arm64: add support for kernel mode NEON in interrupt context
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>
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 7a90014..50f559f 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -41,6 +41,17 @@
unsigned int cpu;
};
+/*
+ * Struct for stacking the bottom 'n' FP/SIMD registers.
+ */
+struct fpsimd_partial_state {
+ u32 fpsr;
+ u32 fpcr;
+ u32 num_regs;
+ __uint128_t vregs[32];
+};
+
+
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/* Masks for extracting the FPSR and FPCR from the FPSCR */
#define VFP_FPSCR_STAT_MASK 0xf800009f
@@ -66,6 +77,10 @@
extern void fpsimd_flush_task_state(struct task_struct *target);
+extern void fpsimd_save_partial_state(struct fpsimd_partial_state *state,
+ u32 num_regs);
+extern void fpsimd_load_partial_state(struct fpsimd_partial_state *state);
+
#endif
#endif
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index bbec599..768414d 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -62,3 +62,38 @@
ldr w\tmpnr, [\state, #16 * 2 + 4]
msr fpcr, x\tmpnr
.endm
+
+.altmacro
+.macro fpsimd_save_partial state, numnr, tmpnr1, tmpnr2
+ mrs x\tmpnr1, fpsr
+ str w\numnr, [\state, #8]
+ mrs x\tmpnr2, fpcr
+ stp w\tmpnr1, w\tmpnr2, [\state]
+ 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
+ .irp qb, %(qa + 1)
+ stp q\qa, q\qb, [\state, # -16 * \qa - 16]
+ .endr
+ .endr
+0:
+.endm
+
+.macro fpsimd_restore_partial state, tmpnr1, tmpnr2
+ ldp w\tmpnr1, w\tmpnr2, [\state]
+ msr fpsr, x\tmpnr1
+ msr fpcr, x\tmpnr2
+ adr x\tmpnr1, 0f
+ ldr w\tmpnr2, [\state, #8]
+ 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
+ .irp qb, %(qa + 1)
+ ldp q\qa, q\qb, [\state, # -16 * \qa - 16]
+ .endr
+ .endr
+0:
+.endm
diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
index b0cc58a9..13ce4cc 100644
--- a/arch/arm64/include/asm/neon.h
+++ b/arch/arm64/include/asm/neon.h
@@ -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);