- 27 Jun, 2022 40 commits
-
-
Peter Zijlstra authored
The whole MMIO/RETBLEED enumeration went overboard on steppings. Get rid of all that and simply use ANY. If a future stepping of these models would not be affected, it had better set the relevant ARCH_CAP_$FOO_NO bit in IA32_ARCH_CAPABILITIES. Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by:
Borislav Petkov <bp@suse.de> Acked-by:
Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by:
-
Josh Poimboeuf authored
On VMX, there are some balanced returns between the time the guest's SPEC_CTRL value is written, and the vmenter. Balanced returns (matched by a preceding call) are usually ok, but it's at least theoretically possible an NMI with a deep call stack could empty the RSB before one of the returns. For maximum paranoia, don't allow *any* returns (balanced or otherwise) between the SPEC_CTRL write and the vmenter. [ bp: Fix 32-bit build. ] Signed-off-by:
Josh Poimboeuf <jpoimboe@kernel.org> Signed-off-by:
-
Josh Poimboeuf authored
Prevent RSB underflow/poisoning attacks with RSB. While at it, add a bunch of comments to attempt to document the current state of tribal knowledge about RSB attacks and what exactly is being mitigated. Signed-off-by:
-
Josh Poimboeuf authored
For legacy IBRS to work, the IBRS bit needs to be always re-written after vmexit, even if it's already on. Signed-off-by:
-
Josh Poimboeuf authored
On eIBRS systems, the returns in the vmexit return path from __vmx_vcpu_run() to vmx_vcpu_run() are exposed to RSB poisoning attacks. Fix that by moving the post-vmexit spec_ctrl handling to immediately after the vmexit. Signed-off-by:
-
Josh Poimboeuf authored
Convert __vmx_vcpu_run()'s 'launched' argument to 'flags', in preparation for doing SPEC_CTRL handling immediately after vmexit, which will need another flag. This is much easier than adding a fourth argument, because this code supports both 32-bit and 64-bit, and the fourth argument on 32-bit would have to be pushed on the stack. Note that __vmx_vcpu_run_flags() is called outside of the noinstr critical section because it will soon start calling potentially traceable functions. Signed-off-by:
-
Josh Poimboeuf authored
Move the vmx_vm{enter,exit}() functionality into __vmx_vcpu_run(). This will make it easier to do the spec_ctrl handling before the first RET. Signed-off-by: -
Josh Poimboeuf authored
Commit c536ed2f ("objtool: Remove SAVE/RESTORE hints") removed the save/restore unwind hints because they were no longer needed. Now they're going to be needed again so re-add them. Signed-off-by:
-
Josh Poimboeuf authored
This mask has been made redundant by kvm_spec_ctrl_test_value(). And it doesn't even work when MSR interception is disabled, as the guest can just write to SPEC_CTRL directly. Signed-off-by:
Paolo Bonzini <pbonzini@redhat.com> Signed-off-by:
-
Josh Poimboeuf authored
There's no need to recalculate the host value for every entry/exit. Just use the cached value in spec_ctrl_current(). Signed-off-by:
-
Josh Poimboeuf authored
If the SMT state changes, SSBD might get accidentally disabled. Fix that. Signed-off-by:
-
Josh Poimboeuf authored
The firmware entry code may accidentally clear STIBP or SSBD. Fix that. Signed-off-by:
-
Josh Poimboeuf authored
If a kernel is built with CONFIG_RETPOLINE=n, but the user still wants to mitigate Spectre v2 using IBRS or eIBRS, the RSB filling will be silently disabled. There's nothing retpoline-specific about RSB buffer filling. Remove the CONFIG_RETPOLINE guards around it. Signed-off-by:
-
Peter Zijlstra authored
Zen2 uarchs have an undocumented, unnamed, MSR that contains a chicken bit for some speculation behaviour. It needs setting. Note: very belatedly AMD released naming; it's now officially called MSR_AMD64_DE_CFG2 and MSR_AMD64_DE_CFG2_SUPPRESS_NOBR_PRED_BIT but shall remain the SPECTRAL CHICKEN. Suggested-by:Andrew Cooper <Andrew.Cooper3@citrix.com> Signed-off-by:
-
Peter Zijlstra authored
Since entry asm is tricky, add a validation pass that ensures the retbleed mitigation has been done before the first actual RET instruction. Entry points are those that either have UNWIND_HINT_ENTRY, which acts as UNWIND_HINT_EMPTY but marks the instruction as an entry point, or those that have UWIND_HINT_IRET_REGS at +0. This is basically a variant of validate_branch() that is intra-function and it will simply follow all branches from marked entry points and ensures that all paths lead to ANNOTATE_UNRET_END. If a path hits RET or an indirection the path is a fail and will be reported. There are 3 ANNOTATE_UNRET_END instances: - UNTRAIN_RET itself - exception from-kernel; this path doesn't need UNTRAIN_RET - all early exceptions; these also don't need UNTRAIN_RET Signed-off-by:
-
Josh Poimboeuf authored
When booting with retbleed=auto, if the kernel wasn't built with CONFIG_CC_HAS_RETURN_THUNK, the mitigation falls back to IBPB. Make sure a warning is printed in that case. The IBPB fallback check is done twice, but it really only needs to be done once. Signed-off-by:
-
Peter Zijlstra authored
jmp2ret mitigates the easy-to-attack case at relatively low overhead. It mitigates the long speculation windows after a mispredicted RET, but it does not mitigate the short speculation window from arbitrary instruction boundaries. On Zen2, there is a chicken bit which needs setting, which mitigates "arbitrary instruction boundaries" down to just "basic block boundaries". But there is no fix for the short speculation window on basic block boundaries, other than to flush the entire BTB to evict all attacker predictions. On the spectrum of "fast & blurry" -> "safe", there is (on top of STIBP or no-SMT): 1) Nothing System wide open 2) jmp2ret May stop a script kiddy 3) jmp2ret+chickenbit Raises the bar rather further 4) IBPB Only thing which can count as "safe". Tentative numbers put IBPB-on-entry at a 2.5x hit on Zen2, and a 10x hit on Zen1 according to lmbench. [ bp: Fixup feature bit comments, document option, 32-bit build fix. ] Suggested-by:
-
Peter Zijlstra authored
Ensure the Xen entry also passes through UNTRAIN_RET. Signed-off-by:
-
Peter Zijlstra authored
Native SYS{CALL,ENTER} entry points are called entry_SYS{CALL,ENTER}_{64,compat}, make sure the Xen versions are named consistently. Signed-off-by: -
Peter Zijlstra authored
Update retpoline validation with the new CONFIG_RETPOLINE requirement of not having bare naked RET instructions. Signed-off-by:
-
Peter Zijlstra authored
Having IBRS enabled while the SMT sibling is idle unnecessarily slows down the running sibling. OTOH, disabling IBRS around idle takes two MSR writes, which will increase the idle latency. Therefore, only disable IBRS around deeper idle states. Shallow idle states are bounded by the tick in duration, since NOHZ is not allowed for them by virtue of their short target residency. Only do this for mwait-driven idle, since that keeps interrupts disabled across idle, which makes disabling IBRS vs IRQ-entry a non-issue. Note: C6 is a random threshold, most importantly C1 probably shouldn't disable IBRS, benchmarking needed. Suggested-by:
Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by:
-
Peter Zijlstra authored
Skylake suffers from RSB underflow speculation issues; report this vulnerability and it's mitigation (spectre_v2=ibrs). [jpoimboe: cleanups, eibrs] Signed-off-by:
-
Peter Zijlstra authored
retbleed will depend on spectre_v2, while spectre_v2_user depends on retbleed. Break this cycle. Signed-off-by:
-
Pawan Gupta authored
Extend spectre_v2= boot option with Kernel IBRS. [jpoimboe: no STIBP with IBRS] Signed-off-by:
Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Signed-off-by:
-
Peter Zijlstra authored
When changing SPEC_CTRL for user control, the WRMSR can be delayed until return-to-user when KERNEL_IBRS has been enabled. This avoids an MSR write during context switch. Signed-off-by:
-
Peter Zijlstra authored
Implement Kernel IBRS - currently the only known option to mitigate RSB underflow speculation issues on Skylake hardware. Note: since IBRS_ENTER requires fuller context established than UNTRAIN_RET, it must be placed after it. However, since UNTRAIN_RET itself implies a RET, it must come after IBRS_ENTER. This means IBRS_ENTER needs to also move UNTRAIN_RET. Note 2: KERNEL_IBRS is sub-optimal for XenPV. Signed-off-by:
-
Peter Zijlstra authored
Due to TIF_SSBD and TIF_SPEC_IB the actual IA32_SPEC_CTRL value can differ from x86_spec_ctrl_base. As such, keep a per-CPU value reflecting the current task's MSR content. [jpoimboe: rename] Signed-off-by:
-
Kim Phillips authored
For untrained return thunks to be fully effective, STIBP must be enabled or SMT disabled. Co-developed-by:
Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by:
Kim Phillips <kim.phillips@amd.com> Signed-off-by:
-
Alexandre Chartre authored
Add the "retbleed=<value>" boot parameter to select a mitigation for RETBleed. Possible values are "off", "auto" and "unret" (JMP2RET mitigation). The default value is "auto". Currently, "retbleed=auto" will select the unret mitigation on AMD and Hygon and no mitigation on Intel (JMP2RET is not effective on Intel). [peterz: rebase; add hygon] [jpoimboe: cleanups] Signed-off-by:
Alexandre Chartre <alexandre.chartre@oracle.com> Signed-off-by:
-
Alexandre Chartre authored
Report that AMD x86 CPUs are vulnerable to the RETBleed (Arbitrary Speculative Code Execution with Return Instructions) attack. [peterz: add hygon] [kim: invert parity; fam15h] Co-developed-by:
-
Peter Zijlstra authored
Note: needs to be in a section distinct from Retpolines such that the Retpoline RET substitution cannot possibly use immediate jumps. ORC unwinding for zen_untrain_ret() and __x86_return_thunk() is a little tricky but works due to the fact that zen_untrain_ret() doesn't have any stack ops and as such will emit a single ORC entry at the start (+0x3f). Meanwhile, unwinding an IP, including the __x86_return_thunk() one (+0x40) will search for the largest ORC entry smaller or equal to the IP, these will find the one ORC entry (+0x3f) and all works. [ Alexandre: SVM part. ] [ bp: Build fix, massages. ] Suggested-by:
-
Peter Zijlstra authored
Needed because zen_untrain_ret() will be called from noinstr code. Also makes sense since the thunks MUST NOT contain instrumentation nor be poked with dynamic instrumentation. Signed-off-by:
-
Peter Zijlstra authored
Commit ee774dac ("x86/entry: Move PUSH_AND_CLEAR_REGS out of error_entry()") manages to introduce a CALL/RET pair that is before SWITCH_TO_KERNEL_CR3, which means it is before RETBleed can be mitigated. Revert to an earlier version of the commit in Fixes. Down side is that this will bloat .text size somewhat. The alternative is fully reverting it. The purpose of this patch was to allow migrating error_entry() to C, including the whole of kPTI. Much care needs to be taken moving that forward to not re-introduce this problem of early RETs. Fixes: ee774dac ("x86/entry: Move PUSH_AND_CLEAR_REGS out of error_entry()") Signed-off-by:
-
Peter Zijlstra authored
Use the return thunk in asm code. If the thunk isn't needed, it will get patched into a RET instruction during boot by apply_returns(). Since alternatives can't handle relocations outside of the first instruction, putting a 'jmp __x86_return_thunk' in one is not valid, therefore carve out the memmove ERMS path into a separate label and jump to it. Signed-off-by:
-
Kim Phillips authored
Specifically, it's because __enc_copy() encrypts the kernel after being relocated outside the kernel in sme_encrypt_execute(), and the RET macro's jmp offset isn't amended prior to execution. Signed-off-by:
-
Peter Zijlstra authored
This is userspace code and doesn't play by the normal kernel rules. Signed-off-by:
-
Peter Zijlstra authored
Prepare the SETcc fastop stuff for when RET can be larger still. The tricky bit here is that the expressions should not only be constant C expressions, but also absolute GAS expressions. This means no ?: and 'true' is ~0. Also ensure em_setcc() has the same alignment as the actual FOP_SETCC() ops, this ensures there cannot be an alignment hole between em_setcc() and the first op. Additionally, add a .skip directive to the FOP_SETCC() macro to fill any remaining space with INT3 traps; however the primary purpose of this directive is to generate AS warnings when the remaining space goes negative. Which is a very good indication the alignment magic went side-ways. Signed-off-by:
-
Peter Zijlstra authored
Use the return thunk in eBPF generated code, if needed. Signed-off-by:
-
Peter Zijlstra authored
Use the return thunk in ftrace trampolines, if needed. Signed-off-by:
-
Peter Zijlstra authored
In addition to teaching static_call about the new way to spell 'RET', there is an added complication in that static_call() is allowed to rewrite text before it is known which particular spelling is required. In order to deal with this; have a static_call specific fixup in the apply_return() 'alternative' patching routine that will rewrite the static_call trampoline to match the definite sequence. This in turn creates the problem of uniquely identifying static call trampolines. Currently trampolines are 8 bytes, the first 5 being the jmp.d32/ret sequence and the final 3 a byte sequence that spells out 'SCT'. This sequence is used in __static_call_validate() to ensure it is patching a trampoline and not a random other jmp.d32. That is, false-positives shouldn't be plenty, but aren't a big concern. OTOH the new __static_call_fixup() must not have false-positives, and 'SCT' decodes to the somewhat weird but semi plausible sequence: push %rbx rex.XB push %r12 Additionally, there are SLS concerns with immediate jumps. Combined it seems like a good moment to change the signature to a single 3 byte trap instruction that is unique to this usage and will not ever get generated by accident. As such, change the signature to: '0x0f, 0xb9, 0xcc', which decodes to: ud1 %esp, %ecx Signed-off-by:
-
