Merge tag 'powerpc-4.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Nothing really major this release, despite quite a lot of activity.
  Just lots of things all over the place.

  Some things of note include:

   - Access via perf to a new type of PMU (IMC) on Power9, which can
     count both core events as well as nest unit events (Memory
     controller etc).

   - Optimisations to the radix MMU TLB flushing, mostly to avoid
     unnecessary Page Walk Cache (PWC) flushes when the structure of the
     tree is not changing.

   - Reworks/cleanups of do_page_fault() to modernise it and bring it
     closer to other architectures where possible.

   - Rework of our page table walking so that THP updates only need to
     send IPIs to CPUs where the affected mm has run, rather than all
     CPUs.

   - The size of our vmalloc area is increased to 56T on 64-bit hash MMU
     systems. This avoids problems with the percpu allocator on systems
     with very sparse NUMA layouts.

   - STRICT_KERNEL_RWX support on PPC32.

   - A new sched domain topology for Power9, to capture the fact that
     pairs of cores may share an L2 cache.

   - Power9 support for VAS, which is a new mechanism for accessing
     coprocessors, and initial support for using it with the NX
     compression accelerator.

   - Major work on the instruction emulation support, adding support for
     many new instructions, and reworking it so it can be used to
     implement the emulation needed to fixup alignment faults.

   - Support for guests under PowerVM to use the Power9 XIVE interrupt
     controller.

  And probably that many things again that are almost as interesting,
  but I had to keep the list short. Plus the usual fixes and cleanups as
  always.

  Thanks to: Alexey Kardashevskiy, Alistair Popple, Andreas Schwab,
  Aneesh Kumar K.V, Anju T Sudhakar, Arvind Yadav, Balbir Singh,
  Benjamin Herrenschmidt, Bhumika Goyal, Breno Leitao, Bryant G. Ly,
  Christophe Leroy, Cédric Le Goater, Dan Carpenter, Dou Liyang,
  Frederic Barrat, Gautham R. Shenoy, Geliang Tang, Geoff Levand, Hannes
  Reinecke, Haren Myneni, Ivan Mikhaylov, John Allen, Julia Lawall,
  LABBE Corentin, Laurentiu Tudor, Madhavan Srinivasan, Markus Elfring,
  Masahiro Yamada, Matt Brown, Michael Neuling, Murilo Opsfelder Araujo,
  Nathan Fontenot, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran,
  Paul Mackerras, Rashmica Gupta, Rob Herring, Rui Teng, Sam Bobroff,
  Santosh Sivaraj, Scott Wood, Shilpasri G Bhat, Sukadev Bhattiprolu,
  Suraj Jitindar Singh, Tobin C. Harding, Victor Aoqui"

* tag 'powerpc-4.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (321 commits)
  powerpc/xive: Fix section __init warning
  powerpc: Fix kernel crash in emulation of vector loads and stores
  powerpc/xive: improve debugging macros
  powerpc/xive: add XIVE Exploitation Mode to CAS
  powerpc/xive: introduce H_INT_ESB hcall
  powerpc/xive: add the HW IRQ number under xive_irq_data
  powerpc/xive: introduce xive_esb_write()
  powerpc/xive: rename xive_poke_esb() in xive_esb_read()
  powerpc/xive: guest exploitation of the XIVE interrupt controller
  powerpc/xive: introduce a common routine xive_queue_page_alloc()
  powerpc/sstep: Avoid used uninitialized error
  axonram: Return directly after a failed kzalloc() in axon_ram_probe()
  axonram: Improve a size determination in axon_ram_probe()
  axonram: Delete an error message for a failed memory allocation in axon_ram_probe()
  powerpc/powernv/npu: Move tlb flush before launching ATSD
  powerpc/macintosh: constify wf_sensor_ops structures
  powerpc/iommu: Use permission-specific DEVICE_ATTR variants
  powerpc/eeh: Delete an error out of memory message at init time
  powerpc/mm: Use seq_putc() in two functions
  macintosh: Convert to using %pOF instead of full_name
  ...

4 files changed, 474 insertions, 56 deletions

diff --git a/drivers/crypto/nx/Kconfig b/drivers/crypto/nx/Kconfig
index ad7552a6998c..cd5dda9c48f4 100644
--- a/drivers/crypto/nx/Kconfig
+++ b/drivers/crypto/nx/Kconfig
@@ -38,6 +38,7 @@ config CRYPTO_DEV_NX_COMPRESS_PSERIES
 config CRYPTO_DEV_NX_COMPRESS_POWERNV
 	tristate "Compression acceleration support on PowerNV platform"
 	depends on PPC_POWERNV
+	depends on PPC_VAS
 	default y
 	help
 	  Support for PowerPC Nest (NX) compression acceleration. This
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
index 1710f80a09ec..874ddf5e9087 100644
--- a/drivers/crypto/nx/nx-842-powernv.c
+++ b/drivers/crypto/nx/nx-842-powernv.c
@@ -22,6 +22,8 @@
 
 #include <asm/prom.h>
 #include <asm/icswx.h>
+#include <asm/vas.h>
+#include <asm/reg.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
@@ -31,6 +33,9 @@ MODULE_ALIAS_CRYPTO("842-nx");
 
 #define WORKMEM_ALIGN	(CRB_ALIGN)
 #define CSB_WAIT_MAX	(5000) /* ms */
+#define VAS_RETRIES	(10)
+/* # of requests allowed per RxFIFO at a time. 0 for unlimited */
+#define MAX_CREDITS_PER_RXFIFO	(1024)
 
 struct nx842_workmem {
 	/* Below fields must be properly aligned */
@@ -41,19 +46,34 @@ struct nx842_workmem {
 
 	ktime_t start;
 
+	struct vas_window *txwin;	/* Used with VAS function */
 	char padding[WORKMEM_ALIGN]; /* unused, to allow alignment */
 } __packed __aligned(WORKMEM_ALIGN);
 
 struct nx842_coproc {
 	unsigned int chip_id;
 	unsigned int ct;
-	unsigned int ci;
+	unsigned int ci;	/* Coprocessor instance, used with icswx */
+	struct {
+		struct vas_window *rxwin;
+		int id;
+	} vas;
 	struct list_head list;
 };
 
+/*
+ * Send the request to NX engine on the chip for the corresponding CPU
+ * where the process is executing. Use with VAS function.
+ */
+static DEFINE_PER_CPU(struct nx842_coproc *, coproc_inst);
+
 /* no cpu hotplug on powernv, so this list never changes after init */
 static LIST_HEAD(nx842_coprocs);
-static unsigned int nx842_ct;
+static unsigned int nx842_ct;	/* used in icswx function */
+
+static int (*nx842_powernv_exec)(const unsigned char *in,
+				unsigned int inlen, unsigned char *out,
+				unsigned int *outlenp, void *workmem, int fc);
 
 /**
  * setup_indirect_dde - Setup an indirect DDE
@@ -238,6 +258,13 @@ static int wait_for_csb(struct nx842_workmem *wmem,
 	case CSB_CC_TEMPL_OVERFLOW:
 		CSB_ERR(csb, "Compressed data template shows data past end");
 		return -EINVAL;
+	case CSB_CC_EXCEED_BYTE_COUNT:	/* P9 or later */
+		/*
+		 * DDE byte count exceeds the limit specified in Maximum
+		 * byte count register.
+		 */
+		CSB_ERR(csb, "DDE byte count exceeds the limit");
+		return -EINVAL;
 
 	/* these should not happen */
 	case CSB_CC_INVALID_ALIGN:
@@ -279,9 +306,17 @@ static int wait_for_csb(struct nx842_workmem *wmem,
 		CSB_ERR(csb, "Too many DDEs in DDL");
 		return -EINVAL;
 	case CSB_CC_TRANSPORT:
+	case CSB_CC_INVALID_CRB:	/* P9 or later */
 		/* shouldn't happen, we setup CRB correctly */
 		CSB_ERR(csb, "Invalid CRB");
 		return -EINVAL;
+	case CSB_CC_INVALID_DDE:	/* P9 or later */
+		/*
+		 * shouldn't happen, setup_direct/indirect_dde creates
+		 * DDE right
+		 */
+		CSB_ERR(csb, "Invalid DDE");
+		return -EINVAL;
 	case CSB_CC_SEGMENTED_DDL:
 		/* shouldn't happen, setup_ddl creates DDL right */
 		CSB_ERR(csb, "Segmented DDL error");
@@ -325,6 +360,9 @@ static int wait_for_csb(struct nx842_workmem *wmem,
 	case CSB_CC_HW:
 		CSB_ERR(csb, "Correctable hardware error");
 		return -EPROTO;
+	case CSB_CC_HW_EXPIRED_TIMER:	/* P9 or later */
+		CSB_ERR(csb, "Job did not finish within allowed time");
+		return -EPROTO;
 
 	default:
 		CSB_ERR(csb, "Invalid CC %d", csb->cc);
@@ -353,8 +391,42 @@ static int wait_for_csb(struct nx842_workmem *wmem,
 	return 0;
 }
 
+static int nx842_config_crb(const unsigned char *in, unsigned int inlen,
+			unsigned char *out, unsigned int outlen,
+			struct nx842_workmem *wmem)
+{
+	struct coprocessor_request_block *crb;
+	struct coprocessor_status_block *csb;
+	u64 csb_addr;
+	int ret;
+
+	crb = &wmem->crb;
+	csb = &crb->csb;
+
+	/* Clear any previous values */
+	memset(crb, 0, sizeof(*crb));
+
+	/* set up DDLs */
+	ret = setup_ddl(&crb->source, wmem->ddl_in,
+			(unsigned char *)in, inlen, true);
+	if (ret)
+		return ret;
+
+	ret = setup_ddl(&crb->target, wmem->ddl_out,
+			out, outlen, false);
+	if (ret)
+		return ret;
+
+	/* set up CRB's CSB addr */
+	csb_addr = nx842_get_pa(csb) & CRB_CSB_ADDRESS;
+	csb_addr |= CRB_CSB_AT; /* Addrs are phys */
+	crb->csb_addr = cpu_to_be64(csb_addr);
+
+	return 0;
+}
+
 /**
- * nx842_powernv_function - compress/decompress data using the 842 algorithm
+ * nx842_exec_icswx - compress/decompress data using the 842 algorithm
  *
  * (De)compression provided by the NX842 coprocessor on IBM PowerNV systems.
  * This compresses or decompresses the provided input buffer into the provided
@@ -384,7 +456,7 @@ static int wait_for_csb(struct nx842_workmem *wmem,
  *   -ETIMEDOUT	hardware did not complete operation in reasonable time
  *   -EINTR	operation was aborted
  */
-static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
+static int nx842_exec_icswx(const unsigned char *in, unsigned int inlen,
 				  unsigned char *out, unsigned int *outlenp,
 				  void *workmem, int fc)
 {
@@ -392,7 +464,6 @@ static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
 	struct coprocessor_status_block *csb;
 	struct nx842_workmem *wmem;
 	int ret;
-	u64 csb_addr;
 	u32 ccw;
 	unsigned int outlen = *outlenp;
 
@@ -406,32 +477,18 @@ static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
 		return -ENODEV;
 	}
 
-	crb = &wmem->crb;
-	csb = &crb->csb;
-
-	/* Clear any previous values */
-	memset(crb, 0, sizeof(*crb));
-
-	/* set up DDLs */
-	ret = setup_ddl(&crb->source, wmem->ddl_in,
-			(unsigned char *)in, inlen, true);
-	if (ret)
-		return ret;
-	ret = setup_ddl(&crb->target, wmem->ddl_out,
-			out, outlen, false);
+	ret = nx842_config_crb(in, inlen, out, outlen, wmem);
 	if (ret)
 		return ret;
 
+	crb = &wmem->crb;
+	csb = &crb->csb;
+
 	/* set up CCW */
 	ccw = 0;
-	ccw = SET_FIELD(ccw, CCW_CT, nx842_ct);
-	ccw = SET_FIELD(ccw, CCW_CI_842, 0); /* use 0 for hw auto-selection */
-	ccw = SET_FIELD(ccw, CCW_FC_842, fc);
-
-	/* set up CRB's CSB addr */
-	csb_addr = nx842_get_pa(csb) & CRB_CSB_ADDRESS;
-	csb_addr |= CRB_CSB_AT; /* Addrs are phys */
-	crb->csb_addr = cpu_to_be64(csb_addr);
+	ccw = SET_FIELD(CCW_CT, ccw, nx842_ct);
+	ccw = SET_FIELD(CCW_CI_842, ccw, 0); /* use 0 for hw auto-selection */
+	ccw = SET_FIELD(CCW_FC_842, ccw, fc);
 
 	wmem->start = ktime_get();
 
@@ -471,6 +528,104 @@ static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
 }
 
 /**
+ * nx842_exec_vas - compress/decompress data using the 842 algorithm
+ *
+ * (De)compression provided by the NX842 coprocessor on IBM PowerNV systems.
+ * This compresses or decompresses the provided input buffer into the provided
+ * output buffer.
+ *
+ * Upon return from this function @outlen contains the length of the
+ * output data.  If there is an error then @outlen will be 0 and an
+ * error will be specified by the return code from this function.
+ *
+ * The @workmem buffer should only be used by one function call at a time.
+ *
+ * @in: input buffer pointer
+ * @inlen: input buffer size
+ * @out: output buffer pointer
+ * @outlenp: output buffer size pointer
+ * @workmem: working memory buffer pointer, size determined by
+ *           nx842_powernv_driver.workmem_size
+ * @fc: function code, see CCW Function Codes in nx-842.h
+ *
+ * Returns:
+ *   0		Success, output of length @outlenp stored in the buffer
+ *		at @out
+ *   -ENODEV	Hardware unavailable
+ *   -ENOSPC	Output buffer is to small
+ *   -EMSGSIZE	Input buffer too large
+ *   -EINVAL	buffer constraints do not fix nx842_constraints
+ *   -EPROTO	hardware error during operation
+ *   -ETIMEDOUT	hardware did not complete operation in reasonable time
+ *   -EINTR	operation was aborted
+ */
+static int nx842_exec_vas(const unsigned char *in, unsigned int inlen,
+				  unsigned char *out, unsigned int *outlenp,
+				  void *workmem, int fc)
+{
+	struct coprocessor_request_block *crb;
+	struct coprocessor_status_block *csb;
+	struct nx842_workmem *wmem;
+	struct vas_window *txwin;
+	int ret, i = 0;
+	u32 ccw;
+	unsigned int outlen = *outlenp;
+
+	wmem = PTR_ALIGN(workmem, WORKMEM_ALIGN);
+
+	*outlenp = 0;
+
+	crb = &wmem->crb;
+	csb = &crb->csb;
+
+	ret = nx842_config_crb(in, inlen, out, outlen, wmem);
+	if (ret)
+		return ret;
+
+	ccw = 0;
+	ccw = SET_FIELD(CCW_FC_842, ccw, fc);
+	crb->ccw = cpu_to_be32(ccw);
+
+	txwin = wmem->txwin;
+	/* shoudn't happen, we don't load without a coproc */
+	if (!txwin) {
+		pr_err_ratelimited("NX-842 coprocessor is not available");
+		return -ENODEV;
+	}
+
+	do {
+		wmem->start = ktime_get();
+		preempt_disable();
+		/*
+		 * VAS copy CRB into L2 cache. Refer <asm/vas.h>.
+		 * @crb and @offset.
+		 */
+		vas_copy_crb(crb, 0);
+
+		/*
+		 * VAS paste previously copied CRB to NX.
+		 * @txwin, @offset and @last (must be true).
+		 */
+		ret = vas_paste_crb(txwin, 0, 1);
+		preempt_enable();
+		/*
+		 * Retry copy/paste function for VAS failures.
+		 */
+	} while (ret && (i++ < VAS_RETRIES));
+
+	if (ret) {
+		pr_err_ratelimited("VAS copy/paste failed\n");
+		return ret;
+	}
+
+	ret = wait_for_csb(wmem, csb);
+	if (!ret)
+		*outlenp = be32_to_cpu(csb->count);
+
+	return ret;
+}
+
+/**
  * nx842_powernv_compress - Compress data using the 842 algorithm
  *
  * Compression provided by the NX842 coprocessor on IBM PowerNV systems.
@@ -488,13 +643,13 @@ static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
  * @workmem: working memory buffer pointer, size determined by
  *           nx842_powernv_driver.workmem_size
  *
- * Returns: see @nx842_powernv_function()
+ * Returns: see @nx842_powernv_exec()
  */
 static int nx842_powernv_compress(const unsigned char *in, unsigned int inlen,
 				  unsigned char *out, unsigned int *outlenp,
 				  void *wmem)
 {
-	return nx842_powernv_function(in, inlen, out, outlenp,
+	return nx842_powernv_exec(in, inlen, out, outlenp,
 				      wmem, CCW_FC_842_COMP_CRC);
 }
 
@@ -516,16 +671,219 @@ static int nx842_powernv_compress(const unsigned char *in, unsigned int inlen,
  * @workmem: working memory buffer pointer, size determined by
  *           nx842_powernv_driver.workmem_size
  *
- * Returns: see @nx842_powernv_function()
+ * Returns: see @nx842_powernv_exec()
  */
 static int nx842_powernv_decompress(const unsigned char *in, unsigned int inlen,
 				    unsigned char *out, unsigned int *outlenp,
 				    void *wmem)
 {
-	return nx842_powernv_function(in, inlen, out, outlenp,
+	return nx842_powernv_exec(in, inlen, out, outlenp,
 				      wmem, CCW_FC_842_DECOMP_CRC);
 }
 
+static inline void nx842_add_coprocs_list(struct nx842_coproc *coproc,
+					int chipid)
+{
+	coproc->chip_id = chipid;
+	INIT_LIST_HEAD(&coproc->list);
+	list_add(&coproc->list, &nx842_coprocs);
+}
+
+/*
+ * Identify chip ID for each CPU and save coprocesor adddress for the
+ * corresponding NX engine in percpu coproc_inst.
+ * coproc_inst is used in crypto_init to open send window on the NX instance
+ * for the corresponding CPU / chip where the open request is executed.
+ */
+static void nx842_set_per_cpu_coproc(struct nx842_coproc *coproc)
+{
+	unsigned int i, chip_id;
+
+	for_each_possible_cpu(i) {
+		chip_id = cpu_to_chip_id(i);
+
+		if (coproc->chip_id == chip_id)
+			per_cpu(coproc_inst, i) = coproc;
+	}
+}
+
+
+static struct vas_window *nx842_alloc_txwin(struct nx842_coproc *coproc)
+{
+	struct vas_window *txwin = NULL;
+	struct vas_tx_win_attr txattr;
+
+	/*
+	 * Kernel requests will be high priority. So open send
+	 * windows only for high priority RxFIFO entries.
+	 */
+	vas_init_tx_win_attr(&txattr, coproc->ct);
+	txattr.lpid = 0;	/* lpid is 0 for kernel requests */
+	txattr.pid = 0;		/* pid is 0 for kernel requests */
+
+	/*
+	 * Open a VAS send window which is used to send request to NX.
+	 */
+	txwin = vas_tx_win_open(coproc->vas.id, coproc->ct, &txattr);
+	if (IS_ERR(txwin)) {
+		pr_err("ibm,nx-842: Can not open TX window: %ld\n",
+				PTR_ERR(txwin));
+		return NULL;
+	}
+
+	return txwin;
+}
+
+static int __init vas_cfg_coproc_info(struct device_node *dn, int chip_id,
+					int vasid)
+{
+	struct vas_window *rxwin = NULL;
+	struct vas_rx_win_attr rxattr;
+	struct nx842_coproc *coproc;
+	u32 lpid, pid, tid, fifo_size;
+	u64 rx_fifo;
+	const char *priority;
+	int ret;
+
+	ret = of_property_read_u64(dn, "rx-fifo-address", &rx_fifo);
+	if (ret) {
+		pr_err("Missing rx-fifo-address property\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(dn, "rx-fifo-size", &fifo_size);
+	if (ret) {
+		pr_err("Missing rx-fifo-size property\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(dn, "lpid", &lpid);
+	if (ret) {
+		pr_err("Missing lpid property\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(dn, "pid", &pid);
+	if (ret) {
+		pr_err("Missing pid property\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(dn, "tid", &tid);
+	if (ret) {
+		pr_err("Missing tid property\n");
+		return ret;
+	}
+
+	ret = of_property_read_string(dn, "priority", &priority);
+	if (ret) {
+		pr_err("Missing priority property\n");
+		return ret;
+	}
+
+	coproc = kzalloc(sizeof(*coproc), GFP_KERNEL);
+	if (!coproc)
+		return -ENOMEM;
+
+	if (!strcmp(priority, "High"))
+		coproc->ct = VAS_COP_TYPE_842_HIPRI;
+	else if (!strcmp(priority, "Normal"))
+		coproc->ct = VAS_COP_TYPE_842;
+	else {
+		pr_err("Invalid RxFIFO priority value\n");
+		ret =  -EINVAL;
+		goto err_out;
+	}
+
+	vas_init_rx_win_attr(&rxattr, coproc->ct);
+	rxattr.rx_fifo = (void *)rx_fifo;
+	rxattr.rx_fifo_size = fifo_size;
+	rxattr.lnotify_lpid = lpid;
+	rxattr.lnotify_pid = pid;
+	rxattr.lnotify_tid = tid;
+	rxattr.wcreds_max = MAX_CREDITS_PER_RXFIFO;
+
+	/*
+	 * Open a VAS receice window which is used to configure RxFIFO
+	 * for NX.
+	 */
+	rxwin = vas_rx_win_open(vasid, coproc->ct, &rxattr);
+	if (IS_ERR(rxwin)) {
+		ret = PTR_ERR(rxwin);
+		pr_err("setting RxFIFO with VAS failed: %d\n",
+			ret);
+		goto err_out;
+	}
+
+	coproc->vas.rxwin = rxwin;
+	coproc->vas.id = vasid;
+	nx842_add_coprocs_list(coproc, chip_id);
+
+	/*
+	 * Kernel requests use only high priority FIFOs. So save coproc
+	 * info in percpu coproc_inst which will be used to open send
+	 * windows for crypto open requests later.
+	 */
+	if (coproc->ct == VAS_COP_TYPE_842_HIPRI)
+		nx842_set_per_cpu_coproc(coproc);
+
+	return 0;
+
+err_out:
+	kfree(coproc);
+	return ret;
+}
+
+
+static int __init nx842_powernv_probe_vas(struct device_node *pn)
+{
+	struct device_node *dn;
+	int chip_id, vasid, ret = 0;
+	int nx_fifo_found = 0;
+
+	chip_id = of_get_ibm_chip_id(pn);
+	if (chip_id < 0) {
+		pr_err("ibm,chip-id missing\n");
+		return -EINVAL;
+	}
+
+	for_each_compatible_node(dn, NULL, "ibm,power9-vas-x") {
+		if (of_get_ibm_chip_id(dn) == chip_id)
+			break;
+	}
+
+	if (!dn) {
+		pr_err("Missing VAS device node\n");
+		return -EINVAL;
+	}
+
+	if (of_property_read_u32(dn, "ibm,vas-id", &vasid)) {
+		pr_err("Missing ibm,vas-id device property\n");
+		of_node_put(dn);
+		return -EINVAL;
+	}
+
+	of_node_put(dn);
+
+	for_each_child_of_node(pn, dn) {
+		if (of_device_is_compatible(dn, "ibm,p9-nx-842")) {
+			ret = vas_cfg_coproc_info(dn, chip_id, vasid);
+			if (ret) {
+				of_node_put(dn);
+				return ret;
+			}
+			nx_fifo_found++;
+		}
+	}
+
+	if (!nx_fifo_found) {
+		pr_err("NX842 FIFO nodes are missing\n");
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
 static int __init nx842_powernv_probe(struct device_node *dn)
 {
 	struct nx842_coproc *coproc;
@@ -552,11 +910,9 @@ static int __init nx842_powernv_probe(struct device_node *dn)
 	if (!coproc)
 		return -ENOMEM;
 
-	coproc->chip_id = chip_id;
 	coproc->ct = ct;
 	coproc->ci = ci;
-	INIT_LIST_HEAD(&coproc->list);
-	list_add(&coproc->list, &nx842_coprocs);
+	nx842_add_coprocs_list(coproc, chip_id);
 
 	pr_info("coprocessor found on chip %d, CT %d CI %d\n", chip_id, ct, ci);
 
@@ -569,6 +925,19 @@ static int __init nx842_powernv_probe(struct device_node *dn)
 	return 0;
 }
 
+static void nx842_delete_coprocs(void)
+{
+	struct nx842_coproc *coproc, *n;
+
+	list_for_each_entry_safe(coproc, n, &nx842_coprocs, list) {
+		if (coproc->vas.rxwin)
+			vas_win_close(coproc->vas.rxwin);
+
+		list_del(&coproc->list);
+		kfree(coproc);
+	}
+}
+
 static struct nx842_constraints nx842_powernv_constraints = {
 	.alignment =	DDE_BUFFER_ALIGN,
 	.multiple =	DDE_BUFFER_LAST_MULT,
@@ -585,6 +954,46 @@ static struct nx842_driver nx842_powernv_driver = {
 	.decompress =	nx842_powernv_decompress,
 };
 
+static int nx842_powernv_crypto_init_vas(struct crypto_tfm *tfm)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct nx842_workmem *wmem;
+	struct nx842_coproc *coproc;
+	int ret;
+
+	ret = nx842_crypto_init(tfm, &nx842_powernv_driver);
+
+	if (ret)
+		return ret;
+
+	wmem = PTR_ALIGN((struct nx842_workmem *)ctx->wmem, WORKMEM_ALIGN);
+	coproc = per_cpu(coproc_inst, smp_processor_id());
+
+	ret = -EINVAL;
+	if (coproc && coproc->vas.rxwin) {
+		wmem->txwin = nx842_alloc_txwin(coproc);
+		if (!IS_ERR(wmem->txwin))
+			return 0;
+
+		ret = PTR_ERR(wmem->txwin);
+	}
+
+	return ret;
+}
+
+void nx842_powernv_crypto_exit_vas(struct crypto_tfm *tfm)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct nx842_workmem *wmem;
+
+	wmem = PTR_ALIGN((struct nx842_workmem *)ctx->wmem, WORKMEM_ALIGN);
+
+	if (wmem && wmem->txwin)
+		vas_win_close(wmem->txwin);
+
+	nx842_crypto_exit(tfm);
+}
+
 static int nx842_powernv_crypto_init(struct crypto_tfm *tfm)
 {
 	return nx842_crypto_init(tfm, &nx842_powernv_driver);
@@ -618,21 +1027,31 @@ static __init int nx842_powernv_init(void)
 	BUILD_BUG_ON(DDE_BUFFER_ALIGN % DDE_BUFFER_SIZE_MULT);
 	BUILD_BUG_ON(DDE_BUFFER_SIZE_MULT % DDE_BUFFER_LAST_MULT);
 
-	for_each_compatible_node(dn, NULL, "ibm,power-nx")
-		nx842_powernv_probe(dn);
+	for_each_compatible_node(dn, NULL, "ibm,power9-nx") {
+		ret = nx842_powernv_probe_vas(dn);
+		if (ret) {
+			nx842_delete_coprocs();
+			return ret;
+		}
+	}
 
-	if (!nx842_ct)
-		return -ENODEV;
+	if (list_empty(&nx842_coprocs)) {
+		for_each_compatible_node(dn, NULL, "ibm,power-nx")
+			nx842_powernv_probe(dn);
 
-	ret = crypto_register_alg(&nx842_powernv_alg);
-	if (ret) {
-		struct nx842_coproc *coproc, *n;
+		if (!nx842_ct)
+			return -ENODEV;
 
-		list_for_each_entry_safe(coproc, n, &nx842_coprocs, list) {
-			list_del(&coproc->list);
-			kfree(coproc);
-		}
+		nx842_powernv_exec = nx842_exec_icswx;
+	} else {
+		nx842_powernv_exec = nx842_exec_vas;
+		nx842_powernv_alg.cra_init = nx842_powernv_crypto_init_vas;
+		nx842_powernv_alg.cra_exit = nx842_powernv_crypto_exit_vas;
+	}
 
+	ret = crypto_register_alg(&nx842_powernv_alg);
+	if (ret) {
+		nx842_delete_coprocs();
 		return ret;
 	}
 
@@ -642,13 +1061,8 @@ module_init(nx842_powernv_init);
 
 static void __exit nx842_powernv_exit(void)
 {
-	struct nx842_coproc *coproc, *n;
-
 	crypto_unregister_alg(&nx842_powernv_alg);
 
-	list_for_each_entry_safe(coproc, n, &nx842_coprocs, list) {
-		list_del(&coproc->list);
-		kfree(coproc);
-	}
+	nx842_delete_coprocs();
 }
 module_exit(nx842_powernv_exit);
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index d94e25df503b..da3cb8c35ec7 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -116,7 +116,7 @@ int nx842_crypto_init(struct crypto_tfm *tfm, struct nx842_driver *driver)
 
 	spin_lock_init(&ctx->lock);
 	ctx->driver = driver;
-	ctx->wmem = kmalloc(driver->workmem_size, GFP_KERNEL);
+	ctx->wmem = kzalloc(driver->workmem_size, GFP_KERNEL);
 	ctx->sbounce = (u8 *)__get_free_pages(GFP_KERNEL, BOUNCE_BUFFER_ORDER);
 	ctx->dbounce = (u8 *)__get_free_pages(GFP_KERNEL, BOUNCE_BUFFER_ORDER);
 	if (!ctx->wmem || !ctx->sbounce || !ctx->dbounce) {
diff --git a/drivers/crypto/nx/nx-842.h b/drivers/crypto/nx/nx-842.h
index a4eee3bba937..bb2f31792683 100644
--- a/drivers/crypto/nx/nx-842.h
+++ b/drivers/crypto/nx/nx-842.h
@@ -76,9 +76,17 @@
 #define CSB_CC_DECRYPT_OVERFLOW	(64)
 /* asym crypt codes */
 #define CSB_CC_MINV_OVERFLOW	(128)
+/*
+ * HW error - Job did not finish in the maximum time allowed.
+ * Job terminated.
+ */
+#define CSB_CC_HW_EXPIRED_TIMER		(224)
 /* These are reserved for hypervisor use */
 #define CSB_CC_HYP_RESERVE_START	(240)
 #define CSB_CC_HYP_RESERVE_END		(253)
+#define CSB_CC_HYP_RESERVE_P9_END	(251)
+/* No valid interrupt server (P9 or later). */
+#define CSB_CC_HYP_RESERVE_NO_INTR_SERVER	(252)
 #define CSB_CC_HYP_NO_HW		(254)
 #define CSB_CC_HYP_HANG_ABORTED		(255)
 
@@ -100,11 +108,6 @@ static inline unsigned long nx842_get_pa(void *addr)
 	return page_to_phys(vmalloc_to_page(addr)) + offset_in_page(addr);
 }
 
-/* Get/Set bit fields */
-#define MASK_LSH(m)		(__builtin_ffsl(m) - 1)
-#define GET_FIELD(v, m)		(((v) & (m)) >> MASK_LSH(m))
-#define SET_FIELD(v, m, val)	(((v) & ~(m)) | (((val) << MASK_LSH(m)) & (m)))
-
 /**
  * This provides the driver's constraints.  Different nx842 implementations
  * may have varying requirements.  The constraints are: