Merge branch 'staging/for_v3.7' into v4l_for_linus

* staging/for_v3.7: (2891 commits)
  em28xx: regression fix: use DRX-K sync firmware requests on em28xx
  drxk: allow loading firmware synchrousnously
  em28xx: Make all em28xx extensions to be initialized asynchronously
  [media] tda18271: properly report read errors in tda18271_get_id
  [media] tda18271: delay IR & RF calibration until init() if delay_cal is set
  [media] MAINTAINERS: add Michael Krufky as tda827x maintainer
  [media] MAINTAINERS: add Michael Krufky as tda8290 maintainer
  [media] MAINTAINERS: add Michael Krufky as cxusb maintainer
  [media] MAINTAINERS: add Michael Krufky as lg2160 maintainer
  [media] MAINTAINERS: add Michael Krufky as lgdt3305 maintainer
  [media] MAINTAINERS: add Michael Krufky as mxl111sf maintainer
  [media] MAINTAINERS: add Michael Krufky as mxl5007t maintainer
  [media] MAINTAINERS: add Michael Krufky as tda18271 maintainer
  [media] s5p-tv: Report only multi-plane capabilities in vidioc_querycap
  [media] s5p-mfc: Fix misplaced return statement in s5p_mfc_suspend()
  [media] exynos-gsc: Add missing static storage class specifiers
  [media] exynos-gsc: Remove <linux/version.h> header file inclusion
  [media] s5p-fimc: Fix incorrect condition in fimc_lite_reqbufs()
  [media] s5p-tv: Fix potential NULL pointer dereference error
  [media] s5k6aa: Fix possible NULL pointer dereference
  ...

Conflicts:
	drivers/media/platform/s5p-fimc/fimc-capture.c
	drivers/media/platform/s5p-fimc/fimc-lite.c

5 files changed, 367 insertions, 139 deletions

diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h
index 57226424690..6ec0fff79bc 100644
--- a/drivers/char/agp/intel-agp.h
+++ b/drivers/char/agp/intel-agp.h
@@ -64,6 +64,7 @@
 #define I830_PTE_SYSTEM_CACHED  0x00000006
 /* GT PTE cache control fields */
 #define GEN6_PTE_UNCACHED	0x00000002
+#define HSW_PTE_UNCACHED	0x00000000
 #define GEN6_PTE_LLC		0x00000004
 #define GEN6_PTE_LLC_MLC	0x00000006
 #define GEN6_PTE_GFDT		0x00000008
@@ -239,16 +240,45 @@
 #define PCI_DEVICE_ID_INTEL_IVYBRIDGE_S_GT2_IG		0x016A
 #define PCI_DEVICE_ID_INTEL_VALLEYVIEW_HB		0x0F00 /* VLV1 */
 #define PCI_DEVICE_ID_INTEL_VALLEYVIEW_IG		0x0F30
-#define PCI_DEVICE_ID_INTEL_HASWELL_HB				0x0400 /* Desktop */
+#define PCI_DEVICE_ID_INTEL_HASWELL_HB			0x0400 /* Desktop */
 #define PCI_DEVICE_ID_INTEL_HASWELL_D_GT1_IG		0x0402
 #define PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_IG		0x0412
-#define PCI_DEVICE_ID_INTEL_HASWELL_M_HB			0x0404 /* Mobile */
+#define PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_PLUS_IG	0x0422
+#define PCI_DEVICE_ID_INTEL_HASWELL_M_HB		0x0404 /* Mobile */
 #define PCI_DEVICE_ID_INTEL_HASWELL_M_GT1_IG		0x0406
 #define PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_IG		0x0416
-#define PCI_DEVICE_ID_INTEL_HASWELL_S_HB			0x0408 /* Server */
+#define PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_PLUS_IG	0x0426
+#define PCI_DEVICE_ID_INTEL_HASWELL_S_HB		0x0408 /* Server */
 #define PCI_DEVICE_ID_INTEL_HASWELL_S_GT1_IG		0x040a
 #define PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_IG		0x041a
-#define PCI_DEVICE_ID_INTEL_HASWELL_SDV		0x0c16 /* SDV */
-#define PCI_DEVICE_ID_INTEL_HASWELL_E_HB			0x0c04
+#define PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_PLUS_IG	0x042a
+#define PCI_DEVICE_ID_INTEL_HASWELL_E_HB		0x0c04
+#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT1_IG	0x0C02
+#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_IG	0x0C12
+#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_PLUS_IG	0x0C22
+#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT1_IG	0x0C06
+#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_IG	0x0C16
+#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_PLUS_IG	0x0C26
+#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT1_IG	0x0C0A
+#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_IG	0x0C1A
+#define PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_PLUS_IG	0x0C2A
+#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT1_IG	0x0A02
+#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_IG	0x0A12
+#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_PLUS_IG	0x0A22
+#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT1_IG	0x0A06
+#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_IG	0x0A16
+#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_PLUS_IG	0x0A26
+#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT1_IG	0x0A0A
+#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_IG	0x0A1A
+#define PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_PLUS_IG	0x0A2A
+#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT1_IG	0x0D12
+#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_IG	0x0D22
+#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_PLUS_IG	0x0D32
+#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT1_IG	0x0D16
+#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_IG	0x0D26
+#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_PLUS_IG	0x0D36
+#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT1_IG	0x0D1A
+#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_IG	0x0D2A
+#define PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_PLUS_IG	0x0D3A
 
 #endif
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 9ed92ef5829..58e32f7c322 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -1156,6 +1156,30 @@ static bool gen6_check_flags(unsigned int flags)
 	return true;
 }
 
+static void haswell_write_entry(dma_addr_t addr, unsigned int entry,
+				unsigned int flags)
+{
+	unsigned int type_mask = flags & ~AGP_USER_CACHED_MEMORY_GFDT;
+	unsigned int gfdt = flags & AGP_USER_CACHED_MEMORY_GFDT;
+	u32 pte_flags;
+
+	if (type_mask == AGP_USER_MEMORY)
+		pte_flags = HSW_PTE_UNCACHED | I810_PTE_VALID;
+	else if (type_mask == AGP_USER_CACHED_MEMORY_LLC_MLC) {
+		pte_flags = GEN6_PTE_LLC_MLC | I810_PTE_VALID;
+		if (gfdt)
+			pte_flags |= GEN6_PTE_GFDT;
+	} else { /* set 'normal'/'cached' to LLC by default */
+		pte_flags = GEN6_PTE_LLC | I810_PTE_VALID;
+		if (gfdt)
+			pte_flags |= GEN6_PTE_GFDT;
+	}
+
+	/* gen6 has bit11-4 for physical addr bit39-32 */
+	addr |= (addr >> 28) & 0xff0;
+	writel(addr | pte_flags, intel_private.gtt + entry);
+}
+
 static void gen6_write_entry(dma_addr_t addr, unsigned int entry,
 			     unsigned int flags)
 {
@@ -1382,6 +1406,15 @@ static const struct intel_gtt_driver sandybridge_gtt_driver = {
 	.check_flags = gen6_check_flags,
 	.chipset_flush = i9xx_chipset_flush,
 };
+static const struct intel_gtt_driver haswell_gtt_driver = {
+	.gen = 6,
+	.setup = i9xx_setup,
+	.cleanup = gen6_cleanup,
+	.write_entry = haswell_write_entry,
+	.dma_mask_size = 40,
+	.check_flags = gen6_check_flags,
+	.chipset_flush = i9xx_chipset_flush,
+};
 static const struct intel_gtt_driver valleyview_gtt_driver = {
 	.gen = 7,
 	.setup = i9xx_setup,
@@ -1499,19 +1532,77 @@ static const struct intel_gtt_driver_description {
 	{ PCI_DEVICE_ID_INTEL_VALLEYVIEW_IG,
 	    "ValleyView", &valleyview_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_D_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_M_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT1_IG,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
 	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_IG,
-	    "Haswell", &sandybridge_gtt_driver },
-	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV,
-	    "Haswell", &sandybridge_gtt_driver },
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_S_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT1_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_D_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT1_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_M_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT1_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_SDV_S_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT1_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_D_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT1_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_M_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT1_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_ULT_S_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT1_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_D_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT1_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_M_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT1_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_IG,
+	    "Haswell", &haswell_gtt_driver },
+	{ PCI_DEVICE_ID_INTEL_HASWELL_CRW_S_GT2_PLUS_IG,
+	    "Haswell", &haswell_gtt_driver },
 	{ 0, NULL, NULL }
 };
 
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index d706bd0e9e8..4fbdceb6f77 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -160,7 +160,7 @@ static int __exit omap_rng_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 
 static int omap_rng_suspend(struct device *dev)
 {
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 4ec04a75473..b86eae9b77d 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;
+	unsigned long time = get_cycles() ^ jiffies;
 
-	desc = irq_to_desc(irq);
-
-	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;
 
@@ -637,13 +683,9 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 		goto out;
 
 	sample.jiffies = jiffies;
-
-	/* Use arch random value, fall back to cycles */
-	if (!arch_get_random_int(&sample.cycles))
-		sample.cycles = get_cycles();
-
+	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.
@@ -700,17 +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
@@ -742,7 +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) {
@@ -761,7 +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);
 	}
 }
@@ -820,13 +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
@@ -837,13 +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));
 
@@ -852,20 +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);
 
@@ -873,6 +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");
@@ -898,6 +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);
 
@@ -931,17 +1026,35 @@ 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)
 {
+	extract_entropy(&nonblocking_pool, buf, nbytes, 0, 0);
+}
+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;
 		
@@ -950,9 +1063,11 @@ void get_random_bytes(void *buf, int nbytes)
 		nbytes -= chunk;
 	}
 
-	extract_entropy(&nonblocking_pool, p, nbytes, 0, 0);
+	if (nbytes)
+		extract_entropy(&nonblocking_pool, p, nbytes, 0, 0);
 }
-EXPORT_SYMBOL(get_random_bytes);
+EXPORT_SYMBOL(get_random_bytes_arch);
+
 
 /*
  * init_std_data - initialize pool with system data
@@ -966,23 +1081,30 @@ EXPORT_SYMBOL(get_random_bytes);
 static void init_std_data(struct entropy_store *r)
 {
 	int i;
-	ktime_t now;
-	unsigned long flags;
+	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));
-	for (i = r->poolinfo->POOLBYTES; i > 0; i -= sizeof flags) {
-		if (!arch_get_random_long(&flags))
+	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, &flags, sizeof(flags));
+		mix_pool_bytes(r, &rv, sizeof(rv), NULL);
 	}
-	mix_pool_bytes(r, utsname(), sizeof(*(utsname())));
+	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);
@@ -992,24 +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)
 {
@@ -1117,7 +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();
 	}
 
@@ -1279,6 +1383,7 @@ static int proc_do_uuid(ctl_table *table, int write,
 }
 
 static int sysctl_poolsize = INPUT_POOL_WORDS * 32;
+extern ctl_table random_table[];
 ctl_table random_table[] = {
 	{
 		.procname	= "poolsize",
@@ -1344,7 +1449,7 @@ late_initcall(random_int_secret_init);
  * value is not cryptographically secure but for several uses the cost of
  * depleting entropy is too high
  */
-DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash);
+static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash);
 unsigned int get_random_int(void)
 {
 	__u32 *hash;
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 89682fa8801..c4be3519a58 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -807,6 +807,7 @@ module_param_string(hid, tpm_pnp_tbl[TIS_HID_USR_IDX].id,
 MODULE_PARM_DESC(hid, "Set additional specific HID for this driver to probe");
 #endif
 
+#ifdef CONFIG_PM_SLEEP
 static int tpm_tis_resume(struct device *dev)
 {
 	struct tpm_chip *chip = dev_get_drvdata(dev);
@@ -816,6 +817,7 @@ static int tpm_tis_resume(struct device *dev)
 
 	return tpm_pm_resume(dev);
 }
+#endif
 
 static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume);