- 22 Dec, 2017 12 commits
-
-
Peter Zijlstra authored
Since uv_flush_tlb_others() implements flush_tlb_others() which is about flushing user mappings, we should use __flush_tlb_single(), which too is about flushing user mappings. Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by:
Thomas Gleixner <tglx@linutronix.de> Acked-by:
Andrew Banman <abanman@hpe.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Laight <David.Laight@aculab.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Eduardo Valentin <eduval@amazon.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Travis <mike.travis@hpe.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will.deacon@arm.com> Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Cc: linux-mm@kvack.org Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
Dave Hansen authored
If the kernel oopses while on the trampoline stack, it will print "<SYSENTER>" even if SYSENTER is not involved. That is rather confusing. The "SYSENTER" stack is used for a lot more than SYSENTER now. Give it a better string to display in stack dumps, and rename the kernel code to match. Also move the 32-bit code over to the new naming even though it still uses the entry stack only for SYSENTER. Signed-off-by:
Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by:
-
Peter Zijlstra authored
Signed-off-by:
-
Andy Lutomirski authored
The old docs had the vsyscall range wrong and were missing the fixmap. Fix both. There used to be 8 MB reserved for future vsyscalls, but that's long gone. Signed-off-by:
Andy Lutomirski <luto@kernel.org> Signed-off-by:
-
Thomas Gleixner authored
The LDT is inherited across fork() or exec(), but that makes no sense at all because exec() is supposed to start the process clean. The reason why this happens is that init_new_context_ldt() is called from init_new_context() which obviously needs to be called for both fork() and exec(). It would be surprising if anything relies on that behaviour, so it seems to be safe to remove that misfeature. Split the context initialization into two parts. Clear the LDT pointer and initialize the mutex from the general context init and move the LDT duplication to arch_dup_mmap() which is only called on fork(). Signed-off-by:
-
Peter Zijlstra authored
The LDT is duplicated on fork() and on exec(), which is wrong as exec() should start from a clean state, i.e. without LDT. To fix this the LDT duplication code will be moved into arch_dup_mmap() which is only called for fork(). This introduces a locking problem. arch_dup_mmap() holds mmap_sem of the parent process, but the LDT duplication code needs to acquire mm->context.lock to access the LDT data safely, which is the reverse lock order of write_ldt() where mmap_sem nests into context.lock. Solve this by introducing a new rw semaphore which serializes the read/write_ldt() syscall operations and use context.lock to protect the actual installment of the LDT descriptor. So context.lock stabilizes mm->context.ldt and can nest inside of the new semaphore or mmap_sem. Signed-off-by:
-
Thomas Gleixner authored
In order to sanitize the LDT initialization on x86 arch_dup_mmap() must be allowed to fail. Fix up all instances. Signed-off-by:
-
Andy Lutomirski authored
If something goes wrong with pagetable setup, vsyscall=native will accidentally fall back to emulation. Make it warn and fail so that we notice. Signed-off-by:
-
Andy Lutomirski authored
The kernel is very erratic as to which pagetables have _PAGE_USER set. The vsyscall page gets lucky: it seems that all of the relevant pagetables are among the apparently arbitrary ones that set _PAGE_USER. Rather than relying on chance, just explicitly set _PAGE_USER. This will let us clean up pagetable setup to stop setting _PAGE_USER. The added code can also be reused by pagetable isolation to manage the _PAGE_USER bit in the usermode tables. [ tglx: Folded paravirt fix from Juergen Gross ] Signed-off-by:
-
Thomas Gleixner authored
The address hints are a trainwreck. The array entry numbers have to kept magically in sync with the actual hints, which is doomed as some of the array members are initialized at runtime via the entry numbers. Designated initializers have been around before this code was implemented.... Use the entry numbers to populate the address hints array and add the missing bits and pieces. Split 32 and 64 bit for readability sake. Signed-off-by:
-
Thomas Gleixner authored
The check for a present page in printk_prot(): if (!pgprot_val(prot)) { /* Not present */ is bogus. If a PTE is set to PAGE_NONE then the pgprot_val is not zero and the entry is decoded in bogus ways, e.g. as RX GLB. That is confusing when analyzing mapping correctness. Check for the present bit to make an informed decision. Signed-off-by: -
Thomas Gleixner authored
The recent cpu_entry_area changes fail to compile on 32-bit when BIGSMP=y and NR_CPUS=512, because the fixmap area becomes too big. Limit the number of CPUs with BIGSMP to 64, which is already way to big for 32-bit, but it's at least a working limitation. We performed a quick survey of 32-bit-only machines that might be affected by this change negatively, but found none. Signed-off-by:
-
- 17 Dec, 2017 28 commits
-
-
Thomas Gleixner authored
There is currently no way to force CPU bug bits like CPU feature bits. That makes it impossible to set a bug bit once at boot and have it stick for all upcoming CPUs. Extend the force set/clear arrays to handle bug bits as well. Signed-off-by:
Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@kernel.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bpetkov@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Laight <David.Laight@aculab.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Eduardo Valentin <eduval@amazon.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Will Deacon <will.deacon@arm.com> Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150606.992156574@linutronix.deSigned-off-by:
-
Thomas Gleixner authored
There is no generic way to test whether a kernel is running on a specific hypervisor. But that's required to prevent the upcoming user address space separation feature in certain guest modes. Make the hypervisor type enum unconditionally available and provide a helper function which allows to test for a specific type. Signed-off-by:
Juergen Gross <jgross@suse.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bpetkov@suse.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Laight <David.Laight@aculab.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Eduardo Valentin <eduval@amazon.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Will Deacon <will.deacon@arm.com> Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150606.912938129@linutronix.deSigned-off-by:
-
Thomas Gleixner authored
native_flush_tlb_single() will be changed with the upcoming PAGE_TABLE_ISOLATION feature. This requires to have more code in there than INVLPG. Remove the paravirt patching for it. Signed-off-by:
Josh Poimboeuf <jpoimboe@redhat.com> Reviewed-by:
-
Andy Lutomirski authored
The TSS is a fairly juicy target for exploits, and, now that the TSS is in the cpu_entry_area, it's no longer protected by kASLR. Make it read-only on x86_64. On x86_32, it can't be RO because it's written by the CPU during task switches, and we use a task gate for double faults. I'd also be nervous about errata if we tried to make it RO even on configurations without double fault handling. [ tglx: AMD confirmed that there is no problem on 64-bit with TSS RO. So it's probably safe to assume that it's a non issue, though Intel might have been creative in that area. Still waiting for confirmation. ] Signed-off-by:
Borislav Petkov <bpetkov@suse.de> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Laight <David.Laight@aculab.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Eduardo Valentin <eduval@amazon.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Will Deacon <will.deacon@arm.com> Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150606.733700132@linutronix.deSigned-off-by:
-
Andy Lutomirski authored
The existing code was a mess, mainly because C arrays are nasty. Turn SYSENTER_stack into a struct, add a helper to find it, and do all the obvious cleanups this enables. Signed-off-by:
-
Andy Lutomirski authored
Now that the SYSENTER stack has a guard page, there's no need for a canary to detect overflow after the fact. Signed-off-by:
-
Andy Lutomirski authored
The IST stacks are needed when an IST exception occurs and are accessed before any kernel code at all runs. Move them into struct cpu_entry_area. The IST stacks are unlike the rest of cpu_entry_area: they're used even for entries from kernel mode. This means that they should be set up before we load the final IDT. Move cpu_entry_area setup to trap_init() for the boot CPU and set it up for all possible CPUs at once in native_smp_prepare_cpus(). Signed-off-by:
-
Andy Lutomirski authored
Handling SYSCALL is tricky: the SYSCALL handler is entered with every single register (except FLAGS), including RSP, live. It somehow needs to set RSP to point to a valid stack, which means it needs to save the user RSP somewhere and find its own stack pointer. The canonical way to do this is with SWAPGS, which lets us access percpu data using the %gs prefix. With PAGE_TABLE_ISOLATION-like pagetable switching, this is problematic. Without a scratch register, switching CR3 is impossible, so %gs-based percpu memory would need to be mapped in the user pagetables. Doing that without information leaks is difficult or impossible. Instead, use a different sneaky trick. Map a copy of the first part of the SYSCALL asm at a different address for each CPU. Now RIP varies depending on the CPU, so we can use RIP-relative memory access to access percpu memory. By putting the relevant information (one scratch slot and the stack address) at a constant offset relative to RIP, we can make SYSCALL work without relying on %gs. A nice thing about this approach is that we can easily switch it on and off if we want pagetable switching to be configurable. The compat variant of SYSCALL doesn't have this problem in the first place -- there are plenty of scratch registers, since we don't care about preserving r8-r15. This patch therefore doesn't touch SYSCALL32 at all. This patch actually seems to be a small speedup. With this patch, SYSCALL touches an extra cache line and an extra virtual page, but the pipeline no longer stalls waiting for SWAPGS. It seems that, at least in a tight loop, the latter outweights the former. Thanks to David Laight for an optimization tip. Signed-off-by:
-
Andy Lutomirski authored
By itself, this is useless. It gives us the ability to run some final code before exit that cannnot run on the kernel stack. This could include a CR3 switch a la PAGE_TABLE_ISOLATION or some kernel stack erasing, for example. (Or even weird things like *changing* which kernel stack gets used as an ASLR-strengthening mechanism.) The SYSRET32 path is not covered yet. It could be in the future or we could just ignore it and force the slow path if needed. Signed-off-by:
-
Andy Lutomirski authored
Historically, IDT entries from usermode have always gone directly to the running task's kernel stack. Rearrange it so that we enter on a per-CPU trampoline stack and then manually switch to the task's stack. This touches a couple of extra cachelines, but it gives us a chance to run some code before we touch the kernel stack. The asm isn't exactly beautiful, but I think that fully refactoring it can wait. Signed-off-by:
-
Andy Lutomirski authored
When we start using an entry trampoline, a #GP from userspace will be delivered on the entry stack, not on the task stack. Fix the espfix64 #DF fixup to set up #GP according to TSS.SP0, rather than assuming that pt_regs + 1 == SP0. This won't change anything without an entry stack, but it will make the code continue to work when an entry stack is added. While we're at it, improve the comments to explain what's actually going on. Signed-off-by:
-
Andy Lutomirski authored
On 64-bit kernels, we used to assume that TSS.sp0 was the current top of stack. With the addition of an entry trampoline, this will no longer be the case. Store the current top of stack in TSS.sp1, which is otherwise unused but shares the same cacheline. Signed-off-by:
-
Andy Lutomirski authored
This has a secondary purpose: it puts the entry stack into a region with a well-controlled layout. A subsequent patch will take advantage of this to streamline the SYSCALL entry code to be able to find it more easily. Signed-off-by:
-
Andy Lutomirski authored
SYSENTER_stack should have reliable overflow detection, which means that it needs to be at the bottom of a page, not the top. Move it to the beginning of struct tss_struct and page-align it. Also add an assertion to make sure that the fixed hardware TSS doesn't cross a page boundary. Signed-off-by:
-
Andy Lutomirski authored
We currently special-case stack overflow on the task stack. We're going to start putting special stacks in the fixmap with a custom layout, so they'll have guard pages, too. Teach the unwinder to be able to unwind an overflow of any of the stacks. Signed-off-by:
-
Andy Lutomirski authored
A future patch will move SYSENTER_stack to the beginning of cpu_tss to help detect overflow. Before this can happen, fix several code paths that hardcode assumptions about the old layout. Signed-off-by:
Dave Hansen <dave.hansen@intel.com> Reviewed-by:
-
Andy Lutomirski authored
The cpu_entry_area will contain stacks. Make sure that KASAN has appropriate shadow mappings for them. Signed-off-by:
Andrey Ryabinin <aryabinin@virtuozzo.com> Signed-off-by:
-
Andy Lutomirski authored
Currently, the GDT is an ad-hoc array of pages, one per CPU, in the fixmap. Generalize it to be an array of a new 'struct cpu_entry_area' so that we can cleanly add new things to it. Signed-off-by:
-
Andy Lutomirski authored
We currently have CPU 0's GDT at the top of the GDT range and higher-numbered CPUs at lower addresses. This happens because the fixmap is upside down (index 0 is the top of the fixmap). Flip it so that GDTs are in ascending order by virtual address. This will simplify a future patch that will generalize the GDT remap to contain multiple pages. Signed-off-by:
-
Andy Lutomirski authored
get_stack_info() doesn't currently know about the SYSENTER stack, so unwinding will fail if we entered the kernel on the SYSENTER stack and haven't fully switched off. Teach get_stack_info() about the SYSENTER stack. With future patches applied that run part of the entry code on the SYSENTER stack and introduce an intentional BUG(), I would get: PANIC: double fault, error_code: 0x0 ... RIP: 0010:do_error_trap+0x33/0x1c0 ... Call Trace: Code: ... With this patch, I get: PANIC: double fault, error_code: 0x0 ... Call Trace: <SYSENTER> ? async_page_fault+0x36/0x60 ? invalid_op+0x22/0x40 ? async_page_fault+0x36/0x60 ? sync_regs+0x3c/0x40 ? sync_regs+0x2e/0x40 ? error_entry+0x6c/0xd0 ? async_page_fault+0x36/0x60 </SYSENTER> Code: ... which is a lot more informative. Signed-off-by:
-
Andy Lutomirski authored
This will simplify future changes that want scratch variables early in the SYSENTER handler -- they'll be able to spill registers to the stack. It also lets us get rid of a SWAPGS_UNSAFE_STACK user. This does not depend on CONFIG_IA32_EMULATION=y because we'll want the stack space even without IA32 emulation. As far as I can tell, the reason that this wasn't done from day 1 is that we use IST for #DB and #BP, which is IMO rather nasty and causes a lot more problems than it solves. But, since #DB uses IST, we don't actually need a real stack for SYSENTER (because SYSENTER with TF set will invoke #DB on the IST stack rather than the SYSENTER stack). I want to remove IST usage from these vectors some day, and this patch is a prerequisite for that as well. Signed-off-by:
-
Andy Lutomirski authored
In case something goes wrong with unwind (not unlikely in case of overflow), print the offending IP where we detected the overflow. Signed-off-by:
-
Andy Lutomirski authored
That race has been fixed and code cleaned up for a while now. Signed-off-by:
-
Josh Poimboeuf authored
There are at least two unwinder bugs hindering the debugging of stack-overflow crashes: - It doesn't deal gracefully with the case where the stack overflows and the stack pointer itself isn't on a valid stack but the to-be-dereferenced data *is*. - The ORC oops dump code doesn't know how to print partial pt_regs, for the case where if we get an interrupt/exception in *early* entry code before the full pt_regs have been saved. Fix both issues. http://lkml.kernel.org/r/20171126024031.uxi4numpbjm5rlbr@trebleSigned-off-by:
-
Andy Lutomirski authored
If the stack overflows into a guard page and the ORC unwinder should work well: by construction, there can't be any meaningful data in the guard page because no writes to the guard page will have succeeded. But there is a bug that prevents unwinding from working correctly: if the starting register state has RSP pointing into a stack guard page, the ORC unwinder bails out immediately. Instead of bailing out immediately check whether the next page up is a valid check page and if so analyze that. As a result the ORC unwinder will start the unwind. Tested by intentionally overflowing the task stack. The result is an accurate call trace instead of a trace consisting purely of '?' entries. There are a few other bugs that are triggered if the unwinder encounters a stack overflow after the first step, but they are outside the scope of this fix. Signed-off-by:
-
Boris Ostrovsky authored
Commit 1d3e53e8 ("x86/entry/64: Refactor IRQ stacks and make them NMI-safe") added DEBUG_ENTRY_ASSERT_IRQS_OFF macro that acceses eflags using 'pushfq' instruction when testing for IF bit. On PV Xen guests looking at IF flag directly will always see it set, resulting in 'ud2'. Introduce SAVE_FLAGS() macro that will use appropriate save_fl pv op when running paravirt. Signed-off-by:
Boris Ostrovsky <boris.ostrovsky@oracle.com> Signed-off-by:
-
Andrey Ryabinin authored
[ Note, this is a Git cherry-pick of the following commit: d17a1d97: ("x86/mm/kasan: don't use vmemmap_populate() to initialize shadow") ... for easier x86 PTI code testing and back-porting. ] The KASAN shadow is currently mapped using vmemmap_populate() since that provides a semi-convenient way to map pages into init_top_pgt. However, since that no longer zeroes the mapped pages, it is not suitable for KASAN, which requires zeroed shadow memory. Add kasan_populate_shadow() interface and use it instead of vmemmap_populate(). Besides, this allows us to take advantage of gigantic pages and use them to populate the shadow, which should save us some memory wasted on page tables and reduce TLB pressure. Link: http://lkml.kernel.org/r/20171103185147.2688-2-pasha.tatashin@oracle.comSigned-off-by:Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Steven Sistare <steven.sistare@oracle.com> Cc: Daniel Jordan <daniel.m.jordan@oracle.com> Cc: Bob Picco <bob.picco@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Alexander Potapenko <glider@google.com> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: David S. Miller <davem@davemloft.net> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@kernel.org> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by:
-
Will Deacon authored
[ Note, this is a Git cherry-pick of the following commit: 506458ef ("locking/barriers: Convert users of lockless_dereference() to READ_ONCE()") ... for easier x86 PTI code testing and back-porting. ] READ_ONCE() now has an implicit smp_read_barrier_depends() call, so it can be used instead of lockless_dereference() without any change in semantics. Signed-off-by:Will Deacon <will.deacon@arm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1508840570-22169-4-git-send-email-will.deacon@arm.comSigned-off-by:
-
