The total number of out-of-line (OOL) stubs required for function
tracing is determined using the following command:
$(OBJDUMP) -r -j __patchable_function_entries vmlinux.o
While this works correctly with GNU objdump, llvm-objdump does not
list the expected relocation records for this section. Fix this by
using the -d option and counting R_PPC64_ADDR64 relocation entries.
This works as desired with both objdump and llvm-objdump.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260127084926.34497-3-hbathini@linux.ibm.com
ARCH_USING_PATCHABLE_FUNCTION_ENTRY depends on toolchain support for
-fpatchable-function-entry option. The current script that checks
for this support only handles GCC. Rename the script and extend it
to detect support for -fpatchable-function-entry with Clang as well,
allowing clean cross-compilation with Clang toolchains.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260127084926.34497-2-hbathini@linux.ibm.com
Booting a KASAN=y kernel with the recently added ftrace out-of-line
support causes a warning at boot:
------------[ cut here ]------------
Stub index overflow (1729 > 1728)
WARNING: CPU: 0 PID: 0 at arch/powerpc/kernel/trace/ftrace.c:209 ftrace_init_nop+0x408/0x444
...
NIP ftrace_init_nop+0x408/0x444
LR ftrace_init_nop+0x404/0x444
Call Trace:
ftrace_init_nop+0x404/0x444 (unreliable)
ftrace_process_locs+0x544/0x8a0
ftrace_init+0xb4/0x22c
start_kernel+0x1dc/0x4d4
start_here_common+0x1c/0x20
...
ftrace failed to modify
[<c0000000030beddc>] _sub_I_65535_1+0x8/0x3c
actual: 00:00:00:60
Initializing ftrace call sites
ftrace record flags: 0
(0)
expected tramp: c00000000008b418
------------[ cut here ]------------
The function in question, _sub_I_65535_1 is some sort of trampoline
generated for KASAN, and is in the .text.startup section. That section
is part of INIT_TEXT, meaning is_kernel_inittext() returns true for it.
But the script that determines how many out-of-line ftrace stubs are
needed isn't doesn't consider .text.startup as inittext, leading to
there not being enough space for the init stubs.
Conversely the logic to calculate how many stubs are needed for the text
section isn't filtering out the symbols in .text.startup and so ends up
over counting.
Fix both problems by calculating the total number of stubs first, then
the number that count as inittext, and then subtract the latter from the
former to get the count for the text section.
Fixes: eec37961a5 ("powerpc64/ftrace: Move ftrace sequence out of line")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://patch.msgid.link/20241107111630.31068-1-mpe@ellerman.id.au
Implement support for DYNAMIC_FTRACE_WITH_CALL_OPS similar to the
arm64 implementation.
This works by patching-in a pointer to an associated ftrace_ops
structure before each traceable function. If multiple ftrace_ops are
associated with a call site, then a special ftrace_list_ops is used to
enable iterating over all the registered ftrace_ops. If no ftrace_ops
are associated with a call site, then a special ftrace_nop_ops structure
is used to render the ftrace call as a no-op. ftrace trampoline can then
read the associated ftrace_ops for a call site by loading from an offset
from the LR, and branch directly to the associated function.
The primary advantage with this approach is that we don't have to
iterate over all the registered ftrace_ops for call sites that have a
single ftrace_ops registered. This is the equivalent of implementing
support for dynamic ftrace trampolines, which set up a special ftrace
trampoline for each registered ftrace_ops and have individual call sites
branch into those directly.
A secondary advantage is that this gives us a way to add support for
direct ftrace callers without having to resort to using stubs. The
address of the direct call trampoline can be loaded from the ftrace_ops
structure.
To support this, we reserve a nop before each function on 32-bit
powerpc. For 64-bit powerpc, two nops are reserved before each
out-of-line stub. During ftrace activation, we update this location with
the associated ftrace_ops pointer. Then, on ftrace entry, we load from
this location and call into ftrace_ops->func().
For 64-bit powerpc, we ensure that the out-of-line stub area is
doubleword aligned so that ftrace_ops address can be updated atomically.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://patch.msgid.link/20241030070850.1361304-15-hbathini@linux.ibm.com
We are restricted to a .text size of ~32MB when using out-of-line
function profile sequence. Allow this to be extended up to the previous
limit of ~64MB by reserving space in the middle of .text.
A new config option CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE is
introduced to specify the number of function stubs that are reserved in
.text. On boot, ftrace utilizes stubs from this area first before using
the stub area at the end of .text.
A ppc64le defconfig has ~44k functions that can be traced. A more
conservative value of 32k functions is chosen as the default value of
PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE so that we do not allot more space
than necessary by default. If building a kernel that only has 32k
trace-able functions, we won't allot any more space at the end of .text
during the pass on vmlinux.o. Otherwise, only the remaining functions
get space for stubs at the end of .text. This default value should help
cover a .text size of ~48MB in total (including space reserved at the
end of .text which can cover up to 32MB), which should be sufficient for
most common builds. For a very small kernel build, this can be set to 0.
Or, this can be bumped up to a larger value to support vmlinux .text
size up to ~64MB.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://patch.msgid.link/20241030070850.1361304-14-hbathini@linux.ibm.com
Function profile sequence on powerpc includes two instructions at the
beginning of each function:
mflr r0
bl ftrace_caller
The call to ftrace_caller() gets nop'ed out during kernel boot and is
patched in when ftrace is enabled.
Given the sequence, we cannot return from ftrace_caller with 'blr' as we
need to keep LR and r0 intact. This results in link stack (return
address predictor) imbalance when ftrace is enabled. To address that, we
would like to use a three instruction sequence:
mflr r0
bl ftrace_caller
mtlr r0
Further more, to support DYNAMIC_FTRACE_WITH_CALL_OPS, we need to
reserve two instruction slots before the function. This results in a
total of five instruction slots to be reserved for ftrace use on each
function that is traced.
Move the function profile sequence out-of-line to minimize its impact.
To do this, we reserve a single nop at function entry using
-fpatchable-function-entry=1 and add a pass on vmlinux.o to determine
the total number of functions that can be traced. This is then used to
generate a .S file reserving the appropriate amount of space for use as
ftrace stubs, which is built and linked into vmlinux.
On bootup, the stub space is split into separate stubs per function and
populated with the proper instruction sequence. A pointer to the
associated stub is maintained in dyn_arch_ftrace.
For modules, space for ftrace stubs is reserved from the generic module
stub space.
This is restricted to and enabled by default only on 64-bit powerpc,
though there are some changes to accommodate 32-bit powerpc. This is
done so that 32-bit powerpc could choose to opt into this based on
further tests and benchmarks.
As an example, after this patch, kernel functions will have a single nop
at function entry:
<kernel_clone>:
addis r2,r12,467
addi r2,r2,-16028
nop
mfocrf r11,8
...
When ftrace is enabled, the nop is converted to an unconditional branch
to the stub associated with that function:
<kernel_clone>:
addis r2,r12,467
addi r2,r2,-16028
b ftrace_ool_stub_text_end+0x11b28
mfocrf r11,8
...
The associated stub:
<ftrace_ool_stub_text_end+0x11b28>:
mflr r0
bl ftrace_caller
mtlr r0
b kernel_clone+0xc
...
This change showed an improvement of ~10% in null_syscall benchmark on a
Power 10 system with ftrace enabled.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://patch.msgid.link/20241030070850.1361304-13-hbathini@linux.ibm.com
Function tracer on powerpc can only work with vmlinux having a .text
size of up to ~64MB due to powerpc branch instruction having a limited
relative branch range of 32MB. Today, this is only detected on kernel
boot when ftrace is init'ed. Add a post-link script to check the size of
.text so that we can detect this at build time, and break the build if
necessary.
We add a dependency on !COMPILE_TEST for CONFIG_HAVE_FUNCTION_TRACER so
that allyesconfig and other test builds can continue to work without
enabling ftrace.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://patch.msgid.link/20241030070850.1361304-11-hbathini@linux.ibm.com
Toolchains don't always default to the ELFv2 ABI. This is true with at
least the kernel.org toolchains. As such, pass -mabi=elfv2 explicitly to
ensure that we are testing against the correct compiler output.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
[mpe: Tweak comment wording]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20230530093821.298590-1-naveen@kernel.org
GCC v13.1 updated support for -fpatchable-function-entry on ppc64le to
emit nops after the local entry point, rather than before it. This
allows us to use this in the kernel for ftrace purposes. A new script is
added under arch/powerpc/tools/ to help detect if nops are emitted after
the function local entry point, or before the global entry point.
With -fpatchable-function-entry, we no longer have the profiling
instructions generated at function entry, so we only need to validate
the presence of two nops at the ftrace location in ftrace_init_nop(). We
patch the preceding instruction with 'mflr r0' to match the
-mprofile-kernel ABI for subsequent ftrace use.
This changes the profiling instructions used on ppc32. The default -pg
option emits an additional 'stw' instruction after 'mflr r0' and before
the branch to _mcount 'bl _mcount'. This is very similar to the original
-mprofile-kernel implementation on ppc64le, where an additional 'std'
instruction was used to save LR to its save location in the caller's
stackframe. Subsequently, this additional store was removed in later
compiler versions for performance reasons. The same reasons apply for
ppc32 so we only patch in a 'mflr r0'.
Signed-off-by: Naveen N Rao <naveen@kernel.org>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/68586d22981a2c3bb45f27a2b621173d10a7d092.1687166935.git.naveen@kernel.org
Relocating kernel at runtime is done very early in the boot process, so
it is not convenient to check for relocations there and react in case a
relocation was not expected.
Powerpc architecture has a script that allows to check at compile time
for such unexpected relocations: extract the common logic to scripts/
so that other architectures can take advantage of it.
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Reviewed-by: Anup Patel <anup@brainfault.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Link: https://lore.kernel.org/r/20230329045329.64565-5-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
When ld detects unaligned relocations, it emits R_PPC64_UADDR64
relocations instead of R_PPC64_RELATIVE. Currently R_PPC64_UADDR64 are
detected by arch/powerpc/tools/relocs_check.sh and expected not to work.
Below is a simple chunk to trigger this behaviour (this disables
optimization for the demonstration purposes only, this also happens with
-O1/-O2 when CONFIG_PRINTK_INDEX=y, for example):
\#pragma GCC push_options
\#pragma GCC optimize ("O0")
struct entry {
const char *file;
int line;
} __attribute__((packed));
static const struct entry e1 = { .file = __FILE__, .line = __LINE__ };
static const struct entry e2 = { .file = __FILE__, .line = __LINE__ };
...
prom_printf("e1=%s %lx %lx\n", e1.file, (unsigned long) e1.file, mfmsr());
prom_printf("e2=%s %lx\n", e2.file, (unsigned long) e2.file);
\#pragma GCC pop_options
This adds support for UADDR64 for 64bit. This reuses __dynamic_symtab
from the 32bit code which supports more relocation types already.
Because RELACOUNT includes only R_PPC64_RELATIVE, this replaces it with
RELASZ which is the size of all relocation records.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220309061822.168173-1-aik@ozlabs.ru
As of commit bdc48fa11e, scripts/checkpatch.pl now has a default line
length warning of 100 characters. The powerpc wrapper script was using
a length of 90 instead of 80 in order to make checkpatch less
restrictive, but now it's making it more restrictive instead.
I think it makes sense to just use the default value now.
Signed-off-by: Russell Currey <ruscur@russell.cc>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200828020542.393022-1-ruscur@russell.cc
Currently, using llvm-objtool, this script just silently succeeds without
actually do the intended checking. So this updates it to work properly.
Firstly, llvm-objdump does not add target symbol names to the end
of branches in its asm output, so we have to drop the branch to
__start_initialization_multiplatform using its address.
Secondly, v9 and 10 specify branch targets as .+<offset>, so we convert
those to actual addresses.
Thirdly, v10 and 11 error out on a vmlinux if given the -R option
complaining that it is "not a dynamic object". The -R does not make
any difference to the asm output, so remove it.
Lastly, v11 produces asm that is very similar to Gnu objtool (at least
as far as branches are concerned), so no further changes are necessary
to make it work.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200812081036.7969-3-sfr@canb.auug.org.au
