[PATCH v4 2/2] gpu: nova-core: add support for GPU timer block. (v4)

[Dave Airlie via B4 Relay <devnull+airlied.redhat.com@kernel.org>]

From: Dave Airlie <airlied@redhat.com>

This is needed to calculate the system timer offset that is passed
to GSP init.

2 HALs exist:

a) tu102 is the gv100 path from open-gpu, the priv level is checked
and the cpu time is written to the gpu timer. no offset is used.

b) gh100 as two variants, gh100 and gb100.
This is the gh100 path from open-gpu, where the secure system
timer is read, the offset is calculated.
On gh100 which need a work around we avoid sending it to registers
other we write the offset to registers.
The gb100 path just avoids the war.
The value is also stored to send to GSP.

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/nova-core/fsp.rs             |  5 +-
 drivers/gpu/nova-core/fsp/regs.rs        | 30 ++++++++++++
 drivers/gpu/nova-core/gpu.rs             |  8 ++++
 drivers/gpu/nova-core/nova_core.rs       |  1 +
 drivers/gpu/nova-core/timer.rs           | 33 +++++++++++++
 drivers/gpu/nova-core/timer/hal.rs       | 27 +++++++++++
 drivers/gpu/nova-core/timer/hal/gh100.rs | 79 ++++++++++++++++++++++++++++++
 drivers/gpu/nova-core/timer/hal/tu102.rs | 53 +++++++++++++++++++++
 drivers/gpu/nova-core/timer/regs.rs      | 82 ++++++++++++++++++++++++++++++++
 9 files changed, 316 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/nova-core/fsp.rs b/drivers/gpu/nova-core/fsp.rs
index b738dcabcdef..222b3dbaca47 100644
--- a/drivers/gpu/nova-core/fsp.rs
+++ b/drivers/gpu/nova-core/fsp.rs
@@ -51,10 +51,11 @@
         NvdmType, //
     },
     num,
-    regs, //
+    regs as bootregs, //
 };
 
 mod hal;
+pub(crate) mod regs;
 
 /// PRC message sub-command.
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -429,7 +430,7 @@ fn wait_secure_boot(
 
         read_poll_timeout(
             || Ok(hal.fsp_boot_status(bar)),
-            |&status| status == regs::NV_THERM_I2CS_SCRATCH_FSP_BOOT_COMPLETE_STATUS_SUCCESS,
+            |&status| status == bootregs::NV_THERM_I2CS_SCRATCH_FSP_BOOT_COMPLETE_STATUS_SUCCESS,
             Delta::from_millis(10),
             Delta::from_millis(FSP_SECURE_BOOT_TIMEOUT_MS),
         )
diff --git a/drivers/gpu/nova-core/fsp/regs.rs b/drivers/gpu/nova-core/fsp/regs.rs
new file mode 100644
index 000000000000..d4b8482a6854
--- /dev/null
+++ b/drivers/gpu/nova-core/fsp/regs.rs
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+
+pub(crate) mod gh100 {
+    use kernel::io::register;
+
+    use crate::{
+        driver::NovaRegisters,
+    };
+
+    // FSP PRI space; the timer is its only consumer so far.
+    register! {
+        base: NovaRegisters;
+
+        /// FSP ucode version, encoded as `major.minor` in bits 11:8 and 7:0, written by the FSP
+        /// during boot. (`NV_PFSP_FALCON_COMMON_SCRATCH_GROUP_3(1)` in the hardware headers.)
+        pub(crate) NV_GFW_FSP_UCODE_VERSION(u32) @ 0x008f0334 {
+            11:0 full;
+        }
+    }
+
+    impl NV_GFW_FSP_UCODE_VERSION {
+        /// Check if the hopper only workaround is required
+        pub(crate) fn is_bug3957833_affected(self) -> bool {
+            /// FSP ucode version from which on the fix for bug 3957833 is included.
+            const FSP_BUG_3957833_FIX_VERSION: u32 = 0x44c;
+
+            self.full().get() < FSP_BUG_3957833_FIX_VERSION
+        }
+    }
+}
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index 4e59072cab50..99b6e33aa243 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -53,6 +53,10 @@
         GpuMm,
         VramAddress, //
     },
+    timer::{
+        Timer,
+        TimerState, //
+    },
     vgpu::VgpuManager, //
 };
 
@@ -331,6 +335,8 @@ struct GspResources<'gpu> {
     // TODO: use different resource types for each boot method, and make the relevant Gsp methods
     // generic against them.
     fsp: Option<Fsp<'gpu>>,
+    /// Timer state - contains system timer offset
+    timer: TimerState,
     /// vGPU state detected before GSP boot.
     vgpu: VgpuManager,
     /// GSP runtime data.
@@ -497,6 +503,8 @@ pub(crate) fn new<'a>(
 
                 fsp: Fsp::try_new(dev, bar, spec.chipset)?,
 
+                timer: Timer::init(bar, spec.chipset)?,
+
                 vgpu: VgpuManager::new(pdev, spec.chipset, fsp.as_mut()),
 
                 gsp <- Gsp::new(pdev, bar),
diff --git a/drivers/gpu/nova-core/nova_core.rs b/drivers/gpu/nova-core/nova_core.rs
index a8f6dc22057b..ee59d81e5105 100644
--- a/drivers/gpu/nova-core/nova_core.rs
+++ b/drivers/gpu/nova-core/nova_core.rs
@@ -27,6 +27,7 @@
 mod sbuffer;
 #[cfg(CONFIG_NOVA_CORE_SELFTESTS)]
 mod selftest;
+mod timer;
 mod vbios;
 mod vgpu;
 
diff --git a/drivers/gpu/nova-core/timer.rs b/drivers/gpu/nova-core/timer.rs
new file mode 100644
index 000000000000..e7ad37806e5b
--- /dev/null
+++ b/drivers/gpu/nova-core/timer.rs
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+mod hal;
+mod regs;
+
+use kernel::{
+    prelude::*, //
+};
+
+use crate::{
+    driver::Bar0,
+    gpu::Chipset, //
+};
+
+pub(crate) struct Timer;
+
+// struct that just holds the sys timer offset
+// after initialising the GPU timer block.
+pub(crate) struct TimerState {
+    /// This value is to be passed to GspInit SYS_TIMER_OFFSET_NS
+    /// It is considered an opaque value, passed from timer hal to GSP.
+    #[allow(dead_code)]
+    sys_timer_offset_ns: u64,
+}
+
+impl Timer {
+    /// Initialize the GPU timer.
+    pub(crate) fn init(bar: Bar0<'_>, chipset: Chipset) -> Result<TimerState> {
+        Ok(TimerState {
+            sys_timer_offset_ns: hal::timer_hal(chipset).init(bar)?,
+        })
+    }
+}
diff --git a/drivers/gpu/nova-core/timer/hal.rs b/drivers/gpu/nova-core/timer/hal.rs
new file mode 100644
index 000000000000..b78066bf9a0d
--- /dev/null
+++ b/drivers/gpu/nova-core/timer/hal.rs
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use kernel::prelude::*;
+
+use crate::{
+    driver::Bar0,
+    gpu::{
+        Architecture,
+        Chipset, //
+    },
+};
+
+mod gh100;
+mod tu102;
+
+pub(super) trait TimerHal {
+    /// return system timer offset ns
+    fn init(&self, bar: Bar0<'_>) -> Result<u64>;
+}
+
+pub(super) fn timer_hal(chipset: Chipset) -> &'static dyn TimerHal {
+    match chipset.arch() {
+        Architecture::Turing | Architecture::Ampere | Architecture::Ada => tu102::TU102_HAL,
+        Architecture::Hopper => gh100::GH100_HAL,
+        Architecture::BlackwellGB10x | Architecture::BlackwellGB20x => gh100::GB100_HAL,
+    }
+}
diff --git a/drivers/gpu/nova-core/timer/hal/gh100.rs b/drivers/gpu/nova-core/timer/hal/gh100.rs
new file mode 100644
index 000000000000..0486df588964
--- /dev/null
+++ b/drivers/gpu/nova-core/timer/hal/gh100.rs
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use super::TimerHal;
+
+use kernel::{
+    io::Io,
+    prelude::*,
+    time::*, //
+};
+
+use crate::{
+    driver::Bar0,
+    fsp::regs as fspregs,
+    timer::regs, //
+};
+
+/// Timer HAL for Hopper and Blackwell.
+struct Gh100 {
+    /// `true` on Hopper, FSP ucode on newer GPUs always has the fix.
+    fsp_bug3957833_war: bool,
+}
+
+impl Gh100 {
+    /// kfspRequiresBug3957833WAR_HAL: returns `true` if the FSP ucode predates the fix for
+    /// bug 3957833 and hence the sys timer offset must not be programmed. Can only be true
+    /// on GH100 with older FSP.
+    fn requires_bug3957833_war(&self, bar: Bar0<'_>) -> bool {
+        self.fsp_bug3957833_war
+            && bar.read(fspregs::gh100::NV_GFW_FSP_UCODE_VERSION).is_bug3957833_affected()
+    }
+
+    fn timer_time(&self, bar: Bar0<'_>, time_ns: u64) -> Result<u64> {
+        let mut sec_hi2 = u32::from(bar.read(regs::gh100::NV_PGC6_SCI_SEC_TIMER_TIME_1));
+        let sec_timer_ns: u64;
+        loop {
+            let sec_lo = u32::from(bar.read(regs::gh100::NV_PGC6_SCI_SEC_TIMER_TIME_0));
+            let sec_hi = u32::from(bar.read(regs::gh100::NV_PGC6_SCI_SEC_TIMER_TIME_1));
+            if sec_hi == sec_hi2 {
+                sec_timer_ns = u64::from(sec_hi) << 32 | u64::from(sec_lo);
+                break;
+            }
+            sec_hi2 = u32::from(bar.read(regs::gh100::NV_PGC6_SCI_SEC_TIMER_TIME_1));
+        }
+
+        // The system and the GPU timer are both free-running with unrelated epochs, so the
+        // difference can be negative. Both operands are < 2^62, hence this cannot overflow.
+        let sys_timer_offset_ns = time_ns.checked_sub(sec_timer_ns).ok_or(EINVAL)?;
+
+        if !self.requires_bug3957833_war(bar) {
+            bar.write_reg(
+                regs::gh100::NV_PGC6_SCI_SYS_TIMER_OFFSET_1::try_from_nsec(sys_timer_offset_ns)?
+            );
+            bar.write_reg(
+                regs::gh100::NV_PGC6_SCI_SYS_TIMER_OFFSET_0::try_from_nsec(sys_timer_offset_ns)?
+                    .with_update(true),
+            );
+        }
+        Ok(sys_timer_offset_ns)
+    }
+}
+
+impl TimerHal for Gh100 {
+    fn init(&self, bar: Bar0<'_>) -> Result<u64> {
+        // The open drivers uses wall clock time here not monotonic
+        let sys_time_ns = Instant::<RealTime>::now().as_nanos();
+
+        self.timer_time(bar, sys_time_ns as u64)
+    }
+}
+
+const GH100: Gh100 = Gh100 {
+    fsp_bug3957833_war: true,
+};
+const GB100: Gh100 = Gh100 {
+    fsp_bug3957833_war: false,
+};
+
+pub(super) const GH100_HAL: &dyn TimerHal = &GH100;
+pub(super) const GB100_HAL: &dyn TimerHal = &GB100;
diff --git a/drivers/gpu/nova-core/timer/hal/tu102.rs b/drivers/gpu/nova-core/timer/hal/tu102.rs
new file mode 100644
index 000000000000..c0777b777362
--- /dev/null
+++ b/drivers/gpu/nova-core/timer/hal/tu102.rs
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use super::TimerHal;
+
+use kernel::{
+    io::Io,
+    prelude::*,
+    time::*, //
+};
+
+use crate::{
+    driver::Bar0,
+    timer::regs, //
+};
+struct Tu102;
+
+// this code will be used in the gb10b hal eventually
+#[expect(dead_code)]
+fn timer_read(bar: Bar0<'_>) -> u64 {
+    let mut hi2: u32 = u32::from(bar.read(regs::NV_PTIMER_TIME_1));
+    loop {
+        let lo = u32::from(bar.read(regs::NV_PTIMER_TIME_0));
+        let hi = u32::from(bar.read(regs::NV_PTIMER_TIME_1));
+        if hi == hi2 {
+            return u64::from(hi) << 32 | u64::from(lo);
+        }
+        hi2 = u32::from(bar.read(regs::NV_PTIMER_TIME_1));
+    }
+}
+
+fn timer_time(bar: Bar0<'_>, time_ns: u64) -> Result {
+    if bar.read(regs::NV_PTIMER_TIME_PRIV_LEVEL_MASK).level0() {
+        bar.write_reg(regs::NV_PTIMER_TIME_1::try_from_nsec(time_ns)?);
+        bar.write_reg(regs::NV_PTIMER_TIME_0::try_from_nsec(time_ns)?);
+        Ok(())
+    } else {
+        Err(EINVAL)
+    }
+}
+
+impl TimerHal for Tu102 {
+    fn init(&self, bar: Bar0<'_>) -> Result<u64> {
+        // The RM uses wall clock time here (osGetSystemTime -> ktime_get_real), so the GPU time
+        // matches the host's real time, e.g. for timestamp correlation in userspace.
+        let sys_time_ns = Instant::<RealTime>::now().as_nanos();
+
+        timer_time(bar, sys_time_ns as u64)?;
+        Ok(0_u64)
+    }
+}
+
+const TU102: Tu102 = Tu102;
+pub(super) const TU102_HAL: &dyn TimerHal = &TU102;
diff --git a/drivers/gpu/nova-core/timer/regs.rs b/drivers/gpu/nova-core/timer/regs.rs
new file mode 100644
index 000000000000..3de7174f20db
--- /dev/null
+++ b/drivers/gpu/nova-core/timer/regs.rs
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use kernel::io::register;
+use kernel::prelude::*;
+
+use crate::{
+    driver::NovaRegisters,
+};
+use pin_init::Zeroable;
+
+// PTIMER
+
+register! {
+    base: NovaRegisters;
+
+    pub(crate) NV_PTIMER_TIME_PRIV_LEVEL_MASK(u32) @ 0x00009430 {
+        4:4 level0 => bool;
+    }
+
+    pub(crate) NV_PTIMER_TIME_0(u32) @ 0x00009400 {
+        31:5 nsec;
+    }
+
+    pub(crate) NV_PTIMER_TIME_1(u32) @ 0x00009410 {
+        28:0 nsec;
+    }
+}
+
+impl NV_PTIMER_TIME_0 {
+    pub(crate) fn try_from_nsec(nsec: u64) -> Result<Self> {
+        Ok(Self::zeroed().try_with_nsec(((nsec >> 5) & 0x7FF_FFFF) as u32)?)
+    }
+}
+
+impl NV_PTIMER_TIME_1 {
+    pub(crate) fn try_from_nsec(nsec: u64) -> Result<Self> {
+        Ok(Self::zeroed().try_with_nsec(((nsec >> 32) & 0x1FFF_FFFF) as u32)?)
+    }
+}
+
+pub(crate) mod gh100 {
+    use kernel::io::register;
+    use kernel::prelude::*;
+
+    use crate::driver::NovaRegisters;
+    use pin_init::Zeroable;
+
+    // PGC6/TIMER
+    register! {
+        base: NovaRegisters;
+
+        pub(crate) NV_PGC6_SCI_SEC_TIMER_TIME_0(u32) @ 0x00118f54 {
+            31:5 nsec;
+        }
+
+        pub(crate) NV_PGC6_SCI_SEC_TIMER_TIME_1(u32) @ 0x00118f58 {
+            28:0 nsec;
+        }
+
+        pub(crate) NV_PGC6_SCI_SYS_TIMER_OFFSET_0(u32) @ 0x00118df4 {
+            0:0 update;
+            31:5 nsec;
+        }
+
+        pub(crate) NV_PGC6_SCI_SYS_TIMER_OFFSET_1(u32) @ 0x00118df8 {
+            28:0 nsec;
+        }
+
+    }
+
+    impl NV_PGC6_SCI_SYS_TIMER_OFFSET_0 {
+        pub(crate) fn try_from_nsec(nsec: u64) -> Result<Self> {
+            Ok(Self::zeroed().try_with_nsec(((nsec >> 5) & 0x7FF_FFFF) as u32)?)
+        }
+    }
+
+    impl NV_PGC6_SCI_SYS_TIMER_OFFSET_1 {
+        pub(crate) fn try_from_nsec(nsec: u64) -> Result<Self> {
+            Ok(Self::zeroed().try_with_nsec(((nsec >> 32) & 0x1FFF_FFFF) as u32)?)
+        }
+    }
+}

-- 
2.56.0