perfctr-2.6.4 released with PPC32 support

perfctr-2.6.4 released with PPC32 support

[Mikael Pettersson]

Version 2.6.4 of perfctr, the Linux performance
monitoring counters driver, is now available at the usual
place: http://www.csd.uu.se/~mikpe/linux/perfctr/

Three architectures are now supported: x86, AMD64, and PPC32.

Since I only have a PPC750, I'm looking for testers with 74xx
or 604 processors. Even if you don't intend to use the driver,
booting a kernel configured with CONFIG_PERFCTR_INIT_TESTS=y,
loading the driver module (if not built-in), and emailing me the
PERFCTR INIT kernel log messages would be helpful.

Version 2.6.4, 2004-01-12
- Added support for PowerPC 604/7xx/74xx processors.
  * Overflow interrupts are not yet supported due to a hardware
    erratum affecting many 7xx and early 74xx processors.
  * The user-space components support PowerPC, but CPU detection
    and event set descriptions are not yet implemented.
  * Supported in 2.6.1 and 2.4.23 and newer 2.4 kernels.
- Updated kernel support: 2.6.1, 2.4.25-pre4, 2.4.22-1.2140.nptl
  (FC1 update), 2.4.21-4.0.2.EL (RHEL update), and 2.4.20-28.x
  (RH 7.x/8.0/9 update).

/ Mikael Pettersson

Re: perfctr-2.6.4 released with PPC32 support

[Christian]

Mikael Pettersson wrote:
> Version 2.6.4 of perfctr, the Linux performance
> monitoring counters driver, is now available at the usual
> place: http://www.csd.uu.se/~mikpe/linux/perfctr/
>
> Three architectures are now supported: x86, AMD64, and PPC32.
>
> Since I only have a PPC750, I'm looking for testers with 74xx
> or 604 processors. Even if you don't intend to use the driver,

kernel patches applied with no fuzz to 2.4.24, but compiling the library
gives:

[...]
make[4]: Leaving directory `/usr/local/src/perfctr-2.6.4/examples/perfex'
make[4]: Entering directory `/usr/local/src/perfctr-2.6.4/examples/signal'
gcc -O2 -fomit-frame-pointer -Wall -I../../linux/include -I../../usr.lib
  -c -o ppc.o ppc.c
ppc.c: In function `mcontext_pc':
ppc.c:15: error: structure has no member named `regs'
make[4]: *** [ppc.o] Error 1
make[4]: Leaving directory `/usr/local/src/perfctr-2.6.4/examples/signal'
make[3]: Leaving directory `/usr/local/src/perfctr-2.6.4/examples'
make[2]: Leaving directory `/usr/local/src/perfctr-2.6.4/examples'
make[1]: Leaving directory `/usr/local/src/perfctr-2.6.4'
evil@sheep:/usr/local/src/perfctr-2.6.4$

evil@sheep:/usr/local/src/perfctr-2.6.4$ gcc --version | head -n1
gcc (GCC) 3.3.3 20031229 (prerelease) (Debian)

evil@sheep:/usr/local/src/perfctr-2.6.4$ cat /proc/cpuinfo
processor       : 0
cpu             : 604r
clock           : ???
revision        : 49.2 (pvr 0009 3102)
bogomips        : 299.00
machine         : PReP Utah (Powerstack II Pro4000)
l2 cache        : 512KiB, parity disabled SRAM:synchronous, pipelined,
no parity

Christian.
--
BOFH excuse #123:

user to computer ratio too high.

** Sent via the linuxppc-dev mail list. See http://lists.linuxppc.org/

Re: perfctr-2.6.4 released with PPC32 support

[Mikael Pettersson]

On Tue, 13 Jan 2004 00:04:31 +0100, Christian <evil@g-house.de> wrote:
>Mikael Pettersson wrote:
>> Version 2.6.4 of perfctr, the Linux performance
>> monitoring counters driver, is now available at the usual
>> place: http://www.csd.uu.se/~mikpe/linux/perfctr/
>>
>> Three architectures are now supported: x86, AMD64, and PPC32.
>>
>> Since I only have a PPC750, I'm looking for testers with 74xx
>> or 604 processors. Even if you don't intend to use the driver,
>
>kernel patches applied with no fuzz to 2.4.24, but compiling the library
>gives:
>
>[...]
>make[4]: Leaving directory `/usr/local/src/perfctr-2.6.4/examples/perfex'
>make[4]: Entering directory `/usr/local/src/perfctr-2.6.4/examples/signal'
>gcc -O2 -fomit-frame-pointer -Wall -I../../linux/include -I../../usr.lib
>  -c -o ppc.o ppc.c
>ppc.c: In function `mcontext_pc':
>ppc.c:15: error: structure has no member named `regs'
>make[4]: *** [ppc.o] Error 1

Hmm, must be a glibc or kernel headers version problem.
I'm running YDL3.0.1 with glibc-2.3.1.

What version of glibc do you have? How does it define an
mcontext_t (struct sigcontext_struct)?

>evil@sheep:/usr/local/src/perfctr-2.6.4$ cat /proc/cpuinfo
>processor       : 0
>cpu             : 604r
>clock           : ???
>revision        : 49.2 (pvr 0009 3102)
>bogomips        : 299.00
>machine         : PReP Utah (Powerstack II Pro4000)
>l2 cache        : 512KiB, parity disabled SRAM:synchronous, pipelined,
>no parity

Nothing in dmesg?

/Mikael

** Sent via the linuxppc-dev mail list. See http://lists.linuxppc.org/

Re: perfctr-2.6.4 released with PPC32 support

[Christian]

[-- Attachment #1: Type: text/plain, Size: 1612 bytes --]


Mikael Pettersson wrote:
|>ppc.c: In function `mcontext_pc':
|>ppc.c:15: error: structure has no member named `regs'
|>make[4]: *** [ppc.o] Error 1
|
| Hmm, must be a glibc or kernel headers version problem.
| I'm running YDL3.0.1 with glibc-2.3.1.

this is debian/unstable with glibc 2.3.2.ds1-10, kernel headers are
*not* under /usr/src/linux/include as one might expect, any way to
specify them with the "make" command? i did not see any hint in the
Makefile how to do this, sorry. but: there is a package named
"linux-kernel-headers" in debian/unstable since a few weeks (?) now. i
have to install it, other -dev packages depend on it, its version is
"2.5.999-test7-bk-14", kinda weird, perhaps this is some bug or so and
hopefully resolved soon by the maintainer.

| What version of glibc do you have? How does it define an
| mcontext_t (struct sigcontext_struct)?

hm, don't know if i picked the one you meant, but
/usr/include/sys/ucontext.h shows:

- -----------------
/* Context to describe whole processor state.  */
typedef struct
{
~        gregset_t gregs;
~        fpregset_t fpregs;
~        vrregset_t vrregs __attribute__((__aligned__(16)));
} mcontext_t;

#else

/* For 64-bit, a machine context is exactly a sigcontext.  */
typedef struct sigcontext mcontext_t;

#endif
- -----------------

| Nothing in dmesg?

/var/log/dmesg is attached (booting a vanilla (!) 2.4.24), but there are
of course no messages during "make"...

no, i was not even aware of using perfctr, but you said testing helps,
and so i did :-)

Thank you for your time,
Christian.

- --
BOFH excuse #429:

Temporal anomaly

[-- Attachment #2: dmesg --]
[-- Type: text/plain, Size: 5941 bytes --]

Memory BAT mapping: BAT2=128Mb, BAT3=0Mb, residual: 0Mb
Total memory = 128MB; using 256kB for hash table (at c0200000)
Linux version 2.4.24 (evil@sheep) (gcc-Version 3.3.3 20031229 (prerelease) (Debian)) #2 Fr Jan 9 13:38:41 CET 2004
PReP architecture
On node 0 totalpages: 32768
zone(0): 32768 pages.
zone(1): 0 pages.
zone(2): 0 pages.
Kernel command line: root=/dev/sda5
time_init: decrementer frequency = 16.657714 MHz
Console: colour VGA+ 80x25
Calibrating delay loop... 299.00 BogoMIPS
Memory: 127400k available (1108k kernel code, 468k data, 276k init, 0k highmem)
Dentry cache hash table entries: 16384 (order: 5, 131072 bytes)
Inode cache hash table entries: 8192 (order: 4, 65536 bytes)
Mount cache hash table entries: 512 (order: 0, 4096 bytes)
Buffer cache hash table entries: 8192 (order: 3, 32768 bytes)
Page-cache hash table entries: 32768 (order: 5, 131072 bytes)
POSIX conformance testing by UNIFIX
PCI: Probing PCI hardware
Setting PCI interrupts for a "Utah (Powerstack II Pro4000)"
PCI: moved device 00:0b.1 resource 4 (101) to 10a0
PCI: moved device 00:0b.1 resource 5 (101) to 10b0
PCI: moved device 00:12.0 resource 0 (1208) to 0
Linux NET4.0 for Linux 2.4
Based upon Swansea University Computer Society NET3.039
Initializing RT netlink socket
Starting kswapd
Journalled Block Device driver loaded
pty: 256 Unix98 ptys configured
SCSI subsystem driver Revision: 1.00
PCI: Enabling device 00:0c.0 (0000 -> 0003)
sym53c8xx: at PCI bus 0, device 12, function 0
sym53c8xx: setting PCI_COMMAND_MASTER PCI_COMMAND_PARITY...(fix-up)
sym53c8xx: changing PCI_LATENCY_TIMER from 0 to 80.
sym53c8xx: 53c825a detected 
sym53c825a-0: rev 0x13 on pci bus 0 device 12 function 0 irq 15
sym53c825a-0: ID 7, Fast-10, Parity Checking
scsi0 : sym53c8xx-1.7.3c-20010512
blk: queue c7feb174, I/O limit 4095Mb (mask 0xffffffff)
sym53c825a-0-<0,*>: FAST-10 WIDE SCSI 20.0 MB/s (100.0 ns, offset 8)
  Vendor: IBM-ESXS  Model: ST318305LW    !#  Rev: B245
  Type:   Direct-Access                      ANSI SCSI revision: 03
blk: queue c7feb274, I/O limit 4095Mb (mask 0xffffffff)
sym53c825a-0-<1,*>: FAST-10 WIDE SCSI 20.0 MB/s (100.0 ns, offset 8)
  Vendor: IBM-ESXS  Model: ST318305LW    !#  Rev: B244
  Type:   Direct-Access                      ANSI SCSI revision: 03
blk: queue c7feb374, I/O limit 4095Mb (mask 0xffffffff)
sym53c825a-0-<2,*>: FAST-10 WIDE SCSI 20.0 MB/s (100.0 ns, offset 8)
  Vendor: IBM-ESXS  Model: ST336607LW    FN  Rev: B258
  Type:   Direct-Access                      ANSI SCSI revision: 03
blk: queue c7feb474, I/O limit 4095Mb (mask 0xffffffff)
Attached scsi disk sda at scsi0, channel 0, id 0, lun 0
Attached scsi disk sdb at scsi0, channel 0, id 1, lun 0
Attached scsi disk sdc at scsi0, channel 0, id 2, lun 0
sym53c825a-0-<0,*>: FAST-10 WIDE SCSI 20.0 MB/s (100.0 ns, offset 8)
SCSI device sda: 35548320 512-byte hdwr sectors (18201 MB)
Partition check:
 sda: sda1 sda2 sda3 < sda5 sda6 sda7 sda8 sda9 > sda4
sym53c825a-0-<1,*>: FAST-10 WIDE SCSI 20.0 MB/s (100.0 ns, offset 8)
SCSI device sdb: 35548320 512-byte hdwr sectors (18201 MB)
 sdb: sdb1 sdb2 sdb3
sym53c825a-0-<2,*>: FAST-10 WIDE SCSI 20.0 MB/s (100.0 ns, offset 8)
SCSI device sdc: 71096640 512-byte hdwr sectors (36401 MB)
 sdc: sdc1 sdc2
Initializing Cryptographic API
NET4: Linux TCP/IP 1.0 for NET4.0
IP Protocols: ICMP, UDP, TCP
IP: routing cache hash table of 1024 buckets, 8Kbytes
TCP: Hash tables configured (established 8192 bind 16384)
NET4: Unix domain sockets 1.0/SMP for Linux NET4.0.
kjournald starting.  Commit interval 5 seconds
EXT3-fs: mounted filesystem with ordered data mode.
VFS: Mounted root (ext3 filesystem) readonly.
Freeing unused kernel memory: 276k init 32k pmac 4k chrp 4k openfirmware
Adding Swap: 320032k swap-space (priority 1)
Adding Swap: 99320k swap-space (priority 1)
EXT3 FS 2.4-0.9.19, 19 August 2002 on sd(8,5), internal journal
loop: loaded (max 8 devices)
kjournald starting.  Commit interval 5 seconds
EXT3 FS 2.4-0.9.19, 19 August 2002 on sd(8,6), internal journal
EXT3-fs: mounted filesystem with ordered data mode.
kjournald starting.  Commit interval 5 seconds
EXT3 FS 2.4-0.9.19, 19 August 2002 on sd(8,9), internal journal
EXT3-fs: mounted filesystem with ordered data mode.
kjournald starting.  Commit interval 5 seconds
EXT3 FS 2.4-0.9.19, 19 August 2002 on sd(8,7), internal journal
EXT3-fs: mounted filesystem with ordered data mode.
kjournald starting.  Commit interval 5 seconds
EXT3 FS 2.4-0.9.19, 19 August 2002 on sd(8,8), internal journal
EXT3-fs: mounted filesystem with ordered data mode.
kjournald starting.  Commit interval 5 seconds
EXT3 FS 2.4-0.9.19, 19 August 2002 on sd(8,4), internal journal
EXT3-fs: mounted filesystem with ordered data mode.
kjournald starting.  Commit interval 5 seconds
EXT3 FS 2.4-0.9.19, 19 August 2002 on sd(8,33), internal journal
EXT3-fs: mounted filesystem with ordered data mode.
kjournald starting.  Commit interval 5 seconds
EXT3 FS 2.4-0.9.19, 19 August 2002 on sd(8,17), internal journal
EXT3-fs: mounted filesystem with ordered data mode.
kjournald starting.  Commit interval 5 seconds
EXT3 FS 2.4-0.9.19, 19 August 2002 on loop(7,7), internal journal
EXT3-fs: mounted filesystem with ordered data mode.
PCI: Enabling device 00:10.0 (0000 -> 0003)
3c59x: Donald Becker and others. www.scyld.com/network/vortex.html
See Documentation/networking/vortex.txt
00:10.0: 3Com PCI 3c905C Tornado at 0x1000. Vers LK1.1.18-ac
 00:01:02:f1:83:37, IRQ 10
  product code 464a rev 00.13 date 11-12-00
  Internal config register is 1800000, transceivers 0xa.
  8K byte-wide RAM 5:3 Rx:Tx split, autoselect/Autonegotiate interface.
  MII transceiver found at address 24, status 782d.
  Enabling bus-master transmits and whole-frame receives.
00:10.0: scatter/gather enabled. h/w checksums enabled
Serial driver version 5.05c (2001-07-08) with MANY_PORTS SHARE_IRQ SERIAL_PCI enabled
ttyS00 at 0x03f8 (irq = 4) is a 16550A
ttyS01 at 0x02f8 (irq = 3) is a 16550A