summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorDavid Hildenbrand <david@redhat.com>2020-01-04 12:59:33 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2020-01-04 13:55:08 -0800
commitfeee6b2989165631b17ac6d4ccdbf6759254e85a (patch)
tree2f7f2f83222bd1e4f19c49191612e2d9da0068ac /arch
parent5613970af3f5f8372c596b138bd64f3918513515 (diff)
downloadlinux-feee6b2989165631b17ac6d4ccdbf6759254e85a.tar.bz2
mm/memory_hotplug: shrink zones when offlining memory
We currently try to shrink a single zone when removing memory. We use the zone of the first page of the memory we are removing. If that memmap was never initialized (e.g., memory was never onlined), we will read garbage and can trigger kernel BUGs (due to a stale pointer): BUG: unable to handle page fault for address: 000000000000353d #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP PTI CPU: 1 PID: 7 Comm: kworker/u8:0 Not tainted 5.3.0-rc5-next-20190820+ #317 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.4 Workqueue: kacpi_hotplug acpi_hotplug_work_fn RIP: 0010:clear_zone_contiguous+0x5/0x10 Code: 48 89 c6 48 89 c3 e8 2a fe ff ff 48 85 c0 75 cf 5b 5d c3 c6 85 fd 05 00 00 01 5b 5d c3 0f 1f 840 RSP: 0018:ffffad2400043c98 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000200000000 RCX: 0000000000000000 RDX: 0000000000200000 RSI: 0000000000140000 RDI: 0000000000002f40 RBP: 0000000140000000 R08: 0000000000000000 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000140000 R13: 0000000000140000 R14: 0000000000002f40 R15: ffff9e3e7aff3680 FS: 0000000000000000(0000) GS:ffff9e3e7bb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000353d CR3: 0000000058610000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __remove_pages+0x4b/0x640 arch_remove_memory+0x63/0x8d try_remove_memory+0xdb/0x130 __remove_memory+0xa/0x11 acpi_memory_device_remove+0x70/0x100 acpi_bus_trim+0x55/0x90 acpi_device_hotplug+0x227/0x3a0 acpi_hotplug_work_fn+0x1a/0x30 process_one_work+0x221/0x550 worker_thread+0x50/0x3b0 kthread+0x105/0x140 ret_from_fork+0x3a/0x50 Modules linked in: CR2: 000000000000353d Instead, shrink the zones when offlining memory or when onlining failed. Introduce and use remove_pfn_range_from_zone(() for that. We now properly shrink the zones, even if we have DIMMs whereby - Some memory blocks fall into no zone (never onlined) - Some memory blocks fall into multiple zones (offlined+re-onlined) - Multiple memory blocks that fall into different zones Drop the zone parameter (with a potential dubious value) from __remove_pages() and __remove_section(). Link: http://lkml.kernel.org/r/20191006085646.5768-6-david@redhat.com Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online") [visible after d0dc12e86b319] Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Michal Hocko <mhocko@suse.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Logan Gunthorpe <logang@deltatee.com> Cc: <stable@vger.kernel.org> [5.0+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'arch')
-rw-r--r--arch/arm64/mm/mmu.c4
-rw-r--r--arch/ia64/mm/init.c4
-rw-r--r--arch/powerpc/mm/mem.c3
-rw-r--r--arch/s390/mm/init.c4
-rw-r--r--arch/sh/mm/init.c4
-rw-r--r--arch/x86/mm/init_32.c4
-rw-r--r--arch/x86/mm/init_64.c4
7 files changed, 7 insertions, 20 deletions
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 5a3b15a14a7f..40797cbfba2d 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1070,7 +1070,6 @@ void arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
/*
* FIXME: Cleanup page tables (also in arch_add_memory() in case
@@ -1079,7 +1078,6 @@ void arch_remove_memory(int nid, u64 start, u64 size,
* unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be
* unlocked yet.
*/
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
}
#endif
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 58fd67068bac..b01d68a2d5d9 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -689,9 +689,7 @@ void arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
}
#endif
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 617c2777926f..f5535eae637f 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -151,10 +151,9 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
int ret;
- __remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
/* Remove htab bolted mappings for this section of memory */
start = (unsigned long)__va(start);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f0ce22220565..ac44bd76db4b 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -292,10 +292,8 @@ void arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
vmem_remove_mapping(start, size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index dfdbaa50946e..d1b1ff2be17a 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -434,9 +434,7 @@ void arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = PFN_DOWN(start);
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 930edeb41ec3..0a74407ef92e 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -865,10 +865,8 @@ void arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
}
#endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index dcb9bc961b39..bcfede46fe02 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1212,10 +1212,8 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
- struct zone *zone = page_zone(page);
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
kernel_physical_mapping_remove(start, start + size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */