Dave Airlie
2024-Aug-15 20:19 UTC
[PATCH] nouveau/firmware: using dma non-coherent interfaces for fw loading. (v2)
From: Dave Airlie <airlied at redhat.com>
Currently, enabling SG_DEBUG in the kernel will cause nouveau to hit a
BUG() on startup, when the iommu is enabled:
kernel BUG at include/linux/scatterlist.h:187!
invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 7 PID: 930 Comm: (udev-worker) Not tainted 6.9.0-rc3Lyude-Test+ #30
Hardware name: MSI MS-7A39/A320M GAMING PRO (MS-7A39), BIOS 1.I0 01/22/2019
RIP: 0010:sg_init_one+0x85/0xa0
Code: 69 88 32 01 83 e1 03 f6 c3 03 75 20 a8 01 75 1e 48 09 cb 41 89 54
24 08 49 89 1c 24 41 89 6c 24 0c 5b 5d 41 5c e9 7b b9 88 00 <0f> 0b 0f 0b
0f 0b 48 8b 05 5e 46 9a 01 eb b2 66 66 2e 0f 1f 84 00
RSP: 0018:ffffa776017bf6a0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffffa77600d87000 RCX: 000000000000002b
RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffffa77680d87000
RBP: 000000000000e000 R08: 0000000000000000 R09: 0000000000000000
R10: ffff98f4c46aa508 R11: 0000000000000000 R12: ffff98f4c46aa508
R13: ffff98f4c46aa008 R14: ffffa77600d4a000 R15: ffffa77600d4a018
FS: 00007feeb5aae980(0000) GS:ffff98f5c4dc0000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f22cb9a4520 CR3: 00000001043ba000 CR4: 00000000003506f0
Call Trace:
<TASK>
? die+0x36/0x90
? do_trap+0xdd/0x100
? sg_init_one+0x85/0xa0
? do_error_trap+0x65/0x80
? sg_init_one+0x85/0xa0
? exc_invalid_op+0x50/0x70
? sg_init_one+0x85/0xa0
? asm_exc_invalid_op+0x1a/0x20
? sg_init_one+0x85/0xa0
nvkm_firmware_ctor+0x14a/0x250 [nouveau]
nvkm_falcon_fw_ctor+0x42/0x70 [nouveau]
ga102_gsp_booter_ctor+0xb4/0x1a0 [nouveau]
r535_gsp_oneinit+0xb3/0x15f0 [nouveau]
? srso_return_thunk+0x5/0x5f
? srso_return_thunk+0x5/0x5f
? nvkm_udevice_new+0x95/0x140 [nouveau]
? srso_return_thunk+0x5/0x5f
? srso_return_thunk+0x5/0x5f
? ktime_get+0x47/0xb0
Fix this by using the non-coherent allocator instead, I think there
might be a better answer to this, but it involve ripping up some of
APIs using sg lists.
v2: fix build warning
Signed-off-by: Dave Airlie <airlied at redhat.com>
Cc: stable at vger.kernel.org
---
drivers/gpu/drm/nouveau/nvkm/core/firmware.c | 9 ++++++---
drivers/gpu/drm/nouveau/nvkm/falcon/fw.c | 6 ++++++
2 files changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
index adc60b25f8e6..0af01a0ec601 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
@@ -205,7 +205,8 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw)
break;
case NVKM_FIRMWARE_IMG_DMA:
nvkm_memory_unref(&memory);
- dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl),
fw->img, fw->phys);
+ dma_free_noncoherent(fw->device->dev, sg_dma_len(&fw->mem.sgl),
+ fw->img, fw->phys, DMA_TO_DEVICE);
break;
case NVKM_FIRMWARE_IMG_SGT:
nvkm_memory_unref(&memory);
@@ -236,10 +237,12 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func,
const char *name,
break;
case NVKM_FIRMWARE_IMG_DMA: {
dma_addr_t addr;
-
len = ALIGN(fw->len, PAGE_SIZE);
- fw->img = dma_alloc_coherent(fw->device->dev, len, &addr,
GFP_KERNEL);
+ fw->img = dma_alloc_noncoherent(fw->device->dev,
+ len, &addr,
+ DMA_TO_DEVICE,
+ GFP_KERNEL);
if (fw->img) {
memcpy(fw->img, src, fw->len);
fw->phys = addr;
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
index 80a480b12174..a1c8545f1249 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
@@ -89,6 +89,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct
nvkm_subdev *user,
nvkm_falcon_fw_dtor_sigs(fw);
}
+ /* after last write to the img, sync dma mappings */
+ dma_sync_single_for_device(fw->fw.device->dev,
+ fw->fw.phys,
+ sg_dma_len(&fw->fw.mem.sgl),
+ DMA_TO_DEVICE);
+
FLCNFW_DBG(fw, "resetting");
fw->func->reset(fw);
--
2.46.0
Timur Tabi
2024-Aug-15 20:45 UTC
[PATCH] nouveau/firmware: using dma non-coherent interfaces for fw loading. (v2)
On Fri, 2024-08-16 at 06:19 +1000, Dave Airlie wrote:> Fix this by using the non-coherent allocator instead, I think there > might be a better answer to this, but it involve ripping up some of > APIs using sg lists.Thanks for fixing this, but what is the relationshio between non-coherent DMA and sg_set_buf()? ? You're still calling?sg_init_one() and hitting this check: #ifdef CONFIG_DEBUG_SG BUG_ON(!virt_addr_valid(buf)); #endif Does a non-coherent DMA buffer have a different kind of virtual address than a coherent DMA buffer?
Danilo Krummrich
2024-Aug-16 00:53 UTC
[PATCH] nouveau/firmware: using dma non-coherent interfaces for fw loading. (v2)
On Fri, Aug 16, 2024 at 06:19:23AM +1000, Dave Airlie wrote:> From: Dave Airlie <airlied at redhat.com> > > Currently, enabling SG_DEBUG in the kernel will cause nouveau to hit a > BUG() on startup, when the iommu is enabled: > > kernel BUG at include/linux/scatterlist.h:187! > invalid opcode: 0000 [#1] PREEMPT SMP NOPTI > CPU: 7 PID: 930 Comm: (udev-worker) Not tainted 6.9.0-rc3Lyude-Test+ #30 > Hardware name: MSI MS-7A39/A320M GAMING PRO (MS-7A39), BIOS 1.I0 01/22/2019 > RIP: 0010:sg_init_one+0x85/0xa0 > Code: 69 88 32 01 83 e1 03 f6 c3 03 75 20 a8 01 75 1e 48 09 cb 41 89 54 > 24 08 49 89 1c 24 41 89 6c 24 0c 5b 5d 41 5c e9 7b b9 88 00 <0f> 0b 0f 0b > 0f 0b 48 8b 05 5e 46 9a 01 eb b2 66 66 2e 0f 1f 84 00 > RSP: 0018:ffffa776017bf6a0 EFLAGS: 00010246 > RAX: 0000000000000000 RBX: ffffa77600d87000 RCX: 000000000000002b > RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffffa77680d87000 > RBP: 000000000000e000 R08: 0000000000000000 R09: 0000000000000000 > R10: ffff98f4c46aa508 R11: 0000000000000000 R12: ffff98f4c46aa508 > R13: ffff98f4c46aa008 R14: ffffa77600d4a000 R15: ffffa77600d4a018 > FS: 00007feeb5aae980(0000) GS:ffff98f5c4dc0000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > CR2: 00007f22cb9a4520 CR3: 00000001043ba000 CR4: 00000000003506f0 > Call Trace: > <TASK> > ? die+0x36/0x90 > ? do_trap+0xdd/0x100 > ? sg_init_one+0x85/0xa0 > ? do_error_trap+0x65/0x80 > ? sg_init_one+0x85/0xa0 > ? exc_invalid_op+0x50/0x70 > ? sg_init_one+0x85/0xa0 > ? asm_exc_invalid_op+0x1a/0x20 > ? sg_init_one+0x85/0xa0 > nvkm_firmware_ctor+0x14a/0x250 [nouveau] > nvkm_falcon_fw_ctor+0x42/0x70 [nouveau] > ga102_gsp_booter_ctor+0xb4/0x1a0 [nouveau] > r535_gsp_oneinit+0xb3/0x15f0 [nouveau] > ? srso_return_thunk+0x5/0x5f > ? srso_return_thunk+0x5/0x5f > ? nvkm_udevice_new+0x95/0x140 [nouveau] > ? srso_return_thunk+0x5/0x5f > ? srso_return_thunk+0x5/0x5f > ? ktime_get+0x47/0xb0 > > Fix this by using the non-coherent allocator instead, I think there > might be a better answer to this, but it involve ripping up some of > APIs using sg lists. > > v2: fix build warning > > Signed-off-by: Dave Airlie <airlied at redhat.com> > Cc: stable at vger.kernel.orgDoes this need the following fixes tag? Fixes: 2541626cfb79 ("drm/nouveau/acr: use common falcon HS FW code for ACR FWs")> --- > drivers/gpu/drm/nouveau/nvkm/core/firmware.c | 9 ++++++--- > drivers/gpu/drm/nouveau/nvkm/falcon/fw.c | 6 ++++++ > 2 files changed, 12 insertions(+), 3 deletions(-) > > diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c > index adc60b25f8e6..0af01a0ec601 100644 > --- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c > +++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c > @@ -205,7 +205,8 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw) > break; > case NVKM_FIRMWARE_IMG_DMA: > nvkm_memory_unref(&memory); > - dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys); > + dma_free_noncoherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), > + fw->img, fw->phys, DMA_TO_DEVICE); > break; > case NVKM_FIRMWARE_IMG_SGT: > nvkm_memory_unref(&memory); > @@ -236,10 +237,12 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name, > break; > case NVKM_FIRMWARE_IMG_DMA: { > dma_addr_t addr; > - > len = ALIGN(fw->len, PAGE_SIZE); > > - fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL); > + fw->img = dma_alloc_noncoherent(fw->device->dev, > + len, &addr, > + DMA_TO_DEVICE, > + GFP_KERNEL); > if (fw->img) { > memcpy(fw->img, src, fw->len); > fw->phys = addr; > diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c > index 80a480b12174..a1c8545f1249 100644 > --- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c > +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c > @@ -89,6 +89,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user, > nvkm_falcon_fw_dtor_sigs(fw); > } > > + /* after last write to the img, sync dma mappings */ > + dma_sync_single_for_device(fw->fw.device->dev, > + fw->fw.phys, > + sg_dma_len(&fw->fw.mem.sgl), > + DMA_TO_DEVICE); > + > FLCNFW_DBG(fw, "resetting"); > fw->func->reset(fw); > > -- > 2.46.0 >
Apparently Analagous Threads
- [PATCH] nouveau/firmware: using dma non-coherent interfaces for fw loading. (v2)
- [PATCH 1/2] drm/nouveau/firmware: Fix SG_DEBUG error with nvkm_firmware_ctor()
- [PATCH] nouveau: fw: sync dma after setup is called.
- [PATCH 1/2] drm/nouveau/firmware: Fix SG_DEBUG error with nvkm_firmware_ctor()
- [PATCH 1/2] drm/nouveau/firmware: Fix SG_DEBUG error with nvkm_firmware_ctor()