@@ -39,6 +39,19 @@ struct fpsimd_state {
};
};
+/*
+ * Struct for stacking the bottom 'n' FP/SIMD registers.
+ * Mainly intended for kernel use of v8 Crypto Extensions which only
+ * needs a few registers and may need to execute in atomic context.
+ */
+struct fpsimd_partial_state {
+ u32 num_regs;
+ u32 fpsr;
+ u32 fpcr;
+ __uint128_t vregs[32] __aligned(16);
+} __aligned(16);
+
+
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/* Masks for extracting the FPSR and FPCR from the FPSCR */
#define VFP_FPSCR_STAT_MASK 0xf800009f
@@ -55,6 +68,10 @@ struct task_struct;
extern void fpsimd_save_state(struct fpsimd_state *state);
extern void fpsimd_load_state(struct fpsimd_state *state);
+void fpsimd_save_partial_state(struct fpsimd_partial_state *state,
+ u32 num_regs);
+void fpsimd_load_partial_state(struct fpsimd_partial_state *state);
+
extern void fpsimd_thread_switch(struct task_struct *next);
extern void fpsimd_flush_thread(void);
@@ -62,3 +62,40 @@
ldr w\tmpnr, [\state, #16 * 2 + 4]
msr fpcr, x\tmpnr
.endm
+
+.altmacro
+.macro q2op, op, q1, q2, state
+ \op q\q1, q\q2, [\state, # -16 * \q1 - 16]
+.endm
+
+.macro fpsimd_save_partial state, numnr, tmpnr1, tmpnr2
+ mrs x\tmpnr1, fpsr
+ str w\numnr, [\state]
+ mrs x\tmpnr2, fpcr
+ stp w\tmpnr1, w\tmpnr2, [\state, #4]
+ adr x\tmpnr1, 0f
+ add \state, \state, x\numnr, lsl #4
+ sub x\tmpnr1, x\tmpnr1, x\numnr, lsl #1
+ br x\tmpnr1
+ .irp qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0
+ qb = \qa + 1
+ q2op stp, \qa, %qb, \state
+ .endr
+0:
+.endm
+
+.macro fpsimd_restore_partial state, tmpnr1, tmpnr2
+ ldp w\tmpnr1, w\tmpnr2, [\state, #4]
+ msr fpsr, x\tmpnr1
+ msr fpcr, x\tmpnr2
+ adr x\tmpnr1, 0f
+ ldr w\tmpnr2, [\state]
+ add \state, \state, x\tmpnr2, lsl #4
+ sub x\tmpnr1, x\tmpnr1, x\tmpnr2, lsl #1
+ br x\tmpnr1
+ .irp qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0
+ qb = \qa + 1
+ q2op ldp, \qa, %qb, \state
+ .endr
+0:
+.endm
@@ -8,7 +8,11 @@
* published by the Free Software Foundation.
*/
+#include <linux/types.h>
+
#define cpu_has_neon() (1)
-void kernel_neon_begin(void);
+#define kernel_neon_begin() kernel_neon_begin_partial(32)
+
+void kernel_neon_begin_partial(u32 num_regs);
void kernel_neon_end(void);
@@ -41,3 +41,27 @@ ENTRY(fpsimd_load_state)
fpsimd_restore x0, 8
ret
ENDPROC(fpsimd_load_state)
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Save the bottom n FP registers.
+ *
+ * x0 - pointer to struct fpsimd_partial_state
+ */
+ENTRY(fpsimd_save_partial_state)
+ fpsimd_save_partial x0, 1, 8, 9
+ ret
+ENDPROC(fpsimd_load_partial_state)
+
+/*
+ * Load the bottom n FP registers.
+ *
+ * x0 - pointer to struct fpsimd_partial_state
+ */
+ENTRY(fpsimd_load_partial_state)
+ fpsimd_restore_partial x0, 8, 9
+ ret
+ENDPROC(fpsimd_load_partial_state)
+
+#endif
@@ -86,26 +86,39 @@ void fpsimd_flush_thread(void)
#ifdef CONFIG_KERNEL_MODE_NEON
+static DEFINE_PER_CPU(struct fpsimd_partial_state, hardirq_fpsimdstate);
+static DEFINE_PER_CPU(struct fpsimd_partial_state, softirq_fpsimdstate);
+
/*
* Kernel-side NEON support functions
*/
-void kernel_neon_begin(void)
+void kernel_neon_begin_partial(u32 num_regs)
{
- /* Avoid using the NEON in interrupt context */
- BUG_ON(in_interrupt());
- preempt_disable();
-
- if (current->mm)
- fpsimd_save_state(¤t->thread.fpsimd_state);
+ BUG_ON(num_regs > 32);
+
+ if (in_interrupt()) {
+ struct fpsimd_partial_state *s = this_cpu_ptr(
+ in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
+ fpsimd_save_partial_state(s, roundup(num_regs, 2));
+ } else {
+ preempt_disable();
+ if (current->mm)
+ fpsimd_save_state(¤t->thread.fpsimd_state);
+ }
}
-EXPORT_SYMBOL(kernel_neon_begin);
+EXPORT_SYMBOL(kernel_neon_begin_partial);
void kernel_neon_end(void)
{
- if (current->mm)
- fpsimd_load_state(¤t->thread.fpsimd_state);
-
- preempt_enable();
+ if (in_interrupt()) {
+ struct fpsimd_partial_state *s = this_cpu_ptr(
+ in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
+ fpsimd_load_partial_state(s);
+ } else {
+ if (current->mm)
+ fpsimd_load_state(¤t->thread.fpsimd_state);
+ preempt_enable();
+ }
}
EXPORT_SYMBOL(kernel_neon_end);
This patch modifies kernel_neon_begin() and kernel_neon_end(), so they may be called from any context. To address the case where only a couple of registers are needed, kernel_neon_begin_partial(u32) is introduced which takes as a parameter the number of bottom 'n' NEON q-registers required. To mark the end of such a partial section, the regular kernel_neon_end() should be used. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- Instead of having arm/arm64 versions at every iteration, I propose to discuss this for arm64, which has a much stronger case for this feature with the Crypto Extensions. Once we are aligned I will implement for ARM as well. arch/arm64/include/asm/fpsimd.h | 17 ++++++++++++++++ arch/arm64/include/asm/fpsimdmacros.h | 37 +++++++++++++++++++++++++++++++++++ arch/arm64/include/asm/neon.h | 6 +++++- arch/arm64/kernel/entry-fpsimd.S | 24 +++++++++++++++++++++++ arch/arm64/kernel/fpsimd.c | 37 +++++++++++++++++++++++------------ 5 files changed, 108 insertions(+), 13 deletions(-)