Merge tag 'v5.12-rc8' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

10 files changed, 122 insertions, 74 deletions

diff --git a/include/uapi/linux/blkpg.h b/include/uapi/linux/blkpg.h
index ac6474e4f29d..d0a64ee97c6d 100644
--- a/include/uapi/linux/blkpg.h
+++ b/include/uapi/linux/blkpg.h
@@ -2,29 +2,6 @@
 #ifndef _UAPI__LINUX_BLKPG_H
 #define _UAPI__LINUX_BLKPG_H
 
-/*
- * Partition table and disk geometry handling
- *
- * A single ioctl with lots of subfunctions:
- *
- * Device number stuff:
- *    get_whole_disk()		(given the device number of a partition,
- *                               find the device number of the encompassing disk)
- *    get_all_partitions()	(given the device number of a disk, return the
- *				 device numbers of all its known partitions)
- *
- * Partition stuff:
- *    add_partition()
- *    delete_partition()
- *    test_partition_in_use()	(also for test_disk_in_use)
- *
- * Geometry stuff:
- *    get_geometry()
- *    set_geometry()
- *    get_bios_drivedata()
- *
- * For today, only the partition stuff - aeb, 990515
- */
 #include <linux/compiler.h>
 #include <linux/ioctl.h>
 
@@ -52,9 +29,8 @@ struct blkpg_partition {
 	long long start;		/* starting offset in bytes */
 	long long length;		/* length in bytes */
 	int pno;			/* partition number */
-	char devname[BLKPG_DEVNAMELTH];	/* partition name, like sda5 or c0d1p2,
-					   to be used in kernel messages */
-	char volname[BLKPG_VOLNAMELTH];	/* volume label */
+	char devname[BLKPG_DEVNAMELTH];	/* unused / ignored */
+	char volname[BLKPG_VOLNAMELTH];	/* unused / ignore */
 };
 
 #endif /* _UAPI__LINUX_BLKPG_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4c24daa43bac..4ba4ef0ff63a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3850,8 +3850,7 @@ union bpf_attr {
  *
  * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
  *	Description
-
- *		Check ctx packet size against exceeding MTU of net device (based
+ *		Check packet size against exceeding MTU of net device (based
  *		on *ifindex*).  This helper will likely be used in combination
  *		with helpers that adjust/change the packet size.
  *
@@ -3868,6 +3867,14 @@ union bpf_attr {
  *		against the current net device.  This is practical if this isn't
  *		used prior to redirect.
  *
+ *		On input *mtu_len* must be a valid pointer, else verifier will
+ *		reject BPF program.  If the value *mtu_len* is initialized to
+ *		zero then the ctx packet size is use.  When value *mtu_len* is
+ *		provided as input this specify the L3 length that the MTU check
+ *		is done against. Remember XDP and TC length operate at L2, but
+ *		this value is L3 as this correlate to MTU and IP-header tot_len
+ *		values which are L3 (similar behavior as bpf_fib_lookup).
+ *
  *		The Linux kernel route table can configure MTUs on a more
  *		specific per route level, which is not provided by this helper.
  *		For route level MTU checks use the **bpf_fib_lookup**\ ()
@@ -3892,11 +3899,9 @@ union bpf_attr {
  *
  *		On return *mtu_len* pointer contains the MTU value of the net
  *		device.  Remember the net device configured MTU is the L3 size,
- *		which is returned here and XDP and TX length operate at L2.
+ *		which is returned here and XDP and TC length operate at L2.
  *		Helper take this into account for you, but remember when using
- *		MTU value in your BPF-code.  On input *mtu_len* must be a valid
- *		pointer and be initialized (to zero), else verifier will reject
- *		BPF program.
+ *		MTU value in your BPF-code.
  *
  *	Return
  *		* 0 on success, and populate MTU value in *mtu_len* pointer.
diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index f75238ac6dce..c7535352fef6 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -113,7 +113,7 @@ struct can_frame {
 		 */
 		__u8 len;
 		__u8 can_dlc; /* deprecated */
-	};
+	} __attribute__((packed)); /* disable padding added in some ABIs */
 	__u8 __pad; /* padding */
 	__u8 __res0; /* reserved / padding */
 	__u8 len8_dlc; /* optional DLC for 8 byte payload length (9 .. 15) */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index cde753bb2093..5afea692a3f7 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -26,6 +26,14 @@
  * have the same layout for 32-bit and 64-bit userland.
  */
 
+/* Note on reserved space.
+ * Reserved fields must not be accessed directly by user space because
+ * they may be replaced by a different field in the future. They must
+ * be initialized to zero before making the request, e.g. via memset
+ * of the entire structure or implicitly by not being set in a structure
+ * initializer.
+ */
+
 /**
  * struct ethtool_cmd - DEPRECATED, link control and status
  * This structure is DEPRECATED, please use struct ethtool_link_settings.
@@ -67,6 +75,7 @@
  *	and other link features that the link partner advertised
  *	through autonegotiation; 0 if unknown or not applicable.
  *	Read-only.
+ * @reserved: Reserved for future use; see the note on reserved space.
  *
  * The link speed in Mbps is split between @speed and @speed_hi.  Use
  * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to
@@ -155,6 +164,7 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep)
  * @bus_info: Device bus address.  This should match the dev_name()
  *	string for the underlying bus device, if there is one.  May be
  *	an empty string.
+ * @reserved2: Reserved for future use; see the note on reserved space.
  * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and
  *	%ETHTOOL_SPFLAGS commands; also the number of strings in the
  *	%ETH_SS_PRIV_FLAGS set
@@ -356,6 +366,7 @@ struct ethtool_eeprom {
  * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting
  *	its tx lpi (after reaching 'idle' state). Effective only when eee
  *	was negotiated and tx_lpi_enabled was set.
+ * @reserved: Reserved for future use; see the note on reserved space.
  */
 struct ethtool_eee {
 	__u32	cmd;
@@ -374,6 +385,7 @@ struct ethtool_eee {
  * @cmd: %ETHTOOL_GMODULEINFO
  * @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx
  * @eeprom_len: Length of the eeprom
+ * @reserved: Reserved for future use; see the note on reserved space.
  *
  * This structure is used to return the information to
  * properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM.
@@ -579,9 +591,7 @@ struct ethtool_pauseparam {
 	__u32	tx_pause;
 };
 
-/**
- * enum ethtool_link_ext_state - link extended state
- */
+/* Link extended state */
 enum ethtool_link_ext_state {
 	ETHTOOL_LINK_EXT_STATE_AUTONEG,
 	ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE,
@@ -595,10 +605,7 @@ enum ethtool_link_ext_state {
 	ETHTOOL_LINK_EXT_STATE_OVERHEAT,
 };
 
-/**
- * enum ethtool_link_ext_substate_autoneg - more information in addition to
- * ETHTOOL_LINK_EXT_STATE_AUTONEG.
- */
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */
 enum ethtool_link_ext_substate_autoneg {
 	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1,
 	ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED,
@@ -608,9 +615,7 @@ enum ethtool_link_ext_substate_autoneg {
 	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD,
 };
 
-/**
- * enum ethtool_link_ext_substate_link_training - more information in addition to
- * ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
  */
 enum ethtool_link_ext_substate_link_training {
 	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1,
@@ -619,9 +624,7 @@ enum ethtool_link_ext_substate_link_training {
 	ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT,
 };
 
-/**
- * enum ethtool_link_ext_substate_logical_mismatch - more information in addition
- * to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
  */
 enum ethtool_link_ext_substate_link_logical_mismatch {
 	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1,
@@ -631,19 +634,14 @@ enum ethtool_link_ext_substate_link_logical_mismatch {
 	ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED,
 };
 
-/**
- * enum ethtool_link_ext_substate_bad_signal_integrity - more information in
- * addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
  */
 enum ethtool_link_ext_substate_bad_signal_integrity {
 	ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1,
 	ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE,
 };
 
-/**
- * enum ethtool_link_ext_substate_cable_issue - more information in
- * addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE.
- */
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */
 enum ethtool_link_ext_substate_cable_issue {
 	ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1,
 	ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE,
@@ -661,6 +659,7 @@ enum ethtool_link_ext_substate_cable_issue {
  *	now deprecated
  * @ETH_SS_FEATURES: Device feature names
  * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names
+ * @ETH_SS_TUNABLES: tunable names
  * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS
  * @ETH_SS_PHY_TUNABLES: PHY tunable names
  * @ETH_SS_LINK_MODES: link mode names
@@ -670,6 +669,8 @@ enum ethtool_link_ext_substate_cable_issue {
  * @ETH_SS_TS_TX_TYPES: timestamping Tx types
  * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters
  * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types
+ *
+ * @ETH_SS_COUNT: number of defined string sets
  */
 enum ethtool_stringset {
 	ETH_SS_TEST		= 0,
@@ -715,6 +716,7 @@ struct ethtool_gstrings {
 /**
  * struct ethtool_sset_info - string set information
  * @cmd: Command number = %ETHTOOL_GSSET_INFO
+ * @reserved: Reserved for future use; see the note on reserved space.
  * @sset_mask: On entry, a bitmask of string sets to query, with bits
  *	numbered according to &enum ethtool_stringset.  On return, a
  *	bitmask of those string sets queried that are supported.
@@ -759,6 +761,7 @@ enum ethtool_test_flags {
  * @flags: A bitmask of flags from &enum ethtool_test_flags.  Some
  *	flags may be set by the user on entry; others may be set by
  *	the driver on return.
+ * @reserved: Reserved for future use; see the note on reserved space.
  * @len: On return, the number of test results
  * @data: Array of test results
  *
@@ -959,6 +962,7 @@ union ethtool_flow_union {
  * @vlan_etype: VLAN EtherType
  * @vlan_tci: VLAN tag control information
  * @data: user defined data
+ * @padding: Reserved for future use; see the note on reserved space.
  *
  * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT
  * is set in &struct ethtool_rx_flow_spec @flow_type.
@@ -1134,7 +1138,8 @@ struct ethtool_rxfh_indir {
  *	hardware hash key.
  * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
  *	Valid values are one of the %ETH_RSS_HASH_*.
- * @rsvd:	Reserved for future extensions.
+ * @rsvd8: Reserved for future use; see the note on reserved space.
+ * @rsvd32: Reserved for future use; see the note on reserved space.
  * @rss_config: RX ring/queue index for each hash value i.e., indirection table
  *	of @indir_size __u32 elements, followed by hash key of @key_size
  *	bytes.
@@ -1302,7 +1307,9 @@ struct ethtool_sfeatures {
  * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags
  * @phc_index: device index of the associated PHC, or -1 if there is none
  * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values
+ * @tx_reserved: Reserved for future use; see the note on reserved space.
  * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values
+ * @rx_reserved: Reserved for future use; see the note on reserved space.
  *
  * The bits in the 'tx_types' and 'rx_filters' fields correspond to
  * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values,
@@ -1958,6 +1965,11 @@ enum ethtool_reset_flags {
  *	autonegotiation; 0 if unknown or not applicable.  Read-only.
  * @transceiver: Used to distinguish different possible PHY types,
  *	reported consistently by PHYLIB.  Read-only.
+ * @master_slave_cfg: Master/slave port mode.
+ * @master_slave_state: Master/slave port state.
+ * @reserved: Reserved for future use; see the note on reserved space.
+ * @reserved1: Reserved for future use; see the note on reserved space.
+ * @link_mode_masks: Variable length bitmaps.
  *
  * If autonegotiation is disabled, the speed and @duplex represent the
  * fixed link mode and are writable if the driver supports multiple
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 98ca64d1beb6..54442612c48b 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -903,7 +903,8 @@ struct fuse_notify_retrieve_in {
 };
 
 /* Device ioctls: */
-#define FUSE_DEV_IOC_CLONE	_IOR(229, 0, uint32_t)
+#define FUSE_DEV_IOC_MAGIC		229
+#define FUSE_DEV_IOC_CLONE		_IOR(FUSE_DEV_IOC_MAGIC, 0, uint32_t)
 
 struct fuse_lseek_in {
 	uint64_t	fh;
diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h
index 236d437947bc..e33997b4d750 100644
--- a/include/uapi/linux/idxd.h
+++ b/include/uapi/linux/idxd.h
@@ -247,8 +247,8 @@ struct dsa_completion_record {
 			uint32_t	rsvd2:8;
 		};
 
-		uint16_t	delta_rec_size;
-		uint16_t	crc_val;
+		uint32_t	delta_rec_size;
+		uint32_t	crc_val;
 
 		/* DIF check & strip */
 		struct {
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 30c80d5ba4bf..bab8c9708611 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -145,6 +145,7 @@ enum {
 	L2TP_ATTR_RX_ERRORS,		/* u64 */
 	L2TP_ATTR_STATS_PAD,
 	L2TP_ATTR_RX_COOKIE_DISCARDS,	/* u64 */
+	L2TP_ATTR_RX_INVALID,		/* u64 */
 	__L2TP_ATTR_STATS_MAX,
 };
 
diff --git a/include/uapi/linux/netfilter/nfnetlink_cthelper.h b/include/uapi/linux/netfilter/nfnetlink_cthelper.h
index a13137afc429..70af02092d16 100644
--- a/include/uapi/linux/netfilter/nfnetlink_cthelper.h
+++ b/include/uapi/linux/netfilter/nfnetlink_cthelper.h
@@ -5,7 +5,7 @@
 #define NFCT_HELPER_STATUS_DISABLED	0
 #define NFCT_HELPER_STATUS_ENABLED	1
 
-enum nfnl_acct_msg_types {
+enum nfnl_cthelper_msg_types {
 	NFNL_MSG_CTHELPER_NEW,
 	NFNL_MSG_CTHELPER_GET,
 	NFNL_MSG_CTHELPER_DEL,
diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h
index aea26ab1431c..bff5032c98df 100644
--- a/include/uapi/linux/psample.h
+++ b/include/uapi/linux/psample.h
@@ -3,7 +3,6 @@
 #define __UAPI_PSAMPLE_H
 
 enum {
-	/* sampled packet metadata */
 	PSAMPLE_ATTR_IIFINDEX,
 	PSAMPLE_ATTR_OIFINDEX,
 	PSAMPLE_ATTR_ORIGSIZE,
@@ -11,10 +10,8 @@ enum {
 	PSAMPLE_ATTR_GROUP_SEQ,
 	PSAMPLE_ATTR_SAMPLE_RATE,
 	PSAMPLE_ATTR_DATA,
-	PSAMPLE_ATTR_TUNNEL,
-
-	/* commands attributes */
 	PSAMPLE_ATTR_GROUP_REFCOUNT,
+	PSAMPLE_ATTR_TUNNEL,
 
 	__PSAMPLE_ATTR_MAX
 };
diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h
index 03e8af87b364..9b77cfc42efa 100644
--- a/include/uapi/linux/rfkill.h
+++ b/include/uapi/linux/rfkill.h
@@ -86,34 +86,90 @@ enum rfkill_hard_block_reasons {
  * @op: operation code
  * @hard: hard state (0/1)
  * @soft: soft state (0/1)
+ *
+ * Structure used for userspace communication on /dev/rfkill,
+ * used for events from the kernel and control to the kernel.
+ */
+struct rfkill_event {
+	__u32 idx;
+	__u8  type;
+	__u8  op;
+	__u8  soft;
+	__u8  hard;
+} __attribute__((packed));
+
+/**
+ * struct rfkill_event_ext - events for userspace on /dev/rfkill
+ * @idx: index of dev rfkill
+ * @type: type of the rfkill struct
+ * @op: operation code
+ * @hard: hard state (0/1)
+ * @soft: soft state (0/1)
  * @hard_block_reasons: valid if hard is set. One or several reasons from
  *	&enum rfkill_hard_block_reasons.
  *
  * Structure used for userspace communication on /dev/rfkill,
  * used for events from the kernel and control to the kernel.
+ *
+ * See the extensibility docs below.
  */
-struct rfkill_event {
+struct rfkill_event_ext {
 	__u32 idx;
 	__u8  type;
 	__u8  op;
 	__u8  soft;
 	__u8  hard;
+
+	/*
+	 * older kernels will accept/send only up to this point,
+	 * and if extended further up to any chunk marked below
+	 */
+
 	__u8  hard_block_reasons;
 } __attribute__((packed));
 
-/*
- * We are planning to be backward and forward compatible with changes
- * to the event struct, by adding new, optional, members at the end.
- * When reading an event (whether the kernel from userspace or vice
- * versa) we need to accept anything that's at least as large as the
- * version 1 event size, but might be able to accept other sizes in
- * the future.
+/**
+ * DOC: Extensibility
+ *
+ * Originally, we had planned to allow backward and forward compatible
+ * changes by just adding fields at the end of the structure that are
+ * then not reported on older kernels on read(), and not written to by
+ * older kernels on write(), with the kernel reporting the size it did
+ * accept as the result.
+ *
+ * This would have allowed userspace to detect on read() and write()
+ * which kernel structure version it was dealing with, and if was just
+ * recompiled it would have gotten the new fields, but obviously not
+ * accessed them, but things should've continued to work.
+ *
+ * Unfortunately, while actually exercising this mechanism to add the
+ * hard block reasons field, we found that userspace (notably systemd)
+ * did all kinds of fun things not in line with this scheme:
+ *
+ * 1. treat the (expected) short writes as an error;
+ * 2. ask to read sizeof(struct rfkill_event) but then compare the
+ *    actual return value to RFKILL_EVENT_SIZE_V1 and treat any
+ *    mismatch as an error.
+ *
+ * As a consequence, just recompiling with a new struct version caused
+ * things to no longer work correctly on old and new kernels.
+ *
+ * Hence, we've rolled back &struct rfkill_event to the original version
+ * and added &struct rfkill_event_ext. This effectively reverts to the
+ * old behaviour for all userspace, unless it explicitly opts in to the
+ * rules outlined here by using the new &struct rfkill_event_ext.
+ *
+ * Userspace using &struct rfkill_event_ext must adhere to the following
+ * rules
  *
- * One exception is the kernel -- we already have two event sizes in
- * that we've made the 'hard' member optional since our only option
- * is to ignore it anyway.
+ * 1. accept short writes, optionally using them to detect that it's
+ *    running on an older kernel;
+ * 2. accept short reads, knowing that this means it's running on an
+ *    older kernel;
+ * 3. treat reads that are as long as requested as acceptable, not
+ *    checking against RFKILL_EVENT_SIZE_V1 or such.
  */
-#define RFKILL_EVENT_SIZE_V1	8
+#define RFKILL_EVENT_SIZE_V1	sizeof(struct rfkill_event)
 
 /* ioctl for turning off rfkill-input (if present) */
 #define RFKILL_IOC_MAGIC	'R'