[PATCH 3.16 240/366] RDMA/cxgb4: release hw resources on device removal

[Ben Hutchings <ben@decadent.org.uk>]

3.16.60-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Raju Rangoju <rajur@chelsio.com>

commit 26bff1bd74a4f7417509a83295614e9dab995b2a upstream.

The c4iw_rdev_close() logic was not releasing all the hw
resources (PBL and RQT memory) during the device removal
event (driver unload / system reboot). This can cause panic
in gen_pool_destroy().

The module remove function will wait for all the hw
resources to be released during the device removal event.

Fixes c12a67fe(iw_cxgb4: free EQ queue memory on last deref)
Signed-off-by: Raju Rangoju <rajur@chelsio.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -698,6 +698,12 @@ static int c4iw_rdev_open(struct c4iw_rd
 		goto err4;
 	}
 	rdev->status_page->db_off = 0;
+
+	init_completion(&rdev->rqt_compl);
+	init_completion(&rdev->pbl_compl);
+	kref_init(&rdev->rqt_kref);
+	kref_init(&rdev->pbl_kref);
+
 	return 0;
 err4:
 	c4iw_rqtpool_destroy(rdev);
@@ -714,6 +720,8 @@ static void c4iw_rdev_close(struct c4iw_
 	free_page((unsigned long)rdev->status_page);
 	c4iw_pblpool_destroy(rdev);
 	c4iw_rqtpool_destroy(rdev);
+	wait_for_completion(&rdev->pbl_compl);
+	wait_for_completion(&rdev->rqt_compl);
 	c4iw_destroy_resource(&rdev->resource);
 }
 
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -157,6 +157,10 @@ struct c4iw_rdev {
 	void __iomem *oc_mw_kva;
 	struct c4iw_stats stats;
 	struct t4_dev_status_page *status_page;
+	struct completion rqt_compl;
+	struct completion pbl_compl;
+	struct kref rqt_kref;
+	struct kref pbl_kref;
 };
 
 static inline int c4iw_fatal_error(struct c4iw_rdev *rdev)
--- a/drivers/infiniband/hw/cxgb4/resource.c
+++ b/drivers/infiniband/hw/cxgb4/resource.c
@@ -260,12 +260,22 @@ u32 c4iw_pblpool_alloc(struct c4iw_rdev
 		rdev->stats.pbl.cur += roundup(size, 1 << MIN_PBL_SHIFT);
 		if (rdev->stats.pbl.cur > rdev->stats.pbl.max)
 			rdev->stats.pbl.max = rdev->stats.pbl.cur;
+		kref_get(&rdev->pbl_kref);
 	} else
 		rdev->stats.pbl.fail++;
 	mutex_unlock(&rdev->stats.lock);
 	return (u32)addr;
 }
 
+static void destroy_pblpool(struct kref *kref)
+{
+	struct c4iw_rdev *rdev;
+
+	rdev = container_of(kref, struct c4iw_rdev, pbl_kref);
+	gen_pool_destroy(rdev->pbl_pool);
+	complete(&rdev->pbl_compl);
+}
+
 void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
 {
 	PDBG("%s addr 0x%x size %d\n", __func__, addr, size);
@@ -273,6 +283,7 @@ void c4iw_pblpool_free(struct c4iw_rdev
 	rdev->stats.pbl.cur -= roundup(size, 1 << MIN_PBL_SHIFT);
 	mutex_unlock(&rdev->stats.lock);
 	gen_pool_free(rdev->pbl_pool, (unsigned long)addr, size);
+	kref_put(&rdev->pbl_kref, destroy_pblpool);
 }
 
 int c4iw_pblpool_create(struct c4iw_rdev *rdev)
@@ -312,7 +323,7 @@ int c4iw_pblpool_create(struct c4iw_rdev
 
 void c4iw_pblpool_destroy(struct c4iw_rdev *rdev)
 {
-	gen_pool_destroy(rdev->pbl_pool);
+	kref_put(&rdev->pbl_kref, destroy_pblpool);
 }
 
 /*
@@ -333,12 +344,22 @@ u32 c4iw_rqtpool_alloc(struct c4iw_rdev
 		rdev->stats.rqt.cur += roundup(size << 6, 1 << MIN_RQT_SHIFT);
 		if (rdev->stats.rqt.cur > rdev->stats.rqt.max)
 			rdev->stats.rqt.max = rdev->stats.rqt.cur;
+		kref_get(&rdev->rqt_kref);
 	} else
 		rdev->stats.rqt.fail++;
 	mutex_unlock(&rdev->stats.lock);
 	return (u32)addr;
 }
 
+static void destroy_rqtpool(struct kref *kref)
+{
+	struct c4iw_rdev *rdev;
+
+	rdev = container_of(kref, struct c4iw_rdev, rqt_kref);
+	gen_pool_destroy(rdev->rqt_pool);
+	complete(&rdev->rqt_compl);
+}
+
 void c4iw_rqtpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
 {
 	PDBG("%s addr 0x%x size %d\n", __func__, addr, size << 6);
@@ -346,6 +367,7 @@ void c4iw_rqtpool_free(struct c4iw_rdev
 	rdev->stats.rqt.cur -= roundup(size << 6, 1 << MIN_RQT_SHIFT);
 	mutex_unlock(&rdev->stats.lock);
 	gen_pool_free(rdev->rqt_pool, (unsigned long)addr, size << 6);
+	kref_put(&rdev->rqt_kref, destroy_rqtpool);
 }
 
 int c4iw_rqtpool_create(struct c4iw_rdev *rdev)
@@ -383,7 +405,7 @@ int c4iw_rqtpool_create(struct c4iw_rdev
 
 void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev)
 {
-	gen_pool_destroy(rdev->rqt_pool);
+	kref_put(&rdev->rqt_kref, destroy_rqtpool);
 }
 
 /*