lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240122170956.496436-1-mhklinux@outlook.com>
Date: Mon, 22 Jan 2024 09:09:56 -0800
From: mhkelley58@...il.com
To: haiyangz@...rosoft.com,
	wei.liu@...nel.org,
	decui@...rosoft.com,
	jejb@...ux.ibm.com,
	martin.petersen@...cle.com,
	linux-kernel@...r.kernel.org,
	linux-hyperv@...r.kernel.org,
	linux-scsi@...r.kernel.org
Subject: [PATCH 1/1] scsi: storvsc: Fix ring buffer size calculation

From: Michael Kelley <mhklinux@...look.com>

Current code uses the specified ring buffer size (either the default of
128 Kbytes or a module parameter specified value) to encompass the one page
ring buffer header plus the actual ring itself.  When the page size is
4K, carving off one page for the header isn't significant.  But when the
page size is 64K on ARM64, only half of the default 128 Kbytes is left
for the actual ring.  While this doesn't break anything, the smaller
ring size could be a performance bottleneck.

Fix this by applying the VMBUS_RING_SIZE macro to the specified ring
buffer size.  This macro adds a page for the header, and rounds up
the size to a page boundary, using the page size for which the kernel
is built.  Use this new size for subsequent ring buffer calculations.
For example, on ARM64 with 64K page size and the default ring size,
this results in the actual ring being 128 Kbytes, which is intended.

Cc: <stable@...r.kernel.org> # 5.15.x
Signed-off-by: Michael Kelley <mhklinux@...look.com>
---
 drivers/scsi/storvsc_drv.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index a95936b18f69..7ceb982040a5 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -330,6 +330,7 @@ enum storvsc_request_type {
  */
 
 static int storvsc_ringbuffer_size = (128 * 1024);
+static int aligned_ringbuffer_size;
 static u32 max_outstanding_req_per_channel;
 static int storvsc_change_queue_depth(struct scsi_device *sdev, int queue_depth);
 
@@ -687,8 +688,8 @@ static void handle_sc_creation(struct vmbus_channel *new_sc)
 	new_sc->next_request_id_callback = storvsc_next_request_id;
 
 	ret = vmbus_open(new_sc,
-			 storvsc_ringbuffer_size,
-			 storvsc_ringbuffer_size,
+			 aligned_ringbuffer_size,
+			 aligned_ringbuffer_size,
 			 (void *)&props,
 			 sizeof(struct vmstorage_channel_properties),
 			 storvsc_on_channel_callback, new_sc);
@@ -1973,7 +1974,7 @@ static int storvsc_probe(struct hv_device *device,
 	dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1);
 
 	stor_device->port_number = host->host_no;
-	ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc);
+	ret = storvsc_connect_to_vsp(device, aligned_ringbuffer_size, is_fc);
 	if (ret)
 		goto err_out1;
 
@@ -2164,7 +2165,7 @@ static int storvsc_resume(struct hv_device *hv_dev)
 {
 	int ret;
 
-	ret = storvsc_connect_to_vsp(hv_dev, storvsc_ringbuffer_size,
+	ret = storvsc_connect_to_vsp(hv_dev, aligned_ringbuffer_size,
 				     hv_dev_is_fc(hv_dev));
 	return ret;
 }
@@ -2198,8 +2199,9 @@ static int __init storvsc_drv_init(void)
 	 * the ring buffer indices) by the max request size (which is
 	 * vmbus_channel_packet_multipage_buffer + struct vstor_packet + u64)
 	 */
+	aligned_ringbuffer_size = VMBUS_RING_SIZE(storvsc_ringbuffer_size);
 	max_outstanding_req_per_channel =
-		((storvsc_ringbuffer_size - PAGE_SIZE) /
+		((aligned_ringbuffer_size - PAGE_SIZE) /
 		ALIGN(MAX_MULTIPAGE_BUFFER_PACKET +
 		sizeof(struct vstor_packet) + sizeof(u64),
 		sizeof(u64)));
-- 
2.25.1


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ