kvm : Paravirt-spinlock support for KVM guests

In reply to Konrad Rzeszutek Wilk

Signed-off-by Konrad Rzeszutek Wilk <[email protected]>

---

arch/x86/xen/debugfs.c +0 ~~-104~~

index ef1db19..c8377fb 100644
@@ -19,107 +19,3 @@ struct dentry * __init xen_init_debugfs(void)
 	return d_xen_debug;
 }
 
-struct array_data
-{
-	void *array;
-	unsigned elements;
-};
-
-static int u32_array_open(struct inode *inode, struct file *file)
-{
-	file->private_data = NULL;
-	return nonseekable_open(inode, file);
-}
-
-static size_t format_array(char *buf, size_t bufsize, const char *fmt,
-			   u32 *array, unsigned array_size)
-{
-	size_t ret = 0;
-	unsigned i;
-
-	for(i = 0; i < array_size; i++) {
-		size_t len;
-
-		len = snprintf(buf, bufsize, fmt, array[i]);
-		len++;	/* ' ' or '\n' */
-		ret += len;
-
-		if (buf) {
-			buf += len;
-			bufsize -= len;
-			buf[-1] = (i == array_size-1) ? '\n' : ' ';
-		}
-	}
-
-	ret++;		/* \0 */
-	if (buf)
-		*buf = '\0';
-
-	return ret;
-}
-
-static char *format_array_alloc(const char *fmt, u32 *array, unsigned array_size)
-{
-	size_t len = format_array(NULL, 0, fmt, array, array_size);
-	char *ret;
-
-	ret = kmalloc(len, GFP_KERNEL);
-	if (ret == NULL)
-		return NULL;
-
-	format_array(ret, len, fmt, array, array_size);
-	return ret;
-}
-
-static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len,
-			      loff_t *ppos)
-{
-	struct inode *inode = file->f_path.dentry->d_inode;
-	struct array_data *data = inode->i_private;
-	size_t size;
-
-	if (*ppos == 0) {
-		if (file->private_data) {
-			kfree(file->private_data);
-			file->private_data = NULL;
-		}
-
-		file->private_data = format_array_alloc("%u", data->array, data->elements);
-	}
-
-	size = 0;
-	if (file->private_data)
-		size = strlen(file->private_data);
-
-	return simple_read_from_buffer(buf, len, ppos, file->private_data, size);
-}
-
-static int xen_array_release(struct inode *inode, struct file *file)
-{
-	kfree(file->private_data);
-
-	return 0;
-}
-
-static const struct file_operations u32_array_fops = {
-	.owner	= THIS_MODULE,
-	.open	= u32_array_open,
-	.release= xen_array_release,
-	.read	= u32_array_read,
-	.llseek = no_llseek,
-};
-
-struct dentry *xen_debugfs_create_u32_array(const char *name, umode_t mode,
-					    struct dentry *parent,
-					    u32 *array, unsigned elements)
-{
-	struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL);
-
-	if (data == NULL)
-		return NULL;
-
-	data->array = array;
-	data->elements = elements;
-
-	return debugfs_create_file(name, mode, parent, data, &u32_array_fops);
-}

arch/x86/xen/debugfs.h +0 -4

index 78d2549..12ebf33 100644
@@ -3,8 +3,4 @@
 
 struct dentry * __init xen_init_debugfs(void);
 
-struct dentry *xen_debugfs_create_u32_array(const char *name, umode_t mode,
-					    struct dentry *parent,
-					    u32 *array, unsigned elements);
-
 #endif /* _XEN_DEBUGFS_H */

arch/x86/xen/spinlock.c +1 -1

index 4926974..b74cebb 100644
@@ -314,7 +314,7 @@ static int __init xen_spinlock_debugfs(void)
 	debugfs_create_u64("time_blocked", 0444, d_spin_debug,
 			   &spinlock_stats.time_blocked);
 
-	xen_debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
+	debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
 				     spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
 
 	return 0;

fs/debugfs/file.c +128 -0

140 lines not on this page · raw message

include/linux/debugfs.h +11 -0

index 6169c26..5cb4435 100644
@@ -93,6 +93,10 @@ struct dentry *debugfs_create_regset32(const char *name, mode_t mode,
 int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
 			 int nregs, void __iomem *base, char *prefix);
 
+struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
+					struct dentry *parent,
+					u32 *array, u32 elements);
+
 bool debugfs_initialized(void);
 
 #else

@@ -219,6 +223,13 @@ static inline bool debugfs_initialized(void)
 	return false;
 }
 
+struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
+					struct dentry *parent,
+					u32 *array, u32 elements)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 #endif
 
 #endif

Konrad Rzeszutek Wilk

2012-03-30 20:49 UTC #2 lore raw

Re: [Xen-devel] [PATCH RFC V5 1/6] debugfs: Add support to print u32 array in debugfs

Quoted 9 lines · Raghavendra K T

From: Srivatsa Vaddagiri <[email protected]>
Move the code from Xen to debugfs to make the code common for other users as well.
Signed-off-by Srivatsa Vaddagiri <[email protected]>
Signed-off-by Suzuki Poulose <[email protected]>
Signed-off-by Raghavendra K T <[email protected]>
Signed-off-by Konrad Rzeszutek Wilk <[email protected]>

Greg,

I was thinking to stick this patch in my queue, but I need your OK since it touches fs/debugfs/file.c.

Quoted 320 lines

---

arch/x86/xen/debugfs.c +0 ~~-104~~

index ef1db19..c8377fb 100644
@@ -19,107 +19,3 @@ struct dentry * __init xen_init_debugfs(void)
 	return d_xen_debug;
 }
 
-struct array_data
-{
-	void *array;
-	unsigned elements;
-};
-
-static int u32_array_open(struct inode *inode, struct file *file)
-{
-	file->private_data = NULL;
-	return nonseekable_open(inode, file);
-}
-
-static size_t format_array(char *buf, size_t bufsize, const char *fmt,
-			   u32 *array, unsigned array_size)
-{
-	size_t ret = 0;
-	unsigned i;
-
-	for(i = 0; i < array_size; i++) {
-		size_t len;
-
-		len = snprintf(buf, bufsize, fmt, array[i]);
-		len++;	/* ' ' or '\n' */
-		ret += len;
-
-		if (buf) {
-			buf += len;
-			bufsize -= len;
-			buf[-1] = (i == array_size-1) ? '\n' : ' ';
-		}
-	}
-
-	ret++;		/* \0 */
-	if (buf)
-		*buf = '\0';
-
-	return ret;
-}
-
-static char *format_array_alloc(const char *fmt, u32 *array, unsigned array_size)
-{
-	size_t len = format_array(NULL, 0, fmt, array, array_size);
-	char *ret;
-
-	ret = kmalloc(len, GFP_KERNEL);
-	if (ret == NULL)
-		return NULL;
-
-	format_array(ret, len, fmt, array, array_size);
-	return ret;
-}
-
-static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len,
-			      loff_t *ppos)
-{
-	struct inode *inode = file->f_path.dentry->d_inode;
-	struct array_data *data = inode->i_private;
-	size_t size;
-
-	if (*ppos == 0) {
-		if (file->private_data) {
-			kfree(file->private_data);
-			file->private_data = NULL;
-		}
-
-		file->private_data = format_array_alloc("%u", data->array, data->elements);
-	}
-
-	size = 0;
-	if (file->private_data)
-		size = strlen(file->private_data);
-
-	return simple_read_from_buffer(buf, len, ppos, file->private_data, size);
-}
-
-static int xen_array_release(struct inode *inode, struct file *file)
-{
-	kfree(file->private_data);
-
-	return 0;
-}
-
-static const struct file_operations u32_array_fops = {
-	.owner	= THIS_MODULE,
-	.open	= u32_array_open,
-	.release= xen_array_release,
-	.read	= u32_array_read,
-	.llseek = no_llseek,
-};
-
-struct dentry *xen_debugfs_create_u32_array(const char *name, umode_t mode,
-					    struct dentry *parent,
-					    u32 *array, unsigned elements)
-{
-	struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL);
-
-	if (data == NULL)
-		return NULL;
-
-	data->array = array;
-	data->elements = elements;
-
-	return debugfs_create_file(name, mode, parent, data, &u32_array_fops);
-}

arch/x86/xen/debugfs.h +0 -4

index 78d2549..12ebf33 100644
@@ -3,8 +3,4 @@
 
 struct dentry * __init xen_init_debugfs(void);
 
-struct dentry *xen_debugfs_create_u32_array(const char *name, umode_t mode,
-					    struct dentry *parent,
-					    u32 *array, unsigned elements);
-
 #endif /* _XEN_DEBUGFS_H */

arch/x86/xen/spinlock.c +1 -1

index 4926974..b74cebb 100644
@@ -314,7 +314,7 @@ static int __init xen_spinlock_debugfs(void)
 	debugfs_create_u64("time_blocked", 0444, d_spin_debug,
 			   &spinlock_stats.time_blocked);
 
-	xen_debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
+	debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
 				     spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
 
 	return 0;

fs/debugfs/file.c +128 -0

index ef023ee..cb6cff3 100644
@@ -20,6 +20,7 @@
 #include <linux/namei.h>
 #include <linux/debugfs.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 
 static ssize_t default_read_file(struct file *file, char __user *buf,
 				 size_t count, loff_t *ppos)

@@ -528,6 +529,133 @@ struct dentry *debugfs_create_blob(const char *name, umode_t mode,
 }
 EXPORT_SYMBOL_GPL(debugfs_create_blob);
 
+struct array_data {
+	void *array;
+	u32 elements;
+};
+
+static int u32_array_open(struct inode *inode, struct file *file)
+{
+	file->private_data = NULL;
+	return nonseekable_open(inode, file);
+}
+
+static size_t format_array(char *buf, size_t bufsize, const char *fmt,
+			   u32 *array, u32 array_size)
+{
+	size_t ret = 0;
+	u32 i;
+
+	for (i = 0; i < array_size; i++) {
+		size_t len;
+
+		len = snprintf(buf, bufsize, fmt, array[i]);
+		len++;	/* ' ' or '\n' */
+		ret += len;
+
+		if (buf) {
+			buf += len;
+			bufsize -= len;
+			buf[-1] = (i == array_size-1) ? '\n' : ' ';
+		}
+	}
+
+	ret++;		/* \0 */
+	if (buf)
+		*buf = '\0';
+
+	return ret;
+}
+
+static char *format_array_alloc(const char *fmt, u32 *array,
+						u32 array_size)
+{
+	size_t len = format_array(NULL, 0, fmt, array, array_size);
+	char *ret;
+
+	ret = kmalloc(len, GFP_KERNEL);
+	if (ret == NULL)
+		return NULL;
+
+	format_array(ret, len, fmt, array, array_size);
+	return ret;
+}
+
+static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len,
+			      loff_t *ppos)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct array_data *data = inode->i_private;
+	size_t size;
+
+	if (*ppos == 0) {
+		if (file->private_data) {
+			kfree(file->private_data);
+			file->private_data = NULL;
+		}
+
+		file->private_data = format_array_alloc("%u", data->array,
+							      data->elements);
+	}
+
+	size = 0;
+	if (file->private_data)
+		size = strlen(file->private_data);
+
+	return simple_read_from_buffer(buf, len, ppos,
+					file->private_data, size);
+}
+
+static int u32_array_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+
+	return 0;
+}
+
+static const struct file_operations u32_array_fops = {
+	.owner	 = THIS_MODULE,
+	.open	 = u32_array_open,
+	.release = u32_array_release,
+	.read	 = u32_array_read,
+	.llseek  = no_llseek,
+};
+
+/**
+ * debugfs_create_u32_array - create a debugfs file that is used to read u32
+ * array.
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have.
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is %NULL, then the
+ *          file will be created in the root of the debugfs filesystem.
+ * @array: u32 array that provides data.
+ * @elements: total number of elements in the array.
+ *
+ * This function creates a file in debugfs with the given name that exports
+ * @array as data. If the @mode variable is so set it can be read from.
+ * Writing is not supported. Seek within the file is also not supported.
+ * Once array is created its size can not be changed.
+ *
+ * The function returns a pointer to dentry on success. If debugfs is not
+ * enabled in the kernel, the value -%ENODEV will be returned.
+ */
+struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
+					    struct dentry *parent,
+					    u32 *array, u32 elements)
+{
+	struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL);
+
+	if (data == NULL)
+		return NULL;
+
+	data->array = array;
+	data->elements = elements;
+
+	return debugfs_create_file(name, mode, parent, data, &u32_array_fops);
+}
+EXPORT_SYMBOL_GPL(debugfs_create_u32_array);
+
 #ifdef CONFIG_HAS_IOMEM
 
 /*

include/linux/debugfs.h +11 -0

index 6169c26..5cb4435 100644
@@ -93,6 +93,10 @@ struct dentry *debugfs_create_regset32(const char *name, mode_t mode,
 int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
 			 int nregs, void __iomem *base, char *prefix);
 
+struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
+					struct dentry *parent,
+					u32 *array, u32 elements);
+
 bool debugfs_initialized(void);
 
 #else

@@ -219,6 +223,13 @@ static inline bool debugfs_initialized(void)
 	return false;
 }
 
+struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
+					struct dentry *parent,
+					u32 *array, u32 elements)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 #endif
 
 #endif

_______________________________________________
Xen-devel mailing list
[email protected]
http://lists.xen.org/xen-devel

Greg KH

maintainer Acked-by

2012-03-30 21:11 UTC #3 lore raw

Re: [Xen-devel] [PATCH RFC V5 1/6] debugfs: Add support to print u32 array in debugfs

Quoted 11 lines · Konrad Rzeszutek Wilk

Quoted 9 lines · Raghavendra K T
From: Srivatsa Vaddagiri <[email protected]>
Move the code from Xen to debugfs to make the code common for other users as well.
Signed-off-by Srivatsa Vaddagiri <[email protected]>
Signed-off-by Suzuki Poulose <[email protected]>
Signed-off-by Raghavendra K T <[email protected]>
Signed-off-by Konrad Rzeszutek Wilk <[email protected]>

Quoted 4 lines

Greg,
I was thinking to stick this patch in my queue, but I need your OK since it touches fs/debugfs/file.c.

That's fine with me:

Acked-by Greg Kroah-Hartman <[email protected]>

Greg KH

maintainer Acked-by

2012-03-30 21:11 UTC #4 lore raw

Re: [Xen-devel] [PATCH RFC V5 1/6] debugfs: Add support to print u32 array in debugfs

Quoted 11 lines · Konrad Rzeszutek Wilk

Quoted 9 lines · Raghavendra K T
From: Srivatsa Vaddagiri <[email protected]>
Move the code from Xen to debugfs to make the code common for other users as well.
Signed-off-by Srivatsa Vaddagiri <[email protected]>
Signed-off-by Suzuki Poulose <[email protected]>
Signed-off-by Raghavendra K T <[email protected]>
Signed-off-by Konrad Rzeszutek Wilk <[email protected]>

Quoted 4 lines

Greg,
I was thinking to stick this patch in my queue, but I need your OK since it touches fs/debugfs/file.c.

That's fine with me:

Acked-by Greg Kroah-Hartman <[email protected]>

Raghavendra K T

author

2012-03-23 08:07 UTC #5 lore raw

RFC PATCH v5 2/6 kvm hypervisor : Add a hypercall to KVM hypervisor to support pv-ticketlocks

From: Srivatsa Vaddagiri <[email protected]>

KVM_HC_KICK_CPU allows the calling vcpu to kick another vcpu out of halt state.

The presence of these hypercalls is indicated to guest via KVM_FEATURE_PV_UNHALT/KVM_CAP_PV_UNHALT.

Signed-off-by Srivatsa Vaddagiri <[email protected]>

---

arch/x86/include/asm/kvm_para.h +3 -0

index 734c376..9234f13 100644
@@ -16,12 +16,14 @@
 #define KVM_FEATURE_CLOCKSOURCE		0
 #define KVM_FEATURE_NOP_IO_DELAY	1
 #define KVM_FEATURE_MMU_OP		2
+
 /* This indicates that the new set of kvmclock msrs
  * are available. The use of 0x11 and 0x12 is deprecated
  */
 #define KVM_FEATURE_CLOCKSOURCE2        3
 #define KVM_FEATURE_ASYNC_PF		4
 #define KVM_FEATURE_STEAL_TIME		5
+#define KVM_FEATURE_PV_UNHALT		6
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.

@@ -32,6 +34,7 @@
 #define MSR_KVM_SYSTEM_TIME 0x12
 
 #define KVM_MSR_ENABLED 1
+
 /* Custom MSRs falls in the range 0x4b564d00-0x4b564dff */
 #define MSR_KVM_WALL_CLOCK_NEW  0x4b564d00
 #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01

arch/x86/kvm/cpuid.c +2 -1

index 89b02bf..61388b9 100644
@@ -408,7 +408,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			     (1 << KVM_FEATURE_NOP_IO_DELAY) |
 			     (1 << KVM_FEATURE_CLOCKSOURCE2) |
 			     (1 << KVM_FEATURE_ASYNC_PF) |
-			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
+			     (1 << KVM_FEATURE_PV_UNHALT);
 
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);

arch/x86/kvm/x86.c +30 -0

index 9cbfc06..bd5ef91 100644
@@ -2079,6 +2079,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_XSAVE:
 	case KVM_CAP_ASYNC_PF:
 	case KVM_CAP_GET_TSC_KHZ:
+	case KVM_CAP_PV_UNHALT:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:

@@ -4913,6 +4914,30 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+/*
+ * kvm_pv_kick_cpu_op:  Kick a vcpu.
+ *
+ * @apicid - apicid of vcpu to be kicked.
+ */
+static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_apic_present(vcpu))
+			continue;
+
+		if (kvm_apic_match_dest(vcpu, 0, 0, apicid, 0))
+			break;
+	}
+	if (vcpu) {
+		vcpu->pv_unhalted = 1;
+		smp_mb();
+		kvm_vcpu_kick(vcpu);
+	}
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;

@@ -4946,6 +4971,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
+	case KVM_HC_KICK_CPU:
+		kvm_pv_kick_cpu_op(vcpu->kvm, a0);
+		ret = 0;
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;

@@ -6174,6 +6203,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 		!vcpu->arch.apf.halted)
 		|| !list_empty_careful(&vcpu->async_pf.done)
 		|| vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
+		|| vcpu->pv_unhalted
 		|| atomic_read(&vcpu->arch.nmi_queued) ||
 		(kvm_arch_interrupt_allowed(vcpu) &&
 		 kvm_cpu_has_interrupt(vcpu));

include/linux/kvm.h +1 -0

index 68e67e5..e822d96 100644
@@ -558,6 +558,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_PAPR 68
 #define KVM_CAP_S390_GMAP 71
 #define KVM_CAP_TSC_DEADLINE_TIMER 72
+#define KVM_CAP_PV_UNHALT 73
 
 #ifdef KVM_CAP_IRQ_ROUTING

include/linux/kvm_host.h +1 -0

index 900c763..433ae97 100644
@@ -158,6 +158,7 @@ struct kvm_vcpu {
 #endif
 
 	struct kvm_vcpu_arch arch;
+	int pv_unhalted;
 };
 
 static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)

include/linux/kvm_para.h +1 -0

index ff476dd..38226e1 100644
@@ -19,6 +19,7 @@
 #define KVM_HC_MMU_OP			2
 #define KVM_HC_FEATURES			3
 #define KVM_HC_PPC_MAP_MAGIC_PAGE	4
+#define KVM_HC_KICK_CPU			5
 
 /*
  * hypercalls use architecture specific

virt/kvm/kvm_main.c +4 -0

index a91f980..d3b98b1 100644
@@ -226,6 +226,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->kvm = kvm;
 	vcpu->vcpu_id = id;
 	vcpu->pid = NULL;
+	vcpu->pv_unhalted = 0;
 	init_waitqueue_head(&vcpu->wq);
 	kvm_async_pf_vcpu_init(vcpu);

@@ -1567,6 +1568,9 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
 		if (kvm_arch_vcpu_runnable(vcpu)) {
+			vcpu->pv_unhalted = 0;
+			/* preventing reordering should be enough here */
+			barrier();
 			kvm_make_request(KVM_REQ_UNHALT, vcpu);
 			break;
 		}

Marcelo Tosatti

2012-04-12 00:06 UTC #6 lore raw

Re: [PATCH RFC V5 2/6] kvm hypervisor : Add a hypercall to KVM hypervisor to support pv-ticketlocks

Quoted 163 lines · Raghavendra K T

From: Srivatsa Vaddagiri <[email protected]>

KVM_HC_KICK_CPU allows the calling vcpu to kick another vcpu out of halt state.

The presence of these hypercalls is indicated to guest via KVM_FEATURE_PV_UNHALT/KVM_CAP_PV_UNHALT.

Signed-off-by Srivatsa Vaddagiri <[email protected]>

---

arch/x86/include/asm/kvm_para.h +3 -0

index 734c376..9234f13 100644
@@ -16,12 +16,14 @@
 #define KVM_FEATURE_CLOCKSOURCE		0
 #define KVM_FEATURE_NOP_IO_DELAY	1
 #define KVM_FEATURE_MMU_OP		2
+
 /* This indicates that the new set of kvmclock msrs
  * are available. The use of 0x11 and 0x12 is deprecated
  */
 #define KVM_FEATURE_CLOCKSOURCE2        3
 #define KVM_FEATURE_ASYNC_PF		4
 #define KVM_FEATURE_STEAL_TIME		5
+#define KVM_FEATURE_PV_UNHALT		6
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.

@@ -32,6 +34,7 @@
 #define MSR_KVM_SYSTEM_TIME 0x12
 
 #define KVM_MSR_ENABLED 1
+
 /* Custom MSRs falls in the range 0x4b564d00-0x4b564dff */
 #define MSR_KVM_WALL_CLOCK_NEW  0x4b564d00
 #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01

arch/x86/kvm/cpuid.c +2 -1

index 89b02bf..61388b9 100644
@@ -408,7 +408,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			     (1 << KVM_FEATURE_NOP_IO_DELAY) |
 			     (1 << KVM_FEATURE_CLOCKSOURCE2) |
 			     (1 << KVM_FEATURE_ASYNC_PF) |
-			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
+			     (1 << KVM_FEATURE_PV_UNHALT);
 
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);

arch/x86/kvm/x86.c +30 -0

index 9cbfc06..bd5ef91 100644
@@ -2079,6 +2079,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_XSAVE:
 	case KVM_CAP_ASYNC_PF:
 	case KVM_CAP_GET_TSC_KHZ:
+	case KVM_CAP_PV_UNHALT:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:

@@ -4913,6 +4914,30 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+/*
+ * kvm_pv_kick_cpu_op:  Kick a vcpu.
+ *
+ * @apicid - apicid of vcpu to be kicked.
+ */
+static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_apic_present(vcpu))
+			continue;
+
+		if (kvm_apic_match_dest(vcpu, 0, 0, apicid, 0))
+			break;
+	}
+	if (vcpu) {
+		vcpu->pv_unhalted = 1;
+		smp_mb();
+		kvm_vcpu_kick(vcpu);
+	}
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;

@@ -4946,6 +4971,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
+	case KVM_HC_KICK_CPU:
+		kvm_pv_kick_cpu_op(vcpu->kvm, a0);
+		ret = 0;
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;

@@ -6174,6 +6203,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 		!vcpu->arch.apf.halted)
 		|| !list_empty_careful(&vcpu->async_pf.done)
 		|| vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
+		|| vcpu->pv_unhalted
 		|| atomic_read(&vcpu->arch.nmi_queued) ||
 		(kvm_arch_interrupt_allowed(vcpu) &&
 		 kvm_cpu_has_interrupt(vcpu));

include/linux/kvm.h +1 -0

index 68e67e5..e822d96 100644
@@ -558,6 +558,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_PAPR 68
 #define KVM_CAP_S390_GMAP 71
 #define KVM_CAP_TSC_DEADLINE_TIMER 72
+#define KVM_CAP_PV_UNHALT 73
 
 #ifdef KVM_CAP_IRQ_ROUTING

include/linux/kvm_host.h +1 -0

index 900c763..433ae97 100644
@@ -158,6 +158,7 @@ struct kvm_vcpu {
 #endif
 
 	struct kvm_vcpu_arch arch;
+	int pv_unhalted;
 };
 
 static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)

include/linux/kvm_para.h +1 -0

index ff476dd..38226e1 100644
@@ -19,6 +19,7 @@
 #define KVM_HC_MMU_OP			2
 #define KVM_HC_FEATURES			3
 #define KVM_HC_PPC_MAP_MAGIC_PAGE	4
+#define KVM_HC_KICK_CPU			5
 
 /*
  * hypercalls use architecture specific

virt/kvm/kvm_main.c +1 -0

index a91f980..d3b98b1 100644
@@ -226,6 +226,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->kvm = kvm;
 	vcpu->vcpu_id = id;
 	vcpu->pid = NULL;
+	vcpu->pv_unhalted = 0;
 	init_waitqueue_head(&vcpu->wq);
 	kvm_async_pf_vcpu_init(vcpu);

virt/kvm/kvm_main.c void kvm_vcpu_block(struct kvm_vcpu *vcpu) · line 1573

Quoted 6 lines

virt/kvm/kvm_main.c +3 -0

@@ -1567,6 +1568,9 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
 		if (kvm_arch_vcpu_runnable(vcpu)) {
+			vcpu->pv_unhalted = 0;
+			/* preventing reordering should be enough here */
+			barrier();

Is it always OK to erase the notification, even in case an unrelated event such as interrupt was the source of wakeup?

It would be easier to verify that notifications are not lost with atomic

test_and_clear(pv_unhalted).

Also x86 specific code should remain in arch/x86/kvm/

Marcelo Tosatti

2012-04-12 00:29 UTC #7 lore raw

Re: [PATCH RFC V5 2/6] kvm hypervisor : Add a hypercall to KVM hypervisor to support pv-ticketlocks

Quoted 166 lines · Marcelo Tosatti

Quoted 165 lines · Raghavendra K T

From: Srivatsa Vaddagiri <[email protected]>

KVM_HC_KICK_CPU allows the calling vcpu to kick another vcpu out of halt state.

The presence of these hypercalls is indicated to guest via KVM_FEATURE_PV_UNHALT/KVM_CAP_PV_UNHALT.

Signed-off-by Srivatsa Vaddagiri <[email protected]>

---

arch/x86/include/asm/kvm_para.h +3 -0

index 734c376..9234f13 100644
@@ -16,12 +16,14 @@
 #define KVM_FEATURE_CLOCKSOURCE		0
 #define KVM_FEATURE_NOP_IO_DELAY	1
 #define KVM_FEATURE_MMU_OP		2
+
 /* This indicates that the new set of kvmclock msrs
  * are available. The use of 0x11 and 0x12 is deprecated
  */
 #define KVM_FEATURE_CLOCKSOURCE2        3
 #define KVM_FEATURE_ASYNC_PF		4
 #define KVM_FEATURE_STEAL_TIME		5
+#define KVM_FEATURE_PV_UNHALT		6
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.

@@ -32,6 +34,7 @@
 #define MSR_KVM_SYSTEM_TIME 0x12
 
 #define KVM_MSR_ENABLED 1
+
 /* Custom MSRs falls in the range 0x4b564d00-0x4b564dff */
 #define MSR_KVM_WALL_CLOCK_NEW  0x4b564d00
 #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01

arch/x86/kvm/cpuid.c +2 -1

index 89b02bf..61388b9 100644
@@ -408,7 +408,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			     (1 << KVM_FEATURE_NOP_IO_DELAY) |
 			     (1 << KVM_FEATURE_CLOCKSOURCE2) |
 			     (1 << KVM_FEATURE_ASYNC_PF) |
-			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
+			     (1 << KVM_FEATURE_PV_UNHALT);
 
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);

arch/x86/kvm/x86.c +30 -0

index 9cbfc06..bd5ef91 100644
@@ -2079,6 +2079,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_XSAVE:
 	case KVM_CAP_ASYNC_PF:
 	case KVM_CAP_GET_TSC_KHZ:
+	case KVM_CAP_PV_UNHALT:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:

@@ -4913,6 +4914,30 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+/*
+ * kvm_pv_kick_cpu_op:  Kick a vcpu.
+ *
+ * @apicid - apicid of vcpu to be kicked.
+ */
+static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_apic_present(vcpu))
+			continue;
+
+		if (kvm_apic_match_dest(vcpu, 0, 0, apicid, 0))
+			break;
+	}
+	if (vcpu) {
+		vcpu->pv_unhalted = 1;
+		smp_mb();
+		kvm_vcpu_kick(vcpu);
+	}
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;

@@ -4946,6 +4971,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
+	case KVM_HC_KICK_CPU:
+		kvm_pv_kick_cpu_op(vcpu->kvm, a0);
+		ret = 0;
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;

@@ -6174,6 +6203,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 		!vcpu->arch.apf.halted)
 		|| !list_empty_careful(&vcpu->async_pf.done)
 		|| vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
+		|| vcpu->pv_unhalted
 		|| atomic_read(&vcpu->arch.nmi_queued) ||
 		(kvm_arch_interrupt_allowed(vcpu) &&
 		 kvm_cpu_has_interrupt(vcpu));

include/linux/kvm.h +1 -0

index 68e67e5..e822d96 100644
@@ -558,6 +558,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_PAPR 68
 #define KVM_CAP_S390_GMAP 71
 #define KVM_CAP_TSC_DEADLINE_TIMER 72
+#define KVM_CAP_PV_UNHALT 73
 
 #ifdef KVM_CAP_IRQ_ROUTING

include/linux/kvm_host.h +1 -0

index 900c763..433ae97 100644
@@ -158,6 +158,7 @@ struct kvm_vcpu {
 #endif
 
 	struct kvm_vcpu_arch arch;
+	int pv_unhalted;
 };
 
 static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)

include/linux/kvm_para.h +1 -0

index ff476dd..38226e1 100644
@@ -19,6 +19,7 @@
 #define KVM_HC_MMU_OP			2
 #define KVM_HC_FEATURES			3
 #define KVM_HC_PPC_MAP_MAGIC_PAGE	4
+#define KVM_HC_KICK_CPU			5
 
 /*
  * hypercalls use architecture specific

virt/kvm/kvm_main.c +1 -0

index a91f980..d3b98b1 100644
@@ -226,6 +226,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->kvm = kvm;
 	vcpu->vcpu_id = id;
 	vcpu->pid = NULL;
+	vcpu->pv_unhalted = 0;
 	init_waitqueue_head(&vcpu->wq);
 	kvm_async_pf_vcpu_init(vcpu);

@@ -1567,6 +1568,9 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);

Quoted 7 lines

virt/kvm/kvm_main.c void kvm_vcpu_block(struct kvm_vcpu *vcpu) · line 1573
Quoted 4 lines
virt/kvm/kvm_main.c +3 -0
 		if (kvm_arch_vcpu_runnable(vcpu)) {
+			vcpu->pv_unhalted = 0;
+			/* preventing reordering should be enough here */
+			barrier();
Is it always OK to erase the notification, even in case an unrelated event such as interrupt was the source of wakeup?

Note i am only asking whether it is OK to lose a notification, not requesting a change to atomic test-and-clear.

It would be nice to have a comment explaining it.

Quoted 6 lines

It would be easier to verify that notifications are not lost with atomic test_and_clear(pv_unhalted).
Also x86 specific code should remain in arch/x86/kvm/

Raghavendra K T

author

2012-04-17 07:06 UTC #8 lore raw

Re: [PATCH RFC V5 2/6] kvm hypervisor : Add a hypercall to KVM hypervisor to support pv-ticketlocks

Quoted 4 lines · Marcelo Tosatti

Quoted 3 lines · Marcelo Tosatti
Quoted 2 lines · Raghavendra K T
From: Srivatsa Vaddagiri<[email protected]>

[...]

		barrier();

Quoted 6 lines

Quoted 3 lines
Is it always OK to erase the notification, even in case an unrelated event such as interrupt was the source of wakeup?
Note i am only asking whether it is OK to lose a notification, not requesting a change to atomic test-and-clear.

Yes.. got your point.
IMO, this is the only (safe) place where it can clear kicked(pv_unhalted) flag. Since it is going to be runnable.

and you are also right in having concern on unwanted clear of flag since that would result in vcpu /vm hangs eventually.

Hope I did not miss anything.

Quoted 3 lines

It would be nice to have a comment explaining it.

Sure will do that

Quoted 1 line

Quoted 1 line

Raghavendra K T

author

2012-04-17 07:06 UTC #9 lore raw

Re: [PATCH RFC V5 2/6] kvm hypervisor : Add a hypercall to KVM hypervisor to support pv-ticketlocks

Quoted 4 lines · Marcelo Tosatti

Quoted 3 lines · Marcelo Tosatti
Quoted 2 lines · Raghavendra K T
From: Srivatsa Vaddagiri<[email protected]>

[...]

		barrier();

Quoted 6 lines

Quoted 3 lines
Is it always OK to erase the notification, even in case an unrelated event such as interrupt was the source of wakeup?
Note i am only asking whether it is OK to lose a notification, not requesting a change to atomic test-and-clear.

Yes.. got your point.
IMO, this is the only (safe) place where it can clear kicked(pv_unhalted) flag. Since it is going to be runnable.

and you are also right in having concern on unwanted clear of flag since that would result in vcpu /vm hangs eventually.

Hope I did not miss anything.

Quoted 3 lines

It would be nice to have a comment explaining it.

Sure will do that

Quoted 1 line

Quoted 1 line

Raghavendra K T

author

2012-04-17 03:49 UTC #10 lore raw

Re: [PATCH RFC V5 2/6] kvm hypervisor : Add a hypercall to KVM hypervisor to support pv-ticketlocks

Sorry for late reply,
was on vacation for a week (without IMAP access :( )

Quoted 2 lines · Marcelo Tosatti

Quoted 1 line · Raghavendra K T
From: Srivatsa Vaddagiri<[email protected]>

[snip]

Quoted 10 lines

virt/kvm/kvm_main.c void kvm_vcpu_block(struct kvm_vcpu *vcpu) · line 1573
Quoted 7 lines
virt/kvm/kvm_main.c +3 -0
@@ -1567,6 +1568,9 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
  		prepare_to_wait(&vcpu->wq,&wait, TASK_INTERRUPTIBLE);
 
  		if (kvm_arch_vcpu_runnable(vcpu)) {
+			vcpu->pv_unhalted = 0;
+			/* preventing reordering should be enough here */
+			barrier();
Is it always OK to erase the notification, even in case an unrelated event such as interrupt was the source of wakeup?

Erasing notification is not good, But I think in this case,

kvm_make_request(KVM_REQ_UNHALT, vcpu);

below this would take care of the rest.

Quoted 4 lines

It would be easier to verify that notifications are not lost with atomic
test_and_clear(pv_unhalted).

true, I 'll verify that (with pv_unhalt as atomic variable). my heart says current code is just fine, since we are about to unblock.

Quoted 3 lines

Also x86 specific code should remain in arch/x86/kvm/

I agree. 'll have clear function in arch/x86/kvm and add stub to rest of the archs

Quoted 1 line

Raghavendra K T

author

2012-04-17 03:49 UTC #11 lore raw

Re: [PATCH RFC V5 2/6] kvm hypervisor : Add a hypercall to KVM hypervisor to support pv-ticketlocks

Sorry for late reply,
was on vacation for a week (without IMAP access :( )

Quoted 2 lines · Marcelo Tosatti

Quoted 1 line · Raghavendra K T
From: Srivatsa Vaddagiri<[email protected]>

[snip]

Quoted 10 lines

virt/kvm/kvm_main.c void kvm_vcpu_block(struct kvm_vcpu *vcpu) · line 1573
Quoted 7 lines
virt/kvm/kvm_main.c +3 -0
@@ -1567,6 +1568,9 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
  		prepare_to_wait(&vcpu->wq,&wait, TASK_INTERRUPTIBLE);
 
  		if (kvm_arch_vcpu_runnable(vcpu)) {
+			vcpu->pv_unhalted = 0;
+			/* preventing reordering should be enough here */
+			barrier();
Is it always OK to erase the notification, even in case an unrelated event such as interrupt was the source of wakeup?

Erasing notification is not good, But I think in this case,

kvm_make_request(KVM_REQ_UNHALT, vcpu);

below this would take care of the rest.

Quoted 4 lines

It would be easier to verify that notifications are not lost with atomic
test_and_clear(pv_unhalted).

true, I 'll verify that (with pv_unhalt as atomic variable). my heart says current code is just fine, since we are about to unblock.

Quoted 3 lines

Also x86 specific code should remain in arch/x86/kvm/

I agree. 'll have clear function in arch/x86/kvm and add stub to rest of the archs

Quoted 1 line

Raghavendra K T

author

2012-03-23 08:07 UTC #12 lore raw

RFC PATCH v5 3/6 kvm : Add unhalt msr to aid (live) migration

From: Raghavendra K T <[email protected]>

Currently guest does not need to know pv_unhalt state and intended to be used via GET/SET_MSR ioctls during migration.

---

arch/x86/include/asm/kvm_para.h +1 -0

index 9234f13..46f9751 100644
@@ -40,6 +40,7 @@
 #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01
 #define MSR_KVM_ASYNC_PF_EN 0x4b564d02
 #define MSR_KVM_STEAL_TIME  0x4b564d03
+#define MSR_KVM_PV_UNHALT   0x4b564d04
 
 struct kvm_steal_time {
 	__u64 steal;

arch/x86/kvm/x86.c +8 -2

index bd5ef91..38e6c47 100644
@@ -784,12 +784,13 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	9
+#define KVM_SAVE_MSRS_BEGIN	10
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
 	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
+	MSR_KVM_PV_UNHALT,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_STAR,
 #ifdef CONFIG_X86_64

@@ -1606,7 +1607,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 
 		break;
-
+	case MSR_KVM_PV_UNHALT:
+		vcpu->pv_unhalted = (u32) data;
+		break;
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:

@@ -1917,6 +1920,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_KVM_STEAL_TIME:
 		data = vcpu->arch.st.msr_val;
 		break;
+	case MSR_KVM_PV_UNHALT:
+		data = (u64)vcpu->pv_unhalted;
+		break;
 	case MSR_IA32_P5_MC_ADDR:
 	case MSR_IA32_P5_MC_TYPE:
 	case MSR_IA32_MCG_CAP:

Marcelo Tosatti

2012-04-12 00:15 UTC #13 lore raw

Re: [PATCH RFC V5 3/6] kvm : Add unhalt msr to aid (live) migration

Quoted 50 lines · Raghavendra K T

From: Raghavendra K T <[email protected]>

Currently guest does not need to know pv_unhalt state and intended to be used via GET/SET_MSR ioctls during migration.

---

arch/x86/include/asm/kvm_para.h +1 -0

index 9234f13..46f9751 100644
@@ -40,6 +40,7 @@
 #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01
 #define MSR_KVM_ASYNC_PF_EN 0x4b564d02
 #define MSR_KVM_STEAL_TIME  0x4b564d03
+#define MSR_KVM_PV_UNHALT   0x4b564d04
 
 struct kvm_steal_time {
 	__u64 steal;

arch/x86/kvm/x86.c +5 -2

index bd5ef91..38e6c47 100644
@@ -784,12 +784,13 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	9
+#define KVM_SAVE_MSRS_BEGIN	10
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
 	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
+	MSR_KVM_PV_UNHALT,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_STAR,
 #ifdef CONFIG_X86_64

@@ -1606,7 +1607,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 
 		break;
-
+	case MSR_KVM_PV_UNHALT:
+		vcpu->pv_unhalted = (u32) data;
+		break;
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:

arch/x86/kvm/x86.c int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) · line 1928

Quoted 9 lines

arch/x86/kvm/x86.c +3 -0

@@ -1917,6 +1920,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_KVM_STEAL_TIME:
 		data = vcpu->arch.st.msr_val;
 		break;
+	case MSR_KVM_PV_UNHALT:
+		data = (u64)vcpu->pv_unhalted;
+		break;
 	case MSR_IA32_P5_MC_ADDR:
 	case MSR_IA32_P5_MC_TYPE:
 	case MSR_IA32_MCG_CAP:

Unless there is a reason to use an MSR, should use a normal ioctl such as KVM_{GET,SET}_MP_STATE.

Raghavendra K T

author

2012-04-17 07:17 UTC #14 lore raw

Re: [PATCH RFC V5 3/6] kvm : Add unhalt msr to aid (live) migration

Quoted 3 lines · Marcelo Tosatti

Quoted 2 lines · Raghavendra K T
From: Raghavendra K T<[email protected]>

[...]

Quoted 5 lines

Unless there is a reason to use an MSR, should use a normal ioctl such as KVM_{GET,SET}_MP_STATE.

I agree with you. In the current implementation, since we are not doing any communication between host/guest (on this flag), I too felt MSR is an overkill for this.

IMO, patch like below should do the job, which I am planning to include in next version of patch.
Let me know if you foresee any side-effects.

---

arch/x86/kvm/x86.c +3 -1

index aa44292..5c81a66 100644
@@ -5691,7 +5691,9 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	mp_state->mp_state = vcpu->arch.mp_state;
+	mp_state->mp_state = (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
+				vcpu->pv_unhalted)?
+				KVM_MP_STATE_RUNNABLE : vcpu->arch.mp_state;
 	return 0;
 }

Raghavendra K T

author

2012-04-17 07:17 UTC #15 lore raw

Re: [PATCH RFC V5 3/6] kvm : Add unhalt msr to aid (live) migration

Quoted 3 lines · Marcelo Tosatti

Quoted 2 lines · Raghavendra K T
From: Raghavendra K T<[email protected]>

[...]

Quoted 5 lines

Unless there is a reason to use an MSR, should use a normal ioctl such as KVM_{GET,SET}_MP_STATE.

I agree with you. In the current implementation, since we are not doing any communication between host/guest (on this flag), I too felt MSR is an overkill for this.

IMO, patch like below should do the job, which I am planning to include in next version of patch.
Let me know if you foresee any side-effects.

---

arch/x86/kvm/x86.c +3 -1

index aa44292..5c81a66 100644
@@ -5691,7 +5691,9 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	mp_state->mp_state = vcpu->arch.mp_state;
+	mp_state->mp_state = (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
+				vcpu->pv_unhalted)?
+				KVM_MP_STATE_RUNNABLE : vcpu->arch.mp_state;
 	return 0;
 }

Raghavendra K T

author

2012-03-23 08:08 UTC #16 lore raw

RFC PATCH v5 4/6 kvm guest : Added configuration support to enable debug information for KVM Guests

From: Srivatsa Vaddagiri <[email protected]>

Signed-off-by Srivatsa Vaddagiri <[email protected]>

---

arch/x86/Kconfig +9 -0

index 10c28ec..a4530bd 100644
@@ -600,6 +600,15 @@ config KVM_GUEST
 	  This option enables various optimizations for running under the KVM
 	  hypervisor.
 
+config KVM_DEBUG_FS
+	bool "Enable debug information for KVM Guests in debugfs"
+	depends on KVM_GUEST && DEBUG_FS
+	default n
+	---help---
+	  This option enables collection of various statistics for KVM guest.
+   	  Statistics are displayed in debugfs filesystem. Enabling this option
+	  may incur significant overhead.
+
 source "arch/x86/lguest/Kconfig"
 
 config PARAVIRT

Raghavendra K T

author

2012-03-23 08:08 UTC #17 lore raw

RFC PATCH v5 5/6 kvm : pv-ticketlocks support for linux guests running on KVM hypervisor

From: Srivatsa Vaddagiri <[email protected]>

During smp_boot_cpus paravirtualied KVM guest detects if the hypervisor has required feature (KVM_FEATURE_PV_UNHALT) to support pv-ticketlocks. If so,
support for pv-ticketlocks is registered via pv_lock_ops.

Use KVM_HC_KICK_CPU hypercall to wakeup waiting/halted vcpu.

Signed-off-by Srivatsa Vaddagiri <[email protected]>

---

arch/x86/include/asm/kvm_para.h +12 -2

index 46f9751..2888c45 100644
@@ -197,10 +197,20 @@ void kvm_async_pf_task_wait(u32 token);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
 extern void kvm_disable_steal_time(void);
-#else
-#define kvm_guest_init() do { } while (0)
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void __init kvm_spinlock_init(void);
+#else /* !CONFIG_PARAVIRT_SPINLOCKS */
+static void kvm_spinlock_init(void)
+{
+}
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+#else /* CONFIG_KVM_GUEST */
+#define kvm_guest_init() do {} while (0)
 #define kvm_async_pf_task_wait(T) do {} while(0)
 #define kvm_async_pf_task_wake(T) do {} while(0)
+
 static inline u32 kvm_read_and_reset_pf_reason(void)
 {
 	return 0;

arch/x86/kernel/kvm.c +254 -0

269 lines not on this page · raw message

Raghavendra K T

author

2012-03-23 08:08 UTC #18 lore raw

RFC PATCH v5 6/6 Documentation/kvm : Add documentation on Hypercalls and features used for PV spinlock

From: Raghavendra K T <[email protected]>

KVM_HC_KICK_CPU hypercall added to wakeup halted vcpu in paravirtual spinlock enabled guest.

KVM_FEATURE_PV_UNHALT enables guest to check whether pv spinlock can be enabled in guest. support in host is queried via ioctl(KVM_CHECK_EXTENSION, KVM_CAP_PV_UNHALT)

Thanks Alex for KVM_HC_FEATURES inputs and Vatsa for rewriting KVM_HC_KICK_CPU

Signed-off-by Srivatsa Vaddagiri <[email protected]>

---

Documentation/virtual/kvm/api.txt +7 -0

index e1d94bf..cf8bf3b 100644
@@ -1109,6 +1109,13 @@ support.  Instead it is reported via
 if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
 feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
 
+Paravirtualized ticket spinlocks can be enabled in guest by checking whether
+support exists in host via,
+
+  ioctl(KVM_CHECK_EXTENSION, KVM_CAP_PV_UNHALT)
+
+if this call return true, guest can use the feature.
+
 4.47 KVM_PPC_GET_PVINFO
 
 Capability: KVM_CAP_PPC_GET_PVINFO

Documentation/virtual/kvm/cpuid.txt +4 -0

index 8820685..062dff9 100644
@@ -39,6 +39,10 @@ KVM_FEATURE_CLOCKSOURCE2           ||     3 || kvmclock available at msrs
 KVM_FEATURE_ASYNC_PF               ||     4 || async pf can be enabled by
                                    ||       || writing to msr 0x4b564d02
 ------------------------------------------------------------------------------
+KVM_FEATURE_PV_UNHALT              ||     6 || guest checks this feature bit
+                                   ||       || before enabling paravirtualized
+                                   ||       || spinlock support.
+------------------------------------------------------------------------------
 KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
                                    ||       || per-cpu warps are expected in
                                    ||       || kvmclock.

Documentation/virtual/kvm/hypercalls.txt new file +59 -0

59 lines not on this page · raw message

Documentation/virtual/kvm/msr.txt +9 -0

index 5031780..a7662d3 100644
@@ -219,3 +219,12 @@ MSR_KVM_STEAL_TIME: 0x4b564d03
 		steal: the amount of time in which this vCPU did not run, in
 		nanoseconds. Time during which the vcpu is idle, will not be
 		reported as steal time.
+
+MSR_KVM_PV_UNHALT: 0x4b564d04
+	data: 32 bit flag indicating the paravirtual unhalt state of the VCPU.
+	This data is not expected to reside in guest memory. The unhalt state
+	indicates that corresponding VCPU (halted for some reason) is ready for
+	unhalt operation.
+
+	This data is expected to be filled only via ioctl. This is needed for
+	live migration of virtual machine.

Raghavendra K T

author

2012-03-28 18:32 UTC #19 lore raw