On Wed Sep 24, 2025 at 3:10 PM UTC, Patrick Roy wrote: > From: Patrick Roy <[email protected]> > > [ based on kvm/next ] > > Unmapping virtual machine guest memory from the host kernel's direct map is a > successful mitigation against Spectre-style transient execution issues: If the > kernel page tables do not contain entries pointing to guest memory, then any > attempted speculative read through the direct map will necessarily be blocked > by the MMU before any observable microarchitectural side-effects happen. This > means that Spectre-gadgets and similar cannot be used to target virtual > machine > memory. Roughly 60% of speculative execution issues fall into this category > [1, > Table 1]. > > This patch series extends guest_memfd with the ability to remove its memory > from the host kernel's direct map, to be able to attain the above protection > for KVM guests running inside guest_memfd. > > Additionally, a Firecracker branch with support for these VMs can be found on > GitHub [2]. > > For more details, please refer to the v5 cover letter [v5]. No > substantial changes in design have taken place since. > > === Changes Since v6 === > > - Drop patch for passing struct address_space to ->free_folio(), due to > possible races with freeing of the address_space. (Hugh) > - Stop using PG_uptodate / gmem preparedness tracking to keep track of > direct map state. Instead, use the lowest bit of folio->private. (Mike, > David) > - Do direct map removal when establishing mapping of gmem folio instead > of at allocation time, due to impossibility of handling direct map > removal errors in kvm_gmem_populate(). (Patrick) > - Do TLB flushes after direct map removal, and provide a module > parameter to opt out from them, and a new patch to export > flush_tlb_kernel_range() to KVM. (Will) > > [1]: https://download.vusec.net/papers/quarantine_raid23.pdf > [2]: > https://github.com/firecracker-microvm/firecracker/tree/feature/secret-hiding
I just got around to trying this out, I checked out this patchset using its base-commit and grabbed the Firecracker branch. Things seem OK until I set the secrets_free flag in the Firecracker config which IIUC makes it set GUEST_MEMFD_FLAG_NO_DIRECT_MAP. If I set it, I find the guest doesn't show anything on the console. Running it in a VM and attaching GDB suggests that it's entering the guest repeatedly, it doesn't seem like the vCPU thread is stuck or anything. I'm a bit clueless about how to debug that (so far, whenever I've broken KVM, things always exploded very dramatically). Anyway, if I then kill the firecracker process, the host sometimes crashes, I think this is the most suggestive splat I've seen: [ 99.673420][ T2] BUG: unable to handle page fault for address: ffff888012804000 [ 99.676216][ T2] #PF: supervisor write access in kernel mode [ 99.678381][ T2] #PF: error_code(0x0002) - not-present page [ 99.680499][ T2] PGD 2e01067 P4D 2e01067 PUD 2e02067 PMD 12801063 PTE 800fffffed7fb020 [ 99.683374][ T2] Oops: Oops: 0002 [#1] SMP [ 99.685004][ T2] CPU: 0 UID: 0 PID: 2 Comm: kthreadd Not tainted 6.17.0-rc7-00366-g473c46a3cb2a #106 NONE [ 99.688514][ T2] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.1 11/11/2019 [ 99.691547][ T2] RIP: 0010:clear_page_erms+0x7/0x10 [ 99.693440][ T2] Code: 48 89 47 18 48 89 47 20 48 89 47 28 48 89 47 30 48 89 47 38 48 8d 7f 40 75 d9 90 c3 0f 1f 80 00 00 00 00 b9 00 10 00 00 31 c0 <f3> aa c3 66 0f 1f 44 00 00 48 83 f9 40 73 2a 83 f9 08 73 0f 85 c9 [ 99.700188][ T2] RSP: 0018:ffff88800318fc10 EFLAGS: 00010246 [ 99.702321][ T2] RAX: 0000000000000000 RBX: 0000000000400dc0 RCX: 0000000000001000 [ 99.705100][ T2] RDX: ffffea00004a0100 RSI: ffffea00004a0200 RDI: ffff888012804000 [ 99.707861][ T2] RBP: 0000000000000801 R08: 0000000000000000 R09: 0000000000000000 [ 99.710648][ T2] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000002 [ 99.713412][ T2] R13: 0000000000000801 R14: ffffea00004a0100 R15: ffffffff81f4df80 [ 99.716191][ T2] FS: 0000000000000000(0000) GS:ffff8880bbf28000(0000) knlGS:0000000000000000 [ 99.719316][ T2] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 99.721648][ T2] CR2: ffff888012804000 CR3: 0000000007583001 CR4: 0000000000372eb0 [ 99.724421][ T2] Call Trace: [ 99.725608][ T2] <TASK> [ 99.726646][ T2] get_page_from_freelist+0x6fe/0x14b0 [ 99.728583][ T2] ? fs_reclaim_acquire+0x43/0xe0 [ 99.730325][ T2] ? find_held_lock+0x2b/0x80 [ 99.731965][ T2] __alloc_frozen_pages_noprof+0x147/0x2d0 [ 99.734003][ T2] __alloc_pages_noprof+0x5/0x50 [ 99.735766][ T2] copy_process+0x1b1/0x1b30 [ 99.737398][ T2] ? lock_is_held_type+0x89/0x100 [ 99.739157][ T2] ? kthreadd+0x25/0x190 [ 99.740664][ T2] kernel_clone+0x59/0x390 [ 99.742213][ T2] ? kthreadd+0x25/0x190 [ 99.743728][ T2] kernel_thread+0x55/0x70 [ 99.745310][ T2] ? kthread_complete_and_exit+0x20/0x20 [ 99.747265][ T2] kthreadd+0x117/0x190 [ 99.748748][ T2] ? kthread_is_per_cpu+0x30/0x30 [ 99.750509][ T2] ret_from_fork+0x16b/0x1e0 [ 99.752193][ T2] ? kthread_is_per_cpu+0x30/0x30 [ 99.753992][ T2] ret_from_fork_asm+0x11/0x20 [ 99.755717][ T2] </TASK> [ 99.756861][ T2] CR2: ffff888012804000 [ 99.758353][ T2] ---[ end trace 0000000000000000 ]--- [ 99.760319][ T2] RIP: 0010:clear_page_erms+0x7/0x10 [ 99.762209][ T2] Code: 48 89 47 18 48 89 47 20 48 89 47 28 48 89 47 30 48 89 47 38 48 8d 7f 40 75 d9 90 c3 0f 1f 80 00 00 00 00 b9 00 10 00 00 31 c0 <f3> aa c3 66 0f 1f 44 00 00 48 83 f9 40 73 2a 83 f9 08 73 0f 85 c9 [ 99.769129][ T2] RSP: 0018:ffff88800318fc10 EFLAGS: 00010246 [ 99.771297][ T2] RAX: 0000000000000000 RBX: 0000000000400dc0 RCX: 0000000000001000 [ 99.774126][ T2] RDX: ffffea00004a0100 RSI: ffffea00004a0200 RDI: ffff888012804000 [ 99.777013][ T2] RBP: 0000000000000801 R08: 0000000000000000 R09: 0000000000000000 [ 99.779827][ T2] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000002 [ 99.782641][ T2] R13: 0000000000000801 R14: ffffea00004a0100 R15: ffffffff81f4df80 [ 99.785487][ T2] FS: 0000000000000000(0000) GS:ffff8880bbf28000(0000) knlGS:0000000000000000 [ 99.788671][ T2] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 99.791012][ T2] CR2: ffff888012804000 CR3: 0000000007583001 CR4: 0000000000372eb0 [ 99.793863][ T2] Kernel panic - not syncing: Fatal exception [ 99.796760][ T2] Kernel Offset: disabled [ 99.798296][ T2] ---[ end Kernel panic - not syncing: Fatal exception ]--- This makes me suspect the kvm_gmem_folio_restore_direct_map() path isn't working or isn't getting called. If anyone wants help trying to reproduce this let me know.
