arm64/sve: Fix missing SVE/FPSIMD endianness conversions

The in-memory representation of SVE and FPSIMD registers is
different: the FPSIMD V-registers are stored as single 128-bit
host-endian values, whereas SVE registers are stored in an
endianness-invariant byte order.

This means that the two representations differ when running on a
big-endian host.  But we blindly copy data from one representation
to another when converting between the two, resulting in the
register contents being unintentionally byteswapped in certain
situations.  Currently this can be triggered by the first SVE
instruction after a syscall, for example (though the potential
trigger points may vary in future).

So, fix the conversion functions fpsimd_to_sve(), sve_to_fpsimd()
and sve_sync_from_fpsimd_zeropad() to swab where appropriate.

There is no common swahl128() or swab128() that we could use here.
Maybe it would be worth making this generic, but for now add a
simple local hack.

Since the byte order differences are exposed in ABI, also clarify
the documentation.

Cc: Alex Bennée <alex.bennee@linaro.org>
Cc: Peter Maydell <peter.maydell@linaro.org>
Cc: Alan Hayward <alan.hayward@arm.com>
Cc: Julien Grall <julien.grall@arm.com>
Fixes: bc0ee4760364 ("arm64/sve: Core task context handling")
Fixes: 8cd969d28fd2 ("arm64/sve: Signal handling support")
Fixes: 43d4da2c45b2 ("arm64/sve: ptrace and ELF coredump support")
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
[will: Fix typos in comments and docs spotted by Julien]
Signed-off-by: Will Deacon <will.deacon@arm.com>

1 files changed, 33 insertions, 9 deletions

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index a38bf74bcca8..bb42cd04baec 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -39,6 +39,7 @@
 #include <linux/slab.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
+#include <linux/swab.h>
 
 #include <asm/esr.h>
 #include <asm/fpsimd.h>
@@ -352,6 +353,23 @@ static int __init sve_sysctl_init(void) { return 0; }
 #define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
 	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
 
+#ifdef CONFIG_CPU_BIG_ENDIAN
+static __uint128_t arm64_cpu_to_le128(__uint128_t x)
+{
+	u64 a = swab64(x);
+	u64 b = swab64(x >> 64);
+
+	return ((__uint128_t)a << 64) | b;
+}
+#else
+static __uint128_t arm64_cpu_to_le128(__uint128_t x)
+{
+	return x;
+}
+#endif
+
+#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x)
+
 /*
  * Transfer the FPSIMD state in task->thread.uw.fpsimd_state to
  * task->thread.sve_state.
@@ -369,14 +387,16 @@ static void fpsimd_to_sve(struct task_struct *task)
 	void *sst = task->thread.sve_state;
 	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
 	unsigned int i;
+	__uint128_t *p;
 
 	if (!system_supports_sve())
 		return;
 
 	vq = sve_vq_from_vl(task->thread.sve_vl);
-	for (i = 0; i < 32; ++i)
-		memcpy(ZREG(sst, vq, i), &fst->vregs[i],
-		       sizeof(fst->vregs[i]));
+	for (i = 0; i < 32; ++i) {
+		p = (__uint128_t *)ZREG(sst, vq, i);
+		*p = arm64_cpu_to_le128(fst->vregs[i]);
+	}
 }
 
 /*
@@ -395,14 +415,16 @@ static void sve_to_fpsimd(struct task_struct *task)
 	void const *sst = task->thread.sve_state;
 	struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state;
 	unsigned int i;
+	__uint128_t const *p;
 
 	if (!system_supports_sve())
 		return;
 
 	vq = sve_vq_from_vl(task->thread.sve_vl);
-	for (i = 0; i < 32; ++i)
-		memcpy(&fst->vregs[i], ZREG(sst, vq, i),
-		       sizeof(fst->vregs[i]));
+	for (i = 0; i < 32; ++i) {
+		p = (__uint128_t const *)ZREG(sst, vq, i);
+		fst->vregs[i] = arm64_le128_to_cpu(*p);
+	}
 }
 
 #ifdef CONFIG_ARM64_SVE
@@ -491,6 +513,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 	void *sst = task->thread.sve_state;
 	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
 	unsigned int i;
+	__uint128_t *p;
 
 	if (!test_tsk_thread_flag(task, TIF_SVE))
 		return;
@@ -499,9 +522,10 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 
 	memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
 
-	for (i = 0; i < 32; ++i)
-		memcpy(ZREG(sst, vq, i), &fst->vregs[i],
-		       sizeof(fst->vregs[i]));
+	for (i = 0; i < 32; ++i) {
+		p = (__uint128_t *)ZREG(sst, vq, i);
+		*p = arm64_cpu_to_le128(fst->vregs[i]);
+	}
 }
 
 int sve_set_vector_length(struct task_struct *task,