Unverified Commit 9e1664c0 authored by openeuler-ci-bot's avatar openeuler-ci-bot Committed by Gitee
Browse files

!5134 modpost: Optimize symbol search from linear to binary search 

Merge Pull Request from: @ci-robot 
 
PR sync from: Hongchen Zhang <zhanghongchen@loongson.cn>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/TG6RZ33EDNHJYQQUJFDTRJMQYJBFPBJC/ 
 
https://gitee.com/openeuler/kernel/issues/I97HOU 
 
Link:https://gitee.com/openeuler/kernel/pulls/5134

 

Reviewed-by: default avatarXie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: default avatarZheng Zengkai <zhengzengkai@huawei.com>
parents 05cfc0f5 6fdbd9f2

scripts/mod/Makefile

+2 −2
Original line number Diff line number Diff line
@@ -5,7 +5,7 @@ CFLAGS_REMOVE_empty.o += $(CC_FLAGS_LTO) 
hostprogs-always-y	+= modpost mk_elfconfig

always-y		+= empty.o



modpost-objs	:= modpost.o file2alias.o sumversion.o

modpost-objs	:= modpost.o file2alias.o sumversion.o symsearch.o



devicetable-offsets-file := devicetable-offsets.h
@@ -16,7 +16,7 @@ targets += $(devicetable-offsets-file) devicetable-offsets.s 


# dependencies on generated files need to be listed explicitly



$(obj)/modpost.o $(obj)/file2alias.o $(obj)/sumversion.o: $(obj)/elfconfig.h

$(obj)/modpost.o $(obj)/file2alias.o $(obj)/sumversion.o $(obj)/symsearch.o: $(obj)/elfconfig.h

$(obj)/file2alias.o: $(obj)/$(devicetable-offsets-file)



quiet_cmd_elfconfig = MKELF   $@

scripts/mod/modpost.c

+6 −64
Original line number Diff line number Diff line
@@ -22,7 +22,6 @@ 
#include <errno.h>

#include "modpost.h"

#include "../../include/linux/license.h"

#include "../../include/linux/module_symbol.h"



static bool module_enabled;

/* Are we using CONFIG_MODVERSIONS? */
@@ -577,11 +576,14 @@ static int parse_elf(struct elf_info *info, const char *filename) 
			*p = TO_NATIVE(*p);

	}



	symsearch_init(info);



	return 1;

}



static void parse_elf_finish(struct elf_info *info)

{

	symsearch_finish(info);

	release_file(info->hdr, info->size);

}
@@ -1050,71 +1052,10 @@ static int secref_whitelist(const char *fromsec, const char *fromsym, 
	return 1;

}



/*

 * If there's no name there, ignore it; likewise, ignore it if it's

 * one of the magic symbols emitted used by current tools.

 *

 * Otherwise if find_symbols_between() returns those symbols, they'll

 * fail the whitelist tests and cause lots of false alarms ... fixable

 * only by merging __exit and __init sections into __text, bloating

 * the kernel (which is especially evil on embedded platforms).

 */

static inline int is_valid_name(struct elf_info *elf, Elf_Sym *sym)

{

	const char *name = elf->strtab + sym->st_name;



	if (!name || !strlen(name))

		return 0;

	return !is_mapping_symbol(name);

}



/* Look up the nearest symbol based on the section and the address */

static Elf_Sym *find_nearest_sym(struct elf_info *elf, Elf_Addr addr,

				 unsigned int secndx, bool allow_negative,

				 Elf_Addr min_distance)

{

	Elf_Sym *sym;

	Elf_Sym *near = NULL;

	Elf_Addr sym_addr, distance;

	bool is_arm = (elf->hdr->e_machine == EM_ARM);



	for (sym = elf->symtab_start; sym < elf->symtab_stop; sym++) {

		if (get_secindex(elf, sym) != secndx)

			continue;

		if (!is_valid_name(elf, sym))

			continue;



		sym_addr = sym->st_value;



		/*

		 * For ARM Thumb instruction, the bit 0 of st_value is set

		 * if the symbol is STT_FUNC type. Mask it to get the address.

		 */

		if (is_arm && ELF_ST_TYPE(sym->st_info) == STT_FUNC)

			 sym_addr &= ~1;



		if (addr >= sym_addr)

			distance = addr - sym_addr;

		else if (allow_negative)

			distance = sym_addr - addr;

		else

			continue;



		if (distance <= min_distance) {

			min_distance = distance;

			near = sym;

		}



		if (min_distance == 0)

			break;

	}

	return near;

}



static Elf_Sym *find_fromsym(struct elf_info *elf, Elf_Addr addr,

			     unsigned int secndx)

{

	return find_nearest_sym(elf, addr, secndx, false, ~0);

	return symsearch_find_nearest(elf, addr, secndx, false, ~0);

}



static Elf_Sym *find_tosym(struct elf_info *elf, Elf_Addr addr, Elf_Sym *sym)
@@ -1127,7 +1068,8 @@ static Elf_Sym *find_tosym(struct elf_info *elf, Elf_Addr addr, Elf_Sym *sym) 
	 * Strive to find a better symbol name, but the resulting name may not

	 * match the symbol referenced in the original code.

	 */

	return find_nearest_sym(elf, addr, get_secindex(elf, sym), true, 20);

	return symsearch_find_nearest(elf, addr, get_secindex(elf, sym),

				      true, 20);

}



static bool is_executable_section(struct elf_info *elf, unsigned int secndx)

scripts/mod/modpost.h

+25 −0
Original line number Diff line number Diff line
@@ -10,6 +10,7 @@ 
#include <fcntl.h>

#include <unistd.h>

#include <elf.h>

#include "../../include/linux/module_symbol.h"



#include "list.h"

#include "elfconfig.h"
@@ -128,6 +129,8 @@ struct elf_info { 
	 * take shndx from symtab_shndx_start[N] instead */

	Elf32_Word   *symtab_shndx_start;

	Elf32_Word   *symtab_shndx_stop;



	struct symsearch *symsearch;

};



/* Accessor for sym->st_shndx, hides ugliness of "64k sections" */
@@ -154,6 +157,28 @@ static inline unsigned int get_secindex(const struct elf_info *info, 
	return index;

}



/*

 * If there's no name there, ignore it; likewise, ignore it if it's

 * one of the magic symbols emitted used by current tools.

 *

 * Internal symbols created by tools should be ignored by modpost.

 */

static inline int is_valid_name(struct elf_info *elf, Elf_Sym *sym)

{

	const char *name = elf->strtab + sym->st_name;



	if (!name || !strlen(name))

		return 0;

	return !is_mapping_symbol(name);

}



/* symsearch.c */

void symsearch_init(struct elf_info *elf);

void symsearch_finish(struct elf_info *elf);

Elf_Sym *symsearch_find_nearest(struct elf_info *elf, Elf_Addr addr,

				unsigned int secndx, bool allow_negative,

				Elf_Addr min_distance);



/* file2alias.c */

void handle_moddevtable(struct module *mod, struct elf_info *info,

			Elf_Sym *sym, const char *symname);

scripts/mod/symsearch.c

0 → 100644
+199 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0



/*

 * Helper functions for finding the symbol in an ELF which is "nearest"

 * to a given address.

 */



#include "modpost.h"



struct syminfo {

	unsigned int symbol_index;

	unsigned int section_index;

	Elf_Addr addr;

};



/*

 * Container used to hold an entire binary search table.

 * Entries in table are ascending, sorted first by section_index,

 * then by addr, and last by symbol_index.  The sorting by

 * symbol_index is used to ensure predictable behavior when

 * multiple symbols are present with the same address; all

 * symbols past the first are effectively ignored, by eliding

 * them in symsearch_fixup().

 */

struct symsearch {

	unsigned int table_size;

	struct syminfo table[];

};



static int syminfo_compare(const void *s1, const void *s2)

{

	const struct syminfo *sym1 = s1;

	const struct syminfo *sym2 = s2;



	if (sym1->section_index > sym2->section_index)

		return 1;

	if (sym1->section_index < sym2->section_index)

		return -1;

	if (sym1->addr > sym2->addr)

		return 1;

	if (sym1->addr < sym2->addr)

		return -1;

	if (sym1->symbol_index > sym2->symbol_index)

		return 1;

	if (sym1->symbol_index < sym2->symbol_index)

		return -1;

	return 0;

}



static unsigned int symbol_count(struct elf_info *elf)

{

	unsigned int result = 0;



	for (Elf_Sym *sym = elf->symtab_start; sym < elf->symtab_stop; sym++) {

		if (is_valid_name(elf, sym))

			result++;

	}

	return result;

}



/*

 * Populate the search array that we just allocated.

 * Be slightly paranoid here.  The ELF file is mmap'd and could

 * conceivably change between symbol_count() and symsearch_populate().

 * If we notice any difference, bail out rather than potentially

 * propagating errors or crashing.

 */

static void symsearch_populate(struct elf_info *elf,

			       struct syminfo *table,

			       unsigned int table_size)

{

	bool is_arm = (elf->hdr->e_machine == EM_ARM);



	for (Elf_Sym *sym = elf->symtab_start; sym < elf->symtab_stop; sym++) {

		if (is_valid_name(elf, sym)) {

			if (table_size-- == 0)

				fatal("%s: size mismatch\n", __func__);

			table->symbol_index = sym - elf->symtab_start;

			table->section_index = get_secindex(elf, sym);

			table->addr = sym->st_value;



			/*

			 * For ARM Thumb instruction, the bit 0 of st_value is

			 * set if the symbol is STT_FUNC type. Mask it to get

			 * the address.

			 */

			if (is_arm && ELF_ST_TYPE(sym->st_info) == STT_FUNC)

				table->addr &= ~1;



			table++;

		}

	}



	if (table_size != 0)

		fatal("%s: size mismatch\n", __func__);

}



/*

 * Do any fixups on the table after sorting.

 * For now, this just finds adjacent entries which have

 * the same section_index and addr, and it propagates

 * the first symbol_index over the subsequent entries,

 * so that only one symbol_index is seen for any given

 * section_index and addr.  This ensures that whether

 * we're looking at an address from "above" or "below"

 * that we see the same symbol_index.

 * This does leave some duplicate entries in the table;

 * in practice, these are a small fraction of the

 * total number of entries, and they are harmless to

 * the binary search algorithm other than a few occasional

 * unnecessary comparisons.

 */

static void symsearch_fixup(struct syminfo *table, unsigned int table_size)

{

	/* Don't look at index 0, it will never change. */

	for (unsigned int i = 1; i < table_size; i++) {

		if (table[i].addr == table[i - 1].addr &&

		    table[i].section_index == table[i - 1].section_index) {

			table[i].symbol_index = table[i - 1].symbol_index;

		}

	}

}



void symsearch_init(struct elf_info *elf)

{

	unsigned int table_size = symbol_count(elf);



	elf->symsearch = NOFAIL(malloc(sizeof(struct symsearch) +

				       sizeof(struct syminfo) * table_size));

	elf->symsearch->table_size = table_size;



	symsearch_populate(elf, elf->symsearch->table, table_size);

	qsort(elf->symsearch->table, table_size,

	      sizeof(struct syminfo), syminfo_compare);



	symsearch_fixup(elf->symsearch->table, table_size);

}



void symsearch_finish(struct elf_info *elf)

{

	free(elf->symsearch);

	elf->symsearch = NULL;

}



/*

 * Find the syminfo which is in secndx and "nearest" to addr.

 * allow_negative: allow returning a symbol whose address is > addr.

 * min_distance: ignore symbols which are further away than this.

 *

 * Returns a pointer into the symbol table for success.

 * Returns NULL if no legal symbol is found within the requested range.

 */

Elf_Sym *symsearch_find_nearest(struct elf_info *elf, Elf_Addr addr,

				unsigned int secndx, bool allow_negative,

				Elf_Addr min_distance)

{

	unsigned int hi = elf->symsearch->table_size;

	unsigned int lo = 0;

	struct syminfo *table = elf->symsearch->table;

	struct syminfo target;



	target.addr = addr;

	target.section_index = secndx;

	target.symbol_index = ~0;  /* compares greater than any actual index */

	while (hi > lo) {

		unsigned int mid = lo + (hi - lo) / 2;  /* Avoids overflow */



		if (syminfo_compare(&table[mid], &target) > 0)

			hi = mid;

		else

			lo = mid + 1;

	}



	/*

	 * table[hi], if it exists, is the first entry in the array which

	 * lies beyond target.  table[hi - 1], if it exists, is the last

	 * entry in the array which comes before target, including the

	 * case where it perfectly matches the section and the address.

	 *

	 * Note -- if the address we're looking up falls perfectly

	 * in the middle of two symbols, this is written to always

	 * prefer the symbol with the lower address.

	 */

	Elf_Sym *result = NULL;



	if (allow_negative &&

	    hi < elf->symsearch->table_size &&

	    table[hi].section_index == secndx &&

	    table[hi].addr - addr <= min_distance) {

		min_distance = table[hi].addr - addr;

		result = &elf->symtab_start[table[hi].symbol_index];

	}

	if (hi > 0 &&

	    table[hi - 1].section_index == secndx &&

	    addr - table[hi - 1].addr <= min_distance) {

		result = &elf->symtab_start[table[hi - 1].symbol_index];

	}

	return result;

}