remoteproc: imx_dsp_rproc: Add custom memory copy implementation for i.MX DSP Cores

The IRAM is part of the HiFi DSP.
According to hardware specification only 32-bits write are allowed
otherwise we get a Kernel panic.

Therefore add a custom memory copy and memset functions to deal with
the above restriction.

Signed-off-by: Iuliana Prodan <iuliana.prodan@nxp.com>
Link: https://lore.kernel.org/r/20230221170356.27923-1-iuliana.prodan@oss.nxp.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>

Author: iuliana-prodan

drivers/remoteproc/imx_dsp_rproc.c

@@ -738,6 +738,191 @@ static void imx_dsp_rproc_kick(struct rproc *rproc, int vqid)
 		dev_err(dev, "%s: failed (%d, err:%d)\n", __func__, vqid, err);
 }
 
+/*
+ * Custom memory copy implementation for i.MX DSP Cores
+ *
+ * The IRAM is part of the HiFi DSP.
+ * According to hw specs only 32-bits writes are allowed.
+ */
+static int imx_dsp_rproc_memcpy(void *dest, const void *src, size_t size)
+{
+	const u8 *src_byte = src;
+	const u32 *source = src;
+	u32 affected_mask;
+	u32 *dst = dest;
+	int i, q, r;
+	u32 tmp;
+
+	/* destination must be 32bit aligned */
+	if (!IS_ALIGNED((uintptr_t)dest, 4))
+		return -EINVAL;
+
+	q = size / 4;
+	r = size % 4;
+
+	/* copy data in units of 32 bits at a time */
+	for (i = 0; i < q; i++)
+		writel(source[i], &dst[i]);
+
+	if (r) {
+		affected_mask = GENMASK(8 * r, 0);
+
+		/*
+		 * first read the 32bit data of dest, then change affected
+		 * bytes, and write back to dest.
+		 * For unaffected bytes, it should not be changed
+		 */
+		tmp = readl(dest + q * 4);
+		tmp &= ~affected_mask;
+
+		/* avoid reading after end of source */
+		for (i = 0; i < r; i++)
+			tmp |= (src_byte[q * 4 + i] << (8 * i));
+
+		writel(tmp, dest + q * 4);
+	}
+
+	return 0;
+}
+
+/*
+ * Custom memset implementation for i.MX DSP Cores
+ *
+ * The IRAM is part of the HiFi DSP.
+ * According to hw specs only 32-bits writes are allowed.
+ */
+static int imx_dsp_rproc_memset(void *addr, u8 value, size_t size)
+{
+	u32 tmp_val = value;
+	u32 *tmp_dst = addr;
+	u32 affected_mask;
+	int q, r;
+	u32 tmp;
+
+	/* destination must be 32bit aligned */
+	if (!IS_ALIGNED((uintptr_t)addr, 4))
+		return -EINVAL;
+
+	tmp_val |= tmp_val << 8;
+	tmp_val |= tmp_val << 16;
+
+	q = size / 4;
+	r = size % 4;
+
+	while (q--)
+		writel(tmp_val, tmp_dst++);
+
+	if (r) {
+		affected_mask = GENMASK(8 * r, 0);
+
+		/*
+		 * first read the 32bit data of addr, then change affected
+		 * bytes, and write back to addr.
+		 * For unaffected bytes, it should not be changed
+		 */
+		tmp = readl(tmp_dst);
+		tmp &= ~affected_mask;
+
+		tmp |= (tmp_val & affected_mask);
+		writel(tmp, tmp_dst);
+	}
+
+	return 0;
+}
+
+/*
+ * imx_dsp_rproc_elf_load_segments() - load firmware segments to memory
+ * @rproc: remote processor which will be booted using these fw segments
+ * @fw: the ELF firmware image
+ *
+ * This function loads the firmware segments to memory, where the remote
+ * processor expects them.
+ *
+ * Return: 0 on success and an appropriate error code otherwise
+ */
+static int imx_dsp_rproc_elf_load_segments(struct rproc *rproc, const struct firmware *fw)
+{
+	struct device *dev = &rproc->dev;
+	const void *ehdr, *phdr;
+	int i, ret = 0;
+	u16 phnum;
+	const u8 *elf_data = fw->data;
+	u8 class = fw_elf_get_class(fw);
+	u32 elf_phdr_get_size = elf_size_of_phdr(class);
+
+	ehdr = elf_data;
+	phnum = elf_hdr_get_e_phnum(class, ehdr);
+	phdr = elf_data + elf_hdr_get_e_phoff(class, ehdr);
+
+	/* go through the available ELF segments */
+	for (i = 0; i < phnum; i++, phdr += elf_phdr_get_size) {
+		u64 da = elf_phdr_get_p_paddr(class, phdr);
+		u64 memsz = elf_phdr_get_p_memsz(class, phdr);
+		u64 filesz = elf_phdr_get_p_filesz(class, phdr);
+		u64 offset = elf_phdr_get_p_offset(class, phdr);
+		u32 type = elf_phdr_get_p_type(class, phdr);
+		void *ptr;
+
+		if (type != PT_LOAD || !memsz)
+			continue;
+
+		dev_dbg(dev, "phdr: type %d da 0x%llx memsz 0x%llx filesz 0x%llx\n",
+			type, da, memsz, filesz);
+
+		if (filesz > memsz) {
+			dev_err(dev, "bad phdr filesz 0x%llx memsz 0x%llx\n",
+				filesz, memsz);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (offset + filesz > fw->size) {
+			dev_err(dev, "truncated fw: need 0x%llx avail 0x%zx\n",
+				offset + filesz, fw->size);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (!rproc_u64_fit_in_size_t(memsz)) {
+			dev_err(dev, "size (%llx) does not fit in size_t type\n",
+				memsz);
+			ret = -EOVERFLOW;
+			break;
+		}
+
+		/* grab the kernel address for this device address */
+		ptr = rproc_da_to_va(rproc, da, memsz, NULL);
+		if (!ptr) {
+			dev_err(dev, "bad phdr da 0x%llx mem 0x%llx\n", da,
+				memsz);
+			ret = -EINVAL;
+			break;
+		}
+
+		/* put the segment where the remote processor expects it */
+		if (filesz) {
+			ret = imx_dsp_rproc_memcpy(ptr, elf_data + offset, filesz);
+			if (ret) {
+				dev_err(dev, "memory copy failed for da 0x%llx memsz 0x%llx\n",
+					da, memsz);
+				break;
+			}
+		}
+
+		/* zero out remaining memory for this segment */
+		if (memsz > filesz) {
+			ret = imx_dsp_rproc_memset(ptr + filesz, 0, memsz - filesz);
+			if (ret) {
+				dev_err(dev, "memset failed for da 0x%llx memsz 0x%llx\n",
+					da, memsz);
+				break;
+			}
+		}
+	}
+
+	return ret;
+}
+
 static int imx_dsp_rproc_parse_fw(struct rproc *rproc, const struct firmware *fw)
 {
 	if (rproc_elf_load_rsc_table(rproc, fw))
@@ -752,7 +937,7 @@ static const struct rproc_ops imx_dsp_rproc_ops = {
 	.start		= imx_dsp_rproc_start,
 	.stop		= imx_dsp_rproc_stop,
 	.kick		= imx_dsp_rproc_kick,
-	.load		= rproc_elf_load_segments,
+	.load		= imx_dsp_rproc_elf_load_segments,
 	.parse_fw	= imx_dsp_rproc_parse_fw,
 	.sanity_check	= rproc_elf_sanity_check,
 	.get_boot_addr	= rproc_elf_get_boot_addr,