Merge tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "A bit of a small release, I suspect in part due to me travelling for
  KS. But my backlog of patches to review is smaller than usual, so I
  think in part folks just didn't send as much this cycle.

  Non-highlights:

   - Five fixes for the >128T address space handling, both to fix bugs
     in our implementation and to bring the semantics exactly into line
     with x86.

  Highlights:

   - Support for a new OPAL call on bare metal machines which gives us a
     true NMI (ie. is not masked by MSR[EE]=0) for debugging etc.

   - Support for Power9 DD2 in the CXL driver.

   - Improvements to machine check handling so that uncorrectable errors
     can be reported into the generic memory_failure() machinery.

   - Some fixes and improvements for VPHN, which is used under PowerVM
     to notify the Linux partition of topology changes.

   - Plumbing to enable TM (transactional memory) without suspend on
     some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND).

   - Support for emulating vector loads form cache-inhibited memory, on
     some Power9 revisions.

   - Disable the fast-endian switch "syscall" by default (behind a
     CONFIG), we believe it has never had any users.

   - A major rework of the API drivers use when initiating and waiting
     for long running operations performed by OPAL firmware, and changes
     to the powernv_flash driver to use the new API.

   - Several fixes for the handling of FP/VMX/VSX while processes are
     using transactional memory.

   - Optimisations of TLB range flushes when using the radix MMU on
     Power9.

   - Improvements to the VAS facility used to access coprocessors on
     Power9, and related improvements to the way the NX crypto driver
     handles requests.

   - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit.

  Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew
  Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin
  Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard,
  Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven,
  Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley,
  Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu,
  Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao,
  Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia
  Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee,
  Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel
  Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, and William A.
  Kennington III"

* tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (151 commits)
  powerpc/64s: Fix Power9 DD2.0 workarounds by adding DD2.1 feature
  powerpc/64s: Fix masking of SRR1 bits on instruction fault
  powerpc/64s: mm_context.addr_limit is only used on hash
  powerpc/64s/radix: Fix 128TB-512TB virtual address boundary case allocation
  powerpc/64s/hash: Allow MAP_FIXED allocations to cross 128TB boundary
  powerpc/64s/hash: Fix fork() with 512TB process address space
  powerpc/64s/hash: Fix 128TB-512TB virtual address boundary case allocation
  powerpc/64s/hash: Fix 512T hint detection to use >= 128T
  powerpc: Fix DABR match on hash based systems
  powerpc/signal: Properly handle return value from uprobe_deny_signal()
  powerpc/fadump: use kstrtoint to handle sysfs store
  powerpc/lib: Implement UACCESS_FLUSHCACHE API
  powerpc/lib: Implement PMEM API
  powerpc/powernv/npu: Don't explicitly flush nmmu tlb
  powerpc/powernv/npu: Use flush_all_mm() instead of flush_tlb_mm()
  powerpc/powernv/idle: Round up latency and residency values
  powerpc/kprobes: refactor kprobe_lookup_name for safer string operations
  powerpc/kprobes: Blacklist emulate_update_regs() from kprobes
  powerpc/kprobes: Do not disable interrupts for optprobes and kprobes_on_ftrace
  powerpc/kprobes: Disable preemption before invoking probe handler for optprobes
  ...

1 files changed, 53 insertions, 30 deletions

diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c
index f5396f26ddb4..26f9feaa5d17 100644
--- a/drivers/mtd/devices/powernv_flash.c
+++ b/drivers/mtd/devices/powernv_flash.c
@@ -47,6 +47,11 @@ enum flash_op {
 	FLASH_OP_ERASE,
 };
 
+/*
+ * Don't return -ERESTARTSYS if we can't get a token, the MTD core
+ * might have split up the call from userspace and called into the
+ * driver more than once, we'll already have done some amount of work.
+ */
 static int powernv_flash_async_op(struct mtd_info *mtd, enum flash_op op,
 		loff_t offset, size_t len, size_t *retlen, u_char *buf)
 {
@@ -63,7 +68,8 @@ static int powernv_flash_async_op(struct mtd_info *mtd, enum flash_op op,
 	if (token < 0) {
 		if (token != -ERESTARTSYS)
 			dev_err(dev, "Failed to get an async token\n");
-
+		else
+			token = -EINTR;
 		return token;
 	}
 
@@ -78,32 +84,53 @@ static int powernv_flash_async_op(struct mtd_info *mtd, enum flash_op op,
 		rc = opal_flash_erase(info->id, offset, len, token);
 		break;
 	default:
-		BUG_ON(1);
-	}
-
-	if (rc != OPAL_ASYNC_COMPLETION) {
-		dev_err(dev, "opal_flash_async_op(op=%d) failed (rc %d)\n",
-				op, rc);
+		WARN_ON_ONCE(1);
 		opal_async_release_token(token);
 		return -EIO;
 	}
 
-	rc = opal_async_wait_response(token, &msg);
-	opal_async_release_token(token);
-	if (rc) {
-		dev_err(dev, "opal async wait failed (rc %d)\n", rc);
-		return -EIO;
+	if (rc == OPAL_ASYNC_COMPLETION) {
+		rc = opal_async_wait_response_interruptible(token, &msg);
+		if (rc) {
+			/*
+			 * If we return the mtd core will free the
+			 * buffer we've just passed to OPAL but OPAL
+			 * will continue to read or write from that
+			 * memory.
+			 * It may be tempting to ultimately return 0
+			 * if we're doing a read or a write since we
+			 * are going to end up waiting until OPAL is
+			 * done. However, because the MTD core sends
+			 * us the userspace request in chunks, we need
+			 * it to know we've been interrupted.
+			 */
+			rc = -EINTR;
+			if (opal_async_wait_response(token, &msg))
+				dev_err(dev, "opal_async_wait_response() failed\n");
+			goto out;
+		}
+		rc = opal_get_async_rc(msg);
 	}
 
-	rc = opal_get_async_rc(msg);
-	if (rc == OPAL_SUCCESS) {
-		rc = 0;
-		if (retlen)
-			*retlen = len;
-	} else {
-		rc = -EIO;
-	}
+	/*
+	 * OPAL does mutual exclusion on the flash, it will return
+	 * OPAL_BUSY.
+	 * During firmware updates by the service processor OPAL may
+	 * be (temporarily) prevented from accessing the flash, in
+	 * this case OPAL will also return OPAL_BUSY.
+	 * Both cases aren't errors exactly but the flash could have
+	 * changed, userspace should be informed.
+	 */
+	if (rc != OPAL_SUCCESS && rc != OPAL_BUSY)
+		dev_err(dev, "opal_flash_async_op(op=%d) failed (rc %d)\n",
+				op, rc);
+
+	if (rc == OPAL_SUCCESS && retlen)
+		*retlen = len;
 
+	rc = opal_error_code(rc);
+out:
+	opal_async_release_token(token);
 	return rc;
 }
 
@@ -220,21 +247,20 @@ static int powernv_flash_probe(struct platform_device *pdev)
 	int ret;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
-	if (!data) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!data)
+		return -ENOMEM;
+
 	data->mtd.priv = data;
 
 	ret = of_property_read_u32(dev->of_node, "ibm,opal-id", &(data->id));
 	if (ret) {
 		dev_err(dev, "no device property 'ibm,opal-id'\n");
-		goto out;
+		return ret;
 	}
 
 	ret = powernv_flash_set_driver_info(dev, &data->mtd);
 	if (ret)
-		goto out;
+		return ret;
 
 	dev_set_drvdata(dev, data);
 
@@ -243,10 +269,7 @@ static int powernv_flash_probe(struct platform_device *pdev)
 	 * with an ffs partition at the start, it should prove easier for users
 	 * to deal with partitions or not as they see fit
 	 */
-	ret = mtd_device_register(&data->mtd, NULL, 0);
-
-out:
-	return ret;
+	return mtd_device_register(&data->mtd, NULL, 0);
 }
 
 /**