<HTML><BODY>And another note.<br>I took a look at the MMU chapter in the Cell Architecture handbook and indeed the first 15 bits in VA are treated as 0 by the hardware.<br><br>Quote:<br><br>1. High-order bits above 65 bits in the 80-bit virtual address (VA[0:14]) are not implemented. The hardware always<br> treats these bits as `0'. Software must not set these bits to any other value than `0' or the results are undefined in<br> the PPE.<br><br><br>regards<br><br><br>Воскресенье, 10 февраля 2013, 12:59 +04:00 от Phileas Fogg <phileas-fogg@mail.ru>:<br>
<blockquote style="border-left:1px solid #0857A6; margin:10px; padding:0 0 0 10px;" class="mailru-blockquote">
<div id=""><div class="js-helper js-readmsg-msg">
<style type="text/css"></style>
<div id="style_13604868320000000291" class="mr_read__body">
<base target="_self" href="https://e.mail.ru/cgi-bin/">
<div id="style_13604868320000000291_BODY"> Hi,<br><br>i found where the problem lies.<br>I also printed some values in ps3_hpte_insert with and without 64TB support, i used OpenWRT with Linux 3.7.6 for testing.<br><br>Some values without 64TB support:<br>-------------------------------------------------<br><br>[ 0.060487] RPC: Registered named UNIX socket transport module.<br>[ 0.060511] RPC: Registered udp transport module.<br>[ 0.060672] RPC: Registered tcp transport module.<br>[ 0.060873] RPC: Registered tcp NFSv4.1 backchannel transport module.<br>[ 0.061080] initcall .init_sunrpc+0x0/0xbc returned 0 after 784 usecs<br>[ 0.061280] calling .populate_rootfs+0x0/0x120 @ 1<br>[ 0.061683] ps3_hpte_insert:result=0 vpn=f09b89af50101 pa=d4e0000 ix=dfa0 v=f09b89af5001 r=6c005d4e0194 psize=0 ssize=0 lpar=6c005d4e0000<br>[ 0.061733] ps3_hpte_insert:result=0 vpn=f09b89af50102 pa=d4e1000 ix=dfb8 v=f09b89af5001 r=6c005d4e1194 psize=0 ssize=0 lpar=6c005d4e1000<br>[ 0.061895] ps3_hpte_insert:result=0 vpn=f09b89af50103 pa=d4e2000 ix=dfb0 v=f09b89af5001 r=6c005d4e2194 psize=0 ssize=0 lpar=6c005d4e2000<br><br><br>Some values with 64TB support:<br>-------------------------------------------------<br><br>[ 0.076477] calling .init_sunrpc+0x0/0xbc @ 1<br>[ 0.076992] RPC: Registered named UNIX socket transport module.<br>[ 0.077017] RPC: Registered udp transport module.<br>[ 0.077076] RPC: Registered tcp transport module.<br>[ 0.077277] RPC: Registered tcp NFSv4.1 backchannel transport module.<br>[ 0.077484] initcall .init_sunrpc+0x0/0xbc returned 0 after 784 usecs<br>[ 0.077684] calling .populate_rootfs+0x0/0x120 @ 1<br>[ 0.078126] ps3_hpte_insert:result=-17 vpn=25008684d80101 pa=d567000 ix=2ec8 v=25008684d8001 r=6c005d567194 psize=0 ssize=0 lpar=6c005d567000<br>[ 0.078164] ps3_hpte_insert:result=-17 vpn=25008684d80101 pa=d567000 ix=2ec8 v=25008684d8001 r=6c005d567194 psize=0 ssize=0 lpar=6c005d567000<br>[ 0.078287] ------------[ cut here ]------------<br>[ 0.078482] Kernel BUG at c00000000002cb3c [verbose debug info unavailable]<br>[ 0.078686] Oops: Exception in kernel mode, sig: 5 [#1]<br>[ 0.078883] SMP NR_CPUS=2 PS3<br>[ 0.079084] Modules linked in:<br>[ 0.079287] NIP: c00000000002cb3c LR: c00000000002cb38 CTR: 00000000002ffc38<br>[ 0.079489] REGS: c00000000d04f0e0 TRAP: 0700 Not tainted (3.7.6)<br>[ 0.079687] MSR: 8000000000020032 <SF,IR,DR,RI> CR: 22000022 XER: 00000000<br>[ 0.079888] SOFTE: 0<br>[ 0.080090] TASK = c00000000d049060[1] 'swapper/1' THREAD: c00000000d04c000 CPU: 1<br>GPR00: c00000000002cb38 c00000000d04f360 c0000000012ec8d0 0000000000000081 <br>GPR04: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 <br>GPR08: 0000000000000000 c00000000124ce10 0000000000000000 c00000000002bcf0 <br>GPR12: 0000000022000022 c000000007ffe280 c000000000008c94 c0000000005cba00 <br><br><br><br>And now take a look at 'v' values in both cases.<br><br>Without 64TB support: v=f09b89af5001<br>With 64TB support: v=25008684d8001<br><br>Number of leading zeros in f09b89af5001 is 16.<br>Number of leading zeros in 25008684d8001 is 14.<br><br>And that's why lv1_insert_htab_entry fails with -17 which means LV1_ILLEGAL_PARAMETER_VALUE because<br>the Hypervisor of PS3 checks 'AVPN' values for number of leading zeros and allows at least 15 bits which in case<br>of 'v' value 25008684d8001 is too small of course.<br><br>Not sure how to fix it in current Linux kernel. You guys know it better than me.<br><br>Regards<br><br><br><br><br>Понедельник, 14 января 2013, 15:37 -08:00 от Geoff Levand <<a href="sentmsg?compose&To=geoff@infradead.org">geoff@infradead.org</a>>:<br>>Hi,<br>><br>>On Fri, 2013-01-11 at 18:12 -0800, Geoff Levand wrote:<br>>> I checked these, and Michael's 407821a34fce89b4f0b031dbab5cec7d059f46bc<br>>> does indeed cause the LV1 hypervisor to panic early, and if that is<br>>> reverted, Aneesh's 048ee0993ec8360abb0b51bdf8f8721e9ed62ec4 hits a BUG.<br>><br>>Just to give an update, I did a little more work on it and found that<br>>the call to lv1_insert_htab_entry() inside ps3_hpte_insert() is<br>>failing.<br>><br>> <a href="http://git.kernel.org/?p=linux/kernel/git/geoff/ps3-linux.git;a=blob;f=arch/powerpc/platforms/ps3/htab.c;hb=HEAD#l70" target="_blank">http://git.kernel.org/?p=linux/kernel/git/geoff/ps3-linux.git;a=blob;f=arch/powerpc/platforms/ps3/htab.c;hb=HEAD#l70</a><br>><br>>The values of the variables printed all look strange compared with<br>>commit 048ee0993 reverted. I'll try do some more work on it this<br>>week.<br>><br>>-Geoff<br>><br>><br>><br>><br>><br>>_______________________________________________<br>>Linuxppc-dev mailing list<br>>Linuxppc-dev@lists.ozlabs.org<br>><a href="https://lists.ozlabs.org/listinfo/linuxppc-dev" target="_blank">https://lists.ozlabs.org/listinfo/linuxppc-dev</a><br><br>_______________________________________________<br>Linuxppc-dev mailing list<br><a href="sentmsg?compose&To=Linuxppc%2ddev@lists.ozlabs.org">Linuxppc-dev@lists.ozlabs.org</a><br><a href="https://lists.ozlabs.org/listinfo/linuxppc-dev" target="_blank">https://lists.ozlabs.org/listinfo/linuxppc-dev</a><br data-mce-bogus="1"></div>
<base target="_self" href="https://e.mail.ru/cgi-bin/">
</div>
</div>
</div>
</blockquote>
<br></BODY></HTML>