[RFC] - Mapping ACPI tables as CACHED

[Jack Steiner <steiner@sgi.com>]

I'd like feedback on the following performance problem &
suggestions for a proper solution.


Large SGI UV systems (3072p, 5TB) take a long time to boot. A significant
part of the boot time is scanning ACPI tables. ACPI tables on UV systems
are located in RAM memory that is physically attached to node 0.

User programs (ex., acpidump) read the ACPI tables by mapping them thru
/dev/mem.  Although mmap tries to map the tables as CACHED, there are
existing kernel UNCACHED mapping that conflict and the tables end up as
being mapped UNCACHED.  (See the call to track_pfn_vma_new() in
remap_pfn_range()).

Much of the access is to small fields (bytes (checksums), shorts, etc).
Late in boot, there is significant scanning of the ACPI tables that take
place from nodes other than zero. Since the tables are not cached, each
reference accesses physical memory that is attached to remote nodes. These
memory requests must cross the numalink interconnect which adds several
hundred nsec to each access. This slows the boot process.  Access from
node 0, although faster, is still very slow.



The following experimental patch changes the kernel mapping for ACPI tables
to CACHED. This eliminates the page attibute conflict & allows users to map
the tables CACHEABLE. This significantly speeds up boot:

	38 minutes without the patch
	27 minutes with the patch
		~30% improvement

Time to run ACPIDUMP on a large system:
	527 seconds without the patch
	  8 seconds with the patch


I don't know if the patch in it's current form is the correct solution. I'm
interested in feedback on how this should be solved. I expect there
are issues on other platforms so for now, the patch uses x86_platform_ops
to change mappings only on UV platforms (I'm paranoid :-).

I also need to experiment with early_ioremap'ing of the ACPI tables. I suspect
this is also mapped UNCACHED. There may be additional improvements if this
could be mapped CACHED. However, the potential performance gain is much
less since these references all occur from node 0.



Signed-off-by: Jack Steiner <steiner@sgi.com>


---
 arch/x86/include/asm/x86_init.h    |    2 ++
 arch/x86/kernel/apic/x2apic_uv_x.c |    6 ++++++
 arch/x86/kernel/x86_init.c         |    3 +++
 drivers/acpi/osl.c                 |   12 +++++++++---
 4 files changed, 20 insertions(+), 3 deletions(-)

Index: linux/arch/x86/include/asm/x86_init.h
===================================================================
--- linux.orig/arch/x86/include/asm/x86_init.h	2010-07-21 16:53:30.226241589 -0500
+++ linux/arch/x86/include/asm/x86_init.h	2010-07-21 16:57:46.614872338 -0500
@@ -113,6 +113,7 @@ struct x86_cpuinit_ops {
 
 /**
  * struct x86_platform_ops - platform specific runtime functions
+ * @is_wb_acpi_tables		E820 ACPI table are in WB memory
  * @is_untracked_pat_range	exclude from PAT logic
  * @calibrate_tsc:		calibrate TSC
  * @get_wallclock:		get time from HW clock like RTC etc.
@@ -120,6 +121,7 @@ struct x86_cpuinit_ops {
  * @nmi_init			enable NMI on cpus
  */
 struct x86_platform_ops {
+	int (*is_wb_acpi_tables)(void);
 	int (*is_untracked_pat_range)(u64 start, u64 end);
 	unsigned long (*calibrate_tsc)(void);
 	unsigned long (*get_wallclock)(void);
Index: linux/arch/x86/kernel/apic/x2apic_uv_x.c
===================================================================
--- linux.orig/arch/x86/kernel/apic/x2apic_uv_x.c	2010-07-21 16:53:30.226241589 -0500
+++ linux/arch/x86/kernel/apic/x2apic_uv_x.c	2010-07-21 16:54:46.358866486 -0500
@@ -58,6 +58,11 @@ static int uv_is_untracked_pat_range(u64
 	return is_ISA_range(start, end) || is_GRU_range(start, end);
 }
 
+static int uv_is_wb_acpi_tables(void)
+{
+	return 1;
+}
+
 static int early_get_nodeid(void)
 {
 	union uvh_node_id_u node_id;
@@ -81,6 +86,7 @@ static int __init uv_acpi_madt_oem_check
 		nodeid = early_get_nodeid();
 		x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
 		x86_platform.nmi_init = uv_nmi_init;
+		x86_platform.is_wb_acpi_tables = uv_is_wb_acpi_tables;
 		if (!strcmp(oem_table_id, "UVL"))
 			uv_system_type = UV_LEGACY_APIC;
 		else if (!strcmp(oem_table_id, "UVX"))
Index: linux/arch/x86/kernel/x86_init.c
===================================================================
--- linux.orig/arch/x86/kernel/x86_init.c	2010-07-21 16:53:30.226241589 -0500
+++ linux/arch/x86/kernel/x86_init.c	2010-07-21 16:58:17.106240870 -0500
@@ -71,7 +71,10 @@ struct x86_cpuinit_ops x86_cpuinit __cpu
 
 static void default_nmi_init(void) { };
 
+static int default_wb_acpi_tables(void) {return 0;}
+
 struct x86_platform_ops x86_platform = {
+	.is_wb_acpi_tables		= default_wb_acpi_tables,
 	.is_untracked_pat_range		= default_is_untracked_pat_range,
 	.calibrate_tsc			= native_calibrate_tsc,
 	.get_wallclock			= mach_get_cmos_time,
Index: linux/drivers/acpi/osl.c
===================================================================
--- linux.orig/drivers/acpi/osl.c	2010-07-21 16:53:30.226241589 -0500
+++ linux/drivers/acpi/osl.c	2010-07-21 17:58:20.370414172 -0500
@@ -293,12 +293,18 @@ acpi_os_map_memory(acpi_physical_address
 		printk(KERN_ERR PREFIX "Cannot map memory that high\n");
 		return NULL;
 	}
-	if (acpi_gbl_permanent_mmap)
+	if (acpi_gbl_permanent_mmap) {
 		/*
 		* ioremap checks to ensure this is in reserved space
 		*/
-		return ioremap((unsigned long)phys, size);
-	else
+		if (x86_platform.is_wb_acpi_tables() &&
+				(e820_all_mapped(phys, phys + size, E820_RAM) ||
+				e820_all_mapped(phys, phys + size, E820_ACPI) ||
+				e820_all_mapped(phys, phys + size, E820_NVS)))
+			return ioremap_cache((unsigned long)phys, size);
+		else
+			return ioremap((unsigned long)phys, size);
+	} else
 		return __acpi_map_table((unsigned long)phys, size);
 }
 EXPORT_SYMBOL_GPL(acpi_os_map_memory);