Merge tag 'riscv-for-linus-4.17-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux

Pull RISC-V updates from Palmer Dabbelt:
 "This contains the new features we'd like to incorporate into the
  RISC-V port for 4.17. We might have a bit more stuff land later in the
  merge window, but I wanted to get this out earlier just so everyone
  can see where we currently stand.

  A short summary of the changes is:

   - We've added support for dynamic ftrace on RISC-V targets.

   - There have been a handful of cleanups to our atomic and locking
     routines. They now more closely match the released RISC-V memory
     model draft.

   - Our module loading support has been cleaned up and is now enabled
     by default, despite some limitations still existing.

   - A patch to define COMMANDLINE_FORCE instead of COMMANDLINE_OVERRIDE
     so the generic device tree code picks up handling all our command
     line stuff.

  There's more information in the merge commits for each patch set"

* tag 'riscv-for-linus-4.17-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux: (21 commits)
  RISC-V: Rename CONFIG_CMDLINE_OVERRIDE to CONFIG_CMDLINE_FORCE
  RISC-V: Add definition of relocation types
  RISC-V: Enable module support in defconfig
  RISC-V: Support SUB32 relocation type in kernel module
  RISC-V: Support ADD32 relocation type in kernel module
  RISC-V: Support ALIGN relocation type in kernel module
  RISC-V: Support RVC_BRANCH/JUMP relocation type in kernel modulewq
  RISC-V: Support HI20/LO12_I/LO12_S relocation type in kernel module
  RISC-V: Support CALL relocation type in kernel module
  RISC-V: Support GOT_HI20/CALL_PLT relocation type in kernel module
  RISC-V: Add section of GOT.PLT for kernel module
  RISC-V: Add sections of PLT and GOT for kernel module
  riscv/atomic: Strengthen implementations with fences
  riscv/spinlock: Strengthen implementations with fences
  riscv/barrier: Define __smp_{store_release,load_acquire}
  riscv/ftrace: Add HAVE_FUNCTION_GRAPH_RET_ADDR_PTR support
  riscv/ftrace: Add DYNAMIC_FTRACE_WITH_REGS support
  riscv/ftrace: Add ARCH_SUPPORTS_FTRACE_OPS support
  riscv/ftrace: Add dynamic function graph tracer support
  riscv/ftrace: Add dynamic function tracer support
  ...

1 files changed, 156 insertions, 0 deletions

diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
new file mode 100644
index 0000000..bbbd26e
--- /dev/null
+++ b/arch/riscv/kernel/module-sections.c
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (C) 2014-2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * Copyright (C) 2018 Andes Technology Corporation <zong@andestech.com>
+ */
+
+#include <linux/elf.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+u64 module_emit_got_entry(struct module *mod, u64 val)
+{
+	struct mod_section *got_sec = &mod->arch.got;
+	int i = got_sec->num_entries;
+	struct got_entry *got = get_got_entry(val, got_sec);
+
+	if (got)
+		return (u64)got;
+
+	/* There is no duplicate entry, create a new one */
+	got = (struct got_entry *)got_sec->shdr->sh_addr;
+	got[i] = emit_got_entry(val);
+
+	got_sec->num_entries++;
+	BUG_ON(got_sec->num_entries > got_sec->max_entries);
+
+	return (u64)&got[i];
+}
+
+u64 module_emit_plt_entry(struct module *mod, u64 val)
+{
+	struct mod_section *got_plt_sec = &mod->arch.got_plt;
+	struct got_entry *got_plt;
+	struct mod_section *plt_sec = &mod->arch.plt;
+	struct plt_entry *plt = get_plt_entry(val, plt_sec, got_plt_sec);
+	int i = plt_sec->num_entries;
+
+	if (plt)
+		return (u64)plt;
+
+	/* There is no duplicate entry, create a new one */
+	got_plt = (struct got_entry *)got_plt_sec->shdr->sh_addr;
+	got_plt[i] = emit_got_entry(val);
+	plt = (struct plt_entry *)plt_sec->shdr->sh_addr;
+	plt[i] = emit_plt_entry(val, (u64)&plt[i], (u64)&got_plt[i]);
+
+	plt_sec->num_entries++;
+	got_plt_sec->num_entries++;
+	BUG_ON(plt_sec->num_entries > plt_sec->max_entries);
+
+	return (u64)&plt[i];
+}
+
+static int is_rela_equal(const Elf64_Rela *x, const Elf64_Rela *y)
+{
+	return x->r_info == y->r_info && x->r_addend == y->r_addend;
+}
+
+static bool duplicate_rela(const Elf64_Rela *rela, int idx)
+{
+	int i;
+	for (i = 0; i < idx; i++) {
+		if (is_rela_equal(&rela[i], &rela[idx]))
+			return true;
+	}
+	return false;
+}
+
+static void count_max_entries(Elf64_Rela *relas, int num,
+			      unsigned int *plts, unsigned int *gots)
+{
+	unsigned int type, i;
+
+	for (i = 0; i < num; i++) {
+		type = ELF64_R_TYPE(relas[i].r_info);
+		if (type == R_RISCV_CALL_PLT) {
+			if (!duplicate_rela(relas, i))
+				(*plts)++;
+		} else if (type == R_RISCV_GOT_HI20) {
+			if (!duplicate_rela(relas, i))
+				(*gots)++;
+		}
+	}
+}
+
+int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
+			      char *secstrings, struct module *mod)
+{
+	unsigned int num_plts = 0;
+	unsigned int num_gots = 0;
+	int i;
+
+	/*
+	 * Find the empty .got and .plt sections.
+	 */
+	for (i = 0; i < ehdr->e_shnum; i++) {
+		if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
+			mod->arch.plt.shdr = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".got"))
+			mod->arch.got.shdr = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".got.plt"))
+			mod->arch.got_plt.shdr = sechdrs + i;
+	}
+
+	if (!mod->arch.plt.shdr) {
+		pr_err("%s: module PLT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
+	if (!mod->arch.got.shdr) {
+		pr_err("%s: module GOT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
+	if (!mod->arch.got_plt.shdr) {
+		pr_err("%s: module GOT.PLT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
+
+	/* Calculate the maxinum number of entries */
+	for (i = 0; i < ehdr->e_shnum; i++) {
+		Elf64_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset;
+		int num_rela = sechdrs[i].sh_size / sizeof(Elf64_Rela);
+		Elf64_Shdr *dst_sec = sechdrs + sechdrs[i].sh_info;
+
+		if (sechdrs[i].sh_type != SHT_RELA)
+			continue;
+
+		/* ignore relocations that operate on non-exec sections */
+		if (!(dst_sec->sh_flags & SHF_EXECINSTR))
+			continue;
+
+		count_max_entries(relas, num_rela, &num_plts, &num_gots);
+	}
+
+	mod->arch.plt.shdr->sh_type = SHT_NOBITS;
+	mod->arch.plt.shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.plt.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.plt.shdr->sh_size = (num_plts + 1) * sizeof(struct plt_entry);
+	mod->arch.plt.num_entries = 0;
+	mod->arch.plt.max_entries = num_plts;
+
+	mod->arch.got.shdr->sh_type = SHT_NOBITS;
+	mod->arch.got.shdr->sh_flags = SHF_ALLOC;
+	mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.got.shdr->sh_size = (num_gots + 1) * sizeof(struct got_entry);
+	mod->arch.got.num_entries = 0;
+	mod->arch.got.max_entries = num_gots;
+
+	mod->arch.got_plt.shdr->sh_type = SHT_NOBITS;
+	mod->arch.got_plt.shdr->sh_flags = SHF_ALLOC;
+	mod->arch.got_plt.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.got_plt.shdr->sh_size = (num_plts + 1) * sizeof(struct got_entry);
+	mod->arch.got_plt.num_entries = 0;
+	mod->arch.got_plt.max_entries = num_plts;
+	return 0;
+}