From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/drivers/block/xen-blkback/xenbus.c | 230 +++++++++++++++++++++++++++++++++++---------------------
1 files changed, 143 insertions(+), 87 deletions(-)
diff --git a/kernel/drivers/block/xen-blkback/xenbus.c b/kernel/drivers/block/xen-blkback/xenbus.c
index 42af2f3..ddea362 100644
--- a/kernel/drivers/block/xen-blkback/xenbus.c
+++ b/kernel/drivers/block/xen-blkback/xenbus.c
@@ -1,16 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/* Xenbus code for blkif backend
Copyright (C) 2005 Rusty Russell <rusty@rustcorp.com.au>
Copyright (C) 2005 XenSource Ltd
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2 of the License, or
- (at your option) any later version.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
*/
@@ -152,8 +144,7 @@
INIT_LIST_HEAD(&ring->pending_free);
INIT_LIST_HEAD(&ring->persistent_purge_list);
INIT_WORK(&ring->persistent_purge_work, xen_blkbk_unmap_purged_grants);
- spin_lock_init(&ring->free_pages_lock);
- INIT_LIST_HEAD(&ring->free_pages);
+ gnttab_page_cache_init(&ring->free_pages);
spin_lock_init(&ring->pending_free_lock);
init_waitqueue_head(&ring->pending_free_wq);
@@ -165,6 +156,11 @@
return 0;
}
+
+/* Enable the persistent grants feature. */
+static bool feature_persistent = true;
+module_param(feature_persistent, bool, 0644);
+MODULE_PARM_DESC(feature_persistent, "Enables the persistent grants feature");
static struct xen_blkif *xen_blkif_alloc(domid_t domid)
{
@@ -198,6 +194,9 @@
{
int err;
struct xen_blkif *blkif = ring->blkif;
+ const struct blkif_common_sring *sring_common;
+ RING_IDX rsp_prod, req_prod;
+ unsigned int size;
/* Already connected through? */
if (ring->irq)
@@ -208,45 +207,61 @@
if (err < 0)
return err;
+ sring_common = (struct blkif_common_sring *)ring->blk_ring;
+ rsp_prod = READ_ONCE(sring_common->rsp_prod);
+ req_prod = READ_ONCE(sring_common->req_prod);
+
switch (blkif->blk_protocol) {
case BLKIF_PROTOCOL_NATIVE:
{
- struct blkif_sring *sring;
- sring = (struct blkif_sring *)ring->blk_ring;
- BACK_RING_INIT(&ring->blk_rings.native, sring,
- XEN_PAGE_SIZE * nr_grefs);
+ struct blkif_sring *sring_native =
+ (struct blkif_sring *)ring->blk_ring;
+
+ BACK_RING_ATTACH(&ring->blk_rings.native, sring_native,
+ rsp_prod, XEN_PAGE_SIZE * nr_grefs);
+ size = __RING_SIZE(sring_native, XEN_PAGE_SIZE * nr_grefs);
break;
}
case BLKIF_PROTOCOL_X86_32:
{
- struct blkif_x86_32_sring *sring_x86_32;
- sring_x86_32 = (struct blkif_x86_32_sring *)ring->blk_ring;
- BACK_RING_INIT(&ring->blk_rings.x86_32, sring_x86_32,
- XEN_PAGE_SIZE * nr_grefs);
+ struct blkif_x86_32_sring *sring_x86_32 =
+ (struct blkif_x86_32_sring *)ring->blk_ring;
+
+ BACK_RING_ATTACH(&ring->blk_rings.x86_32, sring_x86_32,
+ rsp_prod, XEN_PAGE_SIZE * nr_grefs);
+ size = __RING_SIZE(sring_x86_32, XEN_PAGE_SIZE * nr_grefs);
break;
}
case BLKIF_PROTOCOL_X86_64:
{
- struct blkif_x86_64_sring *sring_x86_64;
- sring_x86_64 = (struct blkif_x86_64_sring *)ring->blk_ring;
- BACK_RING_INIT(&ring->blk_rings.x86_64, sring_x86_64,
- XEN_PAGE_SIZE * nr_grefs);
+ struct blkif_x86_64_sring *sring_x86_64 =
+ (struct blkif_x86_64_sring *)ring->blk_ring;
+
+ BACK_RING_ATTACH(&ring->blk_rings.x86_64, sring_x86_64,
+ rsp_prod, XEN_PAGE_SIZE * nr_grefs);
+ size = __RING_SIZE(sring_x86_64, XEN_PAGE_SIZE * nr_grefs);
break;
}
default:
BUG();
}
+ err = -EIO;
+ if (req_prod - rsp_prod > size)
+ goto fail;
+
err = bind_interdomain_evtchn_to_irqhandler_lateeoi(blkif->domid,
evtchn, xen_blkif_be_int, 0, "blkif-backend", ring);
- if (err < 0) {
- xenbus_unmap_ring_vfree(blkif->be->dev, ring->blk_ring);
- ring->blk_rings.common.sring = NULL;
- return err;
- }
+ if (err < 0)
+ goto fail;
ring->irq = err;
return 0;
+
+fail:
+ xenbus_unmap_ring_vfree(blkif->be->dev, ring->blk_ring);
+ ring->blk_rings.common.sring = NULL;
+ return err;
}
static int xen_blkif_disconnect(struct xen_blkif *blkif)
@@ -307,8 +322,7 @@
BUG_ON(atomic_read(&ring->persistent_gnt_in_use) != 0);
BUG_ON(!list_empty(&ring->persistent_purge_list));
BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts));
- BUG_ON(!list_empty(&ring->free_pages));
- BUG_ON(ring->free_pages_num != 0);
+ BUG_ON(ring->free_pages.num_pages != 0);
BUG_ON(ring->persistent_gnt_c != 0);
WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages));
ring->active = false;
@@ -349,6 +363,12 @@
return -ENOMEM;
return 0;
+}
+
+void xen_blkif_interface_fini(void)
+{
+ kmem_cache_destroy(xen_blkif_cachep);
+ xen_blkif_cachep = NULL;
}
/*
@@ -450,7 +470,6 @@
device_remove_file(&dev->dev, &dev_attr_physical_device);
}
-
static void xen_vbd_free(struct xen_vbd *vbd)
{
if (vbd->bdev)
@@ -507,6 +526,7 @@
handle, blkif->domid);
return 0;
}
+
static int xen_blkbk_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
@@ -590,6 +610,7 @@
if (err)
dev_warn(&dev->dev, "writing feature-discard (%d)", err);
}
+
int xen_blkbk_barrier(struct xenbus_transaction xbt,
struct backend_info *be, int state)
{
@@ -674,7 +695,6 @@
xen_blkbk_remove(dev);
return err;
}
-
/*
* Callback received when the hotplug scripts have placed the physical-device
@@ -767,7 +787,6 @@
}
}
-
/*
* Callback received when the frontend's state changes.
*/
@@ -828,7 +847,7 @@
xenbus_switch_state(dev, XenbusStateClosed);
if (xenbus_dev_is_online(dev))
break;
- /* fall through */
+ fallthrough;
/* if not online */
case XenbusStateUnknown:
/* implies xen_blkif_disconnect() via xen_blkbk_remove() */
@@ -842,9 +861,27 @@
}
}
+/* Once a memory pressure is detected, squeeze free page pools for a while. */
+static unsigned int buffer_squeeze_duration_ms = 10;
+module_param_named(buffer_squeeze_duration_ms,
+ buffer_squeeze_duration_ms, int, 0644);
+MODULE_PARM_DESC(buffer_squeeze_duration_ms,
+"Duration in ms to squeeze pages buffer when a memory pressure is detected");
+
+/*
+ * Callback received when the memory pressure is detected.
+ */
+static void reclaim_memory(struct xenbus_device *dev)
+{
+ struct backend_info *be = dev_get_drvdata(&dev->dev);
+
+ if (!be)
+ return;
+ be->blkif->buffer_squeeze_end = jiffies +
+ msecs_to_jiffies(buffer_squeeze_duration_ms);
+}
/* ** Connection ** */
-
/*
* Write the physical details regarding the block device to the store, and
@@ -873,7 +910,8 @@
xen_blkbk_barrier(xbt, be, be->blkif->vbd.flush_support);
- err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u", 1);
+ err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u",
+ be->blkif->vbd.feature_gnt_persistent_parm);
if (err) {
xenbus_dev_fatal(dev, err, "writing %s/feature-persistent",
dev->nodename);
@@ -937,7 +975,7 @@
int err, i, j;
struct xen_blkif *blkif = ring->blkif;
struct xenbus_device *dev = blkif->be->dev;
- unsigned int ring_page_order, nr_grefs, evtchn;
+ unsigned int nr_grefs, evtchn;
err = xenbus_scanf(XBT_NIL, dir, "event-channel", "%u",
&evtchn);
@@ -947,43 +985,33 @@
return err;
}
- err = xenbus_scanf(XBT_NIL, dev->otherend, "ring-page-order", "%u",
- &ring_page_order);
- if (err != 1) {
- err = xenbus_scanf(XBT_NIL, dir, "ring-ref", "%u", &ring_ref[0]);
+ nr_grefs = blkif->nr_ring_pages;
+
+ if (unlikely(!nr_grefs)) {
+ WARN_ON(true);
+ return -EINVAL;
+ }
+
+ for (i = 0; i < nr_grefs; i++) {
+ char ring_ref_name[RINGREF_NAME_LEN];
+
+ if (blkif->multi_ref)
+ snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i);
+ else {
+ WARN_ON(i != 0);
+ snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref");
+ }
+
+ err = xenbus_scanf(XBT_NIL, dir, ring_ref_name,
+ "%u", &ring_ref[i]);
+
if (err != 1) {
err = -EINVAL;
- xenbus_dev_fatal(dev, err, "reading %s/ring-ref", dir);
+ xenbus_dev_fatal(dev, err, "reading %s/%s",
+ dir, ring_ref_name);
return err;
- }
- nr_grefs = 1;
- } else {
- unsigned int i;
-
- if (ring_page_order > xen_blkif_max_ring_order) {
- err = -EINVAL;
- xenbus_dev_fatal(dev, err, "%s/request %d ring page order exceed max:%d",
- dir, ring_page_order,
- xen_blkif_max_ring_order);
- return err;
- }
-
- nr_grefs = 1 << ring_page_order;
- for (i = 0; i < nr_grefs; i++) {
- char ring_ref_name[RINGREF_NAME_LEN];
-
- snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i);
- err = xenbus_scanf(XBT_NIL, dir, ring_ref_name,
- "%u", &ring_ref[i]);
- if (err != 1) {
- err = -EINVAL;
- xenbus_dev_fatal(dev, err, "reading %s/%s",
- dir, ring_ref_name);
- return err;
- }
}
}
- blkif->nr_ring_pages = nr_grefs;
err = -ENOMEM;
for (i = 0; i < nr_grefs * XEN_BLKIF_REQS_PER_PAGE; i++) {
@@ -1034,35 +1062,39 @@
static int connect_ring(struct backend_info *be)
{
struct xenbus_device *dev = be->dev;
- unsigned int pers_grants;
+ struct xen_blkif *blkif = be->blkif;
char protocol[64] = "";
int err, i;
char *xspath;
size_t xspathsize;
const size_t xenstore_path_ext_size = 11; /* sufficient for "/queue-NNN" */
unsigned int requested_num_queues = 0;
+ unsigned int ring_page_order;
pr_debug("%s %s\n", __func__, dev->otherend);
- be->blkif->blk_protocol = BLKIF_PROTOCOL_DEFAULT;
+ blkif->blk_protocol = BLKIF_PROTOCOL_DEFAULT;
err = xenbus_scanf(XBT_NIL, dev->otherend, "protocol",
"%63s", protocol);
if (err <= 0)
strcpy(protocol, "unspecified, assuming default");
else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_NATIVE))
- be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
+ blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_X86_32))
- be->blkif->blk_protocol = BLKIF_PROTOCOL_X86_32;
+ blkif->blk_protocol = BLKIF_PROTOCOL_X86_32;
else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_X86_64))
- be->blkif->blk_protocol = BLKIF_PROTOCOL_X86_64;
+ blkif->blk_protocol = BLKIF_PROTOCOL_X86_64;
else {
xenbus_dev_fatal(dev, err, "unknown fe protocol %s", protocol);
return -ENOSYS;
}
- pers_grants = xenbus_read_unsigned(dev->otherend, "feature-persistent",
- 0);
- be->blkif->vbd.feature_gnt_persistent = pers_grants;
- be->blkif->vbd.overflow_max_grants = 0;
+
+ blkif->vbd.feature_gnt_persistent_parm = feature_persistent;
+ blkif->vbd.feature_gnt_persistent =
+ blkif->vbd.feature_gnt_persistent_parm &&
+ xenbus_read_unsigned(dev->otherend, "feature-persistent", 0);
+
+ blkif->vbd.overflow_max_grants = 0;
/*
* Read the number of hardware queues from frontend.
@@ -1078,16 +1110,33 @@
requested_num_queues, xenblk_max_queues);
return -ENOSYS;
}
- be->blkif->nr_rings = requested_num_queues;
- if (xen_blkif_alloc_rings(be->blkif))
+ blkif->nr_rings = requested_num_queues;
+ if (xen_blkif_alloc_rings(blkif))
return -ENOMEM;
pr_info("%s: using %d queues, protocol %d (%s) %s\n", dev->nodename,
- be->blkif->nr_rings, be->blkif->blk_protocol, protocol,
- pers_grants ? "persistent grants" : "");
+ blkif->nr_rings, blkif->blk_protocol, protocol,
+ blkif->vbd.feature_gnt_persistent ? "persistent grants" : "");
- if (be->blkif->nr_rings == 1)
- return read_per_ring_refs(&be->blkif->rings[0], dev->otherend);
+ err = xenbus_scanf(XBT_NIL, dev->otherend, "ring-page-order", "%u",
+ &ring_page_order);
+ if (err != 1) {
+ blkif->nr_ring_pages = 1;
+ blkif->multi_ref = false;
+ } else if (ring_page_order <= xen_blkif_max_ring_order) {
+ blkif->nr_ring_pages = 1 << ring_page_order;
+ blkif->multi_ref = true;
+ } else {
+ err = -EINVAL;
+ xenbus_dev_fatal(dev, err,
+ "requested ring page order %d exceed max:%d",
+ ring_page_order,
+ xen_blkif_max_ring_order);
+ return err;
+ }
+
+ if (blkif->nr_rings == 1)
+ return read_per_ring_refs(&blkif->rings[0], dev->otherend);
else {
xspathsize = strlen(dev->otherend) + xenstore_path_ext_size;
xspath = kmalloc(xspathsize, GFP_KERNEL);
@@ -1096,10 +1145,10 @@
return -ENOMEM;
}
- for (i = 0; i < be->blkif->nr_rings; i++) {
+ for (i = 0; i < blkif->nr_rings; i++) {
memset(xspath, 0, xspathsize);
snprintf(xspath, xspathsize, "%s/queue-%u", dev->otherend, i);
- err = read_per_ring_refs(&be->blkif->rings[i], xspath);
+ err = read_per_ring_refs(&blkif->rings[i], xspath);
if (err) {
kfree(xspath);
return err;
@@ -1119,10 +1168,17 @@
.ids = xen_blkbk_ids,
.probe = xen_blkbk_probe,
.remove = xen_blkbk_remove,
- .otherend_changed = frontend_changed
+ .otherend_changed = frontend_changed,
+ .allow_rebind = true,
+ .reclaim_memory = reclaim_memory,
};
int xen_blkif_xenbus_init(void)
{
return xenbus_register_backend(&xen_blkbk_driver);
}
+
+void xen_blkif_xenbus_fini(void)
+{
+ xenbus_unregister_driver(&xen_blkbk_driver);
+}
--
Gitblit v1.6.2