Re: glxsb?
On 2008-05-23, Adam Jacob Muller [EMAIL PROTECTED] wrote: I was under the impression that kern.usercrypto did this. it seems to have a negligible affect on my net5501 I do have a glxsb [EMAIL PROTECTED] (set -ex;sysctl kern.usercrypto=1;openssl speed -evp aes-256-cbc;sysctl kern.usercrypto=0;openssl speed -evp aes-256-cbc) glxsb(4) accelerates only AES128. You also need to use the -elapsed flag to openssl speed.
glxsb?
On Tue, May 20, 2008 at 4:34 PM, Paul de Weerd [EMAIL PROTECTED] wrote: glxsb (4/i386) - Geode LX Security Block crypto accelerator In other words, there's onboard crypto support in these machines that is supported in OpenBSD. You may not need a separate accelerator. Thanks for the reminder, I forgot the (slightly more expensive) Net5501 had this chip :) Does this just automagically accelerate anything using entropy or AES? Is there any way to temporarily disable acceleration to run benchmarks? Thanks, Kevin
Re: glxsb?
On May 22, 2008, at 9:27 PM, K K wrote: On Tue, May 20, 2008 at 4:34 PM, Paul de Weerd [EMAIL PROTECTED] wrote: glxsb (4/i386) - Geode LX Security Block crypto accelerator In other words, there's onboard crypto support in these machines that is supported in OpenBSD. You may not need a separate accelerator. Thanks for the reminder, I forgot the (slightly more expensive) Net5501 had this chip :) Does this just automagically accelerate anything using entropy or AES? Is there any way to temporarily disable acceleration to run benchmarks? Thanks, Kevin I was under the impression that kern.usercrypto did this. it seems to have a negligible affect on my net5501 I do have a glxsb -=[~]=- -=[Thu May 22]=- -=[21:58:20]=- [EMAIL PROTECTED] (set -ex;sysctl kern.usercrypto=1;openssl speed -evp aes-256-cbc;sysctl kern.usercrypto=0;openssl speed -evp aes-256-cbc) + sysctl kern.usercrypto=1 kern.usercrypto: 1 - 1 + openssl speed -evp aes-256-cbc To get the most accurate results, try to run this program when this computer is idle. Doing aes-256-cbc for 3s on 16 size blocks: 721327 aes-256-cbc's in 2.71s Doing aes-256-cbc for 3s on 64 size blocks: 216391 aes-256-cbc's in 2.91s Doing aes-256-cbc for 3s on 256 size blocks: 54838 aes-256-cbc's in 2.85s Doing aes-256-cbc for 3s on 1024 size blocks: 13739 aes-256-cbc's in 2.86s Doing aes-256-cbc for 3s on 8192 size blocks: 1722 aes-256-cbc's in 2.94s OpenSSL 0.9.7j 04 May 2006 built on: date not available options:bn(64,32) md2(int) rc4(idx,int) des(ptr,risc1,16,long) aes(partial) blowfish(idx) compiler: information not available available timing options: USE_TOD HZ=100 [sysconf value] timing function used: getrusage The 'numbers' are in 1000s of bytes per second processed. type 16 bytes 64 bytes256 bytes 1024 bytes 8192 bytes aes-256-cbc 4257.29k 4765.26k 4923.10k 4920.21k 4802.25k + sysctl kern.usercrypto=0 kern.usercrypto: 1 - 0 + openssl speed -evp aes-256-cbc To get the most accurate results, try to run this program when this computer is idle. Doing aes-256-cbc for 3s on 16 size blocks: 758660 aes-256-cbc's in 2.84s Doing aes-256-cbc for 3s on 64 size blocks: 212083 aes-256-cbc's in 2.84s Doing aes-256-cbc for 3s on 256 size blocks: 55383 aes-256-cbc's in 2.87s Doing aes-256-cbc for 3s on 1024 size blocks: 13931 aes-256-cbc's in 2.88s Doing aes-256-cbc for 3s on 8192 size blocks: 1749 aes-256-cbc's in 2.88s OpenSSL 0.9.7j 04 May 2006 built on: date not available options:bn(64,32) md2(int) rc4(idx,int) des(ptr,risc1,16,long) aes(partial) blowfish(idx) compiler: information not available available timing options: USE_TOD HZ=100 [sysconf value] timing function used: getrusage The 'numbers' are in 1000s of bytes per second processed. type 16 bytes 64 bytes256 bytes 1024 bytes 8192 bytes aes-256-cbc 4268.50k 4773.03k 4944.93k 4961.86k 4970.08k -=[~]=- -=[Thu May 22]=- -=[21:59:29]=- [EMAIL PROTECTED] grep glxsb /var/run/dmesg.boot glxsb0 at pci0 dev 1 function 2 AMD Geode LX Crypto rev 0x00: RNG AES
Re: glxsb crypto crash
For the archives, the following two commits have fixed this: -- CVSROOT:/cvs Module name:src Changes by: [EMAIL PROTECTED] 2007/11/14 12:10:44 Modified files: sys/arch/i386/i386: via.c sys/arch/i386/pci: glxsb.c Log message: do not process requests linked to unused sessions. (crypto_freesession might happen between enqueuing a crypto request and scheduling of the crypto thread); ok hshoexer -- CVSROOT:/cvs Module name:src Changes by: [EMAIL PROTECTED] 2007/11/14 12:12:37 Modified files: sys/crypto : crypto.c Log message: do not call crypto_done() on errors, since the drivers already do this. otherwise we call the callback twice; fixes panics on crypto errors as seen on reboot; ok hshoexer -- Regards, Mitja -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Mitja Muenih Sent: Saturday, November 10, 2007 10:56 PM To: misc@openbsd.org Subject: glxsb crypto crash Not my day, obviously On a net5501 machine that I just upgraded to 4.2 I experienced a sudden reboot and found this in dmesg: uvm_fault(0xd078d120, 0x0, 0, 1) - e fatal page fault (6) in supervisor mode trap type 6 code 0 eip d03d4fab cs 8 eflags 10296 cr2 4 cpl 90 panic: trap type 6, code=0, pc=d03d4fab Starting stack trace... panic(0,d6a0215c,da48ed3c,0,d6a0215c) at panic+0x71 panic(d06a2ca7,6,0,d03d4fab,d067c27d) at panic+0x71 trap() at trap+0x119 --- trap (number 6) --- swcr_authcompute(d6845068,d68440e0,0,d69a5900,2) at swcr_authcompute+0x33 glxsb_crypto_freesession(d6845068,d68440e0,0,d69a5900,90) at glxsb_crypto_freese ssion+0xe3 glxsb_crypto_process(d6845068,0,da48ef6c,d0332d78) at glxsb_crypto_process+0xd4 crypto_invoke(d6845068,24,d0690993,0) at crypto_invoke+0xbc crypto_thread(d6a0215c) at crypto_thread+0x38 Bad frame pointer: 0xd08c7eb8 End of stack trace. syncing disks... 22 22 21 19 15 9 2 1 1 1 1 1 1 1 1 1 1 1 1 1 giving up It's a moderately loaded machine with approx. 40 ipsec tunnels active, this crash happened within an hour since my last reboot. Any hints on how to debug this? I'd settle for disabling the use of glxsb crypto acceleration if necessary, don't have that much ipsec traffic (yet). Regards, Mitja dmesg: OpenBSD 4.2 (GENERIC) #375: Tue Aug 28 10:38:44 MDT 2007 [EMAIL PROTECTED]:/usr/src/sys/arch/i386/compile/GENERIC cpu0: Geode(TM) Integrated Processor by AMD PCS (AuthenticAMD 586-class) 500 MHz cpu0: FPU,DE,PSE,TSC,MSR,CX8,SEP,PGE,CMOV,CFLUSH,MMX real mem = 536440832 (511MB) avail mem = 511070208 (487MB) mainbus0 at root bios0 at mainbus0: AT/286+ BIOS, date 20/70/19, BIOS32 rev. 0 @ 0xfac40 pcibios0 at bios0: rev 2.0 @ 0xf/0x1 pcibios0: pcibios_get_intr_routing - function not supported pcibios0: PCI IRQ Routing information unavailable. pcibios0: PCI bus #1 is the last bus bios0: ROM list: 0xc8000/0xa800 cpu0 at mainbus0 pci0 at mainbus0 bus 0: configuration mode 1 (no bios) pchb0 at pci0 dev 1 function 0 AMD Geode LX rev 0x31 glxsb0 at pci0 dev 1 function 2 AMD Geode LX Crypto rev 0x00: RNG AES vr0 at pci0 dev 6 function 0 VIA VT6105M RhineIII rev 0x96: irq 11, address 00:00:24:c8:de:2c ukphy0 at vr0 phy 1: Generic IEEE 802.3u media interface, rev. 3: OUI 0x004063, model 0x0034 vr1 at pci0 dev 7 function 0 VIA VT6105M RhineIII rev 0x96: irq 5, address 00:00:24:c8:de:2d ukphy1 at vr1 phy 1: Generic IEEE 802.3u media interface, rev. 3: OUI 0x004063, model 0x0034 vr2 at pci0 dev 8 function 0 VIA VT6105M RhineIII rev 0x96: irq 9, address 00:00:24:c8:de:2e ukphy2 at vr2 phy 1: Generic IEEE 802.3u media interface, rev. 3: OUI 0x004063, model 0x0034 vr3 at pci0 dev 9 function 0 VIA VT6105M RhineIII rev 0x96: irq 12, address 00:00:24:c8:de:2f ukphy3 at vr3 phy 1: Generic IEEE 802.3u media interface, rev. 3: OUI 0x004063, model 0x0034 ppb0 at pci0 dev 14 function 0 TI PCI2250 PCI-PCI rev 0x02 pci1 at ppb0 bus 1 sis0 at pci1 dev 0 function 0 NS DP83815 10/100 rev 0x00, DP83816A: irq 10, address 00:00:24:c3:47:fc nsphyter0 at sis0 phy 0: DP83815 10/100 PHY, rev. 1 sis1 at pci1 dev 1 function 0 NS DP83815 10/100 rev 0x00, DP83816A: irq 7, address 00:00:24:c3:47:fd nsphyter1 at sis1 phy 0: DP83815 10/100 PHY, rev. 1 pcib0 at pci0 dev 20 function 0 AMD CS5536 ISA rev 0x03 pciide0 at pci0 dev 20 function 2 AMD CS5536 IDE rev 0x01: DMA, channel 0 wired to compatibility, channel 1 wired to compatibility wd0 at pciide0 channel 0 drive 0: SanDisk SDCFH-1024 wd0: 4-sector PIO, LBA, 977MB, 2001888 sectors wd0(pciide0:0:0): using PIO mode 4, DMA mode 2 pciide0: channel 1 ignored (disabled) ohci0 at pci0 dev 21 function 0 AMD CS5536 USB rev 0x02: irq 15, version 1.0, legacy support ehci0 at pci0 dev 21 function 1 AMD CS5536 USB rev 0x02: irq 15 usb0 at ehci0: USB revision 2.0 uhub0 at usb0: AMD EHCI root hub, rev 2.00/1.00, addr 1 isa0 at pcib0
glxsb crypto crash
Not my day, obviously On a net5501 machine that I just upgraded to 4.2 I experienced a sudden reboot and found this in dmesg: uvm_fault(0xd078d120, 0x0, 0, 1) - e fatal page fault (6) in supervisor mode trap type 6 code 0 eip d03d4fab cs 8 eflags 10296 cr2 4 cpl 90 panic: trap type 6, code=0, pc=d03d4fab Starting stack trace... panic(0,d6a0215c,da48ed3c,0,d6a0215c) at panic+0x71 panic(d06a2ca7,6,0,d03d4fab,d067c27d) at panic+0x71 trap() at trap+0x119 --- trap (number 6) --- swcr_authcompute(d6845068,d68440e0,0,d69a5900,2) at swcr_authcompute+0x33 glxsb_crypto_freesession(d6845068,d68440e0,0,d69a5900,90) at glxsb_crypto_freese ssion+0xe3 glxsb_crypto_process(d6845068,0,da48ef6c,d0332d78) at glxsb_crypto_process+0xd4 crypto_invoke(d6845068,24,d0690993,0) at crypto_invoke+0xbc crypto_thread(d6a0215c) at crypto_thread+0x38 Bad frame pointer: 0xd08c7eb8 End of stack trace. syncing disks... 22 22 21 19 15 9 2 1 1 1 1 1 1 1 1 1 1 1 1 1 giving up It's a moderately loaded machine with approx. 40 ipsec tunnels active, this crash happened within an hour since my last reboot. Any hints on how to debug this? I'd settle for disabling the use of glxsb crypto acceleration if necessary, don't have that much ipsec traffic (yet). Regards, Mitja dmesg: OpenBSD 4.2 (GENERIC) #375: Tue Aug 28 10:38:44 MDT 2007 [EMAIL PROTECTED]:/usr/src/sys/arch/i386/compile/GENERIC cpu0: Geode(TM) Integrated Processor by AMD PCS (AuthenticAMD 586-class) 500 MHz cpu0: FPU,DE,PSE,TSC,MSR,CX8,SEP,PGE,CMOV,CFLUSH,MMX real mem = 536440832 (511MB) avail mem = 511070208 (487MB) mainbus0 at root bios0 at mainbus0: AT/286+ BIOS, date 20/70/19, BIOS32 rev. 0 @ 0xfac40 pcibios0 at bios0: rev 2.0 @ 0xf/0x1 pcibios0: pcibios_get_intr_routing - function not supported pcibios0: PCI IRQ Routing information unavailable. pcibios0: PCI bus #1 is the last bus bios0: ROM list: 0xc8000/0xa800 cpu0 at mainbus0 pci0 at mainbus0 bus 0: configuration mode 1 (no bios) pchb0 at pci0 dev 1 function 0 AMD Geode LX rev 0x31 glxsb0 at pci0 dev 1 function 2 AMD Geode LX Crypto rev 0x00: RNG AES vr0 at pci0 dev 6 function 0 VIA VT6105M RhineIII rev 0x96: irq 11, address 00:00:24:c8:de:2c ukphy0 at vr0 phy 1: Generic IEEE 802.3u media interface, rev. 3: OUI 0x004063, model 0x0034 vr1 at pci0 dev 7 function 0 VIA VT6105M RhineIII rev 0x96: irq 5, address 00:00:24:c8:de:2d ukphy1 at vr1 phy 1: Generic IEEE 802.3u media interface, rev. 3: OUI 0x004063, model 0x0034 vr2 at pci0 dev 8 function 0 VIA VT6105M RhineIII rev 0x96: irq 9, address 00:00:24:c8:de:2e ukphy2 at vr2 phy 1: Generic IEEE 802.3u media interface, rev. 3: OUI 0x004063, model 0x0034 vr3 at pci0 dev 9 function 0 VIA VT6105M RhineIII rev 0x96: irq 12, address 00:00:24:c8:de:2f ukphy3 at vr3 phy 1: Generic IEEE 802.3u media interface, rev. 3: OUI 0x004063, model 0x0034 ppb0 at pci0 dev 14 function 0 TI PCI2250 PCI-PCI rev 0x02 pci1 at ppb0 bus 1 sis0 at pci1 dev 0 function 0 NS DP83815 10/100 rev 0x00, DP83816A: irq 10, address 00:00:24:c3:47:fc nsphyter0 at sis0 phy 0: DP83815 10/100 PHY, rev. 1 sis1 at pci1 dev 1 function 0 NS DP83815 10/100 rev 0x00, DP83816A: irq 7, address 00:00:24:c3:47:fd nsphyter1 at sis1 phy 0: DP83815 10/100 PHY, rev. 1 pcib0 at pci0 dev 20 function 0 AMD CS5536 ISA rev 0x03 pciide0 at pci0 dev 20 function 2 AMD CS5536 IDE rev 0x01: DMA, channel 0 wired to compatibility, channel 1 wired to compatibility wd0 at pciide0 channel 0 drive 0: SanDisk SDCFH-1024 wd0: 4-sector PIO, LBA, 977MB, 2001888 sectors wd0(pciide0:0:0): using PIO mode 4, DMA mode 2 pciide0: channel 1 ignored (disabled) ohci0 at pci0 dev 21 function 0 AMD CS5536 USB rev 0x02: irq 15, version 1.0, legacy support ehci0 at pci0 dev 21 function 1 AMD CS5536 USB rev 0x02: irq 15 usb0 at ehci0: USB revision 2.0 uhub0 at usb0: AMD EHCI root hub, rev 2.00/1.00, addr 1 isa0 at pcib0 isadma0 at isa0 pckbc0 at isa0 port 0x60/5 pckbd0 at pckbc0 (kbd slot) pckbc0: using irq 1 for kbd slot wskbd0 at pckbd0: console keyboard pcppi0 at isa0 port 0x61 midi0 at pcppi0: PC speaker spkr0 at pcppi0 nsclpcsio0 at isa0 port 0x2e/2: NSC PC87366 rev 9: GPIO VLM TMS gpio0 at nsclpcsio0: 29 pins npx0 at isa0 port 0xf0/16: reported by CPUID; using exception 16 pccom0 at isa0 port 0x3f8/8 irq 4: ns16550a, 16 byte fifo pccom0: console pccom1 at isa0 port 0x2f8/8 irq 3: ns16550a, 16 byte fifo usb1 at ohci0: USB revision 1.0 uhub1 at usb1: AMD OHCI root hub, rev 1.00/1.00, addr 1 biomask e145 netmask ffe5 ttymask ffe7 pctr: user-level cycle counter enabled mtrr: K6-family MTRR support (2 registers) dkcsum: wd0 matches BIOS drive 0x80 root on wd0a swap on wd0b dump on wd0b WARNING: / was not properly unmounted