From 3d5611b4d7efbefb85a74fcdbc35c603847cc022 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 6 Dec 2024 19:06:15 +0800 Subject: [PATCH 01/16] bpf: Remove unnecessary kfree(im_node) in lpm_trie_update_elem MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit There is no need to call kfree(im_node) when updating element fails, because im_node must be NULL. Remove the unnecessary kfree() for im_node. Reviewed-by: Toke Høiland-Jørgensen Acked-by: Daniel Borkmann Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20241206110622.1161752-3-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/lpm_trie.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 73fd593d3745..b5e281a55760 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -315,7 +315,7 @@ static long trie_update_elem(struct bpf_map *map, void *_key, void *value, u64 flags) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); - struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL; + struct lpm_trie_node *node, *im_node, *new_node = NULL; struct lpm_trie_node *free_node = NULL; struct lpm_trie_node __rcu **slot; struct bpf_lpm_trie_key_u8 *key = _key; @@ -431,9 +431,7 @@ out: if (ret) { if (new_node) trie->n_entries--; - kfree(new_node); - kfree(im_node); } spin_unlock_irqrestore(&trie->lock, irq_flags); -- 2.51.0 From eae6a075e9537dd69891cf77ca5a88fa8a28b4a1 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 6 Dec 2024 19:06:16 +0800 Subject: [PATCH 02/16] bpf: Handle BPF_EXIST and BPF_NOEXIST for LPM trie MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Add the currently missing handling for the BPF_EXIST and BPF_NOEXIST flags. These flags can be specified by users and are relevant since LPM trie supports exact matches during update. Fixes: b95a5c4db09b ("bpf: add a longest prefix match trie map implementation") Reviewed-by: Toke Høiland-Jørgensen Acked-by: Daniel Borkmann Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20241206110622.1161752-4-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/lpm_trie.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index b5e281a55760..be5bf0389532 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -375,6 +375,10 @@ static long trie_update_elem(struct bpf_map *map, * simply assign the @new_node to that slot and be done. */ if (!node) { + if (flags == BPF_EXIST) { + ret = -ENOENT; + goto out; + } rcu_assign_pointer(*slot, new_node); goto out; } @@ -383,18 +387,31 @@ static long trie_update_elem(struct bpf_map *map, * which already has the correct data array set. */ if (node->prefixlen == matchlen) { + if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) { + if (flags == BPF_NOEXIST) { + ret = -EEXIST; + goto out; + } + trie->n_entries--; + } else if (flags == BPF_EXIST) { + ret = -ENOENT; + goto out; + } + new_node->child[0] = node->child[0]; new_node->child[1] = node->child[1]; - if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) - trie->n_entries--; - rcu_assign_pointer(*slot, new_node); free_node = node; goto out; } + if (flags == BPF_EXIST) { + ret = -ENOENT; + goto out; + } + /* If the new node matches the prefix completely, it must be inserted * as an ancestor. Simply insert it between @node and *@slot. */ -- 2.51.0 From 532d6b36b2bfac5514426a97a4df8d103d700d43 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 6 Dec 2024 19:06:17 +0800 Subject: [PATCH 03/16] bpf: Handle in-place update for full LPM trie correctly MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit When a LPM trie is full, in-place updates of existing elements incorrectly return -ENOSPC. Fix this by deferring the check of trie->n_entries. For new insertions, n_entries must not exceed max_entries. However, in-place updates are allowed even when the trie is full. Fixes: b95a5c4db09b ("bpf: add a longest prefix match trie map implementation") Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20241206110622.1161752-5-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/lpm_trie.c | 44 +++++++++++++++++++++---------------------- 1 file changed, 21 insertions(+), 23 deletions(-) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index be5bf0389532..df6cc0a1c9bf 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -310,6 +310,16 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, return node; } +static int trie_check_add_elem(struct lpm_trie *trie, u64 flags) +{ + if (flags == BPF_EXIST) + return -ENOENT; + if (trie->n_entries == trie->map.max_entries) + return -ENOSPC; + trie->n_entries++; + return 0; +} + /* Called from syscall or from eBPF program */ static long trie_update_elem(struct bpf_map *map, void *_key, void *value, u64 flags) @@ -333,20 +343,12 @@ static long trie_update_elem(struct bpf_map *map, spin_lock_irqsave(&trie->lock, irq_flags); /* Allocate and fill a new node */ - - if (trie->n_entries == trie->map.max_entries) { - ret = -ENOSPC; - goto out; - } - new_node = lpm_trie_node_alloc(trie, value); if (!new_node) { ret = -ENOMEM; goto out; } - trie->n_entries++; - new_node->prefixlen = key->prefixlen; RCU_INIT_POINTER(new_node->child[0], NULL); RCU_INIT_POINTER(new_node->child[1], NULL); @@ -375,10 +377,10 @@ static long trie_update_elem(struct bpf_map *map, * simply assign the @new_node to that slot and be done. */ if (!node) { - if (flags == BPF_EXIST) { - ret = -ENOENT; + ret = trie_check_add_elem(trie, flags); + if (ret) goto out; - } + rcu_assign_pointer(*slot, new_node); goto out; } @@ -392,10 +394,10 @@ static long trie_update_elem(struct bpf_map *map, ret = -EEXIST; goto out; } - trie->n_entries--; - } else if (flags == BPF_EXIST) { - ret = -ENOENT; - goto out; + } else { + ret = trie_check_add_elem(trie, flags); + if (ret) + goto out; } new_node->child[0] = node->child[0]; @@ -407,10 +409,9 @@ static long trie_update_elem(struct bpf_map *map, goto out; } - if (flags == BPF_EXIST) { - ret = -ENOENT; + ret = trie_check_add_elem(trie, flags); + if (ret) goto out; - } /* If the new node matches the prefix completely, it must be inserted * as an ancestor. Simply insert it between @node and *@slot. @@ -424,6 +425,7 @@ static long trie_update_elem(struct bpf_map *map, im_node = lpm_trie_node_alloc(trie, NULL); if (!im_node) { + trie->n_entries--; ret = -ENOMEM; goto out; } @@ -445,12 +447,8 @@ static long trie_update_elem(struct bpf_map *map, rcu_assign_pointer(*slot, im_node); out: - if (ret) { - if (new_node) - trie->n_entries--; + if (ret) kfree(new_node); - } - spin_unlock_irqrestore(&trie->lock, irq_flags); kfree_rcu(free_node, rcu); -- 2.51.0 From 27abc7b3fa2e09bbe41e2924d328121546865eda Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 6 Dec 2024 19:06:18 +0800 Subject: [PATCH 04/16] bpf: Fix exact match conditions in trie_get_next_key() MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit trie_get_next_key() uses node->prefixlen == key->prefixlen to identify an exact match, However, it is incorrect because when the target key doesn't fully match the found node (e.g., node->prefixlen != matchlen), these two nodes may also have the same prefixlen. It will return expected result when the passed key exist in the trie. However when a recently-deleted key or nonexistent key is passed to trie_get_next_key(), it may skip keys and return incorrect result. Fix it by using node->prefixlen == matchlen to identify exact matches. When the condition is true after the search, it also implies node->prefixlen equals key->prefixlen, otherwise, the search would return NULL instead. Fixes: b471f2f1de8b ("bpf: implement MAP_GET_NEXT_KEY command for LPM_TRIE map") Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20241206110622.1161752-6-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/lpm_trie.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index df6cc0a1c9bf..9ba6ae145239 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -645,7 +645,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) struct lpm_trie_node **node_stack = NULL; int err = 0, stack_ptr = -1; unsigned int next_bit; - size_t matchlen; + size_t matchlen = 0; /* The get_next_key follows postorder. For the 4 node example in * the top of this file, the trie_get_next_key() returns the following @@ -684,7 +684,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) next_bit = extract_bit(key->data, node->prefixlen); node = rcu_dereference(node->child[next_bit]); } - if (!node || node->prefixlen != key->prefixlen || + if (!node || node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) goto find_leftmost; -- 2.51.0 From 3d8dc43eb2a3d179809f5fc27c88c93a57ea123d Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 6 Dec 2024 19:06:19 +0800 Subject: [PATCH 05/16] bpf: Switch to bpf mem allocator for LPM trie MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Multiple syzbot warnings have been reported. These warnings are mainly about the lock order between trie->lock and kmalloc()'s internal lock. See report [1] as an example: ====================================================== WARNING: possible circular locking dependency detected 6.10.0-rc7-syzkaller-00003-g4376e966ecb7 #0 Not tainted ------------------------------------------------------ syz.3.2069/15008 is trying to acquire lock: ffff88801544e6d8 (&n->list_lock){-.-.}-{2:2}, at: get_partial_node ... but task is already holding lock: ffff88802dcc89f8 (&trie->lock){-.-.}-{2:2}, at: trie_update_elem ... which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&trie->lock){-.-.}-{2:2}: __raw_spin_lock_irqsave _raw_spin_lock_irqsave+0x3a/0x60 trie_delete_elem+0xb0/0x820 ___bpf_prog_run+0x3e51/0xabd0 __bpf_prog_run32+0xc1/0x100 bpf_dispatcher_nop_func ...... bpf_trace_run2+0x231/0x590 __bpf_trace_contention_end+0xca/0x110 trace_contention_end.constprop.0+0xea/0x170 __pv_queued_spin_lock_slowpath+0x28e/0xcc0 pv_queued_spin_lock_slowpath queued_spin_lock_slowpath queued_spin_lock do_raw_spin_lock+0x210/0x2c0 __raw_spin_lock_irqsave _raw_spin_lock_irqsave+0x42/0x60 __put_partials+0xc3/0x170 qlink_free qlist_free_all+0x4e/0x140 kasan_quarantine_reduce+0x192/0x1e0 __kasan_slab_alloc+0x69/0x90 kasan_slab_alloc slab_post_alloc_hook slab_alloc_node kmem_cache_alloc_node_noprof+0x153/0x310 __alloc_skb+0x2b1/0x380 ...... -> #0 (&n->list_lock){-.-.}-{2:2}: check_prev_add check_prevs_add validate_chain __lock_acquire+0x2478/0x3b30 lock_acquire lock_acquire+0x1b1/0x560 __raw_spin_lock_irqsave _raw_spin_lock_irqsave+0x3a/0x60 get_partial_node.part.0+0x20/0x350 get_partial_node get_partial ___slab_alloc+0x65b/0x1870 __slab_alloc.constprop.0+0x56/0xb0 __slab_alloc_node slab_alloc_node __do_kmalloc_node __kmalloc_node_noprof+0x35c/0x440 kmalloc_node_noprof bpf_map_kmalloc_node+0x98/0x4a0 lpm_trie_node_alloc trie_update_elem+0x1ef/0xe00 bpf_map_update_value+0x2c1/0x6c0 map_update_elem+0x623/0x910 __sys_bpf+0x90c/0x49a0 ... other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&trie->lock); lock(&n->list_lock); lock(&trie->lock); lock(&n->list_lock); *** DEADLOCK *** [1]: https://syzkaller.appspot.com/bug?extid=9045c0a3d5a7f1b119f7 A bpf program attached to trace_contention_end() triggers after acquiring &n->list_lock. The program invokes trie_delete_elem(), which then acquires trie->lock. However, it is possible that another process is invoking trie_update_elem(). trie_update_elem() will acquire trie->lock first, then invoke kmalloc_node(). kmalloc_node() may invoke get_partial_node() and try to acquire &n->list_lock (not necessarily the same lock object). Therefore, lockdep warns about the circular locking dependency. Invoking kmalloc() before acquiring trie->lock could fix the warning. However, since BPF programs call be invoked from any context (e.g., through kprobe/tracepoint/fentry), there may still be lock ordering problems for internal locks in kmalloc() or trie->lock itself. To eliminate these potential lock ordering problems with kmalloc()'s internal locks, replacing kmalloc()/kfree()/kfree_rcu() with equivalent BPF memory allocator APIs that can be invoked in any context. The lock ordering problems with trie->lock (e.g., reentrance) will be handled separately. Three aspects of this change require explanation: 1. Intermediate and leaf nodes are allocated from the same allocator. Since the value size of LPM trie is usually small, using a single alocator reduces the memory overhead of the BPF memory allocator. 2. Leaf nodes are allocated before disabling IRQs. This handles cases where leaf_size is large (e.g., > 4KB - 8) and updates require intermediate node allocation. If leaf nodes were allocated in IRQ-disabled region, the free objects in BPF memory allocator would not be refilled timely and the intermediate node allocation may fail. 3. Paired migrate_{disable|enable}() calls for node alloc and free. The BPF memory allocator uses per-CPU struct internally, these paired calls are necessary to guarantee correctness. Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20241206110622.1161752-7-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/lpm_trie.c | 71 +++++++++++++++++++++++++++++-------------- 1 file changed, 48 insertions(+), 23 deletions(-) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 9ba6ae145239..f850360e75ce 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -15,6 +15,7 @@ #include #include #include +#include /* Intermediate node */ #define LPM_TREE_NODE_FLAG_IM BIT(0) @@ -22,7 +23,6 @@ struct lpm_trie_node; struct lpm_trie_node { - struct rcu_head rcu; struct lpm_trie_node __rcu *child[2]; u32 prefixlen; u32 flags; @@ -32,6 +32,7 @@ struct lpm_trie_node { struct lpm_trie { struct bpf_map map; struct lpm_trie_node __rcu *root; + struct bpf_mem_alloc ma; size_t n_entries; size_t max_prefixlen; size_t data_size; @@ -287,17 +288,18 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) return found->data + trie->data_size; } -static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, - const void *value) +static struct lpm_trie_node *lpm_trie_node_alloc(struct lpm_trie *trie, + const void *value, + bool disable_migration) { struct lpm_trie_node *node; - size_t size = sizeof(struct lpm_trie_node) + trie->data_size; - if (value) - size += trie->map.value_size; + if (disable_migration) + migrate_disable(); + node = bpf_mem_cache_alloc(&trie->ma); + if (disable_migration) + migrate_enable(); - node = bpf_map_kmalloc_node(&trie->map, size, GFP_NOWAIT | __GFP_NOWARN, - trie->map.numa_node); if (!node) return NULL; @@ -325,7 +327,7 @@ static long trie_update_elem(struct bpf_map *map, void *_key, void *value, u64 flags) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); - struct lpm_trie_node *node, *im_node, *new_node = NULL; + struct lpm_trie_node *node, *im_node, *new_node; struct lpm_trie_node *free_node = NULL; struct lpm_trie_node __rcu **slot; struct bpf_lpm_trie_key_u8 *key = _key; @@ -340,14 +342,14 @@ static long trie_update_elem(struct bpf_map *map, if (key->prefixlen > trie->max_prefixlen) return -EINVAL; - spin_lock_irqsave(&trie->lock, irq_flags); + /* Allocate and fill a new node. Need to disable migration before + * invoking bpf_mem_cache_alloc(). + */ + new_node = lpm_trie_node_alloc(trie, value, true); + if (!new_node) + return -ENOMEM; - /* Allocate and fill a new node */ - new_node = lpm_trie_node_alloc(trie, value); - if (!new_node) { - ret = -ENOMEM; - goto out; - } + spin_lock_irqsave(&trie->lock, irq_flags); new_node->prefixlen = key->prefixlen; RCU_INIT_POINTER(new_node->child[0], NULL); @@ -423,7 +425,8 @@ static long trie_update_elem(struct bpf_map *map, goto out; } - im_node = lpm_trie_node_alloc(trie, NULL); + /* migration is disabled within the locked scope */ + im_node = lpm_trie_node_alloc(trie, NULL, false); if (!im_node) { trie->n_entries--; ret = -ENOMEM; @@ -447,10 +450,13 @@ static long trie_update_elem(struct bpf_map *map, rcu_assign_pointer(*slot, im_node); out: - if (ret) - kfree(new_node); spin_unlock_irqrestore(&trie->lock, irq_flags); - kfree_rcu(free_node, rcu); + + migrate_disable(); + if (ret) + bpf_mem_cache_free(&trie->ma, new_node); + bpf_mem_cache_free_rcu(&trie->ma, free_node); + migrate_enable(); return ret; } @@ -548,8 +554,11 @@ static long trie_delete_elem(struct bpf_map *map, void *_key) out: spin_unlock_irqrestore(&trie->lock, irq_flags); - kfree_rcu(free_parent, rcu); - kfree_rcu(free_node, rcu); + + migrate_disable(); + bpf_mem_cache_free_rcu(&trie->ma, free_parent); + bpf_mem_cache_free_rcu(&trie->ma, free_node); + migrate_enable(); return ret; } @@ -571,6 +580,8 @@ out: static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; + size_t leaf_size; + int err; /* check sanity of attributes */ if (attr->max_entries == 0 || @@ -595,7 +606,17 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) spin_lock_init(&trie->lock); + /* Allocate intermediate and leaf nodes from the same allocator */ + leaf_size = sizeof(struct lpm_trie_node) + trie->data_size + + trie->map.value_size; + err = bpf_mem_alloc_init(&trie->ma, leaf_size, false); + if (err) + goto free_out; return &trie->map; + +free_out: + bpf_map_area_free(trie); + return ERR_PTR(err); } static void trie_free(struct bpf_map *map) @@ -627,13 +648,17 @@ static void trie_free(struct bpf_map *map) continue; } - kfree(node); + /* No bpf program may access the map, so freeing the + * node without waiting for the extra RCU GP. + */ + bpf_mem_cache_raw_free(node); RCU_INIT_POINTER(*slot, NULL); break; } } out: + bpf_mem_alloc_destroy(&trie->ma); bpf_map_area_free(trie); } -- 2.51.0 From 6a5c63d43c0216d64915baa0e0eacf2beb66b271 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 6 Dec 2024 19:06:20 +0800 Subject: [PATCH 06/16] bpf: Use raw_spinlock_t for LPM trie After switching from kmalloc() to the bpf memory allocator, there will be no blocking operation during the update of LPM trie. Therefore, change trie->lock from spinlock_t to raw_spinlock_t to make LPM trie usable in atomic context, even on RT kernels. The max value of prefixlen is 2048. Therefore, update or deletion operations will find the target after at most 2048 comparisons. Constructing a test case which updates an element after 2048 comparisons under a 8 CPU VM, and the average time and the maximal time for such update operation is about 210us and 900us. Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20241206110622.1161752-8-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/lpm_trie.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index f850360e75ce..f8bc1e096182 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -36,7 +36,7 @@ struct lpm_trie { size_t n_entries; size_t max_prefixlen; size_t data_size; - spinlock_t lock; + raw_spinlock_t lock; }; /* This trie implements a longest prefix match algorithm that can be used to @@ -349,7 +349,7 @@ static long trie_update_elem(struct bpf_map *map, if (!new_node) return -ENOMEM; - spin_lock_irqsave(&trie->lock, irq_flags); + raw_spin_lock_irqsave(&trie->lock, irq_flags); new_node->prefixlen = key->prefixlen; RCU_INIT_POINTER(new_node->child[0], NULL); @@ -450,7 +450,7 @@ static long trie_update_elem(struct bpf_map *map, rcu_assign_pointer(*slot, im_node); out: - spin_unlock_irqrestore(&trie->lock, irq_flags); + raw_spin_unlock_irqrestore(&trie->lock, irq_flags); migrate_disable(); if (ret) @@ -477,7 +477,7 @@ static long trie_delete_elem(struct bpf_map *map, void *_key) if (key->prefixlen > trie->max_prefixlen) return -EINVAL; - spin_lock_irqsave(&trie->lock, irq_flags); + raw_spin_lock_irqsave(&trie->lock, irq_flags); /* Walk the tree looking for an exact key/length match and keeping * track of the path we traverse. We will need to know the node @@ -553,7 +553,7 @@ static long trie_delete_elem(struct bpf_map *map, void *_key) free_node = node; out: - spin_unlock_irqrestore(&trie->lock, irq_flags); + raw_spin_unlock_irqrestore(&trie->lock, irq_flags); migrate_disable(); bpf_mem_cache_free_rcu(&trie->ma, free_parent); @@ -604,7 +604,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) offsetof(struct bpf_lpm_trie_key_u8, data); trie->max_prefixlen = trie->data_size * 8; - spin_lock_init(&trie->lock); + raw_spin_lock_init(&trie->lock); /* Allocate intermediate and leaf nodes from the same allocator */ leaf_size = sizeof(struct lpm_trie_node) + trie->data_size + -- 2.51.0 From 3e18f5f1e5a152a51dbb6c234e2a0421aec11e31 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 6 Dec 2024 19:06:21 +0800 Subject: [PATCH 07/16] selftests/bpf: Move test_lpm_map.c to map_tests Move test_lpm_map.c to map_tests/ to include LPM trie test cases in regular test_maps run. Most code remains unchanged, including the use of assert(). Only reduce n_lookups from 64K to 512, which decreases test_lpm_map runtime from 37s to 0.7s. Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20241206110622.1161752-9-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/.gitignore | 1 - tools/testing/selftests/bpf/Makefile | 2 +- .../lpm_trie_map_basic_ops.c} | 10 +++------- 3 files changed, 4 insertions(+), 9 deletions(-) rename tools/testing/selftests/bpf/{test_lpm_map.c => map_tests/lpm_trie_map_basic_ops.c} (99%) diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index c2a1842c3d8b..e9c377001f93 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -5,7 +5,6 @@ bpf-syscall* test_verifier test_maps test_lru_map -test_lpm_map test_tag FEATURE-DUMP.libbpf FEATURE-DUMP.selftests diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 6ad3b1ba1920..7eeb3cbe18c7 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -83,7 +83,7 @@ CLANG_CPUV4 := 1 endif # Order correspond to 'make run_tests' order -TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ +TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_progs \ test_sockmap \ test_tcpnotify_user test_sysctl \ test_progs-no_alu32 diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c similarity index 99% rename from tools/testing/selftests/bpf/test_lpm_map.c rename to tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c index d98c72dc563e..f375c89d78a4 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c @@ -223,7 +223,7 @@ static void test_lpm_map(int keysize) n_matches = 0; n_matches_after_delete = 0; n_nodes = 1 << 8; - n_lookups = 1 << 16; + n_lookups = 1 << 9; data = alloca(keysize); memset(data, 0, keysize); @@ -770,16 +770,13 @@ static void test_lpm_multi_thread(void) close(map_fd); } -int main(void) +void test_lpm_trie_map_basic_ops(void) { int i; /* we want predictable, pseudo random tests */ srand(0xf00ba1); - /* Use libbpf 1.0 API mode */ - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - test_lpm_basic(); test_lpm_order(); @@ -792,6 +789,5 @@ int main(void) test_lpm_get_next_key(); test_lpm_multi_thread(); - printf("test_lpm: OK\n"); - return 0; + printf("%s: PASS\n", __func__); } -- 2.51.0 From 04d4ce91b0bed4120e0c5fadc5291cebaa9c2a06 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 6 Dec 2024 19:06:22 +0800 Subject: [PATCH 08/16] selftests/bpf: Add more test cases for LPM trie Add more test cases for LPM trie in test_maps: 1) test_lpm_trie_update_flags It constructs various use cases for BPF_EXIST and BPF_NOEXIST and check whether the return value of update operation is expected. 2) test_lpm_trie_update_full_maps It tests the update operations on a full LPM trie map. Adding new node will fail and overwriting the value of existed node will succeed. 3) test_lpm_trie_iterate_strs and test_lpm_trie_iterate_ints There two test cases test whether the iteration through get_next_key is sorted and expected. These two test cases delete the minimal key after each iteration and check whether next iteration returns the second minimal key. The only difference between these two test cases is the former one saves strings in the LPM trie and the latter saves integers. Without the fix of get_next_key, these two cases will fail as shown below: test_lpm_trie_iterate_strs(1091):FAIL:iterate #2 got abc exp abS test_lpm_trie_iterate_ints(1142):FAIL:iterate #1 got 0x2 exp 0x1 Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20241206110622.1161752-10-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- .../bpf/map_tests/lpm_trie_map_basic_ops.c | 395 ++++++++++++++++++ 1 file changed, 395 insertions(+) diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c index f375c89d78a4..d32e4edac930 100644 --- a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c +++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c @@ -20,10 +20,12 @@ #include #include #include +#include #include #include #include +#include #include "bpf_util.h" @@ -33,6 +35,22 @@ struct tlpm_node { uint8_t key[]; }; +struct lpm_trie_bytes_key { + union { + struct bpf_lpm_trie_key_hdr hdr; + __u32 prefixlen; + }; + unsigned char data[8]; +}; + +struct lpm_trie_int_key { + union { + struct bpf_lpm_trie_key_hdr hdr; + __u32 prefixlen; + }; + unsigned int data; +}; + static struct tlpm_node *tlpm_match(struct tlpm_node *list, const uint8_t *key, size_t n_bits); @@ -770,6 +788,378 @@ static void test_lpm_multi_thread(void) close(map_fd); } +static int lpm_trie_create(unsigned int key_size, unsigned int value_size, unsigned int max_entries) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int fd; + + opts.map_flags = BPF_F_NO_PREALLOC; + fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie", key_size, value_size, max_entries, + &opts); + CHECK(fd < 0, "bpf_map_create", "error %d\n", errno); + + return fd; +} + +static void test_lpm_trie_update_flags(void) +{ + struct lpm_trie_int_key key; + unsigned int value, got; + int fd, err; + + fd = lpm_trie_create(sizeof(key), sizeof(value), 3); + + /* invalid flags (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 0; + err = bpf_map_update_elem(fd, &key, &value, BPF_F_LOCK); + CHECK(err != -EINVAL, "invalid update flag", "error %d\n", err); + + /* invalid flags (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 0; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST | BPF_EXIST); + CHECK(err != -EINVAL, "invalid update flag", "error %d\n", err); + + /* overwrite an empty qp-trie (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err != -ENOENT, "overwrite empty qp-trie", "error %d\n", err); + + /* add a new node */ + key.prefixlen = 16; + key.data = 0; + value = 1; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add the same node as new node (Error) */ + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err != -EEXIST, "add new elem again", "error %d\n", err); + + /* overwrite the existed node */ + value = 4; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* overwrite the node */ + value = 1; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err, "update elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* overwrite a non-existent node which is the prefix of the first + * node (Error). + */ + key.prefixlen = 8; + key.data = 0; + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err != -ENOENT, "overwrite nonexistent elem", "error %d\n", err); + + /* add a new node which is the prefix of the first node */ + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup key", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add another new node which will be the sibling of the first node */ + key.prefixlen = 9; + key.data = htobe32(1 << 23); + value = 5; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup key", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* overwrite the third node */ + value = 3; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup key", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* delete the second node to make it an intermediate node */ + key.prefixlen = 8; + key.data = 0; + err = bpf_map_delete_elem(fd, &key); + CHECK(err, "del elem", "error %d\n", err); + + /* overwrite the intermediate node (Error) */ + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err != -ENOENT, "overwrite nonexistent elem", "error %d\n", err); + + close(fd); +} + +static void test_lpm_trie_update_full_map(void) +{ + struct lpm_trie_int_key key; + int value, got; + int fd, err; + + fd = lpm_trie_create(sizeof(key), sizeof(value), 3); + + /* add a new node */ + key.prefixlen = 16; + key.data = 0; + value = 0; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add new node */ + key.prefixlen = 8; + key.data = 0; + value = 1; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add new node */ + key.prefixlen = 9; + key.data = htobe32(1 << 23); + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* try to add more node (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 3; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err != -ENOSPC, "add to full trie", "error %d\n", err); + + /* update the value of an existed node with BPF_EXIST */ + key.prefixlen = 16; + key.data = 0; + value = 4; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* update the value of an existed node with BPF_ANY */ + key.prefixlen = 9; + key.data = htobe32(1 << 23); + value = 5; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + close(fd); +} + +static int cmp_str(const void *a, const void *b) +{ + const char *str_a = *(const char **)a, *str_b = *(const char **)b; + + return strcmp(str_a, str_b); +} + +/* Save strings in LPM trie. The trailing '\0' for each string will be + * accounted in the prefixlen. The strings returned during the iteration + * should be sorted as expected. + */ +static void test_lpm_trie_iterate_strs(void) +{ + static const char * const keys[] = { + "ab", "abO", "abc", "abo", "abS", "abcd", + }; + const char *sorted_keys[ARRAY_SIZE(keys)]; + struct lpm_trie_bytes_key key, next_key; + unsigned int value, got, i, j, len; + struct lpm_trie_bytes_key *cur; + int fd, err; + + fd = lpm_trie_create(sizeof(key), sizeof(value), ARRAY_SIZE(keys)); + + for (i = 0; i < ARRAY_SIZE(keys); i++) { + unsigned int flags; + + /* add i-th element */ + flags = i % 2 ? BPF_NOEXIST : 0; + len = strlen(keys[i]); + /* include the trailing '\0' */ + key.prefixlen = (len + 1) * 8; + memset(key.data, 0, sizeof(key.data)); + memcpy(key.data, keys[i], len); + value = i + 100; + err = bpf_map_update_elem(fd, &key, &value, flags); + CHECK(err, "add elem", "#%u error %d\n", i, err); + + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "#%u error %d\n", i, err); + CHECK(got != value, "lookup elem", "#%u expect %u got %u\n", i, value, got); + + /* re-add i-th element (Error) */ + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err != -EEXIST, "re-add elem", "#%u error %d\n", i, err); + + /* Overwrite i-th element */ + flags = i % 2 ? 0 : BPF_EXIST; + value = i; + err = bpf_map_update_elem(fd, &key, &value, flags); + CHECK(err, "update elem", "error %d\n", err); + + /* Lookup #[0~i] elements */ + for (j = 0; j <= i; j++) { + len = strlen(keys[j]); + key.prefixlen = (len + 1) * 8; + memset(key.data, 0, sizeof(key.data)); + memcpy(key.data, keys[j], len); + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "#%u/%u error %d\n", i, j, err); + CHECK(got != j, "lookup elem", "#%u/%u expect %u got %u\n", + i, j, value, got); + } + } + + /* Add element to a full qp-trie (Error) */ + key.prefixlen = sizeof(key.data) * 8; + memset(key.data, 0, sizeof(key.data)); + value = 0; + err = bpf_map_update_elem(fd, &key, &value, 0); + CHECK(err != -ENOSPC, "add to full qp-trie", "error %d\n", err); + + /* Iterate sorted elements: no deletion */ + memcpy(sorted_keys, keys, sizeof(keys)); + qsort(sorted_keys, ARRAY_SIZE(sorted_keys), sizeof(sorted_keys[0]), cmp_str); + cur = NULL; + for (i = 0; i < ARRAY_SIZE(sorted_keys); i++) { + len = strlen(sorted_keys[i]); + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err, "iterate", "#%u error %d\n", i, err); + CHECK(next_key.prefixlen != (len + 1) * 8, "iterate", + "#%u invalid len %u expect %u\n", + i, next_key.prefixlen, (len + 1) * 8); + CHECK(memcmp(sorted_keys[i], next_key.data, len + 1), "iterate", + "#%u got %.*s exp %.*s\n", i, len, next_key.data, len, sorted_keys[i]); + + cur = &next_key; + } + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err != -ENOENT, "more element", "error %d\n", err); + + /* Iterate sorted elements: delete the found key after each iteration */ + cur = NULL; + for (i = 0; i < ARRAY_SIZE(sorted_keys); i++) { + len = strlen(sorted_keys[i]); + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err, "iterate", "#%u error %d\n", i, err); + CHECK(next_key.prefixlen != (len + 1) * 8, "iterate", + "#%u invalid len %u expect %u\n", + i, next_key.prefixlen, (len + 1) * 8); + CHECK(memcmp(sorted_keys[i], next_key.data, len + 1), "iterate", + "#%u got %.*s exp %.*s\n", i, len, next_key.data, len, sorted_keys[i]); + + cur = &next_key; + + err = bpf_map_delete_elem(fd, cur); + CHECK(err, "delete", "#%u error %d\n", i, err); + } + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err != -ENOENT, "non-empty qp-trie", "error %d\n", err); + + close(fd); +} + +/* Use the fixed prefixlen (32) and save integers in LPM trie. The iteration of + * LPM trie will return these integers in big-endian order, therefore, convert + * these integers to big-endian before update. After each iteration, delete the + * found key (the smallest integer) and expect the next iteration will return + * the second smallest number. + */ +static void test_lpm_trie_iterate_ints(void) +{ + struct lpm_trie_int_key key, next_key; + unsigned int i, max_entries; + struct lpm_trie_int_key *cur; + unsigned int *data_set; + int fd, err; + bool value; + + max_entries = 4096; + data_set = calloc(max_entries, sizeof(*data_set)); + CHECK(!data_set, "malloc", "no mem\n"); + for (i = 0; i < max_entries; i++) + data_set[i] = i; + + fd = lpm_trie_create(sizeof(key), sizeof(value), max_entries); + value = true; + for (i = 0; i < max_entries; i++) { + key.prefixlen = 32; + key.data = htobe32(data_set[i]); + + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add elem", "#%u error %d\n", i, err); + } + + cur = NULL; + for (i = 0; i < max_entries; i++) { + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err, "iterate", "#%u error %d\n", i, err); + CHECK(next_key.prefixlen != 32, "iterate", "#%u invalid len %u\n", + i, next_key.prefixlen); + CHECK(be32toh(next_key.data) != data_set[i], "iterate", "#%u got 0x%x exp 0x%x\n", + i, be32toh(next_key.data), data_set[i]); + cur = &next_key; + + /* + * Delete the minimal key, the next call of bpf_get_next_key() + * will return the second minimal key. + */ + err = bpf_map_delete_elem(fd, &next_key); + CHECK(err, "del elem", "#%u elem error %d\n", i, err); + } + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err != -ENOENT, "more element", "error %d\n", err); + + err = bpf_map_get_next_key(fd, NULL, &next_key); + CHECK(err != -ENOENT, "no-empty qp-trie", "error %d\n", err); + + free(data_set); + + close(fd); +} + void test_lpm_trie_map_basic_ops(void) { int i; @@ -789,5 +1179,10 @@ void test_lpm_trie_map_basic_ops(void) test_lpm_get_next_key(); test_lpm_multi_thread(); + test_lpm_trie_update_flags(); + test_lpm_trie_update_full_map(); + test_lpm_trie_iterate_strs(); + test_lpm_trie_iterate_ints(); + printf("%s: PASS\n", __func__); } -- 2.51.0 From 492077668fb453b8b16c842fcf3fafc2ebc190e9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 6 Dec 2024 08:20:06 -0800 Subject: [PATCH 09/16] x86/CPU/AMD: WARN when setting EFER.AUTOIBRS if and only if the WRMSR fails When ensuring EFER.AUTOIBRS is set, WARN only on a negative return code from msr_set_bit(), as '1' is used to indicate the WRMSR was successful ('0' indicates the MSR bit was already set). Fixes: 8cc68c9c9e92 ("x86/CPU/AMD: Make sure EFER[AIBRSE] is set") Reported-by: Nathan Chancellor Signed-off-by: Sean Christopherson Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/Z1MkNofJjt7Oq0G6@google.com Closes: https://lore.kernel.org/all/20241205220604.GA2054199@thelio-3990X --- arch/x86/kernel/cpu/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index d8408aafeed9..79d2e17f6582 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1065,7 +1065,7 @@ static void init_amd(struct cpuinfo_x86 *c) */ if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && cpu_has(c, X86_FEATURE_AUTOIBRS)) - WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS)); + WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS) < 0); /* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */ clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); -- 2.51.0 From 7912405643a14b527cd4a4f33c1d4392da900888 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 1 Dec 2024 12:17:30 +0100 Subject: [PATCH 10/16] modpost: Add .irqentry.text to OTHER_SECTIONS The compiler can fully inline the actual handler function of an interrupt entry into the .irqentry.text entry point. If such a function contains an access which has an exception table entry, modpost complains about a section mismatch: WARNING: vmlinux.o(__ex_table+0x447c): Section mismatch in reference ... The relocation at __ex_table+0x447c references section ".irqentry.text" which is not in the list of authorized sections. Add .irqentry.text to OTHER_SECTIONS to cure the issue. Reported-by: Sergey Senozhatsky Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org # needed for linux-5.4-y Link: https://lore.kernel.org/all/20241128111844.GE10431@google.com/ Signed-off-by: Masahiro Yamada --- scripts/mod/modpost.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 0584cbcdbd2d..fb787a5715f5 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -772,7 +772,7 @@ static void check_section(const char *modname, struct elf_info *elf, ".ltext", ".ltext.*" #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \ ".fixup", ".entry.text", ".exception.text", \ - ".coldtext", ".softirqentry.text" + ".coldtext", ".softirqentry.text", ".irqentry.text" #define ALL_TEXT_SECTIONS ".init.text", ".exit.text", \ TEXT_SECTIONS, OTHER_TEXT_SECTIONS -- 2.51.0 From d8d326d64f6702caab01ea0cd48f6c0054f3d1b4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 8 Dec 2024 16:56:45 +0900 Subject: [PATCH 11/16] kbuild: deb-pkg: fix build error with O= Since commit 13b25489b6f8 ("kbuild: change working directory to external module directory with M="), the Debian package build fails if a relative path is specified with the O= option. $ make O=build bindeb-pkg [ snip ] dpkg-deb: building package 'linux-image-6.13.0-rc1' in '../linux-image-6.13.0-rc1_6.13.0-rc1-6_amd64.deb'. Rebuilding host programs with x86_64-linux-gnu-gcc... make[6]: Entering directory '/home/masahiro/linux/build' /home/masahiro/linux/Makefile:190: *** specified kernel directory "build" does not exist. Stop. This occurs because the sub_make_done flag is cleared, even though the working directory is already in the output directory. Passing KBUILD_OUTPUT=. resolves the issue. Fixes: 13b25489b6f8 ("kbuild: change working directory to external module directory with M=") Reported-by: Charlie Jenkins Closes: https://lore.kernel.org/all/Z1DnP-GJcfseyrM3@ghost/ Tested-by: Charlie Jenkins Reviewed-by: Charlie Jenkins Signed-off-by: Masahiro Yamada --- scripts/package/install-extmod-build | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index 64d958ee45f3..d3c5b104c063 100755 --- a/scripts/package/install-extmod-build +++ b/scripts/package/install-extmod-build @@ -69,7 +69,7 @@ if [ "${CC}" != "${HOSTCC}" ]; then # # Use the single-target build to avoid the modpost invocation, which # would overwrite Module.symvers. - "${MAKE}" HOSTCC="${CC}" KBUILD_EXTMOD="${destdir}" scripts/ + "${MAKE}" HOSTCC="${CC}" KBUILD_OUTPUT=. KBUILD_EXTMOD="${destdir}" scripts/ cat <<-'EOF' > "${destdir}/scripts/Kbuild" subdir-y := basic @@ -78,7 +78,7 @@ if [ "${CC}" != "${HOSTCC}" ]; then EOF # Run once again to rebuild scripts/basic/ and scripts/mod/modpost. - "${MAKE}" HOSTCC="${CC}" KBUILD_EXTMOD="${destdir}" scripts/ + "${MAKE}" HOSTCC="${CC}" KBUILD_OUTPUT=. KBUILD_EXTMOD="${destdir}" scripts/ rm -f "${destdir}/Kbuild" "${destdir}/scripts/Kbuild" fi -- 2.51.0 From fac04efc5c793dccbd07e2d59af9f90b7fc0dca4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 8 Dec 2024 14:03:39 -0800 Subject: [PATCH 12/16] Linux 6.13-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 93ab62cef244..64c594bd7ad0 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Baby Opossum Posse # *DOCUMENTATION* -- 2.51.0 From 1201f226c863b7da739f7420ddba818cedf372fc Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 10 Dec 2024 17:32:58 -0800 Subject: [PATCH 13/16] KVM: x86: Cache CPUID.0xD XSTATE offsets+sizes during module init Snapshot the output of CPUID.0xD.[1..n] during kvm.ko initiliaization to avoid the overead of CPUID during runtime. The offset, size, and metadata for CPUID.0xD.[1..n] sub-leaves does not depend on XCR0 or XSS values, i.e. is constant for a given CPU, and thus can be cached during module load. On Intel's Emerald Rapids, CPUID is *wildly* expensive, to the point where recomputing XSAVE offsets and sizes results in a 4x increase in latency of nested VM-Enter and VM-Exit (nested transitions can trigger xstate_required_size() multiple times per transition), relative to using cached values. The issue is easily visible by running `perf top` while triggering nested transitions: kvm_update_cpuid_runtime() shows up at a whopping 50%. As measured via RDTSC from L2 (using KVM-Unit-Test's CPUID VM-Exit test and a slightly modified L1 KVM to handle CPUID in the fastpath), a nested roundtrip to emulate CPUID on Skylake (SKX), Icelake (ICX), and Emerald Rapids (EMR) takes: SKX 11650 ICX 22350 EMR 28850 Using cached values, the latency drops to: SKX 6850 ICX 9000 EMR 7900 The underlying issue is that CPUID itself is slow on ICX, and comically slow on EMR. The problem is exacerbated on CPUs which support XSAVES and/or XSAVEC, as KVM invokes xstate_required_size() twice on each runtime CPUID update, and because there are more supported XSAVE features (CPUID for supported XSAVE feature sub-leafs is significantly slower). SKX: CPUID.0xD.2 = 348 cycles CPUID.0xD.3 = 400 cycles CPUID.0xD.4 = 276 cycles CPUID.0xD.5 = 236 cycles EMR: CPUID.0xD.2 = 1138 cycles CPUID.0xD.3 = 1362 cycles CPUID.0xD.4 = 1068 cycles CPUID.0xD.5 = 910 cycles CPUID.0xD.6 = 914 cycles CPUID.0xD.7 = 1350 cycles CPUID.0xD.8 = 734 cycles CPUID.0xD.9 = 766 cycles CPUID.0xD.10 = 732 cycles CPUID.0xD.11 = 718 cycles CPUID.0xD.12 = 734 cycles CPUID.0xD.13 = 1700 cycles CPUID.0xD.14 = 1126 cycles CPUID.0xD.15 = 898 cycles CPUID.0xD.16 = 716 cycles CPUID.0xD.17 = 748 cycles CPUID.0xD.18 = 776 cycles Note, updating runtime CPUID information multiple times per nested transition is itself a flaw, especially since CPUID is a mandotory intercept on both Intel and AMD. E.g. KVM doesn't need to ensure emulated CPUID state is up-to-date while running L2. That flaw will be fixed in a future patch, as deferring runtime CPUID updates is more subtle than it appears at first glance, the benefits aren't super critical to have once the XSAVE issue is resolved, and caching CPUID output is desirable even if KVM's updates are deferred. Cc: Jim Mattson Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-ID: <20241211013302.1347853-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 31 ++++++++++++++++++++++++++----- arch/x86/kvm/cpuid.h | 1 + arch/x86/kvm/x86.c | 2 ++ 3 files changed, 29 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 097bdc022d0f..ae0b438a2c99 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -36,6 +36,26 @@ u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly; EXPORT_SYMBOL_GPL(kvm_cpu_caps); +struct cpuid_xstate_sizes { + u32 eax; + u32 ebx; + u32 ecx; +}; + +static struct cpuid_xstate_sizes xstate_sizes[XFEATURE_MAX] __ro_after_init; + +void __init kvm_init_xstate_sizes(void) +{ + u32 ign; + int i; + + for (i = XFEATURE_YMM; i < ARRAY_SIZE(xstate_sizes); i++) { + struct cpuid_xstate_sizes *xs = &xstate_sizes[i]; + + cpuid_count(0xD, i, &xs->eax, &xs->ebx, &xs->ecx, &ign); + } +} + u32 xstate_required_size(u64 xstate_bv, bool compacted) { int feature_bit = 0; @@ -44,14 +64,15 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) xstate_bv &= XFEATURE_MASK_EXTEND; while (xstate_bv) { if (xstate_bv & 0x1) { - u32 eax, ebx, ecx, edx, offset; - cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx); + struct cpuid_xstate_sizes *xs = &xstate_sizes[feature_bit]; + u32 offset; + /* ECX[1]: 64B alignment in compacted form */ if (compacted) - offset = (ecx & 0x2) ? ALIGN(ret, 64) : ret; + offset = (xs->ecx & 0x2) ? ALIGN(ret, 64) : ret; else - offset = ebx; - ret = max(ret, offset + eax); + offset = xs->ebx; + ret = max(ret, offset + xs->eax); } xstate_bv >>= 1; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index c8dc66eddefd..f16a7b2c2adc 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -31,6 +31,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only); +void __init kvm_init_xstate_sizes(void); u32 xstate_required_size(u64 xstate_bv, bool compacted); int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2e713480933a..c8160baf3838 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13997,6 +13997,8 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault); static int __init kvm_x86_init(void) { + kvm_init_xstate_sizes(); + kvm_mmu_x86_module_init(); mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible(); return 0; -- 2.51.0 From 915d2f0718a42ee0b334be34cc53664a865a5928 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 27 Nov 2024 16:55:32 -0800 Subject: [PATCH 14/16] KVM: Move KVM_REG_SIZE() definition to common uAPI header Define KVM_REG_SIZE() in the common kvm.h header, and delete the arm64 and RISC-V versions. As evidenced by the surrounding definitions, all aspects of the register size encoding are generic, i.e. RISC-V should have moved arm64's definition to common code instead of copy+pasting. Acked-by: Anup Patel Reviewed-by: Andrew Jones Reviewed-by: Muhammad Usama Anjum Link: https://lore.kernel.org/r/20241128005547.4077116-2-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/arm64/include/uapi/asm/kvm.h | 3 --- arch/riscv/include/uapi/asm/kvm.h | 3 --- include/uapi/linux/kvm.h | 4 ++++ 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 66736ff04011..568bf858f319 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -43,9 +43,6 @@ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #define KVM_DIRTY_LOG_PAGE_OFFSET 64 -#define KVM_REG_SIZE(id) \ - (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) - struct kvm_regs { struct user_pt_regs regs; /* sp = sp_el0 */ diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index 3482c9a73d1b..9f60d6185077 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -211,9 +211,6 @@ struct kvm_riscv_sbi_sta { #define KVM_RISCV_TIMER_STATE_OFF 0 #define KVM_RISCV_TIMER_STATE_ON 1 -#define KVM_REG_SIZE(id) \ - (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) - /* If you need to interpret the index values, here is the key: */ #define KVM_REG_RISCV_TYPE_MASK 0x00000000FF000000 #define KVM_REG_RISCV_TYPE_SHIFT 24 diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 502ea63b5d2e..343de0a51797 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1070,6 +1070,10 @@ struct kvm_dirty_tlb { #define KVM_REG_SIZE_SHIFT 52 #define KVM_REG_SIZE_MASK 0x00f0000000000000ULL + +#define KVM_REG_SIZE(id) \ + (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) + #define KVM_REG_SIZE_U8 0x0000000000000000ULL #define KVM_REG_SIZE_U16 0x0010000000000000ULL #define KVM_REG_SIZE_U32 0x0020000000000000ULL -- 2.51.0 From 09bb926d290789ff35e7fa53045811a8c57356a9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 27 Nov 2024 16:55:33 -0800 Subject: [PATCH 15/16] KVM: selftests: Return a value from vcpu_get_reg() instead of using an out-param Return a uint64_t from vcpu_get_reg() instead of having the caller provide a pointer to storage, as none of the vcpu_get_reg() usage in KVM selftests accesses a register larger than 64 bits, and vcpu_set_reg() only accepts a 64-bit value. If a use case comes along that needs to get a register that is larger than 64 bits, then a utility can be added to assert success and take a void pointer, but until then, forcing an out param yields ugly code and prevents feeding the output of vcpu_get_reg() into vcpu_set_reg(). Reviewed-by: Andrew Jones Acked-by: Claudio Imbrenda Link: https://lore.kernel.org/r/20241128005547.4077116-3-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/aarch64/aarch32_id_regs.c | 10 +-- .../selftests/kvm/aarch64/debug-exceptions.c | 4 +- .../selftests/kvm/aarch64/hypercalls.c | 6 +- .../selftests/kvm/aarch64/no-vgic-v3.c | 2 +- .../testing/selftests/kvm/aarch64/psci_test.c | 8 +-- .../selftests/kvm/aarch64/set_id_regs.c | 22 +++---- .../kvm/aarch64/vpmu_counter_access.c | 19 +++--- .../testing/selftests/kvm/include/kvm_util.h | 6 +- .../selftests/kvm/lib/aarch64/processor.c | 8 +-- .../selftests/kvm/lib/riscv/processor.c | 66 +++++++++---------- .../testing/selftests/kvm/riscv/arch_timer.c | 2 +- .../testing/selftests/kvm/riscv/ebreak_test.c | 2 +- .../selftests/kvm/riscv/sbi_pmu_test.c | 2 +- tools/testing/selftests/kvm/s390x/resets.c | 2 +- tools/testing/selftests/kvm/steal_time.c | 3 +- 15 files changed, 81 insertions(+), 81 deletions(-) diff --git a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c index 8e5bd07a3727..447d61cae4db 100644 --- a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c +++ b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c @@ -97,7 +97,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu) uint64_t reg_id = raz_wi_reg_ids[i]; uint64_t val; - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); /* @@ -106,7 +106,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu) */ vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL); - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); } } @@ -126,14 +126,14 @@ static void test_user_raz_invariant(struct kvm_vcpu *vcpu) uint64_t reg_id = raz_invariant_reg_ids[i]; uint64_t val; - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); r = __vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL); TEST_ASSERT(r < 0 && errno == EINVAL, "unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno); - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); } } @@ -144,7 +144,7 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu) { uint64_t val, el0; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val); return el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY; diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c index ff7a949fc96a..c7fb55c9135b 100644 --- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c @@ -501,7 +501,7 @@ void test_single_step_from_userspace(int test_cnt) TEST_ASSERT(ss_enable, "Unexpected KVM_EXIT_DEBUG"); /* Check if the current pc is expected. */ - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc); + pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); TEST_ASSERT(!test_pc || pc == test_pc, "Unexpected pc 0x%lx (expected 0x%lx)", pc, test_pc); @@ -583,7 +583,7 @@ int main(int argc, char *argv[]) uint64_t aa64dfr0; vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &aa64dfr0); + aa64dfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1)); __TEST_REQUIRE(debug_version(aa64dfr0) >= 6, "Armv8 debug architecture not supported."); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c index 9d192ce0078d..ec54ec7726e9 100644 --- a/tools/testing/selftests/kvm/aarch64/hypercalls.c +++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c @@ -173,7 +173,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu) const struct kvm_fw_reg_info *reg_info = &fw_reg_info[i]; /* First 'read' should be an upper limit of the features supported */ - vcpu_get_reg(vcpu, reg_info->reg, &val); + val = vcpu_get_reg(vcpu, reg_info->reg); TEST_ASSERT(val == FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), "Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx", reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), val); @@ -184,7 +184,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu) "Failed to clear all the features of reg: 0x%lx; ret: %d", reg_info->reg, errno); - vcpu_get_reg(vcpu, reg_info->reg, &val); + val = vcpu_get_reg(vcpu, reg_info->reg); TEST_ASSERT(val == 0, "Expected all the features to be cleared for reg: 0x%lx", reg_info->reg); @@ -214,7 +214,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu) * Before starting the VM, the test clears all the bits. * Check if that's still the case. */ - vcpu_get_reg(vcpu, reg_info->reg, &val); + val = vcpu_get_reg(vcpu, reg_info->reg); TEST_ASSERT(val == 0, "Expected all the features to be cleared for reg: 0x%lx", reg_info->reg); diff --git a/tools/testing/selftests/kvm/aarch64/no-vgic-v3.c b/tools/testing/selftests/kvm/aarch64/no-vgic-v3.c index 58304bbc2036..ebd70430c89d 100644 --- a/tools/testing/selftests/kvm/aarch64/no-vgic-v3.c +++ b/tools/testing/selftests/kvm/aarch64/no-vgic-v3.c @@ -164,7 +164,7 @@ int main(int argc, char *argv[]) uint64_t pfr0; vm = vm_create_with_one_vcpu(&vcpu, NULL); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &pfr0); + pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); __TEST_REQUIRE(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), pfr0), "GICv3 not supported."); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c index eaa7655fefc1..ab491ee9e5f7 100644 --- a/tools/testing/selftests/kvm/aarch64/psci_test.c +++ b/tools/testing/selftests/kvm/aarch64/psci_test.c @@ -111,8 +111,8 @@ static void assert_vcpu_reset(struct kvm_vcpu *vcpu) { uint64_t obs_pc, obs_x0; - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &obs_pc); - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.regs[0]), &obs_x0); + obs_pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); + obs_x0 = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.regs[0])); TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR, "unexpected target cpu pc: %lx (expected: %lx)", @@ -152,7 +152,7 @@ static void host_test_cpu_on(void) */ vcpu_power_off(target); - vcpu_get_reg(target, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr); + target_mpidr = vcpu_get_reg(target, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1)); vcpu_args_set(source, 1, target_mpidr & MPIDR_HWID_BITMASK); enter_guest(source); @@ -244,7 +244,7 @@ static void host_test_system_off2(void) setup_vm(guest_test_system_off2, &source, &target); - vcpu_get_reg(target, KVM_REG_ARM_PSCI_VERSION, &psci_version); + psci_version = vcpu_get_reg(target, KVM_REG_ARM_PSCI_VERSION); TEST_ASSERT(psci_version >= PSCI_VERSION(1, 3), "Unexpected PSCI version %lu.%lu", diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/aarch64/set_id_regs.c index a79b7f18452d..bc6cf50e5135 100644 --- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c +++ b/tools/testing/selftests/kvm/aarch64/set_id_regs.c @@ -346,7 +346,7 @@ static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg, uint64_t mask = ftr_bits->mask; uint64_t val, new_val, ftr; - vcpu_get_reg(vcpu, reg, &val); + val = vcpu_get_reg(vcpu, reg); ftr = (val & mask) >> shift; ftr = get_safe_value(ftr_bits, ftr); @@ -356,7 +356,7 @@ static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg, val |= ftr; vcpu_set_reg(vcpu, reg, val); - vcpu_get_reg(vcpu, reg, &new_val); + new_val = vcpu_get_reg(vcpu, reg); TEST_ASSERT_EQ(new_val, val); return new_val; @@ -370,7 +370,7 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg, uint64_t val, old_val, ftr; int r; - vcpu_get_reg(vcpu, reg, &val); + val = vcpu_get_reg(vcpu, reg); ftr = (val & mask) >> shift; ftr = get_invalid_value(ftr_bits, ftr); @@ -384,7 +384,7 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg, TEST_ASSERT(r < 0 && errno == EINVAL, "Unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno); - vcpu_get_reg(vcpu, reg, &val); + val = vcpu_get_reg(vcpu, reg); TEST_ASSERT_EQ(val, old_val); } @@ -471,7 +471,7 @@ static void test_user_set_mpam_reg(struct kvm_vcpu *vcpu) } /* Get the id register value */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); /* Try to set MPAM=0. This should always be possible. */ val &= ~ID_AA64PFR0_EL1_MPAM_MASK; @@ -508,7 +508,7 @@ static void test_user_set_mpam_reg(struct kvm_vcpu *vcpu) } /* Get the id register value */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); /* Try to set MPAM_frac=0. This should always be possible. */ val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK; @@ -576,7 +576,7 @@ static void test_clidr(struct kvm_vcpu *vcpu) uint64_t clidr; int level; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1), &clidr); + clidr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1)); /* find the first empty level in the cache hierarchy */ for (level = 1; level < 7; level++) { @@ -601,7 +601,7 @@ static void test_ctr(struct kvm_vcpu *vcpu) { u64 ctr; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CTR_EL0), &ctr); + ctr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CTR_EL0)); ctr &= ~CTR_EL0_DIC_MASK; if (ctr & CTR_EL0_IminLine_MASK) ctr--; @@ -617,7 +617,7 @@ static void test_vcpu_ftr_id_regs(struct kvm_vcpu *vcpu) test_clidr(vcpu); test_ctr(vcpu); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1)); val++; vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), val); @@ -630,7 +630,7 @@ static void test_assert_id_reg_unchanged(struct kvm_vcpu *vcpu, uint32_t encodin size_t idx = encoding_to_range_idx(encoding); uint64_t observed; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding), &observed); + observed = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding)); TEST_ASSERT_EQ(test_reg_vals[idx], observed); } @@ -665,7 +665,7 @@ int main(void) vm = vm_create_with_one_vcpu(&vcpu, guest_code); /* Check for AARCH64 only system */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val); aarch64_only = (el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY); diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c index f9c0c86d7e85..f16b3b27e32e 100644 --- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c +++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c @@ -440,8 +440,7 @@ static void create_vpmu_vm(void *guest_code) "Failed to create vgic-v3, skipping"); /* Make sure that PMUv3 support is indicated in the ID register */ - vcpu_get_reg(vpmu_vm.vcpu, - KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &dfr0); + dfr0 = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1)); pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0); TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF && pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP, @@ -484,7 +483,7 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail) create_vpmu_vm(guest_code); vcpu = vpmu_vm.vcpu; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr_orig); + pmcr_orig = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); pmcr = pmcr_orig; /* @@ -493,7 +492,7 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail) */ set_pmcr_n(&pmcr, pmcr_n); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), pmcr); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr); + pmcr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); if (expect_fail) TEST_ASSERT(pmcr_orig == pmcr, @@ -521,7 +520,7 @@ static void run_access_test(uint64_t pmcr_n) vcpu = vpmu_vm.vcpu; /* Save the initial sp to restore them later to run the guest again */ - vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1), &sp); + sp = vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1)); run_vcpu(vcpu, pmcr_n); @@ -572,12 +571,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n) * Test if the 'set' and 'clr' variants of the registers * are initialized based on the number of valid counters. */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(set_reg_id), reg_val); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(clr_reg_id), reg_val); @@ -589,12 +588,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n) */ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), max_counters_mask); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(set_reg_id), reg_val); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(clr_reg_id), reg_val); @@ -625,7 +624,7 @@ static uint64_t get_pmcr_n_limit(void) uint64_t pmcr; create_vpmu_vm(guest_code); - vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr); + pmcr = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); destroy_vpmu_vm(); return get_pmcr_n(pmcr); } diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index bc7c242480d6..287a3ec06df4 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -702,11 +702,13 @@ static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t va return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); } -static inline void vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +static inline uint64_t vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id) { - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; + uint64_t val; + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); + return val; } static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) { diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 698e34f39241..7ba3aa3755f3 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -281,8 +281,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) */ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1); + sctlr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1)); + tcr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1)); /* Configure base granule size */ switch (vm->mode) { @@ -360,8 +360,8 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) { uint64_t pstate, pc; - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate), &pstate); - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc); + pstate = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate)); + pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); fprintf(stream, "%*spstate: 0x%.16lx pc: 0x%.16lx\n", indent, "", pstate, pc); diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index 6ae47b3d6b25..dd663bcf0cc0 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -221,39 +221,39 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) { struct kvm_riscv_core core; - vcpu_get_reg(vcpu, RISCV_CORE_REG(mode), &core.mode); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &core.regs.pc); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.ra), &core.regs.ra); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.sp), &core.regs.sp); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.gp), &core.regs.gp); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.tp), &core.regs.tp); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t0), &core.regs.t0); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t1), &core.regs.t1); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t2), &core.regs.t2); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s0), &core.regs.s0); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s1), &core.regs.s1); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a0), &core.regs.a0); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a1), &core.regs.a1); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a2), &core.regs.a2); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a3), &core.regs.a3); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a4), &core.regs.a4); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a5), &core.regs.a5); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a6), &core.regs.a6); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a7), &core.regs.a7); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s2), &core.regs.s2); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s3), &core.regs.s3); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s4), &core.regs.s4); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s5), &core.regs.s5); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s6), &core.regs.s6); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s7), &core.regs.s7); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s8), &core.regs.s8); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s9), &core.regs.s9); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s10), &core.regs.s10); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s11), &core.regs.s11); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t3), &core.regs.t3); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t4), &core.regs.t4); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t5), &core.regs.t5); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t6), &core.regs.t6); + core.mode = vcpu_get_reg(vcpu, RISCV_CORE_REG(mode)); + core.regs.pc = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc)); + core.regs.ra = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.ra)); + core.regs.sp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.sp)); + core.regs.gp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.gp)); + core.regs.tp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.tp)); + core.regs.t0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t0)); + core.regs.t1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t1)); + core.regs.t2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t2)); + core.regs.s0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s0)); + core.regs.s1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s1)); + core.regs.a0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a0)); + core.regs.a1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a1)); + core.regs.a2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a2)); + core.regs.a3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a3)); + core.regs.a4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a4)); + core.regs.a5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a5)); + core.regs.a6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a6)); + core.regs.a7 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a7)); + core.regs.s2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s2)); + core.regs.s3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s3)); + core.regs.s4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s4)); + core.regs.s5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s5)); + core.regs.s6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s6)); + core.regs.s7 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s7)); + core.regs.s8 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s8)); + core.regs.s9 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s9)); + core.regs.s10 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s10)); + core.regs.s11 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s11)); + core.regs.t3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t3)); + core.regs.t4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t4)); + core.regs.t5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t5)); + core.regs.t6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t6)); fprintf(stream, " MODE: 0x%lx\n", core.mode); diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c index 2c792228ac0b..9e370800a6a2 100644 --- a/tools/testing/selftests/kvm/riscv/arch_timer.c +++ b/tools/testing/selftests/kvm/riscv/arch_timer.c @@ -93,7 +93,7 @@ struct kvm_vm *test_vm_create(void) vcpu_init_vector_tables(vcpus[i]); /* Initialize guest timer frequency. */ - vcpu_get_reg(vcpus[0], RISCV_TIMER_REG(frequency), &timer_freq); + timer_freq = vcpu_get_reg(vcpus[0], RISCV_TIMER_REG(frequency)); sync_global_to_guest(vm, timer_freq); pr_debug("timer_freq: %lu\n", timer_freq); diff --git a/tools/testing/selftests/kvm/riscv/ebreak_test.c b/tools/testing/selftests/kvm/riscv/ebreak_test.c index 0e0712854953..cfed6c727bfc 100644 --- a/tools/testing/selftests/kvm/riscv/ebreak_test.c +++ b/tools/testing/selftests/kvm/riscv/ebreak_test.c @@ -60,7 +60,7 @@ int main(void) TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &pc); + pc = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc)); TEST_ASSERT_EQ(pc, LABEL_ADDRESS(sw_bp_1)); /* skip sw_bp_1 */ diff --git a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c index f299cbfd23ca..f45c0ecc902d 100644 --- a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c +++ b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c @@ -608,7 +608,7 @@ static void test_vm_events_overflow(void *guest_code) vcpu_init_vector_tables(vcpu); /* Initialize guest timer frequency. */ - vcpu_get_reg(vcpu, RISCV_TIMER_REG(frequency), &timer_freq); + timer_freq = vcpu_get_reg(vcpu, RISCV_TIMER_REG(frequency)); sync_global_to_guest(vm, timer_freq); run_vcpu(vcpu); diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c index 357943f2bea8..b58f75b381e5 100644 --- a/tools/testing/selftests/kvm/s390x/resets.c +++ b/tools/testing/selftests/kvm/s390x/resets.c @@ -61,7 +61,7 @@ static void test_one_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t value) { uint64_t eval_reg; - vcpu_get_reg(vcpu, id, &eval_reg); + eval_reg = vcpu_get_reg(vcpu, id); TEST_ASSERT(eval_reg == value, "value == 0x%lx", value); } diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index a8d3afa0b86b..cce2520af720 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -269,9 +269,8 @@ static void guest_code(int cpu) static bool is_steal_time_supported(struct kvm_vcpu *vcpu) { uint64_t id = RISCV_SBI_EXT_REG(KVM_RISCV_SBI_EXT_STA); - unsigned long enabled; + unsigned long enabled = vcpu_get_reg(vcpu, id); - vcpu_get_reg(vcpu, id, &enabled); TEST_ASSERT(enabled == 0 || enabled == 1, "Expected boolean result"); return enabled; -- 2.51.0 From fe85ce31b2891611a2e4d788872be815cea85a4b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 27 Nov 2024 16:55:34 -0800 Subject: [PATCH 16/16] KVM: selftests: Assert that vcpu_{g,s}et_reg() won't truncate Assert that the register being read/written by vcpu_{g,s}et_reg() is no larger than a uint64_t, i.e. that a selftest isn't unintentionally truncating the value being read/written. Ideally, the assert would be done at compile-time, but that would limit the checks to hardcoded accesses and/or require fancier compile-time assertion infrastructure to filter out dynamic usage. Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20241128005547.4077116-4-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/include/kvm_util.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 287a3ec06df4..4c4e5a847f67 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -707,6 +707,8 @@ static inline uint64_t vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id) uint64_t val; struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id); + vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); return val; } @@ -714,6 +716,8 @@ static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val { struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id); + vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); } -- 2.51.0