MAX_FAULTS_SAVED_PER_VM(9)

💅 MAX_FAULTS_SAVED_PER_VM 💅

okay so bestie, welcome to the MAX_FAULTS_SAVED_PER_VM(9) page from the Kernel API Manual — yes it's a real manpage, yes it's a whole vibe, and yes it's about to make sense. sit down, grab a strawberry drink 🍓, let's go.

✨ NAME ✨

MAX_FAULTS_SAVED_PER_VM — the maximum number of faults each vm can store before future faults get discarded, and the whole point of that is to prevent memory overuse. like, the vm has a little fault-collection jar 🫙 and once it's full, new faults just... don't get in. no cap. it's a memory-safety thing, not a mean thing.

🌸 SYNOPSIS 🌸

MAX_FAULTS_SAVED_PER_VM

that's it. that's the whole synopsis. it's literally just the name, sitting there, being iconic. no arguments, no params, no nothing — she's a constant-style macro situation and she knows it 👑

🦋 SEE ALSO 🦋

okay this is the part where the page goes full main-character and name-drops everyone at the function party 🎉. all of these live in the kernel file ./drivers/gpu/drm/xe/xe_vm.h:

• xe_vm_has_scratch(9)
• gpuvm_to_vm(9)
• Provide accessors for vma members to facilitate easy change of(9)
• to_userptr_vma(9)
• xe_vm_reactivate_rebind(9)
• xe_vm_resv(9)
• xe_vm_assert_held(9)
• xe_vm_set_validating(9)
• xe_vm_clear_validating(9)
• xe_vm_is_validating(9)
• xe_vm_set_validation_exec(9)
• xe_vm_validation_exec(9)
• xe_vm_has_valid_gpu_mapping(9)

fr fr go read these next, they're the friend group and this macro is just the one holding the group chat together 💖

and that's the whole page, bestie — short, sweet, and fully booked 📚✨

sign-off szn 🎀: this lil masterpiece comes from the source path ./drivers/gpu/drm/xe, stamped with the version date October 2026, and it's filed under MAX_FAULTS_SAVED_PER_VM(9) in the Kernel API Manual. periodt. 💅⭐