arm64/sme: Add ptrace support for ZA

The ZA array can be read and written with the NT_ARM_ZA.  Similarly to
our interface for the SVE vector registers the regset consists of a
header with information on the current vector length followed by an
optional register data payload, represented as for signals as a series
of horizontal vectors from 0 to VL/8 in the endianness independent
format used for vectors.

On get if ZA is enabled then register data will be provided, otherwise
it will be omitted.  On set if register data is provided then ZA is
enabled and initialized using the provided data, otherwise it is
disabled.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-22-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

1 files changed, 144 insertions, 0 deletions

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 60185c27b394..47d8a7472171 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -997,6 +997,141 @@ static int ssve_set(struct task_struct *target,
 			      ARM64_VEC_SME);
 }
 
+static int za_get(struct task_struct *target,
+		  const struct user_regset *regset,
+		  struct membuf to)
+{
+	struct user_za_header header;
+	unsigned int vq;
+	unsigned long start, end;
+
+	if (!system_supports_sme())
+		return -EINVAL;
+
+	/* Header */
+	memset(&header, 0, sizeof(header));
+
+	if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT))
+		header.flags |= ZA_PT_VL_INHERIT;
+
+	header.vl = task_get_sme_vl(target);
+	vq = sve_vq_from_vl(header.vl);
+	header.max_vl = sme_max_vl();
+	header.max_size = ZA_PT_SIZE(vq);
+
+	/* If ZA is not active there is only the header */
+	if (thread_za_enabled(&target->thread))
+		header.size = ZA_PT_SIZE(vq);
+	else
+		header.size = ZA_PT_ZA_OFFSET;
+
+	membuf_write(&to, &header, sizeof(header));
+
+	BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header));
+	end = ZA_PT_ZA_OFFSET;
+
+	if (target == current)
+		fpsimd_preserve_current_state();
+
+	/* Any register data to include? */
+	if (thread_za_enabled(&target->thread)) {
+		start = end;
+		end = ZA_PT_SIZE(vq);
+		membuf_write(&to, target->thread.za_state, end - start);
+	}
+
+	/* Zero any trailing padding */
+	start = end;
+	end = ALIGN(header.size, SVE_VQ_BYTES);
+	return membuf_zero(&to, end - start);
+}
+
+static int za_set(struct task_struct *target,
+		  const struct user_regset *regset,
+		  unsigned int pos, unsigned int count,
+		  const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct user_za_header header;
+	unsigned int vq;
+	unsigned long start, end;
+
+	if (!system_supports_sme())
+		return -EINVAL;
+
+	/* Header */
+	if (count < sizeof(header))
+		return -EINVAL;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header,
+				 0, sizeof(header));
+	if (ret)
+		goto out;
+
+	/*
+	 * All current ZA_PT_* flags are consumed by
+	 * vec_set_vector_length(), which will also validate them for
+	 * us:
+	 */
+	ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl,
+		((unsigned long)header.flags) << 16);
+	if (ret)
+		goto out;
+
+	/* Actual VL set may be less than the user asked for: */
+	vq = sve_vq_from_vl(task_get_sme_vl(target));
+
+	/* Ensure there is some SVE storage for streaming mode */
+	if (!target->thread.sve_state) {
+		sve_alloc(target);
+		if (!target->thread.sve_state) {
+			clear_thread_flag(TIF_SME);
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
+
+	/* Allocate/reinit ZA storage */
+	sme_alloc(target);
+	if (!target->thread.za_state) {
+		ret = -ENOMEM;
+		clear_tsk_thread_flag(target, TIF_SME);
+		goto out;
+	}
+
+	/* If there is no data then disable ZA */
+	if (!count) {
+		target->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK;
+		goto out;
+	}
+
+	/*
+	 * If setting a different VL from the requested VL and there is
+	 * register data, the data layout will be wrong: don't even
+	 * try to set the registers in this case.
+	 */
+	if (vq != sve_vq_from_vl(header.vl)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header));
+	start = ZA_PT_ZA_OFFSET;
+	end = ZA_PT_SIZE(vq);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 target->thread.za_state,
+				 start, end);
+	if (ret)
+		goto out;
+
+	/* Mark ZA as active and let userspace use it */
+	set_tsk_thread_flag(target, TIF_SME);
+	target->thread.svcr |= SYS_SVCR_EL0_ZA_MASK;
+
+out:
+	fpsimd_flush_task_state(target);
+	return ret;
+}
+
 #endif /* CONFIG_ARM64_SME */
 
 #ifdef CONFIG_ARM64_PTR_AUTH
@@ -1218,6 +1353,7 @@ enum aarch64_regset {
 #endif
 #ifdef CONFIG_ARM64_SVE
 	REGSET_SSVE,
+	REGSET_ZA,
 #endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	REGSET_PAC_MASK,
@@ -1309,6 +1445,14 @@ static const struct user_regset aarch64_regsets[] = {
 		.regset_get = ssve_get,
 		.set = ssve_set,
 	},
+	[REGSET_ZA] = { /* SME ZA */
+		.core_note_type = NT_ARM_ZA,
+		.n = DIV_ROUND_UP(ZA_PT_ZA_SIZE(SVE_VQ_MAX), SVE_VQ_BYTES),
+		.size = SVE_VQ_BYTES,
+		.align = SVE_VQ_BYTES,
+		.regset_get = za_get,
+		.set = za_set,
+	},
 #endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	[REGSET_PAC_MASK] = {