On Fri, Mar 23, 2012 at 1:54 PM, Yinghai Lu <yinghai@xxxxxxxxxx> wrote:
> On Fri, Mar 23, 2012 at 7:29 AM, Thomas Renninger <trenn@xxxxxxx> wrote:
>> Details can be found in:
>> Documentation/acpi/initrd_table_override.txt
>>
>> Additional dmesg output of a booted system with
>> FACP (FADT), DSDT and SSDT (the 9th dynamically loaded one)
>> tables overridden (with ### marked comments):
>>
>> ### ACPI tables found glued to initrd
>> DSDT ACPI table found in initrd - size: 16234
>> FACP ACPI table found in initrd - size: 116
>> SSDT ACPI table found in initrd - size: 334
>> ### Re-printed e820 map via e820_update() with additionally created
>> ### ACPI data section at 0xcff55000 where the ACPI tables passed via
>> ### initrd where copied to
>> modified physical RAM map:
>> ...
>> ### New ACPI data section:
>> modified: 00000000cff55000 - 00000000cff5912c (ACPI data)
>> ### BIOS e820 provided ACPI data section:
>> modified: 00000000cff60000 - 00000000cff69000 (ACPI data)
>> ...
>> ### Total size of all ACPI tables glued to initrd
>> ### The address is initrd_start which gets updated to
>> ### initrd_start = initrd_start + "size of all ACPI tables glued to initrd"
>> Found acpi tables of size: 16684 at 0xffff8800374c4000
>>
>> Disabling lock debugging due to kernel taint
>> ### initrd provided FACP and DSDT tables are used instead of BIOS provided ones
>> ACPI: FACP @ 0x00000000cff68dd8 Phys table override, replaced with:
>> ACPI: FACP 00000000cff58f6a 00074 (v01 INTEL TUMWATER 06040000 PTL 00000003)
>> ACPI: DSDT @ 0x00000000cff649d4 Phys table override, replaced with:
>> ACPI: DSDT 00000000cff55000 04404 (v01 Intel BLAKFORD 06040000 MSFT 0100000E)
>> ...
>> ### Much later, the 9th (/sys/firmware/acpi/table/dynamic/SSDT9) dynamically
>> ### loaded ACPI table matches and gets overridden:
>> ACPI: SSDT @ 0x00000000cff64824 Phys table override, replaced with:
>> ACPI: SSDT 00000000cff58fde 0014E (v01 PmRef Cpu7Ist 00003000 INTL 20110316)
>> ACPI: Dynamic OEM Table Load:
>> ACPI: SSDT (null) 0014E (v01 PmRef Cpu7Ist 00003000 INTL 20110316)
>> ...
>>
>> If the initrd does not start with a valid ACPI table signature or the ACPI
>> table's checksum is wrong, there is no functional change.
updated it a little bit to remove 2 #ifdef. please check attached.
Yinghai
From: Thomas Renninger <trenn@xxxxxxx>
Cc: eric.piel@xxxxxxxxxxxxxxxx, vojcek@xxxxxxx, dsdt@xxxxxxxxxxx,
Thomas Renninger <trenn@xxxxxxx>, linux-acpi@xxxxxxxxxxxxxxx,
linux-kernel@xxxxxxxxxxxxxxx, x86@xxxxxxxxxx,
Lin Ming <ming.m.lin@xxxxxxxxx>, lenb@xxxxxxxxxx,
robert.moore@xxxxxxxxx, hpa@xxxxxxxxx
Subject: [PATCH] ACPI: Implement overriding of arbitrary ACPI tables via initrd
Date: Fri, 23 Mar 2012 15:29:44 +0100
Message-Id: <1332512984-79664-1-git-send-email-trenn@xxxxxxx>
Details can be found in:
Documentation/acpi/initrd_table_override.txt
Additional dmesg output of a booted system with
FACP (FADT), DSDT and SSDT (the 9th dynamically loaded one)
tables overridden (with ### marked comments):
### ACPI tables found glued to initrd
DSDT ACPI table found in initrd - size: 16234
FACP ACPI table found in initrd - size: 116
SSDT ACPI table found in initrd - size: 334
### Re-printed e820 map via e820_update() with additionally created
### ACPI data section at 0xcff55000 where the ACPI tables passed via
### initrd where copied to
modified physical RAM map:
...
### New ACPI data section:
modified: 00000000cff55000 - 00000000cff5912c (ACPI data)
### BIOS e820 provided ACPI data section:
modified: 00000000cff60000 - 00000000cff69000 (ACPI data)
...
### Total size of all ACPI tables glued to initrd
### The address is initrd_start which gets updated to
### initrd_start = initrd_start + "size of all ACPI tables glued to initrd"
Found acpi tables of size: 16684 at 0xffff8800374c4000
Disabling lock debugging due to kernel taint
### initrd provided FACP and DSDT tables are used instead of BIOS provided ones
ACPI: FACP @ 0x00000000cff68dd8 Phys table override, replaced with:
ACPI: FACP 00000000cff58f6a 00074 (v01 INTEL TUMWATER 06040000 PTL 00000003)
ACPI: DSDT @ 0x00000000cff649d4 Phys table override, replaced with:
ACPI: DSDT 00000000cff55000 04404 (v01 Intel BLAKFORD 06040000 MSFT 0100000E)
...
### Much later, the 9th (/sys/firmware/acpi/table/dynamic/SSDT9) dynamically
### loaded ACPI table matches and gets overridden:
ACPI: SSDT @ 0x00000000cff64824 Phys table override, replaced with:
ACPI: SSDT 00000000cff58fde 0014E (v01 PmRef Cpu7Ist 00003000 INTL 20110316)
ACPI: Dynamic OEM Table Load:
ACPI: SSDT (null) 0014E (v01 PmRef Cpu7Ist 00003000 INTL 20110316)
...
If the initrd does not start with a valid ACPI table signature or the ACPI
table's checksum is wrong, there is no functional change.
-v2: remove 2 #ifdef.
Signed-off-by: Thomas Renninger <trenn@xxxxxxx>
CC: linux-acpi@xxxxxxxxxxxxxxx
CC: linux-kernel@xxxxxxxxxxxxxxx
CC: x86@xxxxxxxxxx
CC: Lin Ming <ming.m.lin@xxxxxxxxx>
CC: lenb@xxxxxxxxxx
CC: robert.moore@xxxxxxxxx
CC: hpa@xxxxxxxxx
---
Documentation/acpi/initrd_table_override.txt | 110 +++++++++++++++++++++
arch/x86/kernel/e820.c | 24 ++++
arch/x86/kernel/setup.c | 15 ++
arch/x86/mm/init.c | 4
drivers/acpi/Kconfig | 10 +
drivers/acpi/osl.c | 136 ++++++++++++++++++++++++++-
include/linux/acpi.h | 9 +
include/linux/initrd.h | 5
8 files changed, 304 insertions(+), 9 deletions(-)
create mode 100644 Documentation/acpi/initrd_table_override.txt
Index: linux-2.6/Documentation/acpi/initrd_table_override.txt
===================================================================
--- /dev/null
+++ linux-2.6/Documentation/acpi/initrd_table_override.txt
@@ -0,0 +1,110 @@
+Overriding ACPI tables via initrd
+=================================
+
+1) Introduction (What is this about)
+2) What is this for
+3) How does it work
+4) References (Where to retrieve userspace tools)
+
+1) What is this about
+---------------------
+
+If ACPI_INITRD_TABLE_OVERRIDE compile option is true, it is possible to
+override nearly any ACPI table provided by the BIOS with an instrumented,
+modified one.
+
+Up to 10 arbitrary ACPI tables can be passed.
+For a full list of ACPI tables that can be overridden, take a look at
+the char *table_sigs[MAX_ACPI_SIGNATURE]; definition in drivers/acpi/osl.c
+All ACPI tables iasl (Intel's ACPI compiler and disassembler) knows should
+be overridable, except:
+ - ACPI_SIG_RSDP (has a signature of 6 bytes)
+ - ACPI_SIG_FACS (does not have an ordinary ACPI table header)
+Both could get implemented as well.
+
+
+2) What is this for
+-------------------
+
+Please keep in mind that this is a debug option.
+ACPI tables should not get overridden for productive use.
+If BIOS ACPI tables are overridden the kernel will get tainted with the
+TAINT_OVERRIDDEN_ACPI_TABLE flag.
+Complain to your platform/BIOS vendor if you find a bug which is that sever
+that a workaround is not accepted in the Linus kernel.
+
+Still, it can and should be enabled in any kernel, because:
+ - There is no functional change with not instrumented initrds
+ - It provides a powerful feature to easily debug and test ACPI BIOS table
+ compatibility with the Linux kernel.
+
+Until now it was only possible to override the DSDT by compiling it into
+the kernel. This is a nightmare when trying to work on ACPI related bugs
+and a lot bugs got stuck because of that.
+Even for people with enough kernel knowledge, building a kernel to try out
+things is very time consuming. Also people may have to browse and modify the
+ACPI interpreter code to find a possible BIOS bug. With this feature, people
+can correct the ACPI tables and try out quickly whether this is the root cause
+that needs to get addressed in the kernel.
+
+This could even ease up testing for BIOS providers who could flush their BIOS
+to test, but overriding table via initrd is much easier and quicker.
+For example one could prepare different initrds overriding NUMA tables with
+different affinity settings. Set up a script, let the machine reboot and
+run tests over night and one can get a picture how these settings influence
+the Linux kernel and which values are best.
+
+People can instrument the dynamic ACPI (ASL) code (for example with debug
+statements showing up in syslog when the ACPI code is processed, etc.),
+to better understand BIOS to OS interfaces, to hunt down ACPI BIOS code related
+bugs quickly or to easier develop ACPI based drivers.
+
+Intstrumenting ACPI code in SSDTs is now much easier. Before, one had to copy
+all SSDTs into the DSDT to compile it into the kernel for testing
+(because only DSDT could get overridden). That's what the acpi_no_auto_ssdt
+boot param is for: the BIOS provided SSDTs are ignored and all have to get
+copied into the DSDT, complicated and time consuming.
+
+Much more use cases, depending on which ACPI parts you are working on...
+
+
+3) How does it work
+-------------------
+
+# Extract the machine's ACPI tables:
+acpidump >acpidump
+acpixtract -a acpidump
+# Disassemble, modify and recompile them:
+iasl -d *.dat
+# For example add this statement into a _PRT (PCI Routing Table) function
+# of the DSDT:
+Store("Hello World", debug)
+iasl -sa *.dsl
+# glue them together with the initrd. ACPI tables go first, original initrd
+# goes on top:
+cat TBL1.dat >>instrumented_initrd
+cat TBL2.dat >>instrumented_initrd
+cat TBL3.dat >>instrumented_initrd
+cat /boot/initrd >>instrumented_initrd
+# reboot with increased acpi debug level, e.g. boot params:
+acpi.debug_level=0x2 acpi.debug_layer=0xFFFFFFFF
+# and check your syslog:
+[ 1.268089] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
+[ 1.272091] [ACPI Debug] String [0x0B] "HELLO WORLD"
+
+iasl is able to disassemble and recompile quite a lot different,
+also static ACPI tables.
+
+4) Where to retrieve userspace tools
+------------------------------------
+
+iasl and acpixtract are part of Intel's ACPICA project:
+http://acpica.org/
+and should be packaged by distributions (for example in the acpica package
+on SUSE).
+
+acpidump can be found in Len Browns pmtools:
+ftp://kernel.org/pub/linux/kernel/people/lenb/acpi/utils/pmtools/acpidump
+This tool is also part of the acpica package on SUSE.
+Alternatively used ACPI tables can be retrieved via sysfs in latest kernels:
+/sys/firmware/acpi/tables
Index: linux-2.6/arch/x86/kernel/setup.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/setup.c
+++ linux-2.6/arch/x86/kernel/setup.c
@@ -412,12 +412,19 @@ static void __init reserve_initrd(void)
*/
initrd_start = ramdisk_image + PAGE_OFFSET;
initrd_end = initrd_start + ramdisk_size;
- return;
+ } else {
+ relocate_initrd();
+ memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
}
- relocate_initrd();
-
- memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
+ acpi_initrd_offset = acpi_initrd_table_override((void *)initrd_start,
+ (void *)initrd_end);
+ if (!acpi_initrd_offset)
+ return;
+ printk(KERN_INFO "Found acpi tables of size: %lu at 0x%lx\n",
+ acpi_initrd_offset, initrd_start);
+ initrd_start += acpi_initrd_offset;
+ return;
}
#else
static void __init reserve_initrd(void)
Index: linux-2.6/arch/x86/mm/init.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init.c
+++ linux-2.6/arch/x86/mm/init.c
@@ -407,7 +407,9 @@ void free_initrd_mem(unsigned long start
* - relocate_initrd()
* So here We can do PAGE_ALIGN() safely to get partial page to be freed
*/
- free_init_pages("initrd memory", start, PAGE_ALIGN(end));
+ /* need to offset back acpi tables in acpi tables */
+ free_init_pages("initrd memory", start - acpi_initrd_offset,
+ PAGE_ALIGN(end));
}
#endif
Index: linux-2.6/drivers/acpi/Kconfig
===================================================================
--- linux-2.6.orig/drivers/acpi/Kconfig
+++ linux-2.6/drivers/acpi/Kconfig
@@ -261,6 +261,16 @@ config ACPI_CUSTOM_DSDT
bool
default ACPI_CUSTOM_DSDT_FILE != ""
+config ACPI_INITRD_TABLE_OVERRIDE
+ bool
+ depends on X86
+ default y
+ help
+ This option provides functionality to override arbitrary ACPI tables
+ via initrd. No functional change if no ACPI tables are glued to the
+ initrd, therefore it's safe to say Y.
+ See Documentation/acpi/initrd_table_override.txt for details
+
config ACPI_BLACKLIST_YEAR
int "Disable ACPI for systems before Jan 1st this year" if X86_32
default 0
Index: linux-2.6/drivers/acpi/osl.c
===================================================================
--- linux-2.6.orig/drivers/acpi/osl.c
+++ linux-2.6/drivers/acpi/osl.c
@@ -533,6 +533,92 @@ acpi_os_predefined_override(const struct
return AE_OK;
}
+#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
+
+#define ACPI_OVERRIDE_TABLES 10
+
+static unsigned long acpi_table_override_offset[ACPI_OVERRIDE_TABLES];
+static u64 acpi_tables_inram;
+
+unsigned long acpi_initrd_offset;
+
+/* Copied from acpica/tbutils.c:acpi_tb_checksum() */
+u8 __init acpi_table_checksum(u8 *buffer, u32 length)
+{
+ u8 sum = 0;
+ u8 *end = buffer + length;
+
+ while (buffer < end)
+ sum = (u8) (sum + *(buffer++));
+ return sum;
+}
+
+/* All but ACPI_SIG_RSDP and ACPI_SIG_FACS: */
+#define MAX_ACPI_SIGNATURE 35
+static const char *table_sigs[MAX_ACPI_SIGNATURE] = {
+ 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 };
+
+u64 __weak early_alloc_ram_for_acpi(u64 size, u64 align);
+int __init acpi_initrd_table_override(void *start_addr, void *end_addr)
+{
+ int table_nr, sig;
+ unsigned long offset = 0, max_len = end_addr - start_addr;
+ char *p;
+
+ for (table_nr = 0; table_nr < ACPI_OVERRIDE_TABLES; table_nr++) {
+ struct acpi_table_header *table;
+ if (max_len < offset + sizeof(struct acpi_table_header)) {
+ WARN_ON(1);
+ return 0;
+ }
+ table = start_addr + offset;
+
+ for (sig = 0; sig < MAX_ACPI_SIGNATURE; sig++)
+ if (!memcmp(table->signature, table_sigs[sig], 4))
+ break;
+
+ if (sig >= MAX_ACPI_SIGNATURE)
+ break;
+
+ if (max_len < offset + table->length) {
+ WARN_ON(1);
+ return 0;
+ }
+
+ if (acpi_table_checksum(start_addr + offset, table->length)) {
+ WARN(1, "%4.4s has invalid checksum\n",
+ table->signature);
+ continue;
+ }
+ printk(KERN_INFO "%4.4s ACPI table found in initrd"
+ " - size: %d\n", table->signature, table->length);
+
+ offset += table->length;
+ acpi_table_override_offset[table_nr] = offset;
+ }
+ if (!offset)
+ return 0;
+
+ acpi_tables_inram = early_alloc_ram_for_acpi(offset, PAGE_SIZE);
+
+ if (!acpi_tables_inram)
+ panic("Cannot find place for ACPI override tables\n");
+
+ p = early_ioremap(acpi_tables_inram, offset);
+ memcpy(p, start_addr, offset);
+ early_iounmap(p, offset);
+ return offset;
+}
+#endif
+
acpi_status
acpi_os_table_override(struct acpi_table_header * existing_table,
struct acpi_table_header ** new_table)
@@ -558,13 +644,55 @@ acpi_os_table_override(struct acpi_table
acpi_status
acpi_os_physical_table_override(struct acpi_table_header *existing_table,
- acpi_physical_address * new_address,
- u32 *new_table_length)
+ acpi_physical_address *address,
+ u32 *table_length)
{
- return AE_SUPPORT;
+#ifndef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
+ *table_length = 0;
+ *address = 0;
+ return AE_OK;
+#else
+ int table_nr = 0;
+ *table_length = 0;
+ *address = 0;
+ for (; table_nr < ACPI_OVERRIDE_TABLES &&
+ acpi_table_override_offset[table_nr]; table_nr++) {
+ int table_offset;
+ int table_len;
+ struct acpi_table_header *table;
+
+ if (table_nr == 0)
+ table_offset = 0;
+ else
+ table_offset = acpi_table_override_offset[table_nr - 1];
+
+ table_len = acpi_table_override_offset[table_nr] - table_offset;
+
+ table = acpi_os_map_memory(acpi_tables_inram + table_offset,
+ table_len);
+
+ if (memcmp(existing_table->signature, table->signature, 4)) {
+ acpi_os_unmap_memory(table, table_len);
+ continue;
+ }
+
+ /* Only override tables with matching oem id */
+ if (memcmp(table->oem_table_id, existing_table->oem_table_id,
+ ACPI_OEM_TABLE_ID_SIZE)) {
+ acpi_os_unmap_memory(table, table_len);
+ continue;
+ }
+
+ acpi_os_unmap_memory(table, table_len);
+ *address = acpi_tables_inram + table_offset;
+ *table_length = table_len;
+ add_taint(TAINT_OVERRIDDEN_ACPI_TABLE);
+ break;
+ }
+ return AE_OK;
+#endif
}
-
static irqreturn_t acpi_irq(int irq, void *dev_id)
{
u32 handled;
Index: linux-2.6/include/linux/acpi.h
===================================================================
--- linux-2.6.orig/include/linux/acpi.h
+++ linux-2.6/include/linux/acpi.h
@@ -82,6 +82,15 @@ struct acpi_subtable_proc {
int count;
};
+#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
+int acpi_initrd_table_override(void *start_addr, void *end_addr);
+#else
+static inline int acpi_initrd_table_override(void *start_addr, void *end_addr)
+{
+ return 0;
+}
+#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);
Index: linux-2.6/include/linux/initrd.h
===================================================================
--- linux-2.6.orig/include/linux/initrd.h
+++ linux-2.6/include/linux/initrd.h
@@ -16,5 +16,10 @@ extern int initrd_below_start_ok;
/* free_initrd_mem always gets called with the next two as arguments.. */
extern unsigned long initrd_start, initrd_end;
extern void free_initrd_mem(unsigned long, unsigned long);
+#ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
+extern unsigned long acpi_initrd_offset;
+#else
+#define acpi_initrd_offset 0
+#endif
extern unsigned int real_root_dev;
Index: linux-2.6/arch/x86/kernel/e820.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/e820.c
+++ linux-2.6/arch/x86/kernel/e820.c
@@ -746,6 +746,30 @@ u64 __init early_reserve_e820(u64 size,
return addr;
}
+u64 early_alloc_ram_for_acpi(u64 size, u64 align)
+{
+ u64 addr = memblock_find_in_range(0, max_low_pfn_mapped << PAGE_SHIFT,
+ size, align);
+
+ if (!addr)
+ return 0;
+
+ /*
+ * Only calling e820_add_reserve does not work and the
+ * tables are invalid (memory got used) later.
+ * memblock_x86_reserve_range works as expected and the tables
+ * won't get modified. But it's not enough because ioremap will
+ * complain later (used by acpi_os_map_memory) that the pages
+ * that should get mapped are not marked "reserved".
+ * Both memblock_x86_reserve_range and e820_add_region works fine.
+ */
+ memblock_reserve(addr, addr + size);
+ e820_update_range(addr, size, E820_RAM, E820_ACPI);
+ update_e820();
+
+ return addr;
+}
+
#ifdef CONFIG_X86_32
# ifdef CONFIG_X86_PAE
# define MAX_ARCH_PFN (1ULL<<(36-PAGE_SHIFT))
