summaryrefslogtreecommitdiffstats
path: root/arch/arm64
diff options
context:
space:
mode:
authorArd Biesheuvel <ard.biesheuvel@linaro.org>2014-02-24 15:26:29 +0100
committerArd Biesheuvel <ard.biesheuvel@linaro.org>2014-05-08 11:31:57 +0200
commit190f1ca85d071114930dd7abe6b5d103e9d5572f (patch)
tree27344d61659e775df00892c8a13ae2473aad29b1 /arch/arm64
parent005f78cd88494457ed38ce817f4e3fe5d372f0cb (diff)
downloadop-kernel-dev-190f1ca85d071114930dd7abe6b5d103e9d5572f.zip
op-kernel-dev-190f1ca85d071114930dd7abe6b5d103e9d5572f.tar.gz
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>
Diffstat (limited to 'arch/arm64')
-rw-r--r--arch/arm64/include/asm/fpsimd.h15
-rw-r--r--arch/arm64/include/asm/fpsimdmacros.h35
-rw-r--r--arch/arm64/include/asm/neon.h6
-rw-r--r--arch/arm64/kernel/entry-fpsimd.S24
-rw-r--r--arch/arm64/kernel/fpsimd.c44
5 files changed, 109 insertions, 15 deletions
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 @@ struct fpsimd_state {
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_update_current_state(struct fpsimd_state *state);
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);
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 6a27cd6..d358cca 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -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
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 5ae8930..ad8aebb 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -218,29 +218,45 @@ void fpsimd_flush_task_state(struct task_struct *t)
#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 (in_interrupt()) {
+ struct fpsimd_partial_state *s = this_cpu_ptr(
+ in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
- /*
- * Save the userland FPSIMD state if we have one and if we haven't done
- * so already. Clear fpsimd_last_state to indicate that there is no
- * longer userland FPSIMD state in the registers.
- */
- if (current->mm && !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
- fpsimd_save_state(&current->thread.fpsimd_state);
- this_cpu_write(fpsimd_last_state, NULL);
+ BUG_ON(num_regs > 32);
+ fpsimd_save_partial_state(s, roundup(num_regs, 2));
+ } else {
+ /*
+ * Save the userland FPSIMD state if we have one and if we
+ * haven't done so already. Clear fpsimd_last_state to indicate
+ * that there is no longer userland FPSIMD state in the
+ * registers.
+ */
+ preempt_disable();
+ if (current->mm &&
+ !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
+ fpsimd_save_state(&current->thread.fpsimd_state);
+ this_cpu_write(fpsimd_last_state, NULL);
+ }
}
-EXPORT_SYMBOL(kernel_neon_begin);
+EXPORT_SYMBOL(kernel_neon_begin_partial);
void kernel_neon_end(void)
{
- 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 {
+ preempt_enable();
+ }
}
EXPORT_SYMBOL(kernel_neon_end);
OpenPOWER on IntegriCloud