Merge tag 'powerpc-6.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Add initial support to recognise the HeXin C2000 processor.

 - Add papr-vpd and papr-sysparm character device drivers for VPD &
   sysparm retrieval, so userspace tools can be adapted to avoid doing
   raw firmware calls from userspace.

 - Sched domains optimisations for shared processor partitions on
   P9/P10.

 - A series of optimisations for KVM running as a nested HV under
   PowerVM.

 - Other small features and fixes.

Thanks to Aditya Gupta, Aneesh Kumar K.V, Arnd Bergmann, Christophe
Leroy, Colin Ian King, Dario Binacchi, David Heidelberg, Geoff Levand,
Gustavo A. R. Silva, Haoran Liu, Jordan Niethe, Kajol Jain, Kevin Hao,
Kunwu Chan, Li kunyu, Li zeming, Masahiro Yamada, Michal Suchánek,
Nathan Lynch, Naveen N Rao, Nicholas Piggin, Randy Dunlap, Sathvika
Vasireddy, Srikar Dronamraju, Stephen Rothwell, Vaibhav Jain, and
Zhao Ke.

* tag 'powerpc-6.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (96 commits)
  powerpc/ps3_defconfig: Disable PPC64_BIG_ENDIAN_ELF_ABI_V2
  powerpc/86xx: Drop unused CONFIG_MPC8610
  powerpc/powernv: Add error handling to opal_prd_range_is_valid
  selftests/powerpc: Fix spelling mistake "EACCESS" -> "EACCES"
  powerpc/hvcall: Reorder Nestedv2 hcall opcodes
  powerpc/ps3: Add missing set_freezable() for ps3_probe_thread()
  powerpc/mpc83xx: Use wait_event_freezable() for freezable kthread
  powerpc/mpc83xx: Add the missing set_freezable() for agent_thread_fn()
  powerpc/fsl: Fix fsl,tmu-calibration to match the schema
  powerpc/smp: Dynamically build Powerpc topology
  powerpc/smp: Avoid asym packing within thread_group of a core
  powerpc/smp: Add __ro_after_init attribute
  powerpc/smp: Disable MC domain for shared processor
  powerpc/smp: Enable Asym packing for cores on shared processor
  powerpc/sched: Cleanup vcpu_is_preempted()
  powerpc: add cpu_spec.cpu_features to vmcoreinfo
  powerpc/imc-pmu: Add a null pointer check in update_events_in_group()
  powerpc/powernv: Add a null pointer check in opal_powercap_init()
  powerpc/powernv: Add a null pointer check in opal_event_init()
  powerpc/powernv: Add a null pointer check to scom_debug_init_one()
  ...

7 files changed, 767 insertions, 16 deletions

diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 1476c5e4433c..f936962a2946 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -4,6 +4,7 @@ ccflags-$(CONFIG_PPC_PSERIES_DEBUG)	+= -DDEBUG
 
 obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
 			   of_helpers.o rtas-work-area.o papr-sysparm.o \
+			   papr-vpd.o \
 			   setup.o iommu.o event_sources.o ras.o \
 			   firmware.o power.o dlpar.o mobility.o rng.o \
 			   pci.o pci_dlpar.o eeh_pseries.o msi.o \
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index def184da51cf..b1ae0c0d1187 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -252,7 +252,7 @@ static int pseries_eeh_cap_start(struct pci_dn *pdn)
 	if (!pdn)
 		return 0;
 
-	rtas_read_config(pdn, PCI_STATUS, 2, &status);
+	rtas_pci_dn_read_config(pdn, PCI_STATUS, 2, &status);
 	if (!(status & PCI_STATUS_CAP_LIST))
 		return 0;
 
@@ -270,11 +270,11 @@ static int pseries_eeh_find_cap(struct pci_dn *pdn, int cap)
 		return 0;
 
         while (cnt--) {
-		rtas_read_config(pdn, pos, 1, &pos);
+		rtas_pci_dn_read_config(pdn, pos, 1, &pos);
 		if (pos < 0x40)
 			break;
 		pos &= ~3;
-		rtas_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
+		rtas_pci_dn_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
 		if (id == 0xff)
 			break;
 		if (id == cap)
@@ -294,7 +294,7 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap)
 
 	if (!edev || !edev->pcie_cap)
 		return 0;
-	if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+	if (rtas_pci_dn_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
 		return 0;
 	else if (!header)
 		return 0;
@@ -307,7 +307,7 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap)
 		if (pos < 256)
 			break;
 
-		if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+		if (rtas_pci_dn_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
 			break;
 	}
 
@@ -412,8 +412,8 @@ static void pseries_eeh_init_edev(struct pci_dn *pdn)
 	if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
 		edev->mode |= EEH_DEV_BRIDGE;
 		if (edev->pcie_cap) {
-			rtas_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
-					 2, &pcie_flags);
+			rtas_pci_dn_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
+						2, &pcie_flags);
 			pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4;
 			if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT)
 				edev->mode |= EEH_DEV_ROOT_PORT;
@@ -676,7 +676,7 @@ static int pseries_eeh_read_config(struct eeh_dev *edev, int where, int size, u3
 {
 	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
-	return rtas_read_config(pdn, where, size, val);
+	return rtas_pci_dn_read_config(pdn, where, size, val);
 }
 
 /**
@@ -692,7 +692,7 @@ static int pseries_eeh_write_config(struct eeh_dev *edev, int where, int size, u
 {
 	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
-	return rtas_write_config(pdn, where, size, val);
+	return rtas_pci_dn_write_config(pdn, where, size, val);
 }
 
 #ifdef CONFIG_PCI_IOV
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index a43bfb01720a..3fe3ddb30c04 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -208,8 +208,10 @@ static int dlpar_change_lmb_state(struct drmem_lmb *lmb, bool online)
 	int rc;
 
 	mem_block = lmb_to_memblock(lmb);
-	if (!mem_block)
+	if (!mem_block) {
+		pr_err("Failed memory block lookup for LMB 0x%x\n", lmb->drc_index);
 		return -EINVAL;
+	}
 
 	if (online && mem_block->dev.offline)
 		rc = device_online(&mem_block->dev);
@@ -436,14 +438,15 @@ static int dlpar_memory_remove_by_index(u32 drc_index)
 		}
 	}
 
-	if (!lmb_found)
+	if (!lmb_found) {
+		pr_debug("Failed to look up LMB for drc index %x\n", drc_index);
 		rc = -EINVAL;
-
-	if (rc)
+	} else if (rc) {
 		pr_debug("Failed to hot-remove memory at %llx\n",
 			 lmb->base_addr);
-	else
+	} else {
 		pr_debug("Memory at %llx was hot-removed\n", lmb->base_addr);
+	}
 
 	return rc;
 }
@@ -575,6 +578,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 	rc = update_lmb_associativity_index(lmb);
 	if (rc) {
 		dlpar_release_drc(lmb->drc_index);
+		pr_err("Failed to configure LMB 0x%x\n", lmb->drc_index);
 		return rc;
 	}
 
@@ -588,12 +592,14 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 	/* Add the memory */
 	rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_MEMMAP_ON_MEMORY);
 	if (rc) {
+		pr_err("Failed to add LMB 0x%x to node %u", lmb->drc_index, nid);
 		invalidate_lmb_associativity_index(lmb);
 		return rc;
 	}
 
 	rc = dlpar_online_lmb(lmb);
 	if (rc) {
+		pr_err("Failed to online LMB 0x%x on node %u\n", lmb->drc_index, nid);
 		__remove_memory(lmb->base_addr, block_sz);
 		invalidate_lmb_associativity_index(lmb);
 	} else {
diff --git a/arch/powerpc/platforms/pseries/papr-sysparm.c b/arch/powerpc/platforms/pseries/papr-sysparm.c
index fedc61599e6c..7063ce8884e4 100644
--- a/arch/powerpc/platforms/pseries/papr-sysparm.c
+++ b/arch/powerpc/platforms/pseries/papr-sysparm.c
@@ -2,14 +2,20 @@
 
 #define pr_fmt(fmt)	"papr-sysparm: " fmt
 
+#include <linux/anon_inodes.h>
 #include <linux/bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/miscdevice.h>
 #include <linux/printk.h>
 #include <linux/slab.h>
-#include <asm/rtas.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
 #include <asm/papr-sysparm.h>
 #include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
 
 struct papr_sysparm_buf *papr_sysparm_buf_alloc(void)
 {
@@ -23,6 +29,46 @@ void papr_sysparm_buf_free(struct papr_sysparm_buf *buf)
 	kfree(buf);
 }
 
+static size_t papr_sysparm_buf_get_length(const struct papr_sysparm_buf *buf)
+{
+	return be16_to_cpu(buf->len);
+}
+
+static void papr_sysparm_buf_set_length(struct papr_sysparm_buf *buf, size_t length)
+{
+	WARN_ONCE(length > sizeof(buf->val),
+		  "bogus length %zu, clamping to safe value", length);
+	length = min(sizeof(buf->val), length);
+	buf->len = cpu_to_be16(length);
+}
+
+/*
+ * For use on buffers returned from ibm,get-system-parameter before
+ * returning them to callers. Ensures the encoded length of valid data
+ * cannot overrun buf->val[].
+ */
+static void papr_sysparm_buf_clamp_length(struct papr_sysparm_buf *buf)
+{
+	papr_sysparm_buf_set_length(buf, papr_sysparm_buf_get_length(buf));
+}
+
+/*
+ * Perform some basic diligence on the system parameter buffer before
+ * submitting it to RTAS.
+ */
+static bool papr_sysparm_buf_can_submit(const struct papr_sysparm_buf *buf)
+{
+	/*
+	 * Firmware ought to reject buffer lengths that exceed the
+	 * maximum specified in PAPR, but there's no reason for the
+	 * kernel to allow them either.
+	 */
+	if (papr_sysparm_buf_get_length(buf) > sizeof(buf->val))
+		return false;
+
+	return true;
+}
+
 /**
  * papr_sysparm_get() - Retrieve the value of a PAPR system parameter.
  * @param: PAPR system parameter token as described in
@@ -47,7 +93,6 @@ void papr_sysparm_buf_free(struct papr_sysparm_buf *buf)
  *
  * Return: 0 on success, -errno otherwise. @buf is unmodified on error.
  */
-
 int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
 {
 	const s32 token = rtas_function_token(RTAS_FN_IBM_GET_SYSTEM_PARAMETER);
@@ -63,6 +108,9 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
 	if (token == RTAS_UNKNOWN_SERVICE)
 		return -ENOENT;
 
+	if (!papr_sysparm_buf_can_submit(buf))
+		return -EINVAL;
+
 	work_area = rtas_work_area_alloc(sizeof(*buf));
 
 	memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf));
@@ -77,6 +125,7 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
 	case 0:
 		ret = 0;
 		memcpy(buf, rtas_work_area_raw_buf(work_area), sizeof(*buf));
+		papr_sysparm_buf_clamp_length(buf);
 		break;
 	case -3: /* parameter not implemented */
 		ret = -EOPNOTSUPP;
@@ -115,6 +164,9 @@ int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf)
 	if (token == RTAS_UNKNOWN_SERVICE)
 		return -ENOENT;
 
+	if (!papr_sysparm_buf_can_submit(buf))
+		return -EINVAL;
+
 	work_area = rtas_work_area_alloc(sizeof(*buf));
 
 	memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf));
@@ -149,3 +201,152 @@ int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf)
 
 	return ret;
 }
+
+static struct papr_sysparm_buf *
+papr_sysparm_buf_from_user(const struct papr_sysparm_io_block __user *user_iob)
+{
+	struct papr_sysparm_buf *kern_spbuf;
+	long err;
+	u16 len;
+
+	/*
+	 * The length of valid data that userspace claims to be in
+	 * user_iob->data[].
+	 */
+	if (get_user(len, &user_iob->length))
+		return ERR_PTR(-EFAULT);
+
+	static_assert(sizeof(user_iob->data) >= PAPR_SYSPARM_MAX_INPUT);
+	static_assert(sizeof(kern_spbuf->val) >= PAPR_SYSPARM_MAX_INPUT);
+
+	if (len > PAPR_SYSPARM_MAX_INPUT)
+		return ERR_PTR(-EINVAL);
+
+	kern_spbuf = papr_sysparm_buf_alloc();
+	if (!kern_spbuf)
+		return ERR_PTR(-ENOMEM);
+
+	papr_sysparm_buf_set_length(kern_spbuf, len);
+
+	if (len > 0 && copy_from_user(kern_spbuf->val, user_iob->data, len)) {
+		err = -EFAULT;
+		goto free_sysparm_buf;
+	}
+
+	return kern_spbuf;
+
+free_sysparm_buf:
+	papr_sysparm_buf_free(kern_spbuf);
+	return ERR_PTR(err);
+}
+
+static int papr_sysparm_buf_to_user(const struct papr_sysparm_buf *kern_spbuf,
+				    struct papr_sysparm_io_block __user *user_iob)
+{
+	u16 len_out = papr_sysparm_buf_get_length(kern_spbuf);
+
+	if (put_user(len_out, &user_iob->length))
+		return -EFAULT;
+
+	static_assert(sizeof(user_iob->data) >= PAPR_SYSPARM_MAX_OUTPUT);
+	static_assert(sizeof(kern_spbuf->val) >= PAPR_SYSPARM_MAX_OUTPUT);
+
+	if (copy_to_user(user_iob->data, kern_spbuf->val, PAPR_SYSPARM_MAX_OUTPUT))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long papr_sysparm_ioctl_get(struct papr_sysparm_io_block __user *user_iob)
+{
+	struct papr_sysparm_buf *kern_spbuf;
+	papr_sysparm_t param;
+	long ret;
+
+	if (get_user(param.token, &user_iob->parameter))
+		return -EFAULT;
+
+	kern_spbuf = papr_sysparm_buf_from_user(user_iob);
+	if (IS_ERR(kern_spbuf))
+		return PTR_ERR(kern_spbuf);
+
+	ret = papr_sysparm_get(param, kern_spbuf);
+	if (ret)
+		goto free_sysparm_buf;
+
+	ret = papr_sysparm_buf_to_user(kern_spbuf, user_iob);
+	if (ret)
+		goto free_sysparm_buf;
+
+	ret = 0;
+
+free_sysparm_buf:
+	papr_sysparm_buf_free(kern_spbuf);
+	return ret;
+}
+
+
+static long papr_sysparm_ioctl_set(struct papr_sysparm_io_block __user *user_iob)
+{
+	struct papr_sysparm_buf *kern_spbuf;
+	papr_sysparm_t param;
+	long ret;
+
+	if (get_user(param.token, &user_iob->parameter))
+		return -EFAULT;
+
+	kern_spbuf = papr_sysparm_buf_from_user(user_iob);
+	if (IS_ERR(kern_spbuf))
+		return PTR_ERR(kern_spbuf);
+
+	ret = papr_sysparm_set(param, kern_spbuf);
+	if (ret)
+		goto free_sysparm_buf;
+
+	ret = 0;
+
+free_sysparm_buf:
+	papr_sysparm_buf_free(kern_spbuf);
+	return ret;
+}
+
+static long papr_sysparm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (__force void __user *)arg;
+	long ret;
+
+	switch (ioctl) {
+	case PAPR_SYSPARM_IOC_GET:
+		ret = papr_sysparm_ioctl_get(argp);
+		break;
+	case PAPR_SYSPARM_IOC_SET:
+		if (filp->f_mode & FMODE_WRITE)
+			ret = papr_sysparm_ioctl_set(argp);
+		else
+			ret = -EBADF;
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations papr_sysparm_ops = {
+	.unlocked_ioctl = papr_sysparm_ioctl,
+};
+
+static struct miscdevice papr_sysparm_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-sysparm",
+	.fops = &papr_sysparm_ops,
+};
+
+static __init int papr_sysparm_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_GET_SYSTEM_PARAMETER))
+		return -ENODEV;
+
+	return misc_register(&papr_sysparm_dev);
+}
+machine_device_initcall(pseries, papr_sysparm_init);
diff --git a/arch/powerpc/platforms/pseries/papr-vpd.c b/arch/powerpc/platforms/pseries/papr-vpd.c
new file mode 100644
index 000000000000..c29e85db5f35
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-vpd.c
@@ -0,0 +1,541 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-vpd: " fmt
+
+#include <linux/anon_inodes.h>
+#include <linux/build_bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/lockdep.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/string_helpers.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
+#include <asm/papr-vpd.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <uapi/asm/papr-vpd.h>
+
+/*
+ * Function-specific return values for ibm,get-vpd, derived from PAPR+
+ * v2.13 7.3.20 "ibm,get-vpd RTAS Call".
+ */
+#define RTAS_IBM_GET_VPD_COMPLETE    0 /* All VPD has been retrieved. */
+#define RTAS_IBM_GET_VPD_MORE_DATA   1 /* More VPD is available. */
+#define RTAS_IBM_GET_VPD_START_OVER -4 /* VPD changed, restart call sequence. */
+
+/**
+ * struct rtas_ibm_get_vpd_params - Parameters (in and out) for ibm,get-vpd.
+ * @loc_code:  In: Caller-provided location code buffer. Must be RTAS-addressable.
+ * @work_area: In: Caller-provided work area buffer for results.
+ * @sequence:  In: Sequence number. Out: Next sequence number.
+ * @written:   Out: Bytes written by ibm,get-vpd to @work_area.
+ * @status:    Out: RTAS call status.
+ */
+struct rtas_ibm_get_vpd_params {
+	const struct papr_location_code *loc_code;
+	struct rtas_work_area *work_area;
+	u32 sequence;
+	u32 written;
+	s32 status;
+};
+
+/**
+ * rtas_ibm_get_vpd() - Call ibm,get-vpd to fill a work area buffer.
+ * @params: See &struct rtas_ibm_get_vpd_params.
+ *
+ * Calls ibm,get-vpd until it errors or successfully deposits data
+ * into the supplied work area. Handles RTAS retry statuses. Maps RTAS
+ * error statuses to reasonable errno values.
+ *
+ * The caller is expected to invoke rtas_ibm_get_vpd() multiple times
+ * to retrieve all the VPD for the provided location code. Only one
+ * sequence should be in progress at any time; starting a new sequence
+ * will disrupt any sequence already in progress. Serialization of VPD
+ * retrieval sequences is the responsibility of the caller.
+ *
+ * The caller should inspect @params.status to determine whether more
+ * calls are needed to complete the sequence.
+ *
+ * Context: May sleep.
+ * Return: -ve on error, 0 otherwise.
+ */
+static int rtas_ibm_get_vpd(struct rtas_ibm_get_vpd_params *params)
+{
+	const struct papr_location_code *loc_code = params->loc_code;
+	struct rtas_work_area *work_area = params->work_area;
+	u32 rets[2];
+	s32 fwrc;
+	int ret;
+
+	lockdep_assert_held(&rtas_ibm_get_vpd_lock);
+
+	do {
+		fwrc = rtas_call(rtas_function_token(RTAS_FN_IBM_GET_VPD), 4, 3,
+				 rets,
+				 __pa(loc_code),
+				 rtas_work_area_phys(work_area),
+				 rtas_work_area_size(work_area),
+				 params->sequence);
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_INVALID_PARAMETER:
+		ret = -EINVAL;
+		break;
+	case RTAS_IBM_GET_VPD_START_OVER:
+		ret = -EAGAIN;
+		break;
+	case RTAS_IBM_GET_VPD_MORE_DATA:
+		params->sequence = rets[0];
+		fallthrough;
+	case RTAS_IBM_GET_VPD_COMPLETE:
+		params->written = rets[1];
+		/*
+		 * Kernel or firmware bug, do not continue.
+		 */
+		if (WARN(params->written > rtas_work_area_size(work_area),
+			 "possible write beyond end of work area"))
+			ret = -EFAULT;
+		else
+			ret = 0;
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,get-vpd status %d\n", fwrc);
+		break;
+	}
+
+	params->status = fwrc;
+	return ret;
+}
+
+/*
+ * Internal VPD "blob" APIs for accumulating ibm,get-vpd results into
+ * an immutable buffer to be attached to a file descriptor.
+ */
+struct vpd_blob {
+	const char *data;
+	size_t len;
+};
+
+static bool vpd_blob_has_data(const struct vpd_blob *blob)
+{
+	return blob->data && blob->len;
+}
+
+static void vpd_blob_free(const struct vpd_blob *blob)
+{
+	if (blob) {
+		kvfree(blob->data);
+		kfree(blob);
+	}
+}
+
+/**
+ * vpd_blob_extend() - Append data to a &struct vpd_blob.
+ * @blob: The blob to extend.
+ * @data: The new data to append to @blob.
+ * @len:  The length of @data.
+ *
+ * Context: May sleep.
+ * Return: -ENOMEM on allocation failure, 0 otherwise.
+ */
+static int vpd_blob_extend(struct vpd_blob *blob, const char *data, size_t len)
+{
+	const size_t new_len = blob->len + len;
+	const size_t old_len = blob->len;
+	const char *old_ptr = blob->data;
+	char *new_ptr;
+
+	new_ptr = old_ptr ?
+		kvrealloc(old_ptr, old_len, new_len, GFP_KERNEL_ACCOUNT) :
+		kvmalloc(len, GFP_KERNEL_ACCOUNT);
+
+	if (!new_ptr)
+		return -ENOMEM;
+
+	memcpy(&new_ptr[old_len], data, len);
+	blob->data = new_ptr;
+	blob->len = new_len;
+	return 0;
+}
+
+/**
+ * vpd_blob_generate() - Construct a new &struct vpd_blob.
+ * @generator: Function that supplies the blob data.
+ * @arg:       Context pointer supplied by caller, passed to @generator.
+ *
+ * The @generator callback is invoked until it returns NULL. @arg is
+ * passed to @generator in its first argument on each call. When
+ * @generator returns data, it should store the data length in its
+ * second argument.
+ *
+ * Context: May sleep.
+ * Return: A completely populated &struct vpd_blob, or NULL on error.
+ */
+static const struct vpd_blob *
+vpd_blob_generate(const char * (*generator)(void *, size_t *), void *arg)
+{
+	struct vpd_blob *blob;
+	const char *buf;
+	size_t len;
+	int err = 0;
+
+	blob  = kzalloc(sizeof(*blob), GFP_KERNEL_ACCOUNT);
+	if (!blob)
+		return NULL;
+
+	while (err == 0 && (buf = generator(arg, &len)))
+		err = vpd_blob_extend(blob, buf, len);
+
+	if (err != 0 || !vpd_blob_has_data(blob))
+		goto free_blob;
+
+	return blob;
+free_blob:
+	vpd_blob_free(blob);
+	return NULL;
+}
+
+/*
+ * Internal VPD sequence APIs. A VPD sequence is a series of calls to
+ * ibm,get-vpd for a given location code. The sequence ends when an
+ * error is encountered or all VPD for the location code has been
+ * returned.
+ */
+
+/**
+ * struct vpd_sequence - State for managing a VPD sequence.
+ * @error:  Shall be zero as long as the sequence has not encountered an error,
+ *          -ve errno otherwise. Use vpd_sequence_set_err() to update this.
+ * @params: Parameter block to pass to rtas_ibm_get_vpd().
+ */
+struct vpd_sequence {
+	int error;
+	struct rtas_ibm_get_vpd_params params;
+};
+
+/**
+ * vpd_sequence_begin() - Begin a VPD retrieval sequence.
+ * @seq:      Uninitialized sequence state.
+ * @loc_code: Location code that defines the scope of the VPD to return.
+ *
+ * Initializes @seq with the resources necessary to carry out a VPD
+ * sequence. Callers must pass @seq to vpd_sequence_end() regardless
+ * of whether the sequence succeeds.
+ *
+ * Context: May sleep.
+ */
+static void vpd_sequence_begin(struct vpd_sequence *seq,
+			       const struct papr_location_code *loc_code)
+{
+	/*
+	 * Use a static data structure for the location code passed to
+	 * RTAS to ensure it's in the RMA and avoid a separate work
+	 * area allocation. Guarded by the function lock.
+	 */
+	static struct papr_location_code static_loc_code;
+
+	/*
+	 * We could allocate the work area before acquiring the
+	 * function lock, but that would allow concurrent requests to
+	 * exhaust the limited work area pool for no benefit. So
+	 * allocate the work area under the lock.
+	 */
+	mutex_lock(&rtas_ibm_get_vpd_lock);
+	static_loc_code = *loc_code;
+	*seq = (struct vpd_sequence) {
+		.params = {
+			.work_area = rtas_work_area_alloc(SZ_4K),
+			.loc_code = &static_loc_code,
+			.sequence = 1,
+		},
+	};
+}
+
+/**
+ * vpd_sequence_end() - Finalize a VPD retrieval sequence.
+ * @seq: Sequence state.
+ *
+ * Releases resources obtained by vpd_sequence_begin().
+ */
+static void vpd_sequence_end(struct vpd_sequence *seq)
+{
+	rtas_work_area_free(seq->params.work_area);
+	mutex_unlock(&rtas_ibm_get_vpd_lock);
+}
+
+/**
+ * vpd_sequence_should_stop() - Determine whether a VPD retrieval sequence
+ *                              should continue.
+ * @seq: VPD sequence state.
+ *
+ * Examines the sequence error state and outputs of the last call to
+ * ibm,get-vpd to determine whether the sequence in progress should
+ * continue or stop.
+ *
+ * Return: True if the sequence has encountered an error or if all VPD for
+ *         this sequence has been retrieved. False otherwise.
+ */
+static bool vpd_sequence_should_stop(const struct vpd_sequence *seq)
+{
+	bool done;
+
+	if (seq->error)
+		return true;
+
+	switch (seq->params.status) {
+	case 0:
+		if (seq->params.written == 0)
+			done = false; /* Initial state. */
+		else
+			done = true; /* All data consumed. */
+		break;
+	case 1:
+		done = false; /* More data available. */
+		break;
+	default:
+		done = true; /* Error encountered. */
+		break;
+	}
+
+	return done;
+}
+
+static int vpd_sequence_set_err(struct vpd_sequence *seq, int err)
+{
+	/* Preserve the first error recorded. */
+	if (seq->error == 0)
+		seq->error = err;
+
+	return seq->error;
+}
+
+/*
+ * Generator function to be passed to vpd_blob_generate().
+ */
+static const char *vpd_sequence_fill_work_area(void *arg, size_t *len)
+{
+	struct vpd_sequence *seq = arg;
+	struct rtas_ibm_get_vpd_params *p = &seq->params;
+
+	if (vpd_sequence_should_stop(seq))
+		return NULL;
+	if (vpd_sequence_set_err(seq, rtas_ibm_get_vpd(p)))
+		return NULL;
+	*len = p->written;
+	return rtas_work_area_raw_buf(p->work_area);
+}
+
+/*
+ * Higher-level VPD retrieval code below. These functions use the
+ * vpd_blob_* and vpd_sequence_* APIs defined above to create fd-based
+ * VPD handles for consumption by user space.
+ */
+
+/**
+ * papr_vpd_run_sequence() - Run a single VPD retrieval sequence.
+ * @loc_code: Location code that defines the scope of VPD to return.
+ *
+ * Context: May sleep. Holds a mutex and an RTAS work area for its
+ *          duration. Typically performs multiple sleepable slab
+ *          allocations.
+ *
+ * Return: A populated &struct vpd_blob on success. Encoded error
+ * pointer otherwise.
+ */
+static const struct vpd_blob *papr_vpd_run_sequence(const struct papr_location_code *loc_code)
+{
+	const struct vpd_blob *blob;
+	struct vpd_sequence seq;
+
+	vpd_sequence_begin(&seq, loc_code);
+	blob = vpd_blob_generate(vpd_sequence_fill_work_area, &seq);
+	if (!blob)
+		vpd_sequence_set_err(&seq, -ENOMEM);
+	vpd_sequence_end(&seq);
+
+	if (seq.error) {
+		vpd_blob_free(blob);
+		return ERR_PTR(seq.error);
+	}
+
+	return blob;
+}
+
+/**
+ * papr_vpd_retrieve() - Return the VPD for a location code.
+ * @loc_code: Location code that defines the scope of VPD to return.
+ *
+ * Run VPD sequences against @loc_code until a blob is successfully
+ * instantiated, or a hard error is encountered, or a fatal signal is
+ * pending.
+ *
+ * Context: May sleep.
+ * Return: A fully populated VPD blob when successful. Encoded error
+ * pointer otherwise.
+ */
+static const struct vpd_blob *papr_vpd_retrieve(const struct papr_location_code *loc_code)
+{
+	const struct vpd_blob *blob;
+
+	/*
+	 * EAGAIN means the sequence errored with a -4 (VPD changed)
+	 * status from ibm,get-vpd, and we should attempt a new
+	 * sequence. PAPR+ v2.13 R1–7.3.20–5 indicates that this
+	 * should be a transient condition, not something that happens
+	 * continuously. But we'll stop trying on a fatal signal.
+	 */
+	do {
+		blob = papr_vpd_run_sequence(loc_code);
+		if (!IS_ERR(blob)) /* Success. */
+			break;
+		if (PTR_ERR(blob) != -EAGAIN) /* Hard error. */
+			break;
+		pr_info_ratelimited("VPD changed during retrieval, retrying\n");
+		cond_resched();
+	} while (!fatal_signal_pending(current));
+
+	return blob;
+}
+
+static ssize_t papr_vpd_handle_read(struct file *file, char __user *buf, size_t size, loff_t *off)
+{
+	const struct vpd_blob *blob = file->private_data;
+
+	/* bug: we should not instantiate a handle without any data attached. */
+	if (!vpd_blob_has_data(blob)) {
+		pr_err_once("handle without data\n");
+		return -EIO;
+	}
+
+	return simple_read_from_buffer(buf, size, off, blob->data, blob->len);
+}
+
+static int papr_vpd_handle_release(struct inode *inode, struct file *file)
+{
+	const struct vpd_blob *blob = file->private_data;
+
+	vpd_blob_free(blob);
+
+	return 0;
+}
+
+static loff_t papr_vpd_handle_seek(struct file *file, loff_t off, int whence)
+{
+	const struct vpd_blob *blob = file->private_data;
+
+	return fixed_size_llseek(file, off, whence, blob->len);
+}
+
+
+static const struct file_operations papr_vpd_handle_ops = {
+	.read = papr_vpd_handle_read,
+	.llseek = papr_vpd_handle_seek,
+	.release = papr_vpd_handle_release,
+};
+
+/**
+ * papr_vpd_create_handle() - Create a fd-based handle for reading VPD.
+ * @ulc: Location code in user memory; defines the scope of the VPD to
+ *       retrieve.
+ *
+ * Handler for PAPR_VPD_IOC_CREATE_HANDLE ioctl command. Validates
+ * @ulc and instantiates an immutable VPD "blob" for it. The blob is
+ * attached to a file descriptor for reading by user space. The memory
+ * backing the blob is freed when the file is released.
+ *
+ * The entire requested VPD is retrieved by this call and all
+ * necessary RTAS interactions are performed before returning the fd
+ * to user space. This keeps the read handler simple and ensures that
+ * the kernel can prevent interleaving of ibm,get-vpd call sequences.
+ *
+ * Return: The installed fd number if successful, -ve errno otherwise.
+ */
+static long papr_vpd_create_handle(struct papr_location_code __user *ulc)
+{
+	struct papr_location_code klc;
+	const struct vpd_blob *blob;
+	struct file *file;
+	long err;
+	int fd;
+
+	if (copy_from_user(&klc, ulc, sizeof(klc)))
+		return -EFAULT;
+
+	if (!string_is_terminated(klc.str, ARRAY_SIZE(klc.str)))
+		return -EINVAL;
+
+	blob = papr_vpd_retrieve(&klc);
+	if (IS_ERR(blob))
+		return PTR_ERR(blob);
+
+	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		err = fd;
+		goto free_blob;
+	}
+
+	file = anon_inode_getfile("[papr-vpd]", &papr_vpd_handle_ops,
+				  (void *)blob, O_RDONLY);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto put_fd;
+	}
+
+	file->f_mode |= FMODE_LSEEK | FMODE_PREAD;
+	fd_install(fd, file);
+	return fd;
+put_fd:
+	put_unused_fd(fd);
+free_blob:
+	vpd_blob_free(blob);
+	return err;
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr-vpd.
+ */
+static long papr_vpd_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (__force void __user *)arg;
+	long ret;
+
+	switch (ioctl) {
+	case PAPR_VPD_IOC_CREATE_HANDLE:
+		ret = papr_vpd_create_handle(argp);
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations papr_vpd_ops = {
+	.unlocked_ioctl = papr_vpd_dev_ioctl,
+};
+
+static struct miscdevice papr_vpd_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-vpd",
+	.fops = &papr_vpd_ops,
+};
+
+static __init int papr_vpd_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_GET_VPD))
+		return -ENODEV;
+
+	return misc_register(&papr_vpd_dev);
+}
+machine_device_initcall(pseries, papr_vpd_init);
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 8376f03f932a..bba4ad192b0f 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -55,6 +55,7 @@ extern int dlpar_detach_node(struct device_node *);
 extern int dlpar_acquire_drc(u32 drc_index);
 extern int dlpar_release_drc(u32 drc_index);
 extern int dlpar_unisolate_drc(u32 drc_index);
+extern void post_mobility_fixup(void);
 
 void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog);
 int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_errlog);
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 5c43435472cc..382003dfdb9a 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -13,6 +13,7 @@
 #include <asm/mmu.h>
 #include <asm/rtas.h>
 #include <asm/topology.h>
+#include "pseries.h"
 
 static struct device suspend_dev;