Commit Graph

71 Commits

Author SHA1 Message Date
John Baldwin
ae67737a4c libc: Remove _get_tp() and _set_tp().
Their uses have been replaced by _tcb_get() and _tcb_set() from
<machine/tls.h>.

Reviewed by:	kib, jrtc27
Sponsored by:	The University of Cambridge, Google Inc.
Differential Revision:	https://reviews.freebsd.org/D33354
2021-12-09 13:23:26 -08:00
Konstantin Belousov
77b2c2f814 Add sched_getcpu()
for compatibility with Linux.

Reviewed by:	jhb
Sponsored by:	The FreeBSD Foundation
MFC after:	1 week
Differential revision:	https://reviews.freebsd.org/D32901
2021-11-10 21:18:54 +02:00
Konstantin Belousov
06d8a116bd libc: add _get_tp() private function
which returns pointer to tcb

Sponsored by:	The FreeBSD Foundation
MFC after:	1 week
Differential revision:	https://reviews.freebsd.org/D29623
2021-04-09 23:46:24 +03:00
Konstantin Belousov
4c2e9c35fb libc/<arch>/sys/cerror.S: fix typo
Sponsored by:	The FreeBSD Foundation
MFC after:	3 days
2021-04-04 01:00:57 +03:00
Leandro Lupori
9f50aa45be [PowerPC64] Port optimized strcpy to PPC64LE
Submitted by:           Bruno Larsen <bruno.larsen@eldorado.org.br>
Reviewed by:            luporl, bdragon (IRC)
MFC after:              1 week
Sponsored by:           Eldorado Research Institute (eldorado.org.br)
Differential Revision:  https://reviews.freebsd.org/D29067
2021-03-25 13:20:12 -03:00
Leandro Lupori
2f56128403 [PowerPC64] Enforce natural alignment in bcopy
POWER architecture CPUs (Book-S) require natural alignment for
cache-inhibited storage accesses. Since we can't know the caching model
for a page ahead of time, always enforce natural alignment in bcopy.
This fixes a SIGBUS when calling the function with misaligned pointers
on POWER7.

Submitted by:		Bruno Larsen <bruno.larsen@eldorado.org.br>
Reviewed by:		luporl, bdragon (IRC)
MFC after:		1 week
Sponsored by:		Eldorado Research Institute (eldorado.org.br)
Differential Revision:	https://reviews.freebsd.org/D28776
2021-03-25 13:07:01 -03:00
Brandon Bergren
dd95b39235 [PowerPC64] Fix multiple issues in fpsetmask().
Building R exposed a problem in fpsetmask() whereby we were not properly
clamping the provided mask to the valid range.

R initilizes the mask by calling fpsetmask(~0) on FreeBSD. Since we
recently enabled precise exceptions, this was causing an immediate
SIGFPE because we were attempting to set invalid bits in the fpscr.

Properly limit the range of bits that can be set via fpsetmask().

While here, use the correct fp_except_t type instead of fp_rnd_t.

Reported by:	pkubaj (in IRC)
MFC after:	1 week
Sponsored by:	Tag1 Consulting, Inc.
2021-02-28 20:37:48 -06:00
Conrad Meyer
78599c32ef Add CFI start/end proc directives to arm64, i386, and ppc
Follow-up to r353959 and r368070: do the same for other architectures.

arm32 already seems to use its own .fnstart/.fnend directives, which
appear to be ARM-specific variants of the same thing.  Likewise, MIPS
uses .frame directives.

Reviewed by:	arichardson
Differential Revision:	https://reviews.freebsd.org/D27387
2020-12-05 00:33:28 +00:00
Brandon Bergren
b257310103 [PowerPC64LE] Fix gdtoa configurations on LE.
gdtoa wins the award for "most outdated endianness naming convention"
with its IEEE_8087 vs IEEE_MC68k defines. I had a good chuckle.

Update softfloat and arith.h to adjust to BE or LE automatically
based on the low level preprocessor defines.

Fixes printf/scanf on PowerPC64LE, although there is still a problem
lurking regarding Signalling NaNs...

Sponsored by:	Tag1 Consulting, Inc.
2020-09-23 02:05:44 +00:00
Brandon Bergren
24faccc241 [PowerPC64LE] Use a shared LIBC_ARCH for powerpc64le.
Given that we have converted to ELFv2 for BE already, endianness is the only
difference between the two ARCHs.

As such, there is no need to differentiate LIBC_ARCH between the two.

Combining them like this lets us avoid needing to have two copies of several
bits for no good reason.

Sponsored by:	Tag1 Consulting, Inc.
2020-09-23 00:21:51 +00:00
Brandon Bergren
328b5f2570 [PowerPC] Implement VDSO timebase access on powerpc*
Implement the remaining pieces needed to allow userland timestamp reading.

Rewritten based on an intial essay into the problem by Justin Hibbits.
(Copyright changed to my own on his request.)

Tested on ppc64 (POWER9 Talos II), powerpcspe (e500v2 RB800), and
powerpc (g4 PowerBook).

Reviewed by:	jhibbits (in irc)
Sponsored by:	Tag1 Consulting, Inc.
Differential Revision:	https://reviews.freebsd.org/D26347
2020-09-08 03:00:31 +00:00
Brandon Bergren
e039e3d1d2 [POWERPC] Fix ppc64 makecontext() parameter overflow handling.
On ELFv2, the overflow parameters in the stack frame are at a different offset
from sp than ELFv1. Adjust code to use the correct offset in all cases.

This had resulted in argv[8] and up being copied to the incorrect address
in the new context's initial stack frame.

This is not necessarily the only bug in this function, I need to do a full
review still and ensure the rest of the math is sane for ELFv2 stack frames.

Reported by:	pherde (Probably. My notes are a bit unclear.)
Reviewed by:	jhibbits (in irc)
Sponsored by:	Tag1 Consulting, Inc.
2020-08-06 17:49:19 +00:00
Brandon Bergren
db7f521db7 Fix r358688 -- Remember to actually save r3 before processing.
Crash was noticed by pkubaj building gcc9.

Apparently non dword-aligned char pointers are somewhat rare in the wild.

Reported by:	pkubaj
Sponsored by:	Tag1 Consulting, Inc.
2020-03-11 23:34:44 +00:00
Justin Hibbits
dcfc676147 powerpc/memcpy: Don't predict the src and dst will be misaligned
Predicting misalignment will pessimize the expected common case.  Don't
predict true or false in thise case.
2020-03-06 03:46:48 +00:00
Justin Hibbits
021abafa5c Finish revert of r358672, missed in r358688.
Manual reverts never succeed correctly.

Reported by:	luporl
2020-03-06 02:30:04 +00:00
Justin Hibbits
00797360b5 powerpc/powerpc64: Enforce natural alignment in memcpy
Summary:
POWER architecture CPUs (Book-S) require natural alignment for
cache-inhibited storage accesses.  Since we can't know the caching model
for a page ahead of time, always enforce natural alignment in memcpy.
This fixes a SIGBUS in X with acceleration enabled on POWER9.

As part of this, revert r358672, it's no longer necessary with this fix.

Regression tested by alfredo.

Reviewed by: alfredo
Differential Revision: https://reviews.freebsd.org/D23969
2020-03-06 01:45:03 +00:00
Alfredo Dal'Ava Junior
2b37373c48 [PowerPC64] restrict memcpy/bcopy optimization to POWER ISA >=V2.07
VSX instructions were added in POWER ISA V2.06 (POWER7), but it
requires data to be word-aligned. Such requirement was removed in
ISA V2.07B (POWER8).

Since current memcpy/bcopy optimization relies on VSX instructions
handling misalignment transparently, and kernel doesn't currently
implement an alignment error handler, this optimzation should be
restrict to ISA V2.07 onwards.

SIGBUS on stxvd2x instruction was reproduced in POWER7+ CPU.

Reviewed by:	luporl, jhibbits, bdragon
Approved by:	jhibbits (mentor)
Differential Revision:	https://reviews.freebsd.org/D23958
2020-03-05 14:13:22 +00:00
Leandro Lupori
e16c18650c [PPC64] memcpy/memmove/bcopy optimization
For copies shorter than 512 bytes, the data is copied using plain
ld/std instructions.
For 512 bytes or more, the copy is done in 3 phases:

Phase 1: copy from the src buffer until it's aligned at a 16-byte boundary
Phase 2: copy as many aligned 64-byte blocks from the src buffer as possible
Phase 3: copy the remaining data, if any

In phase 2, this code uses VSX instructions when available. Otherwise,
it uses ldx/stdx.

Submitted by:	Luis Pires <lffpires_ruabrasil.org> (original version)
Reviewed by:	jhibbits
Differential Revision:	https://reviews.freebsd.org/D15118
2020-01-15 20:25:52 +00:00
Leandro Lupori
181e35008c [PPC64] strncpy optimization
Assembly optimization of strncpy for PowerPC64, using double words
instead of bytes to copy strings.

Submitted by:	Leonardo Bianconi <leonardo.bianconi_eldorado.org.br> (original version)
Reviewed by:	jhibbits
Differential Revision:	https://reviews.freebsd.org/D15369
2020-01-15 19:53:03 +00:00
Leandro Lupori
075fb85f09 [PPC64] strcpy optimization
Assembly optimization of strcpy for PowerPC64, using double words
instead of bytes to copy strings.

Submitted by:	Leonardo Bianconi <leonardo.bianconi_eldorado.org.br> (original version)
Reviewed by:	jhibbits
Differential Revision:	https://reviews.freebsd.org/D15368
2020-01-15 19:46:01 +00:00
Brandon Bergren
59e1870182 [PowerPC] Fully define gdtoa settings on powerpc64.
The settings in arith.h were not fully defined on powerpc64 after the gdtoa
switchover. Generate them using arithchk.c, similar to what AMD64 did for
r114814.

Technically, none of this is necessary in FreeBSD gdtoa, but since the other
platforms have full definitions, we might as well have full definitions
too.

Approved by:	jhibbits (in irc)
Differential Revision:	https://reviews.freebsd.org/D22775
2019-12-13 20:30:26 +00:00
Brandon Bergren
7316504cd5 [PowerPC] Fix *context on ELFv2
Due to ELFv1 specific code in _ctx_start.S and makecontext.c, userspace
context switching was completely broken on ELFv2.

With this change, we now pass the libthr test suite.

Approved by: jhibbits (mentor)
Differential Revision: https://reviews.freebsd.org/D22421
2019-11-16 20:33:46 +00:00
Justin Hibbits
2f420a7c7f revert r346588 for now
The rewrite of strcmp in assembly uses an instruction added in PowerISA
2.05, making it SIGILL on CPUs older than the POWER6, such as the PPC970 in
the PowerMac G5.  Revert this until we get clang+lld, or retire the in-tree
binutils in favor of newer binutils with IFUNC support, whichever comes
first.
2019-05-11 15:17:42 +00:00
Justin Hibbits
89a0487c97 powerpc64: Rewrite strcmp in asm to take advantage of word size
Summary:
Optimize strcmp for powerpc64.
Data is loaded by double words and cmpb intruction is used to find '\0'.

Some performance gain rates between the current and the optimized solution:

String size (bytes)		Gain rate
	<=8			0.59%
	<=16			1.92%
	32			3.02%
	64			5.60%
	128			10.16%
	256			18.05%
	512			30.18%
	1024			42.82%

Submitted by:	alexandre.yamashita_eldorado.org.br,
		leonardo.bianconi_eldorado.org.br
Differential Revision: https://reviews.freebsd.org/D15220
2019-04-23 02:53:53 +00:00
Konstantin Belousov
5d00c5a657 Fix initial exec TLS mode for dynamically loaded shared objects.
If dso uses initial exec TLS mode, rtld tries to allocate TLS in
static space. If there is no space left, the dlopen(3) fails. If space
if allocated, initial content from PT_TLS segment is distributed to
all threads' pcbs, which was missed and caused un-initialized TLS
segment for such dso after dlopen(3).

The mode is auto-detected either due to the relocation used, or if the
DF_STATIC_TLS dynamic flag is set.  In the later case, the TLS segment
is tried to allocate earlier, which increases chance of the dlopen(3)
to succeed.  LLD was recently fixed to properly emit the flag, ld.bdf
did it always.

Initial test by:	dumbbell
Tested by:	emaste (amd64), ian (arm)
Tested by:	Gerald Aryeetey <aryeeteygerald_rogers.com> (arm64)
Sponsored by:	The FreeBSD Foundation
MFC after:	2 weeks
Differential revision:	https://reviews.freebsd.org/D19072
2019-03-29 17:52:57 +00:00
Brooks Davis
db19a093bb Remove MD __sys_* private symbols.
No references to any of these exist in the tree. The list was also
erratic with different architectures exporting different things
(arm64 and riscv exported none).

Reviewed by:	kib
Sponsored by:	DARPA, AFRL
Differential Revision:	https://reviews.freebsd.org/D18425
2018-12-05 00:46:09 +00:00
Mark Johnston
9f9c9b22ec Reimplement brk() and sbrk() to avoid the use of _end.
Previously, libc.so would initialize its notion of the break address
using _end, a special symbol emitted by the static linker following
the bss section.  Compatibility issues between lld and ld.bfd could
cause the wrong definition of _end (libc.so's definition rather than
that of the executable) to be used, breaking the brk()/sbrk()
interface.

Avoid this problem and future interoperability issues by simply not
relying on _end.  Instead, modify the break() system call to return
the kernel's view of the current break address, and have libc
initialize its state using an extra syscall upon the first use of the
interface.  As a side effect, this appears to fix brk()/sbrk() usage
in executables run with rtld direct exec, since the kernel and libc.so
no longer maintain separate views of the process' break address.

PR:		228574
Reviewed by:	kib (previous version)
MFC after:	2 months
Differential Revision:	https://reviews.freebsd.org/D15663
2018-06-04 19:35:15 +00:00
Brooks Davis
87385baff6 Replace MD assembly exect() with a portable version.
Originally, on the VAX exect() enable tracing once the new executable
image was loaded.  This was possible because tracing was controllable
through user space code by setting the PSL_T flag.  The following
instruction is a system call that activated tracing (as all
instructions do) by copying PSL_T to PSL_TP (trace pending).  The
first instruction of the new executable image would trigger a trace
fault.

This is not portable to all platforms and the behavior was replaced with
ptrace(PT_TRACE_ME, ...) since FreeBSD forked off of the CSRG repository.
Platforms either incorrectly call execve(), trigger trace faults inside
the original executable, or do contain an implementation of this
function.

The exect() interfaces is deprecated or removed on NetBSD and OpenBSD.

Submitted by:	Ali Mashtizadeh <ali@mashtizadeh.com>
Reviewed by:	kib
Differential Revision:	https://reviews.freebsd.org/D14989
2018-04-12 18:23:14 +00:00
Brooks Davis
047a2ef697 Remove caching from getlogin(2).
This caching has existed since the CSRG import, but serves no obvious
purpose. Sure, setlogin() is called rarely, but calls to getlogin()
should also be infrequent. The required invalidation was not
implemented on aarch64, arm, mips, amd riscv so updates would never
occur if getlogin() was called before setlogin().

Reported by:	Ali Mashtizadeh <ali@mashtizadeh.com>
Reviewed by:	kib
Sponsored by:	DARPA, AFRL
Differential Revision:	https://reviews.freebsd.org/D14965
2018-04-06 17:17:34 +00:00
John Baldwin
80996ef878 Remove bogus checks against NCARGS.
NCARGS isn't a limit on the number of arguments to pass to a function,
but the number of bytes that can be consumed by arguments to exec.  As
such, it is not suitable for a limit on the count of arguments passed
to makecontext().

Sponsored by:	DARPA / AFRL
2018-01-31 17:57:59 +00:00
Pedro F. Giffuni
d915a14ef0 libc: further adoption of SPDX licensing ID tags.
Mainly focus on files that use BSD 2-Clause license, however the tool I
was using mis-identified many licenses so this was mostly a manual - error
prone - task.

The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.
2017-11-25 17:12:48 +00:00
Pedro F. Giffuni
8a16b7a18f General further adoption of SPDX licensing ID tags.
Mainly focus on files that use BSD 3-Clause license.

The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.

Special thanks to Wind River for providing access to "The Duke of
Highlander" tool: an older (2014) run over FreeBSD tree was useful as a
starting point.
2017-11-20 19:49:47 +00:00
Brooks Davis
13f2393362 Correct an misunderstanding of MDSRCS.
MDSRCS it intended to allow assembly versions of funtions with C
implementations listed in MISRCS. The selection of the correct
machdep_ldis?.c for a given architecture does not follow this pattern
and the file should be added to SRCS directly.

Reviewed by:	emaste, imp, jhb
MFC after:	1 week
Sponsored by:	DARPA, AFRL
Differential Revision:	https://reviews.freebsd.org/D9841
2017-03-02 17:07:28 +00:00
Brooks Davis
aec2fba60f Reduce duplicate NOASM and PSEUDO definitions
The initial value of NOASM is nearly the same in all cases and the
initial value of PSEUDO is the same in all cases so reduce duplication
(and hopefully, future merge conflicts) by machine independent defaults.

Also document the PSEUDO variable.

Reviewed by:	jhb, kib
Obtained from:	CheriBSD
Sponsored by:	DARPA, AFRL
Differential Revision:	https://reviews.freebsd.org/D7820
2016-09-08 22:38:20 +00:00
Konstantin Belousov
afd3e268d2 Rewrite ptrace(2) wrappers in C.
Besides removing hand-translation to assembler, this also adds missing
wrappers for arm64 and risc-v.

Reviewed by:	emaste, jhb
Sponsored by:	The FreeBSD Foundation
MFC after:	1 week
Differential revision:	https://reviews.freebsd.org/D7694
2016-08-29 18:47:51 +00:00
George V. Neville-Neil
5cba398b0c Remove unusedd and obsolete openbsd_poll system call. (Phase 1)
Reported by:	brooks
Reviewed by:	brooks,jhb
Differential Revision:	https://reviews.freebsd.org/D7548
2016-08-18 10:50:40 +00:00
Brooks Davis
b60998c633 Replace use of the pipe(2) system call with pipe2(2) with a zero flags
value.

This eliminates the need for machine dependant assembly wrappers for
pipe(2).

It also make passing an invalid address to pipe(2) return EFAULT rather
than triggering a segfault.  Document this behavior (which was already
true for pipe2(2), but undocumented).

Reviewed by:	andrew
Approved by:	re (gjb)
Sponsored by:	DARPA, AFRL
Differential Revision:	https://reviews.freebsd.org/D6815
2016-06-22 21:11:27 +00:00
Pedro F. Giffuni
bf51882a09 libc: make some more use of the nitems() macro.
We have an nitems() macro in the <sys/param.h> header that is
convenient to re-use as it makes things easier to read.
Given that it is available already without adding additional
headers and other parts of libc already use it, extend a bit
more its use.
2016-04-16 17:52:00 +00:00
Ed Maste
a38e4f5cc6 libc: stop exporting cerror
i386 stopped exporting .cerror in r240152, and likewise for amd64 in
r240178. It is not used by other libraries on any platform, so apply
the same change to the remaining architectures.

Reviewed by:	jhibbits, jilles
Sponsored by:	The FreeBSD Foundation
Differential Revision:	https://reviews.freebsd.org/D5774
2016-03-30 14:42:09 +00:00
Ed Maste
dae2d550d6 libc: stop exporting curbrk and minbrk in the private namespace
They are not used anywhere else in the base system and are an internal
implementation detail that does not need to be exposed.

Reviewed by:	kib
Sponsored by:	The FreeBSD Foundation
Differential Revision:	https://reviews.freebsd.org/D5728
2016-03-24 18:47:19 +00:00
Nathan Whitehorn
97a5390e6d Make unions in PowerPC libc endian-safe. 2016-02-26 20:38:23 +00:00
Craig Rodrigues
6874645fa9 Add include for declaration of _set_tp(). Eliminates -Wmissing-prototypes warnings. 2015-09-20 04:59:01 +00:00
Konstantin Belousov
0538aafc41 The lseek(2), mmap(2), truncate(2), ftruncate(2), pread(2), and
pwrite(2) syscalls are wrapped to provide compatibility with pre-7.x
kernels which required padding before the off_t parameter.  The
fcntl(2) contains compatibility code to handle kernels before the
struct flock was changed during the 8.x CURRENT development.  The
shims were reasonable to allow easier revert to the older kernel at
that time.

Now, two or three major releases later, shims do not serve any
purpose.  Such old kernels cannot handle current libc, so revert the
compatibility code.

Make padded syscalls support conditional under the COMPAT6 config
option.  For COMPAT32, the syscalls were under COMPAT6 already.

Remove WITHOUT_SYSCALL_COMPAT build option, which only purpose was to
(partially) disable the removed shims.

Reviewed by:	jhb, imp (previous versions)
Discussed with:	peter
Sponsored by:	The FreeBSD Foundation
MFC after:	1 week
2015-04-18 21:50:13 +00:00
Ed Maste
541236cf60 libc: Eliminate duplicate copies of __vdso_gettc.c
Sponsored by:	The FreeBSD Foundation
Differential Revision:	https://reviews.freebsd.org/D2152
2015-04-02 21:18:11 +00:00
Nathan Whitehorn
1ee3532451 Save and restore non-volatile floating-point registers during longjmp().
This should also save and restore non-volatile Altivec registers, but that
needs to wait on solving two problems:
1. Adding the nonvolatile vector registers means we need 5 more than _JBLEN
   entries in jmp_buf on 32-bit targets (64-bit is OK).
2. Need to figure out how to determine if saving/restoring vector regs
   is supported on the current CPU from userland.

MFC after:	1 month
2015-03-08 19:37:08 +00:00
Ed Maste
4b12fb6103 Remove duplicate copies of trivial getcontextx.c
Only i386 and amd64 provide a non-trivial __getcontextx(). Use a common
trivial implementation in gen/ for other architectures, rather than
copying the file to each MD subdirectory.

Reviewed by:	kib
Sponsored by:	The FreeBSD Foundation
Differential Revision:	https://reviews.freebsd.org/D1472
2015-01-12 18:13:38 +00:00
Justin Hibbits
85eda151ff Avoid use of register variables. Clang 3.5 treats this as undefined behavior,
and bad things happen.

MFC after:	1 week
2015-01-06 03:50:43 +00:00
Baptiste Daroussin
ad9bbe9854 Ensure that every ENTRY(foo) has a matching END(foo).
It allows to build with newer binutils

Differential Revision:	https://reviews.freebsd.org/D877
Reviewed by:	jhibbits
2014-10-01 15:00:21 +00:00
Warner Losh
a5fc5b6223 Convert from WITHOUT_SYSCALL_COMPAT to MK_SYSCALL_COMPAT. 2014-04-05 17:54:43 +00:00
Marcel Moolenaar
8876613dc5 Replace use of ${.CURDIR} by ${LIBC_SRCTOP} and define ${LIBC_SRCTOP}
if not already defined. This allows building libc from outside of
lib/libc using a reach-over makefile.

A typical use-case is to build a standard ILP32 version and a COMPAT32
version in a single iteration by building the COMPAT32 version using a
reach-over makefile.

Obtained from:	Juniper Networks, Inc.
2014-03-04 02:19:39 +00:00