acpi, memory-hotplug: parse SRAT before memblock is ready

On linux, the pages used by kernel could not be migrated.  As a result,
if a memory range is used by kernel, it cannot be hot-removed.  So if we
want to hot-remove memory, we should prevent kernel from using it.

The way now used to prevent this is specify a memory range by
movablemem_map boot option and set it as ZONE_MOVABLE.

But when the system is booting, memblock will allocate memory, and
reserve the memory for kernel.  And before we parse SRAT, and know the
node memory ranges, memblock is working.  And it may allocate memory in
ranges to be set as ZONE_MOVABLE.  This memory can be used by kernel,
and never be freed.

So, let's parse SRAT before memblock is called first.  And it is early
enough.

The first call of memblock_find_in_range_node() is in:

  setup_arch()
    |-->setup_real_mode()

so, this patch add a function early_parse_srat() to parse SRAT, and call
it before setup_real_mode() is called.

NOTE:

1) early_parse_srat() is called before numa_init(), and has initialized
   numa_meminfo.  So DO NOT clear numa_nodes_parsed in numa_init() and DO
   NOT zero numa_meminfo in numa_init(), otherwise we will lose memory
   numa info.

2) I don't know why using count of memory affinities parsed from SRAT
   as a return value in original acpi_numa_init().  So I add a static
   variable srat_mem_cnt to remember this count and use it as the return
   value of the new acpi_numa_init()

[mhocko@suse.cz: parse SRAT before memblock is ready fix]
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Reviewed-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Wu Jianguo <wujianguo@huawei.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Len Brown <lenb@kernel.org>
Cc: "Brown, Len" <len.brown@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 915f5efefcf5203e66f00955083be008de064554..9c857f05cef0fccea2dab9769a865ff2f63c920b 100644 (file)
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1056,6 +1056,15 @@ void __init setup_arch(char **cmdline_p)
        setup_bios_corruption_check();
 #endif
 
+       /*
+        * In the memory hotplug case, the kernel needs info from SRAT to
+        * determine which memory is hotpluggable before allocating memory
+        * using memblock.
+        */
+       acpi_boot_table_init();
+       early_acpi_boot_init();
+       early_parse_srat();
+
 #ifdef CONFIG_X86_32
        printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
                        (max_pfn_mapped<<PAGE_SHIFT) - 1);
@@ -1101,10 +1110,6 @@ void __init setup_arch(char **cmdline_p)
        /*
         * Parse the ACPI tables for possible boot-time SMP configuration.
         */
-       acpi_boot_table_init();
-
-       early_acpi_boot_init();
-
        initmem_init();
        memblock_find_dma_reserve();
 

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index e3963f52aaead52bfe321b38f4c482779c8add32..dfd30259eb893564e5a678f95f65f2a4ab240be4 100644 (file)
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -560,10 +560,12 @@ static int __init numa_init(int (*init_func)(void))
        for (i = 0; i < MAX_LOCAL_APIC; i++)
                set_apicid_to_node(i, NUMA_NO_NODE);
 
-       nodes_clear(numa_nodes_parsed);
+       /*
+        * Do not clear numa_nodes_parsed or zero numa_meminfo here, because
+        * SRAT was parsed earlier in early_parse_srat().
+        */
        nodes_clear(node_possible_map);
        nodes_clear(node_online_map);
-       memset(&numa_meminfo, 0, sizeof(numa_meminfo));
        WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES));
        numa_reset_distance();
 

diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 33e609f6358580647412dd0d029f065fdfb73741..59844ee149bed01dbe522393637c39f74f7c8ae7 100644 (file)
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -282,10 +282,10 @@ acpi_table_parse_srat(enum acpi_srat_type id,
                                            handler, max_entries);
 }
 
-int __init acpi_numa_init(void)
-{
-       int cnt = 0;
+static int srat_mem_cnt;
 
+void __init early_parse_srat(void)
+{
        /*
         * Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
         * SRAT cpu entries could have different order with that in MADT.
@@ -295,21 +295,24 @@ int __init acpi_numa_init(void)
        /* SRAT: Static Resource Affinity Table */
        if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
                acpi_table_parse_srat(ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY,
-                                    acpi_parse_x2apic_affinity, 0);
+                                     acpi_parse_x2apic_affinity, 0);
                acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY,
-                                    acpi_parse_processor_affinity, 0);
-               cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
-                                           acpi_parse_memory_affinity,
-                                           NR_NODE_MEMBLKS);
+                                     acpi_parse_processor_affinity, 0);
+               srat_mem_cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
+                                                    acpi_parse_memory_affinity,
+                                                    NR_NODE_MEMBLKS);
        }
+}
 
+int __init acpi_numa_init(void)
+{
        /* SLIT: System Locality Information Table */
        acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit);
 
        acpi_numa_arch_fixup();
 
-       if (cnt < 0)
-               return cnt;
+       if (srat_mem_cnt < 0)
+               return srat_mem_cnt;
        else if (!parsed_numa_memblks)
                return -ENOENT;
        return 0;

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index bcbdd7484e581404d54be807c034fced32ba45c2..f46cfd73a5536dab4705a6a51f379306560ca4f0 100644 (file)
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -485,6 +485,14 @@ static inline bool acpi_driver_match_device(struct device *dev,
 
 #endif /* !CONFIG_ACPI */
 
+#ifdef CONFIG_ACPI_NUMA
+void __init early_parse_srat(void);
+#else
+static inline void early_parse_srat(void)
+{
+}
+#endif
+
 #ifdef CONFIG_ACPI
 void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
                               u32 pm1a_ctrl,  u32 pm1b_ctrl));