@@ -831,7 +831,8 @@ static void xhci_giveback_urb_in_irq(struct xhci_hcd *xhci,
usb_amd_quirk_pll_enable();
}
}
- xhci_urb_free_priv(urb_priv);
+ if (urb_priv != (void *)urb->hcpriv_buffer)
+ xhci_urb_free_priv(urb_priv);
usb_hcd_unlink_urb_from_ep(hcd, urb);
trace_xhci_urb_giveback(urb);
usb_hcd_giveback_urb(hcd, urb, status);
@@ -1539,6 +1539,7 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
unsigned int *ep_state;
struct urb_priv *urb_priv;
int num_tds;
+ size_t private_size;
ep_index = xhci_get_endpoint_index(&urb->ep->desc);
@@ -1552,7 +1553,13 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
else
num_tds = 1;
- urb_priv = kzalloc(struct_size(urb_priv, td, num_tds), mem_flags);
+ private_size = struct_size(urb_priv, td, num_tds);
+ if (private_size <= sizeof(urb->hcpriv_buffer)) {
+ memset(urb->hcpriv_buffer, 0, sizeof(urb->hcpriv_buffer));
+ urb_priv = (struct urb_priv *)urb->hcpriv_buffer;
+ } else {
+ urb_priv = kzalloc(private_size, mem_flags);
+ }
if (!urb_priv)
return -ENOMEM;
@@ -1626,7 +1633,8 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
if (ret) {
free_priv:
- xhci_urb_free_priv(urb_priv);
+ if (urb_priv != (void *)urb->hcpriv_buffer)
+ xhci_urb_free_priv(urb_priv);
urb->hcpriv = NULL;
}
spin_unlock_irqrestore(&xhci->lock, flags);
@@ -1789,7 +1797,7 @@ static int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
return ret;
err_giveback:
- if (urb_priv)
+ if (urb_priv && urb_priv != (void *)urb->hcpriv_buffer)
xhci_urb_free_priv(urb_priv);
usb_hcd_unlink_urb_from_ep(hcd, urb);
spin_unlock_irqrestore(&xhci->lock, flags);
@@ -1602,6 +1602,7 @@ struct urb {
struct kref kref; /* reference count of the URB */
int unlinked; /* unlink error code */
void *hcpriv; /* private data for host controller */
+ u8 hcpriv_buffer[4096]; /* small buffer if private data can fit */
atomic_t use_count; /* concurrent submissions counter */
atomic_t reject; /* submissions will fail */
--- I was checking memory allocation behaviors (via memory profiling[1]), when I notice a high frequent memory allocation in xhci_urb_enqueue, about 250/s when using a USB webcam. If those alloced buffer could be kept and reused, lots of memory allocations could be avoid over time. This patch is just a POC, about 0/s memory allocation in xhci with this patch, when I use my USB devices, webcam/keyboard/mouse. A dynamic cached memory would be better: URB keep host controller's private data, if larger size buffer needed for private data, old buffer released and a larger buffer alloced. I did not observe any nagative impact with xhci's 250/s allocations when using my system, hence no measurement of how useful this changes can make to user. Just want to collect feedbacks before putting more effort. [1] https://lore.kernel.org/all/20240221194052.927623-1-surenb@google.com/ --- xhci keeps allocing new memory when enque a urb for private data, and enque frequency could be high, about 250/s when using a usb webcam, about 30/s for high pace USB keyboard/mouse usage. Using a cache/buffer for those private data could avoid lots memory allocations. Signed-off-by: David Wang <00107082@163.com> --- drivers/usb/host/xhci-ring.c | 3 ++- drivers/usb/host/xhci.c | 14 +++++++++++--- include/linux/usb.h | 1 + 3 files changed, 14 insertions(+), 4 deletions(-)