// SPDX-License-Identifier: Apache-2.0
//
// /dev/pci -- device access from userspace.
//
// docs/plan/hybrid.md, mechanisms 2 and 4: MMIO and DMA to a process. This is
// the interface a driver that does not live in the kernel talks to, and it is
// deliberately about *PCI devices*, not about any particular driver model.
//
// That generality is the point, and it is worth being explicit about why.
// The first users of this will be SchOS's own drivers, evicted one at a time
// -- virtio-gpu, then xHCI -- and the interface has to be judged by them.
// Something that hosts foreign drivers later is then a consumer of a general
// mechanism rather than a hole shaped like one, which is both the honest
// design and the only one that stays honest under examination.
//
// What a driver needs from a kernel, and all it needs:
//
//   - to find its device, and read what the bus says about it   INFO
//   - to be given it, exclusively                                CLAIM
//   - to reach its registers                                     mmap(BAR)
//   - memory it can hand to the device                           DMA
//   - to be told when the device wants attention                 IRQ + read()
//
// There is no IOMMU. A process holding a DMA buffer can point the device at
// any physical address, so this isolates a driver against its own *bugs* and
// not against its own *intent*. docs/plan/hybrid.md says so at length and it
// remains true here: a crashed driver that restarts instead of taking the
// machine down is the whole benefit, and it is not a security boundary.

#ifndef PCIUSER_H
#define PCIUSER_H

#define PCIUSER_MAJOR 9

#define PCIUSER_MAXBAR 6

struct pciuser_bar {
    unsigned long long base;    // physical address, 0 when the BAR is unused
    unsigned long long size;
    unsigned int       flags;   // PCIUSER_BAR_*
    unsigned int       pad;
};

#define PCIUSER_BAR_MMIO   0x01   // memory space; mappable
#define PCIUSER_BAR_IO     0x02   // I/O port space; not mappable
#define PCIUSER_BAR_PREFETCH 0x04

// One device, as the bus describes it. `index` is the only field the caller
// fills in; everything else comes back.
struct pciuser_info {
    unsigned int  index;            // in: 0 .. PCIIOC_COUNT-1
    unsigned char bus, slot, func;
    unsigned char header_type;

    unsigned short vendor, device;
    unsigned char  class, subclass, prog_if, revision;

    unsigned char irq;              // interrupt line, 0xFF when unrouted
    unsigned char claimed;          // 1 when a userspace process holds it
    unsigned short pad;

    // The name of whatever owns it: an in-kernel driver, "userspace" when a
    // process has claimed it, or empty when nothing has.
    char driver[16];

    struct pciuser_bar bar[PCIUSER_MAXBAR];
};

// A DMA buffer. The kernel allocates it from the DMA arena, maps it into the
// caller, and reports the physical address the *device* must be given -- which
// is the entire reason a driver cannot do this for itself with mmap.
// A dword of PCI configuration space. A virtio device says where its registers
// live in vendor capabilities, which are here and nowhere else -- so without
// this a driver cannot find its own device.
struct pciuser_cfg {
    unsigned int index;             // in
    unsigned int offset;            // in: dword-aligned, 0..0xFC
    unsigned int value;             // out
    unsigned int pad;
};

struct pciuser_dma {
    unsigned long long size;        // in:  bytes, rounded up to a page
    unsigned long long uaddr;       // out: where it landed in this process
    unsigned long long paddr;       // out: what to program into the device
};

#define PCIIOC_COUNT    0x9000   // out: int, how many devices the bus has
#define PCIIOC_INFO     0x9001   // struct pciuser_info
#define PCIIOC_CLAIM    0x9002   // in: int index -- take it from the kernel
#define PCIIOC_RELEASE  0x9003   // in: int index
#define PCIIOC_DMA      0x9004   // struct pciuser_dma
#define PCIIOC_CFG      0x9006   // struct pciuser_cfg -- read config space
#define PCIIOC_IRQ      0x9005   // in: int index -- deliver this device's
                                 //     interrupts to this process

// Interrupts arrive by *reading* this device, which is how Linux's uio does it
// and for the same reason: a descriptor composes with poll, and a driver that
// stops reading falls behind rather than losing events.
//
//     ioctl(fd, PCIIOC_IRQ, &index);
//     for (;;) {
//         unsigned long long n;
//         read(fd, &n, sizeof n);      // blocks until the device interrupts
//         ... service the device, and ACK IT AT THE DEVICE ...
//         write(fd, &n, sizeof n);     // re-arm
//     }
//
// **The write is not optional.** A PCI interrupt line is level-triggered: it
// stays asserted until the driver clears the cause *at the device*, and the
// kernel cannot do that because clearing it is device-specific -- it is a
// different register on every chip. So the kernel masks the line when the
// interrupt arrives and leaves it masked until the write says the device has
// been dealt with.
//
// Without that, EOI is signalled on a line that is still asserted and the
// interrupt re-fires immediately, for ever. That is not hypothetical: it
// happened in this kernel, at 72,000 interrupts a second, and what it looked
// like from userspace was a clock running seven times slow.
// See docs/history/kernel.md section 13.
//
// One device per process. A driver drives one thing; if you need two, run two.



// Registers are reached with mmap() on this device, where the *offset is the
// physical address of the BAR*:
//
//     ioctl(fd, PCIIOC_INFO, &info);
//     ioctl(fd, PCIIOC_CLAIM, &info.index);
//     regs = mmap(0, info.bar[0].size, PROT_READ|PROT_WRITE, MAP_SHARED,
//                 fd, info.bar[0].base);
//
// The kernel refuses an offset that is not inside a BAR of a device this
// process has claimed, which is what stops this being /dev/mem with extra
// steps.

#endif // PCIUSER_H