From 0c0672922dcc70ffba11d96385e98e42fb3ae08d Mon Sep 17 00:00:00 2001 From: Alexander Spyridakis Date: Fri, 4 Sep 2015 17:06:24 +0200 Subject: arm/arm64: KVM: Fix PSCI affinity info return value for non valid cores If a guest requests the affinity info for a non-existing vCPU we need to properly return an error, instead of erroneously reporting an off state. Signed-off-by: Alexander Spyridakis Signed-off-by: Alvise Rigo Acked-by: Mark Rutland Reviewed-by: Marc Zyngier Signed-off-by: Marc Zyngier --- arch/arm/kvm/psci.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 4b94b513168d..ad6f6424f1d1 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -126,7 +126,7 @@ 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; + int i, matching_cpus = 0; unsigned long mpidr; unsigned long target_affinity; unsigned long target_affinity_mask; @@ -151,12 +151,16 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) */ kvm_for_each_vcpu(i, tmp, kvm) { mpidr = kvm_vcpu_get_mpidr_aff(tmp); - if (((mpidr & target_affinity_mask) == target_affinity) && - !tmp->arch.pause) { - return PSCI_0_2_AFFINITY_LEVEL_ON; + if ((mpidr & target_affinity_mask) == target_affinity) { + matching_cpus++; + if (!tmp->arch.pause) + return PSCI_0_2_AFFINITY_LEVEL_ON; } } + if (!matching_cpus) + return PSCI_RET_INVALID_PARAMS; + return PSCI_0_2_AFFINITY_LEVEL_OFF; } -- cgit v1.2.3 From 62bea5bff486644ecf363fe8a1a2f6f32c614a49 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 15 Sep 2015 18:27:57 +0200 Subject: KVM: add halt_attempted_poll to VCPU stats This new statistic can help diagnosing VCPUs that, for any reason, trigger bad behavior of halt_poll_ns autotuning. For example, say halt_poll_ns = 480000, and wakeups are spaced exactly like 479us, 481us, 479us, 481us. Then KVM always fails polling and wastes 10+20+40+80+160+320+480 = 1110 microseconds out of every 479+481+479+481+479+481+479 = 3359 microseconds. The VCPU then is consuming about 30% more CPU than it would use without polling. This would show as an abnormally high number of attempted polling compared to the successful polls. Acked-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- arch/arm/include/asm/kvm_host.h | 1 + arch/arm64/include/asm/kvm_host.h | 1 + arch/mips/include/asm/kvm_host.h | 1 + arch/mips/kvm/mips.c | 1 + arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/kvm/book3s.c | 1 + arch/powerpc/kvm/booke.c | 1 + arch/s390/include/asm/kvm_host.h | 1 + arch/s390/kvm/kvm-s390.c | 1 + arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/x86.c | 1 + virt/kvm/kvm_main.c | 1 + 12 files changed, 12 insertions(+) (limited to 'arch/arm') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index dcba0fa5176e..687ddeba3611 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -148,6 +148,7 @@ struct kvm_vm_stat { struct kvm_vcpu_stat { u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; }; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 415938dc45cf..486594583cc6 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -195,6 +195,7 @@ struct kvm_vm_stat { struct kvm_vcpu_stat { u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; }; diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index e8c8d9d0c45f..3a54dbca9f7e 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -128,6 +128,7 @@ struct kvm_vcpu_stat { u32 msa_disabled_exits; u32 flush_dcache_exits; u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; }; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index cd4c129ce743..49ff3bfc007e 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -55,6 +55,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "msa_disabled", VCPU_STAT(msa_disabled_exits), KVM_STAT_VCPU }, { "flush_dcache", VCPU_STAT(flush_dcache_exits), KVM_STAT_VCPU }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll), KVM_STAT_VCPU }, + { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), KVM_STAT_VCPU }, { "halt_wakeup", VCPU_STAT(halt_wakeup), KVM_STAT_VCPU }, {NULL} }; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 98eebbf66340..195886a583ba 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -108,6 +108,7 @@ struct kvm_vcpu_stat { u32 dec_exits; u32 ext_intr_exits; u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; u32 dbell_exits; u32 gdbell_exits; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index d75bf325f54a..cf009167d208 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -53,6 +53,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "ext_intr", VCPU_STAT(ext_intr_exits) }, { "queue_intr", VCPU_STAT(queue_intr) }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll), }, + { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "pf_storage", VCPU_STAT(pf_storage) }, { "sp_storage", VCPU_STAT(sp_storage) }, diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index ae458f0fd061..fd5875179e5c 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -63,6 +63,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "dec", VCPU_STAT(dec_exits) }, { "ext_intr", VCPU_STAT(ext_intr_exits) }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, + { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "doorbell", VCPU_STAT(dbell_exits) }, { "guest doorbell", VCPU_STAT(gdbell_exits) }, diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 3d012e071647..6ce4a0b7e8da 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -210,6 +210,7 @@ struct kvm_vcpu_stat { u32 exit_validity; u32 exit_instruction; u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; u32 instruction_lctl; u32 instruction_lctlg; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index c91eb941b444..2f807ab1725e 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -63,6 +63,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "exit_program_interruption", VCPU_STAT(exit_program_interruption) }, { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, + { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "instruction_lctlg", VCPU_STAT(instruction_lctlg) }, { "instruction_lctl", VCPU_STAT(instruction_lctl) }, diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c12e845f59e6..349f80a82b82 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -711,6 +711,7 @@ struct kvm_vcpu_stat { u32 nmi_window_exits; u32 halt_exits; u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; u32 request_irq_exits; u32 irq_exits; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a60bdbccff51..6bbb0dfb99d0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -149,6 +149,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "nmi_window", VCPU_STAT(nmi_window_exits) }, { "halt_exits", VCPU_STAT(halt_exits) }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, + { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "hypercalls", VCPU_STAT(hypercalls) }, { "request_irq", VCPU_STAT(request_irq_exits) }, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9af68db73c6a..04146a2e1d81 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2004,6 +2004,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) if (vcpu->halt_poll_ns) { ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns); + ++vcpu->stat.halt_attempted_poll; do { /* * This sets KVM_REQ_UNHALT if an interrupt -- cgit v1.2.3 From ca09f02f122b2ecb0f5ddfc5fd47b29ed657d4fd Mon Sep 17 00:00:00 2001 From: Marek Majtyka Date: Wed, 16 Sep 2015 12:04:55 +0200 Subject: arm: KVM: Fix incorrect device to IPA mapping A critical bug has been found in device memory stage1 translation for VMs with more then 4GB of address space. Once vm_pgoff size is smaller then pa (which is true for LPAE case, u32 and u64 respectively) some more significant bits of pa may be lost as a shift operation is performed on u32 and later cast onto u64. Example: vm_pgoff(u32)=0x00210030, PAGE_SHIFT=12 expected pa(u64): 0x0000002010030000 produced pa(u64): 0x0000000010030000 The fix is to change the order of operations (casting first onto phys_addr_t and then shifting). Reviewed-by: Marc Zyngier [maz: fixed changelog and patch formatting] Cc: stable@vger.kernel.org Signed-off-by: Marek Majtyka Signed-off-by: Marc Zyngier --- arch/arm/kvm/mmu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 7b4201294187..6984342da13d 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1792,8 +1792,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (vma->vm_flags & VM_PFNMAP) { gpa_t gpa = mem->guest_phys_addr + (vm_start - mem->userspace_addr); - phys_addr_t pa = (vma->vm_pgoff << PAGE_SHIFT) + - vm_start - vma->vm_start; + 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) -- cgit v1.2.3 From c2f58514cfb374d5368c9da945f1765cd48eb0da Mon Sep 17 00:00:00 2001 From: Pavel Fedin Date: Wed, 5 Aug 2015 11:53:57 +0100 Subject: arm/arm64: KVM: vgic: Check for !irqchip_in_kernel() when mapping resources Until b26e5fdac43c ("arm/arm64: KVM: introduce per-VM ops"), kvm_vgic_map_resources() used to include a check on irqchip_in_kernel(), and vgic_v2_map_resources() still has it. But now vm_ops are not initialized until we call kvm_vgic_create(). Therefore kvm_vgic_map_resources() can being called without a VGIC, and we die because vm_ops.map_resources is NULL. Fixing this restores QEMU's kernel-irqchip=off option to a working state, allowing to use GIC emulation in userspace. Fixes: b26e5fdac43c ("arm/arm64: KVM: introduce per-VM ops") Cc: stable@vger.kernel.org Signed-off-by: Pavel Fedin [maz: reworked commit message] Signed-off-by: Marc Zyngier --- arch/arm/kvm/arm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index ce404a5c3062..dc017adfddc8 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -446,7 +446,7 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) * Map the VGIC hardware resources before running a vcpu the first * time on this VM. */ - if (unlikely(!vgic_ready(kvm))) { + if (unlikely(irqchip_in_kernel(kvm) && !vgic_ready(kvm))) { ret = kvm_vgic_map_resources(kvm); if (ret) return ret; -- cgit v1.2.3 From 688bc577ac42ae3d07c889a1f0a72f0b23763d58 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 16 Sep 2015 16:18:59 +0100 Subject: arm: KVM: Disable virtual timer even if the guest is not using it When running a guest with the architected timer disabled (with QEMU and the kernel_irqchip=off option, for example), it is important to make sure the timer gets turned off. Otherwise, the guest may try to enable it anyway, leading to a screaming HW interrupt. The fix is to unconditionally turn off the virtual timer on guest exit. Cc: stable@vger.kernel.org Signed-off-by: Marc Zyngier --- arch/arm/kvm/interrupts_head.S | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 702740d37465..51a59504bef4 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -515,8 +515,7 @@ ARM_BE8(rev r6, r6 ) mrc p15, 0, r2, c14, c3, 1 @ CNTV_CTL str r2, [vcpu, #VCPU_TIMER_CNTV_CTL] - bic r2, #1 @ Clear ENABLE - mcr p15, 0, r2, c14, c3, 1 @ CNTV_CTL + isb mrrc p15, 3, rr_lo_hi(r2, r3), c14 @ CNTV_CVAL @@ -529,6 +528,9 @@ ARM_BE8(rev r6, r6 ) mcrr p15, 4, r2, r2, c14 @ CNTVOFF 1: + mov r2, #0 @ Clear ENABLE + mcr p15, 0, r2, c14, c3, 1 @ CNTV_CTL + @ Allow physical timer/counter access for the host mrc p15, 4, r2, c14, c1, 0 @ CNTHCTL orr r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN) -- cgit v1.2.3 From ef748917b529847277f07c98c55e1c0ce416449f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 2 Sep 2015 14:31:21 +0800 Subject: arm/arm64: KVM: Remove 'config KVM_ARM_MAX_VCPUS' This patch removes config option of KVM_ARM_MAX_VCPUS, and like other ARCHs, just choose the maximum allowed value from hardware, and follows the reasons: 1) from distribution view, the option has to be defined as the max allowed value because it need to meet all kinds of virtulization applications and need to support most of SoCs; 2) using a bigger value doesn't introduce extra memory consumption, and the help text in Kconfig isn't accurate because kvm_vpu structure isn't allocated until request of creating VCPU is sent from QEMU; 3) the main effect is that the field of vcpus[] in 'struct kvm' becomes a bit bigger(sizeof(void *) per vcpu) and need more cache lines to hold the structure, but 'struct kvm' is one generic struct, and it has worked well on other ARCHs already in this way. Also, the world switch frequecy is often low, for example, it is ~2000 when running kernel building load in VM from APM xgene KVM host, so the effect is very small, and the difference can't be observed in my test at all. Cc: Dann Frazier Signed-off-by: Ming Lei Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_host.h | 8 ++------ arch/arm/kvm/Kconfig | 11 ----------- arch/arm64/include/asm/kvm_host.h | 8 ++------ arch/arm64/kvm/Kconfig | 11 ----------- include/kvm/arm_vgic.h | 6 +----- virt/kvm/arm/vgic-v3.c | 2 +- 6 files changed, 6 insertions(+), 40 deletions(-) (limited to 'arch/arm') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index dcba0fa5176e..c8c226a19dbe 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -29,12 +29,6 @@ #define __KVM_HAVE_ARCH_INTC_INITIALIZED -#if defined(CONFIG_KVM_ARM_MAX_VCPUS) -#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS -#else -#define KVM_MAX_VCPUS 0 -#endif - #define KVM_USER_MEM_SLOTS 32 #define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -44,6 +38,8 @@ #include +#define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS + u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode); int __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index bfb915d05665..210eccadb69a 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -45,15 +45,4 @@ config KVM_ARM_HOST ---help--- Provides host support for ARM processors. -config KVM_ARM_MAX_VCPUS - int "Number maximum supported virtual CPUs per VM" - depends on KVM_ARM_HOST - default 4 - help - Static number of max supported virtual CPUs per VM. - - If you choose a high number, the vcpu structures will be quite - large, so only choose a reasonable number that you expect to - actually use. - endif # VIRTUALIZATION diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 415938dc45cf..3fb58ea944eb 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -30,12 +30,6 @@ #define __KVM_HAVE_ARCH_INTC_INITIALIZED -#if defined(CONFIG_KVM_ARM_MAX_VCPUS) -#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS -#else -#define KVM_MAX_VCPUS 0 -#endif - #define KVM_USER_MEM_SLOTS 32 #define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -43,6 +37,8 @@ #include #include +#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS + #define KVM_VCPU_MAX_FEATURES 3 int __attribute_const__ kvm_target_cpu(void); diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index bfffe8f4bd53..5c7e920e4861 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -41,15 +41,4 @@ config KVM_ARM_HOST ---help--- Provides host support for ARM processors. -config KVM_ARM_MAX_VCPUS - int "Number maximum supported virtual CPUs per VM" - depends on KVM_ARM_HOST - default 4 - help - Static number of max supported virtual CPUs per VM. - - If you choose a high number, the vcpu structures will be quite - large, so only choose a reasonable number that you expect to - actually use. - endif # VIRTUALIZATION diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index d901f1a47be6..4e14dac282bb 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -35,11 +35,7 @@ #define VGIC_V3_MAX_LRS 16 #define VGIC_MAX_IRQS 1024 #define VGIC_V2_MAX_CPUS 8 - -/* Sanity checks... */ -#if (KVM_MAX_VCPUS > 255) -#error Too many KVM VCPUs, the VGIC only supports up to 255 VCPUs for now -#endif +#define VGIC_V3_MAX_CPUS 255 #if (VGIC_NR_IRQS_LEGACY & 31) #error "VGIC_NR_IRQS must be a multiple of 32" diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c index afbf925b00f4..7dd5d62f10a1 100644 --- a/virt/kvm/arm/vgic-v3.c +++ b/virt/kvm/arm/vgic-v3.c @@ -288,7 +288,7 @@ int vgic_v3_probe(struct device_node *vgic_node, vgic->vctrl_base = NULL; vgic->type = VGIC_V3; - vgic->max_gic_vcpus = KVM_MAX_VCPUS; + vgic->max_gic_vcpus = VGIC_V3_MAX_CPUS; kvm_info("%s@%llx IRQ%d\n", vgic_node->name, vcpu_res.start, vgic->maint_irq); -- cgit v1.2.3