leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
23d9a9280efea105852de358f21d69231992ae73
linux/arch/arm/include/asm/current.h

63 lines
1.7 KiB
C
Raw Normal View History

ARM: smp: Store current pointer in TPIDRURO register if available Now that the user space TLS register is assigned on every return to user space, we can use it to keep the 'current' pointer while running in the kernel. This removes the need to access it via thread_info, which is located at the base of the stack, but will be moved out of there in a subsequent patch. Use the __builtin_thread_pointer() helper when available - this will help GCC understand that reloading the value within the same function is not necessary, even when using the per-task stack protector (which also generates accesses via the TLS register). For example, the generated code below loads TPIDRURO only once, and uses it to access both the stack canary and the preempt_count fields. <do_one_initcall>: e92d 41f0 stmdb sp!, {r4, r5, r6, r7, r8, lr} ee1d 4f70 mrc 15, 0, r4, cr13, cr0, {3} 4606 mov r6, r0 b094 sub sp, #80 ; 0x50 f8d4 34e8 ldr.w r3, [r4, #1256] ; 0x4e8 <- stack canary 9313 str r3, [sp, #76] ; 0x4c f8d4 8004 ldr.w r8, [r4, #4] <- preempt count Co-developed-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
2021-09-18 10:44:37 +02:00
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (c) 2021 Keith Packard <keithp@keithp.com>
* Copyright (c) 2021 Google, LLC <ardb@kernel.org>
*/
#ifndef _ASM_ARM_CURRENT_H
#define _ASM_ARM_CURRENT_H
#ifndef __ASSEMBLY__
ARM: implement THREAD_INFO_IN_TASK for uniprocessor systems On UP systems, only a single task can be 'current' at the same time, which means we can use a global variable to track it. This means we can also enable THREAD_INFO_IN_TASK for those systems, as in that case, thread_info is accessed via current rather than the other way around, removing the need to store thread_info at the base of the task stack. This, in turn, permits us to enable IRQ stacks and vmap'ed stacks on UP systems as well. To partially mitigate the performance overhead of this arrangement, use a ADD/ADD/LDR sequence with the appropriate PC-relative group relocations to load the value of current when needed. This means that accessing current will still only require a single load as before, avoiding the need for a literal to carry the address of the global variable in each function. However, accessing thread_info will now require this load as well. Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Tested-by: Marc Zyngier <maz@kernel.org> Tested-by: Vladimir Murzin <vladimir.murzin@arm.com> # ARMv7M
2021-11-24 14:08:11 +01:00
#include <asm/insn.h>
ARM: smp: Store current pointer in TPIDRURO register if available Now that the user space TLS register is assigned on every return to user space, we can use it to keep the 'current' pointer while running in the kernel. This removes the need to access it via thread_info, which is located at the base of the stack, but will be moved out of there in a subsequent patch. Use the __builtin_thread_pointer() helper when available - this will help GCC understand that reloading the value within the same function is not necessary, even when using the per-task stack protector (which also generates accesses via the TLS register). For example, the generated code below loads TPIDRURO only once, and uses it to access both the stack canary and the preempt_count fields. <do_one_initcall>: e92d 41f0 stmdb sp!, {r4, r5, r6, r7, r8, lr} ee1d 4f70 mrc 15, 0, r4, cr13, cr0, {3} 4606 mov r6, r0 b094 sub sp, #80 ; 0x50 f8d4 34e8 ldr.w r3, [r4, #1256] ; 0x4e8 <- stack canary 9313 str r3, [sp, #76] ; 0x4c f8d4 8004 ldr.w r8, [r4, #4] <- preempt count Co-developed-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
2021-09-18 10:44:37 +02:00
struct task_struct;
ARM: implement THREAD_INFO_IN_TASK for uniprocessor systems On UP systems, only a single task can be 'current' at the same time, which means we can use a global variable to track it. This means we can also enable THREAD_INFO_IN_TASK for those systems, as in that case, thread_info is accessed via current rather than the other way around, removing the need to store thread_info at the base of the task stack. This, in turn, permits us to enable IRQ stacks and vmap'ed stacks on UP systems as well. To partially mitigate the performance overhead of this arrangement, use a ADD/ADD/LDR sequence with the appropriate PC-relative group relocations to load the value of current when needed. This means that accessing current will still only require a single load as before, avoiding the need for a literal to carry the address of the global variable in each function. However, accessing thread_info will now require this load as well. Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Tested-by: Marc Zyngier <maz@kernel.org> Tested-by: Vladimir Murzin <vladimir.murzin@arm.com> # ARMv7M
2021-11-24 14:08:11 +01:00
extern struct task_struct *__current;
ARM: smp: Store current pointer in TPIDRURO register if available Now that the user space TLS register is assigned on every return to user space, we can use it to keep the 'current' pointer while running in the kernel. This removes the need to access it via thread_info, which is located at the base of the stack, but will be moved out of there in a subsequent patch. Use the __builtin_thread_pointer() helper when available - this will help GCC understand that reloading the value within the same function is not necessary, even when using the per-task stack protector (which also generates accesses via the TLS register). For example, the generated code below loads TPIDRURO only once, and uses it to access both the stack canary and the preempt_count fields. <do_one_initcall>: e92d 41f0 stmdb sp!, {r4, r5, r6, r7, r8, lr} ee1d 4f70 mrc 15, 0, r4, cr13, cr0, {3} 4606 mov r6, r0 b094 sub sp, #80 ; 0x50 f8d4 34e8 ldr.w r3, [r4, #1256] ; 0x4e8 <- stack canary 9313 str r3, [sp, #76] ; 0x4c f8d4 8004 ldr.w r8, [r4, #4] <- preempt count Co-developed-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
2021-09-18 10:44:37 +02:00
ARM: implement THREAD_INFO_IN_TASK for uniprocessor systems On UP systems, only a single task can be 'current' at the same time, which means we can use a global variable to track it. This means we can also enable THREAD_INFO_IN_TASK for those systems, as in that case, thread_info is accessed via current rather than the other way around, removing the need to store thread_info at the base of the task stack. This, in turn, permits us to enable IRQ stacks and vmap'ed stacks on UP systems as well. To partially mitigate the performance overhead of this arrangement, use a ADD/ADD/LDR sequence with the appropriate PC-relative group relocations to load the value of current when needed. This means that accessing current will still only require a single load as before, avoiding the need for a literal to carry the address of the global variable in each function. However, accessing thread_info will now require this load as well. Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Tested-by: Marc Zyngier <maz@kernel.org> Tested-by: Vladimir Murzin <vladimir.murzin@arm.com> # ARMv7M
2021-11-24 14:08:11 +01:00
static inline __attribute_const__ struct task_struct *get_current(void)
ARM: smp: Store current pointer in TPIDRURO register if available Now that the user space TLS register is assigned on every return to user space, we can use it to keep the 'current' pointer while running in the kernel. This removes the need to access it via thread_info, which is located at the base of the stack, but will be moved out of there in a subsequent patch. Use the __builtin_thread_pointer() helper when available - this will help GCC understand that reloading the value within the same function is not necessary, even when using the per-task stack protector (which also generates accesses via the TLS register). For example, the generated code below loads TPIDRURO only once, and uses it to access both the stack canary and the preempt_count fields. <do_one_initcall>: e92d 41f0 stmdb sp!, {r4, r5, r6, r7, r8, lr} ee1d 4f70 mrc 15, 0, r4, cr13, cr0, {3} 4606 mov r6, r0 b094 sub sp, #80 ; 0x50 f8d4 34e8 ldr.w r3, [r4, #1256] ; 0x4e8 <- stack canary 9313 str r3, [sp, #76] ; 0x4c f8d4 8004 ldr.w r8, [r4, #4] <- preempt count Co-developed-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
2021-09-18 10:44:37 +02:00
{
struct task_struct *cur;
ARM: 9151/1: Thumb2: avoid __builtin_thread_pointer() on Clang If available, we use the __builtin_thread_pointer() helper to get the value of the TLS register, to help the compiler understand that it doesn't need to reload it every time we access 'current'. Unfortunately, Clang fails to emit the MRC system register read directly when building for Thumb2, and instead, it issues a call to the __aeabi_read_tp helper, which the kernel does not provide, and so this result in link failures at build time. So create a special case for this, and emit the MRC directly using an asm() block, just like we do when the helper is not available to begin with. Link: https://github.com/ClangBuiltLinux/linux/issues/1485 Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Reviewed-by: Nathan Chancellor <nathan@kernel.org> Tested-by: Nathan Chancellor <nathan@kernel.org> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
2021-10-29 17:49:37 +01:00
#if __has_builtin(__builtin_thread_pointer) && \
ARM: implement THREAD_INFO_IN_TASK for uniprocessor systems On UP systems, only a single task can be 'current' at the same time, which means we can use a global variable to track it. This means we can also enable THREAD_INFO_IN_TASK for those systems, as in that case, thread_info is accessed via current rather than the other way around, removing the need to store thread_info at the base of the task stack. This, in turn, permits us to enable IRQ stacks and vmap'ed stacks on UP systems as well. To partially mitigate the performance overhead of this arrangement, use a ADD/ADD/LDR sequence with the appropriate PC-relative group relocations to load the value of current when needed. This means that accessing current will still only require a single load as before, avoiding the need for a literal to carry the address of the global variable in each function. However, accessing thread_info will now require this load as well. Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Tested-by: Marc Zyngier <maz@kernel.org> Tested-by: Vladimir Murzin <vladimir.murzin@arm.com> # ARMv7M
2021-11-24 14:08:11 +01:00
defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) && \
ARM: 9151/1: Thumb2: avoid __builtin_thread_pointer() on Clang If available, we use the __builtin_thread_pointer() helper to get the value of the TLS register, to help the compiler understand that it doesn't need to reload it every time we access 'current'. Unfortunately, Clang fails to emit the MRC system register read directly when building for Thumb2, and instead, it issues a call to the __aeabi_read_tp helper, which the kernel does not provide, and so this result in link failures at build time. So create a special case for this, and emit the MRC directly using an asm() block, just like we do when the helper is not available to begin with. Link: https://github.com/ClangBuiltLinux/linux/issues/1485 Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Reviewed-by: Nathan Chancellor <nathan@kernel.org> Tested-by: Nathan Chancellor <nathan@kernel.org> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
2021-10-29 17:49:37 +01:00
!(defined(CONFIG_THUMB2_KERNEL) && \
defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 130001)
ARM: smp: Store current pointer in TPIDRURO register if available Now that the user space TLS register is assigned on every return to user space, we can use it to keep the 'current' pointer while running in the kernel. This removes the need to access it via thread_info, which is located at the base of the stack, but will be moved out of there in a subsequent patch. Use the __builtin_thread_pointer() helper when available - this will help GCC understand that reloading the value within the same function is not necessary, even when using the per-task stack protector (which also generates accesses via the TLS register). For example, the generated code below loads TPIDRURO only once, and uses it to access both the stack canary and the preempt_count fields. <do_one_initcall>: e92d 41f0 stmdb sp!, {r4, r5, r6, r7, r8, lr} ee1d 4f70 mrc 15, 0, r4, cr13, cr0, {3} 4606 mov r6, r0 b094 sub sp, #80 ; 0x50 f8d4 34e8 ldr.w r3, [r4, #1256] ; 0x4e8 <- stack canary 9313 str r3, [sp, #76] ; 0x4c f8d4 8004 ldr.w r8, [r4, #4] <- preempt count Co-developed-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
2021-09-18 10:44:37 +02:00
/*
* Use the __builtin helper when available - this results in better
* code, especially when using GCC in combination with the per-task
* stack protector, as the compiler will recognize that it needs to
* load the TLS register only once in every function.
ARM: 9151/1: Thumb2: avoid __builtin_thread_pointer() on Clang If available, we use the __builtin_thread_pointer() helper to get the value of the TLS register, to help the compiler understand that it doesn't need to reload it every time we access 'current'. Unfortunately, Clang fails to emit the MRC system register read directly when building for Thumb2, and instead, it issues a call to the __aeabi_read_tp helper, which the kernel does not provide, and so this result in link failures at build time. So create a special case for this, and emit the MRC directly using an asm() block, just like we do when the helper is not available to begin with. Link: https://github.com/ClangBuiltLinux/linux/issues/1485 Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Reviewed-by: Nathan Chancellor <nathan@kernel.org> Tested-by: Nathan Chancellor <nathan@kernel.org> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
2021-10-29 17:49:37 +01:00
*
* Clang < 13.0.1 gets this wrong for Thumb2 builds:
* https://github.com/ClangBuiltLinux/linux/issues/1485
ARM: smp: Store current pointer in TPIDRURO register if available Now that the user space TLS register is assigned on every return to user space, we can use it to keep the 'current' pointer while running in the kernel. This removes the need to access it via thread_info, which is located at the base of the stack, but will be moved out of there in a subsequent patch. Use the __builtin_thread_pointer() helper when available - this will help GCC understand that reloading the value within the same function is not necessary, even when using the per-task stack protector (which also generates accesses via the TLS register). For example, the generated code below loads TPIDRURO only once, and uses it to access both the stack canary and the preempt_count fields. <do_one_initcall>: e92d 41f0 stmdb sp!, {r4, r5, r6, r7, r8, lr} ee1d 4f70 mrc 15, 0, r4, cr13, cr0, {3} 4606 mov r6, r0 b094 sub sp, #80 ; 0x50 f8d4 34e8 ldr.w r3, [r4, #1256] ; 0x4e8 <- stack canary 9313 str r3, [sp, #76] ; 0x4c f8d4 8004 ldr.w r8, [r4, #4] <- preempt count Co-developed-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
2021-09-18 10:44:37 +02:00
*/
cur = __builtin_thread_pointer();
ARM: implement THREAD_INFO_IN_TASK for uniprocessor systems On UP systems, only a single task can be 'current' at the same time, which means we can use a global variable to track it. This means we can also enable THREAD_INFO_IN_TASK for those systems, as in that case, thread_info is accessed via current rather than the other way around, removing the need to store thread_info at the base of the task stack. This, in turn, permits us to enable IRQ stacks and vmap'ed stacks on UP systems as well. To partially mitigate the performance overhead of this arrangement, use a ADD/ADD/LDR sequence with the appropriate PC-relative group relocations to load the value of current when needed. This means that accessing current will still only require a single load as before, avoiding the need for a literal to carry the address of the global variable in each function. However, accessing thread_info will now require this load as well. Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Tested-by: Marc Zyngier <maz@kernel.org> Tested-by: Vladimir Murzin <vladimir.murzin@arm.com> # ARMv7M
2021-11-24 14:08:11 +01:00
#elif defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP)
asm("0: mrc p15, 0, %0, c13, c0, 3 \n\t"
#ifdef CONFIG_CPU_V6
"1: \n\t"
" .subsection 1 \n\t"
"2: " LOAD_SYM_ARMV6(%0, __current) " \n\t"
" b 1b \n\t"
" .previous \n\t"
" .pushsection \".alt.smp.init\", \"a\" \n\t"
" .long 0b - . \n\t"
" b . + (2b - 0b) \n\t"
" .popsection \n\t"
#endif
: "=r"(cur));
#elif __LINUX_ARM_ARCH__>=7 || \
(defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
cur = __current;
ARM: smp: Store current pointer in TPIDRURO register if available Now that the user space TLS register is assigned on every return to user space, we can use it to keep the 'current' pointer while running in the kernel. This removes the need to access it via thread_info, which is located at the base of the stack, but will be moved out of there in a subsequent patch. Use the __builtin_thread_pointer() helper when available - this will help GCC understand that reloading the value within the same function is not necessary, even when using the per-task stack protector (which also generates accesses via the TLS register). For example, the generated code below loads TPIDRURO only once, and uses it to access both the stack canary and the preempt_count fields. <do_one_initcall>: e92d 41f0 stmdb sp!, {r4, r5, r6, r7, r8, lr} ee1d 4f70 mrc 15, 0, r4, cr13, cr0, {3} 4606 mov r6, r0 b094 sub sp, #80 ; 0x50 f8d4 34e8 ldr.w r3, [r4, #1256] ; 0x4e8 <- stack canary 9313 str r3, [sp, #76] ; 0x4c f8d4 8004 ldr.w r8, [r4, #4] <- preempt count Co-developed-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
2021-09-18 10:44:37 +02:00
#else
ARM: implement THREAD_INFO_IN_TASK for uniprocessor systems On UP systems, only a single task can be 'current' at the same time, which means we can use a global variable to track it. This means we can also enable THREAD_INFO_IN_TASK for those systems, as in that case, thread_info is accessed via current rather than the other way around, removing the need to store thread_info at the base of the task stack. This, in turn, permits us to enable IRQ stacks and vmap'ed stacks on UP systems as well. To partially mitigate the performance overhead of this arrangement, use a ADD/ADD/LDR sequence with the appropriate PC-relative group relocations to load the value of current when needed. This means that accessing current will still only require a single load as before, avoiding the need for a literal to carry the address of the global variable in each function. However, accessing thread_info will now require this load as well. Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Tested-by: Marc Zyngier <maz@kernel.org> Tested-by: Vladimir Murzin <vladimir.murzin@arm.com> # ARMv7M
2021-11-24 14:08:11 +01:00
asm(LOAD_SYM_ARMV6(%0, __current) : "=r"(cur));
ARM: smp: Store current pointer in TPIDRURO register if available Now that the user space TLS register is assigned on every return to user space, we can use it to keep the 'current' pointer while running in the kernel. This removes the need to access it via thread_info, which is located at the base of the stack, but will be moved out of there in a subsequent patch. Use the __builtin_thread_pointer() helper when available - this will help GCC understand that reloading the value within the same function is not necessary, even when using the per-task stack protector (which also generates accesses via the TLS register). For example, the generated code below loads TPIDRURO only once, and uses it to access both the stack canary and the preempt_count fields. <do_one_initcall>: e92d 41f0 stmdb sp!, {r4, r5, r6, r7, r8, lr} ee1d 4f70 mrc 15, 0, r4, cr13, cr0, {3} 4606 mov r6, r0 b094 sub sp, #80 ; 0x50 f8d4 34e8 ldr.w r3, [r4, #1256] ; 0x4e8 <- stack canary 9313 str r3, [sp, #76] ; 0x4c f8d4 8004 ldr.w r8, [r4, #4] <- preempt count Co-developed-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Keith Packard <keithpac@amazon.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
2021-09-18 10:44:37 +02:00
#endif
return cur;
}
#define current get_current()
#endif /* __ASSEMBLY__ */
#endif /* _ASM_ARM_CURRENT_H */
Reference in New Issue Copy Permalink