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):
:/# [ 23.912993] BUG: unable to handle page fault for address: 000000000000353d
[ 23.914219] #PF: supervisor write access in kernel mode
[ 23.915199] #PF: error_code(0x0002) - not-present page
[ 23.916160] PGD 0 P4D 0
[ 23.916627] Oops: 0002 [#1] SMP PTI
[ 23.917256] CPU: 1 PID: 7 Comm: kworker/u8:0 Not tainted 5.3.0-rc5-next-20190820+ #317
[ 23.918900] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.4
[ 23.921194] Workqueue: kacpi_hotplug acpi_hotplug_work_fn
[ 23.922249] RIP: 0010:clear_zone_contiguous+0x5/0x10
[ 23.923173] 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
[ 23.926876] RSP: 0018:ffffad2400043c98 EFLAGS: 00010246
[ 23.927928] RAX: 0000000000000000 RBX: 0000000200000000 RCX: 0000000000000000
[ 23.929458] RDX: 0000000000200000 RSI: 0000000000140000 RDI: 0000000000002f40
[ 23.930899] RBP: 0000000140000000 R08: 0000000000000000 R09: 0000000000000001
[ 23.932362] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000140000
[ 23.933603] R13: 0000000000140000 R14: 0000000000002f40 R15: ffff9e3e7aff3680
[ 23.934913] FS: 0000000000000000(0000) GS:ffff9e3e7bb00000(0000) knlGS:0000000000000000
[ 23.936294] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 23.937481] CR2: 000000000000353d CR3: 0000000058610000 CR4: 00000000000006e0
[ 23.938687] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 23.939889] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 23.941168] Call Trace:
[ 23.941580] __remove_pages+0x4b/0x640
[ 23.942303] ? mark_held_locks+0x49/0x70
[ 23.943149] arch_remove_memory+0x63/0x8d
[ 23.943921] try_remove_memory+0xdb/0x130
[ 23.944766] ? walk_memory_blocks+0x7f/0x9e
[ 23.945616] __remove_memory+0xa/0x11
[ 23.946274] acpi_memory_device_remove+0x70/0x100
[ 23.947308] acpi_bus_trim+0x55/0x90
[ 23.947914] acpi_device_hotplug+0x227/0x3a0
[ 23.948714] acpi_hotplug_work_fn+0x1a/0x30
[ 23.949433] process_one_work+0x221/0x550
[ 23.950190] worker_thread+0x50/0x3b0
[ 23.950993] kthread+0x105/0x140
[ 23.951644] ? process_one_work+0x550/0x550
[ 23.952508] ? kthread_park+0x80/0x80
[ 23.953367] ret_from_fork+0x3a/0x50
[ 23.954025] Modules linked in:
[ 23.954613] CR2: 000000000000353d
[ 23.955248] ---[ end trace 93d982b1fb3e1a69 ]---
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().
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Cc: Vasily Gorbik <gor@xxxxxxxxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Cc: Yoshinori Sato <ysato@xxxxxxxxxxxxxxxxxxxx>
Cc: Rich Felker <dalias@xxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Steve Capper <steve.capper@xxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxxxxx>
Cc: Anshuman Khandual <anshuman.khandual@xxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Jun Yao <yaojun8558363@xxxxxxxxx>
Cc: Robin Murphy <robin.murphy@xxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Cc: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
Cc: Christophe Leroy <christophe.leroy@xxxxxx>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Gerald Schaefer <gerald.schaefer@xxxxxxxxxx>
Cc: Halil Pasic <pasic@xxxxxxxxxxxxx>
Cc: Tom Lendacky <thomas.lendacky@xxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Masahiro Yamada <yamada.masahiro@xxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Wei Yang <richard.weiyang@xxxxxxxxx>
Cc: Qian Cai <cai@xxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Cc: Ira Weiny <ira.weiny@xxxxxxxxx>
Cc: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
Cc: linux-ia64@xxxxxxxxxxxxxxx
Cc: linuxppc-dev@xxxxxxxxxxxxxxxx
Cc: linux-s390@xxxxxxxxxxxxxxx
Cc: linux-sh@xxxxxxxxxxxxxxx
Fixes: d0dc12e86b31 ("mm/memory_hotplug: optimize memory hotplug")
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
arch/arm64/mm/mmu.c | 4 +---
arch/ia64/mm/init.c | 4 +---
arch/powerpc/mm/mem.c | 3 +--
arch/s390/mm/init.c | 4 +---
arch/sh/mm/init.c | 4 +---
arch/x86/mm/init_32.c | 4 +---
arch/x86/mm/init_64.c | 4 +---
include/linux/memory_hotplug.h | 7 +++++--
mm/memory_hotplug.c | 31 ++++++++++++++++---------------
mm/memremap.c | 3 +--
10 files changed, 29 insertions(+), 39 deletions(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 60c929f3683b..d10247fab0fd 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1069,7 +1069,6 @@ 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
@@ -1078,7 +1077,6 @@ 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 bf9df2625bc8..a6dd80a2c939 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 be941d382c8d..97e5922cb52e 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -130,10 +130,9 @@ 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 a124f19f7b3c..c1d96e588152 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -291,10 +291,8 @@ 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 a6b5c653727b..b8541d77452c 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 */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index bc477e98a310..517b70943732 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -126,8 +126,8 @@ static inline bool movable_node_is_enabled(void)
extern void arch_remove_memory(int nid, u64 start, u64 size,
struct vmem_altmap *altmap);
-extern void __remove_pages(struct zone *zone, unsigned long start_pfn,
- unsigned long nr_pages, struct vmem_altmap *altmap);
+extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
+ struct vmem_altmap *altmap);
/* reasonably generic interface to expand the physical pages */
extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
@@ -346,6 +346,9 @@ extern int add_memory(int nid, u64 start, u64 size);
extern int add_memory_resource(int nid, struct resource *resource);
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
unsigned long nr_pages, struct vmem_altmap *altmap);
+extern void remove_pfn_range_from_zone(struct zone *zone,
+ unsigned long start_pfn,
+ unsigned long nr_pages);
extern bool is_memblock_offlined(struct memory_block *mem);
extern int sparse_add_section(int nid, unsigned long pfn,
unsigned long nr_pages, struct vmem_altmap *altmap);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index afed8331332b..cef909ebd807 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -457,8 +457,9 @@ static void update_pgdat_span(struct pglist_data *pgdat)
pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
}
-static void __remove_zone(struct zone *zone, unsigned long start_pfn,
- unsigned long nr_pages)
+void __ref remove_pfn_range_from_zone(struct zone *zone,
+ unsigned long start_pfn,
+ unsigned long nr_pages)
{
struct pglist_data *pgdat = zone->zone_pgdat;
unsigned long flags;
@@ -471,28 +472,30 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn,
if (zone_idx(zone) == ZONE_DEVICE)
return;
+ clear_zone_contiguous(zone);
+
pgdat_resize_lock(zone->zone_pgdat, &flags);
shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
update_pgdat_span(pgdat);
pgdat_resize_unlock(zone->zone_pgdat, &flags);
+
+ set_zone_contiguous(zone);
}
-static void __remove_section(struct zone *zone, unsigned long pfn,
- unsigned long nr_pages, unsigned long map_offset,
- struct vmem_altmap *altmap)
+static void __remove_section(unsigned long pfn, unsigned long nr_pages,
+ unsigned long map_offset,
+ struct vmem_altmap *altmap)
{
struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn));
if (WARN_ON_ONCE(!valid_section(ms)))
return;
- __remove_zone(zone, pfn, nr_pages);
sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap);
}
/**
- * __remove_pages() - remove sections of pages from a zone
- * @zone: zone from which pages need to be removed
+ * __remove_pages() - remove sections of pages
* @pfn: starting pageframe (must be aligned to start of a section)
* @nr_pages: number of pages to remove (must be multiple of section size)
* @altmap: alternative device page map or %NULL if default memmap is used
@@ -502,16 +505,14 @@ static void __remove_section(struct zone *zone, unsigned long pfn,
* sure that pages are marked reserved and zones are adjust properly by
* calling offline_pages().
*/
-void __remove_pages(struct zone *zone, unsigned long pfn,
- unsigned long nr_pages, struct vmem_altmap *altmap)
+void __remove_pages(unsigned long pfn, unsigned long nr_pages,
+ struct vmem_altmap *altmap)
{
unsigned long map_offset = 0;
unsigned long nr, start_sec, end_sec;
map_offset = vmem_altmap_offset(altmap);
- clear_zone_contiguous(zone);
-
if (check_pfn_span(pfn, nr_pages, "remove"))
return;
@@ -523,13 +524,11 @@ void __remove_pages(struct zone *zone, unsigned long pfn,
cond_resched();
pfns = min(nr_pages, PAGES_PER_SECTION
- (pfn & ~PAGE_SECTION_MASK));
- __remove_section(zone, pfn, pfns, map_offset, altmap);
+ __remove_section(pfn, pfns, map_offset, altmap);
pfn += pfns;
nr_pages -= pfns;
map_offset = 0;
}
-
- set_zone_contiguous(zone);
}
int set_online_page_callback(online_page_callback_t callback)
@@ -857,6 +856,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
(unsigned long long) pfn << PAGE_SHIFT,
(((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
memory_notify(MEM_CANCEL_ONLINE, &arg);
+ remove_pfn_range_from_zone(zone, pfn, nr_pages);
mem_hotplug_done();
return ret;
}
@@ -1603,6 +1603,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
writeback_set_ratelimit();
memory_notify(MEM_OFFLINE, &arg);
+ remove_pfn_range_from_zone(zone, start_pfn, nr_pages);
mem_hotplug_done();
return 0;
diff --git a/mm/memremap.c b/mm/memremap.c
index 026788b2ac69..734afeaad811 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -140,8 +140,7 @@ void memunmap_pages(struct dev_pagemap *pgmap)
mem_hotplug_begin();
if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- __remove_pages(page_zone(pfn_to_page(start_pfn)), start_pfn,
- nr_pages, NULL);
+ __remove_pages(start_pfn, nr_pages, NULL);
} else {
arch_remove_memory(nid, res->start, resource_size(res),
pgmap_altmap(pgmap));
--
2.21.0
