Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Overlapping changes in drivers/net/phy/marvell.c, bug fix in 'net'
restricting a HW workaround alongside cleanups in 'net-next'.

Signed-off-by: David S. Miller <davem@davemloft.net>

79 files changed, 1433 insertions, 775 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 236d9950221b..c0d8c6ff6380 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -425,10 +425,15 @@ bool amdgpu_fbdev_robj_is_fb(struct amdgpu_device *adev, struct amdgpu_bo *robj)
 
 void amdgpu_fbdev_restore_mode(struct amdgpu_device *adev)
 {
-	struct amdgpu_fbdev *afbdev = adev->mode_info.rfbdev;
+	struct amdgpu_fbdev *afbdev;
 	struct drm_fb_helper *fb_helper;
 	int ret;
 
+	if (!adev)
+		return;
+
+	afbdev = adev->mode_info.rfbdev;
+
 	if (!afbdev)
 		return;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 07ff3b1514f1..8ecf82c5fe74 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -634,7 +634,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job)
 		mutex_unlock(&id_mgr->lock);
 	}
 
-	if (gds_switch_needed) {
+	if (ring->funcs->emit_gds_switch && gds_switch_needed) {
 		id->gds_base = job->gds_base;
 		id->gds_size = job->gds_size;
 		id->gws_base = job->gws_base;
@@ -672,6 +672,7 @@ void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vmhub,
 	struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
 	struct amdgpu_vm_id *id = &id_mgr->ids[vmid];
 
+	atomic64_set(&id->owner, 0);
 	id->gds_base = 0;
 	id->gds_size = 0;
 	id->gws_base = 0;
@@ -681,6 +682,26 @@ void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vmhub,
 }
 
 /**
+ * amdgpu_vm_reset_all_id - reset VMID to zero
+ *
+ * @adev: amdgpu device structure
+ *
+ * Reset VMID to force flush on next use
+ */
+void amdgpu_vm_reset_all_ids(struct amdgpu_device *adev)
+{
+	unsigned i, j;
+
+	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
+		struct amdgpu_vm_id_manager *id_mgr =
+			&adev->vm_manager.id_mgr[i];
+
+		for (j = 1; j < id_mgr->num_ids; ++j)
+			amdgpu_vm_reset_id(adev, i, j);
+	}
+}
+
+/**
  * amdgpu_vm_bo_find - find the bo_va for a specific vm & bo
  *
  * @vm: requested vm
@@ -2270,7 +2291,6 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
 		adev->vm_manager.seqno[i] = 0;
 
-
 	atomic_set(&adev->vm_manager.vm_pte_next_ring, 0);
 	atomic64_set(&adev->vm_manager.client_counter, 0);
 	spin_lock_init(&adev->vm_manager.prt_lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index d97e28b4bdc4..e1d951ece433 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -204,6 +204,7 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job);
 void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vmhub,
 			unsigned vmid);
+void amdgpu_vm_reset_all_ids(struct amdgpu_device *adev);
 int amdgpu_vm_update_directories(struct amdgpu_device *adev,
 				 struct amdgpu_vm *vm);
 int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 6dc1410b380f..ec93714e4524 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -906,6 +906,12 @@ static bool ci_dpm_vblank_too_short(struct amdgpu_device *adev)
 	u32 vblank_time = amdgpu_dpm_get_vblank_time(adev);
 	u32 switch_limit = adev->mc.vram_type == AMDGPU_VRAM_TYPE_GDDR5 ? 450 : 300;
 
+	/* disable mclk switching if the refresh is >120Hz, even if the
+	 * blanking period would allow it
+	 */
+	if (amdgpu_dpm_get_vrefresh(adev) > 120)
+		return true;
+
 	if (vblank_time < switch_limit)
 		return true;
 	else
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index a572979f186c..d860939152df 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -950,10 +950,6 @@ static int gmc_v6_0_suspend(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->vm_manager.enabled) {
-		gmc_v6_0_vm_fini(adev);
-		adev->vm_manager.enabled = false;
-	}
 	gmc_v6_0_hw_fini(adev);
 
 	return 0;
@@ -968,16 +964,9 @@ static int gmc_v6_0_resume(void *handle)
 	if (r)
 		return r;
 
-	if (!adev->vm_manager.enabled) {
-		r = gmc_v6_0_vm_init(adev);
-		if (r) {
-			dev_err(adev->dev, "vm manager initialization failed (%d).\n", r);
-			return r;
-		}
-		adev->vm_manager.enabled = true;
-	}
+	amdgpu_vm_reset_all_ids(adev);
 
-	return r;
+	return 0;
 }
 
 static bool gmc_v6_0_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index a9083a16a250..2750e5c23813 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -1117,10 +1117,6 @@ static int gmc_v7_0_suspend(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->vm_manager.enabled) {
-		gmc_v7_0_vm_fini(adev);
-		adev->vm_manager.enabled = false;
-	}
 	gmc_v7_0_hw_fini(adev);
 
 	return 0;
@@ -1135,16 +1131,9 @@ static int gmc_v7_0_resume(void *handle)
 	if (r)
 		return r;
 
-	if (!adev->vm_manager.enabled) {
-		r = gmc_v7_0_vm_init(adev);
-		if (r) {
-			dev_err(adev->dev, "vm manager initialization failed (%d).\n", r);
-			return r;
-		}
-		adev->vm_manager.enabled = true;
-	}
+	amdgpu_vm_reset_all_ids(adev);
 
-	return r;
+	return 0;
 }
 
 static bool gmc_v7_0_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 4ac99784160a..f56b4089ee9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1209,10 +1209,6 @@ static int gmc_v8_0_suspend(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->vm_manager.enabled) {
-		gmc_v8_0_vm_fini(adev);
-		adev->vm_manager.enabled = false;
-	}
 	gmc_v8_0_hw_fini(adev);
 
 	return 0;
@@ -1227,16 +1223,9 @@ static int gmc_v8_0_resume(void *handle)
 	if (r)
 		return r;
 
-	if (!adev->vm_manager.enabled) {
-		r = gmc_v8_0_vm_init(adev);
-		if (r) {
-			dev_err(adev->dev, "vm manager initialization failed (%d).\n", r);
-			return r;
-		}
-		adev->vm_manager.enabled = true;
-	}
+	amdgpu_vm_reset_all_ids(adev);
 
-	return r;
+	return 0;
 }
 
 static bool gmc_v8_0_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index dc1e1c1d6b24..f936332a069d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -791,10 +791,6 @@ static int gmc_v9_0_suspend(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->vm_manager.enabled) {
-		gmc_v9_0_vm_fini(adev);
-		adev->vm_manager.enabled = false;
-	}
 	gmc_v9_0_hw_fini(adev);
 
 	return 0;
@@ -809,17 +805,9 @@ static int gmc_v9_0_resume(void *handle)
 	if (r)
 		return r;
 
-	if (!adev->vm_manager.enabled) {
-		r = gmc_v9_0_vm_init(adev);
-		if (r) {
-			dev_err(adev->dev,
-				"vm manager initialization failed (%d).\n", r);
-			return r;
-		}
-		adev->vm_manager.enabled = true;
-	}
+	amdgpu_vm_reset_all_ids(adev);
 
-	return r;
+	return 0;
 }
 
 static bool gmc_v9_0_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index a74a3db3056c..102eb6d029fa 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -2655,6 +2655,28 @@ static int smu7_get_power_state_size(struct pp_hwmgr *hwmgr)
 	return sizeof(struct smu7_power_state);
 }
 
+static int smu7_vblank_too_short(struct pp_hwmgr *hwmgr,
+				 uint32_t vblank_time_us)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	uint32_t switch_limit_us;
+
+	switch (hwmgr->chip_id) {
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
+		switch_limit_us = data->is_memory_gddr5 ? 190 : 150;
+		break;
+	default:
+		switch_limit_us = data->is_memory_gddr5 ? 450 : 150;
+		break;
+	}
+
+	if (vblank_time_us < switch_limit_us)
+		return true;
+	else
+		return false;
+}
 
 static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				struct pp_power_state *request_ps,
@@ -2669,6 +2691,7 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 	bool disable_mclk_switching;
 	bool disable_mclk_switching_for_frame_lock;
 	struct cgs_display_info info = {0};
+	struct cgs_mode_info mode_info = {0};
 	const struct phm_clock_and_voltage_limits *max_limits;
 	uint32_t i;
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
@@ -2677,6 +2700,7 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 	int32_t count;
 	int32_t stable_pstate_sclk = 0, stable_pstate_mclk = 0;
 
+	info.mode_info = &mode_info;
 	data->battery_state = (PP_StateUILabel_Battery ==
 			request_ps->classification.ui_label);
 
@@ -2703,8 +2727,6 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 
 	cgs_get_active_displays_info(hwmgr->device, &info);
 
-	/*TO DO result = PHM_CheckVBlankTime(hwmgr, &vblankTooShort);*/
-
 	minimum_clocks.engineClock = hwmgr->display_config.min_core_set_clock;
 	minimum_clocks.memoryClock = hwmgr->display_config.min_mem_set_clock;
 
@@ -2769,8 +2791,10 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				    PHM_PlatformCaps_DisableMclkSwitchingForFrameLock);
 
 
-	disable_mclk_switching = (1 < info.display_count) ||
-				    disable_mclk_switching_for_frame_lock;
+	disable_mclk_switching = ((1 < info.display_count) ||
+				  disable_mclk_switching_for_frame_lock ||
+				  smu7_vblank_too_short(hwmgr, mode_info.vblank_time_us) ||
+				  (mode_info.refresh_rate > 120));
 
 	sclk = smu7_ps->performance_levels[0].engine_clock;
 	mclk = smu7_ps->performance_levels[0].memory_clock;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index ad30f5d3a10d..2614af2f553f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -4186,7 +4186,7 @@ static int vega10_force_clock_level(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, uint32_t mask)
 {
 	struct vega10_hwmgr *data = (struct vega10_hwmgr *)(hwmgr->backend);
-	uint32_t i;
+	int i;
 
 	if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index fedd4d60d9cd..5dc8c4350602 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -948,8 +948,6 @@ retry:
 	}
 
 out:
-	if (ret && crtc->funcs->page_flip_target)
-		drm_crtc_vblank_put(crtc);
 	if (fb)
 		drm_framebuffer_put(fb);
 	if (crtc->primary->old_fb)
@@ -964,5 +962,8 @@ out:
 	drm_modeset_drop_locks(&ctx);
 	drm_modeset_acquire_fini(&ctx);
 
+	if (ret && crtc->funcs->page_flip_target)
+		drm_crtc_vblank_put(crtc);
+
 	return ret;
 }
diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c
index 0066fe7e622e..be3eefec5152 100644
--- a/drivers/gpu/drm/gma500/psb_intel_lvds.c
+++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c
@@ -759,20 +759,23 @@ void psb_intel_lvds_init(struct drm_device *dev,
 		if (scan->type & DRM_MODE_TYPE_PREFERRED) {
 			mode_dev->panel_fixed_mode =
 			    drm_mode_duplicate(dev, scan);
+			DRM_DEBUG_KMS("Using mode from DDC\n");
 			goto out;	/* FIXME: check for quirks */
 		}
 	}
 
 	/* Failed to get EDID, what about VBT? do we need this? */
-	if (mode_dev->vbt_mode)
+	if (dev_priv->lfp_lvds_vbt_mode) {
 		mode_dev->panel_fixed_mode =
-		    drm_mode_duplicate(dev, mode_dev->vbt_mode);
+			drm_mode_duplicate(dev, dev_priv->lfp_lvds_vbt_mode);
 
-	if (!mode_dev->panel_fixed_mode)
-		if (dev_priv->lfp_lvds_vbt_mode)
-			mode_dev->panel_fixed_mode =
-				drm_mode_duplicate(dev,
-					dev_priv->lfp_lvds_vbt_mode);
+		if (mode_dev->panel_fixed_mode) {
+			mode_dev->panel_fixed_mode->type |=
+				DRM_MODE_TYPE_PREFERRED;
+			DRM_DEBUG_KMS("Using mode from VBT\n");
+			goto out;
+		}
+	}
 
 	/*
 	 * If we didn't get EDID, try checking if the panel is already turned
@@ -789,6 +792,7 @@ void psb_intel_lvds_init(struct drm_device *dev,
 		if (mode_dev->panel_fixed_mode) {
 			mode_dev->panel_fixed_mode->type |=
 			    DRM_MODE_TYPE_PREFERRED;
+			DRM_DEBUG_KMS("Using pre-programmed mode\n");
 			goto out;	/* FIXME: check for quirks */
 		}
 	}
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 058340a002c2..4a340efd8ba6 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -575,8 +575,6 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane,
 	if (ret)
 		return;
 
-	cmd = (struct qxl_cursor_cmd *) qxl_release_map(qdev, release);
-
 	if (fb != old_state->fb) {
 		obj = to_qxl_framebuffer(fb)->obj;
 		user_bo = gem_to_qxl_bo(obj);
@@ -614,6 +612,7 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane,
 		qxl_bo_kunmap(cursor_bo);
 		qxl_bo_kunmap(user_bo);
 
+		cmd = (struct qxl_cursor_cmd *) qxl_release_map(qdev, release);
 		cmd->u.set.visible = 1;
 		cmd->u.set.shape = qxl_bo_physical_address(qdev,
 							   cursor_bo, 0);
@@ -624,6 +623,7 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane,
 		if (ret)
 			goto out_free_release;
 
+		cmd = (struct qxl_cursor_cmd *) qxl_release_map(qdev, release);
 		cmd->type = QXL_CURSOR_MOVE;
 	}
 
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 7ba450832e6b..ea36dc4dd5d2 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -776,6 +776,12 @@ bool ci_dpm_vblank_too_short(struct radeon_device *rdev)
 	u32 vblank_time = r600_dpm_get_vblank_time(rdev);
 	u32 switch_limit = pi->mem_gddr5 ? 450 : 300;
 
+	/* disable mclk switching if the refresh is >120Hz, even if the
+        * blanking period would allow it
+        */
+	if (r600_dpm_get_vrefresh(rdev) > 120)
+		return true;
+
 	if (vblank_time < switch_limit)
 		return true;
 	else
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index ccebe0f8d2e1..008c145b7f29 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -7401,7 +7401,7 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
@@ -7431,7 +7431,7 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_RX_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index f130ec41ee4b..0bf103536404 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -4927,7 +4927,7 @@ static void evergreen_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
@@ -4958,7 +4958,7 @@ static void evergreen_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_RX_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 0a085176e79b..e06e2d8feab3 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -3988,7 +3988,7 @@ static void r600_irq_ack(struct radeon_device *rdev)
 			WREG32(DC_HPD5_INT_CONTROL, tmp);
 		}
 		if (rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD6_INTERRUPT) {
-			tmp = RREG32(DC_HPD5_INT_CONTROL);
+			tmp = RREG32(DC_HPD6_INT_CONTROL);
 			tmp |= DC_HPDx_INT_ACK;
 			WREG32(DC_HPD6_INT_CONTROL, tmp);
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index e3e7cb1d10a2..4761f27f2ca2 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -116,7 +116,7 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	if ((radeon_runtime_pm != 0) &&
 	    radeon_has_atpx() &&
 	    ((flags & RADEON_IS_IGP) == 0) &&
-	    !pci_is_thunderbolt_attached(rdev->pdev))
+	    !pci_is_thunderbolt_attached(dev->pdev))
 		flags |= RADEON_IS_PX;
 
 	/* radeon_device_init should report only fatal error
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index ceee87f029d9..76d1888528e6 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -6317,7 +6317,7 @@ static inline void si_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
@@ -6348,7 +6348,7 @@ static inline void si_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_RX_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
diff --git a/drivers/i2c/busses/i2c-tiny-usb.c b/drivers/i2c/busses/i2c-tiny-usb.c
index 0ed77eeff31e..a2e3dd715380 100644
--- a/drivers/i2c/busses/i2c-tiny-usb.c
+++ b/drivers/i2c/busses/i2c-tiny-usb.c
@@ -178,22 +178,39 @@ static int usb_read(struct i2c_adapter *adapter, int cmd,
 		    int value, int index, void *data, int len)
 {
 	struct i2c_tiny_usb *dev = (struct i2c_tiny_usb *)adapter->algo_data;
+	void *dmadata = kmalloc(len, GFP_KERNEL);
+	int ret;
+
+	if (!dmadata)
+		return -ENOMEM;
 
 	/* do control transfer */
-	return usb_control_msg(dev->usb_dev, usb_rcvctrlpipe(dev->usb_dev, 0),
+	ret = usb_control_msg(dev->usb_dev, usb_rcvctrlpipe(dev->usb_dev, 0),
 			       cmd, USB_TYPE_VENDOR | USB_RECIP_INTERFACE |
-			       USB_DIR_IN, value, index, data, len, 2000);
+			       USB_DIR_IN, value, index, dmadata, len, 2000);
+
+	memcpy(data, dmadata, len);
+	kfree(dmadata);
+	return ret;
 }
 
 static int usb_write(struct i2c_adapter *adapter, int cmd,
 		     int value, int index, void *data, int len)
 {
 	struct i2c_tiny_usb *dev = (struct i2c_tiny_usb *)adapter->algo_data;
+	void *dmadata = kmemdup(data, len, GFP_KERNEL);
+	int ret;
+
+	if (!dmadata)
+		return -ENOMEM;
 
 	/* do control transfer */
-	return usb_control_msg(dev->usb_dev, usb_sndctrlpipe(dev->usb_dev, 0),
+	ret = usb_control_msg(dev->usb_dev, usb_sndctrlpipe(dev->usb_dev, 0),
 			       cmd, USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
-			       value, index, data, len, 2000);
+			       value, index, dmadata, len, 2000);
+
+	kfree(dmadata);
+	return ret;
 }
 
 static void i2c_tiny_usb_free(struct i2c_tiny_usb *dev)
diff --git a/drivers/leds/leds-pca955x.c b/drivers/leds/leds-pca955x.c
index 78a7ce816a47..9a873118ea5f 100644
--- a/drivers/leds/leds-pca955x.c
+++ b/drivers/leds/leds-pca955x.c
@@ -285,7 +285,7 @@ static int pca955x_probe(struct i2c_client *client,
 			"slave address 0x%02x\n",
 			client->name, chip->bits, client->addr);
 
-	if (!i2c_check_functionality(adapter, I2C_FUNC_I2C))
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
 		return -EIO;
 
 	if (pdata) {
diff --git a/drivers/mmc/core/pwrseq_simple.c b/drivers/mmc/core/pwrseq_simple.c
index 1304160de168..13ef162cf066 100644
--- a/drivers/mmc/core/pwrseq_simple.c
+++ b/drivers/mmc/core/pwrseq_simple.c
@@ -27,6 +27,7 @@ struct mmc_pwrseq_simple {
 	struct mmc_pwrseq pwrseq;
 	bool clk_enabled;
 	u32 post_power_on_delay_ms;
+	u32 power_off_delay_us;
 	struct clk *ext_clk;
 	struct gpio_descs *reset_gpios;
 };
@@ -78,6 +79,10 @@ static void mmc_pwrseq_simple_power_off(struct mmc_host *host)
 
 	mmc_pwrseq_simple_set_gpios_value(pwrseq, 1);
 
+	if (pwrseq->power_off_delay_us)
+		usleep_range(pwrseq->power_off_delay_us,
+			2 * pwrseq->power_off_delay_us);
+
 	if (!IS_ERR(pwrseq->ext_clk) && pwrseq->clk_enabled) {
 		clk_disable_unprepare(pwrseq->ext_clk);
 		pwrseq->clk_enabled = false;
@@ -119,6 +124,8 @@ static int mmc_pwrseq_simple_probe(struct platform_device *pdev)
 
 	device_property_read_u32(dev, "post-power-on-delay-ms",
 				 &pwrseq->post_power_on_delay_ms);
+	device_property_read_u32(dev, "power-off-delay-us",
+				 &pwrseq->power_off_delay_us);
 
 	pwrseq->pwrseq.dev = dev;
 	pwrseq->pwrseq.ops = &mmc_pwrseq_simple_ops;
diff --git a/drivers/mmc/host/cavium-octeon.c b/drivers/mmc/host/cavium-octeon.c
index 772d0900026d..951d2cdd7888 100644
--- a/drivers/mmc/host/cavium-octeon.c
+++ b/drivers/mmc/host/cavium-octeon.c
@@ -108,7 +108,7 @@ static void octeon_mmc_release_bus(struct cvm_mmc_host *host)
 static void octeon_mmc_int_enable(struct cvm_mmc_host *host, u64 val)
 {
 	writeq(val, host->base + MIO_EMM_INT(host));
-	if (!host->dma_active || (host->dma_active && !host->has_ciu3))
+	if (!host->has_ciu3)
 		writeq(val, host->base + MIO_EMM_INT_EN(host));
 }
 
@@ -267,7 +267,7 @@ static int octeon_mmc_probe(struct platform_device *pdev)
 	}
 
 	host->global_pwr_gpiod = devm_gpiod_get_optional(&pdev->dev,
-							 "power-gpios",
+							 "power",
 							 GPIOD_OUT_HIGH);
 	if (IS_ERR(host->global_pwr_gpiod)) {
 		dev_err(&pdev->dev, "Invalid power GPIO\n");
@@ -288,11 +288,20 @@ static int octeon_mmc_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev, "Error populating slots\n");
 			octeon_mmc_set_shared_power(host, 0);
-			return ret;
+			goto error;
 		}
 		i++;
 	}
 	return 0;
+
+error:
+	for (i = 0; i < CAVIUM_MAX_MMC; i++) {
+		if (host->slot[i])
+			cvm_mmc_of_slot_remove(host->slot[i]);
+		if (host->slot_pdev[i])
+			of_platform_device_destroy(&host->slot_pdev[i]->dev, NULL);
+	}
+	return ret;
 }
 
 static int octeon_mmc_remove(struct platform_device *pdev)
diff --git a/drivers/mmc/host/cavium-thunderx.c b/drivers/mmc/host/cavium-thunderx.c
index fe3d77267cd6..b9cc95998799 100644
--- a/drivers/mmc/host/cavium-thunderx.c
+++ b/drivers/mmc/host/cavium-thunderx.c
@@ -146,6 +146,12 @@ static int thunder_mmc_probe(struct pci_dev *pdev,
 	return 0;
 
 error:
+	for (i = 0; i < CAVIUM_MAX_MMC; i++) {
+		if (host->slot[i])
+			cvm_mmc_of_slot_remove(host->slot[i]);
+		if (host->slot_pdev[i])
+			of_platform_device_destroy(&host->slot_pdev[i]->dev, NULL);
+	}
 	clk_disable_unprepare(host->clk);
 	return ret;
 }
diff --git a/drivers/mmc/host/cavium.c b/drivers/mmc/host/cavium.c
index 58b51ba6aabd..b8aaf0fdb77c 100644
--- a/drivers/mmc/host/cavium.c
+++ b/drivers/mmc/host/cavium.c
@@ -839,14 +839,14 @@ static void cvm_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		cvm_mmc_reset_bus(slot);
 		if (host->global_pwr_gpiod)
 			host->set_shared_power(host, 0);
-		else
+		else if (!IS_ERR(mmc->supply.vmmc))
 			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
 		break;
 
 	case MMC_POWER_UP:
 		if (host->global_pwr_gpiod)
 			host->set_shared_power(host, 1);
-		else
+		else if (!IS_ERR(mmc->supply.vmmc))
 			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd);
 		break;
 	}
@@ -968,20 +968,15 @@ static int cvm_mmc_of_parse(struct device *dev, struct cvm_mmc_slot *slot)
 		return -EINVAL;
 	}
 
-	mmc->supply.vmmc = devm_regulator_get_optional(dev, "vmmc");
-	if (IS_ERR(mmc->supply.vmmc)) {
-		if (PTR_ERR(mmc->supply.vmmc) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-		/*
-		 * Legacy Octeon firmware has no regulator entry, fall-back to
-		 * a hard-coded voltage to get a sane OCR.
-		 */
+	ret = mmc_regulator_get_supply(mmc);
+	if (ret == -EPROBE_DEFER)
+		return ret;
+	/*
+	 * Legacy Octeon firmware has no regulator entry, fall-back to
+	 * a hard-coded voltage to get a sane OCR.
+	 */
+	if (IS_ERR(mmc->supply.vmmc))
 		mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
-	} else {
-		ret = mmc_regulator_get_ocrmask(mmc->supply.vmmc);
-		if (ret > 0)
-			mmc->ocr_avail = ret;
-	}
 
 	/* Common MMC bindings */
 	ret = mmc_of_parse(mmc);
diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c
index 3275d4995812..61666d269771 100644
--- a/drivers/mmc/host/sdhci-iproc.c
+++ b/drivers/mmc/host/sdhci-iproc.c
@@ -187,7 +187,8 @@ static const struct sdhci_iproc_data iproc_cygnus_data = {
 };
 
 static const struct sdhci_pltfm_data sdhci_iproc_pltfm_data = {
-	.quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK,
+	.quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
+		  SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
 	.quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN,
 	.ops = &sdhci_iproc_ops,
 };
diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c
index 6356781f1cca..f7e26b031e76 100644
--- a/drivers/mmc/host/sdhci-xenon-phy.c
+++ b/drivers/mmc/host/sdhci-xenon-phy.c
@@ -787,14 +787,6 @@ int xenon_phy_adj(struct sdhci_host *host, struct mmc_ios *ios)
 	return ret;
 }
 
-void xenon_clean_phy(struct sdhci_host *host)
-{
-	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
-
-	kfree(priv->phy_params);
-}
-
 static int xenon_add_phy(struct device_node *np, struct sdhci_host *host,
 			 const char *phy_name)
 {
@@ -819,11 +811,7 @@ static int xenon_add_phy(struct device_node *np, struct sdhci_host *host,
 	if (ret)
 		return ret;
 
-	ret = xenon_emmc_phy_parse_param_dt(host, np, priv->phy_params);
-	if (ret)
-		xenon_clean_phy(host);
-
-	return ret;
+	return xenon_emmc_phy_parse_param_dt(host, np, priv->phy_params);
 }
 
 int xenon_phy_parse_dt(struct device_node *np, struct sdhci_host *host)
diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c
index 67246655315b..bc1781bb070b 100644
--- a/drivers/mmc/host/sdhci-xenon.c
+++ b/drivers/mmc/host/sdhci-xenon.c
@@ -486,7 +486,7 @@ static int xenon_probe(struct platform_device *pdev)
 
 	err = xenon_sdhc_prepare(host);
 	if (err)
-		goto clean_phy_param;
+		goto err_clk;
 
 	err = sdhci_add_host(host);
 	if (err)
@@ -496,8 +496,6 @@ static int xenon_probe(struct platform_device *pdev)
 
 remove_sdhc:
 	xenon_sdhc_unprepare(host);
-clean_phy_param:
-	xenon_clean_phy(host);
 err_clk:
 	clk_disable_unprepare(pltfm_host->clk);
 free_pltfm:
@@ -510,8 +508,6 @@ static int xenon_remove(struct platform_device *pdev)
 	struct sdhci_host *host = platform_get_drvdata(pdev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 
-	xenon_clean_phy(host);
-
 	sdhci_remove_host(host, 0);
 
 	xenon_sdhc_unprepare(host);
diff --git a/drivers/mmc/host/sdhci-xenon.h b/drivers/mmc/host/sdhci-xenon.h
index 6e6523ea01ce..73debb42dc2f 100644
--- a/drivers/mmc/host/sdhci-xenon.h
+++ b/drivers/mmc/host/sdhci-xenon.h
@@ -93,7 +93,6 @@ struct xenon_priv {
 };
 
 int xenon_phy_adj(struct sdhci_host *host, struct mmc_ios *ios);
-void xenon_clean_phy(struct sdhci_host *host);
 int xenon_phy_parse_dt(struct device_node *np,
 		       struct sdhci_host *host);
 void xenon_soc_pad_ctrl(struct sdhci_host *host,
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 73313318399c..2359478b977f 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2612,11 +2612,13 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		unsigned long trans_start = dev_trans_start(slave->dev);
 
+		slave->new_link = BOND_LINK_NOCHANGE;
+
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, trans_start, 1) &&
 			    bond_time_in_interval(bond, slave->last_rx, 1)) {
 
-				slave->link  = BOND_LINK_UP;
+				slave->new_link = BOND_LINK_UP;
 				slave_state_changed = 1;
 
 				/* primary_slave has no meaning in round-robin
@@ -2643,7 +2645,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			if (!bond_time_in_interval(bond, trans_start, 2) ||
 			    !bond_time_in_interval(bond, slave->last_rx, 2)) {
 
-				slave->link  = BOND_LINK_DOWN;
+				slave->new_link = BOND_LINK_DOWN;
 				slave_state_changed = 1;
 
 				if (slave->link_failure_count < UINT_MAX)
@@ -2674,6 +2676,11 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 		if (!rtnl_trylock())
 			goto re_arm;
 
+		bond_for_each_slave(bond, slave, iter) {
+			if (slave->new_link != BOND_LINK_NOCHANGE)
+				slave->link = slave->new_link;
+		}
+
 		if (slave_state_changed) {
 			bond_slave_state_change(bond);
 			if (BOND_MODE(bond) == BOND_MODE_XOR)
diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c
index 2f0ee3d7ceb1..05d9d3e2e92e 100644
--- a/drivers/net/ethernet/8390/ax88796.c
+++ b/drivers/net/ethernet/8390/ax88796.c
@@ -754,13 +754,13 @@ static int ax_init_dev(struct net_device *dev)
 
 	ret = ax_mii_init(dev);
 	if (ret)
-		goto out_irq;
+		goto err_out;
 
 	ax_NS8390_init(dev, 0);
 
 	ret = register_netdev(dev);
 	if (ret)
-		goto out_irq;
+		goto err_out;
 
 	netdev_info(dev, "%dbit, irq %d, %lx, MAC: %pM\n",
 		    ei_local->word16 ? 16 : 8, dev->irq, dev->base_addr,
@@ -768,9 +768,6 @@ static int ax_init_dev(struct net_device *dev)
 
 	return 0;
 
- out_irq:
-	/* cleanup irq */
-	free_irq(dev->irq, dev);
  err_out:
 	return ret;
 }
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 800055113583..319eee36649b 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5089,9 +5089,11 @@ static netdev_features_t be_features_check(struct sk_buff *skb,
 	struct be_adapter *adapter = netdev_priv(dev);
 	u8 l4_hdr = 0;
 
-	/* The code below restricts offload features for some tunneled packets.
+	/* The code below restricts offload features for some tunneled and
+	 * Q-in-Q packets.
 	 * Offload features for normal (non tunnel) packets are unchanged.
 	 */
+	features = vlan_features_check(skb, features);
 	if (!skb->encapsulation ||
 	    !(adapter->flags & BE_FLAGS_VXLAN_OFFLOADS))
 		return features;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 56a563f90b0b..f7c8649fd28f 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3192,7 +3192,7 @@ static int fec_reset_phy(struct platform_device *pdev)
 {
 	int err, phy_reset;
 	bool active_high = false;
-	int msec = 1;
+	int msec = 1, phy_post_delay = 0;
 	struct device_node *np = pdev->dev.of_node;
 
 	if (!np)
@@ -3209,6 +3209,11 @@ static int fec_reset_phy(struct platform_device *pdev)
 	else if (!gpio_is_valid(phy_reset))
 		return 0;
 
+	err = of_property_read_u32(np, "phy-reset-post-delay", &phy_post_delay);
+	/* valid reset duration should be less than 1s */
+	if (!err && phy_post_delay > 1000)
+		return -EINVAL;
+
 	active_high = of_property_read_bool(np, "phy-reset-active-high");
 
 	err = devm_gpio_request_one(&pdev->dev, phy_reset,
@@ -3226,6 +3231,15 @@ static int fec_reset_phy(struct platform_device *pdev)
 
 	gpio_set_value_cansleep(phy_reset, !active_high);
 
+	if (!phy_post_delay)
+		return 0;
+
+	if (phy_post_delay > 20)
+		msleep(phy_post_delay);
+	else
+		usleep_range(phy_post_delay * 1000,
+			     phy_post_delay * 1000 + 1000);
+
 	return 0;
 }
 #else /* CONFIG_OF */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 5bdaf3d545b2..10d282841f5b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -774,7 +774,7 @@ static void cb_timeout_handler(struct work_struct *work)
 	mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 		       mlx5_command_str(msg_to_opcode(ent->in)),
 		       msg_to_opcode(ent->in));
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 }
 
 static void cmd_work_handler(struct work_struct *work)
@@ -804,6 +804,7 @@ static void cmd_work_handler(struct work_struct *work)
 	}
 
 	cmd->ent_arr[ent->idx] = ent;
+	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
@@ -825,6 +826,20 @@ static void cmd_work_handler(struct work_struct *work)
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
 
+	/* Skip sending command to fw if internal error */
+	if (pci_channel_offline(dev->pdev) ||
+	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+		u8 status = 0;
+		u32 drv_synd;
+
+		ent->ret = mlx5_internal_err_ret_value(dev, msg_to_opcode(ent->in), &drv_synd, &status);
+		MLX5_SET(mbox_out, ent->out, status, status);
+		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
+
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		return;
+	}
+
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
@@ -835,7 +850,7 @@ static void cmd_work_handler(struct work_struct *work)
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT));
 	}
 }
 
@@ -879,7 +894,7 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		wait_for_completion(&ent->done);
 	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
 		ent->ret = -ETIMEDOUT;
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 	}
 
 	err = ent->ret;
@@ -1375,7 +1390,7 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
 	}
 }
 
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
+void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	struct mlx5_cmd_work_ent *ent;
@@ -1395,6 +1410,19 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 			struct semaphore *sem;
 
 			ent = cmd->ent_arr[i];
+
+			/* if we already completed the command, ignore it */
+			if (!test_and_clear_bit(MLX5_CMD_ENT_STATE_PENDING_COMP,
+						&ent->state)) {
+				/* only real completion can free the cmd slot */
+				if (!forced) {
+					mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n",
+						      ent->idx);
+					free_ent(cmd, ent->idx);
+				}
+				continue;
+			}
+
 			if (ent->callback)
 				cancel_delayed_work(&ent->cb_timeout_work);
 			if (ent->page_queue)
@@ -1417,7 +1445,10 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 				mlx5_core_dbg(dev, "command completed. ret 0x%x, delivery status %s(0x%x)\n",
 					      ent->ret, deliv_status_to_str(ent->status), ent->status);
 			}
-			free_ent(cmd, ent->idx);
+
+			/* only real completion will free the entry slot */
+			if (!forced)
+				free_ent(cmd, ent->idx);
 
 			if (ent->callback) {
 				ds = ent->ts2 - ent->ts1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 7b1566f0ae58..66b5fec15313 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1041,6 +1041,8 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 #define MLX5_IB_GRH_BYTES       40
 #define MLX5_IPOIB_ENCAP_LEN    4
 #define MLX5_GID_SIZE           16
+#define MLX5_IPOIB_PSEUDO_LEN   20
+#define MLX5_IPOIB_HARD_LEN     (MLX5_IPOIB_PSEUDO_LEN + MLX5_IPOIB_ENCAP_LEN)
 
 static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 					 struct mlx5_cqe64 *cqe,
@@ -1048,6 +1050,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 					 struct sk_buff *skb)
 {
 	struct net_device *netdev = rq->netdev;
+	char *pseudo_header;
 	u8 *dgid;
 	u8 g;
 
@@ -1076,8 +1079,11 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	if (likely(netdev->features & NETIF_F_RXHASH))
 		mlx5e_skb_set_hash(cqe, skb);
 
+	/* 20 bytes of ipoib header and 4 for encap existing */
+	pseudo_header = skb_push(skb, MLX5_IPOIB_PSEUDO_LEN);
+	memset(pseudo_header, 0, MLX5_IPOIB_PSEUDO_LEN);
 	skb_reset_mac_header(skb);
-	skb_pull(skb, MLX5_IPOIB_ENCAP_LEN);
+	skb_pull(skb, MLX5_IPOIB_HARD_LEN);
 
 	skb->dev = netdev;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b46c2f22b1b3..d2f90ba2dbc4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -43,6 +43,7 @@
 #include <net/tc_act/tc_vlan.h>
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_pedit.h>
+#include <net/tc_act/tc_csum.h>
 #include <net/vxlan.h>
 #include <net/arp.h>
 #include "en.h"
@@ -384,7 +385,7 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 		if (e->flags & MLX5_ENCAP_ENTRY_VALID)
 			mlx5_encap_dealloc(priv->mdev, e->encap_id);
 
-		hlist_del_rcu(&e->encap_hlist);
+		hash_del_rcu(&e->encap_hlist);
 		kfree(e->encap_header);
 		kfree(e);
 	}
@@ -925,11 +926,11 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 				struct mlx5e_tc_flow_parse_attr *parse_attr)
 {
 	struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
-	int i, action_size, nactions, max_actions, first, last;
+	int i, action_size, nactions, max_actions, first, last, first_z;
 	void *s_masks_p, *a_masks_p, *vals_p;
-	u32 s_mask, a_mask, val;
 	struct mlx5_fields *f;
 	u8 cmd, field_bsize;
+	u32 s_mask, a_mask;
 	unsigned long mask;
 	void *action;
 
@@ -946,7 +947,8 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 	for (i = 0; i < ARRAY_SIZE(fields); i++) {
 		f = &fields[i];
 		/* avoid seeing bits set from previous iterations */
-		s_mask = a_mask = mask = val = 0;
+		s_mask = 0;
+		a_mask = 0;
 
 		s_masks_p = (void *)set_masks + f->offset;
 		a_masks_p = (void *)add_masks + f->offset;
@@ -981,12 +983,12 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 			memset(a_masks_p, 0, f->size);
 		}
 
-		memcpy(&val, vals_p, f->size);
-
 		field_bsize = f->size * BITS_PER_BYTE;
+
+		first_z = find_first_zero_bit(&mask, field_bsize);
 		first = find_first_bit(&mask, field_bsize);
 		last  = find_last_bit(&mask, field_bsize);
-		if (first > 0 || last != (field_bsize - 1)) {
+		if (first > 0 || last != (field_bsize - 1) || first_z < last) {
 			printk(KERN_WARNING "mlx5: partial rewrite (mask %lx) is currently not offloaded\n",
 			       mask);
 			return -EOPNOTSUPP;
@@ -1002,11 +1004,11 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 		}
 
 		if (field_bsize == 32)
-			MLX5_SET(set_action_in, action, data, ntohl(val));
+			MLX5_SET(set_action_in, action, data, ntohl(*(__be32 *)vals_p));
 		else if (field_bsize == 16)
-			MLX5_SET(set_action_in, action, data, ntohs(val));
+			MLX5_SET(set_action_in, action, data, ntohs(*(__be16 *)vals_p));
 		else if (field_bsize == 8)
-			MLX5_SET(set_action_in, action, data, val);
+			MLX5_SET(set_action_in, action, data, *(u8 *)vals_p);
 
 		action += action_size;
 		nactions++;
@@ -1109,6 +1111,28 @@ out_err:
 	return err;
 }
 
+static bool csum_offload_supported(struct mlx5e_priv *priv, u32 action, u32 update_flags)
+{
+	u32 prot_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR | TCA_CSUM_UPDATE_FLAG_TCP |
+			 TCA_CSUM_UPDATE_FLAG_UDP;
+
+	/*  The HW recalcs checksums only if re-writing headers */
+	if (!(action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)) {
+		netdev_warn(priv->netdev,
+			    "TC csum action is only offloaded with pedit\n");
+		return false;
+	}
+
+	if (update_flags & ~prot_flags) {
+		netdev_warn(priv->netdev,
+			    "can't offload TC csum action for some header/s - flags %#x\n",
+			    update_flags);
+		return false;
+	}
+
+	return true;
+}
+
 static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow)
@@ -1149,6 +1173,14 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			continue;
 		}
 
+		if (is_tcf_csum(a)) {
+			if (csum_offload_supported(priv, attr->action,
+						   tcf_csum_update_flags(a)))
+				continue;
+
+			return -EOPNOTSUPP;
+		}
+
 		if (is_tcf_skbedit_mark(a)) {
 			u32 mark = tcf_skbedit_mark(a);
 
@@ -1651,6 +1683,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			continue;
 		}
 
+		if (is_tcf_csum(a)) {
+			if (csum_offload_supported(priv, attr->action,
+						   tcf_csum_update_flags(a)))
+				continue;
+
+			return -EOPNOTSUPP;
+		}
+
 		if (is_tcf_mirred_egress_redirect(a)) {
 			int ifindex = tcf_mirred_ifindex(a);
 			struct net_device *out_dev, *encap_dev = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 01d2cd7e4746..0ed8e90ba54f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -425,7 +425,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 			break;
 
 		case MLX5_EVENT_TYPE_CMD:
-			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector));
+			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
 			break;
 
 		case MLX5_EVENT_TYPE_PORT_CHANGE:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index c3cedb6cec3f..80b23333de7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -90,7 +90,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev)
 	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
 
 	mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
-	mlx5_cmd_comp_handler(dev, vector);
+	mlx5_cmd_comp_handler(dev, vector, true);
 	return;
 
 no_trig:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ad0202cef203..361cd112bb5b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -613,7 +613,6 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	struct mlx5_priv *priv  = &mdev->priv;
 	struct msix_entry *msix = priv->msix_arr;
 	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
-	int err;
 
 	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
 		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
@@ -623,18 +622,12 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
 			priv->irq_info[i].mask);
 
-	err = irq_set_affinity_hint(irq, priv->irq_info[i].mask);
-	if (err) {
-		mlx5_core_warn(mdev, "irq_set_affinity_hint failed,irq 0x%.4x",
-			       irq);
-		goto err_clear_mask;
-	}
+#ifdef CONFIG_SMP
+	if (irq_set_affinity_hint(irq, priv->irq_info[i].mask))
+		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
+#endif
 
 	return 0;
-
-err_clear_mask:
-	free_cpumask_var(priv->irq_info[i].mask);
-	return err;
 }
 
 static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index dec5d563ab19..959fd12d2e67 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1293,7 +1293,7 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	if (nla_put_u32(skb, IFLA_GENEVE_ID, vni))
 		goto nla_put_failure;
 
-	if (ip_tunnel_info_af(info) == AF_INET) {
+	if (rtnl_dereference(geneve->sock4)) {
 		if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE,
 				    info->key.u.ipv4.dst))
 			goto nla_put_failure;
@@ -1302,8 +1302,10 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			       !!(info->key.tun_flags & TUNNEL_CSUM)))
 			goto nla_put_failure;
 
+	}
+
 #if IS_ENABLED(CONFIG_IPV6)
-	} else {
+	if (rtnl_dereference(geneve->sock6)) {
 		if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6,
 				     &info->key.u.ipv6.dst))
 			goto nla_put_failure;
@@ -1315,8 +1317,8 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
 			       !geneve->use_udp6_rx_checksums))
 			goto nla_put_failure;
-#endif
 	}
+#endif
 
 	if (nla_put_u8(skb, IFLA_GENEVE_TTL, info->key.ttl) ||
 	    nla_put_u8(skb, IFLA_GENEVE_TOS, info->key.tos) ||
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 4fea1b3dfbb4..7b652bb7ebe4 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -873,7 +873,7 @@ static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[])
 
 	/* Check if there's an existing gtpX device to configure */
 	dev = dev_get_by_index_rcu(net, nla_get_u32(nla[GTPA_LINK]));
-	if (dev->netdev_ops == &gtp_netdev_ops)
+	if (dev && dev->netdev_ops == &gtp_netdev_ops)
 		gtp = netdev_priv(dev);
 
 	put_net(net);
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 60ffc9da6a28..c360dd6ead22 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -108,7 +108,7 @@ config MDIO_MOXART
 config MDIO_OCTEON
 	tristate "Octeon and some ThunderX SOCs MDIO buses"
 	depends on 64BIT
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && OF_MDIO
 	select MDIO_CAVIUM
 	help
 	  This module provides a driver for the Octeon and ThunderX MDIO
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 2bd83920f565..1a72bebc588a 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -278,35 +278,6 @@ static int marvell_config_aneg(struct phy_device *phydev)
 {
 	int err;
 
-	/* The Marvell PHY has an errata which requires
-	 * that certain registers get written in order
-	 * to restart autonegotiation
-	 */
-	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
-
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1d, 0x1f);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0x200c);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1d, 0x5);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0x100);
-	if (err < 0)
-		return err;
-
 	err = marvell_set_polarity(phydev, phydev->mdix_ctrl);
 	if (err < 0)
 		return err;
@@ -339,6 +310,42 @@ static int marvell_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int m88e1101_config_aneg(struct phy_device *phydev)
+{
+	int err;
+
+	/* This Marvell PHY has an errata which requires
+	 * that certain registers get written in order
+	 * to restart autonegotiation
+	 */
+	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
+
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1d, 0x1f);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0x200c);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1d, 0x5);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0x100);
+	if (err < 0)
+		return err;
+
+	return marvell_config_aneg(phydev);
+}
+
 static int m88e1111_config_aneg(struct phy_device *phydev)
 {
 	int err;
@@ -1975,7 +1982,7 @@ static struct phy_driver marvell_drivers[] = {
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &marvell_config_init,
-		.config_aneg = &marvell_config_aneg,
+		.config_aneg = &m88e1101_config_aneg,
 		.read_status = &genphy_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
 		.config_intr = &marvell_config_intr,
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index f3ae88fdf332..8ab281b478f2 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -310,6 +310,26 @@ skip:
 		return -ENODEV;
 	}
 
+	return 0;
+
+bad_desc:
+	dev_info(&dev->udev->dev, "bad CDC descriptors\n");
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(usbnet_generic_cdc_bind);
+
+
+/* like usbnet_generic_cdc_bind() but handles filter initialization
+ * correctly
+ */
+int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+	int rv;
+
+	rv = usbnet_generic_cdc_bind(dev, intf);
+	if (rv < 0)
+		goto bail_out;
+
 	/* Some devices don't initialise properly. In particular
 	 * the packet filter is not reset. There are devices that
 	 * don't do reset all the way. So the packet filter should
@@ -317,13 +337,10 @@ skip:
 	 */
 	usbnet_cdc_update_filter(dev);
 
-	return 0;
-
-bad_desc:
-	dev_info(&dev->udev->dev, "bad CDC descriptors\n");
-	return -ENODEV;
+bail_out:
+	return rv;
 }
-EXPORT_SYMBOL_GPL(usbnet_generic_cdc_bind);
+EXPORT_SYMBOL_GPL(usbnet_ether_cdc_bind);
 
 void usbnet_cdc_unbind(struct usbnet *dev, struct usb_interface *intf)
 {
@@ -417,7 +434,7 @@ int usbnet_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
 	BUILD_BUG_ON((sizeof(((struct usbnet *)0)->data)
 			< sizeof(struct cdc_state)));
 
-	status = usbnet_generic_cdc_bind(dev, intf);
+	status = usbnet_ether_cdc_bind(dev, intf);
 	if (status < 0)
 		return status;
 
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 9320d96a1632..3e9246cc49c3 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1989,6 +1989,7 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_poll_controller = virtnet_netpoll,
 #endif
 	.ndo_xdp		= virtnet_xdp,
+	.ndo_features_check	= passthru_features_check,
 };
 
 static void virtnet_config_changed_work(struct work_struct *work)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d5e0906262ea..a60926410438 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -925,6 +925,29 @@ static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
+static void nvme_prep_integrity(struct gendisk *disk, struct nvme_id_ns *id,
+		u16 bs)
+{
+	struct nvme_ns *ns = disk->private_data;
+	u16 old_ms = ns->ms;
+	u8 pi_type = 0;
+
+	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
+	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
+
+	/* PI implementation requires metadata equal t10 pi tuple size */
+	if (ns->ms == sizeof(struct t10_pi_tuple))
+		pi_type = id->dps & NVME_NS_DPS_PI_MASK;
+
+	if (blk_get_integrity(disk) &&
+	    (ns->pi_type != pi_type || ns->ms != old_ms ||
+	     bs != queue_logical_block_size(disk->queue) ||
+	     (ns->ms && ns->ext)))
+		blk_integrity_unregister(disk);
+
+	ns->pi_type = pi_type;
+}
+
 static void nvme_init_integrity(struct nvme_ns *ns)
 {
 	struct blk_integrity integrity;
@@ -951,6 +974,10 @@ static void nvme_init_integrity(struct nvme_ns *ns)
 	blk_queue_max_integrity_segments(ns->queue, 1);
 }
 #else
+static void nvme_prep_integrity(struct gendisk *disk, struct nvme_id_ns *id,
+		u16 bs)
+{
+}
 static void nvme_init_integrity(struct nvme_ns *ns)
 {
 }
@@ -997,37 +1024,22 @@ static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
 static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 {
 	struct nvme_ns *ns = disk->private_data;
-	u8 lbaf, pi_type;
-	u16 old_ms;
-	unsigned short bs;
-
-	old_ms = ns->ms;
-	lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
-	ns->lba_shift = id->lbaf[lbaf].ds;
-	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
-	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
+	u16 bs;
 
 	/*
 	 * If identify namespace failed, use default 512 byte block size so
 	 * block layer can use before failing read/write for 0 capacity.
 	 */
+	ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds;
 	if (ns->lba_shift == 0)
 		ns->lba_shift = 9;
 	bs = 1 << ns->lba_shift;
-	/* XXX: PI implementation requires metadata equal t10 pi tuple size */
-	pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
-					id->dps & NVME_NS_DPS_PI_MASK : 0;
 
 	blk_mq_freeze_queue(disk->queue);
-	if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
-				ns->ms != old_ms ||
-				bs != queue_logical_block_size(disk->queue) ||
-				(ns->ms && ns->ext)))
-		blk_integrity_unregister(disk);
 
-	ns->pi_type = pi_type;
+	if (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
+		nvme_prep_integrity(disk, id, bs);
 	blk_queue_logical_block_size(ns->queue, bs);
-
 	if (ns->ms && !blk_get_integrity(disk) && !ns->ext)
 		nvme_init_integrity(ns);
 	if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
@@ -1605,7 +1617,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	}
 	memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd));
 
-	if (ctrl->ops->is_fabrics) {
+	if (ctrl->ops->flags & NVME_F_FABRICS) {
 		ctrl->icdoff = le16_to_cpu(id->icdoff);
 		ctrl->ioccsz = le32_to_cpu(id->ioccsz);
 		ctrl->iorcsz = le32_to_cpu(id->iorcsz);
@@ -2098,7 +2110,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		if (ns->ndev)
 			nvme_nvm_unregister_sysfs(ns);
 		del_gendisk(ns->disk);
-		blk_mq_abort_requeue_list(ns->queue);
 		blk_cleanup_queue(ns->queue);
 	}
 
@@ -2436,8 +2447,16 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 			continue;
 		revalidate_disk(ns->disk);
 		blk_set_queue_dying(ns->queue);
-		blk_mq_abort_requeue_list(ns->queue);
-		blk_mq_start_stopped_hw_queues(ns->queue, true);
+
+		/*
+		 * Forcibly start all queues to avoid having stuck requests.
+		 * Note that we must ensure the queues are not stopped
+		 * when the final removal happens.
+		 */
+		blk_mq_start_hw_queues(ns->queue);
+
+		/* draining requests in requeue list */
+		blk_mq_kick_requeue_list(ns->queue);
 	}
 	mutex_unlock(&ctrl->namespaces_mutex);
 }
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index dca7165fabcf..5b14cbefb724 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -45,8 +45,6 @@ enum nvme_fc_queue_flags {
 
 #define NVMEFC_QUEUE_DELAY	3		/* ms units */
 
-#define NVME_FC_MAX_CONNECT_ATTEMPTS	1
-
 struct nvme_fc_queue {
 	struct nvme_fc_ctrl	*ctrl;
 	struct device		*dev;
@@ -165,8 +163,6 @@ struct nvme_fc_ctrl {
 	struct work_struct	delete_work;
 	struct work_struct	reset_work;
 	struct delayed_work	connect_work;
-	int			reconnect_delay;
-	int			connect_attempts;
 
 	struct kref		ref;
 	u32			flags;
@@ -1376,9 +1372,9 @@ done:
 	complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op);
 	if (!complete_rq) {
 		if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) {
-			status = cpu_to_le16(NVME_SC_ABORT_REQ);
+			status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
 			if (blk_queue_dying(rq->q))
-				status |= cpu_to_le16(NVME_SC_DNR);
+				status |= cpu_to_le16(NVME_SC_DNR << 1);
 		}
 		nvme_end_request(rq, status, result);
 	} else
@@ -1751,7 +1747,7 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	dev_warn(ctrl->ctrl.device,
 		"NVME-FC{%d}: transport association error detected: %s\n",
 		ctrl->cnum, errmsg);
-	dev_info(ctrl->ctrl.device,
+	dev_warn(ctrl->ctrl.device,
 		"NVME-FC{%d}: resetting controller\n", ctrl->cnum);
 
 	/* stop the queues on error, cleanup is in reset thread */
@@ -2195,9 +2191,6 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
 	if (!opts->nr_io_queues)
 		return 0;
 
-	dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
-			opts->nr_io_queues);
-
 	nvme_fc_init_io_queues(ctrl);
 
 	memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
@@ -2268,9 +2261,6 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl)
 	if (ctrl->queue_count == 1)
 		return 0;
 
-	dev_info(ctrl->ctrl.device, "Recreating %d I/O queues.\n",
-			opts->nr_io_queues);
-
 	nvme_fc_init_io_queues(ctrl);
 
 	ret = blk_mq_reinit_tagset(&ctrl->tag_set);
@@ -2306,7 +2296,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	int ret;
 	bool changed;
 
-	ctrl->connect_attempts++;
+	++ctrl->ctrl.opts->nr_reconnects;
 
 	/*
 	 * Create the admin queue
@@ -2403,9 +2393,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	WARN_ON_ONCE(!changed);
 
-	ctrl->connect_attempts = 0;
-
-	kref_get(&ctrl->ctrl.kref);
+	ctrl->ctrl.opts->nr_reconnects = 0;
 
 	if (ctrl->queue_count > 1) {
 		nvme_start_queues(&ctrl->ctrl);
@@ -2536,26 +2524,32 @@ nvme_fc_delete_ctrl_work(struct work_struct *work)
 
 	/*
 	 * tear down the controller
-	 * This will result in the last reference on the nvme ctrl to
-	 * expire, calling the transport nvme_fc_nvme_ctrl_freed() callback.
-	 * From there, the transport will tear down it's logical queues and
-	 * association.
+	 * After the last reference on the nvme ctrl is removed,
+	 * the transport nvme_fc_nvme_ctrl_freed() callback will be
+	 * invoked. From there, the transport will tear down it's
+	 * logical queues and association.
 	 */
 	nvme_uninit_ctrl(&ctrl->ctrl);
 
 	nvme_put_ctrl(&ctrl->ctrl);
 }
 
-static int
-__nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl)
+static bool
+__nvme_fc_schedule_delete_work(struct nvme_fc_ctrl *ctrl)
 {
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING))
-		return -EBUSY;
+		return true;
 
 	if (!queue_work(nvme_fc_wq, &ctrl->delete_work))
-		return -EBUSY;
+		return true;
 
-	return 0;
+	return false;
+}
+
+static int
+__nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl)
+{
+	return __nvme_fc_schedule_delete_work(ctrl) ? -EBUSY : 0;
 }
 
 /*
@@ -2581,6 +2575,35 @@ nvme_fc_del_nvme_ctrl(struct nvme_ctrl *nctrl)
 }
 
 static void
+nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
+{
+	/* If we are resetting/deleting then do nothing */
+	if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) {
+		WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
+			ctrl->ctrl.state == NVME_CTRL_LIVE);
+		return;
+	}
+
+	dev_info(ctrl->ctrl.device,
+		"NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
+		ctrl->cnum, status);
+
+	if (nvmf_should_reconnect(&ctrl->ctrl)) {
+		dev_info(ctrl->ctrl.device,
+			"NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
+			ctrl->cnum, ctrl->ctrl.opts->reconnect_delay);
+		queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
+				ctrl->ctrl.opts->reconnect_delay * HZ);
+	} else {
+		dev_warn(ctrl->ctrl.device,
+				"NVME-FC{%d}: Max reconnect attempts (%d) "
+				"reached. Removing controller\n",
+				ctrl->cnum, ctrl->ctrl.opts->nr_reconnects);
+		WARN_ON(__nvme_fc_schedule_delete_work(ctrl));
+	}
+}
+
+static void
 nvme_fc_reset_ctrl_work(struct work_struct *work)
 {
 	struct nvme_fc_ctrl *ctrl =
@@ -2591,34 +2614,9 @@ nvme_fc_reset_ctrl_work(struct work_struct *work)
 	nvme_fc_delete_association(ctrl);
 
 	ret = nvme_fc_create_association(ctrl);
-	if (ret) {
-		dev_warn(ctrl->ctrl.device,
-			"NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
-			ctrl->cnum, ret);
-		if (ctrl->connect_attempts >= NVME_FC_MAX_CONNECT_ATTEMPTS) {
-			dev_warn(ctrl->ctrl.device,
-				"NVME-FC{%d}: Max reconnect attempts (%d) "
-				"reached. Removing controller\n",
-				ctrl->cnum, ctrl->connect_attempts);
-
-			if (!nvme_change_ctrl_state(&ctrl->ctrl,
-				NVME_CTRL_DELETING)) {
-				dev_err(ctrl->ctrl.device,
-					"NVME-FC{%d}: failed to change state "
-					"to DELETING\n", ctrl->cnum);
-				return;
-			}
-
-			WARN_ON(!queue_work(nvme_fc_wq, &ctrl->delete_work));
-			return;
-		}
-
-		dev_warn(ctrl->ctrl.device,
-			"NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
-			ctrl->cnum, ctrl->reconnect_delay);
-		queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
-				ctrl->reconnect_delay * HZ);
-	} else
+	if (ret)
+		nvme_fc_reconnect_or_delete(ctrl, ret);
+	else
 		dev_info(ctrl->ctrl.device,
 			"NVME-FC{%d}: controller reset complete\n", ctrl->cnum);
 }
@@ -2632,7 +2630,7 @@ nvme_fc_reset_nvme_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 
-	dev_warn(ctrl->ctrl.device,
+	dev_info(ctrl->ctrl.device,
 		"NVME-FC{%d}: admin requested controller reset\n", ctrl->cnum);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
@@ -2649,7 +2647,7 @@ nvme_fc_reset_nvme_ctrl(struct nvme_ctrl *nctrl)
 static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
 	.name			= "fc",
 	.module			= THIS_MODULE,
-	.is_fabrics		= true,
+	.flags			= NVME_F_FABRICS,
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,
@@ -2671,34 +2669,9 @@ nvme_fc_connect_ctrl_work(struct work_struct *work)
 				struct nvme_fc_ctrl, connect_work);
 
 	ret = nvme_fc_create_association(ctrl);
-	if (ret) {
-		dev_warn(ctrl->ctrl.device,
-			"NVME-FC{%d}: Reconnect attempt failed (%d)\n",
-			ctrl->cnum, ret);
-		if (ctrl->connect_attempts >= NVME_FC_MAX_CONNECT_ATTEMPTS) {
-			dev_warn(ctrl->ctrl.device,
-				"NVME-FC{%d}: Max reconnect attempts (%d) "
-				"reached. Removing controller\n",
-				ctrl->cnum, ctrl->connect_attempts);
-
-			if (!nvme_change_ctrl_state(&ctrl->ctrl,
-				NVME_CTRL_DELETING)) {
-				dev_err(ctrl->ctrl.device,
-					"NVME-FC{%d}: failed to change state "
-					"to DELETING\n", ctrl->cnum);
-				return;
-			}
-
-			WARN_ON(!queue_work(nvme_fc_wq, &ctrl->delete_work));
-			return;
-		}
-
-		dev_warn(ctrl->ctrl.device,
-			"NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
-			ctrl->cnum, ctrl->reconnect_delay);
-		queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
-				ctrl->reconnect_delay * HZ);
-	} else
+	if (ret)
+		nvme_fc_reconnect_or_delete(ctrl, ret);
+	else
 		dev_info(ctrl->ctrl.device,
 			"NVME-FC{%d}: controller reconnect complete\n",
 			ctrl->cnum);
@@ -2755,7 +2728,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	INIT_WORK(&ctrl->delete_work, nvme_fc_delete_ctrl_work);
 	INIT_WORK(&ctrl->reset_work, nvme_fc_reset_ctrl_work);
 	INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work);
-	ctrl->reconnect_delay = opts->reconnect_delay;
 	spin_lock_init(&ctrl->lock);
 
 	/* io queue count */
@@ -2819,7 +2791,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 		ctrl->ctrl.opts = NULL;
 		/* initiate nvme ctrl ref counting teardown */
 		nvme_uninit_ctrl(&ctrl->ctrl);
-		nvme_put_ctrl(&ctrl->ctrl);
 
 		/* as we're past the point where we transition to the ref
 		 * counting teardown path, if we return a bad pointer here,
@@ -2835,6 +2806,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 		return ERR_PTR(ret);
 	}
 
+	kref_get(&ctrl->ctrl.kref);
+
 	dev_info(ctrl->ctrl.device,
 		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
 		ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
@@ -2971,7 +2944,7 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts)
 static struct nvmf_transport_ops nvme_fc_transport = {
 	.name		= "fc",
 	.required_opts	= NVMF_OPT_TRADDR | NVMF_OPT_HOST_TRADDR,
-	.allowed_opts	= NVMF_OPT_RECONNECT_DELAY,
+	.allowed_opts	= NVMF_OPT_RECONNECT_DELAY | NVMF_OPT_CTRL_LOSS_TMO,
 	.create_ctrl	= nvme_fc_create_ctrl,
 };
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 29c708ca9621..9d6a070d4391 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -208,7 +208,9 @@ struct nvme_ns {
 struct nvme_ctrl_ops {
 	const char *name;
 	struct module *module;
-	bool is_fabrics;
+	unsigned int flags;
+#define NVME_F_FABRICS			(1 << 0)
+#define NVME_F_METADATA_SUPPORTED	(1 << 1)
 	int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 	int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
 	int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4c2ff2bb26bc..d52701df7245 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -263,7 +263,7 @@ static void nvme_dbbuf_set(struct nvme_dev *dev)
 	c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr);
 
 	if (nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0)) {
-		dev_warn(dev->dev, "unable to set dbbuf\n");
+		dev_warn(dev->ctrl.device, "unable to set dbbuf\n");
 		/* Free memory and continue on */
 		nvme_dbbuf_dma_free(dev);
 	}
@@ -1394,11 +1394,11 @@ static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
 	result = pci_read_config_word(to_pci_dev(dev->dev), PCI_STATUS,
 				      &pci_status);
 	if (result == PCIBIOS_SUCCESSFUL)
-		dev_warn(dev->dev,
+		dev_warn(dev->ctrl.device,
 			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS=0x%hx\n",
 			 csts, pci_status);
 	else
-		dev_warn(dev->dev,
+		dev_warn(dev->ctrl.device,
 			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n",
 			 csts, result);
 }
@@ -1740,8 +1740,8 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 	 */
 	if (pdev->vendor == PCI_VENDOR_ID_APPLE && pdev->device == 0x2001) {
 		dev->q_depth = 2;
-		dev_warn(dev->dev, "detected Apple NVMe controller, set "
-			"queue depth=%u to work around controller resets\n",
+		dev_warn(dev->ctrl.device, "detected Apple NVMe controller, "
+			"set queue depth=%u to work around controller resets\n",
 			dev->q_depth);
 	}
 
@@ -1759,7 +1759,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 		if (dev->cmbsz) {
 			if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
 						    &dev_attr_cmb.attr, NULL))
-				dev_warn(dev->dev,
+				dev_warn(dev->ctrl.device,
 					 "failed to add sysfs attribute for CMB\n");
 		}
 	}
@@ -2047,6 +2047,7 @@ static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.name			= "pcie",
 	.module			= THIS_MODULE,
+	.flags			= NVME_F_METADATA_SUPPORTED,
 	.reg_read32		= nvme_pci_reg_read32,
 	.reg_write32		= nvme_pci_reg_write32,
 	.reg_read64		= nvme_pci_reg_read64,
@@ -2293,6 +2294,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_VDEVICE(INTEL, 0x0a54),
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
+	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
 	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index dd1c6deef82f..28bd255c144d 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1038,6 +1038,19 @@ static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
 		nvme_rdma_wr_error(cq, wc, "SEND");
 }
 
+static inline int nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue)
+{
+	int sig_limit;
+
+	/*
+	 * We signal completion every queue depth/2 and also handle the
+	 * degenerated case of a  device with queue_depth=1, where we
+	 * would need to signal every message.
+	 */
+	sig_limit = max(queue->queue_size / 2, 1);
+	return (++queue->sig_count % sig_limit) == 0;
+}
+
 static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
 		struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge,
 		struct ib_send_wr *first, bool flush)
@@ -1065,9 +1078,6 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
 	 * Would have been way to obvious to handle this in hardware or
 	 * at least the RDMA stack..
 	 *
-	 * This messy and racy code sniplet is copy and pasted from the iSER
-	 * initiator, and the magic '32' comes from there as well.
-	 *
 	 * Always signal the flushes. The magic request used for the flush
 	 * sequencer is not allocated in our driver's tagset and it's
 	 * triggered to be freed by blk_cleanup_queue(). So we need to
@@ -1075,7 +1085,7 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
 	 * embedded in request's payload, is not freed when __ib_process_cq()
 	 * calls wr_cqe->done().
 	 */
-	if ((++queue->sig_count % 32) == 0 || flush)
+	if (nvme_rdma_queue_sig_limit(queue) || flush)
 		wr.send_flags |= IB_SEND_SIGNALED;
 
 	if (first)
@@ -1782,7 +1792,7 @@ static int nvme_rdma_reset_ctrl(struct nvme_ctrl *nctrl)
 static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
 	.name			= "rdma",
 	.module			= THIS_MODULE,
-	.is_fabrics		= true,
+	.flags			= NVME_F_FABRICS,
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index feb497134aee..e503cfff0337 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -558,7 +558,7 @@ static int nvme_loop_reset_ctrl(struct nvme_ctrl *nctrl)
 static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
 	.name			= "loop",
 	.module			= THIS_MODULE,
-	.is_fabrics		= true,
+	.flags			= NVME_F_FABRICS,
 	.reg_read32		= nvmf_reg_read32,
 	.reg_read64		= nvmf_reg_read64,
 	.reg_write32		= nvmf_reg_write32,
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 71fecc2debfc..703a42118ffc 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -523,7 +523,7 @@ static int __init of_platform_default_populate_init(void)
 arch_initcall_sync(of_platform_default_populate_init);
 #endif
 
-static int of_platform_device_destroy(struct device *dev, void *data)
+int of_platform_device_destroy(struct device *dev, void *data)
 {
 	/* Do not touch devices not populated from the device tree */
 	if (!dev->of_node || !of_node_check_flag(dev->of_node, OF_POPULATED))
@@ -544,6 +544,7 @@ static int of_platform_device_destroy(struct device *dev, void *data)
 	of_node_clear_flag(dev->of_node, OF_POPULATED_BUS);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(of_platform_device_destroy);
 
 /**
  * of_platform_depopulate() - Remove devices populated from device tree
diff --git a/drivers/pci/dwc/pci-imx6.c b/drivers/pci/dwc/pci-imx6.c
index a98cba55c7f0..19a289b8cc94 100644
--- a/drivers/pci/dwc/pci-imx6.c
+++ b/drivers/pci/dwc/pci-imx6.c
@@ -252,7 +252,34 @@ static void imx6_pcie_reset_phy(struct imx6_pcie *imx6_pcie)
 static int imx6q_pcie_abort_handler(unsigned long addr,
 		unsigned int fsr, struct pt_regs *regs)
 {
-	return 0;
+	unsigned long pc = instruction_pointer(regs);
+	unsigned long instr = *(unsigned long *)pc;
+	int reg = (instr >> 12) & 15;
+
+	/*
+	 * If the instruction being executed was a read,
+	 * make it look like it read all-ones.
+	 */
+	if ((instr & 0x0c100000) == 0x04100000) {
+		unsigned long val;
+
+		if (instr & 0x00400000)
+			val = 255;
+		else
+			val = -1;
+
+		regs->uregs[reg] = val;
+		regs->ARM_pc += 4;
+		return 0;
+	}
+
+	if ((instr & 0x0e100090) == 0x00100090) {
+		regs->uregs[reg] = -1;
+		regs->ARM_pc += 4;
+		return 0;
+	}
+
+	return 1;
 }
 
 static void imx6_pcie_assert_core_reset(struct imx6_pcie *imx6_pcie)
@@ -819,8 +846,8 @@ static int __init imx6_pcie_init(void)
 	 * we can install the handler here without risking it
 	 * accessing some uninitialized driver state.
 	 */
-	hook_fault_code(16 + 6, imx6q_pcie_abort_handler, SIGBUS, 0,
-			"imprecise external abort");
+	hook_fault_code(8, imx6q_pcie_abort_handler, SIGBUS, 0,
+			"external abort on non-linefetch");
 
 	return platform_driver_register(&imx6_pcie_driver);
 }
diff --git a/drivers/pci/endpoint/Kconfig b/drivers/pci/endpoint/Kconfig
index c23f146fb5a6..c09623ca8c3b 100644
--- a/drivers/pci/endpoint/Kconfig
+++ b/drivers/pci/endpoint/Kconfig
@@ -6,6 +6,7 @@ menu "PCI Endpoint"
 
 config PCI_ENDPOINT
 	bool "PCI Endpoint Support"
+	depends on HAS_DMA
 	help
 	   Enable this configuration option to support configurable PCI
 	   endpoint. This should be enabled if the platform has a PCI
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index b01bd5bba8e6..563901cd9c06 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2144,7 +2144,8 @@ bool pci_dev_keep_suspended(struct pci_dev *pci_dev)
 
 	if (!pm_runtime_suspended(dev)
 	    || pci_target_state(pci_dev) != pci_dev->current_state
-	    || platform_pci_need_resume(pci_dev))
+	    || platform_pci_need_resume(pci_dev)
+	    || (pci_dev->dev_flags & PCI_DEV_FLAGS_NEEDS_RESUME))
 		return false;
 
 	/*
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index cc6e085008fb..f6a63406c76e 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -1291,7 +1291,6 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev)
 	cdev = &stdev->cdev;
 	cdev_init(cdev, &switchtec_fops);
 	cdev->owner = THIS_MODULE;
-	cdev->kobj.parent = &dev->kobj;
 
 	return stdev;
 
@@ -1442,12 +1441,15 @@ static int switchtec_init_pci(struct switchtec_dev *stdev,
 	stdev->mmio_sys_info = stdev->mmio + SWITCHTEC_GAS_SYS_INFO_OFFSET;
 	stdev->mmio_flash_info = stdev->mmio + SWITCHTEC_GAS_FLASH_INFO_OFFSET;
 	stdev->mmio_ntb = stdev->mmio + SWITCHTEC_GAS_NTB_OFFSET;
-	stdev->partition = ioread8(&stdev->mmio_ntb->partition_id);
+	stdev->partition = ioread8(&stdev->mmio_sys_info->partition_id);
 	stdev->partition_count = ioread8(&stdev->mmio_ntb->partition_count);
 	stdev->mmio_part_cfg_all = stdev->mmio + SWITCHTEC_GAS_PART_CFG_OFFSET;
 	stdev->mmio_part_cfg = &stdev->mmio_part_cfg_all[stdev->partition];
 	stdev->mmio_pff_csr = stdev->mmio + SWITCHTEC_GAS_PFF_CSR_OFFSET;
 
+	if (stdev->partition_count < 1)
+		stdev->partition_count = 1;
+
 	init_pff(stdev);
 
 	pci_set_drvdata(pdev, stdev);
@@ -1479,11 +1481,7 @@ static int switchtec_pci_probe(struct pci_dev *pdev,
 		  SWITCHTEC_EVENT_EN_IRQ,
 		  &stdev->mmio_part_cfg->mrpc_comp_hdr);
 
-	rc = cdev_add(&stdev->cdev, stdev->dev.devt, 1);
-	if (rc)
-		goto err_put;
-
-	rc = device_add(&stdev->dev);
+	rc = cdev_device_add(&stdev->cdev, &stdev->dev);
 	if (rc)
 		goto err_devadd;
 
@@ -1492,7 +1490,6 @@ static int switchtec_pci_probe(struct pci_dev *pdev,
 	return 0;
 
 err_devadd:
-	cdev_del(&stdev->cdev);
 	stdev_kill(stdev);
 err_put:
 	ida_simple_remove(&switchtec_minor_ida, MINOR(stdev->dev.devt));
@@ -1506,8 +1503,7 @@ static void switchtec_pci_remove(struct pci_dev *pdev)
 
 	pci_set_drvdata(pdev, NULL);
 
-	device_del(&stdev->dev);
-	cdev_del(&stdev->cdev);
+	cdev_device_del(&stdev->cdev, &stdev->dev);
 	ida_simple_remove(&switchtec_minor_ida, MINOR(stdev->dev.devt));
 	dev_info(&stdev->dev, "unregistered.\n");
 
diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c
index 622bdabc8894..dab195f04da7 100644
--- a/drivers/scsi/csiostor/csio_hw.c
+++ b/drivers/scsi/csiostor/csio_hw.c
@@ -1769,7 +1769,6 @@ csio_hw_use_fwconfig(struct csio_hw *hw, int reset, u32 *fw_cfg_param)
 		goto bye;
 	}
 
-	mempool_free(mbp, hw->mb_mempool);
 	if (finicsum != cfcsum) {
 		csio_warn(hw,
 		      "Config File checksum mismatch: csum=%#x, computed=%#x\n",
@@ -1780,6 +1779,10 @@ csio_hw_use_fwconfig(struct csio_hw *hw, int reset, u32 *fw_cfg_param)
 	rv = csio_hw_validate_caps(hw, mbp);
 	if (rv != 0)
 		goto bye;
+
+	mempool_free(mbp, hw->mb_mempool);
+	mbp = NULL;
+
 	/*
 	 * Note that we're operating with parameters
 	 * not supplied by the driver, rather than from hard-wired
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index b44c3136eb51..520325867e2b 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -1422,7 +1422,7 @@ static void fc_rport_recv_rtv_req(struct fc_rport_priv *rdata,
 	fp = fc_frame_alloc(lport, sizeof(*rtv));
 	if (!fp) {
 		rjt_data.reason = ELS_RJT_UNAB;
-		rjt_data.reason = ELS_EXPL_INSUF_RES;
+		rjt_data.explan = ELS_EXPL_INSUF_RES;
 		fc_seq_els_rsp_send(in_fp, ELS_LS_RJT, &rjt_data);
 		goto drop;
 	}
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 6d7840b096e6..f2c0ba6ced78 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -141,6 +141,13 @@ struct lpfc_dmabuf {
 	uint32_t   buffer_tag;	/* used for tagged queue ring */
 };
 
+struct lpfc_nvmet_ctxbuf {
+	struct list_head list;
+	struct lpfc_nvmet_rcv_ctx *context;
+	struct lpfc_iocbq *iocbq;
+	struct lpfc_sglq *sglq;
+};
+
 struct lpfc_dma_pool {
 	struct lpfc_dmabuf   *elements;
 	uint32_t    max_count;
@@ -163,9 +170,7 @@ struct rqb_dmabuf {
 	struct lpfc_dmabuf dbuf;
 	uint16_t total_size;
 	uint16_t bytes_recv;
-	void *context;
-	struct lpfc_iocbq *iocbq;
-	struct lpfc_sglq *sglq;
+	uint16_t idx;
 	struct lpfc_queue *hrq;	  /* ptr to associated Header RQ */
 	struct lpfc_queue *drq;	  /* ptr to associated Data RQ */
 };
@@ -670,6 +675,8 @@ struct lpfc_hba {
 					/* INIT_LINK mailbox command */
 #define LS_NPIV_FAB_SUPPORTED 0x2	/* Fabric supports NPIV */
 #define LS_IGNORE_ERATT       0x4	/* intr handler should ignore ERATT */
+#define LS_MDS_LINK_DOWN      0x8	/* MDS Diagnostics Link Down */
+#define LS_MDS_LOOPBACK      0x16	/* MDS Diagnostics Link Up (Loopback) */
 
 	uint32_t hba_flag;	/* hba generic flags */
 #define HBA_ERATT_HANDLED	0x1 /* This flag is set when eratt handled */
@@ -777,7 +784,6 @@ struct lpfc_hba {
 	uint32_t cfg_nvme_oas;
 	uint32_t cfg_nvme_io_channel;
 	uint32_t cfg_nvmet_mrq;
-	uint32_t cfg_nvmet_mrq_post;
 	uint32_t cfg_enable_nvmet;
 	uint32_t cfg_nvme_enable_fb;
 	uint32_t cfg_nvmet_fb_size;
@@ -943,6 +949,7 @@ struct lpfc_hba {
 	struct pci_pool *lpfc_mbuf_pool;
 	struct pci_pool *lpfc_hrb_pool;	/* header receive buffer pool */
 	struct pci_pool *lpfc_drb_pool; /* data receive buffer pool */
+	struct pci_pool *lpfc_nvmet_drb_pool; /* data receive buffer pool */
 	struct pci_pool *lpfc_hbq_pool;	/* SLI3 hbq buffer pool */
 	struct pci_pool *txrdy_payload_pool;
 	struct lpfc_dma_pool lpfc_mbuf_safety_pool;
@@ -1228,7 +1235,11 @@ lpfc_sli_read_hs(struct lpfc_hba *phba)
 static inline struct lpfc_sli_ring *
 lpfc_phba_elsring(struct lpfc_hba *phba)
 {
-	if (phba->sli_rev == LPFC_SLI_REV4)
-		return phba->sli4_hba.els_wq->pring;
+	if (phba->sli_rev == LPFC_SLI_REV4) {
+		if (phba->sli4_hba.els_wq)
+			return phba->sli4_hba.els_wq->pring;
+		else
+			return NULL;
+	}
 	return &phba->sli.sli3_ring[LPFC_ELS_RING];
 }
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 4830370bfab1..bb2d9e238225 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -60,9 +60,9 @@
 #define LPFC_MIN_DEVLOSS_TMO	1
 #define LPFC_MAX_DEVLOSS_TMO	255
 
-#define LPFC_DEF_MRQ_POST	256
-#define LPFC_MIN_MRQ_POST	32
-#define LPFC_MAX_MRQ_POST	512
+#define LPFC_DEF_MRQ_POST	512
+#define LPFC_MIN_MRQ_POST	512
+#define LPFC_MAX_MRQ_POST	2048
 
 /*
  * Write key size should be multiple of 4. If write key is changed
@@ -205,8 +205,9 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 				atomic_read(&tgtp->xmt_ls_rsp_error));
 
 		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP: Rcv %08x Drop %08x\n",
+				"FCP: Rcv %08x Release %08x Drop %08x\n",
 				atomic_read(&tgtp->rcv_fcp_cmd_in),
+				atomic_read(&tgtp->xmt_fcp_release),
 				atomic_read(&tgtp->rcv_fcp_cmd_drop));
 
 		if (atomic_read(&tgtp->rcv_fcp_cmd_in) !=
@@ -218,15 +219,12 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		}
 
 		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x\n",
+				"FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x "
+				"drop %08x\n",
 				atomic_read(&tgtp->xmt_fcp_read),
 				atomic_read(&tgtp->xmt_fcp_read_rsp),
 				atomic_read(&tgtp->xmt_fcp_write),
-				atomic_read(&tgtp->xmt_fcp_rsp));
-
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP Rsp: abort %08x drop %08x\n",
-				atomic_read(&tgtp->xmt_fcp_abort),
+				atomic_read(&tgtp->xmt_fcp_rsp),
 				atomic_read(&tgtp->xmt_fcp_drop));
 
 		len += snprintf(buf+len, PAGE_SIZE-len,
@@ -236,10 +234,22 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 				atomic_read(&tgtp->xmt_fcp_rsp_drop));
 
 		len += snprintf(buf+len, PAGE_SIZE-len,
-				"ABORT: Xmt %08x Err %08x Cmpl %08x",
+				"ABORT: Xmt %08x Cmpl %08x\n",
+				atomic_read(&tgtp->xmt_fcp_abort),
+				atomic_read(&tgtp->xmt_fcp_abort_cmpl));
+
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"ABORT: Sol %08x  Usol %08x Err %08x Cmpl %08x",
+				atomic_read(&tgtp->xmt_abort_sol),
+				atomic_read(&tgtp->xmt_abort_unsol),
 				atomic_read(&tgtp->xmt_abort_rsp),
-				atomic_read(&tgtp->xmt_abort_rsp_error),
-				atomic_read(&tgtp->xmt_abort_cmpl));
+				atomic_read(&tgtp->xmt_abort_rsp_error));
+
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"IO_CTX: %08x outstanding %08x total %x",
+				phba->sli4_hba.nvmet_ctx_cnt,
+				phba->sli4_hba.nvmet_io_wait_cnt,
+				phba->sli4_hba.nvmet_io_wait_total);
 
 		len +=  snprintf(buf+len, PAGE_SIZE-len, "\n");
 		return len;
@@ -3312,14 +3322,6 @@ LPFC_ATTR_R(nvmet_mrq,
 	    "Specify number of RQ pairs for processing NVMET cmds");
 
 /*
- * lpfc_nvmet_mrq_post: Specify number buffers to post on every MRQ
- *
- */
-LPFC_ATTR_R(nvmet_mrq_post, LPFC_DEF_MRQ_POST,
-	    LPFC_MIN_MRQ_POST, LPFC_MAX_MRQ_POST,
-	    "Specify number of buffers to post on every MRQ");
-
-/*
  * lpfc_enable_fc4_type: Defines what FC4 types are supported.
  * Supported Values:  1 - register just FCP
  *                    3 - register both FCP and NVME
@@ -5154,7 +5156,6 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_suppress_rsp,
 	&dev_attr_lpfc_nvme_io_channel,
 	&dev_attr_lpfc_nvmet_mrq,
-	&dev_attr_lpfc_nvmet_mrq_post,
 	&dev_attr_lpfc_nvme_enable_fb,
 	&dev_attr_lpfc_nvmet_fb_size,
 	&dev_attr_lpfc_enable_bg,
@@ -6194,7 +6195,6 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 
 	lpfc_enable_fc4_type_init(phba, lpfc_enable_fc4_type);
 	lpfc_nvmet_mrq_init(phba, lpfc_nvmet_mrq);
-	lpfc_nvmet_mrq_post_init(phba, lpfc_nvmet_mrq_post);
 
 	/* Initialize first burst. Target vs Initiator are different. */
 	lpfc_nvme_enable_fb_init(phba, lpfc_nvme_enable_fb);
@@ -6291,7 +6291,6 @@ lpfc_nvme_mod_param_dep(struct lpfc_hba *phba)
 		/* Not NVME Target mode.  Turn off Target parameters. */
 		phba->nvmet_support = 0;
 		phba->cfg_nvmet_mrq = 0;
-		phba->cfg_nvmet_mrq_post = 0;
 		phba->cfg_nvmet_fb_size = 0;
 	}
 
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 1c55408ac718..8912767e7bc8 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -75,6 +75,10 @@ void lpfc_init_vpi_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_cancel_all_vport_retry_delay_timer(struct lpfc_hba *);
 void lpfc_retry_pport_discovery(struct lpfc_hba *);
 void lpfc_release_rpi(struct lpfc_hba *, struct lpfc_vport *, uint16_t);
+int lpfc_init_iocb_list(struct lpfc_hba *phba, int cnt);
+void lpfc_free_iocb_list(struct lpfc_hba *phba);
+int lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq,
+			struct lpfc_queue *drq, int count, int idx);
 
 void lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
@@ -246,16 +250,14 @@ struct hbq_dmabuf *lpfc_sli4_rb_alloc(struct lpfc_hba *);
 void lpfc_sli4_rb_free(struct lpfc_hba *, struct hbq_dmabuf *);
 struct rqb_dmabuf *lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba);
 void lpfc_sli4_nvmet_free(struct lpfc_hba *phba, struct rqb_dmabuf *dmab);
-void lpfc_nvmet_rq_post(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp,
-			struct lpfc_dmabuf *mp);
+void lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba,
+			    struct lpfc_nvmet_ctxbuf *ctxp);
 int lpfc_nvmet_rcv_unsol_abort(struct lpfc_vport *vport,
 			       struct fc_frame_header *fc_hdr);
 void lpfc_sli4_build_dflt_fcf_record(struct lpfc_hba *, struct fcf_record *,
 			uint16_t);
 int lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq,
 		     struct lpfc_rqe *hrqe, struct lpfc_rqe *drqe);
-int lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hq,
-			struct lpfc_queue *dq, int count);
 int lpfc_free_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hq);
 void lpfc_unregister_fcf(struct lpfc_hba *);
 void lpfc_unregister_fcf_rescan(struct lpfc_hba *);
@@ -271,6 +273,7 @@ int lpfc_sli4_fcf_rr_next_proc(struct lpfc_vport *, uint16_t);
 void lpfc_sli4_clear_fcf_rr_bmask(struct lpfc_hba *);
 
 int lpfc_mem_alloc(struct lpfc_hba *, int align);
+int lpfc_nvmet_mem_alloc(struct lpfc_hba *phba);
 int lpfc_mem_alloc_active_rrq_pool_s4(struct lpfc_hba *);
 void lpfc_mem_free(struct lpfc_hba *);
 void lpfc_mem_free_all(struct lpfc_hba *);
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index c7962dae4dab..f2cd19c6c2df 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -2092,6 +2092,7 @@ lpfc_fdmi_port_attr_fc4type(struct lpfc_vport *vport,
 
 	ae->un.AttrTypes[3] = 0x02; /* Type 1 - ELS */
 	ae->un.AttrTypes[2] = 0x01; /* Type 8 - FCP */
+	ae->un.AttrTypes[6] = 0x01; /* Type 40 - NVME */
 	ae->un.AttrTypes[7] = 0x01; /* Type 32 - CT */
 	size = FOURBYTES + 32;
 	ad->AttrLen = cpu_to_be16(size);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index fce549a91911..4bcb92c844ca 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -798,21 +798,22 @@ lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size)
 				atomic_read(&tgtp->xmt_fcp_rsp));
 
 		len += snprintf(buf + len, size - len,
-				"FCP Rsp: abort %08x drop %08x\n",
-				atomic_read(&tgtp->xmt_fcp_abort),
-				atomic_read(&tgtp->xmt_fcp_drop));
-
-		len += snprintf(buf + len, size - len,
 				"FCP Rsp Cmpl: %08x err %08x drop %08x\n",
 				atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
 				atomic_read(&tgtp->xmt_fcp_rsp_error),
 				atomic_read(&tgtp->xmt_fcp_rsp_drop));
 
 		len += snprintf(buf + len, size - len,
-				"ABORT: Xmt %08x Err %08x Cmpl %08x",
+				"ABORT: Xmt %08x Cmpl %08x\n",
+				atomic_read(&tgtp->xmt_fcp_abort),
+				atomic_read(&tgtp->xmt_fcp_abort_cmpl));
+
+		len += snprintf(buf + len, size - len,
+				"ABORT: Sol %08x  Usol %08x Err %08x Cmpl %08x",
+				atomic_read(&tgtp->xmt_abort_sol),
+				atomic_read(&tgtp->xmt_abort_unsol),
 				atomic_read(&tgtp->xmt_abort_rsp),
-				atomic_read(&tgtp->xmt_abort_rsp_error),
-				atomic_read(&tgtp->xmt_abort_cmpl));
+				atomic_read(&tgtp->xmt_abort_rsp_error));
 
 		len +=  snprintf(buf + len, size - len, "\n");
 
@@ -841,6 +842,12 @@ lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size)
 			}
 			spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		}
+
+		len += snprintf(buf + len, size - len,
+				"IO_CTX: %08x  outstanding %08x total %08x\n",
+				phba->sli4_hba.nvmet_ctx_cnt,
+				phba->sli4_hba.nvmet_io_wait_cnt,
+				phba->sli4_hba.nvmet_io_wait_total);
 	} else {
 		if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
 			return len;
@@ -1959,6 +1966,7 @@ lpfc_debugfs_nvmestat_write(struct file *file, const char __user *buf,
 		atomic_set(&tgtp->rcv_ls_req_out, 0);
 		atomic_set(&tgtp->rcv_ls_req_drop, 0);
 		atomic_set(&tgtp->xmt_ls_abort, 0);
+		atomic_set(&tgtp->xmt_ls_abort_cmpl, 0);
 		atomic_set(&tgtp->xmt_ls_rsp, 0);
 		atomic_set(&tgtp->xmt_ls_drop, 0);
 		atomic_set(&tgtp->xmt_ls_rsp_error, 0);
@@ -1967,19 +1975,22 @@ lpfc_debugfs_nvmestat_write(struct file *file, const char __user *buf,
 		atomic_set(&tgtp->rcv_fcp_cmd_in, 0);
 		atomic_set(&tgtp->rcv_fcp_cmd_out, 0);
 		atomic_set(&tgtp->rcv_fcp_cmd_drop, 0);
-		atomic_set(&tgtp->xmt_fcp_abort, 0);
 		atomic_set(&tgtp->xmt_fcp_drop, 0);
 		atomic_set(&tgtp->xmt_fcp_read_rsp, 0);
 		atomic_set(&tgtp->xmt_fcp_read, 0);
 		atomic_set(&tgtp->xmt_fcp_write, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp, 0);
+		atomic_set(&tgtp->xmt_fcp_release, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp_cmpl, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp_error, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp_drop, 0);
 
+		atomic_set(&tgtp->xmt_fcp_abort, 0);
+		atomic_set(&tgtp->xmt_fcp_abort_cmpl, 0);
+		atomic_set(&tgtp->xmt_abort_sol, 0);
+		atomic_set(&tgtp->xmt_abort_unsol, 0);
 		atomic_set(&tgtp->xmt_abort_rsp, 0);
 		atomic_set(&tgtp->xmt_abort_rsp_error, 0);
-		atomic_set(&tgtp->xmt_abort_cmpl, 0);
 	}
 	return nbytes;
 }
@@ -3070,11 +3081,11 @@ __lpfc_idiag_print_wq(struct lpfc_queue *qp, char *wqtype,
 			qp->assoc_qid, qp->q_cnt_1,
 			(unsigned long long)qp->q_cnt_4);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
-			"\t\tWQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]",
+			"\t\tWQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
 			qp->queue_id, qp->entry_count,
 			qp->entry_size, qp->host_index,
-			qp->hba_index);
+			qp->hba_index, qp->entry_repost);
 	len +=  snprintf(pbuffer + len,
 			LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
 	return len;
@@ -3121,11 +3132,11 @@ __lpfc_idiag_print_cq(struct lpfc_queue *qp, char *cqtype,
 			qp->assoc_qid, qp->q_cnt_1, qp->q_cnt_2,
 			qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
-			"\tCQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]",
+			"\tCQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
 			qp->queue_id, qp->entry_count,
 			qp->entry_size, qp->host_index,
-			qp->hba_index);
+			qp->hba_index, qp->entry_repost);
 
 	len +=  snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
 
@@ -3143,20 +3154,20 @@ __lpfc_idiag_print_rqpair(struct lpfc_queue *qp, struct lpfc_queue *datqp,
 			"\t\t%s RQ info: ", rqtype);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
 			"AssocCQID[%02d]: RQ-STAT[nopost:x%x nobuf:x%x "
-			"trunc:x%x rcv:x%llx]\n",
+			"posted:x%x rcv:x%llx]\n",
 			qp->assoc_qid, qp->q_cnt_1, qp->q_cnt_2,
 			qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
-			"\t\tHQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]\n",
+			"\t\tHQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]\n",
 			qp->queue_id, qp->entry_count, qp->entry_size,
-			qp->host_index, qp->hba_index);
+			qp->host_index, qp->hba_index, qp->entry_repost);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
-			"\t\tDQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]\n",
+			"\t\tDQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]\n",
 			datqp->queue_id, datqp->entry_count,
 			datqp->entry_size, datqp->host_index,
-			datqp->hba_index);
+			datqp->hba_index, datqp->entry_repost);
 	return len;
 }
 
@@ -3242,10 +3253,10 @@ __lpfc_idiag_print_eq(struct lpfc_queue *qp, char *eqtype,
 			eqtype, qp->q_cnt_1, qp->q_cnt_2, qp->q_cnt_3,
 			(unsigned long long)qp->q_cnt_4);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
-			"EQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]",
+			"EQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
 			qp->queue_id, qp->entry_count, qp->entry_size,
-			qp->host_index, qp->hba_index);
+			qp->host_index, qp->hba_index, qp->entry_repost);
 	len +=  snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
 
 	return len;
@@ -5855,8 +5866,10 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 			atomic_dec(&lpfc_debugfs_hba_count);
 		}
 
-		debugfs_remove(lpfc_debugfs_root); /* lpfc */
-		lpfc_debugfs_root = NULL;
+		if (atomic_read(&lpfc_debugfs_hba_count) == 0) {
+			debugfs_remove(lpfc_debugfs_root); /* lpfc */
+			lpfc_debugfs_root = NULL;
+		}
 	}
 #endif
 	return;
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index 9d5a379f4b15..094c97b9e5f7 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -90,6 +90,7 @@ struct lpfc_nodelist {
 #define NLP_FCP_INITIATOR  0x10			/* entry is an FCP Initiator */
 #define NLP_NVME_TARGET    0x20			/* entry is a NVME Target */
 #define NLP_NVME_INITIATOR 0x40			/* entry is a NVME Initiator */
+#define NLP_NVME_DISCOVERY 0x80                 /* entry has NVME disc srvc */
 
 	uint16_t	nlp_fc4_type;		/* FC types node supports. */
 						/* Assigned from GID_FF, only
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 67827e397431..8e532b39ae93 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1047,6 +1047,13 @@ stop_rr_fcf_flogi:
 				 irsp->ulpStatus, irsp->un.ulpWord[4],
 				 irsp->ulpTimeout);
 
+
+		/* If this is not a loop open failure, bail out */
+		if (!(irsp->ulpStatus == IOSTAT_LOCAL_REJECT &&
+		      ((irsp->un.ulpWord[4] & IOERR_PARAM_MASK) ==
+					IOERR_LOOP_OPEN_FAILURE)))
+			goto flogifail;
+
 		/* FLOGI failed, so there is no fabric */
 		spin_lock_irq(shost->host_lock);
 		vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
@@ -2077,16 +2084,19 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	if (irsp->ulpStatus) {
 		/* Check for retry */
+		ndlp->fc4_prli_sent--;
 		if (lpfc_els_retry(phba, cmdiocb, rspiocb)) {
 			/* ELS command is being retried */
-			ndlp->fc4_prli_sent--;
 			goto out;
 		}
+
 		/* PRLI failed */
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
-				 "2754 PRLI failure DID:%06X Status:x%x/x%x\n",
+				 "2754 PRLI failure DID:%06X Status:x%x/x%x, "
+				 "data: x%x\n",
 				 ndlp->nlp_DID, irsp->ulpStatus,
-				 irsp->un.ulpWord[4]);
+				 irsp->un.ulpWord[4], ndlp->fc4_prli_sent);
+
 		/* Do not call DSM for lpfc_els_abort'ed ELS cmds */
 		if (lpfc_error_lost_link(irsp))
 			goto out;
@@ -7441,6 +7451,13 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 	 */
 	spin_lock_irq(&phba->hbalock);
 	pring = lpfc_phba_elsring(phba);
+
+	/* Bail out if we've no ELS wq, like in PCI error recovery case. */
+	if (unlikely(!pring)) {
+		spin_unlock_irq(&phba->hbalock);
+		return;
+	}
+
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		spin_lock(&pring->ring_lock);
 
@@ -8667,7 +8684,8 @@ lpfc_cmpl_els_fdisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		lpfc_do_scr_ns_plogi(phba, vport);
 	goto out;
 fdisc_failed:
-	if (vport->fc_vport->vport_state != FC_VPORT_NO_FABRIC_RSCS)
+	if (vport->fc_vport &&
+	    (vport->fc_vport->vport_state != FC_VPORT_NO_FABRIC_RSCS))
 		lpfc_vport_set_state(vport, FC_VPORT_FAILED);
 	/* Cancel discovery timer */
 	lpfc_can_disctmo(vport);
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 0482c5580331..3ffcd9215ca8 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -693,15 +693,16 @@ lpfc_work_done(struct lpfc_hba *phba)
 	pring = lpfc_phba_elsring(phba);
 	status = (ha_copy & (HA_RXMASK  << (4*LPFC_ELS_RING)));
 	status >>= (4*LPFC_ELS_RING);
-	if ((status & HA_RXMASK) ||
-	    (pring->flag & LPFC_DEFERRED_RING_EVENT) ||
-	    (phba->hba_flag & HBA_SP_QUEUE_EVT)) {
+	if (pring && (status & HA_RXMASK ||
+		      pring->flag & LPFC_DEFERRED_RING_EVENT ||
+		      phba->hba_flag & HBA_SP_QUEUE_EVT)) {
 		if (pring->flag & LPFC_STOP_IOCB_EVENT) {
 			pring->flag |= LPFC_DEFERRED_RING_EVENT;
 			/* Set the lpfc data pending flag */
 			set_bit(LPFC_DATA_READY, &phba->data_flags);
 		} else {
-			if (phba->link_state >= LPFC_LINK_UP) {
+			if (phba->link_state >= LPFC_LINK_UP ||
+			    phba->link_flag & LS_MDS_LOOPBACK) {
 				pring->flag &= ~LPFC_DEFERRED_RING_EVENT;
 				lpfc_sli_handle_slow_ring_event(phba, pring,
 								(status &
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 1d12f2be36bc..e0a5fce416ae 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1356,6 +1356,7 @@ struct lpfc_mbx_wq_destroy {
 
 #define LPFC_HDR_BUF_SIZE 128
 #define LPFC_DATA_BUF_SIZE 2048
+#define LPFC_NVMET_DATA_BUF_SIZE 128
 struct rq_context {
 	uint32_t word0;
 #define lpfc_rq_context_rqe_count_SHIFT	16	/* Version 0 Only */
@@ -4420,6 +4421,19 @@ struct fcp_treceive64_wqe {
 };
 #define TXRDY_PAYLOAD_LEN      12
 
+#define CMD_SEND_FRAME	0xE1
+
+struct send_frame_wqe {
+	struct ulp_bde64 bde;          /* words 0-2 */
+	uint32_t frame_len;            /* word 3 */
+	uint32_t fc_hdr_wd0;           /* word 4 */
+	uint32_t fc_hdr_wd1;           /* word 5 */
+	struct wqe_common wqe_com;     /* words 6-11 */
+	uint32_t fc_hdr_wd2;           /* word 12 */
+	uint32_t fc_hdr_wd3;           /* word 13 */
+	uint32_t fc_hdr_wd4;           /* word 14 */
+	uint32_t fc_hdr_wd5;           /* word 15 */
+};
 
 union lpfc_wqe {
 	uint32_t words[16];
@@ -4438,7 +4452,7 @@ union lpfc_wqe {
 	struct fcp_trsp64_wqe fcp_trsp;
 	struct fcp_tsend64_wqe fcp_tsend;
 	struct fcp_treceive64_wqe fcp_treceive;
-
+	struct send_frame_wqe send_frame;
 };
 
 union lpfc_wqe128 {
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 4b1eb98c228d..9add9473cae5 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -1099,7 +1099,7 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 
 		list_for_each_entry_safe(ctxp, ctxp_next, &nvmet_aborts, list) {
 			ctxp->flag &= ~(LPFC_NVMET_XBUSY | LPFC_NVMET_ABORT_OP);
-			lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+			lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
 		}
 	}
 
@@ -3381,7 +3381,7 @@ lpfc_sli4_nvmet_sgl_update(struct lpfc_hba *phba)
 {
 	struct lpfc_sglq *sglq_entry = NULL, *sglq_entry_next = NULL;
 	uint16_t i, lxri, xri_cnt, els_xri_cnt;
-	uint16_t nvmet_xri_cnt, tot_cnt;
+	uint16_t nvmet_xri_cnt;
 	LIST_HEAD(nvmet_sgl_list);
 	int rc;
 
@@ -3389,15 +3389,9 @@ lpfc_sli4_nvmet_sgl_update(struct lpfc_hba *phba)
 	 * update on pci function's nvmet xri-sgl list
 	 */
 	els_xri_cnt = lpfc_sli4_get_els_iocb_cnt(phba);
-	nvmet_xri_cnt = phba->cfg_nvmet_mrq * phba->cfg_nvmet_mrq_post;
-	tot_cnt = phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
-	if (nvmet_xri_cnt > tot_cnt) {
-		phba->cfg_nvmet_mrq_post = tot_cnt / phba->cfg_nvmet_mrq;
-		nvmet_xri_cnt = phba->cfg_nvmet_mrq * phba->cfg_nvmet_mrq_post;
-		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
-				"6301 NVMET post-sgl count changed to %d\n",
-				phba->cfg_nvmet_mrq_post);
-	}
+
+	/* For NVMET, ALL remaining XRIs are dedicated for IO processing */
+	nvmet_xri_cnt = phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
 
 	if (nvmet_xri_cnt > phba->sli4_hba.nvmet_xri_cnt) {
 		/* els xri-sgl expanded */
@@ -4546,6 +4540,19 @@ lpfc_sli4_async_fc_evt(struct lpfc_hba *phba, struct lpfc_acqe_fc_la *acqe_fc)
 	pmb->vport = phba->pport;
 
 	if (phba->sli4_hba.link_state.status != LPFC_FC_LA_TYPE_LINK_UP) {
+		phba->link_flag &= ~(LS_MDS_LINK_DOWN | LS_MDS_LOOPBACK);
+
+		switch (phba->sli4_hba.link_state.status) {
+		case LPFC_FC_LA_TYPE_MDS_LINK_DOWN:
+			phba->link_flag |= LS_MDS_LINK_DOWN;
+			break;
+		case LPFC_FC_LA_TYPE_MDS_LOOPBACK:
+			phba->link_flag |= LS_MDS_LOOPBACK;
+			break;
+		default:
+			break;
+		}
+
 		/* Parse and translate status field */
 		mb = &pmb->u.mb;
 		mb->mbxStatus = lpfc_sli4_parse_latt_fault(phba,
@@ -5830,6 +5837,9 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		spin_lock_init(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
 		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
+		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_ctx_list);
+		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_io_wait_list);
+
 		/* Fast-path XRI aborted CQ Event work queue list */
 		INIT_LIST_HEAD(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue);
 	}
@@ -5837,6 +5847,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	/* This abort list used by worker thread */
 	spin_lock_init(&phba->sli4_hba.sgl_list_lock);
 	spin_lock_init(&phba->sli4_hba.nvmet_io_lock);
+	spin_lock_init(&phba->sli4_hba.nvmet_io_wait_lock);
 
 	/*
 	 * Initialize driver internal slow-path work queues
@@ -5951,16 +5962,21 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		for (i = 0; i < lpfc_enable_nvmet_cnt; i++) {
 			if (wwn == lpfc_enable_nvmet[i]) {
 #if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
+				if (lpfc_nvmet_mem_alloc(phba))
+					break;
+
+				phba->nvmet_support = 1; /* a match */
+
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 						"6017 NVME Target %016llx\n",
 						wwn);
-				phba->nvmet_support = 1; /* a match */
 #else
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 						"6021 Can't enable NVME Target."
 						" NVME_TARGET_FC infrastructure"
 						" is not in kernel\n");
 #endif
+				break;
 			}
 		}
 	}
@@ -6269,7 +6285,7 @@ lpfc_unset_driver_resource_phase2(struct lpfc_hba *phba)
  *
  * This routine is invoked to free the driver's IOCB list and memory.
  **/
-static void
+void
 lpfc_free_iocb_list(struct lpfc_hba *phba)
 {
 	struct lpfc_iocbq *iocbq_entry = NULL, *iocbq_next = NULL;
@@ -6297,7 +6313,7 @@ lpfc_free_iocb_list(struct lpfc_hba *phba)
  *	0 - successful
  *	other values - error
  **/
-static int
+int
 lpfc_init_iocb_list(struct lpfc_hba *phba, int iocb_count)
 {
 	struct lpfc_iocbq *iocbq_entry = NULL;
@@ -6525,7 +6541,6 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 	uint16_t rpi_limit, curr_rpi_range;
 	struct lpfc_dmabuf *dmabuf;
 	struct lpfc_rpi_hdr *rpi_hdr;
-	uint32_t rpi_count;
 
 	/*
 	 * If the SLI4 port supports extents, posting the rpi header isn't
@@ -6538,8 +6553,7 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 		return NULL;
 
 	/* The limit on the logical index is just the max_rpi count. */
-	rpi_limit = phba->sli4_hba.max_cfg_param.rpi_base +
-	phba->sli4_hba.max_cfg_param.max_rpi - 1;
+	rpi_limit = phba->sli4_hba.max_cfg_param.max_rpi;
 
 	spin_lock_irq(&phba->hbalock);
 	/*
@@ -6550,18 +6564,10 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 	curr_rpi_range = phba->sli4_hba.next_rpi;
 	spin_unlock_irq(&phba->hbalock);
 
-	/*
-	 * The port has a limited number of rpis. The increment here
-	 * is LPFC_RPI_HDR_COUNT - 1 to account for the starting value
-	 * and to allow the full max_rpi range per port.
-	 */
-	if ((curr_rpi_range + (LPFC_RPI_HDR_COUNT - 1)) > rpi_limit)
-		rpi_count = rpi_limit - curr_rpi_range;
-	else
-		rpi_count = LPFC_RPI_HDR_COUNT;
-
-	if (!rpi_count)
+	/* Reached full RPI range */
+	if (curr_rpi_range == rpi_limit)
 		return NULL;
+
 	/*
 	 * First allocate the protocol header region for the port.  The
 	 * port expects a 4KB DMA-mapped memory region that is 4K aligned.
@@ -6595,13 +6601,9 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 
 	/* The rpi_hdr stores the logical index only. */
 	rpi_hdr->start_rpi = curr_rpi_range;
+	rpi_hdr->next_rpi = phba->sli4_hba.next_rpi + LPFC_RPI_HDR_COUNT;
 	list_add_tail(&rpi_hdr->list, &phba->sli4_hba.lpfc_rpi_hdr_list);
 
-	/*
-	 * The next_rpi stores the next logical module-64 rpi value used
-	 * to post physical rpis in subsequent rpi postings.
-	 */
-	phba->sli4_hba.next_rpi += rpi_count;
 	spin_unlock_irq(&phba->hbalock);
 	return rpi_hdr;
 
@@ -8172,7 +8174,7 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 			/* Create NVMET Receive Queue for header */
 			qdesc = lpfc_sli4_queue_alloc(phba,
 						      phba->sli4_hba.rq_esize,
-						      phba->sli4_hba.rq_ecount);
+						      LPFC_NVMET_RQE_DEF_COUNT);
 			if (!qdesc) {
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 						"3146 Failed allocate "
@@ -8194,7 +8196,7 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 			/* Create NVMET Receive Queue for data */
 			qdesc = lpfc_sli4_queue_alloc(phba,
 						      phba->sli4_hba.rq_esize,
-						      phba->sli4_hba.rq_ecount);
+						      LPFC_NVMET_RQE_DEF_COUNT);
 			if (!qdesc) {
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 						"3156 Failed allocate "
@@ -8326,46 +8328,6 @@ lpfc_sli4_queue_destroy(struct lpfc_hba *phba)
 }
 
 int
-lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq,
-		    struct lpfc_queue *drq, int count)
-{
-	int rc, i;
-	struct lpfc_rqe hrqe;
-	struct lpfc_rqe drqe;
-	struct lpfc_rqb *rqbp;
-	struct rqb_dmabuf *rqb_buffer;
-	LIST_HEAD(rqb_buf_list);
-
-	rqbp = hrq->rqbp;
-	for (i = 0; i < count; i++) {
-		rqb_buffer = (rqbp->rqb_alloc_buffer)(phba);
-		if (!rqb_buffer)
-			break;
-		rqb_buffer->hrq = hrq;
-		rqb_buffer->drq = drq;
-		list_add_tail(&rqb_buffer->hbuf.list, &rqb_buf_list);
-	}
-	while (!list_empty(&rqb_buf_list)) {
-		list_remove_head(&rqb_buf_list, rqb_buffer, struct rqb_dmabuf,
-				 hbuf.list);
-
-		hrqe.address_lo = putPaddrLow(rqb_buffer->hbuf.phys);
-		hrqe.address_hi = putPaddrHigh(rqb_buffer->hbuf.phys);
-		drqe.address_lo = putPaddrLow(rqb_buffer->dbuf.phys);
-		drqe.address_hi = putPaddrHigh(rqb_buffer->dbuf.phys);
-		rc = lpfc_sli4_rq_put(hrq, drq, &hrqe, &drqe);
-		if (rc < 0) {
-			(rqbp->rqb_free_buffer)(phba, rqb_buffer);
-		} else {
-			list_add_tail(&rqb_buffer->hbuf.list,
-				      &rqbp->rqb_buffer_list);
-			rqbp->buffer_count++;
-		}
-	}
-	return 1;
-}
-
-int
 lpfc_free_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *rq)
 {
 	struct lpfc_rqb *rqbp;
@@ -8784,9 +8746,6 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 		goto out_destroy;
 	}
 
-	lpfc_rq_adjust_repost(phba, phba->sli4_hba.hdr_rq, LPFC_ELS_HBQ);
-	lpfc_rq_adjust_repost(phba, phba->sli4_hba.dat_rq, LPFC_ELS_HBQ);
-
 	rc = lpfc_rq_create(phba, phba->sli4_hba.hdr_rq, phba->sli4_hba.dat_rq,
 			    phba->sli4_hba.els_cq, LPFC_USOL);
 	if (rc) {
@@ -11110,7 +11069,7 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	struct lpfc_hba   *phba;
 	struct lpfc_vport *vport = NULL;
 	struct Scsi_Host  *shost = NULL;
-	int error, cnt;
+	int error;
 	uint32_t cfg_mode, intr_mode;
 
 	/* Allocate memory for HBA structure */
@@ -11144,22 +11103,6 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 		goto out_unset_pci_mem_s4;
 	}
 
-	cnt = phba->cfg_iocb_cnt * 1024;
-	if (phba->nvmet_support)
-		cnt += phba->cfg_nvmet_mrq_post * phba->cfg_nvmet_mrq;
-
-	/* Initialize and populate the iocb list per host */
-	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-			"2821 initialize iocb list %d total %d\n",
-			phba->cfg_iocb_cnt, cnt);
-	error = lpfc_init_iocb_list(phba, cnt);
-
-	if (error) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-				"1413 Failed to initialize iocb list.\n");
-		goto out_unset_driver_resource_s4;
-	}
-
 	INIT_LIST_HEAD(&phba->active_rrq_list);
 	INIT_LIST_HEAD(&phba->fcf.fcf_pri_list);
 
@@ -11168,7 +11111,7 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	if (error) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 				"1414 Failed to set up driver resource.\n");
-		goto out_free_iocb_list;
+		goto out_unset_driver_resource_s4;
 	}
 
 	/* Get the default values for Model Name and Description */
@@ -11268,8 +11211,6 @@ out_destroy_shost:
 	lpfc_destroy_shost(phba);
 out_unset_driver_resource:
 	lpfc_unset_driver_resource_phase2(phba);
-out_free_iocb_list:
-	lpfc_free_iocb_list(phba);
 out_unset_driver_resource_s4:
 	lpfc_sli4_driver_resource_unset(phba);
 out_unset_pci_mem_s4:
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index 5986c7957199..fcc05a1517c2 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -214,6 +214,21 @@ fail_free_drb_pool:
 	return -ENOMEM;
 }
 
+int
+lpfc_nvmet_mem_alloc(struct lpfc_hba *phba)
+{
+	phba->lpfc_nvmet_drb_pool =
+		pci_pool_create("lpfc_nvmet_drb_pool",
+				phba->pcidev, LPFC_NVMET_DATA_BUF_SIZE,
+				SGL_ALIGN_SZ, 0);
+	if (!phba->lpfc_nvmet_drb_pool) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"6024 Can't enable NVME Target - no memory\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
 /**
  * lpfc_mem_free - Frees memory allocated by lpfc_mem_alloc
  * @phba: HBA to free memory for
@@ -232,6 +247,9 @@ lpfc_mem_free(struct lpfc_hba *phba)
 
 	/* Free HBQ pools */
 	lpfc_sli_hbqbuf_free_all(phba);
+	if (phba->lpfc_nvmet_drb_pool)
+		pci_pool_destroy(phba->lpfc_nvmet_drb_pool);
+	phba->lpfc_nvmet_drb_pool = NULL;
 	if (phba->lpfc_drb_pool)
 		pci_pool_destroy(phba->lpfc_drb_pool);
 	phba->lpfc_drb_pool = NULL;
@@ -611,8 +629,6 @@ struct rqb_dmabuf *
 lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba)
 {
 	struct rqb_dmabuf *dma_buf;
-	struct lpfc_iocbq *nvmewqe;
-	union lpfc_wqe128 *wqe;
 
 	dma_buf = kzalloc(sizeof(struct rqb_dmabuf), GFP_KERNEL);
 	if (!dma_buf)
@@ -624,69 +640,15 @@ lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba)
 		kfree(dma_buf);
 		return NULL;
 	}
-	dma_buf->dbuf.virt = pci_pool_alloc(phba->lpfc_drb_pool, GFP_KERNEL,
-					    &dma_buf->dbuf.phys);
+	dma_buf->dbuf.virt = pci_pool_alloc(phba->lpfc_nvmet_drb_pool,
+					    GFP_KERNEL, &dma_buf->dbuf.phys);
 	if (!dma_buf->dbuf.virt) {
 		pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
 			      dma_buf->hbuf.phys);
 		kfree(dma_buf);
 		return NULL;
 	}
-	dma_buf->total_size = LPFC_DATA_BUF_SIZE;
-
-	dma_buf->context = kzalloc(sizeof(struct lpfc_nvmet_rcv_ctx),
-				   GFP_KERNEL);
-	if (!dma_buf->context) {
-		pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
-			      dma_buf->dbuf.phys);
-		pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
-			      dma_buf->hbuf.phys);
-		kfree(dma_buf);
-		return NULL;
-	}
-
-	dma_buf->iocbq = lpfc_sli_get_iocbq(phba);
-	if (!dma_buf->iocbq) {
-		kfree(dma_buf->context);
-		pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
-			      dma_buf->dbuf.phys);
-		pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
-			      dma_buf->hbuf.phys);
-		kfree(dma_buf);
-		lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
-				"2621 Ran out of nvmet iocb/WQEs\n");
-		return NULL;
-	}
-	dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
-	nvmewqe = dma_buf->iocbq;
-	wqe = (union lpfc_wqe128 *)&nvmewqe->wqe;
-	/* Initialize WQE */
-	memset(wqe, 0, sizeof(union lpfc_wqe));
-	/* Word 7 */
-	bf_set(wqe_ct, &wqe->generic.wqe_com, SLI4_CT_RPI);
-	bf_set(wqe_class, &wqe->generic.wqe_com, CLASS3);
-	bf_set(wqe_pu, &wqe->generic.wqe_com, 1);
-	/* Word 10 */
-	bf_set(wqe_nvme, &wqe->fcp_tsend.wqe_com, 1);
-	bf_set(wqe_ebde_cnt, &wqe->generic.wqe_com, 0);
-	bf_set(wqe_qosd, &wqe->generic.wqe_com, 0);
-
-	dma_buf->iocbq->context1 = NULL;
-	spin_lock(&phba->sli4_hba.sgl_list_lock);
-	dma_buf->sglq = __lpfc_sli_get_nvmet_sglq(phba, dma_buf->iocbq);
-	spin_unlock(&phba->sli4_hba.sgl_list_lock);
-	if (!dma_buf->sglq) {
-		lpfc_sli_release_iocbq(phba, dma_buf->iocbq);
-		kfree(dma_buf->context);
-		pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
-			      dma_buf->dbuf.phys);
-		pci_pool_free(phba->lpfc_hrb_pool, dma_buf->hbuf.virt,
-			      dma_buf->hbuf.phys);
-		kfree(dma_buf);
-		lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
-				"6132 Ran out of nvmet XRIs\n");
-		return NULL;
-	}
+	dma_buf->total_size = LPFC_NVMET_DATA_BUF_SIZE;
 	return dma_buf;
 }
 
@@ -705,20 +667,9 @@ lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba)
 void
 lpfc_sli4_nvmet_free(struct lpfc_hba *phba, struct rqb_dmabuf *dmab)
 {
-	unsigned long flags;
-
-	__lpfc_clear_active_sglq(phba, dmab->sglq->sli4_lxritag);
-	dmab->sglq->state = SGL_FREED;
-	dmab->sglq->ndlp = NULL;
-
-	spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock, flags);
-	list_add_tail(&dmab->sglq->list, &phba->sli4_hba.lpfc_nvmet_sgl_list);
-	spin_unlock_irqrestore(&phba->sli4_hba.sgl_list_lock, flags);
-
-	lpfc_sli_release_iocbq(phba, dmab->iocbq);
-	kfree(dmab->context);
 	pci_pool_free(phba->lpfc_hrb_pool, dmab->hbuf.virt, dmab->hbuf.phys);
-	pci_pool_free(phba->lpfc_drb_pool, dmab->dbuf.virt, dmab->dbuf.phys);
+	pci_pool_free(phba->lpfc_nvmet_drb_pool,
+		      dmab->dbuf.virt, dmab->dbuf.phys);
 	kfree(dmab);
 }
 
@@ -803,6 +754,11 @@ lpfc_rq_buf_free(struct lpfc_hba *phba, struct lpfc_dmabuf *mp)
 	rc = lpfc_sli4_rq_put(rqb_entry->hrq, rqb_entry->drq, &hrqe, &drqe);
 	if (rc < 0) {
 		(rqbp->rqb_free_buffer)(phba, rqb_entry);
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"6409 Cannot post to RQ %d: %x %x\n",
+				rqb_entry->hrq->queue_id,
+				rqb_entry->hrq->host_index,
+				rqb_entry->hrq->hba_index);
 	} else {
 		list_add_tail(&rqb_entry->hbuf.list, &rqbp->rqb_buffer_list);
 		rqbp->buffer_count++;
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 8777c2d5f50d..bff3de053df4 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -1944,7 +1944,13 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 		/* Target driver cannot solicit NVME FB. */
 		if (bf_get_be32(prli_tgt, nvpr)) {
+			/* Complete the nvme target roles.  The transport
+			 * needs to know if the rport is capable of
+			 * discovery in addition to its role.
+			 */
 			ndlp->nlp_type |= NLP_NVME_TARGET;
+			if (bf_get_be32(prli_disc, nvpr))
+				ndlp->nlp_type |= NLP_NVME_DISCOVERY;
 			if ((bf_get_be32(prli_fba, nvpr) == 1) &&
 			    (bf_get_be32(prli_fb_sz, nvpr) > 0) &&
 			    (phba->cfg_nvme_enable_fb) &&
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 0488580eea12..074a6b5e7763 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -142,7 +142,7 @@ out:
 }
 
 /**
- * lpfc_nvmet_rq_post - Repost a NVMET RQ DMA buffer and clean up context
+ * lpfc_nvmet_ctxbuf_post - Repost a NVMET RQ DMA buffer and clean up context
  * @phba: HBA buffer is associated with
  * @ctxp: context to clean up
  * @mp: Buffer to free
@@ -155,24 +155,113 @@ out:
  * Returns: None
  **/
 void
-lpfc_nvmet_rq_post(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp,
-		   struct lpfc_dmabuf *mp)
+lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf)
 {
-	if (ctxp) {
-		if (ctxp->flag)
-			lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
-				"6314 rq_post ctx xri x%x flag x%x\n",
-				ctxp->oxid, ctxp->flag);
-
-		if (ctxp->txrdy) {
-			pci_pool_free(phba->txrdy_payload_pool, ctxp->txrdy,
-				      ctxp->txrdy_phys);
-			ctxp->txrdy = NULL;
-			ctxp->txrdy_phys = 0;
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
+	struct lpfc_nvmet_rcv_ctx *ctxp = ctx_buf->context;
+	struct lpfc_nvmet_tgtport *tgtp;
+	struct fc_frame_header *fc_hdr;
+	struct rqb_dmabuf *nvmebuf;
+	struct lpfc_dmabuf *hbufp;
+	uint32_t *payload;
+	uint32_t size, oxid, sid, rc;
+	unsigned long iflag;
+
+	if (ctxp->txrdy) {
+		pci_pool_free(phba->txrdy_payload_pool, ctxp->txrdy,
+			      ctxp->txrdy_phys);
+		ctxp->txrdy = NULL;
+		ctxp->txrdy_phys = 0;
+	}
+	ctxp->state = LPFC_NVMET_STE_FREE;
+
+	spin_lock_irqsave(&phba->sli4_hba.nvmet_io_wait_lock, iflag);
+	if (phba->sli4_hba.nvmet_io_wait_cnt) {
+		hbufp = &nvmebuf->hbuf;
+		list_remove_head(&phba->sli4_hba.lpfc_nvmet_io_wait_list,
+				 nvmebuf, struct rqb_dmabuf,
+				 hbuf.list);
+		phba->sli4_hba.nvmet_io_wait_cnt--;
+		spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_wait_lock,
+				       iflag);
+
+		fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
+		oxid = be16_to_cpu(fc_hdr->fh_ox_id);
+		tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+		payload = (uint32_t *)(nvmebuf->dbuf.virt);
+		size = nvmebuf->bytes_recv;
+		sid = sli4_sid_from_fc_hdr(fc_hdr);
+
+		ctxp = (struct lpfc_nvmet_rcv_ctx *)ctx_buf->context;
+		memset(ctxp, 0, sizeof(ctxp->ctx));
+		ctxp->wqeq = NULL;
+		ctxp->txrdy = NULL;
+		ctxp->offset = 0;
+		ctxp->phba = phba;
+		ctxp->size = size;
+		ctxp->oxid = oxid;
+		ctxp->sid = sid;
+		ctxp->state = LPFC_NVMET_STE_RCV;
+		ctxp->entry_cnt = 1;
+		ctxp->flag = 0;
+		ctxp->ctxbuf = ctx_buf;
+		spin_lock_init(&ctxp->ctxlock);
+
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+		if (phba->ktime_on) {
+			ctxp->ts_cmd_nvme = ktime_get_ns();
+			ctxp->ts_isr_cmd = ctxp->ts_cmd_nvme;
+			ctxp->ts_nvme_data = 0;
+			ctxp->ts_data_wqput = 0;
+			ctxp->ts_isr_data = 0;
+			ctxp->ts_data_nvme = 0;
+			ctxp->ts_nvme_status = 0;
+			ctxp->ts_status_wqput = 0;
+			ctxp->ts_isr_status = 0;
+			ctxp->ts_status_nvme = 0;
 		}
-		ctxp->state = LPFC_NVMET_STE_FREE;
+#endif
+		atomic_inc(&tgtp->rcv_fcp_cmd_in);
+		/*
+		 * The calling sequence should be:
+		 * nvmet_fc_rcv_fcp_req->lpfc_nvmet_xmt_fcp_op/cmp- req->done
+		 * lpfc_nvmet_xmt_fcp_op_cmp should free the allocated ctxp.
+		 * When we return from nvmet_fc_rcv_fcp_req, all relevant info
+		 * the NVME command / FC header is stored.
+		 * A buffer has already been reposted for this IO, so just free
+		 * the nvmebuf.
+		 */
+		rc = nvmet_fc_rcv_fcp_req(phba->targetport, &ctxp->ctx.fcp_req,
+					  payload, size);
+
+		/* Process FCP command */
+		if (rc == 0) {
+			atomic_inc(&tgtp->rcv_fcp_cmd_out);
+			nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf);
+			return;
+		}
+
+		atomic_inc(&tgtp->rcv_fcp_cmd_drop);
+		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+				"2582 FCP Drop IO x%x: err x%x: x%x x%x x%x\n",
+				ctxp->oxid, rc,
+				atomic_read(&tgtp->rcv_fcp_cmd_in),
+				atomic_read(&tgtp->rcv_fcp_cmd_out),
+				atomic_read(&tgtp->xmt_fcp_release));
+
+		lpfc_nvmet_defer_release(phba, ctxp);
+		lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, sid, oxid);
+		nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf);
+		return;
 	}
-	lpfc_rq_buf_free(phba, mp);
+	spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_wait_lock, iflag);
+
+	spin_lock_irqsave(&phba->sli4_hba.nvmet_io_lock, iflag);
+	list_add_tail(&ctx_buf->list,
+		      &phba->sli4_hba.lpfc_nvmet_ctx_list);
+	phba->sli4_hba.nvmet_ctx_cnt++;
+	spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_lock, iflag);
+#endif
 }
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
@@ -502,6 +591,7 @@ lpfc_nvmet_xmt_ls_rsp(struct nvmet_fc_target_port *tgtport,
 				"6150 LS Drop IO x%x: Prep\n",
 				ctxp->oxid);
 		lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+		atomic_inc(&nvmep->xmt_ls_abort);
 		lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp,
 						ctxp->sid, ctxp->oxid);
 		return -ENOMEM;
@@ -545,6 +635,7 @@ lpfc_nvmet_xmt_ls_rsp(struct nvmet_fc_target_port *tgtport,
 	lpfc_nlp_put(nvmewqeq->context1);
 
 	lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+	atomic_inc(&nvmep->xmt_ls_abort);
 	lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp, ctxp->sid, ctxp->oxid);
 	return -ENXIO;
 }
@@ -612,9 +703,9 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 	lpfc_nvmeio_data(phba, "NVMET FCP CMND: xri x%x op x%x len x%x\n",
 			 ctxp->oxid, rsp->op, rsp->rsplen);
 
+	ctxp->flag |= LPFC_NVMET_IO_INP;
 	rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, nvmewqeq);
 	if (rc == WQE_SUCCESS) {
-		ctxp->flag |= LPFC_NVMET_IO_INP;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 		if (!phba->ktime_on)
 			return 0;
@@ -692,6 +783,7 @@ static void
 lpfc_nvmet_xmt_fcp_release(struct nvmet_fc_target_port *tgtport,
 			   struct nvmefc_tgt_fcp_req *rsp)
 {
+	struct lpfc_nvmet_tgtport *lpfc_nvmep = tgtport->private;
 	struct lpfc_nvmet_rcv_ctx *ctxp =
 		container_of(rsp, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
 	struct lpfc_hba *phba = ctxp->phba;
@@ -710,10 +802,12 @@ lpfc_nvmet_xmt_fcp_release(struct nvmet_fc_target_port *tgtport,
 	lpfc_nvmeio_data(phba, "NVMET FCP FREE: xri x%x ste %d\n", ctxp->oxid,
 			 ctxp->state, 0);
 
+	atomic_inc(&lpfc_nvmep->xmt_fcp_release);
+
 	if (aborting)
 		return;
 
-	lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+	lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
 }
 
 static struct nvmet_fc_target_template lpfc_tgttemplate = {
@@ -734,17 +828,128 @@ static struct nvmet_fc_target_template lpfc_tgttemplate = {
 	.target_priv_sz = sizeof(struct lpfc_nvmet_tgtport),
 };
 
+void
+lpfc_nvmet_cleanup_io_context(struct lpfc_hba *phba)
+{
+	struct lpfc_nvmet_ctxbuf *ctx_buf, *next_ctx_buf;
+	unsigned long flags;
+
+	list_for_each_entry_safe(
+		ctx_buf, next_ctx_buf,
+		&phba->sli4_hba.lpfc_nvmet_ctx_list, list) {
+		spin_lock_irqsave(
+			&phba->sli4_hba.abts_nvme_buf_list_lock, flags);
+		list_del_init(&ctx_buf->list);
+		spin_unlock_irqrestore(
+			&phba->sli4_hba.abts_nvme_buf_list_lock, flags);
+		__lpfc_clear_active_sglq(phba,
+					 ctx_buf->sglq->sli4_lxritag);
+		ctx_buf->sglq->state = SGL_FREED;
+		ctx_buf->sglq->ndlp = NULL;
+
+		spin_lock_irqsave(&phba->sli4_hba.sgl_list_lock, flags);
+		list_add_tail(&ctx_buf->sglq->list,
+			      &phba->sli4_hba.lpfc_nvmet_sgl_list);
+		spin_unlock_irqrestore(&phba->sli4_hba.sgl_list_lock,
+				       flags);
+
+		lpfc_sli_release_iocbq(phba, ctx_buf->iocbq);
+		kfree(ctx_buf->context);
+	}
+}
+
+int
+lpfc_nvmet_setup_io_context(struct lpfc_hba *phba)
+{
+	struct lpfc_nvmet_ctxbuf *ctx_buf;
+	struct lpfc_iocbq *nvmewqe;
+	union lpfc_wqe128 *wqe;
+	int i;
+
+	lpfc_printf_log(phba, KERN_INFO, LOG_NVME,
+			"6403 Allocate NVMET resources for %d XRIs\n",
+			phba->sli4_hba.nvmet_xri_cnt);
+
+	/* For all nvmet xris, allocate resources needed to process a
+	 * received command on a per xri basis.
+	 */
+	for (i = 0; i < phba->sli4_hba.nvmet_xri_cnt; i++) {
+		ctx_buf = kzalloc(sizeof(*ctx_buf), GFP_KERNEL);
+		if (!ctx_buf) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+					"6404 Ran out of memory for NVMET\n");
+			return -ENOMEM;
+		}
+
+		ctx_buf->context = kzalloc(sizeof(*ctx_buf->context),
+					   GFP_KERNEL);
+		if (!ctx_buf->context) {
+			kfree(ctx_buf);
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+					"6405 Ran out of NVMET "
+					"context memory\n");
+			return -ENOMEM;
+		}
+		ctx_buf->context->ctxbuf = ctx_buf;
+
+		ctx_buf->iocbq = lpfc_sli_get_iocbq(phba);
+		if (!ctx_buf->iocbq) {
+			kfree(ctx_buf->context);
+			kfree(ctx_buf);
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+					"6406 Ran out of NVMET iocb/WQEs\n");
+			return -ENOMEM;
+		}
+		ctx_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
+		nvmewqe = ctx_buf->iocbq;
+		wqe = (union lpfc_wqe128 *)&nvmewqe->wqe;
+		/* Initialize WQE */
+		memset(wqe, 0, sizeof(union lpfc_wqe));
+		/* Word 7 */
+		bf_set(wqe_ct, &wqe->generic.wqe_com, SLI4_CT_RPI);
+		bf_set(wqe_class, &wqe->generic.wqe_com, CLASS3);
+		bf_set(wqe_pu, &wqe->generic.wqe_com, 1);
+		/* Word 10 */
+		bf_set(wqe_nvme, &wqe->fcp_tsend.wqe_com, 1);
+		bf_set(wqe_ebde_cnt, &wqe->generic.wqe_com, 0);
+		bf_set(wqe_qosd, &wqe->generic.wqe_com, 0);
+
+		ctx_buf->iocbq->context1 = NULL;
+		spin_lock(&phba->sli4_hba.sgl_list_lock);
+		ctx_buf->sglq = __lpfc_sli_get_nvmet_sglq(phba, ctx_buf->iocbq);
+		spin_unlock(&phba->sli4_hba.sgl_list_lock);
+		if (!ctx_buf->sglq) {
+			lpfc_sli_release_iocbq(phba, ctx_buf->iocbq);
+			kfree(ctx_buf->context);
+			kfree(ctx_buf);
+			lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
+					"6407 Ran out of NVMET XRIs\n");
+			return -ENOMEM;
+		}
+		spin_lock(&phba->sli4_hba.nvmet_io_lock);
+		list_add_tail(&ctx_buf->list,
+			      &phba->sli4_hba.lpfc_nvmet_ctx_list);
+		spin_unlock(&phba->sli4_hba.nvmet_io_lock);
+	}
+	phba->sli4_hba.nvmet_ctx_cnt = phba->sli4_hba.nvmet_xri_cnt;
+	return 0;
+}
+
 int
 lpfc_nvmet_create_targetport(struct lpfc_hba *phba)
 {
 	struct lpfc_vport  *vport = phba->pport;
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct nvmet_fc_port_info pinfo;
-	int error = 0;
+	int error;
 
 	if (phba->targetport)
 		return 0;
 
+	error = lpfc_nvmet_setup_io_context(phba);
+	if (error)
+		return error;
+
 	memset(&pinfo, 0, sizeof(struct nvmet_fc_port_info));
 	pinfo.node_name = wwn_to_u64(vport->fc_nodename.u.wwn);
 	pinfo.port_name = wwn_to_u64(vport->fc_portname.u.wwn);
@@ -772,13 +977,16 @@ lpfc_nvmet_create_targetport(struct lpfc_hba *phba)
 					     &phba->pcidev->dev,
 					     &phba->targetport);
 #else
-	error = -ENOMEM;
+	error = -ENOENT;
 #endif
 	if (error) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
 				"6025 Cannot register NVME targetport "
 				"x%x\n", error);
 		phba->targetport = NULL;
+
+		lpfc_nvmet_cleanup_io_context(phba);
+
 	} else {
 		tgtp = (struct lpfc_nvmet_tgtport *)
 			phba->targetport->private;
@@ -795,6 +1003,7 @@ lpfc_nvmet_create_targetport(struct lpfc_hba *phba)
 		atomic_set(&tgtp->rcv_ls_req_out, 0);
 		atomic_set(&tgtp->rcv_ls_req_drop, 0);
 		atomic_set(&tgtp->xmt_ls_abort, 0);
+		atomic_set(&tgtp->xmt_ls_abort_cmpl, 0);
 		atomic_set(&tgtp->xmt_ls_rsp, 0);
 		atomic_set(&tgtp->xmt_ls_drop, 0);
 		atomic_set(&tgtp->xmt_ls_rsp_error, 0);
@@ -802,18 +1011,21 @@ lpfc_nvmet_create_targetport(struct lpfc_hba *phba)
 		atomic_set(&tgtp->rcv_fcp_cmd_in, 0);
 		atomic_set(&tgtp->rcv_fcp_cmd_out, 0);
 		atomic_set(&tgtp->rcv_fcp_cmd_drop, 0);
-		atomic_set(&tgtp->xmt_fcp_abort, 0);
 		atomic_set(&tgtp->xmt_fcp_drop, 0);
 		atomic_set(&tgtp->xmt_fcp_read_rsp, 0);
 		atomic_set(&tgtp->xmt_fcp_read, 0);
 		atomic_set(&tgtp->xmt_fcp_write, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp, 0);
+		atomic_set(&tgtp->xmt_fcp_release, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp_cmpl, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp_error, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp_drop, 0);
+		atomic_set(&tgtp->xmt_fcp_abort, 0);
+		atomic_set(&tgtp->xmt_fcp_abort_cmpl, 0);
+		atomic_set(&tgtp->xmt_abort_unsol, 0);
+		atomic_set(&tgtp->xmt_abort_sol, 0);
 		atomic_set(&tgtp->xmt_abort_rsp, 0);
 		atomic_set(&tgtp->xmt_abort_rsp_error, 0);
-		atomic_set(&tgtp->xmt_abort_cmpl, 0);
 	}
 	return error;
 }
@@ -864,7 +1076,7 @@ lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
 	list_for_each_entry_safe(ctxp, next_ctxp,
 				 &phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
 				 list) {
-		if (ctxp->rqb_buffer->sglq->sli4_xritag != xri)
+		if (ctxp->ctxbuf->sglq->sli4_xritag != xri)
 			continue;
 
 		/* Check if we already received a free context call
@@ -885,7 +1097,7 @@ lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
 		    (ndlp->nlp_state == NLP_STE_UNMAPPED_NODE ||
 		     ndlp->nlp_state == NLP_STE_MAPPED_NODE)) {
 			lpfc_set_rrq_active(phba, ndlp,
-				ctxp->rqb_buffer->sglq->sli4_lxritag,
+				ctxp->ctxbuf->sglq->sli4_lxritag,
 				rxid, 1);
 			lpfc_sli4_abts_err_handler(phba, ndlp, axri);
 		}
@@ -894,8 +1106,8 @@ lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
 				"6318 XB aborted %x flg x%x (%x)\n",
 				ctxp->oxid, ctxp->flag, released);
 		if (released)
-			lpfc_nvmet_rq_post(phba, ctxp,
-					   &ctxp->rqb_buffer->hbuf);
+			lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
+
 		if (rrq_empty)
 			lpfc_worker_wake_up(phba);
 		return;
@@ -923,7 +1135,7 @@ lpfc_nvmet_rcv_unsol_abort(struct lpfc_vport *vport,
 	list_for_each_entry_safe(ctxp, next_ctxp,
 				 &phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
 				 list) {
-		if (ctxp->rqb_buffer->sglq->sli4_xritag != xri)
+		if (ctxp->ctxbuf->sglq->sli4_xritag != xri)
 			continue;
 
 		spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
@@ -975,6 +1187,7 @@ lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba)
 		init_completion(&tgtp->tport_unreg_done);
 		nvmet_fc_unregister_targetport(phba->targetport);
 		wait_for_completion_timeout(&tgtp->tport_unreg_done, 5);
+		lpfc_nvmet_cleanup_io_context(phba);
 	}
 	phba->targetport = NULL;
 #endif
@@ -1010,6 +1223,7 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		oxid = 0;
 		size = 0;
 		sid = 0;
+		ctxp = NULL;
 		goto dropit;
 	}
 
@@ -1104,39 +1318,71 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 	struct lpfc_nvmet_rcv_ctx *ctxp;
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct fc_frame_header *fc_hdr;
+	struct lpfc_nvmet_ctxbuf *ctx_buf;
 	uint32_t *payload;
-	uint32_t size, oxid, sid, rc;
+	uint32_t size, oxid, sid, rc, qno;
+	unsigned long iflag;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	uint32_t id;
 #endif
 
+	ctx_buf = NULL;
 	if (!nvmebuf || !phba->targetport) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-				"6157 FCP Drop IO\n");
+				"6157 NVMET FCP Drop IO\n");
 		oxid = 0;
 		size = 0;
 		sid = 0;
+		ctxp = NULL;
 		goto dropit;
 	}
 
+	spin_lock_irqsave(&phba->sli4_hba.nvmet_io_lock, iflag);
+	if (phba->sli4_hba.nvmet_ctx_cnt) {
+		list_remove_head(&phba->sli4_hba.lpfc_nvmet_ctx_list,
+				 ctx_buf, struct lpfc_nvmet_ctxbuf, list);
+		phba->sli4_hba.nvmet_ctx_cnt--;
+	}
+	spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_lock, iflag);
 
-	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
-	payload = (uint32_t *)(nvmebuf->dbuf.virt);
 	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
-	size = nvmebuf->bytes_recv;
 	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
-	sid = sli4_sid_from_fc_hdr(fc_hdr);
+	size = nvmebuf->bytes_recv;
 
-	ctxp = (struct lpfc_nvmet_rcv_ctx *)nvmebuf->context;
-	if (ctxp == NULL) {
-		atomic_inc(&tgtp->rcv_fcp_cmd_drop);
-		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-				"6158 FCP Drop IO x%x: Alloc\n",
-				oxid);
-		lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
-		/* Cannot send ABTS without context */
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	if (phba->cpucheck_on & LPFC_CHECK_NVMET_RCV) {
+		id = smp_processor_id();
+		if (id < LPFC_CHECK_CPU_CNT)
+			phba->cpucheck_rcv_io[id]++;
+	}
+#endif
+
+	lpfc_nvmeio_data(phba, "NVMET FCP  RCV: xri x%x sz %d CPU %02x\n",
+			 oxid, size, smp_processor_id());
+
+	if (!ctx_buf) {
+		/* Queue this NVME IO to process later */
+		spin_lock_irqsave(&phba->sli4_hba.nvmet_io_wait_lock, iflag);
+		list_add_tail(&nvmebuf->hbuf.list,
+			      &phba->sli4_hba.lpfc_nvmet_io_wait_list);
+		phba->sli4_hba.nvmet_io_wait_cnt++;
+		phba->sli4_hba.nvmet_io_wait_total++;
+		spin_unlock_irqrestore(&phba->sli4_hba.nvmet_io_wait_lock,
+				       iflag);
+
+		/* Post a brand new DMA buffer to RQ */
+		qno = nvmebuf->idx;
+		lpfc_post_rq_buffer(
+			phba, phba->sli4_hba.nvmet_mrq_hdr[qno],
+			phba->sli4_hba.nvmet_mrq_data[qno], 1, qno);
 		return;
 	}
+
+	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+	payload = (uint32_t *)(nvmebuf->dbuf.virt);
+	sid = sli4_sid_from_fc_hdr(fc_hdr);
+
+	ctxp = (struct lpfc_nvmet_rcv_ctx *)ctx_buf->context;
 	memset(ctxp, 0, sizeof(ctxp->ctx));
 	ctxp->wqeq = NULL;
 	ctxp->txrdy = NULL;
@@ -1146,9 +1392,9 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 	ctxp->oxid = oxid;
 	ctxp->sid = sid;
 	ctxp->state = LPFC_NVMET_STE_RCV;
-	ctxp->rqb_buffer = nvmebuf;
 	ctxp->entry_cnt = 1;
 	ctxp->flag = 0;
+	ctxp->ctxbuf = ctx_buf;
 	spin_lock_init(&ctxp->ctxlock);
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
@@ -1164,22 +1410,16 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 		ctxp->ts_isr_status = 0;
 		ctxp->ts_status_nvme = 0;
 	}
-
-	if (phba->cpucheck_on & LPFC_CHECK_NVMET_RCV) {
-		id = smp_processor_id();
-		if (id < LPFC_CHECK_CPU_CNT)
-			phba->cpucheck_rcv_io[id]++;
-	}
 #endif
 
-	lpfc_nvmeio_data(phba, "NVMET FCP  RCV: xri x%x sz %d CPU %02x\n",
-			 oxid, size, smp_processor_id());
-
 	atomic_inc(&tgtp->rcv_fcp_cmd_in);
 	/*
 	 * The calling sequence should be:
 	 * nvmet_fc_rcv_fcp_req -> lpfc_nvmet_xmt_fcp_op/cmp -> req->done
 	 * lpfc_nvmet_xmt_fcp_op_cmp should free the allocated ctxp.
+	 * When we return from nvmet_fc_rcv_fcp_req, all relevant info in
+	 * the NVME command / FC header is stored, so we are free to repost
+	 * the buffer.
 	 */
 	rc = nvmet_fc_rcv_fcp_req(phba->targetport, &ctxp->ctx.fcp_req,
 				  payload, size);
@@ -1187,26 +1427,32 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 	/* Process FCP command */
 	if (rc == 0) {
 		atomic_inc(&tgtp->rcv_fcp_cmd_out);
+		lpfc_rq_buf_free(phba, &nvmebuf->hbuf); /* repost */
 		return;
 	}
 
 	atomic_inc(&tgtp->rcv_fcp_cmd_drop);
 	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-			"6159 FCP Drop IO x%x: err x%x\n",
-			ctxp->oxid, rc);
+			"6159 FCP Drop IO x%x: err x%x: x%x x%x x%x\n",
+			ctxp->oxid, rc,
+			atomic_read(&tgtp->rcv_fcp_cmd_in),
+			atomic_read(&tgtp->rcv_fcp_cmd_out),
+			atomic_read(&tgtp->xmt_fcp_release));
 dropit:
 	lpfc_nvmeio_data(phba, "NVMET FCP DROP: xri x%x sz %d from %06x\n",
 			 oxid, size, sid);
 	if (oxid) {
+		lpfc_nvmet_defer_release(phba, ctxp);
 		lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, sid, oxid);
+		lpfc_rq_buf_free(phba, &nvmebuf->hbuf); /* repost */
 		return;
 	}
 
-	if (nvmebuf) {
-		nvmebuf->iocbq->hba_wqidx = 0;
-		/* We assume a rcv'ed cmd ALWAYs fits into 1 buffer */
-		lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
-	}
+	if (ctx_buf)
+		lpfc_nvmet_ctxbuf_post(phba, ctx_buf);
+
+	if (nvmebuf)
+		lpfc_rq_buf_free(phba, &nvmebuf->hbuf); /* repost */
 #endif
 }
 
@@ -1258,7 +1504,7 @@ lpfc_nvmet_unsol_fcp_event(struct lpfc_hba *phba,
 			   uint64_t isr_timestamp)
 {
 	if (phba->nvmet_support == 0) {
-		lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
+		lpfc_rq_buf_free(phba, &nvmebuf->hbuf);
 		return;
 	}
 	lpfc_nvmet_unsol_fcp_buffer(phba, pring, nvmebuf,
@@ -1459,7 +1705,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 	nvmewqe = ctxp->wqeq;
 	if (nvmewqe == NULL) {
 		/* Allocate buffer for  command wqe */
-		nvmewqe = ctxp->rqb_buffer->iocbq;
+		nvmewqe = ctxp->ctxbuf->iocbq;
 		if (nvmewqe == NULL) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 					"6110 lpfc_nvmet_prep_fcp_wqe: No "
@@ -1486,7 +1732,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 		return NULL;
 	}
 
-	sgl  = (struct sli4_sge *)ctxp->rqb_buffer->sglq->sgl;
+	sgl  = (struct sli4_sge *)ctxp->ctxbuf->sglq->sgl;
 	switch (rsp->op) {
 	case NVMET_FCOP_READDATA:
 	case NVMET_FCOP_READDATA_RSP:
@@ -1811,7 +2057,8 @@ lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	result = wcqe->parameter;
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
-	atomic_inc(&tgtp->xmt_abort_cmpl);
+	if (ctxp->flag & LPFC_NVMET_ABORT_OP)
+		atomic_inc(&tgtp->xmt_fcp_abort_cmpl);
 
 	ctxp->state = LPFC_NVMET_STE_DONE;
 
@@ -1826,6 +2073,7 @@ lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	}
 	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+	atomic_inc(&tgtp->xmt_abort_rsp);
 
 	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
 			"6165 ABORT cmpl: xri x%x flg x%x (%d) "
@@ -1834,15 +2082,16 @@ lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 			wcqe->word0, wcqe->total_data_placed,
 			result, wcqe->word3);
 
+	cmdwqe->context2 = NULL;
+	cmdwqe->context3 = NULL;
 	/*
 	 * if transport has released ctx, then can reuse it. Otherwise,
 	 * will be recycled by transport release call.
 	 */
 	if (released)
-		lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+		lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
 
-	cmdwqe->context2 = NULL;
-	cmdwqe->context3 = NULL;
+	/* This is the iocbq for the abort, not the command */
 	lpfc_sli_release_iocbq(phba, cmdwqe);
 
 	/* Since iaab/iaar are NOT set, there is no work left.
@@ -1876,7 +2125,8 @@ lpfc_nvmet_unsol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	result = wcqe->parameter;
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
-	atomic_inc(&tgtp->xmt_abort_cmpl);
+	if (ctxp->flag & LPFC_NVMET_ABORT_OP)
+		atomic_inc(&tgtp->xmt_fcp_abort_cmpl);
 
 	if (!ctxp) {
 		/* if context is clear, related io alrady complete */
@@ -1906,6 +2156,7 @@ lpfc_nvmet_unsol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	}
 	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+	atomic_inc(&tgtp->xmt_abort_rsp);
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
 			"6316 ABTS cmpl xri x%x flg x%x (%x) "
@@ -1913,15 +2164,15 @@ lpfc_nvmet_unsol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 			ctxp->oxid, ctxp->flag, released,
 			wcqe->word0, wcqe->total_data_placed,
 			result, wcqe->word3);
+
+	cmdwqe->context2 = NULL;
+	cmdwqe->context3 = NULL;
 	/*
 	 * if transport has released ctx, then can reuse it. Otherwise,
 	 * will be recycled by transport release call.
 	 */
 	if (released)
-		lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
-
-	cmdwqe->context2 = NULL;
-	cmdwqe->context3 = NULL;
+		lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
 
 	/* Since iaab/iaar are NOT set, there is no work left.
 	 * For LPFC_NVMET_XBUSY, lpfc_sli4_nvmet_xri_aborted
@@ -1952,7 +2203,7 @@ lpfc_nvmet_xmt_ls_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	result = wcqe->parameter;
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
-	atomic_inc(&tgtp->xmt_abort_cmpl);
+	atomic_inc(&tgtp->xmt_ls_abort_cmpl);
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
 			"6083 Abort cmpl: ctx %p WCQE: %08x %08x %08x %08x\n",
@@ -1983,10 +2234,6 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba,
 			sid, xri, ctxp->wqeq->sli4_xritag);
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
-	if (!ctxp->wqeq) {
-		ctxp->wqeq = ctxp->rqb_buffer->iocbq;
-		ctxp->wqeq->hba_wqidx = 0;
-	}
 
 	ndlp = lpfc_findnode_did(phba->pport, sid);
 	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp) ||
@@ -2082,7 +2329,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 	if (!ctxp->wqeq) {
-		ctxp->wqeq = ctxp->rqb_buffer->iocbq;
+		ctxp->wqeq = ctxp->ctxbuf->iocbq;
 		ctxp->wqeq->hba_wqidx = 0;
 	}
 
@@ -2103,6 +2350,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	/* Issue ABTS for this WQE based on iotag */
 	ctxp->abort_wqeq = lpfc_sli_get_iocbq(phba);
 	if (!ctxp->abort_wqeq) {
+		atomic_inc(&tgtp->xmt_abort_rsp_error);
 		lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
 				"6161 ABORT failed: No wqeqs: "
 				"xri: x%x\n", ctxp->oxid);
@@ -2127,6 +2375,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	/* driver queued commands are in process of being flushed */
 	if (phba->hba_flag & HBA_NVME_IOQ_FLUSH) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
+		atomic_inc(&tgtp->xmt_abort_rsp_error);
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
 				"6163 Driver in reset cleanup - flushing "
 				"NVME Req now. hba_flag x%x oxid x%x\n",
@@ -2139,6 +2388,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	/* Outstanding abort is in progress */
 	if (abts_wqeq->iocb_flag & LPFC_DRIVER_ABORTED) {
 		spin_unlock_irqrestore(&phba->hbalock, flags);
+		atomic_inc(&tgtp->xmt_abort_rsp_error);
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
 				"6164 Outstanding NVME I/O Abort Request "
 				"still pending on oxid x%x\n",
@@ -2189,9 +2439,12 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
 	abts_wqeq->context2 = ctxp;
 	rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_wqeq);
 	spin_unlock_irqrestore(&phba->hbalock, flags);
-	if (rc == WQE_SUCCESS)
+	if (rc == WQE_SUCCESS) {
+		atomic_inc(&tgtp->xmt_abort_sol);
 		return 0;
+	}
 
+	atomic_inc(&tgtp->xmt_abort_rsp_error);
 	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 	lpfc_sli_release_iocbq(phba, abts_wqeq);
 	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
@@ -2214,7 +2467,7 @@ lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *phba,
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 	if (!ctxp->wqeq) {
-		ctxp->wqeq = ctxp->rqb_buffer->iocbq;
+		ctxp->wqeq = ctxp->ctxbuf->iocbq;
 		ctxp->wqeq->hba_wqidx = 0;
 	}
 
@@ -2230,11 +2483,11 @@ lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *phba,
 	rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_wqeq);
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 	if (rc == WQE_SUCCESS) {
-		atomic_inc(&tgtp->xmt_abort_rsp);
 		return 0;
 	}
 
 aerr:
+	atomic_inc(&tgtp->xmt_abort_rsp_error);
 	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
 	atomic_inc(&tgtp->xmt_abort_rsp_error);
 	lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
@@ -2269,6 +2522,7 @@ lpfc_nvmet_unsol_ls_issue_abort(struct lpfc_hba *phba,
 	}
 	abts_wqeq = ctxp->wqeq;
 	wqe_abts = &abts_wqeq->wqe;
+
 	lpfc_nvmet_unsol_issue_abort(phba, ctxp, sid, xri);
 
 	spin_lock_irqsave(&phba->hbalock, flags);
@@ -2278,7 +2532,7 @@ lpfc_nvmet_unsol_ls_issue_abort(struct lpfc_hba *phba,
 	rc = lpfc_sli4_issue_wqe(phba, LPFC_ELS_RING, abts_wqeq);
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 	if (rc == WQE_SUCCESS) {
-		atomic_inc(&tgtp->xmt_abort_rsp);
+		atomic_inc(&tgtp->xmt_abort_unsol);
 		return 0;
 	}
 
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h
index 128759fe6650..6eb2f5d8d4ed 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.h
+++ b/drivers/scsi/lpfc/lpfc_nvmet.h
@@ -22,6 +22,7 @@
  ********************************************************************/
 
 #define LPFC_NVMET_DEFAULT_SEGS		(64 + 1)	/* 256K IOs */
+#define LPFC_NVMET_RQE_DEF_COUNT	512
 #define LPFC_NVMET_SUCCESS_LEN	12
 
 /* Used for NVME Target */
@@ -34,6 +35,7 @@ struct lpfc_nvmet_tgtport {
 	atomic_t rcv_ls_req_out;
 	atomic_t rcv_ls_req_drop;
 	atomic_t xmt_ls_abort;
+	atomic_t xmt_ls_abort_cmpl;
 
 	/* Stats counters - lpfc_nvmet_xmt_ls_rsp */
 	atomic_t xmt_ls_rsp;
@@ -47,9 +49,9 @@ struct lpfc_nvmet_tgtport {
 	atomic_t rcv_fcp_cmd_in;
 	atomic_t rcv_fcp_cmd_out;
 	atomic_t rcv_fcp_cmd_drop;
+	atomic_t xmt_fcp_release;
 
 	/* Stats counters - lpfc_nvmet_xmt_fcp_op */
-	atomic_t xmt_fcp_abort;
 	atomic_t xmt_fcp_drop;
 	atomic_t xmt_fcp_read_rsp;
 	atomic_t xmt_fcp_read;
@@ -62,12 +64,13 @@ struct lpfc_nvmet_tgtport {
 	atomic_t xmt_fcp_rsp_drop;
 
 
-	/* Stats counters - lpfc_nvmet_unsol_issue_abort */
+	/* Stats counters - lpfc_nvmet_xmt_fcp_abort */
+	atomic_t xmt_fcp_abort;
+	atomic_t xmt_fcp_abort_cmpl;
+	atomic_t xmt_abort_sol;
+	atomic_t xmt_abort_unsol;
 	atomic_t xmt_abort_rsp;
 	atomic_t xmt_abort_rsp_error;
-
-	/* Stats counters - lpfc_nvmet_xmt_abort_cmp */
-	atomic_t xmt_abort_cmpl;
 };
 
 struct lpfc_nvmet_rcv_ctx {
@@ -103,6 +106,7 @@ struct lpfc_nvmet_rcv_ctx {
 #define LPFC_NVMET_CTX_RLS		0x8  /* ctx free requested */
 #define LPFC_NVMET_ABTS_RCV		0x10  /* ABTS received on exchange */
 	struct rqb_dmabuf *rqb_buffer;
+	struct lpfc_nvmet_ctxbuf *ctxbuf;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	uint64_t ts_isr_cmd;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 2a4fc00dfa9b..d6b184839bc2 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -74,6 +74,8 @@ static struct lpfc_iocbq *lpfc_sli4_els_wcqe_to_rspiocbq(struct lpfc_hba *,
 							 struct lpfc_iocbq *);
 static void lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *,
 				      struct hbq_dmabuf *);
+static void lpfc_sli4_handle_mds_loopback(struct lpfc_vport *vport,
+					  struct hbq_dmabuf *dmabuf);
 static int lpfc_sli4_fp_handle_cqe(struct lpfc_hba *, struct lpfc_queue *,
 				    struct lpfc_cqe *);
 static int lpfc_sli4_post_sgl_list(struct lpfc_hba *, struct list_head *,
@@ -479,22 +481,23 @@ lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq,
 	if (unlikely(!hq) || unlikely(!dq))
 		return -ENOMEM;
 	put_index = hq->host_index;
-	temp_hrqe = hq->qe[hq->host_index].rqe;
+	temp_hrqe = hq->qe[put_index].rqe;
 	temp_drqe = dq->qe[dq->host_index].rqe;
 
 	if (hq->type != LPFC_HRQ || dq->type != LPFC_DRQ)
 		return -EINVAL;
-	if (hq->host_index != dq->host_index)
+	if (put_index != dq->host_index)
 		return -EINVAL;
 	/* If the host has not yet processed the next entry then we are done */
-	if (((hq->host_index + 1) % hq->entry_count) == hq->hba_index)
+	if (((put_index + 1) % hq->entry_count) == hq->hba_index)
 		return -EBUSY;
 	lpfc_sli_pcimem_bcopy(hrqe, temp_hrqe, hq->entry_size);
 	lpfc_sli_pcimem_bcopy(drqe, temp_drqe, dq->entry_size);
 
 	/* Update the host index to point to the next slot */
-	hq->host_index = ((hq->host_index + 1) % hq->entry_count);
+	hq->host_index = ((put_index + 1) % hq->entry_count);
 	dq->host_index = ((dq->host_index + 1) % dq->entry_count);
+	hq->RQ_buf_posted++;
 
 	/* Ring The Header Receive Queue Doorbell */
 	if (!(hq->host_index % hq->entry_repost)) {
@@ -5906,7 +5909,7 @@ lpfc_set_features(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox,
 		bf_set(lpfc_mbx_set_feature_mds,
 		       &mbox->u.mqe.un.set_feature, 1);
 		bf_set(lpfc_mbx_set_feature_mds_deep_loopbk,
-		       &mbox->u.mqe.un.set_feature, 0);
+		       &mbox->u.mqe.un.set_feature, 1);
 		mbox->u.mqe.un.set_feature.feature = LPFC_SET_MDS_DIAGS;
 		mbox->u.mqe.un.set_feature.param_len = 8;
 		break;
@@ -6512,6 +6515,50 @@ lpfc_set_host_data(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
 		 (phba->hba_flag & HBA_FCOE_MODE) ? "FCoE" : "FC");
 }
 
+int
+lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq,
+		    struct lpfc_queue *drq, int count, int idx)
+{
+	int rc, i;
+	struct lpfc_rqe hrqe;
+	struct lpfc_rqe drqe;
+	struct lpfc_rqb *rqbp;
+	struct rqb_dmabuf *rqb_buffer;
+	LIST_HEAD(rqb_buf_list);
+
+	rqbp = hrq->rqbp;
+	for (i = 0; i < count; i++) {
+		/* IF RQ is already full, don't bother */
+		if (rqbp->buffer_count + i >= rqbp->entry_count - 1)
+			break;
+		rqb_buffer = rqbp->rqb_alloc_buffer(phba);
+		if (!rqb_buffer)
+			break;
+		rqb_buffer->hrq = hrq;
+		rqb_buffer->drq = drq;
+		rqb_buffer->idx = idx;
+		list_add_tail(&rqb_buffer->hbuf.list, &rqb_buf_list);
+	}
+	while (!list_empty(&rqb_buf_list)) {
+		list_remove_head(&rqb_buf_list, rqb_buffer, struct rqb_dmabuf,
+				 hbuf.list);
+
+		hrqe.address_lo = putPaddrLow(rqb_buffer->hbuf.phys);
+		hrqe.address_hi = putPaddrHigh(rqb_buffer->hbuf.phys);
+		drqe.address_lo = putPaddrLow(rqb_buffer->dbuf.phys);
+		drqe.address_hi = putPaddrHigh(rqb_buffer->dbuf.phys);
+		rc = lpfc_sli4_rq_put(hrq, drq, &hrqe, &drqe);
+		if (rc < 0) {
+			rqbp->rqb_free_buffer(phba, rqb_buffer);
+		} else {
+			list_add_tail(&rqb_buffer->hbuf.list,
+				      &rqbp->rqb_buffer_list);
+			rqbp->buffer_count++;
+		}
+	}
+	return 1;
+}
+
 /**
  * lpfc_sli4_hba_setup - SLI4 device initialization PCI function
  * @phba: Pointer to HBA context object.
@@ -6524,7 +6571,7 @@ lpfc_set_host_data(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
 int
 lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 {
-	int rc, i;
+	int rc, i, cnt;
 	LPFC_MBOXQ_t *mboxq;
 	struct lpfc_mqe *mqe;
 	uint8_t *vpd;
@@ -6875,6 +6922,21 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 			goto out_destroy_queue;
 		}
 		phba->sli4_hba.nvmet_xri_cnt = rc;
+
+		cnt = phba->cfg_iocb_cnt * 1024;
+		/* We need 1 iocbq for every SGL, for IO processing */
+		cnt += phba->sli4_hba.nvmet_xri_cnt;
+		/* Initialize and populate the iocb list per host */
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+				"2821 initialize iocb list %d total %d\n",
+				phba->cfg_iocb_cnt, cnt);
+		rc = lpfc_init_iocb_list(phba, cnt);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"1413 Failed to init iocb list.\n");
+			goto out_destroy_queue;
+		}
+
 		lpfc_nvmet_create_targetport(phba);
 	} else {
 		/* update host scsi xri-sgl sizes and mappings */
@@ -6894,28 +6956,34 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 					"and mapping: %d\n", rc);
 			goto out_destroy_queue;
 		}
+
+		cnt = phba->cfg_iocb_cnt * 1024;
+		/* Initialize and populate the iocb list per host */
+		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
+				"2820 initialize iocb list %d total %d\n",
+				phba->cfg_iocb_cnt, cnt);
+		rc = lpfc_init_iocb_list(phba, cnt);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+					"6301 Failed to init iocb list.\n");
+			goto out_destroy_queue;
+		}
 	}
 
 	if (phba->nvmet_support && phba->cfg_nvmet_mrq) {
-
 		/* Post initial buffers to all RQs created */
 		for (i = 0; i < phba->cfg_nvmet_mrq; i++) {
 			rqbp = phba->sli4_hba.nvmet_mrq_hdr[i]->rqbp;
 			INIT_LIST_HEAD(&rqbp->rqb_buffer_list);
 			rqbp->rqb_alloc_buffer = lpfc_sli4_nvmet_alloc;
 			rqbp->rqb_free_buffer = lpfc_sli4_nvmet_free;
-			rqbp->entry_count = 256;
+			rqbp->entry_count = LPFC_NVMET_RQE_DEF_COUNT;
 			rqbp->buffer_count = 0;
 
-			/* Divide by 4 and round down to multiple of 16 */
-			rc = (phba->cfg_nvmet_mrq_post >> 2) & 0xfff8;
-			phba->sli4_hba.nvmet_mrq_hdr[i]->entry_repost = rc;
-			phba->sli4_hba.nvmet_mrq_data[i]->entry_repost = rc;
-
 			lpfc_post_rq_buffer(
 				phba, phba->sli4_hba.nvmet_mrq_hdr[i],
 				phba->sli4_hba.nvmet_mrq_data[i],
-				phba->cfg_nvmet_mrq_post);
+				LPFC_NVMET_RQE_DEF_COUNT, i);
 		}
 	}
 
@@ -7082,6 +7150,7 @@ out_unset_queue:
 	/* Unset all the queues set up in this routine when error out */
 	lpfc_sli4_queue_unset(phba);
 out_destroy_queue:
+	lpfc_free_iocb_list(phba);
 	lpfc_sli4_queue_destroy(phba);
 out_stop_timers:
 	lpfc_stop_hba_timers(phba);
@@ -8621,8 +8690,11 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		memset(wqe, 0, sizeof(union lpfc_wqe128));
 	/* Some of the fields are in the right position already */
 	memcpy(wqe, &iocbq->iocb, sizeof(union lpfc_wqe));
-	wqe->generic.wqe_com.word7 = 0; /* The ct field has moved so reset */
-	wqe->generic.wqe_com.word10 = 0;
+	if (iocbq->iocb.ulpCommand != CMD_SEND_FRAME) {
+		/* The ct field has moved so reset */
+		wqe->generic.wqe_com.word7 = 0;
+		wqe->generic.wqe_com.word10 = 0;
+	}
 
 	abort_tag = (uint32_t) iocbq->iotag;
 	xritag = iocbq->sli4_xritag;
@@ -9116,6 +9188,10 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		}
 
 		break;
+	case CMD_SEND_FRAME:
+		bf_set(wqe_xri_tag, &wqe->generic.wqe_com, xritag);
+		bf_set(wqe_reqtag, &wqe->generic.wqe_com, iocbq->iotag);
+		return 0;
 	case CMD_XRI_ABORTED_CX:
 	case CMD_CREATE_XRI_CR: /* Do we expect to use this? */
 	case CMD_IOCB_FCP_IBIDIR64_CR: /* bidirectional xfer */
@@ -12788,6 +12864,7 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 	struct fc_frame_header *fc_hdr;
 	struct lpfc_queue *hrq = phba->sli4_hba.hdr_rq;
 	struct lpfc_queue *drq = phba->sli4_hba.dat_rq;
+	struct lpfc_nvmet_tgtport *tgtp;
 	struct hbq_dmabuf *dma_buf;
 	uint32_t status, rq_id;
 	unsigned long iflags;
@@ -12808,7 +12885,6 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 	case FC_STATUS_RQ_BUF_LEN_EXCEEDED:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 				"2537 Receive Frame Truncated!!\n");
-		hrq->RQ_buf_trunc++;
 	case FC_STATUS_RQ_SUCCESS:
 		lpfc_sli4_rq_release(hrq, drq);
 		spin_lock_irqsave(&phba->hbalock, iflags);
@@ -12819,6 +12895,7 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 			goto out;
 		}
 		hrq->RQ_rcv_buf++;
+		hrq->RQ_buf_posted--;
 		memcpy(&dma_buf->cq_event.cqe.rcqe_cmpl, rcqe, sizeof(*rcqe));
 
 		/* If a NVME LS event (type 0x28), treat it as Fast path */
@@ -12832,8 +12909,21 @@ lpfc_sli4_sp_handle_rcqe(struct lpfc_hba *phba, struct lpfc_rcqe *rcqe)
 		spin_unlock_irqrestore(&phba->hbalock, iflags);
 		workposted = true;
 		break;
-	case FC_STATUS_INSUFF_BUF_NEED_BUF:
 	case FC_STATUS_INSUFF_BUF_FRM_DISC:
+		if (phba->nvmet_support) {
+			tgtp = phba->targetport->private;
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI | LOG_NVME,
+					"6402 RQE Error x%x, posted %d err_cnt "
+					"%d: %x %x %x\n",
+					status, hrq->RQ_buf_posted,
+					hrq->RQ_no_posted_buf,
+					atomic_read(&tgtp->rcv_fcp_cmd_in),
+					atomic_read(&tgtp->rcv_fcp_cmd_out),
+					atomic_read(&tgtp->xmt_fcp_release));
+		}
+		/* fallthrough */
+
+	case FC_STATUS_INSUFF_BUF_NEED_BUF:
 		hrq->RQ_no_posted_buf++;
 		/* Post more buffers if possible */
 		spin_lock_irqsave(&phba->hbalock, iflags);
@@ -12951,7 +13041,7 @@ lpfc_sli4_sp_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 		while ((cqe = lpfc_sli4_cq_get(cq))) {
 			workposted |= lpfc_sli4_sp_handle_mcqe(phba, cqe);
 			if (!(++ecount % cq->entry_repost))
-				lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+				break;
 			cq->CQ_mbox++;
 		}
 		break;
@@ -12965,7 +13055,7 @@ lpfc_sli4_sp_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe,
 				workposted |= lpfc_sli4_sp_handle_cqe(phba, cq,
 								      cqe);
 			if (!(++ecount % cq->entry_repost))
-				lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+				break;
 		}
 
 		/* Track the max number of CQEs processed in 1 EQ */
@@ -13135,6 +13225,7 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	struct lpfc_queue *drq;
 	struct rqb_dmabuf *dma_buf;
 	struct fc_frame_header *fc_hdr;
+	struct lpfc_nvmet_tgtport *tgtp;
 	uint32_t status, rq_id;
 	unsigned long iflags;
 	uint32_t fctl, idx;
@@ -13165,8 +13256,6 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	case FC_STATUS_RQ_BUF_LEN_EXCEEDED:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 				"6126 Receive Frame Truncated!!\n");
-		hrq->RQ_buf_trunc++;
-		break;
 	case FC_STATUS_RQ_SUCCESS:
 		lpfc_sli4_rq_release(hrq, drq);
 		spin_lock_irqsave(&phba->hbalock, iflags);
@@ -13178,6 +13267,7 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 		}
 		spin_unlock_irqrestore(&phba->hbalock, iflags);
 		hrq->RQ_rcv_buf++;
+		hrq->RQ_buf_posted--;
 		fc_hdr = (struct fc_frame_header *)dma_buf->hbuf.virt;
 
 		/* Just some basic sanity checks on FCP Command frame */
@@ -13200,14 +13290,23 @@ lpfc_sli4_nvmet_handle_rcqe(struct lpfc_hba *phba, struct lpfc_queue *cq,
 drop:
 		lpfc_in_buf_free(phba, &dma_buf->dbuf);
 		break;
-	case FC_STATUS_INSUFF_BUF_NEED_BUF:
 	case FC_STATUS_INSUFF_BUF_FRM_DISC:
+		if (phba->nvmet_support) {
+			tgtp = phba->targetport->private;
+			lpfc_printf_log(phba, KERN_ERR, LOG_SLI | LOG_NVME,
+					"6401 RQE Error x%x, posted %d err_cnt "
+					"%d: %x %x %x\n",
+					status, hrq->RQ_buf_posted,
+					hrq->RQ_no_posted_buf,
+					atomic_read(&tgtp->rcv_fcp_cmd_in),
+					atomic_read(&tgtp->rcv_fcp_cmd_out),
+					atomic_read(&tgtp->xmt_fcp_release));
+		}
+		/* fallthrough */
+
+	case FC_STATUS_INSUFF_BUF_NEED_BUF:
 		hrq->RQ_no_posted_buf++;
 		/* Post more buffers if possible */
-		spin_lock_irqsave(&phba->hbalock, iflags);
-		phba->hba_flag |= HBA_POST_RECEIVE_BUFFER;
-		spin_unlock_irqrestore(&phba->hbalock, iflags);
-		workposted = true;
 		break;
 	}
 out:
@@ -13361,7 +13460,7 @@ process_cq:
 	while ((cqe = lpfc_sli4_cq_get(cq))) {
 		workposted |= lpfc_sli4_fp_handle_cqe(phba, cq, cqe);
 		if (!(++ecount % cq->entry_repost))
-			lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+			break;
 	}
 
 	/* Track the max number of CQEs processed in 1 EQ */
@@ -13452,7 +13551,7 @@ lpfc_sli4_fof_handle_eqe(struct lpfc_hba *phba, struct lpfc_eqe *eqe)
 	while ((cqe = lpfc_sli4_cq_get(cq))) {
 		workposted |= lpfc_sli4_fp_handle_cqe(phba, cq, cqe);
 		if (!(++ecount % cq->entry_repost))
-			lpfc_sli4_cq_release(cq, LPFC_QUEUE_NOARM);
+			break;
 	}
 
 	/* Track the max number of CQEs processed in 1 EQ */
@@ -13534,7 +13633,7 @@ lpfc_sli4_fof_intr_handler(int irq, void *dev_id)
 	while ((eqe = lpfc_sli4_eq_get(eq))) {
 		lpfc_sli4_fof_handle_eqe(phba, eqe);
 		if (!(++ecount % eq->entry_repost))
-			lpfc_sli4_eq_release(eq, LPFC_QUEUE_NOARM);
+			break;
 		eq->EQ_processed++;
 	}
 
@@ -13651,7 +13750,7 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 
 		lpfc_sli4_hba_handle_eqe(phba, eqe, hba_eqidx);
 		if (!(++ecount % fpeq->entry_repost))
-			lpfc_sli4_eq_release(fpeq, LPFC_QUEUE_NOARM);
+			break;
 		fpeq->EQ_processed++;
 	}
 
@@ -13832,17 +13931,10 @@ lpfc_sli4_queue_alloc(struct lpfc_hba *phba, uint32_t entry_size,
 	}
 	queue->entry_size = entry_size;
 	queue->entry_count = entry_count;
-
-	/*
-	 * entry_repost is calculated based on the number of entries in the
-	 * queue. This works out except for RQs. If buffers are NOT initially
-	 * posted for every RQE, entry_repost should be adjusted accordingly.
-	 */
-	queue->entry_repost = (entry_count >> 3);
-	if (queue->entry_repost < LPFC_QUEUE_MIN_REPOST)
-		queue->entry_repost = LPFC_QUEUE_MIN_REPOST;
 	queue->phba = phba;
 
+	/* entry_repost will be set during q creation */
+
 	return queue;
 out_fail:
 	lpfc_sli4_queue_free(queue);
@@ -14073,6 +14165,7 @@ lpfc_eq_create(struct lpfc_hba *phba, struct lpfc_queue *eq, uint32_t imax)
 		status = -ENXIO;
 	eq->host_index = 0;
 	eq->hba_index = 0;
+	eq->entry_repost = LPFC_EQ_REPOST;
 
 	mempool_free(mbox, phba->mbox_mem_pool);
 	return status;
@@ -14146,9 +14239,9 @@ lpfc_cq_create(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	default:
 		lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
 				"0361 Unsupported CQ count: "
-				"entry cnt %d sz %d pg cnt %d repost %d\n",
+				"entry cnt %d sz %d pg cnt %d\n",
 				cq->entry_count, cq->entry_size,
-				cq->page_count, cq->entry_repost);
+				cq->page_count);
 		if (cq->entry_count < 256) {
 			status = -EINVAL;
 			goto out;
@@ -14201,6 +14294,7 @@ lpfc_cq_create(struct lpfc_hba *phba, struct lpfc_queue *cq,
 	cq->assoc_qid = eq->queue_id;
 	cq->host_index = 0;
 	cq->hba_index = 0;
+	cq->entry_repost = LPFC_CQ_REPOST;
 
 out:
 	mempool_free(mbox, phba->mbox_mem_pool);
@@ -14392,6 +14486,7 @@ lpfc_cq_create_set(struct lpfc_hba *phba, struct lpfc_queue **cqp,
 		cq->assoc_qid = eq->queue_id;
 		cq->host_index = 0;
 		cq->hba_index = 0;
+		cq->entry_repost = LPFC_CQ_REPOST;
 
 		rc = 0;
 		list_for_each_entry(dmabuf, &cq->page_list, list) {
@@ -14640,6 +14735,7 @@ lpfc_mq_create(struct lpfc_hba *phba, struct lpfc_queue *mq,
 	mq->subtype = subtype;
 	mq->host_index = 0;
 	mq->hba_index = 0;
+	mq->entry_repost = LPFC_MQ_REPOST;
 
 	/* link the mq onto the parent cq child list */
 	list_add_tail(&mq->list, &cq->child_list);
@@ -14865,34 +14961,6 @@ out:
 }
 
 /**
- * lpfc_rq_adjust_repost - Adjust entry_repost for an RQ
- * @phba: HBA structure that indicates port to create a queue on.
- * @rq:   The queue structure to use for the receive queue.
- * @qno:  The associated HBQ number
- *
- *
- * For SLI4 we need to adjust the RQ repost value based on
- * the number of buffers that are initially posted to the RQ.
- */
-void
-lpfc_rq_adjust_repost(struct lpfc_hba *phba, struct lpfc_queue *rq, int qno)
-{
-	uint32_t cnt;
-
-	/* sanity check on queue memory */
-	if (!rq)
-		return;
-	cnt = lpfc_hbq_defs[qno]->entry_count;
-
-	/* Recalc repost for RQs based on buffers initially posted */
-	cnt = (cnt >> 3);
-	if (cnt < LPFC_QUEUE_MIN_REPOST)
-		cnt = LPFC_QUEUE_MIN_REPOST;
-
-	rq->entry_repost = cnt;
-}
-
-/**
  * lpfc_rq_create - Create a Receive Queue on the HBA
  * @phba: HBA structure that indicates port to create a queue on.
  * @hrq: The queue structure to use to create the header receive queue.
@@ -15077,6 +15145,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 	hrq->subtype = subtype;
 	hrq->host_index = 0;
 	hrq->hba_index = 0;
+	hrq->entry_repost = LPFC_RQ_REPOST;
 
 	/* now create the data queue */
 	lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_FCOE,
@@ -15087,7 +15156,12 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 	if (phba->sli4_hba.pc_sli4_params.rqv == LPFC_Q_CREATE_VERSION_1) {
 		bf_set(lpfc_rq_context_rqe_count_1,
 		       &rq_create->u.request.context, hrq->entry_count);
-		rq_create->u.request.context.buffer_size = LPFC_DATA_BUF_SIZE;
+		if (subtype == LPFC_NVMET)
+			rq_create->u.request.context.buffer_size =
+				LPFC_NVMET_DATA_BUF_SIZE;
+		else
+			rq_create->u.request.context.buffer_size =
+				LPFC_DATA_BUF_SIZE;
 		bf_set(lpfc_rq_context_rqe_size, &rq_create->u.request.context,
 		       LPFC_RQE_SIZE_8);
 		bf_set(lpfc_rq_context_page_size, &rq_create->u.request.context,
@@ -15124,8 +15198,14 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 			       LPFC_RQ_RING_SIZE_4096);
 			break;
 		}
-		bf_set(lpfc_rq_context_buf_size, &rq_create->u.request.context,
-		       LPFC_DATA_BUF_SIZE);
+		if (subtype == LPFC_NVMET)
+			bf_set(lpfc_rq_context_buf_size,
+			       &rq_create->u.request.context,
+			       LPFC_NVMET_DATA_BUF_SIZE);
+		else
+			bf_set(lpfc_rq_context_buf_size,
+			       &rq_create->u.request.context,
+			       LPFC_DATA_BUF_SIZE);
 	}
 	bf_set(lpfc_rq_context_cq_id, &rq_create->u.request.context,
 	       cq->queue_id);
@@ -15158,6 +15238,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 	drq->subtype = subtype;
 	drq->host_index = 0;
 	drq->hba_index = 0;
+	drq->entry_repost = LPFC_RQ_REPOST;
 
 	/* link the header and data RQs onto the parent cq child list */
 	list_add_tail(&hrq->list, &cq->child_list);
@@ -15270,7 +15351,7 @@ lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
 			       cq->queue_id);
 			bf_set(lpfc_rq_context_data_size,
 			       &rq_create->u.request.context,
-			       LPFC_DATA_BUF_SIZE);
+			       LPFC_NVMET_DATA_BUF_SIZE);
 			bf_set(lpfc_rq_context_hdr_size,
 			       &rq_create->u.request.context,
 			       LPFC_HDR_BUF_SIZE);
@@ -15315,6 +15396,7 @@ lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
 		hrq->subtype = subtype;
 		hrq->host_index = 0;
 		hrq->hba_index = 0;
+		hrq->entry_repost = LPFC_RQ_REPOST;
 
 		drq->db_format = LPFC_DB_RING_FORMAT;
 		drq->db_regaddr = phba->sli4_hba.RQDBregaddr;
@@ -15323,6 +15405,7 @@ lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
 		drq->subtype = subtype;
 		drq->host_index = 0;
 		drq->hba_index = 0;
+		drq->entry_repost = LPFC_RQ_REPOST;
 
 		list_add_tail(&hrq->list, &cq->child_list);
 		list_add_tail(&drq->list, &cq->child_list);
@@ -16063,6 +16146,8 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	struct fc_vft_header *fc_vft_hdr;
 	uint32_t *header = (uint32_t *) fc_hdr;
 
+#define FC_RCTL_MDS_DIAGS	0xF4
+
 	switch (fc_hdr->fh_r_ctl) {
 	case FC_RCTL_DD_UNCAT:		/* uncategorized information */
 	case FC_RCTL_DD_SOL_DATA:	/* solicited data */
@@ -16090,6 +16175,7 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	case FC_RCTL_F_BSY:	/* fabric busy to data frame */
 	case FC_RCTL_F_BSYL:	/* fabric busy to link control frame */
 	case FC_RCTL_LCR:	/* link credit reset */
+	case FC_RCTL_MDS_DIAGS: /* MDS Diagnostics */
 	case FC_RCTL_END:	/* end */
 		break;
 	case FC_RCTL_VFTH:	/* Virtual Fabric tagging Header */
@@ -16099,12 +16185,16 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	default:
 		goto drop;
 	}
+
+#define FC_TYPE_VENDOR_UNIQUE	0xFF
+
 	switch (fc_hdr->fh_type) {
 	case FC_TYPE_BLS:
 	case FC_TYPE_ELS:
 	case FC_TYPE_FCP:
 	case FC_TYPE_CT:
 	case FC_TYPE_NVME:
+	case FC_TYPE_VENDOR_UNIQUE:
 		break;
 	case FC_TYPE_IP:
 	case FC_TYPE_ILS:
@@ -16115,12 +16205,14 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr)
 	lpfc_printf_log(phba, KERN_INFO, LOG_ELS,
 			"2538 Received frame rctl:%s (x%x), type:%s (x%x), "
 			"frame Data:%08x %08x %08x %08x %08x %08x %08x\n",
+			(fc_hdr->fh_r_ctl == FC_RCTL_MDS_DIAGS) ? "MDS Diags" :
 			lpfc_rctl_names[fc_hdr->fh_r_ctl], fc_hdr->fh_r_ctl,
-			lpfc_type_names[fc_hdr->fh_type], fc_hdr->fh_type,
-			be32_to_cpu(header[0]), be32_to_cpu(header[1]),
-			be32_to_cpu(header[2]), be32_to_cpu(header[3]),
-			be32_to_cpu(header[4]), be32_to_cpu(header[5]),
-			be32_to_cpu(header[6]));
+			(fc_hdr->fh_type == FC_TYPE_VENDOR_UNIQUE) ?
+			"Vendor Unique" : lpfc_type_names[fc_hdr->fh_type],
+			fc_hdr->fh_type, be32_to_cpu(header[0]),
+			be32_to_cpu(header[1]), be32_to_cpu(header[2]),
+			be32_to_cpu(header[3]), be32_to_cpu(header[4]),
+			be32_to_cpu(header[5]), be32_to_cpu(header[6]));
 	return 0;
 drop:
 	lpfc_printf_log(phba, KERN_WARNING, LOG_ELS,
@@ -16926,6 +17018,96 @@ lpfc_sli4_send_seq_to_ulp(struct lpfc_vport *vport,
 	lpfc_sli_release_iocbq(phba, iocbq);
 }
 
+static void
+lpfc_sli4_mds_loopback_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
+			    struct lpfc_iocbq *rspiocb)
+{
+	struct lpfc_dmabuf *pcmd = cmdiocb->context2;
+
+	if (pcmd && pcmd->virt)
+		pci_pool_free(phba->lpfc_drb_pool, pcmd->virt, pcmd->phys);
+	kfree(pcmd);
+	lpfc_sli_release_iocbq(phba, cmdiocb);
+}
+
+static void
+lpfc_sli4_handle_mds_loopback(struct lpfc_vport *vport,
+			      struct hbq_dmabuf *dmabuf)
+{
+	struct fc_frame_header *fc_hdr;
+	struct lpfc_hba *phba = vport->phba;
+	struct lpfc_iocbq *iocbq = NULL;
+	union  lpfc_wqe *wqe;
+	struct lpfc_dmabuf *pcmd = NULL;
+	uint32_t frame_len;
+	int rc;
+
+	fc_hdr = (struct fc_frame_header *)dmabuf->hbuf.virt;
+	frame_len = bf_get(lpfc_rcqe_length, &dmabuf->cq_event.cqe.rcqe_cmpl);
+
+	/* Send the received frame back */
+	iocbq = lpfc_sli_get_iocbq(phba);
+	if (!iocbq)
+		goto exit;
+
+	/* Allocate buffer for command payload */
+	pcmd = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
+	if (pcmd)
+		pcmd->virt = pci_pool_alloc(phba->lpfc_drb_pool, GFP_KERNEL,
+					    &pcmd->phys);
+	if (!pcmd || !pcmd->virt)
+		goto exit;
+
+	INIT_LIST_HEAD(&pcmd->list);
+
+	/* copyin the payload */
+	memcpy(pcmd->virt, dmabuf->dbuf.virt, frame_len);
+
+	/* fill in BDE's for command */
+	iocbq->iocb.un.xseq64.bdl.addrHigh = putPaddrHigh(pcmd->phys);
+	iocbq->iocb.un.xseq64.bdl.addrLow = putPaddrLow(pcmd->phys);
+	iocbq->iocb.un.xseq64.bdl.bdeFlags = BUFF_TYPE_BDE_64;
+	iocbq->iocb.un.xseq64.bdl.bdeSize = frame_len;
+
+	iocbq->context2 = pcmd;
+	iocbq->vport = vport;
+	iocbq->iocb_flag &= ~LPFC_FIP_ELS_ID_MASK;
+	iocbq->iocb_flag |= LPFC_USE_FCPWQIDX;
+
+	/*
+	 * Setup rest of the iocb as though it were a WQE
+	 * Build the SEND_FRAME WQE
+	 */
+	wqe = (union lpfc_wqe *)&iocbq->iocb;
+
+	wqe->send_frame.frame_len = frame_len;
+	wqe->send_frame.fc_hdr_wd0 = be32_to_cpu(*((uint32_t *)fc_hdr));
+	wqe->send_frame.fc_hdr_wd1 = be32_to_cpu(*((uint32_t *)fc_hdr + 1));
+	wqe->send_frame.fc_hdr_wd2 = be32_to_cpu(*((uint32_t *)fc_hdr + 2));
+	wqe->send_frame.fc_hdr_wd3 = be32_to_cpu(*((uint32_t *)fc_hdr + 3));
+	wqe->send_frame.fc_hdr_wd4 = be32_to_cpu(*((uint32_t *)fc_hdr + 4));
+	wqe->send_frame.fc_hdr_wd5 = be32_to_cpu(*((uint32_t *)fc_hdr + 5));
+
+	iocbq->iocb.ulpCommand = CMD_SEND_FRAME;
+	iocbq->iocb.ulpLe = 1;
+	iocbq->iocb_cmpl = lpfc_sli4_mds_loopback_cmpl;
+	rc = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, iocbq, 0);
+	if (rc == IOCB_ERROR)
+		goto exit;
+
+	lpfc_in_buf_free(phba, &dmabuf->dbuf);
+	return;
+
+exit:
+	lpfc_printf_log(phba, KERN_WARNING, LOG_SLI,
+			"2023 Unable to process MDS loopback frame\n");
+	if (pcmd && pcmd->virt)
+		pci_pool_free(phba->lpfc_drb_pool, pcmd->virt, pcmd->phys);
+	kfree(pcmd);
+	lpfc_sli_release_iocbq(phba, iocbq);
+	lpfc_in_buf_free(phba, &dmabuf->dbuf);
+}
+
 /**
  * lpfc_sli4_handle_received_buffer - Handle received buffers from firmware
  * @phba: Pointer to HBA context object.
@@ -16964,6 +17146,13 @@ lpfc_sli4_handle_received_buffer(struct lpfc_hba *phba,
 		fcfi = bf_get(lpfc_rcqe_fcf_id,
 			      &dmabuf->cq_event.cqe.rcqe_cmpl);
 
+	if (fc_hdr->fh_r_ctl == 0xF4 && fc_hdr->fh_type == 0xFF) {
+		vport = phba->pport;
+		/* Handle MDS Loopback frames */
+		lpfc_sli4_handle_mds_loopback(vport, dmabuf);
+		return;
+	}
+
 	/* d_id this frame is directed to */
 	did = sli4_did_from_fc_hdr(fc_hdr);
 
@@ -17137,6 +17326,14 @@ lpfc_sli4_post_rpi_hdr(struct lpfc_hba *phba, struct lpfc_rpi_hdr *rpi_page)
 				"status x%x add_status x%x, mbx status x%x\n",
 				shdr_status, shdr_add_status, rc);
 		rc = -ENXIO;
+	} else {
+		/*
+		 * The next_rpi stores the next logical module-64 rpi value used
+		 * to post physical rpis in subsequent rpi postings.
+		 */
+		spin_lock_irq(&phba->hbalock);
+		phba->sli4_hba.next_rpi = rpi_page->next_rpi;
+		spin_unlock_irq(&phba->hbalock);
 	}
 	return rc;
 }
@@ -18717,7 +18914,7 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, uint32_t ring_number,
 
 		spin_lock_irqsave(&pring->ring_lock, iflags);
 		ctxp = pwqe->context2;
-		sglq = ctxp->rqb_buffer->sglq;
+		sglq = ctxp->ctxbuf->sglq;
 		if (pwqe->sli4_xritag ==  NO_XRI) {
 			pwqe->sli4_lxritag = sglq->sli4_lxritag;
 			pwqe->sli4_xritag = sglq->sli4_xritag;
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index da46471337c8..cf863db27700 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -24,7 +24,6 @@
 #define LPFC_XRI_EXCH_BUSY_WAIT_TMO		10000
 #define LPFC_XRI_EXCH_BUSY_WAIT_T1   		10
 #define LPFC_XRI_EXCH_BUSY_WAIT_T2              30000
-#define LPFC_RELEASE_NOTIFICATION_INTERVAL	32
 #define LPFC_RPI_LOW_WATER_MARK			10
 
 #define LPFC_UNREG_FCF                          1
@@ -155,7 +154,11 @@ struct lpfc_queue {
 	uint32_t entry_count;	/* Number of entries to support on the queue */
 	uint32_t entry_size;	/* Size of each queue entry. */
 	uint32_t entry_repost;	/* Count of entries before doorbell is rung */
-#define LPFC_QUEUE_MIN_REPOST	8
+#define LPFC_EQ_REPOST		8
+#define LPFC_MQ_REPOST		8
+#define LPFC_CQ_REPOST		64
+#define LPFC_RQ_REPOST		64
+#define LPFC_RELEASE_NOTIFICATION_INTERVAL	32  /* For WQs */
 	uint32_t queue_id;	/* Queue ID assigned by the hardware */
 	uint32_t assoc_qid;     /* Queue ID associated with, for CQ/WQ/MQ */
 	uint32_t page_count;	/* Number of pages allocated for this queue */
@@ -195,7 +198,7 @@ struct lpfc_queue {
 /* defines for RQ stats */
 #define	RQ_no_posted_buf	q_cnt_1
 #define	RQ_no_buf_found		q_cnt_2
-#define	RQ_buf_trunc		q_cnt_3
+#define	RQ_buf_posted		q_cnt_3
 #define	RQ_rcv_buf		q_cnt_4
 
 	uint64_t isr_timestamp;
@@ -617,12 +620,17 @@ struct lpfc_sli4_hba {
 	uint16_t scsi_xri_start;
 	uint16_t els_xri_cnt;
 	uint16_t nvmet_xri_cnt;
+	uint16_t nvmet_ctx_cnt;
+	uint16_t nvmet_io_wait_cnt;
+	uint16_t nvmet_io_wait_total;
 	struct list_head lpfc_els_sgl_list;
 	struct list_head lpfc_abts_els_sgl_list;
 	struct list_head lpfc_nvmet_sgl_list;
 	struct list_head lpfc_abts_nvmet_ctx_list;
 	struct list_head lpfc_abts_scsi_buf_list;
 	struct list_head lpfc_abts_nvme_buf_list;
+	struct list_head lpfc_nvmet_ctx_list;
+	struct list_head lpfc_nvmet_io_wait_list;
 	struct lpfc_sglq **lpfc_sglq_active_list;
 	struct list_head lpfc_rpi_hdr_list;
 	unsigned long *rpi_bmask;
@@ -654,6 +662,7 @@ struct lpfc_sli4_hba {
 	spinlock_t abts_scsi_buf_list_lock; /* list of aborted SCSI IOs */
 	spinlock_t sgl_list_lock; /* list of aborted els IOs */
 	spinlock_t nvmet_io_lock;
+	spinlock_t nvmet_io_wait_lock; /* IOs waiting for ctx resources */
 	uint32_t physical_port;
 
 	/* CPU to vector mapping information */
@@ -661,8 +670,6 @@ struct lpfc_sli4_hba {
 	uint16_t num_online_cpu;
 	uint16_t num_present_cpu;
 	uint16_t curr_disp_cpu;
-
-	uint16_t nvmet_mrq_post_idx;
 };
 
 enum lpfc_sge_type {
@@ -698,6 +705,7 @@ struct lpfc_rpi_hdr {
 	struct lpfc_dmabuf *dmabuf;
 	uint32_t page_count;
 	uint32_t start_rpi;
+	uint16_t next_rpi;
 };
 
 struct lpfc_rsrc_blks {
@@ -762,7 +770,6 @@ int lpfc_rq_create(struct lpfc_hba *, struct lpfc_queue *,
 int lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
 			struct lpfc_queue **drqp, struct lpfc_queue **cqp,
 			uint32_t subtype);
-void lpfc_rq_adjust_repost(struct lpfc_hba *, struct lpfc_queue *, int);
 int lpfc_eq_destroy(struct lpfc_hba *, struct lpfc_queue *);
 int lpfc_cq_destroy(struct lpfc_hba *, struct lpfc_queue *);
 int lpfc_mq_destroy(struct lpfc_hba *, struct lpfc_queue *);
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 1c26dc67151b..c2653244221c 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "11.2.0.12"
+#define LPFC_DRIVER_VERSION "11.2.0.14"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index e31f1cc90b81..99e16ac479e3 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1851,7 +1851,7 @@ static int scsi_mq_prep_fn(struct request *req)
 
 	/* zero out the cmd, except for the embedded scsi_request */
 	memset((char *)cmd + sizeof(cmd->req), 0,
-		sizeof(*cmd) - sizeof(cmd->req));
+		sizeof(*cmd) - sizeof(cmd->req) + shost->hostt->cmd_size);
 
 	req->special = cmd;
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index f9d1432d7cc5..b6bb4e0ce0e3 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -827,21 +827,32 @@ static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
 	u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
 	u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+	int ret;
 
 	if (!(rq->cmd_flags & REQ_NOUNMAP)) {
 		switch (sdkp->zeroing_mode) {
 		case SD_ZERO_WS16_UNMAP:
-			return sd_setup_write_same16_cmnd(cmd, true);
+			ret = sd_setup_write_same16_cmnd(cmd, true);
+			goto out;
 		case SD_ZERO_WS10_UNMAP:
-			return sd_setup_write_same10_cmnd(cmd, true);
+			ret = sd_setup_write_same10_cmnd(cmd, true);
+			goto out;
 		}
 	}
 
 	if (sdp->no_write_same)
 		return BLKPREP_INVALID;
+
 	if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff)
-		return sd_setup_write_same16_cmnd(cmd, false);
-	return sd_setup_write_same10_cmnd(cmd, false);
+		ret = sd_setup_write_same16_cmnd(cmd, false);
+	else
+		ret = sd_setup_write_same10_cmnd(cmd, false);
+
+out:
+	if (sd_is_zoned(sdkp) && ret == BLKPREP_OK)
+		return sd_zbc_write_lock_zone(cmd);
+
+	return ret;
 }
 
 static void sd_config_write_same(struct scsi_disk *sdkp)
@@ -948,6 +959,10 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 	rq->__data_len = sdp->sector_size;
 	ret = scsi_init_io(cmd);
 	rq->__data_len = nr_bytes;
+
+	if (sd_is_zoned(sdkp) && ret != BLKPREP_OK)
+		sd_zbc_write_unlock_zone(cmd);
+
 	return ret;
 }
 
@@ -1567,17 +1582,21 @@ out:
 	return retval;
 }
 
-static int sd_sync_cache(struct scsi_disk *sdkp)
+static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
 {
 	int retries, res;
 	struct scsi_device *sdp = sdkp->device;
 	const int timeout = sdp->request_queue->rq_timeout
 		* SD_FLUSH_TIMEOUT_MULTIPLIER;
-	struct scsi_sense_hdr sshdr;
+	struct scsi_sense_hdr my_sshdr;
 
 	if (!scsi_device_online(sdp))
 		return -ENODEV;
 
+	/* caller might not be interested in sense, but we need it */
+	if (!sshdr)
+		sshdr = &my_sshdr;
+
 	for (retries = 3; retries > 0; --retries) {
 		unsigned char cmd[10] = { 0 };
 
@@ -1586,7 +1605,7 @@ static int sd_sync_cache(struct scsi_disk *sdkp)
 		 * Leave the rest of the command zero to indicate
 		 * flush everything.
 		 */
-		res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
+		res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, sshdr,
 				timeout, SD_MAX_RETRIES, 0, RQF_PM, NULL);
 		if (res == 0)
 			break;
@@ -1596,11 +1615,12 @@ static int sd_sync_cache(struct scsi_disk *sdkp)
 		sd_print_result(sdkp, "Synchronize Cache(10) failed", res);
 
 		if (driver_byte(res) & DRIVER_SENSE)
-			sd_print_sense_hdr(sdkp, &sshdr);
+			sd_print_sense_hdr(sdkp, sshdr);
+
 		/* we need to evaluate the error return  */
-		if (scsi_sense_valid(&sshdr) &&
-			(sshdr.asc == 0x3a ||	/* medium not present */
-			 sshdr.asc == 0x20))	/* invalid command */
+		if (scsi_sense_valid(sshdr) &&
+			(sshdr->asc == 0x3a ||	/* medium not present */
+			 sshdr->asc == 0x20))	/* invalid command */
 				/* this is no error here */
 				return 0;
 
@@ -3444,7 +3464,7 @@ static void sd_shutdown(struct device *dev)
 
 	if (sdkp->WCE && sdkp->media_present) {
 		sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
-		sd_sync_cache(sdkp);
+		sd_sync_cache(sdkp, NULL);
 	}
 
 	if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) {
@@ -3456,6 +3476,7 @@ static void sd_shutdown(struct device *dev)
 static int sd_suspend_common(struct device *dev, bool ignore_stop_errors)
 {
 	struct scsi_disk *sdkp = dev_get_drvdata(dev);
+	struct scsi_sense_hdr sshdr;
 	int ret = 0;
 
 	if (!sdkp)	/* E.g.: runtime suspend following sd_remove() */
@@ -3463,12 +3484,23 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors)
 
 	if (sdkp->WCE && sdkp->media_present) {
 		sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
-		ret = sd_sync_cache(sdkp);
+		ret = sd_sync_cache(sdkp, &sshdr);
+
 		if (ret) {
 			/* ignore OFFLINE device */
 			if (ret == -ENODEV)
-				ret = 0;
-			goto done;
+				return 0;
+
+			if (!scsi_sense_valid(&sshdr) ||
+			    sshdr.sense_key != ILLEGAL_REQUEST)
+				return ret;
+
+			/*
+			 * sshdr.sense_key == ILLEGAL_REQUEST means this drive
+			 * doesn't support sync. There's not much to do and
+			 * suspend shouldn't fail.
+			 */
+			 ret = 0;
 		}
 	}
 
@@ -3480,7 +3512,6 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors)
 			ret = 0;
 	}
 
-done:
 	return ret;
 }
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 0a38ba01b7b4..82c33a6edbea 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -2074,11 +2074,12 @@ sg_get_rq_mark(Sg_fd * sfp, int pack_id)
 		if ((1 == resp->done) && (!resp->sg_io_owned) &&
 		    ((-1 == pack_id) || (resp->header.pack_id == pack_id))) {
 			resp->done = 2;	/* guard against other readers */
-			break;
+			write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
+			return resp;
 		}
 	}
 	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
-	return resp;
+	return NULL;
 }
 
 /* always adds to end of list */
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index abc7e87937cc..ffe8d8608818 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -7698,6 +7698,12 @@ static inline void ufshcd_add_sysfs_nodes(struct ufs_hba *hba)
 	ufshcd_add_spm_lvl_sysfs_nodes(hba);
 }
 
+static inline void ufshcd_remove_sysfs_nodes(struct ufs_hba *hba)
+{
+	device_remove_file(hba->dev, &hba->rpm_lvl_attr);
+	device_remove_file(hba->dev, &hba->spm_lvl_attr);
+}
+
 /**
  * ufshcd_shutdown - shutdown routine
  * @hba: per adapter instance
@@ -7735,6 +7741,7 @@ EXPORT_SYMBOL(ufshcd_shutdown);
  */
 void ufshcd_remove(struct ufs_hba *hba)
 {
+	ufshcd_remove_sysfs_nodes(hba);
 	scsi_remove_host(hba->host);
 	/* disable interrupts */
 	ufshcd_disable_intr(hba, hba->intr_mask);