Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto update from Herbert Xu:
 "Here is the crypto update for 4.6:

  API:
   - Convert remaining crypto_hash users to shash or ahash, also convert
     blkcipher/ablkcipher users to skcipher.
   - Remove crypto_hash interface.
   - Remove crypto_pcomp interface.
   - Add crypto engine for async cipher drivers.
   - Add akcipher documentation.
   - Add skcipher documentation.

  Algorithms:
   - Rename crypto/crc32 to avoid name clash with lib/crc32.
   - Fix bug in keywrap where we zero the wrong pointer.

  Drivers:
   - Support T5/M5, T7/M7 SPARC CPUs in n2 hwrng driver.
   - Add PIC32 hwrng driver.
   - Support BCM6368 in bcm63xx hwrng driver.
   - Pack structs for 32-bit compat users in qat.
   - Use crypto engine in omap-aes.
   - Add support for sama5d2x SoCs in atmel-sha.
   - Make atmel-sha available again.
   - Make sahara hashing available again.
   - Make ccp hashing available again.
   - Make sha1-mb available again.
   - Add support for multiple devices in ccp.
   - Improve DMA performance in caam.
   - Add hashing support to rockchip"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (116 commits)
  crypto: qat - remove redundant arbiter configuration
  crypto: ux500 - fix checks of error code returned by devm_ioremap_resource()
  crypto: atmel - fix checks of error code returned by devm_ioremap_resource()
  crypto: qat - Change the definition of icp_qat_uof_regtype
  hwrng: exynos - use __maybe_unused to hide pm functions
  crypto: ccp - Add abstraction for device-specific calls
  crypto: ccp - CCP versioning support
  crypto: ccp - Support for multiple CCPs
  crypto: ccp - Remove check for x86 family and model
  crypto: ccp - memset request context to zero during import
  lib/mpi: use "static inline" instead of "extern inline"
  lib/mpi: avoid assembler warning
  hwrng: bcm63xx - fix non device tree compatibility
  crypto: testmgr - allow rfc3686 aes-ctr variants in fips mode.
  crypto: qat - The AE id should be less than the maximal AE number
  lib/mpi: Endianness fix
  crypto: rockchip - add hash support for crypto engine in rk3288
  crypto: xts - fix compile errors
  crypto: doc - add skcipher API documentation
  crypto: doc - update AEAD AD handling
  ...

1 files changed, 148 insertions, 323 deletions

diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c
index 861bacc1bb94..336e5b780fcb 100644
--- a/drivers/crypto/ccp/ccp-dev.c
+++ b/drivers/crypto/ccp/ccp-dev.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -16,6 +16,8 @@
 #include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
+#include <linux/rwlock_types.h>
+#include <linux/types.h>
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/hw_random.h>
@@ -37,20 +39,107 @@ struct ccp_tasklet_data {
 	struct ccp_cmd *cmd;
 };
 
-static struct ccp_device *ccp_dev;
-static inline struct ccp_device *ccp_get_device(void)
+/* List of CCPs, CCP count, read-write access lock, and access functions
+ *
+ * Lock structure: get ccp_unit_lock for reading whenever we need to
+ * examine the CCP list. While holding it for reading we can acquire
+ * the RR lock to update the round-robin next-CCP pointer. The unit lock
+ * must be acquired before the RR lock.
+ *
+ * If the unit-lock is acquired for writing, we have total control over
+ * the list, so there's no value in getting the RR lock.
+ */
+static DEFINE_RWLOCK(ccp_unit_lock);
+static LIST_HEAD(ccp_units);
+
+/* Round-robin counter */
+static DEFINE_RWLOCK(ccp_rr_lock);
+static struct ccp_device *ccp_rr;
+
+/* Ever-increasing value to produce unique unit numbers */
+static atomic_t ccp_unit_ordinal;
+unsigned int ccp_increment_unit_ordinal(void)
 {
-	return ccp_dev;
+	return atomic_inc_return(&ccp_unit_ordinal);
 }
 
-static inline void ccp_add_device(struct ccp_device *ccp)
+/**
+ * ccp_add_device - add a CCP device to the list
+ *
+ * @ccp: ccp_device struct pointer
+ *
+ * Put this CCP on the unit list, which makes it available
+ * for use.
+ *
+ * Returns zero if a CCP device is present, -ENODEV otherwise.
+ */
+void ccp_add_device(struct ccp_device *ccp)
 {
-	ccp_dev = ccp;
+	unsigned long flags;
+
+	write_lock_irqsave(&ccp_unit_lock, flags);
+	list_add_tail(&ccp->entry, &ccp_units);
+	if (!ccp_rr)
+		/* We already have the list lock (we're first) so this
+		 * pointer can't change on us. Set its initial value.
+		 */
+		ccp_rr = ccp;
+	write_unlock_irqrestore(&ccp_unit_lock, flags);
 }
 
-static inline void ccp_del_device(struct ccp_device *ccp)
+/**
+ * ccp_del_device - remove a CCP device from the list
+ *
+ * @ccp: ccp_device struct pointer
+ *
+ * Remove this unit from the list of devices. If the next device
+ * up for use is this one, adjust the pointer. If this is the last
+ * device, NULL the pointer.
+ */
+void ccp_del_device(struct ccp_device *ccp)
 {
-	ccp_dev = NULL;
+	unsigned long flags;
+
+	write_lock_irqsave(&ccp_unit_lock, flags);
+	if (ccp_rr == ccp) {
+		/* ccp_unit_lock is read/write; any read access
+		 * will be suspended while we make changes to the
+		 * list and RR pointer.
+		 */
+		if (list_is_last(&ccp_rr->entry, &ccp_units))
+			ccp_rr = list_first_entry(&ccp_units, struct ccp_device,
+						  entry);
+		else
+			ccp_rr = list_next_entry(ccp_rr, entry);
+	}
+	list_del(&ccp->entry);
+	if (list_empty(&ccp_units))
+		ccp_rr = NULL;
+	write_unlock_irqrestore(&ccp_unit_lock, flags);
+}
+
+static struct ccp_device *ccp_get_device(void)
+{
+	unsigned long flags;
+	struct ccp_device *dp = NULL;
+
+	/* We round-robin through the unit list.
+	 * The (ccp_rr) pointer refers to the next unit to use.
+	 */
+	read_lock_irqsave(&ccp_unit_lock, flags);
+	if (!list_empty(&ccp_units)) {
+		write_lock_irqsave(&ccp_rr_lock, flags);
+		dp = ccp_rr;
+		if (list_is_last(&ccp_rr->entry, &ccp_units))
+			ccp_rr = list_first_entry(&ccp_units, struct ccp_device,
+						  entry);
+		else
+			ccp_rr = list_next_entry(ccp_rr, entry);
+		write_unlock_irqrestore(&ccp_rr_lock, flags);
+	}
+	read_unlock_irqrestore(&ccp_unit_lock, flags);
+
+	return dp;
 }
 
 /**
@@ -60,14 +149,41 @@ static inline void ccp_del_device(struct ccp_device *ccp)
  */
 int ccp_present(void)
 {
-	if (ccp_get_device())
-		return 0;
+	unsigned long flags;
+	int ret;
 
-	return -ENODEV;
+	read_lock_irqsave(&ccp_unit_lock, flags);
+	ret = list_empty(&ccp_units);
+	read_unlock_irqrestore(&ccp_unit_lock, flags);
+
+	return ret ? -ENODEV : 0;
 }
 EXPORT_SYMBOL_GPL(ccp_present);
 
 /**
+ * ccp_version - get the version of the CCP device
+ *
+ * Returns the version from the first unit on the list;
+ * otherwise a zero if no CCP device is present
+ */
+unsigned int ccp_version(void)
+{
+	struct ccp_device *dp;
+	unsigned long flags;
+	int ret = 0;
+
+	read_lock_irqsave(&ccp_unit_lock, flags);
+	if (!list_empty(&ccp_units)) {
+		dp = list_first_entry(&ccp_units, struct ccp_device, entry);
+		ret = dp->vdata->version;
+	}
+	read_unlock_irqrestore(&ccp_unit_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ccp_version);
+
+/**
  * ccp_enqueue_cmd - queue an operation for processing by the CCP
  *
  * @cmd: ccp_cmd struct to be processed
@@ -221,7 +337,12 @@ static void ccp_do_cmd_complete(unsigned long data)
 	complete(&tdata->completion);
 }
 
-static int ccp_cmd_queue_thread(void *data)
+/**
+ * ccp_cmd_queue_thread - create a kernel thread to manage a CCP queue
+ *
+ * @data: thread-specific data
+ */
+int ccp_cmd_queue_thread(void *data)
 {
 	struct ccp_cmd_queue *cmd_q = (struct ccp_cmd_queue *)data;
 	struct ccp_cmd *cmd;
@@ -257,35 +378,6 @@ static int ccp_cmd_queue_thread(void *data)
 	return 0;
 }
 
-static int ccp_trng_read(struct hwrng *rng, void *data, size_t max, bool wait)
-{
-	struct ccp_device *ccp = container_of(rng, struct ccp_device, hwrng);
-	u32 trng_value;
-	int len = min_t(int, sizeof(trng_value), max);
-
-	/*
-	 * Locking is provided by the caller so we can update device
-	 * hwrng-related fields safely
-	 */
-	trng_value = ioread32(ccp->io_regs + TRNG_OUT_REG);
-	if (!trng_value) {
-		/* Zero is returned if not data is available or if a
-		 * bad-entropy error is present. Assume an error if
-		 * we exceed TRNG_RETRIES reads of zero.
-		 */
-		if (ccp->hwrng_retries++ > TRNG_RETRIES)
-			return -EIO;
-
-		return 0;
-	}
-
-	/* Reset the counter and save the rng value */
-	ccp->hwrng_retries = 0;
-	memcpy(data, &trng_value, len);
-
-	return len;
-}
-
 /**
  * ccp_alloc_struct - allocate and initialize the ccp_device struct
  *
@@ -309,253 +401,11 @@ struct ccp_device *ccp_alloc_struct(struct device *dev)
 	ccp->ksb_count = KSB_COUNT;
 	ccp->ksb_start = 0;
 
-	return ccp;
-}
-
-/**
- * ccp_init - initialize the CCP device
- *
- * @ccp: ccp_device struct
- */
-int ccp_init(struct ccp_device *ccp)
-{
-	struct device *dev = ccp->dev;
-	struct ccp_cmd_queue *cmd_q;
-	struct dma_pool *dma_pool;
-	char dma_pool_name[MAX_DMAPOOL_NAME_LEN];
-	unsigned int qmr, qim, i;
-	int ret;
-
-	/* Find available queues */
-	qim = 0;
-	qmr = ioread32(ccp->io_regs + Q_MASK_REG);
-	for (i = 0; i < MAX_HW_QUEUES; i++) {
-		if (!(qmr & (1 << i)))
-			continue;
-
-		/* Allocate a dma pool for this queue */
-		snprintf(dma_pool_name, sizeof(dma_pool_name), "ccp_q%d", i);
-		dma_pool = dma_pool_create(dma_pool_name, dev,
-					   CCP_DMAPOOL_MAX_SIZE,
-					   CCP_DMAPOOL_ALIGN, 0);
-		if (!dma_pool) {
-			dev_err(dev, "unable to allocate dma pool\n");
-			ret = -ENOMEM;
-			goto e_pool;
-		}
-
-		cmd_q = &ccp->cmd_q[ccp->cmd_q_count];
-		ccp->cmd_q_count++;
-
-		cmd_q->ccp = ccp;
-		cmd_q->id = i;
-		cmd_q->dma_pool = dma_pool;
-
-		/* Reserve 2 KSB regions for the queue */
-		cmd_q->ksb_key = KSB_START + ccp->ksb_start++;
-		cmd_q->ksb_ctx = KSB_START + ccp->ksb_start++;
-		ccp->ksb_count -= 2;
-
-		/* Preset some register values and masks that are queue
-		 * number dependent
-		 */
-		cmd_q->reg_status = ccp->io_regs + CMD_Q_STATUS_BASE +
-				    (CMD_Q_STATUS_INCR * i);
-		cmd_q->reg_int_status = ccp->io_regs + CMD_Q_INT_STATUS_BASE +
-					(CMD_Q_STATUS_INCR * i);
-		cmd_q->int_ok = 1 << (i * 2);
-		cmd_q->int_err = 1 << ((i * 2) + 1);
-
-		cmd_q->free_slots = CMD_Q_DEPTH(ioread32(cmd_q->reg_status));
-
-		init_waitqueue_head(&cmd_q->int_queue);
-
-		/* Build queue interrupt mask (two interrupts per queue) */
-		qim |= cmd_q->int_ok | cmd_q->int_err;
+	ccp->ord = ccp_increment_unit_ordinal();
+	snprintf(ccp->name, MAX_CCP_NAME_LEN, "ccp-%u", ccp->ord);
+	snprintf(ccp->rngname, MAX_CCP_NAME_LEN, "ccp-%u-rng", ccp->ord);
 
-#ifdef CONFIG_ARM64
-		/* For arm64 set the recommended queue cache settings */
-		iowrite32(ccp->axcache, ccp->io_regs + CMD_Q_CACHE_BASE +
-			  (CMD_Q_CACHE_INC * i));
-#endif
-
-		dev_dbg(dev, "queue #%u available\n", i);
-	}
-	if (ccp->cmd_q_count == 0) {
-		dev_notice(dev, "no command queues available\n");
-		ret = -EIO;
-		goto e_pool;
-	}
-	dev_notice(dev, "%u command queues available\n", ccp->cmd_q_count);
-
-	/* Disable and clear interrupts until ready */
-	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-
-		ioread32(cmd_q->reg_int_status);
-		ioread32(cmd_q->reg_status);
-	}
-	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
-
-	/* Request an irq */
-	ret = ccp->get_irq(ccp);
-	if (ret) {
-		dev_err(dev, "unable to allocate an IRQ\n");
-		goto e_pool;
-	}
-
-	/* Initialize the queues used to wait for KSB space and suspend */
-	init_waitqueue_head(&ccp->ksb_queue);
-	init_waitqueue_head(&ccp->suspend_queue);
-
-	/* Create a kthread for each queue */
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		struct task_struct *kthread;
-
-		cmd_q = &ccp->cmd_q[i];
-
-		kthread = kthread_create(ccp_cmd_queue_thread, cmd_q,
-					 "ccp-q%u", cmd_q->id);
-		if (IS_ERR(kthread)) {
-			dev_err(dev, "error creating queue thread (%ld)\n",
-				PTR_ERR(kthread));
-			ret = PTR_ERR(kthread);
-			goto e_kthread;
-		}
-
-		cmd_q->kthread = kthread;
-		wake_up_process(kthread);
-	}
-
-	/* Register the RNG */
-	ccp->hwrng.name = "ccp-rng";
-	ccp->hwrng.read = ccp_trng_read;
-	ret = hwrng_register(&ccp->hwrng);
-	if (ret) {
-		dev_err(dev, "error registering hwrng (%d)\n", ret);
-		goto e_kthread;
-	}
-
-	/* Make the device struct available before enabling interrupts */
-	ccp_add_device(ccp);
-
-	/* Enable interrupts */
-	iowrite32(qim, ccp->io_regs + IRQ_MASK_REG);
-
-	return 0;
-
-e_kthread:
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		if (ccp->cmd_q[i].kthread)
-			kthread_stop(ccp->cmd_q[i].kthread);
-
-	ccp->free_irq(ccp);
-
-e_pool:
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		dma_pool_destroy(ccp->cmd_q[i].dma_pool);
-
-	return ret;
-}
-
-/**
- * ccp_destroy - tear down the CCP device
- *
- * @ccp: ccp_device struct
- */
-void ccp_destroy(struct ccp_device *ccp)
-{
-	struct ccp_cmd_queue *cmd_q;
-	struct ccp_cmd *cmd;
-	unsigned int qim, i;
-
-	/* Remove general access to the device struct */
-	ccp_del_device(ccp);
-
-	/* Unregister the RNG */
-	hwrng_unregister(&ccp->hwrng);
-
-	/* Stop the queue kthreads */
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		if (ccp->cmd_q[i].kthread)
-			kthread_stop(ccp->cmd_q[i].kthread);
-
-	/* Build queue interrupt mask (two interrupt masks per queue) */
-	qim = 0;
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-		qim |= cmd_q->int_ok | cmd_q->int_err;
-	}
-
-	/* Disable and clear interrupts */
-	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-
-		ioread32(cmd_q->reg_int_status);
-		ioread32(cmd_q->reg_status);
-	}
-	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
-
-	ccp->free_irq(ccp);
-
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		dma_pool_destroy(ccp->cmd_q[i].dma_pool);
-
-	/* Flush the cmd and backlog queue */
-	while (!list_empty(&ccp->cmd)) {
-		/* Invoke the callback directly with an error code */
-		cmd = list_first_entry(&ccp->cmd, struct ccp_cmd, entry);
-		list_del(&cmd->entry);
-		cmd->callback(cmd->data, -ENODEV);
-	}
-	while (!list_empty(&ccp->backlog)) {
-		/* Invoke the callback directly with an error code */
-		cmd = list_first_entry(&ccp->backlog, struct ccp_cmd, entry);
-		list_del(&cmd->entry);
-		cmd->callback(cmd->data, -ENODEV);
-	}
-}
-
-/**
- * ccp_irq_handler - handle interrupts generated by the CCP device
- *
- * @irq: the irq associated with the interrupt
- * @data: the data value supplied when the irq was created
- */
-irqreturn_t ccp_irq_handler(int irq, void *data)
-{
-	struct device *dev = data;
-	struct ccp_device *ccp = dev_get_drvdata(dev);
-	struct ccp_cmd_queue *cmd_q;
-	u32 q_int, status;
-	unsigned int i;
-
-	status = ioread32(ccp->io_regs + IRQ_STATUS_REG);
-
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-
-		q_int = status & (cmd_q->int_ok | cmd_q->int_err);
-		if (q_int) {
-			cmd_q->int_status = status;
-			cmd_q->q_status = ioread32(cmd_q->reg_status);
-			cmd_q->q_int_status = ioread32(cmd_q->reg_int_status);
-
-			/* On error, only save the first error value */
-			if ((q_int & cmd_q->int_err) && !cmd_q->cmd_error)
-				cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
-
-			cmd_q->int_rcvd = 1;
-
-			/* Acknowledge the interrupt and wake the kthread */
-			iowrite32(q_int, ccp->io_regs + IRQ_STATUS_REG);
-			wake_up_interruptible(&cmd_q->int_queue);
-		}
-	}
-
-	return IRQ_HANDLED;
+	return ccp;
 }
 
 #ifdef CONFIG_PM
@@ -577,41 +427,22 @@ bool ccp_queues_suspended(struct ccp_device *ccp)
 }
 #endif
 
-#ifdef CONFIG_X86
-static const struct x86_cpu_id ccp_support[] = {
-	{ X86_VENDOR_AMD, 22, },
-	{ },
-};
-#endif
-
 static int __init ccp_mod_init(void)
 {
 #ifdef CONFIG_X86
-	struct cpuinfo_x86 *cpuinfo = &boot_cpu_data;
 	int ret;
 
-	if (!x86_match_cpu(ccp_support))
-		return -ENODEV;
-
-	switch (cpuinfo->x86) {
-	case 22:
-		if ((cpuinfo->x86_model < 48) || (cpuinfo->x86_model > 63))
-			return -ENODEV;
-
-		ret = ccp_pci_init();
-		if (ret)
-			return ret;
-
-		/* Don't leave the driver loaded if init failed */
-		if (!ccp_get_device()) {
-			ccp_pci_exit();
-			return -ENODEV;
-		}
-
-		return 0;
+	ret = ccp_pci_init();
+	if (ret)
+		return ret;
 
-		break;
+	/* Don't leave the driver loaded if init failed */
+	if (ccp_present() != 0) {
+		ccp_pci_exit();
+		return -ENODEV;
 	}
+
+	return 0;
 #endif
 
 #ifdef CONFIG_ARM64
@@ -622,7 +453,7 @@ static int __init ccp_mod_init(void)
 		return ret;
 
 	/* Don't leave the driver loaded if init failed */
-	if (!ccp_get_device()) {
+	if (ccp_present() != 0) {
 		ccp_platform_exit();
 		return -ENODEV;
 	}
@@ -636,13 +467,7 @@ static int __init ccp_mod_init(void)
 static void __exit ccp_mod_exit(void)
 {
 #ifdef CONFIG_X86
-	struct cpuinfo_x86 *cpuinfo = &boot_cpu_data;
-
-	switch (cpuinfo->x86) {
-	case 22:
-		ccp_pci_exit();
-		break;
-	}
+	ccp_pci_exit();
 #endif
 
 #ifdef CONFIG_ARM64