kho: allocate metadata directly from the buddy allocator

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.

Link: https://lkml.kernel.org/r/20251021000852.2924827-4-pasha.tatashin@soleen.com
Fixes: fc33e4b44b27 ("kexec: enable KHO support for memory preservation")
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Pratyush Yadav <pratyush@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: David Matlack <dmatlack@google.com>
Cc: Alexander Graf <graf@amazon.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Samiullah Khawaja <skhawaja@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 0ceb4e09306c4a7098d5a61645396e3b82a1ca30..623bee335383ef0a2d868488993d939fa3edb4cf 100644 (file)
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -7,6 +7,7 @@
 #include <linux/mmzone.h>
 #include <linux/topology.h>
 #include <linux/alloc_tag.h>
+#include <linux/cleanup.h>
 #include <linux/sched.h>
 
 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 9217d2fdd2d31d5a51aff58615abdaced9d52ebf..2a8c20c238a847e338c92fe036b8f8cd23ec720a 100644 (file)
--- 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);