Merge tag 'powerpc-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Removal of the NPU DMA code, used by the out-of-tree Nvidia driver,
     as well as some other functions only used by drivers that haven't
     (yet?) made it upstream.

   - A fix for a bug in our handling of hardware watchpoints (eg. perf
     record -e mem: ...) which could lead to register corruption and
     kernel crashes.

   - Enable HAVE_ARCH_HUGE_VMAP, which allows us to use large pages for
     vmalloc when using the Radix MMU.

   - A large but incremental rewrite of our exception handling code to
     use gas macros rather than multiple levels of nested CPP macros.

  And the usual small fixes, cleanups and improvements.

  Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Andreas Schwab,
  Aneesh Kumar K.V, Anju T Sudhakar, Anton Blanchard, Arnd Bergmann,
  Athira Rajeev, Cédric Le Goater, Christian Lamparter, Christophe
  Leroy, Christophe Lombard, Christoph Hellwig, Daniel Axtens, Denis
  Efremov, Enrico Weigelt, Frederic Barrat, Gautham R. Shenoy, Geert
  Uytterhoeven, Geliang Tang, Gen Zhang, Greg Kroah-Hartman, Greg Kurz,
  Gustavo Romero, Krzysztof Kozlowski, Madhavan Srinivasan, Masahiro
  Yamada, Mathieu Malaterre, Michael Neuling, Nathan Lynch, Naveen N.
  Rao, Nicholas Piggin, Nishad Kamdar, Oliver O'Halloran, Qian Cai, Ravi
  Bangoria, Sachin Sant, Sam Bobroff, Satheesh Rajendran, Segher
  Boessenkool, Shaokun Zhang, Shawn Anastasio, Stewart Smith, Suraj
  Jitindar Singh, Thiago Jung Bauermann, YueHaibing"

* tag 'powerpc-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (163 commits)
  powerpc/powernv/idle: Fix restore of SPRN_LDBAR for POWER9 stop state.
  powerpc/eeh: Handle hugepages in ioremap space
  ocxl: Update for AFU descriptor template version 1.1
  powerpc/boot: pass CONFIG options in a simpler and more robust way
  powerpc/boot: add {get, put}_unaligned_be32 to xz_config.h
  powerpc/irq: Don't WARN continuously in arch_local_irq_restore()
  powerpc/module64: Use symbolic instructions names.
  powerpc/module32: Use symbolic instructions names.
  powerpc: Move PPC_HA() PPC_HI() and PPC_LO() to ppc-opcode.h
  powerpc/module64: Fix comment in R_PPC64_ENTRY handling
  powerpc/boot: Add lzo support for uImage
  powerpc/boot: Add lzma support for uImage
  powerpc/boot: don't force gzipped uImage
  powerpc/8xx: Add microcode patch to move SMC parameter RAM.
  powerpc/8xx: Use IO accessors in microcode programming.
  powerpc/8xx: replace #ifdefs by IS_ENABLED() in microcode.c
  powerpc/8xx: refactor programming of microcode CPM params.
  powerpc/8xx: refactor printing of microcode patch name.
  powerpc/8xx: Refactor microcode write
  powerpc/8xx: refactor writing of CPM microcode arrays
  ...

4 files changed, 179 insertions, 24 deletions

diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index 01e298f620f3..276065c888bc 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -132,7 +132,7 @@ static void smu_start_cmd(void)
 	/* Flush command and data to RAM */
 	faddr = (unsigned long)smu->cmd_buf;
 	fend = faddr + smu->cmd_buf->length + 2;
-	flush_inval_dcache_range(faddr, fend);
+	flush_dcache_range(faddr, fend);
 
 
 	/* We also disable NAP mode for the duration of the command
@@ -194,7 +194,7 @@ static irqreturn_t smu_db_intr(int irq, void *arg)
 		 * reply length (it's only 2 cache lines anyway)
 		 */
 		faddr = (unsigned long)smu->cmd_buf;
-		flush_inval_dcache_range(faddr, faddr + 256);
+		flush_dcache_range(faddr, faddr + 256);
 
 		/* Now check ack */
 		ack = (~cmd->cmd) & 0xff;
diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c
index 5e65acb8e134..c8e19bfb5ef9 100644
--- a/drivers/misc/ocxl/config.c
+++ b/drivers/misc/ocxl/config.c
@@ -20,11 +20,14 @@
 #define OCXL_DVSEC_TEMPL_MMIO_GLOBAL_SZ  0x28
 #define OCXL_DVSEC_TEMPL_MMIO_PP         0x30
 #define OCXL_DVSEC_TEMPL_MMIO_PP_SZ      0x38
-#define OCXL_DVSEC_TEMPL_MEM_SZ          0x3C
-#define OCXL_DVSEC_TEMPL_WWID            0x40
+#define OCXL_DVSEC_TEMPL_ALL_MEM_SZ      0x3C
+#define OCXL_DVSEC_TEMPL_LPC_MEM_START   0x40
+#define OCXL_DVSEC_TEMPL_WWID            0x48
+#define OCXL_DVSEC_TEMPL_LPC_MEM_SZ      0x58
 
 #define OCXL_MAX_AFU_PER_FUNCTION 64
-#define OCXL_TEMPL_LEN            0x58
+#define OCXL_TEMPL_LEN_1_0        0x58
+#define OCXL_TEMPL_LEN_1_1        0x60
 #define OCXL_TEMPL_NAME_LEN       24
 #define OCXL_CFG_TIMEOUT     3
 
@@ -269,34 +272,72 @@ static int read_afu_info(struct pci_dev *dev, struct ocxl_fn_config *fn,
 	return 0;
 }
 
+/**
+ * Read the template version from the AFU
+ * dev: the device for the AFU
+ * fn: the AFU offsets
+ * len: outputs the template length
+ * version: outputs the major<<8,minor version
+ *
+ * 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)
+{
+	u32 val32;
+	u8 major, minor;
+	int rc;
+
+	rc = read_afu_info(dev, fn, OCXL_DVSEC_TEMPL_VERSION, &val32);
+	if (rc)
+		return rc;
+
+	*len = EXTRACT_BITS(val32, 16, 31);
+	major = EXTRACT_BITS(val32, 8, 15);
+	minor = EXTRACT_BITS(val32, 0, 7);
+	*version = (major << 8) + minor;
+	return 0;
+}
+
 int ocxl_config_check_afu_index(struct pci_dev *dev,
 				struct ocxl_fn_config *fn, int afu_idx)
 {
-	u32 val;
-	int rc, templ_major, templ_minor, len;
+	int rc;
+	u16 templ_version;
+	u16 len, expected_len;
 
 	pci_write_config_byte(dev,
 			fn->dvsec_afu_info_pos + OCXL_DVSEC_AFU_INFO_AFU_IDX,
 			afu_idx);
-	rc = read_afu_info(dev, fn, OCXL_DVSEC_TEMPL_VERSION, &val);
+
+	rc = read_template_version(dev, fn, &len, &templ_version);
 	if (rc)
 		return rc;
 
-	/* AFU index map can have holes */
-	if (!val)
+	/* AFU index map can have holes, in which case we read all 0's */
+	if (!templ_version && !len)
 		return 0;
 
-	templ_major = EXTRACT_BITS(val, 8, 15);
-	templ_minor = EXTRACT_BITS(val, 0, 7);
 	dev_dbg(&dev->dev, "AFU descriptor template version %d.%d\n",
-		templ_major, templ_minor);
-
-	len = EXTRACT_BITS(val, 16, 31);
-	if (len != OCXL_TEMPL_LEN) {
-		dev_warn(&dev->dev,
-			"Unexpected template length in AFU information (%#x)\n",
-			len);
+		templ_version >> 8, templ_version & 0xFF);
+
+	switch (templ_version) {
+	case 0x0005: // v0.5 was used prior to the spec approval
+	case 0x0100:
+		expected_len = OCXL_TEMPL_LEN_1_0;
+		break;
+	case 0x0101:
+		expected_len = OCXL_TEMPL_LEN_1_1;
+		break;
+	default:
+		dev_warn(&dev->dev, "Unknown AFU template version %#x\n",
+			templ_version);
+		expected_len = len;
 	}
+	if (len != expected_len)
+		dev_warn(&dev->dev,
+			"Unexpected template length %#x in AFU information, expected %#x for version %#x\n",
+			len, expected_len, templ_version);
 	return 1;
 }
 
@@ -434,6 +475,102 @@ static int validate_afu(struct pci_dev *dev, struct ocxl_afu_config *afu)
 	return 0;
 }
 
+/**
+ * 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
+ *
+ * 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)
+{
+	int rc;
+	u32 val32;
+	u16 templ_version;
+	u16 templ_len;
+	u64 total_mem_size = 0;
+	u64 lpc_mem_size = 0;
+
+	afu->lpc_mem_offset = 0;
+	afu->lpc_mem_size = 0;
+	afu->special_purpose_mem_offset = 0;
+	afu->special_purpose_mem_size = 0;
+	/*
+	 * For AFUs following template v1.0, the LPC memory covers the
+	 * total memory. Its size is a power of 2.
+	 *
+	 * For AFUs with template >= v1.01, the total memory size is
+	 * still a power of 2, but it is split in 2 parts:
+	 * - the LPC memory, whose size can now be anything
+	 * - the remainder memory is a special purpose memory, whose
+	 *   definition is AFU-dependent. It is not accessible through
+	 *   the usual commands for LPC memory
+	 */
+	rc = read_afu_info(dev, fn, OCXL_DVSEC_TEMPL_ALL_MEM_SZ, &val32);
+	if (rc)
+		return rc;
+
+	val32 = EXTRACT_BITS(val32, 0, 7);
+	if (!val32)
+		return 0; /* No LPC memory */
+
+	/*
+	 * The configuration space spec allows for a memory size of up
+	 * to 2^255 bytes.
+	 *
+	 * Current generation hardware uses 56-bit physical addresses,
+	 * but we won't be able to get near close to that, as we won't
+	 * have a hole big enough in the memory map.  Let it pass in
+	 * the driver for now. We'll get an error from the firmware
+	 * when trying to configure something too big.
+	 */
+	total_mem_size = 1ull << val32;
+
+	rc = read_afu_info(dev, fn, OCXL_DVSEC_TEMPL_LPC_MEM_START, &val32);
+	if (rc)
+		return rc;
+
+	afu->lpc_mem_offset = val32;
+
+	rc = read_afu_info(dev, fn, OCXL_DVSEC_TEMPL_LPC_MEM_START + 4, &val32);
+	if (rc)
+		return rc;
+
+	afu->lpc_mem_offset |= (u64) val32 << 32;
+
+	rc = read_template_version(dev, fn, &templ_len, &templ_version);
+	if (rc)
+		return rc;
+
+	if (templ_version >= 0x0101) {
+		rc = read_afu_info(dev, fn,
+				OCXL_DVSEC_TEMPL_LPC_MEM_SZ, &val32);
+		if (rc)
+			return rc;
+		lpc_mem_size = val32;
+
+		rc = read_afu_info(dev, fn,
+				OCXL_DVSEC_TEMPL_LPC_MEM_SZ + 4, &val32);
+		if (rc)
+			return rc;
+		lpc_mem_size |= (u64) val32 << 32;
+	} else {
+		lpc_mem_size = total_mem_size;
+	}
+	afu->lpc_mem_size = lpc_mem_size;
+
+	if (lpc_mem_size < total_mem_size) {
+		afu->special_purpose_mem_offset =
+			afu->lpc_mem_offset + lpc_mem_size;
+		afu->special_purpose_mem_size =
+			total_mem_size - lpc_mem_size;
+	}
+	return 0;
+}
+
 int ocxl_config_read_afu(struct pci_dev *dev, struct ocxl_fn_config *fn,
 			struct ocxl_afu_config *afu, u8 afu_idx)
 {
@@ -467,10 +604,9 @@ int ocxl_config_read_afu(struct pci_dev *dev, struct ocxl_fn_config *fn,
 	if (rc)
 		return rc;
 
-	rc = read_afu_info(dev, fn, OCXL_DVSEC_TEMPL_MEM_SZ, &val32);
+	rc = read_afu_lpc_memory_info(dev, fn, afu);
 	if (rc)
 		return rc;
-	afu->log_mem_size = EXTRACT_BITS(val32, 0, 7);
 
 	rc = read_afu_control(dev, afu);
 	if (rc)
@@ -487,7 +623,12 @@ int ocxl_config_read_afu(struct pci_dev *dev, struct ocxl_fn_config *fn,
 	dev_dbg(&dev->dev, "  pp mmio bar = %hhu\n", afu->pp_mmio_bar);
 	dev_dbg(&dev->dev, "  pp mmio offset = %#llx\n", afu->pp_mmio_offset);
 	dev_dbg(&dev->dev, "  pp mmio stride = %#x\n", afu->pp_mmio_stride);
-	dev_dbg(&dev->dev, "  mem size (log) = %hhu\n", afu->log_mem_size);
+	dev_dbg(&dev->dev, "  lpc_mem offset = %#llx\n", afu->lpc_mem_offset);
+	dev_dbg(&dev->dev, "  lpc_mem size = %#llx\n", afu->lpc_mem_size);
+	dev_dbg(&dev->dev, "  special purpose mem offset = %#llx\n",
+		afu->special_purpose_mem_offset);
+	dev_dbg(&dev->dev, "  special purpose mem size = %#llx\n",
+		afu->special_purpose_mem_size);
 	dev_dbg(&dev->dev, "  pasid supported (log) = %u\n",
 		afu->pasid_supported_log);
 	dev_dbg(&dev->dev, "  actag supported = %u\n",
diff --git a/drivers/misc/ocxl/pci.c b/drivers/misc/ocxl/pci.c
index f2a3ef4b9bdd..cb920aa88d3a 100644
--- a/drivers/misc/ocxl/pci.c
+++ b/drivers/misc/ocxl/pci.c
@@ -41,7 +41,7 @@ static int ocxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	return 0;
 }
 
-void ocxl_remove(struct pci_dev *dev)
+static void ocxl_remove(struct pci_dev *dev)
 {
 	struct ocxl_fn *fn;
 	struct ocxl_afu *afu;
diff --git a/drivers/tty/hvc/hvc_vio.c b/drivers/tty/hvc/hvc_vio.c
index 6de6d4a1a221..7af54d6ed5b8 100644
--- a/drivers/tty/hvc/hvc_vio.c
+++ b/drivers/tty/hvc/hvc_vio.c
@@ -107,6 +107,14 @@ static int hvterm_raw_get_chars(uint32_t vtermno, char *buf, int count)
 	return got;
 }
 
+/**
+ * hvterm_raw_put_chars: send characters to firmware for given vterm adapter
+ * @vtermno: The virtual terminal number.
+ * @buf: The characters to send. Because of the underlying hypercall in
+ *       hvc_put_chars(), this buffer must be at least 16 bytes long, even if
+ *       you are sending fewer chars.
+ * @count: number of chars to send.
+ */
 static int hvterm_raw_put_chars(uint32_t vtermno, const char *buf, int count)
 {
 	struct hvterm_priv *pv = hvterm_privs[vtermno];
@@ -219,6 +227,7 @@ static const struct hv_ops hvterm_hvsi_ops = {
 static void udbg_hvc_putc(char c)
 {
 	int count = -1;
+	unsigned char bounce_buffer[16];
 
 	if (!hvterm_privs[0])
 		return;
@@ -229,7 +238,12 @@ static void udbg_hvc_putc(char c)
 	do {
 		switch(hvterm_privs[0]->proto) {
 		case HV_PROTOCOL_RAW:
-			count = hvterm_raw_put_chars(0, &c, 1);
+			/*
+			 * hvterm_raw_put_chars requires at least a 16-byte
+			 * buffer, so go via the bounce buffer
+			 */
+			bounce_buffer[0] = c;
+			count = hvterm_raw_put_chars(0, bounce_buffer, 1);
 			break;
 		case HV_PROTOCOL_HVSI:
 			count = hvterm_hvsi_put_chars(0, &c, 1);