USB: add binary API to usbmon

This patch adds a new, "binary" API in addition to the old, text API usbmon
had before. The new API allows for less CPU use, and it allows to capture
all data from a packet where old API only captured 32 bytes at most. There
are some limitations and conditions to this, e.g. in case someone constructs
a URB with 1GB of data, it's not likely to be captured, because even the
huge buffers of the new reader are finite. Nonetheless, I expect this new
capability to capture all data for all real life scenarios.

The downside is, a special user mode application is required where cat(1)
worked before. I have sample code at http://people.redhat.com/zaitcev/linux/
and Paolo Abeni is working on patching libpcap.

This patch was initially written by Paolo and later I tweaked it, and
we had a little back-and-forth. So this is a jointly authored patch, but
I am submitting this I am responsible for the bugs.

Signed-off-by: Paolo Abeni <paolo.abeni@email.it>
Signed-off-by: Pete Zaitcev <zaitcev@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

Documentation/usb/usbmon.txt

@@ -77,7 +77,7 @@ that the file size is not excessive for your favourite editor.
 
 The '1t' type data consists of a stream of events, such as URB submission,
 URB callback, submission error. Every event is a text line, which consists
-of whitespace separated words. The number of position of words may depend
+of whitespace separated words. The number or position of words may depend
 on the event type, but there is a set of words, common for all types.
 
 Here is the list of words, from left to right:
@@ -170,4 +170,152 @@ dd65f0e8 4128379808 C Bo:005:02 0 31 >
 
 * Raw binary format and API
 
-TBD
+The overall architecture of the API is about the same as the one above,
+only the events are delivered in binary format. Each event is sent in
+the following structure (its name is made up, so that we can refer to it):
+
+struct usbmon_packet {
+	u64 id;			/*  0: URB ID - from submission to callback */
+	unsigned char type;	/*  8: Same as text; extensible. */
+	unsigned char xfer_type; /*    ISO (0), Intr, Control, Bulk (3) */
+	unsigned char epnum;	/*     Endpoint number and transfer direction */
+	unsigned char devnum;	/*     Device address */
+	u16 busnum;		/* 12: Bus number */
+	char flag_setup;	/* 14: Same as text */
+	char flag_data;		/* 15: Same as text; Binary zero is OK. */
+	s64 ts_sec;		/* 16: gettimeofday */
+	s32 ts_usec;		/* 24: gettimeofday */
+	int status;		/* 28: */
+	unsigned int length;	/* 32: Length of data (submitted or actual) */
+	unsigned int len_cap;	/* 36: Delivered length */
+	unsigned char setup[8];	/* 40: Only for Control 'S' */
+};				/* 48 bytes total */
+
+These events can be received from a character device by reading with read(2),
+with an ioctl(2), or by accessing the buffer with mmap.
+
+The character device is usually called /dev/usbmonN, where N is the USB bus
+number. Number zero (/dev/usbmon0) is special and means "all buses".
+However, this feature is not implemented yet. Note that specific naming
+policy is set by your Linux distribution.
+
+If you create /dev/usbmon0 by hand, make sure that it is owned by root
+and has mode 0600. Otherwise, unpriviledged users will be able to snoop
+keyboard traffic.
+
+The following ioctl calls are available, with MON_IOC_MAGIC 0x92:
+
+ MON_IOCQ_URB_LEN, defined as _IO(MON_IOC_MAGIC, 1)
+
+This call returns the length of data in the next event. Note that majority of
+events contain no data, so if this call returns zero, it does not mean that
+no events are available.
+
+ MON_IOCG_STATS, defined as _IOR(MON_IOC_MAGIC, 3, struct mon_bin_stats)
+
+The argument is a pointer to the following structure:
+
+struct mon_bin_stats {
+	u32 queued;
+	u32 dropped;
+};
+
+The member "queued" refers to the number of events currently queued in the
+buffer (and not to the number of events processed since the last reset).
+
+The member "dropped" is the number of events lost since the last call
+to MON_IOCG_STATS.
+
+ MON_IOCT_RING_SIZE, defined as _IO(MON_IOC_MAGIC, 4)
+
+This call sets the buffer size. The argument is the size in bytes.
+The size may be rounded down to the next chunk (or page). If the requested
+size is out of [unspecified] bounds for this kernel, the call fails with
+-EINVAL.
+
+ MON_IOCQ_RING_SIZE, defined as _IO(MON_IOC_MAGIC, 5)
+
+This call returns the current size of the buffer in bytes.
+
+ MON_IOCX_GET, defined as _IOW(MON_IOC_MAGIC, 6, struct mon_get_arg)
+
+This call waits for events to arrive if none were in the kernel buffer,
+then returns the first event. Its argument is a pointer to the following
+structure:
+
+struct mon_get_arg {
+	struct usbmon_packet *hdr;
+	void *data;
+	size_t alloc;		/* Length of data (can be zero) */
+};
+
+Before the call, hdr, data, and alloc should be filled. Upon return, the area
+pointed by hdr contains the next event structure, and the data buffer contains
+the data, if any. The event is removed from the kernel buffer.
+
+ MON_IOCX_MFETCH, defined as _IOWR(MON_IOC_MAGIC, 7, struct mon_mfetch_arg)
+
+This ioctl is primarily used when the application accesses the buffer
+with mmap(2). Its argument is a pointer to the following structure:
+
+struct mon_mfetch_arg {
+	uint32_t *offvec;	/* Vector of events fetched */
+	uint32_t nfetch;	/* Number of events to fetch (out: fetched) */
+	uint32_t nflush;	/* Number of events to flush */
+};
+
+The ioctl operates in 3 stages.
+
+First, it removes and discards up to nflush events from the kernel buffer.
+The actual number of events discarded is returned in nflush.
+
+Second, it waits for an event to be present in the buffer, unless the pseudo-
+device is open with O_NONBLOCK.
+
+Third, it extracts up to nfetch offsets into the mmap buffer, and stores
+them into the offvec. The actual number of event offsets is stored into
+the nfetch.
+
+ MON_IOCH_MFLUSH, defined as _IO(MON_IOC_MAGIC, 8)
+
+This call removes a number of events from the kernel buffer. Its argument
+is the number of events to remove. If the buffer contains fewer events
+than requested, all events present are removed, and no error is reported.
+This works when no events are available too.
+
+ FIONBIO
+
+The ioctl FIONBIO may be implemented in the future, if there's a need.
+
+In addition to ioctl(2) and read(2), the special file of binary API can
+be polled with select(2) and poll(2). But lseek(2) does not work.
+
+* Memory-mapped access of the kernel buffer for the binary API
+
+The basic idea is simple:
+
+To prepare, map the buffer by getting the current size, then using mmap(2).
+Then, execute a loop similar to the one written in pseudo-code below:
+
+   struct mon_mfetch_arg fetch;
+   struct usbmon_packet *hdr;
+   int nflush = 0;
+   for (;;) {
+      fetch.offvec = vec; // Has N 32-bit words
+      fetch.nfetch = N;   // Or less than N
+      fetch.nflush = nflush;
+      ioctl(fd, MON_IOCX_MFETCH, &fetch);   // Process errors, too
+      nflush = fetch.nfetch;       // This many packets to flush when done
+      for (i = 0; i < nflush; i++) {
+         hdr = (struct ubsmon_packet *) &mmap_area[vec[i]];
+         if (hdr->type == '@')     // Filler packet
+            continue;
+         caddr_t data = &mmap_area[vec[i]] + 64;
+         process_packet(hdr, data);
+      }
+   }
+
+Thus, the main idea is to execute only one ioctl per N events.
+
+Although the buffer is circular, the returned headers and data do not cross
+the end of the buffer, so the above pseudo-code does not need any gathering.

drivers/usb/mon/Makefile

@@ -2,7 +2,7 @@
 # Makefile for USB Core files and filesystem
 #
 
-usbmon-objs	:= mon_main.o mon_stat.o mon_text.o mon_dma.o
+usbmon-objs	:= mon_main.o mon_stat.o mon_text.o mon_bin.o mon_dma.o
 
 # This does not use CONFIG_USB_MON because we want this to use a tristate.
 obj-$(CONFIG_USB)	+= usbmon.o

drivers/usb/mon/mon_dma.c

@@ -48,6 +48,36 @@ char mon_dmapeek(unsigned char *dst, dma_addr_t dma_addr, int len)
 	local_irq_restore(flags);
 	return 0;
 }
+
+void mon_dmapeek_vec(const struct mon_reader_bin *rp,
+    unsigned int offset, dma_addr_t dma_addr, unsigned int length)
+{
+	unsigned long flags;
+	unsigned int step_len;
+	struct page *pg;
+	unsigned char *map;
+	unsigned long page_off, page_len;
+
+	local_irq_save(flags);
+	while (length) {
+		/* compute number of bytes we are going to copy in this page */
+		step_len = length;
+		page_off = dma_addr & (PAGE_SIZE-1);
+		page_len = PAGE_SIZE - page_off;
+		if (page_len < step_len)
+			step_len = page_len;
+
+		/* copy data and advance pointers */
+		pg = phys_to_page(dma_addr);
+		map = kmap_atomic(pg, KM_IRQ0);
+		offset = mon_copy_to_buff(rp, offset, map + page_off, step_len);
+		kunmap_atomic(map, KM_IRQ0);
+		dma_addr += step_len;
+		length -= step_len;
+	}
+	local_irq_restore(flags);
+}
+
 #endif /* __i386__ */
 
 #ifndef MON_HAS_UNMAP
@@ -55,4 +85,11 @@ char mon_dmapeek(unsigned char *dst, dma_addr_t dma_addr, int len)
 {
 	return 'D';
 }
-#endif
+
+void mon_dmapeek_vec(const struct mon_reader_bin *rp,
+    unsigned int offset, dma_addr_t dma_addr, unsigned int length)
+{
+	;
+}
+
+#endif /* MON_HAS_UNMAP */

drivers/usb/mon/mon_main.c

@@ -9,7 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/usb.h>
-#include <linux/debugfs.h>
 #include <linux/smp_lock.h>
 #include <linux/notifier.h>
 #include <linux/mutex.h>
@@ -22,11 +21,10 @@ static void mon_complete(struct usb_bus *ubus, struct urb *urb);
 static void mon_stop(struct mon_bus *mbus);
 static void mon_dissolve(struct mon_bus *mbus, struct usb_bus *ubus);
 static void mon_bus_drop(struct kref *r);
-static void mon_bus_init(struct dentry *mondir, struct usb_bus *ubus);
+static void mon_bus_init(struct usb_bus *ubus);
 
 DEFINE_MUTEX(mon_lock);
 
-static struct dentry *mon_dir;		/* /dbg/usbmon */
 static LIST_HEAD(mon_buses);		/* All buses we know: struct mon_bus */
 
 /*
@@ -200,7 +198,7 @@ static void mon_stop(struct mon_bus *mbus)
  */
 static void mon_bus_add(struct usb_bus *ubus)
 {
-	mon_bus_init(mon_dir, ubus);
+	mon_bus_init(ubus);
 }
 
 /*
@@ -212,8 +210,8 @@ static void mon_bus_remove(struct usb_bus *ubus)
 
 	mutex_lock(&mon_lock);
 	list_del(&mbus->bus_link);
-	debugfs_remove(mbus->dent_t);
+	if (mbus->text_inited)
-	debugfs_remove(mbus->dent_s);
+		mon_text_del(mbus);
 
 	mon_dissolve(mbus, ubus);
 	kref_put(&mbus->ref, mon_bus_drop);
@@ -281,13 +279,9 @@ static void mon_bus_drop(struct kref *r)
  *  - refcount USB bus struct
  *  - link
  */
-static void mon_bus_init(struct dentry *mondir, struct usb_bus *ubus)
+static void mon_bus_init(struct usb_bus *ubus)
 {
-	struct dentry *d;
 	struct mon_bus *mbus;
-	enum { NAMESZ = 10 };
-	char name[NAMESZ];
-	int rc;
 
 	if ((mbus = kzalloc(sizeof(struct mon_bus), GFP_KERNEL)) == NULL)
 		goto err_alloc;
@@ -303,57 +297,54 @@ static void mon_bus_init(struct dentry *mondir, struct usb_bus *ubus)
 	ubus->mon_bus = mbus;
 	mbus->uses_dma = ubus->uses_dma;
 
-	rc = snprintf(name, NAMESZ, "%dt", ubus->busnum);
+	mbus->text_inited = mon_text_add(mbus, ubus);
-	if (rc <= 0 || rc >= NAMESZ)
+	// mon_bin_add(...)
-		goto err_print_t;
-	d = debugfs_create_file(name, 0600, mondir, mbus, &mon_fops_text);
-	if (d == NULL)
-		goto err_create_t;
-	mbus->dent_t = d;
-
-	rc = snprintf(name, NAMESZ, "%ds", ubus->busnum);
-	if (rc <= 0 || rc >= NAMESZ)
-		goto err_print_s;
-	d = debugfs_create_file(name, 0600, mondir, mbus, &mon_fops_stat);
-	if (d == NULL)
-		goto err_create_s;
-	mbus->dent_s = d;
 
 	mutex_lock(&mon_lock);
 	list_add_tail(&mbus->bus_link, &mon_buses);
 	mutex_unlock(&mon_lock);
 	return;
 
-err_create_s:
-err_print_s:
-	debugfs_remove(mbus->dent_t);
-err_create_t:
-err_print_t:
-	kfree(mbus);
 err_alloc:
 	return;
 }
 
+/*
+ * Search a USB bus by number. Notice that USB bus numbers start from one,
+ * which we may later use to identify "all" with zero.
+ *
+ * This function must be called with mon_lock held.
+ *
+ * This is obviously inefficient and may be revised in the future.
+ */
+struct mon_bus *mon_bus_lookup(unsigned int num)
+{
+	struct list_head *p;
+	struct mon_bus *mbus;
+
+	list_for_each (p, &mon_buses) {
+		mbus = list_entry(p, struct mon_bus, bus_link);
+		if (mbus->u_bus->busnum == num) {
+			return mbus;
+		}
+	}
+	return NULL;
+}
+
 static int __init mon_init(void)
 {
 	struct usb_bus *ubus;
-	struct dentry *mondir;
+	int rc;
 
-	mondir = debugfs_create_dir("usbmon", NULL);
+	if ((rc = mon_text_init()) != 0)
-	if (IS_ERR(mondir)) {
+		goto err_text;
-		printk(KERN_NOTICE TAG ": debugfs is not available\n");
+	if ((rc = mon_bin_init()) != 0)
-		return -ENODEV;
+		goto err_bin;
-	}
-	if (mondir == NULL) {
-		printk(KERN_NOTICE TAG ": unable to create usbmon directory\n");
-		return -ENODEV;
-	}
-	mon_dir = mondir;
 
 	if (usb_mon_register(&mon_ops_0) != 0) {
 		printk(KERN_NOTICE TAG ": unable to register with the core\n");
-		debugfs_remove(mondir);
+		rc = -ENODEV;
-		return -ENODEV;
+		goto err_reg;
 	}
 	// MOD_INC_USE_COUNT(which_module?);
 
@@ -361,10 +352,17 @@ static int __init mon_init(void)
 
 	mutex_lock(&usb_bus_list_lock);
 	list_for_each_entry (ubus, &usb_bus_list, bus_list) {
-		mon_bus_init(mondir, ubus);
+		mon_bus_init(ubus);
 	}
 	mutex_unlock(&usb_bus_list_lock);
 	return 0;
+
+err_reg:
+	mon_bin_exit();
+err_bin:
+	mon_text_exit();
+err_text:
+	return rc;
 }
 
 static void __exit mon_exit(void)
@@ -381,8 +379,8 @@ static void __exit mon_exit(void)
 		mbus = list_entry(p, struct mon_bus, bus_link);
 		list_del(p);
 
-		debugfs_remove(mbus->dent_t);
+		if (mbus->text_inited)
-		debugfs_remove(mbus->dent_s);
+			mon_text_del(mbus);
 
 		/*
 		 * This never happens, because the open/close paths in
@@ -401,7 +399,8 @@ static void __exit mon_exit(void)
 	}
 	mutex_unlock(&mon_lock);
 
-	debugfs_remove(mon_dir);
+	mon_text_exit();
+	mon_bin_exit();
 }
 
 module_init(mon_init);

drivers/usb/mon/mon_text.c

@@ -9,6 +9,7 @@
 #include <linux/usb.h>
 #include <linux/time.h>
 #include <linux/mutex.h>
+#include <linux/debugfs.h>
 #include <asm/uaccess.h>
 
 #include "usb_mon.h"
@@ -63,6 +64,8 @@ struct mon_reader_text {
 	char slab_name[SLAB_NAME_SZ];
 };
 
+static struct dentry *mon_dir;		/* Usually /sys/kernel/debug/usbmon */
+
 static void mon_text_ctor(void *, struct kmem_cache *, unsigned long);
 
 /*
@@ -436,7 +439,7 @@ static int mon_text_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-const struct file_operations mon_fops_text = {
+static const struct file_operations mon_fops_text = {
 	.owner =	THIS_MODULE,
 	.open =		mon_text_open,
 	.llseek =	no_llseek,
@@ -447,6 +450,47 @@ const struct file_operations mon_fops_text = {
 	.release =	mon_text_release,
 };
 
+int mon_text_add(struct mon_bus *mbus, const struct usb_bus *ubus)
+{
+	struct dentry *d;
+	enum { NAMESZ = 10 };
+	char name[NAMESZ];
+	int rc;
+
+	rc = snprintf(name, NAMESZ, "%dt", ubus->busnum);
+	if (rc <= 0 || rc >= NAMESZ)
+		goto err_print_t;
+	d = debugfs_create_file(name, 0600, mon_dir, mbus, &mon_fops_text);
+	if (d == NULL)
+		goto err_create_t;
+	mbus->dent_t = d;
+
+	/* XXX The stats do not belong to here (text API), but oh well... */
+	rc = snprintf(name, NAMESZ, "%ds", ubus->busnum);
+	if (rc <= 0 || rc >= NAMESZ)
+		goto err_print_s;
+	d = debugfs_create_file(name, 0600, mon_dir, mbus, &mon_fops_stat);
+	if (d == NULL)
+		goto err_create_s;
+	mbus->dent_s = d;
+
+	return 1;
+
+err_create_s:
+err_print_s:
+	debugfs_remove(mbus->dent_t);
+	mbus->dent_t = NULL;
+err_create_t:
+err_print_t:
+	return 0;
+}
+
+void mon_text_del(struct mon_bus *mbus)
+{
+	debugfs_remove(mbus->dent_t);
+	debugfs_remove(mbus->dent_s);
+}
+
 /*
  * Slab interface: constructor.
  */
@@ -459,3 +503,24 @@ static void mon_text_ctor(void *mem, struct kmem_cache *slab, unsigned long sfla
 	memset(mem, 0xe5, sizeof(struct mon_event_text));
 }
 
+int __init mon_text_init(void)
+{
+	struct dentry *mondir;
+
+	mondir = debugfs_create_dir("usbmon", NULL);
+	if (IS_ERR(mondir)) {
+		printk(KERN_NOTICE TAG ": debugfs is not available\n");
+		return -ENODEV;
+	}
+	if (mondir == NULL) {
+		printk(KERN_NOTICE TAG ": unable to create usbmon directory\n");
+		return -ENODEV;
+	}
+	mon_dir = mondir;
+	return 0;
+}
+
+void __exit mon_text_exit(void)
+{
+	debugfs_remove(mon_dir);
+}

drivers/usb/mon/usb_mon.h

@@ -17,9 +17,11 @@
 struct mon_bus {
 	struct list_head bus_link;
 	spinlock_t lock;
+	struct usb_bus *u_bus;
+
+	int text_inited;
 	struct dentry *dent_s;		/* Debugging file */
 	struct dentry *dent_t;		/* Text interface file */
-	struct usb_bus *u_bus;
 	int uses_dma;
 
 	/* Ref */
@@ -48,13 +50,35 @@ struct mon_reader {
 void mon_reader_add(struct mon_bus *mbus, struct mon_reader *r);
 void mon_reader_del(struct mon_bus *mbus, struct mon_reader *r);
 
+struct mon_bus *mon_bus_lookup(unsigned int num);
+
+int /*bool*/ mon_text_add(struct mon_bus *mbus, const struct usb_bus *ubus);
+void mon_text_del(struct mon_bus *mbus);
+// void mon_bin_add(struct mon_bus *);
+
+int __init mon_text_init(void);
+void __exit mon_text_exit(void);
+int __init mon_bin_init(void);
+void __exit mon_bin_exit(void);
+
 /*
- */
+ * DMA interface.
+ *
+ * XXX The vectored side needs a serious re-thinking. Abstracting vectors,
+ * like in Paolo's original patch, produces a double pkmap. We need an idea.
+*/
 extern char mon_dmapeek(unsigned char *dst, dma_addr_t dma_addr, int len);
 
+struct mon_reader_bin;
+extern void mon_dmapeek_vec(const struct mon_reader_bin *rp,
+    unsigned int offset, dma_addr_t dma_addr, unsigned int len);
+extern unsigned int mon_copy_to_buff(const struct mon_reader_bin *rp,
+    unsigned int offset, const unsigned char *from, unsigned int len);
+
+/*
+ */
 extern struct mutex mon_lock;
 
-extern const struct file_operations mon_fops_text;
 extern const struct file_operations mon_fops_stat;
 
 #endif /* __USB_MON_H */