mirror of
https://github.com/torvalds/linux.git
synced 2026-04-27 11:02:31 -04:00
da67179e55
At the moment - the memory allocation for fwsec-sb is created as-needed and
is released after being used. Typically this is at some point well after
driver load, which can cause runtime suspend/resume to initially work on
driver load but then later fail on a machine that has been running for long
enough with sufficiently high enough memory pressure:
kworker/7:1: page allocation failure: order:5, mode:0xcc0(GFP_KERNEL),
nodemask=(null),cpuset=/,mems_allowed=0
CPU: 7 UID: 0 PID: 875159 Comm: kworker/7:1 Not tainted
6.17.8-300.fc43.x86_64 #1 PREEMPT(lazy)
Hardware name: SLIMBOOK Executive/Executive, BIOS N.1.10GRU06 02/02/2024
Workqueue: pm pm_runtime_work
Call Trace:
<TASK>
dump_stack_lvl+0x5d/0x80
warn_alloc+0x163/0x190
? __alloc_pages_direct_compact+0x1b3/0x220
__alloc_pages_slowpath.constprop.0+0x57a/0xb10
__alloc_frozen_pages_noprof+0x334/0x350
__alloc_pages_noprof+0xe/0x20
__dma_direct_alloc_pages.isra.0+0x1eb/0x330
dma_direct_alloc_pages+0x3c/0x190
dma_alloc_pages+0x29/0x130
nvkm_firmware_ctor+0x1ae/0x280 [nouveau]
nvkm_falcon_fw_ctor+0x3e/0x60 [nouveau]
nvkm_gsp_fwsec+0x10e/0x2c0 [nouveau]
? sysvec_apic_timer_interrupt+0xe/0x90
nvkm_gsp_fwsec_sb+0x27/0x70 [nouveau]
tu102_gsp_fini+0x65/0x110 [nouveau]
? ktime_get+0x3c/0xf0
nvkm_subdev_fini+0x67/0xc0 [nouveau]
nvkm_device_fini+0x94/0x140 [nouveau]
nvkm_udevice_fini+0x50/0x70 [nouveau]
nvkm_object_fini+0xb1/0x140 [nouveau]
nvkm_object_fini+0x70/0x140 [nouveau]
? __pfx_pci_pm_runtime_suspend+0x10/0x10
nouveau_do_suspend+0xe4/0x170 [nouveau]
nouveau_pmops_runtime_suspend+0x3e/0xb0 [nouveau]
pci_pm_runtime_suspend+0x67/0x1a0
? __pfx_pci_pm_runtime_suspend+0x10/0x10
__rpm_callback+0x45/0x1f0
? __pfx_pci_pm_runtime_suspend+0x10/0x10
rpm_callback+0x6d/0x80
rpm_suspend+0xe5/0x5e0
? finish_task_switch.isra.0+0x99/0x2c0
pm_runtime_work+0x98/0xb0
process_one_work+0x18f/0x350
worker_thread+0x25a/0x3a0
? __pfx_worker_thread+0x10/0x10
kthread+0xf9/0x240
? __pfx_kthread+0x10/0x10
? __pfx_kthread+0x10/0x10
ret_from_fork+0xf1/0x110
? __pfx_kthread+0x10/0x10
ret_from_fork_asm+0x1a/0x30
</TASK>
The reason this happens is because the fwsec-sb firmware image only
supports being booted from a contiguous coherent sysmem allocation. If a
system runs into enough memory fragmentation from memory pressure, such as
what can happen on systems with low amounts of memory, this can lead to a
situation where it later becomes impossible to find space for a large
enough contiguous allocation to hold fwsec-sb. This causes us to fail to
boot the firmware image, causing the GPU to fail booting and causing the
driver to fail.
Since this firmware can't use non-contiguous allocations, the best solution
to avoid this issue is to simply allocate the memory for fwsec-sb during
initial driver-load, and reuse the memory allocation when fwsec-sb needs to
be used. We then release the memory allocations on driver unload.
Signed-off-by: Lyude Paul <lyude@redhat.com>
Fixes: 594766ca3e ("drm/nouveau/gsp: move booter handling to GPU-specific code")
Cc: <stable@vger.kernel.org> # v6.16+
Reviewed-by: Timur Tabi <ttabi@nvidia.com>
Link: https://patch.msgid.link/20251202175918.63533-1-lyude@redhat.com
96 lines
3.2 KiB
C
96 lines
3.2 KiB
C
/* SPDX-License-Identifier: MIT */
|
|
#ifndef __NVKM_GSP_PRIV_H__
|
|
#define __NVKM_GSP_PRIV_H__
|
|
#include <subdev/gsp.h>
|
|
#include <rm/gpu.h>
|
|
enum nvkm_acr_lsf_id;
|
|
|
|
int nvkm_gsp_fwsec_frts(struct nvkm_gsp *);
|
|
|
|
int nvkm_gsp_fwsec_sb_ctor(struct nvkm_gsp *);
|
|
int nvkm_gsp_fwsec_sb(struct nvkm_gsp *);
|
|
void nvkm_gsp_fwsec_sb_dtor(struct nvkm_gsp *);
|
|
|
|
struct nvkm_gsp_fwif {
|
|
int version;
|
|
int (*load)(struct nvkm_gsp *, int ver, const struct nvkm_gsp_fwif *);
|
|
const struct nvkm_gsp_func *func;
|
|
const struct nvkm_rm_impl *rm;
|
|
const char *ver;
|
|
};
|
|
|
|
int nvkm_gsp_load_fw(struct nvkm_gsp *, const char *name, const char *ver,
|
|
const struct firmware **);
|
|
void nvkm_gsp_dtor_fws(struct nvkm_gsp *);
|
|
|
|
int gv100_gsp_nofw(struct nvkm_gsp *, int, const struct nvkm_gsp_fwif *);
|
|
|
|
int tu102_gsp_load(struct nvkm_gsp *, int, const struct nvkm_gsp_fwif *);
|
|
int tu102_gsp_load_rm(struct nvkm_gsp *, const struct nvkm_gsp_fwif *);
|
|
|
|
int gh100_gsp_load(struct nvkm_gsp *, int, const struct nvkm_gsp_fwif *);
|
|
|
|
#define NVKM_GSP_FIRMWARE_BOOTER(chip,vers) \
|
|
MODULE_FIRMWARE("nvidia/"#chip"/gsp/booter_load-"#vers".bin"); \
|
|
MODULE_FIRMWARE("nvidia/"#chip"/gsp/booter_unload-"#vers".bin"); \
|
|
MODULE_FIRMWARE("nvidia/"#chip"/gsp/bootloader-"#vers".bin"); \
|
|
MODULE_FIRMWARE("nvidia/"#chip"/gsp/gsp-"#vers".bin")
|
|
|
|
#define NVKM_GSP_FIRMWARE_FMC(chip,vers) \
|
|
MODULE_FIRMWARE("nvidia/"#chip"/gsp/fmc-"#vers".bin"); \
|
|
MODULE_FIRMWARE("nvidia/"#chip"/gsp/bootloader-"#vers".bin"); \
|
|
MODULE_FIRMWARE("nvidia/"#chip"/gsp/gsp-"#vers".bin")
|
|
|
|
struct nvkm_gsp_func {
|
|
const struct nvkm_falcon_func *flcn;
|
|
const struct nvkm_falcon_fw_func *fwsec;
|
|
|
|
char *sig_section;
|
|
|
|
struct {
|
|
int (*ctor)(struct nvkm_gsp *, const char *name, const struct firmware *,
|
|
struct nvkm_falcon *, struct nvkm_falcon_fw *);
|
|
} booter;
|
|
|
|
void (*dtor)(struct nvkm_gsp *);
|
|
int (*oneinit)(struct nvkm_gsp *);
|
|
int (*init)(struct nvkm_gsp *);
|
|
int (*fini)(struct nvkm_gsp *, bool suspend);
|
|
int (*reset)(struct nvkm_gsp *);
|
|
|
|
struct {
|
|
const struct nvkm_rm_gpu *gpu;
|
|
} rm;
|
|
};
|
|
|
|
extern const struct nvkm_falcon_func tu102_gsp_flcn;
|
|
extern const struct nvkm_falcon_fw_func tu102_gsp_fwsec;
|
|
int tu102_gsp_booter_ctor(struct nvkm_gsp *, const char *, const struct firmware *,
|
|
struct nvkm_falcon *, struct nvkm_falcon_fw *);
|
|
int tu102_gsp_oneinit(struct nvkm_gsp *);
|
|
int tu102_gsp_init(struct nvkm_gsp *);
|
|
int tu102_gsp_fini(struct nvkm_gsp *, bool suspend);
|
|
int tu102_gsp_reset(struct nvkm_gsp *);
|
|
u64 tu102_gsp_wpr_heap_size(struct nvkm_gsp *);
|
|
|
|
extern const struct nvkm_falcon_func ga102_gsp_flcn;
|
|
extern const struct nvkm_falcon_fw_func ga102_gsp_fwsec;
|
|
int ga102_gsp_booter_ctor(struct nvkm_gsp *, const char *, const struct firmware *,
|
|
struct nvkm_falcon *, struct nvkm_falcon_fw *);
|
|
int ga102_gsp_reset(struct nvkm_gsp *);
|
|
|
|
int gh100_gsp_oneinit(struct nvkm_gsp *);
|
|
int gh100_gsp_init(struct nvkm_gsp *);
|
|
int gh100_gsp_fini(struct nvkm_gsp *, bool suspend);
|
|
|
|
void r535_gsp_dtor(struct nvkm_gsp *);
|
|
int r535_gsp_oneinit(struct nvkm_gsp *);
|
|
int r535_gsp_init(struct nvkm_gsp *);
|
|
int r535_gsp_fini(struct nvkm_gsp *, bool suspend);
|
|
|
|
int nvkm_gsp_new_(const struct nvkm_gsp_fwif *, struct nvkm_device *, enum nvkm_subdev_type, int,
|
|
struct nvkm_gsp **);
|
|
|
|
extern const struct nvkm_gsp_func gv100_gsp;
|
|
#endif
|