@@ -1,4 +1,3 @@
-- Replace idr with xa
- Add import and export BO support
- Add debugfs support
- Add debug BO support
@@ -90,11 +90,11 @@ void aie2_restart_ctx(struct amdxdna_client *client)
{
struct amdxdna_dev *xdna = client->xdna;
struct amdxdna_hwctx *hwctx;
- int next = 0;
+ unsigned long hwctx_id;
drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
mutex_lock(&client->hwctx_lock);
- idr_for_each_entry_continue(&client->hwctx_idr, hwctx, next) {
+ amdxdna_for_each_hwctx(client, hwctx_id, hwctx) {
if (hwctx->status != HWCTX_STAT_STOP)
continue;
@@ -315,10 +315,10 @@ int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf,
struct amdxdna_dev *xdna = ndev->xdna;
struct amdxdna_client *client;
struct amdxdna_hwctx *hwctx;
+ unsigned long hwctx_id;
dma_addr_t dma_addr;
u32 aie_bitmap = 0;
u8 *buff_addr;
- int next = 0;
int ret, idx;
buff_addr = dma_alloc_noncoherent(xdna->ddev.dev, size, &dma_addr,
@@ -329,7 +329,7 @@ int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf,
/* Go through each hardware context and mark the AIE columns that are active */
list_for_each_entry(client, &xdna->client_list, node) {
idx = srcu_read_lock(&client->hwctx_srcu);
- idr_for_each_entry_continue(&client->hwctx_idr, hwctx, next)
+ amdxdna_for_each_hwctx(client, hwctx_id, hwctx)
aie_bitmap |= amdxdna_hwctx_col_map(hwctx);
srcu_read_unlock(&client->hwctx_srcu, idx);
}
@@ -674,11 +674,11 @@ static int aie2_get_hwctx_status(struct amdxdna_client *client,
struct amdxdna_drm_query_hwctx *tmp;
struct amdxdna_client *tmp_client;
struct amdxdna_hwctx *hwctx;
+ unsigned long hwctx_id;
bool overflow = false;
u32 req_bytes = 0;
u32 hw_i = 0;
int ret = 0;
- int next;
int idx;
drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
@@ -690,8 +690,7 @@ static int aie2_get_hwctx_status(struct amdxdna_client *client,
buf = u64_to_user_ptr(args->buffer);
list_for_each_entry(tmp_client, &xdna->client_list, node) {
idx = srcu_read_lock(&tmp_client->hwctx_srcu);
- next = 0;
- idr_for_each_entry_continue(&tmp_client->hwctx_idr, hwctx, next) {
+ amdxdna_for_each_hwctx(tmp_client, hwctx_id, hwctx) {
req_bytes += sizeof(*tmp);
if (args->buffer_size < req_bytes) {
/* Continue iterating to get the required size */
@@ -63,11 +63,11 @@ void amdxdna_hwctx_suspend(struct amdxdna_client *client)
{
struct amdxdna_dev *xdna = client->xdna;
struct amdxdna_hwctx *hwctx;
- int next = 0;
+ unsigned long hwctx_id;
drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
mutex_lock(&client->hwctx_lock);
- idr_for_each_entry_continue(&client->hwctx_idr, hwctx, next)
+ amdxdna_for_each_hwctx(client, hwctx_id, hwctx)
xdna->dev_info->ops->hwctx_suspend(hwctx);
mutex_unlock(&client->hwctx_lock);
}
@@ -76,11 +76,11 @@ void amdxdna_hwctx_resume(struct amdxdna_client *client)
{
struct amdxdna_dev *xdna = client->xdna;
struct amdxdna_hwctx *hwctx;
- int next = 0;
+ unsigned long hwctx_id;
drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
mutex_lock(&client->hwctx_lock);
- idr_for_each_entry_continue(&client->hwctx_idr, hwctx, next)
+ amdxdna_for_each_hwctx(client, hwctx_id, hwctx)
xdna->dev_info->ops->hwctx_resume(hwctx);
mutex_unlock(&client->hwctx_lock);
}
@@ -149,13 +149,13 @@ int amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo)
void amdxdna_hwctx_remove_all(struct amdxdna_client *client)
{
struct amdxdna_hwctx *hwctx;
- int next = 0;
+ unsigned long hwctx_id;
mutex_lock(&client->hwctx_lock);
- idr_for_each_entry_continue(&client->hwctx_idr, hwctx, next) {
+ amdxdna_for_each_hwctx(client, hwctx_id, hwctx) {
XDNA_DBG(client->xdna, "PID %d close HW context %d",
client->pid, hwctx->id);
- idr_remove(&client->hwctx_idr, hwctx->id);
+ xa_erase(&client->hwctx_xa, hwctx->id);
mutex_unlock(&client->hwctx_lock);
amdxdna_hwctx_destroy_rcu(hwctx, &client->hwctx_srcu);
mutex_lock(&client->hwctx_lock);
@@ -194,15 +194,13 @@ int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct dr
hwctx->num_tiles = args->num_tiles;
hwctx->mem_size = args->mem_size;
hwctx->max_opc = args->max_opc;
- mutex_lock(&client->hwctx_lock);
- ret = idr_alloc_cyclic(&client->hwctx_idr, hwctx, 0, MAX_HWCTX_ID, GFP_KERNEL);
+ ret = xa_alloc_cyclic(&client->hwctx_xa, &hwctx->id, hwctx,
+ XA_LIMIT(AMDXDNA_INVALID_CTX_HANDLE + 1, MAX_HWCTX_ID),
+ &client->next_hwctxid, GFP_KERNEL);
if (ret < 0) {
- mutex_unlock(&client->hwctx_lock);
XDNA_ERR(xdna, "Allocate hwctx ID failed, ret %d", ret);
goto free_hwctx;
}
- hwctx->id = ret;
- mutex_unlock(&client->hwctx_lock);
hwctx->name = kasprintf(GFP_KERNEL, "hwctx.%d.%d", client->pid, hwctx->id);
if (!hwctx->name) {
@@ -228,9 +226,7 @@ int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct dr
free_name:
kfree(hwctx->name);
rm_id:
- mutex_lock(&client->hwctx_lock);
- idr_remove(&client->hwctx_idr, hwctx->id);
- mutex_unlock(&client->hwctx_lock);
+ xa_erase(&client->hwctx_xa, hwctx->id);
free_hwctx:
kfree(hwctx);
exit:
@@ -249,24 +245,18 @@ int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct d
if (!drm_dev_enter(dev, &idx))
return -ENODEV;
- /*
- * Use hwctx_lock to achieve exclusion with other hwctx writers,
- * SRCU to synchronize with exec/wait command ioctls.
- *
- * The pushed jobs are handled by DRM scheduler during destroy.
- */
- mutex_lock(&client->hwctx_lock);
- hwctx = idr_find(&client->hwctx_idr, args->handle);
+ hwctx = xa_erase(&client->hwctx_xa, args->handle);
if (!hwctx) {
- mutex_unlock(&client->hwctx_lock);
ret = -EINVAL;
XDNA_DBG(xdna, "PID %d HW context %d not exist",
client->pid, args->handle);
goto out;
}
- idr_remove(&client->hwctx_idr, hwctx->id);
- mutex_unlock(&client->hwctx_lock);
+ /*
+ * The pushed jobs are handled by DRM scheduler during destroy.
+ * SRCU to synchronize with exec command ioctls.
+ */
amdxdna_hwctx_destroy_rcu(hwctx, &client->hwctx_srcu);
XDNA_DBG(xdna, "PID %d destroyed HW context %d", client->pid, args->handle);
@@ -324,7 +314,7 @@ int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct dr
mutex_lock(&xdna->dev_lock);
idx = srcu_read_lock(&client->hwctx_srcu);
- hwctx = idr_find(&client->hwctx_idr, args->handle);
+ hwctx = xa_load(&client->hwctx_xa, args->handle);
if (!hwctx) {
XDNA_DBG(xdna, "PID %d failed to get hwctx %d", client->pid, args->handle);
ret = -EINVAL;
@@ -436,7 +426,7 @@ int amdxdna_cmd_submit(struct amdxdna_client *client,
}
idx = srcu_read_lock(&client->hwctx_srcu);
- hwctx = idr_find(&client->hwctx_idr, hwctx_hdl);
+ hwctx = xa_load(&client->hwctx_xa, hwctx_hdl);
if (!hwctx) {
XDNA_DBG(xdna, "PID %d failed to get hwctx %d",
client->pid, hwctx_hdl);
@@ -54,8 +54,8 @@ struct mailbox_channel {
struct xdna_mailbox_chann_res res[CHAN_RES_NUM];
int msix_irq;
u32 iohub_int_addr;
- struct idr chan_idr;
- spinlock_t chan_idr_lock; /* protect chan_idr */
+ struct xarray chan_xa;
+ u32 next_msgid;
u32 x2i_tail;
/* Received msg related fields */
@@ -164,19 +164,17 @@ static inline int mailbox_validate_msgid(int msg_id)
static int mailbox_acquire_msgid(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg)
{
- unsigned long flags;
- int msg_id;
+ u32 msg_id;
+ int ret;
- spin_lock_irqsave(&mb_chann->chan_idr_lock, flags);
- msg_id = idr_alloc_cyclic(&mb_chann->chan_idr, mb_msg, 0,
- MAX_MSG_ID_ENTRIES, GFP_NOWAIT);
- spin_unlock_irqrestore(&mb_chann->chan_idr_lock, flags);
- if (msg_id < 0)
- return msg_id;
+ ret = xa_alloc_cyclic_irq(&mb_chann->chan_xa, &msg_id, mb_msg,
+ XA_LIMIT(0, MAX_MSG_ID_ENTRIES - 1),
+ &mb_chann->next_msgid, GFP_NOWAIT);
+ if (ret < 0)
+ return ret;
/*
- * The IDR becomes less efficient when dealing with larger IDs.
- * Thus, add MAGIC_VAL to the higher bits.
+ * Add MAGIC_VAL to the higher bits.
*/
msg_id |= MAGIC_VAL;
return msg_id;
@@ -184,25 +182,17 @@ static int mailbox_acquire_msgid(struct mailbox_channel *mb_chann, struct mailbo
static void mailbox_release_msgid(struct mailbox_channel *mb_chann, int msg_id)
{
- unsigned long flags;
-
msg_id &= ~MAGIC_VAL_MASK;
- spin_lock_irqsave(&mb_chann->chan_idr_lock, flags);
- idr_remove(&mb_chann->chan_idr, msg_id);
- spin_unlock_irqrestore(&mb_chann->chan_idr_lock, flags);
+ xa_erase_irq(&mb_chann->chan_xa, msg_id);
}
-static int mailbox_release_msg(int id, void *p, void *data)
+static void mailbox_release_msg(struct mailbox_channel *mb_chann,
+ struct mailbox_msg *mb_msg)
{
- struct mailbox_channel *mb_chann = data;
- struct mailbox_msg *mb_msg = p;
-
MB_DBG(mb_chann, "msg_id 0x%x msg opcode 0x%x",
mb_msg->pkg.header.id, mb_msg->pkg.header.opcode);
mb_msg->notify_cb(mb_msg->handle, NULL, 0);
kfree(mb_msg);
-
- return 0;
}
static int
@@ -254,7 +244,6 @@ mailbox_get_resp(struct mailbox_channel *mb_chann, struct xdna_msg_header *heade
void *data)
{
struct mailbox_msg *mb_msg;
- unsigned long flags;
int msg_id;
int ret;
@@ -265,15 +254,11 @@ mailbox_get_resp(struct mailbox_channel *mb_chann, struct xdna_msg_header *heade
}
msg_id &= ~MAGIC_VAL_MASK;
- spin_lock_irqsave(&mb_chann->chan_idr_lock, flags);
- mb_msg = idr_find(&mb_chann->chan_idr, msg_id);
+ mb_msg = xa_erase_irq(&mb_chann->chan_xa, msg_id);
if (!mb_msg) {
MB_ERR(mb_chann, "Cannot find msg 0x%x", msg_id);
- spin_unlock_irqrestore(&mb_chann->chan_idr_lock, flags);
return -EINVAL;
}
- idr_remove(&mb_chann->chan_idr, msg_id);
- spin_unlock_irqrestore(&mb_chann->chan_idr_lock, flags);
MB_DBG(mb_chann, "opcode 0x%x size %d id 0x%x",
header->opcode, header->total_size, header->id);
@@ -497,8 +482,7 @@ xdna_mailbox_create_channel(struct mailbox *mb,
memcpy(&mb_chann->res[CHAN_RES_X2I], x2i, sizeof(*x2i));
memcpy(&mb_chann->res[CHAN_RES_I2X], i2x, sizeof(*i2x));
- spin_lock_init(&mb_chann->chan_idr_lock);
- idr_init(&mb_chann->chan_idr);
+ xa_init_flags(&mb_chann->chan_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
mb_chann->x2i_tail = mailbox_get_tailptr(mb_chann, CHAN_RES_X2I);
mb_chann->i2x_head = mailbox_get_headptr(mb_chann, CHAN_RES_I2X);
@@ -530,13 +514,18 @@ xdna_mailbox_create_channel(struct mailbox *mb,
int xdna_mailbox_destroy_channel(struct mailbox_channel *mb_chann)
{
+ struct mailbox_msg *mb_msg;
+ unsigned long msg_id;
+
MB_DBG(mb_chann, "IRQ disabled and RX work cancelled");
free_irq(mb_chann->msix_irq, mb_chann);
destroy_workqueue(mb_chann->work_q);
/* We can clean up and release resources */
- idr_for_each(&mb_chann->chan_idr, mailbox_release_msg, mb_chann);
- idr_destroy(&mb_chann->chan_idr);
+ xa_for_each(&mb_chann->chan_xa, msg_id, mb_msg)
+ mailbox_release_msg(mb_chann, mb_msg);
+
+ xa_destroy(&mb_chann->chan_xa);
MB_DBG(mb_chann, "Mailbox channel destroyed, irq: %d", mb_chann->msix_irq);
kfree(mb_chann);
@@ -77,7 +77,7 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp)
}
mutex_init(&client->hwctx_lock);
init_srcu_struct(&client->hwctx_srcu);
- idr_init_base(&client->hwctx_idr, AMDXDNA_INVALID_CTX_HANDLE + 1);
+ xa_init_flags(&client->hwctx_xa, XA_FLAGS_ALLOC);
mutex_init(&client->mm_lock);
mutex_lock(&xdna->dev_lock);
@@ -108,7 +108,7 @@ static void amdxdna_drm_close(struct drm_device *ddev, struct drm_file *filp)
XDNA_DBG(xdna, "closing pid %d", client->pid);
- idr_destroy(&client->hwctx_idr);
+ xa_destroy(&client->hwctx_xa);
cleanup_srcu_struct(&client->hwctx_srcu);
mutex_destroy(&client->hwctx_lock);
mutex_destroy(&client->mm_lock);
@@ -100,7 +100,8 @@ struct amdxdna_client {
struct mutex hwctx_lock; /* protect hwctx */
/* do NOT wait this srcu when hwctx_lock is held */
struct srcu_struct hwctx_srcu;
- struct idr hwctx_idr;
+ struct xarray hwctx_xa;
+ u32 next_hwctxid;
struct amdxdna_dev *xdna;
struct drm_file *filp;
@@ -111,6 +112,9 @@ struct amdxdna_client {
int pasid;
};
+#define amdxdna_for_each_hwctx(client, hwctx_id, entry) \
+ xa_for_each(&(client)->hwctx_xa, hwctx_id, entry)
+
/* Add device info below */
extern const struct amdxdna_dev_info dev_npu1_info;
extern const struct amdxdna_dev_info dev_npu2_info;
Switch mailbox message id and hardware context id management over from the idr api to the xarray api. Signed-off-by: Lizhi Hou <lizhi.hou@amd.com> --- drivers/accel/amdxdna/TODO | 1 - drivers/accel/amdxdna/aie2_ctx.c | 4 +- drivers/accel/amdxdna/aie2_message.c | 4 +- drivers/accel/amdxdna/aie2_pci.c | 5 +-- drivers/accel/amdxdna/amdxdna_ctx.c | 46 ++++++++------------- drivers/accel/amdxdna/amdxdna_mailbox.c | 55 ++++++++++--------------- drivers/accel/amdxdna/amdxdna_pci_drv.c | 4 +- drivers/accel/amdxdna/amdxdna_pci_drv.h | 6 ++- 8 files changed, 53 insertions(+), 72 deletions(-)