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

Pull rdma updates from Jason Gunthorpe:
 "This has been a fairly typical cycle, with the usual sorts of driver
  updates. Several series continue to come through which improve and
  modernize various parts of the core code, and we finally are starting
  to get the uAPI command interface cleaned up.

   - Various driver fixes for bnxt_re, cxgb3/4, hfi1, hns, i40iw, mlx4,
     mlx5, qib, rxe, usnic

   - Rework the entire syscall flow for uverbs to be able to run over
     ioctl(). Finally getting past the historic bad choice to use
     write() for command execution

   - More functional coverage with the mlx5 'devx' user API

   - Start of the HFI1 series for 'TID RDMA'

   - SRQ support in the hns driver

   - Support for new IBTA defined 2x lane widths

   - A big series to consolidate all the driver function pointers into a
     big struct and have drivers provide a 'static const' version of the
     struct instead of open coding initialization

   - New 'advise_mr' uAPI to control device caching/loading of page
     tables

   - Support for inline data in SRPT

   - Modernize how umad uses the driver core and creates cdev's and
     sysfs files

   - First steps toward removing 'uobject' from the view of the drivers"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (193 commits)
  RDMA/srpt: Use kmem_cache_free() instead of kfree()
  RDMA/mlx5: Signedness bug in UVERBS_HANDLER()
  IB/uverbs: Signedness bug in UVERBS_HANDLER()
  IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported
  IB/umad: Start using dev_groups of class
  IB/umad: Use class_groups and let core create class file
  IB/umad: Refactor code to use cdev_device_add()
  IB/umad: Avoid destroying device while it is accessed
  IB/umad: Simplify and avoid dynamic allocation of class
  IB/mlx5: Fix wrong error unwind
  IB/mlx4: Remove set but not used variable 'pd'
  RDMA/iwcm: Don't copy past the end of dev_name() string
  IB/mlx5: Fix long EEH recover time with NVMe offloads
  IB/mlx5: Simplify netdev unbinding
  IB/core: Move query port to ioctl
  RDMA/nldev: Expose port_cap_flags2
  IB/core: uverbs copy to struct or zero helper
  IB/rxe: Reuse code which sets port state
  IB/rxe: Make counters thread safe
  IB/mlx5: Use the correct commands for UMEM and UCTX allocation
  ...

1 files changed, 46 insertions, 1 deletions

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 7e6d70936c63..b443642eac02 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1072,6 +1072,8 @@ static void log_state_transition(struct hfi1_pportdata *ppd, u32 state);
 static void log_physical_state(struct hfi1_pportdata *ppd, u32 state);
 static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state,
 				   int msecs);
+static int wait_phys_link_out_of_offline(struct hfi1_pportdata *ppd,
+					 int msecs);
 static void read_planned_down_reason_code(struct hfi1_devdata *dd, u8 *pdrrc);
 static void read_link_down_reason(struct hfi1_devdata *dd, u8 *ldr);
 static void handle_temp_err(struct hfi1_devdata *dd);
@@ -10770,13 +10772,15 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 			break;
 
 		ppd->port_error_action = 0;
-		ppd->host_link_state = HLS_DN_POLL;
 
 		if (quick_linkup) {
 			/* quick linkup does not go into polling */
 			ret = do_quick_linkup(dd);
 		} else {
 			ret1 = set_physical_link_state(dd, PLS_POLLING);
+			if (!ret1)
+				ret1 = wait_phys_link_out_of_offline(ppd,
+								     3000);
 			if (ret1 != HCMD_SUCCESS) {
 				dd_dev_err(dd,
 					   "Failed to transition to Polling link state, return 0x%x\n",
@@ -10784,6 +10788,14 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 				ret = -EINVAL;
 			}
 		}
+
+		/*
+		 * Change the host link state after requesting DC8051 to
+		 * change its physical state so that we can ignore any
+		 * interrupt with stale LNI(XX) error, which will not be
+		 * cleared until DC8051 transitions to Polling state.
+		 */
+		ppd->host_link_state = HLS_DN_POLL;
 		ppd->offline_disabled_reason =
 			HFI1_ODR_MASK(OPA_LINKDOWN_REASON_NONE);
 		/*
@@ -12928,6 +12940,39 @@ static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
 	return read_state;
 }
 
+/*
+ * wait_phys_link_out_of_offline - wait for any out of offline state
+ * @ppd: port device
+ * @msecs: the number of milliseconds to wait
+ *
+ * Wait up to msecs milliseconds for any out of offline physical link
+ * state change to occur.
+ * Returns 0 if at least one state is reached, otherwise -ETIMEDOUT.
+ */
+static int wait_phys_link_out_of_offline(struct hfi1_pportdata *ppd,
+					 int msecs)
+{
+	u32 read_state;
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(msecs);
+	while (1) {
+		read_state = read_physical_state(ppd->dd);
+		if ((read_state & 0xF0) != PLS_OFFLINE)
+			break;
+		if (time_after(jiffies, timeout)) {
+			dd_dev_err(ppd->dd,
+				   "timeout waiting for phy link out of offline. Read state 0x%x, %dms\n",
+				   read_state, msecs);
+			return -ETIMEDOUT;
+		}
+		usleep_range(1950, 2050); /* sleep 2ms-ish */
+	}
+
+	log_state_transition(ppd, read_state);
+	return read_state;
+}
+
 #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \
 (r &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK)