drm/xe: Invalidate userptr VMA on page pin fault
Subsystems (2)
Matthew Brost
maintainerPATCH 1/1 drm/xe: Invalidate userptr VMA on page pin fault
Rather than return an error to the user or ban the VM when userptr VMA page pin fails with -EFAULT, invalidate VMA mappings. This supports the UMD use case of freeing userptr while still having bindings.
--- drivers/gpu/drm/xe/xe_gt_pagefault.c | 4 ++-- drivers/gpu/drm/xe/xe_trace.h | 2 +- drivers/gpu/drm/xe/xe_vm.c | 20 +++++++++++++------- drivers/gpu/drm/xe/xe_vm_types.h | 7 ++----- 4 files changed, 18 insertions(+), 15 deletions(-)
drivers/gpu/drm/xe/xe_gt_pagefault.c +2 -2
@@ -69,7 +69,7 @@ static bool access_is_atomic(enum access_type access_type)static bool vma_is_valid (struct xe_tile *tile,struct xe_vma *vma) {return BIT (tile->id) & vma->tile_present && - !(BIT (tile->id) & vma->usm.tile_invalidated); + !(BIT (tile->id) & vma->tile_invalidated); }static bool vma_matches (struct xe_vma *vma,u64 page_addr)
@@ -226,7 +226,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)if (xe_vma_is_userptr (vma)) ret =xe_vma_userptr_check_repin (to_userptr_vma (vma)); - vma->usm.tile_invalidated &= ~BIT (tile->id); + vma->tile_invalidated &= ~BIT (tile->id); unlock_dma_resv:drm_exec_fini (&exec);
drivers/gpu/drm/xe/xe_trace.h +1 -1
@@ -468,7 +468,7 @@ DEFINE_EVENT(xe_vma, xe_vma_userptr_invalidate,TP_ARGS (vma) ); -DEFINE_EVENT (xe_vma, xe_vma_usm_invalidate, +DEFINE_EVENT (xe_vma, xe_vma_invalidate, TP_PROTO(struct xe_vma *vma),TP_ARGS (vma) );
drivers/gpu/drm/xe/xe_vm.c +13 -7
@@ -724,11 +724,18 @@ int xe_vm_userptr_pin(struct xe_vm *vm)list_for_each_entry_safe (uvma, next, &vm->userptr.repin_list, userptr.repin_link) { err =xe_vma_userptr_pin_pages (uvma); -if (err <0 ) -return err; -list_del_init (&uvma->userptr.repin_link); -list_move_tail (&uvma->vma.combined_links.rebind, &vm->rebind_list); +if (err == -EFAULT ) { + err =xe_vm_invalidate_vma (&uvma->vma); +if (err) +return err; + }else { +if (err <0 ) +return err; + +list_move_tail (&uvma->vma.combined_links.rebind, + &vm->rebind_list); + } }return 0 ;
@@ -3214,9 +3221,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)u8 id;int ret; -xe_assert (xe,xe_vm_in_fault_mode (xe_vma_vm (vma)));xe_assert (xe, !xe_vma_is_null (vma)); -trace_xe_vma_usm_invalidate (vma); +trace_xe_vma_invalidate (vma);/* Check that we don't race with page-table updates */ if (IS_ENABLED (CONFIG_PROVE_LOCKING )) {
@@ -3254,7 +3260,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) } } - vma->usm.tile_invalidated = vma->tile_mask; + vma->tile_invalidated = vma->tile_mask;return 0 ; }
drivers/gpu/drm/xe/xe_vm_types.h +2 -5
@@ -84,11 +84,8 @@ struct xe_vma {struct work_struct destroy_work; }; -/** @usm: unified shared memory state */ -struct { -/** @tile_invalidated: VMA has been invalidated */ -u8 tile_invalidated; - } usm; +/** @tile_invalidated: VMA has been invalidated */ +u8 tile_invalidated;/** @tile_mask: Tile mask of where to create binding for this VMA */ u8 tile_mask;
Signature · 1 line
2.34.1
Patchwork
CI✓ CI.Patch_applied: success for drm/xe: Invalidate userptr VMA on page pin fault
== Series Details ==
== Series Details ==
Series: drm/xe: Invalidate userptr VMA on page pin fault
URL : https://patchwork.freedesktop.org/series/130935/
State : success
== Summary ==
=== Applying kernel patches on branch 'drm-tip' with base: ===
Base commit: 3fde6df89bac drm-tip: 2024y-03m-08d-18h-22m-29s UTC integration manifest === git am output follows ===
Applying: drm/xe: Invalidate userptr VMA on page pin fault
Patchwork
CI✓ CI.checkpatch: success for drm/xe: Invalidate userptr VMA on page pin fault
In reply to Matthew Brost== Series Details ==
== Series Details ==
Series: drm/xe: Invalidate userptr VMA on page pin fault
URL : https://patchwork.freedesktop.org/series/130935/
State : success
== Summary ==
+ KERNEL=/kernel
+ git clone https://gitlab.freedesktop.org/drm/maintainer-tools mt Cloning into 'mt'...
warning: redirecting to https://gitlab.freedesktop.org/drm/maintainer-tools.git/
+ git -C mt rev-list -n1 origin/master a9bb2a8a17457065eb398a81e8fd9aec2b519fd6
+ cd /kernel
+ git config --global --add safe.directory /kernel
+ git log -n1
commit 51be9738e69582621c45a442ac73cfa2571920a7
Author: Matthew Brost <[email protected]> Date: Fri Mar 8 13:37:47 2024 -0800
drm/xe: Invalidate userptr VMA on page pin fault
Rather than return an error to the user or ban the VM when userptr VMA page pin fails with -EFAULT, invalidate VMA mappings. This supports the UMD use case of freeing userptr while still having bindings.
+ /mt/dim checkpatch 3fde6df89bac97416ce1c82b14237a1a67ce3285 drm-intel 51be9738e695 drm/xe: Invalidate userptr VMA on page pin fault
Patchwork
CI✗ CI.KUnit: failure for drm/xe: Invalidate userptr VMA on page pin fault
In reply to Matthew Brost== Series Details ==
== Series Details ==
Series: drm/xe: Invalidate userptr VMA on page pin fault
URL : https://patchwork.freedesktop.org/series/130935/
State : failure
== Summary ==
+ trap cleanup EXIT
+ /kernel/tools/testing/kunit/kunit.py run --kunitconfig /kernel/drivers/gpu/drm/xe/.kunitconfig ERROR:root:../arch/x86/um/user-offsets.c:17:6: warning: no previous prototype for ‘foo’ [-Wmissing-prototypes] 17 | void foo(void)
| ^~~
In file included from ../arch/um/kernel/asm-offsets.c:1:../arch/x86/um/shared/sysdep/kernel-offsets.h:9:6: warning: no previous prototype for ‘foo’ [-Wmissing-prototypes]
9 | void foo(void)
| ^~~../arch/x86/um/bugs_64.c:9:6: warning: no previous prototype for ‘arch_check_bugs’ [-Wmissing-prototypes]
9 | void arch_check_bugs(void)
| ^~~~~~~~~~~~~~~../arch/x86/um/bugs_64.c:13:6: warning: no previous prototype for ‘arch_examine_signal’ [-Wmissing-prototypes]
13 | void arch_examine_signal(int sig, struct uml_pt_regs *regs)
| ^~~~~~~~~~~~~~~~~~~
../arch/x86/um/fault.c:18:5: warning: no previous prototype for ‘arch_fixup’ [-Wmissing-prototypes]
18 | int arch_fixup(unsigned long address, struct uml_pt_regs *regs)
| ^~~~~~~~~~
../arch/x86/um/os-Linux/registers.c:146:15: warning: no previous prototype for ‘get_thread_reg’ [-Wmissing-prototypes]
146 | unsigned long get_thread_reg(int reg, jmp_buf *buf)
| ^~~~~~~~~~~~~~
../arch/x86/um/vdso/um_vdso.c:16:5: warning: no previous prototype for ‘__vdso_clock_gettime’ [-Wmissing-prototypes]
16 | int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts)
| ^~~~~~~~~~~~~~~~~~~~
../arch/x86/um/vdso/um_vdso.c:30:5: warning: no previous prototype for ‘__vdso_gettimeofday’ [-Wmissing-prototypes]
30 | int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
| ^~~~~~~~~~~~~~~~~~~
../arch/x86/um/vdso/um_vdso.c:44:21: warning: no previous prototype for ‘__vdso_time’ [-Wmissing-prototypes]
44 | __kernel_old_time_t __vdso_time(__kernel_old_time_t *t)
| ^~~~~~~~~~~
../arch/x86/um/vdso/um_vdso.c:57:1: warning: no previous prototype for ‘__vdso_getcpu’ [-Wmissing-prototypes]
57 | __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
| ^~~~~~~~~~~~~../arch/x86/um/os-Linux/mcontext.c:7:6: warning: no previous prototype for ‘get_regs_from_mc’ [-Wmissing-prototypes]
7 | void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
| ^~~~~~~~~~~~~~~~../arch/um/os-Linux/skas/process.c:107:6: warning: no previous prototype for ‘wait_stub_done’ [-Wmissing-prototypes]
107 | void wait_stub_done(int pid)
| ^~~~~~~~~~~~~~
../arch/um/os-Linux/skas/process.c:683:6: warning: no previous prototype for ‘__switch_mm’ [-Wmissing-prototypes]
683 | void __switch_mm(struct mm_id *mm_idp)
| ^~~~~~~~~~~
../arch/um/kernel/skas/mmu.c:17:5: warning: no previous prototype for ‘init_new_context’ [-Wmissing-prototypes]
17 | int init_new_context(struct task_struct *task, struct mm_struct *mm)
| ^~~~~~~~~~~~~~~~
../arch/um/kernel/skas/mmu.c:60:6: warning: no previous prototype for ‘destroy_context’ [-Wmissing-prototypes]
60 | void destroy_context(struct mm_struct *mm)
| ^~~~~~~~~~~~~~~
../arch/x86/um/ptrace_64.c:111:5: warning: no previous prototype for ‘poke_user’ [-Wmissing-prototypes]
111 | int poke_user(struct task_struct *child, long addr, long data)
| ^~~~~~~~~
../arch/x86/um/ptrace_64.c:171:5: warning: no previous prototype for ‘peek_user’ [-Wmissing-prototypes]
171 | int peek_user(struct task_struct *child, long addr, long data)
| ^~~~~~~~~
../arch/um/os-Linux/main.c:187:7: warning: no previous prototype for ‘__wrap_malloc’ [-Wmissing-prototypes]
187 | void *__wrap_malloc(int size)
| ^~~~~~~~~~~~~
../arch/um/os-Linux/main.c:208:7: warning: no previous prototype for ‘__wrap_calloc’ [-Wmissing-prototypes]
208 | void *__wrap_calloc(int n, int size)
| ^~~~~~~~~~~~~
../arch/um/os-Linux/main.c:222:6: warning: no previous prototype for ‘__wrap_free’ [-Wmissing-prototypes]
222 | void __wrap_free(void *ptr)
| ^~~~~~~~~~~
../arch/um/os-Linux/mem.c:28:6: warning: no previous prototype for ‘kasan_map_memory’ [-Wmissing-prototypes]
28 | void kasan_map_memory(void *start, size_t len)
| ^~~~~~~~~~~~~~~~
../arch/um/os-Linux/mem.c:212:13: warning: no previous prototype for ‘check_tmpexec’ [-Wmissing-prototypes]
212 | void __init check_tmpexec(void)
| ^~~~~~~~~~~~~
../arch/um/kernel/skas/process.c:36:12: warning: no previous prototype for ‘start_uml’ [-Wmissing-prototypes]
36 | int __init start_uml(void)
| ^~~~~~~~~
../arch/um/os-Linux/signal.c:75:6: warning: no previous prototype for ‘sig_handler’ [-Wmissing-prototypes]
75 | void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
| ^~~~~~~~~~~
../arch/um/os-Linux/signal.c:111:6: warning: no previous prototype for ‘timer_alarm_handler’ [-Wmissing-prototypes]
111 | void timer_alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc)
| ^~~~~~~~~~~~~~~~~~~
../arch/um/os-Linux/start_up.c:301:12: warning: no previous prototype for ‘parse_iomem’ [-Wmissing-prototypes]
301 | int __init parse_iomem(char *str, int *add)
| ^~~~~~~~~~~
../arch/x86/um/signal.c:560:6: warning: no previous prototype for ‘sys_rt_sigreturn’ [-Wmissing-prototypes]
560 | long sys_rt_sigreturn(void)
| ^~~~~~~~~~~~~~~~
../arch/x86/um/syscalls_64.c:48:6: warning: no previous prototype for ‘arch_switch_to’ [-Wmissing-prototypes]
48 | void arch_switch_to(struct task_struct *to)
| ^~~~~~~~~~~~~~
../arch/um/kernel/mem.c:202:8: warning: no previous prototype for ‘pgd_alloc’ [-Wmissing-prototypes]
202 | pgd_t *pgd_alloc(struct mm_struct *mm)
| ^~~~~~~~~
../arch/um/kernel/mem.c:215:7: warning: no previous prototype for ‘uml_kmalloc’ [-Wmissing-prototypes]
215 | void *uml_kmalloc(int size, int flags)
| ^~~~~~~~~~~
../arch/um/kernel/process.c:51:5: warning: no previous prototype for ‘pid_to_processor_id’ [-Wmissing-prototypes]
51 | int pid_to_processor_id(int pid)
| ^~~~~~~~~~~~~~~~~~~
../arch/um/kernel/process.c:87:7: warning: no previous prototype for ‘__switch_to’ [-Wmissing-prototypes]
87 | void *__switch_to(struct task_struct *from, struct task_struct *to)
| ^~~~~~~~~~~
../arch/um/kernel/process.c:140:6: warning: no previous prototype for ‘fork_handler’ [-Wmissing-prototypes]
140 | void fork_handler(void)
| ^~~~~~~~~~~~
../arch/um/kernel/process.c:217:6: warning: no previous prototype for ‘arch_cpu_idle’ [-Wmissing-prototypes]
217 | void arch_cpu_idle(void)
| ^~~~~~~~~~~~~
../arch/um/kernel/process.c:253:5: warning: no previous prototype for ‘copy_to_user_proc’ [-Wmissing-prototypes]
253 | int copy_to_user_proc(void __user *to, void *from, int size)
| ^~~~~~~~~~~~~~~~~
../arch/um/kernel/process.c:263:5: warning: no previous prototype for ‘clear_user_proc’ [-Wmissing-prototypes]
263 | int clear_user_proc(void __user *buf, int size)
| ^~~~~~~~~~~~~~~
../arch/um/kernel/process.c:271:6: warning: no previous prototype for ‘set_using_sysemu’ [-Wmissing-prototypes]
271 | void set_using_sysemu(int value)
| ^~~~~~~~~~~~~~~~
../arch/um/kernel/process.c:278:5: warning: no previous prototype for ‘get_using_sysemu’ [-Wmissing-prototypes]
278 | int get_using_sysemu(void)
| ^~~~~~~~~~~~~~~~
../arch/um/kernel/process.c:316:12: warning: no previous prototype for ‘make_proc_sysemu’ [-Wmissing-prototypes]
316 | int __init make_proc_sysemu(void)
| ^~~~~~~~~~~~~~~~
../arch/um/kernel/process.c:348:15: warning: no previous prototype for ‘arch_align_stack’ [-Wmissing-prototypes]
348 | unsigned long arch_align_stack(unsigned long sp)
| ^~~~~~~~~~~~~~~~
../arch/um/kernel/reboot.c:45:6: warning: no previous prototype for ‘machine_restart’ [-Wmissing-prototypes]
45 | void machine_restart(char * __unused)
| ^~~~~~~~~~~~~~~
../arch/um/kernel/reboot.c:51:6: warning: no previous prototype for ‘machine_power_off’ [-Wmissing-prototypes]
51 | void machine_power_off(void)
| ^~~~~~~~~~~~~~~~~
../arch/um/kernel/reboot.c:57:6: warning: no previous prototype for ‘machine_halt’ [-Wmissing-prototypes]
57 | void machine_halt(void)
| ^~~~~~~~~~~~
../arch/um/kernel/tlb.c:579:6: warning: no previous prototype for ‘flush_tlb_mm_range’ [-Wmissing-prototypes]
579 | void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
| ^~~~~~~~~~~~~~~~~~
../arch/um/kernel/tlb.c:594:6: warning: no previous prototype for ‘force_flush_all’ [-Wmissing-prototypes]
594 | void force_flush_all(void)
| ^~~~~~~~~~~~~~~
../arch/um/kernel/kmsg_dump.c:60:12: warning: no previous prototype for ‘kmsg_dumper_stdout_init’ [-Wmissing-prototypes]
60 | int __init kmsg_dumper_stdout_init(void)
| ^~~~~~~~~~~~~~~~~~~~~~~
../arch/um/kernel/um_arch.c:408:19: warning: no previous prototype for ‘read_initrd’ [-Wmissing-prototypes]
408 | int __init __weak read_initrd(void)
| ^~~~~~~~~~~
../arch/um/kernel/um_arch.c:461:7: warning: no previous prototype for ‘text_poke’ [-Wmissing-prototypes]
461 | void *text_poke(void *addr, const void *opcode, size_t len)
| ^~~~~~~~~
../arch/um/kernel/um_arch.c:473:6: warning: no previous prototype for ‘text_poke_sync’ [-Wmissing-prototypes]
473 | void text_poke_sync(void)
| ^~~~~~~~~~~~~~
../lib/iomap.c:156:5: warning: no previous prototype for ‘ioread64_lo_hi’ [-Wmissing-prototypes]
156 | u64 ioread64_lo_hi(const void __iomem *addr)
| ^~~~~~~~~~~~~~
../lib/iomap.c:163:5: warning: no previous prototype for ‘ioread64_hi_lo’ [-Wmissing-prototypes]
163 | u64 ioread64_hi_lo(const void __iomem *addr)
| ^~~~~~~~~~~~~~
../lib/iomap.c:170:5: warning: no previous prototype for ‘ioread64be_lo_hi’ [-Wmissing-prototypes]
170 | u64 ioread64be_lo_hi(const void __iomem *addr)
| ^~~~~~~~~~~~~~~~
../lib/iomap.c:178:5: warning: no previous prototype for ‘ioread64be_hi_lo’ [-Wmissing-prototypes]
178 | u64 ioread64be_hi_lo(const void __iomem *addr)
| ^~~~~~~~~~~~~~~~
../lib/iomap.c:264:6: warning: no previous prototype for ‘iowrite64_lo_hi’ [-Wmissing-prototypes]
264 | void iowrite64_lo_hi(u64 val, void __iomem *addr)
| ^~~~~~~~~~~~~~~
../lib/iomap.c:272:6: warning: no previous prototype for ‘iowrite64_hi_lo’ [-Wmissing-prototypes]
272 | void iowrite64_hi_lo(u64 val, void __iomem *addr)
| ^~~~~~~~~~~~~~~
../lib/iomap.c:280:6: warning: no previous prototype for ‘iowrite64be_lo_hi’ [-Wmissing-prototypes]
280 | void iowrite64be_lo_hi(u64 val, void __iomem *addr)
| ^~~~~~~~~~~~~~~~~
../lib/iomap.c:288:6: warning: no previous prototype for ‘iowrite64be_hi_lo’ [-Wmissing-prototypes]
288 | void iowrite64be_hi_lo(u64 val, void __iomem *addr)
| ^~~~~~~~~~~~~~~~~../drivers/gpu/drm/xe/xe_vm.c: In function ‘xe_vm_prefetch’:../drivers/gpu/drm/xe/xe_vm.c:2034:49: error: ‘struct xe_vma’ has no member named ‘usm’
2034 | if (vma->tile_mask != (vma->tile_present & ~vma->usm.tile_invalidated)) {
| ^~../drivers/gpu/drm/xe/xe_vm.c:2053:1: error: control reaches end of non-void function [-Werror=return-type]
2053 | }
| ^
cc1: some warnings being treated as errors
make[7]: *** [../scripts/Makefile.build:243: drivers/gpu/drm/xe/xe_vm.o] Error 1 make[7]: *** Waiting for unfinished jobs....
make[6]: *** [../scripts/Makefile.build:481: drivers/gpu/drm/xe] Error 2 make[5]: *** [../scripts/Makefile.build:481: drivers/gpu/drm] Error 2 make[4]: *** [../scripts/Makefile.build:481: drivers/gpu] Error 2 make[3]: *** [../scripts/Makefile.build:481: drivers] Error 2 make[2]: *** [/kernel/Makefile:1921: .] Error 2
make[1]: *** [/kernel/Makefile:240: __sub-make] Error 2
make: *** [Makefile:240: __sub-make] Error 2
[21:42:48] Configuring KUnit Kernel ...
Generating .config ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig [21:42:52] Building KUnit Kernel ... Populating config with: $ make ARCH=um O=.kunit olddefconfig Building with: $ make ARCH=um O=.kunit --jobs=48 + cleanup ++ stat -c %u:%g /kernel + chown -R 1003:1003 /kernel
Thomas Hellström
maintainerHi, Matthew
Quoted 69 lines · Matthew Brost
Rather than return an error to the user or ban the VM when userptr VMA
page pin fails with-EFAULT, invalidate VMA mappings. This supports the
UMD use case of freeing userptr while still having bindings.Signed-off-by Matthew Brost <[email protected]>---
drivers/gpu/drm/xe/xe_gt_pagefault.c | 4 ++-- drivers/gpu/drm/xe/xe_trace.h | 2 +- drivers/gpu/drm/xe/xe_vm.c | 20 +++++++++++++------- drivers/gpu/drm/xe/xe_vm_types.h | 7 ++-----4 files changed, 18 insertions(+), 15 deletions(-)drivers/gpu/drm/xe/xe_gt_pagefault.c +0
-0@@ -69,7 +69,7 @@ static bool access_is_atomic(enum access_type access_type) static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma) {return
BIT(tile->id)&vma->tile_present&&drivers/gpu/drm/xe/xe_gt_pagefault.c +1
-1- !(BIT (tile->id) & vma->usm.tile_invalidated); + !(BIT (tile->id) & vma->tile_invalidated);}
static boolvma_matches(struct xe_vma *vma, u64 page_addr)drivers/gpu/drm/xe/xe_gt_pagefault.c +0
-0@@ -226,7 +226,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)
if (xe_vma_is_userptr(vma))
ret =
xe_vma_userptr_check_repin(to_userptr_vma(vma));drivers/gpu/drm/xe/xe_gt_pagefault.c +1
-1- vma->usm.tile_invalidated &= ~BIT (tile->id); + vma->tile_invalidated &= ~BIT (tile->id);
unlock_dma_resv:
drm_exec_fini(&exec);drivers/gpu/drm/xe/xe_trace.h +0
-0@@ -468,7 +468,7 @@ DEFINE_EVENT(xe_vma, xe_vma_userptr_invalidate, TP_ARGS(vma) );drivers/gpu/drm/xe/xe_trace.h +1
-1-DEFINE_EVENT(xe_vma, xe_vma_usm_invalidate, +DEFINE_EVENT(xe_vma, xe_vma_invalidate,
TP_PROTO(struct xe_vma *vma),
TP_ARGS(vma)
);drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -724,11 +724,18 @@ int xe_vm_userptr_pin(struct xe_vm *vm)list_for_each_entry_safe(uvma, next, &vm-
Quoted 1 line
userptr.repin_list,
userptr.repin_link) { err =
xe_vma_userptr_pin_pages(uvma);drivers/gpu/drm/xe/xe_vm.c +0
-3-if (err <0 ) -return err; -
list_del_init(&uvma->userptr.repin_link);drivers/gpu/drm/xe/xe_vm.c +0
-1- list_move_tail(&uvma->vma.combined_links.rebind,
&vm->rebind_list);
drivers/gpu/drm/xe/xe_vm.c int xe_vm_userptr_pin(struct xe_vm *vm) · line 729
Quoted 2 lines
drivers/gpu/drm/xe/xe_vm.c +2
-0+if (err == -EFAULT ) { + err =xe_vm_invalidate_vma (&uvma->vma);
I think we need to check for FAULT_MODE here. If we hit this path in FAULT_MODE, we already have an invalid gpu access and can kill the VM.
In preempt-fence mode, we should probably be calling xe_vm_unbind_vma(), because xe_vm_invalidate_vma() isn't safe to call outside of the mmu_notifier, and if there are still BOOKKEEP fences pending- see the asserts in that function.
Quoted 42 lines
drivers/gpu/drm/xe/xe_vm.c +7
-0+if (err) +return err; + }else { +if (err <0 ) +return err; + + list_move_tail(&uvma-Quoted 1 line
vma.combined_links.rebind,
drivers/gpu/drm/xe/xe_vm.c +2
-0+ &vm->rebind_list); + }}
return 0;drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -3214,9 +3221,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) u8 id; int ret;drivers/gpu/drm/xe/xe_vm.c +0
-1-xe_assert (xe,xe_vm_in_fault_mode (xe_vma_vm (vma)));
xe_assert(xe, !xe_vma_is_null(vma));drivers/gpu/drm/xe/xe_vm.c +1
-1-trace_xe_vma_usm_invalidate (vma); +trace_xe_vma_invalidate (vma);
/* Check that we don't race with page-table updates */ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -3254,7 +3260,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) } }drivers/gpu/drm/xe/xe_vm.c +1
-1- vma->usm.tile_invalidated = vma->tile_mask; + vma->tile_invalidated = vma->tile_mask;
return 0;
}drivers/gpu/drm/xe/xe_vm_types.h +0
-0@@ -84,11 +84,8 @@ struct xe_vma { struct work_struct destroy_work; };
drivers/gpu/drm/xe/xe_vm_types.h struct xe_vma { · line 88
Quoted 7 lines
drivers/gpu/drm/xe/xe_vm_types.h +2
-5-/** @usm: unified shared memory state */ -struct { -/** @tile_invalidated: VMA has been invalidated */ -u8 tile_invalidated; - } usm; +/** @tile_invalidated: VMA has been invalidated */ +u8 tile_invalidated;
Add a comment in the commit message about removing the usm struct? /Thomas
Quoted 4 lines
/** @tile_mask: Tile mask of where to create binding for this VMA */
u8tile_mask;
Thomas Hellström
maintainerQuoted 80 lines · Thomas Hellström
Hi, Matthew
Quoted 70 lines · Matthew Brost
Rather than return an error to the user or ban the VM when userptr VMA
page pin fails with-EFAULT, invalidate VMA mappings. This supports the
UMD use case of freeing userptr while still having bindings.Signed-off-by Matthew Brost <[email protected]>---
drivers/gpu/drm/xe/xe_gt_pagefault.c | 4 ++-- drivers/gpu/drm/xe/xe_trace.h | 2 +- drivers/gpu/drm/xe/xe_vm.c | 20 +++++++++++++------- drivers/gpu/drm/xe/xe_vm_types.h | 7 ++-----4 files changed, 18 insertions(+), 15 deletions(-)drivers/gpu/drm/xe/xe_gt_pagefault.c +0
-0@@ -69,7 +69,7 @@ static bool access_is_atomic(enum access_type access_type) static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma) {return
BIT(tile->id)&vma->tile_present&&drivers/gpu/drm/xe/xe_gt_pagefault.c +1
-1- !(BIT (tile->id) & vma->usm.tile_invalidated); + !(BIT (tile->id) & vma->tile_invalidated);}
static boolvma_matches(struct xe_vma *vma, u64 page_addr)drivers/gpu/drm/xe/xe_gt_pagefault.c +0
-0@@ -226,7 +226,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)
if (xe_vma_is_userptr(vma))
ret =
xe_vma_userptr_check_repin(to_userptr_vma(vma));drivers/gpu/drm/xe/xe_gt_pagefault.c +1
-1- vma->usm.tile_invalidated &= ~BIT (tile->id); + vma->tile_invalidated &= ~BIT (tile->id);
unlock_dma_resv:
drm_exec_fini(&exec);drivers/gpu/drm/xe/xe_trace.h +0
-0@@ -468,7 +468,7 @@ DEFINE_EVENT(xe_vma, xe_vma_userptr_invalidate, TP_ARGS(vma) );drivers/gpu/drm/xe/xe_trace.h +1
-1-DEFINE_EVENT(xe_vma, xe_vma_usm_invalidate, +DEFINE_EVENT(xe_vma, xe_vma_invalidate,
TP_PROTO(struct xe_vma *vma),
TP_ARGS(vma)
);drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -724,11 +724,18 @@ int xe_vm_userptr_pin(struct xe_vm *vm)list_for_each_entry_safe(uvma, next, &vm-
Quoted 1 line
userptr.repin_list,
userptr.repin_link) { err =
xe_vma_userptr_pin_pages(uvma);drivers/gpu/drm/xe/xe_vm.c +0
-3-if (err <0 ) -return err; -
list_del_init(&uvma->userptr.repin_link);drivers/gpu/drm/xe/xe_vm.c +0
-1- list_move_tail(&uvma->vma.combined_links.rebind,
&vm->rebind_list);drivers/gpu/drm/xe/xe_vm.c int xe_vm_userptr_pin(struct xe_vm *vm) · line 729
Quoted 2 lines
drivers/gpu/drm/xe/xe_vm.c +2
-0+if (err == -EFAULT ) { + err =xe_vm_invalidate_vma (&uvma->vma);I think we need to check for
FAULT_MODEhere. If we hit this path inFAULT_MODE, we already have an invalid gpu access and can kill the VM.
Quoted 4 lines
In preempt-fence mode, we should probably be calling
xe_vm_unbind_vma(), becausexe_vm_invalidate_vma()isn't safe to call outside of themmu_notifier, and if there are still BOOKKEEP fences pending- see the asserts in that function.
Actually, xe_vm_invalidate_vma() would probably work if we grabbed the vm resv and waited for bookkeep fences first, and updated the asserts.
But then xe_vm_unbind_vma() might still be better since we also clean up the page-tables.
/Thomas
Quoted 60 lines
Quoted 43 lines
drivers/gpu/drm/xe/xe_vm.c +7
-0+if (err) +return err; + }else { +if (err <0 ) +return err; + + list_move_tail(&uvma-Quoted 1 line
vma.combined_links.rebind,
drivers/gpu/drm/xe/xe_vm.c +2
-0+ &vm->rebind_list); + }}
return 0;drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -3214,9 +3221,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) u8 id; int ret;drivers/gpu/drm/xe/xe_vm.c +0
-1-xe_assert (xe,xe_vm_in_fault_mode (xe_vma_vm (vma)));
xe_assert(xe, !xe_vma_is_null(vma));drivers/gpu/drm/xe/xe_vm.c +1
-1-trace_xe_vma_usm_invalidate (vma); +trace_xe_vma_invalidate (vma);
/* Check that we don't race with page-table updates */ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -3254,7 +3260,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) } }drivers/gpu/drm/xe/xe_vm.c +1
-1- vma->usm.tile_invalidated = vma->tile_mask; + vma->tile_invalidated = vma->tile_mask;
return 0;
}drivers/gpu/drm/xe/xe_vm_types.h +0
-0@@ -84,11 +84,8 @@ struct xe_vma { struct work_struct destroy_work; };drivers/gpu/drm/xe/xe_vm_types.h struct xe_vma { · line 88
Quoted 7 lines
drivers/gpu/drm/xe/xe_vm_types.h +2
-5-/** @usm: unified shared memory state */ -struct { -/** @tile_invalidated: VMA has been invalidated */ -u8 tile_invalidated; - } usm; +/** @tile_invalidated: VMA has been invalidated */ +u8 tile_invalidated;Add a comment in the commit message about removing the usm struct? /Thomas
Quoted 4 lines
/** @tile_mask: Tile mask of where to create binding for this VMA */
u8tile_mask;
Matthew Brost
maintainerQuoted 66 lines · Thomas Hellström
Quoted 65 lines · Thomas Hellström
Hi, Matthew
Quoted 62 lines · Matthew Brost
Rather than return an error to the user or ban the VM when userptr VMA
page pin fails with-EFAULT, invalidate VMA mappings. This supports the
UMD use case of freeing userptr while still having bindings.Signed-off-by Matthew Brost <[email protected]>---
drivers/gpu/drm/xe/xe_gt_pagefault.c | 4 ++-- drivers/gpu/drm/xe/xe_trace.h | 2 +- drivers/gpu/drm/xe/xe_vm.c | 20 +++++++++++++------- drivers/gpu/drm/xe/xe_vm_types.h | 7 ++-----4 files changed, 18 insertions(+), 15 deletions(-)drivers/gpu/drm/xe/xe_gt_pagefault.c +0
-0@@ -69,7 +69,7 @@ static bool access_is_atomic(enum access_type access_type) static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma) {return
BIT(tile->id)&vma->tile_present&&drivers/gpu/drm/xe/xe_gt_pagefault.c +1
-1- !(BIT (tile->id) & vma->usm.tile_invalidated); + !(BIT (tile->id) & vma->tile_invalidated);}
static boolvma_matches(struct xe_vma *vma, u64 page_addr)drivers/gpu/drm/xe/xe_gt_pagefault.c +0
-0@@ -226,7 +226,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)
if (xe_vma_is_userptr(vma))
ret =
xe_vma_userptr_check_repin(to_userptr_vma(vma));drivers/gpu/drm/xe/xe_gt_pagefault.c +1
-1- vma->usm.tile_invalidated &= ~BIT (tile->id); + vma->tile_invalidated &= ~BIT (tile->id);
unlock_dma_resv:
drm_exec_fini(&exec);drivers/gpu/drm/xe/xe_trace.h +0
-0@@ -468,7 +468,7 @@ DEFINE_EVENT(xe_vma, xe_vma_userptr_invalidate, TP_ARGS(vma) );drivers/gpu/drm/xe/xe_trace.h +1
-1-DEFINE_EVENT(xe_vma, xe_vma_usm_invalidate, +DEFINE_EVENT(xe_vma, xe_vma_invalidate,
TP_PROTO(struct xe_vma *vma),
TP_ARGS(vma)
);drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -724,11 +724,18 @@ int xe_vm_userptr_pin(struct xe_vm *vm)list_for_each_entry_safe(uvma, next, &vm-
Quoted 1 line
userptr.repin_list,
Quoted 15 lines
Quoted 6 lines
Quoted 6 lines
userptr.repin_link) { err =
xe_vma_userptr_pin_pages(uvma);drivers/gpu/drm/xe/xe_vm.c +0
-3-if (err <0 ) -return err; -
list_del_init(&uvma->userptr.repin_link);Quoted 9 lines
drivers/gpu/drm/xe/xe_vm.c int xe_vm_userptr_pin(struct xe_vm *vm) · line 729
Quoted 4 lines
drivers/gpu/drm/xe/xe_vm.c +0
-1- list_move_tail(&uvma->vma.combined_links.rebind,
&vm->rebind_list);drivers/gpu/drm/xe/xe_vm.c +2
-0+if (err == -EFAULT ) { + err =xe_vm_invalidate_vma (&uvma->vma);I think we need to check for
FAULT_MODEhere. If we hit this path inFAULT_MODE, we already have an invalid gpu access and can kill the VM.
Agree, will fix.
Quoted 9 lines
Quoted 4 lines
In preempt-fence mode, we should probably be calling
xe_vm_unbind_vma(), becausexe_vm_invalidate_vma()isn't safe to call outside of themmu_notifier, and if there are still BOOKKEEP fences pending- see the asserts in that function.Actually,
xe_vm_invalidate_vma()would probably work if we grabbed the vm resv and waited for bookkeep fences first, and updated the asserts.
Yes, I think that will work but is that even needed? We have vm->lock here in write mode which should prevent any further updates to the page tables. What are we trying prevent a race a against? An in-flight bind job which touches the same page tables? I guess that is possible.
Quoted 3 lines
But then
xe_vm_unbind_vma()might still be better since we also clean up the page-tables.
I think we do not want to mess with the VMA state as that should only be changed by user IOCTLs. An invalidation seems to be the right call here.
Quoted 55 lines
/Thomas
Quoted 52 lines
Quoted 43 lines
drivers/gpu/drm/xe/xe_vm.c +7
-0+if (err) +return err; + }else { +if (err <0 ) +return err; + + list_move_tail(&uvma-Quoted 1 line
vma.combined_links.rebind,
drivers/gpu/drm/xe/xe_vm.c +2
-0+ &vm->rebind_list); + }}
return 0;drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -3214,9 +3221,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) u8 id; int ret;drivers/gpu/drm/xe/xe_vm.c +0
-1-xe_assert (xe,xe_vm_in_fault_mode (xe_vma_vm (vma)));
xe_assert(xe, !xe_vma_is_null(vma));drivers/gpu/drm/xe/xe_vm.c +1
-1-trace_xe_vma_usm_invalidate (vma); +trace_xe_vma_invalidate (vma);
/* Check that we don't race with page-table updates */ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -3254,7 +3260,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) } }drivers/gpu/drm/xe/xe_vm.c +1
-1- vma->usm.tile_invalidated = vma->tile_mask; + vma->tile_invalidated = vma->tile_mask;
return 0;
}drivers/gpu/drm/xe/xe_vm_types.h +0
-0@@ -84,11 +84,8 @@ struct xe_vma { struct work_struct destroy_work; };drivers/gpu/drm/xe/xe_vm_types.h struct xe_vma { · line 88
Quoted 7 lines
drivers/gpu/drm/xe/xe_vm_types.h +2
-5-/** @usm: unified shared memory state */ -struct { -/** @tile_invalidated: VMA has been invalidated */ -u8 tile_invalidated; - } usm; +/** @tile_invalidated: VMA has been invalidated */ +u8 tile_invalidated;Add a comment in the commit message about removing the usm struct?
Will add.
Matt
Quoted 9 lines
Quoted 8 lines
/Thomas
Quoted 4 lines
/** @tile_mask: Tile mask of where to create binding for this VMA */
u8tile_mask;
Thomas Hellström
maintainerQuoted 108 lines · Matthew Brost
Quoted 82 lines · Thomas Hellström
Quoted 81 lines · Thomas Hellström
Hi, Matthew
Quoted 78 lines · Matthew Brost
Rather than return an error to the user or ban the VM when userptr
VMA
page pin fails with-EFAULT, invalidate VMA mappings. This supports
the
UMD use case of freeing userptr while still having bindings.Signed-off-by Matthew Brost <[email protected]>---
drivers/gpu/drm/xe/xe_gt_pagefault.c | 4 ++-- drivers/gpu/drm/xe/xe_trace.h | 2 +- drivers/gpu/drm/xe/xe_vm.c | 20 +++++++++++++------- drivers/gpu/drm/xe/xe_vm_types.h | 7 ++-----4 files changed, 18 insertions(+), 15 deletions(-)drivers/gpu/drm/xe/xe_gt_pagefault.c +0
-0@@ -69,7 +69,7 @@ static bool access_is_atomic(enum access_type access_type)static bool
vma_is_valid(struct xe_tile *tile, struct xe_vma *vma)
{
returnBIT(tile->id)&vma->tile_present&&drivers/gpu/drm/xe/xe_gt_pagefault.c +1
-1- !(BIT (tile->id) & vma->usm.tile_invalidated); + !(BIT (tile->id) & vma->tile_invalidated);}
static boolvma_matches(struct xe_vma *vma, u64 page_addr)drivers/gpu/drm/xe/xe_gt_pagefault.c +0
-0@@ -226,7 +226,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)
if (xe_vma_is_userptr(vma))
ret =
xe_vma_userptr_check_repin(to_userptr_vma(vma));drivers/gpu/drm/xe/xe_gt_pagefault.c +1
-1- vma->usm.tile_invalidated &= ~BIT (tile->id); + vma->tile_invalidated &= ~BIT (tile->id);
unlock_dma_resv:
drm_exec_fini(&exec);drivers/gpu/drm/xe/xe_trace.h +0
-0@@ -468,7 +468,7 @@ DEFINE_EVENT(xe_vma, xe_vma_userptr_invalidate, TP_ARGS(vma) );drivers/gpu/drm/xe/xe_trace.h +1
-1-DEFINE_EVENT(xe_vma, xe_vma_usm_invalidate, +DEFINE_EVENT(xe_vma, xe_vma_invalidate,
TP_PROTO(struct xe_vma *vma),
TP_ARGS(vma)
);drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -724,11 +724,18 @@ int xe_vm_userptr_pin(struct xe_vm *vm)list_for_each_entry_safe(uvma, next, &vm-
Quoted 1 line
userptr.repin_list,
userptr.repin_link) { err =
xe_vma_userptr_pin_pages(uvma);drivers/gpu/drm/xe/xe_vm.c +0
-3-if (err <0 ) -return err; -
list_del_init(&uvma->userptr.repin_link);drivers/gpu/drm/xe/xe_vm.c +0
-1- list_move_tail(&uvma-Quoted 1 line
vma.combined_links.rebind,
&vm->rebind_list);drivers/gpu/drm/xe/xe_vm.c +2
-0+if (err == -EFAULT ) { + err = xe_vm_invalidate_vma(&uvma-Quoted 8 lines
Quoted 8 lines
Quoted 1 line
Quoted 1 line
vma);
I think we need to check for
FAULT_MODEhere. If we hit this path inFAULT_MODE, we already have an invalid gpu access and can kill the
VM.Agree, will fix.
Quoted 8 lines
Quoted 6 lines
In preempt-fence mode, we should probably be calling
xe_vm_unbind_vma(), becausexe_vm_invalidate_vma()isn't safe to call
outside of themmu_notifier, and if there are still BOOKKEEP fences
pending- see the asserts in that function.Quoted 5 lines
Actually,
xe_vm_invalidate_vma()would probably work if we grabbed the
vm resv and waited for bookkeep fences first, and updated the asserts.
Quoted 6 lines
Yes, I think that will work but is that even needed? We have
vm->lockhere in write mode which should prevent any further updates to the page
tables. What are we trying prevent a race a against? An in-flight bind
job which touches the same page tables? I guess that is possible.
Yeah, if we adhere to the locking rules for page tables we don't need to care about keeping track of current and future potential racing code paths.
Quoted 10 lines
Quoted 4 lines
But then
xe_vm_unbind_vma()might still be better since we also clean
up the page-tables.I think we do not want to mess with the VMA state as that should only be
changed by user IOCTLs. An invalidation seems to be the right call here.
I think the tile_present is the only vma_state touched there. What I'm after is really also freeing the now unused page-directories, but that's not a necessity.
/Thomas
Quoted 75 lines
Quoted 60 lines
/Thomas
Quoted 56 lines
Quoted 49 lines
drivers/gpu/drm/xe/xe_vm.c +7
-0+if (err) +return err; + }else { +if (err <0 ) +return err; + + list_move_tail(&uvma-Quoted 1 line
vma.combined_links.rebind,
drivers/gpu/drm/xe/xe_vm.c +2
-0+ &vm->rebind_list); + }}
return 0;drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -3214,9 +3221,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) u8 id; int ret;drivers/gpu/drm/xe/xe_vm.c +0
-1-xe_assert (xe,xe_vm_in_fault_mode (xe_vma_vm (vma)));
xe_assert(xe, !xe_vma_is_null(vma));drivers/gpu/drm/xe/xe_vm.c +1
-1-trace_xe_vma_usm_invalidate (vma); +trace_xe_vma_invalidate (vma);
/* Check that we don't race with page-table updates */ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {drivers/gpu/drm/xe/xe_vm.c +0
-0@@ -3254,7 +3260,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) } }drivers/gpu/drm/xe/xe_vm.c +1
-1- vma->usm.tile_invalidated = vma->tile_mask; + vma->tile_invalidated = vma->tile_mask;
return 0;
}drivers/gpu/drm/xe/xe_vm_types.h +0
-0@@ -84,11 +84,8 @@ struct xe_vma { struct work_struct destroy_work; };drivers/gpu/drm/xe/xe_vm_types.h +0
-3-/** @usm: unified shared memory state */ -struct { -/** @tile_invalidated: VMA has been invalidated */
drivers/gpu/drm/xe/xe_vm_types.h struct xe_vma { · line 88
Quoted 4 lines
drivers/gpu/drm/xe/xe_vm_types.h +2
-2-u8 tile_invalidated; - } usm; +/** @tile_invalidated: VMA has been invalidated */ +u8 tile_invalidated;Add a comment in the commit message about removing the usm struct?
Will add.
Matt
Quoted 10 lines
Quoted 9 lines
/Thomas
Quoted 5 lines
/** @tile_mask: Tile mask of where to create binding for
this VMA */
u8tile_mask;