Skip to contentSkip to conversation

mm/vmemmap/devdax: Fix kernel crash when probing devdax devices

PATCH In review Aneesh Kumar K.V 2 participants 3 messages Apr 12, 2023 – Apr 13, 2023

Subsystems (7)
Memory management x86 VFS MM core +3 more subsystems
lore
Share & tools
lore
#0 lore raw

PATCH v3 1/2 mm/vmemmap/devdax: Fix kernel crash when probing devdax devices

commit 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps") added support for using optimized vmmemap for devdax devices. But how vmemmap mappings are created are architecture specific. For example, powerpc with hash translation doesn't have vmemmap mappings in init_mm page table instead they are bolted table entries in the hardware page table

vmemmap_populate_compound_pages() used by vmemmap optimization code is not aware of these architecture-specific mapping. Hence allow architecture to opt for this feature. Architectures supporting HUGETLB_PAGE_OPTIMIZE_VMEMMAP option are selected when supporting this feature.

On ppc64 (pmem) where this isn't supported, it fixes below crash:'

BUG: Unable to handle kernel data access on write at 0xc00c000100400038
Faulting instruction address: 0xc000000001269d90
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 7 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc5-150500.34-default+ #2 5c90a668b6bbd142599890245c2fb5de19d7d28a
Hardware name: IBM,9009-42G POWER9 (raw) 0x4e0202 0xf000005 of:IBM,FW950.40 (VL950_099) hv:phyp pSeries
NIP:  c000000001269d90 LR: c0000000004c57d4 CTR: 0000000000000000
REGS: c000000003632c30 TRAP: 0300   Not tainted  (6.3.0-rc5-150500.34-default+)
MSR:  8000000000009033 <SF,EE,ME,IR,DR,RI,LE>  CR: 24842228  XER: 00000000
CFAR: c0000000004c57d0 DAR: c00c000100400038 DSISR: 42000000 IRQMASK: 0
....
NIP [c000000001269d90] __init_single_page.isra.74+0x14/0x4c
LR [c0000000004c57d4] __init_zone_device_page+0x44/0xd0
Call Trace:

[c000000003632ed0] [c000000003632f60] 0xc000000003632f60 (unreliable) [c000000003632f10] [c0000000004c5ca0] memmap_init_zone_device+0x170/0x250 [c000000003632fe0] [c0000000005575f8] memremap_pages+0x2c8/0x7f0 [c0000000036330c0] [c000000000557b5c] devm_memremap_pages+0x3c/0xa0 [c000000003633100] [c000000000d458a8] dev_dax_probe+0x108/0x3e0 [c0000000036331a0] [c000000000d41430] dax_bus_probe+0xb0/0x140 [c0000000036331d0] [c000000000cef27c] really_probe+0x19c/0x520 [c000000003633260] [c000000000cef6b4] __driver_probe_device+0xb4/0x230 [c0000000036332e0] [c000000000cef888] driver_probe_device+0x58/0x120 [c000000003633320] [c000000000cefa6c] __device_attach_driver+0x11c/0x1e0 [c0000000036333a0] [c000000000cebc58] bus_for_each_drv+0xa8/0x130 [c000000003633400] [c000000000ceefcc] __device_attach+0x15c/0x250 [c0000000036334a0] [c000000000ced458] bus_probe_device+0x108/0x110 [c0000000036334f0] [c000000000ce92dc] device_add+0x7fc/0xa10 [c0000000036335b0] [c000000000d447c8] devm_create_dev_dax+0x1d8/0x530 [c000000003633640] [c000000000d46b60] __dax_pmem_probe+0x200/0x270 [c0000000036337b0] [c000000000d46bf0] dax_pmem_probe+0x20/0x70 [c0000000036337d0] [c000000000d2279c] nvdimm_bus_probe+0xac/0x2b0 [c000000003633860] [c000000000cef27c] really_probe+0x19c/0x520 [c0000000036338f0] [c000000000cef6b4] __driver_probe_device+0xb4/0x230 [c000000003633970] [c000000000cef888] driver_probe_device+0x58/0x120 [c0000000036339b0] [c000000000cefd08] __driver_attach+0x1d8/0x240 [c000000003633a30] [c000000000cebb04] bus_for_each_dev+0xb4/0x130 [c000000003633a90] [c000000000cee564] driver_attach+0x34/0x50 [c000000003633ab0] [c000000000ced878] bus_add_driver+0x218/0x300 [c000000003633b40] [c000000000cf1144] driver_register+0xa4/0x1b0 [c000000003633bb0] [c000000000d21a0c] __nd_driver_register+0x5c/0x100 [c000000003633c10] [c00000000206a2e8] dax_pmem_init+0x34/0x48 [c000000003633c30] [c0000000000132d0] do_one_initcall+0x60/0x320 [c000000003633d00] [c0000000020051b0] kernel_init_freeable+0x360/0x400 [c000000003633de0] [c000000000013764] kernel_init+0x34/0x1d0 [c000000003633e50] [c00000000000de14] ret_from_kernel_thread+0x5c/0x64

Fixes 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps")
Cc Joao Martins <[email protected]>
Cc Muchun Song <[email protected]>
Cc Dan Williams <[email protected]>
Cc Mike Kravetz <[email protected]>
---
 include/linux/mm.h  | 16 ++++++++++++++++
 mm/page_alloc.c     | 11 +++++++----
 mm/sparse-vmemmap.c |  3 +--
 3 files changed, 24 insertions(+), 6 deletions(-)
include/linux/mm.h +16 -0
index 1f79667824eb..ced82b9c18e5 100644
@@ -3425,6 +3425,22 @@ void vmemmap_populate_print_last(void);
 void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap);
 #endif
+
+#ifdef CONFIG_ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
+					   struct dev_pagemap *pgmap)
+{
+	return is_power_of_2(sizeof(struct page)) &&
+		pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap;
+}
+#else
+static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
+					   struct dev_pagemap *pgmap)
+{
+	return false;
+}
+#endif
+
 void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
 				  unsigned long nr_pages);
 
mm/page_alloc.c +7 -4
index 7136c36c5d01..cf9f9ddfbd19 100644
@@ -6889,10 +6889,13 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn,
  * of an altmap. See vmemmap_populate_compound_pages().
  */
 static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap,
-					      unsigned long nr_pages)
+					      struct dev_pagemap *pgmap)
 {
-	return is_power_of_2(sizeof(struct page)) &&
-		!altmap ? 2 * (PAGE_SIZE / sizeof(struct page)) : nr_pages;
+
+	if (!vmemmap_can_optimize(altmap, pgmap))
+		return pgmap_vmemmap_nr(pgmap);
+
+	return 2 * (PAGE_SIZE / sizeof(struct page));
 }
 
 static void __ref memmap_init_compound(struct page *head,
@@ -6957,7 +6960,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
 			continue;
 
 		memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
-				     compound_nr_pages(altmap, pfns_per_compound));
+				     compound_nr_pages(altmap, pgmap));
 	}
 
 	pr_info("%s initialised %lu pages in %ums\n", __func__,
mm/sparse-vmemmap.c +1 -2
index c5398a5960d0..10d73a0dfcec 100644
@@ -458,8 +458,7 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
 		!IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION)))
 		return NULL;
 
-	if (is_power_of_2(sizeof(struct page)) &&
-	    pgmap && pgmap_vmemmap_nr(pgmap) > 1 && !altmap)
+	if (vmemmap_can_optimize(altmap, pgmap))
 		r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap);
 	else
 		r = vmemmap_populate(start, end, nid, altmap);
Signature · 1 line
2.39.2
#1 lore raw

PATCH v3 2/2 mm/hugetlb_vmemmap: Rename ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP

Now we use ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP config option to indicate devdax and hugetlb vmemmap optimization support. Hence rename that to a generic ARCH_WANT_OPTIMIZE_VMEMMAP

Cc Joao Martins <[email protected]>
Cc Muchun Song <[email protected]>
Cc Dan Williams <[email protected]>
Cc Mike Kravetz <[email protected]>
---
 arch/loongarch/Kconfig | 2 +-
 arch/s390/Kconfig      | 2 +-
 arch/x86/Kconfig       | 2 +-
 fs/Kconfig             | 9 +--------
 include/linux/mm.h     | 2 +-
 mm/Kconfig             | 6 ++++++
 6 files changed, 11 insertions(+), 12 deletions(-)
arch/loongarch/Kconfig +1 -1
index 7fd51257e0ed..f46baa3f3ea8 100644
@@ -53,8 +53,8 @@ config LOONGARCH
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
-	select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	select ARCH_WANT_LD_ORPHAN_WARN
+	select ARCH_WANT_OPTIMIZE_VMEMMAP
 	select ARCH_WANTS_NO_INSTR
 	select BUILDTIME_TABLE_SORT
 	select COMMON_CLK
arch/s390/Kconfig +1 -1
index 9809c74e1240..f06d7927b8b7 100644
@@ -125,8 +125,8 @@ config S390
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANT_DEFAULT_BPF_JIT
-	select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	select ARCH_WANT_IPC_PARSE_VERSION
+	select ARCH_WANT_OPTIMIZE_VMEMMAP
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS2
 	select DMA_OPS if PCI
arch/x86/Kconfig +1 -1
index a825bf031f49..5269131cc248 100644
@@ -125,8 +125,8 @@ config X86
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANT_GENERAL_HUGETLB
 	select ARCH_WANT_HUGE_PMD_SHARE
-	select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP	if X86_64
 	select ARCH_WANT_LD_ORPHAN_WARN
+	select ARCH_WANT_OPTIMIZE_VMEMMAP	if X86_64
 	select ARCH_WANTS_THP_SWAP		if X86_64
 	select ARCH_HAS_PARANOID_L1D_FLUSH
 	select BUILDTIME_TABLE_SORT
fs/Kconfig +1 -8
index e99830c65033..cc07a0cd3172 100644
@@ -250,16 +250,9 @@ config HUGETLBFS
 config HUGETLB_PAGE
 	def_bool HUGETLBFS
 
-#
-# Select this config option from the architecture Kconfig, if it is preferred
-# to enable the feature of HugeTLB Vmemmap Optimization (HVO).
-#
-config ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
-	bool
-
 config HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	def_bool HUGETLB_PAGE
-	depends on ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+	depends on ARCH_WANT_OPTIMIZE_VMEMMAP
 	depends on SPARSEMEM_VMEMMAP
 
 config HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON
include/linux/mm.h +1 -1
index ced82b9c18e5..cd30c279003c 100644
@@ -3426,7 +3426,7 @@ void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap);
 #endif
 
-#ifdef CONFIG_ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP
 static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
 					   struct dev_pagemap *pgmap)
 {
mm/Kconfig +6 -0
index 4751031f3f05..8a3dfc8bc3a3 100644
@@ -479,6 +479,12 @@ config SPARSEMEM_VMEMMAP
 	  SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
 	  pfn_to_page and page_to_pfn operations.  This is the most
 	  efficient option when sufficient kernel resources are available.
+#
+# Select this config option from the architecture Kconfig, if it is preferred
+# to enable the feature of HugeTLB/dev_dax vmemmap optimization.
+#
+config ARCH_WANT_OPTIMIZE_VMEMMAP
+	bool
 
 config HAVE_MEMBLOCK_PHYS_MAP
 	bool
Signature · 1 line
2.39.2
Reviewed-by on v3 1/2
#2 lore raw
In reply to Aneesh Kumar K.V
Quoted 61 lines · Aneesh Kumar K.V

commit 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps") added support for using optimized vmmemap for devdax devices. But how vmemmap mappings are created are architecture specific. For example, powerpc with hash translation doesn't have vmemmap mappings in init_mm page table instead they are bolted table entries in the hardware page table

vmemmap_populate_compound_pages() used by vmemmap optimization code is not aware of these architecture-specific mapping. Hence allow architecture to opt for this feature. Architectures supporting HUGETLB_PAGE_OPTIMIZE_VMEMMAP option are selected when supporting this feature.

On ppc64 (pmem) where this isn't supported, it fixes below crash:'

BUG: Unable to handle kernel data access on write at 0xc00c000100400038
Faulting instruction address: 0xc000000001269d90
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 7 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc5-150500.34-default+ #2 5c90a668b6bbd142599890245c2fb5de19d7d28a
Hardware name: IBM,9009-42G POWER9 (raw) 0x4e0202 0xf000005 of:IBM,FW950.40 (VL950_099) hv:phyp pSeries
NIP:  c000000001269d90 LR: c0000000004c57d4 CTR: 0000000000000000
REGS: c000000003632c30 TRAP: 0300   Not tainted  (6.3.0-rc5-150500.34-default+)
MSR:  8000000000009033 <SF,EE,ME,IR,DR,RI,LE>  CR: 24842228  XER: 00000000
CFAR: c0000000004c57d0 DAR: c00c000100400038 DSISR: 42000000 IRQMASK: 0
....
NIP [c000000001269d90] __init_single_page.isra.74+0x14/0x4c
LR [c0000000004c57d4] __init_zone_device_page+0x44/0xd0
Call Trace:

[c000000003632ed0] [c000000003632f60] 0xc000000003632f60 (unreliable) [c000000003632f10] [c0000000004c5ca0] memmap_init_zone_device+0x170/0x250 [c000000003632fe0] [c0000000005575f8] memremap_pages+0x2c8/0x7f0 [c0000000036330c0] [c000000000557b5c] devm_memremap_pages+0x3c/0xa0 [c000000003633100] [c000000000d458a8] dev_dax_probe+0x108/0x3e0 [c0000000036331a0] [c000000000d41430] dax_bus_probe+0xb0/0x140 [c0000000036331d0] [c000000000cef27c] really_probe+0x19c/0x520 [c000000003633260] [c000000000cef6b4] __driver_probe_device+0xb4/0x230 [c0000000036332e0] [c000000000cef888] driver_probe_device+0x58/0x120 [c000000003633320] [c000000000cefa6c] __device_attach_driver+0x11c/0x1e0 [c0000000036333a0] [c000000000cebc58] bus_for_each_drv+0xa8/0x130 [c000000003633400] [c000000000ceefcc] __device_attach+0x15c/0x250 [c0000000036334a0] [c000000000ced458] bus_probe_device+0x108/0x110 [c0000000036334f0] [c000000000ce92dc] device_add+0x7fc/0xa10 [c0000000036335b0] [c000000000d447c8] devm_create_dev_dax+0x1d8/0x530 [c000000003633640] [c000000000d46b60] __dax_pmem_probe+0x200/0x270 [c0000000036337b0] [c000000000d46bf0] dax_pmem_probe+0x20/0x70 [c0000000036337d0] [c000000000d2279c] nvdimm_bus_probe+0xac/0x2b0 [c000000003633860] [c000000000cef27c] really_probe+0x19c/0x520 [c0000000036338f0] [c000000000cef6b4] __driver_probe_device+0xb4/0x230 [c000000003633970] [c000000000cef888] driver_probe_device+0x58/0x120 [c0000000036339b0] [c000000000cefd08] __driver_attach+0x1d8/0x240 [c000000003633a30] [c000000000cebb04] bus_for_each_dev+0xb4/0x130 [c000000003633a90] [c000000000cee564] driver_attach+0x34/0x50 [c000000003633ab0] [c000000000ced878] bus_add_driver+0x218/0x300 [c000000003633b40] [c000000000cf1144] driver_register+0xa4/0x1b0 [c000000003633bb0] [c000000000d21a0c] __nd_driver_register+0x5c/0x100 [c000000003633c10] [c00000000206a2e8] dax_pmem_init+0x34/0x48 [c000000003633c30] [c0000000000132d0] do_one_initcall+0x60/0x320 [c000000003633d00] [c0000000020051b0] kernel_init_freeable+0x360/0x400 [c000000003633de0] [c000000000013764] kernel_init+0x34/0x1d0 [c000000003633e50] [c00000000000de14] ret_from_kernel_thread+0x5c/0x64

Quoted 7 lines
Fixes 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps")
Cc Joao Martins <[email protected]>
Cc Muchun Song <[email protected]>
Cc Dan Williams <[email protected]>
Cc Mike Kravetz <[email protected]>
Quoted 77 lines
---
 include/linux/mm.h  | 16 ++++++++++++++++
 mm/page_alloc.c     | 11 +++++++----
 mm/sparse-vmemmap.c |  3 +--
 3 files changed, 24 insertions(+), 6 deletions(-)
include/linux/mm.h +16 -0
index 1f79667824eb..ced82b9c18e5 100644
@@ -3425,6 +3425,22 @@ void vmemmap_populate_print_last(void);
 void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap);
 #endif
+
+#ifdef CONFIG_ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
+					   struct dev_pagemap *pgmap)
+{
+	return is_power_of_2(sizeof(struct page)) &&
+		pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap;
+}
+#else
+static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
+					   struct dev_pagemap *pgmap)
+{
+	return false;
+}
+#endif
+
 void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
 				  unsigned long nr_pages);
 
mm/page_alloc.c +7 -4
index 7136c36c5d01..cf9f9ddfbd19 100644
@@ -6889,10 +6889,13 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn,
  * of an altmap. See vmemmap_populate_compound_pages().
  */
 static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap,
-					      unsigned long nr_pages)
+					      struct dev_pagemap *pgmap)
 {
-	return is_power_of_2(sizeof(struct page)) &&
-		!altmap ? 2 * (PAGE_SIZE / sizeof(struct page)) : nr_pages;
+
+	if (!vmemmap_can_optimize(altmap, pgmap))
+		return pgmap_vmemmap_nr(pgmap);
+
+	return 2 * (PAGE_SIZE / sizeof(struct page));
 }
 
 static void __ref memmap_init_compound(struct page *head,
@@ -6957,7 +6960,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
 			continue;
 
 		memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
-				     compound_nr_pages(altmap, pfns_per_compound));
+				     compound_nr_pages(altmap, pgmap));
 	}
 
 	pr_info("%s initialised %lu pages in %ums\n", __func__,
mm/sparse-vmemmap.c +1 -2
index c5398a5960d0..10d73a0dfcec 100644
@@ -458,8 +458,7 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
 		!IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION)))
 		return NULL;
 
-	if (is_power_of_2(sizeof(struct page)) &&
-	    pgmap && pgmap_vmemmap_nr(pgmap) > 1 && !altmap)
+	if (vmemmap_can_optimize(altmap, pgmap))
 		r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap);
 	else
 		r = vmemmap_populate(start, end, nid, altmap);