linux/arch/powerpc/kernel/vmlinux.lds.S
Naveen N. Rao 67361cf807 powerpc/ftrace: Handle large kernel configs
Currently, we expect to be able to reach ftrace_caller() from all
ftrace-enabled functions through a single relative branch. With large
kernel configs, we see functions outside of 32MB of ftrace_caller()
causing ftrace_init() to bail.

In such configurations, gcc/ld emits two types of trampolines for mcount():
1. A long_branch, which has a single branch to mcount() for functions that
   are one hop away from mcount():
	c0000000019e8544 <00031b56.long_branch._mcount>:
	c0000000019e8544:	4a 69 3f ac 	b       c00000000007c4f0 <._mcount>

2. A plt_branch, for functions that are farther away from mcount():
	c0000000051f33f8 <0008ba04.plt_branch._mcount>:
	c0000000051f33f8:	3d 82 ff a4 	addis   r12,r2,-92
	c0000000051f33fc:	e9 8c 04 20 	ld      r12,1056(r12)
	c0000000051f3400:	7d 89 03 a6 	mtctr   r12
	c0000000051f3404:	4e 80 04 20 	bctr

We can reuse those trampolines for ftrace if we can have those
trampolines go to ftrace_caller() instead. However, with ABIv2, we
cannot depend on r2 being valid. As such, we use only the long_branch
trampolines by patching those to instead branch to ftrace_caller or
ftrace_regs_caller.

In addition, we add additional trampolines around .text and .init.text
to catch locations that are covered by the plt branches. This allows
ftrace to work with most large kernel configurations.

For now, we always patch the trampolines to go to ftrace_regs_caller,
which is slightly inefficient. This can be optimized further at a later
point.

Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-10-20 13:26:47 +11:00

395 lines
8.6 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
#ifdef CONFIG_PPC64
#define PROVIDE32(x) PROVIDE(__unused__##x)
#else
#define PROVIDE32(x) PROVIDE(x)
#endif
#define BSS_FIRST_SECTIONS *(.bss.prominit)
#include <asm/page.h>
#include <asm-generic/vmlinux.lds.h>
#include <asm/cache.h>
#include <asm/thread_info.h>
#if defined(CONFIG_STRICT_KERNEL_RWX) && !defined(CONFIG_PPC32)
#define STRICT_ALIGN_SIZE (1 << 24)
#else
#define STRICT_ALIGN_SIZE PAGE_SIZE
#endif
ENTRY(_stext)
PHDRS {
kernel PT_LOAD FLAGS(7); /* RWX */
notes PT_NOTE FLAGS(0);
dummy PT_NOTE FLAGS(0);
/* binutils < 2.18 has a bug that makes it misbehave when taking an
ELF file with all segments at load address 0 as input. This
happens when running "strip" on vmlinux, because of the AT() magic
in this linker script. People using GCC >= 4.2 won't run into
this problem, because the "build-id" support will put some data
into the "notes" segment (at a non-zero load address).
To work around this, we force some data into both the "dummy"
segment and the kernel segment, so the dummy segment will get a
non-zero load address. It's not enough to always create the
"notes" segment, since if nothing gets assigned to it, its load
address will be zero. */
}
#ifdef CONFIG_PPC64
OUTPUT_ARCH(powerpc:common64)
jiffies = jiffies_64;
#else
OUTPUT_ARCH(powerpc:common)
jiffies = jiffies_64 + 4;
#endif
SECTIONS
{
. = KERNELBASE;
/*
* Text, read only data and other permanent read-only sections
*/
_text = .;
_stext = .;
/*
* Head text.
* This needs to be in its own output section to avoid ld placing
* branch trampoline stubs randomly throughout the fixed sections,
* which it will do (even if the branch comes from another section)
* in order to optimize stub generation.
*/
.head.text : AT(ADDR(.head.text) - LOAD_OFFSET) {
#ifdef CONFIG_PPC64
KEEP(*(.head.text.first_256B));
#ifdef CONFIG_PPC_BOOK3E
#else
KEEP(*(.head.text.real_vectors));
*(.head.text.real_trampolines);
KEEP(*(.head.text.virt_vectors));
*(.head.text.virt_trampolines);
# if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
KEEP(*(.head.data.fwnmi_page));
# endif
#endif
#else /* !CONFIG_PPC64 */
HEAD_TEXT
#endif
} :kernel
__head_end = .;
#ifdef CONFIG_PPC64
/*
* BLOCK(0) overrides the default output section alignment because
* this needs to start right after .head.text in order for fixed
* section placement to work.
*/
.text BLOCK(0) : AT(ADDR(.text) - LOAD_OFFSET) {
#ifdef CONFIG_LD_HEAD_STUB_CATCH
KEEP(*(.linker_stub_catch));
. = . ;
#endif
#else
.text : AT(ADDR(.text) - LOAD_OFFSET) {
ALIGN_FUNCTION();
#endif
/* careful! __ftr_alt_* sections need to be close to .text */
*(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text);
#ifdef CONFIG_PPC64
*(.tramp.ftrace.text);
#endif
SCHED_TEXT
CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
SOFTIRQENTRY_TEXT
/*
* -Os builds call FP save/restore functions. The powerpc64
* linker generates those on demand in the .sfpr section.
* .sfpr gets placed at the beginning of a group of input
* sections, which can break start-of-text offset if it is
* included with the main text sections, so put it by itself.
*/
*(.sfpr);
MEM_KEEP(init.text)
MEM_KEEP(exit.text)
#ifdef CONFIG_PPC32
*(.got1)
__got2_start = .;
*(.got2)
__got2_end = .;
#endif /* CONFIG_PPC32 */
} :kernel
. = ALIGN(PAGE_SIZE);
_etext = .;
PROVIDE32 (etext = .);
/* Read-only data */
RO_DATA(PAGE_SIZE)
#ifdef CONFIG_PPC64
. = ALIGN(8);
__stf_entry_barrier_fixup : AT(ADDR(__stf_entry_barrier_fixup) - LOAD_OFFSET) {
__start___stf_entry_barrier_fixup = .;
*(__stf_entry_barrier_fixup)
__stop___stf_entry_barrier_fixup = .;
}
. = ALIGN(8);
__stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) {
__start___stf_exit_barrier_fixup = .;
*(__stf_exit_barrier_fixup)
__stop___stf_exit_barrier_fixup = .;
}
. = ALIGN(8);
__rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) {
__start___rfi_flush_fixup = .;
*(__rfi_flush_fixup)
__stop___rfi_flush_fixup = .;
}
#endif /* CONFIG_PPC64 */
#ifdef CONFIG_PPC_BARRIER_NOSPEC
. = ALIGN(8);
__spec_barrier_fixup : AT(ADDR(__spec_barrier_fixup) - LOAD_OFFSET) {
__start___barrier_nospec_fixup = .;
*(__barrier_nospec_fixup)
__stop___barrier_nospec_fixup = .;
}
#endif /* CONFIG_PPC_BARRIER_NOSPEC */
EXCEPTION_TABLE(0)
NOTES :kernel :notes
/* The dummy segment contents for the bug workaround mentioned above
near PHDRS. */
.dummy : AT(ADDR(.dummy) - LOAD_OFFSET) {
LONG(0)
LONG(0)
LONG(0)
} :kernel :dummy
/*
* Init sections discarded at runtime
*/
. = ALIGN(STRICT_ALIGN_SIZE);
__init_begin = .;
. = ALIGN(PAGE_SIZE);
.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
_sinittext = .;
INIT_TEXT
_einittext = .;
#ifdef CONFIG_PPC64
*(.tramp.ftrace.init);
#endif
} :kernel
/* .exit.text is discarded at runtime, not link time,
* to deal with references from __bug_table
*/
.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
EXIT_TEXT
}
.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
INIT_DATA
__vtop_table_begin = .;
KEEP(*(.vtop_fixup));
__vtop_table_end = .;
__ptov_table_begin = .;
KEEP(*(.ptov_fixup));
__ptov_table_end = .;
}
.init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
INIT_SETUP(16)
}
.initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
INIT_CALLS
}
.con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
CON_INITCALL
}
SECURITY_INIT
. = ALIGN(8);
__ftr_fixup : AT(ADDR(__ftr_fixup) - LOAD_OFFSET) {
__start___ftr_fixup = .;
KEEP(*(__ftr_fixup))
__stop___ftr_fixup = .;
}
. = ALIGN(8);
__mmu_ftr_fixup : AT(ADDR(__mmu_ftr_fixup) - LOAD_OFFSET) {
__start___mmu_ftr_fixup = .;
KEEP(*(__mmu_ftr_fixup))
__stop___mmu_ftr_fixup = .;
}
. = ALIGN(8);
__lwsync_fixup : AT(ADDR(__lwsync_fixup) - LOAD_OFFSET) {
__start___lwsync_fixup = .;
KEEP(*(__lwsync_fixup))
__stop___lwsync_fixup = .;
}
#ifdef CONFIG_PPC64
. = ALIGN(8);
__fw_ftr_fixup : AT(ADDR(__fw_ftr_fixup) - LOAD_OFFSET) {
__start___fw_ftr_fixup = .;
KEEP(*(__fw_ftr_fixup))
__stop___fw_ftr_fixup = .;
}
#endif
.init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
INIT_RAM_FS
}
PERCPU_SECTION(L1_CACHE_BYTES)
. = ALIGN(8);
.machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
__machine_desc_start = . ;
KEEP(*(.machine.desc))
__machine_desc_end = . ;
}
#ifdef CONFIG_RELOCATABLE
. = ALIGN(8);
.dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET)
{
#ifdef CONFIG_PPC32
__dynamic_symtab = .;
#endif
*(.dynsym)
}
.dynstr : AT(ADDR(.dynstr) - LOAD_OFFSET) { *(.dynstr) }
.dynamic : AT(ADDR(.dynamic) - LOAD_OFFSET)
{
__dynamic_start = .;
*(.dynamic)
}
.hash : AT(ADDR(.hash) - LOAD_OFFSET) { *(.hash) }
.interp : AT(ADDR(.interp) - LOAD_OFFSET) { *(.interp) }
.rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET)
{
__rela_dyn_start = .;
*(.rela*)
}
#endif
/* .exit.data is discarded at runtime, not link time,
* to deal with references from .exit.text
*/
.exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
EXIT_DATA
}
/* freed after init ends here */
. = ALIGN(PAGE_SIZE);
__init_end = .;
/*
* And now the various read/write data
*/
. = ALIGN(PAGE_SIZE);
_sdata = .;
#ifdef CONFIG_PPC32
.data : AT(ADDR(.data) - LOAD_OFFSET) {
DATA_DATA
*(.data.rel*)
*(SDATA_MAIN)
*(.sdata2)
*(.got.plt) *(.got)
*(.plt)
}
#else
.data : AT(ADDR(.data) - LOAD_OFFSET) {
DATA_DATA
*(.data.rel*)
*(.toc1)
*(.branch_lt)
}
.opd : AT(ADDR(.opd) - LOAD_OFFSET) {
__start_opd = .;
KEEP(*(.opd))
__end_opd = .;
}
. = ALIGN(256);
.got : AT(ADDR(.got) - LOAD_OFFSET) {
__toc_start = .;
#ifndef CONFIG_RELOCATABLE
__prom_init_toc_start = .;
arch/powerpc/kernel/prom_init.o*(.toc .got)
__prom_init_toc_end = .;
#endif
*(.got)
*(.toc)
}
#endif
/* The initial task and kernel stack */
INIT_TASK_DATA_SECTION(THREAD_SIZE)
.data..page_aligned : AT(ADDR(.data..page_aligned) - LOAD_OFFSET) {
PAGE_ALIGNED_DATA(PAGE_SIZE)
}
.data..cacheline_aligned : AT(ADDR(.data..cacheline_aligned) - LOAD_OFFSET) {
CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
}
.data..read_mostly : AT(ADDR(.data..read_mostly) - LOAD_OFFSET) {
READ_MOSTLY_DATA(L1_CACHE_BYTES)
}
. = ALIGN(PAGE_SIZE);
.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
NOSAVE_DATA
}
BUG_TABLE
. = ALIGN(PAGE_SIZE);
_edata = .;
PROVIDE32 (edata = .);
/*
* And finally the bss
*/
BSS_SECTION(0, 0, 0)
. = ALIGN(PAGE_SIZE);
_end = . ;
PROVIDE32 (end = .);
STABS_DEBUG
DWARF_DEBUG
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
*(.glink .iplt .plt .rela* .comment)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
}
}