From patchwork series 497059

Fox Snowpatch · Fox Snowpatch · commit 5cdf00c0b23d · 2026-03-23T07:51:10.000Z
https://patchwork.ozlabs.org//project/linuxppc-dev/list/?series=497059
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
@@ -385,9 +385,6 @@ void free_initmem(void)
 	WARN_ON(!IS_ALIGNED((unsigned long)lm_init_begin, PAGE_SIZE));
 	WARN_ON(!IS_ALIGNED((unsigned long)lm_init_end, PAGE_SIZE));
 
-	/* Delete __init region from memblock.reserved. */
-	memblock_free(lm_init_begin, lm_init_end - lm_init_begin);
-
 	free_reserved_area(lm_init_begin, lm_init_end,
 			   POISON_FREE_INITMEM, "unused kernel");
 	/*
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
@@ -775,24 +775,12 @@ void __init fadump_update_elfcore_header(char *bufp)
 
 static void *__init fadump_alloc_buffer(unsigned long size)
 {
-	unsigned long count, i;
-	struct page *page;
-	void *vaddr;
-
-	vaddr = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
-	if (!vaddr)
-		return NULL;
-
-	count = PAGE_ALIGN(size) / PAGE_SIZE;
-	page = virt_to_page(vaddr);
-	for (i = 0; i < count; i++)
-		mark_page_reserved(page + i);
-	return vaddr;
+	return  alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
 }
 
 static void fadump_free_buffer(unsigned long vaddr, unsigned long size)
 {
-	free_reserved_area((void *)vaddr, (void *)(vaddr + size), -1, NULL);
+	free_pages_exact((void *)vaddr, size);
 }
 
 s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus)
diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c
@@ -303,7 +303,6 @@ static int __init create_opalcore(void)
 	struct device_node *dn;
 	struct opalcore *new;
 	loff_t opalcore_off;
-	struct page *page;
 	Elf64_Phdr *phdr;
 	Elf64_Ehdr *elf;
 	int i, ret;
@@ -328,11 +327,6 @@ static int __init create_opalcore(void)
 		oc_conf->opalcorebuf_sz = 0;
 		return -ENOMEM;
 	}
-	count = oc_conf->opalcorebuf_sz / PAGE_SIZE;
-	page = virt_to_page(oc_conf->opalcorebuf);
-	for (i = 0; i < count; i++)
-		mark_page_reserved(page + i);
-
 	pr_debug("opalcorebuf = 0x%llx\n", (u64)oc_conf->opalcorebuf);
 
 	/* Read OPAL related device-tree entries */
@@ -437,10 +431,7 @@ static void opalcore_cleanup(void)
 
 	/* free the buffer used for setting up OPAL core */
 	if (oc_conf->opalcorebuf) {
-		void *end = (void *)((u64)oc_conf->opalcorebuf +
-				     oc_conf->opalcorebuf_sz);
-
-		free_reserved_area(oc_conf->opalcorebuf, end, -1, NULL);
+		free_pages_exact(oc_conf->opalcorebuf, oc_conf->opalcorebuf_sz);
 		oc_conf->opalcorebuf = NULL;
 		oc_conf->opalcorebuf_sz = 0;
 	}
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
@@ -183,14 +183,12 @@ static struct mdesc_handle * __init mdesc_memblock_alloc(unsigned int mdesc_size
 static void __init mdesc_memblock_free(struct mdesc_handle *hp)
 {
 	unsigned int alloc_size;
-	unsigned long start;
 
 	BUG_ON(refcount_read(&hp->refcnt) != 0);
 	BUG_ON(!list_empty(&hp->list));
 
 	alloc_size = PAGE_ALIGN(hp->handle_size);
-	start = __pa(hp);
-	memblock_free_late(start, alloc_size);
+	memblock_free(hp, alloc_size);
 }
 
 static struct mdesc_mem_ops memblock_mdesc_ops = {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
@@ -426,7 +426,7 @@ int __init ima_free_kexec_buffer(void)
 	if (!ima_kexec_buffer_size)
 		return -ENOENT;
 
-	memblock_free_late(ima_kexec_buffer_phys,
+	memblock_phys_free(ima_kexec_buffer_phys,
 			   ima_kexec_buffer_size);
 
 	ima_kexec_buffer_phys = 0;
diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c
@@ -34,10 +34,7 @@ static
 void __init __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags)
 {
 	if (flags & EFI_MEMMAP_MEMBLOCK) {
-		if (slab_is_available())
-			memblock_free_late(phys, size);
-		else
-			memblock_phys_free(phys, size);
+		memblock_phys_free(phys, size);
 	} else if (flags & EFI_MEMMAP_SLAB) {
 		struct page *p = pfn_to_page(PHYS_PFN(phys));
 		unsigned int order = get_order(size);
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
@@ -372,7 +372,7 @@ void __init efi_reserve_boot_services(void)
 		 * doesn't make sense as far as the firmware is
 		 * concerned, but it does provide us with a way to tag
 		 * those regions that must not be paired with
-		 * memblock_free_late().
+		 * memblock_phys_free().
 		 */
 		md->attribute |= EFI_MEMORY_RUNTIME;
 	}
diff --git a/drivers/firmware/efi/apple-properties.c b/drivers/firmware/efi/apple-properties.c
@@ -226,7 +226,7 @@ static int __init map_properties(void)
 		 */
 		data->len = 0;
 		memunmap(data);
-		memblock_free_late(pa_data + sizeof(*data), data_len);
+		memblock_phys_free(pa_data + sizeof(*data), data_len);
 
 		return ret;
 	}
diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c
@@ -175,7 +175,7 @@ int __init ima_free_kexec_buffer(void)
 	if (ret)
 		return ret;
 
-	memblock_free_late(addr, size);
+	memblock_phys_free(addr, size);
 	return 0;
 }
 #endif
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
@@ -172,8 +172,6 @@ void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags,
 			  struct memblock_type *type_b, phys_addr_t *out_start,
 			  phys_addr_t *out_end, int *out_nid);
 
-void memblock_free_late(phys_addr_t base, phys_addr_t size);
-
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
 static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
 					phys_addr_t *out_start,
diff --git a/init/initramfs.c b/init/initramfs.c
@@ -652,13 +652,6 @@ void __init reserve_initrd_mem(void)
 
 void __weak __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-#ifdef CONFIG_ARCH_KEEP_MEMBLOCK
-	unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE);
-	unsigned long aligned_end = ALIGN(end, PAGE_SIZE);
-
-	memblock_free((void *)aligned_start, aligned_end - aligned_start);
-#endif
-
 	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
 			"initrd");
 }
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
@@ -546,10 +546,10 @@ void __init swiotlb_exit(void)
 		free_pages(tbl_vaddr, get_order(tbl_size));
 		free_pages((unsigned long)mem->slots, get_order(slots_size));
 	} else {
-		memblock_free_late(__pa(mem->areas),
+		memblock_free(mem->areas,
 			array_size(sizeof(*mem->areas), mem->nareas));
-		memblock_free_late(mem->start, tbl_size);
-		memblock_free_late(__pa(mem->slots), slots_size);
+		memblock_phys_free(mem->start, tbl_size);
+		memblock_free(mem->slots, slots_size);
 	}
 
 	memset(mem, 0, sizeof(*mem));
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
@@ -64,7 +64,7 @@ static inline void __init xbc_free_mem(void *addr, size_t size, bool early)
 	if (early)
 		memblock_free(addr, size);
 	else if (addr)
-		memblock_free_late(__pa(addr), size);
+		memblock_free(addr, size);
 }
 
 #else /* !__KERNEL__ */
diff --git a/mm/internal.h b/mm/internal.h
@@ -1233,7 +1233,17 @@ static inline void vunmap_range_noflush(unsigned long start, unsigned long end)
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 DECLARE_STATIC_KEY_TRUE(deferred_pages);
 
+static inline bool deferred_pages_enabled(void)
+{
+	return static_branch_unlikely(&deferred_pages);
+}
+
 bool __init deferred_grow_zone(struct zone *zone, unsigned int order);
+#else
+static inline bool deferred_pages_enabled(void)
+{
+	return false;
+}
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 void init_deferred_page(unsigned long pfn, int nid);
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
@@ -731,10 +731,10 @@ static bool __init kfence_init_pool_early(void)
 	 * fails for the first page, and therefore expect addr==__kfence_pool in
 	 * most failure cases.
 	 */
-	memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool));
+	memblock_free((void *)addr, KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool));
 	__kfence_pool = NULL;
 
-	memblock_free_late(__pa(kfence_metadata_init), KFENCE_METADATA_SIZE);
+	memblock_free(kfence_metadata_init, KFENCE_METADATA_SIZE);
 	kfence_metadata_init = NULL;
 
 	return false;
diff --git a/mm/memblock.c b/mm/memblock.c
@@ -384,26 +384,27 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
  */
 void __init memblock_discard(void)
 {
-	phys_addr_t addr, size;
+	phys_addr_t size;
+	void *addr;
 
 	if (memblock.reserved.regions != memblock_reserved_init_regions) {
-		addr = __pa(memblock.reserved.regions);
+		addr = memblock.reserved.regions;
 		size = PAGE_ALIGN(sizeof(struct memblock_region) *
 				  memblock.reserved.max);
 		if (memblock_reserved_in_slab)
-			kfree(memblock.reserved.regions);
+			kfree(addr);
 		else
-			memblock_free_late(addr, size);
+			memblock_free(addr, size);
 	}
 
 	if (memblock.memory.regions != memblock_memory_init_regions) {
-		addr = __pa(memblock.memory.regions);
+		addr = memblock.memory.regions;
 		size = PAGE_ALIGN(sizeof(struct memblock_region) *
 				  memblock.memory.max);
 		if (memblock_memory_in_slab)
-			kfree(memblock.memory.regions);
+			kfree(addr);
 		else
-			memblock_free_late(addr, size);
+			memblock_free(addr, size);
 	}
 
 	memblock_memory = NULL;
@@ -893,13 +894,81 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
 	return memblock_remove_range(&memblock.memory, base, size);
 }
 
+static unsigned long __free_reserved_area(phys_addr_t start, phys_addr_t end,
+					  int poison)
+{
+	unsigned long pages = 0, pfn;
+
+	if (deferred_pages_enabled()) {
+		WARN(1, "Cannot free reserved memory because of deferred initialization of the memory map");
+		return 0;
+	}
+
+	for_each_valid_pfn(pfn, PFN_UP(start), PFN_DOWN(end)) {
+		struct page *page = pfn_to_page(pfn);
+		void *direct_map_addr;
+
+		/*
+		 * 'direct_map_addr' might be different from the kernel virtual
+		 * address because some architectures use aliases.
+		 * Going via physical address, pfn_to_page() and page_address()
+		 * ensures that we get a _writeable_ alias for the memset().
+		 */
+		direct_map_addr = page_address(page);
+		/*
+		 * Perform a kasan-unchecked memset() since this memory
+		 * has not been initialized.
+		 */
+		direct_map_addr = kasan_reset_tag(direct_map_addr);
+		if ((unsigned int)poison <= 0xFF)
+			memset(direct_map_addr, poison, PAGE_SIZE);
+
+		free_reserved_page(page);
+		pages++;
+	}
+	return pages;
+}
+
+unsigned long free_reserved_area(void *start, void *end, int poison, const char *s)
+{
+	phys_addr_t start_pa, end_pa;
+	unsigned long pages;
+
+	/*
+	 * end is the first address past the region and it may be beyond what
+	 * __pa() or __pa_symbol() can handle.
+	 * Use the address included in the range for the conversion and add back
+	 * 1 afterwards.
+	 */
+	if (__is_kernel((unsigned long)start)) {
+		start_pa = __pa_symbol(start);
+		end_pa = __pa_symbol(end - 1) + 1;
+	} else {
+		start_pa = __pa(start);
+		end_pa = __pa(end - 1) + 1;
+	}
+
+	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
+		if (start_pa < end_pa)
+			memblock_remove_range(&memblock.reserved,
+					      start_pa, end_pa - start_pa);
+	}
+
+	pages = __free_reserved_area(start_pa, end_pa, poison);
+	if (pages && s)
+		pr_info("Freeing %s memory: %ldK\n", s, K(pages));
+
+	return pages;
+}
+
 /**
  * memblock_free - free boot memory allocation
  * @ptr: starting address of the  boot memory allocation
  * @size: size of the boot memory block in bytes
  *
  * Free boot memory block previously allocated by memblock_alloc_xx() API.
- * The freeing memory will not be released to the buddy allocator.
+ * If called after the buddy allocator is available, the memory is released to
+ * the buddy allocator.
  */
 void __init_memblock memblock_free(void *ptr, size_t size)
 {
@@ -913,17 +982,24 @@ void __init_memblock memblock_free(void *ptr, size_t size)
  * @size: size of the boot memory block in bytes
  *
  * Free boot memory block previously allocated by memblock_phys_alloc_xx() API.
- * The freeing memory will not be released to the buddy allocator.
+ * If called after the buddy allocator is available, the memory is released to
+ * the buddy allocator.
  */
 int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size)
 {
 	phys_addr_t end = base + size - 1;
+	int ret;
 
 	memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
 		     &base, &end, (void *)_RET_IP_);
 
 	kmemleak_free_part_phys(base, size);
-	return memblock_remove_range(&memblock.reserved, base, size);
+	ret = memblock_remove_range(&memblock.reserved, base, size);
+
+	if (slab_is_available())
+		__free_reserved_area(base, base + size, -1);
+
+	return ret;
 }
 
 int __init_memblock __memblock_reserve(phys_addr_t base, phys_addr_t size,
@@ -1751,32 +1827,6 @@ void *__init __memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align,
 	return addr;
 }
 
-/**
- * memblock_free_late - free pages directly to buddy allocator
- * @base: phys starting address of the  boot memory block
- * @size: size of the boot memory block in bytes
- *
- * This is only useful when the memblock allocator has already been torn
- * down, but we are still initializing the system.  Pages are released directly
- * to the buddy allocator.
- */
-void __init memblock_free_late(phys_addr_t base, phys_addr_t size)
-{
-	phys_addr_t cursor, end;
-
-	end = base + size - 1;
-	memblock_dbg("%s: [%pa-%pa] %pS\n",
-		     __func__, &base, &end, (void *)_RET_IP_);
-	kmemleak_free_part_phys(base, size);
-	cursor = PFN_UP(base);
-	end = PFN_DOWN(base + size);
-
-	for (; cursor < end; cursor++) {
-		memblock_free_pages(cursor, 0);
-		totalram_pages_inc();
-	}
-}
-
 /*
  * Remaining API functions
  */
@@ -2434,7 +2484,7 @@ int reserve_mem_release_by_name(const char *name)
 		return 0;
 
 	start = phys_to_virt(map->start);
-	end = start + map->size - 1;
+	end = start + map->size;
 	snprintf(buf, sizeof(buf), "reserve_mem:%s", name);
 	free_reserved_area(start, end, 0, buf);
 	map->size = 0;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h
diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h

Original file line number	Diff line number	Diff line change
`@@ -775,24 +775,12 @@ void __init fadump_update_elfcore_header(char *bufp)`
`775`	`775`
`776`	`776`	`static void *__init fadump_alloc_buffer(unsigned long size)`
`777`	`777`	`{`
`778`		`- unsigned long count, i;`
`779`		`- struct page *page;`
`780`		`- void *vaddr;`
`781`		`-`
`782`		`- vaddr = alloc_pages_exact(size, GFP_KERNEL \| __GFP_ZERO);`
`783`		`- if (!vaddr)`
`784`		`- return NULL;`
`785`		`-`
`786`		`- count = PAGE_ALIGN(size) / PAGE_SIZE;`
`787`		`- page = virt_to_page(vaddr);`
`788`		`- for (i = 0; i < count; i++)`
`789`		`- mark_page_reserved(page + i);`
`790`		`- return vaddr;`
	`778`	`+ return alloc_pages_exact(size, GFP_KERNEL \| __GFP_ZERO);`
`791`	`779`	`}`
`792`	`780`
`793`	`781`	`static void fadump_free_buffer(unsigned long vaddr, unsigned long size)`
`794`	`782`	`{`
`795`		`- free_reserved_area((void )vaddr, (void )(vaddr + size), -1, NULL);`
	`783`	`+ free_pages_exact((void *)vaddr, size);`
`796`	`784`	`}`
`797`	`785`
`798`	`786`	`s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus)`
Original file line number	Diff line number	Diff line change
`@@ -183,14 +183,12 @@ static struct mdesc_handle * __init mdesc_memblock_alloc(unsigned int mdesc_size`
`183`	`183`	`static void __init mdesc_memblock_free(struct mdesc_handle *hp)`
`184`	`184`	`{`
`185`	`185`	`unsigned int alloc_size;`
`186`		`- unsigned long start;`
`187`	`186`
`188`	`187`	`BUG_ON(refcount_read(&hp->refcnt) != 0);`
`189`	`188`	`BUG_ON(!list_empty(&hp->list));`
`190`	`189`
`191`	`190`	`alloc_size = PAGE_ALIGN(hp->handle_size);`
`192`		`- start = __pa(hp);`
`193`		`- memblock_free_late(start, alloc_size);`
	`191`	`+ memblock_free(hp, alloc_size);`
`194`	`192`	`}`
`195`	`193`
`196`	`194`	`static struct mdesc_mem_ops memblock_mdesc_ops = {`
Original file line number	Diff line number	Diff line change
`@@ -372,7 +372,7 @@ void __init efi_reserve_boot_services(void)`
`372`	`372`	`* doesn't make sense as far as the firmware is`
`373`	`373`	`* concerned, but it does provide us with a way to tag`
`374`	`374`	`* those regions that must not be paired with`
`375`		`- * memblock_free_late().`
	`375`	`+ * memblock_phys_free().`
`376`	`376`	`*/`
`377`	`377`	`md->attribute \|= EFI_MEMORY_RUNTIME;`
`378`	`378`	`}`
Original file line number	Diff line number	Diff line change
`@@ -226,7 +226,7 @@ static int __init map_properties(void)`
`226`	`226`	`*/`
`227`	`227`	`data->len = 0;`
`228`	`228`	`memunmap(data);`
`229`		`- memblock_free_late(pa_data + sizeof(*data), data_len);`
	`229`	`+ memblock_phys_free(pa_data + sizeof(*data), data_len);`
`230`	`230`
`231`	`231`	`return ret;`
`232`	`232`	`}`
Original file line number	Diff line number	Diff line change
`@@ -175,7 +175,7 @@ int __init ima_free_kexec_buffer(void)`
`175`	`175`	`if (ret)`
`176`	`176`	`return ret;`
`177`	`177`
`178`		`- memblock_free_late(addr, size);`
	`178`	`+ memblock_phys_free(addr, size);`
`179`	`179`	`return 0;`
`180`	`180`	`}`
`181`	`181`	`#endif`