[PATCH v2] efivarfs: add nostatfs mount option to skip QueryVariableInfo()

[Prashant Singh <singhpra@juniper.net>]

QueryVariableInfo() is an EFI runtime service that, on some firmware,
takes tens of milliseconds and runs with preemption disabled, stalling
the CPU that services it. efivarfs_statfs() calls it (rate-limited since
commit b2326338dc68 ("efivarfs: Rate limit statfs() handler")) to report
the variable-store used/available capacity, so any statfs(2) -- e.g.
every "df" -- can inject that stall into unrelated latency-sensitive
workloads on the same CPU.

Add a "nostatfs" mount option: when set, statfs(2) skips
QueryVariableInfo() entirely and reports zero used/available. It is set
by default on CONFIG_PREEMPT_RT so real-time kernels do not take the
stall out of the box.

Tested on an Intel Xeon E5-2628L v4, 6.12 kernel with CONFIG_PREEMPT_RT
not set (so reporting defaults to enabled and nostatfs must be passed
explicitly), via "strace -T -e trace=statfs df" on the efivarfs mount.

Default mount: statfs() calls QueryVariableInfo() and returns the real
store capacity, ~66-129 ms per call:

  statfs("/sys/firmware/efi/efivars", {f_type=EFIVARFS_MAGIC,
      f_bsize=1, f_blocks=90024, f_bfree=33387, f_bavail=28267, ...})
      = 0 <0.129124>

With -o nostatfs: no firmware call, capacity reported as zero, ~11 us per
call:

  statfs("/sys/firmware/efi/efivars", {f_type=EFIVARFS_MAGIC,
      f_bsize=1, f_blocks=0, f_bfree=0, f_bavail=0, ...}) = 0 <0.000011>

Signed-off-by: Prashant Singh <singhpra@juniper.net>
---
Changes since v1:
  - Per review, dropped the fs.efivarfs sysctl / cached-capacity approach
    entirely; instead add a simple "nostatfs" mount option that skips
    QueryVariableInfo() in statfs() and reports zero, set by default on
    CONFIG_PREEMPT_RT.

v1: https://lore.kernel.org/all/20260917071600.5587-1-singhpra@juniper.net/

 Documentation/filesystems/efivarfs.rst | 10 ++++++++++
 fs/efivarfs/internal.h                 |  1 +
 fs/efivarfs/super.c                    | 20 +++++++++++++++++---
 3 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/Documentation/filesystems/efivarfs.rst b/Documentation/filesystems/efivarfs.rst
index f646c3f0980f..3ead638c796a 100644
--- a/Documentation/filesystems/efivarfs.rst
+++ b/Documentation/filesystems/efivarfs.rst
@@ -37,6 +37,16 @@ accidentally.
           |4_bytes_of_attributes + efivar_data|
           +-----------------------------------+
 
+Mount options
+=============
+
+nostatfs
+      Do not report the variable-store used/available capacity in
+      ``statfs(2)``; report zero instead. Obtaining the capacity requires the
+      ``QueryVariableInfo()`` EFI runtime service, which on some firmware takes
+      tens of milliseconds and runs with preemption disabled, stalling the
+      calling CPU. This option is set by default on ``CONFIG_PREEMPT_RT``.
+
 *See also:*
 
 - Documentation/admin-guide/acpi/ssdt-overlays.rst
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index f913b6824289..0cb053884b4b 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -11,6 +11,7 @@
 struct efivarfs_mount_opts {
 	kuid_t uid;
 	kgid_t gid;
+	bool nostatfs;		/* skip QueryVariableInfo() in statfs() */
 };
 
 struct efivarfs_fs_info {
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 8d33f11db2a1..fbdaa4915d30 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -74,6 +74,8 @@ static int efivarfs_show_options(struct seq_file *m, struct dentry *root)
 	if (!gid_eq(opts->gid, GLOBAL_ROOT_GID))
 		seq_printf(m, ",gid=%u",
 				from_kgid_munged(&init_user_ns, opts->gid));
+	if (opts->nostatfs)
+		seq_puts(m, ",nostatfs");
 	return 0;
 }
 
@@ -82,13 +84,19 @@ static int efivarfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	const u32 attr = EFI_VARIABLE_NON_VOLATILE |
 			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
 			 EFI_VARIABLE_RUNTIME_ACCESS;
+	struct efivarfs_fs_info *sfi = dentry->d_sb->s_fs_info;
 	u64 storage_space, remaining_space, max_variable_size;
 	u64 id = huge_encode_dev(dentry->d_sb->s_dev);
 	efi_status_t status;
 
-	/* Some UEFI firmware does not implement QueryVariableInfo() */
+	/*
+	 * Some UEFI firmware does not implement QueryVariableInfo(); the
+	 * nostatfs mount option also disables this (preempt-disabled,
+	 * potentially slow) call entirely, reporting zero used/available.
+	 */
 	storage_space = remaining_space = 0;
-	if (efi_rt_services_supported(EFI_RT_SUPPORTED_QUERY_VARIABLE_INFO)) {
+	if (!sfi->mount_opts.nostatfs &&
+	    efi_rt_services_supported(EFI_RT_SUPPORTED_QUERY_VARIABLE_INFO)) {
 		static DEFINE_RATELIMIT_STATE(_rs, 2 * HZ, 5);
 		static u64 storage, remaining;
 		static DEFINE_SPINLOCK(lock);
@@ -323,12 +331,13 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 }
 
 enum {
-	Opt_uid, Opt_gid,
+	Opt_uid, Opt_gid, Opt_nostatfs,
 };
 
 static const struct fs_parameter_spec efivarfs_parameters[] = {
 	fsparam_uid("uid", Opt_uid),
 	fsparam_gid("gid", Opt_gid),
+	fsparam_flag("nostatfs", Opt_nostatfs),
 	{},
 };
 
@@ -350,6 +359,9 @@ static int efivarfs_parse_param(struct fs_context *fc, struct fs_parameter *para
 	case Opt_gid:
 		opts->gid = result.gid;
 		break;
+	case Opt_nostatfs:
+		opts->nostatfs = true;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -526,6 +538,8 @@ static int efivarfs_init_fs_context(struct fs_context *fc)
 
 	sfi->mount_opts.uid = GLOBAL_ROOT_UID;
 	sfi->mount_opts.gid = GLOBAL_ROOT_GID;
+	/* QueryVariableInfo() stalls the CPU; default nostatfs on PREEMPT_RT. */
+	sfi->mount_opts.nostatfs = IS_ENABLED(CONFIG_PREEMPT_RT);
 
 	fc->s_fs_info = sfi;
 	fc->ops = &efivarfs_context_ops;

base-commit: 9b87fdc9af2fbfcdb5c24a64139685ef80f6573f
-- 
2.34.1