| Message ID | 20240401185821.224068-1-ubizjak@gmail.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | x86/bpf: Fixes for the BPF JIT with retbleed=stuff | expand |
Hello: This series was applied to bpf/bpf.git (master) by Alexei Starovoitov <ast@kernel.org>: On Mon, 1 Apr 2024 20:55:28 +0200 you wrote: > From: Joan Bruguera Micó <joanbrugueram@gmail.com> > > Fixes two issues that cause kernels panic when using the BPF JIT with > the call depth tracking / stuffing mitigation for Skylake processors > (`retbleed=stuff`). Both issues can be triggered by running simple > BPF programs (e.g. running the test suite should trigger both). > > [...] Here is the summary with links: - [RESEND,bpf,v2,1/2] x86/bpf: Fix IP after emitting call depth accounting https://git.kernel.org/bpf/bpf/c/9d98aa088386 - [RESEND,bpf,v2,2/2] x86/bpf: Fix IP for relocating call depth accounting https://git.kernel.org/bpf/bpf/c/6a537453000a You are awesome, thank you!
* patchwork-bot+netdevbpf@kernel.org <patchwork-bot+netdevbpf@kernel.org> wrote: > Hello: > > This series was applied to bpf/bpf.git (master) > by Alexei Starovoitov <ast@kernel.org>: > > On Mon, 1 Apr 2024 20:55:28 +0200 you wrote: > > From: Joan Bruguera Micó <joanbrugueram@gmail.com> > > > > Fixes two issues that cause kernels panic when using the BPF JIT with > > the call depth tracking / stuffing mitigation for Skylake processors > > (`retbleed=stuff`). Both issues can be triggered by running simple > > BPF programs (e.g. running the test suite should trigger both). > > > > [...] > > Here is the summary with links: > - [RESEND,bpf,v2,1/2] x86/bpf: Fix IP after emitting call depth accounting > https://git.kernel.org/bpf/bpf/c/9d98aa088386 > - [RESEND,bpf,v2,2/2] x86/bpf: Fix IP for relocating call depth accounting > https://git.kernel.org/bpf/bpf/c/6a537453000a Just wondering, which kernel version is this targeted for? The bug is upstream as well, so a fix needs to be sent to Linus. I can pick all of this up into tip:x86/urgent, if that accelerates things. Thanks, Ingo
On Wed, Apr 3, 2024 at 9:26 AM Ingo Molnar <mingo@kernel.org> wrote: > > > * patchwork-bot+netdevbpf@kernel.org <patchwork-bot+netdevbpf@kernel.org> wrote: > > > Hello: > > > > This series was applied to bpf/bpf.git (master) > > by Alexei Starovoitov <ast@kernel.org>: > > > > On Mon, 1 Apr 2024 20:55:28 +0200 you wrote: > > > From: Joan Bruguera Micó <joanbrugueram@gmail.com> > > > > > > Fixes two issues that cause kernels panic when using the BPF JIT with > > > the call depth tracking / stuffing mitigation for Skylake processors > > > (`retbleed=stuff`). Both issues can be triggered by running simple > > > BPF programs (e.g. running the test suite should trigger both). > > > > > > [...] > > > > Here is the summary with links: > > - [RESEND,bpf,v2,1/2] x86/bpf: Fix IP after emitting call depth accounting > > https://git.kernel.org/bpf/bpf/c/9d98aa088386 > > - [RESEND,bpf,v2,2/2] x86/bpf: Fix IP for relocating call depth accounting > > https://git.kernel.org/bpf/bpf/c/6a537453000a > > Just wondering, which kernel version is this targeted for? The whole series is intended for the current mainline (v6.9), this is why it is developed against the bpf (*not* bpf-next) branch. Please note that the kernel panics with retbleed=stuff even without %rip-relative changes (patch 1/2 above) [1], so patch 1/2 should be backported to stable branches. [1] https://lore.kernel.org/lkml/20230105214922.250473-1-joanbrugueram@gmail.com/ Uros. > The bug is upstream as well, so a fix needs to be sent to Linus. > > I can pick all of this up into tip:x86/urgent, if that accelerates > things. > > Thanks, > > Ingo
* Uros Bizjak <ubizjak@gmail.com> wrote: > > > Here is the summary with links: > > > - [RESEND,bpf,v2,1/2] x86/bpf: Fix IP after emitting call depth accounting > > > https://git.kernel.org/bpf/bpf/c/9d98aa088386 > > > - [RESEND,bpf,v2,2/2] x86/bpf: Fix IP for relocating call depth accounting > > > https://git.kernel.org/bpf/bpf/c/6a537453000a > > > > Just wondering, which kernel version is this targeted for? > > The whole series is intended for the current mainline (v6.9), this is > why it is developed against the bpf (*not* bpf-next) branch. I see - so bpf.git:master are current-mainline BPF fixes - that's perfect. BTW., bpf-next is not a branch, but a separate Git tree. (Which is what confused me.) Thanks, Ingo
On 4/3/24 10:01 AM, Ingo Molnar wrote: > * Uros Bizjak <ubizjak@gmail.com> wrote: > >>>> Here is the summary with links: >>>> - [RESEND,bpf,v2,1/2] x86/bpf: Fix IP after emitting call depth accounting >>>> https://git.kernel.org/bpf/bpf/c/9d98aa088386 >>>> - [RESEND,bpf,v2,2/2] x86/bpf: Fix IP for relocating call depth accounting >>>> https://git.kernel.org/bpf/bpf/c/6a537453000a >>> >>> Just wondering, which kernel version is this targeted for? >> >> The whole series is intended for the current mainline (v6.9), this is >> why it is developed against the bpf (*not* bpf-next) branch. > > I see - so bpf.git:master are current-mainline BPF fixes - that's perfect. Yes, correct, that is for mainline (v6.9). Thanks, Daniel
From: Joan Bruguera Micó <joanbrugueram@gmail.com> Fixes two issues that cause kernels panic when using the BPF JIT with the call depth tracking / stuffing mitigation for Skylake processors (`retbleed=stuff`). Both issues can be triggered by running simple BPF programs (e.g. running the test suite should trigger both). The first (resubmit) fixes a trivial issue related to calculating the destination IP for call instructions with call depth tracking. The second is related to using the correct IP for relocations, related to the recently introduced %rip-relative addressing for PER_CPU_VAR. Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> --- v2: Simplify calculation of "ip". Add more details to the commit message. Joan Bruguera Micó (1): x86/bpf: Fix IP for relocating call depth accounting Uros Bizjak (1): x86/bpf: Fix IP after emitting call depth accounting arch/x86/include/asm/alternative.h | 4 ++-- arch/x86/kernel/callthunks.c | 4 ++-- arch/x86/net/bpf_jit_comp.c | 19 ++++++++----------- 3 files changed, 12 insertions(+), 15 deletions(-)