summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/x86/boot/cpuflags.c13
-rw-r--r--arch/x86/boot/startup/sev-shared.c7
-rw-r--r--arch/x86/coco/sev/core.c21
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/sev.h19
-rw-r--r--arch/x86/kernel/cpu/scattered.c1
-rw-r--r--fs/btrfs/extent_io.c11
-rw-r--r--fs/btrfs/inode.c8
-rw-r--r--fs/btrfs/qgroup.c3
-rw-r--r--fs/btrfs/relocation.c19
-rw-r--r--fs/btrfs/tree-log.c19
-rw-r--r--fs/btrfs/zoned.c2
-rw-r--r--fs/nfsd/localio.c5
-rw-r--r--fs/nfsd/vfs.c10
-rw-r--r--net/sunrpc/svcsock.c43
15 files changed, 148 insertions, 34 deletions
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index 916bac09b464..63e037e94e4c 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -106,5 +106,18 @@ void get_cpuflags(void)
cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6],
&cpu.flags[1]);
}
+
+ if (max_amd_level >= 0x8000001f) {
+ u32 ebx;
+
+ /*
+ * The X86_FEATURE_COHERENCY_SFW_NO feature bit is in
+ * the virtualization flags entry (word 8) and set by
+ * scattered.c, so the bit needs to be explicitly set.
+ */
+ cpuid(0x8000001f, &ignored, &ebx, &ignored, &ignored);
+ if (ebx & BIT(31))
+ set_bit(X86_FEATURE_COHERENCY_SFW_NO, cpu.flags);
+ }
}
}
diff --git a/arch/x86/boot/startup/sev-shared.c b/arch/x86/boot/startup/sev-shared.c
index 7a706db87b93..ac7dfd21ddd4 100644
--- a/arch/x86/boot/startup/sev-shared.c
+++ b/arch/x86/boot/startup/sev-shared.c
@@ -810,6 +810,13 @@ static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr,
if (ret)
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
}
+
+ /*
+ * If validating memory (making it private) and affected by the
+ * cache-coherency vulnerability, perform the cache eviction mitigation.
+ */
+ if (validate && !has_cpuflag(X86_FEATURE_COHERENCY_SFW_NO))
+ sev_evict_cache((void *)vaddr, 1);
}
/*
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index fc59ce78c477..400a6ab75d45 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -358,10 +358,31 @@ static void svsm_pval_pages(struct snp_psc_desc *desc)
static void pvalidate_pages(struct snp_psc_desc *desc)
{
+ struct psc_entry *e;
+ unsigned int i;
+
if (snp_vmpl)
svsm_pval_pages(desc);
else
pval_pages(desc);
+
+ /*
+ * If not affected by the cache-coherency vulnerability there is no need
+ * to perform the cache eviction mitigation.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_COHERENCY_SFW_NO))
+ return;
+
+ for (i = 0; i <= desc->hdr.end_entry; i++) {
+ e = &desc->entries[i];
+
+ /*
+ * If validating memory (making it private) perform the cache
+ * eviction mitigation.
+ */
+ if (e->operation == SNP_PAGE_STATE_PRIVATE)
+ sev_evict_cache(pfn_to_kaddr(e->gfn), e->pagesize ? 512 : 1);
+ }
}
static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 602957dd2609..06fc0479a23f 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -218,6 +218,7 @@
#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */
#define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */
#define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */
+#define X86_FEATURE_COHERENCY_SFW_NO ( 8*32+ 4) /* SNP cache coherency software work around not needed */
#define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */
#define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 89075ff19afa..02236962fdb1 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -619,6 +619,24 @@ int rmp_make_shared(u64 pfn, enum pg_level level);
void snp_leak_pages(u64 pfn, unsigned int npages);
void kdump_sev_callback(void);
void snp_fixup_e820_tables(void);
+
+static inline void sev_evict_cache(void *va, int npages)
+{
+ volatile u8 val __always_unused;
+ u8 *bytes = va;
+ int page_idx;
+
+ /*
+ * For SEV guests, a read from the first/last cache-lines of a 4K page
+ * using the guest key is sufficient to cause a flush of all cache-lines
+ * associated with that 4K page without incurring all the overhead of a
+ * full CLFLUSH sequence.
+ */
+ for (page_idx = 0; page_idx < npages; page_idx++) {
+ val = bytes[page_idx * PAGE_SIZE];
+ val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1];
+ }
+}
#else
static inline bool snp_probe_rmptable_info(void) { return false; }
static inline int snp_rmptable_init(void) { return -ENOSYS; }
@@ -634,6 +652,7 @@ static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV
static inline void snp_leak_pages(u64 pfn, unsigned int npages) {}
static inline void kdump_sev_callback(void) { }
static inline void snp_fixup_e820_tables(void) {}
+static inline void sev_evict_cache(void *va, int npages) {}
#endif
#endif
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index b4a1f6732a3a..6b868afb26c3 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -48,6 +48,7 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 },
{ X86_FEATURE_AMD_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 },
{ X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 },
+ { X86_FEATURE_COHERENCY_SFW_NO, CPUID_EBX, 31, 0x8000001f, 0 },
{ X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 },
{ X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 },
{ X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 },
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 835b0deef9bb..f23d75986947 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4331,15 +4331,18 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
unsigned long end = index + (PAGE_SIZE >> fs_info->nodesize_bits) - 1;
int ret;
- xa_lock_irq(&fs_info->buffer_tree);
+ rcu_read_lock();
xa_for_each_range(&fs_info->buffer_tree, index, eb, start, end) {
/*
* The same as try_release_extent_buffer(), to ensure the eb
* won't disappear out from under us.
*/
spin_lock(&eb->refs_lock);
+ rcu_read_unlock();
+
if (refcount_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
spin_unlock(&eb->refs_lock);
+ rcu_read_lock();
continue;
}
@@ -4358,11 +4361,10 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
* check the folio private at the end. And
* release_extent_buffer() will release the refs_lock.
*/
- xa_unlock_irq(&fs_info->buffer_tree);
release_extent_buffer(eb);
- xa_lock_irq(&fs_info->buffer_tree);
+ rcu_read_lock();
}
- xa_unlock_irq(&fs_info->buffer_tree);
+ rcu_read_unlock();
/*
* Finally to check if we have cleared folio private, as if we have
@@ -4375,7 +4377,6 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
ret = 0;
spin_unlock(&folio->mapping->i_private_lock);
return ret;
-
}
int try_release_extent_buffer(struct folio *folio)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b77dd22b8cdb..d740910e071a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -401,10 +401,12 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
while (index <= end_index) {
folio = filemap_get_folio(inode->vfs_inode.i_mapping, index);
- index++;
- if (IS_ERR(folio))
+ if (IS_ERR(folio)) {
+ index++;
continue;
+ }
+ index = folio_end(folio) >> PAGE_SHIFT;
/*
* Here we just clear all Ordered bits for every page in the
* range, then btrfs_mark_ordered_io_finished() will handle
@@ -2013,7 +2015,7 @@ static int nocow_one_range(struct btrfs_inode *inode, struct folio *locked_folio
* cleaered by the caller.
*/
if (ret < 0)
- btrfs_cleanup_ordered_extents(inode, file_pos, end);
+ btrfs_cleanup_ordered_extents(inode, file_pos, len);
return ret;
}
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 1a5972178b3a..ccaa9a3cf1ce 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1453,7 +1453,6 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
struct btrfs_qgroup *src, int sign)
{
struct btrfs_qgroup *qgroup;
- struct btrfs_qgroup *cur;
LIST_HEAD(qgroup_list);
u64 num_bytes = src->excl;
int ret = 0;
@@ -1463,7 +1462,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
goto out;
qgroup_iterator_add(&qgroup_list, qgroup);
- list_for_each_entry(cur, &qgroup_list, iterator) {
+ list_for_each_entry(qgroup, &qgroup_list, iterator) {
struct btrfs_qgroup_list *glist;
qgroup->rfer += sign * num_bytes;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index e58151933844..7256f6748c8f 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -602,6 +602,25 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
if (btrfs_root_id(root) == objectid) {
u64 commit_root_gen;
+ /*
+ * Relocation will wait for cleaner thread, and any half-dropped
+ * subvolume will be fully cleaned up at mount time.
+ * So here we shouldn't hit a subvolume with non-zero drop_progress.
+ *
+ * If this isn't the case, error out since it can make us attempt to
+ * drop references for extents that were already dropped before.
+ */
+ if (unlikely(btrfs_disk_key_objectid(&root->root_item.drop_progress))) {
+ struct btrfs_key cpu_key;
+
+ btrfs_disk_key_to_cpu(&cpu_key, &root->root_item.drop_progress);
+ btrfs_err(fs_info,
+ "cannot relocate partially dropped subvolume %llu, drop progress key (%llu %u %llu)",
+ objectid, cpu_key.objectid, cpu_key.type, cpu_key.offset);
+ ret = -EUCLEAN;
+ goto fail;
+ }
+
/* called by btrfs_init_reloc_root */
ret = btrfs_copy_root(trans, root, root->commit_root, &eb,
BTRFS_TREE_RELOC_OBJECTID);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2186e87fb61b..69e11557fd13 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2605,14 +2605,14 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
/*
* Correctly adjust the reserved bytes occupied by a log tree extent buffer
*/
-static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
+static int unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
{
struct btrfs_block_group *cache;
cache = btrfs_lookup_block_group(fs_info, start);
if (!cache) {
btrfs_err(fs_info, "unable to find block group for %llu", start);
- return;
+ return -ENOENT;
}
spin_lock(&cache->space_info->lock);
@@ -2623,27 +2623,22 @@ static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
spin_unlock(&cache->space_info->lock);
btrfs_put_block_group(cache);
+
+ return 0;
}
static int clean_log_buffer(struct btrfs_trans_handle *trans,
struct extent_buffer *eb)
{
- int ret;
-
btrfs_tree_lock(eb);
btrfs_clear_buffer_dirty(trans, eb);
wait_on_extent_buffer_writeback(eb);
btrfs_tree_unlock(eb);
- if (trans) {
- ret = btrfs_pin_reserved_extent(trans, eb);
- if (ret)
- return ret;
- } else {
- unaccount_log_buffer(eb->fs_info, eb->start);
- }
+ if (trans)
+ return btrfs_pin_reserved_extent(trans, eb);
- return 0;
+ return unaccount_log_buffer(eb->fs_info, eb->start);
}
static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 245e813ecd78..db11b5b5f0e6 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2650,7 +2650,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info)
spin_lock(&block_group->lock);
if (block_group->reserved || block_group->alloc_offset == 0 ||
- (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM) ||
+ !(block_group->flags & BTRFS_BLOCK_GROUP_DATA) ||
test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
continue;
diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
index 4f6468eb2adf..cb237f1b902a 100644
--- a/fs/nfsd/localio.c
+++ b/fs/nfsd/localio.c
@@ -103,10 +103,11 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
if (nfsd_file_get(new) == NULL)
goto again;
/*
- * Drop the ref we were going to install and the
- * one we were going to return.
+ * Drop the ref we were going to install (both file and
+ * net) and the one we were going to return (only file).
*/
nfsd_file_put(localio);
+ nfsd_net_put(net);
nfsd_file_put(localio);
localio = new;
}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 98ab55ba3ced..edf050766e57 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -470,7 +470,15 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap)
if (!iap->ia_valid)
return 0;
- iap->ia_valid |= ATTR_CTIME;
+ /*
+ * If ATTR_DELEG is set, then this is an update from a client that
+ * holds a delegation. If this is an update for only the atime, the
+ * ctime should not be changed. If the update contains the mtime
+ * too, then ATTR_CTIME should already be set.
+ */
+ if (!(iap->ia_valid & ATTR_DELEG))
+ iap->ia_valid |= ATTR_CTIME;
+
return notify_change(&nop_mnt_idmap, dentry, iap, NULL);
}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 46c156b121db..e2c5e0e626f9 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -257,20 +257,47 @@ svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
}
static int
-svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg)
+svc_tcp_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags)
{
union {
struct cmsghdr cmsg;
u8 buf[CMSG_SPACE(sizeof(u8))];
} u;
- struct socket *sock = svsk->sk_sock;
+ u8 alert[2];
+ struct kvec alert_kvec = {
+ .iov_base = alert,
+ .iov_len = sizeof(alert),
+ };
+ struct msghdr msg = {
+ .msg_flags = *msg_flags,
+ .msg_control = &u,
+ .msg_controllen = sizeof(u),
+ };
+ int ret;
+
+ iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
+ alert_kvec.iov_len);
+ ret = sock_recvmsg(sock, &msg, MSG_DONTWAIT);
+ if (ret > 0 &&
+ tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
+ iov_iter_revert(&msg.msg_iter, ret);
+ ret = svc_tcp_sock_process_cmsg(sock, &msg, &u.cmsg, -EAGAIN);
+ }
+ return ret;
+}
+
+static int
+svc_tcp_sock_recvmsg(struct svc_sock *svsk, struct msghdr *msg)
+{
int ret;
+ struct socket *sock = svsk->sk_sock;
- msg->msg_control = &u;
- msg->msg_controllen = sizeof(u);
ret = sock_recvmsg(sock, msg, MSG_DONTWAIT);
- if (unlikely(msg->msg_controllen != sizeof(u)))
- ret = svc_tcp_sock_process_cmsg(sock, msg, &u.cmsg, ret);
+ if (msg->msg_flags & MSG_CTRUNC) {
+ msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR);
+ if (ret == 0 || ret == -EIO)
+ ret = svc_tcp_sock_recv_cmsg(sock, &msg->msg_flags);
+ }
return ret;
}
@@ -321,7 +348,7 @@ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen,
iov_iter_advance(&msg.msg_iter, seek);
buflen -= seek;
}
- len = svc_tcp_sock_recv_cmsg(svsk, &msg);
+ len = svc_tcp_sock_recvmsg(svsk, &msg);
if (len > 0)
svc_flush_bvec(bvec, len, seek);
@@ -1018,7 +1045,7 @@ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk,
iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen;
iov.iov_len = want;
iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, want);
- len = svc_tcp_sock_recv_cmsg(svsk, &msg);
+ len = svc_tcp_sock_recvmsg(svsk, &msg);
if (len < 0)
return len;
svsk->sk_tcplen += len;
generated by cgit (git 2.34.1) at 2025-08-12 19:31:20 +0000