diff options
401 files changed, 7684 insertions, 4033 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 9725c546a0d4..4eaefb0983a8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2413,8 +2413,12 @@ Default is 1 (enabled) kvm-intel.emulate_invalid_guest_state= - [KVM,Intel] Enable emulation of invalid guest states - Default is 0 (disabled) + [KVM,Intel] Disable emulation of invalid guest state. + Ignored if kvm-intel.enable_unrestricted_guest=1, as + guest state is never invalid for unrestricted guests. + This param doesn't apply to nested guests (L2), as KVM + never emulates invalid L2 guest state. + Default is 1 (enabled) kvm-intel.flexpriority= [KVM,Intel] Disable FlexPriority feature (TPR shadow). @@ -4144,6 +4148,14 @@ Override pmtimer IOPort with a hex value. e.g. pmtmr=0x508 + pmu_override= [PPC] Override the PMU. + This option takes over the PMU facility, so it is no + longer usable by perf. Setting this option starts the + PMU counters by setting MMCR0 to 0 (the FC bit is + cleared). If a number is given, then MMCR1 is set to + that number, otherwise (e.g., 'pmu_override=on'), MMCR1 + remains 0. + pm_debug_messages [SUSPEND,KNL] Enable suspend/resume debug messages during boot up. diff --git a/Documentation/arm64/pointer-authentication.rst b/Documentation/arm64/pointer-authentication.rst index f127666ea3a8..e5dad2e40aa8 100644 --- a/Documentation/arm64/pointer-authentication.rst +++ b/Documentation/arm64/pointer-authentication.rst @@ -53,11 +53,10 @@ The number of bits that the PAC occupies in a pointer is 55 minus the virtual address size configured by the kernel. For example, with a virtual address size of 48, the PAC is 7 bits wide. -Recent versions of GCC can compile code with APIAKey-based return -address protection when passed the -msign-return-address option. This -uses instructions in the HINT space (unless -march=armv8.3-a or higher -is also passed), and such code can run on systems without the pointer -authentication extension. +When ARM64_PTR_AUTH_KERNEL is selected, the kernel will be compiled +with HINT space pointer authentication instructions protecting +function returns. Kernels built with this option will work on hardware +with or without pointer authentication support. In addition to exec(), keys can also be reinitialized to random values using the PR_PAC_RESET_KEYS prctl. A bitmask of PR_PAC_APIAKEY, diff --git a/Documentation/cpu-freq/core.rst b/Documentation/cpu-freq/core.rst index 33cb90bd1d8f..4ceef8e7217c 100644 --- a/Documentation/cpu-freq/core.rst +++ b/Documentation/cpu-freq/core.rst @@ -73,12 +73,12 @@ CPUFREQ_POSTCHANGE. The third argument is a struct cpufreq_freqs with the following values: -===== =========================== -cpu number of the affected CPU +====== ====================================== +policy a pointer to the struct cpufreq_policy old old frequency new new frequency flags flags of the cpufreq driver -===== =========================== +====== ====================================== 3. CPUFreq Table Generation with Operating Performance Point (OPP) ================================================================== diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index bb68d39f03b7..375baca7edcd 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ================================= -NETWORK FILESYSTEM HELPER LIBRARY +Network Filesystem Helper Library ================================= .. Contents: @@ -37,22 +37,22 @@ into a common call framework. The following services are provided: - * Handles transparent huge pages (THPs). + * Handle folios that span multiple pages. - * Insulates the netfs from VM interface changes. + * Insulate the netfs from VM interface changes. - * Allows the netfs to arbitrarily split reads up into pieces, even ones that - don't match page sizes or page alignments and that may cross pages. + * Allow the netfs to arbitrarily split reads up into pieces, even ones that + don't match folio sizes or folio alignments and that may cross folios. - * Allows the netfs to expand a readahead request in both directions to meet - its needs. + * Allow the netfs to expand a readahead request in both directions to meet its + needs. - * Allows the netfs to partially fulfil a read, which will then be resubmitted. + * Allow the netfs to partially fulfil a read, which will then be resubmitted. - * Handles local caching, allowing cached data and server-read data to be + * Handle local caching, allowing cached data and server-read data to be interleaved for a single request. - * Handles clearing of bufferage that aren't on the server. + * Handle clearing of bufferage that aren't on the server. * Handle retrying of reads that failed, switching reads from the cache to the server as necessary. @@ -70,22 +70,22 @@ Read Helper Functions Three read helpers are provided:: - * void netfs_readahead(struct readahead_control *ractl, - const struct netfs_read_request_ops *ops, - void *netfs_priv);`` - * int netfs_readpage(struct file *file, - struct page *page, - const struct netfs_read_request_ops *ops, - void *netfs_priv); - * int netfs_write_begin(struct file *file, - struct address_space *mapping, - loff_t pos, - unsigned int len, - unsigned int flags, - struct page **_page, - void **_fsdata, - const struct netfs_read_request_ops *ops, - void *netfs_priv); + void netfs_readahead(struct readahead_control *ractl, + const struct netfs_read_request_ops *ops, + void *netfs_priv); + int netfs_readpage(struct file *file, + struct folio *folio, + const struct netfs_read_request_ops *ops, + void *netfs_priv); + int netfs_write_begin(struct file *file, + struct address_space *mapping, + loff_t pos, + unsigned int len, + unsigned int flags, + struct folio **_folio, + void **_fsdata, + const struct netfs_read_request_ops *ops, + void *netfs_priv); Each corresponds to a VM operation, with the addition of a couple of parameters for the use of the read helpers: @@ -103,8 +103,8 @@ Both of these values will be stored into the read request structure. For ->readahead() and ->readpage(), the network filesystem should just jump into the corresponding read helper; whereas for ->write_begin(), it may be a little more complicated as the network filesystem might want to flush -conflicting writes or track dirty data and needs to put the acquired page if an -error occurs after calling the helper. +conflicting writes or track dirty data and needs to put the acquired folio if +an error occurs after calling the helper. The helpers manage the read request, calling back into the network filesystem through the suppplied table of operations. Waits will be performed as @@ -253,7 +253,7 @@ through which it can issue requests and negotiate:: void (*issue_op)(struct netfs_read_subrequest *subreq); bool (*is_still_valid)(struct netfs_read_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, - struct page *page, void **_fsdata); + struct folio *folio, void **_fsdata); void (*done)(struct netfs_read_request *rreq); void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; @@ -313,13 +313,14 @@ The operations are as follows: There is no return value; the netfs_subreq_terminated() function should be called to indicate whether or not the operation succeeded and how much data - it transferred. The filesystem also should not deal with setting pages + it transferred. The filesystem also should not deal with setting folios uptodate, unlocking them or dropping their refs - the helpers need to deal with this as they have to coordinate with copying to the local cache. - Note that the helpers have the pages locked, but not pinned. It is possible - to use the ITER_XARRAY iov iterator to refer to the range of the inode that - is being operated upon without the need to allocate large bvec tables. + Note that the helpers have the folios locked, but not pinned. It is + possible to use the ITER_XARRAY iov iterator to refer to the range of the + inode that is being operated upon without the need to allocate large bvec + tables. * ``is_still_valid()`` @@ -330,15 +331,15 @@ The operations are as follows: * ``check_write_begin()`` [Optional] This is called from the netfs_write_begin() helper once it has - allocated/grabbed the page to be modified to allow the filesystem to flush + allocated/grabbed the folio to be modified to allow the filesystem to flush conflicting state before allowing it to be modified. - It should return 0 if everything is now fine, -EAGAIN if the page should be + It should return 0 if everything is now fine, -EAGAIN if the folio should be regrabbed and any other error code to abort the operation. * ``done`` - [Optional] This is called after the pages in the request have all been + [Optional] This is called after the folios in the request have all been unlocked (and marked uptodate if applicable). * ``cleanup`` @@ -390,7 +391,7 @@ The read helpers work by the following general procedure: * If NETFS_SREQ_CLEAR_TAIL was set, a short read will be cleared to the end of the slice instead of reissuing. - * Once the data is read, the pages that have been fully read/cleared: + * Once the data is read, the folios that have been fully read/cleared: * Will be marked uptodate. @@ -398,11 +399,11 @@ The read helpers work by the following general procedure: * Unlocked - * Any pages that need writing to the cache will then have DIO writes issued. + * Any folios that need writing to the cache will then have DIO writes issued. * Synchronous operations will wait for reading to be complete. - * Writes to the cache will proceed asynchronously and the pages will have the + * Writes to the cache will proceed asynchronously and the folios will have the PG_fscache mark removed when that completes. * The request structures will be cleaned up when everything has completed. @@ -452,6 +453,9 @@ operation table looks like the following:: netfs_io_terminated_t term_func, void *term_func_priv); + int (*prepare_write)(struct netfs_cache_resources *cres, + loff_t *_start, size_t *_len, loff_t i_size); + int (*write)(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, @@ -509,6 +513,14 @@ The methods defined in the table are: indicating whether the termination is definitely happening in the caller's context. + * ``prepare_write()`` + + [Required] Called to adjust a write to the cache and check that there is + sufficient space in the cache. The start and length values indicate the + size of the write that netfslib is proposing, and this can be adjusted by + the cache to respect DIO boundaries. The file size is passed for + information. + * ``write()`` [Required] Called to write to the cache. The start file offset is given @@ -525,4 +537,9 @@ not the read request structure as they could be used in other situations where there isn't a read request structure as well, such as writing dirty data to the cache. + +API Function Reference +====================== + .. kernel-doc:: include/linux/netfs.h +.. kernel-doc:: fs/netfs/read_helper.c diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index aeeb071c7688..b86c7edae888 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -3701,7 +3701,7 @@ KVM with the currently defined set of flags. :Architectures: s390 :Type: vm ioctl :Parameters: struct kvm_s390_skeys -:Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage +:Returns: 0 on success, KVM_S390_GET_SKEYS_NONE if guest is not using storage keys, negative value on error This ioctl is used to get guest storage key values on the s390 @@ -3720,7 +3720,7 @@ you want to get. The count field is the number of consecutive frames (starting from start_gfn) whose storage keys to get. The count field must be at least 1 and the maximum -allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range +allowed value is defined as KVM_S390_SKEYS_MAX. Values outside this range will cause the ioctl to return -EINVAL. The skeydata_addr field is the address to a buffer large enough to hold count @@ -3744,7 +3744,7 @@ you want to set. The count field is the number of consecutive frames (starting from start_gfn) whose storage keys to get. The count field must be at least 1 and the maximum -allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range +allowed value is defined as KVM_S390_SKEYS_MAX. Values outside this range will cause the ioctl to return -EINVAL. The skeydata_addr field is the address to a buffer containing count bytes of diff --git a/Documentation/virt/kvm/mmu.rst b/Documentation/virt/kvm/mmu.rst index f60f5488e121..5b1ebad24c77 100644 --- a/Documentation/virt/kvm/mmu.rst +++ b/Documentation/virt/kvm/mmu.rst @@ -161,7 +161,7 @@ Shadow pages contain the following information: If clear, this page corresponds to a guest page table denoted by the gfn field. role.quadrant: - When role.gpte_is_8_bytes=0, the guest uses 32-bit gptes while the host uses 64-bit + When role.has_4_byte_gpte=1, the guest uses 32-bit gptes while the host uses 64-bit sptes. That means a guest page table contains more ptes than the host, so multiple shadow pages are needed to shadow one guest page. For first-level shadow pages, role.quadrant can be 0 or 1 and denotes the @@ -177,9 +177,9 @@ Shadow pages contain the following information: The page is invalid and should not be used. It is a root page that is currently pinned (by a cpu hardware register pointing to it); once it is unpinned it will be destroyed. - role.gpte_is_8_bytes: - Reflects the size of the guest PTE for which the page is valid, i.e. '1' - if 64-bit gptes are in use, '0' if 32-bit gptes are in use. + role.has_4_byte_gpte: + Reflects the size of the guest PTE for which the page is valid, i.e. '0' + if direct map or 64-bit gptes are in use, '1' if 32-bit gptes are in use. role.efer_nx: Contains the value of efer.nx for which the page is valid. role.cr0_wp: diff --git a/MAINTAINERS b/MAINTAINERS index 360e9aa0205d..43007f2d29e0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15979,6 +15979,7 @@ F: arch/mips/generic/board-ranchu.c RANDOM NUMBER DRIVER M: "Theodore Ts'o" <[email protected]> +M: Jason A. Donenfeld <[email protected]> S: Maintained F: drivers/char/random.c @@ -16501,6 +16502,12 @@ T: git git://linuxtv.org/media_tree.git F: Documentation/devicetree/bindings/media/allwinner,sun8i-a83t-de2-rotate.yaml F: drivers/media/platform/sunxi/sun8i-rotate/ +RPMSG TTY DRIVER +M: Arnaud Pouliquen <[email protected]> +S: Maintained +F: drivers/tty/rpmsg_tty.c + RTL2830 MEDIA DRIVER M: Antti Palosaari <[email protected]> @@ -16623,7 +16630,8 @@ F: drivers/iommu/s390-iommu.c S390 IUCV NETWORK LAYER M: Julian Wiedmann <[email protected]> -M: Karsten Graul <[email protected]> +M: Alexandra Winter <[email protected]> +M: Wenjia Zhang <[email protected]> S: Supported @@ -16634,7 +16642,8 @@ F: net/iucv/ S390 NETWORK DRIVERS M: Julian Wiedmann <[email protected]> -M: Karsten Graul <[email protected]> +M: Alexandra Winter <[email protected]> +M: Wenjia Zhang <[email protected]> S: Supported @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Gobble Gobble # *DOCUMENTATION* diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index a39fcf318c77..01d47c5886dc 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -91,7 +91,7 @@ #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) /* TCR_EL2 Registers bits */ -#define TCR_EL2_RES1 ((1 << 31) | (1 << 23)) +#define TCR_EL2_RES1 ((1U << 31) | (1 << 23)) #define TCR_EL2_TBI (1 << 20) #define TCR_EL2_PS_SHIFT 16 #define TCR_EL2_PS_MASK (7 << TCR_EL2_PS_SHIFT) @@ -276,7 +276,7 @@ #define CPTR_EL2_TFP_SHIFT 10 /* Hyp Coprocessor Trap Register */ -#define CPTR_EL2_TCPAC (1 << 31) +#define CPTR_EL2_TCPAC (1U << 31) #define CPTR_EL2_TAM (1 << 30) #define CPTR_EL2_TTA (1 << 20) #define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index cd5fd9b92b04..d62405ce3e6d 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -41,6 +41,8 @@ void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +void kvm_vcpu_wfi(struct kvm_vcpu *vcpu); + static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { return !(vcpu->arch.hcr_el2 & HCR_RW); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index ceef621db64e..3b44ea17af88 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -712,7 +712,6 @@ void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu); static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} void kvm_arm_init_debug(void); void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index b3e4f9a088b1..8cf970d219f5 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -77,11 +77,17 @@ .endm SYM_CODE_START(ftrace_regs_caller) +#ifdef BTI_C + BTI_C +#endif ftrace_regs_entry 1 b ftrace_common SYM_CODE_END(ftrace_regs_caller) SYM_CODE_START(ftrace_caller) +#ifdef BTI_C + BTI_C +#endif ftrace_regs_entry 0 b ftrace_common SYM_CODE_END(ftrace_caller) diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 1038494135c8..6fb31c117ebe 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -147,7 +147,7 @@ int machine_kexec_post_load(struct kimage *kimage) if (rc) return rc; kimage->arch.ttbr1 = __pa(trans_pgd); - kimage->arch.zero_page = __pa(empty_zero_page); + kimage->arch.zero_page = __pa_symbol(empty_zero_page); reloc_size = __relocate_new_kernel_end - __relocate_new_kernel_start; memcpy(reloc_code, __relocate_new_kernel_start, reloc_size); diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 8ffcbe29395e..f1f8fc069a97 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -39,6 +39,7 @@ menuconfig KVM select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_VCPU_RUN_PID_CHANGE select SCHED_INFO + select INTERVAL_TREE help Support hosting virtualized guest machines. diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 8ca8cf6f5619..39b11a4f9063 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -5,14 +5,12 @@ ccflags-y += -I $(srctree)/$(src) -KVM=../../../virt/kvm +include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM) += hyp/ -kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ - $(KVM)/vfio.o $(KVM)/irqchip.o $(KVM)/binary_stats.o \ - arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ +kvm-y += arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o \ vgic-sys-reg-v3.o fpsimd.o pmu.o pkvm.o \ diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 3df67c127489..6e542e2eae32 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -467,7 +467,7 @@ out: } /* - * Schedule the background timer before calling kvm_vcpu_block, so that this + * Schedule the background timer before calling kvm_vcpu_halt, so that this * thread is removed from its waitqueue and made runnable when there's a timer * interrupt to handle. */ @@ -649,7 +649,6 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; - struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); if (unlikely(!timer->enabled)) return; @@ -672,7 +671,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); - if (rcuwait_active(wait)) + if (kvm_vcpu_is_blocking(vcpu)) kvm_timer_blocking(vcpu); /* @@ -750,7 +749,7 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) /* Make the updates of cntvoff for all vtimer contexts atomic */ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff) { - int i; + unsigned long i; struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tmp; @@ -1189,8 +1188,8 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) { - int vtimer_irq, ptimer_irq; - int i, ret; + int vtimer_irq, ptimer_irq, ret; + unsigned long i; vtimer_irq = vcpu_vtimer(vcpu)->irq.irq; ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu)); @@ -1297,7 +1296,7 @@ void kvm_timer_init_vhe(void) static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu_vtimer(vcpu)->irq.irq = vtimer_irq; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 6057f3c5aafe..868109cf96b4 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -175,19 +175,11 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) */ void kvm_arch_destroy_vm(struct kvm *kvm) { - int i; - bitmap_free(kvm->arch.pmu_filter); kvm_vgic_destroy(kvm); - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - atomic_set(&kvm->online_vcpus, 0); + kvm_destroy_vcpus(kvm); kvm_unshare_hyp(kvm, kvm + 1); } @@ -370,27 +362,12 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { - /* - * If we're about to block (most likely because we've just hit a - * WFI), we need to sync back the state of the GIC CPU interface - * so that we have the latest PMR and group enables. This ensures - * that kvm_arch_vcpu_runnable has up-to-date data to decide - * whether we have pending interrupts. - * - * For the same reason, we want to tell GICv4 that we need - * doorbells to be signalled, should an interrupt become pending. - */ - preempt_disable(); - kvm_vgic_vmcr_sync(vcpu); - vgic_v4_put(vcpu, true); - preempt_enable(); + } void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - preempt_disable(); - vgic_v4_load(vcpu); - preempt_enable(); + } void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -660,7 +637,7 @@ bool kvm_arch_intc_initialized(struct kvm *kvm) void kvm_arm_halt_guest(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) @@ -670,12 +647,12 @@ void kvm_arm_halt_guest(struct kvm *kvm) void kvm_arm_resume_guest(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.pause = false; - rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); + __kvm_vcpu_wake_up(vcpu); } } @@ -700,6 +677,39 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu) smp_rmb(); } +/** + * kvm_vcpu_wfi - emulate Wait-For-Interrupt behavior + * @vcpu: The VCPU pointer + * + * Suspend execution of a vCPU until a valid wake event is detected, i.e. until + * the vCPU is runnable. The vCPU may or may not be scheduled out, depending + * on when a wake event arrives, e.g. there may already be a pending wake event. + */ +void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) +{ + /* + * Sync back the state of the GIC CPU interface so that we have + * the latest PMR and group enables. This ensures that + * kvm_arch_vcpu_runnable has up-to-date data to decide whether + * we have pending interrupts, e.g. when determining if the + * vCPU should block. + * + * For the same reason, we want to tell GICv4 that we need + * doorbells to be signalled, should an interrupt become pending. + */ + preempt_disable(); + kvm_vgic_vmcr_sync(vcpu); + vgic_v4_put(vcpu, true); + preempt_enable(); + + kvm_vcpu_halt(vcpu); + kvm_clear_request(KVM_REQ_UNHALT, vcpu); + + preempt_disable(); + vgic_v4_load(vcpu); + preempt_enable(); +} + static void check_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_request_pending(vcpu)) { @@ -2045,7 +2055,7 @@ static int finalize_hyp_mode(void) struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; mpidr &= MPIDR_HWID_BITMASK; kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 275a27368a04..6d0baf71aa67 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -82,7 +82,7 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu) * * WFE: Yield the CPU and come back to this vcpu when the scheduler * decides to. - * WFI: Simply call kvm_vcpu_block(), which will halt execution of + * WFI: Simply call kvm_vcpu_halt(), which will halt execution of * world-switches and schedule other host processes until there is an * incoming IRQ or FIQ to the VM. */ @@ -95,8 +95,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu) } else { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false); vcpu->stat.wfi_exit_stat++; - kvm_vcpu_block(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); + kvm_vcpu_wfi(vcpu); } kvm_incr_pc(vcpu); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 11e8580f2fdc..58e14f8ead23 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -381,6 +381,8 @@ typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *); static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu); +static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code); + /* * Allow the hypervisor to handle the exit with an exit handler if it has one. * @@ -407,6 +409,18 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code) */ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { + /* + * Save PSTATE early so that we can evaluate the vcpu mode + * early on. + */ + vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR); + + /* + * Check whether we want to repaint the state one way or + * another. + */ + early_exit_filter(vcpu, exit_code); + if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index de7e14c862e6..7ecca8b07851 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -70,7 +70,12 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) { ctxt->regs.pc = read_sysreg_el2(SYS_ELR); - ctxt->regs.pstate = read_sysreg_el2(SYS_SPSR); + /* + * Guest PSTATE gets saved at guest fixup time in all + * cases. We still need to handle the nVHE host side here. + */ + if (!has_vhe() && ctxt->__hyp_running_vcpu) + ctxt->regs.pstate = read_sysreg_el2(SYS_SPSR); if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2); diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 329c706af39f..6410d21d8695 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -232,7 +232,7 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) * Returns false if the guest ran in AArch32 when it shouldn't have, and * thus should exit to the host, or true if a the guest run loop can continue. */ -static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code) +static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) { struct kvm *kvm = kern_hyp_va(vcpu->kvm); @@ -247,10 +247,7 @@ static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code) vcpu->arch.target = -1; *exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT); *exit_code |= ARM_EXCEPTION_IL; - return false; } - - return true; } /* Switch to the guest for legacy non-VHE systems */ @@ -315,9 +312,6 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) /* Jump in the fire! */ exit_code = __guest_enter(vcpu); - if (unlikely(!handle_aarch32_guest(vcpu, &exit_code))) - break; - /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 1d162b9c78bf..11d053fdd604 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -111,6 +111,10 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) return hyp_exit_handlers; } +static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) +{ +} + /* Switch to the guest for VHE systems running in EL2 */ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 9a43373c7c45..bc2aba953299 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -210,13 +210,13 @@ static void stage2_flush_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int idx; + int idx, bkt; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) + kvm_for_each_memslot(memslot, bkt, slots) stage2_flush_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); @@ -716,14 +716,14 @@ void stage2_unmap_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int idx; + int idx, bkt; idx = srcu_read_lock(&kvm->srcu); mmap_read_lock(current->mm); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) + kvm_for_each_memslot(memslot, bkt, slots) stage2_unmap_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); @@ -1587,7 +1587,6 @@ out: } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -1597,25 +1596,24 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * allocated dirty_bitmap[], dirty pages will be tracked while the * memory slot is write protected. */ - if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) { /* * If we're with initial-all-set, we don't need to write * protect any pages because they're all reported as dirty. * Huge pages and normal pages will be write protect gradually. */ if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) { - kvm_mmu_wp_memory_region(kvm, mem->slot); + kvm_mmu_wp_memory_region(kvm, new->id); } } } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - hva_t hva = mem->userspace_addr; - hva_t reg_end = hva + mem->memory_size; + hva_t hva, reg_end; int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && @@ -1626,9 +1624,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the IPA * space addressable by the KVM guest IPA space. */ - if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT)) + if ((new->base_gfn + new->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT)) return -EFAULT; + hva = new->userspace_addr; + reg_end = hva + (new->npages << PAGE_SHIFT); + mmap_read_lock(current->mm); /* * A memory region could potentially cover multiple VMAs, and any holes @@ -1660,7 +1661,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (vma->vm_flags & VM_PFNMAP) { /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; break; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index ca92cc5c71c6..a123c89238df 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -901,7 +901,7 @@ static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu) */ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 9b82d6878aac..3eae32876897 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -46,7 +46,7 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) * specification (ARM DEN 0022A). This means all suspend states * for KVM will preserve the register state. */ - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); return PSCI_RET_SUCCESS; @@ -121,8 +121,8 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) { - int i, matching_cpus = 0; - unsigned long mpidr; + int matching_cpus = 0; + unsigned long i, mpidr; unsigned long target_affinity; unsigned long target_affinity_mask; unsigned long lowest_affinity_level; @@ -164,7 +164,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type) { - int i; + unsigned long i; struct kvm_vcpu *tmp; /* diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 1cd1c10b6190..25e0041d840b 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -185,7 +185,7 @@ static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) { struct kvm_vcpu *tmp; bool is32bit; - int i; + unsigned long i; is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index ce2b42c38e62..fc00304fe7d8 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -70,8 +70,9 @@ void kvm_vgic_early_init(struct kvm *kvm) */ int kvm_vgic_create(struct kvm *kvm, u32 type) { - int i, ret; struct kvm_vcpu *vcpu; + unsigned long i; + int ret; if (irqchip_in_kernel(kvm)) return -EEXIST; @@ -255,7 +256,8 @@ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0, i, idx; + int ret = 0, i; + unsigned long idx; if (vgic_initialized(kvm)) return 0; @@ -308,7 +310,7 @@ int vgic_init(struct kvm *kvm) goto out; } - kvm_for_each_vcpu(i, vcpu, kvm) + kvm_for_each_vcpu(idx, vcpu, kvm) kvm_vgic_vcpu_enable(vcpu); ret = kvm_vgic_setup_default_irq_routing(kvm); @@ -370,7 +372,7 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) static void __kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; vgic_debug_destroy(kvm); diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 0d000d2fe8d2..c6d52a1fd9c8 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -325,7 +325,7 @@ void unlock_all_vcpus(struct kvm *kvm) bool lock_all_vcpus(struct kvm *kvm) { struct kvm_vcpu *tmp_vcpu; - int c; + unsigned long c; /* * Any time a vcpu is run, vcpu_load is called which tries to grab the diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c index 5f9014ae595b..12e4c223e6b8 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c @@ -113,9 +113,8 @@ static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu, int intid = val & 0xf; int targets = (val >> 16) & 0xff; int mode = (val >> 24) & 0x03; - int c; struct kvm_vcpu *vcpu; - unsigned long flags; + unsigned long flags, c; switch (mode) { case 0x0: /* as specified by targets */ diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 9943a3fe1b0a..58e40b4874f8 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -754,7 +754,8 @@ static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) static int vgic_register_all_redist_iodevs(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int c, ret = 0; + unsigned long c; + int ret = 0; kvm_for_each_vcpu(c, vcpu, kvm) { ret = vgic_register_redist_iodev(vcpu); @@ -997,10 +998,10 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) struct kvm_vcpu *c_vcpu; u16 target_cpus; u64 mpidr; - int sgi, c; + int sgi; int vcpu_id = vcpu->vcpu_id; bool broadcast; - unsigned long flags; + unsigned long c, flags; sgi = (reg & ICC_SGI1R_SGI_ID_MASK) >> ICC_SGI1R_SGI_ID_SHIFT; broadcast = reg & BIT_ULL(ICC_SGI1R_IRQ_ROUTING_MODE_BIT); diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 78cf674c1230..a33d4366b326 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -542,13 +542,13 @@ int vgic_v3_map_resources(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; int ret = 0; - int c; + unsigned long c; kvm_for_each_vcpu(c, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { - kvm_debug("vcpu %d redistributor base not set\n", c); + kvm_debug("vcpu %ld redistributor base not set\n", c); return -ENXIO; } } diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 772dd15a22c7..ad06ba6c9b00 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -189,7 +189,7 @@ void vgic_v4_configure_vsgis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_arm_halt_guest(kvm); @@ -235,7 +235,8 @@ int vgic_v4_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int i, nr_vcpus, ret; + int nr_vcpus, ret; + unsigned long i; if (!kvm_vgic_global_state.has_gicv4) return 0; /* Nothing to see here... move along. */ diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 5dad4996cfb2..9b98876a8a93 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -990,7 +990,7 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) void vgic_kick_vcpus(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int c; + unsigned long c; /* * We've injected an interrupt, time to find out who deserves diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 696f6b009377..72b90d45a46e 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -897,7 +897,6 @@ static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB int kvm_arch_flush_remote_tlb(struct kvm *kvm); diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index a77297480f56..91d197bee9c0 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -27,6 +27,7 @@ config KVM select KVM_MMIO select MMU_NOTIFIER select SRCU + select INTERVAL_TREE help Support for hosting Guest kernels. diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile index d3710959da55..21ff75bcdbc4 100644 --- a/arch/mips/kvm/Makefile +++ b/arch/mips/kvm/Makefile @@ -2,9 +2,10 @@ # Makefile for KVM support for MIPS # +include $(srctree)/virt/kvm/Makefile.kvm + ccflags-y += -Ivirt/kvm -Iarch/mips/kvm -kvm-y := $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o eventfd.o binary_stats.o) kvm-$(CONFIG_CPU_HAS_MSA) += msa.o kvm-y += mips.o emulate.o entry.o \ diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 22e745e49b0a..b494d8d39290 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -952,7 +952,7 @@ enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu) if (!vcpu->arch.pending_exceptions) { kvm_vz_lose_htimer(vcpu); vcpu->arch.wait = 1; - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); /* * We we are runnable, then definitely go off to user space to diff --git a/arch/mips/kvm/loongson_ipi.c b/arch/mips/kvm/loongson_ipi.c index 3681fc8fba38..5d53f32d837c 100644 --- a/arch/mips/kvm/loongson_ipi.c +++ b/arch/mips/kvm/loongson_ipi.c @@ -120,7 +120,7 @@ static int loongson_vipi_write(struct loongson_kvm_ipi *ipi, s->status |= data; irq.cpu = id; irq.irq = 6; - kvm_vcpu_ioctl_interrupt(kvm->vcpus[id], &irq); + kvm_vcpu_ioctl_interrupt(kvm_get_vcpu(kvm, id), &irq); break; case CORE0_CLEAR_OFF: @@ -128,7 +128,7 @@ static int loongson_vipi_write(struct loongson_kvm_ipi *ipi, if (!s->status) { irq.cpu = id; irq.irq = -6; - kvm_vcpu_ioctl_interrupt(kvm->vcpus[id], &irq); + kvm_vcpu_ioctl_interrupt(kvm_get_vcpu(kvm, id), &irq); } break; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index aa20d074d388..e59cb6246f76 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -171,25 +171,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return 0; } -void kvm_mips_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) { - kvm_vcpu_destroy(vcpu); - } - - mutex_lock(&kvm->lock); - - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - - mutex_unlock(&kvm->lock); -} - static void kvm_mips_free_gpa_pt(struct kvm *kvm) { /* It should always be safe to remove after flushing the whole range */ @@ -199,7 +180,7 @@ static void kvm_mips_free_gpa_pt(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { - kvm_mips_free_vcpus(kvm); + kvm_destroy_vcpus(kvm); kvm_mips_free_gpa_pt(kvm); } @@ -233,25 +214,20 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { int needs_flush; - kvm_debug("%s: kvm: %p slot: %d, GPA: %llx, size: %llx, QVA: %llx\n", - __func__, kvm, mem->slot, mem->guest_phys_addr, - mem->memory_size, mem->userspace_addr); - /* * If dirty page logging is enabled, write protect all pages in the slot * ready for dirty logging. @@ -498,7 +474,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, if (irq->cpu == -1) dvcpu = vcpu; else - dvcpu = vcpu->kvm->vcpus[irq->cpu]; + dvcpu = kvm_get_vcpu(vcpu->kvm, irq->cpu); if (intr == 2 || intr == 3 || intr == 4 || intr == 6) { kvm_mips_callbacks->queue_io_int(dvcpu, irq); diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 8db4af4879d0..82d77f4b0d08 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -15,7 +15,12 @@ # Mike Shaver, Helge Deller and Martin K. Petersen # +ifdef CONFIG_PARISC_SELF_EXTRACT +boot := arch/parisc/boot +KBUILD_IMAGE := $(boot)/bzImage +else KBUILD_IMAGE := vmlinuz +endif NM = sh $(srctree)/arch/parisc/nm CHECKFLAGS += -D__hppa__=1 diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index d2daeac2b217..1b8fd80cbe7f 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -1,7 +1,9 @@ CONFIG_LOCALVERSION="-64bit" # CONFIG_LOCALVERSION_AUTO is not set +CONFIG_KERNEL_LZ4=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +CONFIG_AUDIT=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -35,6 +37,7 @@ CONFIG_MODVERSIONS=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set +CONFIG_MEMORY_FAILURE=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -65,12 +68,15 @@ CONFIG_SCSI_ISCSI_ATTRS=y CONFIG_SCSI_SRP_ATTRS=y CONFIG_ISCSI_BOOT_SYSFS=y CONFIG_SCSI_MPT2SAS=y -CONFIG_SCSI_LASI700=m +CONFIG_SCSI_LASI700=y CONFIG_SCSI_SYM53C8XX_2=y CONFIG_SCSI_ZALON=y CONFIG_SCSI_QLA_ISCSI=m CONFIG_SCSI_DH=y CONFIG_ATA=y +CONFIG_SATA_SIL=y +CONFIG_SATA_SIS=y +CONFIG_SATA_VIA=y CONFIG_PATA_NS87415=y CONFIG_PATA_SIL680=y CONFIG_ATA_GENERIC=y @@ -79,6 +85,7 @@ CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_RAID=m CONFIG_DM_UEVENT=y +CONFIG_DM_AUDIT=y CONFIG_FUSION=y CONFIG_FUSION_SPI=y CONFIG_FUSION_SAS=y @@ -196,10 +203,15 @@ CONFIG_FB_MATROX_G=y CONFIG_FB_MATROX_I2C=y CONFIG_FB_MATROX_MAVEN=y CONFIG_FB_RADEON=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_CLUT224 is not set CONFIG_HIDRAW=y CONFIG_HID_PID=y CONFIG_USB_HIDDEV=y CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_UIO=y CONFIG_UIO_PDRV_GENIRQ=m CONFIG_UIO_AEC=m diff --git a/arch/parisc/install.sh b/arch/parisc/install.sh index 056d588befdd..70d3cffb0251 100644 --- a/arch/parisc/install.sh +++ b/arch/parisc/install.sh @@ -39,6 +39,7 @@ verify "$3" if [ -n "${INSTALLKERNEL}" ]; then if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi + if [ -x /usr/sbin/${INSTALLKERNEL} ]; then exec /usr/sbin/${INSTALLKERNEL} "$@"; fi fi # Default install diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 9fb1e794831b..061119a56fbe 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -249,30 +249,16 @@ void __init time_init(void) static int __init init_cr16_clocksource(void) { /* - * The cr16 interval timers are not syncronized across CPUs on - * different sockets, so mark them unstable and lower rating on - * multi-socket SMP systems. + * The cr16 interval timers are not syncronized across CPUs, even if + * they share the same socket. */ if (num_online_cpus() > 1 && !running_on_qemu) { - int cpu; - unsigned long cpu0_loc; - cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; - - for_each_online_cpu(cpu) { - if (cpu == 0) - continue; - if ((cpu0_loc != 0) && - (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc)) - continue; - - /* mark sched_clock unstable */ - clear_sched_clock_stable(); - - clocksource_cr16.name = "cr16_unstable"; - clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; - clocksource_cr16.rating = 0; - break; - } + /* mark sched_clock unstable */ + clear_sched_clock_stable(); + + clocksource_cr16.name = "cr16_unstable"; + clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; + clocksource_cr16.rating = 0; } /* register at clocksource framework */ diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 222823861a67..41b8a1e1144a 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -141,11 +141,6 @@ static inline void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ -void kvmhv_save_host_pmu(void); -void kvmhv_load_host_pmu(void); -void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use); -void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu); - void kvmppc_p9_enter_guest(struct kvm_vcpu *vcpu); long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr); diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index fbbf3cec92e9..d68d71987d5c 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -79,6 +79,7 @@ #define BOOK3S_INTERRUPT_FP_UNAVAIL 0x800 #define BOOK3S_INTERRUPT_DECREMENTER 0x900 #define BOOK3S_INTERRUPT_HV_DECREMENTER 0x980 +#define BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER 0x1980 #define BOOK3S_INTERRUPT_DOORBELL 0xa00 #define BOOK3S_INTERRUPT_SYSCALL 0xc00 #define BOOK3S_INTERRUPT_TRACE 0xd00 diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 3d31f2c59e43..91c9f937edcd 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -406,6 +406,12 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) return vcpu->arch.fault_dar; } +/* Expiry time of vcpu DEC relative to host TB */ +static inline u64 kvmppc_dec_expires_host_tb(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.dec_expires - vcpu->arch.vcore->tb_offset; +} + static inline bool is_kvmppc_resume_guest(int r) { return (r == RESUME_GUEST || r == RESUME_GUEST_NV); diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index fff391b9b97b..fe07558173ef 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -44,7 +44,6 @@ struct kvm_nested_guest { struct mutex tlb_lock; /* serialize page faults and tlbies */ struct kvm_nested_guest *next; cpumask_t need_tlb_flush; - cpumask_t cpu_in_guest; short prev_cpu[NR_CPUS]; u8 radix; /* is this nested guest radix */ }; @@ -154,7 +153,9 @@ static inline bool kvmhv_vcpu_is_radix(struct kvm_vcpu *vcpu) return radix; } -int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr); +unsigned long kvmppc_msr_hard_disable_set_facilities(struct kvm_vcpu *vcpu, unsigned long msr); + +int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb); #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ #endif diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e4d23193eba7..a770443cd6e0 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -287,7 +287,6 @@ struct kvm_arch { u32 online_vcores; atomic_t hpte_mod_interest; cpumask_t need_tlb_flush; - cpumask_t cpu_in_guest; u8 radix; u8 fwnmi_enabled; u8 secure_guest; @@ -579,6 +578,10 @@ struct kvm_vcpu_arch { ulong cfar; ulong ppr; u32 pspb; + u8 load_ebb; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + u8 load_tm; +#endif ulong fscr; ulong shadow_fscr; ulong ebbhr; @@ -741,7 +744,7 @@ struct kvm_vcpu_arch { struct hrtimer dec_timer; u64 dec_jiffies; - u64 dec_expires; + u64 dec_expires; /* Relative to guest timebase. */ unsigned long pending_exceptions; u8 ceded; u8 prodded; @@ -749,6 +752,7 @@ struct kvm_vcpu_arch { u8 irq_pending; /* Used by XIVE to signal pending guest irqs */ u32 last_inst; + struct rcuwait wait; struct rcuwait *waitp; struct kvmppc_vcore *vcore; int ret; @@ -864,6 +868,5 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_exit(void) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} #endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 671fbd1a765e..a14dbcd1b8ce 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -200,12 +200,11 @@ extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); extern void kvmppc_core_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, @@ -274,12 +273,11 @@ struct kvmppc_ops { int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log); void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot); int (*prepare_memory_region)(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); void (*commit_memory_region)(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range); @@ -552,8 +550,7 @@ extern void kvm_hv_vm_activated(void); extern void kvm_hv_vm_deactivated(void); extern bool kvm_hv_mode_active(void); -extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu, - struct kvm_nested_guest *nested); +extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu); #else static inline void __init kvm_cma_reserve(void) @@ -760,6 +757,7 @@ void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu); void kvmppc_subcore_enter_guest(void); void kvmppc_subcore_exit_guest(void); long kvmppc_realmode_hmi_handler(void); +long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu); long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel); long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags, diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 9d1fbd8be1c7..1f43ef696033 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -112,6 +112,9 @@ static inline void clear_task_ebb(struct task_struct *t) #endif } +void kvmppc_save_user_regs(void); +void kvmppc_save_current_sprs(void); + extern int set_thread_tidr(struct task_struct *t); #endif /* _ASM_POWERPC_SWITCH_TO_H */ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 8c2c3dd4ddba..924b2157882f 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -18,6 +18,8 @@ #include <asm/vdso/timebase.h> /* time.c */ +extern u64 decrementer_max; + extern unsigned long tb_ticks_per_jiffy; extern unsigned long tb_ticks_per_usec; extern unsigned long tb_ticks_per_sec; @@ -97,19 +99,16 @@ extern void div128_by_32(u64 dividend_high, u64 dividend_low, extern void secondary_cpu_time_init(void); extern void __init time_init(void); -#ifdef CONFIG_PPC64 -static inline unsigned long test_irq_work_pending(void) -{ - unsigned long x; +DECLARE_PER_CPU(u64, decrementers_next_tb); - asm volatile("lbz %0,%1(13)" - : "=r" (x) - : "i" (offsetof(struct paca_struct, irq_work_pending))); - return x; +static inline u64 timer_get_next_tb(void) +{ + return __this_cpu_read(decrementers_next_tb); } -#endif -DECLARE_PER_CPU(u64, decrementers_next_tb); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void timer_rearm_host_dec(u64 now); +#endif /* Convert timebase ticks to nanoseconds */ unsigned long long tb_to_ns(unsigned long long tb_ticks); diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c index 3cca88ee96d7..3dc61e203f37 100644 --- a/arch/powerpc/kernel/cpu_setup_power.c +++ b/arch/powerpc/kernel/cpu_setup_power.c @@ -109,7 +109,7 @@ static void init_PMU_HV_ISA207(void) static void init_PMU(void) { mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); } @@ -123,7 +123,7 @@ static void init_PMU_ISA31(void) { mtspr(SPRN_MMCR3, 0); mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE); - mtspr(SPRN_MMCR0, MMCR0_PMCCEXT); + mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT); } /* @@ -137,6 +137,7 @@ void __setup_cpu_power7(unsigned long offset, struct cpu_spec *t) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH); } @@ -150,6 +151,7 @@ void __restore_cpu_power7(void) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH); } @@ -164,6 +166,7 @@ void __setup_cpu_power8(unsigned long offset, struct cpu_spec *t) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */ init_HFSCR(); @@ -184,6 +187,7 @@ void __restore_cpu_power8(void) return; mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */ init_HFSCR(); @@ -202,6 +206,7 @@ void __setup_cpu_power9(unsigned long offset, struct cpu_spec *t) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -223,6 +228,7 @@ void __restore_cpu_power9(void) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -242,6 +248,7 @@ void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); @@ -264,6 +271,7 @@ void __restore_cpu_power10(void) mtspr(SPRN_PSSCR, 0); mtspr(SPRN_LPID, 0); mtspr(SPRN_PID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_PCR, PCR_MASK); init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index ba527fb52993..d2b35fb9181d 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -80,6 +80,7 @@ static void __restore_cpu_cpufeatures(void) mtspr(SPRN_LPCR, system_registers.lpcr); if (hv_mode) { mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_HFSCR, system_registers.hfscr); mtspr(SPRN_PCR, system_registers.pcr); } @@ -216,6 +217,7 @@ static int __init feat_enable_hv(struct dt_cpu_feature *f) } mtspr(SPRN_LPID, 0); + mtspr(SPRN_AMOR, ~0); lpcr = mfspr(SPRN_LPCR); lpcr &= ~LPCR_LPES0; /* HV external interrupts */ @@ -351,7 +353,7 @@ static void init_pmu_power8(void) } mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); mtspr(SPRN_MMCRS, 0); @@ -390,7 +392,7 @@ static void init_pmu_power9(void) mtspr(SPRN_MMCRC, 0); mtspr(SPRN_MMCRA, 0); - mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR0, MMCR0_FC); mtspr(SPRN_MMCR1, 0); mtspr(SPRN_MMCR2, 0); } @@ -426,7 +428,7 @@ static void init_pmu_power10(void) mtspr(SPRN_MMCR3, 0); mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE); - mtspr(SPRN_MMCR0, MMCR0_PMCCEXT); + mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT); } static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 406d7ee9e322..5d2333d2a283 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1156,6 +1156,40 @@ static inline void save_sprs(struct thread_struct *t) #endif } +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void kvmppc_save_user_regs(void) +{ + unsigned long usermsr; + + if (!current->thread.regs) + return; + + usermsr = current->thread.regs->msr; + + if (usermsr & MSR_FP) + save_fpu(current); + + if (usermsr & MSR_VEC) + save_altivec(current); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (usermsr & MSR_TM) { + current->thread.tm_tfhar = mfspr(SPRN_TFHAR); + current->thread.tm_tfiar = mfspr(SPRN_TFIAR); + current->thread.tm_texasr = mfspr(SPRN_TEXASR); + current->thread.regs->msr &= ~MSR_TM; + } +#endif +} +EXPORT_SYMBOL_GPL(kvmppc_save_user_regs); + +void kvmppc_save_current_sprs(void) +{ + save_sprs(¤t->thread); +} +EXPORT_SYMBOL_GPL(kvmppc_save_current_sprs); +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ + static inline void restore_sprs(struct thread_struct *old_thread, struct thread_struct *new_thread) { diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index cae8f03a44fe..f7cddb82938f 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -88,6 +88,7 @@ static struct clocksource clocksource_timebase = { #define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF u64 decrementer_max = DECREMENTER_DEFAULT_MAX; +EXPORT_SYMBOL_GPL(decrementer_max); /* for KVM HDEC */ static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev); @@ -107,6 +108,7 @@ struct clock_event_device decrementer_clockevent = { EXPORT_SYMBOL(decrementer_clockevent); DEFINE_PER_CPU(u64, decrementers_next_tb); +EXPORT_SYMBOL_GPL(decrementers_next_tb); static DEFINE_PER_CPU(struct clock_event_device, decrementers); #define XSEC_PER_SEC (1024*1024) @@ -496,6 +498,16 @@ EXPORT_SYMBOL(profile_pc); * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable... */ #ifdef CONFIG_PPC64 +static inline unsigned long test_irq_work_pending(void) +{ + unsigned long x; + + asm volatile("lbz %0,%1(13)" + : "=r" (x) + : "i" (offsetof(struct paca_struct, irq_work_pending))); + return x; +} + static inline void set_irq_work_pending_flag(void) { asm volatile("stb %0,%1(13)" : : @@ -539,13 +551,44 @@ void arch_irq_work_raise(void) preempt_enable(); } +static void set_dec_or_work(u64 val) +{ + set_dec(val); + /* We may have raced with new irq work */ + if (unlikely(test_irq_work_pending())) + set_dec(1); +} + #else /* CONFIG_IRQ_WORK */ #define test_irq_work_pending() 0 #define clear_irq_work_pending() +static void set_dec_or_work(u64 val) +{ + set_dec(val); +} #endif /* CONFIG_IRQ_WORK */ +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void timer_rearm_host_dec(u64 now) +{ + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); + + WARN_ON_ONCE(!arch_irqs_disabled()); + WARN_ON_ONCE(mfmsr() & MSR_EE); + + if (now >= *next_tb) { + local_paca->irq_happened |= PACA_IRQ_DEC; + } else { + now = *next_tb - now; + if (now <= decrementer_max) + set_dec_or_work(now); + } +} +EXPORT_SYMBOL_GPL(timer_rearm_host_dec); +#endif + /* * timer_interrupt - gets called when the decrementer overflows, * with interrupts disabled. @@ -606,10 +649,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) } else { now = *next_tb - now; if (now <= decrementer_max) - set_dec(now); - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); + set_dec_or_work(now); __this_cpu_inc(irq_stat.timer_irqs_others); } @@ -843,11 +883,7 @@ static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { __this_cpu_write(decrementers_next_tb, get_tb() + evt); - set_dec(evt); - - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); + set_dec_or_work(evt); return 0; } diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index ff581d70f20c..c8e156011db9 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -26,6 +26,7 @@ config KVM select KVM_VFIO select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS + select INTERVAL_TREE config KVM_BOOK3S_HANDLER bool @@ -130,6 +131,21 @@ config KVM_BOOK3S_HV_EXIT_TIMING If unsure, say N. +config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND + bool "Nested L0 host workaround for L1 KVM host PMU handling bug" if EXPERT + depends on KVM_BOOK3S_HV_POSSIBLE + default !EXPERT + help + Old nested HV capable Linux guests have a bug where they don't + reflect the PMU in-use status of their L2 guest to the L0 host + while the L2 PMU registers are live. This can result in loss + of L2 PMU register state, causing perf to not work correctly in + L2 guests. + + Selecting this option for the L0 host implements a workaround for + those buggy L1s which saves the L2 state, at the cost of performance + in all nested-capable guest entry/exit. + config KVM_BOOKE_HV bool diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 583c14ef596e..9bdfc8b50899 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -4,11 +4,8 @@ # ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm -KVM := ../../../virt/kvm -common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/binary_stats.o -common-objs-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o -common-objs-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o +include $(srctree)/virt/kvm/Makefile.kvm common-objs-y += powerpc.o emulate_loadstore.o obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o @@ -125,9 +122,8 @@ kvm-book3s_32-objs := \ kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs) kvm-objs-$(CONFIG_KVM_MPIC) += mpic.o -kvm-objs-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o -kvm-objs := $(kvm-objs-m) $(kvm-objs-y) +kvm-y += $(kvm-objs-m) $(kvm-objs-y) obj-$(CONFIG_KVM_E500V2) += kvm.o obj-$(CONFIG_KVM_E500MC) += kvm.o diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index b785f6772391..6d525285dbe8 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -847,21 +847,19 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) } int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { - return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem, - change); + return kvm->arch.kvm_ops->prepare_memory_region(kvm, old, new, change); } void kvmppc_core_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change); + kvm->arch.kvm_ops->commit_memory_region(kvm, old, new, change); } bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 3fbd570f9c1e..0215f32932a9 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -337,7 +337,7 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum, static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large) { - int i; + unsigned long i; struct kvm_vcpu *v; /* flush this VA on all cpus */ diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 983b8c18bc31..05e003eb5d90 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -374,11 +374,16 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) BEGIN_FTR_SECTION mtspr SPRN_DAWRX1,r10 END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) - mtspr SPRN_PID,r10 /* - * Switch to host MMU mode + * Switch to host MMU mode (don't have the real host PID but we aren't + * going back to userspace). */ + hwsync + isync + + mtspr SPRN_PID,r10 + ld r10, HSTATE_KVM_VCPU(r13) ld r10, VCPU_KVM(r10) lwz r10, KVM_HOST_LPID(r10) @@ -389,6 +394,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) ld r10, KVM_HOST_LPCR(r10) mtspr SPRN_LPCR,r10 + isync + /* * Set GUEST_MODE_NONE so the handler won't branch to KVM, and clear * MSR_RI in r12 ([H]SRR1) so the handler won't try to return. diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index feee40cb2ba1..61290282fd9e 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -530,7 +530,7 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va, bool large) { u64 mask = 0xFFFFFFFFFULL; - long i; + unsigned long i; struct kvm_vcpu *v; dprintk("KVM MMU: tlbie(0x%lx)\n", va); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index c63e263312a4..213232914367 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -734,11 +734,11 @@ void kvmppc_rmap_reset(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { /* Mutual exclusion with kvm_unmap_hva_range etc. */ spin_lock(&kvm->mmu_lock); /* diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 16359525a40f..8cebe5542256 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -57,6 +57,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, preempt_disable(); + asm volatile("hwsync" ::: "memory"); + isync(); /* switch the lpid first to avoid running host with unallocated pid */ old_lpid = mfspr(SPRN_LPID); if (old_lpid != lpid) @@ -75,6 +77,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, ret = __copy_to_user_inatomic((void __user *)to, from, n); pagefault_enable(); + asm volatile("hwsync" ::: "memory"); + isync(); /* switch the pid first to avoid running host with unallocated pid */ if (quadrant == 1 && pid != old_pid) mtspr(SPRN_PID, old_pid); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 7b74fc0a986b..d1817cd9a691 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -80,6 +80,7 @@ #include <asm/plpar_wrappers.h> #include "book3s.h" +#include "book3s_hv.h" #define CREATE_TRACE_POINTS #include "trace_hv.h" @@ -127,11 +128,6 @@ static bool nested = true; module_param(nested, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(nested, "Enable nested virtualization (only on POWER9)"); -static inline bool nesting_enabled(struct kvm *kvm) -{ - return kvm->arch.nested_enable && kvm_is_radix(kvm); -} - static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); /* @@ -276,22 +272,26 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) * they should never fail.) */ -static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc) +static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc, u64 tb) { unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); - vc->preempt_tb = mftb(); + vc->preempt_tb = tb; spin_unlock_irqrestore(&vc->stoltb_lock, flags); } -static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc) +static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc, u64 tb) { unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); if (vc->preempt_tb != TB_NIL) { - vc->stolen_tb += mftb() - vc->preempt_tb; + vc->stolen_tb += tb - vc->preempt_tb; vc->preempt_tb = TB_NIL; } spin_unlock_irqrestore(&vc->stoltb_lock, flags); @@ -301,6 +301,12 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long flags; + u64 now; + + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return; + + now = mftb(); /* * We can test vc->runner without taking the vcore lock, @@ -309,12 +315,12 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) * ever sets it to NULL. */ if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING) - kvmppc_core_end_stolen(vc); + kvmppc_core_end_stolen(vc, now); spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST && vcpu->arch.busy_preempt != TB_NIL) { - vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt; + vcpu->arch.busy_stolen += now - vcpu->arch.busy_preempt; vcpu->arch.busy_preempt = TB_NIL; } spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); @@ -324,13 +330,19 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long flags; + u64 now; + + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return; + + now = mftb(); if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING) - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, now); spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST) - vcpu->arch.busy_preempt = mftb(); + vcpu->arch.busy_preempt = now; spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); } @@ -675,6 +687,8 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) u64 p; unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); p = vc->stolen_tb; if (vc->vcore_state != VCORE_INACTIVE && @@ -684,35 +698,30 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) return p; } -static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, - struct kvmppc_vcore *vc) +static void __kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, + unsigned int pcpu, u64 now, + unsigned long stolen) { struct dtl_entry *dt; struct lppaca *vpa; - unsigned long stolen; - unsigned long core_stolen; - u64 now; - unsigned long flags; dt = vcpu->arch.dtl_ptr; vpa = vcpu->arch.vpa.pinned_addr; - now = mftb(); - core_stolen = vcore_stolen_time(vc, now); - stolen = core_stolen - vcpu->arch.stolen_logged; - vcpu->arch.stolen_logged = core_stolen; - spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); - stolen += vcpu->arch.busy_stolen; - vcpu->arch.busy_stolen = 0; - spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); + if (!dt || !vpa) return; - memset(dt, 0, sizeof(struct dtl_entry)); + dt->dispatch_reason = 7; - dt->processor_id = cpu_to_be16(vc->pcpu + vcpu->arch.ptid); - dt->timebase = cpu_to_be64(now + vc->tb_offset); + dt->preempt_reason = 0; + dt->processor_id = cpu_to_be16(pcpu + vcpu->arch.ptid); dt->enqueue_to_dispatch_time = cpu_to_be32(stolen); + dt->ready_to_enqueue_time = 0; + dt->waiting_to_ready_time = 0; + dt->timebase = cpu_to_be64(now); + dt->fault_addr = 0; dt->srr0 = cpu_to_be64(kvmppc_get_pc(vcpu)); dt->srr1 = cpu_to_be64(vcpu->arch.shregs.msr); + ++dt; if (dt == vcpu->arch.dtl.pinned_end) dt = vcpu->arch.dtl.pinned_addr; @@ -723,6 +732,27 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, vcpu->arch.dtl.dirty = true; } +static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, + struct kvmppc_vcore *vc) +{ + unsigned long stolen; + unsigned long core_stolen; + u64 now; + unsigned long flags; + + now = mftb(); + + core_stolen = vcore_stolen_time(vc, now); + stolen = core_stolen - vcpu->arch.stolen_logged; + vcpu->arch.stolen_logged = core_stolen; + spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); + stolen += vcpu->arch.busy_stolen; + vcpu->arch.busy_stolen = 0; + spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); + + __kvmppc_create_dtl_entry(vcpu, vc->pcpu, now + vc->tb_offset, stolen); +} + /* See if there is a doorbell interrupt pending for a vcpu */ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu) { @@ -731,6 +761,8 @@ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu) if (vcpu->arch.doorbell_request) return true; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return false; /* * Ensure that the read of vcore->dpdes comes after the read * of vcpu->doorbell_request. This barrier matches the @@ -900,13 +932,14 @@ static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target) * mode handler is not called but no other threads are in the * source vcore. */ - - spin_lock(&vcore->lock); - if (target->arch.state == KVMPPC_VCPU_RUNNABLE && - vcore->vcore_state != VCORE_INACTIVE && - vcore->runner) - target = vcore->runner; - spin_unlock(&vcore->lock); + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + spin_lock(&vcore->lock); + if (target->arch.state == KVMPPC_VCPU_RUNNABLE && + vcore->vcore_state != VCORE_INACTIVE && + vcore->runner) + target = vcore->runner; + spin_unlock(&vcore->lock); + } return kvm_vcpu_yield_to(target); } @@ -1421,6 +1454,43 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) return RESUME_GUEST; } +/* + * If the lppaca had pmcregs_in_use clear when we exited the guest, then + * HFSCR_PM is cleared for next entry. If the guest then tries to access + * the PMU SPRs, we get this facility unavailable interrupt. Putting HFSCR_PM + * back in the guest HFSCR will cause the next entry to load the PMU SPRs and + * allow the guest access to continue. + */ +static int kvmppc_pmu_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_PM)) + return EMULATE_FAIL; + + vcpu->arch.hfscr |= HFSCR_PM; + + return RESUME_GUEST; +} + +static int kvmppc_ebb_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_EBB)) + return EMULATE_FAIL; + + vcpu->arch.hfscr |= HFSCR_EBB; + + return RESUME_GUEST; +} + +static int kvmppc_tm_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_TM)) + return EMULATE_FAIL; + + vcpu->arch.hfscr |= HFSCR_TM; + + return RESUME_GUEST; +} + static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, struct task_struct *tsk) { @@ -1451,6 +1521,10 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, run->ready_for_interrupt_injection = 1; switch (vcpu->arch.trap) { /* We're good on these - the host merely wanted to get our attention */ + case BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER: + WARN_ON_ONCE(1); /* Should never happen */ + vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; + fallthrough; case BOOK3S_INTERRUPT_HV_DECREMENTER: vcpu->stat.dec_exits++; r = RESUME_GUEST; @@ -1575,7 +1649,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, unsigned long vsid; long err; - if (vcpu->arch.fault_dsisr == HDSISR_CANARY) { + if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG) && + unlikely(vcpu->arch.fault_dsisr == HDSISR_CANARY)) { r = RESUME_GUEST; /* Just retry if it's the canary */ break; } @@ -1702,16 +1777,26 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * to emulate. * Otherwise, we just generate a program interrupt to the guest. */ - case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: + case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: { + u64 cause = vcpu->arch.hfscr >> 56; + r = EMULATE_FAIL; - if (((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) && - cpu_has_feature(CPU_FTR_ARCH_300)) - r = kvmppc_emulate_doorbell_instr(vcpu); + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (cause == FSCR_MSGP_LG) + r = kvmppc_emulate_doorbell_instr(vcpu); + if (cause == FSCR_PM_LG) + r = kvmppc_pmu_unavailable(vcpu); + if (cause == FSCR_EBB_LG) + r = kvmppc_ebb_unavailable(vcpu); + if (cause == FSCR_TM_LG) + r = kvmppc_tm_unavailable(vcpu); + } if (r == EMULATE_FAIL) { kvmppc_core_queue_program(vcpu, SRR1_PROGILL); r = RESUME_GUEST; } break; + } case BOOK3S_INTERRUPT_HV_RM_HARD: r = RESUME_PASSTHROUGH; @@ -1768,6 +1853,12 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) vcpu->stat.ext_intr_exits++; r = RESUME_GUEST; break; + /* These need to go to the nested HV */ + case BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER: + vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; + vcpu->stat.dec_exits++; + r = RESUME_HOST; + break; /* SR/HMI/PMI are HV interrupts that host has handled. Resume guest.*/ case BOOK3S_INTERRUPT_HMI: case BOOK3S_INTERRUPT_PERFMON: @@ -1993,7 +2084,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, */ if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.vcore != vc) @@ -2096,8 +2187,10 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, * either vcore->dpdes or doorbell_request. * On POWER8, doorbell_request is 0. */ - *val = get_reg_val(id, vcpu->arch.vcore->dpdes | - vcpu->arch.doorbell_request); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + *val = get_reg_val(id, vcpu->arch.doorbell_request); + else + *val = get_reg_val(id, vcpu->arch.vcore->dpdes); break; case KVM_REG_PPC_VTB: *val = get_reg_val(id, vcpu->arch.vcore->vtb); @@ -2238,8 +2331,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.vcore->arch_compat); break; case KVM_REG_PPC_DEC_EXPIRY: - *val = get_reg_val(id, vcpu->arch.dec_expires + - vcpu->arch.vcore->tb_offset); + *val = get_reg_val(id, vcpu->arch.dec_expires); break; case KVM_REG_PPC_ONLINE: *val = get_reg_val(id, vcpu->arch.online); @@ -2335,7 +2427,10 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.pspb = set_reg_val(id, *val); break; case KVM_REG_PPC_DPDES: - vcpu->arch.vcore->dpdes = set_reg_val(id, *val); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + vcpu->arch.doorbell_request = set_reg_val(id, *val) & 1; + else + vcpu->arch.vcore->dpdes = set_reg_val(id, *val); break; case KVM_REG_PPC_VTB: vcpu->arch.vcore->vtb = set_reg_val(id, *val); @@ -2491,8 +2586,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DEC_EXPIRY: - vcpu->arch.dec_expires = set_reg_val(id, *val) - - vcpu->arch.vcore->tb_offset; + vcpu->arch.dec_expires = set_reg_val(id, *val); break; case KVM_REG_PPC_ONLINE: i = set_reg_val(id, *val); @@ -2715,6 +2809,11 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) #endif #endif vcpu->arch.mmcr[0] = MMCR0_FC; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + vcpu->arch.mmcr[0] |= MMCR0_PMCCEXT; + vcpu->arch.mmcra = MMCRA_BHRB_DISABLE; + } + vcpu->arch.ctrl = CTRL_RUNLATCH; /* default to host PVR, since we can't spoof it */ kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR)); @@ -2745,6 +2844,11 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) vcpu->arch.hfscr_permitted = vcpu->arch.hfscr; + /* + * PM, EBB, TM are demand-faulted so start with it clear. + */ + vcpu->arch.hfscr &= ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM); + kvmppc_mmu_book3s_hv_init(vcpu); vcpu->arch.state = KVMPPC_VCPU_NOTREADY; @@ -2869,13 +2973,13 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) unsigned long dec_nsec, now; now = get_tb(); - if (now > vcpu->arch.dec_expires) { + if (now > kvmppc_dec_expires_host_tb(vcpu)) { /* decrementer has already gone negative */ kvmppc_core_queue_dec(vcpu); kvmppc_core_prepare_to_enter(vcpu); return; } - dec_nsec = tb_to_ns(vcpu->arch.dec_expires - now); + dec_nsec = tb_to_ns(kvmppc_dec_expires_host_tb(vcpu) - now); hrtimer_start(&vcpu->arch.dec_timer, dec_nsec, HRTIMER_MODE_REL); vcpu->arch.timer_running = 1; } @@ -2883,14 +2987,14 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) extern int __kvmppc_vcore_entry(void); static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, - struct kvm_vcpu *vcpu) + struct kvm_vcpu *vcpu, u64 tb) { u64 now; if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE) return; spin_lock_irq(&vcpu->arch.tbacct_lock); - now = mftb(); + now = tb; vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) - vcpu->arch.stolen_logged; vcpu->arch.busy_preempt = now; @@ -2945,30 +3049,59 @@ static void kvmppc_release_hwthread(int cpu) tpaca->kvm_hstate.kvm_split_mode = NULL; } +static DEFINE_PER_CPU(struct kvm *, cpu_in_guest); + static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) { struct kvm_nested_guest *nested = vcpu->arch.nested; - cpumask_t *cpu_in_guest; + cpumask_t *need_tlb_flush; int i; + if (nested) + need_tlb_flush = &nested->need_tlb_flush; + else + need_tlb_flush = &kvm->arch.need_tlb_flush; + cpu = cpu_first_tlb_thread_sibling(cpu); - if (nested) { - cpumask_set_cpu(cpu, &nested->need_tlb_flush); - cpu_in_guest = &nested->cpu_in_guest; - } else { - cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush); - cpu_in_guest = &kvm->arch.cpu_in_guest; - } + for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu); + i += cpu_tlb_thread_sibling_step()) + cpumask_set_cpu(i, need_tlb_flush); + /* - * Make sure setting of bit in need_tlb_flush precedes - * testing of cpu_in_guest bits. The matching barrier on - * the other side is the first smp_mb() in kvmppc_run_core(). + * Make sure setting of bit in need_tlb_flush precedes testing of + * cpu_in_guest. The matching barrier on the other side is hwsync + * when switching to guest MMU mode, which happens between + * cpu_in_guest being set to the guest kvm, and need_tlb_flush bit + * being tested. */ smp_mb(); + for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu); - i += cpu_tlb_thread_sibling_step()) - if (cpumask_test_cpu(i, cpu_in_guest)) + i += cpu_tlb_thread_sibling_step()) { + struct kvm *running = *per_cpu_ptr(&cpu_in_guest, i); + + if (running == kvm) smp_call_function_single(i, do_nothing, NULL, 1); + } +} + +static void do_migrate_away_vcpu(void *arg) +{ + struct kvm_vcpu *vcpu = arg; + struct kvm *kvm = vcpu->kvm; + + /* + * If the guest has GTSE, it may execute tlbie, so do a eieio; tlbsync; + * ptesync sequence on the old CPU before migrating to a new one, in + * case we interrupted the guest between a tlbie ; eieio ; + * tlbsync; ptesync sequence. + * + * Otherwise, ptesync is sufficient for ordering tlbiel sequences. + */ + if (kvm->arch.lpcr & LPCR_GTSE) + asm volatile("eieio; tlbsync; ptesync"); + else + asm volatile("ptesync"); } static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) @@ -2994,14 +3127,17 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) * can move around between pcpus. To cope with this, when * a vcpu moves from one pcpu to another, we need to tell * any vcpus running on the same core as this vcpu previously - * ran to flush the TLB. The TLB is shared between threads, - * so we use a single bit in .need_tlb_flush for all 4 threads. + * ran to flush the TLB. */ if (prev_cpu != pcpu) { - if (prev_cpu >= 0 && - cpu_first_tlb_thread_sibling(prev_cpu) != - cpu_first_tlb_thread_sibling(pcpu)) - radix_flush_cpu(kvm, prev_cpu, vcpu); + if (prev_cpu >= 0) { + if (cpu_first_tlb_thread_sibling(prev_cpu) != + cpu_first_tlb_thread_sibling(pcpu)) + radix_flush_cpu(kvm, prev_cpu, vcpu); + + smp_call_function_single(prev_cpu, + do_migrate_away_vcpu, vcpu, 1); + } if (nested) nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu; else @@ -3013,7 +3149,6 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) { int cpu; struct paca_struct *tpaca; - struct kvm *kvm = vc->kvm; cpu = vc->pcpu; if (vcpu) { @@ -3024,7 +3159,6 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) cpu += vcpu->arch.ptid; vcpu->cpu = vc->pcpu; vcpu->arch.thread_cpu = cpu; - cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest); } tpaca = paca_ptrs[cpu]; tpaca->kvm_hstate.kvm_vcpu = vcpu; @@ -3125,6 +3259,8 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc) { struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores); + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + vc->vcore_state = VCORE_PREEMPT; vc->pcpu = smp_processor_id(); if (vc->num_threads < threads_per_vcore(vc->kvm)) { @@ -3134,14 +3270,16 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc) } /* Start accumulating stolen time */ - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, mftb()); } static void kvmppc_vcore_end_preempt(struct kvmppc_vcore *vc) { struct preempted_vcore_list *lp; - kvmppc_core_end_stolen(vc); + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + + kvmppc_core_end_stolen(vc, mftb()); if (!list_empty(&vc->preempt_list)) { lp = &per_cpu(preempted_vcores, vc->pcpu); spin_lock(&lp->lock); @@ -3268,7 +3406,7 @@ static void prepare_threads(struct kvmppc_vcore *vc) vcpu->arch.ret = RESUME_GUEST; else continue; - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } } @@ -3287,7 +3425,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) list_del_init(&pvc->preempt_list); if (pvc->runner == NULL) { pvc->vcore_state = VCORE_INACTIVE; - kvmppc_core_end_stolen(pvc); + kvmppc_core_end_stolen(pvc, mftb()); } spin_unlock(&pvc->lock); continue; @@ -3296,7 +3434,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) spin_unlock(&pvc->lock); continue; } - kvmppc_core_end_stolen(pvc); + kvmppc_core_end_stolen(pvc, mftb()); pvc->vcore_state = VCORE_PIGGYBACK; if (cip->total_threads >= target_threads) break; @@ -3340,7 +3478,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) */ spin_unlock(&vc->lock); /* cancel pending dec exception if dec is positive */ - if (now < vcpu->arch.dec_expires && + if (now < kvmppc_dec_expires_host_tb(vcpu) && kvmppc_core_pending_dec(vcpu)) kvmppc_core_dequeue_dec(vcpu); @@ -3363,7 +3501,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) else ++still_running; } else { - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } } @@ -3372,7 +3510,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) kvmppc_vcore_preempt(vc); } else if (vc->runner) { vc->vcore_state = VCORE_PREEMPT; - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, mftb()); } else { vc->vcore_state = VCORE_INACTIVE; } @@ -3503,7 +3641,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) { for_each_runnable_thread(i, vcpu, vc) { vcpu->arch.ret = -EBUSY; - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } goto out; @@ -3748,7 +3886,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_release_hwthread(pcpu + i); if (sip && sip->napped[i]) kvmppc_ipi_thread(pcpu + i); - cpumask_clear_cpu(pcpu + i, &vc->kvm->arch.cpu_in_guest); } spin_unlock(&vc->lock); @@ -3770,211 +3907,137 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) trace_kvmppc_run_core(vc, 1); } -static void load_spr_state(struct kvm_vcpu *vcpu) -{ - mtspr(SPRN_DSCR, vcpu->arch.dscr); - mtspr(SPRN_IAMR, vcpu->arch.iamr); - mtspr(SPRN_PSPB, vcpu->arch.pspb); - mtspr(SPRN_FSCR, vcpu->arch.fscr); - mtspr(SPRN_TAR, vcpu->arch.tar); - mtspr(SPRN_EBBHR, vcpu->arch.ebbhr); - mtspr(SPRN_EBBRR, vcpu->arch.ebbrr); - mtspr(SPRN_BESCR, vcpu->arch.bescr); - mtspr(SPRN_TIDR, vcpu->arch.tid); - mtspr(SPRN_AMR, vcpu->arch.amr); - mtspr(SPRN_UAMOR, vcpu->arch.uamor); - - /* - * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI] - * clear (or hstate set appropriately to catch those registers - * being clobbered if we take a MCE or SRESET), so those are done - * later. - */ - - if (!(vcpu->arch.ctrl & 1)) - mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1); -} - -static void store_spr_state(struct kvm_vcpu *vcpu) -{ - vcpu->arch.ctrl = mfspr(SPRN_CTRLF); - - vcpu->arch.iamr = mfspr(SPRN_IAMR); - vcpu->arch.pspb = mfspr(SPRN_PSPB); - vcpu->arch.fscr = mfspr(SPRN_FSCR); - vcpu->arch.tar = mfspr(SPRN_TAR); - vcpu->arch.ebbhr = mfspr(SPRN_EBBHR); - vcpu->arch.ebbrr = mfspr(SPRN_EBBRR); - vcpu->arch.bescr = mfspr(SPRN_BESCR); - vcpu->arch.tid = mfspr(SPRN_TIDR); - vcpu->arch.amr = mfspr(SPRN_AMR); - vcpu->arch.uamor = mfspr(SPRN_UAMOR); - vcpu->arch.dscr = mfspr(SPRN_DSCR); -} - -/* - * Privileged (non-hypervisor) host registers to save. - */ -struct p9_host_os_sprs { - unsigned long dscr; - unsigned long tidr; - unsigned long iamr; - unsigned long amr; - unsigned long fscr; -}; - -static void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs) -{ - host_os_sprs->dscr = mfspr(SPRN_DSCR); - host_os_sprs->tidr = mfspr(SPRN_TIDR); - host_os_sprs->iamr = mfspr(SPRN_IAMR); - host_os_sprs->amr = mfspr(SPRN_AMR); - host_os_sprs->fscr = mfspr(SPRN_FSCR); -} - -/* vcpu guest regs must already be saved */ -static void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, - struct p9_host_os_sprs *host_os_sprs) -{ - mtspr(SPRN_PSPB, 0); - mtspr(SPRN_UAMOR, 0); - - mtspr(SPRN_DSCR, host_os_sprs->dscr); - mtspr(SPRN_TIDR, host_os_sprs->tidr); - mtspr(SPRN_IAMR, host_os_sprs->iamr); - - if (host_os_sprs->amr != vcpu->arch.amr) - mtspr(SPRN_AMR, host_os_sprs->amr); - - if (host_os_sprs->fscr != vcpu->arch.fscr) - mtspr(SPRN_FSCR, host_os_sprs->fscr); - - /* Save guest CTRL register, set runlatch to 1 */ - if (!(vcpu->arch.ctrl & 1)) - mtspr(SPRN_CTRLT, 1); -} - static inline bool hcall_is_xics(unsigned long req) { return req == H_EOI || req == H_CPPR || req == H_IPI || req == H_IPOLL || req == H_XIRR || req == H_XIRR_X; } -/* - * Guest entry for POWER9 and later CPUs. - */ -static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, - unsigned long lpcr) +static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu) +{ + struct lppaca *lp = vcpu->arch.vpa.pinned_addr; + if (lp) { + u32 yield_count = be32_to_cpu(lp->yield_count) + 1; + lp->yield_count = cpu_to_be32(yield_count); + vcpu->arch.vpa.dirty = 1; + } +} + +/* call our hypervisor to load up HV regs and go */ +static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) { struct kvmppc_vcore *vc = vcpu->arch.vcore; + unsigned long host_psscr; + unsigned long msr; + struct hv_guest_state hvregs; struct p9_host_os_sprs host_os_sprs; s64 dec; - u64 tb; - int trap, save_pmu; + int trap; - WARN_ON_ONCE(vcpu->arch.ceded); - - dec = mfspr(SPRN_DEC); - tb = mftb(); - if (dec < 0) - return BOOK3S_INTERRUPT_HV_DECREMENTER; - local_paca->kvm_hstate.dec_expires = dec + tb; - if (local_paca->kvm_hstate.dec_expires < time_limit) - time_limit = local_paca->kvm_hstate.dec_expires; + msr = mfmsr(); save_p9_host_os_sprs(&host_os_sprs); - kvmhv_save_host_pmu(); /* saves it to PACA kvm_hstate */ + /* + * We need to save and restore the guest visible part of the + * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor + * doesn't do this for us. Note only required if pseries since + * this is done in kvmhv_vcpu_entry_p9() below otherwise. + */ + host_psscr = mfspr(SPRN_PSSCR_PR); - kvmppc_subcore_enter_guest(); + kvmppc_msr_hard_disable_set_facilities(vcpu, msr); + if (lazy_irq_pending()) + return 0; - vc->entry_exit_map = 1; - vc->in_guest = 1; + if (unlikely(load_vcpu_state(vcpu, &host_os_sprs))) + msr = mfmsr(); /* TM restore can update msr */ - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - u32 yield_count = be32_to_cpu(lp->yield_count) + 1; - lp->yield_count = cpu_to_be32(yield_count); - vcpu->arch.vpa.dirty = 1; - } - - if (cpu_has_feature(CPU_FTR_TM) || - cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - kvmppc_restore_tm_hv(vcpu, vcpu->arch.shregs.msr, true); + if (vcpu->arch.psscr != host_psscr) + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); -#ifdef CONFIG_PPC_PSERIES - if (kvmhv_on_pseries()) { - barrier(); - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - get_lppaca()->pmcregs_in_use = lp->pmcregs_in_use; - } else { - get_lppaca()->pmcregs_in_use = 1; - } - barrier(); + kvmhv_save_hv_regs(vcpu, &hvregs); + hvregs.lpcr = lpcr; + vcpu->arch.regs.msr = vcpu->arch.shregs.msr; + hvregs.version = HV_GUEST_STATE_VERSION; + if (vcpu->arch.nested) { + hvregs.lpid = vcpu->arch.nested->shadow_lpid; + hvregs.vcpu_token = vcpu->arch.nested_vcpu_id; + } else { + hvregs.lpid = vcpu->kvm->arch.lpid; + hvregs.vcpu_token = vcpu->vcpu_id; } -#endif - kvmhv_load_guest_pmu(vcpu); - - msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX); - load_fp_state(&vcpu->arch.fp); -#ifdef CONFIG_ALTIVEC - load_vr_state(&vcpu->arch.vr); -#endif - mtspr(SPRN_VRSAVE, vcpu->arch.vrsave); - - load_spr_state(vcpu); + hvregs.hdec_expiry = time_limit; /* - * When setting DEC, we must always deal with irq_work_raise via NMI vs - * setting DEC. The problem occurs right as we switch into guest mode - * if a NMI hits and sets pending work and sets DEC, then that will - * apply to the guest and not bring us back to the host. + * When setting DEC, we must always deal with irq_work_raise + * via NMI vs setting DEC. The problem occurs right as we + * switch into guest mode if a NMI hits and sets pending work + * and sets DEC, then that will apply to the guest and not + * bring us back to the host. * - * irq_work_raise could check a flag (or possibly LPCR[HDICE] for - * example) and set HDEC to 1? That wouldn't solve the nested hv - * case which needs to abort the hcall or zero the time limit. + * irq_work_raise could check a flag (or possibly LPCR[HDICE] + * for example) and set HDEC to 1? That wouldn't solve the + * nested hv case which needs to abort the hcall or zero the + * time limit. * * XXX: Another day's problem. */ - mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb()); + mtspr(SPRN_DEC, kvmppc_dec_expires_host_tb(vcpu) - *tb); + + mtspr(SPRN_DAR, vcpu->arch.shregs.dar); + mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); + switch_pmu_to_guest(vcpu, &host_os_sprs); + trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), + __pa(&vcpu->arch.regs)); + kvmhv_restore_hv_return_state(vcpu, &hvregs); + switch_pmu_to_host(vcpu, &host_os_sprs); + vcpu->arch.shregs.msr = vcpu->arch.regs.msr; + vcpu->arch.shregs.dar = mfspr(SPRN_DAR); + vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + + store_vcpu_state(vcpu); - if (kvmhv_on_pseries()) { - /* - * We need to save and restore the guest visible part of the - * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor - * doesn't do this for us. Note only required if pseries since - * this is done in kvmhv_vcpu_entry_p9() below otherwise. - */ - unsigned long host_psscr; - /* call our hypervisor to load up HV regs and go */ - struct hv_guest_state hvregs; + dec = mfspr(SPRN_DEC); + if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ + dec = (s32) dec; + *tb = mftb(); + vcpu->arch.dec_expires = dec + (*tb + vc->tb_offset); - host_psscr = mfspr(SPRN_PSSCR_PR); - mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); - kvmhv_save_hv_regs(vcpu, &hvregs); - hvregs.lpcr = lpcr; - vcpu->arch.regs.msr = vcpu->arch.shregs.msr; - hvregs.version = HV_GUEST_STATE_VERSION; - if (vcpu->arch.nested) { - hvregs.lpid = vcpu->arch.nested->shadow_lpid; - hvregs.vcpu_token = vcpu->arch.nested_vcpu_id; - } else { - hvregs.lpid = vcpu->kvm->arch.lpid; - hvregs.vcpu_token = vcpu->vcpu_id; - } - hvregs.hdec_expiry = time_limit; - mtspr(SPRN_DAR, vcpu->arch.shregs.dar); - mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); - trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), - __pa(&vcpu->arch.regs)); - kvmhv_restore_hv_return_state(vcpu, &hvregs); - vcpu->arch.shregs.msr = vcpu->arch.regs.msr; - vcpu->arch.shregs.dar = mfspr(SPRN_DAR); - vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); - vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + timer_rearm_host_dec(*tb); + + restore_p9_host_os_sprs(vcpu, &host_os_sprs); + if (vcpu->arch.psscr != host_psscr) mtspr(SPRN_PSSCR_PR, host_psscr); + return trap; +} + +/* + * Guest entry for POWER9 and later CPUs. + */ +static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, + unsigned long lpcr, u64 *tb) +{ + u64 next_timer; + int trap; + + next_timer = timer_get_next_tb(); + if (*tb >= next_timer) + return BOOK3S_INTERRUPT_HV_DECREMENTER; + if (next_timer < time_limit) + time_limit = next_timer; + else if (*tb >= time_limit) /* nested time limit */ + return BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER; + + vcpu->arch.ceded = 0; + + vcpu_vpa_increment_dispatch(vcpu); + + if (kvmhv_on_pseries()) { + trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb); + /* H_CEDE has to be handled now, not later */ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && kvmppc_get_gpr(vcpu, 3) == H_CEDE) { @@ -3982,9 +4045,16 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, kvmppc_set_gpr(vcpu, 3, 0); trap = 0; } + } else { + struct kvm *kvm = vcpu->kvm; + kvmppc_xive_push_vcpu(vcpu); - trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr); + + __this_cpu_write(cpu_in_guest, kvm); + trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr, tb); + __this_cpu_write(cpu_in_guest, NULL); + if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && !(vcpu->arch.shregs.msr & MSR_PR)) { unsigned long req = kvmppc_get_gpr(vcpu, 3); @@ -4009,65 +4079,11 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, } kvmppc_xive_pull_vcpu(vcpu); - if (kvm_is_radix(vcpu->kvm)) + if (kvm_is_radix(kvm)) vcpu->arch.slb_max = 0; } - dec = mfspr(SPRN_DEC); - if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ - dec = (s32) dec; - tb = mftb(); - vcpu->arch.dec_expires = dec + tb; - vcpu->cpu = -1; - vcpu->arch.thread_cpu = -1; - - store_spr_state(vcpu); - - restore_p9_host_os_sprs(vcpu, &host_os_sprs); - - msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX); - store_fp_state(&vcpu->arch.fp); -#ifdef CONFIG_ALTIVEC - store_vr_state(&vcpu->arch.vr); -#endif - vcpu->arch.vrsave = mfspr(SPRN_VRSAVE); - - if (cpu_has_feature(CPU_FTR_TM) || - cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - kvmppc_save_tm_hv(vcpu, vcpu->arch.shregs.msr, true); - - save_pmu = 1; - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - u32 yield_count = be32_to_cpu(lp->yield_count) + 1; - lp->yield_count = cpu_to_be32(yield_count); - vcpu->arch.vpa.dirty = 1; - save_pmu = lp->pmcregs_in_use; - } - /* Must save pmu if this guest is capable of running nested guests */ - save_pmu |= nesting_enabled(vcpu->kvm); - - kvmhv_save_guest_pmu(vcpu, save_pmu); -#ifdef CONFIG_PPC_PSERIES - if (kvmhv_on_pseries()) { - barrier(); - get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse(); - barrier(); - } -#endif - - vc->entry_exit_map = 0x101; - vc->in_guest = 0; - - mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - mftb()); - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); - mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso); - - kvmhv_load_host_pmu(); - - kvmppc_subcore_exit_guest(); + vcpu_vpa_increment_dispatch(vcpu); return trap; } @@ -4132,6 +4148,13 @@ static bool kvmppc_vcpu_woken(struct kvm_vcpu *vcpu) return false; } +static bool kvmppc_vcpu_check_block(struct kvm_vcpu *vcpu) +{ + if (!vcpu->arch.ceded || kvmppc_vcpu_woken(vcpu)) + return true; + return false; +} + /* * Check to see if any of the runnable vcpus on the vcore have pending * exceptions or are no longer ceded @@ -4142,7 +4165,7 @@ static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc) int i; for_each_runnable_thread(i, vcpu, vc) { - if (!vcpu->arch.ceded || kvmppc_vcpu_woken(vcpu)) + if (kvmppc_vcpu_check_block(vcpu)) return 1; } @@ -4159,6 +4182,8 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) int do_sleep = 1; u64 block_ns; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + /* Poll for pending exceptions and ceded state */ cur = start_poll = ktime_get(); if (vc->halt_poll_ns) { @@ -4355,7 +4380,7 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) for_each_runnable_thread(i, v, vc) { kvmppc_core_prepare_to_enter(v); if (signal_pending(v->arch.run_task)) { - kvmppc_remove_runnable(vc, v); + kvmppc_remove_runnable(vc, v, mftb()); v->stat.signal_exits++; v->run->exit_reason = KVM_EXIT_INTR; v->arch.ret = -EINTR; @@ -4396,7 +4421,7 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) kvmppc_vcore_end_preempt(vc); if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) { - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); vcpu->stat.signal_exits++; run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; @@ -4417,12 +4442,15 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr) { + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); struct kvm_run *run = vcpu->run; int trap, r, pcpu; int srcu_idx; struct kvmppc_vcore *vc; struct kvm *kvm = vcpu->kvm; struct kvm_nested_guest *nested = vcpu->arch.nested; + unsigned long flags; + u64 tb; trace_kvmppc_run_vcpu_enter(vcpu); @@ -4433,16 +4461,11 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, vc = vcpu->arch.vcore; vcpu->arch.ceded = 0; vcpu->arch.run_task = current; - vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb()); vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; - vcpu->arch.busy_preempt = TB_NIL; vcpu->arch.last_inst = KVM_INST_FETCH_FAILED; - vc->runnable_threads[0] = vcpu; - vc->n_runnable = 1; - vc->runner = vcpu; /* See if the MMU is ready to go */ - if (!kvm->arch.mmu_ready) { + if (unlikely(!kvm->arch.mmu_ready)) { r = kvmhv_setup_mmu(vcpu); if (r) { run->exit_reason = KVM_EXIT_FAIL_ENTRY; @@ -4457,29 +4480,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, kvmppc_update_vpas(vcpu); - init_vcore_to_run(vc); - vc->preempt_tb = TB_NIL; - preempt_disable(); pcpu = smp_processor_id(); - vc->pcpu = pcpu; if (kvm_is_radix(kvm)) kvmppc_prepare_radix_vcpu(vcpu, pcpu); - local_irq_disable(); - hard_irq_disable(); + /* flags save not required, but irq_pmu has no disable/enable API */ + powerpc_local_irq_pmu_save(flags); + if (signal_pending(current)) goto sigpend; - if (lazy_irq_pending() || need_resched() || !kvm->arch.mmu_ready) + if (need_resched() || !kvm->arch.mmu_ready) goto out; if (!nested) { kvmppc_core_prepare_to_enter(vcpu); - if (vcpu->arch.doorbell_request) { - vc->dpdes = 1; - smp_wmb(); - vcpu->arch.doorbell_request = 0; - } if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions)) lpcr |= LPCR_MER; @@ -4490,16 +4505,23 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, goto out; } - kvmppc_clear_host_core(pcpu); + if (vcpu->arch.timer_running) { + hrtimer_try_to_cancel(&vcpu->arch.dec_timer); + vcpu->arch.timer_running = 0; + } - local_paca->kvm_hstate.napping = 0; - local_paca->kvm_hstate.kvm_split_mode = NULL; - kvmppc_start_thread(vcpu, vc); - kvmppc_create_dtl_entry(vcpu, vc); - trace_kvm_guest_enter(vcpu); + tb = mftb(); - vc->vcore_state = VCORE_RUNNING; - trace_kvmppc_run_core(vc, 0); + vcpu->cpu = pcpu; + vcpu->arch.thread_cpu = pcpu; + vc->pcpu = pcpu; + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.ptid = 0; + local_paca->kvm_hstate.fake_suspend = 0; + + __kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0); + + trace_kvm_guest_enter(vcpu); guest_enter_irqoff(); @@ -4510,7 +4532,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, /* Tell lockdep that we're about to enable interrupts */ trace_hardirqs_on(); - trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr); + trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr, &tb); vcpu->arch.trap = trap; trace_hardirqs_off(); @@ -4521,8 +4543,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, set_irq_happened(trap); - kvmppc_set_host_core(pcpu); - context_tracking_guest_exit(); if (!vtime_accounting_enabled_this_cpu()) { local_irq_enable(); @@ -4538,9 +4558,10 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, } vtime_account_guest_exit(); - local_irq_enable(); + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; - cpumask_clear_cpu(pcpu, &kvm->arch.cpu_in_guest); + powerpc_local_irq_pmu_restore(flags); preempt_enable(); @@ -4550,7 +4571,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, * by L2 and the L1 decrementer is provided in hdec_expires */ if (kvmppc_core_pending_dec(vcpu) && - ((get_tb() < vcpu->arch.dec_expires) || + ((tb < kvmppc_dec_expires_host_tb(vcpu)) || (trap == BOOK3S_INTERRUPT_SYSCALL && kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED))) kvmppc_core_dequeue_dec(vcpu); @@ -4565,28 +4586,31 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, } vcpu->arch.ret = r; - if (is_kvmppc_resume_guest(r) && vcpu->arch.ceded && - !kvmppc_vcpu_woken(vcpu)) { + if (is_kvmppc_resume_guest(r) && !kvmppc_vcpu_check_block(vcpu)) { kvmppc_set_timer(vcpu); - while (vcpu->arch.ceded && !kvmppc_vcpu_woken(vcpu)) { + + prepare_to_rcuwait(wait); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); if (signal_pending(current)) { vcpu->stat.signal_exits++; run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; break; } - spin_lock(&vc->lock); - kvmppc_vcore_blocked(vc); - spin_unlock(&vc->lock); + + if (kvmppc_vcpu_check_block(vcpu)) + break; + + trace_kvmppc_vcore_blocked(vc, 0); + schedule(); + trace_kvmppc_vcore_blocked(vc, 1); } + finish_rcuwait(wait); } vcpu->arch.ceded = 0; - vc->vcore_state = VCORE_INACTIVE; - trace_kvmppc_run_core(vc, 1); - done: - kvmppc_remove_runnable(vc, vcpu); trace_kvmppc_run_vcpu_exit(vcpu); return vcpu->arch.ret; @@ -4596,7 +4620,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; out: - local_irq_enable(); + powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; } @@ -4606,23 +4630,25 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) struct kvm_run *run = vcpu->run; int r; int srcu_idx; - unsigned long ebb_regs[3] = {}; /* shut up GCC */ - unsigned long user_tar = 0; - unsigned int user_vrsave; struct kvm *kvm; + unsigned long msr; if (!vcpu->arch.sane) { run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; } + /* No need to go into the guest when all we'll do is come back out */ + if (signal_pending(current)) { + run->exit_reason = KVM_EXIT_INTR; + return -EINTR; + } + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM /* * Don't allow entry with a suspended transaction, because * the guest entry/exit code will lose it. - * If the guest has TM enabled, save away their TM-related SPRs - * (they will get restored by the TM unavailable interrupt). */ -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs && (current->thread.regs->msr & MSR_TM)) { if (MSR_TM_ACTIVE(current->thread.regs->msr)) { @@ -4630,12 +4656,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) run->fail_entry.hardware_entry_failure_reason = 0; return -EINVAL; } - /* Enable TM so we can read the TM SPRs */ - mtmsr(mfmsr() | MSR_TM); - current->thread.tm_tfhar = mfspr(SPRN_TFHAR); - current->thread.tm_tfiar = mfspr(SPRN_TFIAR); - current->thread.tm_texasr = mfspr(SPRN_TEXASR); - current->thread.regs->msr &= ~MSR_TM; } #endif @@ -4650,29 +4670,30 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) kvmppc_core_prepare_to_enter(vcpu); - /* No need to go into the guest when all we'll do is come back out */ - if (signal_pending(current)) { - run->exit_reason = KVM_EXIT_INTR; - return -EINTR; - } - kvm = vcpu->kvm; atomic_inc(&kvm->arch.vcpus_running); /* Order vcpus_running vs. mmu_ready, see kvmppc_alloc_reset_hpt */ smp_mb(); - flush_all_to_thread(current); + msr = 0; + if (IS_ENABLED(CONFIG_PPC_FPU)) + msr |= MSR_FP; + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + msr |= MSR_VEC; + if (cpu_has_feature(CPU_FTR_VSX)) + msr |= MSR_VSX; + if ((cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) && + (vcpu->arch.hfscr & HFSCR_TM)) + msr |= MSR_TM; + msr = msr_check_and_set(msr); - /* Save userspace EBB and other register values */ - if (cpu_has_feature(CPU_FTR_ARCH_207S)) { - ebb_regs[0] = mfspr(SPRN_EBBHR); - ebb_regs[1] = mfspr(SPRN_EBBRR); - ebb_regs[2] = mfspr(SPRN_BESCR); - user_tar = mfspr(SPRN_TAR); - } - user_vrsave = mfspr(SPRN_VRSAVE); + kvmppc_save_user_regs(); + + kvmppc_save_current_sprs(); - vcpu->arch.waitp = &vcpu->arch.vcore->wait; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + vcpu->arch.waitp = &vcpu->arch.vcore->wait; vcpu->arch.pgdir = kvm->mm->pgd; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; @@ -4711,15 +4732,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) } } while (is_kvmppc_resume_guest(r)); - /* Restore userspace EBB and other register values */ - if (cpu_has_feature(CPU_FTR_ARCH_207S)) { - mtspr(SPRN_EBBHR, ebb_regs[0]); - mtspr(SPRN_EBBRR, ebb_regs[1]); - mtspr(SPRN_BESCR, ebb_regs[2]); - mtspr(SPRN_TAR, user_tar); - } - mtspr(SPRN_VRSAVE, user_vrsave); - vcpu->arch.state = KVMPPC_VCPU_NOTREADY; atomic_dec(&kvm->arch.vcpus_running); @@ -4786,8 +4798,8 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int i, r; - unsigned long n; + int r; + unsigned long n, i; unsigned long *buf, *p; struct kvm_vcpu *vcpu; @@ -4854,37 +4866,38 @@ static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *slot) } static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, - struct kvm_memory_slot *slot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { - unsigned long npages = mem->memory_size >> PAGE_SHIFT; - if (change == KVM_MR_CREATE) { - slot->arch.rmap = vzalloc(array_size(npages, - sizeof(*slot->arch.rmap))); - if (!slot->arch.rmap) + unsigned long size = array_size(new->npages, sizeof(*new->arch.rmap)); + + if ((size >> PAGE_SHIFT) > totalram_pages()) + return -ENOMEM; + + new->arch.rmap = vzalloc(size); + if (!new->arch.rmap) return -ENOMEM; + } else if (change != KVM_MR_DELETE) { + new->arch.rmap = old->arch.rmap; } return 0; } static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - unsigned long npages = mem->memory_size >> PAGE_SHIFT; - /* - * If we are making a new memslot, it might make + * If we are creating or modifying a memslot, it might make * some address that was previously cached as emulated * MMIO be no longer emulated MMIO, so invalidate * all the caches of emulated MMIO translations. */ - if (npages) + if (change != KVM_MR_DELETE) atomic64_inc(&kvm->arch.mmio_update); /* @@ -5072,6 +5085,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) */ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) { + unsigned long lpcr, lpcr_mask; + if (nesting_enabled(kvm)) kvmhv_release_all_nested(kvm); kvmppc_rmap_reset(kvm); @@ -5081,8 +5096,13 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) kvm->arch.radix = 0; spin_unlock(&kvm->mmu_lock); kvmppc_free_radix(kvm); - kvmppc_update_lpcr(kvm, LPCR_VPM1, - LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR); + + lpcr = LPCR_VPM1; + lpcr_mask = LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_ARCH_31)) + lpcr_mask |= LPCR_HAIL; + kvmppc_update_lpcr(kvm, lpcr, lpcr_mask); + return 0; } @@ -5092,6 +5112,7 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) */ int kvmppc_switch_mmu_to_radix(struct kvm *kvm) { + unsigned long lpcr, lpcr_mask; int err; err = kvmppc_init_vm_radix(kvm); @@ -5103,8 +5124,17 @@ int kvmppc_switch_mmu_to_radix(struct kvm *kvm) kvm->arch.radix = 1; spin_unlock(&kvm->mmu_lock); kvmppc_free_hpt(&kvm->arch.hpt); - kvmppc_update_lpcr(kvm, LPCR_UPRT | LPCR_GTSE | LPCR_HR, - LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR); + + lpcr = LPCR_UPRT | LPCR_GTSE | LPCR_HR; + lpcr_mask = LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + lpcr_mask |= LPCR_HAIL; + if (cpu_has_feature(CPU_FTR_HVMODE) && + (kvm->arch.host_lpcr & LPCR_HAIL)) + lpcr |= LPCR_HAIL; + } + kvmppc_update_lpcr(kvm, lpcr, lpcr_mask); + return 0; } @@ -5126,6 +5156,9 @@ void kvmppc_alloc_host_rm_ops(void) int cpu, core; int size; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return; + /* Not the first time here ? */ if (kvmppc_host_rm_ops_hv != NULL) return; @@ -5268,6 +5301,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) kvm->arch.mmu_ready = 1; lpcr &= ~LPCR_VPM1; lpcr |= LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_HVMODE) && + cpu_has_feature(CPU_FTR_ARCH_31) && + (kvm->arch.host_lpcr & LPCR_HAIL)) + lpcr |= LPCR_HAIL; ret = kvmppc_init_vm_radix(kvm); if (ret) { kvmppc_free_lpid(kvm->arch.lpid); @@ -5861,7 +5898,7 @@ static int kvmhv_svm_off(struct kvm *kvm) int mmu_was_ready; int srcu_idx; int ret = 0; - int i; + unsigned long i; if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) return ret; @@ -5883,11 +5920,12 @@ static int kvmhv_svm_off(struct kvm *kvm) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { struct kvm_memory_slot *memslot; struct kvm_memslots *slots = __kvm_memslots(kvm, i); + int bkt; if (!slots) continue; - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { kvmppc_uvmem_drop_pages(memslot, kvm, true); uv_unregister_mem_slot(kvm->arch.lpid, memslot->id); } @@ -6063,9 +6101,11 @@ static int kvmppc_book3s_init_hv(void) if (r) return r; - r = kvm_init_subcore_bitmap(); - if (r) - return r; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + r = kvm_init_subcore_bitmap(); + if (r) + return r; + } /* * We need a way of accessing the XICS interrupt controller, diff --git a/arch/powerpc/kvm/book3s_hv.h b/arch/powerpc/kvm/book3s_hv.h new file mode 100644 index 000000000000..6b7f07d9026b --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv.h @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Privileged (non-hypervisor) host registers to save. + */ +struct p9_host_os_sprs { + unsigned long iamr; + unsigned long amr; + + unsigned int pmc1; + unsigned int pmc2; + unsigned int pmc3; + unsigned int pmc4; + unsigned int pmc5; + unsigned int pmc6; + unsigned long mmcr0; + unsigned long mmcr1; + unsigned long mmcr2; + unsigned long mmcr3; + unsigned long mmcra; + unsigned long siar; + unsigned long sier1; + unsigned long sier2; + unsigned long sier3; + unsigned long sdar; +}; + +static inline bool nesting_enabled(struct kvm *kvm) +{ + return kvm->arch.nested_enable && kvm_is_radix(kvm); +} + +bool load_vcpu_state(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); +void store_vcpu_state(struct kvm_vcpu *vcpu); +void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs); +void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); +void switch_pmu_to_guest(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); +void switch_pmu_to_host(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 70b7a8f97153..7d6d91338c3f 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -649,6 +649,8 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu) int ext; unsigned long lpcr; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + /* Insert EXTERNAL bit into LPCR at the MER bit position */ ext = (vcpu->arch.pending_exceptions >> BOOK3S_IRQPRIO_EXTERNAL) & 1; lpcr = mfspr(SPRN_LPCR); @@ -682,60 +684,23 @@ static void flush_guest_tlb(struct kvm *kvm) unsigned long rb, set; rb = PPC_BIT(52); /* IS = 2 */ - if (kvm_is_radix(kvm)) { - /* R=1 PRS=1 RIC=2 */ + for (set = 0; set < kvm->arch.tlb_sets; ++set) { + /* R=0 PRS=0 RIC=0 */ asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) - : : "r" (rb), "i" (1), "i" (1), "i" (2), + : : "r" (rb), "i" (0), "i" (0), "i" (0), "r" (0) : "memory"); - for (set = 1; set < kvm->arch.tlb_sets; ++set) { - rb += PPC_BIT(51); /* increment set number */ - /* R=1 PRS=1 RIC=0 */ - asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) - : : "r" (rb), "i" (1), "i" (1), "i" (0), - "r" (0) : "memory"); - } - asm volatile("ptesync": : :"memory"); - // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. - asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); - } else { - for (set = 0; set < kvm->arch.tlb_sets; ++set) { - /* R=0 PRS=0 RIC=0 */ - asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) - : : "r" (rb), "i" (0), "i" (0), "i" (0), - "r" (0) : "memory"); - rb += PPC_BIT(51); /* increment set number */ - } - asm volatile("ptesync": : :"memory"); - // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. - if (cpu_has_feature(CPU_FTR_ARCH_300)) - asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); + rb += PPC_BIT(51); /* increment set number */ } + asm volatile("ptesync": : :"memory"); } -void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu, - struct kvm_nested_guest *nested) +void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu) { - cpumask_t *need_tlb_flush; - - /* - * On POWER9, individual threads can come in here, but the - * TLB is shared between the 4 threads in a core, hence - * invalidating on one thread invalidates for all. - * Thus we make all 4 threads use the same bit. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) - pcpu = cpu_first_tlb_thread_sibling(pcpu); - - if (nested) - need_tlb_flush = &nested->need_tlb_flush; - else - need_tlb_flush = &kvm->arch.need_tlb_flush; - - if (cpumask_test_cpu(pcpu, need_tlb_flush)) { + if (cpumask_test_cpu(pcpu, &kvm->arch.need_tlb_flush)) { flush_guest_tlb(kvm); /* Clear the bit after the TLB flush */ - cpumask_clear_cpu(pcpu, need_tlb_flush); + cpumask_clear_cpu(pcpu, &kvm->arch.need_tlb_flush); } } EXPORT_SYMBOL_GPL(kvmppc_check_need_tlb_flush); diff --git a/arch/powerpc/kvm/book3s_hv_hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c index 9af660476314..1ec50c69678b 100644 --- a/arch/powerpc/kvm/book3s_hv_hmi.c +++ b/arch/powerpc/kvm/book3s_hv_hmi.c @@ -20,10 +20,15 @@ void wait_for_subcore_guest_exit(void) /* * NULL bitmap pointer indicates that KVM module hasn't - * been loaded yet and hence no guests are running. + * been loaded yet and hence no guests are running, or running + * on POWER9 or newer CPU. + * * If no KVM is in use, no need to co-ordinate among threads * as all of them will always be in host and no one is going * to modify TB other than the opal hmi handler. + * + * POWER9 and newer don't need this synchronisation. + * * Hence, just return from here. */ if (!local_paca->sibling_subcore_state) diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 4444f83cb133..59d89e4b154a 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -104,7 +104,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) mtlr r0 blr -_GLOBAL(kvmhv_save_host_pmu) +/* + * void kvmhv_save_host_pmu(void) + */ +kvmhv_save_host_pmu: BEGIN_FTR_SECTION /* Work around P8 PMAE bug */ li r3, -1 @@ -138,14 +141,6 @@ BEGIN_FTR_SECTION std r8, HSTATE_MMCR2(r13) std r9, HSTATE_SIER(r13) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - mfspr r5, SPRN_MMCR3 - mfspr r6, SPRN_SIER2 - mfspr r7, SPRN_SIER3 - std r5, HSTATE_MMCR3(r13) - std r6, HSTATE_SIER2(r13) - std r7, HSTATE_SIER3(r13) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) mfspr r3, SPRN_PMC1 mfspr r5, SPRN_PMC2 mfspr r6, SPRN_PMC3 diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index ed8a2c9f5629..8f8daaeeb3b7 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -358,6 +358,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* convert TB values/offsets to host (L0) values */ hdec_exp = l2_hv.hdec_expiry - vc->tb_offset; vc->tb_offset += l2_hv.tb_offset; + vcpu->arch.dec_expires += l2_hv.tb_offset; /* set L1 state to L2 state */ vcpu->arch.nested = l2; @@ -374,11 +375,6 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) vcpu->arch.ret = RESUME_GUEST; vcpu->arch.trap = 0; do { - if (mftb() >= hdec_exp) { - vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; - r = RESUME_HOST; - break; - } r = kvmhv_run_single_vcpu(vcpu, hdec_exp, lpcr); } while (is_kvmppc_resume_guest(r)); @@ -399,6 +395,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) if (l2_regs.msr & MSR_TS_MASK) vcpu->arch.shregs.msr |= MSR_TS_S; vc->tb_offset = saved_l1_hv.tb_offset; + /* XXX: is this always the same delta as saved_l1_hv.tb_offset? */ + vcpu->arch.dec_expires -= l2_hv.tb_offset; restore_hv_regs(vcpu, &saved_l1_hv); vcpu->arch.purr += delta_purr; vcpu->arch.spurr += delta_spurr; @@ -582,7 +580,7 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) if (eaddr & (0xFFFUL << 52)) return H_PARAMETER; - buf = kzalloc(n, GFP_KERNEL); + buf = kzalloc(n, GFP_KERNEL | __GFP_NOWARN); if (!buf) return H_NO_MEM; @@ -749,7 +747,7 @@ void kvmhv_release_all_nested(struct kvm *kvm) struct kvm_nested_guest *gp; struct kvm_nested_guest *freelist = NULL; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; spin_lock(&kvm->mmu_lock); for (i = 0; i <= kvm->arch.max_nested_lpid; i++) { @@ -770,7 +768,7 @@ void kvmhv_release_all_nested(struct kvm *kvm) } srcu_idx = srcu_read_lock(&kvm->srcu); - kvm_for_each_memslot(memslot, kvm_memslots(kvm)) + kvm_for_each_memslot(memslot, bkt, kvm_memslots(kvm)) kvmhv_free_memslot_nest_rmap(memslot); srcu_read_unlock(&kvm->srcu, srcu_idx); } diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c index 961b3d70483c..a28e5b3daabd 100644 --- a/arch/powerpc/kvm/book3s_hv_p9_entry.c +++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c @@ -4,8 +4,439 @@ #include <asm/asm-prototypes.h> #include <asm/dbell.h> #include <asm/kvm_ppc.h> +#include <asm/pmc.h> #include <asm/ppc-opcode.h> +#include "book3s_hv.h" + +static void freeze_pmu(unsigned long mmcr0, unsigned long mmcra) +{ + if (!(mmcr0 & MMCR0_FC)) + goto do_freeze; + if (mmcra & MMCRA_SAMPLE_ENABLE) + goto do_freeze; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + if (!(mmcr0 & MMCR0_PMCCEXT)) + goto do_freeze; + if (!(mmcra & MMCRA_BHRB_DISABLE)) + goto do_freeze; + } + return; + +do_freeze: + mmcr0 = MMCR0_FC; + mmcra = 0; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mmcr0 |= MMCR0_PMCCEXT; + mmcra = MMCRA_BHRB_DISABLE; + } + + mtspr(SPRN_MMCR0, mmcr0); + mtspr(SPRN_MMCRA, mmcra); + isync(); +} + +void switch_pmu_to_guest(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + struct lppaca *lp; + int load_pmu = 1; + + lp = vcpu->arch.vpa.pinned_addr; + if (lp) + load_pmu = lp->pmcregs_in_use; + + /* Save host */ + if (ppc_get_pmu_inuse()) { + /* + * It might be better to put PMU handling (at least for the + * host) in the perf subsystem because it knows more about what + * is being used. + */ + + /* POWER9, POWER10 do not implement HPMC or SPMC */ + + host_os_sprs->mmcr0 = mfspr(SPRN_MMCR0); + host_os_sprs->mmcra = mfspr(SPRN_MMCRA); + + freeze_pmu(host_os_sprs->mmcr0, host_os_sprs->mmcra); + + host_os_sprs->pmc1 = mfspr(SPRN_PMC1); + host_os_sprs->pmc2 = mfspr(SPRN_PMC2); + host_os_sprs->pmc3 = mfspr(SPRN_PMC3); + host_os_sprs->pmc4 = mfspr(SPRN_PMC4); + host_os_sprs->pmc5 = mfspr(SPRN_PMC5); + host_os_sprs->pmc6 = mfspr(SPRN_PMC6); + host_os_sprs->mmcr1 = mfspr(SPRN_MMCR1); + host_os_sprs->mmcr2 = mfspr(SPRN_MMCR2); + host_os_sprs->sdar = mfspr(SPRN_SDAR); + host_os_sprs->siar = mfspr(SPRN_SIAR); + host_os_sprs->sier1 = mfspr(SPRN_SIER); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + host_os_sprs->mmcr3 = mfspr(SPRN_MMCR3); + host_os_sprs->sier2 = mfspr(SPRN_SIER2); + host_os_sprs->sier3 = mfspr(SPRN_SIER3); + } + } + +#ifdef CONFIG_PPC_PSERIES + /* After saving PMU, before loading guest PMU, flip pmcregs_in_use */ + if (kvmhv_on_pseries()) { + barrier(); + get_lppaca()->pmcregs_in_use = load_pmu; + barrier(); + } +#endif + + /* + * Load guest. If the VPA said the PMCs are not in use but the guest + * tried to access them anyway, HFSCR[PM] will be set by the HFAC + * fault so we can make forward progress. + */ + if (load_pmu || (vcpu->arch.hfscr & HFSCR_PM)) { + mtspr(SPRN_PMC1, vcpu->arch.pmc[0]); + mtspr(SPRN_PMC2, vcpu->arch.pmc[1]); + mtspr(SPRN_PMC3, vcpu->arch.pmc[2]); + mtspr(SPRN_PMC4, vcpu->arch.pmc[3]); + mtspr(SPRN_PMC5, vcpu->arch.pmc[4]); + mtspr(SPRN_PMC6, vcpu->arch.pmc[5]); + mtspr(SPRN_MMCR1, vcpu->arch.mmcr[1]); + mtspr(SPRN_MMCR2, vcpu->arch.mmcr[2]); + mtspr(SPRN_SDAR, vcpu->arch.sdar); + mtspr(SPRN_SIAR, vcpu->arch.siar); + mtspr(SPRN_SIER, vcpu->arch.sier[0]); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_MMCR3, vcpu->arch.mmcr[3]); + mtspr(SPRN_SIER2, vcpu->arch.sier[1]); + mtspr(SPRN_SIER3, vcpu->arch.sier[2]); + } + + /* Set MMCRA then MMCR0 last */ + mtspr(SPRN_MMCRA, vcpu->arch.mmcra); + mtspr(SPRN_MMCR0, vcpu->arch.mmcr[0]); + /* No isync necessary because we're starting counters */ + + if (!vcpu->arch.nested && + (vcpu->arch.hfscr_permitted & HFSCR_PM)) + vcpu->arch.hfscr |= HFSCR_PM; + } +} +EXPORT_SYMBOL_GPL(switch_pmu_to_guest); + +void switch_pmu_to_host(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + struct lppaca *lp; + int save_pmu = 1; + + lp = vcpu->arch.vpa.pinned_addr; + if (lp) + save_pmu = lp->pmcregs_in_use; + if (IS_ENABLED(CONFIG_KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND)) { + /* + * Save pmu if this guest is capable of running nested guests. + * This is option is for old L1s that do not set their + * lppaca->pmcregs_in_use properly when entering their L2. + */ + save_pmu |= nesting_enabled(vcpu->kvm); + } + + if (save_pmu) { + vcpu->arch.mmcr[0] = mfspr(SPRN_MMCR0); + vcpu->arch.mmcra = mfspr(SPRN_MMCRA); + + freeze_pmu(vcpu->arch.mmcr[0], vcpu->arch.mmcra); + + vcpu->arch.pmc[0] = mfspr(SPRN_PMC1); + vcpu->arch.pmc[1] = mfspr(SPRN_PMC2); + vcpu->arch.pmc[2] = mfspr(SPRN_PMC3); + vcpu->arch.pmc[3] = mfspr(SPRN_PMC4); + vcpu->arch.pmc[4] = mfspr(SPRN_PMC5); + vcpu->arch.pmc[5] = mfspr(SPRN_PMC6); + vcpu->arch.mmcr[1] = mfspr(SPRN_MMCR1); + vcpu->arch.mmcr[2] = mfspr(SPRN_MMCR2); + vcpu->arch.sdar = mfspr(SPRN_SDAR); + vcpu->arch.siar = mfspr(SPRN_SIAR); + vcpu->arch.sier[0] = mfspr(SPRN_SIER); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + vcpu->arch.mmcr[3] = mfspr(SPRN_MMCR3); + vcpu->arch.sier[1] = mfspr(SPRN_SIER2); + vcpu->arch.sier[2] = mfspr(SPRN_SIER3); + } + + } else if (vcpu->arch.hfscr & HFSCR_PM) { + /* + * The guest accessed PMC SPRs without specifying they should + * be preserved, or it cleared pmcregs_in_use after the last + * access. Just ensure they are frozen. + */ + freeze_pmu(mfspr(SPRN_MMCR0), mfspr(SPRN_MMCRA)); + + /* + * Demand-fault PMU register access in the guest. + * + * This is used to grab the guest's VPA pmcregs_in_use value + * and reflect it into the host's VPA in the case of a nested + * hypervisor. + * + * It also avoids having to zero-out SPRs after each guest + * exit to avoid side-channels when. + * + * This is cleared here when we exit the guest, so later HFSCR + * interrupt handling can add it back to run the guest with + * PM enabled next time. + */ + if (!vcpu->arch.nested) + vcpu->arch.hfscr &= ~HFSCR_PM; + } /* otherwise the PMU should still be frozen */ + +#ifdef CONFIG_PPC_PSERIES + if (kvmhv_on_pseries()) { + barrier(); + get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse(); + barrier(); + } +#endif + + if (ppc_get_pmu_inuse()) { + mtspr(SPRN_PMC1, host_os_sprs->pmc1); + mtspr(SPRN_PMC2, host_os_sprs->pmc2); + mtspr(SPRN_PMC3, host_os_sprs->pmc3); + mtspr(SPRN_PMC4, host_os_sprs->pmc4); + mtspr(SPRN_PMC5, host_os_sprs->pmc5); + mtspr(SPRN_PMC6, host_os_sprs->pmc6); + mtspr(SPRN_MMCR1, host_os_sprs->mmcr1); + mtspr(SPRN_MMCR2, host_os_sprs->mmcr2); + mtspr(SPRN_SDAR, host_os_sprs->sdar); + mtspr(SPRN_SIAR, host_os_sprs->siar); + mtspr(SPRN_SIER, host_os_sprs->sier1); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_MMCR3, host_os_sprs->mmcr3); + mtspr(SPRN_SIER2, host_os_sprs->sier2); + mtspr(SPRN_SIER3, host_os_sprs->sier3); + } + + /* Set MMCRA then MMCR0 last */ + mtspr(SPRN_MMCRA, host_os_sprs->mmcra); + mtspr(SPRN_MMCR0, host_os_sprs->mmcr0); + isync(); + } +} +EXPORT_SYMBOL_GPL(switch_pmu_to_host); + +static void load_spr_state(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + /* TAR is very fast */ + mtspr(SPRN_TAR, vcpu->arch.tar); + +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC) && + current->thread.vrsave != vcpu->arch.vrsave) + mtspr(SPRN_VRSAVE, vcpu->arch.vrsave); +#endif + + if (vcpu->arch.hfscr & HFSCR_EBB) { + if (current->thread.ebbhr != vcpu->arch.ebbhr) + mtspr(SPRN_EBBHR, vcpu->arch.ebbhr); + if (current->thread.ebbrr != vcpu->arch.ebbrr) + mtspr(SPRN_EBBRR, vcpu->arch.ebbrr); + if (current->thread.bescr != vcpu->arch.bescr) + mtspr(SPRN_BESCR, vcpu->arch.bescr); + } + + if (cpu_has_feature(CPU_FTR_P9_TIDR) && + current->thread.tidr != vcpu->arch.tid) + mtspr(SPRN_TIDR, vcpu->arch.tid); + if (host_os_sprs->iamr != vcpu->arch.iamr) + mtspr(SPRN_IAMR, vcpu->arch.iamr); + if (host_os_sprs->amr != vcpu->arch.amr) + mtspr(SPRN_AMR, vcpu->arch.amr); + if (vcpu->arch.uamor != 0) + mtspr(SPRN_UAMOR, vcpu->arch.uamor); + if (current->thread.fscr != vcpu->arch.fscr) + mtspr(SPRN_FSCR, vcpu->arch.fscr); + if (current->thread.dscr != vcpu->arch.dscr) + mtspr(SPRN_DSCR, vcpu->arch.dscr); + if (vcpu->arch.pspb != 0) + mtspr(SPRN_PSPB, vcpu->arch.pspb); + + /* + * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI] + * clear (or hstate set appropriately to catch those registers + * being clobbered if we take a MCE or SRESET), so those are done + * later. + */ + + if (!(vcpu->arch.ctrl & 1)) + mtspr(SPRN_CTRLT, 0); +} + +static void store_spr_state(struct kvm_vcpu *vcpu) +{ + vcpu->arch.tar = mfspr(SPRN_TAR); + +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + vcpu->arch.vrsave = mfspr(SPRN_VRSAVE); +#endif + + if (vcpu->arch.hfscr & HFSCR_EBB) { + vcpu->arch.ebbhr = mfspr(SPRN_EBBHR); + vcpu->arch.ebbrr = mfspr(SPRN_EBBRR); + vcpu->arch.bescr = mfspr(SPRN_BESCR); + } + + if (cpu_has_feature(CPU_FTR_P9_TIDR)) + vcpu->arch.tid = mfspr(SPRN_TIDR); + vcpu->arch.iamr = mfspr(SPRN_IAMR); + vcpu->arch.amr = mfspr(SPRN_AMR); + vcpu->arch.uamor = mfspr(SPRN_UAMOR); + vcpu->arch.fscr = mfspr(SPRN_FSCR); + vcpu->arch.dscr = mfspr(SPRN_DSCR); + vcpu->arch.pspb = mfspr(SPRN_PSPB); + + vcpu->arch.ctrl = mfspr(SPRN_CTRLF); +} + +/* Returns true if current MSR and/or guest MSR may have changed */ +bool load_vcpu_state(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + bool ret = false; + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + unsigned long guest_msr = vcpu->arch.shregs.msr; + if (MSR_TM_ACTIVE(guest_msr)) { + kvmppc_restore_tm_hv(vcpu, guest_msr, true); + ret = true; + } else if (vcpu->arch.hfscr & HFSCR_TM) { + mtspr(SPRN_TEXASR, vcpu->arch.texasr); + mtspr(SPRN_TFHAR, vcpu->arch.tfhar); + mtspr(SPRN_TFIAR, vcpu->arch.tfiar); + } + } +#endif + + load_spr_state(vcpu, host_os_sprs); + + load_fp_state(&vcpu->arch.fp); +#ifdef CONFIG_ALTIVEC + load_vr_state(&vcpu->arch.vr); +#endif + + return ret; +} +EXPORT_SYMBOL_GPL(load_vcpu_state); + +void store_vcpu_state(struct kvm_vcpu *vcpu) +{ + store_spr_state(vcpu); + + store_fp_state(&vcpu->arch.fp); +#ifdef CONFIG_ALTIVEC + store_vr_state(&vcpu->arch.vr); +#endif + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + unsigned long guest_msr = vcpu->arch.shregs.msr; + if (MSR_TM_ACTIVE(guest_msr)) { + kvmppc_save_tm_hv(vcpu, guest_msr, true); + } else if (vcpu->arch.hfscr & HFSCR_TM) { + vcpu->arch.texasr = mfspr(SPRN_TEXASR); + vcpu->arch.tfhar = mfspr(SPRN_TFHAR); + vcpu->arch.tfiar = mfspr(SPRN_TFIAR); + + if (!vcpu->arch.nested) { + vcpu->arch.load_tm++; /* see load_ebb comment */ + if (!vcpu->arch.load_tm) + vcpu->arch.hfscr &= ~HFSCR_TM; + } + } + } +#endif +} +EXPORT_SYMBOL_GPL(store_vcpu_state); + +void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs) +{ + host_os_sprs->iamr = mfspr(SPRN_IAMR); + host_os_sprs->amr = mfspr(SPRN_AMR); +} +EXPORT_SYMBOL_GPL(save_p9_host_os_sprs); + +/* vcpu guest regs must already be saved */ +void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + /* + * current->thread.xxx registers must all be restored to host + * values before a potential context switch, othrewise the context + * switch itself will overwrite current->thread.xxx with the values + * from the guest SPRs. + */ + + mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso); + + if (cpu_has_feature(CPU_FTR_P9_TIDR) && + current->thread.tidr != vcpu->arch.tid) + mtspr(SPRN_TIDR, current->thread.tidr); + if (host_os_sprs->iamr != vcpu->arch.iamr) + mtspr(SPRN_IAMR, host_os_sprs->iamr); + if (vcpu->arch.uamor != 0) + mtspr(SPRN_UAMOR, 0); + if (host_os_sprs->amr != vcpu->arch.amr) + mtspr(SPRN_AMR, host_os_sprs->amr); + if (current->thread.fscr != vcpu->arch.fscr) + mtspr(SPRN_FSCR, current->thread.fscr); + if (current->thread.dscr != vcpu->arch.dscr) + mtspr(SPRN_DSCR, current->thread.dscr); + if (vcpu->arch.pspb != 0) + mtspr(SPRN_PSPB, 0); + + /* Save guest CTRL register, set runlatch to 1 */ + if (!(vcpu->arch.ctrl & 1)) + mtspr(SPRN_CTRLT, 1); + +#ifdef CONFIG_ALTIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC) && + vcpu->arch.vrsave != current->thread.vrsave) + mtspr(SPRN_VRSAVE, current->thread.vrsave); +#endif + if (vcpu->arch.hfscr & HFSCR_EBB) { + if (vcpu->arch.bescr != current->thread.bescr) + mtspr(SPRN_BESCR, current->thread.bescr); + if (vcpu->arch.ebbhr != current->thread.ebbhr) + mtspr(SPRN_EBBHR, current->thread.ebbhr); + if (vcpu->arch.ebbrr != current->thread.ebbrr) + mtspr(SPRN_EBBRR, current->thread.ebbrr); + + if (!vcpu->arch.nested) { + /* + * This is like load_fp in context switching, turn off + * the facility after it wraps the u8 to try avoiding + * saving and restoring the registers each partition + * switch. + */ + vcpu->arch.load_ebb++; + if (!vcpu->arch.load_ebb) + vcpu->arch.hfscr &= ~HFSCR_EBB; + } + } + + if (vcpu->arch.tar != current->thread.tar) + mtspr(SPRN_TAR, current->thread.tar); +} +EXPORT_SYMBOL_GPL(restore_p9_host_os_sprs); + #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) { @@ -56,10 +487,22 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator #define accumulate_time(vcpu, next) do {} while (0) #endif -static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev) +static inline u64 mfslbv(unsigned int idx) { - asm volatile("slbmfev %0,%1" : "=r" (*slbev) : "r" (idx)); - asm volatile("slbmfee %0,%1" : "=r" (*slbee) : "r" (idx)); + u64 slbev; + + asm volatile("slbmfev %0,%1" : "=r" (slbev) : "r" (idx)); + + return slbev; +} + +static inline u64 mfslbe(unsigned int idx) +{ + u64 slbee; + + asm volatile("slbmfee %0,%1" : "=r" (slbee) : "r" (idx)); + + return slbee; } static inline void mtslb(u64 slbee, u64 slbev) @@ -100,17 +543,19 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6 lpid = nested ? nested->shadow_lpid : kvm->arch.lpid; /* - * All the isync()s are overkill but trivially follow the ISA - * requirements. Some can likely be replaced with justification - * comment for why they are not needed. + * Prior memory accesses to host PID Q3 must be completed before we + * start switching, and stores must be drained to avoid not-my-LPAR + * logic (see switch_mmu_to_host). */ + asm volatile("hwsync" ::: "memory"); isync(); mtspr(SPRN_LPID, lpid); - isync(); mtspr(SPRN_LPCR, lpcr); - isync(); mtspr(SPRN_PID, vcpu->arch.pid); - isync(); + /* + * isync not required here because we are HRFID'ing to guest before + * any guest context access, which is context synchronising. + */ } static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr) @@ -120,25 +565,41 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpid = kvm->arch.lpid; + /* + * See switch_mmu_to_guest_radix. ptesync should not be required here + * even if the host is in HPT mode because speculative accesses would + * not cause RC updates (we are in real mode). + */ + asm volatile("hwsync" ::: "memory"); + isync(); mtspr(SPRN_LPID, lpid); mtspr(SPRN_LPCR, lpcr); mtspr(SPRN_PID, vcpu->arch.pid); for (i = 0; i < vcpu->arch.slb_max; i++) mtslb(vcpu->arch.slb[i].orige, vcpu->arch.slb[i].origv); - - isync(); + /* + * isync not required here, see switch_mmu_to_guest_radix. + */ } static void switch_mmu_to_host(struct kvm *kvm, u32 pid) { + /* + * The guest has exited, so guest MMU context is no longer being + * non-speculatively accessed, but a hwsync is needed before the + * mtLPIDR / mtPIDR switch, in order to ensure all stores are drained, + * so the not-my-LPAR tlbie logic does not overlook them. + */ + asm volatile("hwsync" ::: "memory"); isync(); mtspr(SPRN_PID, pid); - isync(); mtspr(SPRN_LPID, kvm->arch.host_lpid); - isync(); mtspr(SPRN_LPCR, kvm->arch.host_lpcr); - isync(); + /* + * isync is not required after the switch, because mtmsrd with L=0 + * is performed after this switch, which is context synchronising. + */ if (!radix_enabled()) slb_restore_bolted_realmode(); @@ -171,8 +632,10 @@ static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu) */ for (i = 0; i < vcpu->arch.slb_nr; i++) { u64 slbee, slbev; - mfslb(i, &slbee, &slbev); + + slbee = mfslbe(i); if (slbee & SLB_ESID_V) { + slbev = mfslbv(i); vcpu->arch.slb[nr].orige = slbee | i; vcpu->arch.slb[nr].origv = slbev; nr++; @@ -183,15 +646,128 @@ static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu) } } -int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr) +static void flush_guest_tlb(struct kvm *kvm) { + unsigned long rb, set; + + rb = PPC_BIT(52); /* IS = 2 */ + if (kvm_is_radix(kvm)) { + /* R=1 PRS=1 RIC=2 */ + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r" (rb), "i" (1), "i" (1), "i" (2), + "r" (0) : "memory"); + for (set = 1; set < kvm->arch.tlb_sets; ++set) { + rb += PPC_BIT(51); /* increment set number */ + /* R=1 PRS=1 RIC=0 */ + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r" (rb), "i" (1), "i" (1), "i" (0), + "r" (0) : "memory"); + } + asm volatile("ptesync": : :"memory"); + // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. + asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); + } else { + for (set = 0; set < kvm->arch.tlb_sets; ++set) { + /* R=0 PRS=0 RIC=0 */ + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r" (rb), "i" (0), "i" (0), "i" (0), + "r" (0) : "memory"); + rb += PPC_BIT(51); /* increment set number */ + } + asm volatile("ptesync": : :"memory"); + // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); + } +} + +static void check_need_tlb_flush(struct kvm *kvm, int pcpu, + struct kvm_nested_guest *nested) +{ + cpumask_t *need_tlb_flush; + bool all_set = true; + int i; + + if (nested) + need_tlb_flush = &nested->need_tlb_flush; + else + need_tlb_flush = &kvm->arch.need_tlb_flush; + + if (likely(!cpumask_test_cpu(pcpu, need_tlb_flush))) + return; + + /* + * Individual threads can come in here, but the TLB is shared between + * the 4 threads in a core, hence invalidating on one thread + * invalidates for all, so only invalidate the first time (if all bits + * were set. The others must still execute a ptesync. + * + * If a race occurs and two threads do the TLB flush, that is not a + * problem, just sub-optimal. + */ + for (i = cpu_first_tlb_thread_sibling(pcpu); + i <= cpu_last_tlb_thread_sibling(pcpu); + i += cpu_tlb_thread_sibling_step()) { + if (!cpumask_test_cpu(i, need_tlb_flush)) { + all_set = false; + break; + } + } + if (all_set) + flush_guest_tlb(kvm); + else + asm volatile("ptesync" ::: "memory"); + + /* Clear the bit after the TLB flush */ + cpumask_clear_cpu(pcpu, need_tlb_flush); +} + +unsigned long kvmppc_msr_hard_disable_set_facilities(struct kvm_vcpu *vcpu, unsigned long msr) +{ + unsigned long msr_needed = 0; + + msr &= ~MSR_EE; + + /* MSR bits may have been cleared by context switch so must recheck */ + if (IS_ENABLED(CONFIG_PPC_FPU)) + msr_needed |= MSR_FP; + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + msr_needed |= MSR_VEC; + if (cpu_has_feature(CPU_FTR_VSX)) + msr_needed |= MSR_VSX; + if ((cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) && + (vcpu->arch.hfscr & HFSCR_TM)) + msr_needed |= MSR_TM; + + /* + * This could be combined with MSR[RI] clearing, but that expands + * the unrecoverable window. It would be better to cover unrecoverable + * with KVM bad interrupt handling rather than use MSR[RI] at all. + * + * Much more difficult and less worthwhile to combine with IR/DR + * disable. + */ + if ((msr & msr_needed) != msr_needed) { + msr |= msr_needed; + __mtmsrd(msr, 0); + } else { + __hard_irq_disable(); + } + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + return msr; +} +EXPORT_SYMBOL_GPL(kvmppc_msr_hard_disable_set_facilities); + +int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) +{ + struct p9_host_os_sprs host_os_sprs; struct kvm *kvm = vcpu->kvm; struct kvm_nested_guest *nested = vcpu->arch.nested; struct kvmppc_vcore *vc = vcpu->arch.vcore; - s64 hdec; - u64 tb, purr, spurr; + s64 hdec, dec; + u64 purr, spurr; u64 *exsave; - bool ri_set; int trap; unsigned long msr; unsigned long host_hfscr; @@ -199,11 +775,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc unsigned long host_dawr0; unsigned long host_dawrx0; unsigned long host_psscr; + unsigned long host_hpsscr; unsigned long host_pidr; unsigned long host_dawr1; unsigned long host_dawrx1; + unsigned long dpdes; - hdec = time_limit - mftb(); + hdec = time_limit - *tb; if (hdec < 0) return BOOK3S_INTERRUPT_HV_DECREMENTER; @@ -214,51 +792,84 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc vcpu->arch.ceded = 0; - if (vc->tb_offset) { - u64 new_tb = mftb() + vc->tb_offset; - mtspr(SPRN_TBU40, new_tb); - tb = mftb(); - if ((tb & 0xffffff) < (new_tb & 0xffffff)) - mtspr(SPRN_TBU40, new_tb + 0x1000000); - vc->tb_offset_applied = vc->tb_offset; - } - - msr = mfmsr(); + /* Save MSR for restore, with EE clear. */ + msr = mfmsr() & ~MSR_EE; host_hfscr = mfspr(SPRN_HFSCR); host_ciabr = mfspr(SPRN_CIABR); - host_dawr0 = mfspr(SPRN_DAWR0); - host_dawrx0 = mfspr(SPRN_DAWRX0); - host_psscr = mfspr(SPRN_PSSCR); + host_psscr = mfspr(SPRN_PSSCR_PR); + if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) + host_hpsscr = mfspr(SPRN_PSSCR); host_pidr = mfspr(SPRN_PID); - if (cpu_has_feature(CPU_FTR_DAWR1)) { - host_dawr1 = mfspr(SPRN_DAWR1); - host_dawrx1 = mfspr(SPRN_DAWRX1); - } - if (vc->pcr) - mtspr(SPRN_PCR, vc->pcr | PCR_MASK); - mtspr(SPRN_DPDES, vc->dpdes); - mtspr(SPRN_VTB, vc->vtb); + if (dawr_enabled()) { + host_dawr0 = mfspr(SPRN_DAWR0); + host_dawrx0 = mfspr(SPRN_DAWRX0); + if (cpu_has_feature(CPU_FTR_DAWR1)) { + host_dawr1 = mfspr(SPRN_DAWR1); + host_dawrx1 = mfspr(SPRN_DAWRX1); + } + } local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR); local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR); + + save_p9_host_os_sprs(&host_os_sprs); + + msr = kvmppc_msr_hard_disable_set_facilities(vcpu, msr); + if (lazy_irq_pending()) { + trap = 0; + goto out; + } + + if (unlikely(load_vcpu_state(vcpu, &host_os_sprs))) + msr = mfmsr(); /* MSR may have been updated */ + + if (vc->tb_offset) { + u64 new_tb = *tb + vc->tb_offset; + mtspr(SPRN_TBU40, new_tb); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + *tb = new_tb; + vc->tb_offset_applied = vc->tb_offset; + } + + mtspr(SPRN_VTB, vc->vtb); mtspr(SPRN_PURR, vcpu->arch.purr); mtspr(SPRN_SPURR, vcpu->arch.spurr); + if (vc->pcr) + mtspr(SPRN_PCR, vc->pcr | PCR_MASK); + if (vcpu->arch.doorbell_request) { + vcpu->arch.doorbell_request = 0; + mtspr(SPRN_DPDES, 1); + } + if (dawr_enabled()) { - mtspr(SPRN_DAWR0, vcpu->arch.dawr0); - mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0); + if (vcpu->arch.dawr0 != host_dawr0) + mtspr(SPRN_DAWR0, vcpu->arch.dawr0); + if (vcpu->arch.dawrx0 != host_dawrx0) + mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0); if (cpu_has_feature(CPU_FTR_DAWR1)) { - mtspr(SPRN_DAWR1, vcpu->arch.dawr1); - mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1); + if (vcpu->arch.dawr1 != host_dawr1) + mtspr(SPRN_DAWR1, vcpu->arch.dawr1); + if (vcpu->arch.dawrx1 != host_dawrx1) + mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1); } } - mtspr(SPRN_CIABR, vcpu->arch.ciabr); - mtspr(SPRN_IC, vcpu->arch.ic); + if (vcpu->arch.ciabr != host_ciabr) + mtspr(SPRN_CIABR, vcpu->arch.ciabr); - mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC | - (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + + if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + } else { + if (vcpu->arch.psscr != host_psscr) + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); + } mtspr(SPRN_HFSCR, vcpu->arch.hfscr); @@ -276,18 +887,34 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc * HDSI which should correctly update the HDSISR the second time HDSI * entry. * - * Just do this on all p9 processors for now. + * The "radix prefetch bug" test can be used to test for this bug, as + * it also exists fo DD2.1 and below. */ - mtspr(SPRN_HDSISR, HDSISR_CANARY); + if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) + mtspr(SPRN_HDSISR, HDSISR_CANARY); mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0); mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1); mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2); mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3); - mtspr(SPRN_AMOR, ~0UL); + /* + * It might be preferable to load_vcpu_state here, in order to get the + * GPR/FP register loads executing in parallel with the previous mtSPR + * instructions, but for now that can't be done because the TM handling + * in load_vcpu_state can change some SPRs and vcpu state (nip, msr). + * But TM could be split out if this would be a significant benefit. + */ - local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_HV_P9; + /* + * MSR[RI] does not need to be cleared (and is not, for radix guests + * with no prefetch bug), because in_guest is set. If we take a SRESET + * or MCE with in_guest set but still in HV mode, then + * kvmppc_p9_bad_interrupt handles the interrupt, which effectively + * clears MSR[RI] and doesn't return. + */ + WRITE_ONCE(local_paca->kvm_hstate.in_guest, KVM_GUEST_MODE_HV_P9); + barrier(); /* Open in_guest critical section */ /* * Hash host, hash guest, or radix guest with prefetch bug, all have @@ -299,17 +926,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc save_clear_host_mmu(kvm); - if (kvm_is_radix(kvm)) { + if (kvm_is_radix(kvm)) switch_mmu_to_guest_radix(kvm, vcpu, lpcr); - if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) - __mtmsrd(0, 1); /* clear RI */ - - } else { + else switch_mmu_to_guest_hpt(kvm, vcpu, lpcr); - } /* TLBIEL uses LPID=LPIDR, so run this after setting guest LPID */ - kvmppc_check_need_tlb_flush(kvm, vc->pcpu, nested); + check_need_tlb_flush(kvm, vc->pcpu, nested); /* * P9 suppresses the HDEC exception when LPCR[HDICE] = 0, @@ -317,6 +940,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc */ mtspr(SPRN_HDEC, hdec); + mtspr(SPRN_DEC, vcpu->arch.dec_expires - *tb); + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_return_to_guest: #endif @@ -327,7 +952,9 @@ tm_return_to_guest: accumulate_time(vcpu, &vcpu->arch.guest_time); + switch_pmu_to_guest(vcpu, &host_os_sprs); kvmppc_p9_enter_guest(vcpu); + switch_pmu_to_host(vcpu, &host_os_sprs); accumulate_time(vcpu, &vcpu->arch.rm_intr); @@ -340,36 +967,27 @@ tm_return_to_guest: /* 0x2 bit for HSRR is only used by PR and P7/8 HV paths, clear it */ trap = local_paca->kvm_hstate.scratch0 & ~0x2; - /* HSRR interrupts leave MSR[RI] unchanged, SRR interrupts clear it. */ - ri_set = false; - if (likely(trap > BOOK3S_INTERRUPT_MACHINE_CHECK)) { - if (trap != BOOK3S_INTERRUPT_SYSCALL && - (vcpu->arch.shregs.msr & MSR_RI)) - ri_set = true; + if (likely(trap > BOOK3S_INTERRUPT_MACHINE_CHECK)) exsave = local_paca->exgen; - } else if (trap == BOOK3S_INTERRUPT_SYSTEM_RESET) { + else if (trap == BOOK3S_INTERRUPT_SYSTEM_RESET) exsave = local_paca->exnmi; - } else { /* trap == 0x200 */ + else /* trap == 0x200 */ exsave = local_paca->exmc; - } vcpu->arch.regs.gpr[1] = local_paca->kvm_hstate.scratch1; vcpu->arch.regs.gpr[3] = local_paca->kvm_hstate.scratch2; /* - * Only set RI after reading machine check regs (DAR, DSISR, SRR0/1) - * and hstate scratch (which we need to move into exsave to make - * re-entrant vs SRESET/MCE) + * After reading machine check regs (DAR, DSISR, SRR0/1) and hstate + * scratch (which we need to move into exsave to make re-entrant vs + * SRESET/MCE), register state is protected from reentrancy. However + * timebase, MMU, among other state is still set to guest, so don't + * enable MSR[RI] here. It gets enabled at the end, after in_guest + * is cleared. + * + * It is possible an NMI could come in here, which is why it is + * important to save the above state early so it can be debugged. */ - if (ri_set) { - if (unlikely(!(mfmsr() & MSR_RI))) { - __mtmsrd(MSR_RI, 1); - WARN_ON_ONCE(1); - } - } else { - WARN_ON_ONCE(mfmsr() & MSR_RI); - __mtmsrd(MSR_RI, 1); - } vcpu->arch.regs.gpr[9] = exsave[EX_R9/sizeof(u64)]; vcpu->arch.regs.gpr[10] = exsave[EX_R10/sizeof(u64)]; @@ -388,7 +1006,7 @@ tm_return_to_guest: kvmppc_realmode_machine_check(vcpu); } else if (unlikely(trap == BOOK3S_INTERRUPT_HMI)) { - kvmppc_realmode_hmi_handler(); + kvmppc_p9_realmode_hmi_handler(vcpu); } else if (trap == BOOK3S_INTERRUPT_H_EMUL_ASSIST) { vcpu->arch.emul_inst = mfspr(SPRN_HEIR); @@ -427,13 +1045,6 @@ tm_return_to_guest: */ mtspr(SPRN_HSRR0, vcpu->arch.regs.nip); mtspr(SPRN_HSRR1, vcpu->arch.shregs.msr); - - /* - * tm_return_to_guest re-loads SRR0/1, DAR, - * DSISR after RI is cleared, in case they had - * been clobbered by a MCE. - */ - __mtmsrd(0, 1); /* clear RI */ goto tm_return_to_guest; } } @@ -445,81 +1056,109 @@ tm_return_to_guest: /* Advance host PURR/SPURR by the amount used by guest */ purr = mfspr(SPRN_PURR); spurr = mfspr(SPRN_SPURR); - mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr + - purr - vcpu->arch.purr); - mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr + - spurr - vcpu->arch.spurr); + local_paca->kvm_hstate.host_purr += purr - vcpu->arch.purr; + local_paca->kvm_hstate.host_spurr += spurr - vcpu->arch.spurr; vcpu->arch.purr = purr; vcpu->arch.spurr = spurr; vcpu->arch.ic = mfspr(SPRN_IC); vcpu->arch.pid = mfspr(SPRN_PID); - vcpu->arch.psscr = mfspr(SPRN_PSSCR) & PSSCR_GUEST_VIS; + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); vcpu->arch.shregs.sprg0 = mfspr(SPRN_SPRG0); vcpu->arch.shregs.sprg1 = mfspr(SPRN_SPRG1); vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2); vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3); - /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ - mtspr(SPRN_PSSCR, host_psscr | - (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); - mtspr(SPRN_HFSCR, host_hfscr); - mtspr(SPRN_CIABR, host_ciabr); - mtspr(SPRN_DAWR0, host_dawr0); - mtspr(SPRN_DAWRX0, host_dawrx0); - if (cpu_has_feature(CPU_FTR_DAWR1)) { - mtspr(SPRN_DAWR1, host_dawr1); - mtspr(SPRN_DAWRX1, host_dawrx1); - } - - if (kvm_is_radix(kvm)) { - /* - * Since this is radix, do a eieio; tlbsync; ptesync sequence - * in case we interrupted the guest between a tlbie and a - * ptesync. - */ - asm volatile("eieio; tlbsync; ptesync"); - } + dpdes = mfspr(SPRN_DPDES); + if (dpdes) + vcpu->arch.doorbell_request = 1; - /* - * cp_abort is required if the processor supports local copy-paste - * to clear the copy buffer that was under control of the guest. - */ - if (cpu_has_feature(CPU_FTR_ARCH_31)) - asm volatile(PPC_CP_ABORT); - - vc->dpdes = mfspr(SPRN_DPDES); vc->vtb = mfspr(SPRN_VTB); - mtspr(SPRN_DPDES, 0); - if (vc->pcr) - mtspr(SPRN_PCR, PCR_MASK); + + dec = mfspr(SPRN_DEC); + if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ + dec = (s32) dec; + *tb = mftb(); + vcpu->arch.dec_expires = dec + *tb; if (vc->tb_offset_applied) { - u64 new_tb = mftb() - vc->tb_offset_applied; + u64 new_tb = *tb - vc->tb_offset_applied; mtspr(SPRN_TBU40, new_tb); - tb = mftb(); - if ((tb & 0xffffff) < (new_tb & 0xffffff)) - mtspr(SPRN_TBU40, new_tb + 0x1000000); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + *tb = new_tb; vc->tb_offset_applied = 0; } - mtspr(SPRN_HDEC, 0x7fffffff); - save_clear_guest_mmu(kvm, vcpu); switch_mmu_to_host(kvm, host_pidr); - local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE; /* - * If we are in real mode, only switch MMU on after the MMU is - * switched to host, to avoid the P9_RADIX_PREFETCH_BUG. + * Enable MSR here in order to have facilities enabled to save + * guest registers. This enables MMU (if we were in realmode), so + * only switch MMU on after the MMU is switched to host, to avoid + * the P9_RADIX_PREFETCH_BUG or hash guest context. */ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && - vcpu->arch.shregs.msr & MSR_TS_MASK) + vcpu->arch.shregs.msr & MSR_TS_MASK) msr |= MSR_TS_S; - __mtmsrd(msr, 0); + store_vcpu_state(vcpu); + + mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr); + mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr); + + if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) { + /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ + mtspr(SPRN_PSSCR, host_hpsscr | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + } + + mtspr(SPRN_HFSCR, host_hfscr); + if (vcpu->arch.ciabr != host_ciabr) + mtspr(SPRN_CIABR, host_ciabr); + + if (dawr_enabled()) { + if (vcpu->arch.dawr0 != host_dawr0) + mtspr(SPRN_DAWR0, host_dawr0); + if (vcpu->arch.dawrx0 != host_dawrx0) + mtspr(SPRN_DAWRX0, host_dawrx0); + if (cpu_has_feature(CPU_FTR_DAWR1)) { + if (vcpu->arch.dawr1 != host_dawr1) + mtspr(SPRN_DAWR1, host_dawr1); + if (vcpu->arch.dawrx1 != host_dawrx1) + mtspr(SPRN_DAWRX1, host_dawrx1); + } + } + + if (dpdes) + mtspr(SPRN_DPDES, 0); + if (vc->pcr) + mtspr(SPRN_PCR, PCR_MASK); + + /* HDEC must be at least as large as DEC, so decrementer_max fits */ + mtspr(SPRN_HDEC, decrementer_max); + + timer_rearm_host_dec(*tb); + + restore_p9_host_os_sprs(vcpu, &host_os_sprs); + + barrier(); /* Close in_guest critical section */ + WRITE_ONCE(local_paca->kvm_hstate.in_guest, KVM_GUEST_MODE_NONE); + /* Interrupts are recoverable at this point */ + + /* + * cp_abort is required if the processor supports local copy-paste + * to clear the copy buffer that was under control of the guest. + */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + asm volatile(PPC_CP_ABORT); + +out: end_timing(vcpu); return trap; diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index d4bca93b79f6..ccfd96965630 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -136,6 +136,60 @@ void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu) vcpu->arch.mce_evt = mce_evt; } + +long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + long ret = 0; + + /* + * Unapply and clear the offset first. That way, if the TB was not + * resynced then it will remain in host-offset, and if it was resynced + * then it is brought into host-offset. Then the tb offset is + * re-applied before continuing with the KVM exit. + * + * This way, we don't need to actually know whether not OPAL resynced + * the timebase or do any of the complicated dance that the P7/8 + * path requires. + */ + if (vc->tb_offset_applied) { + u64 new_tb = mftb() - vc->tb_offset_applied; + mtspr(SPRN_TBU40, new_tb); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + vc->tb_offset_applied = 0; + } + + local_paca->hmi_irqs++; + + if (hmi_handle_debugtrig(NULL) >= 0) { + ret = 1; + goto out; + } + + if (ppc_md.hmi_exception_early) + ppc_md.hmi_exception_early(NULL); + +out: + if (vc->tb_offset) { + u64 new_tb = mftb() + vc->tb_offset; + mtspr(SPRN_TBU40, new_tb); + if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) { + new_tb += 0x1000000; + mtspr(SPRN_TBU40, new_tb); + } + vc->tb_offset_applied = vc->tb_offset; + } + + return ret; +} + +/* + * The following subcore HMI handling is all only for pre-POWER9 CPUs. + */ + /* Check if dynamic split is in force and return subcore size accordingly. */ static inline int kvmppc_cur_subcore_size(void) { diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 2c1f3c6e72d1..2257fb18cb72 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -55,12 +55,6 @@ static int global_invalidates(struct kvm *kvm) smp_wmb(); cpumask_setall(&kvm->arch.need_tlb_flush); cpu = local_paca->kvm_hstate.kvm_vcore->pcpu; - /* - * On POWER9, threads are independent but the TLB is shared, - * so use the bit for the first thread to represent the core. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) - cpu = cpu_first_tlb_thread_sibling(cpu); cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush); } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 32a4b4d412b9..3f1aeff72438 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -778,17 +778,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) /* Restore AMR and UAMOR, set AMOR to all 1s */ ld r5,VCPU_AMR(r4) ld r6,VCPU_UAMOR(r4) - li r7,-1 mtspr SPRN_AMR,r5 mtspr SPRN_UAMOR,r6 - mtspr SPRN_AMOR,r7 - /* Restore state of CTRL run bit; assume 1 on entry */ + /* Restore state of CTRL run bit; the host currently has it set to 1 */ lwz r5,VCPU_CTRL(r4) andi. r5,r5,1 bne 4f - mfspr r6,SPRN_CTRLF - clrrdi r6,r6,1 + li r6,0 mtspr SPRN_CTRLT,r6 4: /* Secondary threads wait for primary to have done partition switch */ @@ -817,10 +814,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) * Set the decrementer to the guest decrementer. */ ld r8,VCPU_DEC_EXPIRES(r4) - /* r8 is a host timebase value here, convert to guest TB */ - ld r5,HSTATE_KVM_VCORE(r13) - ld r6,VCORE_TB_OFFSET_APPL(r5) - add r8,r8,r6 mftb r7 subf r3,r7,r8 mtspr SPRN_DEC,r3 @@ -1195,9 +1188,6 @@ guest_bypass: mftb r6 extsw r5,r5 16: add r5,r5,r6 - /* r5 is a guest timebase value here, convert to host TB */ - ld r4,VCORE_TB_OFFSET_APPL(r3) - subf r5,r4,r5 std r5,VCPU_DEC_EXPIRES(r9) /* Increment exit count, poke other threads to exit */ @@ -1211,12 +1201,12 @@ guest_bypass: stw r0, VCPU_CPU(r9) stw r0, VCPU_THREAD_CPU(r9) - /* Save guest CTRL register, set runlatch to 1 */ + /* Save guest CTRL register, set runlatch to 1 if it was clear */ mfspr r6,SPRN_CTRLF stw r6,VCPU_CTRL(r9) andi. r0,r6,1 bne 4f - ori r6,r6,1 + li r6,1 mtspr SPRN_CTRLT,r6 4: /* @@ -2163,9 +2153,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* save expiry time of guest decrementer */ add r3, r3, r5 ld r4, HSTATE_KVM_VCPU(r13) - ld r5, HSTATE_KVM_VCORE(r13) - ld r6, VCORE_TB_OFFSET_APPL(r5) - subf r3, r6, r3 /* convert to host TB value */ std r3, VCPU_DEC_EXPIRES(r4) #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING @@ -2186,8 +2173,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) * Also clear the runlatch bit before napping. */ kvm_do_nap: - mfspr r0, SPRN_CTRLF - clrrdi r0, r0, 1 + li r0,0 mtspr SPRN_CTRLT, r0 li r0,1 @@ -2206,8 +2192,7 @@ kvm_nap_sequence: /* desired LPCR value in r5 */ bl isa206_idle_insn_mayloss - mfspr r0, SPRN_CTRLF - ori r0, r0, 1 + li r0,1 mtspr SPRN_CTRLT, r0 mtspr SPRN_SRR1, r3 @@ -2264,9 +2249,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* Restore guest decrementer */ ld r3, VCPU_DEC_EXPIRES(r4) - ld r5, HSTATE_KVM_VCORE(r13) - ld r6, VCORE_TB_OFFSET_APPL(r5) - add r3, r3, r6 /* convert host TB to guest TB value */ mftb r7 subf r3, r7, r3 mtspr SPRN_DEC, r3 @@ -2778,10 +2760,11 @@ kvmppc_msr_interrupt: blr /* + * void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu) + * * Load up guest PMU state. R3 points to the vcpu struct. */ -_GLOBAL(kvmhv_load_guest_pmu) -EXPORT_SYMBOL_GPL(kvmhv_load_guest_pmu) +kvmhv_load_guest_pmu: mr r4, r3 mflr r0 li r3, 1 @@ -2816,26 +2799,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG) mtspr SPRN_SIAR, r7 mtspr SPRN_SDAR, r8 BEGIN_FTR_SECTION - ld r5, VCPU_MMCR + 24(r4) - ld r6, VCPU_SIER + 8(r4) - ld r7, VCPU_SIER + 16(r4) - mtspr SPRN_MMCR3, r5 - mtspr SPRN_SIER2, r6 - mtspr SPRN_SIER3, r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) -BEGIN_FTR_SECTION ld r5, VCPU_MMCR + 16(r4) ld r6, VCPU_SIER(r4) mtspr SPRN_MMCR2, r5 mtspr SPRN_SIER, r6 -BEGIN_FTR_SECTION_NESTED(96) lwz r7, VCPU_PMC + 24(r4) lwz r8, VCPU_PMC + 28(r4) ld r9, VCPU_MMCRS(r4) mtspr SPRN_SPMC1, r7 mtspr SPRN_SPMC2, r8 mtspr SPRN_MMCRS, r9 -END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtspr SPRN_MMCR0, r3 isync @@ -2843,10 +2816,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) blr /* + * void kvmhv_load_host_pmu(void) + * * Reload host PMU state saved in the PACA by kvmhv_save_host_pmu. */ -_GLOBAL(kvmhv_load_host_pmu) -EXPORT_SYMBOL_GPL(kvmhv_load_host_pmu) +kvmhv_load_host_pmu: mflr r0 lbz r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */ cmpwi r4, 0 @@ -2884,25 +2858,18 @@ BEGIN_FTR_SECTION mtspr SPRN_MMCR2, r8 mtspr SPRN_SIER, r9 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - ld r5, HSTATE_MMCR3(r13) - ld r6, HSTATE_SIER2(r13) - ld r7, HSTATE_SIER3(r13) - mtspr SPRN_MMCR3, r5 - mtspr SPRN_SIER2, r6 - mtspr SPRN_SIER3, r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) mtspr SPRN_MMCR0, r3 isync mtlr r0 23: blr /* + * void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use) + * * Save guest PMU state into the vcpu struct. * r3 = vcpu, r4 = full save flag (PMU in use flag set in VPA) */ -_GLOBAL(kvmhv_save_guest_pmu) -EXPORT_SYMBOL_GPL(kvmhv_save_guest_pmu) +kvmhv_save_guest_pmu: mr r9, r3 mr r8, r4 BEGIN_FTR_SECTION @@ -2951,14 +2918,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) BEGIN_FTR_SECTION std r10, VCPU_MMCR + 16(r9) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) -BEGIN_FTR_SECTION - mfspr r5, SPRN_MMCR3 - mfspr r6, SPRN_SIER2 - mfspr r7, SPRN_SIER3 - std r5, VCPU_MMCR + 24(r9) - std r6, VCPU_SIER + 8(r9) - std r7, VCPU_SIER + 16(r9) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) std r7, VCPU_SIAR(r9) std r8, VCPU_SDAR(r9) mfspr r3, SPRN_PMC1 @@ -2976,7 +2935,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) BEGIN_FTR_SECTION mfspr r5, SPRN_SIER std r5, VCPU_SIER(r9) -BEGIN_FTR_SECTION_NESTED(96) mfspr r6, SPRN_SPMC1 mfspr r7, SPRN_SPMC2 mfspr r8, SPRN_MMCRS @@ -2985,7 +2943,6 @@ BEGIN_FTR_SECTION_NESTED(96) std r8, VCPU_MMCRS(r9) lis r4, 0x8000 mtspr SPRN_MMCRS, r4 -END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 22: blr diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 28c436df9935..e414ca44839f 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -459,7 +459,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) struct kvm_memslots *slots; struct kvm_memory_slot *memslot, *m; int ret = H_SUCCESS; - int srcu_idx; + int srcu_idx, bkt; kvm->arch.secure_guest = KVMPPC_SECURE_INIT_START; @@ -478,7 +478,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) /* register the memslot */ slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { ret = __kvmppc_uvmem_memslot_create(kvm, memslot); if (ret) break; @@ -486,7 +486,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) if (ret) { slots = kvm_memslots(kvm); - kvm_for_each_memslot(m, slots) { + kvm_for_each_memslot(m, bkt, slots) { if (m == memslot) break; __kvmppc_uvmem_memslot_delete(kvm, memslot); @@ -647,7 +647,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot, unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) { - int srcu_idx; + int srcu_idx, bkt; struct kvm_memory_slot *memslot; /* @@ -662,7 +662,7 @@ unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) srcu_idx = srcu_read_lock(&kvm->srcu); - kvm_for_each_memslot(memslot, kvm_memslots(kvm)) + kvm_for_each_memslot(memslot, bkt, kvm_memslots(kvm)) kvmppc_uvmem_drop_pages(memslot, kvm, false); srcu_read_unlock(&kvm->srcu, srcu_idx); @@ -821,7 +821,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; long ret = H_SUCCESS; if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) @@ -830,7 +830,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) /* migrate any unmoved normal pfn to device pfns*/ srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { ret = kvmppc_uv_migrate_mem_slot(kvm, memslot); if (ret) { /* diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 6bc9425acb32..34a801c3604a 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -428,7 +428,7 @@ static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu) /************* MMU Notifiers *************/ static bool do_kvm_unmap_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - long i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) @@ -492,7 +492,7 @@ static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr) if (msr & MSR_POW) { if (!vcpu->arch.pending_exceptions) { - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); vcpu->stat.generic.halt_wakeup++; @@ -1899,16 +1899,15 @@ static void kvmppc_core_flush_memslot_pr(struct kvm *kvm, } static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { return 0; } static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index ac14239f3424..1f10e7dfcdd0 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -376,7 +376,7 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_stuff_tce(vcpu); case H_CEDE: kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); vcpu->stat.generic.halt_wakeup++; return EMULATE_DONE; diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index ebd5d920de8c..9cc466006e8b 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -942,8 +942,8 @@ static int xics_debug_show(struct seq_file *m, void *private) struct kvmppc_xics *xics = m->private; struct kvm *kvm = xics->kvm; struct kvm_vcpu *vcpu; - int icsid, i; - unsigned long flags; + int icsid; + unsigned long flags, i; unsigned long t_rm_kick_vcpu, t_rm_check_resend; unsigned long t_rm_notify_eoi; unsigned long t_reject, t_check_resend; @@ -1340,7 +1340,7 @@ static int xics_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) static void kvmppc_xics_release(struct kvm_device *dev) { struct kvmppc_xics *xics = dev->private; - int i; + unsigned long i; struct kvm *kvm = xics->kvm; struct kvm_vcpu *vcpu; diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index 6231f76bdd66..8e4c79e2fcd8 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -116,7 +116,7 @@ static inline struct kvmppc_icp *kvmppc_xics_find_server(struct kvm *kvm, u32 nr) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.icp && nr == vcpu->arch.icp->server_num) diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 225008882958..e216c068075d 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -368,7 +368,8 @@ static int xive_check_provisioning(struct kvm *kvm, u8 prio) { struct kvmppc_xive *xive = kvm->arch.xive; struct kvm_vcpu *vcpu; - int i, rc; + unsigned long i; + int rc; lockdep_assert_held(&xive->lock); @@ -439,7 +440,8 @@ static int xive_try_pick_queue(struct kvm_vcpu *vcpu, u8 prio) int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio) { struct kvm_vcpu *vcpu; - int i, rc; + unsigned long i; + int rc; /* Locate target server */ vcpu = kvmppc_xive_find_server(kvm, *server); @@ -1519,7 +1521,8 @@ static void xive_pre_save_queue(struct kvmppc_xive *xive, struct xive_q *q) static void xive_pre_save_scan(struct kvmppc_xive *xive) { struct kvm_vcpu *vcpu = NULL; - int i, j; + unsigned long i; + int j; /* * See comment in xive_get_source() about how this @@ -1700,7 +1703,7 @@ static bool xive_check_delayed_irq(struct kvmppc_xive *xive, u32 irq) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; @@ -2037,7 +2040,7 @@ static void kvmppc_xive_release(struct kvm_device *dev) struct kvmppc_xive *xive = dev->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; pr_devel("Releasing xive device\n"); @@ -2291,7 +2294,7 @@ static int xive_debug_show(struct seq_file *m, void *private) u64 t_vm_h_cppr = 0; u64 t_vm_h_eoi = 0; u64 t_vm_h_ipi = 0; - unsigned int i; + unsigned long i; if (!kvm) return 0; diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index e6a9651c6f1e..09d0657596c3 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -199,7 +199,7 @@ struct kvmppc_xive_vcpu { static inline struct kvm_vcpu *kvmppc_xive_find_server(struct kvm *kvm, u32 nr) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.xive_vcpu && nr == vcpu->arch.xive_vcpu->server_num) @@ -240,7 +240,7 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server) static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id) diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 99db9ac49901..561a5bfe0468 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -807,7 +807,7 @@ static int kvmppc_xive_reset(struct kvmppc_xive *xive) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; pr_devel("%s\n", __func__); @@ -916,7 +916,7 @@ static int kvmppc_xive_native_eq_sync(struct kvmppc_xive *xive) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; pr_devel("%s\n", __func__); @@ -1017,7 +1017,7 @@ static void kvmppc_xive_native_release(struct kvm_device *dev) struct kvmppc_xive *xive = dev->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; pr_devel("Releasing xive native device\n"); @@ -1214,7 +1214,7 @@ static int xive_native_debug_show(struct seq_file *m, void *private) struct kvmppc_xive *xive = m->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; if (!kvm) return 0; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 8c15c90dd3a9..06c5830a93f9 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -718,7 +718,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) if (vcpu->arch.shared->msr & MSR_WE) { local_irq_enable(); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); hard_irq_disable(); @@ -1821,16 +1821,15 @@ void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) } int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { return 0; } void kvmppc_core_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 64eb833e9f02..051102d50c31 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -65,7 +65,7 @@ static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb) ulong param = vcpu->arch.regs.gpr[rb]; int prio = dbell2prio(rb); int pir = param & PPC_DBELL_PIR_MASK; - int i; + unsigned long i; struct kvm_vcpu *cvcpu; if (prio < 0) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index a72920f4f221..2ad0ccd202d5 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -236,7 +236,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) break; case EV_HCALL_TOKEN(EV_IDLE): r = EV_SUCCESS; - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); break; default: @@ -463,9 +463,6 @@ err_out: void kvm_arch_destroy_vm(struct kvm *kvm) { - unsigned int i; - struct kvm_vcpu *vcpu; - #ifdef CONFIG_KVM_XICS /* * We call kick_all_cpus_sync() to ensure that all @@ -476,14 +473,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kick_all_cpus_sync(); #endif - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); + kvm_destroy_vcpus(kvm); mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); kvmppc_core_destroy_vm(kvm); @@ -706,20 +698,19 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - return kvmppc_core_prepare_memory_region(kvm, memslot, mem, change); + return kvmppc_core_prepare_memory_region(kvm, old, new, change); } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - kvmppc_core_commit_memory_region(kvm, mem, old, new, change); + kvmppc_core_commit_memory_region(kvm, old, new, change); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, @@ -762,7 +753,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (err) goto out_vcpu_uninit; - vcpu->arch.waitp = &vcpu->wait; + rcuwait_init(&vcpu->arch.wait); + vcpu->arch.waitp = &vcpu->arch.wait; kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id); return 0; diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 3a600bd7fbc6..77820036c722 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -572,18 +572,6 @@ void __init radix__early_init_devtree(void) return; } -static void radix_init_amor(void) -{ - /* - * In HV mode, we init AMOR (Authority Mask Override Register) so that - * the hypervisor and guest can setup IAMR (Instruction Authority Mask - * Register), enable key 0 and set it to 1. - * - * AMOR = 0b1100 .... 0000 (Mask for key 0 is 11) - */ - mtspr(SPRN_AMOR, (3ul << 62)); -} - void __init radix__early_init_mmu(void) { unsigned long lpcr; @@ -644,7 +632,6 @@ void __init radix__early_init_mmu(void) lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); radix_init_partition_table(); - radix_init_amor(); } else { radix_init_pseries(); } @@ -668,8 +655,6 @@ void radix__early_init_mmu_secondary(void) set_ptcr_when_no_uv(__pa(partition_tb) | (PATB_SIZE_SHIFT - 12)); - - radix_init_amor(); } radix__switch_mmu_context(NULL, &init_mm); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 73e62e9b179b..8d4ff93462fb 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2419,8 +2419,24 @@ int register_power_pmu(struct power_pmu *pmu) } #ifdef CONFIG_PPC64 +static bool pmu_override = false; +static unsigned long pmu_override_val; +static void do_pmu_override(void *data) +{ + ppc_set_pmu_inuse(1); + if (pmu_override_val) + mtspr(SPRN_MMCR1, pmu_override_val); + mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC); +} + static int __init init_ppc64_pmu(void) { + if (cpu_has_feature(CPU_FTR_HVMODE) && pmu_override) { + pr_warn("disabling perf due to pmu_override= command line option.\n"); + on_each_cpu(do_pmu_override, NULL, 1); + return 0; + } + /* run through all the pmu drivers one at a time */ if (!init_power5_pmu()) return 0; @@ -2442,4 +2458,23 @@ static int __init init_ppc64_pmu(void) return init_generic_compat_pmu(); } early_initcall(init_ppc64_pmu); + +static int __init pmu_setup(char *str) +{ + unsigned long val; + + if (!early_cpu_has_feature(CPU_FTR_HVMODE)) + return 0; + + pmu_override = true; + + if (kstrtoul(str, 0, &val)) + val = 0; + + pmu_override_val = val; + + return 1; +} +__setup("pmu_override=", pmu_setup); + #endif diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index e3ffdc8e8567..3bc84e2fe064 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -306,8 +306,8 @@ struct p7_sprs { /* per thread SPRs that get lost in shallow states */ u64 amr; u64 iamr; - u64 amor; u64 uamor; + /* amor is restored to constant ~0 */ }; static unsigned long power7_idle_insn(unsigned long type) @@ -378,7 +378,6 @@ static unsigned long power7_idle_insn(unsigned long type) if (cpu_has_feature(CPU_FTR_ARCH_207S)) { sprs.amr = mfspr(SPRN_AMR); sprs.iamr = mfspr(SPRN_IAMR); - sprs.amor = mfspr(SPRN_AMOR); sprs.uamor = mfspr(SPRN_UAMOR); } @@ -397,7 +396,7 @@ static unsigned long power7_idle_insn(unsigned long type) */ mtspr(SPRN_AMR, sprs.amr); mtspr(SPRN_IAMR, sprs.iamr); - mtspr(SPRN_AMOR, sprs.amor); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_UAMOR, sprs.uamor); } } @@ -589,7 +588,6 @@ struct p9_sprs { u64 purr; u64 spurr; u64 dscr; - u64 wort; u64 ciabr; u64 mmcra; @@ -687,7 +685,6 @@ static unsigned long power9_idle_stop(unsigned long psscr) sprs.amr = mfspr(SPRN_AMR); sprs.iamr = mfspr(SPRN_IAMR); - sprs.amor = mfspr(SPRN_AMOR); sprs.uamor = mfspr(SPRN_UAMOR); srr1 = isa300_idle_stop_mayloss(psscr); /* go idle */ @@ -708,7 +705,7 @@ static unsigned long power9_idle_stop(unsigned long psscr) */ mtspr(SPRN_AMR, sprs.amr); mtspr(SPRN_IAMR, sprs.iamr); - mtspr(SPRN_AMOR, sprs.amor); + mtspr(SPRN_AMOR, ~0); mtspr(SPRN_UAMOR, sprs.uamor); /* diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 8b28ff9d98d1..83100c6524cc 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2107,8 +2107,14 @@ static void dump_300_sprs(void) if (!cpu_has_feature(CPU_FTR_ARCH_300)) return; - printf("pidr = %.16lx tidr = %.16lx\n", - mfspr(SPRN_PID), mfspr(SPRN_TIDR)); + if (cpu_has_feature(CPU_FTR_P9_TIDR)) { + printf("pidr = %.16lx tidr = %.16lx\n", + mfspr(SPRN_PID), mfspr(SPRN_TIDR)); + } else { + printf("pidr = %.16lx\n", + mfspr(SPRN_PID)); + } + printf("psscr = %.16lx\n", hv ? mfspr(SPRN_PSSCR) : mfspr(SPRN_PSSCR_PR)); diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 25ba21f98504..907fafea787e 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -12,14 +12,12 @@ #include <linux/types.h> #include <linux/kvm.h> #include <linux/kvm_types.h> +#include <asm/csr.h> #include <asm/kvm_vcpu_fp.h> #include <asm/kvm_vcpu_timer.h> -#ifdef CONFIG_64BIT -#define KVM_MAX_VCPUS (1U << 16) -#else -#define KVM_MAX_VCPUS (1U << 9) -#endif +#define KVM_MAX_VCPUS \ + ((HGATP_VMID_MASK >> HGATP_VMID_SHIFT) + 1) #define KVM_HALT_POLL_NS_DEFAULT 500000 @@ -210,7 +208,6 @@ struct kvm_vcpu_arch { static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} #define KVM_ARCH_WANT_MMU_NOTIFIER diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 30cdd1df0098..300590225348 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -5,14 +5,10 @@ ccflags-y += -I $(srctree)/$(src) -KVM := ../../../virt/kvm +include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o -kvm-y += $(KVM)/kvm_main.o -kvm-y += $(KVM)/coalesced_mmio.o -kvm-y += $(KVM)/binary_stats.o -kvm-y += $(KVM)/eventfd.o kvm-y += main.o kvm-y += vm.o kvm-y += vmid.o diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index d81bae8eb55e..7d884b15cf5e 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -453,10 +453,15 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { + gpa_t gpa = slot->base_gfn << PAGE_SHIFT; + phys_addr_t size = slot->npages << PAGE_SHIFT; + + spin_lock(&kvm->mmu_lock); + stage2_unmap_range(kvm, gpa, size, false); + spin_unlock(&kvm->mmu_lock); } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -466,18 +471,18 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * allocated dirty_bitmap[], dirty pages will be tracked while * the memory slot is write protected. */ - if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) - stage2_wp_memory_region(kvm, mem->slot); + if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) + stage2_wp_memory_region(kvm, new->id); } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - hva_t hva = mem->userspace_addr; - hva_t reg_end = hva + mem->memory_size; - bool writable = !(mem->flags & KVM_MEM_READONLY); + hva_t hva, reg_end, size; + gpa_t base_gpa; + bool writable; int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && @@ -488,10 +493,16 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the GPA * space addressable by the KVM guest GPA space. */ - if ((memslot->base_gfn + memslot->npages) >= + if ((new->base_gfn + new->npages) >= (stage2_gpa_size >> PAGE_SHIFT)) return -EFAULT; + hva = new->userspace_addr; + size = new->npages << PAGE_SHIFT; + reg_end = hva + size; + base_gpa = new->base_gfn << PAGE_SHIFT; + writable = !(new->flags & KVM_MEM_READONLY); + mmap_read_lock(current->mm); /* @@ -527,15 +538,14 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, vm_end = min(reg_end, vma->vm_end); if (vma->vm_flags & VM_PFNMAP) { - gpa_t gpa = mem->guest_phys_addr + - (vm_start - mem->userspace_addr); + gpa_t gpa = base_gpa + (vm_start - hva); phys_addr_t pa; pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; pa += vm_start - vma->vm_start; /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; goto out; } @@ -553,8 +563,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, spin_lock(&kvm->mmu_lock); if (ret) - stage2_unmap_range(kvm, mem->guest_phys_addr, - mem->memory_size, false); + stage2_unmap_range(kvm, base_gpa, size, false); spin_unlock(&kvm->mmu_lock); out: diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index 7f2d742ae4c6..571f319e995a 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -146,7 +146,7 @@ static int system_opcode_insn(struct kvm_vcpu *vcpu, vcpu->stat.wfi_exit_stat++; if (!kvm_arch_vcpu_runnable(vcpu)) { srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); } diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 3b0e703d22cf..d0d2bcab2f7b 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -60,7 +60,7 @@ int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) static void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu, struct kvm_run *run, u32 type) { - int i; + unsigned long i; struct kvm_vcpu *tmp; kvm_for_each_vcpu(i, tmp, vcpu->kvm) diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index fb18af34a4b5..7619691d8953 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -46,15 +46,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) void kvm_arch_destroy_vm(struct kvm *kvm) { - int i; - - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - atomic_set(&kvm->online_vcpus, 0); + kvm_destroy_vcpus(kvm); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c index 2c6253b293bc..807228f8f409 100644 --- a/arch/riscv/kvm/vmid.c +++ b/arch/riscv/kvm/vmid.c @@ -65,7 +65,7 @@ bool kvm_riscv_stage2_vmid_ver_changed(struct kvm_vmid *vmid) void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu) { - int i; + unsigned long i; struct kvm_vcpu *v; struct cpumask hmask; struct kvm_vmid *vmid = &vcpu->kvm->arch.vmid; diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index fd825097cf04..b626bc6e0eaf 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -403,7 +403,6 @@ CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y @@ -476,6 +475,7 @@ CONFIG_MACVLAN=m CONFIG_MACVTAP=m CONFIG_VXLAN=m CONFIG_BAREUDP=m +CONFIG_AMT=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m @@ -489,6 +489,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ASIX is not set # CONFIG_NET_VENDOR_ATHEROS is not set # CONFIG_NET_VENDOR_BROADCOM is not set # CONFIG_NET_VENDOR_BROCADE is not set @@ -571,6 +572,7 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m +# CONFIG_DRM_DEBUG_MODESET_LOCK is not set CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y @@ -775,12 +777,14 @@ CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m CONFIG_RANDOM32_SELFTEST=y +CONFIG_XZ_DEC_MICROLZMA=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y CONFIG_HEADERS_INSTALL=y CONFIG_DEBUG_SECTION_MISMATCH=y @@ -807,6 +811,7 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_KFENCE=y +CONFIG_KFENCE_STATIC_KEYS=y CONFIG_DEBUG_SHIRQ=y CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y @@ -842,6 +847,7 @@ CONFIG_FTRACE_STARTUP_TEST=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m CONFIG_SAMPLE_FTRACE_DIRECT=m +CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m CONFIG_DEBUG_ENTRY=y CONFIG_CIO_INJECT=y CONFIG_KUNIT=m @@ -860,7 +866,7 @@ CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_MIN_HEAP=y -CONFIG_KPROBES_SANITY_TEST=y +CONFIG_KPROBES_SANITY_TEST=m CONFIG_RBTREE_TEST=y CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index c9c3cedff2d8..0056cab27372 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -394,7 +394,6 @@ CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y @@ -467,6 +466,7 @@ CONFIG_MACVLAN=m CONFIG_MACVTAP=m CONFIG_VXLAN=m CONFIG_BAREUDP=m +CONFIG_AMT=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m @@ -480,6 +480,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ASIX is not set # CONFIG_NET_VENDOR_ATHEROS is not set # CONFIG_NET_VENDOR_BROADCOM is not set # CONFIG_NET_VENDOR_BROCADE is not set @@ -762,12 +763,14 @@ CONFIG_PRIME_NUMBERS=m CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m +CONFIG_XZ_DEC_MICROLZMA=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y @@ -792,9 +795,11 @@ CONFIG_HIST_TRIGGERS=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m CONFIG_SAMPLE_FTRACE_DIRECT=m +CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m CONFIG_KUNIT=m CONFIG_KUNIT_DEBUGFS=y CONFIG_LKDTM=m +CONFIG_KPROBES_SANITY_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index aceccf3b9a88..eed3b9acfa71 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -65,9 +65,11 @@ CONFIG_ZFCP=y # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" # CONFIG_ZLIB_DFLTCC is not set +CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y # CONFIG_SYMBOLIC_ERRNAME is not set CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index a604d51acfc8..a22c9266ea05 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1010,6 +1010,4 @@ static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm, static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} -void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu); - #endif diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index e4dc64cc9c55..287bb88f7698 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -14,12 +14,13 @@ /* I/O Map */ #define ZPCI_IOMAP_SHIFT 48 -#define ZPCI_IOMAP_ADDR_BASE 0x8000000000000000UL +#define ZPCI_IOMAP_ADDR_SHIFT 62 +#define ZPCI_IOMAP_ADDR_BASE (1UL << ZPCI_IOMAP_ADDR_SHIFT) #define ZPCI_IOMAP_ADDR_OFF_MASK ((1UL << ZPCI_IOMAP_SHIFT) - 1) #define ZPCI_IOMAP_MAX_ENTRIES \ - ((ULONG_MAX - ZPCI_IOMAP_ADDR_BASE + 1) / (1UL << ZPCI_IOMAP_SHIFT)) + (1UL << (ZPCI_IOMAP_ADDR_SHIFT - ZPCI_IOMAP_SHIFT)) #define ZPCI_IOMAP_ADDR_IDX_MASK \ - (~ZPCI_IOMAP_ADDR_OFF_MASK - ZPCI_IOMAP_ADDR_BASE) + ((ZPCI_IOMAP_ADDR_BASE - 1) & ~ZPCI_IOMAP_ADDR_OFF_MASK) struct zpci_iomap_entry { u32 fh; diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 72d3e49c2860..86218382d29c 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -91,23 +91,23 @@ struct uv_cb_header { /* Query Ultravisor Information */ struct uv_cb_qui { - struct uv_cb_header header; - u64 reserved08; - u64 inst_calls_list[4]; - u64 reserved30[2]; - u64 uv_base_stor_len; - u64 reserved48; - u64 conf_base_phys_stor_len; - u64 conf_base_virt_stor_len; - u64 conf_virt_var_stor_len; - u64 cpu_stor_len; - u32 reserved70[3]; - u32 max_num_sec_conf; - u64 max_guest_stor_addr; - u8 reserved88[158 - 136]; - u16 max_guest_cpu_id; - u64 uv_feature_indications; - u8 reserveda0[200 - 168]; + struct uv_cb_header header; /* 0x0000 */ + u64 reserved08; /* 0x0008 */ + u64 inst_calls_list[4]; /* 0x0010 */ + u64 reserved30[2]; /* 0x0030 */ + u64 uv_base_stor_len; /* 0x0040 */ + u64 reserved48; /* 0x0048 */ + u64 conf_base_phys_stor_len; /* 0x0050 */ + u64 conf_base_virt_stor_len; /* 0x0058 */ + u64 conf_virt_var_stor_len; /* 0x0060 */ + u64 cpu_stor_len; /* 0x0068 */ + u32 reserved70[3]; /* 0x0070 */ + u32 max_num_sec_conf; /* 0x007c */ + u64 max_guest_stor_addr; /* 0x0080 */ + u8 reserved88[158 - 136]; /* 0x0088 */ + u16 max_guest_cpu_id; /* 0x009e */ + u64 uv_feature_indications; /* 0x00a0 */ + u8 reserveda8[200 - 168]; /* 0x00a8 */ } __packed __aligned(8); /* Initialize Ultravisor */ diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 67a8e770e369..2e84d3922f7c 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -33,6 +33,7 @@ config KVM select HAVE_KVM_NO_POLL select SRCU select KVM_VFIO + select INTERVAL_TREE help Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index b3aaadc60ead..26f4a74e5ce4 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -3,13 +3,11 @@ # # Copyright IBM Corp. 2008 -KVM := ../../../virt/kvm -common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o \ - $(KVM)/irqchip.o $(KVM)/vfio.o $(KVM)/binary_stats.o +include $(srctree)/virt/kvm/Makefile.kvm ccflags-y := -Ivirt/kvm -Iarch/s390/kvm -kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o -kvm-objs += diag.o gaccess.o guestdbg.o vsie.o pv.o +kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o +kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 6af59c59cc1b..4460808c3b9a 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -794,46 +794,100 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu, return 1; } -static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, - unsigned long *pages, unsigned long nr_pages, - const union asce asce, enum gacc_mode mode) +/** + * guest_range_to_gpas() - Calculate guest physical addresses of page fragments + * covering a logical range + * @vcpu: virtual cpu + * @ga: guest address, start of range + * @ar: access register + * @gpas: output argument, may be NULL + * @len: length of range in bytes + * @asce: address-space-control element to use for translation + * @mode: access mode + * + * Translate a logical range to a series of guest absolute addresses, + * such that the concatenation of page fragments starting at each gpa make up + * the whole range. + * The translation is performed as if done by the cpu for the given @asce, @ar, + * @mode and state of the @vcpu. + * If the translation causes an exception, its program interruption code is + * returned and the &struct kvm_s390_pgm_info pgm member of @vcpu is modified + * such that a subsequent call to kvm_s390_inject_prog_vcpu() will inject + * a correct exception into the guest. + * The resulting gpas are stored into @gpas, unless it is NULL. + * + * Note: All fragments except the first one start at the beginning of a page. + * When deriving the boundaries of a fragment from a gpa, all but the last + * fragment end at the end of the page. + * + * Return: + * * 0 - success + * * <0 - translation could not be performed, for example if guest + * memory could not be accessed + * * >0 - an access exception occurred. In this case the returned value + * is the program interruption code and the contents of pgm may + * be used to inject an exception into the guest. + */ +static int guest_range_to_gpas(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, + unsigned long *gpas, unsigned long len, + const union asce asce, enum gacc_mode mode) { psw_t *psw = &vcpu->arch.sie_block->gpsw; + unsigned int offset = offset_in_page(ga); + unsigned int fragment_len; int lap_enabled, rc = 0; enum prot_type prot; + unsigned long gpa; lap_enabled = low_address_protection_enabled(vcpu, asce); - while (nr_pages) { + while (min(PAGE_SIZE - offset, len) > 0) { + fragment_len = min(PAGE_SIZE - offset, len); ga = kvm_s390_logical_to_effective(vcpu, ga); if (mode == GACC_STORE && lap_enabled && is_low_address(ga)) return trans_exc(vcpu, PGM_PROTECTION, ga, ar, mode, PROT_TYPE_LA); - ga &= PAGE_MASK; if (psw_bits(*psw).dat) { - rc = guest_translate(vcpu, ga, pages, asce, mode, &prot); + rc = guest_translate(vcpu, ga, &gpa, asce, mode, &prot); if (rc < 0) return rc; } else { - *pages = kvm_s390_real_to_abs(vcpu, ga); - if (kvm_is_error_gpa(vcpu->kvm, *pages)) + gpa = kvm_s390_real_to_abs(vcpu, ga); + if (kvm_is_error_gpa(vcpu->kvm, gpa)) rc = PGM_ADDRESSING; } if (rc) return trans_exc(vcpu, rc, ga, ar, mode, prot); - ga += PAGE_SIZE; - pages++; - nr_pages--; + if (gpas) + *gpas++ = gpa; + offset = 0; + ga += fragment_len; + len -= fragment_len; } return 0; } +static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa, + void *data, unsigned int len) +{ + const unsigned int offset = offset_in_page(gpa); + const gfn_t gfn = gpa_to_gfn(gpa); + int rc; + + if (mode == GACC_STORE) + rc = kvm_write_guest_page(kvm, gfn, data, offset, len); + else + rc = kvm_read_guest_page(kvm, gfn, data, offset, len); + return rc; +} + int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data, unsigned long len, enum gacc_mode mode) { psw_t *psw = &vcpu->arch.sie_block->gpsw; - unsigned long _len, nr_pages, gpa, idx; - unsigned long pages_array[2]; - unsigned long *pages; + unsigned long nr_pages, idx; + unsigned long gpa_array[2]; + unsigned int fragment_len; + unsigned long *gpas; int need_ipte_lock; union asce asce; int rc; @@ -845,49 +899,42 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data, if (rc) return rc; nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1; - pages = pages_array; - if (nr_pages > ARRAY_SIZE(pages_array)) - pages = vmalloc(array_size(nr_pages, sizeof(unsigned long))); - if (!pages) + gpas = gpa_array; + if (nr_pages > ARRAY_SIZE(gpa_array)) + gpas = vmalloc(array_size(nr_pages, sizeof(unsigned long))); + if (!gpas) return -ENOMEM; need_ipte_lock = psw_bits(*psw).dat && !asce.r; if (need_ipte_lock) ipte_lock(vcpu); - rc = guest_page_range(vcpu, ga, ar, pages, nr_pages, asce, mode); + rc = guest_range_to_gpas(vcpu, ga, ar, gpas, len, asce, mode); for (idx = 0; idx < nr_pages && !rc; idx++) { - gpa = *(pages + idx) + (ga & ~PAGE_MASK); - _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); - if (mode == GACC_STORE) - rc = kvm_write_guest(vcpu->kvm, gpa, data, _len); - else - rc = kvm_read_guest(vcpu->kvm, gpa, data, _len); - len -= _len; - ga += _len; - data += _len; + fragment_len = min(PAGE_SIZE - offset_in_page(gpas[idx]), len); + rc = access_guest_page(vcpu->kvm, mode, gpas[idx], data, fragment_len); + len -= fragment_len; + data += fragment_len; } if (need_ipte_lock) ipte_unlock(vcpu); - if (nr_pages > ARRAY_SIZE(pages_array)) - vfree(pages); + if (nr_pages > ARRAY_SIZE(gpa_array)) + vfree(gpas); return rc; } int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, unsigned long len, enum gacc_mode mode) { - unsigned long _len, gpa; + unsigned int fragment_len; + unsigned long gpa; int rc = 0; while (len && !rc) { gpa = kvm_s390_real_to_abs(vcpu, gra); - _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); - if (mode) - rc = write_guest_abs(vcpu, gpa, data, _len); - else - rc = read_guest_abs(vcpu, gpa, data, _len); - len -= _len; - gra += _len; - data += _len; + fragment_len = min(PAGE_SIZE - offset_in_page(gpa), len); + rc = access_guest_page(vcpu->kvm, mode, gpa, data, fragment_len); + len -= fragment_len; + gra += fragment_len; + data += fragment_len; } return rc; } @@ -909,8 +956,6 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, unsigned long *gpa, enum gacc_mode mode) { - psw_t *psw = &vcpu->arch.sie_block->gpsw; - enum prot_type prot; union asce asce; int rc; @@ -918,23 +963,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, rc = get_vcpu_asce(vcpu, &asce, gva, ar, mode); if (rc) return rc; - if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) { - if (mode == GACC_STORE) - return trans_exc(vcpu, PGM_PROTECTION, gva, 0, - mode, PROT_TYPE_LA); - } - - if (psw_bits(*psw).dat && !asce.r) { /* Use DAT? */ - rc = guest_translate(vcpu, gva, gpa, asce, mode, &prot); - if (rc > 0) - return trans_exc(vcpu, rc, gva, 0, mode, prot); - } else { - *gpa = kvm_s390_real_to_abs(vcpu, gva); - if (kvm_is_error_gpa(vcpu->kvm, *gpa)) - return trans_exc(vcpu, rc, gva, PGM_ADDRESSING, mode, 0); - } - - return rc; + return guest_range_to_gpas(vcpu, gva, ar, gpa, 1, asce, mode); } /** @@ -948,17 +977,14 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar, unsigned long length, enum gacc_mode mode) { - unsigned long gpa; - unsigned long currlen; + union asce asce; int rc = 0; + rc = get_vcpu_asce(vcpu, &asce, gva, ar, mode); + if (rc) + return rc; ipte_lock(vcpu); - while (length > 0 && !rc) { - currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE)); - rc = guest_translate_address(vcpu, gva, ar, &gpa, mode); - gva += currlen; - length -= currlen; - } + rc = guest_range_to_gpas(vcpu, gva, ar, NULL, length, asce, mode); ipte_unlock(vcpu); return rc; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c3bd993fdd0c..db933c252dbc 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1335,7 +1335,8 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime); no_timer: srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); + vcpu->valid_wakeup = false; __unset_cpu_idle(vcpu); vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); @@ -2115,6 +2116,13 @@ int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu) return test_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); } +int kvm_s390_is_restart_irq_pending(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + return test_bit(IRQ_PEND_RESTART, &li->pending_irqs); +} + void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -2659,7 +2667,7 @@ static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr) static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r = 0; - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; switch (attr->group) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 14a18ba5ff2c..9c6d45d0d345 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -295,7 +295,7 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val, { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; unsigned long long *delta = v; list_for_each_entry(kvm, &vm_list, vm_list) { @@ -682,7 +682,7 @@ out: static void icpt_operexc_on_all_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -936,7 +936,7 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_s390_vcpu_block_all(kvm); @@ -1021,7 +1021,7 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr) static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) { - int cx; + unsigned long cx; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(cx, vcpu, kvm) @@ -1037,13 +1037,13 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) struct kvm_memory_slot *ms; struct kvm_memslots *slots; unsigned long ram_pages = 0; - int slotnr; + int bkt; /* migration mode already enabled */ if (kvm->arch.migration_mode) return 0; slots = kvm_memslots(kvm); - if (!slots || !slots->used_slots) + if (!slots || kvm_memslots_empty(slots)) return -EINVAL; if (!kvm->arch.use_cmma) { @@ -1051,8 +1051,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) return 0; } /* mark all the pages in active slots as dirty */ - for (slotnr = 0; slotnr < slots->used_slots; slotnr++) { - ms = slots->memslots + slotnr; + kvm_for_each_memslot(ms, bkt, slots) { if (!ms->dirty_bitmap) return -EINVAL; /* @@ -1943,41 +1942,6 @@ out: /* for consistency */ #define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX) -/* - * Similar to gfn_to_memslot, but returns the index of a memslot also when the - * address falls in a hole. In that case the index of one of the memslots - * bordering the hole is returned. - */ -static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn) -{ - int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->last_used_slot); - struct kvm_memory_slot *memslots = slots->memslots; - - if (gfn >= memslots[slot].base_gfn && - gfn < memslots[slot].base_gfn + memslots[slot].npages) - return slot; - - while (start < end) { - slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - if (start >= slots->used_slots) - return slots->used_slots - 1; - - if (gfn >= memslots[start].base_gfn && - gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->last_used_slot, start); - } - - return start; -} - static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, u8 *res, unsigned long bufsize) { @@ -2001,26 +1965,31 @@ static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, return 0; } +static struct kvm_memory_slot *gfn_to_memslot_approx(struct kvm_memslots *slots, + gfn_t gfn) +{ + return ____gfn_to_memslot(slots, gfn, true); +} + static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots, unsigned long cur_gfn) { - int slotidx = gfn_to_memslot_approx(slots, cur_gfn); - struct kvm_memory_slot *ms = slots->memslots + slotidx; + struct kvm_memory_slot *ms = gfn_to_memslot_approx(slots, cur_gfn); unsigned long ofs = cur_gfn - ms->base_gfn; + struct rb_node *mnode = &ms->gfn_node[slots->node_idx]; if (ms->base_gfn + ms->npages <= cur_gfn) { - slotidx--; + mnode = rb_next(mnode); /* If we are above the highest slot, wrap around */ - if (slotidx < 0) - slotidx = slots->used_slots - 1; + if (!mnode) + mnode = rb_first(&slots->gfn_tree); - ms = slots->memslots + slotidx; + ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]); ofs = 0; } ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs); - while ((slotidx > 0) && (ofs >= ms->npages)) { - slotidx--; - ms = slots->memslots + slotidx; + while (ofs >= ms->npages && (mnode = rb_next(mnode))) { + ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]); ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0); } return ms->base_gfn + ofs; @@ -2033,7 +2002,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *ms; - if (unlikely(!slots->used_slots)) + if (unlikely(kvm_memslots_empty(slots))) return 0; cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn); @@ -2043,7 +2012,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, if (!ms) return 0; next_gfn = kvm_s390_next_dirty_cmma(slots, cur_gfn + 1); - mem_end = slots->memslots[0].base_gfn + slots->memslots[0].npages; + mem_end = kvm_s390_get_gfn_end(slots); while (args->count < bufsize) { hva = gfn_to_hva(kvm, cur_gfn); @@ -2206,7 +2175,7 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) struct kvm_vcpu *vcpu; u16 rc, rrc; int ret = 0; - int i; + unsigned long i; /* * We ignore failures and try to destroy as many CPUs as possible. @@ -2230,7 +2199,8 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc) { - int i, r = 0; + unsigned long i; + int r = 0; u16 dummy; struct kvm_vcpu *vcpu; @@ -2821,27 +2791,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)(vcpu->arch.sie_block)); } -static void kvm_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); - - mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - mutex_unlock(&kvm->lock); -} - void kvm_arch_destroy_vm(struct kvm *kvm) { u16 rc, rrc; - kvm_free_vcpus(kvm); + kvm_destroy_vcpus(kvm); sca_dispose(kvm); kvm_s390_gisa_destroy(kvm); /* @@ -2945,7 +2899,7 @@ static int sca_switch_to_extended(struct kvm *kvm) struct bsca_block *old_sca = kvm->arch.sca; struct esca_block *new_sca; struct kvm_vcpu *vcpu; - unsigned int vcpu_idx; + unsigned long vcpu_idx; u32 scaol, scaoh; if (kvm->arch.use_esca) @@ -3427,7 +3381,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, struct kvm *kvm = gmap->private; struct kvm_vcpu *vcpu; unsigned long prefix; - int i; + unsigned long i; if (gmap_is_shadow(gmap)) return; @@ -3449,7 +3403,7 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { /* do not poll with more than halt_poll_max_steal percent of steal time */ if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >= - halt_poll_max_steal) { + READ_ONCE(halt_poll_max_steal)) { vcpu->stat.halt_no_poll_steal++; return true; } @@ -3920,7 +3874,7 @@ void kvm_s390_set_tod_clock(struct kvm *kvm, { struct kvm_vcpu *vcpu; union tod_clock clk; - int i; + unsigned long i; mutex_lock(&kvm->lock); preempt_disable(); @@ -4552,7 +4506,7 @@ static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) static void __disable_ibs_on_all_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -4590,7 +4544,7 @@ int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) } for (i = 0; i < online_vcpus; i++) { - if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) + if (!is_vcpu_stopped(kvm_get_vcpu(vcpu->kvm, i))) started_vcpus++; } @@ -4645,16 +4599,23 @@ int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) } } - /* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */ + /* + * Set the VCPU to STOPPED and THEN clear the interrupt flag, + * now that the SIGP STOP and SIGP STOP AND STORE STATUS orders + * have been fully processed. This will ensure that the VCPU + * is kept BUSY if another VCPU is inquiring with SIGP SENSE. + */ + kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED); kvm_s390_clear_stop_irq(vcpu); - kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED); __disable_ibs_on_vcpu(vcpu); for (i = 0; i < online_vcpus; i++) { - if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) { + struct kvm_vcpu *tmp = kvm_get_vcpu(vcpu->kvm, i); + + if (!is_vcpu_stopped(tmp)) { started_vcpus++; - started_vcpu = vcpu->kvm->vcpus[i]; + started_vcpu = tmp; } } @@ -5020,32 +4981,38 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { + gpa_t size; + + /* When we are protected, we should not change the memory slots */ + if (kvm_s390_pv_get_handle(kvm)) + return -EINVAL; + + if (change == KVM_MR_DELETE || change == KVM_MR_FLAGS_ONLY) + return 0; + /* A few sanity checks. We can have memory slots which have to be located/ended at a segment boundary (1MB). The memory in userland is ok to be fragmented into various different vmas. It is okay to mmap() and munmap() stuff in this slot after doing this call at any time */ - if (mem->userspace_addr & 0xffffful) + if (new->userspace_addr & 0xffffful) return -EINVAL; - if (mem->memory_size & 0xffffful) + size = new->npages * PAGE_SIZE; + if (size & 0xffffful) return -EINVAL; - if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit) + if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit) return -EINVAL; - /* When we are protected, we should not change the memory slots */ - if (kvm_s390_pv_get_handle(kvm)) - return -EINVAL; return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -5064,8 +5031,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, break; fallthrough; case KVM_MR_CREATE: - rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, - mem->guest_phys_addr, mem->memory_size); + rc = gmap_map_segment(kvm->arch.gmap, new->userspace_addr, + new->base_gfn * PAGE_SIZE, + new->npages * PAGE_SIZE); break; case KVM_MR_FLAGS_ONLY: break; @@ -5084,11 +5052,6 @@ static inline unsigned long nonhyp_mask(int i) return 0x0000ffffffffffffUL >> (nonhyp_fai << 4); } -void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) -{ - vcpu->valid_wakeup = false; -} - static int __init kvm_s390_init(void) { int i; diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index c07a050d757d..098831e815e6 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -217,6 +217,20 @@ static inline void kvm_s390_set_user_cpu_state_ctrl(struct kvm *kvm) kvm->arch.user_cpu_state_ctrl = 1; } +/* get the end gfn of the last (highest gfn) memslot */ +static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots) +{ + struct rb_node *node; + struct kvm_memory_slot *ms; + + if (WARN_ON(kvm_memslots_empty(slots))) + return 0; + + node = rb_last(&slots->gfn_tree); + ms = container_of(node, struct kvm_memory_slot, gfn_node[slots->node_idx]); + return ms->base_gfn + ms->npages; +} + /* implemented in pv.c */ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); @@ -357,7 +371,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); static inline void kvm_s390_vcpu_block_all(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; WARN_ON(!mutex_is_locked(&kvm->lock)); @@ -367,7 +381,7 @@ static inline void kvm_s390_vcpu_block_all(struct kvm *kvm) static inline void kvm_s390_vcpu_unblock_all(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) @@ -427,6 +441,7 @@ void kvm_s390_destroy_adapters(struct kvm *kvm); int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu); extern struct kvm_device_ops kvm_flic_ops; int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu); +int kvm_s390_is_restart_irq_pending(struct kvm_vcpu *vcpu); void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu); int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *buf, int len); diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 00d272d134c2..7f7c0d6af2ce 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -116,7 +116,6 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) unsigned long base = uv_info.guest_base_stor_len; unsigned long virt = uv_info.guest_virt_var_stor_len; unsigned long npages = 0, vlen = 0; - struct kvm_memory_slot *memslot; kvm->arch.pv.stor_var = NULL; kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL_ACCOUNT, get_order(base)); @@ -130,8 +129,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) * Slots are sorted by GFN */ mutex_lock(&kvm->slots_lock); - memslot = kvm_memslots(kvm)->memslots; - npages = memslot->base_gfn + memslot->npages; + npages = kvm_s390_get_gfn_end(kvm_memslots(kvm)); mutex_unlock(&kvm->slots_lock); kvm->arch.pv.guest_len = npages * PAGE_SIZE; diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index cf4de80bd541..8aaee2892ec3 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -276,6 +276,34 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code, if (!dst_vcpu) return SIGP_CC_NOT_OPERATIONAL; + /* + * SIGP RESTART, SIGP STOP, and SIGP STOP AND STORE STATUS orders + * are processed asynchronously. Until the affected VCPU finishes + * its work and calls back into KVM to clear the (RESTART or STOP) + * interrupt, we need to return any new non-reset orders "busy". + * + * This is important because a single VCPU could issue: + * 1) SIGP STOP $DESTINATION + * 2) SIGP SENSE $DESTINATION + * + * If the SIGP SENSE would not be rejected as "busy", it could + * return an incorrect answer as to whether the VCPU is STOPPED + * or OPERATING. + */ + if (order_code != SIGP_INITIAL_CPU_RESET && + order_code != SIGP_CPU_RESET) { + /* + * Lockless check. Both SIGP STOP and SIGP (RE)START + * properly synchronize everything while processing + * their orders, while the guest cannot observe a + * difference when issuing other orders from two + * different VCPUs. + */ + if (kvm_s390_is_stop_irq_pending(dst_vcpu) || + kvm_s390_is_restart_irq_pending(dst_vcpu)) + return SIGP_CC_BUSY; + } + switch (order_code) { case SIGP_SENSE: vcpu->stat.instruction_sigp_sense++; diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index cfc5f5557c06..bc7973359ae2 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -173,10 +173,11 @@ static noinline int unwindme_func4(struct unwindme *u) } /* - * trigger specification exception + * Trigger operation exception; use insn notation to bypass + * llvm's integrated assembler sanity checks. */ asm volatile( - " mvcl %%r1,%%r1\n" + " .insn e,0x0000\n" /* illegal opcode */ "0: nopr %%r7\n" EX_TABLE(0b, 0b) :); diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index e38a4cf795d9..97b1f84bb53f 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -574,6 +574,10 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) ud2 1: #endif +#ifdef CONFIG_XEN_PV + ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV +#endif + POP_REGS pop_rdi=0 /* @@ -890,6 +894,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) .Lparanoid_entry_checkgs: /* EBX = 1 -> kernel GSBASE active, no restore required */ movl $1, %ebx + /* * The kernel-enforced convention is a negative GSBASE indicates * a kernel value. No SWAPGS needed on entry and exit. @@ -897,21 +902,14 @@ SYM_CODE_START_LOCAL(paranoid_entry) movl $MSR_GS_BASE, %ecx rdmsr testl %edx, %edx - jns .Lparanoid_entry_swapgs - ret + js .Lparanoid_kernel_gsbase -.Lparanoid_entry_swapgs: + /* EBX = 0 -> SWAPGS required on exit */ + xorl %ebx, %ebx swapgs +.Lparanoid_kernel_gsbase: - /* - * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an - * unconditional CR3 write, even in the PTI case. So do an lfence - * to prevent GS speculation, regardless of whether PTI is enabled. - */ FENCE_SWAPGS_KERNEL_ENTRY - - /* EBX = 0 -> SWAPGS required on exit */ - xorl %ebx, %ebx ret SYM_CODE_END(paranoid_entry) @@ -993,11 +991,6 @@ SYM_CODE_START_LOCAL(error_entry) pushq %r12 ret -.Lerror_entry_done_lfence: - FENCE_SWAPGS_KERNEL_ENTRY -.Lerror_entry_done: - ret - /* * There are two places in the kernel that can potentially fault with * usergs. Handle them here. B stepping K8s sometimes report a @@ -1020,8 +1013,14 @@ SYM_CODE_START_LOCAL(error_entry) * .Lgs_change's error handler with kernel gsbase. */ SWAPGS - FENCE_SWAPGS_USER_ENTRY - jmp .Lerror_entry_done + + /* + * Issue an LFENCE to prevent GS speculation, regardless of whether it is a + * kernel or user gsbase. + */ +.Lerror_entry_done_lfence: + FENCE_SWAPGS_KERNEL_ENTRY + ret .Lbstep_iret: /* Fix truncated RIP */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5a0bcf8b78d7..048b6d5aff50 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -108,7 +108,7 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ -#define INTEL_FAM6_RAPTOR_LAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE 0xB7 /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index cefe1d81e2e8..9e50da3ed01a 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -47,6 +47,7 @@ KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) KVM_X86_OP(set_rflags) +KVM_X86_OP(get_if_flag) KVM_X86_OP(tlb_flush_all) KVM_X86_OP(tlb_flush_current) KVM_X86_OP_NULL(tlb_remote_flush) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6ac61f85e07b..344ced0b6b68 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -97,7 +97,7 @@ KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) #define KVM_REQ_TLB_FLUSH_GUEST \ - KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP) + KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29) #define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \ @@ -135,7 +135,7 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) -#define KVM_PERMILLE_MMU_PAGES 20 +#define KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO 50 #define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) @@ -291,25 +291,31 @@ struct kvm_kernel_irq_routing_entry; * the number of unique SPs that can theoretically be created is 2^n, where n * is the number of bits that are used to compute the role. * - * But, even though there are 18 bits in the mask below, not all combinations - * of modes and flags are possible. The maximum number of possible upper-level - * shadow pages for a single gfn is in the neighborhood of 2^13. + * But, even though there are 19 bits in the mask below, not all combinations + * of modes and flags are possible: * - * - invalid shadow pages are not accounted. - * - level is effectively limited to four combinations, not 16 as the number - * bits would imply, as 4k SPs are not tracked (allowed to go unsync). - * - level is effectively unused for non-PAE paging because there is exactly - * one upper level (see 4k SP exception above). - * - quadrant is used only for non-PAE paging and is exclusive with - * gpte_is_8_bytes. - * - execonly and ad_disabled are used only for nested EPT, which makes it - * exclusive with quadrant. + * - invalid shadow pages are not accounted, so the bits are effectively 18 + * + * - quadrant will only be used if has_4_byte_gpte=1 (non-PAE paging); + * execonly and ad_disabled are only used for nested EPT which has + * has_4_byte_gpte=0. Therefore, 2 bits are always unused. + * + * - the 4 bits of level are effectively limited to the values 2/3/4/5, + * as 4k SPs are not tracked (allowed to go unsync). In addition non-PAE + * paging has exactly one upper level, making level completely redundant + * when has_4_byte_gpte=1. + * + * - on top of this, smep_andnot_wp and smap_andnot_wp are only set if + * cr0_wp=0, therefore these three bits only give rise to 5 possibilities. + * + * Therefore, the maximum number of possible upper-level shadow pages for a + * single gfn is a bit less than 2^13. */ union kvm_mmu_page_role { u32 word; struct { unsigned level:4; - unsigned gpte_is_8_bytes:1; + unsigned has_4_byte_gpte:1; unsigned quadrant:2; unsigned direct:1; unsigned access:3; @@ -420,10 +426,9 @@ struct kvm_mmu { int (*page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); - gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa, - u32 access, struct x86_exception *exception); - gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception); + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t gva_or_gpa, u32 access, + struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa); @@ -1036,6 +1041,7 @@ struct kvm_x86_msr_filter { #define APICV_INHIBIT_REASON_PIT_REINJ 4 #define APICV_INHIBIT_REASON_X2APIC 5 #define APICV_INHIBIT_REASON_BLOCKIRQ 6 +#define APICV_INHIBIT_REASON_ABSENT 7 struct kvm_arch { unsigned long n_used_mmu_pages; @@ -1348,6 +1354,7 @@ struct kvm_x86_ops { void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); + bool (*get_if_flag)(struct kvm_vcpu *vcpu); void (*tlb_flush_all)(struct kvm_vcpu *vcpu); void (*tlb_flush_current)(struct kvm_vcpu *vcpu); @@ -1585,10 +1592,9 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_zap_all(struct kvm *kvm); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); -unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); -int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); @@ -1638,7 +1644,8 @@ extern u64 kvm_mce_cap_supported; * * EMULTYPE_SKIP - Set when emulating solely to skip an instruction, i.e. to * decode the instruction length. For use *only* by - * kvm_x86_ops.skip_emulated_instruction() implementations. + * kvm_x86_ops.skip_emulated_instruction() implementations if + * EMULTYPE_COMPLETE_USER_EXIT is not set. * * EMULTYPE_ALLOW_RETRY_PF - Set when the emulator should resume the guest to * retry native execution under certain conditions, @@ -1658,6 +1665,10 @@ extern u64 kvm_mce_cap_supported; * * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which * case the CR2/GPA value pass on the stack is valid. + * + * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility + * state and inject single-step #DBs after skipping + * an instruction (after completing userspace I/O). */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) @@ -1666,6 +1677,7 @@ extern u64 kvm_mce_cap_supported; #define EMULTYPE_TRAP_UD_FORCED (1 << 4) #define EMULTYPE_VMWARE_GP (1 << 5) #define EMULTYPE_PF (1 << 6) +#define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, @@ -1690,7 +1702,7 @@ int kvm_emulate_monitor(struct kvm_vcpu *vcpu); int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); -int kvm_vcpu_halt(struct kvm_vcpu *vcpu); +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu); int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); @@ -1756,12 +1768,9 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); -void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, ulong roots_to_free); void kvm_mmu_free_guest_mode_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu); -gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, @@ -1925,8 +1934,6 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) static_call_cond(kvm_x86_vcpu_unblocking)(vcpu); } -static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} - static inline int kvm_cpu_get_apicid(int mps_cpu) { #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 9d4a3b1b25b9..eb186bc57f6a 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -63,9 +63,9 @@ void kvm_slot_page_track_add_page(struct kvm *kvm, void kvm_slot_page_track_remove_page(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, enum kvm_page_track_mode mode); -bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode); +bool kvm_slot_page_track_is_active(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, enum kvm_page_track_mode mode); void kvm_page_track_register_notifier(struct kvm *kvm, diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 2cef6c5a52c2..6acaf5af0a3d 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -73,4 +73,15 @@ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) +/* + * Error codes related to GHCB input that can be communicated back to the guest + * by setting the lower 32-bits of the GHCB SW_EXITINFO1 field to 2. + */ +#define GHCB_ERR_NOT_REGISTERED 1 +#define GHCB_ERR_INVALID_USAGE 2 +#define GHCB_ERR_INVALID_SCRATCH_AREA 3 +#define GHCB_ERR_MISSING_INPUT 4 +#define GHCB_ERR_INVALID_INPUT 5 +#define GHCB_ERR_INVALID_EVENT 6 + #endif diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index d5958278eba6..91d4b6de58ab 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -118,7 +118,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, struct fpstate *fpstate) { struct xregs_state __user *x = buf; - struct _fpx_sw_bytes sw_bytes; + struct _fpx_sw_bytes sw_bytes = {}; u32 xfeatures; int err; diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 74f0ec955384..a9fc2ac7a8bd 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -294,11 +294,6 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, char *dst, char *buf, size_t size) { unsigned long error_code = X86_PF_PROT | X86_PF_WRITE; - char __user *target = (char __user *)dst; - u64 d8; - u32 d4; - u16 d2; - u8 d1; /* * This function uses __put_user() independent of whether kernel or user @@ -320,26 +315,42 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, * instructions here would cause infinite nesting. */ switch (size) { - case 1: + case 1: { + u8 d1; + u8 __user *target = (u8 __user *)dst; + memcpy(&d1, buf, 1); if (__put_user(d1, target)) goto fault; break; - case 2: + } + case 2: { + u16 d2; + u16 __user *target = (u16 __user *)dst; + memcpy(&d2, buf, 2); if (__put_user(d2, target)) goto fault; break; - case 4: + } + case 4: { + u32 d4; + u32 __user *target = (u32 __user *)dst; + memcpy(&d4, buf, 4); if (__put_user(d4, target)) goto fault; break; - case 8: + } + case 8: { + u64 d8; + u64 __user *target = (u64 __user *)dst; + memcpy(&d8, buf, 8); if (__put_user(d8, target)) goto fault; break; + } default: WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); return ES_UNSUPPORTED; @@ -362,11 +373,6 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, char *src, char *buf, size_t size) { unsigned long error_code = X86_PF_PROT; - char __user *s = (char __user *)src; - u64 d8; - u32 d4; - u16 d2; - u8 d1; /* * This function uses __get_user() independent of whether kernel or user @@ -388,26 +394,41 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, * instructions here would cause infinite nesting. */ switch (size) { - case 1: + case 1: { + u8 d1; + u8 __user *s = (u8 __user *)src; + if (__get_user(d1, s)) goto fault; memcpy(buf, &d1, 1); break; - case 2: + } + case 2: { + u16 d2; + u16 __user *s = (u16 __user *)src; + if (__get_user(d2, s)) goto fault; memcpy(buf, &d2, 2); break; - case 4: + } + case 4: { + u32 d4; + u32 __user *s = (u32 __user *)src; + if (__get_user(d4, s)) goto fault; memcpy(buf, &d4, 4); break; - case 8: + } + case 8: { + u64 d8; + u64 __user *s = (u64 __user *)src; if (__get_user(d8, s)) goto fault; memcpy(buf, &d8, 8); break; + } default: WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); return ES_UNSUPPORTED; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 2e076a459a0c..a698196377be 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1180,6 +1180,12 @@ void mark_tsc_unstable(char *reason) EXPORT_SYMBOL_GPL(mark_tsc_unstable); +static void __init tsc_disable_clocksource_watchdog(void) +{ + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; +} + static void __init check_system_tsc_reliable(void) { #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) @@ -1196,6 +1202,23 @@ static void __init check_system_tsc_reliable(void) #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; + + /* + * Disable the clocksource watchdog when the system has: + * - TSC running at constant frequency + * - TSC which does not stop in C-States + * - the TSC_ADJUST register which allows to detect even minimal + * modifications + * - not more than two sockets. As the number of sockets cannot be + * evaluated at the early boot stage where this has to be + * invoked, check the number of online memory nodes as a + * fallback solution which is an reasonable estimate. + */ + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && + boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && + boot_cpu_has(X86_FEATURE_TSC_ADJUST) && + nr_online_nodes <= 2) + tsc_disable_clocksource_watchdog(); } /* @@ -1387,9 +1410,6 @@ static int __init init_tsc_clocksource(void) if (tsc_unstable) goto unreg; - if (tsc_clocksource_reliable || no_tsc_watchdog) - clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; - if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; @@ -1527,7 +1547,7 @@ void __init tsc_init(void) } if (tsc_clocksource_reliable || no_tsc_watchdog) - clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + tsc_disable_clocksource_watchdog(); clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 50a4515fe0ad..9452dc9664b5 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -30,6 +30,7 @@ struct tsc_adjust { }; static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust); +static struct timer_list tsc_sync_check_timer; /* * TSC's on different sockets may be reset asynchronously. @@ -77,6 +78,46 @@ void tsc_verify_tsc_adjust(bool resume) } } +/* + * Normally the tsc_sync will be checked every time system enters idle + * state, but there is still caveat that a system won't enter idle, + * either because it's too busy or configured purposely to not enter + * idle. + * + * So setup a periodic timer (every 10 minutes) to make sure the check + * is always on. + */ + +#define SYNC_CHECK_INTERVAL (HZ * 600) + +static void tsc_sync_check_timer_fn(struct timer_list *unused) +{ + int next_cpu; + + tsc_verify_tsc_adjust(false); + + /* Run the check for all onlined CPUs in turn */ + next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); + if (next_cpu >= nr_cpu_ids) + next_cpu = cpumask_first(cpu_online_mask); + + tsc_sync_check_timer.expires += SYNC_CHECK_INTERVAL; + add_timer_on(&tsc_sync_check_timer, next_cpu); +} + +static int __init start_sync_check_timer(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_TSC_ADJUST) || tsc_clocksource_reliable) + return 0; + + timer_setup(&tsc_sync_check_timer, tsc_sync_check_timer_fn, 0); + tsc_sync_check_timer.expires = jiffies + SYNC_CHECK_INTERVAL; + add_timer(&tsc_sync_check_timer); + + return 0; +} +late_initcall(start_sync_check_timer); + static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval, unsigned int cpu, bool bootcpu) { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 619186138176..03b2ce34e7f4 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -27,6 +27,7 @@ config KVM select MMU_NOTIFIER select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD + select HAVE_KVM_DIRTY_RING select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING @@ -43,6 +44,7 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO select SRCU + select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM help Support hosting fully virtualized guest machines using hardware diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 75dfd27b6e8a..30f244b64523 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -7,12 +7,7 @@ ifeq ($(CONFIG_FRAME_POINTER),y) OBJECT_FILES_NON_STANDARD_vmenter.o := y endif -KVM := ../../../virt/kvm - -kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ - $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \ - $(KVM)/dirty_ring.o $(KVM)/binary_stats.o -kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o +include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 07e9215e911d..0b920e12bb6d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -523,7 +523,7 @@ void kvm_set_cpu_caps(void) F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | - F(TOPOEXT) | F(PERFCTR_CORE) + F(TOPOEXT) | 0 /* PERFCTR_CORE */ ); kvm_cpu_cap_mask(CPUID_8000_0001_EDX, diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 54a83a744538..543a8c04025c 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -107,9 +107,10 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + int bkt; + slots = __kvm_memslots(kvm, i); - for (j = 0; j < slots->used_slots; j++) { - slot = &slots->memslots[j]; + kvm_for_each_memslot(slot, bkt, slots) for (k = 0; k < KVM_NR_PAGE_SIZES; k++) { rmap = slot->arch.rmap[k]; lpage_size = kvm_mmu_slot_lpages(slot, k + 1); @@ -121,7 +122,6 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) cur[index]++; } } - } } write_unlock(&kvm->mmu_lock); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 5e19e6e4c2ce..6e38a7d22e97 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -164,7 +164,7 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (vpidx >= KVM_MAX_VCPUS) return NULL; @@ -1716,7 +1716,8 @@ static __always_inline unsigned long *sparse_set_to_vcpu_mask( { struct kvm_hv *hv = to_kvm_hv(kvm); struct kvm_vcpu *vcpu; - int i, bank, sbank = 0; + int bank, sbank = 0; + unsigned long i; memset(vp_bitmap, 0, KVM_HV_MAX_SPARSE_VCPU_SET_BITS * sizeof(*vp_bitmap)); @@ -1863,7 +1864,7 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, .vector = vector }; struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu_bitmap && !test_bit(i, vcpu_bitmap)) @@ -1922,11 +1923,13 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; + if (all_cpus) + goto check_and_send_ipi; + if (!sparse_banks_len) goto ret_success; - if (!all_cpus && - kvm_read_guest(kvm, + if (kvm_read_guest(kvm, hc->ingpa + offsetof(struct hv_send_ipi_ex, vp_set.bank_contents), sparse_banks, @@ -1934,6 +1937,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool return HV_STATUS_INVALID_HYPERCALL_INPUT; } +check_and_send_ipi: if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) return HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -2516,6 +2520,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, case HYPERV_CPUID_NESTED_FEATURES: ent->eax = evmcs_ver; + if (evmcs_ver) + ent->eax |= HV_X64_NESTED_MSR_BITMAP; break; diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 5a69cce4d72d..0b65a764ed3a 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -242,7 +242,7 @@ static void pit_do_work(struct kthread_work *work) struct kvm_pit *pit = container_of(work, struct kvm_pit, expired); struct kvm *kvm = pit->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; struct kvm_kpit_state *ps = &pit->pit_state; if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0)) diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 0b80263d46d8..814064d06016 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -50,7 +50,7 @@ static void pic_unlock(struct kvm_pic *s) { bool wakeup = s->wakeup_needed; struct kvm_vcpu *vcpu; - int i; + unsigned long i; s->wakeup_needed = false; @@ -270,7 +270,8 @@ int kvm_pic_read_irq(struct kvm *kvm) static void kvm_pic_reset(struct kvm_kpic_state *s) { - int irq, i; + int irq; + unsigned long i; struct kvm_vcpu *vcpu; u8 edge_irr = s->irr & ~s->elcr; bool found = false; diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 816a82515dcd..decfa36b7891 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -149,7 +149,7 @@ void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; if (RTC_GSI >= IOAPIC_NUM_PINS) return; @@ -184,7 +184,7 @@ static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic) static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index e66e620c3bed..539333ac4b38 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -81,7 +81,6 @@ struct kvm_ioapic { unsigned long irq_states[IOAPIC_NUM_PINS]; struct kvm_io_device dev; struct kvm *kvm; - void (*ack_notifier)(void *opaque, int irq); spinlock_t lock; struct rtc_status rtc_status; struct delayed_work eoi_inject; diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 650642b18d15..c2d7cfe82d00 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -56,7 +56,6 @@ struct kvm_pic { struct kvm_io_device dev_master; struct kvm_io_device dev_slave; struct kvm_io_device dev_elcr; - void (*ack_notifier)(void *opaque, int irq); unsigned long irq_states[PIC_NUM_PINS]; }; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index d5b72a08e566..39ad02d6dc63 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -45,9 +45,9 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, struct dest_map *dest_map) { - int i, r = -1; + int r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; - unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + unsigned long i, dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; unsigned int dest_vcpus = 0; if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) @@ -320,7 +320,8 @@ int kvm_set_routing_entry(struct kvm *kvm, bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu) { - int i, r = 0; + int r = 0; + unsigned long i; struct kvm_vcpu *vcpu; if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu)) diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 90e1ffdc05b7..3febc342360c 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -9,6 +9,12 @@ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) +#define X86_CR0_PDPTR_BITS (X86_CR0_CD | X86_CR0_NW | X86_CR0_PG) +#define X86_CR4_TLBFLUSH_BITS (X86_CR4_PGE | X86_CR4_PCIDE | X86_CR4_PAE | X86_CR4_SMEP) +#define X86_CR4_PDPTR_BITS (X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP) + +static_assert(!(KVM_POSSIBLE_CR0_GUEST_BITS & X86_CR0_PDPTR_BITS)); + #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ { \ @@ -37,6 +43,13 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif +/* + * avail dirty + * 0 0 register in VMCS/VMCB + * 0 1 *INVALID* + * 1 0 register in vcpu->arch + * 1 1 register in vcpu->arch, needs to be stored back + */ static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, enum kvm_reg reg) { @@ -55,13 +68,6 @@ static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); } -static inline void kvm_register_clear_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); - __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, enum kvm_reg reg) { diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index c7db2df50a7a..b469f45e3fe4 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -33,7 +33,8 @@ int hv_remote_flush_tlb_with_range(struct kvm *kvm, { struct kvm_arch *kvm_arch = &kvm->arch; struct kvm_vcpu *vcpu; - int ret = 0, i, nr_unique_valid_roots; + int ret = 0, nr_unique_valid_roots; + unsigned long i; hpa_t root; spin_lock(&kvm_arch->hv_root_tdp_lock); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 759952dd1222..c5028e6b0f96 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -185,7 +185,7 @@ void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; - int i; + unsigned long i; u32 max_id = 255; /* enough space for any xAPIC ID */ /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ @@ -673,41 +673,40 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED; } -static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) -{ - u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) { - printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); - return false; - } - return val & KVM_PV_EOI_ENABLED; -} - static void pv_eoi_set_pending(struct kvm_vcpu *vcpu) { - if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) { - printk(KERN_WARNING "Can't set EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); + if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) return; - } + __set_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) +static bool pv_eoi_test_and_clr_pending(struct kvm_vcpu *vcpu) { - if (pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) { - printk(KERN_WARNING "Can't clear EOI MSR value: 0x%llx\n", - (unsigned long long)vcpu->arch.pv_eoi.msr_val); - return; - } + u8 val; + + if (pv_eoi_get_user(vcpu, &val) < 0) + return false; + + val &= KVM_PV_EOI_ENABLED; + + if (val && pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) + return false; + + /* + * Clear pending bit in any case: it will be set again on vmentry. + * While this might not be ideal from performance point of view, + * this makes sure pv eoi is only enabled when we know it's safe. + */ __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); + + return val; } static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) { int highest_irr; - if (apic->vcpu->arch.apicv_active) + if (kvm_x86_ops.sync_pir_to_irr) highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu); else highest_irr = apic_find_highest_irr(apic); @@ -1101,6 +1100,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, kvm_lapic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); + } else { + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector); } break; @@ -1172,8 +1174,8 @@ void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_lapic *src = NULL; struct kvm_apic_map *map; struct kvm_vcpu *vcpu; - unsigned long bitmap; - int i, vcpu_idx; + unsigned long bitmap, i; + int vcpu_idx; bool ret; rcu_read_lock(); @@ -1931,7 +1933,7 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) /* If the preempt notifier has already run, it also called apic_timer_expired */ if (!apic->lapic_timer.hv_timer_in_use) goto out; - WARN_ON(rcuwait_active(&vcpu->wait)); + WARN_ON(kvm_vcpu_is_blocking(vcpu)); apic_timer_expired(apic, false); cancel_hv_timer(apic); @@ -2677,7 +2679,6 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, struct kvm_lapic *apic) { - bool pending; int vector; /* * PV EOI state is derived from KVM_APIC_PV_EOI_PENDING in host @@ -2691,14 +2692,8 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, * -> host enabled PV EOI, guest executed EOI. */ BUG_ON(!pv_eoi_enabled(vcpu)); - pending = pv_eoi_get_pending(vcpu); - /* - * Clear pending bit in any case: it will be set again on vmentry. - * While this might not be ideal from performance point of view, - * this makes sure pv eoi is only enabled when we know it's safe. - */ - pv_eoi_clr_pending(vcpu); - if (pending) + + if (pv_eoi_test_and_clr_pending(vcpu)) return; vector = apic_set_eoi(apic); trace_kvm_pv_eoi(apic, vector); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 9ae6168d381e..e9fbb2c8bbe2 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -71,7 +71,8 @@ void kvm_init_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, unsigned long cr4, u64 efer, gpa_t nested_cr3); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, - bool accessed_dirty, gpa_t new_eptp); + int huge_page_level, bool accessed_dirty, + gpa_t new_eptp); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); @@ -351,4 +352,17 @@ static inline void kvm_update_page_stats(struct kvm *kvm, int level, int count) { atomic64_add(count, &kvm->stat.pages[level - 1]); } + +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, + struct x86_exception *exception); + +static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu, + gpa_t gpa, u32 access, + struct x86_exception *exception) +{ + if (mmu != &vcpu->arch.nested_mmu) + return gpa; + return translate_nested_gpa(vcpu, gpa, access, exception); +} #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 3be9beea838d..1d275e9d76b5 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -335,12 +335,6 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) return likely(kvm_gen == spte_gen); } -static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, - struct x86_exception *exception) -{ - return gpa; -} - static int is_cpuid_PSE36(void) { return 1; @@ -1454,7 +1448,7 @@ static bool kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, { u64 *sptep; struct rmap_iterator iter; - int need_flush = 0; + bool need_flush = false; u64 new_spte; kvm_pfn_t new_pfn; @@ -1466,7 +1460,7 @@ restart: rmap_printk("spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); - need_flush = 1; + need_flush = true; if (pte_write(pte)) { pte_list_remove(kvm, rmap_head, sptep); @@ -1482,7 +1476,7 @@ restart: if (need_flush && kvm_available_flush_tlb_with_range()) { kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); - return 0; + return false; } return need_flush; @@ -1582,7 +1576,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp); if (is_tdp_mmu_enabled(kvm)) - flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); + flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); return flush; } @@ -1623,8 +1617,8 @@ static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, for_each_rmap_spte(rmap_head, &iter, sptep) if (is_accessed_spte(*sptep)) - return 1; - return 0; + return true; + return false; } #define RMAP_RECYCLE_THRESHOLD 1000 @@ -1936,7 +1930,11 @@ static void mmu_audit_disable(void) { } static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { - return sp->role.invalid || + if (sp->role.invalid) + return true; + + /* TDP MMU pages due not use the MMU generation. */ + return !sp->tdp_mmu_page && unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } @@ -2082,10 +2080,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role = vcpu->arch.mmu->mmu_role.base; role.level = level; role.direct = direct; - if (role.direct) - role.gpte_is_8_bytes = true; role.access = access; - if (!direct_mmu && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) { + if (role.has_4_byte_gpte) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; @@ -2173,10 +2169,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato iterator->shadow_addr = root; iterator->level = vcpu->arch.mmu->shadow_root_level; - if (iterator->level == PT64_ROOT_4LEVEL && + if (iterator->level >= PT64_ROOT_4LEVEL && vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL && !vcpu->arch.mmu->direct_map) - --iterator->level; + iterator->level = PT32E_ROOT_LEVEL; if (iterator->level == PT32E_ROOT_LEVEL) { /* @@ -2561,10 +2557,10 @@ static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) return r; } -static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static void kvm_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) { trace_kvm_mmu_unsync_page(sp); - ++vcpu->kvm->stat.mmu_unsync; + ++kvm->stat.mmu_unsync; sp->unsync = 1; kvm_mmu_mark_parents_unsync(sp); @@ -2576,7 +2572,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must * be write-protected. */ -int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, +int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch) { struct kvm_mmu_page *sp; @@ -2587,7 +2583,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, * track machinery is used to write-protect upper-level shadow pages, * i.e. this guards the role.level == 4K assertion below! */ - if (kvm_slot_page_track_is_active(vcpu, slot, gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE)) return -EPERM; /* @@ -2596,7 +2592,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, * that case, KVM must complete emulation of the guest TLB flush before * allowing shadow pages to become unsync (writable by the guest). */ - for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { + for_each_gfn_indirect_valid_sp(kvm, sp, gfn) { if (!can_unsync) return -EPERM; @@ -2615,7 +2611,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, */ if (!locked) { locked = true; - spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + spin_lock(&kvm->arch.mmu_unsync_pages_lock); /* * Recheck after taking the spinlock, a different vCPU @@ -2630,10 +2626,10 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } WARN_ON(sp->role.level != PG_LEVEL_4K); - kvm_unsync_page(vcpu, sp); + kvm_unsync_page(kvm, sp); } if (locked) - spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + spin_unlock(&kvm->arch.mmu_unsync_pages_lock); /* * We need to ensure that the marking of unsync pages is visible @@ -3405,7 +3401,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; - int r = 0, i; + int r = 0, i, bkt; /* * Check if this is the first shadow root being allocated before @@ -3430,7 +3426,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(slot, slots) { + kvm_for_each_memslot(slot, bkt, slots) { /* * Both of these functions are no-ops if the target is * already allocated, so unconditionally calling both @@ -3730,21 +3726,13 @@ void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu) kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free); } -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, struct x86_exception *exception) -{ - if (exception) - exception->error_code = 0; - return vaddr; -} - -static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, - struct x86_exception *exception) +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t vaddr, u32 access, + struct x86_exception *exception) { if (exception) exception->error_code = 0; - return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception); + return kvm_translate_gpa(vcpu, mmu, vaddr, access, exception); } static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) @@ -3884,7 +3872,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, * guest is writing the page which is write tracked which can * not be fixed by page fault handler. */ - if (kvm_slot_page_track_is_active(vcpu, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) return true; return false; @@ -3976,6 +3964,34 @@ out_retry: return true; } +/* + * Returns true if the page fault is stale and needs to be retried, i.e. if the + * root was invalidated by a memslot update or a relevant mmu_notifier fired. + */ +static bool is_page_fault_stale(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, int mmu_seq) +{ + struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root_hpa); + + /* Special roots, e.g. pae_root, are not backed by shadow pages. */ + if (sp && is_obsolete_sp(vcpu->kvm, sp)) + return true; + + /* + * Roots without an associated shadow page are considered invalid if + * there is a pending request to free obsolete roots. The request is + * only a hint that the current root _may_ be obsolete and needs to be + * reloaded, e.g. if the guest frees a PGD that KVM is tracking as a + * previous root, then __kvm_mmu_prepare_zap_page() signals all vCPUs + * to reload even if no vCPU is actively using the root. + */ + if (!sp && kvm_test_request(KVM_REQ_MMU_RELOAD, vcpu)) + return true; + + return fault->slot && + mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva); +} + static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu); @@ -4013,8 +4029,9 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault else write_lock(&vcpu->kvm->mmu_lock); - if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva)) + if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; + r = make_mmu_pages_available(vcpu); if (r) goto out_unlock; @@ -4355,22 +4372,28 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, - u64 pa_bits_rsvd, bool execonly) + u64 pa_bits_rsvd, bool execonly, int huge_page_level) { u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); + u64 large_1g_rsvd = 0, large_2m_rsvd = 0; u64 bad_mt_xwr; + if (huge_page_level < PG_LEVEL_1G) + large_1g_rsvd = rsvd_bits(7, 7); + if (huge_page_level < PG_LEVEL_2M) + large_2m_rsvd = rsvd_bits(7, 7); + rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | rsvd_bits(3, 7); rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | rsvd_bits(3, 7); - rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6); - rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6); + rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6) | large_1g_rsvd; + rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6) | large_2m_rsvd; rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* large page */ rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; - rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29); - rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20); + rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29) | large_1g_rsvd; + rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20) | large_2m_rsvd; rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */ @@ -4386,10 +4409,11 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, } static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, bool execonly) + struct kvm_mmu *context, bool execonly, int huge_page_level) { __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check, - vcpu->arch.reserved_gpa_bits, execonly); + vcpu->arch.reserved_gpa_bits, execonly, + huge_page_level); } static inline u64 reserved_hpa_bits(void) @@ -4465,7 +4489,8 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, false, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - reserved_hpa_bits(), false); + reserved_hpa_bits(), false, + max_huge_page_level); if (!shadow_me_mask) return; @@ -4485,7 +4510,8 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, - reserved_hpa_bits(), execonly); + reserved_hpa_bits(), execonly, + max_huge_page_level); } #define BYTE_MASK(access) \ @@ -4734,7 +4760,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, role.base.ad_disabled = (shadow_accessed_mask == 0); role.base.level = kvm_mmu_get_tdp_level(vcpu); role.base.direct = true; - role.base.gpte_is_8_bytes = true; + role.base.has_4_byte_gpte = false; return role; } @@ -4779,7 +4805,7 @@ kvm_calc_shadow_root_page_role_common(struct kvm_vcpu *vcpu, role.base.smep_andnot_wp = role.ext.cr4_smep && !____is_cr0_wp(regs); role.base.smap_andnot_wp = role.ext.cr4_smap && !____is_cr0_wp(regs); - role.base.gpte_is_8_bytes = ____is_cr0_pg(regs) && ____is_cr4_pae(regs); + role.base.has_4_byte_gpte = ____is_cr0_pg(regs) && !____is_cr4_pae(regs); return role; } @@ -4855,7 +4881,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, struct kvm_mmu *context = &vcpu->arch.guest_mmu; struct kvm_mmu_role_regs regs = { .cr0 = cr0, - .cr4 = cr4, + .cr4 = cr4 & ~X86_CR4_PKE, .efer = efer, }; union kvm_mmu_role new_role; @@ -4878,7 +4904,7 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm; role.base.level = level; - role.base.gpte_is_8_bytes = true; + role.base.has_4_byte_gpte = false; role.base.direct = false; role.base.ad_disabled = !accessed_dirty; role.base.guest_mode = true; @@ -4893,7 +4919,8 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, } void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, - bool accessed_dirty, gpa_t new_eptp) + int huge_page_level, bool accessed_dirty, + gpa_t new_eptp) { struct kvm_mmu *context = &vcpu->arch.guest_mmu; u8 level = vmx_eptp_page_walk_level(new_eptp); @@ -4919,8 +4946,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->direct_map = false; update_permission_bitmask(context, true); - update_pkru_bitmask(context); - reset_rsvds_bits_mask_ept(vcpu, context, execonly); + context->pkru_mask = 0; + reset_rsvds_bits_mask_ept(vcpu, context, execonly, huge_page_level); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); @@ -4984,13 +5011,13 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) * the gva_to_gpa functions between mmu and nested_mmu are swapped. */ if (!is_paging(vcpu)) - g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested; + g_context->gva_to_gpa = nonpaging_gva_to_gpa; else if (is_long_mode(vcpu)) - g_context->gva_to_gpa = paging64_gva_to_gpa_nested; + g_context->gva_to_gpa = paging64_gva_to_gpa; else if (is_pae(vcpu)) - g_context->gva_to_gpa = paging64_gva_to_gpa_nested; + g_context->gva_to_gpa = paging64_gva_to_gpa; else - g_context->gva_to_gpa = paging32_gva_to_gpa_nested; + g_context->gva_to_gpa = paging32_gva_to_gpa; reset_guest_paging_metadata(vcpu, g_context); } @@ -5025,6 +5052,14 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) /* * Invalidate all MMU roles to force them to reinitialize as CPUID * information is factored into reserved bit calculations. + * + * Correctly handling multiple vCPU models with respect to paging and + * physical address properties) in a single VM would require tracking + * all relevant CPUID information in kvm_mmu_page_role. That is very + * undesirable as it would increase the memory requirements for + * gfn_track (see struct kvm_mmu_page_role comments). For now that + * problem is swept under the rug; KVM's CPUID API is horrific and + * it's all but impossible to solve it without introducing a new API. */ vcpu->arch.root_mmu.mmu_role.ext.valid = 0; vcpu->arch.guest_mmu.mmu_role.ext.valid = 0; @@ -5032,24 +5067,10 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); /* - * KVM does not correctly handle changing guest CPUID after KVM_RUN, as - * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't - * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page - * faults due to reusing SPs/SPTEs. Alert userspace, but otherwise - * sweep the problem under the rug. - * - * KVM's horrific CPUID ABI makes the problem all but impossible to - * solve, as correctly handling multiple vCPU models (with respect to - * paging and physical address properties) in a single VM would require - * tracking all relevant CPUID information in kvm_mmu_page_role. That - * is very undesirable as it would double the memory requirements for - * gfn_track (see struct kvm_mmu_page_role comments), and in practice - * no sane VMM mucks with the core vCPU model on the fly. + * Changing guest CPUID after KVM_RUN is forbidden, see the comment in + * kvm_arch_vcpu_ioctl(). */ - if (vcpu->arch.last_vmentry_cpu != -1) { - pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} after KVM_RUN may cause guest instability\n"); - pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} will fail after KVM_RUN starting with Linux 5.16\n"); - } + KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm); } void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) @@ -5161,7 +5182,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, gpa, bytes, sp->role.word); offset = offset_in_page(gpa); - pte_size = sp->role.gpte_is_8_bytes ? 8 : 4; + pte_size = sp->role.has_4_byte_gpte ? 4 : 8; /* * Sometimes, the OS only writes the last one bytes to update status @@ -5185,7 +5206,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) page_offset = offset_in_page(gpa); level = sp->role.level; *nspte = 1; - if (!sp->role.gpte_is_8_bytes) { + if (sp->role.has_4_byte_gpte) { page_offset <<= 1; /* 32->64 */ /* * A 32-bit pde maps 4MB while the shadow pdes map @@ -5369,7 +5390,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { - kvm_mmu_invalidate_gva(vcpu, vcpu->arch.mmu, gva, INVALID_PAGE); + kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); @@ -5497,10 +5518,13 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) mmu->root_hpa = INVALID_PAGE; mmu->root_pgd = 0; - mmu->translate_gpa = translate_gpa; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; + /* vcpu->arch.guest_mmu isn't used when !tdp_enabled. */ + if (!tdp_enabled && mmu == &vcpu->arch.guest_mmu) + return 0; + /* * When using PAE paging, the four PDPTEs are treated as 'root' pages, * while the PDP table is a per-vCPU construct that's allocated at MMU @@ -5510,7 +5534,7 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) * generally doesn't use PAE paging and can skip allocating the PDP * table. The main exception, handled here, is SVM's 32-bit NPT. The * other exception is for shadowing L1's 32-bit or PAE NPT on 64-bit - * KVM; that horror is handled on-demand by mmu_alloc_shadow_roots(). + * KVM; that horror is handled on-demand by mmu_alloc_special_roots(). */ if (tdp_enabled && kvm_mmu_get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) return 0; @@ -5555,8 +5579,6 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; - vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; - ret = __kvm_mmu_create(vcpu, &vcpu->arch.guest_mmu); if (ret) return ret; @@ -5715,6 +5737,7 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { const struct kvm_memory_slot *memslot; struct kvm_memslots *slots; + struct kvm_memslot_iter iter; bool flush = false; gfn_t start, end; int i; @@ -5724,10 +5747,12 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) { + + kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { + memslot = iter.slot; start = max(gfn_start, memslot->base_gfn); end = min(gfn_end, memslot->base_gfn + memslot->npages); - if (start >= end) + if (WARN_ON_ONCE(start >= end)) continue; flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, @@ -5748,6 +5773,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) bool flush; int i; + if (WARN_ON_ONCE(gfn_end <= gfn_start)) + return; + write_lock(&kvm->mmu_lock); kvm_inc_notifier_count(kvm, gfn_start, gfn_end); @@ -5854,8 +5882,6 @@ restart: void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *slot) { - bool flush = false; - if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); /* @@ -5863,17 +5889,14 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, * logging at a 4k granularity and never creates collapsible * 2m SPTEs during dirty logging. */ - flush = slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true); - if (flush) + if (slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true)) kvm_arch_flush_remote_tlbs_memslot(kvm, slot); write_unlock(&kvm->mmu_lock); } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); - flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush); - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, slot); + kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); read_unlock(&kvm->mmu_lock); } } @@ -6142,30 +6165,6 @@ out: return ret; } -/* - * Calculate mmu pages needed for kvm. - */ -unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) -{ - unsigned long nr_mmu_pages; - unsigned long nr_pages = 0; - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; - int i; - - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - slots = __kvm_memslots(kvm, i); - - kvm_for_each_memslot(memslot, slots) - nr_pages += memslot->npages; - } - - nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; - nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); - - return nr_mmu_pages; -} - void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); @@ -6182,23 +6181,46 @@ void kvm_mmu_module_exit(void) mmu_audit_disable(); } +/* + * Calculate the effective recovery period, accounting for '0' meaning "let KVM + * select a halving time of 1 hour". Returns true if recovery is enabled. + */ +static bool calc_nx_huge_pages_recovery_period(uint *period) +{ + /* + * Use READ_ONCE to get the params, this may be called outside of the + * param setters, e.g. by the kthread to compute its next timeout. + */ + bool enabled = READ_ONCE(nx_huge_pages); + uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + + if (!enabled || !ratio) + return false; + + *period = READ_ONCE(nx_huge_pages_recovery_period_ms); + if (!*period) { + /* Make sure the period is not less than one second. */ + ratio = min(ratio, 3600u); + *period = 60 * 60 * 1000 / ratio; + } + return true; +} + static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp) { bool was_recovery_enabled, is_recovery_enabled; uint old_period, new_period; int err; - was_recovery_enabled = nx_huge_pages_recovery_ratio; - old_period = nx_huge_pages_recovery_period_ms; + was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period); err = param_set_uint(val, kp); if (err) return err; - is_recovery_enabled = nx_huge_pages_recovery_ratio; - new_period = nx_huge_pages_recovery_period_ms; + is_recovery_enabled = calc_nx_huge_pages_recovery_period(&new_period); - if (READ_ONCE(nx_huge_pages) && is_recovery_enabled && + if (is_recovery_enabled && (!was_recovery_enabled || old_period > new_period)) { struct kvm *kvm; @@ -6262,18 +6284,13 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) static long get_nx_lpage_recovery_timeout(u64 start_time) { - uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio); - uint period = READ_ONCE(nx_huge_pages_recovery_period_ms); + bool enabled; + uint period; - if (!period && ratio) { - /* Make sure the period is not less than one second. */ - ratio = min(ratio, 3600u); - period = 60 * 60 * 1000 / ratio; - } + enabled = calc_nx_huge_pages_recovery_period(&period); - return READ_ONCE(nx_huge_pages) && ratio - ? start_time + msecs_to_jiffies(period) - get_jiffies_64() - : MAX_SCHEDULE_TIMEOUT; + return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; } static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 52c6527b1a06..da6166b5c377 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -104,7 +104,7 @@ static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) return kvm_mmu_role_as_id(sp->role); } -static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) +static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) { /* * When using the EPT page-modification log, the GPAs in the CPU dirty @@ -112,13 +112,12 @@ static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) * on write protection to record dirty pages, which bypasses PML, since * writes now result in a vmexit. Note, the check on CPU dirty logging * being enabled is mandatory as the bits used to denote WP-only SPTEs - * are reserved for NPT w/ PAE (32-bit KVM). + * are reserved for PAE paging (32-bit KVM). */ - return vcpu->arch.mmu == &vcpu->arch.guest_mmu && - kvm_x86_ops.cpu_dirty_log_size; + return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode; } -int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, +int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch); void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index b8151bbca36a..de5e8e4e1aa7 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -35,7 +35,7 @@ " %snxe %sad root %u %s%c", \ __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ - role.gpte_is_8_bytes ? 8 : 4, \ + role.has_4_byte_gpte ? 4 : 8, \ role.quadrant, \ role.direct ? " direct" : "", \ access_str[role.access], \ diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index cc4eb5b7fb76..68eb1fb548b6 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -173,9 +173,9 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page); /* * check if the corresponding access on the specified guest page is tracked. */ -bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) +bool kvm_slot_page_track_is_active(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, enum kvm_page_track_mode mode) { int index; @@ -186,7 +186,7 @@ bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, return false; if (mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(vcpu->kvm)) + !kvm_page_track_write_tracking_enabled(kvm)) return false; index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index f87d36898c44..5b5bdac97c7b 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -403,9 +403,8 @@ retry_walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), - nested_access, - &walker->fault); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(table_gfn), + nested_access, &walker->fault); /* * FIXME: This can happen if emulation (for of an INS/OUTS @@ -467,7 +466,7 @@ retry_walk: if (PTTYPE == 32 && walker->level > PG_LEVEL_4K && is_cpuid_PSE36()) gfn += pse36_gfn_delta(pte); - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(gfn), access, &walker->fault); if (real_gpa == UNMAPPED_GVA) return 0; @@ -547,16 +546,6 @@ static int FNAME(walk_addr)(struct guest_walker *walker, access); } -#if PTTYPE != PTTYPE_EPT -static int FNAME(walk_addr_nested)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, - u32 access) -{ - return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu, - addr, access); -} -#endif - static bool FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, pt_element_t gpte, bool no_dirty_log) @@ -911,7 +900,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva)) + + if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); @@ -999,50 +989,29 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) } /* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ -static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access, +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gpa_t addr, u32 access, struct x86_exception *exception) { struct guest_walker walker; gpa_t gpa = UNMAPPED_GVA; int r; - r = FNAME(walk_addr)(&walker, vcpu, addr, access); - - if (r) { - gpa = gfn_to_gpa(walker.gfn); - gpa |= addr & ~PAGE_MASK; - } else if (exception) - *exception = walker.fault; - - return gpa; -} - -#if PTTYPE != PTTYPE_EPT -/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */ -static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, - u32 access, - struct x86_exception *exception) -{ - struct guest_walker walker; - gpa_t gpa = UNMAPPED_GVA; - int r; - #ifndef CONFIG_X86_64 /* A 64-bit GVA should be impossible on 32-bit KVM. */ - WARN_ON_ONCE(vaddr >> 32); + WARN_ON_ONCE((addr >> 32) && mmu == vcpu->arch.walk_mmu); #endif - r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access); + r = FNAME(walk_addr_generic)(&walker, vcpu, mmu, addr, access); if (r) { gpa = gfn_to_gpa(walker.gfn); - gpa |= vaddr & ~PAGE_MASK; + gpa |= addr & ~PAGE_MASK; } else if (exception) *exception = walker.fault; return gpa; } -#endif /* * Using the cached information from sp->gfns is safe because: diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 0c76c45fdb68..8a7b03207762 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -90,7 +90,7 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) } bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct kvm_memory_slot *slot, + const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte) @@ -101,7 +101,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (sp->role.ad_disabled) spte |= SPTE_TDP_AD_DISABLED_MASK; - else if (kvm_vcpu_ad_need_write_protect(vcpu)) + else if (kvm_mmu_page_ad_need_write_protect(sp)) spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK; /* @@ -161,7 +161,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * e.g. it's write-tracked (upper-level SPs) or has one or more * shadow pages and unsync'ing pages is not allowed. */ - if (mmu_try_to_unsync_pages(vcpu, slot, gfn, can_unsync, prefetch)) { + if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) { pgprintk("%s: found shadow page for %llx, marking ro\n", __func__, gfn); wrprot = true; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index cc432f9a966b..a4af2a42695c 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -330,7 +330,7 @@ static inline u64 get_mmio_spte_generation(u64 spte) } bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct kvm_memory_slot *slot, + const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte); diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index b3ed302c1a35..caa96c270b95 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -26,6 +26,7 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level) */ void tdp_iter_restart(struct tdp_iter *iter) { + iter->yielded = false; iter->yielded_gfn = iter->next_last_level_gfn; iter->level = iter->root_level; @@ -160,6 +161,11 @@ static bool try_step_up(struct tdp_iter *iter) */ void tdp_iter_next(struct tdp_iter *iter) { + if (iter->yielded) { + tdp_iter_restart(iter); + return; + } + if (try_step_down(iter)) return; diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index b1748b988d3a..e19cabbcb65c 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -45,6 +45,12 @@ struct tdp_iter { * iterator walks off the end of the paging structure. */ bool valid; + /* + * True if KVM dropped mmu_lock and yielded in the middle of a walk, in + * which case tdp_iter_next() needs to restart the walk at the root + * level instead of advancing to the next entry. + */ + bool yielded; }; /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index a54c3491af42..7b1bc816b7c3 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -165,7 +165,7 @@ static union kvm_mmu_page_role page_role_for_level(struct kvm_vcpu *vcpu, role = vcpu->arch.mmu->mmu_role.base; role.level = level; role.direct = true; - role.gpte_is_8_bytes = true; + role.has_4_byte_gpte = false; role.access = ACC_ALL; role.ad_disabled = !shadow_accessed_mask; @@ -317,9 +317,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt)); int level = sp->role.level; gfn_t base_gfn = sp->gfn; - u64 old_child_spte; - u64 *sptep; - gfn_t gfn; int i; trace_kvm_mmu_prepare_zap_page(sp); @@ -327,8 +324,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, tdp_mmu_unlink_page(kvm, sp, shared); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - sptep = rcu_dereference(pt) + i; - gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); + u64 *sptep = rcu_dereference(pt) + i; + gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); + u64 old_child_spte; if (shared) { /* @@ -374,7 +372,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, shared); } - kvm_flush_remote_tlbs_with_address(kvm, gfn, + kvm_flush_remote_tlbs_with_address(kvm, base_gfn, KVM_PAGES_PER_HPAGE(level + 1)); call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); @@ -504,6 +502,8 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte) { + WARN_ON_ONCE(iter->yielded); + lockdep_assert_held_read(&kvm->mmu_lock); /* @@ -577,6 +577,8 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte, bool record_acc_track, bool record_dirty_log) { + WARN_ON_ONCE(iter->yielded); + lockdep_assert_held_write(&kvm->mmu_lock); /* @@ -642,18 +644,19 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm, * If this function should yield and flush is set, it will perform a remote * TLB flush before yielding. * - * If this function yields, it will also reset the tdp_iter's walk over the - * paging structure and the calling function should skip to the next - * iteration to allow the iterator to continue its traversal from the - * paging structure root. + * If this function yields, iter->yielded is set and the caller must skip to + * the next iteration, where tdp_iter_next() will reset the tdp_iter's walk + * over the paging structures to allow the iterator to continue its traversal + * from the paging structure root. * - * Return true if this function yielded and the iterator's traversal was reset. - * Return false if a yield was not needed. + * Returns true if this function yielded. */ -static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, - struct tdp_iter *iter, bool flush, - bool shared) +static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, + struct tdp_iter *iter, + bool flush, bool shared) { + WARN_ON(iter->yielded); + /* Ensure forward progress has been made before yielding. */ if (iter->next_last_level_gfn == iter->yielded_gfn) return false; @@ -673,12 +676,10 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, WARN_ON(iter->gfn > iter->next_last_level_gfn); - tdp_iter_restart(iter); - - return true; + iter->yielded = true; } - return false; + return iter->yielded; } /* @@ -1033,9 +1034,9 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, { struct kvm_mmu_page *root; - for_each_tdp_mmu_root(kvm, root, range->slot->as_id) - flush |= zap_gfn_range(kvm, root, range->start, range->end, - range->may_block, flush, false); + for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) + flush = zap_gfn_range(kvm, root, range->start, range->end, + range->may_block, flush, false); return flush; } @@ -1364,10 +1365,9 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, * Clear leaf entries which could be replaced by large mappings, for * GFNs within the slot. */ -static bool zap_collapsible_spte_range(struct kvm *kvm, +static void zap_collapsible_spte_range(struct kvm *kvm, struct kvm_mmu_page *root, - const struct kvm_memory_slot *slot, - bool flush) + const struct kvm_memory_slot *slot) { gfn_t start = slot->base_gfn; gfn_t end = start + slot->npages; @@ -1378,10 +1378,8 @@ static bool zap_collapsible_spte_range(struct kvm *kvm, tdp_root_for_each_pte(iter, root, start, end) { retry: - if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) { - flush = false; + if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - } if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) @@ -1393,6 +1391,7 @@ retry: pfn, PG_LEVEL_NUM)) continue; + /* Note, a successful atomic zap also does a remote TLB flush. */ if (!tdp_mmu_zap_spte_atomic(kvm, &iter)) { /* * The iter must explicitly re-read the SPTE because @@ -1401,30 +1400,24 @@ retry: iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep)); goto retry; } - flush = true; } rcu_read_unlock(); - - return flush; } /* * Clear non-leaf entries (and free associated page tables) which could * be replaced by large mappings, for GFNs within the slot. */ -bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot, - bool flush) +void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, + const struct kvm_memory_slot *slot) { struct kvm_mmu_page *root; lockdep_assert_held_read(&kvm->mmu_lock); for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) - flush = zap_collapsible_spte_range(kvm, root, slot, flush); - - return flush; + zap_collapsible_spte_range(kvm, root, slot); } /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 476b133544dd..3899004a5d91 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -64,9 +64,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, unsigned long mask, bool wrprot); -bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot, - bool flush); +void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, + const struct kvm_memory_slot *slot); bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index affc0ea98d30..0e5b49294086 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -293,7 +293,7 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { bool m = kvm_apic_match_dest(vcpu, source, @@ -675,10 +675,18 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) smp_mb__after_atomic(); if (avic_vcpu_is_running(vcpu)) { - int cpuid = vcpu->cpu; + int cpu = READ_ONCE(vcpu->cpu); - if (cpuid != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid)); + /* + * Note, the vCPU could get migrated to a different pCPU at any + * point, which could result in signalling the wrong/previous + * pCPU. But if that happens the vCPU is guaranteed to do a + * VMRUN (after being migrated) and thus will process pending + * interrupts, i.e. a doorbell is not needed (and the spurious + * one is harmless). + */ + if (cpu != get_cpu()) + wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); put_cpu(); } else kvm_vcpu_wake_up(vcpu); @@ -900,6 +908,7 @@ out: bool svm_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_NESTED) | BIT(APICV_INHIBIT_REASON_IRQWIN) | @@ -989,16 +998,18 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) { struct vcpu_svm *svm = to_svm(vcpu); + int cpu = get_cpu(); + WARN_ON(cpu != vcpu->cpu); svm->avic_is_running = is_run; - if (!kvm_vcpu_apicv_active(vcpu)) - return; - - if (is_run) - avic_vcpu_load(vcpu, vcpu->cpu); - else - avic_vcpu_put(vcpu); + if (kvm_vcpu_apicv_active(vcpu)) { + if (is_run) + avic_vcpu_load(vcpu, cpu); + else + avic_vcpu_put(vcpu); + } + put_cpu(); } void svm_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index f8b7bc04b3e7..cf206855ebf0 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -58,8 +58,9 @@ static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_excep struct vcpu_svm *svm = to_svm(vcpu); WARN_ON(!is_guest_mode(vcpu)); - if (vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && - !svm->nested.nested_run_pending) { + if (vmcb12_is_intercept(&svm->nested.ctl, + INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && + !svm->nested.nested_run_pending) { svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR; svm->vmcb->control.exit_code_hi = 0; svm->vmcb->control.exit_info_1 = fault->error_code; @@ -121,7 +122,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) void recalc_intercepts(struct vcpu_svm *svm) { - struct vmcb_control_area *c, *h, *g; + struct vmcb_control_area *c, *h; + struct vmcb_ctrl_area_cached *g; unsigned int i; vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); @@ -163,37 +165,6 @@ void recalc_intercepts(struct vcpu_svm *svm) vmcb_set_intercept(c, INTERCEPT_VMSAVE); } -static void copy_vmcb_control_area(struct vmcb_control_area *dst, - struct vmcb_control_area *from) -{ - unsigned int i; - - for (i = 0; i < MAX_INTERCEPT; i++) - dst->intercepts[i] = from->intercepts[i]; - - dst->iopm_base_pa = from->iopm_base_pa; - dst->msrpm_base_pa = from->msrpm_base_pa; - dst->tsc_offset = from->tsc_offset; - /* asid not copied, it is handled manually for svm->vmcb. */ - dst->tlb_ctl = from->tlb_ctl; - dst->int_ctl = from->int_ctl; - dst->int_vector = from->int_vector; - dst->int_state = from->int_state; - dst->exit_code = from->exit_code; - dst->exit_code_hi = from->exit_code_hi; - dst->exit_info_1 = from->exit_info_1; - dst->exit_info_2 = from->exit_info_2; - dst->exit_int_info = from->exit_int_info; - dst->exit_int_info_err = from->exit_int_info_err; - dst->nested_ctl = from->nested_ctl; - dst->event_inj = from->event_inj; - dst->event_inj_err = from->event_inj_err; - dst->nested_cr3 = from->nested_cr3; - dst->virt_ext = from->virt_ext; - dst->pause_filter_count = from->pause_filter_count; - dst->pause_filter_thresh = from->pause_filter_thresh; -} - static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { /* @@ -203,7 +174,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) */ int i; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return true; for (i = 0; i < MSRPM_OFFSETS; i++) { @@ -250,10 +221,10 @@ static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl) } } -static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu, - struct vmcb_control_area *control) +static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, + struct vmcb_ctrl_area_cached *control) { - if (CC(!vmcb_is_intercept(control, INTERCEPT_VMRUN))) + if (CC(!vmcb12_is_intercept(control, INTERCEPT_VMRUN))) return false; if (CC(control->asid == 0)) @@ -275,9 +246,20 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu, return true; } -static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu, - struct vmcb_save_area *save) +/* Common checks that apply to both L1 and L2 state. */ +static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu, + struct vmcb_save_area_cached *save) { + if (CC(!(save->efer & EFER_SVME))) + return false; + + if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) || + CC(save->cr0 & ~0xffffffffULL)) + return false; + + if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7))) + return false; + /* * These checks are also performed by KVM_SET_SREGS, * except that EFER.LMA is not checked by SVM against @@ -293,48 +275,90 @@ static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu, if (CC(!kvm_is_valid_cr4(vcpu, save->cr4))) return false; + if (CC(!kvm_valid_efer(vcpu, save->efer))) + return false; + return true; } -/* Common checks that apply to both L1 and L2 state. */ -static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu, - struct vmcb_save_area *save) +static bool nested_vmcb_check_save(struct kvm_vcpu *vcpu) { - /* - * FIXME: these should be done after copying the fields, - * to avoid TOC/TOU races. For these save area checks - * the possible damage is limited since kvm_set_cr0 and - * kvm_set_cr4 handle failure; EFER_SVME is an exception - * so it is force-set later in nested_prepare_vmcb_save. - */ - if (CC(!(save->efer & EFER_SVME))) - return false; + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_save_area_cached *save = &svm->nested.save; - if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) || - CC(save->cr0 & ~0xffffffffULL)) - return false; + return __nested_vmcb_check_save(vcpu, save); +} - if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7))) - return false; +static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_ctrl_area_cached *ctl = &svm->nested.ctl; - if (!nested_vmcb_check_cr3_cr4(vcpu, save)) - return false; + return __nested_vmcb_check_controls(vcpu, ctl); +} - if (CC(!kvm_valid_efer(vcpu, save->efer))) - return false; +static +void __nested_copy_vmcb_control_to_cache(struct vmcb_ctrl_area_cached *to, + struct vmcb_control_area *from) +{ + unsigned int i; - return true; + for (i = 0; i < MAX_INTERCEPT; i++) + to->intercepts[i] = from->intercepts[i]; + + to->iopm_base_pa = from->iopm_base_pa; + to->msrpm_base_pa = from->msrpm_base_pa; + to->tsc_offset = from->tsc_offset; + to->tlb_ctl = from->tlb_ctl; + to->int_ctl = from->int_ctl; + to->int_vector = from->int_vector; + to->int_state = from->int_state; + to->exit_code = from->exit_code; + to->exit_code_hi = from->exit_code_hi; + to->exit_info_1 = from->exit_info_1; + to->exit_info_2 = from->exit_info_2; + to->exit_int_info = from->exit_int_info; + to->exit_int_info_err = from->exit_int_info_err; + to->nested_ctl = from->nested_ctl; + to->event_inj = from->event_inj; + to->event_inj_err = from->event_inj_err; + to->nested_cr3 = from->nested_cr3; + to->virt_ext = from->virt_ext; + to->pause_filter_count = from->pause_filter_count; + to->pause_filter_thresh = from->pause_filter_thresh; + + /* Copy asid here because nested_vmcb_check_controls will check it. */ + to->asid = from->asid; + to->msrpm_base_pa &= ~0x0fffULL; + to->iopm_base_pa &= ~0x0fffULL; } -void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control) +void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, + struct vmcb_control_area *control) { - copy_vmcb_control_area(&svm->nested.ctl, control); + __nested_copy_vmcb_control_to_cache(&svm->nested.ctl, control); +} + +static void __nested_copy_vmcb_save_to_cache(struct vmcb_save_area_cached *to, + struct vmcb_save_area *from) +{ + /* + * Copy only fields that are validated, as we need them + * to avoid TOC/TOU races. + */ + to->efer = from->efer; + to->cr0 = from->cr0; + to->cr3 = from->cr3; + to->cr4 = from->cr4; - /* Copy it here because nested_svm_check_controls will check it. */ - svm->nested.ctl.asid = control->asid; - svm->nested.ctl.msrpm_base_pa &= ~0x0fffULL; - svm->nested.ctl.iopm_base_pa &= ~0x0fffULL; + to->dr6 = from->dr6; + to->dr7 = from->dr7; +} + +void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, + struct vmcb_save_area *save) +{ + __nested_copy_vmcb_save_to_cache(&svm->nested.save, save); } /* @@ -437,14 +461,13 @@ static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, return -EINVAL; if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && - CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) + CC(!load_pdptrs(vcpu, cr3))) return -EINVAL; if (!nested_npt) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ kvm_init_mmu(vcpu); @@ -490,15 +513,10 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); - /* - * Force-set EFER_SVME even though it is checked earlier on the - * VMCB12, because the guest can flip the bit between the check - * and now. Clearing EFER_SVME would call svm_free_nested. - */ - svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME); + svm_set_efer(&svm->vcpu, svm->nested.save.efer); - svm_set_cr0(&svm->vcpu, vmcb12->save.cr0); - svm_set_cr4(&svm->vcpu, vmcb12->save.cr4); + svm_set_cr0(&svm->vcpu, svm->nested.save.cr0); + svm_set_cr4(&svm->vcpu, svm->nested.save.cr4); svm->vcpu.arch.cr2 = vmcb12->save.cr2; @@ -513,8 +531,8 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 /* These bits will be set properly on the first execution when new_vmc12 is true */ if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DR))) { - svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1; - svm->vcpu.arch.dr6 = vmcb12->save.dr6 | DR6_ACTIVE_LOW; + svm->vmcb->save.dr7 = svm->nested.save.dr7 | DR7_FIXED_1; + svm->vcpu.arch.dr6 = svm->nested.save.dr6 | DR6_ACTIVE_LOW; vmcb_mark_dirty(svm->vmcb, VMCB_DR); } } @@ -628,7 +646,7 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, nested_vmcb02_prepare_control(svm); nested_vmcb02_prepare_save(svm, vmcb12); - ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, + ret = nested_svm_load_cr3(&svm->vcpu, svm->nested.save.cr3, nested_npt_enabled(svm), from_vmrun); if (ret) return ret; @@ -678,10 +696,11 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) if (WARN_ON_ONCE(!svm->nested.initialized)) return -EINVAL; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - if (!nested_vmcb_valid_sregs(vcpu, &vmcb12->save) || - !nested_vmcb_check_controls(vcpu, &svm->nested.ctl)) { + if (!nested_vmcb_check_save(vcpu) || + !nested_vmcb_check_controls(vcpu)) { vmcb12->control.exit_code = SVM_EXIT_ERR; vmcb12->control.exit_code_hi = 0; vmcb12->control.exit_info_1 = 0; @@ -988,7 +1007,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) u32 offset, msr, value; int write, mask; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return NESTED_EXIT_HOST; msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; @@ -1015,7 +1034,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm) u8 start_bit; u64 gpa; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) return NESTED_EXIT_HOST; port = svm->vmcb->control.exit_info_1 >> 16; @@ -1046,12 +1065,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm) vmexit = nested_svm_intercept_ioio(svm); break; case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; break; } @@ -1069,7 +1088,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm) break; } default: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; } } @@ -1147,7 +1166,7 @@ static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm) static inline bool nested_exit_on_init(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); } static int svm_check_nested_events(struct kvm_vcpu *vcpu) @@ -1251,11 +1270,47 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu) svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio); } +/* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */ +static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst, + struct vmcb_ctrl_area_cached *from) +{ + unsigned int i; + + memset(dst, 0, sizeof(struct vmcb_control_area)); + + for (i = 0; i < MAX_INTERCEPT; i++) + dst->intercepts[i] = from->intercepts[i]; + + dst->iopm_base_pa = from->iopm_base_pa; + dst->msrpm_base_pa = from->msrpm_base_pa; + dst->tsc_offset = from->tsc_offset; + dst->asid = from->asid; + dst->tlb_ctl = from->tlb_ctl; + dst->int_ctl = from->int_ctl; + dst->int_vector = from->int_vector; + dst->int_state = from->int_state; + dst->exit_code = from->exit_code; + dst->exit_code_hi = from->exit_code_hi; + dst->exit_info_1 = from->exit_info_1; + dst->exit_info_2 = from->exit_info_2; + dst->exit_int_info = from->exit_int_info; + dst->exit_int_info_err = from->exit_int_info_err; + dst->nested_ctl = from->nested_ctl; + dst->event_inj = from->event_inj; + dst->event_inj_err = from->event_inj_err; + dst->nested_cr3 = from->nested_cr3; + dst->virt_ext = from->virt_ext; + dst->pause_filter_count = from->pause_filter_count; + dst->pause_filter_thresh = from->pause_filter_thresh; +} + static int svm_get_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, u32 user_data_size) { struct vcpu_svm *svm; + struct vmcb_control_area *ctl; + unsigned long r; struct kvm_nested_state kvm_state = { .flags = 0, .format = KVM_STATE_NESTED_FORMAT_SVM, @@ -1297,9 +1352,18 @@ static int svm_get_nested_state(struct kvm_vcpu *vcpu, */ if (clear_user(user_vmcb, KVM_STATE_NESTED_SVM_VMCB_SIZE)) return -EFAULT; - if (copy_to_user(&user_vmcb->control, &svm->nested.ctl, - sizeof(user_vmcb->control))) + + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + if (!ctl) + return -ENOMEM; + + nested_copy_vmcb_cache_to_control(ctl, &svm->nested.ctl); + r = copy_to_user(&user_vmcb->control, ctl, + sizeof(user_vmcb->control)); + kfree(ctl); + if (r) return -EFAULT; + if (copy_to_user(&user_vmcb->save, &svm->vmcb01.ptr->save, sizeof(user_vmcb->save))) return -EFAULT; @@ -1316,6 +1380,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, &user_kvm_nested_state->data.svm[0]; struct vmcb_control_area *ctl; struct vmcb_save_area *save; + struct vmcb_save_area_cached save_cached; + struct vmcb_ctrl_area_cached ctl_cached; unsigned long cr0; int ret; @@ -1368,7 +1434,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, goto out_free; ret = -EINVAL; - if (!nested_vmcb_check_controls(vcpu, ctl)) + __nested_copy_vmcb_control_to_cache(&ctl_cached, ctl); + if (!__nested_vmcb_check_controls(vcpu, &ctl_cached)) goto out_free; /* @@ -1383,10 +1450,11 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * Validate host state saved from before VMRUN (see * nested_svm_check_permissions). */ + __nested_copy_vmcb_save_to_cache(&save_cached, save); if (!(save->cr0 & X86_CR0_PG) || !(save->cr0 & X86_CR0_PE) || (save->rflags & X86_EFLAGS_VM) || - !nested_vmcb_valid_sregs(vcpu, save)) + !__nested_vmcb_check_save(vcpu, &save_cached)) goto out_free; /* @@ -1422,7 +1490,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save); - nested_load_control_from_vmcb12(svm, ctl); + nested_copy_vmcb_control_to_cache(svm, ctl); svm_switch_vmcb(svm, &svm->nested.vmcb02); nested_vmcb02_prepare_control(svm); @@ -1449,7 +1517,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) * the guest CR3 might be restored prior to setting the nested * state which can lead to a load of wrong PDPTRs. */ - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; if (!nested_svm_vmrun_msrpm(svm)) { diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 871c426ec389..0cf05e4caa4c 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -16,6 +16,7 @@ #include "cpuid.h" #include "lapic.h" #include "pmu.h" +#include "svm.h" enum pmu_type { PMU_TYPE_COUNTER = 0, @@ -100,6 +101,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); + if (!pmu) + return NULL; + switch (msr) { case MSR_F15H_PERF_CTL0: case MSR_F15H_PERF_CTL1: @@ -281,7 +285,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; - pmu->reserved_bits = 0xffffffff00200000ull; + pmu->reserved_bits = 0xfffffff000280000ull; pmu->version = 1; /* not applicable to AMD; but clean them to prevent any fall out */ pmu->counter_bitmask[KVM_PMC_FIXED] = 0; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 21ac0a5de4e0..322553322202 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -636,7 +636,8 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_vcpu *vcpu; - int i, ret; + unsigned long i; + int ret; if (!sev_es_guest(kvm)) return -ENOTTY; @@ -1543,35 +1544,57 @@ static bool is_cmd_allowed_from_mirror(u32 cmd_id) return false; } -static int sev_lock_for_migration(struct kvm *kvm) +static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; + int r = -EBUSY; + + if (dst_kvm == src_kvm) + return -EINVAL; /* - * Bail if this VM is already involved in a migration to avoid deadlock - * between two VMs trying to migrate to/from each other. + * Bail if these VMs are already involved in a migration to avoid + * deadlock between two VMs trying to migrate to/from each other. */ - if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1)) + if (atomic_cmpxchg_acquire(&dst_sev->migration_in_progress, 0, 1)) return -EBUSY; - mutex_lock(&kvm->lock); + if (atomic_cmpxchg_acquire(&src_sev->migration_in_progress, 0, 1)) + goto release_dst; + r = -EINTR; + if (mutex_lock_killable(&dst_kvm->lock)) + goto release_src; + if (mutex_lock_killable(&src_kvm->lock)) + goto unlock_dst; return 0; + +unlock_dst: + mutex_unlock(&dst_kvm->lock); +release_src: + atomic_set_release(&src_sev->migration_in_progress, 0); +release_dst: + atomic_set_release(&dst_sev->migration_in_progress, 0); + return r; } -static void sev_unlock_after_migration(struct kvm *kvm) +static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; - mutex_unlock(&kvm->lock); - atomic_set_release(&sev->migration_in_progress, 0); + mutex_unlock(&dst_kvm->lock); + mutex_unlock(&src_kvm->lock); + atomic_set_release(&dst_sev->migration_in_progress, 0); + atomic_set_release(&src_sev->migration_in_progress, 0); } static int sev_lock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, j; + unsigned long i, j; kvm_for_each_vcpu(i, vcpu, kvm) { if (mutex_lock_killable(&vcpu->mutex)) @@ -1593,7 +1616,7 @@ out_unlock: static void sev_unlock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { mutex_unlock(&vcpu->mutex); @@ -1607,19 +1630,20 @@ static void sev_migrate_from(struct kvm_sev_info *dst, dst->asid = src->asid; dst->handle = src->handle; dst->pages_locked = src->pages_locked; + dst->enc_context_owner = src->enc_context_owner; src->asid = 0; src->active = false; src->handle = 0; src->pages_locked = 0; + src->enc_context_owner = NULL; - INIT_LIST_HEAD(&dst->regions_list); - list_replace_init(&src->regions_list, &dst->regions_list); + list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list); } static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) { - int i; + unsigned long i; struct kvm_vcpu *dst_vcpu, *src_vcpu; struct vcpu_svm *dst_svm, *src_svm; @@ -1666,15 +1690,6 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) bool charged = false; int ret; - ret = sev_lock_for_migration(kvm); - if (ret) - return ret; - - if (sev_guest(kvm)) { - ret = -EINVAL; - goto out_unlock; - } - source_kvm_file = fget(source_fd); if (!file_is_kvm(source_kvm_file)) { ret = -EBADF; @@ -1682,16 +1697,26 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) } source_kvm = source_kvm_file->private_data; - ret = sev_lock_for_migration(source_kvm); + ret = sev_lock_two_vms(kvm, source_kvm); if (ret) goto out_fput; - if (!sev_guest(source_kvm)) { + if (sev_guest(kvm) || !sev_guest(source_kvm)) { ret = -EINVAL; - goto out_source; + goto out_unlock; } src_sev = &to_kvm_svm(source_kvm)->sev_info; + + /* + * VMs mirroring src's encryption context rely on it to keep the + * ASID allocated, but below we are clearing src_sev->asid. + */ + if (src_sev->num_mirrored_vms) { + ret = -EBUSY; + goto out_unlock; + } + dst_sev->misc_cg = get_current_misc_cg(); cg_cleanup_sev = dst_sev; if (dst_sev->misc_cg != src_sev->misc_cg) { @@ -1728,13 +1753,11 @@ out_dst_cgroup: sev_misc_cg_uncharge(cg_cleanup_sev); put_misc_cg(cg_cleanup_sev->misc_cg); cg_cleanup_sev->misc_cg = NULL; -out_source: - sev_unlock_after_migration(source_kvm); +out_unlock: + sev_unlock_two_vms(kvm, source_kvm); out_fput: if (source_kvm_file) fput(source_kvm_file); -out_unlock: - sev_unlock_after_migration(kvm); return ret; } @@ -1953,76 +1976,60 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) { struct file *source_kvm_file; struct kvm *source_kvm; - struct kvm_sev_info source_sev, *mirror_sev; + struct kvm_sev_info *source_sev, *mirror_sev; int ret; source_kvm_file = fget(source_fd); if (!file_is_kvm(source_kvm_file)) { ret = -EBADF; - goto e_source_put; + goto e_source_fput; } source_kvm = source_kvm_file->private_data; - mutex_lock(&source_kvm->lock); - - if (!sev_guest(source_kvm)) { - ret = -EINVAL; - goto e_source_unlock; - } + ret = sev_lock_two_vms(kvm, source_kvm); + if (ret) + goto e_source_fput; - /* Mirrors of mirrors should work, but let's not get silly */ - if (is_mirroring_enc_context(source_kvm) || source_kvm == kvm) { + /* + * Mirrors of mirrors should work, but let's not get silly. Also + * disallow out-of-band SEV/SEV-ES init if the target is already an + * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being + * created after SEV/SEV-ES initialization, e.g. to init intercepts. + */ + if (sev_guest(kvm) || !sev_guest(source_kvm) || + is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) { ret = -EINVAL; - goto e_source_unlock; + goto e_unlock; } - memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info, - sizeof(source_sev)); - /* * The mirror kvm holds an enc_context_owner ref so its asid can't * disappear until we're done with it */ + source_sev = &to_kvm_svm(source_kvm)->sev_info; kvm_get_kvm(source_kvm); - - fput(source_kvm_file); - mutex_unlock(&source_kvm->lock); - mutex_lock(&kvm->lock); - - /* - * Disallow out-of-band SEV/SEV-ES init if the target is already an - * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being - * created after SEV/SEV-ES initialization, e.g. to init intercepts. - */ - if (sev_guest(kvm) || kvm->created_vcpus) { - ret = -EINVAL; - goto e_mirror_unlock; - } + source_sev->num_mirrored_vms++; /* Set enc_context_owner and copy its encryption context over */ mirror_sev = &to_kvm_svm(kvm)->sev_info; mirror_sev->enc_context_owner = source_kvm; mirror_sev->active = true; - mirror_sev->asid = source_sev.asid; - mirror_sev->fd = source_sev.fd; - mirror_sev->es_active = source_sev.es_active; - mirror_sev->handle = source_sev.handle; + mirror_sev->asid = source_sev->asid; + mirror_sev->fd = source_sev->fd; + mirror_sev->es_active = source_sev->es_active; + mirror_sev->handle = source_sev->handle; + INIT_LIST_HEAD(&mirror_sev->regions_list); + ret = 0; + /* * Do not copy ap_jump_table. Since the mirror does not share the same * KVM contexts as the original, and they may have different * memory-views. */ - mutex_unlock(&kvm->lock); - return 0; - -e_mirror_unlock: - mutex_unlock(&kvm->lock); - kvm_put_kvm(source_kvm); - return ret; -e_source_unlock: - mutex_unlock(&source_kvm->lock); -e_source_put: +e_unlock: + sev_unlock_two_vms(kvm, source_kvm); +e_source_fput: if (source_kvm_file) fput(source_kvm_file); return ret; @@ -2034,17 +2041,24 @@ void sev_vm_destroy(struct kvm *kvm) struct list_head *head = &sev->regions_list; struct list_head *pos, *q; + WARN_ON(sev->num_mirrored_vms); + if (!sev_guest(kvm)) return; /* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */ if (is_mirroring_enc_context(kvm)) { - kvm_put_kvm(sev->enc_context_owner); + struct kvm *owner_kvm = sev->enc_context_owner; + struct kvm_sev_info *owner_sev = &to_kvm_svm(owner_kvm)->sev_info; + + mutex_lock(&owner_kvm->lock); + if (!WARN_ON(!owner_sev->num_mirrored_vms)) + owner_sev->num_mirrored_vms--; + mutex_unlock(&owner_kvm->lock); + kvm_put_kvm(owner_kvm); return; } - mutex_lock(&kvm->lock); - /* * Ensure that all guest tagged cache entries are flushed before * releasing the pages back to the system for use. CLFLUSH will @@ -2064,8 +2078,6 @@ void sev_vm_destroy(struct kvm *kvm) } } - mutex_unlock(&kvm->lock); - sev_unbind_asid(kvm, sev->handle); sev_asid_free(sev); } @@ -2249,7 +2261,7 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) __free_page(virt_to_page(svm->sev_es.vmsa)); if (svm->sev_es.ghcb_sa_free) - kfree(svm->sev_es.ghcb_sa); + kvfree(svm->sev_es.ghcb_sa); } static void dump_ghcb(struct vcpu_svm *svm) @@ -2341,24 +2353,29 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } -static int sev_es_validate_vmgexit(struct vcpu_svm *svm) +static bool sev_es_validate_vmgexit(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu; struct ghcb *ghcb; - u64 exit_code = 0; + u64 exit_code; + u64 reason; ghcb = svm->sev_es.ghcb; - /* Only GHCB Usage code 0 is supported */ - if (ghcb->ghcb_usage) - goto vmgexit_err; - /* - * Retrieve the exit code now even though is may not be marked valid + * Retrieve the exit code now even though it may not be marked valid * as it could help with debugging. */ exit_code = ghcb_get_sw_exit_code(ghcb); + /* Only GHCB Usage code 0 is supported */ + if (ghcb->ghcb_usage) { + reason = GHCB_ERR_INVALID_USAGE; + goto vmgexit_err; + } + + reason = GHCB_ERR_MISSING_INPUT; + if (!ghcb_sw_exit_code_is_valid(ghcb) || !ghcb_sw_exit_info_1_is_valid(ghcb) || !ghcb_sw_exit_info_2_is_valid(ghcb)) @@ -2437,30 +2454,34 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_UNSUPPORTED_EVENT: break; default: + reason = GHCB_ERR_INVALID_EVENT; goto vmgexit_err; } - return 0; + return true; vmgexit_err: vcpu = &svm->vcpu; - if (ghcb->ghcb_usage) { + if (reason == GHCB_ERR_INVALID_USAGE) { vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", ghcb->ghcb_usage); + } else if (reason == GHCB_ERR_INVALID_EVENT) { + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n", + exit_code); } else { - vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n", + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n", exit_code); dump_ghcb(svm); } - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = exit_code; - vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + /* Clear the valid entries fields */ + memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); + + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, reason); - return -EINVAL; + return false; } void sev_es_unmap_ghcb(struct vcpu_svm *svm) @@ -2482,7 +2503,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) svm->sev_es.ghcb_sa_sync = false; } - kfree(svm->sev_es.ghcb_sa); + kvfree(svm->sev_es.ghcb_sa); svm->sev_es.ghcb_sa = NULL; svm->sev_es.ghcb_sa_free = false; } @@ -2530,14 +2551,14 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); if (!scratch_gpa_beg) { pr_err("vmgexit: scratch gpa not provided\n"); - return false; + goto e_scratch; } scratch_gpa_end = scratch_gpa_beg + len; if (scratch_gpa_end < scratch_gpa_beg) { pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n", len, scratch_gpa_beg); - return false; + goto e_scratch; } if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) { @@ -2555,7 +2576,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) scratch_gpa_end > ghcb_scratch_end) { pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n", scratch_gpa_beg, scratch_gpa_end); - return false; + goto e_scratch; } scratch_va = (void *)svm->sev_es.ghcb; @@ -2568,18 +2589,18 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) if (len > GHCB_SCRATCH_AREA_LIMIT) { pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n", len, GHCB_SCRATCH_AREA_LIMIT); - return false; + goto e_scratch; } - scratch_va = kzalloc(len, GFP_KERNEL_ACCOUNT); + scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT); if (!scratch_va) - return false; + goto e_scratch; if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) { /* Unable to copy scratch area from guest */ pr_err("vmgexit: kvm_read_guest for scratch area failed\n"); - kfree(scratch_va); - return false; + kvfree(scratch_va); + goto e_scratch; } /* @@ -2596,6 +2617,12 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) svm->sev_es.ghcb_sa_len = len; return true; + +e_scratch: + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); + + return false; } static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask, @@ -2646,7 +2673,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID); if (!ret) { - ret = -EINVAL; + /* Error, keep GHCB MSR value as-is */ break; } @@ -2682,10 +2709,13 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) GHCB_MSR_TERM_REASON_POS); pr_info("SEV-ES guest requested termination: %#llx:%#llx\n", reason_set, reason_code); - fallthrough; + + ret = -EINVAL; + break; } default: - ret = -EINVAL; + /* Error, keep GHCB MSR value as-is */ + break; } trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id, @@ -2709,14 +2739,18 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) if (!ghcb_gpa) { vcpu_unimpl(vcpu, "vmgexit: GHCB gpa is not set\n"); - return -EINVAL; + + /* Without a GHCB, just return right back to the guest */ + return 1; } if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) { /* Unable to map GHCB from guest */ vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", ghcb_gpa); - return -EINVAL; + + /* Without a GHCB, just return right back to the guest */ + return 1; } svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; @@ -2726,15 +2760,14 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) exit_code = ghcb_get_sw_exit_code(ghcb); - ret = sev_es_validate_vmgexit(svm); - if (ret) - return ret; + if (!sev_es_validate_vmgexit(svm)) + return 1; sev_es_sync_from_ghcb(svm); ghcb_set_sw_exit_info_1(ghcb, 0); ghcb_set_sw_exit_info_2(ghcb, 0); - ret = -EINVAL; + ret = 1; switch (exit_code) { case SVM_VMGEXIT_MMIO_READ: if (!setup_vmgexit_scratch(svm, true, control->exit_info_2)) @@ -2775,20 +2808,17 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) default: pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n", control->exit_info_1); - ghcb_set_sw_exit_info_1(ghcb, 1); - ghcb_set_sw_exit_info_2(ghcb, - X86_TRAP_UD | - SVM_EVTINJ_TYPE_EXEPT | - SVM_EVTINJ_VALID); + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT); } - ret = 1; break; } case SVM_VMGEXIT_UNSUPPORTED_EVENT: vcpu_unimpl(vcpu, "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", control->exit_info_1, control->exit_info_2); + ret = -EINVAL; break; default: ret = svm_invoke_exit_handler(vcpu, exit_code); @@ -2810,7 +2840,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) return -EINVAL; if (!setup_vmgexit_scratch(svm, in, bytes)) - return -EINVAL; + return 1; return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa, count, in); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5630c241d5f6..5557867dcb69 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -192,6 +192,10 @@ module_param(vgif, int, 0444); static int lbrv = true; module_param(lbrv, int, 0444); +/* enable/disable PMU virtualization */ +bool pmu = true; +module_param(pmu, bool, 0444); + static int tsc_scaling = true; module_param(tsc_scaling, int, 0444); @@ -265,7 +269,7 @@ u32 svm_msrpm_offset(u32 msr) #define MAX_INST_SIZE 15 -static int get_max_npt_level(void) +static int get_npt_level(void) { #ifdef CONFIG_X86_64 return pgtable_l5_enabled() ? PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; @@ -585,12 +589,10 @@ static int svm_cpu_init(int cpu) if (!sd) return ret; sd->cpu = cpu; - sd->save_area = alloc_page(GFP_KERNEL); + sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!sd->save_area) goto free_cpu_data; - clear_page(page_address(sd->save_area)); - ret = sev_cpu_init(sd); if (ret) goto free_save_area; @@ -954,6 +956,10 @@ static __init void svm_set_cpu_caps(void) boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); + /* AMD PMU PERFCTR_CORE CPUID */ + if (pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) + kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE); + /* CPUID 0x8000001F (SME/SEV features) */ sev_set_cpu_caps(); } @@ -1029,9 +1035,9 @@ static __init int svm_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; - /* Force VM NPT level equal to the host's max NPT level */ - kvm_configure_mmu(npt_enabled, get_max_npt_level(), - get_max_npt_level(), PG_LEVEL_1G); + /* Force VM NPT level equal to the host's paging level */ + kvm_configure_mmu(npt_enabled, get_npt_level(), + get_npt_level(), PG_LEVEL_1G); pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); /* Note, SEV setup consumes npt_enabled. */ @@ -1087,6 +1093,9 @@ static __init int svm_hardware_setup(void) pr_info("LBR virtualization supported\n"); } + if (!pmu) + pr_info("PMU virtualization is disabled\n"); + svm_set_cpu_caps(); /* @@ -1585,12 +1594,27 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_svm(vcpu)->vmcb->save.rflags = rflags; } +static bool svm_get_if_flag(struct kvm_vcpu *vcpu) +{ + struct vmcb *vmcb = to_svm(vcpu)->vmcb; + + return sev_es_guest(vcpu->kvm) + ? vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK + : kvm_get_rflags(vcpu) & X86_EFLAGS_IF; +} + static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { + kvm_register_mark_available(vcpu, reg); + switch (reg) { case VCPU_EXREG_PDPTR: - BUG_ON(!npt_enabled); - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + /* + * When !npt_enabled, mmu->pdptrs[] is already available since + * it is always updated per SDM when moving to CRs. + */ + if (npt_enabled) + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); break; default: KVM_BUG_ON(1, vcpu->kvm); @@ -2508,7 +2532,7 @@ static bool check_selective_cr0_intercepted(struct kvm_vcpu *vcpu, bool ret = false; if (!is_guest_mode(vcpu) || - (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) + (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) return false; cr0 &= ~SVM_CR0_SELECTIVE_MASK; @@ -3568,14 +3592,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) if (!gif_set(svm)) return true; - if (sev_es_guest(vcpu->kvm)) { - /* - * SEV-ES guests to not expose RFLAGS. Use the VMCB interrupt mask - * bit to determine the state of the IF flag. - */ - if (!(vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK)) - return true; - } else if (is_guest_mode(vcpu)) { + if (is_guest_mode(vcpu)) { /* As long as interrupts are being delivered... */ if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) ? !(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF) @@ -3586,7 +3603,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) if (nested_exit_on_intr(svm)) return false; } else { - if (!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF)) + if (!svm_get_if_flag(vcpu)) return true; } @@ -3929,6 +3946,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; } + vcpu->arch.regs_dirty = 0; if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(vcpu); @@ -3963,8 +3981,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); - if (npt_enabled) - kvm_register_clear_available(vcpu, VCPU_EXREG_PDPTR); + vcpu->arch.regs_avail &= ~SVM_REGS_LAZY_LOAD_SET; /* * We need to handle MC intercepts here before the vcpu has a chance to @@ -3994,9 +4011,6 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, hv_track_root_tdp(vcpu, root_hpa); - /* Loading L2's CR3 is handled by enter_svm_guest_mode. */ - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - return; cr3 = vcpu->arch.cr3; } else if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) { cr3 = __sme_set(root_hpa) | kvm_get_active_pcid(vcpu); @@ -4215,7 +4229,7 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, info->intercept == x86_intercept_clts) break; - if (!(vmcb_is_intercept(&svm->nested.ctl, + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0))) break; @@ -4434,7 +4448,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) */ vmcb12 = map.hva; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); unmap_save: @@ -4621,6 +4636,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, + .get_if_flag = svm_get_if_flag, .tlb_flush_all = svm_flush_tlb, .tlb_flush_current = svm_flush_tlb, @@ -4651,7 +4667,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .load_eoi_exitmap = svm_load_eoi_exitmap, .hwapic_irr_update = svm_hwapic_irr_update, .hwapic_isr_update = svm_hwapic_isr_update, - .sync_pir_to_irr = kvm_lapic_find_highest_irr, .apicv_post_state_restore = avic_post_state_restore, .set_tss_addr = svm_set_tss_addr, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5faad3dc10e2..9f153c59f2c8 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -32,6 +32,7 @@ extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; extern bool intercept_smi; +extern bool pmu; /* * Clean bits in VMCB. @@ -79,6 +80,7 @@ struct kvm_sev_info { struct list_head regions_list; /* List of registered regions */ u64 ap_jump_table; /* SEV-ES AP Jump Table address */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ + unsigned long num_mirrored_vms; /* Number of VMs sharing this ASID */ struct misc_cg *misc_cg; /* For misc cgroup accounting */ atomic_t migration_in_progress; }; @@ -104,6 +106,40 @@ struct kvm_vmcb_info { uint64_t asid_generation; }; +struct vmcb_save_area_cached { + u64 efer; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; +}; + +struct vmcb_ctrl_area_cached { + u32 intercepts[MAX_INTERCEPT]; + u16 pause_filter_thresh; + u16 pause_filter_count; + u64 iopm_base_pa; + u64 msrpm_base_pa; + u64 tsc_offset; + u32 asid; + u8 tlb_ctl; + u32 int_ctl; + u32 int_vector; + u32 int_state; + u32 exit_code; + u32 exit_code_hi; + u64 exit_info_1; + u64 exit_info_2; + u32 exit_int_info; + u32 exit_int_info_err; + u64 nested_ctl; + u32 event_inj; + u32 event_inj_err; + u64 nested_cr3; + u64 virt_ext; +}; + struct svm_nested_state { struct kvm_vmcb_info vmcb02; u64 hsave_msr; @@ -119,7 +155,13 @@ struct svm_nested_state { bool nested_run_pending; /* cache for control fields of the guest */ - struct vmcb_control_area ctl; + struct vmcb_ctrl_area_cached ctl; + + /* + * Note: this struct is not kept up-to-date while L2 runs; it is only + * valid within nested_svm_vmrun. + */ + struct vmcb_save_area_cached save; bool initialized; }; @@ -284,6 +326,16 @@ static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_svm, vcpu); } +/* + * Only the PDPTRs are loaded on demand into the shadow MMU. All other + * fields are synchronized in handle_exit, because accessing the VMCB is cheap. + * + * CR3 might be out of date in the VMCB but it is not marked dirty; instead, + * KVM_REQ_LOAD_MMU_PGD is always requested when the cached vcpu->arch.cr3 + * is changed. svm_load_mmu_pgd() then syncs the new CR3 value into the VMCB. + */ +#define SVM_REGS_LAZY_LOAD_SET (1 << VCPU_EXREG_PDPTR) + static inline void vmcb_set_intercept(struct vmcb_control_area *control, u32 bit) { WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); @@ -302,6 +354,12 @@ static inline bool vmcb_is_intercept(struct vmcb_control_area *control, u32 bit) return test_bit(bit, (unsigned long *)&control->intercepts); } +static inline bool vmcb12_is_intercept(struct vmcb_ctrl_area_cached *control, u32 bit) +{ + WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); + return test_bit(bit, (unsigned long *)&control->intercepts); +} + static inline void set_dr_intercepts(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb01.ptr; @@ -454,17 +512,17 @@ static inline bool nested_svm_virtualize_tpr(struct kvm_vcpu *vcpu) static inline bool nested_exit_on_smi(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); } static inline bool nested_exit_on_intr(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); } static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); } int enter_svm_guest_mode(struct kvm_vcpu *vcpu, @@ -493,8 +551,10 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, int nested_svm_exit_special(struct vcpu_svm *svm); void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu); void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier); -void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control); +void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, + struct vmcb_control_area *control); +void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, + struct vmcb_save_area *save); void nested_sync_control_from_vmcb02(struct vcpu_svm *svm); void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm); void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 953b0fcb21ee..92e6f6702f00 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1356,6 +1356,30 @@ TRACE_EVENT(kvm_apicv_update_request, __entry->bit) ); +TRACE_EVENT(kvm_apicv_accept_irq, + TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec), + TP_ARGS(apicid, dm, tm, vec), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( __u16, dm ) + __field( __u16, tm ) + __field( __u8, vec ) + ), + + TP_fast_assign( + __entry->apicid = apicid; + __entry->dm = dm; + __entry->tm = tm; + __entry->vec = vec; + ), + + TP_printk("apicid %x vec %u (%s|%s)", + __entry->apicid, __entry->vec, + __print_symbolic((__entry->dm >> 8 & 0x7), kvm_deliver_mode), + __entry->tm ? "level" : "edge") +); + /* * Tracepoint for AMD AVIC */ diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 4705ad55abb5..c8029b7845b6 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -312,6 +312,15 @@ static inline bool cpu_has_vmx_ept_1g_page(void) return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT; } +static inline int ept_caps_to_lpage_level(u32 ept_caps) +{ + if (ept_caps & VMX_EPT_1GB_PAGE_BIT) + return PG_LEVEL_1G; + if (ept_caps & VMX_EPT_2MB_PAGE_BIT) + return PG_LEVEL_2M; + return PG_LEVEL_4K; +} + static inline bool cpu_has_vmx_ept_ad_bits(void) { return vmx_capability.ept & VMX_EPT_AD_BIT; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1e2f66951566..2f6f465e575f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -269,7 +269,13 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) vmx_sync_vmcs_host_state(vmx, prev); put_cpu(); - vmx_register_cache_reset(vcpu); + vcpu->arch.regs_avail = ~VMX_REGS_LAZY_LOAD_SET; + + /* + * All lazily updated registers will be reloaded from VMCS12 on both + * vmentry and vmexit. + */ + vcpu->arch.regs_dirty = 0; } /* @@ -391,9 +397,11 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, static void nested_ept_new_eptp(struct kvm_vcpu *vcpu) { - kvm_init_shadow_ept_mmu(vcpu, - to_vmx(vcpu)->nested.msrs.ept_caps & - VMX_EPT_EXECUTE_ONLY_BIT, + struct vcpu_vmx *vmx = to_vmx(vcpu); + bool execonly = vmx->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT; + int ept_lpage_level = ept_caps_to_lpage_level(vmx->nested.msrs.ept_caps); + + kvm_init_shadow_ept_mmu(vcpu, execonly, ept_lpage_level, nested_ept_ad_enabled(vcpu), nested_ept_get_eptp(vcpu)); } @@ -591,6 +599,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, int msr; unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; + struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ @@ -598,6 +607,19 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return false; + /* + * MSR bitmap update can be skipped when: + * - MSR bitmap for L1 hasn't changed. + * - Nested hypervisor (L1) is attempting to launch the same L2 as + * before. + * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature + * and tells KVM (L0) there were no changes in MSR bitmap for L2. + */ + if (!vmx->nested.force_msr_bitmap_recalc && evmcs && + evmcs->hv_enlightenments_control.msr_bitmap && + evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) + return true; + if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map)) return false; @@ -664,6 +686,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); + vmx->nested.force_msr_bitmap_recalc = false; + return true; } @@ -1095,7 +1119,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, * must not be dereferenced. */ if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) && - CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { + CC(!load_pdptrs(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_PDPTE; return -EINVAL; } @@ -1104,7 +1128,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ kvm_init_mmu(vcpu); @@ -1162,29 +1186,26 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, WARN_ON(!enable_vpid); /* - * If VPID is enabled and used by vmc12, but L2 does not have a unique - * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate - * a VPID for L2, flush the current context as the effective ASID is - * common to both L1 and L2. - * - * Defer the flush so that it runs after vmcs02.EPTP has been set by - * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid - * redundant flushes further down the nested pipeline. - * - * If a TLB flush isn't required due to any of the above, and vpid12 is - * changing then the new "virtual" VPID (vpid12) will reuse the same - * "real" VPID (vpid02), and so needs to be flushed. There's no direct - * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for - * all nested vCPUs. Remember, a flush on VM-Enter does not invalidate - * guest-physical mappings, so there is no need to sync the nEPT MMU. + * VPID is enabled and in use by vmcs12. If vpid12 is changing, then + * emulate a guest TLB flush as KVM does not track vpid12 history nor + * is the VPID incorporated into the MMU context. I.e. KVM must assume + * that the new vpid12 has never been used and thus represents a new + * guest ASID that cannot have entries in the TLB. */ - if (!nested_has_guest_tlb_tag(vcpu)) { - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } else if (is_vmenter && - vmcs12->virtual_processor_id != vmx->nested.last_vpid) { + if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) { vmx->nested.last_vpid = vmcs12->virtual_processor_id; - vpid_sync_context(nested_get_vpid02(vcpu)); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + return; } + + /* + * If VPID is enabled, used by vmc12, and vpid12 is not changing but + * does not have a unique TLB tag (ASID), i.e. EPT is disabled and + * KVM was unable to allocate a VPID for L2, flush the current context + * as the effective ASID is common to both L1 and L2. + */ + if (!nested_has_guest_tlb_tag(vcpu)) + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) @@ -2024,10 +2045,13 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( * Clean fields data can't be used on VMLAUNCH and when we switch * between different L2 guests as KVM keeps a single VMCS12 per L1. */ - if (from_launch || evmcs_gpa_changed) + if (from_launch || evmcs_gpa_changed) { vmx->nested.hv_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + vmx->nested.force_msr_bitmap_recalc = true; + } + return EVMPTRLD_SUCCEEDED; } @@ -2594,8 +2618,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, - vmcs12->guest_ia32_perf_global_ctrl))) + vmcs12->guest_ia32_perf_global_ctrl))) { + *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; + } kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); @@ -3028,7 +3054,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; + unsigned long cr4; bool vm_fail; if (!nested_early_check) @@ -3051,12 +3077,6 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) */ vmcs_writel(GUEST_RFLAGS, 0); - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } - cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); @@ -3146,7 +3166,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) * the guest CR3 might be restored prior to setting the nested * state which can lead to a load of wrong PDPTRs. */ - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; } @@ -3344,8 +3364,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, }; u32 failed_index; - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); + kvm_service_local_tlb_flush_requests(vcpu); evaluate_pending_interrupts = exec_controls_get(vmx) & (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); @@ -3605,7 +3624,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) && (vmcs12->guest_rflags & X86_EFLAGS_IF))) { vmx->nested.nested_run_pending = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } break; case GUEST_ACTIVITY_WAIT_SIPI: @@ -4502,9 +4521,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, (void)nested_get_evmcs_page(vcpu); } - /* Service the TLB flush request for L2 before switching to L1. */ - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); + /* Service pending TLB flush requests for L2 before switching to L1. */ + kvm_service_local_tlb_flush_requests(vcpu); /* * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between @@ -4857,6 +4875,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) if (!vmx->nested.cached_vmcs12) goto out_cached_vmcs12; + vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA; vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_shadow_vmcs12) goto out_cached_shadow_vmcs12; @@ -5260,6 +5279,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) vmx->nested.need_vmcs12_to_shadow_sync = true; } vmx->nested.dirty_vmcs12 = true; + vmx->nested.force_msr_bitmap_recalc = true; } /* Emulate the VMPTRLD instruction */ @@ -5289,8 +5309,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache; struct vmcs_hdr hdr; - if (ghc->gpa != vmptr && - kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) { + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) { /* * Reads from an unbacked page return all 1s, * which means that the 32 bits located at the @@ -6396,6 +6415,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, goto error_guest_mode; vmx->nested.dirty_vmcs12 = true; + vmx->nested.force_msr_bitmap_recalc = true; ret = nested_vmx_enter_non_root_mode(vcpu, false); if (ret) goto error_guest_mode; diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 5f81ef092bd4..88c53c521094 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -5,15 +5,28 @@ #include <asm/cpu.h> #include "lapic.h" +#include "irq.h" #include "posted_intr.h" #include "trace.h" #include "vmx.h" /* - * We maintain a per-CPU linked-list of vCPU, so in wakeup_handler() we - * can find which vCPU should be waken up. + * Maintain a per-CPU list of vCPUs that need to be awakened by wakeup_handler() + * when a WAKEUP_VECTOR interrupted is posted. vCPUs are added to the list when + * the vCPU is scheduled out and is blocking (e.g. in HLT) with IRQs enabled. + * The vCPUs posted interrupt descriptor is updated at the same time to set its + * notification vector to WAKEUP_VECTOR, so that posted interrupt from devices + * wake the target vCPUs. vCPUs are removed from the list and the notification + * vector is reset when the vCPU is scheduled in. */ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); +/* + * Protect the per-CPU list with a per-CPU spinlock to handle task migration. + * When a blocking vCPU is awakened _and_ migrated to a different pCPU, the + * ->sched_in() path will need to take the vCPU off the list of the _previous_ + * CPU. IRQs must be disabled when taking this lock, otherwise deadlock will + * occur if a wakeup IRQ arrives and attempts to acquire the lock. + */ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) @@ -21,6 +34,20 @@ static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) return &(to_vmx(vcpu)->pi_desc); } +static int pi_try_set_control(struct pi_desc *pi_desc, u64 old, u64 new) +{ + /* + * PID.ON can be set at any time by a different vCPU or by hardware, + * e.g. a device. PID.control must be written atomically, and the + * update must be retried with a fresh snapshot an ON change causes + * the cmpxchg to fail. + */ + if (cmpxchg64(&pi_desc->control, old, new) != old) + return -EBUSY; + + return 0; +} + void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -28,11 +55,14 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) unsigned int dest; /* - * In case of hot-plug or hot-unplug, we may have to undo - * vmx_vcpu_pi_put even if there is no assigned device. And we - * always keep PI.NDST up to date for simplicity: it makes the - * code easier, and CPU migration is not a fast path. + * To simplify hot-plug and dynamic toggling of APICv, keep PI.NDST and + * PI.SN up-to-date even if there is no assigned device or if APICv is + * deactivated due to a dynamic inhibit bit, e.g. for Hyper-V's SyncIC. */ + if (!enable_apicv || !lapic_in_kernel(vcpu)) + return; + + /* Nothing to do if PI.SN and PI.NDST both have the desired value. */ if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; @@ -48,20 +78,17 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) goto after_clear_sn; } - /* The full case. */ - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(cpu); + /* The full case. Set the new destination and clear SN. */ + dest = cpu_physical_id(cpu); + if (!x2apic_mode) + dest = (dest << 8) & 0xFF00; - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + do { + old.control = new.control = READ_ONCE(pi_desc->control); + new.ndst = dest; new.sn = 0; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); + } while (pi_try_set_control(pi_desc, old.control, new.control)); after_clear_sn: @@ -77,13 +104,18 @@ after_clear_sn: pi_set_on(pi_desc); } +static bool vmx_can_use_vtd_pi(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm) && enable_apicv && + kvm_arch_has_assigned_device(kvm) && + irq_remapping_cap(IRQ_POSTING_CAP); +} + void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (!vmx_can_use_vtd_pi(vcpu->kvm)) return; /* Set SN when the vCPU is preempted */ @@ -97,29 +129,31 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) struct pi_desc old, new; unsigned int dest; - do { - old.control = new.control = pi_desc->control; - WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, - "Wakeup handler not enabled while the VCPU is blocked\n"); + /* + * Remove the vCPU from the wakeup list of the _previous_ pCPU, which + * will not be the same as the current pCPU if the task was migrated. + */ + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - dest = cpu_physical_id(vcpu->cpu); + dest = cpu_physical_id(vcpu->cpu); + if (!x2apic_mode) + dest = (dest << 8) & 0xFF00; - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + WARN(pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR, + "Wakeup handler not enabled while the vCPU was blocking"); + + do { + old.control = new.control = READ_ONCE(pi_desc->control); + + new.ndst = dest; /* set 'NV' to 'notification vector' */ new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); - - if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - vcpu->pre_pcpu = -1; - } + } while (pi_try_set_control(pi_desc, old.control, new.control)); + + vcpu->pre_pcpu = -1; } /* @@ -128,7 +162,6 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) * - Store the vCPU to the wakeup list, so when interrupts happen * we can find the right vCPU to wake up. * - Change the Posted-interrupt descriptor as below: - * 'NDST' <-- vcpu->pre_pcpu * 'NV' <-- POSTED_INTR_WAKEUP_VECTOR * - If 'ON' is set during this process, which means at least one * interrupt is posted for this vCPU, we cannot block it, in @@ -137,70 +170,50 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) */ int pi_pre_block(struct kvm_vcpu *vcpu) { - unsigned int dest; struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + unsigned long flags; - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (!vmx_can_use_vtd_pi(vcpu->kvm) || + vmx_interrupt_blocked(vcpu)) return 0; - WARN_ON(irqs_disabled()); - local_irq_disable(); - if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { - vcpu->pre_pcpu = vcpu->cpu; - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - } - - do { - old.control = new.control = pi_desc->control; + local_irq_save(flags); - WARN((pi_desc->sn == 1), - "Warning: SN field of posted-interrupts " - "is set before blocking\n"); + vcpu->pre_pcpu = vcpu->cpu; + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, vcpu->cpu)); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); - /* - * Since vCPU can be preempted during this process, - * vcpu->cpu could be different with pre_pcpu, we - * need to set pre_pcpu as the destination of wakeup - * notification event, then we can find the right vCPU - * to wakeup in wakeup handler if interrupts happen - * when the vCPU is in blocked state. - */ - dest = cpu_physical_id(vcpu->pre_pcpu); + WARN(pi_desc->sn == 1, + "Posted Interrupt Suppress Notification set before blocking"); - if (x2apic_mode) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; + do { + old.control = new.control = READ_ONCE(pi_desc->control); /* set 'NV' to 'wakeup vector' */ new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); + } while (pi_try_set_control(pi_desc, old.control, new.control)); /* We should not block the vCPU if an interrupt is posted for it. */ - if (pi_test_on(pi_desc) == 1) + if (pi_test_on(pi_desc)) __pi_post_block(vcpu); - local_irq_enable(); + local_irq_restore(flags); return (vcpu->pre_pcpu == -1); } void pi_post_block(struct kvm_vcpu *vcpu) { + unsigned long flags; + if (vcpu->pre_pcpu == -1) return; - WARN_ON(irqs_disabled()); - local_irq_disable(); + local_irq_save(flags); __pi_post_block(vcpu); - local_irq_enable(); + local_irq_restore(flags); } /* @@ -216,7 +229,7 @@ void pi_wakeup_handler(void) blocked_vcpu_list) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - if (pi_test_on(pi_desc) == 1) + if (pi_test_on(pi_desc)) kvm_vcpu_kick(vcpu); } spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); @@ -270,9 +283,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, struct vcpu_data vcpu_info; int idx, ret = 0; - if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(kvm->vcpus[0])) + if (!vmx_can_use_vtd_pi(kvm)) return 0; idx = srcu_read_lock(&kvm->irq_srcu); diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 7f7b2326caf5..36ae035f14aa 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -40,7 +40,7 @@ static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } -static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) +static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) { return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } @@ -74,13 +74,13 @@ static inline void pi_clear_sn(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } -static inline int pi_test_on(struct pi_desc *pi_desc) +static inline bool pi_test_on(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); } -static inline int pi_test_sn(struct pi_desc *pi_desc) +static inline bool pi_test_sn(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index ba66c171d951..9bf65e5e4840 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -602,15 +602,13 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, unsigned int slot = msr - vmx->guest_uret_msrs; int ret = 0; - u64 old_msr_data = msr->data; - msr->data = data; if (msr->load_into_hardware) { preempt_disable(); - ret = kvm_set_user_return_msr(slot, msr->data, msr->mask); + ret = kvm_set_user_return_msr(slot, data, msr->mask); preempt_enable(); - if (ret) - msr->data = old_msr_data; } + if (!ret) + msr->data = data; return ret; } @@ -1105,6 +1103,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); #endif + unsigned long cr3; unsigned long fs_base, gs_base; u16 fs_sel, gs_sel; int i; @@ -1169,6 +1168,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) #endif vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); + + /* Host CR3 including its PCID is stable when guest state is loaded. */ + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != host_state->cr3)) { + vmcs_writel(HOST_CR3, cr3); + host_state->cr3 = cr3; + } + vmx->guest_state_loaded = true; } @@ -1271,7 +1278,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, if (!already_loaded) { void *gdt = get_current_gdt_ro(); - unsigned long sysenter_esp; /* * Flush all EPTP/VPID contexts, the new pCPU may have stale @@ -1287,8 +1293,11 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ - rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); - vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ + if (IS_ENABLED(CONFIG_IA32_EMULATION) || IS_ENABLED(CONFIG_X86_32)) { + /* 22.2.3 */ + vmcs_writel(HOST_IA32_SYSENTER_ESP, + (unsigned long)(cpu_entry_stack(cpu) + 1)); + } vmx->loaded_vmcs->cpu = cpu; } @@ -1363,6 +1372,11 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmx->emulation_required = vmx_emulation_required(vcpu); } +static bool vmx_get_if_flag(struct kvm_vcpu *vcpu) +{ + return vmx_get_rflags(vcpu) & X86_EFLAGS_IF; +} + u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) { u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); @@ -1748,7 +1762,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) } /* - * Reads an msr value (of 'msr_index') into 'pdata'. + * Reads an msr value (of 'msr_info->index') into 'msr_info->data'. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ @@ -2095,9 +2109,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } ret = kvm_set_msr_common(vcpu, msr_info); break; - case MSR_IA32_TSC_ADJUST: - ret = kvm_set_msr_common(vcpu, msr_info); - break; case MSR_IA32_MCG_EXT_CTL: if ((!msr_info->host_initiated && !(to_vmx(vcpu)->msr_ia32_feature_control & @@ -2646,15 +2657,6 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) if (!loaded_vmcs->msr_bitmap) goto out_vmcs; memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); - - if (IS_ENABLED(CONFIG_HYPERV) && - static_branch_unlikely(&enable_evmcs) && - (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { - struct hv_enlightened_vmcs *evmcs = - (struct hv_enlightened_vmcs *)loaded_vmcs->vmcs; - - evmcs->hv_enlightenments_control.msr_bitmap = 1; - } } memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); @@ -2918,6 +2920,13 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) } } +static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) +{ + if (is_guest_mode(vcpu)) + return nested_get_vpid02(vcpu); + return to_vmx(vcpu)->vpid; +} + static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; @@ -2930,31 +2939,29 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) if (enable_ept) ept_sync_context(construct_eptp(vcpu, root_hpa, mmu->shadow_root_level)); - else if (!is_guest_mode(vcpu)) - vpid_sync_context(to_vmx(vcpu)->vpid); else - vpid_sync_context(nested_get_vpid02(vcpu)); + vpid_sync_context(vmx_get_current_vpid(vcpu)); } static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { /* - * vpid_sync_vcpu_addr() is a nop if vmx->vpid==0, see the comment in + * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in * vmx_flush_tlb_guest() for an explanation of why this is ok. */ - vpid_sync_vcpu_addr(to_vmx(vcpu)->vpid, addr); + vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr); } static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) { /* - * vpid_sync_context() is a nop if vmx->vpid==0, e.g. if enable_vpid==0 - * or a vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit - * are required to flush GVA->{G,H}PA mappings from the TLB if vpid is + * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a + * vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit are + * required to flush GVA->{G,H}PA mappings from the TLB if vpid is * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed), * i.e. no explicit INVVPID is necessary. */ - vpid_sync_context(to_vmx(vcpu)->vpid); + vpid_sync_context(vmx_get_current_vpid(vcpu)); } void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu) @@ -2984,7 +2991,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); - kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_register_mark_available(vcpu, VCPU_EXREG_PDPTR); } #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ @@ -3109,9 +3116,9 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; - else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + else if (kvm_register_is_dirty(vcpu, VCPU_EXREG_CR3)) guest_cr3 = vcpu->arch.cr3; - else /* vmcs01.GUEST_CR3 is already up-to-date. */ + else /* vmcs.GUEST_CR3 is already up-to-date. */ update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { @@ -3686,6 +3693,19 @@ void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } +static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) +{ + /* + * When KVM is a nested hypervisor on top of Hyper-V and uses + * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR + * bitmap has changed. + */ + if (static_branch_unlikely(&enable_evmcs)) + evmcs_touch_msr_bitmap(); + + vmx->nested.force_msr_bitmap_recalc = true; +} + void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3694,8 +3714,7 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) if (!cpu_has_vmx_msr_bitmap()) return; - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed @@ -3739,8 +3758,7 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) if (!cpu_has_vmx_msr_bitmap()) return; - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed @@ -3930,6 +3948,19 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); + + /* + * This pairs with the smp_mb_*() after setting vcpu->mode in + * vcpu_enter_guest() to guarantee the vCPU sees the event + * request if triggering a posted interrupt "fails" because + * vcpu->mode != IN_GUEST_MODE. The extra barrier is needed as + * the smb_wmb() in kvm_make_request() only ensures everything + * done before making the request is visible when the request + * is visible, it doesn't ensure ordering between the store to + * vcpu->requests and the load from vcpu->mode. + */ + smp_mb__after_atomic(); + /* the PIR and ON have been set by L1. */ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true)) kvm_vcpu_kick(vcpu); @@ -3963,8 +3994,13 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_on(&vmx->pi_desc)) return 0; - if (vcpu != kvm_get_running_vcpu() && - !kvm_vcpu_trigger_posted_interrupt(vcpu, false)) + /* + * The implied barrier in pi_test_and_set_on() pairs with the smp_mb_*() + * after setting vcpu->mode in vcpu_enter_guest(), thus the vCPU is + * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a + * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE. + */ + if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); return 0; @@ -4021,6 +4057,12 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) rdmsr(MSR_IA32_SYSENTER_CS, low32, high32); vmcs_write32(HOST_IA32_SYSENTER_CS, low32); + + /* + * If 32-bit syscall is enabled, vmx_vcpu_load_vcms rewrites + * HOST_IA32_SYSENTER_ESP. + */ + vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ @@ -4039,8 +4081,10 @@ void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) vcpu->arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS & ~vcpu->arch.cr4_guest_rsvd_bits; - if (!enable_ept) - vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PGE; + if (!enable_ept) { + vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_TLBFLUSH_BITS; + vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PDPTR_BITS; + } if (is_guest_mode(&vmx->vcpu)) vcpu->arch.cr4_guest_owned_bits &= ~get_vmcs12(vcpu)->cr4_guest_host_mask; @@ -4692,7 +4736,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, if (kvm_emulate_instruction(vcpu, 0)) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } return 1; } @@ -5363,7 +5407,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } /* @@ -5881,18 +5925,14 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) vmx_flush_pml_buffer(vcpu); /* - * We should never reach this point with a pending nested VM-Enter, and - * more specifically emulation of L2 due to invalid guest state (see - * below) should never happen as that means we incorrectly allowed a - * nested VM-Enter with an invalid vmcs12. + * KVM should never reach this point with a pending nested VM-Enter. + * More specifically, short-circuiting VM-Entry to emulate L2 due to + * invalid guest state should never happen as that means KVM knowingly + * allowed a nested VM-Enter with an invalid vmcs12. More below. */ if (KVM_BUG_ON(vmx->nested.nested_run_pending, vcpu->kvm)) return -EIO; - /* If guest state is invalid, start emulating */ - if (vmx->emulation_required) - return handle_invalid_guest_state(vcpu); - if (is_guest_mode(vcpu)) { /* * PML is never enabled when running L2, bail immediately if a @@ -5914,10 +5954,30 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) */ nested_mark_vmcs12_pages_dirty(vcpu); + /* + * Synthesize a triple fault if L2 state is invalid. In normal + * operation, nested VM-Enter rejects any attempt to enter L2 + * with invalid state. However, those checks are skipped if + * state is being stuffed via RSM or KVM_SET_NESTED_STATE. If + * L2 state is invalid, it means either L1 modified SMRAM state + * or userspace provided bad state. Synthesize TRIPLE_FAULT as + * doing so is architecturally allowed in the RSM case, and is + * the least awful solution for the userspace case without + * risking false positives. + */ + if (vmx->emulation_required) { + nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); + return 1; + } + if (nested_vmx_reflect_vmexit(vcpu)) return 1; } + /* If guest state is invalid, start emulating. L2 is handled above. */ + if (vmx->emulation_required) + return handle_invalid_guest_state(vcpu); + if (exit_reason.failed_vmentry) { dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; @@ -6262,9 +6322,9 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; - bool max_irr_updated; + bool got_posted_interrupt; - if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm)) + if (KVM_BUG_ON(!enable_apicv, vcpu->kvm)) return -EIO; if (pi_test_on(&vmx->pi_desc)) { @@ -6274,22 +6334,33 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); - max_irr_updated = + got_posted_interrupt = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr); - - /* - * If we are running L2 and L1 has a new pending interrupt - * which can be injected, this may cause a vmexit or it may - * be injected into L2. Either way, this interrupt will be - * processed via KVM_REQ_EVENT, not RVI, because we do not use - * virtual interrupt delivery to inject L1 interrupts into L2. - */ - if (is_guest_mode(vcpu) && max_irr_updated) - kvm_make_request(KVM_REQ_EVENT, vcpu); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); + got_posted_interrupt = false; } - vmx_hwapic_irr_update(vcpu, max_irr); + + /* + * Newly recognized interrupts are injected via either virtual interrupt + * delivery (RVI) or KVM_REQ_EVENT. Virtual interrupt delivery is + * disabled in two cases: + * + * 1) If L2 is running and the vCPU has a new pending interrupt. If L1 + * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a + * VM-Exit to L1. If L1 doesn't want to exit, the interrupt is injected + * into L2, but KVM doesn't use virtual interrupt delivery to inject + * interrupts into L2, and so KVM_REQ_EVENT is again needed. + * + * 2) If APICv is disabled for this vCPU, assigned devices may still + * attempt to post interrupts. The posted interrupt vector will cause + * a VM-Exit and the subsequent entry will call sync_pir_to_irr. + */ + if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu)) + vmx_set_rvi(max_irr); + else if (got_posted_interrupt) + kvm_make_request(KVM_REQ_EVENT, vcpu); + return max_irr; } @@ -6588,7 +6659,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; + unsigned long cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -6601,9 +6672,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) * consistency check VM-Exit due to invalid guest state and bail. */ if (unlikely(vmx->emulation_required)) { - - /* We don't emulate invalid state of a nested guest */ - vmx->fail = is_guest_mode(vcpu); + vmx->fail = 0; vmx->exit_reason.full = EXIT_REASON_INVALID_STATE; vmx->exit_reason.failed_vmentry = 1; @@ -6631,12 +6700,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); - - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } + vcpu->arch.regs_dirty = 0; cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { @@ -6725,7 +6789,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) loadsegment(es, __USER_DS); #endif - vmx_register_cache_reset(vcpu); + vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET; pt_guest_exit(vmx); @@ -6826,6 +6890,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) if (err < 0) goto free_pml; + /* + * Use Hyper-V 'Enlightened MSR Bitmap' feature when KVM runs as a + * nested (L1) hypervisor and Hyper-V in L0 supports it. Enable the + * feature only for vmcs01, KVM currently isn't equipped to realize any + * performance benefits from enabling it for vmcs02. + */ + if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) && + (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; + + evmcs->hv_enlightenments_control.msr_bitmap = 1; + } + /* The MSR bitmap starts with all ones */ bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS); bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS); @@ -6931,7 +7008,6 @@ static int __init vmx_check_processor_compat(void) static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { u8 cache; - u64 ipat = 0; /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in * memory aliases with conflicting memory types and sometimes MCEs. @@ -6951,30 +7027,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) * EPT memory type is used to emulate guest CD/MTRR. */ - if (is_mmio) { - cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } + if (is_mmio) + return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { - ipat = VMX_EPT_IPAT_BIT; - cache = MTRR_TYPE_WRBACK; - goto exit; - } + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) + return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; if (kvm_read_cr0(vcpu) & X86_CR0_CD) { - ipat = VMX_EPT_IPAT_BIT; if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) cache = MTRR_TYPE_WRBACK; else cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } - cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn); + return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; + } -exit: - return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; + return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; } static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl) @@ -7509,6 +7577,7 @@ static void hardware_unsetup(void) static bool vmx_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_BLOCKIRQ); @@ -7558,6 +7627,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, + .get_if_flag = vmx_get_if_flag, .tlb_flush_all = vmx_flush_tlb_all, .tlb_flush_current = vmx_flush_tlb_current, @@ -7683,7 +7753,7 @@ static __init int hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; - int r, ept_lpage_level; + int r; store_idt(&dt); host_idt_base = dt.address; @@ -7761,10 +7831,10 @@ static __init int hardware_setup(void) ple_window_shrink = 0; } - if (!cpu_has_vmx_apicv()) { + if (!cpu_has_vmx_apicv()) enable_apicv = 0; + if (!enable_apicv) vmx_x86_ops.sync_pir_to_irr = NULL; - } if (cpu_has_vmx_tsc_scaling()) { kvm_has_tsc_control = true; @@ -7780,16 +7850,8 @@ static __init int hardware_setup(void) kvm_mmu_set_ept_masks(enable_ept_ad_bits, cpu_has_vmx_ept_execute_only()); - if (!enable_ept) - ept_lpage_level = 0; - else if (cpu_has_vmx_ept_1g_page()) - ept_lpage_level = PG_LEVEL_1G; - else if (cpu_has_vmx_ept_2m_page()) - ept_lpage_level = PG_LEVEL_2M; - else - ept_lpage_level = PG_LEVEL_4K; kvm_configure_mmu(enable_ept, 0, vmx_get_max_tdp_level(), - ept_lpage_level); + ept_caps_to_lpage_level(vmx_capability.ept)); /* * Only enable PML when hardware supports PML feature, and both EPT diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 4df2ac24ffc1..6c2c1aff1c3d 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -159,6 +159,15 @@ struct nested_vmx { bool dirty_vmcs12; /* + * Indicates whether MSR bitmap for L2 needs to be rebuilt due to + * changes in MSR bitmap for L1 or switching to a different L2. Note, + * this flag can only be used reliably in conjunction with a paravirt L1 + * which informs L0 whether any changes to MSR bitmap for L2 were done + * on its side. + */ + bool force_msr_bitmap_recalc; + + /* * Indicates lazily loaded guest state has not yet been decached from * vmcs02. */ @@ -473,19 +482,21 @@ BUILD_CONTROLS_SHADOW(pin, PIN_BASED_VM_EXEC_CONTROL) BUILD_CONTROLS_SHADOW(exec, CPU_BASED_VM_EXEC_CONTROL) BUILD_CONTROLS_SHADOW(secondary_exec, SECONDARY_VM_EXEC_CONTROL) -static inline void vmx_register_cache_reset(struct kvm_vcpu *vcpu) -{ - vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) - | (1 << VCPU_EXREG_RFLAGS) - | (1 << VCPU_EXREG_PDPTR) - | (1 << VCPU_EXREG_SEGMENTS) - | (1 << VCPU_EXREG_CR0) - | (1 << VCPU_EXREG_CR3) - | (1 << VCPU_EXREG_CR4) - | (1 << VCPU_EXREG_EXIT_INFO_1) - | (1 << VCPU_EXREG_EXIT_INFO_2)); - vcpu->arch.regs_dirty = 0; -} +/* + * VMX_REGS_LAZY_LOAD_SET - The set of registers that will be updated in the + * cache on demand. Other registers not listed here are synced to + * the cache immediately after VM-Exit. + */ +#define VMX_REGS_LAZY_LOAD_SET ((1 << VCPU_REGS_RIP) | \ + (1 << VCPU_REGS_RSP) | \ + (1 << VCPU_EXREG_RFLAGS) | \ + (1 << VCPU_EXREG_PDPTR) | \ + (1 << VCPU_EXREG_SEGMENTS) | \ + (1 << VCPU_EXREG_CR0) | \ + (1 << VCPU_EXREG_CR3) | \ + (1 << VCPU_EXREG_CR4) | \ + (1 << VCPU_EXREG_EXIT_INFO_1) | \ + (1 << VCPU_EXREG_EXIT_INFO_2)) static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5a403d92833f..8912f44c640d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -118,6 +118,7 @@ static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); +static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu); static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); @@ -710,6 +711,17 @@ int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) } EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); +static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err) +{ + if (err) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE | EMULTYPE_SKIP | + EMULTYPE_COMPLETE_USER_EXIT); +} + void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; @@ -798,8 +810,9 @@ static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) /* * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ -int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; gpa_t real_gpa; int i; @@ -810,8 +823,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) * If the MMU is nested, CR3 holds an L2 GPA and needs to be translated * to an L1 GPA. */ - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(pdpt_gfn), - PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(pdpt_gfn), + PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); if (real_gpa == UNMAPPED_GVA) return 0; @@ -828,8 +841,12 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } } - memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); - kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_register_mark_available(vcpu, VCPU_EXREG_PDPTR); + if (memcmp(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs))) { + memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); + } vcpu->arch.pdptrs_from_userspace = false; return 1; @@ -856,7 +873,6 @@ EXPORT_SYMBOL_GPL(kvm_post_set_cr0); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); - unsigned long pdptr_bits = X86_CR0_CD | X86_CR0_NW | X86_CR0_PG; cr0 |= X86_CR0_ET; @@ -886,11 +902,12 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } #endif if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) && - is_pae(vcpu) && ((cr0 ^ old_cr0) & pdptr_bits) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu))) + is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS) && + !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; - if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + if (!(cr0 & X86_CR0_PG) && + (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))) return 1; static_call(kvm_x86_set_cr0)(vcpu, cr0); @@ -1050,8 +1067,6 @@ EXPORT_SYMBOL_GPL(kvm_post_set_cr4); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP; if (!kvm_is_valid_cr4(vcpu, cr4)) return 1; @@ -1062,9 +1077,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if ((cr4 ^ old_cr4) & X86_CR4_LA57) return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) - && ((cr4 ^ old_cr4) & pdptr_bits) - && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, - kvm_read_cr3(vcpu))) + && ((cr4 ^ old_cr4) & X86_CR4_PDPTR_BITS) + && !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { @@ -1153,14 +1167,14 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) return 1; - if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) return 1; if (cr3 != kvm_read_cr3(vcpu)) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); handle_tlb_flush: /* @@ -1330,7 +1344,7 @@ static const u32 msrs_to_save_all[] = { MSR_IA32_UMWAIT_CONTROL, MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, - MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3, + MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL, MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, @@ -1814,22 +1828,36 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) } EXPORT_SYMBOL_GPL(kvm_set_msr); -static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu) { - int err = vcpu->run->msr.error; - if (!err) { + if (!vcpu->run->msr.error) { kvm_rax_write(vcpu, (u32)vcpu->run->msr.data); kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32); } +} + +static int complete_emulated_msr_access(struct kvm_vcpu *vcpu) +{ + return complete_emulated_insn_gp(vcpu, vcpu->run->msr.error); +} - return static_call(kvm_x86_complete_emulated_msr)(vcpu, err); +static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_emulated_msr_access(vcpu); } -static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) +static int complete_fast_msr_access(struct kvm_vcpu *vcpu) { return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error); } +static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_fast_msr_access(vcpu); +} + static u64 kvm_msr_reason(int r) { switch (r) { @@ -1864,18 +1892,6 @@ static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index, return 1; } -static int kvm_get_msr_user_space(struct kvm_vcpu *vcpu, u32 index, int r) -{ - return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_RDMSR, 0, - complete_emulated_rdmsr, r); -} - -static int kvm_set_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u64 data, int r) -{ - return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_WRMSR, data, - complete_emulated_wrmsr, r); -} - int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = kvm_rcx_read(vcpu); @@ -1884,18 +1900,16 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) r = kvm_get_msr(vcpu, ecx, &data); - /* MSR read failed? See if we should ask user space */ - if (r && kvm_get_msr_user_space(vcpu, ecx, r)) { - /* Bounce to user space */ - return 0; - } - if (!r) { trace_kvm_msr_read(ecx, data); kvm_rax_write(vcpu, data & -1u); kvm_rdx_write(vcpu, (data >> 32) & -1u); } else { + /* MSR read failed? See if we should ask user space */ + if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_RDMSR, 0, + complete_fast_rdmsr, r)) + return 0; trace_kvm_msr_read_ex(ecx); } @@ -1911,19 +1925,18 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) r = kvm_set_msr(vcpu, ecx, data); - /* MSR write failed? See if we should ask user space */ - if (r && kvm_set_msr_user_space(vcpu, ecx, data, r)) - /* Bounce to user space */ - return 0; - - /* Signal all other negative errors to userspace */ - if (r < 0) - return r; - - if (!r) + if (!r) { trace_kvm_msr_write(ecx, data); - else + } else { + /* MSR write failed? See if we should ask user space */ + if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_WRMSR, data, + complete_fast_msr_access, r)) + return 0; + /* Signal all other negative errors to userspace */ + if (r < 0) + return r; trace_kvm_msr_write_ex(ecx, data); + } return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } @@ -2816,7 +2829,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct kvm_vcpu *vcpu; - int i; + unsigned long i; write_seqcount_end(&ka->pvclock_sc); raw_spin_unlock_irq(&ka->tsc_write_lock); @@ -3065,7 +3078,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) static void kvmclock_update_fn(struct work_struct *work) { - int i; + unsigned long i; struct delayed_work *dwork = to_delayed_work(work); struct kvm_arch *ka = container_of(dwork, struct kvm_arch, kvmclock_update_work); @@ -3258,6 +3271,29 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) static_call(kvm_x86_tlb_flush_guest)(vcpu); } + +static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.tlb_flush; + static_call(kvm_x86_tlb_flush_current)(vcpu); +} + +/* + * Service "local" TLB flush requests, which are specific to the current MMU + * context. In addition to the generic event handling in vcpu_enter_guest(), + * TLB flushes that are targeted at an MMU context also need to be serviced + * prior before nested VM-Enter/VM-Exit. + */ +void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu) +{ + if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) + kvm_vcpu_flush_tlb_current(vcpu); + + if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) + kvm_vcpu_flush_tlb_guest(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests); + static void record_steal_time(struct kvm_vcpu *vcpu) { struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; @@ -3389,7 +3425,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated) return 1; - if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM) && kvm_get_msr_feature(&msr_ent)) + if (kvm_get_msr_feature(&msr_ent)) return 1; if (data & ~msr_ent.data) return 1; @@ -4133,6 +4169,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SGX_ATTRIBUTE: #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: + case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: @@ -4448,8 +4485,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); return kvm_apic_get_state(vcpu, s); } @@ -5124,6 +5160,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; + /* + * KVM does not correctly handle changing guest CPUID after KVM_RUN, as + * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't + * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page + * faults due to reusing SPs/SPTEs. In practice no sane VMM mucks with + * the core vCPU model on the fly, so fail. + */ + r = -EINVAL; + if (vcpu->arch.last_vmentry_cpu != -1) + goto out; + r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; @@ -5134,6 +5181,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; + /* + * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in + * KVM_SET_CPUID case above. + */ + r = -EINVAL; + if (vcpu->arch.last_vmentry_cpu != -1) + goto out; + r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; @@ -5650,7 +5705,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) * VM-Exit. */ struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); @@ -5698,6 +5753,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; + kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); r = 0; split_irqchip_unlock: mutex_unlock(&kvm->lock); @@ -5918,7 +5974,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) static int kvm_arch_suspend_notifier(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, ret = 0; + unsigned long i; + int ret = 0; mutex_lock(&kvm->lock); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -6078,6 +6135,7 @@ set_identity_unlock: /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; + kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -6460,13 +6518,14 @@ void kvm_get_segment(struct kvm_vcpu *vcpu, gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.mmu; gpa_t t_gpa; BUG_ON(!mmu_is_nested(vcpu)); /* NPT walks are always user-walks */ access |= PFERR_USER_MASK; - t_gpa = vcpu->arch.mmu->gva_to_gpa(vcpu, gpa, access, exception); + t_gpa = mmu->gva_to_gpa(vcpu, mmu, gpa, access, exception); return t_gpa; } @@ -6474,25 +6533,31 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_FETCH_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); @@ -6500,19 +6565,21 @@ EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, exception); + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + + return mmu->gva_to_gpa(vcpu, mmu, gva, 0, exception); } static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -6540,13 +6607,14 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; /* Inline kvm_read_guest_virt_helper for speed. */ - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access|PFERR_FETCH_MASK, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access|PFERR_FETCH_MASK, + exception); if (unlikely(gpa == UNMAPPED_GVA)) return X86EMUL_PROPAGATE_FAULT; @@ -6605,13 +6673,12 @@ static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes struct kvm_vcpu *vcpu, u32 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, - access, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -6698,6 +6765,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u32 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); @@ -6715,7 +6783,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, return 1; } - *gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + *gpa = mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); if (*gpa == UNMAPPED_GVA) return -1; @@ -7077,7 +7145,13 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port, void *val, unsigned int count) { if (vcpu->arch.pio.count) { - /* Complete previous iteration. */ + /* + * Complete a previous iteration that required userspace I/O. + * Note, @count isn't guaranteed to match pio.count as userspace + * can modify ECX before rerunning the vCPU. Ignore any such + * shenanigans as KVM doesn't support modifying the rep count, + * and the emulator ensures @count doesn't overflow the buffer. + */ } else { int r = __emulator_pio_in(vcpu, size, port, count); if (!r) @@ -7086,7 +7160,6 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, /* Results already available, fall through. */ } - WARN_ON(count != vcpu->arch.pio.count); complete_emulator_pio_in(vcpu, val); return 1; } @@ -7344,7 +7417,8 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, r = kvm_get_msr(vcpu, msr_index, pdata); - if (r && kvm_get_msr_user_space(vcpu, msr_index, r)) { + if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, + complete_emulated_rdmsr, r)) { /* Bounce to user space */ return X86EMUL_IO_NEEDED; } @@ -7360,7 +7434,8 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, r = kvm_set_msr(vcpu, msr_index, data); - if (r && kvm_set_msr_user_space(vcpu, msr_index, data, r)) { + if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, + complete_emulated_msr_access, r)) { /* Bounce to user space */ return X86EMUL_IO_NEEDED; } @@ -8078,12 +8153,23 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } /* - * Note, EMULTYPE_SKIP is intended for use *only* by vendor callbacks - * for kvm_skip_emulated_instruction(). The caller is responsible for - * updating interruptibility state and injecting single-step #DBs. + * EMULTYPE_SKIP without EMULTYPE_COMPLETE_USER_EXIT is intended for + * use *only* by vendor callbacks for kvm_skip_emulated_instruction(). + * The caller is responsible for updating interruptibility state and + * injecting single-step #DBs. */ if (emulation_type & EMULTYPE_SKIP) { - kvm_rip_write(vcpu, ctxt->_eip); + if (ctxt->mode != X86EMUL_MODE_PROT64) + ctxt->eip = (u32)ctxt->_eip; + else + ctxt->eip = ctxt->_eip; + + if (emulation_type & EMULTYPE_COMPLETE_USER_EXIT) { + r = 1; + goto writeback; + } + + kvm_rip_write(vcpu, ctxt->eip); if (ctxt->eflags & X86_EFLAGS_RF) kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); return 1; @@ -8147,11 +8233,15 @@ restart: writeback = false; r = 0; vcpu->arch.complete_userspace_io = complete_emulated_mmio; + } else if (vcpu->arch.complete_userspace_io) { + writeback = false; + r = 0; } else if (r == EMULATION_RESTART) goto restart; else r = 1; +writeback: if (writeback) { unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); @@ -8344,7 +8434,8 @@ static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i, send_ipi = 0; + int send_ipi = 0; + unsigned long i; /* * We allow guests to temporarily run on slowing clocks, @@ -8517,9 +8608,8 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { static void pvclock_gtod_update_fn(struct work_struct *work) { struct kvm *kvm; - struct kvm_vcpu *vcpu; - int i; + unsigned long i; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) @@ -8680,8 +8770,15 @@ void kvm_arch_exit(void) #endif } -static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) +static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { + /* + * The vCPU has halted, e.g. executed HLT. Update the run state if the + * local APIC is in-kernel, the run loop will detect the non-runnable + * state and halt the vCPU. Exit to userspace if the local APIC is + * managed by userspace, in which case userspace is responsible for + * handling wake events. + */ ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { vcpu->arch.mp_state = state; @@ -8692,11 +8789,11 @@ static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) } } -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) { - return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); } -EXPORT_SYMBOL_GPL(kvm_vcpu_halt); +EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); int kvm_emulate_halt(struct kvm_vcpu *vcpu) { @@ -8705,7 +8802,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered * KVM_EXIT_DEBUG here. */ - return kvm_vcpu_halt(vcpu) && ret; + return kvm_emulate_halt_noskip(vcpu) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_halt); @@ -8713,7 +8810,8 @@ int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) { int ret = kvm_skip_emulated_instruction(vcpu); - return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, + KVM_EXIT_AP_RESET_HOLD) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); @@ -8776,10 +8874,9 @@ static void kvm_apicv_init(struct kvm *kvm) { init_rwsem(&kvm->arch.apicv_update_lock); - if (enable_apicv) - clear_bit(APICV_INHIBIT_REASON_DISABLE, - &kvm->arch.apicv_inhibit_reasons); - else + set_bit(APICV_INHIBIT_REASON_ABSENT, + &kvm->arch.apicv_inhibit_reasons); + if (!enable_apicv) set_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); } @@ -8952,14 +9049,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - /* - * if_flag is obsolete and useless, so do not bother - * setting it for SEV-ES guests. Userspace can just - * use kvm_run->ready_for_interrupt_injection. - */ - kvm_run->if_flag = !vcpu->arch.guest_state_protected - && (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - + kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu); kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); @@ -9528,8 +9618,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -9648,10 +9737,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* Flushing all ASIDs flushes the current ASID... */ kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); - if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) - kvm_vcpu_flush_tlb_guest(vcpu); + kvm_service_local_tlb_flush_requests(vcpu); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -9802,10 +9888,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* * This handles the case where a posted interrupt was - * notified with kvm_vcpu_kick. + * notified with kvm_vcpu_kick. Assigned devices can + * use the POSTED_INTR_VECTOR even if APICv is disabled, + * so do it even if APICv is disabled on this vCPU. */ - if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + if (kvm_lapic_enabled(vcpu)) + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; @@ -9849,8 +9937,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + if (kvm_lapic_enabled(vcpu)) + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (unlikely(kvm_vcpu_exit_request(vcpu))) { exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; @@ -9956,7 +10044,10 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) if (!kvm_arch_vcpu_runnable(vcpu) && (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); + if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) + kvm_vcpu_halt(vcpu); + else + kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (kvm_x86_ops.post_block) @@ -10516,7 +10607,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, vcpu->arch.cr2 = sregs->cr2; *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); kvm_set_cr8(vcpu, sregs->cr8); @@ -10533,7 +10624,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, if (update_pdptrs) { idx = srcu_read_lock(&vcpu->kvm->srcu); if (is_pae_paging(vcpu)) { - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); *mmu_reset_needed = 1; } srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -10631,7 +10722,7 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) { bool inhibit = false; struct kvm_vcpu *vcpu; - int i; + unsigned long i; down_write(&kvm->arch.apicv_update_lock); @@ -11119,7 +11210,7 @@ int kvm_arch_hardware_enable(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; int ret; u64 local_tsc; u64 max_tsc = 0; @@ -11372,7 +11463,7 @@ static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) static void kvm_free_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; /* @@ -11382,15 +11473,8 @@ static void kvm_free_vcpus(struct kvm *kvm) kvm_clear_async_pf_completion_queue(vcpu); kvm_unload_vcpu_mmu(vcpu); } - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); - mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - mutex_unlock(&kvm->lock); + kvm_destroy_vcpus(kvm); } void kvm_arch_sync_events(struct kvm *kvm) @@ -11558,9 +11642,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages) } static int kvm_alloc_memslot_metadata(struct kvm *kvm, - struct kvm_memory_slot *slot, - unsigned long npages) + struct kvm_memory_slot *slot) { + unsigned long npages = slot->npages; int i, r; /* @@ -11625,7 +11709,7 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; /* * memslots->generation has been incremented. @@ -11639,13 +11723,18 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) - return kvm_alloc_memslot_metadata(kvm, memslot, - mem->memory_size >> PAGE_SHIFT); + return kvm_alloc_memslot_metadata(kvm, new); + + if (change == KVM_MR_FLAGS_ONLY) + memcpy(&new->arch, &old->arch, sizeof(old->arch)); + else if (WARN_ON_ONCE(change != KVM_MR_DELETE)) + return -EIO; + return 0; } @@ -11669,13 +11758,15 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - bool log_dirty_pages = new->flags & KVM_MEM_LOG_DIRTY_PAGES; + u32 old_flags = old ? old->flags : 0; + u32 new_flags = new ? new->flags : 0; + bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES; /* * Update CPU dirty logging if dirty logging is being toggled. This * applies to all operations. */ - if ((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES) + if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages); /* @@ -11693,7 +11784,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot(). */ - if ((change != KVM_MR_FLAGS_ONLY) || (new->flags & KVM_MEM_READONLY)) + if ((change != KVM_MR_FLAGS_ONLY) || (new_flags & KVM_MEM_READONLY)) return; /* @@ -11701,7 +11792,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty * logging isn't being toggled on or off. */ - if (WARN_ON_ONCE(!((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES))) + if (WARN_ON_ONCE(!((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES))) return; if (!log_dirty_pages) { @@ -11737,14 +11828,18 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (!kvm->arch.n_requested_mmu_pages) - kvm_mmu_change_mmu_pages(kvm, - kvm_mmu_calculate_default_mmu_pages(kvm)); + if (!kvm->arch.n_requested_mmu_pages && + (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { + unsigned long nr_mmu_pages; + + nr_mmu_pages = kvm->nr_memslot_pages / KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO; + nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); + kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + } kvm_mmu_slot_apply_flags(kvm, old, new, change); @@ -12254,12 +12349,13 @@ EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; struct x86_exception fault; u32 access = error_code & (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || - vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) { + mmu->gva_to_gpa(vcpu, mmu, gva, access, &fault) != UNMAPPED_GVA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed @@ -12596,6 +12692,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_accept_irq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 997669ae9caa..4abcd8d9836d 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -103,6 +103,7 @@ static inline unsigned int __shrink_ple_window(unsigned int val, #define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL +void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) @@ -185,12 +186,6 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; } -static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.tlb_flush; - static_call(kvm_x86_tlb_flush_current)(vcpu); -} - static inline int is_pae(struct kvm_vcpu *vcpu) { return kvm_read_cr4_bits(vcpu, X86_CR4_PAE); diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 4a3da7592b99..38d24d2ab38b 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -72,6 +72,7 @@ static void __init setup_real_mode(void) #ifdef CONFIG_X86_64 u64 *trampoline_pgd; u64 efer; + int i; #endif base = (unsigned char *)real_mode_header; @@ -128,8 +129,17 @@ static void __init setup_real_mode(void) trampoline_header->flags = 0; trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); + + /* Map the real mode stub as virtual == physical */ trampoline_pgd[0] = trampoline_pgd_entry.pgd; - trampoline_pgd[511] = init_top_pgt[511].pgd; + + /* + * Include the entirety of the kernel mapping into the trampoline + * PGD. This way, all mappings present in the normal kernel page + * tables are usable while running on trampoline_pgd. + */ + for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++) + trampoline_pgd[i] = init_top_pgt[i].pgd; #endif sme_sev_setup_real_mode(trampoline_header); diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 220dd9678494..444d824775f6 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <../entry/calling.h> .pushsection .noinstr.text, "ax" /* @@ -193,6 +194,25 @@ SYM_CODE_START(xen_iret) SYM_CODE_END(xen_iret) /* + * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is + * also the kernel stack. Reusing swapgs_restore_regs_and_return_to_usermode() + * in XEN pv would cause %rsp to move up to the top of the kernel stack and + * leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI + * interrupts. And swapgs_restore_regs_and_return_to_usermode() pushing the IRET + * frame at the same address is useless. + */ +SYM_CODE_START(xenpv_restore_regs_and_return_to_usermode) + UNWIND_HINT_REGS + POP_REGS + + /* stackleak_erase() can work safely on the kernel stack. */ + STACKLEAK_ERASE_NOCLOBBER + + addq $8, %rsp /* skip regs->orig_ax */ + jmp xen_iret +SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode) + +/* * Xen handles syscall callbacks much like ordinary exceptions, which * means we have: * - kernel gs diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 5b78e86e3459..b9c77885b872 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -827,7 +827,7 @@ static ssize_t ata_scsi_lpm_show(struct device *dev, if (ap->target_lpm_policy >= ARRAY_SIZE(ata_lpm_policy_names)) return -EINVAL; - return snprintf(buf, PAGE_SIZE, "%s\n", + return sysfs_emit(buf, "%s\n", ata_lpm_policy_names[ap->target_lpm_policy]); } DEVICE_ATTR(link_power_management_policy, S_IRUGO | S_IWUSR, diff --git a/drivers/ata/pata_falcon.c b/drivers/ata/pata_falcon.c index 121635aa8c00..823c88622e34 100644 --- a/drivers/ata/pata_falcon.c +++ b/drivers/ata/pata_falcon.c @@ -55,14 +55,14 @@ static unsigned int pata_falcon_data_xfer(struct ata_queued_cmd *qc, /* Transfer multiple of 2 bytes */ if (rw == READ) { if (swap) - raw_insw_swapw((u16 *)data_addr, (u16 *)buf, words); + raw_insw_swapw(data_addr, (u16 *)buf, words); else - raw_insw((u16 *)data_addr, (u16 *)buf, words); + raw_insw(data_addr, (u16 *)buf, words); } else { if (swap) - raw_outsw_swapw((u16 *)data_addr, (u16 *)buf, words); + raw_outsw_swapw(data_addr, (u16 *)buf, words); else - raw_outsw((u16 *)data_addr, (u16 *)buf, words); + raw_outsw(data_addr, (u16 *)buf, words); } /* Transfer trailing byte, if any. */ @@ -74,16 +74,16 @@ static unsigned int pata_falcon_data_xfer(struct ata_queued_cmd *qc, if (rw == READ) { if (swap) - raw_insw_swapw((u16 *)data_addr, (u16 *)pad, 1); + raw_insw_swapw(data_addr, (u16 *)pad, 1); else - raw_insw((u16 *)data_addr, (u16 *)pad, 1); + raw_insw(data_addr, (u16 *)pad, 1); *buf = pad[0]; } else { pad[0] = *buf; if (swap) - raw_outsw_swapw((u16 *)data_addr, (u16 *)pad, 1); + raw_outsw_swapw(data_addr, (u16 *)pad, 1); else - raw_outsw((u16 *)data_addr, (u16 *)pad, 1); + raw_outsw(data_addr, (u16 *)pad, 1); } words++; } diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index e5838b23c9e0..3b31a4f596d8 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1394,6 +1394,14 @@ static int sata_fsl_init_controller(struct ata_host *host) return 0; } +static void sata_fsl_host_stop(struct ata_host *host) +{ + struct sata_fsl_host_priv *host_priv = host->private_data; + + iounmap(host_priv->hcr_base); + kfree(host_priv); +} + /* * scsi mid-layer and libata interface structures */ @@ -1426,6 +1434,8 @@ static struct ata_port_operations sata_fsl_ops = { .port_start = sata_fsl_port_start, .port_stop = sata_fsl_port_stop, + .host_stop = sata_fsl_host_stop, + .pmp_attach = sata_fsl_pmp_attach, .pmp_detach = sata_fsl_pmp_detach, }; @@ -1480,9 +1490,9 @@ static int sata_fsl_probe(struct platform_device *ofdev) host_priv->ssr_base = ssr_base; host_priv->csr_base = csr_base; - irq = irq_of_parse_and_map(ofdev->dev.of_node, 0); - if (!irq) { - dev_err(&ofdev->dev, "invalid irq from platform\n"); + irq = platform_get_irq(ofdev, 0); + if (irq < 0) { + retval = irq; goto error_exit_with_cleanup; } host_priv->irq = irq; @@ -1557,10 +1567,6 @@ static int sata_fsl_remove(struct platform_device *ofdev) ata_host_detach(host); - irq_dispose_mapping(host_priv->irq); - iounmap(host_priv->hcr_base); - kfree(host_priv); - return 0; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a154cab6cd98..c3a36cfaa855 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -2103,7 +2103,7 @@ static int loop_control_remove(int idx) int ret; if (idx < 0) { - pr_warn("deleting an unspecified loop device is not supported.\n"); + pr_warn_once("deleting an unspecified loop device is not supported.\n"); return -EINVAL; } diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c index ed3c4c42fc23..d68d05d5d383 100644 --- a/drivers/char/agp/parisc-agp.c +++ b/drivers/char/agp/parisc-agp.c @@ -281,7 +281,7 @@ agp_ioc_init(void __iomem *ioc_regs) return 0; } -static int +static int __init lba_find_capability(int cap) { struct _parisc_agp_info *info = &parisc_agp_info; @@ -366,7 +366,7 @@ fail: return error; } -static int +static int __init find_quicksilver(struct device *dev, void *data) { struct parisc_device **lba = data; @@ -378,7 +378,7 @@ find_quicksilver(struct device *dev, void *data) return 0; } -static int +static int __init parisc_agp_init(void) { extern struct sba_device *sba_list; diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index deed355422f4..c837d5416e0e 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -191,6 +191,8 @@ struct ipmi_user { struct work_struct remove_work; }; +static struct workqueue_struct *remove_work_wq; + static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index) __acquires(user->release_barrier) { @@ -1297,7 +1299,7 @@ static void free_user(struct kref *ref) struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount); /* SRCU cleanup must happen in task context. */ - schedule_work(&user->remove_work); + queue_work(remove_work_wq, &user->remove_work); } static void _ipmi_destroy_user(struct ipmi_user *user) @@ -3918,9 +3920,11 @@ static int handle_ipmb_direct_rcv_cmd(struct ipmi_smi *intf, /* We didn't find a user, deliver an error response. */ ipmi_inc_stat(intf, unhandled_commands); - msg->data[0] = ((netfn + 1) << 2) | (msg->rsp[4] & 0x3); - msg->data[1] = msg->rsp[2]; - msg->data[2] = msg->rsp[4] & ~0x3; + msg->data[0] = (netfn + 1) << 2; + msg->data[0] |= msg->rsp[2] & 0x3; /* rqLUN */ + msg->data[1] = msg->rsp[1]; /* Addr */ + msg->data[2] = msg->rsp[2] & ~0x3; /* rqSeq */ + msg->data[2] |= msg->rsp[0] & 0x3; /* rsLUN */ msg->data[3] = cmd; msg->data[4] = IPMI_INVALID_CMD_COMPLETION_CODE; msg->data_size = 5; @@ -4455,13 +4459,24 @@ return_unspecified: msg->rsp[2] = IPMI_ERR_UNSPECIFIED; msg->rsp_size = 3; } else if (msg->type == IPMI_SMI_MSG_TYPE_IPMB_DIRECT) { - /* commands must have at least 3 bytes, responses 4. */ - if (is_cmd && (msg->rsp_size < 3)) { + /* commands must have at least 4 bytes, responses 5. */ + if (is_cmd && (msg->rsp_size < 4)) { ipmi_inc_stat(intf, invalid_commands); goto out; } - if (!is_cmd && (msg->rsp_size < 4)) - goto return_unspecified; + if (!is_cmd && (msg->rsp_size < 5)) { + ipmi_inc_stat(intf, invalid_ipmb_responses); + /* Construct a valid error response. */ + msg->rsp[0] = msg->data[0] & 0xfc; /* NetFN */ + msg->rsp[0] |= (1 << 2); /* Make it a response */ + msg->rsp[0] |= msg->data[2] & 3; /* rqLUN */ + msg->rsp[1] = msg->data[1]; /* Addr */ + msg->rsp[2] = msg->data[2] & 0xfc; /* rqSeq */ + msg->rsp[2] |= msg->data[0] & 0x3; /* rsLUN */ + msg->rsp[3] = msg->data[3]; /* Cmd */ + msg->rsp[4] = IPMI_ERR_UNSPECIFIED; + msg->rsp_size = 5; + } } else if ((msg->data_size >= 2) && (msg->data[0] == (IPMI_NETFN_APP_REQUEST << 2)) && (msg->data[1] == IPMI_SEND_MSG_CMD) @@ -5031,6 +5046,7 @@ struct ipmi_smi_msg *ipmi_alloc_smi_msg(void) if (rv) { rv->done = free_smi_msg; rv->user_data = NULL; + rv->type = IPMI_SMI_MSG_TYPE_NORMAL; atomic_inc(&smi_msg_inuse_count); } return rv; @@ -5383,6 +5399,13 @@ static int ipmi_init_msghandler(void) atomic_notifier_chain_register(&panic_notifier_list, &panic_block); + remove_work_wq = create_singlethread_workqueue("ipmi-msghandler-remove-wq"); + if (!remove_work_wq) { + pr_err("unable to create ipmi-msghandler-remove-wq workqueue"); + rv = -ENOMEM; + goto out; + } + initialized = true; out: @@ -5408,6 +5431,8 @@ static void __exit cleanup_ipmi(void) int count; if (initialized) { + destroy_workqueue(remove_work_wq); + atomic_notifier_chain_unregister(&panic_notifier_list, &panic_block); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e338d2f010fe..096c3848fa41 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1004,10 +1004,9 @@ static struct kobj_type ktype_cpufreq = { .release = cpufreq_sysfs_release, }; -static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu) +static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu, + struct device *dev) { - struct device *dev = get_cpu_device(cpu); - if (unlikely(!dev)) return; @@ -1296,8 +1295,9 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy) if (policy->max_freq_req) { /* - * CPUFREQ_CREATE_POLICY notification is sent only after - * successfully adding max_freq_req request. + * Remove max_freq_req after sending CPUFREQ_REMOVE_POLICY + * notification, since CPUFREQ_CREATE_POLICY notification was + * sent after adding max_freq_req earlier. */ blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_REMOVE_POLICY, policy); @@ -1391,7 +1391,7 @@ static int cpufreq_online(unsigned int cpu) if (new_policy) { for_each_cpu(j, policy->related_cpus) { per_cpu(cpufreq_cpu_data, j) = policy; - add_cpu_dev_symlink(policy, j); + add_cpu_dev_symlink(policy, j, get_cpu_device(j)); } policy->min_freq_req = kzalloc(2 * sizeof(*policy->min_freq_req), @@ -1565,7 +1565,7 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) /* Create sysfs link on CPU registration */ policy = per_cpu(cpufreq_cpu_data, cpu); if (policy) - add_cpu_dev_symlink(policy, cpu); + add_cpu_dev_symlink(policy, cpu, dev); return 0; } diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c index f57a39ddd063..ab7fd896d2c4 100644 --- a/drivers/dma-buf/heaps/system_heap.c +++ b/drivers/dma-buf/heaps/system_heap.c @@ -290,7 +290,7 @@ static void system_heap_dma_buf_release(struct dma_buf *dmabuf) int i; table = &buffer->sg_table; - for_each_sg(table->sgl, sg, table->nents, i) { + for_each_sgtable_sg(table, sg, i) { struct page *page = sg_page(sg); __free_pages(page, compound_order(page)); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 71a6a9ef54ac..6348559608ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1396,7 +1396,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( struct sg_table *sg = NULL; uint64_t user_addr = 0; struct amdgpu_bo *bo; - struct drm_gem_object *gobj; + struct drm_gem_object *gobj = NULL; u32 domain, alloc_domain; u64 alloc_flags; int ret; @@ -1506,14 +1506,16 @@ allocate_init_user_pages_failed: remove_kgd_mem_from_kfd_bo_list(*mem, avm->process_info); drm_vma_node_revoke(&gobj->vma_node, drm_priv); err_node_allow: - drm_gem_object_put(gobj); /* Don't unreserve system mem limit twice */ goto err_reserve_limit; err_bo_create: unreserve_mem_limit(adev, size, alloc_domain, !!sg); err_reserve_limit: mutex_destroy(&(*mem)->lock); - kfree(*mem); + if (gobj) + drm_gem_object_put(gobj); + else + kfree(*mem); err: if (sg) { sg_free_table(sg); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d94fa748e6bb..1e651b959141 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3833,7 +3833,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) /* disable all interrupts */ amdgpu_irq_disable_all(adev); if (adev->mode_info.mode_config_initialized){ - if (!amdgpu_device_has_dc_support(adev)) + if (!drm_drv_uses_atomic_modeset(adev_to_drm(adev))) drm_helper_force_disable_all(adev_to_drm(adev)); else drm_atomic_helper_shutdown(adev_to_drm(adev)); @@ -4289,6 +4289,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, { int r; + amdgpu_amdkfd_pre_reset(adev); + if (from_hypervisor) r = amdgpu_virt_request_full_gpu(adev, true); else @@ -4316,6 +4318,7 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, amdgpu_irq_gpu_reset_resume_helper(adev); r = amdgpu_ib_ring_tests(adev); + amdgpu_amdkfd_post_reset(adev); error: if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) { @@ -5030,7 +5033,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, cancel_delayed_work_sync(&tmp_adev->delayed_init_work); - amdgpu_amdkfd_pre_reset(tmp_adev); + if (!amdgpu_sriov_vf(tmp_adev)) + amdgpu_amdkfd_pre_reset(tmp_adev); /* * Mark these ASICs to be reseted as untracked first @@ -5129,7 +5133,7 @@ skip_hw_reset: drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res); } - if (!amdgpu_device_has_dc_support(tmp_adev) && !job_signaled) { + if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) { drm_helper_resume_force_mode(adev_to_drm(tmp_adev)); } @@ -5148,9 +5152,9 @@ skip_hw_reset: skip_sched_resume: list_for_each_entry(tmp_adev, device_list_handle, reset_list) { - /* unlock kfd */ - if (!need_emergency_restart) - amdgpu_amdkfd_post_reset(tmp_adev); + /* unlock kfd: SRIOV would do it separately */ + if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev)) + amdgpu_amdkfd_post_reset(tmp_adev); /* kfd_post_reset will do nothing if kfd device is not initialized, * need to bring up kfd here if it's not be initialized before diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 503995c7ff6c..ea00090b3fb3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -157,6 +157,8 @@ static int hw_id_map[MAX_HWIP] = { [HDP_HWIP] = HDP_HWID, [SDMA0_HWIP] = SDMA0_HWID, [SDMA1_HWIP] = SDMA1_HWID, + [SDMA2_HWIP] = SDMA2_HWID, + [SDMA3_HWIP] = SDMA3_HWID, [MMHUB_HWIP] = MMHUB_HWID, [ATHUB_HWIP] = ATHUB_HWID, [NBIO_HWIP] = NBIF_HWID, @@ -918,6 +920,7 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(3, 0, 64): case IP_VERSION(3, 1, 1): case IP_VERSION(3, 0, 2): + case IP_VERSION(3, 0, 192): amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); if (!amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 4f7c70845785..585961c2f5f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -135,6 +135,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) break; case IP_VERSION(3, 0, 0): case IP_VERSION(3, 0, 64): + case IP_VERSION(3, 0, 192): if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 0)) fw_name = FIRMWARE_SIENNA_CICHLID; else diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index ce982afeff91..ac9a8cd21c4b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -504,8 +504,8 @@ static int amdgpu_vkms_sw_fini(void *handle) int i = 0; for (i = 0; i < adev->mode_info.num_crtc; i++) - if (adev->mode_info.crtcs[i]) - hrtimer_cancel(&adev->mode_info.crtcs[i]->vblank_timer); + if (adev->amdgpu_vkms_output[i].vblank_hrtimer.function) + hrtimer_cancel(&adev->amdgpu_vkms_output[i].vblank_hrtimer); kfree(adev->mode_info.bios_hardcoded_edid); kfree(adev->amdgpu_vkms_output); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 34478bcc4d09..b305fd39874f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -4060,9 +4060,10 @@ static int gfx_v9_0_hw_fini(void *handle) gfx_v9_0_cp_enable(adev, false); - /* Skip suspend with A+A reset */ - if (adev->gmc.xgmi.connected_to_cpu && amdgpu_in_reset(adev)) { - dev_dbg(adev->dev, "Device in reset. Skipping RLC halt\n"); + /* Skip stopping RLC with A+A reset or when RLC controls GFX clock */ + if ((adev->gmc.xgmi.connected_to_cpu && amdgpu_in_reset(adev)) || + (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 4, 2))) { + dev_dbg(adev->dev, "Skipping RLC halt\n"); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index a6659d9ecdd2..2ec1ffb36b1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -183,6 +183,7 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, switch (adev->ip_versions[UVD_HWIP][0]) { case IP_VERSION(3, 0, 0): case IP_VERSION(3, 0, 64): + case IP_VERSION(3, 0, 192): if (amdgpu_sriov_vf(adev)) { if (encode) *codecs = &sriov_sc_video_codecs_encode; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 58b89b53ebe6..3cb4681c5f53 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1574,7 +1574,6 @@ retry_flush_work: static void svm_range_restore_work(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); - struct amdkfd_process_info *process_info; struct svm_range_list *svms; struct svm_range *prange; struct kfd_process *p; @@ -1594,12 +1593,10 @@ static void svm_range_restore_work(struct work_struct *work) * the lifetime of this thread, kfd_process and mm will be valid. */ p = container_of(svms, struct kfd_process, svms); - process_info = p->kgd_process_info; mm = p->mm; if (!mm) return; - mutex_lock(&process_info->lock); svm_range_list_lock_and_flush_work(svms, mm); mutex_lock(&svms->lock); @@ -1652,7 +1649,6 @@ static void svm_range_restore_work(struct work_struct *work) out_reschedule: mutex_unlock(&svms->lock); mmap_write_unlock(mm); - mutex_unlock(&process_info->lock); /* If validation failed, reschedule another attempt */ if (evicted_ranges) { @@ -2614,6 +2610,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, if (atomic_read(&svms->drain_pagefaults)) { pr_debug("draining retry fault, drop fault 0x%llx\n", addr); + r = 0; goto out; } @@ -2623,6 +2620,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, mm = get_task_mm(p->lead_thread); if (!mm) { pr_debug("svms 0x%p failed to get mm\n", svms); + r = 0; goto out; } @@ -2660,6 +2658,7 @@ retry_write_locked: if (svm_range_skip_recover(prange)) { amdgpu_gmc_filter_faults_remove(adev, addr, pasid); + r = 0; goto out_unlock_range; } @@ -2668,6 +2667,7 @@ retry_write_locked: if (timestamp < AMDGPU_SVM_RANGE_RETRY_FAULT_PENDING) { pr_debug("svms 0x%p [0x%lx %lx] already restored\n", svms, prange->start, prange->last); + r = 0; goto out_unlock_range; } @@ -3177,7 +3177,6 @@ static int svm_range_set_attr(struct kfd_process *p, uint64_t start, uint64_t size, uint32_t nattr, struct kfd_ioctl_svm_attribute *attrs) { - struct amdkfd_process_info *process_info = p->kgd_process_info; struct mm_struct *mm = current->mm; struct list_head update_list; struct list_head insert_list; @@ -3196,8 +3195,6 @@ svm_range_set_attr(struct kfd_process *p, uint64_t start, uint64_t size, svms = &p->svms; - mutex_lock(&process_info->lock); - svm_range_list_lock_and_flush_work(svms, mm); r = svm_range_is_valid(p, start, size); @@ -3273,8 +3270,6 @@ out_unlock_range: mutex_unlock(&svms->lock); mmap_read_unlock(mm); out: - mutex_unlock(&process_info->lock); - pr_debug("pasid 0x%x svms 0x%p [0x%llx 0x%llx] done, r=%d\n", p->pasid, &p->svms, start, start + size - 1, r); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c index cce062adc439..8a441a22c46e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c @@ -314,6 +314,14 @@ int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name) ret = -EINVAL; goto cleanup; } + + if ((aconn->base.connector_type != DRM_MODE_CONNECTOR_DisplayPort) && + (aconn->base.connector_type != DRM_MODE_CONNECTOR_eDP)) { + DRM_DEBUG_DRIVER("No DP connector available for CRC source\n"); + ret = -EINVAL; + goto cleanup; + } + } #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 32a5ce09a62a..cc34a35d0bcb 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -36,6 +36,8 @@ #include "dm_helpers.h" #include "dc_link_ddc.h" +#include "ddc_service_types.h" +#include "dpcd_defs.h" #include "i2caux_interface.h" #include "dmub_cmd.h" @@ -157,6 +159,16 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = { }; #if defined(CONFIG_DRM_AMD_DC_DCN) +static bool needs_dsc_aux_workaround(struct dc_link *link) +{ + if (link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_90CC24 && + (link->dpcd_caps.dpcd_rev.raw == DPCD_REV_14 || link->dpcd_caps.dpcd_rev.raw == DPCD_REV_12) && + link->dpcd_caps.sink_count.bits.SINK_COUNT >= 2) + return true; + + return false; +} + static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnector) { struct dc_sink *dc_sink = aconnector->dc_sink; @@ -166,7 +178,7 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto u8 *dsc_branch_dec_caps = NULL; aconnector->dsc_aux = drm_dp_mst_dsc_aux_for_port(port); -#if defined(CONFIG_HP_HOOK_WORKAROUND) + /* * drm_dp_mst_dsc_aux_for_port() will return NULL for certain configs * because it only check the dsc/fec caps of the "port variable" and not the dock @@ -176,10 +188,10 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto * Workaround: explicitly check the use case above and use the mst dock's aux as dsc_aux * */ - - if (!aconnector->dsc_aux && !port->parent->port_parent) + if (!aconnector->dsc_aux && !port->parent->port_parent && + needs_dsc_aux_workaround(aconnector->dc_link)) aconnector->dsc_aux = &aconnector->mst_port->dm_dp_aux.aux; -#endif + if (!aconnector->dsc_aux) return false; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 60544788e911..c8457babfdea 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -758,6 +758,18 @@ static bool detect_dp(struct dc_link *link, dal_ddc_service_set_transaction_type(link->ddc, sink_caps->transaction_type); +#if defined(CONFIG_DRM_AMD_DC_DCN) + /* Apply work around for tunneled MST on certain USB4 docks. Always use DSC if dock + * reports DSC support. + */ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && + link->type == dc_connection_mst_branch && + link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_90CC24 && + link->dpcd_caps.dsc_caps.dsc_basic_caps.fields.dsc_support.DSC_SUPPORT && + !link->dc->debug.dpia_debug.bits.disable_mst_dsc_work_around) + link->wa_flags.dpia_mst_dsc_always_on = true; +#endif + #if defined(CONFIG_DRM_AMD_DC_HDCP) /* In case of fallback to SST when topology discovery below fails * HDCP caps will be querried again later by the upper layer (caller @@ -1203,6 +1215,10 @@ static bool dc_link_detect_helper(struct dc_link *link, LINK_INFO("link=%d, mst branch is now Disconnected\n", link->link_index); + /* Disable work around which keeps DSC on for tunneled MST on certain USB4 docks. */ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + link->wa_flags.dpia_mst_dsc_always_on = false; + dm_helpers_dp_mst_stop_top_mgr(link->ctx, link); link->mst_stream_alloc_table.stream_count = 0; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index cb7bf9148904..13bc69d6b679 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -2138,7 +2138,7 @@ static enum link_training_result dp_perform_8b_10b_link_training( } for (lane = 0; lane < (uint8_t)lt_settings->link_settings.lane_count; lane++) - lt_settings->dpcd_lane_settings[lane].bits.VOLTAGE_SWING_SET = VOLTAGE_SWING_LEVEL0; + lt_settings->dpcd_lane_settings[lane].raw = 0; } if (status == LINK_TRAINING_SUCCESS) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index c32fdccd4d92..e2d9a46d0e1a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1664,6 +1664,10 @@ bool dc_is_stream_unchanged( if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param) return false; + // Only Have Audio left to check whether it is same or not. This is a corner case for Tiled sinks + if (old_stream->audio_info.mode_count != stream->audio_info.mode_count) + return false; + return true; } @@ -2252,16 +2256,6 @@ enum dc_status dc_validate_global_state( if (!new_ctx) return DC_ERROR_UNEXPECTED; -#if defined(CONFIG_DRM_AMD_DC_DCN) - - /* - * Update link encoder to stream assignment. - * TODO: Split out reason allocation from validation. - */ - if (dc->res_pool->funcs->link_encs_assign && fast_validate == false) - dc->res_pool->funcs->link_encs_assign( - dc, new_ctx, new_ctx->streams, new_ctx->stream_count); -#endif if (dc->res_pool->funcs->validate_global) { result = dc->res_pool->funcs->validate_global(dc, new_ctx); @@ -2313,6 +2307,16 @@ enum dc_status dc_validate_global_state( if (!dc->res_pool->funcs->validate_bandwidth(dc, new_ctx, fast_validate)) result = DC_FAIL_BANDWIDTH_VALIDATE; +#if defined(CONFIG_DRM_AMD_DC_DCN) + /* + * Only update link encoder to stream assignment after bandwidth validation passed. + * TODO: Split out assignment and validation. + */ + if (result == DC_OK && dc->res_pool->funcs->link_encs_assign && fast_validate == false) + dc->res_pool->funcs->link_encs_assign( + dc, new_ctx, new_ctx->streams, new_ctx->stream_count); +#endif + return result; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 3aac3f4a2852..618e7989176f 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -508,7 +508,8 @@ union dpia_debug_options { uint32_t disable_dpia:1; uint32_t force_non_lttpr:1; uint32_t extend_aux_rd_interval:1; - uint32_t reserved:29; + uint32_t disable_mst_dsc_work_around:1; + uint32_t reserved:28; } bits; uint32_t raw; }; diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index 180ecd860296..b01077a6af0e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -191,6 +191,8 @@ struct dc_link { bool dp_skip_DID2; bool dp_skip_reset_segment; bool dp_mot_reset_segment; + /* Some USB4 docks do not handle turning off MST DSC once it has been enabled. */ + bool dpia_mst_dsc_always_on; } wa_flags; struct link_mst_stream_allocation_table mst_stream_alloc_table; diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 01168b8955bf..8a3244585d80 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1468,7 +1468,7 @@ static int smu_disable_dpms(struct smu_context *smu) dev_err(adev->dev, "Failed to disable smu features.\n"); } - if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 0, 0) && + if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 4, 2) && adev->gfx.rlc.funcs->stop) adev->gfx.rlc.funcs->stop(adev); diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 39e11eaec1a3..aa7238245b0e 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1640,6 +1640,9 @@ struct intel_dp { struct intel_dp_pcon_frl frl; struct intel_psr psr; + + /* When we last wrote the OUI for eDP */ + unsigned long last_oui_write; }; enum lspcon_vendor { diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index be883469d2fc..a552f05a67e5 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -29,6 +29,7 @@ #include <linux/i2c.h> #include <linux/notifier.h> #include <linux/slab.h> +#include <linux/timekeeping.h> #include <linux/types.h> #include <asm/byteorder.h> @@ -1955,6 +1956,16 @@ intel_edp_init_source_oui(struct intel_dp *intel_dp, bool careful) if (drm_dp_dpcd_write(&intel_dp->aux, DP_SOURCE_OUI, oui, sizeof(oui)) < 0) drm_err(&i915->drm, "Failed to write source OUI\n"); + + intel_dp->last_oui_write = jiffies; +} + +void intel_dp_wait_source_oui(struct intel_dp *intel_dp) +{ + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + + drm_dbg_kms(&i915->drm, "Performing OUI wait\n"); + wait_remaining_ms_from_jiffies(intel_dp->last_oui_write, 30); } /* If the device supports it, try to set the power state appropriately */ diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index ce229026dc91..b64145a3869a 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -119,4 +119,6 @@ void intel_dp_pcon_dsc_configure(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state); void intel_dp_phy_test(struct intel_encoder *encoder); +void intel_dp_wait_source_oui(struct intel_dp *intel_dp); + #endif /* __INTEL_DP_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 569d17b4d00f..3897468140e0 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -36,6 +36,7 @@ #include "intel_backlight.h" #include "intel_display_types.h" +#include "intel_dp.h" #include "intel_dp_aux_backlight.h" /* TODO: @@ -106,6 +107,8 @@ intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector) int ret; u8 tcon_cap[4]; + intel_dp_wait_source_oui(intel_dp); + ret = drm_dp_dpcd_read(aux, INTEL_EDP_HDR_TCON_CAP0, tcon_cap, sizeof(tcon_cap)); if (ret != sizeof(tcon_cap)) return false; @@ -204,6 +207,8 @@ intel_dp_aux_hdr_enable_backlight(const struct intel_crtc_state *crtc_state, int ret; u8 old_ctrl, ctrl; + intel_dp_wait_source_oui(intel_dp); + ret = drm_dp_dpcd_readb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, &old_ctrl); if (ret != 1) { drm_err(&i915->drm, "Failed to read current backlight control mode: %d\n", ret); @@ -293,6 +298,13 @@ intel_dp_aux_vesa_enable_backlight(const struct intel_crtc_state *crtc_state, struct intel_panel *panel = &connector->panel; struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder); + if (!panel->backlight.edp.vesa.info.aux_enable) { + u32 pwm_level = intel_backlight_invert_pwm_level(connector, + panel->backlight.pwm_level_max); + + panel->backlight.pwm_funcs->enable(crtc_state, conn_state, pwm_level); + } + drm_edp_backlight_enable(&intel_dp->aux, &panel->backlight.edp.vesa.info, level); } @@ -304,6 +316,10 @@ static void intel_dp_aux_vesa_disable_backlight(const struct drm_connector_state struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder); drm_edp_backlight_disable(&intel_dp->aux, &panel->backlight.edp.vesa.info); + + if (!panel->backlight.edp.vesa.info.aux_enable) + panel->backlight.pwm_funcs->disable(old_conn_state, + intel_backlight_invert_pwm_level(connector, 0)); } static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, enum pipe pipe) @@ -321,6 +337,15 @@ static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, if (ret < 0) return ret; + if (!panel->backlight.edp.vesa.info.aux_enable) { + ret = panel->backlight.pwm_funcs->setup(connector, pipe); + if (ret < 0) { + drm_err(&i915->drm, + "Failed to setup PWM backlight controls for eDP backlight: %d\n", + ret); + return ret; + } + } panel->backlight.max = panel->backlight.edp.vesa.info.max; panel->backlight.min = 0; if (current_mode == DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) { @@ -340,12 +365,7 @@ intel_dp_aux_supports_vesa_backlight(struct intel_connector *connector) struct intel_dp *intel_dp = intel_attached_dp(connector); struct drm_i915_private *i915 = dp_to_i915(intel_dp); - /* TODO: We currently only support AUX only backlight configurations, not backlights which - * require a mix of PWM and AUX controls to work. In the mean time, these machines typically - * work just fine using normal PWM controls anyway. - */ - if ((intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP) && - drm_edp_backlight_supported(intel_dp->edp_dpcd)) { + if (drm_edp_backlight_supported(intel_dp->edp_dpcd)) { drm_dbg_kms(&i915->drm, "AUX Backlight Control Supported!\n"); return true; } diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index e1f362530889..ed73d9bc9d40 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -621,13 +621,6 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, FF_MODE2_GS_TIMER_MASK, FF_MODE2_GS_TIMER_224, 0, false); - - /* - * Wa_14012131227:dg1 - * Wa_1508744258:tgl,rkl,dg1,adl-s,adl-p - */ - wa_masked_en(wal, GEN7_COMMON_SLICE_CHICKEN1, - GEN9_RHWO_OPTIMIZATION_DISABLE); } static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine, diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index ae11061727ff..39197b4beea7 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -4,8 +4,8 @@ config DRM_MSM tristate "MSM DRM" depends on DRM depends on ARCH_QCOM || SOC_IMX5 || COMPILE_TEST + depends on COMMON_CLK depends on IOMMU_SUPPORT - depends on (OF && COMMON_CLK) || COMPILE_TEST depends on QCOM_OCMEM || QCOM_OCMEM=n depends on QCOM_LLCC || QCOM_LLCC=n depends on QCOM_COMMAND_DB || QCOM_COMMAND_DB=n diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 40577f8856d8..093454457545 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -23,8 +23,10 @@ msm-y := \ hdmi/hdmi_i2c.o \ hdmi/hdmi_phy.o \ hdmi/hdmi_phy_8960.o \ + hdmi/hdmi_phy_8996.o \ hdmi/hdmi_phy_8x60.o \ hdmi/hdmi_phy_8x74.o \ + hdmi/hdmi_pll_8960.o \ edp/edp.o \ edp/edp_aux.o \ edp/edp_bridge.o \ @@ -37,6 +39,7 @@ msm-y := \ disp/mdp4/mdp4_dtv_encoder.o \ disp/mdp4/mdp4_lcdc_encoder.o \ disp/mdp4/mdp4_lvds_connector.o \ + disp/mdp4/mdp4_lvds_pll.o \ disp/mdp4/mdp4_irq.o \ disp/mdp4/mdp4_kms.o \ disp/mdp4/mdp4_plane.o \ @@ -116,9 +119,6 @@ msm-$(CONFIG_DRM_MSM_DP)+= dp/dp_aux.o \ dp/dp_audio.o msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o -msm-$(CONFIG_COMMON_CLK) += disp/mdp4/mdp4_lvds_pll.o -msm-$(CONFIG_COMMON_CLK) += hdmi/hdmi_pll_8960.o -msm-$(CONFIG_COMMON_CLK) += hdmi/hdmi_phy_8996.o msm-$(CONFIG_DRM_MSM_HDMI_HDCP) += hdmi/hdmi_hdcp.o diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 267a880811d6..78aad5216a61 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1424,17 +1424,24 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu) { struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; struct msm_gpu *gpu = &adreno_gpu->base; - u32 gpu_scid, cntl1_regval = 0; + u32 cntl1_regval = 0; if (IS_ERR(a6xx_gpu->llc_mmio)) return; if (!llcc_slice_activate(a6xx_gpu->llc_slice)) { - gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice); + u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice); gpu_scid &= 0x1f; cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) | (gpu_scid << 15) | (gpu_scid << 20); + + /* On A660, the SCID programming for UCHE traffic is done in + * A6XX_GBIF_SCACHE_CNTL0[14:10] + */ + if (adreno_is_a660_family(adreno_gpu)) + gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) | + (1 << 8), (gpu_scid << 10) | (1 << 8)); } /* @@ -1471,13 +1478,6 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu) } gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0), cntl1_regval); - - /* On A660, the SCID programming for UCHE traffic is done in - * A6XX_GBIF_SCACHE_CNTL0[14:10] - */ - if (adreno_is_a660_family(adreno_gpu)) - gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) | - (1 << 8), (gpu_scid << 10) | (1 << 8)); } static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu) @@ -1640,7 +1640,7 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu) return (unsigned long)busy_time; } -void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) +static void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 7501849ed15d..6e90209cd543 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -777,12 +777,12 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); a6xx_state->gmu_registers = state_kcalloc(a6xx_state, - 2, sizeof(*a6xx_state->gmu_registers)); + 3, sizeof(*a6xx_state->gmu_registers)); if (!a6xx_state->gmu_registers) return; - a6xx_state->nr_gmu_registers = 2; + a6xx_state->nr_gmu_registers = 3; /* Get the CX GMU registers from AHB */ _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0], diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c index eb40d8413bca..6d36f63c3338 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.c +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -33,6 +33,7 @@ struct dp_aux_private { bool read; bool no_send_addr; bool no_send_stop; + bool initted; u32 offset; u32 segment; @@ -331,6 +332,10 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, } mutex_lock(&aux->mutex); + if (!aux->initted) { + ret = -EIO; + goto exit; + } dp_aux_update_offset_and_segment(aux, msg); dp_aux_transfer_helper(aux, msg, true); @@ -380,6 +385,8 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, } aux->cmd_busy = false; + +exit: mutex_unlock(&aux->mutex); return ret; @@ -431,8 +438,13 @@ void dp_aux_init(struct drm_dp_aux *dp_aux) aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + mutex_lock(&aux->mutex); + dp_catalog_aux_enable(aux->catalog, true); aux->retry_cnt = 0; + aux->initted = true; + + mutex_unlock(&aux->mutex); } void dp_aux_deinit(struct drm_dp_aux *dp_aux) @@ -441,7 +453,12 @@ void dp_aux_deinit(struct drm_dp_aux *dp_aux) aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + mutex_lock(&aux->mutex); + + aux->initted = false; dp_catalog_aux_enable(aux->catalog, false); + + mutex_unlock(&aux->mutex); } int dp_aux_register(struct drm_dp_aux *dp_aux) diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index f69a125f9559..0afc3b756f92 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -1658,6 +1658,8 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host, if (!prop) { DRM_DEV_DEBUG(dev, "failed to find data lane mapping, using default\n"); + /* Set the number of date lanes to 4 by default. */ + msm_host->num_data_lanes = 4; return 0; } diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index 09d2d279c30a..dee13fedee3b 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -77,6 +77,7 @@ static int msm_gpu_open(struct inode *inode, struct file *file) goto free_priv; pm_runtime_get_sync(&gpu->pdev->dev); + msm_gpu_hw_init(gpu); show_priv->state = gpu->funcs->gpu_state_get(gpu); pm_runtime_put_sync(&gpu->pdev->dev); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 7936e8d498dd..892c04365239 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -967,29 +967,18 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data, return ret; } -static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, - struct drm_file *file) +static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id, + ktime_t timeout) { - struct msm_drm_private *priv = dev->dev_private; - struct drm_msm_wait_fence *args = data; - ktime_t timeout = to_ktime(args->timeout); - struct msm_gpu_submitqueue *queue; - struct msm_gpu *gpu = priv->gpu; struct dma_fence *fence; int ret; - if (args->pad) { - DRM_ERROR("invalid pad: %08x\n", args->pad); + if (fence_id > queue->last_fence) { + DRM_ERROR_RATELIMITED("waiting on invalid fence: %u (of %u)\n", + fence_id, queue->last_fence); return -EINVAL; } - if (!gpu) - return 0; - - queue = msm_submitqueue_get(file->driver_priv, args->queueid); - if (!queue) - return -ENOENT; - /* * Map submitqueue scoped "seqno" (which is actually an idr key) * back to underlying dma-fence @@ -1001,7 +990,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, ret = mutex_lock_interruptible(&queue->lock); if (ret) return ret; - fence = idr_find(&queue->fence_idr, args->fence); + fence = idr_find(&queue->fence_idr, fence_id); if (fence) fence = dma_fence_get_rcu(fence); mutex_unlock(&queue->lock); @@ -1017,6 +1006,32 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, } dma_fence_put(fence); + + return ret; +} + +static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, + struct drm_file *file) +{ + struct msm_drm_private *priv = dev->dev_private; + struct drm_msm_wait_fence *args = data; + struct msm_gpu_submitqueue *queue; + int ret; + + if (args->pad) { + DRM_ERROR("invalid pad: %08x\n", args->pad); + return -EINVAL; + } + + if (!priv->gpu) + return 0; + + queue = msm_submitqueue_get(file->driver_priv, args->queueid); + if (!queue) + return -ENOENT; + + ret = wait_fence(queue, args->fence, to_ktime(args->timeout)); + msm_submitqueue_put(queue); return ret; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 104fdfc14027..512d55eecbaf 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -1056,8 +1056,7 @@ static int msm_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct { struct msm_gem_object *msm_obj = to_msm_bo(obj); - vma->vm_flags &= ~VM_PFNMAP; - vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND; + vma->vm_flags |= VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_page_prot = msm_gem_pgprot(msm_obj, vm_get_page_prot(vma->vm_flags)); return 0; @@ -1121,7 +1120,7 @@ static int msm_gem_new_impl(struct drm_device *dev, break; fallthrough; default: - DRM_DEV_ERROR(dev->dev, "invalid cache flag: %x\n", + DRM_DEV_DEBUG(dev->dev, "invalid cache flag: %x\n", (flags & MSM_BO_CACHE_MASK)); return -EINVAL; } diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 3cb029f10925..282628d6b72c 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -772,6 +772,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, args->nr_cmds); if (IS_ERR(submit)) { ret = PTR_ERR(submit); + submit = NULL; goto out_unlock; } @@ -904,6 +905,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, drm_sched_entity_push_job(&submit->base); args->fence = submit->fence_id; + queue->last_fence = submit->fence_id; msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs); msm_process_post_deps(post_deps, args->nr_out_syncobjs, diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 59cdd00b69d0..48ea2de911f1 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -359,6 +359,8 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio, * @ring_nr: the ringbuffer used by this submitqueue, which is determined * by the submitqueue's priority * @faults: the number of GPU hangs associated with this submitqueue + * @last_fence: the sequence number of the last allocated fence (for error + * checking) * @ctx: the per-drm_file context associated with the submitqueue (ie. * which set of pgtables do submits jobs associated with the * submitqueue use) @@ -374,6 +376,7 @@ struct msm_gpu_submitqueue { u32 flags; u32 ring_nr; int faults; + uint32_t last_fence; struct msm_file_private *ctx; struct list_head node; struct idr fence_idr; diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c index 8b7473f69cb8..384e90c4b2a7 100644 --- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -20,6 +20,10 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq, struct msm_gpu *gpu = dev_to_gpu(dev); struct dev_pm_opp *opp; + /* + * Note that devfreq_recommended_opp() can modify the freq + * to something that actually is in the opp table: + */ opp = devfreq_recommended_opp(dev, freq, flags); /* @@ -28,6 +32,7 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq, */ if (gpu->devfreq.idle_freq) { gpu->devfreq.idle_freq = *freq; + dev_pm_opp_put(opp); return 0; } @@ -203,9 +208,6 @@ static void msm_devfreq_idle_work(struct kthread_work *work) struct msm_gpu *gpu = container_of(df, struct msm_gpu, devfreq); unsigned long idle_freq, target_freq = 0; - if (!df->devfreq) - return; - /* * Hold devfreq lock to synchronize with get_dev_status()/ * target() callbacks @@ -227,6 +229,9 @@ void msm_devfreq_idle(struct msm_gpu *gpu) { struct msm_gpu_devfreq *df = &gpu->devfreq; + if (!df->devfreq) + return; + msm_hrtimer_queue_work(&df->idle_work, ms_to_ktime(1), - HRTIMER_MODE_ABS); + HRTIMER_MODE_REL); } diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index f0b3e4cf5bce..b61792d2aa65 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -337,10 +337,10 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state) struct drm_device *dev = state->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); struct vc4_hvs *hvs = vc4->hvs; - struct drm_crtc_state *old_crtc_state; struct drm_crtc_state *new_crtc_state; struct drm_crtc *crtc; struct vc4_hvs_state *old_hvs_state; + unsigned int channel; int i; for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) { @@ -353,30 +353,32 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state) vc4_hvs_mask_underrun(dev, vc4_crtc_state->assigned_channel); } - if (vc4->hvs->hvs5) - clk_set_min_rate(hvs->core_clk, 500000000); - old_hvs_state = vc4_hvs_get_old_global_state(state); - if (!old_hvs_state) + if (IS_ERR(old_hvs_state)) return; - for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) { - struct vc4_crtc_state *vc4_crtc_state = - to_vc4_crtc_state(old_crtc_state); - unsigned int channel = vc4_crtc_state->assigned_channel; + for (channel = 0; channel < HVS_NUM_CHANNELS; channel++) { + struct drm_crtc_commit *commit; int ret; - if (channel == VC4_HVS_CHANNEL_DISABLED) + if (!old_hvs_state->fifo_state[channel].in_use) continue; - if (!old_hvs_state->fifo_state[channel].in_use) + commit = old_hvs_state->fifo_state[channel].pending_commit; + if (!commit) continue; - ret = drm_crtc_commit_wait(old_hvs_state->fifo_state[channel].pending_commit); + ret = drm_crtc_commit_wait(commit); if (ret) drm_err(dev, "Timed out waiting for commit\n"); + + drm_crtc_commit_put(commit); + old_hvs_state->fifo_state[channel].pending_commit = NULL; } + if (vc4->hvs->hvs5) + clk_set_min_rate(hvs->core_clk, 500000000); + drm_atomic_helper_commit_modeset_disables(dev, state); vc4_ctm_commit(vc4, state); @@ -410,8 +412,8 @@ static int vc4_atomic_commit_setup(struct drm_atomic_state *state) unsigned int i; hvs_state = vc4_hvs_get_new_global_state(state); - if (!hvs_state) - return -EINVAL; + if (WARN_ON(IS_ERR(hvs_state))) + return PTR_ERR(hvs_state); for_each_new_crtc_in_state(state, crtc, crtc_state, i) { struct vc4_crtc_state *vc4_crtc_state = @@ -668,12 +670,6 @@ vc4_hvs_channels_duplicate_state(struct drm_private_obj *obj) for (i = 0; i < HVS_NUM_CHANNELS; i++) { state->fifo_state[i].in_use = old_state->fifo_state[i].in_use; - - if (!old_state->fifo_state[i].pending_commit) - continue; - - state->fifo_state[i].pending_commit = - drm_crtc_commit_get(old_state->fifo_state[i].pending_commit); } return &state->base; @@ -762,8 +758,8 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev, unsigned int i; hvs_new_state = vc4_hvs_get_global_state(state); - if (!hvs_new_state) - return -EINVAL; + if (IS_ERR(hvs_new_state)) + return PTR_ERR(hvs_new_state); for (i = 0; i < ARRAY_SIZE(hvs_new_state->fifo_state); i++) if (!hvs_new_state->fifo_state[i].in_use) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index d86e1ad4a972..5072dbb0669a 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -157,36 +157,6 @@ static void virtio_gpu_config_changed(struct virtio_device *vdev) schedule_work(&vgdev->config_changed_work); } -static __poll_t virtio_gpu_poll(struct file *filp, - struct poll_table_struct *wait) -{ - struct drm_file *drm_file = filp->private_data; - struct virtio_gpu_fpriv *vfpriv = drm_file->driver_priv; - struct drm_device *dev = drm_file->minor->dev; - struct virtio_gpu_device *vgdev = dev->dev_private; - struct drm_pending_event *e = NULL; - __poll_t mask = 0; - - if (!vgdev->has_virgl_3d || !vfpriv || !vfpriv->ring_idx_mask) - return drm_poll(filp, wait); - - poll_wait(filp, &drm_file->event_wait, wait); - - if (!list_empty(&drm_file->event_list)) { - spin_lock_irq(&dev->event_lock); - e = list_first_entry(&drm_file->event_list, - struct drm_pending_event, link); - drm_file->event_space += e->event->length; - list_del(&e->link); - spin_unlock_irq(&dev->event_lock); - - kfree(e); - mask |= EPOLLIN | EPOLLRDNORM; - } - - return mask; -} - static struct virtio_device_id id_table[] = { { VIRTIO_ID_GPU, VIRTIO_DEV_ANY_ID }, { 0 }, @@ -226,17 +196,7 @@ MODULE_AUTHOR("Dave Airlie <[email protected]>"); MODULE_AUTHOR("Gerd Hoffmann <[email protected]>"); MODULE_AUTHOR("Alon Levy"); -static const struct file_operations virtio_gpu_driver_fops = { - .owner = THIS_MODULE, - .open = drm_open, - .release = drm_release, - .unlocked_ioctl = drm_ioctl, - .compat_ioctl = drm_compat_ioctl, - .poll = virtio_gpu_poll, - .read = drm_read, - .llseek = noop_llseek, - .mmap = drm_gem_mmap -}; +DEFINE_DRM_GEM_FOPS(virtio_gpu_driver_fops); static const struct drm_driver driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_RENDER | DRIVER_ATOMIC, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index e0265fe74aa5..0a194aaad419 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -138,7 +138,6 @@ struct virtio_gpu_fence_driver { spinlock_t lock; }; -#define VIRTGPU_EVENT_FENCE_SIGNALED_INTERNAL 0x10000000 struct virtio_gpu_fence_event { struct drm_pending_event base; struct drm_event event; diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 5618a1d5879c..3607646d3229 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -54,7 +54,7 @@ static int virtio_gpu_fence_event_create(struct drm_device *dev, if (!e) return -ENOMEM; - e->event.type = VIRTGPU_EVENT_FENCE_SIGNALED_INTERNAL; + e->event.type = VIRTGPU_EVENT_FENCE_SIGNALED; e->event.length = sizeof(e->event); ret = drm_event_reserve_init(dev, file, &e->base, &e->event); diff --git a/drivers/i2c/busses/i2c-cbus-gpio.c b/drivers/i2c/busses/i2c-cbus-gpio.c index 72df563477b1..f8639a4457d2 100644 --- a/drivers/i2c/busses/i2c-cbus-gpio.c +++ b/drivers/i2c/busses/i2c-cbus-gpio.c @@ -195,8 +195,9 @@ static u32 cbus_i2c_func(struct i2c_adapter *adapter) } static const struct i2c_algorithm cbus_i2c_algo = { - .smbus_xfer = cbus_i2c_smbus_xfer, - .functionality = cbus_i2c_func, + .smbus_xfer = cbus_i2c_smbus_xfer, + .smbus_xfer_atomic = cbus_i2c_smbus_xfer, + .functionality = cbus_i2c_func, }; static int cbus_i2c_remove(struct platform_device *pdev) diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index 819ab4ee517e..02ddb237f69a 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -423,8 +423,8 @@ static void rk3x_i2c_handle_read(struct rk3x_i2c *i2c, unsigned int ipd) if (!(ipd & REG_INT_MBRF)) return; - /* ack interrupt */ - i2c_writel(i2c, REG_INT_MBRF, REG_IPD); + /* ack interrupt (read also produces a spurious START flag, clear it too) */ + i2c_writel(i2c, REG_INT_MBRF | REG_INT_START, REG_IPD); /* Can only handle a maximum of 32 bytes at a time */ if (len > 32) diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index b9b19a2a2ffa..66145d2b9b55 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -1493,6 +1493,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) { struct stm32f7_i2c_dev *i2c_dev = data; struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg; + struct stm32_i2c_dma *dma = i2c_dev->dma; void __iomem *base = i2c_dev->base; u32 status, mask; int ret = IRQ_HANDLED; @@ -1518,6 +1519,10 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n", __func__, f7_msg->addr); writel_relaxed(STM32F7_I2C_ICR_NACKCF, base + STM32F7_I2C_ICR); + if (i2c_dev->use_dma) { + stm32f7_i2c_disable_dma_req(i2c_dev); + dmaengine_terminate_async(dma->chan_using); + } f7_msg->result = -ENXIO; } @@ -1533,7 +1538,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) /* Clear STOP flag */ writel_relaxed(STM32F7_I2C_ICR_STOPCF, base + STM32F7_I2C_ICR); - if (i2c_dev->use_dma) { + if (i2c_dev->use_dma && !f7_msg->result) { ret = IRQ_WAKE_THREAD; } else { i2c_dev->master_mode = false; @@ -1546,7 +1551,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) if (f7_msg->stop) { mask = STM32F7_I2C_CR2_STOP; stm32f7_i2c_set_bits(base + STM32F7_I2C_CR2, mask); - } else if (i2c_dev->use_dma) { + } else if (i2c_dev->use_dma && !f7_msg->result) { ret = IRQ_WAKE_THREAD; } else if (f7_msg->smbus) { stm32f7_i2c_smbus_rep_start(i2c_dev); @@ -1583,7 +1588,7 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) if (!ret) { dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__); stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_all(dma->chan_using); + dmaengine_terminate_async(dma->chan_using); f7_msg->result = -ETIMEDOUT; } @@ -1660,7 +1665,7 @@ static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data) /* Disable dma */ if (i2c_dev->use_dma) { stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_all(dma->chan_using); + dmaengine_terminate_async(dma->chan_using); } i2c_dev->master_mode = false; @@ -1696,12 +1701,26 @@ static int stm32f7_i2c_xfer(struct i2c_adapter *i2c_adap, time_left = wait_for_completion_timeout(&i2c_dev->complete, i2c_dev->adap.timeout); ret = f7_msg->result; + if (ret) { + if (i2c_dev->use_dma) + dmaengine_synchronize(dma->chan_using); + + /* + * It is possible that some unsent data have already been + * written into TXDR. To avoid sending old data in a + * further transfer, flush TXDR in case of any error + */ + writel_relaxed(STM32F7_I2C_ISR_TXE, + i2c_dev->base + STM32F7_I2C_ISR); + goto pm_free; + } if (!time_left) { dev_dbg(i2c_dev->dev, "Access to slave 0x%x timed out\n", i2c_dev->msg->addr); if (i2c_dev->use_dma) - dmaengine_terminate_all(dma->chan_using); + dmaengine_terminate_sync(dma->chan_using); + stm32f7_i2c_wait_free_bus(i2c_dev); ret = -ETIMEDOUT; } @@ -1744,13 +1763,25 @@ static int stm32f7_i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, timeout = wait_for_completion_timeout(&i2c_dev->complete, i2c_dev->adap.timeout); ret = f7_msg->result; - if (ret) + if (ret) { + if (i2c_dev->use_dma) + dmaengine_synchronize(dma->chan_using); + + /* + * It is possible that some unsent data have already been + * written into TXDR. To avoid sending old data in a + * further transfer, flush TXDR in case of any error + */ + writel_relaxed(STM32F7_I2C_ISR_TXE, + i2c_dev->base + STM32F7_I2C_ISR); goto pm_free; + } if (!timeout) { dev_dbg(dev, "Access to slave 0x%x timed out\n", f7_msg->addr); if (i2c_dev->use_dma) - dmaengine_terminate_all(dma->chan_using); + dmaengine_terminate_sync(dma->chan_using); + stm32f7_i2c_wait_free_bus(i2c_dev); ret = -ETIMEDOUT; goto pm_free; } diff --git a/drivers/net/dsa/b53/b53_spi.c b/drivers/net/dsa/b53/b53_spi.c index 01e37b75471e..2b88f03e5252 100644 --- a/drivers/net/dsa/b53/b53_spi.c +++ b/drivers/net/dsa/b53/b53_spi.c @@ -349,6 +349,19 @@ static const struct of_device_id b53_spi_of_match[] = { }; MODULE_DEVICE_TABLE(of, b53_spi_of_match); +static const struct spi_device_id b53_spi_ids[] = { + { .name = "bcm5325" }, + { .name = "bcm5365" }, + { .name = "bcm5395" }, + { .name = "bcm5397" }, + { .name = "bcm5398" }, + { .name = "bcm53115" }, + { .name = "bcm53125" }, + { .name = "bcm53128" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(spi, b53_spi_ids); + static struct spi_driver b53_spi_driver = { .driver = { .name = "b53-switch", @@ -357,6 +370,7 @@ static struct spi_driver b53_spi_driver = { .probe = b53_spi_probe, .remove = b53_spi_remove, .shutdown = b53_spi_shutdown, + .id_table = b53_spi_ids, }; module_spi_driver(b53_spi_driver); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 6ea003678798..55273013bfb5 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -50,11 +50,22 @@ static int mv88e6390_serdes_write(struct mv88e6xxx_chip *chip, } static int mv88e6xxx_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, - u16 status, u16 lpa, + u16 ctrl, u16 status, u16 lpa, struct phylink_link_state *state) { + state->link = !!(status & MV88E6390_SGMII_PHY_STATUS_LINK); + if (status & MV88E6390_SGMII_PHY_STATUS_SPD_DPL_VALID) { - state->link = !!(status & MV88E6390_SGMII_PHY_STATUS_LINK); + /* The Spped and Duplex Resolved register is 1 if AN is enabled + * and complete, or if AN is disabled. So with disabled AN we + * still get here on link up. But we want to set an_complete + * only if AN was enabled, thus we look at BMCR_ANENABLE. + * (According to 802.3-2008 section 22.2.4.2.10, we should be + * able to get this same value from BMSR_ANEGCAPABLE, but tests + * show that these Marvell PHYs don't conform to this part of + * the specificaion - BMSR_ANEGCAPABLE is simply always 1.) + */ + state->an_complete = !!(ctrl & BMCR_ANENABLE); state->duplex = status & MV88E6390_SGMII_PHY_STATUS_DUPLEX_FULL ? DUPLEX_FULL : DUPLEX_HALF; @@ -81,6 +92,18 @@ static int mv88e6xxx_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, dev_err(chip->dev, "invalid PHY speed\n"); return -EINVAL; } + } else if (state->link && + state->interface != PHY_INTERFACE_MODE_SGMII) { + /* If Speed and Duplex Resolved register is 0 and link is up, it + * means that AN was enabled, but link partner had it disabled + * and the PHY invoked the Auto-Negotiation Bypass feature and + * linked anyway. + */ + state->duplex = DUPLEX_FULL; + if (state->interface == PHY_INTERFACE_MODE_2500BASEX) + state->speed = SPEED_2500; + else + state->speed = SPEED_1000; } else { state->link = false; } @@ -168,9 +191,15 @@ int mv88e6352_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port, int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port, int lane, struct phylink_link_state *state) { - u16 lpa, status; + u16 lpa, status, ctrl; int err; + err = mv88e6352_serdes_read(chip, MII_BMCR, &ctrl); + if (err) { + dev_err(chip->dev, "can't read Serdes PHY control: %d\n", err); + return err; + } + err = mv88e6352_serdes_read(chip, 0x11, &status); if (err) { dev_err(chip->dev, "can't read Serdes PHY status: %d\n", err); @@ -183,7 +212,7 @@ int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port, return err; } - return mv88e6xxx_serdes_pcs_get_state(chip, status, lpa, state); + return mv88e6xxx_serdes_pcs_get_state(chip, ctrl, status, lpa, state); } int mv88e6352_serdes_pcs_an_restart(struct mv88e6xxx_chip *chip, int port, @@ -883,10 +912,17 @@ int mv88e6390_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port, static int mv88e6390_serdes_pcs_get_state_sgmii(struct mv88e6xxx_chip *chip, int port, int lane, struct phylink_link_state *state) { - u16 lpa, status; + u16 lpa, status, ctrl; int err; err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS, + MV88E6390_SGMII_BMCR, &ctrl); + if (err) { + dev_err(chip->dev, "can't read Serdes PHY control: %d\n", err); + return err; + } + + err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS, MV88E6390_SGMII_PHY_STATUS, &status); if (err) { dev_err(chip->dev, "can't read Serdes PHY status: %d\n", err); @@ -900,7 +936,7 @@ static int mv88e6390_serdes_pcs_get_state_sgmii(struct mv88e6xxx_chip *chip, return err; } - return mv88e6xxx_serdes_pcs_get_state(chip, status, lpa, state); + return mv88e6xxx_serdes_pcs_get_state(chip, ctrl, status, lpa, state); } static int mv88e6390_serdes_pcs_get_state_10g(struct mv88e6xxx_chip *chip, @@ -1271,9 +1307,31 @@ void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p) } } -static int mv88e6393x_serdes_port_errata(struct mv88e6xxx_chip *chip, int lane) +static int mv88e6393x_serdes_power_lane(struct mv88e6xxx_chip *chip, int lane, + bool on) { - u16 reg, pcs; + u16 reg; + int err; + + err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS, + MV88E6393X_SERDES_CTRL1, ®); + if (err) + return err; + + if (on) + reg &= ~(MV88E6393X_SERDES_CTRL1_TX_PDOWN | + MV88E6393X_SERDES_CTRL1_RX_PDOWN); + else + reg |= MV88E6393X_SERDES_CTRL1_TX_PDOWN | + MV88E6393X_SERDES_CTRL1_RX_PDOWN; + + return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS, + MV88E6393X_SERDES_CTRL1, reg); +} + +static int mv88e6393x_serdes_erratum_4_6(struct mv88e6xxx_chip *chip, int lane) +{ + u16 reg; int err; /* mv88e6393x family errata 4.6: @@ -1284,26 +1342,45 @@ static int mv88e6393x_serdes_port_errata(struct mv88e6xxx_chip *chip, int lane) * It seems that after this workaround the SERDES is automatically * powered up (the bit is cleared), so power it down. */ - if (lane == MV88E6393X_PORT0_LANE || lane == MV88E6393X_PORT9_LANE || - lane == MV88E6393X_PORT10_LANE) { - err = mv88e6390_serdes_read(chip, lane, - MDIO_MMD_PHYXS, - MV88E6393X_SERDES_POC, ®); - if (err) - return err; + err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS, + MV88E6393X_SERDES_POC, ®); + if (err) + return err; - reg &= ~MV88E6393X_SERDES_POC_PDOWN; - reg |= MV88E6393X_SERDES_POC_RESET; + reg &= ~MV88E6393X_SERDES_POC_PDOWN; + reg |= MV88E6393X_SERDES_POC_RESET; - err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS, - MV88E6393X_SERDES_POC, reg); - if (err) - return err; + err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS, + MV88E6393X_SERDES_POC, reg); + if (err) + return err; - err = mv88e6390_serdes_power_sgmii(chip, lane, false); - if (err) - return err; - } + err = mv88e6390_serdes_power_sgmii(chip, lane, false); + if (err) + return err; + + return mv88e6393x_serdes_power_lane(chip, lane, false); +} + +int mv88e6393x_serdes_setup_errata(struct mv88e6xxx_chip *chip) +{ + int err; + + err = mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT0_LANE); + if (err) + return err; + + err = mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT9_LANE); + if (err) + return err; + + return mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT10_LANE); +} + +static int mv88e6393x_serdes_erratum_4_8(struct mv88e6xxx_chip *chip, int lane) +{ + u16 reg, pcs; + int err; /* mv88e6393x family errata 4.8: * When a SERDES port is operating in 1000BASE-X or SGMII mode link may @@ -1334,38 +1411,149 @@ static int mv88e6393x_serdes_port_errata(struct mv88e6xxx_chip *chip, int lane) MV88E6393X_ERRATA_4_8_REG, reg); } -int mv88e6393x_serdes_setup_errata(struct mv88e6xxx_chip *chip) +static int mv88e6393x_serdes_erratum_5_2(struct mv88e6xxx_chip *chip, int lane, + u8 cmode) +{ + static const struct { + u16 dev, reg, val, mask; + } fixes[] = { + { MDIO_MMD_VEND1, 0x8093, 0xcb5a, 0xffff }, + { MDIO_MMD_VEND1, 0x8171, 0x7088, 0xffff }, + { MDIO_MMD_VEND1, 0x80c9, 0x311a, 0xffff }, + { MDIO_MMD_VEND1, 0x80a2, 0x8000, 0xff7f }, + { MDIO_MMD_VEND1, 0x80a9, 0x0000, 0xfff0 }, + { MDIO_MMD_VEND1, 0x80a3, 0x0000, 0xf8ff }, + { MDIO_MMD_PHYXS, MV88E6393X_SERDES_POC, + MV88E6393X_SERDES_POC_RESET, MV88E6393X_SERDES_POC_RESET }, + }; + int err, i; + u16 reg; + + /* mv88e6393x family errata 5.2: + * For optimal signal integrity the following sequence should be applied + * to SERDES operating in 10G mode. These registers only apply to 10G + * operation and have no effect on other speeds. + */ + if (cmode != MV88E6393X_PORT_STS_CMODE_10GBASER) + return 0; + + for (i = 0; i < ARRAY_SIZE(fixes); ++i) { + err = mv88e6390_serdes_read(chip, lane, fixes[i].dev, + fixes[i].reg, ®); + if (err) + return err; + + reg &= ~fixes[i].mask; + reg |= fixes[i].val; + + err = mv88e6390_serdes_write(chip, lane, fixes[i].dev, + fixes[i].reg, reg); + if (err) + return err; + } + + return 0; +} + +static int mv88e6393x_serdes_fix_2500basex_an(struct mv88e6xxx_chip *chip, + int lane, u8 cmode, bool on) { + u16 reg; int err; - err = mv88e6393x_serdes_port_errata(chip, MV88E6393X_PORT0_LANE); + if (cmode != MV88E6XXX_PORT_STS_CMODE_2500BASEX) + return 0; + + /* Inband AN is broken on Amethyst in 2500base-x mode when set by + * standard mechanism (via cmode). + * We can get around this by configuring the PCS mode to 1000base-x + * and then writing value 0x58 to register 1e.8000. (This must be done + * while SerDes receiver and transmitter are disabled, which is, when + * this function is called.) + * It seem that when we do this configuration to 2500base-x mode (by + * changing PCS mode to 1000base-x and frequency to 3.125 GHz from + * 1.25 GHz) and then configure to sgmii or 1000base-x, the device + * thinks that it already has SerDes at 1.25 GHz and does not change + * the 1e.8000 register, leaving SerDes at 3.125 GHz. + * To avoid this, change PCS mode back to 2500base-x when disabling + * SerDes from 2500base-x mode. + */ + err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS, + MV88E6393X_SERDES_POC, ®); + if (err) + return err; + + reg &= ~(MV88E6393X_SERDES_POC_PCS_MASK | MV88E6393X_SERDES_POC_AN); + if (on) + reg |= MV88E6393X_SERDES_POC_PCS_1000BASEX | + MV88E6393X_SERDES_POC_AN; + else + reg |= MV88E6393X_SERDES_POC_PCS_2500BASEX; + reg |= MV88E6393X_SERDES_POC_RESET; + + err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS, + MV88E6393X_SERDES_POC, reg); if (err) return err; - err = mv88e6393x_serdes_port_errata(chip, MV88E6393X_PORT9_LANE); + err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_VEND1, 0x8000, 0x58); if (err) return err; - return mv88e6393x_serdes_port_errata(chip, MV88E6393X_PORT10_LANE); + return 0; } int mv88e6393x_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane, bool on) { u8 cmode = chip->ports[port].cmode; + int err; if (port != 0 && port != 9 && port != 10) return -EOPNOTSUPP; + if (on) { + err = mv88e6393x_serdes_erratum_4_8(chip, lane); + if (err) + return err; + + err = mv88e6393x_serdes_erratum_5_2(chip, lane, cmode); + if (err) + return err; + + err = mv88e6393x_serdes_fix_2500basex_an(chip, lane, cmode, + true); + if (err) + return err; + + err = mv88e6393x_serdes_power_lane(chip, lane, true); + if (err) + return err; + } + switch (cmode) { case MV88E6XXX_PORT_STS_CMODE_SGMII: case MV88E6XXX_PORT_STS_CMODE_1000BASEX: case MV88E6XXX_PORT_STS_CMODE_2500BASEX: - return mv88e6390_serdes_power_sgmii(chip, lane, on); + err = mv88e6390_serdes_power_sgmii(chip, lane, on); + break; case MV88E6393X_PORT_STS_CMODE_5GBASER: case MV88E6393X_PORT_STS_CMODE_10GBASER: - return mv88e6390_serdes_power_10g(chip, lane, on); + err = mv88e6390_serdes_power_10g(chip, lane, on); + break; } - return 0; + if (err) + return err; + + if (!on) { + err = mv88e6393x_serdes_power_lane(chip, lane, false); + if (err) + return err; + + err = mv88e6393x_serdes_fix_2500basex_an(chip, lane, cmode, + false); + } + + return err; } diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index cbb3ba30caea..8dd8ed225b45 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -93,6 +93,10 @@ #define MV88E6393X_SERDES_POC_PCS_MASK 0x0007 #define MV88E6393X_SERDES_POC_RESET BIT(15) #define MV88E6393X_SERDES_POC_PDOWN BIT(5) +#define MV88E6393X_SERDES_POC_AN BIT(3) +#define MV88E6393X_SERDES_CTRL1 0xf003 +#define MV88E6393X_SERDES_CTRL1_TX_PDOWN BIT(9) +#define MV88E6393X_SERDES_CTRL1_RX_PDOWN BIT(8) #define MV88E6393X_ERRATA_4_8_REG 0xF074 #define MV88E6393X_ERRATA_4_8_BIT BIT(14) diff --git a/drivers/net/dsa/rtl8365mb.c b/drivers/net/dsa/rtl8365mb.c index baaae97283c5..078ca4cd7160 100644 --- a/drivers/net/dsa/rtl8365mb.c +++ b/drivers/net/dsa/rtl8365mb.c @@ -107,6 +107,7 @@ #define RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC 2112 /* Family-specific data and limits */ +#define RTL8365MB_PHYADDRMAX 7 #define RTL8365MB_NUM_PHYREGS 32 #define RTL8365MB_PHYREGMAX (RTL8365MB_NUM_PHYREGS - 1) #define RTL8365MB_MAX_NUM_PORTS (RTL8365MB_CPU_PORT_NUM_8365MB_VC + 1) @@ -176,7 +177,7 @@ #define RTL8365MB_INDIRECT_ACCESS_STATUS_REG 0x1F01 #define RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG 0x1F02 #define RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_5_1_MASK GENMASK(4, 0) -#define RTL8365MB_INDIRECT_ACCESS_ADDRESS_PHYNUM_MASK GENMASK(6, 5) +#define RTL8365MB_INDIRECT_ACCESS_ADDRESS_PHYNUM_MASK GENMASK(7, 5) #define RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_9_6_MASK GENMASK(11, 8) #define RTL8365MB_PHY_BASE 0x2000 #define RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG 0x1F03 @@ -679,6 +680,9 @@ static int rtl8365mb_phy_read(struct realtek_smi *smi, int phy, int regnum) u16 val; int ret; + if (phy > RTL8365MB_PHYADDRMAX) + return -EINVAL; + if (regnum > RTL8365MB_PHYREGMAX) return -EINVAL; @@ -704,6 +708,9 @@ static int rtl8365mb_phy_write(struct realtek_smi *smi, int phy, int regnum, u32 ocp_addr; int ret; + if (phy > RTL8365MB_PHYADDRMAX) + return -EINVAL; + if (regnum > RTL8365MB_PHYREGMAX) return -EINVAL; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h index 23b2d390fcdd..ace691d7cd75 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h @@ -40,10 +40,12 @@ #define AQ_DEVICE_ID_AQC113DEV 0x00C0 #define AQ_DEVICE_ID_AQC113CS 0x94C0 +#define AQ_DEVICE_ID_AQC113CA 0x34C0 #define AQ_DEVICE_ID_AQC114CS 0x93C0 #define AQ_DEVICE_ID_AQC113 0x04C0 #define AQ_DEVICE_ID_AQC113C 0x14C0 #define AQ_DEVICE_ID_AQC115C 0x12C0 +#define AQ_DEVICE_ID_AQC116C 0x11C0 #define HW_ATL_NIC_NAME "Marvell (aQuantia) AQtion 10Gbit Network Adapter" @@ -53,20 +55,19 @@ #define AQ_NIC_RATE_10G BIT(0) #define AQ_NIC_RATE_5G BIT(1) -#define AQ_NIC_RATE_5GSR BIT(2) -#define AQ_NIC_RATE_2G5 BIT(3) -#define AQ_NIC_RATE_1G BIT(4) -#define AQ_NIC_RATE_100M BIT(5) -#define AQ_NIC_RATE_10M BIT(6) -#define AQ_NIC_RATE_1G_HALF BIT(7) -#define AQ_NIC_RATE_100M_HALF BIT(8) -#define AQ_NIC_RATE_10M_HALF BIT(9) +#define AQ_NIC_RATE_2G5 BIT(2) +#define AQ_NIC_RATE_1G BIT(3) +#define AQ_NIC_RATE_100M BIT(4) +#define AQ_NIC_RATE_10M BIT(5) +#define AQ_NIC_RATE_1G_HALF BIT(6) +#define AQ_NIC_RATE_100M_HALF BIT(7) +#define AQ_NIC_RATE_10M_HALF BIT(8) -#define AQ_NIC_RATE_EEE_10G BIT(10) -#define AQ_NIC_RATE_EEE_5G BIT(11) -#define AQ_NIC_RATE_EEE_2G5 BIT(12) -#define AQ_NIC_RATE_EEE_1G BIT(13) -#define AQ_NIC_RATE_EEE_100M BIT(14) +#define AQ_NIC_RATE_EEE_10G BIT(9) +#define AQ_NIC_RATE_EEE_5G BIT(10) +#define AQ_NIC_RATE_EEE_2G5 BIT(11) +#define AQ_NIC_RATE_EEE_1G BIT(12) +#define AQ_NIC_RATE_EEE_100M BIT(13) #define AQ_NIC_RATE_EEE_MSK (AQ_NIC_RATE_EEE_10G |\ AQ_NIC_RATE_EEE_5G |\ AQ_NIC_RATE_EEE_2G5 |\ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index 062a300a566a..dbd284660135 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -80,6 +80,8 @@ struct aq_hw_link_status_s { }; struct aq_stats_s { + u64 brc; + u64 btc; u64 uprc; u64 mprc; u64 bprc; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 1acf544afeb4..33f1a1377588 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -316,18 +316,22 @@ int aq_nic_ndev_register(struct aq_nic_s *self) aq_macsec_init(self); #endif - mutex_lock(&self->fwreq_mutex); - err = self->aq_fw_ops->get_mac_permanent(self->aq_hw, addr); - mutex_unlock(&self->fwreq_mutex); - if (err) - goto err_exit; + if (platform_get_ethdev_address(&self->pdev->dev, self->ndev) != 0) { + // If DT has none or an invalid one, ask device for MAC address + mutex_lock(&self->fwreq_mutex); + err = self->aq_fw_ops->get_mac_permanent(self->aq_hw, addr); + mutex_unlock(&self->fwreq_mutex); - eth_hw_addr_set(self->ndev, addr); + if (err) + goto err_exit; - if (!is_valid_ether_addr(self->ndev->dev_addr) || - !aq_nic_is_valid_ether_addr(self->ndev->dev_addr)) { - netdev_warn(self->ndev, "MAC is invalid, will use random."); - eth_hw_addr_random(self->ndev); + if (is_valid_ether_addr(addr) && + aq_nic_is_valid_ether_addr(addr)) { + eth_hw_addr_set(self->ndev, addr); + } else { + netdev_warn(self->ndev, "MAC is invalid, will use random."); + eth_hw_addr_random(self->ndev); + } } #if defined(AQ_CFG_MAC_ADDR_PERMANENT) @@ -905,8 +909,14 @@ u64 *aq_nic_get_stats(struct aq_nic_s *self, u64 *data) data[++i] = stats->mbtc; data[++i] = stats->bbrc; data[++i] = stats->bbtc; - data[++i] = stats->ubrc + stats->mbrc + stats->bbrc; - data[++i] = stats->ubtc + stats->mbtc + stats->bbtc; + if (stats->brc) + data[++i] = stats->brc; + else + data[++i] = stats->ubrc + stats->mbrc + stats->bbrc; + if (stats->btc) + data[++i] = stats->btc; + else + data[++i] = stats->ubtc + stats->mbtc + stats->bbtc; data[++i] = stats->dma_pkt_rc; data[++i] = stats->dma_pkt_tc; data[++i] = stats->dma_oct_rc; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index d4b1976ee69b..797a95142d1f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -49,6 +49,8 @@ static const struct pci_device_id aq_pci_tbl[] = { { PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113), }, { PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113C), }, { PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC115C), }, + { PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113CA), }, + { PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC116C), }, {} }; @@ -85,7 +87,10 @@ static const struct aq_board_revision_s hw_atl_boards[] = { { AQ_DEVICE_ID_AQC113CS, AQ_HWREV_ANY, &hw_atl2_ops, &hw_atl2_caps_aqc113, }, { AQ_DEVICE_ID_AQC114CS, AQ_HWREV_ANY, &hw_atl2_ops, &hw_atl2_caps_aqc113, }, { AQ_DEVICE_ID_AQC113C, AQ_HWREV_ANY, &hw_atl2_ops, &hw_atl2_caps_aqc113, }, - { AQ_DEVICE_ID_AQC115C, AQ_HWREV_ANY, &hw_atl2_ops, &hw_atl2_caps_aqc113, }, + { AQ_DEVICE_ID_AQC115C, AQ_HWREV_ANY, &hw_atl2_ops, &hw_atl2_caps_aqc115c, }, + { AQ_DEVICE_ID_AQC113CA, AQ_HWREV_ANY, &hw_atl2_ops, &hw_atl2_caps_aqc113, }, + { AQ_DEVICE_ID_AQC116C, AQ_HWREV_ANY, &hw_atl2_ops, &hw_atl2_caps_aqc116c, }, + }; MODULE_DEVICE_TABLE(pci, aq_pci_tbl); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index d281322d7dd2..f4774cf051c9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -362,9 +362,6 @@ unsigned int aq_vec_get_sw_stats(struct aq_vec_s *self, const unsigned int tc, u { unsigned int count; - WARN_ONCE(!aq_vec_is_valid_tc(self, tc), - "Invalid tc %u (#rx=%u, #tx=%u)\n", - tc, self->rx_rings, self->tx_rings); if (!aq_vec_is_valid_tc(self, tc)) return 0; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index 3f1704cbe1cb..7e88d7234b14 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -867,12 +867,20 @@ static int hw_atl_fw1x_deinit(struct aq_hw_s *self) int hw_atl_utils_update_stats(struct aq_hw_s *self) { struct aq_stats_s *cs = &self->curr_stats; + struct aq_stats_s curr_stats = *cs; struct hw_atl_utils_mbox mbox; + bool corrupted_stats = false; hw_atl_utils_mpi_read_stats(self, &mbox); -#define AQ_SDELTA(_N_) (self->curr_stats._N_ += \ - mbox.stats._N_ - self->last_stats._N_) +#define AQ_SDELTA(_N_) \ +do { \ + if (!corrupted_stats && \ + ((s64)(mbox.stats._N_ - self->last_stats._N_)) >= 0) \ + curr_stats._N_ += mbox.stats._N_ - self->last_stats._N_; \ + else \ + corrupted_stats = true; \ +} while (0) if (self->aq_link_status.mbps) { AQ_SDELTA(uprc); @@ -892,6 +900,9 @@ int hw_atl_utils_update_stats(struct aq_hw_s *self) AQ_SDELTA(bbrc); AQ_SDELTA(bbtc); AQ_SDELTA(dpc); + + if (!corrupted_stats) + *cs = curr_stats; } #undef AQ_SDELTA diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index eac631c45c56..4d4cfbc91e19 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -132,9 +132,6 @@ static enum hw_atl_fw2x_rate link_speed_mask_2fw2x_ratemask(u32 speed) if (speed & AQ_NIC_RATE_5G) rate |= FW2X_RATE_5G; - if (speed & AQ_NIC_RATE_5GSR) - rate |= FW2X_RATE_5G; - if (speed & AQ_NIC_RATE_2G5) rate |= FW2X_RATE_2G5; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c index c98708bb044c..5dfc751572ed 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c @@ -65,11 +65,25 @@ const struct aq_hw_caps_s hw_atl2_caps_aqc113 = { AQ_NIC_RATE_5G | AQ_NIC_RATE_2G5 | AQ_NIC_RATE_1G | - AQ_NIC_RATE_1G_HALF | AQ_NIC_RATE_100M | - AQ_NIC_RATE_100M_HALF | - AQ_NIC_RATE_10M | - AQ_NIC_RATE_10M_HALF, + AQ_NIC_RATE_10M, +}; + +const struct aq_hw_caps_s hw_atl2_caps_aqc115c = { + DEFAULT_BOARD_BASIC_CAPABILITIES, + .media_type = AQ_HW_MEDIA_TYPE_TP, + .link_speed_msk = AQ_NIC_RATE_2G5 | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M | + AQ_NIC_RATE_10M, +}; + +const struct aq_hw_caps_s hw_atl2_caps_aqc116c = { + DEFAULT_BOARD_BASIC_CAPABILITIES, + .media_type = AQ_HW_MEDIA_TYPE_TP, + .link_speed_msk = AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M | + AQ_NIC_RATE_10M, }; static u32 hw_atl2_sem_act_rslvr_get(struct aq_hw_s *self) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h index de8723f1c28a..346f0dc9912e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h @@ -9,6 +9,8 @@ #include "aq_common.h" extern const struct aq_hw_caps_s hw_atl2_caps_aqc113; +extern const struct aq_hw_caps_s hw_atl2_caps_aqc115c; +extern const struct aq_hw_caps_s hw_atl2_caps_aqc116c; extern const struct aq_hw_ops hw_atl2_ops; #endif /* HW_ATL2_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h index b66fa346581c..6bad64c77b87 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h @@ -239,7 +239,8 @@ struct version_s { u8 minor; u16 build; } phy; - u32 rsvd; + u32 drv_iface_ver:4; + u32 rsvd:28; }; struct link_status_s { @@ -424,7 +425,7 @@ struct cable_diag_status_s { u16 rsvd2; }; -struct statistics_s { +struct statistics_a0_s { struct { u32 link_up; u32 link_down; @@ -457,6 +458,33 @@ struct statistics_s { u32 reserve_fw_gap; }; +struct __packed statistics_b0_s { + u64 rx_good_octets; + u64 rx_pause_frames; + u64 rx_good_frames; + u64 rx_errors; + u64 rx_unicast_frames; + u64 rx_multicast_frames; + u64 rx_broadcast_frames; + + u64 tx_good_octets; + u64 tx_pause_frames; + u64 tx_good_frames; + u64 tx_errors; + u64 tx_unicast_frames; + u64 tx_multicast_frames; + u64 tx_broadcast_frames; + + u32 main_loop_cycles; +}; + +struct __packed statistics_s { + union __packed { + struct statistics_a0_s a0; + struct statistics_b0_s b0; + }; +}; + struct filter_caps_s { u8 l2_filters_base_index:6; u8 flexible_filter_mask:2; @@ -545,7 +573,7 @@ struct management_status_s { u32 rsvd5; }; -struct fw_interface_out { +struct __packed fw_interface_out { struct transaction_counter_s transaction_id; struct version_s version; struct link_status_s link_status; @@ -569,7 +597,6 @@ struct fw_interface_out { struct core_dump_s core_dump; u32 rsvd11; struct statistics_s stats; - u32 rsvd12; struct filter_caps_s filter_caps; struct device_caps_s device_caps; u32 rsvd13; @@ -592,6 +619,9 @@ struct fw_interface_out { #define AQ_HOST_MODE_LOW_POWER 3U #define AQ_HOST_MODE_SHUTDOWN 4U +#define AQ_A2_FW_INTERFACE_A0 0 +#define AQ_A2_FW_INTERFACE_B0 1 + int hw_atl2_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops); int hw_atl2_utils_soft_reset(struct aq_hw_s *self); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c index dd259c8f2f4f..58d426dda3ed 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c @@ -84,7 +84,7 @@ static int hw_atl2_shared_buffer_read_block(struct aq_hw_s *self, if (cnt > AQ_A2_FW_READ_TRY_MAX) return -ETIME; if (tid1.transaction_cnt_a != tid1.transaction_cnt_b) - udelay(1); + mdelay(1); } while (tid1.transaction_cnt_a != tid1.transaction_cnt_b); hw_atl2_mif_shared_buf_read(self, offset, (u32 *)data, dwords); @@ -154,7 +154,7 @@ static void a2_link_speed_mask2fw(u32 speed, { link_options->rate_10G = !!(speed & AQ_NIC_RATE_10G); link_options->rate_5G = !!(speed & AQ_NIC_RATE_5G); - link_options->rate_N5G = !!(speed & AQ_NIC_RATE_5GSR); + link_options->rate_N5G = link_options->rate_5G; link_options->rate_2P5G = !!(speed & AQ_NIC_RATE_2G5); link_options->rate_N2P5G = link_options->rate_2P5G; link_options->rate_1G = !!(speed & AQ_NIC_RATE_1G); @@ -192,8 +192,6 @@ static u32 a2_fw_lkp_to_mask(struct lkp_link_caps_s *lkp_link_caps) rate |= AQ_NIC_RATE_10G; if (lkp_link_caps->rate_5G) rate |= AQ_NIC_RATE_5G; - if (lkp_link_caps->rate_N5G) - rate |= AQ_NIC_RATE_5GSR; if (lkp_link_caps->rate_2P5G) rate |= AQ_NIC_RATE_2G5; if (lkp_link_caps->rate_1G) @@ -335,15 +333,22 @@ static int aq_a2_fw_get_mac_permanent(struct aq_hw_s *self, u8 *mac) return 0; } -static int aq_a2_fw_update_stats(struct aq_hw_s *self) +static void aq_a2_fill_a0_stats(struct aq_hw_s *self, + struct statistics_s *stats) { struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv; - struct statistics_s stats; - - hw_atl2_shared_buffer_read_safe(self, stats, &stats); - -#define AQ_SDELTA(_N_, _F_) (self->curr_stats._N_ += \ - stats.msm._F_ - priv->last_stats.msm._F_) + struct aq_stats_s *cs = &self->curr_stats; + struct aq_stats_s curr_stats = *cs; + bool corrupted_stats = false; + +#define AQ_SDELTA(_N, _F) \ +do { \ + if (!corrupted_stats && \ + ((s64)(stats->a0.msm._F - priv->last_stats.a0.msm._F)) >= 0) \ + curr_stats._N += stats->a0.msm._F - priv->last_stats.a0.msm._F;\ + else \ + corrupted_stats = true; \ +} while (0) if (self->aq_link_status.mbps) { AQ_SDELTA(uprc, rx_unicast_frames); @@ -362,17 +367,76 @@ static int aq_a2_fw_update_stats(struct aq_hw_s *self) AQ_SDELTA(mbtc, tx_multicast_octets); AQ_SDELTA(bbrc, rx_broadcast_octets); AQ_SDELTA(bbtc, tx_broadcast_octets); + + if (!corrupted_stats) + *cs = curr_stats; } #undef AQ_SDELTA - self->curr_stats.dma_pkt_rc = - hw_atl_stats_rx_dma_good_pkt_counter_get(self); - self->curr_stats.dma_pkt_tc = - hw_atl_stats_tx_dma_good_pkt_counter_get(self); - self->curr_stats.dma_oct_rc = - hw_atl_stats_rx_dma_good_octet_counter_get(self); - self->curr_stats.dma_oct_tc = - hw_atl_stats_tx_dma_good_octet_counter_get(self); - self->curr_stats.dpc = hw_atl_rpb_rx_dma_drop_pkt_cnt_get(self); + +} + +static void aq_a2_fill_b0_stats(struct aq_hw_s *self, + struct statistics_s *stats) +{ + struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv; + struct aq_stats_s *cs = &self->curr_stats; + struct aq_stats_s curr_stats = *cs; + bool corrupted_stats = false; + +#define AQ_SDELTA(_N, _F) \ +do { \ + if (!corrupted_stats && \ + ((s64)(stats->b0._F - priv->last_stats.b0._F)) >= 0) \ + curr_stats._N += stats->b0._F - priv->last_stats.b0._F; \ + else \ + corrupted_stats = true; \ +} while (0) + + if (self->aq_link_status.mbps) { + AQ_SDELTA(uprc, rx_unicast_frames); + AQ_SDELTA(mprc, rx_multicast_frames); + AQ_SDELTA(bprc, rx_broadcast_frames); + AQ_SDELTA(erpr, rx_errors); + AQ_SDELTA(brc, rx_good_octets); + + AQ_SDELTA(uptc, tx_unicast_frames); + AQ_SDELTA(mptc, tx_multicast_frames); + AQ_SDELTA(bptc, tx_broadcast_frames); + AQ_SDELTA(erpt, tx_errors); + AQ_SDELTA(btc, tx_good_octets); + + if (!corrupted_stats) + *cs = curr_stats; + } +#undef AQ_SDELTA +} + +static int aq_a2_fw_update_stats(struct aq_hw_s *self) +{ + struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv; + struct aq_stats_s *cs = &self->curr_stats; + struct statistics_s stats; + struct version_s version; + int err; + + err = hw_atl2_shared_buffer_read_safe(self, version, &version); + if (err) + return err; + + err = hw_atl2_shared_buffer_read_safe(self, stats, &stats); + if (err) + return err; + + if (version.drv_iface_ver == AQ_A2_FW_INTERFACE_A0) + aq_a2_fill_a0_stats(self, &stats); + else + aq_a2_fill_b0_stats(self, &stats); + + cs->dma_pkt_rc = hw_atl_stats_rx_dma_good_pkt_counter_get(self); + cs->dma_pkt_tc = hw_atl_stats_tx_dma_good_pkt_counter_get(self); + cs->dma_oct_rc = hw_atl_stats_rx_dma_good_octet_counter_get(self); + cs->dma_oct_tc = hw_atl_stats_tx_dma_good_octet_counter_get(self); + cs->dpc = hw_atl_rpb_rx_dma_drop_pkt_cnt_get(self); memcpy(&priv->last_stats, &stats, sizeof(stats)); @@ -499,9 +563,9 @@ u32 hw_atl2_utils_get_fw_version(struct aq_hw_s *self) hw_atl2_shared_buffer_read_safe(self, version, &version); /* A2 FW version is stored in reverse order */ - return version.mac.major << 24 | - version.mac.minor << 16 | - version.mac.build; + return version.bundle.major << 24 | + version.bundle.minor << 16 | + version.bundle.build; } int hw_atl2_utils_get_action_resolve_table_caps(struct aq_hw_s *self, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 6451c8383639..8e643567abce 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4550,6 +4550,8 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) fsl_mc_portal_free(priv->mc_io); + destroy_workqueue(priv->dpaa2_ptp_wq); + dev_dbg(net_dev->dev.parent, "Removed interface %s\n", net_dev->name); free_netdev(net_dev); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 3cca51735421..0bb3911dd014 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -628,17 +628,9 @@ static bool reuse_rx_pools(struct ibmvnic_adapter *adapter) old_buff_size = adapter->prev_rx_buf_sz; new_buff_size = adapter->cur_rx_buf_sz; - /* Require buff size to be exactly same for now */ - if (old_buff_size != new_buff_size) - return false; - - if (old_num_pools == new_num_pools && old_pool_size == new_pool_size) - return true; - - if (old_num_pools < adapter->min_rx_queues || - old_num_pools > adapter->max_rx_queues || - old_pool_size < adapter->min_rx_add_entries_per_subcrq || - old_pool_size > adapter->max_rx_add_entries_per_subcrq) + if (old_buff_size != new_buff_size || + old_num_pools != new_num_pools || + old_pool_size != new_pool_size) return false; return true; @@ -874,17 +866,9 @@ static bool reuse_tx_pools(struct ibmvnic_adapter *adapter) old_mtu = adapter->prev_mtu; new_mtu = adapter->req_mtu; - /* Require MTU to be exactly same to reuse pools for now */ - if (old_mtu != new_mtu) - return false; - - if (old_num_pools == new_num_pools && old_pool_size == new_pool_size) - return true; - - if (old_num_pools < adapter->min_tx_queues || - old_num_pools > adapter->max_tx_queues || - old_pool_size < adapter->min_tx_entries_per_subcrq || - old_pool_size > adapter->max_tx_entries_per_subcrq) + if (old_mtu != new_mtu || + old_num_pools != new_num_pools || + old_pool_size != new_pool_size) return false; return true; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index ff55cb415b11..bb9a80847298 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -383,6 +383,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) while (i--) { dma = xsk_buff_xdp_get_dma(*xdp); rx_desc->read.pkt_addr = cpu_to_le64(dma); + rx_desc->wb.status_error0 = 0; rx_desc++; xdp++; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index ce486e16489c..6480696c979b 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -7458,7 +7458,7 @@ static int mvpp2_probe(struct platform_device *pdev) shared = num_present_cpus() - priv->nthreads; if (shared > 0) - bitmap_fill(&priv->lock_map, + bitmap_set(&priv->lock_map, 0, min_t(int, shared, MVPP2_MAX_THREADS)); for (i = 0; i < MVPP2_MAX_THREADS; i++) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index cb56e171ddd4..3ca6b942ebe2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2341,7 +2341,7 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, goto free_regions; break; default: - return err; + goto free_regions; } mw->mbox_wq = alloc_workqueue(name, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 066d79e4ecfc..10238bedd694 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -670,7 +670,7 @@ void __init mlx4_en_init_ptys2ethtool_map(void) MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_T, SPEED_1000, ETHTOOL_LINK_MODE_1000baseT_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_CX_SGMII, SPEED_1000, - ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); + ETHTOOL_LINK_MODE_1000baseX_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_KX, SPEED_1000, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_T, SPEED_10000, @@ -682,9 +682,9 @@ void __init mlx4_en_init_ptys2ethtool_map(void) MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_KR, SPEED_10000, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_CR, SPEED_10000, - ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + ETHTOOL_LINK_MODE_10000baseCR_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_SR, SPEED_10000, - ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + ETHTOOL_LINK_MODE_10000baseSR_Full_BIT); MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_20GBASE_KR2, SPEED_20000, ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT, ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 3f6d5c384637..f1c10f2bda78 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2286,9 +2286,14 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, bool carry_xdp_prog) { struct bpf_prog *xdp_prog; - int i, t; + int i, t, ret; - mlx4_en_copy_priv(tmp, priv, prof); + ret = mlx4_en_copy_priv(tmp, priv, prof); + if (ret) { + en_warn(priv, "%s: mlx4_en_copy_priv() failed, return\n", + __func__); + return ret; + } if (mlx4_en_alloc_resources(tmp)) { en_warn(priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 8eaa24d865c5..a46284ca5172 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -341,6 +341,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_DEALLOC_SF: case MLX5_CMD_OP_DESTROY_UCTX: case MLX5_CMD_OP_DESTROY_UMEM: + case MLX5_CMD_OP_MODIFY_RQT: return MLX5_CMD_STAT_OK; case MLX5_CMD_OP_QUERY_HCA_CAP: @@ -446,7 +447,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_MODIFY_TIS: case MLX5_CMD_OP_QUERY_TIS: case MLX5_CMD_OP_CREATE_RQT: - case MLX5_CMD_OP_MODIFY_RQT: case MLX5_CMD_OP_QUERY_RQT: case MLX5_CMD_OP_CREATE_FLOW_TABLE: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c index 142953847996..0015a81eb9a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c @@ -13,6 +13,9 @@ struct mlx5e_rx_res { unsigned int max_nch; u32 drop_rqn; + struct mlx5e_packet_merge_param pkt_merge_param; + struct rw_semaphore pkt_merge_param_sem; + struct mlx5e_rss *rss[MLX5E_MAX_NUM_RSS]; bool rss_active; u32 rss_rqns[MLX5E_INDIR_RQT_SIZE]; @@ -392,6 +395,7 @@ static int mlx5e_rx_res_ptp_init(struct mlx5e_rx_res *res) if (err) goto out; + /* Separated from the channels RQs, does not share pkt_merge state with them */ mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, mlx5e_rqt_get_rqtn(&res->ptp.rqt), inner_ft_support); @@ -447,6 +451,9 @@ int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev, res->max_nch = max_nch; res->drop_rqn = drop_rqn; + res->pkt_merge_param = *init_pkt_merge_param; + init_rwsem(&res->pkt_merge_param_sem); + err = mlx5e_rx_res_rss_init_def(res, init_pkt_merge_param, init_nch); if (err) goto err_out; @@ -513,7 +520,7 @@ u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res) return mlx5e_tir_get_tirn(&res->ptp.tir); } -u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix) +static u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix) { return mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt); } @@ -656,6 +663,9 @@ int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res, if (!builder) return -ENOMEM; + down_write(&res->pkt_merge_param_sem); + res->pkt_merge_param = *pkt_merge_param; + mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param); final_err = 0; @@ -681,6 +691,7 @@ int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res, } } + up_write(&res->pkt_merge_param_sem); mlx5e_tir_builder_free(builder); return final_err; } @@ -689,3 +700,31 @@ struct mlx5e_rss_params_hash mlx5e_rx_res_get_current_hash(struct mlx5e_rx_res * { return mlx5e_rss_get_hash(res->rss[0]); } + +int mlx5e_rx_res_tls_tir_create(struct mlx5e_rx_res *res, unsigned int rxq, + struct mlx5e_tir *tir) +{ + bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT; + struct mlx5e_tir_builder *builder; + u32 rqtn; + int err; + + builder = mlx5e_tir_builder_alloc(false); + if (!builder) + return -ENOMEM; + + rqtn = mlx5e_rx_res_get_rqtn_direct(res, rxq); + + mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, rqtn, + inner_ft_support); + mlx5e_tir_builder_build_direct(builder); + mlx5e_tir_builder_build_tls(builder); + down_read(&res->pkt_merge_param_sem); + mlx5e_tir_builder_build_packet_merge(builder, &res->pkt_merge_param); + err = mlx5e_tir_init(tir, builder, res->mdev, false); + up_read(&res->pkt_merge_param_sem); + + mlx5e_tir_builder_free(builder); + + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h index d09f7d174a51..b39b20a720e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h @@ -37,9 +37,6 @@ u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt); u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res); -/* RQTN getters for modules that create their own TIRs */ -u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix); - /* Activate/deactivate API */ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs); void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res); @@ -69,4 +66,7 @@ struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx); /* Workaround for hairpin */ struct mlx5e_rss_params_hash mlx5e_rx_res_get_current_hash(struct mlx5e_rx_res *res); +/* Accel TIRs */ +int mlx5e_rx_res_tls_tir_create(struct mlx5e_rx_res *res, unsigned int rxq, + struct mlx5e_tir *tir); #endif /* __MLX5_EN_RX_RES_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index fb5397324aa4..2db9573a3fe6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -191,7 +191,7 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; eseg->swp_inner_l4_offset = (skb->csum_start + skb->head - skb->data) / 2; - if (skb->protocol == htons(ETH_P_IPV6)) + if (inner_ip_hdr(skb)->version == 6) eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; break; default: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index a2a9f68579dd..15711814d2d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -100,25 +100,6 @@ mlx5e_ktls_rx_resync_create_resp_list(void) return resp_list; } -static int mlx5e_ktls_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir, u32 rqtn) -{ - struct mlx5e_tir_builder *builder; - int err; - - builder = mlx5e_tir_builder_alloc(false); - if (!builder) - return -ENOMEM; - - mlx5e_tir_builder_build_rqt(builder, mdev->mlx5e_res.hw_objs.td.tdn, rqtn, false); - mlx5e_tir_builder_build_direct(builder); - mlx5e_tir_builder_build_tls(builder); - err = mlx5e_tir_init(tir, builder, mdev, false); - - mlx5e_tir_builder_free(builder); - - return err; -} - static void accel_rule_handle_work(struct work_struct *work) { struct mlx5e_ktls_offload_context_rx *priv_rx; @@ -609,7 +590,6 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, struct mlx5_core_dev *mdev; struct mlx5e_priv *priv; int rxq, err; - u32 rqtn; tls_ctx = tls_get_ctx(sk); priv = netdev_priv(netdev); @@ -635,9 +615,7 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, priv_rx->sw_stats = &priv->tls->sw_stats; mlx5e_set_ktls_rx_priv_ctx(tls_ctx, priv_rx); - rqtn = mlx5e_rx_res_get_rqtn_direct(priv->rx_res, rxq); - - err = mlx5e_ktls_create_tir(mdev, &priv_rx->tir, rqtn); + err = mlx5e_rx_res_tls_tir_create(priv->rx_res, rxq, &priv_rx->tir); if (err) goto err_create_tir; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index e58a9ec42553..48895d79796a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1080,6 +1080,10 @@ static mlx5e_stats_grp_t mlx5e_ul_rep_stats_grps[] = { &MLX5E_STATS_GRP(pme), &MLX5E_STATS_GRP(channels), &MLX5E_STATS_GRP(per_port_buff_congest), +#ifdef CONFIG_MLX5_EN_IPSEC + &MLX5E_STATS_GRP(ipsec_sw), + &MLX5E_STATS_GRP(ipsec_hw), +#endif }; static unsigned int mlx5e_ul_rep_stats_grps_num(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 96967b0a2441..793511d5ee4c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -543,13 +543,13 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, u16 klm_entries, u16 index) { struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; - u16 entries, pi, i, header_offset, err, wqe_bbs, new_entries; + u16 entries, pi, header_offset, err, wqe_bbs, new_entries; u32 lkey = rq->mdev->mlx5e_res.hw_objs.mkey; struct page *page = shampo->last_page; u64 addr = shampo->last_addr; struct mlx5e_dma_info *dma_info; struct mlx5e_umr_wqe *umr_wqe; - int headroom; + int headroom, i; headroom = rq->buff.headroom; new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_ALIGNMENT - 1)); @@ -601,9 +601,7 @@ update_klm: err_unmap: while (--i >= 0) { - if (--index < 0) - index = shampo->hd_per_wq - 1; - dma_info = &shampo->info[index]; + dma_info = &shampo->info[--index]; if (!(i & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1))) { dma_info->addr = ALIGN_DOWN(dma_info->addr, PAGE_SIZE); mlx5e_page_release(rq, dma_info, true); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index c6cc67cb4f6a..d377ddc70fc7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -130,7 +130,7 @@ static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw, /* If vports min rate divider is 0 but their group has bw_share configured, then * need to set bw_share for vports to minimal value. */ - if (!group_level && !max_guarantee && group->bw_share) + if (!group_level && !max_guarantee && group && group->bw_share) return 1; return 0; } @@ -423,7 +423,7 @@ static int esw_qos_vport_update_group(struct mlx5_eswitch *esw, return err; /* Recalculate bw share weights of old and new groups */ - if (vport->qos.bw_share) { + if (vport->qos.bw_share || new_group->bw_share) { esw_qos_normalize_vports_min_rate(esw, curr_group, extack); esw_qos_normalize_vports_min_rate(esw, new_group, extack); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index a46455694f7a..32bc08a39925 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -329,14 +329,25 @@ static bool esw_is_indir_table(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr) { struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + bool result = false; int i; - for (i = esw_attr->split_count; i < esw_attr->out_count; i++) + /* Indirect table is supported only for flows with in_port uplink + * and the destination is vport on the same eswitch as the uplink, + * return false in case at least one of destinations doesn't meet + * this criteria. + */ + for (i = esw_attr->split_count; i < esw_attr->out_count; i++) { if (esw_attr->dests[i].rep && mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport, - esw_attr->dests[i].mdev)) - return true; - return false; + esw_attr->dests[i].mdev)) { + result = true; + } else { + result = false; + break; + } + } + return result; } static int @@ -2512,6 +2523,7 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master, struct mlx5_eswitch *esw = master->priv.eswitch; struct mlx5_flow_table_attr ft_attr = { .max_fte = 1, .prio = 0, .level = 0, + .flags = MLX5_FLOW_TABLE_OTHER_VPORT, }; struct mlx5_flow_namespace *egress_ns; struct mlx5_flow_table *acl; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 64f1abc4dc36..3ca998874c50 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -835,6 +835,9 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) health->timer.expires = jiffies + msecs_to_jiffies(poll_interval_ms); add_timer(&health->timer); + + if (mlx5_core_is_pf(dev) && MLX5_CAP_MCAM_REG(dev, mrtc)) + queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0); } void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health) @@ -902,8 +905,6 @@ int mlx5_health_init(struct mlx5_core_dev *dev) INIT_WORK(&health->fatal_report_work, mlx5_fw_fatal_reporter_err_work); INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work); INIT_DELAYED_WORK(&health->update_fw_log_ts_work, mlx5_health_log_ts_update); - if (mlx5_core_is_pf(dev)) - queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index ad63dd45c8fb..a6592f9c3c05 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -608,4 +608,5 @@ void mlx5_lag_port_sel_destroy(struct mlx5_lag *ldev) if (port_sel->tunnel) mlx5_destroy_ttc_table(port_sel->inner.ttc); mlx5_lag_destroy_definers(ldev); + memset(port_sel, 0, sizeof(*port_sel)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c index 0dd96a6b140d..c1df0d3595d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c @@ -31,11 +31,11 @@ static void tout_set(struct mlx5_core_dev *dev, u64 val, enum mlx5_timeouts_type dev->timeouts->to[type] = val; } -static void tout_set_def_val(struct mlx5_core_dev *dev) +void mlx5_tout_set_def_val(struct mlx5_core_dev *dev) { int i; - for (i = MLX5_TO_FW_PRE_INIT_TIMEOUT_MS; i < MAX_TIMEOUT_TYPES; i++) + for (i = 0; i < MAX_TIMEOUT_TYPES; i++) tout_set(dev, tout_def_sw_val[i], i); } @@ -45,7 +45,6 @@ int mlx5_tout_init(struct mlx5_core_dev *dev) if (!dev->timeouts) return -ENOMEM; - tout_set_def_val(dev); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h index 31faa5c17aa9..1c42ead782fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h @@ -34,6 +34,7 @@ int mlx5_tout_init(struct mlx5_core_dev *dev); void mlx5_tout_cleanup(struct mlx5_core_dev *dev); void mlx5_tout_query_iseg(struct mlx5_core_dev *dev); int mlx5_tout_query_dtor(struct mlx5_core_dev *dev); +void mlx5_tout_set_def_val(struct mlx5_core_dev *dev); u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type); #define mlx5_tout_ms(dev, type) _mlx5_tout_ms(dev, MLX5_TO_##type##_MS) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index a92a92a52346..7df9c7f8d9c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -992,11 +992,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) if (mlx5_core_is_pf(dev)) pcie_print_link_status(dev->pdev); - err = mlx5_tout_init(dev); - if (err) { - mlx5_core_err(dev, "Failed initializing timeouts, aborting\n"); - return err; - } + mlx5_tout_set_def_val(dev); /* wait for firmware to accept initialization segments configurations */ @@ -1005,13 +1001,13 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) if (err) { mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n", mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT)); - goto err_tout_cleanup; + return err; } err = mlx5_cmd_init(dev); if (err) { mlx5_core_err(dev, "Failed initializing command interface, aborting\n"); - goto err_tout_cleanup; + return err; } mlx5_tout_query_iseg(dev); @@ -1075,18 +1071,16 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) mlx5_set_driver_version(dev); - mlx5_start_health_poll(dev); - err = mlx5_query_hca_caps(dev); if (err) { mlx5_core_err(dev, "query hca failed\n"); - goto stop_health; + goto reclaim_boot_pages; } + mlx5_start_health_poll(dev); + return 0; -stop_health: - mlx5_stop_health_poll(dev, boot); reclaim_boot_pages: mlx5_reclaim_startup_pages(dev); err_disable_hca: @@ -1094,8 +1088,6 @@ err_disable_hca: err_cmd_cleanup: mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); -err_tout_cleanup: - mlx5_tout_cleanup(dev); return err; } @@ -1114,7 +1106,6 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) mlx5_core_disable_hca(dev, 0); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); - mlx5_tout_cleanup(dev); return 0; } @@ -1476,6 +1467,12 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) mlx5_debugfs_root); INIT_LIST_HEAD(&priv->traps); + err = mlx5_tout_init(dev); + if (err) { + mlx5_core_err(dev, "Failed initializing timeouts, aborting\n"); + goto err_timeout_init; + } + err = mlx5_health_init(dev); if (err) goto err_health_init; @@ -1501,6 +1498,8 @@ err_adev_init: err_pagealloc_init: mlx5_health_cleanup(dev); err_health_init: + mlx5_tout_cleanup(dev); +err_timeout_init: debugfs_remove(dev->priv.dbg_root); mutex_destroy(&priv->pgdir_mutex); mutex_destroy(&priv->alloc_mutex); @@ -1518,6 +1517,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev) mlx5_adev_cleanup(dev); mlx5_pagealloc_cleanup(dev); mlx5_health_cleanup(dev); + mlx5_tout_cleanup(dev); debugfs_remove_recursive(dev->priv.dbg_root); mutex_destroy(&priv->pgdir_mutex); mutex_destroy(&priv->alloc_mutex); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 409cde1e59c6..1e4ad953cffb 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1563,8 +1563,10 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) } err = ocelot_setup_ptp_traps(ocelot, port, l2, l4); - if (err) + if (err) { + mutex_unlock(&ocelot->ptp_lock); return err; + } if (l2 && l4) cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c index ca4686094701..0a02d8bd0a3e 100644 --- a/drivers/net/ethernet/natsemi/xtsonic.c +++ b/drivers/net/ethernet/natsemi/xtsonic.c @@ -120,7 +120,7 @@ static const struct net_device_ops xtsonic_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, }; -static int __init sonic_probe1(struct net_device *dev) +static int sonic_probe1(struct net_device *dev) { unsigned int silicon_revision; struct sonic_local *lp = netdev_priv(dev); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index d51bac7ba5af..bd0607680329 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -1077,8 +1077,14 @@ static int qlcnic_83xx_add_rings(struct qlcnic_adapter *adapter) sds_mbx_size = sizeof(struct qlcnic_sds_mbx); context_id = recv_ctx->context_id; num_sds = adapter->drv_sds_rings - QLCNIC_MAX_SDS_RINGS; - ahw->hw_ops->alloc_mbx_args(&cmd, adapter, - QLCNIC_CMD_ADD_RCV_RINGS); + err = ahw->hw_ops->alloc_mbx_args(&cmd, adapter, + QLCNIC_CMD_ADD_RCV_RINGS); + if (err) { + dev_err(&adapter->pdev->dev, + "Failed to alloc mbx args %d\n", err); + return err; + } + cmd.req.arg[1] = 0 | (num_sds << 8) | (context_id << 16); /* set up status rings, mbx 2-81 */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 748195697e5a..da8306f60730 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5540,8 +5540,6 @@ static int stmmac_set_features(struct net_device *netdev, netdev_features_t features) { struct stmmac_priv *priv = netdev_priv(netdev); - bool sph_en; - u32 chan; /* Keep the COE Type in case of csum is supporting */ if (features & NETIF_F_RXCSUM) @@ -5553,10 +5551,13 @@ static int stmmac_set_features(struct net_device *netdev, */ stmmac_rx_ipc(priv, priv->hw); - sph_en = (priv->hw->rx_csum > 0) && priv->sph; + if (priv->sph_cap) { + bool sph_en = (priv->hw->rx_csum > 0) && priv->sph; + u32 chan; - for (chan = 0; chan < priv->plat->rx_queues_to_use; chan++) - stmmac_enable_sph(priv, priv->ioaddr, sph_en, chan); + for (chan = 0; chan < priv->plat->rx_queues_to_use; chan++) + stmmac_enable_sph(priv, priv->ioaddr, sph_en, chan); + } return 0; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index f20376c1ef3f..8cd265fc1fd9 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2228,7 +2228,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) if (dev->domain_data.phyirq > 0) phydev->irq = dev->domain_data.phyirq; else - phydev->irq = 0; + phydev->irq = PHY_POLL; netdev_dbg(dev->net, "phydev->irq = %d\n", phydev->irq); /* set to AUTOMDIX */ diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index ccf677015d5b..131c745dc701 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -497,6 +497,7 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); ret = vrf_ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(ret))) dev->stats.tx_errors++; @@ -579,6 +580,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, RT_SCOPE_LINK); } + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); if (unlikely(net_xmit_eval(ret))) vrf_dev->stats.tx_errors++; diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index b7197e80f226..9a4c8ff32d9d 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -163,7 +163,7 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key, return exact; } -static inline void connect_node(struct allowedips_node **parent, u8 bit, struct allowedips_node *node) +static inline void connect_node(struct allowedips_node __rcu **parent, u8 bit, struct allowedips_node *node) { node->parent_bit_packed = (unsigned long)parent | bit; rcu_assign_pointer(*parent, node); diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 551ddaaaf540..a46067c38bf5 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -98,6 +98,7 @@ static int wg_stop(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); struct wg_peer *peer; + struct sk_buff *skb; mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) { @@ -108,7 +109,9 @@ static int wg_stop(struct net_device *dev) wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); } mutex_unlock(&wg->device_update_lock); - skb_queue_purge(&wg->incoming_handshakes); + while ((skb = ptr_ring_consume(&wg->handshake_queue.ring)) != NULL) + kfree_skb(skb); + atomic_set(&wg->handshake_queue_len, 0); wg_socket_reinit(wg, NULL, NULL); return 0; } @@ -235,14 +238,13 @@ static void wg_destruct(struct net_device *dev) destroy_workqueue(wg->handshake_receive_wq); destroy_workqueue(wg->handshake_send_wq); destroy_workqueue(wg->packet_crypt_wq); - wg_packet_queue_free(&wg->decrypt_queue); - wg_packet_queue_free(&wg->encrypt_queue); + wg_packet_queue_free(&wg->handshake_queue, true); + wg_packet_queue_free(&wg->decrypt_queue, false); + wg_packet_queue_free(&wg->encrypt_queue, false); rcu_barrier(); /* Wait for all the peers to be actually freed. */ wg_ratelimiter_uninit(); memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); - skb_queue_purge(&wg->incoming_handshakes); free_percpu(dev->tstats); - free_percpu(wg->incoming_handshakes_worker); kvfree(wg->index_hashtable); kvfree(wg->peer_hashtable); mutex_unlock(&wg->device_update_lock); @@ -298,7 +300,6 @@ static int wg_newlink(struct net *src_net, struct net_device *dev, init_rwsem(&wg->static_identity.lock); mutex_init(&wg->socket_update_lock); mutex_init(&wg->device_update_lock); - skb_queue_head_init(&wg->incoming_handshakes); wg_allowedips_init(&wg->peer_allowedips); wg_cookie_checker_init(&wg->cookie_checker, wg); INIT_LIST_HEAD(&wg->peer_list); @@ -316,16 +317,10 @@ static int wg_newlink(struct net *src_net, struct net_device *dev, if (!dev->tstats) goto err_free_index_hashtable; - wg->incoming_handshakes_worker = - wg_packet_percpu_multicore_worker_alloc( - wg_packet_handshake_receive_worker, wg); - if (!wg->incoming_handshakes_worker) - goto err_free_tstats; - wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s", WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name); if (!wg->handshake_receive_wq) - goto err_free_incoming_handshakes; + goto err_free_tstats; wg->handshake_send_wq = alloc_workqueue("wg-kex-%s", WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name); @@ -347,10 +342,15 @@ static int wg_newlink(struct net *src_net, struct net_device *dev, if (ret < 0) goto err_free_encrypt_queue; - ret = wg_ratelimiter_init(); + ret = wg_packet_queue_init(&wg->handshake_queue, wg_packet_handshake_receive_worker, + MAX_QUEUED_INCOMING_HANDSHAKES); if (ret < 0) goto err_free_decrypt_queue; + ret = wg_ratelimiter_init(); + if (ret < 0) + goto err_free_handshake_queue; + ret = register_netdevice(dev); if (ret < 0) goto err_uninit_ratelimiter; @@ -367,18 +367,18 @@ static int wg_newlink(struct net *src_net, struct net_device *dev, err_uninit_ratelimiter: wg_ratelimiter_uninit(); +err_free_handshake_queue: + wg_packet_queue_free(&wg->handshake_queue, false); err_free_decrypt_queue: - wg_packet_queue_free(&wg->decrypt_queue); + wg_packet_queue_free(&wg->decrypt_queue, false); err_free_encrypt_queue: - wg_packet_queue_free(&wg->encrypt_queue); + wg_packet_queue_free(&wg->encrypt_queue, false); err_destroy_packet_crypt: destroy_workqueue(wg->packet_crypt_wq); err_destroy_handshake_send: destroy_workqueue(wg->handshake_send_wq); err_destroy_handshake_receive: destroy_workqueue(wg->handshake_receive_wq); -err_free_incoming_handshakes: - free_percpu(wg->incoming_handshakes_worker); err_free_tstats: free_percpu(dev->tstats); err_free_index_hashtable: @@ -398,6 +398,7 @@ static struct rtnl_link_ops link_ops __read_mostly = { static void wg_netns_pre_exit(struct net *net) { struct wg_device *wg; + struct wg_peer *peer; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { @@ -407,6 +408,8 @@ static void wg_netns_pre_exit(struct net *net) mutex_lock(&wg->device_update_lock); rcu_assign_pointer(wg->creating_net, NULL); wg_socket_reinit(wg, NULL, NULL); + list_for_each_entry(peer, &wg->peer_list, peer_list) + wg_socket_clear_peer_endpoint_src(peer); mutex_unlock(&wg->device_update_lock); } } diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h index 854bc3d97150..43c7cebbf50b 100644 --- a/drivers/net/wireguard/device.h +++ b/drivers/net/wireguard/device.h @@ -39,21 +39,18 @@ struct prev_queue { struct wg_device { struct net_device *dev; - struct crypt_queue encrypt_queue, decrypt_queue; + struct crypt_queue encrypt_queue, decrypt_queue, handshake_queue; struct sock __rcu *sock4, *sock6; struct net __rcu *creating_net; struct noise_static_identity static_identity; - struct workqueue_struct *handshake_receive_wq, *handshake_send_wq; - struct workqueue_struct *packet_crypt_wq; - struct sk_buff_head incoming_handshakes; - int incoming_handshake_cpu; - struct multicore_worker __percpu *incoming_handshakes_worker; + struct workqueue_struct *packet_crypt_wq,*handshake_receive_wq, *handshake_send_wq; struct cookie_checker cookie_checker; struct pubkey_hashtable *peer_hashtable; struct index_hashtable *index_hashtable; struct allowedips peer_allowedips; struct mutex device_update_lock, socket_update_lock; struct list_head device_list, peer_list; + atomic_t handshake_queue_len; unsigned int num_peers, device_update_gen; u32 fwmark; u16 incoming_port; diff --git a/drivers/net/wireguard/main.c b/drivers/net/wireguard/main.c index 75dbe77b0b4b..ee4da9ab8013 100644 --- a/drivers/net/wireguard/main.c +++ b/drivers/net/wireguard/main.c @@ -17,7 +17,7 @@ #include <linux/genetlink.h> #include <net/rtnetlink.h> -static int __init mod_init(void) +static int __init wg_mod_init(void) { int ret; @@ -60,7 +60,7 @@ err_allowedips: return ret; } -static void __exit mod_exit(void) +static void __exit wg_mod_exit(void) { wg_genetlink_uninit(); wg_device_uninit(); @@ -68,8 +68,8 @@ static void __exit mod_exit(void) wg_allowedips_slab_uninit(); } -module_init(mod_init); -module_exit(mod_exit); +module_init(wg_mod_init); +module_exit(wg_mod_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("WireGuard secure network tunnel"); MODULE_AUTHOR("Jason A. Donenfeld <[email protected]>"); diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c index 48e7b982a307..1de413b19e34 100644 --- a/drivers/net/wireguard/queueing.c +++ b/drivers/net/wireguard/queueing.c @@ -38,11 +38,11 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, return 0; } -void wg_packet_queue_free(struct crypt_queue *queue) +void wg_packet_queue_free(struct crypt_queue *queue, bool purge) { free_percpu(queue->worker); - WARN_ON(!__ptr_ring_empty(&queue->ring)); - ptr_ring_cleanup(&queue->ring, NULL); + WARN_ON(!purge && !__ptr_ring_empty(&queue->ring)); + ptr_ring_cleanup(&queue->ring, purge ? (void(*)(void*))kfree_skb : NULL); } #define NEXT(skb) ((skb)->prev) diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index 4ef2944a68bc..e2388107f7fd 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -23,7 +23,7 @@ struct sk_buff; /* queueing.c APIs: */ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, unsigned int len); -void wg_packet_queue_free(struct crypt_queue *queue); +void wg_packet_queue_free(struct crypt_queue *queue, bool purge); struct multicore_worker __percpu * wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr); diff --git a/drivers/net/wireguard/ratelimiter.c b/drivers/net/wireguard/ratelimiter.c index 3fedd1d21f5e..dd55e5c26f46 100644 --- a/drivers/net/wireguard/ratelimiter.c +++ b/drivers/net/wireguard/ratelimiter.c @@ -176,12 +176,12 @@ int wg_ratelimiter_init(void) (1U << 14) / sizeof(struct hlist_head))); max_entries = table_size * 8; - table_v4 = kvzalloc(table_size * sizeof(*table_v4), GFP_KERNEL); + table_v4 = kvcalloc(table_size, sizeof(*table_v4), GFP_KERNEL); if (unlikely(!table_v4)) goto err_kmemcache; #if IS_ENABLED(CONFIG_IPV6) - table_v6 = kvzalloc(table_size * sizeof(*table_v6), GFP_KERNEL); + table_v6 = kvcalloc(table_size, sizeof(*table_v6), GFP_KERNEL); if (unlikely(!table_v6)) { kvfree(table_v4); goto err_kmemcache; diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 7dc84bcca261..7b8df406c773 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -116,8 +116,8 @@ static void wg_receive_handshake_packet(struct wg_device *wg, return; } - under_load = skb_queue_len(&wg->incoming_handshakes) >= - MAX_QUEUED_INCOMING_HANDSHAKES / 8; + under_load = atomic_read(&wg->handshake_queue_len) >= + MAX_QUEUED_INCOMING_HANDSHAKES / 8; if (under_load) { last_under_load = ktime_get_coarse_boottime_ns(); } else if (last_under_load) { @@ -212,13 +212,14 @@ static void wg_receive_handshake_packet(struct wg_device *wg, void wg_packet_handshake_receive_worker(struct work_struct *work) { - struct wg_device *wg = container_of(work, struct multicore_worker, - work)->ptr; + struct crypt_queue *queue = container_of(work, struct multicore_worker, work)->ptr; + struct wg_device *wg = container_of(queue, struct wg_device, handshake_queue); struct sk_buff *skb; - while ((skb = skb_dequeue(&wg->incoming_handshakes)) != NULL) { + while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) { wg_receive_handshake_packet(wg, skb); dev_kfree_skb(skb); + atomic_dec(&wg->handshake_queue_len); cond_resched(); } } @@ -553,22 +554,28 @@ void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb) case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION): case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE): case cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE): { - int cpu; - - if (skb_queue_len(&wg->incoming_handshakes) > - MAX_QUEUED_INCOMING_HANDSHAKES || - unlikely(!rng_is_initialized())) { + int cpu, ret = -EBUSY; + + if (unlikely(!rng_is_initialized())) + goto drop; + if (atomic_read(&wg->handshake_queue_len) > MAX_QUEUED_INCOMING_HANDSHAKES / 2) { + if (spin_trylock_bh(&wg->handshake_queue.ring.producer_lock)) { + ret = __ptr_ring_produce(&wg->handshake_queue.ring, skb); + spin_unlock_bh(&wg->handshake_queue.ring.producer_lock); + } + } else + ret = ptr_ring_produce_bh(&wg->handshake_queue.ring, skb); + if (ret) { + drop: net_dbg_skb_ratelimited("%s: Dropping handshake packet from %pISpfsc\n", wg->dev->name, skb); goto err; } - skb_queue_tail(&wg->incoming_handshakes, skb); - /* Queues up a call to packet_process_queued_handshake_ - * packets(skb): - */ - cpu = wg_cpumask_next_online(&wg->incoming_handshake_cpu); + atomic_inc(&wg->handshake_queue_len); + cpu = wg_cpumask_next_online(&wg->handshake_queue.last_cpu); + /* Queues up a call to packet_process_queued_handshake_packets(skb): */ queue_work_on(cpu, wg->handshake_receive_wq, - &per_cpu_ptr(wg->incoming_handshakes_worker, cpu)->work); + &per_cpu_ptr(wg->handshake_queue.worker, cpu)->work); break; } case cpu_to_le32(MESSAGE_DATA): diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index 8c496b747108..6f07b949cb81 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -308,7 +308,7 @@ void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer) { write_lock_bh(&peer->endpoint_lock); memset(&peer->endpoint.src6, 0, sizeof(peer->endpoint.src6)); - dst_cache_reset(&peer->endpoint_cache); + dst_cache_reset_now(&peer->endpoint_cache); write_unlock_bh(&peer->endpoint_lock); } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c index c875bf35533c..009dd4be597b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c @@ -86,6 +86,7 @@ static void *iwl_uefi_reduce_power_section(struct iwl_trans *trans, if (len < tlv_len) { IWL_ERR(trans, "invalid TLV len: %zd/%u\n", len, tlv_len); + kfree(reduce_power_data); reduce_power_data = ERR_PTR(-EINVAL); goto out; } @@ -105,6 +106,7 @@ static void *iwl_uefi_reduce_power_section(struct iwl_trans *trans, IWL_DEBUG_FW(trans, "Couldn't allocate (more) reduce_power_data\n"); + kfree(reduce_power_data); reduce_power_data = ERR_PTR(-ENOMEM); goto out; } @@ -134,6 +136,10 @@ static void *iwl_uefi_reduce_power_section(struct iwl_trans *trans, done: if (!size) { IWL_DEBUG_FW(trans, "Empty REDUCE_POWER, skipping.\n"); + /* Better safe than sorry, but 'reduce_power_data' should + * always be NULL if !size. + */ + kfree(reduce_power_data); reduce_power_data = ERR_PTR(-ENOENT); goto out; } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 36196e07b1a0..5cec467b995b 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1313,23 +1313,31 @@ _iwl_op_mode_start(struct iwl_drv *drv, struct iwlwifi_opmode_table *op) const struct iwl_op_mode_ops *ops = op->ops; struct dentry *dbgfs_dir = NULL; struct iwl_op_mode *op_mode = NULL; + int retry, max_retry = !!iwlwifi_mod_params.fw_restart * IWL_MAX_INIT_RETRY; + + for (retry = 0; retry <= max_retry; retry++) { #ifdef CONFIG_IWLWIFI_DEBUGFS - drv->dbgfs_op_mode = debugfs_create_dir(op->name, - drv->dbgfs_drv); - dbgfs_dir = drv->dbgfs_op_mode; + drv->dbgfs_op_mode = debugfs_create_dir(op->name, + drv->dbgfs_drv); + dbgfs_dir = drv->dbgfs_op_mode; #endif - op_mode = ops->start(drv->trans, drv->trans->cfg, &drv->fw, dbgfs_dir); + op_mode = ops->start(drv->trans, drv->trans->cfg, + &drv->fw, dbgfs_dir); + + if (op_mode) + return op_mode; + + IWL_ERR(drv, "retry init count %d\n", retry); #ifdef CONFIG_IWLWIFI_DEBUGFS - if (!op_mode) { debugfs_remove_recursive(drv->dbgfs_op_mode); drv->dbgfs_op_mode = NULL; - } #endif + } - return op_mode; + return NULL; } static void _iwl_op_mode_stop(struct iwl_drv *drv) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h index 2e2d60a58692..0fd009e6d685 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h @@ -89,4 +89,7 @@ void iwl_drv_stop(struct iwl_drv *drv); #define IWL_EXPORT_SYMBOL(sym) #endif +/* max retry for init flow */ +#define IWL_MAX_INIT_RETRY 2 + #endif /* __iwl_drv_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 9fb9c7dad314..897e3b91ddb2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -16,6 +16,7 @@ #include <net/ieee80211_radiotap.h> #include <net/tcp.h> +#include "iwl-drv.h" #include "iwl-op-mode.h" #include "iwl-io.h" #include "mvm.h" @@ -1117,9 +1118,30 @@ static int iwl_mvm_mac_start(struct ieee80211_hw *hw) { struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); int ret; + int retry, max_retry = 0; mutex_lock(&mvm->mutex); - ret = __iwl_mvm_mac_start(mvm); + + /* we are starting the mac not in error flow, and restart is enabled */ + if (!test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status) && + iwlwifi_mod_params.fw_restart) { + max_retry = IWL_MAX_INIT_RETRY; + /* + * This will prevent mac80211 recovery flows to trigger during + * init failures + */ + set_bit(IWL_MVM_STATUS_STARTING, &mvm->status); + } + + for (retry = 0; retry <= max_retry; retry++) { + ret = __iwl_mvm_mac_start(mvm); + if (!ret) + break; + + IWL_ERR(mvm, "mac start retry %d\n", retry); + } + clear_bit(IWL_MVM_STATUS_STARTING, &mvm->status); + mutex_unlock(&mvm->mutex); return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 2b1dcd60e00f..a72d85086fe3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1123,6 +1123,8 @@ struct iwl_mvm { * @IWL_MVM_STATUS_FIRMWARE_RUNNING: firmware is running * @IWL_MVM_STATUS_NEED_FLUSH_P2P: need to flush P2P bcast STA * @IWL_MVM_STATUS_IN_D3: in D3 (or at least about to go into it) + * @IWL_MVM_STATUS_STARTING: starting mac, + * used to disable restart flow while in STARTING state */ enum iwl_mvm_status { IWL_MVM_STATUS_HW_RFKILL, @@ -1134,6 +1136,7 @@ enum iwl_mvm_status { IWL_MVM_STATUS_FIRMWARE_RUNNING, IWL_MVM_STATUS_NEED_FLUSH_P2P, IWL_MVM_STATUS_IN_D3, + IWL_MVM_STATUS_STARTING, }; /* Keep track of completed init configuration */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 232ad531d612..cd08e289cd9a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -686,6 +686,7 @@ static int iwl_mvm_start_get_nvm(struct iwl_mvm *mvm) int ret; rtnl_lock(); + wiphy_lock(mvm->hw->wiphy); mutex_lock(&mvm->mutex); ret = iwl_run_init_mvm_ucode(mvm); @@ -701,6 +702,7 @@ static int iwl_mvm_start_get_nvm(struct iwl_mvm *mvm) iwl_mvm_stop_device(mvm); mutex_unlock(&mvm->mutex); + wiphy_unlock(mvm->hw->wiphy); rtnl_unlock(); if (ret < 0) @@ -1600,6 +1602,9 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error) */ if (!mvm->fw_restart && fw_error) { iwl_fw_error_collect(&mvm->fwrt, false); + } else if (test_bit(IWL_MVM_STATUS_STARTING, + &mvm->status)) { + IWL_ERR(mvm, "Starting mac, retry will be triggered anyway\n"); } else if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) { struct iwl_mvm_reprobe *reprobe; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index c574f041f096..5ce07f28e7c3 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -1339,9 +1339,13 @@ iwl_pci_find_dev_info(u16 device, u16 subsystem_device, u16 mac_type, u8 mac_step, u16 rf_type, u8 cdb, u8 rf_id, u8 no_160, u8 cores) { + int num_devices = ARRAY_SIZE(iwl_dev_info_table); int i; - for (i = ARRAY_SIZE(iwl_dev_info_table) - 1; i >= 0; i--) { + if (!num_devices) + return NULL; + + for (i = num_devices - 1; i >= 0; i--) { const struct iwl_dev_info *dev_info = &iwl_dev_info_table[i]; if (dev_info->device != (u16)IWL_CFG_ANY && @@ -1442,8 +1446,10 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ if (iwl_trans->trans_cfg->rf_id && iwl_trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_9000 && - !CSR_HW_RFID_TYPE(iwl_trans->hw_rf_id) && get_crf_id(iwl_trans)) + !CSR_HW_RFID_TYPE(iwl_trans->hw_rf_id) && get_crf_id(iwl_trans)) { + ret = -EINVAL; goto out_free_trans; + } dev_info = iwl_pci_find_dev_info(pdev->device, pdev->subsystem_device, CSR_HW_REV_TYPE(iwl_trans->hw_rev), diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c index 5ee52cd70a4b..d1806f198aed 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c @@ -143,8 +143,6 @@ int mt7615_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, if (!wcid) wcid = &dev->mt76.global_wcid; - pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb); - if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && msta) { struct mt7615_phy *phy = &dev->phy; @@ -164,6 +162,7 @@ int mt7615_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, if (id < 0) return id; + pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb); mt7615_mac_write_txwi(dev, txwi_ptr, tx_info->skb, wcid, sta, pid, key, false); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c index bd2939ebcbf4..5a6d7829c6e0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c @@ -43,19 +43,11 @@ EXPORT_SYMBOL_GPL(mt7663_usb_sdio_reg_map); static void mt7663_usb_sdio_write_txwi(struct mt7615_dev *dev, struct mt76_wcid *wcid, enum mt76_txq_id qid, struct ieee80211_sta *sta, + struct ieee80211_key_conf *key, int pid, struct sk_buff *skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_key_conf *key = info->control.hw_key; - __le32 *txwi; - int pid; - - if (!wcid) - wcid = &dev->mt76.global_wcid; - - pid = mt76_tx_status_skb_add(&dev->mt76, wcid, skb); + __le32 *txwi = (__le32 *)(skb->data - MT_USB_TXD_SIZE); - txwi = (__le32 *)(skb->data - MT_USB_TXD_SIZE); memset(txwi, 0, MT_USB_TXD_SIZE); mt7615_mac_write_txwi(dev, txwi, skb, wcid, sta, pid, key, false); skb_push(skb, MT_USB_TXD_SIZE); @@ -194,10 +186,14 @@ int mt7663_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, struct mt7615_dev *dev = container_of(mdev, struct mt7615_dev, mt76); struct sk_buff *skb = tx_info->skb; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_key_conf *key = info->control.hw_key; struct mt7615_sta *msta; - int pad; + int pad, err, pktid; msta = wcid ? container_of(wcid, struct mt7615_sta, wcid) : NULL; + if (!wcid) + wcid = &dev->mt76.global_wcid; + if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && msta && !msta->rate_probe) { /* request to configure sampling rate */ @@ -207,7 +203,8 @@ int mt7663_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, spin_unlock_bh(&dev->mt76.lock); } - mt7663_usb_sdio_write_txwi(dev, wcid, qid, sta, skb); + pktid = mt76_tx_status_skb_add(&dev->mt76, wcid, skb); + mt7663_usb_sdio_write_txwi(dev, wcid, qid, sta, key, pktid, skb); if (mt76_is_usb(mdev)) { u32 len = skb->len; @@ -217,7 +214,12 @@ int mt7663_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, pad = round_up(skb->len, 4) - skb->len; } - return mt76_skb_adjust_pad(skb, pad); + err = mt76_skb_adjust_pad(skb, pad); + if (err) + /* Release pktid in case of error. */ + idr_remove(&wcid->pktid, pktid); + + return err; } EXPORT_SYMBOL_GPL(mt7663_usb_sdio_tx_prepare_skb); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c index efd70ddc2fd1..2c6c03809b20 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c @@ -72,6 +72,7 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data, bool ampdu = IEEE80211_SKB_CB(tx_info->skb)->flags & IEEE80211_TX_CTL_AMPDU; enum mt76_qsel qsel; u32 flags; + int err; mt76_insert_hdr_pad(tx_info->skb); @@ -106,7 +107,12 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data, ewma_pktlen_add(&msta->pktlen, tx_info->skb->len); } - return mt76x02u_skb_dma_info(tx_info->skb, WLAN_PORT, flags); + err = mt76x02u_skb_dma_info(tx_info->skb, WLAN_PORT, flags); + if (err && wcid) + /* Release pktid in case of error. */ + idr_remove(&wcid->pktid, pid); + + return err; } EXPORT_SYMBOL_GPL(mt76x02u_tx_prepare_skb); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 5fcf35f2d9fb..809dc18e5083 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -1151,8 +1151,14 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, } } - pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb); + t = (struct mt76_txwi_cache *)(txwi + mdev->drv->txwi_size); + t->skb = tx_info->skb; + + id = mt76_token_consume(mdev, &t); + if (id < 0) + return id; + pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb); mt7915_mac_write_txwi(dev, txwi_ptr, tx_info->skb, wcid, pid, key, false); @@ -1178,13 +1184,6 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, txp->bss_idx = mvif->idx; } - t = (struct mt76_txwi_cache *)(txwi + mdev->drv->txwi_size); - t->skb = tx_info->skb; - - id = mt76_token_consume(mdev, &t); - if (id < 0) - return id; - txp->token = cpu_to_le16(id); if (test_bit(MT_WCID_FLAG_4ADDR, &wcid->flags)) txp->rept_wds_wcid = cpu_to_le16(wcid->idx); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index 899957b9d0f1..852d5d97c70b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -176,7 +176,7 @@ mt7915_get_phy_mode(struct ieee80211_vif *vif, struct ieee80211_sta *sta) if (ht_cap->ht_supported) mode |= PHY_MODE_GN; - if (he_cap->has_he) + if (he_cap && he_cap->has_he) mode |= PHY_MODE_AX_24G; } else if (band == NL80211_BAND_5GHZ) { mode |= PHY_MODE_A; @@ -187,7 +187,7 @@ mt7915_get_phy_mode(struct ieee80211_vif *vif, struct ieee80211_sta *sta) if (vht_cap->vht_supported) mode |= PHY_MODE_AC; - if (he_cap->has_he) + if (he_cap && he_cap->has_he) mode |= PHY_MODE_AX_5G; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c index 137f86a6dbf8..bdec508b6b9f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c @@ -142,15 +142,11 @@ out: static void mt7921s_write_txwi(struct mt7921_dev *dev, struct mt76_wcid *wcid, enum mt76_txq_id qid, struct ieee80211_sta *sta, + struct ieee80211_key_conf *key, int pid, struct sk_buff *skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_key_conf *key = info->control.hw_key; - __le32 *txwi; - int pid; + __le32 *txwi = (__le32 *)(skb->data - MT_SDIO_TXD_SIZE); - pid = mt76_tx_status_skb_add(&dev->mt76, wcid, skb); - txwi = (__le32 *)(skb->data - MT_SDIO_TXD_SIZE); memset(txwi, 0, MT_SDIO_TXD_SIZE); mt7921_mac_write_txwi(dev, txwi, skb, wcid, key, pid, false); skb_push(skb, MT_SDIO_TXD_SIZE); @@ -163,8 +159,9 @@ int mt7921s_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, { struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_info->skb); + struct ieee80211_key_conf *key = info->control.hw_key; struct sk_buff *skb = tx_info->skb; - int pad; + int err, pad, pktid; if (unlikely(tx_info->skb->len <= ETH_HLEN)) return -EINVAL; @@ -181,12 +178,18 @@ int mt7921s_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, } } - mt7921s_write_txwi(dev, wcid, qid, sta, skb); + pktid = mt76_tx_status_skb_add(&dev->mt76, wcid, skb); + mt7921s_write_txwi(dev, wcid, qid, sta, key, pktid, skb); mt7921_skb_add_sdio_hdr(skb, MT7921_SDIO_DATA); pad = round_up(skb->len, 4) - skb->len; - return mt76_skb_adjust_pad(skb, pad); + err = mt76_skb_adjust_pad(skb, pad); + if (err) + /* Release pktid in case of error. */ + idr_remove(&wcid->pktid, pktid); + + return err; } void mt7921s_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e) diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index 11719ef034d8..6b8c9dc80542 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -173,7 +173,7 @@ mt76_tx_status_skb_get(struct mt76_dev *dev, struct mt76_wcid *wcid, int pktid, if (!(cb->flags & MT_TX_CB_DMA_DONE)) continue; - if (!time_is_after_jiffies(cb->jiffies + + if (time_is_after_jiffies(cb->jiffies + MT_TX_STATUS_SKB_TIMEOUT)) continue; } diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c index e4473a551241..74c3d8cb3100 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c @@ -25,6 +25,9 @@ static bool rt2x00usb_check_usb_error(struct rt2x00_dev *rt2x00dev, int status) if (status == -ENODEV || status == -ENOENT) return true; + if (!test_bit(DEVICE_STATE_STARTED, &rt2x00dev->flags)) + return false; + if (status == -EPROTO || status == -ETIMEDOUT) rt2x00dev->num_proto_errs++; else diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index 212aaf577d3c..65ef3dc9d061 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -91,7 +91,6 @@ static int rtw89_fw_hdr_parser(struct rtw89_dev *rtwdev, const u8 *fw, u32 len, info->section_num = GET_FW_HDR_SEC_NUM(fw); info->hdr_len = RTW89_FW_HDR_SIZE + info->section_num * RTW89_FW_SECTION_HDR_SIZE; - SET_FW_HDR_PART_SIZE(fw, FWDL_SECTION_PER_PKT_LEN); bin = fw + info->hdr_len; @@ -275,6 +274,7 @@ static int __rtw89_fw_download_hdr(struct rtw89_dev *rtwdev, const u8 *fw, u32 l } skb_put_data(skb, fw, len); + SET_FW_HDR_PART_SIZE(skb->data, FWDL_SECTION_PER_PKT_LEN); rtw89_h2c_pkt_set_hdr_fwdl(rtwdev, skb, FWCMD_TYPE_H2C, H2C_CAT_MAC, H2C_CL_MAC_FWDL, H2C_FUNC_MAC_FWHDR_DL, len); diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h index 7ee0d9323310..36e8d0da6c1e 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.h +++ b/drivers/net/wireless/realtek/rtw89/fw.h @@ -282,8 +282,10 @@ struct rtw89_h2creg_sch_tx_en { le32_get_bits(*((__le32 *)(fwhdr) + 6), GENMASK(15, 8)) #define GET_FW_HDR_CMD_VERSERION(fwhdr) \ le32_get_bits(*((__le32 *)(fwhdr) + 7), GENMASK(31, 24)) -#define SET_FW_HDR_PART_SIZE(fwhdr, val) \ - le32p_replace_bits((__le32 *)(fwhdr) + 7, val, GENMASK(15, 0)) +static inline void SET_FW_HDR_PART_SIZE(void *fwhdr, u32 val) +{ + le32p_replace_bits((__le32 *)fwhdr + 7, val, GENMASK(15, 0)); +} #define SET_CTRL_INFO_MACID(table, val) \ le32p_replace_bits((__le32 *)(table) + 0, val, GENMASK(6, 0)) diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c index b9fac786246a..2a5c1829aab7 100644 --- a/drivers/powercap/dtpm.c +++ b/drivers/powercap/dtpm.c @@ -463,17 +463,12 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent) static int __init init_dtpm(void) { - struct dtpm_descr *dtpm_descr; - pct = powercap_register_control_type(NULL, "dtpm", NULL); if (IS_ERR(pct)) { pr_err("Failed to register control type\n"); return PTR_ERR(pct); } - for_each_dtpm_table(dtpm_descr) - dtpm_descr->init(); - return 0; } late_initcall(init_dtpm); diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index b940e0268f96..e83453bea2ae 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -5095,14 +5095,9 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, /* NPort Recovery mode or node is just allocated */ if (!lpfc_nlp_not_used(ndlp)) { /* A LOGO is completing and the node is in NPR state. - * If this a fabric node that cleared its transport - * registration, release the rpi. + * Just unregister the RPI because the node is still + * required. */ - spin_lock_irq(&ndlp->lock); - ndlp->nlp_flag &= ~NLP_NPR_2B_DISC; - if (phba->sli_rev == LPFC_SLI_REV4) - ndlp->nlp_flag |= NLP_RELEASE_RPI; - spin_unlock_irq(&ndlp->lock); lpfc_unreg_rpi(vport, ndlp); } else { /* Indicate the node has already released, should diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index 51424557810d..f725248ba57f 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -421,6 +421,13 @@ static int ufs_intel_lkf_init(struct ufs_hba *hba) return err; } +static int ufs_intel_adl_init(struct ufs_hba *hba) +{ + hba->nop_out_timeout = 200; + hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8; + return ufs_intel_common_init(hba); +} + static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .name = "intel-pci", .init = ufs_intel_common_init, @@ -449,6 +456,15 @@ static struct ufs_hba_variant_ops ufs_intel_lkf_hba_vops = { .device_reset = ufs_intel_device_reset, }; +static struct ufs_hba_variant_ops ufs_intel_adl_hba_vops = { + .name = "intel-pci", + .init = ufs_intel_adl_init, + .exit = ufs_intel_common_exit, + .link_startup_notify = ufs_intel_link_startup_notify, + .resume = ufs_intel_resume, + .device_reset = ufs_intel_device_reset, +}; + #ifdef CONFIG_PM_SLEEP static int ufshcd_pci_restore(struct device *dev) { @@ -563,6 +579,8 @@ static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_ehl_hba_vops }, { PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_ehl_hba_vops }, { PCI_VDEVICE(INTEL, 0x98FA), (kernel_ulong_t)&ufs_intel_lkf_hba_vops }, + { PCI_VDEVICE(INTEL, 0x51FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x54FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index 7f656fac503f..5163d60756b7 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -237,6 +237,7 @@ struct brcmuart_priv { u32 rx_err; u32 rx_timeout; u32 rx_abort; + u32 saved_mctrl; }; static struct dentry *brcmuart_debugfs_root; @@ -1133,16 +1134,27 @@ static int brcmuart_remove(struct platform_device *pdev) static int __maybe_unused brcmuart_suspend(struct device *dev) { struct brcmuart_priv *priv = dev_get_drvdata(dev); + struct uart_8250_port *up = serial8250_get_port(priv->line); + struct uart_port *port = &up->port; serial8250_suspend_port(priv->line); clk_disable_unprepare(priv->baud_mux_clk); + /* + * This will prevent resume from enabling RTS before the + * baud rate has been resored. + */ + priv->saved_mctrl = port->mctrl; + port->mctrl = 0; + return 0; } static int __maybe_unused brcmuart_resume(struct device *dev) { struct brcmuart_priv *priv = dev_get_drvdata(dev); + struct uart_8250_port *up = serial8250_get_port(priv->line); + struct uart_port *port = &up->port; int ret; ret = clk_prepare_enable(priv->baud_mux_clk); @@ -1165,6 +1177,7 @@ static int __maybe_unused brcmuart_resume(struct device *dev) start_rx_dma(serial8250_get_port(priv->line)); } serial8250_resume_port(priv->line); + port->mctrl = priv->saved_mctrl; return 0; } diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 5d43de143f33..60f8fffdfd77 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1324,29 +1324,33 @@ pericom_do_set_divisor(struct uart_port *port, unsigned int baud, { int scr; int lcr; - int actual_baud; - int tolerance; - for (scr = 5 ; scr <= 15 ; scr++) { - actual_baud = 921600 * 16 / scr; - tolerance = actual_baud / 50; + for (scr = 16; scr > 4; scr--) { + unsigned int maxrate = port->uartclk / scr; + unsigned int divisor = max(maxrate / baud, 1U); + int delta = maxrate / divisor - baud; - if ((baud < actual_baud + tolerance) && - (baud > actual_baud - tolerance)) { + if (baud > maxrate + baud / 50) + continue; + if (delta > baud / 50) + divisor++; + + if (divisor > 0xffff) + continue; + + /* Update delta due to possible divisor change */ + delta = maxrate / divisor - baud; + if (abs(delta) < baud / 50) { lcr = serial_port_in(port, UART_LCR); serial_port_out(port, UART_LCR, lcr | 0x80); - - serial_port_out(port, UART_DLL, 1); - serial_port_out(port, UART_DLM, 0); + serial_port_out(port, UART_DLL, divisor & 0xff); + serial_port_out(port, UART_DLM, divisor >> 8 & 0xff); serial_port_out(port, 2, 16 - scr); serial_port_out(port, UART_LCR, lcr); return; - } else if (baud > actual_baud) { - break; } } - serial8250_do_set_divisor(port, baud, quot, quot_frac); } static int pci_pericom_setup(struct serial_private *priv, const struct pciserial_board *board, @@ -2291,7 +2295,7 @@ static struct pci_serial_quirk pci_serial_quirks[] = { .setup = pci_pericom_setup_four_at_eight, }, { - .vendor = PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S, + .vendor = PCI_VENDOR_ID_ACCESIO, .device = PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_4, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, @@ -2299,6 +2303,13 @@ static struct pci_serial_quirk pci_serial_quirks[] = { }, { .vendor = PCI_VENDOR_ID_ACCESIO, + .device = PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_pericom_setup_four_at_eight, + }, + { + .vendor = PCI_VENDOR_ID_ACCESIO, .device = PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_4, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 5775cbff8f6e..46e2079ad1aa 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2024,13 +2024,6 @@ void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl) struct uart_8250_port *up = up_to_u8250p(port); unsigned char mcr; - if (port->rs485.flags & SER_RS485_ENABLED) { - if (serial8250_in_MCR(up) & UART_MCR_RTS) - mctrl |= TIOCM_RTS; - else - mctrl &= ~TIOCM_RTS; - } - mcr = serial8250_TIOCM_to_MCR(mctrl); mcr = (mcr & up->mcr_mask) | up->mcr_force | up->mcr; diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 6ff94cfcd9db..fc543ac97c13 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1533,7 +1533,7 @@ config SERIAL_LITEUART tristate "LiteUART serial port support" depends on HAS_IOMEM depends on OF || COMPILE_TEST - depends on LITEX + depends on LITEX || COMPILE_TEST select SERIAL_CORE help This driver is for the FPGA-based LiteUART serial controller from LiteX diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index d361cd84ff8c..52518a606c06 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2947,6 +2947,7 @@ MODULE_DEVICE_TABLE(of, sbsa_uart_of_match); static const struct acpi_device_id __maybe_unused sbsa_uart_acpi_match[] = { { "ARMH0011", 0 }, + { "ARMHB000", 0 }, {}, }; MODULE_DEVICE_TABLE(acpi, sbsa_uart_acpi_match); diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index b1e7190ae483..ac5112def40d 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2625,6 +2625,7 @@ OF_EARLYCON_DECLARE(lpuart, "fsl,vf610-lpuart", lpuart_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1021a-lpuart", lpuart32_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1028a-lpuart", ls1028a_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,imx7ulp-lpuart", lpuart32_imx_early_console_setup); +OF_EARLYCON_DECLARE(lpuart32, "fsl,imx8qxp-lpuart", lpuart32_imx_early_console_setup); EARLYCON_DECLARE(lpuart, lpuart_early_console_setup); EARLYCON_DECLARE(lpuart32, lpuart32_early_console_setup); diff --git a/drivers/tty/serial/liteuart.c b/drivers/tty/serial/liteuart.c index dbc0559a9157..2941659e5274 100644 --- a/drivers/tty/serial/liteuart.c +++ b/drivers/tty/serial/liteuart.c @@ -270,8 +270,10 @@ static int liteuart_probe(struct platform_device *pdev) /* get membase */ port->membase = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); - if (IS_ERR(port->membase)) - return PTR_ERR(port->membase); + if (IS_ERR(port->membase)) { + ret = PTR_ERR(port->membase); + goto err_erase_id; + } /* values not from device tree */ port->dev = &pdev->dev; @@ -285,7 +287,18 @@ static int liteuart_probe(struct platform_device *pdev) port->line = dev_id; spin_lock_init(&port->lock); - return uart_add_one_port(&liteuart_driver, &uart->port); + platform_set_drvdata(pdev, port); + + ret = uart_add_one_port(&liteuart_driver, &uart->port); + if (ret) + goto err_erase_id; + + return 0; + +err_erase_id: + xa_erase(&liteuart_array, uart->id); + + return ret; } static int liteuart_remove(struct platform_device *pdev) @@ -293,6 +306,7 @@ static int liteuart_remove(struct platform_device *pdev) struct uart_port *port = platform_get_drvdata(pdev); struct liteuart_port *uart = to_liteuart_port(port); + uart_remove_one_port(&liteuart_driver, port); xa_erase(&liteuart_array, uart->id); return 0; diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c index fcef7a961430..489d19274f9a 100644 --- a/drivers/tty/serial/msm_serial.c +++ b/drivers/tty/serial/msm_serial.c @@ -598,6 +598,9 @@ static void msm_start_rx_dma(struct msm_port *msm_port) u32 val; int ret; + if (IS_ENABLED(CONFIG_CONSOLE_POLL)) + return; + if (!dma->chan) return; diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index 45e2e4109acd..b6223fab0687 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -1506,7 +1506,7 @@ static struct tegra_uart_chip_data tegra20_uart_chip_data = { .fifo_mode_enable_status = false, .uart_max_port = 5, .max_dma_burst_bytes = 4, - .error_tolerance_low_range = 0, + .error_tolerance_low_range = -4, .error_tolerance_high_range = 4, }; @@ -1517,7 +1517,7 @@ static struct tegra_uart_chip_data tegra30_uart_chip_data = { .fifo_mode_enable_status = false, .uart_max_port = 5, .max_dma_burst_bytes = 4, - .error_tolerance_low_range = 0, + .error_tolerance_low_range = -4, .error_tolerance_high_range = 4, }; diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 1e738f265eea..61e3dd0222af 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1075,6 +1075,11 @@ uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) goto out; if (!tty_io_error(tty)) { + if (uport->rs485.flags & SER_RS485_ENABLED) { + set &= ~TIOCM_RTS; + clear &= ~TIOCM_RTS; + } + uart_update_mctrl(uport, set, clear); ret = 0; } @@ -1549,6 +1554,7 @@ static void uart_tty_port_shutdown(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = uart_port_check(state); + char *buf; /* * At this point, we stop accepting input. To do this, we @@ -1570,8 +1576,18 @@ static void uart_tty_port_shutdown(struct tty_port *port) */ tty_port_set_suspended(port, 0); - uart_change_pm(state, UART_PM_STATE_OFF); + /* + * Free the transmit buffer. + */ + spin_lock_irq(&uport->lock); + buf = state->xmit.buf; + state->xmit.buf = NULL; + spin_unlock_irq(&uport->lock); + if (buf) + free_page((unsigned long)buf); + + uart_change_pm(state, UART_PM_STATE_OFF); } static void uart_wait_until_sent(struct tty_struct *tty, int timeout) diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index 1f3b4a142212..f9af7ebe003d 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -337,19 +337,6 @@ static void cdns3_ep_inc_deq(struct cdns3_endpoint *priv_ep) cdns3_ep_inc_trb(&priv_ep->dequeue, &priv_ep->ccs, priv_ep->num_trbs); } -static void cdns3_move_deq_to_next_trb(struct cdns3_request *priv_req) -{ - struct cdns3_endpoint *priv_ep = priv_req->priv_ep; - int current_trb = priv_req->start_trb; - - while (current_trb != priv_req->end_trb) { - cdns3_ep_inc_deq(priv_ep); - current_trb = priv_ep->dequeue; - } - - cdns3_ep_inc_deq(priv_ep); -} - /** * cdns3_allow_enable_l1 - enable/disable permits to transition to L1. * @priv_dev: Extended gadget object @@ -1517,10 +1504,11 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev, trb = priv_ep->trb_pool + priv_ep->dequeue; - /* Request was dequeued and TRB was changed to TRB_LINK. */ - if (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) { + /* The TRB was changed as link TRB, and the request was handled at ep_dequeue */ + while (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) { trace_cdns3_complete_trb(priv_ep, trb); - cdns3_move_deq_to_next_trb(priv_req); + cdns3_ep_inc_deq(priv_ep); + trb = priv_ep->trb_pool + priv_ep->dequeue; } if (!request->stream_id) { diff --git a/drivers/usb/cdns3/cdnsp-mem.c b/drivers/usb/cdns3/cdnsp-mem.c index ad9aee3f1e39..97866bfb2da9 100644 --- a/drivers/usb/cdns3/cdnsp-mem.c +++ b/drivers/usb/cdns3/cdnsp-mem.c @@ -987,6 +987,9 @@ int cdnsp_endpoint_init(struct cdnsp_device *pdev, /* Set up the endpoint ring. */ pep->ring = cdnsp_ring_alloc(pdev, 2, ring_type, max_packet, mem_flags); + if (!pep->ring) + return -ENOMEM; + pep->skip = false; /* Fill the endpoint context */ diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 8239fe7129dd..019351c0b52c 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -434,6 +434,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1532, 0x0116), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Lenovo Powered USB-C Travel Hub (4X90S92381, RTL8153 GigE) */ + { USB_DEVICE(0x17ef, 0x721e), .driver_info = USB_QUIRK_NO_LPM }, + /* Lenovo ThinkCenter A630Z TI024Gen3 usb-audio */ { USB_DEVICE(0x17ef, 0xa012), .driver_info = USB_QUIRK_DISCONNECT_SUSPEND }, diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 311597bba80e..eaa49aef2935 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -366,7 +366,9 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci, /* Must be called with xhci->lock held, releases and aquires lock back */ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags) { - u32 temp_32; + struct xhci_segment *new_seg = xhci->cmd_ring->deq_seg; + union xhci_trb *new_deq = xhci->cmd_ring->dequeue; + u64 crcr; int ret; xhci_dbg(xhci, "Abort command ring\n"); @@ -375,13 +377,18 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags) /* * The control bits like command stop, abort are located in lower - * dword of the command ring control register. Limit the write - * to the lower dword to avoid corrupting the command ring pointer - * in case if the command ring is stopped by the time upper dword - * is written. + * dword of the command ring control register. + * Some controllers require all 64 bits to be written to abort the ring. + * Make sure the upper dword is valid, pointing to the next command, + * avoiding corrupting the command ring pointer in case the command ring + * is stopped by the time the upper dword is written. */ - temp_32 = readl(&xhci->op_regs->cmd_ring); - writel(temp_32 | CMD_RING_ABORT, &xhci->op_regs->cmd_ring); + next_trb(xhci, NULL, &new_seg, &new_deq); + if (trb_is_link(new_deq)) + next_trb(xhci, NULL, &new_seg, &new_deq); + + crcr = xhci_trb_virt_to_dma(new_seg, new_deq); + xhci_write_64(xhci, crcr | CMD_RING_ABORT, &xhci->op_regs->cmd_ring); /* Section 4.6.1.2 of xHCI 1.0 spec says software should also time the * completion of the Command Abort operation. If CRR is not negated in 5 diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 7f2f3ff1b391..6010b9901126 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4110,11 +4110,7 @@ static void run_state_machine(struct tcpm_port *port) tcpm_try_src(port) ? SRC_TRY : SNK_ATTACHED, 0); - else - /* Wait for VBUS, but not forever */ - tcpm_set_state(port, PORT_RESET, PD_T_PS_SOURCE_ON); break; - case SRC_TRY: port->try_src_count++; tcpm_set_cc(port, tcpm_rp_cc(port)); diff --git a/drivers/vfio/pci/vfio_pci_igd.c b/drivers/vfio/pci/vfio_pci_igd.c index 56cd551e0e04..362f91ec8845 100644 --- a/drivers/vfio/pci/vfio_pci_igd.c +++ b/drivers/vfio/pci/vfio_pci_igd.c @@ -98,7 +98,8 @@ static ssize_t vfio_pci_igd_rw(struct vfio_pci_core_device *vdev, version = cpu_to_le16(0x0201); if (igd_opregion_shift_copy(buf, &off, - &version + (pos - OPREGION_VERSION), + (u8 *)&version + + (pos - OPREGION_VERSION), &pos, &remaining, bytes)) return -EFAULT; } @@ -121,7 +122,7 @@ static ssize_t vfio_pci_igd_rw(struct vfio_pci_core_device *vdev, OPREGION_SIZE : 0); if (igd_opregion_shift_copy(buf, &off, - &rvda + (pos - OPREGION_RVDA), + (u8 *)&rvda + (pos - OPREGION_RVDA), &pos, &remaining, bytes)) return -EFAULT; } diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 82fb75464f92..735d1d344af9 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -232,7 +232,7 @@ static inline bool vfio_iommu_driver_allowed(struct vfio_container *container, } #endif /* CONFIG_VFIO_NOIOMMU */ -/** +/* * IOMMU driver registration */ int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops) @@ -285,7 +285,7 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb, unsigned long action, void *data); static void vfio_group_get(struct vfio_group *group); -/** +/* * Container objects - containers are created when /dev/vfio/vfio is * opened, but their lifecycle extends until the last user is done, so * it's freed via kref. Must support container/group/device being @@ -309,7 +309,7 @@ static void vfio_container_put(struct vfio_container *container) kref_put(&container->kref, vfio_container_release); } -/** +/* * Group objects - create, release, get, put, search */ static struct vfio_group * @@ -488,7 +488,7 @@ static struct vfio_group *vfio_group_get_from_dev(struct device *dev) return group; } -/** +/* * Device objects - create, release, get, put, search */ /* Device reference always implies a group reference */ @@ -595,7 +595,7 @@ static int vfio_dev_viable(struct device *dev, void *data) return ret; } -/** +/* * Async device support */ static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev) @@ -689,7 +689,7 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb, return NOTIFY_OK; } -/** +/* * VFIO driver API */ void vfio_init_group_dev(struct vfio_device *device, struct device *dev, @@ -831,7 +831,7 @@ int vfio_register_emulated_iommu_dev(struct vfio_device *device) } EXPORT_SYMBOL_GPL(vfio_register_emulated_iommu_dev); -/** +/* * Get a reference to the vfio_device for a device. Even if the * caller thinks they own the device, they could be racing with a * release call path, so we can't trust drvdata for the shortcut. @@ -965,7 +965,7 @@ void vfio_unregister_group_dev(struct vfio_device *device) } EXPORT_SYMBOL_GPL(vfio_unregister_group_dev); -/** +/* * VFIO base fd, /dev/vfio/vfio */ static long vfio_ioctl_check_extension(struct vfio_container *container, @@ -1183,7 +1183,7 @@ static const struct file_operations vfio_fops = { .compat_ioctl = compat_ptr_ioctl, }; -/** +/* * VFIO Group fd, /dev/vfio/$GROUP */ static void __vfio_group_unset_container(struct vfio_group *group) @@ -1536,7 +1536,7 @@ static const struct file_operations vfio_group_fops = { .release = vfio_group_fops_release, }; -/** +/* * VFIO Device fd */ static int vfio_device_fops_release(struct inode *inode, struct file *filep) @@ -1611,7 +1611,7 @@ static const struct file_operations vfio_device_fops = { .mmap = vfio_device_fops_mmap, }; -/** +/* * External user API, exported by symbols to be linked dynamically. * * The protocol includes: @@ -1659,7 +1659,7 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep) } EXPORT_SYMBOL_GPL(vfio_group_get_external_user); -/** +/* * External user API, exported by symbols to be linked dynamically. * The external user passes in a device pointer * to verify that: @@ -1725,7 +1725,7 @@ long vfio_external_check_extension(struct vfio_group *group, unsigned long arg) } EXPORT_SYMBOL_GPL(vfio_external_check_extension); -/** +/* * Sub-module support */ /* @@ -2272,7 +2272,7 @@ struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group) } EXPORT_SYMBOL_GPL(vfio_group_iommu_domain); -/** +/* * Module/class support */ static char *vfio_devnode(struct device *dev, umode_t *mode) diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index ef9c57ce0906..9a49ea6b5112 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -366,11 +366,17 @@ static void vgacon_init(struct vc_data *c, int init) struct uni_pagedir *p; /* - * We cannot be loaded as a module, therefore init is always 1, - * but vgacon_init can be called more than once, and init will - * not be 1. + * We cannot be loaded as a module, therefore init will be 1 + * if we are the default console, however if we are a fallback + * console, for example if fbcon has failed registration, then + * init will be 0, so we need to make sure our boot parameters + * have been copied to the console structure for vgacon_resize + * ultimately called by vc_resize. Any subsequent calls to + * vgacon_init init will have init set to 0 too. */ c->vc_can_do_color = vga_can_do_color; + c->vc_scan_lines = vga_scan_lines; + c->vc_font.height = c->vc_cell_height = vga_video_font_height; /* set dimensions manually if init != 0 since vc_resize() will fail */ if (init) { @@ -379,8 +385,6 @@ static void vgacon_init(struct vc_data *c, int init) } else vc_resize(c, vga_video_num_columns, vga_video_num_lines); - c->vc_scan_lines = vga_scan_lines; - c->vc_font.height = c->vc_cell_height = vga_video_font_height; c->vc_complement_mask = 0x7700; if (vga_512_chars) c->vc_hi_font_mask = 0x0800; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 6b705026da1a..18448dbd762a 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1562,6 +1562,10 @@ smbd_connected: /* fscache server cookies are based on primary channel only */ if (!CIFS_SERVER_IS_CHAN(tcp_ses)) cifs_fscache_get_client_cookie(tcp_ses); +#ifdef CONFIG_CIFS_FSCACHE + else + tcp_ses->fscache = tcp_ses->primary_server->fscache; +#endif /* CONFIG_CIFS_FSCACHE */ /* queue echo request delayed work */ queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval); @@ -3046,12 +3050,6 @@ static int mount_get_conns(struct mount_ctx *mnt_ctx) cifs_dbg(VFS, "read only mount of RW share\n"); /* no need to log a RW mount of a typical RW share */ } - /* - * The cookie is initialized from volume info returned above. - * Inside cifs_fscache_get_super_cookie it checks - * that we do not get super cookie twice. - */ - cifs_fscache_get_super_cookie(tcon); } /* @@ -3426,6 +3424,7 @@ static int connect_dfs_root(struct mount_ctx *mnt_ctx, struct dfs_cache_tgt_list */ mount_put_conns(mnt_ctx); mount_get_dfs_conns(mnt_ctx); + set_root_ses(mnt_ctx); full_path = build_unc_path_to_root(ctx, cifs_sb, true); if (IS_ERR(full_path)) diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 7e409a38a2d7..003c5f1f4dfb 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -16,14 +16,7 @@ * Key layout of CIFS server cache index object */ struct cifs_server_key { - struct { - uint16_t family; /* address family */ - __be16 port; /* IP port */ - } hdr; - union { - struct in_addr ipv4_addr; - struct in6_addr ipv6_addr; - }; + __u64 conn_id; } __packed; /* @@ -31,42 +24,23 @@ struct cifs_server_key { */ void cifs_fscache_get_client_cookie(struct TCP_Server_Info *server) { - const struct sockaddr *sa = (struct sockaddr *) &server->dstaddr; - const struct sockaddr_in *addr = (struct sockaddr_in *) sa; - const struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *) sa; struct cifs_server_key key; - uint16_t key_len = sizeof(key.hdr); - - memset(&key, 0, sizeof(key)); /* - * Should not be a problem as sin_family/sin6_family overlays - * sa_family field + * Check if cookie was already initialized so don't reinitialize it. + * In the future, as we integrate with newer fscache features, + * we may want to instead add a check if cookie has changed */ - key.hdr.family = sa->sa_family; - switch (sa->sa_family) { - case AF_INET: - key.hdr.port = addr->sin_port; - key.ipv4_addr = addr->sin_addr; - key_len += sizeof(key.ipv4_addr); - break; - - case AF_INET6: - key.hdr.port = addr6->sin6_port; - key.ipv6_addr = addr6->sin6_addr; - key_len += sizeof(key.ipv6_addr); - break; - - default: - cifs_dbg(VFS, "Unknown network family '%d'\n", sa->sa_family); - server->fscache = NULL; + if (server->fscache) return; - } + + memset(&key, 0, sizeof(key)); + key.conn_id = server->conn_id; server->fscache = fscache_acquire_cookie(cifs_fscache_netfs.primary_index, &cifs_fscache_server_index_def, - &key, key_len, + &key, sizeof(key), NULL, 0, server, 0, true); cifs_dbg(FYI, "%s: (0x%p/0x%p)\n", @@ -92,7 +66,7 @@ void cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) * In the future, as we integrate with newer fscache features, * we may want to instead add a check if cookie has changed */ - if (tcon->fscache == NULL) + if (tcon->fscache) return; sharename = extract_sharename(tcon->treeName); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 82848412ad85..96d083db1737 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1376,6 +1376,13 @@ iget_no_retry: inode = ERR_PTR(rc); } + /* + * The cookie is initialized from volume info returned above. + * Inside cifs_fscache_get_super_cookie it checks + * that we do not get super cookie twice. + */ + cifs_fscache_get_super_cookie(tcon); + out: kfree(path); free_xid(xid); diff --git a/fs/file.c b/fs/file.c index 8627dacfc424..ad4a8bf3cf10 100644 --- a/fs/file.c +++ b/fs/file.c @@ -858,6 +858,10 @@ loop: file = NULL; else if (!get_file_rcu_many(file, refs)) goto loop; + else if (files_lookup_fd_raw(files, fd) != file) { + fput_many(file, refs); + goto loop; + } } rcu_read_unlock(); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 8dbd6fe66420..44a7a4288956 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1857,7 +1857,6 @@ void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs) void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) { - struct gfs2_holder mock_gh = { .gh_gl = gl, .gh_state = state, }; unsigned long delay = 0; unsigned long holdtime; unsigned long now = jiffies; @@ -1890,8 +1889,13 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) * keep the glock until the last strong holder is done with it. */ if (!find_first_strong_holder(gl)) { - if (state == LM_ST_UNLOCKED) - mock_gh.gh_state = LM_ST_EXCLUSIVE; + struct gfs2_holder mock_gh = { + .gh_gl = gl, + .gh_state = (state == LM_ST_UNLOCKED) ? + LM_ST_EXCLUSIVE : state, + .gh_iflags = BIT(HIF_HOLDER) + }; + demote_incompat_holders(gl, &mock_gh); } handle_callback(gl, state, delay, true); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 6424b903e885..89905f4f29bb 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -40,37 +40,6 @@ static const struct inode_operations gfs2_file_iops; static const struct inode_operations gfs2_dir_iops; static const struct inode_operations gfs2_symlink_iops; -static int iget_test(struct inode *inode, void *opaque) -{ - u64 no_addr = *(u64 *)opaque; - - return GFS2_I(inode)->i_no_addr == no_addr; -} - -static int iget_set(struct inode *inode, void *opaque) -{ - u64 no_addr = *(u64 *)opaque; - - GFS2_I(inode)->i_no_addr = no_addr; - inode->i_ino = no_addr; - return 0; -} - -static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr) -{ - struct inode *inode; - -repeat: - inode = iget5_locked(sb, no_addr, iget_test, iget_set, &no_addr); - if (!inode) - return inode; - if (is_bad_inode(inode)) { - iput(inode); - goto repeat; - } - return inode; -} - /** * gfs2_set_iop - Sets inode operations * @inode: The inode with correct i_mode filled in @@ -104,6 +73,22 @@ static void gfs2_set_iop(struct inode *inode) } } +static int iget_test(struct inode *inode, void *opaque) +{ + u64 no_addr = *(u64 *)opaque; + + return GFS2_I(inode)->i_no_addr == no_addr; +} + +static int iget_set(struct inode *inode, void *opaque) +{ + u64 no_addr = *(u64 *)opaque; + + GFS2_I(inode)->i_no_addr = no_addr; + inode->i_ino = no_addr; + return 0; +} + /** * gfs2_inode_lookup - Lookup an inode * @sb: The super block @@ -132,12 +117,11 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, { struct inode *inode; struct gfs2_inode *ip; - struct gfs2_glock *io_gl = NULL; struct gfs2_holder i_gh; int error; gfs2_holder_mark_uninitialized(&i_gh); - inode = gfs2_iget(sb, no_addr); + inode = iget5_locked(sb, no_addr, iget_test, iget_set, &no_addr); if (!inode) return ERR_PTR(-ENOMEM); @@ -145,22 +129,16 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, if (inode->i_state & I_NEW) { struct gfs2_sbd *sdp = GFS2_SB(inode); + struct gfs2_glock *io_gl; error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (unlikely(error)) goto fail; - flush_delayed_work(&ip->i_gl->gl_work); - - error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); - if (unlikely(error)) - goto fail; - if (blktype != GFS2_BLKST_UNLINKED) - gfs2_cancel_delete_work(io_gl); if (type == DT_UNKNOWN || blktype != GFS2_BLKST_FREE) { /* * The GL_SKIP flag indicates to skip reading the inode - * block. We read the inode with gfs2_inode_refresh + * block. We read the inode when instantiating it * after possibly checking the block type. */ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, @@ -181,24 +159,31 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, } } - glock_set_object(ip->i_gl, ip); set_bit(GLF_INSTANTIATE_NEEDED, &ip->i_gl->gl_flags); - error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); + + error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (unlikely(error)) goto fail; - glock_set_object(ip->i_iopen_gh.gh_gl, ip); + if (blktype != GFS2_BLKST_UNLINKED) + gfs2_cancel_delete_work(io_gl); + error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); gfs2_glock_put(io_gl); - io_gl = NULL; + if (unlikely(error)) + goto fail; /* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */ inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1); inode->i_atime.tv_nsec = 0; + glock_set_object(ip->i_gl, ip); + if (type == DT_UNKNOWN) { /* Inode glock must be locked already */ error = gfs2_instantiate(&i_gh); - if (error) + if (error) { + glock_clear_object(ip->i_gl, ip); goto fail; + } } else { ip->i_no_formal_ino = no_formal_ino; inode->i_mode = DT2IF(type); @@ -206,31 +191,23 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); + glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_set_iop(inode); + unlock_new_inode(inode); } if (no_formal_ino && ip->i_no_formal_ino && no_formal_ino != ip->i_no_formal_ino) { - error = -ESTALE; - if (inode->i_state & I_NEW) - goto fail; iput(inode); - return ERR_PTR(error); + return ERR_PTR(-ESTALE); } - if (inode->i_state & I_NEW) - unlock_new_inode(inode); - return inode; fail: - if (gfs2_holder_initialized(&ip->i_iopen_gh)) { - glock_clear_object(ip->i_iopen_gh.gh_gl, ip); + if (gfs2_holder_initialized(&ip->i_iopen_gh)) gfs2_glock_dq_uninit(&ip->i_iopen_gh); - } - if (io_gl) - gfs2_glock_put(io_gl); if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); iget_failed(inode); @@ -730,18 +707,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (error) goto fail_free_inode; - flush_delayed_work(&ip->i_gl->gl_work); error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (error) goto fail_free_inode; gfs2_cancel_delete_work(io_gl); + error = insert_inode_locked4(inode, ip->i_no_addr, iget_test, &ip->i_no_addr); + BUG_ON(error); + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); if (error) goto fail_gunlock2; - glock_set_object(ip->i_gl, ip); error = gfs2_trans_begin(sdp, blocks, 0); if (error) goto fail_gunlock2; @@ -757,9 +735,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_gunlock2; + glock_set_object(ip->i_gl, ip); glock_set_object(io_gl, ip); gfs2_set_iop(inode); - insert_inode_hash(inode); free_vfs_inode = 0; /* After this point, the inode is no longer considered free. Any failures need to undo @@ -801,17 +779,17 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_glock_dq_uninit(ghs + 1); gfs2_glock_put(io_gl); gfs2_qa_put(dip); + unlock_new_inode(inode); return error; fail_gunlock3: + glock_clear_object(ip->i_gl, ip); glock_clear_object(io_gl, ip); gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_gunlock2: - glock_clear_object(io_gl, ip); gfs2_glock_put(io_gl); fail_free_inode: if (ip->i_gl) { - glock_clear_object(ip->i_gl, ip); if (free_vfs_inode) /* else evict will do the put for us */ gfs2_glock_put(ip->i_gl); } @@ -829,7 +807,10 @@ fail_gunlock: mark_inode_dirty(inode); set_bit(free_vfs_inode ? GIF_FREE_VFS_INODE : GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags); - iput(inode); + if (inode->i_state & I_NEW) + iget_failed(inode); + else + iput(inode); } if (gfs2_holder_initialized(ghs + 1)) gfs2_glock_dq_uninit(ghs + 1); diff --git a/fs/io-wq.c b/fs/io-wq.c index 88202de519f6..50cf9f92da36 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -714,6 +714,13 @@ static bool io_wq_work_match_all(struct io_wq_work *work, void *data) static inline bool io_should_retry_thread(long err) { + /* + * Prevent perpetual task_work retry, if the task (or its group) is + * exiting. + */ + if (fatal_signal_pending(current)) + return false; + switch (err) { case -EAGAIN: case -ERESTARTSYS: diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 9320a42dfaf9..7046f9bdd8dc 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -1008,8 +1008,8 @@ out: } EXPORT_SYMBOL(netfs_readpage); -/** - * netfs_skip_folio_read - prep a folio for writing without reading first +/* + * Prepare a folio for writing without reading first * @folio: The folio being prepared * @pos: starting position for the write * @len: length of write diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 64b9bf334806..6771f357ad2c 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3122,7 +3122,6 @@ xfs_rename( * appropriately. */ if (flags & RENAME_WHITEOUT) { - ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE))); error = xfs_rename_alloc_whiteout(mnt_userns, target_dp, &wip); if (error) return error; diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e974caf39d3e..8c8f7a4d93af 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -153,6 +153,8 @@ struct kretprobe { struct kretprobe_holder *rph; }; +#define KRETPROBE_MAX_DATA_SIZE 4096 + struct kretprobe_instance { union { struct freelist_node freelist; diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index 120e5e90fa1d..4da8d4a4140b 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -27,9 +27,9 @@ struct kvm_dirty_ring { int index; }; -#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0) +#ifndef CONFIG_HAVE_KVM_DIRTY_RING /* - * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should + * If CONFIG_HAVE_HVM_DIRTY_RING not defined, kvm_dirty_ring.o should * not be included as well, so define these nop functions for the arch. */ static inline u32 kvm_dirty_ring_get_rsvd_entries(void) @@ -74,7 +74,7 @@ static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) return true; } -#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ +#else /* CONFIG_HAVE_KVM_DIRTY_RING */ u32 kvm_dirty_ring_get_rsvd_entries(void); int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); @@ -98,6 +98,6 @@ struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset); void kvm_dirty_ring_free(struct kvm_dirty_ring *ring); bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring); -#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ +#endif /* CONFIG_HAVE_KVM_DIRTY_RING */ #endif /* KVM_DIRTY_RING_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6d138adc78af..f9bbcf519280 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -29,6 +29,10 @@ #include <linux/refcount.h> #include <linux/nospec.h> #include <linux/notifier.h> +#include <linux/hashtable.h> +#include <linux/interval_tree.h> +#include <linux/rbtree.h> +#include <linux/xarray.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -310,7 +314,9 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; +#ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; +#endif struct pid __rcu *pid; int sigset_active; sigset_t sigset; @@ -355,11 +361,13 @@ struct kvm_vcpu { struct kvm_dirty_ring dirty_ring; /* - * The index of the most recently used memslot by this vCPU. It's ok - * if this becomes stale due to memslot changes since we always check - * it is a valid slot. + * The most recently used memslot by this vCPU and the slots generation + * for which it is valid. + * No wraparound protection is needed since generations won't overflow in + * thousands of years, even assuming 1M memslot operations per second. */ - int last_used_slot; + struct kvm_memory_slot *last_used_slot; + u64 last_used_slot_gen; }; /* must be called with irqs disabled */ @@ -424,7 +432,26 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) +/* + * Since at idle each memslot belongs to two memslot sets it has to contain + * two embedded nodes for each data structure that it forms a part of. + * + * Two memslot sets (one active and one inactive) are necessary so the VM + * continues to run on one memslot set while the other is being modified. + * + * These two memslot sets normally point to the same set of memslots. + * They can, however, be desynchronized when performing a memslot management + * operation by replacing the memslot to be modified by its copy. + * After the operation is complete, both memslot sets once again point to + * the same, common set of memslot data. + * + * The memslots themselves are independent of each other so they can be + * individually added or deleted. + */ struct kvm_memory_slot { + struct hlist_node id_node[2]; + struct interval_tree_node hva_node[2]; + struct rb_node gfn_node[2]; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; @@ -435,7 +462,7 @@ struct kvm_memory_slot { u16 as_id; }; -static inline bool kvm_slot_dirty_track_enabled(struct kvm_memory_slot *slot) +static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; } @@ -519,18 +546,21 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) } #endif -/* - * Note: - * memslots are not sorted by id anymore, please use id_to_memslot() - * to get the memslot by its id. - */ struct kvm_memslots { u64 generation; - /* The mapping table from slot id to the index in memslots[]. */ - short id_to_index[KVM_MEM_SLOTS_NUM]; - atomic_t last_used_slot; - int used_slots; - struct kvm_memory_slot memslots[]; + atomic_long_t last_used_slot; + struct rb_root_cached hva_tree; + struct rb_root gfn_tree; + /* + * The mapping table from slot id to memslot. + * + * 7-bit bucket count matches the size of the old id to index array for + * 512 slots, while giving good performance with this slot count. + * Higher bucket counts bring only small performance improvements but + * always result in higher memory usage (even for lower memslot counts). + */ + DECLARE_HASHTABLE(id_hash, 7); + int node_idx; }; struct kvm { @@ -551,8 +581,12 @@ struct kvm { */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ + unsigned long nr_memslot_pages; + /* The two memslot sets - active and inactive (per address space) */ + struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2]; + /* The current active memslot set for each address space */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; - struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct xarray vcpu_array; /* Used to wait for completion of MMU notifiers. */ spinlock_t mn_invalidate_lock; @@ -701,19 +735,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); - return kvm->vcpus[i]; + return xa_load(&kvm->vcpu_array, i); } -#define kvm_for_each_vcpu(idx, vcpup, kvm) \ - for (idx = 0; \ - idx < atomic_read(&kvm->online_vcpus) && \ - (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ - idx++) +#define kvm_for_each_vcpu(idx, vcpup, kvm) \ + xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ + (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (id < 0) return NULL; @@ -727,13 +759,12 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -#define kvm_for_each_memslot(memslot, slots) \ - for (memslot = &slots->memslots[0]; \ - memslot < slots->memslots + slots->used_slots; memslot++) \ - if (WARN_ON_ONCE(!memslot->npages)) { \ - } else +static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) +{ + return vcpu->vcpu_idx; +} -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); +void kvm_destroy_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); @@ -793,21 +824,124 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) return __kvm_memslots(vcpu->kvm, as_id); } +static inline bool kvm_memslots_empty(struct kvm_memslots *slots) +{ + return RB_EMPTY_ROOT(&slots->gfn_tree); +} + +#define kvm_for_each_memslot(memslot, bkt, slots) \ + hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ + if (WARN_ON_ONCE(!memslot->npages)) { \ + } else + static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { - int index = slots->id_to_index[id]; struct kvm_memory_slot *slot; + int idx = slots->node_idx; - if (index < 0) - return NULL; + hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { + if (slot->id == id) + return slot; + } + + return NULL; +} + +/* Iterator used for walking memslots that overlap a gfn range. */ +struct kvm_memslot_iter { + struct kvm_memslots *slots; + struct rb_node *node; + struct kvm_memory_slot *slot; +}; - slot = &slots->memslots[index]; +static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) +{ + iter->node = rb_next(iter->node); + if (!iter->node) + return; - WARN_ON(slot->id != id); - return slot; + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]); } +static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, + struct kvm_memslots *slots, + gfn_t start) +{ + int idx = slots->node_idx; + struct rb_node *tmp; + struct kvm_memory_slot *slot; + + iter->slots = slots; + + /* + * Find the so called "upper bound" of a key - the first node that has + * its key strictly greater than the searched one (the start gfn in our case). + */ + iter->node = NULL; + for (tmp = slots->gfn_tree.rb_node; tmp; ) { + slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]); + if (start < slot->base_gfn) { + iter->node = tmp; + tmp = tmp->rb_left; + } else { + tmp = tmp->rb_right; + } + } + + /* + * Find the slot with the lowest gfn that can possibly intersect with + * the range, so we'll ideally have slot start <= range start + */ + if (iter->node) { + /* + * A NULL previous node means that the very first slot + * already has a higher start gfn. + * In this case slot start > range start. + */ + tmp = rb_prev(iter->node); + if (tmp) + iter->node = tmp; + } else { + /* a NULL node below means no slots */ + iter->node = rb_last(&slots->gfn_tree); + } + + if (iter->node) { + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]); + + /* + * It is possible in the slot start < range start case that the + * found slot ends before or at range start (slot end <= range start) + * and so it does not overlap the requested range. + * + * In such non-overlapping case the next slot (if it exists) will + * already have slot start > range start, otherwise the logic above + * would have found it instead of the current slot. + */ + if (iter->slot->base_gfn + iter->slot->npages <= start) + kvm_memslot_iter_next(iter); + } +} + +static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) +{ + if (!iter->node) + return false; + + /* + * If this slot starts beyond or at the end of the range so does + * every next one + */ + return iter->slot->base_gfn < end; +} + +/* Iterate over each memslot at least partially intersecting [start, end) range */ +#define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \ + for (kvm_memslot_iter_start(iter, slots, start); \ + kvm_memslot_iter_is_valid(iter, end); \ + kvm_memslot_iter_next(iter)) + /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot @@ -833,11 +967,10 @@ int __kvm_set_memory_region(struct kvm *kvm, void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); @@ -863,9 +996,9 @@ void kvm_set_page_accessed(struct page *page); kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); -kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, +kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, bool *writable, hva_t *hva); @@ -942,7 +1075,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); -void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn); +void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); @@ -969,7 +1102,8 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); -void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_vcpu_halt(struct kvm_vcpu *vcpu); +bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); @@ -1152,6 +1286,20 @@ static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) #endif } +/* + * Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns + * true if the vCPU was blocking and was awakened, false otherwise. + */ +static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) +{ + return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); +} + +static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) +{ + return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)); +} + #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and @@ -1204,25 +1352,15 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* - * Returns a pointer to the memslot at slot_index if it contains gfn. + * Returns a pointer to the memslot if it contains gfn. * Otherwise returns NULL. */ static inline struct kvm_memory_slot * -try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) +try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - struct kvm_memory_slot *slot; - - if (slot_index < 0 || slot_index >= slots->used_slots) + if (!slot) return NULL; - /* - * slot_index can come from vcpu->last_used_slot which is not kept - * in sync with userspace-controllable memslot deletion. So use nospec - * to prevent the CPU from speculating past the end of memslots[]. - */ - slot_index = array_index_nospec(slot_index, slots->used_slots); - slot = &slots->memslots[slot_index]; - if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) return slot; else @@ -1230,63 +1368,63 @@ try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) } /* - * Returns a pointer to the memslot that contains gfn and records the index of - * the slot in index. Otherwise returns NULL. + * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. * - * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! + * With "approx" set returns the memslot also when the address falls + * in a hole. In that case one of the memslots bordering the hole is + * returned. */ static inline struct kvm_memory_slot * -search_memslots(struct kvm_memslots *slots, gfn_t gfn, int *index) +search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) { - int start = 0, end = slots->used_slots; - struct kvm_memory_slot *memslots = slots->memslots; struct kvm_memory_slot *slot; - - if (unlikely(!slots->used_slots)) - return NULL; - - while (start < end) { - int slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - slot = try_get_memslot(slots, start, gfn); - if (slot) { - *index = start; - return slot; + struct rb_node *node; + int idx = slots->node_idx; + + slot = NULL; + for (node = slots->gfn_tree.rb_node; node; ) { + slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]); + if (gfn >= slot->base_gfn) { + if (gfn < slot->base_gfn + slot->npages) + return slot; + node = node->rb_right; + } else + node = node->rb_left; } - return NULL; + return approx ? slot : NULL; } -/* - * __gfn_to_memslot() and its descendants are here because it is called from - * non-modular code in arch/powerpc/kvm/book3s_64_vio{,_hv}.c. gfn_to_memslot() - * itself isn't here as an inline because that would bloat other code too much. - */ static inline struct kvm_memory_slot * -__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; - int slot_index = atomic_read(&slots->last_used_slot); - slot = try_get_memslot(slots, slot_index, gfn); + slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot); + slot = try_get_memslot(slot, gfn); if (slot) return slot; - slot = search_memslots(slots, gfn, &slot_index); + slot = search_memslots(slots, gfn, approx); if (slot) { - atomic_set(&slots->last_used_slot, slot_index); + atomic_long_set(&slots->last_used_slot, (unsigned long)slot); return slot; } return NULL; } +/* + * __gfn_to_memslot() and its descendants are here to allow arch code to inline + * the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline + * because that would bloat other code too much. + */ +static inline struct kvm_memory_slot * +__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +{ + return ____gfn_to_memslot(slots, gfn, false); +} + static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { @@ -1462,7 +1600,8 @@ struct _kvm_stats_desc { STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ - HALT_POLL_HIST_COUNT) + HALT_POLL_HIST_COUNT), \ + STATS_DESC_ICOUNTER(VCPU_GENERIC, blocking) extern struct dentry *kvm_debugfs_dir; diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 234eab059839..888ef12862c9 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -87,6 +87,7 @@ struct kvm_vcpu_stat_generic { u64 halt_poll_success_hist[HALT_POLL_HIST_COUNT]; u64 halt_poll_fail_hist[HALT_POLL_HIST_COUNT]; u64 halt_wait_hist[HALT_POLL_HIST_COUNT]; + u64 blocking; }; #define KVM_STATS_NAME_SIZE 48 diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3636df90899a..fbaab440a484 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9698,7 +9698,10 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 regs_84_to_68[0x11]; u8 tracer_registers[0x4]; - u8 regs_63_to_32[0x20]; + u8 regs_63_to_46[0x12]; + u8 mrtc[0x1]; + u8 regs_44_to_32[0xd]; + u8 regs_31_to_0[0x20]; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ec42495a43a..be5cb3360b94 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4404,7 +4404,8 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); - txq->xmit_lock_owner = cpu; + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, cpu); } static inline bool __netif_tx_acquire(struct netdev_queue *txq) @@ -4421,26 +4422,32 @@ static inline void __netif_tx_release(struct netdev_queue *txq) static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); - txq->xmit_lock_owner = smp_processor_id(); + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } static inline bool __netif_tx_trylock(struct netdev_queue *txq) { bool ok = spin_trylock(&txq->_xmit_lock); - if (likely(ok)) - txq->xmit_lock_owner = smp_processor_id(); + + if (likely(ok)) { + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); + } return ok; } static inline void __netif_tx_unlock(struct netdev_queue *txq) { - txq->xmit_lock_owner = -1; + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { - txq->xmit_lock_owner = -1; + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h index 6c9f19a33865..ce3c58286062 100644 --- a/include/linux/sched/cputime.h +++ b/include/linux/sched/cputime.h @@ -18,15 +18,16 @@ #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void task_cputime(struct task_struct *t, +extern bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime); extern u64 task_gtime(struct task_struct *t); #else -static inline void task_cputime(struct task_struct *t, +static inline bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { *utime = t->utime; *stime = t->stime; + return false; } static inline u64 task_gtime(struct task_struct *t) diff --git a/include/linux/siphash.h b/include/linux/siphash.h index bf21591a9e5e..0cda61855d90 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -27,9 +27,7 @@ static inline bool siphash_key_is_zero(const siphash_key_t *key) } u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key); -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key); -#endif u64 siphash_1u64(const u64 a, const siphash_key_t *key); u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key); @@ -82,10 +80,9 @@ static inline u64 ___siphash_aligned(const __le64 *data, size_t len, static inline u64 siphash(const void *data, size_t len, const siphash_key_t *key) { -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT)) + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + !IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT)) return __siphash_unaligned(data, len, key); -#endif return ___siphash_aligned(data, len, key); } @@ -96,10 +93,8 @@ typedef struct { u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key); -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key); -#endif u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key); u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key); @@ -135,10 +130,9 @@ static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len, static inline u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key) { -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT)) + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + !IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT)) return __hsiphash_unaligned(data, len, key); -#endif return ___hsiphash_aligned(data, len, key); } diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 4202c609bb0b..7994455ec714 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -133,7 +133,7 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) if (unlikely(READ_ONCE(sk->sk_napi_id) != skb->napi_id)) WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif - sk_rx_queue_set(sk, skb); + sk_rx_queue_update(sk, skb); } static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id) diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h index 67634675e919..df6622a5fe98 100644 --- a/include/net/dst_cache.h +++ b/include/net/dst_cache.h @@ -80,6 +80,17 @@ static inline void dst_cache_reset(struct dst_cache *dst_cache) } /** + * dst_cache_reset_now - invalidate the cache contents immediately + * @dst_cache: the cache + * + * The caller must be sure there are no concurrent users, as this frees + * all dst_cache users immediately, rather than waiting for the next + * per-cpu usage like dst_cache_reset does. Most callers should use the + * higher speed lazily-freed dst_cache_reset function instead. + */ +void dst_cache_reset_now(struct dst_cache *dst_cache); + +/** * dst_cache_init - initialize the cache, allocating the required storage * @dst_cache: the cache * @gfp: allocation flags diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 4b10676c69d1..bd07484ab9dd 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -69,7 +69,7 @@ struct fib_rules_ops { int (*action)(struct fib_rule *, struct flowi *, int, struct fib_lookup_arg *); - bool (*suppress)(struct fib_rule *, + bool (*suppress)(struct fib_rule *, int, struct fib_lookup_arg *); int (*match)(struct fib_rule *, struct flowi *, int); @@ -218,7 +218,9 @@ INDIRECT_CALLABLE_DECLARE(int fib4_rule_action(struct fib_rule *rule, struct fib_lookup_arg *arg)); INDIRECT_CALLABLE_DECLARE(bool fib6_rule_suppress(struct fib_rule *rule, + int flags, struct fib_lookup_arg *arg)); INDIRECT_CALLABLE_DECLARE(bool fib4_rule_suppress(struct fib_rule *rule, + int flags, struct fib_lookup_arg *arg)); #endif diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index ab5348e57db1..3417ba2d27ad 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -438,7 +438,7 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { - return net->ipv4.fib_num_tclassid_users; + return atomic_read(&net->ipv4.fib_num_tclassid_users); } #else static inline int fib_num_tclassid_users(struct net *net) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2f65701a43c9..6c5b2efc4f17 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -65,7 +65,7 @@ struct netns_ipv4 { bool fib_has_custom_local_routes; bool fib_offload_disabled; #ifdef CONFIG_IP_ROUTE_CLASSID - int fib_num_tclassid_users; + atomic_t fib_num_tclassid_users; #endif struct hlist_head *fib_table_hash; struct sock *fibnl; diff --git a/include/net/sock.h b/include/net/sock.h index b32906e1ab55..bea21ff70e74 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1913,18 +1913,31 @@ static inline int sk_tx_queue_get(const struct sock *sk) return -1; } -static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) +static inline void __sk_rx_queue_set(struct sock *sk, + const struct sk_buff *skb, + bool force_set) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (skb_rx_queue_recorded(skb)) { u16 rx_queue = skb_get_rx_queue(skb); - if (unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue)) + if (force_set || + unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue)) WRITE_ONCE(sk->sk_rx_queue_mapping, rx_queue); } #endif } +static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) +{ + __sk_rx_queue_set(sk, skb, true); +} + +static inline void sk_rx_queue_update(struct sock *sk, const struct sk_buff *skb) +{ + __sk_rx_queue_set(sk, skb, false); +} + static inline void sk_rx_queue_clear(struct sock *sk) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING @@ -2430,19 +2443,22 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk) * @sk: socket * * Use the per task page_frag instead of the per socket one for - * optimization when we know that we're in the normal context and owns + * optimization when we know that we're in process context and own * everything that's associated with %current. * - * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest - * inside other socket operations and end up recursing into sk_page_frag() - * while it's already in use. + * Both direct reclaim and page faults can nest inside other + * socket operations and end up recursing into sk_page_frag() + * while it's already in use: explicitly avoid task page_frag + * usage if the caller is potentially doing any of them. + * This assumes that page fault handlers use the GFP_NOFS flags. * * Return: a per task page_frag if context allows that, * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if (gfpflags_normal_context(sk->sk_allocation)) + if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) == + (__GFP_DIRECT_RECLAIM | __GFP_FS)) return ¤t->task_frag; return &sk->sk_frag; diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index 31f4c4f9aeea..ac0893df9c76 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -147,7 +147,7 @@ struct snd_soc_acpi_link_adr { */ /* Descriptor for SST ASoC machine driver */ struct snd_soc_acpi_mach { - const u8 id[ACPI_ID_LEN]; + u8 id[ACPI_ID_LEN]; const struct snd_soc_acpi_codecs *comp_ids; const u32 link_mask; const struct snd_soc_acpi_link_adr *links; diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index a13e20cc66b4..0512fde5e697 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -196,6 +196,13 @@ struct drm_virtgpu_context_init { __u64 ctx_set_params; }; +/* + * Event code that's given when VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK is in + * effect. The event size is sizeof(drm_event), since there is no additional + * payload. + */ +#define VIRTGPU_EVENT_FENCE_SIGNALED 0x90000000 + #define DRM_IOCTL_VIRTGPU_MAP \ DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map) diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 5da4ee234e0b..c0c2f3ed5729 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -117,7 +117,7 @@ #define ETH_P_IFE 0xED3E /* ForCES inter-FE LFB type */ #define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */ -#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is less than this value +#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is more than this value * then the frame is Ethernet II. Else it is 802.3 */ /* diff --git a/kernel/kprobes.c b/kernel/kprobes.c index e9db0c810554..21eccc961bba 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2086,6 +2086,9 @@ int register_kretprobe(struct kretprobe *rp) } } + if (rp->data_size > KRETPROBE_MAX_DATA_SIZE) + return -E2BIG; + rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 76f9deeaa942..77563109c0ea 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1918,7 +1918,7 @@ static void __init init_uclamp_rq(struct rq *rq) }; } - rq->uclamp_flags = 0; + rq->uclamp_flags = UCLAMP_FLAG_IDLE; } static void __init init_uclamp(void) @@ -6617,11 +6617,11 @@ static int __init setup_preempt_mode(char *str) int mode = sched_dynamic_mode(str); if (mode < 0) { pr_warn("Dynamic Preempt: unsupported mode: %s\n", str); - return 1; + return 0; } sched_dynamic_update(mode); - return 0; + return 1; } __setup("preempt=", setup_preempt_mode); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 872e481d5098..9392aea1804e 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) .sum_exec_runtime = p->se.sum_exec_runtime, }; - task_cputime(p, &cputime.utime, &cputime.stime); + if (task_cputime(p, &cputime.utime, &cputime.stime)) + cputime.sum_exec_runtime = task_sched_runtime(p); cputime_adjust(&cputime, &p->prev_cputime, ut, st); } EXPORT_SYMBOL_GPL(task_cputime_adjusted); @@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t) * add up the pending nohz execution time since the last * cputime snapshot. */ -void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) +bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { struct vtime *vtime = &t->vtime; unsigned int seq; u64 delta; + int ret; if (!vtime_accounting_enabled()) { *utime = t->utime; *stime = t->stime; - return; + return false; } do { + ret = false; seq = read_seqcount_begin(&vtime->seqcount); *utime = t->utime; @@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) if (vtime->state < VTIME_SYS) continue; + ret = true; delta = vtime_delta(vtime); /* @@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) else *utime += vtime->utime + delta; } while (read_seqcount_retry(&vtime->seqcount, seq)); + + return ret; } static int vtime_state_fetch(struct vtime *vtime, int cpu) diff --git a/kernel/softirq.c b/kernel/softirq.c index 322b65d45676..41f470929e99 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -595,7 +595,8 @@ void irq_enter_rcu(void) { __irq_enter_raw(); - if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)) + if (tick_nohz_full_cpu(smp_processor_id()) || + (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))) tick_irq_enter(); account_hardirq_enter(current); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6bffe5af8cb1..17a283ce2b20 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1375,6 +1375,13 @@ static inline void tick_nohz_irq_enter(void) now = ktime_get(); if (ts->idle_active) tick_nohz_stop_idle(ts, now); + /* + * If all CPUs are idle. We may need to update a stale jiffies value. + * Note nohz_full is a special case: a timekeeper is guaranteed to stay + * alive but it might be busy looping with interrupts disabled in some + * rare case (typically stop machine). So we must make sure we have a + * last resort. + */ if (ts->tick_stopped) tick_nohz_update_jiffies(now); } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 9555b8e1d1e3..319f9c8ca7e7 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3757,7 +3757,7 @@ static int check_synth_field(struct synth_event *event, if (strcmp(field->type, hist_field->type) != 0) { if (field->size != hist_field->size || - field->is_signed != hist_field->is_signed) + (!field->is_string && field->is_signed != hist_field->is_signed)) return -EINVAL; } diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 39bb56d2dcbe..9628b5571846 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -15,6 +15,7 @@ #include <linux/jhash.h> #include <linux/slab.h> #include <linux/sort.h> +#include <linux/kmemleak.h> #include "tracing_map.h" #include "trace.h" @@ -307,6 +308,7 @@ static void tracing_map_array_free(struct tracing_map_array *a) for (i = 0; i < a->n_pages; i++) { if (!a->pages[i]) break; + kmemleak_free(a->pages[i]); free_page((unsigned long)a->pages[i]); } @@ -342,6 +344,7 @@ static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL); if (!a->pages[i]) goto free; + kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL); } out: return a; diff --git a/lib/siphash.c b/lib/siphash.c index a90112ee72a1..72b9068ab57b 100644 --- a/lib/siphash.c +++ b/lib/siphash.c @@ -49,6 +49,7 @@ SIPROUND; \ return (v0 ^ v1) ^ (v2 ^ v3); +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); @@ -80,8 +81,8 @@ u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key) POSTAMBLE } EXPORT_SYMBOL(__siphash_aligned); +#endif -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); @@ -113,7 +114,6 @@ u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key) POSTAMBLE } EXPORT_SYMBOL(__siphash_unaligned); -#endif /** * siphash_1u64 - compute 64-bit siphash PRF value of a u64 @@ -250,6 +250,7 @@ EXPORT_SYMBOL(siphash_3u32); HSIPROUND; \ return (v0 ^ v1) ^ (v2 ^ v3); +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); @@ -280,8 +281,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_aligned); +#endif -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key) { @@ -313,7 +314,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len, HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_unaligned); -#endif /** * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32 @@ -418,6 +418,7 @@ EXPORT_SYMBOL(hsiphash_4u32); HSIPROUND; \ return v1 ^ v3; +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u32)); @@ -438,8 +439,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_aligned); +#endif -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key) { @@ -461,7 +462,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len, HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_unaligned); -#endif /** * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32 diff --git a/net/core/dev.c b/net/core/dev.c index 15ac064b5562..2a352e668d10 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4210,7 +4210,10 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ - if (txq->xmit_lock_owner != cpu) { + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + if (READ_ONCE(txq->xmit_lock_owner) != cpu) { if (dev_xmit_recursion()) goto recursion_alert; diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c index be74ab4551c2..0ccfd5fa5cb9 100644 --- a/net/core/dst_cache.c +++ b/net/core/dst_cache.c @@ -162,3 +162,22 @@ void dst_cache_destroy(struct dst_cache *dst_cache) free_percpu(dst_cache->cache); } EXPORT_SYMBOL_GPL(dst_cache_destroy); + +void dst_cache_reset_now(struct dst_cache *dst_cache) +{ + int i; + + if (!dst_cache->cache) + return; + + dst_cache->reset_ts = jiffies; + for_each_possible_cpu(i) { + struct dst_cache_pcpu *idst = per_cpu_ptr(dst_cache->cache, i); + struct dst_entry *dst = idst->dst; + + idst->cookie = 0; + idst->dst = NULL; + dst_release(dst); + } +} +EXPORT_SYMBOL_GPL(dst_cache_reset_now); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 79df7cd9dbc1..1bb567a3b329 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -323,7 +323,7 @@ jumped: if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress, fib6_rule_suppress, fib4_rule_suppress, - rule, arg)) + rule, flags, arg)) continue; if (err != -EAGAIN) { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 9fe13e4f5d08..4d61ddd8a0ec 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1582,7 +1582,7 @@ static int __net_init fib_net_init(struct net *net) int error; #ifdef CONFIG_IP_ROUTE_CLASSID - net->ipv4.fib_num_tclassid_users = 0; + atomic_set(&net->ipv4.fib_num_tclassid_users, 0); #endif error = ip_fib_net_init(net); if (error < 0) diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index ce54a30c2ef1..d279cb8ac158 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -141,6 +141,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_action(struct fib_rule *rule, } INDIRECT_CALLABLE_SCOPE bool fib4_rule_suppress(struct fib_rule *rule, + int flags, struct fib_lookup_arg *arg) { struct fib_result *result = (struct fib_result *) arg->result; @@ -263,7 +264,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, if (tb[FRA_FLOW]) { rule4->tclassid = nla_get_u32(tb[FRA_FLOW]); if (rule4->tclassid) - net->ipv4.fib_num_tclassid_users++; + atomic_inc(&net->ipv4.fib_num_tclassid_users); } #endif @@ -295,7 +296,7 @@ static int fib4_rule_delete(struct fib_rule *rule) #ifdef CONFIG_IP_ROUTE_CLASSID if (((struct fib4_rule *)rule)->tclassid) - net->ipv4.fib_num_tclassid_users--; + atomic_dec(&net->ipv4.fib_num_tclassid_users); #endif net->ipv4.fib_has_custom_rules = true; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3364cb9c67e0..fde7797b5806 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -220,7 +220,7 @@ void fib_nh_release(struct net *net, struct fib_nh *fib_nh) { #ifdef CONFIG_IP_ROUTE_CLASSID if (fib_nh->nh_tclassid) - net->ipv4.fib_num_tclassid_users--; + atomic_dec(&net->ipv4.fib_num_tclassid_users); #endif fib_nh_common_release(&fib_nh->nh_common); } @@ -632,7 +632,7 @@ int fib_nh_init(struct net *net, struct fib_nh *nh, #ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid = cfg->fc_flow; if (nh->nh_tclassid) - net->ipv4.fib_num_tclassid_users++; + atomic_inc(&net->ipv4.fib_num_tclassid_users); #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH nh->fib_nh_weight = nh_weight; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 40f3e4f9f33a..dcedfe29d9d9 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -267,6 +267,7 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_action(struct fib_rule *rule, } INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule, + int flags, struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; @@ -294,8 +295,7 @@ INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule, return false; suppress_route: - if (!(arg->flags & FIB_LOOKUP_NOREF)) - ip6_rt_put(rt); + ip6_rt_put_flags(rt, flags); return true; } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 1b9827ff8ccf..1cbd49d5788d 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -248,9 +248,9 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, * memcmp() alone below is sufficient, right? */ if ((first_word & htonl(0xF00FFFFF)) || - !ipv6_addr_equal(&iph->saddr, &iph2->saddr) || - !ipv6_addr_equal(&iph->daddr, &iph2->daddr) || - *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) { + !ipv6_addr_equal(&iph->saddr, &iph2->saddr) || + !ipv6_addr_equal(&iph->daddr, &iph2->daddr) || + *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) { not_same_flow: NAPI_GRO_CB(p)->same_flow = 0; continue; diff --git a/net/mctp/route.c b/net/mctp/route.c index 46c44823edb7..cdf09c2a7007 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -952,7 +952,7 @@ static int mctp_route_add(struct mctp_dev *mdev, mctp_eid_t daddr_start, } static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start, - unsigned int daddr_extent) + unsigned int daddr_extent, unsigned char type) { struct net *net = dev_net(mdev->dev); struct mctp_route *rt, *tmp; @@ -969,7 +969,8 @@ static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start, list_for_each_entry_safe(rt, tmp, &net->mctp.routes, list) { if (rt->dev == mdev && - rt->min == daddr_start && rt->max == daddr_end) { + rt->min == daddr_start && rt->max == daddr_end && + rt->type == type) { list_del_rcu(&rt->list); /* TODO: immediate RTM_DELROUTE */ mctp_route_release(rt); @@ -987,7 +988,7 @@ int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr) int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr) { - return mctp_route_remove(mdev, addr, 0); + return mctp_route_remove(mdev, addr, 0, RTN_LOCAL); } /* removes all entries for a given device */ @@ -1195,7 +1196,7 @@ static int mctp_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (rtm->rtm_type != RTN_UNICAST) return -EINVAL; - rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len); + rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len, RTN_UNICAST); return rc; } diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c index cc6b8803aa9d..7b7918702592 100644 --- a/net/mctp/test/utils.c +++ b/net/mctp/test/utils.c @@ -12,7 +12,7 @@ static netdev_tx_t mctp_test_dev_tx(struct sk_buff *skb, struct net_device *ndev) { - kfree(skb); + kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index ffeb2df8be7a..0c7bde1c14a6 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -409,7 +409,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, goto err; /* Find the output device */ - out_dev = rcu_dereference(nh->nh_dev); + out_dev = nh->nh_dev; if (!mpls_output_possible(out_dev)) goto tx_err; @@ -698,7 +698,7 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt, (dev->addr_len != nh->nh_via_alen)) goto errout; - RCU_INIT_POINTER(nh->nh_dev, dev); + nh->nh_dev = dev; if (!(dev->flags & IFF_UP)) { nh->nh_flags |= RTNH_F_DEAD; @@ -1491,26 +1491,53 @@ static void mpls_dev_destroy_rcu(struct rcu_head *head) kfree(mdev); } -static void mpls_ifdown(struct net_device *dev, int event) +static int mpls_ifdown(struct net_device *dev, int event) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); - u8 alive, deleted; unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); + bool nh_del = false; + u8 alive = 0; if (!rt) continue; - alive = 0; - deleted = 0; + if (event == NETDEV_UNREGISTER) { + u8 deleted = 0; + + for_nexthops(rt) { + if (!nh->nh_dev || nh->nh_dev == dev) + deleted++; + if (nh->nh_dev == dev) + nh_del = true; + } endfor_nexthops(rt); + + /* if there are no more nexthops, delete the route */ + if (deleted == rt->rt_nhn) { + mpls_route_update(net, index, NULL, NULL); + continue; + } + + if (nh_del) { + size_t size = sizeof(*rt) + rt->rt_nhn * + rt->rt_nh_size; + struct mpls_route *orig = rt; + + rt = kmalloc(size, GFP_KERNEL); + if (!rt) + return -ENOMEM; + memcpy(rt, orig, size); + } + } + change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; - if (rtnl_dereference(nh->nh_dev) != dev) + if (nh->nh_dev != dev) goto next; switch (event) { @@ -1523,23 +1550,22 @@ static void mpls_ifdown(struct net_device *dev, int event) break; } if (event == NETDEV_UNREGISTER) - RCU_INIT_POINTER(nh->nh_dev, NULL); + nh->nh_dev = NULL; if (nh->nh_flags != nh_flags) WRITE_ONCE(nh->nh_flags, nh_flags); next: if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))) alive++; - if (!rtnl_dereference(nh->nh_dev)) - deleted++; } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); - /* if there are no more nexthops, delete the route */ - if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn) - mpls_route_update(net, index, NULL, NULL); + if (nh_del) + mpls_route_update(net, index, rt, NULL); } + + return 0; } static void mpls_ifup(struct net_device *dev, unsigned int flags) @@ -1559,14 +1585,12 @@ static void mpls_ifup(struct net_device *dev, unsigned int flags) alive = 0; change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; - struct net_device *nh_dev = - rtnl_dereference(nh->nh_dev); if (!(nh_flags & flags)) { alive++; continue; } - if (nh_dev != dev) + if (nh->nh_dev != dev) continue; alive++; nh_flags &= ~flags; @@ -1597,8 +1621,12 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, return NOTIFY_OK; switch (event) { + int err; + case NETDEV_DOWN: - mpls_ifdown(dev, event); + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); break; case NETDEV_UP: flags = dev_get_flags(dev); @@ -1609,13 +1637,18 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, break; case NETDEV_CHANGE: flags = dev_get_flags(dev); - if (flags & (IFF_RUNNING | IFF_LOWER_UP)) + if (flags & (IFF_RUNNING | IFF_LOWER_UP)) { mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); - else - mpls_ifdown(dev, event); + } else { + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); + } break; case NETDEV_UNREGISTER: - mpls_ifdown(dev, event); + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); mdev = mpls_dev_get(dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); @@ -1626,8 +1659,6 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, case NETDEV_CHANGENAME: mdev = mpls_dev_get(dev); if (mdev) { - int err; - mpls_dev_sysctl_unregister(dev, mdev); err = mpls_dev_sysctl_register(dev, mdev); if (err) @@ -1994,7 +2025,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; - dev = rtnl_dereference(nh->nh_dev); + dev = nh->nh_dev; if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; if (nh->nh_flags & RTNH_F_LINKDOWN) @@ -2012,7 +2043,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; for_nexthops(rt) { - dev = rtnl_dereference(nh->nh_dev); + dev = nh->nh_dev; if (!dev) continue; @@ -2123,18 +2154,14 @@ static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, static bool mpls_rt_uses_dev(struct mpls_route *rt, const struct net_device *dev) { - struct net_device *nh_dev; - if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; - nh_dev = rtnl_dereference(nh->nh_dev); - if (dev == nh_dev) + if (nh->nh_dev == dev) return true; } else { for_nexthops(rt) { - nh_dev = rtnl_dereference(nh->nh_dev); - if (nh_dev == dev) + if (nh->nh_dev == dev) return true; } endfor_nexthops(rt); } @@ -2222,7 +2249,7 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt) size_t nhsize = 0; for_nexthops(rt) { - if (!rtnl_dereference(nh->nh_dev)) + if (!nh->nh_dev) continue; nhsize += nla_total_size(sizeof(struct rtnexthop)); /* RTA_VIA */ @@ -2468,7 +2495,7 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; - dev = rtnl_dereference(nh->nh_dev); + dev = nh->nh_dev; if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; @@ -2507,7 +2534,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) rt0 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt0)) goto nort0; - RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo); + rt0->rt_nh->nh_dev = lo; rt0->rt_protocol = RTPROT_KERNEL; rt0->rt_payload_type = MPT_IPV4; rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; @@ -2521,7 +2548,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) rt2 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt2)) goto nort2; - RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo); + rt2->rt_nh->nh_dev = lo; rt2->rt_protocol = RTPROT_KERNEL; rt2->rt_payload_type = MPT_IPV6; rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 838cdfc10e47..893df00b77b6 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -87,7 +87,7 @@ enum mpls_payload_type { }; struct mpls_nh { /* next hop label forwarding entry */ - struct net_device __rcu *nh_dev; + struct net_device *nh_dev; /* nh_flags is accessed under RCU in the packet path; it is * modified handling netdev events with rtnl lock held diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4c575324a985..9eba2e648385 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1852,6 +1852,11 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; + if (len == 0) { + pr_warn_once("Zero length message leads to an empty skb\n"); + return -ENODATA; + } + err = scm_send(sock, msg, &scm, true); if (err < 0) return err; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index abf19c0e3ba0..5327d130c4b5 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -500,7 +500,7 @@ void rds_tcp_tune(struct socket *sock) sk->sk_userlocks |= SOCK_SNDBUF_LOCK; } if (rtn->rcvbuf_size > 0) { - sk->sk_sndbuf = rtn->rcvbuf_size; + sk->sk_rcvbuf = rtn->rcvbuf_size; sk->sk_userlocks |= SOCK_RCVBUF_LOCK; } release_sock(sk); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index dbea0bfee48e..8120138dac01 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -135,16 +135,20 @@ struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle) return bundle; } +static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) +{ + rxrpc_put_peer(bundle->params.peer); + kfree(bundle); +} + void rxrpc_put_bundle(struct rxrpc_bundle *bundle) { unsigned int d = bundle->debug_id; unsigned int u = atomic_dec_return(&bundle->usage); _debug("PUT B=%x %u", d, u); - if (u == 0) { - rxrpc_put_peer(bundle->params.peer); - kfree(bundle); - } + if (u == 0) + rxrpc_free_bundle(bundle); } /* @@ -328,7 +332,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c return candidate; found_bundle_free: - kfree(candidate); + rxrpc_free_bundle(candidate); found_bundle: rxrpc_get_bundle(bundle); spin_unlock(&local->client_bundles_lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 68396d052052..0298fe2ad6d3 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -299,6 +299,12 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, return peer; } +static void rxrpc_free_peer(struct rxrpc_peer *peer) +{ + rxrpc_put_local(peer->local); + kfree_rcu(peer, rcu); +} + /* * Set up a new incoming peer. There shouldn't be any other matching peers * since we've already done a search in the list from the non-reentrant context @@ -365,7 +371,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, spin_unlock_bh(&rxnet->peer_hash_lock); if (peer) - kfree(candidate); + rxrpc_free_peer(candidate); else peer = candidate; } @@ -420,8 +426,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); - rxrpc_put_local(peer->local); - kfree_rcu(peer, rcu); + rxrpc_free_peer(peer); } /* @@ -457,8 +462,7 @@ void rxrpc_put_peer_locked(struct rxrpc_peer *peer) if (n == 0) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); - rxrpc_put_local(peer->local); - kfree_rcu(peer, rcu); + rxrpc_free_peer(peer); } } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 3715d2f5ad55..292e4d904ab6 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -195,6 +195,7 @@ int smc_close_active(struct smc_sock *smc) int old_state; long timeout; int rc = 0; + int rc1 = 0; timeout = current->flags & PF_EXITING ? 0 : sock_flag(sk, SOCK_LINGER) ? @@ -232,8 +233,11 @@ again: /* actively shutdown clcsock before peer close it, * prevent peer from entering TIME_WAIT state. */ - if (smc->clcsock && smc->clcsock->sk) - rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); + if (smc->clcsock && smc->clcsock->sk) { + rc1 = kernel_sock_shutdown(smc->clcsock, + SHUT_RDWR); + rc = rc ? rc : rc1; + } } else { /* peer event has changed the state */ goto again; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index bb52c8b5f148..387d28b2f8dd 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -625,18 +625,17 @@ int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) void smc_lgr_cleanup_early(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; - struct list_head *lgr_list; spinlock_t *lgr_lock; if (!lgr) return; smc_conn_free(conn); - lgr_list = smc_lgr_list_head(lgr, &lgr_lock); + smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); /* do not use this link group for new connections */ - if (!list_empty(lgr_list)) - list_del_init(lgr_list); + if (!list_empty(&lgr->list)) + list_del_init(&lgr->list); spin_unlock_bh(lgr_lock); __smc_lgr_terminate(lgr, true); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d3e7ff90889e..dfe623a4e72f 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -521,7 +521,7 @@ static int tls_do_encryption(struct sock *sk, memcpy(&rec->iv_data[iv_offset], tls_ctx->tx.iv, prot->iv_size + prot->salt_size); - xor_iv_with_seq(prot, rec->iv_data, tls_ctx->tx.rec_seq); + xor_iv_with_seq(prot, rec->iv_data + iv_offset, tls_ctx->tx.rec_seq); sge->offset += prot->prepend_size; sge->length -= prot->prepend_size; @@ -1499,7 +1499,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, else memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size); - xor_iv_with_seq(prot, iv, tls_ctx->rx.rec_seq); + xor_iv_with_seq(prot, iv + iv_offset, tls_ctx->rx.rec_seq); /* Prepare AAD */ tls_make_aad(aad, rxm->full_len - prot->overhead_size + diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 10a0bffc3cf6..4208fa8a4db5 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -252,6 +252,11 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x02c8, }, + { + .flags = FLAG_SOF, + .device = 0x02c8, + .codec_hid = "ESSX8336", + }, /* Cometlake-H */ { .flags = FLAG_SOF, @@ -276,6 +281,11 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x06c8, }, + { + .flags = FLAG_SOF, + .device = 0x06c8, + .codec_hid = "ESSX8336", + }, #endif /* Icelake */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index fe51163f2d82..1b46b599a5cf 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -335,7 +335,10 @@ enum { ((pci)->device == 0x0c0c) || \ ((pci)->device == 0x0d0c) || \ ((pci)->device == 0x160c) || \ - ((pci)->device == 0x490d)) + ((pci)->device == 0x490d) || \ + ((pci)->device == 0x4f90) || \ + ((pci)->device == 0x4f91) || \ + ((pci)->device == 0x4f92)) #define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) @@ -2473,6 +2476,13 @@ static const struct pci_device_id azx_ids[] = { /* DG1 */ { PCI_DEVICE(0x8086, 0x490d), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* DG2 */ + { PCI_DEVICE(0x8086, 0x4f90), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + { PCI_DEVICE(0x8086, 0x4f91), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + { PCI_DEVICE(0x8086, 0x4f92), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Alderlake-S */ { PCI_DEVICE(0x8086, 0x7ad0), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h index ea8ab8b43337..d22c96eb2f8f 100644 --- a/sound/pci/hda/hda_local.h +++ b/sound/pci/hda/hda_local.h @@ -438,6 +438,15 @@ int snd_hda_codec_set_pin_target(struct hda_codec *codec, hda_nid_t nid, #define for_each_hda_codec_node(nid, codec) \ for ((nid) = (codec)->core.start_nid; (nid) < (codec)->core.end_nid; (nid)++) +/* Set the codec power_state flag to indicate to allow unsol event handling; + * see hda_codec_unsol_event() in hda_bind.c. Calling this might confuse the + * state tracking, so use with care. + */ +static inline void snd_hda_codec_allow_unsol_events(struct hda_codec *codec) +{ + codec->core.dev.power.power_state = PMSG_ON; +} + /* * get widget capabilities */ diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index 31ff11ab868e..039b9f2f8e94 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -750,6 +750,11 @@ static void cs42l42_resume(struct sub_codec *cs42l42) if (cs42l42->full_scale_vol) cs8409_i2c_write(cs42l42, 0x2001, 0x01); + /* we have to explicitly allow unsol event handling even during the + * resume phase so that the jack event is processed properly + */ + snd_hda_codec_allow_unsol_events(cs42l42->codec); + cs42l42_enable_jack_detect(cs42l42); } diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 65d2c5539919..415701bd10ac 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4380,10 +4380,11 @@ HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862814, "DG1 HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862815, "Alderlake HDMI", patch_i915_tgl_hdmi), -HDA_CODEC_ENTRY(0x8086281c, "Alderlake-P HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI", patch_i915_tgl_hdmi), +HDA_CODEC_ENTRY(0x80862819, "DG2 HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi), +HDA_CODEC_ENTRY(0x8086281c, "Alderlake-P HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi), diff --git a/sound/soc/codecs/cs35l41-spi.c b/sound/soc/codecs/cs35l41-spi.c index 90a921f726c3..3fa99741779a 100644 --- a/sound/soc/codecs/cs35l41-spi.c +++ b/sound/soc/codecs/cs35l41-spi.c @@ -42,34 +42,6 @@ static const struct spi_device_id cs35l41_id_spi[] = { MODULE_DEVICE_TABLE(spi, cs35l41_id_spi); -static void cs35l41_spi_otp_setup(struct cs35l41_private *cs35l41, - bool is_pre_setup, unsigned int *freq) -{ - struct spi_device *spi; - u32 orig_spi_freq; - - spi = to_spi_device(cs35l41->dev); - - if (!spi) { - dev_err(cs35l41->dev, "%s: No SPI device\n", __func__); - return; - } - - if (is_pre_setup) { - orig_spi_freq = spi->max_speed_hz; - if (orig_spi_freq > CS35L41_SPI_MAX_FREQ_OTP) { - spi->max_speed_hz = CS35L41_SPI_MAX_FREQ_OTP; - spi_setup(spi); - } - *freq = orig_spi_freq; - } else { - if (spi->max_speed_hz != *freq) { - spi->max_speed_hz = *freq; - spi_setup(spi); - } - } -} - static int cs35l41_spi_probe(struct spi_device *spi) { const struct regmap_config *regmap_config = &cs35l41_regmap_spi; @@ -81,6 +53,9 @@ static int cs35l41_spi_probe(struct spi_device *spi) if (!cs35l41) return -ENOMEM; + spi->max_speed_hz = CS35L41_SPI_MAX_FREQ; + spi_setup(spi); + spi_set_drvdata(spi, cs35l41); cs35l41->regmap = devm_regmap_init_spi(spi, regmap_config); if (IS_ERR(cs35l41->regmap)) { @@ -91,7 +66,6 @@ static int cs35l41_spi_probe(struct spi_device *spi) cs35l41->dev = &spi->dev; cs35l41->irq = spi->irq; - cs35l41->otp_setup = cs35l41_spi_otp_setup; return cs35l41_probe(cs35l41, pdata); } diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index 9d0530dde996..9c4d481f7614 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -302,7 +302,6 @@ static int cs35l41_otp_unpack(void *data) const struct cs35l41_otp_packed_element_t *otp_map; struct cs35l41_private *cs35l41 = data; int bit_offset, word_offset, ret, i; - unsigned int orig_spi_freq; unsigned int bit_sum = 8; u32 otp_val, otp_id_reg; u32 *otp_mem; @@ -326,9 +325,6 @@ static int cs35l41_otp_unpack(void *data) goto err_otp_unpack; } - if (cs35l41->otp_setup) - cs35l41->otp_setup(cs35l41, true, &orig_spi_freq); - ret = regmap_bulk_read(cs35l41->regmap, CS35L41_OTP_MEM0, otp_mem, CS35L41_OTP_SIZE_WORDS); if (ret < 0) { @@ -336,9 +332,6 @@ static int cs35l41_otp_unpack(void *data) goto err_otp_unpack; } - if (cs35l41->otp_setup) - cs35l41->otp_setup(cs35l41, false, &orig_spi_freq); - otp_map = otp_map_match->map; bit_offset = otp_map_match->bit_offset; diff --git a/sound/soc/codecs/cs35l41.h b/sound/soc/codecs/cs35l41.h index 6cffe8a55beb..48485b08a6f1 100644 --- a/sound/soc/codecs/cs35l41.h +++ b/sound/soc/codecs/cs35l41.h @@ -726,7 +726,7 @@ #define CS35L41_FS2_WINDOW_MASK 0x00FFF800 #define CS35L41_FS2_WINDOW_SHIFT 12 -#define CS35L41_SPI_MAX_FREQ_OTP 4000000 +#define CS35L41_SPI_MAX_FREQ 4000000 #define CS35L41_RX_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE) #define CS35L41_TX_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE) @@ -764,8 +764,6 @@ struct cs35l41_private { int irq; /* GPIO for /RST */ struct gpio_desc *reset_gpio; - void (*otp_setup)(struct cs35l41_private *cs35l41, bool is_pre_setup, - unsigned int *freq); }; int cs35l41_probe(struct cs35l41_private *cs35l41, diff --git a/sound/soc/codecs/rk817_codec.c b/sound/soc/codecs/rk817_codec.c index 943d7d933e81..03f24edfe4f6 100644 --- a/sound/soc/codecs/rk817_codec.c +++ b/sound/soc/codecs/rk817_codec.c @@ -539,3 +539,4 @@ module_platform_driver(rk817_codec_driver); MODULE_DESCRIPTION("ASoC RK817 codec driver"); MODULE_AUTHOR("binyuan <[email protected]>"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:rk817-codec"); diff --git a/sound/soc/intel/common/soc-acpi-intel-cml-match.c b/sound/soc/intel/common/soc-acpi-intel-cml-match.c index b4eb0c97edf1..4eebc79d4b48 100644 --- a/sound/soc/intel/common/soc-acpi-intel-cml-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-cml-match.c @@ -81,6 +81,12 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_cml_machines[] = { .sof_fw_filename = "sof-cml.ri", .sof_tplg_filename = "sof-cml-da7219-max98390.tplg", }, + { + .id = "ESSX8336", + .drv_name = "sof-essx8336", + .sof_fw_filename = "sof-cml.ri", + .sof_tplg_filename = "sof-cml-es8336.tplg", + }, {}, }; EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_cml_machines); diff --git a/sound/soc/soc-acpi.c b/sound/soc/soc-acpi.c index 2ae99b49d3f5..cbd7ea48837b 100644 --- a/sound/soc/soc-acpi.c +++ b/sound/soc/soc-acpi.c @@ -20,8 +20,10 @@ static bool snd_soc_acpi_id_present(struct snd_soc_acpi_mach *machine) if (comp_ids) { for (i = 0; i < comp_ids->num_codecs; i++) { - if (acpi_dev_present(comp_ids->codecs[i], NULL, -1)) + if (acpi_dev_present(comp_ids->codecs[i], NULL, -1)) { + strscpy(machine->id, comp_ids->codecs[i], ACPI_ID_LEN); return true; + } } } diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index 568d351b7a4e..2c0d4d06ab36 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -58,6 +58,13 @@ int hda_ctrl_dai_widget_setup(struct snd_soc_dapm_widget *w) return -EINVAL; } + /* DAI already configured, reset it before reconfiguring it */ + if (sof_dai->configured) { + ret = hda_ctrl_dai_widget_free(w); + if (ret < 0) + return ret; + } + config = &sof_dai->dai_config[sof_dai->current_config]; /* diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c index 8ee9a77bd83d..a74c980ee775 100644 --- a/sound/soc/tegra/tegra186_dspk.c +++ b/sound/soc/tegra/tegra186_dspk.c @@ -26,51 +26,162 @@ static const struct reg_default tegra186_dspk_reg_defaults[] = { { TEGRA186_DSPK_CODEC_CTRL, 0x03000000 }, }; -static int tegra186_dspk_get_control(struct snd_kcontrol *kcontrol, +static int tegra186_dspk_get_fifo_th(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); - if (strstr(kcontrol->id.name, "FIFO Threshold")) - ucontrol->value.integer.value[0] = dspk->rx_fifo_th; - else if (strstr(kcontrol->id.name, "OSR Value")) - ucontrol->value.integer.value[0] = dspk->osr_val; - else if (strstr(kcontrol->id.name, "LR Polarity Select")) - ucontrol->value.integer.value[0] = dspk->lrsel; - else if (strstr(kcontrol->id.name, "Channel Select")) - ucontrol->value.integer.value[0] = dspk->ch_sel; - else if (strstr(kcontrol->id.name, "Mono To Stereo")) - ucontrol->value.integer.value[0] = dspk->mono_to_stereo; - else if (strstr(kcontrol->id.name, "Stereo To Mono")) - ucontrol->value.integer.value[0] = dspk->stereo_to_mono; + ucontrol->value.integer.value[0] = dspk->rx_fifo_th; return 0; } -static int tegra186_dspk_put_control(struct snd_kcontrol *kcontrol, +static int tegra186_dspk_put_fifo_th(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); - int val = ucontrol->value.integer.value[0]; - - if (strstr(kcontrol->id.name, "FIFO Threshold")) - dspk->rx_fifo_th = val; - else if (strstr(kcontrol->id.name, "OSR Value")) - dspk->osr_val = val; - else if (strstr(kcontrol->id.name, "LR Polarity Select")) - dspk->lrsel = val; - else if (strstr(kcontrol->id.name, "Channel Select")) - dspk->ch_sel = val; - else if (strstr(kcontrol->id.name, "Mono To Stereo")) - dspk->mono_to_stereo = val; - else if (strstr(kcontrol->id.name, "Stereo To Mono")) - dspk->stereo_to_mono = val; + int value = ucontrol->value.integer.value[0]; + + if (value == dspk->rx_fifo_th) + return 0; + + dspk->rx_fifo_th = value; + + return 1; +} + +static int tegra186_dspk_get_osr_val(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); + struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); + + ucontrol->value.enumerated.item[0] = dspk->osr_val; return 0; } +static int tegra186_dspk_put_osr_val(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); + struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == dspk->osr_val) + return 0; + + dspk->osr_val = value; + + return 1; +} + +static int tegra186_dspk_get_pol_sel(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); + struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); + + ucontrol->value.enumerated.item[0] = dspk->lrsel; + + return 0; +} + +static int tegra186_dspk_put_pol_sel(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); + struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == dspk->lrsel) + return 0; + + dspk->lrsel = value; + + return 1; +} + +static int tegra186_dspk_get_ch_sel(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); + struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); + + ucontrol->value.enumerated.item[0] = dspk->ch_sel; + + return 0; +} + +static int tegra186_dspk_put_ch_sel(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); + struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == dspk->ch_sel) + return 0; + + dspk->ch_sel = value; + + return 1; +} + +static int tegra186_dspk_get_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); + struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); + + ucontrol->value.enumerated.item[0] = dspk->mono_to_stereo; + + return 0; +} + +static int tegra186_dspk_put_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); + struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == dspk->mono_to_stereo) + return 0; + + dspk->mono_to_stereo = value; + + return 1; +} + +static int tegra186_dspk_get_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); + struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); + + ucontrol->value.enumerated.item[0] = dspk->stereo_to_mono; + + return 0; +} + +static int tegra186_dspk_put_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); + struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == dspk->stereo_to_mono) + return 0; + + dspk->stereo_to_mono = value; + + return 1; +} + static int __maybe_unused tegra186_dspk_runtime_suspend(struct device *dev) { struct tegra186_dspk *dspk = dev_get_drvdata(dev); @@ -279,17 +390,19 @@ static const struct soc_enum tegra186_dspk_lrsel_enum = static const struct snd_kcontrol_new tegrat186_dspk_controls[] = { SOC_SINGLE_EXT("FIFO Threshold", SND_SOC_NOPM, 0, TEGRA186_DSPK_RX_FIFO_DEPTH - 1, 0, - tegra186_dspk_get_control, tegra186_dspk_put_control), + tegra186_dspk_get_fifo_th, tegra186_dspk_put_fifo_th), SOC_ENUM_EXT("OSR Value", tegra186_dspk_osr_enum, - tegra186_dspk_get_control, tegra186_dspk_put_control), + tegra186_dspk_get_osr_val, tegra186_dspk_put_osr_val), SOC_ENUM_EXT("LR Polarity Select", tegra186_dspk_lrsel_enum, - tegra186_dspk_get_control, tegra186_dspk_put_control), + tegra186_dspk_get_pol_sel, tegra186_dspk_put_pol_sel), SOC_ENUM_EXT("Channel Select", tegra186_dspk_ch_sel_enum, - tegra186_dspk_get_control, tegra186_dspk_put_control), + tegra186_dspk_get_ch_sel, tegra186_dspk_put_ch_sel), SOC_ENUM_EXT("Mono To Stereo", tegra186_dspk_mono_conv_enum, - tegra186_dspk_get_control, tegra186_dspk_put_control), + tegra186_dspk_get_mono_to_stereo, + tegra186_dspk_put_mono_to_stereo), SOC_ENUM_EXT("Stereo To Mono", tegra186_dspk_stereo_conv_enum, - tegra186_dspk_get_control, tegra186_dspk_put_control), + tegra186_dspk_get_stereo_to_mono, + tegra186_dspk_put_stereo_to_mono), }; static const struct snd_soc_component_driver tegra186_dspk_cmpnt = { diff --git a/sound/soc/tegra/tegra210_admaif.c b/sound/soc/tegra/tegra210_admaif.c index bcccdf3ddc52..1a2e868a6220 100644 --- a/sound/soc/tegra/tegra210_admaif.c +++ b/sound/soc/tegra/tegra210_admaif.c @@ -424,46 +424,122 @@ static const struct snd_soc_dai_ops tegra_admaif_dai_ops = { .trigger = tegra_admaif_trigger, }; -static int tegra_admaif_get_control(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) +static int tegra210_admaif_pget_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt); + struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value; + + ucontrol->value.enumerated.item[0] = + admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg]; + + return 0; +} + +static int tegra210_admaif_pput_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt); + struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value; + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg]) + return 0; + + admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg] = value; + + return 1; +} + +static int tegra210_admaif_cget_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt); + struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value; + + ucontrol->value.enumerated.item[0] = + admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg]; + + return 0; +} + +static int tegra210_admaif_cput_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt); struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value; + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg]) + return 0; + + admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg] = value; + + return 1; +} + +static int tegra210_admaif_pget_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt); - long *uctl_val = &ucontrol->value.integer.value[0]; + struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value; - if (strstr(kcontrol->id.name, "Playback Mono To Stereo")) - *uctl_val = admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg]; - else if (strstr(kcontrol->id.name, "Capture Mono To Stereo")) - *uctl_val = admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg]; - else if (strstr(kcontrol->id.name, "Playback Stereo To Mono")) - *uctl_val = admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg]; - else if (strstr(kcontrol->id.name, "Capture Stereo To Mono")) - *uctl_val = admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg]; + ucontrol->value.enumerated.item[0] = + admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg]; return 0; } -static int tegra_admaif_put_control(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) +static int tegra210_admaif_pput_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt); struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value; + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg]) + return 0; + + admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg] = value; + + return 1; +} + +static int tegra210_admaif_cget_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt); - int value = ucontrol->value.integer.value[0]; + struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value; - if (strstr(kcontrol->id.name, "Playback Mono To Stereo")) - admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg] = value; - else if (strstr(kcontrol->id.name, "Capture Mono To Stereo")) - admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg] = value; - else if (strstr(kcontrol->id.name, "Playback Stereo To Mono")) - admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg] = value; - else if (strstr(kcontrol->id.name, "Capture Stereo To Mono")) - admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg] = value; + ucontrol->value.enumerated.item[0] = + admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg]; return 0; } +static int tegra210_admaif_cput_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt); + struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value; + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg]) + return 0; + + admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg] = value; + + return 1; +} + static int tegra_admaif_dai_probe(struct snd_soc_dai *dai) { struct tegra_admaif *admaif = snd_soc_dai_get_drvdata(dai); @@ -559,17 +635,21 @@ static const char * const tegra_admaif_mono_conv_text[] = { } #define TEGRA_ADMAIF_CIF_CTRL(reg) \ - NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Mono To Stereo", reg - 1,\ - tegra_admaif_get_control, tegra_admaif_put_control, \ + NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Mono To Stereo", reg - 1, \ + tegra210_admaif_pget_mono_to_stereo, \ + tegra210_admaif_pput_mono_to_stereo, \ tegra_admaif_mono_conv_text), \ - NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Stereo To Mono", reg - 1,\ - tegra_admaif_get_control, tegra_admaif_put_control, \ + NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Stereo To Mono", reg - 1, \ + tegra210_admaif_pget_stereo_to_mono, \ + tegra210_admaif_pput_stereo_to_mono, \ tegra_admaif_stereo_conv_text), \ - NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Mono To Stereo", reg - 1, \ - tegra_admaif_get_control, tegra_admaif_put_control, \ + NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Mono To Stereo", reg - 1, \ + tegra210_admaif_cget_mono_to_stereo, \ + tegra210_admaif_cput_mono_to_stereo, \ tegra_admaif_mono_conv_text), \ - NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Stereo To Mono", reg - 1, \ - tegra_admaif_get_control, tegra_admaif_put_control, \ + NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Stereo To Mono", reg - 1, \ + tegra210_admaif_cget_stereo_to_mono, \ + tegra210_admaif_cput_stereo_to_mono, \ tegra_admaif_stereo_conv_text) static struct snd_kcontrol_new tegra210_admaif_controls[] = { diff --git a/sound/soc/tegra/tegra210_adx.c b/sound/soc/tegra/tegra210_adx.c index d7c7849c2f92..933c4503fe50 100644 --- a/sound/soc/tegra/tegra210_adx.c +++ b/sound/soc/tegra/tegra210_adx.c @@ -193,6 +193,9 @@ static int tegra210_adx_put_byte_map(struct snd_kcontrol *kcontrol, struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value;; + if (value == bytes_map[mc->reg]) + return 0; + if (value >= 0 && value <= 255) { /* update byte map and enable slot */ bytes_map[mc->reg] = value; diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c index a1989eae2b52..388b815443c7 100644 --- a/sound/soc/tegra/tegra210_ahub.c +++ b/sound/soc/tegra/tegra210_ahub.c @@ -62,6 +62,7 @@ static int tegra_ahub_put_value_enum(struct snd_kcontrol *kctl, unsigned int *item = uctl->value.enumerated.item; unsigned int value = e->values[item[0]]; unsigned int i, bit_pos, reg_idx = 0, reg_val = 0; + int change = 0; if (item[0] >= e->items) return -EINVAL; @@ -86,12 +87,14 @@ static int tegra_ahub_put_value_enum(struct snd_kcontrol *kctl, /* Update widget power if state has changed */ if (snd_soc_component_test_bits(cmpnt, update[i].reg, - update[i].mask, update[i].val)) - snd_soc_dapm_mux_update_power(dapm, kctl, item[0], e, - &update[i]); + update[i].mask, + update[i].val)) + change |= snd_soc_dapm_mux_update_power(dapm, kctl, + item[0], e, + &update[i]); } - return 0; + return change; } static struct snd_soc_dai_driver tegra210_ahub_dais[] = { diff --git a/sound/soc/tegra/tegra210_amx.c b/sound/soc/tegra/tegra210_amx.c index af9bddfc3120..689576302ede 100644 --- a/sound/soc/tegra/tegra210_amx.c +++ b/sound/soc/tegra/tegra210_amx.c @@ -222,6 +222,9 @@ static int tegra210_amx_put_byte_map(struct snd_kcontrol *kcontrol, int reg = mc->reg; int value = ucontrol->value.integer.value[0]; + if (value == bytes_map[reg]) + return 0; + if (value >= 0 && value <= 255) { /* Update byte map and enable slot */ bytes_map[reg] = value; diff --git a/sound/soc/tegra/tegra210_dmic.c b/sound/soc/tegra/tegra210_dmic.c index b096478cd2ef..db95794530f4 100644 --- a/sound/soc/tegra/tegra210_dmic.c +++ b/sound/soc/tegra/tegra210_dmic.c @@ -156,51 +156,162 @@ static int tegra210_dmic_hw_params(struct snd_pcm_substream *substream, return 0; } -static int tegra210_dmic_get_control(struct snd_kcontrol *kcontrol, +static int tegra210_dmic_get_boost_gain(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); + struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); + + ucontrol->value.integer.value[0] = dmic->boost_gain; + + return 0; +} + +static int tegra210_dmic_put_boost_gain(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); + struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); + int value = ucontrol->value.integer.value[0]; + + if (value == dmic->boost_gain) + return 0; + + dmic->boost_gain = value; + + return 1; +} + +static int tegra210_dmic_get_ch_select(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); + struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); + + ucontrol->value.enumerated.item[0] = dmic->ch_select; + + return 0; +} + +static int tegra210_dmic_put_ch_select(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); + struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == dmic->ch_select) + return 0; + + dmic->ch_select = value; + + return 1; +} + +static int tegra210_dmic_get_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); + struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); + + ucontrol->value.enumerated.item[0] = dmic->mono_to_stereo; + + return 0; +} + +static int tegra210_dmic_put_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); + struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == dmic->mono_to_stereo) + return 0; + + dmic->mono_to_stereo = value; + + return 1; +} + +static int tegra210_dmic_get_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); + struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); + + ucontrol->value.enumerated.item[0] = dmic->stereo_to_mono; + + return 0; +} + +static int tegra210_dmic_put_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); + struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == dmic->stereo_to_mono) + return 0; + + dmic->stereo_to_mono = value; + + return 1; +} + +static int tegra210_dmic_get_osr_val(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); - if (strstr(kcontrol->id.name, "Boost Gain Volume")) - ucontrol->value.integer.value[0] = dmic->boost_gain; - else if (strstr(kcontrol->id.name, "Channel Select")) - ucontrol->value.integer.value[0] = dmic->ch_select; - else if (strstr(kcontrol->id.name, "Mono To Stereo")) - ucontrol->value.integer.value[0] = dmic->mono_to_stereo; - else if (strstr(kcontrol->id.name, "Stereo To Mono")) - ucontrol->value.integer.value[0] = dmic->stereo_to_mono; - else if (strstr(kcontrol->id.name, "OSR Value")) - ucontrol->value.integer.value[0] = dmic->osr_val; - else if (strstr(kcontrol->id.name, "LR Polarity Select")) - ucontrol->value.integer.value[0] = dmic->lrsel; + ucontrol->value.enumerated.item[0] = dmic->osr_val; return 0; } -static int tegra210_dmic_put_control(struct snd_kcontrol *kcontrol, +static int tegra210_dmic_put_osr_val(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); - int value = ucontrol->value.integer.value[0]; + unsigned int value = ucontrol->value.enumerated.item[0]; - if (strstr(kcontrol->id.name, "Boost Gain Volume")) - dmic->boost_gain = value; - else if (strstr(kcontrol->id.name, "Channel Select")) - dmic->ch_select = ucontrol->value.integer.value[0]; - else if (strstr(kcontrol->id.name, "Mono To Stereo")) - dmic->mono_to_stereo = value; - else if (strstr(kcontrol->id.name, "Stereo To Mono")) - dmic->stereo_to_mono = value; - else if (strstr(kcontrol->id.name, "OSR Value")) - dmic->osr_val = value; - else if (strstr(kcontrol->id.name, "LR Polarity Select")) - dmic->lrsel = value; + if (value == dmic->osr_val) + return 0; + + dmic->osr_val = value; + + return 1; +} + +static int tegra210_dmic_get_pol_sel(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); + struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); + + ucontrol->value.enumerated.item[0] = dmic->lrsel; return 0; } +static int tegra210_dmic_put_pol_sel(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol); + struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == dmic->lrsel) + return 0; + + dmic->lrsel = value; + + return 1; +} + static const struct snd_soc_dai_ops tegra210_dmic_dai_ops = { .hw_params = tegra210_dmic_hw_params, }; @@ -287,19 +398,22 @@ static const struct soc_enum tegra210_dmic_lrsel_enum = static const struct snd_kcontrol_new tegra210_dmic_controls[] = { SOC_SINGLE_EXT("Boost Gain Volume", 0, 0, MAX_BOOST_GAIN, 0, - tegra210_dmic_get_control, tegra210_dmic_put_control), + tegra210_dmic_get_boost_gain, + tegra210_dmic_put_boost_gain), SOC_ENUM_EXT("Channel Select", tegra210_dmic_ch_enum, - tegra210_dmic_get_control, tegra210_dmic_put_control), + tegra210_dmic_get_ch_select, tegra210_dmic_put_ch_select), SOC_ENUM_EXT("Mono To Stereo", - tegra210_dmic_mono_conv_enum, tegra210_dmic_get_control, - tegra210_dmic_put_control), + tegra210_dmic_mono_conv_enum, + tegra210_dmic_get_mono_to_stereo, + tegra210_dmic_put_mono_to_stereo), SOC_ENUM_EXT("Stereo To Mono", - tegra210_dmic_stereo_conv_enum, tegra210_dmic_get_control, - tegra210_dmic_put_control), + tegra210_dmic_stereo_conv_enum, + tegra210_dmic_get_stereo_to_mono, + tegra210_dmic_put_stereo_to_mono), SOC_ENUM_EXT("OSR Value", tegra210_dmic_osr_enum, - tegra210_dmic_get_control, tegra210_dmic_put_control), + tegra210_dmic_get_osr_val, tegra210_dmic_put_osr_val), SOC_ENUM_EXT("LR Polarity Select", tegra210_dmic_lrsel_enum, - tegra210_dmic_get_control, tegra210_dmic_put_control), + tegra210_dmic_get_pol_sel, tegra210_dmic_put_pol_sel), }; static const struct snd_soc_component_driver tegra210_dmic_compnt = { diff --git a/sound/soc/tegra/tegra210_i2s.c b/sound/soc/tegra/tegra210_i2s.c index 45f31ccb49d8..9552bbb939dd 100644 --- a/sound/soc/tegra/tegra210_i2s.c +++ b/sound/soc/tegra/tegra210_i2s.c @@ -302,85 +302,235 @@ static int tegra210_i2s_set_tdm_slot(struct snd_soc_dai *dai, return 0; } -static int tegra210_i2s_set_dai_bclk_ratio(struct snd_soc_dai *dai, - unsigned int ratio) +static int tegra210_i2s_get_loopback(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { - struct tegra210_i2s *i2s = snd_soc_dai_get_drvdata(dai); + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); - i2s->bclk_ratio = ratio; + ucontrol->value.integer.value[0] = i2s->loopback; return 0; } -static int tegra210_i2s_get_control(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) +static int tegra210_i2s_put_loopback(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + int value = ucontrol->value.integer.value[0]; + + if (value == i2s->loopback) + return 0; + + i2s->loopback = value; + + regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL, I2S_CTRL_LPBK_MASK, + i2s->loopback << I2S_CTRL_LPBK_SHIFT); + + return 1; +} + +static int tegra210_i2s_get_fsync_width(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); - long *uctl_val = &ucontrol->value.integer.value[0]; - - if (strstr(kcontrol->id.name, "Loopback")) - *uctl_val = i2s->loopback; - else if (strstr(kcontrol->id.name, "FSYNC Width")) - *uctl_val = i2s->fsync_width; - else if (strstr(kcontrol->id.name, "Capture Stereo To Mono")) - *uctl_val = i2s->stereo_to_mono[I2S_TX_PATH]; - else if (strstr(kcontrol->id.name, "Capture Mono To Stereo")) - *uctl_val = i2s->mono_to_stereo[I2S_TX_PATH]; - else if (strstr(kcontrol->id.name, "Playback Stereo To Mono")) - *uctl_val = i2s->stereo_to_mono[I2S_RX_PATH]; - else if (strstr(kcontrol->id.name, "Playback Mono To Stereo")) - *uctl_val = i2s->mono_to_stereo[I2S_RX_PATH]; - else if (strstr(kcontrol->id.name, "Playback FIFO Threshold")) - *uctl_val = i2s->rx_fifo_th; - else if (strstr(kcontrol->id.name, "BCLK Ratio")) - *uctl_val = i2s->bclk_ratio; + + ucontrol->value.integer.value[0] = i2s->fsync_width; return 0; } -static int tegra210_i2s_put_control(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) +static int tegra210_i2s_put_fsync_width(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); int value = ucontrol->value.integer.value[0]; - if (strstr(kcontrol->id.name, "Loopback")) { - i2s->loopback = value; + if (value == i2s->fsync_width) + return 0; - regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL, - I2S_CTRL_LPBK_MASK, - i2s->loopback << I2S_CTRL_LPBK_SHIFT); + i2s->fsync_width = value; - } else if (strstr(kcontrol->id.name, "FSYNC Width")) { - /* - * Frame sync width is used only for FSYNC modes and not - * applicable for LRCK modes. Reset value for this field is "0", - * which means the width is one bit clock wide. - * The width requirement may depend on the codec and in such - * cases mixer control is used to update custom values. A value - * of "N" here means, width is "N + 1" bit clock wide. - */ - i2s->fsync_width = value; - - regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL, - I2S_CTRL_FSYNC_WIDTH_MASK, - i2s->fsync_width << I2S_FSYNC_WIDTH_SHIFT); - - } else if (strstr(kcontrol->id.name, "Capture Stereo To Mono")) { - i2s->stereo_to_mono[I2S_TX_PATH] = value; - } else if (strstr(kcontrol->id.name, "Capture Mono To Stereo")) { - i2s->mono_to_stereo[I2S_TX_PATH] = value; - } else if (strstr(kcontrol->id.name, "Playback Stereo To Mono")) { - i2s->stereo_to_mono[I2S_RX_PATH] = value; - } else if (strstr(kcontrol->id.name, "Playback Mono To Stereo")) { - i2s->mono_to_stereo[I2S_RX_PATH] = value; - } else if (strstr(kcontrol->id.name, "Playback FIFO Threshold")) { - i2s->rx_fifo_th = value; - } else if (strstr(kcontrol->id.name, "BCLK Ratio")) { - i2s->bclk_ratio = value; - } + /* + * Frame sync width is used only for FSYNC modes and not + * applicable for LRCK modes. Reset value for this field is "0", + * which means the width is one bit clock wide. + * The width requirement may depend on the codec and in such + * cases mixer control is used to update custom values. A value + * of "N" here means, width is "N + 1" bit clock wide. + */ + regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL, + I2S_CTRL_FSYNC_WIDTH_MASK, + i2s->fsync_width << I2S_FSYNC_WIDTH_SHIFT); + + return 1; +} + +static int tegra210_i2s_cget_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + + ucontrol->value.enumerated.item[0] = i2s->stereo_to_mono[I2S_TX_PATH]; + + return 0; +} + +static int tegra210_i2s_cput_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == i2s->stereo_to_mono[I2S_TX_PATH]) + return 0; + + i2s->stereo_to_mono[I2S_TX_PATH] = value; + + return 1; +} + +static int tegra210_i2s_cget_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + + ucontrol->value.enumerated.item[0] = i2s->mono_to_stereo[I2S_TX_PATH]; + + return 0; +} + +static int tegra210_i2s_cput_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == i2s->mono_to_stereo[I2S_TX_PATH]) + return 0; + + i2s->mono_to_stereo[I2S_TX_PATH] = value; + + return 1; +} + +static int tegra210_i2s_pget_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + + ucontrol->value.enumerated.item[0] = i2s->stereo_to_mono[I2S_RX_PATH]; + + return 0; +} + +static int tegra210_i2s_pput_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == i2s->stereo_to_mono[I2S_RX_PATH]) + return 0; + + i2s->stereo_to_mono[I2S_RX_PATH] = value; + + return 1; +} + +static int tegra210_i2s_pget_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + + ucontrol->value.enumerated.item[0] = i2s->mono_to_stereo[I2S_RX_PATH]; + + return 0; +} + +static int tegra210_i2s_pput_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == i2s->mono_to_stereo[I2S_RX_PATH]) + return 0; + + i2s->mono_to_stereo[I2S_RX_PATH] = value; + + return 1; +} + +static int tegra210_i2s_pget_fifo_th(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + + ucontrol->value.integer.value[0] = i2s->rx_fifo_th; + + return 0; +} + +static int tegra210_i2s_pput_fifo_th(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + int value = ucontrol->value.integer.value[0]; + + if (value == i2s->rx_fifo_th) + return 0; + + i2s->rx_fifo_th = value; + + return 1; +} + +static int tegra210_i2s_get_bclk_ratio(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + + ucontrol->value.integer.value[0] = i2s->bclk_ratio; + + return 0; +} + +static int tegra210_i2s_put_bclk_ratio(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt); + int value = ucontrol->value.integer.value[0]; + + if (value == i2s->bclk_ratio) + return 0; + + i2s->bclk_ratio = value; + + return 1; +} + +static int tegra210_i2s_set_dai_bclk_ratio(struct snd_soc_dai *dai, + unsigned int ratio) +{ + struct tegra210_i2s *i2s = snd_soc_dai_get_drvdata(dai); + + i2s->bclk_ratio = ratio; return 0; } @@ -598,22 +748,28 @@ static const struct soc_enum tegra210_i2s_stereo_conv_enum = tegra210_i2s_stereo_conv_text); static const struct snd_kcontrol_new tegra210_i2s_controls[] = { - SOC_SINGLE_EXT("Loopback", 0, 0, 1, 0, tegra210_i2s_get_control, - tegra210_i2s_put_control), - SOC_SINGLE_EXT("FSYNC Width", 0, 0, 255, 0, tegra210_i2s_get_control, - tegra210_i2s_put_control), + SOC_SINGLE_EXT("Loopback", 0, 0, 1, 0, tegra210_i2s_get_loopback, + tegra210_i2s_put_loopback), + SOC_SINGLE_EXT("FSYNC Width", 0, 0, 255, 0, + tegra210_i2s_get_fsync_width, + tegra210_i2s_put_fsync_width), SOC_ENUM_EXT("Capture Stereo To Mono", tegra210_i2s_stereo_conv_enum, - tegra210_i2s_get_control, tegra210_i2s_put_control), + tegra210_i2s_cget_stereo_to_mono, + tegra210_i2s_cput_stereo_to_mono), SOC_ENUM_EXT("Capture Mono To Stereo", tegra210_i2s_mono_conv_enum, - tegra210_i2s_get_control, tegra210_i2s_put_control), + tegra210_i2s_cget_mono_to_stereo, + tegra210_i2s_cput_mono_to_stereo), SOC_ENUM_EXT("Playback Stereo To Mono", tegra210_i2s_stereo_conv_enum, - tegra210_i2s_get_control, tegra210_i2s_put_control), + tegra210_i2s_pget_mono_to_stereo, + tegra210_i2s_pput_mono_to_stereo), SOC_ENUM_EXT("Playback Mono To Stereo", tegra210_i2s_mono_conv_enum, - tegra210_i2s_get_control, tegra210_i2s_put_control), + tegra210_i2s_pget_stereo_to_mono, + tegra210_i2s_pput_stereo_to_mono), SOC_SINGLE_EXT("Playback FIFO Threshold", 0, 0, I2S_RX_FIFO_DEPTH - 1, - 0, tegra210_i2s_get_control, tegra210_i2s_put_control), - SOC_SINGLE_EXT("BCLK Ratio", 0, 0, INT_MAX, 0, tegra210_i2s_get_control, - tegra210_i2s_put_control), + 0, tegra210_i2s_pget_fifo_th, tegra210_i2s_pput_fifo_th), + SOC_SINGLE_EXT("BCLK Ratio", 0, 0, INT_MAX, 0, + tegra210_i2s_get_bclk_ratio, + tegra210_i2s_put_bclk_ratio), }; static const struct snd_soc_dapm_widget tegra210_i2s_widgets[] = { diff --git a/sound/soc/tegra/tegra210_mixer.c b/sound/soc/tegra/tegra210_mixer.c index 55e61776c565..51d375573cfa 100644 --- a/sound/soc/tegra/tegra210_mixer.c +++ b/sound/soc/tegra/tegra210_mixer.c @@ -192,24 +192,24 @@ static int tegra210_mixer_get_gain(struct snd_kcontrol *kcontrol, return 0; } -static int tegra210_mixer_put_gain(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) +static int tegra210_mixer_apply_gain(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol, + bool instant_gain) { struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value; struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); struct tegra210_mixer *mixer = snd_soc_component_get_drvdata(cmpnt); unsigned int reg = mc->reg, id; - bool instant_gain = false; int err; - if (strstr(kcontrol->id.name, "Instant Gain Volume")) - instant_gain = true; - /* Save gain value for specific MIXER input */ id = (reg - TEGRA210_MIXER_GAIN_CFG_RAM_ADDR_0) / TEGRA210_MIXER_GAIN_CFG_RAM_ADDR_STRIDE; + if (mixer->gain_value[id] == ucontrol->value.integer.value[0]) + return 0; + mixer->gain_value[id] = ucontrol->value.integer.value[0]; err = tegra210_mixer_configure_gain(cmpnt, id, instant_gain); @@ -221,6 +221,18 @@ static int tegra210_mixer_put_gain(struct snd_kcontrol *kcontrol, return 1; } +static int tegra210_mixer_put_gain(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + return tegra210_mixer_apply_gain(kcontrol, ucontrol, false); +} + +static int tegra210_mixer_put_instant_gain(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + return tegra210_mixer_apply_gain(kcontrol, ucontrol, true); +} + static int tegra210_mixer_set_audio_cif(struct tegra210_mixer *mixer, struct snd_pcm_hw_params *params, unsigned int reg, @@ -388,7 +400,7 @@ ADDER_CTRL_DECL(adder5, TEGRA210_MIXER_TX5_ADDER_CONFIG); SOC_SINGLE_EXT("RX" #id " Instant Gain Volume", \ MIXER_GAIN_CFG_RAM_ADDR((id) - 1), 0, \ 0x20000, 0, tegra210_mixer_get_gain, \ - tegra210_mixer_put_gain), + tegra210_mixer_put_instant_gain), /* Volume controls for all MIXER inputs */ static const struct snd_kcontrol_new tegra210_mixer_gain_ctls[] = { diff --git a/sound/soc/tegra/tegra210_mvc.c b/sound/soc/tegra/tegra210_mvc.c index 7b9c7006e419..85b155887ec2 100644 --- a/sound/soc/tegra/tegra210_mvc.c +++ b/sound/soc/tegra/tegra210_mvc.c @@ -136,7 +136,7 @@ static int tegra210_mvc_put_mute(struct snd_kcontrol *kcontrol, struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); struct tegra210_mvc *mvc = snd_soc_component_get_drvdata(cmpnt); unsigned int value; - u8 mute_mask; + u8 new_mask, old_mask; int err; pm_runtime_get_sync(cmpnt->dev); @@ -148,11 +148,19 @@ static int tegra210_mvc_put_mute(struct snd_kcontrol *kcontrol, if (err < 0) goto end; - mute_mask = ucontrol->value.integer.value[0]; + regmap_read(mvc->regmap, TEGRA210_MVC_CTRL, &value); + + old_mask = (value >> TEGRA210_MVC_MUTE_SHIFT) & TEGRA210_MUTE_MASK_EN; + new_mask = ucontrol->value.integer.value[0]; + + if (new_mask == old_mask) { + err = 0; + goto end; + } err = regmap_update_bits(mvc->regmap, mc->reg, TEGRA210_MVC_MUTE_MASK, - mute_mask << TEGRA210_MVC_MUTE_SHIFT); + new_mask << TEGRA210_MVC_MUTE_SHIFT); if (err < 0) goto end; @@ -195,7 +203,7 @@ static int tegra210_mvc_put_vol(struct snd_kcontrol *kcontrol, unsigned int reg = mc->reg; unsigned int value; u8 chan; - int err; + int err, old_volume; pm_runtime_get_sync(cmpnt->dev); @@ -207,10 +215,16 @@ static int tegra210_mvc_put_vol(struct snd_kcontrol *kcontrol, goto end; chan = (reg - TEGRA210_MVC_TARGET_VOL) / REG_SIZE; + old_volume = mvc->volume[chan]; tegra210_mvc_conv_vol(mvc, chan, ucontrol->value.integer.value[0]); + if (mvc->volume[chan] == old_volume) { + err = 0; + goto end; + } + /* Configure init volume same as target volume */ regmap_write(mvc->regmap, TEGRA210_MVC_REG_OFFSET(TEGRA210_MVC_INIT_VOL, chan), @@ -275,7 +289,7 @@ static int tegra210_mvc_get_curve_type(struct snd_kcontrol *kcontrol, struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); struct tegra210_mvc *mvc = snd_soc_component_get_drvdata(cmpnt); - ucontrol->value.integer.value[0] = mvc->curve_type; + ucontrol->value.enumerated.item[0] = mvc->curve_type; return 0; } @@ -285,7 +299,7 @@ static int tegra210_mvc_put_curve_type(struct snd_kcontrol *kcontrol, { struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); struct tegra210_mvc *mvc = snd_soc_component_get_drvdata(cmpnt); - int value; + unsigned int value; regmap_read(mvc->regmap, TEGRA210_MVC_ENABLE, &value); if (value & TEGRA210_MVC_EN) { @@ -294,10 +308,10 @@ static int tegra210_mvc_put_curve_type(struct snd_kcontrol *kcontrol, return -EINVAL; } - if (mvc->curve_type == ucontrol->value.integer.value[0]) + if (mvc->curve_type == ucontrol->value.enumerated.item[0]) return 0; - mvc->curve_type = ucontrol->value.integer.value[0]; + mvc->curve_type = ucontrol->value.enumerated.item[0]; tegra210_mvc_reset_vol_settings(mvc, cmpnt->dev); diff --git a/sound/soc/tegra/tegra210_sfc.c b/sound/soc/tegra/tegra210_sfc.c index dc477ee1b82c..7a2227ed3df6 100644 --- a/sound/soc/tegra/tegra210_sfc.c +++ b/sound/soc/tegra/tegra210_sfc.c @@ -3244,46 +3244,107 @@ static int tegra210_sfc_init(struct snd_soc_dapm_widget *w, return tegra210_sfc_write_coeff_ram(cmpnt); } -static int tegra210_sfc_get_control(struct snd_kcontrol *kcontrol, +static int tegra210_sfc_iget_stereo_to_mono(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt); - if (strstr(kcontrol->id.name, "Input Stereo To Mono")) - ucontrol->value.integer.value[0] = - sfc->stereo_to_mono[SFC_RX_PATH]; - else if (strstr(kcontrol->id.name, "Input Mono To Stereo")) - ucontrol->value.integer.value[0] = - sfc->mono_to_stereo[SFC_RX_PATH]; - else if (strstr(kcontrol->id.name, "Output Stereo To Mono")) - ucontrol->value.integer.value[0] = - sfc->stereo_to_mono[SFC_TX_PATH]; - else if (strstr(kcontrol->id.name, "Output Mono To Stereo")) - ucontrol->value.integer.value[0] = - sfc->mono_to_stereo[SFC_TX_PATH]; + ucontrol->value.enumerated.item[0] = sfc->stereo_to_mono[SFC_RX_PATH]; return 0; } -static int tegra210_sfc_put_control(struct snd_kcontrol *kcontrol, +static int tegra210_sfc_iput_stereo_to_mono(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt); - int value = ucontrol->value.integer.value[0]; - - if (strstr(kcontrol->id.name, "Input Stereo To Mono")) - sfc->stereo_to_mono[SFC_RX_PATH] = value; - else if (strstr(kcontrol->id.name, "Input Mono To Stereo")) - sfc->mono_to_stereo[SFC_RX_PATH] = value; - else if (strstr(kcontrol->id.name, "Output Stereo To Mono")) - sfc->stereo_to_mono[SFC_TX_PATH] = value; - else if (strstr(kcontrol->id.name, "Output Mono To Stereo")) - sfc->mono_to_stereo[SFC_TX_PATH] = value; - else + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == sfc->stereo_to_mono[SFC_RX_PATH]) + return 0; + + sfc->stereo_to_mono[SFC_RX_PATH] = value; + + return 1; +} + +static int tegra210_sfc_iget_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt); + + ucontrol->value.enumerated.item[0] = sfc->mono_to_stereo[SFC_RX_PATH]; + + return 0; +} + +static int tegra210_sfc_iput_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == sfc->mono_to_stereo[SFC_RX_PATH]) return 0; + sfc->mono_to_stereo[SFC_RX_PATH] = value; + + return 1; +} + +static int tegra210_sfc_oget_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt); + + ucontrol->value.enumerated.item[0] = sfc->stereo_to_mono[SFC_TX_PATH]; + + return 0; +} + +static int tegra210_sfc_oput_stereo_to_mono(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == sfc->stereo_to_mono[SFC_TX_PATH]) + return 0; + + sfc->stereo_to_mono[SFC_TX_PATH] = value; + + return 1; +} + +static int tegra210_sfc_oget_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt); + + ucontrol->value.enumerated.item[0] = sfc->mono_to_stereo[SFC_TX_PATH]; + + return 0; +} + +static int tegra210_sfc_oput_mono_to_stereo(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt); + unsigned int value = ucontrol->value.enumerated.item[0]; + + if (value == sfc->mono_to_stereo[SFC_TX_PATH]) + return 0; + + sfc->mono_to_stereo[SFC_TX_PATH] = value; + return 1; } @@ -3384,13 +3445,17 @@ static const struct soc_enum tegra210_sfc_mono_conv_enum = static const struct snd_kcontrol_new tegra210_sfc_controls[] = { SOC_ENUM_EXT("Input Stereo To Mono", tegra210_sfc_stereo_conv_enum, - tegra210_sfc_get_control, tegra210_sfc_put_control), + tegra210_sfc_iget_stereo_to_mono, + tegra210_sfc_iput_stereo_to_mono), SOC_ENUM_EXT("Input Mono To Stereo", tegra210_sfc_mono_conv_enum, - tegra210_sfc_get_control, tegra210_sfc_put_control), + tegra210_sfc_iget_mono_to_stereo, + tegra210_sfc_iput_mono_to_stereo), SOC_ENUM_EXT("Output Stereo To Mono", tegra210_sfc_stereo_conv_enum, - tegra210_sfc_get_control, tegra210_sfc_put_control), + tegra210_sfc_oget_stereo_to_mono, + tegra210_sfc_oput_stereo_to_mono), SOC_ENUM_EXT("Output Mono To Stereo", tegra210_sfc_mono_conv_enum, - tegra210_sfc_get_control, tegra210_sfc_put_control), + tegra210_sfc_oget_mono_to_stereo, + tegra210_sfc_oput_mono_to_stereo), }; static const struct snd_soc_component_driver tegra210_sfc_cmpnt = { diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index a7e54a08fb54..3e8df500cfbd 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -7,6 +7,7 @@ #include <assert.h> #include <linux/build_bug.h> #include <linux/compiler.h> +#include <linux/math.h> #include <endian.h> #include <byteswap.h> @@ -14,8 +15,6 @@ #define UINT_MAX (~0U) #endif -#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) - #define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1) #define __PERF_ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) @@ -52,15 +51,6 @@ _min1 < _min2 ? _min1 : _min2; }) #endif -#ifndef roundup -#define roundup(x, y) ( \ -{ \ - const typeof(y) __y = y; \ - (((x) + (__y - 1)) / __y) * __y; \ -} \ -) -#endif - #ifndef BUG_ON #ifdef NDEBUG #define BUG_ON(cond) do { if (cond) {} } while (0) @@ -104,16 +94,6 @@ int scnprintf_pad(char * buf, size_t size, const char * fmt, ...); #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) -/* - * This looks more complex than it should be. But we need to - * get the type for the ~ right in round_down (it needs to be - * as wide as the result!), and we want to evaluate the macro - * arguments just once each. - */ -#define __round_mask(x, y) ((__typeof__(x))((y)-1)) -#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) -#define round_down(x, y) ((x) & ~__round_mask(x, y)) - #define current_gfp_context(k) 0 #define synchronize_rcu() diff --git a/tools/include/linux/math.h b/tools/include/linux/math.h new file mode 100644 index 000000000000..4e7af99ec9eb --- /dev/null +++ b/tools/include/linux/math.h @@ -0,0 +1,25 @@ +#ifndef _TOOLS_MATH_H +#define _TOOLS_MATH_H + +/* + * This looks more complex than it should be. But we need to + * get the type for the ~ right in round_down (it needs to be + * as wide as the result!), and we want to evaluate the macro + * arguments just once each. + */ +#define __round_mask(x, y) ((__typeof__(x))((y)-1)) +#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +#define round_down(x, y) ((x) & ~__round_mask(x, y)) + +#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) + +#ifndef roundup +#define roundup(x, y) ( \ +{ \ + const typeof(y) __y = y; \ + (((x) + (__y - 1)) / __y) * __y; \ +} \ +) +#endif + +#endif diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 81a4c543ff7e..4b384c907027 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -375,6 +375,7 @@ static int read_symbols(struct elf *elf) return -1; } memset(sym, 0, sizeof(*sym)); + INIT_LIST_HEAD(&sym->pv_target); sym->alias = sym; sym->idx = i; diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index c90c7084e45a..bdf699f6552b 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -153,6 +153,10 @@ void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func) !strcmp(func->name, "_paravirt_ident_64")) return; + /* already added this function */ + if (!list_empty(&func->pv_target)) + return; + list_add(&func->pv_target, &f->pv_ops[idx].targets); f->pv_ops[idx].clean = false; } diff --git a/tools/testing/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h index 565fccdfe6e9..016cff473cfc 100644 --- a/tools/testing/radix-tree/linux/lockdep.h +++ b/tools/testing/radix-tree/linux/lockdep.h @@ -1,5 +1,8 @@ #ifndef _LINUX_LOCKDEP_H #define _LINUX_LOCKDEP_H + +#include <linux/spinlock.h> + struct lock_class_key { unsigned int a; }; diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index f75d4c433fc3..8c129961accf 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -31,10 +31,12 @@ /x86_64/svm_int_ctl_test /x86_64/sync_regs_test /x86_64/tsc_msrs_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_invalid_nested_guest_state /x86_64/vmx_preemption_timer_test /x86_64/vmx_set_nested_state_test /x86_64/vmx_tsc_adjust_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 758b5d0e352e..133d618fcad6 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -59,10 +59,12 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test +TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test +TEST_GEN_PROGS_x86_64 += x86_64/vmx_invalid_nested_guest_state TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 83e93a65db29..f5de7241005b 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -339,6 +339,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm); unsigned int vm_get_page_size(struct kvm_vm *vm); unsigned int vm_get_page_shift(struct kvm_vm *vm); +unsigned long vm_compute_max_gfn(struct kvm_vm *vm); uint64_t vm_get_max_gfn(struct kvm_vm *vm); int vm_get_fd(struct kvm_vm *vm); diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c index f968dfd4ee88..aed9dc3ca1e9 100644 --- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c +++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c @@ -12,6 +12,7 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/resource.h> #include "test_util.h" @@ -40,11 +41,40 @@ int main(int argc, char *argv[]) { int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID); int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); + /* + * Number of file descriptors reqired, KVM_CAP_MAX_VCPUS for vCPU fds + + * an arbitrary number for everything else. + */ + int nr_fds_wanted = kvm_max_vcpus + 100; + struct rlimit rl; pr_info("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id); pr_info("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus); /* + * Check that we're allowed to open nr_fds_wanted file descriptors and + * try raising the limits if needed. + */ + TEST_ASSERT(!getrlimit(RLIMIT_NOFILE, &rl), "getrlimit() failed!"); + + if (rl.rlim_cur < nr_fds_wanted) { + rl.rlim_cur = nr_fds_wanted; + if (rl.rlim_max < nr_fds_wanted) { + int old_rlim_max = rl.rlim_max; + rl.rlim_max = nr_fds_wanted; + + int r = setrlimit(RLIMIT_NOFILE, &rl); + if (r < 0) { + printf("RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n", + old_rlim_max, nr_fds_wanted); + exit(KSFT_SKIP); + } + } else { + TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!"); + } + } + + /* * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID. * Userspace is supposed to use KVM_CAP_MAX_VCPUS as the maximum ID * in this case. diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 3836322add00..ba1fdc3dcf4a 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) #ifdef __s390x__ alignment = max(0x100000, alignment); #endif - guest_test_phys_mem = align_down(guest_test_virt_mem, alignment); + guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); /* Set up the shared data structure test_args */ test_args.vm = vm; diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index f73516cb91f3..ecc53d108ad8 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -324,7 +324,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) (1ULL << (vm->va_bits - 1)) >> vm->page_shift); /* Limit physical addresses to PA-bits. */ - vm->max_gfn = ((1ULL << vm->pa_bits) >> vm->page_shift) - 1; + vm->max_gfn = vm_compute_max_gfn(vm); /* Allocate and setup memory for guest. */ vm->vpages_mapped = sparsebit_alloc(); @@ -2422,6 +2422,11 @@ unsigned int vm_get_page_shift(struct kvm_vm *vm) return vm->page_shift; } +unsigned long __attribute__((weak)) vm_compute_max_gfn(struct kvm_vm *vm) +{ + return ((1ULL << vm->pa_bits) >> vm->page_shift) - 1; +} + uint64_t vm_get_max_gfn(struct kvm_vm *vm) { return vm->max_gfn; diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 82c39db91369..eef7b34756d5 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1431,3 +1431,71 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui return cpuid; } + +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65 + +static inline unsigned x86_family(unsigned int eax) +{ + unsigned int x86; + + x86 = (eax >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (eax >> 20) & 0xff; + + return x86; +} + +unsigned long vm_compute_max_gfn(struct kvm_vm *vm) +{ + const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ + unsigned long ht_gfn, max_gfn, max_pfn; + uint32_t eax, ebx, ecx, edx, max_ext_leaf; + + max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; + + /* Avoid reserved HyperTransport region on AMD processors. */ + eax = ecx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + if (ebx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx || + ecx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx || + edx != X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) + return max_gfn; + + /* On parts with <40 physical address bits, the area is fully hidden */ + if (vm->pa_bits < 40) + return max_gfn; + + /* Before family 17h, the HyperTransport area is just below 1T. */ + ht_gfn = (1 << 28) - num_ht_pages; + eax = 1; + cpuid(&eax, &ebx, &ecx, &edx); + if (x86_family(eax) < 0x17) + goto done; + + /* + * Otherwise it's at the top of the physical address space, possibly + * reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX. Use + * the old conservative value if MAXPHYADDR is not enumerated. + */ + eax = 0x80000000; + cpuid(&eax, &ebx, &ecx, &edx); + max_ext_leaf = eax; + if (max_ext_leaf < 0x80000008) + goto done; + + eax = 0x80000008; + cpuid(&eax, &ebx, &ecx, &edx); + max_pfn = (1ULL << ((eax & 0xff) - vm->page_shift)) - 1; + if (max_ext_leaf >= 0x8000001f) { + eax = 0x8000001f; + cpuid(&eax, &ebx, &ecx, &edx); + max_pfn >>= (ebx >> 6) & 0x3f; + } + + ht_gfn = max_pfn - num_ht_pages; +done: + return min(max_gfn, ht_gfn - 1); +} diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 91d88aaa9899..672915ce73d8 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -165,10 +165,10 @@ static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid, vcpu_set_cpuid(vm, VCPU_ID, cpuid); } -static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, - struct kvm_cpuid2 *best) +static void guest_test_msrs_access(void) { struct kvm_run *run; + struct kvm_vm *vm; struct ucall uc; int stage = 0, r; struct kvm_cpuid_entry2 feat = { @@ -180,11 +180,34 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, struct kvm_cpuid_entry2 dbg = { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }; - struct kvm_enable_cap cap = {0}; - - run = vcpu_state(vm, VCPU_ID); + struct kvm_cpuid2 *best; + vm_vaddr_t msr_gva; + struct kvm_enable_cap cap = { + .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, + .args = {1} + }; + struct msr_data *msr; while (true) { + vm = vm_create_default(VCPU_ID, 0, guest_msr); + + msr_gva = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); + msr = addr_gva2hva(vm, msr_gva); + + vcpu_args_set(vm, VCPU_ID, 1, msr_gva); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + + run = vcpu_state(vm, VCPU_ID); + switch (stage) { case 0: /* @@ -315,6 +338,7 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, * capability enabled and guest visible CPUID bit unset. */ cap.cap = KVM_CAP_HYPERV_SYNIC2; + cap.args[0] = 0; vcpu_enable_cap(vm, VCPU_ID, &cap); break; case 22: @@ -461,9 +485,9 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == stage, - "Unexpected stage: %ld (%d expected)\n", - uc.args[1], stage); + TEST_ASSERT(uc.args[1] == 0, + "Unexpected stage: %ld (0 expected)\n", + uc.args[1]); break; case UCALL_ABORT: TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], @@ -474,13 +498,14 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, } stage++; + kvm_vm_free(vm); } } -static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall, - void *input, void *output, struct kvm_cpuid2 *best) +static void guest_test_hcalls_access(void) { struct kvm_run *run; + struct kvm_vm *vm; struct ucall uc; int stage = 0, r; struct kvm_cpuid_entry2 feat = { @@ -493,10 +518,38 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall struct kvm_cpuid_entry2 dbg = { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }; - - run = vcpu_state(vm, VCPU_ID); + struct kvm_enable_cap cap = { + .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, + .args = {1} + }; + vm_vaddr_t hcall_page, hcall_params; + struct hcall_data *hcall; + struct kvm_cpuid2 *best; while (true) { + vm = vm_create_default(VCPU_ID, 0, guest_hcall); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + + /* Hypercall input/output */ + hcall_page = vm_vaddr_alloc_pages(vm, 2); + hcall = addr_gva2hva(vm, hcall_page); + memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); + + hcall_params = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); + + vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + run = vcpu_state(vm, VCPU_ID); + switch (stage) { case 0: hcall->control = 0xdeadbeef; @@ -606,9 +659,9 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == stage, - "Unexpected stage: %ld (%d expected)\n", - uc.args[1], stage); + TEST_ASSERT(uc.args[1] == 0, + "Unexpected stage: %ld (0 expected)\n", + uc.args[1]); break; case UCALL_ABORT: TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], @@ -619,66 +672,15 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall } stage++; + kvm_vm_free(vm); } } int main(void) { - struct kvm_cpuid2 *best; - struct kvm_vm *vm; - vm_vaddr_t msr_gva, hcall_page, hcall_params; - struct kvm_enable_cap cap = { - .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, - .args = {1} - }; - - /* Test MSRs */ - vm = vm_create_default(VCPU_ID, 0, guest_msr); - - msr_gva = vm_vaddr_alloc_page(vm); - memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); - vcpu_args_set(vm, VCPU_ID, 1, msr_gva); - vcpu_enable_cap(vm, VCPU_ID, &cap); - - vcpu_set_hv_cpuid(vm, VCPU_ID); - - best = kvm_get_supported_hv_cpuid(); - - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); - pr_info("Testing access to Hyper-V specific MSRs\n"); - guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva), - best); - kvm_vm_free(vm); - - /* Test hypercalls */ - vm = vm_create_default(VCPU_ID, 0, guest_hcall); - - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); - - /* Hypercall input/output */ - hcall_page = vm_vaddr_alloc_pages(vm, 2); - memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); - - hcall_params = vm_vaddr_alloc_page(vm); - memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); - - vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); - vcpu_enable_cap(vm, VCPU_ID, &cap); - - vcpu_set_hv_cpuid(vm, VCPU_ID); - - best = kvm_get_supported_hv_cpuid(); + guest_test_msrs_access(); pr_info("Testing access to Hyper-V hypercalls\n"); - guest_test_hcalls_access(vm, addr_gva2hva(vm, hcall_params), - addr_gva2hva(vm, hcall_page), - addr_gva2hva(vm, hcall_page) + getpagesize(), - best); - - kvm_vm_free(vm); + guest_test_hcalls_access(); } diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c index 5ba325cd64bf..29b18d565cf4 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c @@ -54,12 +54,15 @@ static struct kvm_vm *sev_vm_create(bool es) return vm; } -static struct kvm_vm *__vm_create(void) +static struct kvm_vm *aux_vm_create(bool with_vcpus) { struct kvm_vm *vm; int i; vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + if (!with_vcpus) + return vm; + for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) vm_vcpu_add(vm, i); @@ -89,11 +92,11 @@ static void test_sev_migrate_from(bool es) { struct kvm_vm *src_vm; struct kvm_vm *dst_vms[NR_MIGRATE_TEST_VMS]; - int i; + int i, ret; src_vm = sev_vm_create(es); for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i) - dst_vms[i] = __vm_create(); + dst_vms[i] = aux_vm_create(true); /* Initial migration from the src to the first dst. */ sev_migrate_from(dst_vms[0]->fd, src_vm->fd); @@ -102,7 +105,10 @@ static void test_sev_migrate_from(bool es) sev_migrate_from(dst_vms[i]->fd, dst_vms[i - 1]->fd); /* Migrate the guest back to the original VM. */ - sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd); + ret = __sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd); + TEST_ASSERT(ret == -1 && errno == EIO, + "VM that was migrated from should be dead. ret %d, errno: %d\n", ret, + errno); kvm_vm_free(src_vm); for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i) @@ -146,6 +152,8 @@ static void test_sev_migrate_locking(void) for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) pthread_join(pt[i], NULL); + for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) + kvm_vm_free(input[i].vm); } static void test_sev_migrate_parameters(void) @@ -157,12 +165,11 @@ static void test_sev_migrate_parameters(void) sev_vm = sev_vm_create(/* es= */ false); sev_es_vm = sev_vm_create(/* es= */ true); vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); - vm_no_sev = __vm_create(); + vm_no_sev = aux_vm_create(true); sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL); vm_vcpu_add(sev_es_vm_no_vmsa, 1); - ret = __sev_migrate_from(sev_vm->fd, sev_es_vm->fd); TEST_ASSERT( ret == -1 && errno == EINVAL, @@ -191,13 +198,151 @@ static void test_sev_migrate_parameters(void) TEST_ASSERT(ret == -1 && errno == EINVAL, "Migrations require SEV enabled. ret %d, errno: %d\n", ret, errno); + + kvm_vm_free(sev_vm); + kvm_vm_free(sev_es_vm); + kvm_vm_free(sev_es_vm_no_vmsa); + kvm_vm_free(vm_no_vcpu); + kvm_vm_free(vm_no_sev); +} + +static int __sev_mirror_create(int dst_fd, int src_fd) +{ + struct kvm_enable_cap cap = { + .cap = KVM_CAP_VM_COPY_ENC_CONTEXT_FROM, + .args = { src_fd } + }; + + return ioctl(dst_fd, KVM_ENABLE_CAP, &cap); +} + + +static void sev_mirror_create(int dst_fd, int src_fd) +{ + int ret; + + ret = __sev_mirror_create(dst_fd, src_fd); + TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno); +} + +static void test_sev_mirror(bool es) +{ + struct kvm_vm *src_vm, *dst_vm; + struct kvm_sev_launch_start start = { + .policy = es ? SEV_POLICY_ES : 0 + }; + int i; + + src_vm = sev_vm_create(es); + dst_vm = aux_vm_create(false); + + sev_mirror_create(dst_vm->fd, src_vm->fd); + + /* Check that we can complete creation of the mirror VM. */ + for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) + vm_vcpu_add(dst_vm, i); + sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_START, &start); + if (es) + sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + + kvm_vm_free(src_vm); + kvm_vm_free(dst_vm); +} + +static void test_sev_mirror_parameters(void) +{ + struct kvm_vm *sev_vm, *sev_es_vm, *vm_no_vcpu, *vm_with_vcpu; + int ret; + + sev_vm = sev_vm_create(/* es= */ false); + sev_es_vm = sev_vm_create(/* es= */ true); + vm_with_vcpu = aux_vm_create(true); + vm_no_vcpu = aux_vm_create(false); + + ret = __sev_mirror_create(sev_vm->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able copy context to self. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_mirror_create(sev_vm->fd, sev_es_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_mirror_create(sev_es_vm->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Copy context requires SEV enabled. ret %d, errno: %d\n", ret, + errno); + + ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n", + ret, errno); + + kvm_vm_free(sev_vm); + kvm_vm_free(sev_es_vm); + kvm_vm_free(vm_with_vcpu); + kvm_vm_free(vm_no_vcpu); +} + +static void test_sev_move_copy(void) +{ + struct kvm_vm *dst_vm, *sev_vm, *mirror_vm, *dst_mirror_vm; + int ret; + + sev_vm = sev_vm_create(/* es= */ false); + dst_vm = aux_vm_create(true); + mirror_vm = aux_vm_create(false); + dst_mirror_vm = aux_vm_create(false); + + sev_mirror_create(mirror_vm->fd, sev_vm->fd); + ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); + TEST_ASSERT(ret == -1 && errno == EBUSY, + "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, + errno); + + /* The mirror itself can be migrated. */ + sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd); + ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); + TEST_ASSERT(ret == -1 && errno == EBUSY, + "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, + errno); + + /* + * mirror_vm is not a mirror anymore, dst_mirror_vm is. Thus, + * the owner can be copied as soon as dst_mirror_vm is gone. + */ + kvm_vm_free(dst_mirror_vm); + sev_migrate_from(dst_vm->fd, sev_vm->fd); + + kvm_vm_free(mirror_vm); + kvm_vm_free(dst_vm); + kvm_vm_free(sev_vm); } int main(int argc, char *argv[]) { - test_sev_migrate_from(/* es= */ false); - test_sev_migrate_from(/* es= */ true); - test_sev_migrate_locking(); - test_sev_migrate_parameters(); + if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) { + test_sev_migrate_from(/* es= */ false); + test_sev_migrate_from(/* es= */ true); + test_sev_migrate_locking(); + test_sev_migrate_parameters(); + if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) + test_sev_move_copy(); + } + if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { + test_sev_mirror(/* es= */ false); + test_sev_mirror(/* es= */ true); + test_sev_mirror_parameters(); + } return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c index df04f56ce859..30a81038df46 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -75,7 +75,7 @@ static void l1_guest_code(struct svm_test_data *svm) vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; /* No intercepts for real and virtual interrupts */ - vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR); + vmcb->control.intercept &= ~(BIT(INTERCEPT_INTR) | BIT(INTERCEPT_VINTR)); /* Make a virtual interrupt VINTR_IRQ_NUMBER pending */ vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT); diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c new file mode 100644 index 000000000000..e4bef2e05686 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" + +#define VCPU_ID 1 + +static void guest_ins_port80(uint8_t *buffer, unsigned int count) +{ + unsigned long end; + + if (count == 2) + end = (unsigned long)buffer + 1; + else + end = (unsigned long)buffer + 8192; + + asm volatile("cld; rep; insb" : "+D"(buffer), "+c"(count) : "d"(0x80) : "memory"); + GUEST_ASSERT_1(count == 0, count); + GUEST_ASSERT_2((unsigned long)buffer == end, buffer, end); +} + +static void guest_code(void) +{ + uint8_t buffer[8192]; + int i; + + /* + * Special case tests. main() will adjust RCX 2 => 1 and 3 => 8192 to + * test that KVM doesn't explode when userspace modifies the "count" on + * a userspace I/O exit. KVM isn't required to play nice with the I/O + * itself as KVM doesn't support manipulating the count, it just needs + * to not explode or overflow a buffer. + */ + guest_ins_port80(buffer, 2); + guest_ins_port80(buffer, 3); + + /* Verify KVM fills the buffer correctly when not stuffing RCX. */ + memset(buffer, 0, sizeof(buffer)); + guest_ins_port80(buffer, 8192); + for (i = 0; i < 8192; i++) + GUEST_ASSERT_2(buffer[i] == 0xaa, i, buffer[i]); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct kvm_regs regs; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + int rc; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + run = vcpu_state(vm, VCPU_ID); + + memset(®s, 0, sizeof(regs)); + + while (1) { + rc = _vcpu_run(vm, VCPU_ID); + + TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + if (get_ucall(vm, VCPU_ID, &uc)) + break; + + TEST_ASSERT(run->io.port == 0x80, + "Expected I/O at port 0x80, got port 0x%x\n", run->io.port); + + /* + * Modify the rep string count in RCX: 2 => 1 and 3 => 8192. + * Note, this abuses KVM's batching of rep string I/O to avoid + * getting stuck in an infinite loop. That behavior isn't in + * scope from a testing perspective as it's not ABI in any way, + * i.e. it really is abusing internal KVM knowledge. + */ + vcpu_regs_get(vm, VCPU_ID, ®s); + if (regs.rcx == 2) + regs.rcx = 1; + if (regs.rcx == 3) + regs.rcx = 8192; + memset((void *)run + run->io.data_offset, 0xaa, 4096); + vcpu_regs_set(vm, VCPU_ID, ®s); + } + + switch (uc.cmd) { + case UCALL_DONE: + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld : argN+1 = 0x%lx, argN+2 = 0x%lx", + (const char *)uc.args[0], __FILE__, uc.args[1], + uc.args[2], uc.args[3]); + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c new file mode 100644 index 000000000000..489fbed4ca6f --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#include <string.h> +#include <sys/ioctl.h> + +#include "kselftest.h" + +#define VCPU_ID 0 +#define ARBITRARY_IO_PORT 0x2000 + +static struct kvm_vm *vm; + +static void l2_guest_code(void) +{ + /* + * Generate an exit to L0 userspace, i.e. main(), via I/O to an + * arbitrary port. + */ + asm volatile("inb %%dx, %%al" + : : [port] "d" (ARBITRARY_IO_PORT) : "rax"); +} + +static void l1_guest_code(struct vmx_pages *vmx_pages) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); + + /* Prepare the VMCS for L2 execution. */ + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* + * L2 must be run without unrestricted guest, verify that the selftests + * library hasn't enabled it. Because KVM selftests jump directly to + * 64-bit mode, unrestricted guest support isn't required. + */ + GUEST_ASSERT(!(vmreadz(CPU_BASED_VM_EXEC_CONTROL) & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) || + !(vmreadz(SECONDARY_VM_EXEC_CONTROL) & SECONDARY_EXEC_UNRESTRICTED_GUEST)); + + GUEST_ASSERT(!vmlaunch()); + + /* L2 should triple fault after main() stuffs invalid guest state. */ + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_TRIPLE_FAULT); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t vmx_pages_gva; + struct kvm_sregs sregs; + struct kvm_run *run; + struct ucall uc; + + nested_vmx_check_supported(); + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + + /* Allocate VMX pages and shared descriptors (vmx_pages). */ + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + + vcpu_run(vm, VCPU_ID); + + run = vcpu_state(vm, VCPU_ID); + + /* + * The first exit to L0 userspace should be an I/O access from L2. + * Running L1 should launch L2 without triggering an exit to userspace. + */ + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Expected KVM_EXIT_IO, got: %u (%s)\n", + run->exit_reason, exit_reason_str(run->exit_reason)); + + TEST_ASSERT(run->io.port == ARBITRARY_IO_PORT, + "Expected IN from port %d from L2, got port %d", + ARBITRARY_IO_PORT, run->io.port); + + /* + * Stuff invalid guest state for L2 by making TR unusuable. The next + * KVM_RUN should induce a TRIPLE_FAULT in L2 as KVM doesn't support + * emulating invalid guest state for L2. + */ + memset(&sregs, 0, sizeof(sregs)); + vcpu_sregs_get(vm, VCPU_ID, &sregs); + sregs.tr.unusable = 1; + vcpu_sregs_set(vm, VCPU_ID, &sregs); + + vcpu_run(vm, VCPU_ID); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_DONE: + break; + case UCALL_ABORT: + TEST_FAIL("%s", (const char *)uc.args[0]); + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c index 23051d84b907..2454a1f2ca0c 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c @@ -110,22 +110,5 @@ int main(int argc, char *argv[]) ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - /* testcase 4, set capabilities when we don't have PDCM bit */ - entry_1_0->ecx &= ~X86_FEATURE_PDCM; - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); - TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - - /* testcase 5, set capabilities when we don't have PMU version bits */ - entry_1_0->ecx |= X86_FEATURE_PDCM; - eax.split.version_id = 0; - entry_1_0->ecx = eax.full; - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); - TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - - vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, 0); - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), 0); - kvm_vm_free(vm); } diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 3313566ce906..7f5b265fcb90 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -4002,8 +4002,8 @@ EOF ################################################################################ # main -TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_addr_bind ipv4_runtime ipv4_netfilter" -TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_addr_bind ipv6_runtime ipv6_netfilter" +TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_bind ipv4_runtime ipv4_netfilter" +TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_bind ipv6_runtime ipv6_netfilter" TESTS_OTHER="use_cases" PAUSE_ON_FAIL=no diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index ebc4ee0fe179..8a9461aa0878 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -276,7 +276,11 @@ n0 ping -W 1 -c 1 192.168.241.2 n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7 ip2 link del wg0 ip2 link del wg1 -! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel +read _ _ tx_bytes_before < <(n0 wg show wg1 transfer) +! n0 ping -W 1 -c 10 -f 192.168.241.2 || false +sleep 1 +read _ _ tx_bytes_after < <(n0 wg show wg1 transfer) +(( tx_bytes_after - tx_bytes_before < 70000 )) ip0 link del wg1 ip1 link del wg0 @@ -609,6 +613,28 @@ ip0 link set wg0 up kill $ncat_pid ip0 link del wg0 +# Ensure that dst_cache references don't outlive netns lifetime +ip1 link add dev wg0 type wireguard +ip2 link add dev wg0 type wireguard +configure_peers +ip1 link add veth1 type veth peer name veth2 +ip1 link set veth2 netns $netns2 +ip1 addr add fd00:aa::1/64 dev veth1 +ip2 addr add fd00:aa::2/64 dev veth2 +ip1 link set veth1 up +ip2 link set veth2 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +ip1 -6 route add default dev veth1 via fd00:aa::2 +ip2 -6 route add default dev veth2 via fd00:aa::1 +n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2 +n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1 +n1 ping6 -c 1 fd00::2 +pp ip netns delete $netns1 +pp ip netns delete $netns2 +pp ip netns add $netns1 +pp ip netns add $netns2 + # Ensure there aren't circular reference loops ip1 link add wg1 type wireguard ip2 link add wg2 type wireguard @@ -627,7 +653,7 @@ while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do done < /dev/kmsg alldeleted=1 for object in "${!objects[@]}"; do - if [[ ${objects["$object"]} != *createddestroyed ]]; then + if [[ ${objects["$object"]} != *createddestroyed && ${objects["$object"]} != *createdcreateddestroyeddestroyed ]]; then echo "Error: $object: merely ${objects["$object"]}" >&3 alldeleted=0 fi diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index fe07d97df9fa..2b321b8a96cf 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -47,7 +47,7 @@ CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_TRACE_IRQFLAGS=y CONFIG_DEBUG_BUGVERBOSE=y CONFIG_DEBUG_LIST=y -CONFIG_DEBUG_PI_LIST=y +CONFIG_DEBUG_PLIST=y CONFIG_PROVE_RCU=y CONFIG_SPARSE_RCU_POINTER=y CONFIG_RCU_CPU_STALL_TIMEOUT=21 diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index 74db83a0aedd..a9b5a520a1d2 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -66,6 +66,7 @@ CONFIG_PROC_SYSCTL=y CONFIG_SYSFS=y CONFIG_TMPFS=y CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15 +CONFIG_LOG_BUF_SHIFT=18 CONFIG_PRINTK_TIME=y CONFIG_BLK_DEV_INITRD=y CONFIG_LEGACY_VSYSCALL_NONE=y diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 62b39149b8c8..97cf5413ac25 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -13,6 +13,9 @@ config HAVE_KVM_IRQFD config HAVE_KVM_IRQ_ROUTING bool +config HAVE_KVM_DIRTY_RING + bool + config HAVE_KVM_EVENTFD bool select EVENTFD diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm new file mode 100644 index 000000000000..ffdcad3cc97a --- /dev/null +++ b/virt/kvm/Makefile.kvm @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for Kernel-based Virtual Machine module +# + +KVM ?= ../../../virt/kvm + +kvm-y := $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/binary_stats.o +kvm-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o +kvm-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o +kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o +kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o +kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index dd777688d14a..9bfe1d6f6529 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -85,7 +85,7 @@ static void async_pf_execute(struct work_struct *work) trace_kvm_async_pf_completed(addr, cr2_or_gpa); - rcuwait_wake_up(&vcpu->wait); + __kvm_vcpu_wake_up(vcpu); mmput(mm); kvm_put_kvm(vcpu->kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9646bb9112c1..b0f7e6eb00ff 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -305,8 +305,9 @@ bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, { struct kvm_vcpu *vcpu; struct cpumask *cpus; + unsigned long i; bool called; - int i, me; + int me; me = get_cpu(); @@ -421,7 +422,9 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; +#ifndef __KVM_HAVE_ARCH_WQP rcuwait_init(&vcpu->wait); +#endif kvm_async_pf_vcpu_init(vcpu); vcpu->pre_pcpu = -1; @@ -432,10 +435,10 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->preempted = false; vcpu->ready = false; preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); - vcpu->last_used_slot = 0; + vcpu->last_used_slot = NULL; } -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) +static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { kvm_dirty_ring_free(&vcpu->dirty_ring); kvm_arch_vcpu_destroy(vcpu); @@ -450,7 +453,20 @@ void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)vcpu->run); kmem_cache_free(kvm_vcpu_cache, vcpu); } -EXPORT_SYMBOL_GPL(kvm_vcpu_destroy); + +void kvm_destroy_vcpus(struct kvm *kvm) +{ + unsigned long i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_vcpu_destroy(vcpu); + xa_erase(&kvm->vcpu_array, i); + } + + atomic_set(&kvm->online_vcpus, 0); +} +EXPORT_SYMBOL_GPL(kvm_destroy_vcpus); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) @@ -498,6 +514,12 @@ static void kvm_null_fn(void) } #define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn) +/* Iterate over each memslot intersecting [start, last] (inclusive) range */ +#define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \ + for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \ + node; \ + node = interval_tree_iter_next(node, start, last)) \ + static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, const struct kvm_hva_range *range) { @@ -507,6 +529,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, struct kvm_memslots *slots; int i, idx; + if (WARN_ON_ONCE(range->end <= range->start)) + return 0; + /* A null handler is allowed if and only if on_lock() is provided. */ if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) && IS_KVM_NULL_FN(range->handler))) @@ -515,15 +540,17 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, idx = srcu_read_lock(&kvm->srcu); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + struct interval_tree_node *node; + slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(slot, slots) { + kvm_for_each_memslot_in_hva_range(node, slots, + range->start, range->end - 1) { unsigned long hva_start, hva_end; + slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]); hva_start = max(range->start, slot->userspace_addr); hva_end = min(range->end, slot->userspace_addr + (slot->npages << PAGE_SHIFT)); - if (hva_start >= hva_end) - continue; /* * To optimize for the likely case where the address @@ -851,21 +878,6 @@ static void kvm_destroy_pm_notifier(struct kvm *kvm) } #endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ -static struct kvm_memslots *kvm_alloc_memslots(void) -{ - int i; - struct kvm_memslots *slots; - - slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT); - if (!slots) - return NULL; - - for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) - slots->id_to_index[i] = -1; - - return slots; -} - static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) { if (!memslot->dirty_bitmap) @@ -875,27 +887,33 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) memslot->dirty_bitmap = NULL; } +/* This does not remove the slot from struct kvm_memslots data structures */ static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { kvm_destroy_dirty_bitmap(slot); kvm_arch_free_memslot(kvm, slot); - slot->flags = 0; - slot->npages = 0; + kfree(slot); } static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) { + struct hlist_node *idnode; struct kvm_memory_slot *memslot; + int bkt; - if (!slots) + /* + * The same memslot objects live in both active and inactive sets, + * arbitrarily free using index '1' so the second invocation of this + * function isn't operating over a structure with dangling pointers + * (even though this function isn't actually touching them). + */ + if (!slots->node_idx) return; - kvm_for_each_memslot(memslot, slots) + hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1]) kvm_free_memslot(kvm, memslot); - - kvfree(slots); } static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) @@ -1034,8 +1052,9 @@ int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) static struct kvm *kvm_create_vm(unsigned long type) { struct kvm *kvm = kvm_arch_alloc_vm(); + struct kvm_memslots *slots; int r = -ENOMEM; - int i; + int i, j; if (!kvm) return ERR_PTR(-ENOMEM); @@ -1050,6 +1069,7 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_init(&kvm->slots_arch_lock); spin_lock_init(&kvm->mn_invalidate_lock); rcuwait_init(&kvm->mn_memslots_update_rcuwait); + xa_init(&kvm->vcpu_array); INIT_LIST_HEAD(&kvm->devices); @@ -1062,13 +1082,20 @@ static struct kvm *kvm_create_vm(unsigned long type) refcount_set(&kvm->users_count, 1); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_memslots *slots = kvm_alloc_memslots(); + for (j = 0; j < 2; j++) { + slots = &kvm->__memslots[i][j]; - if (!slots) - goto out_err_no_arch_destroy_vm; - /* Generations must be different for each address space. */ - slots->generation = i; - rcu_assign_pointer(kvm->memslots[i], slots); + atomic_long_set(&slots->last_used_slot, (unsigned long)NULL); + slots->hva_tree = RB_ROOT_CACHED; + slots->gfn_tree = RB_ROOT; + hash_init(slots->id_hash); + slots->node_idx = j; + + /* Generations must be different for each address space. */ + slots->generation = i; + } + + rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]); } for (i = 0; i < KVM_NR_BUSES; i++) { @@ -1122,8 +1149,6 @@ out_err_no_arch_destroy_vm: WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm_get_bus(kvm, i)); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, __kvm_memslots(kvm, i)); cleanup_srcu_struct(&kvm->irq_srcu); out_err_no_irq_srcu: cleanup_srcu_struct(&kvm->srcu); @@ -1188,8 +1213,10 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, __kvm_memslots(kvm, i)); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + kvm_free_memslots(kvm, &kvm->__memslots[i][0]); + kvm_free_memslots(kvm, &kvm->__memslots[i][1]); + } cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); @@ -1259,165 +1286,136 @@ static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) return 0; } -/* - * Delete a memslot by decrementing the number of used slots and shifting all - * other entries in the array forward one spot. - */ -static inline void kvm_memslot_delete(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot) +static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id) { - struct kvm_memory_slot *mslots = slots->memslots; - int i; - - if (WARN_ON(slots->id_to_index[memslot->id] == -1)) - return; - - slots->used_slots--; + struct kvm_memslots *active = __kvm_memslots(kvm, as_id); + int node_idx_inactive = active->node_idx ^ 1; - if (atomic_read(&slots->last_used_slot) >= slots->used_slots) - atomic_set(&slots->last_used_slot, 0); - - for (i = slots->id_to_index[memslot->id]; i < slots->used_slots; i++) { - mslots[i] = mslots[i + 1]; - slots->id_to_index[mslots[i].id] = i; - } - mslots[i] = *memslot; - slots->id_to_index[memslot->id] = -1; + return &kvm->__memslots[as_id][node_idx_inactive]; } /* - * "Insert" a new memslot by incrementing the number of used slots. Returns - * the new slot's initial index into the memslots array. + * Helper to get the address space ID when one of memslot pointers may be NULL. + * This also serves as a sanity that at least one of the pointers is non-NULL, + * and that their address space IDs don't diverge. */ -static inline int kvm_memslot_insert_back(struct kvm_memslots *slots) +static int kvm_memslots_get_as_id(struct kvm_memory_slot *a, + struct kvm_memory_slot *b) { - return slots->used_slots++; -} + if (WARN_ON_ONCE(!a && !b)) + return 0; -/* - * Move a changed memslot backwards in the array by shifting existing slots - * with a higher GFN toward the front of the array. Note, the changed memslot - * itself is not preserved in the array, i.e. not swapped at this time, only - * its new index into the array is tracked. Returns the changed memslot's - * current index into the memslots array. - */ -static inline int kvm_memslot_move_backward(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot) -{ - struct kvm_memory_slot *mslots = slots->memslots; - int i; + if (!a) + return b->as_id; + if (!b) + return a->as_id; - if (WARN_ON_ONCE(slots->id_to_index[memslot->id] == -1) || - WARN_ON_ONCE(!slots->used_slots)) - return -1; + WARN_ON_ONCE(a->as_id != b->as_id); + return a->as_id; +} - /* - * Move the target memslot backward in the array by shifting existing - * memslots with a higher GFN (than the target memslot) towards the - * front of the array. - */ - for (i = slots->id_to_index[memslot->id]; i < slots->used_slots - 1; i++) { - if (memslot->base_gfn > mslots[i + 1].base_gfn) - break; +static void kvm_insert_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *slot) +{ + struct rb_root *gfn_tree = &slots->gfn_tree; + struct rb_node **node, *parent; + int idx = slots->node_idx; - WARN_ON_ONCE(memslot->base_gfn == mslots[i + 1].base_gfn); + parent = NULL; + for (node = &gfn_tree->rb_node; *node; ) { + struct kvm_memory_slot *tmp; - /* Shift the next memslot forward one and update its index. */ - mslots[i] = mslots[i + 1]; - slots->id_to_index[mslots[i].id] = i; + tmp = container_of(*node, struct kvm_memory_slot, gfn_node[idx]); + parent = *node; + if (slot->base_gfn < tmp->base_gfn) + node = &(*node)->rb_left; + else if (slot->base_gfn > tmp->base_gfn) + node = &(*node)->rb_right; + else + BUG(); } - return i; + + rb_link_node(&slot->gfn_node[idx], parent, node); + rb_insert_color(&slot->gfn_node[idx], gfn_tree); } -/* - * Move a changed memslot forwards in the array by shifting existing slots with - * a lower GFN toward the back of the array. Note, the changed memslot itself - * is not preserved in the array, i.e. not swapped at this time, only its new - * index into the array is tracked. Returns the changed memslot's final index - * into the memslots array. - */ -static inline int kvm_memslot_move_forward(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot, - int start) +static void kvm_erase_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *slot) { - struct kvm_memory_slot *mslots = slots->memslots; - int i; + rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree); +} - for (i = start; i > 0; i--) { - if (memslot->base_gfn < mslots[i - 1].base_gfn) - break; +static void kvm_replace_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + int idx = slots->node_idx; - WARN_ON_ONCE(memslot->base_gfn == mslots[i - 1].base_gfn); + WARN_ON_ONCE(old->base_gfn != new->base_gfn); - /* Shift the next memslot back one and update its index. */ - mslots[i] = mslots[i - 1]; - slots->id_to_index[mslots[i].id] = i; - } - return i; + rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx], + &slots->gfn_tree); } /* - * Re-sort memslots based on their GFN to account for an added, deleted, or - * moved memslot. Sorting memslots by GFN allows using a binary search during - * memslot lookup. + * Replace @old with @new in the inactive memslots. * - * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! I.e. the entry - * at memslots[0] has the highest GFN. + * With NULL @old this simply adds @new. + * With NULL @new this simply removes @old. * - * The sorting algorithm takes advantage of having initially sorted memslots - * and knowing the position of the changed memslot. Sorting is also optimized - * by not swapping the updated memslot and instead only shifting other memslots - * and tracking the new index for the update memslot. Only once its final - * index is known is the updated memslot copied into its position in the array. - * - * - When deleting a memslot, the deleted memslot simply needs to be moved to - * the end of the array. - * - * - When creating a memslot, the algorithm "inserts" the new memslot at the - * end of the array and then it forward to its correct location. - * - * - When moving a memslot, the algorithm first moves the updated memslot - * backward to handle the scenario where the memslot's GFN was changed to a - * lower value. update_memslots() then falls through and runs the same flow - * as creating a memslot to move the memslot forward to handle the scenario - * where its GFN was changed to a higher value. - * - * Note, slots are sorted from highest->lowest instead of lowest->highest for - * historical reasons. Originally, invalid memslots where denoted by having - * GFN=0, thus sorting from highest->lowest naturally sorted invalid memslots - * to the end of the array. The current algorithm uses dedicated logic to - * delete a memslot and thus does not rely on invalid memslots having GFN=0. - * - * The other historical motiviation for highest->lowest was to improve the - * performance of memslot lookup. KVM originally used a linear search starting - * at memslots[0]. On x86, the largest memslot usually has one of the highest, - * if not *the* highest, GFN, as the bulk of the guest's RAM is located in a - * single memslot above the 4gb boundary. As the largest memslot is also the - * most likely to be referenced, sorting it to the front of the array was - * advantageous. The current binary search starts from the middle of the array - * and uses an LRU pointer to improve performance for all memslots and GFNs. + * If @new is non-NULL its hva_node[slots_idx] range has to be set + * appropriately. */ -static void update_memslots(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot, - enum kvm_mr_change change) +static void kvm_replace_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) { - int i; + int as_id = kvm_memslots_get_as_id(old, new); + struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); + int idx = slots->node_idx; - if (change == KVM_MR_DELETE) { - kvm_memslot_delete(slots, memslot); - } else { - if (change == KVM_MR_CREATE) - i = kvm_memslot_insert_back(slots); - else - i = kvm_memslot_move_backward(slots, memslot); - i = kvm_memslot_move_forward(slots, memslot, i); + if (old) { + hash_del(&old->id_node[idx]); + interval_tree_remove(&old->hva_node[idx], &slots->hva_tree); - /* - * Copy the memslot to its new position in memslots and update - * its index accordingly. - */ - slots->memslots[i] = *memslot; - slots->id_to_index[memslot->id] = i; + if ((long)old == atomic_long_read(&slots->last_used_slot)) + atomic_long_set(&slots->last_used_slot, (long)new); + + if (!new) { + kvm_erase_gfn_node(slots, old); + return; + } + } + + /* + * Initialize @new's hva range. Do this even when replacing an @old + * slot, kvm_copy_memslot() deliberately does not touch node data. + */ + new->hva_node[idx].start = new->userspace_addr; + new->hva_node[idx].last = new->userspace_addr + + (new->npages << PAGE_SHIFT) - 1; + + /* + * (Re)Add the new memslot. There is no O(1) interval_tree_replace(), + * hva_node needs to be swapped with remove+insert even though hva can't + * change when replacing an existing slot. + */ + hash_add(slots->id_hash, &new->id_node[idx], new->id); + interval_tree_insert(&new->hva_node[idx], &slots->hva_tree); + + /* + * If the memslot gfn is unchanged, rb_replace_node() can be used to + * switch the node in the gfn tree instead of removing the old and + * inserting the new as two separate operations. Replacement is a + * single O(1) operation versus two O(log(n)) operations for + * remove+insert. + */ + if (old && old->base_gfn == new->base_gfn) { + kvm_replace_gfn_node(slots, old, new); + } else { + if (old) + kvm_erase_gfn_node(slots, old); + kvm_insert_gfn_node(slots, new); } } @@ -1435,11 +1433,12 @@ static int check_memory_region_flags(const struct kvm_userspace_memory_region *m return 0; } -static struct kvm_memslots *install_new_memslots(struct kvm *kvm, - int as_id, struct kvm_memslots *slots) +static void kvm_swap_active_memslots(struct kvm *kvm, int as_id) { - struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id); - u64 gen = old_memslots->generation; + struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); + + /* Grab the generation from the activate memslots. */ + u64 gen = __kvm_memslots(kvm, as_id)->generation; WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; @@ -1490,61 +1489,226 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, kvm_arch_memslots_updated(kvm, gen); slots->generation = gen; - - return old_memslots; } -static size_t kvm_memslots_size(int slots) +static int kvm_prepare_memory_region(struct kvm *kvm, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { - return sizeof(struct kvm_memslots) + - (sizeof(struct kvm_memory_slot) * slots); + int r; + + /* + * If dirty logging is disabled, nullify the bitmap; the old bitmap + * will be freed on "commit". If logging is enabled in both old and + * new, reuse the existing bitmap. If logging is enabled only in the + * new and KVM isn't using a ring buffer, allocate and initialize a + * new bitmap. + */ + if (change != KVM_MR_DELETE) { + if (!(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) + new->dirty_bitmap = NULL; + else if (old && old->dirty_bitmap) + new->dirty_bitmap = old->dirty_bitmap; + else if (!kvm->dirty_ring_size) { + r = kvm_alloc_dirty_bitmap(new); + if (r) + return r; + + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + bitmap_set(new->dirty_bitmap, 0, new->npages); + } + } + + r = kvm_arch_prepare_memory_region(kvm, old, new, change); + + /* Free the bitmap on failure if it was allocated above. */ + if (r && new && new->dirty_bitmap && old && !old->dirty_bitmap) + kvm_destroy_dirty_bitmap(new); + + return r; } -static void kvm_copy_memslots(struct kvm_memslots *to, - struct kvm_memslots *from) +static void kvm_commit_memory_region(struct kvm *kvm, + struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + enum kvm_mr_change change) { - memcpy(to, from, kvm_memslots_size(from->used_slots)); + /* + * Update the total number of memslot pages before calling the arch + * hook so that architectures can consume the result directly. + */ + if (change == KVM_MR_DELETE) + kvm->nr_memslot_pages -= old->npages; + else if (change == KVM_MR_CREATE) + kvm->nr_memslot_pages += new->npages; + + kvm_arch_commit_memory_region(kvm, old, new, change); + + switch (change) { + case KVM_MR_CREATE: + /* Nothing more to do. */ + break; + case KVM_MR_DELETE: + /* Free the old memslot and all its metadata. */ + kvm_free_memslot(kvm, old); + break; + case KVM_MR_MOVE: + case KVM_MR_FLAGS_ONLY: + /* + * Free the dirty bitmap as needed; the below check encompasses + * both the flags and whether a ring buffer is being used) + */ + if (old->dirty_bitmap && !new->dirty_bitmap) + kvm_destroy_dirty_bitmap(old); + + /* + * The final quirk. Free the detached, old slot, but only its + * memory, not any metadata. Metadata, including arch specific + * data, may be reused by @new. + */ + kfree(old); + break; + default: + BUG(); + } } /* - * Note, at a minimum, the current number of used slots must be allocated, even - * when deleting a memslot, as we need a complete duplicate of the memslots for - * use when invalidating a memslot prior to deleting/moving the memslot. + * Activate @new, which must be installed in the inactive slots by the caller, + * by swapping the active slots and then propagating @new to @old once @old is + * unreachable and can be safely modified. + * + * With NULL @old this simply adds @new to @active (while swapping the sets). + * With NULL @new this simply removes @old from @active and frees it + * (while also swapping the sets). */ -static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old, - enum kvm_mr_change change) +static void kvm_activate_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) { - struct kvm_memslots *slots; - size_t new_size; + int as_id = kvm_memslots_get_as_id(old, new); - if (change == KVM_MR_CREATE) - new_size = kvm_memslots_size(old->used_slots + 1); - else - new_size = kvm_memslots_size(old->used_slots); + kvm_swap_active_memslots(kvm, as_id); - slots = kvzalloc(new_size, GFP_KERNEL_ACCOUNT); - if (likely(slots)) - kvm_copy_memslots(slots, old); + /* Propagate the new memslot to the now inactive memslots. */ + kvm_replace_memslot(kvm, old, new); +} - return slots; +static void kvm_copy_memslot(struct kvm_memory_slot *dest, + const struct kvm_memory_slot *src) +{ + dest->base_gfn = src->base_gfn; + dest->npages = src->npages; + dest->dirty_bitmap = src->dirty_bitmap; + dest->arch = src->arch; + dest->userspace_addr = src->userspace_addr; + dest->flags = src->flags; + dest->id = src->id; + dest->as_id = src->as_id; +} + +static void kvm_invalidate_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *invalid_slot) +{ + /* + * Mark the current slot INVALID. As with all memslot modifications, + * this must be done on an unreachable slot to avoid modifying the + * current slot in the active tree. + */ + kvm_copy_memslot(invalid_slot, old); + invalid_slot->flags |= KVM_MEMSLOT_INVALID; + kvm_replace_memslot(kvm, old, invalid_slot); + + /* + * Activate the slot that is now marked INVALID, but don't propagate + * the slot to the now inactive slots. The slot is either going to be + * deleted or recreated as a new slot. + */ + kvm_swap_active_memslots(kvm, old->as_id); + + /* + * From this point no new shadow pages pointing to a deleted, or moved, + * memslot will be created. Validation of sp->gfn happens in: + * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) + * - kvm_is_visible_gfn (mmu_check_root) + */ + kvm_arch_flush_shadow_memslot(kvm, old); + + /* Was released by kvm_swap_active_memslots, reacquire. */ + mutex_lock(&kvm->slots_arch_lock); + + /* + * Copy the arch-specific field of the newly-installed slot back to the + * old slot as the arch data could have changed between releasing + * slots_arch_lock in install_new_memslots() and re-acquiring the lock + * above. Writers are required to retrieve memslots *after* acquiring + * slots_arch_lock, thus the active slot's data is guaranteed to be fresh. + */ + old->arch = invalid_slot->arch; +} + +static void kvm_create_memslot(struct kvm *kvm, + struct kvm_memory_slot *new) +{ + /* Add the new memslot to the inactive set and activate. */ + kvm_replace_memslot(kvm, NULL, new); + kvm_activate_memslot(kvm, NULL, new); +} + +static void kvm_delete_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *invalid_slot) +{ + /* + * Remove the old memslot (in the inactive memslots) by passing NULL as + * the "new" slot, and for the invalid version in the active slots. + */ + kvm_replace_memslot(kvm, old, NULL); + kvm_activate_memslot(kvm, invalid_slot, NULL); +} + +static void kvm_move_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + struct kvm_memory_slot *invalid_slot) +{ + /* + * Replace the old memslot in the inactive slots, and then swap slots + * and replace the current INVALID with the new as well. + */ + kvm_replace_memslot(kvm, old, new); + kvm_activate_memslot(kvm, invalid_slot, new); +} + +static void kvm_update_flags_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + /* + * Similar to the MOVE case, but the slot doesn't need to be zapped as + * an intermediate step. Instead, the old memslot is simply replaced + * with a new, updated copy in both memslot sets. + */ + kvm_replace_memslot(kvm, old, new); + kvm_activate_memslot(kvm, old, new); } static int kvm_set_memslot(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, - struct kvm_memory_slot *new, int as_id, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - struct kvm_memory_slot *slot; - struct kvm_memslots *slots; + struct kvm_memory_slot *invalid_slot; int r; /* - * Released in install_new_memslots. + * Released in kvm_swap_active_memslots. * * Must be held from before the current memslots are copied until * after the new memslots are installed with rcu_assign_pointer, - * then released before the synchronize srcu in install_new_memslots. + * then released before the synchronize srcu in kvm_swap_active_memslots. * * When modifying memslots outside of the slots_lock, must be held * before reading the pointer to the current memslots until after all @@ -1555,96 +1719,88 @@ static int kvm_set_memslot(struct kvm *kvm, */ mutex_lock(&kvm->slots_arch_lock); - slots = kvm_dup_memslots(__kvm_memslots(kvm, as_id), change); - if (!slots) { - mutex_unlock(&kvm->slots_arch_lock); - return -ENOMEM; - } - + /* + * Invalidate the old slot if it's being deleted or moved. This is + * done prior to actually deleting/moving the memslot to allow vCPUs to + * continue running by ensuring there are no mappings or shadow pages + * for the memslot when it is deleted/moved. Without pre-invalidation + * (and without a lock), a window would exist between effecting the + * delete/move and committing the changes in arch code where KVM or a + * guest could access a non-existent memslot. + * + * Modifications are done on a temporary, unreachable slot. The old + * slot needs to be preserved in case a later step fails and the + * invalidation needs to be reverted. + */ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { - /* - * Note, the INVALID flag needs to be in the appropriate entry - * in the freshly allocated memslots, not in @old or @new. - */ - slot = id_to_memslot(slots, old->id); - slot->flags |= KVM_MEMSLOT_INVALID; - - /* - * We can re-use the memory from the old memslots. - * It will be overwritten with a copy of the new memslots - * after reacquiring the slots_arch_lock below. - */ - slots = install_new_memslots(kvm, as_id, slots); - - /* From this point no new shadow pages pointing to a deleted, - * or moved, memslot will be created. - * - * validation of sp->gfn happens in: - * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) - * - kvm_is_visible_gfn (mmu_check_root) - */ - kvm_arch_flush_shadow_memslot(kvm, slot); - - /* Released in install_new_memslots. */ - mutex_lock(&kvm->slots_arch_lock); + invalid_slot = kzalloc(sizeof(*invalid_slot), GFP_KERNEL_ACCOUNT); + if (!invalid_slot) { + mutex_unlock(&kvm->slots_arch_lock); + return -ENOMEM; + } + kvm_invalidate_memslot(kvm, old, invalid_slot); + } + r = kvm_prepare_memory_region(kvm, old, new, change); + if (r) { /* - * The arch-specific fields of the memslots could have changed - * between releasing the slots_arch_lock in - * install_new_memslots and here, so get a fresh copy of the - * slots. + * For DELETE/MOVE, revert the above INVALID change. No + * modifications required since the original slot was preserved + * in the inactive slots. Changing the active memslots also + * release slots_arch_lock. */ - kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id)); + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { + kvm_activate_memslot(kvm, invalid_slot, old); + kfree(invalid_slot); + } else { + mutex_unlock(&kvm->slots_arch_lock); + } + return r; } - r = kvm_arch_prepare_memory_region(kvm, new, mem, change); - if (r) - goto out_slots; + /* + * For DELETE and MOVE, the working slot is now active as the INVALID + * version of the old slot. MOVE is particularly special as it reuses + * the old slot and returns a copy of the old slot (in working_slot). + * For CREATE, there is no old slot. For DELETE and FLAGS_ONLY, the + * old slot is detached but otherwise preserved. + */ + if (change == KVM_MR_CREATE) + kvm_create_memslot(kvm, new); + else if (change == KVM_MR_DELETE) + kvm_delete_memslot(kvm, old, invalid_slot); + else if (change == KVM_MR_MOVE) + kvm_move_memslot(kvm, old, new, invalid_slot); + else if (change == KVM_MR_FLAGS_ONLY) + kvm_update_flags_memslot(kvm, old, new); + else + BUG(); - update_memslots(slots, new, change); - slots = install_new_memslots(kvm, as_id, slots); + /* Free the temporary INVALID slot used for DELETE and MOVE. */ + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) + kfree(invalid_slot); - kvm_arch_commit_memory_region(kvm, mem, old, new, change); + /* + * No need to refresh new->arch, changes after dropping slots_arch_lock + * will directly hit the final, active memsot. Architectures are + * responsible for knowing that new->arch may be stale. + */ + kvm_commit_memory_region(kvm, old, new, change); - kvfree(slots); return 0; - -out_slots: - if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { - slot = id_to_memslot(slots, old->id); - slot->flags &= ~KVM_MEMSLOT_INVALID; - slots = install_new_memslots(kvm, as_id, slots); - } else { - mutex_unlock(&kvm->slots_arch_lock); - } - kvfree(slots); - return r; } -static int kvm_delete_memslot(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot *old, int as_id) +static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id, + gfn_t start, gfn_t end) { - struct kvm_memory_slot new; - int r; - - if (!old->npages) - return -EINVAL; + struct kvm_memslot_iter iter; - memset(&new, 0, sizeof(new)); - new.id = old->id; - /* - * This is only for debugging purpose; it should never be referenced - * for a removed memslot. - */ - new.as_id = as_id; - - r = kvm_set_memslot(kvm, mem, old, &new, as_id, KVM_MR_DELETE); - if (r) - return r; + kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) { + if (iter.slot->id != id) + return true; + } - kvm_free_memslot(kvm, old); - return 0; + return false; } /* @@ -1658,9 +1814,11 @@ static int kvm_delete_memslot(struct kvm *kvm, int __kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem) { - struct kvm_memory_slot old, new; - struct kvm_memory_slot *tmp; + struct kvm_memory_slot *old, *new; + struct kvm_memslots *slots; enum kvm_mr_change change; + unsigned long npages; + gfn_t base_gfn; int as_id, id; int r; @@ -1672,7 +1830,8 @@ int __kvm_set_memory_region(struct kvm *kvm, id = (u16)mem->slot; /* General sanity checks */ - if (mem->memory_size & (PAGE_SIZE - 1)) + if ((mem->memory_size & (PAGE_SIZE - 1)) || + (mem->memory_size != (unsigned long)mem->memory_size)) return -EINVAL; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) return -EINVAL; @@ -1686,91 +1845,72 @@ int __kvm_set_memory_region(struct kvm *kvm, return -EINVAL; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) return -EINVAL; + if ((mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES) + return -EINVAL; + + slots = __kvm_memslots(kvm, as_id); /* - * Make a full copy of the old memslot, the pointer will become stale - * when the memslots are re-sorted by update_memslots(), and the old - * memslot needs to be referenced after calling update_memslots(), e.g. - * to free its resources and for arch specific behavior. + * Note, the old memslot (and the pointer itself!) may be invalidated + * and/or destroyed by kvm_set_memslot(). */ - tmp = id_to_memslot(__kvm_memslots(kvm, as_id), id); - if (tmp) { - old = *tmp; - tmp = NULL; - } else { - memset(&old, 0, sizeof(old)); - old.id = id; - } + old = id_to_memslot(slots, id); - if (!mem->memory_size) - return kvm_delete_memslot(kvm, mem, &old, as_id); + if (!mem->memory_size) { + if (!old || !old->npages) + return -EINVAL; - new.as_id = as_id; - new.id = id; - new.base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; - new.npages = mem->memory_size >> PAGE_SHIFT; - new.flags = mem->flags; - new.userspace_addr = mem->userspace_addr; + if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages)) + return -EIO; - if (new.npages > KVM_MEM_MAX_NR_PAGES) - return -EINVAL; + return kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE); + } + + base_gfn = (mem->guest_phys_addr >> PAGE_SHIFT); + npages = (mem->memory_size >> PAGE_SHIFT); - if (!old.npages) { + if (!old || !old->npages) { change = KVM_MR_CREATE; - new.dirty_bitmap = NULL; - memset(&new.arch, 0, sizeof(new.arch)); + + /* + * To simplify KVM internals, the total number of pages across + * all memslots must fit in an unsigned long. + */ + if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) + return -EINVAL; } else { /* Modify an existing slot. */ - if ((new.userspace_addr != old.userspace_addr) || - (new.npages != old.npages) || - ((new.flags ^ old.flags) & KVM_MEM_READONLY)) + if ((mem->userspace_addr != old->userspace_addr) || + (npages != old->npages) || + ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) return -EINVAL; - if (new.base_gfn != old.base_gfn) + if (base_gfn != old->base_gfn) change = KVM_MR_MOVE; - else if (new.flags != old.flags) + else if (mem->flags != old->flags) change = KVM_MR_FLAGS_ONLY; else /* Nothing to change. */ return 0; - - /* Copy dirty_bitmap and arch from the current memslot. */ - new.dirty_bitmap = old.dirty_bitmap; - memcpy(&new.arch, &old.arch, sizeof(new.arch)); } - if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { - /* Check for overlaps */ - kvm_for_each_memslot(tmp, __kvm_memslots(kvm, as_id)) { - if (tmp->id == id) - continue; - if (!((new.base_gfn + new.npages <= tmp->base_gfn) || - (new.base_gfn >= tmp->base_gfn + tmp->npages))) - return -EEXIST; - } - } + if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) && + kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages)) + return -EEXIST; - /* Allocate/free page dirty bitmap as needed */ - if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES)) - new.dirty_bitmap = NULL; - else if (!new.dirty_bitmap && !kvm->dirty_ring_size) { - r = kvm_alloc_dirty_bitmap(&new); - if (r) - return r; + /* Allocate a slot that will persist in the memslot. */ + new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); + if (!new) + return -ENOMEM; - if (kvm_dirty_log_manual_protect_and_init_set(kvm)) - bitmap_set(new.dirty_bitmap, 0, new.npages); - } + new->as_id = as_id; + new->id = id; + new->base_gfn = base_gfn; + new->npages = npages; + new->flags = mem->flags; + new->userspace_addr = mem->userspace_addr; - r = kvm_set_memslot(kvm, mem, &old, &new, as_id, change); + r = kvm_set_memslot(kvm, old, new, change); if (r) - goto out_bitmap; - - if (old.dirty_bitmap && !new.dirty_bitmap) - kvm_destroy_dirty_bitmap(&old); - return 0; - -out_bitmap: - if (new.dirty_bitmap && !old.dirty_bitmap) - kvm_destroy_dirty_bitmap(&new); + kfree(new); return r; } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); @@ -2076,21 +2216,30 @@ EXPORT_SYMBOL_GPL(gfn_to_memslot); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu); + u64 gen = slots->generation; struct kvm_memory_slot *slot; - int slot_index; - slot = try_get_memslot(slots, vcpu->last_used_slot, gfn); + /* + * This also protects against using a memslot from a different address space, + * since different address spaces have different generation numbers. + */ + if (unlikely(gen != vcpu->last_used_slot_gen)) { + vcpu->last_used_slot = NULL; + vcpu->last_used_slot_gen = gen; + } + + slot = try_get_memslot(vcpu->last_used_slot, gfn); if (slot) return slot; /* * Fall back to searching all memslots. We purposely use * search_memslots() instead of __gfn_to_memslot() to avoid - * thrashing the VM-wide last_used_index in kvm_memslots. + * thrashing the VM-wide last_used_slot in kvm_memslots. */ - slot = search_memslots(slots, gfn, &slot_index); + slot = search_memslots(slots, gfn, false); if (slot) { - vcpu->last_used_slot = slot_index; + vcpu->last_used_slot = slot; return slot; } @@ -2138,12 +2287,12 @@ out: return size; } -static bool memslot_is_readonly(struct kvm_memory_slot *slot) +static bool memslot_is_readonly(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_READONLY; } -static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, +static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages, bool write) { if (!slot || slot->flags & KVM_MEMSLOT_INVALID) @@ -2438,7 +2587,7 @@ exit: return pfn; } -kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, +kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, bool *writable, hva_t *hva) { @@ -2478,13 +2627,13 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); -kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); -kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL); } @@ -2915,7 +3064,8 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, int r; gpa_t gpa = ghc->gpa + offset; - BUG_ON(len + offset > ghc->len); + if (WARN_ON_ONCE(len + offset > ghc->len)) + return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) @@ -2952,7 +3102,8 @@ int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, int r; gpa_t gpa = ghc->gpa + offset; - BUG_ON(len + offset > ghc->len); + if (WARN_ON_ONCE(len + offset > ghc->len)) + return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) @@ -3001,7 +3152,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) EXPORT_SYMBOL_GPL(kvm_clear_guest); void mark_page_dirty_in_slot(struct kvm *kvm, - struct kvm_memory_slot *memslot, + const struct kvm_memory_slot *memslot, gfn_t gfn) { if (memslot && kvm_slot_dirty_track_enabled(memslot)) { @@ -3121,68 +3272,93 @@ out: return ret; } -static inline void -update_halt_poll_stats(struct kvm_vcpu *vcpu, u64 poll_ns, bool waited) +/* + * Block the vCPU until the vCPU is runnable, an event arrives, or a signal is + * pending. This is mostly used when halting a vCPU, but may also be used + * directly for other vCPU non-runnable states, e.g. x86's Wait-For-SIPI. + */ +bool kvm_vcpu_block(struct kvm_vcpu *vcpu) { - if (waited) - vcpu->stat.generic.halt_poll_fail_ns += poll_ns; - else - vcpu->stat.generic.halt_poll_success_ns += poll_ns; + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); + bool waited = false; + + vcpu->stat.generic.blocking = 1; + + kvm_arch_vcpu_blocking(vcpu); + + prepare_to_rcuwait(wait); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + if (kvm_vcpu_check_block(vcpu) < 0) + break; + + waited = true; + schedule(); + } + finish_rcuwait(wait); + + kvm_arch_vcpu_unblocking(vcpu); + + vcpu->stat.generic.blocking = 0; + + return waited; +} + +static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, + ktime_t end, bool success) +{ + struct kvm_vcpu_stat_generic *stats = &vcpu->stat.generic; + u64 poll_ns = ktime_to_ns(ktime_sub(end, start)); + + ++vcpu->stat.generic.halt_attempted_poll; + + if (success) { + ++vcpu->stat.generic.halt_successful_poll; + + if (!vcpu_valid_wakeup(vcpu)) + ++vcpu->stat.generic.halt_poll_invalid; + + stats->halt_poll_success_ns += poll_ns; + KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_success_hist, poll_ns); + } else { + stats->halt_poll_fail_ns += poll_ns; + KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_fail_hist, poll_ns); + } } /* - * The vCPU has executed a HLT instruction with in-kernel mode enabled. + * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt + * polling is enabled, busy wait for a short time before blocking to avoid the + * expensive block+unblock sequence if a wake event arrives soon after the vCPU + * is halted. */ -void kvm_vcpu_block(struct kvm_vcpu *vcpu) +void kvm_vcpu_halt(struct kvm_vcpu *vcpu) { + bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); + bool do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; ktime_t start, cur, poll_end; bool waited = false; - u64 block_ns; - - kvm_arch_vcpu_blocking(vcpu); + u64 halt_ns; start = cur = poll_end = ktime_get(); - if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) { - ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns); + if (do_halt_poll) { + ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns); - ++vcpu->stat.generic.halt_attempted_poll; do { /* * This sets KVM_REQ_UNHALT if an interrupt * arrives. */ - if (kvm_vcpu_check_block(vcpu) < 0) { - ++vcpu->stat.generic.halt_successful_poll; - if (!vcpu_valid_wakeup(vcpu)) - ++vcpu->stat.generic.halt_poll_invalid; - - KVM_STATS_LOG_HIST_UPDATE( - vcpu->stat.generic.halt_poll_success_hist, - ktime_to_ns(ktime_get()) - - ktime_to_ns(start)); + if (kvm_vcpu_check_block(vcpu) < 0) goto out; - } cpu_relax(); poll_end = cur = ktime_get(); } while (kvm_vcpu_can_poll(cur, stop)); - - KVM_STATS_LOG_HIST_UPDATE( - vcpu->stat.generic.halt_poll_fail_hist, - ktime_to_ns(ktime_get()) - ktime_to_ns(start)); } + waited = kvm_vcpu_block(vcpu); - prepare_to_rcuwait(&vcpu->wait); - for (;;) { - set_current_state(TASK_INTERRUPTIBLE); - - if (kvm_vcpu_check_block(vcpu) < 0) - break; - - waited = true; - schedule(); - } - finish_rcuwait(&vcpu->wait); cur = ktime_get(); if (waited) { vcpu->stat.generic.halt_wait_ns += @@ -3191,42 +3367,43 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) ktime_to_ns(cur) - ktime_to_ns(poll_end)); } out: - kvm_arch_vcpu_unblocking(vcpu); - block_ns = ktime_to_ns(cur) - ktime_to_ns(start); + /* The total time the vCPU was "halted", including polling time. */ + halt_ns = ktime_to_ns(cur) - ktime_to_ns(start); - update_halt_poll_stats( - vcpu, ktime_to_ns(ktime_sub(poll_end, start)), waited); + /* + * Note, halt-polling is considered successful so long as the vCPU was + * never actually scheduled out, i.e. even if the wake event arrived + * after of the halt-polling loop itself, but before the full wait. + */ + if (do_halt_poll) + update_halt_poll_stats(vcpu, start, poll_end, !waited); - if (!kvm_arch_no_poll(vcpu)) { + if (halt_poll_allowed) { if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); } else if (vcpu->kvm->max_halt_poll_ns) { - if (block_ns <= vcpu->halt_poll_ns) + if (halt_ns <= vcpu->halt_poll_ns) ; /* we had a long block, shrink polling */ else if (vcpu->halt_poll_ns && - block_ns > vcpu->kvm->max_halt_poll_ns) + halt_ns > vcpu->kvm->max_halt_poll_ns) shrink_halt_poll_ns(vcpu); /* we had a short halt and our poll time is too small */ else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns && - block_ns < vcpu->kvm->max_halt_poll_ns) + halt_ns < vcpu->kvm->max_halt_poll_ns) grow_halt_poll_ns(vcpu); } else { vcpu->halt_poll_ns = 0; } } - trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu)); - kvm_arch_vcpu_block_finish(vcpu); + trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu)); } -EXPORT_SYMBOL_GPL(kvm_vcpu_block); +EXPORT_SYMBOL_GPL(kvm_vcpu_halt); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { - struct rcuwait *waitp; - - waitp = kvm_arch_vcpu_get_wait(vcpu); - if (rcuwait_wake_up(waitp)) { + if (__kvm_vcpu_wake_up(vcpu)) { WRITE_ONCE(vcpu->ready, true); ++vcpu->stat.generic.halt_wakeup; return true; @@ -3247,6 +3424,19 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) if (kvm_vcpu_wake_up(vcpu)) return; + me = get_cpu(); + /* + * The only state change done outside the vcpu mutex is IN_GUEST_MODE + * to EXITING_GUEST_MODE. Therefore the moderately expensive "should + * kick" check does not need atomic operations if kvm_vcpu_kick is used + * within the vCPU thread itself. + */ + if (vcpu == __this_cpu_read(kvm_running_vcpu)) { + if (vcpu->mode == IN_GUEST_MODE) + WRITE_ONCE(vcpu->mode, EXITING_GUEST_MODE); + goto out; + } + /* * Note, the vCPU could get migrated to a different pCPU at any point * after kvm_arch_vcpu_should_kick(), which could result in sending an @@ -3254,12 +3444,12 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the * vCPU also requires it to leave IN_GUEST_MODE. */ - me = get_cpu(); if (kvm_arch_vcpu_should_kick(vcpu)) { cpu = READ_ONCE(vcpu->cpu); if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); } +out: put_cpu(); } EXPORT_SYMBOL_GPL(kvm_vcpu_kick); @@ -3357,10 +3547,10 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + unsigned long i; int yielded = 0; int try = 3; int pass; - int i; kvm_vcpu_set_in_spin_loop(me, true); /* @@ -3381,8 +3571,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; if (vcpu == me) continue; - if (rcuwait_active(&vcpu->wait) && - !vcpu_dy_runnable(vcpu)) + if (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu)) continue; if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && !kvm_arch_dy_has_pending_interrupt(vcpu) && @@ -3411,7 +3600,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff) { -#if KVM_DIRTY_LOG_PAGE_OFFSET > 0 +#ifdef CONFIG_HAVE_KVM_DIRTY_RING return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) && (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET + kvm->dirty_ring_size / PAGE_SIZE); @@ -3567,7 +3756,10 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - BUG_ON(kvm->vcpus[vcpu->vcpu_idx]); + r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); + BUG_ON(r == -EBUSY); + if (r) + goto unlock_vcpu_destroy; /* Fill the stats id string for the vcpu */ snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d", @@ -3577,15 +3769,14 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) { + xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); kvm_put_kvm_no_destroy(kvm); goto unlock_vcpu_destroy; } - kvm->vcpus[vcpu->vcpu_idx] = vcpu; - /* - * Pairs with smp_rmb() in kvm_get_vcpu. Write kvm->vcpus - * before kvm->online_vcpu's incremented value. + * Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu + * pointer before kvm->online_vcpu's incremented value. */ smp_wmb(); atomic_inc(&kvm->online_vcpus); @@ -4114,7 +4305,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_NR_MEMSLOTS: return KVM_USER_MEM_SLOTS; case KVM_CAP_DIRTY_LOG_RING: -#if KVM_DIRTY_LOG_PAGE_OFFSET > 0 +#ifdef CONFIG_HAVE_KVM_DIRTY_RING return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; @@ -4167,7 +4358,7 @@ static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size) static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; int cleared = 0; @@ -5086,7 +5277,7 @@ static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; *val = 0; @@ -5099,7 +5290,7 @@ static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) |