freebsd-dev/sys/dev/pci
John Baldwin 5fe82bca57 Expand the MSI/MSI-X API to address some deficiencies in the MSI-X support.
- First off, device drivers really do need to know if they are allocating
  MSI or MSI-X messages.  MSI requires allocating powerof2() messages for
  example where MSI-X does not.  To address this, split out the MSI-X
  support from pci_msi_count() and pci_alloc_msi() into new driver-visible
  functions pci_msix_count() and pci_alloc_msix().  As a result,
  pci_msi_count() now just returns a count of the max supported MSI
  messages for the device, and pci_alloc_msi() only tries to allocate MSI
  messages.  To get a count of the max supported MSI-X messages, use
  pci_msix_count().  To allocate MSI-X messages, use pci_alloc_msix().
  pci_release_msi() still handles both MSI and MSI-X messages, however.
  As a result of this change, drivers using the existing API will only
  use MSI messages and will no longer try to use MSI-X messages.
- Because MSI-X allows for each message to have its own data and address
  values (and thus does not require all of the messages to have their
  MD vectors allocated as a group), some devices allow for "sparse" use
  of MSI-X message slots.  For example, if a device supports 8 messages
  but the OS is only able to allocate 2 messages, the device may make the
  best use of 2 IRQs if it enables the messages at slots 1 and 4 rather
  than default of using the first N slots (or indicies) at 1 and 2.  To
  support this, add a new pci_remap_msix() function that a driver may call
  after a successful pci_alloc_msix() (but before allocating any of the
  SYS_RES_IRQ resources) to allow the allocated IRQ resources to be
  assigned to different message indices.  For example, from the earlier
  example, after pci_alloc_msix() returned a value of 2, the driver would
  call pci_remap_msix() passing in array of integers { 1, 4 } as the
  new message indices to use.  The rid's for the SYS_RES_IRQ resources
  will always match the message indices.  Thus, after the call to
  pci_remap_msix() the driver would be able to access the first message
  in slot 1 at SYS_RES_IRQ rid 1, and the second message at slot 4 at
  SYS_RES_IRQ rid 4.  Note that the message slots/indices are 1-based
  rather than 0-based so that they will always correspond to the rid
  values (SYS_RES_IRQ rid 0 is reserved for the legacy INTx interrupt).
  To support this API, a new PCIB_REMAP_MSIX() method was added to the
  pcib interface to change the message index for a single IRQ.

Tested by:	scottl
2007-01-22 21:48:44 +00:00
..
eisa_pci.c Add missing <sys/module.h> includes 2004-05-30 20:08:47 +00:00
fixup_pci.c Workaround a hang on some nForce2 systems that can happen if the CPU goes 2006-05-24 14:08:31 +00:00
hostb_pci.c Move the hostb driver out of the i386 and amd64 PCI code (where it was 2005-12-20 21:09:45 +00:00
ignore_pci.c Add some missing <sys/module.h> includes which are masked by the 2004-05-30 17:57:46 +00:00
isa_pci.c Don't save and restore the ELCR register across suspend and resume for 2005-09-29 15:00:09 +00:00
pci_if.m Expand the MSI/MSI-X API to address some deficiencies in the MSI-X support. 2007-01-22 21:48:44 +00:00
pci_pci.c Expand the MSI/MSI-X API to address some deficiencies in the MSI-X support. 2007-01-22 21:48:44 +00:00
pci_private.h Expand the MSI/MSI-X API to address some deficiencies in the MSI-X support. 2007-01-22 21:48:44 +00:00
pci_user.c Actually make bounds checking for PCIOCREAD and PCIOCWRITE work. 2006-10-06 14:31:32 +00:00
pci.c Expand the MSI/MSI-X API to address some deficiencies in the MSI-X support. 2007-01-22 21:48:44 +00:00
pcib_if.m Expand the MSI/MSI-X API to address some deficiencies in the MSI-X support. 2007-01-22 21:48:44 +00:00
pcib_private.h Expand the MSI/MSI-X API to address some deficiencies in the MSI-X support. 2007-01-22 21:48:44 +00:00
pcireg.h - Change the PCI-X registers constants to be relative to the PCI-X PCI 2007-01-19 22:37:52 +00:00
pcivar.h Expand the MSI/MSI-X API to address some deficiencies in the MSI-X support. 2007-01-22 21:48:44 +00:00
vga_pci.c Don't add an agp child in vgapci's attach routine if the PCIY_AGP 2006-02-01 15:45:29 +00:00