From bd2a6394fd2d3ea528d4b9c67f829e35f1f5d5dd Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Fri, 23 Feb 2018 17:23:57 +0100 Subject: KVM: arm/arm64: Introduce kvm_arch_vcpu_run_pid_change MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KVM/ARM differs from other architectures in having to maintain an additional virtual address space from that of the host and the guest, because we split the execution of KVM across both EL1 and EL2. This results in a need to explicitly map data structures into EL2 (hyp) which are accessed from the hyp code. As we are about to be more clever with our FPSIMD handling on arm64, which stores data in the task struct and uses thread_info flags, we will have to map parts of the currently executing task struct into the EL2 virtual address space. However, we don't want to do this on every KVM_RUN, because it is a fairly expensive operation to walk the page tables, and the common execution mode is to map a single thread to a VCPU. By introducing a hook that architectures can select with HAVE_KVM_VCPU_RUN_PID_CHANGE, we do not introduce overhead for other architectures, but have a simple way to only map the data we need when required for arm64. This patch introduces the framework only, and wires it up in the arm/arm64 KVM common code. No functional change. Signed-off-by: Christoffer Dall Signed-off-by: Dave Martin Reviewed-by: Marc Zyngier Reviewed-by: Alex Bennée Signed-off-by: Marc Zyngier --- virt/kvm/Kconfig | 3 +++ virt/kvm/kvm_main.c | 7 ++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'virt') diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index cca7e06..72143cf 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -54,3 +54,6 @@ config HAVE_KVM_IRQ_BYPASS config HAVE_KVM_VCPU_ASYNC_IOCTL bool + +config HAVE_KVM_VCPU_RUN_PID_CHANGE + bool diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c7b2e92..c32e240 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2550,8 +2550,13 @@ static long kvm_vcpu_ioctl(struct file *filp, oldpid = rcu_access_pointer(vcpu->pid); if (unlikely(oldpid != current->pids[PIDTYPE_PID].pid)) { /* The thread running this VCPU changed. */ - struct pid *newpid = get_task_pid(current, PIDTYPE_PID); + struct pid *newpid; + r = kvm_arch_vcpu_run_pid_change(vcpu); + if (r) + break; + + newpid = get_task_pid(current, PIDTYPE_PID); rcu_assign_pointer(vcpu->pid, newpid); if (oldpid) synchronize_rcu(); -- cgit v1.1 From e6b673b741ea0d7cd275ad40748bfc225accc423 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Fri, 6 Apr 2018 14:55:59 +0100 Subject: KVM: arm64: Optimise FPSIMD handling to reduce guest/host thrashing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch refactors KVM to align the host and guest FPSIMD save/restore logic with each other for arm64. This reduces the number of redundant save/restore operations that must occur, and reduces the common-case IRQ blackout time during guest exit storms by saving the host state lazily and optimising away the need to restore the host state before returning to the run loop. Four hooks are defined in order to enable this: * kvm_arch_vcpu_run_map_fp(): Called on PID change to map necessary bits of current to Hyp. * kvm_arch_vcpu_load_fp(): Set up FP/SIMD for entering the KVM run loop (parse as "vcpu_load fp"). * kvm_arch_vcpu_ctxsync_fp(): Get FP/SIMD into a safe state for re-enabling interrupts after a guest exit back to the run loop. For arm64 specifically, this involves updating the host kernel's FPSIMD context tracking metadata so that kernel-mode NEON use will cause the vcpu's FPSIMD state to be saved back correctly into the vcpu struct. This must be done before re-enabling interrupts because kernel-mode NEON may be used by softirqs. * kvm_arch_vcpu_put_fp(): Save guest FP/SIMD state back to memory and dissociate from the CPU ("vcpu_put fp"). Also, the arm64 FPSIMD context switch code is updated to enable it to save back FPSIMD state for a vcpu, not just current. A few helpers drive this: * fpsimd_bind_state_to_cpu(struct user_fpsimd_state *fp): mark this CPU as having context fp (which may belong to a vcpu) currently loaded in its registers. This is the non-task equivalent of the static function fpsimd_bind_to_cpu() in fpsimd.c. * task_fpsimd_save(): exported to allow KVM to save the guest's FPSIMD state back to memory on exit from the run loop. * fpsimd_flush_state(): invalidate any context's FPSIMD state that is currently loaded. Used to disassociate the vcpu from the CPU regs on run loop exit. These changes allow the run loop to enable interrupts (and thus softirqs that may use kernel-mode NEON) without having to save the guest's FPSIMD state eagerly. Some new vcpu_arch fields are added to make all this work. Because host FPSIMD state can now be saved back directly into current's thread_struct as appropriate, host_cpu_context is no longer used for preserving the FPSIMD state. However, it is still needed for preserving other things such as the host's system registers. To avoid ABI churn, the redundant storage space in host_cpu_context is not removed for now. arch/arm is not addressed by this patch and continues to use its current save/restore logic. It could provide implementations of the helpers later if desired. Signed-off-by: Dave Martin Reviewed-by: Marc Zyngier Reviewed-by: Christoffer Dall Reviewed-by: Alex Bennée Acked-by: Catalin Marinas Signed-off-by: Marc Zyngier --- virt/kvm/arm/arm.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'virt') diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index a4c1b76..bee226c 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -363,10 +363,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_vgic_load(vcpu); kvm_timer_vcpu_load(vcpu); kvm_vcpu_load_sysregs(vcpu); + kvm_arch_vcpu_load_fp(vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + kvm_arch_vcpu_put_fp(vcpu); kvm_vcpu_put_sysregs(vcpu); kvm_timer_vcpu_put(vcpu); kvm_vgic_put(vcpu); @@ -778,6 +780,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) if (static_branch_unlikely(&userspace_irqchip_in_use)) kvm_timer_sync_hwstate(vcpu); + kvm_arch_vcpu_ctxsync_fp(vcpu); + /* * We may have taken a host interrupt in HYP mode (ie * while executing the guest). This interrupt is still -- cgit v1.1 From 85acda3b4a27ee3e20c54783a44f307b51912c2b Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Fri, 20 Apr 2018 16:20:43 +0100 Subject: KVM: arm64: Save host SVE context as appropriate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds SVE context saving to the hyp FPSIMD context switch path. This means that it is no longer necessary to save the host SVE state in advance of entering the guest, when in use. In order to avoid adding pointless complexity to the code, VHE is assumed if SVE is in use. VHE is an architectural prerequisite for SVE, so there is no good reason to turn CONFIG_ARM64_VHE off in kernels that support both SVE and KVM. Historically, software models exist that can expose the architecturally invalid configuration of SVE without VHE, so if this situation is detected at kvm_init() time then KVM will be disabled. Signed-off-by: Dave Martin Reviewed-by: Alex Bennée Acked-by: Catalin Marinas Signed-off-by: Marc Zyngier --- virt/kvm/arm/arm.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'virt') diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index bee226c..ce7c6f3 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -16,6 +16,7 @@ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ +#include #include #include #include @@ -41,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -1574,6 +1576,11 @@ int kvm_arch_init(void *opaque) return -ENODEV; } + if (!kvm_arch_check_sve_has_vhe()) { + kvm_pr_unimpl("SVE system without VHE unsupported. Broken cpu?"); + return -ENODEV; + } + for_each_online_cpu(cpu) { smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1); if (ret < 0) { -- cgit v1.1 From 21cdd7fd76e3259b06d78c909e9caeb084c04b65 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Fri, 20 Apr 2018 17:39:16 +0100 Subject: KVM: arm64: Remove eager host SVE state saving MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that the host SVE context can be saved on demand from Hyp, there is no longer any need to save this state in advance before entering the guest. This patch removes the relevant call to kvm_fpsimd_flush_cpu_state(). Since the problem that function was intended to solve now no longer exists, the function and its dependencies are also deleted. Signed-off-by: Dave Martin Reviewed-by: Alex Bennée Acked-by: Christoffer Dall Acked-by: Marc Zyngier Acked-by: Catalin Marinas Signed-off-by: Marc Zyngier --- virt/kvm/arm/arm.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'virt') diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index ce7c6f3..39e7771 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -682,9 +682,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) */ preempt_disable(); - /* Flush FP/SIMD state that can't survive guest entry/exit */ - kvm_fpsimd_flush_cpu_state(); - kvm_pmu_flush_hwstate(vcpu); local_irq_disable(); -- cgit v1.1 From 9153ab724ea1f47840cab0cedb12683b37272067 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 22 May 2018 09:55:06 +0200 Subject: KVM: arm/arm64: Set dist->spis to NULL after kfree in case kvm_vgic_map_resources() fails, typically if the vgic distributor is not defined, __kvm_vgic_destroy will be called several times. Indeed kvm_vgic_map_resources() is called on first vcpu run. As a result dist->spis is freeed more than once and on the second time it causes a "kernel BUG at mm/slub.c:3912!" Set dist->spis to NULL to avoid the crash. Fixes: ad275b8bb1e6 ("KVM: arm/arm64: vgic-new: vgic_init: implement vgic_init") Signed-off-by: Eric Auger Reviewed-by: Marc Zyngier Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic/vgic-init.c | 1 + 1 file changed, 1 insertion(+) (limited to 'virt') diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index e07156c..9a5aed7 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -308,6 +308,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) dist->initialized = false; kfree(dist->spis); + dist->spis = NULL; dist->nr_spis = 0; if (vgic_supports_direct_msis(kvm)) -- cgit v1.1 From dbd9733ab6742dfb7d4f6c49e7d412d4e792d8be Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 22 May 2018 09:55:08 +0200 Subject: KVM: arm/arm64: Replace the single rdist region by a list At the moment KVM supports a single rdist region. We want to support several separate rdist regions so let's introduce a list of them. This patch currently only cares about a single entry in this list as the functionality to register several redist regions is not yet there. So this only translates the existing code into something functionally similar using that new data struct. The redistributor region handle is stored in the vgic_cpu structure to allow later computation of the TYPER last bit. Signed-off-by: Eric Auger Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic/vgic-init.c | 16 ++++++++++++++-- virt/kvm/arm/vgic/vgic-kvm-device.c | 13 +++++++++++-- virt/kvm/arm/vgic/vgic-mmio-v3.c | 38 +++++++++++++++++++++++++++++-------- virt/kvm/arm/vgic/vgic-v3.c | 20 +++++++++++-------- 4 files changed, 67 insertions(+), 20 deletions(-) (limited to 'virt') diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index 9a5aed7..8901b2d 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -167,8 +167,11 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) kvm->arch.vgic.vgic_model = type; kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; - kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; - kvm->arch.vgic.vgic_redist_base = VGIC_ADDR_UNDEF; + + if (type == KVM_DEV_TYPE_ARM_VGIC_V2) + kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; + else + INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); out_unlock: for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { @@ -303,6 +306,7 @@ out: static void kvm_vgic_dist_destroy(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_redist_region *rdreg, *next; dist->ready = false; dist->initialized = false; @@ -311,6 +315,14 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) dist->spis = NULL; dist->nr_spis = 0; + 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); + } + INIT_LIST_HEAD(&dist->rd_regions); + } + if (vgic_supports_direct_msis(kvm)) vgic_v4_teardown(kvm); } diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c index 10ae6f3..76ab369 100644 --- a/virt/kvm/arm/vgic/vgic-kvm-device.c +++ b/virt/kvm/arm/vgic/vgic-kvm-device.c @@ -66,6 +66,7 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) int r = 0; struct vgic_dist *vgic = &kvm->arch.vgic; phys_addr_t *addr_ptr, alignment; + u64 undef_value = VGIC_ADDR_UNDEF; mutex_lock(&kvm->lock); switch (type) { @@ -84,7 +85,9 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) addr_ptr = &vgic->vgic_dist_base; alignment = SZ_64K; break; - case KVM_VGIC_V3_ADDR_TYPE_REDIST: + case KVM_VGIC_V3_ADDR_TYPE_REDIST: { + struct vgic_redist_region *rdreg; + r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); if (r) break; @@ -92,8 +95,14 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) r = vgic_v3_set_redist_base(kvm, *addr); goto out; } - addr_ptr = &vgic->vgic_redist_base; + rdreg = list_first_entry(&vgic->rd_regions, + struct vgic_redist_region, list); + if (!rdreg) + addr_ptr = &undef_value; + else + addr_ptr = &rdreg->base; break; + } default: r = -ENODEV; } diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index 671fe81..d1aab18 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -580,8 +580,10 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct vgic_dist *vgic = &kvm->arch.vgic; + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev; + struct vgic_redist_region *rdreg; gpa_t rd_base, sgi_base; int ret; @@ -591,13 +593,17 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) * function for all VCPUs when the base address is set. Just return * without doing any work for now. */ - if (IS_VGIC_ADDR_UNDEF(vgic->vgic_redist_base)) + rdreg = list_first_entry(&vgic->rd_regions, + struct vgic_redist_region, list); + if (!rdreg) return 0; if (!vgic_v3_check_base(kvm)) return -EINVAL; - rd_base = vgic->vgic_redist_base + vgic->vgic_redist_free_offset; + vgic_cpu->rdreg = rdreg; + + rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE; sgi_base = rd_base + SZ_64K; kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops); @@ -631,7 +637,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) goto out; } - vgic->vgic_redist_free_offset += 2 * SZ_64K; + rdreg->free_index++; out: mutex_unlock(&kvm->slots_lock); return ret; @@ -673,19 +679,31 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm) int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr) { struct vgic_dist *vgic = &kvm->arch.vgic; + struct vgic_redist_region *rdreg; int ret; /* vgic_check_ioaddr makes sure we don't do this twice */ - ret = vgic_check_ioaddr(kvm, &vgic->vgic_redist_base, addr, SZ_64K); + if (!list_empty(&vgic->rd_regions)) + return -EINVAL; + + rdreg = kzalloc(sizeof(*rdreg), GFP_KERNEL); + if (!rdreg) + return -ENOMEM; + + rdreg->base = VGIC_ADDR_UNDEF; + + ret = vgic_check_ioaddr(kvm, &rdreg->base, addr, SZ_64K); if (ret) - return ret; + goto out; - vgic->vgic_redist_base = addr; + rdreg->base = addr; if (!vgic_v3_check_base(kvm)) { - vgic->vgic_redist_base = VGIC_ADDR_UNDEF; - return -EINVAL; + ret = -EINVAL; + goto out; } + list_add(&rdreg->list, &vgic->rd_regions); + /* * Register iodevs for each existing VCPU. Adding more VCPUs * afterwards will register the iodevs when needed. @@ -695,6 +713,10 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr) return ret; return 0; + +out: + kfree(rdreg); + return ret; } int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index c7423f3..56e6e90 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -427,6 +427,9 @@ bool vgic_v3_check_base(struct kvm *kvm) { struct vgic_dist *d = &kvm->arch.vgic; gpa_t redist_size = KVM_VGIC_V3_REDIST_SIZE; + struct vgic_redist_region *rdreg = + list_first_entry(&d->rd_regions, + struct vgic_redist_region, list); redist_size *= atomic_read(&kvm->online_vcpus); @@ -434,18 +437,17 @@ bool vgic_v3_check_base(struct kvm *kvm) d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base) return false; - if (!IS_VGIC_ADDR_UNDEF(d->vgic_redist_base) && - d->vgic_redist_base + redist_size < d->vgic_redist_base) + if (rdreg && (rdreg->base + redist_size < rdreg->base)) return false; /* Both base addresses must be set to check if they overlap */ - if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) || - IS_VGIC_ADDR_UNDEF(d->vgic_redist_base)) + if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) || !rdreg) return true; - if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE <= d->vgic_redist_base) + if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE <= rdreg->base) return true; - if (d->vgic_redist_base + redist_size <= d->vgic_dist_base) + + if (rdreg->base + redist_size <= d->vgic_dist_base) return true; return false; @@ -455,12 +457,14 @@ int vgic_v3_map_resources(struct kvm *kvm) { int ret = 0; struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_redist_region *rdreg = + list_first_entry(&dist->rd_regions, + struct vgic_redist_region, list); if (vgic_ready(kvm)) goto out; - if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || - IS_VGIC_ADDR_UNDEF(dist->vgic_redist_base)) { + if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || !rdreg) { kvm_err("Need to set vgic distributor addresses first\n"); ret = -ENXIO; goto out; -- cgit v1.1 From dc524619369c320e057cb198bbca017f3a0bb69a Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 22 May 2018 09:55:09 +0200 Subject: KVM: arm/arm64: Helper to locate free rdist index We introduce vgic_v3_rdist_free_slot to help identifying where we can place a new 2x64KB redistributor. Signed-off-by: Eric Auger Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic/vgic-mmio-v3.c | 3 +-- virt/kvm/arm/vgic/vgic-v3.c | 23 +++++++++++++++++++++++ virt/kvm/arm/vgic/vgic.h | 11 +++++++++++ 3 files changed, 35 insertions(+), 2 deletions(-) (limited to 'virt') diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index d1aab18..49ca176 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -593,8 +593,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) * function for all VCPUs when the base address is set. Just return * without doing any work for now. */ - rdreg = list_first_entry(&vgic->rd_regions, - struct vgic_redist_region, list); + rdreg = vgic_v3_rdist_free_slot(&vgic->rd_regions); if (!rdreg) return 0; diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 56e6e90..2a11fe8 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -453,6 +453,29 @@ bool vgic_v3_check_base(struct kvm *kvm) return false; } +/** + * vgic_v3_rdist_free_slot - Look up registered rdist regions and identify one + * which has free space to put a new rdist region. + * + * @rd_regions: redistributor region list head + * + * A redistributor regions maps n redistributors, n = region size / (2 x 64kB). + * Stride between redistributors is 0 and regions are filled in the index order. + * + * Return: the redist region handle, if any, that has space to map a new rdist + * region. + */ +struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions) +{ + struct vgic_redist_region *rdreg; + + list_for_each_entry(rdreg, rd_regions, list) { + if (!vgic_v3_redist_region_full(rdreg)) + return rdreg; + } + return NULL; +} + int vgic_v3_map_resources(struct kvm *kvm) { int ret = 0; diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 32c25d4..fddd57f 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -265,6 +265,17 @@ static inline int vgic_v3_max_apr_idx(struct kvm_vcpu *vcpu) } } +static inline bool +vgic_v3_redist_region_full(struct vgic_redist_region *region) +{ + if (!region->count) + return false; + + return (region->free_index >= region->count); +} + +struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rdregs); + int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq **irq); struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi); -- cgit v1.1 From ba7b3f1275fdd1a4059d25db0e248f05f72b9113 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 22 May 2018 09:55:10 +0200 Subject: KVM: arm/arm64: Revisit Redistributor TYPER last bit computation The TYPER of an redistributor reflects whether the rdist is the last one of the redistributor region. Let's compare the TYPER GPA against the address of the last occupied slot within the redistributor region. Signed-off-by: Eric Auger Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic/vgic-mmio-v3.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'virt') diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index 49ca176..ce5c927 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -184,12 +184,17 @@ 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); + 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; value = (u64)(mpidr & GENMASK(23, 0)) << 32; value |= ((target_vcpu_id & 0xffff) << 8); - if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1) + + if (addr == last_rdist_typer) value |= GICR_TYPER_LAST; if (vgic_has_its(vcpu->kvm)) value |= GICR_TYPER_PLPIS; -- cgit v1.1 From 028bf278d31a0d04b096ebb5340949e9fc9e2010 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 22 May 2018 09:55:11 +0200 Subject: KVM: arm/arm64: Adapt vgic_v3_check_base to multiple rdist regions vgic_v3_check_base() currently only handles the case of a unique legacy redistributor region whose size is not explicitly set but inferred, instead, from the number of online vcpus. We adapt it to handle the case of multiple redistributor regions with explicitly defined size. We rely on two new helpers: - vgic_v3_rdist_overlap() is used to detect overlap with the dist region if defined - vgic_v3_rd_region_size computes the size of the redist region, would it be a legacy unique region or a new explicitly sized region. Signed-off-by: Eric Auger Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic/vgic-v3.c | 49 +++++++++++++++++++++++++++++---------------- virt/kvm/arm/vgic/vgic.h | 10 +++++++++ 2 files changed, 42 insertions(+), 17 deletions(-) (limited to 'virt') diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 2a11fe8..ce4476a 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -419,6 +419,29 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) return 0; } +/** + * vgic_v3_rdist_overlap - check if a region overlaps with any + * existing redistributor region + * + * @kvm: kvm handle + * @base: base of the region + * @size: size of region + * + * Return: true if there is an overlap + */ +bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size) +{ + struct vgic_dist *d = &kvm->arch.vgic; + struct vgic_redist_region *rdreg; + + list_for_each_entry(rdreg, &d->rd_regions, list) { + if ((base + size > rdreg->base) && + (base < rdreg->base + vgic_v3_rd_region_size(kvm, rdreg))) + return true; + } + return false; +} + /* * Check for overlapping regions and for regions crossing the end of memory * for base addresses which have already been set. @@ -426,31 +449,23 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) bool vgic_v3_check_base(struct kvm *kvm) { struct vgic_dist *d = &kvm->arch.vgic; - gpa_t redist_size = KVM_VGIC_V3_REDIST_SIZE; - struct vgic_redist_region *rdreg = - list_first_entry(&d->rd_regions, - struct vgic_redist_region, list); - - redist_size *= atomic_read(&kvm->online_vcpus); + struct vgic_redist_region *rdreg; if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base) return false; - if (rdreg && (rdreg->base + redist_size < rdreg->base)) - return false; - - /* Both base addresses must be set to check if they overlap */ - if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) || !rdreg) - return true; - - if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE <= rdreg->base) - return true; + list_for_each_entry(rdreg, &d->rd_regions, list) { + if (rdreg->base + vgic_v3_rd_region_size(kvm, rdreg) < + rdreg->base) + return false; + } - if (rdreg->base + redist_size <= d->vgic_dist_base) + if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base)) return true; - return false; + return !vgic_v3_rdist_overlap(kvm, d->vgic_dist_base, + KVM_VGIC_V3_DIST_SIZE); } /** diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index fddd57f..e9f1926 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -276,6 +276,16 @@ vgic_v3_redist_region_full(struct vgic_redist_region *region) struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rdregs); +static inline size_t +vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) +{ + if (!rdreg->count) + return atomic_read(&kvm->online_vcpus) * KVM_VGIC_V3_REDIST_SIZE; + else + return rdreg->count * KVM_VGIC_V3_REDIST_SIZE; +} +bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); + int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq **irq); struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi); -- cgit v1.1 From ccc27bf5be7b78f64b67902bf27f6ef484bedc2c Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 22 May 2018 09:55:12 +0200 Subject: KVM: arm/arm64: Helper to register a new redistributor region We introduce a new helper that creates and inserts a new redistributor region into the rdist region list. This helper both handles the case where the redistributor region size is known at registration time and the legacy case where it is not (eventually depending on the number of online vcpus). Depending on pfns, we perform all the possible checks that we can do: - end of memory crossing - incorrect alignment of the base address - collision with distributor region if already defined - collision with already registered rdist regions - check of the new index Rdist regions must be inserted by increasing order of indices. Indices must be contiguous. Signed-off-by: Eric Auger Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic/vgic-mmio-v3.c | 89 ++++++++++++++++++++++++++++++++-------- virt/kvm/arm/vgic/vgic.h | 8 ++++ 2 files changed, 81 insertions(+), 16 deletions(-) (limited to 'virt') diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index ce5c927..3dbc057 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -680,14 +680,63 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm) return ret; } -int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr) +/** + * vgic_v3_insert_redist_region - Insert 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 + * (ie. count != 0). The list is sorted by rdist region index. + * + * @kvm: kvm handle + * @index: redist region index + * @base: base of the new rdist region + * @count: number of redistributors the region is made of (0 in the old style + * single region, whose size is induced from the number of vcpus) + * + * 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) { - struct vgic_dist *vgic = &kvm->arch.vgic; + struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; + struct list_head *rd_regions = &d->rd_regions; + size_t size = count * KVM_VGIC_V3_REDIST_SIZE; int ret; - /* vgic_check_ioaddr makes sure we don't do this twice */ - if (!list_empty(&vgic->rd_regions)) + /* single rdist region already set ?*/ + if (!count && !list_empty(rd_regions)) + return -EINVAL; + + /* cross the end of memory ? */ + if (base + size < base) + return -EINVAL; + + if (list_empty(rd_regions)) { + if (index != 0) + return -EINVAL; + } else { + rdreg = list_last_entry(rd_regions, + struct vgic_redist_region, list); + if (index != rdreg->index + 1) + return -EINVAL; + + /* Cannot add an explicitly sized regions after legacy region */ + if (!rdreg->count) + return -EINVAL; + } + + /* + * For legacy single-region redistributor regions (!count), + * check that the redistributor region does not overlap with the + * distributor's address space. + */ + if (!count && !IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && + vgic_dist_overlap(kvm, base, size)) + return -EINVAL; + + /* collision with any other rdist region? */ + if (vgic_v3_rdist_overlap(kvm, base, size)) return -EINVAL; rdreg = kzalloc(sizeof(*rdreg), GFP_KERNEL); @@ -696,17 +745,29 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr) rdreg->base = VGIC_ADDR_UNDEF; - ret = vgic_check_ioaddr(kvm, &rdreg->base, addr, SZ_64K); + ret = vgic_check_ioaddr(kvm, &rdreg->base, base, SZ_64K); if (ret) - goto out; + goto free; - rdreg->base = addr; - if (!vgic_v3_check_base(kvm)) { - ret = -EINVAL; - goto out; - } + rdreg->base = base; + rdreg->count = count; + rdreg->free_index = 0; + rdreg->index = index; - list_add(&rdreg->list, &vgic->rd_regions); + list_add_tail(&rdreg->list, rd_regions); + return 0; +free: + kfree(rdreg); + return ret; +} + +int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr) +{ + int ret; + + ret = vgic_v3_insert_redist_region(kvm, 0, addr, 0); + if (ret) + return ret; /* * Register iodevs for each existing VCPU. Adding more VCPUs @@ -717,10 +778,6 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr) return ret; return 0; - -out: - kfree(rdreg); - return ret; } int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index e9f1926..1c8af4e 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -286,6 +286,14 @@ vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) } bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); +static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size) +{ + struct vgic_dist *d = &kvm->arch.vgic; + + return (base + size > d->vgic_dist_base) && + (base < d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE); +} + int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq **irq); struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi); -- cgit v1.1 From 5ec17fbac6713be82b90f54d5a31251803fd8de5 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 22 May 2018 09:55:13 +0200 Subject: KVM: arm/arm64: Remove kvm_vgic_vcpu_early_init kvm_vgic_vcpu_early_init gets called after kvm_vgic_cpu_init which is confusing. The call path is as follows: kvm_vm_ioctl_create_vcpu |_ kvm_arch_cpu_create |_ kvm_vcpu_init |_ kvm_arch_vcpu_init |_ kvm_vgic_vcpu_init |_ kvm_arch_vcpu_postcreate |_ kvm_vgic_vcpu_early_init Static initialization currently done in kvm_vgic_vcpu_early_init() can be moved to kvm_vgic_vcpu_init(). So let's move the code and remove kvm_vgic_vcpu_early_init(). kvm_arch_vcpu_postcreate() does nothing. Signed-off-by: Eric Auger Signed-off-by: Marc Zyngier --- virt/kvm/arm/arm.c | 1 - virt/kvm/arm/vgic/vgic-init.c | 80 ++++++++++++++++++++----------------------- 2 files changed, 37 insertions(+), 44 deletions(-) (limited to 'virt') diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 39e7771..126b98f 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -292,7 +292,6 @@ out: void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { - kvm_vgic_vcpu_early_init(vcpu); } void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index 8901b2d..272af97 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -44,7 +44,7 @@ * * CPU Interface: * - * - kvm_vgic_vcpu_early_init(): initialization of static data that + * - kvm_vgic_vcpu_init(): initialization of static data that * doesn't depend on any sizing information or emulation type. No * allocation is allowed there. */ @@ -67,46 +67,6 @@ void kvm_vgic_early_init(struct kvm *kvm) spin_lock_init(&dist->lpi_list_lock); } -/** - * kvm_vgic_vcpu_early_init() - Initialize static VGIC VCPU data structures - * @vcpu: The VCPU whose VGIC data structures whould be initialized - * - * Only do initialization, but do not actually enable the VGIC CPU interface - * yet. - */ -void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - int i; - - INIT_LIST_HEAD(&vgic_cpu->ap_list_head); - spin_lock_init(&vgic_cpu->ap_list_lock); - - /* - * Enable and configure all SGIs to be edge-triggered and - * configure all PPIs as level-triggered. - */ - for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { - struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; - - INIT_LIST_HEAD(&irq->ap_list); - spin_lock_init(&irq->irq_lock); - irq->intid = i; - irq->vcpu = NULL; - irq->target_vcpu = vcpu; - irq->targets = 1U << vcpu->vcpu_id; - kref_init(&irq->refcount); - if (vgic_irq_is_sgi(i)) { - /* SGIs */ - irq->enabled = 1; - irq->config = VGIC_CONFIG_EDGE; - } else { - /* PPIs */ - irq->config = VGIC_CONFIG_LEVEL; - } - } -} - /* CREATION */ /** @@ -224,13 +184,47 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) } /** - * kvm_vgic_vcpu_init() - Register VCPU-specific KVM iodevs + * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data + * structures and register VCPU-specific KVM iodevs + * * @vcpu: pointer to the VCPU being created and initialized + * + * Only do initialization, but do not actually enable the + * VGIC CPU interface */ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) { - int ret = 0; + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + int ret = 0; + int i; + + INIT_LIST_HEAD(&vgic_cpu->ap_list_head); + spin_lock_init(&vgic_cpu->ap_list_lock); + + /* + * Enable and configure all SGIs to be edge-triggered and + * configure all PPIs as level-triggered. + */ + for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { + struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; + + INIT_LIST_HEAD(&irq->ap_list); + spin_lock_init(&irq->irq_lock); + irq->intid = i; + irq->vcpu = NULL; + irq->target_vcpu = vcpu; + irq->targets = 1U << vcpu->vcpu_id; + kref_init(&irq->refcount); + if (vgic_irq_is_sgi(i)) { + /* SGIs */ + irq->enabled = 1; + irq->config = VGIC_CONFIG_EDGE; + } else { + /* PPIs */ + irq->config = VGIC_CONFIG_LEVEL; + } + } if (!irqchip_in_kernel(vcpu->kvm)) return 0; -- cgit v1.1 From c011f4ea106b94e5499358b62d8c2d74f7e184f9 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 22 May 2018 09:55:14 +0200 Subject: KVM: arm/arm64: Check vcpu redist base before registering an iodev As we are going to register several redist regions, vgic_register_all_redist_iodevs() may be called several times. We need to register a redist_iodev for a given vcpu only once. So let's check if the base address has already been set. Initialize this latter in kvm_vgic_vcpu_init(). Signed-off-by: Eric Auger Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic/vgic-init.c | 3 +++ virt/kvm/arm/vgic/vgic-mmio-v3.c | 3 +++ 2 files changed, 6 insertions(+) (limited to 'virt') diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index 272af97..2673efc 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -199,6 +199,9 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) int ret = 0; int i; + vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + vgic_cpu->sgi_iodev.base_addr = VGIC_ADDR_UNDEF; + INIT_LIST_HEAD(&vgic_cpu->ap_list_head); spin_lock_init(&vgic_cpu->ap_list_lock); diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index 3dbc057..1c6c535 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -592,6 +592,9 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) gpa_t rd_base, sgi_base; int ret; + if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) + return 0; + /* * We may be creating VCPUs before having set the base address for the * redistributor region, in which case we will come back to this -- cgit v1.1 From c957a6d63e176e1ca068f935ca1efc439581aa6c Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 22 May 2018 09:55:15 +0200 Subject: KVM: arm/arm64: Check all vcpu redistributors are set on map_resources On vcpu first run, we eventually know the actual number of vcpus. This is a synchronization point to check all redistributors were assigned. On kvm_vgic_map_resources() we check both dist and redist were set, eventually check potential base address inconsistencies. Signed-off-by: Eric Auger Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic/vgic-v3.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'virt') diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index ce4476a..eb32b21 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -493,16 +493,25 @@ struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions) int vgic_v3_map_resources(struct kvm *kvm) { - int ret = 0; struct vgic_dist *dist = &kvm->arch.vgic; - struct vgic_redist_region *rdreg = - list_first_entry(&dist->rd_regions, - struct vgic_redist_region, list); + struct kvm_vcpu *vcpu; + int ret = 0; + int c; if (vgic_ready(kvm)) goto out; - if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || !rdreg) { + 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); + ret = -ENXIO; + goto out; + } + } + + if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { kvm_err("Need to set vgic distributor addresses first\n"); ret = -ENXIO; goto out; -- cgit v1.1 From 04c11093222579128ed4c0448024190ec7f4e212 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 22 May 2018 09:55:17 +0200 Subject: KVM: arm/arm64: Implement KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION Now all the internals are ready to handle multiple redistributor regions, let's allow the userspace to register them. Signed-off-by: Eric Auger Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic/vgic-kvm-device.c | 40 ++++++++++++++++++++++++++++++++++++- virt/kvm/arm/vgic/vgic-mmio-v3.c | 4 ++-- virt/kvm/arm/vgic/vgic-v3.c | 14 +++++++++++++ virt/kvm/arm/vgic/vgic.h | 13 +++++++++++- 4 files changed, 67 insertions(+), 4 deletions(-) (limited to 'virt') diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c index 76ab369..6ada243 100644 --- a/virt/kvm/arm/vgic/vgic-kvm-device.c +++ b/virt/kvm/arm/vgic/vgic-kvm-device.c @@ -92,7 +92,7 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) if (r) break; if (write) { - r = vgic_v3_set_redist_base(kvm, *addr); + r = vgic_v3_set_redist_base(kvm, 0, *addr, 0); goto out; } rdreg = list_first_entry(&vgic->rd_regions, @@ -103,6 +103,43 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) addr_ptr = &rdreg->base; break; } + case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: + { + struct vgic_redist_region *rdreg; + u8 index; + + r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); + if (r) + break; + + index = *addr & KVM_VGIC_V3_RDIST_INDEX_MASK; + + if (write) { + gpa_t base = *addr & KVM_VGIC_V3_RDIST_BASE_MASK; + u32 count = (*addr & KVM_VGIC_V3_RDIST_COUNT_MASK) + >> KVM_VGIC_V3_RDIST_COUNT_SHIFT; + u8 flags = (*addr & KVM_VGIC_V3_RDIST_FLAGS_MASK) + >> KVM_VGIC_V3_RDIST_FLAGS_SHIFT; + + if (!count || flags) + r = -EINVAL; + else + r = vgic_v3_set_redist_base(kvm, index, + base, count); + goto out; + } + + rdreg = vgic_v3_rdist_region_from_index(kvm, index); + if (!rdreg) { + r = -ENOENT; + goto out; + } + + *addr = index; + *addr |= rdreg->base; + *addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT; + goto out; + } default: r = -ENODEV; } @@ -674,6 +711,7 @@ static int vgic_v3_has_attr(struct kvm_device *dev, switch (attr->attr) { case KVM_VGIC_V3_ADDR_TYPE_DIST: case KVM_VGIC_V3_ADDR_TYPE_REDIST: + case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: return 0; } break; diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index 1c6c535..2877840 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -764,11 +764,11 @@ free: return ret; } -int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr) +int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) { int ret; - ret = vgic_v3_insert_redist_region(kvm, 0, addr, 0); + ret = vgic_v3_insert_redist_region(kvm, index, addr, count); if (ret) return ret; diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index eb32b21..7c6d278 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -491,6 +491,20 @@ struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions) return NULL; } +struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, + u32 index) +{ + struct list_head *rd_regions = &kvm->arch.vgic.rd_regions; + struct vgic_redist_region *rdreg; + + list_for_each_entry(rdreg, rd_regions, list) { + if (rdreg->index == index) + return rdreg; + } + return NULL; +} + + int vgic_v3_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 1c8af4e..6879cf4 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -96,6 +96,13 @@ /* we only support 64 kB translation table page size */ #define KVM_ITS_L1E_ADDR_MASK GENMASK_ULL(51, 16) +#define KVM_VGIC_V3_RDIST_INDEX_MASK GENMASK_ULL(11, 0) +#define KVM_VGIC_V3_RDIST_FLAGS_MASK GENMASK_ULL(15, 12) +#define KVM_VGIC_V3_RDIST_FLAGS_SHIFT 12 +#define KVM_VGIC_V3_RDIST_BASE_MASK GENMASK_ULL(51, 16) +#define KVM_VGIC_V3_RDIST_COUNT_MASK GENMASK_ULL(63, 52) +#define KVM_VGIC_V3_RDIST_COUNT_SHIFT 52 + /* Requires the irq_lock to be held by the caller. */ static inline bool irq_is_pending(struct vgic_irq *irq) { @@ -215,7 +222,7 @@ int vgic_v3_probe(const struct gic_kvm_info *info); int vgic_v3_map_resources(struct kvm *kvm); int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq); int vgic_v3_save_pending_tables(struct kvm *kvm); -int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr); +int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count); int vgic_register_redist_iodev(struct kvm_vcpu *vcpu); bool vgic_v3_check_base(struct kvm *kvm); @@ -284,6 +291,10 @@ vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) else return rdreg->count * KVM_VGIC_V3_REDIST_SIZE; } + +struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, + u32 index); + bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size) -- cgit v1.1 From 7053df4edb3ae3ae15c316fe49122c0b3936e9dd Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 16 May 2018 17:21:28 +0200 Subject: KVM: introduce kvm_make_vcpus_request_mask() API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Hyper-V style PV TLB flush hypercalls inmplementation will use this API. To avoid memory allocation in CONFIG_CPUMASK_OFFSTACK case add cpumask_var_t argument. Signed-off-by: Vitaly Kuznetsov Signed-off-by: Radim Krčmář --- virt/kvm/kvm_main.c | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c7b2e92..b125d94 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -203,29 +203,47 @@ static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) return true; } -bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) +bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap, cpumask_var_t tmp) { int i, cpu, me; - cpumask_var_t cpus; - bool called; struct kvm_vcpu *vcpu; - - zalloc_cpumask_var(&cpus, GFP_ATOMIC); + bool called; me = get_cpu(); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!test_bit(i, vcpu_bitmap)) + continue; + kvm_make_request(req, vcpu); cpu = vcpu->cpu; if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) continue; - if (cpus != NULL && cpu != -1 && cpu != me && + if (tmp != NULL && cpu != -1 && cpu != me && kvm_request_needs_ipi(vcpu, req)) - __cpumask_set_cpu(cpu, cpus); + __cpumask_set_cpu(cpu, tmp); } - called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); + + called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT)); put_cpu(); + + return called; +} + +bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) +{ + cpumask_var_t cpus; + bool called; + static unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)] + = {[0 ... BITS_TO_LONGS(KVM_MAX_VCPUS)-1] = ULONG_MAX}; + + zalloc_cpumask_var(&cpus, GFP_ATOMIC); + + called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap, cpus); + free_cpumask_var(cpus); return called; } -- cgit v1.1 From 1499fa809e9e6713952ef84a7e9d51606881681f Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Thu, 19 Apr 2018 00:49:58 +0530 Subject: kvm: Change return type to vm_fault_t Use new return type vm_fault_t for fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. commit 1c8f422059ae ("mm: change return type to vm_fault_t") Signed-off-by: Souptick Joarder Reviewed-by: Matthew Wilcox Signed-off-by: Paolo Bonzini --- virt/kvm/arm/arm.c | 2 +- virt/kvm/kvm_main.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'virt') diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 126b98f..3d92214 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -165,7 +165,7 @@ int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) return 0; } -int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) +vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c5f6a55..8938c9e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2358,7 +2358,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) } EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); -static int kvm_vcpu_fault(struct vm_fault *vmf) +static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf) { struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data; struct page *page; -- cgit v1.1 From d1e5b0e98ea27b4f17871dc4e8ea4b0447e35221 Mon Sep 17 00:00:00 2001 From: Marc Orr Date: Tue, 15 May 2018 04:37:37 -0700 Subject: kvm: Make VM ioctl do valloc for some archs The kvm struct has been bloating. For example, it's tens of kilo-bytes for x86, which turns out to be a large amount of memory to allocate contiguously via kzalloc. Thus, this patch does the following: 1. Uses architecture-specific routines to allocate the kvm struct via vzalloc for x86. 2. Switches arm to __KVM_HAVE_ARCH_VM_ALLOC so that it can use vzalloc when has_vhe() is true. Other architectures continue to default to kalloc, as they have a dependency on kalloc or have a small-enough struct kvm. Signed-off-by: Marc Orr Reviewed-by: Marc Zyngier Signed-off-by: Paolo Bonzini --- virt/kvm/arm/arm.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'virt') diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 3d92214..72be779 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -251,6 +251,21 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } +struct kvm *kvm_arch_alloc_vm(void) +{ + if (!has_vhe()) + return kzalloc(sizeof(struct kvm), GFP_KERNEL); + + return vzalloc(sizeof(struct kvm)); +} + +void kvm_arch_free_vm(struct kvm *kvm) +{ + if (!has_vhe()) + kfree(kvm); + else + vfree(kvm); +} struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { -- cgit v1.1 From 929f45e32499171ce3e5a15db972256eac513ad7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 29 May 2018 18:22:04 +0200 Subject: kvm: no need to check return value of debugfs_create functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. This cleans up the error handling a lot, as this code will never get hit. Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Christoffer Dall Cc: Marc Zyngier Cc: Paolo Bonzini Cc: "Radim KrÄmář" Cc: Arvind Yadav Cc: Eric Auger Cc: Andre Przywara Cc: kvm-ppc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-kernel@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: kvmarm@lists.cs.columbia.edu Cc: kvm@vger.kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Paolo Bonzini --- virt/kvm/arm/vgic/vgic-debug.c | 17 ++++------------- virt/kvm/arm/vgic/vgic.h | 4 ++-- virt/kvm/kvm_main.c | 40 ++++++++-------------------------------- 3 files changed, 14 insertions(+), 47 deletions(-) (limited to 'virt') diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c index 4ffc0b5..c589d4c 100644 --- a/virt/kvm/arm/vgic/vgic-debug.c +++ b/virt/kvm/arm/vgic/vgic-debug.c @@ -264,21 +264,12 @@ static const struct file_operations vgic_debug_fops = { .release = seq_release }; -int vgic_debug_init(struct kvm *kvm) +void vgic_debug_init(struct kvm *kvm) { - if (!kvm->debugfs_dentry) - return -ENOENT; - - if (!debugfs_create_file("vgic-state", 0444, - kvm->debugfs_dentry, - kvm, - &vgic_debug_fops)) - return -ENOMEM; - - return 0; + debugfs_create_file("vgic-state", 0444, kvm->debugfs_dentry, kvm, + &vgic_debug_fops); } -int vgic_debug_destroy(struct kvm *kvm) +void vgic_debug_destroy(struct kvm *kvm) { - return 0; } diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 6879cf4..ead00b2 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -250,8 +250,8 @@ void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); int vgic_lazy_init(struct kvm *kvm); int vgic_init(struct kvm *kvm); -int vgic_debug_init(struct kvm *kvm); -int vgic_debug_destroy(struct kvm *kvm); +void vgic_debug_init(struct kvm *kvm); +void vgic_debug_destroy(struct kvm *kvm); bool lock_all_vcpus(struct kvm *kvm); void unlock_all_vcpus(struct kvm *kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8938c9e..aa7da1d8e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -590,10 +590,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) return 0; snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd); - kvm->debugfs_dentry = debugfs_create_dir(dir_name, - kvm_debugfs_dir); - if (!kvm->debugfs_dentry) - return -ENOMEM; + kvm->debugfs_dentry = debugfs_create_dir(dir_name, kvm_debugfs_dir); kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries, sizeof(*kvm->debugfs_stat_data), @@ -609,11 +606,8 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) stat_data->kvm = kvm; stat_data->offset = p->offset; kvm->debugfs_stat_data[p - debugfs_entries] = stat_data; - if (!debugfs_create_file(p->name, 0644, - kvm->debugfs_dentry, - stat_data, - stat_fops_per_vm[p->kind])) - return -ENOMEM; + debugfs_create_file(p->name, 0644, kvm->debugfs_dentry, + stat_data, stat_fops_per_vm[p->kind]); } return 0; } @@ -3919,29 +3913,18 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) kfree(env); } -static int kvm_init_debug(void) +static void kvm_init_debug(void) { - int r = -EEXIST; struct kvm_stats_debugfs_item *p; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); - if (kvm_debugfs_dir == NULL) - goto out; kvm_debugfs_num_entries = 0; for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) { - if (!debugfs_create_file(p->name, 0644, kvm_debugfs_dir, - (void *)(long)p->offset, - stat_fops[p->kind])) - goto out_dir; + debugfs_create_file(p->name, 0644, kvm_debugfs_dir, + (void *)(long)p->offset, + stat_fops[p->kind]); } - - return 0; - -out_dir: - debugfs_remove_recursive(kvm_debugfs_dir); -out: - return r; } static int kvm_suspend(void) @@ -4069,20 +4052,13 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; - r = kvm_init_debug(); - if (r) { - pr_err("kvm: create debugfs files failed\n"); - goto out_undebugfs; - } + kvm_init_debug(); r = kvm_vfio_ops_init(); WARN_ON(r); return 0; -out_undebugfs: - unregister_syscore_ops(&kvm_syscore_ops); - misc_deregister(&kvm_dev); out_unreg: kvm_async_pf_deinit(); out_free: -- cgit v1.1