arm64: patching: implement text_poke API

The text_poke API is used to implement functions like memcpy() and
memset() for instruction memory (RO+X). The implementation is similar to
the x86 version.

This will be used by the BPF JIT to write and modify BPF programs. There
could be more users of this in the future.

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20240228141824.119877-2-puranjay12@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: puranjaymohan

arch/arm64/include/asm/patching.h

@@ -8,6 +8,8 @@ int aarch64_insn_read(void *addr, u32 *insnp);
 int aarch64_insn_write(void *addr, u32 insn);
 
 int aarch64_insn_write_literal_u64(void *addr, u64 val);
+void *aarch64_insn_set(void *dst, u32 insn, size_t len);
+void *aarch64_insn_copy(void *dst, void *src, size_t len);
 
 int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);

arch/arm64/kernel/patching.c

@@ -105,6 +105,81 @@ noinstr int aarch64_insn_write_literal_u64(void *addr, u64 val)
 	return ret;
 }
 
+typedef void text_poke_f(void *dst, void *src, size_t patched, size_t len);
+
+static void *__text_poke(text_poke_f func, void *addr, void *src, size_t len)
+{
+	unsigned long flags;
+	size_t patched = 0;
+	size_t size;
+	void *waddr;
+	void *ptr;
+
+	raw_spin_lock_irqsave(&patch_lock, flags);
+
+	while (patched < len) {
+		ptr = addr + patched;
+		size = min_t(size_t, PAGE_SIZE - offset_in_page(ptr),
+			     len - patched);
+
+		waddr = patch_map(ptr, FIX_TEXT_POKE0);
+		func(waddr, src, patched, size);
+		patch_unmap(FIX_TEXT_POKE0);
+
+		patched += size;
+	}
+	raw_spin_unlock_irqrestore(&patch_lock, flags);
+
+	flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len);
+
+	return addr;
+}
+
+static void text_poke_memcpy(void *dst, void *src, size_t patched, size_t len)
+{
+	copy_to_kernel_nofault(dst, src + patched, len);
+}
+
+static void text_poke_memset(void *dst, void *src, size_t patched, size_t len)
+{
+	u32 c = *(u32 *)src;
+
+	memset32(dst, c, len / 4);
+}
+
+/**
+ * aarch64_insn_copy - Copy instructions into (an unused part of) RX memory
+ * @dst: address to modify
+ * @src: source of the copy
+ * @len: length to copy
+ *
+ * Useful for JITs to dump new code blocks into unused regions of RX memory.
+ */
+noinstr void *aarch64_insn_copy(void *dst, void *src, size_t len)
+{
+	/* A64 instructions must be word aligned */
+	if ((uintptr_t)dst & 0x3)
+		return NULL;
+
+	return __text_poke(text_poke_memcpy, dst, src, len);
+}
+
+/**
+ * aarch64_insn_set - memset for RX memory regions.
+ * @dst: address to modify
+ * @insn: value to set
+ * @len: length of memory region.
+ *
+ * Useful for JITs to fill regions of RX memory with illegal instructions.
+ */
+noinstr void *aarch64_insn_set(void *dst, u32 insn, size_t len)
+{
+	if ((uintptr_t)dst & 0x3)
+		return NULL;
+
+	return __text_poke(text_poke_memset, dst, &insn, len);
+}
+
 int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
 {
 	u32 *tp = addr;