Merge tag 'powerpc-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Add support for (optionally) using queued spinlocks & rwlocks.

 - Support for a new faster system call ABI using the scv instruction on
   Power9 or later.

 - Drop support for the PROT_SAO mmap/mprotect flag as it will be
   unsupported on Power10 and future processors, leaving us with no way
   to implement the functionality it requests. This risks breaking
   userspace, though we believe it is unused in practice.

 - A bug fix for, and then the removal of, our custom stack expansion
   checking. We now allow stack expansion up to the rlimit, like other
   architectures.

 - Remove the remnants of our (previously disabled) topology update
   code, which tried to react to NUMA layout changes on virtualised
   systems, but was prone to crashes and other problems.

 - Add PMU support for Power10 CPUs.

 - A change to our signal trampoline so that we don't unbalance the link
   stack (branch return predictor) in the signal delivery path.

 - Lots of other cleanups, refactorings, smaller features and so on as
   usual.

Thanks to: Abhishek Goel, Alastair D'Silva, Alexander A. Klimov, Alexey
Kardashevskiy, Alistair Popple, Andrew Donnellan, Aneesh Kumar K.V, Anju
T Sudhakar, Anton Blanchard, Arnd Bergmann, Athira Rajeev, Balamuruhan
S, Bharata B Rao, Bill Wendling, Bin Meng, Cédric Le Goater, Chris
Packham, Christophe Leroy, Christoph Hellwig, Daniel Axtens, Dan
Williams, David Lamparter, Desnes A. Nunes do Rosario, Erhard F., Finn
Thain, Frederic Barrat, Ganesh Goudar, Gautham R. Shenoy, Geoff Levand,
Greg Kurz, Gustavo A. R. Silva, Hari Bathini, Harish, Imre Kaloz, Joel
Stanley, Joe Perches, John Crispin, Jordan Niethe, Kajol Jain, Kamalesh
Babulal, Kees Cook, Laurent Dufour, Leonardo Bras, Li RongQing, Madhavan
Srinivasan, Mahesh Salgaonkar, Mark Cave-Ayland, Michal Suchanek, Milton
Miller, Mimi Zohar, Murilo Opsfelder Araujo, Nathan Chancellor, Nathan
Lynch, Naveen N. Rao, Nayna Jain, Nicholas Piggin, Oliver O'Halloran,
Palmer Dabbelt, Pedro Miraglia Franco de Carvalho, Philippe Bergheaud,
Pingfan Liu, Pratik Rajesh Sampat, Qian Cai, Qinglang Miao, Randy
Dunlap, Ravi Bangoria, Sachin Sant, Sam Bobroff, Sandipan Das, Santosh
Sivaraj, Satheesh Rajendran, Shirisha Ganta, Sourabh Jain, Srikar
Dronamraju, Stan Johnson, Stephen Rothwell, Thadeu Lima de Souza
Cascardo, Thiago Jung Bauermann, Tom Lane, Vaibhav Jain, Vladis Dronov,
Wei Yongjun, Wen Xiong, YueHaibing.

* tag 'powerpc-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (337 commits)
  selftests/powerpc: Fix pkey syscall redefinitions
  powerpc: Fix circular dependency between percpu.h and mmu.h
  powerpc/powernv/sriov: Fix use of uninitialised variable
  selftests/powerpc: Skip vmx/vsx/tar/etc tests on older CPUs
  powerpc/40x: Fix assembler warning about r0
  powerpc/papr_scm: Add support for fetching nvdimm 'fuel-gauge' metric
  powerpc/papr_scm: Fetch nvdimm performance stats from PHYP
  cpuidle: pseries: Fixup exit latency for CEDE(0)
  cpuidle: pseries: Add function to parse extended CEDE records
  cpuidle: pseries: Set the latency-hint before entering CEDE
  selftests/powerpc: Fix online CPU selection
  powerpc/perf: Consolidate perf_callchain_user_[64|32]()
  powerpc/pseries/hotplug-cpu: Remove double free in error path
  powerpc/pseries/mobility: Add pr_debug() for device tree changes
  powerpc/pseries/mobility: Set pr_fmt()
  powerpc/cacheinfo: Warn if cache object chain becomes unordered
  powerpc/cacheinfo: Improve diagnostics about malformed cache lists
  powerpc/cacheinfo: Use name@unit instead of full DT path in debug messages
  powerpc/cacheinfo: Set pr_fmt()
  powerpc: fix function annotations to avoid section mismatch warnings with gcc-10
  ...

1 files changed, 295 insertions, 1 deletions

diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 9c569078a09f..f439f0dfea7d 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -13,9 +13,11 @@
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/seq_buf.h>
+#include <linux/nd.h>
 
 #include <asm/plpar_wrappers.h>
 #include <asm/papr_pdsm.h>
+#include <asm/mce.h>
 
 #define BIND_ANY_ADDR (~0ul)
 
@@ -62,6 +64,26 @@
 				    PAPR_PMEM_HEALTH_FATAL |	\
 				    PAPR_PMEM_HEALTH_UNHEALTHY)
 
+#define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS)
+#define PAPR_SCM_PERF_STATS_VERSION 0x1
+
+/* Struct holding a single performance metric */
+struct papr_scm_perf_stat {
+	u8 stat_id[8];
+	__be64 stat_val;
+} __packed;
+
+/* Struct exchanged between kernel and PHYP for fetching drc perf stats */
+struct papr_scm_perf_stats {
+	u8 eye_catcher[8];
+	/* Should be PAPR_SCM_PERF_STATS_VERSION */
+	__be32 stats_version;
+	/* Number of stats following */
+	__be32 num_statistics;
+	/* zero or more performance matrics */
+	struct papr_scm_perf_stat scm_statistic[];
+} __packed;
+
 /* private struct associated with each region */
 struct papr_scm_priv {
 	struct platform_device *pdev;
@@ -80,6 +102,7 @@ struct papr_scm_priv {
 	struct resource res;
 	struct nd_region *region;
 	struct nd_interleave_set nd_set;
+	struct list_head region_list;
 
 	/* Protect dimm health data from concurrent read/writes */
 	struct mutex health_mutex;
@@ -89,8 +112,14 @@ struct papr_scm_priv {
 
 	/* Health information for the dimm */
 	u64 health_bitmap;
+
+	/* length of the stat buffer as expected by phyp */
+	size_t stat_buffer_len;
 };
 
+static LIST_HEAD(papr_nd_regions);
+static DEFINE_MUTEX(papr_ndr_lock);
+
 static int drc_pmem_bind(struct papr_scm_priv *p)
 {
 	unsigned long ret[PLPAR_HCALL_BUFSIZE];
@@ -195,6 +224,79 @@ 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
+ * 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
+ * hold them.
+ * - if buff_stats != NULL and num_stats > 0 then copy the requested
+ * performance-statistics to buff_stats.
+ */
+static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p,
+				    struct papr_scm_perf_stats *buff_stats,
+				    unsigned int num_stats)
+{
+	unsigned long ret[PLPAR_HCALL_BUFSIZE];
+	size_t size;
+	s64 rc;
+
+	/* Setup the out buffer */
+	if (buff_stats) {
+		memcpy(buff_stats->eye_catcher,
+		       PAPR_SCM_PERF_STATS_EYECATCHER, 8);
+		buff_stats->stats_version =
+			cpu_to_be32(PAPR_SCM_PERF_STATS_VERSION);
+		buff_stats->num_statistics =
+			cpu_to_be32(num_stats);
+
+		/*
+		 * Calculate the buffer size based on num-stats provided
+		 * or use the prefetched max buffer length
+		 */
+		if (num_stats)
+			/* Calculate size from the num_stats */
+			size = sizeof(struct papr_scm_perf_stats) +
+				num_stats * sizeof(struct papr_scm_perf_stat);
+		else
+			size = p->stat_buffer_len;
+	} else {
+		/* In case of no out buffer ignore the size */
+		size = 0;
+	}
+
+	/* Do the HCALL asking PHYP for info */
+	rc = plpar_hcall(H_SCM_PERFORMANCE_STATS, ret, p->drc_index,
+			 buff_stats ? virt_to_phys(buff_stats) : 0,
+			 size);
+
+	/* Check if the error was due to an unknown stat-id */
+	if (rc == H_PARTIAL) {
+		dev_err(&p->pdev->dev,
+			"Unknown performance stats, Err:0x%016lX\n", ret[0]);
+		return -ENOENT;
+	} else if (rc != H_SUCCESS) {
+		dev_err(&p->pdev->dev,
+			"Failed to query performance stats, Err:%lld\n", rc);
+		return -EIO;
+
+	} else if (!size) {
+		/* Handle case where stat buffer size was requested */
+		dev_dbg(&p->pdev->dev,
+			"Performance stats size %ld\n", ret[0]);
+		return ret[0];
+	}
+
+	/* Successfully fetched the requested stats from phyp */
+	dev_dbg(&p->pdev->dev,
+		"Performance stats returned %d stats\n",
+		be32_to_cpu(buff_stats->num_statistics));
+	return 0;
+}
+
+/*
  * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the
  * health information.
  */
@@ -416,6 +518,51 @@ static int is_cmd_valid(struct nvdimm *nvdimm, unsigned int cmd, void *buf,
 	return 0;
 }
 
+static int papr_pdsm_fuel_gauge(struct papr_scm_priv *p,
+				union nd_pdsm_payload *payload)
+{
+	int rc, size;
+	u64 statval;
+	struct papr_scm_perf_stat *stat;
+	struct papr_scm_perf_stats *stats;
+
+	/* Silently fail if fetching performance metrics isn't  supported */
+	if (!p->stat_buffer_len)
+		return 0;
+
+	/* Allocate request buffer enough to hold single performance stat */
+	size = sizeof(struct papr_scm_perf_stats) +
+		sizeof(struct papr_scm_perf_stat);
+
+	stats = kzalloc(size, GFP_KERNEL);
+	if (!stats)
+		return -ENOMEM;
+
+	stat = &stats->scm_statistic[0];
+	memcpy(&stat->stat_id, "MemLife ", sizeof(stat->stat_id));
+	stat->stat_val = 0;
+
+	/* Fetch the fuel gauge and populate it in payload */
+	rc = drc_pmem_query_stats(p, stats, 1);
+	if (rc < 0) {
+		dev_dbg(&p->pdev->dev, "Err(%d) fetching fuel gauge\n", rc);
+		goto free_stats;
+	}
+
+	statval = be64_to_cpu(stat->stat_val);
+	dev_dbg(&p->pdev->dev,
+		"Fetched fuel-gauge %llu", statval);
+	payload->health.extension_flags |=
+		PDSM_DIMM_HEALTH_RUN_GAUGE_VALID;
+	payload->health.dimm_fuel_gauge = statval;
+
+	rc = sizeof(struct nd_papr_pdsm_health);
+
+free_stats:
+	kfree(stats);
+	return rc;
+}
+
 /* 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)
@@ -456,6 +603,10 @@ static int papr_pdsm_health(struct papr_scm_priv *p,
 
 	/* struct populated hence can release the mutex now */
 	mutex_unlock(&p->health_mutex);
+
+	/* Populate the fuel gauge meter in the payload */
+	papr_pdsm_fuel_gauge(p, payload);
+
 	rc = sizeof(struct nd_papr_pdsm_health);
 
 out:
@@ -631,6 +782,48 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc,
 	return 0;
 }
 
+static ssize_t perf_stats_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	int index, rc;
+	struct seq_buf s;
+	struct papr_scm_perf_stat *stat;
+	struct papr_scm_perf_stats *stats;
+	struct nvdimm *dimm = to_nvdimm(dev);
+	struct papr_scm_priv *p = nvdimm_provider_data(dimm);
+
+	if (!p->stat_buffer_len)
+		return -ENOENT;
+
+	/* Allocate the buffer for phyp where stats are written */
+	stats = kzalloc(p->stat_buffer_len, GFP_KERNEL);
+	if (!stats)
+		return -ENOMEM;
+
+	/* Ask phyp to return all dimm perf stats */
+	rc = drc_pmem_query_stats(p, stats, 0);
+	if (rc)
+		goto free_stats;
+	/*
+	 * Go through the returned output buffer and print stats and
+	 * values. Since stat_id is essentially a char string of
+	 * 8 bytes, simply use the string format specifier to print it.
+	 */
+	seq_buf_init(&s, buf, PAGE_SIZE);
+	for (index = 0, stat = stats->scm_statistic;
+	     index < be32_to_cpu(stats->num_statistics);
+	     ++index, ++stat) {
+		seq_buf_printf(&s, "%.8s = 0x%016llX\n",
+			       stat->stat_id,
+			       be64_to_cpu(stat->stat_val));
+	}
+
+free_stats:
+	kfree(stats);
+	return rc ? rc : seq_buf_used(&s);
+}
+DEVICE_ATTR_RO(perf_stats);
+
 static ssize_t flags_show(struct device *dev,
 			  struct device_attribute *attr, char *buf)
 {
@@ -676,6 +869,7 @@ DEVICE_ATTR_RO(flags);
 /* papr_scm specific dimm attributes */
 static struct attribute *papr_nd_attributes[] = {
 	&dev_attr_flags.attr,
+	&dev_attr_perf_stats.attr,
 	NULL,
 };
 
@@ -696,6 +890,7 @@ 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;
@@ -759,6 +954,20 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 		dev_info(dev, "Region registered with target node %d and online node %d",
 			 target_nid, online_nid);
 
+	mutex_lock(&papr_ndr_lock);
+	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);
@@ -766,6 +975,68 @@ err:	nvdimm_bus_unregister(p->bus);
 	return -ENXIO;
 }
 
+static void papr_scm_add_badblock(struct nd_region *region,
+				  struct nvdimm_bus *bus, u64 phys_addr)
+{
+	u64 aligned_addr = ALIGN_DOWN(phys_addr, L1_CACHE_BYTES);
+
+	if (nvdimm_bus_add_badrange(bus, aligned_addr, L1_CACHE_BYTES)) {
+		pr_err("Bad block registration for 0x%llx failed\n", phys_addr);
+		return;
+	}
+
+	pr_debug("Add memory range (0x%llx - 0x%llx) as bad range\n",
+		 aligned_addr, aligned_addr + L1_CACHE_BYTES);
+
+	nvdimm_region_notify(region, NVDIMM_REVALIDATE_POISON);
+}
+
+static int handle_mce_ue(struct notifier_block *nb, unsigned long val,
+			 void *data)
+{
+	struct machine_check_event *evt = data;
+	struct papr_scm_priv *p;
+	u64 phys_addr;
+	bool found = false;
+
+	if (evt->error_type != MCE_ERROR_TYPE_UE)
+		return NOTIFY_DONE;
+
+	if (list_empty(&papr_nd_regions))
+		return NOTIFY_DONE;
+
+	/*
+	 * The physical address obtained here is PAGE_SIZE aligned, so get the
+	 * exact address from the effective address
+	 */
+	phys_addr = evt->u.ue_error.physical_address +
+			(evt->u.ue_error.effective_address & ~PAGE_MASK);
+
+	if (!evt->u.ue_error.physical_address_provided ||
+	    !is_zone_device_page(pfn_to_page(phys_addr >> PAGE_SHIFT)))
+		return NOTIFY_DONE;
+
+	/* mce notifier is called from a process context, so mutex is safe */
+	mutex_lock(&papr_ndr_lock);
+	list_for_each_entry(p, &papr_nd_regions, region_list) {
+		if (phys_addr >= p->res.start && phys_addr <= p->res.end) {
+			found = true;
+			break;
+		}
+	}
+
+	if (found)
+		papr_scm_add_badblock(p->region, p->bus, phys_addr);
+
+	mutex_unlock(&papr_ndr_lock);
+
+	return found ? NOTIFY_OK : NOTIFY_DONE;
+}
+
+static struct notifier_block mce_ue_nb = {
+	.notifier_call = handle_mce_ue
+};
+
 static int papr_scm_probe(struct platform_device *pdev)
 {
 	struct device_node *dn = pdev->dev.of_node;
@@ -866,6 +1137,10 @@ static int papr_scm_remove(struct platform_device *pdev)
 {
 	struct papr_scm_priv *p = platform_get_drvdata(pdev);
 
+	mutex_lock(&papr_ndr_lock);
+	list_del(&p->region_list);
+	mutex_unlock(&papr_ndr_lock);
+
 	nvdimm_bus_unregister(p->bus);
 	drc_pmem_unbind(p);
 	kfree(p->bus_desc.provider_name);
@@ -876,6 +1151,7 @@ static int papr_scm_remove(struct platform_device *pdev)
 
 static const struct of_device_id papr_scm_match[] = {
 	{ .compatible = "ibm,pmemory" },
+	{ .compatible = "ibm,pmemory-v2" },
 	{ },
 };
 
@@ -888,7 +1164,25 @@ static struct platform_driver papr_scm_driver = {
 	},
 };
 
-module_platform_driver(papr_scm_driver);
+static int __init papr_scm_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&papr_scm_driver);
+	if (!ret)
+		mce_register_notifier(&mce_ue_nb);
+
+	return ret;
+}
+module_init(papr_scm_init);
+
+static void __exit papr_scm_exit(void)
+{
+	mce_unregister_notifier(&mce_ue_nb);
+	platform_driver_unregister(&papr_scm_driver);
+}
+module_exit(papr_scm_exit);
+
 MODULE_DEVICE_TABLE(of, papr_scm_match);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("IBM Corporation");