The platform that supports SMP currently is a SWARM with a dual-core Sibyte
processor. The kernel config file to use is SWARM_SMP.
Reviewed by: imp, rrs
The basic idea is to use a the same virtual address as a window onto
distinct physical memory locations - one per processor. The physical
address that you access through this mapping depends on which cpu you
are currently executing on. We can now use the same virtual address
on any processor to access its per-cpu area.
The details are:
- The virtual address for 'struct pcpu *pcpup' is obtained by
stealing 2 pages worth of KVA in pmap_bootstrap().
- The mapping from the constant virtual address to a distinct
physical page is done in cpu_pcpu_init() through a wired TLB entry.
- A side-effect of this is that we reserve 2 pages worth of memory
for the pcpu but in reality it needs much less than that. The unused
memory is now used as the boot stack for the BSP and APs.
Remove SMP-specific bits from locore.S. The plan is to use a separate
mpboot.S for AP bootstrap.
Discussed on: freebsd-mips
Approved by: imp (mentor)
through fork_trampoline.
This was caused because we were clearing the SR_INT_IE and setting
SR_EXL bits of the status register at the same time. This meant
that if an interrupt happened while this MTC0 was making its way
through the pipeline the exception processing would see the
status register with SR_EXL bit set. This in turn would mean that
the COP_0_EXC_PC would not be updated so the return from exception
would be to an incorrect address.
It is easy to verify this fix by a program that forks in a loop
and the child just exits:
while (1) {
pid_t pid = vfork();
if (pid == 0)
_exit(0);
if (pid != -1)
waitpid(pid, NULL, 0);
}
Also remove two instances where we set SR_EXL bit gratuitously in exception.S.
Approved by: imp (mentor)
available for use. All data below this address considered to be used
by kernel. Along with kernel own data it might be symbol tables
prepeared by trampoline code, boot loader service data passed for
further analysis by kernel, etc... By default kernel_kseg0_end points
to the end of loaded kernel.
- Introduce mips_postboot_fixup function. It checks for symbol information
copied by ELF trampoline and passes it to KDB
r201881 | imp | 2010-01-08 20:08:22 -0700 (Fri, 08 Jan 2010) | 3 lines
Rename mips_pcpu_init to mips_pcpu0_init since it applies only to the
BSP. Provide a missing prototype.
r200343 | imp | 2009-12-09 18:44:11 -0700 (Wed, 09 Dec 2009) | 4 lines
Get the sense of this right. We use uintpr_t for bus_addr_t when
we're building everything except octeon && 32-bit. As note before, we
need a clearner way, but at least now the hack is right.
r199760 | imp | 2009-11-24 10:15:22 -0700 (Tue, 24 Nov 2009) | 2 lines
Add in Cavium's CID. Report what the unknown CID is.
r199754 | imp | 2009-11-24 09:32:31 -0700 (Tue, 24 Nov 2009) | 6 lines
Include opt_cputype.h for all .c and .S files referencing TARGET_OCTEON.
Spell ld script name right.
r199599 | imp | 2009-11-20 09:32:26 -0700 (Fri, 20 Nov 2009) | 2 lines
Another kludge for 64-bit bus_addr_t with 32-bit pointers...
r199496 | gonzo | 2009-11-18 15:52:05 -0700 (Wed, 18 Nov 2009) | 5 lines
- Add cpu_init_interrupts function that is supposed to
prepeare stuff required for spinning out interrupts later
- Add API for managing intrcnt/intrnames arrays
- Some minor style(9) fixes
r198958 | rrs | 2009-11-05 11:15:47 -0700 (Thu, 05 Nov 2009) | 2 lines
For XLR adds extern for its bus space routines
r198669 | rrs | 2009-10-30 02:53:11 -0600 (Fri, 30 Oct 2009) | 5 lines
With this commit our friend RMI will now compile. I have
not tested it and the chances of it running yet are about
ZERO.. but it will now compile. The hard part now begins,
making it run ;-)
r198666 | imp | 2009-10-29 18:37:50 -0600 (Thu, 29 Oct 2009) | 2 lines
Add some newer MIPS CO cores.
r198665 | imp | 2009-10-29 18:37:04 -0600 (Thu, 29 Oct 2009) | 4 lines
db_expr_t is really closer to a register_t.
Submitted by: bde@
r198531 | gonzo | 2009-10-27 18:01:20 -0600 (Tue, 27 Oct 2009) | 3 lines
- Remove bunch of declared but not defined cach-related variables
- Add mips_picache_linesize and mips_pdcache_linesize variables
r198354 | neel | 2009-10-21 20:51:31 -0600 (Wed, 21 Oct 2009) | 9 lines
Get rid of the hardcoded constants to define cacheable memory:
SDRAM_ADDR_START, SDRAM_ADDR_END and SDRAM_MEM_SIZE
Instead we now keep a copy of the memory regions enumerated by
platform-specific code and use that to determine whether an address
is cacheable or not.
r198310 | gonzo | 2009-10-20 17:13:08 -0600 (Tue, 20 Oct 2009) | 5 lines
- Commit missing part of "bt" fix: store PC register in pcb_context struct
in cpu_switch and use it in stack_trace function later. pcb_regs contains
state of the process stored by exception handler and therefor is not
valid for sleeping processes.
r198207 | imp | 2009-10-18 08:57:04 -0600 (Sun, 18 Oct 2009) | 2 lines
Undo spamage of last MFC.
r198206 | imp | 2009-10-18 08:56:33 -0600 (Sun, 18 Oct 2009) | 3 lines
_ALIGN has to return u_long, since pointers don't fit into u_int in
64-bit mips.
r198182 | gonzo | 2009-10-16 18:22:07 -0600 (Fri, 16 Oct 2009) | 11 lines
- Use PC/RA/SP values as arguments for stacktrace_subr instead of trapframe.
Context info could be obtained from other sources (see below) no only from
td_pcb field
- Do not show a0..a3 values unless they're obtained from the stack. These
are only confirmed values.
- Fix bt command in DDB. Previous implementation used thread's trapframe
structure as a source info for trace unwinding, but this structure
is filled only when exception occurs. Valid register values for sleeping
processes are in pcb_context array. For curthread use pc/sp/ra for current
frame
r198181 | gonzo | 2009-10-16 16:52:18 -0600 (Fri, 16 Oct 2009) | 2 lines
- Get rid of label_t. It came from NetBSD and was used only in one place
r198154 | rrs | 2009-10-15 15:03:32 -0600 (Thu, 15 Oct 2009) | 10 lines
Does 4 things:
1) Adds future RMI directories
2) Places intr_machdep.c in specfic files.arch pointing to the generic
intr_machdep.c. This allows us to have an architecture dependant
intr_machdep.c (which we will need for RMI) in the machine specific
directory
3) removes intr_machdep.c from files.mips
4) Adds some TARGET_XLR_XLS ifdef's for the machine specific intra_machdep.h. We
may need to look at finding a better place to put this. But first I want to
get this thing compiling.
r198066 | gonzo | 2009-10-13 19:43:53 -0600 (Tue, 13 Oct 2009) | 5 lines
- Move stack tracing function to db_trace.c
- Axe unused extern MipsXXX declarations
- Move all declarations for functions in exceptions.S/swtch.S
from trap.c to respective headers
r197685 | gonzo | 2009-10-01 14:05:36 -0600 (Thu, 01 Oct 2009) | 2 lines
- Sync caches properly when dealing with sf_buf
r196215 | imp | 2009-08-14 10:15:18 -0600 (Fri, 14 Aug 2009) | 6 lines
(u_int) is the wrong type here. Use unsigned long instead, even
though that's only less wrong...
r196199 | imp | 2009-08-13 13:47:13 -0600 (Thu, 13 Aug 2009) | 7 lines
Use unsigned long instead of unsigned for the integer casts here. The
former works for both ILP32 and LP64 programming models, while the
latter fails LP64.
r196089 | gonzo | 2009-08-09 19:49:59 -0600 (Sun, 09 Aug 2009) | 4 lines
- Make i/d cache size field 32-bit to prevent overflow
Submited by: Neelkanth Natu
r195582 | imp | 2009-07-10 13:07:07 -0600 (Fri, 10 Jul 2009) | 2 lines
fix prototype for MipsEmulateBranch.
r195581 | imp | 2009-07-10 13:06:43 -0600 (Fri, 10 Jul 2009) | 2 lines
Better definitions for a few types for n32/n64.
r195580 | imp | 2009-07-10 13:06:15 -0600 (Fri, 10 Jul 2009) | 5 lines
Fixed aligned macros...
r195478 | gonzo | 2009-07-08 16:28:36 -0600 (Wed, 08 Jul 2009) | 5 lines
- Port busdma code from FreeBSD/arm. This is more mature version
that takes into account all limitation to DMA memory (boundaries,
alignment) and implements bounce pages.
- Add BUS_DMASYNC_POSTREAD case to bus_dmamap_sync_buf
r195440 | imp | 2009-07-08 00:01:37 -0600 (Wed, 08 Jul 2009) | 2 lines
Fix atomic_store_64 prototype for 64-bit systems.
r195392 | imp | 2009-07-05 20:27:03 -0600 (Sun, 05 Jul 2009) | 3 lines
The MCOUNT macro isn't going to work in 64-bit mode. Add a note to
this effect.
r195391 | imp | 2009-07-05 20:22:51 -0600 (Sun, 05 Jul 2009) | 3 lines
Provide a macro for PTR_ADDU as well. We may need to implement this
differently for N32... Use PTR_ADDU in DO_AST macro.
r195390 | imp | 2009-07-05 20:22:06 -0600 (Sun, 05 Jul 2009) | 4 lines
Change the addu here to daddu.
addu paranoina prodded by: jmallet@
r195382 | imp | 2009-07-05 15:16:26 -0600 (Sun, 05 Jul 2009) | 5 lines
addu and subu are special. We need to use daddu and dsubu here to get
proper behavior.
Submitted by: jmallet@
r195370 | imp | 2009-07-05 09:20:16 -0600 (Sun, 05 Jul 2009) | 6 lines
The SB1 has cohernet memory, so add it.
Also, Maxmem is better as a long.
Submitted by: Neelkanth Natu
r195369 | imp | 2009-07-05 09:19:28 -0600 (Sun, 05 Jul 2009) | 4 lines
The SB1 needs a special value for the cache field of the pte.
Submitted by: Neelkanth Natu
r195368 | imp | 2009-07-05 09:18:06 -0600 (Sun, 05 Jul 2009) | 2 lines
compute the areas to save registers in for 64-bit access correctly.
r195367 | imp | 2009-07-05 09:17:11 -0600 (Sun, 05 Jul 2009) | 3 lines
First cut at 64-bit types. not 100% sure these are all correct for
N32 ABI.
r195366 | imp | 2009-07-05 09:16:27 -0600 (Sun, 05 Jul 2009) | 3 lines
Trim unreferenced goo. SDRAM likely should be next, but it is still
referenced.
r195365 | imp | 2009-07-05 09:13:24 -0600 (Sun, 05 Jul 2009) | 9 lines
First cut at atomics for 64-bit machines and SMP machines.
# Note: Cavium provided a port that has atomics similar to these, but
# that does a syncw; sync; atomic; sync; syncw where we just do the classic
# mips 'atomic' operation (eg ll; frob; sc). It is unclear to me why
# the extra is needed. Since my initial target is one core, I'll defer
# investigation until I bring up multiple cores. syncw is an octeon specific
# instruction.
r195359 | imp | 2009-07-05 02:14:00 -0600 (Sun, 05 Jul 2009) | 4 lines
Bring in cdefs.h from NetBSD to define ABI goo.
Obtained from: NetBSD
r195358 | imp | 2009-07-05 02:13:19 -0600 (Sun, 05 Jul 2009) | 4 lines
Pull in machine/cdefs.h for the ABI definitions. Provide a PTR_LA,
ala sgi, and use it in preference to a bare 'la' so that it gets
translated to a 'dla' for the 64-bit pointer ABIs.
r195357 | imp | 2009-07-05 01:01:34 -0600 (Sun, 05 Jul 2009) | 2 lines
Use uintptr_t rather than unsigned here for 64-bit correctness.
r195356 | imp | 2009-07-05 01:00:51 -0600 (Sun, 05 Jul 2009) | 6 lines
Define __ELF_WORD_SIZE appropriately for n64. Note for N32 I believe
this is correct. While registers are 64-bit, n32 is a 32-bit ABI and
lives in a 32-bit world (with explicit 64-bit registers, however).
Change an 8, which was 4 + 4 or sizeof(int) + SZREG to be a simple '4
+ SZREG' to reflect the actual offset of the structure in question.
r195355 | imp | 2009-07-05 00:56:51 -0600 (Sun, 05 Jul 2009) | 7 lines
(1) Use uintptr_t in preference to unsigned. The latter isn't right for
64-bit case, while the former is.
(2) include a SB1 specific coherency mapping
Submitted by: Neelkanth Nath (2)
r195352 | imp | 2009-07-05 00:44:37 -0600 (Sun, 05 Jul 2009) | 3 lines
db_expr_t should be a intptr_t, not an int. These expressions can be
addresses or numbers, and that's a intptr_t if I ever saw one.
r195351 | imp | 2009-07-05 00:43:01 -0600 (Sun, 05 Jul 2009) | 4 lines
Define COP0_SYNC for SB1 CPU.
Submitted by: Neelkanth Natu
r195350 | imp | 2009-07-05 00:39:37 -0600 (Sun, 05 Jul 2009) | 7 lines
Switch to ABI agnostic ta0-ta3. Provide defs for this in the right
places. Provide n32/n64 register name defintions. This should have
no effect for the O32 builds that everybody else uses, but should help
make N64 builds possible (lots of other changes are needed for that).
Obtained from: NetBSD (for the regdef.h changes)
r195128 | gonzo | 2009-06-27 17:27:41 -0600 (Sat, 27 Jun 2009) | 4 lines
- Add support for handling TLS area address in kernel space.
From the userland point of view get/set operations are
performed using sysarch(2) call.
r195076 | gonzo | 2009-06-26 13:54:06 -0600 (Fri, 26 Jun 2009) | 2 lines
- Add guards to ensure that these files are included only once
r194469 | gonzo | 2009-06-18 22:43:49 -0600 (Thu, 18 Jun 2009) | 16 lines
- Mark temp variable as "earlyclobber" in assembler inline in
atomic_fetchadd_32. Without it gcc would use it as input
register for v and sometimes generate following code for
function call like atomic_fetchadd_32(&(fp)->f_count, -1):
801238b4: 2402ffff li v0,-1
801238b8: c2230018 ll v1,24(s1)
801238bc: 00431021 addu v0,v0,v1
801238c0: e2220018 sc v0,24(s1)
801238c4: 1040fffc beqz v0,801238b8 <dupfdopen+0x2e8>
801238c8: 00000000 nop
Which is definitly wrong because if sc fails v0 is set to 0
and previous value of -1 is overriden hence whole operation
turns to bogus
r194164 | imp | 2009-06-14 00:14:25 -0600 (Sun, 14 Jun 2009) | 3 lines
bye bye. This is no longer referenced, but much code from it will
resurface for a bus-space implementation.
r194160 | imp | 2009-06-14 00:10:36 -0600 (Sun, 14 Jun 2009) | 3 lines
Cavium-specific goo is no longer necessary here. Of course, I now
have to write a bus space for cavium, but that shouldn't be too hard.
r194157 | imp | 2009-06-14 00:01:46 -0600 (Sun, 14 Jun 2009) | 2 lines
Move this to a more approrpiate plae.
r194156 | imp | 2009-06-13 23:29:13 -0600 (Sat, 13 Jun 2009) | 2 lines
Bring this in from the cavium port.
r193487 | gonzo | 2009-06-05 02:37:11 -0600 (Fri, 05 Jun 2009) | 2 lines
- Use restoreintr instead of enableint while accessing pcpu in DO_AST
r192864 | gonzo | 2009-05-26 16:40:12 -0600 (Tue, 26 May 2009) | 4 lines
- Replace CPU_NOFPU and SOFTFLOAT options with CPU_FPU. By default
we assume that there is no FPU, because majority of SoC does
not have it.
r192817 | gonzo | 2009-05-26 10:35:05 -0600 (Tue, 26 May 2009) | 2 lines
- Add type cast for atomic_cmpset_acq_ptr arguments
r192792 | gonzo | 2009-05-26 00:01:17 -0600 (Tue, 26 May 2009) | 2 lines
- Remove now unused NetBSDism intr.h
r192177 | gonzo | 2009-05-15 20:39:13 -0600 (Fri, 15 May 2009) | 4 lines
- Add MIPS_IS_KSEG0_ADDR, MIPS_IS_KSEG1_ADDR and MIPS_IS_VALID_PTR
macroses thet check if address belongs to KSEG0, KSEG1 or both
of them respectively.
r191589 | gonzo | 2009-04-27 13:18:55 -0600 (Mon, 27 Apr 2009) | 3 lines
- Cast argument to proper type in order to avoid warnings like
"shift value is too large for given type"
r191577 | gonzo | 2009-04-27 12:29:59 -0600 (Mon, 27 Apr 2009) | 4 lines
- Use naming convention the same as MIPS spec does: eliminate _sel1 sufix
and just use selector number. e.g. mips_rd_config_sel1 -> mips_rd_config1
- Add WatchHi/WatchLo accessors for selctors 1..3 (for debug purposes)
r191451 | gonzo | 2009-04-23 22:17:21 -0600 (Thu, 23 Apr 2009) | 4 lines
- Define accessor functions for CP0 Config(16) register selects 1, 2, 3.
Content of these registers is defined in MIPS spec and can be used
for obtaining info about CPU capabilities.
r191282 | gonzo | 2009-04-19 16:02:14 -0600 (Sun, 19 Apr 2009) | 3 lines
- Make mips_bus_space_generic be of type bus_space_tag_t instead of
struct bus_space and update all relevant places.
r191084 | gonzo | 2009-04-14 20:28:26 -0600 (Tue, 14 Apr 2009) | 6 lines
Use FreeBSD/arm approach for handling bus space access: space tag is a pointer
to bus_space structure that defines access methods and hence every bus can
define own accessors. Default space is mips_bus_space_generic. It's a simple
interface to physical memory, values are read with regard to host system
byte order.
r195128 | gonzo | 2009-06-27 17:27:41 -0600 (Sat, 27 Jun 2009) | 4 lines
- Add support for handling TLS area address in kernel space.
From the userland point of view get/set operations are
performed using sysarch(2) call.
SDRAM_ADDR_START, SDRAM_ADDR_END and SDRAM_MEM_SIZE
Instead we now keep a copy of the memory regions enumerated by
platform-specific code and use that to determine whether an address
is cacheable or not.
Approved by: imp (mentor)
in cpu_switch and use it in stack_trace function later. pcb_regs contains
state of the process stored by exception handler and therefor is not
valid for sleeping processes.
Context info could be obtained from other sources (see below) no only from
td_pcb field
- Do not show a0..a3 values unless they're obtained from the stack. These
are only confirmed values.
- Fix bt command in DDB. Previous implementation used thread's trapframe
structure as a source info for trace unwinding, but this structure
is filled only when exception occurs. Valid register values for sleeping
processes are in pcb_context array. For curthread use pc/sp/ra for current
frame
1) Adds future RMI directories
2) Places intr_machdep.c in specfic files.arch pointing to the generic
intr_machdep.c. This allows us to have an architecture dependant intr_machdep.c
(which we will need for RMI) in the machine specific directory
3) removes intr_machdep.c from files.mips
4) Adds some TARGET_XLR_XLS ifdef's for the machine specific intra_machdep.h. We
may need to look at finding a better place to put this. But first I want to
get this thing compiling.
by looking at the bases used for non-relocatable executables by gnu ld(1),
and adjusting it slightly.
Discussed with: bz
Reviewed by: kan
Tested by: bz (i386, amd64), bsam (linux)
MFC after: some time
former works for both ILP32 and LP64 programming models, while the
latter fails LP64.
# uintpr_t is better, but iirc, we can't pollute the name space to use it
# I likely need to audit all my uintptr_t changes for that issue...
has proven to have a good effect when entering KDB by using a NMI,
but it completely violates all the good rules about interrupts
disabled while holding a spinlock in other occasions. This can be the
cause of deadlocks on events where a normal IPI_STOP is expected.
* Adds an new IPI called IPI_STOP_HARD on all the supported architectures.
This IPI is responsible for sending a stop message among CPUs using a
privileged channel when disponible. In other cases it just does match a
normal IPI_STOP.
Right now the IPI_STOP_HARD functionality uses a NMI on ia32 and amd64
architectures, while on the other has a normal IPI_STOP effect. It is
responsibility of maintainers to eventually implement an hard stop
when necessary and possible.
* Use the new IPI facility in order to implement a new userend SMP kernel
function called stop_cpus_hard(). That is specular to stop_cpu() but
it does use the privileged channel for the stopping facility.
* Let KDB use the newly introduced function stop_cpus_hard() and leave
stop_cpus() for all the other cases
* Disable interrupts on CPU0 when starting the process of APs suspension.
* Style cleanup and comments adding
This patch should fix the reboot/shutdown deadlocks many users are
constantly reporting on mailing lists.
Please don't forget to update your config file with the STOP_NMI
option removal
Reviewed by: jhb
Tested by: pho, bz, rink
Approved by: re (kib)
dependent memory attributes:
Rename vm_cache_mode_t to vm_memattr_t. The new name reflects the
fact that there are machine-dependent memory attributes that have
nothing to do with controlling the cache's behavior.
Introduce vm_object_set_memattr() for setting the default memory
attributes that will be given to an object's pages.
Introduce and use pmap_page_{get,set}_memattr() for getting and
setting a page's machine-dependent memory attributes. Add full
support for these functions on amd64 and i386 and stubs for them on
the other architectures. The function pmap_page_set_memattr() is also
responsible for any other machine-dependent aspects of changing a
page's memory attributes, such as flushing the cache or updating the
direct map. The uses include kmem_alloc_contig(), vm_page_alloc(),
and the device pager:
kmem_alloc_contig() can now be used to allocate kernel memory with
non-default memory attributes on amd64 and i386.
vm_page_alloc() and the device pager will set the memory attributes
for the real or fictitious page according to the object's default
memory attributes.
Update the various pmap functions on amd64 and i386 that map pages to
incorporate each page's memory attributes in the mapping.
Notes: (1) Inherent to this design are safety features that prevent
the specification of inconsistent memory attributes by different
mappings on amd64 and i386. In addition, the device pager provides a
warning when a device driver creates a fictitious page with memory
attributes that are inconsistent with the real page that the
fictitious page is an alias for. (2) Storing the machine-dependent
memory attributes for amd64 and i386 as a dedicated "int" in "struct
md_page" represents a compromise between space efficiency and the ease
of MFCing these changes to RELENG_7.
In collaboration with: jhb
Approved by: re (kib)
