linuxmsm/laptops-kernel
0
0
Fork 0
mirror of https://github.com/linux-msm/laptops-kernel.git synced 2026-08-13 14:19:53 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'mm-hotfixes-stable' into mm-nonmm-stable in order to be able

Browse Source 
to merge "kho: make debugfs interface optional" into mm-nonmm-stable.
This commit is contained in:
Andrew Morton
2025-11-27 14:17:02 -08:00
parent 58b6fcd2ab 7c9580f44f
commit bc947af677
43 changed files with 531 additions and 199 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.mailmap
+3
View File
@@ -206,6 +206,7 @@ Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com>
David Brownell <david-b@pacbell.net>
David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org>
David Heidelberg <david@ixit.cz> <d.okias@gmail.com>
David Hildenbrand <david@kernel.org> <david@redhat.com>
David Rheinsberg <david@readahead.eu> <dh.herrmann@gmail.com>
David Rheinsberg <david@readahead.eu> <dh.herrmann@googlemail.com>
David Rheinsberg <david@readahead.eu> <david.rheinsberg@gmail.com>
@@ -687,6 +688,8 @@ Sachin Mokashi <sachin.mokashi@intel.com> <sachinx.mokashi@intel.com>
Sachin P Sant <ssant@in.ibm.com>
Sai Prakash Ranjan <quic_saipraka@quicinc.com> <saiprakash.ranjan@codeaurora.org>
Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi>
Sam Protsenko <semen.protsenko@linaro.org>
Sam Protsenko <semen.protsenko@linaro.org> <semen.protsenko@globallogic.com>
Sam Ravnborg <sam@mars.ravnborg.org>
Sankeerth Billakanti <quic_sbillaka@quicinc.com> <sbillaka@codeaurora.org>
Santosh Shilimkar <santosh.shilimkar@oracle.org>
MAINTAINERS
+17 -16
View File
@@ -11526,7 +11526,7 @@ F: include/linux/platform_data/huawei-gaokun-ec.h
HUGETLB SUBSYSTEM
M: Muchun Song <muchun.song@linux.dev>
M: Oscar Salvador <osalvador@suse.de>
R: David Hildenbrand <david@redhat.com>
R: David Hildenbrand <david@kernel.org>
L: linux-mm@kvack.org
S: Maintained
F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages
@@ -13734,7 +13734,7 @@ KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
M: Christian Borntraeger <borntraeger@linux.ibm.com>
M: Janosch Frank <frankja@linux.ibm.com>
M: Claudio Imbrenda <imbrenda@linux.ibm.com>
R: David Hildenbrand <david@redhat.com>
R: David Hildenbrand <david@kernel.org>
L: kvm@vger.kernel.org
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git
@@ -13800,6 +13800,7 @@ F: Documentation/admin-guide/mm/kho.rst
F: Documentation/core-api/kho/*
F: include/linux/kexec_handover.h
F: kernel/kexec_handover.c
F: lib/test_kho.c
F: tools/testing/selftests/kho/
KEYS-ENCRYPTED
@@ -16222,7 +16223,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git
F: drivers/devfreq/tegra30-devfreq.c
MEMORY HOT(UN)PLUG
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
M: Oscar Salvador <osalvador@suse.de>
L: linux-mm@kvack.org
S: Maintained
@@ -16247,7 +16248,7 @@ F: tools/mm/
MEMORY MANAGEMENT - CORE
M: Andrew Morton <akpm@linux-foundation.org>
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
R: Liam R. Howlett <Liam.Howlett@oracle.com>
R: Vlastimil Babka <vbabka@suse.cz>
@@ -16303,7 +16304,7 @@ F: mm/execmem.c
MEMORY MANAGEMENT - GUP (GET USER PAGES)
M: Andrew Morton <akpm@linux-foundation.org>
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
R: Jason Gunthorpe <jgg@nvidia.com>
R: John Hubbard <jhubbard@nvidia.com>
R: Peter Xu <peterx@redhat.com>
@@ -16319,7 +16320,7 @@ F: tools/testing/selftests/mm/gup_test.c
MEMORY MANAGEMENT - KSM (Kernel Samepage Merging)
M: Andrew Morton <akpm@linux-foundation.org>
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
R: Xu Xin <xu.xin16@zte.com.cn>
R: Chengming Zhou <chengming.zhou@linux.dev>
L: linux-mm@kvack.org
@@ -16335,7 +16336,7 @@ F: mm/mm_slot.h
MEMORY MANAGEMENT - MEMORY POLICY AND MIGRATION
M: Andrew Morton <akpm@linux-foundation.org>
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
R: Zi Yan <ziy@nvidia.com>
R: Matthew Brost <matthew.brost@intel.com>
R: Joshua Hahn <joshua.hahnjy@gmail.com>
@@ -16375,7 +16376,7 @@ F: mm/workingset.c
MEMORY MANAGEMENT - MISC
M: Andrew Morton <akpm@linux-foundation.org>
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
R: Liam R. Howlett <Liam.Howlett@oracle.com>
R: Vlastimil Babka <vbabka@suse.cz>
@@ -16463,7 +16464,7 @@ F: mm/shuffle.h
MEMORY MANAGEMENT - RECLAIM
M: Andrew Morton <akpm@linux-foundation.org>
M: Johannes Weiner <hannes@cmpxchg.org>
R: David Hildenbrand <david@redhat.com>
R: David Hildenbrand <david@kernel.org>
R: Michal Hocko <mhocko@kernel.org>
R: Qi Zheng <zhengqi.arch@bytedance.com>
R: Shakeel Butt <shakeel.butt@linux.dev>
@@ -16476,7 +16477,7 @@ F: mm/workingset.c
MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
M: Andrew Morton <akpm@linux-foundation.org>
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
R: Rik van Riel <riel@surriel.com>
R: Liam R. Howlett <Liam.Howlett@oracle.com>
@@ -16500,12 +16501,12 @@ F: mm/secretmem.c
MEMORY MANAGEMENT - SWAP
M: Andrew Morton <akpm@linux-foundation.org>
M: Chris Li <chrisl@kernel.org>
M: Kairui Song <kasong@tencent.com>
R: Kemeng Shi <shikemeng@huaweicloud.com>
R: Kairui Song <kasong@tencent.com>
R: Nhat Pham <nphamcs@gmail.com>
R: Baoquan He <bhe@redhat.com>
R: Barry Song <baohua@kernel.org>
R: Chris Li <chrisl@kernel.org>
L: linux-mm@kvack.org
S: Maintained
F: Documentation/mm/swap-table.rst
@@ -16521,7 +16522,7 @@ F: mm/swapfile.c
MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
M: Andrew Morton <akpm@linux-foundation.org>
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
R: Zi Yan <ziy@nvidia.com>
R: Baolin Wang <baolin.wang@linux.alibaba.com>
@@ -16623,7 +16624,7 @@ MEMORY MAPPING - MADVISE (MEMORY ADVICE)
M: Andrew Morton <akpm@linux-foundation.org>
M: Liam R. Howlett <Liam.Howlett@oracle.com>
M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
R: Vlastimil Babka <vbabka@suse.cz>
R: Jann Horn <jannh@google.com>
L: linux-mm@kvack.org
@@ -27090,7 +27091,7 @@ F: net/vmw_vsock/virtio_transport_common.c
VIRTIO BALLOON
M: "Michael S. Tsirkin" <mst@redhat.com>
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
L: virtualization@lists.linux.dev
S: Maintained
F: drivers/virtio/virtio_balloon.c
@@ -27245,7 +27246,7 @@ F: drivers/iommu/virtio-iommu.c
F: include/uapi/linux/virtio_iommu.h
VIRTIO MEM DRIVER
M: David Hildenbrand <david@redhat.com>
M: David Hildenbrand <david@kernel.org>
L: virtualization@lists.linux.dev
S: Maintained
W: https://virtio-mem.gitlab.io/
arch/arm64/kernel/mte.c
+2 -1
View File
@@ -476,7 +476,8 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr,
folio = page_folio(page);
if (folio_test_hugetlb(folio))
WARN_ON_ONCE(!folio_test_hugetlb_mte_tagged(folio));
WARN_ON_ONCE(!folio_test_hugetlb_mte_tagged(folio) &&
!is_huge_zero_folio(folio));
else
WARN_ON_ONCE(!page_mte_tagged(page) && !is_zero_page(page));
arch/arm64/mm/fault.c
+10
View File
@@ -969,6 +969,16 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
void tag_clear_highpage(struct page *page)
{
/*
* Check if MTE is supported and fall back to clear_highpage().
* get_huge_zero_folio() unconditionally passes __GFP_ZEROTAGS and
* post_alloc_hook() will invoke tag_clear_highpage().
*/
if (!system_supports_mte()) {
clear_highpage(page);
return;
}
/* Newly allocated page, shouldn't have been tagged yet */
WARN_ON_ONCE(!try_page_mte_tagging(page));
mte_zero_clear_page_tags(page_address(page));
arch/powerpc/Kconfig
+1
View File
@@ -137,6 +137,7 @@ config PPC
select ARCH_HAS_DMA_OPS if PPC64
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_GIGANTIC_PAGE if ARCH_SUPPORTS_HUGETLBFS
select ARCH_HAS_KCOV
select ARCH_HAS_KERNEL_FPU_SUPPORT if PPC64 && PPC_FPU
select ARCH_HAS_MEMBARRIER_CALLBACKS
arch/powerpc/platforms/Kconfig.cputype
-1
View File
@@ -423,7 +423,6 @@ config PPC_64S_HASH_MMU
config PPC_RADIX_MMU
bool "Radix MMU Support"
depends on PPC_BOOK3S_64
select ARCH_HAS_GIGANTIC_PAGE
default y
help
Enable support for the Power ISA 3.0 Radix style MMU. Currently this
fs/nilfs2/segment.c
+6 -1
View File
@@ -2768,7 +2768,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
if (sci->sc_task) {
wake_up(&sci->sc_wait_daemon);
kthread_stop(sci->sc_task);
if (kthread_stop(sci->sc_task)) {
spin_lock(&sci->sc_state_lock);
sci->sc_task = NULL;
timer_shutdown_sync(&sci->sc_timer);
spin_unlock(&sci->sc_state_lock);
}
}
spin_lock(&sci->sc_state_lock);
fs/proc/generic.c
+9 -3
View File
@@ -698,6 +698,12 @@ void pde_put(struct proc_dir_entry *pde)
}
}
static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent)
{
rb_erase(&pde->subdir_node, &parent->subdir);
RB_CLEAR_NODE(&pde->subdir_node);
}
/*
* Remove a /proc entry and free it if it's not currently in use.
*/
@@ -720,7 +726,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
WARN(1, "removing permanent /proc entry '%s'", de->name);
de = NULL;
} else {
rb_erase(&de->subdir_node, &parent->subdir);
pde_erase(de, parent);
if (S_ISDIR(de->mode))
parent->nlink--;
}
@@ -764,7 +770,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
root->parent->name, root->name);
return -EINVAL;
}
rb_erase(&root->subdir_node, &parent->subdir);
pde_erase(root, parent);
de = root;
while (1) {
@@ -776,7 +782,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
next->parent->name, next->name);
return -EINVAL;
}
rb_erase(&next->subdir_node, &de->subdir);
pde_erase(next, de);
de = next;
continue;
}
include/linux/gfp.h
+3
View File
@@ -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 */
include/linux/huge_mm.h
+23 -32
View File
@@ -376,45 +376,30 @@ bool non_uniform_split_supported(struct folio *folio, unsigned int new_order,
int folio_split(struct folio *folio, unsigned int new_order, struct page *page,
struct list_head *list);
/*
* try_folio_split - try to split a @folio at @page using non uniform split.
* try_folio_split_to_order - try to split a @folio at @page to @new_order using
* non uniform split.
* @folio: folio to be split
* @page: split to order-0 at the given page
* @list: store the after-split folios
* @page: split to @new_order at the given page
* @new_order: the target split order
*
* Try to split a @folio at @page using non uniform split to order-0, if
* non uniform split is not supported, fall back to uniform split.
* Try to split a @folio at @page using non uniform split to @new_order, if
* non uniform split is not supported, fall back to uniform split. After-split
* folios are put back to LRU list. Use min_order_for_split() to get the lower
* bound of @new_order.
*
* Return: 0: split is successful, otherwise split failed.
*/
static inline int try_folio_split(struct folio *folio, struct page *page,
struct list_head *list)
static inline int try_folio_split_to_order(struct folio *folio,
struct page *page, unsigned int new_order)
{
int ret = min_order_for_split(folio);
if (ret < 0)
return ret;
if (!non_uniform_split_supported(folio, 0, false))
return split_huge_page_to_list_to_order(&folio->page, list,
ret);
return folio_split(folio, ret, page, list);
if (!non_uniform_split_supported(folio, new_order, /* warns= */ false))
return split_huge_page_to_list_to_order(&folio->page, NULL,
new_order);
return folio_split(folio, new_order, page, NULL);
}
static inline int split_huge_page(struct page *page)
{
struct folio *folio = page_folio(page);
int ret = min_order_for_split(folio);
if (ret < 0)
return ret;
/*
* split_huge_page() locks the page before splitting and
* expects the same page that has been split to be locked when
* returned. split_folio(page_folio(page)) cannot be used here
* because it converts the page to folio and passes the head
* page to be split.
*/
return split_huge_page_to_list_to_order(page, NULL, ret);
return split_huge_page_to_list_to_order(page, NULL, 0);
}
void deferred_split_folio(struct folio *folio, bool partially_mapped);
@@ -597,14 +582,20 @@ static inline int split_huge_page(struct page *page)
return -EINVAL;
}
static inline int min_order_for_split(struct folio *folio)
{
VM_WARN_ON_ONCE_FOLIO(1, folio);
return -EINVAL;
}
static inline int split_folio_to_list(struct folio *folio, struct list_head *list)
{
VM_WARN_ON_ONCE_FOLIO(1, folio);
return -EINVAL;
}
static inline int try_folio_split(struct folio *folio, struct page *page,
struct list_head *list)
static inline int try_folio_split_to_order(struct folio *folio,
struct page *page, unsigned int new_order)
{
VM_WARN_ON_ONCE_FOLIO(1, folio);
return -EINVAL;
include/linux/mm.h
+10 -3
View File
@@ -2074,7 +2074,7 @@ static inline unsigned long folio_nr_pages(const struct folio *folio)
return folio_large_nr_pages(folio);
}
#if !defined(CONFIG_ARCH_HAS_GIGANTIC_PAGE)
#if !defined(CONFIG_HAVE_GIGANTIC_FOLIOS)
/*
* We don't expect any folios that exceed buddy sizes (and consequently
* memory sections).
@@ -2087,10 +2087,17 @@ static inline unsigned long folio_nr_pages(const struct folio *folio)
* pages are guaranteed to be contiguous.
*/
#define MAX_FOLIO_ORDER PFN_SECTION_SHIFT
#else
#elif defined(CONFIG_HUGETLB_PAGE)
/*
* There is no real limit on the folio size. We limit them to the maximum we
* currently expect (e.g., hugetlb, dax).
* currently expect (see CONFIG_HAVE_GIGANTIC_FOLIOS): with hugetlb, we expect
* no folios larger than 16 GiB on 64bit and 1 GiB on 32bit.
*/
#define MAX_FOLIO_ORDER get_order(IS_ENABLED(CONFIG_64BIT) ? SZ_16G : SZ_1G)
#else
/*
* Without hugetlb, gigantic folios that are bigger than a single PUD are
* currently impossible.
*/
#define MAX_FOLIO_ORDER PUD_ORDER
#endif
kernel/Kconfig.kexec
+9
View File
@@ -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
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
kernel/Makefile
+1
View File
@@ -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/
kernel/crash_core.c
+1 -1
View File
@@ -373,7 +373,7 @@ static int __crash_shrink_memory(struct resource *old_res,
old_res->start = 0;
old_res->end = 0;
} else {
crashk_res.end = ram_res->start - 1;
old_res->end = ram_res->start - 1;
}
crash_free_reserved_phys_range(ram_res->start, ram_res->end);
kernel/gcov/gcc_4_7.c
+3 -1
View File
@@ -18,7 +18,9 @@
#include <linux/mm.h>
#include "gcov.h"
#if (__GNUC__ >= 14)
#if (__GNUC__ >= 15)
#define GCOV_COUNTERS 10
#elif (__GNUC__ >= 14)
#define GCOV_COUNTERS 9
#elif (__GNUC__ >= 10)
#define GCOV_COUNTERS 8
kernel/kexec_handover.c
+58 -37
View File
@@ -8,6 +8,7 @@
#define pr_fmt(fmt) "KHO: " fmt
#include <linux/cleanup.h>
#include <linux/cma.h>
#include <linux/count_zeros.h>
#include <linux/debugfs.h>
@@ -22,6 +23,7 @@
#include <asm/early_ioremap.h>
#include "kexec_handover_internal.h"
/*
* KHO is tightly coupled with mm init and needs access to some of mm
* internal APIs.
@@ -67,10 +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
@@ -78,12 +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
@@ -131,28 +135,28 @@ 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 *elm, *res;
void *res = xa_load(xa, index);
elm = xa_load(xa, index);
if (elm)
return elm;
if (res)
return res;
void *elm __free(free_page) = (void *)get_zeroed_page(GFP_KERNEL);
elm = kzalloc(sz, GFP_KERNEL);
if (!elm)
return ERR_PTR(-ENOMEM);
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);
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,
@@ -167,12 +171,12 @@ static void __kho_unpreserve(struct kho_mem_track *track, unsigned long pfn,
const unsigned long pfn_high = pfn >> order;
physxa = xa_load(&track->orders, order);
if (!physxa)
continue;
if (WARN_ON_ONCE(!physxa))
return;
bits = xa_load(&physxa->phys_bits, pfn_high / PRESERVE_BITS);
if (!bits)
continue;
if (WARN_ON_ONCE(!bits))
return;
clear_bit(pfn_high % PRESERVE_BITS, bits->preserve);
@@ -216,8 +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);
@@ -345,15 +348,19 @@ 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(free_page) = NULL;
chunk = kzalloc(PAGE_SIZE, GFP_KERNEL);
chunk = (void *)get_zeroed_page(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 +381,17 @@ 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 +401,10 @@ 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 +421,7 @@ 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,
@@ -465,8 +477,8 @@ static void __init kho_mem_deserialize(const void *fdt)
* area for early allocations that happen before page allocator is
* initialized.
*/
static struct kho_scratch *kho_scratch;
static unsigned int kho_scratch_cnt;
struct kho_scratch *kho_scratch;
unsigned int kho_scratch_cnt;
/*
* The scratch areas are scaled by default as percent of memory allocated from
@@ -752,6 +764,9 @@ 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 +790,11 @@ 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));
@@ -862,16 +882,17 @@ err_free:
return NULL;
}
static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk)
static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk,
unsigned short order)
{
struct kho_mem_track *track = &kho_out.ser.track;
unsigned long pfn = PHYS_PFN(virt_to_phys(chunk));
__kho_unpreserve(track, pfn, pfn + 1);
for (int i = 0; chunk->phys[i]; i++) {
for (int i = 0; i < ARRAY_SIZE(chunk->phys) && chunk->phys[i]; i++) {
pfn = PHYS_PFN(chunk->phys[i]);
__kho_unpreserve(track, pfn, pfn + 1);
__kho_unpreserve(track, pfn, pfn + (1 << order));
}
}
@@ -882,7 +903,7 @@ static void kho_vmalloc_free_chunks(struct kho_vmalloc *kho_vmalloc)
while (chunk) {
struct kho_vmalloc_chunk *tmp = chunk;
kho_vmalloc_unpreserve_chunk(chunk);
kho_vmalloc_unpreserve_chunk(chunk, kho_vmalloc->order);
chunk = KHOSER_LOAD_PTR(chunk->hdr.next);
free_page((unsigned long)tmp);
@@ -992,7 +1013,7 @@ void *kho_restore_vmalloc(const struct kho_vmalloc *preservation)
while (chunk) {
struct page *page;
for (int i = 0; chunk->phys[i]; i++) {
for (int i = 0; i < ARRAY_SIZE(chunk->phys) && chunk->phys[i]; i++) {
phys_addr_t phys = chunk->phys[i];
if (idx + contig_pages > total_pages)
kernel/kexec_handover_debug.c
+25
View File
@@ -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 <pasha.tatashin@soleen.com>
*/
#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;
}
kernel/kexec_handover_internal.h
+20
View File
@@ -0,0 +1,20 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef LINUX_KEXEC_HANDOVER_INTERNAL_H
#define LINUX_KEXEC_HANDOVER_INTERNAL_H
#include <linux/kexec_handover.h>
#include <linux/types.h>
extern struct kho_scratch *kho_scratch;
extern unsigned int kho_scratch_cnt;
#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 */
lib/maple_tree.c
+16 -14
View File
@@ -64,6 +64,8 @@
#define CREATE_TRACE_POINTS
#include <trace/events/maple_tree.h>
#define TP_FCT tracepoint_string(__func__)
/*
* Kernel pointer hashing renders much of the maple tree dump useless as tagged
* pointers get hashed to arbitrary values.
@@ -2756,7 +2758,7 @@ static inline void mas_rebalance(struct ma_state *mas,
MA_STATE(l_mas, mas->tree, mas->index, mas->last);
MA_STATE(r_mas, mas->tree, mas->index, mas->last);
trace_ma_op(__func__, mas);
trace_ma_op(TP_FCT, mas);
/*
* Rebalancing occurs if a node is insufficient. Data is rebalanced
@@ -2997,7 +2999,7 @@ static void mas_split(struct ma_state *mas, struct maple_big_node *b_node)
MA_STATE(prev_l_mas, mas->tree, mas->index, mas->last);
MA_STATE(prev_r_mas, mas->tree, mas->index, mas->last);
trace_ma_op(__func__, mas);
trace_ma_op(TP_FCT, mas);
mast.l = &l_mas;
mast.r = &r_mas;
@@ -3172,7 +3174,7 @@ static bool mas_is_span_wr(struct ma_wr_state *wr_mas)
return false;
}
trace_ma_write(__func__, wr_mas->mas, wr_mas->r_max, entry);
trace_ma_write(TP_FCT, wr_mas->mas, wr_mas->r_max, entry);
return true;
}
@@ -3416,7 +3418,7 @@ static noinline void mas_wr_spanning_store(struct ma_wr_state *wr_mas)
* of data may happen.
*/
mas = wr_mas->mas;
trace_ma_op(__func__, mas);
trace_ma_op(TP_FCT, mas);
if (unlikely(!mas->index && mas->last == ULONG_MAX))
return mas_new_root(mas, wr_mas->entry);
@@ -3552,7 +3554,7 @@ done:
} else {
memcpy(wr_mas->node, newnode, sizeof(struct maple_node));
}
trace_ma_write(__func__, mas, 0, wr_mas->entry);
trace_ma_write(TP_FCT, mas, 0, wr_mas->entry);
mas_update_gap(mas);
mas->end = new_end;
return;
@@ -3596,7 +3598,7 @@ static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas)
mas->offset++; /* Keep mas accurate. */
}
trace_ma_write(__func__, mas, 0, wr_mas->entry);
trace_ma_write(TP_FCT, mas, 0, wr_mas->entry);
/*
* Only update gap when the new entry is empty or there is an empty
* entry in the original two ranges.
@@ -3717,7 +3719,7 @@ static inline void mas_wr_append(struct ma_wr_state *wr_mas,
mas_update_gap(mas);
mas->end = new_end;
trace_ma_write(__func__, mas, new_end, wr_mas->entry);
trace_ma_write(TP_FCT, mas, new_end, wr_mas->entry);
return;
}
@@ -3731,7 +3733,7 @@ static void mas_wr_bnode(struct ma_wr_state *wr_mas)
{
struct maple_big_node b_node;
trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry);
trace_ma_write(TP_FCT, wr_mas->mas, 0, wr_mas->entry);
memset(&b_node, 0, sizeof(struct maple_big_node));
mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end);
mas_commit_b_node(wr_mas, &b_node);
@@ -5062,7 +5064,7 @@ void *mas_store(struct ma_state *mas, void *entry)
{
MA_WR_STATE(wr_mas, mas, entry);
trace_ma_write(__func__, mas, 0, entry);
trace_ma_write(TP_FCT, mas, 0, entry);
#ifdef CONFIG_DEBUG_MAPLE_TREE
if (MAS_WARN_ON(mas, mas->index > mas->last))
pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last,
@@ -5163,7 +5165,7 @@ void mas_store_prealloc(struct ma_state *mas, void *entry)
}
store:
trace_ma_write(__func__, mas, 0, entry);
trace_ma_write(TP_FCT, mas, 0, entry);
mas_wr_store_entry(&wr_mas);
MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas));
mas_destroy(mas);
@@ -5882,7 +5884,7 @@ void *mtree_load(struct maple_tree *mt, unsigned long index)
MA_STATE(mas, mt, index, index);
void *entry;
trace_ma_read(__func__, &mas);
trace_ma_read(TP_FCT, &mas);
rcu_read_lock();
retry:
entry = mas_start(&mas);
@@ -5925,7 +5927,7 @@ int mtree_store_range(struct maple_tree *mt, unsigned long index,
MA_STATE(mas, mt, index, last);
int ret = 0;
trace_ma_write(__func__, &mas, 0, entry);
trace_ma_write(TP_FCT, &mas, 0, entry);
if (WARN_ON_ONCE(xa_is_advanced(entry)))
return -EINVAL;
@@ -6148,7 +6150,7 @@ void *mtree_erase(struct maple_tree *mt, unsigned long index)
void *entry = NULL;
MA_STATE(mas, mt, index, index);
trace_ma_op(__func__, &mas);
trace_ma_op(TP_FCT, &mas);
mtree_lock(mt);
entry = mas_erase(&mas);
@@ -6485,7 +6487,7 @@ void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max)
unsigned long copy = *index;
#endif
trace_ma_read(__func__, &mas);
trace_ma_read(TP_FCT, &mas);
if ((*index) > max)
return NULL;
lib/test_kho.c
+3
View File
@@ -301,6 +301,9 @@ static int __init kho_test_init(void)
phys_addr_t fdt_phys;
int err;
if (!kho_is_enabled())
return 0;
err = kho_retrieve_subtree(KHO_TEST_FDT, &fdt_phys);
if (!err)
return kho_test_restore(fdt_phys);

Some files were not shown because too many files have changed in this diff Show More