From 343f5683cfa443000904c88ce2e23656375fc51c Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Wed, 10 Dec 2025 20:51:25 -0800 Subject: [PATCH] accel/amdxdna: Fix race where send ring appears full due to delayed head update The firmware sends a response and interrupts the driver before advancing the mailbox send ring head pointer. As a result, the driver may observe the response and attempt to send a new request before the firmware has updated the head pointer. In this window, the send ring still appears full, causing the driver to incorrectly fail the send operation. This race can be triggered more easily in a multithreaded environment, leading to unexpected and spurious "send ring full" failures. To address this, poll the send ring head pointer for up to 100us before returning a full-ring condition. This allows the firmware time to update the head pointer. Fixes: b87f920b9344 ("accel/amdxdna: Support hardware mailbox") Reviewed-by: Mario Limonciello (AMD) Signed-off-by: Lizhi Hou Link: https://patch.msgid.link/20251211045125.1724604-1-lizhi.hou@amd.com --- drivers/accel/amdxdna/amdxdna_mailbox.c | 27 +++++++++++++++---------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c index a60a85ce564c..469242ed8224 100644 --- a/drivers/accel/amdxdna/amdxdna_mailbox.c +++ b/drivers/accel/amdxdna/amdxdna_mailbox.c @@ -191,26 +191,34 @@ mailbox_send_msg(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg) u32 head, tail; u32 start_addr; u32 tmp_tail; + int ret; head = mailbox_get_headptr(mb_chann, CHAN_RES_X2I); tail = mb_chann->x2i_tail; - ringbuf_size = mailbox_get_ringbuf_size(mb_chann, CHAN_RES_X2I); + ringbuf_size = mailbox_get_ringbuf_size(mb_chann, CHAN_RES_X2I) - sizeof(u32); start_addr = mb_chann->res[CHAN_RES_X2I].rb_start_addr; tmp_tail = tail + mb_msg->pkg_size; - if (tail < head && tmp_tail >= head) - goto no_space; - - if (tail >= head && (tmp_tail > ringbuf_size - sizeof(u32) && - mb_msg->pkg_size >= head)) - goto no_space; - if (tail >= head && tmp_tail > ringbuf_size - sizeof(u32)) { +check_again: + if (tail >= head && tmp_tail > ringbuf_size) { write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail; writel(TOMBSTONE, write_addr); /* tombstone is set. Write from the start of the ringbuf */ tail = 0; + tmp_tail = tail + mb_msg->pkg_size; + } + + if (tail < head && tmp_tail >= head) { + ret = read_poll_timeout(mailbox_get_headptr, head, + tmp_tail < head || tail >= head, + 1, 100, false, mb_chann, CHAN_RES_X2I); + if (ret) + return ret; + + if (tail >= head) + goto check_again; } write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail; @@ -222,9 +230,6 @@ mailbox_send_msg(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg) mb_msg->pkg.header.id); return 0; - -no_space: - return -ENOSPC; } static int -- 2.47.3