Re: [PATCH v1 2/4] memblock: allow to specify flags with memblock_add_node()
On Mon, Sep 27, 2021 at 5:05 PM David Hildenbrand wrote: > We want to specify flags when hotplugging memory. Let's prepare to pass > flags to memblock_add_node() by adjusting all existing users. > > Note that when hotplugging memory the system is already up and running > and we don't want to add the memory first and apply flags later: it > should happen within one memblock call. > > Signed-off-by: David Hildenbrand > arch/m68k/mm/mcfmmu.c| 3 ++- > arch/m68k/mm/motorola.c | 6 -- Acked-by: Geert Uytterhoeven Gr{oetje,eeting}s, Geert -- Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- ge...@linux-m68k.org In personal conversations with technical people, I call myself a hacker. But when I'm talking to journalists I just say "programmer" or something like that. -- Linus Torvalds ___ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec
Re: [PATCH v1 0/4] mm/memory_hotplug: full support for
Intended subject was "[PATCH v1 0/4] mm/memory_hotplug: full support for add_memory_driver_managed() with CONFIG_ARCH_KEEP_MEMBLOCK" -- Thanks, David / dhildenb ___ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec
[PATCH v1 2/4] memblock: allow to specify flags with memblock_add_node()
We want to specify flags when hotplugging memory. Let's prepare to pass flags to memblock_add_node() by adjusting all existing users. Note that when hotplugging memory the system is already up and running and we don't want to add the memory first and apply flags later: it should happen within one memblock call. Signed-off-by: David Hildenbrand --- arch/arc/mm/init.c | 4 ++-- arch/ia64/mm/contig.c| 2 +- arch/ia64/mm/init.c | 2 +- arch/m68k/mm/mcfmmu.c| 3 ++- arch/m68k/mm/motorola.c | 6 -- arch/mips/loongson64/init.c | 4 +++- arch/mips/sgi-ip27/ip27-memory.c | 3 ++- arch/s390/kernel/setup.c | 3 ++- include/linux/memblock.h | 3 ++- include/linux/mm.h | 2 +- mm/memblock.c| 9 + mm/memory_hotplug.c | 2 +- 12 files changed, 26 insertions(+), 17 deletions(-) diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 699ecf119641..110eb69e9bee 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -59,13 +59,13 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) low_mem_sz = size; in_use = 1; - memblock_add_node(base, size, 0); + memblock_add_node(base, size, 0, MEMBLOCK_NONE); } else { #ifdef CONFIG_HIGHMEM high_mem_start = base; high_mem_sz = size; in_use = 1; - memblock_add_node(base, size, 1); + memblock_add_node(base, size, 1, MEMBLOCK_NONE); memblock_reserve(base, size); #endif } diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 42e025cfbd08..24901d809301 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -153,7 +153,7 @@ find_memory (void) efi_memmap_walk(find_max_min_low_pfn, NULL); max_pfn = max_low_pfn; - memblock_add_node(0, PFN_PHYS(max_low_pfn), 0); + memblock_add_node(0, PFN_PHYS(max_low_pfn), 0, MEMBLOCK_NONE); find_initrd(); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 5c6da8d83c1a..5d165607bf35 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -378,7 +378,7 @@ int __init register_active_ranges(u64 start, u64 len, int nid) #endif if (start < end) - memblock_add_node(__pa(start), end - start, nid); + memblock_add_node(__pa(start), end - start, nid, MEMBLOCK_NONE); return 0; } diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index eac9dde65193..6f1f25125294 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -174,7 +174,8 @@ void __init cf_bootmem_alloc(void) m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; - memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0, + MEMBLOCK_NONE); /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 3a653f0a4188..e80c5d7e6728 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -410,7 +410,8 @@ void __init paging_init(void) min_addr = m68k_memory[0].addr; max_addr = min_addr + m68k_memory[0].size; - memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0, + MEMBLOCK_NONE); for (i = 1; i < m68k_num_memory;) { if (m68k_memory[i].addr < min_addr) { printk("Ignoring memory chunk at 0x%lx:0x%lx before the first chunk\n", @@ -421,7 +422,8 @@ void __init paging_init(void) (m68k_num_memory - i) * sizeof(struct m68k_mem_info)); continue; } - memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i); + memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i, + MEMBLOCK_NONE); addr = m68k_memory[i].addr + m68k_memory[i].size; if (addr > max_addr) max_addr = addr; diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c index 76e0a9636a0e..4ac5ba80bbf6 100644 --- a/arch/mips/loongson64/init.c +++ b/arch/mips/loongson64/init.c @@ -77,7 +77,9 @@ void __init szmem(unsigned int node) (u32)node_id, mem_type, mem_start, mem_size); pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); - memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(node_psize), node); + memblock_add_node(PFN_PHYS(start_pfn), +
[PATCH v1 3/4] memblock: add MEMBLOCK_DRIVER_MANAGED to mimic IORESOURCE_SYSRAM_DRIVER_MANAGED
Let's add a flag that corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED. Similar to MEMBLOCK_HOTPLUG, most infrastructure has to treat such memory like ordinary MEMBLOCK_NONE memory -- for example, when selecting memory regions to add to the vmcore for dumping in the crashkernel via for_each_mem_range(). However, especially kexec_file is not supposed to select such memblocks via for_each_free_mem_range() / for_each_free_mem_range_reverse() to place kexec images, similar to how we handle IORESOURCE_SYSRAM_DRIVER_MANAGED without CONFIG_ARCH_KEEP_MEMBLOCK. Let's document why kexec_walk_memblock() won't try placing images on areas marked MEMBLOCK_DRIVER_MANAGED -- similar to IORESOURCE_SYSRAM_DRIVER_MANAGED handling in locate_mem_hole_callback() via kexec_walk_resources(). We'll make sure that memory hotplug code sets the flag where applicable (IORESOURCE_SYSRAM_DRIVER_MANAGED) next. This prepares architectures that need CONFIG_ARCH_KEEP_MEMBLOCK, such as arm64, for virtio-mem support. Signed-off-by: David Hildenbrand --- include/linux/memblock.h | 16 ++-- kernel/kexec_file.c | 5 + mm/memblock.c| 4 3 files changed, 23 insertions(+), 2 deletions(-) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b49a58f621bc..7d8d656d5082 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -33,12 +33,17 @@ extern unsigned long long max_possible_pfn; * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as * reserved in the memory map; refer to memblock_mark_nomap() description * for further details + * @MEMBLOCK_DRIVER_MANAGED: memory region that is always detected via a driver, + * corresponding to IORESOURCE_SYSRAM_DRIVER_MANAGED in the kernel resource + * tree. Especially kexec should never use this memory for placing images and + * shouldn't expose this memory to the second kernel. */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG= 0x1, /* hotpluggable region */ MEMBLOCK_MIRROR = 0x2, /* mirrored region */ MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ + MEMBLOCK_DRIVER_MANAGED = 0x8, /* always detected via a driver */ }; /** @@ -209,7 +214,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range(i, p_start, p_end) \ __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \ -MEMBLOCK_HOTPLUG, p_start, p_end, NULL) +MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED, \ +p_start, p_end, NULL) /** * for_each_mem_range_rev - reverse iterate through memblock areas from @@ -220,7 +226,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range_rev(i, p_start, p_end) \ __for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \ -MEMBLOCK_HOTPLUG, p_start, p_end, NULL) +MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED,\ +p_start, p_end, NULL) /** * for_each_reserved_mem_range - iterate over all reserved memblock areas @@ -250,6 +257,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m) return m->flags & MEMBLOCK_NOMAP; } +static inline bool memblock_is_driver_managed(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_DRIVER_MANAGED; +} + int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 33400ff051a8..8347fc158d2b 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -556,6 +556,11 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf, if (kbuf->image->type == KEXEC_TYPE_CRASH) return func(&crashk_res, kbuf); + /* +* Using MEMBLOCK_NONE will properly skip MEMBLOCK_DRIVER_MANAGED. See +* IORESOURCE_SYSRAM_DRIVER_MANAGED handling in +* locate_mem_hole_callback(). +*/ if (kbuf->top_down) { for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE, &mstart, &mend, NULL) { diff --git a/mm/memblock.c b/mm/memblock.c index 47a56b223141..540a35317fb0 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -979,6 +979,10 @@ static bool should_skip_region(struct memblock_type *type, if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; + /* skip driver-managed memory unless we were asked for it explicitly */ + if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) + return true; +
[PATCH v1 0/4] mm/memory_hotplug: full support for
Architectures that require CONFIG_ARCH_KEEP_MEMBLOCK=y, such as arm64, don't cleanly support add_memory_driver_managed() yet. Most prominently, kexec_file can still end up placing images on such driver-managed memory, resulting in undesired behavior. Teaching kexec to not place images on driver-managed memory is especially relevant for virtio-mem. Details can be found in commit 7b7b27214bba ("mm/memory_hotplug: introduce add_memory_driver_managed()"). Extend memblock with a new flag and set it from memory hotplug code when applicable. This is required to fully support virtio-mem on arm64, making also kexec_file behave like on x86-64. Alternative A: Extend kexec_walk_memblock() to consult the kernel resource tree whether IORESOURCE_SYSRAM_DRIVER_MANAGED is set. This feels wrong, because the goal was to rely on memblock and not the resource tree. Alternative B: Reuse MEMBLOCK_HOTPLUG. MEMBLOCK_HOTPLUG serves a different purpose, though. Cc: Andrew Morton Cc: Mike Rapoport Cc: Michal Hocko Cc: Oscar Salvador Cc: Jianyong Wu Cc: Aneesh Kumar K.V Cc: Vineet Gupta Cc: Geert Uytterhoeven Cc: Huacai Chen Cc: Jiaxun Yang Cc: Thomas Bogendoerfer Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Eric Biederman Cc: Arnd Bergmann Cc: linux-snps-...@lists.infradead.org Cc: linux-i...@vger.kernel.org Cc: linux-m...@lists.linux-m68k.org Cc: linux-m...@vger.kernel.org Cc: linux-s...@vger.kernel.org Cc: linux...@kvack.org Cc: kexec@lists.infradead.org David Hildenbrand (4): mm/memory_hotplug: handle memblock_add_node() failures in add_memory_resource() memblock: allow to specify flags with memblock_add_node() memblock: add MEMBLOCK_DRIVER_MANAGED to mimic IORESOURCE_SYSRAM_DRIVER_MANAGED mm/memory_hotplug: indicate MEMBLOCK_DRIVER_MANAGED with IORESOURCE_SYSRAM_DRIVER_MANAGED arch/arc/mm/init.c | 4 ++-- arch/ia64/mm/contig.c| 2 +- arch/ia64/mm/init.c | 2 +- arch/m68k/mm/mcfmmu.c| 3 ++- arch/m68k/mm/motorola.c | 6 -- arch/mips/loongson64/init.c | 4 +++- arch/mips/sgi-ip27/ip27-memory.c | 3 ++- arch/s390/kernel/setup.c | 3 ++- include/linux/memblock.h | 19 --- include/linux/mm.h | 2 +- kernel/kexec_file.c | 5 + mm/memblock.c| 13 + mm/memory_hotplug.c | 11 +-- 13 files changed, 57 insertions(+), 20 deletions(-) base-commit: 5816b3e6577eaa676ceb00a848f0fd65fe2adc29 -- 2.31.1 ___ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec
[PATCH v1 1/4] mm/memory_hotplug: handle memblock_add_node() failures in add_memory_resource()
If memblock_add_node() fails, we're most probably running out of memory. While this is unlikely to happen, it can happen and having memory added without a memblock can be problematic for architectures that use memblock to detect valid memory. Let's fail in a nice way instead of silently ignoring the error. Signed-off-by: David Hildenbrand --- mm/memory_hotplug.c | 8 ++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9fd0be32a281..917b3528636d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1384,8 +1384,11 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) mem_hotplug_begin(); - if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) - memblock_add_node(start, size, nid); + if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { + ret = memblock_add_node(start, size, nid); + if (ret) + goto error_mem_hotplug_end; + } ret = __try_online_node(nid, false); if (ret < 0) @@ -1458,6 +1461,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) rollback_node_hotadd(nid); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) memblock_remove(start, size); +error_mem_hotplug_end: mem_hotplug_done(); return ret; } -- 2.31.1 ___ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec
[PATCH v1 4/4] mm/memory_hotplug: indicate MEMBLOCK_DRIVER_MANAGED with IORESOURCE_SYSRAM_DRIVER_MANAGED
Let's communicate driver-managed regions to memblock, to properly teach kexec_file with CONFIG_ARCH_KEEP_MEMBLOCK to not place images on these memory regions. Signed-off-by: David Hildenbrand --- mm/memory_hotplug.c | 5 - 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 5f873e7f5b29..6d90818d4ce8 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1357,6 +1357,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size) int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) { struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; + enum memblock_flags memblock_flags = MEMBLOCK_NONE; struct vmem_altmap mhp_altmap = {}; struct memory_group *group = NULL; u64 start, size; @@ -1385,7 +1386,9 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) mem_hotplug_begin(); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { - ret = memblock_add_node(start, size, nid, MEMBLOCK_NONE); + if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED) + memblock_flags = MEMBLOCK_DRIVER_MANAGED; + ret = memblock_add_node(start, size, nid, memblock_flags); if (ret) goto error_mem_hotplug_end; } -- 2.31.1 ___ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec