Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1208925 > unrolled thread

Re: [PATCH 2/3] QIB: Removing usage of pcie_set_mps()

Started byBjorn Helgaas <bhelgaas@google.com>
First post2015-08-18 00:40 +0200
Last post2015-08-18 03:50 +0200
Articles 4 — 3 participants

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.


Contents

  Re: [PATCH 2/3] QIB: Removing usage of pcie_set_mps() Bjorn Helgaas <bhelgaas@google.com> - 2015-08-18 00:40 +0200
    Re: [PATCH 2/3] QIB: Removing usage of pcie_set_mps() "Jiang, Dave" <dave.jiang@intel.com> - 2015-08-18 01:00 +0200
      Re: [PATCH 2/3] QIB: Removing usage of pcie_set_mps() Bjorn Helgaas <bhelgaas@google.com> - 2015-08-18 02:10 +0200
        Re: [PATCH 2/3] QIB: Removing usage of pcie_set_mps() Jason Gunthorpe <jgunthorpe@obsidianresearch.com> - 2015-08-18 03:50 +0200

#1208925 — Re: [PATCH 2/3] QIB: Removing usage of pcie_set_mps()

FromBjorn Helgaas <bhelgaas@google.com>
Date2015-08-18 00:40 +0200
SubjectRe: [PATCH 2/3] QIB: Removing usage of pcie_set_mps()
Message-ID<pYBeq-407-5@gated-at.bofh.it>
[+cc Mike, linux-rdma]

On Wed, Jul 29, 2015 at 04:18:54PM -0600, Keith Busch wrote:
> From: Dave Jiang <dave.jiang@intel.com>
> 
> This is in perperation of un-exporting the pcie_set_mps() function
> symbol. A driver should not be changing the MPS as that is the
> responsibility of the PCI subsystem.

Please explain the implications of removing this code.  Does this affect
performance of the device?  If so, how do we get that performance back?

I also cc'd the QIB maintainers for you:

  QIB DRIVER
  M:      Mike Marciniszyn <infinipath@intel.com>
  L:      linux-rdma@vger.kernel.org
  F:      drivers/infiniband/hw/qib/

> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
> ---
>  drivers/infiniband/hw/qib/qib_pcie.c |   27 +--------------------------
>  1 file changed, 1 insertion(+), 26 deletions(-)
> 
> diff --git a/drivers/infiniband/hw/qib/qib_pcie.c b/drivers/infiniband/hw/qib/qib_pcie.c
> index 4758a38..b8a2dcd 100644
> --- a/drivers/infiniband/hw/qib/qib_pcie.c
> +++ b/drivers/infiniband/hw/qib/qib_pcie.c
> @@ -557,12 +557,11 @@ static void qib_tune_pcie_coalesce(struct qib_devdata *dd)
>   */
>  static int qib_pcie_caps;
>  module_param_named(pcie_caps, qib_pcie_caps, int, S_IRUGO);
> -MODULE_PARM_DESC(pcie_caps, "Max PCIe tuning: Payload (0..3), ReadReq (4..7)");
> +MODULE_PARM_DESC(pcie_caps, "Max PCIe tuning: ReadReq (4..7)");
>  
>  static void qib_tune_pcie_caps(struct qib_devdata *dd)
>  {
>  	struct pci_dev *parent;
> -	u16 rc_mpss, rc_mps, ep_mpss, ep_mps;
>  	u16 rc_mrrs, ep_mrrs, max_mrrs;
>  
>  	/* Find out supported and configured values for parent (root) */
> @@ -575,30 +574,6 @@ static void qib_tune_pcie_caps(struct qib_devdata *dd)
>  	if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev))
>  		return;
>  
> -	rc_mpss = parent->pcie_mpss;
> -	rc_mps = ffs(pcie_get_mps(parent)) - 8;
> -	/* Find out supported and configured values for endpoint (us) */
> -	ep_mpss = dd->pcidev->pcie_mpss;
> -	ep_mps = ffs(pcie_get_mps(dd->pcidev)) - 8;
> -
> -	/* Find max payload supported by root, endpoint */
> -	if (rc_mpss > ep_mpss)
> -		rc_mpss = ep_mpss;
> -
> -	/* If Supported greater than limit in module param, limit it */
> -	if (rc_mpss > (qib_pcie_caps & 7))
> -		rc_mpss = qib_pcie_caps & 7;
> -	/* If less than (allowed, supported), bump root payload */
> -	if (rc_mpss > rc_mps) {
> -		rc_mps = rc_mpss;
> -		pcie_set_mps(parent, 128 << rc_mps);
> -	}
> -	/* If less than (allowed, supported), bump endpoint payload */
> -	if (rc_mpss > ep_mps) {
> -		ep_mps = rc_mpss;
> -		pcie_set_mps(dd->pcidev, 128 << ep_mps);
> -	}
> -
>  	/*
>  	 * Now the Read Request size.
>  	 * No field for max supported, but PCIe spec limits it to 4096,
> -- 
> 1.7.10.4
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]


#1208935

From"Jiang, Dave" <dave.jiang@intel.com>
Date2015-08-18 01:00 +0200
Message-ID<pYBxL-4mJ-9@gated-at.bofh.it>
In reply to#1208925
T24gTW9uLCAyMDE1LTA4LTE3IGF0IDE3OjMwIC0wNTAwLCBCam9ybiBIZWxnYWFzIHdyb3RlOg0K
PiBbK2NjIE1pa2UsIGxpbnV4LXJkbWFdDQo+IA0KPiBPbiBXZWQsIEp1bCAyOSwgMjAxNSBhdCAw
NDoxODo1NFBNIC0wNjAwLCBLZWl0aCBCdXNjaCB3cm90ZToNCj4gPiBGcm9tOiBEYXZlIEppYW5n
IDxkYXZlLmppYW5nQGludGVsLmNvbT4NCj4gPiANCj4gPiBUaGlzIGlzIGluIHBlcnBlcmF0aW9u
IG9mIHVuLWV4cG9ydGluZyB0aGUgcGNpZV9zZXRfbXBzKCkgZnVuY3Rpb24NCj4gPiBzeW1ib2wu
IEEgZHJpdmVyIHNob3VsZCBub3QgYmUgY2hhbmdpbmcgdGhlIE1QUyBhcyB0aGF0IGlzIHRoZQ0K
PiA+IHJlc3BvbnNpYmlsaXR5IG9mIHRoZSBQQ0kgc3Vic3lzdGVtLg0KPiANCj4gUGxlYXNlIGV4
cGxhaW4gdGhlIGltcGxpY2F0aW9ucyBvZiByZW1vdmluZyB0aGlzIGNvZGUuICBEb2VzIHRoaXMg
DQo+IGFmZmVjdA0KPiBwZXJmb3JtYW5jZSBvZiB0aGUgZGV2aWNlPyAgSWYgc28sIGhvdyBkbyB3
ZSBnZXQgdGhhdCBwZXJmb3JtYW5jZSANCj4gYmFjaz8NCg0KSG9uZXN0bHkgSSBkb24ndCBrbm93
LiBCdXQgYXQgdGhlIHNhbWUgdGltZSBJIHRoaW5rIHRoZSBkcml2ZXINCnNob3VsZG4ndCBiZSB0
b3VjaGluZyB0aGUgTVBTIGF0IGFsbC4gU2hvdWxkbid0IHRoYXQgYmUgbGVmdCB0byB0aGUNClBD
SWUgc3Vic3lzdGVtIGFuZCByZWx5IG9uIHRoZSBQQ0llIHN1YnN5c3RlbSB0byBzZXQgdGhpcyB0
byBhIHNhbmUNCnZhbHVlPyANCg0KPiANCj4gSSBhbHNvIGNjJ2QgdGhlIFFJQiBtYWludGFpbmVy
cyBmb3IgeW91Og0KPiANCj4gICBRSUIgRFJJVkVSDQo+ICAgTTogICAgICBNaWtlIE1hcmNpbmlz
enluIDxpbmZpbmlwYXRoQGludGVsLmNvbT4NCj4gICBMOiAgICAgIGxpbnV4LXJkbWFAdmdlci5r
ZXJuZWwub3JnDQo+ICAgRjogICAgICBkcml2ZXJzL2luZmluaWJhbmQvaHcvcWliLw0KPiANCj4g
PiBTaWduZWQtb2ZmLWJ5OiBEYXZlIEppYW5nIDxkYXZlLmppYW5nQGludGVsLmNvbT4NCj4gPiAt
LS0NCj4gPiAgZHJpdmVycy9pbmZpbmliYW5kL2h3L3FpYi9xaWJfcGNpZS5jIHwgICAyNyArLS0t
LS0tLS0tLS0tLS0tLS0tLS0tDQo+ID4gLS0tLS0NCj4gPiAgMSBmaWxlIGNoYW5nZWQsIDEgaW5z
ZXJ0aW9uKCspLCAyNiBkZWxldGlvbnMoLSkNCj4gPiANCj4gPiBkaWZmIC0tZ2l0IGEvZHJpdmVy
cy9pbmZpbmliYW5kL2h3L3FpYi9xaWJfcGNpZS5jIA0KPiA+IGIvZHJpdmVycy9pbmZpbmliYW5k
L2h3L3FpYi9xaWJfcGNpZS5jDQo+ID4gaW5kZXggNDc1OGEzOC4uYjhhMmRjZCAxMDA2NDQNCj4g
PiAtLS0gYS9kcml2ZXJzL2luZmluaWJhbmQvaHcvcWliL3FpYl9wY2llLmMNCj4gPiArKysgYi9k
cml2ZXJzL2luZmluaWJhbmQvaHcvcWliL3FpYl9wY2llLmMNCj4gPiBAQCAtNTU3LDEyICs1NTcs
MTEgQEAgc3RhdGljIHZvaWQgcWliX3R1bmVfcGNpZV9jb2FsZXNjZShzdHJ1Y3QgDQo+ID4gcWli
X2RldmRhdGEgKmRkKQ0KPiA+ICAgKi8NCj4gPiAgc3RhdGljIGludCBxaWJfcGNpZV9jYXBzOw0K
PiA+ICBtb2R1bGVfcGFyYW1fbmFtZWQocGNpZV9jYXBzLCBxaWJfcGNpZV9jYXBzLCBpbnQsIFNf
SVJVR08pOw0KPiA+IC1NT0RVTEVfUEFSTV9ERVNDKHBjaWVfY2FwcywgIk1heCBQQ0llIHR1bmlu
ZzogUGF5bG9hZCAoMC4uMyksIA0KPiA+IFJlYWRSZXEgKDQuLjcpIik7DQo+ID4gK01PRFVMRV9Q
QVJNX0RFU0MocGNpZV9jYXBzLCAiTWF4IFBDSWUgdHVuaW5nOiBSZWFkUmVxICg0Li43KSIpOw0K
PiA+ICANCj4gPiAgc3RhdGljIHZvaWQgcWliX3R1bmVfcGNpZV9jYXBzKHN0cnVjdCBxaWJfZGV2
ZGF0YSAqZGQpDQo+ID4gIHsNCj4gPiAgCXN0cnVjdCBwY2lfZGV2ICpwYXJlbnQ7DQo+ID4gLQl1
MTYgcmNfbXBzcywgcmNfbXBzLCBlcF9tcHNzLCBlcF9tcHM7DQo+ID4gIAl1MTYgcmNfbXJycywg
ZXBfbXJycywgbWF4X21ycnM7DQo+ID4gIA0KPiA+ICAJLyogRmluZCBvdXQgc3VwcG9ydGVkIGFu
ZCBjb25maWd1cmVkIHZhbHVlcyBmb3IgcGFyZW50IA0KPiA+IChyb290KSAqLw0KPiA+IEBAIC01
NzUsMzAgKzU3NCw2IEBAIHN0YXRpYyB2b2lkIHFpYl90dW5lX3BjaWVfY2FwcyhzdHJ1Y3QgDQo+
ID4gcWliX2RldmRhdGEgKmRkKQ0KPiA+ICAJaWYgKCFwY2lfaXNfcGNpZShwYXJlbnQpIHx8ICFw
Y2lfaXNfcGNpZShkZC0+cGNpZGV2KSkNCj4gPiAgCQlyZXR1cm47DQo+ID4gIA0KPiA+IC0JcmNf
bXBzcyA9IHBhcmVudC0+cGNpZV9tcHNzOw0KPiA+IC0JcmNfbXBzID0gZmZzKHBjaWVfZ2V0X21w
cyhwYXJlbnQpKSAtIDg7DQo+ID4gLQkvKiBGaW5kIG91dCBzdXBwb3J0ZWQgYW5kIGNvbmZpZ3Vy
ZWQgdmFsdWVzIGZvciBlbmRwb2ludCANCj4gPiAodXMpICovDQo+ID4gLQllcF9tcHNzID0gZGQt
PnBjaWRldi0+cGNpZV9tcHNzOw0KPiA+IC0JZXBfbXBzID0gZmZzKHBjaWVfZ2V0X21wcyhkZC0+
cGNpZGV2KSkgLSA4Ow0KPiA+IC0NCj4gPiAtCS8qIEZpbmQgbWF4IHBheWxvYWQgc3VwcG9ydGVk
IGJ5IHJvb3QsIGVuZHBvaW50ICovDQo+ID4gLQlpZiAocmNfbXBzcyA+IGVwX21wc3MpDQo+ID4g
LQkJcmNfbXBzcyA9IGVwX21wc3M7DQo+ID4gLQ0KPiA+IC0JLyogSWYgU3VwcG9ydGVkIGdyZWF0
ZXIgdGhhbiBsaW1pdCBpbiBtb2R1bGUgcGFyYW0sIGxpbWl0IA0KPiA+IGl0ICovDQo+ID4gLQlp
ZiAocmNfbXBzcyA+IChxaWJfcGNpZV9jYXBzICYgNykpDQo+ID4gLQkJcmNfbXBzcyA9IHFpYl9w
Y2llX2NhcHMgJiA3Ow0KPiA+IC0JLyogSWYgbGVzcyB0aGFuIChhbGxvd2VkLCBzdXBwb3J0ZWQp
LCBidW1wIHJvb3QgcGF5bG9hZCAqLw0KPiA+IC0JaWYgKHJjX21wc3MgPiByY19tcHMpIHsNCj4g
PiAtCQlyY19tcHMgPSByY19tcHNzOw0KPiA+IC0JCXBjaWVfc2V0X21wcyhwYXJlbnQsIDEyOCA8
PCByY19tcHMpOw0KPiA+IC0JfQ0KPiA+IC0JLyogSWYgbGVzcyB0aGFuIChhbGxvd2VkLCBzdXBw
b3J0ZWQpLCBidW1wIGVuZHBvaW50IA0KPiA+IHBheWxvYWQgKi8NCj4gPiAtCWlmIChyY19tcHNz
ID4gZXBfbXBzKSB7DQo+ID4gLQkJZXBfbXBzID0gcmNfbXBzczsNCj4gPiAtCQlwY2llX3NldF9t
cHMoZGQtPnBjaWRldiwgMTI4IDw8IGVwX21wcyk7DQo+ID4gLQl9DQo+ID4gLQ0KPiA+ICAJLyoN
Cj4gPiAgCSAqIE5vdyB0aGUgUmVhZCBSZXF1ZXN0IHNpemUuDQo+ID4gIAkgKiBObyBmaWVsZCBm
b3IgbWF4IHN1cHBvcnRlZCwgYnV0IFBDSWUgc3BlYyBsaW1pdHMgaXQgdG8gDQo+ID4gNDA5Niw=
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]


#1208974

FromBjorn Helgaas <bhelgaas@google.com>
Date2015-08-18 02:10 +0200
Message-ID<pYCDv-6cc-13@gated-at.bofh.it>
In reply to#1208935
On Mon, Aug 17, 2015 at 5:50 PM, Jiang, Dave <dave.jiang@intel.com> wrote:
> On Mon, 2015-08-17 at 17:30 -0500, Bjorn Helgaas wrote:
>> [+cc Mike, linux-rdma]
>>
>> On Wed, Jul 29, 2015 at 04:18:54PM -0600, Keith Busch wrote:
>> > From: Dave Jiang <dave.jiang@intel.com>
>> >
>> > This is in perperation of un-exporting the pcie_set_mps() function
>> > symbol. A driver should not be changing the MPS as that is the
>> > responsibility of the PCI subsystem.
>>
>> Please explain the implications of removing this code.  Does this
>> affect
>> performance of the device?  If so, how do we get that performance
>> back?
>
> Honestly I don't know. But at the same time I think the driver
> shouldn't be touching the MPS at all. Shouldn't that be left to the
> PCIe subsystem and rely on the PCIe subsystem to set this to a sane
> value?

Yes, I think in principle the PCI core should own this, but I also
don't want to introduce a performance regression, so I think we need
to understand whether there's a problem, and if there is, fix it.

>> I also cc'd the QIB maintainers for you:
>>
>>   QIB DRIVER
>>   M:      Mike Marciniszyn <infinipath@intel.com>
>>   L:      linux-rdma@vger.kernel.org
>>   F:      drivers/infiniband/hw/qib/
>>
>> > Signed-off-by: Dave Jiang <dave.jiang@intel.com>
>> > ---
>> >  drivers/infiniband/hw/qib/qib_pcie.c |   27 +---------------------
>> > -----
>> >  1 file changed, 1 insertion(+), 26 deletions(-)
>> >
>> > diff --git a/drivers/infiniband/hw/qib/qib_pcie.c
>> > b/drivers/infiniband/hw/qib/qib_pcie.c
>> > index 4758a38..b8a2dcd 100644
>> > --- a/drivers/infiniband/hw/qib/qib_pcie.c
>> > +++ b/drivers/infiniband/hw/qib/qib_pcie.c
>> > @@ -557,12 +557,11 @@ static void qib_tune_pcie_coalesce(struct
>> > qib_devdata *dd)
>> >   */
>> >  static int qib_pcie_caps;
>> >  module_param_named(pcie_caps, qib_pcie_caps, int, S_IRUGO);
>> > -MODULE_PARM_DESC(pcie_caps, "Max PCIe tuning: Payload (0..3),
>> > ReadReq (4..7)");
>> > +MODULE_PARM_DESC(pcie_caps, "Max PCIe tuning: ReadReq (4..7)");
>> >
>> >  static void qib_tune_pcie_caps(struct qib_devdata *dd)
>> >  {
>> >     struct pci_dev *parent;
>> > -   u16 rc_mpss, rc_mps, ep_mpss, ep_mps;
>> >     u16 rc_mrrs, ep_mrrs, max_mrrs;
>> >
>> >     /* Find out supported and configured values for parent
>> > (root) */
>> > @@ -575,30 +574,6 @@ static void qib_tune_pcie_caps(struct
>> > qib_devdata *dd)
>> >     if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev))
>> >             return;
>> >
>> > -   rc_mpss = parent->pcie_mpss;
>> > -   rc_mps = ffs(pcie_get_mps(parent)) - 8;
>> > -   /* Find out supported and configured values for endpoint
>> > (us) */
>> > -   ep_mpss = dd->pcidev->pcie_mpss;
>> > -   ep_mps = ffs(pcie_get_mps(dd->pcidev)) - 8;
>> > -
>> > -   /* Find max payload supported by root, endpoint */
>> > -   if (rc_mpss > ep_mpss)
>> > -           rc_mpss = ep_mpss;
>> > -
>> > -   /* If Supported greater than limit in module param, limit
>> > it */
>> > -   if (rc_mpss > (qib_pcie_caps & 7))
>> > -           rc_mpss = qib_pcie_caps & 7;
>> > -   /* If less than (allowed, supported), bump root payload */
>> > -   if (rc_mpss > rc_mps) {
>> > -           rc_mps = rc_mpss;
>> > -           pcie_set_mps(parent, 128 << rc_mps);
>> > -   }
>> > -   /* If less than (allowed, supported), bump endpoint
>> > payload */
>> > -   if (rc_mpss > ep_mps) {
>> > -           ep_mps = rc_mpss;
>> > -           pcie_set_mps(dd->pcidev, 128 << ep_mps);
>> > -   }
>> > -
>> >     /*
>> >      * Now the Read Request size.
>> >      * No field for max supported, but PCIe spec limits it to
>> > 4096,
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]


#1208998

FromJason Gunthorpe <jgunthorpe@obsidianresearch.com>
Date2015-08-18 03:50 +0200
Message-ID<pYEch-8op-7@gated-at.bofh.it>
In reply to#1208974
On Mon, Aug 17, 2015 at 07:06:10PM -0500, Bjorn Helgaas wrote:
> On Mon, Aug 17, 2015 at 5:50 PM, Jiang, Dave <dave.jiang@intel.com> wrote:
> > On Mon, 2015-08-17 at 17:30 -0500, Bjorn Helgaas wrote:
> >> [+cc Mike, linux-rdma]
> >>
> >> On Wed, Jul 29, 2015 at 04:18:54PM -0600, Keith Busch wrote:
> >> > From: Dave Jiang <dave.jiang@intel.com>
> >> >
> >> > This is in perperation of un-exporting the pcie_set_mps() function
> >> > symbol. A driver should not be changing the MPS as that is the
> >> > responsibility of the PCI subsystem.
> >>
> >> Please explain the implications of removing this code.  Does this
> >> affect
> >> performance of the device?  If so, how do we get that performance
> >> back?
> >
> > Honestly I don't know. But at the same time I think the driver
> > shouldn't be touching the MPS at all. Shouldn't that be left to the
> > PCIe subsystem and rely on the PCIe subsystem to set this to a sane
> > value?
> 
> Yes, I think in principle the PCI core should own this, but I also
> don't want to introduce a performance regression, so I think we need
> to understand whether there's a problem, and if there is, fix it.

Making sure Mike is CC'd directly..

Mike: I see this has been cut and pasted to HFI1 too, I would be
disappointed if HFI needs it as well. :(

FWIW, I totally agree with the above. MPS/MRS and related have to do
with root port capability, switches in the path and any platform
bugs..

I'm not sure why a driver would ever want to mess with this, and since
this code doesn't walk the bus toward the root port, it is technically
wrong, right? I also find it strange that qib_pcie_caps defaults to
zero which means the 'tuning' reduces the payload size to the minimums
(??)

> >> >     /*
> >> >      * Now the Read Request size.
> >> >      * No field for max supported, but PCIe spec limits it to
> >> > 4096,

.. it has been a bit since I looked at this, but IIRC, MRRS is also
something that should not be touched by a driver?

Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web