From: Joachim Fenkes <fenkes@de.ibm.com>
To: "LinuxPPC-Dev" <linuxppc-dev@ozlabs.org>,
LKML <linux-kernel@vger.kernel.org>,
"OF-General" <general@lists.openfabrics.org>,
Roland Dreier <rolandd@cisco.com>,
"OF-EWG" <ewg@lists.openfabrics.org>
Cc: "Hoang-Nam Nguyen" <hnguyen@de.ibm.com>,
Christoph Raisch <raisch@de.ibm.com>,
Stefan Roscher <stefan.roscher@de.ibm.com>
Subject: [PATCH 11/12] IB/ehca: Serialize MR alloc and MR free hvCalls
Date: Tue, 11 Sep 2007 15:34:35 +0200 [thread overview]
Message-ID: <200709111534.35916.fenkes@de.ibm.com> (raw)
In-Reply-To: <200709111518.26276.fenkes@de.ibm.com>
Some firmware levels exhibit a race condition between H_ALLOC_RESOURCE(MR)
and H_FREE_RESOURCE(MR). Work around this problem by locking these hvCalls
against each other.
Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
---
drivers/infiniband/hw/ehca/hcp_if.c | 28 +++++++++++++++++++++-------
1 files changed, 21 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/hw/ehca/hcp_if.c b/drivers/infiniband/hw/ehca/hcp_if.c
index a70a5ed..d3d1ef2 100644
--- a/drivers/infiniband/hw/ehca/hcp_if.c
+++ b/drivers/infiniband/hw/ehca/hcp_if.c
@@ -120,15 +120,28 @@ static long ehca_plpar_hcall_norets(unsigned long opcode,
unsigned long arg7)
{
long ret;
- int i, sleep_msecs;
+ int i, sleep_msecs, do_lock;
+ unsigned long flags;
ehca_gen_dbg("opcode=%lx " HCALL7_REGS_FORMAT,
opcode, arg1, arg2, arg3, arg4, arg5, arg6, arg7);
+ /* lock H_FREE_RESOURCE(MR) against itself and H_ALLOC_RESOURCE(MR) */
+ if ((opcode == H_FREE_RESOURCE) && (arg7 == 5)) {
+ arg7 = 0; /* better not upset firmware */
+ do_lock = 1;
+ }
+
for (i = 0; i < 5; i++) {
+ if (do_lock)
+ spin_lock_irqsave(&hcall_lock, flags);
+
ret = plpar_hcall_norets(opcode, arg1, arg2, arg3, arg4,
arg5, arg6, arg7);
+ if (do_lock)
+ spin_unlock_irqrestore(&hcall_lock, flags);
+
if (H_IS_LONG_BUSY(ret)) {
sleep_msecs = get_longbusy_msecs(ret);
msleep_interruptible(sleep_msecs);
@@ -161,23 +174,24 @@ static long ehca_plpar_hcall9(unsigned long opcode,
unsigned long arg9)
{
long ret;
- int i, sleep_msecs, lock_is_set = 0;
+ int i, sleep_msecs, do_lock;
unsigned long flags = 0;
ehca_gen_dbg("INPUT -- opcode=%lx " HCALL9_REGS_FORMAT, opcode,
arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8, arg9);
+ /* lock H_ALLOC_RESOURCE(MR) against itself and H_FREE_RESOURCE(MR) */
+ do_lock = ((opcode == H_ALLOC_RESOURCE) && (arg2 == 5));
+
for (i = 0; i < 5; i++) {
- if ((opcode == H_ALLOC_RESOURCE) && (arg2 == 5)) {
+ if (do_lock)
spin_lock_irqsave(&hcall_lock, flags);
- lock_is_set = 1;
- }
ret = plpar_hcall9(opcode, outs,
arg1, arg2, arg3, arg4, arg5,
arg6, arg7, arg8, arg9);
- if (lock_is_set)
+ if (do_lock)
spin_unlock_irqrestore(&hcall_lock, flags);
if (H_IS_LONG_BUSY(ret)) {
@@ -807,7 +821,7 @@ u64 hipz_h_free_resource_mr(const struct ipz_adapter_handle adapter_handle,
return ehca_plpar_hcall_norets(H_FREE_RESOURCE,
adapter_handle.handle, /* r4 */
mr->ipz_mr_handle.handle, /* r5 */
- 0, 0, 0, 0, 0);
+ 0, 0, 0, 0, 5);
}
u64 hipz_h_reregister_pmr(const struct ipz_adapter_handle adapter_handle,
--
1.5.2
next prev parent reply other threads:[~2007-09-11 13:36 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-09-11 13:18 [PATCH 00/12] IB/ehca: New features and fixes for 2.6.24 Joachim Fenkes
2007-09-11 13:26 ` [PATCH 01/12] IB/ehca: Small QP userspace support Joachim Fenkes
2007-09-11 13:29 ` [PATCH 02/12] IB/ehca: Add 1 is not longer needed because of firmware interface change Joachim Fenkes
2007-09-12 20:21 ` Roland Dreier
2007-09-14 13:48 ` Joachim Fenkes
2007-09-14 16:05 ` Roland Dreier
2007-09-11 13:29 ` [PATCH 03/12] IB/ehca: Support more than 4k QPs for userspace and kernelspace Joachim Fenkes
2007-09-11 13:31 ` [PATCH 04/12] IB/ehca: Use remap_4k_pfn() to map firmware contexts to user space Joachim Fenkes
2007-09-11 13:31 ` [PATCH 05/12] IB/ehca: Refactor hvcall tracing Joachim Fenkes
2007-09-11 13:32 ` [PATCH 06/12] IB/ehca: Print return codes as signed decimal integers Joachim Fenkes
2007-09-11 13:32 ` [PATCH 07/12] IB/ehca: ehca_gen_warn() should always print Joachim Fenkes
2007-09-11 13:33 ` [PATCH 08/12] IB/ehca: Replace get_paca()->paca_index by the more portable smp_processor_id() Joachim Fenkes
2007-09-11 14:51 ` Nathan Lynch
2007-09-12 14:42 ` Joachim Fenkes
2007-09-12 14:44 ` [PATCH 08/12] IB/ehca: Replace get_paca()->paca_index by the more portable raw_smp_processor_id() Joachim Fenkes
2007-09-11 13:33 ` [PATCH 09/12] IB/ehca: Add check for max #SGE to create_qp() Joachim Fenkes
2007-09-11 13:34 ` [PATCH 10/12] IB/ehca: Path migration support Joachim Fenkes
2007-09-11 13:34 ` Joachim Fenkes [this message]
2007-09-11 13:35 ` [PATCH 12/12] IB/ehca: Bump version number and change its format Joachim Fenkes
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=200709111534.35916.fenkes@de.ibm.com \
--to=fenkes@de.ibm.com \
--cc=ewg@lists.openfabrics.org \
--cc=general@lists.openfabrics.org \
--cc=hnguyen@de.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@ozlabs.org \
--cc=raisch@de.ibm.com \
--cc=rolandd@cisco.com \
--cc=stefan.roscher@de.ibm.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