diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-05-01 10:14:08 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-05-01 10:14:08 -0700 |
commit | 152d32aa846835987966fd20ee1143b0e05036a0 (patch) | |
tree | 728cfb095b62bb3cb3ede5ff12f70d0042db49d4 /arch/arm64/kvm/vgic | |
parent | 4f9701057a9cc1ae6bfc533204c9d3ba386687de (diff) | |
parent | 3bf0fcd754345d7ea63e1446015ba65ece6788ca (diff) | |
download | linux-152d32aa846835987966fd20ee1143b0e05036a0.tar.bz2 |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"This is a large update by KVM standards, including AMD PSP (Platform
Security Processor, aka "AMD Secure Technology") and ARM CoreSight
(debug and trace) changes.
ARM:
- CoreSight: Add support for ETE and TRBE
- Stage-2 isolation for the host kernel when running in protected
mode
- Guest SVE support when running in nVHE mode
- Force W^X hypervisor mappings in nVHE mode
- ITS save/restore for guests using direct injection with GICv4.1
- nVHE panics now produce readable backtraces
- Guest support for PTP using the ptp_kvm driver
- Performance improvements in the S2 fault handler
x86:
- AMD PSP driver changes
- Optimizations and cleanup of nested SVM code
- AMD: Support for virtual SPEC_CTRL
- Optimizations of the new MMU code: fast invalidation, zap under
read lock, enable/disably dirty page logging under read lock
- /dev/kvm API for AMD SEV live migration (guest API coming soon)
- support SEV virtual machines sharing the same encryption context
- support SGX in virtual machines
- add a few more statistics
- improved directed yield heuristics
- Lots and lots of cleanups
Generic:
- Rework of MMU notifier interface, simplifying and optimizing the
architecture-specific code
- a handful of "Get rid of oprofile leftovers" patches
- Some selftests improvements"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (379 commits)
KVM: selftests: Speed up set_memory_region_test
selftests: kvm: Fix the check of return value
KVM: x86: Take advantage of kvm_arch_dy_has_pending_interrupt()
KVM: SVM: Skip SEV cache flush if no ASIDs have been used
KVM: SVM: Remove an unnecessary prototype declaration of sev_flush_asids()
KVM: SVM: Drop redundant svm_sev_enabled() helper
KVM: SVM: Move SEV VMCB tracking allocation to sev.c
KVM: SVM: Explicitly check max SEV ASID during sev_hardware_setup()
KVM: SVM: Unconditionally invoke sev_hardware_teardown()
KVM: SVM: Enable SEV/SEV-ES functionality by default (when supported)
KVM: SVM: Condition sev_enabled and sev_es_enabled on CONFIG_KVM_AMD_SEV=y
KVM: SVM: Append "_enabled" to module-scoped SEV/SEV-ES control variables
KVM: SEV: Mask CPUID[0x8000001F].eax according to supported features
KVM: SVM: Move SEV module params/variables to sev.c
KVM: SVM: Disable SEV/SEV-ES if NPT is disabled
KVM: SVM: Free sev_asid_bitmap during init if SEV setup fails
KVM: SVM: Zero out the VMCB array used to track SEV ASID association
x86/sev: Drop redundant and potentially misleading 'sev_enabled'
KVM: x86: Move reverse CPUID helpers to separate header file
KVM: x86: Rename GPR accessors to make mode-aware variants the defaults
...
Diffstat (limited to 'arch/arm64/kvm/vgic')
-rw-r--r-- | arch/arm64/kvm/vgic/vgic-init.c | 12 | ||||
-rw-r--r-- | arch/arm64/kvm/vgic/vgic-its.c | 6 | ||||
-rw-r--r-- | arch/arm64/kvm/vgic/vgic-kvm-device.c | 7 | ||||
-rw-r--r-- | arch/arm64/kvm/vgic/vgic-mmio-v3.c | 81 | ||||
-rw-r--r-- | arch/arm64/kvm/vgic/vgic-mmio.c | 10 | ||||
-rw-r--r-- | arch/arm64/kvm/vgic/vgic-v3.c | 66 | ||||
-rw-r--r-- | arch/arm64/kvm/vgic/vgic-v4.c | 38 | ||||
-rw-r--r-- | arch/arm64/kvm/vgic/vgic.h | 2 |
8 files changed, 169 insertions, 53 deletions
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 052917deb149..58cbda00e56d 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -335,13 +335,14 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) kfree(dist->spis); dist->spis = NULL; dist->nr_spis = 0; + dist->vgic_dist_base = VGIC_ADDR_UNDEF; - if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) { - list_del(&rdreg->list); - kfree(rdreg); - } + if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) + vgic_v3_free_redist_region(rdreg); INIT_LIST_HEAD(&dist->rd_regions); + } else { + dist->vgic_cpu_base = VGIC_ADDR_UNDEF; } if (vgic_has_its(kvm)) @@ -362,6 +363,7 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) vgic_flush_pending_lpis(vcpu); INIT_LIST_HEAD(&vgic_cpu->ap_list_head); + vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; } /* To be called with kvm->lock held */ diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index b9518f94bd43..61728c543eb9 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2218,10 +2218,10 @@ static int vgic_its_save_itt(struct vgic_its *its, struct its_device *device) /* * If an LPI carries the HW bit, this means that this * interrupt is controlled by GICv4, and we do not - * have direct access to that state. Let's simply fail - * the save operation... + * have direct access to that state without GICv4.1. + * Let's simply fail the save operation... */ - if (ite->irq->hw) + if (ite->irq->hw && !kvm_vgic_global_state.has_gicv4_1) return -EACCES; ret = vgic_its_save_ite(its, device, ite, gpa, ite_esz); diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 44419679f91a..7740995de982 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -87,8 +87,8 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) r = vgic_v3_set_redist_base(kvm, 0, *addr, 0); goto out; } - rdreg = list_first_entry(&vgic->rd_regions, - struct vgic_redist_region, list); + rdreg = list_first_entry_or_null(&vgic->rd_regions, + struct vgic_redist_region, list); if (!rdreg) addr_ptr = &undef_value; else @@ -226,6 +226,9 @@ static int vgic_get_common_attr(struct kvm_device *dev, u64 addr; unsigned long type = (unsigned long)attr->attr; + if (copy_from_user(&addr, uaddr, sizeof(addr))) + return -EFAULT; + r = kvm_vgic_addr(dev->kvm, type, &addr, false); if (r) return (r == -ENODEV) ? -ENXIO : r; diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 2f1b156021a6..a09cdc0b953c 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -251,30 +251,35 @@ static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu, vgic_enable_lpis(vcpu); } -static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) +static bool vgic_mmio_vcpu_rdist_is_last(struct kvm_vcpu *vcpu) { - unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + struct vgic_dist *vgic = &vcpu->kvm->arch.vgic; struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_redist_region *rdreg = vgic_cpu->rdreg; - int target_vcpu_id = vcpu->vcpu_id; - gpa_t last_rdist_typer = rdreg->base + GICR_TYPER + - (rdreg->free_index - 1) * KVM_VGIC_V3_REDIST_SIZE; - u64 value; + struct vgic_redist_region *iter, *rdreg = vgic_cpu->rdreg; - value = (u64)(mpidr & GENMASK(23, 0)) << 32; - value |= ((target_vcpu_id & 0xffff) << 8); + if (!rdreg) + return false; - if (addr == last_rdist_typer) - value |= GICR_TYPER_LAST; - if (vgic_has_its(vcpu->kvm)) - value |= GICR_TYPER_PLPIS; + if (vgic_cpu->rdreg_index < rdreg->free_index - 1) { + return false; + } else if (rdreg->count && vgic_cpu->rdreg_index == (rdreg->count - 1)) { + struct list_head *rd_regions = &vgic->rd_regions; + gpa_t end = rdreg->base + rdreg->count * KVM_VGIC_V3_REDIST_SIZE; - return extract_bytes(value, addr & 7, len); + /* + * the rdist is the last one of the redist region, + * check whether there is no other contiguous rdist region + */ + list_for_each_entry(iter, rd_regions, list) { + if (iter->base == end && iter->free_index > 0) + return false; + } + } + return true; } -static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) +static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) { unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); int target_vcpu_id = vcpu->vcpu_id; @@ -286,7 +291,9 @@ static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu, if (vgic_has_its(vcpu->kvm)) value |= GICR_TYPER_PLPIS; - /* reporting of the Last bit is not supported for userspace */ + if (vgic_mmio_vcpu_rdist_is_last(vcpu)) + value |= GICR_TYPER_LAST; + return extract_bytes(value, addr & 7, len); } @@ -612,7 +619,7 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_TYPER, vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, - vgic_uaccess_read_v3r_typer, vgic_mmio_uaccess_write_wi, 8, + NULL, vgic_mmio_uaccess_write_wi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_WAKER, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, @@ -714,6 +721,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) return -EINVAL; vgic_cpu->rdreg = rdreg; + vgic_cpu->rdreg_index = rdreg->free_index; rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE; @@ -768,7 +776,7 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm) } /** - * vgic_v3_insert_redist_region - Insert a new redistributor region + * vgic_v3_alloc_redist_region - Allocate a new redistributor region * * Performs various checks before inserting the rdist region in the list. * Those tests depend on whether the size of the rdist region is known @@ -782,8 +790,8 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm) * * Return 0 on success, < 0 otherwise */ -static int vgic_v3_insert_redist_region(struct kvm *kvm, uint32_t index, - gpa_t base, uint32_t count) +static int vgic_v3_alloc_redist_region(struct kvm *kvm, uint32_t index, + gpa_t base, uint32_t count) { struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; @@ -791,10 +799,6 @@ static int vgic_v3_insert_redist_region(struct kvm *kvm, uint32_t index, size_t size = count * KVM_VGIC_V3_REDIST_SIZE; int ret; - /* single rdist region already set ?*/ - if (!count && !list_empty(rd_regions)) - return -EINVAL; - /* cross the end of memory ? */ if (base + size < base) return -EINVAL; @@ -805,11 +809,15 @@ static int vgic_v3_insert_redist_region(struct kvm *kvm, uint32_t index, } else { rdreg = list_last_entry(rd_regions, struct vgic_redist_region, list); - if (index != rdreg->index + 1) + + /* Don't mix single region and discrete redist regions */ + if (!count && rdreg->count) return -EINVAL; - /* Cannot add an explicitly sized regions after legacy region */ - if (!rdreg->count) + if (!count) + return -EEXIST; + + if (index != rdreg->index + 1) return -EINVAL; } @@ -848,11 +856,17 @@ free: return ret; } +void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg) +{ + list_del(&rdreg->list); + kfree(rdreg); +} + int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) { int ret; - ret = vgic_v3_insert_redist_region(kvm, index, addr, count); + ret = vgic_v3_alloc_redist_region(kvm, index, addr, count); if (ret) return ret; @@ -861,8 +875,13 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) * afterwards will register the iodevs when needed. */ ret = vgic_register_all_redist_iodevs(kvm); - if (ret) + if (ret) { + struct vgic_redist_region *rdreg; + + rdreg = vgic_v3_rdist_region_from_index(kvm, index); + vgic_v3_free_redist_region(rdreg); return ret; + } return 0; } diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index b2d73fc0d1ef..48c6067fc5ec 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -938,10 +938,9 @@ vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, return region; } -static int vgic_uaccess_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, +static int vgic_uaccess_read(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, u32 *val) { - struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); const struct vgic_register_region *region; struct kvm_vcpu *r_vcpu; @@ -960,10 +959,9 @@ static int vgic_uaccess_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, return 0; } -static int vgic_uaccess_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, +static int vgic_uaccess_write(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, const u32 *val) { - struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); const struct vgic_register_region *region; struct kvm_vcpu *r_vcpu; @@ -986,9 +984,9 @@ int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev, bool is_write, int offset, u32 *val) { if (is_write) - return vgic_uaccess_write(vcpu, &dev->dev, offset, val); + return vgic_uaccess_write(vcpu, dev, offset, val); else - return vgic_uaccess_read(vcpu, &dev->dev, offset, val); + return vgic_uaccess_read(vcpu, dev, offset, val); } static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 6f530925a231..41ecf219c333 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/irqchip/arm-gic-v3.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> @@ -356,6 +358,32 @@ retry: return 0; } +/* + * The deactivation of the doorbell interrupt will trigger the + * unmapping of the associated vPE. + */ +static void unmap_all_vpes(struct vgic_dist *dist) +{ + struct irq_desc *desc; + int i; + + for (i = 0; i < dist->its_vm.nr_vpes; i++) { + desc = irq_to_desc(dist->its_vm.vpes[i]->irq); + irq_domain_deactivate_irq(irq_desc_get_irq_data(desc)); + } +} + +static void map_all_vpes(struct vgic_dist *dist) +{ + struct irq_desc *desc; + int i; + + for (i = 0; i < dist->its_vm.nr_vpes; i++) { + desc = irq_to_desc(dist->its_vm.vpes[i]->irq); + irq_domain_activate_irq(irq_desc_get_irq_data(desc), false); + } +} + /** * vgic_v3_save_pending_tables - Save the pending tables into guest RAM * kvm lock and all vcpu lock must be held @@ -365,13 +393,28 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; gpa_t last_ptr = ~(gpa_t)0; - int ret; + bool vlpi_avail = false; + int ret = 0; u8 val; + if (unlikely(!vgic_initialized(kvm))) + return -ENXIO; + + /* + * A preparation for getting any VLPI states. + * The above vgic initialized check also ensures that the allocation + * and enabling of the doorbells have already been done. + */ + if (kvm_vgic_global_state.has_gicv4_1) { + unmap_all_vpes(dist); + vlpi_avail = true; + } + list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { int byte_offset, bit_nr; struct kvm_vcpu *vcpu; gpa_t pendbase, ptr; + bool is_pending; bool stored; vcpu = irq->target_vcpu; @@ -387,24 +430,35 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) if (ptr != last_ptr) { ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) - return ret; + goto out; last_ptr = ptr; } stored = val & (1U << bit_nr); - if (stored == irq->pending_latch) + + is_pending = irq->pending_latch; + + if (irq->hw && vlpi_avail) + vgic_v4_get_vlpi_state(irq, &is_pending); + + if (stored == is_pending) continue; - if (irq->pending_latch) + if (is_pending) val |= 1 << bit_nr; else val &= ~(1 << bit_nr); ret = kvm_write_guest_lock(kvm, ptr, &val, 1); if (ret) - return ret; + goto out; } - return 0; + +out: + if (vlpi_avail) + map_all_vpes(dist); + + return ret; } /** diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 66508b03094f..c1845d8f5f7e 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -203,6 +203,25 @@ void vgic_v4_configure_vsgis(struct kvm *kvm) kvm_arm_resume_guest(kvm); } +/* + * Must be called with GICv4.1 and the vPE unmapped, which + * indicates the invalidation of any VPT caches associated + * with the vPE, thus we can get the VLPI state by peeking + * at the VPT. + */ +void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val) +{ + struct its_vpe *vpe = &irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + int mask = BIT(irq->intid % BITS_PER_BYTE); + void *va; + u8 *ptr; + + va = page_address(vpe->vpt_page); + ptr = va + irq->intid / BITS_PER_BYTE; + + *val = !!(*ptr & mask); +} + /** * vgic_v4_init - Initialize the GICv4 data structures * @kvm: Pointer to the VM being initialized @@ -385,6 +404,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, struct vgic_its *its; struct vgic_irq *irq; struct its_vlpi_map map; + unsigned long flags; int ret; if (!vgic_supports_direct_msis(kvm)) @@ -430,6 +450,24 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, irq->host_irq = virq; atomic_inc(&map.vpe->vlpi_count); + /* Transfer pending state */ + raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->pending_latch) { + ret = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + irq->pending_latch); + WARN_RATELIMIT(ret, "IRQ %d", irq->host_irq); + + /* + * Clear pending_latch and communicate this state + * change via vgic_queue_irq_unlock. + */ + irq->pending_latch = false; + vgic_queue_irq_unlock(kvm, irq, flags); + } else { + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } + out: mutex_unlock(&its->its_lock); return ret; diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 64fcd7511110..dc1f3d1657ee 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -293,6 +293,7 @@ vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, u32 index); +void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg); bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); @@ -317,5 +318,6 @@ bool vgic_supports_direct_msis(struct kvm *kvm); int vgic_v4_init(struct kvm *kvm); void vgic_v4_teardown(struct kvm *kvm); void vgic_v4_configure_vsgis(struct kvm *kvm); +void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val); #endif |