Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma

Pull rdma updates from Doug Ledford:
 "This is the complete update for the rdma stack for this release cycle.

  Most of it is typical driver and core updates, but there is the
  entirely new VMWare pvrdma driver. You may have noticed that there
  were changes in DaveM's pull request to the bnxt Ethernet driver to
  support a RoCE RDMA driver. The bnxt_re driver was tentatively set to
  be pulled in this release cycle, but it simply wasn't ready in time
  and was dropped (a few review comments still to address, and some
  multi-arch build issues like prefetch() not working across all
  arches).

  Summary:

   - shared mlx5 updates with net stack (will drop out on merge if
     Dave's tree has already been merged)

   - driver updates: cxgb4, hfi1, hns-roce, i40iw, mlx4, mlx5, qedr, rxe

   - debug cleanups

   - new connection rejection helpers

   - SRP updates

   - various misc fixes

   - new paravirt driver from vmware"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (210 commits)
  IB: Add vmw_pvrdma driver
  IB/mlx4: fix improper return value
  IB/ocrdma: fix bad initialization
  infiniband: nes: return value of skb_linearize should be handled
  MAINTAINERS: Update Intel RDMA RNIC driver maintainers
  MAINTAINERS: Remove Mitesh Ahuja from emulex maintainers
  IB/core: fix unmap_sg argument
  qede: fix general protection fault may occur on probe
  IB/mthca: Replace pci_pool_alloc by pci_pool_zalloc
  mlx5, calc_sq_size(): Make a debug message more informative
  mlx5: Remove a set-but-not-used variable
  mlx5: Use { } instead of { 0 } to init struct
  IB/srp: Make writing the add_target sysfs attr interruptible
  IB/srp: Make mapping failures easier to debug
  IB/srp: Make login failures easier to debug
  IB/srp: Introduce a local variable in srp_add_one()
  IB/srp: Fix CONFIG_DYNAMIC_DEBUG=n build
  IB/multicast: Check ib_find_pkey() return value
  IPoIB: Avoid reading an uninitialized member variable
  IB/mad: Fix an array index check
  ...

1 files changed, 167 insertions, 26 deletions

diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c
index 202433178864..838fe84e285a 100644
--- a/drivers/infiniband/hw/hfi1/platform.c
+++ b/drivers/infiniband/hw/hfi1/platform.c
@@ -49,6 +49,90 @@
 #include "efivar.h"
 #include "eprom.h"
 
+static int validate_scratch_checksum(struct hfi1_devdata *dd)
+{
+	u64 checksum = 0, temp_scratch = 0;
+	int i, j, version;
+
+	temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH);
+	version = (temp_scratch & BITMAP_VERSION_SMASK) >> BITMAP_VERSION_SHIFT;
+
+	/* Prevent power on default of all zeroes from passing checksum */
+	if (!version)
+		return 0;
+
+	/*
+	 * ASIC scratch 0 only contains the checksum and bitmap version as
+	 * fields of interest, both of which are handled separately from the
+	 * loop below, so skip it
+	 */
+	checksum += version;
+	for (i = 1; i < ASIC_NUM_SCRATCH; i++) {
+		temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH + (8 * i));
+		for (j = sizeof(u64); j != 0; j -= 2) {
+			checksum += (temp_scratch & 0xFFFF);
+			temp_scratch >>= 16;
+		}
+	}
+
+	while (checksum >> 16)
+		checksum = (checksum & CHECKSUM_MASK) + (checksum >> 16);
+
+	temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH);
+	temp_scratch &= CHECKSUM_SMASK;
+	temp_scratch >>= CHECKSUM_SHIFT;
+
+	if (checksum + temp_scratch == 0xFFFF)
+		return 1;
+	return 0;
+}
+
+static void save_platform_config_fields(struct hfi1_devdata *dd)
+{
+	struct hfi1_pportdata *ppd = dd->pport;
+	u64 temp_scratch = 0, temp_dest = 0;
+
+	temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH_1);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_PORT_TYPE_SMASK :
+		     PORT0_PORT_TYPE_SMASK);
+	ppd->port_type = temp_dest >>
+			 (dd->hfi1_id ? PORT1_PORT_TYPE_SHIFT :
+			  PORT0_PORT_TYPE_SHIFT);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_LOCAL_ATTEN_SMASK :
+		     PORT0_LOCAL_ATTEN_SMASK);
+	ppd->local_atten = temp_dest >>
+			   (dd->hfi1_id ? PORT1_LOCAL_ATTEN_SHIFT :
+			    PORT0_LOCAL_ATTEN_SHIFT);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_REMOTE_ATTEN_SMASK :
+		     PORT0_REMOTE_ATTEN_SMASK);
+	ppd->remote_atten = temp_dest >>
+			    (dd->hfi1_id ? PORT1_REMOTE_ATTEN_SHIFT :
+			     PORT0_REMOTE_ATTEN_SHIFT);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_DEFAULT_ATTEN_SMASK :
+		     PORT0_DEFAULT_ATTEN_SMASK);
+	ppd->default_atten = temp_dest >>
+			     (dd->hfi1_id ? PORT1_DEFAULT_ATTEN_SHIFT :
+			      PORT0_DEFAULT_ATTEN_SHIFT);
+
+	temp_scratch = read_csr(dd, dd->hfi1_id ? ASIC_CFG_SCRATCH_3 :
+				ASIC_CFG_SCRATCH_2);
+
+	ppd->tx_preset_eq = (temp_scratch & TX_EQ_SMASK) >> TX_EQ_SHIFT;
+	ppd->tx_preset_noeq = (temp_scratch & TX_NO_EQ_SMASK) >> TX_NO_EQ_SHIFT;
+	ppd->rx_preset = (temp_scratch & RX_SMASK) >> RX_SHIFT;
+
+	ppd->max_power_class = (temp_scratch & QSFP_MAX_POWER_SMASK) >>
+				QSFP_MAX_POWER_SHIFT;
+}
+
 void get_platform_config(struct hfi1_devdata *dd)
 {
 	int ret = 0;
@@ -56,38 +140,49 @@ void get_platform_config(struct hfi1_devdata *dd)
 	u8 *temp_platform_config = NULL;
 	u32 esize;
 
-	ret = eprom_read_platform_config(dd, (void **)&temp_platform_config,
-					 &esize);
-	if (!ret) {
-		/* success */
-		size = esize;
-		goto success;
+	if (is_integrated(dd)) {
+		if (validate_scratch_checksum(dd)) {
+			save_platform_config_fields(dd);
+			return;
+		}
+		dd_dev_err(dd, "%s: Config bitmap corrupted/uninitialized\n",
+			   __func__);
+		dd_dev_err(dd,
+			   "%s: Please update your BIOS to support active channels\n",
+			   __func__);
+	} else {
+		ret = eprom_read_platform_config(dd,
+						 (void **)&temp_platform_config,
+						 &esize);
+		if (!ret) {
+			/* success */
+			dd->platform_config.data = temp_platform_config;
+			dd->platform_config.size = esize;
+			return;
+		}
+		/* fail, try EFI variable */
+
+		ret = read_hfi1_efi_var(dd, "configuration", &size,
+					(void **)&temp_platform_config);
+		if (!ret) {
+			dd->platform_config.data = temp_platform_config;
+			dd->platform_config.size = size;
+			return;
+		}
 	}
-	/* fail, try EFI variable */
-
-	ret = read_hfi1_efi_var(dd, "configuration", &size,
-				(void **)&temp_platform_config);
-	if (!ret)
-		goto success;
-
-	dd_dev_info(dd,
-		    "%s: Failed to get platform config from UEFI, falling back to request firmware\n",
-		    __func__);
+	dd_dev_err(dd,
+		   "%s: Failed to get platform config, falling back to sub-optimal default file\n",
+		   __func__);
 	/* fall back to request firmware */
 	platform_config_load = 1;
-	return;
-
-success:
-	dd->platform_config.data = temp_platform_config;
-	dd->platform_config.size = size;
 }
 
 void free_platform_config(struct hfi1_devdata *dd)
 {
 	if (!platform_config_load) {
 		/*
-		 * was loaded from EFI, release memory
-		 * allocated by read_efi_var
+		 * was loaded from EFI or the EPROM, release memory
+		 * allocated by read_efi_var/eprom_read_platform_config
 		 */
 		kfree(dd->platform_config.data);
 	}
@@ -100,12 +195,16 @@ void free_platform_config(struct hfi1_devdata *dd)
 void get_port_type(struct hfi1_pportdata *ppd)
 {
 	int ret;
+	u32 temp;
 
 	ret = get_platform_config_field(ppd->dd, PLATFORM_CONFIG_PORT_TABLE, 0,
-					PORT_TABLE_PORT_TYPE, &ppd->port_type,
+					PORT_TABLE_PORT_TYPE, &temp,
 					4);
-	if (ret)
+	if (ret) {
 		ppd->port_type = PORT_TYPE_UNKNOWN;
+		return;
+	}
+	ppd->port_type = temp;
 }
 
 int set_qsfp_tx(struct hfi1_pportdata *ppd, int on)
@@ -538,6 +637,38 @@ static void apply_tx_lanes(struct hfi1_pportdata *ppd, u8 field_id,
 	}
 }
 
+/*
+ * Return a special SerDes setting for low power AOC cables.  The power class
+ * threshold and setting being used were all found by empirical testing.
+ *
+ * Summary of the logic:
+ *
+ * if (QSFP and QSFP_TYPE == AOC and QSFP_POWER_CLASS < 4)
+ *     return 0xe
+ * return 0; // leave at default
+ */
+static u8 aoc_low_power_setting(struct hfi1_pportdata *ppd)
+{
+	u8 *cache = ppd->qsfp_info.cache;
+	int power_class;
+
+	/* QSFP only */
+	if (ppd->port_type != PORT_TYPE_QSFP)
+		return 0; /* leave at default */
+
+	/* active optical cables only */
+	switch ((cache[QSFP_MOD_TECH_OFFS] & 0xF0) >> 4) {
+	case 0x0 ... 0x9: /* fallthrough */
+	case 0xC: /* fallthrough */
+	case 0xE:
+		/* active AOC */
+		power_class = get_qsfp_power_class(cache[QSFP_MOD_PWR_OFFS]);
+		if (power_class < QSFP_POWER_CLASS_4)
+			return 0xe;
+	}
+	return 0; /* leave at default */
+}
+
 static void apply_tunings(
 		struct hfi1_pportdata *ppd, u32 tx_preset_index,
 		u8 tuning_method, u32 total_atten, u8 limiting_active)
@@ -606,7 +737,17 @@ static void apply_tunings(
 		tx_preset_index, TX_PRESET_TABLE_POSTCUR, &tx_preset, 4);
 	postcur = tx_preset;
 
-	config_data = precur | (attn << 8) | (postcur << 16);
+	/*
+	 * NOTES:
+	 * o The aoc_low_power_setting is applied to all lanes even
+	 *   though only lane 0's value is examined by the firmware.
+	 * o A lingering low power setting after a cable swap does
+	 *   not occur.  On cable unplug the 8051 is reset and
+	 *   restarted on cable insert.  This resets all settings to
+	 *   their default, erasing any previous low power setting.
+	 */
+	config_data = precur | (attn << 8) | (postcur << 16) |
+			(aoc_low_power_setting(ppd) << 24);
 
 	apply_tx_lanes(ppd, TX_EQ_SETTINGS, config_data,
 		       "Applying TX settings");