[RFC 7/8] p2pmem: Support device removal

From: Logan Gunthorpe
Date: Thu Mar 30 2017 - 18:13:47 EST

Next message: Logan Gunthorpe: "[RFC 4/8] p2pmem: Add debugfs "stats" file"
Previous message: Alexey Gladkov: "Re: [PATCH RFC 0/4] proc: support multiple separate proc instances per pidnamespace"
In reply to: Logan Gunthorpe: "[RFC 0/8] Copy Offload with Peer-to-Peer PCI Memory"
Next in thread: Logan Gunthorpe: "[RFC 4/8] p2pmem: Add debugfs "stats" file"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This patch creates a list of callbacks to notify users of this memory
that the p2pmem device is going away or gone.

In nvmet-rdma, we disconnect any queue using p2p memory.
The remote side will then automatically reconnect in a
couple seconds and regular system memory (or a different p2pmem device)
will be used.

Signed-off-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Signed-off-by: Stephen Bates <sbates@xxxxxxxxxxxx>
Signed-off-by: Steve Wise <swise@xxxxxxxxxxxxxxxxxxxxx>
---
drivers/memory/p2pmem.c | 75 ++++++++++++++++++++++++++++++++---
drivers/nvme/target/rdma.c | 98 ++++++++++++++++++++++++++--------------------
include/linux/p2pmem.h | 19 +++++++--
3 files changed, 140 insertions(+), 52 deletions(-)

diff --git a/drivers/memory/p2pmem.c b/drivers/memory/p2pmem.c
index 71741c2..499d42c 100644
--- a/drivers/memory/p2pmem.c
+++ b/drivers/memory/p2pmem.c
@@ -105,6 +105,21 @@ static void p2pmem_release(struct device *dev)
kfree(p);
}

+struct remove_callback {
+ struct list_head list;
+ void (*callback)(void *context);
+ void *context;
+};
+
+static void p2pmem_remove(struct p2pmem_dev *p)
+{
+ struct remove_callback *remove_call, *tmp;
+
+ p->alive = false;
+ list_for_each_entry_safe(remove_call, tmp, &p->remove_list, list)
+ remove_call->callback(remove_call->context);
+}
+
/**
* p2pmem_create() - create a new p2pmem device
* @parent: the parent device to create it under
@@ -123,6 +138,10 @@ struct p2pmem_dev *p2pmem_create(struct device *parent)
return ERR_PTR(-ENOMEM);

init_completion(&p->cmp);
+ mutex_init(&p->remove_mutex);
+ INIT_LIST_HEAD(&p->remove_list);
+ p->alive = true;
+
device_initialize(&p->dev);
p->dev.class = p2pmem_class;
p->dev.parent = parent;
@@ -187,6 +206,7 @@ void p2pmem_unregister(struct p2pmem_dev *p)

dev_info(&p->dev, "unregistered");
device_del(&p->dev);
+ p2pmem_remove(p);
ida_simple_remove(&p2pmem_ida, p->id);
put_device(&p->dev);
}
@@ -291,6 +311,9 @@ EXPORT_SYMBOL(p2pmem_add_pci_region);
*/
void *p2pmem_alloc(struct p2pmem_dev *p, size_t size)
{
+ if (!p->alive)
+ return NULL;
+
return (void *)gen_pool_alloc(p->pool, size);
}
EXPORT_SYMBOL(p2pmem_alloc);
@@ -349,6 +372,9 @@ static int upstream_bridges_match(struct device *p2pmem,
struct pci_dev *p2p_up;
struct pci_dev *dma_up;

+ if (!to_p2pmem(p2pmem)->alive)
+ return false;
+
p2p_up = get_upstream_switch_port(p2pmem);
if (!p2p_up) {
dev_warn(p2pmem, "p2pmem is not behind a pci switch");
@@ -383,6 +409,8 @@ static int upstream_bridges_match(struct device *p2pmem,
* specified devices
* @dma_devices: a null terminated array of device pointers which
* all must be compatible with the returned p2pmem device
+ * @remove_callback: this callback will be called if the p2pmem
+ * device is removed.
*
* For now, we only support cases where all the devices that
* will transfer to the p2pmem device are on the same switch.
@@ -400,9 +428,13 @@ static int upstream_bridges_match(struct device *p2pmem,
* (use p2pmem_put to return the reference) or NULL if no compatible
* p2pmem device is found.
*/
-struct p2pmem_dev *p2pmem_find_compat(struct device **dma_devices)
+struct p2pmem_dev *p2pmem_find_compat(struct device **dma_devices,
+ void (*remove_callback)(void *context),
+ void *context)
{
struct device *dev;
+ struct p2pmem_dev *p;
+ struct remove_callback *remove_call;

dev = class_find_device(p2pmem_class, NULL, dma_devices,
upstream_bridges_match);
@@ -410,21 +442,54 @@ struct p2pmem_dev *p2pmem_find_compat(struct device **dma_devices)
if (!dev)
return NULL;

- return to_p2pmem(dev);
+ p = to_p2pmem(dev);
+ mutex_lock(&p->remove_mutex);
+
+ if (!p->alive) {
+ p = NULL;
+ goto out;
+ }
+
+ remove_call = kzalloc(sizeof(*remove_call), GFP_KERNEL);
+ remove_call->callback = remove_callback;
+ remove_call->context = context;
+ INIT_LIST_HEAD(&remove_call->list);
+ list_add(&remove_call->list, &p->remove_list);
+
+out:
+ mutex_unlock(&p->remove_mutex);
+ return p;
}
EXPORT_SYMBOL(p2pmem_find_compat);

/**
* p2pmem_put() - decrement a p2pmem device reference
* @p: p2pmem device to return
+ * @data: data pointer that was passed to p2pmem_find_compat
*
* Dereference and free (if last) the device's reference counter.
* It's safe to pass a NULL pointer to this function.
*/
-void p2pmem_put(struct p2pmem_dev *p)
+void p2pmem_put(struct p2pmem_dev *p, void *context)
{
- if (p)
- put_device(&p->dev);
+ struct remove_callback *remove_call;
+
+ if (!p)
+ return;
+
+ mutex_lock(&p->remove_mutex);
+
+ list_for_each_entry(remove_call, &p->remove_list, list) {
+ if (remove_call->context != context)
+ continue;
+
+ list_del(&remove_call->list);
+ kfree(remove_call);
+ break;
+ }
+
+ mutex_unlock(&p->remove_mutex);
+ put_device(&p->dev);
}
EXPORT_SYMBOL(p2pmem_put);

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index abab544..9ebcda6 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1008,7 +1008,7 @@ static void nvmet_rdma_free_queue(struct nvmet_rdma_queue *queue)
!queue->host_qid);
}
nvmet_rdma_free_rsps(queue);
- p2pmem_put(queue->p2pmem);
+ p2pmem_put(queue->p2pmem, queue);
ida_simple_remove(&nvmet_rdma_queue_ida, queue->idx);
kfree(queue);
}
@@ -1204,6 +1204,58 @@ static int nvmet_rdma_cm_accept(struct rdma_cm_id *cm_id,
return ret;
}

+static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
+{
+ bool disconnect = false;
+ unsigned long flags;
+
+ pr_debug("cm_id= %p queue->state= %d\n", queue->cm_id, queue->state);
+
+ spin_lock_irqsave(&queue->state_lock, flags);
+ switch (queue->state) {
+ case NVMET_RDMA_Q_CONNECTING:
+ case NVMET_RDMA_Q_LIVE:
+ queue->state = NVMET_RDMA_Q_DISCONNECTING;
+ case NVMET_RDMA_IN_DEVICE_REMOVAL:
+ disconnect = true;
+ break;
+ case NVMET_RDMA_Q_DISCONNECTING:
+ break;
+ }
+ spin_unlock_irqrestore(&queue->state_lock, flags);
+
+ if (disconnect) {
+ rdma_disconnect(queue->cm_id);
+ schedule_work(&queue->release_work);
+ }
+}
+
+static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
+{
+ bool disconnect = false;
+
+ mutex_lock(&nvmet_rdma_queue_mutex);
+ if (!list_empty(&queue->queue_list)) {
+ list_del_init(&queue->queue_list);
+ disconnect = true;
+ }
+ mutex_unlock(&nvmet_rdma_queue_mutex);
+
+ if (disconnect)
+ __nvmet_rdma_queue_disconnect(queue);
+}
+
+static void nvmet_rdma_p2pmem_remove(void *context)
+{
+ struct nvmet_rdma_queue *queue = context;
+
+ if (!queue->p2pmem)
+ return;
+
+ nvmet_rdma_queue_disconnect(queue);
+ flush_scheduled_work();
+}
+
/*
* If allow_p2pmem is set, we will try to use P2P memory for our
* sgl lists. This requires the p2pmem device to be compatible with
@@ -1241,7 +1293,8 @@ static void nvmet_rdma_queue_setup_p2pmem(struct nvmet_rdma_queue *queue)

dma_devs[i++] = NULL;

- queue->p2pmem = p2pmem_find_compat(dma_devs);
+ queue->p2pmem = p2pmem_find_compat(dma_devs, nvmet_rdma_p2pmem_remove,
+ queue);

if (queue->p2pmem)
pr_debug("using %s for rdma nvme target queue",
@@ -1317,47 +1370,6 @@ static void nvmet_rdma_queue_established(struct nvmet_rdma_queue *queue)
spin_unlock_irqrestore(&queue->state_lock, flags);
}

-static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
-{
- bool disconnect = false;
- unsigned long flags;
-
- pr_debug("cm_id= %p queue->state= %d\n", queue->cm_id, queue->state);
-
- spin_lock_irqsave(&queue->state_lock, flags);
- switch (queue->state) {
- case NVMET_RDMA_Q_CONNECTING:
- case NVMET_RDMA_Q_LIVE:
- queue->state = NVMET_RDMA_Q_DISCONNECTING;
- case NVMET_RDMA_IN_DEVICE_REMOVAL:
- disconnect = true;
- break;
- case NVMET_RDMA_Q_DISCONNECTING:
- break;
- }
- spin_unlock_irqrestore(&queue->state_lock, flags);
-
- if (disconnect) {
- rdma_disconnect(queue->cm_id);
- schedule_work(&queue->release_work);
- }
-}
-
-static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
-{
- bool disconnect = false;
-
- mutex_lock(&nvmet_rdma_queue_mutex);
- if (!list_empty(&queue->queue_list)) {
- list_del_init(&queue->queue_list);
- disconnect = true;
- }
- mutex_unlock(&nvmet_rdma_queue_mutex);
-
- if (disconnect)
- __nvmet_rdma_queue_disconnect(queue);
-}
-
static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id,
struct nvmet_rdma_queue *queue)
{
diff --git a/include/linux/p2pmem.h b/include/linux/p2pmem.h
index 4cd6f35..9365b02 100644
--- a/include/linux/p2pmem.h
+++ b/include/linux/p2pmem.h
@@ -22,12 +22,16 @@
struct p2pmem_dev {
struct device dev;
int id;
+ bool alive;

struct percpu_ref ref;
struct completion cmp;
struct gen_pool *pool;

struct dentry *debugfs_root;
+
+ struct mutex remove_mutex; /* protects the remove callback list */
+ struct list_head remove_list;
};

#ifdef CONFIG_P2PMEM
@@ -41,8 +45,12 @@ int p2pmem_add_pci_region(struct p2pmem_dev *p, struct pci_dev *pdev, int bar);
void *p2pmem_alloc(struct p2pmem_dev *p, size_t size);
void p2pmem_free(struct p2pmem_dev *p, void *addr, size_t size);

-struct p2pmem_dev *p2pmem_find_compat(struct device **dma_devices);
-void p2pmem_put(struct p2pmem_dev *p);
+struct p2pmem_dev *
+p2pmem_find_compat(struct device **dma_devices,
+ void (*unregister_callback)(void *context),
+ void *context);
+
+void p2pmem_put(struct p2pmem_dev *p, void *context);

#else

@@ -76,12 +84,15 @@ static inline void p2pmem_free(struct p2pmem_dev *p, void *addr, size_t size)
{
}

-static inline struct p2pmem_dev *p2pmem_find_compat(struct device **dma_devs)
+static inline struct p2pmem_dev *
+p2pmem_find_compat(struct device **dma_devices,
+ void (*unregister_callback)(void *context),
+ void *context)
{
return NULL;
}

-static inline void p2pmem_put(struct p2pmem_dev *p)
+static inline void p2pmem_put(struct p2pmem_dev *p, void *context)
{
}

--
2.1.4

Next message: Logan Gunthorpe: "[RFC 4/8] p2pmem: Add debugfs "stats" file"
Previous message: Alexey Gladkov: "Re: [PATCH RFC 0/4] proc: support multiple separate proc instances per pidnamespace"
In reply to: Logan Gunthorpe: "[RFC 0/8] Copy Offload with Peer-to-Peer PCI Memory"
Next in thread: Logan Gunthorpe: "[RFC 4/8] p2pmem: Add debugfs "stats" file"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]