<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"> <head> <meta http-equiv="Content-Type" content="text/html; charset=us-ascii"> <meta name="Generator" content="Microsoft Word 15 (filtered medium)"> <style></style> </head> <body lang="EN-US" link="#0563C1" vlink="#954F72" style="word-wrap:break-word"> <div class="WordSection1"> Hello,<o:p></o:p> <o:p></o:p> We have run into a timing issue between threads when using the memif interface type and need some guidance.<o:p></o:p> <o:p></o:p> Our application has a DPDK based process operating (among other things) a memif server interface. The problem is exposed when this memif interface receives a memif.disconnect message from the remote client, while in the middle of an rte_eth_rx_burst() on this same memif interface. As the IRQ message handling is on its own thread as compared to the DPDK worker thread doing the rx_burst, this resulted in a crash. The backtraces for which have been shared below. How does one ensure there are guard rails in place to gracefully exit the rx-burst when a disconnect occurs? Or, how do we properly modify the code such that we defer responding to the disconnect CB after the rx-burst operation has completed?<o:p></o:p> <o:p></o:p> We are utilizing DPDK 21.11.2. I have diff’d dpdks-stable:22.11.3 in ./drivers/net/memif, but I do not see anything obvious that would address this. I did a similar diff for dpdk:23.07, but do not see anything obvious there either.<o:p></o:p> <o:p></o:p> -Mike<o:p></o:p> <o:p></o:p> (gdb) thread 1<o:p></o:p> [Switching to thread 1 (Thread 0x7f17e2813600 (LWP 470))]<o:p></o:p> #0 0x00007f17e374d225 in eth_memif_rx (queue=0x1189023b00, bufs=0x7f17e28100e8, nb_pkts=32) at ../git/drivers/net/memif/rte_eth_memif.c:338<o:p></o:p> 338 last_slot = __atomic_load_n(&ring->head, __ATOMIC_ACQUIRE);<o:p></o:p> (gdb) bt<o:p></o:p> #0 0x00007f17e374d225 in eth_memif_rx (queue=0x1189023b00, bufs=0x7f17e28100e8, nb_pkts=32) at ../git/drivers/net/memif/rte_eth_memif.c:338<o:p></o:p> #1 0x000000000047e6fb in rte_eth_rx_burst (nb_pkts=32, rx_pkts=0x7f17e28100e8, queue_id=0, port_id=<optimized out>) at /usr/include/rte_ethdev.h:5368<o:p></o:p> #2 pmd_main_loop () at ../git/swfw/api/src/swfwPmd.c:1086<o:p></o:p> #3 0x000000000047f309 in pmd_launch_one_lcore (dummy=<optimized out>) at ../git/my_process.c:1157<o:p></o:p> #4 0x00007f17f7070e7c in eal_thread_loop (arg=<optimized out>) at ../git/lib/eal/linux/eal_thread.c:146<o:p></o:p> #5 0x00007f17f4c3da72 in start_thread (arg=<optimized out>) at pthread_create.c:442<o:p></o:p> #6 0x00007f17f4cbf930 in clone3 () at ../sysdeps/unix/sysv/linux/x86_64/clone3.S:81<o:p></o:p> (gdb) l<o:p></o:p> 333 ring_size = 1 << mq->log2_ring_size;<o:p></o:p> 334 mask = ring_size - 1;<o:p></o:p> 335<o:p></o:p> 336 if (type == MEMIF_RING_C2S) {<o:p></o:p> 337 cur_slot = mq->last_head;<o:p></o:p> 338 last_slot = __atomic_load_n(&ring->head, __ATOMIC_ACQUIRE);<o:p></o:p> 339 } else {<o:p></o:p> 340 cur_slot = mq->last_tail;<o:p></o:p> 341 last_slot = __atomic_load_n(&ring->tail, __ATOMIC_ACQUIRE);<o:p></o:p> 342 }<o:p></o:p> (gdb) p ring->head<o:p></o:p> Cannot access memory at address 0x7f17d8e58006<o:p></o:p> <o:p></o:p> (gdb) thread 19<o:p></o:p> [Switching to thread 19 (Thread 0x7f17f0804600 (LWP 468))]<o:p></o:p> #0 0x00007f17f4caf97b in __GI___close (fd=494) at ../sysdeps/unix/sysv/linux/close.c:27<o:p></o:p> 27 return SYSCALL_CANCEL (close, fd);<o:p></o:p> (gdb) bt<o:p></o:p> #0 0x00007f17f4caf97b in __GI___close (fd=494) at ../sysdeps/unix/sysv/linux/close.c:27<o:p></o:p> #1 0x00007f17e374f01f in memif_free_regions (dev=dev@entry=0x7f17f727f000 <rte_eth_devices+99072>) at ../git/drivers/net/memif/rte_eth_memif.c:882<o:p></o:p> #2 0x00007f17e37475d0 in memif_disconnect (dev=0x7f17f727f000 <rte_eth_devices+99072>) at ../git/drivers/net/memif/memif_socket.c:623<o:p></o:p> #3 0x00007f17f7091bd2 in eal_intr_process_interrupts (nfds=<optimized out>, events=<optimized out>) at ../git/lib/eal/linux/eal_interrupts.c:1026<o:p></o:p> #4 eal_intr_handle_interrupts (totalfds=<optimized out>, pfd=20) at ../git/lib/eal/linux/eal_interrupts.c:1100<o:p></o:p> #5 eal_intr_thread_main (arg=<optimized out>) at ../git/lib/eal/linux/eal_interrupts.c:1172<o:p></o:p> #6 0x00007f17f4c3da72 in start_thread (arg=<optimized out>) at pthread_create.c:442<o:p></o:p> #7 0x00007f17f4cbf930 in clone3 () at ../sysdeps/unix/sysv/linux/x86_64/clone3.S:81<o:p></o:p> <o:p> </o:p> </div> </body> </html>