[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20170131053604.421212904@linuxfoundation.org>
Date: Tue, 31 Jan 2017 06:36:34 +0100
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org, Max Gurtovoy <maxg@...lanox.com>,
Sagi Grimberg <sagi@...mberg.me>,
Doug Ledford <dledford@...hat.com>
Subject: [PATCH 4.9 30/66] IB/iser: Fix sg_tablesize calculation
4.9-stable review patch. If anyone has any objections, please let me know.
------------------
From: Max Gurtovoy <maxg@...lanox.com>
commit 1e5db6c31ade4150c2e2b1a21e39f776c38fea39 upstream.
For devices that can register page list that is bigger than
USHRT_MAX, we actually take the wrong value for sg_tablesize.
E.g: for CX4 max_fast_reg_page_list_len is 65536 (bigger than USHRT_MAX)
so we set sg_tablesize to 0 by mistake. Therefore, each IO that is
bigger than 4k splitted to "< 4k" chunks that cause performance degredation.
Remove wrong sg_tablesize assignment, and use the value that was set during
address resolution handler with the needed casting.
Signed-off-by: Max Gurtovoy <maxg@...lanox.com>
Reviewed-by: Sagi Grimberg <sagi@...mberg.me>
Signed-off-by: Doug Ledford <dledford@...hat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
drivers/infiniband/ulp/iser/iscsi_iser.c | 7 -------
1 file changed, 7 deletions(-)
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -651,13 +651,6 @@ iscsi_iser_session_create(struct iscsi_e
SHOST_DIX_GUARD_CRC);
}
- /*
- * Limit the sg_tablesize and max_sectors based on the device
- * max fastreg page list length.
- */
- shost->sg_tablesize = min_t(unsigned short, shost->sg_tablesize,
- ib_conn->device->ib_device->attrs.max_fast_reg_page_list_len);
-
if (iscsi_host_add(shost,
ib_conn->device->ib_device->dma_device)) {
mutex_unlock(&iser_conn->state_mutex);
Powered by blists - more mailing lists