diff options
author | Linus Torvalds <[email protected]> | 2023-10-18 20:41:58 +0200 |
---|---|---|
committer | Ingo Molnar <[email protected]> | 2023-10-20 11:24:22 +0200 |
commit | 24b8a23638cbf92449c353f828b1d309548c78f4 (patch) | |
tree | ea69830f0ac605520d2ee26f36ccd106d412a32d /arch/x86/kernel | |
parent | e39828d2c1c0781ccfcf742791daf88fdfa481ea (diff) |
x86/fpu: Clean up FPU switching in the middle of task switching
It happens to work, but it's very very wrong, because our 'current'
macro is magic that is supposedly loading a stable value.
It just happens to be not quite stable enough and the compilers
re-load the value enough for this code to work. But it's wrong.
The whole
struct fpu *prev_fpu = &prev->fpu;
thing in __switch_to() is pretty ugly. There's no reason why we
should look at that 'prev_fpu' pointer there, or pass it down.
And it only generates worse code, in how it loads 'current' when
__switch_to() has the right task pointers.
The attached patch not only cleans this up, it actually
generates better code too:
(a) it removes one push/pop pair at entry/exit because there's one
less register used (no 'current')
(b) it removes that pointless load of 'current' because it just uses
the right argument:
- movq %gs:pcpu_hot(%rip), %r12
- testq $16384, (%r12)
+ testq $16384, (%rdi)
Signed-off-by: Linus Torvalds <[email protected]>
Signed-off-by: Uros Bizjak <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r-- | arch/x86/kernel/process_32.c | 7 | ||||
-rw-r--r-- | arch/x86/kernel/process_64.c | 7 |
2 files changed, 6 insertions, 8 deletions
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 708c87b88cc1..0917c7f25720 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -156,13 +156,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread, *next = &next_p->thread; - struct fpu *prev_fpu = &prev->fpu; int cpu = smp_processor_id(); /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_prepare(prev_fpu, cpu); + if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD)) + switch_fpu_prepare(prev_p, cpu); /* * Save away %gs. No need to save %fs, as it was saved on the @@ -209,7 +208,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) raw_cpu_write(pcpu_hot.current_task, next_p); - switch_fpu_finish(); + switch_fpu_finish(next_p); /* Load the Intel cache allocation PQR MSR. */ resctrl_sched_in(next_p); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 33b268747bb7..1553e19904e0 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -562,14 +562,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; - struct fpu *prev_fpu = &prev->fpu; int cpu = smp_processor_id(); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && this_cpu_read(pcpu_hot.hardirq_stack_inuse)); - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_prepare(prev_fpu, cpu); + if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD)) + switch_fpu_prepare(prev_p, cpu); /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). @@ -623,7 +622,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) raw_cpu_write(pcpu_hot.current_task, next_p); raw_cpu_write(pcpu_hot.top_of_stack, task_top_of_stack(next_p)); - switch_fpu_finish(); + switch_fpu_finish(next_p); /* Reload sp0. */ update_task_stack(next_p); |