diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-06-21 09:46:14 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-06-21 09:46:14 -0700 |
| commit | d639d9fa162aadec1ae9980c4dcf6e50bd2f8290 (patch) | |
| tree | f9bc42aecac73a391e96e08d944a8fe962821356 /kernel | |
| parent | 1e762b53a86d7ed19016c66cc1883e4b9f8b2c1b (diff) | |
| parent | e98a9c61721c14bcd29f11f4802e52e908701f7a (diff) | |
| download | lwn-d639d9fa162aadec1ae9980c4dcf6e50bd2f8290.tar.gz lwn-d639d9fa162aadec1ae9980c4dcf6e50bd2f8290.zip | |
Merge tag 'liveupdate-v7.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/liveupdate/linux
Pull liveupdate updates from Mike Rapoport:
"Kexec Handover (KHO):
- make memory preservation compatible with deferred initialization
of the memory map
Live Update Orchestrator (LUO):
- add LIVEUPDATE_SESSION_GET_NAME ioctl and parameter verification
for LIVEUPDATE_IOCTL_CREATE_SESSION ioctl
- documentation updates for liveupdate=on command line option,
systemd support and the current compatibility status
- remove the fixed limits on the number of files that can be
preserved within a single session, and the total number of
sessions managed by the LUO
Misc fixes:
- reference count incoming File-Lifecycle-Bound (FLB) data so
it cannot be freed while a subsystem is still using it
- fixes for a TOCTOU race in luo_session_retrieve(), a use-
after-free in the file finish and unpreserve paths, concurrent
session mutations during reboot and serialization on
preserve_context kexec
- make sure ioctls for incoming LUO sessions are blocked for
outgoing sessions and vice versa
- make sure KHO scratch size is always aligned by
CMA_MIN_ALIGNMENT_BYTES
- fix memblock tests build issue introduced by KHO changes"
* tag 'liveupdate-v7.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/liveupdate/linux: (36 commits)
liveupdate: Document that retrieve failure is permanent
docs: memfd_preservation: fix rendering of ABI documentation
selftests/liveupdate: Add stress-files kexec test
selftests/liveupdate: Add stress-sessions kexec test
selftests/liveupdate: Test session and file limit removal
liveupdate: Remove limit on the number of files per session
liveupdate: Remove limit on the number of sessions
liveupdate: defer session block allocation and physical address setting
kho: add support for linked-block serialization
liveupdate: Extract luo_session_deserialize_one helper
liveupdate: Extract luo_file_deserialize_one helper
liveupdate: register luo_ser as KHO subtree
liveupdate: centralize state management into struct luo_ser
liveupdate: avoid mixing cleanup guards with goto in luo_session_retrieve_fd
liveupdate: change file_set->count type to u64 for type safety
liveupdate: Remove unused ser field from struct luo_session
liveupdate: fix u-a-f in luo_file_unpreserve_files() and luo_file_finish()
liveupdate: block session mutations during reboot
liveupdate: fix TOCTOU race in luo_session_retrieve()
liveupdate: skip serialization for context-preserving kexec
...
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/kexec_core.c | 8 | ||||
| -rw-r--r-- | kernel/liveupdate/Kconfig | 2 | ||||
| -rw-r--r-- | kernel/liveupdate/Makefile | 1 | ||||
| -rw-r--r-- | kernel/liveupdate/kexec_handover.c | 84 | ||||
| -rw-r--r-- | kernel/liveupdate/kho_block.c | 416 | ||||
| -rw-r--r-- | kernel/liveupdate/luo_core.c | 103 | ||||
| -rw-r--r-- | kernel/liveupdate/luo_file.c | 210 | ||||
| -rw-r--r-- | kernel/liveupdate/luo_flb.c | 112 | ||||
| -rw-r--r-- | kernel/liveupdate/luo_internal.h | 18 | ||||
| -rw-r--r-- | kernel/liveupdate/luo_session.c | 336 |
10 files changed, 865 insertions, 425 deletions
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index a43d2da0fe3e..dc770b9a6d05 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1146,9 +1146,11 @@ int kernel_kexec(void) goto Unlock; } - error = liveupdate_reboot(); - if (error) - goto Unlock; + if (!kexec_image->preserve_context) { + error = liveupdate_reboot(); + if (error) + goto Unlock; + } #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { diff --git a/kernel/liveupdate/Kconfig b/kernel/liveupdate/Kconfig index 1a8513f16ef7..c13af38ba23a 100644 --- a/kernel/liveupdate/Kconfig +++ b/kernel/liveupdate/Kconfig @@ -1,12 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only menu "Live Update and Kexec HandOver" - depends on !DEFERRED_STRUCT_PAGE_INIT config KEXEC_HANDOVER bool "kexec handover" depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE - depends on !DEFERRED_STRUCT_PAGE_INIT select MEMBLOCK_KHO_SCRATCH select KEXEC_FILE select LIBFDT diff --git a/kernel/liveupdate/Makefile b/kernel/liveupdate/Makefile index d2f779cbe279..eec9d3ae07eb 100644 --- a/kernel/liveupdate/Makefile +++ b/kernel/liveupdate/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 luo-y := \ + kho_block.o \ luo_core.o \ luo_file.o \ luo_flb.o \ diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index 1b592d86dc48..4834a809985a 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -459,6 +459,31 @@ struct page *kho_restore_pages(phys_addr_t phys, unsigned long nr_pages) } EXPORT_SYMBOL_GPL(kho_restore_pages); +/* + * With CONFIG_DEFERRED_STRUCT_PAGE_INIT, struct pages in higher memory regions + * may not be initialized yet at the time KHO deserializes preserved memory. + * KHO uses the struct page to store metadata and a later initialization would + * overwrite it. + * Ensure all the struct pages in the preservation are + * initialized. kho_preserved_memory_reserve() marks the reservation as noinit + * to make sure they don't get re-initialized later. + */ +static struct page *__init kho_get_preserved_page(phys_addr_t phys, + unsigned int order) +{ + unsigned long pfn = PHYS_PFN(phys); + int nid; + + if (!IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT)) + return pfn_to_page(pfn); + + nid = early_pfn_to_nid(pfn); + for (unsigned long i = 0; i < (1UL << order); i++) + init_deferred_page(pfn + i, nid); + + return pfn_to_page(pfn); +} + static int __init kho_preserved_memory_reserve(phys_addr_t phys, unsigned int order) { @@ -467,7 +492,7 @@ static int __init kho_preserved_memory_reserve(phys_addr_t phys, u64 sz; sz = 1 << (order + PAGE_SHIFT); - page = phys_to_page(phys); + page = kho_get_preserved_page(phys, order); /* Reserve the memory preserved in KHO in memblock */ memblock_reserve(phys, sz); @@ -593,20 +618,30 @@ early_param("kho_scratch", kho_parse_scratch_size); static void __init scratch_size_update(void) { - phys_addr_t size; + /* + * If fixed sizes are not provided via command line, calculate them + * now. + */ + if (scratch_scale) { + phys_addr_t size; - if (!scratch_scale) - return; + size = memblock_reserved_kern_size(ARCH_LOW_ADDRESS_LIMIT, + NUMA_NO_NODE); + size = size * scratch_scale / 100; + scratch_size_lowmem = size; - size = memblock_reserved_kern_size(ARCH_LOW_ADDRESS_LIMIT, - NUMA_NO_NODE); - size = size * scratch_scale / 100; - scratch_size_lowmem = round_up(size, CMA_MIN_ALIGNMENT_BYTES); + size = memblock_reserved_kern_size(MEMBLOCK_ALLOC_ANYWHERE, + NUMA_NO_NODE); + size = size * scratch_scale / 100 - scratch_size_lowmem; + scratch_size_global = size; + } - size = memblock_reserved_kern_size(MEMBLOCK_ALLOC_ANYWHERE, - NUMA_NO_NODE); - size = size * scratch_scale / 100 - scratch_size_lowmem; - scratch_size_global = round_up(size, CMA_MIN_ALIGNMENT_BYTES); + /* + * Scratch areas are released as MIGRATE_CMA. Round them up to the right + * size. + */ + scratch_size_lowmem = round_up(scratch_size_lowmem, CMA_MIN_ALIGNMENT_BYTES); + scratch_size_global = round_up(scratch_size_global, CMA_MIN_ALIGNMENT_BYTES); } static phys_addr_t __init scratch_size_node(int nid) @@ -1584,35 +1619,10 @@ err_free_scratch: } fs_initcall(kho_init); -static void __init kho_release_scratch(void) -{ - phys_addr_t start, end; - u64 i; - - memmap_init_kho_scratch_pages(); - - /* - * Mark scratch mem as CMA before we return it. That way we - * ensure that no kernel allocations happen on it. That means - * we can reuse it as scratch memory again later. - */ - __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, - MEMBLOCK_KHO_SCRATCH, &start, &end, NULL) { - ulong start_pfn = pageblock_start_pfn(PFN_DOWN(start)); - ulong end_pfn = pageblock_align(PFN_UP(end)); - ulong pfn; - - for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) - init_pageblock_migratetype(pfn_to_page(pfn), - MIGRATE_CMA, false); - } -} - void __init kho_memory_init(void) { if (kho_in.scratch_phys) { kho_scratch = phys_to_virt(kho_in.scratch_phys); - kho_release_scratch(); if (kho_mem_retrieve(kho_get_fdt())) kho_in.fdt_phys = 0; diff --git a/kernel/liveupdate/kho_block.c b/kernel/liveupdate/kho_block.c new file mode 100644 index 000000000000..0d2a342ef422 --- /dev/null +++ b/kernel/liveupdate/kho_block.c @@ -0,0 +1,416 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2026, Google LLC. + * Pasha Tatashin <pasha.tatashin@soleen.com> + */ + +/** + * DOC: KHO Serialization Blocks + * + * KHO provides a mechanism to preserve stateful data across a kexec handover + * by serializing it into memory blocks, and provides the common + * infrastructure for managing these blocks. + * + * Each block consists of a header (struct kho_block_header_ser) followed by an + * array of serialized entries. Multiple blocks are linked together via a + * physical pointer in the header, forming a linked list that can be easily + * traversed in both the current and the next kernel. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/io.h> +#include <linux/kexec_handover.h> +#include <linux/kho/abi/block.h> +#include <linux/kho_block.h> +#include <linux/slab.h> + +/* + * Safeguard limit for the number of serialization blocks. This is used to + * prevent infinite loops and excessive memory allocation in case of memory + * corruption in the preserved state. + * + * With a 4KB page size, 10k blocks is about 40MB. For 32-byte entries + * (e.g. 4 u64s), each block holds up to 127 entries (accounting for the + * 16-byte header), allowing the block set to hold up to 1.27M entries. + */ +#define KHO_MAX_BLOCKS 10000 + +/** + * kho_block_set_init - Initialize a block set. + * @bs: The block set to initialize. + * @entry_size: The size of each entry in the blocks. + */ +void kho_block_set_init(struct kho_block_set *bs, size_t entry_size) +{ + *bs = (struct kho_block_set)KHO_BLOCK_SET_INIT(*bs, entry_size); + WARN_ON_ONCE(!bs->count_per_block); +} + +/* Serialized entries start immediately after the block header */ +static void *kho_block_entries(struct kho_block *block) +{ + return (void *)(block->ser + 1); +} + +/* Get the address of the serialized entry at the specified index */ +static void *kho_block_entry(struct kho_block_set_it *it, u64 index) +{ + return kho_block_entries(it->block) + (index * it->bs->entry_size); +} + +/* Free serialized data */ +static void kho_block_free_ser(struct kho_block_set *bs, + struct kho_block_header_ser *ser) +{ + if (bs->incoming) + kho_restore_free(ser); + else + kho_unpreserve_free(ser); +} + +static struct kho_block_header_ser *kho_block_alloc_ser(struct kho_block_set *bs) +{ + WARN_ON_ONCE(bs->incoming); + return kho_alloc_preserve(KHO_BLOCK_SIZE); +} + +static int kho_block_add(struct kho_block_set *bs, + struct kho_block_header_ser *ser) +{ + struct kho_block *block, *last; + + if (bs->nblocks >= KHO_MAX_BLOCKS) + return -ENOSPC; + + block = kzalloc_obj(*block); + if (!block) + return -ENOMEM; + + block->ser = ser; + last = list_last_entry_or_null(&bs->blocks, struct kho_block, list); + list_add_tail(&block->list, &bs->blocks); + bs->nblocks++; + + if (last) + last->ser->next = virt_to_phys(ser); + else + bs->head_pa = virt_to_phys(ser); + + return 0; +} + +static int kho_block_set_grow_one(struct kho_block_set *bs) +{ + struct kho_block_header_ser *ser; + int err; + + ser = kho_block_alloc_ser(bs); + if (IS_ERR(ser)) + return PTR_ERR(ser); + + err = kho_block_add(bs, ser); + if (err) { + kho_block_free_ser(bs, ser); + return err; + } + + return 0; +} + +static void kho_block_set_shrink_one(struct kho_block_set *bs) +{ + struct kho_block *last, *new_last; + + if (list_empty(&bs->blocks)) + return; + + last = list_last_entry(&bs->blocks, struct kho_block, list); + list_del(&last->list); + bs->nblocks--; + kho_block_free_ser(bs, last->ser); + kfree(last); + + new_last = list_last_entry_or_null(&bs->blocks, struct kho_block, list); + if (new_last) + new_last->ser->next = 0; + else + bs->head_pa = 0; +} + +/** + * kho_block_set_grow - Expand the block set to accommodate the target count. + * @bs: The block set. + * @count: The target number of valid entries to accommodate. + * + * Dynamically preallocates and links preserved memory blocks if the target + * entry count exceeds the current total capacity of the set, ensuring they + * are available during serialization/deserialization. + * + * Context: Caller must hold a lock protecting the block set. + * Return: 0 on success, or a negative errno on failure. + */ +int kho_block_set_grow(struct kho_block_set *bs, u64 count) +{ + long orig_nblocks = bs->nblocks; + int err; + + if (WARN_ON_ONCE(bs->incoming)) + return -EINVAL; + + while (count > bs->nblocks * bs->count_per_block) { + err = kho_block_set_grow_one(bs); + if (err) + goto err_shrink; + } + + return 0; + +err_shrink: + while (bs->nblocks > orig_nblocks) + kho_block_set_shrink_one(bs); + return err; +} + +/** + * kho_block_set_shrink - Shrink the block set to accommodate the target count. + * @bs: The block set. + * @count: The target number of valid entries to accommodate. + * + * Releases and unallocates redundant preserved memory blocks. Checks if the + * last block in the set can be removed because the remaining entry count is + * fully accommodated by the preceding blocks. + * + * Note: It is the caller's responsibility to ensure that entries are removed + * in the reverse order of their insertion. Because shrinking destroys the last + * block in the set, removing entries in any other order would corrupt active + * data. + * + * Context: Caller must hold a lock protecting the block set. + */ +void kho_block_set_shrink(struct kho_block_set *bs, u64 count) +{ + while (bs->nblocks > 0 && count <= (bs->nblocks - 1) * bs->count_per_block) + kho_block_set_shrink_one(bs); +} + +/* + * kho_block_set_is_cyclic - Check for cycles in a linked list of blocks. + * Uses Floyd's cycle-finding algorithm to ensure sanity of the incoming list. + * + * Return: true if a cycle or corruption is detected, false otherwise. + */ +static bool kho_block_set_is_cyclic(struct kho_block_set *bs) +{ + struct kho_block_header_ser *fast; + struct kho_block_header_ser *slow; + int count = 0; + + fast = phys_to_virt(bs->head_pa); + slow = fast; + + while (fast) { + if (count++ >= KHO_MAX_BLOCKS) { + pr_err("Block set is corrupted\n"); + return true; + } + + if (!fast->next) + break; + + fast = phys_to_virt(fast->next); + if (!fast->next) + break; + + fast = phys_to_virt(fast->next); + slow = phys_to_virt(slow->next); + + if (slow == fast) { + pr_err("Block set is corrupted\n"); + return true; + } + } + + return false; +} + +/** + * kho_block_set_restore - Restore a block set from a physical address. + * @bs: The block set to restore. + * @head_pa: Physical address of the first block header. + * + * Restores a serialized block set from a given physical address. The caller is + * responsible for ensuring that the block set @bs has been allocated and + * initialized prior to calling this function. + * + * Return: 0 on success, or a negative errno on failure. + */ +int kho_block_set_restore(struct kho_block_set *bs, u64 head_pa) +{ + struct kho_block_header_ser *ser; + u64 next_pa = head_pa; + int err; + + /* Restored block sets use size from the previous kernel */ + bs->incoming = true; + if (!head_pa) + return 0; + + bs->head_pa = head_pa; + if (kho_block_set_is_cyclic(bs)) { + bs->head_pa = 0; + return -EINVAL; + } + + while (next_pa) { + ser = phys_to_virt(next_pa); + if (!ser->count || ser->count > bs->count_per_block) { + pr_warn("Block contains invalid entry count: %llu\n", + ser->count); + err = -EINVAL; + goto err_destroy; + } + err = kho_block_add(bs, ser); + if (err) + goto err_destroy; + next_pa = ser->next; + } + + return 0; + +err_destroy: + kho_block_set_destroy(bs); + + /* Free the remaining un-restored blocks in the physical chain */ + while (next_pa) { + struct kho_block_header_ser *next_ser = phys_to_virt(next_pa); + + next_pa = next_ser->next; + kho_block_free_ser(bs, next_ser); + } + return err; +} + +/** + * kho_block_set_destroy - Destroy all blocks in a block set. + * @bs: The block set. + */ +void kho_block_set_destroy(struct kho_block_set *bs) +{ + struct kho_block *block, *tmp; + + list_for_each_entry_safe(block, tmp, &bs->blocks, list) { + list_del(&block->list); + kho_block_free_ser(bs, block->ser); + kfree(block); + } + bs->nblocks = 0; + bs->head_pa = 0; +} + +/** + * kho_block_set_clear - Clear all serialized data in a block set. + * @bs: The block set to clear. + */ +void kho_block_set_clear(struct kho_block_set *bs) +{ + struct kho_block *block; + + list_for_each_entry(block, &bs->blocks, list) { + block->ser->count = 0; + memset(block->ser + 1, 0, KHO_BLOCK_SIZE - sizeof(*block->ser)); + } +} + +/** + * kho_block_set_it_init - Initialize a block set iterator. + * @it: The iterator to initialize. + * @bs: The block set to iterate over. + */ +void kho_block_set_it_init(struct kho_block_set_it *it, struct kho_block_set *bs) +{ + it->bs = bs; + it->block = list_first_entry_or_null(&bs->blocks, struct kho_block, list); + it->i = 0; +} + +/** + * kho_block_set_it_reserve_entry - Reserve and return the next available slot for writing. + * @it: The block iterator. + * + * Reserves a slot in the current block during state serialization to add a new + * entry, advancing the internal index. If the current block is full, it + * automatically moves to the next block in the set. + * + * Return: A pointer to the reserved entry slot, or NULL if the block set's + * capacity is fully exhausted. + */ +void *kho_block_set_it_reserve_entry(struct kho_block_set_it *it) +{ + void *entry; + + if (!it->block) + return NULL; + + if (it->i == it->bs->count_per_block) { + if (list_is_last(&it->block->list, &it->bs->blocks)) + return NULL; + it->block = list_next_entry(it->block, list); + it->i = 0; + } + + entry = kho_block_entry(it, it->i++); + it->block->ser->count = it->i; + return entry; +} + +/** + * kho_block_set_it_read_entry - Read the next serialized entry from the block set. + * @it: The block iterator. + * + * Iterates through previously written entries during state deserialization, + * respecting the actual count stored in each block's header. + * + * Return: A pointer to the next serialized entry, or NULL if all serialized + * entries have been read. + */ +void *kho_block_set_it_read_entry(struct kho_block_set_it *it) +{ + if (!it->block) + return NULL; + + if (it->i == it->block->ser->count) { + if (list_is_last(&it->block->list, &it->bs->blocks)) + return NULL; + it->block = list_next_entry(it->block, list); + it->i = 0; + } + + return kho_block_entry(it, it->i++); +} + +/** + * kho_block_set_it_prev - Return the previous entry slot in the block set. + * @it: The block iterator. + * + * If the current index is at the start of a block, it automatically moves to + * the end of the previous block. + * + * Return: A pointer to the previous entry slot, or NULL if at the very + * beginning of the block set. + */ +void *kho_block_set_it_prev(struct kho_block_set_it *it) +{ + if (!it->block) + return NULL; + + if (it->i == 0) { + if (list_is_first(&it->block->list, &it->bs->blocks)) + return NULL; + it->block = list_prev_entry(it->block, list); + it->i = it->bs->count_per_block; + } + + return kho_block_entry(it, --it->i); +} diff --git a/kernel/liveupdate/luo_core.c b/kernel/liveupdate/luo_core.c index 803f51c84275..1b2bda22902d 100644 --- a/kernel/liveupdate/luo_core.c +++ b/kernel/liveupdate/luo_core.c @@ -36,6 +36,10 @@ * * LUO uses Kexec Handover to transfer memory state from the current kernel to * the next kernel. For more details see Documentation/core-api/kho/index.rst. + * + * .. note:: + * To enable LUO, boot the kernel with the ``liveupdate=on`` command line + * parameter. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -50,22 +54,19 @@ #include <linux/kexec_handover.h> #include <linux/kho/abi/luo.h> #include <linux/kobject.h> -#include <linux/libfdt.h> #include <linux/liveupdate.h> #include <linux/miscdevice.h> #include <linux/mm.h> #include <linux/rwsem.h> #include <linux/sizes.h> #include <linux/string.h> -#include <linux/unaligned.h> #include "kexec_handover_internal.h" #include "luo_internal.h" static struct { bool enabled; - void *fdt_out; - void *fdt_in; + struct luo_ser *luo_ser_out; u64 liveupdate_num; } luo_global; @@ -82,9 +83,10 @@ early_param("liveupdate", early_liveupdate_param); static int __init luo_early_startup(void) { - phys_addr_t fdt_phys; - int err, ln_size; - const void *ptr; + phys_addr_t luo_ser_phys; + struct luo_ser *luo_ser; + size_t len; + int err; if (!kho_is_enabled()) { if (liveupdate_enabled()) @@ -93,48 +95,43 @@ static int __init luo_early_startup(void) return 0; } - /* Retrieve LUO subtree, and verify its format. */ - err = kho_retrieve_subtree(LUO_FDT_KHO_ENTRY_NAME, &fdt_phys, NULL); + /* Retrieve LUO state from KHO. */ + err = kho_retrieve_subtree(LUO_KHO_ENTRY_NAME, &luo_ser_phys, &len); if (err) { if (err != -ENOENT) { - pr_err("failed to retrieve FDT '%s' from KHO: %pe\n", - LUO_FDT_KHO_ENTRY_NAME, ERR_PTR(err)); + pr_err("failed to retrieve LUO state '%s' from KHO: %pe\n", + LUO_KHO_ENTRY_NAME, ERR_PTR(err)); return err; } return 0; } - luo_global.fdt_in = phys_to_virt(fdt_phys); - err = fdt_node_check_compatible(luo_global.fdt_in, 0, - LUO_FDT_COMPATIBLE); - if (err) { - pr_err("FDT '%s' is incompatible with '%s' [%d]\n", - LUO_FDT_KHO_ENTRY_NAME, LUO_FDT_COMPATIBLE, err); - + if (len < sizeof(*luo_ser)) { + pr_err("LUO state is too small (%zu < %zu)\n", len, sizeof(*luo_ser)); return -EINVAL; } - ln_size = 0; - ptr = fdt_getprop(luo_global.fdt_in, 0, LUO_FDT_LIVEUPDATE_NUM, - &ln_size); - if (!ptr || ln_size != sizeof(luo_global.liveupdate_num)) { - pr_err("Unable to get live update number '%s' [%d]\n", - LUO_FDT_LIVEUPDATE_NUM, ln_size); - + luo_ser = phys_to_virt(luo_ser_phys); + if (strncmp(luo_ser->compatible, LUO_ABI_COMPATIBLE, LUO_ABI_COMPAT_LEN)) { + pr_err("LUO state is incompatible with '%s'\n", LUO_ABI_COMPATIBLE); return -EINVAL; } - luo_global.liveupdate_num = get_unaligned((u64 *)ptr); + luo_global.liveupdate_num = luo_ser->liveupdate_num; pr_info("Retrieved live update data, liveupdate number: %lld\n", luo_global.liveupdate_num); - err = luo_session_setup_incoming(luo_global.fdt_in); + err = luo_session_setup_incoming(luo_ser->sessions_pa); if (err) - return err; + goto out_free_ser; + + luo_flb_setup_incoming(luo_ser->flbs_pa); - err = luo_flb_setup_incoming(luo_global.fdt_in); + err = 0; +out_free_ser: + kho_restore_free(luo_ser); return err; } @@ -153,42 +150,38 @@ static int __init liveupdate_early_init(void) } early_initcall(liveupdate_early_init); -/* Called during boot to create outgoing LUO fdt tree */ -static int __init luo_fdt_setup(void) +/* Called during boot to create outgoing LUO state */ +static int __init luo_state_setup(void) { - const u64 ln = luo_global.liveupdate_num + 1; - void *fdt_out; + struct luo_ser *luo_ser; int err; - fdt_out = kho_alloc_preserve(LUO_FDT_SIZE); - if (IS_ERR(fdt_out)) { - pr_err("failed to allocate/preserve FDT memory\n"); - return PTR_ERR(fdt_out); + luo_ser = kho_alloc_preserve(sizeof(*luo_ser)); + if (IS_ERR(luo_ser)) { + pr_err("failed to allocate/preserve LUO state memory\n"); + return PTR_ERR(luo_ser); } - err = fdt_create(fdt_out, LUO_FDT_SIZE); - err |= fdt_finish_reservemap(fdt_out); - err |= fdt_begin_node(fdt_out, ""); - err |= fdt_property_string(fdt_out, "compatible", LUO_FDT_COMPATIBLE); - err |= fdt_property(fdt_out, LUO_FDT_LIVEUPDATE_NUM, &ln, sizeof(ln)); - err |= luo_session_setup_outgoing(fdt_out); - err |= luo_flb_setup_outgoing(fdt_out); - err |= fdt_end_node(fdt_out); - err |= fdt_finish(fdt_out); + strscpy(luo_ser->compatible, LUO_ABI_COMPATIBLE, sizeof(luo_ser->compatible)); + luo_ser->liveupdate_num = luo_global.liveupdate_num + 1; + + luo_session_setup_outgoing(&luo_ser->sessions_pa); + + err = luo_flb_setup_outgoing(&luo_ser->flbs_pa); if (err) - goto exit_free; + goto exit_free_luo_ser; - err = kho_add_subtree(LUO_FDT_KHO_ENTRY_NAME, fdt_out, - fdt_totalsize(fdt_out)); + err = kho_add_subtree(LUO_KHO_ENTRY_NAME, luo_ser, sizeof(*luo_ser)); if (err) - goto exit_free; - luo_global.fdt_out = fdt_out; + goto exit_free_luo_ser; + + luo_global.luo_ser_out = luo_ser; return 0; -exit_free: - kho_unpreserve_free(fdt_out); - pr_err("failed to prepare LUO FDT: %d\n", err); +exit_free_luo_ser: + kho_unpreserve_free(luo_ser); + pr_err("failed to prepare LUO state: %d\n", err); return err; } @@ -204,7 +197,7 @@ static int __init luo_late_startup(void) if (!liveupdate_enabled()) return 0; - err = luo_fdt_setup(); + err = luo_state_setup(); if (err) luo_global.enabled = false; diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c index a0a419085e28..c39f96961a85 100644 --- a/kernel/liveupdate/luo_file.c +++ b/kernel/liveupdate/luo_file.c @@ -118,11 +118,6 @@ static LIST_HEAD(luo_file_handler_list); /* Keep track of files being preserved by LUO */ static DEFINE_XARRAY(luo_preserved_files); -/* 2 4K pages, give space for 128 files per file_set */ -#define LUO_FILE_PGCNT 2ul -#define LUO_FILE_MAX \ - ((LUO_FILE_PGCNT << PAGE_SHIFT) / sizeof(struct luo_file_ser)) - /** * struct luo_file - Represents a single preserved file instance. * @fh: Pointer to the &struct liveupdate_file_handler that manages @@ -174,39 +169,6 @@ struct luo_file { u64 token; }; -static int luo_alloc_files_mem(struct luo_file_set *file_set) -{ - size_t size; - void *mem; - - if (file_set->files) - return 0; - - WARN_ON_ONCE(file_set->count); - - size = LUO_FILE_PGCNT << PAGE_SHIFT; - mem = kho_alloc_preserve(size); - if (IS_ERR(mem)) - return PTR_ERR(mem); - - file_set->files = mem; - - return 0; -} - -static void luo_free_files_mem(struct luo_file_set *file_set) -{ - /* If file_set has files, no need to free preservation memory */ - if (file_set->count) - return; - - if (!file_set->files) - return; - - kho_unpreserve_free(file_set->files); - file_set->files = NULL; -} - static unsigned long luo_get_id(struct liveupdate_file_handler *fh, struct file *file) { @@ -276,16 +238,15 @@ int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd) if (luo_token_is_used(file_set, token)) return -EEXIST; - if (file_set->count == LUO_FILE_MAX) - return -ENOSPC; + err = kho_block_set_grow(&file_set->block_set, file_set->count + 1); + if (err) + return err; file = fget(fd); - if (!file) - return -EBADF; - - err = luo_alloc_files_mem(file_set); - if (err) - goto err_fput; + if (!file) { + err = -EBADF; + goto err_shrink; + } err = -ENOENT; down_read(&luo_register_rwlock); @@ -300,7 +261,7 @@ int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd) /* err is still -ENOENT if no handler was found */ if (err) - goto err_free_files_mem; + goto err_fput; err = xa_insert(&luo_preserved_files, luo_get_id(fh, file), file, GFP_KERNEL); @@ -343,10 +304,10 @@ err_erase_xa: xa_erase(&luo_preserved_files, luo_get_id(fh, file)); err_module_put: module_put(fh->ops->owner); -err_free_files_mem: - luo_free_files_mem(file_set); err_fput: fput(file); +err_shrink: + kho_block_set_shrink(&file_set->block_set, file_set->count); return err; } @@ -385,19 +346,21 @@ void luo_file_unpreserve_files(struct luo_file_set *file_set) args.private_data = luo_file->private_data; luo_file->fh->ops->unpreserve(&args); luo_flb_file_unpreserve(luo_file->fh); - module_put(luo_file->fh->ops->owner); xa_erase(&luo_preserved_files, luo_get_id(luo_file->fh, luo_file->file)); + module_put(luo_file->fh->ops->owner); + list_del(&luo_file->list); file_set->count--; + kho_block_set_shrink(&file_set->block_set, file_set->count); fput(luo_file->file); mutex_destroy(&luo_file->mutex); kfree(luo_file); } - luo_free_files_mem(file_set); + kho_block_set_destroy(&file_set->block_set); } static int luo_file_freeze_one(struct luo_file_set *file_set, @@ -453,7 +416,7 @@ static void __luo_file_unfreeze(struct luo_file_set *file_set, luo_file_unfreeze_one(file_set, luo_file); } - memset(file_set->files, 0, LUO_FILE_PGCNT << PAGE_SHIFT); + kho_block_set_clear(&file_set->block_set); } /** @@ -492,19 +455,24 @@ static void __luo_file_unfreeze(struct luo_file_set *file_set, int luo_file_freeze(struct luo_file_set *file_set, struct luo_file_set_ser *file_set_ser) { - struct luo_file_ser *file_ser = file_set->files; struct luo_file *luo_file; + struct kho_block_set_it it; int err; - int i; if (!file_set->count) return 0; - if (WARN_ON(!file_ser)) - return -EINVAL; + kho_block_set_it_init(&it, &file_set->block_set); - i = 0; list_for_each_entry(luo_file, &file_set->files_list, list) { + struct luo_file_ser *file_ser = kho_block_set_it_reserve_entry(&it); + + /* This should not fail normally as blocks were pre-allocated */ + if (WARN_ON_ONCE(!file_ser)) { + err = -ENOSPC; + goto err_unfreeze; + } + err = luo_file_freeze_one(file_set, luo_file); if (err < 0) { pr_warn("Freeze failed for token[%#0llx] handler[%s] err[%pe]\n", @@ -513,16 +481,14 @@ int luo_file_freeze(struct luo_file_set *file_set, goto err_unfreeze; } - strscpy(file_ser[i].compatible, luo_file->fh->compatible, - sizeof(file_ser[i].compatible)); - file_ser[i].data = luo_file->serialized_data; - file_ser[i].token = luo_file->token; - i++; + strscpy(file_ser->compatible, luo_file->fh->compatible, + sizeof(file_ser->compatible)); + file_ser->data = luo_file->serialized_data; + file_ser->token = luo_file->token; } file_set_ser->count = file_set->count; - if (file_set->files) - file_set_ser->files = virt_to_phys(file_set->files); + file_set_ser->files = kho_block_set_head_pa(&file_set->block_set); return 0; @@ -677,7 +643,6 @@ static void luo_file_finish_one(struct luo_file_set *file_set, luo_file->fh->ops->finish(&args); luo_flb_file_finish(luo_file->fh); - module_put(luo_file->fh->ops->owner); } /** @@ -738,17 +703,56 @@ int luo_file_finish(struct luo_file_set *file_set) luo_get_id(luo_file->fh, luo_file->file)); fput(luo_file->file); } + module_put(luo_file->fh->ops->owner); list_del(&luo_file->list); file_set->count--; + kho_block_set_shrink(&file_set->block_set, file_set->count); mutex_destroy(&luo_file->mutex); kfree(luo_file); } - if (file_set->files) { - kho_restore_free(file_set->files); - file_set->files = NULL; + kho_block_set_destroy(&file_set->block_set); + + return 0; +} + +static int luo_file_deserialize_one(struct luo_file_set *file_set, + struct luo_file_ser *ser) +{ + struct liveupdate_file_handler *fh; + bool handler_found = false; + struct luo_file *luo_file; + + down_read(&luo_register_rwlock); + list_private_for_each_entry(fh, &luo_file_handler_list, list) { + if (!strcmp(fh->compatible, ser->compatible)) { + if (try_module_get(fh->ops->owner)) + handler_found = true; + break; + } + } + up_read(&luo_register_rwlock); + + if (!handler_found) { + pr_warn("No registered handler for compatible '%.*s'\n", + (int)sizeof(ser->compatible), + ser->compatible); + return -ENOENT; } + luo_file = kzalloc_obj(*luo_file); + if (!luo_file) { + module_put(fh->ops->owner); + return -ENOMEM; + } + + luo_file->fh = fh; + luo_file->file = NULL; + luo_file->serialized_data = ser->data; + luo_file->token = ser->token; + mutex_init(&luo_file->mutex); + list_add_tail(&luo_file->list, &file_set->files_list); + return 0; } @@ -781,15 +785,18 @@ int luo_file_deserialize(struct luo_file_set *file_set, struct luo_file_set_ser *file_set_ser) { struct luo_file_ser *file_ser; - u64 i; + struct kho_block_set_it it; + int err; if (!file_set_ser->files) { WARN_ON(file_set_ser->count); return 0; } - file_set->count = file_set_ser->count; - file_set->files = phys_to_virt(file_set_ser->files); + file_set->count = 0; + err = kho_block_set_restore(&file_set->block_set, file_set_ser->files); + if (err) + return err; /* * Note on error handling: @@ -806,55 +813,50 @@ int luo_file_deserialize(struct luo_file_set *file_set, * userspace to detect the failure and trigger a reboot, which will * reliably reset devices and reclaim memory. */ - file_ser = file_set->files; - for (i = 0; i < file_set->count; i++) { - struct liveupdate_file_handler *fh; - bool handler_found = false; - struct luo_file *luo_file; + kho_block_set_it_init(&it, &file_set->block_set); + while ((file_ser = kho_block_set_it_read_entry(&it))) { + err = luo_file_deserialize_one(file_set, file_ser); + if (err) + goto err_destroy_blocks; + file_set->count++; + } - down_read(&luo_register_rwlock); - list_private_for_each_entry(fh, &luo_file_handler_list, list) { - if (!strcmp(fh->compatible, file_ser[i].compatible)) { - if (try_module_get(fh->ops->owner)) - handler_found = true; - break; - } - } - up_read(&luo_register_rwlock); + if (file_set->count != file_set_ser->count) { + pr_warn("File count mismatch: expected %llu, found %llu\n", + file_set_ser->count, file_set->count); + err = -EINVAL; + goto err_destroy_blocks; + } - if (!handler_found) { - pr_warn("No registered handler for compatible '%.*s'\n", - (int)sizeof(file_ser[i].compatible), - file_ser[i].compatible); - return -ENOENT; - } + return 0; - luo_file = kzalloc_obj(*luo_file); - if (!luo_file) { - module_put(fh->ops->owner); - return -ENOMEM; - } +err_destroy_blocks: + while (!list_empty(&file_set->files_list)) { + struct luo_file *luo_file; - luo_file->fh = fh; - luo_file->file = NULL; - luo_file->serialized_data = file_ser[i].data; - luo_file->token = file_ser[i].token; - mutex_init(&luo_file->mutex); - list_add_tail(&luo_file->list, &file_set->files_list); + luo_file = list_first_entry(&file_set->files_list, + struct luo_file, list); + list_del(&luo_file->list); + module_put(luo_file->fh->ops->owner); + mutex_destroy(&luo_file->mutex); + kfree(luo_file); } - - return 0; + file_set->count = 0; + kho_block_set_destroy(&file_set->block_set); + return err; } void luo_file_set_init(struct luo_file_set *file_set) { INIT_LIST_HEAD(&file_set->files_list); + kho_block_set_init(&file_set->block_set, sizeof(struct luo_file_ser)); } void luo_file_set_destroy(struct luo_file_set *file_set) { WARN_ON(file_set->count); WARN_ON(!list_empty(&file_set->files_list)); + WARN_ON(!kho_block_set_is_empty(&file_set->block_set)); } /** diff --git a/kernel/liveupdate/luo_flb.c b/kernel/liveupdate/luo_flb.c index 00f5494812c4..5c27134ce7ba 100644 --- a/kernel/liveupdate/luo_flb.c +++ b/kernel/liveupdate/luo_flb.c @@ -44,13 +44,11 @@ #include <linux/io.h> #include <linux/kexec_handover.h> #include <linux/kho/abi/luo.h> -#include <linux/libfdt.h> #include <linux/list_private.h> #include <linux/liveupdate.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> -#include <linux/unaligned.h> #include "luo_internal.h" #define LUO_FLB_PGCNT 1ul @@ -111,7 +109,7 @@ static int luo_flb_file_preserve_one(struct liveupdate_flb *flb) struct luo_flb_private *private = luo_flb_get_private(flb); scoped_guard(mutex, &private->outgoing.lock) { - if (!private->outgoing.count) { + if (!refcount_read(&private->outgoing.count)) { struct liveupdate_flb_op_args args = {0}; int err; @@ -126,8 +124,10 @@ static int luo_flb_file_preserve_one(struct liveupdate_flb *flb) } private->outgoing.data = args.data; private->outgoing.obj = args.obj; + refcount_set(&private->outgoing.count, 1); + } else { + refcount_inc(&private->outgoing.count); } - private->outgoing.count++; } return 0; @@ -138,8 +138,7 @@ static void luo_flb_file_unpreserve_one(struct liveupdate_flb *flb) struct luo_flb_private *private = luo_flb_get_private(flb); scoped_guard(mutex, &private->outgoing.lock) { - private->outgoing.count--; - if (!private->outgoing.count) { + if (refcount_dec_and_test(&private->outgoing.count)) { struct liveupdate_flb_op_args args = {0}; args.flb = flb; @@ -164,7 +163,7 @@ static int luo_flb_retrieve_one(struct liveupdate_flb *flb) bool found = false; int err; - guard(mutex)(&private->incoming.lock); + lockdep_assert_held(&private->incoming.lock); if (private->incoming.finished) return -ENODATA; @@ -178,7 +177,7 @@ static int luo_flb_retrieve_one(struct liveupdate_flb *flb) for (int i = 0; i < fh->header_ser->count; i++) { if (!strcmp(fh->ser[i].name, flb->compatible)) { private->incoming.data = fh->ser[i].data; - private->incoming.count = fh->ser[i].count; + refcount_set(&private->incoming.count, fh->ser[i].count); found = true; break; } @@ -205,16 +204,14 @@ static int luo_flb_retrieve_one(struct liveupdate_flb *flb) return 0; } -static void luo_flb_file_finish_one(struct liveupdate_flb *flb) +void liveupdate_flb_put_incoming(struct liveupdate_flb *flb) { struct luo_flb_private *private = luo_flb_get_private(flb); - u64 count; - - scoped_guard(mutex, &private->incoming.lock) - count = --private->incoming.count; + struct liveupdate_flb_op_args args = {0}; - if (!count) { - struct liveupdate_flb_op_args args = {0}; + scoped_guard(mutex, &private->incoming.lock) { + if (!refcount_dec_and_test(&private->incoming.count)) + return; if (!private->incoming.retrieved) { int err = luo_flb_retrieve_one(flb); @@ -223,16 +220,14 @@ static void luo_flb_file_finish_one(struct liveupdate_flb *flb) return; } - scoped_guard(mutex, &private->incoming.lock) { - args.flb = flb; - args.obj = private->incoming.obj; - flb->ops->finish(&args); + args.flb = flb; + args.obj = private->incoming.obj; + flb->ops->finish(&args); - private->incoming.data = 0; - private->incoming.obj = NULL; - private->incoming.finished = true; - module_put(flb->ops->owner); - } + private->incoming.data = 0; + private->incoming.obj = NULL; + private->incoming.finished = true; + module_put(flb->ops->owner); } } @@ -315,7 +310,7 @@ void luo_flb_file_finish(struct liveupdate_file_handler *fh) guard(rwsem_read)(&luo_register_rwlock); list_for_each_entry_reverse(iter, flb_list, list) - luo_flb_file_finish_one(iter->flb); + liveupdate_flb_put_incoming(iter->flb); } static void luo_flb_unregister_one(struct liveupdate_file_handler *fh, @@ -512,6 +507,8 @@ int liveupdate_flb_get_incoming(struct liveupdate_flb *flb, void **objp) if (!liveupdate_enabled()) return -EOPNOTSUPP; + guard(mutex)(&private->incoming.lock); + if (!private->incoming.obj) { int err = luo_flb_retrieve_one(flb); @@ -519,7 +516,7 @@ int liveupdate_flb_get_incoming(struct liveupdate_flb *flb, void **objp) return err; } - guard(mutex)(&private->incoming.lock); + refcount_inc(&private->incoming.count); *objp = private->incoming.obj; return 0; @@ -552,27 +549,15 @@ int liveupdate_flb_get_outgoing(struct liveupdate_flb *flb, void **objp) return 0; } -int __init luo_flb_setup_outgoing(void *fdt_out) +int __init luo_flb_setup_outgoing(u64 *flbs_pa) { struct luo_flb_header_ser *header_ser; - u64 header_ser_pa; - int err; header_ser = kho_alloc_preserve(LUO_FLB_PGCNT << PAGE_SHIFT); if (IS_ERR(header_ser)) return PTR_ERR(header_ser); - header_ser_pa = virt_to_phys(header_ser); - - err = fdt_begin_node(fdt_out, LUO_FDT_FLB_NODE_NAME); - err |= fdt_property_string(fdt_out, "compatible", - LUO_FDT_FLB_COMPATIBLE); - err |= fdt_property(fdt_out, LUO_FDT_FLB_HEADER, &header_ser_pa, - sizeof(header_ser_pa)); - err |= fdt_end_node(fdt_out); - - if (err) - goto err_unpreserve; + *flbs_pa = virt_to_phys(header_ser); header_ser->pgcnt = LUO_FLB_PGCNT; luo_flb_global.outgoing.header_ser = header_ser; @@ -580,53 +565,19 @@ int __init luo_flb_setup_outgoing(void *fdt_out) luo_flb_global.outgoing.active = true; return 0; - -err_unpreserve: - kho_unpreserve_free(header_ser); - - return err; } -int __init luo_flb_setup_incoming(void *fdt_in) +void __init luo_flb_setup_incoming(u64 flbs_pa) { struct luo_flb_header_ser *header_ser; - int err, header_size, offset; - const void *ptr; - u64 header_ser_pa; - offset = fdt_subnode_offset(fdt_in, 0, LUO_FDT_FLB_NODE_NAME); - if (offset < 0) { - pr_err("Unable to get FLB node [%s]\n", LUO_FDT_FLB_NODE_NAME); - - return -ENOENT; - } - - err = fdt_node_check_compatible(fdt_in, offset, - LUO_FDT_FLB_COMPATIBLE); - if (err) { - pr_err("FLB node is incompatible with '%s' [%d]\n", - LUO_FDT_FLB_COMPATIBLE, err); - - return -EINVAL; - } - - header_size = 0; - ptr = fdt_getprop(fdt_in, offset, LUO_FDT_FLB_HEADER, &header_size); - if (!ptr || header_size != sizeof(u64)) { - pr_err("Unable to get FLB header property '%s' [%d]\n", - LUO_FDT_FLB_HEADER, header_size); - - return -EINVAL; - } - - header_ser_pa = get_unaligned((u64 *)ptr); - header_ser = phys_to_virt(header_ser_pa); + if (!flbs_pa) + return; + header_ser = phys_to_virt(flbs_pa); luo_flb_global.incoming.header_ser = header_ser; luo_flb_global.incoming.ser = (void *)(header_ser + 1); luo_flb_global.incoming.active = true; - - return 0; } /** @@ -652,12 +603,13 @@ void luo_flb_serialize(void) guard(rwsem_read)(&luo_register_rwlock); list_private_for_each_entry(gflb, &luo_flb_global.list, private.list) { struct luo_flb_private *private = luo_flb_get_private(gflb); + long count = refcount_read(&private->outgoing.count); - if (private->outgoing.count > 0) { + if (count > 0) { strscpy(fh->ser[i].name, gflb->compatible, sizeof(fh->ser[i].name)); fh->ser[i].data = private->outgoing.data; - fh->ser[i].count = private->outgoing.count; + fh->ser[i].count = count; i++; } } diff --git a/kernel/liveupdate/luo_internal.h b/kernel/liveupdate/luo_internal.h index 875844d7a41d..64879ffe7378 100644 --- a/kernel/liveupdate/luo_internal.h +++ b/kernel/liveupdate/luo_internal.h @@ -10,6 +10,7 @@ #include <linux/liveupdate.h> #include <linux/uaccess.h> +#include <linux/kho_block.h> struct luo_ucmd { void __user *ubuffer; @@ -44,22 +45,20 @@ static inline int luo_ucmd_respond(struct luo_ucmd *ucmd, * struct luo_file_set - A set of files that belong to the same sessions. * @files_list: An ordered list of files associated with this session, it is * ordered by preservation time. - * @files: The physically contiguous memory block that holds the serialized - * state of files. + * @block_set: The set of serialization blocks. * @count: A counter tracking the number of files currently stored in the * @files_list for this session. */ struct luo_file_set { struct list_head files_list; - struct luo_file_ser *files; - long count; + struct kho_block_set block_set; + u64 count; }; /** * struct luo_session - Represents an active or incoming Live Update session. * @name: A unique name for this session, used for identification and * retrieval. - * @ser: Pointer to the serialized data for this session. * @list: A list_head member used to link this session into a global list * of either outgoing (to be preserved) or incoming (restored from * previous kernel) sessions. @@ -70,7 +69,6 @@ struct luo_file_set { */ struct luo_session { char name[LIVEUPDATE_SESSION_NAME_LENGTH]; - struct luo_session_ser *ser; struct list_head list; bool retrieved; struct luo_file_set file_set; @@ -81,8 +79,8 @@ extern struct rw_semaphore luo_register_rwlock; int luo_session_create(const char *name, struct file **filep); int luo_session_retrieve(const char *name, struct file **filep); -int __init luo_session_setup_outgoing(void *fdt); -int __init luo_session_setup_incoming(void *fdt); +void __init luo_session_setup_outgoing(u64 *sessions_pa); +int __init luo_session_setup_incoming(u64 sessions_pa); int luo_session_serialize(void); int luo_session_deserialize(void); @@ -104,8 +102,8 @@ int luo_flb_file_preserve(struct liveupdate_file_handler *fh); void luo_flb_file_unpreserve(struct liveupdate_file_handler *fh); void luo_flb_file_finish(struct liveupdate_file_handler *fh); void luo_flb_unregister_all(struct liveupdate_file_handler *fh); -int __init luo_flb_setup_outgoing(void *fdt); -int __init luo_flb_setup_incoming(void *fdt); +int __init luo_flb_setup_outgoing(u64 *flbs_pa); +void __init luo_flb_setup_incoming(u64 flbs_pa); void luo_flb_serialize(void); #ifdef CONFIG_LIVEUPDATE_TEST diff --git a/kernel/liveupdate/luo_session.c b/kernel/liveupdate/luo_session.c index 7a42385dabe2..b79b2a488974 100644 --- a/kernel/liveupdate/luo_session.c +++ b/kernel/liveupdate/luo_session.c @@ -24,10 +24,10 @@ * ioctls on /dev/liveupdate. * * - Serialization: Session metadata is preserved using the KHO framework. When - * a live update is triggered via kexec, an array of `struct luo_session_ser` - * is populated and placed in a preserved memory region. An FDT node is also - * created, containing the count of sessions and the physical address of this - * array. + * a live update is triggered via kexec, session metadata is serialized into + * a chain of linked-blocks and placed in a preserved memory region. The + * physical address of the first block header is stored in the centralized + * `struct luo_ser` structure. * * Session Lifecycle: * @@ -46,6 +46,38 @@ * 4. Retrieval: A userspace agent in the new kernel can then call * `luo_session_retrieve()` with a session name to get a new file * descriptor and access the preserved state. + * + * Locking: + * + * The LUO session subsystem uses a three-tier locking hierarchy to ensure thread + * safety and prevent deadlocks during concurrent session mutations and kexec + * serialization: + * + * 1. `luo_session_serialize_rwsem` (global rwsem): + * Protects session mutations (creation, retrieval, release, and ioctls) + * against the serialization process during reboot. + * + * - Readers: Taken by any path modifying or accessing session state (e.g., + * `luo_session_create()`, `luo_session_retrieve()`, `luo_session_release()`, + * and `luo_session_ioctl()`). + * - Writer: Taken by the serialization process (`luo_session_serialize()`) + * during reboot. On success, the write lock is held indefinitely to freeze + * the subsystem. On failure, it is released to allow recovery. + * + * 2. `luo_session_header->rwsem` (per-list rwsem): + * Synchronizes list-level operations for the incoming and outgoing session headers. + * + * - Writer: Taken during list mutation operations (inserting or removing a + * session from the list). + * - Reader: Taken when traversing the list (e.g., retrieving a session by name). + * + * 3. `luo_session->mutex` (per-session mutex): + * Protects the internal state and file sets of an individual session. It is + * acquired during per-session operations such as preserving, retrieving, + * or freezing files. + * + * Lock Hierarchy: + * `luo_session_serialize_rwsem` -> `luo_session_header->rwsem` -> `luo_session->mutex` */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -58,41 +90,34 @@ #include <linux/fs.h> #include <linux/io.h> #include <linux/kexec_handover.h> +#include <linux/kho_block.h> #include <linux/kho/abi/luo.h> -#include <linux/libfdt.h> #include <linux/list.h> #include <linux/liveupdate.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/slab.h> -#include <linux/unaligned.h> #include <uapi/linux/liveupdate.h> #include "luo_internal.h" -/* 16 4K pages, give space for 744 sessions */ -#define LUO_SESSION_PGCNT 16ul -#define LUO_SESSION_MAX (((LUO_SESSION_PGCNT << PAGE_SHIFT) - \ - sizeof(struct luo_session_header_ser)) / \ - sizeof(struct luo_session_ser)) - +static DECLARE_RWSEM(luo_session_serialize_rwsem); /** * struct luo_session_header - Header struct for managing LUO sessions. - * @count: The number of sessions currently tracked in the @list. - * @list: The head of the linked list of `struct luo_session` instances. - * @rwsem: A read-write semaphore providing synchronized access to the - * session list and other fields in this structure. - * @header_ser: The header data of serialization array. - * @ser: The serialized session data (an array of - * `struct luo_session_ser`). - * @active: Set to true when first initialized. If previous kernel did not - * send session data, active stays false for incoming. + * @count: The number of sessions currently tracked in the @list. + * @list: The head of the linked list of `struct luo_session` instances. + * @rwsem: A read-write semaphore providing synchronized access to the + * session list and other fields in this structure. + * @block_set: The set of serialization blocks. + * @sessions_pa: Points to the location of sessions_pa within struct luo_ser. + * @active: Set to true when first initialized. If previous kernel did not + * send session data, active stays false for incoming. */ struct luo_session_header { long count; struct list_head list; struct rw_semaphore rwsem; - struct luo_session_header_ser *header_ser; - struct luo_session_ser *ser; + struct kho_block_set block_set; + u64 *sessions_pa; bool active; }; @@ -110,10 +135,14 @@ static struct luo_session_global luo_session_global = { .incoming = { .list = LIST_HEAD_INIT(luo_session_global.incoming.list), .rwsem = __RWSEM_INITIALIZER(luo_session_global.incoming.rwsem), + .block_set = KHO_BLOCK_SET_INIT(luo_session_global.incoming.block_set, + sizeof(struct luo_session_ser)), }, .outgoing = { .list = LIST_HEAD_INIT(luo_session_global.outgoing.list), .rwsem = __RWSEM_INITIALIZER(luo_session_global.outgoing.rwsem), + .block_set = KHO_BLOCK_SET_INIT(luo_session_global.outgoing.block_set, + sizeof(struct luo_session_ser)), }, }; @@ -144,6 +173,7 @@ static int luo_session_insert(struct luo_session_header *sh, struct luo_session *session) { struct luo_session *it; + int err; guard(rwsem_write)(&sh->rwsem); @@ -152,8 +182,9 @@ static int luo_session_insert(struct luo_session_header *sh, * for new session. */ if (sh == &luo_session_global.outgoing) { - if (sh->count == LUO_SESSION_MAX) - return -ENOMEM; + err = kho_block_set_grow(&sh->block_set, sh->count + 1); + if (err) + return err; } /* @@ -178,6 +209,8 @@ static void luo_session_remove(struct luo_session_header *sh, guard(rwsem_write)(&sh->rwsem); list_del(&session->list); sh->count--; + if (sh == &luo_session_global.outgoing) + kho_block_set_shrink(&sh->block_set, sh->count); } static int luo_session_finish_one(struct luo_session *session) @@ -205,6 +238,7 @@ static int luo_session_release(struct inode *inodep, struct file *filep) struct luo_session *session = filep->private_data; struct luo_session_header *sh; + guard(rwsem_read)(&luo_session_serialize_rwsem); /* If retrieved is set, it means this session is from incoming list */ if (session->retrieved) { int err = luo_session_finish_one(session); @@ -256,10 +290,11 @@ static int luo_session_retrieve_fd(struct luo_session *session, if (argp->fd < 0) return argp->fd; - guard(mutex)(&session->mutex); + mutex_lock(&session->mutex); err = luo_retrieve_file(&session->file_set, argp->token, &file); + mutex_unlock(&session->mutex); if (err < 0) - goto err_put_fd; + goto err_put_fd; err = luo_ucmd_respond(ucmd, sizeof(*argp)); if (err) @@ -289,38 +324,80 @@ static int luo_session_finish(struct luo_session *session, return luo_ucmd_respond(ucmd, sizeof(*argp)); } +static int luo_session_get_name(struct luo_session *session, + struct luo_ucmd *ucmd) +{ + struct liveupdate_session_get_name *argp = ucmd->cmd; + + if (argp->reserved != 0) + return -EINVAL; + + strscpy((char *)argp->name, session->name, sizeof(argp->name)); + + return luo_ucmd_respond(ucmd, sizeof(*argp)); +} + union ucmd_buffer { struct liveupdate_session_finish finish; struct liveupdate_session_preserve_fd preserve; struct liveupdate_session_retrieve_fd retrieve; + struct liveupdate_session_get_name get_name; +}; + +/* Type of sessions the ioctl applies to. */ +enum luo_ioctl_type { + LUO_IOCTL_INCOMING, + LUO_IOCTL_OUTGOING, + LUO_IOCTL_ALL, }; struct luo_ioctl_op { unsigned int size; unsigned int min_size; unsigned int ioctl_num; + enum luo_ioctl_type type; int (*execute)(struct luo_session *session, struct luo_ucmd *ucmd); }; -#define IOCTL_OP(_ioctl, _fn, _struct, _last) \ +#define IOCTL_OP(_ioctl, _fn, _struct, _last, _type) \ [_IOC_NR(_ioctl) - LIVEUPDATE_CMD_SESSION_BASE] = { \ .size = sizeof(_struct) + \ BUILD_BUG_ON_ZERO(sizeof(union ucmd_buffer) < \ sizeof(_struct)), \ .min_size = offsetofend(_struct, _last), \ .ioctl_num = _ioctl, \ + .type = _type, \ .execute = _fn, \ } static const struct luo_ioctl_op luo_session_ioctl_ops[] = { IOCTL_OP(LIVEUPDATE_SESSION_FINISH, luo_session_finish, - struct liveupdate_session_finish, reserved), + struct liveupdate_session_finish, reserved, LUO_IOCTL_INCOMING), IOCTL_OP(LIVEUPDATE_SESSION_PRESERVE_FD, luo_session_preserve_fd, - struct liveupdate_session_preserve_fd, token), + struct liveupdate_session_preserve_fd, token, LUO_IOCTL_OUTGOING), IOCTL_OP(LIVEUPDATE_SESSION_RETRIEVE_FD, luo_session_retrieve_fd, - struct liveupdate_session_retrieve_fd, token), + struct liveupdate_session_retrieve_fd, token, LUO_IOCTL_INCOMING), + IOCTL_OP(LIVEUPDATE_SESSION_GET_NAME, luo_session_get_name, + struct liveupdate_session_retrieve_fd, token, LUO_IOCTL_ALL), }; +static bool luo_ioctl_type_valid(struct luo_session *session, + const struct luo_ioctl_op *op) +{ + switch (op->type) { + case LUO_IOCTL_INCOMING: + /* Retrieved is only set on incoming sessions */ + return session->retrieved; + case LUO_IOCTL_OUTGOING: + return !session->retrieved; + case LUO_IOCTL_ALL: + return true; + } + + /* Catch-all. */ + return false; +} + static long luo_session_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) { @@ -345,6 +422,8 @@ static long luo_session_ioctl(struct file *filep, unsigned int cmd, op = &luo_session_ioctl_ops[nr - LIVEUPDATE_CMD_SESSION_BASE]; if (op->ioctl_num != cmd) return -ENOIOCTLCMD; + if (!luo_ioctl_type_valid(session, op)) + return -EINVAL; if (ucmd.user_size < op->min_size) return -EINVAL; @@ -354,6 +433,7 @@ static long luo_session_ioctl(struct file *filep, unsigned int cmd, if (ret) return ret; + guard(rwsem_read)(&luo_session_serialize_rwsem); return op->execute(session, &ucmd); } @@ -382,21 +462,28 @@ static int luo_session_getfile(struct luo_session *session, struct file **filep) int luo_session_create(const char *name, struct file **filep) { + size_t len = strnlen(name, LIVEUPDATE_SESSION_NAME_LENGTH); struct luo_session *session; int err; + if (len == 0 || len > LIVEUPDATE_SESSION_NAME_LENGTH - 1) + return -EINVAL; + session = luo_session_alloc(name); if (IS_ERR(session)) return PTR_ERR(session); + down_read(&luo_session_serialize_rwsem); err = luo_session_insert(&luo_session_global.outgoing, session); if (err) goto err_free; - scoped_guard(mutex, &session->mutex) - err = luo_session_getfile(session, filep); + mutex_lock(&session->mutex); + err = luo_session_getfile(session, filep); + mutex_unlock(&session->mutex); if (err) goto err_remove; + up_read(&luo_session_serialize_rwsem); return 0; @@ -404,6 +491,7 @@ err_remove: luo_session_remove(&luo_session_global.outgoing, session); err_free: luo_session_free(session); + up_read(&luo_session_serialize_rwsem); return err; } @@ -415,12 +503,12 @@ int luo_session_retrieve(const char *name, struct file **filep) struct luo_session *it; int err; - scoped_guard(rwsem_read, &sh->rwsem) { - list_for_each_entry(it, &sh->list, list) { - if (!strncmp(it->name, name, sizeof(it->name))) { - session = it; - break; - } + guard(rwsem_read)(&luo_session_serialize_rwsem); + guard(rwsem_read)(&sh->rwsem); + list_for_each_entry(it, &sh->list, list) { + if (!strncmp(it->name, name, sizeof(it->name))) { + session = it; + break; } } @@ -438,74 +526,58 @@ int luo_session_retrieve(const char *name, struct file **filep) return err; } -int __init luo_session_setup_outgoing(void *fdt_out) +void __init luo_session_setup_outgoing(u64 *sessions_pa) { - struct luo_session_header_ser *header_ser; - u64 header_ser_pa; - int err; + luo_session_global.outgoing.sessions_pa = sessions_pa; + luo_session_global.outgoing.active = true; +} - header_ser = kho_alloc_preserve(LUO_SESSION_PGCNT << PAGE_SHIFT); - if (IS_ERR(header_ser)) - return PTR_ERR(header_ser); - header_ser_pa = virt_to_phys(header_ser); +int __init luo_session_setup_incoming(u64 sessions_pa) +{ + struct luo_session_header *sh = &luo_session_global.incoming; + int err; - err = fdt_begin_node(fdt_out, LUO_FDT_SESSION_NODE_NAME); - err |= fdt_property_string(fdt_out, "compatible", - LUO_FDT_SESSION_COMPATIBLE); - err |= fdt_property(fdt_out, LUO_FDT_SESSION_HEADER, &header_ser_pa, - sizeof(header_ser_pa)); - err |= fdt_end_node(fdt_out); + if (!sessions_pa) + return 0; + err = kho_block_set_restore(&sh->block_set, sessions_pa); if (err) - goto err_unpreserve; - - luo_session_global.outgoing.header_ser = header_ser; - luo_session_global.outgoing.ser = (void *)(header_ser + 1); - luo_session_global.outgoing.active = true; + return err; + sh->active = true; return 0; - -err_unpreserve: - kho_unpreserve_free(header_ser); - return err; } -int __init luo_session_setup_incoming(void *fdt_in) +static int luo_session_deserialize_one(struct luo_session_header *sh, + struct luo_session_ser *ser) { - struct luo_session_header_ser *header_ser; - int err, header_size, offset; - u64 header_ser_pa; - const void *ptr; - - offset = fdt_subnode_offset(fdt_in, 0, LUO_FDT_SESSION_NODE_NAME); - if (offset < 0) { - pr_err("Unable to get session node: [%s]\n", - LUO_FDT_SESSION_NODE_NAME); - return -EINVAL; + struct luo_session *session; + int err; + + session = luo_session_alloc(ser->name); + if (IS_ERR(session)) { + pr_warn("Failed to allocate session [%.*s] during deserialization %pe\n", + (int)sizeof(ser->name), ser->name, session); + return PTR_ERR(session); } - err = fdt_node_check_compatible(fdt_in, offset, - LUO_FDT_SESSION_COMPATIBLE); + err = luo_session_insert(sh, session); if (err) { - pr_err("Session node incompatible [%s]\n", - LUO_FDT_SESSION_COMPATIBLE); - return -EINVAL; + pr_warn("Failed to insert session [%s] %pe\n", + session->name, ERR_PTR(err)); + luo_session_free(session); + return err; } - header_size = 0; - ptr = fdt_getprop(fdt_in, offset, LUO_FDT_SESSION_HEADER, &header_size); - if (!ptr || header_size != sizeof(u64)) { - pr_err("Unable to get session header '%s' [%d]\n", - LUO_FDT_SESSION_HEADER, header_size); - return -EINVAL; + scoped_guard(mutex, &session->mutex) { + err = luo_file_deserialize(&session->file_set, + &ser->file_set_ser); + } + if (err) { + pr_warn("Failed to deserialize files for session [%s] %pe\n", + session->name, ERR_PTR(err)); + return err; } - - header_ser_pa = get_unaligned((u64 *)ptr); - header_ser = phys_to_virt(header_ser_pa); - - luo_session_global.incoming.header_ser = header_ser; - luo_session_global.incoming.ser = (void *)(header_ser + 1); - luo_session_global.incoming.active = true; return 0; } @@ -514,6 +586,8 @@ int luo_session_deserialize(void) { struct luo_session_header *sh = &luo_session_global.incoming; static bool is_deserialized; + struct luo_session_ser *ser; + struct kho_block_set_it it; static int saved_err; int err; @@ -540,43 +614,19 @@ int luo_session_deserialize(void) * userspace to detect the failure and trigger a reboot, which will * reliably reset devices and reclaim memory. */ - for (int i = 0; i < sh->header_ser->count; i++) { - struct luo_session *session; - - session = luo_session_alloc(sh->ser[i].name); - if (IS_ERR(session)) { - pr_warn("Failed to allocate session [%.*s] during deserialization %pe\n", - (int)sizeof(sh->ser[i].name), - sh->ser[i].name, session); - err = PTR_ERR(session); - goto save_err; - } - - err = luo_session_insert(sh, session); - if (err) { - pr_warn("Failed to insert session [%s] %pe\n", - session->name, ERR_PTR(err)); - luo_session_free(session); - goto save_err; - } - - scoped_guard(mutex, &session->mutex) { - err = luo_file_deserialize(&session->file_set, - &sh->ser[i].file_set_ser); - } - if (err) { - pr_warn("Failed to deserialize files for session [%s] %pe\n", - session->name, ERR_PTR(err)); + kho_block_set_it_init(&it, &sh->block_set); + while ((ser = kho_block_set_it_read_entry(&it))) { + err = luo_session_deserialize_one(sh, ser); + if (err) goto save_err; - } } - kho_restore_free(sh->header_ser); - sh->header_ser = NULL; - sh->ser = NULL; + kho_block_set_destroy(&sh->block_set); return 0; + save_err: + kho_block_set_destroy(&sh->block_set); saved_err = err; return err; } @@ -585,30 +635,48 @@ int luo_session_serialize(void) { struct luo_session_header *sh = &luo_session_global.outgoing; struct luo_session *session; - int i = 0; + struct kho_block_set_it it; int err; - guard(rwsem_write)(&sh->rwsem); + down_write(&luo_session_serialize_rwsem); + down_write(&sh->rwsem); + *sh->sessions_pa = 0; + + kho_block_set_it_init(&it, &sh->block_set); + list_for_each_entry(session, &sh->list, list) { - err = luo_session_freeze_one(session, &sh->ser[i]); - if (err) + struct luo_session_ser *ser = kho_block_set_it_reserve_entry(&it); + + /* This should not fail normally as blocks were pre-allocated */ + if (WARN_ON_ONCE(!ser)) { + err = -ENOSPC; + goto err_undo; + } + + err = luo_session_freeze_one(session, ser); + if (err) { + kho_block_set_it_prev(&it); goto err_undo; + } - strscpy(sh->ser[i].name, session->name, - sizeof(sh->ser[i].name)); - i++; + strscpy(ser->name, session->name, sizeof(ser->name)); } - sh->header_ser->count = sh->count; + + if (sh->count > 0) + *sh->sessions_pa = kho_block_set_head_pa(&sh->block_set); + up_write(&sh->rwsem); return 0; err_undo: list_for_each_entry_continue_reverse(session, &sh->list, list) { - i--; - luo_session_unfreeze_one(session, &sh->ser[i]); - memset(sh->ser[i].name, 0, sizeof(sh->ser[i].name)); + struct luo_session_ser *ser = kho_block_set_it_prev(&it); + + luo_session_unfreeze_one(session, ser); + memset(ser->name, 0, sizeof(ser->name)); } + up_write(&sh->rwsem); + up_write(&luo_session_serialize_rwsem); return err; } - |
