| From 79e482e9c3ae86e849c701c846592e72baddda5a Mon Sep 17 00:00:00 2001 |
| From: Mike Rapoport <rppt@linux.ibm.com> |
| Date: Fri, 23 Jul 2021 15:50:26 -0700 |
| Subject: memblock: make for_each_mem_range() traverse MEMBLOCK_HOTPLUG regions |
| |
| From: Mike Rapoport <rppt@linux.ibm.com> |
| |
| commit 79e482e9c3ae86e849c701c846592e72baddda5a upstream. |
| |
| Commit b10d6bca8720 ("arch, drivers: replace for_each_membock() with |
| for_each_mem_range()") didn't take into account that when there is |
| movable_node parameter in the kernel command line, for_each_mem_range() |
| would skip ranges marked with MEMBLOCK_HOTPLUG. |
| |
| The page table setup code in POWER uses for_each_mem_range() to create |
| the linear mapping of the physical memory and since the regions marked |
| as MEMORY_HOTPLUG are skipped, they never make it to the linear map. |
| |
| A later access to the memory in those ranges will fail: |
| |
| BUG: Unable to handle kernel data access on write at 0xc000000400000000 |
| Faulting instruction address: 0xc00000000008a3c0 |
| Oops: Kernel access of bad area, sig: 11 [#1] |
| LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries |
| Modules linked in: |
| CPU: 0 PID: 53 Comm: kworker/u2:0 Not tainted 5.13.0 #7 |
| NIP: c00000000008a3c0 LR: c0000000003c1ed8 CTR: 0000000000000040 |
| REGS: c000000008a57770 TRAP: 0300 Not tainted (5.13.0) |
| MSR: 8000000002009033 <SF,VEC,EE,ME,IR,DR,RI,LE> CR: 84222202 XER: 20040000 |
| CFAR: c0000000003c1ed4 DAR: c000000400000000 DSISR: 42000000 IRQMASK: 0 |
| GPR00: c0000000003c1ed8 c000000008a57a10 c0000000019da700 c000000400000000 |
| GPR04: 0000000000000280 0000000000000180 0000000000000400 0000000000000200 |
| GPR08: 0000000000000100 0000000000000080 0000000000000040 0000000000000300 |
| GPR12: 0000000000000380 c000000001bc0000 c0000000001660c8 c000000006337e00 |
| GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 |
| GPR20: 0000000040000000 0000000020000000 c000000001a81990 c000000008c30000 |
| GPR24: c000000008c20000 c000000001a81998 000fffffffff0000 c000000001a819a0 |
| GPR28: c000000001a81908 c00c000001000000 c000000008c40000 c000000008a64680 |
| NIP clear_user_page+0x50/0x80 |
| LR __handle_mm_fault+0xc88/0x1910 |
| Call Trace: |
| __handle_mm_fault+0xc44/0x1910 (unreliable) |
| handle_mm_fault+0x130/0x2a0 |
| __get_user_pages+0x248/0x610 |
| __get_user_pages_remote+0x12c/0x3e0 |
| get_arg_page+0x54/0xf0 |
| copy_string_kernel+0x11c/0x210 |
| kernel_execve+0x16c/0x220 |
| call_usermodehelper_exec_async+0x1b0/0x2f0 |
| ret_from_kernel_thread+0x5c/0x70 |
| Instruction dump: |
| 79280fa4 79271764 79261f24 794ae8e2 7ca94214 7d683a14 7c893a14 7d893050 |
| 7d4903a6 60000000 60000000 60000000 <7c001fec> 7c091fec 7c081fec 7c051fec |
| ---[ end trace 490b8c67e6075e09 ]--- |
| |
| Making for_each_mem_range() include MEMBLOCK_HOTPLUG regions in the |
| traversal fixes this issue. |
| |
| Link: https://bugzilla.redhat.com/show_bug.cgi?id=1976100 |
| Link: https://lkml.kernel.org/r/20210712071132.20902-1-rppt@kernel.org |
| Fixes: b10d6bca8720 ("arch, drivers: replace for_each_membock() with for_each_mem_range()") |
| Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> |
| Tested-by: Greg Kurz <groug@kaod.org> |
| Reviewed-by: David Hildenbrand <david@redhat.com> |
| Cc: <stable@vger.kernel.org> [5.10+] |
| Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
| Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
| --- |
| include/linux/memblock.h | 4 ++-- |
| mm/memblock.c | 3 ++- |
| 2 files changed, 4 insertions(+), 3 deletions(-) |
| |
| --- a/include/linux/memblock.h |
| +++ b/include/linux/memblock.h |
| @@ -207,7 +207,7 @@ static inline void __next_physmem_range( |
| */ |
| #define for_each_mem_range(i, p_start, p_end) \ |
| __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \ |
| - MEMBLOCK_NONE, p_start, p_end, NULL) |
| + MEMBLOCK_HOTPLUG, p_start, p_end, NULL) |
| |
| /** |
| * for_each_mem_range_rev - reverse iterate through memblock areas from |
| @@ -218,7 +218,7 @@ static inline void __next_physmem_range( |
| */ |
| #define for_each_mem_range_rev(i, p_start, p_end) \ |
| __for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \ |
| - MEMBLOCK_NONE, p_start, p_end, NULL) |
| + MEMBLOCK_HOTPLUG, p_start, p_end, NULL) |
| |
| /** |
| * for_each_reserved_mem_range - iterate over all reserved memblock areas |
| --- a/mm/memblock.c |
| +++ b/mm/memblock.c |
| @@ -940,7 +940,8 @@ static bool should_skip_region(struct me |
| return true; |
| |
| /* skip hotpluggable memory regions if needed */ |
| - if (movable_node_is_enabled() && memblock_is_hotpluggable(m)) |
| + if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && |
| + !(flags & MEMBLOCK_HOTPLUG)) |
| return true; |
| |
| /* if we want mirror memory skip non-mirror memory regions */ |