linux/arch/powerpc/kernel/vmlinux.lds.S
Michael Ellerman aa8a5e0062 powerpc/64s: Add support for RFI flush of L1-D cache
On some CPUs we can prevent the Meltdown vulnerability by flushing the
L1-D cache on exit from kernel to user mode, and from hypervisor to
guest.

This is known to be the case on at least Power7, Power8 and Power9. At
this time we do not know the status of the vulnerability on other CPUs
such as the 970 (Apple G5), pasemi CPUs (AmigaOne X1000) or Freescale
CPUs. As more information comes to light we can enable this, or other
mechanisms on those CPUs.

The vulnerability occurs when the load of an architecturally
inaccessible memory region (eg. userspace load of kernel memory) is
speculatively executed to the point where its result can influence the
address of a subsequent speculatively executed load.

In order for that to happen, the first load must hit in the L1,
because before the load is sent to the L2 the permission check is
performed. Therefore if no kernel addresses hit in the L1 the
vulnerability can not occur. We can ensure that is the case by
flushing the L1 whenever we return to userspace. Similarly for
hypervisor vs guest.

In order to flush the L1-D cache on exit, we add a section of nops at
each (h)rfi location that returns to a lower privileged context, and
patch that with some sequence. Newer firmwares are able to advertise
to us that there is a special nop instruction that flushes the L1-D.
If we do not see that advertised, we fall back to doing a displacement
flush in software.

For guest kernels we support migration between some CPU versions, and
different CPUs may use different flush instructions. So that we are
prepared to migrate to a machine with a different flush instruction
activated, we may have to patch more than one flush instruction at
boot if the hypervisor tells us to.

In the end this patch is mostly the work of Nicholas Piggin and
Michael Ellerman. However a cast of thousands contributed to analysis
of the issue, earlier versions of the patch, back ports testing etc.
Many thanks to all of them.

Tested-by: Jon Masters <jcm@redhat.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-01-10 21:27:06 +11:00

355 lines
7.6 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
#ifdef CONFIG_PPC64
#define PROVIDE32(x) PROVIDE(__unused__##x)
#else
#define PROVIDE32(x) PROVIDE(x)
#endif
#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
*(.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 .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text);
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);
__rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) {
__start___rfi_flush_fixup = .;
*(__rfi_flush_fixup)
__stop___rfi_flush_fixup = .;
}
#endif
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 = .;
INIT_TEXT_SECTION(PAGE_SIZE) :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 = .;
*(.vtop_fixup);
__vtop_table_end = .;
__ptov_table_begin = .;
*(.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 = .;
*(__ftr_fixup)
__stop___ftr_fixup = .;
}
. = ALIGN(8);
__mmu_ftr_fixup : AT(ADDR(__mmu_ftr_fixup) - LOAD_OFFSET) {
__start___mmu_ftr_fixup = .;
*(__mmu_ftr_fixup)
__stop___mmu_ftr_fixup = .;
}
. = ALIGN(8);
__lwsync_fixup : AT(ADDR(__lwsync_fixup) - LOAD_OFFSET) {
__start___lwsync_fixup = .;
*(__lwsync_fixup)
__stop___lwsync_fixup = .;
}
#ifdef CONFIG_PPC64
. = ALIGN(8);
__fw_ftr_fixup : AT(ADDR(__fw_ftr_fixup) - LOAD_OFFSET) {
__start___fw_ftr_fixup = .;
*(__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 = . ;
*(.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
*(.sdata)
*(.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) {
*(.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)
}
}