diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-14 19:46:06 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-14 19:46:06 +0300 |
commit | 958f338e96f874a0d29442396d6adf9c1e17aa2d (patch) | |
tree | 86a3df90304cd7c1a8af389bcde0d93db7551a49 /arch/x86/include/asm/pgtable.h | |
parent | 781fca5b104693bc9242199cc47c690dcaf6a4cb (diff) | |
parent | 07d981ad4cf1e78361c6db1c28ee5ba105f96cc1 (diff) | |
download | linux-958f338e96f874a0d29442396d6adf9c1e17aa2d.tar.xz |
Merge branch 'l1tf-final' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Merge L1 Terminal Fault fixes from Thomas Gleixner:
"L1TF, aka L1 Terminal Fault, is yet another speculative hardware
engineering trainwreck. It's a hardware vulnerability which allows
unprivileged speculative access to data which is available in the
Level 1 Data Cache when the page table entry controlling the virtual
address, which is used for the access, has the Present bit cleared or
other reserved bits set.
If an instruction accesses a virtual address for which the relevant
page table entry (PTE) has the Present bit cleared or other reserved
bits set, then speculative execution ignores the invalid PTE and loads
the referenced data if it is present in the Level 1 Data Cache, as if
the page referenced by the address bits in the PTE was still present
and accessible.
While this is a purely speculative mechanism and the instruction will
raise a page fault when it is retired eventually, the pure act of
loading the data and making it available to other speculative
instructions opens up the opportunity for side channel attacks to
unprivileged malicious code, similar to the Meltdown attack.
While Meltdown breaks the user space to kernel space protection, L1TF
allows to attack any physical memory address in the system and the
attack works across all protection domains. It allows an attack of SGX
and also works from inside virtual machines because the speculation
bypasses the extended page table (EPT) protection mechanism.
The assoicated CVEs are: CVE-2018-3615, CVE-2018-3620, CVE-2018-3646
The mitigations provided by this pull request include:
- Host side protection by inverting the upper address bits of a non
present page table entry so the entry points to uncacheable memory.
- Hypervisor protection by flushing L1 Data Cache on VMENTER.
- SMT (HyperThreading) control knobs, which allow to 'turn off' SMT
by offlining the sibling CPU threads. The knobs are available on
the kernel command line and at runtime via sysfs
- Control knobs for the hypervisor mitigation, related to L1D flush
and SMT control. The knobs are available on the kernel command line
and at runtime via sysfs
- Extensive documentation about L1TF including various degrees of
mitigations.
Thanks to all people who have contributed to this in various ways -
patches, review, testing, backporting - and the fruitful, sometimes
heated, but at the end constructive discussions.
There is work in progress to provide other forms of mitigations, which
might be less horrible performance wise for a particular kind of
workloads, but this is not yet ready for consumption due to their
complexity and limitations"
* 'l1tf-final' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (75 commits)
x86/microcode: Allow late microcode loading with SMT disabled
tools headers: Synchronise x86 cpufeatures.h for L1TF additions
x86/mm/kmmio: Make the tracer robust against L1TF
x86/mm/pat: Make set_memory_np() L1TF safe
x86/speculation/l1tf: Make pmd/pud_mknotpresent() invert
x86/speculation/l1tf: Invert all not present mappings
cpu/hotplug: Fix SMT supported evaluation
KVM: VMX: Tell the nested hypervisor to skip L1D flush on vmentry
x86/speculation: Use ARCH_CAPABILITIES to skip L1D flush on vmentry
x86/speculation: Simplify sysfs report of VMX L1TF vulnerability
Documentation/l1tf: Remove Yonah processors from not vulnerable list
x86/KVM/VMX: Don't set l1tf_flush_l1d from vmx_handle_external_intr()
x86/irq: Let interrupt handlers set kvm_cpu_l1tf_flush_l1d
x86: Don't include linux/irq.h from asm/hardirq.h
x86/KVM/VMX: Introduce per-host-cpu analogue of l1tf_flush_l1d
x86/irq: Demote irq_cpustat_t::__softirq_pending to u16
x86/KVM/VMX: Move the l1tf_flush_l1d test to vmx_l1d_flush()
x86/KVM/VMX: Replace 'vmx_l1d_flush_always' with 'vmx_l1d_flush_cond'
x86/KVM/VMX: Don't set l1tf_flush_l1d to true from vmx_l1d_flush()
cpu/hotplug: detect SMT disabled by BIOS
...
Diffstat (limited to 'arch/x86/include/asm/pgtable.h')
-rw-r--r-- | arch/x86/include/asm/pgtable.h | 74 |
1 files changed, 51 insertions, 23 deletions
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index a1cb3339da8d..e4ffa565a69f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -188,19 +188,29 @@ static inline int pte_special(pte_t pte) return pte_flags(pte) & _PAGE_SPECIAL; } +/* Entries that were set to PROT_NONE are inverted */ + +static inline u64 protnone_mask(u64 val); + static inline unsigned long pte_pfn(pte_t pte) { - return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT; + phys_addr_t pfn = pte_val(pte); + pfn ^= protnone_mask(pfn); + return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; } static inline unsigned long pmd_pfn(pmd_t pmd) { - return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; + phys_addr_t pfn = pmd_val(pmd); + pfn ^= protnone_mask(pfn); + return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } static inline unsigned long pud_pfn(pud_t pud) { - return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT; + phys_addr_t pfn = pud_val(pud); + pfn ^= protnone_mask(pfn); + return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; } static inline unsigned long p4d_pfn(p4d_t p4d) @@ -403,11 +413,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_RW); } -static inline pmd_t pmd_mknotpresent(pmd_t pmd) -{ - return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE); -} - static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); @@ -462,11 +467,6 @@ static inline pud_t pud_mkwrite(pud_t pud) return pud_set_flags(pud, _PAGE_RW); } -static inline pud_t pud_mknotpresent(pud_t pud) -{ - return pud_clear_flags(pud, _PAGE_PRESENT | _PAGE_PROTNONE); -} - #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { @@ -548,25 +548,45 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot) static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { - return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) | - check_pgprot(pgprot)); + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PTE_PFN_MASK; + return __pte(pfn | check_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { - return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) | - check_pgprot(pgprot)); + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PHYSICAL_PMD_PAGE_MASK; + return __pmd(pfn | check_pgprot(pgprot)); } static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) { - return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) | - check_pgprot(pgprot)); + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PHYSICAL_PUD_PAGE_MASK; + return __pud(pfn | check_pgprot(pgprot)); } +static inline pmd_t pmd_mknotpresent(pmd_t pmd) +{ + return pfn_pmd(pmd_pfn(pmd), + __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); +} + +static inline pud_t pud_mknotpresent(pud_t pud) +{ + return pfn_pud(pud_pfn(pud), + __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); +} + +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); + static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - pteval_t val = pte_val(pte); + pteval_t val = pte_val(pte), oldval = val; /* * Chop off the NX bit (if present), and add the NX portion of @@ -574,17 +594,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) */ val &= _PAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK; - + val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); return __pte(val); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmdval_t val = pmd_val(pmd); + pmdval_t val = pmd_val(pmd), oldval = val; val &= _HPAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; - + val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); return __pmd(val); } @@ -1410,6 +1430,14 @@ static inline bool pud_access_permitted(pud_t pud, bool write) return __pte_access_permitted(pud_val(pud), write); } +#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 +extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); + +static inline bool arch_has_pfn_modify_check(void) +{ + return boot_cpu_has_bug(X86_BUG_L1TF); +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ |