| xj | b04a402 | 2021-11-25 15:01:52 +0800 | [diff] [blame] | 1 | config PAGE_EXTENSION |
| 2 | bool "Extend memmap on extra space for more information on page" |
| 3 | ---help--- |
| 4 | Extend memmap on extra space for more information on page. This |
| 5 | could be used for debugging features that need to insert extra |
| 6 | field for every page. This extension enables us to save memory |
| 7 | by not allocating this extra memory according to boottime |
| 8 | configuration. |
| 9 | |
| 10 | config DEBUG_PAGEALLOC |
| 11 | bool "Debug page memory allocations" |
| 12 | depends on DEBUG_KERNEL |
| 13 | depends on !HIBERNATION || ARCH_SUPPORTS_DEBUG_PAGEALLOC && !PPC && !SPARC |
| 14 | select PAGE_EXTENSION |
| 15 | select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC |
| 16 | ---help--- |
| 17 | Unmap pages from the kernel linear mapping after free_pages(). |
| 18 | Depending on runtime enablement, this results in a small or large |
| 19 | slowdown, but helps to find certain types of memory corruption. |
| 20 | |
| 21 | For architectures which don't enable ARCH_SUPPORTS_DEBUG_PAGEALLOC, |
| 22 | fill the pages with poison patterns after free_pages() and verify |
| 23 | the patterns before alloc_pages(). Additionally, |
| 24 | this option cannot be enabled in combination with hibernation as |
| 25 | that would result in incorrect warnings of memory corruption after |
| 26 | a resume because free pages are not saved to the suspend image. |
| 27 | |
| 28 | By default this option will have a small overhead, e.g. by not |
| 29 | allowing the kernel mapping to be backed by large pages on some |
| 30 | architectures. Even bigger overhead comes when the debugging is |
| 31 | enabled by DEBUG_PAGEALLOC_ENABLE_DEFAULT or the debug_pagealloc |
| 32 | command line parameter. |
| 33 | |
| 34 | config DEBUG_PAGEALLOC_ENABLE_DEFAULT |
| 35 | bool "Enable debug page memory allocations by default?" |
| 36 | default n |
| 37 | depends on DEBUG_PAGEALLOC |
| 38 | ---help--- |
| 39 | Enable debug page memory allocations by default? This value |
| 40 | can be overridden by debug_pagealloc=off|on. |
| 41 | |
| 42 | config PAGE_POISONING |
| 43 | bool "Poison pages after freeing" |
| 44 | select PAGE_POISONING_NO_SANITY if HIBERNATION |
| 45 | ---help--- |
| 46 | Fill the pages with poison patterns after free_pages() and verify |
| 47 | the patterns before alloc_pages. The filling of the memory helps |
| 48 | reduce the risk of information leaks from freed data. This does |
| 49 | have a potential performance impact if enabled with the |
| 50 | "page_poison=1" kernel boot option. |
| 51 | |
| 52 | Note that "poison" here is not the same thing as the "HWPoison" |
| 53 | for CONFIG_MEMORY_FAILURE. This is software poisoning only. |
| 54 | |
| 55 | If unsure, say N |
| 56 | |
| 57 | config PAGE_POISONING_NO_SANITY |
| 58 | depends on PAGE_POISONING |
| 59 | bool "Only poison, don't sanity check" |
| 60 | ---help--- |
| 61 | Skip the sanity checking on alloc, only fill the pages with |
| 62 | poison on free. This reduces some of the overhead of the |
| 63 | poisoning feature. |
| 64 | |
| 65 | If you are only interested in sanitization, say Y. Otherwise |
| 66 | say N. |
| 67 | |
| 68 | config PAGE_POISONING_ZERO |
| 69 | bool "Use zero for poisoning instead of debugging value" |
| 70 | depends on PAGE_POISONING |
| 71 | ---help--- |
| 72 | Instead of using the existing poison value, fill the pages with |
| 73 | zeros. This makes it harder to detect when errors are occurring |
| 74 | due to sanitization but the zeroing at free means that it is |
| 75 | no longer necessary to write zeros when GFP_ZERO is used on |
| 76 | allocation. |
| 77 | |
| 78 | If unsure, say N |
| 79 | |
| 80 | config DEBUG_PAGE_REF |
| 81 | bool "Enable tracepoint to track down page reference manipulation" |
| 82 | depends on DEBUG_KERNEL |
| 83 | depends on TRACEPOINTS |
| 84 | ---help--- |
| 85 | This is a feature to add tracepoint for tracking down page reference |
| 86 | manipulation. This tracking is useful to diagnose functional failure |
| 87 | due to migration failures caused by page reference mismatches. Be |
| 88 | careful when enabling this feature because it adds about 30 KB to the |
| 89 | kernel code. However the runtime performance overhead is virtually |
| 90 | nil until the tracepoints are actually enabled. |
| 91 | |
| 92 | config DEBUG_RODATA_TEST |
| 93 | bool "Testcase for the marking rodata read-only" |
| 94 | depends on STRICT_KERNEL_RWX |
| 95 | ---help--- |
| 96 | This option enables a testcase for the setting rodata read-only. |