0509666660
On each context switch we save the FPU registers on stack of old process and restore FPU registers from the stack of new one. That allows us to avoid doing that each time we enter/leave the kernel mode; however, that can get suboptimal in some cases. For one thing, we don't need to bother saving anything for kernel threads. For another, if between entering and leaving the kernel a thread gives CPU up more than once, it will do useless work, saving the same values every time, only to discard the saved copy as soon as it returns from switch_to(). Alternative solution: * move the array we save into from switch_stack to thread_info * have a (thread-synchronous) flag set when we save them * have another flag set when they should be restored on return to userland. * do *NOT* save/restore them in do_switch_stack()/undo_switch_stack(). * restore on the exit to user mode if the restore flag had been set. Clear both flags. * on context switch, entry to fork/clone/vfork, before entry into do_signal() and on entry into straced syscall save the registers and set the 'saved' flag unless it had been already set. * on context switch set the 'restore' flag as well. * have copy_thread() set both flags for child, so the registers would be restored once the child returns to userland. * use the saved data in setup_sigcontext(); have restore_sigcontext() set both flags and copy from sigframe to save area. * teach ptrace to look for FPU registers in thread_info instead of switch_stack. * teach isolated accesses to FPU registers (rdfpcr, wrfpcr, etc.) to check the 'saved' flag (under preempt_disable()) and work with the save area if it's been set; if 'saved' flag is found upon write access, set 'restore' flag as well. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Matt Turner <mattst88@gmail.com>
74 lines
1.7 KiB
C
74 lines
1.7 KiB
C
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
|
|
#ifndef _UAPI_ASMAXP_PTRACE_H
|
|
#define _UAPI_ASMAXP_PTRACE_H
|
|
|
|
|
|
/*
|
|
* This struct defines the way the registers are stored on the
|
|
* kernel stack during a system call or other kernel entry
|
|
*
|
|
* NOTE! I want to minimize the overhead of system calls, so this
|
|
* struct has as little information as possible. It does not have
|
|
*
|
|
* - floating point regs: the kernel doesn't change those
|
|
* - r9-15: saved by the C compiler
|
|
*
|
|
* This makes "fork()" and "exec()" a bit more complex, but should
|
|
* give us low system call latency.
|
|
*/
|
|
|
|
struct pt_regs {
|
|
unsigned long r0;
|
|
unsigned long r1;
|
|
unsigned long r2;
|
|
unsigned long r3;
|
|
unsigned long r4;
|
|
unsigned long r5;
|
|
unsigned long r6;
|
|
unsigned long r7;
|
|
unsigned long r8;
|
|
unsigned long r19;
|
|
unsigned long r20;
|
|
unsigned long r21;
|
|
unsigned long r22;
|
|
unsigned long r23;
|
|
unsigned long r24;
|
|
unsigned long r25;
|
|
unsigned long r26;
|
|
unsigned long r27;
|
|
unsigned long r28;
|
|
unsigned long hae;
|
|
/* JRP - These are the values provided to a0-a2 by PALcode */
|
|
unsigned long trap_a0;
|
|
unsigned long trap_a1;
|
|
unsigned long trap_a2;
|
|
/* These are saved by PAL-code: */
|
|
unsigned long ps;
|
|
unsigned long pc;
|
|
unsigned long gp;
|
|
unsigned long r16;
|
|
unsigned long r17;
|
|
unsigned long r18;
|
|
};
|
|
|
|
/*
|
|
* This is the extended stack used by signal handlers and the context
|
|
* switcher: it's pushed after the normal "struct pt_regs".
|
|
*/
|
|
struct switch_stack {
|
|
unsigned long r9;
|
|
unsigned long r10;
|
|
unsigned long r11;
|
|
unsigned long r12;
|
|
unsigned long r13;
|
|
unsigned long r14;
|
|
unsigned long r15;
|
|
unsigned long r26;
|
|
#ifndef __KERNEL__
|
|
unsigned long fp[32]; /* fp[31] is fpcr */
|
|
#endif
|
|
};
|
|
|
|
|
|
#endif /* _UAPI_ASMAXP_PTRACE_H */
|