summaryrefslogtreecommitdiff
path: root/drivers/uio/uio_hv_generic.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/uio/uio_hv_generic.c')
-rw-r--r--drivers/uio/uio_hv_generic.c164
1 files changed, 91 insertions, 73 deletions
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index 3976360d0096..f19efad4d6f8 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -65,6 +65,16 @@ struct hv_uio_private_data {
char send_name[32];
};
+static void set_event(struct vmbus_channel *channel, s32 irq_state)
+{
+ channel->inbound.ring_buffer->interrupt_mask = !irq_state;
+ if (!channel->offermsg.monitor_allocated && irq_state) {
+ /* MB is needed for host to see the interrupt mask first */
+ virt_mb();
+ vmbus_set_event(channel);
+ }
+}
+
/*
* This is the irqcontrol callback to be registered to uio_info.
* It can be used to disable/enable interrupt from user space processes.
@@ -79,12 +89,15 @@ hv_uio_irqcontrol(struct uio_info *info, s32 irq_state)
{
struct hv_uio_private_data *pdata = info->priv;
struct hv_device *dev = pdata->device;
+ struct vmbus_channel *primary, *sc;
- dev->channel->inbound.ring_buffer->interrupt_mask = !irq_state;
- virt_mb();
+ primary = dev->channel;
+ set_event(primary, irq_state);
- if (!dev->channel->offermsg.monitor_allocated && irq_state)
- vmbus_setevent(dev->channel);
+ mutex_lock(&vmbus_connection.channel_mutex);
+ list_for_each_entry(sc, &primary->sc_list, sc_list)
+ set_event(sc, irq_state);
+ mutex_unlock(&vmbus_connection.channel_mutex);
return 0;
}
@@ -95,12 +108,19 @@ hv_uio_irqcontrol(struct uio_info *info, s32 irq_state)
static void hv_uio_channel_cb(void *context)
{
struct vmbus_channel *chan = context;
- struct hv_device *hv_dev = chan->device_obj;
- struct hv_uio_private_data *pdata = hv_get_drvdata(hv_dev);
+ struct hv_device *hv_dev;
+ struct hv_uio_private_data *pdata;
chan->inbound.ring_buffer->interrupt_mask = 1;
virt_mb();
+ /*
+ * The callback may come from a subchannel, in which case look
+ * for the hv device in the primary channel
+ */
+ hv_dev = chan->primary_channel ?
+ chan->primary_channel->device_obj : chan->device_obj;
+ pdata = hv_get_drvdata(hv_dev);
uio_event_notify(&pdata->info);
}
@@ -131,15 +151,12 @@ static void hv_uio_rescind(struct vmbus_channel *channel)
vmbus_device_unregister(channel->device_obj);
}
-/* Sysfs API to allow mmap of the ring buffers
+/* Function used for mmap of ring buffer sysfs interface.
* The ring buffer is allocated as contiguous memory by vmbus_open
*/
-static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
- const struct bin_attribute *attr,
- struct vm_area_struct *vma)
+static int
+hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma)
{
- struct vmbus_channel *channel
- = container_of(kobj, struct vmbus_channel, kobj);
void *ring_buffer = page_address(channel->ringbuffer_page);
if (channel->state != CHANNEL_OPENED_STATE)
@@ -149,15 +166,6 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
channel->ringbuffer_pagecount << PAGE_SHIFT);
}
-static const struct bin_attribute ring_buffer_bin_attr = {
- .attr = {
- .name = "ring",
- .mode = 0600,
- },
- .size = 2 * SZ_2M,
- .mmap = hv_uio_ring_mmap,
-};
-
/* Callback from VMBUS subsystem when new channel created. */
static void
hv_uio_new_channel(struct vmbus_channel *new_sc)
@@ -178,8 +186,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc)
/* Disable interrupts on sub channel */
new_sc->inbound.ring_buffer->interrupt_mask = 1;
set_channel_read_mode(new_sc, HV_CALL_ISR);
-
- ret = sysfs_create_bin_file(&new_sc->kobj, &ring_buffer_bin_attr);
+ ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap);
if (ret) {
dev_err(device, "sysfs create ring bin file failed; %d\n", ret);
vmbus_close(new_sc);
@@ -256,6 +263,9 @@ hv_uio_probe(struct hv_device *dev,
if (!ring_size)
ring_size = SZ_2M;
+ /* Adjust ring size if necessary to have it page aligned */
+ ring_size = VMBUS_RING_SIZE(ring_size);
+
pdata = devm_kzalloc(&dev->device, sizeof(*pdata), GFP_KERNEL);
if (!pdata)
return -ENOMEM;
@@ -287,60 +297,60 @@ hv_uio_probe(struct hv_device *dev,
pdata->info.mem[INT_PAGE_MAP].name = "int_page";
pdata->info.mem[INT_PAGE_MAP].addr
= (uintptr_t)vmbus_connection.int_page;
- pdata->info.mem[INT_PAGE_MAP].size = PAGE_SIZE;
+ pdata->info.mem[INT_PAGE_MAP].size = HV_HYP_PAGE_SIZE;
pdata->info.mem[INT_PAGE_MAP].memtype = UIO_MEM_LOGICAL;
pdata->info.mem[MON_PAGE_MAP].name = "monitor_page";
pdata->info.mem[MON_PAGE_MAP].addr
= (uintptr_t)vmbus_connection.monitor_pages[1];
- pdata->info.mem[MON_PAGE_MAP].size = PAGE_SIZE;
+ pdata->info.mem[MON_PAGE_MAP].size = HV_HYP_PAGE_SIZE;
pdata->info.mem[MON_PAGE_MAP].memtype = UIO_MEM_LOGICAL;
- pdata->recv_buf = vzalloc(RECV_BUFFER_SIZE);
- if (pdata->recv_buf == NULL) {
- ret = -ENOMEM;
- goto fail_free_ring;
+ if (channel->device_id == HV_NIC) {
+ pdata->recv_buf = vzalloc(RECV_BUFFER_SIZE);
+ if (!pdata->recv_buf) {
+ ret = -ENOMEM;
+ goto fail_free_ring;
+ }
+
+ ret = vmbus_establish_gpadl(channel, pdata->recv_buf,
+ RECV_BUFFER_SIZE, &pdata->recv_gpadl);
+ if (ret) {
+ if (!pdata->recv_gpadl.decrypted)
+ vfree(pdata->recv_buf);
+ goto fail_close;
+ }
+
+ /* put Global Physical Address Label in name */
+ snprintf(pdata->recv_name, sizeof(pdata->recv_name),
+ "recv:%u", pdata->recv_gpadl.gpadl_handle);
+ pdata->info.mem[RECV_BUF_MAP].name = pdata->recv_name;
+ pdata->info.mem[RECV_BUF_MAP].addr = (uintptr_t)pdata->recv_buf;
+ pdata->info.mem[RECV_BUF_MAP].size = RECV_BUFFER_SIZE;
+ pdata->info.mem[RECV_BUF_MAP].memtype = UIO_MEM_VIRTUAL;
+
+ pdata->send_buf = vzalloc(SEND_BUFFER_SIZE);
+ if (!pdata->send_buf) {
+ ret = -ENOMEM;
+ goto fail_close;
+ }
+
+ ret = vmbus_establish_gpadl(channel, pdata->send_buf,
+ SEND_BUFFER_SIZE, &pdata->send_gpadl);
+ if (ret) {
+ if (!pdata->send_gpadl.decrypted)
+ vfree(pdata->send_buf);
+ goto fail_close;
+ }
+
+ snprintf(pdata->send_name, sizeof(pdata->send_name),
+ "send:%u", pdata->send_gpadl.gpadl_handle);
+ pdata->info.mem[SEND_BUF_MAP].name = pdata->send_name;
+ pdata->info.mem[SEND_BUF_MAP].addr = (uintptr_t)pdata->send_buf;
+ pdata->info.mem[SEND_BUF_MAP].size = SEND_BUFFER_SIZE;
+ pdata->info.mem[SEND_BUF_MAP].memtype = UIO_MEM_VIRTUAL;
}
- ret = vmbus_establish_gpadl(channel, pdata->recv_buf,
- RECV_BUFFER_SIZE, &pdata->recv_gpadl);
- if (ret) {
- if (!pdata->recv_gpadl.decrypted)
- vfree(pdata->recv_buf);
- goto fail_close;
- }
-
- /* put Global Physical Address Label in name */
- snprintf(pdata->recv_name, sizeof(pdata->recv_name),
- "recv:%u", pdata->recv_gpadl.gpadl_handle);
- pdata->info.mem[RECV_BUF_MAP].name = pdata->recv_name;
- pdata->info.mem[RECV_BUF_MAP].addr
- = (uintptr_t)pdata->recv_buf;
- pdata->info.mem[RECV_BUF_MAP].size = RECV_BUFFER_SIZE;
- pdata->info.mem[RECV_BUF_MAP].memtype = UIO_MEM_VIRTUAL;
-
- pdata->send_buf = vzalloc(SEND_BUFFER_SIZE);
- if (pdata->send_buf == NULL) {
- ret = -ENOMEM;
- goto fail_close;
- }
-
- ret = vmbus_establish_gpadl(channel, pdata->send_buf,
- SEND_BUFFER_SIZE, &pdata->send_gpadl);
- if (ret) {
- if (!pdata->send_gpadl.decrypted)
- vfree(pdata->send_buf);
- goto fail_close;
- }
-
- snprintf(pdata->send_name, sizeof(pdata->send_name),
- "send:%u", pdata->send_gpadl.gpadl_handle);
- pdata->info.mem[SEND_BUF_MAP].name = pdata->send_name;
- pdata->info.mem[SEND_BUF_MAP].addr
- = (uintptr_t)pdata->send_buf;
- pdata->info.mem[SEND_BUF_MAP].size = SEND_BUFFER_SIZE;
- pdata->info.mem[SEND_BUF_MAP].memtype = UIO_MEM_VIRTUAL;
-
pdata->info.priv = pdata;
pdata->device = dev;
@@ -350,10 +360,18 @@ hv_uio_probe(struct hv_device *dev,
goto fail_close;
}
- ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr);
- if (ret)
- dev_notice(&dev->device,
- "sysfs create ring bin file failed; %d\n", ret);
+ /*
+ * This internally calls sysfs_update_group, which returns a non-zero value if it executes
+ * before sysfs_create_group. This is expected as the 'ring' will be created later in
+ * vmbus_device_register() -> vmbus_add_channel_kobj(). Thus, no need to check the return
+ * value and print warning.
+ *
+ * Creating/exposing sysfs in driver probe is not encouraged as it can lead to race
+ * conditions with userspace. For backward compatibility, "ring" sysfs could not be removed
+ * or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify
+ * APIs to make sure that ring is created.
+ */
+ hv_create_ring_sysfs(channel, hv_uio_ring_mmap);
hv_set_drvdata(dev, pdata);
@@ -375,7 +393,7 @@ hv_uio_remove(struct hv_device *dev)
if (!pdata)
return;
- sysfs_remove_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr);
+ hv_remove_ring_sysfs(dev->channel);
uio_unregister_device(&pdata->info);
hv_uio_cleanup(dev, pdata);