[PATCH 00/12] For 4.9 rc

[PATCH 00/12] For 4.9 rc

[Dennis Dalessandro]

Doug,

Here are some more patches for hfi1 and rdmavt. That I didn't bother to send
at the tail end of the merge window based on Linus' recent response on the
list. 

I think these could for the next RC. They build on the most recent patch set
[1] that is pending on the list.

If we need to remove any of these, or from [1] for the RC let me know and I can
respin or you can just drop.

Note there is another stable fix in here.

[1] http://marc.info/?l=linux-rdma&m=147610526924704&w=2

Can also be found in GitHub repo at:
https://github.com/ddalessa/kernel/tree/for-4.9

---

Dennis Dalessandro (1):
      IB/hfi1: Remove leftover snoop references

Easwar Hariharan (3):
      IB/hfi1: Add active channel and backplane support for integrated devices
      IB/hfi1: Clean up unused argument
      IB/hfi1: Delete unused lock

Ira Weiny (1):
      IB/hfi1: Fix rnr_timer addition

Jakub Pawlak (1):
      IB/hfi1: Unify access to GUID entries

Jianxin Xiong (1):
      IB/hfi1: Fix a potential memory leak in hfi1_create_ctxts()

Krzysztof Blaszkowski (1):
      IB/hfi1: Return ENODEV for unsupported PCI device ids.

Mike Marciniszyn (2):
      IB/rdmvat: Organize hot path calldowns into a single cacheline
      IB/hfi1: Optimize pio cachelines

Sebastian Sanchez (1):
      IB/hfi1: Optimize devdata cachelines

Tadeusz Struk (1):
      IB/hfi1: Fix an Oops on pci device force remove


 drivers/infiniband/hw/hfi1/chip.c           |   29 +---
 drivers/infiniband/hw/hfi1/chip_registers.h |    3 
 drivers/infiniband/hw/hfi1/file_ops.c       |    5 +
 drivers/infiniband/hw/hfi1/firmware.c       |  136 ++++++++++++++++---
 drivers/infiniband/hw/hfi1/hfi.h            |  193 +++++++++++++--------------
 drivers/infiniband/hw/hfi1/init.c           |   58 +++++---
 drivers/infiniband/hw/hfi1/mad.c            |   19 +--
 drivers/infiniband/hw/hfi1/pcie.c           |    3 
 drivers/infiniband/hw/hfi1/pio.h            |   10 +
 drivers/infiniband/hw/hfi1/platform.c       |  149 +++++++++++++++++----
 drivers/infiniband/hw/hfi1/platform.h       |  117 ++++++++++++++++
 drivers/infiniband/hw/hfi1/rc.c             |    2 
 drivers/infiniband/hw/hfi1/ruc.c            |   16 --
 drivers/infiniband/hw/hfi1/trace_rx.h       |   60 --------
 drivers/infiniband/hw/hfi1/verbs.c          |   15 +-
 drivers/infiniband/hw/hfi1/verbs.h          |    3 
 include/rdma/rdma_vt.h                      |   46 +++---
 17 files changed, 557 insertions(+), 307 deletions(-)

--
-Denny

[PATCH 01/12] IB/rdmvat: Organize hot path calldowns into a single cacheline

[Dennis Dalessandro]

From: Mike Marciniszyn <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

Save a cacheline by having hot path calldowns together.

Reviewed-by: Sebastian Sanchez <sebastian.sanchez-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 include/rdma/rdma_vt.h |   46 ++++++++++++++++++++++++----------------------
 1 files changed, 24 insertions(+), 22 deletions(-)

diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index e315021..861e23e 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -185,6 +185,27 @@ struct rvt_driver_provided {
 	 * check_support() for details.
 	 */
 
+	/* hot path calldowns in a single cacheline */
+
+	/*
+	 * Give the driver a notice that there is send work to do. It is up to
+	 * the driver to generally push the packets out, this just queues the
+	 * work with the driver. There are two variants here. The no_lock
+	 * version requires the s_lock not to be held. The other assumes the
+	 * s_lock is held.
+	 */
+	void (*schedule_send)(struct rvt_qp *qp);
+	void (*schedule_send_no_lock)(struct rvt_qp *qp);
+
+	/* Driver specific work request checking */
+	int (*check_send_wqe)(struct rvt_qp *qp, struct rvt_swqe *wqe);
+
+	/*
+	 * Sometimes rdmavt needs to kick the driver's send progress. That is
+	 * done by this call back.
+	 */
+	void (*do_send)(struct rvt_qp *qp);
+
 	/* Passed to ib core registration. Callback to create syfs files */
 	int (*port_callback)(struct ib_device *, u8, struct kobject *);
 
@@ -223,22 +244,6 @@ struct rvt_driver_provided {
 	void (*notify_qp_reset)(struct rvt_qp *qp);
 
 	/*
-	 * Give the driver a notice that there is send work to do. It is up to
-	 * the driver to generally push the packets out, this just queues the
-	 * work with the driver. There are two variants here. The no_lock
-	 * version requires the s_lock not to be held. The other assumes the
-	 * s_lock is held.
-	 */
-	void (*schedule_send)(struct rvt_qp *qp);
-	void (*schedule_send_no_lock)(struct rvt_qp *qp);
-
-	/*
-	 * Sometimes rdmavt needs to kick the driver's send progress. That is
-	 * done by this call back.
-	 */
-	void (*do_send)(struct rvt_qp *qp);
-
-	/*
 	 * Get a path mtu from the driver based on qp attributes.
 	 */
 	int (*get_pmtu_from_attr)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
@@ -324,9 +329,6 @@ struct rvt_driver_provided {
 	void (*modify_qp)(struct rvt_qp *qp, struct ib_qp_attr *attr,
 			  int attr_mask, struct ib_udata *udata);
 
-	/* Driver specific work request checking */
-	int (*check_send_wqe)(struct rvt_qp *qp, struct rvt_swqe *wqe);
-
 	/* Notify driver a mad agent has been created */
 	void (*notify_create_mad_agent)(struct rvt_dev_info *rdi, int port_idx);
 
@@ -355,12 +357,12 @@ struct rvt_dev_info {
 	/* post send table */
 	const struct rvt_operation_params *post_parms;
 
-	struct rvt_mregion __rcu *dma_mr;
-	struct rvt_lkey_table lkey_table;
-
 	/* Driver specific helper functions */
 	struct rvt_driver_provided driver_f;
 
+	struct rvt_mregion __rcu *dma_mr;
+	struct rvt_lkey_table lkey_table;
+
 	/* Internal use */
 	int n_pds_allocated;
 	spinlock_t n_pds_lock; /* Protect pd allocated count */

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 02/12] IB/hfi1: Optimize pio cachelines

[Dennis Dalessandro]

From: Mike Marciniszyn <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

Move buffers_allocated pcpu pointer to allocator line.

Move hw_free pointer to releaser line.

Fill other holes revealed by pahole.

Reviewed-by: Sebastian Sanchez <sebastian.sanchez-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/hfi1/pio.h |   10 +++++-----
 1 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/pio.h b/drivers/infiniband/hw/hfi1/pio.h
index e709eaf..bd19507 100644
--- a/drivers/infiniband/hw/hfi1/pio.h
+++ b/drivers/infiniband/hw/hfi1/pio.h
@@ -104,7 +104,6 @@ struct send_context {
 	void __iomem *base_addr;	/* start of PIO memory */
 	union pio_shadow_ring *sr;	/* shadow ring */
 
-	volatile __le64 *hw_free;	/* HW free counter */
 	struct work_struct halt_work;	/* halted context work queue entry */
 	unsigned long flags;		/* flags */
 	int node;			/* context home node */
@@ -116,19 +115,20 @@ struct send_context {
 	u32 group;			/* credit return group */
 	/* allocator fields */
 	spinlock_t alloc_lock ____cacheline_aligned_in_smp;
+	u32 sr_head;			/* shadow ring head */
 	unsigned long fill;		/* official alloc count */
 	unsigned long alloc_free;	/* copy of free (less cache thrash) */
-	u32 sr_head;			/* shadow ring head */
+	u32 __percpu *buffers_allocated;/* count of buffers allocated */
 	/* releaser fields */
 	spinlock_t release_lock ____cacheline_aligned_in_smp;
-	unsigned long free;		/* official free count */
 	u32 sr_tail;			/* shadow ring tail */
+	unsigned long free;		/* official free count */
+	volatile __le64 *hw_free;	/* HW free counter */
 	/* list for PIO waiters */
 	struct list_head piowait  ____cacheline_aligned_in_smp;
 	spinlock_t credit_ctrl_lock ____cacheline_aligned_in_smp;
-	u64 credit_ctrl;		/* cache for credit control */
 	u32 credit_intr_count;		/* count of credit intr users */
-	u32 __percpu *buffers_allocated;/* count of buffers allocated */
+	u64 credit_ctrl;		/* cache for credit control */
 	wait_queue_head_t halt_wait;    /* wait until kernel sees interrupt */
 };
 

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 03/12] IB/hfi1: Fix an Oops on pci device force remove

[Dennis Dalessandro]

From: Tadeusz Struk <tadeusz.struk-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

This patch fixes an Oops on device unbind, when the device is used
by a PSM user process. PSM processes access device resources which
are freed on device removal. Similar protection exists in uverbs
in ib_core for Verbs clients, but PSM doesn't use ib_uverbs hence
a separate protection is required for PSM clients.

Cc: Jason Gunthorpe <jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
Reviewed-by: Ira Weiny <ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Reviewed-by: Dean Luick <dean.luick-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Tadeusz Struk <tadeusz.struk-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/hfi1/chip.c     |    5 +++++
 drivers/infiniband/hw/hfi1/file_ops.c |    5 +++++
 drivers/infiniband/hw/hfi1/hfi.h      |    4 ++++
 drivers/infiniband/hw/hfi1/init.c     |   19 +++++++++++++++++--
 4 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 9bf5f23..7992152 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -14691,6 +14691,11 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 	if (ret)
 		goto bail_free_cntrs;
 
+	init_completion(&dd->user_comp);
+
+	/* The user refcount starts with one to inidicate an active device */
+	atomic_set(&dd->user_refcount, 1);
+
 	goto bail;
 
 bail_free_rcverr:
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 677efa0..14fd63f 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -183,6 +183,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 		fd->rec_cpu_num = -1; /* no cpu affinity by default */
 		fd->mm = current->mm;
 		atomic_inc(&fd->mm->mm_count);
+		atomic_inc(&dd->user_refcount);
 	}
 
 	fp->private_data = fd;
@@ -798,6 +799,10 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
 done:
 	mmdrop(fdata->mm);
 	kobject_put(&dd->kobj);
+
+	if (atomic_dec_and_test(&dd->user_refcount))
+		complete(&dd->user_comp);
+
 	kfree(fdata);
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 3c06d20..368e96c 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1174,6 +1174,10 @@ struct hfi1_devdata {
 	spinlock_t aspm_lock;
 	/* Number of verbs contexts which have disabled ASPM */
 	atomic_t aspm_disabled_cnt;
+	/* Keeps track of user space clients */
+	atomic_t user_refcount;
+	/* Used to wait for outstanding user space clients before dev removal */
+	struct completion user_comp;
 
 	struct hfi1_affinity *affinity;
 	struct rhashtable sdma_rht;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 60db615..18f1976 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1538,12 +1538,29 @@ bail:
 	return ret;
 }
 
+static void wait_for_clients(struct hfi1_devdata *dd)
+{
+	/*
+	 * Remove the device init value and wait for active
+	 * users to finish if there are any.
+	 */
+	if (atomic_sub_return(1, &dd->user_refcount))
+		wait_for_completion(&dd->user_comp);
+}
+
 static void remove_one(struct pci_dev *pdev)
 {
 	struct hfi1_devdata *dd = pci_get_drvdata(pdev);
 
 	/* close debugfs files before ib unregister */
 	hfi1_dbg_ibdev_exit(&dd->verbs_dev);
+
+	/* remove the /dev hfi1 interface */
+	hfi1_device_remove(dd);
+
+	/* wait for existing user space clients to finish */
+	wait_for_clients(dd);
+
 	/* unregister from IB core */
 	hfi1_unregister_ib_device(dd);
 
@@ -1558,8 +1575,6 @@ static void remove_one(struct pci_dev *pdev)
 	/* wait until all of our (qsfp) queue_work() calls complete */
 	flush_workqueue(ib_wq);
 
-	hfi1_device_remove(dd);
-
 	postinit_cleanup(dd);
 }
 

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH 03/12] IB/hfi1: Fix an Oops on pci device force remove

[Jason Gunthorpe]

On Mon, Oct 17, 2016 at 04:19:19AM -0700, Dennis Dalessandro wrote:
> @@ -183,6 +183,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
>  		fd->rec_cpu_num = -1; /* no cpu affinity by default */
>  		fd->mm = current->mm;
>  		atomic_inc(&fd->mm->mm_count);
> +		atomic_inc(&dd->user_refcount);

This doesn't look like enough locking on acquire.. What prevents the
driver from already having been unloaded at this point?

> +static void wait_for_clients(struct hfi1_devdata *dd)
> +{
> +	/*
> +	 * Remove the device init value and wait for active
> +	 * users to finish if there are any.
> +	 */
> +	if (atomic_sub_return(1, &dd->user_refcount))
> +		wait_for_completion(&dd->user_comp);
> +}

Shouldn't this be a while loop to avoid races?

.. and shouldn't the inc 'latch off' once the removal process starts?

I think you need to study how kernfs_drain is implemented and
basically copy that approach, including the locking.

FWIW, it is much easier and probably long term better to arrange
things so the FD can remain open but just return ENODEV to all calls.
Eg the srcu based approach in uverbs.

Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH 03/12] IB/hfi1: Fix an Oops on pci device force remove

[Tadeusz Struk]

Hi Jason,
On 10/17/2016 09:07 AM, Jason Gunthorpe wrote:
>> +		atomic_inc(&dd->user_refcount);
> This doesn't look like enough locking on acquire.. What prevents the
> driver from already having been unloaded at this point?

Thanks for your feedback. We will address this in v2.

> 
> Shouldn't this be a while loop to avoid races?
> 
> .. and shouldn't the inc 'latch off' once the removal process starts?
> 
> I think you need to study how kernfs_drain is implemented and
> basically copy that approach, including the locking.

as to kernfs_drain approach, I think the same mechanism as in ib_verbs
will work better here.

> 
> FWIW, it is much easier and probably long term better to arrange
> things so the FD can remain open but just return ENODEV to all calls.
> Eg the srcu based approach in uverbs.

We need to hold the device because not all the clients will talk to the
device via the FD. The PIO clients for instance don't go to kernel.
Thanks,
-- 
TS
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v2 03/12] IB/hfi1: Fix an Oops on pci device force remove

[Dennis Dalessandro]

From: Tadeusz Struk <tadeusz.struk-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

This patch fixes an Oops on device unbind, when the device is used
by a PSM user process. PSM processes access device resources which
are freed on device removal. Similar protection exists in uverbs
in ib_core for Verbs clients, but PSM doesn't use ib_uverbs hence
a separate protection is required for PSM clients.

Cc: Jason Gunthorpe <jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
Reviewed-by: Ira Weiny <ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Reviewed-by: Dean Luick <dean.luick-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Tadeusz Struk <tadeusz.struk-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

---
Changes in v2:
Fixed race condition between open and unbind repored by Jason.
---
 drivers/infiniband/hw/hfi1/chip.c     |    5 +++++
 drivers/infiniband/hw/hfi1/file_ops.c |   19 ++++++++++++++++---
 drivers/infiniband/hw/hfi1/hfi.h      |    4 ++++
 drivers/infiniband/hw/hfi1/init.c     |   21 +++++++++++++++++++--
 4 files changed, 44 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 9bf5f23..7992152 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -14691,6 +14691,11 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 	if (ret)
 		goto bail_free_cntrs;
 
+	init_completion(&dd->user_comp);
+
+	/* The user refcount starts with one to inidicate an active device */
+	atomic_set(&dd->user_refcount, 1);
+
 	goto bail;
 
 bail_free_rcverr:
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 677efa0..bd786b7 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -172,6 +172,9 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 					       struct hfi1_devdata,
 					       user_cdev);
 
+	if (!atomic_inc_not_zero(&dd->user_refcount))
+		return -ENXIO;
+
 	/* Just take a ref now. Not all opens result in a context assign */
 	kobject_get(&dd->kobj);
 
@@ -183,11 +186,17 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 		fd->rec_cpu_num = -1; /* no cpu affinity by default */
 		fd->mm = current->mm;
 		atomic_inc(&fd->mm->mm_count);
-	}
+		fp->private_data = fd;
+	} else {
+		fp->private_data = NULL;
+
+		if (atomic_dec_and_test(&dd->user_refcount))
+			complete(&dd->user_comp);
 
-	fp->private_data = fd;
+		return -ENOMEM;
+	}
 
-	return fd ? 0 : -ENOMEM;
+	return 0;
 }
 
 static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
@@ -798,6 +807,10 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
 done:
 	mmdrop(fdata->mm);
 	kobject_put(&dd->kobj);
+
+	if (atomic_dec_and_test(&dd->user_refcount))
+		complete(&dd->user_comp);
+
 	kfree(fdata);
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 3c06d20..368e96c 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1174,6 +1174,10 @@ struct hfi1_devdata {
 	spinlock_t aspm_lock;
 	/* Number of verbs contexts which have disabled ASPM */
 	atomic_t aspm_disabled_cnt;
+	/* Keeps track of user space clients */
+	atomic_t user_refcount;
+	/* Used to wait for outstanding user space clients before dev removal */
+	struct completion user_comp;
 
 	struct hfi1_affinity *affinity;
 	struct rhashtable sdma_rht;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 60db615..e28a6b6 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1538,12 +1538,31 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return ret;
 }
 
+static void wait_for_clients(struct hfi1_devdata *dd)
+{
+	/*
+	 * Remove the device init value and complete the device if there is
+	 * no clients or wait for active clients to finish.
+	 */
+	if (atomic_dec_and_test(&dd->user_refcount))
+		complete(&dd->user_comp);
+
+	wait_for_completion(&dd->user_comp);
+}
+
 static void remove_one(struct pci_dev *pdev)
 {
 	struct hfi1_devdata *dd = pci_get_drvdata(pdev);
 
 	/* close debugfs files before ib unregister */
 	hfi1_dbg_ibdev_exit(&dd->verbs_dev);
+
+	/* remove the /dev hfi1 interface */
+	hfi1_device_remove(dd);
+
+	/* wait for existing user space clients to finish */
+	wait_for_clients(dd);
+
 	/* unregister from IB core */
 	hfi1_unregister_ib_device(dd);
 
@@ -1558,8 +1577,6 @@ static void remove_one(struct pci_dev *pdev)
 	/* wait until all of our (qsfp) queue_work() calls complete */
 	flush_workqueue(ib_wq);
 
-	hfi1_device_remove(dd);
-
 	postinit_cleanup(dd);
 }
 

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v2 03/12] IB/hfi1: Fix an Oops on pci device force remove

[Jason Gunthorpe]

On Tue, Oct 25, 2016 at 08:57:55AM -0700, Dennis Dalessandro wrote:
> From: Tadeusz Struk <tadeusz.struk-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
> 
> This patch fixes an Oops on device unbind, when the device is used
> by a PSM user process. PSM processes access device resources which
> are freed on device removal. Similar protection exists in uverbs
> in ib_core for Verbs clients, but PSM doesn't use ib_uverbs hence
> a separate protection is required for PSM clients.

nit: This isn't similar to uverbs or other IB core interfaces - they
all allow unbind while the FD remains open, this forces the FD to
become closed - which means hot plug will not be supported by hfi1.

Otherwise this seems resonable.

Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v2 03/12] IB/hfi1: Fix an Oops on pci device force remove

[Tadeusz Struk]

On 10/25/2016 09:48 AM, Jason Gunthorpe wrote:
> nit: This isn't similar to uverbs or other IB core interfaces - they
> all allow unbind while the FD remains open, this forces the FD to
> become closed - which means hot plug will not be supported by hfi1.
> 

That's correct, the reason, as I said before, is that PIO processes
don't go via FD, but talk directly to MMIO PCI regions.

> Otherwise this seems resonable.

Thanks for reviewing Jason.
Thanks,
-- 
TS
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v2 03/12] IB/hfi1: Fix an Oops on pci device force remove

[Jason Gunthorpe]

On Tue, Oct 25, 2016 at 10:38:55AM -0700, Tadeusz Struk wrote:
> On 10/25/2016 09:48 AM, Jason Gunthorpe wrote:
> > nit: This isn't similar to uverbs or other IB core interfaces - they
> > all allow unbind while the FD remains open, this forces the FD to
> > become closed - which means hot plug will not be supported by hfi1.
> > 
> 
> That's correct, the reason, as I said before, is that PIO processes
> don't go via FD, but talk directly to MMIO PCI regions.

Most of the IB drivers do this - Mellanox implemented a forced
remapping of the user space VMA on unplug to deal with it, you can use
that technique in HFI1 too.

Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 04/12] IB/hfi1: Return ENODEV for unsupported PCI device ids.

[Dennis Dalessandro]

From: Krzysztof Blaszkowski <krzysztof.blaszkowski-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

Clean up device type checking.

Reviewed-by: Dean Luick <dean.luick-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Krzysztof Blaszkowski <krzysztof.blaszkowski-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Tymoteusz Kielan <tymoteusz.kielan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/hfi1/init.c |   25 ++++++++++++-------------
 1 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 18f1976..5872f10 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1402,7 +1402,7 @@ static void postinit_cleanup(struct hfi1_devdata *dd)
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int ret = 0, j, pidx, initfail;
-	struct hfi1_devdata *dd = ERR_PTR(-EINVAL);
+	struct hfi1_devdata *dd;
 	struct hfi1_pportdata *ppd;
 
 	/* First, lock the non-writable module parameters */
@@ -1461,26 +1461,25 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		goto bail;
 
-	/*
-	 * Do device-specific initialization, function table setup, dd
-	 * allocation, etc.
-	 */
-	switch (ent->device) {
-	case PCI_DEVICE_ID_INTEL0:
-	case PCI_DEVICE_ID_INTEL1:
-		dd = hfi1_init_dd(pdev, ent);
-		break;
-	default:
+	if (!(ent->device == PCI_DEVICE_ID_INTEL0 ||
+	      ent->device == PCI_DEVICE_ID_INTEL1)) {
 		hfi1_early_err(&pdev->dev,
 			       "Failing on unknown Intel deviceid 0x%x\n",
 			       ent->device);
 		ret = -ENODEV;
+		goto clean_bail;
 	}
 
-	if (IS_ERR(dd))
+	/*
+	 * Do device-specific initialization, function table setup, dd
+	 * allocation, etc.
+	 */
+	dd = hfi1_init_dd(pdev, ent);
+
+	if (IS_ERR(dd)) {
 		ret = PTR_ERR(dd);
-	if (ret)
 		goto clean_bail; /* error already printed */
+	}
 
 	ret = create_workqueues(dd);
 	if (ret)

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 05/12] IB/hfi1: Unify access to GUID entries

[Dennis Dalessandro]

From: Jakub Pawlak <jakub.pawlak-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

This patch consolidates the node GUIDs and the port GUID handling
and unifies access to these items. The knowledge of hfi1 GUIDs'
design and their location are kept in accessors to centralize access.

Reviewed-by: Mike Marciniszyn <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Reviewed-by: Brian Welty <brian.welty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Jakub Pawlak <jakub.pawlak-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/hfi1/chip.c  |    4 ++--
 drivers/infiniband/hw/hfi1/hfi.h   |   19 +++++++++++++++++--
 drivers/infiniband/hw/hfi1/mad.c   |   19 ++++++++++---------
 drivers/infiniband/hw/hfi1/ruc.c   |   16 +++-------------
 drivers/infiniband/hw/hfi1/verbs.c |   15 +++++++--------
 drivers/infiniband/hw/hfi1/verbs.h |    3 ---
 6 files changed, 39 insertions(+), 37 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 7992152..a0f05d7 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -9567,11 +9567,11 @@ int bringup_serdes(struct hfi1_pportdata *ppd)
 	if (HFI1_CAP_IS_KSET(EXTENDED_PSN))
 		add_rcvctrl(dd, RCV_CTRL_RCV_EXTENDED_PSN_ENABLE_SMASK);
 
-	guid = ppd->guid;
+	guid = ppd->guids[HFI1_PORT_GUID_INDEX];
 	if (!guid) {
 		if (dd->base_guid)
 			guid = dd->base_guid + ppd->port - 1;
-		ppd->guid = guid;
+		ppd->guids[HFI1_PORT_GUID_INDEX] = guid;
 	}
 
 	/* Set linkinit_reason on power up per OPA spec */
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 368e96c..87847cc 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -512,6 +512,9 @@ struct rvt_sge_state;
 #define HFI1_MIN_VLS_SUPPORTED 1
 #define HFI1_MAX_VLS_SUPPORTED 8
 
+#define HFI1_GUIDS_PER_PORT  5
+#define HFI1_PORT_GUID_INDEX 0
+
 static inline void incr_cntr64(u64 *cntr)
 {
 	if (*cntr < (u64)-1LL)
@@ -582,8 +585,9 @@ struct hfi1_pportdata {
 	u32 port_type;
 	struct qsfp_data qsfp_info;
 
-	/* GUID for this interface, in host order */
-	u64 guid;
+	/* GUIDs for this interface, in host order, guids[0] is a port guid */
+	u64 guids[HFI1_GUIDS_PER_PORT];
+
 	/* GUID for peer interface, in host order */
 	u64 neighbor_guid;
 
@@ -1637,6 +1641,17 @@ static inline u16 hfi1_get_pkey(struct hfi1_ibport *ibp, unsigned index)
 }
 
 /*
+ * Return the indexed GUID from the port GUIDs table.
+ */
+static inline __be64 get_sguid(struct hfi1_ibport *ibp, unsigned int index)
+{
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+
+	WARN_ON(index >= HFI1_GUIDS_PER_PORT);
+	return cpu_to_be64(ppd->guids[index]);
+}
+
+/*
  * Called by readers of cc_state only, must call under rcu_read_lock().
  */
 static inline struct cc_state *get_cc_state(struct hfi1_pportdata *ppd)
diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index 9487c9b..0ef62e6 100644
--- a/drivers/infiniband/hw/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -336,20 +336,20 @@ static int __subn_get_opa_nodeinfo(struct opa_smp *smp, u32 am, u8 *data,
 	ni = (struct opa_node_info *)data;
 
 	/* GUID 0 is illegal */
-	if (am || pidx >= dd->num_pports || dd->pport[pidx].guid == 0) {
+	if (am || pidx >= dd->num_pports || ibdev->node_guid == 0 ||
+	    get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX) == 0) {
 		smp->status |= IB_SMP_INVALID_FIELD;
 		return reply((struct ib_mad_hdr *)smp);
 	}
 
-	ni->port_guid = cpu_to_be64(dd->pport[pidx].guid);
+	ni->port_guid = get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX);
 	ni->base_version = OPA_MGMT_BASE_VERSION;
 	ni->class_version = OPA_SMI_CLASS_VERSION;
 	ni->node_type = 1;     /* channel adapter */
 	ni->num_ports = ibdev->phys_port_cnt;
 	/* This is already in network order */
 	ni->system_image_guid = ib_hfi1_sys_image_guid;
-	/* Use first-port GUID as node */
-	ni->node_guid = cpu_to_be64(dd->pport->guid);
+	ni->node_guid = ibdev->node_guid;
 	ni->partition_cap = cpu_to_be16(hfi1_get_npkeys(dd));
 	ni->device_id = cpu_to_be16(dd->pcidev->device);
 	ni->revision = cpu_to_be32(dd->minrev);
@@ -373,19 +373,20 @@ static int subn_get_nodeinfo(struct ib_smp *smp, struct ib_device *ibdev,
 
 	/* GUID 0 is illegal */
 	if (smp->attr_mod || pidx >= dd->num_pports ||
-	    dd->pport[pidx].guid == 0)
+	    ibdev->node_guid == 0 ||
+	    get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX) == 0) {
 		smp->status |= IB_SMP_INVALID_FIELD;
-	else
-		nip->port_guid = cpu_to_be64(dd->pport[pidx].guid);
+		return reply((struct ib_mad_hdr *)smp);
+	}
 
+	nip->port_guid = get_sguid(to_iport(ibdev, port), HFI1_PORT_GUID_INDEX);
 	nip->base_version = OPA_MGMT_BASE_VERSION;
 	nip->class_version = OPA_SMI_CLASS_VERSION;
 	nip->node_type = 1;     /* channel adapter */
 	nip->num_ports = ibdev->phys_port_cnt;
 	/* This is already in network order */
 	nip->sys_guid = ib_hfi1_sys_image_guid;
-	 /* Use first-port GUID as node */
-	nip->node_guid = cpu_to_be64(dd->pport->guid);
+	nip->node_guid = ibdev->node_guid;
 	nip->partition_cap = cpu_to_be16(hfi1_get_npkeys(dd));
 	nip->device_id = cpu_to_be16(dd->pcidev->device);
 	nip->revision = cpu_to_be32(dd->minrev);
diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index a1576ae..5a70e91 100644
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -239,16 +239,6 @@ bail:
 	return ret;
 }
 
-static __be64 get_sguid(struct hfi1_ibport *ibp, unsigned index)
-{
-	if (!index) {
-		struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-
-		return cpu_to_be64(ppd->guid);
-	}
-	return ibp->guids[index - 1];
-}
-
 static int gid_ok(union ib_gid *gid, __be64 gid_prefix, __be64 id)
 {
 	return (gid->global.interface_id == id &&
@@ -699,9 +689,9 @@ u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr,
 	/* The SGID is 32-bit aligned. */
 	hdr->sgid.global.subnet_prefix = ibp->rvp.gid_prefix;
 	hdr->sgid.global.interface_id =
-		grh->sgid_index && grh->sgid_index < ARRAY_SIZE(ibp->guids) ?
-		ibp->guids[grh->sgid_index - 1] :
-			cpu_to_be64(ppd_from_ibp(ibp)->guid);
+		grh->sgid_index < HFI1_GUIDS_PER_PORT ?
+		get_sguid(ibp, grh->sgid_index) :
+		get_sguid(ibp, HFI1_PORT_GUID_INDEX);
 	hdr->dgid = grh->dgid;
 
 	/* GRH header size in 32-bit words. */
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 9c3c237..6d8e37f 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -1485,15 +1485,11 @@ static int hfi1_get_guid_be(struct rvt_dev_info *rdi, struct rvt_ibport *rvp,
 			    int guid_index, __be64 *guid)
 {
 	struct hfi1_ibport *ibp = container_of(rvp, struct hfi1_ibport, rvp);
-	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 
-	if (guid_index == 0)
-		*guid = cpu_to_be64(ppd->guid);
-	else if (guid_index < HFI1_GUIDS_PER_PORT)
-		*guid = ibp->guids[guid_index - 1];
-	else
+	if (guid_index >= HFI1_GUIDS_PER_PORT)
 		return -EINVAL;
 
+	*guid = get_sguid(ibp, guid_index);
 	return 0;
 }
 
@@ -1622,6 +1618,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	struct hfi1_ibdev *dev = &dd->verbs_dev;
 	struct ib_device *ibdev = &dev->rdi.ibdev;
 	struct hfi1_pportdata *ppd = dd->pport;
+	struct hfi1_ibport *ibp = &ppd->ibport_data;
 	unsigned i;
 	int ret;
 	size_t lcpysz = IB_DEVICE_NAME_MAX;
@@ -1642,17 +1639,19 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	if (ret)
 		goto err_verbs_txreq;
 
+	/* Use first-port GUID as node guid */
+	ibdev->node_guid = get_sguid(ibp, HFI1_PORT_GUID_INDEX);
+
 	/*
 	 * The system image GUID is supposed to be the same for all
 	 * HFIs in a single system but since there can be other
 	 * device types in the system, we can't be sure this is unique.
 	 */
 	if (!ib_hfi1_sys_image_guid)
-		ib_hfi1_sys_image_guid = cpu_to_be64(ppd->guid);
+		ib_hfi1_sys_image_guid = ibdev->node_guid;
 	lcpysz = strlcpy(ibdev->name, class_name(), lcpysz);
 	strlcpy(ibdev->name + lcpysz, "_%d", IB_DEVICE_NAME_MAX - lcpysz);
 	ibdev->owner = THIS_MODULE;
-	ibdev->node_guid = cpu_to_be64(ppd->guid);
 	ibdev->phys_port_cnt = dd->num_pports;
 	ibdev->dma_device = &dd->pcidev->dev;
 	ibdev->modify_device = modify_device;
diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index 7a8af39..e6b8930 100644
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -73,7 +73,6 @@ struct hfi1_packet;
 #include "iowait.h"
 
 #define HFI1_MAX_RDMA_ATOMIC     16
-#define HFI1_GUIDS_PER_PORT	5
 
 /*
  * Increment this value if any changes that break userspace ABI
@@ -169,8 +168,6 @@ struct hfi1_ibport {
 	struct rvt_qp __rcu *qp[2];
 	struct rvt_ibport rvp;
 
-	__be64 guids[HFI1_GUIDS_PER_PORT	- 1];	/* writable GUIDs */
-
 	/* the first 16 entries are sl_to_vl for !OPA */
 	u8 sl_to_sc[32];
 	u8 sc_to_sl[32];

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 06/12] IB/hfi1: Optimize devdata cachelines

[Dennis Dalessandro]

From: Sebastian Sanchez <sebastian.sanchez-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

Profiling shows hot path struct members that need
to be in a minimum set of cachelines.

Group these struct member in the same cacheline:
	sc2vl_lock
	sc2vl
	rhf_rcv_function_map
	rcv_limit
	rhf_offset

Group these struct member in the same cacheline:
	process_pio_send
	process_dma_send
	pport
	rcd
	int_counter
	flags
	num_pports
	first_user_ctxt

Fill holes in struct hfi1_devdata revealed by pahole.

Reviewed-by: Mike Marciniszyn <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Sebastian Sanchez <sebastian.sanchez-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/hfi1/hfi.h |  111 +++++++++++++++++++-------------------
 1 files changed, 56 insertions(+), 55 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 87847cc..bec4607 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -852,32 +852,29 @@ struct hfi1_devdata {
 	u8 __iomem *kregend;
 	/* physical address of chip for io_remap, etc. */
 	resource_size_t physaddr;
-	/* receive context data */
-	struct hfi1_ctxtdata **rcd;
+	/* Per VL data. Enough for all VLs but not all elements are set/used. */
+	struct per_vl_data vld[PER_VL_SEND_CONTEXTS];
 	/* send context data */
 	struct send_context_info *send_contexts;
 	/* map hardware send contexts to software index */
 	u8 *hw_to_sw;
 	/* spinlock for allocating and releasing send context resources */
 	spinlock_t sc_lock;
-	/* Per VL data. Enough for all VLs but not all elements are set/used. */
-	struct per_vl_data vld[PER_VL_SEND_CONTEXTS];
 	/* lock for pio_map */
 	spinlock_t pio_map_lock;
+	/* Send Context initialization lock. */
+	spinlock_t sc_init_lock;
+	/* lock for sdma_map */
+	spinlock_t                          sde_map_lock;
 	/* array of kernel send contexts */
 	struct send_context **kernel_send_context;
 	/* array of vl maps */
 	struct pio_vl_map __rcu *pio_map;
-	/* seqlock for sc2vl */
-	seqlock_t sc2vl_lock;
-	u64 sc2vl[4];
-	/* Send Context initialization lock. */
-	spinlock_t sc_init_lock;
+	/* default flags to last descriptor */
+	u64 default_desc1;
 
 	/* fields common to all SDMA engines */
 
-	/* default flags to last descriptor */
-	u64 default_desc1;
 	volatile __le64                    *sdma_heads_dma; /* DMA'ed by chip */
 	dma_addr_t                          sdma_heads_phys;
 	void                               *sdma_pad_dma; /* DMA'ed by chip */
@@ -888,8 +885,6 @@ struct hfi1_devdata {
 	u32                                 chip_sdma_engines;
 	/* num used */
 	u32                                 num_sdma;
-	/* lock for sdma_map */
-	spinlock_t                          sde_map_lock;
 	/* array of engines sized by num_sdma */
 	struct sdma_engine                 *per_sdma;
 	/* array of vl maps */
@@ -898,14 +893,11 @@ struct hfi1_devdata {
 	wait_queue_head_t		  sdma_unfreeze_wq;
 	atomic_t			  sdma_unfreeze_count;
 
+	u32 lcb_access_count;		/* count of LCB users */
+
 	/* common data between shared ASIC HFIs in this OS */
 	struct hfi1_asic_data *asic_data;
 
-	/* hfi1_pportdata, points to array of (physical) port-specific
-	 * data structs, indexed by pidx (0..n-1)
-	 */
-	struct hfi1_pportdata *pport;
-
 	/* mem-mapped pointer to base of PIO buffers */
 	void __iomem *piobase;
 	/*
@@ -922,20 +914,13 @@ struct hfi1_devdata {
 	/* send context numbers and sizes for each type */
 	struct sc_config_sizes sc_sizes[SC_MAX];
 
-	u32 lcb_access_count;		/* count of LCB users */
-
 	char *boardname; /* human readable board info */
 
-	/* device (not port) flags, basically device capabilities */
-	u32 flags;
-
 	/* reset value */
 	u64 z_int_counter;
 	u64 z_rcv_limit;
 	u64 z_send_schedule;
-	/* percpu int_counter */
-	u64 __percpu *int_counter;
-	u64 __percpu *rcv_limit;
+
 	u64 __percpu *send_schedule;
 	/* number of receive contexts in use by the driver */
 	u32 num_rcv_contexts;
@@ -950,6 +935,7 @@ struct hfi1_devdata {
 	/* base receive interrupt timeout, in CSR units */
 	u32 rcv_intr_timeout_csr;
 
+	u32 freezelen; /* max length of freezemsg */
 	u64 __iomem *egrtidbase;
 	spinlock_t sendctrl_lock; /* protect changes to SendCtrl */
 	spinlock_t rcvctrl_lock; /* protect changes to RcvCtrl */
@@ -971,7 +957,6 @@ struct hfi1_devdata {
 	 * IB link status cheaply
 	 */
 	struct hfi1_status *status;
-	u32 freezelen; /* max length of freezemsg */
 
 	/* revision register shadow */
 	u64 revision;
@@ -999,6 +984,8 @@ struct hfi1_devdata {
 	u16 rcvegrbufsize_shift;
 	/* both sides of the PCIe link are gen3 capable */
 	u8 link_gen3_capable;
+	/* default link down value (poll/sleep) */
+	u8 link_default;
 	/* localbus width (1, 2,4,8,16,32) from config space  */
 	u32 lbus_width;
 	/* localbus speed in MHz */
@@ -1034,8 +1021,6 @@ struct hfi1_devdata {
 	u8 hfi1_id;
 	/* implementation code */
 	u8 icode;
-	/* default link down value (poll/sleep) */
-	u8 link_default;
 	/* vAU of this device */
 	u8 vau;
 	/* vCU of this device */
@@ -1046,27 +1031,17 @@ struct hfi1_devdata {
 	u16 vl15_init;
 
 	/* Misc small ints */
-	/* Number of physical ports available */
-	u8 num_pports;
-	/* Lowest context number which can be used by user processes */
-	u8 first_user_ctxt;
 	u8 n_krcv_queues;
 	u8 qos_shift;
-	u8 qpn_mask;
 
-	u16 rhf_offset; /* offset of RHF within receive header entry */
 	u16 irev;	/* implementation revision */
 	u16 dc8051_ver; /* 8051 firmware version */
 
+	spinlock_t hfi1_diag_trans_lock; /* protect diag observer ops */
 	struct platform_config platform_config;
 	struct platform_config_cache pcfg_cache;
 
 	struct diag_client *diag_client;
-	spinlock_t hfi1_diag_trans_lock; /* protect diag observer ops */
-
-	u8 psxmitwait_supported;
-	/* cycle length of PS* counters in HW (in picoseconds) */
-	u16 psxmitwait_check_rate;
 
 	/* MSI-X information */
 	struct hfi1_msix_entry *msix_entries;
@@ -1081,6 +1056,9 @@ struct hfi1_devdata {
 
 	struct rcv_array_data rcv_entries;
 
+	/* cycle length of PS* counters in HW (in picoseconds) */
+	u16 psxmitwait_check_rate;
+
 	/*
 	 * 64 bit synthetic counters
 	 */
@@ -1113,11 +1091,11 @@ struct hfi1_devdata {
 	struct err_info_rcvport err_info_rcvport;
 	struct err_info_constraint err_info_rcv_constraint;
 	struct err_info_constraint err_info_xmit_constraint;
-	u8 err_info_uncorrectable;
-	u8 err_info_fmconfig;
 
 	atomic_t drop_packet;
 	u8 do_drop;
+	u8 err_info_uncorrectable;
+	u8 err_info_fmconfig;
 
 	/*
 	 * Software counters for the status bits defined by the
@@ -1140,51 +1118,74 @@ struct hfi1_devdata {
 	u64 sw_cce_err_status_aggregate;
 	/* Software counter that aggregates all bypass packet rcv errors */
 	u64 sw_rcv_bypass_packet_errors;
-	/* receive interrupt functions */
-	rhf_rcv_function_ptr *rhf_rcv_function_map;
+	/* receive interrupt function */
 	rhf_rcv_function_ptr normal_rhf_rcv_functions[8];
 
+	/* Save the enabled LCB error bits */
+	u64 lcb_err_en;
+
 	/*
 	 * Handlers for outgoing data so that snoop/capture does not
 	 * have to have its hooks in the send path
 	 */
-	send_routine process_pio_send;
+	send_routine process_pio_send ____cacheline_aligned_in_smp;
 	send_routine process_dma_send;
 	void (*pio_inline_send)(struct hfi1_devdata *dd, struct pio_buf *pbuf,
 				u64 pbc, const void *from, size_t count);
+	/* hfi1_pportdata, points to array of (physical) port-specific
+	 * data structs, indexed by pidx (0..n-1)
+	 */
+	struct hfi1_pportdata *pport;
+	/* receive context data */
+	struct hfi1_ctxtdata **rcd;
+	u64 __percpu *int_counter;
+	/* device (not port) flags, basically device capabilities */
+	u16 flags;
+	/* Number of physical ports available */
+	u8 num_pports;
+	/* Lowest context number which can be used by user processes */
+	u8 first_user_ctxt;
+	/* adding a new field here would make it part of this cacheline */
+
+	/* seqlock for sc2vl */
+	seqlock_t sc2vl_lock ____cacheline_aligned_in_smp;
+	u64 sc2vl[4];
+	/* receive interrupt functions */
+	rhf_rcv_function_ptr *rhf_rcv_function_map;
+	u64 __percpu *rcv_limit;
+	u16 rhf_offset; /* offset of RHF within receive header entry */
+	/* adding a new field here would make it part of this cacheline */
 
 	/* OUI comes from the HW. Used everywhere as 3 separate bytes. */
 	u8 oui1;
 	u8 oui2;
 	u8 oui3;
+	u8 dc_shutdown;
+
 	/* Timer and counter used to detect RcvBufOvflCnt changes */
 	struct timer_list rcverr_timer;
-	u32 rcv_ovfl_cnt;
 
 	wait_queue_head_t event_queue;
 
-	/* Save the enabled LCB error bits */
-	u64 lcb_err_en;
-	u8 dc_shutdown;
-
 	/* receive context tail dummy address */
 	__le64 *rcvhdrtail_dummy_kvaddr;
 	dma_addr_t rcvhdrtail_dummy_dma;
 
-	bool eprom_available;	/* true if EPROM is available for this device */
-	bool aspm_supported;	/* Does HW support ASPM */
-	bool aspm_enabled;	/* ASPM state: enabled/disabled */
+	u32 rcv_ovfl_cnt;
 	/* Serialize ASPM enable/disable between multiple verbs contexts */
 	spinlock_t aspm_lock;
 	/* Number of verbs contexts which have disabled ASPM */
 	atomic_t aspm_disabled_cnt;
 	/* Keeps track of user space clients */
 	atomic_t user_refcount;
+	struct hfi1_affinity *affinity;
 	/* Used to wait for outstanding user space clients before dev removal */
 	struct completion user_comp;
-
-	struct hfi1_affinity *affinity;
+	bool eprom_available;	/* true if EPROM is available for this device */
+	bool aspm_supported;	/* Does HW support ASPM */
+	bool aspm_enabled;	/* ASPM state: enabled/disabled */
 	struct rhashtable sdma_rht;
+
 	struct kobject kobj;
 };
 

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 07/12] IB/hfi1: Fix a potential memory leak in hfi1_create_ctxts()

[Dennis Dalessandro]

From: Jianxin Xiong <jianxin.xiong-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

In the function hfi1_create_ctxts the array "dd->rcd" is allocated and
then populated with allocated resources in a loop. Previously, if
error happened during the loop, only resource allocated in the current
iteration would be freed. The array itself would then be freed, leaving
the resources that were allocated in previous iterations and referenced
by the array elements in limbo.

This patch makes sure all allocated resources are freed before freeing
the array "dd->rcd". Also the resource allocation now takes account of
the numa node the device is attached to.

Reviewed-by: Tadeusz Struk <tadeusz.struk-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Jianxin Xiong <jianxin.xiong-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/hfi1/init.c |   13 +++++++------
 1 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 5872f10..4a7e741 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -144,6 +144,8 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd)
 		struct hfi1_ctxtdata *rcd;
 
 		ppd = dd->pport + (i % dd->num_pports);
+
+		/* dd->rcd[i] gets assigned inside the callee */
 		rcd = hfi1_create_ctxtdata(ppd, i, dd->node);
 		if (!rcd) {
 			dd_dev_err(dd,
@@ -169,8 +171,6 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd)
 		if (!rcd->sc) {
 			dd_dev_err(dd,
 				   "Unable to allocate kernel send context, failing\n");
-			dd->rcd[rcd->ctxt] = NULL;
-			hfi1_free_ctxtdata(dd, rcd);
 			goto nomem;
 		}
 
@@ -178,9 +178,6 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd)
 		if (ret < 0) {
 			dd_dev_err(dd,
 				   "Failed to setup kernel receive context, failing\n");
-			sc_free(rcd->sc);
-			dd->rcd[rcd->ctxt] = NULL;
-			hfi1_free_ctxtdata(dd, rcd);
 			ret = -EFAULT;
 			goto bail;
 		}
@@ -196,6 +193,10 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd)
 nomem:
 	ret = -ENOMEM;
 bail:
+	if (dd->rcd) {
+		for (i = 0; i < dd->num_rcv_contexts; ++i)
+			hfi1_free_ctxtdata(dd, dd->rcd[i]);
+	}
 	kfree(dd->rcd);
 	dd->rcd = NULL;
 	return ret;
@@ -216,7 +217,7 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
 	    dd->num_rcv_contexts - dd->first_user_ctxt)
 		kctxt_ngroups = (dd->rcv_entries.nctxt_extra -
 				 (dd->num_rcv_contexts - dd->first_user_ctxt));
-	rcd = kzalloc(sizeof(*rcd), GFP_KERNEL);
+	rcd = kzalloc_node(sizeof(*rcd), GFP_KERNEL, numa);
 	if (rcd) {
 		u32 rcvtids, max_entries;
 

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 08/12] IB/hfi1: Add active channel and backplane support for integrated devices

[Dennis Dalessandro]

From: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

Use scratch registers within the HFI1 device to recover signal
integrity information that is then used to tune the channel. While
there, update error messages to better convey the result of falling
back to a backup file.

Reviewed-by: Ira Weiny <ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Reviewed-by: Dean Luick <dean.luick-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/hfi1/chip_registers.h |    3 +
 drivers/infiniband/hw/hfi1/firmware.c       |  136 +++++++++++++++++++++----
 drivers/infiniband/hw/hfi1/hfi.h            |   16 +++
 drivers/infiniband/hw/hfi1/platform.c       |  149 ++++++++++++++++++++++-----
 drivers/infiniband/hw/hfi1/platform.h       |  117 +++++++++++++++++++++
 5 files changed, 376 insertions(+), 45 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/chip_registers.h b/drivers/infiniband/hw/hfi1/chip_registers.h
index 5b99938..5bfa839 100644
--- a/drivers/infiniband/hw/hfi1/chip_registers.h
+++ b/drivers/infiniband/hw/hfi1/chip_registers.h
@@ -415,6 +415,9 @@
 #define ASIC_CFG_SBUS_REQUEST_DATA_IN_SHIFT 32
 #define ASIC_CFG_SBUS_REQUEST_RECEIVER_ADDR_SHIFT 0
 #define ASIC_CFG_SCRATCH (ASIC + 0x000000000020)
+#define ASIC_CFG_SCRATCH_1 (ASIC_CFG_SCRATCH + 0x08)
+#define ASIC_CFG_SCRATCH_2 (ASIC_CFG_SCRATCH + 0x10)
+#define ASIC_CFG_SCRATCH_3 (ASIC_CFG_SCRATCH + 0x18)
 #define ASIC_CFG_THERM_POLL_EN (ASIC + 0x000000000050)
 #define ASIC_EEP_ADDR_CMD (ASIC + 0x000000000308)
 #define ASIC_EEP_ADDR_CMD_EP_ADDR_MASK 0xFFFFFFull
diff --git a/drivers/infiniband/hw/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c
index 13db8eb..9a36c8c 100644
--- a/drivers/infiniband/hw/hfi1/firmware.c
+++ b/drivers/infiniband/hw/hfi1/firmware.c
@@ -707,6 +707,9 @@ static int obtain_firmware(struct hfi1_devdata *dd)
 				       &dd->pcidev->dev);
 		if (err) {
 			platform_config = NULL;
+			dd_dev_err(dd,
+				   "%s: No default platform config file found\n",
+				   __func__);
 			goto done;
 		}
 		dd->platform_config.data = platform_config->data;
@@ -1761,8 +1764,17 @@ int parse_platform_config(struct hfi1_devdata *dd)
 	u32 record_idx = 0, table_type = 0, table_length_dwords = 0;
 	int ret = -EINVAL; /* assume failure */
 
+	/*
+	 * For integrated devices that did not fall back to the default file,
+	 * the SI tuning information for active channels is acquired from the
+	 * scratch register bitmap, thus there is no platform config to parse.
+	 * Skip parsing in these situations.
+	 */
+	if (is_integrated(dd) && !platform_config_load)
+		return 0;
+
 	if (!dd->platform_config.data) {
-		dd_dev_info(dd, "%s: Missing config file\n", __func__);
+		dd_dev_err(dd, "%s: Missing config file\n", __func__);
 		goto bail;
 	}
 	ptr = (u32 *)dd->platform_config.data;
@@ -1770,7 +1782,7 @@ int parse_platform_config(struct hfi1_devdata *dd)
 	magic_num = *ptr;
 	ptr++;
 	if (magic_num != PLATFORM_CONFIG_MAGIC_NUM) {
-		dd_dev_info(dd, "%s: Bad config file\n", __func__);
+		dd_dev_err(dd, "%s: Bad config file\n", __func__);
 		goto bail;
 	}
 
@@ -1797,9 +1809,9 @@ int parse_platform_config(struct hfi1_devdata *dd)
 		header1 = *ptr;
 		header2 = *(ptr + 1);
 		if (header1 != ~header2) {
-			dd_dev_info(dd, "%s: Failed validation at offset %ld\n",
-				    __func__, (ptr - (u32 *)
-					       dd->platform_config.data));
+			dd_dev_err(dd, "%s: Failed validation at offset %ld\n",
+				   __func__, (ptr - (u32 *)
+					      dd->platform_config.data));
 			goto bail;
 		}
 
@@ -1841,11 +1853,11 @@ int parse_platform_config(struct hfi1_devdata *dd)
 							table_length_dwords;
 				break;
 			default:
-				dd_dev_info(dd,
-					    "%s: Unknown data table %d, offset %ld\n",
-					    __func__, table_type,
-					    (ptr - (u32 *)
-					     dd->platform_config.data));
+				dd_dev_err(dd,
+					   "%s: Unknown data table %d, offset %ld\n",
+					   __func__, table_type,
+					   (ptr - (u32 *)
+					    dd->platform_config.data));
 				goto bail; /* We don't trust this file now */
 			}
 			pcfgcache->config_tables[table_type].table = ptr;
@@ -1865,11 +1877,11 @@ int parse_platform_config(struct hfi1_devdata *dd)
 			case PLATFORM_CONFIG_VARIABLE_SETTINGS_TABLE:
 				break;
 			default:
-				dd_dev_info(dd,
-					    "%s: Unknown meta table %d, offset %ld\n",
-					    __func__, table_type,
-					    (ptr -
-					     (u32 *)dd->platform_config.data));
+				dd_dev_err(dd,
+					   "%s: Unknown meta table %d, offset %ld\n",
+					   __func__, table_type,
+					   (ptr -
+					    (u32 *)dd->platform_config.data));
 				goto bail; /* We don't trust this file now */
 			}
 			pcfgcache->config_tables[table_type].table_metadata =
@@ -1884,10 +1896,9 @@ int parse_platform_config(struct hfi1_devdata *dd)
 		/* Jump the table */
 		ptr += table_length_dwords;
 		if (crc != *ptr) {
-			dd_dev_info(dd, "%s: Failed CRC check at offset %ld\n",
-				    __func__, (ptr -
-					       (u32 *)
-					       dd->platform_config.data));
+			dd_dev_err(dd, "%s: Failed CRC check at offset %ld\n",
+				   __func__, (ptr -
+				   (u32 *)dd->platform_config.data));
 			goto bail;
 		}
 		/* Jump the CRC DWORD */
@@ -1901,6 +1912,84 @@ bail:
 	return ret;
 }
 
+static void get_integrated_platform_config_field(
+		struct hfi1_devdata *dd,
+		enum platform_config_table_type_encoding table_type,
+		int field_index, u32 *data)
+{
+	struct hfi1_pportdata *ppd = dd->pport;
+	u8 *cache = ppd->qsfp_info.cache;
+	u32 tx_preset = 0;
+
+	switch (table_type) {
+	case PLATFORM_CONFIG_SYSTEM_TABLE:
+		if (field_index == SYSTEM_TABLE_QSFP_POWER_CLASS_MAX)
+			*data = ppd->max_power_class;
+		else if (field_index == SYSTEM_TABLE_QSFP_ATTENUATION_DEFAULT_25G)
+			*data = ppd->default_atten;
+		break;
+	case PLATFORM_CONFIG_PORT_TABLE:
+		if (field_index == PORT_TABLE_PORT_TYPE)
+			*data = ppd->port_type;
+		else if (field_index == PORT_TABLE_LOCAL_ATTEN_25G)
+			*data = ppd->local_atten;
+		else if (field_index == PORT_TABLE_REMOTE_ATTEN_25G)
+			*data = ppd->remote_atten;
+		break;
+	case PLATFORM_CONFIG_RX_PRESET_TABLE:
+		if (field_index == RX_PRESET_TABLE_QSFP_RX_CDR_APPLY)
+			*data = (ppd->rx_preset & QSFP_RX_CDR_APPLY_SMASK) >>
+				QSFP_RX_CDR_APPLY_SHIFT;
+		else if (field_index == RX_PRESET_TABLE_QSFP_RX_EMP_APPLY)
+			*data = (ppd->rx_preset & QSFP_RX_EMP_APPLY_SMASK) >>
+				QSFP_RX_EMP_APPLY_SHIFT;
+		else if (field_index == RX_PRESET_TABLE_QSFP_RX_AMP_APPLY)
+			*data = (ppd->rx_preset & QSFP_RX_AMP_APPLY_SMASK) >>
+				QSFP_RX_AMP_APPLY_SHIFT;
+		else if (field_index == RX_PRESET_TABLE_QSFP_RX_CDR)
+			*data = (ppd->rx_preset & QSFP_RX_CDR_SMASK) >>
+				QSFP_RX_CDR_SHIFT;
+		else if (field_index == RX_PRESET_TABLE_QSFP_RX_EMP)
+			*data = (ppd->rx_preset & QSFP_RX_EMP_SMASK) >>
+				QSFP_RX_EMP_SHIFT;
+		else if (field_index == RX_PRESET_TABLE_QSFP_RX_AMP)
+			*data = (ppd->rx_preset & QSFP_RX_AMP_SMASK) >>
+				QSFP_RX_AMP_SHIFT;
+		break;
+	case PLATFORM_CONFIG_TX_PRESET_TABLE:
+		if (cache[QSFP_EQ_INFO_OFFS] & 0x4)
+			tx_preset = ppd->tx_preset_eq;
+		else
+			tx_preset = ppd->tx_preset_noeq;
+		if (field_index == TX_PRESET_TABLE_PRECUR)
+			*data = (tx_preset & TX_PRECUR_SMASK) >>
+				TX_PRECUR_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_ATTN)
+			*data = (tx_preset & TX_ATTN_SMASK) >>
+				TX_ATTN_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_POSTCUR)
+			*data = (tx_preset & TX_POSTCUR_SMASK) >>
+				TX_POSTCUR_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_QSFP_TX_CDR_APPLY)
+			*data = (tx_preset & QSFP_TX_CDR_APPLY_SMASK) >>
+				QSFP_TX_CDR_APPLY_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_QSFP_TX_EQ_APPLY)
+			*data = (tx_preset & QSFP_TX_EQ_APPLY_SMASK) >>
+				QSFP_TX_EQ_APPLY_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_QSFP_TX_CDR)
+			*data = (tx_preset & QSFP_TX_CDR_SMASK) >>
+				QSFP_TX_CDR_SHIFT;
+		else if (field_index == TX_PRESET_TABLE_QSFP_TX_EQ)
+			*data = (tx_preset & QSFP_TX_EQ_SMASK) >>
+				QSFP_TX_EQ_SHIFT;
+		break;
+	case PLATFORM_CONFIG_QSFP_ATTEN_TABLE:
+	case PLATFORM_CONFIG_VARIABLE_SETTINGS_TABLE:
+	default:
+		break;
+	}
+}
+
 static int get_platform_fw_field_metadata(struct hfi1_devdata *dd, int table,
 					  int field, u32 *field_len_bits,
 					  u32 *field_start_bits)
@@ -1976,6 +2065,15 @@ int get_platform_config_field(struct hfi1_devdata *dd,
 	else
 		return -EINVAL;
 
+	if (is_integrated(dd) && !platform_config_load) {
+		/*
+		 * Use saved configuration from ppd for integrated platforms
+		 */
+		get_integrated_platform_config_field(dd, table_type,
+						     field_index, data);
+		return 0;
+	}
+
 	ret = get_platform_fw_field_metadata(dd, table_type, field_index,
 					     &field_len_bits,
 					     &field_start_bits);
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index bec4607..94cc5f2 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -582,8 +582,16 @@ struct hfi1_pportdata {
 	struct kobject vl2mtu_kobj;
 
 	/* PHY support */
-	u32 port_type;
 	struct qsfp_data qsfp_info;
+	/* Values for SI tuning of SerDes */
+	u32 port_type;
+	u32 tx_preset_eq;
+	u32 tx_preset_noeq;
+	u32 rx_preset;
+	u8  local_atten;
+	u8  remote_atten;
+	u8  default_atten;
+	u8  max_power_class;
 
 	/* GUIDs for this interface, in host order, guids[0] is a port guid */
 	u64 guids[HFI1_GUIDS_PER_PORT];
@@ -2037,6 +2045,12 @@ static inline u32 qsfp_resource(struct hfi1_devdata *dd)
 	return i2c_target(dd->hfi1_id);
 }
 
+/* Is this device integrated or discrete? */
+static inline bool is_integrated(struct hfi1_devdata *dd)
+{
+	return dd->pcidev->device == PCI_DEVICE_ID_INTEL1;
+}
+
 int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp);
 
 #define DD_DEV_ENTRY(dd)       __string(dev, dev_name(&(dd)->pcidev->dev))
diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c
index 2024331..0e70438 100644
--- a/drivers/infiniband/hw/hfi1/platform.c
+++ b/drivers/infiniband/hw/hfi1/platform.c
@@ -49,6 +49,90 @@
 #include "efivar.h"
 #include "eprom.h"
 
+static int validate_scratch_checksum(struct hfi1_devdata *dd)
+{
+	u64 checksum = 0, temp_scratch = 0;
+	int i, j, version;
+
+	temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH);
+	version = (temp_scratch & BITMAP_VERSION_SMASK) >> BITMAP_VERSION_SHIFT;
+
+	/* Prevent power on default of all zeroes from passing checksum */
+	if (!version)
+		return 0;
+
+	/*
+	 * ASIC scratch 0 only contains the checksum and bitmap version as
+	 * fields of interest, both of which are handled separately from the
+	 * loop below, so skip it
+	 */
+	checksum += version;
+	for (i = 1; i < ASIC_NUM_SCRATCH; i++) {
+		temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH + (8 * i));
+		for (j = sizeof(u64); j != 0; j -= 2) {
+			checksum += (temp_scratch & 0xFFFF);
+			temp_scratch >>= 16;
+		}
+	}
+
+	while (checksum >> 16)
+		checksum = (checksum & CHECKSUM_MASK) + (checksum >> 16);
+
+	temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH);
+	temp_scratch &= CHECKSUM_SMASK;
+	temp_scratch >>= CHECKSUM_SHIFT;
+
+	if (checksum + temp_scratch == 0xFFFF)
+		return 1;
+	return 0;
+}
+
+static void save_platform_config_fields(struct hfi1_devdata *dd)
+{
+	struct hfi1_pportdata *ppd = dd->pport;
+	u64 temp_scratch = 0, temp_dest = 0;
+
+	temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH_1);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_PORT_TYPE_SMASK :
+		     PORT0_PORT_TYPE_SMASK);
+	ppd->port_type = temp_dest >>
+			 (dd->hfi1_id ? PORT1_PORT_TYPE_SHIFT :
+			  PORT0_PORT_TYPE_SHIFT);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_LOCAL_ATTEN_SMASK :
+		     PORT0_LOCAL_ATTEN_SMASK);
+	ppd->local_atten = temp_dest >>
+			   (dd->hfi1_id ? PORT1_LOCAL_ATTEN_SHIFT :
+			    PORT0_LOCAL_ATTEN_SHIFT);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_REMOTE_ATTEN_SMASK :
+		     PORT0_REMOTE_ATTEN_SMASK);
+	ppd->remote_atten = temp_dest >>
+			    (dd->hfi1_id ? PORT1_REMOTE_ATTEN_SHIFT :
+			     PORT0_REMOTE_ATTEN_SHIFT);
+
+	temp_dest = temp_scratch &
+		    (dd->hfi1_id ? PORT1_DEFAULT_ATTEN_SMASK :
+		     PORT0_DEFAULT_ATTEN_SMASK);
+	ppd->default_atten = temp_dest >>
+			     (dd->hfi1_id ? PORT1_DEFAULT_ATTEN_SHIFT :
+			      PORT0_DEFAULT_ATTEN_SHIFT);
+
+	temp_scratch = read_csr(dd, dd->hfi1_id ? ASIC_CFG_SCRATCH_3 :
+				ASIC_CFG_SCRATCH_2);
+
+	ppd->tx_preset_eq = (temp_scratch & TX_EQ_SMASK) >> TX_EQ_SHIFT;
+	ppd->tx_preset_noeq = (temp_scratch & TX_NO_EQ_SMASK) >> TX_NO_EQ_SHIFT;
+	ppd->rx_preset = (temp_scratch & RX_SMASK) >> RX_SHIFT;
+
+	ppd->max_power_class = (temp_scratch & QSFP_MAX_POWER_SMASK) >>
+				QSFP_MAX_POWER_SHIFT;
+}
+
 void get_platform_config(struct hfi1_devdata *dd)
 {
 	int ret = 0;
@@ -56,38 +140,49 @@ void get_platform_config(struct hfi1_devdata *dd)
 	u8 *temp_platform_config = NULL;
 	u32 esize;
 
-	ret = eprom_read_platform_config(dd, (void **)&temp_platform_config,
-					 &esize);
-	if (!ret) {
-		/* success */
-		size = esize;
-		goto success;
+	if (is_integrated(dd)) {
+		if (validate_scratch_checksum(dd)) {
+			save_platform_config_fields(dd);
+			return;
+		}
+		dd_dev_err(dd, "%s: Config bitmap corrupted/uninitialized\n",
+			   __func__);
+		dd_dev_err(dd,
+			   "%s: Please update your BIOS to support active channels\n",
+			   __func__);
+	} else {
+		ret = eprom_read_platform_config(dd,
+						 (void **)&temp_platform_config,
+						 &esize);
+		if (!ret) {
+			/* success */
+			dd->platform_config.data = temp_platform_config;
+			dd->platform_config.size = esize;
+			return;
+		}
+		/* fail, try EFI variable */
+
+		ret = read_hfi1_efi_var(dd, "configuration", &size,
+					(void **)&temp_platform_config);
+		if (!ret) {
+			dd->platform_config.data = temp_platform_config;
+			dd->platform_config.size = size;
+			return;
+		}
 	}
-	/* fail, try EFI variable */
-
-	ret = read_hfi1_efi_var(dd, "configuration", &size,
-				(void **)&temp_platform_config);
-	if (!ret)
-		goto success;
-
-	dd_dev_info(dd,
-		    "%s: Failed to get platform config from UEFI, falling back to request firmware\n",
-		    __func__);
+	dd_dev_err(dd,
+		   "%s: Failed to get platform config, falling back to sub-optimal default file\n",
+		   __func__);
 	/* fall back to request firmware */
 	platform_config_load = 1;
-	return;
-
-success:
-	dd->platform_config.data = temp_platform_config;
-	dd->platform_config.size = size;
 }
 
 void free_platform_config(struct hfi1_devdata *dd)
 {
 	if (!platform_config_load) {
 		/*
-		 * was loaded from EFI, release memory
-		 * allocated by read_efi_var
+		 * was loaded from EFI or the EPROM, release memory
+		 * allocated by read_efi_var/eprom_read_platform_config
 		 */
 		kfree(dd->platform_config.data);
 	}
@@ -100,12 +195,16 @@ void free_platform_config(struct hfi1_devdata *dd)
 void get_port_type(struct hfi1_pportdata *ppd)
 {
 	int ret;
+	u32 temp;
 
 	ret = get_platform_config_field(ppd->dd, PLATFORM_CONFIG_PORT_TABLE, 0,
-					PORT_TABLE_PORT_TYPE, &ppd->port_type,
+					PORT_TABLE_PORT_TYPE, &temp,
 					4);
-	if (ret)
+	if (ret) {
 		ppd->port_type = PORT_TYPE_UNKNOWN;
+		return;
+	}
+	ppd->port_type = temp;
 }
 
 int set_qsfp_tx(struct hfi1_pportdata *ppd, int on)
diff --git a/drivers/infiniband/hw/hfi1/platform.h b/drivers/infiniband/hw/hfi1/platform.h
index e2c2161..3115540 100644
--- a/drivers/infiniband/hw/hfi1/platform.h
+++ b/drivers/infiniband/hw/hfi1/platform.h
@@ -295,6 +295,123 @@ enum link_tuning_encoding {
 	OPA_UNKNOWN_TUNING
 };
 
+/*
+ * Shifts and masks for the link SI tuning values stuffed into the ASIC scratch
+ * registers for integrated platforms
+ */
+#define PORT0_PORT_TYPE_SHIFT		0
+#define PORT0_LOCAL_ATTEN_SHIFT		4
+#define PORT0_REMOTE_ATTEN_SHIFT	10
+#define PORT0_DEFAULT_ATTEN_SHIFT	32
+
+#define PORT1_PORT_TYPE_SHIFT		16
+#define PORT1_LOCAL_ATTEN_SHIFT		20
+#define PORT1_REMOTE_ATTEN_SHIFT	26
+#define PORT1_DEFAULT_ATTEN_SHIFT	40
+
+#define PORT0_PORT_TYPE_MASK		0xFUL
+#define PORT0_LOCAL_ATTEN_MASK		0x3FUL
+#define PORT0_REMOTE_ATTEN_MASK		0x3FUL
+#define PORT0_DEFAULT_ATTEN_MASK	0xFFUL
+
+#define PORT1_PORT_TYPE_MASK		0xFUL
+#define PORT1_LOCAL_ATTEN_MASK		0x3FUL
+#define PORT1_REMOTE_ATTEN_MASK		0x3FUL
+#define PORT1_DEFAULT_ATTEN_MASK	0xFFUL
+
+#define PORT0_PORT_TYPE_SMASK		(PORT0_PORT_TYPE_MASK << \
+					 PORT0_PORT_TYPE_SHIFT)
+#define PORT0_LOCAL_ATTEN_SMASK		(PORT0_LOCAL_ATTEN_MASK << \
+					 PORT0_LOCAL_ATTEN_SHIFT)
+#define PORT0_REMOTE_ATTEN_SMASK	(PORT0_REMOTE_ATTEN_MASK << \
+					 PORT0_REMOTE_ATTEN_SHIFT)
+#define PORT0_DEFAULT_ATTEN_SMASK	(PORT0_DEFAULT_ATTEN_MASK << \
+					 PORT0_DEFAULT_ATTEN_SHIFT)
+
+#define PORT1_PORT_TYPE_SMASK		(PORT1_PORT_TYPE_MASK << \
+					 PORT1_PORT_TYPE_SHIFT)
+#define PORT1_LOCAL_ATTEN_SMASK		(PORT1_LOCAL_ATTEN_MASK << \
+					 PORT1_LOCAL_ATTEN_SHIFT)
+#define PORT1_REMOTE_ATTEN_SMASK	(PORT1_REMOTE_ATTEN_MASK << \
+					 PORT1_REMOTE_ATTEN_SHIFT)
+#define PORT1_DEFAULT_ATTEN_SMASK	(PORT1_DEFAULT_ATTEN_MASK << \
+					 PORT1_DEFAULT_ATTEN_SHIFT)
+
+#define QSFP_MAX_POWER_SHIFT		0
+#define TX_NO_EQ_SHIFT			4
+#define TX_EQ_SHIFT			25
+#define RX_SHIFT			46
+
+#define QSFP_MAX_POWER_MASK		0xFUL
+#define TX_NO_EQ_MASK			0x1FFFFFUL
+#define TX_EQ_MASK			0x1FFFFFUL
+#define RX_MASK				0xFFFFUL
+
+#define QSFP_MAX_POWER_SMASK		(QSFP_MAX_POWER_MASK << \
+					 QSFP_MAX_POWER_SHIFT)
+#define TX_NO_EQ_SMASK			(TX_NO_EQ_MASK << TX_NO_EQ_SHIFT)
+#define TX_EQ_SMASK			(TX_EQ_MASK << TX_EQ_SHIFT)
+#define RX_SMASK			(RX_MASK << RX_SHIFT)
+
+#define TX_PRECUR_SHIFT			0
+#define TX_ATTN_SHIFT			4
+#define QSFP_TX_CDR_APPLY_SHIFT		9
+#define QSFP_TX_EQ_APPLY_SHIFT		10
+#define QSFP_TX_CDR_SHIFT		11
+#define QSFP_TX_EQ_SHIFT		12
+#define TX_POSTCUR_SHIFT		16
+
+#define TX_PRECUR_MASK			0xFUL
+#define TX_ATTN_MASK			0x1FUL
+#define QSFP_TX_CDR_APPLY_MASK		0x1UL
+#define QSFP_TX_EQ_APPLY_MASK		0x1UL
+#define QSFP_TX_CDR_MASK		0x1UL
+#define QSFP_TX_EQ_MASK			0xFUL
+#define TX_POSTCUR_MASK			0x1FUL
+
+#define TX_PRECUR_SMASK			(TX_PRECUR_MASK << TX_PRECUR_SHIFT)
+#define TX_ATTN_SMASK			(TX_ATTN_MASK << TX_ATTN_SHIFT)
+#define QSFP_TX_CDR_APPLY_SMASK		(QSFP_TX_CDR_APPLY_MASK << \
+					 QSFP_TX_CDR_APPLY_SHIFT)
+#define QSFP_TX_EQ_APPLY_SMASK		(QSFP_TX_EQ_APPLY_MASK << \
+					 QSFP_TX_EQ_APPLY_SHIFT)
+#define QSFP_TX_CDR_SMASK		(QSFP_TX_CDR_MASK << QSFP_TX_CDR_SHIFT)
+#define QSFP_TX_EQ_SMASK		(QSFP_TX_EQ_MASK << QSFP_TX_EQ_SHIFT)
+#define TX_POSTCUR_SMASK		(TX_POSTCUR_MASK << TX_POSTCUR_SHIFT)
+
+#define QSFP_RX_CDR_APPLY_SHIFT		0
+#define QSFP_RX_EMP_APPLY_SHIFT		1
+#define QSFP_RX_AMP_APPLY_SHIFT		2
+#define QSFP_RX_CDR_SHIFT		3
+#define QSFP_RX_EMP_SHIFT		4
+#define QSFP_RX_AMP_SHIFT		8
+
+#define QSFP_RX_CDR_APPLY_MASK		0x1UL
+#define QSFP_RX_EMP_APPLY_MASK		0x1UL
+#define QSFP_RX_AMP_APPLY_MASK		0x1UL
+#define QSFP_RX_CDR_MASK		0x1UL
+#define QSFP_RX_EMP_MASK		0xFUL
+#define QSFP_RX_AMP_MASK		0x3UL
+
+#define QSFP_RX_CDR_APPLY_SMASK		(QSFP_RX_CDR_APPLY_MASK << \
+					 QSFP_RX_CDR_APPLY_SHIFT)
+#define QSFP_RX_EMP_APPLY_SMASK		(QSFP_RX_EMP_APPLY_MASK << \
+					 QSFP_RX_EMP_APPLY_SHIFT)
+#define QSFP_RX_AMP_APPLY_SMASK		(QSFP_RX_AMP_APPLY_MASK << \
+					 QSFP_RX_AMP_APPLY_SHIFT)
+#define QSFP_RX_CDR_SMASK		(QSFP_RX_CDR_MASK << QSFP_RX_CDR_SHIFT)
+#define QSFP_RX_EMP_SMASK		(QSFP_RX_EMP_MASK << QSFP_RX_EMP_SHIFT)
+#define QSFP_RX_AMP_SMASK		(QSFP_RX_AMP_MASK << QSFP_RX_AMP_SHIFT)
+
+#define BITMAP_VERSION			1
+#define BITMAP_VERSION_SHIFT		44
+#define BITMAP_VERSION_MASK		0xFUL
+#define BITMAP_VERSION_SMASK		(BITMAP_VERSION_MASK << \
+					 BITMAP_VERSION_SHIFT)
+#define CHECKSUM_SHIFT			48
+#define CHECKSUM_MASK			0xFFFFUL
+#define CHECKSUM_SMASK			(CHECKSUM_MASK << CHECKSUM_SHIFT)
+
 /* platform.c */
 void get_platform_config(struct hfi1_devdata *dd);
 void free_platform_config(struct hfi1_devdata *dd);

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 09/12] IB/hfi1: Remove leftover snoop references

[Dennis Dalessandro]

A few snoop related variables were missed in the snoop/capture removal
to get out of staging. Go back and clean those up too.

Reviewed-by: Dean Luick <dean.luick-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/hfi1/chip.c     |   18 +---------
 drivers/infiniband/hw/hfi1/hfi.h      |   40 +---------------------
 drivers/infiniband/hw/hfi1/trace_rx.h |   60 ---------------------------------
 3 files changed, 4 insertions(+), 114 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index a0f05d7..bf645e9 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -6301,19 +6301,8 @@ void set_up_vl15(struct hfi1_devdata *dd, u8 vau, u16 vl15buf)
 	/* leave shared count at zero for both global and VL15 */
 	write_global_credit(dd, vau, vl15buf, 0);
 
-	/* We may need some credits for another VL when sending packets
-	 * with the snoop interface. Dividing it down the middle for VL15
-	 * and VL0 should suffice.
-	 */
-	if (unlikely(dd->hfi1_snoop.mode_flag == HFI1_PORT_SNOOP_MODE)) {
-		write_csr(dd, SEND_CM_CREDIT_VL15, (u64)(vl15buf >> 1)
-		    << SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT);
-		write_csr(dd, SEND_CM_CREDIT_VL, (u64)(vl15buf >> 1)
-		    << SEND_CM_CREDIT_VL_DEDICATED_LIMIT_VL_SHIFT);
-	} else {
-		write_csr(dd, SEND_CM_CREDIT_VL15, (u64)vl15buf
-			<< SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT);
-	}
+	write_csr(dd, SEND_CM_CREDIT_VL15, (u64)vl15buf
+		  << SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT);
 }
 
 /*
@@ -9915,9 +9904,6 @@ static void set_lidlmc(struct hfi1_pportdata *ppd)
 	u32 mask = ~((1U << ppd->lmc) - 1);
 	u64 c1 = read_csr(ppd->dd, DCC_CFG_PORT_CONFIG1);
 
-	if (dd->hfi1_snoop.mode_flag)
-		dd_dev_info(dd, "Set lid/lmc while snooping");
-
 	c1 &= ~(DCC_CFG_PORT_CONFIG1_TARGET_DLID_SMASK
 		| DCC_CFG_PORT_CONFIG1_DLID_MASK_SMASK);
 	c1 |= ((ppd->lid & DCC_CFG_PORT_CONFIG1_TARGET_DLID_MASK)
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 94cc5f2..1453c5c 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -367,26 +367,6 @@ struct hfi1_packet {
 	u8 etype;
 };
 
-/*
- * Private data for snoop/capture support.
- */
-struct hfi1_snoop_data {
-	int mode_flag;
-	struct cdev cdev;
-	struct device *class_dev;
-	/* protect snoop data */
-	spinlock_t snoop_lock;
-	struct list_head queue;
-	wait_queue_head_t waitq;
-	void *filter_value;
-	int (*filter_callback)(void *hdr, void *data, void *value);
-	u64 dcc_cfg; /* saved value of DCC Cfg register */
-};
-
-/* snoop mode_flag values */
-#define HFI1_PORT_SNOOP_MODE     1U
-#define HFI1_PORT_CAPTURE_MODE   2U
-
 struct rvt_sge_state;
 
 /*
@@ -1094,8 +1074,6 @@ struct hfi1_devdata {
 	char *portcntrnames;
 	size_t portcntrnameslen;
 
-	struct hfi1_snoop_data hfi1_snoop;
-
 	struct err_info_rcvport err_info_rcvport;
 	struct err_info_constraint err_info_rcv_constraint;
 	struct err_info_constraint err_info_xmit_constraint;
@@ -1133,8 +1111,8 @@ struct hfi1_devdata {
 	u64 lcb_err_en;
 
 	/*
-	 * Handlers for outgoing data so that snoop/capture does not
-	 * have to have its hooks in the send path
+	 * Capability to have different send engines simply by changing a
+	 * pointer value.
 	 */
 	send_routine process_pio_send ____cacheline_aligned_in_smp;
 	send_routine process_dma_send;
@@ -1238,8 +1216,6 @@ struct hfi1_devdata *hfi1_lookup(int unit);
 extern u32 hfi1_cpulist_count;
 extern unsigned long *hfi1_cpulist;
 
-extern unsigned int snoop_drop_send;
-extern unsigned int snoop_force_capture;
 int hfi1_init(struct hfi1_devdata *, int);
 int hfi1_count_units(int *npresentp, int *nupp);
 int hfi1_count_active_units(void);
@@ -1574,13 +1550,6 @@ void set_up_vl15(struct hfi1_devdata *dd, u8 vau, u16 vl15buf);
 void reset_link_credits(struct hfi1_devdata *dd);
 void assign_remote_cm_au_table(struct hfi1_devdata *dd, u8 vcu);
 
-int snoop_recv_handler(struct hfi1_packet *packet);
-int snoop_send_dma_handler(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
-			   u64 pbc);
-int snoop_send_pio_handler(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
-			   u64 pbc);
-void snoop_inline_pio_send(struct hfi1_devdata *dd, struct pio_buf *pbuf,
-			   u64 pbc, const void *from, size_t count);
 int set_buffer_control(struct hfi1_pportdata *ppd, struct buffer_control *bc);
 
 static inline struct hfi1_devdata *dd_from_ppd(struct hfi1_pportdata *ppd)
@@ -1827,8 +1796,6 @@ int kdeth_process_expected(struct hfi1_packet *packet);
 int kdeth_process_eager(struct hfi1_packet *packet);
 int process_receive_invalid(struct hfi1_packet *packet);
 
-extern rhf_rcv_function_ptr snoop_rhf_rcv_functions[8];
-
 void update_sge(struct rvt_sge_state *ss, u32 length);
 
 /* global module parameter variables */
@@ -1855,9 +1822,6 @@ extern struct mutex hfi1_mutex;
 #define DRIVER_NAME		"hfi1"
 #define HFI1_USER_MINOR_BASE     0
 #define HFI1_TRACE_MINOR         127
-#define HFI1_DIAGPKT_MINOR       128
-#define HFI1_DIAG_MINOR_BASE     129
-#define HFI1_SNOOP_CAPTURE_BASE  200
 #define HFI1_NMINORS             255
 
 #define PCI_VENDOR_ID_INTEL 0x8086
diff --git a/drivers/infiniband/hw/hfi1/trace_rx.h b/drivers/infiniband/hw/hfi1/trace_rx.h
index 11e02b2..f77e59f 100644
--- a/drivers/infiniband/hw/hfi1/trace_rx.h
+++ b/drivers/infiniband/hw/hfi1/trace_rx.h
@@ -253,66 +253,6 @@ TRACE_EVENT(hfi1_mmu_invalidate,
 		      )
 	    );
 
-#define SNOOP_PRN \
-	"slid %.4x dlid %.4x qpn 0x%.6x opcode 0x%.2x,%s " \
-	"svc lvl %d pkey 0x%.4x [header = %d bytes] [data = %d bytes]"
-
-TRACE_EVENT(snoop_capture,
-	    TP_PROTO(struct hfi1_devdata *dd,
-		     int hdr_len,
-		     struct ib_header *hdr,
-		     int data_len,
-		     void *data),
-	    TP_ARGS(dd, hdr_len, hdr, data_len, data),
-	    TP_STRUCT__entry(
-			     DD_DEV_ENTRY(dd)
-			     __field(u16, slid)
-			     __field(u16, dlid)
-			     __field(u32, qpn)
-			     __field(u8, opcode)
-			     __field(u8, sl)
-			     __field(u16, pkey)
-			     __field(u32, hdr_len)
-			     __field(u32, data_len)
-			     __field(u8, lnh)
-			     __dynamic_array(u8, raw_hdr, hdr_len)
-			     __dynamic_array(u8, raw_pkt, data_len)
-			     ),
-	    TP_fast_assign(
-		struct ib_other_headers *ohdr;
-
-		__entry->lnh = (u8)(be16_to_cpu(hdr->lrh[0]) & 3);
-		if (__entry->lnh == HFI1_LRH_BTH)
-		ohdr = &hdr->u.oth;
-		else
-		ohdr = &hdr->u.l.oth;
-		DD_DEV_ASSIGN(dd);
-		__entry->slid = be16_to_cpu(hdr->lrh[3]);
-		__entry->dlid = be16_to_cpu(hdr->lrh[1]);
-		__entry->qpn = be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK;
-		__entry->opcode = (be32_to_cpu(ohdr->bth[0]) >> 24) & 0xff;
-		__entry->sl = (u8)(be16_to_cpu(hdr->lrh[0]) >> 4) & 0xf;
-		__entry->pkey =	be32_to_cpu(ohdr->bth[0]) & 0xffff;
-		__entry->hdr_len = hdr_len;
-		__entry->data_len = data_len;
-		memcpy(__get_dynamic_array(raw_hdr), hdr, hdr_len);
-		memcpy(__get_dynamic_array(raw_pkt), data, data_len);
-		),
-	    TP_printk(
-		"[%s] " SNOOP_PRN,
-		__get_str(dev),
-		__entry->slid,
-		__entry->dlid,
-		__entry->qpn,
-		__entry->opcode,
-		show_ib_opcode(__entry->opcode),
-		__entry->sl,
-		__entry->pkey,
-		__entry->hdr_len,
-		__entry->data_len
-		)
-);
-
 #endif /* __HFI1_TRACE_RX_H */
 
 #undef TRACE_INCLUDE_PATH

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 10/12] IB/hfi1: Clean up unused argument

[Dennis Dalessandro]

From: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

hfi1_pcie_ddinit takes the PCI device id as an argument but never
uses it. Clean it up.

Reviewed-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/hfi1/chip.c |    2 +-
 drivers/infiniband/hw/hfi1/hfi.h  |    3 +--
 drivers/infiniband/hw/hfi1/pcie.c |    3 +--
 3 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index bf645e9..3371361 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -14449,7 +14449,7 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 	 * Any error printing is already done by the init code.
 	 * On return, we have the chip mapped.
 	 */
-	ret = hfi1_pcie_ddinit(dd, pdev, ent);
+	ret = hfi1_pcie_ddinit(dd, pdev);
 	if (ret < 0)
 		goto bail_free;
 
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 1453c5c..6f05f68 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1760,8 +1760,7 @@ int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len);
 
 int hfi1_pcie_init(struct pci_dev *, const struct pci_device_id *);
 void hfi1_pcie_cleanup(struct pci_dev *);
-int hfi1_pcie_ddinit(struct hfi1_devdata *, struct pci_dev *,
-		     const struct pci_device_id *);
+int hfi1_pcie_ddinit(struct hfi1_devdata *, struct pci_dev *);
 void hfi1_pcie_ddcleanup(struct hfi1_devdata *);
 void hfi1_pcie_flr(struct hfi1_devdata *);
 int pcie_speeds(struct hfi1_devdata *);
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 89c68da..4ac8f33 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -157,8 +157,7 @@ void hfi1_pcie_cleanup(struct pci_dev *pdev)
  * fields required to re-initialize after a chip reset, or for
  * various other purposes
  */
-int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev,
-		     const struct pci_device_id *ent)
+int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev)
 {
 	unsigned long len;
 	resource_size_t addr;

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 11/12] IB/hfi1: Delete unused lock

[Dennis Dalessandro]

From: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

The lock is an unused vestige from qib. Remove it.

Reviewed-by: Mike Marciniszyn <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/hfi1/hfi.h  |    2 --
 drivers/infiniband/hw/hfi1/init.c |    1 -
 2 files changed, 0 insertions(+), 3 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 6f05f68..1707334 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -605,8 +605,6 @@ struct hfi1_pportdata {
 	struct mutex hls_lock;
 	u32 host_link_state;
 
-	spinlock_t            sdma_alllock ____cacheline_aligned_in_smp;
-
 	u32 lstate;	/* logical link state */
 
 	/* these are the "32 bit" regs */
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 4a7e741..c317e69 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -507,7 +507,6 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd,
 	INIT_WORK(&ppd->qsfp_info.qsfp_work, qsfp_event);
 
 	mutex_init(&ppd->hls_lock);
-	spin_lock_init(&ppd->sdma_alllock);
 	spin_lock_init(&ppd->qsfp_info.qsfp_lock);
 
 	ppd->qsfp_info.ppd = ppd;

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 12/12] IB/hfi1: Fix rnr_timer addition

[Dennis Dalessandro]

From: Ira Weiny <ira.weiny@intel.com>

The new s_rnr_timeout was not properly being set and the code was
incorrectly setting a different timer.

Found by code inspection.

Cc: <stable@vger.kernel.org> # 4.7.x
Fixes: 08279d5c9424 ("staging/rdma/hfi1: use new RNR timer")
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
---
 drivers/infiniband/hw/hfi1/rc.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 8bc5013..83198a8 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -89,7 +89,7 @@ void hfi1_add_rnr_timer(struct rvt_qp *qp, u32 to)
 
 	lockdep_assert_held(&qp->s_lock);
 	qp->s_flags |= RVT_S_WAIT_RNR;
-	qp->s_timer.expires = jiffies + usecs_to_jiffies(to);
+	priv->s_rnr_timer.expires = jiffies + usecs_to_jiffies(to);
 	add_timer(&priv->s_rnr_timer);
 }