gpu: nova-core: complete conversion to kernel `num` module
Subsystems (5)
Alexandre Courbot
maintainercover gpu: nova-core: complete conversion to kernel `num` module
This is extracted from the now-defunct const_as series [1] and does the groundwork required to eventually convert nova-core to use the cv! macro [2].
Patch 1 does the minimum necessary to convert nova-core to the kernel's num module and removes its local copy. Patch 2 broadens the use of FromSafeCast to avoid having to refer the casts module at every conversion. After it, the only references left to casts are the conversions done in const context, that will eventually be replaced by the cv! macro.
This series is based on master and should be mergeable after -rc1 has been tagged.
[1] https://lore.kernel.org/all/[email protected]/
[2] https://lore.kernel.org/all/[email protected]/
---
Alexandre Courbot (2):
gpu: nova-core: use kernel lossless integer conversion module
gpu: nova-core: use FromSafeCast wherever possible
drivers/gpu/nova-core/falcon.rs | 12 +- drivers/gpu/nova-core/falcon/fsp.rs | 4 +- drivers/gpu/nova-core/fb.rs | 2 +- drivers/gpu/nova-core/fb/hal/gb100.rs | 6 +- drivers/gpu/nova-core/firmware.rs | 4 +- drivers/gpu/nova-core/firmware/booter.rs | 4 +- drivers/gpu/nova-core/firmware/fwsec.rs | 2 +- drivers/gpu/nova-core/firmware/fwsec/bootloader.rs | 4 +- drivers/gpu/nova-core/firmware/gsp.rs | 9 +- drivers/gpu/nova-core/firmware/tlv.rs | 11 +- drivers/gpu/nova-core/fsp.rs | 8 +- drivers/gpu/nova-core/gsp.rs | 4 +- drivers/gpu/nova-core/gsp/cmdq.rs | 25 +-- drivers/gpu/nova-core/gsp/fw.rs | 42 ++-- drivers/gpu/nova-core/gsp/fw/commands.rs | 4 +- drivers/gpu/nova-core/gsp/sequencer.rs | 2 +- drivers/gpu/nova-core/mctp.rs | 8 +- drivers/gpu/nova-core/num.rs | 211 --------------------- drivers/gpu/nova-core/vbios.rs | 2 +- 19 files changed, 81 insertions(+), 283 deletions(-)
---
base-commit: 1b78070aaef63512688aebfbc82365ef9d6660f1
change-id: 20260828-nova_num-64e1b2e84f77
Best regards,
Signature · 1 line
Alexandre Courbot <[email protected]>
Alexandre Courbot
maintainerPATCH 1/2 gpu: nova-core: use kernel lossless integer conversion module
The kernel crate now features a replacement for our lossless integer conversion routines. Switch to the kernel version and remove our own.
--- drivers/gpu/nova-core/falcon.rs | 12 +- drivers/gpu/nova-core/falcon/fsp.rs | 4 +- drivers/gpu/nova-core/fb.rs | 2 +- drivers/gpu/nova-core/fb/hal/gb100.rs | 6 +- drivers/gpu/nova-core/firmware.rs | 4 +- drivers/gpu/nova-core/firmware/booter.rs | 4 +- drivers/gpu/nova-core/firmware/fwsec.rs | 2 +- drivers/gpu/nova-core/firmware/fwsec/bootloader.rs | 4 +- drivers/gpu/nova-core/firmware/gsp.rs | 9 +- drivers/gpu/nova-core/firmware/tlv.rs | 11 +- drivers/gpu/nova-core/fsp.rs | 8 +- drivers/gpu/nova-core/gsp.rs | 4 +- drivers/gpu/nova-core/gsp/cmdq.rs | 22 +-- drivers/gpu/nova-core/gsp/fw.rs | 42 ++-- drivers/gpu/nova-core/gsp/fw/commands.rs | 4 +- drivers/gpu/nova-core/gsp/sequencer.rs | 2 +- drivers/gpu/nova-core/mctp.rs | 8 +- drivers/gpu/nova-core/num.rs | 211 --------------------- drivers/gpu/nova-core/vbios.rs | 2 +- 19 files changed, 78 insertions(+), 283 deletions(-)
drivers/gpu/nova-core/falcon.rs +6 -6
@@ -20,6 +20,10 @@ }, Io, }, + num::casts::{ + self, + FromSafeCast, // + }, prelude::*, time::Delta, };
@@ -29,11 +33,7 @@ driver::Bar0, falcon::hal::LoadMethod, gpu::Chipset, - num::{ - self, - FromSafeCast, // - }, - regs, + regs, // };pub (crate )mod fsp;
@@ -510,7 +510,7 @@ fn dma_wr( target_mem: FalconMem, load_offsets: FalconDmaLoadTarget, ) -> Result { - const DMA_LEN: u32 = num::usize_into_u32::<{ MEM_BLOCK_ALIGNMENT }>(); + const DMA_LEN: u32 = casts::usize_into_u32::<{ MEM_BLOCK_ALIGNMENT }>();// DMA transfers can only be done in units of 256 bytes. Compute how many such transfers we // need to perform.
drivers/gpu/nova-core/falcon/fsp.rs +2 -2
@@ -16,6 +16,7 @@ }, Io, // }, + num::casts, prelude::*, sizes::SZ_1K, time::Delta,
@@ -28,7 +29,6 @@ PFalcon2Base, PFalconBase, // }, - num, regs, // };
@@ -165,7 +165,7 @@ pub(crate) fn recv_msg(&mut self) -> Result<KVec<u8>> { Delta::from_millis(10), Delta::from_millis(FSP_MSG_TIMEOUT_MS), ) - .map (num::u32_as_usize)?; + .map (casts::u32_as_usize)?;// Don't blindly allocate more than the maximum we expect from FSP. if msg_size >FSP_EMEM_CHANNEL_0_SIZE {
drivers/gpu/nova-core/fb.rs +1 -1
@@ -10,6 +10,7 @@ dma::CoherentHandle, fmt, io::Io, + num::casts::FromSafeCast, prelude::*, ptr::{Alignable ,
@@ -23,7 +24,6 @@ firmware::gsp::GspFirmware, gpu::Chipset, gsp, - num::FromSafeCast, vgpu::VgpuState, // };
drivers/gpu/nova-core/fb/hal/gb100.rs +4 -2
@@ -11,7 +11,10 @@ }, Io, // }, - num::Bounded, + num::{ + casts::usize_into_u32, + Bounded, // + }, prelude::*, ptr::{ const_align_up,
@@ -26,7 +29,6 @@ hal::FbHal, regs, // }, - num::usize_into_u32, };struct Gb100 ;
drivers/gpu/nova-core/firmware.rs +2 -2
@@ -9,6 +9,7 @@use kernel::{ firmware, + num::casts::IntoSafeCast , prelude::*,// };
@@ -18,8 +19,7 @@ FalconFirmware, // }, gpu, - gsp::boot_firmware_files, - num::IntoSafeCast, // + gsp::boot_firmware_files, // };pub (crate )mod booter;
drivers/gpu/nova-core/firmware/booter.rs +2 -2
@@ -10,6 +10,7 @@use kernel::{ device, dma::Coherent , + num::casts::IntoSafeCast , prelude::*,// };
@@ -32,8 +33,7 @@ Signed, Unsigned, // }, - gpu::Chipset, - num::IntoSafeCast, + gpu::Chipset, // };/// Signature for Booter firmware. Their size is encoded into the header and not known a compile
drivers/gpu/nova-core/firmware/fwsec.rs +1 -1
@@ -19,6 +19,7 @@ self, Device, // }, + num::casts::FromSafeCast, prelude::*, transmute::{AsBytes ,
@@ -42,7 +43,6 @@ Signed, Unsigned, // }, - num::FromSafeCast, vbios::Vbios, };
drivers/gpu/nova-core/firmware/fwsec/bootloader.rs +2 -2
@@ -13,6 +13,7 @@ }, dma::Coherent, io::{register::WithBase, Io}, + num::casts::FromSafeCast, prelude::*, ptr::{Alignable ,
@@ -45,8 +46,7 @@ }, }, gpu::Chipset, - num::FromSafeCast, // - regs, + regs, // };/// Structure used by the boot-loader to load the rest of the code.
drivers/gpu/nova-core/firmware/gsp.rs +6 -3
@@ -9,6 +9,10 @@ DmaAddress, // }, firmware, + num::casts::{ + arch::FromSafeCastArch, + FromSafeCast, // + }, prelude::*, scatterlist::{Owned ,
@@ -26,8 +30,7 @@ }, }, gpu::Chipset, - gsp::GSP_PAGE_SIZE, - num::FromSafeCast, + gsp::GSP_PAGE_SIZE, // };/// GSP firmware with 3-level radix page tables for the GSP bootloader.
@@ -154,7 +157,7 @@ pub(crate) fn radix3_dma_address(&self) -> DmaAddress {fn map_into_lvl (sg_table: &SGTable <Owned <VVec <u8 >>>,mut dst:VVec <u8 >) ->Result <VVec <u8 >> {for sg_entryin sg_table.iter () {// Number of pages we need to map. -let num_pages = usize::from_safe_cast (sg_entry.dma_len ()).div_ceil (GSP_PAGE_SIZE ); +let num_pages = usize::from_safe_cast_arch (sg_entry.dma_len ()).div_ceil (GSP_PAGE_SIZE );for iin 0 ..num_pages {let entry = sg_entry.dma_address ()
drivers/gpu/nova-core/firmware/tlv.rs +6 -5
@@ -4,14 +4,15 @@use kernel::{ device, firmware, + num::casts::{ + self, +IntoSafeCast ,// + }, prelude::*, str::CString ,// }; -use crate ::{ - gpu, - num::*,// -}; +use crate ::gpu;/// Requests the GPU firmware TLV `name` suitable for `chipset`. pub(crate) fn request_tlv(
@@ -51,7 +52,7 @@ fn parse(hdr: &[u8]) -> Option<Self> {return None ; }let len_arr = <[u8 ;4 ]>::try_from (hdr.get (4 ..Self ::SIZE )?).ok ()?; -let length =u32_as_usize (u32::from_le_bytes (len_arr)); +let length = casts::u32_as_usize (u32::from_le_bytes (len_arr));Some (Self { tag, length }) } }
drivers/gpu/nova-core/fsp.rs +5 -3
@@ -11,7 +11,10 @@ device, dma::Coherent, io::poll::read_poll_timeout, - num::TryIntoBounded, + num::{ + casts, + TryIntoBounded, // + }, prelude::*, ptr::{Alignable ,
@@ -47,7 +50,6 @@ NvdmHeader, NvdmType, // }, - num, regs, // };
@@ -285,7 +287,7 @@ fn new<'a>( };let version = hal.cot_version (); -let size = num::usize_into_u16 ::<{ core::mem::size_of ::<NvdmPayloadCot >() }>(); +let size = casts::usize_into_u16 ::<{ core::mem::size_of ::<NvdmPayloadCot >() }>(); Ok(init!(Self { header: FspMessageHeader::new(NvdmType::Cot),
drivers/gpu/nova-core/gsp.rs +2 -2
@@ -17,6 +17,7 @@ io_write, Io, // }, + num::casts, pci, prelude::*, // };
@@ -48,7 +49,6 @@ cmdq::Cmdq, fw::GspArgumentsPadded, // }, - num, vgpu::VgpuManager, // };
@@ -92,7 +92,7 @@ fn init(view: CoherentView<'_, Self>, start: DmaAddress) -> Result<()> {for iin 0 ..NUM_PAGES {io_write! (view, .0 [build: i], start - .checked_add (num::usize_as_u64 (i) <<GSP_PAGE_SHIFT ) + .checked_add (casts::usize_as_u64 (i) <<GSP_PAGE_SHIFT ) .ok_or (EOVERFLOW )? ); }
drivers/gpu/nova-core/gsp/cmdq.rs +11 -11
@@ -23,6 +23,7 @@ Io, // }, new_mutex, + num::casts, prelude::*, ptr, sync::{
@@ -57,7 +58,6 @@ GSP_PAGE_SHIFT, GSP_PAGE_SIZE, // }, - num, sbuffer::SBufferIter, // };
@@ -162,7 +162,7 @@ fn read(#[repr( C , align( 0x1000 ))] #[derive( Debug )] struct MsgqData { - data: [[u8 ;GSP_PAGE_SIZE ]; num::u32_as_usize (MSGQ_NUM_PAGES )], + data: [[u8 ;GSP_PAGE_SIZE ]; casts::u32_as_usize (MSGQ_NUM_PAGES )], }// Annoyingly we are forced to use a literal to specify the alignment of
@@ -235,8 +235,8 @@ unsafe impl FromBytes for GspMem {}impl DmaGspMem {/// Allocate a new instance and map it for `dev`. fn new (dev: &device::Device <device::Bound >) ->Result <Self > { -const MSGQ_SIZE :u32 = num::usize_into_u32 ::<{size_of ::<Msgq >() }>(); -const RX_HDR_OFF :u32 = num::usize_into_u32 ::<{ mem::offset_of!(Msgq , rx) }>(); +const MSGQ_SIZE :u32 = casts::usize_into_u32 ::<{size_of ::<Msgq >() }>(); +const RX_HDR_OFF :u32 = casts::usize_into_u32 ::<{ mem::offset_of!(Msgq , rx) }>();let mut gsp_mem =CoherentBox ::<GspMem >::zeroed (dev,GFP_KERNEL )?; gsp_mem.cpuq.tx =MsgqTxHeader ::new (MSGQ_SIZE ,RX_HDR_OFF ,MSGQ_NUM_PAGES );
@@ -289,10 +289,10 @@ fn new(dev: &device::Device<device::Bound>) -> Result<Self> {unsafe { ( core::slice::from_raw_parts_mut ( - data.add (num::u32_as_usize (tx)), - num::u32_as_usize (tail_end - tx), + data.add (casts::u32_as_usize (tx)), + casts::u32_as_usize (tail_end - tx), ), - core::slice::from_raw_parts_mut (data, num::u32_as_usize (wrap_end)), + core::slice::from_raw_parts_mut (data, casts::u32_as_usize (wrap_end)), ) } }
@@ -307,7 +307,7 @@ fn driver_write_area_size(&self) -> usize {// `cpu_write_ptr`. The minimum value case is where `rx == 0` and `tx == MSGQ_NUM_PAGES - // 1`, which gives `0 + MSGQ_NUM_PAGES - (MSGQ_NUM_PAGES - 1) - 1 == 0`. let slots = (rx +MSGQ_NUM_PAGES - tx -1 ) %MSGQ_NUM_PAGES ; - num::u32_as_usize (slots) *GSP_PAGE_SIZE + casts::u32_as_usize (slots) *GSP_PAGE_SIZE }/// Returns the region of the GSP message queue that the driver is currently allowed to read
@@ -343,10 +343,10 @@ fn driver_write_area_size(&self) -> usize {unsafe { ( core::slice::from_raw_parts ( - data.add (num::u32_as_usize (rx)), - num::u32_as_usize (tail_end - rx), + data.add (casts::u32_as_usize (rx)), + casts::u32_as_usize (tail_end - rx), ), - core::slice::from_raw_parts (data, num::u32_as_usize (wrap_end)), + core::slice::from_raw_parts (data, casts::u32_as_usize (wrap_end)), ) } }
drivers/gpu/nova-core/gsp/fw.rs +21 -21
107 lines not on this page · raw message
drivers/gpu/nova-core/gsp/fw/commands.rs +2 -2
@@ -5,6 +5,7 @@use kernel::{ device, + num::casts::IntoSafeCast , pci, prelude::*, transmute::{
@@ -15,8 +16,7 @@use crate ::{ gpu::Chipset , - gsp::GSP_PAGE_SIZE , - num::IntoSafeCast ,// + gsp::GSP_PAGE_SIZE ,// };use super ::bindings;
drivers/gpu/nova-core/gsp/sequencer.rs +1 -1
@@ -11,6 +11,7 @@ poll::read_poll_timeout, Io, // }, + num::casts::FromSafeCast, prelude::*, time::{ delay::fsleep,
@@ -35,7 +36,6 @@ GspBootContext, LibosMemoryRegionInitArgument, // }, - num::FromSafeCast, sbuffer::SBufferIter, };
drivers/gpu/nova-core/mctp.rs +3 -5
@@ -9,14 +9,12 @@use kernel::{ bitfield, + num::casts, pci::Vendor , prelude::*,// }; -use crate ::{ - bounded_enum, - num,// -}; +use crate ::bounded_enum;bounded_enum! {/// NVDM message type identifiers carried over MCTP.
@@ -76,7 +74,7 @@ impl NvdmHeader {/// Builds an NVDM header for the given message type. pub (crate )fn new (nvdm_type:NvdmType ) ->Self {Self ::zeroed () - .with_const_msg_type ::<{ num::u8_as_u32 (MSG_TYPE_VENDOR_PCI ) }>() + .with_const_msg_type ::<{ casts::u8_as_u32 (MSG_TYPE_VENDOR_PCI ) }>() .with_vendor_id (Vendor ::NVIDIA .as_raw ()) .with_nvdm_type (nvdm_type) }
drivers/gpu/nova-core/num.rs +0 -211
217 lines not on this page · raw message
drivers/gpu/nova-core/vbios.rs +1 -1
@@ -5,6 +5,7 @@use kernel::{ device, io::Io , + num::casts::FromSafeCast , prelude::*, ptr::{Alignable ,
@@ -23,7 +24,6 @@ FalconUCodeDescV2, FalconUCodeDescV3, // }, - num::FromSafeCast, };/// BIOS Image Type from PCI Data Structure code_type field.
Signature · 1 line
2.55.0
[email protected]
AI reviewRe: [PATCH 1/2] gpu: nova-core: use kernel lossless integer conversion module
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] A TOCTOU double-fetch vulnerability in GSP message parsing allows compromised or malicious GSP firmware to corrupt the CPU's message queue read pointer, causing desynchronization and potential denial of service. --
commit eaaa0723c196a2c00643733ca548b4c1354725ff
Author: Alexandre Courbot <[email protected]>
gpu: nova-core: use kernel lossless integer conversion module
The kernel crate now features a replacement for our lossless integer conversion routines. Switch to the kernel version and remove our own.
Quoted 4 lines
drivers/gpu/nova-core/gsp/cmdq.rs +0
-0
[ ... ]
drivers/gpu/nova-core/gsp/cmdq.rs fn read( · line 166
Quoted 7 lines
drivers/gpu/nova-core/gsp/cmdq.rs +1
-1@@ -162,7 +162,7 @@ fn read(#[repr( C , align( 0x1000 ))] #[derive( Debug )] struct MsgqData { - data: [[u8 ;GSP_PAGE_SIZE ]; num::u32_as_usize (MSGQ_NUM_PAGES )], + data: [[u8 ;GSP_PAGE_SIZE ]; casts::u32_as_usize (MSGQ_NUM_PAGES )], }
[Severity: High]
This isn't a bug introduced by this patch, but while reviewing cmdq.rs, I noticed a pre-existing double-fetch issue that could allow a compromised GSP firmware to desynchronize the message queue.
Could the GSP modify the message length in DMA memory after it has been validated, causing the host to corrupt its CPU read pointer?
In CmdqInner::wait_for_msg(), the message length is fetched from DMA memory and validated against the available buffer size to ensure it is safe:
CmdqInner::wait_for_msg() {
...
let payload_length = header.payload_length();
// Check that the driver read area is large enough for the message.
if slice_1.len() + slice_2.len() < payload_length {
return Err(EIO);
}
...
}However, upon returning to CmdqInner::receive_msg(), the length is fetched a second time directly from the shared memory when advancing the queue read pointer:
CmdqInner::receive_msg() {
...
let message = self.wait_for_msg(timeout)?;
...
// Advance the read pointer past this message.
self.gsp_mem.advance_cpu_read_ptr(u32::try_from(
message.header.length().div_ceil(GSP_PAGE_SIZE),
)?);
...
}Because message.header is a reference into DMA memory, this second fetch uses an unvalidated value. If the GSP modifies the length field in DMA memory between these two reads, the kernel will advance its read pointer by an unvalidated amount. This could cause the kernel to misinterpret queue memory, fail subsequent validations, and lose communication with the GSP.
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
Danilo Krummrich
maintainerRe: [PATCH 1/2] gpu: nova-core: use kernel lossless integer conversion module
In reply to Alexandre Courbot(Cc: Miguel)
Quoted 19 lines · Alexandre Courbot
The
kernelcrate now features a replacement for our lossless integer conversion routines. Switch to the kernel version and remove our own.Signed-off-by Alexandre Courbot <[email protected]>Reviewed-by Danilo Krummrich <[email protected]>Reviewed-by Eliot Courtney <[email protected]>--- drivers/gpu/nova-core/falcon.rs | 12 +- drivers/gpu/nova-core/falcon/fsp.rs | 4 +- drivers/gpu/nova-core/fb.rs | 2 +- drivers/gpu/nova-core/fb/hal/gb100.rs | 6 +- drivers/gpu/nova-core/firmware.rs | 4 +- drivers/gpu/nova-core/firmware/booter.rs | 4 +- drivers/gpu/nova-core/firmware/fwsec.rs | 2 +- drivers/gpu/nova-core/firmware/fwsec/bootloader.rs | 4 +- drivers/gpu/nova-core/firmware/gsp.rs | 9 +- drivers/gpu/nova-core/firmware/tlv.rs | 11 +- drivers/gpu/nova-core/fsp.rs | 8 +- drivers/gpu/nova-core/gsp.rs | 4 +-
Quoted 8 lines
drivers/gpu/nova-core/gsp/cmdq.rs | 22 +-- drivers/gpu/nova-core/gsp/fw.rs | 42 ++-- drivers/gpu/nova-core/gsp/fw/commands.rs | 4 +- drivers/gpu/nova-core/gsp/sequencer.rs | 2 +- drivers/gpu/nova-core/mctp.rs | 8 +- drivers/gpu/nova-core/num.rs | 211 --------------------- drivers/gpu/nova-core/vbios.rs | 2 +- 19 files changed, 78 insertions(+), 283 deletions(-)
Please see the discussion in [1].
If we make this change, then the subsequent conversion to const_as!() would need to go through the Rust tree next cycle, which could be a bit of a mess, as I'd expect a bunch of conflicts.
Alternatively, we could the the full three cycle dance, or have a signed tag for const_as!() and use it right away.
But honestly, the former would just be unnecessary noise. If we don't do the latter, let's just keep the nova-core num module until the dust has been settled.
[1] https://lore.kernel.org/all/CANiq72k+-fNWZCwGuQ=FTchxgm-X-f6WR=tG=Ercn19ic1edQg@mail.gmail.com/
Re: [PATCH 1/2] gpu: nova-core: use kernel lossless integer conversion module
Quoted 4 lines · Danilo Krummrich
But honestly, the former would just be unnecessary noise. If we don't do the latter, let's just keep the nova-core num module until the dust has been settled.
Yeah, keeping the nova num for a bit sounds fine.
Cheers,
Miguel
Alexandre Courbot
maintainerRe: [PATCH 1/2] gpu: nova-core: use kernel lossless integer conversion module
In reply to Danilo KrummrichQuoted 37 lines · Danilo Krummrich
(Cc: Miguel)
Quoted 19 lines · Alexandre Courbot
The
kernelcrate now features a replacement for our lossless integer conversion routines. Switch to the kernel version and remove our own.Signed-off-by Alexandre Courbot <[email protected]>Reviewed-by Danilo Krummrich <[email protected]>Reviewed-by Eliot Courtney <[email protected]>--- drivers/gpu/nova-core/falcon.rs | 12 +- drivers/gpu/nova-core/falcon/fsp.rs | 4 +- drivers/gpu/nova-core/fb.rs | 2 +- drivers/gpu/nova-core/fb/hal/gb100.rs | 6 +- drivers/gpu/nova-core/firmware.rs | 4 +- drivers/gpu/nova-core/firmware/booter.rs | 4 +- drivers/gpu/nova-core/firmware/fwsec.rs | 2 +- drivers/gpu/nova-core/firmware/fwsec/bootloader.rs | 4 +- drivers/gpu/nova-core/firmware/gsp.rs | 9 +- drivers/gpu/nova-core/firmware/tlv.rs | 11 +- drivers/gpu/nova-core/fsp.rs | 8 +- drivers/gpu/nova-core/gsp.rs | 4 +-Quoted 8 lines
drivers/gpu/nova-core/gsp/cmdq.rs | 22 +-- drivers/gpu/nova-core/gsp/fw.rs | 42 ++-- drivers/gpu/nova-core/gsp/fw/commands.rs | 4 +- drivers/gpu/nova-core/gsp/sequencer.rs | 2 +- drivers/gpu/nova-core/mctp.rs | 8 +- drivers/gpu/nova-core/num.rs | 211 --------------------- drivers/gpu/nova-core/vbios.rs | 2 +- 19 files changed, 78 insertions(+), 283 deletions(-)Please see the discussion in [1].
If we make this change, then the subsequent conversion to const_as!() would need to go through the Rust tree next cycle, which could be a bit of a mess, as I'd expect a bunch of conflicts.
Quoted 8 lines
Alternatively, we could the the full three cycle dance, or have a signed tag for const_as!() and use it right away.
But honestly, the former would just be unnecessary noise. If we don't do the latter, let's just keep the nova-core num module until the dust has been settled.
[1] https://lore.kernel.org/all/CANiq72k+-fNWZCwGuQ=FTchxgm-X-f6WR=tG=Ercn19ic1edQg@mail.gmail.com/
Maybe I am missing something, but wouldn't the following work?
- rc1 gets tagged, drm-rust-next gets the num::casts module,
- This series gets applied to drm-rust-next, then cv! (without the nova-core conversion patch) in rust-next,
- We wait one cycle for cv! to trickle down to drm-rust-next before converting nova-core to use cv!.
Would that work? This series doesn't overlap with the const conversions that cv! covers on purpose, and it would have the benefit of getting rid of the local num module in nova-core quickly.
Danilo Krummrich
maintainerRe: [PATCH 1/2] gpu: nova-core: use kernel lossless integer conversion module
Quoted 55 lines · Alexandre Courbot
Quoted 37 lines · Danilo Krummrich
(Cc: Miguel)
Quoted 19 lines · Alexandre Courbot
The
kernelcrate now features a replacement for our lossless integer conversion routines. Switch to the kernel version and remove our own.Signed-off-by Alexandre Courbot <[email protected]>Reviewed-by Danilo Krummrich <[email protected]>Reviewed-by Eliot Courtney <[email protected]>--- drivers/gpu/nova-core/falcon.rs | 12 +- drivers/gpu/nova-core/falcon/fsp.rs | 4 +- drivers/gpu/nova-core/fb.rs | 2 +- drivers/gpu/nova-core/fb/hal/gb100.rs | 6 +- drivers/gpu/nova-core/firmware.rs | 4 +- drivers/gpu/nova-core/firmware/booter.rs | 4 +- drivers/gpu/nova-core/firmware/fwsec.rs | 2 +- drivers/gpu/nova-core/firmware/fwsec/bootloader.rs | 4 +- drivers/gpu/nova-core/firmware/gsp.rs | 9 +- drivers/gpu/nova-core/firmware/tlv.rs | 11 +- drivers/gpu/nova-core/fsp.rs | 8 +- drivers/gpu/nova-core/gsp.rs | 4 +-Quoted 8 lines
drivers/gpu/nova-core/gsp/cmdq.rs | 22 +-- drivers/gpu/nova-core/gsp/fw.rs | 42 ++-- drivers/gpu/nova-core/gsp/fw/commands.rs | 4 +- drivers/gpu/nova-core/gsp/sequencer.rs | 2 +- drivers/gpu/nova-core/mctp.rs | 8 +- drivers/gpu/nova-core/num.rs | 211 --------------------- drivers/gpu/nova-core/vbios.rs | 2 +- 19 files changed, 78 insertions(+), 283 deletions(-)Please see the discussion in [1].
If we make this change, then the subsequent conversion to const_as!() would need to go through the Rust tree next cycle, which could be a bit of a mess, as I'd expect a bunch of conflicts.
Quoted 8 lines
Alternatively, we could the the full three cycle dance, or have a signed tag for const_as!() and use it right away.
But honestly, the former would just be unnecessary noise. If we don't do the latter, let's just keep the nova-core num module until the dust has been settled.
[1] https://lore.kernel.org/all/CANiq72k+-fNWZCwGuQ=FTchxgm-X-f6WR=tG=Ercn19ic1edQg@mail.gmail.com/
Maybe I am missing something, but wouldn't the following work?
- rc1 gets tagged,
drm-rust-nextgets thenum::castsmodule,
- This series gets applied todrm-rust-next, thencv!(without the nova-core conversion patch) inrust-next,
- We wait one cycle forcv!to trickle down todrm-rust-nextbefore converting nova-core to usecv!.
Quoted 3 lines
Would that work? This series doesn't overlap with the const conversions that
cv!covers on purpose, and it would have the benefit of getting rid of the localnummodule in nova-core quickly.
Take casts::usize_into_u32() for instance, drm-rust-next replaces the usage of it next cycle, but rust-next wants to remove the API from rust/kernel/num/casts.rs.
In this case rust-next would need to get rid of the users (including nova-core), but drm-rust-next will likely do different changes, so we'd get unnecessary merge conflicts.
You can resolve this either by keeping casts::usize_into_u32 and friends around for one additional cycle, so that all users we introduce now are gone. Or, since there's no rush anyways, we just wait one cycle and use the real thing right away.
Alexandre Courbot
maintainerRe: [PATCH 1/2] gpu: nova-core: use kernel lossless integer conversion module
Quoted 64 lines · Danilo Krummrich
Quoted 55 lines · Alexandre Courbot
Quoted 37 lines · Danilo Krummrich
(Cc: Miguel)
Quoted 19 lines · Alexandre Courbot
The
kernelcrate now features a replacement for our lossless integer conversion routines. Switch to the kernel version and remove our own.Signed-off-by Alexandre Courbot <[email protected]>Reviewed-by Danilo Krummrich <[email protected]>Reviewed-by Eliot Courtney <[email protected]>--- drivers/gpu/nova-core/falcon.rs | 12 +- drivers/gpu/nova-core/falcon/fsp.rs | 4 +- drivers/gpu/nova-core/fb.rs | 2 +- drivers/gpu/nova-core/fb/hal/gb100.rs | 6 +- drivers/gpu/nova-core/firmware.rs | 4 +- drivers/gpu/nova-core/firmware/booter.rs | 4 +- drivers/gpu/nova-core/firmware/fwsec.rs | 2 +- drivers/gpu/nova-core/firmware/fwsec/bootloader.rs | 4 +- drivers/gpu/nova-core/firmware/gsp.rs | 9 +- drivers/gpu/nova-core/firmware/tlv.rs | 11 +- drivers/gpu/nova-core/fsp.rs | 8 +- drivers/gpu/nova-core/gsp.rs | 4 +-Quoted 8 lines
drivers/gpu/nova-core/gsp/cmdq.rs | 22 +-- drivers/gpu/nova-core/gsp/fw.rs | 42 ++-- drivers/gpu/nova-core/gsp/fw/commands.rs | 4 +- drivers/gpu/nova-core/gsp/sequencer.rs | 2 +- drivers/gpu/nova-core/mctp.rs | 8 +- drivers/gpu/nova-core/num.rs | 211 --------------------- drivers/gpu/nova-core/vbios.rs | 2 +- 19 files changed, 78 insertions(+), 283 deletions(-)Please see the discussion in [1].
If we make this change, then the subsequent conversion to const_as!() would need to go through the Rust tree next cycle, which could be a bit of a mess, as I'd expect a bunch of conflicts.
Quoted 8 lines
Alternatively, we could the the full three cycle dance, or have a signed tag for const_as!() and use it right away.
But honestly, the former would just be unnecessary noise. If we don't do the latter, let's just keep the nova-core num module until the dust has been settled.
[1] https://lore.kernel.org/all/CANiq72k+-fNWZCwGuQ=FTchxgm-X-f6WR=tG=Ercn19ic1edQg@mail.gmail.com/
Maybe I am missing something, but wouldn't the following work?
- rc1 gets tagged,
drm-rust-nextgets thenum::castsmodule,
- This series gets applied todrm-rust-next, thencv!(without the nova-core conversion patch) inrust-next,
- We wait one cycle forcv!to trickle down todrm-rust-nextbefore converting nova-core to usecv!.Quoted 3 lines
Would that work? This series doesn't overlap with the const conversions that
cv!covers on purpose, and it would have the benefit of getting rid of the localnummodule in nova-core quickly.Take
casts::usize_into_u32()for instance, drm-rust-next replaces the usage of it next cycle, but rust-next wants to remove the API fromrust/kernel/num/casts.rs.
Quoted 8 lines
In this case rust-next would need to get rid of the users (including nova-core), but drm-rust-next will likely do different changes, so we'd get unnecessary merge conflicts.
You can resolve this either by keeping
casts::usize_into_u32and friends around for one additional cycle, so that all users we introduce now are gone. Or, since there's no rush anyways, we just wait one cycle and use the real thing right away.
Sorry, I should have explicitly mentioned that *_into_* would remain alongside cv! for the next cycle.
The reason why I think it's preferable to use casts in nova-core sooner is that some of the series currently under review (and that will likely be merged next cycle) add more uses of the local num methods, making the eentual conversion more painful. If we move to use casts early we can at least avoid the churn on those cases that do not use cv!.
Danilo Krummrich
maintainerRe: [PATCH 1/2] gpu: nova-core: use kernel lossless integer conversion module
Quoted 69 lines · Alexandre Courbot
Quoted 68 lines · Danilo Krummrich
Quoted 55 lines · Alexandre Courbot
Quoted 37 lines · Danilo Krummrich
(Cc: Miguel)
Quoted 19 lines · Alexandre Courbot
The
kernelcrate now features a replacement for our lossless integer conversion routines. Switch to the kernel version and remove our own.Signed-off-by Alexandre Courbot <[email protected]>Reviewed-by Danilo Krummrich <[email protected]>Reviewed-by Eliot Courtney <[email protected]>--- drivers/gpu/nova-core/falcon.rs | 12 +- drivers/gpu/nova-core/falcon/fsp.rs | 4 +- drivers/gpu/nova-core/fb.rs | 2 +- drivers/gpu/nova-core/fb/hal/gb100.rs | 6 +- drivers/gpu/nova-core/firmware.rs | 4 +- drivers/gpu/nova-core/firmware/booter.rs | 4 +- drivers/gpu/nova-core/firmware/fwsec.rs | 2 +- drivers/gpu/nova-core/firmware/fwsec/bootloader.rs | 4 +- drivers/gpu/nova-core/firmware/gsp.rs | 9 +- drivers/gpu/nova-core/firmware/tlv.rs | 11 +- drivers/gpu/nova-core/fsp.rs | 8 +- drivers/gpu/nova-core/gsp.rs | 4 +-Quoted 8 lines
drivers/gpu/nova-core/gsp/cmdq.rs | 22 +-- drivers/gpu/nova-core/gsp/fw.rs | 42 ++-- drivers/gpu/nova-core/gsp/fw/commands.rs | 4 +- drivers/gpu/nova-core/gsp/sequencer.rs | 2 +- drivers/gpu/nova-core/mctp.rs | 8 +- drivers/gpu/nova-core/num.rs | 211 --------------------- drivers/gpu/nova-core/vbios.rs | 2 +- 19 files changed, 78 insertions(+), 283 deletions(-)Please see the discussion in [1].
If we make this change, then the subsequent conversion to const_as!() would need to go through the Rust tree next cycle, which could be a bit of a mess, as I'd expect a bunch of conflicts.
Quoted 8 lines
Alternatively, we could the the full three cycle dance, or have a signed tag for const_as!() and use it right away.
But honestly, the former would just be unnecessary noise. If we don't do the latter, let's just keep the nova-core num module until the dust has been settled.
[1] https://lore.kernel.org/all/CANiq72k+-fNWZCwGuQ=FTchxgm-X-f6WR=tG=Ercn19ic1edQg@mail.gmail.com/
Maybe I am missing something, but wouldn't the following work?
- rc1 gets tagged,
drm-rust-nextgets thenum::castsmodule,
- This series gets applied todrm-rust-next, thencv!(without the nova-core conversion patch) inrust-next,
- We wait one cycle forcv!to trickle down todrm-rust-nextbefore converting nova-core to usecv!.Quoted 3 lines
Would that work? This series doesn't overlap with the const conversions that
cv!covers on purpose, and it would have the benefit of getting rid of the localnummodule in nova-core quickly.Take
casts::usize_into_u32()for instance, drm-rust-next replaces the usage of it next cycle, but rust-next wants to remove the API fromrust/kernel/num/casts.rs.In this case rust-next would need to get rid of the users (including nova-core), but drm-rust-next will likely do different changes, so we'd get unnecessary merge conflicts.
Quoted 7 lines
Quoted 4 lines
You can resolve this either by keeping
casts::usize_into_u32and friends around for one additional cycle, so that all users we introduce now are gone. Or, since there's no rush anyways, we just wait one cycle and use the real thing right away.Sorry, I should have explicitly mentioned that
*_into_*would remain alongsidecv!for the next cycle.
Maybe we have a different understanding of what "next cycle" means. As of today we are in the v7.4 cycle, so I call this the current cycle.
In the next cycle, as discussed in [1], rust-next will drop casts::*_into_*(), and so would drm-rust-next, if we start using casts::*_into_*() in nova-core this cycle.
I don't want this situation, so we can either keep casts::*_into_*() around for even longer, or just never start using it.
Quoted 6 lines
The reason why I think it's preferable to use
castsin nova-core sooner is that some of the series currently under review (and that will likely be merged next cycle) add more uses of the localnummethods, making the eentual conversion more painful. If we move to usecastsearly we can at least avoid the churn on those cases that do not usecv!.
It would come at the price of adding cross tree dependencies and converting the cv! parts twice, which is much worse than one clean and independent conversion.
Alexandre Courbot
maintainerRe: [PATCH 1/2] gpu: nova-core: use kernel lossless integer conversion module
Quoted 95 lines · Danilo Krummrich
Quoted 69 lines · Alexandre Courbot
Quoted 68 lines · Danilo Krummrich
Quoted 55 lines · Alexandre Courbot
Quoted 37 lines · Danilo Krummrich
(Cc: Miguel)
Quoted 19 lines · Alexandre Courbot
The
kernelcrate now features a replacement for our lossless integer conversion routines. Switch to the kernel version and remove our own.Signed-off-by Alexandre Courbot <[email protected]>Reviewed-by Danilo Krummrich <[email protected]>Reviewed-by Eliot Courtney <[email protected]>--- drivers/gpu/nova-core/falcon.rs | 12 +- drivers/gpu/nova-core/falcon/fsp.rs | 4 +- drivers/gpu/nova-core/fb.rs | 2 +- drivers/gpu/nova-core/fb/hal/gb100.rs | 6 +- drivers/gpu/nova-core/firmware.rs | 4 +- drivers/gpu/nova-core/firmware/booter.rs | 4 +- drivers/gpu/nova-core/firmware/fwsec.rs | 2 +- drivers/gpu/nova-core/firmware/fwsec/bootloader.rs | 4 +- drivers/gpu/nova-core/firmware/gsp.rs | 9 +- drivers/gpu/nova-core/firmware/tlv.rs | 11 +- drivers/gpu/nova-core/fsp.rs | 8 +- drivers/gpu/nova-core/gsp.rs | 4 +-Quoted 8 lines
drivers/gpu/nova-core/gsp/cmdq.rs | 22 +-- drivers/gpu/nova-core/gsp/fw.rs | 42 ++-- drivers/gpu/nova-core/gsp/fw/commands.rs | 4 +- drivers/gpu/nova-core/gsp/sequencer.rs | 2 +- drivers/gpu/nova-core/mctp.rs | 8 +- drivers/gpu/nova-core/num.rs | 211 --------------------- drivers/gpu/nova-core/vbios.rs | 2 +- 19 files changed, 78 insertions(+), 283 deletions(-)Please see the discussion in [1].
If we make this change, then the subsequent conversion to const_as!() would need to go through the Rust tree next cycle, which could be a bit of a mess, as I'd expect a bunch of conflicts.
Quoted 8 lines
Alternatively, we could the the full three cycle dance, or have a signed tag for const_as!() and use it right away.
But honestly, the former would just be unnecessary noise. If we don't do the latter, let's just keep the nova-core num module until the dust has been settled.
[1] https://lore.kernel.org/all/CANiq72k+-fNWZCwGuQ=FTchxgm-X-f6WR=tG=Ercn19ic1edQg@mail.gmail.com/
Maybe I am missing something, but wouldn't the following work?
- rc1 gets tagged,
drm-rust-nextgets thenum::castsmodule,
- This series gets applied todrm-rust-next, thencv!(without the nova-core conversion patch) inrust-next,
- We wait one cycle forcv!to trickle down todrm-rust-nextbefore converting nova-core to usecv!.Quoted 3 lines
Would that work? This series doesn't overlap with the const conversions that
cv!covers on purpose, and it would have the benefit of getting rid of the localnummodule in nova-core quickly.Take
casts::usize_into_u32()for instance, drm-rust-next replaces the usage of it next cycle, but rust-next wants to remove the API fromrust/kernel/num/casts.rs.In this case rust-next would need to get rid of the users (including nova-core), but drm-rust-next will likely do different changes, so we'd get unnecessary merge conflicts.
Quoted 7 lines
Quoted 4 lines
You can resolve this either by keeping
casts::usize_into_u32and friends around for one additional cycle, so that all users we introduce now are gone. Or, since there's no rush anyways, we just wait one cycle and use the real thing right away.Sorry, I should have explicitly mentioned that
*_into_*would remain alongsidecv!for the next cycle.Maybe we have a different understanding of what "next cycle" means. As of today we are in the v7.4 cycle, so I call this the current cycle.
In the next cycle, as discussed in [1], rust-next will drop casts::*_into_*(), and so would drm-rust-next, if we start using casts::*_into_*() in nova-core this cycle.
I don't want this situation, so we can either keep casts::*_into_*() around for even longer, or just never start using it.
Quoted 6 lines
The reason why I think it's preferable to use
castsin nova-core sooner is that some of the series currently under review (and that will likely be merged next cycle) add more uses of the localnummethods, making the eentual conversion more painful. If we move to usecastsearly we can at least avoid the churn on those cases that do not usecv!.
Quoted 2 lines
It would come at the price of adding cross tree dependencies and converting the cv! parts twice, which is much worse than one clean and independent conversion.
Got it - let's keep nova-core's num for one more cycle then. This will make for a larger conversion, but the silver lining is that this means less rebasing for the patches currently in-flight.
I'll revisit this series for 7.5 (?), although I guess patch 2 is still relevant as long as it keeps using nova-core's num crate.
Alexandre Courbot
maintainerPATCH 2/2 gpu: nova-core: use FromSafeCast wherever possible
In reply to Alexandre CourbotFromSafeCast should be preferred to the *_as_* family of functions when it can be used (i.e. in non-const contexts), as it requires a single import to perform all valid conversions.
After this patch, the only remaining references to the casts module are those done in const context, which means the casts import can be removed once these are converted to use the cv! macro.
--- drivers/gpu/nova-core/falcon/fsp.rs | 4 ++-- drivers/gpu/nova-core/firmware/tlv.rs | 4 ++-- drivers/gpu/nova-core/gsp.rs | 4 ++-- drivers/gpu/nova-core/gsp/cmdq.rs | 19 +++++++++++-------- drivers/gpu/nova-core/gsp/fw.rs | 8 ++++---- 5 files changed, 21 insertions(+), 18 deletions(-)
drivers/gpu/nova-core/falcon/fsp.rs +2 -2
@@ -16,7 +16,7 @@ }, Io, // }, - num::casts, + num::casts::FromSafeCast, prelude::*, sizes::SZ_1K, time::Delta,
@@ -165,7 +165,7 @@ pub(crate) fn recv_msg(&mut self) -> Result<KVec<u8>> { Delta::from_millis(10), Delta::from_millis(FSP_MSG_TIMEOUT_MS), ) - .map (casts::u32_as_usize)?; + .map (usize::from_safe_cast)?;// Don't blindly allocate more than the maximum we expect from FSP. if msg_size >FSP_EMEM_CHANNEL_0_SIZE {
drivers/gpu/nova-core/firmware/tlv.rs +2 -2
@@ -5,7 +5,7 @@ device, firmware, num::casts::{ - self, + FromSafeCast, IntoSafeCast, // }, prelude::*,
@@ -52,7 +52,7 @@ fn parse(hdr: &[u8]) -> Option<Self> {return None ; }let len_arr = <[u8 ;4 ]>::try_from (hdr.get (4 ..Self ::SIZE )?).ok ()?; -let length = casts::u32_as_usize (u32::from_le_bytes (len_arr)); +let length = usize::from_safe_cast (u32::from_le_bytes (len_arr));Some (Self { tag, length }) } }
drivers/gpu/nova-core/gsp.rs +2 -2
@@ -17,7 +17,7 @@ io_write, Io, // }, - num::casts, + num::casts::FromSafeCast, pci, prelude::*, // };
@@ -92,7 +92,7 @@ fn init(view: CoherentView<'_, Self>, start: DmaAddress) -> Result<()> {for iin 0 ..NUM_PAGES {io_write! (view, .0 [build: i], start - .checked_add (casts::usize_as_u64 (i) <<GSP_PAGE_SHIFT ) + .checked_add (u64 ::from_safe_cast (i) <<GSP_PAGE_SHIFT ) .ok_or (EOVERFLOW )? ); }
drivers/gpu/nova-core/gsp/cmdq.rs +11 -8
@@ -23,7 +23,10 @@ Io, // }, new_mutex, - num::casts, + num::casts::{ + self, + FromSafeCast, // + }, prelude::*, ptr, sync::{
@@ -289,10 +292,10 @@ fn new(dev: &device::Device<device::Bound>) -> Result<Self> {unsafe { ( core::slice::from_raw_parts_mut ( - data.add (casts::u32_as_usize (tx)), - casts::u32_as_usize (tail_end - tx), + data.add (usize::from_safe_cast (tx)), + usize::from_safe_cast (tail_end - tx), ), - core::slice::from_raw_parts_mut (data, casts::u32_as_usize (wrap_end)), + core::slice::from_raw_parts_mut (data, usize::from_safe_cast (wrap_end)), ) } }
@@ -307,7 +310,7 @@ fn driver_write_area_size(&self) -> usize {// `cpu_write_ptr`. The minimum value case is where `rx == 0` and `tx == MSGQ_NUM_PAGES - // 1`, which gives `0 + MSGQ_NUM_PAGES - (MSGQ_NUM_PAGES - 1) - 1 == 0`. let slots = (rx +MSGQ_NUM_PAGES - tx -1 ) %MSGQ_NUM_PAGES ; - casts::u32_as_usize (slots) *GSP_PAGE_SIZE + usize::from_safe_cast (slots) *GSP_PAGE_SIZE }/// Returns the region of the GSP message queue that the driver is currently allowed to read
@@ -343,10 +346,10 @@ fn driver_write_area_size(&self) -> usize {unsafe { ( core::slice::from_raw_parts ( - data.add (casts::u32_as_usize (rx)), - casts::u32_as_usize (tail_end - rx), + data.add (usize::from_safe_cast (rx)), + usize::from_safe_cast (tail_end - rx), ), - core::slice::from_raw_parts (data, casts::u32_as_usize (wrap_end)), + core::slice::from_raw_parts (data, usize::from_safe_cast (wrap_end)), ) } }
drivers/gpu/nova-core/gsp/fw.rs +4 -4
@@ -681,7 +681,7 @@ fn id8(name: &str) -> u64 { let init_inner = init!(bindings::LibosMemoryRegionInitArgument { id8: id8(name), pa: obj.dma_address(), - size: casts::usize_as_u64(obj.size()), + size: u64::from_safe_cast(obj.size()), kind: casts::u32_into_u8::< { bindings::LibosMemoryRegionKind_LIBOS_MEMORY_REGION_CONTIGUOUS }, >(),
@@ -851,7 +851,7 @@ pub(crate) fn set_checksum(&mut self, checksum: u32) {/// Returns the length of the message's payload. pub (crate )fn payload_length (&self) ->usize {// `rpc.length` includes the length of the RPC message header. - casts::u32_as_usize (self.inner.rpc.length) + usize::from_safe_cast (self.inner.rpc.length) .saturating_sub (size_of ::<bindings::rpc_message_header_v >()) }
@@ -948,8 +948,8 @@ fn new(cmdq: &Cmdq) -> impl Init<Self> + '_ {init! (MessageQueueInitArguments { sharedMemPhysAddr: cmdq.dma_addr, pageTableEntryCount: casts::usize_into_u32 ::<{Cmdq ::NUM_PTES }>(), - cmdQueueOffset: casts::usize_as_u64 (Cmdq ::CMDQ_OFFSET ), - statQueueOffset: casts::usize_as_u64 (Cmdq ::STATQ_OFFSET ), + cmdQueueOffset:u64 ::from_safe_cast (Cmdq ::CMDQ_OFFSET ), + statQueueOffset:u64 ::from_safe_cast (Cmdq ::STATQ_OFFSET ), ..Zeroable ::init_zeroed () }) }
Signature · 1 line
2.55.0
Re: [PATCH 2/2] gpu: nova-core: use FromSafeCast wherever possible
Quoted 10 lines · Alexandre Courbot
FromSafeCastshould be preferred to the*_as_*family of functions when it can be used (i.e. in non-const contexts), as it requires a single import to perform all valid conversions.After this patch, the only remaining references to the
castsmodule are those done in const context, which means thecastsimport can be removed once these are converted to use thecv!macro.Signed-off-by Alexandre Courbot <[email protected]>---
[email protected]
AI reviewRe: [PATCH 2/2] gpu: nova-core: use FromSafeCast wherever possible
In reply to Alexandre CourbotThank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
Pre-existing issues:
- [High] Missing DMA write memory barrier before updating the GSP command queue write pointer.
- [High] Missing DMA read memory barrier after reading the GSP message queue write pointer. --
commit 899e3ba6af7f4cc7e2c28b0f4f3f73db18de1f16
Author: Alexandre Courbot <[email protected]>
gpu: nova-core: use FromSafeCast wherever possible
Replaces various *_as_* casting functions with FromSafeCast in non-const contexts to simplify conversions.
Quoted 4 lines
drivers/gpu/nova-core/gsp/cmdq.rs +0
-0
[ ... ]
Quoted 4 lines
drivers/gpu/nova-core/gsp/cmdq.rs +0
-0@@ -343,10 +346,10 @@ fn driver_write_area_size(&self) -> usize { unsafe { ( core::slice::from_raw_parts(
drivers/gpu/nova-core/gsp/cmdq.rs fn driver_write_area_size(&self) -> usize { · line 355
Quoted 10 lines
drivers/gpu/nova-core/gsp/cmdq.rs +3
-3- data.add(casts::u32_as_usize(rx)), - casts::u32_as_usize(tail_end - rx), + data.add(usize::from_safe_cast(rx)), + usize::from_safe_cast(tail_end - rx), ), - core::slice::from_raw_parts(data, casts::u32_as_usize(wrap_end)), + core::slice::from_raw_parts(data, usize::from_safe_cast(wrap_end)), ) } }
[Severity: High]
This isn't a bug introduced by this patch, but while reviewing this file I noticed a potential memory barrier issue in advance_cpu_write_ptr():
Quoted 8 lines
fn advance_cpu_write_ptr(&mut self, elem_count: u32) {
let tx = io_project!(self.0, .cpuq.tx);
let wptr = MsgqTxHeader::write_ptr(tx).wrapping_add(elem_count) % MSGQ_NUM_PAGES;
MsgqTxHeader::set_write_ptr(tx, wptr);
// Ensure all command data is visible before triggering the GSP read.
fence(Ordering::SeqCst);
}Because there is no memory barrier between the payload writes (done prior to calling this function) and the write pointer volatile write in MsgqTxHeader::set_write_ptr(), the CPU can reorder them.
If the GSP observes the updated write pointer before the payload writes are globally visible, could it read stale command data?
[Severity: High]
This is also a pre-existing issue, but is there a missing read memory barrier after reading the message queue write pointer in wait_for_msg()?
Quoted 4 lines
fn wait_for_msg(&self, timeout: Delta) -> Result<GspMessage<'_>> {
// Wait for a message to arrive from the GSP.
let (slice_1, slice_2) = read_poll_timeout(
|| Ok(self.gsp_mem.driver_read_area()),Quoted 8 lines
|driver_area| !driver_area.0.is_empty(),
Delta::from_millis(1),
timeout,
)
.map(|(slice_1, slice_2)| (slice_1.as_flattened(), slice_2.as_flattened()))?;
// Extract the `GspMsgElement`.
let (header, slice_1) = GspMsgElement::from_bytes_prefix(slice_1).ok_or(EIO)?;When polling for a new message, read_poll_timeout repeatedly evaluates driver_read_area(), which performs a volatile read of the GSP write pointer.
Once a new message is indicated, the payload memory slices are immediately accessed.
Since there is no read memory barrier between the volatile read of the write pointer and the payload access, could modern CPUs speculatively execute the data loads before the write pointer read completes, causing the driver to read stale payload data?
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=2