Merge tag 'powerpc-5.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - A big series refactoring parts of our KVM code, and converting some
   to C.

 - Support for ARCH_HAS_SET_MEMORY, and ARCH_HAS_STRICT_MODULE_RWX on
   some CPUs.

 - Support for the Microwatt soft-core.

 - Optimisations to our interrupt return path on 64-bit.

 - Support for userspace access to the NX GZIP accelerator on PowerVM on
   Power10.

 - Enable KUAP and KUEP by default on 32-bit Book3S CPUs.

 - Other smaller features, fixes & cleanups.

Thanks to: Andy Shevchenko, Aneesh Kumar K.V, Arnd Bergmann, Athira
Rajeev, Baokun Li, Benjamin Herrenschmidt, Bharata B Rao, Christophe
Leroy, Daniel Axtens, Daniel Henrique Barboza, Finn Thain, Geoff Levand,
Haren Myneni, Jason Wang, Jiapeng Chong, Joel Stanley, Jordan Niethe,
Kajol Jain, Nathan Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas
Piggin, Nick Desaulniers, Paul Mackerras, Russell Currey, Sathvika
Vasireddy, Shaokun Zhang, Stephen Rothwell, Sudeep Holla, Suraj Jitindar
Singh, Tom Rix, Vaibhav Jain, YueHaibing, Zhang Jianhua, and Zhen Lei.

* tag 'powerpc-5.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (218 commits)
  powerpc: Only build restart_table.c for 64s
  powerpc/64s: move ret_from_fork etc above __end_soft_masked
  powerpc/64s/interrupt: clean up interrupt return labels
  powerpc/64/interrupt: add missing kprobe annotations on interrupt exit symbols
  powerpc/64: enable MSR[EE] in irq replay pt_regs
  powerpc/64s/interrupt: preserve regs->softe for NMI interrupts
  powerpc/64s: add a table of implicit soft-masked addresses
  powerpc/64e: remove implicit soft-masking and interrupt exit restart logic
  powerpc/64e: fix CONFIG_RELOCATABLE build warnings
  powerpc/64s: fix hash page fault interrupt handler
  powerpc/4xx: Fix setup_kuep() on SMP
  powerpc/32s: Fix setup_{kuap/kuep}() on SMP
  powerpc/interrupt: Use names in check_return_regs_valid()
  powerpc/interrupt: Also use exit_must_hard_disable() on PPC32
  powerpc/sysfs: Replace sizeof(arr)/sizeof(arr[0]) with ARRAY_SIZE
  powerpc/ptrace: Refactor regs_set_return_{msr/ip}
  powerpc/ptrace: Move set_return_regs_changed() before regs_set_return_{msr/ip}
  powerpc/stacktrace: Fix spurious "stale" traces in raise_backtrace_ipi()
  powerpc/pseries/vas: Include irqdomain.h
  powerpc: mark local variables around longjmp as volatile
  ...

10 files changed, 908 insertions, 63 deletions

diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index c8a2b0b05ac0..4cda0ef87be0 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -30,3 +30,4 @@ obj-$(CONFIG_PPC_SVM)		+= svm.o
 obj-$(CONFIG_FA_DUMP)		+= rtas-fadump.o
 
 obj-$(CONFIG_SUSPEND)		+= suspend.o
+obj-$(CONFIG_PPC_VAS)		+= vas.o
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 3ac70790ec7a..b1f01ac0c29e 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -289,8 +289,7 @@ int dlpar_acquire_drc(u32 drc_index)
 {
 	int dr_status, rc;
 
-	rc = rtas_call(rtas_token("get-sensor-state"), 2, 2, &dr_status,
-		       DR_ENTITY_SENSE, drc_index);
+	rc = rtas_get_sensor(DR_ENTITY_SENSE, drc_index, &dr_status);
 	if (rc || dr_status != DR_ENTITY_UNUSABLE)
 		return -1;
 
@@ -311,8 +310,7 @@ int dlpar_release_drc(u32 drc_index)
 {
 	int dr_status, rc;
 
-	rc = rtas_call(rtas_token("get-sensor-state"), 2, 2, &dr_status,
-		       DR_ENTITY_SENSE, drc_index);
+	rc = rtas_get_sensor(DR_ENTITY_SENSE, drc_index, &dr_status);
 	if (rc || dr_status != DR_ENTITY_PRESENT)
 		return -1;
 
@@ -333,8 +331,7 @@ int dlpar_unisolate_drc(u32 drc_index)
 {
 	int dr_status, rc;
 
-	rc = rtas_call(rtas_token("get-sensor-state"), 2, 2, &dr_status,
-				DR_ENTITY_SENSE, drc_index);
+	rc = rtas_get_sensor(DR_ENTITY_SENSE, drc_index, &dr_status);
 	if (rc || dr_status != DR_ENTITY_PRESENT)
 		return -1;
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 8377f1f7c78e..377d852f5a9a 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -348,7 +348,8 @@ static int pseries_remove_mem_node(struct device_node *np)
 
 static bool lmb_is_removable(struct drmem_lmb *lmb)
 {
-	if (!(lmb->flags & DRCONF_MEM_ASSIGNED))
+	if ((lmb->flags & DRCONF_MEM_RESERVED) ||
+		!(lmb->flags & DRCONF_MEM_ASSIGNED))
 		return false;
 
 #ifdef CONFIG_FA_DUMP
@@ -401,7 +402,7 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb)
 static int dlpar_memory_remove_by_count(u32 lmbs_to_remove)
 {
 	struct drmem_lmb *lmb;
-	int lmbs_removed = 0;
+	int lmbs_reserved = 0;
 	int lmbs_available = 0;
 	int rc;
 
@@ -435,12 +436,12 @@ static int dlpar_memory_remove_by_count(u32 lmbs_to_remove)
 		 */
 		drmem_mark_lmb_reserved(lmb);
 
-		lmbs_removed++;
-		if (lmbs_removed == lmbs_to_remove)
+		lmbs_reserved++;
+		if (lmbs_reserved == lmbs_to_remove)
 			break;
 	}
 
-	if (lmbs_removed != lmbs_to_remove) {
+	if (lmbs_reserved != lmbs_to_remove) {
 		pr_err("Memory hot-remove failed, adding LMB's back\n");
 
 		for_each_drmem_lmb(lmb) {
@@ -453,6 +454,10 @@ static int dlpar_memory_remove_by_count(u32 lmbs_to_remove)
 				       lmb->drc_index);
 
 			drmem_remove_lmb_reservation(lmb);
+
+			lmbs_reserved--;
+			if (lmbs_reserved == 0)
+				break;
 		}
 
 		rc = -EINVAL;
@@ -466,6 +471,10 @@ static int dlpar_memory_remove_by_count(u32 lmbs_to_remove)
 				lmb->base_addr);
 
 			drmem_remove_lmb_reservation(lmb);
+
+			lmbs_reserved--;
+			if (lmbs_reserved == 0)
+				break;
 		}
 		rc = 0;
 	}
@@ -508,7 +517,6 @@ static int dlpar_memory_remove_by_index(u32 drc_index)
 static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
 {
 	struct drmem_lmb *lmb, *start_lmb, *end_lmb;
-	int lmbs_available = 0;
 	int rc;
 
 	pr_info("Attempting to hot-remove %u LMB(s) at %x\n",
@@ -521,18 +529,29 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
 	if (rc)
 		return -EINVAL;
 
-	/* Validate that there are enough LMBs to satisfy the request */
+	/*
+	 * Validate that all LMBs in range are not reserved. Note that it
+	 * is ok if they are !ASSIGNED since our goal here is to remove the
+	 * LMB range, regardless of whether some LMBs were already removed
+	 * by any other reason.
+	 *
+	 * This is a contrast to what is done in remove_by_count() where we
+	 * check for both RESERVED and !ASSIGNED (via lmb_is_removable()),
+	 * because we want to remove a fixed amount of LMBs in that function.
+	 */
 	for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
-		if (lmb->flags & DRCONF_MEM_RESERVED)
-			break;
-
-		lmbs_available++;
+		if (lmb->flags & DRCONF_MEM_RESERVED) {
+			pr_err("Memory at %llx (drc index %x) is reserved\n",
+				lmb->base_addr, lmb->drc_index);
+			return -EINVAL;
+		}
 	}
 
-	if (lmbs_available < lmbs_to_remove)
-		return -EINVAL;
-
 	for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
+		/*
+		 * dlpar_remove_lmb() will error out if the LMB is already
+		 * !ASSIGNED, but this case is a no-op for us.
+		 */
 		if (!(lmb->flags & DRCONF_MEM_ASSIGNED))
 			continue;
 
@@ -551,6 +570,13 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
 			if (!drmem_lmb_reserved(lmb))
 				continue;
 
+			/*
+			 * Setting the isolation state of an UNISOLATED/CONFIGURED
+			 * device to UNISOLATE is a no-op, but the hypervisor can
+			 * use it as a hint that the LMB removal failed.
+			 */
+			dlpar_unisolate_drc(lmb->drc_index);
+
 			rc = dlpar_add_lmb(lmb);
 			if (rc)
 				pr_err("Failed to add LMB, drc index %x\n",
@@ -585,10 +611,6 @@ static inline int pseries_remove_mem_node(struct device_node *np)
 {
 	return 0;
 }
-static inline int dlpar_memory_remove(struct pseries_hp_errorlog *hp_elog)
-{
-	return -EOPNOTSUPP;
-}
 static int dlpar_remove_lmb(struct drmem_lmb *lmb)
 {
 	return -EOPNOTSUPP;
@@ -651,7 +673,7 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
 {
 	struct drmem_lmb *lmb;
 	int lmbs_available = 0;
-	int lmbs_added = 0;
+	int lmbs_reserved = 0;
 	int rc;
 
 	pr_info("Attempting to hot-add %d LMB(s)\n", lmbs_to_add);
@@ -661,6 +683,9 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
 
 	/* Validate that there are enough LMBs to satisfy the request */
 	for_each_drmem_lmb(lmb) {
+		if (lmb->flags & DRCONF_MEM_RESERVED)
+			continue;
+
 		if (!(lmb->flags & DRCONF_MEM_ASSIGNED))
 			lmbs_available++;
 
@@ -689,13 +714,12 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
 		 * requested LMBs cannot be added.
 		 */
 		drmem_mark_lmb_reserved(lmb);
-
-		lmbs_added++;
-		if (lmbs_added == lmbs_to_add)
+		lmbs_reserved++;
+		if (lmbs_reserved == lmbs_to_add)
 			break;
 	}
 
-	if (lmbs_added != lmbs_to_add) {
+	if (lmbs_reserved != lmbs_to_add) {
 		pr_err("Memory hot-add failed, removing any added LMBs\n");
 
 		for_each_drmem_lmb(lmb) {
@@ -710,6 +734,10 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
 				dlpar_release_drc(lmb->drc_index);
 
 			drmem_remove_lmb_reservation(lmb);
+			lmbs_reserved--;
+
+			if (lmbs_reserved == 0)
+				break;
 		}
 		rc = -EINVAL;
 	} else {
@@ -720,6 +748,10 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
 			pr_debug("Memory at %llx (drc index %x) was hot-added\n",
 				 lmb->base_addr, lmb->drc_index);
 			drmem_remove_lmb_reservation(lmb);
+			lmbs_reserved--;
+
+			if (lmbs_reserved == 0)
+				break;
 		}
 		rc = 0;
 	}
@@ -764,7 +796,6 @@ static int dlpar_memory_add_by_index(u32 drc_index)
 static int dlpar_memory_add_by_ic(u32 lmbs_to_add, u32 drc_index)
 {
 	struct drmem_lmb *lmb, *start_lmb, *end_lmb;
-	int lmbs_available = 0;
 	int rc;
 
 	pr_info("Attempting to hot-add %u LMB(s) at index %x\n",
@@ -779,15 +810,14 @@ static int dlpar_memory_add_by_ic(u32 lmbs_to_add, u32 drc_index)
 
 	/* Validate that the LMBs in this range are not reserved */
 	for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
-		if (lmb->flags & DRCONF_MEM_RESERVED)
-			break;
-
-		lmbs_available++;
+		/* Fail immediately if the whole range can't be hot-added */
+		if (lmb->flags & DRCONF_MEM_RESERVED) {
+			pr_err("Memory at %llx (drc index %x) is reserved\n",
+					lmb->base_addr, lmb->drc_index);
+			return -EINVAL;
+		}
 	}
 
-	if (lmbs_available < lmbs_to_add)
-		return -EINVAL;
-
 	for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
 		if (lmb->flags & DRCONF_MEM_ASSIGNED)
 			continue;
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index 8a2b8d64265b..ab9fc6506861 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -108,6 +108,10 @@ _GLOBAL_TOC(plpar_hcall_norets_notrace)
 	mfcr	r0
 	stw	r0,8(r1)
 	HVSC				/* invoke the hypervisor */
+
+	li	r4,0
+	stb	r4,PACASRR_VALID(r13)
+
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
 	blr				/* return r3 = status */
@@ -120,6 +124,9 @@ _GLOBAL_TOC(plpar_hcall_norets)
 	HCALL_BRANCH(plpar_hcall_norets_trace)
 	HVSC				/* invoke the hypervisor */
 
+	li	r4,0
+	stb	r4,PACASRR_VALID(r13)
+
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
 	blr				/* return r3 = status */
@@ -129,6 +136,10 @@ plpar_hcall_norets_trace:
 	HCALL_INST_PRECALL(R4)
 	HVSC
 	HCALL_INST_POSTCALL_NORETS
+
+	li	r4,0
+	stb	r4,PACASRR_VALID(r13)
+
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
 	blr
@@ -159,6 +170,9 @@ _GLOBAL_TOC(plpar_hcall)
 	std	r6, 16(r12)
 	std	r7, 24(r12)
 
+	li	r4,0
+	stb	r4,PACASRR_VALID(r13)
+
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
 
@@ -188,6 +202,9 @@ plpar_hcall_trace:
 
 	HCALL_INST_POSTCALL(r12)
 
+	li	r4,0
+	stb	r4,PACASRR_VALID(r13)
+
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
 
@@ -223,6 +240,9 @@ _GLOBAL(plpar_hcall_raw)
 	std	r6, 16(r12)
 	std	r7, 24(r12)
 
+	li	r4,0
+	stb	r4,PACASRR_VALID(r13)
+
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
 
@@ -262,6 +282,9 @@ _GLOBAL_TOC(plpar_hcall9)
 	std	r11,56(r12)
 	std	r0, 64(r12)
 
+	li	r4,0
+	stb	r4,PACASRR_VALID(r13)
+
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
 
@@ -300,6 +323,9 @@ plpar_hcall9_trace:
 
 	HCALL_INST_POSTCALL(r12)
 
+	li	r4,0
+	stb	r4,PACASRR_VALID(r13)
+
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
 
@@ -339,6 +365,9 @@ _GLOBAL(plpar_hcall9_raw)
 	std	r11,56(r12)
 	std	r0, 64(r12)
 
+	li	r4,0
+	stb	r4,PACASRR_VALID(r13)
+
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
 
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index ef26fe40efb0..f48e87ac89c9 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -18,6 +18,7 @@
 #include <asm/plpar_wrappers.h>
 #include <asm/papr_pdsm.h>
 #include <asm/mce.h>
+#include <asm/unaligned.h>
 
 #define BIND_ANY_ADDR (~0ul)
 
@@ -114,6 +115,9 @@ struct papr_scm_priv {
 	/* Health information for the dimm */
 	u64 health_bitmap;
 
+	/* Holds the last known dirty shutdown counter value */
+	u64 dirty_shutdown_counter;
+
 	/* length of the stat buffer as expected by phyp */
 	size_t stat_buffer_len;
 };
@@ -260,7 +264,7 @@ err_out:
  * Query the Dimm performance stats from PHYP and copy them (if returned) to
  * provided struct papr_scm_perf_stats instance 'stats' that can hold atleast
  * (num_stats + header) bytes.
- * - If buff_stats == NULL the return value is the size in byes of the buffer
+ * - If buff_stats == NULL the return value is the size in bytes of the buffer
  * needed to hold all supported performance-statistics.
  * - If buff_stats != NULL and num_stats == 0 then we copy all known
  * performance-statistics to 'buff_stat' and expect to be large enough to
@@ -310,6 +314,13 @@ static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p,
 		dev_err(&p->pdev->dev,
 			"Unknown performance stats, Err:0x%016lX\n", ret[0]);
 		return -ENOENT;
+	} else if (rc == H_AUTHORITY) {
+		dev_info(&p->pdev->dev,
+			 "Permission denied while accessing performance stats");
+		return -EPERM;
+	} else if (rc == H_UNSUPPORTED) {
+		dev_dbg(&p->pdev->dev, "Performance stats unsupported\n");
+		return -EOPNOTSUPP;
 	} else if (rc != H_SUCCESS) {
 		dev_err(&p->pdev->dev,
 			"Failed to query performance stats, Err:%lld\n", rc);
@@ -596,6 +607,16 @@ free_stats:
 	return rc;
 }
 
+/* Add the dirty-shutdown-counter value to the pdsm */
+static int papr_pdsm_dsc(struct papr_scm_priv *p,
+			 union nd_pdsm_payload *payload)
+{
+	payload->health.extension_flags |= PDSM_DIMM_DSC_VALID;
+	payload->health.dimm_dsc = p->dirty_shutdown_counter;
+
+	return sizeof(struct nd_papr_pdsm_health);
+}
+
 /* Fetch the DIMM health info and populate it in provided package. */
 static int papr_pdsm_health(struct papr_scm_priv *p,
 			    union nd_pdsm_payload *payload)
@@ -639,6 +660,8 @@ static int papr_pdsm_health(struct papr_scm_priv *p,
 
 	/* Populate the fuel gauge meter in the payload */
 	papr_pdsm_fuel_gauge(p, payload);
+	/* Populate the dirty-shutdown-counter field */
+	papr_pdsm_dsc(p, payload);
 
 	rc = sizeof(struct nd_papr_pdsm_health);
 
@@ -900,15 +923,41 @@ static ssize_t flags_show(struct device *dev,
 }
 DEVICE_ATTR_RO(flags);
 
+static ssize_t dirty_shutdown_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *dimm = to_nvdimm(dev);
+	struct papr_scm_priv *p = nvdimm_provider_data(dimm);
+
+	return sysfs_emit(buf, "%llu\n", p->dirty_shutdown_counter);
+}
+DEVICE_ATTR_RO(dirty_shutdown);
+
+static umode_t papr_nd_attribute_visible(struct kobject *kobj,
+					 struct attribute *attr, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct papr_scm_priv *p = nvdimm_provider_data(nvdimm);
+
+	/* For if perf-stats not available remove perf_stats sysfs */
+	if (attr == &dev_attr_perf_stats.attr && p->stat_buffer_len == 0)
+		return 0;
+
+	return attr->mode;
+}
+
 /* papr_scm specific dimm attributes */
 static struct attribute *papr_nd_attributes[] = {
 	&dev_attr_flags.attr,
 	&dev_attr_perf_stats.attr,
+	&dev_attr_dirty_shutdown.attr,
 	NULL,
 };
 
 static struct attribute_group papr_nd_attribute_group = {
 	.name = "papr",
+	.is_visible = papr_nd_attribute_visible,
 	.attrs = papr_nd_attributes,
 };
 
@@ -924,7 +973,6 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	struct nd_region_desc ndr_desc;
 	unsigned long dimm_flags;
 	int target_nid, online_nid;
-	ssize_t stat_size;
 
 	p->bus_desc.ndctl = papr_scm_ndctl;
 	p->bus_desc.module = THIS_MODULE;
@@ -1009,16 +1057,6 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	list_add_tail(&p->region_list, &papr_nd_regions);
 	mutex_unlock(&papr_ndr_lock);
 
-	/* Try retriving the stat buffer and see if its supported */
-	stat_size = drc_pmem_query_stats(p, NULL, 0);
-	if (stat_size > 0) {
-		p->stat_buffer_len = stat_size;
-		dev_dbg(&p->pdev->dev, "Max perf-stat size %lu-bytes\n",
-			p->stat_buffer_len);
-	} else {
-		dev_info(&p->pdev->dev, "Dimm performance stats unavailable\n");
-	}
-
 	return 0;
 
 err:	nvdimm_bus_unregister(p->bus);
@@ -1094,8 +1132,10 @@ static int papr_scm_probe(struct platform_device *pdev)
 	u32 drc_index, metadata_size;
 	u64 blocks, block_size;
 	struct papr_scm_priv *p;
+	u8 uuid_raw[UUID_SIZE];
 	const char *uuid_str;
-	u64 uuid[2];
+	ssize_t stat_size;
+	uuid_t uuid;
 	int rc;
 
 	/* check we have all the required DT properties */
@@ -1137,17 +1177,28 @@ static int papr_scm_probe(struct platform_device *pdev)
 	p->is_volatile = !of_property_read_bool(dn, "ibm,cache-flush-required");
 	p->hcall_flush_required = of_property_read_bool(dn, "ibm,hcall-flush-required");
 
+	if (of_property_read_u64(dn, "ibm,persistence-failed-count",
+				 &p->dirty_shutdown_counter))
+		p->dirty_shutdown_counter = 0;
+
 	/* We just need to ensure that set cookies are unique across */
-	uuid_parse(uuid_str, (uuid_t *) uuid);
+	uuid_parse(uuid_str, &uuid);
+
 	/*
-	 * cookie1 and cookie2 are not really little endian
-	 * we store a little endian representation of the
-	 * uuid str so that we can compare this with the label
-	 * area cookie irrespective of the endian config with which
-	 * the kernel is built.
+	 * The cookie1 and cookie2 are not really little endian.
+	 * We store a raw buffer representation of the
+	 * uuid string so that we can compare this with the label
+	 * area cookie irrespective of the endian configuration
+	 * with which the kernel is built.
+	 *
+	 * Historically we stored the cookie in the below format.
+	 * for a uuid string 72511b67-0b3b-42fd-8d1d-5be3cae8bcaa
+	 *	cookie1 was 0xfd423b0b671b5172
+	 *	cookie2 was 0xaabce8cae35b1d8d
 	 */
-	p->nd_set.cookie1 = cpu_to_le64(uuid[0]);
-	p->nd_set.cookie2 = cpu_to_le64(uuid[1]);
+	export_uuid(uuid_raw, &uuid);
+	p->nd_set.cookie1 = get_unaligned_le64(&uuid_raw[0]);
+	p->nd_set.cookie2 = get_unaligned_le64(&uuid_raw[8]);
 
 	/* might be zero */
 	p->metadata_size = metadata_size;
@@ -1172,6 +1223,14 @@ static int papr_scm_probe(struct platform_device *pdev)
 	p->res.name  = pdev->name;
 	p->res.flags = IORESOURCE_MEM;
 
+	/* Try retrieving the stat buffer and see if its supported */
+	stat_size = drc_pmem_query_stats(p, NULL, 0);
+	if (stat_size > 0) {
+		p->stat_buffer_len = stat_size;
+		dev_dbg(&p->pdev->dev, "Max perf-stat size %lu-bytes\n",
+			p->stat_buffer_len);
+	}
+
 	rc = papr_scm_nvdimm_init(p);
 	if (rc)
 		goto err2;
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 9d4ef65da7f3..167f2e1b8d39 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -487,8 +487,8 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
 	if ((be64_to_cpu(regs->msr) &
 			(MSR_LE|MSR_RI|MSR_DR|MSR_IR|MSR_ME|MSR_PR|
 			 MSR_ILE|MSR_HV|MSR_SF)) == (MSR_DR|MSR_SF)) {
-		regs->nip = be64_to_cpu((__be64)regs->nip);
-		regs->msr = 0;
+		regs_set_return_ip(regs, be64_to_cpu((__be64)regs->nip));
+		regs_set_return_msr(regs, 0);
 	}
 #endif
 
@@ -593,8 +593,6 @@ static int mce_handle_err_virtmode(struct pt_regs *regs,
 		mce_err.severity = MCE_SEV_SEVERE;
 	else if (severity == RTAS_SEVERITY_ERROR)
 		mce_err.severity = MCE_SEV_SEVERE;
-	else if (severity == RTAS_SEVERITY_FATAL)
-		mce_err.severity = MCE_SEV_FATAL;
 	else
 		mce_err.severity = MCE_SEV_FATAL;
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 754e493b7c05..631a0d57b6cd 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -549,6 +549,15 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result)
 	if (!(result->behaviour & H_CPU_BEHAV_L1D_FLUSH_PR))
 		security_ftr_clear(SEC_FTR_L1D_FLUSH_PR);
 
+	if (result->behaviour & H_CPU_BEHAV_NO_L1D_FLUSH_ENTRY)
+		security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY);
+
+	if (result->behaviour & H_CPU_BEHAV_NO_L1D_FLUSH_UACCESS)
+		security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS);
+
+	if (result->behaviour & H_CPU_BEHAV_NO_STF_BARRIER)
+		security_ftr_clear(SEC_FTR_STF_BARRIER);
+
 	if (!(result->behaviour & H_CPU_BEHAV_BNDS_CHK_SPEC_BAR))
 		security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR);
 }
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index c70b4be9f0a5..096629f54576 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -211,7 +211,9 @@ static __init void pSeries_smp_probe(void)
 	if (!cpu_has_feature(CPU_FTR_SMT))
 		return;
 
-	if (check_kvm_guest()) {
+	check_kvm_guest();
+
+	if (is_kvm_guest()) {
 		/*
 		 * KVM emulates doorbells by disabling FSCR[MSGP] so msgsndp
 		 * faults to the hypervisor which then reads the instruction
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
new file mode 100644
index 000000000000..b5c1cf1bc64d
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -0,0 +1,595 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2020-21 IBM Corp.
+ */
+
+#define pr_fmt(fmt) "vas: " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <asm/machdep.h>
+#include <asm/hvcall.h>
+#include <asm/plpar_wrappers.h>
+#include <asm/vas.h>
+#include "vas.h"
+
+#define VAS_INVALID_WIN_ADDRESS	0xFFFFFFFFFFFFFFFFul
+#define VAS_DEFAULT_DOMAIN_ID	0xFFFFFFFFFFFFFFFFul
+/* The hypervisor allows one credit per window right now */
+#define DEF_WIN_CREDS		1
+
+static struct vas_all_caps caps_all;
+static bool copypaste_feat;
+
+static struct vas_caps vascaps[VAS_MAX_FEAT_TYPE];
+static DEFINE_MUTEX(vas_pseries_mutex);
+
+static long hcall_return_busy_check(long rc)
+{
+	/* Check if we are stalled for some time */
+	if (H_IS_LONG_BUSY(rc)) {
+		msleep(get_longbusy_msecs(rc));
+		rc = H_BUSY;
+	} else if (rc == H_BUSY) {
+		cond_resched();
+	}
+
+	return rc;
+}
+
+/*
+ * Allocate VAS window hcall
+ */
+static int h_allocate_vas_window(struct pseries_vas_window *win, u64 *domain,
+				     u8 wintype, u16 credits)
+{
+	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+	long rc;
+
+	do {
+		rc = plpar_hcall9(H_ALLOCATE_VAS_WINDOW, retbuf, wintype,
+				  credits, domain[0], domain[1], domain[2],
+				  domain[3], domain[4], domain[5]);
+
+		rc = hcall_return_busy_check(rc);
+	} while (rc == H_BUSY);
+
+	if (rc == H_SUCCESS) {
+		if (win->win_addr == VAS_INVALID_WIN_ADDRESS) {
+			pr_err("H_ALLOCATE_VAS_WINDOW: COPY/PASTE is not supported\n");
+			return -ENOTSUPP;
+		}
+		win->vas_win.winid = retbuf[0];
+		win->win_addr = retbuf[1];
+		win->complete_irq = retbuf[2];
+		win->fault_irq = retbuf[3];
+		return 0;
+	}
+
+	pr_err("H_ALLOCATE_VAS_WINDOW error: %ld, wintype: %u, credits: %u\n",
+		rc, wintype, credits);
+
+	return -EIO;
+}
+
+/*
+ * Deallocate VAS window hcall.
+ */
+static int h_deallocate_vas_window(u64 winid)
+{
+	long rc;
+
+	do {
+		rc = plpar_hcall_norets(H_DEALLOCATE_VAS_WINDOW, winid);
+
+		rc = hcall_return_busy_check(rc);
+	} while (rc == H_BUSY);
+
+	if (rc == H_SUCCESS)
+		return 0;
+
+	pr_err("H_DEALLOCATE_VAS_WINDOW error: %ld, winid: %llu\n",
+		rc, winid);
+	return -EIO;
+}
+
+/*
+ * Modify VAS window.
+ * After the window is opened with allocate window hcall, configure it
+ * with flags and LPAR PID before using.
+ */
+static int h_modify_vas_window(struct pseries_vas_window *win)
+{
+	long rc;
+	u32 lpid = mfspr(SPRN_PID);
+
+	/*
+	 * AMR value is not supported in Linux VAS implementation.
+	 * The hypervisor ignores it if 0 is passed.
+	 */
+	do {
+		rc = plpar_hcall_norets(H_MODIFY_VAS_WINDOW,
+					win->vas_win.winid, lpid, 0,
+					VAS_MOD_WIN_FLAGS, 0);
+
+		rc = hcall_return_busy_check(rc);
+	} while (rc == H_BUSY);
+
+	if (rc == H_SUCCESS)
+		return 0;
+
+	pr_err("H_MODIFY_VAS_WINDOW error: %ld, winid %u lpid %u\n",
+			rc, win->vas_win.winid, lpid);
+	return -EIO;
+}
+
+/*
+ * This hcall is used to determine the capabilities from the hypervisor.
+ * @hcall: H_QUERY_VAS_CAPABILITIES or H_QUERY_NX_CAPABILITIES
+ * @query_type: If 0 is passed, the hypervisor returns the overall
+ *		capabilities which provides all feature(s) that are
+ *		available. Then query the hypervisor to get the
+ *		corresponding capabilities for the specific feature.
+ *		Example: H_QUERY_VAS_CAPABILITIES provides VAS GZIP QoS
+ *			and VAS GZIP Default capabilities.
+ *			H_QUERY_NX_CAPABILITIES provides NX GZIP
+ *			capabilities.
+ * @result: Return buffer to save capabilities.
+ */
+int h_query_vas_capabilities(const u64 hcall, u8 query_type, u64 result)
+{
+	long rc;
+
+	rc = plpar_hcall_norets(hcall, query_type, result);
+
+	if (rc == H_SUCCESS)
+		return 0;
+
+	pr_err("HCALL(%llx) error %ld, query_type %u, result buffer 0x%llx\n",
+			hcall, rc, query_type, result);
+	return -EIO;
+}
+EXPORT_SYMBOL_GPL(h_query_vas_capabilities);
+
+/*
+ * hcall to get fault CRB from the hypervisor.
+ */
+static int h_get_nx_fault(u32 winid, u64 buffer)
+{
+	long rc;
+
+	rc = plpar_hcall_norets(H_GET_NX_FAULT, winid, buffer);
+
+	if (rc == H_SUCCESS)
+		return 0;
+
+	pr_err("H_GET_NX_FAULT error: %ld, winid %u, buffer 0x%llx\n",
+		rc, winid, buffer);
+	return -EIO;
+
+}
+
+/*
+ * Handle the fault interrupt.
+ * When the fault interrupt is received for each window, query the
+ * hypervisor to get the fault CRB on the specific fault. Then
+ * process the CRB by updating CSB or send signal if the user space
+ * CSB is invalid.
+ * Note: The hypervisor forwards an interrupt for each fault request.
+ *	So one fault CRB to process for each H_GET_NX_FAULT hcall.
+ */
+irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data)
+{
+	struct pseries_vas_window *txwin = data;
+	struct coprocessor_request_block crb;
+	struct vas_user_win_ref *tsk_ref;
+	int rc;
+
+	rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
+	if (!rc) {
+		tsk_ref = &txwin->vas_win.task_ref;
+		vas_dump_crb(&crb);
+		vas_update_csb(&crb, tsk_ref);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * Allocate window and setup IRQ mapping.
+ */
+static int allocate_setup_window(struct pseries_vas_window *txwin,
+				 u64 *domain, u8 wintype)
+{
+	int rc;
+
+	rc = h_allocate_vas_window(txwin, domain, wintype, DEF_WIN_CREDS);
+	if (rc)
+		return rc;
+	/*
+	 * On PowerVM, the hypervisor setup and forwards the fault
+	 * interrupt per window. So the IRQ setup and fault handling
+	 * will be done for each open window separately.
+	 */
+	txwin->fault_virq = irq_create_mapping(NULL, txwin->fault_irq);
+	if (!txwin->fault_virq) {
+		pr_err("Failed irq mapping %d\n", txwin->fault_irq);
+		rc = -EINVAL;
+		goto out_win;
+	}
+
+	txwin->name = kasprintf(GFP_KERNEL, "vas-win-%d",
+				txwin->vas_win.winid);
+	if (!txwin->name) {
+		rc = -ENOMEM;
+		goto out_irq;
+	}
+
+	rc = request_threaded_irq(txwin->fault_virq, NULL,
+				  pseries_vas_fault_thread_fn, IRQF_ONESHOT,
+				  txwin->name, txwin);
+	if (rc) {
+		pr_err("VAS-Window[%d]: Request IRQ(%u) failed with %d\n",
+		       txwin->vas_win.winid, txwin->fault_virq, rc);
+		goto out_free;
+	}
+
+	txwin->vas_win.wcreds_max = DEF_WIN_CREDS;
+
+	return 0;
+out_free:
+	kfree(txwin->name);
+out_irq:
+	irq_dispose_mapping(txwin->fault_virq);
+out_win:
+	h_deallocate_vas_window(txwin->vas_win.winid);
+	return rc;
+}
+
+static inline void free_irq_setup(struct pseries_vas_window *txwin)
+{
+	free_irq(txwin->fault_virq, txwin);
+	kfree(txwin->name);
+	irq_dispose_mapping(txwin->fault_virq);
+}
+
+static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
+					      enum vas_cop_type cop_type)
+{
+	long domain[PLPAR_HCALL9_BUFSIZE] = {VAS_DEFAULT_DOMAIN_ID};
+	struct vas_cop_feat_caps *cop_feat_caps;
+	struct vas_caps *caps;
+	struct pseries_vas_window *txwin;
+	int rc;
+
+	txwin = kzalloc(sizeof(*txwin), GFP_KERNEL);
+	if (!txwin)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * A VAS window can have many credits which means that many
+	 * requests can be issued simultaneously. But the hypervisor
+	 * restricts one credit per window.
+	 * The hypervisor introduces 2 different types of credits:
+	 * Default credit type (Uses normal priority FIFO):
+	 *	A limited number of credits are assigned to partitions
+	 *	based on processor entitlement. But these credits may be
+	 *	over-committed on a system depends on whether the CPUs
+	 *	are in shared or dedicated modes - that is, more requests
+	 *	may be issued across the system than NX can service at
+	 *	once which can result in paste command failure (RMA_busy).
+	 *	Then the process has to resend requests or fall-back to
+	 *	SW compression.
+	 * Quality of Service (QoS) credit type (Uses high priority FIFO):
+	 *	To avoid NX HW contention, the system admins can assign
+	 *	QoS credits for each LPAR so that this partition is
+	 *	guaranteed access to NX resources. These credits are
+	 *	assigned to partitions via the HMC.
+	 *	Refer PAPR for more information.
+	 *
+	 * Allocate window with QoS credits if user requested. Otherwise
+	 * default credits are used.
+	 */
+	if (flags & VAS_TX_WIN_FLAG_QOS_CREDIT)
+		caps = &vascaps[VAS_GZIP_QOS_FEAT_TYPE];
+	else
+		caps = &vascaps[VAS_GZIP_DEF_FEAT_TYPE];
+
+	cop_feat_caps = &caps->caps;
+
+	if (atomic_inc_return(&cop_feat_caps->used_lpar_creds) >
+			atomic_read(&cop_feat_caps->target_lpar_creds)) {
+		pr_err("Credits are not available to allocate window\n");
+		rc = -EINVAL;
+		goto out;
+	}
+
+	if (vas_id == -1) {
+		/*
+		 * The user space is requesting to allocate a window on
+		 * a VAS instance where the process is executing.
+		 * On PowerVM, domain values are passed to the hypervisor
+		 * to select VAS instance. Useful if the process is
+		 * affinity to NUMA node.
+		 * The hypervisor selects VAS instance if
+		 * VAS_DEFAULT_DOMAIN_ID (-1) is passed for domain values.
+		 * The h_allocate_vas_window hcall is defined to take a
+		 * domain values as specified by h_home_node_associativity,
+		 * So no unpacking needs to be done.
+		 */
+		rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, domain,
+				  VPHN_FLAG_VCPU, smp_processor_id());
+		if (rc != H_SUCCESS) {
+			pr_err("H_HOME_NODE_ASSOCIATIVITY error: %d\n", rc);
+			goto out;
+		}
+	}
+
+	/*
+	 * Allocate / Deallocate window hcalls and setup / free IRQs
+	 * have to be protected with mutex.
+	 * Open VAS window: Allocate window hcall and setup IRQ
+	 * Close VAS window: Deallocate window hcall and free IRQ
+	 *	The hypervisor waits until all NX requests are
+	 *	completed before closing the window. So expects OS
+	 *	to handle NX faults, means IRQ can be freed only
+	 *	after the deallocate window hcall is returned.
+	 * So once the window is closed with deallocate hcall before
+	 * the IRQ is freed, it can be assigned to new allocate
+	 * hcall with the same fault IRQ by the hypervisor. It can
+	 * result in setup IRQ fail for the new window since the
+	 * same fault IRQ is not freed by the OS before.
+	 */
+	mutex_lock(&vas_pseries_mutex);
+	rc = allocate_setup_window(txwin, (u64 *)&domain[0],
+				   cop_feat_caps->win_type);
+	mutex_unlock(&vas_pseries_mutex);
+	if (rc)
+		goto out;
+
+	/*
+	 * Modify window and it is ready to use.
+	 */
+	rc = h_modify_vas_window(txwin);
+	if (!rc)
+		rc = get_vas_user_win_ref(&txwin->vas_win.task_ref);
+	if (rc)
+		goto out_free;
+
+	vas_user_win_add_mm_context(&txwin->vas_win.task_ref);
+	txwin->win_type = cop_feat_caps->win_type;
+	mutex_lock(&vas_pseries_mutex);
+	list_add(&txwin->win_list, &caps->list);
+	mutex_unlock(&vas_pseries_mutex);
+
+	return &txwin->vas_win;
+
+out_free:
+	/*
+	 * Window is not operational. Free IRQ before closing
+	 * window so that do not have to hold mutex.
+	 */
+	free_irq_setup(txwin);
+	h_deallocate_vas_window(txwin->vas_win.winid);
+out:
+	atomic_dec(&cop_feat_caps->used_lpar_creds);
+	kfree(txwin);
+	return ERR_PTR(rc);
+}
+
+static u64 vas_paste_address(struct vas_window *vwin)
+{
+	struct pseries_vas_window *win;
+
+	win = container_of(vwin, struct pseries_vas_window, vas_win);
+	return win->win_addr;
+}
+
+static int deallocate_free_window(struct pseries_vas_window *win)
+{
+	int rc = 0;
+
+	/*
+	 * The hypervisor waits for all requests including faults
+	 * are processed before closing the window - Means all
+	 * credits have to be returned. In the case of fault
+	 * request, a credit is returned after OS issues
+	 * H_GET_NX_FAULT hcall.
+	 * So free IRQ after executing H_DEALLOCATE_VAS_WINDOW
+	 * hcall.
+	 */
+	rc = h_deallocate_vas_window(win->vas_win.winid);
+	if (!rc)
+		free_irq_setup(win);
+
+	return rc;
+}
+
+static int vas_deallocate_window(struct vas_window *vwin)
+{
+	struct pseries_vas_window *win;
+	struct vas_cop_feat_caps *caps;
+	int rc = 0;
+
+	if (!vwin)
+		return -EINVAL;
+
+	win = container_of(vwin, struct pseries_vas_window, vas_win);
+
+	/* Should not happen */
+	if (win->win_type >= VAS_MAX_FEAT_TYPE) {
+		pr_err("Window (%u): Invalid window type %u\n",
+				vwin->winid, win->win_type);
+		return -EINVAL;
+	}
+
+	caps = &vascaps[win->win_type].caps;
+	mutex_lock(&vas_pseries_mutex);
+	rc = deallocate_free_window(win);
+	if (rc) {
+		mutex_unlock(&vas_pseries_mutex);
+		return rc;
+	}
+
+	list_del(&win->win_list);
+	atomic_dec(&caps->used_lpar_creds);
+	mutex_unlock(&vas_pseries_mutex);
+
+	put_vas_user_win_ref(&vwin->task_ref);
+	mm_context_remove_vas_window(vwin->task_ref.mm);
+
+	kfree(win);
+	return 0;
+}
+
+static const struct vas_user_win_ops vops_pseries = {
+	.open_win	= vas_allocate_window,	/* Open and configure window */
+	.paste_addr	= vas_paste_address,	/* To do copy/paste */
+	.close_win	= vas_deallocate_window, /* Close window */
+};
+
+/*
+ * Supporting only nx-gzip coprocessor type now, but this API code
+ * extended to other coprocessor types later.
+ */
+int vas_register_api_pseries(struct module *mod, enum vas_cop_type cop_type,
+			     const char *name)
+{
+	int rc;
+
+	if (!copypaste_feat)
+		return -ENOTSUPP;
+
+	rc = vas_register_coproc_api(mod, cop_type, name, &vops_pseries);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(vas_register_api_pseries);
+
+void vas_unregister_api_pseries(void)
+{
+	vas_unregister_coproc_api();
+}
+EXPORT_SYMBOL_GPL(vas_unregister_api_pseries);
+
+/*
+ * Get the specific capabilities based on the feature type.
+ * Right now supports GZIP default and GZIP QoS capabilities.
+ */
+static int get_vas_capabilities(u8 feat, enum vas_cop_feat_type type,
+				struct hv_vas_cop_feat_caps *hv_caps)
+{
+	struct vas_cop_feat_caps *caps;
+	struct vas_caps *vcaps;
+	int rc = 0;
+
+	vcaps = &vascaps[type];
+	memset(vcaps, 0, sizeof(*vcaps));
+	INIT_LIST_HEAD(&vcaps->list);
+
+	caps = &vcaps->caps;
+
+	rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, feat,
+					  (u64)virt_to_phys(hv_caps));
+	if (rc)
+		return rc;
+
+	caps->user_mode = hv_caps->user_mode;
+	if (!(caps->user_mode & VAS_COPY_PASTE_USER_MODE)) {
+		pr_err("User space COPY/PASTE is not supported\n");
+		return -ENOTSUPP;
+	}
+
+	caps->descriptor = be64_to_cpu(hv_caps->descriptor);
+	caps->win_type = hv_caps->win_type;
+	if (caps->win_type >= VAS_MAX_FEAT_TYPE) {
+		pr_err("Unsupported window type %u\n", caps->win_type);
+		return -EINVAL;
+	}
+	caps->max_lpar_creds = be16_to_cpu(hv_caps->max_lpar_creds);
+	caps->max_win_creds = be16_to_cpu(hv_caps->max_win_creds);
+	atomic_set(&caps->target_lpar_creds,
+		   be16_to_cpu(hv_caps->target_lpar_creds));
+	if (feat == VAS_GZIP_DEF_FEAT) {
+		caps->def_lpar_creds = be16_to_cpu(hv_caps->def_lpar_creds);
+
+		if (caps->max_win_creds < DEF_WIN_CREDS) {
+			pr_err("Window creds(%u) > max allowed window creds(%u)\n",
+			       DEF_WIN_CREDS, caps->max_win_creds);
+			return -EINVAL;
+		}
+	}
+
+	copypaste_feat = true;
+
+	return 0;
+}
+
+static int __init pseries_vas_init(void)
+{
+	struct hv_vas_cop_feat_caps *hv_cop_caps;
+	struct hv_vas_all_caps *hv_caps;
+	int rc;
+
+	/*
+	 * Linux supports user space COPY/PASTE only with Radix
+	 */
+	if (!radix_enabled()) {
+		pr_err("API is supported only with radix page tables\n");
+		return -ENOTSUPP;
+	}
+
+	hv_caps = kmalloc(sizeof(*hv_caps), GFP_KERNEL);
+	if (!hv_caps)
+		return -ENOMEM;
+	/*
+	 * Get VAS overall capabilities by passing 0 to feature type.
+	 */
+	rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, 0,
+					  (u64)virt_to_phys(hv_caps));
+	if (rc)
+		goto out;
+
+	caps_all.descriptor = be64_to_cpu(hv_caps->descriptor);
+	caps_all.feat_type = be64_to_cpu(hv_caps->feat_type);
+
+	hv_cop_caps = kmalloc(sizeof(*hv_cop_caps), GFP_KERNEL);
+	if (!hv_cop_caps) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	/*
+	 * QOS capabilities available
+	 */
+	if (caps_all.feat_type & VAS_GZIP_QOS_FEAT_BIT) {
+		rc = get_vas_capabilities(VAS_GZIP_QOS_FEAT,
+					  VAS_GZIP_QOS_FEAT_TYPE, hv_cop_caps);
+
+		if (rc)
+			goto out_cop;
+	}
+	/*
+	 * Default capabilities available
+	 */
+	if (caps_all.feat_type & VAS_GZIP_DEF_FEAT_BIT) {
+		rc = get_vas_capabilities(VAS_GZIP_DEF_FEAT,
+					  VAS_GZIP_DEF_FEAT_TYPE, hv_cop_caps);
+		if (rc)
+			goto out_cop;
+	}
+
+	pr_info("GZIP feature is available\n");
+
+out_cop:
+	kfree(hv_cop_caps);
+out:
+	kfree(hv_caps);
+	return rc;
+}
+machine_device_initcall(pseries, pseries_vas_init);
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
new file mode 100644
index 000000000000..4ecb3fcabd10
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -0,0 +1,125 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2020-21 IBM Corp.
+ */
+
+#ifndef _VAS_H
+#define _VAS_H
+#include <asm/vas.h>
+#include <linux/mutex.h>
+#include <linux/stringify.h>
+
+/*
+ * VAS window modify flags
+ */
+#define VAS_MOD_WIN_CLOSE	PPC_BIT(0)
+#define VAS_MOD_WIN_JOBS_KILL	PPC_BIT(1)
+#define VAS_MOD_WIN_DR		PPC_BIT(3)
+#define VAS_MOD_WIN_PR		PPC_BIT(4)
+#define VAS_MOD_WIN_SF		PPC_BIT(5)
+#define VAS_MOD_WIN_TA		PPC_BIT(6)
+#define VAS_MOD_WIN_FLAGS	(VAS_MOD_WIN_JOBS_KILL | VAS_MOD_WIN_DR | \
+				VAS_MOD_WIN_PR | VAS_MOD_WIN_SF)
+
+#define VAS_WIN_ACTIVE		0x0
+#define VAS_WIN_CLOSED		0x1
+#define VAS_WIN_INACTIVE	0x2	/* Inactive due to HW failure */
+/* Process of being modified, deallocated, or quiesced */
+#define VAS_WIN_MOD_IN_PROCESS	0x3
+
+#define VAS_COPY_PASTE_USER_MODE	0x00000001
+#define VAS_COP_OP_USER_MODE		0x00000010
+
+/*
+ * Co-processor feature - GZIP QoS windows or GZIP default windows
+ */
+enum vas_cop_feat_type {
+	VAS_GZIP_QOS_FEAT_TYPE,
+	VAS_GZIP_DEF_FEAT_TYPE,
+	VAS_MAX_FEAT_TYPE,
+};
+
+/*
+ * Use to get feature specific capabilities from the
+ * hypervisor.
+ */
+struct hv_vas_cop_feat_caps {
+	__be64	descriptor;
+	u8	win_type;		/* Default or QoS type */
+	u8	user_mode;
+	__be16	max_lpar_creds;
+	__be16	max_win_creds;
+	union {
+		__be16	reserved;
+		__be16	def_lpar_creds; /* Used for default capabilities */
+	};
+	__be16	target_lpar_creds;
+} __packed __aligned(0x1000);
+
+/*
+ * Feature specific (QoS or default) capabilities.
+ */
+struct vas_cop_feat_caps {
+	u64		descriptor;
+	u8		win_type;	/* Default or QoS type */
+	u8		user_mode;	/* User mode copy/paste or COP HCALL */
+	u16		max_lpar_creds;	/* Max credits available in LPAR */
+	/* Max credits can be assigned per window */
+	u16		max_win_creds;
+	union {
+		u16	reserved;	/* Used for QoS credit type */
+		u16	def_lpar_creds; /* Used for default credit type */
+	};
+	/* Total LPAR available credits. Can be different from max LPAR */
+	/* credits due to DLPAR operation */
+	atomic_t	target_lpar_creds;
+	atomic_t	used_lpar_creds; /* Used credits so far */
+	u16		avail_lpar_creds; /* Remaining available credits */
+};
+
+/*
+ * Feature (QoS or Default) specific to store capabilities and
+ * the list of open windows.
+ */
+struct vas_caps {
+	struct vas_cop_feat_caps caps;
+	struct list_head list;	/* List of open windows */
+};
+
+/*
+ * To get window information from the hypervisor.
+ */
+struct hv_vas_win_lpar {
+	__be16	version;
+	u8	win_type;
+	u8	status;
+	__be16	credits;	/* No of credits assigned to this window */
+	__be16	reserved;
+	__be32	pid;		/* LPAR Process ID */
+	__be32	tid;		/* LPAR Thread ID */
+	__be64	win_addr;	/* Paste address */
+	__be32	interrupt;	/* Interrupt when NX request completes */
+	__be32	fault;		/* Interrupt when NX sees fault */
+	/* Associativity Domain Identifiers as returned in */
+	/* H_HOME_NODE_ASSOCIATIVITY */
+	__be64	domain[6];
+	__be64	win_util;	/* Number of bytes processed */
+} __packed __aligned(0x1000);
+
+struct pseries_vas_window {
+	struct vas_window vas_win;
+	u64 win_addr;		/* Physical paste address */
+	u8 win_type;		/* QoS or Default window */
+	u32 complete_irq;	/* Completion interrupt */
+	u32 fault_irq;		/* Fault interrupt */
+	u64 domain[6];		/* Associativity domain Ids */
+				/* this window is allocated */
+	u64 util;
+
+	/* List of windows opened which is used for LPM */
+	struct list_head win_list;
+	u64 flags;
+	char *name;
+	int fault_virq;
+};
+#endif /* _VAS_H */