linux/arch/arm64/kernel/ftrace.c

329 lines
9.0 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* arch/arm64/kernel/ftrace.c
*
* Copyright (C) 2013 Linaro Limited
* Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
*/
#include <linux/ftrace.h>
#include <linux/module.h>
#include <linux/swab.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/debug-monitors.h>
#include <asm/ftrace.h>
#include <asm/insn.h>
#include <asm/patching.h>
#ifdef CONFIG_DYNAMIC_FTRACE
/*
* Replace a single instruction, which may be a branch or NOP.
* If @validate == true, a replaced instruction is checked against 'old'.
*/
static int ftrace_modify_code(unsigned long pc, u32 old, u32 new,
bool validate)
{
u32 replaced;
/*
* Note:
* We are paranoid about modifying text, as if a bug were to happen, it
* could cause us to read or write to someplace that could cause harm.
* Carefully read and modify the code with aarch64_insn_*() which uses
* probe_kernel_*(), and make sure what we read is what we expected it
* to be before modifying it.
*/
if (validate) {
if (aarch64_insn_read((void *)pc, &replaced))
return -EFAULT;
if (replaced != old)
return -EINVAL;
}
if (aarch64_insn_patch_text_nosync((void *)pc, new))
return -EPERM;
return 0;
}
/*
* Replace tracer function in ftrace_caller()
*/
int ftrace_update_ftrace_func(ftrace_func_t func)
{
unsigned long pc;
u32 new;
pc = (unsigned long)ftrace_call;
new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func,
AARCH64_INSN_BRANCH_LINK);
return ftrace_modify_code(pc, 0, new, false);
}
arm64: implement ftrace with regs This patch implements FTRACE_WITH_REGS for arm64, which allows a traced function's arguments (and some other registers) to be captured into a struct pt_regs, allowing these to be inspected and/or modified. This is a building block for live-patching, where a function's arguments may be forwarded to another function. This is also necessary to enable ftrace and in-kernel pointer authentication at the same time, as it allows the LR value to be captured and adjusted prior to signing. Using GCC's -fpatchable-function-entry=N option, we can have the compiler insert a configurable number of NOPs between the function entry point and the usual prologue. This also ensures functions are AAPCS compliant (e.g. disabling inter-procedural register allocation). For example, with -fpatchable-function-entry=2, GCC 8.1.0 compiles the following: | unsigned long bar(void); | | unsigned long foo(void) | { | return bar() + 1; | } ... to: | <foo>: | nop | nop | stp x29, x30, [sp, #-16]! | mov x29, sp | bl 0 <bar> | add x0, x0, #0x1 | ldp x29, x30, [sp], #16 | ret This patch builds the kernel with -fpatchable-function-entry=2, prefixing each function with two NOPs. To trace a function, we replace these NOPs with a sequence that saves the LR into a GPR, then calls an ftrace entry assembly function which saves this and other relevant registers: | mov x9, x30 | bl <ftrace-entry> Since patchable functions are AAPCS compliant (and the kernel does not use x18 as a platform register), x9-x18 can be safely clobbered in the patched sequence and the ftrace entry code. There are now two ftrace entry functions, ftrace_regs_entry (which saves all GPRs), and ftrace_entry (which saves the bare minimum). A PLT is allocated for each within modules. Signed-off-by: Torsten Duwe <duwe@suse.de> [Mark: rework asm, comments, PLTs, initialization, commit message] Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Torsten Duwe <duwe@suse.de> Cc: AKASHI Takahiro <takahiro.akashi@linaro.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Julien Thierry <jthierry@redhat.com> Cc: Will Deacon <will@kernel.org>
2019-02-08 18:10:19 +03:00
static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
{
#ifdef CONFIG_ARM64_MODULE_PLTS
arm64: implement ftrace with regs This patch implements FTRACE_WITH_REGS for arm64, which allows a traced function's arguments (and some other registers) to be captured into a struct pt_regs, allowing these to be inspected and/or modified. This is a building block for live-patching, where a function's arguments may be forwarded to another function. This is also necessary to enable ftrace and in-kernel pointer authentication at the same time, as it allows the LR value to be captured and adjusted prior to signing. Using GCC's -fpatchable-function-entry=N option, we can have the compiler insert a configurable number of NOPs between the function entry point and the usual prologue. This also ensures functions are AAPCS compliant (e.g. disabling inter-procedural register allocation). For example, with -fpatchable-function-entry=2, GCC 8.1.0 compiles the following: | unsigned long bar(void); | | unsigned long foo(void) | { | return bar() + 1; | } ... to: | <foo>: | nop | nop | stp x29, x30, [sp, #-16]! | mov x29, sp | bl 0 <bar> | add x0, x0, #0x1 | ldp x29, x30, [sp], #16 | ret This patch builds the kernel with -fpatchable-function-entry=2, prefixing each function with two NOPs. To trace a function, we replace these NOPs with a sequence that saves the LR into a GPR, then calls an ftrace entry assembly function which saves this and other relevant registers: | mov x9, x30 | bl <ftrace-entry> Since patchable functions are AAPCS compliant (and the kernel does not use x18 as a platform register), x9-x18 can be safely clobbered in the patched sequence and the ftrace entry code. There are now two ftrace entry functions, ftrace_regs_entry (which saves all GPRs), and ftrace_entry (which saves the bare minimum). A PLT is allocated for each within modules. Signed-off-by: Torsten Duwe <duwe@suse.de> [Mark: rework asm, comments, PLTs, initialization, commit message] Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Torsten Duwe <duwe@suse.de> Cc: AKASHI Takahiro <takahiro.akashi@linaro.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Julien Thierry <jthierry@redhat.com> Cc: Will Deacon <will@kernel.org>
2019-02-08 18:10:19 +03:00
struct plt_entry *plt = mod->arch.ftrace_trampolines;
if (addr == FTRACE_ADDR)
return &plt[FTRACE_PLT_IDX];
if (addr == FTRACE_REGS_ADDR &&
IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
arm64: implement ftrace with regs This patch implements FTRACE_WITH_REGS for arm64, which allows a traced function's arguments (and some other registers) to be captured into a struct pt_regs, allowing these to be inspected and/or modified. This is a building block for live-patching, where a function's arguments may be forwarded to another function. This is also necessary to enable ftrace and in-kernel pointer authentication at the same time, as it allows the LR value to be captured and adjusted prior to signing. Using GCC's -fpatchable-function-entry=N option, we can have the compiler insert a configurable number of NOPs between the function entry point and the usual prologue. This also ensures functions are AAPCS compliant (e.g. disabling inter-procedural register allocation). For example, with -fpatchable-function-entry=2, GCC 8.1.0 compiles the following: | unsigned long bar(void); | | unsigned long foo(void) | { | return bar() + 1; | } ... to: | <foo>: | nop | nop | stp x29, x30, [sp, #-16]! | mov x29, sp | bl 0 <bar> | add x0, x0, #0x1 | ldp x29, x30, [sp], #16 | ret This patch builds the kernel with -fpatchable-function-entry=2, prefixing each function with two NOPs. To trace a function, we replace these NOPs with a sequence that saves the LR into a GPR, then calls an ftrace entry assembly function which saves this and other relevant registers: | mov x9, x30 | bl <ftrace-entry> Since patchable functions are AAPCS compliant (and the kernel does not use x18 as a platform register), x9-x18 can be safely clobbered in the patched sequence and the ftrace entry code. There are now two ftrace entry functions, ftrace_regs_entry (which saves all GPRs), and ftrace_entry (which saves the bare minimum). A PLT is allocated for each within modules. Signed-off-by: Torsten Duwe <duwe@suse.de> [Mark: rework asm, comments, PLTs, initialization, commit message] Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Torsten Duwe <duwe@suse.de> Cc: AKASHI Takahiro <takahiro.akashi@linaro.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Julien Thierry <jthierry@redhat.com> Cc: Will Deacon <will@kernel.org>
2019-02-08 18:10:19 +03:00
return &plt[FTRACE_REGS_PLT_IDX];
#endif
arm64: implement ftrace with regs This patch implements FTRACE_WITH_REGS for arm64, which allows a traced function's arguments (and some other registers) to be captured into a struct pt_regs, allowing these to be inspected and/or modified. This is a building block for live-patching, where a function's arguments may be forwarded to another function. This is also necessary to enable ftrace and in-kernel pointer authentication at the same time, as it allows the LR value to be captured and adjusted prior to signing. Using GCC's -fpatchable-function-entry=N option, we can have the compiler insert a configurable number of NOPs between the function entry point and the usual prologue. This also ensures functions are AAPCS compliant (e.g. disabling inter-procedural register allocation). For example, with -fpatchable-function-entry=2, GCC 8.1.0 compiles the following: | unsigned long bar(void); | | unsigned long foo(void) | { | return bar() + 1; | } ... to: | <foo>: | nop | nop | stp x29, x30, [sp, #-16]! | mov x29, sp | bl 0 <bar> | add x0, x0, #0x1 | ldp x29, x30, [sp], #16 | ret This patch builds the kernel with -fpatchable-function-entry=2, prefixing each function with two NOPs. To trace a function, we replace these NOPs with a sequence that saves the LR into a GPR, then calls an ftrace entry assembly function which saves this and other relevant registers: | mov x9, x30 | bl <ftrace-entry> Since patchable functions are AAPCS compliant (and the kernel does not use x18 as a platform register), x9-x18 can be safely clobbered in the patched sequence and the ftrace entry code. There are now two ftrace entry functions, ftrace_regs_entry (which saves all GPRs), and ftrace_entry (which saves the bare minimum). A PLT is allocated for each within modules. Signed-off-by: Torsten Duwe <duwe@suse.de> [Mark: rework asm, comments, PLTs, initialization, commit message] Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Torsten Duwe <duwe@suse.de> Cc: AKASHI Takahiro <takahiro.akashi@linaro.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Julien Thierry <jthierry@redhat.com> Cc: Will Deacon <will@kernel.org>
2019-02-08 18:10:19 +03:00
return NULL;
}
/*
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
* Find the address the callsite must branch to in order to reach '*addr'.
*
* Due to the limited range of 'BL' instructions, modules may be placed too far
* away to branch directly and must use a PLT.
*
* Returns true when '*addr' contains a reachable target address, or has been
* modified to contain a PLT address. Returns false otherwise.
*/
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
struct module *mod,
unsigned long *addr)
{
unsigned long pc = rec->ip;
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
long offset = (long)*addr - (long)pc;
struct plt_entry *plt;
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
/*
* When the target is within range of the 'BL' instruction, use 'addr'
* as-is and branch to that directly.
*/
if (offset >= -SZ_128M && offset < SZ_128M)
return true;
arm64: module/ftrace: intialize PLT at load time Currently we lazily-initialize a module's ftrace PLT at runtime when we install the first ftrace call. To do so we have to apply a number of sanity checks, transiently mark the module text as RW, and perform an IPI as part of handling Neoverse-N1 erratum #1542419. We only expect the ftrace trampoline to point at ftrace_caller() (AKA FTRACE_ADDR), so let's simplify all of this by intializing the PLT at module load time, before the module loader marks the module RO and performs the intial I-cache maintenance for the module. Thus we can rely on the module having been correctly intialized, and can simplify the runtime work necessary to install an ftrace call in a module. This will also allow for the removal of module_disable_ro(). Tested by forcing ftrace_make_call() to use the module PLT, and then loading up a module after setting up ftrace with: | echo ":mod:<module-name>" > set_ftrace_filter; | echo function > current_tracer; | modprobe <module-name> Since FTRACE_ADDR is only defined when CONFIG_DYNAMIC_FTRACE is selected, we wrap its use along with most of module_init_ftrace_plt() with ifdeffery rather than using IS_ENABLED(). Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Torsten Duwe <duwe@suse.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: James Morse <james.morse@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org>
2019-10-17 17:26:38 +03:00
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
/*
* When the target is outside of the range of a 'BL' instruction, we
* must use a PLT to reach it. We can only place PLTs for modules, and
* only when module PLT support is built-in.
*/
if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
return false;
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
/*
* 'mod' is only set at module load time, but if we end up
* dealing with an out-of-range condition, we can assume it
* is due to a module being loaded far away from the kernel.
*
* NOTE: __module_text_address() must be called with preemption
* disabled, but we can rely on ftrace_lock to ensure that 'mod'
* retains its validity throughout the remainder of this code.
*/
if (!mod) {
preempt_disable();
mod = __module_text_address(pc);
preempt_enable();
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
}
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
if (WARN_ON(!mod))
return false;
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
plt = get_ftrace_plt(mod, *addr);
if (!plt) {
pr_err("ftrace: no module PLT for %ps\n", (void *)*addr);
return false;
}
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
*addr = (unsigned long)plt;
return true;
}
/*
* Turn on the call to ftrace_caller() in instrumented function
*/
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long pc = rec->ip;
u32 old, new;
if (!ftrace_find_callable_addr(rec, NULL, &addr))
return -EINVAL;
old = aarch64_insn_gen_nop();
new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
return ftrace_modify_code(pc, old, new, true);
}
arm64: implement ftrace with regs This patch implements FTRACE_WITH_REGS for arm64, which allows a traced function's arguments (and some other registers) to be captured into a struct pt_regs, allowing these to be inspected and/or modified. This is a building block for live-patching, where a function's arguments may be forwarded to another function. This is also necessary to enable ftrace and in-kernel pointer authentication at the same time, as it allows the LR value to be captured and adjusted prior to signing. Using GCC's -fpatchable-function-entry=N option, we can have the compiler insert a configurable number of NOPs between the function entry point and the usual prologue. This also ensures functions are AAPCS compliant (e.g. disabling inter-procedural register allocation). For example, with -fpatchable-function-entry=2, GCC 8.1.0 compiles the following: | unsigned long bar(void); | | unsigned long foo(void) | { | return bar() + 1; | } ... to: | <foo>: | nop | nop | stp x29, x30, [sp, #-16]! | mov x29, sp | bl 0 <bar> | add x0, x0, #0x1 | ldp x29, x30, [sp], #16 | ret This patch builds the kernel with -fpatchable-function-entry=2, prefixing each function with two NOPs. To trace a function, we replace these NOPs with a sequence that saves the LR into a GPR, then calls an ftrace entry assembly function which saves this and other relevant registers: | mov x9, x30 | bl <ftrace-entry> Since patchable functions are AAPCS compliant (and the kernel does not use x18 as a platform register), x9-x18 can be safely clobbered in the patched sequence and the ftrace entry code. There are now two ftrace entry functions, ftrace_regs_entry (which saves all GPRs), and ftrace_entry (which saves the bare minimum). A PLT is allocated for each within modules. Signed-off-by: Torsten Duwe <duwe@suse.de> [Mark: rework asm, comments, PLTs, initialization, commit message] Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Torsten Duwe <duwe@suse.de> Cc: AKASHI Takahiro <takahiro.akashi@linaro.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Julien Thierry <jthierry@redhat.com> Cc: Will Deacon <will@kernel.org>
2019-02-08 18:10:19 +03:00
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
unsigned long pc = rec->ip;
u32 old, new;
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
if (!ftrace_find_callable_addr(rec, NULL, &old_addr))
return -EINVAL;
if (!ftrace_find_callable_addr(rec, NULL, &addr))
return -EINVAL;
arm64: implement ftrace with regs This patch implements FTRACE_WITH_REGS for arm64, which allows a traced function's arguments (and some other registers) to be captured into a struct pt_regs, allowing these to be inspected and/or modified. This is a building block for live-patching, where a function's arguments may be forwarded to another function. This is also necessary to enable ftrace and in-kernel pointer authentication at the same time, as it allows the LR value to be captured and adjusted prior to signing. Using GCC's -fpatchable-function-entry=N option, we can have the compiler insert a configurable number of NOPs between the function entry point and the usual prologue. This also ensures functions are AAPCS compliant (e.g. disabling inter-procedural register allocation). For example, with -fpatchable-function-entry=2, GCC 8.1.0 compiles the following: | unsigned long bar(void); | | unsigned long foo(void) | { | return bar() + 1; | } ... to: | <foo>: | nop | nop | stp x29, x30, [sp, #-16]! | mov x29, sp | bl 0 <bar> | add x0, x0, #0x1 | ldp x29, x30, [sp], #16 | ret This patch builds the kernel with -fpatchable-function-entry=2, prefixing each function with two NOPs. To trace a function, we replace these NOPs with a sequence that saves the LR into a GPR, then calls an ftrace entry assembly function which saves this and other relevant registers: | mov x9, x30 | bl <ftrace-entry> Since patchable functions are AAPCS compliant (and the kernel does not use x18 as a platform register), x9-x18 can be safely clobbered in the patched sequence and the ftrace entry code. There are now two ftrace entry functions, ftrace_regs_entry (which saves all GPRs), and ftrace_entry (which saves the bare minimum). A PLT is allocated for each within modules. Signed-off-by: Torsten Duwe <duwe@suse.de> [Mark: rework asm, comments, PLTs, initialization, commit message] Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Torsten Duwe <duwe@suse.de> Cc: AKASHI Takahiro <takahiro.akashi@linaro.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Julien Thierry <jthierry@redhat.com> Cc: Will Deacon <will@kernel.org>
2019-02-08 18:10:19 +03:00
old = aarch64_insn_gen_branch_imm(pc, old_addr,
AARCH64_INSN_BRANCH_LINK);
new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
return ftrace_modify_code(pc, old, new, true);
}
/*
* The compiler has inserted two NOPs before the regular function prologue.
* All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live,
* and x9-x18 are free for our use.
*
* At runtime we want to be able to swing a single NOP <-> BL to enable or
* disable the ftrace call. The BL requires us to save the original LR value,
* so here we insert a <MOV X9, LR> over the first NOP so the instructions
* before the regular prologue are:
*
* | Compiled | Disabled | Enabled |
* +----------+------------+------------+
* | NOP | MOV X9, LR | MOV X9, LR |
* | NOP | NOP | BL <entry> |
*
* The LR value will be recovered by ftrace_regs_entry, and restored into LR
* before returning to the regular function prologue. When a function is not
* being traced, the MOV is not harmful given x9 is not live per the AAPCS.
*
* Note: ftrace_process_locs() has pre-adjusted rec->ip to be the address of
* the BL.
*/
int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
{
unsigned long pc = rec->ip - AARCH64_INSN_SIZE;
u32 old, new;
old = aarch64_insn_gen_nop();
new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9,
AARCH64_INSN_REG_LR,
AARCH64_INSN_VARIANT_64BIT);
return ftrace_modify_code(pc, old, new, true);
}
#endif
/*
* Turn off the call to ftrace_caller() in instrumented function
*/
int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
unsigned long addr)
{
unsigned long pc = rec->ip;
u32 old = 0, new;
arm64: ftrace: fix module PLTs with mcount Li Huafei reports that mcount-based ftrace with module PLTs was broken by commit: a6253579977e4c6f ("arm64: ftrace: consistently handle PLTs.") When a module PLTs are used and a module is loaded sufficiently far away from the kernel, we'll create PLTs for any branches which are out-of-range. These are separate from the special ftrace trampoline PLTs, which the module PLT code doesn't directly manipulate. When mcount is in use this is a problem, as each mcount callsite in a module will be initialized to point to a module PLT, but since commit a6253579977e4c6f ftrace_make_nop() will assume that the callsite has been initialized to point to the special ftrace trampoline PLT, and ftrace_find_callable_addr() rejects other cases. This means that when ftrace tries to initialize a callsite via ftrace_make_nop(), the call to ftrace_find_callable_addr() will find that the `_mcount` stub is out-of-range and is not handled by the ftrace PLT, resulting in a splat: | ftrace_test: loading out-of-tree module taints kernel. | ftrace: no module PLT for _mcount | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffff800029180014>] 0xffff800029180014 | actual: 44:00:00:94 | Initializing ftrace call sites | ftrace record flags: 2000000 | (0) | expected tramp: ffff80000802eb3c | ------------[ cut here ]------------ | WARNING: CPU: 3 PID: 157 at kernel/trace/ftrace.c:2120 ftrace_bug+0x94/0x270 | Modules linked in: | CPU: 3 PID: 157 Comm: insmod Tainted: G O 6.0.0-rc6-00151-gcd722513a189-dirty #22 | Hardware name: linux,dummy-virt (DT) | pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x94/0x270 | lr : ftrace_bug+0x21c/0x270 | sp : ffff80000b2bbaf0 | x29: ffff80000b2bbaf0 x28: 0000000000000000 x27: ffff0000c4d38000 | x26: 0000000000000001 x25: ffff800009d7e000 x24: ffff0000c4d86e00 | x23: 0000000002000000 x22: ffff80000a62b000 x21: ffff8000098ebea8 | x20: ffff0000c4d38000 x19: ffff80000aa24158 x18: ffffffffffffffff | x17: 0000000000000000 x16: 0a0d2d2d2d2d2d2d x15: ffff800009aa9118 | x14: 0000000000000000 x13: 6333626532303830 x12: 3030303866666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : 3362653230383030 | x8 : c0000000ffffefff x7 : 0000000000017fe8 x6 : 000000000000bff4 | x5 : 0000000000057fa8 x4 : 0000000000000000 x3 : 0000000000000001 | x2 : ad2cb14bb5438900 x1 : 0000000000000000 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x94/0x270 | ftrace_process_locs+0x308/0x430 | ftrace_module_init+0x44/0x60 | load_module+0x15b4/0x1ce8 | __do_sys_init_module+0x1ec/0x238 | __arm64_sys_init_module+0x24/0x30 | invoke_syscall+0x54/0x118 | el0_svc_common.constprop.4+0x84/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x1c/0x50 | el0t_64_sync_handler+0x90/0xb8 | el0t_64_sync+0x15c/0x160 | ---[ end trace 0000000000000000 ]--- | ---------test_init----------- Fix this by reverting to the old behaviour of ignoring the old instruction when initialising an mcount callsite in a module, which was the behaviour prior to commit a6253579977e4c6f. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Fixes: a6253579977e ("arm64: ftrace: consistently handle PLTs.") Reported-by: Li Huafei <lihuafei1@huawei.com> Link: https://lore.kernel.org/linux-arm-kernel/20220929094134.99512-1-lihuafei1@huawei.com Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20220929134525.798593-1-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-09-29 16:45:25 +03:00
new = aarch64_insn_gen_nop();
/*
* When using mcount, callsites in modules may have been initalized to
* call an arbitrary module PLT (which redirects to the _mcount stub)
* rather than the ftrace PLT we'll use at runtime (which redirects to
* the ftrace trampoline). We can ignore the old PLT when initializing
* the callsite.
*
* Note: 'mod' is only set at module load time.
*/
if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) &&
IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && mod) {
return aarch64_insn_patch_text_nosync((void *)pc, new);
}
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
if (!ftrace_find_callable_addr(rec, mod, &addr))
return -EINVAL;
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
arm64: ftrace: consistently handle PLTs. Sometimes it is necessary to use a PLT entry to call an ftrace trampoline. This is handled by ftrace_make_call() and ftrace_make_nop(), with each having *almost* identical logic, but this is not handled by ftrace_modify_call() since its introduction in commit: 3b23e4991fb66f6d ("arm64: implement ftrace with regs") Due to this, if we ever were to call ftrace_modify_call() for a callsite which requires a PLT entry for a trampoline, then either: a) If the old addr requires a trampoline, ftrace_modify_call() will use an out-of-range address to generate the 'old' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm() and ftrace_modify_code(), and no instructions will be modified. As ftrace_modify_call() will return an error, this will result in subsequent internal ftrace errors. b) If the old addr does not require a trampoline, but the new addr does, ftrace_modify_call() will use an out-of-range address to generate the 'new' branch instruction. This will result in warnings from aarch64_insn_gen_branch_imm(), and ftrace_modify_code() will replace the 'old' branch with a BRK. This will result in a kernel panic when this BRK is later executed. Practically speaking, case (a) is vastly more likely than case (b), and typically this will result in internal ftrace errors that don't necessarily affect the rest of the system. This can be demonstrated with an out-of-tree test module which triggers ftrace_modify_call(), e.g. | # insmod test_ftrace.ko | test_ftrace: Function test_function raw=0xffffb3749399201c, callsite=0xffffb37493992024 | branch_imm_common: offset out of range | branch_imm_common: offset out of range | ------------[ ftrace bug ]------------ | ftrace failed to modify | [<ffffb37493992024>] test_function+0x8/0x38 [test_ftrace] | actual: 1d:00:00:94 | Updating ftrace call site to call a different ftrace function | ftrace record flags: e0000002 | (2) R | expected tramp: ffffb374ae42ed54 | ------------[ cut here ]------------ | WARNING: CPU: 0 PID: 165 at kernel/trace/ftrace.c:2085 ftrace_bug+0x280/0x2b0 | Modules linked in: test_ftrace(+) | CPU: 0 PID: 165 Comm: insmod Not tainted 5.19.0-rc2-00002-g4d9ead8b45ce #13 | Hardware name: linux,dummy-virt (DT) | pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : ftrace_bug+0x280/0x2b0 | lr : ftrace_bug+0x280/0x2b0 | sp : ffff80000839ba00 | x29: ffff80000839ba00 x28: 0000000000000000 x27: ffff80000839bcf0 | x26: ffffb37493994180 x25: ffffb374b0991c28 x24: ffffb374b0d70000 | x23: 00000000ffffffea x22: ffffb374afcc33b0 x21: ffffb374b08f9cc8 | x20: ffff572b8462c000 x19: ffffb374b08f9000 x18: ffffffffffffffff | x17: 6c6c6163202c6331 x16: ffffb374ae5ad110 x15: ffffb374b0d51ee4 | x14: 0000000000000000 x13: 3435646532346561 x12: 3437336266666666 | x11: 203a706d61727420 x10: 6465746365707865 x9 : ffffb374ae5149e8 | x8 : 336266666666203a x7 : 706d617274206465 x6 : 00000000fffff167 | x5 : ffff572bffbc4a08 x4 : 00000000fffff167 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffff572b84461e00 x0 : 0000000000000022 | Call trace: | ftrace_bug+0x280/0x2b0 | ftrace_replace_code+0x98/0xa0 | ftrace_modify_all_code+0xe0/0x144 | arch_ftrace_update_code+0x14/0x20 | ftrace_startup+0xf8/0x1b0 | register_ftrace_function+0x38/0x90 | test_ftrace_init+0xd0/0x1000 [test_ftrace] | do_one_initcall+0x50/0x2b0 | do_init_module+0x50/0x1f0 | load_module+0x17c8/0x1d64 | __do_sys_finit_module+0xa8/0x100 | __arm64_sys_finit_module+0x2c/0x3c | invoke_syscall+0x50/0x120 | el0_svc_common.constprop.0+0xdc/0x100 | do_el0_svc+0x3c/0xd0 | el0_svc+0x34/0xb0 | el0t_64_sync_handler+0xbc/0x140 | el0t_64_sync+0x18c/0x190 | ---[ end trace 0000000000000000 ]--- We can solve this by consistently determining whether to use a PLT entry for an address. Note that since (the earlier) commit: f1a54ae9af0da4d7 ("arm64: module/ftrace: intialize PLT at load time") ... we can consistently determine the PLT address that a given callsite will use, and therefore ftrace_make_nop() does not need to skip validation when a PLT is in use. This patch factors the existing logic out of ftrace_make_call() and ftrace_make_nop() into a common ftrace_find_callable_addr() helper function, which is used by ftrace_make_call(), ftrace_make_nop(), and ftrace_modify_call(). In ftrace_make_nop() the patching is consistently validated by ftrace_modify_code() as we can always determine what the old instruction should have been. Fixes: 3b23e4991fb6 ("arm64: implement ftrace with regs") Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Will Deacon <will@kernel.org> Tested-by: "Ivan T. Ivanov" <iivanov@suse.de> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220614080944.1349146-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-06-14 11:09:43 +03:00
return ftrace_modify_code(pc, old, new, true);
}
void arch_ftrace_update_code(int command)
{
command |= FTRACE_MAY_SLEEP;
ftrace_modify_all_code(command);
}
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/*
* function_graph tracer expects ftrace_return_to_handler() to be called
* on the way back to parent. For this purpose, this function is called
* in _mcount() or ftrace_caller() to replace return address (*parent) on
* the call stack to return_to_handler.
*/
void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
unsigned long frame_pointer)
{
unsigned long return_hooker = (unsigned long)&return_to_handler;
unsigned long old;
if (unlikely(atomic_read(&current->tracing_graph_pause)))
return;
/*
* Note:
* No protection against faulting at *parent, which may be seen
* on other archs. It's unlikely on AArch64.
*/
old = *parent;
arm64: ftrace: use HAVE_FUNCTION_GRAPH_RET_ADDR_PTR When CONFIG_FUNCTION_GRAPH_TRACER is selected and the function graph tracer is in use, unwind_frame() may erroneously associate a traced function with an incorrect return address. This can happen when starting an unwind from a pt_regs, or when unwinding across an exception boundary. This can be seen when recording with perf while the function graph tracer is in use. For example: | # echo function_graph > /sys/kernel/debug/tracing/current_tracer | # perf record -g -e raw_syscalls:sys_enter:k /bin/true | # perf report ... reports the callchain erroneously as: | el0t_64_sync | el0t_64_sync_handler | el0_svc_common.constprop.0 | perf_callchain | get_perf_callchain | syscall_trace_enter | syscall_trace_enter ... whereas when the function graph tracer is not in use, it reports: | el0t_64_sync | el0t_64_sync_handler | el0_svc | do_el0_svc | el0_svc_common.constprop.0 | syscall_trace_enter | syscall_trace_enter The underlying problem is that ftrace_graph_get_ret_stack() takes an index offset from the most recent entry added to the fgraph return stack. We start an unwind at offset 0, and increment the offset each time we encounter a rewritten return address (i.e. when we see `return_to_handler`). This is broken in two cases: 1) Between creating a pt_regs and starting the unwind, function calls may place entries on the stack, leaving an arbitrary offset which we can only determine by performing a full unwind from the caller of the unwind code (and relying on none of the unwind code being instrumented). This can result in erroneous entries being reported in a backtrace recorded by perf or kfence when the function graph tracer is in use. Currently show_regs() is unaffected as dump_backtrace() performs an initial unwind. 2) When unwinding across an exception boundary (whether continuing an unwind or starting a new unwind from regs), we currently always skip the LR of the interrupted context. Where this was live and contained a rewritten address, we won't consume the corresponding fgraph ret stack entry, leaving subsequent entries off-by-one. This can result in erroneous entries being reported in a backtrace performed by any in-kernel unwinder when that backtrace crosses an exception boundary, with entries after the boundary being reported incorrectly. This includes perf, kfence, show_regs(), panic(), etc. To fix this, we need to be able to uniquely identify each rewritten return address such that we can map this back to the original return address. We can use HAVE_FUNCTION_GRAPH_RET_ADDR_PTR to associate each rewritten return address with a unique location on the stack. As the return address is passed in the LR (and so is not guaranteed a unique location in memory), we use the FP upon entry to the function (i.e. the address of the caller's frame record) as the return address pointer. Any nested call will have a different FP value as the caller must create its own frame record and update FP to point to this. Since ftrace_graph_ret_addr() requires the return address with the PAC stripped, the stripping of the PAC is moved before the fixup of the rewritten address. As we would unconditionally strip the PAC, moving this earlier is not harmful, and we can avoid a redundant strip in the return address fixup code. I've tested this with the perf case above, the ftrace selftests, and a number of ad-hoc unwinder tests. The tests all pass, and I have seen no unexpected behaviour as a result of this change. I've tested with pointer authentication under QEMU TCG where magic-sysrq+l correctly recovers the original return addresses. Note that this doesn't fix the issue of skipping a live LR at an exception boundary, which is a more general problem and requires more substantial rework. Were we to consume the LR in all cases this would result in warnings where the interrupted context's LR contains `return_to_handler`, but the FP has been altered, e.g. | func: | <--- ftrace entry ---> // logs FP & LR, rewrites LR | STP FP, LR, [SP, #-16]! | MOV FP, SP | <--- INTERRUPT ---> ... as ftrace_graph_get_ret_stack() fill not find a matching entry, triggering the WARN_ON_ONCE() in unwind_frame(). Link: https://lore.kernel.org/r/20211025164925.GB2001@C02TD0UTHF1T.local Link: https://lore.kernel.org/r/20211027132529.30027-1-mark.rutland@arm.com Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Cc: Mark Brown <broonie@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Will Deacon <will@kernel.org> Reviewed-by: Mark Brown <broonie@kernel.org> Link: https://lore.kernel.org/r/20211029162245.39761-1-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2021-10-29 19:22:45 +03:00
if (!function_graph_enter(old, self_addr, frame_pointer,
(void *)frame_pointer)) {
*parent = return_hooker;
arm64: ftrace: use HAVE_FUNCTION_GRAPH_RET_ADDR_PTR When CONFIG_FUNCTION_GRAPH_TRACER is selected and the function graph tracer is in use, unwind_frame() may erroneously associate a traced function with an incorrect return address. This can happen when starting an unwind from a pt_regs, or when unwinding across an exception boundary. This can be seen when recording with perf while the function graph tracer is in use. For example: | # echo function_graph > /sys/kernel/debug/tracing/current_tracer | # perf record -g -e raw_syscalls:sys_enter:k /bin/true | # perf report ... reports the callchain erroneously as: | el0t_64_sync | el0t_64_sync_handler | el0_svc_common.constprop.0 | perf_callchain | get_perf_callchain | syscall_trace_enter | syscall_trace_enter ... whereas when the function graph tracer is not in use, it reports: | el0t_64_sync | el0t_64_sync_handler | el0_svc | do_el0_svc | el0_svc_common.constprop.0 | syscall_trace_enter | syscall_trace_enter The underlying problem is that ftrace_graph_get_ret_stack() takes an index offset from the most recent entry added to the fgraph return stack. We start an unwind at offset 0, and increment the offset each time we encounter a rewritten return address (i.e. when we see `return_to_handler`). This is broken in two cases: 1) Between creating a pt_regs and starting the unwind, function calls may place entries on the stack, leaving an arbitrary offset which we can only determine by performing a full unwind from the caller of the unwind code (and relying on none of the unwind code being instrumented). This can result in erroneous entries being reported in a backtrace recorded by perf or kfence when the function graph tracer is in use. Currently show_regs() is unaffected as dump_backtrace() performs an initial unwind. 2) When unwinding across an exception boundary (whether continuing an unwind or starting a new unwind from regs), we currently always skip the LR of the interrupted context. Where this was live and contained a rewritten address, we won't consume the corresponding fgraph ret stack entry, leaving subsequent entries off-by-one. This can result in erroneous entries being reported in a backtrace performed by any in-kernel unwinder when that backtrace crosses an exception boundary, with entries after the boundary being reported incorrectly. This includes perf, kfence, show_regs(), panic(), etc. To fix this, we need to be able to uniquely identify each rewritten return address such that we can map this back to the original return address. We can use HAVE_FUNCTION_GRAPH_RET_ADDR_PTR to associate each rewritten return address with a unique location on the stack. As the return address is passed in the LR (and so is not guaranteed a unique location in memory), we use the FP upon entry to the function (i.e. the address of the caller's frame record) as the return address pointer. Any nested call will have a different FP value as the caller must create its own frame record and update FP to point to this. Since ftrace_graph_ret_addr() requires the return address with the PAC stripped, the stripping of the PAC is moved before the fixup of the rewritten address. As we would unconditionally strip the PAC, moving this earlier is not harmful, and we can avoid a redundant strip in the return address fixup code. I've tested this with the perf case above, the ftrace selftests, and a number of ad-hoc unwinder tests. The tests all pass, and I have seen no unexpected behaviour as a result of this change. I've tested with pointer authentication under QEMU TCG where magic-sysrq+l correctly recovers the original return addresses. Note that this doesn't fix the issue of skipping a live LR at an exception boundary, which is a more general problem and requires more substantial rework. Were we to consume the LR in all cases this would result in warnings where the interrupted context's LR contains `return_to_handler`, but the FP has been altered, e.g. | func: | <--- ftrace entry ---> // logs FP & LR, rewrites LR | STP FP, LR, [SP, #-16]! | MOV FP, SP | <--- INTERRUPT ---> ... as ftrace_graph_get_ret_stack() fill not find a matching entry, triggering the WARN_ON_ONCE() in unwind_frame(). Link: https://lore.kernel.org/r/20211025164925.GB2001@C02TD0UTHF1T.local Link: https://lore.kernel.org/r/20211027132529.30027-1-mark.rutland@arm.com Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Cc: Mark Brown <broonie@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Will Deacon <will@kernel.org> Reviewed-by: Mark Brown <broonie@kernel.org> Link: https://lore.kernel.org/r/20211029162245.39761-1-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2021-10-29 19:22:45 +03:00
}
}
#ifdef CONFIG_DYNAMIC_FTRACE
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
/*
* When DYNAMIC_FTRACE_WITH_REGS is selected, `fregs` can never be NULL
* and arch_ftrace_get_regs(fregs) will always give a non-NULL pt_regs
* in which we can safely modify the LR.
*/
struct pt_regs *regs = arch_ftrace_get_regs(fregs);
unsigned long *parent = (unsigned long *)&procedure_link_pointer(regs);
prepare_ftrace_return(ip, parent, frame_pointer(regs));
}
#else
/*
* Turn on/off the call to ftrace_graph_caller() in ftrace_caller()
* depending on @enable.
*/
static int ftrace_modify_graph_caller(bool enable)
{
unsigned long pc = (unsigned long)&ftrace_graph_call;
u32 branch, nop;
branch = aarch64_insn_gen_branch_imm(pc,
(unsigned long)ftrace_graph_caller,
AARCH64_INSN_BRANCH_NOLINK);
nop = aarch64_insn_gen_nop();
if (enable)
return ftrace_modify_code(pc, nop, branch, true);
else
return ftrace_modify_code(pc, branch, nop, true);
}
int ftrace_enable_ftrace_graph_caller(void)
{
return ftrace_modify_graph_caller(true);
}
int ftrace_disable_ftrace_graph_caller(void)
{
return ftrace_modify_graph_caller(false);
}
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */