target/arm: Implement MTE tag-checking functions for FEAT_MOPS

The FEAT_MOPS instructions need a couple of helper routines that
check for MTE tag failures:
 * mte_mops_probe() checks whether there is going to be a tag
   error in the next up-to-a-page worth of data
 * mte_check_fail() is an existing function to record the fact
   of a tag failure, which we need to make global so we can
   call it from helper-a64.c

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20230912140434.1333369-7-peter.maydell@linaro.org

2 files changed, 80 insertions, 2 deletions

diff --git a/target/arm/internals.h b/target/arm/internals.h
index 5f5393b..a70a7fd 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -1272,6 +1272,34 @@ FIELD(MTEDESC, SIZEM1, 12, SIMD_DATA_BITS - 12)  /* size - 1 */
 bool mte_probe(CPUARMState *env, uint32_t desc, uint64_t ptr);
 uint64_t mte_check(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra);
 
+/**
+ * mte_mops_probe: Check where the next MTE failure is for a FEAT_MOPS operation
+ * @env: CPU env
+ * @ptr: start address of memory region (dirty pointer)
+ * @size: length of region (guaranteed not to cross a page boundary)
+ * @desc: MTEDESC descriptor word (0 means no MTE checks)
+ * Returns: the size of the region that can be copied without hitting
+ *          an MTE tag failure
+ *
+ * Note that we assume that the caller has already checked the TBI
+ * and TCMA bits with mte_checks_needed() and an MTE check is definitely
+ * required.
+ */
+uint64_t mte_mops_probe(CPUARMState *env, uint64_t ptr, uint64_t size,
+                        uint32_t desc);
+
+/**
+ * mte_check_fail: Record an MTE tag check failure
+ * @env: CPU env
+ * @desc: MTEDESC descriptor word
+ * @dirty_ptr: Failing dirty address
+ * @ra: TCG retaddr
+ *
+ * This may never return (if the MTE tag checks are configured to fault).
+ */
+void mte_check_fail(CPUARMState *env, uint32_t desc,
+                    uint64_t dirty_ptr, uintptr_t ra);
+
 static inline int allocation_tag_from_addr(uint64_t ptr)
 {
     return extract64(ptr, 56, 4);
diff --git a/target/arm/tcg/mte_helper.c b/target/arm/tcg/mte_helper.c
index 303bcc7..1cb61ce 100644
--- a/target/arm/tcg/mte_helper.c
+++ b/target/arm/tcg/mte_helper.c
@@ -617,8 +617,8 @@ static void mte_async_check_fail(CPUARMState *env, uint64_t dirty_ptr,
 }
 
 /* Record a tag check failure.  */
-static void mte_check_fail(CPUARMState *env, uint32_t desc,
-                           uint64_t dirty_ptr, uintptr_t ra)
+void mte_check_fail(CPUARMState *env, uint32_t desc,
+                    uint64_t dirty_ptr, uintptr_t ra)
 {
     int mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX);
     ARMMMUIdx arm_mmu_idx = core_to_aa64_mmu_idx(mmu_idx);
@@ -991,3 +991,53 @@ uint64_t HELPER(mte_check_zva)(CPUARMState *env, uint32_t desc, uint64_t ptr)
  done:
     return useronly_clean_ptr(ptr);
 }
+
+uint64_t mte_mops_probe(CPUARMState *env, uint64_t ptr, uint64_t size,
+                        uint32_t desc)
+{
+    int mmu_idx, tag_count;
+    uint64_t ptr_tag, tag_first, tag_last;
+    void *mem;
+    bool w = FIELD_EX32(desc, MTEDESC, WRITE);
+    uint32_t n;
+
+    mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX);
+    /* True probe; this will never fault */
+    mem = allocation_tag_mem_probe(env, mmu_idx, ptr,
+                                   w ? MMU_DATA_STORE : MMU_DATA_LOAD,
+                                   size, MMU_DATA_LOAD, true, 0);
+    if (!mem) {
+        return size;
+    }
+
+    /*
+     * TODO: checkN() is not designed for checks of the size we expect
+     * for FEAT_MOPS operations, so we should implement this differently.
+     * Maybe we should do something like
+     *   if (region start and size are aligned nicely) {
+     *      do direct loads of 64 tag bits at a time;
+     *   } else {
+     *      call checkN()
+     *   }
+     */
+    /* Round the bounds to the tag granule, and compute the number of tags. */
+    ptr_tag = allocation_tag_from_addr(ptr);
+    tag_first = QEMU_ALIGN_DOWN(ptr, TAG_GRANULE);
+    tag_last = QEMU_ALIGN_DOWN(ptr + size - 1, TAG_GRANULE);
+    tag_count = ((tag_last - tag_first) / TAG_GRANULE) + 1;
+    n = checkN(mem, ptr & TAG_GRANULE, ptr_tag, tag_count);
+    if (likely(n == tag_count)) {
+        return size;
+    }
+
+    /*
+     * Failure; for the first granule, it's at @ptr. Otherwise
+     * it's at the first byte of the nth granule. Calculate how
+     * many bytes we can access without hitting that failure.
+     */
+    if (n == 0) {
+        return 0;
+    } else {
+        return n * TAG_GRANULE - (ptr - tag_first);
+    }
+}