Time functions are directly implemented in assembly in arm64, and it
is desirable to keep it this way for performance reasons (everything
fits in registers, so that the stack is not used at all). However, the
current implementation is quite difficult to read and understand (even
considering it's assembly). Additionally, due to the structure of
__kernel_clock_gettime, which heavily uses conditional branches to
share code between the different clocks, it is difficult to support a
new clock without making the branches even harder to follow.
This commit completely refactors the structure of clock_gettime (and
gettimeofday along the way) while keeping exactly the same algorithms.
We no longer try to share code; instead, macros provide common
operations. This new approach comes with a number of advantages:
- In clock_gettime, clock implementations are no longer interspersed,
making them much more readable. Additionally, macros only use
registers passed as arguments or reserved with .req, this way it is
easy to make sure that registers are properly allocated. To avoid a
large number of branches in a given execution path, a jump table is
used; a normal execution uses 3 unconditional branches.
- __do_get_tspec has been replaced with 2 macros (get_ts_clock_mono,
get_clock_shifted_nsec) and explicit loading of data from the vDSO
page. Consequently, clock_gettime and gettimeofday are now leaf
functions, and saving x30 (lr) is no longer necessary.
- Variables protected by tb_seq_count are now loaded all at once,
allowing to merge the seqcnt_read macro into seqcnt_check.
- For CLOCK_REALTIME_COARSE, removed an unused load of the wall to
monotonic timespec.
- For CLOCK_MONOTONIC_COARSE, removed a few shift instructions.
Obviously, the downside of sharing less code is an increase in code
size. However since the vDSO has its own code page, this does not
really matter, as long as the size of the DSO remains below 4 kB. For
now this should be all right:
Before After
vdso.so size (B) 2776 3000
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Reviewed-by: Dave Martin <dave.martin@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
arm64/kernel/{vdso,signal}.c include vdso-offsets.h, as well as any
file that includes asm/vdso.h. Therefore, vdso-offsets.h must be
generated before these files are compiled.
The current rules in arm64/kernel/Makefile do not actually enforce
this, because even though $(obj)/vdso is listed as a prerequisite for
vdso-offsets.h, this does not result in the intended effect of
building the vdso subdirectory (before all the other objects). As a
consequence, depending on the order in which the rules are followed,
vdso-offsets.h is updated or not before arm64/kernel/{vdso,signal}.o
are built. The current rules also impose an unnecessary dependency on
vdso-offsets.h for all arm64/kernel/*.o, resulting in unnecessary
rebuilds. This is made obvious when using make -j:
touch arch/arm64/kernel/vdso/gettimeofday.S && make -j$NCPUS arch/arm64/kernel
will sometimes result in none of arm64/kernel/*.o being
rebuilt, sometimes all of them, or even just some of them.
It is quite difficult to ensure that a header is generated before it
is used with recursive Makefiles by using normal rules. Instead,
arch-specific generated headers are normally built in the archprepare
recipe in the arch Makefile (see for instance arch/ia64/Makefile).
Unfortunately, asm-offsets.h is included in gettimeofday.S, and must
therefore be generated before vdso-offsets.h, which is not the case if
archprepare is used. For this reason, a rule run after archprepare has
to be used.
This commit adds rules in arm64/Makefile to build vdso-offsets.h
during the prepare step, ensuring that vdso-offsets.h is generated
before building anything. It also removes the now-unnecessary
dependencies on vdso-offsets.h in arm64/kernel/Makefile. Finally, it
removes the duplication of asm-offsets.h between arm64/kernel/vdso/
and include/generated/ and makes include/generated/vdso-offsets.h a
target in arm64/kernel/vdso/Makefile.
Cc: Will Deacon <will.deacon@arm.com>
Cc: Michal Marek <mmarek@suse.com>
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This reverts commit 90f777beb7.
While this commit was aimed at fixing the dependencies, with a large
make -j the vdso-offsets.h file is not generated, leading to build
failures.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
arch/arm64/kernel/{vdso,signal}.c include generated/vdso-offsets.h, and
therefore the symbol offsets must be generated before these files are
compiled.
The current rules in arm64/kernel/Makefile do not actually enforce
this, because even though $(obj)/vdso is listed as a prerequisite for
vdso-offsets.h, this does not result in the intended effect of
building the vdso subdirectory (before all the other objects). As a
consequence, depending on the order in which the rules are followed,
vdso-offsets.h is updated or not before arm64/kernel/{vdso,signal}.o
are built. The current rules also impose an unnecessary dependency on
vdso-offsets.h for all arm64/kernel/*.o, resulting in unnecessary
rebuilds.
This patch removes the arch/arm64/kernel/vdso/vdso-offsets.h file
generation, leaving only the include/generated/vdso-offsets.h one. It
adds a forced dependency check of the vdso-offsets.h file in
arch/arm64/kernel/Makefile which, if not up to date according to the
arch/arm64/kernel/vdso/Makefile rules (depending on vdso.so.dbg), will
trigger the vdso/ subdirectory build and vdso-offsets.h re-generation.
Automatic kbuild dependency rules between kernel/{vdso,signal}.c rules
and vdso-offsets.h will guarantee that the vDSO object is built first,
followed by the generated symbol offsets header file.
Reported-by: Kevin Brodsky <kevin.brodsky@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Although the arm64 vDSO is cleanly separated by code/data with the
code being read-only in userspace mappings, the code page is still
writable from the kernel. There have been exploits (such as
http://itszn.com/blog/?p=21) that take advantage of this on x86 to go
from a bad kernel write to full root.
Prevent this specific exploit on arm64 by putting the vDSO code page
in read-only memory as well.
Before the change:
[ 3.138366] vdso: 2 pages (1 code @ ffffffc000a71000, 1 data @ ffffffc000a70000)
---[ Kernel Mapping ]---
0xffffffc000000000-0xffffffc000082000 520K RW NX SHD AF UXN MEM/NORMAL
0xffffffc000082000-0xffffffc000200000 1528K ro x SHD AF UXN MEM/NORMAL
0xffffffc000200000-0xffffffc000800000 6M ro x SHD AF BLK UXN MEM/NORMAL
0xffffffc000800000-0xffffffc0009b6000 1752K ro x SHD AF UXN MEM/NORMAL
0xffffffc0009b6000-0xffffffc000c00000 2344K RW NX SHD AF UXN MEM/NORMAL
0xffffffc000c00000-0xffffffc008000000 116M RW NX SHD AF BLK UXN MEM/NORMAL
0xffffffc00c000000-0xffffffc07f000000 1840M RW NX SHD AF BLK UXN MEM/NORMAL
0xffffffc800000000-0xffffffc840000000 1G RW NX SHD AF BLK UXN MEM/NORMAL
0xffffffc840000000-0xffffffc87ae00000 942M RW NX SHD AF BLK UXN MEM/NORMAL
0xffffffc87ae00000-0xffffffc87ae70000 448K RW NX SHD AF UXN MEM/NORMAL
0xffffffc87af80000-0xffffffc87af8a000 40K RW NX SHD AF UXN MEM/NORMAL
0xffffffc87af8b000-0xffffffc87b000000 468K RW NX SHD AF UXN MEM/NORMAL
0xffffffc87b000000-0xffffffc87fe00000 78M RW NX SHD AF BLK UXN MEM/NORMAL
0xffffffc87fe00000-0xffffffc87ff50000 1344K RW NX SHD AF UXN MEM/NORMAL
0xffffffc87ff90000-0xffffffc87ffa0000 64K RW NX SHD AF UXN MEM/NORMAL
0xffffffc87fff0000-0xffffffc880000000 64K RW NX SHD AF UXN MEM/NORMAL
After:
[ 3.138368] vdso: 2 pages (1 code @ ffffffc0006de000, 1 data @ ffffffc000a74000)
---[ Kernel Mapping ]---
0xffffffc000000000-0xffffffc000082000 520K RW NX SHD AF UXN MEM/NORMAL
0xffffffc000082000-0xffffffc000200000 1528K ro x SHD AF UXN MEM/NORMAL
0xffffffc000200000-0xffffffc000800000 6M ro x SHD AF BLK UXN MEM/NORMAL
0xffffffc000800000-0xffffffc0009b8000 1760K ro x SHD AF UXN MEM/NORMAL
0xffffffc0009b8000-0xffffffc000c00000 2336K RW NX SHD AF UXN MEM/NORMAL
0xffffffc000c00000-0xffffffc008000000 116M RW NX SHD AF BLK UXN MEM/NORMAL
0xffffffc00c000000-0xffffffc07f000000 1840M RW NX SHD AF BLK UXN MEM/NORMAL
0xffffffc800000000-0xffffffc840000000 1G RW NX SHD AF BLK UXN MEM/NORMAL
0xffffffc840000000-0xffffffc87ae00000 942M RW NX SHD AF BLK UXN MEM/NORMAL
0xffffffc87ae00000-0xffffffc87ae70000 448K RW NX SHD AF UXN MEM/NORMAL
0xffffffc87af80000-0xffffffc87af8a000 40K RW NX SHD AF UXN MEM/NORMAL
0xffffffc87af8b000-0xffffffc87b000000 468K RW NX SHD AF UXN MEM/NORMAL
0xffffffc87b000000-0xffffffc87fe00000 78M RW NX SHD AF BLK UXN MEM/NORMAL
0xffffffc87fe00000-0xffffffc87ff50000 1344K RW NX SHD AF UXN MEM/NORMAL
0xffffffc87ff90000-0xffffffc87ffa0000 64K RW NX SHD AF UXN MEM/NORMAL
0xffffffc87fff0000-0xffffffc880000000 64K RW NX SHD AF UXN MEM/NORMAL
Inspired by https://lkml.org/lkml/2016/1/19/494 based on work by the
PaX Team, Brad Spengler, and Kees Cook.
Signed-off-by: David Brown <david.brown@linaro.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
[catalin.marinas@arm.com: removed superfluous __PAGE_ALIGNED_DATA]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
On a cross-toolchain without glibc support, libgcov may not be
available, and attempting to build an arm64 kernel with GCOV
enabled then results in a build error:
/home/arnd/cross-gcc/lib/gcc/aarch64-linux/5.2.1/../../../../aarch64-linux/bin/ld: cannot find -lgcov
We don't really want to link libgcov into the vdso anyway, so
this patch just disables GCOV in the vdso directory, just as
we do for most other architectures.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
When building the kernel with a bare-metal (ELF) toolchain, the -shared
option may not be passed down to collect2, resulting in silent corruption
of the vDSO image (in particular, the DYNAMIC section is omitted).
The effect of this corruption is that the dynamic linker fails to find
the vDSO symbols and libc is instead used for the syscalls that we
intended to optimise (e.g. gettimeofday). Functionally, there is no
issue as the sigreturn trampoline is still intact and located by the
kernel.
This patch fixes the problem by explicitly passing -shared to the linker
when building the vDSO.
Cc: <stable@vger.kernel.org>
Reported-by: Szabolcs Nagy <Szabolcs.Nagy@arm.com>
Reported-by: James Greenlaigh <james.greenhalgh@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The vdso implementation of clock_getres currently returns 0 (success)
whenever a null timespec is provided by the caller, regardless of the
clock id supplied.
This behavior is incorrect. It should fall back to syscall when an
unrecognized clock id is passed, even when the timespec argument is
null. This ensures that clock_getres always returns an error for
invalid clock ids.
Signed-off-by: Nathan Lynch <nathan_lynch@mentor.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Building a kernel with CPU_BIG_ENDIAN fails if there are stale objects
from a !CPU_BIG_ENDIAN build. Due to a missing FORCE prerequisite on an
if_changed rule in the VDSO Makefile, we attempt to link a stale LE
object into the new BE kernel.
According to Documentation/kbuild/makefiles.txt, FORCE is required for
if_changed rules and forgetting it is a common mistake, so fix it by
'Forcing' the build of vdso. This patch fixes build errors like these:
arch/arm64/kernel/vdso/note.o: compiled for a little endian system and target is big endian
failed to merge target specific data of file arch/arm64/kernel/vdso/note.o
arch/arm64/kernel/vdso/sigreturn.o: compiled for a little endian system and target is big endian
failed to merge target specific data of file arch/arm64/kernel/vdso/sigreturn.o
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Arun Chandran <achandran@mvista.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Andy pointed out that binutils generates additional sections in the vdso
image (e.g. section string table) which, if our .text section gets big
enough, could cross a page boundary and end up screwing up the location
where the kernel expects to put the data page.
This patch solves the issue in the same manner as x86_32, by moving the
data page before the code pages.
Cc: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
When __kernel_clock_gettime is called with a CLOCK_MONOTONIC_COARSE or
CLOCK_REALTIME_COARSE clock id, it returns incorrectly to whatever the
caller has placed in x2 ("ret x2" to return from the fast path). Fix
this by saving x30/LR to x2 only in code that will call
__do_get_tspec, restoring x30 afterward, and using a plain "ret" to
return from the routine.
Also: while the resulting tv_nsec value for CLOCK_REALTIME and
CLOCK_MONOTONIC must be computed using intermediate values that are
left-shifted by cs_shift (x12, set by __do_get_tspec), the results for
coarse clocks should be calculated using unshifted values
(xtime_coarse_nsec is in units of actual nanoseconds). The current
code shifts intermediate values by x12 unconditionally, but x12 is
uninitialized when servicing a coarse clock. Fix this by setting x12
to 0 once we know we are dealing with a coarse clock id.
Signed-off-by: Nathan Lynch <nathan_lynch@mentor.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Whilst the text segment for our VDSO is marked as PT_LOAD in the ELF
headers, it is mapped by the kernel and not actually subject to
demand-paging. ld doesn't realise this, and emits a p_align field of 64k
(the maximum supported page size), which conflicts with the load address
picked by the kernel on 4k systems, which will be 4k aligned. This
causes GDB to fail with "Failed to read a valid object file image from
memory" when attempting to load the VDSO.
This patch passes the -n option to ld, which prevents it from aligning
PT_LOAD segments to the maximum page size.
Cc: <stable@vger.kernel.org>
Reported-by: Kyle McMartin <kyle@redhat.com>
Acked-by: Kyle McMartin <kyle@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch is an arm64 version of ce73ec6db4 ("powerpc/vdso: Remove
redundant locking in update_vsyscall_tz()").
Timezone data is not protected, so the sequence counter is not required
to ensure consistency. Furthermore, having multiple paths updating the
counter leads to a race between update_vsyscall and update_vsyscall_tz,
so remove the timezone sequence counting from both the kernel and the
vdso.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
We want to use the virtual counter at EL0, as the physical counter
may not track the current clocksource for guests running under a
hypervisor.
This patch updates the vdso and generic timer driver to use the virtual
counter. The kernel EL2 entry code is also updated to ensure that the
virtual offset is initialised to zero.
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Shifting the nanosecond component of the computed timespec early can
lead to sub-ns inaccuracies when using the truncated value as input to
further arithmetic for things like conversions to monotonic time.
This patch defers the timespec shifting until after the final value has
been computed.
Reported-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
In preparation for sub-ns precision in the vdso timespec maths, change
the __do_get_tspec register allocation so that we return the clocksource
shift value instead of the unused xtime tspec.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
When returning coarse realtime values from clock_gettime, we must still
check the sequence counter to ensure that the kernel does not update
the vdso datapage whilst we are loading the coarse timespec as this
could potentially result in time appearing to go backwards.
This patch delays the coarse realtime check until after we have loaded
successfully from the vdso datapage. This does mean that we always load
the wtm timespec, but conditionalising the load and adding an extra
sequence test is unlikely to buy us anything other than messy code,
particularly as the sequence test implies a read barrier.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The generic timer clocksource has 56 bits of precision and as such must
be masked appropriately after we have read it. The current mask
generated by a movn instruction is off by 4 bits, so we accidentally
include the top 4 bits in the final value.
This patch fixes the broken mask.
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This patch adds VDSO support for 64-bit applications. The VDSO code is
currently used for sys_rt_sigreturn() and optimised gettimeofday()
(using the user-accessible generic counter).
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Nicolas Pitre <nico@linaro.org>
Acked-by: Olof Johansson <olof@lixom.net>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
