[PATCH v2 03/20] x86, ACPI, mm: Kill max_low_pfn_mapped

[PATCH v2 03/20] x86, ACPI, mm: Kill max_low_pfn_mapped

[Yinghai Lu]

Now we have arch_pfn_mapped array, and max_low_pfn_mapped should not
be used anymore.

User should use arch_pfn_mapped or just 1UL<<(32-PAGE_SHIFT) instead.

Only user is ACPI_INITRD_TABLE_OVERRIDE, and it should not use that,
as later accessing is using early_ioremap(). Change to try to 4G below
and then 4G above.

-v2: Leave alone max_low_pfn_mapped in i915 code according to tj.

Suggested-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: Jacob Shin <jacob.shin@amd.com>
Cc: linux-acpi@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
---
 arch/x86/include/asm/page_types.h |    1 -
 arch/x86/kernel/setup.c           |    4 +---
 arch/x86/mm/init.c                |    4 ----
 drivers/acpi/osl.c                |   10 +++++++---
 4 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 54c9787..b012b82 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -43,7 +43,6 @@
 
 extern int devmem_is_allowed(unsigned long pagenr);
 
-extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
 static inline phys_addr_t get_max_mapped(void)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 1629577..e75c6e6 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -113,13 +113,11 @@
 #include <asm/prom.h>
 
 /*
- * max_low_pfn_mapped: highest direct mapped pfn under 4GB
- * max_pfn_mapped:     highest direct mapped pfn over 4GB
+ * max_pfn_mapped:     highest direct mapped pfn
  *
  * The direct mapping only covers E820_RAM regions, so the ranges and gaps are
  * represented by pfn_mapped
  */
-unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
 
 #ifdef CONFIG_DMI
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 59b7fc4..abcc241 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -313,10 +313,6 @@ static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn)
 	nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_X_MAX);
 
 	max_pfn_mapped = max(max_pfn_mapped, end_pfn);
-
-	if (start_pfn < (1UL<<(32-PAGE_SHIFT)))
-		max_low_pfn_mapped = max(max_low_pfn_mapped,
-					 min(end_pfn, 1UL<<(32-PAGE_SHIFT)));
 }
 
 bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn)
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 586e7e9..c08cdb6 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -624,9 +624,13 @@ void __init acpi_initrd_override(void *data, size_t size)
 	if (table_nr == 0)
 		return;
 
-	acpi_tables_addr =
-		memblock_find_in_range(0, max_low_pfn_mapped << PAGE_SHIFT,
-				       all_tables_size, PAGE_SIZE);
+	/* under 4G at first, then above 4G */
+	acpi_tables_addr = memblock_find_in_range(0, (1ULL<<32) - 1,
+					all_tables_size, PAGE_SIZE);
+	if (!acpi_tables_addr)
+		acpi_tables_addr = memblock_find_in_range(0,
+					~(phys_addr_t)0,
+					all_tables_size, PAGE_SIZE);
 	if (!acpi_tables_addr) {
 		WARN_ON(1);
 		return;
-- 
1.7.10.4

Re: [PATCH v2 03/20] x86, ACPI, mm: Kill max_low_pfn_mapped

[Tejun Heo]

Hello,

On Sat, Mar 09, 2013 at 10:44:30PM -0800, Yinghai Lu wrote:
> Now we have arch_pfn_mapped array, and max_low_pfn_mapped should not
> be used anymore.
> 
> User should use arch_pfn_mapped or just 1UL<<(32-PAGE_SHIFT) instead.
> 
> Only user is ACPI_INITRD_TABLE_OVERRIDE, and it should not use that,
> as later accessing is using early_ioremap(). Change to try to 4G below
> and then 4G above.
...
> diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
> index 586e7e9..c08cdb6 100644
> --- a/drivers/acpi/osl.c
> +++ b/drivers/acpi/osl.c
> @@ -624,9 +624,13 @@ void __init acpi_initrd_override(void *data, size_t size)
>  	if (table_nr == 0)
>  		return;
>  
> -	acpi_tables_addr =
> -		memblock_find_in_range(0, max_low_pfn_mapped << PAGE_SHIFT,
> -				       all_tables_size, PAGE_SIZE);
> +	/* under 4G at first, then above 4G */
> +	acpi_tables_addr = memblock_find_in_range(0, (1ULL<<32) - 1,
> +					all_tables_size, PAGE_SIZE);
> +	if (!acpi_tables_addr)
> +		acpi_tables_addr = memblock_find_in_range(0,
> +					~(phys_addr_t)0,
> +					all_tables_size, PAGE_SIZE);

So, it's changing the allocation from <=4G to <=4G first and then >4G.
The only explanation given is "as later accessing is using
early_ioremap()", but I can't see why that can be a reason for that.
early_ioremap() doesn't care whether the given physaddr is under 4G or
not, it unconditionally maps it into fixmap, so whether the allocated
address is below or above 4G doesn't make any difference.

Changing the allowed range of the allocation should be a separate
patch.  It has some chance of its own breakage and the change itself
isn't really related to this one.

Please try to elaborate the reasoning behind "why", so that readers of
the description don't have to deduce (oh well, guess) your intentions
behind the changes.  As much as it would help the readers, it'd also
help you even more as you would have had to explicitly write something
like "the table is accessed with early_ioremap() so the address
doesn't need to be restricted under 4G; however, to avoid unnecessary
remappings, first try <= 4G and then > 4G."  Then, you would be
compelled to check whether the statement you explicitly wrote is true,
which isn't in this case and you would also realize that the change
isn't trivial and doesn't really belong with this patch.  By not doing
the due diligence, you're offloading what you should have done to
others, which isn't very nice.

I think the descriptions are better in this posting than the last time
but it's still lacking, so, please putfff more effort into describing
the changes and reasoning behind them.

Thanks.

-- 
tejun

Re: [PATCH v2 03/20] x86, ACPI, mm: Kill max_low_pfn_mapped

[Yinghai Lu]

On Thu, Apr 4, 2013 at 10:36 AM, Tejun Heo <tj@kernel.org> wrote:
> Hello,
>
> On Sat, Mar 09, 2013 at 10:44:30PM -0800, Yinghai Lu wrote:
>> Now we have arch_pfn_mapped array, and max_low_pfn_mapped should not
>> be used anymore.
>>
>> User should use arch_pfn_mapped or just 1UL<<(32-PAGE_SHIFT) instead.
>>
>> Only user is ACPI_INITRD_TABLE_OVERRIDE, and it should not use that,
>> as later accessing is using early_ioremap(). Change to try to 4G below
>> and then 4G above.
> ...
>> diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
>> index 586e7e9..c08cdb6 100644
>> --- a/drivers/acpi/osl.c
>> +++ b/drivers/acpi/osl.c
>> @@ -624,9 +624,13 @@ void __init acpi_initrd_override(void *data, size_t size)
>>       if (table_nr == 0)
>>               return;
>>
>> -     acpi_tables_addr =
>> -             memblock_find_in_range(0, max_low_pfn_mapped << PAGE_SHIFT,
>> -                                    all_tables_size, PAGE_SIZE);
>> +     /* under 4G at first, then above 4G */
>> +     acpi_tables_addr = memblock_find_in_range(0, (1ULL<<32) - 1,
>> +                                     all_tables_size, PAGE_SIZE);
>> +     if (!acpi_tables_addr)
>> +             acpi_tables_addr = memblock_find_in_range(0,
>> +                                     ~(phys_addr_t)0,
>> +                                     all_tables_size, PAGE_SIZE);
>
> So, it's changing the allocation from <=4G to <=4G first and then >4G.
> The only explanation given is "as later accessing is using
> early_ioremap()", but I can't see why that can be a reason for that.
> early_ioremap() doesn't care whether the given physaddr is under 4G or
> not, it unconditionally maps it into fixmap, so whether the allocated
> address is below or above 4G doesn't make any difference.
>
> Changing the allowed range of the allocation should be a separate
> patch.  It has some chance of its own breakage and the change itself
> isn't really related to this one.

Ok, will separate that  "try above 4G" to another patch.

>
> Please try to elaborate the reasoning behind "why", so that readers of
> the description don't have to deduce (oh well, guess) your intentions
> behind the changes.  As much as it would help the readers, it'd also
> help you even more as you would have had to explicitly write something
> like "the table is accessed with early_ioremap() so the address
> doesn't need to be restricted under 4G; however, to avoid unnecessary
> remappings, first try <= 4G and then > 4G."  Then, you would be
> compelled to check whether the statement you explicitly wrote is true,
> which isn't in this case and you would also realize that the change
> isn't trivial and doesn't really belong with this patch.  By not doing
> the due diligence, you're offloading what you should have done to
> others, which isn't very nice.
>
> I think the descriptions are better in this posting than the last time
> but it's still lacking, so, please putfff more effort into describing
> the changes and reasoning behind them.

ok.

Thanks a lot.

Yinghai

[PATCH v2 04/20] x86, ACPI: Increase override tables number limit

[Yinghai Lu]

Current acpi tables in initrd is limited to 10, that is too small.
64 should be good enough as we have 35 sigs and could have several
SSDT.

Two problems in current code prevent us from increasing limit:
1. that cpio file info array is put in stack, as every element is 32
   bytes, could run out of stack if we have that array size to 64.
   We can move it out from stack, and make it as global and put it in
   __initdata section.
2. early_ioremap only can remap 256k one time. Current code is mapping
   10 tables one time. If we increase that limit, whole size could be
   more than 256k, early_ioremap will fail with that.
   We can map table one by one during copying, instead of mapping
   all them one time.

-v2: According to tj, split it out to separated patch, also
     rename array name to acpi_initrd_files.

Signed-off-by: Yinghai <yinghai@kernel.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: linux-acpi@vger.kernel.org
---
 drivers/acpi/osl.c |   21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index c08cdb6..8aaf721 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -569,8 +569,8 @@ static const char * const table_sigs[] = {
 
 #define ACPI_HEADER_SIZE sizeof(struct acpi_table_header)
 
-/* Must not increase 10 or needs code modification below */
-#define ACPI_OVERRIDE_TABLES 10
+#define ACPI_OVERRIDE_TABLES 64
+static struct cpio_data __initdata acpi_initrd_files[ACPI_OVERRIDE_TABLES];
 
 void __init acpi_initrd_override(void *data, size_t size)
 {
@@ -579,7 +579,6 @@ void __init acpi_initrd_override(void *data, size_t size)
 	struct acpi_table_header *table;
 	char cpio_path[32] = "kernel/firmware/acpi/";
 	struct cpio_data file;
-	struct cpio_data early_initrd_files[ACPI_OVERRIDE_TABLES];
 	char *p;
 
 	if (data == NULL || size == 0)
@@ -617,8 +616,8 @@ void __init acpi_initrd_override(void *data, size_t size)
 			table->signature, cpio_path, file.name, table->length);
 
 		all_tables_size += table->length;
-		early_initrd_files[table_nr].data = file.data;
-		early_initrd_files[table_nr].size = file.size;
+		acpi_initrd_files[table_nr].data = file.data;
+		acpi_initrd_files[table_nr].size = file.size;
 		table_nr++;
 	}
 	if (table_nr == 0)
@@ -648,14 +647,14 @@ void __init acpi_initrd_override(void *data, size_t size)
 	memblock_reserve(acpi_tables_addr, acpi_tables_addr + all_tables_size);
 	arch_reserve_mem_area(acpi_tables_addr, all_tables_size);
 
-	p = early_ioremap(acpi_tables_addr, all_tables_size);
-
 	for (no = 0; no < table_nr; no++) {
-		memcpy(p + total_offset, early_initrd_files[no].data,
-		       early_initrd_files[no].size);
-		total_offset += early_initrd_files[no].size;
+		phys_addr_t size = acpi_initrd_files[no].size;
+
+		p = early_ioremap(acpi_tables_addr + total_offset, size);
+		memcpy(p, acpi_initrd_files[no].data, size);
+		early_iounmap(p, size);
+		total_offset += size;
 	}
-	early_iounmap(p, all_tables_size);
 }
 #endif /* CONFIG_ACPI_INITRD_TABLE_OVERRIDE */
 
-- 
1.7.10.4

Re: [PATCH v2 04/20] x86, ACPI: Increase override tables number limit

[Tejun Heo]

On Sat, Mar 09, 2013 at 10:44:31PM -0800, Yinghai Lu wrote:
> Current acpi tables in initrd is limited to 10, that is too small.
> 64 should be good enough as we have 35 sigs and could have several
> SSDT.
> 
> Two problems in current code prevent us from increasing limit:
> 1. that cpio file info array is put in stack, as every element is 32
>    bytes, could run out of stack if we have that array size to 64.
>    We can move it out from stack, and make it as global and put it in
>    __initdata section.
> 2. early_ioremap only can remap 256k one time. Current code is mapping
>    10 tables one time. If we increase that limit, whole size could be
>    more than 256k, early_ioremap will fail with that.
>    We can map table one by one during copying, instead of mapping
>    all them one time.
> 
> -v2: According to tj, split it out to separated patch, also
>      rename array name to acpi_initrd_files.
> 
> Signed-off-by: Yinghai <yinghai@kernel.org>
> Cc: Rafael J. Wysocki <rjw@sisk.pl>
> Cc: linux-acpi@vger.kernel.org

Acked-by: Tejun Heo <tj@kernel.org>

> @@ -648,14 +647,14 @@ void __init acpi_initrd_override(void *data, size_t size)
>  	memblock_reserve(acpi_tables_addr, acpi_tables_addr + all_tables_size);
>  	arch_reserve_mem_area(acpi_tables_addr, all_tables_size);
>  
> -	p = early_ioremap(acpi_tables_addr, all_tables_size);
> -

It'd be nice to have a brief comment here explaining why we're mapping
each table separately.

>  	for (no = 0; no < table_nr; no++) {
> -		memcpy(p + total_offset, early_initrd_files[no].data,
> -		       early_initrd_files[no].size);
> -		total_offset += early_initrd_files[no].size;
> +		phys_addr_t size = acpi_initrd_files[no].size;
> +
> +		p = early_ioremap(acpi_tables_addr + total_offset, size);
> +		memcpy(p, acpi_initrd_files[no].data, size);
> +		early_iounmap(p, size);
> +		total_offset += size;
>  	}
> -	early_iounmap(p, all_tables_size);

Thanks.

-- 
tejun

Re: [PATCH v2 04/20] x86, ACPI: Increase override tables number limit

[Yinghai Lu]

On Thu, Apr 4, 2013 at 10:50 AM, Tejun Heo <tj@kernel.org> wrote:
> On Sat, Mar 09, 2013 at 10:44:31PM -0800, Yinghai Lu wrote:

>> @@ -648,14 +647,14 @@ void __init acpi_initrd_override(void *data, size_t size)
>>       memblock_reserve(acpi_tables_addr, acpi_tables_addr + all_tables_size);
>>       arch_reserve_mem_area(acpi_tables_addr, all_tables_size);
>>
>> -     p = early_ioremap(acpi_tables_addr, all_tables_size);
>> -
>
> It'd be nice to have a brief comment here explaining why we're mapping
> each table separately.

ok, will copy lines from changelog to comment.

Thanks

Yinghai

[PATCH v2 05/20] x86, ACPI: Split acpi_initrd_override to find/copy two functions

[Yinghai Lu]

To parse srat early, we need to move acpi table probing early.
acpi_initrd_table_override is before acpi table probing. So we need to
move it early too.

Current code acpi_initrd_table_override is after init_mem_mapping and
relocate_initrd(), so it can scan initrd and copy acpi tables with kernel
virtual address of initrd.
Copying need to be after memblock is ready, because it need to allocate
buffer for new acpi tables.

So we have to split that function to find and copy two functions.
Find should be as early as possible. Copy should be after memblock is ready.

Finding could be done in head_32.S and head64.c, just like microcode
early scanning. In head_32.S, it is 32bit flat mode, we don't
need to set page table to access it. In head64.c, #PF set page table
could help us access initrd with kernel low mapping address.

Copying could be done just after memblock is ready and before probing
acpi tables, and we need to early_ioremap to access source and target
range, as init_mem_mapping is not called yet.

Also move down two functions declaration to avoid #ifdef in setup.c

ACPI_INITRD_TABLE_OVERRIDE depends one ACPI and BLK_DEV_INITRD.
So could move declaration out from #ifdef CONFIG_ACPI protection.

-v2: Split one patch out according to tj.
     also don't pass table_nr around.

Signed-off-by: Yinghai <yinghai@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Jacob Shin <jacob.shin@amd.com>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: linux-acpi@vger.kernel.org
---
 arch/x86/kernel/setup.c |    6 +++---
 drivers/acpi/osl.c      |   18 +++++++++++++-----
 include/linux/acpi.h    |   16 ++++++++--------
 3 files changed, 24 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index e75c6e6..d0cc176 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1092,9 +1092,9 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_initrd();
 
-#if defined(CONFIG_ACPI) && defined(CONFIG_BLK_DEV_INITRD)
-	acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start);
-#endif
+	acpi_initrd_override_find((void *)initrd_start,
+					initrd_end - initrd_start);
+	acpi_initrd_override_copy();
 
 	reserve_crashkernel();
 
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 8aaf721..d66ae0e 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -572,14 +572,13 @@ static const char * const table_sigs[] = {
 #define ACPI_OVERRIDE_TABLES 64
 static struct cpio_data __initdata acpi_initrd_files[ACPI_OVERRIDE_TABLES];
 
-void __init acpi_initrd_override(void *data, size_t size)
+void __init acpi_initrd_override_find(void *data, size_t size)
 {
-	int sig, no, table_nr = 0, total_offset = 0;
+	int sig, no, table_nr = 0;
 	long offset = 0;
 	struct acpi_table_header *table;
 	char cpio_path[32] = "kernel/firmware/acpi/";
 	struct cpio_data file;
-	char *p;
 
 	if (data == NULL || size == 0)
 		return;
@@ -620,7 +619,14 @@ void __init acpi_initrd_override(void *data, size_t size)
 		acpi_initrd_files[table_nr].size = file.size;
 		table_nr++;
 	}
-	if (table_nr == 0)
+}
+
+void __init acpi_initrd_override_copy(void)
+{
+	int no, total_offset = 0;
+	char *p;
+
+	if (!all_tables_size)
 		return;
 
 	/* under 4G at first, then above 4G */
@@ -647,9 +653,11 @@ void __init acpi_initrd_override(void *data, size_t size)
 	memblock_reserve(acpi_tables_addr, acpi_tables_addr + all_tables_size);
 	arch_reserve_mem_area(acpi_tables_addr, all_tables_size);
 
-	for (no = 0; no < table_nr; no++) {
+	for (no = 0; no < ACPI_OVERRIDE_TABLES; no++) {
 		phys_addr_t size = acpi_initrd_files[no].size;
 
+		if (!size)
+			break;
 		p = early_ioremap(acpi_tables_addr + total_offset, size);
 		memcpy(p, acpi_initrd_files[no].data, size);
 		early_iounmap(p, size);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index bcbdd74..1654a241 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -79,14 +79,6 @@ typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table);
 typedef int (*acpi_tbl_entry_handler)(struct acpi_subtable_header *header,
 				      const unsigned long end);
 
-#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
-void acpi_initrd_override(void *data, size_t size);
-#else
-static inline void acpi_initrd_override(void *data, size_t size)
-{
-}
-#endif
-
 char * __acpi_map_table (unsigned long phys_addr, unsigned long size);
 void __acpi_unmap_table(char *map, unsigned long size);
 int early_acpi_boot_init(void);
@@ -485,6 +477,14 @@ static inline bool acpi_driver_match_device(struct device *dev,
 
 #endif	/* !CONFIG_ACPI */
 
+#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
+void acpi_initrd_override_find(void *data, size_t size);
+void acpi_initrd_override_copy(void);
+#else
+static inline void acpi_initrd_override_find(void *data, size_t size) { }
+static inline void acpi_initrd_override_copy(void) { }
+#endif
+
 #ifdef CONFIG_ACPI
 void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
 			       u32 pm1a_ctrl,  u32 pm1b_ctrl));
-- 
1.7.10.4

Re: [PATCH v2 05/20] x86, ACPI: Split acpi_initrd_override to find/copy two functions

[Tejun Heo]

On Sat, Mar 09, 2013 at 10:44:32PM -0800, Yinghai Lu wrote:
> To parse srat early, we need to move acpi table probing early.
> acpi_initrd_table_override is before acpi table probing. So we need to
> move it early too.
> 
> Current code acpi_initrd_table_override is after init_mem_mapping and
> relocate_initrd(), so it can scan initrd and copy acpi tables with kernel
> virtual address of initrd.
> Copying need to be after memblock is ready, because it need to allocate
> buffer for new acpi tables.
> 
> So we have to split that function to find and copy two functions.
> Find should be as early as possible. Copy should be after memblock is ready.
> 
> Finding could be done in head_32.S and head64.c, just like microcode
> early scanning. In head_32.S, it is 32bit flat mode, we don't
> need to set page table to access it. In head64.c, #PF set page table
> could help us access initrd with kernel low mapping address.
> 
> Copying could be done just after memblock is ready and before probing
> acpi tables, and we need to early_ioremap to access source and target
> range, as init_mem_mapping is not called yet.
> 
> Also move down two functions declaration to avoid #ifdef in setup.c
> 
> ACPI_INITRD_TABLE_OVERRIDE depends one ACPI and BLK_DEV_INITRD.
> So could move declaration out from #ifdef CONFIG_ACPI protection.

Heh, I couldn't really follow the above.  How about something like the
following.

 While a dummy version of acpi_initrd_override() was defined when
 !CONFIG_ACPI_INITRD_TABLE_OVERRIDE, the prototype and dummy version
 were conditionalized inside CONFIG_ACPI.  This forced setup_arch() to
 have its own #ifdefs around acpi_initrd_override() as otherwise build
 would fail when !CONFIG_ACPI.  Move the prototypes and dummy
 implementations of the newly split functions below CONFIG_ACPI block
 in acpi.h so that we can do away with #ifdefs in its user.

Acked-by: Tejun Heo <tj@kernel.org>

Thanks.

-- 
tejun

Re: [PATCH v2 05/20] x86, ACPI: Split acpi_initrd_override to find/copy two functions

[Yinghai Lu]

On Thu, Apr 4, 2013 at 11:07 AM, Tejun Heo <tj@kernel.org> wrote:
>>
>> Also move down two functions declaration to avoid #ifdef in setup.c
>>
>> ACPI_INITRD_TABLE_OVERRIDE depends one ACPI and BLK_DEV_INITRD.
>> So could move declaration out from #ifdef CONFIG_ACPI protection.
>
> Heh, I couldn't really follow the above.  How about something like the
> following.
>
>  While a dummy version of acpi_initrd_override() was defined when
>  !CONFIG_ACPI_INITRD_TABLE_OVERRIDE, the prototype and dummy version
>  were conditionalized inside CONFIG_ACPI.  This forced setup_arch() to
>  have its own #ifdefs around acpi_initrd_override() as otherwise build
>  would fail when !CONFIG_ACPI.  Move the prototypes and dummy
>  implementations of the newly split functions below CONFIG_ACPI block
>  in acpi.h so that we can do away with #ifdefs in its user.

update changelog with your changes.

Thanks

Yinghai

[PATCH v2 06/20] x86, ACPI: Store override acpi tables phys addr in cpio files info array

[Yinghai Lu]

In 32bit we will find table with phys address during 32bit flat mode
in head_32.S, because at that time we don't need set page table to
access initrd.

For copying we could use early_ioremap() with phys directly before mem mapping
is set.

To keep 32bit and 64bit consistent, use phys_addr for all.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: linux-acpi@vger.kernel.org
---
 drivers/acpi/osl.c |   14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index d66ae0e..54bcc37 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -615,7 +615,7 @@ void __init acpi_initrd_override_find(void *data, size_t size)
 			table->signature, cpio_path, file.name, table->length);
 
 		all_tables_size += table->length;
-		acpi_initrd_files[table_nr].data = file.data;
+		acpi_initrd_files[table_nr].data = (void *)__pa(file.data);
 		acpi_initrd_files[table_nr].size = file.size;
 		table_nr++;
 	}
@@ -624,7 +624,7 @@ void __init acpi_initrd_override_find(void *data, size_t size)
 void __init acpi_initrd_override_copy(void)
 {
 	int no, total_offset = 0;
-	char *p;
+	char *p, *q;
 
 	if (!all_tables_size)
 		return;
@@ -654,12 +654,20 @@ void __init acpi_initrd_override_copy(void)
 	arch_reserve_mem_area(acpi_tables_addr, all_tables_size);
 
 	for (no = 0; no < ACPI_OVERRIDE_TABLES; no++) {
+		/*
+		 * have to use unsigned long, otherwise 32bit spit warning
+		 * and it is ok to unsigned long, as bootloader would not
+		 * load initrd above 4G for 32bit kernel.
+		 */
+		unsigned long addr = (unsigned long)acpi_initrd_files[no].data;
 		phys_addr_t size = acpi_initrd_files[no].size;
 
 		if (!size)
 			break;
+		q = early_ioremap(addr, size);
 		p = early_ioremap(acpi_tables_addr + total_offset, size);
-		memcpy(p, acpi_initrd_files[no].data, size);
+		memcpy(p, q, size);
+		early_iounmap(q, size);
 		early_iounmap(p, size);
 		total_offset += size;
 	}
-- 
1.7.10.4

Re: [PATCH v2 06/20] x86, ACPI: Store override acpi tables phys addr in cpio files info array

[Tejun Heo]

On Sat, Mar 09, 2013 at 10:44:33PM -0800, Yinghai Lu wrote:
> In 32bit we will find table with phys address during 32bit flat mode
> in head_32.S, because at that time we don't need set page table to
> access initrd.
> 
> For copying we could use early_ioremap() with phys directly before mem mapping
> is set.
> 
> To keep 32bit and 64bit consistent, use phys_addr for all.
> 
> Signed-off-by: Yinghai Lu <yinghai@kernel.org>
> Cc: Rafael J. Wysocki <rjw@sisk.pl>
> Cc: linux-acpi@vger.kernel.org
> ---
>  drivers/acpi/osl.c |   14 +++++++++++---
>  1 file changed, 11 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
> index d66ae0e..54bcc37 100644
> --- a/drivers/acpi/osl.c
> +++ b/drivers/acpi/osl.c
> @@ -615,7 +615,7 @@ void __init acpi_initrd_override_find(void *data, size_t size)
>  			table->signature, cpio_path, file.name, table->length);
>  
>  		all_tables_size += table->length;
> -		acpi_initrd_files[table_nr].data = file.data;
> +		acpi_initrd_files[table_nr].data = (void *)__pa(file.data);
>  		acpi_initrd_files[table_nr].size = file.size;
>  		table_nr++;
>  	}
> @@ -624,7 +624,7 @@ void __init acpi_initrd_override_find(void *data, size_t size)
>  void __init acpi_initrd_override_copy(void)
>  {
>  	int no, total_offset = 0;
> -	char *p;
> +	char *p, *q;
>  
>  	if (!all_tables_size)
>  		return;
> @@ -654,12 +654,20 @@ void __init acpi_initrd_override_copy(void)
>  	arch_reserve_mem_area(acpi_tables_addr, all_tables_size);
>  
>  	for (no = 0; no < ACPI_OVERRIDE_TABLES; no++) {
> +		/*
> +		 * have to use unsigned long, otherwise 32bit spit warning
> +		 * and it is ok to unsigned long, as bootloader would not
> +		 * load initrd above 4G for 32bit kernel.
> +		 */
> +		unsigned long addr = (unsigned long)acpi_initrd_files[no].data;

I can't say I like this.  It's stuffing phys_addr_t into void *.  It
might work okay but the code is a bit misleading / confusing.  "void
*" shouldn't contain a physical address.  Maybe the alternatives are
uglier, I don't know.  If you can think of a reasonable way to not do
this, it would be great.

Thanks.

-- 
tejun

Re: [PATCH v2 06/20] x86, ACPI: Store override acpi tables phys addr in cpio files info array

[Tejun Heo]

On Thu, Apr 04, 2013 at 11:27:42AM -0700, Tejun Heo wrote:
> > +		/*
> > +		 * have to use unsigned long, otherwise 32bit spit warning
> > +		 * and it is ok to unsigned long, as bootloader would not
> > +		 * load initrd above 4G for 32bit kernel.
> > +		 */
> > +		unsigned long addr = (unsigned long)acpi_initrd_files[no].data;
> 
> I can't say I like this.  It's stuffing phys_addr_t into void *.  It
> might work okay but the code is a bit misleading / confusing.  "void
> *" shouldn't contain a physical address.  Maybe the alternatives are
> uglier, I don't know.  If you can think of a reasonable way to not do
> this, it would be great.

Also the comment contradicts with what you wrote in the next patch.

  Boot loader could load initrd above max_low_pfn.

Hmmm?

-- 
tejun

Re: [PATCH v2 06/20] x86, ACPI: Store override acpi tables phys addr in cpio files info array

[Yinghai Lu]

On Thu, Apr 4, 2013 at 11:30 AM, Tejun Heo <tj@kernel.org> wrote:
> Also the comment contradicts with what you wrote in the next patch.
>
>   Boot loader could load initrd above max_low_pfn.

It does not contradict:
this patch: bootloader would not load initrd above 4G for 32bit kernel

max_low_pfn is below 4G.

Thanks

Yinghai

Re: [PATCH v2 06/20] x86, ACPI: Store override acpi tables phys addr in cpio files info array

[Yinghai Lu]

[-- Attachment #1: Type: text/plain, Size: 925 bytes --]

On Thu, Apr 4, 2013 at 11:27 AM, Tejun Heo <tj@kernel.org> wrote:
>>       for (no = 0; no < ACPI_OVERRIDE_TABLES; no++) {
>> +             /*
>> +              * have to use unsigned long, otherwise 32bit spit warning
>> +              * and it is ok to unsigned long, as bootloader would not
>> +              * load initrd above 4G for 32bit kernel.
>> +              */
>> +             unsigned long addr = (unsigned long)acpi_initrd_files[no].data;
>
> I can't say I like this.  It's stuffing phys_addr_t into void *.  It
> might work okay but the code is a bit misleading / confusing.  "void
> *" shouldn't contain a physical address.  Maybe the alternatives are
> uglier, I don't know.  If you can think of a reasonable way to not do
> this, it would be great.

Please check if you are happy with attached.

-v2: introduce file_pos to save phys address instead of abusing cpio_data
        that tj is not happy with.

[-- Attachment #2: fix_acpi_override_2.patch --]
[-- Type: application/octet-stream, Size: 2390 bytes --]

Subject: [PATCH] x86, ACPI: Store override acpi tables phys addr in cpio files info array

In 32bit we will find table with phys address during 32bit flat mode
in head_32.S, because at that time we don't need set page table to
access initrd.

For copying we could use early_ioremap() with phys directly before mem mapping
is set.

To keep 32bit and 64bit consistent, use phys_addr for all.

-v2: introduce file_pos to save phys address instead of abusing cpio_data
	that tj is not happy with.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: linux-acpi@vger.kernel.org

---
 drivers/acpi/osl.c |   15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

Index: linux-2.6/drivers/acpi/osl.c
===================================================================
--- linux-2.6.orig/drivers/acpi/osl.c
+++ linux-2.6/drivers/acpi/osl.c
@@ -570,7 +570,11 @@ static const char * const table_sigs[] =
 #define ACPI_HEADER_SIZE sizeof(struct acpi_table_header)
 
 #define ACPI_OVERRIDE_TABLES 64
-static struct cpio_data __initdata acpi_initrd_files[ACPI_OVERRIDE_TABLES];
+struct file_pos {
+	phys_addr_t data;
+	phys_addr_t size;
+};
+static struct file_pos __initdata acpi_initrd_files[ACPI_OVERRIDE_TABLES];
 
 void __init acpi_initrd_override_find(void *data, size_t size)
 {
@@ -615,7 +619,7 @@ void __init acpi_initrd_override_find(vo
 			table->signature, cpio_path, file.name, table->length);
 
 		all_tables_size += table->length;
-		acpi_initrd_files[table_nr].data = file.data;
+		acpi_initrd_files[table_nr].data = __pa_nodebug(file.data);
 		acpi_initrd_files[table_nr].size = file.size;
 		table_nr++;
 	}
@@ -624,7 +628,7 @@ void __init acpi_initrd_override_find(vo
 void __init acpi_initrd_override_copy(void)
 {
 	int no, total_offset = 0;
-	char *p;
+	char *p, *q;
 
 	if (!all_tables_size)
 		return;
@@ -659,12 +663,15 @@ void __init acpi_initrd_override_copy(vo
 	 * one by one during copying.
 	 */
 	for (no = 0; no < ACPI_OVERRIDE_TABLES; no++) {
+		phys_addr_t addr = acpi_initrd_files[no].data;
 		phys_addr_t size = acpi_initrd_files[no].size;
 
 		if (!size)
 			break;
+		q = early_ioremap(addr, size);
 		p = early_ioremap(acpi_tables_addr + total_offset, size);
-		memcpy(p, acpi_initrd_files[no].data, size);
+		memcpy(p, q, size);
+		early_iounmap(q, size);
 		early_iounmap(p, size);
 		total_offset += size;
 	}

[PATCH v2 07/20] x86, ACPI: Make acpi_initrd_override_find work with 32bit flat mode

[Yinghai Lu]

For finding with 32bit, it would be easy to access initrd in 32bit
flat mode, as we don't need to set page table.

That is from head_32.S, and microcode updating already use this trick.

Need to change acpi_initrd_override_find to use phys to access global
variables.

Pass is_phys in the function, as we can not use address to decide if it
is phys or virtual address on 32 bit. Boot loader could load initrd above
max_low_pfn.

Don't call printk as it uses global variables, so delay print later
during copying.

Change table_sigs to use stack instead, otherwise it is too messy to change
string array to phys and still keep offset calculating correct.
That size is about 36x4 bytes, and it is small to settle in stack.

Also remove "continue" in MARCO to make code more readable.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Jacob Shin <jacob.shin@amd.com>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: linux-acpi@vger.kernel.org
---
 arch/x86/kernel/setup.c |    2 +-
 drivers/acpi/osl.c      |   85 ++++++++++++++++++++++++++++++++---------------
 include/linux/acpi.h    |    5 +--
 3 files changed, 63 insertions(+), 29 deletions(-)

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d0cc176..16a703f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1093,7 +1093,7 @@ void __init setup_arch(char **cmdline_p)
 	reserve_initrd();
 
 	acpi_initrd_override_find((void *)initrd_start,
-					initrd_end - initrd_start);
+					initrd_end - initrd_start, false);
 	acpi_initrd_override_copy();
 
 	reserve_crashkernel();
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 54bcc37..611ca9b 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -551,38 +551,54 @@ u8 __init acpi_table_checksum(u8 *buffer, u32 length)
 	return sum;
 }
 
-/* All but ACPI_SIG_RSDP and ACPI_SIG_FACS: */
-static const char * const table_sigs[] = {
-	ACPI_SIG_BERT, ACPI_SIG_CPEP, ACPI_SIG_ECDT, ACPI_SIG_EINJ,
-	ACPI_SIG_ERST, ACPI_SIG_HEST, ACPI_SIG_MADT, ACPI_SIG_MSCT,
-	ACPI_SIG_SBST, ACPI_SIG_SLIT, ACPI_SIG_SRAT, ACPI_SIG_ASF,
-	ACPI_SIG_BOOT, ACPI_SIG_DBGP, ACPI_SIG_DMAR, ACPI_SIG_HPET,
-	ACPI_SIG_IBFT, ACPI_SIG_IVRS, ACPI_SIG_MCFG, ACPI_SIG_MCHI,
-	ACPI_SIG_SLIC, ACPI_SIG_SPCR, ACPI_SIG_SPMI, ACPI_SIG_TCPA,
-	ACPI_SIG_UEFI, ACPI_SIG_WAET, ACPI_SIG_WDAT, ACPI_SIG_WDDT,
-	ACPI_SIG_WDRT, ACPI_SIG_DSDT, ACPI_SIG_FADT, ACPI_SIG_PSDT,
-	ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT, NULL };
-
 /* Non-fatal errors: Affected tables/files are ignored */
 #define INVALID_TABLE(x, path, name)					\
-	{ pr_err("ACPI OVERRIDE: " x " [%s%s]\n", path, name); continue; }
+	do { pr_err("ACPI OVERRIDE: " x " [%s%s]\n", path, name); } while (0)
 
 #define ACPI_HEADER_SIZE sizeof(struct acpi_table_header)
 
 #define ACPI_OVERRIDE_TABLES 64
 static struct cpio_data __initdata acpi_initrd_files[ACPI_OVERRIDE_TABLES];
 
-void __init acpi_initrd_override_find(void *data, size_t size)
+/*
+ * acpi_initrd_override_find() is called from head_32.S and head64.c.
+ * head_32.S calling path is with 32bit flat mode, so we can access
+ * initrd early without setting pagetable or relocating initrd. For
+ * global variables accessing, we need to use phys address instead of
+ * kernel virtual address, try to put table_sigs string array in stack,
+ * so avoid switching for it.
+ * Also don't call printk as it uses global variables.
+ */
+void __init acpi_initrd_override_find(void *data, size_t size, bool is_phys)
 {
 	int sig, no, table_nr = 0;
 	long offset = 0;
 	struct acpi_table_header *table;
 	char cpio_path[32] = "kernel/firmware/acpi/";
 	struct cpio_data file;
+	struct cpio_data *files = acpi_initrd_files;
+	int *all_tables_size_p = &all_tables_size;
+
+	/* All but ACPI_SIG_RSDP and ACPI_SIG_FACS: */
+	char *table_sigs[] = {
+		ACPI_SIG_BERT, ACPI_SIG_CPEP, ACPI_SIG_ECDT, ACPI_SIG_EINJ,
+		ACPI_SIG_ERST, ACPI_SIG_HEST, ACPI_SIG_MADT, ACPI_SIG_MSCT,
+		ACPI_SIG_SBST, ACPI_SIG_SLIT, ACPI_SIG_SRAT, ACPI_SIG_ASF,
+		ACPI_SIG_BOOT, ACPI_SIG_DBGP, ACPI_SIG_DMAR, ACPI_SIG_HPET,
+		ACPI_SIG_IBFT, ACPI_SIG_IVRS, ACPI_SIG_MCFG, ACPI_SIG_MCHI,
+		ACPI_SIG_SLIC, ACPI_SIG_SPCR, ACPI_SIG_SPMI, ACPI_SIG_TCPA,
+		ACPI_SIG_UEFI, ACPI_SIG_WAET, ACPI_SIG_WDAT, ACPI_SIG_WDDT,
+		ACPI_SIG_WDRT, ACPI_SIG_DSDT, ACPI_SIG_FADT, ACPI_SIG_PSDT,
+		ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT, NULL };
 
 	if (data == NULL || size == 0)
 		return;
 
+	if (is_phys) {
+		files = (struct cpio_data *)__pa_symbol(acpi_initrd_files);
+		all_tables_size_p = (int *)__pa_symbol(&all_tables_size);
+	}
+
 	for (no = 0; no < ACPI_OVERRIDE_TABLES; no++) {
 		file = find_cpio_data(cpio_path, data, size, &offset);
 		if (!file.data)
@@ -591,9 +607,12 @@ void __init acpi_initrd_override_find(void *data, size_t size)
 		data += offset;
 		size -= offset;
 
-		if (file.size < sizeof(struct acpi_table_header))
-			INVALID_TABLE("Table smaller than ACPI header",
+		if (file.size < sizeof(struct acpi_table_header)) {
+			if (!is_phys)
+				INVALID_TABLE("Table smaller than ACPI header",
 				      cpio_path, file.name);
+			continue;
+		}
 
 		table = file.data;
 
@@ -601,22 +620,33 @@ void __init acpi_initrd_override_find(void *data, size_t size)
 			if (!memcmp(table->signature, table_sigs[sig], 4))
 				break;
 
-		if (!table_sigs[sig])
-			INVALID_TABLE("Unknown signature",
+		if (!table_sigs[sig]) {
+			if (!is_phys)
+				 INVALID_TABLE("Unknown signature",
 				      cpio_path, file.name);
-		if (file.size != table->length)
-			INVALID_TABLE("File length does not match table length",
+			continue;
+		}
+		if (file.size != table->length) {
+			if (!is_phys)
+				INVALID_TABLE("File length does not match table length",
 				      cpio_path, file.name);
-		if (acpi_table_checksum(file.data, table->length))
-			INVALID_TABLE("Bad table checksum",
+			continue;
+		}
+		if (acpi_table_checksum(file.data, table->length)) {
+			if (!is_phys)
+				INVALID_TABLE("Bad table checksum",
 				      cpio_path, file.name);
+			continue;
+		}
 
-		pr_info("%4.4s ACPI table found in initrd [%s%s][0x%x]\n",
+		if (!is_phys)
+			pr_info("%4.4s ACPI table found in initrd [%s%s][0x%x]\n",
 			table->signature, cpio_path, file.name, table->length);
 
-		all_tables_size += table->length;
-		acpi_initrd_files[table_nr].data = (void *)__pa(file.data);
-		acpi_initrd_files[table_nr].size = file.size;
+		(*all_tables_size_p) += table->length;
+		files[table_nr].data = is_phys ?
+					    file.data : (void *)__pa(file.data);
+		files[table_nr].size = file.size;
 		table_nr++;
 	}
 }
@@ -666,6 +696,9 @@ void __init acpi_initrd_override_copy(void)
 			break;
 		q = early_ioremap(addr, size);
 		p = early_ioremap(acpi_tables_addr + total_offset, size);
+		pr_info("%4.4s ACPI table found in initrd [%#010llx-%#010llx]\n",
+				((struct acpi_table_header *)q)->signature,
+				(u64)addr, (u64)(addr + size - 1));
 		memcpy(p, q, size);
 		early_iounmap(q, size);
 		early_iounmap(p, size);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 1654a241..4b943e6 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -478,10 +478,11 @@ static inline bool acpi_driver_match_device(struct device *dev,
 #endif	/* !CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
-void acpi_initrd_override_find(void *data, size_t size);
+void acpi_initrd_override_find(void *data, size_t size, bool is_phys);
 void acpi_initrd_override_copy(void);
 #else
-static inline void acpi_initrd_override_find(void *data, size_t size) { }
+static inline void acpi_initrd_override_find(void *data, size_t size,
+						 bool is_phys) { }
 static inline void acpi_initrd_override_copy(void) { }
 #endif
 
-- 
1.7.10.4

Re: [PATCH v2 07/20] x86, ACPI: Make acpi_initrd_override_find work with 32bit flat mode

[Tejun Heo]

Hello,

On Sat, Mar 09, 2013 at 10:44:34PM -0800, Yinghai Lu wrote:
> For finding with 32bit, it would be easy to access initrd in 32bit
> flat mode, as we don't need to set page table.
> 
> That is from head_32.S, and microcode updating already use this trick.
> 
> Need to change acpi_initrd_override_find to use phys to access global
> variables.
> 
> Pass is_phys in the function, as we can not use address to decide if it
> is phys or virtual address on 32 bit. Boot loader could load initrd above
> max_low_pfn.
> 
> Don't call printk as it uses global variables, so delay print later
> during copying.
> 
> Change table_sigs to use stack instead, otherwise it is too messy to change
> string array to phys and still keep offset calculating correct.
> That size is about 36x4 bytes, and it is small to settle in stack.
> 
> Also remove "continue" in MARCO to make code more readable.

It'd be nice if the error message can be stored somewhere and then
printed out after the system is in proper address mode if that isn't
too complex to achieve.  If it gets too messy, no need to bother.

Thanks.

-- 
tejun

Re: [PATCH v2 07/20] x86, ACPI: Make acpi_initrd_override_find work with 32bit flat mode

[Yinghai Lu]

On Thu, Apr 4, 2013 at 11:35 AM, Tejun Heo <tj@kernel.org> wrote:
>
> It'd be nice if the error message can be stored somewhere and then
> printed out after the system is in proper address mode if that isn't
> too complex to achieve.  If it gets too messy, no need to bother.

Maybe not necessary. As later during coping, another print out
is added there for successful one.

@@ -670,6 +700,9 @@ void __init acpi_initrd_override_copy(vo
                        break;
                q = early_ioremap(addr, size);
                p = early_ioremap(acpi_tables_addr + total_offset, size);
+               pr_info("%4.4s ACPI table found in initrd
[%#010llx-%#010llx]\n",
+                               ((struct acpi_table_header *)q)->signature,
+                               (u64)addr, (u64)(addr + size - 1));

Thanks

Yinghai

[PATCH v2 08/20] x86, ACPI: Find acpi tables in initrd early from head_32.S/head64.c

[Yinghai Lu]

head64.c could use #PF handler set page table to access initrd before
init mem mapping and initrd relocating.

head_32.S could use 32bit flat mode to access initrd before init mem
mapping initrd relocating.

That make 32bit and 64 bit more consistent.

-v2: use inline function in header file instead according to tj.
     also still need to keep #idef head_32.S to avoid compiling error.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Jacob Shin <jacob.shin@amd.com>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: linux-acpi@vger.kernel.org
---
 arch/x86/include/asm/setup.h |    6 ++++++
 arch/x86/kernel/head64.c     |    2 ++
 arch/x86/kernel/head_32.S    |    4 ++++
 arch/x86/kernel/setup.c      |   30 ++++++++++++++++++++++++++++--
 4 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 4f71d48..6f885b7 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -42,6 +42,12 @@ extern void visws_early_detect(void);
 static inline void visws_early_detect(void) { }
 #endif
 
+#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
+void x86_acpi_override_find(void);
+#else
+static inline void x86_acpi_override_find(void) { }
+#endif
+
 extern unsigned long saved_video_mode;
 
 extern void reserve_standard_io_resources(void);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index c5e403f..a31bc63 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -174,6 +174,8 @@ void __init x86_64_start_kernel(char * real_mode_data)
 	if (console_loglevel == 10)
 		early_printk("Kernel alive\n");
 
+	x86_acpi_override_find();
+
 	clear_page(init_level4_pgt);
 	/* set init_level4_pgt kernel high mapping*/
 	init_level4_pgt[511] = early_level4_pgt[511];
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 73afd11..ca08f0e 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -149,6 +149,10 @@ ENTRY(startup_32)
 	call load_ucode_bsp
 #endif
 
+#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
+	call x86_acpi_override_find
+#endif
+
 /*
  * Initialize page tables.  This creates a PDE and a set of page
  * tables, which are located immediately beyond __brk_base.  The variable
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 16a703f..b067663 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -424,6 +424,34 @@ static void __init reserve_initrd(void)
 }
 #endif /* CONFIG_BLK_DEV_INITRD */
 
+#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
+void __init x86_acpi_override_find(void)
+{
+	unsigned long ramdisk_image, ramdisk_size;
+	unsigned char *p = NULL;
+
+#ifdef CONFIG_X86_32
+	struct boot_params *boot_params_p;
+
+	/*
+	 * 32bit is from head_32.S, and it is 32bit flat mode.
+	 * So need to use phys address to access global variables.
+	 */
+	boot_params_p = (struct boot_params *)__pa_symbol(&boot_params);
+	ramdisk_image = get_ramdisk_image(boot_params_p);
+	ramdisk_size  = get_ramdisk_size(boot_params_p);
+	p = (unsigned char *)ramdisk_image;
+	acpi_initrd_override_find(p, ramdisk_size, true);
+#else
+	ramdisk_image = get_ramdisk_image(&boot_params);
+	ramdisk_size  = get_ramdisk_size(&boot_params);
+	if (ramdisk_image)
+		p = __va(ramdisk_image);
+	acpi_initrd_override_find(p, ramdisk_size, false);
+#endif
+}
+#endif
+
 static void __init parse_setup_data(void)
 {
 	struct setup_data *data;
@@ -1092,8 +1120,6 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_initrd();
 
-	acpi_initrd_override_find((void *)initrd_start,
-					initrd_end - initrd_start, false);
 	acpi_initrd_override_copy();
 
 	reserve_crashkernel();
-- 
1.7.10.4

Re: [PATCH v2 08/20] x86, ACPI: Find acpi tables in initrd early from head_32.S/head64.c

[Pekka Enberg]

On Sun, Mar 10, 2013 at 8:44 AM, Yinghai Lu <yinghai@kernel.org> wrote:
> +void __init x86_acpi_override_find(void)
> +{
> +       unsigned long ramdisk_image, ramdisk_size;
> +       unsigned char *p = NULL;
> +
> +#ifdef CONFIG_X86_32
> +       struct boot_params *boot_params_p;
> +
> +       /*
> +        * 32bit is from head_32.S, and it is 32bit flat mode.
> +        * So need to use phys address to access global variables.
> +        */
> +       boot_params_p = (struct boot_params *)__pa_symbol(&boot_params);
> +       ramdisk_image = get_ramdisk_image(boot_params_p);
> +       ramdisk_size  = get_ramdisk_size(boot_params_p);
> +       p = (unsigned char *)ramdisk_image;
> +       acpi_initrd_override_find(p, ramdisk_size, true);
> +#else
> +       ramdisk_image = get_ramdisk_image(&boot_params);
> +       ramdisk_size  = get_ramdisk_size(&boot_params);
> +       if (ramdisk_image)
> +               p = __va(ramdisk_image);
> +       acpi_initrd_override_find(p, ramdisk_size, false);
> +#endif
> +}
> +#endif

What is preventing us from making the 64-bit variant also work in flat
mode to make the code consistent and not hiding the differences under
the rug? What am I missing here?

                        Pekka

Re: [PATCH v2 08/20] x86, ACPI: Find acpi tables in initrd early from head_32.S/head64.c

[Yinghai Lu]

On Sun, Mar 10, 2013 at 3:25 AM, Pekka Enberg <penberg@kernel.org> wrote:
>
> What is preventing us from making the 64-bit variant also work in flat
> mode to make the code consistent and not hiding the differences under
> the rug? What am I missing here?

Boot loader could start kernel from 64bit directly from
from arch/x86/boot/compressed/head_64.s::startup_64.

initrd can be loaded by 64bit bootloader above 4G.

So we even switch back to 32bit flat mode, we still can not access those initrd
directly.

Thanks

Yinghai

Re: [PATCH v2 08/20] x86, ACPI: Find acpi tables in initrd early from head_32.S/head64.c

[H. Peter Anvin]

There is no 64-bit flat mode.  We use a #PF handler to emulate one by creating page tables on the fly.

Yinghai Lu <yinghai@kernel.org> wrote:

>On Sun, Mar 10, 2013 at 3:25 AM, Pekka Enberg <penberg@kernel.org>
>wrote:
>>
>> What is preventing us from making the 64-bit variant also work in
>flat
>> mode to make the code consistent and not hiding the differences under
>> the rug? What am I missing here?
>
>Boot loader could start kernel from 64bit directly from
>from arch/x86/boot/compressed/head_64.s::startup_64.
>
>initrd can be loaded by 64bit bootloader above 4G.
>
>So we even switch back to 32bit flat mode, we still can not access
>those initrd
>directly.
>
>Thanks
>
>Yinghai

-- 
Sent from my mobile phone. Please excuse brevity and lack of formatting.

Re: [PATCH v2 08/20] x86, ACPI: Find acpi tables in initrd early from head_32.S/head64.c

[H. Peter Anvin]

On 03/10/2013 03:25 AM, Pekka Enberg wrote:
> 
> What is preventing us from making the 64-bit variant also work in flat
> mode to make the code consistent and not hiding the differences under
> the rug? What am I missing here?
> 

There is no such thing as "flat mode" in 64-bit mode.  We use a #PF
handler to emulate it, but we add the normal kernel offset when doing so.

In the 32-bit case the problem is that the kernel offset is not
available while in linear mode.  It *could* be created using segment
bases, but that would break Xen, I'm pretty sure, and possibly some
other too-clever environments.

	-hpa

[PATCH v2 16/20] x86, ACPI, numa, ia64: split SLIT handling out

[Yinghai Lu]

We need to handle slit later, as it need to allocate buffer for distance
matrix. Also we do not need SLIT info before init_mem_mapping.

So move SLIT parsing later.

x86_acpi_numa_init become x86_acpi_numa_init_srat/x86_acpi_numa_init_slit.

It should not break ia64 by replacing acpi_numa_init with
acpi_numa_init_srat/acpi_numa_init_slit/acpi_num_arch_fixup.

-v2: Change name to acpi_numa_init_srat/acpi_numa_init_slit according tj.
     remove the reset_numa_distance() in numa_init(), as get we only set
     distance in slit handling.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: linux-acpi@vger.kernel.org
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: linux-ia64@vger.kernel.org
---
 arch/ia64/kernel/setup.c    |    4 +++-
 arch/x86/include/asm/acpi.h |    3 ++-
 arch/x86/mm/numa.c          |   14 ++++++++++++--
 arch/x86/mm/srat.c          |   11 +++++++----
 drivers/acpi/numa.c         |   13 +++++++------
 include/linux/acpi.h        |    3 ++-
 6 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 2029cc0..6a2efb5 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -558,7 +558,9 @@ setup_arch (char **cmdline_p)
 	acpi_table_init();
 	early_acpi_boot_init();
 # ifdef CONFIG_ACPI_NUMA
-	acpi_numa_init();
+	acpi_numa_init_srat();
+	acpi_numa_init_slit();
+	acpi_numa_arch_fixup();
 #  ifdef CONFIG_ACPI_HOTPLUG_CPU
 	prefill_possible_map();
 #  endif
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index b31bf97..651db0b 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -178,7 +178,8 @@ static inline void disable_acpi(void) { }
 
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
-extern int x86_acpi_numa_init(void);
+int x86_acpi_numa_init_srat(void);
+void x86_acpi_numa_init_slit(void);
 #endif /* CONFIG_ACPI_NUMA */
 
 #define acpi_unlazy_tlb(x)	leave_mm(x)
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 90fd123..182e085 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -598,7 +598,6 @@ static int __init numa_init(int (*init_func)(void))
 
 	nodes_clear(numa_nodes_parsed);
 	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
-	numa_reset_distance();
 
 	ret = init_func();
 	if (ret < 0)
@@ -636,6 +635,10 @@ static int __init dummy_numa_init(void)
 	return 0;
 }
 
+#ifdef CONFIG_ACPI_NUMA
+static bool srat_used __initdata;
+#endif
+
 /**
  * x86_numa_init - Initialize NUMA
  *
@@ -651,8 +654,10 @@ static void __init early_x86_numa_init(void)
 			return;
 #endif
 #ifdef CONFIG_ACPI_NUMA
-		if (!numa_init(x86_acpi_numa_init))
+		if (!numa_init(x86_acpi_numa_init_srat)) {
+			srat_used = true;
 			return;
+		}
 #endif
 #ifdef CONFIG_AMD_NUMA
 		if (!numa_init(amd_numa_init))
@@ -670,6 +675,11 @@ void __init x86_numa_init(void)
 
 	early_x86_numa_init();
 
+#ifdef CONFIG_ACPI_NUMA
+	if (srat_used)
+		x86_acpi_numa_init_slit();
+#endif
+
 	numa_emulation(&numa_meminfo, numa_distance_cnt);
 
 	node_possible_map = numa_nodes_parsed;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index cdd0da9..443f9ef 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -185,14 +185,17 @@ out_err:
 	return -1;
 }
 
-void __init acpi_numa_arch_fixup(void) {}
-
-int __init x86_acpi_numa_init(void)
+int __init x86_acpi_numa_init_srat(void)
 {
 	int ret;
 
-	ret = acpi_numa_init();
+	ret = acpi_numa_init_srat();
 	if (ret < 0)
 		return ret;
 	return srat_disabled() ? -EINVAL : 0;
 }
+
+void __init x86_acpi_numa_init_slit(void)
+{
+	acpi_numa_init_slit();
+}
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 33e609f..6460db4 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -282,7 +282,7 @@ acpi_table_parse_srat(enum acpi_srat_type id,
 					    handler, max_entries);
 }
 
-int __init acpi_numa_init(void)
+int __init acpi_numa_init_srat(void)
 {
 	int cnt = 0;
 
@@ -303,11 +303,6 @@ int __init acpi_numa_init(void)
 					    NR_NODE_MEMBLKS);
 	}
 
-	/* SLIT: System Locality Information Table */
-	acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit);
-
-	acpi_numa_arch_fixup();
-
 	if (cnt < 0)
 		return cnt;
 	else if (!parsed_numa_memblks)
@@ -315,6 +310,12 @@ int __init acpi_numa_init(void)
 	return 0;
 }
 
+void __init acpi_numa_init_slit(void)
+{
+	/* SLIT: System Locality Information Table */
+	acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit);
+}
+
 int acpi_get_pxm(acpi_handle h)
 {
 	unsigned long long pxm;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4b943e6..4a78235 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -85,7 +85,8 @@ int early_acpi_boot_init(void);
 int acpi_boot_init (void);
 void acpi_boot_table_init (void);
 int acpi_mps_check (void);
-int acpi_numa_init (void);
+int acpi_numa_init_srat(void);
+void acpi_numa_init_slit(void);
 
 int acpi_table_init (void);
 int acpi_table_parse(char *id, acpi_tbl_table_handler handler);
-- 
1.7.10.4