lwn.git/arch/x86/include/asm, branch v6.8-rc5

work around gcc bugs with 'asm goto' with outputs

2024-02-09T23:57:48+00:00

We've had issues with gcc and 'asm goto' before, and we created a 'asm_volatile_goto()' macro for that in the past: see commits 3f0116c3238a ("compiler/gcc4: Add quirk for 'asm goto' miscompilation bug") and a9f180345f53 ("compiler/gcc4: Make quirk for asm_volatile_goto() unconditional"). Then, much later, we ended up removing the workaround in commit 43c249ea0b1e ("compiler-gcc.h: remove ancient workaround for gcc PR 58670") because we no longer supported building the kernel with the affected gcc versions, but we left the macro uses around. Now, Sean Christopherson reports a new version of a very similar problem, which is fixed by re-applying that ancient workaround. But the problem in question is limited to only the 'asm goto with outputs' cases, so instead of re-introducing the old workaround as-is, let's rename and limit the workaround to just that much less common case. It looks like there are at least two separate issues that all hit in this area: (a) some versions of gcc don't mark the asm goto as 'volatile' when it has outputs: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420 which is easy to work around by just adding the 'volatile' by hand. (b) Internal compiler errors: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422 which are worked around by adding the extra empty 'asm' as a barrier, as in the original workaround. but the problem Sean sees may be a third thing since it involves bad code generation (not an ICE) even with the manually added 'volatile'. but the same old workaround works for this case, even if this feels a bit like voodoo programming and may only be hiding the issue. Reported-and-tested-by: Sean Christopherson Link: https://lore.kernel.org/all/20240208220604.140859-1-seanjc@google.com/ Cc: Nick Desaulniers Cc: Uros Bizjak Cc: Jakub Jelinek Cc: Andrew Pinski Signed-off-by: Linus Torvalds

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

2024-02-07T17:52:16+00:00

Pull kvm fixes from Paolo Bonzini: "x86 guest: - Avoid false positive for check that only matters on AMD processors x86: - Give a hint when Win2016 might fail to boot due to XSAVES && !XSAVEC configuration - Do not allow creating an in-kernel PIT unless an IOAPIC already exists RISC-V: - Allow ISA extensions that were enabled for bare metal in 6.8 (Zbc, scalar and vector crypto, Zfh[min], Zihintntl, Zvfh[min], Zfa) S390: - fix CC for successful PQAP instruction - fix a race when creating a shadow page" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: x86/coco: Define cc_vendor without CONFIG_ARCH_HAS_CC_PLATFORM x86/kvm: Fix SEV check in sev_map_percpu_data() KVM: x86: Give a hint when Win2016 might fail to boot due to XSAVES erratum KVM: x86: Check irqchip mode before create PIT KVM: riscv: selftests: Add Zfa extension to get-reg-list test RISC-V: KVM: Allow Zfa extension for Guest/VM KVM: riscv: selftests: Add Zvfh[min] extensions to get-reg-list test RISC-V: KVM: Allow Zvfh[min] extensions for Guest/VM KVM: riscv: selftests: Add Zihintntl extension to get-reg-list test RISC-V: KVM: Allow Zihintntl extension for Guest/VM KVM: riscv: selftests: Add Zfh[min] extensions to get-reg-list test RISC-V: KVM: Allow Zfh[min] extensions for Guest/VM KVM: riscv: selftests: Add vector crypto extensions to get-reg-list test RISC-V: KVM: Allow vector crypto extensions for Guest/VM KVM: riscv: selftests: Add scaler crypto extensions to get-reg-list test RISC-V: KVM: Allow scalar crypto extensions for Guest/VM KVM: riscv: selftests: Add Zbc extension to get-reg-list test RISC-V: KVM: Allow Zbc extension for Guest/VM KVM: s390: fix cc for successful PQAP KVM: s390: vsie: fix race during shadow creation

x86/coco: Define cc_vendor without CONFIG_ARCH_HAS_CC_PLATFORM

2024-02-06T08:56:04+00:00

After commit a9ef277488cf ("x86/kvm: Fix SEV check in sev_map_percpu_data()"), there is a build error when building x86_64_defconfig with GCOV using LLVM: ld.lld: error: undefined symbol: cc_vendor >>> referenced by kvm.c >>> arch/x86/kernel/kvm.o:(kvm_smp_prepare_boot_cpu) in archive vmlinux.a which corresponds to if (cc_vendor != CC_VENDOR_AMD || !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return; Without GCOV, clang is able to eliminate the use of cc_vendor because cc_platform_has() evaluates to false when CONFIG_ARCH_HAS_CC_PLATFORM is not set, meaning that if statement will be true no matter what value cc_vendor has. With GCOV, the instrumentation keeps the use of cc_vendor around for code coverage purposes but cc_vendor is only declared, not defined, without CONFIG_ARCH_HAS_CC_PLATFORM, leading to the build error above. Provide a macro definition of cc_vendor when CONFIG_ARCH_HAS_CC_PLATFORM is not set with a value of CC_VENDOR_NONE, so that the first condition can always be evaluated/eliminated at compile time, avoiding the build error altogether. This is very similar to the situation prior to commit da86eb961184 ("x86/coco: Get rid of accessor functions"). Signed-off-by: Nathan Chancellor Acked-by: Borislav Petkov (AMD) Message-Id: <20240202-provide-cc_vendor-without-arch_has_cc_platform-v1-1-09ad5f2a3099@kernel.org> Fixes: a9ef277488cf ("x86/kvm: Fix SEV check in sev_map_percpu_data()", 2024-01-31) Signed-off-by: Paolo Bonzini

KVM: x86: Give a hint when Win2016 might fail to boot due to XSAVES erratum

2024-01-31T21:21:00+00:00

Since commit b0563468eeac ("x86/CPU/AMD: Disable XSAVES on AMD family 0x17") kernel unconditionally clears the XSAVES CPU feature bit on Zen1/2 CPUs. Because KVM CPU caps are initialized from the kernel boot CPU features this makes the XSAVES feature also unavailable for KVM guests in this case. At the same time the XSAVEC feature is left enabled. Unfortunately, having XSAVEC but no XSAVES in CPUID breaks Hyper-V enabled Windows Server 2016 VMs that have more than one vCPU. Let's at least give users hint in the kernel log what could be wrong since these VMs currently simply hang at boot with a black screen - giving no clue what suddenly broke them and how to make them work again. Trigger the kernel message hint based on the particular guest ID written to the Guest OS Identity Hyper-V MSR implemented by KVM. Defer this check to when the L1 Hyper-V hypervisor enables SVM in EFER since we want to limit this message to Hyper-V enabled Windows guests only (Windows session running nested as L2) but the actual Guest OS Identity MSR write is done by L1 and happens before it enables SVM. Fixes: b0563468eeac ("x86/CPU/AMD: Disable XSAVES on AMD family 0x17") Signed-off-by: Maciej S. Szmigiero Message-Id: [Move some checks before mutex_lock(), rename function. - Paolo] Signed-off-by: Paolo Bonzini

Merge tag 'mm-hotfixes-stable-2024-01-28-23-21' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

2024-01-30T01:12:16+00:00

Pull misc fixes from Andrew Morton: "22 hotfixes. 11 are cc:stable and the remainder address post-6.7 issues or aren't considered appropriate for backporting" * tag 'mm-hotfixes-stable-2024-01-28-23-21' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (22 commits) mm: thp_get_unmapped_area must honour topdown preference mm: huge_memory: don't force huge page alignment on 32 bit userfaultfd: fix mmap_changing checking in mfill_atomic_hugetlb selftests/mm: ksm_tests should only MADV_HUGEPAGE valid memory scs: add CONFIG_MMU dependency for vfree_atomic() mm/memory: fix folio_set_dirty() vs. folio_mark_dirty() in zap_pte_range() mm/huge_memory: fix folio_set_dirty() vs. folio_mark_dirty() selftests/mm: Update va_high_addr_switch.sh to check CPU for la57 flag selftests: mm: fix map_hugetlb failure on 64K page size systems MAINTAINERS: supplement of zswap maintainers update stackdepot: make fast paths lock-less again stackdepot: add stats counters exported via debugfs mm, kmsan: fix infinite recursion due to RCU critical section mm/writeback: fix possible divide-by-zero in wb_dirty_limits(), again selftests/mm: switch to bash from sh MAINTAINERS: add man-pages git trees mm: memcontrol: don't throttle dying tasks on memory.high mm: mmap: map MAP_STACK to VM_NOHUGEPAGE uprobes: use pagesize-aligned virtual address when replacing pages selftests/mm: mremap_test: fix build warning ...

mm, kmsan: fix infinite recursion due to RCU critical section

2024-01-26T07:52:21+00:00

Alexander Potapenko writes in [1]: "For every memory access in the code instrumented by KMSAN we call kmsan_get_metadata() to obtain the metadata for the memory being accessed. For virtual memory the metadata pointers are stored in the corresponding `struct page`, therefore we need to call virt_to_page() to get them. According to the comment in arch/x86/include/asm/page.h, virt_to_page(kaddr) returns a valid pointer iff virt_addr_valid(kaddr) is true, so KMSAN needs to call virt_addr_valid() as well. To avoid recursion, kmsan_get_metadata() must not call instrumented code, therefore ./arch/x86/include/asm/kmsan.h forks parts of arch/x86/mm/physaddr.c to check whether a virtual address is valid or not. But the introduction of rcu_read_lock() to pfn_valid() added instrumented RCU API calls to virt_to_page_or_null(), which is called by kmsan_get_metadata(), so there is an infinite recursion now. I do not think it is correct to stop that recursion by doing kmsan_enter_runtime()/kmsan_exit_runtime() in kmsan_get_metadata(): that would prevent instrumented functions called from within the runtime from tracking the shadow values, which might introduce false positives." Fix the issue by switching pfn_valid() to the _sched() variant of rcu_read_lock/unlock(), which does not require calling into RCU. Given the critical section in pfn_valid() is very small, this is a reasonable trade-off (with preemptible RCU). KMSAN further needs to be careful to suppress calls into the scheduler, which would be another source of recursion. This can be done by wrapping the call to pfn_valid() into preempt_disable/enable_no_resched(). The downside is that this sacrifices breaking scheduling guarantees; however, a kernel compiled with KMSAN has already given up any performance guarantees due to being heavily instrumented. Note, KMSAN code already disables tracing via Makefile, and since mmzone.h is included, it is not necessary to use the notrace variant, which is generally preferred in all other cases. Link: https://lkml.kernel.org/r/20240115184430.2710652-1-glider@google.com [1] Link: https://lkml.kernel.org/r/20240118110022.2538350-1-elver@google.com Fixes: 5ec8e8ea8b77 ("mm/sparsemem: fix race in accessing memory_section->usage") Signed-off-by: Marco Elver Reported-by: Alexander Potapenko Reported-by: syzbot+93a9e8a3dea8d6085e12@syzkaller.appspotmail.com Reviewed-by: Alexander Potapenko Tested-by: Alexander Potapenko Cc: Charan Teja Kalla Cc: Borislav Petkov (AMD) Cc: Dave Hansen Cc: Dmitry Vyukov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton

x86/entry/ia32: Ensure s32 is sign extended to s64

2024-01-24T10:49:19+00:00

Presently ia32 registers stored in ptregs are unconditionally cast to unsigned int by the ia32 stub. They are then cast to long when passed to __se_sys*, but will not be sign extended. This takes the sign of the syscall argument into account in the ia32 stub. It still casts to unsigned int to avoid implementation specific behavior. However then casts to int or unsigned int as necessary. So that the following cast to long sign extends the value. This fixes the io_pgetevents02 LTP test when compiled with -m32. Presently the systemcall io_pgetevents_time64() unexpectedly accepts -1 for the maximum number of events. It doesn't appear other systemcalls with signed arguments are effected because they all have compat variants defined and wired up. Fixes: ebeb8c82ffaf ("syscalls/x86: Use 'struct pt_regs' based syscall calling for IA32_EMULATION and x32") Suggested-by: Arnd Bergmann Signed-off-by: Richard Palethorpe Signed-off-by: Nikolay Borisov Signed-off-by: Thomas Gleixner Reviewed-by: Arnd Bergmann Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240110130122.3836513-1-nik.borisov@suse.com Link: https://lore.kernel.org/ltp/20210921130127.24131-1-rpalethorpe@suse.com/

x86/cpu: Add model number for Intel Clearwater Forest processor

2024-01-23T10:08:08+00:00

Server product based on the Atom Darkmont core. Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20240117191844.56180-1-tony.luck@intel.com

x86/CPU/AMD: Add X86_FEATURE_ZEN5

2024-01-23T10:06:18+00:00

Add a synthetic feature flag for Zen5. Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20240104201138.5072-1-bp@alien8.de

Merge tag 'x86_tdx_for_6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2024-01-18T21:41:48+00:00

Pull x86 TDX updates from Dave Hansen: "This contains the initial support for host-side TDX support so that KVM can run TDX-protected guests. This does not include the actual KVM-side support which will come from the KVM folks. The TDX host interactions with kexec also needs to be ironed out before this is ready for prime time, so this code is currently Kconfig'd off when kexec is on. The majority of the code here is the kernel telling the TDX module which memory to protect and handing some additional memory over to it to use to store TDX module metadata. That sounds pretty simple, but the TDX architecture is rather flexible and it takes quite a bit of back-and-forth to say, "just protect all memory, please." There is also some code tacked on near the end of the series to handle a hardware erratum. The erratum can make software bugs such as a kernel write to TDX-protected memory cause a machine check and masquerade as a real hardware failure. The erratum handling watches out for these and tries to provide nicer user errors" * tag 'x86_tdx_for_6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits) x86/virt/tdx: Make TDX host depend on X86_MCE x86/virt/tdx: Disable TDX host support when kexec is enabled Documentation/x86: Add documentation for TDX host support x86/mce: Differentiate real hardware #MCs from TDX erratum ones x86/cpu: Detect TDX partial write machine check erratum x86/virt/tdx: Handle TDX interaction with sleep and hibernation x86/virt/tdx: Initialize all TDMRs x86/virt/tdx: Configure global KeyID on all packages x86/virt/tdx: Configure TDX module with the TDMRs and global KeyID x86/virt/tdx: Designate reserved areas for all TDMRs x86/virt/tdx: Allocate and set up PAMTs for TDMRs x86/virt/tdx: Fill out TDMRs to cover all TDX memory regions x86/virt/tdx: Add placeholder to construct TDMRs to cover all TDX memory regions x86/virt/tdx: Get module global metadata for module initialization x86/virt/tdx: Use all system memory when initializing TDX module as TDX memory x86/virt/tdx: Add skeleton to enable TDX on demand x86/virt/tdx: Add SEAMCALL error printing for module initialization x86/virt/tdx: Handle SEAMCALL no entropy error in common code x86/virt/tdx: Make INTEL_TDX_HOST depend on X86_X2APIC x86/virt/tdx: Define TDX supported page sizes as macros ...