Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 278 insertions, 0 deletions

diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
new file mode 100644
index 000000000..574af8243
--- /dev/null
+++ b/drivers/scsi/sd.h
@@ -0,0 +1,278 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _SCSI_DISK_H
+#define _SCSI_DISK_H
+
+/*
+ * More than enough for everybody ;)  The huge number of majors
+ * is a leftover from 16bit dev_t days, we don't really need that
+ * much numberspace.
+ */
+#define SD_MAJORS	16
+
+/*
+ * Time out in seconds for disks and Magneto-opticals (which are slower).
+ */
+#define SD_TIMEOUT		(30 * HZ)
+#define SD_MOD_TIMEOUT		(75 * HZ)
+/*
+ * Flush timeout is a multiplier over the standard device timeout which is
+ * user modifiable via sysfs but initially set to SD_TIMEOUT
+ */
+#define SD_FLUSH_TIMEOUT_MULTIPLIER	2
+#define SD_WRITE_SAME_TIMEOUT	(120 * HZ)
+
+/*
+ * Number of allowed retries
+ */
+#define SD_MAX_RETRIES		5
+#define SD_PASSTHROUGH_RETRIES	1
+#define SD_MAX_MEDIUM_TIMEOUTS	2
+
+/*
+ * Size of the initial data buffer for mode and read capacity data
+ */
+#define SD_BUF_SIZE		512
+
+/*
+ * Number of sectors at the end of the device to avoid multi-sector
+ * accesses to in the case of last_sector_bug
+ */
+#define SD_LAST_BUGGY_SECTORS	8
+
+enum {
+	SD_EXT_CDB_SIZE = 32,	/* Extended CDB size */
+	SD_MEMPOOL_SIZE = 2,	/* CDB pool size */
+};
+
+enum {
+	SD_DEF_XFER_BLOCKS = 0xffff,
+	SD_MAX_XFER_BLOCKS = 0xffffffff,
+	SD_MAX_WS10_BLOCKS = 0xffff,
+	SD_MAX_WS16_BLOCKS = 0x7fffff,
+};
+
+enum {
+	SD_LBP_FULL = 0,	/* Full logical block provisioning */
+	SD_LBP_UNMAP,		/* Use UNMAP command */
+	SD_LBP_WS16,		/* Use WRITE SAME(16) with UNMAP bit */
+	SD_LBP_WS10,		/* Use WRITE SAME(10) with UNMAP bit */
+	SD_LBP_ZERO,		/* Use WRITE SAME(10) with zero payload */
+	SD_LBP_DISABLE,		/* Discard disabled due to failed cmd */
+};
+
+enum {
+	SD_ZERO_WRITE = 0,	/* Use WRITE(10/16) command */
+	SD_ZERO_WS,		/* Use WRITE SAME(10/16) command */
+	SD_ZERO_WS16_UNMAP,	/* Use WRITE SAME(16) with UNMAP */
+	SD_ZERO_WS10_UNMAP,	/* Use WRITE SAME(10) with UNMAP */
+};
+
+/**
+ * struct zoned_disk_info - Specific properties of a ZBC SCSI device.
+ * @nr_zones: number of zones.
+ * @zone_blocks: number of logical blocks per zone.
+ *
+ * This data structure holds the ZBC SCSI device properties that are retrieved
+ * twice: a first time before the gendisk capacity is known and a second time
+ * after the gendisk capacity is known.
+ */
+struct zoned_disk_info {
+	u32		nr_zones;
+	u32		zone_blocks;
+};
+
+struct scsi_disk {
+	struct scsi_device *device;
+
+	/*
+	 * disk_dev is used to show attributes in /sys/class/scsi_disk/,
+	 * but otherwise not really needed.  Do not use for refcounting.
+	 */
+	struct device	disk_dev;
+	struct gendisk	*disk;
+	struct opal_dev *opal_dev;
+#ifdef CONFIG_BLK_DEV_ZONED
+	/* Updated during revalidation before the gendisk capacity is known. */
+	struct zoned_disk_info	early_zone_info;
+	/* Updated during revalidation after the gendisk capacity is known. */
+	struct zoned_disk_info	zone_info;
+	u32		zones_optimal_open;
+	u32		zones_optimal_nonseq;
+	u32		zones_max_open;
+	/*
+	 * Either zero or a power of two. If not zero it means that the offset
+	 * between zone starting LBAs is constant.
+	 */
+	u32		zone_starting_lba_gran;
+#endif
+	atomic_t	openers;
+	sector_t	capacity;	/* size in logical blocks */
+	int		max_retries;
+	u32		min_xfer_blocks;
+	u32		max_xfer_blocks;
+	u32		opt_xfer_blocks;
+	u32		max_ws_blocks;
+	u32		max_unmap_blocks;
+	u32		unmap_granularity;
+	u32		unmap_alignment;
+
+	u32		max_atomic;
+	u32		atomic_alignment;
+	u32		atomic_granularity;
+	u32		max_atomic_with_boundary;
+	u32		max_atomic_boundary;
+
+	u32		index;
+	unsigned int	physical_block_size;
+	unsigned int	max_medium_access_timeouts;
+	unsigned int	medium_access_timed_out;
+			/* number of permanent streams */
+	u16		permanent_stream_count;
+	u8		media_present;
+	u8		write_prot;
+	u8		protection_type;/* Data Integrity Field */
+	u8		provisioning_mode;
+	u8		zeroing_mode;
+	u8		nr_actuators;		/* Number of actuators */
+	bool		suspended;	/* Disk is suspended (stopped) */
+	unsigned	ATO : 1;	/* state of disk ATO bit */
+	unsigned	cache_override : 1; /* temp override of WCE,RCD */
+	unsigned	WCE : 1;	/* state of disk WCE bit */
+	unsigned	RCD : 1;	/* state of disk RCD bit, unused */
+	unsigned	DPOFUA : 1;	/* state of disk DPOFUA bit */
+	unsigned	first_scan : 1;
+	unsigned	lbpme : 1;
+	unsigned	lbprz : 1;
+	unsigned	lbpu : 1;
+	unsigned	lbpws : 1;
+	unsigned	lbpws10 : 1;
+	unsigned	lbpvpd : 1;
+	unsigned	ws10 : 1;
+	unsigned	ws16 : 1;
+	unsigned	rc_basis: 2;
+	unsigned	zoned: 2;
+	unsigned	urswrz : 1;
+	unsigned	security : 1;
+	unsigned	ignore_medium_access_errors : 1;
+	unsigned	rscs : 1; /* reduced stream control support */
+	unsigned	use_atomic_write_boundary : 1;
+};
+#define to_scsi_disk(obj) container_of(obj, struct scsi_disk, disk_dev)
+
+static inline struct scsi_disk *scsi_disk(struct gendisk *disk)
+{
+	return disk->private_data;
+}
+
+#define sd_printk(prefix, sdsk, fmt, a...)				\
+        (sdsk)->disk ?							\
+	      sdev_prefix_printk(prefix, (sdsk)->device,		\
+				 (sdsk)->disk->disk_name, fmt, ##a) :	\
+	      sdev_printk(prefix, (sdsk)->device, fmt, ##a)
+
+#define sd_first_printk(prefix, sdsk, fmt, a...)			\
+	do {								\
+		if ((sdsk)->first_scan)					\
+			sd_printk(prefix, sdsk, fmt, ##a);		\
+	} while (0)
+
+static inline int scsi_medium_access_command(struct scsi_cmnd *scmd)
+{
+	switch (scmd->cmnd[0]) {
+	case READ_6:
+	case READ_10:
+	case READ_12:
+	case READ_16:
+	case SYNCHRONIZE_CACHE:
+	case VERIFY:
+	case VERIFY_12:
+	case VERIFY_16:
+	case WRITE_6:
+	case WRITE_10:
+	case WRITE_12:
+	case WRITE_16:
+	case WRITE_SAME:
+	case WRITE_SAME_16:
+	case UNMAP:
+		return 1;
+	case VARIABLE_LENGTH_CMD:
+		switch (scmd->cmnd[9]) {
+		case READ_32:
+		case VERIFY_32:
+		case WRITE_32:
+		case WRITE_SAME_32:
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static inline sector_t logical_to_sectors(struct scsi_device *sdev, sector_t blocks)
+{
+	return blocks << (ilog2(sdev->sector_size) - 9);
+}
+
+static inline unsigned int logical_to_bytes(struct scsi_device *sdev, sector_t blocks)
+{
+	return blocks * sdev->sector_size;
+}
+
+static inline sector_t bytes_to_logical(struct scsi_device *sdev, unsigned int bytes)
+{
+	return bytes >> ilog2(sdev->sector_size);
+}
+
+static inline sector_t sectors_to_logical(struct scsi_device *sdev, sector_t sector)
+{
+	return sector >> (ilog2(sdev->sector_size) - 9);
+}
+
+void sd_dif_config_host(struct scsi_disk *sdkp, struct queue_limits *lim);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+
+int sd_zbc_read_zones(struct scsi_disk *sdkp, struct queue_limits *lim,
+		u8 buf[SD_BUF_SIZE]);
+int sd_zbc_revalidate_zones(struct scsi_disk *sdkp);
+blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
+					 unsigned char op, bool all);
+unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
+			     struct scsi_sense_hdr *sshdr);
+int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
+		unsigned int nr_zones, struct blk_report_zones_args *args);
+
+#else /* CONFIG_BLK_DEV_ZONED */
+
+static inline int sd_zbc_read_zones(struct scsi_disk *sdkp,
+		struct queue_limits *lim, u8 buf[SD_BUF_SIZE])
+{
+	return 0;
+}
+
+static inline int sd_zbc_revalidate_zones(struct scsi_disk *sdkp)
+{
+	return 0;
+}
+
+static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
+						       unsigned char op,
+						       bool all)
+{
+	return BLK_STS_TARGET;
+}
+
+static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd,
+			unsigned int good_bytes, struct scsi_sense_hdr *sshdr)
+{
+	return good_bytes;
+}
+
+#define sd_zbc_report_zones NULL
+
+#endif /* CONFIG_BLK_DEV_ZONED */
+
+void sd_print_sense_hdr(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr);
+void sd_print_result(const struct scsi_disk *sdkp, const char *msg, int result);
+
+#endif /* _SCSI_DISK_H */