diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2025-08-03 16:23:09 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2025-08-03 16:23:09 -0700 |
| commit | e991acf1bce7a428794514cbbe216973c9c0a3c8 (patch) | |
| tree | 0f2bdee8143718218252d8f5fd5373057e2ab8d9 /kernel/kexec_file.c | |
| parent | 3c4a063b1f8ab71352df1421d9668521acb63cd9 (diff) | |
| parent | 085dece6cc88b5c6fc6f2eca0403bfd2c5fbc7cb (diff) | |
Merge tag 'mm-nonmm-stable-2025-08-03-12-47' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull non-MM updates from Andrew Morton:
"Significant patch series in this pull request:
- "squashfs: Remove page->mapping references" (Matthew Wilcox) gets
us closer to being able to remove page->mapping
- "relayfs: misc changes" (Jason Xing) does some maintenance and
minor feature addition work in relayfs
- "kdump: crashkernel reservation from CMA" (Jiri Bohac) switches
us from static preallocation of the kdump crashkernel's working
memory over to dynamic allocation. So the difficulty of a-priori
estimation of the second kernel's needs is removed and the first
kernel obtains extra memory
- "generalize panic_print's dump function to be used by other
kernel parts" (Feng Tang) implements some consolidation and
rationalization of the various ways in which a failing kernel
splats information at the operator
* tag 'mm-nonmm-stable-2025-08-03-12-47' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (80 commits)
tools/getdelays: add backward compatibility for taskstats version
kho: add test for kexec handover
delaytop: enhance error logging and add PSI feature description
samples: Kconfig: fix spelling mistake "instancess" -> "instances"
fat: fix too many log in fat_chain_add()
scripts/spelling.txt: add notifer||notifier to spelling.txt
xen/xenbus: fix typo "notifer"
net: mvneta: fix typo "notifer"
drm/xe: fix typo "notifer"
cxl: mce: fix typo "notifer"
KVM: x86: fix typo "notifer"
MAINTAINERS: add maintainers for delaytop
ucount: use atomic_long_try_cmpxchg() in atomic_long_inc_below()
ucount: fix atomic_long_inc_below() argument type
kexec: enable CMA based contiguous allocation
stackdepot: make max number of pools boot-time configurable
lib/xxhash: remove unused functions
init/Kconfig: restore CONFIG_BROKEN help text
lib/raid6: update recov_rvv.c zero page usage
docs: update docs after introducing delaytop
...
Diffstat (limited to 'kernel/kexec_file.c')
| -rw-r--r-- | kernel/kexec_file.c | 51 |
1 files changed, 50 insertions, 1 deletions
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index b835033c65eb..91d46502a817 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -26,6 +26,7 @@ #include <linux/kernel_read_file.h> #include <linux/syscalls.h> #include <linux/vmalloc.h> +#include <linux/dma-map-ops.h> #include "kexec_internal.h" #ifdef CONFIG_KEXEC_SIG @@ -253,6 +254,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, ret = 0; } + image->no_cma = !!(flags & KEXEC_FILE_NO_CMA); + if (cmdline_len) { image->cmdline_buf = memdup_user(cmdline_ptr, cmdline_len); if (IS_ERR(image->cmdline_buf)) { @@ -434,7 +437,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, i, ksegment->buf, ksegment->bufsz, ksegment->mem, ksegment->memsz); - ret = kimage_load_segment(image, &image->segment[i]); + ret = kimage_load_segment(image, i); if (ret) goto out; } @@ -663,6 +666,43 @@ static int kexec_walk_resources(struct kexec_buf *kbuf, return walk_system_ram_res(0, ULONG_MAX, kbuf, func); } +static int kexec_alloc_contig(struct kexec_buf *kbuf) +{ + size_t nr_pages = kbuf->memsz >> PAGE_SHIFT; + unsigned long mem; + struct page *p; + + /* User space disabled CMA allocations, bail out. */ + if (kbuf->image->no_cma) + return -EPERM; + + /* Skip CMA logic for crash kernel */ + if (kbuf->image->type == KEXEC_TYPE_CRASH) + return -EPERM; + + p = dma_alloc_from_contiguous(NULL, nr_pages, get_order(kbuf->buf_align), true); + if (!p) + return -ENOMEM; + + pr_debug("allocated %zu DMA pages at 0x%lx", nr_pages, page_to_boot_pfn(p)); + + mem = page_to_boot_pfn(p) << PAGE_SHIFT; + + if (kimage_is_destination_range(kbuf->image, mem, mem + kbuf->memsz)) { + /* Our region is already in use by a statically defined one. Bail out. */ + pr_debug("CMA overlaps existing mem: 0x%lx+0x%lx\n", mem, kbuf->memsz); + dma_release_from_contiguous(NULL, p, nr_pages); + return -EBUSY; + } + + kbuf->mem = page_to_boot_pfn(p) << PAGE_SHIFT; + kbuf->cma = p; + + arch_kexec_post_alloc_pages(page_address(p), (int)nr_pages, 0); + + return 0; +} + /** * kexec_locate_mem_hole - find free memory for the purgatory or the next kernel * @kbuf: Parameters for the memory search. @@ -687,6 +727,13 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf) if (ret <= 0) return ret; + /* + * Try to find a free physically contiguous block of memory first. With that, we + * can avoid any copying at kexec time. + */ + if (!kexec_alloc_contig(kbuf)) + return 0; + if (!IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) ret = kexec_walk_resources(kbuf, locate_mem_hole_callback); else @@ -732,6 +779,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf) /* Ensure minimum alignment needed for segments. */ kbuf->memsz = ALIGN(kbuf->memsz, PAGE_SIZE); kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE); + kbuf->cma = NULL; /* Walk the RAM ranges and allocate a suitable range for the buffer */ ret = arch_kexec_locate_mem_hole(kbuf); @@ -744,6 +792,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf) ksegment->bufsz = kbuf->bufsz; ksegment->mem = kbuf->mem; ksegment->memsz = kbuf->memsz; + kbuf->image->segment_cma[kbuf->image->nr_segments] = kbuf->cma; kbuf->image->nr_segments++; return 0; } |