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
  ...

15 files changed, 587 insertions, 288 deletions

diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 1b299e801f74..addaa6e6718b 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -244,20 +244,6 @@ static inline void add_powernv_state(int index, const char *name,
 	stop_psscr_table[index].mask = psscr_mask;
 }
 
-/*
- * Returns 0 if prop1_len == prop2_len. Else returns -1
- */
-static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len,
-					 const char *prop2, int prop2_len)
-{
-	if (prop1_len == prop2_len)
-		return 0;
-
-	pr_warn("cpuidle-powernv: array sizes don't match for %s and %s\n",
-		prop1, prop2);
-	return -1;
-}
-
 extern u32 pnv_get_supported_cpuidle_states(void);
 static int powernv_add_idle_states(void)
 {
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 6513ef2af66a..ff6d99e923a4 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -21,8 +21,9 @@
 #include <asm/runlatch.h>
 #include <asm/idle.h>
 #include <asm/plpar_wrappers.h>
+#include <asm/rtas.h>
 
-struct cpuidle_driver pseries_idle_driver = {
+static struct cpuidle_driver pseries_idle_driver = {
 	.name             = "pseries_idle",
 	.owner            = THIS_MODULE,
 };
@@ -86,19 +87,150 @@ static void check_and_cede_processor(void)
 	}
 }
 
+/*
+ * XCEDE: Extended CEDE states discovered through the
+ *        "ibm,get-systems-parameter" RTAS call with the token
+ *        CEDE_LATENCY_TOKEN
+ */
+
+/*
+ * Section 7.3.16 System Parameters Option of PAPR version 2.8.1 has a
+ * table with all the parameters to ibm,get-system-parameters.
+ * CEDE_LATENCY_TOKEN corresponds to the token value for Cede Latency
+ * Settings Information.
+ */
+#define CEDE_LATENCY_TOKEN	45
+
+/*
+ * If the platform supports the cede latency settings information system
+ * parameter it must provide the following information in the NULL terminated
+ * parameter string:
+ *
+ * a. The first byte is the length “N” of each cede latency setting record minus
+ *    one (zero indicates a length of 1 byte).
+ *
+ * b. For each supported cede latency setting a cede latency setting record
+ *    consisting of the first “N” bytes as per the following table.
+ *
+ *    -----------------------------
+ *    | Field           | Field   |
+ *    | Name            | Length  |
+ *    -----------------------------
+ *    | Cede Latency    | 1 Byte  |
+ *    | Specifier Value |         |
+ *    -----------------------------
+ *    | Maximum wakeup  |         |
+ *    | latency in      | 8 Bytes |
+ *    | tb-ticks        |         |
+ *    -----------------------------
+ *    | Responsive to   |         |
+ *    | external        | 1 Byte  |
+ *    | interrupts      |         |
+ *    -----------------------------
+ *
+ * This version has cede latency record size = 10.
+ *
+ * The structure xcede_latency_payload represents a) and b) with
+ * xcede_latency_record representing the table in b).
+ *
+ * xcede_latency_parameter is what gets returned by
+ * ibm,get-systems-parameter RTAS call when made with
+ * CEDE_LATENCY_TOKEN.
+ *
+ * These structures are only used to represent the data obtained by the RTAS
+ * call. The data is in big-endian.
+ */
+struct xcede_latency_record {
+	u8	hint;
+	__be64	latency_ticks;
+	u8	wake_on_irqs;
+} __packed;
+
+// Make space for 16 records, which "should be enough".
+struct xcede_latency_payload {
+	u8     record_size;
+	struct xcede_latency_record records[16];
+} __packed;
+
+struct xcede_latency_parameter {
+	__be16  payload_size;
+	struct xcede_latency_payload payload;
+	u8 null_char;
+} __packed;
+
+static unsigned int nr_xcede_records;
+static struct xcede_latency_parameter xcede_latency_parameter __initdata;
+
+static int __init parse_cede_parameters(void)
+{
+	struct xcede_latency_payload *payload;
+	u32 total_xcede_records_size;
+	u8 xcede_record_size;
+	u16 payload_size;
+	int ret, i;
+
+	ret = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+			NULL, CEDE_LATENCY_TOKEN, __pa(&xcede_latency_parameter),
+			sizeof(xcede_latency_parameter));
+	if (ret) {
+		pr_err("xcede: Error parsing CEDE_LATENCY_TOKEN\n");
+		return ret;
+	}
+
+	payload_size = be16_to_cpu(xcede_latency_parameter.payload_size);
+	payload = &xcede_latency_parameter.payload;
+
+	xcede_record_size = payload->record_size + 1;
+
+	if (xcede_record_size != sizeof(struct xcede_latency_record)) {
+		pr_err("xcede: Expected record-size %lu. Observed size %u.\n",
+		       sizeof(struct xcede_latency_record), xcede_record_size);
+		return -EINVAL;
+	}
+
+	pr_info("xcede: xcede_record_size = %d\n", xcede_record_size);
+
+	/*
+	 * Since the payload_size includes the last NULL byte and the
+	 * xcede_record_size, the remaining bytes correspond to array of all
+	 * cede_latency settings.
+	 */
+	total_xcede_records_size = payload_size - 2;
+	nr_xcede_records = total_xcede_records_size / xcede_record_size;
+
+	for (i = 0; i < nr_xcede_records; i++) {
+		struct xcede_latency_record *record = &payload->records[i];
+		u64 latency_ticks = be64_to_cpu(record->latency_ticks);
+		u8 wake_on_irqs = record->wake_on_irqs;
+		u8 hint = record->hint;
+
+		pr_info("xcede: Record %d : hint = %u, latency = 0x%llx tb ticks, Wake-on-irq = %u\n",
+			i, hint, latency_ticks, wake_on_irqs);
+	}
+
+	return 0;
+}
+
+#define NR_DEDICATED_STATES	2 /* snooze, CEDE */
+static u8 cede_latency_hint[NR_DEDICATED_STATES];
+
 static int dedicated_cede_loop(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv,
 				int index)
 {
+	u8 old_latency_hint;
 
 	pseries_idle_prolog();
 	get_lppaca()->donate_dedicated_cpu = 1;
+	old_latency_hint = get_lppaca()->cede_latency_hint;
+	get_lppaca()->cede_latency_hint = cede_latency_hint[index];
 
 	HMT_medium();
 	check_and_cede_processor();
 
 	local_irq_disable();
 	get_lppaca()->donate_dedicated_cpu = 0;
+	get_lppaca()->cede_latency_hint = old_latency_hint;
 
 	pseries_idle_epilog();
 
@@ -130,7 +262,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
 /*
  * States for dedicated partition case.
  */
-static struct cpuidle_state dedicated_states[] = {
+static struct cpuidle_state dedicated_states[NR_DEDICATED_STATES] = {
 	{ /* Snooze */
 		.name = "snooze",
 		.desc = "snooze",
@@ -211,6 +343,54 @@ static int pseries_cpuidle_driver_init(void)
 	return 0;
 }
 
+static void __init fixup_cede0_latency(void)
+{
+	struct xcede_latency_payload *payload;
+	u64 min_latency_us;
+	int i;
+
+	min_latency_us = dedicated_states[1].exit_latency; // CEDE latency
+
+	if (parse_cede_parameters())
+		return;
+
+	pr_info("cpuidle: Skipping the %d Extended CEDE idle states\n",
+		nr_xcede_records);
+
+	payload = &xcede_latency_parameter.payload;
+	for (i = 0; i < nr_xcede_records; i++) {
+		struct xcede_latency_record *record = &payload->records[i];
+		u64 latency_tb = be64_to_cpu(record->latency_ticks);
+		u64 latency_us = tb_to_ns(latency_tb) / NSEC_PER_USEC;
+
+		if (latency_us < min_latency_us)
+			min_latency_us = latency_us;
+	}
+
+	/*
+	 * By default, we assume that CEDE(0) has exit latency 10us,
+	 * since there is no way for us to query from the platform.
+	 *
+	 * However, if the wakeup latency of an Extended CEDE state is
+	 * smaller than 10us, then we can be sure that CEDE(0)
+	 * requires no more than that.
+	 *
+	 * Perform the fix-up.
+	 */
+	if (min_latency_us < dedicated_states[1].exit_latency) {
+		u64 cede0_latency = min_latency_us - 1;
+
+		if (cede0_latency <= 0)
+			cede0_latency = min_latency_us;
+
+		dedicated_states[1].exit_latency = cede0_latency;
+		dedicated_states[1].target_residency = 10 * (cede0_latency);
+		pr_info("cpuidle: Fixed up CEDE exit latency to %llu us\n",
+			cede0_latency);
+	}
+
+}
+
 /*
  * pseries_idle_probe()
  * Choose state table for shared versus dedicated partition
@@ -232,8 +412,9 @@ static int pseries_idle_probe(void)
 			cpuidle_state_table = shared_states;
 			max_idle_state = ARRAY_SIZE(shared_states);
 		} else {
+			fixup_cede0_latency();
 			cpuidle_state_table = dedicated_states;
-			max_idle_state = ARRAY_SIZE(dedicated_states);
+			max_idle_state = NR_DEDICATED_STATES;
 		}
 	} else
 		return -ENODEV;
diff --git a/drivers/crypto/vmx/aesp8-ppc.pl b/drivers/crypto/vmx/aesp8-ppc.pl
index db874367b602..50a0a18f35da 100644
--- a/drivers/crypto/vmx/aesp8-ppc.pl
+++ b/drivers/crypto/vmx/aesp8-ppc.pl
@@ -50,7 +50,7 @@
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 # project. The module is, however, dual licensed under OpenSSL and
 # CRYPTOGAMS licenses depending on where you obtain it. For further
-# details see http://www.openssl.org/~appro/cryptogams/.
+# details see https://www.openssl.org/~appro/cryptogams/.
 # ====================================================================
 #
 # This module implements support for AES instructions as per PowerISA
diff --git a/drivers/crypto/vmx/ghashp8-ppc.pl b/drivers/crypto/vmx/ghashp8-ppc.pl
index 38b06503ede0..09bba1852eec 100644
--- a/drivers/crypto/vmx/ghashp8-ppc.pl
+++ b/drivers/crypto/vmx/ghashp8-ppc.pl
@@ -13,7 +13,7 @@
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
 # project. The module is, however, dual licensed under OpenSSL and
 # CRYPTOGAMS licenses depending on where you obtain it. For further
-# details see http://www.openssl.org/~appro/cryptogams/.
+# details see https://www.openssl.org/~appro/cryptogams/.
 # ====================================================================
 #
 # GHASH for for PowerISA v2.07.
diff --git a/drivers/macintosh/adb-iop.c b/drivers/macintosh/adb-iop.c
index fca31640e3ef..f3d1a460fbce 100644
--- a/drivers/macintosh/adb-iop.c
+++ b/drivers/macintosh/adb-iop.c
@@ -7,10 +7,6 @@
  * 1999-07-01 (jmt) - First implementation for new driver architecture.
  *
  * 1999-07-31 (jmt) - First working version.
- *
- * TODO:
- *
- * o Implement SRQ handling.
  */
 
 #include <linux/types.h>
@@ -18,24 +14,17 @@
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/proc_fs.h>
 
 #include <asm/macintosh.h>
 #include <asm/macints.h>
 #include <asm/mac_iop.h>
-#include <asm/mac_oss.h>
 #include <asm/adb_iop.h>
 
 #include <linux/adb.h>
 
-/*#define DEBUG_ADB_IOP*/
-
 static struct adb_request *current_req;
 static struct adb_request *last_req;
-#if 0
-static unsigned char reply_buff[16];
-static unsigned char *reply_ptr;
-#endif
+static unsigned int autopoll_devs;
 
 static enum adb_iop_state {
 	idle,
@@ -62,13 +51,19 @@ struct adb_driver adb_iop_driver = {
 	.reset_bus    = adb_iop_reset_bus
 };
 
-static void adb_iop_end_req(struct adb_request *req, int state)
+static void adb_iop_done(void)
 {
+	struct adb_request *req = current_req;
+
+	adb_iop_state = idle;
+
 	req->complete = 1;
 	current_req = req->next;
 	if (req->done)
 		(*req->done)(req);
-	adb_iop_state = state;
+
+	if (adb_iop_state == idle)
+		adb_iop_start();
 }
 
 /*
@@ -79,15 +74,14 @@ static void adb_iop_end_req(struct adb_request *req, int state)
 
 static void adb_iop_complete(struct iop_msg *msg)
 {
-	struct adb_request *req;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
-	req = current_req;
-	if ((adb_iop_state == sending) && req && req->reply_expected) {
+	if (current_req->reply_expected)
 		adb_iop_state = awaiting_reply;
-	}
+	else
+		adb_iop_done();
 
 	local_irq_restore(flags);
 }
@@ -102,52 +96,36 @@ static void adb_iop_complete(struct iop_msg *msg)
 static void adb_iop_listen(struct iop_msg *msg)
 {
 	struct adb_iopmsg *amsg = (struct adb_iopmsg *)msg->message;
-	struct adb_request *req;
 	unsigned long flags;
-#ifdef DEBUG_ADB_IOP
-	int i;
-#endif
+	bool req_done = false;
 
 	local_irq_save(flags);
 
-	req = current_req;
+	/* Handle a timeout. Timeout packets seem to occur even after
+	 * we've gotten a valid reply to a TALK, presumably because of
+	 * autopolling.
+	 */
+
+	if (amsg->flags & ADB_IOP_EXPLICIT) {
+		if (adb_iop_state == awaiting_reply) {
+			struct adb_request *req = current_req;
 
-#ifdef DEBUG_ADB_IOP
-	printk("adb_iop_listen %p: rcvd packet, %d bytes: %02X %02X", req,
-	       (uint)amsg->count + 2, (uint)amsg->flags, (uint)amsg->cmd);
-	for (i = 0; i < amsg->count; i++)
-		printk(" %02X", (uint)amsg->data[i]);
-	printk("\n");
-#endif
-
-	/* Handle a timeout. Timeout packets seem to occur even after */
-	/* we've gotten a valid reply to a TALK, so I'm assuming that */
-	/* a "timeout" is actually more like an "end-of-data" signal. */
-	/* We need to send back a timeout packet to the IOP to shut   */
-	/* it up, plus complete the current request, if any.          */
-
-	if (amsg->flags & ADB_IOP_TIMEOUT) {
-		msg->reply[0] = ADB_IOP_TIMEOUT | ADB_IOP_AUTOPOLL;
-		msg->reply[1] = 0;
-		msg->reply[2] = 0;
-		if (req && (adb_iop_state != idle)) {
-			adb_iop_end_req(req, idle);
-		}
-	} else {
-		/* TODO: is it possible for more than one chunk of data  */
-		/*       to arrive before the timeout? If so we need to */
-		/*       use reply_ptr here like the other drivers do.  */
-		if ((adb_iop_state == awaiting_reply) &&
-		    (amsg->flags & ADB_IOP_EXPLICIT)) {
 			req->reply_len = amsg->count + 1;
 			memcpy(req->reply, &amsg->cmd, req->reply_len);
-		} else {
-			adb_input(&amsg->cmd, amsg->count + 1,
-				  amsg->flags & ADB_IOP_AUTOPOLL);
+
+			req_done = true;
 		}
-		memcpy(msg->reply, msg->message, IOP_MSG_LEN);
+	} else if (!(amsg->flags & ADB_IOP_TIMEOUT)) {
+		adb_input(&amsg->cmd, amsg->count + 1,
+			  amsg->flags & ADB_IOP_AUTOPOLL);
 	}
+
+	msg->reply[0] = autopoll_devs ? ADB_IOP_AUTOPOLL : 0;
 	iop_complete_message(msg);
+
+	if (req_done)
+		adb_iop_done();
+
 	local_irq_restore(flags);
 }
 
@@ -160,63 +138,50 @@ static void adb_iop_listen(struct iop_msg *msg)
 
 static void adb_iop_start(void)
 {
-	unsigned long flags;
 	struct adb_request *req;
 	struct adb_iopmsg amsg;
-#ifdef DEBUG_ADB_IOP
-	int i;
-#endif
 
 	/* get the packet to send */
 	req = current_req;
 	if (!req)
 		return;
 
-	local_irq_save(flags);
-
-#ifdef DEBUG_ADB_IOP
-	printk("adb_iop_start %p: sending packet, %d bytes:", req, req->nbytes);
-	for (i = 0; i < req->nbytes; i++)
-		printk(" %02X", (uint)req->data[i]);
-	printk("\n");
-#endif
-
-	/* The IOP takes MacII-style packets, so */
-	/* strip the initial ADB_PACKET byte.    */
-
+	/* The IOP takes MacII-style packets, so strip the initial
+	 * ADB_PACKET byte.
+	 */
 	amsg.flags = ADB_IOP_EXPLICIT;
 	amsg.count = req->nbytes - 2;
 
-	/* amsg.data immediately follows amsg.cmd, effectively making */
-	/* amsg.cmd a pointer to the beginning of a full ADB packet.  */
+	/* amsg.data immediately follows amsg.cmd, effectively making
+	 * &amsg.cmd a pointer to the beginning of a full ADB packet.
+	 */
 	memcpy(&amsg.cmd, req->data + 1, req->nbytes - 1);
 
 	req->sent = 1;
 	adb_iop_state = sending;
-	local_irq_restore(flags);
-
-	/* Now send it. The IOP manager will call adb_iop_complete */
-	/* when the packet has been sent.                          */
 
+	/* Now send it. The IOP manager will call adb_iop_complete
+	 * when the message has been sent.
+	 */
 	iop_send_message(ADB_IOP, ADB_CHAN, req, sizeof(amsg), (__u8 *)&amsg,
 			 adb_iop_complete);
 }
 
-int adb_iop_probe(void)
+static int adb_iop_probe(void)
 {
 	if (!iop_ism_present)
 		return -ENODEV;
 	return 0;
 }
 
-int adb_iop_init(void)
+static int adb_iop_init(void)
 {
 	pr_info("adb: IOP ISM driver v0.4 for Unified ADB\n");
 	iop_listen(ADB_IOP, ADB_CHAN, adb_iop_listen, "ADB");
 	return 0;
 }
 
-int adb_iop_send_request(struct adb_request *req, int sync)
+static int adb_iop_send_request(struct adb_request *req, int sync)
 {
 	int err;
 
@@ -240,14 +205,14 @@ static int adb_iop_write(struct adb_request *req)
 		return -EINVAL;
 	}
 
-	local_irq_save(flags);
-
 	req->next = NULL;
 	req->sent = 0;
 	req->complete = 0;
 	req->reply_len = 0;
 
-	if (current_req != 0) {
+	local_irq_save(flags);
+
+	if (current_req) {
 		last_req->next = req;
 		last_req = req;
 	} else {
@@ -255,39 +220,58 @@ static int adb_iop_write(struct adb_request *req)
 		last_req = req;
 	}
 
-	local_irq_restore(flags);
-
 	if (adb_iop_state == idle)
 		adb_iop_start();
+
+	local_irq_restore(flags);
+
 	return 0;
 }
 
-int adb_iop_autopoll(int devs)
+static void adb_iop_set_ap_complete(struct iop_msg *msg)
 {
-	/* TODO: how do we enable/disable autopoll? */
+	struct adb_iopmsg *amsg = (struct adb_iopmsg *)msg->message;
+
+	autopoll_devs = (amsg->data[1] << 8) | amsg->data[0];
+}
+
+static int adb_iop_autopoll(int devs)
+{
+	struct adb_iopmsg amsg;
+	unsigned long flags;
+	unsigned int mask = (unsigned int)devs & 0xFFFE;
+
+	local_irq_save(flags);
+
+	amsg.flags = ADB_IOP_SET_AUTOPOLL | (mask ? ADB_IOP_AUTOPOLL : 0);
+	amsg.count = 2;
+	amsg.cmd = 0;
+	amsg.data[0] = mask & 0xFF;
+	amsg.data[1] = (mask >> 8) & 0xFF;
+
+	iop_send_message(ADB_IOP, ADB_CHAN, NULL, sizeof(amsg), (__u8 *)&amsg,
+			 adb_iop_set_ap_complete);
+
+	local_irq_restore(flags);
+
 	return 0;
 }
 
-void adb_iop_poll(void)
+static void adb_iop_poll(void)
 {
-	if (adb_iop_state == idle)
-		adb_iop_start();
 	iop_ism_irq_poll(ADB_IOP);
 }
 
-int adb_iop_reset_bus(void)
+static int adb_iop_reset_bus(void)
 {
-	struct adb_request req = {
-		.reply_expected = 0,
-		.nbytes = 2,
-		.data = { ADB_PACKET, 0 },
-	};
-
-	adb_iop_write(&req);
-	while (!req.complete) {
-		adb_iop_poll();
-		schedule();
-	}
+	struct adb_request req;
+
+	/* Command = 0, Address = ignored */
+	adb_request(&req, NULL, ADBREQ_NOSEND, 1, ADB_BUSRESET);
+	adb_iop_send_request(&req, 1);
+
+	/* Don't want any more requests during the Global Reset low time. */
+	mdelay(3);
 
 	return 0;
 }
diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c
index e49d1f287a17..73b396189039 100644
--- a/drivers/macintosh/adb.c
+++ b/drivers/macintosh/adb.c
@@ -163,7 +163,7 @@ static int adb_scan_bus(void)
 			 * See if anybody actually moved. This is suggested
 			 * by HW TechNote 01:
 			 *
-			 * http://developer.apple.com/technotes/hw/hw_01.html
+			 * https://developer.apple.com/technotes/hw/hw_01.html
 			 */
 			adb_request(&req, NULL, ADBREQ_SYNC | ADBREQ_REPLY, 1,
 				    (highFree << 4) | 0xf);
diff --git a/drivers/macintosh/therm_adt746x.c b/drivers/macintosh/therm_adt746x.c
index 8f7725dc2166..7e218437730c 100644
--- a/drivers/macintosh/therm_adt746x.c
+++ b/drivers/macintosh/therm_adt746x.c
@@ -5,8 +5,8 @@
  * Copyright (C) 2003, 2004 Colin Leroy, Rasmus Rohde, Benjamin Herrenschmidt
  *
  * Documentation from 115254175ADT7467_pra.pdf and 3686221171167ADT7460_b.pdf
- * http://www.onsemi.com/PowerSolutions/product.do?id=ADT7467
- * http://www.onsemi.com/PowerSolutions/product.do?id=ADT7460
+ * https://www.onsemi.com/PowerSolutions/product.do?id=ADT7467
+ * https://www.onsemi.com/PowerSolutions/product.do?id=ADT7460
  *
  */
 
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index ac824d7b2dcf..060e03f2264b 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -77,6 +77,12 @@ static volatile unsigned char *via;
 #define ST_ODD		0x20		/* ADB state: odd data byte */
 #define ST_IDLE		0x30		/* ADB state: idle, nothing to send */
 
+/* ADB command byte structure */
+#define ADDR_MASK	0xF0
+#define CMD_MASK	0x0F
+#define OP_MASK		0x0C
+#define TALK		0x0C
+
 static int macii_init_via(void);
 static void macii_start(void);
 static irqreturn_t macii_interrupt(int irq, void *arg);
@@ -104,21 +110,22 @@ static enum macii_state {
 	idle,
 	sending,
 	reading,
-	read_done,
 } macii_state;
 
 static struct adb_request *current_req; /* first request struct in the queue */
 static struct adb_request *last_req;     /* last request struct in the queue */
 static unsigned char reply_buf[16];        /* storage for autopolled replies */
 static unsigned char *reply_ptr;     /* next byte in reply_buf or req->reply */
-static int reading_reply;        /* store reply in reply_buf else req->reply */
+static bool reading_reply;       /* store reply in reply_buf else req->reply */
 static int data_index;      /* index of the next byte to send from req->data */
 static int reply_len; /* number of bytes received in reply_buf or req->reply */
 static int status;          /* VIA's ADB status bits captured upon interrupt */
-static int last_status;              /* status bits as at previous interrupt */
-static int srq_asserted;     /* have to poll for the device that asserted it */
-static int command_byte;         /* the most recent command byte transmitted */
-static int autopoll_devs;      /* bits set are device addresses to be polled */
+static bool bus_timeout;                   /* no data was sent by the device */
+static bool srq_asserted;    /* have to poll for the device that asserted it */
+static u8 last_cmd;              /* the most recent command byte transmitted */
+static u8 last_talk_cmd;    /* the most recent Talk command byte transmitted */
+static u8 last_poll_cmd; /* the most recent Talk R0 command byte transmitted */
+static unsigned int autopoll_devs;  /* bits set are device addresses to poll */
 
 /* Check for MacII style ADB */
 static int macii_probe(void)
@@ -133,7 +140,7 @@ static int macii_probe(void)
 }
 
 /* Initialize the driver */
-int macii_init(void)
+static int macii_init(void)
 {
 	unsigned long flags;
 	int err;
@@ -165,7 +172,6 @@ static int macii_init_via(void)
 
 	/* Set up state: idle */
 	via[B] |= ST_IDLE;
-	last_status = via[B] & (ST_MASK | CTLR_IRQ);
 
 	/* Shift register on input */
 	via[ACR] = (via[ACR] & ~SR_CTRL) | SR_EXT;
@@ -179,35 +185,49 @@ static int macii_init_via(void)
 /* Send an ADB poll (Talk Register 0 command prepended to the request queue) */
 static void macii_queue_poll(void)
 {
-	/* No point polling the active device as it will never assert SRQ, so
-	 * poll the next device in the autopoll list. This could leave us
-	 * stuck in a polling loop if an unprobed device is asserting SRQ.
-	 * In theory, that could only happen if a device was plugged in after
-	 * probing started. Unplugging it again will break the cycle.
-	 * (Simply polling the next higher device often ends up polling almost
-	 * every device (after wrapping around), which takes too long.)
-	 */
-	int device_mask;
-	int next_device;
 	static struct adb_request req;
+	unsigned char poll_command;
+	unsigned int poll_addr;
 
+	/* This only polls devices in the autopoll list, which assumes that
+	 * unprobed devices never assert SRQ. That could happen if a device was
+	 * plugged in after the adb bus scan. Unplugging it again will resolve
+	 * the problem. This behaviour is similar to MacOS.
+	 */
 	if (!autopoll_devs)
 		return;
 
-	device_mask = (1 << (((command_byte & 0xF0) >> 4) + 1)) - 1;
-	if (autopoll_devs & ~device_mask)
-		next_device = ffs(autopoll_devs & ~device_mask) - 1;
-	else
-		next_device = ffs(autopoll_devs) - 1;
+	/* The device most recently polled may not be the best device to poll
+	 * right now. Some other device(s) may have signalled SRQ (the active
+	 * device won't do that). Or the autopoll list may have been changed.
+	 * Try polling the next higher address.
+	 */
+	poll_addr = (last_poll_cmd & ADDR_MASK) >> 4;
+	if ((srq_asserted && last_cmd == last_poll_cmd) ||
+	    !(autopoll_devs & (1 << poll_addr))) {
+		unsigned int higher_devs;
+
+		higher_devs = autopoll_devs & -(1 << (poll_addr + 1));
+		poll_addr = ffs(higher_devs ? higher_devs : autopoll_devs) - 1;
+	}
 
-	adb_request(&req, NULL, ADBREQ_NOSEND, 1, ADB_READREG(next_device, 0));
+	/* Send a Talk Register 0 command */
+	poll_command = ADB_READREG(poll_addr, 0);
+
+	/* No need to repeat this Talk command. The transceiver will do that
+	 * as long as it is idle.
+	 */
+	if (poll_command == last_cmd)
+		return;
+
+	adb_request(&req, NULL, ADBREQ_NOSEND, 1, poll_command);
 
 	req.sent = 0;
 	req.complete = 0;
 	req.reply_len = 0;
 	req.next = current_req;
 
-	if (current_req != NULL) {
+	if (WARN_ON(current_req)) {
 		current_req = &req;
 	} else {
 		current_req = &req;
@@ -266,40 +286,22 @@ static int macii_write(struct adb_request *req)
 /* Start auto-polling */
 static int macii_autopoll(int devs)
 {
-	static struct adb_request req;
 	unsigned long flags;
-	int err = 0;
-
-	/* bit 1 == device 1, and so on. */
-	autopoll_devs = devs & 0xFFFE;
-
-	if (!autopoll_devs)
-		return 0;
 
 	local_irq_save(flags);
 
-	if (current_req == NULL) {
-		/* Send a Talk Reg 0. The controller will repeatedly transmit
-		 * this as long as it is idle.
-		 */
-		adb_request(&req, NULL, ADBREQ_NOSEND, 1,
-		            ADB_READREG(ffs(autopoll_devs) - 1, 0));
-		err = macii_write(&req);
+	/* bit 1 == device 1, and so on. */
+	autopoll_devs = (unsigned int)devs & 0xFFFE;
+
+	if (!current_req) {
+		macii_queue_poll();
+		if (current_req && macii_state == idle)
+			macii_start();
 	}
 
 	local_irq_restore(flags);
-	return err;
-}
 
-static inline int need_autopoll(void)
-{
-	/* Was the last command Talk Reg 0
-	 * and is the target on the autopoll list?
-	 */
-	if ((command_byte & 0x0F) == 0x0C &&
-	    ((1 << ((command_byte & 0xF0) >> 4)) & autopoll_devs))
-		return 0;
-	return 1;
+	return 0;
 }
 
 /* Prod the chip without interrupts */
@@ -311,7 +313,7 @@ static void macii_poll(void)
 /* Reset the bus */
 static int macii_reset_bus(void)
 {
-	static struct adb_request req;
+	struct adb_request req;
 
 	/* Command = 0, Address = ignored */
 	adb_request(&req, NULL, ADBREQ_NOSEND, 1, ADB_BUSRESET);
@@ -335,8 +337,6 @@ static void macii_start(void)
 	 * And req->nbytes is the number of bytes of real data plus one.
 	 */
 
-	/* store command byte */
-	command_byte = req->data[1];
 	/* Output mode */
 	via[ACR] |= SR_OUT;
 	/* Load data */
@@ -346,6 +346,9 @@ static void macii_start(void)
 
 	macii_state = sending;
 	data_index = 2;
+
+	bus_timeout = false;
+	srq_asserted = false;
 }
 
 /*
@@ -354,15 +357,17 @@ static void macii_start(void)
  * generating shift register interrupts (SR_INT) for us. This means there has
  * to be activity on the ADB bus. The chip will poll to achieve this.
  *
- * The basic ADB state machine was left unchanged from the original MacII code
- * by Alan Cox, which was based on the CUDA driver for PowerMac.
- * The syntax of the ADB status lines is totally different on MacII,
- * though. MacII uses the states Command -> Even -> Odd -> Even ->...-> Idle
- * for sending and Idle -> Even -> Odd -> Even ->...-> Idle for receiving.
- * Start and end of a receive packet are signalled by asserting /IRQ on the
- * interrupt line (/IRQ means the CTLR_IRQ bit in port B; not to be confused
- * with the VIA shift register interrupt. /IRQ never actually interrupts the
- * processor, it's just an ordinary input.)
+ * The VIA Port B output signalling works as follows. After the ADB transceiver
+ * sees a transition on the PB4 and PB5 lines it will crank over the VIA shift
+ * register which eventually raises the SR_INT interrupt. The PB4/PB5 outputs
+ * are toggled with each byte as the ADB transaction progresses.
+ *
+ * Request with no reply expected (and empty transceiver buffer):
+ *     CMD -> IDLE
+ * Request with expected reply packet (or with buffered autopoll packet):
+ *     CMD -> EVEN -> ODD -> EVEN -> ... -> IDLE
+ * Unsolicited packet:
+ *     IDLE -> EVEN -> ODD -> EVEN -> ... -> IDLE
  */
 static irqreturn_t macii_interrupt(int irq, void *arg)
 {
@@ -382,31 +387,31 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
 		}
 	}
 
-	last_status = status;
 	status = via[B] & (ST_MASK | CTLR_IRQ);
 
 	switch (macii_state) {
 	case idle:
-		if (reading_reply) {
-			reply_ptr = current_req->reply;
-		} else {
-			WARN_ON(current_req);
-			reply_ptr = reply_buf;
-		}
+		WARN_ON((status & ST_MASK) != ST_IDLE);
+
+		reply_ptr = reply_buf;
+		reading_reply = false;
+
+		bus_timeout = false;
+		srq_asserted = false;
 
 		x = via[SR];
 
-		if ((status & CTLR_IRQ) && (x == 0xFF)) {
-			/* Bus timeout without SRQ sequence:
-			 *     data is "FF" while CTLR_IRQ is "H"
+		if (!(status & CTLR_IRQ)) {
+			/* /CTLR_IRQ asserted in idle state means we must
+			 * read an autopoll reply from the transceiver buffer.
 			 */
-			reply_len = 0;
-			srq_asserted = 0;
-			macii_state = read_done;
-		} else {
 			macii_state = reading;
 			*reply_ptr = x;
 			reply_len = 1;
+		} else {
+			/* bus timeout */
+			reply_len = 0;
+			break;
 		}
 
 		/* set ADB state = even for first data byte */
@@ -415,41 +420,83 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
 
 	case sending:
 		req = current_req;
-		if (data_index >= req->nbytes) {
+
+		if (status == (ST_CMD | CTLR_IRQ)) {
+			/* /CTLR_IRQ de-asserted after the command byte means
+			 * the host can continue with the transaction.
+			 */
+
+			/* Store command byte */
+			last_cmd = req->data[1];
+			if ((last_cmd & OP_MASK) == TALK) {
+				last_talk_cmd = last_cmd;
+				if ((last_cmd & CMD_MASK) == ADB_READREG(0, 0))
+					last_poll_cmd = last_cmd;
+			}
+		}
+
+		if (status == ST_CMD) {
+			/* /CTLR_IRQ asserted after the command byte means we
+			 * must read an autopoll reply. The first byte was
+			 * lost because the shift register was an output.
+			 */
+			macii_state = reading;
+
+			reading_reply = false;
+			reply_ptr = reply_buf;
+			*reply_ptr = last_talk_cmd;
+			reply_len = 1;
+
+			/* reset to shift in */
+			via[ACR] &= ~SR_OUT;
+			x = via[SR];
+		} else if (data_index >= req->nbytes) {
 			req->sent = 1;
-			macii_state = idle;
 
 			if (req->reply_expected) {
-				reading_reply = 1;
-			} else {
+				macii_state = reading;
+
+				reading_reply = true;
+				reply_ptr = req->reply;
+				*reply_ptr = req->data[1];
+				reply_len = 1;
+
+				via[ACR] &= ~SR_OUT;
+				x = via[SR];
+			} else if ((req->data[1] & OP_MASK) == TALK) {
+				macii_state = reading;
+
+				reading_reply = false;
+				reply_ptr = reply_buf;
+				*reply_ptr = req->data[1];
+				reply_len = 1;
+
+				via[ACR] &= ~SR_OUT;
+				x = via[SR];
+
 				req->complete = 1;
 				current_req = req->next;
 				if (req->done)
 					(*req->done)(req);
+			} else {
+				macii_state = idle;
 
-				if (current_req)
-					macii_start();
-				else if (need_autopoll())
-					macii_autopoll(autopoll_devs);
-			}
-
-			if (macii_state == idle) {
-				/* reset to shift in */
-				via[ACR] &= ~SR_OUT;
-				x = via[SR];
-				/* set ADB state idle - might get SRQ */
-				via[B] = (via[B] & ~ST_MASK) | ST_IDLE;
+				req->complete = 1;
+				current_req = req->next;
+				if (req->done)
+					(*req->done)(req);
+				break;
 			}
 		} else {
 			via[SR] = req->data[data_index++];
+		}
 
-			if ((via[B] & ST_MASK) == ST_CMD) {
-				/* just sent the command byte, set to EVEN */
-				via[B] = (via[B] & ~ST_MASK) | ST_EVEN;
-			} else {
-				/* invert state bits, toggle ODD/EVEN */
-				via[B] ^= ST_MASK;
-			}
+		if ((via[B] & ST_MASK) == ST_CMD) {
+			/* just sent the command byte, set to EVEN */
+			via[B] = (via[B] & ~ST_MASK) | ST_EVEN;
+		} else {
+			/* invert state bits, toggle ODD/EVEN */
+			via[B] ^= ST_MASK;
 		}
 		break;
 
@@ -458,33 +505,35 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
 		WARN_ON((status & ST_MASK) == ST_CMD ||
 			(status & ST_MASK) == ST_IDLE);
 
-		/* Bus timeout with SRQ sequence:
-		 *     data is "XX FF"      while CTLR_IRQ is "L L"
-		 * End of packet without SRQ sequence:
-		 *     data is "XX...YY 00" while CTLR_IRQ is "L...H L"
-		 * End of packet SRQ sequence:
-		 *     data is "XX...YY 00" while CTLR_IRQ is "L...L L"
-		 * (where XX is the first response byte and
-		 * YY is the last byte of valid response data.)
-		 */
-
-		srq_asserted = 0;
 		if (!(status & CTLR_IRQ)) {
-			if (x == 0xFF) {
-				if (!(last_status & CTLR_IRQ)) {
-					macii_state = read_done;
+			if (status == ST_EVEN && reply_len == 1) {
+				bus_timeout = true;
+			} else if (status == ST_ODD && reply_len == 2) {
+				srq_asserted = true;
+			} else {
+				macii_state = idle;
+
+				if (bus_timeout)
 					reply_len = 0;
-					srq_asserted = 1;
+
+				if (reading_reply) {
+					struct adb_request *req = current_req;
+
+					req->reply_len = reply_len;
+
+					req->complete = 1;
+					current_req = req->next;
+					if (req->done)
+						(*req->done)(req);
+				} else if (reply_len && autopoll_devs &&
+					   reply_buf[0] == last_poll_cmd) {
+					adb_input(reply_buf, reply_len, 1);
 				}
-			} else if (x == 0x00) {
-				macii_state = read_done;
-				if (!(last_status & CTLR_IRQ))
-					srq_asserted = 1;
+				break;
 			}
 		}
 
-		if (macii_state == reading &&
-		    reply_len < ARRAY_SIZE(reply_buf)) {
+		if (reply_len < ARRAY_SIZE(reply_buf)) {
 			reply_ptr++;
 			*reply_ptr = x;
 			reply_len++;
@@ -494,37 +543,22 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
 		via[B] ^= ST_MASK;
 		break;
 
-	case read_done:
-		x = via[SR];
+	default:
+		break;
+	}
 
-		if (reading_reply) {
-			reading_reply = 0;
-			req = current_req;
-			req->reply_len = reply_len;
-			req->complete = 1;
-			current_req = req->next;
-			if (req->done)
-				(*req->done)(req);
-		} else if (reply_len && autopoll_devs)
-			adb_input(reply_buf, reply_len, 0);
-
-		macii_state = idle;
-
-		/* SRQ seen before, initiate poll now */
-		if (srq_asserted)
+	if (macii_state == idle) {
+		if (!current_req)
 			macii_queue_poll();
 
 		if (current_req)
 			macii_start();
-		else if (need_autopoll())
-			macii_autopoll(autopoll_devs);
 
-		if (macii_state == idle)
+		if (macii_state == idle) {
+			via[ACR] &= ~SR_OUT;
+			x = via[SR];
 			via[B] = (via[B] & ~ST_MASK) | ST_IDLE;
-		break;
-
-	default:
-		break;
+		}
 	}
 
 	local_irq_restore(flags);
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index cfea054863a4..86dbe0c8b45c 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -538,7 +538,7 @@ static void ssd_commit_superblock(struct dm_writecache *wc)
 static void writecache_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
 {
 	if (WC_MODE_PMEM(wc))
-		wmb();
+		pmem_wmb();
 	else
 		ssd_commit_flushed(wc, wait_for_ios);
 }
diff --git a/drivers/misc/ocxl/Kconfig b/drivers/misc/ocxl/Kconfig
index 2d2266c1439e..6551007a066c 100644
--- a/drivers/misc/ocxl/Kconfig
+++ b/drivers/misc/ocxl/Kconfig
@@ -23,7 +23,7 @@ config OCXL
 	  The ocxl driver enables userspace programs to access these
 	  accelerators through devices in /dev/ocxl/.
 
-	  For more information, see http://opencapi.org.
+	  For more information, see https://opencapi.org.
 
 	  This is not to be confused with the support for IBM CAPI
 	  accelerators (CONFIG_CXL), which are PCI-based instead of a
diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c
index e3b99a39d207..4d490b92d951 100644
--- a/drivers/misc/ocxl/config.c
+++ b/drivers/misc/ocxl/config.c
@@ -71,6 +71,20 @@ static int find_dvsec_afu_ctrl(struct pci_dev *dev, u8 afu_idx)
 	return 0;
 }
 
+/**
+ * get_function_0() - Find a related PCI device (function 0)
+ * @device: PCI device to match
+ *
+ * Returns a pointer to the related device, or null if not found
+ */
+static struct pci_dev *get_function_0(struct pci_dev *dev)
+{
+	unsigned int devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0);
+
+	return pci_get_domain_bus_and_slot(pci_domain_nr(dev->bus),
+					   dev->bus->number, devfn);
+}
+
 static void read_pasid(struct pci_dev *dev, struct ocxl_fn_config *fn)
 {
 	u16 val;
@@ -159,14 +173,15 @@ static int read_dvsec_afu_info(struct pci_dev *dev, struct ocxl_fn_config *fn)
 static int read_dvsec_vendor(struct pci_dev *dev)
 {
 	int pos;
-	u32 cfg, tlx, dlx;
+	u32 cfg, tlx, dlx, reset_reload;
 
 	/*
-	 * vendor specific DVSEC is optional
+	 * vendor specific DVSEC, for IBM images only. Some older
+	 * images may not have it
 	 *
-	 * It's currently only used on function 0 to specify the
-	 * version of some logic blocks. Some older images may not
-	 * even have it so we ignore any errors
+	 * It's only used on function 0 to specify the version of some
+	 * logic blocks and to give access to special registers to
+	 * enable host-based flashing.
 	 */
 	if (PCI_FUNC(dev->devfn) != 0)
 		return 0;
@@ -178,11 +193,67 @@ static int read_dvsec_vendor(struct pci_dev *dev)
 	pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_CFG_VERS, &cfg);
 	pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_TLX_VERS, &tlx);
 	pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_DLX_VERS, &dlx);
+	pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+			      &reset_reload);
 
 	dev_dbg(&dev->dev, "Vendor specific DVSEC:\n");
 	dev_dbg(&dev->dev, "  CFG version = 0x%x\n", cfg);
 	dev_dbg(&dev->dev, "  TLX version = 0x%x\n", tlx);
 	dev_dbg(&dev->dev, "  DLX version = 0x%x\n", dlx);
+	dev_dbg(&dev->dev, "  ResetReload = 0x%x\n", reset_reload);
+	return 0;
+}
+
+static int get_dvsec_vendor0(struct pci_dev *dev, struct pci_dev **dev0,
+			     int *out_pos)
+{
+	int pos;
+
+	if (PCI_FUNC(dev->devfn) != 0) {
+		dev = get_function_0(dev);
+		if (!dev)
+			return -1;
+	}
+	pos = find_dvsec(dev, OCXL_DVSEC_VENDOR_ID);
+	if (!pos)
+		return -1;
+	*dev0 = dev;
+	*out_pos = pos;
+	return 0;
+}
+
+int ocxl_config_get_reset_reload(struct pci_dev *dev, int *val)
+{
+	struct pci_dev *dev0;
+	u32 reset_reload;
+	int pos;
+
+	if (get_dvsec_vendor0(dev, &dev0, &pos))
+		return -1;
+
+	pci_read_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+			      &reset_reload);
+	*val = !!(reset_reload & BIT(0));
+	return 0;
+}
+
+int ocxl_config_set_reset_reload(struct pci_dev *dev, int val)
+{
+	struct pci_dev *dev0;
+	u32 reset_reload;
+	int pos;
+
+	if (get_dvsec_vendor0(dev, &dev0, &pos))
+		return -1;
+
+	pci_read_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+			      &reset_reload);
+	if (val)
+		reset_reload |= BIT(0);
+	else
+		reset_reload &= ~BIT(0);
+	pci_write_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+			       reset_reload);
 	return 0;
 }
 
@@ -273,7 +344,7 @@ static int read_afu_info(struct pci_dev *dev, struct ocxl_fn_config *fn,
 }
 
 /**
- * read_template_version - Read the template version from the AFU
+ * read_template_version() - Read the template version from the AFU
  * @dev: the device for the AFU
  * @fn: the AFU offsets
  * @len: outputs the template length
@@ -282,7 +353,7 @@ static int read_afu_info(struct pci_dev *dev, struct ocxl_fn_config *fn,
  * Returns 0 on success, negative on failure
  */
 static int read_template_version(struct pci_dev *dev, struct ocxl_fn_config *fn,
-		u16 *len, u16 *version)
+				 u16 *len, u16 *version)
 {
 	u32 val32;
 	u8 major, minor;
@@ -476,7 +547,7 @@ static int validate_afu(struct pci_dev *dev, struct ocxl_afu_config *afu)
 }
 
 /**
- * read_afu_lpc_memory_info - Populate AFU metadata regarding LPC memory
+ * read_afu_lpc_memory_info() - Populate AFU metadata regarding LPC memory
  * @dev: the device for the AFU
  * @fn: the AFU offsets
  * @afu: the AFU struct to populate the LPC metadata into
@@ -484,8 +555,8 @@ static int validate_afu(struct pci_dev *dev, struct ocxl_afu_config *afu)
  * Returns 0 on success, negative on failure
  */
 static int read_afu_lpc_memory_info(struct pci_dev *dev,
-				struct ocxl_fn_config *fn,
-				struct ocxl_afu_config *afu)
+				    struct ocxl_fn_config *fn,
+				    struct ocxl_afu_config *afu)
 {
 	int rc;
 	u32 val32;
diff --git a/drivers/misc/ocxl/ocxl_internal.h b/drivers/misc/ocxl/ocxl_internal.h
index 345bf843a38e..0bad0a123af6 100644
--- a/drivers/misc/ocxl/ocxl_internal.h
+++ b/drivers/misc/ocxl/ocxl_internal.h
@@ -113,6 +113,12 @@ void ocxl_actag_afu_free(struct ocxl_fn *fn, u32 start, u32 size);
 int ocxl_config_get_pasid_info(struct pci_dev *dev, int *count);
 
 /*
+ * Control whether the FPGA is reloaded on a link reset
+ */
+int ocxl_config_get_reset_reload(struct pci_dev *dev, int *val);
+int ocxl_config_set_reset_reload(struct pci_dev *dev, int val);
+
+/*
  * Check if an AFU index is valid for the given function.
  *
  * AFU indexes can be sparse, so a driver should check all indexes up
@@ -122,11 +128,12 @@ int ocxl_config_check_afu_index(struct pci_dev *dev,
 				struct ocxl_fn_config *fn, int afu_idx);
 
 /**
- * Update values within a Process Element
+ * ocxl_link_update_pe() - Update values within a Process Element
+ * @link_handle: the link handle associated with the process element
+ * @pasid: the PASID for the AFU context
+ * @tid: the new thread id for the process element
  *
- * link_handle: the link handle associated with the process element
- * pasid: the PASID for the AFU context
- * tid: the new thread id for the process element
+ * Returns 0 on success
  */
 int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid);
 
diff --git a/drivers/misc/ocxl/sysfs.c b/drivers/misc/ocxl/sysfs.c
index 58f1ba264206..25c78df8055d 100644
--- a/drivers/misc/ocxl/sysfs.c
+++ b/drivers/misc/ocxl/sysfs.c
@@ -51,11 +51,46 @@ static ssize_t contexts_show(struct device *device,
 			afu->pasid_count, afu->pasid_max);
 }
 
+static ssize_t reload_on_reset_show(struct device *device,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct ocxl_afu *afu = to_afu(device);
+	struct ocxl_fn *fn = afu->fn;
+	struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
+	int val;
+
+	if (ocxl_config_get_reset_reload(pci_dev, &val))
+		return scnprintf(buf, PAGE_SIZE, "unavailable\n");
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t reload_on_reset_store(struct device *device,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct ocxl_afu *afu = to_afu(device);
+	struct ocxl_fn *fn = afu->fn;
+	struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
+	int rc, val;
+
+	rc = kstrtoint(buf, 0, &val);
+	if (rc || (val != 0 && val != 1))
+		return -EINVAL;
+
+	if (ocxl_config_set_reset_reload(pci_dev, val))
+		return -ENODEV;
+
+	return count;
+}
+
 static struct device_attribute afu_attrs[] = {
 	__ATTR_RO(global_mmio_size),
 	__ATTR_RO(pp_mmio_size),
 	__ATTR_RO(afu_version),
 	__ATTR_RO(contexts),
+	__ATTR_RW(reload_on_reset),
 };
 
 static ssize_t global_mmio_read(struct file *filp, struct kobject *kobj,
diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c
index 6826a274a1f1..10dbdcdfb9ce 100644
--- a/drivers/nvdimm/of_pmem.c
+++ b/drivers/nvdimm/of_pmem.c
@@ -90,6 +90,7 @@ static int of_pmem_region_remove(struct platform_device *pdev)
 
 static const struct of_device_id of_pmem_region_match[] = {
 	{ .compatible = "pmem-region" },
+	{ .compatible = "pmem-region-v2" },
 	{ },
 };
 
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 4502f9c4708d..c3237c2b03a6 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -1206,13 +1206,13 @@ int generic_nvdimm_flush(struct nd_region *nd_region)
 	idx = this_cpu_add_return(flush_idx, hash_32(current->pid + idx, 8));
 
 	/*
-	 * The first wmb() is needed to 'sfence' all previous writes
-	 * such that they are architecturally visible for the platform
-	 * buffer flush.  Note that we've already arranged for pmem
+	 * The pmem_wmb() is needed to 'sfence' all
+	 * previous writes such that they are architecturally visible for
+	 * the platform buffer flush. Note that we've already arranged for pmem
 	 * writes to avoid the cache via memcpy_flushcache().  The final
 	 * wmb() ensures ordering for the NVDIMM flush write.
 	 */
-	wmb();
+	pmem_wmb();
 	for (i = 0; i < nd_region->ndr_mappings; i++)
 		if (ndrd_get_flush_wpq(ndrd, i, 0))
 			writeq(1, ndrd_get_flush_wpq(ndrd, i, idx));