public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: "Bryan O'Sullivan" <bos@pathscale.com>
To: rdreier@cisco.com
Cc: openib-general@openib.org, linux-kernel@vger.kernel.org
Subject: [PATCH 4 of 53] ipath - cap number of PDs that can be allocated
Date: Fri, 12 May 2006 16:42:49 -0700	[thread overview]
Message-ID: <300f0aa6f034eec6a806.1147477369@eng-12.pathscale.com> (raw)
In-Reply-To: <patchbomb.1147477365@eng-12.pathscale.com>

Put an arbitrary cap on the maximum number of PDs that can be allocated
for a device.  This is arbitrary because the number we support
is constrained only by system memory and what kmalloc can give us.
Nevertheless, if we don't have a limit, some third-party  OpenIB stress
tests fail.  The limit can be changed on the fly using a module parameter.

Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>

diff -r 5d5e1e641b16 -r 300f0aa6f034 drivers/infiniband/hw/ipath/ipath_verbs.c
--- a/drivers/infiniband/hw/ipath/ipath_verbs.c	Fri May 12 15:55:27 2006 -0700
+++ b/drivers/infiniband/hw/ipath/ipath_verbs.c	Fri May 12 15:55:27 2006 -0700
@@ -54,6 +54,11 @@ unsigned int ib_ipath_debug;	/* debug ma
 unsigned int ib_ipath_debug;	/* debug mask */
 module_param_named(debug, ib_ipath_debug, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(debug, "Verbs debug mask");
+
+static unsigned int ib_ipath_max_pds = 0xFFFF;
+module_param_named(max_pds, ib_ipath_max_pds, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(max_pds,
+		 "Maximum number of protection domains to support");
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("PathScale <support@pathscale.com>");
@@ -589,7 +594,7 @@ static int ipath_query_device(struct ib_
 	props->max_cq = 0xffff;
 	props->max_cqe = 0xffff;
 	props->max_mr = dev->lk_table.max;
-	props->max_pd = 0xffff;
+	props->max_pd = ib_ipath_max_pds;
 	props->max_qp_rd_atom = 1;
 	props->max_qp_init_rd_atom = 1;
 	/* props->max_res_rd_atom */
@@ -743,8 +748,23 @@ static struct ib_pd *ipath_alloc_pd(stru
 				    struct ib_ucontext *context,
 				    struct ib_udata *udata)
 {
+	struct ipath_ibdev *dev = to_idev(ibdev);
 	struct ipath_pd *pd;
 	struct ib_pd *ret;
+
+	/*
+	 * This is actually totally arbitrary.	Some correctness tests
+	 * assume there's a maximum number of PDs that can be allocated.
+	 * We don't actually have this limit, but we fail the test if
+	 * we allow allocations of more than we report for this value.
+	 */
+
+	if (dev->n_pds_allocated == ib_ipath_max_pds) {
+		ret = ERR_PTR(-ENOMEM);
+		goto bail;
+	}
+
+	dev->n_pds_allocated++;
 
 	pd = kmalloc(sizeof *pd, GFP_KERNEL);
 	if (!pd) {
@@ -764,6 +784,9 @@ static int ipath_dealloc_pd(struct ib_pd
 static int ipath_dealloc_pd(struct ib_pd *ibpd)
 {
 	struct ipath_pd *pd = to_ipd(ibpd);
+	struct ipath_ibdev *dev = to_idev(ibpd->device);
+
+	dev->n_pds_allocated--;
 
 	kfree(pd);
 
diff -r 5d5e1e641b16 -r 300f0aa6f034 drivers/infiniband/hw/ipath/ipath_verbs.h
--- a/drivers/infiniband/hw/ipath/ipath_verbs.h	Fri May 12 15:55:27 2006 -0700
+++ b/drivers/infiniband/hw/ipath/ipath_verbs.h	Fri May 12 15:55:27 2006 -0700
@@ -431,6 +431,7 @@ struct ipath_ibdev {
 	__be64 sys_image_guid;	/* in network order */
 	__be64 gid_prefix;	/* in network order */
 	__be64 mkey;
+	u32 n_pds_allocated;	/* number of PDs allocated for device */
 	u64 ipath_sword;	/* total dwords sent (sample result) */
 	u64 ipath_rword;	/* total dwords received (sample result) */
 	u64 ipath_spkts;	/* total packets sent (sample result) */

  parent reply	other threads:[~2006-05-12 23:44 UTC|newest]

Thread overview: 87+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-05-12 23:42 [PATCH 0 of 53] ipath driver updates for 2.6.17-rc4 Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 1 of 53] ipath - fix spinlock recursion bug Bryan O'Sullivan
2006-05-13  1:01   ` Joshua Hudson
2006-05-12 23:42 ` [PATCH 2 of 53] ipath - purge sps_lid and sps_mlid arrays, and /sys entries Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 3 of 53] ipath - report max MR and QP sizes based on table sizes Bryan O'Sullivan
2006-05-12 23:42 ` Bryan O'Sullivan [this message]
2006-05-15 15:45   ` [PATCH 4 of 53] ipath - cap number of PDs that can be allocated Roland Dreier
2006-05-15 21:06     ` Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 5 of 53] ipath - forbid creation of AHs with illegal ports Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 6 of 53] ipath - forbid creation of AH with DLID of 0 Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 7 of 53] ipath - cap maximum number of AHs Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 8 of 53] ipath - cap number of CQEs Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 9 of 53] ipath - cap number of CQs Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 10 of 53] ipath - require capabilities when creating a QP Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 11 of 53] ipath - don't modify QP if changes fail Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 12 of 53] ipath - reduce overhead of receive interrupts Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 13 of 53] ipath - limit number of SGEs and WRs per QP Bryan O'Sullivan
2006-05-12 23:42 ` [PATCH 14 of 53] ipath - forbid empty MRs Bryan O'Sullivan
2006-05-15 15:46   ` Roland Dreier
2006-05-15 21:17     ` Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 15 of 53] ipath - make some maximum values more sane Bryan O'Sullivan
2006-05-15 15:48   ` Roland Dreier
2006-05-16 22:44   ` [openib-general] " Arlin Davis
2006-05-12 23:43 ` [PATCH 16 of 53] ipath - fix reporting of driver version to userspace Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 17 of 53] ipath - fail properly if GID missing Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 18 of 53] ipath - make max mcast sizes configurable Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 19 of 53] ipath - replace uses of LIST_POISON Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 20 of 53] ipath - more sharing between RC and UC code Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 21 of 53] ipath - use phys_to_virt instead of bus_to_virt Bryan O'Sullivan
2006-05-15 15:50   ` Roland Dreier
2006-05-15 21:21     ` Bryan O'Sullivan
2006-05-15 21:28       ` Roland Dreier
2006-05-15 23:13         ` [openib-general] " Grant Grundler
2006-05-15 23:16           ` Roland Dreier
2006-05-15 23:30             ` Grant Grundler
2006-05-15 23:34               ` Roland Dreier
2006-05-16 20:05       ` Christoph Hellwig
2006-05-12 23:43 ` [PATCH 22 of 53] ipath - fix "many lost ticks" warning Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 23 of 53] ipath - [TRIVIAL] typo fixes Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 24 of 53] ipath - count dropped VL15 packets Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 25 of 53] ipath - remove some duplicated lines of code Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 26 of 53] ipath - treat PE800 rev1 and rev2 as similar Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 27 of 53] ipath - fix accounting of data packets with bad VLs Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 28 of 53] ipath - forbid setting of invalid MLID Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 29 of 53] ipath - remove redundant register read Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 30 of 53] ipath - count VL15 packet drops due to bad VL or lack of buffers Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 31 of 53] ipath - forbid sending of bad packet sizes Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 32 of 53] ipath - fix NULL dereference during cleanup Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 33 of 53] ipath - clean up some comments Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 34 of 53] ipath - fix occasional hangs in SDP Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 35 of 53] ipath - some interrelated stability and cleanliness fixes Bryan O'Sullivan
2006-05-15 15:53   ` Roland Dreier
2006-05-12 23:43 ` [PATCH 36 of 53] ipath - count local link integrity errors Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 37 of 53] ipath - name zero counter offsets consistently Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 38 of 53] ipath - SRQ compliance checks Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 39 of 53] ipath - count PE800 receive interrupts on user ports Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 40 of 53] ipath - remember to drop spinlock Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 41 of 53] ipath - disable interrupts while holding spinlock in RWQE get Bryan O'Sullivan
2006-05-15 15:55   ` Roland Dreier
2006-05-12 23:43 ` [PATCH 42 of 53] ipath - increment pointer properly when doing a diag read Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 43 of 53] ipath - fix memory leak when creating a QP fails Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 44 of 53] ipath - allow diags on any unit Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 45 of 53] ipath - fix memory leak when create of QP fails Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 46 of 53] ipath - enable GPIO interrupt on HT-460 Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 47 of 53] ipath - fix problem with lost interrupts on HT-400 Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 48 of 53] ipath - QP should ignore receive queue size if SRQ specified Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 49 of 53] ipath - NULL-terminate pci_device_id table Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 50 of 53] ipath - reduce maximum table sizes Bryan O'Sullivan
2006-05-15 16:00   ` Roland Dreier
2006-05-12 23:43 ` [PATCH 51 of 53] ipath - fix reporting of vendor ID and a few other trivial bits Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 52 of 53] ipath - register as IB device owner Bryan O'Sullivan
2006-05-12 23:43 ` [PATCH 53 of 53] ipath - add memory barrier when waiting for writes Bryan O'Sullivan
2006-05-15 15:57   ` Roland Dreier
2006-05-15 21:10     ` Bryan O'Sullivan
2006-05-15 23:01       ` ralphc
2006-05-15 23:08         ` Roland Dreier
2006-05-15 23:25           ` ralphc
2006-05-15 23:28             ` [openib-general] " Roland Dreier
2006-05-15 23:38               ` ralphc
2006-05-15 23:47                 ` Roland Dreier
2006-05-15 15:02 ` [openib-general] [PATCH 0 of 53] ipath driver updates for 2.6.17-rc4 Roger Heflin
2006-05-15 15:44 ` Roland Dreier
2006-05-15 16:00   ` [openib-general] " Roger Heflin
2006-05-15 16:04     ` Roland Dreier
2006-05-15 20:11       ` Roger Heflin
2006-05-15 21:09         ` Bryan O'Sullivan
2006-05-15 21:07   ` Bryan O'Sullivan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=300f0aa6f034eec6a806.1147477369@eng-12.pathscale.com \
    --to=bos@pathscale.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=openib-general@openib.org \
    --cc=rdreier@cisco.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox