From: Andi Kleen <ak@suse.de>
To: rientjes@google.com, ak@suse.de, lenb@kernel.org,
patches@x86-64.org, linux-kernel@vger.kernel.org
Subject: [PATCH] [45/58] x86_64: fake pxm-to-node mapping for fake numa
Date: Thu, 19 Jul 2007 11:55:31 +0200 (CEST) [thread overview]
Message-ID: <20070719095531.C4DFE14E05@wotan.suse.de> (raw)
In-Reply-To: <200707191154.642492000@suse.de>
From: David Rientjes <rientjes@google.com>
For NUMA emulation, our SLIT should represent the true NUMA topology of the
system but our proximity domain to node ID mapping needs to reflect the
emulated state.
When NUMA emulation has successfully setup fake nodes on the system, a new
function, acpi_fake_nodes() is called. This function determines the proximity
domain (_PXM) for each true node found on the system. It then finds which
emulated nodes have been allocated on this true node as determined by its
starting address. The node ID to PXM mapping is changed so that each fake
node ID points to the PXM of the true node that it is located on.
If the machine failed to register a SLIT, then we assume there is no special
requirement for emulated node affinity so we use the default LOCAL_DISTANCE,
which is newly exported to this code, as our measurement if the emulated nodes
appear in the same PXM. Otherwise, we use REMOTE_DISTANCE.
PXM_INVAL and NID_INVAL are also exported to the ACPI header file so that we
can compare node_to_pxm() results in generic code (in this case, the SRAT
code).
Cc: Andi Kleen <ak@suse.de>
Cc: Len Brown <lenb@kernel.org>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andi Kleen <ak@suse.de>
---
arch/x86_64/mm/numa.c | 1
arch/x86_64/mm/srat.c | 76 ++++++++++++++++++++++++++++++++++++++++++++--
drivers/acpi/numa.c | 11 ++++--
include/acpi/acpi_numa.h | 1
include/asm-x86_64/acpi.h | 11 ++++++
include/linux/acpi.h | 3 +
6 files changed, 96 insertions(+), 7 deletions(-)
Index: linux/arch/x86_64/mm/numa.c
===================================================================
--- linux.orig/arch/x86_64/mm/numa.c
+++ linux/arch/x86_64/mm/numa.c
@@ -484,6 +484,7 @@ out:
nodes[i].end >> PAGE_SHIFT);
setup_node_bootmem(i, nodes[i].start, nodes[i].end);
}
+ acpi_fake_nodes(nodes, num_nodes);
numa_init_array();
return 0;
}
Index: linux/arch/x86_64/mm/srat.c
===================================================================
--- linux.orig/arch/x86_64/mm/srat.c
+++ linux/arch/x86_64/mm/srat.c
@@ -350,7 +350,7 @@ acpi_numa_memory_affinity_init(struct ac
/* Sanity check to catch more bad SRATs (they are amazingly common).
Make sure the PXMs cover all memory. */
-static int nodes_cover_memory(void)
+static int __init nodes_cover_memory(const struct bootnode *nodes)
{
int i;
unsigned long pxmram, e820ram;
@@ -406,7 +406,7 @@ int __init acpi_scan_nodes(unsigned long
}
}
- if (!nodes_cover_memory()) {
+ if (!nodes_cover_memory(nodes)) {
bad_srat();
return -1;
}
@@ -440,6 +440,75 @@ int __init acpi_scan_nodes(unsigned long
return 0;
}
+#ifdef CONFIG_NUMA_EMU
+static int __init find_node_by_addr(unsigned long addr)
+{
+ int ret = NUMA_NO_NODE;
+ int i;
+
+ for_each_node_mask(i, nodes_parsed) {
+ /*
+ * Find the real node that this emulated node appears on. For
+ * the sake of simplicity, we only use a real node's starting
+ * address to determine which emulated node it appears on.
+ */
+ if (addr >= nodes[i].start && addr < nodes[i].end) {
+ ret = i;
+ break;
+ }
+ }
+ return i;
+}
+
+/*
+ * In NUMA emulation, we need to setup proximity domain (_PXM) to node ID
+ * mappings that respect the real ACPI topology but reflect our emulated
+ * environment. For each emulated node, we find which real node it appears on
+ * and create PXM to NID mappings for those fake nodes which mirror that
+ * locality. SLIT will now represent the correct distances between emulated
+ * nodes as a result of the real topology.
+ */
+void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
+{
+ int i;
+ int fake_node_to_pxm_map[MAX_NUMNODES] = {
+ [0 ... MAX_NUMNODES-1] = PXM_INVAL
+ };
+
+ printk(KERN_INFO "Faking PXM affinity for fake nodes on real "
+ "topology.\n");
+ for (i = 0; i < num_nodes; i++) {
+ int nid, pxm;
+
+ nid = find_node_by_addr(fake_nodes[i].start);
+ if (nid == NUMA_NO_NODE)
+ continue;
+ pxm = node_to_pxm(nid);
+ if (pxm == PXM_INVAL)
+ continue;
+ fake_node_to_pxm_map[i] = pxm;
+ }
+ for (i = 0; i < num_nodes; i++)
+ __acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i);
+
+ nodes_clear(nodes_parsed);
+ for (i = 0; i < num_nodes; i++)
+ if (fake_nodes[i].start != fake_nodes[i].end)
+ node_set(i, nodes_parsed);
+ WARN_ON(!nodes_cover_memory(fake_nodes));
+}
+
+static int null_slit_node_compare(int a, int b)
+{
+ return node_to_pxm(a) == node_to_pxm(b);
+}
+#else
+static int null_slit_node_compare(int a, int b)
+{
+ return a == b;
+}
+#endif /* CONFIG_NUMA_EMU */
+
void __init srat_reserve_add_area(int nodeid)
{
if (found_add_area && nodes_add[nodeid].end) {
@@ -464,7 +533,8 @@ int __node_distance(int a, int b)
int index;
if (!acpi_slit)
- return a == b ? LOCAL_DISTANCE : REMOTE_DISTANCE;
+ return null_slit_node_compare(a, b) ? LOCAL_DISTANCE :
+ REMOTE_DISTANCE;
index = acpi_slit->locality_count * node_to_pxm(a);
return acpi_slit->entry[index + node_to_pxm(b)];
}
Index: linux/drivers/acpi/numa.c
===================================================================
--- linux.orig/drivers/acpi/numa.c
+++ linux/drivers/acpi/numa.c
@@ -36,8 +36,6 @@
ACPI_MODULE_NAME("numa");
static nodemask_t nodes_found_map = NODE_MASK_NONE;
-#define PXM_INVAL -1
-#define NID_INVAL -1
/* maps to convert between proximity domain and logical node ID */
static int __cpuinitdata pxm_to_node_map[MAX_PXM_DOMAINS]
@@ -59,6 +57,12 @@ int node_to_pxm(int node)
return node_to_pxm_map[node];
}
+void __acpi_map_pxm_to_node(int pxm, int node)
+{
+ pxm_to_node_map[pxm] = node;
+ node_to_pxm_map[node] = pxm;
+}
+
int acpi_map_pxm_to_node(int pxm)
{
int node = pxm_to_node_map[pxm];
@@ -67,8 +71,7 @@ int acpi_map_pxm_to_node(int pxm)
if (nodes_weight(nodes_found_map) >= MAX_NUMNODES)
return NID_INVAL;
node = first_unset_node(nodes_found_map);
- pxm_to_node_map[pxm] = node;
- node_to_pxm_map[node] = pxm;
+ __acpi_map_pxm_to_node(pxm, node);
node_set(node, nodes_found_map);
}
Index: linux/include/acpi/acpi_numa.h
===================================================================
--- linux.orig/include/acpi/acpi_numa.h
+++ linux/include/acpi/acpi_numa.h
@@ -13,6 +13,7 @@
extern int pxm_to_node(int);
extern int node_to_pxm(int);
+extern void __acpi_map_pxm_to_node(int, int);
extern int acpi_map_pxm_to_node(int);
extern void __cpuinit acpi_unmap_pxm_to_node(int);
Index: linux/include/asm-x86_64/acpi.h
===================================================================
--- linux.orig/include/asm-x86_64/acpi.h
+++ linux/include/asm-x86_64/acpi.h
@@ -29,6 +29,7 @@
#ifdef __KERNEL__
#include <acpi/pdc_intel.h>
+#include <asm/numa.h>
#define COMPILER_DEPENDENT_INT64 long long
#define COMPILER_DEPENDENT_UINT64 unsigned long long
@@ -141,6 +142,16 @@ extern int acpi_pci_disabled;
extern int acpi_skip_timer_override;
extern int acpi_use_timer_override;
+#ifdef CONFIG_ACPI_NUMA
+extern void __init acpi_fake_nodes(const struct bootnode *fake_nodes,
+ int num_nodes);
+#else
+static inline void acpi_fake_nodes(const struct bootnode *fake_nodes,
+ int num_nodes)
+{
+}
+#endif
+
#endif /*__KERNEL__*/
#endif /*_ASM_ACPI_H*/
Index: linux/include/linux/acpi.h
===================================================================
--- linux.orig/include/linux/acpi.h
+++ linux/include/linux/acpi.h
@@ -231,6 +231,9 @@ extern int acpi_paddr_to_node(u64 start_
extern int pnpacpi_disabled;
+#define PXM_INVAL (-1)
+#define NID_INVAL (-1)
+
#else /* CONFIG_ACPI */
static inline int acpi_boot_init(void)
next prev parent reply other threads:[~2007-07-19 10:21 UTC|newest]
Thread overview: 119+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-07-19 9:54 [PATCH] [0/58] First batch of x86 patches for .23 Andi Kleen
2007-07-19 9:54 ` [PATCH] [1/58] x86: Always flush pages in change_page_attr Andi Kleen
2007-08-06 10:15 ` [patches] " Jan Beulich
2007-08-06 10:36 ` Andi Kleen
2007-08-06 10:49 ` Jan Beulich
2007-07-19 9:54 ` [PATCH] [2/58] x86_64: Tell gcc to only align stack to 8 bytes Andi Kleen
2007-07-19 11:50 ` Serge Belyshev
2007-07-19 12:06 ` Andi Kleen
2007-07-19 14:42 ` Chuck Ebbert
2007-07-19 9:54 ` [PATCH] [3/58] x86_64: asm/ptrace.h needs linux/compiler.h Andi Kleen
2007-07-19 9:54 ` [PATCH] [4/58] x86_64: Don't rely on a unique IO-APIC ID Andi Kleen
2007-07-19 9:54 ` [PATCH] [5/58] x86_64: Report the pending irq if available in smp_affinity Andi Kleen
2007-07-19 10:23 ` Ingo Molnar
2007-07-19 9:54 ` [PATCH] [6/58] x86_64: Use LOCAL_DISTANCE and REMOTE_DISTANCE in x86_64 ACPI code Andi Kleen
2007-07-19 9:54 ` [PATCH] [7/58] x86_64: various cleanups in NUMA scan node Andi Kleen
2007-07-19 17:15 ` Yinghai Lu
2007-07-19 17:21 ` Andi Kleen
2007-07-19 17:38 ` Yinghai Lu
2007-07-19 20:00 ` Andi Kleen
2007-07-19 21:01 ` David Rientjes
2007-07-19 9:54 ` [PATCH] [8/58] x86_64: Use string instruction memcpy/memset on AMD Fam10 Andi Kleen
2007-07-19 16:43 ` Jan Engelhardt
2007-07-19 17:00 ` Yinghai Lu
2007-07-19 9:54 ` [PATCH] [9/58] x86_64: Always use builtin memcpy on gcc 4.3 Andi Kleen
2007-07-21 23:16 ` Oleg Verych
2007-07-21 23:27 ` Andi Kleen
2007-07-22 0:29 ` Denis Vlasenko
2007-07-19 9:54 ` [PATCH] [10/58] i386: Move all simple string operations out of line Andi Kleen
2007-07-19 9:54 ` [PATCH] [11/58] x86: Support __attribute__((__cold__)) in gcc 4.3 Andi Kleen
2007-07-19 9:54 ` [PATCH] [12/58] x86_64: Add vDSO for x86-64 with gettimeofday/clock_gettime/getcpu Andi Kleen
2007-08-21 16:25 ` Daniel Walker
2007-08-21 18:45 ` Andi Kleen
2007-08-21 18:40 ` Andrew Morton
2007-07-19 9:54 ` [PATCH] [13/58] x86: Separate checking of unsynchronized and unstable TSC Andi Kleen
2007-07-19 9:54 ` [PATCH] [14/58] x86_64: Add on_cpu_single Andi Kleen
2007-07-19 11:09 ` Satyam Sharma
2007-07-19 12:07 ` Andi Kleen
2007-07-19 9:54 ` [PATCH] [15/58] i386: Rewrite sched_clock Andi Kleen
2007-07-19 16:51 ` Daniel Walker
2007-07-19 17:13 ` Andi Kleen
2007-07-19 17:15 ` Daniel Walker
2007-07-19 17:22 ` Andi Kleen
2007-07-19 17:31 ` Daniel Walker
2007-07-19 17:38 ` Andi Kleen
2007-07-19 17:43 ` Daniel Walker
2007-07-19 18:00 ` Andi Kleen
2007-07-19 18:00 ` Daniel Walker
2007-07-20 3:11 ` Mathieu Desnoyers
2007-07-20 3:47 ` Mathieu Desnoyers
2007-07-20 4:18 ` [PATCH] [15/58] i386: Rewrite sched_clock (cmpxchg8b) Mathieu Desnoyers
2007-07-20 5:07 ` Nick Piggin
2007-07-20 5:47 ` Mathieu Desnoyers
2007-07-20 8:27 ` [PATCH] [15/58] i386: Rewrite sched_clock Andi Kleen
2007-07-20 14:12 ` Mathieu Desnoyers
2007-07-20 14:39 ` Mathieu Desnoyers
2007-07-20 15:14 ` Andi Kleen
2007-07-20 15:22 ` Mathieu Desnoyers
2007-07-20 16:49 ` [PATCH] 80386 and 80486 cmpxchg64 and cmpxchg64_local fallback Mathieu Desnoyers
2007-07-19 9:55 ` [PATCH] [16/58] x86_64: Use new shared sched_clock in x86-64 too Andi Kleen
2007-07-19 9:55 ` [PATCH] [17/58] i386: Add L3 cache support to AMD CPUID4 emulation Andi Kleen
2007-07-20 17:00 ` [patches] " Andreas Herrmann
2007-07-20 17:15 ` Andreas Herrmann
2007-07-19 9:55 ` [PATCH] [18/58] x86_64: remove extra extern declaring about dmi_ioremap Andi Kleen
2007-07-19 9:55 ` [PATCH] [19/58] x86_64: Don't use softirq save locks in smp_call_function Andi Kleen
2007-07-19 12:16 ` Satyam Sharma
2007-07-19 12:19 ` Andi Kleen
2007-07-19 9:55 ` [PATCH] [20/58] x86: Always probe the NMI watchdog Andi Kleen
2007-07-19 10:24 ` Björn Steinbrink
2007-07-19 10:42 ` Andi Kleen
2007-07-19 9:55 ` [PATCH] [21/58] i386: Reserve the right performance counter for the Intel PerfMon " Andi Kleen
2007-07-19 10:21 ` Björn Steinbrink
2007-07-19 10:45 ` Andi Kleen
2007-07-19 9:55 ` [PATCH] [22/58] x86_64: hpet tsc calibration fix broken smi detection logic Andi Kleen
2007-07-19 9:55 ` [PATCH] [23/58] i386: remove pit_interrupt_hook Andi Kleen
2007-07-19 9:55 ` [PATCH] [24/58] x86_64: Untangle asm/hpet.h from asm/timex.h Andi Kleen
2007-07-19 9:55 ` [PATCH] [25/58] x86_64: use generic cmos update Andi Kleen
2007-07-19 9:55 ` [PATCH] [26/58] x86_64: Use generic xtime init Andi Kleen
2007-07-19 9:55 ` [PATCH] [27/58] x86_64: Remove dead code and other janitor work in tsc.c Andi Kleen
2007-07-19 9:55 ` [PATCH] [28/58] x86_64: Fix APIC typo Andi Kleen
2007-07-19 9:55 ` [PATCH] [29/58] x86_64: fiuxp pt_reqs leftovers Andi Kleen
2007-07-19 9:55 ` [PATCH] [30/58] x86: share hpet.h with i386 Andi Kleen
2007-07-19 9:55 ` [PATCH] [31/58] x86_64: apic.c coding style janitor work Andi Kleen
2007-07-19 9:55 ` [PATCH] [32/58] x86_64: time.c white space wreckage cleanup Andi Kleen
2007-07-19 9:55 ` [PATCH] [33/58] x86_64: Avoid too many remote cpu references due to /proc/stat Andi Kleen
2007-07-19 10:21 ` Christoph Hellwig
2007-07-19 10:41 ` Andi Kleen
2007-07-19 10:55 ` Adrian Bunk
2007-07-19 9:55 ` [PATCH] [34/58] x86_64: ia32entry adjustments Andi Kleen
2007-07-19 14:46 ` Jeff Garzik
2007-08-06 10:43 ` Jan Beulich
2007-07-19 9:55 ` [PATCH] [35/58] i386: allow debuggers to access the vsyscall page with compat vDSO Andi Kleen
2007-07-19 9:55 ` [PATCH] [36/58] x86_64: minor exception trace variables cleanup Andi Kleen
2007-07-19 9:55 ` [PATCH] [37/58] x86_64: remove unused variable maxcpus Andi Kleen
2007-07-19 9:55 ` [PATCH] [38/58] i386: smp-alt-once option is only useful with HOTPLUG_CPU Andi Kleen
2007-07-19 9:55 ` [PATCH] [39/58] i386: minor nx handling adjustment Andi Kleen
2007-07-19 9:55 ` [PATCH] [40/58] i386: remapped_pgdat_init() static Andi Kleen
2007-07-19 9:55 ` [PATCH] [41/58] i386: arch/i386/kernel/i8253.c should #include <asm/timer.h> Andi Kleen
2007-07-19 9:55 ` [PATCH] [42/58] i386: timer_irq_works() static again Andi Kleen
2007-07-19 9:55 ` [PATCH] [43/58] x86_64: Quicklist support for x86_64 Andi Kleen
2007-07-19 9:55 ` [PATCH] [44/58] x86_64: extract helper function from e820_register_active_regions Andi Kleen
2007-07-19 9:55 ` Andi Kleen [this message]
2007-07-19 9:55 ` [PATCH] [46/58] x86_64: fake apicid_to_node mapping for fake numa Andi Kleen
2007-07-19 9:55 ` [PATCH] [47/58] i386: insert unclaimed MMCONFIG resources Andi Kleen
2007-07-19 9:55 ` [PATCH] [48/58] x86_64: O_EXCL on /dev/mcelog Andi Kleen
2007-07-19 9:55 ` [PATCH] [49/58] x86_64: support poll() " Andi Kleen
2007-07-19 9:55 ` [PATCH] [50/58] x86_64: mcelog tolerant level cleanup Andi Kleen
2007-07-19 9:55 ` [PATCH] [51/58] i386: fix machine rebooting Andi Kleen
2007-07-19 9:55 ` [PATCH] [52/58] i386: fix section mismatch warnings in mtrr Andi Kleen
2007-07-19 9:55 ` [PATCH] [53/58] x86: PM_TRACE support Andi Kleen
2007-07-19 9:55 ` [PATCH] [54/58] x86: Make Alt-SysRq-p display the debug register contents Andi Kleen
2007-07-19 9:55 ` [PATCH] [55/58] i386: add reference to the arguments Andi Kleen
2007-07-19 9:55 ` [PATCH] [56/58] x86: round_jiffies() for i386 and x86-64 non-critical/corrected MCE polling Andi Kleen
2007-07-19 9:55 ` [PATCH] [57/58] x86_64: check remote IRR bit before migrating level triggered irq Andi Kleen
2007-07-19 9:55 ` [PATCH] [58/58] x86: remove support for the Rise CPU Andi Kleen
2007-07-19 10:45 ` Alan Cox
2007-07-19 10:48 ` Adrian Bunk
2007-07-19 11:13 ` Alan Cox
2007-07-19 12:03 ` Andi Kleen
2007-07-19 14:56 ` Jeff Garzik
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20070719095531.C4DFE14E05@wotan.suse.de \
--to=ak@suse.de \
--cc=lenb@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=patches@x86-64.org \
--cc=rientjes@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®