The patch below does not apply to the 6.17-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.17.y
git checkout FETCH_HEAD
git cherry-pick -x fa759cd75bce5489eed34596daa53f721849a86f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025112149-ahoy-manliness-1554@gregkh' --subject-prefix 'PATCH 6.17.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From fa759cd75bce5489eed34596daa53f721849a86f Mon Sep 17 00:00:00 2001
From: Pasha Tatashin <pasha.tatashin(a)soleen.com>
Date: Mon, 20 Oct 2025 20:08:52 -0400
Subject: [PATCH] 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(a)soleen.com>
Reviewed-by: Pratyush Yadav <pratyush(a)kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org>
Reviewed-by: David Matlack <dmatlack(a)google.com>
Cc: Alexander Graf <graf(a)amazon.com>
Cc: Christian Brauner <brauner(a)kernel.org>
Cc: Jason Gunthorpe <jgg(a)ziepe.ca>
Cc: Jonathan Corbet <corbet(a)lwn.net>
Cc: Masahiro Yamada <masahiroy(a)kernel.org>
Cc: Miguel Ojeda <ojeda(a)kernel.org>
Cc: Randy Dunlap <rdunlap(a)infradead.org>
Cc: Samiullah Khawaja <skhawaja(a)google.com>
Cc: Tejun Heo <tj(a)kernel.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
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 <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 9217d2fdd2d3..2a8c20c238a8 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);
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 74207de2ba10c2973334906822dc94d2e859ffc5
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025112026-substance-senator-8409@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 74207de2ba10c2973334906822dc94d2e859ffc5 Mon Sep 17 00:00:00 2001
From: Kiryl Shutsemau <kas(a)kernel.org>
Date: Mon, 27 Oct 2025 11:56:35 +0000
Subject: [PATCH] mm/memory: do not populate page table entries beyond i_size
Patch series "Fix SIGBUS semantics with large folios", v3.
Accessing memory within a VMA, but beyond i_size rounded up to the next
page size, is supposed to generate SIGBUS.
Darrick reported[1] an xfstests regression in v6.18-rc1. generic/749
failed due to missing SIGBUS. This was caused by my recent changes that
try to fault in the whole folio where possible:
19773df031bc ("mm/fault: try to map the entire file folio in finish_fault()")
357b92761d94 ("mm/filemap: map entire large folio faultaround")
These changes did not consider i_size when setting up PTEs, leading to
xfstest breakage.
However, the problem has been present in the kernel for a long time -
since huge tmpfs was introduced in 2016. The kernel happily maps
PMD-sized folios as PMD without checking i_size. And huge=always tmpfs
allocates PMD-size folios on any writes.
I considered this corner case when I implemented a large tmpfs, and my
conclusion was that no one in their right mind should rely on receiving a
SIGBUS signal when accessing beyond i_size. I cannot imagine how it could
be useful for the workload.
But apparently filesystem folks care a lot about preserving strict SIGBUS
semantics.
Generic/749 was introduced last year with reference to POSIX, but no real
workloads were mentioned. It also acknowledged the tmpfs deviation from
the test case.
POSIX indeed says[3]:
References within the address range starting at pa and
continuing for len bytes to whole pages following the end of an
object shall result in delivery of a SIGBUS signal.
The patchset fixes the regression introduced by recent changes as well as
more subtle SIGBUS breakage due to split failure on truncation.
This patch (of 2):
Accesses within VMA, but beyond i_size rounded up to PAGE_SIZE are
supposed to generate SIGBUS.
Recent changes attempted to fault in full folio where possible. They did
not respect i_size, which led to populating PTEs beyond i_size and
breaking SIGBUS semantics.
Darrick reported generic/749 breakage because of this.
However, the problem existed before the recent changes. With huge=always
tmpfs, any write to a file leads to PMD-size allocation. Following the
fault-in of the folio will install PMD mapping regardless of i_size.
Fix filemap_map_pages() and finish_fault() to not install:
- PTEs beyond i_size;
- PMD mappings across i_size;
Make an exception for shmem/tmpfs that for long time intentionally
mapped with PMDs across i_size.
Link: https://lkml.kernel.org/r/20251027115636.82382-1-kirill@shutemov.name
Link: https://lkml.kernel.org/r/20251027115636.82382-2-kirill@shutemov.name
Signed-off-by: Kiryl Shutsemau <kas(a)kernel.org>
Fixes: 6795801366da ("xfs: Support large folios")
Reported-by: "Darrick J. Wong" <djwong(a)kernel.org>
Cc: Al Viro <viro(a)zeniv.linux.org.uk>
Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com>
Cc: Christian Brauner <brauner(a)kernel.org>
Cc: Dave Chinner <david(a)fromorbit.com>
Cc: David Hildenbrand <david(a)redhat.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Johannes Weiner <hannes(a)cmpxchg.org>
Cc: Liam Howlett <liam.howlett(a)oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com>
Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Mike Rapoport <rppt(a)kernel.org>
Cc: Rik van Riel <riel(a)surriel.com>
Cc: Shakeel Butt <shakeel.butt(a)linux.dev>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/mm/filemap.c b/mm/filemap.c
index 13f0259d993c..2f1e7e283a51 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3681,7 +3681,8 @@ static struct folio *next_uptodate_folio(struct xa_state *xas,
static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
struct folio *folio, unsigned long start,
unsigned long addr, unsigned int nr_pages,
- unsigned long *rss, unsigned short *mmap_miss)
+ unsigned long *rss, unsigned short *mmap_miss,
+ bool can_map_large)
{
unsigned int ref_from_caller = 1;
vm_fault_t ret = 0;
@@ -3696,7 +3697,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
* The folio must not cross VMA or page table boundary.
*/
addr0 = addr - start * PAGE_SIZE;
- if (folio_within_vma(folio, vmf->vma) &&
+ if (can_map_large && folio_within_vma(folio, vmf->vma) &&
(addr0 & PMD_MASK) == ((addr0 + folio_size(folio) - 1) & PMD_MASK)) {
vmf->pte -= start;
page -= start;
@@ -3811,13 +3812,27 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
unsigned long rss = 0;
unsigned int nr_pages = 0, folio_type;
unsigned short mmap_miss = 0, mmap_miss_saved;
+ bool can_map_large;
rcu_read_lock();
folio = next_uptodate_folio(&xas, mapping, end_pgoff);
if (!folio)
goto out;
- if (filemap_map_pmd(vmf, folio, start_pgoff)) {
+ file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
+ end_pgoff = min(end_pgoff, file_end);
+
+ /*
+ * Do not allow to map with PTEs beyond i_size and with PMD
+ * across i_size to preserve SIGBUS semantics.
+ *
+ * Make an exception for shmem/tmpfs that for long time
+ * intentionally mapped with PMDs across i_size.
+ */
+ can_map_large = shmem_mapping(mapping) ||
+ file_end >= folio_next_index(folio);
+
+ if (can_map_large && filemap_map_pmd(vmf, folio, start_pgoff)) {
ret = VM_FAULT_NOPAGE;
goto out;
}
@@ -3830,10 +3845,6 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
goto out;
}
- file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
- if (end_pgoff > file_end)
- end_pgoff = file_end;
-
folio_type = mm_counter_file(folio);
do {
unsigned long end;
@@ -3850,7 +3861,8 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
else
ret |= filemap_map_folio_range(vmf, folio,
xas.xa_index - folio->index, addr,
- nr_pages, &rss, &mmap_miss);
+ nr_pages, &rss, &mmap_miss,
+ can_map_large);
folio_unlock(folio);
} while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL);
diff --git a/mm/memory.c b/mm/memory.c
index 74b45e258323..b59ae7ce42eb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -65,6 +65,7 @@
#include <linux/gfp.h>
#include <linux/migrate.h>
#include <linux/string.h>
+#include <linux/shmem_fs.h>
#include <linux/memory-tiers.h>
#include <linux/debugfs.h>
#include <linux/userfaultfd_k.h>
@@ -5501,8 +5502,25 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
return ret;
}
+ if (!needs_fallback && vma->vm_file) {
+ struct address_space *mapping = vma->vm_file->f_mapping;
+ pgoff_t file_end;
+
+ file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
+
+ /*
+ * Do not allow to map with PTEs beyond i_size and with PMD
+ * across i_size to preserve SIGBUS semantics.
+ *
+ * Make an exception for shmem/tmpfs that for long time
+ * intentionally mapped with PMDs across i_size.
+ */
+ needs_fallback = !shmem_mapping(mapping) &&
+ file_end < folio_next_index(folio);
+ }
+
if (pmd_none(*vmf->pmd)) {
- if (folio_test_pmd_mappable(folio)) {
+ if (!needs_fallback && folio_test_pmd_mappable(folio)) {
ret = do_set_pmd(vmf, folio, page);
if (ret != VM_FAULT_FALLBACK)
return ret;
The patch below does not apply to the 6.17-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.17.y
git checkout FETCH_HEAD
git cherry-pick -x fa04f5b60fda62c98a53a60de3a1e763f11feb41
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025112037-resurface-backlight-da75@gregkh' --subject-prefix 'PATCH 6.17.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From fa04f5b60fda62c98a53a60de3a1e763f11feb41 Mon Sep 17 00:00:00 2001
From: Kiryl Shutsemau <kas(a)kernel.org>
Date: Mon, 27 Oct 2025 11:56:36 +0000
Subject: [PATCH] mm/truncate: unmap large folio on split failure
Accesses within VMA, but beyond i_size rounded up to PAGE_SIZE are
supposed to generate SIGBUS.
This behavior might not be respected on truncation.
During truncation, the kernel splits a large folio in order to reclaim
memory. As a side effect, it unmaps the folio and destroys PMD mappings
of the folio. The folio will be refaulted as PTEs and SIGBUS semantics
are preserved.
However, if the split fails, PMD mappings are preserved and the user will
not receive SIGBUS on any accesses within the PMD.
Unmap the folio on split failure. It will lead to refault as PTEs and
preserve SIGBUS semantics.
Make an exception for shmem/tmpfs that for long time intentionally mapped
with PMDs across i_size.
Link: https://lkml.kernel.org/r/20251027115636.82382-3-kirill@shutemov.name
Fixes: b9a8a4195c7d ("truncate,shmem: Handle truncates that split large folios")
Signed-off-by: Kiryl Shutsemau <kas(a)kernel.org>
Cc: Al Viro <viro(a)zeniv.linux.org.uk>
Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com>
Cc: Christian Brauner <brauner(a)kernel.org>
Cc: "Darrick J. Wong" <djwong(a)kernel.org>
Cc: Dave Chinner <david(a)fromorbit.com>
Cc: David Hildenbrand <david(a)redhat.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Johannes Weiner <hannes(a)cmpxchg.org>
Cc: Liam Howlett <liam.howlett(a)oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com>
Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Mike Rapoport <rppt(a)kernel.org>
Cc: Rik van Riel <riel(a)surriel.com>
Cc: Shakeel Butt <shakeel.butt(a)linux.dev>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/mm/truncate.c b/mm/truncate.c
index 9210cf808f5c..3c5a50ae3274 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -177,6 +177,32 @@ int truncate_inode_folio(struct address_space *mapping, struct folio *folio)
return 0;
}
+static int try_folio_split_or_unmap(struct folio *folio, struct page *split_at,
+ unsigned long min_order)
+{
+ enum ttu_flags ttu_flags =
+ TTU_SYNC |
+ TTU_SPLIT_HUGE_PMD |
+ TTU_IGNORE_MLOCK;
+ int ret;
+
+ ret = try_folio_split_to_order(folio, split_at, min_order);
+
+ /*
+ * If the split fails, unmap the folio, so it will be refaulted
+ * with PTEs to respect SIGBUS semantics.
+ *
+ * Make an exception for shmem/tmpfs that for long time
+ * intentionally mapped with PMDs across i_size.
+ */
+ if (ret && !shmem_mapping(folio->mapping)) {
+ try_to_unmap(folio, ttu_flags);
+ WARN_ON(folio_mapped(folio));
+ }
+
+ return ret;
+}
+
/*
* Handle partial folios. The folio may be entirely within the
* range if a split has raced with us. If not, we zero the part of the
@@ -226,7 +252,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
min_order = mapping_min_folio_order(folio->mapping);
split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE);
- if (!try_folio_split_to_order(folio, split_at, min_order)) {
+ if (!try_folio_split_or_unmap(folio, split_at, min_order)) {
/*
* try to split at offset + length to make sure folios within
* the range can be dropped, especially to avoid memory waste
@@ -250,13 +276,10 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
if (!folio_trylock(folio2))
goto out;
- /*
- * make sure folio2 is large and does not change its mapping.
- * Its split result does not matter here.
- */
+ /* make sure folio2 is large and does not change its mapping */
if (folio_test_large(folio2) &&
folio2->mapping == folio->mapping)
- try_folio_split_to_order(folio2, split_at2, min_order);
+ try_folio_split_or_unmap(folio2, split_at2, min_order);
folio_unlock(folio2);
out:
kstack_offset was previously maintained per-cpu, but this caused a
couple of issues. So let's instead make it per-task.
Issue 1: add_random_kstack_offset() and choose_random_kstack_offset()
expected and required to be called with interrupts and preemption
disabled so that it could manipulate per-cpu state. But arm64, loongarch
and risc-v are calling them with interrupts and preemption enabled. I
don't _think_ this causes any functional issues, but it's certainly
unexpected and could lead to manipulating the wrong cpu's state, which
could cause a minor performance degradation due to bouncing the cache
lines. By maintaining the state per-task those functions can safely be
called in preemptible context.
Issue 2: add_random_kstack_offset() is called before executing the
syscall and expands the stack using a previously chosen rnadom offset.
choose_random_kstack_offset() is called after executing the syscall and
chooses and stores a new random offset for the next syscall. With
per-cpu storage for this offset, an attacker could force cpu migration
during the execution of the syscall and prevent the offset from being
updated for the original cpu such that it is predictable for the next
syscall on that cpu. By maintaining the state per-task, this problem
goes away because the per-task random offset is updated after the
syscall regardless of which cpu it is executing on.
Fixes: 39218ff4c625 ("stack: Optionally randomize kernel stack offset each syscall")
Closes: https://lore.kernel.org/all/dd8c37bc-795f-4c7a-9086-69e584d8ab24@arm.com/
Cc: stable(a)vger.kernel.org
Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com>
---
include/linux/randomize_kstack.h | 26 +++++++++++++++-----------
include/linux/sched.h | 4 ++++
init/main.c | 1 -
kernel/fork.c | 2 ++
4 files changed, 21 insertions(+), 12 deletions(-)
diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h
index 1d982dbdd0d0..089b1432f7e6 100644
--- a/include/linux/randomize_kstack.h
+++ b/include/linux/randomize_kstack.h
@@ -9,7 +9,6 @@
DECLARE_STATIC_KEY_MAYBE(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
randomize_kstack_offset);
-DECLARE_PER_CPU(u32, kstack_offset);
/*
* Do not use this anywhere else in the kernel. This is used here because
@@ -50,15 +49,14 @@ DECLARE_PER_CPU(u32, kstack_offset);
* add_random_kstack_offset - Increase stack utilization by previously
* chosen random offset
*
- * This should be used in the syscall entry path when interrupts and
- * preempt are disabled, and after user registers have been stored to
- * the stack. For testing the resulting entropy, please see:
- * tools/testing/selftests/lkdtm/stack-entropy.sh
+ * This should be used in the syscall entry path after user registers have been
+ * stored to the stack. Preemption may be enabled. For testing the resulting
+ * entropy, please see: tools/testing/selftests/lkdtm/stack-entropy.sh
*/
#define add_random_kstack_offset() do { \
if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \
&randomize_kstack_offset)) { \
- u32 offset = raw_cpu_read(kstack_offset); \
+ u32 offset = current->kstack_offset; \
u8 *ptr = __kstack_alloca(KSTACK_OFFSET_MAX(offset)); \
/* Keep allocation even after "ptr" loses scope. */ \
asm volatile("" :: "r"(ptr) : "memory"); \
@@ -69,9 +67,9 @@ DECLARE_PER_CPU(u32, kstack_offset);
* choose_random_kstack_offset - Choose the random offset for the next
* add_random_kstack_offset()
*
- * This should only be used during syscall exit when interrupts and
- * preempt are disabled. This position in the syscall flow is done to
- * frustrate attacks from userspace attempting to learn the next offset:
+ * This should only be used during syscall exit. Preemption may be enabled. This
+ * position in the syscall flow is done to frustrate attacks from userspace
+ * attempting to learn the next offset:
* - Maximize the timing uncertainty visible from userspace: if the
* offset is chosen at syscall entry, userspace has much more control
* over the timing between choosing offsets. "How long will we be in
@@ -85,14 +83,20 @@ DECLARE_PER_CPU(u32, kstack_offset);
#define choose_random_kstack_offset(rand) do { \
if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \
&randomize_kstack_offset)) { \
- u32 offset = raw_cpu_read(kstack_offset); \
+ u32 offset = current->kstack_offset; \
offset = ror32(offset, 5) ^ (rand); \
- raw_cpu_write(kstack_offset, offset); \
+ current->kstack_offset = offset; \
} \
} while (0)
+
+static inline void random_kstack_task_init(struct task_struct *tsk)
+{
+ current->kstack_offset = 0;
+}
#else /* CONFIG_RANDOMIZE_KSTACK_OFFSET */
#define add_random_kstack_offset() do { } while (0)
#define choose_random_kstack_offset(rand) do { } while (0)
+#define random_kstack_task_init(tsk) do { } while (0)
#endif /* CONFIG_RANDOMIZE_KSTACK_OFFSET */
#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b469878de25c..dae227d217ef 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1613,6 +1613,10 @@ struct task_struct {
unsigned long prev_lowest_stack;
#endif
+#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
+ u32 kstack_offset;
+#endif
+
#ifdef CONFIG_X86_MCE
void __user *mce_vaddr;
__u64 mce_kflags;
diff --git a/init/main.c b/init/main.c
index 07a3116811c5..048a62538242 100644
--- a/init/main.c
+++ b/init/main.c
@@ -830,7 +830,6 @@ static inline void initcall_debug_enable(void)
#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
DEFINE_STATIC_KEY_MAYBE_RO(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
randomize_kstack_offset);
-DEFINE_PER_CPU(u32, kstack_offset);
static int __init early_randomize_kstack_offset(char *buf)
{
diff --git a/kernel/fork.c b/kernel/fork.c
index 3da0f08615a9..c0dced542b8a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -95,6 +95,7 @@
#include <linux/thread_info.h>
#include <linux/kstack_erase.h>
#include <linux/kasan.h>
+#include <linux/randomize_kstack.h>
#include <linux/scs.h>
#include <linux/io_uring.h>
#include <linux/bpf.h>
@@ -2191,6 +2192,7 @@ __latent_entropy struct task_struct *copy_process(
if (retval)
goto bad_fork_cleanup_io;
+ random_kstack_task_init(p);
stackleak_task_init(p);
if (pid != &init_struct_pid) {
--
2.43.0