diff mbox series

nouveau/firmware: using dma non-coherent interfaces for fw loading.

Message ID 20240513064350.1050994-1-airlied@gmail.com (mailing list archive)
State New, archived
Headers show
Series nouveau/firmware: using dma non-coherent interfaces for fw loading. | expand

Commit Message

Dave Airlie May 13, 2024, 6:43 a.m. UTC
From: Dave Airlie <airlied@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.

Signed-off-by: Dave Airlie <airlied@redhat.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/nouveau/nvkm/core/firmware.c | 11 ++++++-----
 drivers/gpu/drm/nouveau/nvkm/falcon/fw.c     |  6 ++++++
 2 files changed, 12 insertions(+), 5 deletions(-)

Comments

kernel test robot May 13, 2024, 9:23 a.m. UTC | #1
Hi Dave,

kernel test robot noticed the following build errors:

[auto build test ERROR on drm-misc/drm-misc-next]
[also build test ERROR on linus/master v6.9 next-20240513]
[cannot apply to drm-tip/drm-tip]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Dave-Airlie/nouveau-firmware-using-dma-non-coherent-interfaces-for-fw-loading/20240513-144435
base:   git://anongit.freedesktop.org/drm/drm-misc drm-misc-next
patch link:    https://lore.kernel.org/r/20240513064350.1050994-1-airlied%40gmail.com
patch subject: [PATCH] nouveau/firmware: using dma non-coherent interfaces for fw loading.
config: parisc-defconfig (https://download.01.org/0day-ci/archive/20240513/202405131724.YtoCSRmy-lkp@intel.com/config)
compiler: hppa-linux-gcc (GCC) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240513/202405131724.YtoCSRmy-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202405131724.YtoCSRmy-lkp@intel.com/

All errors (new ones prefixed by >>):

   drivers/gpu/drm/nouveau/nvkm/core/firmware.c: In function 'nvkm_firmware_ctor':
>> drivers/gpu/drm/nouveau/nvkm/core/firmware.c:242:54: error: passing argument 3 of 'dma_alloc_noncoherent' from incompatible pointer type [-Werror=incompatible-pointer-types]
     242 |                                                 len, &fw->phys,
         |                                                      ^~~~~~~~~
         |                                                      |
         |                                                      u64 * {aka long long unsigned int *}
   In file included from include/linux/pci.h:2693,
                    from drivers/gpu/drm/nouveau/include/nvif/os.h:8,
                    from drivers/gpu/drm/nouveau/include/nvkm/core/os.h:4,
                    from drivers/gpu/drm/nouveau/include/nvkm/core/oclass.h:3,
                    from drivers/gpu/drm/nouveau/include/nvkm/core/device.h:4,
                    from drivers/gpu/drm/nouveau/nvkm/core/firmware.c:22:
   include/linux/dma-mapping.h:321:29: note: expected 'dma_addr_t *' {aka 'unsigned int *'} but argument is of type 'u64 *' {aka 'long long unsigned int *'}
     321 |                 dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
         |                 ~~~~~~~~~~~~^~~~~~~~~~
   cc1: some warnings being treated as errors


vim +/dma_alloc_noncoherent +242 drivers/gpu/drm/nouveau/nvkm/core/firmware.c

   224	
   225	int
   226	nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name,
   227			   struct nvkm_device *device, const void *src, int len, struct nvkm_firmware *fw)
   228	{
   229		fw->func = func;
   230		fw->name = name;
   231		fw->device = device;
   232		fw->len = len;
   233	
   234		switch (fw->func->type) {
   235		case NVKM_FIRMWARE_IMG_RAM:
   236			fw->img = kmemdup(src, fw->len, GFP_KERNEL);
   237			break;
   238		case NVKM_FIRMWARE_IMG_DMA: {
   239			len = ALIGN(fw->len, PAGE_SIZE);
   240	
   241			fw->img = dma_alloc_noncoherent(fw->device->dev,
 > 242							len, &fw->phys,
kernel test robot May 13, 2024, 3:16 p.m. UTC | #2
Hi Dave,

kernel test robot noticed the following build errors:

[auto build test ERROR on drm-misc/drm-misc-next]
[also build test ERROR on drm-tip/drm-tip linus/master v6.9 next-20240513]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Dave-Airlie/nouveau-firmware-using-dma-non-coherent-interfaces-for-fw-loading/20240513-144435
base:   git://anongit.freedesktop.org/drm/drm-misc drm-misc-next
patch link:    https://lore.kernel.org/r/20240513064350.1050994-1-airlied%40gmail.com
patch subject: [PATCH] nouveau/firmware: using dma non-coherent interfaces for fw loading.
config: arm-defconfig (https://download.01.org/0day-ci/archive/20240513/202405132205.FVKltMCq-lkp@intel.com/config)
compiler: clang version 14.0.6 (https://github.com/llvm/llvm-project f28c006a5895fc0e329fe15fead81e37457cb1d1)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240513/202405132205.FVKltMCq-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202405132205.FVKltMCq-lkp@intel.com/

All errors (new ones prefixed by >>):

>> drivers/gpu/drm/nouveau/nvkm/core/firmware.c:242:12: error: incompatible pointer types passing 'u64 *' (aka 'unsigned long long *') to parameter of type 'dma_addr_t *' (aka 'unsigned int *') [-Werror,-Wincompatible-pointer-types]
                                                   len, &fw->phys,
                                                        ^~~~~~~~~
   include/linux/dma-mapping.h:321:15: note: passing argument to parameter 'dma_handle' here
                   dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
                               ^
   1 error generated.


vim +242 drivers/gpu/drm/nouveau/nvkm/core/firmware.c

   224	
   225	int
   226	nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name,
   227			   struct nvkm_device *device, const void *src, int len, struct nvkm_firmware *fw)
   228	{
   229		fw->func = func;
   230		fw->name = name;
   231		fw->device = device;
   232		fw->len = len;
   233	
   234		switch (fw->func->type) {
   235		case NVKM_FIRMWARE_IMG_RAM:
   236			fw->img = kmemdup(src, fw->len, GFP_KERNEL);
   237			break;
   238		case NVKM_FIRMWARE_IMG_DMA: {
   239			len = ALIGN(fw->len, PAGE_SIZE);
   240	
   241			fw->img = dma_alloc_noncoherent(fw->device->dev,
 > 242							len, &fw->phys,
diff mbox series

Patch

diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
index adc60b25f8e6..c9bee980777c 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);
@@ -235,14 +236,14 @@  nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name,
 		fw->img = kmemdup(src, fw->len, GFP_KERNEL);
 		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, &fw->phys,
+						DMA_TO_DEVICE,
+						GFP_KERNEL);
 		if (fw->img) {
 			memcpy(fw->img, src, fw->len);
-			fw->phys = addr;
 		}
 
 		sg_init_one(&fw->mem.sgl, fw->img, len);
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);