$Id: CHANGES,v 1.142.2.72 2010/11/07 19:48:14 mikpe Exp $

			CHANGES

			=======

[High-level changes in reverse chronological order. Detailed

 driver changes are in linux/drivers/perfctr/RELEASE-NOTES.]

Version 2.6.42, 2010-11-07

- Classify Westmere processors as Westmere not Nehalem.

- Update update-kernel to install arch-specific header files

  in arch/$arch/include/asm/ for newer kernels.  Also make

  update-kernel --test trace file installation steps.

- Update usr.src/Makefile to use the LD make variable rather

  than plain 'ld' if set.  Useful for cross-compilation and

  builds with non-default target options.

- Updated kernel support: 2.6.18-194.17.4.el5 (RHEL5).

Version 2.6.41, 2010-06-08

- Extend examples/perfex/ to allow users to set up values for

  the OFFCORE_RSP MSRs on Nehalem-based processors.

- Add driver support for OFFCORE_RSP MSRs on Nehalem-based processors.

- Recognise more Nehalem-based processors (models 30, 37).

- Renamed PERFCTR_X86_INTEL_COREI7 symbolic CPU/PMU type constant

  to PERFCTR_X86_INTEL_NHLM, since it denotes the entire Nehalem

  family not just the (original) Core i7. The old constant is

  also defined for now, to not break source code compatibility.

- Correct Core i7 event setup in examples/global/ to actually

  work. It was rejected by the driver due to a copy-paste error.

- Rewrite the missing event list message in `perfex -l/-L' to

  indicate that this is a user-space library omission, not an

  issue with the driver or the hardware.

- Updated kernel support: 2.6.18-194.3.1.el5, 2.6.18-194.el5,

  2.6.18-164.15.1.el5 (RHEL5).

Version 2.6.40, 2010-01-30

- Preliminary support for Intel Xeon 7500 (Nehalem-based) processors.

- Preliminary support for Intel i7-980X Gulftown processors.

- Added support for AMD Family 11h processors (compatible with fam 10h).

- Updated kernel support: 2.6.32, 2.6.31, 2.6.18-164.11.1.el5 and

  2.6.18-164.el5 (RHEL5), 2.6.9-89.0.19.EL (RHEL4).

Version 2.6.39, 2009-06-11

- Updated driver's AMD multicore detection code to actually work.

  Tested on Istanbul and Shanghai Opterons.

- Updated driver to allow per-thread counting of Northbridge events

  on multicore AMD processors. Since the NB is shared between cores,

  threads counting NB events will be forced via their CPU affinity

  mask to core0 of the available processors. On early K8 RevE processors

  NB events remain limited to global-mode counting, due to an erratum.

- Updated kernel support: 2.6.30, 2.6.29, 2.6.18-128.1.10.el5 (RHEL5),

  2.6.18-92.1.26.el5 (RHEL5), 2.6.9-89.EL (RHEL4), 2.6.9-78.0.22.EL (RHEL4).

Version 2.6.38, 2009-01-23

- Added rvperfctr_iresume() procedure to the user-space library.

  This allows a monitor process to resume overflow counters in a

  target process after the target has received an overflow signal.

- Updated kernel support: 2.6.29-rc2, 2.6.28, 2.6.18-128.el5

  (RHEL5.3), 2.6.9-78.0.13.EL (RHEL4).

- Removed support for 2.4 kernels. 2.4 kernels have effectively

  been unsupported since early 2007, this change makes it official

  by removing all 2.4-specific files and #ifdefs.

Version 2.6.37, 2008-11-30

- Preliminary support for Intel Core i7 (Nehalem) processors

  (family 6 model 26). They are currently treated like Core 2s

  but with four general-purpose counters, and with different

  events and a new symbolic CPU type. The AnyThread evntsel flag

  and "uncore" event monitoring are not yet supported.

- Updated x86 driver to recognise Xeon 7400 (family 6 model 29)

  as a member of the Core 2 family.

- Extended x86 driver's CPU initialisation on Intel Core 2 and

  newer CPUs to work around vtune leaving the performance monitor

  unit in a "very" disabled state. Thanks to Mark Krentel for

  reporting the problem and for facilitating tests that allowed

  the cause of the problem to be identified.

- Updated kernel support: 2.6.28-rc6, 2.6.18-120.el5 (RHEL5.3 beta),

  2.6.18-92.1.18.el5 (RHEL5), 2.6.9-78.0.8.EL (RHEL4).

Version 2.6.36, 2008-10-19

- Fixed a driver error which caused Intel Family 6 Model 23

  processors to crash kernels with general protection faults

  if the fixed-function counters ran in interrupt-on-overflow

  mode. Older Intel Family 6 Model 15 processors tolerate the

  error which is why it was not detected before. Thanks to

  Mark Krentel for reporting the problem and for facilitating

  tests that allowed the cause of the problem to be identified.

- Updated kernel support: 2.6.27, 2.6.26, 2.6.18-92.1.13.el5

  (RHEL5), 2.6.9-78.0.5.EL (RHEL4).

Version 2.6.35, 2008-06-30

- Preliminary support for Intel Atom processors added.

  These processors are very poorly documented, but they are

  known to be family 6 model 28, and to support Intel's

  "architectural performance monitor". Current models seem

  to have two general-purpose counters, one fixed-function

  counter, and to support the seven architectural events.

  Thanks to Steve Blackburn for running tests on his Atom.

- Updated x86 driver to recognise the Celeron model 16h

  as a member of the Core2 family.

- Corrected an error in the x86 driver's control validation

  procedure. The error was introduced in perfctr-2.6.29 when

  support for the Core2's fixed-function counters was added.

  The error made the driver accept some invalid controls

  (on Core2 processors only), which could result in kernel

  hangs due to exceptions from invalid register accesses.

  Thanks to Anton Ertl for reporting the initial problem.

- Updated README to add Atom and AMD Family 10h to list of

  supported processors.

- Updated kernel support: 2.6.26-rc8, 2.6.18-92.1.6.el5 (RHEL5),

  2.6.18-92.1.1.el5 (RHEL5), 2.6.9-67.0.20.EL (RHEL4).

Version 2.6.35-pre1, 2008-06-23

- Added optional close-on-exec feature for per-process perfctrs.

  To enable it, set control.flags |= VPERFCTR_CONTROL_CLOEXEC

  in a struct vperfctr_control object before passing it to

  vperfctr_control(). If the flag is set when a thread executes

  an execve() system call, then its perfctr state is detached

  from the thread as if a call to vperfctr_unlink() had occurred.

  If the flag is clear then the state survives execve() just like

  it always did before.

- The vperfctr_open() library function now sets close-on-exec

  on the file descriptor embedded in the returned vperfctr handle.

- Removed library support for the ancient /proc/<pid>/perfctr

  kernel interface which hasn't worked since perfctr-2.6.0.

Version 2.6.34, 2008-05-29

- Updated kernel support: 2.6.26-rc4, 2.6.18-92.el5 (RHEL5U2),

  2.6.18-53.1.21.el5 (RHEL5), 2.6.16.42-0.12 (SuSE).

- Corrected the kernel driver's version number: perfctr-2.6.33

  forgot to increment it.

Version 2.6.33, 2008-05-18

- x86: The support for Intel Family 6 Model 23 processors added in

  perfctr-2.6.32 was incomplete, causing overflow interrupts to not

  work properly on those processors. This has been fixed. (Thanks

  to Mark Krentel for reporting the issue and testing patches.)

- Updated kernel support: 2.6.26-rc2, 2.6.18-53.1.19.el5 (RHEL5),

  2.6.9-67.0.15.EL (RHEL4).

Version 2.6.32, 2008-04-20

- Library: add experimental vperfctr_open_mode(mode) procedure.

  The plain vperfctr_open() always opens the perfctr state in

  O_CREAT|O_EXCL mode, which means that it will fail if the

  invoking thread already has a perfctr state. The mode parameter

  to vperfctr_open_mode() can be used to avoid this behaviour:

  with mode == 0 no state will be created and a handle to the

  thread's existing state (if any) is returned; to select the

  current behaviour pass mode == VPERFCTR_OPEN_CREAT_EXCL to

  vperfctr_open_mode(). For example:

  the_state_is_shared = 0;

  vperfctr = vperfctr_open_mode(VPERFCTR_OPEN_CREAT_EXCL);

  if (vperfctr == NULL && errno == EEXIST) {

     // error out due to the resource conflict, or:

     vperfctr = vperfctr_open_mode(0);

     the_state_is_shared = 1;

  }

  ...

  The purpose of this API extension is to hopefully allow PAPI

  to handle some use cases that currently cause it to error out.

- Fix 'make install' to select the correct file to install

  as <asm/perfctr.h>. Fixes regression caused by i386/x86_64

  arch unification in perfctr-2.6.30. ppc32 also needed fixing.

- x86: Recognize Intel Family 6 Model 23 as Core2.

- Updated kernel support: 2.6.25, 2.6.18-53.1.14.el5 (RHEL5),

  2.6.9-67.0.7.EL (RHEL4).

Version 2.6.31, 2008-01-26

- x86: Barcelona (AMD Family 10h) updates:

  * Correct CPU type constant to read FAM10H with trailing H.

    The old spelling also remains, for now.

  * Barcelona event selectors are 64-bit, not 32-bit as in K8.

    Add evntsel_high[] array to struct perfctr_cpu_control to

    allow passing high 32 bits of evntsels to the driver.

    This array overlaps the p4 control sub-struct. (Uses a GCC

    anonymous union, to avoid source-incompatible changes.)

    Currently only some Northbridge events need the high bits.

  * Update driver to accept and check high evntsel bits on

    Barcelona, and to maintain all 64 evntsel bits in PMU

    context switches.

  * Update examples/perfex/ to indicate how to also set up

    the high 32 evntsel bits for Barcelona (run perfex -h).

- Minor coding style (mostly obsolete whitespace style) fixes.

- Updated kernel support: 2.6.24, 2.6.18-53.1.6.el5 (RHEL5),

  2.6.9-67.0.1.EL (RHEL4).

Version 2.6.30, 2007-10-28

- Kernel 2.6.24-rc1 replaced the previously separate i386

  and x86_64 source code directories with new shared x86

  directories. Updated the linux/include/ hierarchy and the

  update-kernel script to handle new and old source layouts.

- Several driver updates to handle kernel 2.6.24-rc1 changes

  on both x86 and ppc32.

- Fixed a problem which could break RHEL5 kernel builds in

  some configurations.

- Updated kernel support: 2.6.24-rc1, 2.6.23, 2.6.18-8.1.14.el5

  (RHEL5), and 2.6.9-55.0.6.EL (RHEL4).

Version 2.6.29, 2007-10-07

- Added support for the fixed-function counters in Intel Core 2

  processors. To user-space they look like ordinary P6 counters,

  except their PMC numbers are 0x40000000..0x40000002, and their

  evntsels only need Enable, INT, and CPL fields set.

- Preliminary support for AMD Family 10h processors.

  Currently only events that do not need to use the high 32 bits

  of the event select control registers are expected to work.

- Fixed driver compilation warnings caused by perfctr needing

  its own definitions of macros/constants that may or may not

  be defined in the specific kernel version used.

- Updated kernel support: 2.6.23-rc9, 2.6.5-7.276 (SuSE).

Version 2.6.28, 2007-07-18

- Fixed path to udev rules file (/etc/udev.d/ -> /etc/udev/).

- Updated to handle changes in the 2.6.22 kernel on ppc32.

- Updated to handle changes in the 2.6.22 kernel on x86.

- Updated kernel support: 2.6.22, 2.6.21, 2.6.18-8.1.8.el5 (RHEL5),

  2.6.9-55.0.2.EL (RHEL4), and 2.6.9-55.EL (RHEL4).

Version 2.6.27, 2007-04-09

- Updated INSTALL with instructions for making /dev/perfctr

  creation and perfctr module autoloading work with udev.

  These instructions are known to work on Fedora Core 4.

  Also updated the rpm package accordingly.

- Updated for the RHEL5 2.6.18-8.1.1.el5 kernel. This kernel

  removed a ptrace-related function that is used for perfctr's

  remote-control API. For now, remote-control is disabled in

  the RHEL5 kernel, but everything else should work.

- Updated kernel support: 2.6.21-rc6, 2.6.18.2-34 (SuSE),

  2.6.9-42.0.10.EL (RHEL4).

Version 2.6.26, 2007-02-11

- My old @csd.uu.se email address no longer works. Updated

  documentation and kernel messages to show my @it.uu.se address.

- Added driver support for ARM/XScale processors. Overflow

  interrupts are not yet supported, in part due to conflicts

  with Intel's ixp400_eth driver. Plain event counting works.

- Updated kernel support: 2.6.20, 2.6.19, 2.6.9-42.0.8.EL (RHEL4),

  2.4.34, 2.4.21-47.0.1.EL (RHEL3), 2.6.16.21 (SLES10).

Version 2.6.25, 2006-10-15

- The Intel Core 2 processors are substantially different from

  the old Core processors. Core 2 processors are now mapped to a

  new cpu_type PERFCTR_X86_INTEL_CORE2, and must be programmed

  so that every EVNTSEL used has its Enable flag set. This is

  consistent with Intel's documentation and observations made by

  others on later steppings of the Core 2. Early steppings may

  be more P6-like (master Enable in EVNTSEL0), but as long as a

  control setup includes EVNTSEL0 it should work on any stepping.

- Major x86 driver updates for changes in kernel 2.6.19-rc1.

- Updated kernel support: 2.6.19-rc2, 2.6.18, 2.6.9-42.0.3.EL (RHEL4),

  and 2.4.34-pre4.

- Fixed perfex -l/-L to handle unavailability of event set data

  gracefully and not signal an error in those cases.

Version 2.6.24, 2006-09-17

- Fixed a driver linkage failure in 64-bit x86 kernels when

  CONFIG_PERFCTR_INIT_TESTS was enabled, caused by an omission

  in the perfctr-2.6.23 changes to support Intel Core 2 CPUs.

- Updated kernel support: 2.6.18-rc7, 2.6.9-42.0.2.EL (RHEL4),

  and 2.4.34-pre2.

Version 2.6.23, 2006-08-20

- Intel Core 2 fixes: detect Core2 processors (Model 15) and

  allow them to be used in 64-bit builds.

- Updated kernel support: 2.6.18-rc4, 2.6.17, 2.6.9-34.0.2.EL (RHEL4),

  2.4.33, 2.4.34-pre1, and 2.4.21-47.EL (RHEL3).

- The update-kernel script is now able to automatically identify

  SuSE Linux kernel versions. A SuSE kernel MUST be configured

  (".config" exists) for the identification to work.

Version 2.6.22, 2006-06-02

- Preliminary support for Intel Core (family 6 model 14) processors.

- A serious error in the x86 driver's code to identify hyper-threads

  was fixed. The driver logic is correct but it used a kernel function

  which does not provide the required behaviour in 64-bit kernels or

  older 32-bit kernels. As a result bogus data could be input to the

  hyper-thread detection code, leading to various failures.

- A change in the 2.6.16 32-bit x86 kernel caused a compilation error

  when CONFIG_PERFCTR_INIT_TESTS was enabled. Fixed this.

- Updated kernel support: 2.6.9-34.0.1 (RHEL4), 2.6.17-rc5, and

  2.4.33-pre3.

Version 2.6.21, 2006-04-03

- Updated kernel support: 2.4.21-40.EL (RHEL3), 2.6.16, and

  2.6.17-rc1.

- Updates for internal changes in kernels 2.6.16 and 2.6.17-rc1.

- Corrected a mistake in perfctr-2.6.20 which caused compilation

  errors with RHEL3 kernels.

Version 2.6.20, 2006-03-12

- Updated kernel support: 2.6.9-34 (RHEL4), 2.6.16-rc6, and

  2.4.33-pre2.

Version 2.6.19, 2006-01-22

- Updated ppc32 driver for ppc32/ppc64 kernel merging changes

  in the 2.6.16-rc1 kernel. The driver now dynamically claims

  and release the hardware, allowing it to coexist with other

  PMU drivers such as oprofile.

- Updated kernel support: 2.6.16-rc1, 2.6.9-22.0.2 (RHEL4).

Version 2.6.18, 2006-01-03

- Added perfctr_get_info() library API procedure, which allows

  users to acquire information about the system without needing

  a handle to an open perfctr (per-process or global) state.

- Rearranged structure marshalling descriptor declarations to

  increase code sharing for all supported architectures.

- Updated kernel support: 2.6.15, 2.6.14, 2.6.9-22.0.1 (RHEL4),

  2.6.5-7.201 (SuSE), 2.4.33-pre1, 2.4.32.

Version 2.6.17, 2005-10-02

- The x86 kernel driver has been updated to work correctly

  on dual-core P4 processors. Previous versions would fail

  during CPU detection (on HT DC P4s) or would erroneously

  restrict access for one of the cores (non-HT DC P4s).

- Updated kernel support: 2.4.21-37.EL (RHEL3), 2.4.32-rc1,

  and 2.6.14-rc3.

Version 2.6.16, 2005-09-04

- The ppc32 driver will now compile in kernels that lack Open

  Firmware support, which is needed for some embedded systems.

- Updated kernel support: 2.6.9-11.EL (RHEL4), 2.4.21-32.0.1.EL

  (RHEL3), 2.6.12, 2.6.13, 2.4.31, and 2.4.32-pre3.

Version 2.6.15, 2005-05-06

- Preliminary code in the x86/x86-64 low-level driver to detect

  multicore AMD K8 processors, and to prevent resource conflicts

  and an erratum related to northbridge events. On multicore K8s,

  northbridge events are only allowed when using the global-mode

  counters API.

- Updated kernel support: 2.6.9-5.0.5.EL (RHEL4), 2.4.21-27.0.4.EL

  (RHEL3), 2.4.31-pre1, and 2.6.12-rc3.

Version 2.6.14, 2005-04-09

- Changed vperfctr_open() so that if the thread already has

  an attached perfctr state, then the call fails with EEXIST.

  This allows self-monitoring code to detect if it is under

  the control of an external monitoring agent, before it

  changes the counters' control setup.

- Reverted the workaround in perfctr-2.6.13 for the problem

  that gcc-4.0 snapshots broke the x86/x86-64 low-level driver,

  as recent gcc-4.0 prereleases seem to work correctly.

- Updated kernel support: 2.4.30, 2.6.12-rc2, and 2.6.9-5.0.3

  (RHEL4).

Version 2.6.13, 2005-02-13

- Changed the global-mode counters to allow user-space to

  disable the in-kernel sampling timer and to move the sampling

  points into the read system calls. This may improve sampling

  precision in some scenarios.

- gcc-4.0 snapshots broke the x86/x86-64 low-level driver.

  Changed the driver to prevent those problems.

- Updated kernel support: 2.6.11-rc4, 2.4.30-pre1, and

  2.4.21-27.0.2 (RHEL3).

Version 2.6.12, 2004-12-19

- PPC32 driver updated to be more robust in its detection of

  timebase and core clock frequencies. Some information sources

  can give wrong values for those frequencies, so the driver

  now tries other more reliable methods first.

- On x86/x86-64, perfctr_event_codes.h now includes P4 events.

- On x86-64 libraries will now be installed in PREFIX/lib64/,

  as per current standards, unless overridden by LIBDIR.

- Perfex had a bug in which it interpreted all numbers as hex,

  even those without "0x" prefixes. Perfex now emits warnings

  for ambiguous numbers. To silence the warnings, (a) prefix

  hex numbers with "0x" (preferred), or (b) use the "-d" option

  to enable decimal numbers, which requires "0x" prefixes on

  hex numbers, or (c) use the "-x" option to force all numbers

  to be interpreted as hex (deprecated). The "-d" option should

  be the default, but unfortunately that would break user-level

  scripts that assumed that "0x"-less numbers are still hex.

- Changes in examples/signal/ to handle glibc-2.3.3 on PPC32.

Version 2.6.11, 2004-11-14

- Workarounds for a hardware quirk on x86 and x86-64, where

  interrupts can be delivered some time after the counters have

  been stopped. Due to scheduling, an interrupt could be taken

  in the context of an unrelated process, which would prematurely

  terminate interrupt reporting for the original process.

- Fixed a bug in the x86 and x86-64 kernels where the context-switch

  path suspended the previous process' performance counters too late.

  This could allow an overflow interrupt to be taken in the context

  of an unrelated process, with effects similar to the hardware quirk

  described above.

- PPC32 updates: Enable overflow interrupts on all G4 processors

  starting with the 7410 Rev 1.3, and all IBM G3 processors starting

  with the 750FX DD2.3. Add support for MPC7447A and MPC7448.

- Removed patches for obsolete kernels.

Version 2.6.10.3, 2004-10-24

- Driver modifications to handle two significant changes in

  the 2.6.10-rc1 kernel.

- PPC32: added MPC7447A and MPC7448 support.

- Cleanups to bring the driver closer to the development version.

Version 2.6.10.2, 2004-10-19

- Updated kernel support: 2.6.9, 2.4.28-pre4.

- Corrected the PPC32 driver's handling of MMCR0 changes due

  to use of the FCECE or TRIGGER control flags.

- Fixed a synchronisation error in the interface between

  the per-process counters driver and the low-level drivers.

  The error triggered warnings in DEBUG_SPINLOCK_SLEEP-

  enabled kernels.

Version 2.6.10.1, 2004-09-18

- Fixed a problem causing an incomplete "wrapper" file to be

  installed as /usr/include/asm/perfctr.h on x86_64 systems.

Version 2.6.10, 2004-09-14

- Eliminated a potential kernel crash on P4 model 3 Prescott

  processors, due to the driver initialising two control

  registers that have been removed from P4M3. The P4M3 Nocona

  does not appear to have been affected by this error.

- Fixed install procedure to not fail to install the shared

  library's symbolic links when updating an older installation.

- Updated kernel support: 2.4.21-20 (RHEL3), 2.4.28-pre3, 2.6.9-rc2.

Version 2.6.10-pre1, 2004-08-03

- x86-64 now uses the same driver and data structures as x86.

  Intel's 64-bit P4 Xeon should work in the x86-64 kernel.

  x86-64 application-level data structures have changed.

- Updated library and example applications to include P4

  support on x86-64.

- Fixed update-kernel script to use 'head' in a POSIX

  compliant way.

- Added kernel support for the Model 13 Pentium-M.

- Many code cleanups in the x86 driver.

- Event 0x76 is now officially CPU_CLK_UNHALTED on AMD64.

- Updated kernel support: 2.4.27-rc4.

Version 2.6.9, 2004-07-27

- Updated kernel support: 2.4.27-rc3, 2.6.7, 2.6.8-rc2,

  2.4.21-15.0.3 (RHEL3), 2.6.5-7.95 (SuSE).

- x86: enforce -fno-unit-at-a-time with gcc-3.4, to prevent

  kernel crashes due to stack overflow in 2.6 kernels < 2.6.6.

- x86: do sync_core() before rdtsc() in the internal micro-

  benchmarking code, to avoid bogus data on K8 processors.

- x86: prevent stray WRMSR at driver init time, which could

  disable the NMI watchdog or Oprofile.

- x86: prevent inlining from breaking code backpatching mechanism.

- x86: fix CONFIG_X86_LOCAL_APIC=n linkage error in init tests.

- PPC32: fix to allow 7400/7410 to specify MMCR2[THRESHMULT].

- PPC32: add support for generic processors using only the

  timebase register for high-resolution time measurements.

Version 2.6.8, 2004-05-29

- Added support for the IBM PowerPC 750GX processor.

- Updated kernel support: 2.4.27-pre3, 2.6.7-rc1, 2.6.7-rc1-mm1,

  2.4.21-15.EL (RHEL3), 2.6.5-1.358 (FC2).

- Fixed an error in the 2.4.21-193 SuSE kernel patch file which

  broke compilation on x86-64.

- Perfctr and Oprofile can now coexist safely in newer kernels,

  thanks to changes in kernel 2.6.6. Backported support for

  those changes from perfctr-2.7.1.

Version 2.6.7, 2004-05-04

- Merged several x86_64-specific driver files with their x86

  counterparts, reducing the amount of duplicated code.

- Added textual descriptions to the library's P6 event sets.

  From Bryan O'Sullivan.

- Changed examples/signal/signal to count retired instructions

  instead of retired micro-operations on AMD K7. Needed to avoid

  a loop with the same instruction overflowing indefinitely.

- Updated kernel support: 2.6.6-rc3, 2.4.27-pre1, 2.4.22-1.2188.nptl

  (FC1), 2.4.21-9.0.1 (RHEL3), 2.4.20-31.9 (RH9).

Version 2.6.6, 2004-02-21

- Pentium-M has an undocumented local APIC quirk which can stop

  perfctr interrupt delivery. Added workaround to prevent this.

- Fixed a bug in x86-64's perfctr interrupt entry code in 2.4 kernels.

  Luckily, the bug turned out to be harmless (a bogus "rip" value was

  retrieved, but never used by the higher-level interrupt handler).

- Added support for Pentium 4 Model 3 processors, which have slight

  event set changes from earlier models.

- Updated kernel support: 2.6.3, 2.4.25, 2.4.22-1.2174.nptl (FC1),

  2.4.20-30.9 (RH9), and 2.4.21-193 (SuSE). Removed support for some

  obsolete FC1 and RH update kernels.

Version 2.6.5, 2004-01-26

- Relaxed and corrected control checks on Pentium 4:

  * Allow ESCR.CPL_T1 to be non-zero when using global-mode

    counters on HT processors.

  * Don't require ESCR.CPL_T0 to be non-zero. CPL_T0==0b00

    is safe and potentially useful (global counters on HT).

  * Require CCCR.ACTIVE_THREAD==0b11 on non-HT processors, as

    documented in the IA32 Volume 3 manual. Old non-HT P4s

    seem to work Ok for all four values, but this is neither

    guaranteed nor useful.

- Per-process counters driver updated for filp->f_mapping

  change in 2.6.2-rc kernels.

- Support 2.4.21-9.EL (RHEL3) and 2.4.22-1.2149.nptl (FC1) kernels.

- Library updates for PowerPC:

  * Added cpu_type constants for struct perfctr_info.

  * Decode PVR and define perfctr_info.cpu_type accordingly.

  * Added event set descriptions for 604/604e/750.

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).

Version 2.6.3-pl1, 2004-01-01

- Updated kernel support: 2.6.1-rc1, 2.4.24-pre3,

  2.4.22-1.2135.nptl (FC1 update), 2.4.21-6.EL (RHEL Taroon

  beta update), and 2.4.20-27.x (RH 7.x/8.0/9 update).

- Moved the x86 performance counter interrupt handler code

  from the driver source to the kernel, via the patch kit.

  Needed to cope with changes in RedHat's 2.4.21-6.EL kernel.

  This change only affects 2.4.21 and later 2.4 kernels.

Version 2.6.3, 2003-12-21

- Fixed a bug where a read of the global-mode counters could

  fail with EOVERFLOW due to an incorrect structure descriptor.

  The bug only existed in perfctr-2.6.2.

  (Thanks to Pavel Machek for reporting this problem.)

- AMD64 IA32 emulation code cleaned up for kernel 2.4.23.

- Updated kernel support: 2.6.0, 2.4.24-pre1, 2.4.23,

  2.4.22-1.2129.nptl (FC1 update), 2.4.21-1.1931.2.393.ent

  (RHEL Taroon beta), and 2.4.20-24 (RH 7.x/8/9 update).

- User-space package rpm spec file fixes:

  * Don't remove /dev/perfctr on package uninstall.

  * Don't add alias to /etc/modules.conf if it's already there.

Version 2.6.2, 2003-11-23

- libperfctr.so is now installed with proper versioning.

- ABI control and info structures padded to accommodate some

  extensions without breaking application/library binary

  compatibility. ABI version incremented to '5'.

- Driver checks that only P4 models <= 2 use IQ_ESCR0/1.

- Added support for Fedora Core 1's 2.4.22-1.2115.nptl kernel.

- Driver compile fix for AMD64 in SMP 2.6 kernels.

Version 2.6.1, 2003-10-05

- Opening a process' virtual perfctrs is now done via

  /dev/perfctr instead of /proc/<pid>/perfctr. This is needed

  due to the changed semantics for /proc/self and /proc/<pid>/

  in kernel 2.6.0-test6. User-space is not affected since the

  perfctr-2.6 API and user-space library was prepared for

  this access method change.

  User-space code monitoring other processes should use

  gettid() to identify tasks in 2.6 kernels, since getpid()

  does the wrong thing for process threads.

- Driver cleanups from obsoleting 2.4.15 and older kernels.

- Made examples/global/global.c more robust.

- Simplified usage with 2.6 kernels: it's no longer necessary

  to add an 'alias' declaration in /etc/modprobe.conf.

- Added support for AMD K8 Revision C processors.

Version 2.6.0, 2003-09-08

- The driver now kills a process' performance counters if the

  process migrates to a forbidden CPU. This ensures that unsafe

  changes to a process' CPU affinity mask don't break the driver,

  the hardware state, or other processes. (This is an issue on

  hyper-threaded P4s only.)

- A bug fix in perfctr-2.6.0-pre3 broke compiling the driver

  non-modular in modular 2.4 kernels. Corrected that problem.

Version 2.6.0-pre5, 2003-08-31

- Disabled driver debug code which could printk() in the kernel's

  context-switch path, as that is disallowed.

- 2.4.16 is now the oldest supported kernel.

- Compilation fixes for driver's ia32 emulation code on x86-64.

Version 2.6.0-pre4, 2003-08-19

- Kernel/user-space API switched to a new "sparse marshalling"

  mechanism, which supports x86 application code on x86-64,

  and API struct extensions w/o breaking binary compatibility.

- Prepared the library for the future non-/proc/pid/perfctr API.

- Fixed a bug in the per-process perfctr creation code. The

  remote-control interface was racy in preemptible kernels.

- Fixed a bug in the process exit code for preemptible kernels.

- Changes to handle 2.6 kernels with the cpumask_t patch (-mm, -osdl):

  * Driver converted to use cpumask_t API, with compatibility wrapper

    for cpumask_t-free kernels.

  * API change: removed the cpus and cpus_forbidden sets from the

    perfctr_info struct, added new data type and commands for retrieving

    these sets. (cpumask_t values cannot be exported as-is since their

    sizes depend on kernel configuration, and the type definition uses

    'long' which breaks 32/64-bit binary compatibility.)

  * Updated library and example programs for the API change.

- Fixed a dependency bug in the library Makefile.

- Added support for VIA C3 Antaur/Nehemiah processors.

Version 2.6.0-pre3, 2003-08-03

- Replaced 'long' by 'int' in the API structures to eliminate

  unnecessary ABI incompatibilities between x86 and x86-64.

- Simplified global-mode perfctrs API: the write-control and

  read-state commands now operate on a single CPU instead of on

  a set of CPUs. Added a new start command to start the counters.

- Added thin library wrappers for per-process perfctr kernel calls.

  Cleaned up examples/perfex and the library itself.

- Removed the requirement that CCCR.ACTIVE_THREAD == 3 on P4.

- Extended cascading should now work on Pentium 4 Model 2 processors.

- Fixed a bug where the perfctr module's refcount could be zero with

  code still running in the module. This could race with rmmod in

  preemptive kernels, and in theory also in SMP kernels.

Version 2.6.0-pre2, 2003-07-13

- Per-process perfctrs API fixes: control data is retrieved using

  new READ_CONTROL operation, mmap()ed state no longer exposes the

  control data, the SAMPLE operation is renamed to READ_SUM and

  now updates a given user-space buffer, non-write operations are

  permitted on dead perfctrs.

  Retrieving control explicitly makes the user-visible mmap()ed

  state binary compatible between x86 and x86-64. The other changes

  simplify the user-space library and allow perfex to replace raw

  mmap() accesses with higher-level operations.

- Driver cleanups, including eliminating many #ifdefs and

  removing some unnecessary P4-specific driver procedures.

- Fixes for macro redefinition warnings in the 2.4.22-pre3 kernel.

- Perfctr library RPM spec file updates from Bryan O'Sullivan.

Version 2.6.0-pre1, 2003-07-02

- Rearranged the data structure holding the counter state to

  reduce the number of caches lines needed to be touched at key

  operations. The new representation is also binary compatible

  between x86 and x86-64, which matters since user-space mmaps() it.

- Added RPM spec file for the library. (From Bryan O'Sullivan).

- Patch kit updated for kernels 2.4.22-pre2 and 2.5.73.

Version 2.5.5, 2003-06-15

- Updates for driver model changes in kernel 2.5.71.

- Minor updates to the library's event descriptions for Pentium 4.

- Now supports SuSE's 2.4.19.SuSE-206 kernel for SLES 8 users.

  Autodetection of SuSE kernel versions is not yet implemented:

  pass "--patch=2.4.19.SuSE-206" to perfctr's update-kernel script

  to ensure that the correct patch is applied.

- Patch kit updates for 2.4.21 final and 2.4.20-18 RH kernels.

Version 2.5.4, 2003-06-01

- Corrected the driver's handling of OVF_PMI+FORCE_OVF counters

  on Pentium 4. This configuration didn't work at all, and

  lead to various BUG messages from the driver.

  These restrictions apply to OVF_PMI+FORCE_OVF counters:

  * The ireset value must be -1.

  * Once the counter has interrupted once, it will continue

    to interrupt when the faulting instruction is restarted,

    causing it to never complete. This problem also occurs

    for non-FORCE_OVF interrupt-mode counters if the ireset

    value is of too small magnitude, like -1.

    This appears to be a P4 hardware quirk. Don't restart

    FORCE_OVF interrupt-mode counters, and don't use ireset

    values too small to allow instructions to complete.

- Updated library's K8 event descriptions to match current

  documentation. Corrected several omissions and errors.

- Patch kit updated for kernels 2.5.70 and 2.4.21-rc6.

Version 2.5.3.1, 2003-05-21

- Patch kit updated for recent RedHat 6.2/7.x/8.0/9 update kernels

  (2.2.24-{6.2.3,7.0.3} and 2.4.20-13.{7,8,9}).

- Fixed a driver compile warning which occurred when the driver

  is built as a module in 2.4 SMP kernels using module versions.

- x86-64 now uses 'long long' for 64-bit sums, like x86. This

  reduces x86 and x86-64 user-space source code incompatibility.

Version 2.5.3, 2003-05-16

- Added support for the Pentium M processor. It is mostly like

  a Pentium III with some more events, except that six old

  Pentium III / Pentium Pro events have been redefined.

- Added support for K8 in 64-bit mode (the x86_64 kernel arch).

  Updated driver, user-space library, and example programs.

  The shared library libperfctr.so is now compiled with -fPIC.

- K8 bug fix in examples/signal/signal.c: a missing INT flag

  caused the driver to reject the control setup.

- P4 event descriptions updated from recent documentation changes.

Version 2.5.2, 2003-04-13

- Updated power management code for the local APIC and NMI

  watchdog driver model changes in kernel 2.5.67.

- Timer-based sampling of per-process performance counters is

  now always enabled: previously it was only done on SMP.

  Needed to avoid counter inaccuracies on high core-clock CPUs.

- Fixes to user-space library implementation of remote-control

  virtual performance counters: open() failed due to a missing

  return; avoid potential buffer overflow error; fix the "read

  counters" procedure for the case where the remote process is

  sampling the time-stamp counter but no performance counters.

- Added support for RedHat 9's 2.4.20-8 and 2.4.20-9 kernels.

Version 2.5.1, 2003-03-23

- Fixed initialisation on hyper-threading capable P4s in

  SMP kernels older than 2.4.15 to not signal an error if

  hyper-threading is disabled: in this case the absence of

  working set_cpus_allowed() support is not a problem.

- Fixed two compilation errors in the set_cpus_allowed()

  emulation affecting old 2.4 kernels configured for SMP.

- INSTALL file updates.

Version 2.5.0, 2003-03-10

- Added a simple user-space library API for accessing other

  processes' virtual performance counters. This uses a new

  type and a new set of operations since remote access has

  different requirements than accessing one's own counters.

  Following Mike Marty's suggestion, I left out the process

  control calls needed around these operations (ptrace() and

  wait()), so applications must handle that themselves.

- Added 'make install' support for the user-space components.

- Driver API cleanups. The 'eventsel_aux[]' array in 'struct

  perfctr_cpu_control' has been renamed as 'escr[]' and has been

  moved into the 'p4' sub-structure. (The change highlights the

  fact that this field was and is P4-only.) The 'version[]' string

  in 'struct perfctr_info' has been renamed to 'driver_version[]',

  since perfctr_info now also contains an 'abi_version' field.

  Some changes in the driver ABI: while not strictly necessary,

  they clean things up and make room for future changes. The ABI

  changed anyway from perfctr-2.4, so this shouldn't be a problem.

- Added a perfctr_cpu_control_print() procedure to the library,

  and updated the example programs to use it.

- Updated the perfex example program's help text to describe the

  syntax and meaning of event specifiers.

- Patch kit updates for 2.2.24/2.4.18-26(RedHat)/2.5.64 kernels.

Version 2.5.0-pre2, 2003-03-03

- Added a way for user-space to query the driver's ABI version,

  and updated the library to check it.

- Fixed <linux/perfctr.h> to not include <asm/perfctr.h> when

  perfctr hasn't been configured. This allows the patched kernel

  source to compile cleanly also in archs not supported by perfctr.

- Major patch kit overhaul. Updated configuration help texts.

  Removed unnecessary features and patches. Some cleanups. Added

  aliasing support to the 'update-kernel' script, which allows a

  patch to serve several kernels (when applicable).

- The perfctr configuration option was poorly placed. It is now

  at the end of the "Processor type and features" menu.

- Removed "notsc" kernel option support from the 2.2 kernel patches.

  To use the driver with an IDT WinChip (Centaur C6/2/3) CPU now

  requires a newer kernel with native "notsc" support.

- Driver fixes for changes in the 2.4.21-pre5 and 2.5.63 kernels.

Version 2.5.0-pre1, 2003-02-19

- Fixed the driver's API to support global-mode perfctrs on 2.5

  SMP kernels and asymmetric hyper-threaded P4 multiprocessors.

  Updated examples/global/global.c for the new API.

- Minor library cleanups. Updated example programs accordingly.

- API cleanup: Removed obsolete STOP command from the driver

  for virtual perfctrs. The library now uses CONTROL instead.

- Proper detection and support for AMD K8 processors. They are

  similar to the K7s, but the event sets are not identical.

- The library's event set descriptions have been redesigned and

  expanded to include unit mask descriptions and descriptions of

  Intel P4 and AMD K8 events. The etc/perfctr-events.tab text file

  has been removed since event_codes.h now is generated from the

  library's data structures.

Version 2.4.5, 2003-02-09

- Corrected the unit mask definition for the K7 SYSTEM_REQUEST_TYPE

  event in etc/perfctr-events.tab: WC is 0x02 not 0x04.

- Fixed two compile warnings which could be triggered in 2.5 kernels.

- Patch kit updates for 2.4.21-pre4/2.4.18-24(RedHat)/2.5.59-osdl2 kernels.

Version 2.4.4, 2003-01-18

- Fixed a context-switch bug where an interrupt-mode counter could

  increment unexpectedly, and also miss the overflow interrupt.

- Fixed some ugly log messages the new HT P4 support code added

  in perfctr-2.4.3 could generate at driver initialisation time.

- Added preliminary support for AMD K8 processors with the

  regular 32-bit x86 kernel. The K8 performance counters appear

  to be identical or very similar to the K7 performance counters.

Version 2.4.3, 2002-12-11

- Support for hyper-threaded Pentium 4s added. In a HT P4, the

  two logical processors share the performance counter state.

  HT P4s are therefore _asymmetric_ multi-processors, and the

  driver enforces CPU affinity masks on users of per-process

  performance counters to avoid resource conflicts. (Users are

  restricted to logical processor #0 in each physical CPU.)

  Limitations:

  * The kernel mechanism for updating a process' CPU affinity

    mask uses no or very weak locking, which makes certain race

    conditions possible that can break the driver's CPU affinity

    mask restrictions. For now, users should NOT use the

    sched_setaffinity() system call on processes using per-process

    performance counters.

  * Global-mode performance counters don't work on HT P4s due to

    limitations in the API. This will be fixed in perfctr-2.5.

  * 2.2 kernels don't have CPU affinity masks, and therefore can't

    support HT P4s.

Version 2.4.2, 2002-11-25

- Fixed a driver bug where it could fail to prevent simultaneous

  use of global-mode and per-process performance counters.

- Made the driver safe for preemptible 2.5 kernels.

- New patches for RedHat update kernels 2.2.22-6.2.2, 2.2.22-7.0.2,

  2.4.18-18.7.x, and 2.4.18-18.8.0.

Version 2.4.1, 2002-10-12

- Support RedHat 8.0's 2.4.18-14 kernel. Building perfctr as

  a module caused a namespace clash in this kernel. The fix

  required a change to the driver's kernel-resident glue code.

Version 2.4.0, 2002-09-26

- Fixed an overly strict access control check which prevented

  opening another process' /proc/<pid>/perfctr when the driver

  was built as a module.

- Updates for kernels 2.2.22, 2.4.18-10-redhat, 2.4.20-pre8, 2.5.36.

Version 2.4.0-pre2, 2002-08-27

- vperfctr_control() now allows the user to specify that some PMC

  sums are not to be cleared when updating the control.

  There is a new bitmap field `preserve' in struct vperfctr_control:

  if bit i is set then PMC(i)'s sum is not cleared.

  `preserve' is a simple `unsigned long' for now, since this type

  fits all currently known CPU types.

  This change breaks binary compatibility, but user-space code which

  clears the entire control record before filling in relevant fields

  will continue to work as before after a recompile.

  This feature removes a limitation which some people felt was a

  problem for some usage scenarios.

Version 2.4.0-pre1, 2002-08-12

- The kernel driver has an initial implementation of a new

  remote-control API for virtual per-process perfctrs.

  A monitor process may access a target process' perfctrs via

  open(), mmap(), and ioctl() on the target's /proc/pid/perfctr.

  For open() and ioctl(), the monitor must hold the target under

  ptrace ATTACH control. The user-space library and examples have

  not been updated for the new API.

Version 2.3.12, 2002-08-12

- Updated patch kit for the 2.4.19 final kernel.

- Spelling fix in INSTALL.

- Minor driver code size reduction on uniprocessor kernels.

Version 2.3.11, 2002-07-21

- Interrupt-mode performance counters now have accumulated sums.

  The library procedures vperfctr_read_pmc() and vperfctr_read_ctrs()

  can now retrieve the sums of interrupt-mode counters.

- Corrected the name of K7 event 0x42 to DATA_CACHE_REFILLS_FROM_L2.

Version 2.3.10, 2002-07-19

- Added a script, `update-kernel', to simplify the process of

  patching the kernel source code. See INSTALL for details.

- The counter and control registers are now cleared when the

  driver is idle. This should allow the counter hardware to

  power down when not used, especially on P4.

- Some Pentium MMX and Pentium Pro processors have an erratum

  which causes System Management Mode to shut down if user-space

  has been granted access to the RDPMC instruction. The driver

  now avoids granting RDPMC access on the affected processors.

  The user-space library makes this change transparent.

- New CPU type code for Model 2 Pentium 4s, due to a few but

  significant changes between Model 0 and 1 and Model 2 CPUs.  

- The driver now supports Replay Tagging on the Pentium 4.

  The perfex program has been updated to allow users to specify

  values to store in PEBS_ENABLE and PEBS_MATRIX_VERT.

  For example, the following command could be use to count the

  number of L1 cache read misses on a Pentium 4:

  perfex -e 0x0003B000/0x12000204@0x8000000C --p4pe=0x01000001 --p4pmv=0x1 some_program

  Explanation: IQ_CCCR0 is bound to CRU_ESCR2, CRU_ESCR2 is set up

  for replay_event with non-bogus uops and CPL>0, and PEBS_ENABLE

  and PEBS_MATRIX_VERT are set up for the 1stL_cache_load_miss_retired

  metric. Note that bit 25 is NOT set in PEBS_ENABLE.

Version 2.3.9, 2002-06-27

- Pentium 4 bug fix: An error in older revisions of Intel's IA32

  Volume 3 manual caused the driver to program the wrong control

  register in a few cases, affecting uses of the uop_type event.

  Revision -007 of Intel document #245472 corrects the error,

  and the driver has been updated accordingly.

Version 2.3.8.1, 2002-06-27

- Regenerated the patch file for RedHat's 2.4.18-5 kernel. The

  patch file in 2.3.8 only contained an error message from 'diff'.

Version 2.3.8, 2002-06-26

- Added counter overflow interrupt support for Intel P4.

- New kernel support: standard kernels 2.2.21 and 2.4.19-rc1,

  and RedHat kernels 2.2.19-7.0.16, 2.4.9-34, and 2.4.18-5.

- API changes: Removed unused and obsolete fields from the vperfctr

  state and control objects. Added fields to perfctr_cpu_control