static __always_inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next, struct rq_flags *rf)
{
struct mm_struct *mm, *oldmm;
prepare_task_switch(rq, prev, next);
mm = next->mm;
oldmm = prev->active_mm;
/*
* For paravirt, this is coupled with an exit in switch_to to
* combine the page table reload and the switch backend into
* one hypercall.
*/
arch_start_context_switch(prev);
if (!mm) {
next->active_mm = oldmm;
mmgrab(oldmm);
enter_lazy_tlb(oldmm, next);
} else
switch_mm_irqs_off(oldmm, mm, next);
if (!prev->mm) {
prev->active_mm = NULL;
rq->prev_mm = oldmm;
}
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
/*
* Since the runqueue lock will be released by the next
* task (which is an invalid locking op but in the case
* of the scheduler it's an obvious special-case), so we
* do an early lockdep release here:
*/
rq_unpin_lock(rq, rf);
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
/* Here we just switch the register state and the stack. */
switch_to(prev, next, prev);
barrier();
return finish_task_switch(prev);
}
__notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
struct task_struct *next)
{
struct task_struct *last;
fpsimd_thread_switch(next);
tls_thread_switch(next);
hw_breakpoint_thread_switch(next);
contextidr_thread_switch(next);
entry_task_switch(next);
uao_thread_switch(next);
/*
* Complete any pending TLB or cache maintenance on this CPU in case
* the thread migrates to a different CPU.
* This full barrier is also required by the membarrier system
* call.
*/
dsb(ish);
/* the actual thread switch */
last = cpu_switch_to(prev, next);
return last;
}
/*
* Register switch for AArch64. The callee-saved registers need to be saved
* and restored. On entry:
* x0 = previous task_struct (must be preserved across the switch)
* x1 = next task_struct
* Previous and next are guaranteed not to be the same.
*
*/
ENTRY(cpu_switch_to)
mov x10, #THREAD_CPU_CONTEXT
add x8, x0, x10
mov x9, sp
stp x19, x20, [x8], #16 // store callee-saved registers
stp x21, x22, [x8], #16
stp x23, x24, [x8], #16
stp x25, x26, [x8], #16
stp x27, x28, [x8], #16
stp x29, x9, [x8], #16
str lr, [x8]
add x8, x1, x10
ldp x19, x20, [x8], #16 // restore callee-saved registers
ldp x21, x22, [x8], #16
ldp x23, x24, [x8], #16
ldp x25, x26, [x8], #16
ldp x27, x28, [x8], #16
ldp x29, x9, [x8], #16
ldr lr, [x8]
mov sp, x9
msr sp_el0, x1
ret
ENDPROC(cpu_switch_to)
NOKPROBE(cpu_switch_to)
void fpsimd_thread_switch(struct task_struct *next)
{
if (!system_supports_fpsimd())
return;
__get_cpu_fpsimd_context();
/*
* Save the current FPSIMD state to memory, but only if whatever is in
* the registers is in fact the most recent userland FPSIMD state of
* 'current'.
*/
if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
fpsimd_save_state(¤t->thread.fpsimd_state);
if (next->mm) {
/*
* If we are switching to a task whose most recent userland
* FPSIMD state is already in the registers of *this* cpu,
* we can skip loading the state from memory. Otherwise, set
* the TIF_FOREIGN_FPSTATE flag so the state will be loaded
* upon the next return to userland.
*/
struct fpsimd_state *st = &next->thread.fpsimd_state;
if (__this_cpu_read(fpsimd_last_state) == st
&& st->cpu == smp_processor_id())
clear_ti_thread_flag(task_thread_info(next),
TIF_FOREIGN_FPSTATE);
else
set_ti_thread_flag(task_thread_info(next),
TIF_FOREIGN_FPSTATE);
}
__put_cpu_fpsimd_context();
}
/*
* Save the FP registers.
*
* x0 - pointer to struct fpsimd_state
*/
ENTRY(fpsimd_save_state)
fpsimd_save x0, 8
ret
ENDPROC(fpsimd_save_state)
.macro fpsimd_save state, tmpnr
stp q0, q1, [\state, #16 * 0]
stp q2, q3, [\state, #16 * 2]
stp q4, q5, [\state, #16 * 4]
stp q6, q7, [\state, #16 * 6]
stp q8, q9, [\state, #16 * 8]
stp q10, q11, [\state, #16 * 10]
stp q12, q13, [\state, #16 * 12]
stp q14, q15, [\state, #16 * 14]
stp q16, q17, [\state, #16 * 16]
stp q18, q19, [\state, #16 * 18]
stp q20, q21, [\state, #16 * 20]
stp q22, q23, [\state, #16 * 22]
stp q24, q25, [\state, #16 * 24]
stp q26, q27, [\state, #16 * 26]
stp q28, q29, [\state, #16 * 28]
stp q30, q31, [\state, #16 * 30]!
mrs x\tmpnr, fpsr
str w\tmpnr, [\state, #16 * 2]
mrs x\tmpnr, fpcr
str w\tmpnr, [\state, #16 * 2 + 4]
.endm
/*
* In order to reduce the number of times the FPSIMD state is needlessly saved
* and restored, we need to keep track of two things:
* (a) for each task, we need to remember which CPU was the last one to have
* the task's FPSIMD state loaded into its FPSIMD registers;
* (b) for each CPU, we need to remember which task's userland FPSIMD state has
* been loaded into its FPSIMD registers most recently, or whether it has
* been used to perform kernel mode NEON in the meantime.
*
* For (a), we add a 'cpu' field to struct fpsimd_state, which gets updated to
* the id of the current CPU every time the state is loaded onto a CPU. For (b),
* we add the per-cpu variable 'fpsimd_last_state' (below), which contains the
* address of the userland FPSIMD state of the task that was loaded onto the CPU
* the most recently, or NULL if kernel mode NEON has been performed after that.
*
* With this in place, we no longer have to restore the next FPSIMD state right
* when switching between tasks. Instead, we can defer this check to userland
* resume, at which time we verify whether the CPU's fpsimd_last_state and the
* task's fpsimd_state.cpu are still mutually in sync. If this is the case, we
* can omit the FPSIMD restore.
*
* As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to
* indicate whether or not the userland FPSIMD state of the current task is
* present in the registers. The flag is set unless the FPSIMD registers of this
* CPU currently contain the most recent userland FPSIMD state of the current
* task.
*
* In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may
* save the task's FPSIMD context back to task_struct from softirq context.
* To prevent this from racing with the manipulation of the task's FPSIMD state
* from task context and thereby corrupting the state, it is necessary to
* protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE
* flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to
* run but prevent them to use FPSIMD.
*
* For a certain task, the sequence may look something like this:
* - the task gets scheduled in; if both the task's fpsimd_state.cpu field
* contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu
* variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is
* cleared, otherwise it is set;
*
* - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's
* userland FPSIMD state is copied from memory to the registers, the task's
* fpsimd_state.cpu field is set to the id of the current CPU, the current
* CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the
* TIF_FOREIGN_FPSTATE flag is cleared;
*
* - the task executes an ordinary syscall; upon return to userland, the
* TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is
* restored;
*
* - the task executes a syscall which executes some NEON instructions; this is
* preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD
* register contents to memory, clears the fpsimd_last_state per-cpu variable
* and sets the TIF_FOREIGN_FPSTATE flag;
*
* - the task gets preempted after kernel_neon_end() is called; as we have not
* returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
* whatever is in the FPSIMD registers is not saved to memory, but discarded.
*/