#
1.28 |
|
17-Sep-2023 |
cheloha |
clockintr: remove clockintr_init(), clockintr_flags
All the state initialization once done in clockintr_init() has been moved to other parts of the kernel. It's a dead function. Remove it.
Likewise, the clockintr_flags variable no longer sports any meaningful flags. Remove it. This frees up the CL_* flag namespace, which might be useful to the clockintr frontend if we ever need to add behavior flags to any of those functions.
|
#
1.27 |
|
14-Sep-2023 |
cheloha |
clockintr: replace CL_RNDSTAT with global variable statclock_is_randomized
In order to separate the statclock from the clock interrupt subsystem we need to move all statclock state out into the broader kernel.
Start by replacing the CL_RNDSTAT flag with a new global variable, "statclock_is_randomized", in kern_clock.c. Update all clockintr_init() callers to set the boolean instead of passing the flag.
Thread: https://marc.info/?l=openbsd-tech&m=169428749720476&w=2
|
#
1.26 |
|
23-Aug-2023 |
cheloha |
all platforms: separate cpu_initclocks() from cpu_startclock()
To give the primary CPU an opportunity to perform clock interrupt preparation in a machine-independent manner we need to separate the "initialization" parts of cpu_initclocks() from the "start the clock interrupt" parts. Currently, cpu_initclocks() does everything all at once, so there is no space for this MI setup.
Many platforms have more-or-less already done this separation by implementing a separate routine named "cpu_startclock()". This patch promotes cpu_startclock() from de facto standard to mandatory API.
- Prototype cpu_startclock() in sys/systm.h alongside cpu_initclocks(). The separation of responsibility between the two routines is a bit fuzzy but the basic guidelines are as follows:
+ cpu_initclocks() must initialize hz, stathz, and profhz, and call clockintr_init().
+ cpu_startclock() must call clockintr_cpu_init() and start the clock interrupt cycle on the calling CPU.
These guidelines will shift in the future, but that's the way things stand as of *this* commit.
- In initclocks(): first call cpu_initclocks(), then do MI setup, and last call cpu_startclock().
- On platforms where cpu_startclock() already exists: don't call cpu_startclock() from cpu_initclocks() anymore.
- On platforms where cpu_startclock() doesn't yet exist: implement it. Usually this is as simple as dividing cpu_initclocks() in two.
Tested on amd64 (i8254, lapic), arm64, i386 (i8254, lapic), macppc, mips64/octeon, and sparc64. Tested on arm/armv7 (agtimer(4)) by phessler@ and jmatthew@. Tested on m88k/luna88k by aoyama@. Tested on powerpc64 by gkoehler@ and mlarkin@. Tested on riscv64 by jmatthew@.
Thread: https://marc.info/?l=openbsd-tech&m=169195251322149&w=2
|
#
1.25 |
|
11-Aug-2023 |
cheloha |
agtimer(4/arm64): call CPU_BUSY_CYCLE() during spin-loop
For consistency with other delay(9) implementations, agtimer(4/arm64) ought to call CPU_BUSY_CYCLE() as it spins.
kettenis@ notes that we could reduce the power consumed in agtimer_delay() by enabling CNTKCTL_EL1.EVNTEN and configuring ENTKCTL_EL1.EVNTI.
kettenis@ also notes that Armv8.7 adds FEAT_WFxT, which will, when the feature appears in real hardware, make it even easier to save power in agtimer_delay().
With input from drahn@ and kettenis@.
Thread: https://marc.info/?l=openbsd-tech&m=169146193022516&w=2
ok kettenis@
|
#
1.24 |
|
10-Aug-2023 |
cheloha |
agtimer(4/arm64): agtimer_delay: compute cycle count with 64-bit arithmetic
Converting from microseconds to timer cycles is much simpler with 64-bit arithmetic.
Thread: https://marc.info/?l=openbsd-tech&m=169146193022516&w=2
ok drahn@ kettenis@
|
#
1.23 |
|
25-Jul-2023 |
cheloha |
statclock: move profil(2), GPROF code to profclock(), gmonclock()
This patch isolates profil(2) and GPROF from statclock(). Currently, statclock() implements both profil(2) and GPROF through a complex mechanism involving both platform code (setstatclockrate) and the scheduler (pscnt, psdiv, and psratio). We have a machine-independent interface to the clock interrupt hardware now, so we no longer need to do it this way.
- Move profil(2)-specific code from statclock() to a new clock interrupt callback, profclock(), in subr_prof.c. Each schedstate_percpu has its own profclock handle. The profclock is enabled/disabled for a given CPU when it is needed by the running thread during mi_switch() and sched_exit().
- Move GPROF-specific code from statclock() to a new clock interrupt callback, gmonclock(), in subr_prof.c. Where available, each cpu_info has its own gmonclock handle . The gmonclock is enabled/disabled for a given CPU via sysctl(2) in prof_state_toggle().
- Both profclock() and gmonclock() have a fixed period, profclock_period, that is initialized during initclocks().
- Export clockintr_advance(), clockintr_cancel(), clockintr_establish(), and clockintr_stagger() via <sys/clockintr.h>. They have external callers now.
- Delete pscnt, psdiv, psratio. From schedstate_percpu, also delete spc_pscnt and spc_psdiv. The statclock frequency is not dynamic anymore so these variables are now useless.
- Delete code/state related to the dynamic statclock frequency from kern_clockintr.c. The statclock frequency can still be pseudo-random, so move the contents of clockintr_statvar_init() into clockintr_init().
With input from miod@, deraadt@, and claudio@. Early revisions cleaned up by claudio. Early revisions tested by claudio@. Tested by cheloha@ on amd64, arm64, macppc, octeon, and sparc64 (sun4v). Compile- and boot- tested on i386 by mlarkin@. riscv64 compilation bugs found by mlarkin@. Tested on riscv64 by jca@. Tested on powerpc64 by gkoehler@.
|
Revision tags: OPENBSD_7_3_BASE
|
#
1.22 |
|
04-Feb-2023 |
cheloha |
timecounting: remove incomplete PPS support
The timecounting code has had stubs for pulse-per-second (PPS) polling since it was imported in 2004. At this point it seems unlikely that anyone is going to finish adding PPS support, so let's remove the stubs:
- Delete the dead tc_poll_pps() call from tc_windup(). - Remove all tc_poll_pps symbols from the kernel.
Link: https://marc.info/?l=openbsd-tech&m=167519035723210&w=2
ok miod@
|
#
1.21 |
|
09-Jan-2023 |
kettenis |
Allwinner hardware sucks! The ARM generic timer on the A64 has a bug where the bottom 9 bits of the counter register can't be trusted if any of the higher bits are rolling over. This is an unpublished errata so the details aren't known. Adopt the same workaround that Linux has.
This will disable the userland timecounter support on hardware affected by the hardware. We will need a similar workaround in libc to restore that functionality.
tested by semarie@ ok cheloha@
|
#
1.20 |
|
08-Nov-2022 |
cheloha |
arm64: switch to clockintr(9)
Switch arm64 to the clockintr(9) subsystem.
- Remove the custom per-CPU clock interrupt schedule from agtimer(4). - Remove the custom randomized statclock() pieces from agtimer(4). - Add agtimer_rearm(), agtimer_trigger(), and wire up agtimer_intrclock.
There is one wart:
- The AArch64 spec says that a value written to CNTV_TVAL_EL0 is "treated as a signed 32-bit integer" [1]. kettenis@ doesn't know what to make of this. I'm capping the value at INT32_MAX for now. It's possible I am misreading this, though.
Tested by kettenis@ on his Apple M1 mini. Tested by me on my Raspberry Pi 4B.
Link: https://marc.info/?l=openbsd-tech&m=166776342503304&w=2
[1] "Arm Architecture Reference Manual for A-profile architecture" issue I.a, section D17.11.27 ("CNTV_TVAL_EL0").
ok kettenis@
|
Revision tags: OPENBSD_7_1_BASE OPENBSD_7_2_BASE
|
#
1.19 |
|
24-Oct-2021 |
mpi |
Constify struct cfattach.
ok visa@ a long time ago, ok patrick@
|
Revision tags: OPENBSD_6_9_BASE OPENBSD_7_0_BASE
|
#
1.18 |
|
11-Mar-2021 |
jsg |
spelling
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.27 |
|
14-Sep-2023 |
cheloha |
clockintr: replace CL_RNDSTAT with global variable statclock_is_randomized
In order to separate the statclock from the clock interrupt subsystem we need to move all statclock state out into the broader kernel.
Start by replacing the CL_RNDSTAT flag with a new global variable, "statclock_is_randomized", in kern_clock.c. Update all clockintr_init() callers to set the boolean instead of passing the flag.
Thread: https://marc.info/?l=openbsd-tech&m=169428749720476&w=2
|
#
1.26 |
|
23-Aug-2023 |
cheloha |
all platforms: separate cpu_initclocks() from cpu_startclock()
To give the primary CPU an opportunity to perform clock interrupt preparation in a machine-independent manner we need to separate the "initialization" parts of cpu_initclocks() from the "start the clock interrupt" parts. Currently, cpu_initclocks() does everything all at once, so there is no space for this MI setup.
Many platforms have more-or-less already done this separation by implementing a separate routine named "cpu_startclock()". This patch promotes cpu_startclock() from de facto standard to mandatory API.
- Prototype cpu_startclock() in sys/systm.h alongside cpu_initclocks(). The separation of responsibility between the two routines is a bit fuzzy but the basic guidelines are as follows:
+ cpu_initclocks() must initialize hz, stathz, and profhz, and call clockintr_init().
+ cpu_startclock() must call clockintr_cpu_init() and start the clock interrupt cycle on the calling CPU.
These guidelines will shift in the future, but that's the way things stand as of *this* commit.
- In initclocks(): first call cpu_initclocks(), then do MI setup, and last call cpu_startclock().
- On platforms where cpu_startclock() already exists: don't call cpu_startclock() from cpu_initclocks() anymore.
- On platforms where cpu_startclock() doesn't yet exist: implement it. Usually this is as simple as dividing cpu_initclocks() in two.
Tested on amd64 (i8254, lapic), arm64, i386 (i8254, lapic), macppc, mips64/octeon, and sparc64. Tested on arm/armv7 (agtimer(4)) by phessler@ and jmatthew@. Tested on m88k/luna88k by aoyama@. Tested on powerpc64 by gkoehler@ and mlarkin@. Tested on riscv64 by jmatthew@.
Thread: https://marc.info/?l=openbsd-tech&m=169195251322149&w=2
|
#
1.25 |
|
11-Aug-2023 |
cheloha |
agtimer(4/arm64): call CPU_BUSY_CYCLE() during spin-loop
For consistency with other delay(9) implementations, agtimer(4/arm64) ought to call CPU_BUSY_CYCLE() as it spins.
kettenis@ notes that we could reduce the power consumed in agtimer_delay() by enabling CNTKCTL_EL1.EVNTEN and configuring ENTKCTL_EL1.EVNTI.
kettenis@ also notes that Armv8.7 adds FEAT_WFxT, which will, when the feature appears in real hardware, make it even easier to save power in agtimer_delay().
With input from drahn@ and kettenis@.
Thread: https://marc.info/?l=openbsd-tech&m=169146193022516&w=2
ok kettenis@
|
#
1.24 |
|
10-Aug-2023 |
cheloha |
agtimer(4/arm64): agtimer_delay: compute cycle count with 64-bit arithmetic
Converting from microseconds to timer cycles is much simpler with 64-bit arithmetic.
Thread: https://marc.info/?l=openbsd-tech&m=169146193022516&w=2
ok drahn@ kettenis@
|
#
1.23 |
|
25-Jul-2023 |
cheloha |
statclock: move profil(2), GPROF code to profclock(), gmonclock()
This patch isolates profil(2) and GPROF from statclock(). Currently, statclock() implements both profil(2) and GPROF through a complex mechanism involving both platform code (setstatclockrate) and the scheduler (pscnt, psdiv, and psratio). We have a machine-independent interface to the clock interrupt hardware now, so we no longer need to do it this way.
- Move profil(2)-specific code from statclock() to a new clock interrupt callback, profclock(), in subr_prof.c. Each schedstate_percpu has its own profclock handle. The profclock is enabled/disabled for a given CPU when it is needed by the running thread during mi_switch() and sched_exit().
- Move GPROF-specific code from statclock() to a new clock interrupt callback, gmonclock(), in subr_prof.c. Where available, each cpu_info has its own gmonclock handle . The gmonclock is enabled/disabled for a given CPU via sysctl(2) in prof_state_toggle().
- Both profclock() and gmonclock() have a fixed period, profclock_period, that is initialized during initclocks().
- Export clockintr_advance(), clockintr_cancel(), clockintr_establish(), and clockintr_stagger() via <sys/clockintr.h>. They have external callers now.
- Delete pscnt, psdiv, psratio. From schedstate_percpu, also delete spc_pscnt and spc_psdiv. The statclock frequency is not dynamic anymore so these variables are now useless.
- Delete code/state related to the dynamic statclock frequency from kern_clockintr.c. The statclock frequency can still be pseudo-random, so move the contents of clockintr_statvar_init() into clockintr_init().
With input from miod@, deraadt@, and claudio@. Early revisions cleaned up by claudio. Early revisions tested by claudio@. Tested by cheloha@ on amd64, arm64, macppc, octeon, and sparc64 (sun4v). Compile- and boot- tested on i386 by mlarkin@. riscv64 compilation bugs found by mlarkin@. Tested on riscv64 by jca@. Tested on powerpc64 by gkoehler@.
|
Revision tags: OPENBSD_7_3_BASE
|
#
1.22 |
|
04-Feb-2023 |
cheloha |
timecounting: remove incomplete PPS support
The timecounting code has had stubs for pulse-per-second (PPS) polling since it was imported in 2004. At this point it seems unlikely that anyone is going to finish adding PPS support, so let's remove the stubs:
- Delete the dead tc_poll_pps() call from tc_windup(). - Remove all tc_poll_pps symbols from the kernel.
Link: https://marc.info/?l=openbsd-tech&m=167519035723210&w=2
ok miod@
|
#
1.21 |
|
09-Jan-2023 |
kettenis |
Allwinner hardware sucks! The ARM generic timer on the A64 has a bug where the bottom 9 bits of the counter register can't be trusted if any of the higher bits are rolling over. This is an unpublished errata so the details aren't known. Adopt the same workaround that Linux has.
This will disable the userland timecounter support on hardware affected by the hardware. We will need a similar workaround in libc to restore that functionality.
tested by semarie@ ok cheloha@
|
#
1.20 |
|
08-Nov-2022 |
cheloha |
arm64: switch to clockintr(9)
Switch arm64 to the clockintr(9) subsystem.
- Remove the custom per-CPU clock interrupt schedule from agtimer(4). - Remove the custom randomized statclock() pieces from agtimer(4). - Add agtimer_rearm(), agtimer_trigger(), and wire up agtimer_intrclock.
There is one wart:
- The AArch64 spec says that a value written to CNTV_TVAL_EL0 is "treated as a signed 32-bit integer" [1]. kettenis@ doesn't know what to make of this. I'm capping the value at INT32_MAX for now. It's possible I am misreading this, though.
Tested by kettenis@ on his Apple M1 mini. Tested by me on my Raspberry Pi 4B.
Link: https://marc.info/?l=openbsd-tech&m=166776342503304&w=2
[1] "Arm Architecture Reference Manual for A-profile architecture" issue I.a, section D17.11.27 ("CNTV_TVAL_EL0").
ok kettenis@
|
Revision tags: OPENBSD_7_1_BASE OPENBSD_7_2_BASE
|
#
1.19 |
|
24-Oct-2021 |
mpi |
Constify struct cfattach.
ok visa@ a long time ago, ok patrick@
|
Revision tags: OPENBSD_6_9_BASE OPENBSD_7_0_BASE
|
#
1.18 |
|
11-Mar-2021 |
jsg |
spelling
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.26 |
|
23-Aug-2023 |
cheloha |
all platforms: separate cpu_initclocks() from cpu_startclock()
To give the primary CPU an opportunity to perform clock interrupt preparation in a machine-independent manner we need to separate the "initialization" parts of cpu_initclocks() from the "start the clock interrupt" parts. Currently, cpu_initclocks() does everything all at once, so there is no space for this MI setup.
Many platforms have more-or-less already done this separation by implementing a separate routine named "cpu_startclock()". This patch promotes cpu_startclock() from de facto standard to mandatory API.
- Prototype cpu_startclock() in sys/systm.h alongside cpu_initclocks(). The separation of responsibility between the two routines is a bit fuzzy but the basic guidelines are as follows:
+ cpu_initclocks() must initialize hz, stathz, and profhz, and call clockintr_init().
+ cpu_startclock() must call clockintr_cpu_init() and start the clock interrupt cycle on the calling CPU.
These guidelines will shift in the future, but that's the way things stand as of *this* commit.
- In initclocks(): first call cpu_initclocks(), then do MI setup, and last call cpu_startclock().
- On platforms where cpu_startclock() already exists: don't call cpu_startclock() from cpu_initclocks() anymore.
- On platforms where cpu_startclock() doesn't yet exist: implement it. Usually this is as simple as dividing cpu_initclocks() in two.
Tested on amd64 (i8254, lapic), arm64, i386 (i8254, lapic), macppc, mips64/octeon, and sparc64. Tested on arm/armv7 (agtimer(4)) by phessler@ and jmatthew@. Tested on m88k/luna88k by aoyama@. Tested on powerpc64 by gkoehler@ and mlarkin@. Tested on riscv64 by jmatthew@.
Thread: https://marc.info/?l=openbsd-tech&m=169195251322149&w=2
|
#
1.25 |
|
11-Aug-2023 |
cheloha |
agtimer(4/arm64): call CPU_BUSY_CYCLE() during spin-loop
For consistency with other delay(9) implementations, agtimer(4/arm64) ought to call CPU_BUSY_CYCLE() as it spins.
kettenis@ notes that we could reduce the power consumed in agtimer_delay() by enabling CNTKCTL_EL1.EVNTEN and configuring ENTKCTL_EL1.EVNTI.
kettenis@ also notes that Armv8.7 adds FEAT_WFxT, which will, when the feature appears in real hardware, make it even easier to save power in agtimer_delay().
With input from drahn@ and kettenis@.
Thread: https://marc.info/?l=openbsd-tech&m=169146193022516&w=2
ok kettenis@
|
#
1.24 |
|
10-Aug-2023 |
cheloha |
agtimer(4/arm64): agtimer_delay: compute cycle count with 64-bit arithmetic
Converting from microseconds to timer cycles is much simpler with 64-bit arithmetic.
Thread: https://marc.info/?l=openbsd-tech&m=169146193022516&w=2
ok drahn@ kettenis@
|
#
1.23 |
|
25-Jul-2023 |
cheloha |
statclock: move profil(2), GPROF code to profclock(), gmonclock()
This patch isolates profil(2) and GPROF from statclock(). Currently, statclock() implements both profil(2) and GPROF through a complex mechanism involving both platform code (setstatclockrate) and the scheduler (pscnt, psdiv, and psratio). We have a machine-independent interface to the clock interrupt hardware now, so we no longer need to do it this way.
- Move profil(2)-specific code from statclock() to a new clock interrupt callback, profclock(), in subr_prof.c. Each schedstate_percpu has its own profclock handle. The profclock is enabled/disabled for a given CPU when it is needed by the running thread during mi_switch() and sched_exit().
- Move GPROF-specific code from statclock() to a new clock interrupt callback, gmonclock(), in subr_prof.c. Where available, each cpu_info has its own gmonclock handle . The gmonclock is enabled/disabled for a given CPU via sysctl(2) in prof_state_toggle().
- Both profclock() and gmonclock() have a fixed period, profclock_period, that is initialized during initclocks().
- Export clockintr_advance(), clockintr_cancel(), clockintr_establish(), and clockintr_stagger() via <sys/clockintr.h>. They have external callers now.
- Delete pscnt, psdiv, psratio. From schedstate_percpu, also delete spc_pscnt and spc_psdiv. The statclock frequency is not dynamic anymore so these variables are now useless.
- Delete code/state related to the dynamic statclock frequency from kern_clockintr.c. The statclock frequency can still be pseudo-random, so move the contents of clockintr_statvar_init() into clockintr_init().
With input from miod@, deraadt@, and claudio@. Early revisions cleaned up by claudio. Early revisions tested by claudio@. Tested by cheloha@ on amd64, arm64, macppc, octeon, and sparc64 (sun4v). Compile- and boot- tested on i386 by mlarkin@. riscv64 compilation bugs found by mlarkin@. Tested on riscv64 by jca@. Tested on powerpc64 by gkoehler@.
|
Revision tags: OPENBSD_7_3_BASE
|
#
1.22 |
|
04-Feb-2023 |
cheloha |
timecounting: remove incomplete PPS support
The timecounting code has had stubs for pulse-per-second (PPS) polling since it was imported in 2004. At this point it seems unlikely that anyone is going to finish adding PPS support, so let's remove the stubs:
- Delete the dead tc_poll_pps() call from tc_windup(). - Remove all tc_poll_pps symbols from the kernel.
Link: https://marc.info/?l=openbsd-tech&m=167519035723210&w=2
ok miod@
|
#
1.21 |
|
09-Jan-2023 |
kettenis |
Allwinner hardware sucks! The ARM generic timer on the A64 has a bug where the bottom 9 bits of the counter register can't be trusted if any of the higher bits are rolling over. This is an unpublished errata so the details aren't known. Adopt the same workaround that Linux has.
This will disable the userland timecounter support on hardware affected by the hardware. We will need a similar workaround in libc to restore that functionality.
tested by semarie@ ok cheloha@
|
#
1.20 |
|
08-Nov-2022 |
cheloha |
arm64: switch to clockintr(9)
Switch arm64 to the clockintr(9) subsystem.
- Remove the custom per-CPU clock interrupt schedule from agtimer(4). - Remove the custom randomized statclock() pieces from agtimer(4). - Add agtimer_rearm(), agtimer_trigger(), and wire up agtimer_intrclock.
There is one wart:
- The AArch64 spec says that a value written to CNTV_TVAL_EL0 is "treated as a signed 32-bit integer" [1]. kettenis@ doesn't know what to make of this. I'm capping the value at INT32_MAX for now. It's possible I am misreading this, though.
Tested by kettenis@ on his Apple M1 mini. Tested by me on my Raspberry Pi 4B.
Link: https://marc.info/?l=openbsd-tech&m=166776342503304&w=2
[1] "Arm Architecture Reference Manual for A-profile architecture" issue I.a, section D17.11.27 ("CNTV_TVAL_EL0").
ok kettenis@
|
Revision tags: OPENBSD_7_1_BASE OPENBSD_7_2_BASE
|
#
1.19 |
|
24-Oct-2021 |
mpi |
Constify struct cfattach.
ok visa@ a long time ago, ok patrick@
|
Revision tags: OPENBSD_6_9_BASE OPENBSD_7_0_BASE
|
#
1.18 |
|
11-Mar-2021 |
jsg |
spelling
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.25 |
|
11-Aug-2023 |
cheloha |
agtimer(4/arm64): call CPU_BUSY_CYCLE() during spin-loop
For consistency with other delay(9) implementations, agtimer(4/arm64) ought to call CPU_BUSY_CYCLE() as it spins.
kettenis@ notes that we could reduce the power consumed in agtimer_delay() by enabling CNTKCTL_EL1.EVNTEN and configuring ENTKCTL_EL1.EVNTI.
kettenis@ also notes that Armv8.7 adds FEAT_WFxT, which will, when the feature appears in real hardware, make it even easier to save power in agtimer_delay().
With input from drahn@ and kettenis@.
Thread: https://marc.info/?l=openbsd-tech&m=169146193022516&w=2
ok kettenis@
|
#
1.24 |
|
10-Aug-2023 |
cheloha |
agtimer(4/arm64): agtimer_delay: compute cycle count with 64-bit arithmetic
Converting from microseconds to timer cycles is much simpler with 64-bit arithmetic.
Thread: https://marc.info/?l=openbsd-tech&m=169146193022516&w=2
ok drahn@ kettenis@
|
#
1.23 |
|
25-Jul-2023 |
cheloha |
statclock: move profil(2), GPROF code to profclock(), gmonclock()
This patch isolates profil(2) and GPROF from statclock(). Currently, statclock() implements both profil(2) and GPROF through a complex mechanism involving both platform code (setstatclockrate) and the scheduler (pscnt, psdiv, and psratio). We have a machine-independent interface to the clock interrupt hardware now, so we no longer need to do it this way.
- Move profil(2)-specific code from statclock() to a new clock interrupt callback, profclock(), in subr_prof.c. Each schedstate_percpu has its own profclock handle. The profclock is enabled/disabled for a given CPU when it is needed by the running thread during mi_switch() and sched_exit().
- Move GPROF-specific code from statclock() to a new clock interrupt callback, gmonclock(), in subr_prof.c. Where available, each cpu_info has its own gmonclock handle . The gmonclock is enabled/disabled for a given CPU via sysctl(2) in prof_state_toggle().
- Both profclock() and gmonclock() have a fixed period, profclock_period, that is initialized during initclocks().
- Export clockintr_advance(), clockintr_cancel(), clockintr_establish(), and clockintr_stagger() via <sys/clockintr.h>. They have external callers now.
- Delete pscnt, psdiv, psratio. From schedstate_percpu, also delete spc_pscnt and spc_psdiv. The statclock frequency is not dynamic anymore so these variables are now useless.
- Delete code/state related to the dynamic statclock frequency from kern_clockintr.c. The statclock frequency can still be pseudo-random, so move the contents of clockintr_statvar_init() into clockintr_init().
With input from miod@, deraadt@, and claudio@. Early revisions cleaned up by claudio. Early revisions tested by claudio@. Tested by cheloha@ on amd64, arm64, macppc, octeon, and sparc64 (sun4v). Compile- and boot- tested on i386 by mlarkin@. riscv64 compilation bugs found by mlarkin@. Tested on riscv64 by jca@. Tested on powerpc64 by gkoehler@.
|
Revision tags: OPENBSD_7_3_BASE
|
#
1.22 |
|
04-Feb-2023 |
cheloha |
timecounting: remove incomplete PPS support
The timecounting code has had stubs for pulse-per-second (PPS) polling since it was imported in 2004. At this point it seems unlikely that anyone is going to finish adding PPS support, so let's remove the stubs:
- Delete the dead tc_poll_pps() call from tc_windup(). - Remove all tc_poll_pps symbols from the kernel.
Link: https://marc.info/?l=openbsd-tech&m=167519035723210&w=2
ok miod@
|
#
1.21 |
|
09-Jan-2023 |
kettenis |
Allwinner hardware sucks! The ARM generic timer on the A64 has a bug where the bottom 9 bits of the counter register can't be trusted if any of the higher bits are rolling over. This is an unpublished errata so the details aren't known. Adopt the same workaround that Linux has.
This will disable the userland timecounter support on hardware affected by the hardware. We will need a similar workaround in libc to restore that functionality.
tested by semarie@ ok cheloha@
|
#
1.20 |
|
08-Nov-2022 |
cheloha |
arm64: switch to clockintr(9)
Switch arm64 to the clockintr(9) subsystem.
- Remove the custom per-CPU clock interrupt schedule from agtimer(4). - Remove the custom randomized statclock() pieces from agtimer(4). - Add agtimer_rearm(), agtimer_trigger(), and wire up agtimer_intrclock.
There is one wart:
- The AArch64 spec says that a value written to CNTV_TVAL_EL0 is "treated as a signed 32-bit integer" [1]. kettenis@ doesn't know what to make of this. I'm capping the value at INT32_MAX for now. It's possible I am misreading this, though.
Tested by kettenis@ on his Apple M1 mini. Tested by me on my Raspberry Pi 4B.
Link: https://marc.info/?l=openbsd-tech&m=166776342503304&w=2
[1] "Arm Architecture Reference Manual for A-profile architecture" issue I.a, section D17.11.27 ("CNTV_TVAL_EL0").
ok kettenis@
|
Revision tags: OPENBSD_7_1_BASE OPENBSD_7_2_BASE
|
#
1.19 |
|
24-Oct-2021 |
mpi |
Constify struct cfattach.
ok visa@ a long time ago, ok patrick@
|
Revision tags: OPENBSD_6_9_BASE OPENBSD_7_0_BASE
|
#
1.18 |
|
11-Mar-2021 |
jsg |
spelling
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.23 |
|
25-Jul-2023 |
cheloha |
statclock: move profil(2), GPROF code to profclock(), gmonclock()
This patch isolates profil(2) and GPROF from statclock(). Currently, statclock() implements both profil(2) and GPROF through a complex mechanism involving both platform code (setstatclockrate) and the scheduler (pscnt, psdiv, and psratio). We have a machine-independent interface to the clock interrupt hardware now, so we no longer need to do it this way.
- Move profil(2)-specific code from statclock() to a new clock interrupt callback, profclock(), in subr_prof.c. Each schedstate_percpu has its own profclock handle. The profclock is enabled/disabled for a given CPU when it is needed by the running thread during mi_switch() and sched_exit().
- Move GPROF-specific code from statclock() to a new clock interrupt callback, gmonclock(), in subr_prof.c. Where available, each cpu_info has its own gmonclock handle . The gmonclock is enabled/disabled for a given CPU via sysctl(2) in prof_state_toggle().
- Both profclock() and gmonclock() have a fixed period, profclock_period, that is initialized during initclocks().
- Export clockintr_advance(), clockintr_cancel(), clockintr_establish(), and clockintr_stagger() via <sys/clockintr.h>. They have external callers now.
- Delete pscnt, psdiv, psratio. From schedstate_percpu, also delete spc_pscnt and spc_psdiv. The statclock frequency is not dynamic anymore so these variables are now useless.
- Delete code/state related to the dynamic statclock frequency from kern_clockintr.c. The statclock frequency can still be pseudo-random, so move the contents of clockintr_statvar_init() into clockintr_init().
With input from miod@, deraadt@, and claudio@. Early revisions cleaned up by claudio. Early revisions tested by claudio@. Tested by cheloha@ on amd64, arm64, macppc, octeon, and sparc64 (sun4v). Compile- and boot- tested on i386 by mlarkin@. riscv64 compilation bugs found by mlarkin@. Tested on riscv64 by jca@. Tested on powerpc64 by gkoehler@.
|
Revision tags: OPENBSD_7_3_BASE
|
#
1.22 |
|
04-Feb-2023 |
cheloha |
timecounting: remove incomplete PPS support
The timecounting code has had stubs for pulse-per-second (PPS) polling since it was imported in 2004. At this point it seems unlikely that anyone is going to finish adding PPS support, so let's remove the stubs:
- Delete the dead tc_poll_pps() call from tc_windup(). - Remove all tc_poll_pps symbols from the kernel.
Link: https://marc.info/?l=openbsd-tech&m=167519035723210&w=2
ok miod@
|
#
1.21 |
|
09-Jan-2023 |
kettenis |
Allwinner hardware sucks! The ARM generic timer on the A64 has a bug where the bottom 9 bits of the counter register can't be trusted if any of the higher bits are rolling over. This is an unpublished errata so the details aren't known. Adopt the same workaround that Linux has.
This will disable the userland timecounter support on hardware affected by the hardware. We will need a similar workaround in libc to restore that functionality.
tested by semarie@ ok cheloha@
|
#
1.20 |
|
08-Nov-2022 |
cheloha |
arm64: switch to clockintr(9)
Switch arm64 to the clockintr(9) subsystem.
- Remove the custom per-CPU clock interrupt schedule from agtimer(4). - Remove the custom randomized statclock() pieces from agtimer(4). - Add agtimer_rearm(), agtimer_trigger(), and wire up agtimer_intrclock.
There is one wart:
- The AArch64 spec says that a value written to CNTV_TVAL_EL0 is "treated as a signed 32-bit integer" [1]. kettenis@ doesn't know what to make of this. I'm capping the value at INT32_MAX for now. It's possible I am misreading this, though.
Tested by kettenis@ on his Apple M1 mini. Tested by me on my Raspberry Pi 4B.
Link: https://marc.info/?l=openbsd-tech&m=166776342503304&w=2
[1] "Arm Architecture Reference Manual for A-profile architecture" issue I.a, section D17.11.27 ("CNTV_TVAL_EL0").
ok kettenis@
|
Revision tags: OPENBSD_7_1_BASE OPENBSD_7_2_BASE
|
#
1.19 |
|
24-Oct-2021 |
mpi |
Constify struct cfattach.
ok visa@ a long time ago, ok patrick@
|
Revision tags: OPENBSD_6_9_BASE OPENBSD_7_0_BASE
|
#
1.18 |
|
11-Mar-2021 |
jsg |
spelling
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.22 |
|
04-Feb-2023 |
cheloha |
timecounting: remove incomplete PPS support
The timecounting code has had stubs for pulse-per-second (PPS) polling since it was imported in 2004. At this point it seems unlikely that anyone is going to finish adding PPS support, so let's remove the stubs:
- Delete the dead tc_poll_pps() call from tc_windup(). - Remove all tc_poll_pps symbols from the kernel.
Link: https://marc.info/?l=openbsd-tech&m=167519035723210&w=2
ok miod@
|
#
1.21 |
|
09-Jan-2023 |
kettenis |
Allwinner hardware sucks! The ARM generic timer on the A64 has a bug where the bottom 9 bits of the counter register can't be trusted if any of the higher bits are rolling over. This is an unpublished errata so the details aren't known. Adopt the same workaround that Linux has.
This will disable the userland timecounter support on hardware affected by the hardware. We will need a similar workaround in libc to restore that functionality.
tested by semarie@ ok cheloha@
|
#
1.20 |
|
08-Nov-2022 |
cheloha |
arm64: switch to clockintr(9)
Switch arm64 to the clockintr(9) subsystem.
- Remove the custom per-CPU clock interrupt schedule from agtimer(4). - Remove the custom randomized statclock() pieces from agtimer(4). - Add agtimer_rearm(), agtimer_trigger(), and wire up agtimer_intrclock.
There is one wart:
- The AArch64 spec says that a value written to CNTV_TVAL_EL0 is "treated as a signed 32-bit integer" [1]. kettenis@ doesn't know what to make of this. I'm capping the value at INT32_MAX for now. It's possible I am misreading this, though.
Tested by kettenis@ on his Apple M1 mini. Tested by me on my Raspberry Pi 4B.
Link: https://marc.info/?l=openbsd-tech&m=166776342503304&w=2
[1] "Arm Architecture Reference Manual for A-profile architecture" issue I.a, section D17.11.27 ("CNTV_TVAL_EL0").
ok kettenis@
|
Revision tags: OPENBSD_7_1_BASE OPENBSD_7_2_BASE
|
#
1.19 |
|
24-Oct-2021 |
mpi |
Constify struct cfattach.
ok visa@ a long time ago, ok patrick@
|
Revision tags: OPENBSD_6_9_BASE OPENBSD_7_0_BASE
|
#
1.18 |
|
11-Mar-2021 |
jsg |
spelling
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.21 |
|
09-Jan-2023 |
kettenis |
Allwinner hardware sucks! The ARM generic timer on the A64 has a bug where the bottom 9 bits of the counter register can't be trusted if any of the higher bits are rolling over. This is an unpublished errata so the details aren't known. Adopt the same workaround that Linux has.
This will disable the userland timecounter support on hardware affected by the hardware. We will need a similar workaround in libc to restore that functionality.
tested by semarie@ ok cheloha@
|
#
1.20 |
|
08-Nov-2022 |
cheloha |
arm64: switch to clockintr(9)
Switch arm64 to the clockintr(9) subsystem.
- Remove the custom per-CPU clock interrupt schedule from agtimer(4). - Remove the custom randomized statclock() pieces from agtimer(4). - Add agtimer_rearm(), agtimer_trigger(), and wire up agtimer_intrclock.
There is one wart:
- The AArch64 spec says that a value written to CNTV_TVAL_EL0 is "treated as a signed 32-bit integer" [1]. kettenis@ doesn't know what to make of this. I'm capping the value at INT32_MAX for now. It's possible I am misreading this, though.
Tested by kettenis@ on his Apple M1 mini. Tested by me on my Raspberry Pi 4B.
Link: https://marc.info/?l=openbsd-tech&m=166776342503304&w=2
[1] "Arm Architecture Reference Manual for A-profile architecture" issue I.a, section D17.11.27 ("CNTV_TVAL_EL0").
ok kettenis@
|
Revision tags: OPENBSD_7_1_BASE OPENBSD_7_2_BASE
|
#
1.19 |
|
24-Oct-2021 |
mpi |
Constify struct cfattach.
ok visa@ a long time ago, ok patrick@
|
Revision tags: OPENBSD_6_9_BASE OPENBSD_7_0_BASE
|
#
1.18 |
|
11-Mar-2021 |
jsg |
spelling
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.20 |
|
08-Nov-2022 |
cheloha |
arm64: switch to clockintr(9)
Switch arm64 to the clockintr(9) subsystem.
- Remove the custom per-CPU clock interrupt schedule from agtimer(4). - Remove the custom randomized statclock() pieces from agtimer(4). - Add agtimer_rearm(), agtimer_trigger(), and wire up agtimer_intrclock.
There is one wart:
- The AArch64 spec says that a value written to CNTV_TVAL_EL0 is "treated as a signed 32-bit integer" [1]. kettenis@ doesn't know what to make of this. I'm capping the value at INT32_MAX for now. It's possible I am misreading this, though.
Tested by kettenis@ on his Apple M1 mini. Tested by me on my Raspberry Pi 4B.
Link: https://marc.info/?l=openbsd-tech&m=166776342503304&w=2
[1] "Arm Architecture Reference Manual for A-profile architecture" issue I.a, section D17.11.27 ("CNTV_TVAL_EL0").
ok kettenis@
|
Revision tags: OPENBSD_7_1_BASE OPENBSD_7_2_BASE
|
#
1.19 |
|
24-Oct-2021 |
mpi |
Constify struct cfattach.
ok visa@ a long time ago, ok patrick@
|
Revision tags: OPENBSD_6_9_BASE OPENBSD_7_0_BASE
|
#
1.18 |
|
11-Mar-2021 |
jsg |
spelling
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.19 |
|
24-Oct-2021 |
mpi |
Constify struct cfattach.
ok visa@ a long time ago, ok patrick@
|
Revision tags: OPENBSD_6_9_BASE OPENBSD_7_0_BASE
|
#
1.18 |
|
11-Mar-2021 |
jsg |
spelling
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.18 |
|
11-Mar-2021 |
jsg |
spelling
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.17 |
|
23-Feb-2021 |
cheloha |
timecounting: use C99-style initialization for all timecounter structs
The timecounter struct is large and I think it may change in the future. Changing it later will be easier if we use C99-style initialization for all timecounter structs. It also makes reading the code a bit easier.
For reasons I cannot explain, switching to C99-style initialization sometimes changes the hash of the resulting object file, even though the resulting struct should be the same. So there is a binary change here, but only sometimes. No behavior should change in either case.
I can't compile-test this everywhere but I have been staring at the diff for days now and I'm relatively confident this will not break compilation. Fingers crossed.
ok gnezdo@
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.16 |
|
19-Jan-2021 |
kettenis |
s/KHz/kHz/ and reduce dmesg spam a bit
ok tb@, deraadt@
|
Revision tags: OPENBSD_6_8_BASE
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.15 |
|
15-Jul-2020 |
kettenis |
Userland timecounter implementation for arm64.
ok naddy@
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.14 |
|
11-Jul-2020 |
kettenis |
Some whitespace fixes for the inline assembly.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.13 |
|
06-Jul-2020 |
pirofti |
Add support for timeconting in userland.
This diff exposes parts of clock_gettime(2) and gettimeofday(2) to userland via libc eliberating processes from the need for a context switch everytime they want to count the passage of time.
If a timecounter clock can be exposed to userland than it needs to set its tc_user member to a non-zero value. Tested with one or multiple counters per architecture.
The timing data is shared through a pointer found in the new ELF auxiliary vector AUX_openbsd_timekeep containing timehands information that is frequently updated by the kernel.
Timing differences between the last kernel update and the current time are adjusted in userland by the tc_get_timecount() function inside the MD usertc.c file.
This permits a much more responsive environment, quite visible in browsers, office programs and gaming (apparently one is are able to fly in Minecraft now).
Tested by robert@, sthen@, naddy@, kmos@, phessler@, and many others!
OK from at least kettenis@, cheloha@, naddy@, sthen@
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.12 |
|
05-Jun-2020 |
kettenis |
Allow userland access to the virtual counter.
ok patrick@, deraadt@
|
Revision tags: OPENBSD_6_6_BASE OPENBSD_6_7_BASE
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.11 |
|
05-Oct-2019 |
kettenis |
Add workaround for Cortex-A73 errata 858921. Pointed out by drahn@ who also came up with the initial implementation.
ok drahn@, jsg@
|
Revision tags: OPENBSD_6_4_BASE OPENBSD_6_5_BASE
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.10 |
|
11-Aug-2018 |
kettenis |
Use MAXCPUS as the number of elements for the array of per-cpu data. Fixes machines with more than 8 cores.
ok jsg@, patrick@
|
Revision tags: OPENBSD_6_3_BASE
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
#
1.9 |
|
31-Jan-2018 |
kettenis |
Add MULTIPROCESSOR support to the interrupt controller drivers. This makes the secondary CPUs receive clock interrupts. Based on diffs from drahn@.
ok patrick@
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|
Revision tags: OPENBSD_6_1_BASE OPENBSD_6_2_BASE
|
#
1.8 |
|
26-Mar-2017 |
drahn |
Switch arm64 generic timer to use virtual timer instead of physical timer. virtual timer will always be present where physical timer may be disabled by hypervisor. Other OSes use virtual timer. ok patrick@
|
#
1.7 |
|
18-Feb-2017 |
patrick |
Make sure that the timer control registers are written before any further code is executed. Additionally, make sure the counter is read only after all previous code has executed.
|
#
1.6 |
|
18-Feb-2017 |
patrick |
Bump variables related to arithmetic operations to 64-bit. Especially the bump of usec and csec is of concern since a timer frequency of around 187MHz overflows in a 32-bit only calculation, as seen on the AMD Seattle SoC. Since we are running a 64-bit architecture, doing 64-bit arithmetic operations doesn't hurt us as much as on the 32-bit ARMv7 port.
|
#
1.5 |
|
18-Feb-2017 |
patrick |
Initialize the generic timer early so that its delay function can be used early, similar to the armv7 implementation.
|
#
1.4 |
|
07-Feb-2017 |
patrick |
The default frequency we chose for the generic timer does not always ring true. Instead, unless overwritten by the device tree, we should ask the generic timer for its frequency. This fixes time on my AMD Seattle and should improve time management on QEMU as well.
|
#
1.3 |
|
23-Jan-2017 |
kettenis |
Also attach to "arm,armv7-timer".
ok patrick@
|
#
1.2 |
|
05-Jan-2017 |
patrick |
Pass value as input instead of output register, otherwise we write garbage into the control register. While there remove positional argument leftover from the 32-bit version.
|
#
1.1 |
|
17-Dec-2016 |
patrick |
Import of OpenBSD/arm64
This commit contains all the kernel files related to the OpenBSD/arm64 port. It is based on the PowerPC pmap, loongson, arm/armv7 code and FreeBSD aarch64 code. Hard work done by Dale Rahn.
|