Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - kdump support, including two necessary memblock additions:
   memblock_clear_nomap() and memblock_cap_memory_range()

 - ARMv8.3 HWCAP bits for JavaScript conversion instructions, complex
   numbers and weaker release consistency

 - arm64 ACPI platform MSI support

 - arm perf updates: ACPI PMU support, L3 cache PMU in some Qualcomm
   SoCs, Cortex-A53 L2 cache events and DTLB refills, MAINTAINERS update
   for DT perf bindings

 - architected timer errata framework (the arch/arm64 changes only)

 - support for DMA_ATTR_FORCE_CONTIGUOUS in the arm64 iommu DMA API

 - arm64 KVM refactoring to use common system register definitions

 - remove support for ASID-tagged VIVT I-cache (no ARMv8 implementation
   using it and deprecated in the architecture) together with some
   I-cache handling clean-up

 - PE/COFF EFI header clean-up/hardening

 - define BUG() instruction without CONFIG_BUG

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (92 commits)
  arm64: Fix the DMA mmap and get_sgtable API with DMA_ATTR_FORCE_CONTIGUOUS
  arm64: Print DT machine model in setup_machine_fdt()
  arm64: pmu: Wire-up Cortex A53 L2 cache events and DTLB refills
  arm64: module: split core and init PLT sections
  arm64: pmuv3: handle pmuv3+
  arm64: Add CNTFRQ_EL0 trap handler
  arm64: Silence spurious kbuild warning on menuconfig
  arm64: pmuv3: use arm_pmu ACPI framework
  arm64: pmuv3: handle !PMUv3 when probing
  drivers/perf: arm_pmu: add ACPI framework
  arm64: add function to get a cpu's MADT GICC table
  drivers/perf: arm_pmu: split out platform device probe logic
  drivers/perf: arm_pmu: move irq request/free into probe
  drivers/perf: arm_pmu: split cpu-local irq request/free
  drivers/perf: arm_pmu: rename irq request/free functions
  drivers/perf: arm_pmu: handle no platform_device
  drivers/perf: arm_pmu: simplify cpu_pmu_request_irqs()
  drivers/perf: arm_pmu: factor out pmu registration
  drivers/perf: arm_pmu: fold init into alloc
  drivers/perf: arm_pmu: define armpmu_init_fn
  ...

1 files changed, 63 insertions, 45 deletions

diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index 1ce90d8450ae..d05dbe658409 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2014-2016 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2014-2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -26,35 +26,21 @@ struct plt_entry {
 	__le32	br;	/* br	x16				*/
 };
 
-u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela,
+static bool in_init(const struct module *mod, void *loc)
+{
+	return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size;
+}
+
+u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
 			  Elf64_Sym *sym)
 {
-	struct plt_entry *plt = (struct plt_entry *)mod->arch.plt->sh_addr;
-	int i = mod->arch.plt_num_entries;
+	struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
+							  &mod->arch.init;
+	struct plt_entry *plt = (struct plt_entry *)pltsec->plt->sh_addr;
+	int i = pltsec->plt_num_entries;
 	u64 val = sym->st_value + rela->r_addend;
 
 	/*
-	 * We only emit PLT entries against undefined (SHN_UNDEF) symbols,
-	 * which are listed in the ELF symtab section, but without a type
-	 * or a size.
-	 * So, similar to how the module loader uses the Elf64_Sym::st_value
-	 * field to store the resolved addresses of undefined symbols, let's
-	 * borrow the Elf64_Sym::st_size field (whose value is never used by
-	 * the module loader, even for symbols that are defined) to record
-	 * the address of a symbol's associated PLT entry as we emit it for a
-	 * zero addend relocation (which is the only kind we have to deal with
-	 * in practice). This allows us to find duplicates without having to
-	 * go through the table every time.
-	 */
-	if (rela->r_addend == 0 && sym->st_size != 0) {
-		BUG_ON(sym->st_size < (u64)plt || sym->st_size >= (u64)&plt[i]);
-		return sym->st_size;
-	}
-
-	mod->arch.plt_num_entries++;
-	BUG_ON(mod->arch.plt_num_entries > mod->arch.plt_max_entries);
-
-	/*
 	 * MOVK/MOVN/MOVZ opcode:
 	 * +--------+------------+--------+-----------+-------------+---------+
 	 * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
@@ -72,8 +58,19 @@ u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela,
 		cpu_to_le32(0xd61f0200)
 	};
 
-	if (rela->r_addend == 0)
-		sym->st_size = (u64)&plt[i];
+	/*
+	 * Check if the entry we just created is a duplicate. Given that the
+	 * relocations are sorted, this will be the last entry we allocated.
+	 * (if one exists).
+	 */
+	if (i > 0 &&
+	    plt[i].mov0 == plt[i - 1].mov0 &&
+	    plt[i].mov1 == plt[i - 1].mov1 &&
+	    plt[i].mov2 == plt[i - 1].mov2)
+		return (u64)&plt[i - 1];
+
+	pltsec->plt_num_entries++;
+	BUG_ON(pltsec->plt_num_entries > pltsec->plt_max_entries);
 
 	return (u64)&plt[i];
 }
@@ -104,7 +101,8 @@ static bool duplicate_rel(const Elf64_Rela *rela, int num)
 	return num > 0 && cmp_rela(rela + num, rela + num - 1) == 0;
 }
 
-static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num)
+static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num,
+			       Elf64_Word dstidx)
 {
 	unsigned int ret = 0;
 	Elf64_Sym *s;
@@ -116,13 +114,17 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num)
 		case R_AARCH64_CALL26:
 			/*
 			 * We only have to consider branch targets that resolve
-			 * to undefined symbols. This is not simply a heuristic,
-			 * it is a fundamental limitation, since the PLT itself
-			 * is part of the module, and needs to be within 128 MB
-			 * as well, so modules can never grow beyond that limit.
+			 * to symbols that are defined in a different section.
+			 * This is not simply a heuristic, it is a fundamental
+			 * limitation, since there is no guaranteed way to emit
+			 * PLT entries sufficiently close to the branch if the
+			 * section size exceeds the range of a branch
+			 * instruction. So ignore relocations against defined
+			 * symbols if they live in the same section as the
+			 * relocation target.
 			 */
 			s = syms + ELF64_R_SYM(rela[i].r_info);
-			if (s->st_shndx != SHN_UNDEF)
+			if (s->st_shndx == dstidx)
 				break;
 
 			/*
@@ -149,7 +151,8 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num)
 int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			      char *secstrings, struct module *mod)
 {
-	unsigned long plt_max_entries = 0;
+	unsigned long core_plts = 0;
+	unsigned long init_plts = 0;
 	Elf64_Sym *syms = NULL;
 	int i;
 
@@ -158,14 +161,16 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	 * entries. Record the symtab address as well.
 	 */
 	for (i = 0; i < ehdr->e_shnum; i++) {
-		if (strcmp(".plt", secstrings + sechdrs[i].sh_name) == 0)
-			mod->arch.plt = sechdrs + i;
+		if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
+			mod->arch.core.plt = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
+			mod->arch.init.plt = sechdrs + i;
 		else if (sechdrs[i].sh_type == SHT_SYMTAB)
 			syms = (Elf64_Sym *)sechdrs[i].sh_addr;
 	}
 
-	if (!mod->arch.plt) {
-		pr_err("%s: module PLT section missing\n", mod->name);
+	if (!mod->arch.core.plt || !mod->arch.init.plt) {
+		pr_err("%s: module PLT section(s) missing\n", mod->name);
 		return -ENOEXEC;
 	}
 	if (!syms) {
@@ -188,14 +193,27 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		/* sort by type, symbol index and addend */
 		sort(rels, numrels, sizeof(Elf64_Rela), cmp_rela, NULL);
 
-		plt_max_entries += count_plts(syms, rels, numrels);
+		if (strncmp(secstrings + dstsec->sh_name, ".init", 5) != 0)
+			core_plts += count_plts(syms, rels, numrels,
+						sechdrs[i].sh_info);
+		else
+			init_plts += count_plts(syms, rels, numrels,
+						sechdrs[i].sh_info);
 	}
 
-	mod->arch.plt->sh_type = SHT_NOBITS;
-	mod->arch.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
-	mod->arch.plt->sh_addralign = L1_CACHE_BYTES;
-	mod->arch.plt->sh_size = plt_max_entries * sizeof(struct plt_entry);
-	mod->arch.plt_num_entries = 0;
-	mod->arch.plt_max_entries = plt_max_entries;
+	mod->arch.core.plt->sh_type = SHT_NOBITS;
+	mod->arch.core.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.core.plt->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.core.plt->sh_size = (core_plts  + 1) * sizeof(struct plt_entry);
+	mod->arch.core.plt_num_entries = 0;
+	mod->arch.core.plt_max_entries = core_plts;
+
+	mod->arch.init.plt->sh_type = SHT_NOBITS;
+	mod->arch.init.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.init.plt->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.init.plt->sh_size = (init_plts + 1) * sizeof(struct plt_entry);
+	mod->arch.init.plt_num_entries = 0;
+	mod->arch.init.plt_max_entries = init_plts;
+
 	return 0;
 }