Merge remote-tracking branch 'linux-stable/linux-3.0.y' into p-android-omap-3.0-dev-espresso

Conflicts:
	Makefile
	arch/arm/include/asm/hardware/cache-l2x0.h
	arch/arm/kernel/smp.c
	arch/arm/mach-omap2/board-4430sdp.c
	arch/arm/mach-omap2/board-omap4panda.c
	arch/arm/mach-omap2/opp.c
	arch/ia64/include/asm/futex.h
	drivers/bluetooth/ath3k.c
	drivers/bluetooth/btusb.c
	drivers/firmware/efivars.c
	drivers/gpu/drm/i915/intel_lvds.c
	drivers/gpu/drm/radeon/radeon_atombios.c
	drivers/gpu/drm/radeon/radeon_irq_kms.c
	drivers/hwmon/fam15h_power.c
	drivers/mfd/twl6030-irq.c
	drivers/mmc/core/sdio.c
	drivers/net/tun.c
	drivers/net/usb/ipheth.c
	drivers/net/usb/usbnet.c
	drivers/usb/core/hub.c
	drivers/usb/host/xhci-mem.c
	drivers/usb/host/xhci.h
	drivers/usb/musb/omap2430.c
	drivers/usb/serial/ftdi_sio.c
	drivers/usb/serial/ftdi_sio_ids.h
	drivers/usb/serial/option.c
	drivers/usb/serial/qcserial.c
	drivers/usb/serial/ti_usb_3410_5052.c
	drivers/usb/serial/ti_usb_3410_5052.h
	drivers/video/omap2/dss/hdmi.c
	fs/splice.c
	include/asm-generic/pgtable.h
	include/net/sch_generic.h
	kernel/cgroup.c
	kernel/futex.c
	kernel/time/timekeeping.c
	net/ipv4/route.c
	net/ipv4/syncookies.c
	net/ipv4/tcp_ipv4.c
	net/wireless/util.c
	security/commoncap.c
	sound/soc/soc-dapm.c

12 files changed, 348 insertions, 170 deletions

diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c
index b427711..58b49d1 100644
--- a/drivers/char/agp/intel-agp.c
+++ b/drivers/char/agp/intel-agp.c
@@ -897,6 +897,7 @@ static struct pci_device_id agp_intel_pci_table[] = {
 	ID(PCI_DEVICE_ID_INTEL_B43_HB),
 	ID(PCI_DEVICE_ID_INTEL_B43_1_HB),
 	ID(PCI_DEVICE_ID_INTEL_IRONLAKE_D_HB),
+	ID(PCI_DEVICE_ID_INTEL_IRONLAKE_D2_HB),
 	ID(PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB),
 	ID(PCI_DEVICE_ID_INTEL_IRONLAKE_MA_HB),
 	ID(PCI_DEVICE_ID_INTEL_IRONLAKE_MC2_HB),
diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h
index 5da67f1..6f24604 100644
--- a/drivers/char/agp/intel-agp.h
+++ b/drivers/char/agp/intel-agp.h
@@ -211,6 +211,7 @@
 #define PCI_DEVICE_ID_INTEL_G41_HB          0x2E30
 #define PCI_DEVICE_ID_INTEL_G41_IG          0x2E32
 #define PCI_DEVICE_ID_INTEL_IRONLAKE_D_HB	    0x0040
+#define PCI_DEVICE_ID_INTEL_IRONLAKE_D2_HB	    0x0069
 #define PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG	    0x0042
 #define PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB	    0x0044
 #define PCI_DEVICE_ID_INTEL_IRONLAKE_MA_HB	    0x0062
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 34d6a1c..853f8e8 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -374,26 +374,14 @@ static int hpet_mmap(struct file *file, struct vm_area_struct *vma)
 	struct hpet_dev *devp;
 	unsigned long addr;
 
-	if (((vma->vm_end - vma->vm_start) != PAGE_SIZE) || vma->vm_pgoff)
-		return -EINVAL;
-
 	devp = file->private_data;
 	addr = devp->hd_hpets->hp_hpet_phys;
 
 	if (addr & (PAGE_SIZE - 1))
 		return -ENOSYS;
 
-	vma->vm_flags |= VM_IO;
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
-	if (io_remap_pfn_range(vma, vma->vm_start, addr >> PAGE_SHIFT,
-					PAGE_SIZE, vma->vm_page_prot)) {
-		printk(KERN_ERR "%s: io_remap_pfn_range failed\n",
-			__func__);
-		return -EAGAIN;
-	}
-
-	return 0;
+	return vm_iomap_memory(vma, addr, PAGE_SIZE);
 #else
 	return -ENOSYS;
 #endif
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 2016aad..564f6c4 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -40,6 +40,7 @@
 #include <linux/init.h>
 #include <linux/miscdevice.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 
 
@@ -52,8 +53,12 @@ static struct hwrng *current_rng;
 static LIST_HEAD(rng_list);
 static DEFINE_MUTEX(rng_mutex);
 static int data_avail;
-static u8 rng_buffer[SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES]
-	__cacheline_aligned;
+static u8 *rng_buffer;
+
+static size_t rng_buffer_size(void)
+{
+	return SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES;
+}
 
 static inline int hwrng_init(struct hwrng *rng)
 {
@@ -116,7 +121,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf,
 
 		if (!data_avail) {
 			bytes_read = rng_get_data(current_rng, rng_buffer,
-				sizeof(rng_buffer),
+				rng_buffer_size(),
 				!(filp->f_flags & O_NONBLOCK));
 			if (bytes_read < 0) {
 				err = bytes_read;
@@ -307,6 +312,14 @@ int hwrng_register(struct hwrng *rng)
 
 	mutex_lock(&rng_mutex);
 
+	/* kmalloc makes this safe for virt_to_page() in virtio_rng.c */
+	err = -ENOMEM;
+	if (!rng_buffer) {
+		rng_buffer = kmalloc(rng_buffer_size(), GFP_KERNEL);
+		if (!rng_buffer)
+			goto out_unlock;
+	}
+
 	/* Must not register two RNGs with the same name. */
 	err = -EEXIST;
 	list_for_each_entry(tmp, &rng_list, list) {
diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c
index 75f1cbd..ca7570d 100644
--- a/drivers/char/hw_random/virtio-rng.c
+++ b/drivers/char/hw_random/virtio-rng.c
@@ -88,14 +88,22 @@ static int virtrng_probe(struct virtio_device *vdev)
 {
 	int err;
 
+	if (vq) {
+		/* We only support one device for now */
+		return -EBUSY;
+	}
 	/* We expect a single virtqueue. */
 	vq = virtio_find_single_vq(vdev, random_recv_done, "input");
-	if (IS_ERR(vq))
-		return PTR_ERR(vq);
+	if (IS_ERR(vq)) {
+		err = PTR_ERR(vq);
+		vq = NULL;
+		return err;
+	}
 
 	err = hwrng_register(&virtio_hwrng);
 	if (err) {
 		vdev->config->del_vqs(vdev);
+		vq = NULL;
 		return err;
 	}
 
@@ -107,6 +115,7 @@ static void __devexit virtrng_remove(struct virtio_device *vdev)
 	vdev->config->reset(vdev);
 	hwrng_unregister(&virtio_hwrng);
 	vdev->config->del_vqs(vdev);
+	vq = NULL;
 }
 
 static struct virtio_device_id id_table[] = {
diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c
index 3ed20e8..92ce302 100644
--- a/drivers/char/ipmi/ipmi_bt_sm.c
+++ b/drivers/char/ipmi/ipmi_bt_sm.c
@@ -95,9 +95,9 @@ struct si_sm_data {
 	enum bt_states	state;
 	unsigned char	seq;		/* BT sequence number */
 	struct si_sm_io	*io;
-	unsigned char	write_data[IPMI_MAX_MSG_LENGTH];
+	unsigned char	write_data[IPMI_MAX_MSG_LENGTH + 2]; /* +2 for memcpy */
 	int		write_count;
-	unsigned char	read_data[IPMI_MAX_MSG_LENGTH];
+	unsigned char	read_data[IPMI_MAX_MSG_LENGTH + 2]; /* +2 for memcpy */
 	int		read_count;
 	int		truncated;
 	long		timeout;	/* microseconds countdown */
diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c
index 2aa3977..8dde1f5 100644
--- a/drivers/char/ipmi/ipmi_devintf.c
+++ b/drivers/char/ipmi/ipmi_devintf.c
@@ -838,13 +838,25 @@ static long compat_ipmi_ioctl(struct file *filep, unsigned int cmd,
 		return ipmi_ioctl(filep, cmd, arg);
 	}
 }
+
+static long unlocked_compat_ipmi_ioctl(struct file *filep, unsigned int cmd,
+				       unsigned long arg)
+{
+	int ret;
+
+	mutex_lock(&ipmi_mutex);
+	ret = compat_ipmi_ioctl(filep, cmd, arg);
+	mutex_unlock(&ipmi_mutex);
+
+	return ret;
+}
 #endif
 
 static const struct file_operations ipmi_fops = {
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= ipmi_unlocked_ioctl,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl   = compat_ipmi_ioctl,
+	.compat_ioctl   = unlocked_compat_ipmi_ioctl,
 #endif
 	.open		= ipmi_open,
 	.release	= ipmi_release,
diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c
index 25d139c..579051c 100644
--- a/drivers/char/mspec.c
+++ b/drivers/char/mspec.c
@@ -284,7 +284,7 @@ mspec_mmap(struct file *file, struct vm_area_struct *vma,
 	vdata->flags = flags;
 	vdata->type = type;
 	spin_lock_init(&vdata->lock);
-	vdata->refcnt = ATOMIC_INIT(1);
+	atomic_set(&vdata->refcnt, 1);
 	vma->vm_private_data = vdata;
 
 	vma->vm_flags |= (VM_IO | VM_RESERVED | VM_PFNMAP | VM_DONTEXPAND);
diff --git a/drivers/char/random.c b/drivers/char/random.c
index c35a785..e7e479c 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -125,21 +125,26 @@
  * The current exported interfaces for gathering environmental noise
  * from the devices are:
  *
+ *	void add_device_randomness(const void *buf, unsigned int size);
  * 	void add_input_randomness(unsigned int type, unsigned int code,
  *                                unsigned int value);
- * 	void add_interrupt_randomness(int irq);
+ *	void add_interrupt_randomness(int irq, int irq_flags);
  * 	void add_disk_randomness(struct gendisk *disk);
  *
+ * add_device_randomness() is for adding data to the random pool that
+ * is likely to differ between two devices (or possibly even per boot).
+ * This would be things like MAC addresses or serial numbers, or the
+ * read-out of the RTC. This does *not* add any actual entropy to the
+ * pool, but it initializes the pool to different values for devices
+ * that might otherwise be identical and have very little entropy
+ * available to them (particularly common in the embedded world).
+ *
  * add_input_randomness() uses the input layer interrupt timing, as well as
  * the event type information from the hardware.
  *
- * add_interrupt_randomness() uses the inter-interrupt timing as random
- * inputs to the entropy pool.  Note that not all interrupts are good
- * sources of randomness!  For example, the timer interrupts is not a
- * good choice, because the periodicity of the interrupts is too
- * regular, and hence predictable to an attacker.  Network Interface
- * Controller interrupts are a better measure, since the timing of the
- * NIC interrupts are more unpredictable.
+ * add_interrupt_randomness() uses the interrupt timing as random
+ * inputs to the entropy pool. Using the cycle counters and the irq source
+ * as inputs, it feeds the randomness roughly once a second.
  *
  * add_disk_randomness() uses what amounts to the seek time of block
  * layer request events, on a per-disk_devt basis, as input to the
@@ -248,6 +253,8 @@
 #include <linux/percpu.h>
 #include <linux/cryptohash.h>
 #include <linux/fips.h>
+#include <linux/ptrace.h>
+#include <linux/kmemcheck.h>
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 # include <linux/irq.h>
@@ -256,8 +263,12 @@
 #include <asm/processor.h>
 #include <asm/uaccess.h>
 #include <asm/irq.h>
+#include <asm/irq_regs.h>
 #include <asm/io.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/random.h>
+
 /*
  * Configuration information
  */
@@ -266,6 +277,8 @@
 #define SEC_XFER_SIZE 512
 #define EXTRACT_SIZE 10
 
+#define LONGS(x) (((x) + sizeof(unsigned long) - 1)/sizeof(unsigned long))
+
 /*
  * The minimum number of bits of entropy before we wake up a read on
  * /dev/random.  Should be enough to do a significant reseed.
@@ -420,8 +433,10 @@ struct entropy_store {
 	/* read-write data: */
 	spinlock_t lock;
 	unsigned add_ptr;
+	unsigned input_rotate;
 	int entropy_count;
-	int input_rotate;
+	int entropy_total;
+	unsigned int initialized:1;
 	__u8 last_data[EXTRACT_SIZE];
 };
 
@@ -454,6 +469,10 @@ static struct entropy_store nonblocking_pool = {
 	.pool = nonblocking_pool_data
 };
 
+static __u32 const twist_table[8] = {
+	0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
+	0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
+
 /*
  * This function adds bytes into the entropy "pool".  It does not
  * update the entropy estimate.  The caller should call
@@ -464,29 +483,24 @@ static struct entropy_store nonblocking_pool = {
  * it's cheap to do so and helps slightly in the expected case where
  * the entropy is concentrated in the low-order bits.
  */
-static void mix_pool_bytes_extract(struct entropy_store *r, const void *in,
-				   int nbytes, __u8 out[64])
+static void _mix_pool_bytes(struct entropy_store *r, const void *in,
+			    int nbytes, __u8 out[64])
 {
-	static __u32 const twist_table[8] = {
-		0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
-		0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
 	unsigned long i, j, tap1, tap2, tap3, tap4, tap5;
 	int input_rotate;
 	int wordmask = r->poolinfo->poolwords - 1;
 	const char *bytes = in;
 	__u32 w;
-	unsigned long flags;
 
-	/* Taps are constant, so we can load them without holding r->lock.  */
 	tap1 = r->poolinfo->tap1;
 	tap2 = r->poolinfo->tap2;
 	tap3 = r->poolinfo->tap3;
 	tap4 = r->poolinfo->tap4;
 	tap5 = r->poolinfo->tap5;
 
-	spin_lock_irqsave(&r->lock, flags);
-	input_rotate = r->input_rotate;
-	i = r->add_ptr;
+	smp_rmb();
+	input_rotate = ACCESS_ONCE(r->input_rotate);
+	i = ACCESS_ONCE(r->add_ptr);
 
 	/* mix one byte at a time to simplify size handling and churn faster */
 	while (nbytes--) {
@@ -513,19 +527,61 @@ static void mix_pool_bytes_extract(struct entropy_store *r, const void *in,
 		input_rotate += i ? 7 : 14;
 	}
 
-	r->input_rotate = input_rotate;
-	r->add_ptr = i;
+	ACCESS_ONCE(r->input_rotate) = input_rotate;
+	ACCESS_ONCE(r->add_ptr) = i;
+	smp_wmb();
 
 	if (out)
 		for (j = 0; j < 16; j++)
 			((__u32 *)out)[j] = r->pool[(i - j) & wordmask];
+}
 
+static void __mix_pool_bytes(struct entropy_store *r, const void *in,
+			     int nbytes, __u8 out[64])
+{
+	trace_mix_pool_bytes_nolock(r->name, nbytes, _RET_IP_);
+	_mix_pool_bytes(r, in, nbytes, out);
+}
+
+static void mix_pool_bytes(struct entropy_store *r, const void *in,
+			   int nbytes, __u8 out[64])
+{
+	unsigned long flags;
+
+	trace_mix_pool_bytes(r->name, nbytes, _RET_IP_);
+	spin_lock_irqsave(&r->lock, flags);
+	_mix_pool_bytes(r, in, nbytes, out);
 	spin_unlock_irqrestore(&r->lock, flags);
 }
 
-static void mix_pool_bytes(struct entropy_store *r, const void *in, int bytes)
+struct fast_pool {
+	__u32		pool[4];
+	unsigned long	last;
+	unsigned short	count;
+	unsigned char	rotate;
+	unsigned char	last_timer_intr;
+};
+
+/*
+ * This is a fast mixing routine used by the interrupt randomness
+ * collector.  It's hardcoded for an 128 bit pool and assumes that any
+ * locks that might be needed are taken by the caller.
+ */
+static void fast_mix(struct fast_pool *f, const void *in, int nbytes)
 {
-       mix_pool_bytes_extract(r, in, bytes, NULL);
+	const char	*bytes = in;
+	__u32		w;
+	unsigned	i = f->count;
+	unsigned	input_rotate = f->rotate;
+
+	while (nbytes--) {
+		w = rol32(*bytes++, input_rotate & 31) ^ f->pool[i & 3] ^
+			f->pool[(i + 1) & 3];
+		f->pool[i & 3] = (w >> 3) ^ twist_table[w & 7];
+		input_rotate += (i++ & 3) ? 7 : 14;
+	}
+	f->count = i;
+	f->rotate = input_rotate;
 }
 
 /*
@@ -533,30 +589,38 @@ static void mix_pool_bytes(struct entropy_store *r, const void *in, int bytes)
  */
 static void credit_entropy_bits(struct entropy_store *r, int nbits)
 {
-	unsigned long flags;
-	int entropy_count;
+	int entropy_count, orig;
 
 	if (!nbits)
 		return;
 
-	spin_lock_irqsave(&r->lock, flags);
-
 	DEBUG_ENT("added %d entropy credits to %s\n", nbits, r->name);
-	entropy_count = r->entropy_count;
+retry:
+	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
 	entropy_count += nbits;
+
 	if (entropy_count < 0) {
 		DEBUG_ENT("negative entropy/overflow\n");
 		entropy_count = 0;
 	} else if (entropy_count > r->poolinfo->POOLBITS)
 		entropy_count = r->poolinfo->POOLBITS;
-	r->entropy_count = entropy_count;
+	if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
+		goto retry;
+
+	if (!r->initialized && nbits > 0) {
+		r->entropy_total += nbits;
+		if (r->entropy_total > 128)
+			r->initialized = 1;
+	}
+
+	trace_credit_entropy_bits(r->name, nbits, entropy_count,
+				  r->entropy_total, _RET_IP_);
 
 	/* should we wake readers? */
 	if (r == &input_pool && entropy_count >= random_read_wakeup_thresh) {
 		wake_up_interruptible(&random_read_wait);
 		kill_fasync(&fasync, SIGIO, POLL_IN);
 	}
-	spin_unlock_irqrestore(&r->lock, flags);
 }
 
 /*********************************************************************
@@ -572,42 +636,24 @@ struct timer_rand_state {
 	unsigned dont_count_entropy:1;
 };
 
-#ifndef CONFIG_GENERIC_HARDIRQS
-
-static struct timer_rand_state *irq_timer_state[NR_IRQS];
-
-static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
-{
-	return irq_timer_state[irq];
-}
-
-static void set_timer_rand_state(unsigned int irq,
-				 struct timer_rand_state *state)
-{
-	irq_timer_state[irq] = state;
-}
-
-#else
-
-static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	return desc->timer_rand_state;
-}
-
-static void set_timer_rand_state(unsigned int irq,
-				 struct timer_rand_state *state)
+/*
+ * Add device- or boot-specific data to the input and nonblocking
+ * pools to help initialize them to unique values.
+ *
+ * None of this adds any entropy, it is meant to avoid the
+ * problem of the nonblocking pool having similar initial state
+ * across largely identical devices.
+ */
+void add_device_randomness(const void *buf, unsigned int size)
 {
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
+	unsigned long time = get_cycles() ^ jiffies;
 
-	desc->timer_rand_state = state;
+	mix_pool_bytes(&input_pool, buf, size, NULL);
+	mix_pool_bytes(&input_pool, &time, sizeof(time), NULL);
+	mix_pool_bytes(&nonblocking_pool, buf, size, NULL);
+	mix_pool_bytes(&nonblocking_pool, &time, sizeof(time), NULL);
 }
-#endif
+EXPORT_SYMBOL(add_device_randomness);
 
 static struct timer_rand_state input_timer_state;
 
@@ -624,8 +670,8 @@ static struct timer_rand_state input_timer_state;
 static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 {
 	struct {
-		cycles_t cycles;
 		long jiffies;
+		unsigned cycles;
 		unsigned num;
 	} sample;
 	long delta, delta2, delta3;
@@ -639,7 +685,7 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 	sample.jiffies = jiffies;
 	sample.cycles = get_cycles();
 	sample.num = num;
-	mix_pool_bytes(&input_pool, &sample, sizeof(sample));
+	mix_pool_bytes(&input_pool, &sample, sizeof(sample), NULL);
 
 	/*
 	 * Calculate number of bits of randomness we probably added.
@@ -696,17 +742,48 @@ void add_input_randomness(unsigned int type, unsigned int code,
 }
 EXPORT_SYMBOL_GPL(add_input_randomness);
 
-void add_interrupt_randomness(int irq)
+static DEFINE_PER_CPU(struct fast_pool, irq_randomness);
+
+void add_interrupt_randomness(int irq, int irq_flags)
 {
-	struct timer_rand_state *state;
+	struct entropy_store	*r;
+	struct fast_pool	*fast_pool = &__get_cpu_var(irq_randomness);
+	struct pt_regs		*regs = get_irq_regs();
+	unsigned long		now = jiffies;
+	__u32			input[4], cycles = get_cycles();
+
+	input[0] = cycles ^ jiffies;
+	input[1] = irq;
+	if (regs) {
+		__u64 ip = instruction_pointer(regs);
+		input[2] = ip;
+		input[3] = ip >> 32;
+	}
 
-	state = get_timer_rand_state(irq);
+	fast_mix(fast_pool, input, sizeof(input));
 
-	if (state == NULL)
+	if ((fast_pool->count & 1023) &&
+	    !time_after(now, fast_pool->last + HZ))
 		return;
 
-	DEBUG_ENT("irq event %d\n", irq);
-	add_timer_randomness(state, 0x100 + irq);
+	fast_pool->last = now;
+
+	r = nonblocking_pool.initialized ? &input_pool : &nonblocking_pool;
+	__mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL);
+	/*
+	 * If we don't have a valid cycle counter, and we see
+	 * back-to-back timer interrupts, then skip giving credit for
+	 * any entropy.
+	 */
+	if (cycles == 0) {
+		if (irq_flags & __IRQF_TIMER) {
+			if (fast_pool->last_timer_intr)
+				return;
+			fast_pool->last_timer_intr = 1;
+		} else
+			fast_pool->last_timer_intr = 0;
+	}
+	credit_entropy_bits(r, 1);
 }
 
 #ifdef CONFIG_BLOCK
@@ -738,7 +815,7 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf,
  */
 static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 {
-	__u32 tmp[OUTPUT_POOL_WORDS];
+	__u32	tmp[OUTPUT_POOL_WORDS];
 
 	if (r->pull && r->entropy_count < nbytes * 8 &&
 	    r->entropy_count < r->poolinfo->POOLBITS) {
@@ -757,7 +834,7 @@ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 
 		bytes = extract_entropy(r->pull, tmp, bytes,
 					random_read_wakeup_thresh / 8, rsvd);
-		mix_pool_bytes(r, tmp, bytes);
+		mix_pool_bytes(r, tmp, bytes, NULL);
 		credit_entropy_bits(r, bytes*8);
 	}
 }
@@ -816,13 +893,19 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
 static void extract_buf(struct entropy_store *r, __u8 *out)
 {
 	int i;
-	__u32 hash[5], workspace[SHA_WORKSPACE_WORDS];
+	union {
+		__u32 w[5];
+		unsigned long l[LONGS(EXTRACT_SIZE)];
+	} hash;
+	__u32 workspace[SHA_WORKSPACE_WORDS];
 	__u8 extract[64];
+	unsigned long flags;
 
 	/* Generate a hash across the pool, 16 words (512 bits) at a time */
-	sha_init(hash);
+	sha_init(hash.w);
+	spin_lock_irqsave(&r->lock, flags);
 	for (i = 0; i < r->poolinfo->poolwords; i += 16)
-		sha_transform(hash, (__u8 *)(r->pool + i), workspace);
+		sha_transform(hash.w, (__u8 *)(r->pool + i), workspace);
 
 	/*
 	 * We mix the hash back into the pool to prevent backtracking
@@ -833,13 +916,14 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	 * brute-forcing the feedback as hard as brute-forcing the
 	 * hash.
 	 */
-	mix_pool_bytes_extract(r, hash, sizeof(hash), extract);
+	__mix_pool_bytes(r, hash.w, sizeof(hash.w), extract);
+	spin_unlock_irqrestore(&r->lock, flags);
 
 	/*
 	 * To avoid duplicates, we atomically extract a portion of the
 	 * pool while mixing, and hash one final time.
 	 */
-	sha_transform(hash, extract, workspace);
+	sha_transform(hash.w, extract, workspace);
 	memset(extract, 0, sizeof(extract));
 	memset(workspace, 0, sizeof(workspace));
 
@@ -848,20 +932,32 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	 * pattern, we fold it in half. Thus, we always feed back
 	 * twice as much data as we output.
 	 */
-	hash[0] ^= hash[3];
-	hash[1] ^= hash[4];
-	hash[2] ^= rol32(hash[2], 16);
-	memcpy(out, hash, EXTRACT_SIZE);
-	memset(hash, 0, sizeof(hash));
+	hash.w[0] ^= hash.w[3];
+	hash.w[1] ^= hash.w[4];
+	hash.w[2] ^= rol32(hash.w[2], 16);
+
+	/*
+	 * If we have a architectural hardware random number
+	 * generator, mix that in, too.
+	 */
+	for (i = 0; i < LONGS(EXTRACT_SIZE); i++) {
+		unsigned long v;
+		if (!arch_get_random_long(&v))
+			break;
+		hash.l[i] ^= v;
+	}
+
+	memcpy(out, &hash, EXTRACT_SIZE);
+	memset(&hash, 0, sizeof(hash));
 }
 
 static ssize_t extract_entropy(struct entropy_store *r, void *buf,
-			       size_t nbytes, int min, int reserved)
+				 size_t nbytes, int min, int reserved)
 {
 	ssize_t ret = 0, i;
 	__u8 tmp[EXTRACT_SIZE];
-	unsigned long flags;
 
+	trace_extract_entropy(r->name, nbytes, r->entropy_count, _RET_IP_);
 	xfer_secondary_pool(r, nbytes);
 	nbytes = account(r, nbytes, min, reserved);
 
@@ -869,6 +965,8 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf,
 		extract_buf(r, tmp);
 
 		if (fips_enabled) {
+			unsigned long flags;
+
 			spin_lock_irqsave(&r->lock, flags);
 			if (!memcmp(tmp, r->last_data, EXTRACT_SIZE))
 				panic("Hardware RNG duplicated output!\n");
@@ -894,6 +992,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
 	ssize_t ret = 0, i;
 	__u8 tmp[EXTRACT_SIZE];
 
+	trace_extract_entropy_user(r->name, nbytes, r->entropy_count, _RET_IP_);
 	xfer_secondary_pool(r, nbytes);
 	nbytes = account(r, nbytes, 0, 0);
 
@@ -927,8 +1026,9 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
 
 /*
  * This function is the exported kernel interface.  It returns some
- * number of good random numbers, suitable for seeding TCP sequence
- * numbers, etc.
+ * number of good random numbers, suitable for key generation, seeding
+ * TCP sequence numbers, etc.  It does not use the hw random number
+ * generator, if available; use get_random_bytes_arch() for that.
  */
 void get_random_bytes(void *buf, int nbytes)
 {
@@ -937,6 +1037,39 @@ void get_random_bytes(void *buf, int nbytes)
 EXPORT_SYMBOL(get_random_bytes);
 
 /*
+ * This function will use the architecture-specific hardware random
+ * number generator if it is available.  The arch-specific hw RNG will
+ * almost certainly be faster than what we can do in software, but it
+ * is impossible to verify that it is implemented securely (as
+ * opposed, to, say, the AES encryption of a sequence number using a
+ * key known by the NSA).  So it's useful if we need the speed, but
+ * only if we're willing to trust the hardware manufacturer not to
+ * have put in a back door.
+ */
+void get_random_bytes_arch(void *buf, int nbytes)
+{
+	char *p = buf;
+
+	trace_get_random_bytes(nbytes, _RET_IP_);
+	while (nbytes) {
+		unsigned long v;
+		int chunk = min(nbytes, (int)sizeof(unsigned long));
+
+		if (!arch_get_random_long(&v))
+			break;
+
+		memcpy(p, &v, chunk);
+		p += chunk;
+		nbytes -= chunk;
+	}
+
+	if (nbytes)
+		extract_entropy(&nonblocking_pool, p, nbytes, 0, 0);
+}
+EXPORT_SYMBOL(get_random_bytes_arch);
+
+
+/*
  * init_std_data - initialize pool with system data
  *
  * @r: pool to initialize
@@ -947,18 +1080,31 @@ EXPORT_SYMBOL(get_random_bytes);
  */
 static void init_std_data(struct entropy_store *r)
 {
-	ktime_t now;
-	unsigned long flags;
+	int i;
+	ktime_t now = ktime_get_real();
+	unsigned long rv;
 
-	spin_lock_irqsave(&r->lock, flags);
 	r->entropy_count = 0;
-	spin_unlock_irqrestore(&r->lock, flags);
-
-	now = ktime_get_real();
-	mix_pool_bytes(r, &now, sizeof(now));
-	mix_pool_bytes(r, utsname(), sizeof(*(utsname())));
+	r->entropy_total = 0;
+	mix_pool_bytes(r, &now, sizeof(now), NULL);
+	for (i = r->poolinfo->POOLBYTES; i > 0; i -= sizeof(rv)) {
+		if (!arch_get_random_long(&rv))
+			break;
+		mix_pool_bytes(r, &rv, sizeof(rv), NULL);
+	}
+	mix_pool_bytes(r, utsname(), sizeof(*(utsname())), NULL);
 }
 
+/*
+ * Note that setup_arch() may call add_device_randomness()
+ * long before we get here. This allows seeding of the pools
+ * with some platform dependent data very early in the boot
+ * process. But it limits our options here. We must use
+ * statically allocated structures that already have all
+ * initializations complete at compile time. We should also
+ * take care not to overwrite the precious per platform data
+ * we were given.
+ */
 static int rand_initialize(void)
 {
 	init_std_data(&input_pool);
@@ -968,24 +1114,6 @@ static int rand_initialize(void)
 }
 module_init(rand_initialize);
 
-void rand_initialize_irq(int irq)
-{
-	struct timer_rand_state *state;
-
-	state = get_timer_rand_state(irq);
-
-	if (state)
-		return;
-
-	/*
-	 * If kzalloc returns null, we just won't use that entropy
-	 * source.
-	 */
-	state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
-	if (state)
-		set_timer_rand_state(irq, state);
-}
-
 #ifdef CONFIG_BLOCK
 void rand_initialize_disk(struct gendisk *disk)
 {
@@ -1093,7 +1221,7 @@ write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
 		count -= bytes;
 		p += bytes;
 
-		mix_pool_bytes(r, buf, bytes);
+		mix_pool_bytes(r, buf, bytes, NULL);
 		cond_resched();
 	}
 
@@ -1236,10 +1364,15 @@ static int proc_do_uuid(ctl_table *table, int write,
 	uuid = table->data;
 	if (!uuid) {
 		uuid = tmp_uuid;
-		uuid[8] = 0;
-	}
-	if (uuid[8] == 0)
 		generate_random_uuid(uuid);
+	} else {
+		static DEFINE_SPINLOCK(bootid_spinlock);
+
+		spin_lock(&bootid_spinlock);
+		if (!uuid[8])
+			generate_random_uuid(uuid);
+		spin_unlock(&bootid_spinlock);
+	}
 
 	sprintf(buf, "%pU", uuid);
 
@@ -1302,12 +1435,11 @@ ctl_table random_table[] = {
 
 static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
 
-static int __init random_int_secret_init(void)
+int random_int_secret_init(void)
 {
 	get_random_bytes(random_int_secret, sizeof(random_int_secret));
 	return 0;
 }
-late_initcall(random_int_secret_init);
 
 /*
  * Get a random word for internal kernel use only. Similar to urandom but
@@ -1318,9 +1450,14 @@ late_initcall(random_int_secret_init);
 DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash);
 unsigned int get_random_int(void)
 {
-	__u32 *hash = get_cpu_var(get_random_int_hash);
+	__u32 *hash;
 	unsigned int ret;
 
+	if (arch_get_random_int(&ret))
+		return ret;
+
+	hash = get_cpu_var(get_random_int_hash);
+
 	hash[0] += current->pid + jiffies + get_cycles();
 	md5_transform(hash, random_int_secret);
 	ret = hash[0];
diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c
index b85ee76..65b9d6f 100644
--- a/drivers/char/tpm/tpm.c
+++ b/drivers/char/tpm/tpm.c
@@ -1019,17 +1019,20 @@ ssize_t tpm_write(struct file *file, const char __user *buf,
 		  size_t size, loff_t *off)
 {
 	struct tpm_chip *chip = file->private_data;
-	size_t in_size = size, out_size;
+	size_t in_size = size;
+	ssize_t out_size;
 
 	/* cannot perform a write until the read has cleared
-	   either via tpm_read or a user_read_timer timeout */
-	while (atomic_read(&chip->data_pending) != 0)
-		msleep(TPM_TIMEOUT);
-
-	mutex_lock(&chip->buffer_mutex);
+	   either via tpm_read or a user_read_timer timeout.
+	   This also prevents splitted buffered writes from blocking here.
+	*/
+	if (atomic_read(&chip->data_pending) != 0)
+		return -EBUSY;
 
 	if (in_size > TPM_BUFSIZE)
-		in_size = TPM_BUFSIZE;
+		return -E2BIG;
+
+	mutex_lock(&chip->buffer_mutex);
 
 	if (copy_from_user
 	    (chip->data_buffer, (void __user *) buf, in_size)) {
@@ -1039,6 +1042,10 @@ ssize_t tpm_write(struct file *file, const char __user *buf,
 
 	/* atomic tpm command send and result receive */
 	out_size = tpm_transmit(chip, chip->data_buffer, TPM_BUFSIZE);
+	if (out_size < 0) {
+		mutex_unlock(&chip->buffer_mutex);
+		return out_size;
+	}
 
 	atomic_set(&chip->data_pending, out_size);
 	mutex_unlock(&chip->buffer_mutex);
diff --git a/drivers/char/ttyprintk.c b/drivers/char/ttyprintk.c
index a1f68af..acce1a7 100644
--- a/drivers/char/ttyprintk.c
+++ b/drivers/char/ttyprintk.c
@@ -66,7 +66,7 @@ static int tpk_printk(const unsigned char *buf, int count)
 				tmp[tpk_curr + 1] = '\0';
 				printk(KERN_INFO "%s%s", tpk_tag, tmp);
 				tpk_curr = 0;
-				if (buf[i + 1] == '\n')
+				if ((i + 1) < count && buf[i + 1] == '\n')
 					i++;
 				break;
 			case '\n':
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index fb68b12..f2fb2f2 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -241,9 +241,12 @@ static struct port *find_port_by_devt_in_portdev(struct ports_device *portdev,
 	unsigned long flags;
 
 	spin_lock_irqsave(&portdev->ports_lock, flags);
-	list_for_each_entry(port, &portdev->ports, list)
-		if (port->cdev->dev == dev)
+	list_for_each_entry(port, &portdev->ports, list) {
+		if (port->cdev->dev == dev) {
+			kref_get(&port->kref);
 			goto out;
+		}
+	}
 	port = NULL;
 out:
 	spin_unlock_irqrestore(&portdev->ports_lock, flags);
@@ -622,6 +625,10 @@ static ssize_t port_fops_read(struct file *filp, char __user *ubuf,
 
 	port = filp->private_data;
 
+	/* Port is hot-unplugged. */
+	if (!port->guest_connected)
+		return -ENODEV;
+
 	if (!port_has_data(port)) {
 		/*
 		 * If nothing's connected on the host just return 0 in
@@ -638,7 +645,7 @@ static ssize_t port_fops_read(struct file *filp, char __user *ubuf,
 		if (ret < 0)
 			return ret;
 	}
-	/* Port got hot-unplugged. */
+	/* Port got hot-unplugged while we were waiting above. */
 	if (!port->guest_connected)
 		return -ENODEV;
 	/*
@@ -781,14 +788,14 @@ static int port_fops_open(struct inode *inode, struct file *filp)
 	struct port *port;
 	int ret;
 
+	/* We get the port with a kref here */
 	port = find_port_by_devt(cdev->dev);
+	if (!port) {
+		/* Port was unplugged before we could proceed */
+		return -ENXIO;
+	}
 	filp->private_data = port;
 
-	/* Prevent against a port getting hot-unplugged at the same time */
-	spin_lock_irq(&port->portdev->ports_lock);
-	kref_get(&port->kref);
-	spin_unlock_irq(&port->portdev->ports_lock);
-
 	/*
 	 * Don't allow opening of console port devices -- that's done
 	 * via /dev/hvc
@@ -1243,14 +1250,6 @@ static void remove_port(struct kref *kref)
 
 	port = container_of(kref, struct port, kref);
 
-	sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
-	device_destroy(pdrvdata.class, port->dev->devt);
-	cdev_del(port->cdev);
-
-	kfree(port->name);
-
-	debugfs_remove(port->debugfs_file);
-
 	kfree(port);
 }
 
@@ -1268,12 +1267,14 @@ static void unplug_port(struct port *port)
 	spin_unlock_irq(&port->portdev->ports_lock);
 
 	if (port->guest_connected) {
+		/* Let the app know the port is going down. */
+		send_sigio_to_port(port);
+
+		/* Do this after sigio is actually sent */
 		port->guest_connected = false;
 		port->host_connected = false;
-		wake_up_interruptible(&port->waitqueue);
 
-		/* Let the app know the port is going down. */
-		send_sigio_to_port(port);
+		wake_up_interruptible(&port->waitqueue);
 	}
 
 	if (is_console_port(port)) {
@@ -1299,6 +1300,14 @@ static void unplug_port(struct port *port)
 	 */
 	port->portdev = NULL;
 
+	sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
+	device_destroy(pdrvdata.class, port->dev->devt);
+	cdev_del(port->cdev);
+
+	kfree(port->name);
+
+	debugfs_remove(port->debugfs_file);
+
 	/*
 	 * Locks around here are not necessary - a port can't be
 	 * opened after we removed the port struct from ports_list
@@ -1750,7 +1759,8 @@ static void virtcons_remove(struct virtio_device *vdev)
 	/* Disable interrupts for vqs */
 	vdev->config->reset(vdev);
 	/* Finish up work that's lined up */
-	cancel_work_sync(&portdev->control_work);
+	if (use_multiport(portdev))
+		cancel_work_sync(&portdev->control_work);
 
 	list_for_each_entry_safe(port, port2, &portdev->ports, list)
 		unplug_port(port);