diff options
135 files changed, 1309 insertions, 878 deletions
diff --git a/.gitignore b/.gitignore index 3ec73ead6757..20dce5c3b9e0 100644 --- a/.gitignore +++ b/.gitignore @@ -39,6 +39,7 @@ *.o.* *.patch *.rmeta +*.rpm *.rsi *.s *.so diff --git a/Documentation/maintainer/maintainer-entry-profile.rst b/Documentation/maintainer/maintainer-entry-profile.rst index 93b2ae6c34a9..cfd37f31077f 100644 --- a/Documentation/maintainer/maintainer-entry-profile.rst +++ b/Documentation/maintainer/maintainer-entry-profile.rst @@ -104,3 +104,4 @@ to do something different in the near future. ../riscv/patch-acceptance ../driver-api/media/maintainer-entry-profile ../driver-api/vfio-pci-device-specific-driver-acceptance + ../nvme/feature-and-quirk-policy diff --git a/Documentation/nvme/feature-and-quirk-policy.rst b/Documentation/nvme/feature-and-quirk-policy.rst new file mode 100644 index 000000000000..c01d836d8e41 --- /dev/null +++ b/Documentation/nvme/feature-and-quirk-policy.rst @@ -0,0 +1,77 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================================= +Linux NVMe feature and and quirk policy +======================================= + +This file explains the policy used to decide what is supported by the +Linux NVMe driver and what is not. + + +Introduction +============ + +NVM Express is an open collection of standards and information. + +The Linux NVMe host driver in drivers/nvme/host/ supports devices +implementing the NVM Express (NVMe) family of specifications, which +currently consists of a number of documents: + + - the NVMe Base specification + - various Command Set specifications (e.g. NVM Command Set) + - various Transport specifications (e.g. PCIe, Fibre Channel, RDMA, TCP) + - the NVMe Management Interface specification + +See https://nvmexpress.org/developers/ for the NVMe specifications. + + +Supported features +================== + +NVMe is a large suite of specifications, and contains features that are only +useful or suitable for specific use-cases. It is important to note that Linux +does not aim to implement every feature in the specification. Every additional +feature implemented introduces more code, more maintenance and potentially more +bugs. Hence there is an inherent tradeoff between functionality and +maintainability of the NVMe host driver. + +Any feature implemented in the Linux NVMe host driver must support the +following requirements: + + 1. The feature is specified in a release version of an official NVMe + specification, or in a ratified Technical Proposal (TP) that is + available on NVMe website. Or if it is not directly related to the + on-wire protocol, does not contradict any of the NVMe specifications. + 2. Does not conflict with the Linux architecture, nor the design of the + NVMe host driver. + 3. Has a clear, indisputable value-proposition and a wide consensus across + the community. + +Vendor specific extensions are generally not supported in the NVMe host +driver. + +It is strongly recommended to work with the Linux NVMe and block layer +maintainers and get feedback on specification changes that are intended +to be used by the Linux NVMe host driver in order to avoid conflict at a +later stage. + + +Quirks +====== + +Sometimes implementations of open standards fail to correctly implement parts +of the standards. Linux uses identifier-based quirks to work around such +implementation bugs. The intent of quirks is to deal with widely available +hardware, usually consumer, which Linux users can't use without these quirks. +Typically these implementations are not or only superficially tested with Linux +by the hardware manufacturer. + +The Linux NVMe maintainers decide ad hoc whether to quirk implementations +based on the impact of the problem to Linux users and how it impacts +maintainability of the driver. In general quirks are a last resort, if no +firmware updates or other workarounds are available from the vendor. + +Quirks will not be added to the Linux kernel for hardware that isn't available +on the mass market. Hardware that fails qualification for enterprise Linux +distributions, ChromeOS, Android or other consumers of the Linux kernel +should be fixed before it is shipped instead of relying on Linux quirks. diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 0dd5d8733dd5..deb494f759ed 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5343,9 +5343,9 @@ KVM_XEN_ATTR_TYPE_SHARED_INFO 32 vCPUs in the shared_info page, KVM does not automatically do so and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO be used explicitly even when the vcpu_info for a given vCPU resides at the - "default" location in the shared_info page. This is because KVM is - not aware of the Xen CPU id which is used as the index into the - vcpu_info[] array, so cannot know the correct default location. + "default" location in the shared_info page. This is because KVM may + not be aware of the Xen CPU id which is used as the index into the + vcpu_info[] array, so may know the correct default location. Note that the shared info page may be constantly written to by KVM; it contains the event channel bitmap used to deliver interrupts to @@ -5356,23 +5356,29 @@ KVM_XEN_ATTR_TYPE_SHARED_INFO any vCPU has been running or any event channel interrupts can be routed to the guest. + Setting the gfn to KVM_XEN_INVALID_GFN will disable the shared info + page. + KVM_XEN_ATTR_TYPE_UPCALL_VECTOR Sets the exception vector used to deliver Xen event channel upcalls. This is the HVM-wide vector injected directly by the hypervisor (not through the local APIC), typically configured by a guest via - HVM_PARAM_CALLBACK_IRQ. + HVM_PARAM_CALLBACK_IRQ. This can be disabled again (e.g. for guest + SHUTDOWN_soft_reset) by setting it to zero. KVM_XEN_ATTR_TYPE_EVTCHN This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures an outbound port number for interception of EVTCHNOP_send requests - from the guest. A given sending port number may be directed back - to a specified vCPU (by APIC ID) / port / priority on the guest, - or to trigger events on an eventfd. The vCPU and priority can be - changed by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, - but other fields cannot change for a given sending port. A port - mapping is removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags - field. + from the guest. A given sending port number may be directed back to + a specified vCPU (by APIC ID) / port / priority on the guest, or to + trigger events on an eventfd. The vCPU and priority can be changed + by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but but other + fields cannot change for a given sending port. A port mapping is + removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags field. Passing + KVM_XEN_EVTCHN_RESET in the flags field removes all interception of + outbound event channels. The values of the flags field are mutually + exclusive and cannot be combined as a bitmask. KVM_XEN_ATTR_TYPE_XEN_VERSION This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates @@ -5388,7 +5394,7 @@ KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG support for KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG. It enables the XEN_RUNSTATE_UPDATE flag which allows guest vCPUs to safely read other vCPUs' vcpu_runstate_info. Xen guests enable this feature via - the VM_ASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist + the VMASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist hypercall. 4.127 KVM_XEN_HVM_GET_ATTR @@ -5446,15 +5452,18 @@ KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO As with the shared_info page for the VM, the corresponding page may be dirtied at any time if event channel interrupt delivery is enabled, so userspace should always assume that the page is dirty without relying - on dirty logging. + on dirty logging. Setting the gpa to KVM_XEN_INVALID_GPA will disable + the vcpu_info. KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO Sets the guest physical address of an additional pvclock structure for a given vCPU. This is typically used for guest vsyscall support. + Setting the gpa to KVM_XEN_INVALID_GPA will disable the structure. KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR Sets the guest physical address of the vcpu_runstate_info for a given vCPU. This is how a Xen guest tracks CPU state such as steal time. + Setting the gpa to KVM_XEN_INVALID_GPA will disable the runstate area. KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT Sets the runstate (RUNSTATE_running/_runnable/_blocked/_offline) of @@ -5487,7 +5496,8 @@ KVM_XEN_VCPU_ATTR_TYPE_TIMER This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the event channel port/priority for the VIRQ_TIMER of the vCPU, as well - as allowing a pending timer to be saved/restored. + as allowing a pending timer to be saved/restored. Setting the timer + port to zero disables kernel handling of the singleshot timer. KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates @@ -5495,7 +5505,8 @@ KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR per-vCPU local APIC upcall vector, configured by a Xen guest with the HVMOP_set_evtchn_upcall_vector hypercall. This is typically used by Windows guests, and is distinct from the HVM-wide upcall - vector configured with HVM_PARAM_CALLBACK_IRQ. + vector configured with HVM_PARAM_CALLBACK_IRQ. It is disabled by + setting the vector to zero. 4.129 KVM_XEN_VCPU_GET_ATTR @@ -6577,11 +6588,6 @@ Please note that the kernel is allowed to use the kvm_run structure as the primary storage for certain register types. Therefore, the kernel may use the values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set. -:: - - }; - - 6. Capabilities that can be enabled on vCPUs ============================================ diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 845a561629f1..a3ca76f9be75 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -16,17 +16,26 @@ The acquisition orders for mutexes are as follows: - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring them together is quite rare. -- Unlike kvm->slots_lock, kvm->slots_arch_lock is released before - synchronize_srcu(&kvm->srcu). Therefore kvm->slots_arch_lock - can be taken inside a kvm->srcu read-side critical section, - while kvm->slots_lock cannot. - - kvm->mn_active_invalidate_count ensures that pairs of invalidate_range_start() and invalidate_range_end() callbacks use the same memslots array. kvm->slots_lock and kvm->slots_arch_lock are taken on the waiting side in install_new_memslots, so MMU notifiers must not take either kvm->slots_lock or kvm->slots_arch_lock. +For SRCU: + +- ``synchronize_srcu(&kvm->srcu)`` is called _inside_ + the kvm->slots_lock critical section, therefore kvm->slots_lock + cannot be taken inside a kvm->srcu read-side critical section. + Instead, kvm->slots_arch_lock is released before the call + to ``synchronize_srcu()`` and _can_ be taken inside a + kvm->srcu read-side critical section. + +- kvm->lock is taken inside kvm->srcu, therefore + ``synchronize_srcu(&kvm->srcu)`` cannot be called inside + a kvm->lock critical section. If you cannot delay the + call until after kvm->lock is released, use ``call_srcu``. + On x86: - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock diff --git a/MAINTAINERS b/MAINTAINERS index f61eb221415b..7f86d02cb427 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11468,7 +11468,7 @@ F: arch/x86/kvm/hyperv.* F: arch/x86/kvm/kvm_onhyperv.* F: arch/x86/kvm/svm/hyperv.* F: arch/x86/kvm/svm/svm_onhyperv.* -F: arch/x86/kvm/vmx/evmcs.* +F: arch/x86/kvm/vmx/hyperv.* KVM X86 Xen (KVM/Xen) M: David Woodhouse <dwmw2@infradead.org> @@ -14916,6 +14916,7 @@ L: linux-nvme@lists.infradead.org S: Supported W: http://git.infradead.org/nvme.git T: git://git.infradead.org/nvme.git +F: Documentation/nvme/ F: drivers/nvme/host/ F: drivers/nvme/common/ F: include/linux/nvme* @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* @@ -297,7 +297,7 @@ no-compiler-targets := $(no-dot-config-targets) install dtbs_install \ headers_install modules_install kernelrelease image_name no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease \ image_name -single-targets := %.a %.i %.rsi %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/ +single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.rsi %.s %.symtypes %/ config-build := mixed-build := diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index cfd4c95b9f04..669d9e4f2901 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -386,8 +386,8 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) { unsigned long *reg, val, vaddr; char buffer[MAX_INSN_SIZE]; + enum insn_mmio_type mmio; struct insn insn = {}; - enum mmio_type mmio; int size, extend_size; u8 extend_val = 0; @@ -402,10 +402,10 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EINVAL; mmio = insn_decode_mmio(&insn, &size); - if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED)) + if (WARN_ON_ONCE(mmio == INSN_MMIO_DECODE_FAILED)) return -EINVAL; - if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { + if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) { reg = insn_get_modrm_reg_ptr(&insn, regs); if (!reg) return -EINVAL; @@ -426,23 +426,23 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) /* Handle writes first */ switch (mmio) { - case MMIO_WRITE: + case INSN_MMIO_WRITE: memcpy(&val, reg, size); if (!mmio_write(size, ve->gpa, val)) return -EIO; return insn.length; - case MMIO_WRITE_IMM: + case INSN_MMIO_WRITE_IMM: val = insn.immediate.value; if (!mmio_write(size, ve->gpa, val)) return -EIO; return insn.length; - case MMIO_READ: - case MMIO_READ_ZERO_EXTEND: - case MMIO_READ_SIGN_EXTEND: + case INSN_MMIO_READ: + case INSN_MMIO_READ_ZERO_EXTEND: + case INSN_MMIO_READ_SIGN_EXTEND: /* Reads are handled below */ break; - case MMIO_MOVS: - case MMIO_DECODE_FAILED: + case INSN_MMIO_MOVS: + case INSN_MMIO_DECODE_FAILED: /* * MMIO was accessed with an instruction that could not be * decoded or handled properly. It was likely not using io.h @@ -459,15 +459,15 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EIO; switch (mmio) { - case MMIO_READ: + case INSN_MMIO_READ: /* Zero-extend for 32-bit operation */ extend_size = size == 4 ? sizeof(*reg) : 0; break; - case MMIO_READ_ZERO_EXTEND: + case INSN_MMIO_READ_ZERO_EXTEND: /* Zero extend based on operand size */ extend_size = insn.opnd_bytes; break; - case MMIO_READ_SIGN_EXTEND: + case INSN_MMIO_READ_SIGN_EXTEND: /* Sign extend based on operand size */ extend_size = insn.opnd_bytes; if (size == 1 && val & BIT(7)) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index d6f3703e4119..4386b10682ce 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -1387,7 +1387,7 @@ static int __init amd_core_pmu_init(void) * numbered counter following it. */ for (i = 0; i < x86_pmu.num_counters - 1; i += 2) - even_ctr_mask |= 1 << i; + even_ctr_mask |= BIT_ULL(i); pair_constraint = (struct event_constraint) __EVENT_CONSTRAINT(0, even_ctr_mask, 0, diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index f07faa61c7f3..54368a43abf6 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -32,16 +32,16 @@ int insn_fetch_from_user_inatomic(struct pt_regs *regs, bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE], int buf_size); -enum mmio_type { - MMIO_DECODE_FAILED, - MMIO_WRITE, - MMIO_WRITE_IMM, - MMIO_READ, - MMIO_READ_ZERO_EXTEND, - MMIO_READ_SIGN_EXTEND, - MMIO_MOVS, +enum insn_mmio_type { + INSN_MMIO_DECODE_FAILED, + INSN_MMIO_WRITE, + INSN_MMIO_WRITE_IMM, + INSN_MMIO_READ, + INSN_MMIO_READ_ZERO_EXTEND, + INSN_MMIO_READ_SIGN_EXTEND, + INSN_MMIO_MOVS, }; -enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes); +enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes); #endif /* _ASM_X86_INSN_EVAL_H */ diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 7d2c75ec9a8c..ffea98f9064b 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -119,7 +119,7 @@ static bool is_coretext(const struct core_text *ct, void *addr) return within_module_coretext(addr); } -static __init_or_module bool skip_addr(void *dest) +static bool skip_addr(void *dest) { if (dest == error_entry) return true; @@ -181,7 +181,7 @@ static const u8 nops[] = { 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, }; -static __init_or_module void *patch_dest(void *dest, bool direct) +static void *patch_dest(void *dest, bool direct) { unsigned int tsize = SKL_TMPL_SIZE; u8 *pad = dest - tsize; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d970ddb0cc65..bca0bd8f4846 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1981,6 +1981,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); task_update_spec_tif(task); + if (task == current) + indirect_branch_prediction_barrier(); break; default: return -ERANGE; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 9730c88530fc..305514431f26 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -401,10 +401,8 @@ int crash_load_segments(struct kimage *image) kbuf.buf_align = ELF_CORE_HEADER_ALIGN; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); - if (ret) { - vfree((void *)image->elf_headers); + if (ret) return ret; - } image->elf_load_addr = kbuf.mem; pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", image->elf_load_addr, kbuf.bufsz, kbuf.memsz); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 66299682b6b7..b36f3c367cb2 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -37,6 +37,7 @@ #include <linux/extable.h> #include <linux/kdebug.h> #include <linux/kallsyms.h> +#include <linux/kgdb.h> #include <linux/ftrace.h> #include <linux/kasan.h> #include <linux/moduleloader.h> @@ -281,12 +282,15 @@ static int can_probe(unsigned long paddr) if (ret < 0) return 0; +#ifdef CONFIG_KGDB /* - * Another debugging subsystem might insert this breakpoint. - * In that case, we can't recover it. + * If there is a dynamically installed kgdb sw breakpoint, + * this function should not be probed. */ - if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && + kgdb_has_hit_break(addr)) return 0; +#endif addr += insn.length; } diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index e6b8c5362b94..e57e07b0edb6 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -15,6 +15,7 @@ #include <linux/extable.h> #include <linux/kdebug.h> #include <linux/kallsyms.h> +#include <linux/kgdb.h> #include <linux/ftrace.h> #include <linux/objtool.h> #include <linux/pgtable.h> @@ -279,19 +280,6 @@ static int insn_is_indirect_jump(struct insn *insn) return ret; } -static bool is_padding_int3(unsigned long addr, unsigned long eaddr) -{ - unsigned char ops; - - for (; addr < eaddr; addr++) { - if (get_kernel_nofault(ops, (void *)addr) < 0 || - ops != INT3_INSN_OPCODE) - return false; - } - - return true; -} - /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { @@ -334,15 +322,15 @@ static int can_optimize(unsigned long paddr) ret = insn_decode_kernel(&insn, (void *)recovered_insn); if (ret < 0) return 0; - +#ifdef CONFIG_KGDB /* - * In the case of detecting unknown breakpoint, this could be - * a padding INT3 between functions. Let's check that all the - * rest of the bytes are also INT3. + * If there is a dynamically installed kgdb sw breakpoint, + * this function should not be probed. */ - if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) - return is_padding_int3(addr, paddr - offset + size) ? 1 : 0; - + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && + kgdb_has_hit_break(addr)) + return 0; +#endif /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index a428c62330d3..679026a640ef 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -1536,32 +1536,32 @@ static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt, static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct insn *insn = &ctxt->insn; + enum insn_mmio_type mmio; unsigned int bytes = 0; - enum mmio_type mmio; enum es_result ret; u8 sign_byte; long *reg_data; mmio = insn_decode_mmio(insn, &bytes); - if (mmio == MMIO_DECODE_FAILED) + if (mmio == INSN_MMIO_DECODE_FAILED) return ES_DECODE_FAILED; - if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { + if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) { reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs); if (!reg_data) return ES_DECODE_FAILED; } switch (mmio) { - case MMIO_WRITE: + case INSN_MMIO_WRITE: memcpy(ghcb->shared_buffer, reg_data, bytes); ret = vc_do_mmio(ghcb, ctxt, bytes, false); break; - case MMIO_WRITE_IMM: + case INSN_MMIO_WRITE_IMM: memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes); ret = vc_do_mmio(ghcb, ctxt, bytes, false); break; - case MMIO_READ: + case INSN_MMIO_READ: ret = vc_do_mmio(ghcb, ctxt, bytes, true); if (ret) break; @@ -1572,7 +1572,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) memcpy(reg_data, ghcb->shared_buffer, bytes); break; - case MMIO_READ_ZERO_EXTEND: + case INSN_MMIO_READ_ZERO_EXTEND: ret = vc_do_mmio(ghcb, ctxt, bytes, true); if (ret) break; @@ -1581,7 +1581,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) memset(reg_data, 0, insn->opnd_bytes); memcpy(reg_data, ghcb->shared_buffer, bytes); break; - case MMIO_READ_SIGN_EXTEND: + case INSN_MMIO_READ_SIGN_EXTEND: ret = vc_do_mmio(ghcb, ctxt, bytes, true); if (ret) break; @@ -1600,7 +1600,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) memset(reg_data, sign_byte, insn->opnd_bytes); memcpy(reg_data, ghcb->shared_buffer, bytes); break; - case MMIO_MOVS: + case INSN_MMIO_MOVS: ret = vc_handle_mmio_movs(ctxt, bytes); break; default: diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 2c7f2a26421e..e8296942a868 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1769,6 +1769,7 @@ static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_ba } struct kvm_hv_hcall { + /* Hypercall input data */ u64 param; u64 ingpa; u64 outgpa; @@ -1779,12 +1780,21 @@ struct kvm_hv_hcall { bool fast; bool rep; sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS]; + + /* + * Current read offset when KVM reads hypercall input data gradually, + * either offset in bytes from 'ingpa' for regular hypercalls or the + * number of already consumed 'XMM halves' for 'fast' hypercalls. + */ + union { + gpa_t data_offset; + int consumed_xmm_halves; + }; }; static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, - u16 orig_cnt, u16 cnt_cap, u64 *data, - int consumed_xmm_halves, gpa_t offset) + u16 orig_cnt, u16 cnt_cap, u64 *data) { /* * Preserve the original count when ignoring entries via a "cap", KVM @@ -1799,11 +1809,11 @@ static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, * Each XMM holds two sparse banks, but do not count halves that * have already been consumed for hypercall parameters. */ - if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves) + if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - hc->consumed_xmm_halves) return HV_STATUS_INVALID_HYPERCALL_INPUT; for (i = 0; i < cnt; i++) { - j = i + consumed_xmm_halves; + j = i + hc->consumed_xmm_halves; if (j % 2) data[i] = sse128_hi(hc->xmm[j / 2]); else @@ -1812,27 +1822,24 @@ static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, return 0; } - return kvm_read_guest(kvm, hc->ingpa + offset, data, + return kvm_read_guest(kvm, hc->ingpa + hc->data_offset, data, cnt * sizeof(*data)); } static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc, - u64 *sparse_banks, int consumed_xmm_halves, - gpa_t offset) + u64 *sparse_banks) { if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS) return -EINVAL; /* Cap var_cnt to ignore banks that cannot contain a legal VP index. */ return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS, - sparse_banks, consumed_xmm_halves, offset); + sparse_banks); } -static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[], - int consumed_xmm_halves, gpa_t offset) +static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[]) { - return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, - entries, consumed_xmm_halves, offset); + return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, entries); } static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu, @@ -1926,8 +1933,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) struct kvm_vcpu *v; unsigned long i; bool all_cpus; - int consumed_xmm_halves = 0; - gpa_t data_offset; /* * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS @@ -1955,12 +1960,12 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush.address_space = hc->ingpa; flush.flags = hc->outgpa; flush.processor_mask = sse128_lo(hc->xmm[0]); - consumed_xmm_halves = 1; + hc->consumed_xmm_halves = 1; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush, sizeof(flush)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; - data_offset = sizeof(flush); + hc->data_offset = sizeof(flush); } trace_kvm_hv_flush_tlb(flush.processor_mask, @@ -1985,12 +1990,12 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush_ex.flags = hc->outgpa; memcpy(&flush_ex.hv_vp_set, &hc->xmm[0], sizeof(hc->xmm[0])); - consumed_xmm_halves = 2; + hc->consumed_xmm_halves = 2; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex, sizeof(flush_ex)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; - data_offset = sizeof(flush_ex); + hc->data_offset = sizeof(flush_ex); } trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask, @@ -2009,8 +2014,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (!hc->var_cnt) goto ret_success; - if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, - consumed_xmm_halves, data_offset)) + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } @@ -2021,8 +2025,10 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) * consumed_xmm_halves to make sure TLB flush entries are read * from the correct offset. */ - data_offset += hc->var_cnt * sizeof(sparse_banks[0]); - consumed_xmm_halves += hc->var_cnt; + if (hc->fast) + hc->consumed_xmm_halves += hc->var_cnt; + else + hc->data_offset += hc->var_cnt * sizeof(sparse_banks[0]); } if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE || @@ -2030,8 +2036,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) { tlb_flush_entries = NULL; } else { - if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries, - consumed_xmm_halves, data_offset)) + if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries)) return HV_STATUS_INVALID_HYPERCALL_INPUT; tlb_flush_entries = __tlb_flush_entries; } @@ -2180,9 +2185,13 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (!hc->var_cnt) goto ret_success; - if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, 1, - offsetof(struct hv_send_ipi_ex, - vp_set.bank_contents))) + if (!hc->fast) + hc->data_offset = offsetof(struct hv_send_ipi_ex, + vp_set.bank_contents); + else + hc->consumed_xmm_halves = 1; + + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 0687162c4f22..3742d9adacfc 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -426,8 +426,9 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); if (irq.trig_mode && - kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, - irq.dest_id, irq.dest_mode)) + (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + irq.dest_id, irq.dest_mode) || + kvm_apic_pending_eoi(vcpu, irq.vector))) __set_bit(irq.vector, ioapic_handled_vectors); } } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 28e3769066e2..58c3242fcc7a 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -188,11 +188,11 @@ static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu) extern struct static_key_false_deferred apic_hw_disabled; -static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic) +static inline bool kvm_apic_hw_enabled(struct kvm_lapic *apic) { if (static_branch_unlikely(&apic_hw_disabled.key)) return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE; - return MSR_IA32_APICBASE_ENABLE; + return true; } extern struct static_key_false_deferred apic_sw_disabled; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 1f03701b943a..6f54dc9409c9 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -363,7 +363,7 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, * A shadow-present leaf SPTE may be non-writable for 4 possible reasons: * * 1. To intercept writes for dirty logging. KVM write-protects huge pages - * so that they can be split be split down into the dirty logging + * so that they can be split down into the dirty logging * granularity (4KiB) whenever the guest writes to them. KVM also * write-protects 4KiB pages so that writes can be recorded in the dirty log * (e.g. if not using PML). SPTEs are write-protected for dirty logging diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 771210ce5181..d6df38d371a0 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1074,7 +1074,9 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int ret = RET_PF_FIXED; bool wrprot = false; - WARN_ON(sp->role.level != fault->goal_level); + if (WARN_ON_ONCE(sp->role.level != fault->goal_level)) + return RET_PF_RETRY; + if (unlikely(!fault->slot)) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); else @@ -1173,9 +1175,6 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, iter.old_spte, iter.level); - if (iter.level == fault->goal_level) - break; - /* * If SPTE has been frozen by another thread, just give up and * retry, avoiding unnecessary page table allocation and free. @@ -1183,6 +1182,9 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (is_removed_spte(iter.old_spte)) goto retry; + if (iter.level == fault->goal_level) + goto map_target_level; + /* Step down into the lower level page table if it exists. */ if (is_shadow_present_pte(iter.old_spte) && !is_large_pte(iter.old_spte)) @@ -1203,8 +1205,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) r = tdp_mmu_link_sp(kvm, &iter, sp, true); /* - * Also force the guest to retry the access if the upper level SPTEs - * aren't in place. + * Force the guest to retry if installing an upper level SPTE + * failed, e.g. because a different task modified the SPTE. */ if (r) { tdp_mmu_free_sp(sp); @@ -1214,11 +1216,20 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->huge_page_disallowed && fault->req_level >= iter.level) { spin_lock(&kvm->arch.tdp_mmu_pages_lock); - track_possible_nx_huge_page(kvm, sp); + if (sp->nx_huge_page_disallowed) + track_possible_nx_huge_page(kvm, sp); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } } + /* + * The walk aborted before reaching the target level, e.g. because the + * iterator detected an upper level SPTE was frozen during traversal. + */ + WARN_ON_ONCE(iter.level == fault->goal_level); + goto retry; + +map_target_level: ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter); retry: diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 684393c22105..eb594620dd75 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -238,7 +238,8 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return false; /* recalibrate sample period and check if it's accepted by perf core */ - if (perf_event_period(pmc->perf_event, + if (is_sampling_event(pmc->perf_event) && + perf_event_period(pmc->perf_event, get_sample_period(pmc, pmc->counter))) return false; diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 85ff3c0588ba..cdb91009701d 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -140,7 +140,8 @@ static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) static inline void pmc_update_sample_period(struct kvm_pmc *pmc) { - if (!pmc->perf_event || pmc->is_paused) + if (!pmc->perf_event || pmc->is_paused || + !is_sampling_event(pmc->perf_event)) return; perf_event_period(pmc->perf_event, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index b6f4411b613e..d93c715cda6a 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5296,10 +5296,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); - kvm_vcpu_write_guest(vcpu, - vmptr + offsetof(struct vmcs12, - launch_state), - &zero, sizeof(zero)); + /* + * Silently ignore memory errors on VMCLEAR, Intel's pseudocode + * for VMCLEAR includes a "ensure that data for VMCS referenced + * by the operand is in memory" clause that guards writes to + * memory, i.e. doing nothing for I/O is architecturally valid. + * + * FIXME: Suppress failures if and only if no memslot is found, + * i.e. exit to userspace if __copy_to_user() fails. + */ + (void)kvm_vcpu_write_guest(vcpu, + vmptr + offsetof(struct vmcs12, + launch_state), + &zero, sizeof(zero)); } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { nested_release_evmcs(vcpu); } @@ -6873,7 +6882,8 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_RDSEED_EXITING | SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_TSC_SCALING; + SECONDARY_EXEC_TSC_SCALING | + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; /* * We can emulate "VMCS shadowing," even if the hardware diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index fe5615fd8295..fc9008dbed33 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4459,6 +4459,13 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, * controls for features that are/aren't exposed to the guest. */ if (nested) { + /* + * All features that can be added or removed to VMX MSRs must + * be supported in the first place for nested virtualization. + */ + if (WARN_ON_ONCE(!(vmcs_config.nested.secondary_ctls_high & control))) + enabled = false; + if (enabled) vmx->nested.msrs.secondary_ctls_high |= control; else diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 312aea1854ae..da4bbd043a7b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13132,6 +13132,9 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e) { if (r == X86EMUL_PROPAGATE_FAULT) { + if (KVM_BUG_ON(!e, vcpu->kvm)) + return -EIO; + kvm_inject_emulated_page_fault(vcpu, e); return 1; } diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index d7af40240248..2e29bdc2949c 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -41,7 +41,7 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) int ret = 0; int idx = srcu_read_lock(&kvm->srcu); - if (gfn == GPA_INVALID) { + if (gfn == KVM_XEN_INVALID_GFN) { kvm_gpc_deactivate(gpc); goto out; } @@ -659,7 +659,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) if (kvm->arch.xen.shinfo_cache.active) data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa); else - data->u.shared_info.gfn = GPA_INVALID; + data->u.shared_info.gfn = KVM_XEN_INVALID_GFN; r = 0; break; @@ -705,7 +705,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) BUILD_BUG_ON(offsetof(struct vcpu_info, time) != offsetof(struct compat_vcpu_info, time)); - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); r = 0; break; @@ -719,7 +719,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache); r = 0; break; @@ -739,7 +739,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) r = -EOPNOTSUPP; break; } - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { r = 0; deactivate_out: kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache); @@ -937,7 +937,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) if (vcpu->arch.xen.vcpu_info_cache.active) data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa; else - data->u.gpa = GPA_INVALID; + data->u.gpa = KVM_XEN_INVALID_GPA; r = 0; break; @@ -945,7 +945,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) if (vcpu->arch.xen.vcpu_time_info_cache.active) data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa; else - data->u.gpa = GPA_INVALID; + data->u.gpa = KVM_XEN_INVALID_GPA; r = 0; break; @@ -1069,6 +1069,7 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 : kvm->arch.xen_hvm_config.blob_size_32; u8 *page; + int ret; if (page_num >= blob_size) return 1; @@ -1079,10 +1080,10 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) if (IS_ERR(page)) return PTR_ERR(page); - if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) { - kfree(page); + ret = kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE); + kfree(page); + if (ret) return 1; - } } return 0; } @@ -1183,30 +1184,22 @@ static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, u64 param, u64 *r) { - int idx, i; struct sched_poll sched_poll; evtchn_port_t port, *ports; - gpa_t gpa; + struct x86_exception e; + int i; if (!lapic_in_kernel(vcpu) || !(vcpu->kvm->arch.xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND)) return false; - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - if (!gpa) { - *r = -EFAULT; - return true; - } - if (IS_ENABLED(CONFIG_64BIT) && !longmode) { struct compat_sched_poll sp32; /* Sanity check that the compat struct definition is correct */ BUILD_BUG_ON(sizeof(sp32) != 16); - if (kvm_vcpu_read_guest(vcpu, gpa, &sp32, sizeof(sp32))) { + if (kvm_read_guest_virt(vcpu, param, &sp32, sizeof(sp32), &e)) { *r = -EFAULT; return true; } @@ -1220,8 +1213,8 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, sched_poll.nr_ports = sp32.nr_ports; sched_poll.timeout = sp32.timeout; } else { - if (kvm_vcpu_read_guest(vcpu, gpa, &sched_poll, - sizeof(sched_poll))) { + if (kvm_read_guest_virt(vcpu, param, &sched_poll, + sizeof(sched_poll), &e)) { *r = -EFAULT; return true; } @@ -1243,18 +1236,13 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, } else ports = &port; + if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports, + sched_poll.nr_ports * sizeof(*ports), &e)) { + *r = -EFAULT; + return true; + } + for (i = 0; i < sched_poll.nr_ports; i++) { - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, - (gva_t)(sched_poll.ports + i), - NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, - &ports[i], sizeof(port))) { - *r = -EFAULT; - goto out; - } if (ports[i] >= max_evtchn_port(vcpu->kvm)) { *r = -EINVAL; goto out; @@ -1330,9 +1318,8 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, int vcpu_id, u64 param, u64 *r) { struct vcpu_set_singleshot_timer oneshot; + struct x86_exception e; s64 delta; - gpa_t gpa; - int idx; if (!kvm_xen_timer_enabled(vcpu)) return false; @@ -1343,9 +1330,6 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, *r = -EINVAL; return true; } - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); /* * The only difference for 32-bit compat is the 4 bytes of @@ -1363,9 +1347,8 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, BUILD_BUG_ON(sizeof_field(struct compat_vcpu_set_singleshot_timer, flags) != sizeof_field(struct vcpu_set_singleshot_timer, flags)); - if (!gpa || - kvm_vcpu_read_guest(vcpu, gpa, &oneshot, longmode ? sizeof(oneshot) : - sizeof(struct compat_vcpu_set_singleshot_timer))) { + if (kvm_read_guest_virt(vcpu, param, &oneshot, longmode ? sizeof(oneshot) : + sizeof(struct compat_vcpu_set_singleshot_timer), &e)) { *r = -EFAULT; return true; } @@ -1825,20 +1808,20 @@ static int kvm_xen_eventfd_update(struct kvm *kvm, { u32 port = data->u.evtchn.send_port; struct evtchnfd *evtchnfd; + int ret; - if (!port || port >= max_evtchn_port(kvm)) - return -EINVAL; - + /* Protect writes to evtchnfd as well as the idr lookup. */ mutex_lock(&kvm->lock); evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port); - mutex_unlock(&kvm->lock); + ret = -ENOENT; if (!evtchnfd) - return -ENOENT; + goto out_unlock; /* For an UPDATE, nothing may change except the priority/vcpu */ + ret = -EINVAL; if (evtchnfd->type != data->u.evtchn.type) - return -EINVAL; + goto out_unlock; /* * Port cannot change, and if it's zero that was an eventfd @@ -1846,20 +1829,21 @@ static int kvm_xen_eventfd_update(struct kvm *kvm, */ if (!evtchnfd->deliver.port.port || evtchnfd->deliver.port.port != data->u.evtchn.deliver.port.port) - return -EINVAL; + goto out_unlock; /* We only support 2 level event channels for now */ if (data->u.evtchn.deliver.port.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) - return -EINVAL; + goto out_unlock; - mutex_lock(&kvm->lock); evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority; if (evtchnfd->deliver.port.vcpu_id != data->u.evtchn.deliver.port.vcpu) { evtchnfd->deliver.port.vcpu_id = data->u.evtchn.deliver.port.vcpu; evtchnfd->deliver.port.vcpu_idx = -1; } + ret = 0; +out_unlock: mutex_unlock(&kvm->lock); - return 0; + return ret; } /* @@ -1871,12 +1855,9 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, { u32 port = data->u.evtchn.send_port; struct eventfd_ctx *eventfd = NULL; - struct evtchnfd *evtchnfd = NULL; + struct evtchnfd *evtchnfd; int ret = -EINVAL; - if (!port || port >= max_evtchn_port(kvm)) - return -EINVAL; - evtchnfd = kzalloc(sizeof(struct evtchnfd), GFP_KERNEL); if (!evtchnfd) return -ENOMEM; @@ -1952,8 +1933,7 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port) if (!evtchnfd) return -ENOENT; - if (kvm) - synchronize_srcu(&kvm->srcu); + synchronize_srcu(&kvm->srcu); if (!evtchnfd->deliver.port.port) eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx); kfree(evtchnfd); @@ -1962,18 +1942,42 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port) static int kvm_xen_eventfd_reset(struct kvm *kvm) { - struct evtchnfd *evtchnfd; + struct evtchnfd *evtchnfd, **all_evtchnfds; int i; + int n = 0; mutex_lock(&kvm->lock); + + /* + * Because synchronize_srcu() cannot be called inside the + * critical section, first collect all the evtchnfd objects + * in an array as they are removed from evtchn_ports. + */ + idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) + n++; + + all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL); + if (!all_evtchnfds) { + mutex_unlock(&kvm->lock); + return -ENOMEM; + } + + n = 0; idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) { + all_evtchnfds[n++] = evtchnfd; idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port); - synchronize_srcu(&kvm->srcu); + } + mutex_unlock(&kvm->lock); + + synchronize_srcu(&kvm->srcu); + + while (n--) { + evtchnfd = all_evtchnfds[n]; if (!evtchnfd->deliver.port.port) eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx); kfree(evtchnfd); } - mutex_unlock(&kvm->lock); + kfree(all_evtchnfds); return 0; } @@ -2002,20 +2006,22 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r) { struct evtchnfd *evtchnfd; struct evtchn_send send; - gpa_t gpa; - int idx; - - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); + struct x86_exception e; - if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, &send, sizeof(send))) { + /* Sanity check: this structure is the same for 32-bit and 64-bit */ + BUILD_BUG_ON(sizeof(send) != 4); + if (kvm_read_guest_virt(vcpu, param, &send, sizeof(send), &e)) { *r = -EFAULT; return true; } - /* The evtchn_ports idr is protected by vcpu->kvm->srcu */ + /* + * evtchnfd is protected by kvm->srcu; the idr lookup instead + * is protected by RCU. + */ + rcu_read_lock(); evtchnfd = idr_find(&vcpu->kvm->arch.xen.evtchn_ports, send.port); + rcu_read_unlock(); if (!evtchnfd) return false; diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 21104c41cba0..558a605929db 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1595,16 +1595,16 @@ bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs, * Returns: * * Type of the instruction. Size of the memory operand is stored in - * @bytes. If decode failed, MMIO_DECODE_FAILED returned. + * @bytes. If decode failed, INSN_MMIO_DECODE_FAILED returned. */ -enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) +enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes) { - enum mmio_type type = MMIO_DECODE_FAILED; + enum insn_mmio_type type = INSN_MMIO_DECODE_FAILED; *bytes = 0; if (insn_get_opcode(insn)) - return MMIO_DECODE_FAILED; + return INSN_MMIO_DECODE_FAILED; switch (insn->opcode.bytes[0]) { case 0x88: /* MOV m8,r8 */ @@ -1613,7 +1613,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0x89: /* MOV m16/m32/m64, r16/m32/m64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_WRITE; + type = INSN_MMIO_WRITE; break; case 0xc6: /* MOV m8, imm8 */ @@ -1622,7 +1622,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xc7: /* MOV m16/m32/m64, imm16/imm32/imm64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_WRITE_IMM; + type = INSN_MMIO_WRITE_IMM; break; case 0x8a: /* MOV r8, m8 */ @@ -1631,7 +1631,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0x8b: /* MOV r16/r32/r64, m16/m32/m64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_READ; + type = INSN_MMIO_READ; break; case 0xa4: /* MOVS m8, m8 */ @@ -1640,7 +1640,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xa5: /* MOVS m16/m32/m64, m16/m32/m64 */ if (!*bytes) *bytes = insn->opnd_bytes; - type = MMIO_MOVS; + type = INSN_MMIO_MOVS; break; case 0x0f: /* Two-byte instruction */ @@ -1651,7 +1651,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xb7: /* MOVZX r32/r64, m16 */ if (!*bytes) *bytes = 2; - type = MMIO_READ_ZERO_EXTEND; + type = INSN_MMIO_READ_ZERO_EXTEND; break; case 0xbe: /* MOVSX r16/r32/r64, m8 */ @@ -1660,7 +1660,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes) case 0xbf: /* MOVSX r32/r64, m16 */ if (!*bytes) *bytes = 2; - type = MMIO_READ_SIGN_EXTEND; + type = INSN_MMIO_READ_SIGN_EXTEND; break; } break; diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S index a1f9416bf67a..6ff2f56cb0f7 100644 --- a/arch/x86/lib/iomap_copy_64.S +++ b/arch/x86/lib/iomap_copy_64.S @@ -10,6 +10,6 @@ */ SYM_FUNC_START(__iowrite32_copy) movl %edx,%ecx - rep movsd + rep movsl RET SYM_FUNC_END(__iowrite32_copy) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 16f43bbc575a..ccf2204477a5 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5317,8 +5317,8 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync) unsigned long flags; spin_lock_irqsave(&bfqd->lock, flags); - bfq_exit_bfqq(bfqd, bfqq); bic_set_bfqq(bic, NULL, is_sync); + bfq_exit_bfqq(bfqd, bfqq); spin_unlock_irqrestore(&bfqd->lock, flags); } } diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 30d8fd03fec7..97b711e57bff 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -70,11 +70,7 @@ module_param(device_id_scheme, bool, 0444); static int only_lcd = -1; module_param(only_lcd, int, 0444); -/* - * Display probing is known to take up to 5 seconds, so delay the fallback - * backlight registration by 5 seconds + 3 seconds for some extra margin. - */ -static int register_backlight_delay = 8; +static int register_backlight_delay; module_param(register_backlight_delay, int, 0444); MODULE_PARM_DESC(register_backlight_delay, "Delay in seconds before doing fallback (non GPU driver triggered) " @@ -2176,6 +2172,17 @@ static bool should_check_lcd_flag(void) return false; } +/* + * At least one graphics driver has reported that no LCD is connected + * via the native interface. cancel the registration for fallback acpi_video0. + * If another driver still deems this necessary, it can explicitly register it. + */ +void acpi_video_report_nolcd(void) +{ + cancel_delayed_work(&video_bus_register_backlight_work); +} +EXPORT_SYMBOL(acpi_video_report_nolcd); + int acpi_video_register(void) { int ret = 0; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index f27914aedbd5..16dcd31d124f 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -432,10 +432,24 @@ static const struct dmi_system_id asus_laptop[] = { DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"), }, }, + { + .ident = "Asus ExpertBook B2502", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "B2502CBA"), + }, + }, { } }; -static const struct dmi_system_id lenovo_82ra[] = { +static const struct dmi_system_id lenovo_laptop[] = { + { + .ident = "LENOVO IdeaPad Flex 5 14ALC7", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82R9"), + }, + }, { .ident = "LENOVO IdeaPad Flex 5 16ALC7", .matches = { @@ -446,6 +460,17 @@ static const struct dmi_system_id lenovo_82ra[] = { { } }; +static const struct dmi_system_id schenker_gm_rg[] = { + { + .ident = "XMG CORE 15 (M22)", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"), + DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"), + }, + }, + { } +}; + struct irq_override_cmp { const struct dmi_system_id *system; unsigned char irq; @@ -458,8 +483,9 @@ struct irq_override_cmp { static const struct irq_override_cmp override_table[] = { { medion_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, { asus_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, - { lenovo_82ra, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, - { lenovo_82ra, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, + { lenovo_laptop, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, + { lenovo_laptop, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, + { schenker_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, }; static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index a934bbc9dd37..1b78c7434492 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -34,6 +34,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/platform_data/x86/nvidia-wmi-ec-backlight.h> +#include <linux/pnp.h> #include <linux/types.h> #include <linux/workqueue.h> #include <acpi/video.h> @@ -105,6 +106,26 @@ static bool nvidia_wmi_ec_supported(void) } #endif +static bool apple_gmux_backlight_present(void) +{ + struct acpi_device *adev; + struct device *dev; + + adev = acpi_dev_get_first_match_dev(GMUX_ACPI_HID, NULL, -1); + if (!adev) + return false; + + dev = acpi_get_first_physical_node(adev); + if (!dev) + return false; + + /* + * drivers/platform/x86/apple-gmux.c only supports old style + * Apple GMUX with an IO-resource. + */ + return pnp_get_resource(to_pnp_dev(dev), IORESOURCE_IO, 0) != NULL; +} + /* Force to use vendor driver when the ACPI device is known to be * buggy */ static int video_detect_force_vendor(const struct dmi_system_id *d) @@ -767,7 +788,7 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) if (nvidia_wmi_ec_present) return acpi_backlight_nvidia_wmi_ec; - if (apple_gmux_present()) + if (apple_gmux_backlight_present()) return acpi_backlight_apple_gmux; /* Use ACPI video if available, except when native should be preferred. */ diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index 5350c73564b6..c7afce465a07 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -28,10 +28,6 @@ static bool sleep_no_lps0 __read_mostly; module_param(sleep_no_lps0, bool, 0644); MODULE_PARM_DESC(sleep_no_lps0, "Do not use the special LPS0 device interface"); -static bool prefer_microsoft_dsm_guid __read_mostly; -module_param(prefer_microsoft_dsm_guid, bool, 0644); -MODULE_PARM_DESC(prefer_microsoft_dsm_guid, "Prefer using Microsoft GUID in LPS0 device _DSM evaluation"); - static const struct acpi_device_id lps0_device_ids[] = { {"PNP0D80", }, {"", }, @@ -369,27 +365,15 @@ out: } struct amd_lps0_hid_device_data { - const unsigned int rev_id; const bool check_off_by_one; - const bool prefer_amd_guid; }; static const struct amd_lps0_hid_device_data amd_picasso = { - .rev_id = 0, .check_off_by_one = true, - .prefer_amd_guid = false, }; static const struct amd_lps0_hid_device_data amd_cezanne = { - .rev_id = 0, - .check_off_by_one = false, - .prefer_amd_guid = false, -}; - -static const struct amd_lps0_hid_device_data amd_rembrandt = { - .rev_id = 2, .check_off_by_one = false, - .prefer_amd_guid = true, }; static const struct acpi_device_id amd_hid_ids[] = { @@ -397,69 +381,27 @@ static const struct acpi_device_id amd_hid_ids[] = { {"AMD0005", (kernel_ulong_t)&amd_picasso, }, {"AMDI0005", (kernel_ulong_t)&amd_picasso, }, {"AMDI0006", (kernel_ulong_t)&amd_cezanne, }, - {"AMDI0007", (kernel_ulong_t)&amd_rembrandt, }, {} }; -static int lps0_prefer_microsoft(const struct dmi_system_id *id) +static int lps0_prefer_amd(const struct dmi_system_id *id) { - pr_debug("Preferring Microsoft GUID.\n"); - prefer_microsoft_dsm_guid = true; + pr_debug("Using AMD GUID w/ _REV 2.\n"); + rev_id = 2; return 0; } - static const struct dmi_system_id s2idle_dmi_table[] __initconst = { { /* - * ASUS TUF Gaming A17 FA707RE - * https://bugzilla.kernel.org/show_bug.cgi?id=216101 - */ - .callback = lps0_prefer_microsoft, - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ASUS TUF Gaming A17"), - }, - }, - { - /* ASUS ROG Zephyrus G14 (2022) */ - .callback = lps0_prefer_microsoft, - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ROG Zephyrus G14 GA402"), - }, - }, - { - /* - * Lenovo Yoga Slim 7 Pro X 14ARH7 - * https://bugzilla.kernel.org/show_bug.cgi?id=216473 : 82V2 - * https://bugzilla.kernel.org/show_bug.cgi?id=216438 : 82TL - */ - .callback = lps0_prefer_microsoft, - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "82"), - }, - }, - { - /* - * ASUSTeK COMPUTER INC. ROG Flow X13 GV301RE_GV301RE - * https://gitlab.freedesktop.org/drm/amd/-/issues/2148 + * AMD Rembrandt based HP EliteBook 835/845/865 G9 + * Contains specialized AML in AMD/_REV 2 path to avoid + * triggering a bug in Qualcomm WLAN firmware. This may be + * removed in the future if that firmware is fixed. */ - .callback = lps0_prefer_microsoft, + .callback = lps0_prefer_amd, .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow X13 GV301"), - }, - }, - { - /* - * ASUSTeK COMPUTER INC. ROG Flow X16 GV601RW_GV601RW - * https://gitlab.freedesktop.org/drm/amd/-/issues/2148 - */ - .callback = lps0_prefer_microsoft, - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow X16 GV601"), + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_BOARD_NAME, "8990"), }, }, {} @@ -484,16 +426,14 @@ static int lps0_device_attach(struct acpi_device *adev, if (dev_id->id[0]) data = (const struct amd_lps0_hid_device_data *) dev_id->driver_data; else - data = &amd_rembrandt; - rev_id = data->rev_id; + data = &amd_cezanne; lps0_dsm_func_mask = validate_dsm(adev->handle, ACPI_LPS0_DSM_UUID_AMD, rev_id, &lps0_dsm_guid); if (lps0_dsm_func_mask > 0x3 && data->check_off_by_one) { lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1; acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n", ACPI_LPS0_DSM_UUID_AMD, lps0_dsm_func_mask); - } else if (lps0_dsm_func_mask_microsoft > 0 && data->prefer_amd_guid && - !prefer_microsoft_dsm_guid) { + } else if (lps0_dsm_func_mask_microsoft > 0 && rev_id) { lps0_dsm_func_mask_microsoft = -EINVAL; acpi_handle_debug(adev->handle, "_DSM Using AMD method\n"); } @@ -501,8 +441,7 @@ static int lps0_device_attach(struct acpi_device *adev, rev_id = 1; lps0_dsm_func_mask = validate_dsm(adev->handle, ACPI_LPS0_DSM_UUID, rev_id, &lps0_dsm_guid); - if (!prefer_microsoft_dsm_guid) - lps0_dsm_func_mask_microsoft = -EINVAL; + lps0_dsm_func_mask_microsoft = -EINVAL; } if (lps0_dsm_func_mask < 0 && lps0_dsm_func_mask_microsoft < 0) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 0cfd0ec6229b..14a1c0d14916 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -83,6 +83,7 @@ enum board_ids { static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static void ahci_remove_one(struct pci_dev *dev); static void ahci_shutdown_one(struct pci_dev *dev); +static void ahci_intel_pcs_quirk(struct pci_dev *pdev, struct ahci_host_priv *hpriv); static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline); static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class, @@ -676,6 +677,25 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev, ahci_save_initial_config(&pdev->dev, hpriv); } +static int ahci_pci_reset_controller(struct ata_host *host) +{ + struct pci_dev *pdev = to_pci_dev(host->dev); + struct ahci_host_priv *hpriv = host->private_data; + int rc; + + rc = ahci_reset_controller(host); + if (rc) + return rc; + + /* + * If platform firmware failed to enable ports, try to enable + * them here. + */ + ahci_intel_pcs_quirk(pdev, hpriv); + + return 0; +} + static void ahci_pci_init_controller(struct ata_host *host) { struct ahci_host_priv *hpriv = host->private_data; @@ -870,7 +890,7 @@ static int ahci_pci_device_runtime_resume(struct device *dev) struct ata_host *host = pci_get_drvdata(pdev); int rc; - rc = ahci_reset_controller(host); + rc = ahci_pci_reset_controller(host); if (rc) return rc; ahci_pci_init_controller(host); @@ -906,7 +926,7 @@ static int ahci_pci_device_resume(struct device *dev) ahci_mcp89_apple_enable(pdev); if (pdev->dev.power.power_state.event == PM_EVENT_SUSPEND) { - rc = ahci_reset_controller(host); + rc = ahci_pci_reset_controller(host); if (rc) return rc; @@ -1784,12 +1804,6 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* save initial config */ ahci_pci_save_initial_config(pdev, hpriv); - /* - * If platform firmware failed to enable ports, try to enable - * them here. - */ - ahci_intel_pcs_quirk(pdev, hpriv); - /* prepare host */ if (hpriv->cap & HOST_CAP_NCQ) { pi.flags |= ATA_FLAG_NCQ; @@ -1899,7 +1913,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) return rc; - rc = ahci_reset_controller(host); + rc = ahci_pci_reset_controller(host); if (rc) return rc; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 68bd2f7961b3..6a77fa917428 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -315,22 +315,35 @@ static void virtio_commit_rqs(struct blk_mq_hw_ctx *hctx) virtqueue_notify(vq->vq); } +static blk_status_t virtblk_fail_to_queue(struct request *req, int rc) +{ + virtblk_cleanup_cmd(req); + switch (rc) { + case -ENOSPC: + return BLK_STS_DEV_RESOURCE; + case -ENOMEM: + return BLK_STS_RESOURCE; + default: + return BLK_STS_IOERR; + } +} + static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx, struct virtio_blk *vblk, struct request *req, struct virtblk_req *vbr) { blk_status_t status; + int num; status = virtblk_setup_cmd(vblk->vdev, req, vbr); if (unlikely(status)) return status; - vbr->sg_table.nents = virtblk_map_data(hctx, req, vbr); - if (unlikely(vbr->sg_table.nents < 0)) { - virtblk_cleanup_cmd(req); - return BLK_STS_RESOURCE; - } + num = virtblk_map_data(hctx, req, vbr); + if (unlikely(num < 0)) + return virtblk_fail_to_queue(req, -ENOMEM); + vbr->sg_table.nents = num; blk_mq_start_request(req); @@ -364,15 +377,7 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_stop_hw_queue(hctx); spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags); virtblk_unmap_data(req, vbr); - virtblk_cleanup_cmd(req); - switch (err) { - case -ENOSPC: - return BLK_STS_DEV_RESOURCE; - case -ENOMEM: - return BLK_STS_RESOURCE; - default: - return BLK_STS_IOERR; - } + return virtblk_fail_to_queue(req, err); } if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq)) @@ -991,7 +996,7 @@ static int virtblk_probe(struct virtio_device *vdev) blk_queue_max_segments(q, sg_elems); /* No real sector limit. */ - blk_queue_max_hw_sectors(q, -1U); + blk_queue_max_hw_sectors(q, UINT_MAX); max_size = virtio_max_dma_size(vdev); diff --git a/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c index e553ccadbcbc..e5876286828b 100644 --- a/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c @@ -239,7 +239,8 @@ static int virtio_crypto_alg_skcipher_close_session( pr_err("virtio_crypto: Close session failed status: %u, session_id: 0x%llx\n", ctrl_status->status, destroy_session->session_id); - return -EINVAL; + err = -EINVAL; + goto out; } err = 0; 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 50c783e19f5a..86bc23a67d97 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4361,6 +4361,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) amdgpu_set_panel_orientation(&aconnector->base); } + /* If we didn't find a panel, notify the acpi video detection */ + if (dm->adev->flags & AMD_IS_APU && dm->num_of_edps == 0) + acpi_video_report_nolcd(); + /* Software is initialized. Now we can register interrupt handlers. */ switch (adev->asic_type) { #if defined(CONFIG_DRM_AMD_DC_SI) diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c index fce69fa446d5..2cbc1292ab38 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c @@ -41,9 +41,11 @@ #include "i915_drv.h" #include "i915_reg.h" +#include "intel_de.h" #include "intel_display_types.h" #include "intel_dsi.h" #include "intel_dsi_vbt.h" +#include "intel_gmbus_regs.h" #include "vlv_dsi.h" #include "vlv_dsi_regs.h" #include "vlv_sideband.h" @@ -377,6 +379,85 @@ static void icl_exec_gpio(struct intel_connector *connector, drm_dbg_kms(&dev_priv->drm, "Skipping ICL GPIO element execution\n"); } +enum { + MIPI_RESET_1 = 0, + MIPI_AVDD_EN_1, + MIPI_BKLT_EN_1, + MIPI_AVEE_EN_1, + MIPI_VIO_EN_1, + MIPI_RESET_2, + MIPI_AVDD_EN_2, + MIPI_BKLT_EN_2, + MIPI_AVEE_EN_2, + MIPI_VIO_EN_2, +}; + +static void icl_native_gpio_set_value(struct drm_i915_private *dev_priv, + int gpio, bool value) +{ + int index; + + if (drm_WARN_ON(&dev_priv->drm, DISPLAY_VER(dev_priv) == 11 && gpio >= MIPI_RESET_2)) + return; + + switch (gpio) { + case MIPI_RESET_1: + case MIPI_RESET_2: + index = gpio == MIPI_RESET_1 ? HPD_PORT_A : HPD_PORT_B; + + /* + * Disable HPD to set the pin to output, and set output + * value. The HPD pin should not be enabled for DSI anyway, + * assuming the board design and VBT are sane, and the pin isn't + * used by a non-DSI encoder. + * + * The locking protects against concurrent SHOTPLUG_CTL_DDI + * modifications in irq setup and handling. + */ + spin_lock_irq(&dev_priv->irq_lock); + intel_de_rmw(dev_priv, SHOTPLUG_CTL_DDI, + SHOTPLUG_CTL_DDI_HPD_ENABLE(index) | + SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(index), + value ? SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(index) : 0); + spin_unlock_irq(&dev_priv->irq_lock); + break; + case MIPI_AVDD_EN_1: + case MIPI_AVDD_EN_2: + index = gpio == MIPI_AVDD_EN_1 ? 0 : 1; + + intel_de_rmw(dev_priv, PP_CONTROL(index), PANEL_POWER_ON, + value ? PANEL_POWER_ON : 0); + break; + case MIPI_BKLT_EN_1: + case MIPI_BKLT_EN_2: + index = gpio == MIPI_BKLT_EN_1 ? 0 : 1; + + intel_de_rmw(dev_priv, PP_CONTROL(index), EDP_BLC_ENABLE, + value ? EDP_BLC_ENABLE : 0); + break; + case MIPI_AVEE_EN_1: + case MIPI_AVEE_EN_2: + index = gpio == MIPI_AVEE_EN_1 ? 1 : 2; + + intel_de_rmw(dev_priv, GPIO(dev_priv, index), + GPIO_CLOCK_VAL_OUT, + GPIO_CLOCK_DIR_MASK | GPIO_CLOCK_DIR_OUT | + GPIO_CLOCK_VAL_MASK | (value ? GPIO_CLOCK_VAL_OUT : 0)); + break; + case MIPI_VIO_EN_1: + case MIPI_VIO_EN_2: + index = gpio == MIPI_VIO_EN_1 ? 1 : 2; + + intel_de_rmw(dev_priv, GPIO(dev_priv, index), + GPIO_DATA_VAL_OUT, + GPIO_DATA_DIR_MASK | GPIO_DATA_DIR_OUT | + GPIO_DATA_VAL_MASK | (value ? GPIO_DATA_VAL_OUT : 0)); + break; + default: + MISSING_CASE(gpio); + } +} + static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) { struct drm_device *dev = intel_dsi->base.base.dev; @@ -384,8 +465,7 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) struct intel_connector *connector = intel_dsi->attached_connector; u8 gpio_source, gpio_index = 0, gpio_number; bool value; - - drm_dbg_kms(&dev_priv->drm, "\n"); + bool native = DISPLAY_VER(dev_priv) >= 11; if (connector->panel.vbt.dsi.seq_version >= 3) gpio_index = *data++; @@ -398,10 +478,18 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) else gpio_source = 0; + if (connector->panel.vbt.dsi.seq_version >= 4 && *data & BIT(1)) + native = false; + /* pull up/down */ value = *data++ & 1; - if (DISPLAY_VER(dev_priv) >= 11) + drm_dbg_kms(&dev_priv->drm, "GPIO index %u, number %u, source %u, native %s, set to %s\n", + gpio_index, gpio_number, gpio_source, str_yes_no(native), str_on_off(value)); + + if (native) + icl_native_gpio_set_value(dev_priv, gpio_number, value); + else if (DISPLAY_VER(dev_priv) >= 11) icl_exec_gpio(connector, gpio_source, gpio_index, value); else if (IS_VALLEYVIEW(dev_priv)) vlv_exec_gpio(connector, gpio_source, gpio_number, value); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index da09767fda07..f266b68cf012 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -730,32 +730,69 @@ static int eb_reserve(struct i915_execbuffer *eb) bool unpinned; /* - * Attempt to pin all of the buffers into the GTT. - * This is done in 2 phases: + * We have one more buffers that we couldn't bind, which could be due to + * various reasons. To resolve this we have 4 passes, with every next + * level turning the screws tighter: * - * 1. Unbind all objects that do not match the GTT constraints for - * the execbuffer (fenceable, mappable, alignment etc). - * 2. Bind new objects. + * 0. Unbind all objects that do not match the GTT constraints for the + * execbuffer (fenceable, mappable, alignment etc). Bind all new + * objects. This avoids unnecessary unbinding of later objects in order + * to make room for the earlier objects *unless* we need to defragment. * - * This avoid unnecessary unbinding of later objects in order to make - * room for the earlier objects *unless* we need to defragment. + * 1. Reorder the buffers, where objects with the most restrictive + * placement requirements go first (ignoring fixed location buffers for + * now). For example, objects needing the mappable aperture (the first + * 256M of GTT), should go first vs objects that can be placed just + * about anywhere. Repeat the previous pass. * - * Defragmenting is skipped if all objects are pinned at a fixed location. + * 2. Consider buffers that are pinned at a fixed location. Also try to + * evict the entire VM this time, leaving only objects that we were + * unable to lock. Try again to bind the buffers. (still using the new + * buffer order). + * + * 3. We likely have object lock contention for one or more stubborn + * objects in the VM, for which we need to evict to make forward + * progress (perhaps we are fighting the shrinker?). When evicting the + * VM this time around, anything that we can't lock we now track using + * the busy_bo, using the full lock (after dropping the vm->mutex to + * prevent deadlocks), instead of trylock. We then continue to evict the + * VM, this time with the stubborn object locked, which we can now + * hopefully unbind (if still bound in the VM). Repeat until the VM is + * evicted. Finally we should be able bind everything. */ - for (pass = 0; pass <= 2; pass++) { + for (pass = 0; pass <= 3; pass++) { int pin_flags = PIN_USER | PIN_VALIDATE; if (pass == 0) pin_flags |= PIN_NONBLOCK; if (pass >= 1) - unpinned = eb_unbind(eb, pass == 2); + unpinned = eb_unbind(eb, pass >= 2); if (pass == 2) { err = mutex_lock_interruptible(&eb->context->vm->mutex); if (!err) { - err = i915_gem_evict_vm(eb->context->vm, &eb->ww); + err = i915_gem_evict_vm(eb->context->vm, &eb->ww, NULL); + mutex_unlock(&eb->context->vm->mutex); + } + if (err) + return err; + } + + if (pass == 3) { +retry: + err = mutex_lock_interruptible(&eb->context->vm->mutex); + if (!err) { + struct drm_i915_gem_object *busy_bo = NULL; + + err = i915_gem_evict_vm(eb->context->vm, &eb->ww, &busy_bo); mutex_unlock(&eb->context->vm->mutex); + if (err && busy_bo) { + err = i915_gem_object_lock(busy_bo, &eb->ww); + i915_gem_object_put(busy_bo); + if (!err) + goto retry; + } } if (err) return err; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index c29efdef8313..0ad44f3868de 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -369,7 +369,7 @@ retry: if (vma == ERR_PTR(-ENOSPC)) { ret = mutex_lock_interruptible(&ggtt->vm.mutex); if (!ret) { - ret = i915_gem_evict_vm(&ggtt->vm, &ww); + ret = i915_gem_evict_vm(&ggtt->vm, &ww, NULL); mutex_unlock(&ggtt->vm.mutex); } if (ret) diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 767e329e1cc5..9c18b5f2e789 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -1109,9 +1109,15 @@ static void mmio_invalidate_full(struct intel_gt *gt) continue; if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { + u32 val = BIT(engine->instance); + + if (engine->class == VIDEO_DECODE_CLASS || + engine->class == VIDEO_ENHANCEMENT_CLASS || + engine->class == COMPUTE_CLASS) + val = _MASKED_BIT_ENABLE(val); intel_gt_mcr_multicast_write_fw(gt, xehp_regs[engine->class], - BIT(engine->instance)); + val); } else { rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); if (!i915_mmio_reg_offset(rb.reg)) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index 0c80ba51a4bd..2bcdd192f814 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -545,6 +545,32 @@ static int check_ccs_header(struct intel_gt *gt, return 0; } +static int try_firmware_load(struct intel_uc_fw *uc_fw, const struct firmware **fw) +{ + struct intel_gt *gt = __uc_fw_to_gt(uc_fw); + struct device *dev = gt->i915->drm.dev; + int err; + + err = firmware_request_nowarn(fw, uc_fw->file_selected.path, dev); + + if (err) + return err; + + if ((*fw)->size > INTEL_UC_RSVD_GGTT_PER_FW) { + drm_err(>->i915->drm, + "%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, + (*fw)->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K); + + /* try to find another blob to load */ + release_firmware(*fw); + *fw = NULL; + return -ENOENT; + } + + return 0; +} + /** * intel_uc_fw_fetch - fetch uC firmware * @uc_fw: uC firmware @@ -558,7 +584,6 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) struct intel_gt *gt = __uc_fw_to_gt(uc_fw); struct drm_i915_private *i915 = gt->i915; struct intel_uc_fw_file file_ideal; - struct device *dev = i915->drm.dev; struct drm_i915_gem_object *obj; const struct firmware *fw = NULL; bool old_ver = false; @@ -574,20 +599,9 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) __force_fw_fetch_failures(uc_fw, -EINVAL); __force_fw_fetch_failures(uc_fw, -ESTALE); - err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev); + err = try_firmware_load(uc_fw, &fw); memcpy(&file_ideal, &uc_fw->file_wanted, sizeof(file_ideal)); - if (!err && fw->size > INTEL_UC_RSVD_GGTT_PER_FW) { - drm_err(&i915->drm, - "%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n", - intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, - fw->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K); - - /* try to find another blob to load */ - release_firmware(fw); - err = -ENOENT; - } - /* Any error is terminal if overriding. Don't bother searching for older versions */ if (err && intel_uc_fw_is_overridden(uc_fw)) goto fail; @@ -608,7 +622,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) break; } - err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev); + err = try_firmware_load(uc_fw, &fw); } if (err) diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index f025ee4fa526..a4b4d9b7d26c 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -416,6 +416,11 @@ int i915_gem_evict_for_node(struct i915_address_space *vm, * @vm: Address space to cleanse * @ww: An optional struct i915_gem_ww_ctx. If not NULL, i915_gem_evict_vm * will be able to evict vma's locked by the ww as well. + * @busy_bo: Optional pointer to struct drm_i915_gem_object. If not NULL, then + * in the event i915_gem_evict_vm() is unable to trylock an object for eviction, + * then @busy_bo will point to it. -EBUSY is also returned. The caller must drop + * the vm->mutex, before trying again to acquire the contended lock. The caller + * also owns a reference to the object. * * This function evicts all vmas from a vm. * @@ -425,7 +430,8 @@ int i915_gem_evict_for_node(struct i915_address_space *vm, * To clarify: This is for freeing up virtual address space, not for freeing * memory in e.g. the shrinker. */ -int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww) +int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww, + struct drm_i915_gem_object **busy_bo) { int ret = 0; @@ -457,15 +463,22 @@ int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww) * the resv is shared among multiple objects, we still * need the object ref. */ - if (dying_vma(vma) || + if (!i915_gem_object_get_rcu(vma->obj) || (ww && (dma_resv_locking_ctx(vma->obj->base.resv) == &ww->ctx))) { __i915_vma_pin(vma); list_add(&vma->evict_link, &locked_eviction_list); continue; } - if (!i915_gem_object_trylock(vma->obj, ww)) + if (!i915_gem_object_trylock(vma->obj, ww)) { + if (busy_bo) { + *busy_bo = vma->obj; /* holds ref */ + ret = -EBUSY; + break; + } + i915_gem_object_put(vma->obj); continue; + } __i915_vma_pin(vma); list_add(&vma->evict_link, &eviction_list); @@ -473,25 +486,29 @@ int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww) if (list_empty(&eviction_list) && list_empty(&locked_eviction_list)) break; - ret = 0; /* Unbind locked objects first, before unlocking the eviction_list */ list_for_each_entry_safe(vma, vn, &locked_eviction_list, evict_link) { __i915_vma_unpin(vma); - if (ret == 0) + if (ret == 0) { ret = __i915_vma_unbind(vma); - if (ret != -EINTR) /* "Get me out of here!" */ - ret = 0; + if (ret != -EINTR) /* "Get me out of here!" */ + ret = 0; + } + if (!dying_vma(vma)) + i915_gem_object_put(vma->obj); } list_for_each_entry_safe(vma, vn, &eviction_list, evict_link) { __i915_vma_unpin(vma); - if (ret == 0) + if (ret == 0) { ret = __i915_vma_unbind(vma); - if (ret != -EINTR) /* "Get me out of here!" */ - ret = 0; + if (ret != -EINTR) /* "Get me out of here!" */ + ret = 0; + } i915_gem_object_unlock(vma->obj); + i915_gem_object_put(vma->obj); } } while (ret == 0); diff --git a/drivers/gpu/drm/i915/i915_gem_evict.h b/drivers/gpu/drm/i915/i915_gem_evict.h index e593c530f9bd..bf0ee0e4fe60 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.h +++ b/drivers/gpu/drm/i915/i915_gem_evict.h @@ -11,6 +11,7 @@ struct drm_mm_node; struct i915_address_space; struct i915_gem_ww_ctx; +struct drm_i915_gem_object; int __must_check i915_gem_evict_something(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww, @@ -23,6 +24,7 @@ int __must_check i915_gem_evict_for_node(struct i915_address_space *vm, struct drm_mm_node *node, unsigned int flags); int i915_gem_evict_vm(struct i915_address_space *vm, - struct i915_gem_ww_ctx *ww); + struct i915_gem_ww_ctx *ww, + struct drm_i915_gem_object **busy_bo); #endif /* __I915_GEM_EVICT_H__ */ diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index edfe363af838..91c533986041 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1974,7 +1974,10 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) if (ddi_hotplug_trigger) { u32 dig_hotplug_reg; + /* Locking due to DSI native GPIO sequences */ + spin_lock(&dev_priv->irq_lock); dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_DDI, 0, 0); + spin_unlock(&dev_priv->irq_lock); intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, ddi_hotplug_trigger, dig_hotplug_reg, diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 6da9784fe4a2..ccd1f864aa19 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -1129,7 +1129,6 @@ static const struct intel_gt_definition xelpmp_extra_gt[] = { {} }; -__maybe_unused static const struct intel_device_info mtl_info = { XE_HP_FEATURES, XE_LPDP_FEATURES, diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 8e1892d14774..916176872544 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -5988,6 +5988,7 @@ #define SHOTPLUG_CTL_DDI _MMIO(0xc4030) #define SHOTPLUG_CTL_DDI_HPD_ENABLE(hpd_pin) (0x8 << (_HPD_PIN_DDI(hpd_pin) * 4)) +#define SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(hpd_pin) (0x4 << (_HPD_PIN_DDI(hpd_pin) * 4)) #define SHOTPLUG_CTL_DDI_HPD_STATUS_MASK(hpd_pin) (0x3 << (_HPD_PIN_DDI(hpd_pin) * 4)) #define SHOTPLUG_CTL_DDI_HPD_NO_DETECT(hpd_pin) (0x0 << (_HPD_PIN_DDI(hpd_pin) * 4)) #define SHOTPLUG_CTL_DDI_HPD_SHORT_DETECT(hpd_pin) (0x1 << (_HPD_PIN_DDI(hpd_pin) * 4)) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 703fee6b5f75..3a33be5401ed 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1566,7 +1566,7 @@ static int __i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, * locked objects when called from execbuf when pinning * is removed. This would probably regress badly. */ - i915_gem_evict_vm(vm, NULL); + i915_gem_evict_vm(vm, NULL, NULL); mutex_unlock(&vm->mutex); } } while (1); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c index 8c6517d29b8e..37068542aafe 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c @@ -344,7 +344,7 @@ static int igt_evict_vm(void *arg) /* Everything is pinned, nothing should happen */ mutex_lock(&ggtt->vm.mutex); - err = i915_gem_evict_vm(&ggtt->vm, NULL); + err = i915_gem_evict_vm(&ggtt->vm, NULL, NULL); mutex_unlock(&ggtt->vm.mutex); if (err) { pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n", @@ -356,7 +356,7 @@ static int igt_evict_vm(void *arg) for_i915_gem_ww(&ww, err, false) { mutex_lock(&ggtt->vm.mutex); - err = i915_gem_evict_vm(&ggtt->vm, &ww); + err = i915_gem_evict_vm(&ggtt->vm, &ww, NULL); mutex_unlock(&ggtt->vm.mutex); } diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index bb0abbe4491c..4424f53a8a0a 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -953,7 +953,7 @@ int nvme_auth_init_ctrl(struct nvme_ctrl *ctrl) goto err_free_dhchap_secret; if (!ctrl->opts->dhchap_secret && !ctrl->opts->dhchap_ctrl_secret) - return ret; + return 0; ctrl->dhchap_ctxs = kvcalloc(ctrl_max_dhchaps(ctrl), sizeof(*chap), GFP_KERNEL); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 95c488ea91c3..7be562a4e1aa 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1074,6 +1074,18 @@ static u32 nvme_known_admin_effects(u8 opcode) return 0; } +static u32 nvme_known_nvm_effects(u8 opcode) +{ + switch (opcode) { + case nvme_cmd_write: + case nvme_cmd_write_zeroes: + case nvme_cmd_write_uncor: + return NVME_CMD_EFFECTS_LBCC; + default: + return 0; + } +} + u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) { u32 effects = 0; @@ -1081,16 +1093,24 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) if (ns) { if (ns->head->effects) effects = le32_to_cpu(ns->head->effects->iocs[opcode]); + if (ns->head->ids.csi == NVME_CAP_CSS_NVM) + effects |= nvme_known_nvm_effects(opcode); if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC)) dev_warn_once(ctrl->device, - "IO command:%02x has unhandled effects:%08x\n", + "IO command:%02x has unusual effects:%08x\n", opcode, effects); - return 0; - } - if (ctrl->effects) - effects = le32_to_cpu(ctrl->effects->acs[opcode]); - effects |= nvme_known_admin_effects(opcode); + /* + * NVME_CMD_EFFECTS_CSE_MASK causes a freeze all I/O queues, + * which would deadlock when done on an I/O command. Note that + * We already warn about an unusual effect above. + */ + effects &= ~NVME_CMD_EFFECTS_CSE_MASK; + } else { + if (ctrl->effects) + effects = le32_to_cpu(ctrl->effects->acs[opcode]); + effects |= nvme_known_admin_effects(opcode); + } return effects; } @@ -4926,7 +4946,7 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, memset(set, 0, sizeof(*set)); set->ops = ops; - set->queue_depth = ctrl->sqsize + 1; + set->queue_depth = min_t(unsigned, ctrl->sqsize, BLK_MQ_MAX_DEPTH - 1); /* * Some Apple controllers requires tags to be unique across admin and * the (only) I/O queue, so reserve the first 32 tags of the I/O queue. diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 9ddda571f046..a8639919237e 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -11,6 +11,8 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, fmode_t mode) { + u32 effects; + if (capable(CAP_SYS_ADMIN)) return true; @@ -43,11 +45,29 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, } /* - * Only allow I/O commands that transfer data to the controller if the - * special file is open for writing, but always allow I/O commands that - * transfer data from the controller. + * Check if the controller provides a Commands Supported and Effects log + * and marks this command as supported. If not reject unprivileged + * passthrough. + */ + effects = nvme_command_effects(ns->ctrl, ns, c->common.opcode); + if (!(effects & NVME_CMD_EFFECTS_CSUPP)) + return false; + + /* + * Don't allow passthrough for command that have intrusive (or unknown) + * effects. + */ + if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC | + NVME_CMD_EFFECTS_UUID_SEL | + NVME_CMD_EFFECTS_SCOPE_MASK)) + return false; + + /* + * Only allow I/O commands that transfer data to the controller or that + * change the logical block contents if the file descriptor is open for + * writing. */ - if (nvme_is_write(c)) + if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC)) return mode & FMODE_WRITE; return true; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 6bbb73ef8b25..424c8a467a0c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -893,7 +893,7 @@ static inline void nvme_trace_bio_complete(struct request *req) { struct nvme_ns *ns = req->q->queuedata; - if (req->cmd_flags & REQ_NVME_MPATH) + if ((req->cmd_flags & REQ_NVME_MPATH) && req->bio) trace_block_bio_complete(ns->head->disk->queue, req->bio); } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index f0f8027644bb..b13baccedb4a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -36,7 +36,7 @@ #define SQ_SIZE(q) ((q)->q_depth << (q)->sqes) #define CQ_SIZE(q) ((q)->q_depth * sizeof(struct nvme_completion)) -#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct nvme_sgl_desc)) +#define SGES_PER_PAGE (NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc)) /* * These can be higher, but we need to ensure that any command doesn't @@ -144,9 +144,9 @@ struct nvme_dev { mempool_t *iod_mempool; /* shadow doorbell buffer support: */ - u32 *dbbuf_dbs; + __le32 *dbbuf_dbs; dma_addr_t dbbuf_dbs_dma_addr; - u32 *dbbuf_eis; + __le32 *dbbuf_eis; dma_addr_t dbbuf_eis_dma_addr; /* host memory buffer support: */ @@ -208,10 +208,10 @@ struct nvme_queue { #define NVMEQ_SQ_CMB 1 #define NVMEQ_DELETE_ERROR 2 #define NVMEQ_POLLED 3 - u32 *dbbuf_sq_db; - u32 *dbbuf_cq_db; - u32 *dbbuf_sq_ei; - u32 *dbbuf_cq_ei; + __le32 *dbbuf_sq_db; + __le32 *dbbuf_cq_db; + __le32 *dbbuf_sq_ei; + __le32 *dbbuf_cq_ei; struct completion delete_done; }; @@ -343,11 +343,11 @@ static inline int nvme_dbbuf_need_event(u16 event_idx, u16 new_idx, u16 old) } /* Update dbbuf and return true if an MMIO is required */ -static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, - volatile u32 *dbbuf_ei) +static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db, + volatile __le32 *dbbuf_ei) { if (dbbuf_db) { - u16 old_value; + u16 old_value, event_idx; /* * Ensure that the queue is written before updating @@ -355,8 +355,8 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, */ wmb(); - old_value = *dbbuf_db; - *dbbuf_db = value; + old_value = le32_to_cpu(*dbbuf_db); + *dbbuf_db = cpu_to_le32(value); /* * Ensure that the doorbell is updated before reading the event @@ -366,7 +366,8 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, */ mb(); - if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value)) + event_idx = le32_to_cpu(*dbbuf_ei); + if (!nvme_dbbuf_need_event(event_idx, value, old_value)) return false; } @@ -380,9 +381,9 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, */ static int nvme_pci_npages_prp(void) { - unsigned nprps = DIV_ROUND_UP(NVME_MAX_KB_SZ + NVME_CTRL_PAGE_SIZE, - NVME_CTRL_PAGE_SIZE); - return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8); + unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE; + unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE); + return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8); } /* @@ -392,7 +393,7 @@ static int nvme_pci_npages_prp(void) static int nvme_pci_npages_sgl(void) { return DIV_ROUND_UP(NVME_MAX_SEGS * sizeof(struct nvme_sgl_desc), - PAGE_SIZE); + NVME_CTRL_PAGE_SIZE); } static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, @@ -708,7 +709,7 @@ static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge, sge->length = cpu_to_le32(entries * sizeof(*sge)); sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4; } else { - sge->length = cpu_to_le32(PAGE_SIZE); + sge->length = cpu_to_le32(NVME_CTRL_PAGE_SIZE); sge->type = NVME_SGL_FMT_SEG_DESC << 4; } } @@ -2332,10 +2333,12 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) if (dev->cmb_use_sqes) { result = nvme_cmb_qdepth(dev, nr_io_queues, sizeof(struct nvme_command)); - if (result > 0) + if (result > 0) { dev->q_depth = result; - else + dev->ctrl.sqsize = result - 1; + } else { dev->cmb_use_sqes = false; + } } do { @@ -2536,7 +2539,6 @@ static int nvme_pci_enable(struct nvme_dev *dev) dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1, io_queue_depth); - dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */ dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap); dev->dbs = dev->bar + 4096; @@ -2577,7 +2579,7 @@ static int nvme_pci_enable(struct nvme_dev *dev) dev_warn(dev->ctrl.device, "IO queue depth clamped to %d\n", dev->q_depth); } - + dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */ nvme_map_cmb(dev); diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 53a004ea320c..6a54ed6fb121 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -164,26 +164,31 @@ out: static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log) { - log->acs[nvme_admin_get_log_page] = cpu_to_le32(1 << 0); - log->acs[nvme_admin_identify] = cpu_to_le32(1 << 0); - log->acs[nvme_admin_abort_cmd] = cpu_to_le32(1 << 0); - log->acs[nvme_admin_set_features] = cpu_to_le32(1 << 0); - log->acs[nvme_admin_get_features] = cpu_to_le32(1 << 0); - log->acs[nvme_admin_async_event] = cpu_to_le32(1 << 0); - log->acs[nvme_admin_keep_alive] = cpu_to_le32(1 << 0); - - log->iocs[nvme_cmd_read] = cpu_to_le32(1 << 0); - log->iocs[nvme_cmd_write] = cpu_to_le32(1 << 0); - log->iocs[nvme_cmd_flush] = cpu_to_le32(1 << 0); - log->iocs[nvme_cmd_dsm] = cpu_to_le32(1 << 0); - log->iocs[nvme_cmd_write_zeroes] = cpu_to_le32(1 << 0); + log->acs[nvme_admin_get_log_page] = + log->acs[nvme_admin_identify] = + log->acs[nvme_admin_abort_cmd] = + log->acs[nvme_admin_set_features] = + log->acs[nvme_admin_get_features] = + log->acs[nvme_admin_async_event] = + log->acs[nvme_admin_keep_alive] = + cpu_to_le32(NVME_CMD_EFFECTS_CSUPP); + + log->iocs[nvme_cmd_read] = + log->iocs[nvme_cmd_flush] = + log->iocs[nvme_cmd_dsm] = + cpu_to_le32(NVME_CMD_EFFECTS_CSUPP); + log->iocs[nvme_cmd_write] = + log->iocs[nvme_cmd_write_zeroes] = + cpu_to_le32(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC); } static void nvmet_get_cmd_effects_zns(struct nvme_effects_log *log) { - log->iocs[nvme_cmd_zone_append] = cpu_to_le32(1 << 0); - log->iocs[nvme_cmd_zone_mgmt_send] = cpu_to_le32(1 << 0); - log->iocs[nvme_cmd_zone_mgmt_recv] = cpu_to_le32(1 << 0); + log->iocs[nvme_cmd_zone_append] = + log->iocs[nvme_cmd_zone_mgmt_send] = + cpu_to_le32(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC); + log->iocs[nvme_cmd_zone_mgmt_recv] = + cpu_to_le32(NVME_CMD_EFFECTS_CSUPP); } static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req) diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 79af5140af8b..adc0958755d6 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -334,14 +334,13 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req) } /* - * If there are effects for the command we are about to execute, or - * an end_req function we need to use nvme_execute_passthru_rq() - * synchronously in a work item seeing the end_req function and - * nvme_passthru_end() can't be called in the request done callback - * which is typically in interrupt context. + * If a command needs post-execution fixups, or there are any + * non-trivial effects, make sure to execute the command synchronously + * in a workqueue so that nvme_passthru_end gets called. */ effects = nvme_command_effects(ctrl, ns, req->cmd->common.opcode); - if (req->p.use_workqueue || effects) { + if (req->p.use_workqueue || + (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))) { INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work); req->p.rq = rq; queue_work(nvmet_wq, &req->p.work); diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 6af9fdbb86b7..058fbe28107e 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -116,8 +116,9 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, u32 *mkey, u32 *in, int inlen); int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey); int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, - bool *change_map); -int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb); + bool *change_map, unsigned int asid); +int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, + unsigned int asid); void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev); #define mlx5_vdpa_warn(__dev, format, ...) \ diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index a639b9208d41..0a1e0b0dc37e 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -311,7 +311,6 @@ static int add_direct_chain(struct mlx5_vdpa_dev *mvdev, u64 start, u64 size, u8 u64 st; u64 sz; int err; - int i = 0; st = start; while (size) { @@ -336,7 +335,6 @@ static int add_direct_chain(struct mlx5_vdpa_dev *mvdev, u64 start, u64 size, u8 mr->num_directs++; mr->num_klms++; st += sz; - i++; } list_splice_tail(&tmp, &mr->head); return 0; @@ -511,7 +509,8 @@ out: mutex_unlock(&mr->mkey_mtx); } -static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) +static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, + struct vhost_iotlb *iotlb, unsigned int asid) { struct mlx5_vdpa_mr *mr = &mvdev->mr; int err; @@ -519,42 +518,49 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb if (mr->initialized) return 0; - if (iotlb) - err = create_user_mr(mvdev, iotlb); - else - err = create_dma_mr(mvdev, mr); + if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) { + if (iotlb) + err = create_user_mr(mvdev, iotlb); + else + err = create_dma_mr(mvdev, mr); - if (err) - return err; + if (err) + return err; + } - err = dup_iotlb(mvdev, iotlb); - if (err) - goto out_err; + if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) { + err = dup_iotlb(mvdev, iotlb); + if (err) + goto out_err; + } mr->initialized = true; return 0; out_err: - if (iotlb) - destroy_user_mr(mvdev, mr); - else - destroy_dma_mr(mvdev, mr); + if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) { + if (iotlb) + destroy_user_mr(mvdev, mr); + else + destroy_dma_mr(mvdev, mr); + } return err; } -int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) +int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, + unsigned int asid) { int err; mutex_lock(&mvdev->mr.mkey_mtx); - err = _mlx5_vdpa_create_mr(mvdev, iotlb); + err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid); mutex_unlock(&mvdev->mr.mkey_mtx); return err; } int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, - bool *change_map) + bool *change_map, unsigned int asid) { struct mlx5_vdpa_mr *mr = &mvdev->mr; int err = 0; @@ -566,7 +572,7 @@ int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *io *change_map = true; } if (!*change_map) - err = _mlx5_vdpa_create_mr(mvdev, iotlb); + err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid); mutex_unlock(&mr->mkey_mtx); return err; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 90913365def4..3a6dbbc6440d 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1468,11 +1468,13 @@ static int mlx5_vdpa_add_mac_vlan_rules(struct mlx5_vdpa_net *ndev, u8 *mac, dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, outer_headers.dmac_47_16); eth_broadcast_addr(dmac_c); ether_addr_copy(dmac_v, mac); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1); + if (ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)) { + MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1); + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid); + } if (tagged) { MLX5_SET(fte_match_set_lyr_2_4, headers_v, cvlan_tag, 1); - MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, vid); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, vid); } flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; @@ -1684,7 +1686,7 @@ static virtio_net_ctrl_ack handle_ctrl_mac(struct mlx5_vdpa_dev *mvdev, u8 cmd) /* Need recreate the flow table entry, so that the packet could forward back */ - mac_vlan_del(ndev, ndev->config.mac, 0, false); + mac_vlan_del(ndev, mac_back, 0, false); if (mac_vlan_add(ndev, ndev->config.mac, 0, false)) { mlx5_vdpa_warn(mvdev, "failed to insert forward rules, try to restore\n"); @@ -1821,6 +1823,9 @@ static virtio_net_ctrl_ack handle_ctrl_vlan(struct mlx5_vdpa_dev *mvdev, u8 cmd) size_t read; u16 id; + if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN))) + return status; + switch (cmd) { case VIRTIO_NET_CTRL_VLAN_ADD: read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->riov, &vlan, sizeof(vlan)); @@ -2389,7 +2394,8 @@ static void restore_channels_info(struct mlx5_vdpa_net *ndev) } } -static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) +static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, + struct vhost_iotlb *iotlb, unsigned int asid) { struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); int err; @@ -2401,7 +2407,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb teardown_driver(ndev); mlx5_vdpa_destroy_mr(mvdev); - err = mlx5_vdpa_create_mr(mvdev, iotlb); + err = mlx5_vdpa_create_mr(mvdev, iotlb, asid); if (err) goto err_mr; @@ -2582,7 +2588,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) ++mvdev->generation; if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) { - if (mlx5_vdpa_create_mr(mvdev, NULL)) + if (mlx5_vdpa_create_mr(mvdev, NULL, 0)) mlx5_vdpa_warn(mvdev, "create MR failed\n"); } up_write(&ndev->reslock); @@ -2618,41 +2624,20 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev) return mvdev->generation; } -static int set_map_control(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) -{ - u64 start = 0ULL, last = 0ULL - 1; - struct vhost_iotlb_map *map; - int err = 0; - - spin_lock(&mvdev->cvq.iommu_lock); - vhost_iotlb_reset(mvdev->cvq.iotlb); - - for (map = vhost_iotlb_itree_first(iotlb, start, last); map; - map = vhost_iotlb_itree_next(map, start, last)) { - err = vhost_iotlb_add_range(mvdev->cvq.iotlb, map->start, - map->last, map->addr, map->perm); - if (err) - goto out; - } - -out: - spin_unlock(&mvdev->cvq.iommu_lock); - return err; -} - -static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) +static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, + unsigned int asid) { bool change_map; int err; - err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map); + err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map, asid); if (err) { mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err); return err; } if (change_map) - err = mlx5_vdpa_change_map(mvdev, iotlb); + err = mlx5_vdpa_change_map(mvdev, iotlb, asid); return err; } @@ -2665,16 +2650,7 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, unsigned int asid, int err = -EINVAL; down_write(&ndev->reslock); - if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) { - err = set_map_data(mvdev, iotlb); - if (err) - goto out; - } - - if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) - err = set_map_control(mvdev, iotlb); - -out: + err = set_map_data(mvdev, iotlb, asid); up_write(&ndev->reslock); return err; } @@ -2840,8 +2816,8 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev) int i; down_write(&ndev->reslock); - mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); ndev->nb_registered = false; + mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); flush_workqueue(ndev->mvdev.wq); for (i = 0; i < ndev->cur_num_vqs; i++) { mvq = &ndev->vqs[i]; @@ -3019,7 +2995,7 @@ static void update_carrier(struct work_struct *work) else ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP); - if (ndev->config_cb.callback) + if (ndev->nb_registered && ndev->config_cb.callback) ndev->config_cb.callback(ndev->config_cb.private); kfree(wqent); @@ -3036,21 +3012,13 @@ static int event_handler(struct notifier_block *nb, unsigned long event, void *p switch (eqe->sub_type) { case MLX5_PORT_CHANGE_SUBTYPE_DOWN: case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE: - down_read(&ndev->reslock); - if (!ndev->nb_registered) { - up_read(&ndev->reslock); - return NOTIFY_DONE; - } wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC); - if (!wqent) { - up_read(&ndev->reslock); + if (!wqent) return NOTIFY_DONE; - } wqent->mvdev = &ndev->mvdev; INIT_WORK(&wqent->work, update_carrier); queue_work(ndev->mvdev.wq, &wqent->work); - up_read(&ndev->reslock); ret = NOTIFY_OK; break; default: @@ -3185,7 +3153,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, goto err_mpfs; if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) { - err = mlx5_vdpa_create_mr(mvdev, NULL); + err = mlx5_vdpa_create_mr(mvdev, NULL, 0); if (err) goto err_res; } @@ -3237,8 +3205,8 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device * struct workqueue_struct *wq; if (ndev->nb_registered) { - mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); ndev->nb_registered = false; + mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); } wq = mvdev->wq; mvdev->wq = NULL; diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index febdc99b51a7..8ef7aa1365cc 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -855,7 +855,7 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms features_device = vdev->config->get_device_features(vdev); - if (nla_put_u64_64bit(msg, VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, features_device, + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_FEATURES, features_device, VDPA_ATTR_PAD)) return -EMSGSIZE; @@ -935,7 +935,6 @@ static int vdpa_fill_stats_rec(struct vdpa_device *vdev, struct sk_buff *msg, { struct virtio_net_config config = {}; u64 features; - u16 max_vqp; u8 status; int err; @@ -946,15 +945,15 @@ static int vdpa_fill_stats_rec(struct vdpa_device *vdev, struct sk_buff *msg, } vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config)); - max_vqp = __virtio16_to_cpu(true, config.max_virtqueue_pairs); - if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, max_vqp)) - return -EMSGSIZE; - features = vdev->config->get_driver_features(vdev); if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features, VDPA_ATTR_PAD)) return -EMSGSIZE; + err = vdpa_dev_net_mq_config_fill(msg, features, &config); + if (err) + return err; + if (nla_put_u32(msg, VDPA_ATTR_DEV_QUEUE_INDEX, index)) return -EMSGSIZE; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index b071f0d842fb..cb88891b44a8 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -67,8 +67,7 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) { struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; - vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features, - VDPASIM_QUEUE_MAX, false, + vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, false, (struct vring_desc *)(uintptr_t)vq->desc_addr, (struct vring_avail *) (uintptr_t)vq->driver_addr, @@ -690,7 +689,9 @@ static void vdpasim_free(struct vdpa_device *vdpa) } kvfree(vdpasim->buffer); - vhost_iotlb_free(vdpasim->iommu); + for (i = 0; i < vdpasim->dev_attr.nas; i++) + vhost_iotlb_reset(&vdpasim->iommu[i]); + kfree(vdpasim->iommu); kfree(vdpasim->vqs); kfree(vdpasim->config); } diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index c6db1a1baf76..f745926237a8 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -427,8 +427,10 @@ static int __init vdpasim_blk_init(void) int ret; ret = device_register(&vdpasim_blk_mgmtdev); - if (ret) + if (ret) { + put_device(&vdpasim_blk_mgmtdev); return ret; + } ret = vdpa_mgmtdev_register(&mgmt_dev); if (ret) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index c3cb225ea469..584b975a98a7 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -62,6 +62,9 @@ static bool receive_filter(struct vdpasim *vdpasim, size_t len) if (len < ETH_ALEN + hdr_len) return false; + if (is_broadcast_ether_addr(vdpasim->buffer + hdr_len) || + is_multicast_ether_addr(vdpasim->buffer + hdr_len)) + return true; if (!strncmp(vdpasim->buffer + hdr_len, vio_config->mac, ETH_ALEN)) return true; @@ -305,8 +308,10 @@ static int __init vdpasim_net_init(void) int ret; ret = device_register(&vdpasim_net_mgmtdev); - if (ret) + if (ret) { + put_device(&vdpasim_net_mgmtdev); return ret; + } ret = vdpa_mgmtdev_register(&mgmt_dev); if (ret) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 0dd3c1f291da..0c3b48616a9f 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -1440,6 +1440,9 @@ static bool vduse_validate_config(struct vduse_dev_config *config) if (config->config_size > PAGE_SIZE) return false; + if (config->vq_num > 0xffff) + return false; + if (!device_is_allowed(config->device_id)) return false; diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index d448db0c4de3..8fe267ca3e76 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -647,7 +647,7 @@ static void vp_vdpa_remove(struct pci_dev *pdev) mdev = vp_vdpa_mgtdev->mdev; vp_modern_remove(mdev); vdpa_mgmtdev_unregister(&vp_vdpa_mgtdev->mgtdev); - kfree(&vp_vdpa_mgtdev->mgtdev.id_table); + kfree(vp_vdpa_mgtdev->mgtdev.id_table); kfree(mdev); kfree(vp_vdpa_mgtdev); } diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 166044642fd5..ec32f785dfde 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -65,6 +65,10 @@ static DEFINE_IDA(vhost_vdpa_ida); static dev_t vhost_vdpa_major; +static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, + struct vhost_iotlb *iotlb, u64 start, + u64 last, u32 asid); + static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb) { struct vhost_vdpa_as *as = container_of(iotlb, struct @@ -135,7 +139,7 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid) return -EINVAL; hlist_del(&as->hash_link); - vhost_iotlb_reset(&as->iotlb); + vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1, asid); kfree(as); return 0; @@ -683,10 +687,20 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, mutex_unlock(&d->mutex); return r; } +static void vhost_vdpa_general_unmap(struct vhost_vdpa *v, + struct vhost_iotlb_map *map, u32 asid) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + if (ops->dma_map) { + ops->dma_unmap(vdpa, asid, map->start, map->size); + } else if (ops->set_map == NULL) { + iommu_unmap(v->domain, map->start, map->size); + } +} -static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, - struct vhost_iotlb *iotlb, - u64 start, u64 last) +static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, + u64 start, u64 last, u32 asid) { struct vhost_dev *dev = &v->vdev; struct vhost_iotlb_map *map; @@ -703,13 +717,13 @@ static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, unpin_user_page(page); } atomic64_sub(PFN_DOWN(map->size), &dev->mm->pinned_vm); + vhost_vdpa_general_unmap(v, map, asid); vhost_iotlb_map_free(iotlb, map); } } -static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, - struct vhost_iotlb *iotlb, - u64 start, u64 last) +static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, + u64 start, u64 last, u32 asid) { struct vhost_iotlb_map *map; struct vdpa_map_file *map_file; @@ -718,20 +732,21 @@ static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, map_file = (struct vdpa_map_file *)map->opaque; fput(map_file->file); kfree(map_file); + vhost_vdpa_general_unmap(v, map, asid); vhost_iotlb_map_free(iotlb, map); } } static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, - struct vhost_iotlb *iotlb, - u64 start, u64 last) + struct vhost_iotlb *iotlb, u64 start, + u64 last, u32 asid) { struct vdpa_device *vdpa = v->vdpa; if (vdpa->use_va) - return vhost_vdpa_va_unmap(v, iotlb, start, last); + return vhost_vdpa_va_unmap(v, iotlb, start, last, asid); - return vhost_vdpa_pa_unmap(v, iotlb, start, last); + return vhost_vdpa_pa_unmap(v, iotlb, start, last, asid); } static int perm_to_iommu_flags(u32 perm) @@ -798,17 +813,12 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, const struct vdpa_config_ops *ops = vdpa->config; u32 asid = iotlb_to_asid(iotlb); - vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1); + vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1, asid); - if (ops->dma_map) { - ops->dma_unmap(vdpa, asid, iova, size); - } else if (ops->set_map) { + if (ops->set_map) { if (!v->in_batch) ops->set_map(vdpa, asid, iotlb); - } else { - iommu_unmap(v->domain, iova, size); } - /* If we are in the middle of batch processing, delay the free * of AS until BATCH_END. */ @@ -1162,14 +1172,14 @@ static void vhost_vdpa_cleanup(struct vhost_vdpa *v) struct vhost_vdpa_as *as; u32 asid; - vhost_dev_cleanup(&v->vdev); - kfree(v->vdev.vqs); - for (asid = 0; asid < v->vdpa->nas; asid++) { as = asid_to_as(v, asid); if (as) vhost_vdpa_remove_as(v, asid); } + + vhost_dev_cleanup(&v->vdev); + kfree(v->vdev.vqs); } static int vhost_vdpa_open(struct inode *inode, struct file *filep) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5c9fe3c9c364..cbe72bfd2f1f 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2053,7 +2053,7 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len, struct vhost_dev *dev = vq->dev; struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem; struct iovec *_iov; - u64 s = 0; + u64 s = 0, last = addr + len - 1; int ret = 0; while ((u64)len > s) { @@ -2063,7 +2063,7 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len, break; } - map = vhost_iotlb_itree_first(umem, addr, addr + len - 1); + map = vhost_iotlb_itree_first(umem, addr, last); if (map == NULL || map->start > addr) { if (umem != dev->iotlb) { ret = -EFAULT; diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index c9f5c8ea3afb..33eb941fcf15 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -1102,7 +1102,7 @@ static int iotlb_translate(const struct vringh *vrh, struct vhost_iotlb_map *map; struct vhost_iotlb *iotlb = vrh->iotlb; int ret = 0; - u64 s = 0; + u64 s = 0, last = addr + len - 1; spin_lock(vrh->iotlb_lock); @@ -1114,8 +1114,7 @@ static int iotlb_translate(const struct vringh *vrh, break; } - map = vhost_iotlb_itree_first(iotlb, addr, - addr + len - 1); + map = vhost_iotlb_itree_first(iotlb, addr, last); if (!map || map->start > addr) { ret = -EINVAL; break; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index cd6f7776013a..a2b374372363 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -959,7 +959,14 @@ static int __init vhost_vsock_init(void) VSOCK_TRANSPORT_F_H2G); if (ret < 0) return ret; - return misc_register(&vhost_vsock_misc); + + ret = misc_register(&vhost_vsock_misc); + if (ret) { + vsock_core_unregister(&vhost_transport.transport); + return ret; + } + + return 0; }; static void __exit vhost_vsock_exit(void) diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index df6e09f7d242..b2bed599e6c6 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -456,8 +456,8 @@ config FB_ATARI chipset found in Ataris. config FB_OF - bool "Open Firmware frame buffer device support" - depends on (FB = y) && PPC && (!PPC_PSERIES || PCI) + tristate "Open Firmware frame buffer device support" + depends on FB && PPC && (!PPC_PSERIES || PCI) depends on !DRM_OFDRM select APERTURE_HELPERS select FB_CFB_FILLRECT diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index 0ccf5d401ecb..d59215a4992e 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -3192,8 +3192,7 @@ static void aty_init_lcd(struct atyfb_par *par, u32 bios_base) * which we print to the screen. */ id = *(u8 *)par->lcd_table; - strncpy(model, (char *)par->lcd_table+1, 24); - model[23] = 0; + strscpy(model, (char *)par->lcd_table+1, sizeof(model)); width = par->lcd_width = *(u16 *)(par->lcd_table+25); height = par->lcd_height = *(u16 *)(par->lcd_table+27); diff --git a/drivers/video/fbdev/matrox/matroxfb_base.c b/drivers/video/fbdev/matrox/matroxfb_base.c index 0d3cee7ae726..a043a737ea9f 100644 --- a/drivers/video/fbdev/matrox/matroxfb_base.c +++ b/drivers/video/fbdev/matrox/matroxfb_base.c @@ -1378,8 +1378,8 @@ static struct video_board vbG200 = { .lowlevel = &matrox_G100 }; static struct video_board vbG200eW = { - .maxvram = 0x100000, - .maxdisplayable = 0x800000, + .maxvram = 0x1000000, + .maxdisplayable = 0x0800000, .accelID = FB_ACCEL_MATROX_MGAG200, .lowlevel = &matrox_G100 }; diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c index 17cda5765683..1f3df2055ff0 100644 --- a/drivers/video/fbdev/omap/omapfb_main.c +++ b/drivers/video/fbdev/omap/omapfb_main.c @@ -1447,7 +1447,7 @@ static int fbinfo_init(struct omapfb_device *fbdev, struct fb_info *info) info->fbops = &omapfb_ops; info->flags = FBINFO_FLAG_DEFAULT; - strncpy(fix->id, MODULE_NAME, sizeof(fix->id)); + strscpy(fix->id, MODULE_NAME, sizeof(fix->id)); info->pseudo_palette = fbdev->pseudo_palette; @@ -1573,8 +1573,7 @@ static int omapfb_find_ctrl(struct omapfb_device *fbdev) fbdev->ctrl = NULL; - strncpy(name, conf->lcd.ctrl_name, sizeof(name) - 1); - name[sizeof(name) - 1] = '\0'; + strscpy(name, conf->lcd.ctrl_name, sizeof(name)); if (strcmp(name, "internal") == 0) { fbdev->ctrl = fbdev->int_ctrl; diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dsi.c b/drivers/video/fbdev/omap2/omapfb/dss/dsi.c index 54b0f034c2ed..7cddb7b8ae34 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dsi.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dsi.c @@ -1536,22 +1536,28 @@ static void dsi_dump_dsidev_irqs(struct platform_device *dsidev, { struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev); unsigned long flags; - struct dsi_irq_stats stats; + struct dsi_irq_stats *stats; + + stats = kzalloc(sizeof(*stats), GFP_KERNEL); + if (!stats) { + seq_printf(s, "out of memory\n"); + return; + } spin_lock_irqsave(&dsi->irq_stats_lock, flags); - stats = dsi->irq_stats; + *stats = dsi->irq_stats; memset(&dsi->irq_stats, 0, sizeof(dsi->irq_stats)); dsi->irq_stats.last_reset = jiffies; spin_unlock_irqrestore(&dsi->irq_stats_lock, flags); seq_printf(s, "period %u ms\n", - jiffies_to_msecs(jiffies - stats.last_reset)); + jiffies_to_msecs(jiffies - stats->last_reset)); - seq_printf(s, "irqs %d\n", stats.irq_count); + seq_printf(s, "irqs %d\n", stats->irq_count); #define PIS(x) \ - seq_printf(s, "%-20s %10d\n", #x, stats.dsi_irqs[ffs(DSI_IRQ_##x)-1]) + seq_printf(s, "%-20s %10d\n", #x, stats->dsi_irqs[ffs(DSI_IRQ_##x)-1]) seq_printf(s, "-- DSI%d interrupts --\n", dsi->module_id + 1); PIS(VC0); @@ -1575,10 +1581,10 @@ static void dsi_dump_dsidev_irqs(struct platform_device *dsidev, #define PIS(x) \ seq_printf(s, "%-20s %10d %10d %10d %10d\n", #x, \ - stats.vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \ - stats.vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \ - stats.vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \ - stats.vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]); + stats->vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \ + stats->vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \ + stats->vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \ + stats->vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]); seq_printf(s, "-- VC interrupts --\n"); PIS(CS); @@ -1594,7 +1600,7 @@ static void dsi_dump_dsidev_irqs(struct platform_device *dsidev, #define PIS(x) \ seq_printf(s, "%-20s %10d\n", #x, \ - stats.cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]); + stats->cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]); seq_printf(s, "-- CIO interrupts --\n"); PIS(ERRSYNCESC1); @@ -1618,6 +1624,8 @@ static void dsi_dump_dsidev_irqs(struct platform_device *dsidev, PIS(ULPSACTIVENOT_ALL0); PIS(ULPSACTIVENOT_ALL1); #undef PIS + + kfree(stats); } static void dsi1_dump_irqs(struct seq_file *s) diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 828ced060742..b9a80aedee1b 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -15,7 +15,7 @@ static ssize_t device_show(struct device *_d, struct device_attribute *attr, char *buf) { struct virtio_device *dev = dev_to_virtio(_d); - return sprintf(buf, "0x%04x\n", dev->id.device); + return sysfs_emit(buf, "0x%04x\n", dev->id.device); } static DEVICE_ATTR_RO(device); @@ -23,7 +23,7 @@ static ssize_t vendor_show(struct device *_d, struct device_attribute *attr, char *buf) { struct virtio_device *dev = dev_to_virtio(_d); - return sprintf(buf, "0x%04x\n", dev->id.vendor); + return sysfs_emit(buf, "0x%04x\n", dev->id.vendor); } static DEVICE_ATTR_RO(vendor); @@ -31,7 +31,7 @@ static ssize_t status_show(struct device *_d, struct device_attribute *attr, char *buf) { struct virtio_device *dev = dev_to_virtio(_d); - return sprintf(buf, "0x%08x\n", dev->config->get_status(dev)); + return sysfs_emit(buf, "0x%08x\n", dev->config->get_status(dev)); } static DEVICE_ATTR_RO(status); @@ -39,7 +39,7 @@ static ssize_t modalias_show(struct device *_d, struct device_attribute *attr, char *buf) { struct virtio_device *dev = dev_to_virtio(_d); - return sprintf(buf, "virtio:d%08Xv%08X\n", + return sysfs_emit(buf, "virtio:d%08Xv%08X\n", dev->id.device, dev->id.vendor); } static DEVICE_ATTR_RO(modalias); @@ -54,9 +54,9 @@ static ssize_t features_show(struct device *_d, /* We actually represent this as a bitstring, as it could be * arbitrary length in future. */ for (i = 0; i < sizeof(dev->features)*8; i++) - len += sprintf(buf+len, "%c", + len += sysfs_emit_at(buf, len, "%c", __virtio_test_bit(dev, i) ? '1' : '0'); - len += sprintf(buf+len, "\n"); + len += sysfs_emit_at(buf, len, "\n"); return len; } static DEVICE_ATTR_RO(features); diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index c3b9f2761849..9e496e288cfa 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -303,14 +303,14 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, int err; if (index >= vp_modern_get_num_queues(mdev)) - return ERR_PTR(-ENOENT); + return ERR_PTR(-EINVAL); /* Check if queue is either not available or already active. */ num = vp_modern_get_queue_size(mdev, index); if (!num || vp_modern_get_queue_enable(mdev, index)) return ERR_PTR(-ENOENT); - if (num & (num - 1)) { + if (!is_power_of_2(num)) { dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num); return ERR_PTR(-EINVAL); } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 2e7689bb933b..723c4e29e1d3 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1052,7 +1052,7 @@ static int vring_alloc_queue_split(struct vring_virtqueue_split *vring_split, dma_addr_t dma_addr; /* We assume num is a power of 2. */ - if (num & (num - 1)) { + if (!is_power_of_2(num)) { dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num); return -EINVAL; } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 21c92c74bf71..46851511b661 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -484,6 +484,7 @@ static int add_all_parents(struct btrfs_backref_walk_ctx *ctx, u64 wanted_disk_byte = ref->wanted_disk_byte; u64 count = 0; u64 data_offset; + u8 type; if (level != 0) { eb = path->nodes[level]; @@ -538,6 +539,9 @@ static int add_all_parents(struct btrfs_backref_walk_ctx *ctx, continue; } fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); + type = btrfs_file_extent_type(eb, fi); + if (type == BTRFS_FILE_EXTENT_INLINE) + goto next; disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); data_offset = btrfs_file_extent_offset(eb, fi); diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c index 0a3c261b69c9..d81b764a7644 100644 --- a/fs/btrfs/defrag.c +++ b/fs/btrfs/defrag.c @@ -358,8 +358,10 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, goto out; path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + ret = -ENOMEM; + goto out; + } level = btrfs_header_level(root->node); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 8bcad9940154..2ead7b1bdbaf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9377,8 +9377,10 @@ static int btrfs_rename(struct user_namespace *mnt_userns, if (flags & RENAME_WHITEOUT) { whiteout_args.inode = new_whiteout_inode(mnt_userns, old_dir); - if (!whiteout_args.inode) - return -ENOMEM; + if (!whiteout_args.inode) { + ret = -ENOMEM; + goto out_fscrypt_names; + } ret = btrfs_new_inode_prepare(&whiteout_args, &trans_num_items); if (ret) goto out_whiteout_inode; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 5c636e00d77d..d275bf24b250 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2787,6 +2787,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) * current root. It's safe inside commit_transaction(). */ ctx.trans = trans; + ctx.time_seq = BTRFS_SEQ_LAST; ret = btrfs_find_all_roots(&ctx, false); if (ret < 0) goto cleanup; diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 2d90a6b5eb00..6a2cf754912d 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -2646,7 +2646,7 @@ static int recover_scrub_rbio(struct btrfs_raid_bio *rbio) void **pointers = NULL; void **unmap_array = NULL; int sector_nr; - int ret; + int ret = 0; /* * @pointers array stores the pointer for each sector. diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 93f52ee85f6f..d5de18d6517e 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2514,6 +2514,7 @@ static __always_inline void btrfs_exit_btrfs_fs(void) static void __exit exit_btrfs_fs(void) { btrfs_exit_btrfs_fs(); + btrfs_cleanup_fs_uuids(); } static int __init init_btrfs_fs(void) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index a3c43f0b1c95..fb52aa060093 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -7459,8 +7459,11 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, * not fail, but if it does, it's not serious, just bail out and * mark the log for a full commit. */ - if (WARN_ON_ONCE(ret < 0)) + if (WARN_ON_ONCE(ret < 0)) { + fscrypt_free_filename(&fname); goto out; + } + log_pinned = true; path = btrfs_alloc_path(); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 6e43e19c7d1c..97e816590cd9 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2183,7 +2183,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, sector_t last_block_in_file; const unsigned blocksize = blks_to_bytes(inode, 1); struct decompress_io_ctx *dic = NULL; - struct extent_info ei = {0, }; + struct extent_info ei = {}; bool from_dnode = true; int i; int ret = 0; diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 1bd38a78ebba..342af24b2f8c 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -546,7 +546,8 @@ static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs, struct extent_node *en; bool ret = false; - f2fs_bug_on(sbi, !et); + if (!et) + return false; trace_f2fs_lookup_extent_tree_start(inode, pgofs, type); @@ -881,12 +882,14 @@ static unsigned long long __calculate_block_age(unsigned long long new, } /* This returns a new age and allocated blocks in ei */ -static int __get_new_block_age(struct inode *inode, struct extent_info *ei) +static int __get_new_block_age(struct inode *inode, struct extent_info *ei, + block_t blkaddr) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); loff_t f_size = i_size_read(inode); unsigned long long cur_blocks = atomic64_read(&sbi->allocated_data_blocks); + struct extent_info tei = *ei; /* only fofs and len are valid */ /* * When I/O is not aligned to a PAGE_SIZE, update will happen to the last @@ -894,20 +897,20 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei) * block here. */ if ((f_size >> PAGE_SHIFT) == ei->fofs && f_size & (PAGE_SIZE - 1) && - ei->blk == NEW_ADDR) + blkaddr == NEW_ADDR) return -EINVAL; - if (__lookup_extent_tree(inode, ei->fofs, ei, EX_BLOCK_AGE)) { + if (__lookup_extent_tree(inode, ei->fofs, &tei, EX_BLOCK_AGE)) { unsigned long long cur_age; - if (cur_blocks >= ei->last_blocks) - cur_age = cur_blocks - ei->last_blocks; + if (cur_blocks >= tei.last_blocks) + cur_age = cur_blocks - tei.last_blocks; else /* allocated_data_blocks overflow */ - cur_age = ULLONG_MAX - ei->last_blocks + cur_blocks; + cur_age = ULLONG_MAX - tei.last_blocks + cur_blocks; - if (ei->age) - ei->age = __calculate_block_age(cur_age, ei->age); + if (tei.age) + ei->age = __calculate_block_age(cur_age, tei.age); else ei->age = cur_age; ei->last_blocks = cur_blocks; @@ -915,14 +918,14 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei) return 0; } - f2fs_bug_on(sbi, ei->blk == NULL_ADDR); + f2fs_bug_on(sbi, blkaddr == NULL_ADDR); /* the data block was allocated for the first time */ - if (ei->blk == NEW_ADDR) + if (blkaddr == NEW_ADDR) goto out; - if (__is_valid_data_blkaddr(ei->blk) && - !f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE)) { + if (__is_valid_data_blkaddr(blkaddr) && + !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) { f2fs_bug_on(sbi, 1); return -EINVAL; } @@ -938,7 +941,7 @@ out: static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type type) { - struct extent_info ei; + struct extent_info ei = {}; if (!__may_extent_tree(dn->inode, type)) return; @@ -953,8 +956,7 @@ static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type typ else ei.blk = dn->data_blkaddr; } else if (type == EX_BLOCK_AGE) { - ei.blk = dn->data_blkaddr; - if (__get_new_block_age(dn->inode, &ei)) + if (__get_new_block_age(dn->inode, &ei, dn->data_blkaddr)) return; } __update_extent_tree_range(dn->inode, &ei, type); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index a6c401279886..ecbc8c135b49 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2559,7 +2559,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, struct f2fs_map_blocks map = { .m_next_extent = NULL, .m_seg_type = NO_CHECK_TYPE, .m_may_create = false }; - struct extent_info ei = {0, }; + struct extent_info ei = {}; pgoff_t pg_start, pg_end, next_pgofs; unsigned int blk_per_seg = sbi->blocks_per_seg; unsigned int total = 0, sec_num; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 25ddea478fc1..ae3c4e5474ef 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -663,8 +663,7 @@ init_thread: if (IS_ERR(fcc->f2fs_issue_flush)) { int err = PTR_ERR(fcc->f2fs_issue_flush); - kfree(fcc); - SM_I(sbi)->fcc_info = NULL; + fcc->f2fs_issue_flush = NULL; return err; } @@ -3161,7 +3160,7 @@ static int __get_segment_type_4(struct f2fs_io_info *fio) static int __get_age_segment_type(struct inode *inode, pgoff_t pgofs) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct extent_info ei; + struct extent_info ei = {}; if (f2fs_lookup_age_extent_cache(inode, pgofs, &ei)) { if (!ei.age) @@ -5138,11 +5137,9 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi) init_f2fs_rwsem(&sm_info->curseg_lock); - if (!f2fs_readonly(sbi->sb)) { - err = f2fs_create_flush_cmd_control(sbi); - if (err) - return err; - } + err = f2fs_create_flush_cmd_control(sbi); + if (err) + return err; err = create_discard_cmd_control(sbi); if (err) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2b4ae858c89b..ebb4d02a42ce 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3629,6 +3629,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, case nfserr_noent: xdr_truncate_encode(xdr, start_offset); goto skip_entry; + case nfserr_jukebox: + /* + * The pseudoroot should only display dentries that lead to + * exports. If we get EJUKEBOX here, then we can't tell whether + * this entry should be included. Just fail the whole READDIR + * with NFS4ERR_DELAY in that case, and hope that the situation + * will resolve itself by the client's next attempt. + */ + if (cd->rd_fhp->fh_export->ex_flags & NFSEXP_V4ROOT) + goto fail; + fallthrough; default: /* * If the client requested the RDATTR_ERROR attribute, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 56fba1cba3af..325d3d3f1211 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -453,8 +453,8 @@ static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nfsd_file_cache_shutdown_net(net); nfs4_state_shutdown_net(net); + nfsd_file_cache_shutdown_net(net); if (nn->lockd_up) { lockd_down(net); nn->lockd_up = false; diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index e5399ebc3a2b..d294cd975688 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -390,10 +390,10 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size) new_valid = ntfs_up_block(sb, min_t(u64, ni->i_valid, new_size)); - ni_lock(ni); - truncate_setsize(inode, new_size); + ni_lock(ni); + down_write(&ni->file.run_lock); err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, new_size, &new_valid, ni->mi.sbi->options->prealloc, NULL); diff --git a/include/acpi/video.h b/include/acpi/video.h index a275c35e5249..8ed9bec03e53 100644 --- a/include/acpi/video.h +++ b/include/acpi/video.h @@ -53,6 +53,7 @@ enum acpi_backlight_type { }; #if IS_ENABLED(CONFIG_ACPI_VIDEO) +extern void acpi_video_report_nolcd(void); extern int acpi_video_register(void); extern void acpi_video_unregister(void); extern void acpi_video_register_backlight(void); @@ -69,6 +70,7 @@ extern int acpi_video_get_levels(struct acpi_device *device, struct acpi_video_device_brightness **dev_br, int *pmax_level); #else +static inline void acpi_video_report_nolcd(void) { return; }; static inline int acpi_video_register(void) { return -ENODEV; } static inline void acpi_video_unregister(void) { return; } static inline void acpi_video_register_backlight(void) { return; } diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index a94219e9916f..659bf3b31c91 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -891,7 +891,12 @@ #define PRINTK_INDEX #endif +/* + * Discard .note.GNU-stack, which is emitted as PROGBITS by the compiler. + * Otherwise, the type of .notes section would become PROGBITS instead of NOTES. + */ #define NOTES \ + /DISCARD/ : { *(.note.GNU-stack) } \ .notes : AT(ADDR(.notes) - LOAD_OFFSET) { \ BOUNDED_SECTION_BY(.note.*, _notes) \ } NOTES_HEADERS \ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index d6be2a686100..4fad4aa245fb 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -7,6 +7,7 @@ #ifndef _LINUX_NVME_H #define _LINUX_NVME_H +#include <linux/bits.h> #include <linux/types.h> #include <linux/uuid.h> @@ -639,8 +640,9 @@ enum { NVME_CMD_EFFECTS_NCC = 1 << 2, NVME_CMD_EFFECTS_NIC = 1 << 3, NVME_CMD_EFFECTS_CCC = 1 << 4, - NVME_CMD_EFFECTS_CSE_MASK = 3 << 16, + NVME_CMD_EFFECTS_CSE_MASK = GENMASK(18, 16), NVME_CMD_EFFECTS_UUID_SEL = 1 << 19, + NVME_CMD_EFFECTS_SCOPE_MASK = GENMASK(31, 20), }; struct nvme_effects_log { diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 0bce0b4ff2fa..6548b5b5aa60 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -98,7 +98,7 @@ struct raid56_bio_trace_info; EM( FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT") \ EM( FLUSH_DELALLOC_FULL, "FLUSH_DELALLOC_FULL") \ EM( FLUSH_DELAYED_REFS_NR, "FLUSH_DELAYED_REFS_NR") \ - EM( FLUSH_DELAYED_REFS, "FLUSH_ELAYED_REFS") \ + EM( FLUSH_DELAYED_REFS, "FLUSH_DELAYED_REFS") \ EM( ALLOC_CHUNK, "ALLOC_CHUNK") \ EM( ALLOC_CHUNK_FORCE, "ALLOC_CHUNK_FORCE") \ EM( RUN_DELAYED_IPUTS, "RUN_DELAYED_IPUTS") \ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 9d4c4078e8d0..2780bce62faf 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -10,7 +10,15 @@ #include <linux/fs.h> #include <linux/types.h> +/* + * this file is shared with liburing and that has to autodetect + * if linux/time_types.h is available or not, it can + * define UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H + * if linux/time_types.h is not available + */ +#ifndef UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H #include <linux/time_types.h> +#endif #ifdef __cplusplus extern "C" { diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 20522d4ba1e0..55155e262646 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1767,6 +1767,7 @@ struct kvm_xen_hvm_attr { __u8 runstate_update_flag; struct { __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) } shared_info; struct { __u32 send_port; @@ -1798,6 +1799,7 @@ struct kvm_xen_hvm_attr { } u; }; + /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 @@ -1823,6 +1825,7 @@ struct kvm_xen_vcpu_attr { __u16 pad[3]; union { __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) __u64 pad[8]; struct { __u64 state; diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 9bd79235c875..54b649ab0f22 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -53,11 +53,9 @@ enum vdpa_attr { VDPA_ATTR_DEV_VENDOR_ATTR_NAME, /* string */ VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, /* u64 */ + /* virtio features that are provisioned to the vDPA device */ VDPA_ATTR_DEV_FEATURES, /* u64 */ - /* virtio features that are supported by the vDPA device */ - VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, /* u64 */ - /* new attributes must be added above here */ VDPA_ATTR_MAX, }; diff --git a/io_uring/cancel.c b/io_uring/cancel.c index 2291a53cdabd..b4f5dfacc0c3 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -288,24 +288,23 @@ int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg) ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); + mutex_unlock(&ctx->uring_lock); if (ret != -EALREADY) break; - mutex_unlock(&ctx->uring_lock); ret = io_run_task_work_sig(ctx); - if (ret < 0) { - mutex_lock(&ctx->uring_lock); + if (ret < 0) break; - } ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS); - mutex_lock(&ctx->uring_lock); if (!ret) { ret = -ETIME; break; } + mutex_lock(&ctx->uring_lock); } while (1); finish_wait(&ctx->cq_wait, &wait); + mutex_lock(&ctx->uring_lock); if (ret == -ENOENT || ret > 0) ret = 0; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ff2bbac1a10f..58ac13b69dc8 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -677,16 +677,20 @@ static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx) io_cq_unlock_post(ctx); } +static void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx) +{ + /* iopoll syncs against uring_lock, not completion_lock */ + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_lock(&ctx->uring_lock); + __io_cqring_overflow_flush(ctx); + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_unlock(&ctx->uring_lock); +} + static void io_cqring_overflow_flush(struct io_ring_ctx *ctx) { - if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) { - /* iopoll syncs against uring_lock, not completion_lock */ - if (ctx->flags & IORING_SETUP_IOPOLL) - mutex_lock(&ctx->uring_lock); - __io_cqring_overflow_flush(ctx); - if (ctx->flags & IORING_SETUP_IOPOLL) - mutex_unlock(&ctx->uring_lock); - } + if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) + io_cqring_do_overflow_flush(ctx); } void __io_put_task(struct task_struct *task, int nr) @@ -2549,7 +2553,10 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, trace_io_uring_cqring_wait(ctx, min_events); do { - io_cqring_overflow_flush(ctx); + if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) { + finish_wait(&ctx->cq_wait, &iowq.wq); + io_cqring_do_overflow_flush(ctx); + } prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); ret = io_cqring_wait_schedule(ctx, &iowq, timeout); @@ -4013,8 +4020,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, return -EEXIST; if (ctx->restricted) { - if (opcode >= IORING_REGISTER_LAST) - return -EINVAL; opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); if (!test_bit(opcode, ctx->restrictions.register_op)) return -EACCES; @@ -4170,6 +4175,9 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, long ret = -EBADF; struct fd f; + if (opcode >= IORING_REGISTER_LAST) + return -EINVAL; + f = fdget(fd); if (!f.file) return -EBADF; diff --git a/kernel/events/core.c b/kernel/events/core.c index eacc3702654d..d56328e5080e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -380,7 +380,6 @@ enum event_type_t { /* * perf_sched_events : >0 events exist - * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu */ static void perf_sched_delayed(struct work_struct *work); @@ -389,7 +388,6 @@ static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed); static DEFINE_MUTEX(perf_sched_mutex); static atomic_t perf_sched_count; -static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events); static atomic_t nr_mmap_events __read_mostly; @@ -844,9 +842,16 @@ static void perf_cgroup_switch(struct task_struct *task) struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_cgroup *cgrp; - cgrp = perf_cgroup_from_task(task, NULL); + /* + * cpuctx->cgrp is set when the first cgroup event enabled, + * and is cleared when the last cgroup event disabled. + */ + if (READ_ONCE(cpuctx->cgrp) == NULL) + return; WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); + + cgrp = perf_cgroup_from_task(task, NULL); if (READ_ONCE(cpuctx->cgrp) == cgrp) return; @@ -3631,8 +3636,7 @@ void __perf_event_task_sched_out(struct task_struct *task, * to check if we have to switch out PMU state. * cgroup event are system-wide mode only */ - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_switch(next); + perf_cgroup_switch(next); } static bool perf_less_group_idx(const void *l, const void *r) @@ -4974,15 +4978,6 @@ static void unaccount_pmu_sb_event(struct perf_event *event) detach_sb_event(event); } -static void unaccount_event_cpu(struct perf_event *event, int cpu) -{ - if (event->parent) - return; - - if (is_cgroup_event(event)) - atomic_dec(&per_cpu(perf_cgroup_events, cpu)); -} - #ifdef CONFIG_NO_HZ_FULL static DEFINE_SPINLOCK(nr_freq_lock); #endif @@ -5048,8 +5043,6 @@ static void unaccount_event(struct perf_event *event) schedule_delayed_work(&perf_sched_work, HZ); } - unaccount_event_cpu(event, event->cpu); - unaccount_pmu_sb_event(event); } @@ -11679,15 +11672,6 @@ static void account_pmu_sb_event(struct perf_event *event) attach_sb_event(event); } -static void account_event_cpu(struct perf_event *event, int cpu) -{ - if (event->parent) - return; - - if (is_cgroup_event(event)) - atomic_inc(&per_cpu(perf_cgroup_events, cpu)); -} - /* Freq events need the tick to stay alive (see perf_event_task_tick). */ static void account_freq_event_nohz(void) { @@ -11775,8 +11759,6 @@ static void account_event(struct perf_event *event) } enabled: - account_event_cpu(event, event->cpu); - account_pmu_sb_event(event); } @@ -12339,12 +12321,12 @@ SYSCALL_DEFINE5(perf_event_open, if (flags & ~PERF_FLAG_ALL) return -EINVAL; - /* Do we allow access to perf_event_open(2) ? */ - err = security_perf_event_open(&attr, PERF_SECURITY_OPEN); + err = perf_copy_attr(attr_uptr, &attr); if (err) return err; - err = perf_copy_attr(attr_uptr, &attr); + /* Do we allow access to perf_event_open(2) ? */ + err = security_perf_event_open(&attr, PERF_SECURITY_OPEN); if (err) return err; @@ -12689,7 +12671,8 @@ SYSCALL_DEFINE5(perf_event_open, return event_fd; err_context: - /* event->pmu_ctx freed by free_event() */ + put_pmu_ctx(event->pmu_ctx); + event->pmu_ctx = NULL; /* _free_event() */ err_locked: mutex_unlock(&ctx->mutex); perf_unpin_context(ctx); @@ -12802,6 +12785,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, err_pmu_ctx: put_pmu_ctx(pmu_ctx); + event->pmu_ctx = NULL; /* _free_event() */ err_unlock: mutex_unlock(&ctx->mutex); perf_unpin_context(ctx); @@ -12822,13 +12806,11 @@ static void __perf_pmu_remove(struct perf_event_context *ctx, perf_event_groups_for_cpu_pmu(event, groups, cpu, pmu) { perf_remove_from_context(event, 0); - unaccount_event_cpu(event, cpu); put_pmu_ctx(event->pmu_ctx); list_add(&event->migrate_entry, events); for_each_sibling_event(sibling, event) { perf_remove_from_context(sibling, 0); - unaccount_event_cpu(sibling, cpu); put_pmu_ctx(sibling->pmu_ctx); list_add(&sibling->migrate_entry, events); } @@ -12847,7 +12829,6 @@ static void __perf_pmu_install_event(struct pmu *pmu, if (event->state >= PERF_EVENT_STATE_OFF) event->state = PERF_EVENT_STATE_INACTIVE; - account_event_cpu(event, cpu); perf_install_in_context(ctx, event, cpu); } @@ -13231,7 +13212,7 @@ inherit_event(struct perf_event *parent_event, pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event); if (IS_ERR(pmu_ctx)) { free_event(child_event); - return NULL; + return ERR_CAST(pmu_ctx); } child_event->pmu_ctx = pmu_ctx; @@ -13742,8 +13723,7 @@ static int __perf_cgroup_move(void *info) struct task_struct *task = info; preempt_disable(); - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_switch(task); + perf_cgroup_switch(task); preempt_enable(); return 0; diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 086a22d1adb7..a8074079b09e 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -286,19 +286,22 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, } futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); - if (!futexv) - return -ENOMEM; + if (!futexv) { + ret = -ENOMEM; + goto destroy_timer; + } ret = futex_parse_waitv(futexv, waiters, nr_futexes); if (!ret) ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); + kfree(futexv); + +destroy_timer: if (timeout) { hrtimer_cancel(&to.timer); destroy_hrtimer_on_stack(&to.timer); } - - kfree(futexv); return ret; } diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 7779ee8abc2a..010cf4e6d0b8 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -89,15 +89,31 @@ static inline int __ww_mutex_check_kill(struct rt_mutex *lock, * set this bit before looking at the lock. */ -static __always_inline void -rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner) +static __always_inline struct task_struct * +rt_mutex_owner_encode(struct rt_mutex_base *lock, struct task_struct *owner) { unsigned long val = (unsigned long)owner; if (rt_mutex_has_waiters(lock)) val |= RT_MUTEX_HAS_WAITERS; - WRITE_ONCE(lock->owner, (struct task_struct *)val); + return (struct task_struct *)val; +} + +static __always_inline void +rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner) +{ + /* + * lock->wait_lock is held but explicit acquire semantics are needed + * for a new lock owner so WRITE_ONCE is insufficient. + */ + xchg_acquire(&lock->owner, rt_mutex_owner_encode(lock, owner)); +} + +static __always_inline void rt_mutex_clear_owner(struct rt_mutex_base *lock) +{ + /* lock->wait_lock is held so the unlock provides release semantics. */ + WRITE_ONCE(lock->owner, rt_mutex_owner_encode(lock, NULL)); } static __always_inline void clear_rt_mutex_waiters(struct rt_mutex_base *lock) @@ -106,7 +122,8 @@ static __always_inline void clear_rt_mutex_waiters(struct rt_mutex_base *lock) ((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS); } -static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex_base *lock) +static __always_inline void +fixup_rt_mutex_waiters(struct rt_mutex_base *lock, bool acquire_lock) { unsigned long owner, *p = (unsigned long *) &lock->owner; @@ -172,8 +189,21 @@ static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex_base *lock) * still set. */ owner = READ_ONCE(*p); - if (owner & RT_MUTEX_HAS_WAITERS) - WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); + if (owner & RT_MUTEX_HAS_WAITERS) { + /* + * See rt_mutex_set_owner() and rt_mutex_clear_owner() on + * why xchg_acquire() is used for updating owner for + * locking and WRITE_ONCE() for unlocking. + * + * WRITE_ONCE() would work for the acquire case too, but + * in case that the lock acquisition failed it might + * force other lockers into the slow path unnecessarily. + */ + if (acquire_lock) + xchg_acquire(p, owner & ~RT_MUTEX_HAS_WAITERS); + else + WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); + } } /* @@ -208,6 +238,13 @@ static __always_inline void mark_rt_mutex_waiters(struct rt_mutex_base *lock) owner = *p; } while (cmpxchg_relaxed(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner); + + /* + * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE + * operations in the event of contention. Ensure the successful + * cmpxchg is visible. + */ + smp_mb__after_atomic(); } /* @@ -1243,7 +1280,7 @@ static int __sched __rt_mutex_slowtrylock(struct rt_mutex_base *lock) * try_to_take_rt_mutex() sets the lock waiters bit * unconditionally. Clean this up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true); return ret; } @@ -1604,7 +1641,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock, * try_to_take_rt_mutex() sets the waiter bit * unconditionally. We might have to fix that up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true); trace_contention_end(lock, ret); @@ -1719,7 +1756,7 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock) * try_to_take_rt_mutex() sets the waiter bit unconditionally. * We might have to fix that up: */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true); debug_rt_mutex_free_waiter(&waiter); trace_contention_end(lock, 0); diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 900220941caa..cb9fdff76a8a 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -267,7 +267,7 @@ void __sched rt_mutex_init_proxy_locked(struct rt_mutex_base *lock, void __sched rt_mutex_proxy_unlock(struct rt_mutex_base *lock) { debug_rt_mutex_proxy_unlock(lock); - rt_mutex_set_owner(lock, NULL); + rt_mutex_clear_owner(lock); } /** @@ -382,7 +382,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true); raw_spin_unlock_irq(&lock->wait_lock); return ret; @@ -438,7 +438,7 @@ bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex_base *lock, * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, false); raw_spin_unlock_irq(&lock->wait_lock); diff --git a/lib/kunit/string-stream.c b/lib/kunit/string-stream.c index f5f51166d8c2..cc32743c1171 100644 --- a/lib/kunit/string-stream.c +++ b/lib/kunit/string-stream.c @@ -23,8 +23,10 @@ static struct string_stream_fragment *alloc_string_stream_fragment( return ERR_PTR(-ENOMEM); frag->fragment = kunit_kmalloc(test, len, gfp); - if (!frag->fragment) + if (!frag->fragment) { + kunit_kfree(test, frag); return ERR_PTR(-ENOMEM); + } return frag; } diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 5eb5e8280379..0ee296cf520c 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -55,6 +55,17 @@ ifneq ($(findstring i,$(filter-out --%,$(MAKEFLAGS))),) modpost-args += -n endif +ifneq ($(KBUILD_MODPOST_WARN)$(missing-input),) +modpost-args += -w +endif + +# Read out modules.order to pass in modpost. +# Otherwise, allmodconfig would fail with "Argument list too long". +ifdef KBUILD_MODULES +modpost-args += -T $(MODORDER) +modpost-deps += $(MODORDER) +endif + ifeq ($(KBUILD_EXTMOD),) # Generate the list of in-tree objects in vmlinux @@ -113,17 +124,6 @@ modpost-args += -e $(addprefix -i , $(KBUILD_EXTRA_SYMBOLS)) endif # ($(KBUILD_EXTMOD),) -ifneq ($(KBUILD_MODPOST_WARN)$(missing-input),) -modpost-args += -w -endif - -ifdef KBUILD_MODULES -modpost-args += -T $(MODORDER) -modpost-deps += $(MODORDER) -endif - -# Read out modules.order to pass in modpost. -# Otherwise, allmodconfig would fail with "Argument list too long". quiet_cmd_modpost = MODPOST $@ cmd_modpost = \ $(if $(missing-input), \ diff --git a/scripts/Makefile.package b/scripts/Makefile.package index 539e9f765d64..525a2820976f 100644 --- a/scripts/Makefile.package +++ b/scripts/Makefile.package @@ -158,6 +158,7 @@ $(perf-tar-pkgs): PHONY += help help: @echo ' rpm-pkg - Build both source and binary RPM kernel packages' + @echo ' srcrpm-pkg - Build only the source kernel RPM package' @echo ' binrpm-pkg - Build only the binary kernel RPM package' @echo ' deb-pkg - Build both source and binary deb kernel packages' @echo ' bindeb-pkg - Build only the binary kernel deb package' diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index 2328f9a641da..f932aeaba71a 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -94,7 +94,6 @@ #include <unistd.h> #include <fcntl.h> #include <string.h> -#include <stdarg.h> #include <stdlib.h> #include <stdio.h> #include <ctype.h> diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c index 9c549683c627..e67e0db50b2e 100644 --- a/scripts/kconfig/mconf.c +++ b/scripts/kconfig/mconf.c @@ -161,6 +161,12 @@ static const char mconf_readme[] = "(especially with a larger number of unrolled categories) than the\n" "default mode.\n" "\n" + +"Search\n" +"-------\n" +"Pressing the forward-slash (/) anywhere brings up a search dialog box.\n" +"\n" + "Different color themes available\n" "--------------------------------\n" "It is possible to select different color themes using the variable\n" diff --git a/scripts/package/mkspec b/scripts/package/mkspec index dda00a948a01..adab28fa7f89 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -51,7 +51,8 @@ sed -e '/^DEL/d' -e 's/^\t*//' <<EOF URL: https://www.kernel.org $S Source: kernel-$__KERNELRELEASE.tar.gz Provides: $PROVIDES -$S BuildRequires: bc binutils bison dwarves elfutils-libelf-devel flex +$S BuildRequires: bc binutils bison dwarves +$S BuildRequires: (elfutils-libelf-devel or libelf-devel) flex $S BuildRequires: gcc make openssl openssl-devel perl python3 rsync # $UTS_MACHINE as a fallback of _arch in case diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 8015e4471267..386dd9d9143f 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -167,6 +167,7 @@ struct hdmi_spec { struct hdmi_ops ops; bool dyn_pin_out; + bool static_pcm_mapping; /* hdmi interrupt trigger control flag for Nvidia codec */ bool hdmi_intr_trig_ctrl; bool nv_dp_workaround; /* workaround DP audio infoframe for Nvidia */ @@ -1525,13 +1526,16 @@ static void update_eld(struct hda_codec *codec, */ pcm_jack = pin_idx_to_pcm_jack(codec, per_pin); - if (eld->eld_valid) { - hdmi_attach_hda_pcm(spec, per_pin); - hdmi_pcm_setup_pin(spec, per_pin); - } else { - hdmi_pcm_reset_pin(spec, per_pin); - hdmi_detach_hda_pcm(spec, per_pin); + if (!spec->static_pcm_mapping) { + if (eld->eld_valid) { + hdmi_attach_hda_pcm(spec, per_pin); + hdmi_pcm_setup_pin(spec, per_pin); + } else { + hdmi_pcm_reset_pin(spec, per_pin); + hdmi_detach_hda_pcm(spec, per_pin); + } } + /* if pcm_idx == -1, it means this is in monitor connection event * we can get the correct pcm_idx now. */ @@ -2281,8 +2285,8 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec) struct hdmi_spec *spec = codec->spec; int idx, pcm_num; - /* limit the PCM devices to the codec converters */ - pcm_num = spec->num_cvts; + /* limit the PCM devices to the codec converters or available PINs */ + pcm_num = min(spec->num_cvts, spec->num_pins); codec_dbg(codec, "hdmi: pcm_num set to %d\n", pcm_num); for (idx = 0; idx < pcm_num; idx++) { @@ -2379,6 +2383,11 @@ static int generic_hdmi_build_controls(struct hda_codec *codec) struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx); struct hdmi_eld *pin_eld = &per_pin->sink_eld; + if (spec->static_pcm_mapping) { + hdmi_attach_hda_pcm(spec, per_pin); + hdmi_pcm_setup_pin(spec, per_pin); + } + pin_eld->eld_valid = false; hdmi_present_sense(per_pin, 0); } @@ -4419,6 +4428,8 @@ static int patch_atihdmi(struct hda_codec *codec) spec = codec->spec; + spec->static_pcm_mapping = true; + spec->ops.pin_get_eld = atihdmi_pin_get_eld; spec->ops.pin_setup_infoframe = atihdmi_pin_setup_infoframe; spec->ops.pin_hbr_setup = atihdmi_pin_hbr_setup; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index e443d88f627f..3794b522c222 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7175,6 +7175,7 @@ enum { ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK, ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN, ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS, + ALC236_FIXUP_DELL_DUAL_CODECS, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -9130,6 +9131,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, }, + [ALC236_FIXUP_DELL_DUAL_CODECS] = { + .type = HDA_FIXUP_PINS, + .v.func = alc1220_fixup_gb_dual_codecs, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -9232,6 +9239,12 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), + SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c1c, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c1d, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c index 59faa5a9a714..b67617b68e50 100644 --- a/sound/usb/line6/driver.c +++ b/sound/usb/line6/driver.c @@ -304,7 +304,8 @@ static void line6_data_received(struct urb *urb) for (;;) { done = line6_midibuf_read(mb, line6->buffer_message, - LINE6_MIDI_MESSAGE_MAXLEN); + LINE6_MIDI_MESSAGE_MAXLEN, + LINE6_MIDIBUF_READ_RX); if (done <= 0) break; diff --git a/sound/usb/line6/midi.c b/sound/usb/line6/midi.c index ba0e2b7e8fe1..0838632c788e 100644 --- a/sound/usb/line6/midi.c +++ b/sound/usb/line6/midi.c @@ -44,7 +44,8 @@ static void line6_midi_transmit(struct snd_rawmidi_substream *substream) int req, done; for (;;) { - req = min(line6_midibuf_bytes_free(mb), line6->max_packet_size); + req = min3(line6_midibuf_bytes_free(mb), line6->max_packet_size, + LINE6_FALLBACK_MAXPACKETSIZE); done = snd_rawmidi_transmit_peek(substream, chunk, req); if (done == 0) @@ -56,7 +57,8 @@ static void line6_midi_transmit(struct snd_rawmidi_substream *substream) for (;;) { done = line6_midibuf_read(mb, chunk, - LINE6_FALLBACK_MAXPACKETSIZE); + LINE6_FALLBACK_MAXPACKETSIZE, + LINE6_MIDIBUF_READ_TX); if (done == 0) break; diff --git a/sound/usb/line6/midibuf.c b/sound/usb/line6/midibuf.c index 6a70463f82c4..e7f830f7526c 100644 --- a/sound/usb/line6/midibuf.c +++ b/sound/usb/line6/midibuf.c @@ -9,6 +9,7 @@ #include "midibuf.h" + static int midibuf_message_length(unsigned char code) { int message_length; @@ -20,12 +21,7 @@ static int midibuf_message_length(unsigned char code) message_length = length[(code >> 4) - 8]; } else { - /* - Note that according to the MIDI specification 0xf2 is - the "Song Position Pointer", but this is used by Line 6 - to send sysex messages to the host. - */ - static const int length[] = { -1, 2, -1, 2, -1, -1, 1, 1, 1, 1, + static const int length[] = { -1, 2, 2, 2, -1, -1, 1, 1, 1, -1, 1, 1, 1, -1, 1, 1 }; message_length = length[code & 0x0f]; @@ -125,7 +121,7 @@ int line6_midibuf_write(struct midi_buffer *this, unsigned char *data, } int line6_midibuf_read(struct midi_buffer *this, unsigned char *data, - int length) + int length, int read_type) { int bytes_used; int length1, length2; @@ -148,9 +144,22 @@ int line6_midibuf_read(struct midi_buffer *this, unsigned char *data, length1 = this->size - this->pos_read; - /* check MIDI command length */ command = this->buf[this->pos_read]; + /* + PODxt always has status byte lower nibble set to 0010, + when it means to send 0000, so we correct if here so + that control/program changes come on channel 1 and + sysex message status byte is correct + */ + if (read_type == LINE6_MIDIBUF_READ_RX) { + if (command == 0xb2 || command == 0xc2 || command == 0xf2) { + unsigned char fixed = command & 0xf0; + this->buf[this->pos_read] = fixed; + command = fixed; + } + } + /* check MIDI command length */ if (command & 0x80) { midi_length = midibuf_message_length(command); this->command_prev = command; diff --git a/sound/usb/line6/midibuf.h b/sound/usb/line6/midibuf.h index 124a8f9f7e96..542e8d836f87 100644 --- a/sound/usb/line6/midibuf.h +++ b/sound/usb/line6/midibuf.h @@ -8,6 +8,9 @@ #ifndef MIDIBUF_H #define MIDIBUF_H +#define LINE6_MIDIBUF_READ_TX 0 +#define LINE6_MIDIBUF_READ_RX 1 + struct midi_buffer { unsigned char *buf; int size; @@ -23,7 +26,7 @@ extern void line6_midibuf_destroy(struct midi_buffer *mb); extern int line6_midibuf_ignore(struct midi_buffer *mb, int length); extern int line6_midibuf_init(struct midi_buffer *mb, int size, int split); extern int line6_midibuf_read(struct midi_buffer *mb, unsigned char *data, - int length); + int length, int read_type); extern void line6_midibuf_reset(struct midi_buffer *mb); extern int line6_midibuf_write(struct midi_buffer *mb, unsigned char *data, int length); diff --git a/sound/usb/line6/pod.c b/sound/usb/line6/pod.c index cd41aa7f0385..d173971e5f02 100644 --- a/sound/usb/line6/pod.c +++ b/sound/usb/line6/pod.c @@ -159,8 +159,9 @@ static struct line6_pcm_properties pod_pcm_properties = { .bytes_per_channel = 3 /* SNDRV_PCM_FMTBIT_S24_3LE */ }; + static const char pod_version_header[] = { - 0xf2, 0x7e, 0x7f, 0x06, 0x02 + 0xf0, 0x7e, 0x7f, 0x06, 0x02 }; static char *pod_alloc_sysex_buffer(struct usb_line6_pod *pod, int code, diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 6ce8c488d62e..6d9381d60172 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,86 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only -/aarch64/aarch32_id_regs -/aarch64/arch_timer -/aarch64/debug-exceptions -/aarch64/get-reg-list -/aarch64/hypercalls -/aarch64/page_fault_test -/aarch64/psci_test -/aarch64/vcpu_width_config -/aarch64/vgic_init -/aarch64/vgic_irq -/s390x/memop -/s390x/resets -/s390x/sync_regs_test -/s390x/tprot -/x86_64/amx_test -/x86_64/cpuid_test -/x86_64/cr4_cpuid_sync_test -/x86_64/debug_regs -/x86_64/exit_on_emulation_failure_test -/x86_64/fix_hypercall_test -/x86_64/get_msr_index_features -/x86_64/kvm_clock_test -/x86_64/kvm_pv_test -/x86_64/hyperv_clock -/x86_64/hyperv_cpuid -/x86_64/hyperv_evmcs -/x86_64/hyperv_features -/x86_64/hyperv_ipi -/x86_64/hyperv_svm_test -/x86_64/hyperv_tlb_flush -/x86_64/max_vcpuid_cap_test -/x86_64/mmio_warning_test -/x86_64/monitor_mwait_test -/x86_64/nested_exceptions_test -/x86_64/nx_huge_pages_test -/x86_64/platform_info_test -/x86_64/pmu_event_filter_test -/x86_64/set_boot_cpu_id -/x86_64/set_sregs_test -/x86_64/sev_migrate_tests -/x86_64/smaller_maxphyaddr_emulation_test -/x86_64/smm_test -/x86_64/state_test -/x86_64/svm_vmcall_test -/x86_64/svm_int_ctl_test -/x86_64/svm_nested_soft_inject_test -/x86_64/svm_nested_shutdown_test -/x86_64/sync_regs_test -/x86_64/tsc_msrs_test -/x86_64/tsc_scaling_sync -/x86_64/ucna_injection_test -/x86_64/userspace_io_test -/x86_64/userspace_msr_exit_test -/x86_64/vmx_apic_access_test -/x86_64/vmx_close_while_nested_test -/x86_64/vmx_dirty_log_test -/x86_64/vmx_exception_with_invalid_guest_state -/x86_64/vmx_invalid_nested_guest_state -/x86_64/vmx_msrs_test -/x86_64/vmx_preemption_timer_test -/x86_64/vmx_set_nested_state_test -/x86_64/vmx_tsc_adjust_test -/x86_64/vmx_nested_tsc_scaling_test -/x86_64/xapic_ipi_test -/x86_64/xapic_state_test -/x86_64/xen_shinfo_test -/x86_64/xen_vmcall_test -/x86_64/xss_msr_test -/x86_64/vmx_pmu_caps_test -/x86_64/triple_fault_event_test -/access_tracking_perf_test -/demand_paging_test -/dirty_log_test -/dirty_log_perf_test -/hardware_disable_test -/kvm_create_max_vcpus -/kvm_page_table_test -/max_guest_memory_test -/memslot_modification_stress_test -/memslot_perf_test -/rseq_test -/set_memory_region_test -/steal_time -/kvm_binary_stats_test -/system_counter_offset_test +* +!/**/ +!*.c +!*.h +!*.S +!*.sh diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 947676983da1..1750f91dd936 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -7,35 +7,14 @@ top_srcdir = ../../../.. include $(top_srcdir)/scripts/subarch.include ARCH ?= $(SUBARCH) -# For cross-builds to work, UNAME_M has to map to ARCH and arch specific -# directories and targets in this Makefile. "uname -m" doesn't map to -# arch specific sub-directory names. -# -# UNAME_M variable to used to run the compiles pointing to the right arch -# directories and build the right targets for these supported architectures. -# -# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable. -# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable. -# -# x86_64 targets are named to include x86_64 as a suffix and directories -# for includes are in x86_64 sub-directory. s390x and aarch64 follow the -# same convention. "uname -m" doesn't result in the correct mapping for -# s390x and aarch64. -# -# No change necessary for x86_64 -UNAME_M := $(shell uname -m) - -# Set UNAME_M for arm64 compile/install to work -ifeq ($(ARCH),arm64) - UNAME_M := aarch64 -endif -# Set UNAME_M s390x compile/install to work -ifeq ($(ARCH),s390) - UNAME_M := s390x -endif -# Set UNAME_M riscv compile/install to work -ifeq ($(ARCH),riscv) - UNAME_M := riscv +ifeq ($(ARCH),x86) + ARCH_DIR := x86_64 +else ifeq ($(ARCH),arm64) + ARCH_DIR := aarch64 +else ifeq ($(ARCH),s390) + ARCH_DIR := s390x +else + ARCH_DIR := $(ARCH) endif LIBKVM += lib/assert.c @@ -196,10 +175,15 @@ TEST_GEN_PROGS_riscv += kvm_page_table_test TEST_GEN_PROGS_riscv += set_memory_region_test TEST_GEN_PROGS_riscv += kvm_binary_stats_test -TEST_PROGS += $(TEST_PROGS_$(UNAME_M)) -TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) -TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(UNAME_M)) -LIBKVM += $(LIBKVM_$(UNAME_M)) +TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR)) +TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR)) +TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR)) +LIBKVM += $(LIBKVM_$(ARCH_DIR)) + +# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most +# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`, +# which causes the environment variable to override the makefile). +include ../lib.mk INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ @@ -210,25 +194,23 @@ else LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include endif CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ + -Wno-gnu-variable-sized-type-not-at-end \ + -fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ - -I$(<D) -Iinclude/$(UNAME_M) -I ../rseq -I.. $(EXTRA_CFLAGS) \ + -I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \ $(KHDR_INCLUDES) -no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ - $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie) +no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \ + $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) # On s390, build the testcases KVM-enabled -pgste-option = $(call try-run, echo 'int main() { return 0; }' | \ +pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \ $(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste) LDLIBS += -ldl LDFLAGS += -pthread $(no-pie-option) $(pgste-option) -# After inclusion, $(OUTPUT) is defined and -# $(TEST_GEN_PROGS) starts with $(OUTPUT)/ -include ../lib.mk - LIBKVM_C := $(filter %.c,$(LIBKVM)) LIBKVM_S := $(filter %.S,$(LIBKVM)) LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index 95d22cfb7b41..beb944fa6fd4 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -117,7 +117,7 @@ static void guest_cas(void) GUEST_ASSERT(guest_check_lse()); asm volatile(".arch_extension lse\n" "casal %0, %1, [%2]\n" - :: "r" (0), "r" (TEST_DATA), "r" (guest_test_memory)); + :: "r" (0ul), "r" (TEST_DATA), "r" (guest_test_memory)); val = READ_ONCE(*guest_test_memory); GUEST_ASSERT_EQ(val, TEST_DATA); } diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index 562c16dfbb00..f212bd8ab93d 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -14,11 +14,13 @@ static vm_vaddr_t *ucall_exit_mmio_addr; void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) { - virt_pg_map(vm, mmio_gpa, mmio_gpa); + vm_vaddr_t mmio_gva = vm_vaddr_unused_gap(vm, vm->page_size, KVM_UTIL_MIN_VADDR); + + virt_map(vm, mmio_gva, mmio_gpa, 1); vm->ucall_mmio_addr = mmio_gpa; - write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gpa); + write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gva); } void ucall_arch_do_ucall(vm_vaddr_t uc) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index c88c3ace16d2..56d5ea949cbb 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -186,6 +186,15 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); +/* + * Initializes vm->vpages_valid to match the canonical VA space of the + * architecture. + * + * The default implementation is valid for architectures which split the + * range addressed by a single page table into a low and high region + * based on the MSB of the VA. On architectures with this behavior + * the VA region spans [0, 2^(va_bits - 1)), [-(2^(va_bits - 1), -1]. + */ __weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm) { sparsebit_set_num(vm->vpages_valid, @@ -1416,10 +1425,10 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, while (npages--) { virt_pg_map(vm, vaddr, paddr); + sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift); + vaddr += page_size; paddr += page_size; - - sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift); } } diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c index 0cc0971ce60e..2f0e2ea941cc 100644 --- a/tools/testing/selftests/kvm/lib/ucall_common.c +++ b/tools/testing/selftests/kvm/lib/ucall_common.c @@ -4,6 +4,8 @@ #include "linux/bitmap.h" #include "linux/atomic.h" +#define GUEST_UCALL_FAILED -1 + struct ucall_header { DECLARE_BITMAP(in_use, KVM_MAX_VCPUS); struct ucall ucalls[KVM_MAX_VCPUS]; @@ -41,7 +43,8 @@ static struct ucall *ucall_alloc(void) struct ucall *uc; int i; - GUEST_ASSERT(ucall_pool); + if (!ucall_pool) + goto ucall_failed; for (i = 0; i < KVM_MAX_VCPUS; ++i) { if (!test_and_set_bit(i, ucall_pool->in_use)) { @@ -51,7 +54,13 @@ static struct ucall *ucall_alloc(void) } } - GUEST_ASSERT(0); +ucall_failed: + /* + * If the vCPU cannot grab a ucall structure, make a bare ucall with a + * magic value to signal to get_ucall() that things went sideways. + * GUEST_ASSERT() depends on ucall_alloc() and so cannot be used here. + */ + ucall_arch_do_ucall(GUEST_UCALL_FAILED); return NULL; } @@ -93,6 +102,9 @@ uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) addr = ucall_arch_get_ucall(vcpu); if (addr) { + TEST_ASSERT(addr != (void *)GUEST_UCALL_FAILED, + "Guest failed to allocate ucall struct"); + memcpy(uc, addr, sizeof(*uc)); vcpu_run_complete_io(vcpu); } else { diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index c4d368d56cfe..acfa1d01e7df 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1031,7 +1031,7 @@ bool is_amd_cpu(void) void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) { if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) { - *pa_bits == kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32; + *pa_bits = kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32; *va_bits = 32; } else { *pa_bits = kvm_cpu_property(X86_PROPERTY_MAX_PHY_ADDR); diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index e698306bf49d..e6587e193490 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -265,6 +265,9 @@ static uint64_t get_max_slots(struct vm_data *data, uint32_t host_page_size) slots = data->nslots; while (--slots > 1) { pages_per_slot = mempages / slots; + if (!pages_per_slot) + continue; + rempages = mempages % pages_per_slot; if (check_slot_pages(host_page_size, guest_page_size, pages_per_slot, rempages)) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c index 8b791eac7d5a..0cbb0e646ef8 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c @@ -193,8 +193,9 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa) GUEST_SYNC(stage++); /* * 'XMM Fast' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL. - * Nothing to write anything to XMM regs. */ + ipi_ex->vp_set.valid_bank_mask = 0; + hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 2); hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT, IPI_VECTOR, HV_GENERIC_SET_ALL); nop_loop(); diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c index e497ace629c1..b34980d45648 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c @@ -41,8 +41,17 @@ static void guest_int_handler(struct ex_regs *regs) static void l2_guest_code_int(void) { GUEST_ASSERT_1(int_fired == 1, int_fired); - vmmcall(); - ud2(); + + /* + * Same as the vmmcall() function, but with a ud2 sneaked after the + * vmmcall. The caller injects an exception with the return address + * increased by 2, so the "pop rbp" must be after the ud2 and we cannot + * use vmmcall() directly. + */ + __asm__ __volatile__("push %%rbp; vmmcall; ud2; pop %%rbp" + : : "a"(0xdeadbeef), "c"(0xbeefdead) + : "rbx", "rdx", "rsi", "rdi", "r8", "r9", + "r10", "r11", "r12", "r13", "r14", "r15"); GUEST_ASSERT_1(bp_fired == 1, bp_fired); hlt(); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index 5943187e8594..ff8ecdf32ae0 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -49,11 +49,6 @@ enum { NUM_VMX_PAGES, }; -struct kvm_single_msr { - struct kvm_msrs header; - struct kvm_msr_entry entry; -} __attribute__((packed)); - /* The virtual machine object. */ static struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 721f6a693799..dae510c263b4 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -962,6 +962,12 @@ int main(int argc, char *argv[]) } done: + struct kvm_xen_hvm_attr evt_reset = { + .type = KVM_XEN_ATTR_TYPE_EVTCHN, + .u.evtchn.flags = KVM_XEN_EVTCHN_RESET, + }; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset); + alarm(0); clock_gettime(CLOCK_REALTIME, &max_ts); diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h index 6d1fccd3d86c..b68920d52750 100644 --- a/tools/virtio/ringtest/main.h +++ b/tools/virtio/ringtest/main.h @@ -140,25 +140,19 @@ static inline void busy_wait(void) #define smp_wmb() smp_release() #endif -#ifdef __alpha__ -#define smp_read_barrier_depends() smp_acquire() -#else -#define smp_read_barrier_depends() do {} while(0) -#endif - static __always_inline void __read_once_size(const volatile void *p, void *res, int size) { - switch (size) { \ - case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break; \ - case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break; \ - case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break; \ - case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break; \ - default: \ - barrier(); \ - __builtin_memcpy((void *)res, (const void *)p, size); \ - barrier(); \ - } \ + switch (size) { + case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break; + case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break; + case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break; + case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break; + default: + barrier(); + __builtin_memcpy((void *)res, (const void *)p, size); + barrier(); + } } static __always_inline void __write_once_size(volatile void *p, void *res, int size) @@ -175,13 +169,22 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s } } +#ifdef __alpha__ #define READ_ONCE(x) \ ({ \ union { typeof(x) __val; char __c[1]; } __u; \ __read_once_size(&(x), __u.__c, sizeof(x)); \ - smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \ + smp_mb(); /* Enforce dependency ordering from x */ \ + __u.__val; \ +}) +#else +#define READ_ONCE(x) \ +({ \ + union { typeof(x) __val; char __c[1]; } __u; \ + __read_once_size(&(x), __u.__c, sizeof(x)); \ __u.__val; \ }) +#endif #define WRITE_ONCE(x, val) \ ({ \ diff --git a/tools/virtio/virtio-trace/trace-agent-ctl.c b/tools/virtio/virtio-trace/trace-agent-ctl.c index 73d253d4b559..39860be6e2d8 100644 --- a/tools/virtio/virtio-trace/trace-agent-ctl.c +++ b/tools/virtio/virtio-trace/trace-agent-ctl.c @@ -75,7 +75,7 @@ static int wait_order(int ctl_fd) if (ret) break; - }; + } return ret; diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index 86a410ddcedd..120062f94590 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -173,7 +173,7 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq, long started = 0, completed = 0, next_reset = reset_n; long completed_before, started_before; int r, test = 1; - unsigned len; + unsigned int len; long long spurious = 0; const bool random_batch = batch == RANDOM_BATCH; diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c index fa87b58bd5fa..98ff808d6f0c 100644 --- a/tools/virtio/vringh_test.c +++ b/tools/virtio/vringh_test.c @@ -308,6 +308,7 @@ static int parallel_test(u64 features, gvdev.vdev.features = features; INIT_LIST_HEAD(&gvdev.vdev.vqs); + spin_lock_init(&gvdev.vdev.vqs_list_lock); gvdev.to_host_fd = to_host[1]; gvdev.notifies = 0; @@ -455,6 +456,7 @@ int main(int argc, char *argv[]) getrange = getrange_iov; vdev.features = 0; INIT_LIST_HEAD(&vdev.vqs); + spin_lock_init(&vdev.vqs_list_lock); while (argv[1]) { if (strcmp(argv[1], "--indirect") == 0) diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h index a1ab15006af3..180f1a09e6ba 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -14,14 +14,10 @@ #define KVM_MMU_LOCK_INIT(kvm) rwlock_init(&(kvm)->mmu_lock) #define KVM_MMU_LOCK(kvm) write_lock(&(kvm)->mmu_lock) #define KVM_MMU_UNLOCK(kvm) write_unlock(&(kvm)->mmu_lock) -#define KVM_MMU_READ_LOCK(kvm) read_lock(&(kvm)->mmu_lock) -#define KVM_MMU_READ_UNLOCK(kvm) read_unlock(&(kvm)->mmu_lock) #else #define KVM_MMU_LOCK_INIT(kvm) spin_lock_init(&(kvm)->mmu_lock) #define KVM_MMU_LOCK(kvm) spin_lock(&(kvm)->mmu_lock) #define KVM_MMU_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock) -#define KVM_MMU_READ_LOCK(kvm) spin_lock(&(kvm)->mmu_lock) -#define KVM_MMU_READ_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock) #endif /* KVM_HAVE_MMU_RWLOCK */ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible, |