From 812756a82ea51e3c7ff7ba5e6fa3f34345234bc7 Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Tue, 14 Apr 2020 17:56:25 +0200 Subject: kvm_host: unify VM_STAT and VCPU_STAT definitions in a single place The macros VM_STAT and VCPU_STAT are redundantly implemented in multiple files, each used by a different architecure to initialize the debugfs entries for statistics. Since they all have the same purpose, they can be unified in a single common definition in include/linux/kvm_host.h Signed-off-by: Emanuele Giuseppe Esposito Message-Id: <20200414155625.20559-1-eesposit@redhat.com> Acked-by: Cornelia Huck Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01276e3d01b9..658215f6102c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1130,6 +1130,11 @@ struct kvm_stats_debugfs_item { #define KVM_DBGFS_GET_MODE(dbgfs_item) \ ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) +#define VM_STAT(n, x, ...) \ + { n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ } +#define VCPU_STAT(n, x, ...) \ + { n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ } + extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; -- cgit v1.2.3 From c36b71503a2268206ebeda6697094ffb4e7e94c2 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 16 Apr 2020 09:48:07 -0400 Subject: KVM: x86/mmu: Avoid an extra memslot lookup in try_async_pf() for L2 Create a new function kvm_is_visible_memslot() and use it from kvm_is_visible_gfn(); use the new function in try_async_pf() too, to avoid an extra memslot lookup. Opportunistically squish a multi-line comment into a single-line comment. Note, the end result, KVM_PFN_NOSLOT, is unchanged. Cc: Jim Mattson Cc: Rick Edgecombe Suggested-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 658215f6102c..7d4f1eb70274 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1357,6 +1357,12 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ +static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot) +{ + return (memslot && memslot->id < KVM_USER_MEM_SLOTS && + !(memslot->flags & KVM_MEMSLOT_INVALID)); +} + struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); -- cgit v1.2.3 From 1b94f6f81007b4afaea3480ec018bc9236148961 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Thu, 16 Apr 2020 13:10:57 +0800 Subject: KVM: Remove redundant argument to kvm_arch_vcpu_ioctl_run In earlier versions of kvm, 'kvm_run' was an independent structure and was not included in the vcpu structure. At present, 'kvm_run' is already included in the vcpu structure, so the parameter 'kvm_run' is redundant. This patch simplifies the function definition, removes the extra 'kvm_run' parameter, and extracts it from the 'kvm_vcpu' structure if necessary. Signed-off-by: Tianjia Zhang Message-Id: <20200416051057.26526-1-tianjia.zhang@linux.alibaba.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7d4f1eb70274..5285a5568208 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -866,7 +866,7 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); -int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); int kvm_arch_init(void *opaque); void kvm_arch_exit(void); -- cgit v1.2.3 From acd05785e48c01edb2c4f4d014d28478b5f19fb5 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Fri, 17 Apr 2020 15:14:46 -0700 Subject: kvm: add capability for halt polling KVM_CAP_HALT_POLL is a per-VM capability that lets userspace control the halt-polling time, allowing halt-polling to be tuned or disabled on particular VMs. With dynamic halt-polling, a VM's VCPUs can poll from anywhere from [0, halt_poll_ns] on each halt. KVM_CAP_HALT_POLL sets the upper limit on the poll time. Signed-off-by: David Matlack Signed-off-by: Jon Cargille Reviewed-by: Jim Mattson Message-Id: <20200417221446.108733-1-jcargill@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + include/uapi/linux/kvm.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5285a5568208..3cc6ccbb1183 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -503,6 +503,7 @@ struct kvm { struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; + unsigned int max_halt_poll_ns; }; #define kvm_err(fmt, ...) \ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 428c7dde6b4b..ac9eba0289d1 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1017,6 +1017,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_VCPU_RESETS 179 #define KVM_CAP_S390_PROTECTED 180 #define KVM_CAP_PPC_SECURE_GUEST 181 +#define KVM_CAP_HALT_POLL 182 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 9d9a6ebfea329cadeda87544dceae01e9c27aaef Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:34 -0700 Subject: rcuwait: Let rcuwait_wake_up() return whether or not a task was awoken Propagating the return value of wake_up_process() back to the caller can come in handy for future users, such as for statistics or accounting purposes. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-3-dave@stgolabs.net> Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 2ffe1ee6d482..6ebb23258a27 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -25,7 +25,7 @@ static inline void rcuwait_init(struct rcuwait *w) w->task = NULL; } -extern void rcuwait_wake_up(struct rcuwait *w); +extern int rcuwait_wake_up(struct rcuwait *w); /* * The caller is responsible for locking around rcuwait_wait_event(), -- cgit v1.2.3 From 5c21f7b322cb9fcb97f2e22f5976a0ae8dd71354 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:35 -0700 Subject: rcuwait: Introduce prepare_to and finish_rcuwait This allows further flexibility for some callers to implement ad-hoc versions of the generic rcuwait_wait_event(). For example, kvm will need this to maintain tracing semantics. The naming is of course similar to what waitqueue apis offer. Also go ahead and make use of rcu_assign_pointer() for both task writes as it will make the __rcu sparse people happy - this will be the special nil case, thus no added serialization. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-4-dave@stgolabs.net> Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 6ebb23258a27..45bc6604e9b1 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -29,12 +29,25 @@ extern int rcuwait_wake_up(struct rcuwait *w); /* * The caller is responsible for locking around rcuwait_wait_event(), - * such that writes to @task are properly serialized. + * and [prepare_to/finish]_rcuwait() such that writes to @task are + * properly serialized. */ + +static inline void prepare_to_rcuwait(struct rcuwait *w) +{ + rcu_assign_pointer(w->task, current); +} + +static inline void finish_rcuwait(struct rcuwait *w) +{ + rcu_assign_pointer(w->task, NULL); + __set_current_state(TASK_RUNNING); +} + #define rcuwait_wait_event(w, condition, state) \ ({ \ int __ret = 0; \ - rcu_assign_pointer((w)->task, current); \ + prepare_to_rcuwait(w); \ for (;;) { \ /* \ * Implicit barrier (A) pairs with (B) in \ @@ -51,9 +64,7 @@ extern int rcuwait_wake_up(struct rcuwait *w); \ schedule(); \ } \ - \ - WRITE_ONCE((w)->task, NULL); \ - __set_current_state(TASK_RUNNING); \ + finish_rcuwait(w); \ __ret; \ }) -- cgit v1.2.3 From 191a43be61d6791fd4a9098a35c1a09e73f55228 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:36 -0700 Subject: rcuwait: Introduce rcuwait_active() This call is lockless and thus should not be trusted blindly. For example, the return value of rcuwait_wakeup() should be used to track whether a process was woken up. Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-5-dave@stgolabs.net> Acked-by: Peter Zijlstra (Intel) Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 45bc6604e9b1..c1414ce44abc 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -25,6 +25,15 @@ static inline void rcuwait_init(struct rcuwait *w) w->task = NULL; } +/* + * Note: this provides no serialization and, just as with waitqueues, + * requires care to estimate as to whether or not the wait is active. + */ +static inline int rcuwait_active(struct rcuwait *w) +{ + return !!rcu_dereference(w->task); +} + extern int rcuwait_wake_up(struct rcuwait *w); /* -- cgit v1.2.3 From da4ad88cab5867ee240dfd0585e9d115a8cc47db Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:37 -0700 Subject: kvm: Replace vcpu->swait with rcuwait The use of any sort of waitqueue (simple or regular) for wait/waking vcpus has always been an overkill and semantically wrong. Because this is per-vcpu (which is blocked) there is only ever a single waiting vcpu, thus no need for any sort of queue. As such, make use of the rcuwait primitive, with the following considerations: - rcuwait already provides the proper barriers that serialize concurrent waiter and waker. - Task wakeup is done in rcu read critical region, with a stable task pointer. - Because there is no concurrency among waiters, we need not worry about rcuwait_wait_event() calls corrupting the wait->task. As a consequence, this saves the locking done in swait when modifying the queue. This also applies to per-vcore wait for powerpc kvm-hv. The x86 tscdeadline_latency test mentioned in 8577370fb0cb ("KVM: Use simple waitqueue for vcpu->wq") shows that, on avg, latency is reduced by around 15-20% with this change. Cc: Paul Mackerras Cc: kvmarm@lists.cs.columbia.edu Cc: linux-mips@vger.kernel.org Reviewed-by: Marc Zyngier Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-6-dave@stgolabs.net> [Avoid extra logic changes. - Paolo] Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index abfa71cb5d2d..161684696610 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include @@ -277,7 +277,7 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; - struct swait_queue_head wq; + struct rcuwait wait; struct pid __rcu *pid; int sigset_active; sigset_t sigset; @@ -960,12 +960,12 @@ static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) } #endif -static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) +static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) { #ifdef __KVM_HAVE_ARCH_WQP - return vcpu->arch.wqp; + return vcpu->arch.waitp; #else - return &vcpu->wq; + return &vcpu->wait; #endif } -- cgit v1.2.3 From 0995a5dfbe49badff78e78761fb66f46579f2f9a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 4 Mar 2020 13:09:50 +0100 Subject: tracing: Provide lockdep less trace_hardirqs_on/off() variants trace_hardirqs_on/off() is only partially safe vs. RCU idle. The tracer core itself is safe, but the resulting tracepoints can be utilized by e.g. BPF which is unsafe. Provide variants which do not contain the lockdep invocation so the lockdep and tracer invocations can be split at the call site and placed properly. This is required because lockdep needs to be aware of the state before switching away from RCU idle and after switching to RCU idle because these transitions can take locks. As these code pathes are going to be non-instrumentable the tracer can be invoked after RCU is turned on and before the switch to RCU idle. So for these new variants there is no need to invoke the rcuidle aware tracer functions. Name them so they match the lockdep counterparts. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134100.270771162@linutronix.de --- include/linux/irqflags.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 61a9ced3aa50..f150e69ab81d 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -29,6 +29,8 @@ #endif #ifdef CONFIG_TRACE_IRQFLAGS + extern void trace_hardirqs_on_prepare(void); + extern void trace_hardirqs_off_prepare(void); extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); # define lockdep_hardirq_context(p) ((p)->hardirq_context) @@ -96,6 +98,8 @@ do { \ } while (0) #else +# define trace_hardirqs_on_prepare() do { } while (0) +# define trace_hardirqs_off_prepare() do { } while (0) # define trace_hardirqs_on() do { } while (0) # define trace_hardirqs_off() do { } while (0) # define lockdep_hardirq_context(p) 0 -- cgit v1.2.3 From c86e9b987cea3dd0209203e714553a47f5d7c6dd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 18 Mar 2020 14:22:03 +0100 Subject: lockdep: Prepare for noinstr sections Force inlining and prevent instrumentation of all sorts by marking the functions which are invoked from low level entry code with 'noinstr'. Split the irqflags tracking into two parts. One which does the heavy lifting while RCU is watching and the final one which can be invoked after RCU is turned off. Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Link: https://lkml.kernel.org/r/20200505134100.484532537@linutronix.de --- include/linux/irqflags.h | 2 ++ include/linux/sched.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index f150e69ab81d..d7f7e436c3af 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -19,11 +19,13 @@ #ifdef CONFIG_PROVE_LOCKING extern void lockdep_softirqs_on(unsigned long ip); extern void lockdep_softirqs_off(unsigned long ip); + extern void lockdep_hardirqs_on_prepare(unsigned long ip); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); #else static inline void lockdep_softirqs_on(unsigned long ip) { } static inline void lockdep_softirqs_off(unsigned long ip) { } + static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 4418f5cb8324..658de6164853 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -983,6 +983,7 @@ struct task_struct { unsigned int hardirq_disable_event; int hardirqs_enabled; int hardirq_context; + u64 hardirq_chain_key; unsigned long softirq_disable_ip; unsigned long softirq_enable_ip; unsigned int softirq_disable_event; -- cgit v1.2.3 From af1e56b78534c38bb0e0c712ca70e59f816b74e9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 19 Mar 2020 14:53:56 +0100 Subject: context_tracking: Make guest_enter/exit() .noinstr ready Force inlining of the helpers and mark the instrumentable parts accordingly. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134341.672545766@linutronix.de --- include/linux/context_tracking.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 8150f5ac176c..8cac62ee6add 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -101,12 +101,14 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN /* must be called with irqs disabled */ -static inline void guest_enter_irqoff(void) +static __always_inline void guest_enter_irqoff(void) { + instrumentation_begin(); if (vtime_accounting_enabled_this_cpu()) vtime_guest_enter(current); else current->flags |= PF_VCPU; + instrumentation_end(); if (context_tracking_enabled()) __context_tracking_enter(CONTEXT_GUEST); @@ -118,39 +120,48 @@ static inline void guest_enter_irqoff(void) * one time slice). Lets treat guest mode as quiescent state, just like * we do with user-mode execution. */ - if (!context_tracking_enabled_this_cpu()) + if (!context_tracking_enabled_this_cpu()) { + instrumentation_begin(); rcu_virt_note_context_switch(smp_processor_id()); + instrumentation_end(); + } } -static inline void guest_exit_irqoff(void) +static __always_inline void guest_exit_irqoff(void) { if (context_tracking_enabled()) __context_tracking_exit(CONTEXT_GUEST); + instrumentation_begin(); if (vtime_accounting_enabled_this_cpu()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; + instrumentation_end(); } #else -static inline void guest_enter_irqoff(void) +static __always_inline void guest_enter_irqoff(void) { /* * This is running in ioctl context so its safe * to assume that it's the stime pending cputime * to flush. */ + instrumentation_begin(); vtime_account_kernel(current); current->flags |= PF_VCPU; rcu_virt_note_context_switch(smp_processor_id()); + instrumentation_end(); } -static inline void guest_exit_irqoff(void) +static __always_inline void guest_exit_irqoff(void) { + instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ vtime_account_kernel(current); current->flags &= ~PF_VCPU; + instrumentation_end(); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -- cgit v1.2.3 From febd668d375caf13a7fcd93b3498366854de854a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 18 May 2020 06:30:09 -0400 Subject: rcuwait: avoid lockdep splats from rcuwait_active() rcuwait_active only returns whether w->task is not NULL. This is exactly one of the usecases that are mentioned in the documentation for rcu_access_pointer() where it is correct to bypass lockdep checks. This avoids a splat from kvm_vcpu_on_spin(). Reported-by: Wanpeng Li Tested-by: Wanpeng Li Acked-by: Davidlohr Bueso Cc: Peter Zijlstra Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index c1414ce44abc..61c56cca95c4 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -31,7 +31,7 @@ static inline void rcuwait_init(struct rcuwait *w) */ static inline int rcuwait_active(struct rcuwait *w) { - return !!rcu_dereference(w->task); + return !!rcu_access_pointer(w->task); } extern int rcuwait_wake_up(struct rcuwait *w); -- cgit v1.2.3 From fc5d1f1a42fba6266ab95dc3b84937933a9b5a66 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Sat, 1 Dec 2018 08:41:28 -0800 Subject: KVM: arm64: vgic-v3: Take cpu_if pointer directly instead of vcpu If we move the used_lrs field to the version-specific cpu interface structure, the following functions only operate on the struct vgic_v3_cpu_if and not the full vcpu: __vgic_v3_save_state __vgic_v3_restore_state __vgic_v3_activate_traps __vgic_v3_deactivate_traps __vgic_v3_save_aprs __vgic_v3_restore_aprs This is going to be very useful for nested virt, so move the used_lrs field and change the prototypes and implementations of these functions to take the cpu_if parameter directly. No functional change. Reviewed-by: James Morse Signed-off-by: Christoffer Dall Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 69f4164d6477..a8d8fdcd3723 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -274,6 +274,8 @@ struct vgic_v2_cpu_if { u32 vgic_vmcr; u32 vgic_apr; u32 vgic_lr[VGIC_V2_MAX_LRS]; + + unsigned int used_lrs; }; struct vgic_v3_cpu_if { @@ -291,6 +293,8 @@ struct vgic_v3_cpu_if { * linking the Linux IRQ subsystem and the ITS together. */ struct its_vpe its_vpe; + + unsigned int used_lrs; }; struct vgic_cpu { @@ -300,7 +304,6 @@ struct vgic_cpu { struct vgic_v3_cpu_if vgic_v3; }; - unsigned int used_lrs; struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS]; raw_spinlock_t ap_list_lock; /* Protects the ap_list */ -- cgit v1.2.3 From 0958f0cefede403037653e44de0e3332d10b0e1a Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 25 May 2020 16:41:19 +0200 Subject: KVM: introduce kvm_read_guest_offset_cached() We already have kvm_write_guest_offset_cached(), introduce read analogue. Signed-off-by: Vitaly Kuznetsov Message-Id: <20200525144125.143875-5-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 161684696610..f43b59b1294c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -734,6 +734,9 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); +int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned int offset, + unsigned long len); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, -- cgit v1.2.3 From 72de5fa4c16195827252b961ba44028a39dfeaff Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 25 May 2020 16:41:22 +0200 Subject: KVM: x86: announce KVM_FEATURE_ASYNC_PF_INT Introduce new capability to indicate that KVM supports interrupt based delivery of 'page ready' APF events. This includes support for both MSR_KVM_ASYNC_PF_INT and MSR_KVM_ASYNC_PF_ACK. Signed-off-by: Vitaly Kuznetsov Message-Id: <20200525144125.143875-8-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ac9eba0289d1..fc0075988b80 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1018,6 +1018,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED 180 #define KVM_CAP_PPC_SECURE_GUEST 181 #define KVM_CAP_HALT_POLL 182 +#define KVM_CAP_ASYNC_PF_INT 183 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From f7d31e65368aeef973fab788aa22c4f1d5a6af66 Mon Sep 17 00:00:00 2001 From: Jon Doron Date: Fri, 24 Apr 2020 14:37:40 +0300 Subject: x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit The problem the patch is trying to address is the fact that 'struct kvm_hyperv_exit' has different layout on when compiling in 32 and 64 bit modes. In 64-bit mode the default alignment boundary is 64 bits thus forcing extra gaps after 'type' and 'msr' but in 32-bit mode the boundary is at 32 bits thus no extra gaps. This is an issue as even when the kernel is 64 bit, the userspace using the interface can be both 32 and 64 bit but the same 32 bit userspace has to work with 32 bit kernel. The issue is fixed by forcing the 64 bit layout, this leads to ABI change for 32 bit builds and while we are obviously breaking '32 bit userspace with 32 bit kernel' case, we're fixing the '32 bit userspace with 64 bit kernel' one. As the interface has no (known) users and 32 bit KVM is rather baroque nowadays, this seems like a reasonable decision. Reviewed-by: Vitaly Kuznetsov Signed-off-by: Jon Doron Message-Id: <20200424113746.3473563-2-arilou@gmail.com> Reviewed-by: Roman Kagan Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index fc0075988b80..cc04aceb8793 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -189,9 +189,11 @@ struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 __u32 type; + __u32 pad1; union { struct { __u32 msr; + __u32 pad2; __u64 control; __u64 evt_page; __u64 msg_page; -- cgit v1.2.3 From f97f5a56f5977311f3833056a73cdbb0ee56cb1e Mon Sep 17 00:00:00 2001 From: Jon Doron Date: Fri, 29 May 2020 16:45:40 +0300 Subject: x86/kvm/hyper-v: Add support for synthetic debugger interface Add support for Hyper-V synthetic debugger (syndbg) interface. The syndbg interface is using MSRs to emulate a way to send/recv packets data. The debug transport dll (kdvm/kdnet) will identify if Hyper-V is enabled and if it supports the synthetic debugger interface it will attempt to use it, instead of trying to initialize a network adapter. Reviewed-by: Vitaly Kuznetsov Signed-off-by: Jon Doron Message-Id: <20200529134543.1127440-4-arilou@gmail.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index cc04aceb8793..6721eb563eda 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -188,6 +188,7 @@ struct kvm_s390_cmma_log { struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 +#define KVM_EXIT_HYPERV_SYNDBG 3 __u32 type; __u32 pad1; union { @@ -203,6 +204,15 @@ struct kvm_hyperv_exit { __u64 result; __u64 params[2]; } hcall; + struct { + __u32 msr; + __u32 pad2; + __u64 control; + __u64 status; + __u64 send_page; + __u64 recv_page; + __u64 pending_page; + } syndbg; } u; }; -- cgit v1.2.3