Merge tag 'v4.0-rc1' into perf/core, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

45 files changed, 2951 insertions, 684 deletions

diff --git a/tools/hv/Makefile b/tools/hv/Makefile
index bd22f786a60c..99ffe61051a7 100644
--- a/tools/hv/Makefile
+++ b/tools/hv/Makefile
@@ -5,9 +5,9 @@ PTHREAD_LIBS = -lpthread
 WARNINGS = -Wall -Wextra
 CFLAGS = $(WARNINGS) -g $(PTHREAD_LIBS)
 
-all: hv_kvp_daemon hv_vss_daemon
+all: hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $^
 
 clean:
-	$(RM) hv_kvp_daemon hv_vss_daemon
+	$(RM) hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon
diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
index f437d739f37d..9445d8f264a4 100644
--- a/tools/hv/hv_fcopy_daemon.c
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -43,15 +43,9 @@ static int hv_start_fcopy(struct hv_start_fcopy *smsg)
 	int error = HV_E_FAIL;
 	char *q, *p;
 
-	/*
-	 * If possile append a path seperator to the path.
-	 */
-	if (strlen((char *)smsg->path_name) < (W_MAX_PATH - 2))
-		strcat((char *)smsg->path_name, "/");
-
 	p = (char *)smsg->path_name;
 	snprintf(target_fname, sizeof(target_fname), "%s/%s",
-		(char *)smsg->path_name, smsg->file_name);
+		 (char *)smsg->path_name, (char *)smsg->file_name);
 
 	syslog(LOG_INFO, "Target file name: %s", target_fname);
 	/*
@@ -137,7 +131,7 @@ void print_usage(char *argv[])
 
 int main(int argc, char *argv[])
 {
-	int fd, fcopy_fd, len;
+	int fcopy_fd, len;
 	int error;
 	int daemonize = 1, long_index = 0, opt;
 	int version = FCOPY_CURRENT_VERSION;
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 6a6432a20a1d..408bb076a234 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -147,7 +147,6 @@ static void kvp_release_lock(int pool)
 static void kvp_update_file(int pool)
 {
 	FILE *filep;
-	size_t bytes_written;
 
 	/*
 	 * We are going to write our in-memory registry out to
@@ -163,8 +162,7 @@ static void kvp_update_file(int pool)
 		exit(EXIT_FAILURE);
 	}
 
-	bytes_written = fwrite(kvp_file_info[pool].records,
-				sizeof(struct kvp_record),
+	fwrite(kvp_file_info[pool].records, sizeof(struct kvp_record),
 				kvp_file_info[pool].num_records, filep);
 
 	if (ferror(filep) || fclose(filep)) {
@@ -310,7 +308,7 @@ static int kvp_file_init(void)
 	return 0;
 }
 
-static int kvp_key_delete(int pool, const char *key, int key_size)
+static int kvp_key_delete(int pool, const __u8 *key, int key_size)
 {
 	int i;
 	int j, k;
@@ -353,8 +351,8 @@ static int kvp_key_delete(int pool, const char *key, int key_size)
 	return 1;
 }
 
-static int kvp_key_add_or_modify(int pool, const char *key, int key_size, const char *value,
-			int value_size)
+static int kvp_key_add_or_modify(int pool, const __u8 *key, int key_size,
+				 const __u8 *value, int value_size)
 {
 	int i;
 	int num_records;
@@ -407,7 +405,7 @@ static int kvp_key_add_or_modify(int pool, const char *key, int key_size, const
 	return 0;
 }
 
-static int kvp_get_value(int pool, const char *key, int key_size, char *value,
+static int kvp_get_value(int pool, const __u8 *key, int key_size, __u8 *value,
 			int value_size)
 {
 	int i;
@@ -439,8 +437,8 @@ static int kvp_get_value(int pool, const char *key, int key_size, char *value,
 	return 1;
 }
 
-static int kvp_pool_enumerate(int pool, int index, char *key, int key_size,
-				char *value, int value_size)
+static int kvp_pool_enumerate(int pool, int index, __u8 *key, int key_size,
+				__u8 *value, int value_size)
 {
 	struct kvp_record *record;
 
@@ -661,7 +659,7 @@ static char *kvp_if_name_to_mac(char *if_name)
 	char    *p, *x;
 	char    buf[256];
 	char addr_file[256];
-	int i;
+	unsigned int i;
 	char *mac_addr = NULL;
 
 	snprintf(addr_file, sizeof(addr_file), "%s%s%s", "/sys/class/net/",
@@ -700,7 +698,7 @@ static char *kvp_mac_to_if_name(char *mac)
 	char    buf[256];
 	char *kvp_net_dir = "/sys/class/net/";
 	char dev_id[256];
-	int i;
+	unsigned int i;
 
 	dir = opendir(kvp_net_dir);
 	if (dir == NULL)
@@ -750,7 +748,7 @@ static char *kvp_mac_to_if_name(char *mac)
 
 
 static void kvp_process_ipconfig_file(char *cmd,
-					char *config_buf, int len,
+					char *config_buf, unsigned int len,
 					int element_size, int offset)
 {
 	char buf[256];
@@ -768,7 +766,7 @@ static void kvp_process_ipconfig_file(char *cmd,
 	if (offset == 0)
 		memset(config_buf, 0, len);
 	while ((p = fgets(buf, sizeof(buf), file)) != NULL) {
-		if ((len - strlen(config_buf)) < (element_size + 1))
+		if (len < strlen(config_buf) + element_size + 1)
 			break;
 
 		x = strchr(p, '\n');
@@ -916,7 +914,7 @@ static int kvp_process_ip_address(void *addrp,
 
 static int
 kvp_get_ip_info(int family, char *if_name, int op,
-		 void  *out_buffer, int length)
+		 void  *out_buffer, unsigned int length)
 {
 	struct ifaddrs *ifap;
 	struct ifaddrs *curp;
@@ -1019,8 +1017,7 @@ kvp_get_ip_info(int family, char *if_name, int op,
 					weight += hweight32(&w[i]);
 
 				sprintf(cidr_mask, "/%d", weight);
-				if ((length - sn_offset) <
-					(strlen(cidr_mask) + 1))
+				if (length < sn_offset + strlen(cidr_mask) + 1)
 					goto gather_ipaddr;
 
 				if (sn_offset == 0)
@@ -1308,16 +1305,17 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
 	if (error)
 		goto setval_error;
 
+	/*
+	 * The dhcp_enabled flag is only for IPv4. In the case the host only
+	 * injects an IPv6 address, the flag is true, but we still need to
+	 * proceed to parse and pass the IPv6 information to the
+	 * disto-specific script hv_set_ifconfig.
+	 */
 	if (new_val->dhcp_enabled) {
 		error = kvp_write_file(file, "BOOTPROTO", "", "dhcp");
 		if (error)
 			goto setval_error;
 
-		/*
-		 * We are done!.
-		 */
-		goto setval_done;
-
 	} else {
 		error = kvp_write_file(file, "BOOTPROTO", "", "none");
 		if (error)
@@ -1345,7 +1343,6 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
 	if (error)
 		goto setval_error;
 
-setval_done:
 	fclose(file);
 
 	/*
diff --git a/tools/lguest/Makefile b/tools/lguest/Makefile
index 97bca4871ea3..a107b5e4da13 100644
--- a/tools/lguest/Makefile
+++ b/tools/lguest/Makefile
@@ -1,7 +1,13 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE
+CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE -Iinclude
 
 all: lguest
 
+include/linux/virtio_types.h: ../../include/uapi/linux/virtio_types.h
+	mkdir -p include/linux 2>&1 || true
+	ln -sf ../../../../include/uapi/linux/virtio_types.h $@
+
+lguest: include/linux/virtio_types.h
+
 clean:
 	rm -f lguest
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
index 32cf2ce15d69..e44052483ed9 100644
--- a/tools/lguest/lguest.c
+++ b/tools/lguest/lguest.c
@@ -41,6 +41,8 @@
 #include <signal.h>
 #include <pwd.h>
 #include <grp.h>
+#include <sys/user.h>
+#include <linux/pci_regs.h>
 
 #ifndef VIRTIO_F_ANY_LAYOUT
 #define VIRTIO_F_ANY_LAYOUT		27
@@ -61,12 +63,19 @@ typedef uint16_t u16;
 typedef uint8_t u8;
 /*:*/
 
-#include <linux/virtio_config.h>
-#include <linux/virtio_net.h>
-#include <linux/virtio_blk.h>
-#include <linux/virtio_console.h>
-#include <linux/virtio_rng.h>
+#define VIRTIO_CONFIG_NO_LEGACY
+#define VIRTIO_PCI_NO_LEGACY
+#define VIRTIO_BLK_NO_LEGACY
+#define VIRTIO_NET_NO_LEGACY
+
+/* Use in-kernel ones, which defines VIRTIO_F_VERSION_1 */
+#include "../../include/uapi/linux/virtio_config.h"
+#include "../../include/uapi/linux/virtio_net.h"
+#include "../../include/uapi/linux/virtio_blk.h"
+#include "../../include/uapi/linux/virtio_console.h"
+#include "../../include/uapi/linux/virtio_rng.h"
 #include <linux/virtio_ring.h>
+#include "../../include/uapi/linux/virtio_pci.h"
 #include <asm/bootparam.h>
 #include "../../include/linux/lguest_launcher.h"
 
@@ -91,13 +100,16 @@ static bool verbose;
 /* The pointer to the start of guest memory. */
 static void *guest_base;
 /* The maximum guest physical address allowed, and maximum possible. */
-static unsigned long guest_limit, guest_max;
+static unsigned long guest_limit, guest_max, guest_mmio;
 /* The /dev/lguest file descriptor. */
 static int lguest_fd;
 
 /* a per-cpu variable indicating whose vcpu is currently running */
 static unsigned int __thread cpu_id;
 
+/* 5 bit device number in the PCI_CONFIG_ADDR => 32 only */
+#define MAX_PCI_DEVICES 32
+
 /* This is our list of devices. */
 struct device_list {
 	/* Counter to assign interrupt numbers. */
@@ -106,30 +118,50 @@ struct device_list {
 	/* Counter to print out convenient device numbers. */
 	unsigned int device_num;
 
-	/* The descriptor page for the devices. */
-	u8 *descpage;
-
-	/* A single linked list of devices. */
-	struct device *dev;
-	/* And a pointer to the last device for easy append. */
-	struct device *lastdev;
+	/* PCI devices. */
+	struct device *pci[MAX_PCI_DEVICES];
 };
 
 /* The list of Guest devices, based on command line arguments. */
 static struct device_list devices;
 
-/* The device structure describes a single device. */
-struct device {
-	/* The linked-list pointer. */
-	struct device *next;
+struct virtio_pci_cfg_cap {
+	struct virtio_pci_cap cap;
+	u32 pci_cfg_data; /* Data for BAR access. */
+};
 
-	/* The device's descriptor, as mapped into the Guest. */
-	struct lguest_device_desc *desc;
+struct virtio_pci_mmio {
+	struct virtio_pci_common_cfg cfg;
+	u16 notify;
+	u8 isr;
+	u8 padding;
+	/* Device-specific configuration follows this. */
+};
 
-	/* We can't trust desc values once Guest has booted: we use these. */
-	unsigned int feature_len;
-	unsigned int num_vq;
+/* This is the layout (little-endian) of the PCI config space. */
+struct pci_config {
+	u16 vendor_id, device_id;
+	u16 command, status;
+	u8 revid, prog_if, subclass, class;
+	u8 cacheline_size, lat_timer, header_type, bist;
+	u32 bar[6];
+	u32 cardbus_cis_ptr;
+	u16 subsystem_vendor_id, subsystem_device_id;
+	u32 expansion_rom_addr;
+	u8 capabilities, reserved1[3];
+	u32 reserved2;
+	u8 irq_line, irq_pin, min_grant, max_latency;
+
+	/* Now, this is the linked capability list. */
+	struct virtio_pci_cap common;
+	struct virtio_pci_notify_cap notify;
+	struct virtio_pci_cap isr;
+	struct virtio_pci_cap device;
+	struct virtio_pci_cfg_cap cfg_access;
+};
 
+/* The device structure describes a single device. */
+struct device {
 	/* The name of this device, for --verbose. */
 	const char *name;
 
@@ -139,6 +171,25 @@ struct device {
 	/* Is it operational */
 	bool running;
 
+	/* Has it written FEATURES_OK but not re-checked it? */
+	bool wrote_features_ok;
+
+	/* PCI configuration */
+	union {
+		struct pci_config config;
+		u32 config_words[sizeof(struct pci_config) / sizeof(u32)];
+	};
+
+	/* Features we offer, and those accepted. */
+	u64 features, features_accepted;
+
+	/* Device-specific config hangs off the end of this. */
+	struct virtio_pci_mmio *mmio;
+
+	/* PCI MMIO resources (all in BAR0) */
+	size_t mmio_size;
+	u32 mmio_addr;
+
 	/* Device-specific data. */
 	void *priv;
 };
@@ -150,12 +201,15 @@ struct virtqueue {
 	/* Which device owns me. */
 	struct device *dev;
 
-	/* The configuration for this queue. */
-	struct lguest_vqconfig config;
+	/* Name for printing errors. */
+	const char *name;
 
 	/* The actual ring of buffers. */
 	struct vring vring;
 
+	/* The information about this virtqueue (we only use queue_size on) */
+	struct virtio_pci_common_cfg pci_config;
+
 	/* Last available index we saw. */
 	u16 last_avail_idx;
 
@@ -199,6 +253,16 @@ static struct termios orig_term;
 #define le32_to_cpu(v32) (v32)
 #define le64_to_cpu(v64) (v64)
 
+/*
+ * A real device would ignore weird/non-compliant driver behaviour.  We
+ * stop and flag it, to help debugging Linux problems.
+ */
+#define bad_driver(d, fmt, ...) \
+	errx(1, "%s: bad driver: " fmt, (d)->name, ## __VA_ARGS__)
+#define bad_driver_vq(vq, fmt, ...)			       \
+	errx(1, "%s vq %s: bad driver: " fmt, (vq)->dev->name, \
+	     vq->name, ## __VA_ARGS__)
+
 /* Is this iovec empty? */
 static bool iov_empty(const struct iovec iov[], unsigned int num_iov)
 {
@@ -211,7 +275,8 @@ static bool iov_empty(const struct iovec iov[], unsigned int num_iov)
 }
 
 /* Take len bytes from the front of this iovec. */
-static void iov_consume(struct iovec iov[], unsigned num_iov,
+static void iov_consume(struct device *d,
+			struct iovec iov[], unsigned num_iov,
 			void *dest, unsigned len)
 {
 	unsigned int i;
@@ -229,14 +294,7 @@ static void iov_consume(struct iovec iov[], unsigned num_iov,
 		len -= used;
 	}
 	if (len != 0)
-		errx(1, "iovec too short!");
-}
-
-/* The device virtqueue descriptors are followed by feature bitmasks. */
-static u8 *get_feature_bits(struct device *dev)
-{
-	return (u8 *)(dev->desc + 1)
-		+ dev->num_vq * sizeof(struct lguest_vqconfig);
+		bad_driver(d, "iovec too short!");
 }
 
 /*L:100
@@ -309,14 +367,20 @@ static void *map_zeroed_pages(unsigned int num)
 	return addr + getpagesize();
 }
 
-/* Get some more pages for a device. */
-static void *get_pages(unsigned int num)
+/* Get some bytes which won't be mapped into the guest. */
+static unsigned long get_mmio_region(size_t size)
 {
-	void *addr = from_guest_phys(guest_limit);
+	unsigned long addr = guest_mmio;
+	size_t i;
+
+	if (!size)
+		return addr;
+
+	/* Size has to be a power of 2 (and multiple of 16) */
+	for (i = 1; i < size; i <<= 1);
+
+	guest_mmio += i;
 
-	guest_limit += num * getpagesize();
-	if (guest_limit > guest_max)
-		errx(1, "Not enough memory for devices");
 	return addr;
 }
 
@@ -547,9 +611,11 @@ static void tell_kernel(unsigned long start)
 {
 	unsigned long args[] = { LHREQ_INITIALIZE,
 				 (unsigned long)guest_base,
-				 guest_limit / getpagesize(), start };
-	verbose("Guest: %p - %p (%#lx)\n",
-		guest_base, guest_base + guest_limit, guest_limit);
+				 guest_limit / getpagesize(), start,
+				 (guest_mmio+getpagesize()-1) / getpagesize() };
+	verbose("Guest: %p - %p (%#lx, MMIO %#lx)\n",
+		guest_base, guest_base + guest_limit,
+		guest_limit, guest_mmio);
 	lguest_fd = open_or_die("/dev/lguest", O_RDWR);
 	if (write(lguest_fd, args, sizeof(args)) < 0)
 		err(1, "Writing to /dev/lguest");
@@ -564,7 +630,8 @@ static void tell_kernel(unsigned long start)
  * we have a convenient routine which checks it and exits with an error message
  * if something funny is going on:
  */
-static void *_check_pointer(unsigned long addr, unsigned int size,
+static void *_check_pointer(struct device *d,
+			    unsigned long addr, unsigned int size,
 			    unsigned int line)
 {
 	/*
@@ -572,7 +639,8 @@ static void *_check_pointer(unsigned long addr, unsigned int size,
 	 * or addr + size wraps around.
 	 */
 	if ((addr + size) > guest_limit || (addr + size) < addr)
-		errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr);
+		bad_driver(d, "%s:%i: Invalid address %#lx",
+			   __FILE__, line, addr);
 	/*
 	 * We return a pointer for the caller's convenience, now we know it's
 	 * safe to use.
@@ -580,14 +648,14 @@ static void *_check_pointer(unsigned long addr, unsigned int size,
 	return from_guest_phys(addr);
 }
 /* A macro which transparently hands the line number to the real function. */
-#define check_pointer(addr,size) _check_pointer(addr, size, __LINE__)
+#define check_pointer(d,addr,size) _check_pointer(d, addr, size, __LINE__)
 
 /*
  * Each buffer in the virtqueues is actually a chain of descriptors.  This
  * function returns the next descriptor in the chain, or vq->vring.num if we're
  * at the end.
  */
-static unsigned next_desc(struct vring_desc *desc,
+static unsigned next_desc(struct device *d, struct vring_desc *desc,
 			  unsigned int i, unsigned int max)
 {
 	unsigned int next;
@@ -602,7 +670,7 @@ static unsigned next_desc(struct vring_desc *desc,
 	wmb();
 
 	if (next >= max)
-		errx(1, "Desc next is %u", next);
+		bad_driver(d, "Desc next is %u", next);
 
 	return next;
 }
@@ -613,21 +681,48 @@ static unsigned next_desc(struct vring_desc *desc,
  */
 static void trigger_irq(struct virtqueue *vq)
 {
-	unsigned long buf[] = { LHREQ_IRQ, vq->config.irq };
+	unsigned long buf[] = { LHREQ_IRQ, vq->dev->config.irq_line };
 
 	/* Don't inform them if nothing used. */
 	if (!vq->pending_used)
 		return;
 	vq->pending_used = 0;
 
-	/* If they don't want an interrupt, don't send one... */
+	/*
+	 * 2.4.7.1:
+	 *
+	 *  If the VIRTIO_F_EVENT_IDX feature bit is not negotiated:
+	 *    The driver MUST set flags to 0 or 1. 
+	 */
+	if (vq->vring.avail->flags > 1)
+		bad_driver_vq(vq, "avail->flags = %u\n", vq->vring.avail->flags);
+
+	/*
+	 * 2.4.7.2:
+	 *
+	 *  If the VIRTIO_F_EVENT_IDX feature bit is not negotiated:
+	 *
+	 *     - The device MUST ignore the used_event value.
+	 *     - After the device writes a descriptor index into the used ring:
+	 *         - If flags is 1, the device SHOULD NOT send an interrupt.
+	 *         - If flags is 0, the device MUST send an interrupt.
+	 */
 	if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) {
 		return;
 	}
 
+	/*
+	 * 4.1.4.5.1:
+	 *
+	 *  If MSI-X capability is disabled, the device MUST set the Queue
+	 *  Interrupt bit in ISR status before sending a virtqueue notification
+	 *  to the driver.
+	 */
+	vq->dev->mmio->isr = 0x1;
+
 	/* Send the Guest an interrupt tell them we used something up. */
 	if (write(lguest_fd, buf, sizeof(buf)) != 0)
-		err(1, "Triggering irq %i", vq->config.irq);
+		err(1, "Triggering irq %i", vq->dev->config.irq_line);
 }
 
 /*
@@ -646,6 +741,14 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 	struct vring_desc *desc;
 	u16 last_avail = lg_last_avail(vq);
 
+	/*
+	 * 2.4.7.1:
+	 *
+	 *   The driver MUST handle spurious interrupts from the device.
+	 *
+	 * That's why this is a while loop.
+	 */
+
 	/* There's nothing available? */
 	while (last_avail == vq->vring.avail->idx) {
 		u64 event;
@@ -679,8 +782,8 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 
 	/* Check it isn't doing very strange things with descriptor numbers. */
 	if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num)
-		errx(1, "Guest moved used index from %u to %u",
-		     last_avail, vq->vring.avail->idx);
+		bad_driver_vq(vq, "Guest moved used index from %u to %u",
+			      last_avail, vq->vring.avail->idx);
 
 	/* 
 	 * Make sure we read the descriptor number *after* we read the ring
@@ -697,7 +800,7 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 
 	/* If their number is silly, that's a fatal mistake. */
 	if (head >= vq->vring.num)
-		errx(1, "Guest says index %u is available", head);
+		bad_driver_vq(vq, "Guest says index %u is available", head);
 
 	/* When we start there are none of either input nor output. */
 	*out_num = *in_num = 0;
@@ -712,24 +815,73 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 	 * that: no rmb() required.
 	 */
 
-	/*
-	 * If this is an indirect entry, then this buffer contains a descriptor
-	 * table which we handle as if it's any normal descriptor chain.
-	 */
-	if (desc[i].flags & VRING_DESC_F_INDIRECT) {
-		if (desc[i].len % sizeof(struct vring_desc))
-			errx(1, "Invalid size for indirect buffer table");
+	do {
+		/*
+		 * If this is an indirect entry, then this buffer contains a
+		 * descriptor table which we handle as if it's any normal
+		 * descriptor chain.
+		 */
+		if (desc[i].flags & VRING_DESC_F_INDIRECT) {
+			/* 2.4.5.3.1:
+			 *
+			 *  The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT
+			 *  flag unless the VIRTIO_F_INDIRECT_DESC feature was
+			 *  negotiated.
+			 */
+			if (!(vq->dev->features_accepted &
+			      (1<<VIRTIO_RING_F_INDIRECT_DESC)))
+				bad_driver_vq(vq, "vq indirect not negotiated");
 
-		max = desc[i].len / sizeof(struct vring_desc);
-		desc = check_pointer(desc[i].addr, desc[i].len);
-		i = 0;
-	}
+			/*
+			 * 2.4.5.3.1:
+			 *
+			 *   The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT
+			 *   flag within an indirect descriptor (ie. only one
+			 *   table per descriptor).
+			 */
+			if (desc != vq->vring.desc)
+				bad_driver_vq(vq, "Indirect within indirect");
+
+			/*
+			 * Proposed update VIRTIO-134 spells this out:
+			 *
+			 *   A driver MUST NOT set both VIRTQ_DESC_F_INDIRECT
+			 *   and VIRTQ_DESC_F_NEXT in flags.
+			 */
+			if (desc[i].flags & VRING_DESC_F_NEXT)
+				bad_driver_vq(vq, "indirect and next together");
+
+			if (desc[i].len % sizeof(struct vring_desc))
+				bad_driver_vq(vq,
+					      "Invalid size for indirect table");
+			/*
+			 * 2.4.5.3.2:
+			 *
+			 *  The device MUST ignore the write-only flag
+			 *  (flags&VIRTQ_DESC_F_WRITE) in the descriptor that
+			 *  refers to an indirect table.
+			 *
+			 * We ignore it here: :)
+			 */
+
+			max = desc[i].len / sizeof(struct vring_desc);
+			desc = check_pointer(vq->dev, desc[i].addr, desc[i].len);
+			i = 0;
+
+			/* 2.4.5.3.1:
+			 *
+			 *  A driver MUST NOT create a descriptor chain longer
+			 *  than the Queue Size of the device.
+			 */
+			if (max > vq->pci_config.queue_size)
+				bad_driver_vq(vq,
+					      "indirect has too many entries");
+		}
 
-	do {
 		/* Grab the first descriptor, and check it's OK. */
 		iov[*out_num + *in_num].iov_len = desc[i].len;
 		iov[*out_num + *in_num].iov_base
-			= check_pointer(desc[i].addr, desc[i].len);
+			= check_pointer(vq->dev, desc[i].addr, desc[i].len);
 		/* If this is an input descriptor, increment that count. */
 		if (desc[i].flags & VRING_DESC_F_WRITE)
 			(*in_num)++;
@@ -739,14 +891,15 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq,
 			 * to come before any input descriptors.
 			 */
 			if (*in_num)
-				errx(1, "Descriptor has out after in");
+				bad_driver_vq(vq,
+					      "Descriptor has out after in");
 			(*out_num)++;
 		}
 
 		/* If we've got too many, that implies a descriptor loop. */
 		if (*out_num + *in_num > max)
-			errx(1, "Looped descriptor");
-	} while ((i = next_desc(desc, i, max)) != max);
+			bad_driver_vq(vq, "Looped descriptor");
+	} while ((i = next_desc(vq->dev, desc, i, max)) != max);
 
 	return head;
 }
@@ -803,7 +956,7 @@ static void console_input(struct virtqueue *vq)
 	/* Make sure there's a descriptor available. */
 	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 	if (out_num)
-		errx(1, "Output buffers in console in queue?");
+		bad_driver_vq(vq, "Output buffers in console in queue?");
 
 	/* Read into it.  This is where we usually wait. */
 	len = readv(STDIN_FILENO, iov, in_num);
@@ -856,7 +1009,7 @@ static void console_output(struct virtqueue *vq)
 	/* We usually wait in here, for the Guest to give us something. */
 	head = wait_for_vq_desc(vq, iov, &out, &in);
 	if (in)
-		errx(1, "Input buffers in console output queue?");
+		bad_driver_vq(vq, "Input buffers in console output queue?");
 
 	/* writev can return a partial write, so we loop here. */
 	while (!iov_empty(iov, out)) {
@@ -865,7 +1018,7 @@ static void console_output(struct virtqueue *vq)
 			warn("Write to stdout gave %i (%d)", len, errno);
 			break;
 		}
-		iov_consume(iov, out, NULL, len);
+		iov_consume(vq->dev, iov, out, NULL, len);
 	}
 
 	/*
@@ -894,7 +1047,7 @@ static void net_output(struct virtqueue *vq)
 	/* We usually wait in here for the Guest to give us a packet. */
 	head = wait_for_vq_desc(vq, iov, &out, &in);
 	if (in)
-		errx(1, "Input buffers in net output queue?");
+		bad_driver_vq(vq, "Input buffers in net output queue?");
 	/*
 	 * Send the whole thing through to /dev/net/tun.  It expects the exact
 	 * same format: what a coincidence!
@@ -942,7 +1095,7 @@ static void net_input(struct virtqueue *vq)
 	 */
 	head = wait_for_vq_desc(vq, iov, &out, &in);
 	if (out)
-		errx(1, "Output buffers in net input queue?");
+		bad_driver_vq(vq, "Output buffers in net input queue?");
 
 	/*
 	 * If it looks like we'll block reading from the tun device, send them
@@ -986,6 +1139,12 @@ static void kill_launcher(int signal)
 	kill(0, SIGTERM);
 }
 
+static void reset_vq_pci_config(struct virtqueue *vq)
+{
+	vq->pci_config.queue_size = VIRTQUEUE_NUM;
+	vq->pci_config.queue_enable = 0;
+}
+
 static void reset_device(struct device *dev)
 {
 	struct virtqueue *vq;
@@ -993,53 +1152,705 @@ static void reset_device(struct device *dev)
 	verbose("Resetting device %s\n", dev->name);
 
 	/* Clear any features they've acked. */
-	memset(get_feature_bits(dev) + dev->feature_len, 0, dev->feature_len);
+	dev->features_accepted = 0;
 
 	/* We're going to be explicitly killing threads, so ignore them. */
 	signal(SIGCHLD, SIG_IGN);
 
-	/* Zero out the virtqueues, get rid of their threads */
+	/*
+	 * 4.1.4.3.1:
+	 *
+	 *   The device MUST present a 0 in queue_enable on reset. 
+	 *
+	 * This means we set it here, and reset the saved ones in every vq.
+	 */
+	dev->mmio->cfg.queue_enable = 0;
+
+	/* Get rid of the virtqueue threads */
 	for (vq = dev->vq; vq; vq = vq->next) {
+		vq->last_avail_idx = 0;
+		reset_vq_pci_config(vq);
 		if (vq->thread != (pid_t)-1) {
 			kill(vq->thread, SIGTERM);
 			waitpid(vq->thread, NULL, 0);
 			vq->thread = (pid_t)-1;
 		}
-		memset(vq->vring.desc, 0,
-		       vring_size(vq->config.num, LGUEST_VRING_ALIGN));
-		lg_last_avail(vq) = 0;
 	}
 	dev->running = false;
+	dev->wrote_features_ok = false;
 
 	/* Now we care if threads die. */
 	signal(SIGCHLD, (void *)kill_launcher);
 }
 
+static void cleanup_devices(void)
+{
+	unsigned int i;
+
+	for (i = 1; i < MAX_PCI_DEVICES; i++) {
+		struct device *d = devices.pci[i];
+		if (!d)
+			continue;
+		reset_device(d);
+	}
+
+	/* If we saved off the original terminal settings, restore them now. */
+	if (orig_term.c_lflag & (ISIG|ICANON|ECHO))
+		tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
+}
+
+/*L:217
+ * We do PCI.  This is mainly done to let us test the kernel virtio PCI
+ * code.
+ */
+
+/* Linux expects a PCI host bridge: ours is a dummy, and first on the bus. */
+static struct device pci_host_bridge;
+
+static void init_pci_host_bridge(void)
+{
+	pci_host_bridge.name = "PCI Host Bridge";
+	pci_host_bridge.config.class = 0x06; /* bridge */
+	pci_host_bridge.config.subclass = 0; /* host bridge */
+	devices.pci[0] = &pci_host_bridge;
+}
+
+/* The IO ports used to read the PCI config space. */
+#define PCI_CONFIG_ADDR 0xCF8
+#define PCI_CONFIG_DATA 0xCFC
+
+/*
+ * Not really portable, but does help readability: this is what the Guest
+ * writes to the PCI_CONFIG_ADDR IO port.
+ */
+union pci_config_addr {
+	struct {
+		unsigned mbz: 2;
+		unsigned offset: 6;
+		unsigned funcnum: 3;
+		unsigned devnum: 5;
+		unsigned busnum: 8;
+		unsigned reserved: 7;
+		unsigned enabled : 1;
+	} bits;
+	u32 val;
+};
+
+/*
+ * We cache what they wrote to the address port, so we know what they're
+ * talking about when they access the data port.
+ */
+static union pci_config_addr pci_config_addr;
+
+static struct device *find_pci_device(unsigned int index)
+{
+	return devices.pci[index];
+}
+
+/* PCI can do 1, 2 and 4 byte reads; we handle that here. */
+static void ioread(u16 off, u32 v, u32 mask, u32 *val)
+{
+	assert(off < 4);
+	assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF);
+	*val = (v >> (off * 8)) & mask;
+}
+
+/* PCI can do 1, 2 and 4 byte writes; we handle that here. */
+static void iowrite(u16 off, u32 v, u32 mask, u32 *dst)
+{
+	assert(off < 4);
+	assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF);
+	*dst &= ~(mask << (off * 8));
+	*dst |= (v & mask) << (off * 8);
+}
+
+/*
+ * Where PCI_CONFIG_DATA accesses depends on the previous write to
+ * PCI_CONFIG_ADDR.
+ */
+static struct device *dev_and_reg(u32 *reg)
+{
+	if (!pci_config_addr.bits.enabled)
+		return NULL;
+
+	if (pci_config_addr.bits.funcnum != 0)
+		return NULL;
+
+	if (pci_config_addr.bits.busnum != 0)
+		return NULL;
+
+	if (pci_config_addr.bits.offset * 4 >= sizeof(struct pci_config))
+		return NULL;
+
+	*reg = pci_config_addr.bits.offset;
+	return find_pci_device(pci_config_addr.bits.devnum);
+}
+
+/*
+ * We can get invalid combinations of values while they're writing, so we
+ * only fault if they try to write with some invalid bar/offset/length.
+ */
+static bool valid_bar_access(struct device *d,
+			     struct virtio_pci_cfg_cap *cfg_access)
+{
+	/* We only have 1 bar (BAR0) */
+	if (cfg_access->cap.bar != 0)
+		return false;
+
+	/* Check it's within BAR0. */
+	if (cfg_access->cap.offset >= d->mmio_size
+	    || cfg_access->cap.offset + cfg_access->cap.length > d->mmio_size)
+		return false;
+
+	/* Check length is 1, 2 or 4. */
+	if (cfg_access->cap.length != 1
+	    && cfg_access->cap.length != 2
+	    && cfg_access->cap.length != 4)
+		return false;
+
+	/*
+	 * 4.1.4.7.2:
+	 *
+	 *  The driver MUST NOT write a cap.offset which is not a multiple of
+	 *  cap.length (ie. all accesses MUST be aligned).
+	 */
+	if (cfg_access->cap.offset % cfg_access->cap.length != 0)
+		return false;
+
+	/* Return pointer into word in BAR0. */
+	return true;
+}
+
+/* Is this accessing the PCI config address port?. */
+static bool is_pci_addr_port(u16 port)
+{
+	return port >= PCI_CONFIG_ADDR && port < PCI_CONFIG_ADDR + 4;
+}
+
+static bool pci_addr_iowrite(u16 port, u32 mask, u32 val)
+{
+	iowrite(port - PCI_CONFIG_ADDR, val, mask,
+		&pci_config_addr.val);
+	verbose("PCI%s: %#x/%x: bus %u dev %u func %u reg %u\n",
+		pci_config_addr.bits.enabled ? "" : " DISABLED",
+		val, mask,
+		pci_config_addr.bits.busnum,
+		pci_config_addr.bits.devnum,
+		pci_config_addr.bits.funcnum,
+		pci_config_addr.bits.offset);
+	return true;
+}
+
+static void pci_addr_ioread(u16 port, u32 mask, u32 *val)
+{
+	ioread(port - PCI_CONFIG_ADDR, pci_config_addr.val, mask, val);
+}
+
+/* Is this accessing the PCI config data port?. */
+static bool is_pci_data_port(u16 port)
+{
+	return port >= PCI_CONFIG_DATA && port < PCI_CONFIG_DATA + 4;
+}
+
+static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask);
+
+static bool pci_data_iowrite(u16 port, u32 mask, u32 val)
+{
+	u32 reg, portoff;
+	struct device *d = dev_and_reg(&reg);
+
+	/* Complain if they don't belong to a device. */
+	if (!d)
+		return false;
+
+	/* They can do 1 byte writes, etc. */
+	portoff = port - PCI_CONFIG_DATA;
+
+	/*
+	 * PCI uses a weird way to determine the BAR size: the OS
+	 * writes all 1's, and sees which ones stick.
+	 */
+	if (&d->config_words[reg] == &d->config.bar[0]) {
+		int i;
+
+		iowrite(portoff, val, mask, &d->config.bar[0]);
+		for (i = 0; (1 << i) < d->mmio_size; i++)
+			d->config.bar[0] &= ~(1 << i);
+		return true;
+	} else if ((&d->config_words[reg] > &d->config.bar[0]
+		    && &d->config_words[reg] <= &d->config.bar[6])
+		   || &d->config_words[reg] == &d->config.expansion_rom_addr) {
+		/* Allow writing to any other BAR, or expansion ROM */
+		iowrite(portoff, val, mask, &d->config_words[reg]);
+		return true;
+		/* We let them overide latency timer and cacheline size */
+	} else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) {
+		/* Only let them change the first two fields. */
+		if (mask == 0xFFFFFFFF)
+			mask = 0xFFFF;
+		iowrite(portoff, val, mask, &d->config_words[reg]);
+		return true;
+	} else if (&d->config_words[reg] == (void *)&d->config.command
+		   && mask == 0xFFFF) {
+		/* Ignore command writes. */
+		return true;
+	} else if (&d->config_words[reg]
+		   == (void *)&d->config.cfg_access.cap.bar
+		   || &d->config_words[reg]
+		   == &d->config.cfg_access.cap.length
+		   || &d->config_words[reg]
+		   == &d->config.cfg_access.cap.offset) {
+
+		/*
+		 * The VIRTIO_PCI_CAP_PCI_CFG capability
+		 * provides a backdoor to access the MMIO
+		 * regions without mapping them.  Weird, but
+		 * useful.
+		 */
+		iowrite(portoff, val, mask, &d->config_words[reg]);
+		return true;
+	} else if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) {
+		u32 write_mask;
+
+		/*
+		 * 4.1.4.7.1:
+		 *
+		 *  Upon detecting driver write access to pci_cfg_data, the
+		 *  device MUST execute a write access at offset cap.offset at
+		 *  BAR selected by cap.bar using the first cap.length bytes
+		 *  from pci_cfg_data.
+		 */
+
+		/* Must be bar 0 */
+		if (!valid_bar_access(d, &d->config.cfg_access))
+			return false;
+
+		iowrite(portoff, val, mask, &d->config.cfg_access.pci_cfg_data);
+
+		/*
+		 * Now emulate a write.  The mask we use is set by
+		 * len, *not* this write!
+		 */
+		write_mask = (1ULL<<(8*d->config.cfg_access.cap.length)) - 1;
+		verbose("Window writing %#x/%#x to bar %u, offset %u len %u\n",
+			d->config.cfg_access.pci_cfg_data, write_mask,
+			d->config.cfg_access.cap.bar,
+			d->config.cfg_access.cap.offset,
+			d->config.cfg_access.cap.length);
+
+		emulate_mmio_write(d, d->config.cfg_access.cap.offset,
+				   d->config.cfg_access.pci_cfg_data,
+				   write_mask);
+		return true;
+	}
+
+	/*
+	 * 4.1.4.1:
+	 *
+	 *  The driver MUST NOT write into any field of the capability
+	 *  structure, with the exception of those with cap_type
+	 *  VIRTIO_PCI_CAP_PCI_CFG...
+	 */
+	return false;
+}
+
+static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask);
+
+static void pci_data_ioread(u16 port, u32 mask, u32 *val)
+{
+	u32 reg;
+	struct device *d = dev_and_reg(&reg);
+
+	if (!d)
+		return;
+
+	/* Read through the PCI MMIO access window is special */
+	if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) {
+		u32 read_mask;
+
+		/*
+		 * 4.1.4.7.1:
+		 *
+		 *  Upon detecting driver read access to pci_cfg_data, the
+		 *  device MUST execute a read access of length cap.length at
+		 *  offset cap.offset at BAR selected by cap.bar and store the
+		 *  first cap.length bytes in pci_cfg_data.
+		 */
+		/* Must be bar 0 */
+		if (!valid_bar_access(d, &d->config.cfg_access))
+			bad_driver(d,
+			     "Invalid cfg_access to bar%u, offset %u len %u",
+			     d->config.cfg_access.cap.bar,
+			     d->config.cfg_access.cap.offset,
+			     d->config.cfg_access.cap.length);
+
+		/*
+		 * Read into the window.  The mask we use is set by
+		 * len, *not* this read!
+		 */
+		read_mask = (1ULL<<(8*d->config.cfg_access.cap.length))-1;
+		d->config.cfg_access.pci_cfg_data
+			= emulate_mmio_read(d,
+					    d->config.cfg_access.cap.offset,
+					    read_mask);
+		verbose("Window read %#x/%#x from bar %u, offset %u len %u\n",
+			d->config.cfg_access.pci_cfg_data, read_mask,
+			d->config.cfg_access.cap.bar,
+			d->config.cfg_access.cap.offset,
+			d->config.cfg_access.cap.length);
+	}
+	ioread(port - PCI_CONFIG_DATA, d->config_words[reg], mask, val);
+}
+
 /*L:216
- * This actually creates the thread which services the virtqueue for a device.
+ * This is where we emulate a handful of Guest instructions.  It's ugly
+ * and we used to do it in the kernel but it grew over time.
+ */
+
+/*
+ * We use the ptrace syscall's pt_regs struct to talk about registers
+ * to lguest: these macros convert the names to the offsets.
+ */
+#define getreg(name) getreg_off(offsetof(struct user_regs_struct, name))
+#define setreg(name, val) \
+	setreg_off(offsetof(struct user_regs_struct, name), (val))
+
+static u32 getreg_off(size_t offset)
+{
+	u32 r;
+	unsigned long args[] = { LHREQ_GETREG, offset };
+
+	if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
+		err(1, "Getting register %u", offset);
+	if (pread(lguest_fd, &r, sizeof(r), cpu_id) != sizeof(r))
+		err(1, "Reading register %u", offset);
+
+	return r;
+}
+
+static void setreg_off(size_t offset, u32 val)
+{
+	unsigned long args[] = { LHREQ_SETREG, offset, val };
+
+	if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0)
+		err(1, "Setting register %u", offset);
+}
+
+/* Get register by instruction encoding */
+static u32 getreg_num(unsigned regnum, u32 mask)
+{
+	/* 8 bit ops use regnums 4-7 for high parts of word */
+	if (mask == 0xFF && (regnum & 0x4))
+		return getreg_num(regnum & 0x3, 0xFFFF) >> 8;
+
+	switch (regnum) {
+	case 0: return getreg(eax) & mask;
+	case 1: return getreg(ecx) & mask;
+	case 2: return getreg(edx) & mask;
+	case 3: return getreg(ebx) & mask;
+	case 4: return getreg(esp) & mask;
+	case 5: return getreg(ebp) & mask;
+	case 6: return getreg(esi) & mask;
+	case 7: return getreg(edi) & mask;
+	}
+	abort();
+}
+
+/* Set register by instruction encoding */
+static void setreg_num(unsigned regnum, u32 val, u32 mask)
+{
+	/* Don't try to set bits out of range */
+	assert(~(val & ~mask));
+
+	/* 8 bit ops use regnums 4-7 for high parts of word */
+	if (mask == 0xFF && (regnum & 0x4)) {
+		/* Construct the 16 bits we want. */
+		val = (val << 8) | getreg_num(regnum & 0x3, 0xFF);
+		setreg_num(regnum & 0x3, val, 0xFFFF);
+		return;
+	}
+
+	switch (regnum) {
+	case 0: setreg(eax, val | (getreg(eax) & ~mask)); return;
+	case 1: setreg(ecx, val | (getreg(ecx) & ~mask)); return;
+	case 2: setreg(edx, val | (getreg(edx) & ~mask)); return;
+	case 3: setreg(ebx, val | (getreg(ebx) & ~mask)); return;
+	case 4: setreg(esp, val | (getreg(esp) & ~mask)); return;
+	case 5: setreg(ebp, val | (getreg(ebp) & ~mask)); return;
+	case 6: setreg(esi, val | (getreg(esi) & ~mask)); return;
+	case 7: setreg(edi, val | (getreg(edi) & ~mask)); return;
+	}
+	abort();
+}
+
+/* Get bytes of displacement appended to instruction, from r/m encoding */
+static u32 insn_displacement_len(u8 mod_reg_rm)
+{
+	/* Switch on the mod bits */
+	switch (mod_reg_rm >> 6) {
+	case 0:
+		/* If mod == 0, and r/m == 101, 16-bit displacement follows */
+		if ((mod_reg_rm & 0x7) == 0x5)
+			return 2;
+		/* Normally, mod == 0 means no literal displacement */
+		return 0;
+	case 1:
+		/* One byte displacement */
+		return 1;
+	case 2:
+		/* Four byte displacement */
+		return 4;
+	case 3:
+		/* Register mode */
+		return 0;
+	}
+	abort();
+}
+
+static void emulate_insn(const u8 insn[])
+{
+	unsigned long args[] = { LHREQ_TRAP, 13 };
+	unsigned int insnlen = 0, in = 0, small_operand = 0, byte_access;
+	unsigned int eax, port, mask;
+	/*
+	 * Default is to return all-ones on IO port reads, which traditionally
+	 * means "there's nothing there".
+	 */
+	u32 val = 0xFFFFFFFF;
+
+	/*
+	 * This must be the Guest kernel trying to do something, not userspace!
+	 * The bottom two bits of the CS segment register are the privilege
+	 * level.
+	 */
+	if ((getreg(xcs) & 3) != 0x1)
+		goto no_emulate;
+
+	/* Decoding x86 instructions is icky. */
+
+	/*
+	 * Around 2.6.33, the kernel started using an emulation for the
+	 * cmpxchg8b instruction in early boot on many configurations.  This
+	 * code isn't paravirtualized, and it tries to disable interrupts.
+	 * Ignore it, which will Mostly Work.
+	 */
+	if (insn[insnlen] == 0xfa) {
+		/* "cli", or Clear Interrupt Enable instruction.  Skip it. */
+		insnlen = 1;
+		goto skip_insn;
+	}
+
+	/*
+	 * 0x66 is an "operand prefix".  It means a 16, not 32 bit in/out.
+	 */
+	if (insn[insnlen] == 0x66) {
+		small_operand = 1;
+		/* The instruction is 1 byte so far, read the next byte. */
+		insnlen = 1;
+	}
+
+	/* If the lower bit isn't set, it's a single byte access */
+	byte_access = !(insn[insnlen] & 1);
+
+	/*
+	 * Now we can ignore the lower bit and decode the 4 opcodes
+	 * we need to emulate.
+	 */
+	switch (insn[insnlen] & 0xFE) {
+	case 0xE4: /* in     <next byte>,%al */
+		port = insn[insnlen+1];
+		insnlen += 2;
+		in = 1;
+		break;
+	case 0xEC: /* in     (%dx),%al */
+		port = getreg(edx) & 0xFFFF;
+		insnlen += 1;
+		in = 1;
+		break;
+	case 0xE6: /* out    %al,<next byte> */
+		port = insn[insnlen+1];
+		insnlen += 2;
+		break;
+	case 0xEE: /* out    %al,(%dx) */
+		port = getreg(edx) & 0xFFFF;
+		insnlen += 1;
+		break;
+	default:
+		/* OK, we don't know what this is, can't emulate. */
+		goto no_emulate;
+	}
+
+	/* Set a mask of the 1, 2 or 4 bytes, depending on size of IO */
+	if (byte_access)
+		mask = 0xFF;
+	else if (small_operand)
+		mask = 0xFFFF;
+	else
+		mask = 0xFFFFFFFF;
+
+	/*
+	 * If it was an "IN" instruction, they expect the result to be read
+	 * into %eax, so we change %eax.
+	 */
+	eax = getreg(eax);
+
+	if (in) {
+		/* This is the PS/2 keyboard status; 1 means ready for output */
+		if (port == 0x64)
+			val = 1;
+		else if (is_pci_addr_port(port))
+			pci_addr_ioread(port, mask, &val);
+		else if (is_pci_data_port(port))
+			pci_data_ioread(port, mask, &val);
+
+		/* Clear the bits we're about to read */
+		eax &= ~mask;
+		/* Copy bits in from val. */
+		eax |= val & mask;
+		/* Now update the register. */
+		setreg(eax, eax);
+	} else {
+		if (is_pci_addr_port(port)) {
+			if (!pci_addr_iowrite(port, mask, eax))
+				goto bad_io;
+		} else if (is_pci_data_port(port)) {
+			if (!pci_data_iowrite(port, mask, eax))
+				goto bad_io;
+		}
+		/* There are many other ports, eg. CMOS clock, serial
+		 * and parallel ports, so we ignore them all. */
+	}
+
+	verbose("IO %s of %x to %u: %#08x\n",
+		in ? "IN" : "OUT", mask, port, eax);
+skip_insn:
+	/* Finally, we've "done" the instruction, so move past it. */
+	setreg(eip, getreg(eip) + insnlen);
+	return;
+
+bad_io:
+	warnx("Attempt to %s port %u (%#x mask)",
+	      in ? "read from" : "write to", port, mask);
+
+no_emulate:
+	/* Inject trap into Guest. */
+	if (write(lguest_fd, args, sizeof(args)) < 0)
+		err(1, "Reinjecting trap 13 for fault at %#x", getreg(eip));
+}
+
+static struct device *find_mmio_region(unsigned long paddr, u32 *off)
+{
+	unsigned int i;
+
+	for (i = 1; i < MAX_PCI_DEVICES; i++) {
+		struct device *d = devices.pci[i];
+
+		if (!d)
+			continue;
+		if (paddr < d->mmio_addr)
+			continue;
+		if (paddr >= d->mmio_addr + d->mmio_size)
+			continue;
+		*off = paddr - d->mmio_addr;
+		return d;
+	}
+	return NULL;
+}
+
+/* FIXME: Use vq array. */
+static struct virtqueue *vq_by_num(struct device *d, u32 num)
+{
+	struct virtqueue *vq = d->vq;
+
+	while (num-- && vq)
+		vq = vq->next;
+
+	return vq;
+}
+
+static void save_vq_config(const struct virtio_pci_common_cfg *cfg,
+			   struct virtqueue *vq)
+{
+	vq->pci_config = *cfg;
+}
+
+static void restore_vq_config(struct virtio_pci_common_cfg *cfg,
+			      struct virtqueue *vq)
+{
+	/* Only restore the per-vq part */
+	size_t off = offsetof(struct virtio_pci_common_cfg, queue_size);
+
+	memcpy((void *)cfg + off, (void *)&vq->pci_config + off,
+	       sizeof(*cfg) - off);
+}
+
+/*
+ * 4.1.4.3.2:
+ *
+ *  The driver MUST configure the other virtqueue fields before
+ *  enabling the virtqueue with queue_enable.
+ *
+ * When they enable the virtqueue, we check that their setup is valid.
  */
-static void create_thread(struct virtqueue *vq)
+static void check_virtqueue(struct device *d, struct virtqueue *vq)
+{
+	/* Because lguest is 32 bit, all the descriptor high bits must be 0 */
+	if (vq->pci_config.queue_desc_hi
+	    || vq->pci_config.queue_avail_hi
+	    || vq->pci_config.queue_used_hi)
+		bad_driver_vq(vq, "invalid 64-bit queue address");
+
+	/*
+	 * 2.4.1:
+	 *
+	 *  The driver MUST ensure that the physical address of the first byte
+	 *  of each virtqueue part is a multiple of the specified alignment
+	 *  value in the above table.
+	 */
+	if (vq->pci_config.queue_desc_lo % 16
+	    || vq->pci_config.queue_avail_lo % 2
+	    || vq->pci_config.queue_used_lo % 4)
+		bad_driver_vq(vq, "invalid alignment in queue addresses");
+
+	/* Initialize the virtqueue and check they're all in range. */
+	vq->vring.num = vq->pci_config.queue_size;
+	vq->vring.desc = check_pointer(vq->dev,
+				       vq->pci_config.queue_desc_lo,
+				       sizeof(*vq->vring.desc) * vq->vring.num);
+	vq->vring.avail = check_pointer(vq->dev,
+					vq->pci_config.queue_avail_lo,
+					sizeof(*vq->vring.avail)
+					+ (sizeof(vq->vring.avail->ring[0])
+					   * vq->vring.num));
+	vq->vring.used = check_pointer(vq->dev,
+				       vq->pci_config.queue_used_lo,
+				       sizeof(*vq->vring.used)
+				       + (sizeof(vq->vring.used->ring[0])
+					  * vq->vring.num));
+
+	/*
+	 * 2.4.9.1:
+	 *
+	 *   The driver MUST initialize flags in the used ring to 0
+	 *   when allocating the used ring.
+	 */
+	if (vq->vring.used->flags != 0)
+		bad_driver_vq(vq, "invalid initial used.flags %#x",
+			      vq->vring.used->flags);
+}
+
+static void start_virtqueue(struct virtqueue *vq)
 {
 	/*
 	 * Create stack for thread.  Since the stack grows upwards, we point
 	 * the stack pointer to the end of this region.
 	 */
 	char *stack = malloc(32768);
-	unsigned long args[] = { LHREQ_EVENTFD,
-				 vq->config.pfn*getpagesize(), 0 };
 
 	/* Create a zero-initialized eventfd. */
 	vq->eventfd = eventfd(0, 0);
 	if (vq->eventfd < 0)
 		err(1, "Creating eventfd");
-	args[2] = vq->eventfd;
-
-	/*
-	 * Attach an eventfd to this virtqueue: it will go off when the Guest
-	 * does an LHCALL_NOTIFY for this vq.
-	 */
-	if (write(lguest_fd, &args, sizeof(args)) != 0)
-		err(1, "Attaching eventfd");
 
 	/*
 	 * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so
@@ -1048,167 +1859,531 @@ static void create_thread(struct virtqueue *vq)
 	vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq);
 	if (vq->thread == (pid_t)-1)
 		err(1, "Creating clone");
-
-	/* We close our local copy now the child has it. */
-	close(vq->eventfd);
 }
 
-static void start_device(struct device *dev)
+static void start_virtqueues(struct device *d)
 {
-	unsigned int i;
 	struct virtqueue *vq;
 
-	verbose("Device %s OK: offered", dev->name);
-	for (i = 0; i < dev->feature_len; i++)
-		verbose(" %02x", get_feature_bits(dev)[i]);
-	verbose(", accepted");
-	for (i = 0; i < dev->feature_len; i++)
-		verbose(" %02x", get_feature_bits(dev)
-			[dev->feature_len+i]);
-
-	for (vq = dev->vq; vq; vq = vq->next) {
-		if (vq->service)
-			create_thread(vq);
+	for (vq = d->vq; vq; vq = vq->next) {
+		if (vq->pci_config.queue_enable)
+			start_virtqueue(vq);
 	}
-	dev->running = true;
 }
 
-static void cleanup_devices(void)
+static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask)
 {
-	struct device *dev;
+	struct virtqueue *vq;
 
-	for (dev = devices.dev; dev; dev = dev->next)
-		reset_device(dev);
+	switch (off) {
+	case offsetof(struct virtio_pci_mmio, cfg.device_feature_select):
+		/*
+		 * 4.1.4.3.1:
+		 *
+		 * The device MUST present the feature bits it is offering in
+		 * device_feature, starting at bit device_feature_select ∗ 32
+		 * for any device_feature_select written by the driver
+		 */
+		if (val == 0)
+			d->mmio->cfg.device_feature = d->features;
+		else if (val == 1)
+			d->mmio->cfg.device_feature = (d->features >> 32);
+		else
+			d->mmio->cfg.device_feature = 0;
+		goto feature_write_through32;
+	case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select):
+		if (val > 1)
+			bad_driver(d, "Unexpected driver select %u", val);
+		goto feature_write_through32;
+	case offsetof(struct virtio_pci_mmio, cfg.guest_feature):
+		if (d->mmio->cfg.guest_feature_select == 0) {
+			d->features_accepted &= ~((u64)0xFFFFFFFF);
+			d->features_accepted |= val;
+		} else {
+			assert(d->mmio->cfg.guest_feature_select == 1);
+			d->features_accepted &= 0xFFFFFFFF;
+			d->features_accepted |= ((u64)val) << 32;
+		}
+		/*
+		 * 2.2.1:
+		 *
+		 *   The driver MUST NOT accept a feature which the device did
+		 *   not offer
+		 */
+		if (d->features_accepted & ~d->features)
+			bad_driver(d, "over-accepted features %#llx of %#llx",
+				   d->features_accepted, d->features);
+		goto feature_write_through32;
+	case offsetof(struct virtio_pci_mmio, cfg.device_status): {
+		u8 prev;
+
+		verbose("%s: device status -> %#x\n", d->name, val);
+		/*
+		 * 4.1.4.3.1:
+		 * 
+		 *  The device MUST reset when 0 is written to device_status,
+		 *  and present a 0 in device_status once that is done.
+		 */
+		if (val == 0) {
+			reset_device(d);
+			goto write_through8;
+		}
 
-	/* If we saved off the original terminal settings, restore them now. */
-	if (orig_term.c_lflag & (ISIG|ICANON|ECHO))
-		tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
-}
+		/* 2.1.1: The driver MUST NOT clear a device status bit. */
+		if (d->mmio->cfg.device_status & ~val)
+			bad_driver(d, "unset of device status bit %#x -> %#x",
+				   d->mmio->cfg.device_status, val);
 
-/* When the Guest tells us they updated the status field, we handle it. */
-static void update_device_status(struct device *dev)
-{
-	/* A zero status is a reset, otherwise it's a set of flags. */
-	if (dev->desc->status == 0)
-		reset_device(dev);
-	else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
-		warnx("Device %s configuration FAILED", dev->name);
-		if (dev->running)
-			reset_device(dev);
-	} else {
-		if (dev->running)
-			err(1, "Device %s features finalized twice", dev->name);
-		start_device(dev);
+		/*
+		 * 2.1.2:
+		 *
+		 *  The device MUST NOT consume buffers or notify the driver
+		 *  before DRIVER_OK.
+		 */
+		if (val & VIRTIO_CONFIG_S_DRIVER_OK
+		    && !(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK))
+			start_virtqueues(d);
+
+		/*
+		 * 3.1.1:
+		 *
+		 *   The driver MUST follow this sequence to initialize a device:
+		 *   - Reset the device.
+		 *   - Set the ACKNOWLEDGE status bit: the guest OS has
+                 *     notice the device.
+		 *   - Set the DRIVER status bit: the guest OS knows how
+                 *     to drive the device.
+		 *   - Read device feature bits, and write the subset
+		 *     of feature bits understood by the OS and driver
+		 *     to the device. During this step the driver MAY
+		 *     read (but MUST NOT write) the device-specific
+		 *     configuration fields to check that it can
+		 *     support the device before accepting it.
+		 *   - Set the FEATURES_OK status bit.  The driver
+		 *     MUST not accept new feature bits after this
+		 *     step.
+		 *   - Re-read device status to ensure the FEATURES_OK
+		 *     bit is still set: otherwise, the device does
+		 *     not support our subset of features and the
+		 *     device is unusable.
+		 *   - Perform device-specific setup, including
+		 *     discovery of virtqueues for the device,
+		 *     optional per-bus setup, reading and possibly
+		 *     writing the device’s virtio configuration
+		 *     space, and population of virtqueues.
+		 *   - Set the DRIVER_OK status bit. At this point the
+                 *     device is “live”.
+		 */
+		prev = 0;
+		switch (val & ~d->mmio->cfg.device_status) {
+		case VIRTIO_CONFIG_S_DRIVER_OK:
+			prev |= VIRTIO_CONFIG_S_FEATURES_OK; /* fall thru */
+		case VIRTIO_CONFIG_S_FEATURES_OK:
+			prev |= VIRTIO_CONFIG_S_DRIVER; /* fall thru */
+		case VIRTIO_CONFIG_S_DRIVER:
+			prev |= VIRTIO_CONFIG_S_ACKNOWLEDGE; /* fall thru */
+		case VIRTIO_CONFIG_S_ACKNOWLEDGE:
+			break;
+		default:
+			bad_driver(d, "unknown device status bit %#x -> %#x",
+				   d->mmio->cfg.device_status, val);
+		}
+		if (d->mmio->cfg.device_status != prev)
+			bad_driver(d, "unexpected status transition %#x -> %#x",
+				   d->mmio->cfg.device_status, val);
+
+		/* If they just wrote FEATURES_OK, we make sure they read */
+		switch (val & ~d->mmio->cfg.device_status) {
+		case VIRTIO_CONFIG_S_FEATURES_OK:
+			d->wrote_features_ok = true;
+			break;
+		case VIRTIO_CONFIG_S_DRIVER_OK:
+			if (d->wrote_features_ok)
+				bad_driver(d, "did not re-read FEATURES_OK");
+			break;
+		}
+		goto write_through8;
 	}
-}
+	case offsetof(struct virtio_pci_mmio, cfg.queue_select):
+		vq = vq_by_num(d, val);
+		/*
+		 * 4.1.4.3.1:
+		 *
+		 *  The device MUST present a 0 in queue_size if the virtqueue
+		 *  corresponding to the current queue_select is unavailable.
+		 */
+		if (!vq) {
+			d->mmio->cfg.queue_size = 0;
+			goto write_through16;
+		}
+		/* Save registers for old vq, if it was a valid vq */
+		if (d->mmio->cfg.queue_size)
+			save_vq_config(&d->mmio->cfg,
+				       vq_by_num(d, d->mmio->cfg.queue_select));
+		/* Restore the registers for the queue they asked for */
+		restore_vq_config(&d->mmio->cfg, vq);
+		goto write_through16;
+	case offsetof(struct virtio_pci_mmio, cfg.queue_size):
+		/*
+		 * 4.1.4.3.2:
+		 *
+		 *  The driver MUST NOT write a value which is not a power of 2
+		 *  to queue_size.
+		 */
+		if (val & (val-1))
+			bad_driver(d, "invalid queue size %u", val);
+		if (d->mmio->cfg.queue_enable)
+			bad_driver(d, "changing queue size on live device");
+		goto write_through16;
+	case offsetof(struct virtio_pci_mmio, cfg.queue_msix_vector):
+		bad_driver(d, "attempt to set MSIX vector to %u", val);
+	case offsetof(struct virtio_pci_mmio, cfg.queue_enable): {
+		struct virtqueue *vq = vq_by_num(d, d->mmio->cfg.queue_select);
 
-/*L:215
- * This is the generic routine we call when the Guest uses LHCALL_NOTIFY.  In
- * particular, it's used to notify us of device status changes during boot.
- */
-static void handle_output(unsigned long addr)
-{
-	struct device *i;
+		/*
+		 * 4.1.4.3.2:
+		 *
+		 *  The driver MUST NOT write a 0 to queue_enable.
+		 */
+		if (val != 1)
+			bad_driver(d, "setting queue_enable to %u", val);
 
-	/* Check each device. */
-	for (i = devices.dev; i; i = i->next) {
-		struct virtqueue *vq;
+		/*
+		 * 3.1.1:
+		 *
+		 *  7. Perform device-specific setup, including discovery of
+		 *     virtqueues for the device, optional per-bus setup,
+		 *     reading and possibly writing the device’s virtio
+		 *     configuration space, and population of virtqueues.
+		 *  8. Set the DRIVER_OK status bit.
+		 *
+		 * All our devices require all virtqueues to be enabled, so
+		 * they should have done that before setting DRIVER_OK.
+		 */
+		if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK)
+			bad_driver(d, "enabling vq after DRIVER_OK");
 
+		d->mmio->cfg.queue_enable = val;
+		save_vq_config(&d->mmio->cfg, vq);
+		check_virtqueue(d, vq);
+		goto write_through16;
+	}
+	case offsetof(struct virtio_pci_mmio, cfg.queue_notify_off):
+		bad_driver(d, "attempt to write to queue_notify_off");
+	case offsetof(struct virtio_pci_mmio, cfg.queue_desc_lo):
+	case offsetof(struct virtio_pci_mmio, cfg.queue_desc_hi):
+	case offsetof(struct virtio_pci_mmio, cfg.queue_avail_lo):
+	case offsetof(struct virtio_pci_mmio, cfg.queue_avail_hi):
+	case offsetof(struct virtio_pci_mmio, cfg.queue_used_lo):
+	case offsetof(struct virtio_pci_mmio, cfg.queue_used_hi):
 		/*
-		 * Notifications to device descriptors mean they updated the
-		 * device status.
+		 * 4.1.4.3.2:
+		 *
+		 *  The driver MUST configure the other virtqueue fields before
+		 *  enabling the virtqueue with queue_enable.
 		 */
-		if (from_guest_phys(addr) == i->desc) {
-			update_device_status(i);
-			return;
-		}
+		if (d->mmio->cfg.queue_enable)
+			bad_driver(d, "changing queue on live device");
+
+		/*
+		 * 3.1.1:
+		 *
+		 *  The driver MUST follow this sequence to initialize a device:
+		 *...
+		 *  5. Set the FEATURES_OK status bit. The driver MUST not
+		 *  accept new feature bits after this step.
+		 */
+		if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK))
+			bad_driver(d, "setting up vq before FEATURES_OK");
 
-		/* Devices should not be used before features are finalized. */
-		for (vq = i->vq; vq; vq = vq->next) {
-			if (addr != vq->config.pfn*getpagesize())
-				continue;
-			errx(1, "Notification on %s before setup!", i->name);
+		/*
+		 *  6. Re-read device status to ensure the FEATURES_OK bit is
+		 *     still set...
+		 */
+		if (d->wrote_features_ok)
+			bad_driver(d, "didn't re-read FEATURES_OK before setup");
+
+		goto write_through32;
+	case offsetof(struct virtio_pci_mmio, notify):
+		vq = vq_by_num(d, val);
+		if (!vq)
+			bad_driver(d, "Invalid vq notification on %u", val);
+		/* Notify the process handling this vq by adding 1 to eventfd */
+		write(vq->eventfd, "\1\0\0\0\0\0\0\0", 8);
+		goto write_through16;
+	case offsetof(struct virtio_pci_mmio, isr):
+		bad_driver(d, "Unexpected write to isr");
+	/* Weird corner case: write to emerg_wr of console */
+	case sizeof(struct virtio_pci_mmio)
+		+ offsetof(struct virtio_console_config, emerg_wr):
+		if (strcmp(d->name, "console") == 0) {
+			char c = val;
+			write(STDOUT_FILENO, &c, 1);
+			goto write_through32;
 		}
+		/* Fall through... */
+	default:
+		/*
+		 * 4.1.4.3.2:
+		 *
+		 *   The driver MUST NOT write to device_feature, num_queues,
+		 *   config_generation or queue_notify_off.
+		 */
+		bad_driver(d, "Unexpected write to offset %u", off);
 	}
 
+feature_write_through32:
 	/*
-	 * Early console write is done using notify on a nul-terminated string
-	 * in Guest memory.  It's also great for hacking debugging messages
-	 * into a Guest.
+	 * 3.1.1:
+	 *
+	 *   The driver MUST follow this sequence to initialize a device:
+	 *...
+	 *   - Set the DRIVER status bit: the guest OS knows how
+	 *     to drive the device.
+	 *   - Read device feature bits, and write the subset
+	 *     of feature bits understood by the OS and driver
+	 *     to the device.
+	 *...
+	 *   - Set the FEATURES_OK status bit. The driver MUST not
+	 *     accept new feature bits after this step.
 	 */
-	if (addr >= guest_limit)
-		errx(1, "Bad NOTIFY %#lx", addr);
+	if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER))
+		bad_driver(d, "feature write before VIRTIO_CONFIG_S_DRIVER");
+	if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK)
+		bad_driver(d, "feature write after VIRTIO_CONFIG_S_FEATURES_OK");
 
-	write(STDOUT_FILENO, from_guest_phys(addr),
-	      strnlen(from_guest_phys(addr), guest_limit - addr));
+	/*
+	 * 4.1.3.1:
+	 *
+	 *  The driver MUST access each field using the “natural” access
+	 *  method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for
+	 *  16-bit fields and 8-bit accesses for 8-bit fields.
+	 */
+write_through32:
+	if (mask != 0xFFFFFFFF) {
+		bad_driver(d, "non-32-bit write to offset %u (%#x)",
+			   off, getreg(eip));
+		return;
+	}
+	memcpy((char *)d->mmio + off, &val, 4);
+	return;
+
+write_through16:
+	if (mask != 0xFFFF)
+		bad_driver(d, "non-16-bit write to offset %u (%#x)",
+			   off, getreg(eip));
+	memcpy((char *)d->mmio + off, &val, 2);
+	return;
+
+write_through8:
+	if (mask != 0xFF)
+		bad_driver(d, "non-8-bit write to offset %u (%#x)",
+			   off, getreg(eip));
+	memcpy((char *)d->mmio + off, &val, 1);
+	return;
 }
 
-/*L:190
- * Device Setup
- *
- * All devices need a descriptor so the Guest knows it exists, and a "struct
- * device" so the Launcher can keep track of it.  We have common helper
- * routines to allocate and manage them.
- */
-
-/*
- * The layout of the device page is a "struct lguest_device_desc" followed by a
- * number of virtqueue descriptors, then two sets of feature bits, then an
- * array of configuration bytes.  This routine returns the configuration
- * pointer.
- */
-static u8 *device_config(const struct device *dev)
+static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask)
 {
-	return (void *)(dev->desc + 1)
-		+ dev->num_vq * sizeof(struct lguest_vqconfig)
-		+ dev->feature_len * 2;
+	u8 isr;
+	u32 val = 0;
+
+	switch (off) {
+	case offsetof(struct virtio_pci_mmio, cfg.device_feature_select):
+	case offsetof(struct virtio_pci_mmio, cfg.device_feature):
+	case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select):
+	case offsetof(struct virtio_pci_mmio, cfg.guest_feature):
+		/*
+		 * 3.1.1:
+		 *
+		 *   The driver MUST follow this sequence to initialize a device:
+		 *...
+		 *   - Set the DRIVER status bit: the guest OS knows how
+		 *     to drive the device.
+		 *   - Read device feature bits, and write the subset
+		 *     of feature bits understood by the OS and driver
+		 *     to the device.
+		 */
+		if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER))
+			bad_driver(d,
+				   "feature read before VIRTIO_CONFIG_S_DRIVER");
+		goto read_through32;
+	case offsetof(struct virtio_pci_mmio, cfg.msix_config):
+		bad_driver(d, "read of msix_config");
+	case offsetof(struct virtio_pci_mmio, cfg.num_queues):
+		goto read_through16;
+	case offsetof(struct virtio_pci_mmio, cfg.device_status):
+		/* As they did read, any write of FEATURES_OK is now fine. */
+		d->wrote_features_ok = false;
+		goto read_through8;
+	case offsetof(struct virtio_pci_mmio, cfg.config_generation):
+		/*
+		 * 4.1.4.3.1:
+		 *
+		 *  The device MUST present a changed config_generation after
+		 *  the driver has read a device-specific configuration value
+		 *  which has changed since any part of the device-specific
+		 *  configuration was last read.
+		 *
+		 * This is simple: none of our devices change config, so this
+		 * is always 0.
+		 */
+		goto read_through8;
+	case offsetof(struct virtio_pci_mmio, notify):
+		/*
+		 * 3.1.1:
+		 *
+		 *   The driver MUST NOT notify the device before setting
+		 *   DRIVER_OK.
+		 */
+		if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK))
+			bad_driver(d, "notify before VIRTIO_CONFIG_S_DRIVER_OK");
+		goto read_through16;
+	case offsetof(struct virtio_pci_mmio, isr):
+		if (mask != 0xFF)
+			bad_driver(d, "non-8-bit read from offset %u (%#x)",
+				   off, getreg(eip));
+		isr = d->mmio->isr;
+		/*
+		 * 4.1.4.5.1:
+		 *
+		 *  The device MUST reset ISR status to 0 on driver read. 
+		 */
+		d->mmio->isr = 0;
+		return isr;
+	case offsetof(struct virtio_pci_mmio, padding):
+		bad_driver(d, "read from padding (%#x)", getreg(eip));
+	default:
+		/* Read from device config space, beware unaligned overflow */
+		if (off > d->mmio_size - 4)
+			bad_driver(d, "read past end (%#x)", getreg(eip));
+
+		/*
+		 * 3.1.1:
+		 *  The driver MUST follow this sequence to initialize a device:
+		 *...
+		 *  3. Set the DRIVER status bit: the guest OS knows how to
+		 *  drive the device.
+		 *  4. Read device feature bits, and write the subset of
+		 *  feature bits understood by the OS and driver to the
+		 *  device. During this step the driver MAY read (but MUST NOT
+		 *  write) the device-specific configuration fields to check
+		 *  that it can support the device before accepting it.
+		 */
+		if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER))
+			bad_driver(d,
+				   "config read before VIRTIO_CONFIG_S_DRIVER");
+
+		if (mask == 0xFFFFFFFF)
+			goto read_through32;
+		else if (mask == 0xFFFF)
+			goto read_through16;
+		else
+			goto read_through8;
+	}
+
+	/*
+	 * 4.1.3.1:
+	 *
+	 *  The driver MUST access each field using the “natural” access
+	 *  method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for
+	 *  16-bit fields and 8-bit accesses for 8-bit fields.
+	 */
+read_through32:
+	if (mask != 0xFFFFFFFF)
+		bad_driver(d, "non-32-bit read to offset %u (%#x)",
+			   off, getreg(eip));
+	memcpy(&val, (char *)d->mmio + off, 4);
+	return val;
+
+read_through16:
+	if (mask != 0xFFFF)
+		bad_driver(d, "non-16-bit read to offset %u (%#x)",
+			   off, getreg(eip));
+	memcpy(&val, (char *)d->mmio + off, 2);
+	return val;
+
+read_through8:
+	if (mask != 0xFF)
+		bad_driver(d, "non-8-bit read to offset %u (%#x)",
+			   off, getreg(eip));
+	memcpy(&val, (char *)d->mmio + off, 1);
+	return val;
 }
 
-/*
- * This routine allocates a new "struct lguest_device_desc" from descriptor
- * table page just above the Guest's normal memory.  It returns a pointer to
- * that descriptor.
- */
-static struct lguest_device_desc *new_dev_desc(u16 type)
+static void emulate_mmio(unsigned long paddr, const u8 *insn)
 {
-	struct lguest_device_desc d = { .type = type };
-	void *p;
+	u32 val, off, mask = 0xFFFFFFFF, insnlen = 0;
+	struct device *d = find_mmio_region(paddr, &off);
+	unsigned long args[] = { LHREQ_TRAP, 14 };
 
-	/* Figure out where the next device config is, based on the last one. */
-	if (devices.lastdev)
-		p = device_config(devices.lastdev)
-			+ devices.lastdev->desc->config_len;
-	else
-		p = devices.descpage;
+	if (!d) {
+		warnx("MMIO touching %#08lx (not a device)", paddr);
+		goto reinject;
+	}
+
+	/* Prefix makes it a 16 bit op */
+	if (insn[0] == 0x66) {
+		mask = 0xFFFF;
+		insnlen++;
+	}
 
-	/* We only have one page for all the descriptors. */
-	if (p + sizeof(d) > (void *)devices.descpage + getpagesize())
-		errx(1, "Too many devices");
+	/* iowrite */
+	if (insn[insnlen] == 0x89) {
+		/* Next byte is r/m byte: bits 3-5 are register. */
+		val = getreg_num((insn[insnlen+1] >> 3) & 0x7, mask);
+		emulate_mmio_write(d, off, val, mask);
+		insnlen += 2 + insn_displacement_len(insn[insnlen+1]);
+	} else if (insn[insnlen] == 0x8b) { /* ioread */
+		/* Next byte is r/m byte: bits 3-5 are register. */
+		val = emulate_mmio_read(d, off, mask);
+		setreg_num((insn[insnlen+1] >> 3) & 0x7, val, mask);
+		insnlen += 2 + insn_displacement_len(insn[insnlen+1]);
+	} else if (insn[0] == 0x88) { /* 8-bit iowrite */
+		mask = 0xff;
+		/* Next byte is r/m byte: bits 3-5 are register. */
+		val = getreg_num((insn[1] >> 3) & 0x7, mask);
+		emulate_mmio_write(d, off, val, mask);
+		insnlen = 2 + insn_displacement_len(insn[1]);
+	} else if (insn[0] == 0x8a) { /* 8-bit ioread */
+		mask = 0xff;
+		val = emulate_mmio_read(d, off, mask);
+		setreg_num((insn[1] >> 3) & 0x7, val, mask);
+		insnlen = 2 + insn_displacement_len(insn[1]);
+	} else {
+		warnx("Unknown MMIO instruction touching %#08lx:"
+		     " %02x %02x %02x %02x at %u",
+		     paddr, insn[0], insn[1], insn[2], insn[3], getreg(eip));
+	reinject:
+		/* Inject trap into Guest. */
+		if (write(lguest_fd, args, sizeof(args)) < 0)
+			err(1, "Reinjecting trap 14 for fault at %#x",
+			    getreg(eip));
+		return;
+	}
 
-	/* p might not be aligned, so we memcpy in. */
-	return memcpy(p, &d, sizeof(d));
+	/* Finally, we've "done" the instruction, so move past it. */
+	setreg(eip, getreg(eip) + insnlen);
 }
 
-/*
- * Each device descriptor is followed by the description of its virtqueues.  We
- * specify how many descriptors the virtqueue is to have.
+/*L:190
+ * Device Setup
+ *
+ * All devices need a descriptor so the Guest knows it exists, and a "struct
+ * device" so the Launcher can keep track of it.  We have common helper
+ * routines to allocate and manage them.
  */
-static void add_virtqueue(struct device *dev, unsigned int num_descs,
-			  void (*service)(struct virtqueue *))
+static void add_pci_virtqueue(struct device *dev,
+			      void (*service)(struct virtqueue *),
+			      const char *name)
 {
-	unsigned int pages;
 	struct virtqueue **i, *vq = malloc(sizeof(*vq));
-	void *p;
-
-	/* First we need some memory for this virtqueue. */
-	pages = (vring_size(num_descs, LGUEST_VRING_ALIGN) + getpagesize() - 1)
-		/ getpagesize();
-	p = get_pages(pages);
 
 	/* Initialize the virtqueue */
 	vq->next = NULL;
 	vq->last_avail_idx = 0;
 	vq->dev = dev;
+	vq->name = name;
 
 	/*
 	 * This is the routine the service thread will run, and its Process ID
@@ -1218,25 +2393,11 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	vq->thread = (pid_t)-1;
 
 	/* Initialize the configuration. */
-	vq->config.num = num_descs;
-	vq->config.irq = devices.next_irq++;
-	vq->config.pfn = to_guest_phys(p) / getpagesize();
-
-	/* Initialize the vring. */
-	vring_init(&vq->vring, num_descs, p, LGUEST_VRING_ALIGN);
-
-	/*
-	 * Append virtqueue to this device's descriptor.  We use
-	 * device_config() to get the end of the device's current virtqueues;
-	 * we check that we haven't added any config or feature information
-	 * yet, otherwise we'd be overwriting them.
-	 */
-	assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0);
-	memcpy(device_config(dev), &vq->config, sizeof(vq->config));
-	dev->num_vq++;
-	dev->desc->num_vq++;
+	reset_vq_pci_config(vq);
+	vq->pci_config.queue_notify_off = 0;
 
-	verbose("Virtqueue page %#lx\n", to_guest_phys(p));
+	/* Add one to the number of queues */
+	vq->dev->mmio->cfg.num_queues++;
 
 	/*
 	 * Add to tail of list, so dev->vq is first vq, dev->vq->next is
@@ -1246,73 +2407,239 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
 	*i = vq;
 }
 
-/*
- * The first half of the feature bitmask is for us to advertise features.  The
- * second half is for the Guest to accept features.
- */
-static void add_feature(struct device *dev, unsigned bit)
+/* The Guest accesses the feature bits via the PCI common config MMIO region */
+static void add_pci_feature(struct device *dev, unsigned bit)
 {
-	u8 *features = get_feature_bits(dev);
+	dev->features |= (1ULL << bit);
+}
 
-	/* We can't extend the feature bits once we've added config bytes */
-	if (dev->desc->feature_len <= bit / CHAR_BIT) {
-		assert(dev->desc->config_len == 0);
-		dev->feature_len = dev->desc->feature_len = (bit/CHAR_BIT) + 1;
-	}
+/* For devices with no config. */
+static void no_device_config(struct device *dev)
+{
+	dev->mmio_addr = get_mmio_region(dev->mmio_size);
 
-	features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT));
+	dev->config.bar[0] = dev->mmio_addr;
+	/* Bottom 4 bits must be zero */
+	assert(~(dev->config.bar[0] & 0xF));
+}
+
+/* This puts the device config into BAR0 */
+static void set_device_config(struct device *dev, const void *conf, size_t len)
+{
+	/* Set up BAR 0 */
+	dev->mmio_size += len;
+	dev->mmio = realloc(dev->mmio, dev->mmio_size);
+	memcpy(dev->mmio + 1, conf, len);
+
+	/*
+	 * 4.1.4.6:
+	 *
+	 *  The device MUST present at least one VIRTIO_PCI_CAP_DEVICE_CFG
+	 *  capability for any device type which has a device-specific
+	 *  configuration.
+	 */
+	/* Hook up device cfg */
+	dev->config.cfg_access.cap.cap_next
+		= offsetof(struct pci_config, device);
+
+	/*
+	 * 4.1.4.6.1:
+	 *
+	 *  The offset for the device-specific configuration MUST be 4-byte
+	 *  aligned.
+	 */
+	assert(dev->config.cfg_access.cap.cap_next % 4 == 0);
+
+	/* Fix up device cfg field length. */
+	dev->config.device.length = len;
+
+	/* The rest is the same as the no-config case */
+	no_device_config(dev);
+}
+
+static void init_cap(struct virtio_pci_cap *cap, size_t caplen, int type,
+		     size_t bar_offset, size_t bar_bytes, u8 next)
+{
+	cap->cap_vndr = PCI_CAP_ID_VNDR;
+	cap->cap_next = next;
+	cap->cap_len = caplen;
+	cap->cfg_type = type;
+	cap->bar = 0;
+	memset(cap->padding, 0, sizeof(cap->padding));
+	cap->offset = bar_offset;
+	cap->length = bar_bytes;
 }
 
 /*
- * This routine sets the configuration fields for an existing device's
- * descriptor.  It only works for the last device, but that's OK because that's
- * how we use it.
+ * This sets up the pci_config structure, as defined in the virtio 1.0
+ * standard (and PCI standard).
  */
-static void set_config(struct device *dev, unsigned len, const void *conf)
+static void init_pci_config(struct pci_config *pci, u16 type,
+			    u8 class, u8 subclass)
 {
-	/* Check we haven't overflowed our single page. */
-	if (device_config(dev) + len > devices.descpage + getpagesize())
-		errx(1, "Too many devices");
+	size_t bar_offset, bar_len;
+
+	/*
+	 * 4.1.4.4.1:
+	 *
+	 *  The device MUST either present notify_off_multiplier as an even
+	 *  power of 2, or present notify_off_multiplier as 0.
+	 *
+	 * 2.1.2:
+	 *
+	 *   The device MUST initialize device status to 0 upon reset. 
+	 */
+	memset(pci, 0, sizeof(*pci));
+
+	/* 4.1.2.1: Devices MUST have the PCI Vendor ID 0x1AF4 */
+	pci->vendor_id = 0x1AF4;
+	/* 4.1.2.1: ... PCI Device ID calculated by adding 0x1040 ... */
+	pci->device_id = 0x1040 + type;
+
+	/*
+	 * PCI have specific codes for different types of devices.
+	 * Linux doesn't care, but it's a good clue for people looking
+	 * at the device.
+	 */
+	pci->class = class;
+	pci->subclass = subclass;
+
+	/*
+	 * 4.1.2.1:
+	 *
+	 *  Non-transitional devices SHOULD have a PCI Revision ID of 1 or
+	 *  higher
+	 */
+	pci->revid = 1;
+
+	/*
+	 * 4.1.2.1:
+	 *
+	 *  Non-transitional devices SHOULD have a PCI Subsystem Device ID of
+	 *  0x40 or higher.
+	 */
+	pci->subsystem_device_id = 0x40;
+
+	/* We use our dummy interrupt controller, and irq_line is the irq */
+	pci->irq_line = devices.next_irq++;
+	pci->irq_pin = 0;
+
+	/* Support for extended capabilities. */
+	pci->status = (1 << 4);
+
+	/* Link them in. */
+	/*
+	 * 4.1.4.3.1:
+	 *
+	 *  The device MUST present at least one common configuration
+	 *  capability.
+	 */
+	pci->capabilities = offsetof(struct pci_config, common);
+
+	/* 4.1.4.3.1 ... offset MUST be 4-byte aligned. */
+	assert(pci->capabilities % 4 == 0);
+
+	bar_offset = offsetof(struct virtio_pci_mmio, cfg);
+	bar_len = sizeof(((struct virtio_pci_mmio *)0)->cfg);
+	init_cap(&pci->common, sizeof(pci->common), VIRTIO_PCI_CAP_COMMON_CFG,
+		 bar_offset, bar_len,
+		 offsetof(struct pci_config, notify));
+
+	/*
+	 * 4.1.4.4.1:
+	 *
+	 *  The device MUST present at least one notification capability.
+	 */
+	bar_offset += bar_len;
+	bar_len = sizeof(((struct virtio_pci_mmio *)0)->notify);
+
+	/*
+	 * 4.1.4.4.1:
+	 *
+	 *  The cap.offset MUST be 2-byte aligned.
+	 */
+	assert(pci->common.cap_next % 2 == 0);
+
+	/* FIXME: Use a non-zero notify_off, for per-queue notification? */
+	/*
+	 * 4.1.4.4.1:
+	 *
+	 *  The value cap.length presented by the device MUST be at least 2 and
+	 *  MUST be large enough to support queue notification offsets for all
+	 *  supported queues in all possible configurations.
+	 */
+	assert(bar_len >= 2);
+
+	init_cap(&pci->notify.cap, sizeof(pci->notify),
+		 VIRTIO_PCI_CAP_NOTIFY_CFG,
+		 bar_offset, bar_len,
+		 offsetof(struct pci_config, isr));
+
+	bar_offset += bar_len;
+	bar_len = sizeof(((struct virtio_pci_mmio *)0)->isr);
+	/*
+	 * 4.1.4.5.1:
+	 *
+	 *  The device MUST present at least one VIRTIO_PCI_CAP_ISR_CFG
+	 *  capability.
+	 */
+	init_cap(&pci->isr, sizeof(pci->isr),
+		 VIRTIO_PCI_CAP_ISR_CFG,
+		 bar_offset, bar_len,
+		 offsetof(struct pci_config, cfg_access));
+
+	/*
+	 * 4.1.4.7.1:
+	 *
+	 * The device MUST present at least one VIRTIO_PCI_CAP_PCI_CFG
+	 * capability.
+	 */
+	/* This doesn't have any presence in the BAR */
+	init_cap(&pci->cfg_access.cap, sizeof(pci->cfg_access),
+		 VIRTIO_PCI_CAP_PCI_CFG,
+		 0, 0, 0);
 
-	/* Copy in the config information, and store the length. */
-	memcpy(device_config(dev), conf, len);
-	dev->desc->config_len = len;
+	bar_offset += bar_len + sizeof(((struct virtio_pci_mmio *)0)->padding);
+	assert(bar_offset == sizeof(struct virtio_pci_mmio));
 
-	/* Size must fit in config_len field (8 bits)! */
-	assert(dev->desc->config_len == len);
+	/*
+	 * This gets sewn in and length set in set_device_config().
+	 * Some devices don't have a device configuration interface, so
+	 * we never expose this if we don't call set_device_config().
+	 */
+	init_cap(&pci->device, sizeof(pci->device), VIRTIO_PCI_CAP_DEVICE_CFG,
+		 bar_offset, 0, 0);
 }
 
 /*
- * This routine does all the creation and setup of a new device, including
- * calling new_dev_desc() to allocate the descriptor and device memory.  We
- * don't actually start the service threads until later.
+ * This routine does all the creation and setup of a new device, but we don't
+ * actually place the MMIO region until we know the size (if any) of the
+ * device-specific config.  And we don't actually start the service threads
+ * until later.
  *
  * See what I mean about userspace being boring?
  */
-static struct device *new_device(const char *name, u16 type)
+static struct device *new_pci_device(const char *name, u16 type,
+				     u8 class, u8 subclass)
 {
 	struct device *dev = malloc(sizeof(*dev));
 
 	/* Now we populate the fields one at a time. */
-	dev->desc = new_dev_desc(type);
 	dev->name = name;
 	dev->vq = NULL;
-	dev->feature_len = 0;
-	dev->num_vq = 0;
 	dev->running = false;
-	dev->next = NULL;
+	dev->wrote_features_ok = false;
+	dev->mmio_size = sizeof(struct virtio_pci_mmio);
+	dev->mmio = calloc(1, dev->mmio_size);
+	dev->features = (u64)1 << VIRTIO_F_VERSION_1;
+	dev->features_accepted = 0;
 
-	/*
-	 * Append to device list.  Prepending to a single-linked list is
-	 * easier, but the user expects the devices to be arranged on the bus
-	 * in command-line order.  The first network device on the command line
-	 * is eth0, the first block device /dev/vda, etc.
-	 */
-	if (devices.lastdev)
-		devices.lastdev->next = dev;
-	else
-		devices.dev = dev;
-	devices.lastdev = dev;
+	if (devices.device_num + 1 >= MAX_PCI_DEVICES)
+		errx(1, "Can only handle 31 PCI devices");
+
+	init_pci_config(&dev->config, type, class, subclass);
+	assert(!devices.pci[devices.device_num+1]);
+	devices.pci[++devices.device_num] = dev;
 
 	return dev;
 }
@@ -1324,6 +2651,7 @@ static struct device *new_device(const char *name, u16 type)
 static void setup_console(void)
 {
 	struct device *dev;
+	struct virtio_console_config conf;
 
 	/* If we can save the initial standard input settings... */
 	if (tcgetattr(STDIN_FILENO, &orig_term) == 0) {
@@ -1336,7 +2664,7 @@ static void setup_console(void)
 		tcsetattr(STDIN_FILENO, TCSANOW, &term);
 	}
 
-	dev = new_device("console", VIRTIO_ID_CONSOLE);
+	dev = new_pci_device("console", VIRTIO_ID_CONSOLE, 0x07, 0x00);
 
 	/* We store the console state in dev->priv, and initialize it. */
 	dev->priv = malloc(sizeof(struct console_abort));
@@ -1348,10 +2676,14 @@ static void setup_console(void)
 	 * stdin.  When they put something in the output queue, we write it to
 	 * stdout.
 	 */
-	add_virtqueue(dev, VIRTQUEUE_NUM, console_input);
-	add_virtqueue(dev, VIRTQUEUE_NUM, console_output);
+	add_pci_virtqueue(dev, console_input, "input");
+	add_pci_virtqueue(dev, console_output, "output");
+
+	/* We need a configuration area for the emerg_wr early writes. */
+	add_pci_feature(dev, VIRTIO_CONSOLE_F_EMERG_WRITE);
+	set_device_config(dev, &conf, sizeof(conf));
 
-	verbose("device %u: console\n", ++devices.device_num);
+	verbose("device %u: console\n", devices.device_num);
 }
 /*:*/
 
@@ -1449,6 +2781,7 @@ static void configure_device(int fd, const char *tapif, u32 ipaddr)
 static int get_tun_device(char tapif[IFNAMSIZ])
 {
 	struct ifreq ifr;
+	int vnet_hdr_sz;
 	int netfd;
 
 	/* Start with this zeroed.  Messy but sure. */
@@ -1476,6 +2809,18 @@ static int get_tun_device(char tapif[IFNAMSIZ])
 	 */
 	ioctl(netfd, TUNSETNOCSUM, 1);
 
+	/*
+	 * In virtio before 1.0 (aka legacy virtio), we added a 16-bit
+	 * field at the end of the network header iff
+	 * VIRTIO_NET_F_MRG_RXBUF was negotiated.  For virtio 1.0,
+	 * that became the norm, but we need to tell the tun device
+	 * about our expanded header (which is called
+	 * virtio_net_hdr_mrg_rxbuf in the legacy system).
+	 */
+	vnet_hdr_sz = sizeof(struct virtio_net_hdr_v1);
+	if (ioctl(netfd, TUNSETVNETHDRSZ, &vnet_hdr_sz) != 0)
+		err(1, "Setting tun header size to %u", vnet_hdr_sz);
+
 	memcpy(tapif, ifr.ifr_name, IFNAMSIZ);
 	return netfd;
 }
@@ -1499,12 +2844,12 @@ static void setup_tun_net(char *arg)
 	net_info->tunfd = get_tun_device(tapif);
 
 	/* First we create a new network device. */
-	dev = new_device("net", VIRTIO_ID_NET);
+	dev = new_pci_device("net", VIRTIO_ID_NET, 0x02, 0x00);
 	dev->priv = net_info;
 
 	/* Network devices need a recv and a send queue, just like console. */
-	add_virtqueue(dev, VIRTQUEUE_NUM, net_input);
-	add_virtqueue(dev, VIRTQUEUE_NUM, net_output);
+	add_pci_virtqueue(dev, net_input, "rx");
+	add_pci_virtqueue(dev, net_output, "tx");
 
 	/*
 	 * We need a socket to perform the magic network ioctls to bring up the
@@ -1524,7 +2869,7 @@ static void setup_tun_net(char *arg)
 	p = strchr(arg, ':');
 	if (p) {
 		str2mac(p+1, conf.mac);
-		add_feature(dev, VIRTIO_NET_F_MAC);
+		add_pci_feature(dev, VIRTIO_NET_F_MAC);
 		*p = '\0';
 	}
 
@@ -1538,25 +2883,21 @@ static void setup_tun_net(char *arg)
 	configure_device(ipfd, tapif, ip);
 
 	/* Expect Guest to handle everything except UFO */
-	add_feature(dev, VIRTIO_NET_F_CSUM);
-	add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);
-	add_feature(dev, VIRTIO_NET_F_GUEST_TSO4);
-	add_feature(dev, VIRTIO_NET_F_GUEST_TSO6);
-	add_feature(dev, VIRTIO_NET_F_GUEST_ECN);
-	add_feature(dev, VIRTIO_NET_F_HOST_TSO4);
-	add_feature(dev, VIRTIO_NET_F_HOST_TSO6);
-	add_feature(dev, VIRTIO_NET_F_HOST_ECN);
+	add_pci_feature(dev, VIRTIO_NET_F_CSUM);
+	add_pci_feature(dev, VIRTIO_NET_F_GUEST_CSUM);
+	add_pci_feature(dev, VIRTIO_NET_F_GUEST_TSO4);
+	add_pci_feature(dev, VIRTIO_NET_F_GUEST_TSO6);
+	add_pci_feature(dev, VIRTIO_NET_F_GUEST_ECN);
+	add_pci_feature(dev, VIRTIO_NET_F_HOST_TSO4);
+	add_pci_feature(dev, VIRTIO_NET_F_HOST_TSO6);
+	add_pci_feature(dev, VIRTIO_NET_F_HOST_ECN);
 	/* We handle indirect ring entries */
-	add_feature(dev, VIRTIO_RING_F_INDIRECT_DESC);
-	/* We're compliant with the damn spec. */
-	add_feature(dev, VIRTIO_F_ANY_LAYOUT);
-	set_config(dev, sizeof(conf), &conf);
+	add_pci_feature(dev, VIRTIO_RING_F_INDIRECT_DESC);
+	set_device_config(dev, &conf, sizeof(conf));
 
 	/* We don't need the socket any more; setup is done. */
 	close(ipfd);
 
-	devices.device_num++;
-
 	if (bridging)
 		verbose("device %u: tun %s attached to bridge: %s\n",
 			devices.device_num, tapif, arg);
@@ -1607,7 +2948,7 @@ static void blk_request(struct virtqueue *vq)
 	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 
 	/* Copy the output header from the front of the iov (adjusts iov) */
-	iov_consume(iov, out_num, &out, sizeof(out));
+	iov_consume(vq->dev, iov, out_num, &out, sizeof(out));
 
 	/* Find and trim end of iov input array, for our status byte. */
 	in = NULL;
@@ -1619,7 +2960,7 @@ static void blk_request(struct virtqueue *vq)
 		}
 	}
 	if (!in)
-		errx(1, "Bad virtblk cmd with no room for status");
+		bad_driver_vq(vq, "Bad virtblk cmd with no room for status");
 
 	/*
 	 * For historical reasons, block operations are expressed in 512 byte
@@ -1627,15 +2968,7 @@ static void blk_request(struct virtqueue *vq)
 	 */
 	off = out.sector * 512;
 
-	/*
-	 * In general the virtio block driver is allowed to try SCSI commands.
-	 * It'd be nice if we supported eject, for example, but we don't.
-	 */
-	if (out.type & VIRTIO_BLK_T_SCSI_CMD) {
-		fprintf(stderr, "Scsi commands unsupported\n");
-		*in = VIRTIO_BLK_S_UNSUPP;
-		wlen = sizeof(*in);
-	} else if (out.type & VIRTIO_BLK_T_OUT) {
+	if (out.type & VIRTIO_BLK_T_OUT) {
 		/*
 		 * Write
 		 *
@@ -1657,7 +2990,7 @@ static void blk_request(struct virtqueue *vq)
 			/* Trim it back to the correct length */
 			ftruncate64(vblk->fd, vblk->len);
 			/* Die, bad Guest, die. */
-			errx(1, "Write past end %llu+%u", off, ret);
+			bad_driver_vq(vq, "Write past end %llu+%u", off, ret);
 		}
 
 		wlen = sizeof(*in);
@@ -1699,11 +3032,11 @@ static void setup_block_file(const char *filename)
 	struct vblk_info *vblk;
 	struct virtio_blk_config conf;
 
-	/* Creat the device. */
-	dev = new_device("block", VIRTIO_ID_BLOCK);
+	/* Create the device. */
+	dev = new_pci_device("block", VIRTIO_ID_BLOCK, 0x01, 0x80);
 
 	/* The device has one virtqueue, where the Guest places requests. */
-	add_virtqueue(dev, VIRTQUEUE_NUM, blk_request);
+	add_pci_virtqueue(dev, blk_request, "request");
 
 	/* Allocate the room for our own bookkeeping */
 	vblk = dev->priv = malloc(sizeof(*vblk));
@@ -1712,9 +3045,6 @@ static void setup_block_file(const char *filename)
 	vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
 	vblk->len = lseek64(vblk->fd, 0, SEEK_END);
 
-	/* We support FLUSH. */
-	add_feature(dev, VIRTIO_BLK_F_FLUSH);
-
 	/* Tell Guest how many sectors this device has. */
 	conf.capacity = cpu_to_le64(vblk->len / 512);
 
@@ -1722,20 +3052,19 @@ static void setup_block_file(const char *filename)
 	 * Tell Guest not to put in too many descriptors at once: two are used
 	 * for the in and out elements.
 	 */
-	add_feature(dev, VIRTIO_BLK_F_SEG_MAX);
+	add_pci_feature(dev, VIRTIO_BLK_F_SEG_MAX);
 	conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2);
 
-	/* Don't try to put whole struct: we have 8 bit limit. */
-	set_config(dev, offsetof(struct virtio_blk_config, geometry), &conf);
+	set_device_config(dev, &conf, sizeof(struct virtio_blk_config));
 
 	verbose("device %u: virtblock %llu sectors\n",
-		++devices.device_num, le64_to_cpu(conf.capacity));
+		devices.device_num, le64_to_cpu(conf.capacity));
 }
 
 /*L:211
- * Our random number generator device reads from /dev/random into the Guest's
+ * Our random number generator device reads from /dev/urandom into the Guest's
  * input buffers.  The usual case is that the Guest doesn't want random numbers
- * and so has no buffers although /dev/random is still readable, whereas
+ * and so has no buffers although /dev/urandom is still readable, whereas
  * console is the reverse.
  *
  * The same logic applies, however.
@@ -1754,7 +3083,7 @@ static void rng_input(struct virtqueue *vq)
 	/* First we need a buffer from the Guests's virtqueue. */
 	head = wait_for_vq_desc(vq, iov, &out_num, &in_num);
 	if (out_num)
-		errx(1, "Output buffers in rng?");
+		bad_driver_vq(vq, "Output buffers in rng?");
 
 	/*
 	 * Just like the console write, we loop to cover the whole iovec.
@@ -1763,8 +3092,8 @@ static void rng_input(struct virtqueue *vq)
 	while (!iov_empty(iov, in_num)) {
 		len = readv(rng_info->rfd, iov, in_num);
 		if (len <= 0)
-			err(1, "Read from /dev/random gave %i", len);
-		iov_consume(iov, in_num, NULL, len);
+			err(1, "Read from /dev/urandom gave %i", len);
+		iov_consume(vq->dev, iov, in_num, NULL, len);
 		totlen += len;
 	}
 
@@ -1780,17 +3109,20 @@ static void setup_rng(void)
 	struct device *dev;
 	struct rng_info *rng_info = malloc(sizeof(*rng_info));
 
-	/* Our device's privat info simply contains the /dev/random fd. */
-	rng_info->rfd = open_or_die("/dev/random", O_RDONLY);
+	/* Our device's private info simply contains the /dev/urandom fd. */
+	rng_info->rfd = open_or_die("/dev/urandom", O_RDONLY);
 
 	/* Create the new device. */
-	dev = new_device("rng", VIRTIO_ID_RNG);
+	dev = new_pci_device("rng", VIRTIO_ID_RNG, 0xff, 0);
 	dev->priv = rng_info;
 
 	/* The device has one virtqueue, where the Guest places inbufs. */
-	add_virtqueue(dev, VIRTQUEUE_NUM, rng_input);
+	add_pci_virtqueue(dev, rng_input, "input");
 
-	verbose("device %u: rng\n", devices.device_num++);
+	/* We don't have any configuration space */
+	no_device_config(dev);
+
+	verbose("device %u: rng\n", devices.device_num);
 }
 /* That's the end of device setup. */
 
@@ -1820,17 +3152,23 @@ static void __attribute__((noreturn)) restart_guest(void)
 static void __attribute__((noreturn)) run_guest(void)
 {
 	for (;;) {
-		unsigned long notify_addr;
+		struct lguest_pending notify;
 		int readval;
 
 		/* We read from the /dev/lguest device to run the Guest. */
-		readval = pread(lguest_fd, &notify_addr,
-				sizeof(notify_addr), cpu_id);
-
-		/* One unsigned long means the Guest did HCALL_NOTIFY */
-		if (readval == sizeof(notify_addr)) {
-			verbose("Notify on address %#lx\n", notify_addr);
-			handle_output(notify_addr);
+		readval = pread(lguest_fd, &notify, sizeof(notify), cpu_id);
+		if (readval == sizeof(notify)) {
+			if (notify.trap == 13) {
+				verbose("Emulating instruction at %#x\n",
+					getreg(eip));
+				emulate_insn(notify.insn);
+			} else if (notify.trap == 14) {
+				verbose("Emulating MMIO at %#x\n",
+					getreg(eip));
+				emulate_mmio(notify.addr, notify.insn);
+			} else
+				errx(1, "Unknown trap %i addr %#08x\n",
+				     notify.trap, notify.addr);
 		/* ENOENT means the Guest died.  Reading tells us why. */
 		} else if (errno == ENOENT) {
 			char reason[1024] = { 0 };
@@ -1893,11 +3231,9 @@ int main(int argc, char *argv[])
 	main_args = argv;
 
 	/*
-	 * First we initialize the device list.  We keep a pointer to the last
-	 * device, and the next interrupt number to use for devices (1:
-	 * remember that 0 is used by the timer).
+	 * First we initialize the device list.  We remember next interrupt
+	 * number to use for devices (1: remember that 0 is used by the timer).
 	 */
-	devices.lastdev = NULL;
 	devices.next_irq = 1;
 
 	/* We're CPU 0.  In fact, that's the only CPU possible right now. */
@@ -1921,12 +3257,14 @@ int main(int argc, char *argv[])
 			guest_base = map_zeroed_pages(mem / getpagesize()
 						      + DEVICE_PAGES);
 			guest_limit = mem;
-			guest_max = mem + DEVICE_PAGES*getpagesize();
-			devices.descpage = get_pages(1);
+			guest_max = guest_mmio = mem + DEVICE_PAGES*getpagesize();
 			break;
 		}
 	}
 
+	/* We always have a console device, and it's always device 1. */
+	setup_console();
+
 	/* The options are fairly straight-forward */
 	while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) {
 		switch (c) {
@@ -1967,8 +3305,8 @@ int main(int argc, char *argv[])
 
 	verbose("Guest base is at %p\n", guest_base);
 
-	/* We always have a console device */
-	setup_console();
+	/* Initialize the (fake) PCI host bridge device. */
+	init_pci_host_bridge();
 
 	/* Now we load the kernel */
 	start = load_kernel(open_or_die(argv[optind+1], O_RDONLY));
diff --git a/tools/lib/lockdep/.gitignore b/tools/lib/lockdep/.gitignore
new file mode 100644
index 000000000000..cc0e7a9f99e3
--- /dev/null
+++ b/tools/lib/lockdep/.gitignore
@@ -0,0 +1 @@
+liblockdep.so.*
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index 8c3340a4b9f8..0c356fb65022 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -73,7 +73,7 @@ N		=
 
 export Q VERBOSE
 
-INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES)
+INCLUDES = -I. -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES)
 
 # Set compile option CFLAGS if not set elsewhere
 CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g
diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c
index f4b953354ff7..eec688041500 100644
--- a/tools/power/acpi/common/cmfsize.c
+++ b/tools/power/acpi/common/cmfsize.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c
index 2f0f34a36db4..5da129e10aa2 100644
--- a/tools/power/acpi/common/getopt.c
+++ b/tools/power/acpi/common/getopt.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/oslibcfs.c b/tools/power/acpi/os_specific/service_layers/oslibcfs.c
index c13ff9c51d74..b51e40a9a120 100644
--- a/tools/power/acpi/os_specific/service_layers/oslibcfs.c
+++ b/tools/power/acpi/os_specific/service_layers/oslibcfs.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
index 0dc2485dedf5..92f1fd700344 100644
--- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
+++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c
index 733f9e490fc4..e153fcb12b1a 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixdir.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c
index 99b47b6194a3..3853a7350440 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixmap.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c
index 7ccb073f8316..6858c0893c91 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixxf.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h
index a2d37d610639..84bdef0136cb 100644
--- a/tools/power/acpi/tools/acpidump/acpidump.h
+++ b/tools/power/acpi/tools/acpidump/acpidump.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c
index 24d32968802d..c736adf5fb55 100644
--- a/tools/power/acpi/tools/acpidump/apdump.c
+++ b/tools/power/acpi/tools/acpidump/apdump.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c
index d470046a6d81..8f2fe168228e 100644
--- a/tools/power/acpi/tools/acpidump/apfiles.c
+++ b/tools/power/acpi/tools/acpidump/apfiles.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c
index 853b4da22c3e..d0ba6535f5af 100644
--- a/tools/power/acpi/tools/acpidump/apmain.c
+++ b/tools/power/acpi/tools/acpidump/apmain.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index 2e2ba2efa0d9..3ed7c0476d48 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -209,7 +209,7 @@ $(OUTPUT)%.o: %.c
 
 $(OUTPUT)cpupower: $(UTIL_OBJS) $(OUTPUT)libcpupower.so.$(LIB_MAJ)
 	$(ECHO) "  CC      " $@
-	$(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) $(UTIL_OBJS) -lcpupower -lrt -lpci -L$(OUTPUT) -o $@
+	$(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) $(UTIL_OBJS) -lcpupower -Wl,-rpath=./ -lrt -lpci -L$(OUTPUT) -o $@
 	$(QUIET) $(STRIPCMD) $@
 
 $(OUTPUT)po/$(PACKAGE).pot: $(UTIL_SRC)
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 56bfb523c5bb..feea7ad9500b 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -9,40 +9,50 @@ turbostat \- Report processor frequency and idle statistics
 .br
 .B turbostat
 .RB [ Options ]
-.RB [ "\-i interval_sec" ]
+.RB [ "\--interval seconds" ]
 .SH DESCRIPTION
 \fBturbostat \fP reports processor topology, frequency,
-idle power-state statistics, temperature and power on modern X86 processors.
-Either \fBcommand\fP is forked and statistics are printed
-upon its completion, or statistics are printed periodically.
-
-\fBturbostat \fP
-must be run on root, and
-minimally requires that the processor
-supports an "invariant" TSC, plus the APERF and MPERF MSRs.
-Additional information is reported depending on hardware counter support.
-
+idle power-state statistics, temperature and power on X86 processors.
+There are two ways to invoke turbostat.
+The first method is to supply a
+\fBcommand\fP, which is forked and statistics are printed
+upon its completion.
+The second method is to omit the command,
+and turbostat displays statistics every 5 seconds.
+The 5-second interval can be changed using the --interval option.
+
+Some information is not available on older processors.
 .SS Options
-The \fB-p\fP option limits output to the 1st thread in 1st core of each package.
+\fB--Counter MSR#\fP shows the delta of the specified 64-bit MSR counter.
+.PP
+\fB--counter MSR#\fP shows the delta of the specified 32-bit MSR counter.
+.PP
+\fB--Dump\fP displays the raw counter values.
+.PP
+\fB--debug\fP displays additional system configuration information.  Invoking this parameter
+more than once may also enable internal turbostat debug information.
+.PP
+\fB--interval seconds\fP overrides the default 5-second measurement interval.
+.PP
+\fB--help\fP displays usage for the most common parameters.
 .PP
-The \fB-P\fP option limits output to the 1st thread in each Package.
+\fB--Joules\fP displays energy in Joules, rather than dividing Joules by time to print power in Watts.
 .PP
-The \fB-S\fP option limits output to a 1-line System Summary for each interval.
+\fB--MSR MSR#\fP shows the specified 64-bit MSR value.
 .PP
-The \fB-v\fP option increases verbosity.
+\fB--msr MSR#\fP shows the specified 32-bit MSR value.
 .PP
-The \fB-c MSR#\fP option includes the delta of the specified 32-bit MSR counter.
+\fB--Package\fP limits output to the system summary plus the 1st thread in each Package.
 .PP
-The \fB-C MSR#\fP option includes the delta of the specified 64-bit MSR counter.
+\fB--processor\fP limits output to the system summary plus the 1st thread in each processor of each package.  Ie. it skips hyper-threaded siblings.
 .PP
-The \fB-m MSR#\fP option includes the the specified 32-bit MSR value.
+\fB--Summary\fP limits output to a 1-line System Summary for each interval.
 .PP
-The \fB-M MSR#\fP option includes the the specified 64-bit MSR value.
+\fB--TCC temperature\fP sets the Thermal Control Circuit temperature for systems which do not export that value.  This is used for making sense of the Digital Thermal Sensor outputs, as they return degrees Celsius below the TCC activation temperature.
 .PP
-The \fB-i interval_sec\fP option prints statistics every \fiinterval_sec\fP seconds.
-The default is 5 seconds.
+\fB--version\fP displays the version.
 .PP
-The \fBcommand\fP parameter forks \fBcommand\fP and upon its exit,
+The \fBcommand\fP parameter forks \fBcommand\fP, and upon its exit,
 displays the statistics gathered since it was forked.
 .PP
 .SH FIELD DESCRIPTIONS
@@ -52,7 +62,7 @@ displays the statistics gathered since it was forked.
 \fBCPU\fP Linux CPU (logical processor) number.
 Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology.
 \fBAVG_MHz\fP number of cycles executed divided by time elapsed.
-\fB%Buzy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
+\fB%Busy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
 \fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state).
 \fBTSC_MHz\fP average MHz that the TSC ran during the entire interval.
 \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.
@@ -68,7 +78,7 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T
 .fi
 .PP
 .SH EXAMPLE
-Without any parameters, turbostat prints out counters ever 5 seconds.
+Without any parameters, turbostat displays statistics ever 5 seconds.
 (override interval with "-i sec" option, or specify a command
 for turbostat to fork).
 
@@ -91,19 +101,19 @@ Subsequent rows show per-CPU statistics.
        3       3       3    0.20    1596    3492       0    0.44    0.00   99.37    0.00      23
        3       7       5    0.31    1596    3492       0    0.33
 .fi
-.SH VERBOSE EXAMPLE
-The "-v" option adds verbosity to the output:
+.SH DEBUG EXAMPLE
+The "--debug" option prints additional system information before measurements:
 
 .nf
-[root@ivy]# turbostat -v
-turbostat v3.0 November 23, 2012 - Len Brown <lenb@kernel.org>
+turbostat version 4.0 10-Feb, 2015 - Len Brown <lenb@kernel.org>
 CPUID(0): GenuineIntel 13 CPUID levels; family:model:stepping 0x6:3a:9 (6:58:9)
 CPUID(6): APERF, DTS, PTM, EPB
-RAPL: 851 sec. Joule Counter Range
+RAPL: 851 sec. Joule Counter Range, at 77 Watts
 cpu0: MSR_NHM_PLATFORM_INFO: 0x81010f0012300
 16 * 100 = 1600 MHz max efficiency
 35 * 100 = 3500 MHz TSC frequency
-cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e008402 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, locked: pkg-cstate-limit=2: pc6-noret)
+cpu0: MSR_IA32_POWER_CTL: 0x0014005d (C1E auto-promotion: DISabled)
+cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e008402 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, locked: pkg-cstate-limit=2: pc6n)
 cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x25262727
 37 * 100 = 3700 MHz max turbo 4 active cores
 38 * 100 = 3800 MHz max turbo 3 active cores
@@ -112,9 +122,9 @@ cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x25262727
 cpu0: MSR_IA32_ENERGY_PERF_BIAS: 0x00000006 (balanced)
 cpu0: MSR_RAPL_POWER_UNIT: 0x000a1003 (0.125000 Watts, 0.000015 Joules, 0.000977 sec.)
 cpu0: MSR_PKG_POWER_INFO: 0x01e00268 (77 W TDP, RAPL 60 - 0 W, 0.000000 sec.)
-cpu0: MSR_PKG_POWER_LIMIT: 0x830000148268 (UNlocked)
+cpu0: MSR_PKG_POWER_LIMIT: 0x30000148268 (UNlocked)
 cpu0: PKG Limit #1: ENabled (77.000000 Watts, 1.000000 sec, clamp DISabled)
-cpu0: PKG Limit #2: ENabled (96.000000 Watts, 0.000977* sec, clamp DISabled)
+cpu0: PKG Limit #2: DISabled (96.000000 Watts, 0.000977* sec, clamp DISabled)
 cpu0: MSR_PP0_POLICY: 0
 cpu0: MSR_PP0_POWER_LIMIT: 0x00000000 (UNlocked)
 cpu0: Cores Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled)
@@ -123,19 +133,20 @@ cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked)
 cpu0: GFX Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled)
 cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x00691400 (105 C)
 cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884e0000 (27 C)
-cpu0: MSR_IA32_THERM_STATUS: 0x88560000 (19 C +/- 1)
-cpu1: MSR_IA32_THERM_STATUS: 0x88560000 (19 C +/- 1)
-cpu2: MSR_IA32_THERM_STATUS: 0x88540000 (21 C +/- 1)
+cpu0: MSR_IA32_THERM_STATUS: 0x88580000 (17 C +/- 1)
+cpu1: MSR_IA32_THERM_STATUS: 0x885a0000 (15 C +/- 1)
+cpu2: MSR_IA32_THERM_STATUS: 0x88570000 (18 C +/- 1)
 cpu3: MSR_IA32_THERM_STATUS: 0x884e0000 (27 C +/- 1)
  ...
 .fi
 The \fBmax efficiency\fP frequency, a.k.a. Low Frequency Mode, is the frequency
-available at the minimum package voltage.  The \fBTSC frequency\fP is the nominal
-maximum frequency of the processor if turbo-mode were not available.  This frequency
+available at the minimum package voltage.  The \fBTSC frequency\fP is the base
+frequency of the processor -- this should match the brand string
+in /proc/cpuinfo.  This base frequency
 should be sustainable on all CPUs indefinitely, given nominal power and cooling.
 The remaining rows show what maximum turbo frequency is possible
-depending on the number of idle cores.  Note that this information is
-not available on all processors.
+depending on the number of idle cores.  Note that not all information is
+available on all processors.
 .SH FORK EXAMPLE
 If turbostat is invoked with a command, it will fork that command
 and output the statistics gathered when the command exits.
@@ -176,6 +187,11 @@ not including any non-busy idle time.
 
 .B "turbostat "
 must be run as root.
+Alternatively, non-root users can be enabled to run turbostat this way:
+
+# setcap cap_sys_rawio=ep ./turbostat
+
+# chmod +r /dev/cpu/*/msr
 
 .B "turbostat "
 reads hardware counters, but doesn't write them.
@@ -184,15 +200,33 @@ multiple invocations of itself.
 
 \fBturbostat \fP
 may work poorly on Linux-2.6.20 through 2.6.29,
-as \fBacpi-cpufreq \fPperiodically cleared the APERF and MPERF
+as \fBacpi-cpufreq \fPperiodically cleared the APERF and MPERF MSRs
 in those kernels.
 
-If the TSC column does not make sense, then
-the other numbers will also make no sense.
-Turbostat is lightweight, and its data collection is not atomic.
-These issues are usually caused by an extremely short measurement
-interval (much less than 1 second), or system activity that prevents
-turbostat from being able to run on all CPUS to quickly collect data.
+AVG_MHz = APERF_delta/measurement_interval.  This is the actual
+number of elapsed cycles divided by the entire sample interval --
+including idle time.  Note that this calculation is resilient
+to systems lacking a non-stop TSC.
+
+TSC_MHz = TSC_delta/measurement_interval.
+On a system with an invariant TSC, this value will be constant
+and will closely match the base frequency value shown
+in the brand string in /proc/cpuinfo.  On a system where
+the TSC stops in idle, TSC_MHz will drop
+below the processor's base frequency.
+
+%Busy = MPERF_delta/TSC_delta
+
+Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval
+
+Note that these calculations depend on TSC_delta, so they
+are not reliable during intervals when TSC_MHz is not running at the base frequency.
+
+Turbostat data collection is not atomic.
+Extremely short measurement intervals (much less than 1 second),
+or system activity that prevents turbostat from being able
+to run on all CPUS to quickly collect data, will result in
+inconsistent results.
 
 The APERF, MPERF MSRs are defined to count non-halted cycles.
 Although it is not guaranteed by the architecture, turbostat assumes
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 5b1b807265a1..2d089cac8580 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -33,24 +33,29 @@
 #include <signal.h>
 #include <sys/time.h>
 #include <stdlib.h>
+#include <getopt.h>
 #include <dirent.h>
 #include <string.h>
 #include <ctype.h>
 #include <sched.h>
 #include <cpuid.h>
+#include <linux/capability.h>
+#include <errno.h>
 
 char *proc_stat = "/proc/stat";
-unsigned int interval_sec = 5;	/* set with -i interval_sec */
-unsigned int verbose;		/* set with -v */
-unsigned int rapl_verbose;	/* set with -R */
-unsigned int rapl_joules;	/* set with -J */
-unsigned int thermal_verbose;	/* set with -T */
-unsigned int summary_only;	/* set with -S */
-unsigned int dump_only;		/* set with -s */
+unsigned int interval_sec = 5;
+unsigned int debug;
+unsigned int rapl_joules;
+unsigned int summary_only;
+unsigned int dump_only;
 unsigned int skip_c0;
 unsigned int skip_c1;
 unsigned int do_nhm_cstates;
 unsigned int do_snb_cstates;
+unsigned int do_pc2;
+unsigned int do_pc3;
+unsigned int do_pc6;
+unsigned int do_pc7;
 unsigned int do_c8_c9_c10;
 unsigned int do_slm_cstates;
 unsigned int use_c1_residency_msr;
@@ -59,8 +64,8 @@ unsigned int has_epb;
 unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int has_invariant_tsc;
-unsigned int do_nehalem_platform_info;
-unsigned int do_nehalem_turbo_ratio_limit;
+unsigned int do_nhm_platform_info;
+unsigned int do_nhm_turbo_ratio_limit;
 unsigned int do_ivt_turbo_ratio_limit;
 unsigned int extra_msr_offset32;
 unsigned int extra_msr_offset64;
@@ -81,6 +86,9 @@ unsigned int tcc_activation_temp;
 unsigned int tcc_activation_temp_override;
 double rapl_power_units, rapl_energy_units, rapl_time_units;
 double rapl_joule_counter_range;
+unsigned int do_core_perf_limit_reasons;
+unsigned int do_gfx_perf_limit_reasons;
+unsigned int do_ring_perf_limit_reasons;
 
 #define RAPL_PKG		(1 << 0)
 					/* 0x610 MSR_PKG_POWER_LIMIT */
@@ -251,15 +259,13 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 	sprintf(pathname, "/dev/cpu/%d/msr", cpu);
 	fd = open(pathname, O_RDONLY);
 	if (fd < 0)
-		return -1;
+		err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname);
 
 	retval = pread(fd, msr, sizeof *msr, offset);
 	close(fd);
 
-	if (retval != sizeof *msr) {
-		fprintf(stderr, "%s offset 0x%llx read failed\n", pathname, (unsigned long long)offset);
-		return -1;
-	}
+	if (retval != sizeof *msr)
+		err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset);
 
 	return 0;
 }
@@ -281,7 +287,7 @@ void print_header(void)
 		outp += sprintf(outp, "     CPU");
 	if (has_aperf)
 		outp += sprintf(outp, " Avg_MHz");
-	if (do_nhm_cstates)
+	if (has_aperf)
 		outp += sprintf(outp, "   %%Busy");
 	if (has_aperf)
 		outp += sprintf(outp, " Bzy_MHz");
@@ -310,13 +316,13 @@ void print_header(void)
 	if (do_ptm)
 		outp += sprintf(outp, "  PkgTmp");
 
-	if (do_snb_cstates)
+	if (do_pc2)
 		outp += sprintf(outp, " Pkg%%pc2");
-	if (do_nhm_cstates && !do_slm_cstates)
+	if (do_pc3)
 		outp += sprintf(outp, " Pkg%%pc3");
-	if (do_nhm_cstates && !do_slm_cstates)
+	if (do_pc6)
 		outp += sprintf(outp, " Pkg%%pc6");
-	if (do_snb_cstates)
+	if (do_pc7)
 		outp += sprintf(outp, " Pkg%%pc7");
 	if (do_c8_c9_c10) {
 		outp += sprintf(outp, " Pkg%%pc8");
@@ -337,7 +343,7 @@ void print_header(void)
 			outp += sprintf(outp, "   PKG_%%");
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
 			outp += sprintf(outp, "   RAM_%%");
-	} else {
+	} else if (do_rapl && rapl_joules) {
 		if (do_rapl & RAPL_PKG)
 			outp += sprintf(outp, "   Pkg_J");
 		if (do_rapl & RAPL_CORES)
@@ -391,9 +397,12 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 	if (p) {
 		outp += sprintf(outp, "package: %d\n", p->package_id);
 		outp += sprintf(outp, "pc2: %016llX\n", p->pc2);
-		outp += sprintf(outp, "pc3: %016llX\n", p->pc3);
-		outp += sprintf(outp, "pc6: %016llX\n", p->pc6);
-		outp += sprintf(outp, "pc7: %016llX\n", p->pc7);
+		if (do_pc3)
+			outp += sprintf(outp, "pc3: %016llX\n", p->pc3);
+		if (do_pc6)
+			outp += sprintf(outp, "pc6: %016llX\n", p->pc6);
+		if (do_pc7)
+			outp += sprintf(outp, "pc7: %016llX\n", p->pc7);
 		outp += sprintf(outp, "pc8: %016llX\n", p->pc8);
 		outp += sprintf(outp, "pc9: %016llX\n", p->pc9);
 		outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
@@ -457,25 +466,25 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			outp += sprintf(outp, "%8d", t->cpu_id);
 	}
 
-	/* AvgMHz */
+	/* Avg_MHz */
 	if (has_aperf)
 		outp += sprintf(outp, "%8.0f",
 			1.0 / units * t->aperf / interval_float);
 
-	/* %c0 */
-	if (do_nhm_cstates) {
+	/* %Busy */
+	if (has_aperf) {
 		if (!skip_c0)
 			outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc);
 		else
 			outp += sprintf(outp, "********");
 	}
 
-	/* BzyMHz */
+	/* Bzy_MHz */
 	if (has_aperf)
 		outp += sprintf(outp, "%8.0f",
 			1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
 
-	/* TSC */
+	/* TSC_MHz */
 	outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
 
 	/* SMI */
@@ -525,13 +534,13 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (do_ptm)
 		outp += sprintf(outp, "%8d", p->pkg_temp_c);
 
-	if (do_snb_cstates)
+	if (do_pc2)
 		outp += sprintf(outp, "%8.2f", 100.0 * p->pc2/t->tsc);
-	if (do_nhm_cstates && !do_slm_cstates)
+	if (do_pc3)
 		outp += sprintf(outp, "%8.2f", 100.0 * p->pc3/t->tsc);
-	if (do_nhm_cstates && !do_slm_cstates)
+	if (do_pc6)
 		outp += sprintf(outp, "%8.2f", 100.0 * p->pc6/t->tsc);
-	if (do_snb_cstates)
+	if (do_pc7)
 		outp += sprintf(outp, "%8.2f", 100.0 * p->pc7/t->tsc);
 	if (do_c8_c9_c10) {
 		outp += sprintf(outp, "%8.2f", 100.0 * p->pc8/t->tsc);
@@ -561,7 +570,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
 			outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
-	} else {
+	} else if (do_rapl && rapl_joules) {
 		if (do_rapl & RAPL_PKG)
 			outp += sprintf(outp, fmt8,
 					p->energy_pkg * rapl_energy_units);
@@ -578,8 +587,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
 			outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
-	outp += sprintf(outp, fmt8, interval_float);
 
+		outp += sprintf(outp, fmt8, interval_float);
 	}
 done:
 	outp += sprintf(outp, "\n");
@@ -628,9 +637,12 @@ void
 delta_package(struct pkg_data *new, struct pkg_data *old)
 {
 	old->pc2 = new->pc2 - old->pc2;
-	old->pc3 = new->pc3 - old->pc3;
-	old->pc6 = new->pc6 - old->pc6;
-	old->pc7 = new->pc7 - old->pc7;
+	if (do_pc3)
+		old->pc3 = new->pc3 - old->pc3;
+	if (do_pc6)
+		old->pc6 = new->pc6 - old->pc6;
+	if (do_pc7)
+		old->pc7 = new->pc7 - old->pc7;
 	old->pc8 = new->pc8 - old->pc8;
 	old->pc9 = new->pc9 - old->pc9;
 	old->pc10 = new->pc10 - old->pc10;
@@ -670,24 +682,26 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 
 	old->c1 = new->c1 - old->c1;
 
-	if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) {
-		old->aperf = new->aperf - old->aperf;
-		old->mperf = new->mperf - old->mperf;
-	} else {
+	if (has_aperf) {
+		if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) {
+			old->aperf = new->aperf - old->aperf;
+			old->mperf = new->mperf - old->mperf;
+		} else {
 
-		if (!aperf_mperf_unstable) {
-			fprintf(stderr, "%s: APERF or MPERF went backwards *\n", progname);
-			fprintf(stderr, "* Frequency results do not cover entire interval *\n");
-			fprintf(stderr, "* fix this by running Linux-2.6.30 or later *\n");
+			if (!aperf_mperf_unstable) {
+				fprintf(stderr, "%s: APERF or MPERF went backwards *\n", progname);
+				fprintf(stderr, "* Frequency results do not cover entire interval *\n");
+				fprintf(stderr, "* fix this by running Linux-2.6.30 or later *\n");
 
-			aperf_mperf_unstable = 1;
+				aperf_mperf_unstable = 1;
+			}
+			/*
+			 * mperf delta is likely a huge "positive" number
+			 * can not use it for calculating c0 time
+			 */
+			skip_c0 = 1;
+			skip_c1 = 1;
 		}
-		/*
-		 * mperf delta is likely a huge "positive" number
-		 * can not use it for calculating c0 time
-		 */
-		skip_c0 = 1;
-		skip_c1 = 1;
 	}
 
 
@@ -712,7 +726,7 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 	}
 
 	if (old->mperf == 0) {
-		if (verbose > 1) fprintf(stderr, "cpu%d MPERF 0!\n", old->cpu_id);
+		if (debug > 1) fprintf(stderr, "cpu%d MPERF 0!\n", old->cpu_id);
 		old->mperf = 1;	/* divide by 0 protection */
 	}
 
@@ -769,9 +783,12 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	c->core_temp_c = 0;
 
 	p->pc2 = 0;
-	p->pc3 = 0;
-	p->pc6 = 0;
-	p->pc7 = 0;
+	if (do_pc3)
+		p->pc3 = 0;
+	if (do_pc6)
+		p->pc6 = 0;
+	if (do_pc7)
+		p->pc7 = 0;
 	p->pc8 = 0;
 	p->pc9 = 0;
 	p->pc10 = 0;
@@ -810,9 +827,12 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 		return 0;
 
 	average.packages.pc2 += p->pc2;
-	average.packages.pc3 += p->pc3;
-	average.packages.pc6 += p->pc6;
-	average.packages.pc7 += p->pc7;
+	if (do_pc3)
+		average.packages.pc3 += p->pc3;
+	if (do_pc6)
+		average.packages.pc6 += p->pc6;
+	if (do_pc7)
+		average.packages.pc7 += p->pc7;
 	average.packages.pc8 += p->pc8;
 	average.packages.pc9 += p->pc9;
 	average.packages.pc10 += p->pc10;
@@ -854,9 +874,12 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	average.cores.c7 /= topo.num_cores;
 
 	average.packages.pc2 /= topo.num_packages;
-	average.packages.pc3 /= topo.num_packages;
-	average.packages.pc6 /= topo.num_packages;
-	average.packages.pc7 /= topo.num_packages;
+	if (do_pc3)
+		average.packages.pc3 /= topo.num_packages;
+	if (do_pc6)
+		average.packages.pc6 /= topo.num_packages;
+	if (do_pc7)
+		average.packages.pc7 /= topo.num_packages;
 
 	average.packages.pc8 /= topo.num_packages;
 	average.packages.pc9 /= topo.num_packages;
@@ -956,18 +979,18 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		return 0;
 
-	if (do_nhm_cstates && !do_slm_cstates) {
+	if (do_pc3)
 		if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3))
 			return -9;
+	if (do_pc6)
 		if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6))
 			return -10;
-	}
-	if (do_snb_cstates) {
+	if (do_pc2)
 		if (get_msr(cpu, MSR_PKG_C2_RESIDENCY, &p->pc2))
 			return -11;
+	if (do_pc7)
 		if (get_msr(cpu, MSR_PKG_C7_RESIDENCY, &p->pc7))
 			return -12;
-	}
 	if (do_c8_c9_c10) {
 		if (get_msr(cpu, MSR_PKG_C8_RESIDENCY, &p->pc8))
 			return -13;
@@ -1014,12 +1037,43 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	return 0;
 }
 
+/*
+ * MSR_PKG_CST_CONFIG_CONTROL decoding for pkg_cstate_limit:
+ * If you change the values, note they are used both in comparisons
+ * (>= PCL__7) and to index pkg_cstate_limit_strings[].
+ */
+
+#define PCLUKN 0 /* Unknown */
+#define PCLRSV 1 /* Reserved */
+#define PCL__0 2 /* PC0 */
+#define PCL__1 3 /* PC1 */
+#define PCL__2 4 /* PC2 */
+#define PCL__3 5 /* PC3 */
+#define PCL__4 6 /* PC4 */
+#define PCL__6 7 /* PC6 */
+#define PCL_6N 8 /* PC6 No Retention */
+#define PCL_6R 9 /* PC6 Retention */
+#define PCL__7 10 /* PC7 */
+#define PCL_7S 11 /* PC7 Shrink */
+#define PCLUNL 12 /* Unlimited */
+
+int pkg_cstate_limit = PCLUKN;
+char *pkg_cstate_limit_strings[] = { "reserved", "unknown", "pc0", "pc1", "pc2",
+	"pc3", "pc4", "pc6", "pc6n", "pc6r", "pc7", "pc7s", "unlimited"};
+
+int nhm_pkg_cstate_limits[8] = {PCL__0, PCL__1, PCL__3, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLUNL};
+int snb_pkg_cstate_limits[8] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCL__7, PCL_7S, PCLRSV, PCLUNL};
+int hsw_pkg_cstate_limits[8] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S, PCLRSV, PCLUNL};
+int slv_pkg_cstate_limits[8] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7};
+int amt_pkg_cstate_limits[8] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7};
+int phi_pkg_cstate_limits[8] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL};
+
 void print_verbose_header(void)
 {
 	unsigned long long msr;
 	unsigned int ratio;
 
-	if (!do_nehalem_platform_info)
+	if (!do_nhm_platform_info)
 		return;
 
 	get_msr(0, MSR_NHM_PLATFORM_INFO, &msr);
@@ -1093,46 +1147,16 @@ print_nhm_turbo_ratio_limits:
 
 	fprintf(stderr, "cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", msr);
 
-	fprintf(stderr, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: ",
+	fprintf(stderr, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
 		(msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
 		(msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "",
 		(msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "",
 		(msr & NHM_C1_AUTO_DEMOTE) ? "demote-C1, " : "",
 		(msr & (1 << 15)) ? "" : "UN",
-		(unsigned int)msr & 7);
-
-
-	switch(msr & 0x7) {
-	case 0:
-		fprintf(stderr, do_slm_cstates ? "no pkg states" : "pc0");
-		break;
-	case 1:
-		fprintf(stderr, do_slm_cstates ? "no pkg states" : do_snb_cstates ? "pc2" : "pc0");
-		break;
-	case 2:
-		fprintf(stderr, do_slm_cstates ? "invalid" : do_snb_cstates ? "pc6-noret" : "pc3");
-		break;
-	case 3:
-		fprintf(stderr, do_slm_cstates ? "invalid" : "pc6");
-		break;
-	case 4:
-		fprintf(stderr, do_slm_cstates ? "pc4" : "pc7");
-		break;
-	case 5:
-		fprintf(stderr, do_slm_cstates ? "invalid" : do_snb_cstates ? "pc7s" : "invalid");
-		break;
-	case 6:
-		fprintf(stderr, do_slm_cstates ? "pc6" : "invalid");
-		break;
-	case 7:
-		fprintf(stderr, do_slm_cstates ? "pc7" : "unlimited");
-		break;
-	default:
-		fprintf(stderr, "invalid");
-	}
-	fprintf(stderr, ")\n");
+		(unsigned int)msr & 7,
+		pkg_cstate_limit_strings[pkg_cstate_limit]);
 
-	if (!do_nehalem_turbo_ratio_limit)
+	if (!do_nhm_turbo_ratio_limit)
 		return;
 
 	get_msr(0, MSR_NHM_TURBO_RATIO_LIMIT, &msr);
@@ -1178,6 +1202,7 @@ print_nhm_turbo_ratio_limits:
 	if (ratio)
 		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 1 active cores\n",
 			ratio, bclk, ratio * bclk);
+
 }
 
 void free_all_buffers(void)
@@ -1458,18 +1483,66 @@ void check_dev_msr()
 	struct stat sb;
 
 	if (stat("/dev/cpu/0/msr", &sb))
-		err(-5, "no /dev/cpu/0/msr\n"
-		    "Try \"# modprobe msr\"");
+		err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
 }
 
-void check_super_user()
+void check_permissions()
 {
-	if (getuid() != 0)
-		errx(-6, "must be root");
+	struct __user_cap_header_struct cap_header_data;
+	cap_user_header_t cap_header = &cap_header_data;
+	struct __user_cap_data_struct cap_data_data;
+	cap_user_data_t cap_data = &cap_data_data;
+	extern int capget(cap_user_header_t hdrp, cap_user_data_t datap);
+	int do_exit = 0;
+
+	/* check for CAP_SYS_RAWIO */
+	cap_header->pid = getpid();
+	cap_header->version = _LINUX_CAPABILITY_VERSION;
+	if (capget(cap_header, cap_data) < 0)
+		err(-6, "capget(2) failed");
+
+	if ((cap_data->effective & (1 << CAP_SYS_RAWIO)) == 0) {
+		do_exit++;
+		warnx("capget(CAP_SYS_RAWIO) failed,"
+			" try \"# setcap cap_sys_rawio=ep %s\"", progname);
+	}
+
+	/* test file permissions */
+	if (euidaccess("/dev/cpu/0/msr", R_OK)) {
+		do_exit++;
+		warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr");
+	}
+
+	/* if all else fails, thell them to be root */
+	if (do_exit)
+		if (getuid() != 0)
+			warnx("... or simply run as root");
+
+	if (do_exit)
+		exit(-6);
 }
 
-int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model)
+/*
+ * NHM adds support for additional MSRs:
+ *
+ * MSR_SMI_COUNT                   0x00000034
+ *
+ * MSR_NHM_PLATFORM_INFO           0x000000ce
+ * MSR_NHM_SNB_PKG_CST_CFG_CTL     0x000000e2
+ *
+ * MSR_PKG_C3_RESIDENCY            0x000003f8
+ * MSR_PKG_C6_RESIDENCY            0x000003f9
+ * MSR_CORE_C3_RESIDENCY           0x000003fc
+ * MSR_CORE_C6_RESIDENCY           0x000003fd
+ *
+ * Side effect:
+ * sets global pkg_cstate_limit to decode MSR_NHM_SNB_PKG_CST_CFG_CTL
+ */
+int probe_nhm_msrs(unsigned int family, unsigned int model)
 {
+	unsigned long long msr;
+	int *pkg_cstate_limits;
+
 	if (!genuine_intel)
 		return 0;
 
@@ -1482,24 +1555,54 @@ int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model)
 	case 0x1F:	/* Core i7 and i5 Processor - Nehalem */
 	case 0x25:	/* Westmere Client - Clarkdale, Arrandale */
 	case 0x2C:	/* Westmere EP - Gulftown */
+	case 0x2E:	/* Nehalem-EX Xeon - Beckton */
+	case 0x2F:	/* Westmere-EX Xeon - Eagleton */
+		pkg_cstate_limits = nhm_pkg_cstate_limits;
+		break;
 	case 0x2A:	/* SNB */
 	case 0x2D:	/* SNB Xeon */
 	case 0x3A:	/* IVB */
 	case 0x3E:	/* IVB Xeon */
+		pkg_cstate_limits = snb_pkg_cstate_limits;
+		break;
 	case 0x3C:	/* HSW */
 	case 0x3F:	/* HSX */
 	case 0x45:	/* HSW */
 	case 0x46:	/* HSW */
-	case 0x37:	/* BYT */
-	case 0x4D:	/* AVN */
 	case 0x3D:	/* BDW */
+	case 0x47:	/* BDW */
 	case 0x4F:	/* BDX */
 	case 0x56:	/* BDX-DE */
-		return 1;
+		pkg_cstate_limits = hsw_pkg_cstate_limits;
+		break;
+	case 0x37:	/* BYT */
+	case 0x4D:	/* AVN */
+		pkg_cstate_limits = slv_pkg_cstate_limits;
+		break;
+	case 0x4C:	/* AMT */
+		pkg_cstate_limits = amt_pkg_cstate_limits;
+		break;
+	case 0x57:	/* PHI */
+		pkg_cstate_limits = phi_pkg_cstate_limits;
+		break;
+	default:
+		return 0;
+	}
+	get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+
+	pkg_cstate_limit = pkg_cstate_limits[msr & 0x7];
+
+	return 1;
+}
+int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
+{
+	switch (model) {
+	/* Nehalem compatible, but do not include turbo-ratio limit support */
 	case 0x2E:	/* Nehalem-EX Xeon - Beckton */
 	case 0x2F:	/* Westmere-EX Xeon - Eagleton */
-	default:
 		return 0;
+	default:
+		return 1;
 	}
 }
 int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model)
@@ -1564,6 +1667,103 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	return 0;
 }
 
+/*
+ * print_perf_limit()
+ */
+int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	unsigned long long msr;
+	int cpu;
+
+	cpu = t->cpu_id;
+
+	/* per-package */
+	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+		return 0;
+
+	if (cpu_migrate(cpu)) {
+		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		return -1;
+	}
+
+	if (do_core_perf_limit_reasons) {
+		get_msr(cpu, MSR_CORE_PERF_LIMIT_REASONS, &msr);
+		fprintf(stderr, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
+		fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)",
+			(msr & 1 << 0) ? "PROCHOT, " : "",
+			(msr & 1 << 1) ? "ThermStatus, " : "",
+			(msr & 1 << 2) ? "bit2, " : "",
+			(msr & 1 << 4) ? "Graphics, " : "",
+			(msr & 1 << 5) ? "Auto-HWP, " : "",
+			(msr & 1 << 6) ? "VR-Therm, " : "",
+			(msr & 1 << 8) ? "Amps, " : "",
+			(msr & 1 << 9) ? "CorePwr, " : "",
+			(msr & 1 << 10) ? "PkgPwrL1, " : "",
+			(msr & 1 << 11) ? "PkgPwrL2, " : "",
+			(msr & 1 << 12) ? "MultiCoreTurbo, " : "",
+			(msr & 1 << 13) ? "Transitions, " : "",
+			(msr & 1 << 14) ? "bit14, " : "",
+			(msr & 1 << 15) ? "bit15, " : "");
+		fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)\n",
+			(msr & 1 << 16) ? "PROCHOT, " : "",
+			(msr & 1 << 17) ? "ThermStatus, " : "",
+			(msr & 1 << 18) ? "bit18, " : "",
+			(msr & 1 << 20) ? "Graphics, " : "",
+			(msr & 1 << 21) ? "Auto-HWP, " : "",
+			(msr & 1 << 22) ? "VR-Therm, " : "",
+			(msr & 1 << 24) ? "Amps, " : "",
+			(msr & 1 << 25) ? "CorePwr, " : "",
+			(msr & 1 << 26) ? "PkgPwrL1, " : "",
+			(msr & 1 << 27) ? "PkgPwrL2, " : "",
+			(msr & 1 << 28) ? "MultiCoreTurbo, " : "",
+			(msr & 1 << 29) ? "Transitions, " : "",
+			(msr & 1 << 30) ? "bit30, " : "",
+			(msr & 1 << 31) ? "bit31, " : "");
+
+	}
+	if (do_gfx_perf_limit_reasons) {
+		get_msr(cpu, MSR_GFX_PERF_LIMIT_REASONS, &msr);
+		fprintf(stderr, "cpu%d: MSR_GFX_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
+		fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s)",
+			(msr & 1 << 0) ? "PROCHOT, " : "",
+			(msr & 1 << 1) ? "ThermStatus, " : "",
+			(msr & 1 << 4) ? "Graphics, " : "",
+			(msr & 1 << 6) ? "VR-Therm, " : "",
+			(msr & 1 << 8) ? "Amps, " : "",
+			(msr & 1 << 9) ? "GFXPwr, " : "",
+			(msr & 1 << 10) ? "PkgPwrL1, " : "",
+			(msr & 1 << 11) ? "PkgPwrL2, " : "");
+		fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s)\n",
+			(msr & 1 << 16) ? "PROCHOT, " : "",
+			(msr & 1 << 17) ? "ThermStatus, " : "",
+			(msr & 1 << 20) ? "Graphics, " : "",
+			(msr & 1 << 22) ? "VR-Therm, " : "",
+			(msr & 1 << 24) ? "Amps, " : "",
+			(msr & 1 << 25) ? "GFXPwr, " : "",
+			(msr & 1 << 26) ? "PkgPwrL1, " : "",
+			(msr & 1 << 27) ? "PkgPwrL2, " : "");
+	}
+	if (do_ring_perf_limit_reasons) {
+		get_msr(cpu, MSR_RING_PERF_LIMIT_REASONS, &msr);
+		fprintf(stderr, "cpu%d: MSR_RING_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
+		fprintf(stderr, " (Active: %s%s%s%s%s%s)",
+			(msr & 1 << 0) ? "PROCHOT, " : "",
+			(msr & 1 << 1) ? "ThermStatus, " : "",
+			(msr & 1 << 6) ? "VR-Therm, " : "",
+			(msr & 1 << 8) ? "Amps, " : "",
+			(msr & 1 << 10) ? "PkgPwrL1, " : "",
+			(msr & 1 << 11) ? "PkgPwrL2, " : "");
+		fprintf(stderr, " (Logged: %s%s%s%s%s%s)\n",
+			(msr & 1 << 16) ? "PROCHOT, " : "",
+			(msr & 1 << 17) ? "ThermStatus, " : "",
+			(msr & 1 << 22) ? "VR-Therm, " : "",
+			(msr & 1 << 24) ? "Amps, " : "",
+			(msr & 1 << 26) ? "PkgPwrL1, " : "",
+			(msr & 1 << 27) ? "PkgPwrL2, " : "");
+	}
+	return 0;
+}
+
 #define	RAPL_POWER_GRANULARITY	0x7FFF	/* 15 bit power granularity */
 #define	RAPL_TIME_GRANULARITY	0x3F /* 6 bit time granularity */
 
@@ -1609,6 +1809,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 	case 0x45:	/* HSW */
 	case 0x46:	/* HSW */
 	case 0x3D:	/* BDW */
+	case 0x47:	/* BDW */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
 		break;
 	case 0x3F:	/* HSX */
@@ -1647,12 +1848,33 @@ void rapl_probe(unsigned int family, unsigned int model)
 	tdp = get_tdp(model);
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
-	if (verbose)
+	if (debug)
 		fprintf(stderr, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
 
 	return;
 }
 
+void perf_limit_reasons_probe(family, model)
+{
+	if (!genuine_intel)
+		return;
+
+	if (family != 6)
+		return;
+
+	switch (model) {
+	case 0x3C:	/* HSW */
+	case 0x45:	/* HSW */
+	case 0x46:	/* HSW */
+		do_gfx_perf_limit_reasons = 1;
+	case 0x3F:	/* HSX */
+		do_core_perf_limit_reasons = 1;
+		do_ring_perf_limit_reasons = 1;
+	default:
+		return;
+	}
+}
+
 int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
 	unsigned long long msr;
@@ -1751,7 +1973,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
 		return -1;
 
-	if (verbose) {
+	if (debug) {
 		fprintf(stderr, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx "
 			"(%f Watts, %f Joules, %f sec.)\n", cpu, msr,
 			rapl_power_units, rapl_energy_units, rapl_time_units);
@@ -1808,7 +2030,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		print_power_limit_msr(cpu, msr, "DRAM Limit");
 	}
 	if (do_rapl & RAPL_CORE_POLICY) {
-		if (verbose) {
+		if (debug) {
 			if (get_msr(cpu, MSR_PP0_POLICY, &msr))
 				return -7;
 
@@ -1816,7 +2038,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		}
 	}
 	if (do_rapl & RAPL_CORES) {
-		if (verbose) {
+		if (debug) {
 
 			if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
 				return -9;
@@ -1826,7 +2048,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		}
 	}
 	if (do_rapl & RAPL_GFX) {
-		if (verbose) {
+		if (debug) {
 			if (get_msr(cpu, MSR_PP1_POLICY, &msr))
 				return -8;
 
@@ -1842,8 +2064,15 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	return 0;
 }
 
+/*
+ * SNB adds support for additional MSRs:
+ *
+ * MSR_PKG_C7_RESIDENCY            0x000003fa
+ * MSR_CORE_C7_RESIDENCY           0x000003fe
+ * MSR_PKG_C2_RESIDENCY            0x0000060d
+ */
 
-int is_snb(unsigned int family, unsigned int model)
+int has_snb_msrs(unsigned int family, unsigned int model)
 {
 	if (!genuine_intel)
 		return 0;
@@ -1858,6 +2087,7 @@ int is_snb(unsigned int family, unsigned int model)
 	case 0x45:	/* HSW */
 	case 0x46:	/* HSW */
 	case 0x3D:	/* BDW */
+	case 0x47:	/* BDW */
 	case 0x4F:	/* BDX */
 	case 0x56:	/* BDX-DE */
 		return 1;
@@ -1865,7 +2095,14 @@ int is_snb(unsigned int family, unsigned int model)
 	return 0;
 }
 
-int has_c8_c9_c10(unsigned int family, unsigned int model)
+/*
+ * HSW adds support for additional MSRs:
+ *
+ * MSR_PKG_C8_RESIDENCY            0x00000630
+ * MSR_PKG_C9_RESIDENCY            0x00000631
+ * MSR_PKG_C10_RESIDENCY           0x00000632
+ */
+int has_hsw_msrs(unsigned int family, unsigned int model)
 {
 	if (!genuine_intel)
 		return 0;
@@ -1917,7 +2154,7 @@ double slm_bclk(void)
 
 double discover_bclk(unsigned int family, unsigned int model)
 {
-	if (is_snb(family, model))
+	if (has_snb_msrs(family, model))
 		return 100.00;
 	else if (is_slm(family, model))
 		return slm_bclk();
@@ -1965,7 +2202,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 	}
 
 	/* Temperature Target MSR is Nehalem and newer only */
-	if (!do_nehalem_platform_info)
+	if (!do_nhm_platform_info)
 		goto guess;
 
 	if (get_msr(0, MSR_IA32_TEMPERATURE_TARGET, &msr))
@@ -1973,7 +2210,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 
 	target_c_local = (msr >> 16) & 0xFF;
 
-	if (verbose)
+	if (debug)
 		fprintf(stderr, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
 			cpu, msr, target_c_local);
 
@@ -2003,7 +2240,7 @@ void check_cpuid()
 	if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
 		genuine_intel = 1;
 
-	if (verbose)
+	if (debug)
 		fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
 			(char *)&ebx, (char *)&edx, (char *)&ecx);
 
@@ -2014,7 +2251,7 @@ void check_cpuid()
 	if (family == 6 || family == 0xf)
 		model += ((fms >> 16) & 0xf) << 4;
 
-	if (verbose)
+	if (debug)
 		fprintf(stderr, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
 			max_level, family, model, stepping, family, model, stepping);
 
@@ -2029,18 +2266,15 @@ void check_cpuid()
 	ebx = ecx = edx = 0;
 	__get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx);
 
-	if (max_level < 0x80000007)
-		errx(1, "CPUID: no invariant TSC (max_level 0x%x)", max_level);
+	if (max_level >= 0x80000007) {
 
-	/*
-	 * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8
-	 * this check is valid for both Intel and AMD
-	 */
-	__get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
-	has_invariant_tsc = edx & (1 << 8);
-
-	if (!has_invariant_tsc)
-		errx(1, "No invariant TSC");
+		/*
+		 * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8
+		 * this check is valid for both Intel and AMD
+		 */
+		__get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
+		has_invariant_tsc = edx & (1 << 8);
+	}
 
 	/*
 	 * APERF/MPERF is advertised by CPUID.EAX=0x6: ECX.bit0
@@ -2053,36 +2287,51 @@ void check_cpuid()
 	do_ptm = eax & (1 << 6);
 	has_epb = ecx & (1 << 3);
 
-	if (verbose)
-		fprintf(stderr, "CPUID(6): %s%s%s%s\n",
-			has_aperf ? "APERF" : "No APERF!",
-			do_dts ? ", DTS" : "",
-			do_ptm ? ", PTM": "",
-			has_epb ? ", EPB": "");
-
-	if (!has_aperf)
-		errx(-1, "No APERF");
-
-	do_nehalem_platform_info = genuine_intel && has_invariant_tsc;
-	do_nhm_cstates = genuine_intel;	/* all Intel w/ non-stop TSC have NHM counters */
-	do_smi = do_nhm_cstates;
-	do_snb_cstates = is_snb(family, model);
-	do_c8_c9_c10 = has_c8_c9_c10(family, model);
+	if (debug)
+		fprintf(stderr, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sEPB\n",
+			has_aperf ? "" : "No ",
+			do_dts ? "" : "No ",
+			do_ptm ? "" : "No ",
+			has_epb ? "" : "No ");
+
+	do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model);
+	do_snb_cstates = has_snb_msrs(family, model);
+	do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
+	do_pc3 = (pkg_cstate_limit >= PCL__3);
+	do_pc6 = (pkg_cstate_limit >= PCL__6);
+	do_pc7 = do_snb_cstates && (pkg_cstate_limit >= PCL__7);
+	do_c8_c9_c10 = has_hsw_msrs(family, model);
 	do_slm_cstates = is_slm(family, model);
 	bclk = discover_bclk(family, model);
 
-	do_nehalem_turbo_ratio_limit = has_nehalem_turbo_ratio_limit(family, model);
+	do_nhm_turbo_ratio_limit = do_nhm_platform_info && has_nhm_turbo_ratio_limit(family, model);
 	do_ivt_turbo_ratio_limit = has_ivt_turbo_ratio_limit(family, model);
 	rapl_probe(family, model);
+	perf_limit_reasons_probe(family, model);
 
 	return;
 }
 
 
-void usage()
+void help()
 {
-	errx(1, "%s: [-v][-R][-T][-p|-P|-S][-c MSR#][-C MSR#][-m MSR#][-M MSR#][-i interval_sec | command ...]\n",
-	     progname);
+	fprintf(stderr,
+	"Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n"
+	"\n"
+	"Turbostat forks the specified COMMAND and prints statistics\n"
+	"when COMMAND completes.\n"
+	"If no COMMAND is specified, turbostat wakes every 5-seconds\n"
+	"to print statistics, until interrupted.\n"
+	"--debug	run in \"debug\" mode\n"
+	"--interval sec	Override default 5-second measurement interval\n"
+	"--help		print this help message\n"
+	"--counter msr	print 32-bit counter at address \"msr\"\n"
+	"--Counter msr	print 64-bit Counter at address \"msr\"\n"
+	"--msr msr	print 32-bit value at address \"msr\"\n"
+	"--MSR msr	print 64-bit Value at address \"msr\"\n"
+	"--version	print version information\n"
+	"\n"
+	"For more help, run \"man turbostat\"\n");
 }
 
 
@@ -2121,7 +2370,7 @@ void topology_probe()
 	if (!summary_only && topo.num_cpus > 1)
 		show_cpu = 1;
 
-	if (verbose > 1)
+	if (debug > 1)
 		fprintf(stderr, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num);
 
 	cpus = calloc(1, (topo.max_cpu_num  + 1) * sizeof(struct cpu_topology));
@@ -2156,7 +2405,7 @@ void topology_probe()
 		int siblings;
 
 		if (cpu_is_not_present(i)) {
-			if (verbose > 1)
+			if (debug > 1)
 				fprintf(stderr, "cpu%d NOT PRESENT\n", i);
 			continue;
 		}
@@ -2171,26 +2420,26 @@ void topology_probe()
 		siblings = get_num_ht_siblings(i);
 		if (siblings > max_siblings)
 			max_siblings = siblings;
-		if (verbose > 1)
+		if (debug > 1)
 			fprintf(stderr, "cpu %d pkg %d core %d\n",
 				i, cpus[i].physical_package_id, cpus[i].core_id);
 	}
 	topo.num_cores_per_pkg = max_core_id + 1;
-	if (verbose > 1)
+	if (debug > 1)
 		fprintf(stderr, "max_core_id %d, sizing for %d cores per package\n",
 			max_core_id, topo.num_cores_per_pkg);
 	if (!summary_only && topo.num_cores_per_pkg > 1)
 		show_core = 1;
 
 	topo.num_packages = max_package_id + 1;
-	if (verbose > 1)
+	if (debug > 1)
 		fprintf(stderr, "max_package_id %d, sizing for %d packages\n",
 			max_package_id, topo.num_packages);
 	if (!summary_only && topo.num_packages > 1)
 		show_pkg = 1;
 
 	topo.num_threads_per_core = max_siblings;
-	if (verbose > 1)
+	if (debug > 1)
 		fprintf(stderr, "max_siblings %d\n", max_siblings);
 
 	free(cpus);
@@ -2299,25 +2548,27 @@ void setup_all_buffers(void)
 
 void turbostat_init()
 {
-	check_cpuid();
-
 	check_dev_msr();
-	check_super_user();
+	check_permissions();
+	check_cpuid();
 
 	setup_all_buffers();
 
-	if (verbose)
+	if (debug)
 		print_verbose_header();
 
-	if (verbose)
+	if (debug)
 		for_all_cpus(print_epb, ODD_COUNTERS);
 
-	if (verbose)
+	if (debug)
+		for_all_cpus(print_perf_limit, ODD_COUNTERS);
+
+	if (debug)
 		for_all_cpus(print_rapl, ODD_COUNTERS);
 
 	for_all_cpus(set_temperature_target, ODD_COUNTERS);
 
-	if (verbose)
+	if (debug)
 		for_all_cpus(print_thermal, ODD_COUNTERS);
 }
 
@@ -2382,56 +2633,82 @@ int get_and_dump_counters(void)
 	return status;
 }
 
+void print_version() {
+	fprintf(stderr, "turbostat version 4.1 10-Feb, 2015"
+		" - Len Brown <lenb@kernel.org>\n");
+}
+
 void cmdline(int argc, char **argv)
 {
 	int opt;
+	int option_index = 0;
+	static struct option long_options[] = {
+		{"Counter",	required_argument,	0, 'C'},
+		{"counter",	required_argument,	0, 'c'},
+		{"Dump",	no_argument,		0, 'D'},
+		{"debug",	no_argument,		0, 'd'},
+		{"interval",	required_argument,	0, 'i'},
+		{"help",	no_argument,		0, 'h'},
+		{"Joules",	no_argument,		0, 'J'},
+		{"MSR",		required_argument,	0, 'M'},
+		{"msr",		required_argument,	0, 'm'},
+		{"Package",	no_argument,		0, 'p'},
+		{"processor",	no_argument,		0, 'p'},
+		{"Summary",	no_argument,		0, 'S'},
+		{"TCC",		required_argument,	0, 'T'},
+		{"version",	no_argument,		0, 'v' },
+		{0,		0,			0,  0 }
+	};
 
 	progname = argv[0];
 
-	while ((opt = getopt(argc, argv, "+pPsSvi:c:C:m:M:RJT:")) != -1) {
+	while ((opt = getopt_long_only(argc, argv, "C:c:Ddhi:JM:m:PpST:v",
+				long_options, &option_index)) != -1) {
 		switch (opt) {
-		case 'p':
-			show_core_only++;
+		case 'C':
+			sscanf(optarg, "%x", &extra_delta_offset64);
 			break;
-		case 'P':
-			show_pkg_only++;
+		case 'c':
+			sscanf(optarg, "%x", &extra_delta_offset32);
 			break;
-		case 's':
+		case 'D':
 			dump_only++;
 			break;
-		case 'S':
-			summary_only++;
-			break;
-		case 'v':
-			verbose++;
+		case 'd':
+			debug++;
 			break;
+		case 'h':
+		default:
+			help();
+			exit(1);
 		case 'i':
 			interval_sec = atoi(optarg);
 			break;
-		case 'c':
-			sscanf(optarg, "%x", &extra_delta_offset32);
+		case 'J':
+			rapl_joules++;
 			break;
-		case 'C':
-			sscanf(optarg, "%x", &extra_delta_offset64);
+		case 'M':
+			sscanf(optarg, "%x", &extra_msr_offset64);
 			break;
 		case 'm':
 			sscanf(optarg, "%x", &extra_msr_offset32);
 			break;
-		case 'M':
-			sscanf(optarg, "%x", &extra_msr_offset64);
+		case 'P':
+			show_pkg_only++;
 			break;
-		case 'R':
-			rapl_verbose++;
+		case 'p':
+			show_core_only++;
+			break;
+		case 'S':
+			summary_only++;
 			break;
 		case 'T':
 			tcc_activation_temp_override = atoi(optarg);
 			break;
-		case 'J':
-			rapl_joules++;
+		case 'v':
+			print_version();
+			exit(0);
 			break;
-
-		default:
-			usage();
 		}
 	}
 }
@@ -2440,9 +2717,8 @@ int main(int argc, char **argv)
 {
 	cmdline(argc, argv);
 
-	if (verbose)
-		fprintf(stderr, "turbostat v3.7 Feb 6, 2014"
-			" - Len Brown <lenb@kernel.org>\n");
+	if (debug)
+		print_version();
 
 	turbostat_init();
 
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index b9cd036f0442..d08e214ec6e7 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -178,6 +178,7 @@ my $checkout;
 my $localversion;
 my $iteration = 0;
 my $successes = 0;
+my $stty_orig;
 
 my $bisect_good;
 my $bisect_bad;
@@ -197,6 +198,11 @@ my $patchcheck_start;
 my $patchcheck_cherry;
 my $patchcheck_end;
 
+my $build_time;
+my $install_time;
+my $reboot_time;
+my $test_time;
+
 # set when a test is something other that just building or install
 # which would require more options.
 my $buildonly = 1;
@@ -554,6 +560,66 @@ sub get_mandatory_config {
     }
 }
 
+sub show_time {
+    my ($time) = @_;
+
+    my $hours = 0;
+    my $minutes = 0;
+
+    if ($time > 3600) {
+	$hours = int($time / 3600);
+	$time -= $hours * 3600;
+    }
+    if ($time > 60) {
+	$minutes = int($time / 60);
+	$time -= $minutes * 60;
+    }
+
+    if ($hours > 0) {
+	doprint "$hours hour";
+	doprint "s" if ($hours > 1);
+	doprint " ";
+    }
+
+    if ($minutes > 0) {
+	doprint "$minutes minute";
+	doprint "s" if ($minutes > 1);
+	doprint " ";
+    }
+
+    doprint "$time second";
+    doprint "s" if ($time != 1);
+}
+
+sub print_times {
+    doprint "\n";
+    if ($build_time) {
+	doprint "Build time:   ";
+	show_time($build_time);
+	doprint "\n";
+    }
+    if ($install_time) {
+	doprint "Install time: ";
+	show_time($install_time);
+	doprint "\n";
+    }
+    if ($reboot_time) {
+	doprint "Reboot time:  ";
+	show_time($reboot_time);
+	doprint "\n";
+    }
+    if ($test_time) {
+	doprint "Test time:    ";
+	show_time($test_time);
+	doprint "\n";
+    }
+    # reset for iterations like bisect
+    $build_time = 0;
+    $install_time = 0;
+    $reboot_time = 0;
+    $test_time = 0;
+}
+
 sub get_mandatory_configs {
     get_mandatory_config("MACHINE");
     get_mandatory_config("BUILD_DIR");
@@ -1341,23 +1407,83 @@ sub dodie {
 	print " See $opt{LOG_FILE} for more info.\n";
     }
 
+    if ($monitor_cnt) {
+	    # restore terminal settings
+	    system("stty $stty_orig");
+    }
+
     die @_, "\n";
 }
 
+sub create_pty {
+    my ($ptm, $pts) = @_;
+    my $tmp;
+    my $TIOCSPTLCK = 0x40045431;
+    my $TIOCGPTN = 0x80045430;
+
+    sysopen($ptm, "/dev/ptmx", O_RDWR | O_NONBLOCK) or
+	dodie "Cant open /dev/ptmx";
+
+    # unlockpt()
+    $tmp = pack("i", 0);
+    ioctl($ptm, $TIOCSPTLCK, $tmp) or
+	dodie "ioctl TIOCSPTLCK for /dev/ptmx failed";
+
+    # ptsname()
+    ioctl($ptm, $TIOCGPTN, $tmp) or
+	dodie "ioctl TIOCGPTN for /dev/ptmx failed";
+    $tmp = unpack("i", $tmp);
+
+    sysopen($pts, "/dev/pts/$tmp", O_RDWR | O_NONBLOCK) or
+	dodie "Can't open /dev/pts/$tmp";
+}
+
+sub exec_console {
+    my ($ptm, $pts) = @_;
+
+    close($ptm);
+
+    close(\*STDIN);
+    close(\*STDOUT);
+    close(\*STDERR);
+
+    open(\*STDIN, '<&', $pts);
+    open(\*STDOUT, '>&', $pts);
+    open(\*STDERR, '>&', $pts);
+
+    close($pts);
+
+    exec $console or
+	die "Can't open console $console";
+}
+
 sub open_console {
-    my ($fp) = @_;
+    my ($ptm) = @_;
+    my $pts = \*PTSFD;
+    my $pid;
 
-    my $flags;
+    # save terminal settings
+    $stty_orig = `stty -g`;
 
-    my $pid = open($fp, "$console|") or
-	dodie "Can't open console $console";
+    # place terminal in cbreak mode so that stdin can be read one character at
+    # a time without having to wait for a newline
+    system("stty -icanon -echo -icrnl");
 
-    $flags = fcntl($fp, F_GETFL, 0) or
-	dodie "Can't get flags for the socket: $!";
-    $flags = fcntl($fp, F_SETFL, $flags | O_NONBLOCK) or
-	dodie "Can't set flags for the socket: $!";
+    create_pty($ptm, $pts);
+
+    $pid = fork;
+
+    if (!$pid) {
+	# child
+	exec_console($ptm, $pts)
+    }
+
+    # parent
+    close($pts);
 
     return $pid;
+
+    open(PTSFD, "Stop perl from warning about single use of PTSFD");
 }
 
 sub close_console {
@@ -1368,6 +1494,9 @@ sub close_console {
 
     print "closing!\n";
     close($fp);
+
+    # restore terminal settings
+    system("stty $stty_orig");
 }
 
 sub start_monitor {
@@ -1519,6 +1648,8 @@ sub fail {
 	    $name = " ($test_name)";
 	}
 
+	print_times;
+
 	doprint "%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n";
 	doprint "%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n";
 	doprint "KTEST RESULT: TEST $i$name Failed: ", @_, "\n";
@@ -1534,10 +1665,14 @@ sub fail {
 
 sub run_command {
     my ($command, $redirect) = @_;
+    my $start_time;
+    my $end_time;
     my $dolog = 0;
     my $dord = 0;
     my $pid;
 
+    $start_time = time;
+
     $command =~ s/\$SSH_USER/$ssh_user/g;
     $command =~ s/\$MACHINE/$machine/g;
 
@@ -1570,6 +1705,15 @@ sub run_command {
     close(LOG) if ($dolog);
     close(RD)  if ($dord);
 
+    $end_time = time;
+    my $delta = $end_time - $start_time;
+
+    if ($delta == 1) {
+	doprint "[1 second] ";
+    } else {
+	doprint "[$delta seconds] ";
+    }
+
     if ($failed) {
 	doprint "FAILED!\n";
     } else {
@@ -1694,7 +1838,9 @@ sub wait_for_input
 {
     my ($fp, $time) = @_;
     my $rin;
-    my $ready;
+    my $rout;
+    my $nr;
+    my $buf;
     my $line;
     my $ch;
 
@@ -1704,21 +1850,36 @@ sub wait_for_input
 
     $rin = '';
     vec($rin, fileno($fp), 1) = 1;
-    ($ready, $time) = select($rin, undef, undef, $time);
+    vec($rin, fileno(\*STDIN), 1) = 1;
 
-    $line = "";
+    while (1) {
+	$nr = select($rout=$rin, undef, undef, $time);
 
-    # try to read one char at a time
-    while (sysread $fp, $ch, 1) {
-	$line .= $ch;
-	last if ($ch eq "\n");
-    }
+	if ($nr <= 0) {
+	    return undef;
+	}
 
-    if (!length($line)) {
-	return undef;
-    }
+	# copy data from stdin to the console
+	if (vec($rout, fileno(\*STDIN), 1) == 1) {
+	    sysread(\*STDIN, $buf, 1000);
+	    syswrite($fp, $buf, 1000);
+	    next;
+	}
 
-    return $line;
+	$line = "";
+
+	# try to read one char at a time
+	while (sysread $fp, $ch, 1) {
+	    $line .= $ch;
+	    last if ($ch eq "\n");
+	}
+
+	if (!length($line)) {
+	    return undef;
+	}
+
+	return $line;
+    }
 }
 
 sub reboot_to {
@@ -1766,6 +1927,8 @@ sub monitor {
     my $skip_call_trace = 0;
     my $loops;
 
+    my $start_time = time;
+
     wait_for_monitor 5;
 
     my $line;
@@ -1890,6 +2053,9 @@ sub monitor {
 	}
     }
 
+    my $end_time = time;
+    $reboot_time = $end_time - $start_time;
+
     close(DMESG);
 
     if ($bug) {
@@ -1938,6 +2104,8 @@ sub install {
 
     return if ($no_install);
 
+    my $start_time = time;
+
     if (defined($pre_install)) {
 	my $cp_pre_install = eval_kernel_version $pre_install;
 	run_command "$cp_pre_install" or
@@ -1969,6 +2137,8 @@ sub install {
     if (!$install_mods) {
 	do_post_install;
 	doprint "No modules needed\n";
+	my $end_time = time;
+	$install_time = $end_time - $start_time;
 	return;
     }
 
@@ -1996,6 +2166,9 @@ sub install {
     run_ssh "rm -f /tmp/$modtar";
 
     do_post_install;
+
+    my $end_time = time;
+    $install_time = $end_time - $start_time;
 }
 
 sub get_version {
@@ -2008,7 +2181,7 @@ sub get_version {
     $have_version = 1;
 }
 
-sub start_monitor_and_boot {
+sub start_monitor_and_install {
     # Make sure the stable kernel has finished booting
 
     # Install bisects, don't need console
@@ -2208,6 +2381,8 @@ sub build {
 
     unlink $buildlog;
 
+    my $start_time = time;
+
     # Failed builds should not reboot the target
     my $save_no_reboot = $no_reboot;
     $no_reboot = 1;
@@ -2293,6 +2468,9 @@ sub build {
 
     $no_reboot = $save_no_reboot;
 
+    my $end_time = time;
+    $build_time = $end_time - $start_time;
+
     return 1;
 }
 
@@ -2323,6 +2501,8 @@ sub success {
 	$name = " ($test_name)";
     }
 
+    print_times;
+
     doprint "\n\n*******************************************\n";
     doprint     "*******************************************\n";
     doprint     "KTEST RESULT: TEST $i$name SUCCESS!!!!         **\n";
@@ -2383,6 +2563,8 @@ sub do_run_test {
     my $bug = 0;
     my $bug_ignored = 0;
 
+    my $start_time = time;
+
     wait_for_monitor 1;
 
     doprint "run test $run_test\n";
@@ -2449,6 +2631,9 @@ sub do_run_test {
     waitpid $child_pid, 0;
     $child_exit = $?;
 
+    my $end_time = time;
+    $test_time = $end_time - $start_time;
+
     if (!$bug && $in_bisect) {
 	if (defined($bisect_ret_good)) {
 	    if ($child_exit == $bisect_ret_good) {
@@ -2549,7 +2734,7 @@ sub run_bisect_test {
 	dodie "Failed on build" if $failed;
 
 	# Now boot the box
-	start_monitor_and_boot or $failed = 1;
+	start_monitor_and_install or $failed = 1;
 
 	if ($type ne "boot") {
 	    if ($failed && $bisect_skip) {
@@ -2755,6 +2940,7 @@ sub bisect {
     do {
 	$result = run_bisect $type;
 	$test = run_git_bisect "git bisect $result";
+	print_times;
     } while ($test);
 
     run_command "git bisect log" or
@@ -3168,6 +3354,7 @@ sub config_bisect {
 
     do {
 	$ret = run_config_bisect \%good_configs, \%bad_configs;
+	print_times;
     } while (!$ret);
 
     return $ret if ($ret < 0);
@@ -3260,7 +3447,7 @@ sub patchcheck {
 	my $sha1 = $item;
 	$sha1 =~ s/^([[:xdigit:]]+).*/$1/;
 
-	doprint "\nProcessing commit $item\n\n";
+	doprint "\nProcessing commit \"$item\"\n\n";
 
 	run_command "git checkout $sha1" or
 	    die "Failed to checkout $sha1";
@@ -3291,16 +3478,18 @@ sub patchcheck {
 
 	my $failed = 0;
 
-	start_monitor_and_boot or $failed = 1;
+	start_monitor_and_install or $failed = 1;
 
 	if (!$failed && $type ne "boot"){
 	    do_run_test or $failed = 1;
 	}
 	end_monitor;
-	return 0 if ($failed);
-
+	if ($failed) {
+	    print_times;
+	    return 0;
+	}
 	patchcheck_reboot;
-
+	print_times;
     }
     $in_patchcheck = 0;
     success $i;
@@ -3753,7 +3942,7 @@ sub make_min_config {
 	my $failed = 0;
 	build "oldconfig" or $failed = 1;
 	if (!$failed) {
-		start_monitor_and_boot or $failed = 1;
+		start_monitor_and_install or $failed = 1;
 
 		if ($type eq "test" && !$failed) {
 		    do_run_test or $failed = 1;
@@ -4000,6 +4189,11 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
 
     $iteration = $i;
 
+    $build_time = 0;
+    $install_time = 0;
+    $reboot_time = 0;
+    $test_time = 0;
+
     undef %force_config;
 
     my $makecmd = set_test_option("MAKE_CMD", $i);
@@ -4157,15 +4351,20 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
 
     if ($test_type ne "build") {
 	my $failed = 0;
-	start_monitor_and_boot or $failed = 1;
+	start_monitor_and_install or $failed = 1;
 
 	if (!$failed && $test_type ne "boot" && defined($run_test)) {
 	    do_run_test or $failed = 1;
 	}
 	end_monitor;
-	next if ($failed);
+	if ($failed) {
+	    print_times;
+	    next;
+	}
     }
 
+    print_times;
+
     success $i;
 }
 
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index f6ff90a76bd7..1d5e7ad2c460 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -13,7 +13,7 @@ CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CUR
 
 export CC CFLAGS
 
-TARGETS = pmu copyloops mm tm primitives
+TARGETS = pmu copyloops mm tm primitives stringloops
 
 endif
 
diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore
new file mode 100644
index 000000000000..25a192f62c4d
--- /dev/null
+++ b/tools/testing/selftests/powerpc/copyloops/.gitignore
@@ -0,0 +1,4 @@
+copyuser_64
+copyuser_power7
+memcpy_64
+memcpy_power7
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
new file mode 100644
index 000000000000..b43ade0ec861
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -0,0 +1,3 @@
+hugetlb_vs_thp_test
+subpage_prot
+tempfile
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index 357ccbd6bad9..a14c538dd7f8 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -1,9 +1,9 @@
 noarg:
 	$(MAKE) -C ../
 
-PROGS := hugetlb_vs_thp_test
+PROGS := hugetlb_vs_thp_test subpage_prot
 
-all: $(PROGS)
+all: $(PROGS) tempfile
 
 $(PROGS): ../harness.c
 
@@ -12,7 +12,10 @@ run_tests: all
 		./$$PROG; \
 	done;
 
+tempfile:
+	dd if=/dev/zero of=tempfile bs=64k count=1
+
 clean:
-	rm -f $(PROGS)
+	rm -f $(PROGS) tempfile
 
 .PHONY: all run_tests clean
diff --git a/tools/testing/selftests/powerpc/mm/subpage_prot.c b/tools/testing/selftests/powerpc/mm/subpage_prot.c
new file mode 100644
index 000000000000..440180ff8089
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/subpage_prot.c
@@ -0,0 +1,220 @@
+/*
+ * Copyright IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/ptrace.h>
+#include <sys/syscall.h>
+#include <ucontext.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+char *file_name;
+
+int in_test;
+volatile int faulted;
+volatile void *dar;
+int errors;
+
+static void segv(int signum, siginfo_t *info, void *ctxt_v)
+{
+	ucontext_t *ctxt = (ucontext_t *)ctxt_v;
+	struct pt_regs *regs = ctxt->uc_mcontext.regs;
+
+	if (!in_test) {
+		fprintf(stderr, "Segfault outside of test !\n");
+		exit(1);
+	}
+
+	faulted = 1;
+	dar = (void *)regs->dar;
+	regs->nip += 4;
+}
+
+static inline void do_read(const volatile void *addr)
+{
+	int ret;
+
+	asm volatile("lwz %0,0(%1); twi 0,%0,0; isync;\n"
+		     : "=r" (ret) : "r" (addr) : "memory");
+}
+
+static inline void do_write(const volatile void *addr)
+{
+	int val = 0x1234567;
+
+	asm volatile("stw %0,0(%1); sync; \n"
+		     : : "r" (val), "r" (addr) : "memory");
+}
+
+static inline void check_faulted(void *addr, long page, long subpage, int write)
+{
+	int want_fault = (subpage == ((page + 3) % 16));
+
+	if (write)
+		want_fault |= (subpage == ((page + 1) % 16));
+
+	if (faulted != want_fault) {
+		printf("Failed at 0x%p (p=%ld,sp=%ld,w=%d), want=%s, got=%s !\n",
+		       addr, page, subpage, write,
+		       want_fault ? "fault" : "pass",
+		       faulted ? "fault" : "pass");
+		++errors;
+	}
+
+	if (faulted) {
+		if (dar != addr) {
+			printf("Fault expected at 0x%p and happened at 0x%p !\n",
+			       addr, dar);
+		}
+		faulted = 0;
+		asm volatile("sync" : : : "memory");
+	}
+}
+
+static int run_test(void *addr, unsigned long size)
+{
+	unsigned int *map;
+	long i, j, pages, err;
+
+	pages = size / 0x10000;
+	map = malloc(pages * 4);
+	assert(map);
+
+	/*
+	 * for each page, mark subpage i % 16 read only and subpage
+	 * (i + 3) % 16 inaccessible
+	 */
+	for (i = 0; i < pages; i++) {
+		map[i] = (0x40000000 >> (((i + 1) * 2) % 32)) |
+			(0xc0000000 >> (((i + 3) * 2) % 32));
+	}
+
+	err = syscall(__NR_subpage_prot, addr, size, map);
+	if (err) {
+		perror("subpage_perm");
+		return 1;
+	}
+	free(map);
+
+	in_test = 1;
+	errors = 0;
+	for (i = 0; i < pages; i++) {
+		for (j = 0; j < 16; j++, addr += 0x1000) {
+			do_read(addr);
+			check_faulted(addr, i, j, 0);
+			do_write(addr);
+			check_faulted(addr, i, j, 1);
+		}
+	}
+
+	in_test = 0;
+	if (errors) {
+		printf("%d errors detected\n", errors);
+		return 1;
+	}
+
+	return 0;
+}
+
+int test_anon(void)
+{
+	unsigned long align;
+	struct sigaction act = {
+		.sa_sigaction = segv,
+		.sa_flags = SA_SIGINFO
+	};
+	void *mallocblock;
+	unsigned long mallocsize;
+
+	if (getpagesize() != 0x10000) {
+		fprintf(stderr, "Kernel page size must be 64K!\n");
+		return 1;
+	}
+
+	sigaction(SIGSEGV, &act, NULL);
+
+	mallocsize = 4 * 16 * 1024 * 1024;
+
+	FAIL_IF(posix_memalign(&mallocblock, 64 * 1024, mallocsize));
+
+	align = (unsigned long)mallocblock;
+	if (align & 0xffff)
+		align = (align | 0xffff) + 1;
+
+	mallocblock = (void *)align;
+
+	printf("allocated malloc block of 0x%lx bytes at 0x%p\n",
+	       mallocsize, mallocblock);
+
+	printf("testing malloc block...\n");
+
+	return run_test(mallocblock, mallocsize);
+}
+
+int test_file(void)
+{
+	struct sigaction act = {
+		.sa_sigaction = segv,
+		.sa_flags = SA_SIGINFO
+	};
+	void *fileblock;
+	off_t filesize;
+	int fd;
+
+	fd = open(file_name, O_RDWR);
+	if (fd == -1) {
+		perror("failed to open file");
+		return 1;
+	}
+	sigaction(SIGSEGV, &act, NULL);
+
+	filesize = lseek(fd, 0, SEEK_END);
+	if (filesize & 0xffff)
+		filesize &= ~0xfffful;
+
+	fileblock = mmap(NULL, filesize, PROT_READ | PROT_WRITE,
+			 MAP_SHARED, fd, 0);
+	if (fileblock == MAP_FAILED) {
+		perror("failed to map file");
+		return 1;
+	}
+	printf("allocated %s for 0x%lx bytes at 0x%p\n",
+	       file_name, filesize, fileblock);
+
+	printf("testing file map...\n");
+
+	return run_test(fileblock, filesize);
+}
+
+int main(int argc, char *argv[])
+{
+	test_harness(test_anon, "subpage_prot_anon");
+
+	if (argc > 1)
+		file_name = argv[1];
+	else
+		file_name = "tempfile";
+
+	test_harness(test_file, "subpage_prot_file");
+
+	return 0;
+}
diff --git a/tools/testing/selftests/powerpc/pmu/.gitignore b/tools/testing/selftests/powerpc/pmu/.gitignore
new file mode 100644
index 000000000000..e748f336eed3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/.gitignore
@@ -0,0 +1,3 @@
+count_instructions
+l3_bank_test
+per_event_excludes
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore
new file mode 100644
index 000000000000..42bddbed8b64
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore
@@ -0,0 +1,22 @@
+reg_access_test
+event_attributes_test
+cycles_test
+cycles_with_freeze_test
+pmc56_overflow_test
+ebb_vs_cpu_event_test
+cpu_event_vs_ebb_test
+cpu_event_pinned_vs_ebb_test
+task_event_vs_ebb_test
+task_event_pinned_vs_ebb_test
+multi_ebb_procs_test
+multi_counter_test
+pmae_handling_test
+close_clears_pmcc_test
+instruction_count_test
+fork_cleanup_test
+ebb_on_child_test
+ebb_on_willing_child_test
+back_to_back_ebbs_test
+lost_exception_test
+no_handler_test
+cycles_with_mmcr2_test
diff --git a/tools/testing/selftests/powerpc/primitives/.gitignore b/tools/testing/selftests/powerpc/primitives/.gitignore
new file mode 100644
index 000000000000..4cc4e31bed1d
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/.gitignore
@@ -0,0 +1 @@
+load_unaligned_zeropad
diff --git a/tools/testing/selftests/powerpc/stringloops/.gitignore b/tools/testing/selftests/powerpc/stringloops/.gitignore
new file mode 100644
index 000000000000..0b43da74ee46
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/.gitignore
@@ -0,0 +1 @@
+memcmp
diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
new file mode 100644
index 000000000000..506d77346477
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -0,0 +1,20 @@
+# The loops are all 64-bit code
+CFLAGS += -m64
+CFLAGS += -I$(CURDIR)
+
+PROGS := memcmp
+EXTRA_SOURCES := memcmp_64.S ../harness.c
+
+all: $(PROGS)
+
+$(PROGS): $(EXTRA_SOURCES)
+
+run_tests: all
+	@-for PROG in $(PROGS); do \
+		./$$PROG; \
+	done;
+
+clean:
+	rm -f $(PROGS) *.o
+
+.PHONY: all run_tests clean
diff --git a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
new file mode 100644
index 000000000000..11bece87e880
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
@@ -0,0 +1,7 @@
+#include <ppc-asm.h>
+
+#ifndef r1
+#define r1 sp
+#endif
+
+#define _GLOBAL(A) FUNC_START(test_ ## A)
diff --git a/tools/testing/selftests/powerpc/stringloops/memcmp.c b/tools/testing/selftests/powerpc/stringloops/memcmp.c
new file mode 100644
index 000000000000..17417dd70708
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/memcmp.c
@@ -0,0 +1,103 @@
+#include <malloc.h>
+#include <stdlib.h>
+#include <string.h>
+#include "../utils.h"
+
+#define SIZE 256
+#define ITERATIONS 10000
+
+int test_memcmp(const void *s1, const void *s2, size_t n);
+
+/* test all offsets and lengths */
+static void test_one(char *s1, char *s2)
+{
+	unsigned long offset, size;
+
+	for (offset = 0; offset < SIZE; offset++) {
+		for (size = 0; size < (SIZE-offset); size++) {
+			int x, y;
+			unsigned long i;
+
+			y = memcmp(s1+offset, s2+offset, size);
+			x = test_memcmp(s1+offset, s2+offset, size);
+
+			if (((x ^ y) < 0) &&	/* Trick to compare sign */
+				((x | y) != 0)) { /* check for zero */
+				printf("memcmp returned %d, should have returned %d (offset %ld size %ld)\n", x, y, offset, size);
+
+				for (i = offset; i < offset+size; i++)
+					printf("%02x ", s1[i]);
+				printf("\n");
+
+				for (i = offset; i < offset+size; i++)
+					printf("%02x ", s2[i]);
+				printf("\n");
+				abort();
+			}
+		}
+	}
+}
+
+static int testcase(void)
+{
+	char *s1;
+	char *s2;
+	unsigned long i;
+
+	s1 = memalign(128, SIZE);
+	if (!s1) {
+		perror("memalign");
+		exit(1);
+	}
+
+	s2 = memalign(128, SIZE);
+	if (!s2) {
+		perror("memalign");
+		exit(1);
+	}
+
+	srandom(1);
+
+	for (i = 0; i < ITERATIONS; i++) {
+		unsigned long j;
+		unsigned long change;
+
+		for (j = 0; j < SIZE; j++)
+			s1[j] = random();
+
+		memcpy(s2, s1, SIZE);
+
+		/* change one byte */
+		change = random() % SIZE;
+		s2[change] = random() & 0xff;
+
+		test_one(s1, s2);
+	}
+
+	srandom(1);
+
+	for (i = 0; i < ITERATIONS; i++) {
+		unsigned long j;
+		unsigned long change;
+
+		for (j = 0; j < SIZE; j++)
+			s1[j] = random();
+
+		memcpy(s2, s1, SIZE);
+
+		/* change multiple bytes, 1/8 of total */
+		for (j = 0; j < SIZE / 8; j++) {
+			change = random() % SIZE;
+			s2[change] = random() & 0xff;
+		}
+
+		test_one(s1, s2);
+	}
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(testcase, "memcmp");
+}
diff --git a/tools/testing/selftests/powerpc/stringloops/memcmp_64.S b/tools/testing/selftests/powerpc/stringloops/memcmp_64.S
new file mode 120000
index 000000000000..9bc87e438ae9
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/memcmp_64.S
@@ -0,0 +1 @@
+../../../../../arch/powerpc/lib/memcmp_64.S
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
new file mode 100644
index 000000000000..33d02cc54a3e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -0,0 +1 @@
+tm-resched-dscr
diff --git a/tools/testing/selftests/rcutorture/bin/cpus2use.sh b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
index abe14b7f36e9..bb99cde3f5f9 100755
--- a/tools/testing/selftests/rcutorture/bin/cpus2use.sh
+++ b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
@@ -24,7 +24,7 @@
 
 ncpus=`grep '^processor' /proc/cpuinfo | wc -l`
 idlecpus=`mpstat | tail -1 | \
-	awk -v ncpus=$ncpus '{ print ncpus * ($7 + $12) / 100 }'`
+	awk -v ncpus=$ncpus '{ print ncpus * ($7 + $NF) / 100 }'`
 awk -v ncpus=$ncpus -v idlecpus=$idlecpus < /dev/null '
 BEGIN {
 	cpus2use = idlecpus;
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index d6cc07fc137f..559e01ac86be 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -30,6 +30,7 @@ else
 	echo Unreadable results directory: $i
 	exit 1
 fi
+. tools/testing/selftests/rcutorture/bin/functions.sh
 
 configfile=`echo $i | sed -e 's/^.*\///'`
 ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'`
@@ -48,4 +49,21 @@ else
 		title="$title ($ngpsps per second)"
 	fi
 	echo $title
+	nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
+	if test -z "$nclosecalls"
+	then
+		exit 0
+	fi
+	if test "$nclosecalls" -eq 0
+	then
+		exit 0
+	fi
+	# Compute number of close calls per tenth of an hour
+	nclosecalls10=`awk -v nclosecalls=$nclosecalls -v dur=$dur 'BEGIN { print int(nclosecalls * 36000 / dur) }' < /dev/null`
+	if test $nclosecalls10 -gt 5 -a $nclosecalls -gt 1
+	then
+		print_bug $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
+	else
+		print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
+	fi
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 8ca9f21f2efc..5236e073919d 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -8,9 +8,9 @@
 #
 # Usage: kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args
 #
-# qemu-args defaults to "-nographic", along with arguments specifying the
-#			number of CPUs and other options generated from
-#			the underlying CPU architecture.
+# qemu-args defaults to "-enable-kvm -soundhw pcspk -nographic", along with
+#			arguments specifying the number of CPUs and other
+#			options generated from the underlying CPU architecture.
 # boot_args defaults to value returned by the per_version_boot_params
 #			shell function.
 #
@@ -138,7 +138,7 @@ then
 fi
 
 # Generate -smp qemu argument.
-qemu_args="-nographic $qemu_args"
+qemu_args="-enable-kvm -soundhw pcspk -nographic $qemu_args"
 cpu_count=`configNR_CPUS.sh $config_template`
 cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"`
 vcpus=`identify_qemu_vcpus`
@@ -168,6 +168,7 @@ then
 	touch $resdir/buildonly
 	exit 0
 fi
+echo "NOTE: $QEMU either did not run or was interactive" > $builddir/console.log
 echo $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
 ( $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) &
 qemu_pid=$!
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
index 499d1e598e42..a6b57622c2e5 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -26,12 +26,15 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=$1
+F=$1
 title=$2
+T=/tmp/parse-build.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
 
 . functions.sh
 
-if grep -q CC < $T
+if grep -q CC < $F
 then
 	:
 else
@@ -39,18 +42,21 @@ else
 	exit 1
 fi
 
-if grep -q "error:" < $T
+if grep -q "error:" < $F
 then
 	print_bug $title build errors:
-	grep "error:" < $T
+	grep "error:" < $F
 	exit 2
 fi
-exit 0
 
-if egrep -q "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+grep warning: < $F > $T/warnings
+grep "include/linux/*rcu*\.h:" $T/warnings > $T/hwarnings
+grep "kernel/rcu/[^/]*:" $T/warnings > $T/cwarnings
+cat $T/hwarnings $T/cwarnings > $T/rcuwarnings
+if test -s $T/rcuwarnings
 then
 	print_warning $title build errors:
-	egrep "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+	cat $T/rcuwarnings
 	exit 2
 fi
 exit 0
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index f962ba4cf68b..d8f35cf116be 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -36,7 +36,7 @@ if grep -Pq '\x00' < $file
 then
 	print_warning Console output contains nul bytes, old qemu still running?
 fi
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
 if test -s $T
 then
 	print_warning Assertion failure in $file $title
diff --git a/tools/usb/ffs-aio-example/multibuff/host_app/test.c b/tools/usb/ffs-aio-example/multibuff/host_app/test.c
index daa3abe6bebd..2cbcce6e8dd7 100644
--- a/tools/usb/ffs-aio-example/multibuff/host_app/test.c
+++ b/tools/usb/ffs-aio-example/multibuff/host_app/test.c
@@ -33,11 +33,6 @@
 #define VENDOR	0x1d6b
 #define PRODUCT	0x0105
 
-/* endpoints indexes */
-
-#define EP_BULK_IN	(1 | LIBUSB_ENDPOINT_IN)
-#define EP_BULK_OUT	(2 | LIBUSB_ENDPOINT_OUT)
-
 #define BUF_LEN		8192
 
 /*
@@ -159,14 +154,21 @@ void test_exit(struct test_state *state)
 int main(void)
 {
 	struct test_state state;
+	struct libusb_config_descriptor *conf;
+	struct libusb_interface_descriptor const *iface;
+	unsigned char addr;
 
 	if (test_init(&state))
 		return 1;
 
+	libusb_get_config_descriptor(state.found, 0, &conf);
+	iface = &conf->interface[0].altsetting[0];
+	addr = iface->endpoint[0].bEndpointAddress;
+
 	while (1) {
 		static unsigned char buffer[BUF_LEN];
 		int bytes;
-		libusb_bulk_transfer(state.handle, EP_BULK_IN, buffer, BUF_LEN,
+		libusb_bulk_transfer(state.handle, addr, buffer, BUF_LEN,
 				     &bytes, 500);
 	}
 	test_exit(&state);
diff --git a/tools/usb/ffs-aio-example/simple/device_app/aio_simple.c b/tools/usb/ffs-aio-example/simple/device_app/aio_simple.c
index adc310a6d489..1f44a29818bf 100644
--- a/tools/usb/ffs-aio-example/simple/device_app/aio_simple.c
+++ b/tools/usb/ffs-aio-example/simple/device_app/aio_simple.c
@@ -103,12 +103,14 @@ static const struct {
 			.bDescriptorType = USB_DT_ENDPOINT,
 			.bEndpointAddress = 1 | USB_DIR_IN,
 			.bmAttributes = USB_ENDPOINT_XFER_BULK,
+			.wMaxPacketSize = htole16(512),
 		},
 		.bulk_source = {
 			.bLength = sizeof(descriptors.hs_descs.bulk_source),
 			.bDescriptorType = USB_DT_ENDPOINT,
 			.bEndpointAddress = 2 | USB_DIR_OUT,
 			.bmAttributes = USB_ENDPOINT_XFER_BULK,
+			.wMaxPacketSize = htole16(512),
 		},
 	},
 };
diff --git a/tools/usb/ffs-aio-example/simple/host_app/test.c b/tools/usb/ffs-aio-example/simple/host_app/test.c
index acd6332811f3..aed86ffff280 100644
--- a/tools/usb/ffs-aio-example/simple/host_app/test.c
+++ b/tools/usb/ffs-aio-example/simple/host_app/test.c
@@ -33,11 +33,6 @@
 #define VENDOR	0x1d6b
 #define PRODUCT	0x0105
 
-/* endpoints indexes */
-
-#define EP_BULK_IN	(1 | LIBUSB_ENDPOINT_IN)
-#define EP_BULK_OUT	(2 | LIBUSB_ENDPOINT_OUT)
-
 #define BUF_LEN		8192
 
 /*
@@ -159,16 +154,24 @@ void test_exit(struct test_state *state)
 int main(void)
 {
 	struct test_state state;
+	struct libusb_config_descriptor *conf;
+	struct libusb_interface_descriptor const *iface;
+	unsigned char in_addr, out_addr;
 
 	if (test_init(&state))
 		return 1;
 
+	libusb_get_config_descriptor(state.found, 0, &conf);
+	iface = &conf->interface[0].altsetting[0];
+	in_addr = iface->endpoint[0].bEndpointAddress;
+	out_addr = iface->endpoint[1].bEndpointAddress;
+
 	while (1) {
 		static unsigned char buffer[BUF_LEN];
 		int bytes;
-		libusb_bulk_transfer(state.handle, EP_BULK_IN, buffer, BUF_LEN,
+		libusb_bulk_transfer(state.handle, in_addr, buffer, BUF_LEN,
 				     &bytes, 500);
-		libusb_bulk_transfer(state.handle, EP_BULK_OUT, buffer, BUF_LEN,
+		libusb_bulk_transfer(state.handle, out_addr, buffer, BUF_LEN,
 				     &bytes, 500);
 	}
 	test_exit(&state);
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index 264fbc297e0b..8bdf16b8ba60 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -133,6 +133,7 @@ static const char * const page_flag_names[] = {
 	[KPF_KSM]		= "x:ksm",
 	[KPF_THP]		= "t:thp",
 	[KPF_BALLOON]		= "o:balloon",
+	[KPF_ZERO_PAGE]		= "z:zero_page",
 
 	[KPF_RESERVED]		= "r:reserved",
 	[KPF_MLOCKED]		= "m:mlocked",