lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240806221454.1971755-2-pasha.tatashin@soleen.com>
Date: Tue,  6 Aug 2024 22:14:54 +0000
From: Pasha Tatashin <pasha.tatashin@...een.com>
To: agordeev@...ux.ibm.com,
	akpm@...ux-foundation.org,
	alexghiti@...osinc.com,
	aou@...s.berkeley.edu,
	ardb@...nel.org,
	arnd@...db.de,
	bhe@...hat.com,
	bjorn@...osinc.com,
	borntraeger@...ux.ibm.com,
	bp@...en8.de,
	catalin.marinas@....com,
	chenhuacai@...nel.org,
	chenjiahao16@...wei.com,
	christophe.leroy@...roup.eu,
	dave.hansen@...ux.intel.com,
	david@...hat.com,
	dawei.li@...ngroup.cn,
	gerald.schaefer@...ux.ibm.com,
	gor@...ux.ibm.com,
	hca@...ux.ibm.com,
	hpa@...or.com,
	kent.overstreet@...ux.dev,
	kernel@...0n.name,
	linux-arm-kernel@...ts.infradead.org,
	linux-kernel@...r.kernel.org,
	linux-mm@...ck.org,
	linuxppc-dev@...ts.ozlabs.org,
	linux-riscv@...ts.infradead.org,
	linux-s390@...r.kernel.org,
	loongarch@...ts.linux.dev,
	luto@...nel.org,
	maobibo@...ngson.cn,
	mark.rutland@....com,
	mcgrof@...nel.org,
	mingo@...hat.com,
	mpe@...erman.id.au,
	muchun.song@...ux.dev,
	namcao@...utronix.de,
	naveen@...nel.org,
	npiggin@...il.com,
	osalvador@...e.de,
	palmer@...belt.com,
	pasha.tatashin@...een.com,
	paul.walmsley@...ive.com,
	peterz@...radead.org,
	philmd@...aro.org,
	rdunlap@...radead.org,
	rientjes@...gle.com,
	rppt@...nel.org,
	ryan.roberts@....com,
	souravpanda@...gle.com,
	svens@...ux.ibm.com,
	tglx@...utronix.de,
	tzimmermann@...e.de,
	will@...nel.org,
	x86@...nel.org
Subject: [PATCH 2/2] mm: keep nid around during hot-remove

nid is needed during memory hot-remove in order to account the
information about the memmap overhead that is being removed.

In addition, we cannot use page_pgdat(pfn_to_page(pfn)) during
hotremove after remove_pfn_range_from_zone().

We also cannot determine nid from walking through memblocks after
remove_memory_block_devices() is called.

Therefore, pass nid down from the beginning of hotremove to where
it is used for the accounting purposes.

Reported-by: Yi Zhang <yi.zhang@...hat.com>
Closes: https://lore.kernel.org/linux-cxl/CAHj4cs9Ax1=CoJkgBGP_+sNu6-6=6v=_L-ZBZY0bVLD3wUWZQg@mail.gmail.com
Reported-by: Alison Schofield <alison.schofield@...el.com>
Closes: https://lore.kernel.org/linux-mm/Zq0tPd2h6alFz8XF@aschofie-mobl2/#t

Fixes: 15995a352474 ("mm: report per-page metadata information")
Signed-off-by: Pasha Tatashin <pasha.tatashin@...een.com>
---
 arch/arm64/mm/mmu.c            |  5 +++--
 arch/loongarch/mm/init.c       |  5 +++--
 arch/powerpc/mm/mem.c          |  5 +++--
 arch/riscv/mm/init.c           |  5 +++--
 arch/s390/mm/init.c            |  5 +++--
 arch/x86/mm/init_64.c          |  5 +++--
 include/linux/memory_hotplug.h |  7 ++++---
 mm/memory_hotplug.c            | 18 +++++++++---------
 mm/memremap.c                  |  6 ++++--
 mm/sparse-vmemmap.c            | 14 ++++++++------
 mm/sparse.c                    | 20 +++++++++++---------
 11 files changed, 54 insertions(+), 41 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 353ea5dc32b8..cd0808d05551 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1363,12 +1363,13 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return ret;
 }
 
-void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			int nid)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap, nid);
 	__remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
 }
 
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index bf789d114c2d..64cfbfb75c15 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -106,7 +106,8 @@ int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params)
 	return ret;
 }
 
-void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			int nid)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -115,7 +116,7 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 	/* With altmap the first mapped page is offset from @start */
 	if (altmap)
 		page += vmem_altmap_offset(altmap);
-	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap, nid);
 }
 
 #ifdef CONFIG_NUMA
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index d325217ab201..74c0213f995a 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -157,12 +157,13 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
 	return rc;
 }
 
-void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			      int nid)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap, nid);
 	arch_remove_linear_mapping(start, size);
 }
 #endif
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 8b698d9609e7..bf1be25cc513 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1796,9 +1796,10 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *param
 	return ret;
 }
 
-void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			      int nid)
 {
-	__remove_pages(start >> PAGE_SHIFT, size >> PAGE_SHIFT, altmap);
+	__remove_pages(start >> PAGE_SHIFT, size >> PAGE_SHIFT, altmap, nid);
 	remove_linear_mapping(start, size);
 	flush_tlb_all();
 }
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index e3d258f9e726..bf596d87543a 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -290,12 +290,13 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return rc;
 }
 
-void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			int nid)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap, nid);
 	vmem_remove_mapping(start, size);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index d8dbeac8b206..5bb82fbb7c2c 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1262,12 +1262,13 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end)
 	remove_pagetable(start, end, true, NULL);
 }
 
-void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			      int nid)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap, nid);
 	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 ebe876930e78..47c9af202884 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -201,9 +201,10 @@ static inline bool movable_node_is_enabled(void)
 	return movable_node_enabled;
 }
 
-extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap);
+extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			       int nid);
 extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
-			   struct vmem_altmap *altmap);
+			   struct vmem_altmap *altmap, int nid);
 
 /* reasonably generic interface to expand the physical pages */
 extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
@@ -369,7 +370,7 @@ extern int sparse_add_section(int nid, unsigned long pfn,
 		unsigned long nr_pages, struct vmem_altmap *altmap,
 		struct dev_pagemap *pgmap);
 extern void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
-				  struct vmem_altmap *altmap);
+				  struct vmem_altmap *altmap, int nid);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
 extern struct zone *zone_for_pfn_range(int online_type, int nid,
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 66267c26ca1b..c66148049fa6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -571,7 +571,7 @@ void __ref remove_pfn_range_from_zone(struct zone *zone,
  * calling offline_pages().
  */
 void __remove_pages(unsigned long pfn, unsigned long nr_pages,
-		    struct vmem_altmap *altmap)
+		    struct vmem_altmap *altmap, int nid)
 {
 	const unsigned long end_pfn = pfn + nr_pages;
 	unsigned long cur_nr_pages;
@@ -586,7 +586,7 @@ void __remove_pages(unsigned long pfn, unsigned long nr_pages,
 		/* Select all remaining pages up to the next section boundary */
 		cur_nr_pages = min(end_pfn - pfn,
 				   SECTION_ALIGN_UP(pfn + 1) - pfn);
-		sparse_remove_section(pfn, cur_nr_pages, altmap);
+		sparse_remove_section(pfn, cur_nr_pages, altmap, nid);
 	}
 }
 
@@ -1386,7 +1386,7 @@ bool mhp_supports_memmap_on_memory(void)
 }
 EXPORT_SYMBOL_GPL(mhp_supports_memmap_on_memory);
 
-static void __ref remove_memory_blocks_and_altmaps(u64 start, u64 size)
+static void __ref remove_memory_blocks_and_altmaps(u64 start, u64 size, int nid)
 {
 	unsigned long memblock_size = memory_block_size_bytes();
 	u64 cur_start;
@@ -1409,7 +1409,7 @@ static void __ref remove_memory_blocks_and_altmaps(u64 start, u64 size)
 
 		remove_memory_block_devices(cur_start, memblock_size);
 
-		arch_remove_memory(cur_start, memblock_size, altmap);
+		arch_remove_memory(cur_start, memblock_size, altmap, nid);
 
 		/* Verify that all vmemmap pages have actually been freed. */
 		WARN(altmap->alloc, "Altmap not fully unmapped");
@@ -1454,7 +1454,7 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group,
 		ret = create_memory_block_devices(cur_start, memblock_size,
 						  params.altmap, group);
 		if (ret) {
-			arch_remove_memory(cur_start, memblock_size, NULL);
+			arch_remove_memory(cur_start, memblock_size, NULL, nid);
 			kfree(params.altmap);
 			goto out;
 		}
@@ -1463,7 +1463,7 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group,
 	return 0;
 out:
 	if (ret && cur_start != start)
-		remove_memory_blocks_and_altmaps(start, cur_start - start);
+		remove_memory_blocks_and_altmaps(start, cur_start - start, nid);
 	return ret;
 }
 
@@ -1532,7 +1532,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 		/* create memory block devices after memory was added */
 		ret = create_memory_block_devices(start, size, NULL, group);
 		if (ret) {
-			arch_remove_memory(start, size, params.altmap);
+			arch_remove_memory(start, size, params.altmap, nid);
 			goto error;
 		}
 	}
@@ -2275,10 +2275,10 @@ static int __ref try_remove_memory(u64 start, u64 size)
 		 * No altmaps present, do the removal directly
 		 */
 		remove_memory_block_devices(start, size);
-		arch_remove_memory(start, size, NULL);
+		arch_remove_memory(start, size, NULL, nid);
 	} else {
 		/* all memblocks in the range have altmaps */
-		remove_memory_blocks_and_altmaps(start, size);
+		remove_memory_blocks_and_altmaps(start, size, nid);
 	}
 
 	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
diff --git a/mm/memremap.c b/mm/memremap.c
index 40d4547ce514..08e72959eb48 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -112,9 +112,11 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
 {
 	struct range *range = &pgmap->ranges[range_id];
 	struct page *first_page;
+	int nid;
 
 	/* make sure to access a memmap that was actually initialized */
 	first_page = pfn_to_page(pfn_first(pgmap, range_id));
+	nid = page_to_nid(first_page);
 
 	/* pages are dead and unused, undo the arch mapping */
 	mem_hotplug_begin();
@@ -122,10 +124,10 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
 				   PHYS_PFN(range_len(range)));
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
 		__remove_pages(PHYS_PFN(range->start),
-			       PHYS_PFN(range_len(range)), NULL);
+			       PHYS_PFN(range_len(range)), NULL, nid);
 	} else {
 		arch_remove_memory(range->start, range_len(range),
-				pgmap_altmap(pgmap));
+				   pgmap_altmap(pgmap), nid);
 		kasan_remove_zero_shadow(__va(range->start), range_len(range));
 	}
 	mem_hotplug_done();
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 1dda6c53370b..0dafad626ab8 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -469,12 +469,14 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
 	if (r < 0)
 		return NULL;
 
-	if (system_state == SYSTEM_BOOTING) {
-		mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(end - start,
-								  PAGE_SIZE));
-	} else {
-		mod_node_page_state(NODE_DATA(nid), NR_MEMMAP,
-				    DIV_ROUND_UP(end - start, PAGE_SIZE));
+	if (nid != NUMA_NO_NODE) {
+		if (system_state == SYSTEM_BOOTING) {
+			mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(end - start,
+									  PAGE_SIZE));
+		} else {
+			mod_node_page_state(NODE_DATA(nid), NR_MEMMAP,
+					    DIV_ROUND_UP(end - start, PAGE_SIZE));
+		}
 	}
 
 	return pfn_to_page(pfn);
diff --git a/mm/sparse.c b/mm/sparse.c
index e4b830091d13..fc01bc5f0f1d 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -638,13 +638,15 @@ static struct page * __meminit populate_section_memmap(unsigned long pfn,
 }
 
 static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap)
+		struct vmem_altmap *altmap, int nid)
 {
 	unsigned long start = (unsigned long) pfn_to_page(pfn);
 	unsigned long end = start + nr_pages * sizeof(struct page);
 
-	mod_node_page_state(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP,
-			    -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE)));
+	if (nid != NUMA_NO_NODE) {
+		mod_node_page_state(NODE_DATA(nid), NR_MEMMAP,
+				    -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE)));
+	}
 	vmemmap_free(start, end, altmap);
 }
 static void free_map_bootmem(struct page *memmap)
@@ -713,7 +715,7 @@ static struct page * __meminit populate_section_memmap(unsigned long pfn,
 }
 
 static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap)
+		struct vmem_altmap *altmap, int nid)
 {
 	kvfree(pfn_to_page(pfn));
 }
@@ -781,7 +783,7 @@ static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
  * For 2 and 3, the SPARSEMEM_VMEMMAP={y,n} cases are unified
  */
 static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap)
+		struct vmem_altmap *altmap, int nid)
 {
 	struct mem_section *ms = __pfn_to_section(pfn);
 	bool section_is_early = early_section(ms);
@@ -821,7 +823,7 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 	 * section_activate() and pfn_valid() .
 	 */
 	if (!section_is_early)
-		depopulate_section_memmap(pfn, nr_pages, altmap);
+		depopulate_section_memmap(pfn, nr_pages, altmap, nid);
 	else if (memmap)
 		free_map_bootmem(memmap);
 
@@ -865,7 +867,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
 
 	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
 	if (!memmap) {
-		section_deactivate(pfn, nr_pages, altmap);
+		section_deactivate(pfn, nr_pages, altmap, nid);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -928,13 +930,13 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 }
 
 void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
-			   struct vmem_altmap *altmap)
+			   struct vmem_altmap *altmap, int nid)
 {
 	struct mem_section *ms = __pfn_to_section(pfn);
 
 	if (WARN_ON_ONCE(!valid_section(ms)))
 		return;
 
-	section_deactivate(pfn, nr_pages, altmap);
+	section_deactivate(pfn, nr_pages, altmap, nid);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
-- 
2.46.0.76.ge559c4bf1a-goog


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ