<html> <head> <base href="https://bugs.freedesktop.org/" /> </head> <body> <div> <a class="bz_bug_link bz_status_NEW " title="NEW --- - [NV84] Repeated system crashes under graphics load, E[PFIFO] DMA_PUSHER and lots of E[PGRAPH]" href="https://bugs.freedesktop.org/show_bug.cgi?id=70390#c6">Comment # 6</a> on <a class="bz_bug_link bz_status_NEW " title="NEW --- - [NV84] Repeated system crashes under graphics load, E[PFIFO] DMA_PUSHER and lots of E[PGRAPH]" href="https://bugs.freedesktop.org/show_bug.cgi?id=70390">bug 70390</a> from <a class="email" href="mailto:imirkin@alum.mit.edu" title="Ilia Mirkin <imirkin@alum.mit.edu>"> Ilia Mirkin</a> <pre>The commonality here is that in all cases you get [22145.017855] nouveau E[ PFIFO][0000:01:00.0] DMA_PUSHER - ch 4 [stellarium[17059]] get 0x0020049408 put 0x0020053fcc ib_get 0x00000349 ib_put 0x00000352 state 0x80007641 (err: INVALID_CMD) push 0x00406040 But 0x00406040 is a perfectly valid command, ever since the Riva TNT chips. It should decode as method = 0x10 subchan = 3 count = 0x10 This makes sense. These 4 methods deal with semaphore manipulation. <reg32 offset="0x10" name="SEMAPHORE_ADDRESS_HIGH" variants="NV84-"/> <reg32 offset="0x14" name="SEMAPHORE_ADDRESS_LOW" variants="NV84-"/> <reg32 offset="0x18" name="SEMAPHORE_SEQUENCE" variants="NV84-"/> <reg32 offset="0x1c" name="SEMAPHORE_TRIGGER" variants="NV84-"> which happens a fair bit for CPU vs GPU syncs.</pre> </div> <hr> You are receiving this mail because: <ul> <li>You are the assignee for the bug.</li> </ul> </body> </html>