It is invalid for KHO metadata or preserved memory regions to be located within the KHO scratch area, as this area is overwritten when the next kernel is loaded, and used early in boot by the next kernel. This can lead to memory corruption. Adds checks to kho_preserve_* and KHO's internal metadata allocators (xa_load_or_alloc, new_chunk) to verify that the physical address of the memory does not overlap with any defined scratch region. If an overlap is detected, the operation will fail and a WARN_ON is triggered. To avoid performance overhead in production kernels, these checks are enabled only when CONFIG_KEXEC_HANDOVER_DEBUG is selected. Signed-off-by: Pasha Tatashin --- kernel/Kconfig.kexec | 9 ++++++ kernel/Makefile | 1 + kernel/kexec_handover.c | 53 ++++++++++++++++++++++---------- kernel/kexec_handover_debug.c | 25 +++++++++++++++ kernel/kexec_handover_internal.h | 16 ++++++++++ 5 files changed, 87 insertions(+), 17 deletions(-) create mode 100644 kernel/kexec_handover_debug.c create mode 100644 kernel/kexec_handover_internal.h diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 422270d64820..c94d36b5fcd9 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -109,6 +109,15 @@ config KEXEC_HANDOVER to keep data or state alive across the kexec. For this to work, both source and target kernels need to have this option enabled. +config KEXEC_HANDOVER_DEBUG + bool "Enable Kexec Handover debug checks" + depends on KEXEC_HANDOVER_DEBUGFS + help + This option enables extra sanity checks for the Kexec Handover + subsystem. Since, KHO performance is crucial in live update + scenarios and the extra code might be adding overhead it is + only optionally enabled. + config CRASH_DUMP bool "kernel crash dumps" default ARCH_DEFAULT_CRASH_DUMP diff --git a/kernel/Makefile b/kernel/Makefile index df3dd8291bb6..9fe722305c9b 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -83,6 +83,7 @@ obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o +obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o obj-$(CONFIG_COMPAT) += compat.o obj-$(CONFIG_CGROUPS) += cgroup/ diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c index 76f0940fb485..7b460806ef4f 100644 --- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -8,6 +8,7 @@ #define pr_fmt(fmt) "KHO: " fmt +#include #include #include #include @@ -22,6 +23,7 @@ #include +#include "kexec_handover_internal.h" /* * KHO is tightly coupled with mm init and needs access to some of mm * internal APIs. @@ -133,26 +135,26 @@ static struct kho_out kho_out = { static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz) { - void *elm, *res; + void *res = xa_load(xa, index); - elm = xa_load(xa, index); - if (elm) - return elm; + if (res) + return res; + + void *elm __free(kfree) = kzalloc(sz, GFP_KERNEL); - elm = kzalloc(sz, GFP_KERNEL); if (!elm) return ERR_PTR(-ENOMEM); + if (WARN_ON(kho_scratch_overlap(virt_to_phys(elm), sz))) + return ERR_PTR(-EINVAL); + res = xa_cmpxchg(xa, index, NULL, elm, GFP_KERNEL); if (xa_is_err(res)) - res = ERR_PTR(xa_err(res)); - - if (res) { - kfree(elm); + return ERR_PTR(xa_err(res)); + else if (res) return res; - } - return elm; + return no_free_ptr(elm); } static void __kho_unpreserve(struct kho_mem_track *track, unsigned long pfn, @@ -345,15 +347,19 @@ static_assert(sizeof(struct khoser_mem_chunk) == PAGE_SIZE); static struct khoser_mem_chunk *new_chunk(struct khoser_mem_chunk *cur_chunk, unsigned long order) { - struct khoser_mem_chunk *chunk; + struct khoser_mem_chunk *chunk __free(kfree) = NULL; chunk = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!chunk) - return NULL; + return ERR_PTR(-ENOMEM); + + if (WARN_ON(kho_scratch_overlap(virt_to_phys(chunk), PAGE_SIZE))) + return ERR_PTR(-EINVAL); + chunk->hdr.order = order; if (cur_chunk) KHOSER_STORE_PTR(cur_chunk->hdr.next, chunk); - return chunk; + return no_free_ptr(chunk); } static void kho_mem_ser_free(struct khoser_mem_chunk *first_chunk) @@ -374,14 +380,17 @@ static int kho_mem_serialize(struct kho_serialization *ser) struct khoser_mem_chunk *chunk = NULL; struct kho_mem_phys *physxa; unsigned long order; + int err = -ENOMEM; xa_for_each(&ser->track.orders, order, physxa) { struct kho_mem_phys_bits *bits; unsigned long phys; chunk = new_chunk(chunk, order); - if (!chunk) + if (IS_ERR(chunk)) { + err = PTR_ERR(chunk); goto err_free; + } if (!first_chunk) first_chunk = chunk; @@ -391,8 +400,10 @@ static int kho_mem_serialize(struct kho_serialization *ser) if (chunk->hdr.num_elms == ARRAY_SIZE(chunk->bitmaps)) { chunk = new_chunk(chunk, order); - if (!chunk) + if (IS_ERR(chunk)) { + err = PTR_ERR(chunk); goto err_free; + } } elm = &chunk->bitmaps[chunk->hdr.num_elms]; @@ -409,7 +420,7 @@ static int kho_mem_serialize(struct kho_serialization *ser) err_free: kho_mem_ser_free(first_chunk); - return -ENOMEM; + return err; } static void __init deserialize_bitmap(unsigned int order, @@ -752,6 +763,9 @@ int kho_preserve_folio(struct folio *folio) const unsigned int order = folio_order(folio); struct kho_mem_track *track = &kho_out.ser.track; + if (WARN_ON(kho_scratch_overlap(pfn << PAGE_SHIFT, PAGE_SIZE << order))) + return -EINVAL; + return __kho_preserve_order(track, pfn, order); } EXPORT_SYMBOL_GPL(kho_preserve_folio); @@ -775,6 +789,11 @@ int kho_preserve_pages(struct page *page, unsigned int nr_pages) unsigned long failed_pfn = 0; int err = 0; + if (WARN_ON(kho_scratch_overlap(start_pfn << PAGE_SHIFT, + nr_pages << PAGE_SHIFT))) { + return -EINVAL; + } + while (pfn < end_pfn) { const unsigned int order = min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn)); diff --git a/kernel/kexec_handover_debug.c b/kernel/kexec_handover_debug.c new file mode 100644 index 000000000000..6efb696f5426 --- /dev/null +++ b/kernel/kexec_handover_debug.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kexec_handover_debug.c - kexec handover optional debug functionality + * Copyright (C) 2025 Google LLC, Pasha Tatashin + */ + +#define pr_fmt(fmt) "KHO: " fmt + +#include "kexec_handover_internal.h" + +bool kho_scratch_overlap(phys_addr_t phys, size_t size) +{ + phys_addr_t scratch_start, scratch_end; + unsigned int i; + + for (i = 0; i < kho_scratch_cnt; i++) { + scratch_start = kho_scratch[i].addr; + scratch_end = kho_scratch[i].addr + kho_scratch[i].size; + + if (phys < scratch_end && (phys + size) > scratch_start) + return true; + } + + return false; +} diff --git a/kernel/kexec_handover_internal.h b/kernel/kexec_handover_internal.h new file mode 100644 index 000000000000..05e9720ba7b9 --- /dev/null +++ b/kernel/kexec_handover_internal.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_KEXEC_HANDOVER_INTERNAL_H +#define LINUX_KEXEC_HANDOVER_INTERNAL_H + +#include + +#ifdef CONFIG_KEXEC_HANDOVER_DEBUG +bool kho_scratch_overlap(phys_addr_t phys, size_t size); +#else +static inline bool kho_scratch_overlap(phys_addr_t phys, size_t size) +{ + return false; +} +#endif /* CONFIG_KEXEC_HANDOVER_DEBUG */ + +#endif /* LINUX_KEXEC_HANDOVER_INTERNAL_H */ -- 2.51.0.869.ge66316f041-goog KHO memory preservation metadata is preserved in 512 byte chunks which requires their allocation from slab allocator. Slabs are not safe to be used with KHO because of kfence, and because partial slabs may lead leaks to the next kernel. Change the size to be PAGE_SIZE. The kfence specifically may cause memory corruption, where it randomly provides slab objects that can be within the scratch area. The reason for that is that kfence allocates its objects prior to KHO scratch is marked as CMA region. While this change could potentially increase metadata overhead on systems with sparsely preserved memory, this is being mitigated by ongoing work to reduce sparseness during preservation via 1G guest pages. Furthermore, this change aligns with future work on a stateless KHO, which will also use page-sized bitmaps for its radix tree metadata. Signed-off-by: Pasha Tatashin --- kernel/kexec_handover.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c index 7b460806ef4f..e5b91761fbfe 100644 --- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -69,10 +69,10 @@ early_param("kho", kho_parse_enable); * Keep track of memory that is to be preserved across KHO. * * The serializing side uses two levels of xarrays to manage chunks of per-order - * 512 byte bitmaps. For instance if PAGE_SIZE = 4096, the entire 1G order of a - * 1TB system would fit inside a single 512 byte bitmap. For order 0 allocations - * each bitmap will cover 16M of address space. Thus, for 16G of memory at most - * 512K of bitmap memory will be needed for order 0. + * PAGE_SIZE byte bitmaps. For instance if PAGE_SIZE = 4096, the entire 1G order + * of a 8TB system would fit inside a single 4096 byte bitmap. For order 0 + * allocations each bitmap will cover 128M of address space. Thus, for 16G of + * memory at most 512K of bitmap memory will be needed for order 0. * * This approach is fully incremental, as the serialization progresses folios * can continue be aggregated to the tracker. The final step, immediately prior @@ -80,12 +80,14 @@ early_param("kho", kho_parse_enable); * successor kernel to parse. */ -#define PRESERVE_BITS (512 * 8) +#define PRESERVE_BITS (PAGE_SIZE * 8) struct kho_mem_phys_bits { DECLARE_BITMAP(preserve, PRESERVE_BITS); }; +static_assert(sizeof(struct kho_mem_phys_bits) == PAGE_SIZE); + struct kho_mem_phys { /* * Points to kho_mem_phys_bits, a sparse bitmap array. Each bit is sized @@ -133,19 +135,19 @@ static struct kho_out kho_out = { .finalized = false, }; -static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz) +static void *xa_load_or_alloc(struct xarray *xa, unsigned long index) { void *res = xa_load(xa, index); if (res) return res; - void *elm __free(kfree) = kzalloc(sz, GFP_KERNEL); + void *elm __free(kfree) = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!elm) return ERR_PTR(-ENOMEM); - if (WARN_ON(kho_scratch_overlap(virt_to_phys(elm), sz))) + if (WARN_ON(kho_scratch_overlap(virt_to_phys(elm), PAGE_SIZE))) return ERR_PTR(-EINVAL); res = xa_cmpxchg(xa, index, NULL, elm, GFP_KERNEL); @@ -218,8 +220,7 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn, } } - bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS, - sizeof(*bits)); + bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS); if (IS_ERR(bits)) return PTR_ERR(bits); -- 2.51.0.869.ge66316f041-goog KHO allocates metadata for its preserved memory map using the slab allocator via kzalloc(). This metadata is temporary and is used by the next kernel during early boot to find preserved memory. A problem arises when KFENCE is enabled. kzalloc() calls can be randomly intercepted by kfence_alloc(), which services the allocation from a dedicated KFENCE memory pool. This pool is allocated early in boot via memblock. When booting via KHO, the memblock allocator is restricted to a "scratch area", forcing the KFENCE pool to be allocated within it. This creates a conflict, as the scratch area is expected to be ephemeral and overwriteable by a subsequent kexec. If KHO metadata is placed in this KFENCE pool, it leads to memory corruption when the next kernel is loaded. To fix this, modify KHO to allocate its metadata directly from the buddy allocator instead of slab. Fixes: fc33e4b44b27 ("kexec: enable KHO support for memory preservation") Signed-off-by: Pasha Tatashin Reviewed-by: Pratyush Yadav --- include/linux/gfp.h | 3 +++ kernel/kexec_handover.c | 6 +++--- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0ceb4e09306c..623bee335383 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -7,6 +7,7 @@ #include #include #include +#include #include struct vm_area_struct; @@ -463,4 +464,6 @@ static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, /* This should be paired with folio_put() rather than free_contig_range(). */ #define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__)) +DEFINE_FREE(free_page, void *, free_page((unsigned long)_T)) + #endif /* __LINUX_GFP_H */ diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c index e5b91761fbfe..de4466b47455 100644 --- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -142,7 +142,7 @@ static void *xa_load_or_alloc(struct xarray *xa, unsigned long index) if (res) return res; - void *elm __free(kfree) = kzalloc(PAGE_SIZE, GFP_KERNEL); + void *elm __free(free_page) = (void *)get_zeroed_page(GFP_KERNEL); if (!elm) return ERR_PTR(-ENOMEM); @@ -348,9 +348,9 @@ static_assert(sizeof(struct khoser_mem_chunk) == PAGE_SIZE); static struct khoser_mem_chunk *new_chunk(struct khoser_mem_chunk *cur_chunk, unsigned long order) { - struct khoser_mem_chunk *chunk __free(kfree) = NULL; + struct khoser_mem_chunk *chunk __free(free_page) = NULL; - chunk = kzalloc(PAGE_SIZE, GFP_KERNEL); + chunk = (void *)get_zeroed_page(GFP_KERNEL); if (!chunk) return ERR_PTR(-ENOMEM); -- 2.51.0.869.ge66316f041-goog