[Qemu-devel] [PATCH v2 14/23] target/arm: Move the DC ZVA helper into op_helper

["Philippe Mathieu-Daudé" <philmd@redhat.com>]

From: Samuel Ortiz <sameo@linux.intel.com>

Those helpers are a software implementation of the ARM v8 memory zeroing
op code. They should be moved to the op helper file, which is going to
eventually be built only when TCG is enabled.

Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Robert Bradford <robert.bradford@intel.com>
[PMD: Rebased]
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
---
 target/arm/helper.c    | 92 -----------------------------------------
 target/arm/op_helper.c | 93 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 93 insertions(+), 92 deletions(-)

diff --git a/target/arm/helper.c b/target/arm/helper.c
index 24d88eef17..673ada1e86 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -10674,98 +10674,6 @@ bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
 #endif
 }
 
-void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in)
-{
-    /*
-     * Implement DC ZVA, which zeroes a fixed-length block of memory.
-     * Note that we do not implement the (architecturally mandated)
-     * alignment fault for attempts to use this on Device memory
-     * (which matches the usual QEMU behaviour of not implementing either
-     * alignment faults or any memory attribute handling).
-     */
-
-    ARMCPU *cpu = env_archcpu(env);
-    uint64_t blocklen = 4 << cpu->dcz_blocksize;
-    uint64_t vaddr = vaddr_in & ~(blocklen - 1);
-
-#ifndef CONFIG_USER_ONLY
-    {
-        /*
-         * Slightly awkwardly, QEMU's TARGET_PAGE_SIZE may be less than
-         * the block size so we might have to do more than one TLB lookup.
-         * We know that in fact for any v8 CPU the page size is at least 4K
-         * and the block size must be 2K or less, but TARGET_PAGE_SIZE is only
-         * 1K as an artefact of legacy v5 subpage support being present in the
-         * same QEMU executable. So in practice the hostaddr[] array has
-         * two entries, given the current setting of TARGET_PAGE_BITS_MIN.
-         */
-        int maxidx = DIV_ROUND_UP(blocklen, TARGET_PAGE_SIZE);
-        void *hostaddr[DIV_ROUND_UP(2 * KiB, 1 << TARGET_PAGE_BITS_MIN)];
-        int try, i;
-        unsigned mmu_idx = cpu_mmu_index(env, false);
-        TCGMemOpIdx oi = make_memop_idx(MO_UB, mmu_idx);
-
-        assert(maxidx <= ARRAY_SIZE(hostaddr));
-
-        for (try = 0; try < 2; try++) {
-
-            for (i = 0; i < maxidx; i++) {
-                hostaddr[i] = tlb_vaddr_to_host(env,
-                                                vaddr + TARGET_PAGE_SIZE * i,
-                                                1, mmu_idx);
-                if (!hostaddr[i]) {
-                    break;
-                }
-            }
-            if (i == maxidx) {
-                /*
-                 * If it's all in the TLB it's fair game for just writing to;
-                 * we know we don't need to update dirty status, etc.
-                 */
-                for (i = 0; i < maxidx - 1; i++) {
-                    memset(hostaddr[i], 0, TARGET_PAGE_SIZE);
-                }
-                memset(hostaddr[i], 0, blocklen - (i * TARGET_PAGE_SIZE));
-                return;
-            }
-            /*
-             * OK, try a store and see if we can populate the tlb. This
-             * might cause an exception if the memory isn't writable,
-             * in which case we will longjmp out of here. We must for
-             * this purpose use the actual register value passed to us
-             * so that we get the fault address right.
-             */
-            helper_ret_stb_mmu(env, vaddr_in, 0, oi, GETPC());
-            /* Now we can populate the other TLB entries, if any */
-            for (i = 0; i < maxidx; i++) {
-                uint64_t va = vaddr + TARGET_PAGE_SIZE * i;
-                if (va != (vaddr_in & TARGET_PAGE_MASK)) {
-                    helper_ret_stb_mmu(env, va, 0, oi, GETPC());
-                }
-            }
-        }
-
-        /*
-         * Slow path (probably attempt to do this to an I/O device or
-         * similar, or clearing of a block of code we have translations
-         * cached for). Just do a series of byte writes as the architecture
-         * demands. It's not worth trying to use a cpu_physical_memory_map(),
-         * memset(), unmap() sequence here because:
-         *  + we'd need to account for the blocksize being larger than a page
-         *  + the direct-RAM access case is almost always going to be dealt
-         *    with in the fastpath code above, so there's no speed benefit
-         *  + we would have to deal with the map returning NULL because the
-         *    bounce buffer was in use
-         */
-        for (i = 0; i < blocklen; i++) {
-            helper_ret_stb_mmu(env, vaddr + i, 0, oi, GETPC());
-        }
-    }
-#else
-    memset(g2h(vaddr), 0, blocklen);
-#endif
-}
-
 /* Note that signed overflow is undefined in C.  The following routines are
    careful to use unsigned types where modulo arithmetic is required.
    Failure to do so _will_ break on newer gcc.  */
diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
index db4254a67b..29b56039e5 100644
--- a/target/arm/op_helper.c
+++ b/target/arm/op_helper.c
@@ -17,6 +17,7 @@
  * License along with this library; if not, see <http://www.gnu.org/licenses/>.
  */
 #include "qemu/osdep.h"
+#include "qemu/units.h"
 #include "qemu/log.h"
 #include "qemu/main-loop.h"
 #include "cpu.h"
@@ -1316,3 +1317,95 @@ uint32_t HELPER(ror_cc)(CPUARMState *env, uint32_t x, uint32_t i)
         return ((uint32_t)x >> shift) | (x << (32 - shift));
     }
 }
+
+void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in)
+{
+    /*
+     * Implement DC ZVA, which zeroes a fixed-length block of memory.
+     * Note that we do not implement the (architecturally mandated)
+     * alignment fault for attempts to use this on Device memory
+     * (which matches the usual QEMU behaviour of not implementing either
+     * alignment faults or any memory attribute handling).
+     */
+
+    ARMCPU *cpu = env_archcpu(env);
+    uint64_t blocklen = 4 << cpu->dcz_blocksize;
+    uint64_t vaddr = vaddr_in & ~(blocklen - 1);
+
+#ifndef CONFIG_USER_ONLY
+    {
+        /*
+         * Slightly awkwardly, QEMU's TARGET_PAGE_SIZE may be less than
+         * the block size so we might have to do more than one TLB lookup.
+         * We know that in fact for any v8 CPU the page size is at least 4K
+         * and the block size must be 2K or less, but TARGET_PAGE_SIZE is only
+         * 1K as an artefact of legacy v5 subpage support being present in the
+         * same QEMU executable. So in practice the hostaddr[] array has
+         * two entries, given the current setting of TARGET_PAGE_BITS_MIN.
+         */
+        int maxidx = DIV_ROUND_UP(blocklen, TARGET_PAGE_SIZE);
+        void *hostaddr[DIV_ROUND_UP(2 * KiB, 1 << TARGET_PAGE_BITS_MIN)];
+        int try, i;
+        unsigned mmu_idx = cpu_mmu_index(env, false);
+        TCGMemOpIdx oi = make_memop_idx(MO_UB, mmu_idx);
+
+        assert(maxidx <= ARRAY_SIZE(hostaddr));
+
+        for (try = 0; try < 2; try++) {
+
+            for (i = 0; i < maxidx; i++) {
+                hostaddr[i] = tlb_vaddr_to_host(env,
+                                                vaddr + TARGET_PAGE_SIZE * i,
+                                                1, mmu_idx);
+                if (!hostaddr[i]) {
+                    break;
+                }
+            }
+            if (i == maxidx) {
+                /*
+                 * If it's all in the TLB it's fair game for just writing to;
+                 * we know we don't need to update dirty status, etc.
+                 */
+                for (i = 0; i < maxidx - 1; i++) {
+                    memset(hostaddr[i], 0, TARGET_PAGE_SIZE);
+                }
+                memset(hostaddr[i], 0, blocklen - (i * TARGET_PAGE_SIZE));
+                return;
+            }
+            /*
+             * OK, try a store and see if we can populate the tlb. This
+             * might cause an exception if the memory isn't writable,
+             * in which case we will longjmp out of here. We must for
+             * this purpose use the actual register value passed to us
+             * so that we get the fault address right.
+             */
+            helper_ret_stb_mmu(env, vaddr_in, 0, oi, GETPC());
+            /* Now we can populate the other TLB entries, if any */
+            for (i = 0; i < maxidx; i++) {
+                uint64_t va = vaddr + TARGET_PAGE_SIZE * i;
+                if (va != (vaddr_in & TARGET_PAGE_MASK)) {
+                    helper_ret_stb_mmu(env, va, 0, oi, GETPC());
+                }
+            }
+        }
+
+        /*
+         * Slow path (probably attempt to do this to an I/O device or
+         * similar, or clearing of a block of code we have translations
+         * cached for). Just do a series of byte writes as the architecture
+         * demands. It's not worth trying to use a cpu_physical_memory_map(),
+         * memset(), unmap() sequence here because:
+         *  + we'd need to account for the blocksize being larger than a page
+         *  + the direct-RAM access case is almost always going to be dealt
+         *    with in the fastpath code above, so there's no speed benefit
+         *  + we would have to deal with the map returning NULL because the
+         *    bounce buffer was in use
+         */
+        for (i = 0; i < blocklen; i++) {
+            helper_ret_stb_mmu(env, vaddr + i, 0, oi, GETPC());
+        }
+    }
+#else
+    memset(g2h(vaddr), 0, blocklen);
+#endif
+}
-- 
2.20.1