[PATCH v2 06/11] xen-blkfront: add callbacks for PM suspend and hibernation
From: Munehisa Kamata
S4 power transisiton states are much different than xen
suspend/resume. Former is visible to the guest and frontend drivers should
be aware of the state transistions and should be able to take appropriate
actions when needed. In transition to S4 we need to make sure that at least
all the in-flight blkif requests get completed, since they probably contain
bits of the guest's memory image and that's not going to get saved any
other way. Hence, re-issuing of in-flight requests as in case of xen resume
will not work here. This is in contrast to xen-suspend where we need to
freeze with as little processing as possible to avoid dirtying RAM late in
the migration cycle and we know that in-flight data can wait.
Add freeze, thaw and restore callbacks for PM suspend and hibernation
support. All frontend drivers that needs to use PM_HIBERNATION/PM_SUSPEND
events, need to implement these xenbus_driver callbacks. The freeze handler
stops block-layer queue and disconnect the frontend from the backend while
freeing ring_info and associated resources. Before disconnecting from the
backend, we need to prevent any new IO from being queued and wait for
existing IO to complete. Freeze/unfreeze of the queues will guarantee
that there are no requests in use on the shared ring. However, for sanity
we should check state of the ring before disconnecting to make sure that
there are no outstanding requests to be processed on the ring.
The restore handler re-allocates ring_info, unquiesces and unfreezes the
queue and re-connect to the backend, so that rest of the kernel can
continue to use the block device transparently.
Note:For older backends,if a backend doesn't have commit'12ea729645ace'
xen/blkback: unmap all persistent grants when frontend gets disconnected,
the frontend may see massive amount of grant table warning when freeing
resources.
[ 36.852659] deferring g.e. 0xf9 (pfn 0x)
[ 36.855089] xen:grant_table: WARNING:e.g. 0x112 still in use!
In this case, persistent grants would need to be disabled.
[Anchal Agarwal: Changelog]:
RFC v1->v2: Removed timeout per request before disconnect during
blkfront freeze.
Added queue freeze/quiesce to the blkfront_freeze
Code cleanup
RFC v2->v3: None
RFC v3->v1: Code cleanup, Refractoring
v1->v2: * remove err variable in blkfront_freeze
* BugFix: error handling if rings are still busy
after queue freeze/quiesce and returnign driver to
connected state
* add TODO if blkback fails to disconnect on freeze
* Code formatting
Signed-off-by: Anchal Agarwal
Signed-off-by: Munehisa Kamata
---
drivers/block/xen-blkfront.c | 122 +--
1 file changed, 118 insertions(+), 4 deletions(-)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 3b889ea950c2..9e3ed1b9f509 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -48,6 +48,8 @@
#include
#include
#include
+#include
+#include
#include
#include
@@ -80,6 +82,8 @@ enum blkif_state {
BLKIF_STATE_DISCONNECTED,
BLKIF_STATE_CONNECTED,
BLKIF_STATE_SUSPENDED,
+ BLKIF_STATE_FREEZING,
+ BLKIF_STATE_FROZEN,
};
struct grant {
@@ -219,6 +223,7 @@ struct blkfront_info
struct list_head requests;
struct bio_list bio_list;
struct list_head info_list;
+ struct completion wait_backend_disconnected;
};
static unsigned int nr_minors;
@@ -1005,6 +1010,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16
sector_size,
info->sector_size = sector_size;
info->physical_sector_size = physical_sector_size;
blkif_set_queue_limits(info);
+ init_completion(&info->wait_backend_disconnected);
return 0;
}
@@ -1353,6 +1359,8 @@ static void blkif_free(struct blkfront_info *info, int
suspend)
unsigned int i;
struct blkfront_ring_info *rinfo;
+ if (info->connected == BLKIF_STATE_FREEZING)
+ goto free_rings;
/* Prevent new requests being issued until we fix things up. */
info->connected = suspend ?
BLKIF_STATE_SUSPENDED : BLKIF_STATE_DISCONNECTED;
@@ -1360,6 +1368,7 @@ static void blkif_free(struct blkfront_info *info, int
suspend)
if (info->rq)
blk_mq_stop_hw_queues(info->rq);
+free_rings:
for_each_rinfo(info, rinfo, i)
blkif_free_ring(rinfo);
@@ -1563,8 +1572,10 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;
struct blkfront_info *info = rinfo->dev_info;
- if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
+ if (unlikely(info->connected != BLKIF_STATE_CONNECTED &&
+ info->connected != BLKIF_STATE_FREEZING)) {
return IRQ_HANDLED;
+ }
[Xen-devel] [RFC PATCH V2 06/11] xen-blkfront: add callbacks for PM suspend and hibernation
From: Munehisa Kamata
Add freeze, thaw and restore callbacks for PM suspend and hibernation
support. All frontend drivers that needs to use PM_HIBERNATION/PM_SUSPEND
events, need to implement these xenbus_driver callbacks.
The freeze handler stops a block-layer queue and disconnect the
frontend from the backend while freeing ring_info and associated resources.
The restore handler re-allocates ring_info and re-connect to the
backend, so the rest of the kernel can continue to use the block device
transparently. Also, the handlers are used for both PM suspend and
hibernation so that we can keep the existing suspend/resume callbacks for
Xen suspend without modification. Before disconnecting from backend,
we need to prevent any new IO from being queued and wait for existing
IO to complete. Freeze/unfreeze of the queues will guarantee that there
are no requests in use on the shared ring.
Note:For older backends,if a backend doesn't have commit'12ea729645ace'
xen/blkback: unmap all persistent grants when frontend gets disconnected,
the frontend may see massive amount of grant table warning when freeing
resources.
[ 36.852659] deferring g.e. 0xf9 (pfn 0x)
[ 36.855089] xen:grant_table: WARNING:e.g. 0x112 still in use!
In this case, persistent grants would need to be disabled.
[Anchal Changelog: Removed timeout/request during blkfront freeze.
Fixed major part of the code to work with blk-mq]
Signed-off-by: Anchal Agarwal
Signed-off-by: Munehisa Kamata
---
drivers/block/xen-blkfront.c | 119 ---
1 file changed, 112 insertions(+), 7 deletions(-)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index a74d03913822..b1d38ca4600f 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -47,6 +47,8 @@
#include
#include
#include
+#include
+#include
#include
#include
@@ -79,6 +81,8 @@ enum blkif_state {
BLKIF_STATE_DISCONNECTED,
BLKIF_STATE_CONNECTED,
BLKIF_STATE_SUSPENDED,
+ BLKIF_STATE_FREEZING,
+ BLKIF_STATE_FROZEN
};
struct grant {
@@ -220,6 +224,7 @@ struct blkfront_info
struct list_head requests;
struct bio_list bio_list;
struct list_head info_list;
+ struct completion wait_backend_disconnected;
};
static unsigned int nr_minors;
@@ -261,6 +266,7 @@ static DEFINE_SPINLOCK(minor_lock);
static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo);
static void blkfront_gather_backend_features(struct blkfront_info *info);
static int negotiate_mq(struct blkfront_info *info);
+static void __blkif_free(struct blkfront_info *info);
static int get_id_from_freelist(struct blkfront_ring_info *rinfo)
{
@@ -995,6 +1001,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16
sector_size,
info->sector_size = sector_size;
info->physical_sector_size = physical_sector_size;
blkif_set_queue_limits(info);
+ init_completion(&info->wait_backend_disconnected);
return 0;
}
@@ -1218,6 +1225,8 @@ static void xlvbd_release_gendisk(struct blkfront_info
*info)
/* Already hold rinfo->ring_lock. */
static inline void kick_pending_request_queues_locked(struct
blkfront_ring_info *rinfo)
{
+ if (unlikely(rinfo->dev_info->connected == BLKIF_STATE_FREEZING))
+ return;
if (!RING_FULL(&rinfo->ring))
blk_mq_start_stopped_hw_queues(rinfo->dev_info->rq, true);
}
@@ -1341,8 +1350,6 @@ static void blkif_free_ring(struct blkfront_ring_info
*rinfo)
static void blkif_free(struct blkfront_info *info, int suspend)
{
- unsigned int i;
-
/* Prevent new requests being issued until we fix things up. */
info->connected = suspend ?
BLKIF_STATE_SUSPENDED : BLKIF_STATE_DISCONNECTED;
@@ -1350,6 +1357,13 @@ static void blkif_free(struct blkfront_info *info, int
suspend)
if (info->rq)
blk_mq_stop_hw_queues(info->rq);
+ __blkif_free(info);
+}
+
+static void __blkif_free(struct blkfront_info *info)
+{
+ unsigned int i;
+
for (i = 0; i < info->nr_rings; i++)
blkif_free_ring(&info->rinfo[i]);
@@ -1553,8 +1567,10 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;
struct blkfront_info *info = rinfo->dev_info;
- if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
- return IRQ_HANDLED;
+ if (unlikely(info->connected != BLKIF_STATE_CONNECTED)) {
+ if (info->connected != BLKIF_STATE_FREEZING)
+ return IRQ_HANDLED;
+ }
spin_lock_irqsave(&rinfo->ring_lock, flags);
again:
@@ -2020,6 +2036,7 @@ static int blkif_recover(struct blkfront_info *info)
struct bio *bio;
unsigned int segs;
+ bool frozen = info->connected == BLKIF_STATE_FROZEN;
blkfront_gather_backend_feat
