Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20210308' into staging

target-arm queue:
 * sbsa-ref: remove cortex-a53 from list of supported cpus
 * sbsa-ref: add 'max' to list of allowed cpus
 * target/arm: Add support for FEAT_SSBS, Speculative Store Bypass Safe
 * npcm7xx: add EMC model
 * xlnx-zynqmp: Remove obsolete 'has_rpu' property
 * target/arm: Speed up aarch64 TBL/TBX
 * virtio-mmio: improve virtio-mmio get_dev_path alog
 * target/arm: Use TCF0 and TFSRE0 for unprivileged tag checks
 * target/arm: Restrict v8M IDAU to TCG
 * target/arm/cpu: Update coding style to make checkpatch.pl happy
 * musicpal, tc6393xb, omap_lcdc, tcx: drop dead code for non-32-bit-RGB surfaces
 * Add new board: mps3-an524

# gpg: Signature made Mon 08 Mar 2021 11:56:24 GMT
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [ultimate]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20210308: (49 commits)
  hw/arm/mps2: Update old infocenter.arm.com URLs
  docs/system/arm/mps2.rst: Document the new mps3-an524 board
  hw/arm/mps2-tz: Provide PL031 RTC on mps3-an524
  hw/arm/mps2-tz: Stub out USB controller for mps3-an524
  hw/arm/mps2-tz: Add new mps3-an524 board
  hw/arm/mps2-tz: Get armv7m_load_kernel() size argument from RAMInfo
  hw/arm/mps2-tz: Support ROMs as well as RAMs
  hw/arm/mps2-tz: Set MachineClass default_ram info from RAMInfo data
  hw/arm/mps2-tz: Make RAM arrangement board-specific
  hw/arm/mps2-tz: Allow boards to have different PPCInfo data
  hw/arm/mps2-tz: Size the uart-irq-orgate based on the number of UARTs
  hw/arm/mps2-tz: Move device IRQ info to data structures
  hw/arm/mps2-tz: Allow PPCPortInfo structures to specify device interrupts
  hw/arm/mps2-tz: Correct wrong interrupt numbers for DMA and SPI
  hw/misc/mps2-scc: Implement CFG_REG5 and CFG_REG6 for MPS3 AN524
  hw/arm/mps2-tz: Make number of IRQs board-specific
  hw/arm/mps2-tz: Condition IRQ splitting on number of CPUs, not board type
  hw/arm/mps2-tz: Make FPGAIO switch and LED config per-board
  hw/misc/mps2-fpgaio: Support SWITCH register
  hw/misc/mps2-fpgaio: Make number of LEDs configurable by board
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 48 insertions, 0 deletions

diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 7174030377..3fbeae87cb 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -1937,3 +1937,51 @@ DO_VRINT_RMODE(gvec_vrint_rm_h, helper_rinth, uint16_t)
 DO_VRINT_RMODE(gvec_vrint_rm_s, helper_rints, uint32_t)
 
 #undef DO_VRINT_RMODE
+
+#ifdef TARGET_AARCH64
+void HELPER(simd_tblx)(void *vd, void *vm, void *venv, uint32_t desc)
+{
+    const uint8_t *indices = vm;
+    CPUARMState *env = venv;
+    size_t oprsz = simd_oprsz(desc);
+    uint32_t rn = extract32(desc, SIMD_DATA_SHIFT, 5);
+    bool is_tbx = extract32(desc, SIMD_DATA_SHIFT + 5, 1);
+    uint32_t table_len = desc >> (SIMD_DATA_SHIFT + 6);
+    union {
+        uint8_t b[16];
+        uint64_t d[2];
+    } result;
+
+    /*
+     * We must construct the final result in a temp, lest the output
+     * overlaps the input table.  For TBL, begin with zero; for TBX,
+     * begin with the original register contents.  Note that we always
+     * copy 16 bytes here to avoid an extra branch; clearing the high
+     * bits of the register for oprsz == 8 is handled below.
+     */
+    if (is_tbx) {
+        memcpy(&result, vd, 16);
+    } else {
+        memset(&result, 0, 16);
+    }
+
+    for (size_t i = 0; i < oprsz; ++i) {
+        uint32_t index = indices[H1(i)];
+
+        if (index < table_len) {
+            /*
+             * Convert index (a byte offset into the virtual table
+             * which is a series of 128-bit vectors concatenated)
+             * into the correct register element, bearing in mind
+             * that the table can wrap around from V31 to V0.
+             */
+            const uint8_t *table = (const uint8_t *)
+                aa64_vfp_qreg(env, (rn + (index >> 4)) % 32);
+            result.b[H1(i)] = table[H1(index % 16)];
+        }
+    }
+
+    memcpy(vd, &result, 16);
+    clear_tail(vd, oprsz, simd_maxsz(desc));
+}
+#endif