[PATCH RESEND 0/3] Build ORC fast lookup table in scripts/sorttable tool

[PATCH RESEND 0/3] Build ORC fast lookup table in scripts/sorttable tool

[Huaixin Chang]

Move building of fast lookup table from boot to sorttable tool. This saves us
6380us boot time on Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz with cores. It
adds a little more than 7ms to boot time when testing on the same CPU.

Kernel initialization unwind_init() cannot be removed because lookup_num_blocks
is still needed.

Huaixin Chang (3):
  scripts/sorttable: Change section type of orc_lookup to SHT_PROGBITS
  scripts/sorttable: Build orc fast lookup table via sorttable tool
  x86/unwind/orc: Simplify unwind_init() for x86 boot

 arch/x86/kernel/unwind_orc.c      | 41 +---------------
 include/asm-generic/vmlinux.lds.h |  2 +
 scripts/sorttable.h               | 99 ++++++++++++++++++++++++++++++++++++---
 3 files changed, 96 insertions(+), 46 deletions(-)

-- 
2.14.4.44.g2045bb6

[PATCH 1/3] scripts/sorttable: Change section type of orc_lookup to SHT_PROGBITS

[Huaixin Chang]

In order to edit orc_lookup table via sorttable, type of section
orc_lookup needs to be SHT_PROGBITS instead of SHT_NOBITS.

Linker script doesn't seem to allow manual specification of the section
type, so just write a byte into the section instead.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Shile Zhang <shile.zhang@linux.alibaba.com>
---
 include/asm-generic/vmlinux.lds.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index db600ef218d7..49f4f5bc6165 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -826,6 +826,8 @@
 		. += (((SIZEOF(.text) + LOOKUP_BLOCK_SIZE - 1) /	\
 			LOOKUP_BLOCK_SIZE) + 1) * 4;			\
 		orc_lookup_end = .;					\
+		/* HACK: force SHT_PROGBITS so sorttable can edit: */	\
+		BYTE(1);						\
 	}
 #else
 #define ORC_UNWIND_TABLE
-- 
2.14.4.44.g2045bb6

[PATCH 2/3] scripts/sorttable: Build orc fast lookup table via sorttable tool

[Huaixin Chang]

Since orc tables are already sorted by sorttable tool, let us move
building of fast lookup table into sorttable tool too. This saves us
6380us from boot time under Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz
with 64 cores.

Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Shile Zhang <shile.zhang@linux.alibaba.com>
---
 scripts/sorttable.h | 99 +++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 92 insertions(+), 7 deletions(-)

diff --git a/scripts/sorttable.h b/scripts/sorttable.h
index a2baa2fefb13..a36c76c17be4 100644
--- a/scripts/sorttable.h
+++ b/scripts/sorttable.h
@@ -93,12 +93,50 @@
 char g_err[ERRSTR_MAXSZ];
 int *g_orc_ip_table;
 struct orc_entry *g_orc_table;
+static unsigned long orc_ip_table_offset;
 
 pthread_t orc_sort_thread;
 
+struct orc_sort_param {
+	size_t		lookup_table_size;
+	unsigned int	*orc_lookup_table;
+	unsigned long	start_ip;
+	size_t		text_size;
+	unsigned int	orc_num_entries;
+};
+
 static inline unsigned long orc_ip(const int *ip)
 {
-	return (unsigned long)ip + *ip;
+	return (unsigned long)ip + *ip + orc_ip_table_offset;
+}
+
+static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table,
+				    unsigned int num_entries, unsigned long ip)
+{
+	int *first = ip_table;
+	int *last = ip_table + num_entries - 1;
+	int *mid = first, *found = first;
+
+	if (!num_entries)
+		return NULL;
+
+	/*
+	 * Do a binary range search to find the rightmost duplicate of a given
+	 * starting address.  Some entries are section terminators which are
+	 * "weak" entries for ensuring there are no gaps.  They should be
+	 * ignored when they conflict with a real entry.
+	 */
+	while (first <= last) {
+		mid = first + ((last - first) / 2);
+
+		if (orc_ip(mid) <= ip) {
+			found = mid;
+			first = mid + 1;
+		} else
+			last = mid - 1;
+	}
+
+	return u_table + (found - ip_table);
 }
 
 static int orc_sort_cmp(const void *_a, const void *_b)
@@ -130,18 +168,24 @@ static void *sort_orctable(void *arg)
 	int *idxs = NULL;
 	int *tmp_orc_ip_table = NULL;
 	struct orc_entry *tmp_orc_table = NULL;
-	unsigned int *orc_ip_size = (unsigned int *)arg;
-	unsigned int num_entries = *orc_ip_size / sizeof(int);
+	struct orc_sort_param *param = (struct orc_sort_param *)arg;
+	unsigned int num_entries = param->orc_num_entries;
+	unsigned int orc_ip_size = num_entries * sizeof(int);
 	unsigned int orc_size = num_entries * sizeof(struct orc_entry);
+	unsigned int lookup_num_blocks = param->lookup_table_size / sizeof(int);
+	unsigned int *orc_lookup = param->orc_lookup_table;
+	unsigned long lookup_start_ip = param->start_ip;
+	unsigned long lookup_stop_ip = param->start_ip + param->text_size;
+	struct orc_entry *orc;
 
-	idxs = (int *)malloc(*orc_ip_size);
+	idxs = (int *)malloc(orc_ip_size);
 	if (!idxs) {
 		snprintf(g_err, ERRSTR_MAXSZ, "malloc idxs: %s",
 			 strerror(errno));
 		pthread_exit(g_err);
 	}
 
-	tmp_orc_ip_table = (int *)malloc(*orc_ip_size);
+	tmp_orc_ip_table = (int *)malloc(orc_ip_size);
 	if (!tmp_orc_ip_table) {
 		snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_ip_table: %s",
 			 strerror(errno));
@@ -173,6 +217,31 @@ static void *sort_orctable(void *arg)
 		g_orc_table[i] = tmp_orc_table[idxs[i]];
 	}
 
+#define LOOKUP_BLOCK_ORDER	8
+#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
+
+	for (i = 0; i < lookup_num_blocks-1; i++) {
+		orc = __orc_find(g_orc_ip_table, g_orc_table,
+				 num_entries,
+				 lookup_start_ip + (LOOKUP_BLOCK_SIZE * i));
+		if (!orc) {
+			snprintf(g_err, ERRSTR_MAXSZ,
+					"Corrupt .orc_unwind table\n");
+			pthread_exit(g_err);
+		}
+
+		orc_lookup[i] = orc - g_orc_table;
+	}
+
+	/* Initialize the ending block: */
+	orc = __orc_find(g_orc_ip_table, g_orc_table, num_entries,
+			 lookup_stop_ip);
+	if (!orc) {
+		snprintf(g_err, ERRSTR_MAXSZ, "Corrupt .orc_unwind table\n");
+		pthread_exit(g_err);
+	}
+	orc_lookup[lookup_num_blocks-1] = orc - g_orc_table;
+
 	free(idxs);
 	free(tmp_orc_ip_table);
 	free(tmp_orc_table);
@@ -221,6 +290,8 @@ static int do_sort(Elf_Ehdr *ehdr,
 	unsigned int orc_ip_size = 0;
 	unsigned int orc_size = 0;
 	unsigned int orc_num_entries = 0;
+	unsigned long orc_ip_addr = 0;
+	struct orc_sort_param param;
 #endif
 
 	shstrndx = r2(&ehdr->e_shstrndx);
@@ -259,17 +330,27 @@ static int do_sort(Elf_Ehdr *ehdr,
 			orc_ip_size = s->sh_size;
 			g_orc_ip_table = (int *)((void *)ehdr +
 						   s->sh_offset);
+			orc_ip_addr = s->sh_addr;
 		}
 		if (!strcmp(secstrings + idx, ".orc_unwind")) {
 			orc_size = s->sh_size;
 			g_orc_table = (struct orc_entry *)((void *)ehdr +
 							     s->sh_offset);
 		}
+		if (!strcmp(secstrings + idx, ".orc_lookup")) {
+			param.lookup_table_size = s->sh_size;
+			param.orc_lookup_table = (unsigned int *)
+				((void *)ehdr + s->sh_offset);
+		}
+		if (!strcmp(secstrings + idx, ".text")) {
+			param.text_size = s->sh_size;
+			param.start_ip = s->sh_addr;
+		}
 #endif
 	} /* for loop */
 
 #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED)
-	if (!g_orc_ip_table || !g_orc_table) {
+	if (!g_orc_ip_table || !g_orc_table || !param.orc_lookup_table) {
 		fprintf(stderr,
 			"incomplete ORC unwind tables in file: %s\n", fname);
 		goto out;
@@ -285,9 +366,13 @@ static int do_sort(Elf_Ehdr *ehdr,
 		goto out;
 	}
 
+	/* Make orc_ip return virtual address at execution. */
+	orc_ip_table_offset = orc_ip_addr - (unsigned long)g_orc_ip_table;
+
 	/* create thread to sort ORC unwind tables concurrently */
+	param.orc_num_entries = orc_num_entries;
 	if (pthread_create(&orc_sort_thread, NULL,
-			   sort_orctable, &orc_ip_size)) {
+			   sort_orctable, &param)) {
 		fprintf(stderr,
 			"pthread_create orc_sort_thread failed '%s': %s\n",
 			strerror(errno), fname);
-- 
2.14.4.44.g2045bb6

[PATCH 3/3] x86/unwind/orc: Simplify unwind_init() for x86 boot

[Huaixin Chang]

The orc fast lookup table is built by scripts/sorttable tool. All that
is left is setting lookup_num_blocks.

Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Shile Zhang <shile.zhang@linux.alibaba.com>
---
 arch/x86/kernel/unwind_orc.c | 41 ++---------------------------------------
 1 file changed, 2 insertions(+), 39 deletions(-)

diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 7f969b2d240f..0ca4d02d1a69 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -264,48 +264,11 @@ void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size,
 
 void __init unwind_init(void)
 {
-	size_t orc_ip_size = (void *)__stop_orc_unwind_ip - (void *)__start_orc_unwind_ip;
-	size_t orc_size = (void *)__stop_orc_unwind - (void *)__start_orc_unwind;
-	size_t num_entries = orc_ip_size / sizeof(int);
-	struct orc_entry *orc;
-	int i;
-
-	if (!num_entries || orc_ip_size % sizeof(int) != 0 ||
-	    orc_size % sizeof(struct orc_entry) != 0 ||
-	    num_entries != orc_size / sizeof(struct orc_entry)) {
-		orc_warn("WARNING: Bad or missing .orc_unwind table.  Disabling unwinder.\n");
-		return;
-	}
-
 	/*
-	 * Note, the orc_unwind and orc_unwind_ip tables were already
-	 * sorted at build time via the 'sorttable' tool.
-	 * It's ready for binary search straight away, no need to sort it.
+	 * All orc tables are sorted and built via sorttable tool. Initialize
+	 * lookup_num_blocks only.
 	 */
-
-	/* Initialize the fast lookup table: */
 	lookup_num_blocks = orc_lookup_end - orc_lookup;
-	for (i = 0; i < lookup_num_blocks-1; i++) {
-		orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
-				 num_entries,
-				 LOOKUP_START_IP + (LOOKUP_BLOCK_SIZE * i));
-		if (!orc) {
-			orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
-			return;
-		}
-
-		orc_lookup[i] = orc - __start_orc_unwind;
-	}
-
-	/* Initialize the ending block: */
-	orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, num_entries,
-			 LOOKUP_STOP_IP);
-	if (!orc) {
-		orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
-		return;
-	}
-	orc_lookup[lookup_num_blocks-1] = orc - __start_orc_unwind;
-
 	orc_init = true;
 }
 
-- 
2.14.4.44.g2045bb6

Re: [PATCH 2/3] scripts/sorttable: Build orc fast lookup table via sorttable tool

[Ingo Molnar]

* Huaixin Chang <changhuaixin@linux.alibaba.com> wrote:

> Since orc tables are already sorted by sorttable tool, let us move
> building of fast lookup table into sorttable tool too. This saves us
> 6380us from boot time under Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz
> with 64 cores.

Neat!

> +struct orc_sort_param {
> +	size_t		lookup_table_size;
> +	unsigned int	*orc_lookup_table;
> +	unsigned long	start_ip;
> +	size_t		text_size;
> +	unsigned int	orc_num_entries;
> +};

>  
> +#define LOOKUP_BLOCK_ORDER	8
> +#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
> +
> +	for (i = 0; i < lookup_num_blocks-1; i++) {
> +		orc = __orc_find(g_orc_ip_table, g_orc_table,
> +				 num_entries,
> +				 lookup_start_ip + (LOOKUP_BLOCK_SIZE * i));
> +		if (!orc) {
> +			snprintf(g_err, ERRSTR_MAXSZ,
> +					"Corrupt .orc_unwind table\n");
> +			pthread_exit(g_err);
> +		}
> +
> +		orc_lookup[i] = orc - g_orc_table;
> +	}
> +
> +	/* Initialize the ending block: */
> +	orc = __orc_find(g_orc_ip_table, g_orc_table, num_entries,
> +			 lookup_stop_ip);
> +	if (!orc) {
> +		snprintf(g_err, ERRSTR_MAXSZ, "Corrupt .orc_unwind table\n");
> +		pthread_exit(g_err);
> +	}
> +	orc_lookup[lookup_num_blocks-1] = orc - g_orc_table;

Yeah, so now this definition of LOOKUP_BLOCK_* basicaly duplicates the 
arch/x86/include/asm/orc_lookup.h size, with no obvious link between 
the two. This is asking for trouble.

<asm/orc_lookup.h> looks simple enough - can we include it in 
scripts/sorttable.h?

Or better yet, please move these two defines into <asm/orc_types.h>, 
which is already included in sorttable.h.

BTW., please update your patches to spell 'ORC' in a capitalized 
fashion, like most of the existing code does:

>  	/* create thread to sort ORC unwind tables concurrently */

Thanks,

	Ingo

Re: [PATCH 1/3] scripts/sorttable: Change section type of orc_lookup to SHT_PROGBITS

[Ingo Molnar]

* Huaixin Chang <changhuaixin@linux.alibaba.com> wrote:

> In order to edit orc_lookup table via sorttable, type of section
> orc_lookup needs to be SHT_PROGBITS instead of SHT_NOBITS.
> 
> Linker script doesn't seem to allow manual specification of the section
> type, so just write a byte into the section instead.
> 
> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
> Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
> Signed-off-by: Shile Zhang <shile.zhang@linux.alibaba.com>
> ---
>  include/asm-generic/vmlinux.lds.h | 2 ++
>  1 file changed, 2 insertions(+)
> 
> diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
> index db600ef218d7..49f4f5bc6165 100644
> --- a/include/asm-generic/vmlinux.lds.h
> +++ b/include/asm-generic/vmlinux.lds.h
> @@ -826,6 +826,8 @@
>  		. += (((SIZEOF(.text) + LOOKUP_BLOCK_SIZE - 1) /	\
>  			LOOKUP_BLOCK_SIZE) + 1) * 4;			\
>  		orc_lookup_end = .;					\
> +		/* HACK: force SHT_PROGBITS so sorttable can edit: */	\
> +		BYTE(1);						\

Cc:-ing Masahiro Yamada, maybe there's a cleaner solution to this?

Thanks,

	Ingo

Re: [PATCH 2/3] scripts/sorttable: Build orc fast lookup table via sorttable tool

[changhuaixin]

> On Jul 24, 2020, at 9:53 PM, Ingo Molnar <mingo@kernel.org> wrote:
> 
> 
> * Huaixin Chang <changhuaixin@linux.alibaba.com> wrote:
> 
>> Since orc tables are already sorted by sorttable tool, let us move
>> building of fast lookup table into sorttable tool too. This saves us
>> 6380us from boot time under Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz
>> with 64 cores.
> 
> Neat!
> 
>> +struct orc_sort_param {
>> +	size_t		lookup_table_size;
>> +	unsigned int	*orc_lookup_table;
>> +	unsigned long	start_ip;
>> +	size_t		text_size;
>> +	unsigned int	orc_num_entries;
>> +};
> 
>> 
>> +#define LOOKUP_BLOCK_ORDER	8
>> +#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
>> +
>> +	for (i = 0; i < lookup_num_blocks-1; i++) {
>> +		orc = __orc_find(g_orc_ip_table, g_orc_table,
>> +				 num_entries,
>> +				 lookup_start_ip + (LOOKUP_BLOCK_SIZE * i));
>> +		if (!orc) {
>> +			snprintf(g_err, ERRSTR_MAXSZ,
>> +					"Corrupt .orc_unwind table\n");
>> +			pthread_exit(g_err);
>> +		}
>> +
>> +		orc_lookup[i] = orc - g_orc_table;
>> +	}
>> +
>> +	/* Initialize the ending block: */
>> +	orc = __orc_find(g_orc_ip_table, g_orc_table, num_entries,
>> +			 lookup_stop_ip);
>> +	if (!orc) {
>> +		snprintf(g_err, ERRSTR_MAXSZ, "Corrupt .orc_unwind table\n");
>> +		pthread_exit(g_err);
>> +	}
>> +	orc_lookup[lookup_num_blocks-1] = orc - g_orc_table;
> 
> Yeah, so now this definition of LOOKUP_BLOCK_* basicaly duplicates the 
> arch/x86/include/asm/orc_lookup.h size, with no obvious link between 
> the two. This is asking for trouble.
> 
> <asm/orc_lookup.h> looks simple enough - can we include it in 
> scripts/sorttable.h?
> 
> Or better yet, please move these two defines into <asm/orc_types.h>, 
> which is already included in sorttable.h.
> 
Thanks!
Moving these two into <asm/orc_types.h> and capitalized spelling will be done in the following patches.

Huaixin

> BTW., please update your patches to spell 'ORC' in a capitalized 
> fashion, like most of the existing code does:
> 
>> 	/* create thread to sort ORC unwind tables concurrently */
> 
> Thanks,
> 
> 	Ingo

Re: [PATCH 1/3] scripts/sorttable: Change section type of orc_lookup to SHT_PROGBITS

[changhuaixin]

Hi, Ingo

Another way to write SHT_PROGBITS is using elf_create_section to write orc_lookup table headers, when orc_unwind_ip table and orc_unwind table are written. Is this a better solution?

diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 3f98dcfbc177..860d4dcec8e6 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -183,6 +183,10 @@ int create_orc_sections(struct objtool_file *file)
        u_sec = elf_create_section(file->elf, ".orc_unwind",
                                   sizeof(struct orc_entry), idx);

+       /* make flags of section orc_lookup right */
+       if (!elf_create_section(file->elf, ".orc_lookup", sizeof(int), 0))
+               return -1;
+
        /* populate sections */
        idx = 0;
        for_each_sec(file, sec) {

Thanks,
Huaixin

> On Jul 23, 2020, at 11:46 AM, Huaixin Chang <changhuaixin@linux.alibaba.com> wrote:
> 
> In order to edit orc_lookup table via sorttable, type of section
> orc_lookup needs to be SHT_PROGBITS instead of SHT_NOBITS.
> 
> Linker script doesn't seem to allow manual specification of the section
> type, so just write a byte into the section instead.
> 
> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
> Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
> Signed-off-by: Shile Zhang <shile.zhang@linux.alibaba.com>
> ---
> include/asm-generic/vmlinux.lds.h | 2 ++
> 1 file changed, 2 insertions(+)
> 
> diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
> index db600ef218d7..49f4f5bc6165 100644
> --- a/include/asm-generic/vmlinux.lds.h
> +++ b/include/asm-generic/vmlinux.lds.h
> @@ -826,6 +826,8 @@
> 		. += (((SIZEOF(.text) + LOOKUP_BLOCK_SIZE - 1) /	\
> 			LOOKUP_BLOCK_SIZE) + 1) * 4;			\
> 		orc_lookup_end = .;					\
> +		/* HACK: force SHT_PROGBITS so sorttable can edit: */	\
> +		BYTE(1);						\
> 	}
> #else
> #define ORC_UNWIND_TABLE
> -- 
> 2.14.4.44.g2045bb6

Re: [PATCH 1/3] scripts/sorttable: Change section type of orc_lookup to SHT_PROGBITS

[Ingo Molnar]

* changhuaixin <changhuaixin@linux.alibaba.com> wrote:

> Hi, Ingo
> 
> Another way to write SHT_PROGBITS is using elf_create_section to write orc_lookup table headers, when orc_unwind_ip table and orc_unwind table are written. Is this a better solution?
> 
> diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
> index 3f98dcfbc177..860d4dcec8e6 100644
> --- a/tools/objtool/orc_gen.c
> +++ b/tools/objtool/orc_gen.c
> @@ -183,6 +183,10 @@ int create_orc_sections(struct objtool_file *file)
>         u_sec = elf_create_section(file->elf, ".orc_unwind",
>                                    sizeof(struct orc_entry), idx);
> 
> +       /* make flags of section orc_lookup right */
> +       if (!elf_create_section(file->elf, ".orc_lookup", sizeof(int), 0))
> +               return -1;
> +
>         /* populate sections */
>         idx = 0;
>         for_each_sec(file, sec) {

Looks much nicer IMO.

Mind turning this into a proper patch that does it plus reverts the 
hack?

Thanks,

	Ingo

[PATCH v2 0/3] Build ORC fast lookup table in scripts/sorttable tool

[Huaixin Chang]

Move building of fast lookup table from boot to sorttable tool. This saves us
6380us boot time on Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz with cores. It
adds a little more than 7ms to boot time when testing on the same CPU.

Changelog v2:
1. Write .orc_lookup section header via objtool
2. Move two ORC lookup table macro from orc_lookup.h into orc_types.h
3. Spell 'ORC' in capitalized fashion

Huaixin Chang (3):
  objtool: Write .orc_lookup section header
  scripts/sorttable: Build ORC fast lookup table via sorttable tool
  x86/unwind/orc: Simplify unwind_init() for x86 boot

 arch/x86/include/asm/orc_lookup.h      | 16 ------
 arch/x86/include/asm/orc_types.h       | 16 ++++++
 arch/x86/kernel/unwind_orc.c           | 41 +--------------
 arch/x86/kernel/vmlinux.lds.S          |  2 +-
 scripts/sorttable.h                    | 96 +++++++++++++++++++++++++++++++---
 tools/arch/x86/include/asm/orc_types.h | 16 ++++++
 tools/objtool/orc_gen.c                |  4 ++
 7 files changed, 128 insertions(+), 63 deletions(-)

-- 
2.14.4.44.g2045bb6

[PATCH 1/3] objtool: Write .orc_lookup section header

[Huaixin Chang]

The purpose of this patch is to set sh_type to SHT_PROGBITS and remove
write bits away from sh_flags. In order to write section header, just
call elf_create_section() upon section orc_lookup with 0 entry written.

Originally, section headers are as follows:

  [23] .orc_unwind_ip    PROGBITS         ffffffff8259f4b8  0179f4b8
       0000000000178bbc  0000000000000000   A       0     0     1
  [24] .rela.orc_unwind_ RELA             0000000000000000  11e57b58
       00000000008d4668  0000000000000018   I      70    23     8
  [25] .orc_unwind       PROGBITS         ffffffff82718074  01918074
       000000000023519a  0000000000000000   A       0     0     1
  [26] .orc_lookup       NOBITS           ffffffff8294d210  01b4d20e
       0000000000030038  0000000000000000  WA       0     0     1
  [27] .vvar             PROGBITS         ffffffff8297e000  01b7e000
       0000000000001000  0000000000000000  WA       0     0     16

Now, they are changed to:

  [23] .orc_unwind_ip    PROGBITS         ffffffff8259f4b8  0179f4b8
       0000000000178bbc  0000000000000000   A       0     0     1
  [24] .rela.orc_unwind_ RELA             0000000000000000  11e57b58
       00000000008d4668  0000000000000018   I      70    23     8
  [25] .orc_unwind       PROGBITS         ffffffff82718074  01918074
       000000000023519a  0000000000000000   A       0     0     1
  [26] .orc_lookup       PROGBITS         ffffffff8294d210  01b4d210
       0000000000030038  0000000000000000   A       0     0     1
  [27] .vvar             PROGBITS         ffffffff8297e000  01b7e000
       0000000000001000  0000000000000000  WA       0     0     16

Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
---
 tools/objtool/orc_gen.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 968f55e6dd94..2b2653979ad6 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -189,6 +189,10 @@ int create_orc_sections(struct objtool_file *file)
 	u_sec = elf_create_section(file->elf, ".orc_unwind",
 				   sizeof(struct orc_entry), idx);
 
+	/* make flags of section orc_lookup right */
+	if (!elf_create_section(file->elf, ".orc_lookup", sizeof(int), 0))
+		return -1;
+
 	/* populate sections */
 	idx = 0;
 	for_each_sec(file, sec) {
-- 
2.14.4.44.g2045bb6

[PATCH 2/3] scripts/sorttable: Build ORC fast lookup table via sorttable tool

[Huaixin Chang]

Since ORC tables are already sorted by sorttable tool, let us move
building of fast lookup table into sorttable tool too. This saves us
6380us from boot time under Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz
with 64 cores.

Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Shile Zhang <shile.zhang@linux.alibaba.com>
---
 arch/x86/include/asm/orc_lookup.h      | 16 ------
 arch/x86/include/asm/orc_types.h       | 16 ++++++
 arch/x86/kernel/vmlinux.lds.S          |  2 +-
 scripts/sorttable.h                    | 96 +++++++++++++++++++++++++++++++---
 tools/arch/x86/include/asm/orc_types.h | 16 ++++++
 5 files changed, 122 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/orc_lookup.h b/arch/x86/include/asm/orc_lookup.h
index 241631282e43..c75eb1f82bdb 100644
--- a/arch/x86/include/asm/orc_lookup.h
+++ b/arch/x86/include/asm/orc_lookup.h
@@ -5,22 +5,6 @@
 #ifndef _ORC_LOOKUP_H
 #define _ORC_LOOKUP_H
 
-/*
- * This is a lookup table for speeding up access to the .orc_unwind table.
- * Given an input address offset, the corresponding lookup table entry
- * specifies a subset of the .orc_unwind table to search.
- *
- * Each block represents the end of the previous range and the start of the
- * next range.  An extra block is added to give the last range an end.
- *
- * The block size should be a power of 2 to avoid a costly 'div' instruction.
- *
- * A block size of 256 was chosen because it roughly doubles unwinder
- * performance while only adding ~5% to the ORC data footprint.
- */
-#define LOOKUP_BLOCK_ORDER	8
-#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
-
 #ifndef LINKER_SCRIPT
 
 extern unsigned int orc_lookup[];
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index d25534940bde..b93c6a7b4da4 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -9,6 +9,22 @@
 #include <linux/types.h>
 #include <linux/compiler.h>
 
+/*
+ * This is a lookup table for speeding up access to the .orc_unwind table.
+ * Given an input address offset, the corresponding lookup table entry
+ * specifies a subset of the .orc_unwind table to search.
+ *
+ * Each block represents the end of the previous range and the start of the
+ * next range.  An extra block is added to give the last range an end.
+ *
+ * The block size should be a power of 2 to avoid a costly 'div' instruction.
+ *
+ * A block size of 256 was chosen because it roughly doubles unwinder
+ * performance while only adding ~5% to the ORC data footprint.
+ */
+#define LOOKUP_BLOCK_ORDER	8
+#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
+
 /*
  * The ORC_REG_* registers are base registers which are used to find other
  * registers on the stack.
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9a03e5b23135..75760e7f6319 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -29,7 +29,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page_types.h>
-#include <asm/orc_lookup.h>
+#include <asm/orc_types.h>
 #include <asm/cache.h>
 #include <asm/boot.h>
 
diff --git a/scripts/sorttable.h b/scripts/sorttable.h
index a2baa2fefb13..de9822f8ae8f 100644
--- a/scripts/sorttable.h
+++ b/scripts/sorttable.h
@@ -93,12 +93,50 @@
 char g_err[ERRSTR_MAXSZ];
 int *g_orc_ip_table;
 struct orc_entry *g_orc_table;
+static unsigned long orc_ip_table_offset;
 
 pthread_t orc_sort_thread;
 
+struct orc_sort_param {
+	size_t		lookup_table_size;
+	unsigned int	*orc_lookup_table;
+	unsigned long	start_ip;
+	size_t		text_size;
+	unsigned int	orc_num_entries;
+};
+
 static inline unsigned long orc_ip(const int *ip)
 {
-	return (unsigned long)ip + *ip;
+	return (unsigned long)ip + *ip + orc_ip_table_offset;
+}
+
+static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table,
+				    unsigned int num_entries, unsigned long ip)
+{
+	int *first = ip_table;
+	int *last = ip_table + num_entries - 1;
+	int *mid = first, *found = first;
+
+	if (!num_entries)
+		return NULL;
+
+	/*
+	 * Do a binary range search to find the rightmost duplicate of a given
+	 * starting address.  Some entries are section terminators which are
+	 * "weak" entries for ensuring there are no gaps.  They should be
+	 * ignored when they conflict with a real entry.
+	 */
+	while (first <= last) {
+		mid = first + ((last - first) / 2);
+
+		if (orc_ip(mid) <= ip) {
+			found = mid;
+			first = mid + 1;
+		} else
+			last = mid - 1;
+	}
+
+	return u_table + (found - ip_table);
 }
 
 static int orc_sort_cmp(const void *_a, const void *_b)
@@ -130,18 +168,24 @@ static void *sort_orctable(void *arg)
 	int *idxs = NULL;
 	int *tmp_orc_ip_table = NULL;
 	struct orc_entry *tmp_orc_table = NULL;
-	unsigned int *orc_ip_size = (unsigned int *)arg;
-	unsigned int num_entries = *orc_ip_size / sizeof(int);
+	struct orc_sort_param *param = (struct orc_sort_param *)arg;
+	unsigned int num_entries = param->orc_num_entries;
+	unsigned int orc_ip_size = num_entries * sizeof(int);
 	unsigned int orc_size = num_entries * sizeof(struct orc_entry);
+	unsigned int lookup_num_blocks = param->lookup_table_size / sizeof(int);
+	unsigned int *orc_lookup = param->orc_lookup_table;
+	unsigned long lookup_start_ip = param->start_ip;
+	unsigned long lookup_stop_ip = param->start_ip + param->text_size;
+	struct orc_entry *orc;
 
-	idxs = (int *)malloc(*orc_ip_size);
+	idxs = (int *)malloc(orc_ip_size);
 	if (!idxs) {
 		snprintf(g_err, ERRSTR_MAXSZ, "malloc idxs: %s",
 			 strerror(errno));
 		pthread_exit(g_err);
 	}
 
-	tmp_orc_ip_table = (int *)malloc(*orc_ip_size);
+	tmp_orc_ip_table = (int *)malloc(orc_ip_size);
 	if (!tmp_orc_ip_table) {
 		snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_ip_table: %s",
 			 strerror(errno));
@@ -173,6 +217,28 @@ static void *sort_orctable(void *arg)
 		g_orc_table[i] = tmp_orc_table[idxs[i]];
 	}
 
+	for (i = 0; i < lookup_num_blocks-1; i++) {
+		orc = __orc_find(g_orc_ip_table, g_orc_table,
+				 num_entries,
+				 lookup_start_ip + (LOOKUP_BLOCK_SIZE * i));
+		if (!orc) {
+			snprintf(g_err, ERRSTR_MAXSZ,
+					"Corrupt .orc_unwind table\n");
+			pthread_exit(g_err);
+		}
+
+		orc_lookup[i] = orc - g_orc_table;
+	}
+
+	/* Initialize the ending block: */
+	orc = __orc_find(g_orc_ip_table, g_orc_table, num_entries,
+			 lookup_stop_ip);
+	if (!orc) {
+		snprintf(g_err, ERRSTR_MAXSZ, "Corrupt .orc_unwind table\n");
+		pthread_exit(g_err);
+	}
+	orc_lookup[lookup_num_blocks-1] = orc - g_orc_table;
+
 	free(idxs);
 	free(tmp_orc_ip_table);
 	free(tmp_orc_table);
@@ -221,6 +287,8 @@ static int do_sort(Elf_Ehdr *ehdr,
 	unsigned int orc_ip_size = 0;
 	unsigned int orc_size = 0;
 	unsigned int orc_num_entries = 0;
+	unsigned long orc_ip_addr = 0;
+	struct orc_sort_param param;
 #endif
 
 	shstrndx = r2(&ehdr->e_shstrndx);
@@ -259,17 +327,27 @@ static int do_sort(Elf_Ehdr *ehdr,
 			orc_ip_size = s->sh_size;
 			g_orc_ip_table = (int *)((void *)ehdr +
 						   s->sh_offset);
+			orc_ip_addr = s->sh_addr;
 		}
 		if (!strcmp(secstrings + idx, ".orc_unwind")) {
 			orc_size = s->sh_size;
 			g_orc_table = (struct orc_entry *)((void *)ehdr +
 							     s->sh_offset);
 		}
+		if (!strcmp(secstrings + idx, ".orc_lookup")) {
+			param.lookup_table_size = s->sh_size;
+			param.orc_lookup_table = (unsigned int *)
+				((void *)ehdr + s->sh_offset);
+		}
+		if (!strcmp(secstrings + idx, ".text")) {
+			param.text_size = s->sh_size;
+			param.start_ip = s->sh_addr;
+		}
 #endif
 	} /* for loop */
 
 #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED)
-	if (!g_orc_ip_table || !g_orc_table) {
+	if (!g_orc_ip_table || !g_orc_table || !param.orc_lookup_table) {
 		fprintf(stderr,
 			"incomplete ORC unwind tables in file: %s\n", fname);
 		goto out;
@@ -285,9 +363,13 @@ static int do_sort(Elf_Ehdr *ehdr,
 		goto out;
 	}
 
+	/* Make orc_ip return virtual address at execution. */
+	orc_ip_table_offset = orc_ip_addr - (unsigned long)g_orc_ip_table;
+
 	/* create thread to sort ORC unwind tables concurrently */
+	param.orc_num_entries = orc_num_entries;
 	if (pthread_create(&orc_sort_thread, NULL,
-			   sort_orctable, &orc_ip_size)) {
+			   sort_orctable, &param)) {
 		fprintf(stderr,
 			"pthread_create orc_sort_thread failed '%s': %s\n",
 			strerror(errno), fname);
diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h
index d25534940bde..b93c6a7b4da4 100644
--- a/tools/arch/x86/include/asm/orc_types.h
+++ b/tools/arch/x86/include/asm/orc_types.h
@@ -9,6 +9,22 @@
 #include <linux/types.h>
 #include <linux/compiler.h>
 
+/*
+ * This is a lookup table for speeding up access to the .orc_unwind table.
+ * Given an input address offset, the corresponding lookup table entry
+ * specifies a subset of the .orc_unwind table to search.
+ *
+ * Each block represents the end of the previous range and the start of the
+ * next range.  An extra block is added to give the last range an end.
+ *
+ * The block size should be a power of 2 to avoid a costly 'div' instruction.
+ *
+ * A block size of 256 was chosen because it roughly doubles unwinder
+ * performance while only adding ~5% to the ORC data footprint.
+ */
+#define LOOKUP_BLOCK_ORDER	8
+#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
+
 /*
  * The ORC_REG_* registers are base registers which are used to find other
  * registers on the stack.
-- 
2.14.4.44.g2045bb6

[PATCH 3/3] x86/unwind/orc: Simplify unwind_init() for x86 boot

[Huaixin Chang]

The ORC fast lookup table is built by scripts/sorttable tool. All that
is left is setting lookup_num_blocks.

Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Shile Zhang <shile.zhang@linux.alibaba.com>
---
 arch/x86/kernel/unwind_orc.c | 41 ++---------------------------------------
 1 file changed, 2 insertions(+), 39 deletions(-)

diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index ec88bbe08a32..29890389b4f6 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -264,48 +264,11 @@ void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size,
 
 void __init unwind_init(void)
 {
-	size_t orc_ip_size = (void *)__stop_orc_unwind_ip - (void *)__start_orc_unwind_ip;
-	size_t orc_size = (void *)__stop_orc_unwind - (void *)__start_orc_unwind;
-	size_t num_entries = orc_ip_size / sizeof(int);
-	struct orc_entry *orc;
-	int i;
-
-	if (!num_entries || orc_ip_size % sizeof(int) != 0 ||
-	    orc_size % sizeof(struct orc_entry) != 0 ||
-	    num_entries != orc_size / sizeof(struct orc_entry)) {
-		orc_warn("WARNING: Bad or missing .orc_unwind table.  Disabling unwinder.\n");
-		return;
-	}
-
 	/*
-	 * Note, the orc_unwind and orc_unwind_ip tables were already
-	 * sorted at build time via the 'sorttable' tool.
-	 * It's ready for binary search straight away, no need to sort it.
+	 * All ORC tables are sorted and built via sorttable tool. Initialize
+	 * lookup_num_blocks only.
 	 */
-
-	/* Initialize the fast lookup table: */
 	lookup_num_blocks = orc_lookup_end - orc_lookup;
-	for (i = 0; i < lookup_num_blocks-1; i++) {
-		orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
-				 num_entries,
-				 LOOKUP_START_IP + (LOOKUP_BLOCK_SIZE * i));
-		if (!orc) {
-			orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
-			return;
-		}
-
-		orc_lookup[i] = orc - __start_orc_unwind;
-	}
-
-	/* Initialize the ending block: */
-	orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, num_entries,
-			 LOOKUP_STOP_IP);
-	if (!orc) {
-		orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
-		return;
-	}
-	orc_lookup[lookup_num_blocks-1] = orc - __start_orc_unwind;
-
 	orc_init = true;
 }
 
-- 
2.14.4.44.g2045bb6

Re: [PATCH 1/3] scripts/sorttable: Change section type of orc_lookup to SHT_PROGBITS

[changhuaixin]

> On Aug 6, 2020, at 11:08 PM, Ingo Molnar <mingo@kernel.org> wrote:
> 
> 
> * changhuaixin <changhuaixin@linux.alibaba.com> wrote:
> 
>> Hi, Ingo
>> 
>> Another way to write SHT_PROGBITS is using elf_create_section to write orc_lookup table headers, when orc_unwind_ip table and orc_unwind table are written. Is this a better solution?
>> 
>> diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
>> index 3f98dcfbc177..860d4dcec8e6 100644
>> --- a/tools/objtool/orc_gen.c
>> +++ b/tools/objtool/orc_gen.c
>> @@ -183,6 +183,10 @@ int create_orc_sections(struct objtool_file *file)
>>        u_sec = elf_create_section(file->elf, ".orc_unwind",
>>                                   sizeof(struct orc_entry), idx);
>> 
>> +       /* make flags of section orc_lookup right */
>> +       if (!elf_create_section(file->elf, ".orc_lookup", sizeof(int), 0))
>> +               return -1;
>> +
>>        /* populate sections */
>>        idx = 0;
>>        for_each_sec(file, sec) {
> 
> Looks much nicer IMO.
> 
> Mind turning this into a proper patch that does it plus reverts the 
> hack?
> 
A new patchset is sent.

Thanks,
huaixin

> Thanks,
> 
> 	Ingo

Re: [PATCH v2 0/3] Build ORC fast lookup table in scripts/sorttable tool

[changhuaixin]

Hi，Ingo

This patchset reverts the hacks from patchset v1. Also it includes some other fixes upon v1 as suggested.
Will you please have a look at this?

The previous links are:
https://lore.kernel.org/lkml/20200724135531.GB648324@gmail.com/

Thanks,
huaixin

> On Aug 7, 2020, at 12:17 PM, Huaixin Chang <changhuaixin@linux.alibaba.com> wrote:
> 
> Move building of fast lookup table from boot to sorttable tool. This saves us
> 6380us boot time on Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz with cores. It
> adds a little more than 7ms to boot time when testing on the same CPU.
> 
> Changelog v2:
> 1. Write .orc_lookup section header via objtool
> 2. Move two ORC lookup table macro from orc_lookup.h into orc_types.h
> 3. Spell 'ORC' in capitalized fashion
> 
> Huaixin Chang (3):
>  objtool: Write .orc_lookup section header
>  scripts/sorttable: Build ORC fast lookup table via sorttable tool
>  x86/unwind/orc: Simplify unwind_init() for x86 boot
> 
> arch/x86/include/asm/orc_lookup.h      | 16 ------
> arch/x86/include/asm/orc_types.h       | 16 ++++++
> arch/x86/kernel/unwind_orc.c           | 41 +--------------
> arch/x86/kernel/vmlinux.lds.S          |  2 +-
> scripts/sorttable.h                    | 96 +++++++++++++++++++++++++++++++---
> tools/arch/x86/include/asm/orc_types.h | 16 ++++++
> tools/objtool/orc_gen.c                |  4 ++
> 7 files changed, 128 insertions(+), 63 deletions(-)
> 
> -- 
> 2.14.4.44.g2045bb6

[PATCH 2/3] scripts/sorttable: Build orc fast lookup table via sorttable tool

[Huaixin Chang]

Since orc tables are already sorted by sorttable tool, let us move
building of fast lookup table into sorttable tool too. This saves us
6380us from boot time under Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz
with 64 cores.

Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Shile Zhang <shile.zhang@linux.alibaba.com>
---
 scripts/sorttable.h | 99 +++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 92 insertions(+), 7 deletions(-)

diff --git a/scripts/sorttable.h b/scripts/sorttable.h
index a2baa2fefb13..a36c76c17be4 100644
--- a/scripts/sorttable.h
+++ b/scripts/sorttable.h
@@ -93,12 +93,50 @@
 char g_err[ERRSTR_MAXSZ];
 int *g_orc_ip_table;
 struct orc_entry *g_orc_table;
+static unsigned long orc_ip_table_offset;
 
 pthread_t orc_sort_thread;
 
+struct orc_sort_param {
+	size_t		lookup_table_size;
+	unsigned int	*orc_lookup_table;
+	unsigned long	start_ip;
+	size_t		text_size;
+	unsigned int	orc_num_entries;
+};
+
 static inline unsigned long orc_ip(const int *ip)
 {
-	return (unsigned long)ip + *ip;
+	return (unsigned long)ip + *ip + orc_ip_table_offset;
+}
+
+static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table,
+				    unsigned int num_entries, unsigned long ip)
+{
+	int *first = ip_table;
+	int *last = ip_table + num_entries - 1;
+	int *mid = first, *found = first;
+
+	if (!num_entries)
+		return NULL;
+
+	/*
+	 * Do a binary range search to find the rightmost duplicate of a given
+	 * starting address.  Some entries are section terminators which are
+	 * "weak" entries for ensuring there are no gaps.  They should be
+	 * ignored when they conflict with a real entry.
+	 */
+	while (first <= last) {
+		mid = first + ((last - first) / 2);
+
+		if (orc_ip(mid) <= ip) {
+			found = mid;
+			first = mid + 1;
+		} else
+			last = mid - 1;
+	}
+
+	return u_table + (found - ip_table);
 }
 
 static int orc_sort_cmp(const void *_a, const void *_b)
@@ -130,18 +168,24 @@ static void *sort_orctable(void *arg)
 	int *idxs = NULL;
 	int *tmp_orc_ip_table = NULL;
 	struct orc_entry *tmp_orc_table = NULL;
-	unsigned int *orc_ip_size = (unsigned int *)arg;
-	unsigned int num_entries = *orc_ip_size / sizeof(int);
+	struct orc_sort_param *param = (struct orc_sort_param *)arg;
+	unsigned int num_entries = param->orc_num_entries;
+	unsigned int orc_ip_size = num_entries * sizeof(int);
 	unsigned int orc_size = num_entries * sizeof(struct orc_entry);
+	unsigned int lookup_num_blocks = param->lookup_table_size / sizeof(int);
+	unsigned int *orc_lookup = param->orc_lookup_table;
+	unsigned long lookup_start_ip = param->start_ip;
+	unsigned long lookup_stop_ip = param->start_ip + param->text_size;
+	struct orc_entry *orc;
 
-	idxs = (int *)malloc(*orc_ip_size);
+	idxs = (int *)malloc(orc_ip_size);
 	if (!idxs) {
 		snprintf(g_err, ERRSTR_MAXSZ, "malloc idxs: %s",
 			 strerror(errno));
 		pthread_exit(g_err);
 	}
 
-	tmp_orc_ip_table = (int *)malloc(*orc_ip_size);
+	tmp_orc_ip_table = (int *)malloc(orc_ip_size);
 	if (!tmp_orc_ip_table) {
 		snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_ip_table: %s",
 			 strerror(errno));
@@ -173,6 +217,31 @@ static void *sort_orctable(void *arg)
 		g_orc_table[i] = tmp_orc_table[idxs[i]];
 	}
 
+#define LOOKUP_BLOCK_ORDER	8
+#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
+
+	for (i = 0; i < lookup_num_blocks-1; i++) {
+		orc = __orc_find(g_orc_ip_table, g_orc_table,
+				 num_entries,
+				 lookup_start_ip + (LOOKUP_BLOCK_SIZE * i));
+		if (!orc) {
+			snprintf(g_err, ERRSTR_MAXSZ,
+					"Corrupt .orc_unwind table\n");
+			pthread_exit(g_err);
+		}
+
+		orc_lookup[i] = orc - g_orc_table;
+	}
+
+	/* Initialize the ending block: */
+	orc = __orc_find(g_orc_ip_table, g_orc_table, num_entries,
+			 lookup_stop_ip);
+	if (!orc) {
+		snprintf(g_err, ERRSTR_MAXSZ, "Corrupt .orc_unwind table\n");
+		pthread_exit(g_err);
+	}
+	orc_lookup[lookup_num_blocks-1] = orc - g_orc_table;
+
 	free(idxs);
 	free(tmp_orc_ip_table);
 	free(tmp_orc_table);
@@ -221,6 +290,8 @@ static int do_sort(Elf_Ehdr *ehdr,
 	unsigned int orc_ip_size = 0;
 	unsigned int orc_size = 0;
 	unsigned int orc_num_entries = 0;
+	unsigned long orc_ip_addr = 0;
+	struct orc_sort_param param;
 #endif
 
 	shstrndx = r2(&ehdr->e_shstrndx);
@@ -259,17 +330,27 @@ static int do_sort(Elf_Ehdr *ehdr,
 			orc_ip_size = s->sh_size;
 			g_orc_ip_table = (int *)((void *)ehdr +
 						   s->sh_offset);
+			orc_ip_addr = s->sh_addr;
 		}
 		if (!strcmp(secstrings + idx, ".orc_unwind")) {
 			orc_size = s->sh_size;
 			g_orc_table = (struct orc_entry *)((void *)ehdr +
 							     s->sh_offset);
 		}
+		if (!strcmp(secstrings + idx, ".orc_lookup")) {
+			param.lookup_table_size = s->sh_size;
+			param.orc_lookup_table = (unsigned int *)
+				((void *)ehdr + s->sh_offset);
+		}
+		if (!strcmp(secstrings + idx, ".text")) {
+			param.text_size = s->sh_size;
+			param.start_ip = s->sh_addr;
+		}
 #endif
 	} /* for loop */
 
 #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED)
-	if (!g_orc_ip_table || !g_orc_table) {
+	if (!g_orc_ip_table || !g_orc_table || !param.orc_lookup_table) {
 		fprintf(stderr,
 			"incomplete ORC unwind tables in file: %s\n", fname);
 		goto out;
@@ -285,9 +366,13 @@ static int do_sort(Elf_Ehdr *ehdr,
 		goto out;
 	}
 
+	/* Make orc_ip return virtual address at execution. */
+	orc_ip_table_offset = orc_ip_addr - (unsigned long)g_orc_ip_table;
+
 	/* create thread to sort ORC unwind tables concurrently */
+	param.orc_num_entries = orc_num_entries;
 	if (pthread_create(&orc_sort_thread, NULL,
-			   sort_orctable, &orc_ip_size)) {
+			   sort_orctable, &param)) {
 		fprintf(stderr,
 			"pthread_create orc_sort_thread failed '%s': %s\n",
 			strerror(errno), fname);
-- 
2.14.4.44.g2045bb6

[PATCH 2/3] scripts/sorttable: Build orc fast lookup table via sorttable tool

[Huaixin Chang]

Since orc tables are already sorted by sorttable tool, let us move
building of fast lookup table into sorttable tool too. This saves us
6380us from boot time under Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz
with 64 cores.

Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Shile Zhang <shile.zhang@linux.alibaba.com>
---
 scripts/sorttable.h | 99 +++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 92 insertions(+), 7 deletions(-)

diff --git a/scripts/sorttable.h b/scripts/sorttable.h
index a2baa2fefb13..a36c76c17be4 100644
--- a/scripts/sorttable.h
+++ b/scripts/sorttable.h
@@ -93,12 +93,50 @@
 char g_err[ERRSTR_MAXSZ];
 int *g_orc_ip_table;
 struct orc_entry *g_orc_table;
+static unsigned long orc_ip_table_offset;
 
 pthread_t orc_sort_thread;
 
+struct orc_sort_param {
+	size_t		lookup_table_size;
+	unsigned int	*orc_lookup_table;
+	unsigned long	start_ip;
+	size_t		text_size;
+	unsigned int	orc_num_entries;
+};
+
 static inline unsigned long orc_ip(const int *ip)
 {
-	return (unsigned long)ip + *ip;
+	return (unsigned long)ip + *ip + orc_ip_table_offset;
+}
+
+static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table,
+				    unsigned int num_entries, unsigned long ip)
+{
+	int *first = ip_table;
+	int *last = ip_table + num_entries - 1;
+	int *mid = first, *found = first;
+
+	if (!num_entries)
+		return NULL;
+
+	/*
+	 * Do a binary range search to find the rightmost duplicate of a given
+	 * starting address.  Some entries are section terminators which are
+	 * "weak" entries for ensuring there are no gaps.  They should be
+	 * ignored when they conflict with a real entry.
+	 */
+	while (first <= last) {
+		mid = first + ((last - first) / 2);
+
+		if (orc_ip(mid) <= ip) {
+			found = mid;
+			first = mid + 1;
+		} else
+			last = mid - 1;
+	}
+
+	return u_table + (found - ip_table);
 }
 
 static int orc_sort_cmp(const void *_a, const void *_b)
@@ -130,18 +168,24 @@ static void *sort_orctable(void *arg)
 	int *idxs = NULL;
 	int *tmp_orc_ip_table = NULL;
 	struct orc_entry *tmp_orc_table = NULL;
-	unsigned int *orc_ip_size = (unsigned int *)arg;
-	unsigned int num_entries = *orc_ip_size / sizeof(int);
+	struct orc_sort_param *param = (struct orc_sort_param *)arg;
+	unsigned int num_entries = param->orc_num_entries;
+	unsigned int orc_ip_size = num_entries * sizeof(int);
 	unsigned int orc_size = num_entries * sizeof(struct orc_entry);
+	unsigned int lookup_num_blocks = param->lookup_table_size / sizeof(int);
+	unsigned int *orc_lookup = param->orc_lookup_table;
+	unsigned long lookup_start_ip = param->start_ip;
+	unsigned long lookup_stop_ip = param->start_ip + param->text_size;
+	struct orc_entry *orc;
 
-	idxs = (int *)malloc(*orc_ip_size);
+	idxs = (int *)malloc(orc_ip_size);
 	if (!idxs) {
 		snprintf(g_err, ERRSTR_MAXSZ, "malloc idxs: %s",
 			 strerror(errno));
 		pthread_exit(g_err);
 	}
 
-	tmp_orc_ip_table = (int *)malloc(*orc_ip_size);
+	tmp_orc_ip_table = (int *)malloc(orc_ip_size);
 	if (!tmp_orc_ip_table) {
 		snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_ip_table: %s",
 			 strerror(errno));
@@ -173,6 +217,31 @@ static void *sort_orctable(void *arg)
 		g_orc_table[i] = tmp_orc_table[idxs[i]];
 	}
 
+#define LOOKUP_BLOCK_ORDER	8
+#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
+
+	for (i = 0; i < lookup_num_blocks-1; i++) {
+		orc = __orc_find(g_orc_ip_table, g_orc_table,
+				 num_entries,
+				 lookup_start_ip + (LOOKUP_BLOCK_SIZE * i));
+		if (!orc) {
+			snprintf(g_err, ERRSTR_MAXSZ,
+					"Corrupt .orc_unwind table\n");
+			pthread_exit(g_err);
+		}
+
+		orc_lookup[i] = orc - g_orc_table;
+	}
+
+	/* Initialize the ending block: */
+	orc = __orc_find(g_orc_ip_table, g_orc_table, num_entries,
+			 lookup_stop_ip);
+	if (!orc) {
+		snprintf(g_err, ERRSTR_MAXSZ, "Corrupt .orc_unwind table\n");
+		pthread_exit(g_err);
+	}
+	orc_lookup[lookup_num_blocks-1] = orc - g_orc_table;
+
 	free(idxs);
 	free(tmp_orc_ip_table);
 	free(tmp_orc_table);
@@ -221,6 +290,8 @@ static int do_sort(Elf_Ehdr *ehdr,
 	unsigned int orc_ip_size = 0;
 	unsigned int orc_size = 0;
 	unsigned int orc_num_entries = 0;
+	unsigned long orc_ip_addr = 0;
+	struct orc_sort_param param;
 #endif
 
 	shstrndx = r2(&ehdr->e_shstrndx);
@@ -259,17 +330,27 @@ static int do_sort(Elf_Ehdr *ehdr,
 			orc_ip_size = s->sh_size;
 			g_orc_ip_table = (int *)((void *)ehdr +
 						   s->sh_offset);
+			orc_ip_addr = s->sh_addr;
 		}
 		if (!strcmp(secstrings + idx, ".orc_unwind")) {
 			orc_size = s->sh_size;
 			g_orc_table = (struct orc_entry *)((void *)ehdr +
 							     s->sh_offset);
 		}
+		if (!strcmp(secstrings + idx, ".orc_lookup")) {
+			param.lookup_table_size = s->sh_size;
+			param.orc_lookup_table = (unsigned int *)
+				((void *)ehdr + s->sh_offset);
+		}
+		if (!strcmp(secstrings + idx, ".text")) {
+			param.text_size = s->sh_size;
+			param.start_ip = s->sh_addr;
+		}
 #endif
 	} /* for loop */
 
 #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED)
-	if (!g_orc_ip_table || !g_orc_table) {
+	if (!g_orc_ip_table || !g_orc_table || !param.orc_lookup_table) {
 		fprintf(stderr,
 			"incomplete ORC unwind tables in file: %s\n", fname);
 		goto out;
@@ -285,9 +366,13 @@ static int do_sort(Elf_Ehdr *ehdr,
 		goto out;
 	}
 
+	/* Make orc_ip return virtual address at execution. */
+	orc_ip_table_offset = orc_ip_addr - (unsigned long)g_orc_ip_table;
+
 	/* create thread to sort ORC unwind tables concurrently */
+	param.orc_num_entries = orc_num_entries;
 	if (pthread_create(&orc_sort_thread, NULL,
-			   sort_orctable, &orc_ip_size)) {
+			   sort_orctable, &param)) {
 		fprintf(stderr,
 			"pthread_create orc_sort_thread failed '%s': %s\n",
 			strerror(errno), fname);
-- 
2.14.4.44.g2045bb6