From 812756a82ea51e3c7ff7ba5e6fa3f34345234bc7 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
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 <eesposit@redhat.com>
Message-Id: <20200414155625.20559-1-eesposit@redhat.com>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

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 <pbonzini@redhat.com>
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 <jmattson@google.com>
Cc: Rick Edgecombe <rick.p.edgecombe@intel.com>
Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c   | 9 +++------
 include/linux/kvm_host.h | 6 ++++++
 virt/kvm/kvm_main.c      | 6 +-----
 3 files changed, 10 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b67046fa0ac4..e618472c572b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4082,19 +4082,16 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
 			 bool *writable)
 {
-	struct kvm_memory_slot *slot;
+	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	bool async;
 
-	/*
-	 * Don't expose private memslots to L2.
-	 */
-	if (is_guest_mode(vcpu) && !kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+	/* Don't expose private memslots to L2. */
+	if (is_guest_mode(vcpu) && !kvm_is_visible_memslot(slot)) {
 		*pfn = KVM_PFN_NOSLOT;
 		*writable = false;
 		return false;
 	}
 
-	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	async = false;
 	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable);
 	if (!async)
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);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index da8fd45e0e3e..8aa577db131e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1607,11 +1607,7 @@ bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn);
 
-	if (!memslot || memslot->id >= KVM_USER_MEM_SLOTS ||
-	      memslot->flags & KVM_MEMSLOT_INVALID)
-		return false;
-
-	return true;
+	return kvm_is_visible_memslot(memslot);
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
-- 
cgit v1.2.3


From 1b94f6f81007b4afaea3480ec018bc9236148961 Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
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 <tianjia.zhang@linux.alibaba.com>
Message-Id: <20200416051057.26526-1-tianjia.zhang@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/mips/kvm/mips.c       |  3 ++-
 arch/powerpc/kvm/powerpc.c |  3 ++-
 arch/s390/kvm/kvm-s390.c   |  3 ++-
 arch/x86/kvm/x86.c         | 11 ++++++-----
 include/linux/kvm_host.h   |  2 +-
 virt/kvm/arm/arm.c         |  6 +++---
 virt/kvm/kvm_main.c        |  2 +-
 7 files changed, 17 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index fdf1c14d9205..9f50ceef9978 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -438,8 +438,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	return -ENOIOCTLCMD;
 }
 
-int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
+	struct kvm_run *run = vcpu->run;
 	int r = -EINTR;
 
 	vcpu_load(vcpu);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index e15166b0a16d..7e24691e138a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -1764,8 +1764,9 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	return r;
 }
 
-int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
+	struct kvm_run *run = vcpu->run;
 	int r;
 
 	vcpu_load(vcpu);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 5307929a6c89..75471b646fd7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4333,8 +4333,9 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		store_regs_fmt2(vcpu, kvm_run);
 }
 
-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)
 {
+	struct kvm_run *kvm_run = vcpu->run;
 	int rc;
 
 	if (kvm_run->immediate_exit)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8d9bcd5faac5..59958ce2b681 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8710,8 +8710,9 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	trace_kvm_fpu(0);
 }
 
-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)
 {
+	struct kvm_run *kvm_run = vcpu->run;
 	int r;
 
 	vcpu_load(vcpu);
@@ -8729,18 +8730,18 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		r = -EAGAIN;
 		if (signal_pending(current)) {
 			r = -EINTR;
-			vcpu->run->exit_reason = KVM_EXIT_INTR;
+			kvm_run->exit_reason = KVM_EXIT_INTR;
 			++vcpu->stat.signal_exits;
 		}
 		goto out;
 	}
 
-	if (vcpu->run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) {
+	if (kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) {
 		r = -EINVAL;
 		goto out;
 	}
 
-	if (vcpu->run->kvm_dirty_regs) {
+	if (kvm_run->kvm_dirty_regs) {
 		r = sync_regs(vcpu);
 		if (r != 0)
 			goto out;
@@ -8770,7 +8771,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 out:
 	kvm_put_guest_fpu(vcpu);
-	if (vcpu->run->kvm_valid_regs)
+	if (kvm_run->kvm_valid_regs)
 		store_regs(vcpu);
 	post_kvm_run_save(vcpu);
 	kvm_sigset_deactivate(vcpu);
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);
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 48d0ec44ad77..f5390ac2165b 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -639,7 +639,6 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
- * @run:	The kvm_run structure pointer used for userspace state exchange
  *
  * This function is called through the VCPU_RUN ioctl called from user space. It
  * will execute VM code in a loop until the time slice for the process is used
@@ -647,8 +646,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
  * return with return value 0 and with the kvm_run structure filled in with the
  * required data for the requested emulation.
  */
-int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
+	struct kvm_run *run = vcpu->run;
 	int ret;
 
 	if (unlikely(!kvm_vcpu_initialized(vcpu)))
@@ -659,7 +659,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		return ret;
 
 	if (run->exit_reason == KVM_EXIT_MMIO) {
-		ret = kvm_handle_mmio_return(vcpu, vcpu->run);
+		ret = kvm_handle_mmio_return(vcpu, run);
 		if (ret)
 			return ret;
 	}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8aa577db131e..e2f60e313c87 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3129,7 +3129,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 				synchronize_rcu();
 			put_pid(oldpid);
 		}
-		r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
+		r = kvm_arch_vcpu_ioctl_run(vcpu);
 		trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
 		break;
 	}
-- 
cgit v1.2.3


From acd05785e48c01edb2c4f4d014d28478b5f19fb5 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
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 <dmatlack@google.com>
Signed-off-by: Jon Cargille <jcargill@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Message-Id: <20200417221446.108733-1-jcargill@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 17 +++++++++++++++++
 include/linux/kvm_host.h       |  1 +
 include/uapi/linux/kvm.h       |  1 +
 virt/kvm/kvm_main.c            | 19 +++++++++++++++----
 4 files changed, 34 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index efbbe570aa9b..d871dacb984e 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -5802,6 +5802,23 @@ If present, this capability can be enabled for a VM, meaning that KVM
 will allow the transition to secure guest mode.  Otherwise KVM will
 veto the transition.
 
+7.20 KVM_CAP_HALT_POLL
+----------------------
+
+:Architectures: all
+:Target: VM
+:Parameters: args[0] is the maximum poll time in nanoseconds
+:Returns: 0 on success; -1 on error
+
+This capability overrides the kvm module parameter halt_poll_ns for the
+target VM.
+
+VCPU polling allows a VCPU to poll for wakeup events instead of immediately
+scheduling during guest halts. The maximum time a VCPU can spend polling is
+controlled by the kvm module parameter halt_poll_ns. This capability allows
+the maximum halt time to specified on a per-VM basis, effectively overriding
+the module parameter for the target VM.
+
 8. Other capabilities.
 ======================
 
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
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e7436d054305..33e1eee96f75 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -710,6 +710,8 @@ static struct kvm *kvm_create_vm(unsigned long type)
 			goto out_err_no_arch_destroy_vm;
 	}
 
+	kvm->max_halt_poll_ns = halt_poll_ns;
+
 	r = kvm_arch_init_vm(kvm, type);
 	if (r)
 		goto out_err_no_arch_destroy_vm;
@@ -2713,15 +2715,16 @@ out:
 	if (!kvm_arch_no_poll(vcpu)) {
 		if (!vcpu_valid_wakeup(vcpu)) {
 			shrink_halt_poll_ns(vcpu);
-		} else if (halt_poll_ns) {
+		} else if (vcpu->kvm->max_halt_poll_ns) {
 			if (block_ns <= vcpu->halt_poll_ns)
 				;
 			/* we had a long block, shrink polling */
-			else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns)
+			else if (vcpu->halt_poll_ns &&
+					block_ns > vcpu->kvm->max_halt_poll_ns)
 				shrink_halt_poll_ns(vcpu);
 			/* we had a short halt and our poll time is too small */
-			else if (vcpu->halt_poll_ns < halt_poll_ns &&
-				block_ns < halt_poll_ns)
+			else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns &&
+					block_ns < vcpu->kvm->max_halt_poll_ns)
 				grow_halt_poll_ns(vcpu);
 		} else {
 			vcpu->halt_poll_ns = 0;
@@ -3510,6 +3513,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_IOEVENTFD_ANY_LENGTH:
 	case KVM_CAP_CHECK_EXTENSION_VM:
 	case KVM_CAP_ENABLE_CAP_VM:
+	case KVM_CAP_HALT_POLL:
 		return 1;
 #ifdef CONFIG_KVM_MMIO
 	case KVM_CAP_COALESCED_MMIO:
@@ -3560,6 +3564,13 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 		return 0;
 	}
 #endif
+	case KVM_CAP_HALT_POLL: {
+		if (cap->flags || cap->args[0] != (unsigned int)cap->args[0])
+			return -EINVAL;
+
+		kvm->max_halt_poll_ns = cap->args[0];
+		return 0;
+	}
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);
 	}
-- 
cgit v1.2.3


From 9d9a6ebfea329cadeda87544dceae01e9c27aaef Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
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) <peterz@infradead.org>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Message-Id: <20200424054837.5138-3-dave@stgolabs.net>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/rcuwait.h | 2 +-
 kernel/exit.c           | 7 +++++--
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include/linux')

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(),
diff --git a/kernel/exit.c b/kernel/exit.c
index 9f9015f3f6b0..f3beb637acf7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -227,8 +227,9 @@ repeat:
 		goto repeat;
 }
 
-void rcuwait_wake_up(struct rcuwait *w)
+int rcuwait_wake_up(struct rcuwait *w)
 {
+	int ret = 0;
 	struct task_struct *task;
 
 	rcu_read_lock();
@@ -248,8 +249,10 @@ void rcuwait_wake_up(struct rcuwait *w)
 
 	task = rcu_dereference(w->task);
 	if (task)
-		wake_up_process(task);
+		ret = wake_up_process(task);
 	rcu_read_unlock();
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(rcuwait_wake_up);
 
-- 
cgit v1.2.3


From 5c21f7b322cb9fcb97f2e22f5976a0ae8dd71354 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
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) <peterz@infradead.org>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Message-Id: <20200424054837.5138-4-dave@stgolabs.net>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/rcuwait.h | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

(limited to 'include/linux')

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 <dave@stgolabs.net>
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 <dbueso@suse.de>
Message-Id: <20200424054837.5138-5-dave@stgolabs.net>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/rcuwait.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include/linux')

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 <dave@stgolabs.net>
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 <paulus@ozlabs.org>
Cc: kvmarm@lists.cs.columbia.edu
Cc: linux-mips@vger.kernel.org
Reviewed-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Message-Id: <20200424054837.5138-6-dave@stgolabs.net>
[Avoid extra logic changes. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/mips/kvm/mips.c                  |  6 ++----
 arch/powerpc/include/asm/kvm_book3s.h |  2 +-
 arch/powerpc/include/asm/kvm_host.h   |  2 +-
 arch/powerpc/kvm/book3s_hv.c          | 23 ++++++++++-------------
 arch/powerpc/kvm/powerpc.c            |  2 +-
 arch/x86/kvm/lapic.c                  |  2 +-
 include/linux/kvm_host.h              | 10 +++++-----
 virt/kvm/arm/arch_timer.c             |  3 ++-
 virt/kvm/arm/arm.c                    |  9 +++++----
 virt/kvm/async_pf.c                   |  3 +--
 virt/kvm/kvm_main.c                   | 19 +++++++++----------
 11 files changed, 38 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 9f50ceef9978..9787cdec33e6 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -283,8 +283,7 @@ static enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer)
 	kvm_mips_callbacks->queue_timer_int(vcpu);
 
 	vcpu->arch.wait = 0;
-	if (swq_has_sleeper(&vcpu->wq))
-		swake_up_one(&vcpu->wq);
+	rcuwait_wake_up(&vcpu->wait);
 
 	return kvm_mips_count_timeout(vcpu);
 }
@@ -511,8 +510,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 
 	dvcpu->arch.wait = 0;
 
-	if (swq_has_sleeper(&dvcpu->wq))
-		swake_up_one(&dvcpu->wq);
+	rcuwait_wake_up(&dvcpu->wait);
 
 	return 0;
 }
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 506e4df2d730..6e5d85ba588d 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -78,7 +78,7 @@ struct kvmppc_vcore {
 	struct kvm_vcpu *runnable_threads[MAX_SMT_THREADS];
 	struct list_head preempt_list;
 	spinlock_t lock;
-	struct swait_queue_head wq;
+	struct rcuwait wait;
 	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
 	u64 stolen_tb;
 	u64 preempt_tb;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1dc63101ffe1..337047ba4a56 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -751,7 +751,7 @@ struct kvm_vcpu_arch {
 	u8 irq_pending; /* Used by XIVE to signal pending guest irqs */
 	u32 last_inst;
 
-	struct swait_queue_head *wqp;
+	struct rcuwait *waitp;
 	struct kvmppc_vcore *vcore;
 	int ret;
 	int trap;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 93493f0cbfe8..7f59c47a5b9d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -230,13 +230,11 @@ static bool kvmppc_ipi_thread(int cpu)
 static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
 	int cpu;
-	struct swait_queue_head *wqp;
+	struct rcuwait *waitp;
 
-	wqp = kvm_arch_vcpu_wq(vcpu);
-	if (swq_has_sleeper(wqp)) {
-		swake_up_one(wqp);
+	waitp = kvm_arch_vcpu_get_wait(vcpu);
+	if (rcuwait_wake_up(waitp))
 		++vcpu->stat.halt_wakeup;
-	}
 
 	cpu = READ_ONCE(vcpu->arch.thread_cpu);
 	if (cpu >= 0 && kvmppc_ipi_thread(cpu))
@@ -2125,7 +2123,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id)
 
 	spin_lock_init(&vcore->lock);
 	spin_lock_init(&vcore->stoltb_lock);
-	init_swait_queue_head(&vcore->wq);
+	rcuwait_init(&vcore->wait);
 	vcore->preempt_tb = TB_NIL;
 	vcore->lpcr = kvm->arch.lpcr;
 	vcore->first_vcpuid = id;
@@ -3784,7 +3782,6 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	ktime_t cur, start_poll, start_wait;
 	int do_sleep = 1;
 	u64 block_ns;
-	DECLARE_SWAITQUEUE(wait);
 
 	/* Poll for pending exceptions and ceded state */
 	cur = start_poll = ktime_get();
@@ -3812,10 +3809,10 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 		}
 	}
 
-	prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE);
-
+	prepare_to_rcuwait(&vc->wait);
+	set_current_state(TASK_INTERRUPTIBLE);
 	if (kvmppc_vcore_check_block(vc)) {
-		finish_swait(&vc->wq, &wait);
+		finish_rcuwait(&vc->wait);
 		do_sleep = 0;
 		/* If we polled, count this as a successful poll */
 		if (vc->halt_poll_ns)
@@ -3829,7 +3826,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	trace_kvmppc_vcore_blocked(vc, 0);
 	spin_unlock(&vc->lock);
 	schedule();
-	finish_swait(&vc->wq, &wait);
+	finish_rcuwait(&vc->wait);
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
 	trace_kvmppc_vcore_blocked(vc, 1);
@@ -3940,7 +3937,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
-			swake_up_one(&vc->wq);
+		        rcuwait_wake_up(&vc->wait);
 		}
 
 	}
@@ -4279,7 +4276,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 	user_vrsave = mfspr(SPRN_VRSAVE);
 
-	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
+	vcpu->arch.waitp = &vcpu->arch.vcore->wait;
 	vcpu->arch.pgdir = kvm->mm->pgd;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 052614e9d468..27ccff612903 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -752,7 +752,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (err)
 		goto out_vcpu_uninit;
 
-	vcpu->arch.wqp = &vcpu->wq;
+	vcpu->arch.waitp = &vcpu->wait;
 	kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id);
 	return 0;
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 38f7dc9c16ee..42cd2e3ec6fd 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1861,7 +1861,7 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
 	/* If the preempt notifier has already run, it also called apic_timer_expired */
 	if (!apic->lapic_timer.hv_timer_in_use)
 		goto out;
-	WARN_ON(swait_active(&vcpu->wq));
+	WARN_ON(rcuwait_active(&vcpu->wait));
 	cancel_hv_timer(apic);
 	apic_timer_expired(apic);
 
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 <linux/irqflags.h>
 #include <linux/context_tracking.h>
 #include <linux/irqbypass.h>
-#include <linux/swait.h>
+#include <linux/rcuwait.h>
 #include <linux/refcount.h>
 #include <linux/nospec.h>
 #include <asm/signal.h>
@@ -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
 }
 
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 93bd59b46848..d5024416e722 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -571,6 +571,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = vcpu_timer(vcpu);
 	struct timer_map map;
+	struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
 
 	if (unlikely(!timer->enabled))
 		return;
@@ -593,7 +594,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 	if (map.emul_ptimer)
 		soft_timer_cancel(&map.emul_ptimer->hrtimer);
 
-	if (swait_active(kvm_arch_vcpu_wq(vcpu)))
+	if (rcuwait_active(wait))
 		kvm_timer_blocking(vcpu);
 
 	/*
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index f5390ac2165b..d5db0d6141ff 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -579,16 +579,17 @@ void kvm_arm_resume_guest(struct kvm *kvm)
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		vcpu->arch.pause = false;
-		swake_up_one(kvm_arch_vcpu_wq(vcpu));
+		rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu));
 	}
 }
 
 static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 {
-	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
+	struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
 
-	swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
-				       (!vcpu->arch.pause)));
+	rcuwait_wait_event(wait,
+			   (!vcpu->arch.power_off) &&(!vcpu->arch.pause),
+			   TASK_INTERRUPTIBLE);
 
 	if (vcpu->arch.power_off || vcpu->arch.pause) {
 		/* Awaken to handle a signal, request we sleep again later. */
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 15e5b037f92d..10b533f641a6 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -80,8 +80,7 @@ static void async_pf_execute(struct work_struct *work)
 
 	trace_kvm_async_pf_completed(addr, cr2_or_gpa);
 
-	if (swq_has_sleeper(&vcpu->wq))
-		swake_up_one(&vcpu->wq);
+	rcuwait_wake_up(&vcpu->wait);
 
 	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7525f3838160..e12317f32c5e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -349,7 +349,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->kvm = kvm;
 	vcpu->vcpu_id = id;
 	vcpu->pid = NULL;
-	init_swait_queue_head(&vcpu->wq);
+	rcuwait_init(&vcpu->wait);
 	kvm_async_pf_vcpu_init(vcpu);
 
 	vcpu->pre_pcpu = -1;
@@ -2678,7 +2678,6 @@ out:
 void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 {
 	ktime_t start, cur;
-	DECLARE_SWAITQUEUE(wait);
 	bool waited = false;
 	u64 block_ns;
 
@@ -2704,8 +2703,9 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		} while (single_task_running() && ktime_before(cur, stop));
 	}
 
+	prepare_to_rcuwait(&vcpu->wait);
 	for (;;) {
-		prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE);
 
 		if (kvm_vcpu_check_block(vcpu) < 0)
 			break;
@@ -2713,8 +2713,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		waited = true;
 		schedule();
 	}
-
-	finish_swait(&vcpu->wq, &wait);
+	finish_rcuwait(&vcpu->wait);
 	cur = ktime_get();
 out:
 	kvm_arch_vcpu_unblocking(vcpu);
@@ -2746,11 +2745,10 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_block);
 
 bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
 {
-	struct swait_queue_head *wqp;
+	struct rcuwait *waitp;
 
-	wqp = kvm_arch_vcpu_wq(vcpu);
-	if (swq_has_sleeper(wqp)) {
-		swake_up_one(wqp);
+	waitp = kvm_arch_vcpu_get_wait(vcpu);
+	if (rcuwait_wake_up(waitp)) {
 		WRITE_ONCE(vcpu->ready, true);
 		++vcpu->stat.halt_wakeup;
 		return true;
@@ -2892,7 +2890,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 				continue;
 			if (vcpu == me)
 				continue;
-			if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu))
+			if (rcuwait_active(&vcpu->wait) &&
+			    !vcpu_dy_runnable(vcpu))
 				continue;
 			if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode &&
 				!kvm_arch_vcpu_in_kernel(vcpu))
-- 
cgit v1.2.3


From 0995a5dfbe49badff78e78761fb66f46579f2f9a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
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 <tglx@linutronix.de>
Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200505134100.270771162@linutronix.de
---
 include/linux/irqflags.h        |  4 ++++
 kernel/trace/trace_preemptirq.c | 37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+)

(limited to 'include/linux')

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
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index 4d8e99fdbbbe..c00880162b06 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -19,6 +19,24 @@
 /* Per-cpu variable to prevent redundant calls when IRQs already off */
 static DEFINE_PER_CPU(int, tracing_irq_cpu);
 
+/*
+ * Like trace_hardirqs_on() but without the lockdep invocation. This is
+ * used in the low level entry code where the ordering vs. RCU is important
+ * and lockdep uses a staged approach which splits the lockdep hardirq
+ * tracking into a RCU on and a RCU off section.
+ */
+void trace_hardirqs_on_prepare(void)
+{
+	if (this_cpu_read(tracing_irq_cpu)) {
+		if (!in_nmi())
+			trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1);
+		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
+		this_cpu_write(tracing_irq_cpu, 0);
+	}
+}
+EXPORT_SYMBOL(trace_hardirqs_on_prepare);
+NOKPROBE_SYMBOL(trace_hardirqs_on_prepare);
+
 void trace_hardirqs_on(void)
 {
 	if (this_cpu_read(tracing_irq_cpu)) {
@@ -33,6 +51,25 @@ void trace_hardirqs_on(void)
 EXPORT_SYMBOL(trace_hardirqs_on);
 NOKPROBE_SYMBOL(trace_hardirqs_on);
 
+/*
+ * Like trace_hardirqs_off() but without the lockdep invocation. This is
+ * used in the low level entry code where the ordering vs. RCU is important
+ * and lockdep uses a staged approach which splits the lockdep hardirq
+ * tracking into a RCU on and a RCU off section.
+ */
+void trace_hardirqs_off_prepare(void)
+{
+	if (!this_cpu_read(tracing_irq_cpu)) {
+		this_cpu_write(tracing_irq_cpu, 1);
+		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
+		if (!in_nmi())
+			trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1);
+	}
+
+}
+EXPORT_SYMBOL(trace_hardirqs_off_prepare);
+NOKPROBE_SYMBOL(trace_hardirqs_off_prepare);
+
 void trace_hardirqs_off(void)
 {
 	if (!this_cpu_read(tracing_irq_cpu)) {
-- 
cgit v1.2.3


From c86e9b987cea3dd0209203e714553a47f5d7c6dd Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
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 <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com>
Link: https://lkml.kernel.org/r/20200505134100.484532537@linutronix.de
---
 include/linux/irqflags.h        |  2 +
 include/linux/sched.h           |  1 +
 kernel/locking/lockdep.c        | 86 +++++++++++++++++++++++++++++++----------
 kernel/trace/trace_preemptirq.c |  2 +
 lib/debug_locks.c               |  2 +-
 5 files changed, 71 insertions(+), 22 deletions(-)

(limited to 'include/linux')

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;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index ac10db66cc63..9ccd675a8b5a 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3635,13 +3635,10 @@ mark_held_locks(struct task_struct *curr, enum lock_usage_bit base_bit)
 /*
  * Hardirqs will be enabled:
  */
-static void __trace_hardirqs_on_caller(unsigned long ip)
+static void __trace_hardirqs_on_caller(void)
 {
 	struct task_struct *curr = current;
 
-	/* we'll do an OFF -> ON transition: */
-	curr->hardirqs_enabled = 1;
-
 	/*
 	 * We are going to turn hardirqs on, so set the
 	 * usage bit for all held locks:
@@ -3654,15 +3651,19 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
 	 * this bit from being set before)
 	 */
 	if (curr->softirqs_enabled)
-		if (!mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ))
-			return;
-
-	curr->hardirq_enable_ip = ip;
-	curr->hardirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(hardirqs_on_events);
+		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
 }
 
-void lockdep_hardirqs_on(unsigned long ip)
+/**
+ * lockdep_hardirqs_on_prepare - Prepare for enabling interrupts
+ * @ip:		Caller address
+ *
+ * Invoked before a possible transition to RCU idle from exit to user or
+ * guest mode. This ensures that all RCU operations are done before RCU
+ * stops watching. After the RCU transition lockdep_hardirqs_on() has to be
+ * invoked to set the final state.
+ */
+void lockdep_hardirqs_on_prepare(unsigned long ip)
 {
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
@@ -3698,20 +3699,62 @@ void lockdep_hardirqs_on(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(current->hardirq_context))
 		return;
 
+	current->hardirq_chain_key = current->curr_chain_key;
+
 	current->lockdep_recursion++;
-	__trace_hardirqs_on_caller(ip);
+	__trace_hardirqs_on_caller();
 	lockdep_recursion_finish();
 }
-NOKPROBE_SYMBOL(lockdep_hardirqs_on);
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_on_prepare);
+
+void noinstr lockdep_hardirqs_on(unsigned long ip)
+{
+	struct task_struct *curr = current;
+
+	if (unlikely(!debug_locks || curr->lockdep_recursion))
+		return;
+
+	if (curr->hardirqs_enabled) {
+		/*
+		 * Neither irq nor preemption are disabled here
+		 * so this is racy by nature but losing one hit
+		 * in a stat is not a big deal.
+		 */
+		__debug_atomic_inc(redundant_hardirqs_on);
+		return;
+	}
+
+	/*
+	 * We're enabling irqs and according to our state above irqs weren't
+	 * already enabled, yet we find the hardware thinks they are in fact
+	 * enabled.. someone messed up their IRQ state tracing.
+	 */
+	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+		return;
+
+	/*
+	 * Ensure the lock stack remained unchanged between
+	 * lockdep_hardirqs_on_prepare() and lockdep_hardirqs_on().
+	 */
+	DEBUG_LOCKS_WARN_ON(current->hardirq_chain_key !=
+			    current->curr_chain_key);
+
+	/* we'll do an OFF -> ON transition: */
+	curr->hardirqs_enabled = 1;
+	curr->hardirq_enable_ip = ip;
+	curr->hardirq_enable_event = ++curr->irq_events;
+	debug_atomic_inc(hardirqs_on_events);
+}
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_on);
 
 /*
  * Hardirqs were disabled:
  */
-void lockdep_hardirqs_off(unsigned long ip)
+void noinstr lockdep_hardirqs_off(unsigned long ip)
 {
 	struct task_struct *curr = current;
 
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!debug_locks || curr->lockdep_recursion))
 		return;
 
 	/*
@@ -3729,10 +3772,11 @@ void lockdep_hardirqs_off(unsigned long ip)
 		curr->hardirq_disable_ip = ip;
 		curr->hardirq_disable_event = ++curr->irq_events;
 		debug_atomic_inc(hardirqs_off_events);
-	} else
+	} else {
 		debug_atomic_inc(redundant_hardirqs_off);
+	}
 }
-NOKPROBE_SYMBOL(lockdep_hardirqs_off);
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_off);
 
 /*
  * Softirqs will be enabled:
@@ -4408,8 +4452,8 @@ static void print_unlock_imbalance_bug(struct task_struct *curr,
 	dump_stack();
 }
 
-static int match_held_lock(const struct held_lock *hlock,
-					const struct lockdep_map *lock)
+static noinstr int match_held_lock(const struct held_lock *hlock,
+				   const struct lockdep_map *lock)
 {
 	if (hlock->instance == lock)
 		return 1;
@@ -4696,7 +4740,7 @@ __lock_release(struct lockdep_map *lock, unsigned long ip)
 	return 0;
 }
 
-static nokprobe_inline
+static __always_inline
 int __lock_is_held(const struct lockdep_map *lock, int read)
 {
 	struct task_struct *curr = current;
@@ -4956,7 +5000,7 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_release);
 
-int lock_is_held_type(const struct lockdep_map *lock, int read)
+noinstr int lock_is_held_type(const struct lockdep_map *lock, int read)
 {
 	unsigned long flags;
 	int ret = 0;
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index c00880162b06..fb0691b8a88d 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -46,6 +46,7 @@ void trace_hardirqs_on(void)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on);
@@ -93,6 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
diff --git a/lib/debug_locks.c b/lib/debug_locks.c
index a75ee30b77cb..06d3135bd184 100644
--- a/lib/debug_locks.c
+++ b/lib/debug_locks.c
@@ -36,7 +36,7 @@ EXPORT_SYMBOL_GPL(debug_locks_silent);
 /*
  * Generic 'turn off all lock debugging' function:
  */
-int debug_locks_off(void)
+noinstr int debug_locks_off(void)
 {
 	if (debug_locks && __debug_locks_off()) {
 		if (!debug_locks_silent) {
-- 
cgit v1.2.3


From af1e56b78534c38bb0e0c712ca70e59f816b74e9 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
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 <tglx@linutronix.de>
Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
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/linux')

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 <pbonzini@redhat.com>
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 <kernellwp@gmail.com>
Tested-by: Wanpeng Li <kernellwp@gmail.com>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/rcuwait.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

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 0958f0cefede403037653e44de0e3332d10b0e1a Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
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 <vkuznets@redhat.com>
Message-Id: <20200525144125.143875-5-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  3 +++
 virt/kvm/kvm_main.c      | 19 ++++++++++++++-----
 2 files changed, 17 insertions(+), 5 deletions(-)

(limited to 'include/linux')

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,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c9c6db5f77c2..e2af6ffce9c9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2510,13 +2510,15 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest_cached);
 
-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)
 {
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int r;
+	gpa_t gpa = ghc->gpa + offset;
 
-	BUG_ON(len > ghc->len);
+	BUG_ON(len + offset > ghc->len);
 
 	if (slots->generation != ghc->generation) {
 		if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
@@ -2527,14 +2529,21 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 		return -EFAULT;
 
 	if (unlikely(!ghc->memslot))
-		return kvm_read_guest(kvm, ghc->gpa, data, len);
+		return kvm_read_guest(kvm, gpa, data, len);
 
-	r = __copy_from_user(data, (void __user *)ghc->hva, len);
+	r = __copy_from_user(data, (void __user *)ghc->hva + offset, len);
 	if (r)
 		return -EFAULT;
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(kvm_read_guest_offset_cached);
+
+int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			  void *data, unsigned long len)
+{
+	return kvm_read_guest_offset_cached(kvm, ghc, data, 0, len);
+}
 EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
 
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
-- 
cgit v1.2.3