From: Pratyush Yadav <pratyush@kernel.org>
To: "Alexander Graf" <graf@amazon.com>,
"Mike Rapoport" <rppt@kernel.org>,
"Changyuan Lyu" <changyuanl@google.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Baoquan He" <bhe@redhat.com>,
"Pratyush Yadav" <pratyush@kernel.org>,
"Pasha Tatashin" <pasha.tatashin@soleen.com>,
"Jason Gunthorpe" <jgg@nvidia.com>,
"Thomas Weißschuh" <thomas.weissschuh@linutronix.de>,
"Chris Li" <chrisl@kernel.org>, "Jason Miu" <jasonmiu@google.com>,
"David Matlack" <dmatlack@google.com>,
"David Rientjes" <rientjes@google.com>
Cc: linux-kernel@vger.kernel.org, kexec@lists.infradead.org,
linux-mm@kvack.org
Subject: [RFC PATCH 3/4] kho: add support for preserving vmalloc allocations
Date: Tue, 9 Sep 2025 16:44:23 +0200 [thread overview]
Message-ID: <20250909144426.33274-4-pratyush@kernel.org> (raw)
In-Reply-To: <20250909144426.33274-1-pratyush@kernel.org>
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
A vmalloc allocation is preserved using binary structure similar to
global KHO memory tracker. It's a linked list of pages where each page
is an array of physical address of pages in vmalloc area.
kho_preserve_vmalloc() hands out the physical address of the head page
to the caller. This address is used as the argument to
kho_vmalloc_restore() to restore the mapping in the vmalloc address
space and populate it with the preserved pages.
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
[pratyush@kernel.org: use KHO array instead of linked list of pages to
track physical addresses]
Signed-off-by: Pratyush Yadav <pratyush@kernel.org>
---
include/linux/kexec_handover.h | 21 +++++
kernel/kexec_handover.c | 143 +++++++++++++++++++++++++++++++++
2 files changed, 164 insertions(+)
diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h
index 348844cffb136..633f94cec1a35 100644
--- a/include/linux/kexec_handover.h
+++ b/include/linux/kexec_handover.h
@@ -4,6 +4,7 @@
#include <linux/types.h>
#include <linux/errno.h>
+#include <linux/kho_array.h>
struct kho_scratch {
phys_addr_t addr;
@@ -37,13 +38,23 @@ struct notifier_block;
})
struct kho_serialization;
+struct kho_vmalloc;
#ifdef CONFIG_KEXEC_HANDOVER
+struct kho_vmalloc {
+ struct kho_array ka;
+ unsigned int total_pages;
+ unsigned int flags;
+ unsigned short order;
+};
+
bool kho_is_enabled(void);
int kho_preserve_folio(struct folio *folio);
+int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation);
int kho_preserve_phys(phys_addr_t phys, size_t size);
struct folio *kho_restore_folio(phys_addr_t phys);
+void *kho_restore_vmalloc(struct kho_vmalloc *preservation);
int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt);
int kho_retrieve_subtree(const char *name, phys_addr_t *phys);
@@ -70,11 +81,21 @@ static inline int kho_preserve_phys(phys_addr_t phys, size_t size)
return -EOPNOTSUPP;
}
+static inline int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation)
+{
+ return -EOPNOTSUPP;
+}
+
static inline struct folio *kho_restore_folio(phys_addr_t phys)
{
return NULL;
}
+static inline void *kho_restore_vmalloc(struct kho_vmalloc *preservation)
+{
+ return NULL;
+}
+
static inline int kho_add_subtree(struct kho_serialization *ser,
const char *name, void *fdt)
{
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 26f9f5295f07d..5f89134ceeee0 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -19,6 +19,7 @@
#include <linux/notifier.h>
#include <linux/page-isolation.h>
#include <linux/kho_array.h>
+#include <linux/vmalloc.h>
#include <asm/early_ioremap.h>
@@ -723,6 +724,148 @@ int kho_preserve_phys(phys_addr_t phys, size_t size)
}
EXPORT_SYMBOL_GPL(kho_preserve_phys);
+#define KHO_VMALLOC_FLAGS_MASK (VM_ALLOC | VM_ALLOW_HUGE_VMAP)
+
+/**
+ * kho_preserve_vmalloc - preserve memory allocated with vmalloc() across kexec
+ * @ptr: pointer to the area in vmalloc address space
+ * @preservation: pointer to metadata for preserved data.
+ *
+ * Instructs KHO to preserve the area in vmalloc address space at @ptr. The
+ * physical pages mapped at @ptr will be preserved and on successful return
+ * @preservation will hold the structure that describes the metadata for the
+ * preserved pages. @preservation itself is not KHO-preserved. The caller must
+ * do that.
+ *
+ * NOTE: The memory allocated with vmalloc_node() variants cannot be reliably
+ * restored on the same node
+ *
+ * Return: 0 on success, error code on failure
+ */
+int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation)
+{
+ struct kho_mem_track *track = &kho_out.ser.track;
+ struct vm_struct *vm = find_vm_area(ptr);
+ unsigned int order, flags;
+ struct ka_iter iter;
+ int err;
+
+ if (!vm)
+ return -EINVAL;
+
+ if (vm->flags & ~KHO_VMALLOC_FLAGS_MASK)
+ return -EOPNOTSUPP;
+
+ flags = vm->flags & KHO_VMALLOC_FLAGS_MASK;
+ order = get_vm_area_page_order(vm);
+
+ preservation->total_pages = vm->nr_pages;
+ preservation->flags = flags;
+ preservation->order = order;
+
+ ka_iter_init_write(&iter, &preservation->ka);
+
+ for (int i = 0, pos = 0; i < vm->nr_pages; i += (1 << order), pos++) {
+ phys_addr_t phys = page_to_phys(vm->pages[i]);
+
+ err = __kho_preserve_order(track, PHYS_PFN(phys), order);
+ if (err)
+ goto err_free;
+
+ err = ka_iter_setpos(&iter, pos);
+ if (err)
+ goto err_free;
+
+ err = ka_iter_setentry(&iter, ka_mk_value(phys));
+ if (err)
+ goto err_free;
+ }
+
+ err = kho_array_preserve(&preservation->ka);
+ if (err)
+ goto err_free;
+
+ return 0;
+
+err_free:
+ kho_array_destroy(&preservation->ka);
+ return err;
+}
+EXPORT_SYMBOL_GPL(kho_preserve_vmalloc);
+
+/**
+ * kho_restore_vmalloc - recreates and populates an area in vmalloc address
+ * space from the preserved memory.
+ * @preservation: the preservation metadata.
+ *
+ * Recreates an area in vmalloc address space and populates it with memory that
+ * was preserved using kho_preserve_vmalloc().
+ *
+ * Return: pointer to the area in the vmalloc address space, NULL on failure.
+ */
+void *kho_restore_vmalloc(struct kho_vmalloc *preservation)
+{
+ unsigned int align, order, shift, flags;
+ unsigned int idx = 0, nr;
+ unsigned long addr, size;
+ struct vm_struct *area;
+ struct page **pages;
+ struct ka_iter iter;
+ void *entry;
+ int err;
+
+ flags = preservation->flags;
+ if (flags & ~KHO_VMALLOC_FLAGS_MASK)
+ return NULL;
+
+ err = ka_iter_init_restore(&iter, &preservation->ka);
+ if (err)
+ return NULL;
+
+ nr = preservation->total_pages;
+ pages = kvmalloc_array(nr, sizeof(*pages), GFP_KERNEL);
+ if (!pages)
+ goto err_ka_destroy;
+ order = preservation->order;
+ shift = PAGE_SHIFT + order;
+ align = 1 << shift;
+
+ ka_iter_for_each(&iter, entry) {
+ phys_addr_t phys = ka_to_value(entry);
+ struct page *page;
+
+ page = phys_to_page(phys);
+ kho_restore_page(page, 0);
+ pages[idx++] = page;
+ phys += PAGE_SIZE;
+ }
+
+ area = __get_vm_area_node(nr * PAGE_SIZE, align, shift, flags,
+ VMALLOC_START, VMALLOC_END, NUMA_NO_NODE,
+ GFP_KERNEL, __builtin_return_address(0));
+ if (!area)
+ goto err_free_pages_array;
+
+ addr = (unsigned long)area->addr;
+ size = get_vm_area_size(area);
+ err = vmap_pages_range(addr, addr + size, PAGE_KERNEL, pages, shift);
+ if (err)
+ goto err_free_vm_area;
+
+ kho_array_destroy(&preservation->ka);
+
+ return area->addr;
+
+err_free_vm_area:
+ free_vm_area(area);
+err_free_pages_array:
+ kvfree(pages);
+err_ka_destroy:
+ kho_array_destroy(&preservation->ka);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(kho_restore_vmalloc);
+
/* Handling for debug/kho/out */
static struct dentry *debugfs_root;
--
2.47.3
next prev parent reply other threads:[~2025-09-09 14:44 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-09 14:44 [RFC PATCH 0/4] kho: introduce the KHO array Pratyush Yadav
2025-09-09 14:44 ` [RFC PATCH 1/4] " Pratyush Yadav
2025-09-09 15:28 ` Jason Gunthorpe
2025-09-09 15:40 ` Pratyush Yadav
2025-09-09 15:50 ` Jason Gunthorpe
2025-09-09 14:44 ` [RFC PATCH 2/4] kho: use KHO array for preserved memory bitmap serialization Pratyush Yadav
2025-09-09 14:44 ` Pratyush Yadav [this message]
2025-09-09 14:44 ` [RFC PATCH 4/4] lib/test_kho: use kho_preserve_vmalloc instead of storing addresses in fdt Pratyush Yadav
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250909144426.33274-4-pratyush@kernel.org \
--to=pratyush@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=bhe@redhat.com \
--cc=changyuanl@google.com \
--cc=chrisl@kernel.org \
--cc=dmatlack@google.com \
--cc=graf@amazon.com \
--cc=jasonmiu@google.com \
--cc=jgg@nvidia.com \
--cc=kexec@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=pasha.tatashin@soleen.com \
--cc=rientjes@google.com \
--cc=rppt@kernel.org \
--cc=thomas.weissschuh@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox