[i].number; diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index e99871b90ab9..424b14bc29e9 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -1226,12 +1226,12 @@ static int msm_gpio_irq_reqres(struct irq_data *d) /* * If the wakeup_enable bit is present and marked as available for the * requested GPIO, it should be enabled when the GPIO is marked as - * wake irq in order to allow the interrupt event to be transfered to - * the PDC HW. + * wake irq in order to allow the interrupt event to be transferred to + * the PDC/MPM HW. * While the name implies only the wakeup event, it's also required for * the interrupt event. */ - if (test_bit(d->hwirq, pctrl->skip_wake_irqs) && g->intr_wakeup_present_bit) { + if (g->intr_wakeup_present_bit) { u32 intr_cfg; raw_spin_lock_irqsave(&pctrl->lock, flags); @@ -1259,7 +1259,7 @@ static void msm_gpio_irq_relres(struct irq_data *d) unsigned long flags; /* Disable the wakeup_enable bit if it has been set in msm_gpio_irq_reqres() */ - if (test_bit(d->hwirq, pctrl->skip_wake_irqs) && g->intr_wakeup_present_bit) { + if (g->intr_wakeup_present_bit) { u32 intr_cfg; raw_spin_lock_irqsave(&pctrl->lock, flags); diff --git a/drivers/pinctrl/qcom/pinctrl-sc8280xp.c b/drivers/pinctrl/qcom/pinctrl-sc8280xp.c index cf8297e8b8f8..d6e31b00e1c5 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc8280xp.c +++ b/drivers/pinctrl/qcom/pinctrl-sc8280xp.c @@ -1884,16 +1884,17 @@ static const struct msm_gpio_wakeirq_map sc8280xp_pdc_map[] = { { 126, 200 }, { 127, 225 }, { 128, 262 }, { 129, 201 }, { 130, 209 }, { 131, 173 }, { 132, 202 }, { 136, 210 }, { 138, 171 }, { 139, 226 }, { 140, 227 }, { 142, 228 }, - { 144, 229 }, { 145, 230 }, { 146, 231 }, { 148, 232 }, - { 149, 233 }, { 150, 234 }, { 152, 235 }, { 154, 212 }, - { 157, 213 }, { 161, 219 }, { 170, 236 }, { 171, 221 }, - { 174, 222 }, { 175, 237 }, { 176, 223 }, { 177, 170 }, - { 180, 238 }, { 181, 239 }, { 182, 240 }, { 183, 241 }, - { 184, 242 }, { 185, 243 }, { 190, 178 }, { 193, 184 }, - { 196, 185 }, { 198, 186 }, { 200, 174 }, { 201, 175 }, - { 205, 176 }, { 206, 177 }, { 208, 187 }, { 210, 198 }, - { 211, 199 }, { 212, 204 }, { 215, 205 }, { 220, 188 }, - { 221, 194 }, { 223, 195 }, { 225, 196 }, { 227, 197 }, + { 143, 261 }, { 144, 229 }, { 145, 230 }, { 146, 231 }, + { 148, 232 }, { 149, 233 }, { 150, 234 }, { 151, 264 }, + { 152, 235 }, { 154, 212 }, { 157, 213 }, { 161, 219 }, + { 170, 236 }, { 171, 221 }, { 174, 222 }, { 175, 237 }, + { 176, 223 }, { 177, 170 }, { 180, 238 }, { 181, 239 }, + { 182, 240 }, { 183, 241 }, { 184, 242 }, { 185, 243 }, + { 190, 178 }, { 193, 184 }, { 196, 185 }, { 198, 186 }, + { 200, 174 }, { 201, 175 }, { 205, 176 }, { 206, 177 }, + { 208, 187 }, { 210, 198 }, { 211, 199 }, { 212, 204 }, + { 215, 205 }, { 220, 188 }, { 221, 194 }, { 223, 195 }, + { 225, 196 }, { 227, 197 }, }; static struct msm_pinctrl_soc_data sc8280xp_pinctrl = { diff --git a/drivers/power/supply/bq25890_charger.c b/drivers/power/supply/bq25890_charger.c index 868e86e1749b..f246ec871d5c 100644 --- a/drivers/power/supply/bq25890_charger.c +++ b/drivers/power/supply/bq25890_charger.c @@ -320,7 +320,7 @@ static const u32 bq25890_tspct_tbl[] = { 145, 140, 130, 120, 115, 110, 100, 90, 80, 70, 60, 50, 40, 30, 20, 10, 0, -10, -20, -30, -40, -60, -70, -80, - -90, -10, -120, -140, -150, -170, -190, -210, + -90, -100, -120, -140, -150, -170, -190, -210, }; #define BQ25890_TSPCT_TBL_SIZE ARRAY_SIZE(bq25890_tspct_tbl) diff --git a/drivers/power/supply/max17040_battery.c b/drivers/power/supply/max17040_battery.c index 48453508688a..f4748adec092 100644 --- a/drivers/power/supply/max17040_battery.c +++ b/drivers/power/supply/max17040_battery.c @@ -405,7 +405,11 @@ static int max17040_get_property(struct power_supply *psy, val->intval = chip->low_soc_alert; break; case POWER_SUPPLY_PROP_STATUS: - power_supply_get_property_from_supplier(psy, psp, val); + ret = power_supply_get_property_from_supplier(psy, psp, val); + if (ret == -ENODEV) + val->intval = POWER_SUPPLY_STATUS_UNKNOWN; + else if (ret) + return ret; break; case POWER_SUPPLY_PROP_TEMP: if (!chip->channel_temp) diff --git a/drivers/ptp/ptp_netc.c b/drivers/ptp/ptp_netc.c index 5e381c354d74..1c20d7efab92 100644 --- a/drivers/ptp/ptp_netc.c +++ b/drivers/ptp/ptp_netc.c @@ -769,6 +769,7 @@ static void netc_timer_init(struct netc_timer *priv) TMR_CTRL_TE | TMR_CTRL_FS; netc_timer_wr(priv, NETC_TMR_CTRL, tmr_ctrl); netc_timer_wr(priv, NETC_TMR_PRSC, priv->oclk_prsc); + netc_timer_wr(priv, NETC_TMR_TEMASK, 0); /* Disable FIPER by default */ fiper_ctrl = netc_timer_rd(priv, NETC_TMR_FIPER_CTRL); @@ -901,6 +902,11 @@ static irqreturn_t netc_timer_isr(int irq, void *data) /* Clear interrupts status */ netc_timer_wr(priv, NETC_TMR_TEVENT, tmr_event); + if (!tmr_event) { + spin_unlock(&priv->lock); + return IRQ_NONE; + } + if (tmr_event & TMR_TEVENT_ALMEN(0)) netc_timer_alarm_write(priv, NETC_TMR_DEFAULT_ALARM, 0); @@ -936,7 +942,8 @@ static int netc_timer_init_msix_irq(struct netc_timer *priv) } priv->irq = pci_irq_vector(pdev, 0); - err = request_irq(priv->irq, netc_timer_isr, 0, priv->irq_name, priv); + err = request_irq(priv->irq, netc_timer_isr, IRQF_NO_AUTOEN, + priv->irq_name, priv); if (err) { dev_err(&pdev->dev, "request_irq() failed\n"); pci_free_irq_vectors(pdev); @@ -951,7 +958,6 @@ static void netc_timer_free_msix_irq(struct netc_timer *priv) { struct pci_dev *pdev = priv->pdev; - disable_irq(priv->irq); free_irq(priv->irq, priv); pci_free_irq_vectors(pdev); } @@ -1005,6 +1011,8 @@ static int netc_timer_probe(struct pci_dev *pdev, goto free_msix_irq; } + enable_irq(priv->irq); + return 0; free_msix_irq: @@ -1019,9 +1027,10 @@ static void netc_timer_remove(struct pci_dev *pdev) { struct netc_timer *priv = pci_get_drvdata(pdev); + disable_irq(priv->irq); + ptp_clock_unregister(priv->clock); netc_timer_wr(priv, NETC_TMR_TEMASK, 0); netc_timer_wr(priv, NETC_TMR_CTRL, 0); - ptp_clock_unregister(priv->clock); netc_timer_free_msix_irq(priv); netc_timer_pci_remove(pdev); } diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 40bbbada67f9..9dfa14eb09d2 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -21,6 +21,7 @@ #include <linux/seq_file.h> #include <linux/uaccess.h> #include <linux/io.h> +#include <linux/overflow.h> #include <asm/css_chars.h> #include <asm/machine.h> @@ -3476,11 +3477,11 @@ static int dasd_eckd_check_device_format(struct dasd_device *base, { struct dasd_eckd_private *private = base->private; struct eckd_count *fmt_buffer; - struct irb irb; + size_t fmt_buffer_size; + unsigned int trkcount; int rpt_max, rpt_exp; - int fmt_buffer_size; + struct irb irb; int trk_per_cyl; - int trkcount; int tpm = 0; int rc; @@ -3491,7 +3492,9 @@ static int dasd_eckd_check_device_format(struct dasd_device *base, rpt_exp = recs_per_track(&private->rdc_data, 0, cdata->expect.blksize); trkcount = cdata->expect.stop_unit - cdata->expect.start_unit + 1; - fmt_buffer_size = trkcount * rpt_max * sizeof(struct eckd_count); + if (check_mul_overflow(trkcount, rpt_max, &fmt_buffer_size) || + check_mul_overflow(fmt_buffer_size, sizeof(struct eckd_count), &fmt_buffer_size)) + return -EINVAL; fmt_buffer = kzalloc(fmt_buffer_size, GFP_KERNEL | GFP_DMA); if (!fmt_buffer) diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 8308046a9f8f..a9edc0468a31 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -325,7 +325,7 @@ static int dasd_ioctl_check_format(struct block_device *bdev, void __user *argp) static int dasd_release_space(struct dasd_device *device, struct format_data_t *rdata) { - if (!device->discipline->is_ese && !device->discipline->is_ese(device)) + if (!device->discipline->is_ese || !device->discipline->is_ese(device)) return -ENOTSUPP; if (!device->discipline->release_space) return -ENOTSUPP; diff --git a/drivers/s390/crypto/pkey_cca.c b/drivers/s390/crypto/pkey_cca.c index 6c7897a93f27..d780ea60c9e1 100644 --- a/drivers/s390/crypto/pkey_cca.c +++ b/drivers/s390/crypto/pkey_cca.c @@ -233,22 +233,16 @@ static int cca_key2protkey(const struct pkey_apqn *apqns, size_t nr_apqns, if (hdr->type == TOKTYPE_CCA_INTERNAL && hdr->version == TOKVER_CCA_AES) { /* CCA AES data key */ - if (keylen < sizeof(struct secaeskeytoken)) - return -EINVAL; - if (cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0)) + if (cca_check_secaeskeytoken(pkey_dbf_info, 3, key, keylen, 0)) return -EINVAL; } else if (hdr->type == TOKTYPE_CCA_INTERNAL && hdr->version == TOKVER_CCA_VLSC) { /* CCA AES cipher key */ - if (keylen < hdr->len) - return -EINVAL; if (cca_check_secaescipherkey(pkey_dbf_info, - 3, key, 0, 1)) + 3, key, keylen, 0, 1)) return -EINVAL; } else if (hdr->type == TOKTYPE_CCA_INTERNAL_PKA) { /* CCA ECC (private) key */ - if (keylen < sizeof(struct eccprivkeytoken)) - return -EINVAL; if (cca_check_sececckeytoken(pkey_dbf_info, 3, key, keylen, 1)) return -EINVAL; } else { @@ -476,7 +470,7 @@ static int cca_verifykey(const u8 *key, u32 keylen, hdr->version == TOKVER_CCA_AES) { struct secaeskeytoken *t = (struct secaeskeytoken *)key; - rc = cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0); + rc = cca_check_secaeskeytoken(pkey_dbf_info, 3, key, keylen, 0); if (rc) goto out; *keytype = PKEY_TYPE_CCA_DATA; @@ -504,7 +498,8 @@ static int cca_verifykey(const u8 *key, u32 keylen, hdr->version == TOKVER_CCA_VLSC) { struct cipherkeytoken *t = (struct cipherkeytoken *)key; - rc = cca_check_secaescipherkey(pkey_dbf_info, 3, key, 0, 1); + rc = cca_check_secaescipherkey(pkey_dbf_info, 3, + key, keylen, 0, 1); if (rc) goto out; *keytype = PKEY_TYPE_CCA_CIPHER; diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 4e6bf1cb3475..a25b58e06f92 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -1083,7 +1083,7 @@ static long _zcrypt_send_ep11_cprb(u32 xflags, struct ap_perms *perms, print_hex_dump_debug("ep11req: ", DUMP_PREFIX_ADDRESS, 16, 1, ap_msg.msg, ap_msg.len, false); - if (perms != &ap_perms && domain < AUTOSEL_DOM) { + if (perms != &ap_perms && domain < AP_DOMAINS) { if (ap_msg.flags & AP_MSG_FLAG_ADMIN) { if (!test_bit_inv(domain, perms->adm)) { rc = -ENODEV; diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index fe61df34f614..1de67038d164 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -63,12 +63,18 @@ static DEFINE_MUTEX(dev_status_mem_mutex); * also checked. Returns 0 on success or errno value on failure. */ int cca_check_secaeskeytoken(debug_info_t *dbg, int dbflvl, - const u8 *token, int keybitsize) + const u8 *token, u32 keysize, int keybitsize) { struct secaeskeytoken *t = (struct secaeskeytoken *)token; #define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) + if (keysize < sizeof(*t)) { + if (dbg) + DBF("%s keysize %u < min token size %zu\n", + __func__, keysize, sizeof(*t)); + return -EINVAL; + } if (t->type != TOKTYPE_CCA_INTERNAL) { if (dbg) DBF("%s token check failed, type 0x%02x != 0x%02x\n", @@ -102,14 +108,20 @@ EXPORT_SYMBOL(cca_check_secaeskeytoken); * Returns 0 on success or errno value on failure. */ int cca_check_secaescipherkey(debug_info_t *dbg, int dbflvl, - const u8 *token, int keybitsize, - int checkcpacfexport) + const u8 *token, u32 keysize, + int keybitsize, int checkcpacfexport) { struct cipherkeytoken *t = (struct cipherkeytoken *)token; bool keybitsizeok = true; #define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) + if (keysize < sizeof(*t)) { + if (dbg) + DBF("%s keysize %u < min token size %zu\n", + __func__, keysize, sizeof(*t)); + return -EINVAL; + } if (t->type != TOKTYPE_CCA_INTERNAL) { if (dbg) DBF("%s token check failed, type 0x%02x != 0x%02x\n", @@ -122,6 +134,18 @@ int cca_check_secaescipherkey(debug_info_t *dbg, int dbflvl, __func__, (int)t->version, TOKVER_CCA_VLSC); return -EINVAL; } + if (t->len > keysize) { + if (dbg) + DBF("%s token check failed, len %d > keysize %u\n", + __func__, (int)t->len, keysize); + return -EINVAL; + } + if (t->len < sizeof(*t)) { + if (dbg) + DBF("%s token check failed, len %d < min token size %zu\n", + __func__, (int)t->len, sizeof(*t)); + return -EINVAL; + } if (t->algtype != 0x02) { if (dbg) DBF("%s token check failed, algtype 0x%02x != 0x02\n", @@ -196,6 +220,12 @@ int cca_check_sececckeytoken(debug_info_t *dbg, int dbflvl, #define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) + if (keysize < sizeof(*t)) { + if (dbg) + DBF("%s keysize %u < min token size %zu\n", + __func__, keysize, sizeof(*t)); + return -EINVAL; + } if (t->type != TOKTYPE_CCA_INTERNAL_PKA) { if (dbg) DBF("%s token check failed, type 0x%02x != 0x%02x\n", @@ -208,6 +238,12 @@ int cca_check_sececckeytoken(debug_info_t *dbg, int dbflvl, __func__, (int)t->len, keysize); return -EINVAL; } + if (t->len < sizeof(*t)) { + if (dbg) + DBF("%s token check failed, len %d < min token size %zu\n", + __func__, (int)t->len, sizeof(*t)); + return -EINVAL; + } if (t->secid != 0x20) { if (dbg) DBF("%s token check failed, secid 0x%02x != 0x20\n", @@ -444,7 +480,8 @@ int cca_genseckey(u16 cardnr, u16 domain, /* check secure key token */ rc = cca_check_secaeskeytoken(zcrypt_dbf_info, DBF_ERR, - prepparm->lv3.keyblock.tok, 8 * keysize); + prepparm->lv3.keyblock.tok, + seckeysize, 8 * keysize); if (rc) { rc = -EIO; goto out; @@ -583,7 +620,8 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, /* check secure key token */ rc = cca_check_secaeskeytoken(zcrypt_dbf_info, DBF_ERR, - prepparm->lv3.keyblock.tok, 8 * keysize); + prepparm->lv3.keyblock.tok, + seckeysize, 8 * keysize); if (rc) { rc = -EIO; goto out; @@ -843,6 +881,7 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, } kb; } __packed * prepparm; struct cipherkeytoken *t; + u32 keybuflen; /* get already prepared memory for 2 cprbs with param block each */ rc = alloc_and_prep_cprbmem(PARMBSIZE, &mem, @@ -937,23 +976,28 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, } /* and some checks on the generated key */ + t = (struct cipherkeytoken *)prepparm->kb.tlv1.gen_key; + if (prepparm->kb.tlv1.len < 2 * sizeof(uint16_t) + sizeof(*t)) { + rc = -EIO; + goto out; + } + keybuflen = prepparm->kb.tlv1.len - 2 * sizeof(uint16_t); rc = cca_check_secaescipherkey(zcrypt_dbf_info, DBF_ERR, prepparm->kb.tlv1.gen_key, - keybitsize, 1); + keybuflen, keybitsize, 1); if (rc) { rc = -EIO; goto out; } /* copy the generated vlsc key token */ - t = (struct cipherkeytoken *)prepparm->kb.tlv1.gen_key; if (keybuf) { - if (*keybufsize >= t->len) - memcpy(keybuf, t, t->len); + if (*keybufsize >= keybuflen) + memcpy(keybuf, t, keybuflen); else rc = -EINVAL; } - *keybufsize = t->len; + *keybufsize = keybuflen; out: free_cprbmem(mem, PARMBSIZE, false, xflags); @@ -972,7 +1016,8 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, int clr_key_bit_size, u8 *key_token, int *key_token_size, - u32 xflags) + u32 xflags, + bool scrub) { int rc, n; u8 *mem, *ptr; @@ -1112,7 +1157,7 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, *key_token_size = t->len; out: - free_cprbmem(mem, PARMBSIZE, false, xflags); + free_cprbmem(mem, PARMBSIZE, scrub, xflags); return rc; } @@ -1163,28 +1208,32 @@ int cca_clr2cipherkey(u16 card, u16 dom, u32 keybitsize, u32 keygenflags, * 4/4 COMPLETE the secure cipher key import */ rc = _ip_cprb_helper(card, dom, "AES ", "FIRST ", "MIN3PART", - exorbuf, keybitsize, token, &tokensize, xflags); + exorbuf, keybitsize, token, &tokensize, + xflags, true); if (rc) { ZCRYPT_DBF_ERR("%s clear key import 1/4 with CSNBKPI2 failed, rc=%d\n", __func__, rc); goto out; } rc = _ip_cprb_helper(card, dom, "AES ", "ADD-PART", NULL, - clrkey, keybitsize, token, &tokensize, xflags); + clrkey, keybitsize, token, &tokensize, + xflags, true); if (rc) { ZCRYPT_DBF_ERR("%s clear key import 2/4 with CSNBKPI2 failed, rc=%d\n", __func__, rc); goto out; } rc = _ip_cprb_helper(card, dom, "AES ", "ADD-PART", NULL, - exorbuf, keybitsize, token, &tokensize, xflags); + exorbuf, keybitsize, token, &tokensize, + xflags, true); if (rc) { ZCRYPT_DBF_ERR("%s clear key import 3/4 with CSNBKPI2 failed, rc=%d\n", __func__, rc); goto out; } rc = _ip_cprb_helper(card, dom, "AES ", "COMPLETE", NULL, - NULL, keybitsize, token, &tokensize, xflags); + NULL, keybitsize, token, &tokensize, + xflags, true); if (rc) { ZCRYPT_DBF_ERR("%s clear key import 4/4 with CSNBKPI2 failed, rc=%d\n", __func__, rc); @@ -1201,6 +1250,8 @@ int cca_clr2cipherkey(u16 card, u16 dom, u32 keybitsize, u32 keygenflags, *keybufsize = tokensize; out: + memzero_explicit(exorbuf, sizeof(exorbuf)); + memzero_explicit(mem, CPRB_MEMPOOL_ITEM_SIZE); mempool_free(mem, cprb_mempool); return rc; } @@ -1262,6 +1313,9 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, } __packed * prepparm; int keytoklen = ((struct cipherkeytoken *)ckey)->len; + if (keytoklen > PARMBSIZE - sizeof(struct aureqparm)) + return -EINVAL; + /* get already prepared memory for 2 cprbs with param block each */ rc = alloc_and_prep_cprbmem(PARMBSIZE, &mem, &preqcblk, &prepcblk, xflags); @@ -1426,6 +1480,9 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, } __packed * prepparm; int keylen = ((struct eccprivkeytoken *)key)->len; + if (keylen > PARMBSIZE - sizeof(struct aureqparm)) + return -EINVAL; + /* get already prepared memory for 2 cprbs with param block each */ rc = alloc_and_prep_cprbmem(PARMBSIZE, &mem, &preqcblk, &prepcblk, xflags); diff --git a/drivers/s390/crypto/zcrypt_ccamisc.h b/drivers/s390/crypto/zcrypt_ccamisc.h index 1ecc4e37e9ad..5f5bd93e0931 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.h +++ b/drivers/s390/crypto/zcrypt_ccamisc.h @@ -136,7 +136,7 @@ struct eccprivkeytoken { * also checked. Returns 0 on success or errno value on failure. */ int cca_check_secaeskeytoken(debug_info_t *dbg, int dbflvl, - const u8 *token, int keybitsize); + const u8 *token, u32 keysize, int keybitsize); /* * Simple check if the token is a valid CCA secure AES cipher key @@ -146,8 +146,8 @@ int cca_check_secaeskeytoken(debug_info_t *dbg, int dbflvl, * Returns 0 on success or errno value on failure. */ int cca_check_secaescipherkey(debug_info_t *dbg, int dbflvl, - const u8 *token, int keybitsize, - int checkcpacfexport); + const u8 *token, u32 keysize, + int keybitsize, int checkcpacfexport); /* * Simple check if the token is a valid CCA secure ECC private diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index edc0bcd46923..64ca42ca78c4 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -6528,6 +6528,9 @@ int qeth_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *d struct qeth_card *card = dev->ml_priv; int rc = 0; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + switch (cmd) { case SIOC_QETH_ADP_SET_SNMP_CONTROL: rc = qeth_snmp_command(card, data); diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c index dc2265ebb11b..03f723042434 100644 --- a/drivers/s390/scsi/zfcp_aux.c +++ b/drivers/s390/scsi/zfcp_aux.c @@ -254,6 +254,7 @@ static int zfcp_allocate_low_mem_buffers(struct zfcp_adapter *adapter) static void zfcp_free_low_mem_buffers(struct zfcp_adapter *adapter) { mempool_destroy(adapter->pool.erp_req); + mempool_destroy(adapter->pool.gid_pn_req); mempool_destroy(adapter->pool.scsi_req); mempool_destroy(adapter->pool.scsi_abort); mempool_destroy(adapter->pool.qtcb_pool); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index f30d4a58d7ab..16256a052925 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -5261,15 +5261,7 @@ static int _resume_v3_hw(struct device *device) return rc; } phys_init_v3_hw(hisi_hba); - - /* - * If a directly-attached disk is removed during suspend, a deadlock - * may occur, as the PHYE_RESUME_TIMEOUT processing will require the - * hisi_hba->device to be active, which can only happen when resume - * completes. So don't wait for the HA event workqueue to drain upon - * resume. - */ - sas_resume_ha_no_sync(sha); + sas_resume_ha(sha); clear_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags); dev_warn(dev, "end of resuming controller\n"); diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index c9f410c50978..e2adebc80b3a 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -918,7 +918,7 @@ static void iscsi_scsi_cmd_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr, } senselen = get_unaligned_be16(data); - if (datalen < senselen) + if (datalen < senselen + 2) goto invalid_datalen; memcpy(sc->sense_buffer, data + 2, diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index e90805ba868f..7223bb18b048 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -752,13 +752,6 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr) rc = __iscsi_complete_pdu(conn, hdr, NULL, 0); spin_unlock(&conn->session->back_lock); break; - case ISCSI_OP_SCSI_CMD_RSP: - if (tcp_conn->in.datalen) { - iscsi_tcp_data_recv_prep(tcp_conn); - return 0; - } - rc = iscsi_complete_pdu(conn, hdr, NULL, 0); - break; case ISCSI_OP_R2T: if (ahslen) { rc = ISCSI_ERR_AHSLEN; @@ -766,6 +759,7 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr) } rc = iscsi_tcp_r2t_rsp(conn, hdr); break; + case ISCSI_OP_SCSI_CMD_RSP: case ISCSI_OP_LOGIN_RSP: case ISCSI_OP_TEXT_RSP: case ISCSI_OP_REJECT: diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c index 8566bb1208a0..ac157ab6a301 100644 --- a/drivers/scsi/libsas/sas_init.c +++ b/drivers/scsi/libsas/sas_init.c @@ -409,7 +409,7 @@ static void sas_resume_insert_broadcast_ha(struct sas_ha_struct *ha) } } -static void _sas_resume_ha(struct sas_ha_struct *ha, bool drain) +void sas_resume_ha(struct sas_ha_struct *ha) { const unsigned long tmo = msecs_to_jiffies(25000); int i; @@ -425,6 +425,23 @@ static void _sas_resume_ha(struct sas_ha_struct *ha, bool drain) dev_info(ha->dev, "waiting up to 25 seconds for %d phy%s to resume\n", i, i > 1 ? "s" : ""); wait_event_timeout(ha->eh_wait_q, phys_suspended(ha) == 0, tmo); + + /* + * All phys are back up or timed out. Turn on I/O and drain + * pending work. + */ + scsi_unblock_requests(ha->shost); + sas_drain_work(ha); + + /* + * Send PHYE_RESUME_TIMEOUT after sas_drain_work(). The handler + * calls sas_deform_port() -> sas_destruct_devices(), which removes + * SCSI devices and, for LLDDs using device_link() PM sync, waits + * for the host to be runtime-active. Sending it before the drain + * would deadlock: the drain waits for the handler, the handler + * waits for host resume, and host resume waits for the drain to + * finish. + */ for (i = 0; i < ha->num_phys; i++) { struct asd_sas_phy *phy = ha->sas_phy[i]; @@ -435,12 +452,6 @@ static void _sas_resume_ha(struct sas_ha_struct *ha, bool drain) } } - /* all phys are back up or timed out, turn on i/o so we can - * flush out disks that did not return - */ - scsi_unblock_requests(ha->shost); - if (drain) - sas_drain_work(ha); clear_bit(SAS_HA_RESUMING, &ha->state); sas_queue_deferred_work(ha); @@ -449,20 +460,8 @@ static void _sas_resume_ha(struct sas_ha_struct *ha, bool drain) */ sas_resume_insert_broadcast_ha(ha); } - -void sas_resume_ha(struct sas_ha_struct *ha) -{ - _sas_resume_ha(ha, true); -} EXPORT_SYMBOL(sas_resume_ha); -/* A no-sync variant, which does not call sas_drain_ha(). */ -void sas_resume_ha_no_sync(struct sas_ha_struct *ha) -{ - _sas_resume_ha(ha, false); -} -EXPORT_SYMBOL(sas_resume_ha_no_sync); - void sas_suspend_ha(struct sas_ha_struct *ha) { int i; diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 047d56d23bea..bd7c5b60fc38 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -5896,6 +5896,7 @@ static int resp_report_zones(struct scsi_cmnd *scp, u32 alloc_len, rep_opts, rep_len; bool partial; u64 lba, zs_lba; + u64 arr_len; u8 *arr = NULL, *desc; u8 *cmd = scp->cmnd; struct sdeb_zone_state *zsp = NULL; @@ -5917,9 +5918,12 @@ static int resp_report_zones(struct scsi_cmnd *scp, return check_condition_result; } - rep_max_zones = (alloc_len - 64) >> ilog2(RZONES_DESC_HD); + rep_max_zones = (ALIGN((u64)alloc_len, RZONES_DESC_HD) - RZONES_DESC_HD) >> + ilog2(RZONES_DESC_HD); + rep_max_zones = min_t(unsigned int, rep_max_zones, devip->nr_zones); + arr_len = (u64)RZONES_DESC_HD * (rep_max_zones + 1); - arr = kzalloc(alloc_len, GFP_ATOMIC | __GFP_NOWARN); + arr = kzalloc(arr_len, GFP_ATOMIC | __GFP_NOWARN); if (!arr) { mk_sense_buffer(scp, ILLEGAL_REQUEST, INSUFF_RES_ASC, INSUFF_RES_ASCQ); diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 7a745c2e0892..640e8723a08e 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -109,6 +109,7 @@ * @rxbuf: Pointer to the RX buffer * @tx_bytes: Number of bytes left to transfer * @rx_bytes: Number of bytes requested + * @n_bytes: Number of bytes per word * @dev_busy: Device busy flag * @is_decoded_cs: Flag for decoder property set or not * @tx_fifo_depth: Depth of the TX FIFO @@ -120,16 +121,24 @@ struct cdns_spi { struct clk *pclk; unsigned int clk_rate; u32 speed_hz; - const u8 *txbuf; - u8 *rxbuf; + const void *txbuf; + void *rxbuf; int tx_bytes; int rx_bytes; + u8 n_bytes; u8 dev_busy; u32 is_decoded_cs; unsigned int tx_fifo_depth; struct reset_control *rstc; }; +enum cdns_spi_frame_n_bytes { + CDNS_SPI_N_BYTES_NULL = 0, + CDNS_SPI_N_BYTES_U8 = 1, + CDNS_SPI_N_BYTES_U16 = 2, + CDNS_SPI_N_BYTES_U32 = 4 +}; + /* Macros for the SPI controller read/write */ static inline u32 cdns_spi_read(struct cdns_spi *xspi, u32 offset) { @@ -305,13 +314,87 @@ static int cdns_spi_setup_transfer(struct spi_device *spi, return 0; } +static u8 cdns_spi_n_bytes(struct spi_transfer *transfer) +{ + if (transfer->bits_per_word <= 8) + return CDNS_SPI_N_BYTES_U8; + else if (transfer->bits_per_word <= 16) + return CDNS_SPI_N_BYTES_U16; + else + return CDNS_SPI_N_BYTES_U32; +} + +static inline void cdns_spi_reader(struct cdns_spi *xspi) +{ + u32 rxw = 0; + + if (xspi->rxbuf && !IS_ALIGNED((uintptr_t)xspi->rxbuf, xspi->n_bytes)) { + pr_err("%s: rxbuf address is not aligned for %d bytes\n", + __func__, xspi->n_bytes); + return; + } + + rxw = cdns_spi_read(xspi, CDNS_SPI_RXD); + if (xspi->rxbuf) { + switch (xspi->n_bytes) { + case CDNS_SPI_N_BYTES_U8: + *(u8 *)xspi->rxbuf = rxw; + break; + case CDNS_SPI_N_BYTES_U16: + *(u16 *)xspi->rxbuf = rxw; + break; + case CDNS_SPI_N_BYTES_U32: + *(u32 *)xspi->rxbuf = rxw; + break; + default: + pr_err("%s invalid n_bytes %d\n", __func__, + xspi->n_bytes); + return; + } + xspi->rxbuf = (u8 *)xspi->rxbuf + xspi->n_bytes; + } +} + +static inline void cdns_spi_writer(struct cdns_spi *xspi) +{ + u32 txw = 0; + + if (xspi->txbuf && !IS_ALIGNED((uintptr_t)xspi->txbuf, xspi->n_bytes)) { + pr_err("%s: txbuf address is not aligned for %d bytes\n", + __func__, xspi->n_bytes); + return; + } + + if (xspi->txbuf) { + switch (xspi->n_bytes) { + case CDNS_SPI_N_BYTES_U8: + txw = *(u8 *)xspi->txbuf; + break; + case CDNS_SPI_N_BYTES_U16: + txw = *(u16 *)xspi->txbuf; + break; + case CDNS_SPI_N_BYTES_U32: + txw = *(u32 *)xspi->txbuf; + break; + default: + pr_err("%s invalid n_bytes %d\n", __func__, + xspi->n_bytes); + return; + } + cdns_spi_write(xspi, CDNS_SPI_TXD, txw); + xspi->txbuf = (u8 *)xspi->txbuf + xspi->n_bytes; + } +} + /** * cdns_spi_process_fifo - Fills the TX FIFO, and drain the RX FIFO + * @ctlr: Pointer to the spi_controller structure * @xspi: Pointer to the cdns_spi structure * @ntx: Number of bytes to pack into the TX FIFO * @nrx: Number of bytes to drain from the RX FIFO */ -static void cdns_spi_process_fifo(struct cdns_spi *xspi, int ntx, int nrx) +static void cdns_spi_process_fifo(struct spi_controller *ctlr, + struct cdns_spi *xspi, int ntx, int nrx) { ntx = clamp(ntx, 0, xspi->tx_bytes); nrx = clamp(nrx, 0, xspi->rx_bytes); @@ -321,23 +404,24 @@ static void cdns_spi_process_fifo(struct cdns_spi *xspi, int ntx, int nrx) while (ntx || nrx) { if (nrx) { - u8 data = cdns_spi_read(xspi, CDNS_SPI_RXD); - - if (xspi->rxbuf) - *xspi->rxbuf++ = data; - + cdns_spi_reader(xspi); nrx--; } if (ntx) { - if (xspi->txbuf) - cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++); - else - cdns_spi_write(xspi, CDNS_SPI_TXD, 0); + /* When xspi in busy condition, bytes may send failed, + * then spi control didn't work thoroughly, add one byte + * delay. Only in host mode; in target mode this delay + * causes data corruption as the target fails to prepare + * data in time. + */ + if (!spi_controller_is_target(ctlr) && + (cdns_spi_read(xspi, CDNS_SPI_ISR) & CDNS_SPI_IXR_TXFULL)) + udelay(10); + cdns_spi_writer(xspi); ntx--; } - } } @@ -388,14 +472,14 @@ static irqreturn_t cdns_spi_irq(int irq, void *dev_id) cdns_spi_write(xspi, CDNS_SPI_THLD, 1); if (xspi->tx_bytes) { - cdns_spi_process_fifo(xspi, trans_cnt, trans_cnt); + cdns_spi_process_fifo(ctlr, xspi, trans_cnt, trans_cnt); } else { /* Fixed delay due to controller limitation with * RX_NEMPTY incorrect status * Xilinx AR:65885 contains more details */ udelay(10); - cdns_spi_process_fifo(xspi, 0, trans_cnt); + cdns_spi_process_fifo(ctlr, xspi, 0, trans_cnt); cdns_spi_write(xspi, CDNS_SPI_IDR, CDNS_SPI_IXR_DEFAULT); spi_finalize_current_transfer(ctlr); @@ -448,13 +532,11 @@ static int cdns_transfer_one(struct spi_controller *ctlr, cdns_spi_write(xspi, CDNS_SPI_THLD, xspi->tx_fifo_depth >> 1); } - /* When xspi in busy condition, bytes may send failed, - * then spi control didn't work thoroughly, add one byte delay - */ - if (cdns_spi_read(xspi, CDNS_SPI_ISR) & CDNS_SPI_IXR_TXFULL) - udelay(10); + xspi->n_bytes = cdns_spi_n_bytes(transfer); + xspi->tx_bytes = DIV_ROUND_UP(xspi->tx_bytes, xspi->n_bytes); + xspi->rx_bytes = DIV_ROUND_UP(xspi->rx_bytes, xspi->n_bytes); - cdns_spi_process_fifo(xspi, xspi->tx_fifo_depth, 0); + cdns_spi_process_fifo(ctlr, xspi, xspi->tx_fifo_depth, 0); cdns_spi_write(xspi, CDNS_SPI_IER, CDNS_SPI_IXR_DEFAULT); return transfer->len; @@ -653,6 +735,10 @@ static int cdns_spi_probe(struct platform_device *pdev) ctlr->unprepare_transfer_hardware = cdns_unprepare_transfer_hardware; ctlr->mode_bits = SPI_CPOL | SPI_CPHA; ctlr->bits_per_word_mask = SPI_BPW_MASK(8); + ctlr->flags = SPI_CONTROLLER_MUST_TX; + + if (of_device_is_compatible(pdev->dev.of_node, "cix,sky1-spi-r1p6")) + ctlr->bits_per_word_mask |= SPI_BPW_MASK(16) | SPI_BPW_MASK(32); if (!spi_controller_is_target(ctlr)) { ctlr->mode_bits |= SPI_CS_HIGH; @@ -812,6 +898,7 @@ static const struct dev_pm_ops cdns_spi_dev_pm_ops = { static const struct of_device_id cdns_spi_of_match[] = { { .compatible = "xlnx,zynq-spi-r1p6" }, + { .compatible = "cix,sky1-spi-r1p6" }, { .compatible = "cdns,spi-r1p6" }, { /* end of table */ } }; diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c index 95ccb1f7dfaf..b504a5c86692 100644 --- a/drivers/spi/spi-nxp-fspi.c +++ b/drivers/spi/spi-nxp-fspi.c @@ -340,6 +340,18 @@ struct nxp_fspi_devtype_data { unsigned int quirks; unsigned int lut_num; bool little_endian; + /* + * The max clock rate (Hz) that FlexSPI can output to the device + * in SDR mode (RXCLKSRC=0). Defaults to 66MHz if zero. + * Some SoCs (e.g. LX2160A) support up to 100MHz in SDR mode. + */ + unsigned long max_sdr_rate; + /* + * The max clock rate (Hz) that FlexSPI can output to the device + * in DTR mode (RXCLKSRC=3). Defaults to 166MHz if zero. + * Some SoCs (e.g. i.MX95, i.MX8QM, i.MX8DXL) support up to 200MHz. + */ + unsigned long max_dtr_rate; }; static struct nxp_fspi_devtype_data lx2160a_data = { @@ -349,6 +361,10 @@ static struct nxp_fspi_devtype_data lx2160a_data = { .quirks = FSPI_QUIRK_DISABLE_DTR, .lut_num = 32, .little_endian = true, /* little-endian */ + /* + * LX2160ACEC: SDR RXCLKSRC=0 max 100MHz, DTR disabled via quirk. + */ + .max_sdr_rate = 100000000, }; static struct nxp_fspi_devtype_data imx8mm_data = { @@ -358,6 +374,21 @@ static struct nxp_fspi_devtype_data imx8mm_data = { .quirks = 0, .lut_num = 32, .little_endian = true, /* little-endian */ + /* IMX8MMCEC §3.9.10: SDR RXCLKSRC=0 max 66MHz, DDR RXCLKSRC=3 max 166MHz */ + .max_sdr_rate = 66000000, + .max_dtr_rate = 166000000, +}; + +static struct nxp_fspi_devtype_data imx8mp_data = { + .rxfifo = SZ_512, /* (64 * 64 bits) */ + .txfifo = SZ_1K, /* (128 * 64 bits) */ + .ahb_buf_size = SZ_2K, /* (256 * 64 bits) */ + .quirks = 0, + .lut_num = 32, + .little_endian = true, /* little-endian */ + /* IMX8MPCEC: SDR RXCLKSRC=0 max 66MHz, DDR RXCLKSRC=3 max 166MHz */ + .max_sdr_rate = 66000000, + .max_dtr_rate = 166000000, }; static struct nxp_fspi_devtype_data imx8qxp_data = { @@ -367,6 +398,12 @@ static struct nxp_fspi_devtype_data imx8qxp_data = { .quirks = 0, .lut_num = 32, .little_endian = true, /* little-endian */ + /* + * IMX8QXPCEC: SDR RXCLKSRC=0 max 60MHz, DDR RXCLKSRC=3 max 200MHz. + * i.MX8QM and i.MX8DXL share the same FlexSPI IP and limits. + */ + .max_sdr_rate = 60000000, + .max_dtr_rate = 200000000, }; static struct nxp_fspi_devtype_data imx8dxl_data = { @@ -376,6 +413,12 @@ static struct nxp_fspi_devtype_data imx8dxl_data = { .quirks = FSPI_QUIRK_USE_IP_ONLY, .lut_num = 32, .little_endian = true, /* little-endian */ + /* + * IMX8DXLCEC (i.MX 8XLite): SDR RXCLKSRC=0 max 60MHz, + * DDR RXCLKSRC=3 max 200MHz. + */ + .max_sdr_rate = 60000000, + .max_dtr_rate = 200000000, }; static struct nxp_fspi_devtype_data imx8ulp_data = { @@ -385,6 +428,29 @@ static struct nxp_fspi_devtype_data imx8ulp_data = { .quirks = 0, .lut_num = 16, .little_endian = true, /* little-endian */ + /* + * IMX8ULPCEC §7.3.1, Normal Drive (ND, 1.0V) mode: + * SDR RXCLKSRC=0 max 60MHz, DDR RXCLKSRC=3 max 166MHz. + * Note: Overdrive (OD, 1.05V) allows up to 180MHz DTR + * but is not the default use case. + */ + .max_sdr_rate = 60000000, + .max_dtr_rate = 166000000, +}; + +static struct nxp_fspi_devtype_data imx95_data = { + .rxfifo = SZ_512, /* (64 * 64 bits) */ + .txfifo = SZ_1K, /* (128 * 64 bits) */ + .ahb_buf_size = SZ_2K, /* (256 * 64 bits) */ + .quirks = 0, + .lut_num = 32, + .little_endian = true, /* little-endian */ + /* + * IMX95CEC Rev.8 §4.11.7: SDR RXCLKSRC=0 max 66MHz, + * DDR RXCLKSRC=3 max 200MHz (Nominal/Overdrive mode). + */ + .max_sdr_rate = 66000000, + .max_dtr_rate = 200000000, }; struct nxp_fspi { @@ -691,10 +757,20 @@ static void nxp_fspi_select_rx_sample_clk_source(struct nxp_fspi *f, reg = fspi_readl(f, f->iobase + FSPI_MCR0); if (op_is_dtr) { reg |= FSPI_MCR0_RXCLKSRC(3); - f->max_rate = 166000000; + /* + * Use the SoC-specific DTR max rate if provided, otherwise + * fall back to 166MHz (limit from IMX8MN datasheet §3.9.9). + */ + f->max_rate = f->devtype_data->max_dtr_rate ? + f->devtype_data->max_dtr_rate : 166000000; } else { /*select mode 0 */ reg &= ~FSPI_MCR0_RXCLKSRC(3); - f->max_rate = 66000000; + /* + * Use the SoC-specific SDR max rate if provided, otherwise + * fall back to 66MHz (limit from IMX8MN datasheet §3.9.9). + */ + f->max_rate = f->devtype_data->max_sdr_rate ? + f->devtype_data->max_sdr_rate : 66000000; } fspi_writel(f, reg, f->iobase + FSPI_MCR0); } @@ -1446,10 +1522,11 @@ static const struct dev_pm_ops nxp_fspi_pm_ops = { static const struct of_device_id nxp_fspi_dt_ids[] = { { .compatible = "nxp,lx2160a-fspi", .data = (void *)&lx2160a_data, }, { .compatible = "nxp,imx8mm-fspi", .data = (void *)&imx8mm_data, }, - { .compatible = "nxp,imx8mp-fspi", .data = (void *)&imx8mm_data, }, + { .compatible = "nxp,imx8mp-fspi", .data = (void *)&imx8mp_data, }, { .compatible = "nxp,imx8qxp-fspi", .data = (void *)&imx8qxp_data, }, { .compatible = "nxp,imx8dxl-fspi", .data = (void *)&imx8dxl_data, }, { .compatible = "nxp,imx8ulp-fspi", .data = (void *)&imx8ulp_data, }, + { .compatible = "nxp,imx95-fspi", .data = (void *)&imx95_data, }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, nxp_fspi_dt_ids); diff --git a/drivers/spi/spi-qcom-qspi.c b/drivers/spi/spi-qcom-qspi.c index 3aeddada58e1..3c08dad8bd3f 100644 --- a/drivers/spi/spi-qcom-qspi.c +++ b/drivers/spi/spi-qcom-qspi.c @@ -759,7 +759,8 @@ static int qcom_qspi_probe(struct platform_device *pdev) return dev_err_probe(dev, ret, "could not set DMA mask\n"); host->max_speed_hz = 300000000; - host->max_dma_len = 65536; /* as per HPG */ + /* as per HPG, it is 64KB, limit to 60KB to avoid boundary condition failures */ + host->max_dma_len = 0xf000; host->dma_alignment = QSPI_ALIGN_REQ; host->num_chipselect = QSPI_NUM_CS; host->bus_num = -1; diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c index 58ceea1ea8fb..42f8fb272fa6 100644 --- a/drivers/spi/spi-qpic-snand.c +++ b/drivers/spi/spi-qpic-snand.c @@ -1362,6 +1362,22 @@ static int qcom_spi_send_cmdaddr(struct qcom_nand_controller *snandc, snandc->regs->addr0 = cpu_to_le32(op->addr.val); snandc->regs->addr1 = cpu_to_le32(0); + /* + * The feature value has to reach NAND_FLASH_FEATURES before the + * command is executed, otherwise the controller programs the chip + * with whatever the register happened to hold from a previous + * operation. + */ + if (opcode == SPINAND_SET_FEATURE) { + u32 ftr = 0; + + memcpy(&ftr, op->data.buf.out, + min_t(size_t, op->data.nbytes, sizeof(ftr))); + snandc->regs->flash_feature = cpu_to_le32(ftr); + qcom_write_reg_dma(snandc, &snandc->regs->flash_feature, + NAND_FLASH_FEATURES, 1, NAND_BAM_NEXT_SGL); + } + qcom_write_reg_dma(snandc, &snandc->regs->cmd, NAND_FLASH_CMD, 3, NAND_BAM_NEXT_SGL); qcom_write_reg_dma(snandc, &snandc->regs->exec, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); @@ -1399,10 +1415,8 @@ static int qcom_spi_io_op(struct qcom_nand_controller *snandc, const struct spi_ copy_ftr = true; break; case SPINAND_SET_FEATURE: - snandc->regs->flash_feature = cpu_to_le32(*(u32 *)op->data.buf.out); - qcom_write_reg_dma(snandc, &snandc->regs->flash_feature, - NAND_FLASH_FEATURES, 1, NAND_BAM_NEXT_SGL); - break; + /* fully handled by qcom_spi_send_cmdaddr() */ + return 0; case SPINAND_PROGRAM_EXECUTE: case SPINAND_WRITE_EN: case SPINAND_RESET: diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 66c292b7d74b..4ec322f371bc 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -902,7 +902,7 @@ static sense_reason_t iblock_execute_pr_out(struct se_cmd *cmd, u8 sa, u64 key, break; case PRO_PREEMPT: case PRO_PREEMPT_AND_ABORT: - if (!ops->pr_clear) { + if (!ops->pr_preempt) { pr_err("block_device does not support pr_preempt.\n"); return TCM_UNSUPPORTED_SCSI_OPCODE; } @@ -912,8 +912,8 @@ static sense_reason_t iblock_execute_pr_out(struct se_cmd *cmd, u8 sa, u64 key, sa == PRO_PREEMPT_AND_ABORT); break; case PRO_RELEASE: - if (!ops->pr_clear) { - pr_err("block_device does not support pr_pclear.\n"); + if (!ops->pr_release) { + pr_err("block_device does not support pr_release.\n"); return TCM_UNSUPPORTED_SCSI_OPCODE; } diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 88544c911949..5ad2dcf730cd 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1691,6 +1691,7 @@ int target_init_cmd(struct se_cmd *se_cmd, struct se_session *se_sess, u32 data_length, int task_attr, int data_dir, int flags) { struct se_portal_group *se_tpg; + int ret; se_tpg = se_sess->se_tpg; BUG_ON(!se_tpg); @@ -1720,7 +1721,11 @@ int target_init_cmd(struct se_cmd *se_cmd, struct se_session *se_sess, * necessary for fabrics using TARGET_SCF_ACK_KREF that expect a second * kref_put() to happen during fabric packet acknowledgement. */ - return target_get_sess_cmd(se_cmd, flags & TARGET_SCF_ACK_KREF); + ret = target_get_sess_cmd(se_cmd, flags & TARGET_SCF_ACK_KREF); + if (ret) + se_cmd->cmd_cnt = NULL; + + return ret; } EXPORT_SYMBOL_GPL(target_init_cmd); @@ -1996,8 +2001,10 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess, * allocation failure. */ ret = core_tmr_alloc_req(se_cmd, fabric_tmr_ptr, tm_type, gfp); - if (ret < 0) + if (ret < 0) { + se_cmd->cmd_cnt = NULL; return -ENOMEM; + } if (tm_type == TMR_ABORT_TASK) se_cmd->se_tmr_req->ref_task_tag = tag; @@ -2005,6 +2012,7 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess, /* See target_submit_cmd for commentary */ ret = target_get_sess_cmd(se_cmd, flags & TARGET_SCF_ACK_KREF); if (ret) { + se_cmd->cmd_cnt = NULL; core_tmr_release_req(se_cmd->se_tmr_req); return ret; } diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index 458476907eab..6b16fc7254b8 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -785,9 +785,13 @@ static void tb_xdp_handle_request(struct work_struct *work) * the xdomain related to this connection as well in * case there is a change in services it offers. */ - if (xd && device_is_registered(&xd->dev)) - queue_delayed_work(tb->wq, &xd->state_work, - msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT)); + if (xd) { + mutex_lock(&xd->lock); + if (!xd->removing && device_is_registered(&xd->dev)) + queue_delayed_work(tb->wq, &xd->state_work, + msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT)); + mutex_unlock(&xd->lock); + } break; case UUID_REQUEST_OLD: @@ -800,8 +804,12 @@ static void tb_xdp_handle_request(struct work_struct *work) * received UUID request from the remote host. */ if (!ret && xd && xd->state == XDOMAIN_STATE_ERROR) { - dev_dbg(&xd->dev, "restarting handshake\n"); - start_handshake(xd); + mutex_lock(&xd->lock); + if (!xd->removing) { + dev_dbg(&xd->dev, "restarting handshake\n"); + start_handshake(xd); + } + mutex_unlock(&xd->lock); } break; @@ -829,9 +837,13 @@ static void tb_xdp_handle_request(struct work_struct *work) ret = tb_xdp_link_state_change_response(ctl, route, sequence, 0); - xd->target_link_width = lsc->tlw; - queue_delayed_work(tb->wq, &xd->state_work, - msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT)); + mutex_lock(&xd->lock); + if (!xd->removing) { + xd->target_link_width = lsc->tlw; + queue_delayed_work(tb->wq, &xd->state_work, + msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT)); + } + mutex_unlock(&xd->lock); } else { tb_xdp_error_response(ctl, route, sequence, ERROR_NOT_READY); @@ -2074,6 +2086,10 @@ void tb_xdomain_remove(struct tb_xdomain *xd) { tb_xdomain_debugfs_remove(xd); + mutex_lock(&xd->lock); + xd->removing = true; + mutex_unlock(&xd->lock); + stop_handshake(xd); device_for_each_child_reverse(&xd->dev, xd, unregister_service); @@ -2484,8 +2500,12 @@ static int update_xdomain(struct device *dev, void *data) xd = tb_to_xdomain(dev); if (xd) { - queue_delayed_work(xd->tb->wq, &xd->properties_changed_work, - msecs_to_jiffies(50)); + mutex_lock(&xd->lock); + if (!xd->removing) + queue_delayed_work(xd->tb->wq, + &xd->properties_changed_work, + msecs_to_jiffies(50)); + mutex_unlock(&xd->lock); } return 0; diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 8de3d0886a12..504600f1e08c 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -7128,7 +7128,7 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status) } /** - * ufshcd_threaded_intr - Threaded interrupt service routine + * ufshcd_intr - Main interrupt service routine * @irq: irq number * @__hba: pointer to adapter instance * @@ -7136,7 +7136,7 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status) * IRQ_HANDLED - If interrupt is valid * IRQ_NONE - If invalid interrupt */ -static irqreturn_t ufshcd_threaded_intr(int irq, void *__hba) +static irqreturn_t ufshcd_intr(int irq, void *__hba) { u32 last_intr_status, intr_status, enabled_intr_status = 0; irqreturn_t retval = IRQ_NONE; @@ -7175,34 +7175,6 @@ static irqreturn_t ufshcd_threaded_intr(int irq, void *__hba) return retval; } -/** - * ufshcd_intr - Main interrupt service routine - * @irq: irq number - * @__hba: pointer to adapter instance - * - * Return: - * IRQ_HANDLED - If interrupt is valid - * IRQ_WAKE_THREAD - If handling is moved to threaded handled - * IRQ_NONE - If invalid interrupt - */ -static irqreturn_t ufshcd_intr(int irq, void *__hba) -{ - struct ufs_hba *hba = __hba; - u32 intr_status, enabled_intr_status; - - /* Move interrupt handling to thread when MCQ & ESI are not enabled */ - if (!hba->mcq_enabled || !hba->mcq_esi_enabled) - return IRQ_WAKE_THREAD; - - intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS); - enabled_intr_status = intr_status & ufshcd_readl(hba, REG_INTERRUPT_ENABLE); - - ufshcd_writel(hba, intr_status, REG_INTERRUPT_STATUS); - - /* Directly handle interrupts since MCQ ESI handlers does the hard job */ - return ufshcd_sl_intr(hba, enabled_intr_status); -} - static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag) { int err = 0; @@ -9873,6 +9845,7 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) req_link_state == UIC_LINK_ACTIVE_STATE) { ufshcd_disable_auto_bkops(hba); flush_work(&hba->eeh_work); + cancel_delayed_work_sync(&hba->ufs_rtc_update_work); goto vops_suspend; } @@ -10082,10 +10055,11 @@ static int __ufshcd_wl_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op) if (ret) goto set_old_link_state; ufshcd_set_timestamp_attr(hba); - schedule_delayed_work(&hba->ufs_rtc_update_work, - msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS)); } + schedule_delayed_work(&hba->ufs_rtc_update_work, + msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS)); + if (ufshcd_keep_autobkops_enabled_except_suspend(hba)) ufshcd_enable_auto_bkops(hba); else @@ -10829,8 +10803,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) ufshcd_readl(hba, REG_INTERRUPT_ENABLE); /* IRQ registration */ - err = devm_request_threaded_irq(dev, irq, ufshcd_intr, ufshcd_threaded_intr, - IRQF_ONESHOT | IRQF_SHARED, UFSHCD, hba); + err = devm_request_irq(dev, irq, ufshcd_intr, IRQF_SHARED, UFSHCD, hba); if (err) { dev_err(hba->dev, "request irq failed\n"); goto out_disable; diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 01a15ab5a734..0d1062191951 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1741,6 +1741,7 @@ static int ucsi_register_port(struct ucsi *ucsi, struct ucsi_connector *con) INIT_WORK(&con->work, ucsi_handle_connector_change); init_completion(&con->complete); mutex_init(&con->lock); + lockdep_set_class(&con->lock, &con->lock_key); INIT_LIST_HEAD(&con->partner_tasks); con->ucsi = ucsi; @@ -1890,6 +1891,42 @@ static int ucsi_register_port(struct ucsi *ucsi, struct ucsi_connector *con) return ret; } +static void ucsi_unregister_port(struct ucsi_connector *con) +{ + struct ucsi_work *uwork; + + if (con->wq) { + mutex_lock(&con->lock); + ucsi_unregister_partner(con); + /* + * queue delayed items immediately so they can execute + * and free themselves before the wq is destroyed + */ + list_for_each_entry(uwork, &con->partner_tasks, node) { + if (cancel_delayed_work(&uwork->work)) + queue_delayed_work(con->wq, &uwork->work, 0); + } + mutex_unlock(&con->lock); + + destroy_workqueue(con->wq); + con->wq = NULL; + } else { + ucsi_unregister_partner(con); + } + + ucsi_unregister_altmodes(con, UCSI_RECIPIENT_CON); + ucsi_unregister_port_psy(con); + + usb_power_delivery_unregister_capabilities(con->port_sink_caps); + con->port_sink_caps = NULL; + usb_power_delivery_unregister_capabilities(con->port_source_caps); + con->port_source_caps = NULL; + usb_power_delivery_unregister(con->pd); + con->pd = NULL; + typec_unregister_port(con->port); + con->port = NULL; +} + static u64 ucsi_get_supported_notifications(struct ucsi *ucsi) { u16 features = ucsi->cap.features; @@ -1981,6 +2018,9 @@ static int ucsi_init(struct ucsi *ucsi) goto err_reset; } + for (i = 0; i < ucsi->cap.num_connectors; i++) + lockdep_register_key(&connector[i].lock_key); + /* Register all connectors */ for (i = 0; i < ucsi->cap.num_connectors; i++) { connector[i].num = i + 1; @@ -2010,22 +2050,11 @@ static int ucsi_init(struct ucsi *ucsi) return 0; err_unregister: - for (con = connector; con->port; con++) { - if (con->wq) - destroy_workqueue(con->wq); - ucsi_unregister_partner(con); - ucsi_unregister_altmodes(con, UCSI_RECIPIENT_CON); - ucsi_unregister_port_psy(con); - - usb_power_delivery_unregister_capabilities(con->port_sink_caps); - con->port_sink_caps = NULL; - usb_power_delivery_unregister_capabilities(con->port_source_caps); - con->port_source_caps = NULL; - usb_power_delivery_unregister(con->pd); - con->pd = NULL; - typec_unregister_port(con->port); - con->port = NULL; - } + for (con = connector; con->port; con++) + ucsi_unregister_port(con); + for (i = 0; i < ucsi->cap.num_connectors; i++) + lockdep_unregister_key(&connector[i].lock_key); + kfree(connector); err_reset: memset(&ucsi->cap, 0, sizeof(ucsi->cap)); @@ -2253,33 +2282,8 @@ void ucsi_unregister(struct ucsi *ucsi) for (i = 0; i < ucsi->cap.num_connectors; i++) { cancel_work_sync(&ucsi->connector[i].work); - - if (ucsi->connector[i].wq) { - struct ucsi_work *uwork; - - mutex_lock(&ucsi->connector[i].lock); - /* - * queue delayed items immediately so they can execute - * and free themselves before the wq is destroyed - */ - list_for_each_entry(uwork, &ucsi->connector[i].partner_tasks, node) - mod_delayed_work(ucsi->connector[i].wq, &uwork->work, 0); - mutex_unlock(&ucsi->connector[i].lock); - destroy_workqueue(ucsi->connector[i].wq); - } - - ucsi_unregister_partner(&ucsi->connector[i]); - ucsi_unregister_altmodes(&ucsi->connector[i], - UCSI_RECIPIENT_CON); - ucsi_unregister_port_psy(&ucsi->connector[i]); - - usb_power_delivery_unregister_capabilities(ucsi->connector[i].port_sink_caps); - ucsi->connector[i].port_sink_caps = NULL; - usb_power_delivery_unregister_capabilities(ucsi->connector[i].port_source_caps); - ucsi->connector[i].port_source_caps = NULL; - usb_power_delivery_unregister(ucsi->connector[i].pd); - ucsi->connector[i].pd = NULL; - typec_unregister_port(ucsi->connector[i].port); + ucsi_unregister_port(&ucsi->connector[i]); + lockdep_unregister_key(&ucsi->connector[i].lock_key); } kfree(ucsi->connector); diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index a9144c299739..520a1a4f9114 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -502,6 +502,7 @@ struct ucsi_connector { struct ucsi *ucsi; struct mutex lock; /* port lock */ + struct lock_class_key lock_key; struct work_struct work; struct completion complete; struct workqueue_struct *wq; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index bc9556991d7c..2dfcd4a20d10 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -477,6 +477,9 @@ void afs_fs_fetch_data(struct afs_operation *op) if (!call) return afs_op_nomem(op); + if (op->flags & AFS_OPERATION_ASYNC) + call->async = true; + /* marshall the parameters */ bp = call->request; bp[0] = htonl(FSFETCHDATA); @@ -484,7 +487,7 @@ void afs_fs_fetch_data(struct afs_operation *op) bp[2] = htonl(vp->fid.vnode); bp[3] = htonl(vp->fid.unique); bp[4] = htonl(lower_32_bits(subreq->start + subreq->transferred)); - bp[5] = htonl(lower_32_bits(subreq->len + subreq->transferred)); + bp[5] = htonl(lower_32_bits(subreq->len - subreq->transferred)); call->fid = vp->fid; trace_afs_make_fs_call(call, &vp->fid); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index bea8aae5364e..b0ebcb820867 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1420,7 +1420,7 @@ static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *c { struct afs_addr_list *alist = op->estate->addresses; - op->call = call; + op->call = afs_get_call(call, afs_call_trace_get); op->type = call->type; call->op = op; call->key = op->key; @@ -1428,6 +1428,7 @@ static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *c call->peer = rxrpc_kernel_get_peer(alist->addrs[op->addr_index].peer); call->service_id = op->server->service_id; afs_make_call(call, gfp); + afs_put_call(call); } static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size) diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index d44529d5ecf5..5edc41bb100e 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -161,8 +161,10 @@ static Node *get_binfmt_handler(struct binfmt_misc *misc, static void put_binfmt_handler(Node *e) { if (refcount_dec_and_test(&e->users)) { - if (e->flags & MISC_FMT_OPEN_FILE) + if (e->flags & MISC_FMT_OPEN_FILE) { + exe_file_allow_write_access(e->interp_file); filp_close(e->interp_file, NULL); + } kfree(e); } } @@ -246,8 +248,14 @@ static int load_misc_binary(struct linux_binprm *bprm) if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = file_clone_open(fmt->interp_file); - if (!IS_ERR(interp_file)) - deny_write_access(interp_file); + if (!IS_ERR(interp_file)) { + int err = exe_file_deny_write_access(interp_file); + + if (err) { + fput(interp_file); + interp_file = ERR_PTR(err); + } + } } else { interp_file = open_exec(fmt->interpreter); } @@ -375,6 +383,10 @@ static Node *create_entry(const char __user *buffer, size_t count) pr_debug("register: delim: %#x {%c}\n", del, del); + /* A flag-char delimiter runs the flag scan off the buffer. */ + if (del == 'P' || del == 'O' || del == 'C' || del == 'F') + goto einval; + /* Pad the buffer with the delim to simplify parsing below. */ memset(buf + count, del, 8); @@ -944,6 +956,10 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc) if (WARN_ON(user_ns != current_user_ns())) return -EINVAL; + /* Never exec off this instance and never let anything stack on it. */ + sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV; + sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; + /* * Lazily allocate a new binfmt_misc instance for this namespace, i.e. * do it here during the first mount of binfmt_misc. We don't need to diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 0135dceb7baa..4d4852f2ba7e 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1583,8 +1583,10 @@ static void verify_bio_data_sectors(struct btrfs_raid_bio *rbio, int ret; /* No csum for this sector, skip to the next sector. */ - if (!test_bit(total_sector_nr, rbio->csum_bitmap)) + if (!test_bit(total_sector_nr, rbio->csum_bitmap)) { + total_sector_nr++; continue; + } ret = btrfs_check_block_csum(fs_info, paddr, csum_buf, expected_csum); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 736575f92517..157d55134470 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1518,12 +1518,14 @@ static int btrfs_reconfigure(struct fs_context *fc) sync_filesystem(sb); set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); - if (!btrfs_check_options(fs_info, &ctx->mount_opt, fc->sb_flags)) - return -EINVAL; + if (!btrfs_check_options(fs_info, &ctx->mount_opt, fc->sb_flags)) { + ret = -EINVAL; + goto restore; + } ret = btrfs_check_features(fs_info, !(fc->sb_flags & SB_RDONLY)); if (ret < 0) - return ret; + goto restore; btrfs_ctx_to_info(fs_info, ctx); btrfs_remount_begin(fs_info, old_ctx.mount_opt, fc->sb_flags); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b8fc97e33009..0dfbb28b7445 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2167,7 +2167,11 @@ static bool check_bg_is_active(struct btrfs_eb_write_context *ctx, if (fs_info->treelog_bg == block_group->start) { if (!btrfs_zone_activate(block_group)) { - int ret_fin = btrfs_zone_finish_one_bg(fs_info); + int ret_fin; + + btrfs_zoned_meta_io_unlock(fs_info); + ret_fin = btrfs_zone_finish_one_bg(fs_info); + btrfs_zoned_meta_io_lock(fs_info); if (ret_fin != 1 || !btrfs_zone_activate(block_group)) return false; @@ -3167,6 +3171,17 @@ int btrfs_reset_unused_block_groups(struct btrfs_space_info *space_info, u64 num reclaimed = bg->alloc_offset; bg->zone_unusable = bg->length - bg->zone_capacity; bg->alloc_offset = 0; + /* + * The zone was just reset to empty, so alloc_offset went back to + * the start of the zone. For metadata/system block groups the + * write pointer must follow it back to the start of the zone; + * otherwise it stays stale at the previous (finished) zone end, + * and metadata written into the reused zone would sit behind the + * write pointer, could never be written out in sequential order, + * and would be stranded (pinning its folio) until unmount. + */ + if (bg->flags & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)) + bg->meta_write_pointer = bg->start; /* * This holds because we currently reset fully used then freed * block group. diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index d81f3318417d..0d199f6698ff 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -120,6 +120,20 @@ config EROFS_FS_ZIP_LZMA If unsure, say N. +config EROFS_FS_ZIP_LZMA_DEFAULT_MAX_STREAMS + int "EROFS LZMA default maximum decompression streams" + depends on EROFS_FS_ZIP_LZMA + range 1 NR_CPUS + default 16 + help + By default EROFS allocates one LZMA decompression stream per CPU. + Each stream can hold a dictionary of up to 8 MiB taken from the + mounted image, so on systems with many CPUs this can reserve a lot + of memory. This caps the default; the lzma_streams module parameter + still overrides it. + + If unsure, keep the default of 16. + config EROFS_FS_ZIP_DEFLATE bool "EROFS DEFLATE compressed data support" depends on EROFS_FS_ZIP diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 832cffb83a66..90bdc8638199 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -51,7 +51,8 @@ static int __init z_erofs_lzma_init(void) /* by default, use # of possible CPUs instead */ if (!z_erofs_lzma_nstrms) - z_erofs_lzma_nstrms = num_possible_cpus(); + z_erofs_lzma_nstrms = min_t(unsigned int, num_possible_cpus(), + CONFIG_EROFS_FS_ZIP_LZMA_DEFAULT_MAX_STREAMS); for (i = 0; i < z_erofs_lzma_nstrms; ++i) { struct z_erofs_lzma *strm = kzalloc(sizeof(*strm), GFP_KERNEL); diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c index 6c75fbf4d5af..2a86b05c88ef 100644 --- a/fs/iomap/ioend.c +++ b/fs/iomap/ioend.c @@ -11,6 +11,7 @@ struct bio_set iomap_ioend_bioset; EXPORT_SYMBOL_GPL(iomap_ioend_bioset); +static struct bio_set iomap_ioend_split_bioset; struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio, loff_t file_offset, u16 ioend_flags) @@ -409,7 +410,8 @@ struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend, sector_offset = ALIGN_DOWN(sector_offset << SECTOR_SHIFT, i_blocksize(ioend->io_inode)) >> SECTOR_SHIFT; - split = bio_split(bio, sector_offset, GFP_NOFS, &iomap_ioend_bioset); + split = bio_split(bio, sector_offset, GFP_NOFS, + &iomap_ioend_split_bioset); if (IS_ERR(split)) return ERR_CAST(split); split->bi_private = bio->bi_private; @@ -432,8 +434,23 @@ EXPORT_SYMBOL_GPL(iomap_split_ioend); static int __init iomap_ioend_init(void) { - return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE), + const unsigned int nr_mempool_entries = 4 * (PAGE_SIZE / SECTOR_SIZE); + int error; + + error = bioset_init(&iomap_ioend_bioset, nr_mempool_entries, offsetof(struct iomap_ioend, io_bio), BIOSET_NEED_BVECS); + if (error) + return error; + error = bioset_init(&iomap_ioend_split_bioset, nr_mempool_entries, + offsetof(struct iomap_ioend, io_bio), + BIOSET_NEED_BVECS); + if (error) + goto out_exit_ioend_bioset; + return 0; + +out_exit_ioend_bioset: + bioset_exit(&iomap_ioend_bioset); + return error; } fs_initcall(iomap_ioend_init); diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index fab3181c7f86..221287f8925a 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -102,8 +102,10 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq, added = rolling_buffer_load_from_ra(&rreq->buffer, ractl, &put_batch); - if (added < 0) + if (added < 0) { + folio_batch_release(&put_batch); return added; + } rreq->submitted += added; } folio_batch_release(&put_batch); diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index a1489aa29f78..7eacc58abadb 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -54,6 +54,7 @@ static void netfs_pgpriv2_copy_folio(struct netfs_io_request *creq, struct folio /* Attach the folio to the rolling buffer. */ if (rolling_buffer_append(&creq->buffer, folio, 0) < 0) { + folio_end_private_2(folio); clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &creq->flags); return; } diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 76614339554e..5f216907b1e5 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -730,6 +730,7 @@ static int netfs_write_folio_single(struct netfs_io_request *wreq, size_t iter_off = 0; size_t fsize = folio_size(folio), flen; loff_t fpos = folio_pos(folio); + ssize_t ret; bool to_eof = false; bool no_debug = false; @@ -758,7 +759,11 @@ static int netfs_write_folio_single(struct netfs_io_request *wreq, /* Attach the folio to the rolling buffer. */ folio_get(folio); - rolling_buffer_append(&wreq->buffer, folio, NETFS_ROLLBUF_PUT_MARK); + ret = rolling_buffer_append(&wreq->buffer, folio, NETFS_ROLLBUF_PUT_MARK); + if (ret < 0) { + folio_put(folio); + return ret; + } /* Move the submission point forward to allow for write-streaming data * not starting at the front of the page. We don't do write-streaming diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 858b11009c26..48455e2a66a1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -2326,6 +2326,19 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, { unsigned long categories = 0; + if (pte_none(pte)) { + /* + * An unpopulated pte carries no uffd-wp marker, i.e. it is not + * write-protected, the same condition under which the present + * and swap cases below report PAGE_IS_WRITTEN. Report it here + * too so this generic path agrees with the PAGE_IS_WRITTEN fast + * path in pagemap_scan_pmd_entry(), which reports pte_none as + * written and, under PM_SCAN_WP_MATCHING, arms a marker. The + * fast path applies no VMA test, so neither does this. + */ + return PAGE_IS_WRITTEN; + } + if (pte_present(pte)) { struct page *page; @@ -2918,12 +2931,28 @@ static int pagemap_scan_pte_hole(unsigned long addr, unsigned long end, { struct pagemap_scan_private *p = walk->private; struct vm_area_struct *vma = walk->vma; + unsigned long categories; int ret, err; - if (!vma || !pagemap_scan_is_interesting_page(p->cur_vma_category, p)) + if (!vma) + return 0; + + /* + * In a uffd-wp VMA an unpopulated range is treated as written: + * uffd-wp registration populates page tables and installs markers + * with WP_UNPOPULATED, so a missing marker means the range was + * zapped. See the pte_none() handling in pagemap_page_category(). + * + * hugetlb differs, see pagemap_hugetlb_category(). + */ + categories = p->cur_vma_category; + if (userfaultfd_wp(vma) && !is_vm_hugetlb_page(vma)) + categories |= PAGE_IS_WRITTEN; + + if (!pagemap_scan_is_interesting_page(categories, p)) return 0; - ret = pagemap_scan_output(p->cur_vma_category, p, addr, &end); + ret = pagemap_scan_output(categories, p, addr, &end); if (addr == end) return ret; diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 7694ca283fdc..db9d9a1983c7 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1515,8 +1515,10 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms, pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid >> 16)); /* tcon and ses pointer are checked in smb_init */ - if (tcon->ses->server == NULL) + if (!tcon->ses->server) { + cifs_small_buf_release(pSMB); return -ECONNABORTED; + } pSMB->AndXCommand = 0xFF; /* none */ pSMB->Fid = netfid; @@ -1628,8 +1630,10 @@ CIFSSMBWrite(const unsigned int xid, struct cifs_io_parms *io_parms, pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid >> 16)); /* tcon and ses pointer are checked in smb_init */ - if (tcon->ses->server == NULL) + if (!tcon->ses->server) { + cifs_buf_release(pSMB); return -ECONNABORTED; + } pSMB->AndXCommand = 0xFF; /* none */ pSMB->Fid = netfid; @@ -1908,8 +1912,10 @@ CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms, pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid >> 16)); /* tcon and ses pointer are checked in smb_init */ - if (tcon->ses->server == NULL) + if (!tcon->ses->server) { + cifs_small_buf_release(pSMB); return -ECONNABORTED; + } pSMB->AndXCommand = 0xFF; /* none */ pSMB->Fid = netfid; diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 594798a6b0fb..c9e955d0d799 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -3039,6 +3039,7 @@ void cifs_setsize(struct inode *inode, loff_t offset) inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); truncate_pagecache(inode, offset); netfs_wait_for_outstanding_io(inode); + fscache_resize_cookie(cifs_inode_cookie(inode), offset); } int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 8d985568a82f..f8f88651166b 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -197,6 +197,11 @@ void ksmbd_conn_r_count_dec(struct ksmbd_conn *conn); * This is a hack. We will move status to a proper place once we land * a multi-sessions support. */ +static inline bool ksmbd_conn_new(struct ksmbd_conn *conn) +{ + return READ_ONCE(conn->status) == KSMBD_SESS_NEW; +} + static inline bool ksmbd_conn_good(struct ksmbd_conn *conn) { return READ_ONCE(conn->status) == KSMBD_SESS_GOOD; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 64a1cfc4e809..b610cad470ea 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1102,6 +1102,8 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, * smb2_handle_negotiate() - handler for smb2 negotiate command * @work: smb work containing smb request buffer * + * The caller holds conn->srv_mutex. + * * Return: 0 */ int smb2_handle_negotiate(struct ksmbd_work *work) @@ -1115,13 +1117,6 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_debug(SMB, "Received negotiate request\n"); conn->need_neg = false; - if (ksmbd_conn_good(conn)) { - pr_err("conn->tcp_status is already in CifsGood State\n"); - work->send_no_response = 1; - return rc; - } - - ksmbd_conn_lock(conn); smb2_buf_len = get_rfc1002_len(work->request_buf); smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); if (smb2_neg_size > smb2_buf_len) { @@ -1272,7 +1267,6 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_conn_set_need_setup(conn); err_out: - ksmbd_conn_unlock(conn); if (rc) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index b23203a1c286..4ad01a0fa1cf 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -592,23 +592,46 @@ int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command) struct ksmbd_conn *conn = work->conn; int ret; - conn->dialect = - ksmbd_negotiate_smb_dialect(work->request_buf); - ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect); - if (command == SMB2_NEGOTIATE_HE) { + /* + * An SMB2 NEGOTIATE is valid for a new connection, or after an + * SMB1 multi-protocol negotiate has selected SMB2. Do not allow + * a second SMB2 NEGOTIATE to replace connection-wide state + * while a session setup is pending. KSMBD_SESS_NEED_RECONNECT + * is a transient session state and does not restart transport + * negotiation. + */ + ksmbd_conn_lock(conn); + if (!ksmbd_conn_new(conn) && + !ksmbd_conn_need_negotiate(conn)) { + work->send_no_response = 1; + ksmbd_conn_set_exiting(conn); + ksmbd_conn_unlock(conn); + return 0; + } + + conn->dialect = + ksmbd_negotiate_smb_dialect(work->request_buf); + ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect); ret = smb2_handle_negotiate(work); + ksmbd_conn_unlock(conn); return ret; } if (command == SMB_COM_NEGOTIATE) { + ksmbd_conn_lock(conn); + conn->dialect = + ksmbd_negotiate_smb_dialect(work->request_buf); + ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect); if (__smb2_negotiate(conn)) { init_smb3_11_server(conn); - init_smb2_neg_rsp(work); + ret = init_smb2_neg_rsp(work); ksmbd_debug(SMB, "Upgrade to SMB2 negotiation\n"); - return 0; + } else { + ret = smb_handle_negotiate(work); } - return smb_handle_negotiate(work); + ksmbd_conn_unlock(conn); + return ret; } pr_err("Unknown SMB negotiation command: %u\n", command); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 5b6d8bb8edb2..51e37e89d1aa 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -487,6 +487,7 @@ int ksmbd_close_fd(struct ksmbd_work *work, u64 id) { struct ksmbd_file *fp; struct ksmbd_file_table *ft; + bool closed = false; if (!has_file_id(id)) return 0; @@ -501,6 +502,9 @@ int ksmbd_close_fd(struct ksmbd_work *work, u64 id) fp = NULL; else { fp->f_state = FP_CLOSED; + idr_remove(ft->idr, id); + fp->volatile_id = KSMBD_NO_FID; + closed = true; if (!atomic_dec_and_test(&fp->refcount)) fp = NULL; } @@ -508,7 +512,7 @@ int ksmbd_close_fd(struct ksmbd_work *work, u64 id) write_unlock(&ft->lock); if (!fp) - return -EINVAL; + return closed ? 0 : -EINVAL; __put_fd_final(work, fp); return 0; diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index b89c7e3a2047..8862f77241e6 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -62,6 +62,8 @@ struct ms_hyperv_info { }; }; u64 shared_gpa_boundary; + bool msi_ext_dest_id; + bool confidential_vmbus_available; }; extern struct ms_hyperv_info ms_hyperv; extern bool hv_nested; diff --git a/include/drm/drm_exec.h b/include/drm/drm_exec.h index aa786b828a0a..dee6ebdbe416 100644 --- a/include/drm/drm_exec.h +++ b/include/drm/drm_exec.h @@ -65,31 +65,35 @@ drm_exec_obj(struct drm_exec *exec, unsigned long index) return index < exec->num_objects ? exec->objects[index] : NULL; } +/* Helper for drm_exec_for_each_locked_object(). Internal use only. */ +#define __drm_exec_for_each_locked_object(exec, obj, __index) \ + for (unsigned long __index = 0; ((obj) = drm_exec_obj(exec, __index)); ++__index) /** * drm_exec_for_each_locked_object - iterate over all the locked objects * @exec: drm_exec object - * @index: unsigned long index for the iteration * @obj: the current GEM object * * Iterate over all the locked GEM objects inside the drm_exec object. */ -#define drm_exec_for_each_locked_object(exec, index, obj) \ - for ((index) = 0; ((obj) = drm_exec_obj(exec, index)); ++(index)) +#define drm_exec_for_each_locked_object(exec, obj) \ + __drm_exec_for_each_locked_object(exec, obj, __UNIQUE_ID(drm_exec)) +/* Helper for drm_exec_for_each_locked_object_reverse(). Internal use only. */ +#define __drm_exec_for_each_locked_object_reverse(exec, obj, __index) \ + for (unsigned long __index = (exec)->num_objects - 1; \ + ((obj) = drm_exec_obj(exec, __index)); --__index) /** * drm_exec_for_each_locked_object_reverse - iterate over all the locked * objects in reverse locking order * @exec: drm_exec object - * @index: unsigned long index for the iteration * @obj: the current GEM object * * Iterate over all the locked GEM objects inside the drm_exec object in - * reverse locking order. Note that @index may go below zero and wrap, + * reverse locking order. Note that the internal index may wrap around, * but that will be caught by drm_exec_obj(), returning a NULL object. */ -#define drm_exec_for_each_locked_object_reverse(exec, index, obj) \ - for ((index) = (exec)->num_objects - 1; \ - ((obj) = drm_exec_obj(exec, index)); --(index)) +#define drm_exec_for_each_locked_object_reverse(exec, obj) \ + __drm_exec_for_each_locked_object_reverse(exec, obj, __UNIQUE_ID(drm_exec)) /** * drm_exec_until_all_locked - loop until all GEM objects are locked diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index c1d38d54a112..2faf8aaf98dc 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -256,8 +256,6 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var, int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper); -struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper); -void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper); void drm_fb_helper_unregister_info(struct drm_fb_helper *fb_helper); void drm_fb_helper_fill_info(struct fb_info *info, struct drm_fb_helper *fb_helper, @@ -340,16 +338,6 @@ drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) return 0; } -static inline struct fb_info * -drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) -{ - return NULL; -} - -static inline void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper) -{ -} - static inline void drm_fb_helper_unregister_info(struct drm_fb_helper *fb_helper) { } diff --git a/include/hyperv/hvhdk.h b/include/hyperv/hvhdk.h index 1057455b84f2..cdc74199ba3f 100644 --- a/include/hyperv/hvhdk.h +++ b/include/hyperv/hvhdk.h @@ -540,9 +540,15 @@ union hv_interrupt_control { u64 as_uint64; struct { u32 interrupt_type; /* enum hv_interrupt_type */ +#if IS_ENABLED(CONFIG_X86) u32 level_triggered : 1; u32 logical_dest_mode : 1; u32 rsvd : 30; +#elif IS_ENABLED(CONFIG_ARM64) + u32 rsvd1 : 2; + u32 asserted : 1; + u32 rsvd2 : 29; +#endif } __packed; }; diff --git a/include/hyperv/hvhdk_mini.h b/include/hyperv/hvhdk_mini.h index 858f6a3925b3..45827d49c9a5 100644 --- a/include/hyperv/hvhdk_mini.h +++ b/include/hyperv/hvhdk_mini.h @@ -126,8 +126,9 @@ enum hv_dynamic_processor_feature_property { struct hv_input_get_system_property { u32 property_id; /* enum hv_system_property */ + u32 reserved; union { - u32 as_uint32; + u64 as_uint64; #if IS_ENABLED(CONFIG_X86) /* enum hv_dynamic_processor_feature_property */ u32 hv_processor_feature; diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 02de2ede560f..7e7cdc7612be 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -134,6 +134,8 @@ static inline bool mem_alloc_profiling_enabled(void) &mem_alloc_profiling_key); } +bool mem_alloc_profiling_permanently_disabled(void); + static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) { struct alloc_tag_counters v = { 0, 0 }; @@ -239,6 +241,7 @@ static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag) #define DEFINE_ALLOC_TAG(_alloc_tag) static inline bool mem_alloc_profiling_enabled(void) { return false; } +static inline bool mem_alloc_profiling_permanently_disabled(void) { return true; } static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) {} static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 5fb8d0e3f9c1..3287232e3cad 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -58,6 +58,7 @@ extern void can_rx_unregister(struct net *net, struct net_device *dev, void *data); extern int can_send(struct sk_buff *skb, int loop); +void can_set_skb_uid(struct sk_buff *skb); void can_sock_destruct(struct sock *sk); #endif /* !_CAN_CORE_H */ diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index 1abc25a8d144..869ea574a40a 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -49,13 +49,11 @@ bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb); /** * struct can_skb_priv - private additional data inside CAN sk_buffs * @ifindex: ifindex of the first interface the CAN frame appeared on - * @skbcnt: atomic counter to have an unique id together with skb pointer * @frame_len: length of CAN frame in data link layer * @cf: align to the following CAN frame at skb->data */ struct can_skb_priv { int ifindex; - int skbcnt; unsigned int frame_len; struct can_frame cf[]; }; diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index a1194e44b527..bacefa0f1512 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -261,6 +261,10 @@ const volatile void * __must_check_fn(const volatile void *val) * CLASS(name, var)(args...): * declare the variable @var as an instance of the named class * + * CLASS_INIT(name, var, init_expr): + * declare the variable @var as an instance of the named class with + * custom initialization expression. + * * Ex. * * DEFINE_CLASS(fdget, struct fd, fdput(_T), fdget(fd), int fd) @@ -290,6 +294,9 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ class_##_name##_t var __cleanup(class_##_name##_destructor) = \ class_##_name##_constructor +#define CLASS_INIT(_name, _var, _init_expr) \ + class_##_name##_t _var __cleanup(class_##_name##_destructor) = (_init_expr) + #define __scoped_class(_name, var, _label, args...) \ for (CLASS(_name, var)(args); ; ({ goto _label; })) \ if (0) { \ diff --git a/include/linux/dma/qcom_bam_dma.h b/include/linux/dma/qcom_bam_dma.h index 68fc0e643b1b..d9d07a9ab313 100644 --- a/include/linux/dma/qcom_bam_dma.h +++ b/include/linux/dma/qcom_bam_dma.h @@ -13,9 +13,12 @@ * supported by BAM DMA Engine. * * @cmd_and_addr - upper 8 bits command and lower 24 bits register address. - * @data - for write command: content to be written into peripheral register. - * for read command: dest addr to write peripheral register value. - * @mask - register mask. + * @data - For write command: content to be written into peripheral register. + * For read command: lower 32 bits of destination address. + * @mask - For write command: register write mask. + * For read command on BAM v1.6.0+: upper 4 bits of destination address. + * For read command on BAM < v1.6.0: ignored by hardware. + * Setting to 0 ensures 32-bit addressing compatibility. * @reserved - for future usage. * */ @@ -42,6 +45,10 @@ enum bam_command_type { * @addr: target address * @cmd: BAM command * @data: actual data for write and dest addr for read in le32 + * + * For BAM v1.6.0+, the mask field behavior depends on command type: + * - Write commands: mask = write mask (typically 0xffffffff) + * - Read commands: mask = upper 4 bits of destination address (0 for 32-bit) */ static inline void bam_prep_ce_le32(struct bam_cmd_element *bam_ce, u32 addr, @@ -50,7 +57,11 @@ bam_prep_ce_le32(struct bam_cmd_element *bam_ce, u32 addr, bam_ce->cmd_and_addr = cpu_to_le32((addr & 0xffffff) | ((cmd & 0xff) << 24)); bam_ce->data = data; - bam_ce->mask = cpu_to_le32(0xffffffff); + if (cmd == BAM_READ_COMMAND) + bam_ce->mask = cpu_to_le32(0x0); /* 32-bit addressing */ + else + bam_ce->mask = cpu_to_le32(0xffffffff); /* Write mask */ + bam_ce->reserved = 0; } /* @@ -60,7 +71,7 @@ bam_prep_ce_le32(struct bam_cmd_element *bam_ce, u32 addr, * @bam_ce: BAM command element * @addr: target address * @cmd: BAM command - * @data: actual data for write and dest addr for read + * @data: actual data for write and destination address for read */ static inline void bam_prep_ce(struct bam_cmd_element *bam_ce, u32 addr, diff --git a/include/linux/file.h b/include/linux/file.h index af1768d934a0..27484b444d31 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -127,4 +127,129 @@ extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; +/* + * fd_prepare: Combined fd + file allocation cleanup class. + * @err: Error code to indicate if allocation succeeded. + * @__fd: Allocated fd (may not be accessed directly) + * @__file: Allocated struct file pointer (may not be accessed directly) + * + * Allocates an fd and a file together. On error paths, automatically cleans + * up whichever resource was successfully allocated. Allows flexible file + * allocation with different functions per usage. + * + * Do not use directly. + */ +struct fd_prepare { + s32 err; + s32 __fd; /* do not access directly */ + struct file *__file; /* do not access directly */ +}; + +/* Typedef for fd_prepare cleanup guards. */ +typedef struct fd_prepare class_fd_prepare_t; + +/* + * Accessors for fd_prepare class members. + * _Generic() is used for zero-cost type safety. + */ +#define fd_prepare_fd(_fdf) \ + (_Generic((_fdf), struct fd_prepare: (_fdf).__fd)) + +#define fd_prepare_file(_fdf) \ + (_Generic((_fdf), struct fd_prepare: (_fdf).__file)) + +/* Do not use directly. */ +static inline void class_fd_prepare_destructor(const struct fd_prepare *fdf) +{ + if (unlikely(fdf->__fd >= 0)) + put_unused_fd(fdf->__fd); + if (unlikely(!IS_ERR_OR_NULL(fdf->__file))) + fput(fdf->__file); +} + +/* Do not use directly. */ +static inline int class_fd_prepare_lock_err(const struct fd_prepare *fdf) +{ + if (unlikely(fdf->err)) + return fdf->err; + if (unlikely(fdf->__fd < 0)) + return fdf->__fd; + if (unlikely(IS_ERR(fdf->__file))) + return PTR_ERR(fdf->__file); + if (unlikely(!fdf->__file)) + return -ENOMEM; + return 0; +} + +/* + * __FD_PREPARE_INIT - Helper to initialize fd_prepare class. + * @_fd_flags: flags for get_unused_fd_flags() + * @_file_owned: expression that returns struct file * + * + * Returns a struct fd_prepare with fd, file, and err set. + * If fd allocation fails, fd will be negative and err will be set. If + * fd succeeds but file_init_expr fails, file will be ERR_PTR and err + * will be set. The err field is the single source of truth for error + * checking. + */ +#define __FD_PREPARE_INIT(_fd_flags, _file_owned) \ + ({ \ + struct fd_prepare fdf = { \ + .__fd = get_unused_fd_flags((_fd_flags)), \ + }; \ + if (likely(fdf.__fd >= 0)) \ + fdf.__file = (_file_owned); \ + fdf.err = ACQUIRE_ERR(fd_prepare, &fdf); \ + fdf; \ + }) + +/* + * FD_PREPARE - Macro to declare and initialize an fd_prepare variable. + * + * Declares and initializes an fd_prepare variable with automatic + * cleanup. No separate scope required - cleanup happens when variable + * goes out of scope. + * + * @_fdf: name of struct fd_prepare variable to define + * @_fd_flags: flags for get_unused_fd_flags() + * @_file_owned: struct file to take ownership of (can be expression) + */ +#define FD_PREPARE(_fdf, _fd_flags, _file_owned) \ + CLASS_INIT(fd_prepare, _fdf, __FD_PREPARE_INIT(_fd_flags, _file_owned)) + +/* + * fd_publish - Publish prepared fd and file to the fd table. + * @_fdf: struct fd_prepare variable + */ +#define fd_publish(_fdf) \ + ({ \ + struct fd_prepare *fdp = &(_fdf); \ + VFS_WARN_ON_ONCE(fdp->err); \ + VFS_WARN_ON_ONCE(fdp->__fd < 0); \ + VFS_WARN_ON_ONCE(IS_ERR_OR_NULL(fdp->__file)); \ + fd_install(fdp->__fd, fdp->__file); \ + retain_and_null_ptr(fdp->__file); \ + take_fd(fdp->__fd); \ + }) + +/* Do not use directly. */ +#define __FD_ADD(_fdf, _fd_flags, _file_owned) \ + ({ \ + FD_PREPARE(_fdf, _fd_flags, _file_owned); \ + s32 ret = _fdf.err; \ + if (likely(!ret)) \ + ret = fd_publish(_fdf); \ + ret; \ + }) + +/* + * FD_ADD - Allocate and install an fd and file in one step. + * @_fd_flags: flags for get_unused_fd_flags() + * @_file_owned: struct file to take ownership of + * + * Returns the allocated fd number, or negative error code on failure. + */ +#define FD_ADD(_fd_flags, _file_owned) \ + __FD_ADD(__UNIQUE_ID(fd_prepare), _fd_flags, _file_owned) + #endif /* __LINUX_FILE_H */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 84cf41f51f05..6e51f5a48c74 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1657,6 +1657,7 @@ void iopf_free_group(struct iopf_group *group); int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); void iopf_group_response(struct iopf_group *group, enum iommu_page_response_code status); +void iopf_group_dequeue(struct iopf_group *group); #else static inline int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev) @@ -1702,5 +1703,9 @@ static inline void iopf_group_response(struct iopf_group *group, enum iommu_page_response_code status) { } + +static inline void iopf_group_dequeue(struct iopf_group *group) +{ +} #endif /* CONFIG_IOMMU_IOPF */ #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 5c3f98a418c3..7244d8e15536 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -389,7 +389,7 @@ enum { /* This should match the actual table size of * ata_eh_cmd_timeout_table in libata-eh.c. */ - ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8, + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 9, /* * Quirk flags: may be set by libata or controller drivers on drives. diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index dbc614dfe0d5..aafa0c04f917 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -115,7 +115,7 @@ struct nf_nat_sip_hooks { unsigned int *datalen); void (*seq_adjust)(struct sk_buff *skb, - unsigned int protoff, s16 off); + unsigned int protoff, s32 off); unsigned int (*expect)(struct sk_buff *skb, unsigned int protoff, diff --git a/include/linux/slab.h b/include/linux/slab.h index 22daf3f34a76..a12601cc93a1 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -238,7 +238,7 @@ enum _slab_flag_bits { #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ -/* Slab created using create_boot_cache */ +/* Slab caches without obj_exts array */ #ifdef CONFIG_SLAB_OBJ_EXT #define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) #else @@ -641,6 +641,9 @@ enum kmalloc_cache_type { #endif #ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, +#endif +#ifndef CONFIG_SLAB_OBJ_EXT + KMALLOC_NO_OBJ_EXT = KMALLOC_NORMAL, #endif KMALLOC_RANDOM_START = KMALLOC_NORMAL, KMALLOC_RANDOM_END = KMALLOC_RANDOM_START + RANDOM_KMALLOC_CACHES_NR, @@ -654,6 +657,9 @@ enum kmalloc_cache_type { #endif #ifdef CONFIG_MEMCG KMALLOC_CGROUP, +#endif +#ifdef CONFIG_SLAB_OBJ_EXT + KMALLOC_NO_OBJ_EXT, #endif NR_KMALLOC_TYPES }; diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 0ba112175bb3..7204586c10c3 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -209,6 +209,8 @@ enum tb_link_width { * @link_width: Width of the downstream facing link * @link_usb4: Downstream link is USB4 * @is_unplugged: The XDomain is unplugged + * @removing: Set by tb_xdomain_remove() under @lock to prevent + * concurrent delayed work queueing * @needs_uuid: If the XDomain does not have @remote_uuid it will be * queried first * @service_ids: Used to generate IDs for the services @@ -257,6 +259,7 @@ struct tb_xdomain { enum tb_link_width link_width; bool link_usb4; bool is_unplugged; + bool removing; bool needs_uuid; struct ida service_ids; struct ida in_hopids; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index c0e716aec26a..796a380664bd 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -214,7 +214,10 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, { vm_flags &= __VM_UFFD_FLAGS; - if (vma->vm_flags & VM_DROPPABLE) + if (vma->vm_flags & (VM_DROPPABLE | VM_SHADOW_STACK)) + return false; + + if (!is_vm_hugetlb_page(vma) && (vma->vm_flags & VM_SPECIAL)) return false; if ((vm_flags & VM_UFFD_MINOR) && diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 2613cfe5b8a3..87b3f99e6ebf 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -647,6 +647,8 @@ enum { #define HCI_LE_EXT_ADV 0x10 #define HCI_LE_PERIODIC_ADV 0x20 #define HCI_LE_CHAN_SEL_ALG2 0x40 +#define HCI_LE_PAST_SENDER 0x01 +#define HCI_LE_PAST_RECEIVER 0x02 #define HCI_LE_CIS_CENTRAL 0x10 #define HCI_LE_CIS_PERIPHERAL 0x20 #define HCI_LE_ISO_BROADCASTER 0x40 @@ -2068,6 +2070,44 @@ struct hci_cp_le_set_privacy_mode { __u8 mode; } __packed; +#define HCI_OP_LE_PAST 0x205a +struct hci_cp_le_past { + __le16 handle; + __le16 service_data; + __le16 sync_handle; +} __packed; + +struct hci_rp_le_past { + __u8 status; + __le16 handle; +} __packed; + +#define HCI_OP_LE_PAST_SET_INFO 0x205b +struct hci_cp_le_past_set_info { + __le16 handle; + __le16 service_data; + __u8 adv_handle; +} __packed; + +struct hci_rp_le_past_set_info { + __u8 status; + __le16 handle; +} __packed; + +#define HCI_OP_LE_PAST_PARAMS 0x205c +struct hci_cp_le_past_params { + __le16 handle; + __u8 mode; + __le16 skip; + __le16 sync_timeout; + __u8 cte_type; +} __packed; + +struct hci_rp_le_past_params { + __u8 status; + __le16 handle; +} __packed; + #define HCI_OP_LE_READ_BUFFER_SIZE_V2 0x2060 struct hci_rp_le_read_buffer_size_v2 { __u8 status; @@ -2800,6 +2840,20 @@ struct hci_evt_le_ext_adv_set_term { __u8 num_evts; } __packed; +#define HCI_EV_LE_PAST_RECEIVED 0x18 +struct hci_ev_le_past_received { + __u8 status; + __le16 handle; + __le16 service_data; + __le16 sync_handle; + __u8 sid; + __u8 bdaddr_type; + bdaddr_t bdaddr; + __u8 phy; + __le16 interval; + __u8 clock_accuracy; +} __packed; + #define HCI_EVT_LE_CIS_ESTABLISHED 0x19 struct hci_evt_le_cis_established { __u8 status; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index b5640980fbf4..a08d8910ba26 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -2054,6 +2054,18 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define sync_recv_capable(dev) \ ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) #define sync_recv_enabled(dev) (le_enabled(dev) && sync_recv_capable(dev)) +#define past_sender_capable(dev) \ + ((dev)->le_features[3] & HCI_LE_PAST_SENDER) +#define past_receiver_capable(dev) \ + ((dev)->le_features[3] & HCI_LE_PAST_RECEIVER) +#define past_capable(dev) \ + (past_sender_capable(dev) || past_receiver_capable(dev)) +#define past_sender_enabled(dev) \ + (le_enabled(dev) && past_sender_capable(dev)) +#define past_receiver_enabled(dev) \ + (le_enabled(dev) && past_receiver_capable(dev)) +#define past_enabled(dev) \ + (past_sender_enabled(dev) || past_receiver_enabled(dev)) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ (!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG))) diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index f5be96f08b9d..8234915854b6 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -119,6 +119,8 @@ struct mgmt_rp_read_index_list { #define MGMT_SETTING_ISO_BROADCASTER BIT(20) #define MGMT_SETTING_ISO_SYNC_RECEIVER BIT(21) #define MGMT_SETTING_LL_PRIVACY BIT(22) +#define MGMT_SETTING_PAST_SENDER BIT(23) +#define MGMT_SETTING_PAST_RECEIVER BIT(24) #define MGMT_OP_READ_INFO 0x0004 #define MGMT_READ_INFO_SIZE 0 diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 2be04ca409d1..17a97086b294 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -24,7 +24,9 @@ #include <linux/netfilter.h> /* for union nf_inet_addr */ #include <linux/ip.h> #include <linux/ipv6.h> /* for struct ipv6hdr */ +#include <net/route.h> #include <net/ipv6.h> +#include <net/ip6_fib.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif @@ -1637,8 +1639,8 @@ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, - unsigned int hooknum, struct ip_vs_iphdr *iph); + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int hooknum, struct ip_vs_iphdr *ciph); void ip_vs_dest_dst_rcu_free(struct rcu_head *head); #ifdef CONFIG_IP_VS_IPV6 @@ -1651,8 +1653,8 @@ int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, - unsigned int hooknum, struct ip_vs_iphdr *iph); + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int hooknum, struct ip_vs_iphdr *ciph); #endif #ifdef CONFIG_SYSCTL @@ -1717,15 +1719,15 @@ static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp) } void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int dir); + struct ip_vs_conn *cp, int dir, unsigned int toff, + bool has_ports); #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int dir); + struct ip_vs_conn *cp, int dir, unsigned int toff, + bool has_ports, struct ip_vs_iphdr *ciph); #endif -__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset); - static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum) { __be32 diff[2] = { ~old, new }; @@ -1751,6 +1753,33 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } +static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af) +{ + /* Checksum unnecessary or already validated? */ + if (skb_csum_unnecessary(skb)) + return false; + /* LOCAL_OUT ? */ + if (!skb->dev || skb->dev->flags & IFF_LOOPBACK) + return false; + /* !LOCAL_IN (FORWARD) ? */ + if (af == AF_INET6) { + if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL)) + return false; + } else { + if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) + return false; + } + return true; +} + +static inline bool ip_vs_checksum_common_check(struct sk_buff *skb, + int offset, int proto, int af) +{ + if (!ip_vs_checksum_needed(skb, af)) + return true; + return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af); +} + /* Forget current conntrack (unconfirmed) and attach notrack entry */ static inline void ip_vs_notrack(struct sk_buff *skb) { diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 4a30bd458c5a..c13c758aca7e 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -480,11 +480,15 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) { - unsigned int seq, hh_alen; + unsigned int seq, hh_alen = HH_DATA_ALIGN(ETH_HLEN); + int err; + + err = skb_cow_head(skb, hh_alen); + if (err) + return err; do { seq = read_seqbegin(&hh->hh_lock); - hh_alen = HH_DATA_ALIGN(ETH_HLEN); memcpy(skb->data - hh_alen, hh->hh_data, ETH_ALEN + hh_alen - ETH_HLEN); } while (read_seqretry(&hh->hh_lock, seq)); return 0; diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index e9a8350e7ccf..80f50fd0f7ad 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -45,9 +45,12 @@ struct nf_conntrack_expect { void (*expectfn)(struct nf_conn *new, struct nf_conntrack_expect *this); - /* Helper to assign to new connection */ + /* Helper that created this expectation */ struct nf_conntrack_helper __rcu *helper; + /* Helper to assign to new connection */ + struct nf_conntrack_helper __rcu *assign_helper; + /* The conntrack of the master connection */ struct nf_conn *master; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index fda5bc82dd50..e6b31aa9d6b7 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1288,6 +1288,7 @@ static inline void nft_use_inc_restore(u32 *use) * @sets: sets in the table * @objects: stateful objects in the table * @flowtables: flow tables in the table + * @objname_ht: hashtable for objects lookup by name * @hgenerator: handle generator state * @handle: table handle * @use: number of chain references to this table @@ -1307,6 +1308,7 @@ struct nft_table { struct list_head sets; struct list_head objects; struct list_head flowtables; + struct rhltable objname_ht; u64 hgenerator; u64 handle; u32 use; @@ -1394,7 +1396,7 @@ static inline void *nft_obj_data(const struct nft_object *obj) #define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr)) struct nft_object *nft_obj_lookup(const struct net *net, - const struct nft_table *table, + struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask); diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 7c2bc46c6705..8a0967af8f0c 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -80,6 +80,7 @@ struct xdp_sock { * call of __xsk_generic_xmit(). */ struct sk_buff *skb; + bool drain_cont; struct list_head map_list; /* Protects map_list */ diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index cac56e6b0869..92a2358c6ce3 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -85,11 +85,16 @@ struct xsk_buff_pool { bool unaligned; bool tx_sw_csum; void *addrs; - /* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect: - * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when - * sockets share a single cq when the same netdev and queue id is shared. + /* Mutual exclusion of the completion ring in the SKB mode. + * Protect: NAPI TX thread and sendmsg error paths in the SKB + * destructor callback. */ - spinlock_t cq_lock; + spinlock_t cq_prod_lock; + /* Mutual exclusion of the completion ring in the SKB mode. + * Protect: when sockets share a single cq when the same netdev + * and queue id is shared. + */ + spinlock_t cq_cached_prod_lock; struct xdp_buff_xsk *free_heads[]; }; diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index a0635b128d7a..cc0a1f320f17 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -684,7 +684,6 @@ extern int sas_register_ha(struct sas_ha_struct *); extern int sas_unregister_ha(struct sas_ha_struct *); extern void sas_prep_resume_ha(struct sas_ha_struct *sas_ha); extern void sas_resume_ha(struct sas_ha_struct *sas_ha); -extern void sas_resume_ha_no_sync(struct sas_ha_struct *sas_ha); extern void sas_suspend_ha(struct sas_ha_struct *sas_ha); int sas_phy_reset(struct sas_phy *phy, int hard_reset); diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 3b060ea6eed7..810e874639ca 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -1583,11 +1583,11 @@ struct rkisp1_ext_params_wdr_config { sizeof(struct rkisp1_ext_params_wdr_config)) /** - * enum rksip1_ext_param_buffer_version - RkISP1 extensible parameters version + * enum rkisp1_ext_param_buffer_version - RkISP1 extensible parameters version * * @RKISP1_EXT_PARAM_BUFFER_V1: First version of RkISP1 extensible parameters */ -enum rksip1_ext_param_buffer_version { +enum rkisp1_ext_param_buffer_version { RKISP1_EXT_PARAM_BUFFER_V1 = 1, }; @@ -1667,7 +1667,7 @@ enum rksip1_ext_param_buffer_version { * +---------------------------------------------------------------------+ * * @version: The RkISP1 extensible parameters buffer version, see - * :c:type:`rksip1_ext_param_buffer_version` + * :c:type:`rkisp1_ext_param_buffer_version` * @data_size: The RkISP1 configuration data effective size, excluding this * header * @data: The RkISP1 extensible configuration data blocks diff --git a/io_uring/net.c b/io_uring/net.c index 3ab2bfca1bd5..f8b7cf2b2fa5 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -433,6 +433,7 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->flags |= REQ_F_NOWAIT; if (req->flags & REQ_F_BUFFER_SELECT) sr->buf_group = req->buf_index; + sr->mshot_total_len = sr->mshot_len = 0; if (sr->flags & IORING_RECVSEND_BUNDLE) { if (req->opcode == IORING_OP_SENDMSG) return -EINVAL; diff --git a/kernel/audit.c b/kernel/audit.c index e175fce41ef9..b2612f7ca631 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -2115,7 +2115,8 @@ void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, void audit_log_n_string(struct audit_buffer *ab, const char *string, size_t slen) { - int avail, new_len; + int avail; + size_t new_len; unsigned char *ptr; struct sk_buff *skb; @@ -2125,7 +2126,13 @@ void audit_log_n_string(struct audit_buffer *ab, const char *string, BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); - new_len = slen + 3; /* enclosing quotes + null terminator */ + + /* enclosing quotes + null terminator */ + if (check_add_overflow(slen, 3, &new_len)) { + audit_log_format(ab, "?"); + return; + } + if (new_len > avail) { avail = audit_expand(ab, new_len); if (!avail) diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index d0bd6e549634..f9de58df00fe 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1047,6 +1047,10 @@ int audit_del_rule(struct audit_entry *entry) goto out; } + list_del_rcu(&e->list); + list_del(&e->rule.list); + synchronize_rcu(); + if (e->rule.watch) audit_remove_watch_rule(&e->rule); @@ -1064,8 +1068,6 @@ int audit_del_rule(struct audit_entry *entry) audit_signals--; #endif - list_del_rcu(&e->list); - list_del(&e->rule.list); call_rcu(&e->rcu, audit_free_rule_rcu); out: diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 725c5772429d..a5b31443550b 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -830,7 +830,7 @@ static struct uprobe *hprobe_expire(struct hprobe *hprobe, bool get) if (try_cmpxchg(&hprobe->state, &hstate, uprobe ? HPROBE_STABLE : HPROBE_GONE)) { /* We won the race, we are the ones to unlock SRCU */ __srcu_read_unlock(&uretprobes_srcu, hprobe->srcu_idx); - return get ? get_uprobe(uprobe) : uprobe; + return get && uprobe ? get_uprobe(uprobe) : uprobe; } /* diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index e82bb019b920..5d8fc382c4a1 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -870,8 +870,19 @@ static int sugov_start(struct cpufreq_policy *policy) memset(sg_cpu, 0, sizeof(*sg_cpu)); sg_cpu->cpu = cpu; sg_cpu->sg_policy = sg_policy; + } + + /* + * Publish the hooks only after all per-CPU data is initialized, so a + * shared policy's sugov_update_shared() never reads an uninitialized + * sibling sugov_cpu. + */ + for_each_cpu(cpu, policy->cpus) { + struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); + cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, uu); } + return 0; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index d5052f238adf..e8b9cf0767b2 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1036,7 +1036,8 @@ static void update_dl_entity(struct sched_dl_entity *dl_se) if (dl_time_before(dl_se->deadline, rq_clock(rq)) || dl_entity_overflow(dl_se, rq_clock(rq))) { - if (unlikely((!dl_is_implicit(dl_se) || dl_se->dl_defer) && + if (unlikely((!dl_is_implicit(dl_se) || + (dl_se->dl_defer && dl_se->dl_defer_running)) && !dl_time_before(dl_se->deadline, rq_clock(rq)) && !is_dl_boosted(dl_se))) { update_dl_revised_wakeup(dl_se, rq); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 01f98f8a86e6..1c9ae332afad 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -868,10 +868,8 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter return -ENOMEM; ret = get_ips_from_filter(filter, notfilter, addrs, mods, num); - if (ret < 0) - return ret; - - ret = register_fprobe_ips(fp, addrs, ret); + if (ret >= 0) + ret = register_fprobe_ips(fp, addrs, ret); for (int i = 0; i < num; i++) { if (mods[i]) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index b0842df4d6e9..a0a02b482846 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3771,8 +3771,8 @@ static void trace_module_add_events(struct module *mod) end = mod->trace_events + mod->num_trace_events; for_each_event(call, start, end) { - __register_event(*call, mod); - __add_event_to_tracers(*call); + if (!__register_event(*call, mod)) + __add_event_to_tracers(*call); } update_cache_events(mod); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c6679caf2e9b..9c63ea51c8be 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1027,6 +1027,9 @@ static int regex_match_full(char *str, struct regex *r, int len) if (!len) return strcmp(str, r->pattern) == 0; + if (len < r->len) + return 0; + return strncmp(str, r->pattern, len) == 0; } diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index 8001dbf16891..f7eb875811be 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -1481,11 +1481,21 @@ static int enable_trace_fprobe(struct trace_event_call *call, list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) { ret = __register_trace_fprobe(tf); if (ret < 0) - return ret; + goto err; } } return 0; + +err: + /* Failed to enable one of them. Roll back all */ + list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) + __unregister_trace_fprobe(tf); + if (file) + trace_probe_remove_file(tp, file); + else + trace_probe_clear_flag(tp, TP_FLAG_PROFILE); + return ret; } /* diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index dc8a1eafbe57..32b7e1d972a4 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -29,6 +29,7 @@ static void mmio_reset_data(struct trace_array *tr) { overrun_detected = false; prev_overruns = 0; + atomic_set(&dropped_count, 0); tracing_reset_online_cpus(&tr->array_buffer); } @@ -293,11 +294,15 @@ device_initcall(init_mmio_trace); static void __trace_mmiotrace_rw(struct trace_array *tr, struct mmiotrace_rw *rw) { - struct trace_buffer *buffer = tr->array_buffer.buffer; + struct trace_buffer *buffer; struct ring_buffer_event *event; struct trace_mmiotrace_rw *entry; unsigned int trace_ctx; + if (!tr) + return; + + buffer = tr->array_buffer.buffer; trace_ctx = tracing_gen_ctx_flags(0); event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW, sizeof(*entry), trace_ctx); @@ -320,11 +325,15 @@ void mmio_trace_rw(struct mmiotrace_rw *rw) static void __trace_mmiotrace_map(struct trace_array *tr, struct mmiotrace_map *map) { - struct trace_buffer *buffer = tr->array_buffer.buffer; + struct trace_buffer *buffer; struct ring_buffer_event *event; struct trace_mmiotrace_map *entry; unsigned int trace_ctx; + if (!tr) + return; + + buffer = tr->array_buffer.buffer; trace_ctx = tracing_gen_ctx_flags(0); event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP, sizeof(*entry), trace_ctx); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 918fafc5d45c..8e1df280d311 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1906,7 +1906,11 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[], trace_probe_log_err(0, BAD_VAR); return ERR_PTR(-ENOENT); } - /* Note: $argN starts from $arg1 */ + /* Note: $argN starts from $arg1, so $arg0 is invalid. */ + if (n == 0) { + trace_probe_log_err(0, BAD_ARG_NUM); + return ERR_PTR(-EINVAL); + } ret = sprint_nth_btf_arg(n - 1, type, buf + used, bufsize - used, ctx); if (ret < 0) diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 3082d977efaa..7c6d3a086fdc 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -26,6 +26,15 @@ static bool mem_profiling_support = true; static bool mem_profiling_support; #endif +/* + * Memory allocation profiling is permanently disabled and cannot be enabled. + * Must be called after setup_early_mem_profiling(). + */ +bool mem_alloc_profiling_permanently_disabled(void) +{ + return !mem_profiling_support; +} + static struct codetag_type *alloc_tag_cttype; #ifdef CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU diff --git a/lib/assoc_array.c b/lib/assoc_array.c index 388e656ac974..01619e88a52c 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -255,7 +255,8 @@ assoc_array_walk(const struct assoc_array *array, sc_segments = shortcut->index_key[sc_level >> ASSOC_ARRAY_KEY_CHUNK_SHIFT]; dissimilarity = segments ^ sc_segments; - if (round_up(sc_level, ASSOC_ARRAY_KEY_CHUNK_SIZE) > shortcut->skip_to_level) { + if (shortcut->skip_to_level < round_down(sc_level, + ASSOC_ARRAY_KEY_CHUNK_SIZE) + ASSOC_ARRAY_KEY_CHUNK_SIZE) { /* Trim segments that are beyond the shortcut */ int shift = shortcut->skip_to_level & ASSOC_ARRAY_KEY_CHUNK_MASK; dissimilarity &= ~(ULONG_MAX << shift); diff --git a/lib/test_fortify/Makefile b/lib/test_fortify/Makefile index 399cae880e1d..44cd5df41a81 100644 --- a/lib/test_fortify/Makefile +++ b/lib/test_fortify/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 ccflags-y := $(call cc-disable-warning,fortify-source) +ccflags-y += $(call cc-disable-warning,stringop-overread) quiet_cmd_test_fortify = TEST $@ cmd_test_fortify = $(CONFIG_SHELL) $(src)/test_fortify.sh \ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c08aa3db9643..bd3093a6cc62 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3871,6 +3871,18 @@ static int __folio_split(struct folio *folio, unsigned int new_order, remap_flags = RMP_USE_SHARED_ZEROPAGE; remap_page(folio, 1 << order, remap_flags); + /* + * Drop the mapping while the inode is still pinned. @folio stays + * locked and present in the page cache until the loop below, so + * eviction cannot free the inode yet; @lock_at is not enough, it may + * be a tail beyond EOF that the split already dropped from the page + * cache. Nothing past this point may touch the inode or the mapping. + */ + if (mapping) { + i_mmap_unlock_read(mapping); + mapping = NULL; + } + /* * Unlock all after-split folios except the one containing * @lock_at page. If @folio is not split, it will be kept locked. diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e0b36a634eb6..5515870b5b15 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -705,7 +705,7 @@ static int allocate_file_region_entries(struct resv_map *resv, spin_lock(&resv->lock); - list_splice(&allocated_regions, &resv->region_cache); + list_splice_init(&allocated_regions, &resv->region_cache); resv->region_cache_count += to_allocate; } @@ -5634,8 +5634,12 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, */ ; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { - if (!userfaultfd_wp(dst_vma)) - entry = huge_pte_clear_uffd_wp(entry); + /* + * A hwpoison entry never carries the uffd-wp bit: it is + * installed fresh by make_hwpoison_entry() and + * hugetlb_change_protection() leaves it untouched, so + * there is nothing to clear for the child. + */ set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); @@ -5654,7 +5658,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, set_huge_pte_at(src, addr, src_pte, entry, sz); } if (!userfaultfd_wp(dst_vma)) - entry = huge_pte_clear_uffd_wp(entry); + entry = pte_swp_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_pte_marker(entry))) { pte_marker marker = copy_pte_marker( diff --git a/mm/memcontrol-v1.h b/mm/memcontrol-v1.h index 6358464bb416..4cdbab2bffe6 100644 --- a/mm/memcontrol-v1.h +++ b/mm/memcontrol-v1.h @@ -103,7 +103,11 @@ static inline void memcg1_remove_from_trees(struct mem_cgroup *memcg) {} static inline void memcg1_soft_limit_reset(struct mem_cgroup *memcg) {} static inline void memcg1_css_offline(struct mem_cgroup *memcg) {} -static inline bool memcg1_oom_prepare(struct mem_cgroup *memcg, bool *locked) { return true; } +static inline bool memcg1_oom_prepare(struct mem_cgroup *memcg, bool *locked) +{ + *locked = false; + return true; +} static inline void memcg1_oom_finish(struct mem_cgroup *memcg, bool locked) {} static inline void memcg1_oom_recover(struct mem_cgroup *memcg) {} diff --git a/mm/migrate_device.c b/mm/migrate_device.c index abd9f6850db6..4abceeae55ab 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -209,7 +209,8 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, bool anon_exclusive; pte_t swp_pte; - flush_cache_page(vma, addr, pte_pfn(pte)); + if (pte_present(pte)) + flush_cache_page(vma, addr, pte_pfn(pte)); anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page); if (anon_exclusive) { @@ -230,7 +231,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, migrate->cpages++; /* Set the dirty flag on the folio now the pte is gone. */ - if (pte_dirty(pte)) + if (pte_present(pte) && pte_dirty(pte)) folio_mark_dirty(folio); /* Setup special migration page table entry */ diff --git a/mm/mm_init.c b/mm/mm_init.c index 1b977fa9e8be..d2d915984611 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1565,7 +1565,7 @@ void __ref free_area_init_core_hotplug(struct pglist_data *pgdat) { int nid = pgdat->node_id; enum zone_type z; - int cpu; + int cpu, i; pgdat_init_internals(pgdat); @@ -1583,10 +1583,17 @@ void __ref free_area_init_core_hotplug(struct pglist_data *pgdat) pgdat->node_start_pfn = 0; pgdat->node_present_pages = 0; - for_each_online_cpu(cpu) { - struct per_cpu_nodestat *p; + /* + * Hot-unplug can leave per-cpu vmstat deltas unfolded (folders skip + * offline nodes) - reconcile this at online. Foreign access to counters + * is safe: the node is not online yet and we hold the hotplug lock. + */ + for_each_possible_cpu(cpu) { + struct per_cpu_nodestat *p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu); - p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu); + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) + if (p->vm_node_stat_diff[i]) + node_page_state_add(p->vm_node_stat_diff[i], pgdat, i); memset(p, 0, sizeof(*p)); } diff --git a/mm/page_reporting.c b/mm/page_reporting.c index e4c428e61d8c..68c791d243b1 100644 --- a/mm/page_reporting.c +++ b/mm/page_reporting.c @@ -80,7 +80,8 @@ __page_reporting_request(struct page_reporting_dev_info *prdev) * now we are limiting this to running no more than once every * couple of seconds. */ - schedule_delayed_work(&prdev->work, PAGE_REPORTING_DELAY); + queue_delayed_work(system_freezable_wq, &prdev->work, + PAGE_REPORTING_DELAY); } /* notify prdev of free page reporting request */ @@ -343,7 +344,8 @@ static void page_reporting_process(struct work_struct *work) */ state = atomic_cmpxchg(&prdev->state, state, PAGE_REPORTING_IDLE); if (state == PAGE_REPORTING_REQUESTED) - schedule_delayed_work(&prdev->work, PAGE_REPORTING_DELAY); + queue_delayed_work(system_freezable_wq, &prdev->work, + PAGE_REPORTING_DELAY); } static DEFINE_MUTEX(page_reporting_mutex); diff --git a/mm/percpu-km.c b/mm/percpu-km.c index 4efa74a495cb..dc096b5a6ce4 100644 --- a/mm/percpu-km.c +++ b/mm/percpu-km.c @@ -75,7 +75,7 @@ static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) chunk->base_addr = page_address(pages); spin_lock_irqsave(&pcpu_lock, flags); - pcpu_chunk_populated(chunk, 0, nr_pages); + pcpu_chunk_populated(chunk, 0, chunk->nr_pages); spin_unlock_irqrestore(&pcpu_lock, flags); pcpu_stats_chunk_alloc(); diff --git a/mm/slab.h b/mm/slab.h index 36893299fa67..c452f2a32c80 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -394,9 +394,13 @@ static inline struct kmem_cache * kmalloc_slab(size_t size, kmem_buckets *b, gfp_t flags, unsigned long caller) { unsigned int index; + enum kmalloc_cache_type type = kmalloc_type(flags, caller); + + if (flags & __GFP_NO_OBJ_EXT) + type = KMALLOC_NO_OBJ_EXT; if (!b) - b = &kmalloc_caches[kmalloc_type(flags, caller)]; + b = &kmalloc_caches[type]; if (size <= 192) index = kmalloc_size_index[size_index_elem(size)]; else @@ -435,7 +439,8 @@ static inline bool is_kmalloc_normal(struct kmem_cache *s) { if (!is_kmalloc_cache(s)) return false; - return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT)); + + return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT|SLAB_NO_OBJ_EXT)); } bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj); @@ -520,6 +525,25 @@ bool slab_in_kunit_test(void); static inline bool slab_in_kunit_test(void) { return false; } #endif +/* + * Return true if KMALLOC_NORMAL caches may need obj_exts arrays. + * + * Memory allocation profiling requires obj_exts for all caches. + * Memcg usually doesn't need them for normal kmalloc caches, but kmalloc types + * with a priority higher than KMALLOC_CGROUP can be aliased with KMALLOC_NORMAL. + */ +static inline bool need_kmalloc_no_objext(void) +{ + if (!mem_alloc_profiling_permanently_disabled()) + return true; + + if (!mem_cgroup_kmem_disabled() && + (KMALLOC_NORMAL == KMALLOC_RECLAIM)) + return true; + + return false; +} + #ifdef CONFIG_SLAB_OBJ_EXT /* diff --git a/mm/slab_common.c b/mm/slab_common.c index 04583044a2bf..085af9a96fd9 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -803,6 +803,12 @@ EXPORT_SYMBOL(kmalloc_size_roundup); #define KMALLOC_RANDOM_NAME(N, sz) #endif +#ifdef CONFIG_SLAB_OBJ_EXT +#define KMALLOC_NO_OBJ_EXT_NAME(sz) .name[KMALLOC_NO_OBJ_EXT] = "kmalloc-no-objext-" #sz, +#else +#define KMALLOC_NO_OBJ_EXT_NAME(sz) +#endif + #define INIT_KMALLOC_INFO(__size, __short_size) \ { \ .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ @@ -810,6 +816,7 @@ EXPORT_SYMBOL(kmalloc_size_roundup); KMALLOC_CGROUP_NAME(__short_size) \ KMALLOC_DMA_NAME(__short_size) \ KMALLOC_RANDOM_NAME(RANDOM_KMALLOC_CACHES_NR, __short_size) \ + KMALLOC_NO_OBJ_EXT_NAME(__short_size) \ .size = __size, \ } @@ -917,6 +924,12 @@ new_kmalloc_cache(int idx, enum kmalloc_cache_type type) return; } flags |= SLAB_ACCOUNT; + } else if (IS_ENABLED(CONFIG_SLAB_OBJ_EXT) && type == KMALLOC_NO_OBJ_EXT) { + if (!need_kmalloc_no_objext()) { + kmalloc_caches[type][idx] = kmalloc_caches[KMALLOC_NORMAL][idx]; + return; + } + flags |= SLAB_NO_OBJ_EXT | SLAB_NO_MERGE; } else if (IS_ENABLED(CONFIG_ZONE_DMA) && (type == KMALLOC_DMA)) { flags |= SLAB_CACHE_DMA; } diff --git a/mm/slub.c b/mm/slub.c index 71e09c675047..5ddd2a5c9e79 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2096,42 +2096,6 @@ static inline void init_slab_obj_exts(struct slab *slab) slab->obj_exts = 0; } -/* - * Calculate the allocation size for slabobj_ext array. - * - * When memory allocation profiling is enabled, the obj_exts array - * could be allocated from the same slab cache it's being allocated for. - * This would prevent the slab from ever being freed because it would - * always contain at least one allocated object (its own obj_exts array). - * - * To avoid this, increase the allocation size when we detect the array - * may come from the same cache, forcing it to use a different cache. - */ -static inline size_t obj_exts_alloc_size(struct kmem_cache *s, - struct slab *slab, gfp_t gfp) -{ - size_t sz = sizeof(struct slabobj_ext) * slab->objects; - struct kmem_cache *obj_exts_cache; - - if (sz > KMALLOC_MAX_CACHE_SIZE) - return sz; - - if (!is_kmalloc_normal(s)) - return sz; - - obj_exts_cache = kmalloc_slab(sz, NULL, gfp, 0); - /* - * We can't simply compare s with obj_exts_cache, because random kmalloc - * caches have multiple caches per size, selected by caller address. - * Since caller address may differ between kmalloc_slab() and actual - * allocation, bump size when sizes are equal. - */ - if (s->object_size == obj_exts_cache->object_size) - return obj_exts_cache->object_size + 1; - - return sz; -} - int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, gfp_t gfp, bool new_slab) { @@ -2140,13 +2104,17 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, unsigned long new_exts; unsigned long old_exts; struct slabobj_ext *vec; - size_t sz; + size_t sz = sizeof(struct slabobj_ext) * slab->objects; gfp &= ~OBJCGS_CLEAR_MASK; - /* Prevent recursive extension vector allocation */ - gfp |= __GFP_NO_OBJ_EXT; - sz = obj_exts_alloc_size(s, slab, gfp); + /* + * In most cases, obj_exts arrays are allocated from normal kmalloc. + * However, normal kmalloc caches must allocate them from + * KMALLOC_NO_OBJ_EXT caches to prevent recursion. + */ + if (is_kmalloc_normal(s)) + gfp |= __GFP_NO_OBJ_EXT; /* * Note that allow_spin may be false during early boot and its @@ -2155,7 +2123,7 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, * very early allocations on those. */ if (unlikely(!allow_spin)) - vec = kmalloc_nolock(sz, __GFP_ZERO | __GFP_NO_OBJ_EXT, + vec = kmalloc_nolock(sz, __GFP_ZERO | (gfp & __GFP_NO_OBJ_EXT), slab_nid(slab)); else vec = kmalloc_node(sz, gfp | __GFP_ZERO, slab_nid(slab)); @@ -2173,8 +2141,21 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, return -ENOMEM; } - VM_WARN_ON_ONCE(virt_to_slab(vec) != NULL && - virt_to_slab(vec)->slab_cache == s); + if (IS_ENABLED(CONFIG_DEBUG_VM)) { + struct kmem_cache *exts_cache; + struct slab *exts_slab; + + exts_slab = virt_to_slab(vec); + if (exts_slab) { + /* + * The vector must be allocated from either normal or + * KMALLOC_NO_OBJ_EXT kmalloc caches to avoid cycles. + */ + exts_cache = exts_slab->slab_cache; + WARN_ON_ONCE(!is_kmalloc_normal(exts_cache) && + !(exts_cache->flags & SLAB_NO_OBJ_EXT)); + } + } new_exts = (unsigned long)vec; if (unlikely(!allow_spin)) @@ -2198,7 +2179,6 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, * assign slabobj_exts in parallel. In this case the existing * objcg vector should be reused. */ - mark_objexts_empty(vec); if (unlikely(!allow_spin)) kfree_nolock(vec); else @@ -2229,14 +2209,6 @@ static inline void free_slab_obj_exts(struct slab *slab) return; } - /* - * obj_exts was created with __GFP_NO_OBJ_EXT flag, therefore its - * corresponding extension will be NULL. alloc_tag_sub() will throw a - * warning if slab has extensions but the extension of an object is - * NULL, therefore replace NULL with CODETAG_EMPTY to indicate that - * the extension for obj_exts is expected to be NULL. - */ - mark_objexts_empty(obj_exts); if (unlikely(READ_ONCE(slab->obj_exts) & OBJEXTS_NOSPIN_ALLOC)) kfree_nolock(obj_exts); else diff --git a/mm/util.c b/mm/util.c index 8989d5767528..31a59c038ba0 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1263,7 +1263,7 @@ void snapshot_page(struct page_snapshot *ps, const struct page *page) if (ps->idx < MAX_FOLIO_NR_PAGES) { memcpy(&ps->folio_snapshot, foliop, 2 * sizeof(struct page)); nr_pages = folio_nr_pages(&ps->folio_snapshot); - if (nr_pages > 1) + if (nr_pages > 2) memcpy(&ps->folio_snapshot.__page_2, &foliop->__page_2, sizeof(struct page)); set_ps_flags(ps, foliop, page); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index ceeb19158a36..e630d6369a0c 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -2965,9 +2965,17 @@ static int abort_conn_sync(struct hci_dev *hdev, void *data) return hci_abort_conn_sync(hdev, conn, conn->abort_reason); } +static void abort_conn_destroy(struct hci_dev *hdev, void *data, int err) +{ + struct hci_conn *conn = data; + + hci_conn_put(conn); +} + int hci_abort_conn(struct hci_conn *conn, u8 reason) { struct hci_dev *hdev = conn->hdev; + int err; /* If abort_reason has already been set it means the connection is * already being aborted so don't attempt to overwrite it. @@ -2989,7 +2997,11 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) * as a result to MGMT_OP_DISCONNECT/MGMT_OP_UNPAIR which does * already queue its callback on cmd_sync_work. */ - return hci_cmd_sync_run_once(hdev, abort_conn_sync, conn, NULL); + err = hci_cmd_sync_run_once(hdev, abort_conn_sync, hci_conn_get(conn), + abort_conn_destroy); + if (err) + hci_conn_put(conn); + return (err == -EEXIST) ? 0 : err; } void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 396aafa609c9..ce89f7cbebc7 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5950,6 +5950,71 @@ static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, void *data, hci_dev_unlock(hdev); } +static int hci_le_pa_term_sync(struct hci_dev *hdev, __le16 handle) +{ + struct hci_cp_le_pa_term_sync cp; + + memset(&cp, 0, sizeof(cp)); + cp.handle = handle; + + return hci_send_cmd(hdev, HCI_OP_LE_PA_TERM_SYNC, sizeof(cp), &cp); +} + +static void hci_le_past_received_evt(struct hci_dev *hdev, void *data, + struct sk_buff *skb) +{ + struct hci_ev_le_past_received *ev = data; + int mask = hdev->link_mode; + __u8 flags = 0; + struct hci_conn *pa_sync, *conn; + + bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); + + hci_dev_lock(hdev); + + hci_dev_clear_flag(hdev, HCI_PA_SYNC); + + conn = hci_conn_hash_lookup_create_pa_sync(hdev); + if (!conn) { + bt_dev_err(hdev, + "Unable to find connection for dst %pMR sid 0x%2.2x", + &ev->bdaddr, ev->sid); + goto unlock; + } + + conn->sync_handle = le16_to_cpu(ev->sync_handle); + conn->sid = HCI_SID_INVALID; + + mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, PA_LINK, + &flags); + if (!(mask & HCI_LM_ACCEPT)) { + hci_le_pa_term_sync(hdev, ev->sync_handle); + goto unlock; + } + + if (!(flags & HCI_PROTO_DEFER)) + goto unlock; + + /* Add connection to indicate PA sync event */ + pa_sync = hci_conn_add_unset(hdev, PA_LINK, BDADDR_ANY, + HCI_ROLE_SLAVE); + + if (IS_ERR(pa_sync)) + goto unlock; + + pa_sync->sync_handle = le16_to_cpu(ev->sync_handle); + + if (ev->status) { + set_bit(HCI_CONN_PA_SYNC_FAILED, &pa_sync->flags); + + /* Notify iso layer */ + hci_connect_cfm(pa_sync, ev->status); + } + +unlock: + hci_dev_unlock(hdev); +} + static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -6426,16 +6491,6 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, hci_dev_unlock(hdev); } -static int hci_le_pa_term_sync(struct hci_dev *hdev, __le16 handle) -{ - struct hci_cp_le_pa_term_sync cp; - - memset(&cp, 0, sizeof(cp)); - cp.handle = handle; - - return hci_send_cmd(hdev, HCI_OP_LE_PA_TERM_SYNC, sizeof(cp), &cp); -} - static void hci_le_pa_sync_established_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -7250,6 +7305,10 @@ static const struct hci_le_ev { /* [0x12 = HCI_EV_LE_EXT_ADV_SET_TERM] */ HCI_LE_EV(HCI_EV_LE_EXT_ADV_SET_TERM, hci_le_ext_adv_term_evt, sizeof(struct hci_evt_le_ext_adv_set_term)), + /* [0x18 = HCI_EVT_LE_PAST_RECEIVED] */ + HCI_LE_EV(HCI_EV_LE_PAST_RECEIVED, + hci_le_past_received_evt, + sizeof(struct hci_ev_le_past_received)), /* [0x19 = HCI_EVT_LE_CIS_ESTABLISHED] */ HCI_LE_EV(HCI_EVT_LE_CIS_ESTABLISHED, hci_le_cis_established_evt, sizeof(struct hci_evt_le_cis_established)), diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 65c8a490c555..580b4a8583d5 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -825,7 +825,7 @@ int hci_cmd_sync_run_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy) { if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy)) - return 0; + return -EEXIST; return hci_cmd_sync_run(hdev, func, data, destroy); } @@ -1233,10 +1233,11 @@ static int hci_set_adv_set_random_addr_sync(struct hci_dev *hdev, u8 instance, } static int -hci_set_ext_adv_params_sync(struct hci_dev *hdev, struct adv_info *adv, +hci_set_ext_adv_params_sync(struct hci_dev *hdev, u8 instance, const struct hci_cp_le_set_ext_adv_params *cp, struct hci_rp_le_set_ext_adv_params *rp) { + struct adv_info *adv; struct sk_buff *skb; skb = __hci_cmd_sync(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(*cp), @@ -1264,11 +1265,15 @@ hci_set_ext_adv_params_sync(struct hci_dev *hdev, struct adv_info *adv, if (!rp->status) { hdev->adv_addr_type = cp->own_addr_type; - if (!cp->handle) { + if (!instance) { /* Store in hdev for instance 0 */ hdev->adv_tx_power = rp->tx_power; - } else if (adv) { - adv->tx_power = rp->tx_power; + } else { + hci_dev_lock(hdev); + adv = hci_find_adv_instance(hdev, instance); + if (adv) + adv->tx_power = rp->tx_power; + hci_dev_unlock(hdev); } } @@ -1284,9 +1289,13 @@ static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance) int err; if (instance) { + hci_dev_lock(hdev); + adv = hci_find_adv_instance(hdev, instance); - if (!adv || !adv->adv_data_changed) + if (!adv || !adv->adv_data_changed) { + hci_dev_unlock(hdev); return 0; + } } len = eir_create_adv_data(hdev, instance, pdu->data, @@ -1297,16 +1306,27 @@ static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance) pdu->operation = LE_SET_ADV_DATA_OP_COMPLETE; pdu->frag_pref = LE_SET_ADV_DATA_NO_FRAG; + if (adv) { + adv->adv_data_changed = false; + hci_dev_unlock(hdev); + } + err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_DATA, struct_size(pdu, data, len), pdu, HCI_CMD_TIMEOUT); - if (err) + if (err) { + if (instance) { + hci_dev_lock(hdev); + adv = hci_find_adv_instance(hdev, instance); + if (adv) + adv->adv_data_changed = true; + hci_dev_unlock(hdev); + } + return err; + } - /* Update data if the command succeed */ - if (adv) { - adv->adv_data_changed = false; - } else { + if (!instance) { memcpy(hdev->adv_data, pdu->data, len); hdev->adv_data_len = len; } @@ -1360,22 +1380,22 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) struct adv_info *adv; bool secondary_adv; - if (instance > 0) { - adv = hci_find_adv_instance(hdev, instance); - if (!adv) - return -EINVAL; - } else { - adv = NULL; - } - /* Updating parameters of an active instance will return a - * Command Disallowed error, so we must first disable the - * instance if it is active. + * Command Disallowed error, so disable it before taking a snapshot. */ - if (adv) { + if (instance > 0) { err = hci_disable_ext_adv_instance_sync(hdev, instance); if (err) return err; + + hci_dev_lock(hdev); + adv = hci_find_adv_instance(hdev, instance); + if (!adv) { + hci_dev_unlock(hdev); + return -EINVAL; + } + } else { + adv = NULL; } flags = hci_adv_instance_flags(hdev, instance); @@ -1386,8 +1406,11 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) connectable = (flags & MGMT_ADV_FLAG_CONNECTABLE) || mgmt_get_connectable(hdev); - if (!is_advertising_allowed(hdev, connectable)) + if (!is_advertising_allowed(hdev, connectable)) { + if (instance) + hci_dev_unlock(hdev); return -EPERM; + } /* Set require_privacy to true only when non-connectable * advertising is used and it is not periodic. @@ -1398,8 +1421,11 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) err = hci_get_random_address(hdev, require_privacy, adv_use_rpa(hdev, flags), adv, &own_addr_type, &random_addr); - if (err < 0) + if (err < 0) { + if (instance) + hci_dev_unlock(hdev); return err; + } memset(&cp, 0, sizeof(cp)); @@ -1450,6 +1476,9 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) cp.channel_map = hdev->le_adv_channel_map; cp.handle = adv ? adv->handle : instance; + if (instance) + hci_dev_unlock(hdev); + if (flags & MGMT_ADV_FLAG_SEC_2M) { cp.primary_phy = HCI_ADV_PHY_1M; cp.secondary_phy = HCI_ADV_PHY_2M; @@ -1462,12 +1491,12 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) cp.secondary_phy = HCI_ADV_PHY_1M; } - err = hci_set_ext_adv_params_sync(hdev, adv, &cp, &rp); + err = hci_set_ext_adv_params_sync(hdev, instance, &cp, &rp); if (err) return err; /* Update adv data as tx power is known now */ - err = hci_set_ext_adv_data_sync(hdev, cp.handle); + err = hci_set_ext_adv_data_sync(hdev, instance); if (err) return err; @@ -1475,9 +1504,14 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) own_addr_type == ADDR_LE_DEV_RANDOM_RESOLVED) && bacmp(&random_addr, BDADDR_ANY)) { /* Check if random address need to be updated */ - if (adv) { - if (!bacmp(&random_addr, &adv->random_addr)) + if (instance) { + hci_dev_lock(hdev); + adv = hci_find_adv_instance(hdev, instance); + if (!adv || !bacmp(&random_addr, &adv->random_addr)) { + hci_dev_unlock(hdev); return 0; + } + hci_dev_unlock(hdev); } else { if (!bacmp(&random_addr, &hdev->random_addr)) return 0; @@ -1499,9 +1533,13 @@ static int hci_set_ext_scan_rsp_data_sync(struct hci_dev *hdev, u8 instance) int err; if (instance) { + hci_dev_lock(hdev); + adv = hci_find_adv_instance(hdev, instance); - if (!adv || !adv->scan_rsp_changed) + if (!adv || !adv->scan_rsp_changed) { + hci_dev_unlock(hdev); return 0; + } } len = eir_create_scan_rsp(hdev, instance, pdu->data); @@ -1511,15 +1549,27 @@ static int hci_set_ext_scan_rsp_data_sync(struct hci_dev *hdev, u8 instance) pdu->operation = LE_SET_ADV_DATA_OP_COMPLETE; pdu->frag_pref = LE_SET_ADV_DATA_NO_FRAG; + if (adv) { + adv->scan_rsp_changed = false; + hci_dev_unlock(hdev); + } + err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_SCAN_RSP_DATA, struct_size(pdu, data, len), pdu, HCI_CMD_TIMEOUT); - if (err) + if (err) { + if (instance) { + hci_dev_lock(hdev); + adv = hci_find_adv_instance(hdev, instance); + if (adv) + adv->scan_rsp_changed = true; + hci_dev_unlock(hdev); + } + return err; + } - if (adv) { - adv->scan_rsp_changed = false; - } else { + if (!instance) { memcpy(hdev->scan_rsp_data, pdu->data, len); hdev->scan_rsp_data_len = len; } @@ -1534,8 +1584,14 @@ static int __hci_set_scan_rsp_data_sync(struct hci_dev *hdev, u8 instance) memset(&cp, 0, sizeof(cp)); + if (instance) + hci_dev_lock(hdev); + len = eir_create_scan_rsp(hdev, instance, cp.data); + if (instance) + hci_dev_unlock(hdev); + if (hdev->scan_rsp_data_len == len && !memcmp(cp.data, hdev->scan_rsp_data, len)) return 0; @@ -1670,9 +1726,13 @@ static int hci_set_per_adv_data_sync(struct hci_dev *hdev, u8 instance) struct adv_info *adv = NULL; if (instance) { + hci_dev_lock(hdev); + adv = hci_find_adv_instance(hdev, instance); - if (!adv || !adv->periodic) + if (!adv || !adv->periodic) { + hci_dev_unlock(hdev); return 0; + } } len = eir_create_per_adv_data(hdev, instance, pdu->data); @@ -1681,6 +1741,9 @@ static int hci_set_per_adv_data_sync(struct hci_dev *hdev, u8 instance) pdu->handle = adv ? adv->handle : instance; pdu->operation = LE_SET_ADV_DATA_OP_COMPLETE; + if (adv) + hci_dev_unlock(hdev); + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_PER_ADV_DATA, struct_size(pdu, data, len), pdu, HCI_CMD_TIMEOUT); @@ -4450,6 +4513,9 @@ static int hci_le_set_event_mask_sync(struct hci_dev *hdev) if (ext_adv_capable(hdev)) events[2] |= 0x02; /* LE Advertising Set Terminated */ + if (past_receiver_capable(hdev)) + events[2] |= 0x80; /* LE PAST Received */ + if (cis_capable(hdev)) { events[3] |= 0x01; /* LE CIS Established */ if (cis_peripheral_capable(hdev)) @@ -6446,7 +6512,7 @@ static int hci_le_ext_directed_advertising_sync(struct hci_dev *hdev, if (err) return err; - err = hci_set_ext_adv_params_sync(hdev, NULL, &cp, &rp); + err = hci_set_ext_adv_params_sync(hdev, 0, &cp, &rp); if (err) return err; @@ -6617,7 +6683,9 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) if (hci_dev_test_flag(hdev, HCI_LE_SCAN) && hdev->le_scan_type == LE_SCAN_ACTIVE && !hci_dev_test_flag(hdev, HCI_LE_SIMULTANEOUS_ROLES)) { - hci_conn_del(conn); + conn->state = BT_OPEN; + hci_abort_conn_sync(hdev, conn, + HCI_ERROR_REJ_LIMITED_RESOURCES); hci_conn_put(conn); return -EBUSY; } diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 90d32ea8f979..4c32191ec830 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -546,9 +546,10 @@ static int hidp_process_data(struct hidp_session *session, struct sk_buff *skb, } if (test_bit(HIDP_WAITING_FOR_RETURN, &session->flags) && - param == session->waiting_report_type) { + param == session->waiting_report_type) { if (session->waiting_report_number < 0 || - session->waiting_report_number == skb->data[0]) { + (skb->len && + session->waiting_report_number == skb->data[0])) { /* hidp_get_raw_report() is waiting on this report. */ session->report_return = skb; done_with_skb = 0; @@ -563,16 +564,18 @@ static int hidp_process_data(struct hidp_session *session, struct sk_buff *skb, static void hidp_recv_ctrl_frame(struct hidp_session *session, struct sk_buff *skb) { - unsigned char hdr, type, param; + unsigned char type, param; + u8 *hdr; int free_skb = 1; BT_DBG("session %p skb %p len %u", session, skb, skb->len); - hdr = skb->data[0]; - skb_pull(skb, 1); + hdr = skb_pull_data(skb, 1); + if (!hdr) + goto free; - type = hdr & HIDP_HEADER_TRANS_MASK; - param = hdr & HIDP_HEADER_PARAM_MASK; + type = *hdr & HIDP_HEADER_TRANS_MASK; + param = *hdr & HIDP_HEADER_PARAM_MASK; switch (type) { case HIDP_TRANS_HANDSHAKE: @@ -593,6 +596,7 @@ static void hidp_recv_ctrl_frame(struct hidp_session *session, break; } +free: if (free_skb) kfree_skb(skb); } @@ -600,14 +604,15 @@ static void hidp_recv_ctrl_frame(struct hidp_session *session, static void hidp_recv_intr_frame(struct hidp_session *session, struct sk_buff *skb) { - unsigned char hdr; + u8 *hdr; BT_DBG("session %p skb %p len %u", session, skb, skb->len); - hdr = skb->data[0]; - skb_pull(skb, 1); + hdr = skb_pull_data(skb, 1); + if (!hdr) + goto free; - if (hdr == (HIDP_TRANS_DATA | HIDP_DATA_RTYPE_INPUT)) { + if (*hdr == (HIDP_TRANS_DATA | HIDP_DATA_RTYPE_INPUT)) { hidp_set_timer(session); if (session->input) @@ -619,9 +624,10 @@ static void hidp_recv_intr_frame(struct hidp_session *session, BT_DBG("report len %d", skb->len); } } else { - BT_DBG("Unsupported protocol header 0x%02x", hdr); + BT_DBG("Unsupported protocol header 0x%02x", *hdr); } +free: kfree_skb(skb); } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index f2ff10ae76e2..fcf4fd78c7cc 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -23,15 +23,19 @@ static struct bt_sock_list iso_sk_list = { }; /* ---- ISO connections ---- */ +enum { + ISO_CONN_DROPPED, + __ISO_CONN_NUM_FLAGS +}; + struct iso_conn { struct hci_conn *hcon; + DECLARE_BITMAP(flags, __ISO_CONN_NUM_FLAGS); /* @lock: spinlock protecting changes to iso_conn fields */ spinlock_t lock; struct sock *sk; - struct delayed_work timeout_work; - struct sk_buff *rx_skb; __u32 rx_len; __u16 tx_sn; @@ -55,6 +59,7 @@ static void iso_sock_kill(struct sock *sk); enum { BT_SK_BIG_SYNC, BT_SK_PA_SYNC, + BT_SK_KILLED, }; struct iso_pinfo { @@ -73,6 +78,7 @@ struct iso_pinfo { __u8 base_len; __u8 base[BASE_MAX_LENGTH]; struct iso_conn *conn; + struct delayed_work timeout_work; }; static struct bt_iso_qos default_qos; @@ -80,6 +86,7 @@ static struct bt_iso_qos default_qos; static bool check_ucast_qos(struct bt_iso_qos *qos); static bool check_bcast_qos(struct bt_iso_qos *qos); static bool iso_match_sid(struct sock *sk, void *data); +static bool iso_match_sid_past(struct sock *sk, void *data); static bool iso_match_sync_handle(struct sock *sk, void *data); static bool iso_match_sync_handle_pa_report(struct sock *sk, void *data); static void iso_sock_disconn(struct sock *sk); @@ -100,17 +107,12 @@ static void iso_conn_free(struct kref *ref) BT_DBG("conn %p", conn); - if (conn->sk) - iso_pi(conn->sk)->conn = NULL; - if (conn->hcon) { conn->hcon->iso_data = NULL; - hci_conn_drop(conn->hcon); + if (!test_and_set_bit(ISO_CONN_DROPPED, conn->flags)) + hci_conn_drop(conn->hcon); } - /* Ensure no more work items will run since hci_conn has been dropped */ - disable_delayed_work_sync(&conn->timeout_work); - kfree_skb(conn->rx_skb); kfree(conn); @@ -139,6 +141,14 @@ static struct iso_conn *iso_conn_hold_unless_zero(struct iso_conn *conn) return conn; } +static struct iso_conn *iso_conn_hold(struct iso_conn *conn) +{ + BT_DBG("conn %p refcnt %u", conn, kref_read(&conn->ref)); + + kref_get(&conn->ref); + return conn; +} + static struct sock *iso_sock_hold(struct iso_conn *conn) { if (!conn || !bt_sock_linked(&iso_sk_list, conn->sk)) @@ -151,48 +161,45 @@ static struct sock *iso_sock_hold(struct iso_conn *conn) static void iso_sock_timeout(struct work_struct *work) { - struct iso_conn *conn = container_of(work, struct iso_conn, - timeout_work.work); - struct sock *sk; - - conn = iso_conn_hold_unless_zero(conn); - if (!conn) - return; - - iso_conn_lock(conn); - sk = iso_sock_hold(conn); - iso_conn_unlock(conn); - iso_conn_put(conn); - - if (!sk) - return; + struct iso_pinfo *pi = container_of(work, struct iso_pinfo, + timeout_work.work); + struct sock *sk = &pi->bt.sk; BT_DBG("sock %p state %d", sk, sk->sk_state); lock_sock(sk); - sk->sk_err = ETIMEDOUT; - sk->sk_state_change(sk); + if (!sock_flag(sk, SOCK_ZAPPED)) { + sk->sk_err = ETIMEDOUT; + sk->sk_state_change(sk); + } release_sock(sk); - sock_put(sk); } static void iso_sock_set_timer(struct sock *sk, long timeout) { + lockdep_assert(lockdep_sock_is_held(sk)); + + cancel_delayed_work(&iso_pi(sk)->timeout_work); + if (!iso_pi(sk)->conn) return; BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout); - cancel_delayed_work(&iso_pi(sk)->conn->timeout_work); - schedule_delayed_work(&iso_pi(sk)->conn->timeout_work, timeout); + schedule_delayed_work(&iso_pi(sk)->timeout_work, timeout); } static void iso_sock_clear_timer(struct sock *sk) { - if (!iso_pi(sk)->conn) - return; + BT_DBG("sock %p state %d", sk, sk->sk_state); + cancel_delayed_work(&iso_pi(sk)->timeout_work); +} + +static void iso_sock_disable_timer(struct sock *sk) +{ + lockdep_assert(!lockdep_sock_is_held(sk)); BT_DBG("sock %p state %d", sk, sk->sk_state); - cancel_delayed_work(&iso_pi(sk)->conn->timeout_work); + disable_delayed_work_sync(&iso_pi(sk)->timeout_work); } /* ---- ISO connections ---- */ @@ -207,7 +214,6 @@ static struct iso_conn *iso_conn_add(struct hci_conn *hcon) conn->hcon = hcon; iso_conn_unlock(conn); } - iso_conn_put(conn); return conn; } @@ -217,7 +223,6 @@ static struct iso_conn *iso_conn_add(struct hci_conn *hcon) kref_init(&conn->ref); spin_lock_init(&conn->lock); - INIT_DELAYED_WORK(&conn->timeout_work, iso_sock_timeout); hcon->iso_data = conn; conn->hcon = hcon; @@ -261,6 +266,7 @@ static void iso_chan_del(struct sock *sk, int err) } static void iso_conn_del(struct hci_conn *hcon, int err) + __must_hold(&hcon->hdev->lock) { struct iso_conn *conn = hcon->iso_data; struct sock *sk; @@ -275,18 +281,26 @@ static void iso_conn_del(struct hci_conn *hcon, int err) iso_conn_lock(conn); sk = iso_sock_hold(conn); iso_conn_unlock(conn); - iso_conn_put(conn); - if (!sk) { - iso_conn_put(conn); - return; - } + if (!sk) + goto done; + + iso_sock_disable_timer(sk); lock_sock(sk); - iso_sock_clear_timer(sk); iso_chan_del(sk, err); release_sock(sk); + iso_sock_kill(sk); sock_put(sk); + +done: + /* No sk access to conn->hcon any more (lock_sock + hdev->lock) */ + iso_conn_lock(conn); + conn->hcon = NULL; + hcon->iso_data = NULL; + iso_conn_unlock(conn); + + iso_conn_put(conn); } static int __iso_chan_add(struct iso_conn *conn, struct sock *sk, @@ -302,8 +316,14 @@ static int __iso_chan_add(struct iso_conn *conn, struct sock *sk, return -EBUSY; } - iso_pi(sk)->conn = conn; + if (!conn->hcon) { + BT_ERR("conn->hcon missing"); + return -EIO; + } + + iso_pi(sk)->conn = iso_conn_hold(conn); conn->sk = sk; + clear_bit(ISO_CONN_DROPPED, conn->flags); if (parent) bt_accept_enqueue(parent, sk, true); @@ -354,6 +374,7 @@ static int iso_connect_bis(struct sock *sk) return -EHOSTUNREACH; hci_dev_lock(hdev); + lock_sock(sk); if (!bis_capable(hdev)) { err = -EOPNOTSUPP; @@ -406,13 +427,10 @@ static int iso_connect_bis(struct sock *sk) goto unlock; } - lock_sock(sk); - err = iso_chan_add(conn, sk, NULL); - if (err) { - release_sock(sk); + iso_conn_put(conn); + if (err) goto unlock; - } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -428,9 +446,8 @@ static int iso_connect_bis(struct sock *sk) iso_sock_set_timer(sk, READ_ONCE(sk->sk_sndtimeo)); } - release_sock(sk); - unlock: + release_sock(sk); hci_dev_unlock(hdev); hci_dev_put(hdev); return err; @@ -458,6 +475,7 @@ static int iso_connect_cis(struct sock *sk) return -EHOSTUNREACH; hci_dev_lock(hdev); + lock_sock(sk); if (!cis_central_capable(hdev)) { err = -EOPNOTSUPP; @@ -512,13 +530,10 @@ static int iso_connect_cis(struct sock *sk) goto unlock; } - lock_sock(sk); - err = iso_chan_add(conn, sk, NULL); - if (err) { - release_sock(sk); + iso_conn_put(conn); + if (err) goto unlock; - } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -534,9 +549,8 @@ static int iso_connect_cis(struct sock *sk) iso_sock_set_timer(sk, READ_ONCE(sk->sk_sndtimeo)); } - release_sock(sk); - unlock: + release_sock(sk); hci_dev_unlock(hdev); hci_dev_put(hdev); return err; @@ -779,9 +793,15 @@ static void iso_sock_cleanup_listen(struct sock *parent) */ static void iso_sock_kill(struct sock *sk) { + iso_sock_disable_timer(sk); + + lock_sock(sk); + if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket || - sock_flag(sk, SOCK_DEAD)) + test_bit(BT_SK_KILLED, &iso_pi(sk)->flags)) { + release_sock(sk); return; + } BT_DBG("sk %p state %d", sk, sk->sk_state); @@ -795,6 +815,9 @@ static void iso_sock_kill(struct sock *sk) /* Kill poor orphan */ bt_sock_unlink(&iso_sk_list, sk); sock_set_flag(sk, SOCK_DEAD); + set_bit(BT_SK_KILLED, &iso_pi(sk)->flags); + + release_sock(sk); sock_put(sk); } @@ -824,10 +847,8 @@ static void iso_sock_disconn(struct sock *sk) } sk->sk_state = BT_DISCONN; - iso_conn_lock(iso_pi(sk)->conn); - hci_conn_drop(iso_pi(sk)->conn->hcon); - iso_pi(sk)->conn->hcon = NULL; - iso_conn_unlock(iso_pi(sk)->conn); + if (!test_and_set_bit(ISO_CONN_DROPPED, iso_pi(sk)->conn->flags)) + hci_conn_drop(iso_pi(sk)->conn->hcon); } static void __iso_sock_close(struct sock *sk) @@ -869,11 +890,11 @@ static void __iso_sock_close(struct sock *sk) /* Must be called on unlocked socket. */ static void iso_sock_close(struct sock *sk) { + iso_sock_disable_timer(sk); + lock_sock(sk); - iso_sock_clear_timer(sk); __iso_sock_close(sk); release_sock(sk); - iso_sock_kill(sk); } static void iso_sock_init(struct sock *sk, struct sock *parent) @@ -940,6 +961,8 @@ static struct sock *iso_sock_alloc(struct net *net, struct socket *sock, iso_pi(sk)->qos = default_qos; iso_pi(sk)->sync_handle = -1; + INIT_DELAYED_WORK(&iso_pi(sk)->timeout_work, iso_sock_timeout); + bt_sock_link(&iso_sk_list, sk); return sk; } @@ -1028,15 +1051,15 @@ static int iso_sock_bind_pa_sk(struct sock *sk, struct sockaddr_iso *sa, goto done; } - iso_pi(sk)->bc_num_bis = sa->iso_bc->bc_num_bis; - - for (int i = 0; i < iso_pi(sk)->bc_num_bis; i++) + for (int i = 0; i < sa->iso_bc->bc_num_bis; i++) if (sa->iso_bc->bc_bis[i] < 0x01 || sa->iso_bc->bc_bis[i] > 0x1f) { err = -EINVAL; goto done; } + iso_pi(sk)->bc_num_bis = sa->iso_bc->bc_num_bis; + memcpy(iso_pi(sk)->bc_bis, sa->iso_bc->bc_bis, iso_pi(sk)->bc_num_bis); @@ -1209,10 +1232,9 @@ static int iso_listen_bis(struct sock *sk) } err = iso_chan_add(conn, sk, NULL); - if (err) { - hci_conn_drop(hcon); + iso_conn_put(conn); + if (err) goto unlock; - } unlock: release_sock(sk); @@ -1391,6 +1413,8 @@ static int iso_sock_getname(struct socket *sock, struct sockaddr *addr, BT_DBG("sock %p, sk %p", sock, sk); + lock_sock(sk); + addr->sa_family = AF_BLUETOOTH; if (peer) { @@ -1412,6 +1436,8 @@ static int iso_sock_getname(struct socket *sock, struct sockaddr *addr, sa->iso_bdaddr_type = iso_pi(sk)->src_type; } + release_sock(sk); + return len; } @@ -1711,7 +1737,7 @@ static bool check_bcast_qos(struct bt_iso_qos *qos) return false; if (!qos->bcast.timeout) - qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT; + qos->bcast.timeout = BT_ISO_SYNC_TIMEOUT; if (qos->bcast.timeout < 0x000a || qos->bcast.timeout > 0x4000) return false; @@ -1953,8 +1979,16 @@ static int iso_sock_release(struct socket *sock) release_sock(sk); } + /* Make sure sk is valid even if iso_conn_del() is concurrent */ + sock_hold(sk); + + lock_sock(sk); sock_orphan(sk); + release_sock(sk); + iso_sock_kill(sk); + + sock_put(sk); return err; } @@ -1962,14 +1996,17 @@ static void iso_sock_ready(struct sock *sk) { BT_DBG("sk %p", sk); - if (!sk) + lockdep_assert(lockdep_sock_is_held(sk)); + + switch (sk->sk_state) { + case BT_DISCONN: + case BT_CLOSED: return; + } - lock_sock(sk); iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; sk->sk_state_change(sk); - release_sock(sk); } static bool iso_match_big(struct sock *sk, void *data) @@ -1994,7 +2031,7 @@ static bool iso_match_pa_sync_flag(struct sock *sk, void *data) static void iso_conn_ready(struct iso_conn *conn) { struct sock *parent = NULL; - struct sock *sk = conn->sk; + struct sock *sk; struct hci_ev_le_big_sync_established *ev = NULL; struct hci_ev_le_pa_sync_established *ev2 = NULL; struct hci_ev_le_per_adv_report *ev3 = NULL; @@ -2002,8 +2039,43 @@ static void iso_conn_ready(struct iso_conn *conn) BT_DBG("conn %p", conn); + iso_conn_lock(conn); + sk = iso_sock_hold(conn); + iso_conn_unlock(conn); + if (sk) { - iso_sock_ready(conn->sk); + lock_sock(sk); + + /* conn->sk may have become NULL if racing with sk close, but + * due to held hdev->lock, it can't become different sk. + */ + if (!conn->sk) { + release_sock(sk); + sock_put(sk); + return; + } + + /* Attempt to update source address in case of BIS Sender if + * the advertisement is using a random address. + */ + if (conn->hcon->type == BIS_LINK && + conn->hcon->role == HCI_ROLE_MASTER && + !bacmp(&conn->hcon->dst, BDADDR_ANY)) { + struct hci_conn *bis = conn->hcon; + struct adv_info *adv; + + adv = hci_find_adv_instance(bis->hdev, + bis->iso_qos.bcast.bis); + if (adv && bacmp(&adv->random_addr, BDADDR_ANY)) { + iso_pi(sk)->src_type = BDADDR_LE_RANDOM; + bacpy(&iso_pi(sk)->src, &adv->random_addr); + } + } + + iso_sock_ready(sk); + + release_sock(sk); + sock_put(sk); } else { hcon = conn->hcon; if (!hcon) @@ -2142,6 +2214,16 @@ static bool iso_match_sid(struct sock *sk, void *data) return ev->sid == iso_pi(sk)->bc_sid; } +static bool iso_match_sid_past(struct sock *sk, void *data) +{ + struct hci_ev_le_past_received *ev = data; + + if (iso_pi(sk)->bc_sid == HCI_SID_INVALID) + return true; + + return ev->sid == iso_pi(sk)->bc_sid; +} + static bool iso_match_sync_handle(struct sock *sk, void *data) { struct hci_evt_le_big_info_adv_report *ev = data; @@ -2161,6 +2243,7 @@ static bool iso_match_sync_handle_pa_report(struct sock *sk, void *data) int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct hci_ev_le_pa_sync_established *ev1; + struct hci_ev_le_past_received *ev1a; struct hci_evt_le_big_info_adv_report *ev2; struct hci_ev_le_per_adv_report *ev3; struct sock *sk; @@ -2174,6 +2257,7 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) * SID to listen to and once sync is established its handle needs to * be stored in iso_pi(sk)->sync_handle so it can be matched once * receiving the BIG Info. + * 1a. HCI_EV_LE_PAST_RECEIVED: alternative to 1. * 2. HCI_EVT_LE_BIG_INFO_ADV_REPORT: When connect_ind is triggered by a * a BIG Info it attempts to check if there any listening socket with * the same sync_handle and if it does then attempt to create a sync. @@ -2186,8 +2270,24 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_LISTEN, iso_match_sid, ev1); if (sk && !ev1->status) { + lock_sock(sk); iso_pi(sk)->sync_handle = le16_to_cpu(ev1->handle); iso_pi(sk)->bc_sid = ev1->sid; + release_sock(sk); + } + + goto done; + } + + ev1a = hci_recv_event_data(hdev, HCI_EV_LE_PAST_RECEIVED); + if (ev1a) { + sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_LISTEN, + iso_match_sid_past, ev1a); + if (sk && !ev1a->status) { + lock_sock(sk); + iso_pi(sk)->sync_handle = le16_to_cpu(ev1a->sync_handle); + iso_pi(sk)->bc_sid = ev1a->sid; + release_sock(sk); } goto done; @@ -2214,27 +2314,35 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) ev2); if (sk) { - int err; - struct hci_conn *hcon = iso_pi(sk)->conn->hcon; + int err = 0; + bool big_sync; + struct hci_conn *hcon; + lock_sock(sk); + + hcon = iso_pi(sk)->conn ? iso_pi(sk)->conn->hcon : NULL; iso_pi(sk)->qos.bcast.encryption = ev2->encryption; if (ev2->num_bis < iso_pi(sk)->bc_num_bis) iso_pi(sk)->bc_num_bis = ev2->num_bis; - if (!test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) && - !test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { + big_sync = !test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) && + !test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags); + + if (big_sync) err = hci_conn_big_create_sync(hdev, hcon, &iso_pi(sk)->qos, iso_pi(sk)->sync_handle, iso_pi(sk)->bc_num_bis, iso_pi(sk)->bc_bis); - if (err) { - bt_dev_err(hdev, "hci_le_big_create_sync: %d", - err); - sock_put(sk); - sk = NULL; - } + + release_sock(sk); + + if (big_sync && err) { + bt_dev_err(hdev, "hci_le_big_create_sync: %d", + err); + sock_put(sk); + sk = NULL; } } @@ -2252,9 +2360,11 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) if (!sk) goto done; - hcon = iso_pi(sk)->conn->hcon; + lock_sock(sk); + + hcon = iso_pi(sk)->conn ? iso_pi(sk)->conn->hcon : NULL; if (!hcon) - goto done; + goto release3; if (ev3->data_status == LE_PA_DATA_TRUNCATED) { /* The controller was unable to retrieve PA data. */ @@ -2262,12 +2372,12 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) HCI_MAX_PER_AD_TOT_LEN); hcon->le_per_adv_data_len = 0; hcon->le_per_adv_data_offset = 0; - goto done; + goto release3; } if (hcon->le_per_adv_data_offset + ev3->length > HCI_MAX_PER_AD_TOT_LEN) - goto done; + goto release3; memcpy(hcon->le_per_adv_data + hcon->le_per_adv_data_offset, ev3->data, ev3->length); @@ -2286,7 +2396,7 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) &base_len); if (!base || base_len > BASE_MAX_LENGTH) - goto done; + goto release3; memcpy(iso_pi(sk)->base, base, base_len); iso_pi(sk)->base_len = base_len; @@ -2296,6 +2406,9 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) */ hcon->le_per_adv_data_len = 0; } + +release3: + release_sock(sk); } else { sk = iso_get_sock(&hdev->bdaddr, BDADDR_ANY, BT_LISTEN, NULL, NULL); @@ -2314,6 +2427,7 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) } static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) + __must_hold(&hcon->hdev->lock) { if (hcon->type != CIS_LINK && hcon->type != BIS_LINK && hcon->type != PA_LINK) { @@ -2325,8 +2439,10 @@ static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) struct hci_link *link, *t; list_for_each_entry_safe(link, t, &hcon->link_list, - list) + list) { + lockdep_assert_held(&link->conn->hdev->lock); iso_conn_del(link->conn, bt_to_errno(status)); + } return; } @@ -2348,14 +2464,17 @@ static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) struct iso_conn *conn; conn = iso_conn_add(hcon); - if (conn) + if (conn) { iso_conn_ready(conn); + iso_conn_put(conn); + } } else { iso_conn_del(hcon, bt_to_errno(status)); } } static void iso_disconn_cfm(struct hci_conn *hcon, __u8 reason) + __must_hold(&hcon->hdev->lock) { if (hcon->type != CIS_LINK && hcon->type != BIS_LINK && hcon->type != PA_LINK) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index e04948fb6832..6133c65b2017 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4831,6 +4831,10 @@ static int l2cap_le_connect_rsp(struct l2cap_conn *conn, if (!chan) return -EBADSLT; + chan = l2cap_chan_hold_unless_zero(chan); + if (!chan) + return -EBADSLT; + err = 0; l2cap_chan_lock(chan); @@ -4876,6 +4880,7 @@ static int l2cap_le_connect_rsp(struct l2cap_conn *conn, } l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return err; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 79eb605be280..831fff026b0f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -858,6 +858,12 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (ll_privacy_capable(hdev)) settings |= MGMT_SETTING_LL_PRIVACY; + if (past_sender_capable(hdev)) + settings |= MGMT_SETTING_PAST_SENDER; + + if (past_receiver_capable(hdev)) + settings |= MGMT_SETTING_PAST_RECEIVER; + settings |= MGMT_SETTING_PHY_CONFIGURATION; return settings; @@ -943,6 +949,12 @@ static u32 get_current_settings(struct hci_dev *hdev) if (ll_privacy_enabled(hdev)) settings |= MGMT_SETTING_LL_PRIVACY; + if (past_sender_enabled(hdev)) + settings |= MGMT_SETTING_PAST_SENDER; + + if (past_receiver_enabled(hdev)) + settings |= MGMT_SETTING_PAST_RECEIVER; + return settings; } @@ -2687,18 +2699,28 @@ static int mgmt_hci_cmd_sync(struct sock *sk, struct hci_dev *hdev, static bool pending_eir_or_class(struct hci_dev *hdev) { struct mgmt_pending_cmd *cmd; + bool pending = false; + + mutex_lock(&hdev->mgmt_pending_lock); list_for_each_entry(cmd, &hdev->mgmt_pending, list) { switch (cmd->opcode) { case MGMT_OP_ADD_UUID: case MGMT_OP_REMOVE_UUID: case MGMT_OP_SET_DEV_CLASS: + case MGMT_OP_SET_LOCAL_NAME: case MGMT_OP_SET_POWERED: - return true; + pending = true; + break; } + + if (pending) + break; } - return false; + mutex_unlock(&hdev->mgmt_pending_lock); + + return pending; } static const u8 bluetooth_base_uuid[] = { @@ -3505,11 +3527,13 @@ static int set_io_capability(struct sock *sk, struct hci_dev *hdev, void *data, NULL, 0); } -static struct mgmt_pending_cmd *find_pairing(struct hci_conn *conn) +static struct mgmt_pending_cmd *remove_pairing(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct mgmt_pending_cmd *cmd; + mutex_lock(&hdev->mgmt_pending_lock); + list_for_each_entry(cmd, &hdev->mgmt_pending, list) { if (cmd->opcode != MGMT_OP_PAIR_DEVICE) continue; @@ -3517,9 +3541,39 @@ static struct mgmt_pending_cmd *find_pairing(struct hci_conn *conn) if (cmd->user_data != conn) continue; + list_del(&cmd->list); + mutex_unlock(&hdev->mgmt_pending_lock); return cmd; } + mutex_unlock(&hdev->mgmt_pending_lock); + + return NULL; +} + +static struct mgmt_pending_cmd *remove_pairing_by_addr(struct hci_dev *hdev, + bdaddr_t *bdaddr) +{ + struct mgmt_pending_cmd *cmd; + struct hci_conn *conn; + + mutex_lock(&hdev->mgmt_pending_lock); + + list_for_each_entry(cmd, &hdev->mgmt_pending, list) { + if (cmd->opcode != MGMT_OP_PAIR_DEVICE) + continue; + + conn = cmd->user_data; + if (bacmp(bdaddr, &conn->dst) != 0) + continue; + + list_del(&cmd->list); + mutex_unlock(&hdev->mgmt_pending_lock); + return cmd; + } + + mutex_unlock(&hdev->mgmt_pending_lock); + return NULL; } @@ -3557,10 +3611,10 @@ void mgmt_smp_complete(struct hci_conn *conn, bool complete) u8 status = complete ? MGMT_STATUS_SUCCESS : MGMT_STATUS_FAILED; struct mgmt_pending_cmd *cmd; - cmd = find_pairing(conn); + cmd = remove_pairing(conn); if (cmd) { cmd->cmd_complete(cmd, status); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); } } @@ -3570,14 +3624,14 @@ static void pairing_complete_cb(struct hci_conn *conn, u8 status) BT_DBG("status %u", status); - cmd = find_pairing(conn); + cmd = remove_pairing(conn); if (!cmd) { BT_DBG("Unable to find a pending command"); return; } cmd->cmd_complete(cmd, mgmt_status(status)); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); } static void le_pairing_complete_cb(struct hci_conn *conn, u8 status) @@ -3589,14 +3643,14 @@ static void le_pairing_complete_cb(struct hci_conn *conn, u8 status) if (!status) return; - cmd = find_pairing(conn); + cmd = remove_pairing(conn); if (!cmd) { BT_DBG("Unable to find a pending command"); return; } cmd->cmd_complete(cmd, mgmt_status(status)); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); } static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, @@ -3753,23 +3807,17 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - cmd = pending_find(MGMT_OP_PAIR_DEVICE, hdev); + cmd = remove_pairing_by_addr(hdev, &addr->bdaddr); if (!cmd) { err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, MGMT_STATUS_INVALID_PARAMS); goto unlock; } - conn = cmd->user_data; - - if (bacmp(&addr->bdaddr, &conn->dst) != 0) { - err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, - MGMT_STATUS_INVALID_PARAMS); - goto unlock; - } + conn = hci_conn_get(cmd->user_data); cmd->cmd_complete(cmd, MGMT_STATUS_CANCELLED); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, 0, addr, sizeof(*addr)); @@ -3787,6 +3835,8 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, if (conn->conn_reason == CONN_REASON_PAIR_DEVICE) hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); + hci_conn_put(conn); + unlock: hci_dev_unlock(hdev); return err; @@ -4034,6 +4084,12 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } + if (hdev_is_powered(hdev) && pending_eir_or_class(hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, + MGMT_STATUS_BUSY); + goto failed; + } + memcpy(hdev->short_name, cp->short_name, sizeof(hdev->short_name)); if (!hdev_is_powered(hdev)) { @@ -10107,14 +10163,14 @@ void mgmt_auth_failed(struct hci_conn *conn, u8 hci_status) ev.addr.type = link_to_bdaddr(conn->type, conn->dst_type); ev.status = status; - cmd = find_pairing(conn); + cmd = remove_pairing(conn); mgmt_event(MGMT_EV_AUTH_FAILED, conn->hdev, &ev, sizeof(ev), cmd ? cmd->sk : NULL); if (cmd) { cmd->cmd_complete(cmd, status); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); } } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 285a98594ba4..a25b5f626358 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -190,6 +190,9 @@ static void sco_sock_clear_timer(struct sock *sk) } /* ---- SCO connections ---- */ +/* Consumes a reference on @hcon, which the returned sco_conn owns until it is + * freed. On failure (NULL return) the reference is left for the caller to drop. + */ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) { struct sco_conn *conn = hcon->sco_data; @@ -200,6 +203,9 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) sco_conn_lock(conn); conn->hcon = hcon; sco_conn_unlock(conn); + } else { + /* conn already owns a reference on hcon */ + hci_conn_drop(hcon); } return conn; } @@ -267,10 +273,8 @@ static void sco_conn_del(struct hci_conn *hcon, int err) sco_conn_unlock(conn); sco_conn_put(conn); - if (!sk) { - sco_conn_put(conn); + if (!sk) return; - } /* Kill socket */ lock_sock(sk); @@ -285,7 +289,7 @@ static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, { BT_DBG("conn %p", conn); - sco_pi(sk)->conn = conn; + sco_pi(sk)->conn = sco_conn_hold(conn); conn->sk = sk; if (parent) @@ -368,15 +372,15 @@ static int sco_connect(struct sock *sk) */ if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { release_sock(sk); - hci_conn_drop(hcon); + sco_conn_put(conn); err = -EBADFD; goto unlock; } err = sco_chan_add(conn, sk, NULL); + sco_conn_put(conn); if (err) { release_sock(sk); - hci_conn_drop(hcon); goto unlock; } @@ -1452,8 +1456,6 @@ static void sco_conn_ready(struct sco_conn *conn) bacpy(&sco_pi(sk)->src, &conn->hcon->src); bacpy(&sco_pi(sk)->dst, &conn->hcon->dst); - sco_conn_hold(conn); - hci_conn_hold(conn->hcon); __sco_chan_add(conn, sk, parent); if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) @@ -1509,10 +1511,12 @@ static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) if (!status) { struct sco_conn *conn; - conn = sco_conn_add(hcon); + conn = sco_conn_add(hci_conn_hold(hcon)); if (conn) { sco_conn_ready(conn); sco_conn_put(conn); + } else { + hci_conn_drop(hcon); } } else sco_conn_del(hcon, bt_to_errno(status)); diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 3c36fa24bc05..92a0debf4a4a 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -215,7 +215,7 @@ static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp, struct br_mrp_oui_hdr *oui = NULL; u8 length; - length = sizeof(*sub_opt) + sizeof(*sub_tlv) + sizeof(oui) + + length = sizeof(*sub_opt) + sizeof(*sub_tlv) + sizeof(*oui) + MRP_OPT_PADDING; br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_OPTION, length); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index b77b3250afbd..ce34881a9d96 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -3686,6 +3686,7 @@ br_multicast_leave_group(struct net_bridge_mcast *brmctx, p->flags |= MDB_PG_FLAGS_FAST_LEAVE; br_multicast_del_pg(mp, p, pp); + break; } goto out; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 083e2fe96441..6544c18febef 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -296,7 +296,11 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ goto free_skb; } - neigh_hh_bridge(&neigh->hh, skb); + if (neigh_hh_bridge(&neigh->hh, skb)) { + neigh_release(neigh); + goto free_skb; + } + skb->dev = br_indev; ret = br_handle_frame_finish(net, sk, skb); diff --git a/net/can/af_can.c b/net/can/af_can.c index a624c04ed5c6..7a026f3a70a0 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -641,6 +641,16 @@ static int can_rcv_filter(struct can_dev_rcv_lists *dev_rcv_lists, struct sk_buf return matches; } +void can_set_skb_uid(struct sk_buff *skb) +{ + /* create non-zero unique skb identifier together with *skb */ + while (!(skb->hash)) + skb->hash = atomic_inc_return(&skbcounter); + + skb->sw_hash = 1; +} +EXPORT_SYMBOL(can_set_skb_uid); + static void can_receive(struct sk_buff *skb, struct net_device *dev) { struct can_dev_rcv_lists *dev_rcv_lists; @@ -652,9 +662,7 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) atomic_long_inc(&pkg_stats->rx_frames); atomic_long_inc(&pkg_stats->rx_frames_delta); - /* create non-zero unique skb identifier together with *skb */ - while (!(can_skb_prv(skb)->skbcnt)) - can_skb_prv(skb)->skbcnt = atomic_inc_return(&skbcounter); + can_set_skb_uid(skb); rcu_read_lock(); diff --git a/net/can/bcm.c b/net/can/bcm.c index 76bc7f727425..a819872fddef 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -350,7 +350,6 @@ static void bcm_can_tx(struct bcm_op *op, struct canfd_frame *cf) can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; skb_put_data(skb, cf, op->cfsiz); @@ -1621,7 +1620,6 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk, } can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; skb->dev = dev; can_skb_set_owner(skb, sk); err = can_send(skb, 1); /* send with loopback */ diff --git a/net/can/isotp.c b/net/can/isotp.c index c21d816a5274..720b911fe1ed 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -126,6 +126,15 @@ MODULE_PARM_DESC(max_pdu_size, "maximum isotp pdu size (default " #define ISOTP_FC_TIMEOUT 1 /* 1 sec */ #define ISOTP_ECHO_TIMEOUT 2 /* 2 secs */ +/* so->tx_result[so->tx_gen % ISOTP_TX_RESULT_SLOTS] holds the packed value + * (err << ISOTP_TX_RESULT_GEN_BITS | gen) for each tx generation slot, so it + * can be handled with a single READ_ONCE()/WRITE_ONCE() access. + */ +#define ISOTP_TX_RESULT_SLOTS 4 +#define ISOTP_TX_RESULT_GEN_BITS 24 +#define ISOTP_TX_RESULT_GEN_MASK ((1U << ISOTP_TX_RESULT_GEN_BITS) - 1) +#define ISOTP_TX_RESULT_ERR_MASK 0xFF + enum { ISOTP_IDLE = 0, ISOTP_WAIT_FIRST_FC, @@ -165,7 +174,8 @@ struct isotp_sock { u32 force_tx_stmin; u32 force_rx_stmin; u32 cfecho; /* consecutive frame echo tag */ - u32 tx_gen; /* generation, bumped per new tx transfer */ + u32 tx_gen; /* transfer generation, increased per new tx transfer */ + u32 tx_result[ISOTP_TX_RESULT_SLOTS]; /* per-generation result slots */ struct tpcon rx, tx; struct list_head notifier; wait_queue_head_t wait; @@ -176,6 +186,65 @@ static LIST_HEAD(isotp_notifier_list); static DEFINE_SPINLOCK(isotp_notifier_lock); static struct isotp_sock *isotp_busy_notifier; +/* increase (24 bit) tx generation value */ +static u32 isotp_inc_tx_gen(u32 gen) +{ + return (gen + 1) & ISOTP_TX_RESULT_GEN_MASK; +} + +/* store 8 bit error and 24 bit tx generation values in packed u32 element */ +static u32 isotp_pack_tx_result(u32 gen, int err) +{ + return gen | ((u32)err << ISOTP_TX_RESULT_GEN_BITS); +} + +/* get the 24 bit tx generation value from the tx result */ +static u32 isotp_get_tx_gen(u32 gen_err) +{ + return gen_err & ISOTP_TX_RESULT_GEN_MASK; +} + +/* get the 8 bit error value from the tx result */ +static u32 isotp_get_tx_err(u32 gen_err) +{ + return (gen_err >> ISOTP_TX_RESULT_GEN_BITS) & ISOTP_TX_RESULT_ERR_MASK; +} + +/* store transfer result in per-generation%4 so->tx_result[] slot */ +static void isotp_set_tx_result(struct isotp_sock *so, u32 gen, int err) +{ + WRITE_ONCE(so->tx_result[gen % ISOTP_TX_RESULT_SLOTS], + isotp_pack_tx_result(gen, err)); +} + +/* fetch the result recorded for 'gen', as a (negative) errno (0 for success) */ +static int isotp_get_tx_result(struct isotp_sock *so, u32 gen) +{ + u32 result = READ_ONCE(so->tx_result[gen % ISOTP_TX_RESULT_SLOTS]); + + if (isotp_get_tx_gen(result) != gen) { + pr_notice_once("can-isotp: tx_result[] slot reused before read\n"); + + /* report failure rather than risk a false success */ + return -ECOMM; + } + + return -(isotp_get_tx_err(result)); +} + +/* true if done, shut down or superseded ('gen' is no longer the active + * transfer). Reads tx.state first (acquire) so tx_gen/tx_result reads + * below see at least what that state write published (common sequence). + */ +static bool isotp_tx_gen_done(struct isotp_sock *so, u32 gen) +{ + /* read tx.state first for the common sequence */ + u32 state = smp_load_acquire(&so->tx.state); + + return state == ISOTP_IDLE || state == ISOTP_SHUTDOWN || + READ_ONCE(so->tx_gen) != gen; +} + static inline struct isotp_sock *isotp_sk(const struct sock *sk) { return (struct isotp_sock *)sk; @@ -198,7 +267,7 @@ static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) rxtimer); struct sock *sk = &so->sk; - if (so->rx.state == ISOTP_WAIT_DATA) { + if (READ_ONCE(so->rx.state) == ISOTP_WAIT_DATA) { /* we did not get new data frames in time */ /* report 'connection timed out' */ @@ -207,7 +276,7 @@ static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) sk_error_report(sk); /* reset rx state */ - so->rx.state = ISOTP_IDLE; + WRITE_ONCE(so->rx.state, ISOTP_IDLE); } return HRTIMER_NORESTART; @@ -233,7 +302,6 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) can_skb_reserve(nskb); can_skb_prv(nskb)->ifindex = dev->ifindex; - can_skb_prv(nskb)->skbcnt = 0; nskb->dev = dev; can_skb_set_owner(nskb, sk); @@ -366,20 +434,19 @@ static void isotp_send_cframe(struct isotp_sock *so); static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) { struct sock *sk = &so->sk; + int tx_err = EBADMSG; /* default for unknown FC status */ - if (so->tx.state != ISOTP_WAIT_FC && - so->tx.state != ISOTP_WAIT_FIRST_FC) + if (READ_ONCE(so->tx.state) != ISOTP_WAIT_FC && + READ_ONCE(so->tx.state) != ISOTP_WAIT_FIRST_FC) return 0; hrtimer_cancel(&so->txtimer); /* isotp_tx_timeout() may have given up on this job while - * hrtimer_cancel() above waited for it to finish; so->rx_lock - * (held by our caller isotp_rcv()) rules out a concurrent claim, - * so a plain recheck is enough here. + * hrtimer_cancel() above waited for it to finish => recheck */ - if (so->tx.state != ISOTP_WAIT_FC && - so->tx.state != ISOTP_WAIT_FIRST_FC) + if (READ_ONCE(so->tx.state) != ISOTP_WAIT_FC && + READ_ONCE(so->tx.state) != ISOTP_WAIT_FIRST_FC) return 1; if ((cf->len < ae + FC_CONTENT_SZ) || @@ -390,13 +457,15 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); - so->tx.state = ISOTP_IDLE; + isotp_set_tx_result(so, so->tx_gen, EBADMSG); + /* set to IDLE after publishing tx_result */ + smp_store_release(&so->tx.state, ISOTP_IDLE); wake_up_interruptible(&so->wait); return 1; } /* get static/dynamic communication params from first/every FC frame */ - if (so->tx.state == ISOTP_WAIT_FIRST_FC || + if (READ_ONCE(so->tx.state) == ISOTP_WAIT_FIRST_FC || so->opt.flags & CAN_ISOTP_DYN_FC_PARMS) { so->txfc.bs = cf->data[ae + 1]; so->txfc.stmin = cf->data[ae + 2]; @@ -420,13 +489,13 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) so->tx_gap = ktime_add_ns(so->tx_gap, (so->txfc.stmin - 0xF0) * 100000); - so->tx.state = ISOTP_WAIT_FC; + WRITE_ONCE(so->tx.state, ISOTP_WAIT_FC); } switch (cf->data[ae] & 0x0F) { case ISOTP_FC_CTS: so->tx.bs = 0; - so->tx.state = ISOTP_SENDING; + WRITE_ONCE(so->tx.state, ISOTP_SENDING); /* send CF frame and enable echo timeout handling */ hrtimer_start(&so->echotimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); @@ -441,14 +510,19 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) case ISOTP_FC_OVFLW: /* overflow on receiver side - report 'message too long' */ - sk->sk_err = EMSGSIZE; - if (!sock_flag(sk, SOCK_DEAD)) - sk_error_report(sk); + tx_err = EMSGSIZE; fallthrough; default: - /* stop this tx job */ - so->tx.state = ISOTP_IDLE; + /* reserved/unknown flow status (tx_err defaults to EBADMSG) */ + + sk->sk_err = tx_err; + if (!sock_flag(sk, SOCK_DEAD)) + sk_error_report(sk); + + isotp_set_tx_result(so, so->tx_gen, tx_err); + /* set to IDLE after publishing tx_result */ + smp_store_release(&so->tx.state, ISOTP_IDLE); wake_up_interruptible(&so->wait); } return 0; @@ -461,7 +535,7 @@ static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen, struct sk_buff *nskb; hrtimer_cancel(&so->rxtimer); - so->rx.state = ISOTP_IDLE; + WRITE_ONCE(so->rx.state, ISOTP_IDLE); if (!len || len > cf->len - pcilen) return 1; @@ -495,7 +569,7 @@ static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae) int ff_pci_sz; hrtimer_cancel(&so->rxtimer); - so->rx.state = ISOTP_IDLE; + WRITE_ONCE(so->rx.state, ISOTP_IDLE); /* get the used sender LL_DL from the (first) CAN frame data length */ so->rx.ll_dl = padlen(cf->len); @@ -549,7 +623,7 @@ static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae) /* initial setup for this pdu reception */ so->rx.sn = 1; - so->rx.state = ISOTP_WAIT_DATA; + WRITE_ONCE(so->rx.state, ISOTP_WAIT_DATA); /* no creation of flow control frames */ if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) @@ -567,7 +641,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, struct sk_buff *nskb; int i; - if (so->rx.state != ISOTP_WAIT_DATA) + if (READ_ONCE(so->rx.state) != ISOTP_WAIT_DATA) return 0; /* drop if timestamp gap is less than force_rx_stmin nano secs */ @@ -582,11 +656,9 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, hrtimer_cancel(&so->rxtimer); /* isotp_rx_timer_handler() may have raced us for so->rx.state - * while hrtimer_cancel() above waited for it to finish, already - * reporting ETIMEDOUT and resetting the reception; don't process - * this CF into a reassembly that has already been given up on. + * while hrtimer_cancel() above waited for it to finish => recheck */ - if (so->rx.state != ISOTP_WAIT_DATA) + if (READ_ONCE(so->rx.state) != ISOTP_WAIT_DATA) return 1; /* CFs are never longer than the FF */ @@ -607,7 +679,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, sk_error_report(sk); /* reset rx state */ - so->rx.state = ISOTP_IDLE; + WRITE_ONCE(so->rx.state, ISOTP_IDLE); return 1; } so->rx.sn++; @@ -621,7 +693,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, if (so->rx.idx >= so->rx.len) { /* we are done */ - so->rx.state = ISOTP_IDLE; + WRITE_ONCE(so->rx.state, ISOTP_IDLE); if ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, i + 1, so->opt.rxpad_content)) { @@ -692,8 +764,10 @@ static void isotp_rcv(struct sk_buff *skb, void *data) if (so->opt.flags & CAN_ISOTP_HALF_DUPLEX) { /* check rx/tx path half duplex expectations */ - if ((so->tx.state != ISOTP_IDLE && n_pci_type != N_PCI_FC) || - (so->rx.state != ISOTP_IDLE && n_pci_type == N_PCI_FC)) + if ((READ_ONCE(so->tx.state) != ISOTP_IDLE && + n_pci_type != N_PCI_FC) || + (READ_ONCE(so->rx.state) != ISOTP_IDLE && + n_pci_type == N_PCI_FC)) goto out_unlock; } @@ -787,6 +861,7 @@ static void isotp_send_cframe(struct isotp_sock *so) struct canfd_frame *cf; int can_send_ret; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; + u32 old_cfecho; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) @@ -800,7 +875,9 @@ static void isotp_send_cframe(struct isotp_sock *so) can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; + + /* set uid in tx skb to identify CF echo frames */ + can_set_skb_uid(skb); cf = (struct canfd_frame *)skb->data; skb_put_zero(skb, so->ll.mtu); @@ -818,12 +895,15 @@ static void isotp_send_cframe(struct isotp_sock *so) skb->dev = dev; can_skb_set_owner(skb, sk); - /* cfecho should have been zero'ed by init/isotp_rcv_echo() */ - if (so->cfecho) - pr_notice_once("can-isotp: cfecho is %08X != 0\n", so->cfecho); + /* zero'ed by init/isotp_rcv_echo(); reached lock-free via + * isotp_txfr_timer_handler() too, so use READ_ONCE()/WRITE_ONCE() + */ + old_cfecho = READ_ONCE(so->cfecho); + if (old_cfecho) + pr_notice_once("can-isotp: cfecho is %08X != 0\n", old_cfecho); /* set consecutive frame echo tag */ - so->cfecho = *(u32 *)cf->data; + WRITE_ONCE(so->cfecho, skb->hash); /* send frame with local echo enabled */ can_send_ret = can_send(skb, 1); @@ -875,7 +955,6 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) { struct sock *sk = (struct sock *)data; struct isotp_sock *so = isotp_sk(sk); - struct canfd_frame *cf = (struct canfd_frame *)skb->data; /* only handle my own local echo CF/SF skb's (no FF!) */ if (skb->sk != sk) @@ -887,32 +966,35 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) spin_lock(&so->rx_lock); /* so->cfecho may since belong to a new transfer; recheck under lock */ - if (so->cfecho != *(u32 *)cf->data) + if (READ_ONCE(so->cfecho) != skb->hash) goto out_unlock; /* cancel local echo timeout */ hrtimer_cancel(&so->echotimer); /* local echo skb with consecutive frame has been consumed */ - so->cfecho = 0; + WRITE_ONCE(so->cfecho, 0); /* claiming a transfer also takes so->rx_lock, so a plain recheck * is enough: so->tx.state can't have flipped to ISOTP_SENDING for * a new claim while we're still in here */ - if (so->tx.state != ISOTP_SENDING) + if (READ_ONCE(so->tx.state) != ISOTP_SENDING) goto out_unlock; if (so->tx.idx >= so->tx.len) { /* we are done */ - so->tx.state = ISOTP_IDLE; + + isotp_set_tx_result(so, so->tx_gen, 0); + /* set to IDLE after publishing tx_result */ + smp_store_release(&so->tx.state, ISOTP_IDLE); wake_up_interruptible(&so->wait); goto out_unlock; } if (so->txfc.bs && so->tx.bs >= so->txfc.bs) { /* stop and wait for FC with timeout */ - so->tx.state = ISOTP_WAIT_FC; + WRITE_ONCE(so->tx.state, ISOTP_WAIT_FC); hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); goto out_unlock; @@ -934,16 +1016,20 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) spin_unlock(&so->rx_lock); } -/* shared by so->txtimer's and so->echotimer's callbacks. Both timers get - * cancelled under so->rx_lock elsewhere, so this must stay lock-free to - * avoid deadlocking with that; uses so->tx_gen instead to avoid tainting - * a new transfer with an error from the one that just timed out. +/* isotp_tx_timeout: we did not get any flow control or echo frame in time + * + * Shared by so->txtimer's and so->echotimer's callbacks. Both timers get + * cancelled under so->rx_lock elsewhere, so this must stay lock-free. + * + * tx.state is acquired before tx_gen. Common sequence in isotp_tx_gen_done(). + * cmpxchg() only orders itself, not the two preceding loads. */ static enum hrtimer_restart isotp_tx_timeout(struct isotp_sock *so) { struct sock *sk = &so->sk; + /* read tx.state first for the common sequence */ + u32 old_state = smp_load_acquire(&so->tx.state); u32 gen = READ_ONCE(so->tx_gen); - u32 old_state = READ_ONCE(so->tx.state); /* don't handle timeouts in IDLE or SHUTDOWN state */ if (old_state == ISOTP_IDLE || old_state == ISOTP_SHUTDOWN) @@ -953,14 +1039,14 @@ static enum hrtimer_restart isotp_tx_timeout(struct isotp_sock *so) if (cmpxchg(&so->tx.state, old_state, ISOTP_IDLE) != old_state) return HRTIMER_NORESTART; - /* we did not get any flow control or echo frame in time */ + /* detected timeout: report 'communication error on send' */ - if (READ_ONCE(so->tx_gen) == gen) { - /* report 'communication error on send' */ - sk->sk_err = ECOMM; - if (!sock_flag(sk, SOCK_DEAD)) - sk_error_report(sk); - } + /* a stale read of this slot by a waiter still falls back to ECOMM */ + isotp_set_tx_result(so, gen, ECOMM); + + sk->sk_err = ECOMM; + if (!sock_flag(sk, SOCK_DEAD)) + sk_error_report(sk); wake_up_interruptible(&so->wait); @@ -995,7 +1081,7 @@ static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) HRTIMER_MODE_REL_SOFT); /* cfecho should be consumed by isotp_rcv_echo() here */ - if (so->tx.state == ISOTP_SENDING && !so->cfecho) + if (READ_ONCE(so->tx.state) == ISOTP_SENDING && !READ_ONCE(so->cfecho)) isotp_send_cframe(so); return HRTIMER_NORESTART; @@ -1013,10 +1099,12 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) s64 hrtimer_sec = ISOTP_ECHO_TIMEOUT; struct hrtimer *tx_hrt = &so->echotimer; u32 new_state = ISOTP_SENDING; + u32 my_gen; + u32 old_cfecho; int off; int err; - if (!so->bound || so->tx.state == ISOTP_SHUTDOWN) + if (!so->bound || READ_ONCE(so->tx.state) == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; /* claim the socket under so->rx_lock: this serializes the claim @@ -1033,29 +1121,33 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (msg->msg_flags & MSG_DONTWAIT) return -EAGAIN; - if (so->tx.state == ISOTP_SHUTDOWN) + if (READ_ONCE(so->tx.state) == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; /* wait for complete transmission of current pdu */ err = wait_event_interruptible(so->wait, - so->tx.state == ISOTP_IDLE); + READ_ONCE(so->tx.state) == ISOTP_IDLE || + READ_ONCE(so->tx.state) == ISOTP_SHUTDOWN); if (err) return err; } - /* new transfer: bump so->tx_gen and drain the old one's timers, - * still under the so->rx_lock we just claimed the socket with - */ - WRITE_ONCE(so->tx.state, ISOTP_SENDING); - WRITE_ONCE(so->tx_gen, READ_ONCE(so->tx_gen) + 1); + /* txfrtimer's callback re-arms echotimer lock-free: drain it first */ + hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); hrtimer_cancel(&so->echotimer); - hrtimer_cancel(&so->txfrtimer); - so->cfecho = 0; + + /* new transfer: increment so->tx_gen and set tx.state after barrier */ + my_gen = isotp_inc_tx_gen(READ_ONCE(so->tx_gen)); + isotp_set_tx_result(so, my_gen, ECOMM); /* prevent stale slot matching */ + WRITE_ONCE(so->tx_gen, my_gen); + smp_wmb(); /* see smp_load_acquire() in isotp_tx_[timeout|gen_done] */ + WRITE_ONCE(so->tx.state, ISOTP_SENDING); + WRITE_ONCE(so->cfecho, 0); spin_unlock_bh(&so->rx_lock); /* so->bound is only checked once above - a wakeup may have - * unbound/rebound the socket meanwhile, so re-validate it + * unbound/rebound the socket meanwhile => recheck */ if (!so->bound) { err = -EADDRNOTAVAIL; @@ -1106,7 +1198,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; + + /* set uid in tx skb to identify CF echo frames */ + can_set_skb_uid(skb); so->tx.len = size; so->tx.idx = 0; @@ -1115,8 +1209,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) skb_put_zero(skb, so->ll.mtu); /* cfecho should have been zero'ed by init / former isotp_rcv_echo() */ - if (so->cfecho) - pr_notice_once("can-isotp: uninit cfecho %08X\n", so->cfecho); + old_cfecho = READ_ONCE(so->cfecho); + if (old_cfecho) + pr_notice_once("can-isotp: uninit cfecho %08X\n", old_cfecho); /* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) { @@ -1144,7 +1239,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) cf->data[ae] |= size; /* set CF echo tag for isotp_rcv_echo() (SF-mode) */ - so->cfecho = *(u32 *)cf->data; + WRITE_ONCE(so->cfecho, skb->hash); } else { /* send first frame */ @@ -1161,7 +1256,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) so->txfc.bs = 0; /* set CF echo tag for isotp_rcv_echo() (CF-mode) */ - so->cfecho = *(u32 *)cf->data; + WRITE_ONCE(so->cfecho, skb->hash); } else { /* standard flow control check */ new_state = ISOTP_WAIT_FIRST_FC; @@ -1171,12 +1266,12 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) tx_hrt = &so->txtimer; /* no CF echo tag for isotp_rcv_echo() (FF-mode) */ - so->cfecho = 0; + WRITE_ONCE(so->cfecho, 0); } } spin_lock_bh(&so->rx_lock); - if (so->tx.state == ISOTP_SHUTDOWN) { + if (READ_ONCE(so->tx.state) == ISOTP_SHUTDOWN) { /* isotp_release() has since taken over and already drained * our timers - don't send into a socket that's going away */ @@ -1187,7 +1282,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) return -EADDRNOTAVAIL; } /* WAIT_FIRST_FC for standard FF, else stays ISOTP_SENDING */ - so->tx.state = new_state; + WRITE_ONCE(so->tx.state, new_state); hrtimer_start(tx_hrt, ktime_set(hrtimer_sec, 0), HRTIMER_MODE_REL_SOFT); spin_unlock_bh(&so->rx_lock); @@ -1204,20 +1299,49 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) __func__, ERR_PTR(err)); spin_lock_bh(&so->rx_lock); + + /* new transfer already claimed by a concurrent completion, + * timeout or sendmsg() while we were stuck in can_send()? + */ + if (READ_ONCE(so->tx_gen) != my_gen) { + /* don't touch timers and state of the new transfer */ + spin_unlock_bh(&so->rx_lock); + return err; + } + /* no transmission -> no timeout monitoring */ hrtimer_cancel(tx_hrt); goto err_out_drop_locked; } if (wait_tx_done) { - /* wait for complete transmission of current pdu */ - err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + /* wake up for: + * - concurrent sendmsg() claiming a new transfer + * - complete transmission of current PDU + * - shutdown state change in isotp_release() + * isotp_tx_gen_done() uses common tx.state/tx_gen read sequence + */ + err = wait_event_interruptible(so->wait, + isotp_tx_gen_done(so, my_gen)); if (err) goto err_event_drop; - err = sock_error(sk); - if (err) - return err; + /* still our claim, but isotp_release() force-shut it down */ + if (smp_load_acquire(&so->tx.state) == ISOTP_SHUTDOWN && + READ_ONCE(so->tx_gen) == my_gen) { + err = -EADDRNOTAVAIL; + goto err_event_drop; + } + + /* own completion, or tx_gen moved on - either way this is + * what isotp_get_tx_result() recorded for my_gen + */ + err = isotp_get_tx_result(so, my_gen); + + /* drain to avoid stale error for a later poll()/SO_ERROR */ + sock_error(sk); + + return err ? err : size; } return size; @@ -1227,15 +1351,26 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) spin_lock_bh(&so->rx_lock); goto err_out_drop_locked; err_event_drop: - /* interrupted waiting on our own transfer - drain its timers */ + /* interrupted or shut down while waiting on our own transfer */ spin_lock_bh(&so->rx_lock); + + /* new transfer already started by concurrent sendmsg()? */ + if (READ_ONCE(so->tx_gen) != my_gen) { + /* don't touch timers and states of the new transfer */ + spin_unlock_bh(&so->rx_lock); + return err; + } + hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); hrtimer_cancel(&so->echotimer); err_out_drop_locked: /* release the claim; so->rx_lock still held from above */ - so->cfecho = 0; - so->tx.state = ISOTP_IDLE; + WRITE_ONCE(so->cfecho, 0); + + /* only claim to IDLE if isotp_release() has not taken over */ + if (READ_ONCE(so->tx.state) != ISOTP_SHUTDOWN) + WRITE_ONCE(so->tx.state, ISOTP_IDLE); spin_unlock_bh(&so->rx_lock); wake_up_interruptible(&so->wait); @@ -1301,8 +1436,9 @@ static int isotp_release(struct socket *sock) /* best-effort: wait for a running pdu to finish, but don't block on * it forever - give up after the first signal */ - while (so->tx.state != ISOTP_IDLE && - wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0) + while (READ_ONCE(so->tx.state) != ISOTP_IDLE && + wait_event_interruptible(so->wait, + READ_ONCE(so->tx.state) == ISOTP_IDLE) == 0) ; /* claim the socket under so->rx_lock like sendmsg() does, so its @@ -1310,9 +1446,12 @@ static int isotp_release(struct socket *sock) * unconditionally, even when a signal cut the wait above short */ spin_lock_bh(&so->rx_lock); - so->tx.state = ISOTP_SHUTDOWN; + WRITE_ONCE(so->tx.state, ISOTP_SHUTDOWN); spin_unlock_bh(&so->rx_lock); - so->rx.state = ISOTP_IDLE; + WRITE_ONCE(so->rx.state, ISOTP_IDLE); + + /* forced SHUTDOWN may have skipped IDLE (gave up on a signal) */ + wake_up_interruptible(&so->wait); spin_lock(&isotp_notifier_lock); while (isotp_busy_notifier == so) { @@ -1428,7 +1567,8 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) * with so->bound in the same lock_sock() section above, so there is * no window in which a concurrent isotp_notify() could be missed. */ - if (so->tx.state != ISOTP_IDLE || so->rx.state != ISOTP_IDLE) { + if (READ_ONCE(so->tx.state) != ISOTP_IDLE || + READ_ONCE(so->rx.state) != ISOTP_IDLE) { err = -EAGAIN; goto out; } @@ -1462,7 +1602,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) isotp_rcv, sk, "isotp", sk); /* no consecutive frame echo skb in flight */ - so->cfecho = 0; + WRITE_ONCE(so->cfecho, 0); /* register for echo skb's */ can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), @@ -1828,7 +1968,7 @@ static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *w poll_wait(file, &so->wait, wait); /* Check for false positives due to TX state */ - if ((mask & EPOLLWRNORM) && (so->tx.state != ISOTP_IDLE)) + if ((mask & EPOLLWRNORM) && (READ_ONCE(so->tx.state) != ISOTP_IDLE)) mask &= ~(EPOLLOUT | EPOLLWRNORM); return mask; @@ -1888,13 +2028,18 @@ static __init int isotp_module_init(void) pr_info("can: isotp protocol (max_pdu_size %d)\n", max_pdu_size); + err = register_netdevice_notifier(&canisotp_notifier); + if (err) + return err; + err = can_proto_register(&isotp_can_proto); - if (err < 0) + if (err < 0) { pr_err("can: registration of isotp protocol failed %pe\n", ERR_PTR(err)); - else - register_netdevice_notifier(&canisotp_notifier); + unregister_netdevice_notifier(&canisotp_notifier); + return err; + } - return err; + return 0; } static __exit void isotp_module_exit(void) diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c index 797719cb227e..e6d81bcabc89 100644 --- a/net/can/j1939/bus.c +++ b/net/can/j1939/bus.c @@ -20,6 +20,7 @@ static void __j1939_ecu_release(struct kref *kref) struct j1939_priv *priv = ecu->priv; list_del(&ecu->list); + netdev_put(priv->ndev, &ecu->priv_dev_tracker); kfree(ecu); j1939_priv_put(priv); } @@ -155,6 +156,7 @@ struct j1939_ecu *j1939_ecu_create_locked(struct j1939_priv *priv, name_t name) if (!ecu) return ERR_PTR(-ENOMEM); kref_init(&ecu->kref); + netdev_hold(priv->ndev, &ecu->priv_dev_tracker, gfp_any()); ecu->addr = J1939_IDLE_ADDR; ecu->name = name; diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 81f58924b4ac..cf26352d1d8c 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -38,6 +38,7 @@ struct j1939_ecu { struct hrtimer ac_timer; struct kref kref; struct j1939_priv *priv; + netdevice_tracker priv_dev_tracker; /* count users, to help transport protocol decide for interaction */ int nusers; @@ -60,6 +61,7 @@ struct j1939_priv { rwlock_t lock; struct net_device *ndev; + netdevice_tracker dev_tracker; /* list of 256 ecu ptrs, that cache the claimed addresses. * also protected by the above lock @@ -230,6 +232,7 @@ enum j1939_session_state { struct j1939_session { struct j1939_priv *priv; + netdevice_tracker priv_dev_tracker; struct list_head active_session_list_entry; struct list_head sk_session_queue_entry; struct kref kref; diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index a93af55df5fd..21186932f8f6 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -137,7 +137,7 @@ static struct j1939_priv *j1939_priv_create(struct net_device *ndev) priv->ndev = ndev; kref_init(&priv->kref); kref_init(&priv->rx_kref); - dev_hold(ndev); + netdev_hold(ndev, &priv->dev_tracker, GFP_KERNEL); netdev_dbg(priv->ndev, "%s : 0x%p\n", __func__, priv); @@ -163,7 +163,7 @@ static void __j1939_priv_release(struct kref *kref) WARN_ON_ONCE(!list_empty(&priv->ecus)); WARN_ON_ONCE(!list_empty(&priv->j1939_socks)); - dev_put(ndev); + netdev_put(ndev, &priv->dev_tracker); kfree(priv); } @@ -281,7 +281,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) */ kref_get(&priv_new->rx_kref); mutex_unlock(&j1939_netdev_lock); - dev_put(ndev); + netdev_put(ndev, &priv->dev_tracker); kfree(priv); return priv_new; } @@ -298,7 +298,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) j1939_priv_set(ndev, NULL); mutex_unlock(&j1939_netdev_lock); - dev_put(ndev); + netdev_put(ndev, &priv->dev_tracker); kfree(priv); return ERR_PTR(ret); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index e3ba2e9fc0e9..e56d8134938e 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -897,7 +897,6 @@ static struct sk_buff *j1939_sk_alloc_skb(struct net_device *ndev, can_skb_reserve(skb); can_skb_prv(skb)->ifindex = ndev->ifindex; - can_skb_prv(skb)->skbcnt = 0; skb_reserve(skb, offsetof(struct can_frame, data)); ret = memcpy_from_msg(skb_put(skb, size), msg, size); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 9ec929bc0c0d..9d9c342d26d5 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -282,6 +282,7 @@ static void j1939_session_destroy(struct j1939_session *session) kfree_skb(skb); } __j1939_session_drop(session); + netdev_put(session->priv->ndev, &session->priv_dev_tracker); j1939_priv_put(session->priv); kfree(session); } @@ -612,7 +613,6 @@ sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv, skb->dev = priv->ndev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = priv->ndev->ifindex; - can_skb_prv(skb)->skbcnt = 0; /* reserve CAN header */ skb_reserve(skb, offsetof(struct can_frame, data)); @@ -1510,6 +1510,7 @@ static struct j1939_session *j1939_session_new(struct j1939_priv *priv, INIT_LIST_HEAD(&session->active_session_list_entry); INIT_LIST_HEAD(&session->sk_session_queue_entry); kref_init(&session->kref); + netdev_hold(priv->ndev, &session->priv_dev_tracker, gfp_any()); j1939_priv_get(priv); session->priv = priv; @@ -1547,7 +1548,6 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv, skb->dev = priv->ndev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = priv->ndev->ifindex; - can_skb_prv(skb)->skbcnt = 0; skcb = j1939_skb_to_cb(skb); memcpy(skcb, rel_skcb, sizeof(*skcb)); @@ -1558,7 +1558,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv, } /* alloc data area */ - skb_put(skb, size); + skb_put_zero(skb, size); /* skb is recounted in j1939_session_new() */ return session; } diff --git a/net/can/raw.c b/net/can/raw.c index 365559d19dc3..c397071bfa8b 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -76,7 +76,7 @@ MODULE_ALIAS("can-proto-1"); struct uniqframe { const struct sk_buff *skb; - int skbcnt; + u32 hash; unsigned int join_rx_count; }; @@ -164,7 +164,7 @@ static void raw_rcv(struct sk_buff *oskb, void *data) /* eliminate multiple filter matches for the same skb */ if (this_cpu_ptr(ro->uniq)->skb == oskb && - this_cpu_ptr(ro->uniq)->skbcnt == can_skb_prv(oskb)->skbcnt) { + this_cpu_ptr(ro->uniq)->hash == oskb->hash) { if (!ro->join_filters) return; @@ -174,7 +174,7 @@ static void raw_rcv(struct sk_buff *oskb, void *data) return; } else { this_cpu_ptr(ro->uniq)->skb = oskb; - this_cpu_ptr(ro->uniq)->skbcnt = can_skb_prv(oskb)->skbcnt; + this_cpu_ptr(ro->uniq)->hash = oskb->hash; this_cpu_ptr(ro->uniq)->join_rx_count = 1; /* drop first frame to check all enabled filters? */ if (ro->join_filters && ro->count > 1) @@ -954,7 +954,6 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; /* fill the skb before testing for valid CAN frames */ err = memcpy_from_msg(skb_put(skb, size), msg, size); diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 2efcda93d139..5fffdd4e71ad 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -251,8 +251,10 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb) * if there is enough header space in skb. */ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); - if (unlikely(err)) + if (unlikely(err)) { + dst_release(dst); goto err; + } skb_dst_drop(skb); skb_dst_set(skb, dst); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index d41b03fd1f63..a180c061a02d 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3971,6 +3971,7 @@ static void _rem_dev_from_if_list(struct pktgen_thread *t, struct pktgen_dev *p; if_lock(t); + proc_remove(pkt_dev->entry); list_for_each_safe(q, n, &t->if_list) { p = list_entry(q, struct pktgen_dev, list); if (p == pkt_dev) @@ -4000,9 +4001,6 @@ static int pktgen_remove_device(struct pktgen_thread *t, * list to determine if interface already exist, avoid race * with proc_create_data() */ - proc_remove(pkt_dev->entry); - - /* And update the thread if_list */ _rem_dev_from_if_list(t, pkt_dev); #ifdef CONFIG_XFRM diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 43dca2c04576..e75baa72a22e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -895,6 +895,18 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } +/** + * skb_pp_cow_data() - copy skb data into page-pool backed storage + * @pool: page pool to allocate from + * @pskb: pointer to skb pointer, replaced with the copied skb on success + * @headroom: headroom to reserve in the copied skb + * + * skb_copy_bits() handles both frags[] and frag_list input. If the copied + * skb remains non-linear, it uses frags[], which is the representation used + * by XDP multi-buffer. + * + * Return: 0 on success or a negative errno on failure. + */ int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom) { @@ -904,12 +916,6 @@ int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, int err, i, head_off; void *data; - /* XDP does not support fraglist so we need to linearize - * the skb. - */ - if (skb_has_frag_list(skb)) - return -EOPNOTSUPP; - max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom); if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE) return -ENOMEM; diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c index df3948e807a0..9cc7a95f4120 100644 --- a/net/handshake/handshake-test.c +++ b/net/handshake/handshake-test.c @@ -375,6 +375,10 @@ static void handshake_req_cancel_test2(struct kunit *test) /* Pretend to accept this request */ next = handshake_req_next(hn, HANDSHAKE_HANDLER_CLASS_TLSHD); KUNIT_ASSERT_PTR_EQ(test, req, next); + /* Simulate FD_PREPARE() consuming the file reference handed + * off by handshake_req_next(); see handshake_nl_accept_doit(). + */ + fput(filp); /* Act */ result = handshake_req_cancel(sock->sk); @@ -417,6 +421,10 @@ static void handshake_req_cancel_test3(struct kunit *test) /* Pretend to accept this request */ next = handshake_req_next(hn, HANDSHAKE_HANDLER_CLASS_TLSHD); KUNIT_ASSERT_PTR_EQ(test, req, next); + /* Simulate FD_PREPARE() consuming the file reference handed + * off by handshake_req_next(); see handshake_nl_accept_doit(). + */ + fput(filp); /* Pretend to complete this request */ handshake_complete(next, -ETIMEDOUT, NULL); diff --git a/net/handshake/handshake.h b/net/handshake/handshake.h index 2289b0e274f4..da61cadd1ad3 100644 --- a/net/handshake/handshake.h +++ b/net/handshake/handshake.h @@ -24,6 +24,7 @@ enum hn_flags_bits { HANDSHAKE_F_NET_DRAINING, }; +struct file; struct handshake_proto; /* One handshake request */ @@ -32,6 +33,7 @@ struct handshake_req { struct rhash_head hr_rhash; unsigned long hr_flags; const struct handshake_proto *hr_proto; + struct file *hr_file; struct sock *hr_sk; void (*hr_odestruct)(struct sock *sk); diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c index d8211e0ba75c..3fd4fef9bab1 100644 --- a/net/handshake/netlink.c +++ b/net/handshake/netlink.c @@ -92,8 +92,7 @@ int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) struct net *net = sock_net(skb->sk); struct handshake_net *hn = handshake_pernet(net); struct handshake_req *req = NULL; - struct socket *sock; - int class, fd, err; + int class, err; err = -EOPNOTSUPP; if (!hn) @@ -106,29 +105,26 @@ int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) err = -EAGAIN; req = handshake_req_next(hn, class); - if (!req) - goto out_status; - - sock = req->hr_sk->sk_socket; - fd = get_unused_fd_flags(O_CLOEXEC); - if (fd < 0) { - err = fd; - goto out_complete; - } - - err = req->hr_proto->hp_accept(req, info, fd); - if (err) { - put_unused_fd(fd); - goto out_complete; + if (req) { + FD_PREPARE(fdf, O_CLOEXEC, req->hr_file); + if (fdf.err) { + fput(req->hr_file); /* drop ref from handshake_req_next() */ + err = fdf.err; + goto out_complete; + } + + err = req->hr_proto->hp_accept(req, info, fd_prepare_fd(fdf)); + if (err) + goto out_complete; /* Automatic cleanup handles fput */ + + trace_handshake_cmd_accept(net, req, req->hr_sk, fd_prepare_fd(fdf)); + fd_publish(fdf); + return 0; } - fd_install(fd, get_file(sock->file)); - - trace_handshake_cmd_accept(net, req, req->hr_sk, fd); - return 0; - out_complete: - handshake_complete(req, -EIO, NULL); + if (req) + handshake_complete(req, -EIO, NULL); out_status: trace_handshake_cmd_accept_err(net, req, NULL, err); return err; @@ -205,19 +201,19 @@ static void __net_exit handshake_net_exit(struct net *net) */ spin_lock_bh(&hn->hn_lock); set_bit(HANDSHAKE_F_NET_DRAINING, &hn->hn_flags); - list_splice_init(&requests, &hn->hn_requests); + list_splice_init(&hn->hn_requests, &requests); + list_for_each_entry(req, &requests, hr_list) + get_file(req->hr_file); spin_unlock_bh(&hn->hn_lock); while (!list_empty(&requests)) { - req = list_first_entry(&requests, struct handshake_req, hr_list); - list_del(&req->hr_list); - - /* - * Requests on this list have not yet been - * accepted, so they do not have an fd to put. - */ + struct file *file; + req = list_first_entry(&requests, struct handshake_req, hr_list); + file = req->hr_file; + list_del_init(&req->hr_list); handshake_complete(req, -ETIMEDOUT, NULL); + fput(file); } } diff --git a/net/handshake/request.c b/net/handshake/request.c index 62efb7e32730..d4a3a50f8a3b 100644 --- a/net/handshake/request.c +++ b/net/handshake/request.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/inet.h> +#include <linux/file.h> #include <linux/rhashtable.h> #include <net/sock.h> @@ -162,13 +163,16 @@ static void __remove_pending_locked(struct handshake_net *hn, * otherwise %false. * * If @req was on a pending list, it has not yet been accepted. + * Returns %false when the net namespace is draining; the drain + * loop has taken ownership of the pending list. */ static bool remove_pending(struct handshake_net *hn, struct handshake_req *req) { bool ret = false; spin_lock_bh(&hn->hn_lock); - if (!list_empty(&req->hr_list)) { + if (!test_bit(HANDSHAKE_F_NET_DRAINING, &hn->hn_flags) && + !list_empty(&req->hr_list)) { __remove_pending_locked(hn, req); ret = true; } @@ -177,6 +181,17 @@ static bool remove_pending(struct handshake_net *hn, struct handshake_req *req) return ret; } +/** + * handshake_req_next - Return the next queued handshake request + * @hn: per-net handshake state + * @class: handler class to match + * + * On a non-NULL return, the caller owns an extra reference + * on @req->hr_file. FD_PREPARE() consumes it on success; on + * the FD_PREPARE() failure path the caller must fput() it. + * + * Return: pointer to a removed handshake_req, or NULL. + */ struct handshake_req *handshake_req_next(struct handshake_net *hn, int class) { struct handshake_req *req, *pos; @@ -187,6 +202,13 @@ struct handshake_req *handshake_req_next(struct handshake_net *hn, int class) if (pos->hr_proto->hp_handler_class != class) continue; __remove_pending_locked(hn, pos); + /* Hand off a file reference to the accept side under + * hn_lock. A concurrent handshake_req_cancel() can drop + * hr_file before accept reaches FD_PREPARE(); this extra + * reference keeps the file alive until FD_PREPARE() takes + * ownership. + */ + get_file(pos->hr_file); req = pos; break; } @@ -215,9 +237,16 @@ EXPORT_SYMBOL_IF_KUNIT(handshake_req_next); * A zero return value from handshake_req_submit() means that * exactly one subsequent completion callback is guaranteed. * - * A negative return value from handshake_req_submit() means that - * no completion callback will be done and that @req has been - * destroyed. + * A negative return value from handshake_req_submit() guarantees that + * no completion callback will occur and that @req is no longer owned by + * the caller. If cancellation wins the completion race after the request + * has been published, final destruction is deferred until socket teardown. + * + * The caller must hold a reference on @sock->file for the duration + * of this call. Once the request is published to the accept side, a + * concurrent completion or cancellation may release the request's pin on + * @sock->file; the caller's reference is what keeps @sock->sk valid until + * handshake_req_submit() returns. */ int handshake_req_submit(struct socket *sock, struct handshake_req *req, gfp_t flags) @@ -236,6 +265,14 @@ int handshake_req_submit(struct socket *sock, struct handshake_req *req, kfree(req); return -EINVAL; } + + /* + * Pin sock->file for the lifetime of the request so the + * accept side does not race a consumer that releases the + * socket while a handshake is pending. + */ + req->hr_file = get_file(sock->file); + req->hr_odestruct = req->hr_sk->sk_destruct; req->hr_sk->sk_destruct = handshake_sk_destruct; @@ -267,19 +304,19 @@ int handshake_req_submit(struct socket *sock, struct handshake_req *req, goto out_err; } - /* Prevent socket release while a handshake request is pending */ - sock_hold(req->hr_sk); - trace_handshake_submit(net, req, req->hr_sk); return 0; out_unlock: spin_unlock_bh(&hn->hn_lock); out_err: - /* Restore original destructor so socket teardown still runs on failure */ - req->hr_sk->sk_destruct = req->hr_odestruct; trace_handshake_submit_err(net, req, req->hr_sk, ret); - handshake_req_destroy(req); + if (!test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { + /* Restore original destructor so socket teardown still runs. */ + req->hr_sk->sk_destruct = req->hr_odestruct; + fput(req->hr_file); + handshake_req_destroy(req); + } return ret; } EXPORT_SYMBOL(handshake_req_submit); @@ -291,11 +328,12 @@ void handshake_complete(struct handshake_req *req, int status, struct net *net = sock_net(sk); if (!test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { + struct file *file = req->hr_file; + trace_handshake_complete(net, req, sk, status); req->hr_proto->hp_done(req, status, info); - /* Handshake request is no longer pending */ - sock_put(sk); + fput(file); } } EXPORT_SYMBOL_IF_KUNIT(handshake_complete); @@ -342,8 +380,7 @@ bool handshake_req_cancel(struct sock *sk) out_true: trace_handshake_cancel(net, req, sk); - /* Handshake request is no longer pending */ - sock_put(sk); + fput(req->hr_file); return true; } EXPORT_SYMBOL(handshake_req_cancel); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 11d990703d31..778467bea476 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -892,8 +892,6 @@ void ip_rt_send_redirect(struct sk_buff *skb) peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif); if (!peer) { rcu_read_unlock(); - icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, - rt_nexthop(rt, ip_hdr(skb)->daddr)); return; } diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index b13e8f7092f4..4360d159ee8a 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -32,13 +32,12 @@ struct udp_tunnel_nic_table_entry { * @lock: protects all fields * @need_sync: at least one port start changed * @need_replay: space was freed, we need a replay of all ports - * @work_pending: @work is currently scheduled * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded */ struct udp_tunnel_nic { - struct work_struct work; + struct delayed_work work; struct net_device *dev; @@ -46,7 +45,6 @@ struct udp_tunnel_nic { u8 need_sync:1; u8 need_replay:1; - u8 work_pending:1; unsigned int n_tables; unsigned long missed; @@ -301,11 +299,10 @@ __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) static void udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { - if (!utn->need_sync || utn->work_pending) + if (!utn->need_sync) return; - queue_work(udp_tunnel_nic_workqueue, &utn->work); - utn->work_pending = 1; + queue_delayed_work(udp_tunnel_nic_workqueue, &utn->work, 0); } static bool @@ -731,12 +728,17 @@ udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) static void udp_tunnel_nic_device_sync_work(struct work_struct *work) { struct udp_tunnel_nic *utn = - container_of(work, struct udp_tunnel_nic, work); + container_of(work, struct udp_tunnel_nic, work.work); - rtnl_lock(); + /* We cannot block on RTNL here, otherwise we would deadlock with + * udp_tunnel_nic_unregister() calling cancel_delayed_work_sync() + * while holding RTNL. Requeue with 1 jiffy delay if RTNL is contended. + */ + if (!rtnl_trylock()) { + queue_delayed_work(udp_tunnel_nic_workqueue, &utn->work, 1); + return; + } mutex_lock(&utn->lock); - - utn->work_pending = 0; __udp_tunnel_nic_device_sync(utn->dev, utn); if (utn->need_replay) @@ -757,7 +759,7 @@ udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, if (!utn) return NULL; utn->n_tables = n_tables; - INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work); + INIT_DELAYED_WORK(&utn->work, udp_tunnel_nic_device_sync_work); mutex_init(&utn->lock); for (i = 0; i < n_tables; i++) { @@ -901,11 +903,11 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) udp_tunnel_nic_flush(dev, utn); udp_tunnel_nic_unlock(dev); - /* Wait for the work to be done using the state, netdev core will - * retry unregister until we give up our reference on this device. + /* Make sure no work is running or queued before freeing @utn. + * The work handler uses rtnl_trylock(), so it will not deadlock + * against the RTNL we are holding here. */ - if (utn->work_pending) - return; + cancel_delayed_work_sync(&utn->work); udp_tunnel_nic_free(utn); release_dev: diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index fd5f7112a51f..3024e77b3847 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -305,6 +305,7 @@ INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule, suppress_route: ip6_rt_put_flags(rt, flags); + res->rt6 = NULL; return true; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 8f37c9cc868b..9ef6581168f0 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -630,7 +630,7 @@ int ip6_forward(struct sk_buff *skb) /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ - if (inet_peer_xrlim_allow(peer, 1*HZ)) + if (peer && inet_peer_xrlim_allow(peer, 1*HZ)) ndisc_send_redirect(skb, target); rcu_read_unlock(); } else { diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 9df1fba967c6..7262356de10d 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1706,6 +1706,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) } peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr); + if (!peer) + goto release; ret = inet_peer_xrlim_allow(peer, 1*HZ); if (!ret) diff --git a/net/mac80211/s1g.c b/net/mac80211/s1g.c index 1f68df6e8067..7702cff84d54 100644 --- a/net/mac80211/s1g.c +++ b/net/mac80211/s1g.c @@ -101,6 +101,10 @@ ieee80211_s1g_rx_twt_setup(struct ieee80211_sub_if_data *sdata, struct ieee80211_twt_setup *twt = (void *)mgmt->u.action.u.s1g.variable; struct ieee80211_twt_params *twt_agrt = (void *)twt->params; + if (!(twt->control & IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST) && + twt->length < sizeof(twt->control) + sizeof(*twt_agrt)) + return; + twt_agrt->req_type &= cpu_to_le16(~IEEE80211_TWT_REQTYPE_REQUEST); /* broadcast TWT not supported yet */ diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index f7f60025d042..f9b8c4d0f049 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -2468,6 +2468,7 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, r->rtm_family = AF_MPLS; r->rtm_dst_len = 20; r->rtm_src_len = 0; + r->rtm_tos = 0; r->rtm_table = RT_TABLE_MAIN; r->rtm_type = RTN_UNICAST; r->rtm_scope = RT_SCOPE_UNIVERSE; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 0426d012185d..4c1082e38e3d 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -984,7 +984,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, #endif if (SET_WITH_COUNTER(set)) ip_set_init_counter(ext_counter(data, set), ext); - if (SET_WITH_COMMENT(set)) + if (SET_WITH_COMMENT(set) && !ext->target) ip_set_init_comment(set, ext_comment(data, set), ext); if (SET_WITH_SKBINFO(set)) ip_set_init_skbinfo(ext_skbinfo(data, set), ext); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index f9132b359f0c..0c690a30a85d 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -368,7 +368,7 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th))) return 0; - th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len); + th = (struct tcphdr *)(skb->data + ipvsh->len); /* * Remember seq number in case this pkt gets resized @@ -444,7 +444,7 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th))) return 0; - th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len); + th = (struct tcphdr *)(skb->data + ipvsh->len); /* * Remember seq number in case this pkt gets resized diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index bc8ff5f15702..83b28fe9ea8f 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -599,6 +599,9 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) flags = cp->flags; /* Bind with the destination and its corresponding transmitter */ if (flags & IP_VS_CONN_F_SYNC) { + /* Synced conns are hashed, so they can not get this flag */ + conn_flags &= ~IP_VS_CONN_F_ONE_PACKET; + /* if the connection is not template and is created * by sync, preserve the activity flag. */ diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 90619453cb6f..6207a91e93f3 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -689,7 +689,7 @@ static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; } #endif -__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) +static __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); } @@ -746,13 +746,13 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, * - inout: 1=in->out, 0=out->in */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int inout) + struct ip_vs_conn *cp, int inout, unsigned int toff, + bool has_ports) { struct iphdr *iph = ip_hdr(skb); - unsigned int icmp_offset = iph->ihl*4; - struct icmphdr *icmph = (struct icmphdr *)(skb_network_header(skb) + - icmp_offset); + struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff); struct iphdr *ciph = (struct iphdr *)(icmph + 1); + unsigned int coff __maybe_unused = toff + sizeof(struct icmphdr); if (inout) { iph->saddr = cp->vaddr.ip; @@ -767,8 +767,7 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, } /* the TCP/UDP/SCTP port */ - if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol || - IPPROTO_SCTP == ciph->protocol) { + if (has_ports) { __be16 *ports = (void *)ciph + ciph->ihl*4; if (inout) @@ -779,48 +778,40 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, /* And finally the ICMP checksum */ icmph->checksum = 0; - icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset); + icmph->checksum = ip_vs_checksum_complete(skb, toff); skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) - IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, - "Forwarding altered outgoing ICMP"); + IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + "Forwarding altered outgoing ICMP"); else - IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, - "Forwarding altered incoming ICMP"); + IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + "Forwarding altered incoming ICMP"); } #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int inout) + struct ip_vs_conn *cp, int inout, unsigned int toff, + bool has_ports, struct ip_vs_iphdr *ciph) { struct ipv6hdr *iph = ipv6_hdr(skb); - unsigned int icmp_offset = 0; - unsigned int offs = 0; /* header offset*/ - int protocol; struct icmp6hdr *icmph; - struct ipv6hdr *ciph; - unsigned short fragoffs; + struct ipv6hdr *cih; - ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL); - icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset); - offs = icmp_offset + sizeof(struct icmp6hdr); - ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs); - - protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL); + icmph = (struct icmp6hdr *)(skb->data + toff); + cih = (struct ipv6hdr *)(skb->data + ciph->off); if (inout) { iph->saddr = cp->vaddr.in6; - ciph->daddr = cp->vaddr.in6; + cih->daddr = cp->vaddr.in6; } else { iph->daddr = cp->daddr.in6; - ciph->saddr = cp->daddr.in6; + cih->saddr = cp->daddr.in6; } /* the TCP/UDP/SCTP port */ - if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || - IPPROTO_SCTP == protocol)) { - __be16 *ports = (void *)(skb_network_header(skb) + offs); + if (has_ports) { + __be16 *ports = (void *)(skb->data + ciph->len); IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__, ntohs(inout ? ports[1] : ports[0]), @@ -833,19 +824,17 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, /* And finally the ICMP checksum */ icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb->len - icmp_offset, + skb->len - toff, IPPROTO_ICMPV6, 0); - skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset; + skb->csum_start = skb_headroom(skb) + toff; skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum); skb->ip_summed = CHECKSUM_PARTIAL; if (inout) - IP_VS_DBG_PKT(11, AF_INET6, pp, skb, - (void *)ciph - (void *)iph, + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, ciph->off, "Forwarding altered outgoing ICMPv6"); else - IP_VS_DBG_PKT(11, AF_INET6, pp, skb, - (void *)ciph - (void *)iph, + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, ciph->off, "Forwarding altered incoming ICMPv6"); } #endif @@ -855,36 +844,41 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, */ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, - __u8 protocol, struct ip_vs_conn *cp, + struct ip_vs_conn *cp, struct ip_vs_protocol *pp, - unsigned int offset, unsigned int ihl, - unsigned int hooknum) + struct ip_vs_iphdr *ciph, + unsigned int toff, unsigned int hooknum) { + int iproto = af == AF_INET6 ? IPPROTO_ICMPV6 : IPPROTO_ICMP; unsigned int verdict = NF_DROP; + unsigned int ctoff = ciph->len; + bool has_ports = false; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; /* Ensure the checksum is correct */ - if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { + if (!ip_vs_checksum_common_check(skb, toff, iproto, af)) { /* Failed checksum! */ IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n", IP_VS_DBG_ADDR(af, snet)); goto out; } - if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || - IPPROTO_SCTP == protocol) - offset += 2 * sizeof(__u16); - if (skb_ensure_writable(skb, offset)) + if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP || + ciph->protocol == IPPROTO_SCTP) { + ctoff += 2 * sizeof(__u16); + has_ports = true; + } + if (skb_ensure_writable(skb, ctoff)) goto out; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) - ip_vs_nat_icmp_v6(skb, pp, cp, 1); + ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph); else #endif - ip_vs_nat_icmp(skb, pp, cp, 1); + ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; @@ -912,9 +906,9 @@ static int handle_response_icmp(int af, struct sk_buff *skb, * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, - int *related, unsigned int hooknum) + int *related, unsigned int hooknum, + struct ip_vs_iphdr *ipvsh) { - struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; @@ -929,17 +923,19 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; + if (!ip_vs_fill_iph_skb(AF_INET, skb, false, ipvsh)) + return NF_ACCEPT; } - iph = ip_hdr(skb); - offset = ihl = iph->ihl * 4; + ihl = ipvsh->len; + offset = ipvsh->len; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), - &iph->saddr, &iph->daddr); + &ipvsh->saddr.ip, &ipvsh->daddr.ip); /* * Work through seeing if this is for us. @@ -958,7 +954,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + if (!(cih && cih->version == 4 && cih->ihl >= 5)) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(cih->protocol); @@ -966,8 +962,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; /* Is the embedded protocol header present? */ - if (unlikely(cih->frag_off & htons(IP_OFFSET) && - pp->dont_defrag)) + if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, @@ -981,9 +976,9 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, if (!cp) return NF_ACCEPT; - snet.ip = iph->saddr; - return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, - pp, ciph.len, ihl, hooknum); + snet.ip = ipvsh->saddr.ip; + return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, ihl, + hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -996,7 +991,6 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, struct ip_vs_conn *cp; struct ip_vs_protocol *pp; union nf_inet_addr snet; - unsigned int offset; *related = 1; ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph); @@ -1032,6 +1026,10 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, if (!pp) return NF_ACCEPT; + /* Is the embedded protocol header present? */ + if (unlikely(ciph.fragoffs && !pp->dont_defrag)) + return NF_ACCEPT; + /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET6, skb, &ciph); @@ -1039,9 +1037,8 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; snet.in6 = ciph.saddr.in6; - offset = ciph.len; - return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, offset, ipvsh->len, hooknum); + return handle_response_icmp(AF_INET6, skb, &snet, cp, pp, &ciph, + ipvsh->len, hooknum); } #endif @@ -1367,7 +1364,8 @@ ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; - int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum); + int verdict = ip_vs_out_icmp(ipvs, skb, &related, + hooknum, &iph); if (related) return verdict; @@ -1575,9 +1573,8 @@ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, */ static int ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, - unsigned int hooknum) + unsigned int hooknum, struct ip_vs_iphdr *iph) { - struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; @@ -1587,7 +1584,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int offset, offset2, ihl, verdict; bool tunnel, new_cp = false; union nf_inet_addr *raddr; - char *outer_proto = "IPIP"; + char *outer_proto __maybe_unused = "IPIP"; unsigned int hlen_ipip; int ulen = 0; @@ -1597,17 +1594,19 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; + if (!ip_vs_fill_iph_skb(AF_INET, skb, false, iph)) + return NF_ACCEPT; } - iph = ip_hdr(skb); - offset = ihl = iph->ihl * 4; + ihl = iph->len; + offset = iph->len; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), - &iph->saddr, &iph->daddr); + &iph->saddr.ip, &iph->daddr.ip); /* * Work through seeing if this is for us. @@ -1689,8 +1688,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, pp = pd->pp; /* Is the embedded protocol header present? */ - if (unlikely(cih->frag_off & htons(IP_OFFSET) && - pp->dont_defrag)) + if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, @@ -1698,7 +1696,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, offset2 = offset; ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); - offset = ciph.len; /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. @@ -1720,10 +1717,11 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, verdict = NF_DROP; /* Ensure the checksum is correct */ - if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { + if ((IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ || tunnel) && + !ip_vs_checksum_common_check(skb, ihl, IPPROTO_ICMP, AF_INET)) { /* Failed checksum! */ IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n", - &iph->saddr); + &iph->saddr.ip); goto out; } @@ -1791,10 +1789,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); - if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol || - IPPROTO_SCTP == cih->protocol) - offset += 2 * sizeof(__u16); - verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); + verdict = ip_vs_icmp_xmit(skb, cp, pp, iph->len, hooknum, &ciph); out: if (likely(!new_cp)) @@ -1854,8 +1849,8 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; pp = pd->pp; - /* Cannot handle fragmented embedded protocol */ - if (ciph.fragoffs) + /* Is the embedded protocol header present? */ + if (ciph.fragoffs && !pp->dont_defrag) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, @@ -1879,23 +1874,22 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, new_cp = true; } - /* VS/TUN, VS/DR and LOCALNODE just let it go */ - if ((hooknum == NF_INET_LOCAL_OUT) && - (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) { - verdict = NF_ACCEPT; + verdict = NF_DROP; + + /* Ensure the checksum is correct */ + if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ && + !ip_vs_checksum_common_check(skb, iph->len, IPPROTO_ICMPV6, + AF_INET6)) { + /* Failed checksum! */ + IP_VS_DBG(1, "Incoming ICMPv6: failed checksum from %pI6c!\n", + &iph->saddr); goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); - /* Need to mangle contained IPv6 header in ICMPv6 packet */ - offset = ciph.len; - if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || - IPPROTO_SCTP == ciph.protocol) - offset += 2 * sizeof(__u16); /* Also mangle ports */ - - verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph); + verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, iph->len, hooknum, &ciph); out: if (likely(!new_cp)) @@ -1974,7 +1968,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_in_icmp(ipvs, skb, &related, - hooknum); + hooknum, &iph); if (related) return verdict; @@ -2110,6 +2104,7 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct netns_ipvs *ipvs = net_ipvs(state->net); + struct ip_vs_iphdr iphdr; int r; /* ipvs enabled in this netns ? */ @@ -2119,10 +2114,9 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb, if (state->pf == NFPROTO_IPV4) { if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; + ip_vs_fill_iph_skb(AF_INET, skb, false, &iphdr); #ifdef CONFIG_IP_VS_IPV6 } else { - struct ip_vs_iphdr iphdr; - ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); if (iphdr.protocol != IPPROTO_ICMPV6) @@ -2132,7 +2126,7 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb, #endif } - return ip_vs_in_icmp(ipvs, skb, &r, state->hook); + return ip_vs_in_icmp(ipvs, skb, &r, state->hook, &iphdr); } static const struct nf_hook_ops ip_vs_ops4[] = { diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index c67317be17df..3dbd3096e163 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -11,7 +11,7 @@ static int sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int sctphoff); + struct ip_vs_iphdr *iph); static int sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -109,7 +109,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!sctp_csum_check(cp->af, skb, pp, sctphoff)) + if (!sctp_csum_check(cp->af, skb, pp, iph)) return 0; /* Call application helper if needed */ @@ -121,7 +121,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - sctph = (void *) skb_network_header(skb) + sctphoff; + sctph = (void *)skb->data + sctphoff; /* Only update csum if we really have to */ if (sctph->source != cp->vport || payload_csum || @@ -157,7 +157,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!sctp_csum_check(cp->af, skb, pp, sctphoff)) + if (!sctp_csum_check(cp->af, skb, pp, iph)) return 0; /* Call application helper if needed */ @@ -169,7 +169,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - sctph = (void *) skb_network_header(skb) + sctphoff; + sctph = (void *)skb->data + sctphoff; /* Only update csum if we really have to */ if (sctph->dest != cp->dport || payload_csum || @@ -187,19 +187,22 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int sctphoff) + struct ip_vs_iphdr *iph) { + unsigned int sctphoff = iph->len; struct sctphdr *sh; __le32 cmp, val; + if (!ip_vs_checksum_needed(skb, af)) + return 1; sh = (struct sctphdr *)(skb->data + sctphoff); cmp = sh->checksum; val = sctp_compute_cksum(skb, sctphoff); if (val != cmp) { /* CRC failure, dump it. */ - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); + IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off, + "Failed checksum for"); return 0; } return 1; diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index b382810156b2..1ac9c233537d 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -30,7 +30,7 @@ static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int tcphoff); + struct ip_vs_iphdr *iph); static int tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -167,7 +167,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!tcp_csum_check(cp->af, skb, pp, tcphoff)) + if (!tcp_csum_check(cp->af, skb, pp, iph)) return 0; /* Call application helper if needed */ @@ -180,7 +180,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - tcph = (void *)skb_network_header(skb) + tcphoff; + tcph = (void *)skb->data + tcphoff; tcph->source = cp->vport; /* Adjust TCP checksums */ @@ -245,7 +245,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!tcp_csum_check(cp->af, skb, pp, tcphoff)) + if (!tcp_csum_check(cp->af, skb, pp, iph)) return 0; /* @@ -261,7 +261,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - tcph = (void *)skb_network_header(skb) + tcphoff; + tcph = (void *)skb->data + tcphoff; tcph->dest = cp->dport; /* @@ -303,41 +303,13 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int tcphoff) + struct ip_vs_iphdr *iph) { - switch (skb->ip_summed) { - case CHECKSUM_NONE: - skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); - fallthrough; - case CHECKSUM_COMPLETE: -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - tcphoff, - IPPROTO_TCP, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - } else -#endif - if (csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - tcphoff, - ip_hdr(skb)->protocol, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - break; - default: - /* No need to checksum. */ - break; + if (!ip_vs_checksum_common_check(skb, iph->len, IPPROTO_TCP, af)) { + IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off, + "Failed checksum for"); + return 0; } - return 1; } diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index dbd4155bb075..96ac882df15c 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -26,7 +26,7 @@ static int udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int udphoff); + struct ip_vs_iphdr *iph); static int udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -156,7 +156,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!udp_csum_check(cp->af, skb, pp, udphoff)) + if (!udp_csum_check(cp->af, skb, pp, iph)) return 0; /* @@ -171,7 +171,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - udph = (void *)skb_network_header(skb) + udphoff; + udph = (void *)skb->data + udphoff; udph->source = cp->vport; /* @@ -239,7 +239,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!udp_csum_check(cp->af, skb, pp, udphoff)) + if (!udp_csum_check(cp->af, skb, pp, iph)) return 0; /* @@ -255,7 +255,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - udph = (void *)skb_network_header(skb) + udphoff; + udph = (void *)skb->data + udphoff; udph->dest = cp->dport; /* @@ -299,48 +299,20 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int udphoff) + struct ip_vs_iphdr *iph) { struct udphdr _udph, *uh; - uh = skb_header_pointer(skb, udphoff, sizeof(_udph), &_udph); + uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); if (uh == NULL) return 0; - if (uh->check != 0) { - switch (skb->ip_summed) { - case CHECKSUM_NONE: - skb->csum = skb_checksum(skb, udphoff, - skb->len - udphoff, 0); - fallthrough; - case CHECKSUM_COMPLETE: -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - udphoff, - IPPROTO_UDP, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - } else -#endif - if (csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - udphoff, - ip_hdr(skb)->protocol, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - break; - default: - /* No need to checksum. */ - break; - } + if (!uh->check) + return 1; + if (!ip_vs_checksum_common_check(skb, iph->len, IPPROTO_UDP, af)) { + IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off, + "Failed checksum for"); + return 0; } return 1; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index f564b4197cee..ac1827ef7894 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1499,20 +1499,22 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, */ int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, unsigned int hooknum, - struct ip_vs_iphdr *iph) + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int hooknum, struct ip_vs_iphdr *ciph) { struct rtable *rt; /* Route to the other host */ int rc; int local; int rt_mode, was_input; + bool has_ports = false; + unsigned int wlen; /* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be forwarded directly here, because there is no need to translate address/port back */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { if (cp->packet_xmit) - rc = cp->packet_xmit(skb, cp, pp, iph); + rc = cp->packet_xmit(skb, cp, pp, ciph); else rc = NF_ACCEPT; /* do not touch skb anymore */ @@ -1530,7 +1532,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip, rt_mode, - NULL, iph); + NULL, ciph); if (local < 0) goto tx_error; rt = skb_rtable(skb); @@ -1561,14 +1563,21 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } + wlen = ciph->len; + if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP || + ciph->protocol == IPPROTO_SCTP) { + wlen += 2 * sizeof(__u16); /* Also mangle ports */ + has_ports = true; + } + /* copy-on-write the packet before mangling it */ - if (skb_ensure_writable(skb, offset)) + if (skb_ensure_writable(skb, wlen)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp(skb, pp, cp, 0); + ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; @@ -1584,10 +1593,12 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #ifdef CONFIG_IP_VS_IPV6 int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, unsigned int hooknum, - struct ip_vs_iphdr *ipvsh) + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int hooknum, struct ip_vs_iphdr *ciph) { + bool has_ports = false; struct rt6_info *rt; /* Route to the other host */ + unsigned int wlen; int rc; int local; int rt_mode; @@ -1597,7 +1608,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, translate address/port back */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { if (cp->packet_xmit) - rc = cp->packet_xmit(skb, cp, pp, ipvsh); + rc = cp->packet_xmit(skb, cp, pp, ciph); else rc = NF_ACCEPT; /* do not touch skb anymore */ @@ -1614,7 +1625,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest, - &cp->daddr.in6, NULL, ipvsh, 0, rt_mode); + &cp->daddr.in6, NULL, ciph, 0, rt_mode); if (local < 0) goto tx_error; rt = dst_rt6_info(skb_dst(skb)); @@ -1645,14 +1656,21 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } + wlen = ciph->len; + if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP || + ciph->protocol == IPPROTO_SCTP) { + wlen += 2 * sizeof(__u16); /* Also mangle ports */ + has_ports = true; + } + /* copy-on-write the packet before mangling it */ - if (skb_ensure_writable(skb, offset)) + if (skb_ensure_writable(skb, wlen)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp_v6(skb, pp, cp, 0); + ip_vs_nat_icmp_v6(skb, pp, cp, 0, toff, has_ports, ciph); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index 4f39bf7c843f..75e53fde6b29 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -72,6 +72,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, exp->flags = NF_CT_EXPECT_PERMANENT; exp->class = NF_CT_EXPECT_CLASS_DEFAULT; rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, NULL); write_pnet(&exp->net, net); #ifdef CONFIG_NF_CONNTRACK_ZONES exp->zone = ct->zone; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index a877f9ad1cf2..44fa3224cc87 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1771,14 +1771,17 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, spin_lock_bh(&nf_conntrack_expect_lock); exp = nf_ct_find_expectation(net, zone, tuple, !tmpl || nf_ct_is_confirmed(tmpl)); if (exp) { + struct nf_conntrack_helper *assign_helper; + /* Welcome, Mr. Bond. We've been expecting you... */ __set_bit(IPS_EXPECTED_BIT, &ct->status); /* exp->master safe, refcnt bumped in nf_ct_find_expectation */ ct->master = exp->master; - if (exp->helper) { + assign_helper = rcu_dereference(exp->assign_helper); + if (assign_helper) { help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help) - rcu_assign_pointer(help->helper, exp->helper); + rcu_assign_pointer(help->helper, assign_helper); } #ifdef CONFIG_NF_CONNTRACK_MARK diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 24d0576d84b7..8e943efbdf0a 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -344,6 +344,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, helper = rcu_dereference(help->helper); rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, NULL); write_pnet(&exp->net, net); #ifdef CONFIG_NF_CONNTRACK_ZONES exp->zone = ct->zone; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bd7e9e13e4f6..a116c6629e2b 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -642,7 +642,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); - rcu_assign_pointer(exp->helper, &nf_conntrack_helper_h245); + rcu_assign_pointer(exp->assign_helper, &nf_conntrack_helper_h245); nathook = rcu_dereference(nfct_h323_nat_hook); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, @@ -766,7 +766,7 @@ static int expect_callforwarding(struct sk_buff *skb, nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); nathook = rcu_dereference(nfct_h323_nat_hook); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, @@ -1233,7 +1233,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3 : NULL, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); exp->flags = NF_CT_EXPECT_PERMANENT; /* Accept multiple calls */ nathook = rcu_dereference(nfct_h323_nat_hook); @@ -1305,7 +1305,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_UDP, NULL, &port); - rcu_assign_pointer(exp->helper, nf_conntrack_helper_ras); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_ras); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect RAS "); @@ -1522,7 +1522,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); exp->flags = NF_CT_EXPECT_PERMANENT; - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); @@ -1576,7 +1576,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); exp->flags = NF_CT_EXPECT_PERMANENT; - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 9150bcfd7ca8..ea0cdb7ec915 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -419,6 +419,11 @@ static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data) this = rcu_dereference_protected(exp->helper, lockdep_is_held(&nf_conntrack_expect_lock)); + if (this == me) + return true; + + this = rcu_dereference_protected(exp->assign_helper, + lockdep_is_held(&nf_conntrack_expect_lock)); return this == me; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c8fe284b86db..3df7e5fc76c8 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2635,6 +2635,7 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, + const struct nf_conntrack_helper *assign_helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask); @@ -2861,6 +2862,7 @@ static int ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report) { + struct nf_conntrack_helper *assign_helper = NULL; struct nlattr *cda[CTA_EXPECT_MAX+1]; struct nf_conntrack_tuple tuple, mask; struct nf_conntrack_expect *exp; @@ -2876,8 +2878,18 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, if (err < 0) return err; + if (cda[CTA_EXPECT_HELP_NAME]) { + const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); + + assign_helper = __nf_conntrack_helper_find(helpname, + nf_ct_l3num(ct), + tuple.dst.protonum); + if (!assign_helper) + return -EOPNOTSUPP; + } + exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct, - &tuple, &mask); + assign_helper, &tuple, &mask); if (IS_ERR(exp)) return PTR_ERR(exp); @@ -3516,6 +3528,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, + const struct nf_conntrack_helper *assign_helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { @@ -3569,6 +3582,7 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, exp->zone = ct->zone; #endif rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, assign_helper); exp->tuple = *tuple; exp->mask.src.u3 = mask->src.u3; exp->mask.src.u.all = mask->src.u.all; @@ -3624,7 +3638,7 @@ ctnetlink_create_expect(struct net *net, ct = nf_ct_tuplehash_to_ctrack(h); rcu_read_lock(); - exp = ctnetlink_alloc_expect(cda, ct, &tuple, &mask); + exp = ctnetlink_alloc_expect(cda, ct, NULL, &tuple, &mask); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto err_rcu; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 147043f19521..f5f9bd47d288 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1386,7 +1386,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct), saddr, &daddr, proto, NULL, &port); exp->timeout.expires = sip_timeout * HZ; - rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, helper); exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE; hooks = rcu_dereference(nf_nat_sip_hooks); @@ -1629,7 +1629,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, unsigned int matchoff, matchlen; unsigned int msglen, origlen; const char *dptr, *end; - s16 diff, tdiff = 0; + s32 diff, tdiff = 0; int ret = NF_ACCEPT; unsigned long clen; bool term; diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index f7be30c69b5c..a1c41defaf22 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -315,7 +315,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, } static void nf_nat_sip_seq_adjust(struct sk_buff *skb, unsigned int protoff, - s16 off) + s32 off) { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 51d3d4d44918..ca6d2041eee6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -44,8 +44,6 @@ enum { NFT_VALIDATE_DO, }; -static struct rhltable nft_objname_ht; - static u32 nft_chain_hash(const void *data, u32 len, u32 seed); static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed); static int nft_chain_hash_cmp(struct rhashtable_compare_arg *, const void *); @@ -1600,6 +1598,10 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, if (err) goto err_chain_ht; + err = rhltable_init(&table->objname_ht, &nft_objname_ht_params); + if (err < 0) + goto err_obj_ht; + INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); INIT_LIST_HEAD(&table->objects); @@ -1618,6 +1620,8 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, list_add_tail_rcu(&table->list, &nft_net->tables); return 0; err_trans: + rhltable_destroy(&table->objname_ht); +err_obj_ht: rhltable_destroy(&table->chains_ht); err_chain_ht: kfree(table->udata); @@ -1784,6 +1788,7 @@ static void nf_tables_table_destroy(struct nft_table *table) return; rhltable_destroy(&table->chains_ht); + rhltable_destroy(&table->objname_ht); kfree(table->name); kfree(table->udata); kfree(table); @@ -7957,7 +7962,7 @@ void nft_unregister_obj(struct nft_object_type *obj_type) EXPORT_SYMBOL_GPL(nft_unregister_obj); struct nft_object *nft_obj_lookup(const struct net *net, - const struct nft_table *table, + struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask) { @@ -7973,7 +7978,7 @@ struct nft_object *nft_obj_lookup(const struct net *net, !lockdep_commit_lock_is_held(net)); rcu_read_lock(); - list = rhltable_lookup(&nft_objname_ht, &k, nft_objname_ht_params); + list = rhltable_lookup(&table->objname_ht, &k, nft_objname_ht_params); if (!list) goto out; @@ -8252,7 +8257,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, if (err < 0) goto err_trans; - err = rhltable_insert(&nft_objname_ht, &obj->rhlhead, + err = rhltable_insert(&table->objname_ht, &obj->rhlhead, nft_objname_ht_params); if (err < 0) goto err_obj_ht; @@ -8437,8 +8442,8 @@ nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; - const struct nft_table *table; struct net *net = info->net; + struct nft_table *table; struct nft_object *obj; struct sk_buff *skb2; u32 objtype; @@ -10270,9 +10275,9 @@ static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) nf_tables_commit_chain_free_rules_old(g0); } -static void nft_obj_del(struct nft_object *obj) +static void nft_obj_del(struct nft_table *table, struct nft_object *obj) { - rhltable_remove(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); + rhltable_remove(&table->objname_ht, &obj->rhlhead, nft_objname_ht_params); list_del_rcu(&obj->list); } @@ -10960,7 +10965,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: - nft_obj_del(nft_trans_obj(trans)); + nft_obj_del(table, nft_trans_obj(trans)); nf_tables_obj_notify(&ctx, nft_trans_obj(trans), trans->msg_type); break; @@ -11251,7 +11256,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); } else { nft_use_dec_restore(&table->use); - nft_obj_del(nft_trans_obj(trans)); + nft_obj_del(table, nft_trans_obj(trans)); } break; case NFT_MSG_DELOBJ: @@ -11877,7 +11882,7 @@ static void __nft_release_table(struct net *net, struct nft_table *table) nft_set_destroy(&ctx, set); } list_for_each_entry_safe(obj, ne, &table->objects, list) { - nft_obj_del(obj); + nft_obj_del(table, obj); nft_use_dec(&table->use); nft_obj_destroy(&ctx, obj); } @@ -12059,10 +12064,6 @@ static int __init nf_tables_module_init(void) if (err < 0) goto err_netdev_notifier; - err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params); - if (err < 0) - goto err_rht_objname; - err = nft_offload_init(); if (err < 0) goto err_offload; @@ -12085,8 +12086,6 @@ static int __init nf_tables_module_init(void) err_netlink_notifier: nft_offload_exit(); err_offload: - rhltable_destroy(&nft_objname_ht); -err_rht_objname: unregister_netdevice_notifier(&nf_tables_flowtable_notifier); err_netdev_notifier: nf_tables_core_module_exit(); @@ -12108,7 +12107,6 @@ static void __exit nf_tables_module_exit(void) unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_gc_work); rcu_barrier(); - rhltable_destroy(&nft_objname_ht); nf_tables_core_module_exit(); } diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 86a21c2b954f..e07888aaf147 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -259,9 +259,7 @@ static int nft_payload_dump(struct sk_buff *skb, static bool nft_payload_offload_mask(struct nft_offload_reg *reg, u32 priv_len, u32 field_len) { - unsigned int remainder, delta, k; struct nft_data mask = {}; - __be32 remainder_mask; if (priv_len == field_len) { memset(®->mask, 0xff, priv_len); @@ -270,15 +268,7 @@ static bool nft_payload_offload_mask(struct nft_offload_reg *reg, return false; } - memset(&mask, 0xff, field_len); - remainder = priv_len % sizeof(u32); - if (remainder) { - k = priv_len / sizeof(u32); - delta = field_len - priv_len; - remainder_mask = htonl(~((1 << (delta * BITS_PER_BYTE)) - 1)); - mask.data[k] = (__force u32)remainder_mask; - } - + memset(&mask, 0xff, priv_len); memcpy(®->mask, &mask, field_len); return true; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 3b507694e81e..b3f15bbf259e 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -117,6 +117,7 @@ struct xt_hashlimit_htable { refcount_t use; u_int8_t family; bool rnd_initialized; + bool ratematch; struct hashlimit_cfg3 cfg; /* config */ @@ -323,6 +324,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, kvfree(hinfo); return -ENOMEM; } + hinfo->ratematch = !!(cfg->mode & XT_HASHLIMIT_RATE_MATCH); spin_lock_init(&hinfo->lock); switch (revision) { @@ -870,7 +872,10 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, } /* Check for overflow. */ - if (revision >= 3 && cfg->mode & XT_HASHLIMIT_RATE_MATCH) { + if (cfg->mode & XT_HASHLIMIT_RATE_MATCH) { + if (revision < 3) + return -EINVAL; + if (cfg->avg == 0 || cfg->avg > U32_MAX) { pr_info_ratelimited("invalid rate\n"); return -ERANGE; @@ -903,6 +908,15 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, mutex_unlock(&hashlimit_mutex); return ret; } + } else { + if ((cfg->mode & XT_HASHLIMIT_RATE_MATCH && + !(*hinfo)->ratematch) || + (!(cfg->mode & XT_HASHLIMIT_RATE_MATCH) && + (*hinfo)->ratematch)) { + mutex_unlock(&hashlimit_mutex); + htable_put(*hinfo); + return -EINVAL; + } } mutex_unlock(&hashlimit_mutex); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 56ea40d23e28..5d6a4c6b7ea6 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1107,6 +1107,10 @@ static int execute_masked_set_action(struct sk_buff *skb, return err; } +/* When 'last' is true, recirc() should always consume the 'skb'. + * Otherwise, recirc() should keep 'skb' intact regardless what + * actions are executed on recirculation. + */ static int execute_recirc(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *a, bool last) @@ -1117,8 +1121,12 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb, int err; err = ovs_flow_key_update(skb, key); - if (err) + if (err) { + if (last) + ovs_kfree_skb_reason(skb, + OVS_DROP_ACTION_ERROR); return err; + } } BUG_ON(!is_flow_key_valid(key)); @@ -1371,7 +1379,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, if (!is_flow_key_valid(key)) { err = ovs_flow_key_update(skb, key); if (err) - return err; + break; } err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key, diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index cc08e0403909..671984edfe1e 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -133,18 +133,10 @@ static void dp_meter_instance_remove(struct dp_meter_instance *ti, static int attach_meter(struct dp_meter_table *tbl, struct dp_meter *meter) { - struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti); - u32 hash = meter_hash(ti, meter->id); + struct dp_meter_instance *ti; + u32 hash; int err; - /* In generally, slots selected should be empty, because - * OvS uses id-pool to fetch a available id. - */ - if (unlikely(rcu_dereference_ovsl(ti->dp_meters[hash]))) - return -EBUSY; - - dp_meter_instance_insert(ti, meter); - /* That function is thread-safe. */ tbl->count++; if (tbl->count >= tbl->max_meters_allowed) { @@ -152,16 +144,29 @@ static int attach_meter(struct dp_meter_table *tbl, struct dp_meter *meter) goto attach_err; } - if (tbl->count >= ti->n_meters && - dp_meter_instance_realloc(tbl, ti->n_meters * 2)) { - err = -ENOMEM; + ti = rcu_dereference_ovsl(tbl->ti); + if (tbl->count >= ti->n_meters) { + err = dp_meter_instance_realloc(tbl, ti->n_meters * 2); + if (err) + goto attach_err; + + ti = rcu_dereference_ovsl(tbl->ti); + } + + hash = meter_hash(ti, meter->id); + + /* In general, selected slots should be empty, because + * OvS uses id-pool to fetch available ids. + */ + if (unlikely(rcu_dereference_ovsl(ti->dp_meters[hash]))) { + err = -EBUSY; goto attach_err; } + dp_meter_instance_insert(ti, meter); return 0; attach_err: - dp_meter_instance_remove(ti, meter); tbl->count--; return err; } diff --git a/net/rds/ib.c b/net/rds/ib.c index ce5be43c5fba..1061bcf7d131 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -431,6 +431,10 @@ static int rds_ib_laddr_check_cm(struct net *net, const struct in6_addr *addr, sa = (struct sockaddr *)&sin; } else { #if IS_ENABLED(CONFIG_IPV6) + if (!ipv6_mod_enabled()) { + ret = -EADDRNOTAVAIL; + goto out; + } memset(&sin6, 0, sizeof(sin6)); sin6.sin6_family = AF_INET6; sin6.sin6_addr = *addr; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 5289afbb61aa..e50e01abb079 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -810,6 +810,10 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, dp = event->param.conn.private_data; if (isv6) { #if IS_ENABLED(CONFIG_IPV6) + if (!ipv6_mod_enabled()) { + err = -EOPNOTSUPP; + goto out; + } dp_cmn = &dp->ricp_v6.dp_cmn; saddr6 = &dp->ricp_v6.dp_saddr; daddr6 = &dp->ricp_v6.dp_daddr; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 06a2d8d48bba..1980a197034b 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -331,21 +331,25 @@ int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, /* If the scope_id is specified, check only those addresses * hosted on the specified interface. */ + rcu_read_lock(); if (scope_id != 0) { - rcu_read_lock(); dev = dev_get_by_index_rcu(net, scope_id); /* scope_id is not valid... */ if (!dev) { rcu_read_unlock(); return -EADDRNOTAVAIL; } - rcu_read_unlock(); } #if IS_ENABLED(CONFIG_IPV6) - ret = ipv6_chk_addr(net, addr, dev, 0); - if (ret) - return 0; + if (ipv6_mod_enabled()) { + ret = ipv6_chk_addr(net, addr, dev, 0); + if (ret) { + rcu_read_unlock(); + return 0; + } + } #endif + rcu_read_unlock(); return -EADDRNOTAVAIL; } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5793d71852b8..e560f7ee4adb 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -614,6 +614,9 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, return peer; } + if (asoc->peer.transport_count == U16_MAX) + return NULL; + peer = sctp_transport_new(asoc->base.net, addr, gfp); if (!peer) return NULL; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 1f8a1e6069b3..721e147091a9 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1802,9 +1802,9 @@ struct sctp_association *sctp_unpack_cookie( goto fail; } - /* Check to see if the cookie is stale. If there is already - * an association, there is no need to check cookie's expiration - * for init collision case of lost COOKIE ACK. + /* Check to see if the cookie is stale. RFC 9260 Section 5.2.4 + * exempts an expired cookie only when both Verification Tags match + * the current association. * If skb has been timestamped, then use the stamp, otherwise * use current time. This introduces a small possibility that * a cookie may be considered expired, but this would only slow @@ -1815,7 +1815,10 @@ struct sctp_association *sctp_unpack_cookie( else kt = ktime_get_real(); - if (!asoc && ktime_before(bear_cookie->expiration, kt)) { + if ((!asoc || + asoc->c.my_vtag != bear_cookie->my_vtag || + asoc->c.peer_vtag != bear_cookie->peer_vtag) && + ktime_before(bear_cookie->expiration, kt)) { suseconds_t usecs = ktime_to_us(ktime_sub(kt, bear_cookie->expiration)); __be32 n = htonl(usecs); @@ -2168,7 +2171,13 @@ static enum sctp_ierror sctp_verify_param(struct net *net, case SCTP_PARAM_HEARTBEAT_INFO: case SCTP_PARAM_UNRECOGNIZED_PARAMETERS: case SCTP_PARAM_ECN_CAPABLE: + break; case SCTP_PARAM_ADAPTATION_LAYER_IND: + if (ntohs(param.p->length) != sizeof(*param.aind)) { + sctp_process_inv_paramlength(asoc, param.p, + chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + } break; case SCTP_PARAM_SUPPORTED_EXT: diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index be0c2da83d2b..5df4838a6386 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1558,10 +1558,10 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) read_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); while (node) { - read_unlock_bh(&lgr->conns_lock); conn = rb_entry(node, struct smc_connection, alert_node); smc = container_of(conn, struct smc_sock, conn); sock_hold(&smc->sk); /* sock_put below */ + read_unlock_bh(&lgr->conns_lock); lock_sock(&smc->sk); smc_conn_kill(conn, soft); release_sock(&smc->sk); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 24013455fbf0..7823bbcd482b 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -795,7 +795,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, __poll_t revents = 0; sock_poll_wait(file, sock, wait); - trace_tipc_sk_poll(sk, NULL, TIPC_DUMP_ALL, " "); + trace_tipc_sk_poll(sk, NULL, TIPC_DUMP_NONE, " "); if (sk->sk_shutdown & RCV_SHUTDOWN) revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index b65479a738f4..52b17331e9d5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -835,6 +835,7 @@ static int unix_listen(struct socket *sock, int backlog) if (err) goto out; unix_state_lock(sk); + err = -EINVAL; if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN) goto out_unlock; if (backlog > sk->sk_max_ack_backlog) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 9e0a486d54fb..70c57c5d8e1d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -547,12 +547,11 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags) static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool) { - unsigned long flags; int ret; - spin_lock_irqsave(&pool->cq_lock, flags); + spin_lock(&pool->cq_cached_prod_lock); ret = xskq_prod_reserve(pool->cq); - spin_unlock_irqrestore(&pool->cq_lock, flags); + spin_unlock(&pool->cq_cached_prod_lock); return ret; } @@ -603,7 +602,7 @@ static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool, unsigned long flags; u32 idx, i; - spin_lock_irqsave(&pool->cq_lock, flags); + spin_lock_irqsave(&pool->cq_prod_lock, flags); idx = xskq_get_prod(pool->cq); if (unlikely(num_descs > 1)) { @@ -621,16 +620,27 @@ static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool, descs_processed++; } xskq_prod_submit_n(pool->cq, descs_processed); - spin_unlock_irqrestore(&pool->cq_lock, flags); + spin_unlock_irqrestore(&pool->cq_prod_lock, flags); } -static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n) +static void xsk_cq_submit_addr_single_locked(struct xsk_buff_pool *pool, + struct xdp_desc *desc) { unsigned long flags; + u32 idx; - spin_lock_irqsave(&pool->cq_lock, flags); + spin_lock_irqsave(&pool->cq_prod_lock, flags); + idx = xskq_get_prod(pool->cq); + xskq_prod_write_addr(pool->cq, idx, desc->addr); + xskq_prod_submit_n(pool->cq, 1); + spin_unlock_irqrestore(&pool->cq_prod_lock, flags); +} + +static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n) +{ + spin_lock(&pool->cq_cached_prod_lock); xskq_prod_cancel_n(pool->cq, n); - spin_unlock_irqrestore(&pool->cq_lock, flags); + spin_unlock(&pool->cq_cached_prod_lock); } static void xsk_destruct_skb(struct sk_buff *skb) @@ -676,8 +686,11 @@ static void xsk_consume_skb(struct sk_buff *skb) static void xsk_drop_skb(struct sk_buff *skb) { - xdp_sk(skb->sk)->tx->invalid_descs += xsk_get_num_desc(skb); - xsk_consume_skb(skb); + struct xdp_sock *xs = xdp_sk(skb->sk); + + xs->tx->invalid_descs += xsk_get_num_desc(skb); + consume_skb(skb); + xs->skb = NULL; } static int xsk_skb_metadata(struct sk_buff *skb, void *buffer, @@ -768,7 +781,7 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, } /* in case of -EOVERFLOW that could happen below, - * xsk_consume_skb() will release this node as whole skb + * xsk_drop_skb() will release this node as whole skb * would be dropped, which implies freeing all list elements */ xsk_addr->addrs[xsk_addr->num_descs] = desc->addr; @@ -867,6 +880,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; } + xsk_addr->addrs[xsk_addr->num_descs] = desc->addr; + if (unlikely(nr_frags == (MAX_SKB_FRAGS - 1) && xp_mb_desc(desc))) { err = -EOVERFLOW; goto free_err; @@ -884,8 +899,6 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); - - xsk_addr->addrs[xsk_addr->num_descs] = desc->addr; } } @@ -913,13 +926,14 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, static int __xsk_generic_xmit(struct sock *sk) { struct xdp_sock *xs = xdp_sk(sk); - bool sent_frame = false; struct xdp_desc desc; struct sk_buff *skb; + u32 cached_cons; u32 max_batch; int err = 0; mutex_lock(&xs->mutex); + cached_cons = xs->tx->cached_cons; /* Since we dropped the RCU read lock, the socket state might have changed. */ if (unlikely(!xsk_is_bound(xs))) { @@ -948,11 +962,21 @@ static int __xsk_generic_xmit(struct sock *sk) goto out; } + if (unlikely(xs->drain_cont)) { + xsk_cq_submit_addr_single_locked(xs->pool, &desc); + xs->tx->invalid_descs++; + xskq_cons_release(xs->tx); + xs->drain_cont = xp_mb_desc(&desc); + continue; + } + skb = xsk_build_skb(xs, &desc); if (IS_ERR(skb)) { err = PTR_ERR(skb); if (err != -EOVERFLOW) goto out; + if (xp_mb_desc(&desc)) + xs->drain_cont = true; err = 0; continue; } @@ -981,18 +1005,33 @@ static int __xsk_generic_xmit(struct sock *sk) goto out; } - sent_frame = true; xs->skb = NULL; } if (xskq_has_descs(xs->tx)) { + bool drain = xs->skb || xs->drain_cont || xp_mb_desc(&desc); + + err = xsk_cq_reserve_locked(xs->pool); + if (err) { + xs->tx->invalid_descs--; + if (xs->skb) + xsk_drop_skb(xs->skb); + xs->drain_cont = drain; + err = -EAGAIN; + goto out; + } + if (xs->skb) xsk_drop_skb(xs->skb); + + xsk_cq_submit_addr_single_locked(xs->pool, &desc); + xskq_cons_release(xs->tx); + xs->drain_cont = xp_mb_desc(&desc); } out: - if (sent_frame) + if (xs->tx->cached_cons != cached_cons) __xsk_tx_release(xs); mutex_unlock(&xs->mutex); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index a129ce6f1c25..c9688735b643 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -96,7 +96,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, INIT_LIST_HEAD(&pool->xskb_list); INIT_LIST_HEAD(&pool->xsk_tx_list); spin_lock_init(&pool->xsk_tx_list_lock); - spin_lock_init(&pool->cq_lock); + spin_lock_init(&pool->cq_prod_lock); + spin_lock_init(&pool->cq_cached_prod_lock); refcount_set(&pool->users, 1); pool->fq = xs->fq_tmp; diff --git a/security/keys/keyring.c b/security/keys/keyring.c index e105349794f2..fd95a0eb7a46 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -271,6 +271,7 @@ static unsigned long keyring_get_key_chunk(const void *data, int level) unsigned long chunk = 0; const u8 *d; int desc_len = index_key->desc_len, n = sizeof(chunk); + unsigned int offset; level /= ASSOC_ARRAY_KEY_CHUNK_SIZE; switch (level) { @@ -284,17 +285,18 @@ static unsigned long keyring_get_key_chunk(const void *data, int level) return (unsigned long)index_key->domain_tag; default: level -= 4; - if (desc_len <= sizeof(index_key->desc)) + offset = sizeof(index_key->desc) + level * sizeof(long); + if (desc_len <= offset) return 0; - d = index_key->description + sizeof(index_key->desc); - d += level * sizeof(long); - desc_len -= sizeof(index_key->desc); + d = index_key->description + offset; + desc_len -= offset; if (desc_len > n) desc_len = n; + d += desc_len; do { chunk <<= 8; - chunk |= *d++; + chunk |= *--d; } while (--desc_len > 0); return chunk; } @@ -375,7 +377,7 @@ static int keyring_diff_objects(const void *object, const void *data) return -1; differ_plus_i: - level += i; + level += i - (int)sizeof(a->desc); differ: i = level * 8 + __ffs(seg_a ^ seg_b); return i; diff --git a/security/keys/trusted-keys/trusted_dcp.c b/security/keys/trusted-keys/trusted_dcp.c index 7b6eb655df0c..c078adebe190 100644 --- a/security/keys/trusted-keys/trusted_dcp.c +++ b/security/keys/trusted-keys/trusted_dcp.c @@ -69,7 +69,7 @@ static bool skip_zk_test; module_param_named(dcp_skip_zk_test, skip_zk_test, bool, 0); MODULE_PARM_DESC(dcp_skip_zk_test, "Don't test whether device keys are zero'ed"); -static unsigned int calc_blob_len(unsigned int payload_len) +static size_t calc_blob_len(unsigned int payload_len) { return sizeof(struct dcp_blob_fmt) + payload_len + DCP_BLOB_AUTHLEN; } @@ -200,7 +200,8 @@ static int encrypt_blob_key(u8 *plain_key, u8 *encrypted_key) static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob) { struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob; - int blen, ret; + size_t blen; + int ret; u8 *plain_blob_key; blen = calc_blob_len(p->key_len); @@ -242,7 +243,8 @@ static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob) static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob) { struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob; - int blen, ret; + size_t blen; + int ret; u8 *plain_blob_key = NULL; if (b->fmt_version != DCP_BLOB_VERSION) { @@ -253,9 +255,14 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob) } p->key_len = le32_to_cpu(b->payload_len); + if (p->key_len < MIN_KEY_SIZE || p->key_len > MAX_KEY_SIZE) { + ret = -EINVAL; + goto out; + } + blen = calc_blob_len(p->key_len); if (blen != p->blob_len) { - pr_err("DCP blob has bad length: %i != %i\n", blen, + pr_err("DCP blob has bad length: %zu != %u\n", blen, p->blob_len); ret = -EINVAL; goto out; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 0ae95a467089..0e69127bb10b 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2334,6 +2334,7 @@ static void relink_to_local(struct snd_pcm_substream *substream) static int snd_pcm_unlink(struct snd_pcm_substream *substream) { + struct snd_pcm_substream *s; struct snd_pcm_group *group; bool nonatomic = substream->pcm->nonatomic; bool do_free = false; @@ -2346,6 +2347,12 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) group = substream->group; snd_pcm_group_lock_irq(group, nonatomic); + /* release drain waiters before changing membership, else snd_pcm_drain() + * leaves its on-stack wait entry queued on a member's sleep list + */ + snd_pcm_group_for_each_entry(s, substream) + wake_up(&s->runtime->sleep); + relink_to_local(substream); refcount_dec(&group->refs); diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c index 0256caa61c29..a89451f47872 100644 --- a/sound/core/seq/seq_timer.c +++ b/sound/core/seq/seq_timer.c @@ -362,11 +362,10 @@ static int initialize_timer(struct snd_seq_timer *tmr) tmr->ticks = 1; if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE)) { unsigned long r = snd_timer_resolution(tmr->timeri); - if (r) { - tmr->ticks = (unsigned int)(1000000000uL / (r * freq)); - if (! tmr->ticks) - tmr->ticks = 1; - } + unsigned long den; + + if (r && !check_mul_overflow(r, freq, &den)) + tmr->ticks = max(1U, (unsigned int)(1000000000uL / den)); } tmr->initialized = 1; return 0; diff --git a/sound/core/timer.c b/sound/core/timer.c index a2c344b4cc73..c5f0e895ea02 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -409,6 +409,8 @@ static void remove_slave_links(struct snd_timer_instance *timeri, list_del_init(&slave->ack_list); list_del_init(&slave->active_list); } + /* the close is done; a reopen must not see the mark */ + timeri->flags &= ~SNDRV_TIMER_IFLG_DEAD; } /* diff --git a/sound/core/ump.c b/sound/core/ump.c index 8d8681a42ca5..0ba253f50b5a 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -1366,6 +1366,7 @@ int snd_ump_attach_legacy_rawmidi(struct snd_ump_endpoint *ump, &rmidi); if (err < 0) { kfree(ump->out_cvts); + ump->out_cvts = NULL; return err; } diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 40a75d72f712..7a047bdbae46 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6839,6 +6839,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x89d3, "HP EliteBook 645 G9 (MB 89D2)", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x89da, "HP Spectre x360 14t-ea100", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX), SND_PCI_QUIRK(0x103c, 0x89e7, "HP Elite x2 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8a06, "HP Dragonfly Folio G3 2-in-1", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a0f, "HP Pavilion 14-ec1xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a1f, "HP Laptop 14s-dr5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), @@ -7559,7 +7560,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x300f, "TongFang X6AR5xxY", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x3019, "TongFang X6FR5xxY", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x3031, "TongFang X6AR55xU", ALC2XX_FIXUP_HEADSET_MIC), - SND_PCI_QUIRK(0x1d05, 0x3034, "TongFang X6xx45xU", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d05, 0x3033, "TongFang X6SP45xU", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d05, 0x3034, "TongFang X6KK45xU", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), diff --git a/sound/pci/lx6464es/lx6464es.c b/sound/pci/lx6464es/lx6464es.c index 96df00db51d5..3b40ec071379 100644 --- a/sound/pci/lx6464es/lx6464es.c +++ b/sound/pci/lx6464es/lx6464es.c @@ -402,11 +402,8 @@ static void lx_trigger_start(struct lx6464es *chip, struct lx_stream *lx_stream) int err; - const u32 channels = substream->runtime->channels; - const u32 bytes_per_frame = channels * 3; - const u32 period_size = substream->runtime->period_size; const u32 periods = substream->runtime->periods; - const u32 period_bytes = period_size * bytes_per_frame; + const u32 period_bytes = snd_pcm_lib_period_bytes(substream); dma_addr_t buf = substream->dma_buffer.addr; int i; diff --git a/sound/pci/lx6464es/lx_core.c b/sound/pci/lx6464es/lx_core.c index 6f0843cfb3be..9909f1067871 100644 --- a/sound/pci/lx6464es/lx_core.c +++ b/sound/pci/lx6464es/lx_core.c @@ -969,10 +969,7 @@ static int lx_interrupt_request_new_buffer(struct lx6464es *chip, const unsigned int is_capture = lx_stream->is_capture; int err; - const u32 channels = substream->runtime->channels; - const u32 bytes_per_frame = channels * 3; - const u32 period_size = substream->runtime->period_size; - const u32 period_bytes = period_size * bytes_per_frame; + const u32 period_bytes = snd_pcm_lib_period_bytes(substream); const u32 pos = lx_stream->frame_pos; const u32 next_pos = ((pos+1) == substream->runtime->periods) ? 0 : pos + 1; diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 5aff5a459a43..830caf62d0fa 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -2390,8 +2390,9 @@ static int max98090_probe(struct snd_soc_component *component) dev_dbg(component->dev, "max98090_probe\n"); max98090->mclk = devm_clk_get(component->dev, "mclk"); - if (PTR_ERR(max98090->mclk) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (IS_ERR(max98090->mclk)) + if (PTR_ERR(max98090->mclk) == -EPROBE_DEFER) + return -EPROBE_DEFER; max98090->component = component; diff --git a/sound/soc/codecs/max98095.c b/sound/soc/codecs/max98095.c index cfb63fe69267..ad2587d2df81 100644 --- a/sound/soc/codecs/max98095.c +++ b/sound/soc/codecs/max98095.c @@ -1984,8 +1984,9 @@ static int max98095_probe(struct snd_soc_component *component) int ret = 0; max98095->mclk = devm_clk_get(component->dev, "mclk"); - if (PTR_ERR(max98095->mclk) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (IS_ERR(max98095->mclk)) + if (PTR_ERR(max98095->mclk) == -EPROBE_DEFER) + return -EPROBE_DEFER; /* reset the codec, the DSP core, and disable all interrupts */ max98095_reset(component); diff --git a/sound/soc/codecs/tas2562.c b/sound/soc/codecs/tas2562.c index 795c66cb4713..ec1c8d077efc 100644 --- a/sound/soc/codecs/tas2562.c +++ b/sound/soc/codecs/tas2562.c @@ -32,15 +32,16 @@ static const unsigned int float_vol_db_lookup[] = { 0x00000d43, 0x000010b2, 0x00001505, 0x00001a67, 0x00002151, 0x000029f1, 0x000034cd, 0x00004279, 0x000053af, 0x0000695b, -0x0000695b, 0x0000a6fa, 0x0000d236, 0x000108a4, 0x00014d2a, +0x000084a3, 0x0000a6fa, 0x0000d236, 0x000108a4, 0x00014d2a, 0x0001a36e, 0x00021008, 0x000298c0, 0x000344df, 0x00041d8f, 0x00052e5a, 0x000685c8, 0x00083621, 0x000a566d, 0x000d03a7, 0x0010624d, 0x0014a050, 0x0019f786, 0x0020b0bc, 0x0029279d, 0x0033cf8d, 0x004139d3, 0x00521d50, 0x00676044, 0x0082248a, 0x00a3d70a, 0x00ce4328, 0x0103ab3d, 0x0146e75d, 0x019b8c27, 0x02061b89, 0x028c423f, 0x03352529, 0x0409c2b0, 0x05156d68, -0x080e9f96, 0x0a24b062, 0x0cc509ab, 0x10137987, 0x143d1362, -0x197a967f, 0x2013739e, 0x28619ae9, 0x32d64617, 0x40000000 +0x06666666, 0x080e9f96, 0x0a24b062, 0x0cc509ab, 0x10137987, +0x143d1362, 0x197a967f, 0x2013739e, 0x28619ae9, 0x32d64617, +0x40000000 }; struct tas2562_data { @@ -475,20 +476,27 @@ static int tas2562_volume_control_put(struct snd_kcontrol *kcontrol, u32 reg_val; reg_val = float_vol_db_lookup[ucontrol->value.integer.value[0]/2]; - ret = snd_soc_component_write(component, TAS2562_DVC_CFG4, - (reg_val & 0xff)); - if (ret) - return ret; - ret = snd_soc_component_write(component, TAS2562_DVC_CFG3, - ((reg_val >> 8) & 0xff)); + /* + * The device applies the 32-bit coefficient to the playback path on + * the write to DVC_CFG4 (the LSB, book 0 page 2 reg 0x0F), so the + * bytes must be written MSB first and DVC_CFG4 last. Writing CFG4 + * first latches a mix of the previous coefficient's upper bytes and + * the new LSB instead of the requested value. + */ + ret = snd_soc_component_write(component, TAS2562_DVC_CFG1, + ((reg_val >> 24) & 0xff)); if (ret) return ret; ret = snd_soc_component_write(component, TAS2562_DVC_CFG2, ((reg_val >> 16) & 0xff)); if (ret) return ret; - ret = snd_soc_component_write(component, TAS2562_DVC_CFG1, - ((reg_val >> 24) & 0xff)); + ret = snd_soc_component_write(component, TAS2562_DVC_CFG3, + ((reg_val >> 8) & 0xff)); + if (ret) + return ret; + ret = snd_soc_component_write(component, TAS2562_DVC_CFG4, + (reg_val & 0xff)); if (ret) return ret; diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index a3b4d2c3b478..0b83446da45e 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -1303,8 +1303,8 @@ static void cali_reg_update(struct bulk_reg_val *p, t->sin_gn[2]); break; case TAS2781_PRM_SINEGAIN2_REG: - reg = TASDEVICE_REG(t->sin_gn[0], t->sin_gn[1], - t->sin_gn[2]); + reg = TASDEVICE_REG(t->sin_gn2[0], t->sin_gn2[1], + t->sin_gn2[2]); break; default: reg = 0; diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c index 92fb16f7be45..40279becb8d9 100644 --- a/sound/soc/fsl/fsl_asrc.c +++ b/sound/soc/fsl/fsl_asrc.c @@ -1388,7 +1388,7 @@ static int fsl_asrc_probe(struct platform_device *pdev) ret = fsl_asrc_m2m_init(asrc); if (ret) { dev_err(&pdev->dev, "failed to init m2m device %d\n", ret); - return ret; + goto err_pm_get_sync; } return 0; diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c index 59cdf18731a0..70136b2335ce 100644 --- a/sound/soc/fsl/fsl_easrc.c +++ b/sound/soc/fsl/fsl_easrc.c @@ -2266,7 +2266,7 @@ static int fsl_easrc_probe(struct platform_device *pdev) ret = fsl_asrc_m2m_init(easrc); if (ret) { dev_err(&pdev->dev, "failed to init m2m device %d\n", ret); - return ret; + goto err_pm_disable; } return 0; diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c index 4417278e39bb..e0cae47641ba 100644 --- a/sound/soc/sdca/sdca_functions.c +++ b/sound/soc/sdca/sdca_functions.c @@ -849,6 +849,8 @@ static int find_sdca_control_range(struct device *dev, return 0; else if (num_range < 0) return num_range; + else if (num_range < 2 * sizeof(*limits)) + return -EINVAL; range_list = devm_kcalloc(dev, num_range, sizeof(*range_list), GFP_KERNEL); if (!range_list) diff --git a/sound/usb/6fire/chip.c b/sound/usb/6fire/chip.c index 874f6cd503ca..e6cfe0d7ab0b 100644 --- a/sound/usb/6fire/chip.c +++ b/sound/usb/6fire/chip.c @@ -156,6 +156,10 @@ static int usb6fire_chip_probe(struct usb_interface *intf, return 0; destroy_chip: + chip->shutdown = true; + if (card) + snd_card_disconnect(card); + usb6fire_chip_abort(chip); snd_card_free(card); return ret; } diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 15490a87b460..7d96cebba53f 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -1164,10 +1164,12 @@ static int data_ep_set_params(struct snd_usb_endpoint *ep) << (16 - ep->datainterval); } - if (ep->fill_max) + if (ep->fill_max) { ep->curpacksize = ep->maxpacksize; - else + maxsize = ep->curpacksize; + } else { ep->curpacksize = maxsize; + } if (snd_usb_get_speed(chip->dev) != USB_SPEED_FULL) { packs_per_ms = 8 >> ep->datainterval; @@ -1804,11 +1806,13 @@ static void snd_usb_handle_sync_urb(struct snd_usb_endpoint *ep, out_packet->packets = in_ctx->packets; for (i = 0; i < in_ctx->packets; i++) { - if (urb->iso_frame_desc[i].status == 0) - out_packet->packet_size[i] = + if (urb->iso_frame_desc[i].status == 0) { + unsigned int frames = urb->iso_frame_desc[i].actual_length / sender->stride; - else + out_packet->packet_size[i] = min(frames, ep->maxframesize); + } else { out_packet->packet_size[i] = 0; + } } spin_unlock_irqrestore(&ep->lock, flags); diff --git a/sound/usb/midi.c b/sound/usb/midi.c index e09761b6c91f..01ed18b7b48a 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -793,6 +793,8 @@ static void snd_usbmidi_akai_output(struct snd_usb_midi_out_endpoint *ep, msg = urb->transfer_buffer + urb->transfer_buffer_length; buf_end = ep->max_transfer - MAX_AKAI_SYSEX_LEN - 1; + if (buf_end <= 0) + return; /* only try adding more data when there's space for at least 1 SysEx */ while (urb->transfer_buffer_length < buf_end) { diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c index 50b04e5a190b..646333f0cea9 100644 --- a/sound/usb/midi2.c +++ b/sound/usb/midi2.c @@ -329,7 +329,7 @@ ump_to_endpoint(struct snd_ump_endpoint *ump, int dir) { struct snd_usb_midi2_ump *rmidi = ump->private_data; - return rmidi->eps[dir]; + return rmidi ? rmidi->eps[dir] : NULL; } /* ump open callback */ @@ -685,6 +685,8 @@ static void free_all_midi2_umps(struct snd_usb_midi2_interface *umidi) rmidi = list_first_entry(&umidi->rawmidi_list, struct snd_usb_midi2_ump, list); list_del(&rmidi->list); + if (rmidi->ump) + rmidi->ump->private_data = NULL; kfree(rmidi); } } diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 02d9ede67467..ce057bbb2e11 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -3352,7 +3352,7 @@ static int snd_rme_digiface_read_status(struct snd_kcontrol *kcontrol, u32 statu struct usb_mixer_elem_list *list = snd_kcontrol_chip(kcontrol); struct snd_usb_audio *chip = list->mixer->chip; struct usb_device *dev = chip->dev; - __le32 buf[4]; + __le32 buf[4] = {}; int err; err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 2998e1bc088b..2869fcb199ff 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -16,7 +16,7 @@ import shutil import signal import sys import threading -from typing import Iterator, List, Optional, Tuple +from typing import Iterator, List, Optional, Tuple, Any from types import FrameType import kunit_config @@ -265,6 +265,7 @@ class LinuxSourceTree: if kconfig_add: kconfig = kunit_config.parse_from_string('\n'.join(kconfig_add)) self._kconfig.merge_in_entries(kconfig) + self._process : Optional[subprocess.Popen[Any]] = None def arch(self) -> str: return self._arch @@ -345,6 +346,12 @@ class LinuxSourceTree: return False return self.validate_config(build_dir) + def _restore_terminal_if_tty(self) -> None: + # stty requires a controlling terminal; skip headless runs. + if sys.stdin is None or not sys.stdin.isatty(): + return + subprocess.call(['stty', 'sane']) + def run_kernel(self, args: Optional[List[str]]=None, build_dir: str='', filter_glob: str='', filter: str='', filter_action: Optional[str]=None, timeout: Optional[int]=None) -> Iterator[str]: # Copy to avoid mutating the caller-supplied list. exec_tests() reuses # the same args across repeated run_kernel() calls (e.g. --run_isolated), @@ -358,36 +365,45 @@ class LinuxSourceTree: args.append('kunit.filter_action=' + filter_action) args.append('kunit.enable=1') - process = self._ops.start(args, build_dir) - assert process.stdout is not None # tell mypy it's set + self._process = self._ops.start(args, build_dir) + assert self._process is not None # tell mypy it's set + assert self._process.stdout is not None # tell mypy it's set # Enforce the timeout in a background thread. def _wait_proc() -> None: try: - process.wait(timeout=timeout) + if self._process: + self._process.wait(timeout=timeout) except Exception as e: print(e) - process.terminate() - process.wait() + if self._process: + self._process.terminate() + self._process.wait() waiter = threading.Thread(target=_wait_proc) waiter.start() output = open(get_outfile_path(build_dir), 'w') try: # Tee the output to the file and to our caller in real time. - for line in process.stdout: + for line in self._process.stdout: output.write(line) yield line # This runs even if our caller doesn't consume every line. finally: # Flush any leftover output to the file - output.write(process.stdout.read()) + if self._process: + if self._process.stdout: + output.write(self._process.stdout.read()) + self._process.stdout.close() + self._process = None output.close() - process.stdout.close() waiter.join() - subprocess.call(['stty', 'sane']) + self._restore_terminal_if_tty() def signal_handler(self, unused_sig: int, unused_frame: Optional[FrameType]) -> None: logging.error('Build interruption occurred. Cleaning console.') - subprocess.call(['stty', 'sane']) + if self._process: + self._process.terminate() + self._process.wait() + self._restore_terminal_if_tty() diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index ed45bac1548d..0eb61de9abd4 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -515,6 +515,48 @@ class LinuxSourceTreeTest(unittest.TestCase): self.assertIn('kunit.filter_glob=suite.test1', start_calls[0]) self.assertIn('kunit.filter_glob=suite.test2', start_calls[1]) + def test_run_kernel_skips_terminal_reset_without_tty(self): + def fake_start(unused_args, unused_build_dir): + return subprocess.Popen(['printf', 'KTAP version 1\n'], + text=True, stdout=subprocess.PIPE) + + non_tty_stdin = mock.Mock() + non_tty_stdin.isatty.return_value = False + + with tempfile.TemporaryDirectory('') as build_dir: + tree = kunit_kernel.LinuxSourceTree(build_dir, kunitconfig_paths=[os.devnull]) + with mock.patch.object(tree._ops, 'start', side_effect=fake_start), \ + mock.patch.object(kunit_kernel.sys, 'stdin', non_tty_stdin), \ + mock.patch.object(kunit_kernel.subprocess, 'call') as mock_call: + for _ in tree.run_kernel(build_dir=build_dir): + pass + + mock_call.assert_not_called() + + def test_signal_handler_skips_terminal_reset_without_tty(self): + non_tty_stdin = mock.Mock() + non_tty_stdin.isatty.return_value = False + tree = kunit_kernel.LinuxSourceTree('', kunitconfig_paths=[os.devnull]) + + with mock.patch.object(kunit_kernel.sys, 'stdin', non_tty_stdin), \ + mock.patch.object(kunit_kernel.subprocess, 'call') as mock_call, \ + mock.patch.object(kunit_kernel.logging, 'error') as mock_error: + tree.signal_handler(signal.SIGINT, None) + mock_error.assert_called_once() + mock_call.assert_not_called() + + def test_signal_handler_resets_terminal_with_tty(self): + tty_stdin = mock.Mock() + tty_stdin.isatty.return_value = True + tree = kunit_kernel.LinuxSourceTree('', kunitconfig_paths=[os.devnull]) + + with mock.patch.object(kunit_kernel.sys, 'stdin', tty_stdin), \ + mock.patch.object(kunit_kernel.subprocess, 'call') as mock_call, \ + mock.patch.object(kunit_kernel.logging, 'error') as mock_error: + tree.signal_handler(signal.SIGINT, None) + mock_error.assert_called_once() + mock_call.assert_called_once_with(['stty', 'sane']) + def test_build_reconfig_no_config(self): with tempfile.TemporaryDirectory('') as build_dir: with open(kunit_kernel.get_kunitconfig_path(build_dir), 'w') as f: diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c index bfb0da2b4fdd..4debe0756b67 100644 --- a/tools/testing/selftests/clone3/clone3_set_tid.c +++ b/tools/testing/selftests/clone3/clone3_set_tid.c @@ -141,7 +141,7 @@ int main(int argc, char *argv[]) { FILE *f; char buf; - char *line; + char *line = NULL; int status; int ret = -1; size_t len = 0; diff --git a/tools/testing/selftests/filesystems/fclog.c b/tools/testing/selftests/filesystems/fclog.c index 912a8b755c3b..3e6fb609ef56 100644 --- a/tools/testing/selftests/filesystems/fclog.c +++ b/tools/testing/selftests/filesystems/fclog.c @@ -6,10 +6,8 @@ #include <assert.h> #include <errno.h> +#include <fcntl.h> #include <sched.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> #include <unistd.h> #include <sys/mount.h> diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt index cff124c1eddd..665a13a37363 100644 --- a/tools/testing/selftests/lkdtm/tests.txt +++ b/tools/testing/selftests/lkdtm/tests.txt @@ -74,7 +74,7 @@ USERCOPY_STACK_FRAME_TO USERCOPY_STACK_FRAME_FROM USERCOPY_STACK_BEYOND USERCOPY_KERNEL -STACKLEAK_ERASING OK: the rest of the thread stack is properly erased +KSTACK_ERASE OK: the rest of the thread stack is properly erased CFI_FORWARD_PROTO CFI_BACKWARD call trace:|ok: control flow unchanged FORTIFY_STRSCPY detected buffer overflow diff --git a/tools/testing/selftests/mm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index b8d7e966f44c..aa720c52c650 100644 --- a/tools/testing/selftests/mm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c @@ -84,7 +84,7 @@ int get_proc_locked_vm_size(void) int get_proc_page_size(unsigned long addr) { FILE *smaps; - char *line; + char *line = NULL; unsigned long mmupage_size = 0; size_t size; diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 8f9850a71f54..e2e206339967 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -4,7 +4,6 @@ bind_timewait bind_wildcard busy_poller cmsg_sender -diag_uid epoll_busy_poll fin_ack_lat gro @@ -18,7 +17,6 @@ ipv6_flowlabel ipv6_flowlabel_mgr ipv6_fragmentation log.txt -msg_oob msg_zerocopy netlink-dumps nettest @@ -35,9 +33,6 @@ reuseport_bpf_numa reuseport_dualstack rxtimestamp sctp_hello -scm_inq -scm_pidfd -scm_rights sk_bind_sendto_listen sk_connect_zero_addr sk_so_peek_off @@ -45,7 +40,6 @@ skf_net_off socket so_incoming_cpu so_netns_cookie -so_peek_off so_txtime so_rcv_listener stress_reuseport_listen @@ -65,4 +59,3 @@ txtimestamp udpgso udpgso_bench_rx udpgso_bench_tx -unix_connect diff --git a/tools/testing/selftests/net/af_unix/.gitignore b/tools/testing/selftests/net/af_unix/.gitignore new file mode 100644 index 000000000000..973176644103 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/.gitignore @@ -0,0 +1,9 @@ +diag_uid +msg_oob +scm_inq +scm_pidfd +scm_rights +so_peek_off +unix_connect +unix_connreset +unix_listen diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 2889403e3546..57d159803a3a 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -13,6 +13,8 @@ TEST_GEN_PROGS := \ scm_rights \ so_peek_off \ unix_connect \ + unix_connreset \ + unix_listen \ # end of TEST_GEN_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/unix_connreset.c b/tools/testing/selftests/net/af_unix/unix_connreset.c new file mode 100644 index 000000000000..bffef2b54bfd --- /dev/null +++ b/tools/testing/selftests/net/af_unix/unix_connreset.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Selftest for AF_UNIX socket close and ECONNRESET behaviour. + * + * This test verifies: + * 1. SOCK_STREAM returns EOF when the peer closes normally. + * 2. SOCK_STREAM returns ECONNRESET if peer closes with unread data. + * 3. SOCK_SEQPACKET returns EOF when the peer closes normally. + * 4. SOCK_SEQPACKET returns ECONNRESET if the peer closes with unread data. + * 5. SOCK_DGRAM does not return ECONNRESET when the peer closes. + * + * These tests document the intended Linux behaviour. + * + */ + +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <fcntl.h> +#include <unistd.h> +#include <errno.h> +#include <sys/socket.h> +#include <sys/un.h> +#include "../../kselftest_harness.h" + +#define SOCK_PATH "/tmp/af_unix_connreset.sock" + +static void remove_socket_file(void) +{ + unlink(SOCK_PATH); +} + +FIXTURE(unix_sock) +{ + int server; + int client; + int child; +}; + +FIXTURE_VARIANT(unix_sock) +{ + int socket_type; + const char *name; +}; + +FIXTURE_VARIANT_ADD(unix_sock, stream) { + .socket_type = SOCK_STREAM, + .name = "SOCK_STREAM", +}; + +FIXTURE_VARIANT_ADD(unix_sock, dgram) { + .socket_type = SOCK_DGRAM, + .name = "SOCK_DGRAM", +}; + +FIXTURE_VARIANT_ADD(unix_sock, seqpacket) { + .socket_type = SOCK_SEQPACKET, + .name = "SOCK_SEQPACKET", +}; + +FIXTURE_SETUP(unix_sock) +{ + struct sockaddr_un addr = {}; + int err; + + addr.sun_family = AF_UNIX; + strcpy(addr.sun_path, SOCK_PATH); + remove_socket_file(); + + self->server = socket(AF_UNIX, variant->socket_type, 0); + ASSERT_LT(-1, self->server); + + err = bind(self->server, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(0, err); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + err = listen(self->server, 1); + ASSERT_EQ(0, err); + } + + self->client = socket(AF_UNIX, variant->socket_type | SOCK_NONBLOCK, 0); + ASSERT_LT(-1, self->client); + + err = connect(self->client, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(0, err); +} + +FIXTURE_TEARDOWN(unix_sock) +{ + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) + close(self->child); + + close(self->client); + close(self->server); + remove_socket_file(); +} + +/* Test 1: peer closes normally */ +TEST_F(unix_sock, eof) +{ + char buf[16] = {}; + ssize_t n; + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + self->child = accept(self->server, NULL, NULL); + ASSERT_LT(-1, self->child); + + close(self->child); + } else { + close(self->server); + } + + n = recv(self->client, buf, sizeof(buf), 0); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + ASSERT_EQ(0, n); + } else { + ASSERT_EQ(-1, n); + ASSERT_EQ(EAGAIN, errno); + } +} + +/* Test 2: peer closes with unread data */ +TEST_F(unix_sock, reset_unread_behavior) +{ + char buf[16] = {}; + ssize_t n; + + /* Send data that will remain unread */ + send(self->client, "hello", 5, 0); + + if (variant->socket_type == SOCK_DGRAM) { + /* No real connection, just close the server */ + close(self->server); + } else { + self->child = accept(self->server, NULL, NULL); + ASSERT_LT(-1, self->child); + + /* Peer closes before client reads */ + close(self->child); + } + + n = recv(self->client, buf, sizeof(buf), 0); + ASSERT_EQ(-1, n); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + ASSERT_EQ(ECONNRESET, errno); + } else { + ASSERT_EQ(EAGAIN, errno); + } +} + +/* Test 3: closing unaccepted (embryo) server socket should reset client. */ +TEST_F(unix_sock, reset_closed_embryo) +{ + char buf[16] = {}; + ssize_t n; + + if (variant->socket_type == SOCK_DGRAM) + SKIP(return, "This test only applies to SOCK_STREAM and SOCK_SEQPACKET"); + + /* Close server without accept()ing */ + close(self->server); + + n = recv(self->client, buf, sizeof(buf), 0); + + ASSERT_EQ(-1, n); + ASSERT_EQ(ECONNRESET, errno); +} + +TEST_HARNESS_MAIN + diff --git a/tools/testing/selftests/net/af_unix/unix_listen.c b/tools/testing/selftests/net/af_unix/unix_listen.c new file mode 100644 index 000000000000..416fa3e5bfe9 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/unix_listen.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Tests for the state checks in AF_UNIX listen(). + * + * The central case is a regression test: listen() on a bound socket that + * is already connected (i.e. not in TCP_CLOSE or TCP_LISTEN state) must + * fail with EINVAL. A prior change accidentally let it return success + * without doing anything, because a helper called in between reset the + * error code to 0. The neighbouring checks (unbound, already listening) + * are tested too so they cannot silently regress the same way. + * + * Every case runs for both listenable socket types (SOCK_STREAM and + * SOCK_SEQPACKET) and both pathname and abstract addresses. + */ +#define _GNU_SOURCE + +#include <errno.h> +#include <stddef.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> + +#include <sys/socket.h> +#include <sys/un.h> + +#include "kselftest_harness.h" + +#define SK_NAME "unix_listen_sk" +#define SRV_NAME "unix_listen_srv" + +FIXTURE(unix_listen) +{ + int sk; /* socket under test */ + int server; /* a listening peer, when a test needs one */ + struct sockaddr_un addr, srv_addr; + socklen_t addrlen, srv_addrlen; +}; + +FIXTURE_VARIANT(unix_listen) +{ + int type; + int abstract; +}; + +FIXTURE_VARIANT_ADD(unix_listen, stream_pathname) +{ + .type = SOCK_STREAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(unix_listen, stream_abstract) +{ + .type = SOCK_STREAM, + .abstract = 1, +}; + +FIXTURE_VARIANT_ADD(unix_listen, seqpacket_pathname) +{ + .type = SOCK_SEQPACKET, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(unix_listen, seqpacket_abstract) +{ + .type = SOCK_SEQPACKET, + .abstract = 1, +}; + +/* Fill @addr with a pathname or abstract address named @name. */ +static socklen_t unix_set_addr(struct sockaddr_un *addr, const char *name, + int abstract) +{ + size_t len = strlen(name); + + memset(addr, 0, sizeof(*addr)); + addr->sun_family = AF_UNIX; + /* An abstract address leads with a NUL and has no filesystem entry. */ + memcpy(addr->sun_path + (abstract ? 1 : 0), name, len); + + return offsetof(struct sockaddr_un, sun_path) + len + 1; +} + +FIXTURE_SETUP(unix_listen) +{ + self->sk = -1; + self->server = -1; + self->addrlen = unix_set_addr(&self->addr, SK_NAME, variant->abstract); + self->srv_addrlen = unix_set_addr(&self->srv_addr, SRV_NAME, + variant->abstract); +} + +FIXTURE_TEARDOWN(unix_listen) +{ + if (self->sk >= 0) + close(self->sk); + if (self->server >= 0) + close(self->server); + + /* Pathname sockets leave a filesystem entry behind; abstract ones do not. */ + if (!variant->abstract) { + remove(SK_NAME); + remove(SRV_NAME); + } +} + +/* A bound socket in TCP_CLOSE is the normal, allowed case. */ +TEST_F(unix_listen, bound_is_ok) +{ + int err; + + self->sk = socket(AF_UNIX, variant->type, 0); + ASSERT_LE(0, self->sk); + + err = bind(self->sk, (struct sockaddr *)&self->addr, self->addrlen); + ASSERT_EQ(0, err); + + err = listen(self->sk, 8); + EXPECT_EQ(0, err); +} + +/* Listening again on an already-listening socket (TCP_LISTEN) is allowed. */ +TEST_F(unix_listen, relisten_is_ok) +{ + int err; + + self->sk = socket(AF_UNIX, variant->type, 0); + ASSERT_LE(0, self->sk); + + err = bind(self->sk, (struct sockaddr *)&self->addr, self->addrlen); + ASSERT_EQ(0, err); + + err = listen(self->sk, 8); + ASSERT_EQ(0, err); + + err = listen(self->sk, 16); + EXPECT_EQ(0, err); +} + +/* listen() on an unbound socket fails: there is nothing to listen on. */ +TEST_F(unix_listen, unbound_is_einval) +{ + int err; + + self->sk = socket(AF_UNIX, variant->type, 0); + ASSERT_LE(0, self->sk); + + err = listen(self->sk, 8); + EXPECT_EQ(-1, err); + EXPECT_EQ(EINVAL, errno); +} + +/* + * The regression: a bound socket that has already been connected is not in + * TCP_CLOSE or TCP_LISTEN, so listen() must reject it with EINVAL rather + * than quietly succeeding. + */ +TEST_F(unix_listen, connected_is_einval) +{ + int err; + + self->server = socket(AF_UNIX, variant->type, 0); + ASSERT_LE(0, self->server); + + err = bind(self->server, (struct sockaddr *)&self->srv_addr, + self->srv_addrlen); + ASSERT_EQ(0, err); + + err = listen(self->server, 8); + ASSERT_EQ(0, err); + + self->sk = socket(AF_UNIX, variant->type, 0); + ASSERT_LE(0, self->sk); + + /* Bind first so the unbound check does not mask the state check. */ + err = bind(self->sk, (struct sockaddr *)&self->addr, self->addrlen); + ASSERT_EQ(0, err); + + err = connect(self->sk, (struct sockaddr *)&self->srv_addr, + self->srv_addrlen); + ASSERT_EQ(0, err); + + err = listen(self->sk, 8); + EXPECT_EQ(-1, err); + EXPECT_EQ(EINVAL, errno); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 874f17763536..19c9afa0be71 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -5172,7 +5172,8 @@ FIXTURE_SETUP(UPROBE) ASSERT_GE(bit, 0); } - offset = get_uprobe_offset(variant->uretprobe ? probed_uretprobe : probed_uprobe); + offset = get_uprobe_offset(variant->uretprobe ? (void *)probed_uretprobe + : (void *)probed_uprobe); ASSERT_GE(offset, 0); if (variant->uretprobe)