[Bug 1911351] [NEW] x86-64 MTTCG Does not update page table entries atomically

[Bug 1911351] [NEW] x86-64 MTTCG Does not update page table entries atomically

[Marco]

Public bug reported:

It seems like the qemu tcg code for x86-64 doesn't write the access and
dirty flags of the page table entries atomically. Instead, they first
read the entry, see if they need to set the page table entry, and then
overwrite the entry. So if you have two threads running at the same
time, one accessing the virtual address over and over again, and the
other modifying the page table entry, it is possible that after the
second thread modifies the page table entry, qemu overwrites the value
with the old page table entry value, with the access/dirty flags set.

Here's a unit test that reproduces this behavior:

https://github.com/mvanotti/kvm-unit-
tests/commit/09f9722807271226a714b04f25174776454b19cd

You can run it with:

```
/usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
-device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
-vnc none -serial stdio -device pci-testdev \
-smp 4 -machine q35 --accel tcg,thread=multi \
-kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
```

Expected output (failure):

```
kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
enabling apic
enabling apic
enabling apic
enabling apic
paging enabled
cr0 = 80010011
cr3 = 627000
cr4 = 20
found 4 cpus
PASS: Need more than 1 CPU
Detected overwritten PTE:
        want: 0x000000000062e007
        got:  0x000000000062d027
FAIL: PTE not overwritten
PASS: All Reads were zero
SUMMARY: 3 tests, 1 unexpected failures
```

This bug has allows user-to-root privilege escalation inside the guest
VM: if the user is able overwrite an entry that belongs to a second-to-
last level page table, and is able to allocate the referenced page, then
the user would be in control of a last-level page table, being able to
map any memory they want. This is not uncommon in situations where
memory is being decomitted.

** Affects: qemu
     Importance: Undecided
         Status: New

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  New

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty flags of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then overwrite the entry. So if you have two threads running at
  the same time, one accessing the virtual address over and over again,
  and the other modifying the page table entry, it is possible that
  after the second thread modifies the page table entry, qemu overwrites
  the value with the old page table entry value, with the access/dirty
  flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug has allows user-to-root privilege escalation inside the guest
  VM: if the user is able overwrite an entry that belongs to a second-
  to-last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

[Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Peter Maydell]

Yeah, it's a long standing API deficiency inside QEMU that we don't have
a way to do atomic modifications in things like page-table-walk code:
mostly you don't notice unless you go looking for it, but we really
ought to fix this. Thanks for the unit test.


** Changed in: qemu
       Status: New => Confirmed

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Confirmed

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty flags of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then overwrite the entry. So if you have two threads running at
  the same time, one accessing the virtual address over and over again,
  and the other modifying the page table entry, it is possible that
  after the second thread modifies the page table entry, qemu overwrites
  the value with the old page table entry value, with the access/dirty
  flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug has allows user-to-root privilege escalation inside the guest
  VM: if the user is able overwrite an entry that belongs to a second-
  to-last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

[Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Marco]

** Description changed:

  It seems like the qemu tcg code for x86-64 doesn't write the access and
- dirty flags of the page table entries atomically. Instead, they first
+ dirty bits of the page table entries atomically. Instead, they first
  read the entry, see if they need to set the page table entry, and then
- overwrite the entry. So if you have two threads running at the same
- time, one accessing the virtual address over and over again, and the
- other modifying the page table entry, it is possible that after the
- second thread modifies the page table entry, qemu overwrites the value
- with the old page table entry value, with the access/dirty flags set.
+ write back the updated page table entry. So if you have two threads
+ running at the same time, one accessing the virtual address over and
+ over again, and the other modifying the page table entry, it is possible
+ that after the second thread modifies the page table entry, qemu
+ overwrites the value with the old page table entry value, with the
+ access/dirty flags set.
  
  Here's a unit test that reproduces this behavior:
  
  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd
  
  You can run it with:
  
  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```
  
  Expected output (failure):
  
  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
-         want: 0x000000000062e007
-         got:  0x000000000062d027
+         want: 0x000000000062e007
+         got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```
  
- This bug has allows user-to-root privilege escalation inside the guest
- VM: if the user is able overwrite an entry that belongs to a second-to-
- last level page table, and is able to allocate the referenced page, then
- the user would be in control of a last-level page table, being able to
- map any memory they want. This is not uncommon in situations where
- memory is being decomitted.
+ This bug allows user-to-root privilege escalation inside the guest VM:
+ if the user is able overwrite an entry that belongs to a second-to-last
+ level page table, and is able to allocate the referenced page, then the
+ user would be in control of a last-level page table, being able to map
+ any memory they want. This is not uncommon in situations where memory is
+ being decomitted.

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Confirmed

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty bits of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then write back the updated page table entry. So if you have two
  threads running at the same time, one accessing the virtual address
  over and over again, and the other modifying the page table entry, it
  is possible that after the second thread modifies the page table
  entry, qemu overwrites the value with the old page table entry value,
  with the access/dirty flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug allows user-to-root privilege escalation inside the guest VM:
  if the user is able overwrite an entry that belongs to a second-to-
  last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

[Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Philippe Mathieu-Daudé]

** Tags added: i386 tcg

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Confirmed

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty bits of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then write back the updated page table entry. So if you have two
  threads running at the same time, one accessing the virtual address
  over and over again, and the other modifying the page table entry, it
  is possible that after the second thread modifies the page table
  entry, qemu overwrites the value with the old page table entry value,
  with the access/dirty flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug allows user-to-root privilege escalation inside the guest VM:
  if the user is able overwrite an entry that belongs to a second-to-
  last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

[Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Peter Maydell]

Not strictly i386 specific -- any arch that wants to do read-modify-
update to its page tables runs into this. There are some not-yet-
implemented Arm architecture extensions that require this, and likely
other archs too.

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Confirmed

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty bits of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then write back the updated page table entry. So if you have two
  threads running at the same time, one accessing the virtual address
  over and over again, and the other modifying the page table entry, it
  is possible that after the second thread modifies the page table
  entry, qemu overwrites the value with the old page table entry value,
  with the access/dirty flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug allows user-to-root privilege escalation inside the guest VM:
  if the user is able overwrite an entry that belongs to a second-to-
  last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

[Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Marco]

We only tested it on x86-64 and aarch64, but we couldn't repro on arm.
It is possible that this affects other platforms as well, but note that
this is specifically mentioned in the qemu wiki as one of the cases that
should be covered when porting mttcg to a new platform:
https://wiki.qemu.org/Features/tcg-multithread

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Confirmed

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty bits of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then write back the updated page table entry. So if you have two
  threads running at the same time, one accessing the virtual address
  over and over again, and the other modifying the page table entry, it
  is possible that after the second thread modifies the page table
  entry, qemu overwrites the value with the old page table entry value,
  with the access/dirty flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug allows user-to-root privilege escalation inside the guest VM:
  if the user is able overwrite an entry that belongs to a second-to-
  last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

[Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Venkatesh Srinivas]

BTW, the RISC-V MMU code _does_ get this right and the model could be
followed by the x86 version - - something like
https://github.com/vsrinivas/qemu/commit/1efa7dc689c4572d8fe0880ddbe44ec22f8f4348,
(but with more compiling + working) might solve this problem and more
closely model h/w.

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Confirmed

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty bits of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then write back the updated page table entry. So if you have two
  threads running at the same time, one accessing the virtual address
  over and over again, and the other modifying the page table entry, it
  is possible that after the second thread modifies the page table
  entry, qemu overwrites the value with the old page table entry value,
  with the access/dirty flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug allows user-to-root privilege escalation inside the guest VM:
  if the user is able overwrite an entry that belongs to a second-to-
  last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

Re: [Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Peter Maydell]

On Tue, 2 Feb 2021 at 05:07, Venkatesh Srinivas
<1911351@bugs.launchpad.net> wrote:
> BTW, the RISC-V MMU code _does_ get this right and the model could be
> followed by the x86 version - - something like
> https://github.com/vsrinivas/qemu/commit/1efa7dc689c4572d8fe0880ddbe44ec22f8f4348,
> (but with more compiling + working) might solve this problem and more
> closely model h/w

target/i386 is the wrong place to put the fix, though:
the abstraction layers for working with AddressSpaces need to
provide atomic operations and then under the hood do the right
thing to implement them. target-specific code shouldn't need
to manually do the translation, fish out a MemoryRegion,
check whether it's really host RAM, and so on.

thanks
-- PMM

Re: [Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Peter Maydell]

On Tue, 2 Feb 2021 at 05:07, Venkatesh Srinivas
<1911351@bugs.launchpad.net> wrote:
> BTW, the RISC-V MMU code _does_ get this right and the model could be
> followed by the x86 version - - something like
> https://github.com/vsrinivas/qemu/commit/1efa7dc689c4572d8fe0880ddbe44ec22f8f4348,
> (but with more compiling + working) might solve this problem and more
> closely model h/w

target/i386 is the wrong place to put the fix, though:
the abstraction layers for working with AddressSpaces need to
provide atomic operations and then under the hood do the right
thing to implement them. target-specific code shouldn't need
to manually do the translation, fish out a MemoryRegion,
check whether it's really host RAM, and so on.

thanks
-- PMM

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Confirmed

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty bits of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then write back the updated page table entry. So if you have two
  threads running at the same time, one accessing the virtual address
  over and over again, and the other modifying the page table entry, it
  is possible that after the second thread modifies the page table
  entry, qemu overwrites the value with the old page table entry value,
  with the access/dirty flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug allows user-to-root privilege escalation inside the guest VM:
  if the user is able overwrite an entry that belongs to a second-to-
  last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

[Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Thomas Huth]

The QEMU project is currently moving its bug tracking to another system.
For this we need to know which bugs are still valid and which could be
closed already. Thus we are setting the bug state to "Incomplete" now.

If the bug has already been fixed in the latest upstream version of QEMU,
then please close this ticket as "Fix released".

If it is not fixed yet and you think that this bug report here is still
valid, then you have two options:

1) If you already have an account on gitlab.com, please open a new ticket
for this problem in our new tracker here:

    https://gitlab.com/qemu-project/qemu/-/issues

and then close this ticket here on Launchpad (or let it expire auto-
matically after 60 days). Please mention the URL of this bug ticket on
Launchpad in the new ticket on GitLab.

2) If you don't have an account on gitlab.com and don't intend to get
one, but still would like to keep this ticket opened, then please switch
the state back to "New" or "Confirmed" within the next 60 days (other-
wise it will get closed as "Expired"). We will then eventually migrate
the ticket automatically to the new system (but you won't be the reporter
of the bug in the new system and thus you won't get notified on changes
anymore).

Thank you and sorry for the inconvenience.


** Changed in: qemu
       Status: Confirmed => Incomplete

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Incomplete

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty bits of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then write back the updated page table entry. So if you have two
  threads running at the same time, one accessing the virtual address
  over and over again, and the other modifying the page table entry, it
  is possible that after the second thread modifies the page table
  entry, qemu overwrites the value with the old page table entry value,
  with the access/dirty flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug allows user-to-root privilege escalation inside the guest VM:
  if the user is able overwrite an entry that belongs to a second-to-
  last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

[Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Marco]

This issue has been migrated to gitlab issue #279. See
https://gitlab.com/qemu-project/qemu/-/issues/279

** Bug watch added: gitlab.com/qemu-project/qemu/-/issues #279
   https://gitlab.com/qemu-project/qemu/-/issues/279

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Invalid

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty bits of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then write back the updated page table entry. So if you have two
  threads running at the same time, one accessing the virtual address
  over and over again, and the other modifying the page table entry, it
  is possible that after the second thread modifies the page table
  entry, qemu overwrites the value with the old page table entry value,
  with the access/dirty flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug allows user-to-root privilege escalation inside the guest VM:
  if the user is able overwrite an entry that belongs to a second-to-
  last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

[Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Marco]

Closing issue as it has been migrated to https://gitlab.com/qemu-
project/qemu/-/issues/279

** Changed in: qemu
       Status: Incomplete => Invalid

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Invalid

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty bits of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then write back the updated page table entry. So if you have two
  threads running at the same time, one accessing the virtual address
  over and over again, and the other modifying the page table entry, it
  is possible that after the second thread modifies the page table
  entry, qemu overwrites the value with the old page table entry value,
  with the access/dirty flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug allows user-to-root privilege escalation inside the guest VM:
  if the user is able overwrite an entry that belongs to a second-to-
  last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions

[Bug 1911351] Re: x86-64 MTTCG Does not update page table entries atomically

[Marco]

Closing issue as it has been migrated to https://gitlab.com/qemu-
project/qemu/-/issues/279

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1911351

Title:
  x86-64 MTTCG Does not update page table entries atomically

Status in QEMU:
  Invalid

Bug description:
  It seems like the qemu tcg code for x86-64 doesn't write the access
  and dirty bits of the page table entries atomically. Instead, they
  first read the entry, see if they need to set the page table entry,
  and then write back the updated page table entry. So if you have two
  threads running at the same time, one accessing the virtual address
  over and over again, and the other modifying the page table entry, it
  is possible that after the second thread modifies the page table
  entry, qemu overwrites the value with the old page table entry value,
  with the access/dirty flags set.

  Here's a unit test that reproduces this behavior:

  https://github.com/mvanotti/kvm-unit-
  tests/commit/09f9722807271226a714b04f25174776454b19cd

  You can run it with:

  ```
  /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults \
  -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 \
  -vnc none -serial stdio -device pci-testdev \
  -smp 4 -machine q35 --accel tcg,thread=multi \
  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  ```

  Expected output (failure):

  ```
  kvm-unit-tests$ make && /usr/bin/qemu-system-x86_64 --no-reboot -nodefaults -device pc-testdev -device isa-debug-exit,iobase=0xf4,iosize=0x4 -vnc none -serial stdio -device pci-testdev -smp 4 -machine q35 --accel tcg,thread=multi  -kernel x86/mmu-race.flat # -initrd /tmp/tmp.avvPpezMFf
  enabling apic
  enabling apic
  enabling apic
  enabling apic
  paging enabled
  cr0 = 80010011
  cr3 = 627000
  cr4 = 20
  found 4 cpus
  PASS: Need more than 1 CPU
  Detected overwritten PTE:
          want: 0x000000000062e007
          got:  0x000000000062d027
  FAIL: PTE not overwritten
  PASS: All Reads were zero
  SUMMARY: 3 tests, 1 unexpected failures
  ```

  This bug allows user-to-root privilege escalation inside the guest VM:
  if the user is able overwrite an entry that belongs to a second-to-
  last level page table, and is able to allocate the referenced page,
  then the user would be in control of a last-level page table, being
  able to map any memory they want. This is not uncommon in situations
  where memory is being decomitted.

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1911351/+subscriptions