mm: provide kernel parameter to allow disabling page init poisoning

Patch series "Address issues slowing persistent memory initialization", v5.

The main thing this patch set achieves is that it allows us to initialize
each node worth of persistent memory independently.  As a result we reduce
page init time by about 2 minutes because instead of taking 30 to 40
seconds per node and going through each node one at a time, we process all
4 nodes in parallel in the case of a 12TB persistent memory setup spread
evenly over 4 nodes.

This patch (of 3):

On systems with a large amount of memory it can take a significant amount
of time to initialize all of the page structs with the PAGE_POISON_PATTERN
value.  I have seen it take over 2 minutes to initialize a system with
over 12TB of RAM.

In order to work around the issue I had to disable CONFIG_DEBUG_VM and
then the boot time returned to something much more reasonable as the
arch_add_memory call completed in milliseconds versus seconds.  However in
doing that I had to disable all of the other VM debugging on the system.

In order to work around a kernel that might have CONFIG_DEBUG_VM enabled
on a system that has a large amount of memory I have added a new kernel
parameter named "vm_debug" that can be set to "-" in order to disable it.

Link: http://lkml.kernel.org/r/20180925201921.3576.84239.stgit@localhost.localdomain
Reviewed-by: Pavel Tatashin <pavel.tatashin@microsoft.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 8022d902e770c09c8cc7668645aabbc77736106d..dcd082576e79dc48fd8a616f4920242b7fce7814 100644 (file)
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4839,6 +4839,18 @@
                        This is actually a boot loader parameter; the value is
                        passed to the kernel using a special protocol.
 
+       vm_debug[=options]      [KNL] Available with CONFIG_DEBUG_VM=y.
+                       May slow down system boot speed, especially when
+                       enabled on systems with a large amount of memory.
+                       All options are enabled by default, and this
+                       interface is meant to allow for selectively
+                       enabling or disabling specific virtual memory
+                       debugging features.
+
+                       Available options are:
+                         P     Enable page structure init time poisoning
+                         -     Disable all of the above options
+
        vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact
                        size of <nn>. This can be used to increase the
                        minimum size (128MB on x86). It can also be used to

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 4d99504f649604126c7a0c3b5229db7dfb2366f3..934f91ef3f54ecc7688401e87f6d8beae8692e64 100644 (file)
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -163,6 +163,14 @@ static inline int PagePoisoned(const struct page *page)
        return page->flags == PAGE_POISON_PATTERN;
 }
 
+#ifdef CONFIG_DEBUG_VM
+void page_init_poison(struct page *page, size_t size);
+#else
+static inline void page_init_poison(struct page *page, size_t size)
+{
+}
+#endif
+
 /*
  * Page flags policies wrt compound pages
  *

diff --git a/mm/debug.c b/mm/debug.c
index bd10aad8539a42bf5a1263518534946eeac6e050..cdacba12e09aeebdcd4c2e5c904a59d8e940aaeb 100644 (file)
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -13,6 +13,7 @@
 #include <trace/events/mmflags.h>
 #include <linux/migrate.h>
 #include <linux/page_owner.h>
+#include <linux/ctype.h>
 
 #include "internal.h"
 
@@ -175,4 +176,49 @@ void dump_mm(const struct mm_struct *mm)
        );
 }
 
+static bool page_init_poisoning __read_mostly = true;
+
+static int __init setup_vm_debug(char *str)
+{
+       bool __page_init_poisoning = true;
+
+       /*
+        * Calling vm_debug with no arguments is equivalent to requesting
+        * to enable all debugging options we can control.
+        */
+       if (*str++ != '=' || !*str)
+               goto out;
+
+       __page_init_poisoning = false;
+       if (*str == '-')
+               goto out;
+
+       while (*str) {
+               switch (tolower(*str)) {
+               case'p':
+                       __page_init_poisoning = true;
+                       break;
+               default:
+                       pr_err("vm_debug option '%c' unknown. skipped\n",
+                              *str);
+               }
+
+               str++;
+       }
+out:
+       if (page_init_poisoning && !__page_init_poisoning)
+               pr_warn("Page struct poisoning disabled by kernel command line option 'vm_debug'\n");
+
+       page_init_poisoning = __page_init_poisoning;
+
+       return 1;
+}
+__setup("vm_debug", setup_vm_debug);
+
+void page_init_poison(struct page *page, size_t size)
+{
+       if (page_init_poisoning)
+               memset(page, PAGE_POISON_PATTERN, size);
+}
+EXPORT_SYMBOL_GPL(page_init_poison);
 #endif         /* CONFIG_DEBUG_VM */

diff --git a/mm/memblock.c b/mm/memblock.c
index 237944479d25a81483a7d6969cfab05c6f0a4c25..a85315083b5a8d1fbba19329a5b77dc7fe3b6da3 100644 (file)
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1444,10 +1444,9 @@ void * __init memblock_virt_alloc_try_nid_raw(
 
        ptr = memblock_virt_alloc_internal(size, align,
                                           min_addr, max_addr, nid);
-#ifdef CONFIG_DEBUG_VM
        if (ptr && size > 0)
-               memset(ptr, PAGE_POISON_PATTERN, size);
-#endif
+               page_init_poison(ptr, size);
+
        return ptr;
 }
 

diff --git a/mm/sparse.c b/mm/sparse.c
index 10b07eea9a6e450ae2a397351959c624eafe66ad..67ad061f7fb8b1b4a38af7a5f69913f6c4f39e70 100644 (file)
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -696,13 +696,11 @@ int __meminit sparse_add_one_section(struct pglist_data *pgdat,
                goto out;
        }
 
-#ifdef CONFIG_DEBUG_VM
        /*
         * Poison uninitialized struct pages in order to catch invalid flags
         * combinations.
         */
-       memset(memmap, PAGE_POISON_PATTERN, sizeof(struct page) * PAGES_PER_SECTION);
-#endif
+       page_init_poison(memmap, sizeof(struct page) * PAGES_PER_SECTION);
 
        section_mark_present(ms);
        sparse_init_one_section(ms, section_nr, memmap, usemap);