2012-03-05 18:49:32 +07:00
|
|
|
/*
|
|
|
|
|
* Copyright (C) 2012 ARM Ltd.
|
|
|
|
|
*
|
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
|
|
|
* published by the Free Software Foundation.
|
|
|
|
|
*
|
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
|
* GNU General Public License for more details.
|
|
|
|
|
*
|
|
|
|
|
* You should have received a copy of the GNU General Public License
|
|
|
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
|
*/
|
|
|
|
|
#ifndef __ASM_FP_H
|
|
|
|
|
#define __ASM_FP_H
|
|
|
|
|
|
|
|
|
|
#include <asm/ptrace.h>
|
|
|
|
|
|
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
|
|
arm64/sve: Core task context handling
This patch adds the core support for switching and managing the SVE
architectural state of user tasks.
Calls to the existing FPSIMD low-level save/restore functions are
factored out as new functions task_fpsimd_{save,load}(), since SVE
now dynamically may or may not need to be handled at these points
depending on the kernel configuration, hardware features discovered
at boot, and the runtime state of the task. To make these
decisions as fast as possible, const cpucaps are used where
feasible, via the system_supports_sve() helper.
The SVE registers are only tracked for threads that have explicitly
used SVE, indicated by the new thread flag TIF_SVE. Otherwise, the
FPSIMD view of the architectural state is stored in
thread.fpsimd_state as usual.
When in use, the SVE registers are not stored directly in
thread_struct due to their potentially large and variable size.
Because the task_struct slab allocator must be configured very
early during kernel boot, it is also tricky to configure it
correctly to match the maximum vector length provided by the
hardware, since this depends on examining secondary CPUs as well as
the primary. Instead, a pointer sve_state in thread_struct points
to a dynamically allocated buffer containing the SVE register data,
and code is added to allocate and free this buffer at appropriate
times.
TIF_SVE is set when taking an SVE access trap from userspace, if
suitable hardware support has been detected. This enables SVE for
the thread: a subsequent return to userspace will disable the trap
accordingly. If such a trap is taken without sufficient system-
wide hardware support, SIGILL is sent to the thread instead as if
an undefined instruction had been executed: this may happen if
userspace tries to use SVE in a system where not all CPUs support
it for example.
The kernel will clear TIF_SVE and disable SVE for the thread
whenever an explicit syscall is made by userspace. For backwards
compatibility reasons and conformance with the spirit of the base
AArch64 procedure call standard, the subset of the SVE register
state that aliases the FPSIMD registers is still preserved across a
syscall even if this happens. The remainder of the SVE register
state logically becomes zero at syscall entry, though the actual
zeroing work is currently deferred until the thread next tries to
use SVE, causing another trap to the kernel. This implementation
is suboptimal: in the future, the fastpath case may be optimised
to zero the registers in-place and leave SVE enabled for the task,
where beneficial.
TIF_SVE is also cleared in the following slowpath cases, which are
taken as reasonable hints that the task may no longer use SVE:
* exec
* fork and clone
Code is added to sync data between thread.fpsimd_state and
thread.sve_state whenever enabling/disabling SVE, in a manner
consistent with the SVE architectural programmer's model.
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Alex Bennée <alex.bennee@linaro.org>
[will: added #include to fix allnoconfig build]
[will: use enable_daif in do_sve_acc]
Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 22:51:05 +07:00
|
|
|
#include <linux/stddef.h>
|
|
|
|
|
|
2012-03-05 18:49:32 +07:00
|
|
|
/*
|
|
|
|
|
* FP/SIMD storage area has:
|
|
|
|
|
* - FPSR and FPCR
|
|
|
|
|
* - 32 128-bit data registers
|
|
|
|
|
*
|
2012-11-07 02:28:48 +07:00
|
|
|
* Note that user_fpsimd forms a prefix of this structure, which is
|
|
|
|
|
* relied upon in the ptrace FP/SIMD accessors.
|
2012-03-05 18:49:32 +07:00
|
|
|
*/
|
|
|
|
|
struct fpsimd_state {
|
|
|
|
|
union {
|
|
|
|
|
struct user_fpsimd_state user_fpsimd;
|
|
|
|
|
struct {
|
|
|
|
|
__uint128_t vregs[32];
|
|
|
|
|
u32 fpsr;
|
|
|
|
|
u32 fpcr;
|
|
|
|
|
};
|
|
|
|
|
};
|
2014-05-08 16:20:23 +07:00
|
|
|
/* the id of the last cpu to have restored this state */
|
|
|
|
|
unsigned int cpu;
|
2012-03-05 18:49:32 +07:00
|
|
|
};
|
|
|
|
|
|
2014-02-24 21:26:29 +07:00
|
|
|
|
2012-03-05 18:49:32 +07:00
|
|
|
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
|
|
|
|
|
/* Masks for extracting the FPSR and FPCR from the FPSCR */
|
|
|
|
|
#define VFP_FPSCR_STAT_MASK 0xf800009f
|
|
|
|
|
#define VFP_FPSCR_CTRL_MASK 0x07f79f00
|
|
|
|
|
/*
|
|
|
|
|
* The VFP state has 32x64-bit registers and a single 32-bit
|
|
|
|
|
* control/status register.
|
|
|
|
|
*/
|
|
|
|
|
#define VFP_STATE_SIZE ((32 * 8) + 4)
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
struct task_struct;
|
|
|
|
|
|
|
|
|
|
extern void fpsimd_save_state(struct fpsimd_state *state);
|
|
|
|
|
extern void fpsimd_load_state(struct fpsimd_state *state);
|
|
|
|
|
|
|
|
|
|
extern void fpsimd_thread_switch(struct task_struct *next);
|
|
|
|
|
extern void fpsimd_flush_thread(void);
|
|
|
|
|
|
arm64/sve: Signal handling support
This patch implements support for saving and restoring the SVE
registers around signals.
A fixed-size header struct sve_context is always included in the
signal frame encoding the thread's vector length at the time of
signal delivery, optionally followed by a variable-layout structure
encoding the SVE registers.
Because of the need to preserve backwards compatibility, the FPSIMD
view of the SVE registers is always dumped as a struct
fpsimd_context in the usual way, in addition to any sve_context.
The SVE vector registers are dumped in full, including bits 127:0
of each register which alias the corresponding FPSIMD vector
registers in the hardware. To avoid any ambiguity about which
alias to restore during sigreturn, the kernel always restores bits
127:0 of each SVE vector register from the fpsimd_context in the
signal frame (which must be present): userspace needs to take this
into account if it wants to modify the SVE vector register contents
on return from a signal.
FPSR and FPCR, which are used by both FPSIMD and SVE, are not
included in sve_context because they are always present in
fpsimd_context anyway.
For signal delivery, a new helper
fpsimd_signal_preserve_current_state() is added to update _both_
the FPSIMD and SVE views in the task struct, to make it easier to
populate this information into the signal frame. Because of the
redundancy between the two views of the state, only one is updated
otherwise.
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Cc: Alex Bennée <alex.bennee@linaro.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 22:51:07 +07:00
|
|
|
extern void fpsimd_signal_preserve_current_state(void);
|
2014-02-24 21:26:27 +07:00
|
|
|
extern void fpsimd_preserve_current_state(void);
|
2014-05-08 16:20:23 +07:00
|
|
|
extern void fpsimd_restore_current_state(void);
|
2014-02-24 21:26:27 +07:00
|
|
|
extern void fpsimd_update_current_state(struct fpsimd_state *state);
|
|
|
|
|
|
2014-05-08 16:20:23 +07:00
|
|
|
extern void fpsimd_flush_task_state(struct task_struct *target);
|
|
|
|
|
|
2017-10-31 22:51:01 +07:00
|
|
|
extern void sve_save_state(void *state, u32 *pfpsr);
|
|
|
|
|
extern void sve_load_state(void const *state, u32 const *pfpsr,
|
|
|
|
|
unsigned long vq_minus_1);
|
|
|
|
|
extern unsigned int sve_get_vl(void);
|
|
|
|
|
|
arm64/sve: Core task context handling
This patch adds the core support for switching and managing the SVE
architectural state of user tasks.
Calls to the existing FPSIMD low-level save/restore functions are
factored out as new functions task_fpsimd_{save,load}(), since SVE
now dynamically may or may not need to be handled at these points
depending on the kernel configuration, hardware features discovered
at boot, and the runtime state of the task. To make these
decisions as fast as possible, const cpucaps are used where
feasible, via the system_supports_sve() helper.
The SVE registers are only tracked for threads that have explicitly
used SVE, indicated by the new thread flag TIF_SVE. Otherwise, the
FPSIMD view of the architectural state is stored in
thread.fpsimd_state as usual.
When in use, the SVE registers are not stored directly in
thread_struct due to their potentially large and variable size.
Because the task_struct slab allocator must be configured very
early during kernel boot, it is also tricky to configure it
correctly to match the maximum vector length provided by the
hardware, since this depends on examining secondary CPUs as well as
the primary. Instead, a pointer sve_state in thread_struct points
to a dynamically allocated buffer containing the SVE register data,
and code is added to allocate and free this buffer at appropriate
times.
TIF_SVE is set when taking an SVE access trap from userspace, if
suitable hardware support has been detected. This enables SVE for
the thread: a subsequent return to userspace will disable the trap
accordingly. If such a trap is taken without sufficient system-
wide hardware support, SIGILL is sent to the thread instead as if
an undefined instruction had been executed: this may happen if
userspace tries to use SVE in a system where not all CPUs support
it for example.
The kernel will clear TIF_SVE and disable SVE for the thread
whenever an explicit syscall is made by userspace. For backwards
compatibility reasons and conformance with the spirit of the base
AArch64 procedure call standard, the subset of the SVE register
state that aliases the FPSIMD registers is still preserved across a
syscall even if this happens. The remainder of the SVE register
state logically becomes zero at syscall entry, though the actual
zeroing work is currently deferred until the thread next tries to
use SVE, causing another trap to the kernel. This implementation
is suboptimal: in the future, the fastpath case may be optimised
to zero the registers in-place and leave SVE enabled for the task,
where beneficial.
TIF_SVE is also cleared in the following slowpath cases, which are
taken as reasonable hints that the task may no longer use SVE:
* exec
* fork and clone
Code is added to sync data between thread.fpsimd_state and
thread.sve_state whenever enabling/disabling SVE, in a manner
consistent with the SVE architectural programmer's model.
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Alex Bennée <alex.bennee@linaro.org>
[will: added #include to fix allnoconfig build]
[will: use enable_daif in do_sve_acc]
Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 22:51:05 +07:00
|
|
|
#ifdef CONFIG_ARM64_SVE
|
|
|
|
|
|
|
|
|
|
extern size_t sve_state_size(struct task_struct const *task);
|
|
|
|
|
|
|
|
|
|
extern void sve_alloc(struct task_struct *task);
|
|
|
|
|
extern void fpsimd_release_task(struct task_struct *task);
|
|
|
|
|
|
|
|
|
|
#else /* ! CONFIG_ARM64_SVE */
|
|
|
|
|
|
|
|
|
|
static inline void sve_alloc(struct task_struct *task) { }
|
|
|
|
|
static inline void fpsimd_release_task(struct task_struct *task) { }
|
|
|
|
|
|
|
|
|
|
#endif /* ! CONFIG_ARM64_SVE */
|
|
|
|
|
|
2017-08-03 23:23:22 +07:00
|
|
|
/* For use by EFI runtime services calls only */
|
|
|
|
|
extern void __efi_fpsimd_begin(void);
|
|
|
|
|
extern void __efi_fpsimd_end(void);
|
|
|
|
|
|
2012-03-05 18:49:32 +07:00
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#endif
|