3 files changed, 107 insertions, 139 deletions
diff --git a/arch/x86/tools/cpufeaturemasks.awk b/arch/x86/tools/cpufeaturemasks.awk
new file mode 100755
index 000000000000..173d5bf2d999
--- /dev/null
+++ b/arch/x86/tools/cpufeaturemasks.awk
@@ -0,0 +1,88 @@
+#!/usr/bin/awk
+#
+# Convert cpufeatures.h to a list of compile-time masks
+# Note: this blithely assumes that each word has at least one
+# feature defined in it; if not, something else is wrong!
+#
+
+BEGIN {
+	printf "#ifndef _ASM_X86_CPUFEATUREMASKS_H\n";
+	printf "#define _ASM_X86_CPUFEATUREMASKS_H\n\n";
+
+	file = 0
+}
+
+FNR == 1 {
+	++file;
+
+	# arch/x86/include/asm/cpufeatures.h
+	if (file == 1)
+		FS = "[ \t()*+]+";
+
+	# .config
+	if (file == 2)
+		FS = "=";
+}
+
+# Create a dictionary of sorts, containing all defined feature bits
+file == 1 && $1 ~ /^#define$/ && $2 ~ /^X86_FEATURE_/ {
+	nfeat = $3 * $4 + $5;
+	feat = $2;
+	sub(/^X86_FEATURE_/, "", feat);
+	feats[nfeat] = feat;
+}
+file == 1 && $1 ~ /^#define$/ && $2 == "NCAPINTS" {
+	ncapints = int($3);
+}
+
+# Create a dictionary featstat[REQUIRED|DISABLED, FEATURE_NAME] = on | off
+file == 2 && $1 ~ /^CONFIG_X86_(REQUIRED|DISABLED)_FEATURE_/ {
+	on = ($2 == "y");
+	if (split($1, fs, "CONFIG_X86_|_FEATURE_") == 3)
+		featstat[fs[2], fs[3]] = on;
+}
+
+END {
+	sets[1] = "REQUIRED";
+	sets[2] = "DISABLED";
+
+	for (ns in sets) {
+		s = sets[ns];
+
+		printf "/*\n";
+		printf " * %s features:\n", s;
+		printf " *\n";
+		fstr = "";
+		for (i = 0; i < ncapints; i++) {
+			mask = 0;
+			for (j = 0; j < 32; j++) {
+				feat = feats[i*32 + j];
+				if (featstat[s, feat]) {
+					nfstr = fstr " " feat;
+					if (length(nfstr) > 72) {
+						printf " *   %s\n", fstr;
+						nfstr = " " feat;
+					}
+					fstr = nfstr;
+					mask += (2 ^ j);
+				}
+			}
+			masks[i] = mask;
+		}
+		printf " *   %s\n */\n", fstr;
+
+		for (i = 0; i < ncapints; i++)
+			printf "#define %s_MASK%d\t0x%08xU\n", s, i, masks[i];
+
+		printf "\n#define %s_MASK_BIT_SET(x)\t\t\t\\\n", s;
+		printf "\t((\t\t\t\t\t";
+		for (i = 0; i < ncapints; i++) {
+			if (masks[i])
+				printf "\t\\\n\t\t((x) >> 5) == %2d ? %s_MASK%d :", i, s, i;
+		}
+		printf " 0\t\\\n";
+		printf "\t) & (1U << ((x) & 31)))\n\n";
+	}
+
+	printf "#endif /* _ASM_X86_CPUFEATUREMASKS_H */\n";
+}
diff --git a/arch/x86/tools/insn_decoder_test.c b/arch/x86/tools/insn_decoder_test.c
index 472540aeabc2..6c2986d2ad11 100644
--- a/arch/x86/tools/insn_decoder_test.c
+++ b/arch/x86/tools/insn_decoder_test.c
@@ -10,6 +10,7 @@
 #include <assert.h>
 #include <unistd.h>
 #include <stdarg.h>
+#include <linux/kallsyms.h>
 
 #define unlikely(cond) (cond)
 
@@ -106,7 +107,7 @@ static void parse_args(int argc, char **argv)
 	}
 }
 
-#define BUFSIZE 256
+#define BUFSIZE (256 + KSYM_NAME_LEN)
 
 int main(int argc, char **argv)
 {
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 27441e5863b2..5778bc498415 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -29,9 +29,13 @@ static struct relocs		relocs16;
 static struct relocs		relocs32;
 
 #if ELF_BITS == 64
-static struct relocs		relocs32neg;
 static struct relocs		relocs64;
 # define FMT PRIu64
+
+#ifndef R_X86_64_REX_GOTPCRELX
+# define R_X86_64_REX_GOTPCRELX 42
+#endif
+
 #else
 # define FMT PRIu32
 #endif
@@ -86,8 +90,6 @@ static const char * const	sym_regex_kernel[S_NSYMTYPES] = {
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
-	"__per_cpu_load|"
-	"init_per_cpu__.*|"
 	"__end_rodata_hpage_align|"
 #endif
 	"_end)$"
@@ -227,6 +229,7 @@ static const char *rel_type(unsigned type)
 		REL_TYPE(R_X86_64_PC16),
 		REL_TYPE(R_X86_64_8),
 		REL_TYPE(R_X86_64_PC8),
+		REL_TYPE(R_X86_64_REX_GOTPCRELX),
 #else
 		REL_TYPE(R_386_NONE),
 		REL_TYPE(R_386_32),
@@ -284,34 +287,6 @@ static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
 	return name;
 }
 
-static Elf_Sym *sym_lookup(const char *symname)
-{
-	int i;
-
-	for (i = 0; i < shnum; i++) {
-		struct section *sec = &secs[i];
-		long nsyms;
-		char *strtab;
-		Elf_Sym *symtab;
-		Elf_Sym *sym;
-
-		if (sec->shdr.sh_type != SHT_SYMTAB)
-			continue;
-
-		nsyms = sec->shdr.sh_size/sizeof(Elf_Sym);
-		symtab = sec->symtab;
-		strtab = sec->link->strtab;
-
-		for (sym = symtab; --nsyms >= 0; sym++) {
-			if (!sym->st_name)
-				continue;
-			if (strcmp(symname, strtab + sym->st_name) == 0)
-				return sym;
-		}
-	}
-	return 0;
-}
-
 #if BYTE_ORDER == LITTLE_ENDIAN
 # define le16_to_cpu(val)	(val)
 # define le32_to_cpu(val)	(val)
@@ -760,100 +735,18 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 	}
 }
 
-/*
- * The .data..percpu section is a special case for x86_64 SMP kernels.
- * It is used to initialize the actual per_cpu areas and to provide
- * definitions for the per_cpu variables that correspond to their offsets
- * within the percpu area. Since the values of all of the symbols need
- * to be offsets from the start of the per_cpu area the virtual address
- * (sh_addr) of .data..percpu is 0 in SMP kernels.
- *
- * This means that:
- *
- *	Relocations that reference symbols in the per_cpu area do not
- *	need further relocation (since the value is an offset relative
- *	to the start of the per_cpu area that does not change).
- *
- *	Relocations that apply to the per_cpu area need to have their
- *	offset adjusted by by the value of __per_cpu_load to make them
- *	point to the correct place in the loaded image (because the
- *	virtual address of .data..percpu is 0).
- *
- * For non SMP kernels .data..percpu is linked as part of the normal
- * kernel data and does not require special treatment.
- *
- */
-static int per_cpu_shndx = -1;
-static Elf_Addr per_cpu_load_addr;
-
-static void percpu_init(void)
-{
-	int i;
-
-	for (i = 0; i < shnum; i++) {
-		ElfW(Sym) *sym;
-
-		if (strcmp(sec_name(i), ".data..percpu"))
-			continue;
-
-		if (secs[i].shdr.sh_addr != 0)	/* non SMP kernel */
-			return;
-
-		sym = sym_lookup("__per_cpu_load");
-		if (!sym)
-			die("can't find __per_cpu_load\n");
-
-		per_cpu_shndx = i;
-		per_cpu_load_addr = sym->st_value;
-
-		return;
-	}
-}
-
 #if ELF_BITS == 64
 
-/*
- * Check to see if a symbol lies in the .data..percpu section.
- *
- * The linker incorrectly associates some symbols with the
- * .data..percpu section so we also need to check the symbol
- * name to make sure that we classify the symbol correctly.
- *
- * The GNU linker incorrectly associates:
- *	__init_begin
- *	__per_cpu_load
- *
- * The "gold" linker incorrectly associates:
- *	init_per_cpu__fixed_percpu_data
- *	init_per_cpu__gdt_page
- */
-static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
-{
-	int shndx = sym_index(sym);
-
-	return (shndx == per_cpu_shndx) &&
-		strcmp(symname, "__init_begin") &&
-		strcmp(symname, "__per_cpu_load") &&
-		strncmp(symname, "init_per_cpu_", 13);
-}
-
-
 static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 		      const char *symname)
 {
+	int headtext = !strcmp(sec_name(sec->shdr.sh_info), ".head.text");
 	unsigned r_type = ELF64_R_TYPE(rel->r_info);
 	ElfW(Addr) offset = rel->r_offset;
 	int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname);
-
 	if (sym->st_shndx == SHN_UNDEF)
 		return 0;
 
-	/*
-	 * Adjust the offset if this reloc applies to the percpu section.
-	 */
-	if (sec->shdr.sh_info == per_cpu_shndx)
-		offset += per_cpu_load_addr;
-
 	switch (r_type) {
 	case R_X86_64_NONE:
 		/* NONE can be ignored. */
@@ -861,33 +754,23 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 
 	case R_X86_64_PC32:
 	case R_X86_64_PLT32:
+	case R_X86_64_REX_GOTPCRELX:
 		/*
-		 * PC relative relocations don't need to be adjusted unless
-		 * referencing a percpu symbol.
+		 * PC relative relocations don't need to be adjusted.
 		 *
 		 * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32.
 		 */
-		if (is_percpu_sym(sym, symname))
-			add_reloc(&relocs32neg, offset);
 		break;
 
 	case R_X86_64_PC64:
 		/*
 		 * Only used by jump labels
 		 */
-		if (is_percpu_sym(sym, symname))
-			die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n", symname);
 		break;
 
 	case R_X86_64_32:
 	case R_X86_64_32S:
 	case R_X86_64_64:
-		/*
-		 * References to the percpu area don't need to be adjusted.
-		 */
-		if (is_percpu_sym(sym, symname))
-			break;
-
 		if (shn_abs) {
 			/*
 			 * Whitelisted absolute symbols do not require
@@ -900,6 +783,12 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 			break;
 		}
 
+		if (headtext) {
+			die("Absolute reference to symbol '%s' not permitted in .head.text\n",
+			    symname);
+			break;
+		}
+
 		/*
 		 * Relocation offsets for 64 bit kernels are output
 		 * as 32 bits and sign extended back to 64 bits when
@@ -1049,7 +938,8 @@ static int cmp_relocs(const void *va, const void *vb)
 
 static void sort_relocs(struct relocs *r)
 {
-	qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
+	if (r->count)
+		qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
 }
 
 static int write32(uint32_t v, FILE *f)
@@ -1093,7 +983,6 @@ static void emit_relocs(int as_text, int use_real_mode)
 	/* Order the relocations for more efficient processing */
 	sort_relocs(&relocs32);
 #if ELF_BITS == 64
-	sort_relocs(&relocs32neg);
 	sort_relocs(&relocs64);
 #else
 	sort_relocs(&relocs16);
@@ -1125,13 +1014,6 @@ static void emit_relocs(int as_text, int use_real_mode)
 		/* Now print each relocation */
 		for (i = 0; i < relocs64.count; i++)
 			write_reloc(relocs64.offset[i], stdout);
-
-		/* Print a stop */
-		write_reloc(0, stdout);
-
-		/* Now print each inverse 32-bit relocation */
-		for (i = 0; i < relocs32neg.count; i++)
-			write_reloc(relocs32neg.offset[i], stdout);
 #endif
 
 		/* Print a stop */
@@ -1184,9 +1066,6 @@ void process(FILE *fp, int use_real_mode, int as_text,
 	read_symtabs(fp);
 	read_relocs(fp);
 
-	if (ELF_BITS == 64)
-		percpu_init();
-
 	if (show_absolute_syms) {
 		print_absolute_symbols();
 		return;