freebsd-dev/sys/i386/include/intr_machdep.h
John Baldwin e706f7f0c7 Revamp the MSI/MSI-X code a bit to achieve two main goals:
- Simplify the amount of work that has be done for each architecture by
  pushing more of the truly MI code down into the PCI bus driver.
- Don't bind MSI-X indicies to IRQs so that we can allow a driver to map
  multiple MSI-X messages into a single IRQ when handling a message
  shortage.

The changes include:
- Add a new pcib_if method: PCIB_MAP_MSI() which is called by the PCI bus
  to calculate the address and data values for a given MSI/MSI-X IRQ.
  The x86 nexus drivers map this into a call to a new 'msi_map()' function
  in msi.c that does the mapping.
- Retire the pcib_if method PCIB_REMAP_MSIX() and remove the 'index'
  parameter from PCIB_ALLOC_MSIX().  MD code no longer has any knowledge
  of the MSI-X index for a given MSI-X IRQ.
- The PCI bus driver now stores more MSI-X state in a child's ivars.
  Specifically, it now stores an array of IRQs (called "message vectors" in
  the code) that have associated address and data values, and a small
  virtual version of the MSI-X table that specifies the message vector
  that a given MSI-X table entry uses.  Sparse mappings are permitted in
  the virtual table.
- The PCI bus driver now configures the MSI and MSI-X address/data
  registers directly via custom bus_setup_intr() and bus_teardown_intr()
  methods.  pci_setup_intr() invokes PCIB_MAP_MSI() to determine the
  address and data values for a given message as needed.  The MD code
  no longer has to call back down into the PCI bus code to set these
  values from the nexus' bus_setup_intr() handler.
- The PCI bus code provides a callout (pci_remap_msi_irq()) that the MD
  code can call to force the PCI bus to re-invoke PCIB_MAP_MSI() to get
  new values of the address and data fields for a given IRQ.  The x86
  MSI code uses this when an MSI IRQ is moved to a different CPU, requiring
  a new value of the 'address' field.
- The x86 MSI psuedo-driver loses a lot of code, and in fact the separate
  MSI/MSI-X pseudo-PICs are collapsed down into a single MSI PIC driver
  since the only remaining diff between the two is a substring in a
  bootverbose printf.
- The PCI bus driver will now restore MSI-X state (including programming
  entries in the MSI-X table) on device resume.
- The interface for pci_remap_msix() has changed.  Instead of accepting
  indices for the allocated vectors, it accepts a mini-virtual table
  (with a new length parameter).  This table is an array of u_ints, where
  each value specifies which allocated message vector to use for the
  corresponding MSI-X message.  A vector of 0 forces a message to not
  have an associated IRQ.  The device may choose to only use some of the
  IRQs assigned, in which case the unused IRQs must be at the "end" and
  will be released back to the system.  This allows a driver to use the
  same remap table for different shortage values.  For example, if a driver
  wants 4 messages, it can use the same remap table (which only uses the
  first two messages) for the cases when it only gets 2 or 3 messages and
  in the latter case the PCI bus will release the 3rd IRQ back to the
  system.

MFC after:	1 month
2007-05-02 17:50:36 +00:00

156 lines
5.4 KiB
C

/*-
* Copyright (c) 2003 John Baldwin <jhb@FreeBSD.org>
* 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.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 THE AUTHOR 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.
*
* $FreeBSD$
*/
#ifndef __MACHINE_INTR_MACHDEP_H__
#define __MACHINE_INTR_MACHDEP_H__
#ifdef _KERNEL
/*
* The maximum number of I/O interrupts we allow. This number is rather
* arbitrary as it is just the maximum IRQ resource value. The interrupt
* source for a given IRQ maps that I/O interrupt to device interrupt
* source whether it be a pin on an interrupt controller or an MSI interrupt.
* The 16 ISA IRQs are assigned fixed IDT vectors, but all other device
* interrupts allocate IDT vectors on demand. Currently we have 191 IDT
* vectors available for device interrupts. On many systems with I/O APICs,
* a lot of the IRQs are not used, so this number can be much larger than
* 191 and still be safe since only interrupt sources in actual use will
* allocate IDT vectors.
*
* The first 255 IRQs (0 - 254) are reserved for ISA IRQs and PCI intline IRQs.
* IRQ values beyond 256 are used by MSI. We leave 255 unused to avoid
* confusion since 255 is used in PCI to indicate an invalid IRQ.
*/
#define NUM_MSI_INTS 128
#define FIRST_MSI_INT 256
#define NUM_IO_INTS (FIRST_MSI_INT + NUM_MSI_INTS)
/*
* Default base address for MSI messages on x86 platforms.
*/
#define MSI_INTEL_ADDR_BASE 0xfee00000
/*
* - 1 ??? dummy counter.
* - 2 counters for each I/O interrupt.
* - 1 counter for each CPU for lapic timer.
* - 7 counters for each CPU for IPI counters for SMP.
*/
#ifdef SMP
#define INTRCNT_COUNT (1 + NUM_IO_INTS * 2 + (1 + 7) * MAXCPU)
#else
#define INTRCNT_COUNT (1 + NUM_IO_INTS * 2 + 1)
#endif
#ifndef LOCORE
typedef void inthand_t(u_int cs, u_int ef, u_int esp, u_int ss);
#define IDTVEC(name) __CONCAT(X,name)
struct intsrc;
/*
* Methods that a PIC provides to mask/unmask a given interrupt source,
* "turn on" the interrupt on the CPU side by setting up an IDT entry, and
* return the vector associated with this source.
*/
struct pic {
void (*pic_enable_source)(struct intsrc *);
void (*pic_disable_source)(struct intsrc *, int);
void (*pic_eoi_source)(struct intsrc *);
void (*pic_enable_intr)(struct intsrc *);
int (*pic_vector)(struct intsrc *);
int (*pic_source_pending)(struct intsrc *);
void (*pic_suspend)(struct pic *);
void (*pic_resume)(struct pic *);
int (*pic_config_intr)(struct intsrc *, enum intr_trigger,
enum intr_polarity);
void (*pic_assign_cpu)(struct intsrc *, u_int apic_id);
STAILQ_ENTRY(pic) pics;
};
/* Flags for pic_disable_source() */
enum {
PIC_EOI,
PIC_NO_EOI,
};
/*
* An interrupt source. The upper-layer code uses the PIC methods to
* control a given source. The lower-layer PIC drivers can store additional
* private data in a given interrupt source such as an interrupt pin number
* or an I/O APIC pointer.
*/
struct intsrc {
struct pic *is_pic;
struct intr_event *is_event;
u_long *is_count;
u_long *is_straycount;
u_int is_index;
u_int is_enabled:1;
};
struct trapframe;
extern struct mtx icu_lock;
extern int elcr_found;
/* XXX: The elcr_* prototypes probably belong somewhere else. */
int elcr_probe(void);
enum intr_trigger elcr_read_trigger(u_int irq);
void elcr_resume(void);
void elcr_write_trigger(u_int irq, enum intr_trigger trigger);
#ifdef SMP
void intr_add_cpu(u_int cpu);
#endif
int intr_add_handler(const char *name, int vector, driver_filter_t filter,
driver_intr_t handler, void *arg, enum intr_type flags, void **cookiep);
int intr_config_intr(int vector, enum intr_trigger trig,
enum intr_polarity pol);
void intr_execute_handlers(struct intsrc *isrc, struct trapframe *frame);
struct intsrc *intr_lookup_source(int vector);
int intr_register_pic(struct pic *pic);
int intr_register_source(struct intsrc *isrc);
int intr_remove_handler(void *cookie);
void intr_resume(void);
void intr_suspend(void);
void intrcnt_add(const char *name, u_long **countp);
int msi_alloc(device_t dev, int count, int maxcount, int *irqs, int *newirq,
int *newcount);
void msi_init(void);
int msi_map(int irq, uint64_t *addr, uint32_t *data);
int msi_release(int* irqs, int count);
int msix_alloc(device_t dev, int *irq, int *new);
int msix_release(int irq);
#endif /* !LOCORE */
#endif /* _KERNEL */
#endif /* !__MACHINE_INTR_MACHDEP_H__ */