/*
  StarForth — Steady-State Virtual Machine Runtime
  Copyright (c) 2023–2025 Robert A. James. All rights reserved.
  Licensed under the StarForth License, Version 1.0.
 */

/**
 * apic.c (aarch64) - Minimal GICv2 driver + ARM Generic Timer (items 0.6/0.7).
 *
 * "Minimal" is deliberate and stays deliberate: exactly one interrupt (the
 * non-secure EL1 physical timer PPI, or its EL2 hypervisor-timer counterpart
 * if ever run at EL2) is enabled. This is not a general GIC driver and must
 * not grow into one -- no SPI support, no SGI support, no GICv3/ITS.
 *
 * Base addresses and the PPI INTID are QEMU-virt-machine constants, not
 * device-tree-discovered, and that is a deliberate, recorded exception
 * rather than an oversight (FABRIC.md item 0.6, GAP-B1 follow-up):
 * `fdt_valid(boot_info->dtb)` fails on this system's aarch64 firmware
 * (qemu-efi-aarch64 2025.11-3ubuntu7 does not forward a devicetree to the
 * guest), confirmed live rather than assumed. The values below were not
 * recalled from memory either -- they were read out of QEMU 10.2.1's own
 * internal devicetree (`qemu-system-aarch64 -machine virt,dumpdtb=...`,
 * decoded with this tree's own fdt.c reader) and are therefore correct for
 * this exact QEMU version, though not guaranteed stable across others.
 * Register *offsets* within each block (GICD_CTLR, GICC_IAR, etc.) are
 * fixed by the GICv2 architecture, not the board, and were cross-checked
 * against Linux's own driver header (linux/irqchip/arm-gic.h, from the
 * linux-headers package installed on the build host) rather than recalled
 * either.
 */

#include "apic.h"
#include "uefi.h"
#include "console.h"
#include <stdint.h>

/* Defined in arch.c (item 0.4). Same extern-in-place convention as
 * interrupts.c: "exception level" has no cross-ISA meaning. */
extern int aarch64_current_el(void);

/* ---- QEMU virt machine constants (see file header) --------------------- */
#define GICD_BASE_PA   0x08000000UL
#define GICC_BASE_PA   0x08010000UL

/* Non-secure EL1 physical timer PPI = 30 (INTID 16+14); EL2 hypervisor
 * timer PPI = 26 (INTID 16+10). Both read directly out of QEMU's own DT
 * dump for the `timer` node's four-entry `interrupts` property (secure,
 * non-secure, virtual, hypervisor, in that architected order) -- not the
 * architecture-generic PPI numbers assumed from memory. */
#define TIMER_PPI_EL1  30u
#define TIMER_PPI_EL2  26u

/* GICv2 Distributor register byte offsets (ARM IHI 0048B; confirmed against
 * Linux's arm-gic.h, see file header). */
#define GICD_CTLR         0x000
#define GICD_ISENABLER0   0x100
#define GICD_IPRIORITYR   0x400
#define GICD_ICFGR        0xC00

/* GICv2 CPU Interface register byte offsets. */
#define GICC_CTLR   0x00
#define GICC_PMR    0x04
#define GICC_IAR    0x0C
#define GICC_EOIR   0x10

#define GICD_CTLR_ENABLE_GRP0  (1u << 0)
#define GICC_CTLR_ENABLE_GRP0  (1u << 0)

/* Priority: GICv2 compares as "interrupt allowed if priority < PMR", lower
 * value = more urgent. One interrupt is configured, so the specific value
 * only has to be numerically below the PMR mask set in apic_init(). */
#define TIMER_PRIORITY   0x80u
#define PMR_ALLOW_ALL    0xFFu

/* MMIO accessed as identity/physical addresses: arch_mmu_init() for aarch64
 * is still the M3 stub (page-table bring-up deferred), so whatever mapping
 * EDK2 left active at ExitBootServices governs -- the same assumption
 * amd64/timer.c already documents and relies on for its own MMIO (HPET). */
static inline void mmio_write32(uintptr_t base, uint32_t offset, uint32_t val)
{
    *(volatile uint32_t *)(base + offset) = val;
}

static inline uint32_t mmio_read32(uintptr_t base, uint32_t offset)
{
    return *(volatile uint32_t *)(base + offset);
}

/* Set once by apic_init(), read by aarch64_irq_handler() to know which PPI
 * to expect -- computed once (EL cannot change post-boot, same rationale
 * as item 0.5's el2_mode_flag) rather than re-derived per interrupt. */
static uint32_t s_timer_ppi = TIMER_PPI_EL1;

static uint64_t s_timer_period_tsc = 0;

/**
 * @brief Initialise the GICv2 distributor and CPU interface (M4 milestone).
 *
 * Enables exactly one interrupt source: the physical timer PPI for the
 * exception level detected in item 0.4 (30 at EL1, 26 at EL2 — see
 * @c TIMER_PPI_EL1 / @c TIMER_PPI_EL2 above). Sequence:
 *
 * 1. Set this interrupt's priority (@c GICD_IPRIORITYR) below the CPU
 *    interface's priority mask, so it is never itself masked out.
 * 2. Enable it in @c GICD_ISENABLER0 (PPIs 16–31 live in the first word).
 * 3. Enable the distributor, Group 0 only (@c GICD_CTLR) — this deployment
 *    has no GICv2 security-extension split in use.
 * 4. Set the CPU interface priority mask to allow everything through
 *    (@c GICC_PMR = 0xFF) and enable the CPU interface (@c GICC_CTLR).
 *
 * Deliberately not configured: @c GICD_ICFGR (trigger sensitivity). The
 * ARM generic timer's PPI is architecturally level-sensitive; this is not
 * a general GIC driver and item 0.6's own scope does not call for
 * reconfiguring it.
 *
 * @param boot_info Unused — see the file header for why this does not read
 *                  @c boot_info->dtb despite item 0.6 asking for it.
 * @return 0 always.
 */
int apic_init(BootInfo *boot_info)
{
    (void)boot_info;

    s_timer_ppi = (aarch64_current_el() == 2) ? TIMER_PPI_EL2 : TIMER_PPI_EL1;

    /* IPRIORITYR is byte-indexed, one byte per INTID. */
    {
        uint32_t reg_off = GICD_IPRIORITYR + (s_timer_ppi & ~3u);
        uint32_t shift    = (s_timer_ppi & 3u) * 8u;
        uint32_t val      = mmio_read32(GICD_BASE_PA, reg_off);
        val = (val & ~(0xFFu << shift)) | (TIMER_PRIORITY << shift);
        mmio_write32(GICD_BASE_PA, reg_off, val);
    }

    mmio_write32(GICD_BASE_PA, GICD_ISENABLER0, 1u << s_timer_ppi);
    mmio_write32(GICD_BASE_PA, GICD_CTLR, GICD_CTLR_ENABLE_GRP0);

    mmio_write32(GICC_BASE_PA, GICC_PMR, PMR_ALLOW_ALL);
    mmio_write32(GICC_BASE_PA, GICC_CTLR, GICC_CTLR_ENABLE_GRP0);

    console_puts("GICv2: distributor+CPU interface enabled, PPI ");
    console_putc((char)('0' + s_timer_ppi / 10));
    console_putc((char)('0' + s_timer_ppi % 10));
    console_println("");

    return 0;
}

/**
 * @brief Read the GIC CPU interface's Interrupt Acknowledge Register.
 *
 * Reading @c GICC_IAR returns the INTID of the highest-priority pending
 * interrupt and simultaneously moves it to the active state — this is the
 * GICv2 acknowledgement step. Called from @c aarch64_irq_handler() in
 * @c interrupts.c to identify which interrupt fired; the matching
 * @c apic_eoi_intid() call below completes it.
 *
 * @return INTID (10 bits used by GICv2).
 */
uint32_t apic_read_iar(void)
{
    return mmio_read32(GICC_BASE_PA, GICC_IAR);
}

/**
 * @brief Return the timer PPI this build is watching for.
 *
 * Set once in @c apic_init() from @c aarch64_current_el() (30 at EL1, 26 at
 * EL2). @c aarch64_irq_handler() compares @c apic_read_iar()'s result
 * against this rather than a hardcoded constant.
 */
uint32_t apic_timer_ppi(void)
{
    return s_timer_ppi;
}

/**
 * @brief Signal End of Interrupt to the GIC CPU interface.
 *
 * Writes @p intid back to @c GICC_EOIR, matching the value @c GICC_IAR
 * returned in @c aarch64_irq_handler(). Required after every acknowledged
 * interrupt or the GIC considers it permanently active and will not
 * re-signal it.
 *
 * @param intid INTID as read from @c GICC_IAR (10 bits used by GICv2).
 */
void apic_eoi_intid(uint32_t intid)
{
    mmio_write32(GICC_BASE_PA, GICC_EOIR, intid);
}

/**
 * @brief Signal End of Interrupt (common cross-ISA signature — see below).
 *
 * The shared @c apic.h interface has no way to pass which interrupt is
 * being completed, but GICv2's @c GICC_EOIR needs the exact INTID @c GICC_IAR
 * returned, not just "an" EOI. @c aarch64_irq_handler() calls
 * @c apic_eoi_intid() directly with that value instead; this form exists
 * only to satisfy the common call site and is not used on the interrupt
 * path GIC brings up.
 */
void apic_eoi(void)
{
}

/**
 * @brief Compute the expected system-counter ticks per heartbeat period.
 *
 * Computes @c s_timer_period_tsc (the expected number of @c CNTPCT_EL0
 * ticks between heartbeats), used both by @c heartbeat_init() to seed the
 * rolling-window @c expected_delta and by @c apic_timer_start() /
 * @c apic_timer_rearm() (item 0.7) as the @c TVAL step written on every
 * arm and re-arm.
 *
 * If either @p tsc_hz or @p tick_hz is zero, a fallback of 10,000,000
 * ticks is stored (approximately 160 ms at 62.5 MHz, a safe non-zero
 * sentinel that prevents division-by-zero in the heartbeat path).
 *
 * @param tsc_hz  System counter frequency from @c timer_init() (Hz).
 * @param tick_hz Desired heartbeat rate (Hz); 0 → uses fallback.
 * @return 0 always.
 */
int apic_timer_init(uint64_t tsc_hz, uint32_t tick_hz)
{
    if (tick_hz > 0 && tsc_hz > 0) {
        s_timer_period_tsc = tsc_hz / tick_hz;
    } else {
        s_timer_period_tsc = 10000000;
    }
    return 0;
}

/**
 * @brief Arm the ARM Generic Timer and enable its interrupt (item 0.7).
 *
 * Writes @c CNTP_TVAL_EL0 (or @c CNTHP_TVAL_EL2 at EL2 — @c
 * aarch64_current_el(), same EL-aware discipline as items 0.4–0.6) to
 * @c s_timer_period_tsc, then sets @c CTL.ENABLE=1, @c CTL.IMASK=0.
 *
 * @c TVAL is a signed 32-bit *relative* countdown — writing it sets
 * "fire @c s_timer_period_tsc ticks from this instant," unlike riscv64's
 * SBI interface (item 0.3), which takes an absolute deadline the caller
 * must compute. No "now" reading is needed here at all.
 *
 * The @c ISB after the @c CTL write is required, not decorative: per the
 * architecture, and confirmed against Linux's own
 * @c arch_timer_reg_write_cp15() (arch/arm64/include/asm/arch_timer.h),
 * only the *control* register write needs synchronising before the
 * enable/mask state is guaranteed visible to the interrupt pipeline —
 * @c TVAL/@c CVAL writes do not carry the same requirement, which is why
 * @c apic_timer_rearm() below omits it.
 *
 * @c s_timer_period_tsc must already be set by @c apic_timer_init(). If
 * it is still 0, @c TVAL=0 fires immediately and continuously until
 * @c apic_timer_rearm() runs — a correctly-functioning if oddly-paced
 * timer, not a hang.
 */
void apic_timer_start(void)
{
    /* CNTx_TVAL_EL is architecturally 32-bit (bits[63:32] RES0 on write),
     * but MSR to a system register is always a 64-bit (Xn) instruction
     * form -- there is no 32-bit encoding to match a narrower operand.
     * Truncate to 32 bits ourselves, then zero-extend back to 64 for the
     * operand: this supplies explicit, provably-correct zeros in the RES0
     * field rather than depending on how the hardware treats whatever
     * upper bits a narrower operand happened to leave there -- a
     * distinction we could not confirm against a local authoritative
     * source (unlike the GICv2 offsets and CTL bit layout above,
     * cross-checked against Linux headers on this system; TVAL is not,
     * since Linux's own driver only ever uses the 64-bit CVAL form and
     * never exercises this path). */
    uint64_t tval = (uint64_t)(uint32_t)s_timer_period_tsc;

    if (aarch64_current_el() == 2) {
        __asm__ volatile ("msr cnthp_tval_el2, %0" :: "r"(tval));
        __asm__ volatile ("msr cnthp_ctl_el2, %0"  :: "r"((uint64_t)1) : "memory");
    } else {
        __asm__ volatile ("msr cntp_tval_el0, %0" :: "r"(tval));
        __asm__ volatile ("msr cntp_ctl_el0, %0"  :: "r"((uint64_t)1) : "memory");
    }
    __asm__ volatile ("isb" ::: "memory");
}

/**
 * @brief Re-arm the ARM Generic Timer for the next period (item 0.7).
 *
 * Writes a fresh @c TVAL — the entirety of a periodic re-arm, since @c TVAL
 * is relative to "now" rather than an absolute deadline. Unlike riscv64's
 * SBI re-arm (item 0.3), there is no drift-correction bookkeeping: each
 * write means "@c s_timer_period_tsc ticks from this instant," so time
 * spent servicing the interrupt before this call simply lengthens that one
 * period rather than accumulating error across ticks.
 *
 * **This is the one call that must never be skipped.** The ARM Generic
 * Timer does not auto-reload: once @c TVAL crosses zero, @c CTL.ISTATUS
 * latches and stays asserted — a level condition — until software writes
 * a new @c TVAL or clears @c CTL.ENABLE. A return path that skips this
 * leaves the interrupt permanently pending, which the GIC would deliver
 * again the instant it is EOI'd: a real interrupt storm, not a
 * hypothetical one (this is exactly the failure this driver was checked
 * against during item 0.6's own verification, and confirmed absent there
 * only because nothing armed the timer yet).
 *
 * Called from @c aarch64_irq_handler() (interrupts.c) before
 * @c heartbeat_tick() — same ordering discipline as
 * @c riscv64_timer_rearm() (item 0.3): re-arm first, so a fault in the
 * rest of the handler cannot also cost the next tick.
 */
void apic_timer_rearm(void)
{
    /* uint64_t, zero-extended -- see apic_timer_start() for why. */
    uint64_t tval = (uint64_t)(uint32_t)s_timer_period_tsc;

    if (aarch64_current_el() == 2) {
        __asm__ volatile ("msr cnthp_tval_el2, %0" :: "r"(tval));
    } else {
        __asm__ volatile ("msr cntp_tval_el0, %0" :: "r"(tval));
    }
}

/**
 * @brief Stop timer delivery by clearing CTL.ENABLE (item 0.7).
 *
 * Per the architecture, @c ENABLE=0 unconditionally stops the count and
 * de-asserts the interrupt condition regardless of @c IMASK — a single
 * write is sufficient, no separate mask step needed.
 */
void apic_timer_stop(void)
{
    if (aarch64_current_el() == 2) {
        __asm__ volatile ("msr cnthp_ctl_el2, %0" :: "r"((uint64_t)0) : "memory");
    } else {
        __asm__ volatile ("msr cntp_ctl_el0, %0" :: "r"((uint64_t)0) : "memory");
    }
    __asm__ volatile ("isb" ::: "memory");
}

/**
 * @brief Return the expected system-counter ticks per heartbeat period.
 *
 * Returns @c s_timer_period_tsc, set by @c apic_timer_init() as
 * @c tsc_hz / @c tick_hz. This value is consumed by @c heartbeat_init()
 * to seed the rolling-window @c expected_delta so that inter-tick
 * deviation measurements are relative to the correct nominal interval.
 *
 * @return Expected @c CNTPCT_EL0 ticks per heartbeat period; 10,000,000
 *         if frequencies were not available at init time.
 */
uint64_t apic_timer_period_tsc(void)
{
    return s_timer_period_tsc;
}