* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: set i_size properly when fallocating and we already
btrfs: unlock on error in btrfs_file_llseek()
btrfs: btrfs_permission's RO check shouldn't apply to device nodes
Btrfs: truncate pages from clone ioctl target range
Btrfs: fix uninitialized sync_pending
Btrfs: fix wrong free space information
btrfs: memory leak in btrfs_add_inode_defrag()
Btrfs: use plain page_address() in header fields setget functions
Btrfs: forced readonly when btrfs_drop_snapshot() fails
Btrfs: check if there is enough space for balancing smarter
Btrfs: fix a bug of balance on full multi-disk partitions
Btrfs: fix an oops of log replay
Btrfs: detect wether a device supports discard
Btrfs: force unplugs when switching from high to regular priority bios
bridges). In order to ensure that all the data has arrived in memory,
the interrupt handler must read a register on the device which raised
the interrupt. PCI transaction ordering rules require that all the data
-arrives in memory before the value can be returned from the register.
+arrive in memory before the value may be returned from the register.
Using MSIs avoids this problem as the interrupt-generating write cannot
pass the data writes, so by the time the interrupt is raised, the driver
knows that all the data has arrived in memory.
int pci_enable_msi(struct pci_dev *dev)
-A successful call will allocate ONE interrupt to the device, regardless
-of how many MSIs the device supports. The device will be switched from
+A successful call allocates ONE interrupt to the device, regardless
+of how many MSIs the device supports. The device is switched from
pin-based interrupt mode to MSI mode. The dev->irq number is changed
-to a new number which represents the message signaled interrupt.
-This function should be called before the driver calls request_irq()
-since enabling MSIs disables the pin-based IRQ and the driver will not
-receive interrupts on the old interrupt.
+to a new number which represents the message signaled interrupt;
+consequently, this function should be called before the driver calls
+request_irq(), because an MSI is delivered via a vector that is
+different from the vector of a pin-based interrupt.
4.2.2 pci_enable_msi_block
If this function returns a negative number, it indicates an error and
the driver should not attempt to request any more MSI interrupts for
-this device. If this function returns a positive number, it will be
-less than 'count' and indicate the number of interrupts that could have
-been allocated. In neither case will the irq value have been
-updated, nor will the device have been switched into MSI mode.
+this device. If this function returns a positive number, it is
+less than 'count' and indicates the number of interrupts that could have
+been allocated. In neither case is the irq value updated or the device
+switched into MSI mode.
The device driver must decide what action to take if
-pci_enable_msi_block() returns a value less than the number asked for.
-Some devices can make use of fewer interrupts than the maximum they
-request; in this case the driver should call pci_enable_msi_block()
+pci_enable_msi_block() returns a value less than the number requested.
+For instance, the driver could still make use of fewer interrupts;
+in this case the driver should call pci_enable_msi_block()
again. Note that it is not guaranteed to succeed, even when the
'count' has been reduced to the value returned from a previous call to
pci_enable_msi_block(). This is because there are multiple constraints
on the number of vectors that can be allocated; pci_enable_msi_block()
-will return as soon as it finds any constraint that doesn't allow the
+returns as soon as it finds any constraint that doesn't allow the
call to succeed.
4.2.3 pci_disable_msi
interrupt(s). The interrupt may subsequently be assigned to another
device, so drivers should not cache the value of dev->irq.
-A device driver must always call free_irq() on the interrupt(s)
-for which it has called request_irq() before calling this function.
-Failure to do so will result in a BUG_ON(), the device will be left with
-MSI enabled and will leak its vector.
+Before calling this function, a device driver must always call free_irq()
+on any interrupt for which it previously called request_irq().
+Failure to do so results in a BUG_ON(), leaving the device with
+MSI enabled and thus leaking its vector.
4.3 Using MSI-X
};
This allows for the device to use these interrupts in a sparse fashion;
-for example it could use interrupts 3 and 1027 and allocate only a
+for example, it could use interrupts 3 and 1027 and yet allocate only a
two-element array. The driver is expected to fill in the 'entry' value
-in each element of the array to indicate which entries it wants the kernel
-to assign interrupts for. It is invalid to fill in two entries with the
+in each element of the array to indicate for which entries the kernel
+should assign interrupts; it is invalid to fill in two entries with the
same number.
4.3.1 pci_enable_msix
Calling this function asks the PCI subsystem to allocate 'nvec' MSIs.
The 'entries' argument is a pointer to an array of msix_entry structs
which should be at least 'nvec' entries in size. On success, the
-function will return 0 and the device will have been switched into
-MSI-X interrupt mode. The 'vector' elements in each entry will have
-been filled in with the interrupt number. The driver should then call
-request_irq() for each 'vector' that it decides to use.
+device is switched into MSI-X mode and the function returns 0.
+The 'vector' member in each entry is populated with the interrupt number;
+the driver should then call request_irq() for each 'vector' that it
+decides to use. The device driver is responsible for keeping track of the
+interrupts assigned to the MSI-X vectors so it can free them again later.
If this function returns a negative number, it indicates an error and
the driver should not attempt to allocate any more MSI-X interrupts for
This function, in contrast with pci_enable_msi(), does not adjust
dev->irq. The device will not generate interrupts for this interrupt
-number once MSI-X is enabled. The device driver is responsible for
-keeping track of the interrupts assigned to the MSI-X vectors so it can
-free them again later.
+number once MSI-X is enabled.
Device drivers should normally call this function once per device
during the initialization phase.
-It is ideal if drivers can cope with a variable number of MSI-X interrupts,
+It is ideal if drivers can cope with a variable number of MSI-X interrupts;
there are many reasons why the platform may not be able to provide the
-exact number a driver asks for.
+exact number that a driver asks for.
A request loop to achieve that might look like:
void pci_disable_msix(struct pci_dev *dev)
-This API should be used to undo the effect of pci_enable_msix(). It frees
+This function should be used to undo the effect of pci_enable_msix(). It frees
the previously allocated message signaled interrupts. The interrupts may
subsequently be assigned to another device, so drivers should not cache
the value of the 'vector' elements over a call to pci_disable_msix().
-A device driver must always call free_irq() on the interrupt(s)
-for which it has called request_irq() before calling this function.
-Failure to do so will result in a BUG_ON(), the device will be left with
-MSI enabled and will leak its vector.
+Before calling this function, a device driver must always call free_irq()
+on any interrupt for which it previously called request_irq().
+Failure to do so results in a BUG_ON(), leaving the device with
+MSI-X enabled and thus leaking its vector.
4.3.3 The MSI-X Table
4.4 Handling devices implementing both MSI and MSI-X capabilities
If a device implements both MSI and MSI-X capabilities, it can
-run in either MSI mode or MSI-X mode but not both simultaneously.
+run in either MSI mode or MSI-X mode, but not both simultaneously.
This is a requirement of the PCI spec, and it is enforced by the
PCI layer. Calling pci_enable_msi() when MSI-X is already enabled or
-pci_enable_msix() when MSI is already enabled will result in an error.
+pci_enable_msix() when MSI is already enabled results in an error.
If a device driver wishes to switch between MSI and MSI-X at runtime,
it must first quiesce the device, then switch it back to pin-interrupt
mode, before calling pci_enable_msi() or pci_enable_msix() and resuming
above, MSI-X supports any number of interrupts between 1 and 2048.
In constrast, MSI is restricted to a maximum of 32 interrupts (and
must be a power of two). In addition, the MSI interrupt vectors must
-be allocated consecutively, so the system may not be able to allocate
+be allocated consecutively, so the system might not be able to allocate
as many vectors for MSI as it could for MSI-X. On some platforms, MSI
interrupts must all be targeted at the same set of CPUs whereas MSI-X
interrupts can all be targeted at different CPUs.
Using 'lspci -v' (as root) may show some devices with "MSI", "Message
Signalled Interrupts" or "MSI-X" capabilities. Each of these capabilities
-has an 'Enable' flag which will be followed with either "+" (enabled)
+has an 'Enable' flag which is followed with either "+" (enabled)
or "-" (disabled).
Some host chipsets simply don't support MSIs properly. If we're
lucky, the manufacturer knows this and has indicated it in the ACPI
-FADT table. In this case, Linux will automatically disable MSIs.
+FADT table. In this case, Linux automatically disables MSIs.
Some boards don't include this information in the table and so we have
to detect them ourselves. The complete list of these is found near the
quirk_disable_all_msi() function in drivers/pci/quirks.c.
PCI configuration space (especially the Hypertransport chipsets such
as the nVidia nForce and Serverworks HT2000). As with host chipsets,
Linux mostly knows about them and automatically enables MSIs if it can.
-If you have a bridge which Linux doesn't yet know about, you can enable
+If you have a bridge unknown to Linux, you can enable
MSIs in configuration space using whatever method you know works, then
enable MSIs on that bridge by doing:
0000:00:0e.0).
To disable MSIs, echo 0 instead of 1. Changing this value should be
-done with caution as it can break interrupt handling for all devices
+done with caution as it could break interrupt handling for all devices
below this bridge.
Again, please notify linux-pci@vger.kernel.org of any bridges that need
5.3. Disabling MSIs on a single device
Some devices are known to have faulty MSI implementations. Usually this
-is handled in the individual device driver but occasionally it's necessary
+is handled in the individual device driver, but occasionally it's necessary
to handle this with a quirk. Some drivers have an option to disable use
of MSI. While this is a convenient workaround for the driver author,
it is not good practise, and should not be emulated.
have enabled CONFIG_PCI_MSI.
Then, 'lspci -t' gives the list of bridges above a device. Reading
-/sys/bus/pci/devices/*/msi_bus will tell you whether MSI are enabled (1)
+/sys/bus/pci/devices/*/msi_bus will tell you whether MSIs are enabled (1)
or disabled (0). If 0 is found in any of the msi_bus files belonging
to bridges between the PCI root and the device, MSIs are disabled.
- Extremely simple hypervisor for experimental/educational use.
uml/
- User Mode Linux, builds/runs Linux kernel as a userspace program.
+virtio.txt
+ - Text version of draft virtio spec.
+ See http://ozlabs.org/~rusty/virtio-spec
/* We use a simple helper to copy the arguments separated by spaces. */
concat((char *)(boot + 1), argv+optind+2);
+ /* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */
+ boot->hdr.kernel_alignment = 0x1000000;
+
/* Boot protocol version: 2.07 supports the fields for lguest. */
boot->hdr.version = 0x207;
--- /dev/null
+[Generated file: see http://ozlabs.org/~rusty/virtio-spec/]
+Virtio PCI Card Specification
+v0.9.1 DRAFT
+-
+
+Rusty Russell <rusty@rustcorp.com.au>IBM Corporation (Editor)
+
+2011 August 1.
+
+Purpose and Description
+
+This document describes the specifications of the “virtio” family
+of PCI[LaTeX Command: nomenclature] devices. These are devices
+are found in virtual environments[LaTeX Command: nomenclature],
+yet by design they are not all that different from physical PCI
+devices, and this document treats them as such. This allows the
+guest to use standard PCI drivers and discovery mechanisms.
+
+The purpose of virtio and this specification is that virtual
+environments and guests should have a straightforward, efficient,
+standard and extensible mechanism for virtual devices, rather
+than boutique per-environment or per-OS mechanisms.
+
+ Straightforward: Virtio PCI devices use normal PCI mechanisms
+ of interrupts and DMA which should be familiar to any device
+ driver author. There is no exotic page-flipping or COW
+ mechanism: it's just a PCI device.[footnote:
+This lack of page-sharing implies that the implementation of the
+device (e.g. the hypervisor or host) needs full access to the
+guest memory. Communication with untrusted parties (i.e.
+inter-guest communication) requires copying.
+]
+
+ Efficient: Virtio PCI devices consist of rings of descriptors
+ for input and output, which are neatly separated to avoid cache
+ effects from both guest and device writing to the same cache
+ lines.
+
+ Standard: Virtio PCI makes no assumptions about the environment
+ in which it operates, beyond supporting PCI. In fact the virtio
+ devices specified in the appendices do not require PCI at all:
+ they have been implemented on non-PCI buses.[footnote:
+The Linux implementation further separates the PCI virtio code
+from the specific virtio drivers: these drivers are shared with
+the non-PCI implementations (currently lguest and S/390).
+]
+
+ Extensible: Virtio PCI devices contain feature bits which are
+ acknowledged by the guest operating system during device setup.
+ This allows forwards and backwards compatibility: the device
+ offers all the features it knows about, and the driver
+ acknowledges those it understands and wishes to use.
+
+ Virtqueues
+
+The mechanism for bulk data transport on virtio PCI devices is
+pretentiously called a virtqueue. Each device can have zero or
+more virtqueues: for example, the network device has one for
+transmit and one for receive.
+
+Each virtqueue occupies two or more physically-contiguous pages
+(defined, for the purposes of this specification, as 4096 bytes),
+and consists of three parts:
+
+
++-------------------+-----------------------------------+-----------+
+| Descriptor Table | Available Ring (padding) | Used Ring |
++-------------------+-----------------------------------+-----------+
+
+
+When the driver wants to send buffers to the device, it puts them
+in one or more slots in the descriptor table, and writes the
+descriptor indices into the available ring. It then notifies the
+device. When the device has finished with the buffers, it writes
+the descriptors into the used ring, and sends an interrupt.
+
+Specification
+
+ PCI Discovery
+
+Any PCI device with Vendor ID 0x1AF4, and Device ID 0x1000
+through 0x103F inclusive is a virtio device[footnote:
+The actual value within this range is ignored
+]. The device must also have a Revision ID of 0 to match this
+specification.
+
+The Subsystem Device ID indicates which virtio device is
+supported by the device. The Subsystem Vendor ID should reflect
+the PCI Vendor ID of the environment (it's currently only used
+for informational purposes by the guest).
+
+
++----------------------+--------------------+---------------+
+| Subsystem Device ID | Virtio Device | Specification |
++----------------------+--------------------+---------------+
++----------------------+--------------------+---------------+
+| 1 | network card | Appendix C |
++----------------------+--------------------+---------------+
+| 2 | block device | Appendix D |
++----------------------+--------------------+---------------+
+| 3 | console | Appendix E |
++----------------------+--------------------+---------------+
+| 4 | entropy source | Appendix F |
++----------------------+--------------------+---------------+
+| 5 | memory ballooning | Appendix G |
++----------------------+--------------------+---------------+
+| 6 | ioMemory | - |
++----------------------+--------------------+---------------+
+| 9 | 9P transport | - |
++----------------------+--------------------+---------------+
+
+
+ Device Configuration
+
+To configure the device, we use the first I/O region of the PCI
+device. This contains a virtio header followed by a
+device-specific region.
+
+There may be different widths of accesses to the I/O region; the “
+natural” access method for each field in the virtio header must
+be used (i.e. 32-bit accesses for 32-bit fields, etc), but the
+device-specific region can be accessed using any width accesses,
+and should obtain the same results.
+
+Note that this is possible because while the virtio header is PCI
+(i.e. little) endian, the device-specific region is encoded in
+the native endian of the guest (where such distinction is
+applicable).
+
+ Device Initialization Sequence
+
+We start with an overview of device initialization, then expand
+on the details of the device and how each step is preformed.
+
+ Reset the device. This is not required on initial start up.
+
+ The ACKNOWLEDGE status bit is set: we have noticed the device.
+
+ The DRIVER status bit is set: we know how to drive the device.
+
+ Device-specific setup, including reading the Device Feature
+ Bits, discovery of virtqueues for the device, optional MSI-X
+ setup, and reading and possibly writing the virtio
+ configuration space.
+
+ The subset of Device Feature Bits understood by the driver is
+ written to the device.
+
+ The DRIVER_OK status bit is set.
+
+ The device can now be used (ie. buffers added to the
+ virtqueues)[footnote:
+Historically, drivers have used the device before steps 5 and 6.
+This is only allowed if the driver does not use any features
+which would alter this early use of the device.
+]
+
+If any of these steps go irrecoverably wrong, the guest should
+set the FAILED status bit to indicate that it has given up on the
+device (it can reset the device later to restart if desired).
+
+We now cover the fields required for general setup in detail.
+
+ Virtio Header
+
+The virtio header looks as follows:
+
+
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+| Bits || 32 | 32 | 32 | 16 | 16 | 16 | 8 | 8 |
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+| Read/Write || R | R+W | R+W | R | R+W | R+W | R+W | R |
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+| Purpose || Device | Guest | Queue | Queue | Queue | Queue | Device | ISR |
+| || Features bits 0:31 | Features bits 0:31 | Address | Size | Select | Notify | Status | Status |
++------------++---------------------+---------------------+----------+--------+---------+---------+---------+--------+
+
+
+If MSI-X is enabled for the device, two additional fields
+immediately follow this header:
+
+
++------------++----------------+--------+
+| Bits || 16 | 16 |
+ +----------------+--------+
++------------++----------------+--------+
+| Read/Write || R+W | R+W |
++------------++----------------+--------+
+| Purpose || Configuration | Queue |
+| (MSI-X) || Vector | Vector |
++------------++----------------+--------+
+
+
+Finally, if feature bits (VIRTIO_F_FEATURES_HI) this is
+immediately followed by two additional fields:
+
+
++------------++----------------------+----------------------
+| Bits || 32 | 32
++------------++----------------------+----------------------
+| Read/Write || R | R+W
++------------++----------------------+----------------------
+| Purpose || Device | Guest
+| || Features bits 32:63 | Features bits 32:63
++------------++----------------------+----------------------
+
+
+Immediately following these general headers, there may be
+device-specific headers:
+
+
++------------++--------------------+
+| Bits || Device Specific |
+ +--------------------+
++------------++--------------------+
+| Read/Write || Device Specific |
++------------++--------------------+
+| Purpose || Device Specific... |
+| || |
++------------++--------------------+
+
+
+ Device Status
+
+The Device Status field is updated by the guest to indicate its
+progress. This provides a simple low-level diagnostic: it's most
+useful to imagine them hooked up to traffic lights on the console
+indicating the status of each device.
+
+The device can be reset by writing a 0 to this field, otherwise
+at least one bit should be set:
+
+ ACKNOWLEDGE (1) Indicates that the guest OS has found the
+ device and recognized it as a valid virtio device.
+
+ DRIVER (2) Indicates that the guest OS knows how to drive the
+ device. Under Linux, drivers can be loadable modules so there
+ may be a significant (or infinite) delay before setting this
+ bit.
+
+ DRIVER_OK (3) Indicates that the driver is set up and ready to
+ drive the device.
+
+ FAILED (8) Indicates that something went wrong in the guest,
+ and it has given up on the device. This could be an internal
+ error, or the driver didn't like the device for some reason, or
+ even a fatal error during device operation. The device must be
+ reset before attempting to re-initialize.
+
+ Feature Bits
+
+The least significant 31 bits of the first configuration field
+indicates the features that the device supports (the high bit is
+reserved, and will be used to indicate the presence of future
+feature bits elsewhere). If more than 31 feature bits are
+supported, the device indicates so by setting feature bit 31 (see
+[cha:Reserved-Feature-Bits]). The bits are allocated as follows:
+
+ 0 to 23 Feature bits for the specific device type
+
+ 24 to 40 Feature bits reserved for extensions to the queue and
+ feature negotiation mechanisms
+
+ 41 to 63 Feature bits reserved for future extensions
+
+For example, feature bit 0 for a network device (i.e. Subsystem
+Device ID 1) indicates that the device supports checksumming of
+packets.
+
+The feature bits are negotiated: the device lists all the
+features it understands in the Device Features field, and the
+guest writes the subset that it understands into the Guest
+Features field. The only way to renegotiate is to reset the
+device.
+
+In particular, new fields in the device configuration header are
+indicated by offering a feature bit, so the guest can check
+before accessing that part of the configuration space.
+
+This allows for forwards and backwards compatibility: if the
+device is enhanced with a new feature bit, older guests will not
+write that feature bit back to the Guest Features field and it
+can go into backwards compatibility mode. Similarly, if a guest
+is enhanced with a feature that the device doesn't support, it
+will not see that feature bit in the Device Features field and
+can go into backwards compatibility mode (or, for poor
+implementations, set the FAILED Device Status bit).
+
+Access to feature bits 32 to 63 is enabled by Guest by setting
+feature bit 31. If this bit is unset, Device must assume that all
+feature bits > 31 are unset.
+
+ Configuration/Queue Vectors
+
+When MSI-X capability is present and enabled in the device
+(through standard PCI configuration space) 4 bytes at byte offset
+20 are used to map configuration change and queue interrupts to
+MSI-X vectors. In this case, the ISR Status field is unused, and
+device specific configuration starts at byte offset 24 in virtio
+header structure. When MSI-X capability is not enabled, device
+specific configuration starts at byte offset 20 in virtio header.
+
+Writing a valid MSI-X Table entry number, 0 to 0x7FF, to one of
+Configuration/Queue Vector registers, maps interrupts triggered
+by the configuration change/selected queue events respectively to
+the corresponding MSI-X vector. To disable interrupts for a
+specific event type, unmap it by writing a special NO_VECTOR
+value:
+
+/* Vector value used to disable MSI for queue */
+
+#define VIRTIO_MSI_NO_VECTOR 0xffff
+
+Reading these registers returns vector mapped to a given event,
+or NO_VECTOR if unmapped. All queue and configuration change
+events are unmapped by default.
+
+Note that mapping an event to vector might require allocating
+internal device resources, and might fail. Devices report such
+failures by returning the NO_VECTOR value when the relevant
+Vector field is read. After mapping an event to vector, the
+driver must verify success by reading the Vector field value: on
+success, the previously written value is returned, and on
+failure, NO_VECTOR is returned. If a mapping failure is detected,
+the driver can retry mapping with fewervectors, or disable MSI-X.
+
+ Virtqueue Configuration
+
+As a device can have zero or more virtqueues for bulk data
+transport (for example, the network driver has two), the driver
+needs to configure them as part of the device-specific
+configuration.
+
+This is done as follows, for each virtqueue a device has:
+
+ Write the virtqueue index (first queue is 0) to the Queue
+ Select field.
+
+ Read the virtqueue size from the Queue Size field, which is
+ always a power of 2. This controls how big the virtqueue is
+ (see below). If this field is 0, the virtqueue does not exist.
+
+ Allocate and zero virtqueue in contiguous physical memory, on a
+ 4096 byte alignment. Write the physical address, divided by
+ 4096 to the Queue Address field.[footnote:
+The 4096 is based on the x86 page size, but it's also large
+enough to ensure that the separate parts of the virtqueue are on
+separate cache lines.
+]
+
+ Optionally, if MSI-X capability is present and enabled on the
+ device, select a vector to use to request interrupts triggered
+ by virtqueue events. Write the MSI-X Table entry number
+ corresponding to this vector in Queue Vector field. Read the
+ Queue Vector field: on success, previously written value is
+ returned; on failure, NO_VECTOR value is returned.
+
+The Queue Size field controls the total number of bytes required
+for the virtqueue according to the following formula:
+
+#define ALIGN(x) (((x) + 4095) & ~4095)
+
+static inline unsigned vring_size(unsigned int qsz)
+
+{
+
+ return ALIGN(sizeof(struct vring_desc)*qsz + sizeof(u16)*(2
++ qsz))
+
+ + ALIGN(sizeof(struct vring_used_elem)*qsz);
+
+}
+
+This currently wastes some space with padding, but also allows
+future extensions. The virtqueue layout structure looks like this
+(qsz is the Queue Size field, which is a variable, so this code
+won't compile):
+
+struct vring {
+
+ /* The actual descriptors (16 bytes each) */
+
+ struct vring_desc desc[qsz];
+
+
+
+ /* A ring of available descriptor heads with free-running
+index. */
+
+ struct vring_avail avail;
+
+
+
+ // Padding to the next 4096 boundary.
+
+ char pad[];
+
+
+
+ // A ring of used descriptor heads with free-running index.
+
+ struct vring_used used;
+
+};
+
+ A Note on Virtqueue Endianness
+
+Note that the endian of these fields and everything else in the
+virtqueue is the native endian of the guest, not little-endian as
+PCI normally is. This makes for simpler guest code, and it is
+assumed that the host already has to be deeply aware of the guest
+endian so such an “endian-aware” device is not a significant
+issue.
+
+ Descriptor Table
+
+The descriptor table refers to the buffers the guest is using for
+the device. The addresses are physical addresses, and the buffers
+can be chained via the next field. Each descriptor describes a
+buffer which is read-only or write-only, but a chain of
+descriptors can contain both read-only and write-only buffers.
+
+No descriptor chain may be more than 2^32 bytes long in total.struct vring_desc {
+
+ /* Address (guest-physical). */
+
+ u64 addr;
+
+ /* Length. */
+
+ u32 len;
+
+/* This marks a buffer as continuing via the next field. */
+
+#define VRING_DESC_F_NEXT 1
+
+/* This marks a buffer as write-only (otherwise read-only). */
+
+#define VRING_DESC_F_WRITE 2
+
+/* This means the buffer contains a list of buffer descriptors.
+*/
+
+#define VRING_DESC_F_INDIRECT 4
+
+ /* The flags as indicated above. */
+
+ u16 flags;
+
+ /* Next field if flags & NEXT */
+
+ u16 next;
+
+};
+
+The number of descriptors in the table is specified by the Queue
+Size field for this virtqueue.
+
+ <sub:Indirect-Descriptors>Indirect Descriptors
+
+Some devices benefit by concurrently dispatching a large number
+of large requests. The VIRTIO_RING_F_INDIRECT_DESC feature can be
+used to allow this (see [cha:Reserved-Feature-Bits]). To increase
+ring capacity it is possible to store a table of indirect
+descriptors anywhere in memory, and insert a descriptor in main
+virtqueue (with flags&INDIRECT on) that refers to memory buffer
+containing this indirect descriptor table; fields addr and len
+refer to the indirect table address and length in bytes,
+respectively. The indirect table layout structure looks like this
+(len is the length of the descriptor that refers to this table,
+which is a variable, so this code won't compile):
+
+struct indirect_descriptor_table {
+
+ /* The actual descriptors (16 bytes each) */
+
+ struct vring_desc desc[len / 16];
+
+};
+
+The first indirect descriptor is located at start of the indirect
+descriptor table (index 0), additional indirect descriptors are
+chained by next field. An indirect descriptor without next field
+(with flags&NEXT off) signals the end of the indirect descriptor
+table, and transfers control back to the main virtqueue. An
+indirect descriptor can not refer to another indirect descriptor
+table (flags&INDIRECT must be off). A single indirect descriptor
+table can include both read-only and write-only descriptors;
+write-only flag (flags&WRITE) in the descriptor that refers to it
+is ignored.
+
+ Available Ring
+
+The available ring refers to what descriptors we are offering the
+device: it refers to the head of a descriptor chain. The “flags”
+field is currently 0 or 1: 1 indicating that we do not need an
+interrupt when the device consumes a descriptor from the
+available ring. Alternatively, the guest can ask the device to
+delay interrupts until an entry with an index specified by the “
+used_event” field is written in the used ring (equivalently,
+until the idx field in the used ring will reach the value
+used_event + 1). The method employed by the device is controlled
+by the VIRTIO_RING_F_EVENT_IDX feature bit (see [cha:Reserved-Feature-Bits]
+). This interrupt suppression is merely an optimization; it may
+not suppress interrupts entirely.
+
+The “idx” field indicates where we would put the next descriptor
+entry (modulo the ring size). This starts at 0, and increases.
+
+struct vring_avail {
+
+#define VRING_AVAIL_F_NO_INTERRUPT 1
+
+ u16 flags;
+
+ u16 idx;
+
+ u16 ring[qsz]; /* qsz is the Queue Size field read from device
+*/
+
+ u16 used_event;
+
+};
+
+ Used Ring
+
+The used ring is where the device returns buffers once it is done
+with them. The flags field can be used by the device to hint that
+no notification is necessary when the guest adds to the available
+ring. Alternatively, the “avail_event” field can be used by the
+device to hint that no notification is necessary until an entry
+with an index specified by the “avail_event” is written in the
+available ring (equivalently, until the idx field in the
+available ring will reach the value avail_event + 1). The method
+employed by the device is controlled by the guest through the
+VIRTIO_RING_F_EVENT_IDX feature bit (see [cha:Reserved-Feature-Bits]
+). [footnote:
+These fields are kept here because this is the only part of the
+virtqueue written by the device
+].
+
+Each entry in the ring is a pair: the head entry of the
+descriptor chain describing the buffer (this matches an entry
+placed in the available ring by the guest earlier), and the total
+of bytes written into the buffer. The latter is extremely useful
+for guests using untrusted buffers: if you do not know exactly
+how much has been written by the device, you usually have to zero
+the buffer to ensure no data leakage occurs.
+
+/* u32 is used here for ids for padding reasons. */
+
+struct vring_used_elem {
+
+ /* Index of start of used descriptor chain. */
+
+ u32 id;
+
+ /* Total length of the descriptor chain which was used
+(written to) */
+
+ u32 len;
+
+};
+
+
+
+struct vring_used {
+
+#define VRING_USED_F_NO_NOTIFY 1
+
+ u16 flags;
+
+ u16 idx;
+
+ struct vring_used_elem ring[qsz];
+
+ u16 avail_event;
+
+};
+
+ Helpers for Managing Virtqueues
+
+The Linux Kernel Source code contains the definitions above and
+helper routines in a more usable form, in
+include/linux/virtio_ring.h. This was explicitly licensed by IBM
+and Red Hat under the (3-clause) BSD license so that it can be
+freely used by all other projects, and is reproduced (with slight
+variation to remove Linux assumptions) in Appendix A.
+
+ Device Operation
+
+There are two parts to device operation: supplying new buffers to
+the device, and processing used buffers from the device. As an
+example, the virtio network device has two virtqueues: the
+transmit virtqueue and the receive virtqueue. The driver adds
+outgoing (read-only) packets to the transmit virtqueue, and then
+frees them after they are used. Similarly, incoming (write-only)
+buffers are added to the receive virtqueue, and processed after
+they are used.
+
+ Supplying Buffers to The Device
+
+Actual transfer of buffers from the guest OS to the device
+operates as follows:
+
+ Place the buffer(s) into free descriptor(s).
+
+ If there are no free descriptors, the guest may choose to
+ notify the device even if notifications are suppressed (to
+ reduce latency).[footnote:
+The Linux drivers do this only for read-only buffers: for
+write-only buffers, it is assumed that the driver is merely
+trying to keep the receive buffer ring full, and no notification
+of this expected condition is necessary.
+]
+
+ Place the id of the buffer in the next ring entry of the
+ available ring.
+
+ The steps (1) and (2) may be performed repeatedly if batching
+ is possible.
+
+ A memory barrier should be executed to ensure the device sees
+ the updated descriptor table and available ring before the next
+ step.
+
+ The available “idx” field should be increased by the number of
+ entries added to the available ring.
+
+ A memory barrier should be executed to ensure that we update
+ the idx field before checking for notification suppression.
+
+ If notifications are not suppressed, the device should be
+ notified of the new buffers.
+
+Note that the above code does not take precautions against the
+available ring buffer wrapping around: this is not possible since
+the ring buffer is the same size as the descriptor table, so step
+(1) will prevent such a condition.
+
+In addition, the maximum queue size is 32768 (it must be a power
+of 2 which fits in 16 bits), so the 16-bit “idx” value can always
+distinguish between a full and empty buffer.
+
+Here is a description of each stage in more detail.
+
+ Placing Buffers Into The Descriptor Table
+
+A buffer consists of zero or more read-only physically-contiguous
+elements followed by zero or more physically-contiguous
+write-only elements (it must have at least one element). This
+algorithm maps it into the descriptor table:
+
+ for each buffer element, b:
+
+ Get the next free descriptor table entry, d
+
+ Set d.addr to the physical address of the start of b
+
+ Set d.len to the length of b.
+
+ If b is write-only, set d.flags to VRING_DESC_F_WRITE,
+ otherwise 0.
+
+ If there is a buffer element after this:
+
+ Set d.next to the index of the next free descriptor element.
+
+ Set the VRING_DESC_F_NEXT bit in d.flags.
+
+In practice, the d.next fields are usually used to chain free
+descriptors, and a separate count kept to check there are enough
+free descriptors before beginning the mappings.
+
+ Updating The Available Ring
+
+The head of the buffer we mapped is the first d in the algorithm
+above. A naive implementation would do the following:
+
+avail->ring[avail->idx % qsz] = head;
+
+However, in general we can add many descriptors before we update
+the “idx” field (at which point they become visible to the
+device), so we keep a counter of how many we've added:
+
+avail->ring[(avail->idx + added++) % qsz] = head;
+
+ Updating The Index Field
+
+Once the idx field of the virtqueue is updated, the device will
+be able to access the descriptor entries we've created and the
+memory they refer to. This is why a memory barrier is generally
+used before the idx update, to ensure it sees the most up-to-date
+copy.
+
+The idx field always increments, and we let it wrap naturally at
+65536:
+
+avail->idx += added;
+
+ <sub:Notifying-The-Device>Notifying The Device
+
+Device notification occurs by writing the 16-bit virtqueue index
+of this virtqueue to the Queue Notify field of the virtio header
+in the first I/O region of the PCI device. This can be expensive,
+however, so the device can suppress such notifications if it
+doesn't need them. We have to be careful to expose the new idx
+value before checking the suppression flag: it's OK to notify
+gratuitously, but not to omit a required notification. So again,
+we use a memory barrier here before reading the flags or the
+avail_event field.
+
+If the VIRTIO_F_RING_EVENT_IDX feature is not negotiated, and if
+the VRING_USED_F_NOTIFY flag is not set, we go ahead and write to
+the PCI configuration space.
+
+If the VIRTIO_F_RING_EVENT_IDX feature is negotiated, we read the
+avail_event field in the available ring structure. If the
+available index crossed_the avail_event field value since the
+last notification, we go ahead and write to the PCI configuration
+space. The avail_event field wraps naturally at 65536 as well:
+
+(u16)(new_idx - avail_event - 1) < (u16)(new_idx - old_idx)
+
+ <sub:Receiving-Used-Buffers>Receiving Used Buffers From The
+ Device
+
+Once the device has used a buffer (read from or written to it, or
+parts of both, depending on the nature of the virtqueue and the
+device), it sends an interrupt, following an algorithm very
+similar to the algorithm used for the driver to send the device a
+buffer:
+
+ Write the head descriptor number to the next field in the used
+ ring.
+
+ Update the used ring idx.
+
+ Determine whether an interrupt is necessary:
+
+ If the VIRTIO_F_RING_EVENT_IDX feature is not negotiated: check
+ if f the VRING_AVAIL_F_NO_INTERRUPT flag is not set in avail-
+ >flags
+
+ If the VIRTIO_F_RING_EVENT_IDX feature is negotiated: check
+ whether the used index crossed the used_event field value
+ since the last update. The used_event field wraps naturally
+ at 65536 as well:(u16)(new_idx - used_event - 1) < (u16)(new_idx - old_idx)
+
+ If an interrupt is necessary:
+
+ If MSI-X capability is disabled:
+
+ Set the lower bit of the ISR Status field for the device.
+
+ Send the appropriate PCI interrupt for the device.
+
+ If MSI-X capability is enabled:
+
+ Request the appropriate MSI-X interrupt message for the
+ device, Queue Vector field sets the MSI-X Table entry
+ number.
+
+ If Queue Vector field value is NO_VECTOR, no interrupt
+ message is requested for this event.
+
+The guest interrupt handler should:
+
+ If MSI-X capability is disabled: read the ISR Status field,
+ which will reset it to zero. If the lower bit is zero, the
+ interrupt was not for this device. Otherwise, the guest driver
+ should look through the used rings of each virtqueue for the
+ device, to see if any progress has been made by the device
+ which requires servicing.
+
+ If MSI-X capability is enabled: look through the used rings of
+ each virtqueue mapped to the specific MSI-X vector for the
+ device, to see if any progress has been made by the device
+ which requires servicing.
+
+For each ring, guest should then disable interrupts by writing
+VRING_AVAIL_F_NO_INTERRUPT flag in avail structure, if required.
+It can then process used ring entries finally enabling interrupts
+by clearing the VRING_AVAIL_F_NO_INTERRUPT flag or updating the
+EVENT_IDX field in the available structure, Guest should then
+execute a memory barrier, and then recheck the ring empty
+condition. This is necessary to handle the case where, after the
+last check and before enabling interrupts, an interrupt has been
+suppressed by the device:
+
+vring_disable_interrupts(vq);
+
+for (;;) {
+
+ if (vq->last_seen_used != vring->used.idx) {
+
+ vring_enable_interrupts(vq);
+
+ mb();
+
+ if (vq->last_seen_used != vring->used.idx)
+
+ break;
+
+ }
+
+ struct vring_used_elem *e =
+vring.used->ring[vq->last_seen_used%vsz];
+
+ process_buffer(e);
+
+ vq->last_seen_used++;
+
+}
+
+ Dealing With Configuration Changes
+
+Some virtio PCI devices can change the device configuration
+state, as reflected in the virtio header in the PCI configuration
+space. In this case:
+
+ If MSI-X capability is disabled: an interrupt is delivered and
+ the second highest bit is set in the ISR Status field to
+ indicate that the driver should re-examine the configuration
+ space.Note that a single interrupt can indicate both that one
+ or more virtqueue has been used and that the configuration
+ space has changed: even if the config bit is set, virtqueues
+ must be scanned.
+
+ If MSI-X capability is enabled: an interrupt message is
+ requested. The Configuration Vector field sets the MSI-X Table
+ entry number to use. If Configuration Vector field value is
+ NO_VECTOR, no interrupt message is requested for this event.
+
+Creating New Device Types
+
+Various considerations are necessary when creating a new device
+type:
+
+ How Many Virtqueues?
+
+It is possible that a very simple device will operate entirely
+through its configuration space, but most will need at least one
+virtqueue in which it will place requests. A device with both
+input and output (eg. console and network devices described here)
+need two queues: one which the driver fills with buffers to
+receive input, and one which the driver places buffers to
+transmit output.
+
+ What Configuration Space Layout?
+
+Configuration space is generally used for rarely-changing or
+initialization-time parameters. But it is a limited resource, so
+it might be better to use a virtqueue to update configuration
+information (the network device does this for filtering,
+otherwise the table in the config space could potentially be very
+large).
+
+Note that this space is generally the guest's native endian,
+rather than PCI's little-endian.
+
+ What Device Number?
+
+Currently device numbers are assigned quite freely: a simple
+request mail to the author of this document or the Linux
+virtualization mailing list[footnote:
+
+https://lists.linux-foundation.org/mailman/listinfo/virtualization
+] will be sufficient to secure a unique one.
+
+Meanwhile for experimental drivers, use 65535 and work backwards.
+
+ How many MSI-X vectors?
+
+Using the optional MSI-X capability devices can speed up
+interrupt processing by removing the need to read ISR Status
+register by guest driver (which might be an expensive operation),
+reducing interrupt sharing between devices and queues within the
+device, and handling interrupts from multiple CPUs. However, some
+systems impose a limit (which might be as low as 256) on the
+total number of MSI-X vectors that can be allocated to all
+devices. Devices and/or device drivers should take this into
+account, limiting the number of vectors used unless the device is
+expected to cause a high volume of interrupts. Devices can
+control the number of vectors used by limiting the MSI-X Table
+Size or not presenting MSI-X capability in PCI configuration
+space. Drivers can control this by mapping events to as small
+number of vectors as possible, or disabling MSI-X capability
+altogether.
+
+ Message Framing
+
+The descriptors used for a buffer should not effect the semantics
+of the message, except for the total length of the buffer. For
+example, a network buffer consists of a 10 byte header followed
+by the network packet. Whether this is presented in the ring
+descriptor chain as (say) a 10 byte buffer and a 1514 byte
+buffer, or a single 1524 byte buffer, or even three buffers,
+should have no effect.
+
+In particular, no implementation should use the descriptor
+boundaries to determine the size of any header in a request.[footnote:
+The current qemu device implementations mistakenly insist that
+the first descriptor cover the header in these cases exactly, so
+a cautious driver should arrange it so.
+]
+
+ Device Improvements
+
+Any change to configuration space, or new virtqueues, or
+behavioural changes, should be indicated by negotiation of a new
+feature bit. This establishes clarity[footnote:
+Even if it does mean documenting design or implementation
+mistakes!
+] and avoids future expansion problems.
+
+Clusters of functionality which are always implemented together
+can use a single bit, but if one feature makes sense without the
+others they should not be gratuitously grouped together to
+conserve feature bits. We can always extend the spec when the
+first person needs more than 24 feature bits for their device.
+
+[LaTeX Command: printnomenclature]
+
+Appendix A: virtio_ring.h
+
+#ifndef VIRTIO_RING_H
+
+#define VIRTIO_RING_H
+
+/* An interface for efficient virtio implementation.
+
+ *
+
+ * This header is BSD licensed so anyone can use the definitions
+
+ * to implement compatible drivers/servers.
+
+ *
+
+ * Copyright 2007, 2009, IBM Corporation
+
+ * Copyright 2011, Red Hat, Inc
+
+ * All rights reserved.
+
+ *
+
+ * Redistribution and use in source and binary forms, with or
+without
+
+ * modification, are permitted provided that the following
+conditions
+
+ * are met:
+
+ * 1. Redistributions of source code must retain the above
+copyright
+
+ * notice, this list of conditions and the following
+disclaimer.
+
+ * 2. Redistributions in binary form must reproduce the above
+copyright
+
+ * notice, this list of conditions and the following
+disclaimer in the
+
+ * documentation and/or other materials provided with the
+distribution.
+
+ * 3. Neither the name of IBM nor the names of its contributors
+
+ * may be used to endorse or promote products derived from
+this software
+
+ * without specific prior written permission.
+
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+CONTRIBUTORS ``AS IS'' AND
+
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+TO, THE
+
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE
+
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE
+LIABLE
+
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL
+
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS
+
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION)
+
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT
+
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+IN ANY WAY
+
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF
+
+ * SUCH DAMAGE.
+
+ */
+
+
+
+/* This marks a buffer as continuing via the next field. */
+
+#define VRING_DESC_F_NEXT 1
+
+/* This marks a buffer as write-only (otherwise read-only). */
+
+#define VRING_DESC_F_WRITE 2
+
+
+
+/* The Host uses this in used->flags to advise the Guest: don't
+kick me
+
+ * when you add a buffer. It's unreliable, so it's simply an
+
+ * optimization. Guest will still kick if it's out of buffers.
+*/
+
+#define VRING_USED_F_NO_NOTIFY 1
+
+/* The Guest uses this in avail->flags to advise the Host: don't
+
+ * interrupt me when you consume a buffer. It's unreliable, so
+it's
+
+ * simply an optimization. */
+
+#define VRING_AVAIL_F_NO_INTERRUPT 1
+
+
+
+/* Virtio ring descriptors: 16 bytes.
+
+ * These can chain together via "next". */
+
+struct vring_desc {
+
+ /* Address (guest-physical). */
+
+ uint64_t addr;
+
+ /* Length. */
+
+ uint32_t len;
+
+ /* The flags as indicated above. */
+
+ uint16_t flags;
+
+ /* We chain unused descriptors via this, too */
+
+ uint16_t next;
+
+};
+
+
+
+struct vring_avail {
+
+ uint16_t flags;
+
+ uint16_t idx;
+
+ uint16_t ring[];
+
+ uint16_t used_event;
+
+};
+
+
+
+/* u32 is used here for ids for padding reasons. */
+
+struct vring_used_elem {
+
+ /* Index of start of used descriptor chain. */
+
+ uint32_t id;
+
+ /* Total length of the descriptor chain which was written
+to. */
+
+ uint32_t len;
+
+};
+
+
+
+struct vring_used {
+
+ uint16_t flags;
+
+ uint16_t idx;
+
+ struct vring_used_elem ring[];
+
+ uint16_t avail_event;
+
+};
+
+
+
+struct vring {
+
+ unsigned int num;
+
+
+
+ struct vring_desc *desc;
+
+ struct vring_avail *avail;
+
+ struct vring_used *used;
+
+};
+
+
+
+/* The standard layout for the ring is a continuous chunk of
+memory which
+
+ * looks like this. We assume num is a power of 2.
+
+ *
+
+ * struct vring {
+
+ * // The actual descriptors (16 bytes each)
+
+ * struct vring_desc desc[num];
+
+ *
+
+ * // A ring of available descriptor heads with free-running
+index.
+
+ * __u16 avail_flags;
+
+ * __u16 avail_idx;
+
+ * __u16 available[num];
+
+ *
+
+ * // Padding to the next align boundary.
+
+ * char pad[];
+
+ *
+
+ * // A ring of used descriptor heads with free-running
+index.
+
+ * __u16 used_flags;
+
+ * __u16 EVENT_IDX;
+
+ * struct vring_used_elem used[num];
+
+ * };
+
+ * Note: for virtio PCI, align is 4096.
+
+ */
+
+static inline void vring_init(struct vring *vr, unsigned int num,
+void *p,
+
+ unsigned long align)
+
+{
+
+ vr->num = num;
+
+ vr->desc = p;
+
+ vr->avail = p + num*sizeof(struct vring_desc);
+
+ vr->used = (void *)(((unsigned long)&vr->avail->ring[num]
+
+ + align-1)
+
+ & ~(align - 1));
+
+}
+
+
+
+static inline unsigned vring_size(unsigned int num, unsigned long
+align)
+
+{
+
+ return ((sizeof(struct vring_desc)*num +
+sizeof(uint16_t)*(2+num)
+
+ + align - 1) & ~(align - 1))
+
+ + sizeof(uint16_t)*3 + sizeof(struct
+vring_used_elem)*num;
+
+}
+
+
+
+static inline int vring_need_event(uint16_t event_idx, uint16_t
+new_idx, uint16_t old_idx)
+
+{
+
+ return (uint16_t)(new_idx - event_idx - 1) <
+(uint16_t)(new_idx - old_idx);
+
+}
+
+#endif /* VIRTIO_RING_H */
+
+<cha:Reserved-Feature-Bits>Appendix B: Reserved Feature Bits
+
+Currently there are five device-independent feature bits defined:
+
+ VIRTIO_F_NOTIFY_ON_EMPTY (24) Negotiating this feature
+ indicates that the driver wants an interrupt if the device runs
+ out of available descriptors on a virtqueue, even though
+ interrupts are suppressed using the VRING_AVAIL_F_NO_INTERRUPT
+ flag or the used_event field. An example of this is the
+ networking driver: it doesn't need to know every time a packet
+ is transmitted, but it does need to free the transmitted
+ packets a finite time after they are transmitted. It can avoid
+ using a timer if the device interrupts it when all the packets
+ are transmitted.
+
+ VIRTIO_F_RING_INDIRECT_DESC (28) Negotiating this feature
+ indicates that the driver can use descriptors with the
+ VRING_DESC_F_INDIRECT flag set, as described in [sub:Indirect-Descriptors]
+ .
+
+ VIRTIO_F_RING_EVENT_IDX(29) This feature enables the used_event
+ and the avail_event fields. If set, it indicates that the
+ device should ignore the flags field in the available ring
+ structure. Instead, the used_event field in this structure is
+ used by guest to suppress device interrupts. Further, the
+ driver should ignore the flags field in the used ring
+ structure. Instead, the avail_event field in this structure is
+ used by the device to suppress notifications. If unset, the
+ driver should ignore the used_event field; the device should
+ ignore the avail_event field; the flags field is used
+
+ VIRTIO_F_BAD_FEATURE(30) This feature should never be
+ negotiated by the guest; doing so is an indication that the
+ guest is faulty[footnote:
+An experimental virtio PCI driver contained in Linux version
+2.6.25 had this problem, and this feature bit can be used to
+detect it.
+]
+
+ VIRTIO_F_FEATURES_HIGH(31) This feature indicates that the
+ device supports feature bits 32:63. If unset, feature bits
+ 32:63 are unset.
+
+Appendix C: Network Device
+
+The virtio network device is a virtual ethernet card, and is the
+most complex of the devices supported so far by virtio. It has
+enhanced rapidly and demonstrates clearly how support for new
+features should be added to an existing device. Empty buffers are
+placed in one virtqueue for receiving packets, and outgoing
+packets are enqueued into another for transmission in that order.
+A third command queue is used to control advanced filtering
+features.
+
+ Configuration
+
+ Subsystem Device ID 1
+
+ Virtqueues 0:receiveq. 1:transmitq. 2:controlq[footnote:
+Only if VIRTIO_NET_F_CTRL_VQ set
+]
+
+ Feature bits
+
+ VIRTIO_NET_F_CSUM (0) Device handles packets with partial
+ checksum
+
+ VIRTIO_NET_F_GUEST_CSUM (1) Guest handles packets with partial
+ checksum
+
+ VIRTIO_NET_F_MAC (5) Device has given MAC address.
+
+ VIRTIO_NET_F_GSO (6) (Deprecated) device handles packets with
+ any GSO type.[footnote:
+It was supposed to indicate segmentation offload support, but
+upon further investigation it became clear that multiple bits
+were required.
+]
+
+ VIRTIO_NET_F_GUEST_TSO4 (7) Guest can receive TSOv4.
+
+ VIRTIO_NET_F_GUEST_TSO6 (8) Guest can receive TSOv6.
+
+ VIRTIO_NET_F_GUEST_ECN (9) Guest can receive TSO with ECN.
+
+ VIRTIO_NET_F_GUEST_UFO (10) Guest can receive UFO.
+
+ VIRTIO_NET_F_HOST_TSO4 (11) Device can receive TSOv4.
+
+ VIRTIO_NET_F_HOST_TSO6 (12) Device can receive TSOv6.
+
+ VIRTIO_NET_F_HOST_ECN (13) Device can receive TSO with ECN.
+
+ VIRTIO_NET_F_HOST_UFO (14) Device can receive UFO.
+
+ VIRTIO_NET_F_MRG_RXBUF (15) Guest can merge receive buffers.
+
+ VIRTIO_NET_F_STATUS (16) Configuration status field is
+ available.
+
+ VIRTIO_NET_F_CTRL_VQ (17) Control channel is available.
+
+ VIRTIO_NET_F_CTRL_RX (18) Control channel RX mode support.
+
+ VIRTIO_NET_F_CTRL_VLAN (19) Control channel VLAN filtering.
+
+ Device configuration layout Two configuration fields are
+ currently defined. The mac address field always exists (though
+ is only valid if VIRTIO_NET_F_MAC is set), and the status field
+ only exists if VIRTIO_NET_F_STATUS is set. Only one bit is
+ currently defined for the status field: VIRTIO_NET_S_LINK_UP. #define VIRTIO_NET_S_LINK_UP 1
+
+
+
+struct virtio_net_config {
+
+ u8 mac[6];
+
+ u16 status;
+
+};
+
+ Device Initialization
+
+ The initialization routine should identify the receive and
+ transmission virtqueues.
+
+ If the VIRTIO_NET_F_MAC feature bit is set, the configuration
+ space “mac” entry indicates the “physical” address of the the
+ network card, otherwise a private MAC address should be
+ assigned. All guests are expected to negotiate this feature if
+ it is set.
+
+ If the VIRTIO_NET_F_CTRL_VQ feature bit is negotiated, identify
+ the control virtqueue.
+
+ If the VIRTIO_NET_F_STATUS feature bit is negotiated, the link
+ status can be read from the bottom bit of the “status” config
+ field. Otherwise, the link should be assumed active.
+
+ The receive virtqueue should be filled with receive buffers.
+ This is described in detail below in “Setting Up Receive
+ Buffers”.
+
+ A driver can indicate that it will generate checksumless
+ packets by negotating the VIRTIO_NET_F_CSUM feature. This “
+ checksum offload” is a common feature on modern network cards.
+
+ If that feature is negotiated, a driver can use TCP or UDP
+ segmentation offload by negotiating the VIRTIO_NET_F_HOST_TSO4
+ (IPv4 TCP), VIRTIO_NET_F_HOST_TSO6 (IPv6 TCP) and
+ VIRTIO_NET_F_HOST_UFO (UDP fragmentation) features. It should
+ not send TCP packets requiring segmentation offload which have
+ the Explicit Congestion Notification bit set, unless the
+ VIRTIO_NET_F_HOST_ECN feature is negotiated.[footnote:
+This is a common restriction in real, older network cards.
+]
+
+ The converse features are also available: a driver can save the
+ virtual device some work by negotiating these features.[footnote:
+For example, a network packet transported between two guests on
+the same system may not require checksumming at all, nor
+segmentation, if both guests are amenable.
+] The VIRTIO_NET_F_GUEST_CSUM feature indicates that partially
+ checksummed packets can be received, and if it can do that then
+ the VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
+ VIRTIO_NET_F_GUEST_UFO and VIRTIO_NET_F_GUEST_ECN are the input
+ equivalents of the features described above. See “Receiving
+ Packets” below.
+
+ Device Operation
+
+Packets are transmitted by placing them in the transmitq, and
+buffers for incoming packets are placed in the receiveq. In each
+case, the packet itself is preceeded by a header:
+
+struct virtio_net_hdr {
+
+#define VIRTIO_NET_HDR_F_NEEDS_CSUM 1
+
+ u8 flags;
+
+#define VIRTIO_NET_HDR_GSO_NONE 0
+
+#define VIRTIO_NET_HDR_GSO_TCPV4 1
+
+#define VIRTIO_NET_HDR_GSO_UDP 3
+
+#define VIRTIO_NET_HDR_GSO_TCPV6 4
+
+#define VIRTIO_NET_HDR_GSO_ECN 0x80
+
+ u8 gso_type;
+
+ u16 hdr_len;
+
+ u16 gso_size;
+
+ u16 csum_start;
+
+ u16 csum_offset;
+
+/* Only if VIRTIO_NET_F_MRG_RXBUF: */
+
+ u16 num_buffers
+
+};
+
+The controlq is used to control device features such as
+filtering.
+
+ Packet Transmission
+
+Transmitting a single packet is simple, but varies depending on
+the different features the driver negotiated.
+
+ If the driver negotiated VIRTIO_NET_F_CSUM, and the packet has
+ not been fully checksummed, then the virtio_net_hdr's fields
+ are set as follows. Otherwise, the packet must be fully
+ checksummed, and flags is zero.
+
+ flags has the VIRTIO_NET_HDR_F_NEEDS_CSUM set,
+
+ <ite:csum_start-is-set>csum_start is set to the offset within
+ the packet to begin checksumming, and
+
+ csum_offset indicates how many bytes after the csum_start the
+ new (16 bit ones' complement) checksum should be placed.[footnote:
+For example, consider a partially checksummed TCP (IPv4) packet.
+It will have a 14 byte ethernet header and 20 byte IP header
+followed by the TCP header (with the TCP checksum field 16 bytes
+into that header). csum_start will be 14+20 = 34 (the TCP
+checksum includes the header), and csum_offset will be 16. The
+value in the TCP checksum field will be the sum of the TCP pseudo
+header, so that replacing it by the ones' complement checksum of
+the TCP header and body will give the correct result.
+]
+
+ <enu:If-the-driver>If the driver negotiated
+ VIRTIO_NET_F_HOST_TSO4, TSO6 or UFO, and the packet requires
+ TCP segmentation or UDP fragmentation, then the “gso_type”
+ field is set to VIRTIO_NET_HDR_GSO_TCPV4, TCPV6 or UDP.
+ (Otherwise, it is set to VIRTIO_NET_HDR_GSO_NONE). In this
+ case, packets larger than 1514 bytes can be transmitted: the
+ metadata indicates how to replicate the packet header to cut it
+ into smaller packets. The other gso fields are set:
+
+ hdr_len is a hint to the device as to how much of the header
+ needs to be kept to copy into each packet, usually set to the
+ length of the headers, including the transport header.[footnote:
+Due to various bugs in implementations, this field is not useful
+as a guarantee of the transport header size.
+]
+
+ gso_size is the size of the packet beyond that header (ie.
+ MSS).
+
+ If the driver negotiated the VIRTIO_NET_F_HOST_ECN feature, the
+ VIRTIO_NET_HDR_GSO_ECN bit may be set in “gso_type” as well,
+ indicating that the TCP packet has the ECN bit set.[footnote:
+This case is not handled by some older hardware, so is called out
+specifically in the protocol.
+]
+
+ If the driver negotiated the VIRTIO_NET_F_MRG_RXBUF feature,
+ the num_buffers field is set to zero.
+
+ The header and packet are added as one output buffer to the
+ transmitq, and the device is notified of the new entry (see [sub:Notifying-The-Device]
+ ).[footnote:
+Note that the header will be two bytes longer for the
+VIRTIO_NET_F_MRG_RXBUF case.
+]
+
+ Packet Transmission Interrupt
+
+Often a driver will suppress transmission interrupts using the
+VRING_AVAIL_F_NO_INTERRUPT flag (see [sub:Receiving-Used-Buffers]
+) and check for used packets in the transmit path of following
+packets. However, it will still receive interrupts if the
+VIRTIO_F_NOTIFY_ON_EMPTY feature is negotiated, indicating that
+the transmission queue is completely emptied.
+
+The normal behavior in this interrupt handler is to retrieve and
+new descriptors from the used ring and free the corresponding
+headers and packets.
+
+ Setting Up Receive Buffers
+
+It is generally a good idea to keep the receive virtqueue as
+fully populated as possible: if it runs out, network performance
+will suffer.
+
+If the VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6 or
+VIRTIO_NET_F_GUEST_UFO features are used, the Guest will need to
+accept packets of up to 65550 bytes long (the maximum size of a
+TCP or UDP packet, plus the 14 byte ethernet header), otherwise
+1514 bytes. So unless VIRTIO_NET_F_MRG_RXBUF is negotiated, every
+buffer in the receive queue needs to be at least this length [footnote:
+Obviously each one can be split across multiple descriptor
+elements.
+].
+
+If VIRTIO_NET_F_MRG_RXBUF is negotiated, each buffer must be at
+least the size of the struct virtio_net_hdr.
+
+ Packet Receive Interrupt
+
+When a packet is copied into a buffer in the receiveq, the
+optimal path is to disable further interrupts for the receiveq
+(see [sub:Receiving-Used-Buffers]) and process packets until no
+more are found, then re-enable them.
+
+Processing packet involves:
+
+ If the driver negotiated the VIRTIO_NET_F_MRG_RXBUF feature,
+ then the “num_buffers” field indicates how many descriptors
+ this packet is spread over (including this one). This allows
+ receipt of large packets without having to allocate large
+ buffers. In this case, there will be at least “num_buffers” in
+ the used ring, and they should be chained together to form a
+ single packet. The other buffers will not begin with a struct
+ virtio_net_hdr.
+
+ If the VIRTIO_NET_F_MRG_RXBUF feature was not negotiated, or
+ the “num_buffers” field is one, then the entire packet will be
+ contained within this buffer, immediately following the struct
+ virtio_net_hdr.
+
+ If the VIRTIO_NET_F_GUEST_CSUM feature was negotiated, the
+ VIRTIO_NET_HDR_F_NEEDS_CSUM bit in the “flags” field may be
+ set: if so, the checksum on the packet is incomplete and the “
+ csum_start” and “csum_offset” fields indicate how to calculate
+ it (see [ite:csum_start-is-set]).
+
+ If the VIRTIO_NET_F_GUEST_TSO4, TSO6 or UFO options were
+ negotiated, then the “gso_type” may be something other than
+ VIRTIO_NET_HDR_GSO_NONE, and the “gso_size” field indicates the
+ desired MSS (see [enu:If-the-driver]).Control Virtqueue
+
+The driver uses the control virtqueue (if VIRTIO_NET_F_VTRL_VQ is
+negotiated) to send commands to manipulate various features of
+the device which would not easily map into the configuration
+space.
+
+All commands are of the following form:
+
+struct virtio_net_ctrl {
+
+ u8 class;
+
+ u8 command;
+
+ u8 command-specific-data[];
+
+ u8 ack;
+
+};
+
+
+
+/* ack values */
+
+#define VIRTIO_NET_OK 0
+
+#define VIRTIO_NET_ERR 1
+
+The class, command and command-specific-data are set by the
+driver, and the device sets the ack byte. There is little it can
+do except issue a diagnostic if the ack byte is not
+VIRTIO_NET_OK.
+
+ Packet Receive Filtering
+
+If the VIRTIO_NET_F_CTRL_RX feature is negotiated, the driver can
+send control commands for promiscuous mode, multicast receiving,
+and filtering of MAC addresses.
+
+Note that in general, these commands are best-effort: unwanted
+packets may still arrive.
+
+ Setting Promiscuous Mode
+
+#define VIRTIO_NET_CTRL_RX 0
+
+ #define VIRTIO_NET_CTRL_RX_PROMISC 0
+
+ #define VIRTIO_NET_CTRL_RX_ALLMULTI 1
+
+The class VIRTIO_NET_CTRL_RX has two commands:
+VIRTIO_NET_CTRL_RX_PROMISC turns promiscuous mode on and off, and
+VIRTIO_NET_CTRL_RX_ALLMULTI turns all-multicast receive on and
+off. The command-specific-data is one byte containing 0 (off) or
+1 (on).
+
+ Setting MAC Address Filtering
+
+struct virtio_net_ctrl_mac {
+
+ u32 entries;
+
+ u8 macs[entries][ETH_ALEN];
+
+};
+
+
+
+#define VIRTIO_NET_CTRL_MAC 1
+
+ #define VIRTIO_NET_CTRL_MAC_TABLE_SET 0
+
+The device can filter incoming packets by any number of
+destination MAC addresses.[footnote:
+Since there are no guarentees, it can use a hash filter
+orsilently switch to allmulti or promiscuous mode if it is given
+too many addresses.
+] This table is set using the class VIRTIO_NET_CTRL_MAC and the
+command VIRTIO_NET_CTRL_MAC_TABLE_SET. The command-specific-data
+is two variable length tables of 6-byte MAC addresses. The first
+table contains unicast addresses, and the second contains
+multicast addresses.
+
+ VLAN Filtering
+
+If the driver negotiates the VIRTION_NET_F_CTRL_VLAN feature, it
+can control a VLAN filter table in the device.
+
+#define VIRTIO_NET_CTRL_VLAN 2
+
+ #define VIRTIO_NET_CTRL_VLAN_ADD 0
+
+ #define VIRTIO_NET_CTRL_VLAN_DEL 1
+
+Both the VIRTIO_NET_CTRL_VLAN_ADD and VIRTIO_NET_CTRL_VLAN_DEL
+command take a 16-bit VLAN id as the command-specific-data.
+
+Appendix D: Block Device
+
+The virtio block device is a simple virtual block device (ie.
+disk). Read and write requests (and other exotic requests) are
+placed in the queue, and serviced (probably out of order) by the
+device except where noted.
+
+ Configuration
+
+ Subsystem Device ID 2
+
+ Virtqueues 0:requestq.
+
+ Feature bits
+
+ VIRTIO_BLK_F_BARRIER (0) Host supports request barriers.
+
+ VIRTIO_BLK_F_SIZE_MAX (1) Maximum size of any single segment is
+ in “size_max”.
+
+ VIRTIO_BLK_F_SEG_MAX (2) Maximum number of segments in a
+ request is in “seg_max”.
+
+ VIRTIO_BLK_F_GEOMETRY (4) Disk-style geometry specified in “
+ geometry”.
+
+ VIRTIO_BLK_F_RO (5) Device is read-only.
+
+ VIRTIO_BLK_F_BLK_SIZE (6) Block size of disk is in “blk_size”.
+
+ VIRTIO_BLK_F_SCSI (7) Device supports scsi packet commands.
+
+ VIRTIO_BLK_F_FLUSH (9) Cache flush command support.
+
+
+
+ Device configuration layout The capacity of the device
+ (expressed in 512-byte sectors) is always present. The
+ availability of the others all depend on various feature bits
+ as indicated above. struct virtio_blk_config {
+
+ u64 capacity;
+
+ u32 size_max;
+
+ u32 seg_max;
+
+ struct virtio_blk_geometry {
+
+ u16 cylinders;
+
+ u8 heads;
+
+ u8 sectors;
+
+ } geometry;
+
+ u32 blk_size;
+
+
+
+};
+
+ Device Initialization
+
+ The device size should be read from the “capacity”
+ configuration field. No requests should be submitted which goes
+ beyond this limit.
+
+ If the VIRTIO_BLK_F_BLK_SIZE feature is negotiated, the
+ blk_size field can be read to determine the optimal sector size
+ for the driver to use. This does not effect the units used in
+ the protocol (always 512 bytes), but awareness of the correct
+ value can effect performance.
+
+ If the VIRTIO_BLK_F_RO feature is set by the device, any write
+ requests will fail.
+
+
+
+ Device Operation
+
+The driver queues requests to the virtqueue, and they are used by
+the device (not necessarily in order). Each request is of form:
+
+struct virtio_blk_req {
+
+
+
+ u32 type;
+
+ u32 ioprio;
+
+ u64 sector;
+
+ char data[][512];
+
+ u8 status;
+
+};
+
+If the device has VIRTIO_BLK_F_SCSI feature, it can also support
+scsi packet command requests, each of these requests is of form:struct virtio_scsi_pc_req {
+
+ u32 type;
+
+ u32 ioprio;
+
+ u64 sector;
+
+ char cmd[];
+
+ char data[][512];
+
+#define SCSI_SENSE_BUFFERSIZE 96
+
+ u8 sense[SCSI_SENSE_BUFFERSIZE];
+
+ u32 errors;
+
+ u32 data_len;
+
+ u32 sense_len;
+
+ u32 residual;
+
+ u8 status;
+
+};
+
+The type of the request is either a read (VIRTIO_BLK_T_IN), a
+write (VIRTIO_BLK_T_OUT), a scsi packet command
+(VIRTIO_BLK_T_SCSI_CMD or VIRTIO_BLK_T_SCSI_CMD_OUT[footnote:
+the SCSI_CMD and SCSI_CMD_OUT types are equivalent, the device
+does not distinguish between them
+]) or a flush (VIRTIO_BLK_T_FLUSH or VIRTIO_BLK_T_FLUSH_OUT[footnote:
+the FLUSH and FLUSH_OUT types are equivalent, the device does not
+distinguish between them
+]). If the device has VIRTIO_BLK_F_BARRIER feature the high bit
+(VIRTIO_BLK_T_BARRIER) indicates that this request acts as a
+barrier and that all preceeding requests must be complete before
+this one, and all following requests must not be started until
+this is complete. Note that a barrier does not flush caches in
+the underlying backend device in host, and thus does not serve as
+data consistency guarantee. Driver must use FLUSH request to
+flush the host cache.
+
+#define VIRTIO_BLK_T_IN 0
+
+#define VIRTIO_BLK_T_OUT 1
+
+#define VIRTIO_BLK_T_SCSI_CMD 2
+
+#define VIRTIO_BLK_T_SCSI_CMD_OUT 3
+
+#define VIRTIO_BLK_T_FLUSH 4
+
+#define VIRTIO_BLK_T_FLUSH_OUT 5
+
+#define VIRTIO_BLK_T_BARRIER 0x80000000
+
+The ioprio field is a hint about the relative priorities of
+requests to the device: higher numbers indicate more important
+requests.
+
+The sector number indicates the offset (multiplied by 512) where
+the read or write is to occur. This field is unused and set to 0
+for scsi packet commands and for flush commands.
+
+The cmd field is only present for scsi packet command requests,
+and indicates the command to perform. This field must reside in a
+single, separate read-only buffer; command length can be derived
+from the length of this buffer.
+
+Note that these first three (four for scsi packet commands)
+fields are always read-only: the data field is either read-only
+or write-only, depending on the request. The size of the read or
+write can be derived from the total size of the request buffers.
+
+The sense field is only present for scsi packet command requests,
+and indicates the buffer for scsi sense data.
+
+The data_len field is only present for scsi packet command
+requests, this field is deprecated, and should be ignored by the
+driver. Historically, devices copied data length there.
+
+The sense_len field is only present for scsi packet command
+requests and indicates the number of bytes actually written to
+the sense buffer.
+
+The residual field is only present for scsi packet command
+requests and indicates the residual size, calculated as data
+length - number of bytes actually transferred.
+
+The final status byte is written by the device: either
+VIRTIO_BLK_S_OK for success, VIRTIO_BLK_S_IOERR for host or guest
+error or VIRTIO_BLK_S_UNSUPP for a request unsupported by host:#define VIRTIO_BLK_S_OK 0
+
+#define VIRTIO_BLK_S_IOERR 1
+
+#define VIRTIO_BLK_S_UNSUPP 2
+
+Historically, devices assumed that the fields type, ioprio and
+sector reside in a single, separate read-only buffer; the fields
+errors, data_len, sense_len and residual reside in a single,
+separate write-only buffer; the sense field in a separate
+write-only buffer of size 96 bytes, by itself; the fields errors,
+data_len, sense_len and residual in a single write-only buffer;
+and the status field is a separate read-only buffer of size 1
+byte, by itself.
+
+Appendix E: Console Device
+
+The virtio console device is a simple device for data input and
+output. A device may have one or more ports. Each port has a pair
+of input and output virtqueues. Moreover, a device has a pair of
+control IO virtqueues. The control virtqueues are used to
+communicate information between the device and the driver about
+ports being opened and closed on either side of the connection,
+indication from the host about whether a particular port is a
+console port, adding new ports, port hot-plug/unplug, etc., and
+indication from the guest about whether a port or a device was
+successfully added, port open/close, etc.. For data IO, one or
+more empty buffers are placed in the receive queue for incoming
+data and outgoing characters are placed in the transmit queue.
+
+ Configuration
+
+ Subsystem Device ID 3
+
+ Virtqueues 0:receiveq(port0). 1:transmitq(port0), 2:control
+ receiveq[footnote:
+Ports 2 onwards only if VIRTIO_CONSOLE_F_MULTIPORT is set
+], 3:control transmitq, 4:receiveq(port1), 5:transmitq(port1),
+ ...
+
+ Feature bits
+
+ VIRTIO_CONSOLE_F_SIZE (0) Configuration cols and rows fields
+ are valid.
+
+ VIRTIO_CONSOLE_F_MULTIPORT(1) Device has support for multiple
+ ports; configuration fields nr_ports and max_nr_ports are
+ valid and control virtqueues will be used.
+
+ Device configuration layout The size of the console is supplied
+ in the configuration space if the VIRTIO_CONSOLE_F_SIZE feature
+ is set. Furthermore, if the VIRTIO_CONSOLE_F_MULTIPORT feature
+ is set, the maximum number of ports supported by the device can
+ be fetched.struct virtio_console_config {
+
+ u16 cols;
+
+ u16 rows;
+
+
+
+ u32 max_nr_ports;
+
+};
+
+ Device Initialization
+
+ If the VIRTIO_CONSOLE_F_SIZE feature is negotiated, the driver
+ can read the console dimensions from the configuration fields.
+
+ If the VIRTIO_CONSOLE_F_MULTIPORT feature is negotiated, the
+ driver can spawn multiple ports, not all of which may be
+ attached to a console. Some could be generic ports. In this
+ case, the control virtqueues are enabled and according to the
+ max_nr_ports configuration-space value, the appropriate number
+ of virtqueues are created. A control message indicating the
+ driver is ready is sent to the host. The host can then send
+ control messages for adding new ports to the device. After
+ creating and initializing each port, a
+ VIRTIO_CONSOLE_PORT_READY control message is sent to the host
+ for that port so the host can let us know of any additional
+ configuration options set for that port.
+
+ The receiveq for each port is populated with one or more
+ receive buffers.
+
+ Device Operation
+
+ For output, a buffer containing the characters is placed in the
+ port's transmitq.[footnote:
+Because this is high importance and low bandwidth, the current
+Linux implementation polls for the buffer to be used, rather than
+waiting for an interrupt, simplifying the implementation
+significantly. However, for generic serial ports with the
+O_NONBLOCK flag set, the polling limitation is relaxed and the
+consumed buffers are freed upon the next write or poll call or
+when a port is closed or hot-unplugged.
+]
+
+ When a buffer is used in the receiveq (signalled by an
+ interrupt), the contents is the input to the port associated
+ with the virtqueue for which the notification was received.
+
+ If the driver negotiated the VIRTIO_CONSOLE_F_SIZE feature, a
+ configuration change interrupt may occur. The updated size can
+ be read from the configuration fields.
+
+ If the driver negotiated the VIRTIO_CONSOLE_F_MULTIPORT
+ feature, active ports are announced by the host using the
+ VIRTIO_CONSOLE_PORT_ADD control message. The same message is
+ used for port hot-plug as well.
+
+ If the host specified a port `name', a sysfs attribute is
+ created with the name filled in, so that udev rules can be
+ written that can create a symlink from the port's name to the
+ char device for port discovery by applications in the guest.
+
+ Changes to ports' state are effected by control messages.
+ Appropriate action is taken on the port indicated in the
+ control message. The layout of the structure of the control
+ buffer and the events associated are:struct virtio_console_control {
+
+ uint32_t id; /* Port number */
+
+ uint16_t event; /* The kind of control event */
+
+ uint16_t value; /* Extra information for the event */
+
+};
+
+
+
+/* Some events for the internal messages (control packets) */
+
+
+
+#define VIRTIO_CONSOLE_DEVICE_READY 0
+
+#define VIRTIO_CONSOLE_PORT_ADD 1
+
+#define VIRTIO_CONSOLE_PORT_REMOVE 2
+
+#define VIRTIO_CONSOLE_PORT_READY 3
+
+#define VIRTIO_CONSOLE_CONSOLE_PORT 4
+
+#define VIRTIO_CONSOLE_RESIZE 5
+
+#define VIRTIO_CONSOLE_PORT_OPEN 6
+
+#define VIRTIO_CONSOLE_PORT_NAME 7
+
+Appendix F: Entropy Device
+
+The virtio entropy device supplies high-quality randomness for
+guest use.
+
+ Configuration
+
+ Subsystem Device ID 4
+
+ Virtqueues 0:requestq.
+
+ Feature bits None currently defined
+
+ Device configuration layout None currently defined.
+
+ Device Initialization
+
+ The virtqueue is initialized
+
+ Device Operation
+
+When the driver requires random bytes, it places the descriptor
+of one or more buffers in the queue. It will be completely filled
+by random data by the device.
+
+Appendix G: Memory Balloon Device
+
+The virtio memory balloon device is a primitive device for
+managing guest memory: the device asks for a certain amount of
+memory, and the guest supplies it (or withdraws it, if the device
+has more than it asks for). This allows the guest to adapt to
+changes in allowance of underlying physical memory. If the
+feature is negotiated, the device can also be used to communicate
+guest memory statistics to the host.
+
+ Configuration
+
+ Subsystem Device ID 5
+
+ Virtqueues 0:inflateq. 1:deflateq. 2:statsq.[footnote:
+Only if VIRTIO_BALLON_F_STATS_VQ set
+]
+
+ Feature bits
+
+ VIRTIO_BALLOON_F_MUST_TELL_HOST (0) Host must be told before
+ pages from the balloon are used.
+
+ VIRTIO_BALLOON_F_STATS_VQ (1) A virtqueue for reporting guest
+ memory statistics is present.
+
+ Device configuration layout Both fields of this configuration
+ are always available. Note that they are little endian, despite
+ convention that device fields are guest endian:struct virtio_balloon_config {
+
+ u32 num_pages;
+
+ u32 actual;
+
+};
+
+ Device Initialization
+
+ The inflate and deflate virtqueues are identified.
+
+ If the VIRTIO_BALLOON_F_STATS_VQ feature bit is negotiated:
+
+ Identify the stats virtqueue.
+
+ Add one empty buffer to the stats virtqueue and notify the
+ host.
+
+Device operation begins immediately.
+
+ Device Operation
+
+ Memory Ballooning The device is driven by the receipt of a
+ configuration change interrupt.
+
+ The “num_pages” configuration field is examined. If this is
+ greater than the “actual” number of pages, memory must be given
+ to the balloon. If it is less than the “actual” number of
+ pages, memory may be taken back from the balloon for general
+ use.
+
+ To supply memory to the balloon (aka. inflate):
+
+ The driver constructs an array of addresses of unused memory
+ pages. These addresses are divided by 4096[footnote:
+This is historical, and independent of the guest page size
+] and the descriptor describing the resulting 32-bit array is
+ added to the inflateq.
+
+ To remove memory from the balloon (aka. deflate):
+
+ The driver constructs an array of addresses of memory pages it
+ has previously given to the balloon, as described above. This
+ descriptor is added to the deflateq.
+
+ If the VIRTIO_BALLOON_F_MUST_TELL_HOST feature is set, the
+ guest may not use these requested pages until that descriptor
+ in the deflateq has been used by the device.
+
+ Otherwise, the guest may begin to re-use pages previously given
+ to the balloon before the device has acknowledged their
+ withdrawl. [footnote:
+In this case, deflation advice is merely a courtesy
+]
+
+ In either case, once the device has completed the inflation or
+ deflation, the “actual” field of the configuration should be
+ updated to reflect the new number of pages in the balloon.[footnote:
+As updates to configuration space are not atomic, this field
+isn't particularly reliable, but can be used to diagnose buggy
+guests.
+]
+
+ Memory Statistics
+
+The stats virtqueue is atypical because communication is driven
+by the device (not the driver). The channel becomes active at
+driver initialization time when the driver adds an empty buffer
+and notifies the device. A request for memory statistics proceeds
+as follows:
+
+ The device pushes the buffer onto the used ring and sends an
+ interrupt.
+
+ The driver pops the used buffer and discards it.
+
+ The driver collects memory statistics and writes them into a
+ new buffer.
+
+ The driver adds the buffer to the virtqueue and notifies the
+ device.
+
+ The device pops the buffer (retaining it to initiate a
+ subsequent request) and consumes the statistics.
+
+ Memory Statistics Format Each statistic consists of a 16 bit
+ tag and a 64 bit value. Both quantities are represented in the
+ native endian of the guest. All statistics are optional and the
+ driver may choose which ones to supply. To guarantee backwards
+ compatibility, unsupported statistics should be omitted.
+
+ struct virtio_balloon_stat {
+
+#define VIRTIO_BALLOON_S_SWAP_IN 0
+
+#define VIRTIO_BALLOON_S_SWAP_OUT 1
+
+#define VIRTIO_BALLOON_S_MAJFLT 2
+
+#define VIRTIO_BALLOON_S_MINFLT 3
+
+#define VIRTIO_BALLOON_S_MEMFREE 4
+
+#define VIRTIO_BALLOON_S_MEMTOT 5
+
+ u16 tag;
+
+ u64 val;
+
+} __attribute__((packed));
+
+ Tags
+
+ VIRTIO_BALLOON_S_SWAP_IN The amount of memory that has been
+ swapped in (in bytes).
+
+ VIRTIO_BALLOON_S_SWAP_OUT The amount of memory that has been
+ swapped out to disk (in bytes).
+
+ VIRTIO_BALLOON_S_MAJFLT The number of major page faults that
+ have occurred.
+
+ VIRTIO_BALLOON_S_MINFLT The number of minor page faults that
+ have occurred.
+
+ VIRTIO_BALLOON_S_MEMFREE The amount of memory not being used
+ for any purpose (in bytes).
+
+ VIRTIO_BALLOON_S_MEMTOT The total amount of memory available
+ (in bytes).
+
select ACPI_NUMA
select SWIOTLB
select PCI_MSI
- select DMAR
help
This selects the system type of your hardware. A "generic" kernel
will run on any supported IA-64 system. However, if you configure
# CONFIG_CRYPTO_ANSI_CPRNG is not set
CONFIG_CRC_T10DIF=y
CONFIG_MISC_DEVICES=y
+CONFIG_DMAR=y
select PERF_USE_VMALLOC
select IRQ_PREFLOW_FASTEOI
select ARCH_HAVE_NMI_SAFE_CMPXCHG
+ select HAVE_C_RECORDMCOUNT
config ARCH_DEFCONFIG
string
*(volatile __u32 *)&lp->lock = ~0U;
}
+static void inline arch_write_unlock(arch_rwlock_t *lock)
+{
+ __asm__ __volatile__(
+" st %%g0, [%0]"
+ : /* no outputs */
+ : "r" (lock)
+ : "memory");
+}
+
static inline int arch_write_trylock(arch_rwlock_t *rw)
{
unsigned int val;
res; \
})
-#define arch_write_unlock(rw) do { (rw)->lock = 0; } while(0)
-
#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
#define arch_read_lock_flags(rw, flags) arch_read_lock(rw)
#define arch_write_lock_flags(rw, flags) arch_write_lock(rw)
return result;
}
-#define arch_read_lock(p) arch_read_lock(p)
#define arch_read_lock_flags(p, f) arch_read_lock(p)
-#define arch_read_trylock(p) arch_read_trylock(p)
-#define arch_read_unlock(p) arch_read_unlock(p)
-#define arch_write_lock(p) arch_write_lock(p)
#define arch_write_lock_flags(p, f) arch_write_lock(p)
-#define arch_write_unlock(p) arch_write_unlock(p)
-#define arch_write_trylock(p) arch_write_trylock(p)
#define arch_read_can_lock(rw) (!((rw)->lock & 0x80000000UL))
#define arch_write_can_lock(rw) (!(rw)->lock)
depends on HAVE_KVM
# for device assignment:
depends on PCI
+ # for TASKSTATS/TASK_DELAY_ACCT:
+ depends on NET
select PREEMPT_NOTIFIERS
select MMU_NOTIFIER
select ANON_INODES
select KVM_ASYNC_PF
select USER_RETURN_NOTIFIER
select KVM_MMIO
+ select TASKSTATS
select TASK_DELAY_ACCT
---help---
Support hosting fully virtualized guest machines using hardware
#include <asm/traps.h> /* dotraplinkage, ... */
#include <asm/pgalloc.h> /* pgd_*(), ... */
#include <asm/kmemcheck.h> /* kmemcheck_*(), ... */
+#include <asm/vsyscall.h>
/*
* Page fault error code bits:
return 0;
}
+/**
+ * pm_genpd_poweroff_unused - Power off all PM domains with no devices in use.
+ */
+void pm_genpd_poweroff_unused(void)
+{
+ struct generic_pm_domain *genpd;
+
+ mutex_lock(&gpd_list_lock);
+
+ list_for_each_entry(genpd, &gpd_list, gpd_list_node)
+ genpd_queue_power_off_work(genpd);
+
+ mutex_unlock(&gpd_list_lock);
+}
+
#else
static inline void genpd_power_off_work_fn(struct work_struct *work) {}
list_add(&genpd->gpd_list_node, &gpd_list);
mutex_unlock(&gpd_list_lock);
}
-
-/**
- * pm_genpd_poweroff_unused - Power off all PM domains with no devices in use.
- */
-void pm_genpd_poweroff_unused(void)
-{
- struct generic_pm_domain *genpd;
-
- mutex_lock(&gpd_list_lock);
-
- list_for_each_entry(genpd, &gpd_list, gpd_list_node)
- genpd_queue_power_off_work(genpd);
-
- mutex_unlock(&gpd_list_lock);
-}
}
EXPORT_SYMBOL_GPL(regmap_init_i2c);
+MODULE_LICENSE("GPL");
#include <linux/regmap.h>
#include <linux/spi/spi.h>
#include <linux/init.h>
+#include <linux/module.h>
static int regmap_spi_write(struct device *dev, const void *data, size_t count)
{
return regmap_init(&spi->dev, ®map_spi, config);
}
EXPORT_SYMBOL_GPL(regmap_init_spi);
+
+MODULE_LICENSE("GPL");
u8[0] |= map->bus->read_flag_mask;
ret = map->bus->read(map->dev, map->work_buf, map->format.reg_bytes,
- val, map->format.val_bytes);
+ val, val_len);
if (ret != 0)
return ret;
char *type, *optype, *err, *msg;
unsigned long error = m->status & 0x1ff0000l;
u32 optypenum = (m->status >> 4) & 0x07;
- u32 core_err_cnt = (m->status >> 38) && 0x7fff;
+ u32 core_err_cnt = (m->status >> 38) & 0x7fff;
u32 dimm = (m->misc >> 16) & 0x3;
u32 channel = (m->misc >> 18) & 0x3;
u32 syndrome = m->misc >> 32;
struct fw_cdev_event_phy_packet phy_packet;
};
-static inline void __user *u64_to_uptr(__u64 value)
+#ifdef CONFIG_COMPAT
+static void __user *u64_to_uptr(u64 value)
+{
+ if (is_compat_task())
+ return compat_ptr(value);
+ else
+ return (void __user *)(unsigned long)value;
+}
+
+static u64 uptr_to_u64(void __user *ptr)
+{
+ if (is_compat_task())
+ return ptr_to_compat(ptr);
+ else
+ return (u64)(unsigned long)ptr;
+}
+#else
+static inline void __user *u64_to_uptr(u64 value)
{
return (void __user *)(unsigned long)value;
}
-static inline __u64 uptr_to_u64(void __user *ptr)
+static inline u64 uptr_to_u64(void __user *ptr)
{
- return (__u64)(unsigned long)ptr;
+ return (u64)(unsigned long)ptr;
}
+#endif /* CONFIG_COMPAT */
static int fw_device_op_open(struct inode *inode, struct file *file)
{
ohci_driver_name, ohci)) {
fw_error("Failed to allocate interrupt %d.\n", dev->irq);
pci_disable_msi(dev);
- dma_free_coherent(ohci->card.device, CONFIG_ROM_SIZE,
- ohci->config_rom, ohci->config_rom_bus);
+
+ if (config_rom) {
+ dma_free_coherent(ohci->card.device, CONFIG_ROM_SIZE,
+ ohci->next_config_rom,
+ ohci->next_config_rom_bus);
+ ohci->next_config_rom = NULL;
+ }
return -EIO;
}
seq_printf(m, "Interrupts received: %d\n",
atomic_read(&dev_priv->irq_received));
for (i = 0; i < I915_NUM_RINGS; i++) {
- if (IS_GEN6(dev)) {
+ if (IS_GEN6(dev) || IS_GEN7(dev)) {
seq_printf(m, "Graphics Interrupt mask (%s): %08x\n",
dev_priv->ring[i].name,
I915_READ_IMR(&dev_priv->ring[i]));
#include <linux/io-mapping.h>
#include <linux/i2c.h>
#include <drm/intel-gtt.h>
+#include <linux/backlight.h>
/* General customization:
*/
int child_dev_num;
struct child_device_config *child_dev;
struct drm_connector *int_lvds_connector;
+ struct drm_connector *int_edp_connector;
bool mchbar_need_disable;
/* list of fbdev register on this device */
struct intel_fbdev *fbdev;
+ struct backlight_device *backlight;
+
struct drm_property *broadcast_rgb_property;
struct drm_property *force_audio_property;
dev->driver->get_vblank_counter = gm45_get_vblank_counter;
}
-
- dev->driver->get_vblank_timestamp = i915_get_vblank_timestamp;
+ if (drm_core_check_feature(dev, DRIVER_MODESET))
+ dev->driver->get_vblank_timestamp = i915_get_vblank_timestamp;
+ else
+ dev->driver->get_vblank_timestamp = NULL;
dev->driver->get_scanout_position = i915_get_crtc_scanoutpos;
if (IS_IVYBRIDGE(dev)) {
#define ADPA_PIPE_SELECT_MASK (1<<30)
#define ADPA_PIPE_A_SELECT 0
#define ADPA_PIPE_B_SELECT (1<<30)
+#define ADPA_PIPE_SELECT(pipe) ((pipe) << 30)
#define ADPA_USE_VGA_HVPOLARITY (1<<15)
#define ADPA_SETS_HVPOLARITY 0
#define ADPA_VSYNC_CNTL_DISABLE (1<<11)
/* Selects pipe B for LVDS data. Must be set on pre-965. */
#define LVDS_PIPEB_SELECT (1 << 30)
#define LVDS_PIPE_MASK (1 << 30)
+#define LVDS_PIPE(pipe) ((pipe) << 30)
/* LVDS dithering flag on 965/g4x platform */
#define LVDS_ENABLE_DITHER (1 << 25)
/* LVDS sync polarity flags. Set to invert (i.e. negative) */
#define LVDS_B0B3_POWER_DOWN (0 << 2)
#define LVDS_B0B3_POWER_UP (3 << 2)
-#define LVDS_PIPE_ENABLED(V, P) \
- (((V) & (LVDS_PIPE_MASK | LVDS_PORT_EN)) == ((P) << 30 | LVDS_PORT_EN))
-
/* Video Data Island Packet control */
#define VIDEO_DIP_DATA 0x61178
#define VIDEO_DIP_CTL 0x61170
#define ADPA_CRT_HOTPLUG_VOLREF_475MV (1<<17)
#define ADPA_CRT_HOTPLUG_FORCE_TRIGGER (1<<16)
-#define ADPA_PIPE_ENABLED(V, P) \
- (((V) & (ADPA_TRANS_SELECT_MASK | ADPA_DAC_ENABLE)) == ((P) << 30 | ADPA_DAC_ENABLE))
-
/* or SDVOB */
#define HDMIB 0xe1140
#define PORT_ENABLE (1 << 31)
#define TRANSCODER_A (0)
#define TRANSCODER_B (1 << 30)
+#define TRANSCODER(pipe) ((pipe) << 30)
#define TRANSCODER_MASK (1 << 30)
#define COLOR_FORMAT_8bpc (0)
#define COLOR_FORMAT_12bpc (3 << 26)
#define HSYNC_ACTIVE_HIGH (1 << 3)
#define PORT_DETECTED (1 << 2)
-#define HDMI_PIPE_ENABLED(V, P) \
- (((V) & (TRANSCODER_MASK | PORT_ENABLE)) == ((P) << 30 | PORT_ENABLE))
-
/* PCH SDVOB multiplex with HDMIB */
#define PCH_SDVOB HDMIB
#define PORT_TRANS_B_SEL_CPT (1<<29)
#define PORT_TRANS_C_SEL_CPT (2<<29)
#define PORT_TRANS_SEL_MASK (3<<29)
+#define PORT_TRANS_SEL_CPT(pipe) ((pipe) << 29)
#define TRANS_DP_CTL_A 0xe0300
#define TRANS_DP_CTL_B 0xe1300
}
mutex_unlock(&dev->struct_mutex);
- intel_init_clock_gating(dev);
+ if (drm_core_check_feature(dev, DRIVER_MODESET))
+ intel_init_clock_gating(dev);
if (IS_IRONLAKE_M(dev)) {
ironlake_enable_drps(dev);
pipe_name(pipe));
}
-static bool dp_pipe_enabled(struct drm_i915_private *dev_priv, enum pipe pipe,
- int reg, u32 port_sel, u32 val)
+static bool dp_pipe_enabled(struct drm_i915_private *dev_priv,
+ enum pipe pipe, u32 port_sel, u32 val)
{
if ((val & DP_PORT_EN) == 0)
return false;
return true;
}
+static bool hdmi_pipe_enabled(struct drm_i915_private *dev_priv,
+ enum pipe pipe, u32 val)
+{
+ if ((val & PORT_ENABLE) == 0)
+ return false;
+
+ if (HAS_PCH_CPT(dev_priv->dev)) {
+ if ((val & PORT_TRANS_SEL_MASK) != PORT_TRANS_SEL_CPT(pipe))
+ return false;
+ } else {
+ if ((val & TRANSCODER_MASK) != TRANSCODER(pipe))
+ return false;
+ }
+ return true;
+}
+
+static bool lvds_pipe_enabled(struct drm_i915_private *dev_priv,
+ enum pipe pipe, u32 val)
+{
+ if ((val & LVDS_PORT_EN) == 0)
+ return false;
+
+ if (HAS_PCH_CPT(dev_priv->dev)) {
+ if ((val & PORT_TRANS_SEL_MASK) != PORT_TRANS_SEL_CPT(pipe))
+ return false;
+ } else {
+ if ((val & LVDS_PIPE_MASK) != LVDS_PIPE(pipe))
+ return false;
+ }
+ return true;
+}
+
+static bool adpa_pipe_enabled(struct drm_i915_private *dev_priv,
+ enum pipe pipe, u32 val)
+{
+ if ((val & ADPA_DAC_ENABLE) == 0)
+ return false;
+ if (HAS_PCH_CPT(dev_priv->dev)) {
+ if ((val & PORT_TRANS_SEL_MASK) != PORT_TRANS_SEL_CPT(pipe))
+ return false;
+ } else {
+ if ((val & ADPA_PIPE_SELECT_MASK) != ADPA_PIPE_SELECT(pipe))
+ return false;
+ }
+ return true;
+}
+
static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv,
enum pipe pipe, int reg, u32 port_sel)
{
u32 val = I915_READ(reg);
- WARN(dp_pipe_enabled(dev_priv, pipe, reg, port_sel, val),
+ WARN(dp_pipe_enabled(dev_priv, pipe, port_sel, val),
"PCH DP (0x%08x) enabled on transcoder %c, should be disabled\n",
reg, pipe_name(pipe));
}
enum pipe pipe, int reg)
{
u32 val = I915_READ(reg);
- WARN(HDMI_PIPE_ENABLED(val, pipe),
+ WARN(hdmi_pipe_enabled(dev_priv, val, pipe),
"PCH DP (0x%08x) enabled on transcoder %c, should be disabled\n",
reg, pipe_name(pipe));
}
reg = PCH_ADPA;
val = I915_READ(reg);
- WARN(ADPA_PIPE_ENABLED(val, pipe),
+ WARN(adpa_pipe_enabled(dev_priv, val, pipe),
"PCH VGA enabled on transcoder %c, should be disabled\n",
pipe_name(pipe));
reg = PCH_LVDS;
val = I915_READ(reg);
- WARN(LVDS_PIPE_ENABLED(val, pipe),
+ WARN(lvds_pipe_enabled(dev_priv, val, pipe),
"PCH LVDS enabled on transcoder %c, should be disabled\n",
pipe_name(pipe));
enum pipe pipe, int reg, u32 port_sel)
{
u32 val = I915_READ(reg);
- if (dp_pipe_enabled(dev_priv, pipe, reg, port_sel, val)) {
+ if (dp_pipe_enabled(dev_priv, pipe, port_sel, val)) {
DRM_DEBUG_KMS("Disabling pch dp %x on pipe %d\n", reg, pipe);
I915_WRITE(reg, val & ~DP_PORT_EN);
}
enum pipe pipe, int reg)
{
u32 val = I915_READ(reg);
- if (HDMI_PIPE_ENABLED(val, pipe)) {
+ if (hdmi_pipe_enabled(dev_priv, val, pipe)) {
DRM_DEBUG_KMS("Disabling pch HDMI %x on pipe %d\n",
reg, pipe);
I915_WRITE(reg, val & ~PORT_ENABLE);
reg = PCH_ADPA;
val = I915_READ(reg);
- if (ADPA_PIPE_ENABLED(val, pipe))
+ if (adpa_pipe_enabled(dev_priv, val, pipe))
I915_WRITE(reg, val & ~ADPA_DAC_ENABLE);
reg = PCH_LVDS;
val = I915_READ(reg);
- if (LVDS_PIPE_ENABLED(val, pipe)) {
+ if (lvds_pipe_enabled(dev_priv, val, pipe)) {
+ DRM_DEBUG_KMS("disable lvds on pipe %d val 0x%08x\n", pipe, val);
I915_WRITE(reg, val & ~LVDS_PORT_EN);
POSTING_READ(reg);
udelay(100);
return ret;
}
+static void ironlake_update_pch_refclk(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_mode_config *mode_config = &dev->mode_config;
+ struct drm_crtc *crtc;
+ struct intel_encoder *encoder;
+ struct intel_encoder *has_edp_encoder = NULL;
+ u32 temp;
+ bool has_lvds = false;
+
+ /* We need to take the global config into account */
+ list_for_each_entry(crtc, &mode_config->crtc_list, head) {
+ if (!crtc->enabled)
+ continue;
+
+ list_for_each_entry(encoder, &mode_config->encoder_list,
+ base.head) {
+ if (encoder->base.crtc != crtc)
+ continue;
+
+ switch (encoder->type) {
+ case INTEL_OUTPUT_LVDS:
+ has_lvds = true;
+ case INTEL_OUTPUT_EDP:
+ has_edp_encoder = encoder;
+ break;
+ }
+ }
+ }
+
+ /* Ironlake: try to setup display ref clock before DPLL
+ * enabling. This is only under driver's control after
+ * PCH B stepping, previous chipset stepping should be
+ * ignoring this setting.
+ */
+ temp = I915_READ(PCH_DREF_CONTROL);
+ /* Always enable nonspread source */
+ temp &= ~DREF_NONSPREAD_SOURCE_MASK;
+ temp |= DREF_NONSPREAD_SOURCE_ENABLE;
+ temp &= ~DREF_SSC_SOURCE_MASK;
+ temp |= DREF_SSC_SOURCE_ENABLE;
+ I915_WRITE(PCH_DREF_CONTROL, temp);
+
+ POSTING_READ(PCH_DREF_CONTROL);
+ udelay(200);
+
+ if (has_edp_encoder) {
+ if (intel_panel_use_ssc(dev_priv)) {
+ temp |= DREF_SSC1_ENABLE;
+ I915_WRITE(PCH_DREF_CONTROL, temp);
+
+ POSTING_READ(PCH_DREF_CONTROL);
+ udelay(200);
+ }
+ temp &= ~DREF_CPU_SOURCE_OUTPUT_MASK;
+
+ /* Enable CPU source on CPU attached eDP */
+ if (!intel_encoder_is_pch_edp(&has_edp_encoder->base)) {
+ if (intel_panel_use_ssc(dev_priv))
+ temp |= DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD;
+ else
+ temp |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD;
+ } else {
+ /* Enable SSC on PCH eDP if needed */
+ if (intel_panel_use_ssc(dev_priv)) {
+ DRM_ERROR("enabling SSC on PCH\n");
+ temp |= DREF_SUPERSPREAD_SOURCE_ENABLE;
+ }
+ }
+ I915_WRITE(PCH_DREF_CONTROL, temp);
+ POSTING_READ(PCH_DREF_CONTROL);
+ udelay(200);
+ }
+}
+
static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
struct drm_display_mode *mode,
struct drm_display_mode *adjusted_mode,
ironlake_compute_m_n(intel_crtc->bpp, lane, target_clock, link_bw,
&m_n);
- /* Ironlake: try to setup display ref clock before DPLL
- * enabling. This is only under driver's control after
- * PCH B stepping, previous chipset stepping should be
- * ignoring this setting.
- */
- temp = I915_READ(PCH_DREF_CONTROL);
- /* Always enable nonspread source */
- temp &= ~DREF_NONSPREAD_SOURCE_MASK;
- temp |= DREF_NONSPREAD_SOURCE_ENABLE;
- temp &= ~DREF_SSC_SOURCE_MASK;
- temp |= DREF_SSC_SOURCE_ENABLE;
- I915_WRITE(PCH_DREF_CONTROL, temp);
-
- POSTING_READ(PCH_DREF_CONTROL);
- udelay(200);
-
- if (has_edp_encoder) {
- if (intel_panel_use_ssc(dev_priv)) {
- temp |= DREF_SSC1_ENABLE;
- I915_WRITE(PCH_DREF_CONTROL, temp);
-
- POSTING_READ(PCH_DREF_CONTROL);
- udelay(200);
- }
- temp &= ~DREF_CPU_SOURCE_OUTPUT_MASK;
-
- /* Enable CPU source on CPU attached eDP */
- if (!intel_encoder_is_pch_edp(&has_edp_encoder->base)) {
- if (intel_panel_use_ssc(dev_priv))
- temp |= DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD;
- else
- temp |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD;
- } else {
- /* Enable SSC on PCH eDP if needed */
- if (intel_panel_use_ssc(dev_priv)) {
- DRM_ERROR("enabling SSC on PCH\n");
- temp |= DREF_SUPERSPREAD_SOURCE_ENABLE;
- }
- }
- I915_WRITE(PCH_DREF_CONTROL, temp);
- POSTING_READ(PCH_DREF_CONTROL);
- udelay(200);
- }
+ ironlake_update_pch_refclk(dev);
fp = clock.n << 16 | clock.m1 << 8 | clock.m2;
if (has_reduced_clock)
static void
intel_dp_destroy (struct drm_connector *connector)
{
+ struct drm_device *dev = connector->dev;
+
+ if (intel_dpd_is_edp(dev))
+ intel_panel_destroy_backlight(dev);
+
drm_sysfs_connector_remove(connector);
drm_connector_cleanup(connector);
kfree(connector);
DRM_MODE_TYPE_PREFERRED;
}
}
+ dev_priv->int_edp_connector = connector;
+ intel_panel_setup_backlight(dev);
}
intel_dp_add_properties(intel_dp, connector);
extern u32 intel_panel_get_max_backlight(struct drm_device *dev);
extern u32 intel_panel_get_backlight(struct drm_device *dev);
extern void intel_panel_set_backlight(struct drm_device *dev, u32 level);
-extern void intel_panel_setup_backlight(struct drm_device *dev);
+extern int intel_panel_setup_backlight(struct drm_device *dev);
extern void intel_panel_enable_backlight(struct drm_device *dev);
extern void intel_panel_disable_backlight(struct drm_device *dev);
+extern void intel_panel_destroy_backlight(struct drm_device *dev);
extern enum drm_connector_status intel_panel_detect(struct drm_device *dev);
extern void intel_crtc_load_lut(struct drm_crtc *crtc);
{
struct drm_device *dev = intel_lvds->base.base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 ctl_reg, lvds_reg;
+ u32 ctl_reg, lvds_reg, stat_reg;
if (HAS_PCH_SPLIT(dev)) {
ctl_reg = PCH_PP_CONTROL;
lvds_reg = PCH_LVDS;
+ stat_reg = PCH_PP_STATUS;
} else {
ctl_reg = PP_CONTROL;
lvds_reg = LVDS;
+ stat_reg = PP_STATUS;
}
I915_WRITE(lvds_reg, I915_READ(lvds_reg) | LVDS_PORT_EN);
DRM_DEBUG_KMS("applying panel-fitter: %x, %x\n",
intel_lvds->pfit_control,
intel_lvds->pfit_pgm_ratios);
- if (wait_for((I915_READ(PP_STATUS) & PP_ON) == 0, 1000)) {
- DRM_ERROR("timed out waiting for panel to power off\n");
- } else {
- I915_WRITE(PFIT_PGM_RATIOS, intel_lvds->pfit_pgm_ratios);
- I915_WRITE(PFIT_CONTROL, intel_lvds->pfit_control);
- intel_lvds->pfit_dirty = false;
- }
+
+ I915_WRITE(PFIT_PGM_RATIOS, intel_lvds->pfit_pgm_ratios);
+ I915_WRITE(PFIT_CONTROL, intel_lvds->pfit_control);
+ intel_lvds->pfit_dirty = false;
}
I915_WRITE(ctl_reg, I915_READ(ctl_reg) | POWER_TARGET_ON);
POSTING_READ(lvds_reg);
+ if (wait_for((I915_READ(stat_reg) & PP_ON) != 0, 1000))
+ DRM_ERROR("timed out waiting for panel to power on\n");
intel_panel_enable_backlight(dev);
}
{
struct drm_device *dev = intel_lvds->base.base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 ctl_reg, lvds_reg;
+ u32 ctl_reg, lvds_reg, stat_reg;
if (HAS_PCH_SPLIT(dev)) {
ctl_reg = PCH_PP_CONTROL;
lvds_reg = PCH_LVDS;
+ stat_reg = PCH_PP_STATUS;
} else {
ctl_reg = PP_CONTROL;
lvds_reg = LVDS;
+ stat_reg = PP_STATUS;
}
intel_panel_disable_backlight(dev);
I915_WRITE(ctl_reg, I915_READ(ctl_reg) & ~POWER_TARGET_ON);
+ if (wait_for((I915_READ(stat_reg) & PP_ON) == 0, 1000))
+ DRM_ERROR("timed out waiting for panel to power off\n");
if (intel_lvds->pfit_control) {
- if (wait_for((I915_READ(PP_STATUS) & PP_ON) == 0, 1000))
- DRM_ERROR("timed out waiting for panel to power off\n");
-
I915_WRITE(PFIT_CONTROL, 0);
intel_lvds->pfit_dirty = true;
}
static void intel_lvds_prepare(struct drm_encoder *encoder)
{
- struct drm_device *dev = encoder->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_lvds *intel_lvds = to_intel_lvds(encoder);
- /* We try to do the minimum that is necessary in order to unlock
- * the registers for mode setting.
- *
- * On Ironlake, this is quite simple as we just set the unlock key
- * and ignore all subtleties. (This may cause some issues...)
- *
+ /*
* Prior to Ironlake, we must disable the pipe if we want to adjust
* the panel fitter. However at all other times we can just reset
* the registers regardless.
*/
-
- if (HAS_PCH_SPLIT(dev)) {
- I915_WRITE(PCH_PP_CONTROL,
- I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS);
- } else if (intel_lvds->pfit_dirty) {
- I915_WRITE(PP_CONTROL,
- (I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS)
- & ~POWER_TARGET_ON);
- } else {
- I915_WRITE(PP_CONTROL,
- I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS);
- }
+ if (!HAS_PCH_SPLIT(encoder->dev) && intel_lvds->pfit_dirty)
+ intel_lvds_disable(intel_lvds);
}
static void intel_lvds_commit(struct drm_encoder *encoder)
{
- struct drm_device *dev = encoder->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_lvds *intel_lvds = to_intel_lvds(encoder);
- /* Undo any unlocking done in prepare to prevent accidental
- * adjustment of the registers.
- */
- if (HAS_PCH_SPLIT(dev)) {
- u32 val = I915_READ(PCH_PP_CONTROL);
- if ((val & PANEL_UNLOCK_REGS) == PANEL_UNLOCK_REGS)
- I915_WRITE(PCH_PP_CONTROL, val & 0x3);
- } else {
- u32 val = I915_READ(PP_CONTROL);
- if ((val & PANEL_UNLOCK_REGS) == PANEL_UNLOCK_REGS)
- I915_WRITE(PP_CONTROL, val & 0x3);
- }
-
/* Always do a full power on as we do not know what state
* we were left in.
*/
struct drm_device *dev = connector->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ intel_panel_destroy_backlight(dev);
+
if (dev_priv->lid_notifier.notifier_call)
acpi_lid_notifier_unregister(&dev_priv->lid_notifier);
drm_sysfs_connector_remove(connector);
pwm = I915_READ(BLC_PWM_PCH_CTL1);
pwm |= PWM_PCH_ENABLE;
I915_WRITE(BLC_PWM_PCH_CTL1, pwm);
+ /*
+ * Unlock registers and just
+ * leave them unlocked
+ */
+ I915_WRITE(PCH_PP_CONTROL,
+ I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS);
+ } else {
+ /*
+ * Unlock registers and just
+ * leave them unlocked
+ */
+ I915_WRITE(PP_CONTROL,
+ I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS);
}
dev_priv->lid_notifier.notifier_call = intel_lid_notify;
if (acpi_lid_notifier_register(&dev_priv->lid_notifier)) {
/* keep the LVDS connector */
dev_priv->int_lvds_connector = connector;
drm_sysfs_connector_add(connector);
+
+ intel_panel_setup_backlight(dev);
+
return true;
failed:
asle->aslc = asle_stat;
}
-/* Only present on Ironlake+ */
void intel_opregion_gse_intr(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
dev_priv->backlight_enabled = true;
}
-void intel_panel_setup_backlight(struct drm_device *dev)
+static void intel_panel_init_backlight(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
return connector_status_unknown;
}
+
+#ifdef CONFIG_BACKLIGHT_CLASS_DEVICE
+static int intel_panel_update_status(struct backlight_device *bd)
+{
+ struct drm_device *dev = bl_get_data(bd);
+ intel_panel_set_backlight(dev, bd->props.brightness);
+ return 0;
+}
+
+static int intel_panel_get_brightness(struct backlight_device *bd)
+{
+ struct drm_device *dev = bl_get_data(bd);
+ return intel_panel_get_backlight(dev);
+}
+
+static const struct backlight_ops intel_panel_bl_ops = {
+ .update_status = intel_panel_update_status,
+ .get_brightness = intel_panel_get_brightness,
+};
+
+int intel_panel_setup_backlight(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct backlight_properties props;
+ struct drm_connector *connector;
+
+ intel_panel_init_backlight(dev);
+
+ if (dev_priv->int_lvds_connector)
+ connector = dev_priv->int_lvds_connector;
+ else if (dev_priv->int_edp_connector)
+ connector = dev_priv->int_edp_connector;
+ else
+ return -ENODEV;
+
+ props.type = BACKLIGHT_RAW;
+ props.max_brightness = intel_panel_get_max_backlight(dev);
+ dev_priv->backlight =
+ backlight_device_register("intel_backlight",
+ &connector->kdev, dev,
+ &intel_panel_bl_ops, &props);
+
+ if (IS_ERR(dev_priv->backlight)) {
+ DRM_ERROR("Failed to register backlight: %ld\n",
+ PTR_ERR(dev_priv->backlight));
+ dev_priv->backlight = NULL;
+ return -ENODEV;
+ }
+ dev_priv->backlight->props.brightness = intel_panel_get_backlight(dev);
+ return 0;
+}
+
+void intel_panel_destroy_backlight(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ if (dev_priv->backlight)
+ backlight_device_unregister(dev_priv->backlight);
+}
+#else
+int intel_panel_setup_backlight(struct drm_device *dev)
+{
+ intel_panel_init_backlight(dev);
+ return 0;
+}
+
+void intel_panel_destroy_backlight(struct drm_device *dev)
+{
+ return;
+}
+#endif
return true;
}
+bool radeon_dp_needs_link_train(struct radeon_connector *radeon_connector)
+{
+ u8 link_status[DP_LINK_STATUS_SIZE];
+ struct radeon_connector_atom_dig *dig = radeon_connector->con_priv;
+
+ if (!radeon_dp_get_link_status(radeon_connector, link_status))
+ return false;
+ if (dp_channel_eq_ok(link_status, dig->dp_lane_count))
+ return false;
+ return true;
+}
+
struct radeon_dp_link_train_info {
struct radeon_device *rdev;
struct drm_encoder *encoder;
!evergreen_average_bandwidth_vs_available_bandwidth(&wm) ||
!evergreen_check_latency_hiding(&wm) ||
(rdev->disp_priority == 2)) {
- DRM_INFO("force priority to high\n");
+ DRM_DEBUG_KMS("force priority to high\n");
priority_a_cnt |= PRIORITY_ALWAYS_ON;
priority_b_cnt |= PRIORITY_ALWAYS_ON;
}
radeon_hpd_set_polarity(rdev, radeon_connector->hpd.hpd);
- /* powering up/down the eDP panel generates hpd events which
- * can interfere with modesetting.
- */
- if (connector->connector_type == DRM_MODE_CONNECTOR_eDP)
+ /* if the connector is already off, don't turn it back on */
+ if (connector->dpms != DRM_MODE_DPMS_ON)
return;
- /* pre-r600 did not always have the hpd pins mapped accurately to connectors */
- if (rdev->family >= CHIP_R600) {
- if (radeon_hpd_sense(rdev, radeon_connector->hpd.hpd))
+ /* just deal with DP (not eDP) here. */
+ if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
+ int saved_dpms = connector->dpms;
+
+ if (radeon_hpd_sense(rdev, radeon_connector->hpd.hpd) &&
+ radeon_dp_needs_link_train(radeon_connector))
drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
else
drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
+ connector->dpms = saved_dpms;
}
}
{
struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
struct drm_display_mode *native_mode = &radeon_encoder->native_mode;
+ struct drm_display_mode *t, *mode;
+
+ /* If the EDID preferred mode doesn't match the native mode, use it */
+ list_for_each_entry_safe(mode, t, &connector->probed_modes, head) {
+ if (mode->type & DRM_MODE_TYPE_PREFERRED) {
+ if (mode->hdisplay != native_mode->hdisplay ||
+ mode->vdisplay != native_mode->vdisplay)
+ memcpy(native_mode, mode, sizeof(*mode));
+ }
+ }
/* Try to get native mode details from EDID if necessary */
if (!native_mode->clock) {
- struct drm_display_mode *t, *mode;
-
list_for_each_entry_safe(mode, t, &connector->probed_modes, head) {
if (mode->hdisplay == native_mode->hdisplay &&
mode->vdisplay == native_mode->vdisplay) {
}
}
}
+
if (!native_mode->clock) {
DRM_DEBUG_KMS("No LVDS native mode details, disabling RMX\n");
radeon_encoder->rmx_type = RMX_OFF;
#include <drm/radeon_drm.h>
#include <linux/vgaarb.h>
#include <linux/vga_switcheroo.h>
+#include <linux/efi.h>
#include "radeon_reg.h"
#include "radeon.h"
#include "atom.h"
{
uint32_t reg;
+ if (efi_enabled && rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE)
+ return false;
+
/* first check CRTCs */
if (ASIC_IS_DCE41(rdev)) {
reg = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET) |
default:
encoder->possible_crtcs = 0x3;
break;
+ case 4:
+ encoder->possible_crtcs = 0xf;
+ break;
case 6:
encoder->possible_crtcs = 0x3f;
break;
struct drm_display_mode *mode);
extern void radeon_dp_link_train(struct drm_encoder *encoder,
struct drm_connector *connector);
+extern bool radeon_dp_needs_link_train(struct radeon_connector *radeon_connector);
extern u8 radeon_dp_getsinktype(struct radeon_connector *radeon_connector);
extern bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector);
extern void atombios_dig_encoder_setup(struct drm_encoder *encoder, int action, int panel_mode);
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_neigh *neigh;
- struct neighbour *n;
+ struct neighbour *n = NULL;
unsigned long flags;
- n = dst_get_neighbour(skb_dst(skb));
- if (likely(skb_dst(skb) && n)) {
+ if (likely(skb_dst(skb)))
+ n = dst_get_neighbour(skb_dst(skb));
+
+ if (likely(n)) {
if (unlikely(!*to_ipoib_neigh(n))) {
ipoib_path_lookup(skb, dev);
return NETDEV_TX_OK;
/* verify PDU length */
datalen = ntoh24(hdr->dlength);
- if (datalen != rx_data_len) {
- printk(KERN_ERR "iscsi_iser: datalen %d (hdr) != %d (IB) \n",
- datalen, rx_data_len);
+ if (datalen > rx_data_len || (datalen + 4) < rx_data_len) {
+ iser_err("wrong datalen %d (hdr), %d (IB)\n",
+ datalen, rx_data_len);
rc = ISCSI_ERR_DATALEN;
goto error;
}
+ if (datalen != rx_data_len)
+ iser_dbg("aligned datalen (%d) hdr, %d (IB)\n",
+ datalen, rx_data_len);
+
/* read AHS */
ahslen = hdr->hlength * 4;
} while (0)
#define SHIFT_4K 12
-#define SIZE_4K (1UL << SHIFT_4K)
+#define SIZE_4K (1ULL << SHIFT_4K)
#define MASK_4K (~(SIZE_4K-1))
/* support up to 512KB in one RDMA */
memcpy(iser_conn->ib_conn->login_buf, task->data,
task->data_count);
tx_dsg->addr = iser_conn->ib_conn->login_dma;
- tx_dsg->length = data_seg_len;
+ tx_dsg->length = task->data_count;
tx_dsg->lkey = device->mr->lkey;
mdesc->num_sge = 2;
}
static int rtc_update_hrtimer(struct rtc_device *rtc, int enabled)
{
/*
- * We unconditionally cancel the timer here, because otherwise
+ * We always cancel the timer here first, because otherwise
* we could run into BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
* when we manage to start the timer before the callback
* returns HRTIMER_RESTART.
int err = 0;
unsigned long flags;
- if (freq <= 0 || freq > 5000)
+ if (freq <= 0 || freq > RTC_MAX_FREQ)
return -EINVAL;
retry:
spin_lock_irqsave(&rtc->irq_task_lock, flags);
/* Create drm encoder object */
connector = &dsi_connector->base.base;
encoder = &dbi_output->base.base;
+ /* Review this if we ever get MIPI-HDMI bridges or similar */
drm_encoder_init(dev,
encoder,
p_funcs->encoder_funcs,
- DRM_MODE_ENCODER_MIPI);
+ DRM_MODE_ENCODER_LVDS);
drm_encoder_helper_add(encoder, p_funcs->encoder_helper_funcs);
/* Attach to given connector */
#include "mdfld_dsi_output.h"
#include "mdfld_output.h"
-#define DRM_MODE_ENCODER_MIPI 5
-
-
/*
* DBI encoder which inherits from mdfld_dsi_encoder
*/
/* Create drm encoder object */
connector = &dsi_connector->base.base;
encoder = &dpi_output->base.base;
+ /*
+ * On existing hardware this will be a panel of some form,
+ * if future devices also have HDMI bridges this will need
+ * revisiting
+ */
drm_encoder_init(dev,
encoder,
p_funcs->encoder_funcs,
- DRM_MODE_ENCODER_MIPI);
+ DRM_MODE_ENCODER_LVDS);
drm_encoder_helper_add(encoder,
p_funcs->encoder_helper_funcs);
psb_output->type = (pipe == 0) ? INTEL_OUTPUT_MIPI : INTEL_OUTPUT_MIPI2;
connector = &psb_output->base;
- drm_connector_init(dev, connector, &mdfld_dsi_connector_funcs, DRM_MODE_CONNECTOR_MIPI);
+ /* Revisit type if MIPI/HDMI bridges ever appear on Medfield */
+ drm_connector_init(dev, connector, &mdfld_dsi_connector_funcs,
+ DRM_MODE_CONNECTOR_LVDS);
drm_connector_helper_add(connector, &mdfld_dsi_connector_helper_funcs);
connector->display_info.subpixel_order = SubPixelHorizontalRGB;
* DEALINGS IN THE SOFTWARE.
*/
-#define DRM_MODE_ENCODER_MIPI 5
-
/* Medfield DSI controller registers */
#define MIPIA_DEVICE_READY_REG 0xb000
/* Append new drm mode definition here, align with libdrm definition */
#define DRM_MODE_SCALE_NO_SCALE 2
-#define DRM_MODE_CONNECTOR_MIPI 15
enum {
CHIP_PSB_8108 = 0, /* Poulsbo */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/mman.h>
+#include <linux/module.h>
#include <linux/workqueue.h>
#include <xen/balloon.h>
#include <xen/tmem.h>
befs_data_stream *data = &befs_ino->i_data.ds;
befs_off_t len = data->size;
- befs_debug(sb, "Follow long symlink");
-
- link = kmalloc(len, GFP_NOFS);
- if (!link) {
- link = ERR_PTR(-ENOMEM);
- } else if (befs_read_lsymlink(sb, data, link, len) != len) {
- kfree(link);
- befs_error(sb, "Failed to read entire long symlink");
+ if (len == 0) {
+ befs_error(sb, "Long symlink with illegal length");
link = ERR_PTR(-EIO);
} else {
- link[len - 1] = '\0';
+ befs_debug(sb, "Follow long symlink");
+
+ link = kmalloc(len, GFP_NOFS);
+ if (!link) {
+ link = ERR_PTR(-ENOMEM);
+ } else if (befs_read_lsymlink(sb, data, link, len) != len) {
+ kfree(link);
+ befs_error(sb, "Failed to read entire long symlink");
+ link = ERR_PTR(-EIO);
+ } else {
+ link[len - 1] = '\0';
+ }
}
} else {
link = befs_ino->i_data.symlink;
#ifdef CONFIG_CIFS_STATS2
seq_printf(m, " In Send: %d In MaxReq Wait: %d",
- atomic_read(&server->inSend),
+ atomic_read(&server->in_send),
atomic_read(&server->num_waiters));
#endif
return pntsd;
}
-static int set_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, __u16 fid,
- struct cifs_ntsd *pnntsd, u32 acllen)
-{
- int xid, rc;
- struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
-
- if (IS_ERR(tlink))
- return PTR_ERR(tlink);
-
- xid = GetXid();
- rc = CIFSSMBSetCIFSACL(xid, tlink_tcon(tlink), fid, pnntsd, acllen);
- FreeXid(xid);
- cifs_put_tlink(tlink);
-
- cFYI(DBG2, "SetCIFSACL rc = %d", rc);
- return rc;
-}
-
static int set_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, const char *path,
struct cifs_ntsd *pnntsd, u32 acllen)
{
struct inode *inode, const char *path)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
- struct cifsFileInfo *open_file;
- int rc;
cFYI(DBG2, "set ACL for %s from mode 0x%x", path, inode->i_mode);
- open_file = find_readable_file(CIFS_I(inode), true);
- if (!open_file)
- return set_cifs_acl_by_path(cifs_sb, path, pnntsd, acllen);
-
- rc = set_cifs_acl_by_fid(cifs_sb, open_file->netfid, pnntsd, acllen);
- cifsFileInfo_put(open_file);
- return rc;
+ return set_cifs_acl_by_path(cifs_sb, path, pnntsd, acllen);
}
/* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */
extern const struct export_operations cifs_export_ops;
#endif /* CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "1.74"
+#define CIFS_VERSION "1.75"
#endif /* _CIFSFS_H */
struct fscache_cookie *fscache; /* client index cache cookie */
#endif
#ifdef CONFIG_CIFS_STATS2
- atomic_t inSend; /* requests trying to send */
+ atomic_t in_send; /* requests trying to send */
atomic_t num_waiters; /* blocked waiting to get in sendrecv */
#endif
};
bool multiEnd:1; /* both received */
};
-struct oplock_q_entry {
- struct list_head qhead;
- struct inode *pinode;
- struct cifs_tcon *tcon;
- __u16 netfid;
-};
+/* Make code in transport.c a little cleaner by moving
+ update of optional stats into function below */
+#ifdef CONFIG_CIFS_STATS2
+
+static inline void cifs_in_send_inc(struct TCP_Server_Info *server)
+{
+ atomic_inc(&server->in_send);
+}
+
+static inline void cifs_in_send_dec(struct TCP_Server_Info *server)
+{
+ atomic_dec(&server->in_send);
+}
+
+static inline void cifs_num_waiters_inc(struct TCP_Server_Info *server)
+{
+ atomic_inc(&server->num_waiters);
+}
+
+static inline void cifs_num_waiters_dec(struct TCP_Server_Info *server)
+{
+ atomic_dec(&server->num_waiters);
+}
+
+static inline void cifs_save_when_sent(struct mid_q_entry *mid)
+{
+ mid->when_sent = jiffies;
+}
+#else
+static inline void cifs_in_send_inc(struct TCP_Server_Info *server)
+{
+}
+static inline void cifs_in_send_dec(struct TCP_Server_Info *server)
+{
+}
+
+static inline void cifs_num_waiters_inc(struct TCP_Server_Info *server)
+{
+}
+
+static inline void cifs_num_waiters_dec(struct TCP_Server_Info *server)
+{
+}
+
+static inline void cifs_save_when_sent(struct mid_q_entry *mid)
+{
+}
+#endif
/* for pending dnotify requests */
struct dir_notify_req {
kfree(volume_info->username);
kzfree(volume_info->password);
kfree(volume_info->UNC);
- kfree(volume_info->UNCip);
+ if (volume_info->UNCip != volume_info->UNC + 2)
+ kfree(volume_info->UNCip);
kfree(volume_info->domainname);
kfree(volume_info->iocharset);
kfree(volume_info->prepath);
}
rcu_read_unlock();
if (namelen != dfsplen || read_seqretry(&rename_lock, seq)) {
- cERROR(1, "did not end path lookup where expected namelen is %d",
- namelen);
+ cFYI(1, "did not end path lookup where expected. namelen=%d "
+ "dfsplen=%d", namelen, dfsplen);
/* presumably this is only possible if racing with a rename
of one of the parent directories (we can not lock the dentries
above us to prevent this, but retrying should be harmless) */
while (1) {
if (atomic_read(&server->inFlight) >= cifs_max_pending) {
spin_unlock(&GlobalMid_Lock);
-#ifdef CONFIG_CIFS_STATS2
- atomic_inc(&server->num_waiters);
-#endif
+ cifs_num_waiters_inc(server);
wait_event(server->request_q,
atomic_read(&server->inFlight)
< cifs_max_pending);
-#ifdef CONFIG_CIFS_STATS2
- atomic_dec(&server->num_waiters);
-#endif
+ cifs_num_waiters_dec(server);
spin_lock(&GlobalMid_Lock);
} else {
if (server->tcpStatus == CifsExiting) {
mid->callback = callback;
mid->callback_data = cbdata;
mid->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
- atomic_inc(&server->inSend);
-#endif
+
+ cifs_in_send_inc(server);
rc = smb_sendv(server, iov, nvec);
-#ifdef CONFIG_CIFS_STATS2
- atomic_dec(&server->inSend);
- mid->when_sent = jiffies;
-#endif
+ cifs_in_send_dec(server);
+ cifs_save_when_sent(mid);
mutex_unlock(&server->srv_mutex);
+
if (rc)
goto out_err;
}
midQ->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
- atomic_inc(&ses->server->inSend);
-#endif
+ cifs_in_send_inc(ses->server);
rc = smb_sendv(ses->server, iov, n_vec);
-#ifdef CONFIG_CIFS_STATS2
- atomic_dec(&ses->server->inSend);
- midQ->when_sent = jiffies;
-#endif
+ cifs_in_send_dec(ses->server);
+ cifs_save_when_sent(midQ);
mutex_unlock(&ses->server->srv_mutex);
}
midQ->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
- atomic_inc(&ses->server->inSend);
-#endif
+
+ cifs_in_send_inc(ses->server);
rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
-#ifdef CONFIG_CIFS_STATS2
- atomic_dec(&ses->server->inSend);
- midQ->when_sent = jiffies;
-#endif
+ cifs_in_send_dec(ses->server);
+ cifs_save_when_sent(midQ);
mutex_unlock(&ses->server->srv_mutex);
if (rc < 0)
}
midQ->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
- atomic_inc(&ses->server->inSend);
-#endif
+ cifs_in_send_inc(ses->server);
rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
-#ifdef CONFIG_CIFS_STATS2
- atomic_dec(&ses->server->inSend);
- midQ->when_sent = jiffies;
-#endif
+ cifs_in_send_dec(ses->server);
+ cifs_save_when_sent(midQ);
mutex_unlock(&ses->server->srv_mutex);
if (rc < 0) {
struct super_block *sb = dir->i_sb;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
struct buffer_head *bh, *prev, *bhs[3]; /* 32*slots (672bytes) */
- struct msdos_dir_entry *de;
+ struct msdos_dir_entry *uninitialized_var(de);
int err, free_slots, i, nr_bhs;
loff_t pos, i_pos;
out:
/* UTF-8 doesn't provide FAT semantics */
if (!strcmp(opts->iocharset, "utf8")) {
- fat_msg(sb, KERN_ERR, "utf8 is not a recommended IO charset"
+ fat_msg(sb, KERN_WARNING, "utf8 is not a recommended IO charset"
" for FAT filesystems, filesystem will be "
- "case sensitive!\n");
+ "case sensitive!");
}
/* If user doesn't specify allow_utime, it's initialized from dmask. */
sbi->free_clusters = -1; /* Don't know yet */
sbi->free_clus_valid = 0;
sbi->prev_free = FAT_START_ENT;
+ sb->s_maxbytes = 0xffffffff;
if (!sbi->fat_length && b->fat32_length) {
struct fat_boot_fsinfo *fsinfo;
sbi->fat_length = le32_to_cpu(b->fat32_length);
sbi->root_cluster = le32_to_cpu(b->root_cluster);
- sb->s_maxbytes = 0xffffffff;
-
/* MC - if info_sector is 0, don't multiply by 0 */
sbi->fsinfo_sector = le16_to_cpu(b->info_sector);
if (sbi->fsinfo_sector == 0)
/*
* Wait for outstanding transactions to be written to log:
*/
- jfs_flush_journal(log, 1);
+ jfs_flush_journal(log, 2);
/*
* close fileset inode allocation map (aka fileset inode)
*
* remove file system from log active file system list.
*/
- jfs_flush_journal(log, 1);
+ jfs_flush_journal(log, 2);
/*
* Make sure all metadata makes it to disk
})
#define __page_to_pfn(pg) \
-({ struct page *__pg = (pg); \
+({ const struct page *__pg = (pg); \
struct pglist_data *__pgdat = NODE_DATA(page_to_nid(__pg)); \
(unsigned long)(__pg - __pgdat->node_mem_map) + \
__pgdat->node_start_pfn; \
* section[i].section_mem_map == mem_map's address - start_pfn;
*/
#define __page_to_pfn(pg) \
-({ struct page *__pg = (pg); \
+({ const struct page *__pg = (pg); \
int __sec = page_to_section(__pg); \
(unsigned long)(__pg - __section_mem_map_addr(__nr_to_section(__sec))); \
})
return hash >> (32 - bits);
}
-static inline unsigned long hash_ptr(void *ptr, unsigned int bits)
+static inline unsigned long hash_ptr(const void *ptr, unsigned int bits)
{
return hash_long((unsigned long)ptr, bits);
}
#include <linux/errno.h>
#include <linux/topology.h>
#include <linux/wait.h>
+#include <linux/module.h>
#include <asm/irq.h>
#include <asm/ptrace.h>
return d->msi_desc;
}
-int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node);
+int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
+ struct module *owner);
+
+static inline int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt,
+ int node)
+{
+ return __irq_alloc_descs(irq, from, cnt, node, THIS_MODULE);
+}
+
void irq_free_descs(unsigned int irq, unsigned int cnt);
int irq_reserve_irqs(unsigned int from, unsigned int cnt);
#ifdef CONFIG_PROC_FS
struct proc_dir_entry *dir;
#endif
+ struct module *owner;
const char *name;
} ____cacheline_internodealigned_in_smp;
page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
}
-static inline unsigned long page_to_section(struct page *page)
+static inline unsigned long page_to_section(const struct page *page)
{
return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
}
static __always_inline void *lowmem_page_address(const struct page *page)
{
- return __va(PFN_PHYS(page_to_pfn((struct page *)page)));
+ return __va(PFN_PHYS(page_to_pfn(page)));
}
#if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL)
#endif
#if defined(HASHED_PAGE_VIRTUAL)
-void *page_address(struct page *page);
+void *page_address(const struct page *page);
void set_page_address(struct page *page, void *virtual);
void page_address_init(void);
#endif
extern void pm_genpd_init(struct generic_pm_domain *genpd,
struct dev_power_governor *gov, bool is_off);
extern int pm_genpd_poweron(struct generic_pm_domain *genpd);
-extern void pm_genpd_poweroff_unused(void);
-extern void genpd_queue_power_off_work(struct generic_pm_domain *genpd);
#else
static inline int pm_genpd_add_device(struct generic_pm_domain *genpd,
struct device *dev)
{
return -ENOSYS;
}
-static inline void pm_genpd_poweroff_unused(void) {}
+#endif
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_RUNTIME
+extern void genpd_queue_power_off_work(struct generic_pm_domain *genpd);
+extern void pm_genpd_poweroff_unused(void);
+#else
static inline void genpd_queue_power_off_work(struct generic_pm_domain *gpd) {}
+static inline void pm_genpd_poweroff_unused(void) {}
#endif
#endif /* _LINUX_PM_DOMAIN_H */
#define RTC_AF 0x20 /* Alarm interrupt */
#define RTC_UF 0x10 /* Update interrupt for 1Hz RTC */
+
+#define RTC_MAX_FREQ 8192
+
#ifdef __KERNEL__
#include <linux/types.h>
gc->mask_cache = irq_reg_readl(gc->reg_base + ct->regs.mask);
for (i = gc->irq_base; msk; msk >>= 1, i++) {
- if (!msk & 0x01)
+ if (!(msk & 0x01))
continue;
if (flags & IRQ_GC_INIT_NESTED_LOCK)
raw_spin_unlock(&gc_lock);
for (; msk; msk >>= 1, i++) {
- if (!msk & 0x01)
+ if (!(msk & 0x01))
continue;
/* Remove handler first. That will mask the irq line */
static inline int desc_node(struct irq_desc *desc) { return 0; }
#endif
-static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node)
+static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
+ struct module *owner)
{
int cpu;
desc->irq_count = 0;
desc->irqs_unhandled = 0;
desc->name = NULL;
+ desc->owner = owner;
for_each_possible_cpu(cpu)
*per_cpu_ptr(desc->kstat_irqs, cpu) = 0;
desc_smp_init(desc, node);
static inline void free_masks(struct irq_desc *desc) { }
#endif
-static struct irq_desc *alloc_desc(int irq, int node)
+static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
{
struct irq_desc *desc;
gfp_t gfp = GFP_KERNEL;
raw_spin_lock_init(&desc->lock);
lockdep_set_class(&desc->lock, &irq_desc_lock_class);
- desc_set_defaults(irq, desc, node);
+ desc_set_defaults(irq, desc, node, owner);
return desc;
kfree(desc);
}
-static int alloc_descs(unsigned int start, unsigned int cnt, int node)
+static int alloc_descs(unsigned int start, unsigned int cnt, int node,
+ struct module *owner)
{
struct irq_desc *desc;
int i;
for (i = 0; i < cnt; i++) {
- desc = alloc_desc(start + i, node);
+ desc = alloc_desc(start + i, node, owner);
if (!desc)
goto err;
mutex_lock(&sparse_irq_lock);
nr_irqs = initcnt;
for (i = 0; i < initcnt; i++) {
- desc = alloc_desc(i, node);
+ desc = alloc_desc(i, node, NULL);
set_bit(i, allocated_irqs);
irq_insert_desc(i, desc);
}
alloc_masks(&desc[i], GFP_KERNEL, node);
raw_spin_lock_init(&desc[i].lock);
lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
- desc_set_defaults(i, &desc[i], node);
+ desc_set_defaults(i, &desc[i], node, NULL);
}
return arch_early_irq_init();
}
dynamic_irq_cleanup(irq);
}
-static inline int alloc_descs(unsigned int start, unsigned int cnt, int node)
+static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
+ struct module *owner)
{
+ u32 i;
+
+ for (i = 0; i < cnt; i++) {
+ struct irq_desc *desc = irq_to_desc(start + i);
+
+ desc->owner = owner;
+ }
return start;
}
* @from: Start the search from this irq number
* @cnt: Number of consecutive irqs to allocate.
* @node: Preferred node on which the irq descriptor should be allocated
+ * @owner: Owning module (can be NULL)
*
* Returns the first irq number or error code
*/
int __ref
-irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
+__irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
+ struct module *owner)
{
int start, ret;
bitmap_set(allocated_irqs, start, cnt);
mutex_unlock(&sparse_irq_lock);
- return alloc_descs(start, cnt, node);
+ return alloc_descs(start, cnt, node, owner);
err:
mutex_unlock(&sparse_irq_lock);
return ret;
}
-EXPORT_SYMBOL_GPL(irq_alloc_descs);
+EXPORT_SYMBOL_GPL(__irq_alloc_descs);
/**
* irq_reserve_irqs - mark irqs allocated
unsigned long flags;
raw_spin_lock_irqsave(&desc->lock, flags);
- desc_set_defaults(irq, desc, desc_node(desc));
+ desc_set_defaults(irq, desc, desc_node(desc), NULL);
raw_spin_unlock_irqrestore(&desc->lock, flags);
}
if (desc->irq_data.chip == &no_irq_chip)
return -ENOSYS;
+ if (!try_module_get(desc->owner))
+ return -ENODEV;
/*
* Some drivers like serial.c use request_irq() heavily,
* so we have to be careful not to interfere with a
*/
nested = irq_settings_is_nested_thread(desc);
if (nested) {
- if (!new->thread_fn)
- return -EINVAL;
+ if (!new->thread_fn) {
+ ret = -EINVAL;
+ goto out_mput;
+ }
/*
* Replace the primary handler which was provided from
* the driver for non nested interrupt handling by the
t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
new->name);
- if (IS_ERR(t))
- return PTR_ERR(t);
+ if (IS_ERR(t)) {
+ ret = PTR_ERR(t);
+ goto out_mput;
+ }
/*
* We keep the reference to the task struct even if
* the thread dies to avoid that the interrupt code
kthread_stop(t);
put_task_struct(t);
}
+out_mput:
+ module_put(desc->owner);
return ret;
}
put_task_struct(action->thread);
}
+ module_put(desc->owner);
return action;
}
if (!thread_fn)
return -EINVAL;
handler = irq_default_primary_handler;
+ irqflags |= IRQF_ONESHOT;
}
action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!class)
class = look_up_lock_class(lock, 0);
- if (DEBUG_LOCKS_WARN_ON(!class))
+ /*
+ * If look_up_lock_class() failed to find a class, we're trying
+ * to test if we hold a lock that has never yet been acquired.
+ * Clearly if the lock hasn't been acquired _ever_, we're not
+ * holding it either, so report failure.
+ */
+ if (!class)
return 0;
if (DEBUG_LOCKS_WARN_ON(!hlock->nest_lock))
config PM_GENERIC_DOMAINS
bool
depends on PM
+
+config PM_GENERIC_DOMAINS_RUNTIME
+ def_bool y
+ depends on PM_RUNTIME && PM_GENERIC_DOMAINS
spinlock_t lock; /* Protect this bucket's list */
} ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER];
-static struct page_address_slot *page_slot(struct page *page)
+static struct page_address_slot *page_slot(const struct page *page)
{
return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)];
}
*
* Returns the page's virtual address.
*/
-void *page_address(struct page *page)
+void *page_address(const struct page *page)
{
unsigned long flags;
void *ret;
{
int ret = 0;
- if (str)
- ret = parse_line_range_desc(str, ¶ms.line_range);
- INIT_LIST_HEAD(¶ms.line_range.line_list);
+ if (!str)
+ return 0;
+
+ if (params.show_lines) {
+ pr_warning("Warning: more than one --line options are"
+ " detected. Only the first one is valid.\n");
+ return 0;
+ }
+
params.show_lines = true;
+ ret = parse_line_range_desc(str, ¶ms.line_range);
+ INIT_LIST_HEAD(¶ms.line_range.line_list);
return ret;
}
return *lineno ?: -ENOENT;
}
+static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data);
+
+/**
+ * cu_walk_functions_at - Walk on function DIEs at given address
+ * @cu_die: A CU DIE
+ * @addr: An address
+ * @callback: A callback which called with found DIEs
+ * @data: A user data
+ *
+ * Walk on function DIEs at given @addr in @cu_die. Passed DIEs
+ * should be subprogram or inlined-subroutines.
+ */
+int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
+ int (*callback)(Dwarf_Die *, void *), void *data)
+{
+ Dwarf_Die die_mem;
+ Dwarf_Die *sc_die;
+ int ret = -ENOENT;
+
+ /* Inlined function could be recursive. Trace it until fail */
+ for (sc_die = die_find_realfunc(cu_die, addr, &die_mem);
+ sc_die != NULL;
+ sc_die = die_find_child(sc_die, __die_find_inline_cb, &addr,
+ &die_mem)) {
+ ret = callback(sc_die, data);
+ if (ret)
+ break;
+ }
+
+ return ret;
+
+}
+
/**
* die_compare_name - Compare diename and tname
* @dw_die: a DIE
return 0;
}
+/* Get attribute and translate it as a sdata */
+static int die_get_attr_sdata(Dwarf_Die *tp_die, unsigned int attr_name,
+ Dwarf_Sword *result)
+{
+ Dwarf_Attribute attr;
+
+ if (dwarf_attr(tp_die, attr_name, &attr) == NULL ||
+ dwarf_formsdata(&attr, result) != 0)
+ return -ENOENT;
+
+ return 0;
+}
+
/**
* die_is_signed_type - Check whether a type DIE is signed or not
* @tp_die: a DIE of a type
return 0;
}
+/* Get the call file index number in CU DIE */
+static int die_get_call_fileno(Dwarf_Die *in_die)
+{
+ Dwarf_Sword idx;
+
+ if (die_get_attr_sdata(in_die, DW_AT_call_file, &idx) == 0)
+ return (int)idx;
+ else
+ return -ENOENT;
+}
+
+/* Get the declared file index number in CU DIE */
+static int die_get_decl_fileno(Dwarf_Die *pdie)
+{
+ Dwarf_Sword idx;
+
+ if (die_get_attr_sdata(pdie, DW_AT_decl_file, &idx) == 0)
+ return (int)idx;
+ else
+ return -ENOENT;
+}
+
+/**
+ * die_get_call_file - Get callsite file name of inlined function instance
+ * @in_die: a DIE of an inlined function instance
+ *
+ * Get call-site file name of @in_die. This means from which file the inline
+ * function is called.
+ */
+const char *die_get_call_file(Dwarf_Die *in_die)
+{
+ Dwarf_Die cu_die;
+ Dwarf_Files *files;
+ int idx;
+
+ idx = die_get_call_fileno(in_die);
+ if (idx < 0 || !dwarf_diecu(in_die, &cu_die, NULL, NULL) ||
+ dwarf_getsrcfiles(&cu_die, &files, NULL) != 0)
+ return NULL;
+
+ return dwarf_filesrc(files, idx, NULL, NULL);
+}
+
+
/**
* die_find_child - Generic DIE search function in DIE tree
* @rt_die: a root DIE
return die_mem;
}
+struct __instance_walk_param {
+ void *addr;
+ int (*callback)(Dwarf_Die *, void *);
+ void *data;
+ int retval;
+};
+
+static int __die_walk_instances_cb(Dwarf_Die *inst, void *data)
+{
+ struct __instance_walk_param *iwp = data;
+ Dwarf_Attribute attr_mem;
+ Dwarf_Die origin_mem;
+ Dwarf_Attribute *attr;
+ Dwarf_Die *origin;
+ int tmp;
+
+ attr = dwarf_attr(inst, DW_AT_abstract_origin, &attr_mem);
+ if (attr == NULL)
+ return DIE_FIND_CB_CONTINUE;
+
+ origin = dwarf_formref_die(attr, &origin_mem);
+ if (origin == NULL || origin->addr != iwp->addr)
+ return DIE_FIND_CB_CONTINUE;
+
+ /* Ignore redundant instances */
+ if (dwarf_tag(inst) == DW_TAG_inlined_subroutine) {
+ dwarf_decl_line(origin, &tmp);
+ if (die_get_call_lineno(inst) == tmp) {
+ tmp = die_get_decl_fileno(origin);
+ if (die_get_call_fileno(inst) == tmp)
+ return DIE_FIND_CB_CONTINUE;
+ }
+ }
+
+ iwp->retval = iwp->callback(inst, iwp->data);
+
+ return (iwp->retval) ? DIE_FIND_CB_END : DIE_FIND_CB_CONTINUE;
+}
+
+/**
+ * die_walk_instances - Walk on instances of given DIE
+ * @or_die: an abstract original DIE
+ * @callback: a callback function which is called with instance DIE
+ * @data: user data
+ *
+ * Walk on the instances of give @in_die. @in_die must be an inlined function
+ * declartion. This returns the return value of @callback if it returns
+ * non-zero value, or -ENOENT if there is no instance.
+ */
+int die_walk_instances(Dwarf_Die *or_die, int (*callback)(Dwarf_Die *, void *),
+ void *data)
+{
+ Dwarf_Die cu_die;
+ Dwarf_Die die_mem;
+ struct __instance_walk_param iwp = {
+ .addr = or_die->addr,
+ .callback = callback,
+ .data = data,
+ .retval = -ENOENT,
+ };
+
+ if (dwarf_diecu(or_die, &cu_die, NULL, NULL) == NULL)
+ return -ENOENT;
+
+ die_find_child(&cu_die, __die_walk_instances_cb, &iwp, &die_mem);
+
+ return iwp.retval;
+}
+
/* Line walker internal parameters */
struct __line_walk_param {
- const char *fname;
+ bool recursive;
line_walk_callback_t callback;
void *data;
int retval;
static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data)
{
struct __line_walk_param *lw = data;
- Dwarf_Addr addr;
+ Dwarf_Addr addr = 0;
+ const char *fname;
int lineno;
if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) {
+ fname = die_get_call_file(in_die);
lineno = die_get_call_lineno(in_die);
- if (lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) {
- lw->retval = lw->callback(lw->fname, lineno, addr,
- lw->data);
+ if (fname && lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) {
+ lw->retval = lw->callback(fname, lineno, addr, lw->data);
if (lw->retval != 0)
return DIE_FIND_CB_END;
}
}
- return DIE_FIND_CB_SIBLING;
+ if (!lw->recursive)
+ /* Don't need to search recursively */
+ return DIE_FIND_CB_SIBLING;
+
+ if (addr) {
+ fname = dwarf_decl_file(in_die);
+ if (fname && dwarf_decl_line(in_die, &lineno) == 0) {
+ lw->retval = lw->callback(fname, lineno, addr, lw->data);
+ if (lw->retval != 0)
+ return DIE_FIND_CB_END;
+ }
+ }
+
+ /* Continue to search nested inlined function call-sites */
+ return DIE_FIND_CB_CONTINUE;
}
/* Walk on lines of blocks included in given DIE */
-static int __die_walk_funclines(Dwarf_Die *sp_die,
+static int __die_walk_funclines(Dwarf_Die *sp_die, bool recursive,
line_walk_callback_t callback, void *data)
{
struct __line_walk_param lw = {
+ .recursive = recursive,
.callback = callback,
.data = data,
.retval = 0,
};
Dwarf_Die die_mem;
Dwarf_Addr addr;
+ const char *fname;
int lineno;
/* Handle function declaration line */
- lw.fname = dwarf_decl_file(sp_die);
- if (lw.fname && dwarf_decl_line(sp_die, &lineno) == 0 &&
+ fname = dwarf_decl_file(sp_die);
+ if (fname && dwarf_decl_line(sp_die, &lineno) == 0 &&
dwarf_entrypc(sp_die, &addr) == 0) {
- lw.retval = callback(lw.fname, lineno, addr, data);
+ lw.retval = callback(fname, lineno, addr, data);
if (lw.retval != 0)
goto done;
}
{
struct __line_walk_param *lw = data;
- lw->retval = __die_walk_funclines(sp_die, lw->callback, lw->data);
+ lw->retval = __die_walk_funclines(sp_die, true, lw->callback, lw->data);
if (lw->retval != 0)
return DWARF_CB_ABORT;
/**
* die_walk_lines - Walk on lines inside given DIE
- * @rt_die: a root DIE (CU or subprogram)
+ * @rt_die: a root DIE (CU, subprogram or inlined_subroutine)
* @callback: callback routine
* @data: user data
*
size_t nlines, i;
/* Get the CU die */
- if (dwarf_tag(rt_die) == DW_TAG_subprogram)
+ if (dwarf_tag(rt_die) != DW_TAG_compile_unit)
cu_die = dwarf_diecu(rt_die, &die_mem, NULL, NULL);
else
cu_die = rt_die;
if (!cu_die) {
- pr_debug2("Failed to get CU from subprogram\n");
+ pr_debug2("Failed to get CU from given DIE.\n");
return -EINVAL;
}
* subroutines. We have to check functions list or given function.
*/
if (rt_die != cu_die)
- ret = __die_walk_funclines(rt_die, callback, data);
+ /*
+ * Don't need walk functions recursively, because nested
+ * inlined functions don't have lines of the specified DIE.
+ */
+ ret = __die_walk_funclines(rt_die, false, callback, data);
else {
struct __line_walk_param param = {
.callback = callback,
extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
const char **fname, int *lineno);
+/* Walk on funcitons at given address */
+extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
+ int (*callback)(Dwarf_Die *, void *), void *data);
+
/* Compare diename and tname */
extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
/* Get callsite line number of inline-function instance */
extern int die_get_call_lineno(Dwarf_Die *in_die);
+/* Get callsite file name of inlined function instance */
+extern const char *die_get_call_file(Dwarf_Die *in_die);
+
/* Get type die */
extern Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
+/* Walk on the instances of given DIE */
+extern int die_walk_instances(Dwarf_Die *in_die,
+ int (*callback)(Dwarf_Die *, void *), void *data);
+
/* Walker on lines (Note: line number will not be sorted) */
typedef int (* line_walk_callback_t) (const char *fname, int lineno,
Dwarf_Addr addr, void *data);
return -1;
bev.header = old_bev.header;
- bev.pid = 0;
+
+ /*
+ * As the pid is the missing value, we need to fill
+ * it properly. The header.misc value give us nice hint.
+ */
+ bev.pid = HOST_KERNEL_ID;
+ if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER ||
+ bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL)
+ bev.pid = DEFAULT_GUEST_KERNEL_ID;
+
memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id));
__event_process_build_id(&bev, filename, session);
return ret;
}
-/* Find a variable in a subprogram die */
-static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
+/* Find a variable in a scope DIE */
+static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
{
- Dwarf_Die vr_die, *scopes;
+ Dwarf_Die vr_die;
char buf[32], *ptr;
- int ret, nscopes;
+ int ret = 0;
if (!is_c_varname(pf->pvar->var)) {
/* Copy raw parameters */
if (pf->tvar->name == NULL)
return -ENOMEM;
- pr_debug("Searching '%s' variable in context.\n",
- pf->pvar->var);
+ pr_debug("Searching '%s' variable in context.\n", pf->pvar->var);
/* Search child die for local variables and parameters. */
- if (die_find_variable_at(sp_die, pf->pvar->var, pf->addr, &vr_die))
- ret = convert_variable(&vr_die, pf);
- else {
- /* Search upper class */
- nscopes = dwarf_getscopes_die(sp_die, &scopes);
- while (nscopes-- > 1) {
- pr_debug("Searching variables in %s\n",
- dwarf_diename(&scopes[nscopes]));
- /* We should check this scope, so give dummy address */
- if (die_find_variable_at(&scopes[nscopes],
- pf->pvar->var, 0,
- &vr_die)) {
- ret = convert_variable(&vr_die, pf);
- goto found;
- }
- }
- if (scopes)
- free(scopes);
- ret = -ENOENT;
+ if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) {
+ /* Search again in global variables */
+ if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
+ ret = -ENOENT;
}
-found:
+ if (ret == 0)
+ ret = convert_variable(&vr_die, pf);
+
if (ret < 0)
pr_warning("Failed to find '%s' in this function.\n",
pf->pvar->var);
return 0;
}
-/* Call probe_finder callback with real subprogram DIE */
-static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf)
+/* Call probe_finder callback with scope DIE */
+static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
{
- Dwarf_Die die_mem;
Dwarf_Attribute fb_attr;
size_t nops;
int ret;
- /* If no real subprogram, find a real one */
- if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) {
- sp_die = die_find_realfunc(&pf->cu_die, pf->addr, &die_mem);
- if (!sp_die) {
+ if (!sc_die) {
+ pr_err("Caller must pass a scope DIE. Program error.\n");
+ return -EINVAL;
+ }
+
+ /* If not a real subprogram, find a real one */
+ if (dwarf_tag(sc_die) != DW_TAG_subprogram) {
+ if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
pr_warning("Failed to find probe point in any "
"functions.\n");
return -ENOENT;
}
- }
+ } else
+ memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));
- /* Get the frame base attribute/ops */
- dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr);
+ /* Get the frame base attribute/ops from subprogram */
+ dwarf_attr(&pf->sp_die, DW_AT_frame_base, &fb_attr);
ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
if (ret <= 0 || nops == 0) {
pf->fb_ops = NULL;
}
/* Call finder's callback handler */
- ret = pf->callback(sp_die, pf);
+ ret = pf->callback(sc_die, pf);
/* *pf->fb_ops will be cached in libdw. Don't free it. */
pf->fb_ops = NULL;
return ret;
}
+struct find_scope_param {
+ const char *function;
+ const char *file;
+ int line;
+ int diff;
+ Dwarf_Die *die_mem;
+ bool found;
+};
+
+static int find_best_scope_cb(Dwarf_Die *fn_die, void *data)
+{
+ struct find_scope_param *fsp = data;
+ const char *file;
+ int lno;
+
+ /* Skip if declared file name does not match */
+ if (fsp->file) {
+ file = dwarf_decl_file(fn_die);
+ if (!file || strcmp(fsp->file, file) != 0)
+ return 0;
+ }
+ /* If the function name is given, that's what user expects */
+ if (fsp->function) {
+ if (die_compare_name(fn_die, fsp->function)) {
+ memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
+ fsp->found = true;
+ return 1;
+ }
+ } else {
+ /* With the line number, find the nearest declared DIE */
+ dwarf_decl_line(fn_die, &lno);
+ if (lno < fsp->line && fsp->diff > fsp->line - lno) {
+ /* Keep a candidate and continue */
+ fsp->diff = fsp->line - lno;
+ memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
+ fsp->found = true;
+ }
+ }
+ return 0;
+}
+
+/* Find an appropriate scope fits to given conditions */
+static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem)
+{
+ struct find_scope_param fsp = {
+ .function = pf->pev->point.function,
+ .file = pf->fname,
+ .line = pf->lno,
+ .diff = INT_MAX,
+ .die_mem = die_mem,
+ .found = false,
+ };
+
+ cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, &fsp);
+
+ return fsp.found ? die_mem : NULL;
+}
+
static int probe_point_line_walker(const char *fname, int lineno,
Dwarf_Addr addr, void *data)
{
struct probe_finder *pf = data;
+ Dwarf_Die *sc_die, die_mem;
int ret;
if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0)
return 0;
pf->addr = addr;
- ret = call_probe_finder(NULL, pf);
+ sc_die = find_best_scope(pf, &die_mem);
+ if (!sc_die) {
+ pr_warning("Failed to find scope of probe point.\n");
+ return -ENOENT;
+ }
+
+ ret = call_probe_finder(sc_die, pf);
/* Continue if no error, because the line will be in inline function */
return ret < 0 ? ret : 0;
Dwarf_Addr addr, void *data)
{
struct probe_finder *pf = data;
+ Dwarf_Die *sc_die, die_mem;
int ret;
if (!line_list__has_line(&pf->lcache, lineno) ||
pr_debug("Probe line found: line:%d addr:0x%llx\n",
lineno, (unsigned long long)addr);
pf->addr = addr;
- ret = call_probe_finder(NULL, pf);
+ pf->lno = lineno;
+ sc_die = find_best_scope(pf, &die_mem);
+ if (!sc_die) {
+ pr_warning("Failed to find scope of probe point.\n");
+ return -ENOENT;
+ }
+
+ ret = call_probe_finder(sc_die, pf);
/*
* Continue if no error, because the lazy pattern will match
return die_walk_lines(sp_die, probe_point_lazy_walker, pf);
}
-/* Callback parameter with return value */
-struct dwarf_callback_param {
- void *data;
- int retval;
-};
-
static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
{
- struct dwarf_callback_param *param = data;
- struct probe_finder *pf = param->data;
+ struct probe_finder *pf = data;
struct perf_probe_point *pp = &pf->pev->point;
Dwarf_Addr addr;
+ int ret;
if (pp->lazy_line)
- param->retval = find_probe_point_lazy(in_die, pf);
+ ret = find_probe_point_lazy(in_die, pf);
else {
/* Get probe address */
if (dwarf_entrypc(in_die, &addr) != 0) {
pr_warning("Failed to get entry address of %s.\n",
dwarf_diename(in_die));
- param->retval = -ENOENT;
- return DWARF_CB_ABORT;
+ return -ENOENT;
}
pf->addr = addr;
pf->addr += pp->offset;
pr_debug("found inline addr: 0x%jx\n",
(uintmax_t)pf->addr);
- param->retval = call_probe_finder(in_die, pf);
- if (param->retval < 0)
- return DWARF_CB_ABORT;
+ ret = call_probe_finder(in_die, pf);
}
- return DWARF_CB_OK;
+ return ret;
}
+/* Callback parameter with return value for libdw */
+struct dwarf_callback_param {
+ void *data;
+ int retval;
+};
+
/* Search function from function name */
static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
{
/* TODO: Check the address in this function */
param->retval = call_probe_finder(sp_die, pf);
}
- } else {
- struct dwarf_callback_param _param = {.data = (void *)pf,
- .retval = 0};
+ } else
/* Inlined function: search instances */
- dwarf_func_inline_instances(sp_die, probe_point_inline_cb,
- &_param);
- param->retval = _param.retval;
- }
+ param->retval = die_walk_instances(sp_die,
+ probe_point_inline_cb, (void *)pf);
return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */
}
}
/* Add a found probe point into trace event list */
-static int add_probe_trace_event(Dwarf_Die *sp_die, struct probe_finder *pf)
+static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
{
struct trace_event_finder *tf =
container_of(pf, struct trace_event_finder, pf);
}
tev = &tf->tevs[tf->ntevs++];
- ret = convert_to_trace_point(sp_die, pf->addr, pf->pev->point.retprobe,
- &tev->point);
+ /* Trace point should be converted from subprogram DIE */
+ ret = convert_to_trace_point(&pf->sp_die, pf->addr,
+ pf->pev->point.retprobe, &tev->point);
if (ret < 0)
return ret;
for (i = 0; i < pf->pev->nargs; i++) {
pf->pvar = &pf->pev->args[i];
pf->tvar = &tev->args[i];
- ret = find_variable(sp_die, pf);
+ /* Variable should be found from scope DIE */
+ ret = find_variable(sc_die, pf);
if (ret != 0)
return ret;
}
}
/* Add a found vars into available variables list */
-static int add_available_vars(Dwarf_Die *sp_die, struct probe_finder *pf)
+static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
{
struct available_var_finder *af =
container_of(pf, struct available_var_finder, pf);
struct variable_list *vl;
- Dwarf_Die die_mem, *scopes = NULL;
- int ret, nscopes;
+ Dwarf_Die die_mem;
+ int ret;
/* Check number of tevs */
if (af->nvls == af->max_vls) {
}
vl = &af->vls[af->nvls++];
- ret = convert_to_trace_point(sp_die, pf->addr, pf->pev->point.retprobe,
- &vl->point);
+ /* Trace point should be converted from subprogram DIE */
+ ret = convert_to_trace_point(&pf->sp_die, pf->addr,
+ pf->pev->point.retprobe, &vl->point);
if (ret < 0)
return ret;
if (vl->vars == NULL)
return -ENOMEM;
af->child = true;
- die_find_child(sp_die, collect_variables_cb, (void *)af, &die_mem);
+ die_find_child(sc_die, collect_variables_cb, (void *)af, &die_mem);
/* Find external variables */
if (!af->externs)
goto out;
/* Don't need to search child DIE for externs. */
af->child = false;
- nscopes = dwarf_getscopes_die(sp_die, &scopes);
- while (nscopes-- > 1)
- die_find_child(&scopes[nscopes], collect_variables_cb,
- (void *)af, &die_mem);
- if (scopes)
- free(scopes);
+ die_find_child(&pf->cu_die, collect_variables_cb, (void *)af, &die_mem);
out:
if (strlist__empty(vl->vars)) {
static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
{
- struct dwarf_callback_param *param = data;
+ find_line_range_by_line(in_die, data);
- param->retval = find_line_range_by_line(in_die, param->data);
- return DWARF_CB_ABORT; /* No need to find other instances */
+ /*
+ * We have to check all instances of inlined function, because
+ * some execution paths can be optimized out depends on the
+ * function argument of instances
+ */
+ return 0;
}
/* Search function from function name */
pr_debug("New line range: %d to %d\n", lf->lno_s, lf->lno_e);
lr->start = lf->lno_s;
lr->end = lf->lno_e;
- if (dwarf_func_inline(sp_die)) {
- struct dwarf_callback_param _param;
- _param.data = (void *)lf;
- _param.retval = 0;
- dwarf_func_inline_instances(sp_die,
- line_range_inline_cb,
- &_param);
- param->retval = _param.retval;
- } else
+ if (dwarf_func_inline(sp_die))
+ param->retval = die_walk_instances(sp_die,
+ line_range_inline_cb, lf);
+ else
param->retval = find_line_range_by_line(sp_die, lf);
return DWARF_CB_ABORT;
}
struct perf_probe_event *pev; /* Target probe event */
/* Callback when a probe point is found */
- int (*callback)(Dwarf_Die *sp_die, struct probe_finder *pf);
+ int (*callback)(Dwarf_Die *sc_die, struct probe_finder *pf);
/* For function searching */
int lno; /* Line number */
if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
struct stat st;
- if (stat(dso->name, &st) < 0)
+ if (lstat(dso->name, &st) < 0)
return -1;
if (st.st_uid && (st.st_uid != geteuid())) {
return ret;
}
-struct dso *dso__new_kernel(const char *name)
+static struct dso*
+dso__kernel_findnew(struct machine *machine, const char *name,
+ const char *short_name, int dso_type)
{
- struct dso *dso = dso__new(name ?: "[kernel.kallsyms]");
-
- if (dso != NULL) {
- dso__set_short_name(dso, "[kernel]");
- dso->kernel = DSO_TYPE_KERNEL;
- }
-
- return dso;
-}
+ /*
+ * The kernel dso could be created by build_id processing.
+ */
+ struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name);
-static struct dso *dso__new_guest_kernel(struct machine *machine,
- const char *name)
-{
- char bf[PATH_MAX];
- struct dso *dso = dso__new(name ?: machine__mmap_name(machine, bf,
- sizeof(bf)));
+ /*
+ * We need to run this in all cases, since during the build_id
+ * processing we had no idea this was the kernel dso.
+ */
if (dso != NULL) {
- dso__set_short_name(dso, "[guest.kernel]");
- dso->kernel = DSO_TYPE_GUEST_KERNEL;
+ dso__set_short_name(dso, short_name);
+ dso->kernel = dso_type;
}
return dso;
dso->has_build_id = true;
}
-static struct dso *machine__create_kernel(struct machine *machine)
+static struct dso *machine__get_kernel(struct machine *machine)
{
const char *vmlinux_name = NULL;
struct dso *kernel;
if (machine__is_host(machine)) {
vmlinux_name = symbol_conf.vmlinux_name;
- kernel = dso__new_kernel(vmlinux_name);
+ if (!vmlinux_name)
+ vmlinux_name = "[kernel.kallsyms]";
+
+ kernel = dso__kernel_findnew(machine, vmlinux_name,
+ "[kernel]",
+ DSO_TYPE_KERNEL);
} else {
+ char bf[PATH_MAX];
+
if (machine__is_default_guest(machine))
vmlinux_name = symbol_conf.default_guest_vmlinux_name;
- kernel = dso__new_guest_kernel(machine, vmlinux_name);
+ if (!vmlinux_name)
+ vmlinux_name = machine__mmap_name(machine, bf,
+ sizeof(bf));
+
+ kernel = dso__kernel_findnew(machine, vmlinux_name,
+ "[guest.kernel]",
+ DSO_TYPE_GUEST_KERNEL);
}
- if (kernel != NULL) {
+ if (kernel != NULL && (!kernel->has_build_id))
dso__read_running_kernel_build_id(kernel, machine);
- dsos__add(&machine->kernel_dsos, kernel);
- }
+
return kernel;
}
int machine__create_kernel_maps(struct machine *machine)
{
- struct dso *kernel = machine__create_kernel(machine);
+ struct dso *kernel = machine__get_kernel(machine);
if (kernel == NULL ||
__machine__create_kernel_maps(machine, kernel) < 0)
};
struct dso *dso__new(const char *name);
-struct dso *dso__new_kernel(const char *name);
void dso__delete(struct dso *dso);
int dso__name_len(const struct dso *dso);
},
};
- ui_helpline__push("Press <- or ESC to exit");
return perf_top_browser__run(&browser);
}
git.openpandora.org / pandora-kernel.git / commitdiff