This change has the following effects, in order of descreasing importance:
1) Prevent a stack buffer overflow
2) Do not append an unnecessary NULL to an anyway binary buffer, which
is writing one byte past client_digest when caller is:
chap_string_to_hex(client_digest, chap_r, strlen(chap_r));
The latter was found by KASAN (see below) when input value hes expected size
(32 hex chars), and further analysis revealed a stack buffer overflow can
happen when network-received value is longer, allowing an unauthenticated
remote attacker to smash up to 17 bytes after destination buffer (16 bytes
attacker-controlled and one null). As switching to hex2bin requires
specifying destination buffer length, and does not internally append any null,
it solves both issues.
This addresses CVE-2018-14633.
Beyond this:
- Validate received value length and check hex2bin accepted the input, to log
this rejection reason instead of just failing authentication.
- Only log received CHAP_R and CHAP_C values once they passed sanity checks.
==================================================================
BUG: KASAN: stack-out-of-bounds in chap_string_to_hex+0x32/0x60 [iscsi_target_mod]
Write of size 1 at addr ffff8801090ef7c8 by task kworker/0:0/1021
Signed-off-by: Vincent Pelletier <plr.vincent@gmail.com> Reviewed-by: Mike Christie <mchristi@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The final field of a floppy_struct is the field "name", which is a pointer
to a string in kernel memory. The kernel pointer should not be copied to
user memory. The FDGETPRM ioctl copies a floppy_struct to user memory,
including this "name" field. This pointer cannot be used by the user
and it will leak a kernel address to user-space, which will reveal the
location of kernel code and data and undermine KASLR protection.
Model this code after the compat ioctl which copies the returned data
to a previously cleared temporary structure on the stack (excluding the
name pointer) and copy out to userspace from there. As we already have
an inparam union with an appropriate member and that memory is already
cleared even for read only calls make use of that as a temporary store.
Based on an initial patch by Brian Belleville.
CVE-2018-7755 Signed-off-by: Andy Whitcroft <apw@canonical.com>
Broke up long line.
Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
irda: Only insert new objects into the global database via setsockopt
The irda_setsockopt() function conditionally allocates memory for a new
self->ias_object or, in some cases, reuses the existing
self->ias_object. Existing objects were incorrectly reinserted into the
LM_IAS database which corrupted the doubly linked list used for the
hashbin implementation of the LM_IAS database. When combined with a
memory leak in irda_bind(), this issue could be leveraged to create a
use-after-free vulnerability in the hashbin list. This patch fixes the
issue by only inserting newly allocated objects into the database.
CVE-2018-6555
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Tyler Hicks <tyhicks@canonical.com> Reviewed-by: Seth Arnold <seth.arnold@canonical.com> Reviewed-by: Stefan Bader <stefan.bader@canonical.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
irda: Fix memory leak caused by repeated binds of irda socket
The irda_bind() function allocates memory for self->ias_obj without
checking to see if the socket is already bound. A userspace process
could repeatedly bind the socket, have each new object added into the
LM-IAS database, and lose the reference to the old object assigned to
the socket to exhaust memory resources. This patch errors out of the
bind operation when self->ias_obj is already assigned.
CVE-2018-6554
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Tyler Hicks <tyhicks@canonical.com> Reviewed-by: Seth Arnold <seth.arnold@canonical.com> Reviewed-by: Stefan Bader <stefan.bader@canonical.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
In file included from arch/x86/tools/relocs_64.c:17:0:
arch/x86/tools/relocs.c: In function ‘process_64’:
arch/x86/tools/relocs.c:953:2: warning: argument 1 null where non-null expected [-Wnonnull]
qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from arch/x86/tools/relocs.h:6:0,
from arch/x86/tools/relocs_64.c:1:
/usr/include/stdlib.h:741:13: note: in a call to function ‘qsort’ declared here
extern void qsort
This happens because relocs16 is not used for ELF_BITS == 64,
so there is no point in trying to sort it.
Make the sort_relocs(&relocs16) call 32bit only.
Signed-off-by: Markus Trippelsdorf <markus@trippelsdorf.de> Link: http://lkml.kernel.org/r/20161215124513.GA289@x4 Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
[bwh: Backported to 3.16: Also make sort_relocs(&relocs64) conditional,
which was done upstream in commit 6d24c5f72dfb "x86-64: Handle PC-relative
relocations on per-CPU data".] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The cuda_start() function uses spinlock_irq_save/restore for mutual
exclusion. Let's have cuda_poll() do the same when polling the VIA
interrupt.
The benefit to disabling local irqs when the interrupt is being polled
is that the interrupt handler now has the same timing properties
regardless of whether it is invoked normally or from cuda_poll().
This driver was written back when local irqs remained enabled during
execution of interrupt handlers and cuda_poll() was probably trying
to achieve the same effect by use of enable/disable_irq.
Tested-by: Stan Johnson <userm57@yahoo.com> Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
[bwh: Backported to 3.16: adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Two users have reported [1] that they have an "extremely unlikely" system
with more than MAX_PA/2 memory and L1TF mitigation is not effective.
Make the warning more helpful by suggesting the proper mem=X kernel boot
parameter to make it effective and a link to the L1TF document to help
decide if the mitigation is worth the unusable RAM.
The mmio tracer sets io mapping PTEs and PMDs to non present when enabled
without inverting the address bits, which makes the PTE entry vulnerable
for L1TF.
Make it use the right low level macros to actually invert the address bits
to protect against L1TF.
In principle this could be avoided because MMIO tracing is not likely to be
enabled on production machines, but the fix is straigt forward and for
consistency sake it's better to get rid of the open coded PTE manipulation.
Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
set_memory_np() is used to mark kernel mappings not present, but it has
it's own open coded mechanism which does not have the L1TF protection of
inverting the address bits.
Replace the open coded PTE manipulation with the L1TF protecting low level
PTE routines.
Passes the CPA self test.
Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
[bwh: Backported to 3.16:
- cpa->pfn is actually a physical address here and needs to be shifted to
produce a PFN
- Adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Some cases in THP like:
- MADV_FREE
- mprotect
- split
mark the PMD non present for temporarily to prevent races. The window for
an L1TF attack in these contexts is very small, but it wants to be fixed
for correctness sake.
Use the proper low level functions for pmd/pud_mknotpresent() to address
this.
Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
[bwh: Backported to 3.16:
- Drop change to pud_mknotpresent()
- pmd_mknotpresent() does not touch _PAGE_NONE] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Ben Hutchings [Sat, 29 Sep 2018 15:31:50 +0000 (16:31 +0100)]
x86/speculation/l1tf: Protect NUMA-balance entries against L1TF
NUMA balancing has its own functions that manipulated the PRESENT flag
in PTEs and PMDs. These were not affected by the changes in commit 6b28baca9b1f "x86/speculation/l1tf: Protect PROT_NONE PTEs against
speculation".
This is not a problem upstream because NUMA balancing was changed to
use {pte,pmd}_modify() in Linux 4.0.
Override the generic implementations for x86 with implementations
that do the same inversion as {pte,pmd}_modify().
Signed-off-by: Ben Hutchings <ben@decadent.org.uk> Cc: x86@kernel.org Cc: Mel Gorman <mgorman@suse.de>
It turns out that we should *not* invert all not-present mappings,
because the all zeroes case is obviously special.
clear_page() does not undergo the XOR logic to invert the address bits,
i.e. PTE, PMD and PUD entries that have not been individually written
will have val=0 and so will trigger __pte_needs_invert(). As a result,
{pte,pmd,pud}_pfn() will return the wrong PFN value, i.e. all ones
(adjusted by the max PFN mask) instead of zero. A zeroed entry is ok
because the page at physical address 0 is reserved early in boot
specifically to mitigate L1TF, so explicitly exempt them from the
inversion when reading the PFN.
Manifested as an unexpected mprotect(..., PROT_NONE) failure when called
on a VMA that has VM_PFNMAP and was mmap'd to as something other than
PROT_NONE but never used. mprotect() sends the PROT_NONE request down
prot_none_walk(), which walks the PTEs to check the PFNs.
prot_none_pte_entry() gets the bogus PFN from pte_pfn() and returns
-EACCES because it thinks mprotect() is trying to adjust a high MMIO
address.
[ This is a very modified version of Sean's original patch, but all
credit goes to Sean for doing this and also pointing out that
sometimes the __pte_needs_invert() function only gets the protection
bits, not the full eventual pte. But zero remains special even in
just protection bits, so that's ok. - Linus ]
Fixes: f22cc87f6c1f ("x86/speculation/l1tf: Invert all not present mappings") Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
For kernel mappings PAGE_PROTNONE is not necessarily set for a non present
mapping, but the inversion logic explicitely checks for !PRESENT and
PROT_NONE.
Remove the PROT_NONE check and make the inversion unconditional for all not
present mappings.
Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
pfn_modify_allowed() and arch_has_pfn_modify_check() are outside of the
!__ASSEMBLY__ section in include/asm-generic/pgtable.h, which confuses
assembler on archs that don't have __HAVE_ARCH_PFN_MODIFY_ALLOWED (e.g.
ia64) and breaks build:
include/asm-generic/pgtable.h: Assembler messages:
include/asm-generic/pgtable.h:538: Error: Unknown opcode `static inline bool pfn_modify_allowed(unsigned long pfn,pgprot_t prot)'
include/asm-generic/pgtable.h:540: Error: Unknown opcode `return true'
include/asm-generic/pgtable.h:543: Error: Unknown opcode `static inline bool arch_has_pfn_modify_check(void)'
include/asm-generic/pgtable.h:545: Error: Unknown opcode `return false'
arch/ia64/kernel/entry.S:69: Error: `mov' does not fit into bundle
Move those two static inlines into the !__ASSEMBLY__ section so that they
don't confuse the asm build pass.
Fixes: 42e4089c7890 ("x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings") Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[groeck: Context changes] Signed-off-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Jan has noticed that pte_pfn and co. resp. pfn_pte are incorrect for
CONFIG_PAE because phys_addr_t is wider than unsigned long and so the
pte_val reps. shift left would get truncated. Fix this up by using proper
types.
[dwmw2: Backport to 4.9]
Fixes: 6b28baca9b1f ("x86/speculation/l1tf: Protect PROT_NONE PTEs against speculation") Reported-by: Jan Beulich <JBeulich@suse.com> Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16: Adjust context. Also restore the fix to pfn_pud().] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Two users have reported [1] that they have an "extremely unlikely" system
with more than MAX_PA/2 memory and L1TF mitigation is not effective. In
fact it's a CPU with 36bits phys limit (64GB) and 32GB memory, but due to
holes in the e820 map, the main region is almost 500MB over the 32GB limit:
Suggestions to use 'mem=32G' to enable the L1TF mitigation while losing the
500MB revealed, that there's an off-by-one error in the check in
l1tf_select_mitigation().
l1tf_pfn_limit() returns the last usable pfn (inclusive) and the range
check in the mitigation path does not take this into account.
Instead of amending the range check, make l1tf_pfn_limit() return the first
PFN which is over the limit which is less error prone. Adjust the other
users accordingly.
On 32bit PAE kernels on 64bit hardware with enough physical bits,
l1tf_pfn_limit() will overflow unsigned long. This in turn affects
max_swapfile_size() and can lead to swapon returning -EINVAL. This has been
observed in a 32bit guest with 42 bits physical address size, where
max_swapfile_size() overflows exactly to 1 << 32, thus zero, and produces
the following warning to dmesg:
[ 6.396845] Truncating oversized swap area, only using 0k out of 2047996k
Fix this by using unsigned long long instead.
Fixes: 17dbca119312 ("x86/speculation/l1tf: Add sysfs reporting for l1tf") Fixes: 377eeaa8e11f ("x86/speculation/l1tf: Limit swap file size to MAX_PA/2") Reported-by: Dominique Leuenberger <dimstar@suse.de> Reported-by: Adrian Schroeter <adrian@suse.de> Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Andi Kleen <ak@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: "H . Peter Anvin" <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Michal Hocko <mhocko@kernel.org> Link: https://lkml.kernel.org/r/20180820095835.5298-1-vbabka@suse.cz Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The PAE 3-level paging code currently doesn't mitigate L1TF by flipping the
offset bits, and uses the high PTE word, thus bits 32-36 for type, 37-63 for
offset. The lower word is zeroed, thus systems with less than 4GB memory are
safe. With 4GB to 128GB the swap type selects the memory locations vulnerable
to L1TF; with even more memory, also the swap offfset influences the address.
This might be a problem with 32bit PAE guests running on large 64bit hosts.
By continuing to keep the whole swap entry in either high or low 32bit word of
PTE we would limit the swap size too much. Thus this patch uses the whole PAE
PTE with the same layout as the 64bit version does. The macros just become a
bit tricky since they assume the arch-dependent swp_entry_t to be 32bit.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Michal Hocko <mhocko@suse.com>
[bwh: Backported to 3.16: CONFIG_PGTABLE_LEVELS is not defined; use other
config symbols in the condition.] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The introduction of generic_max_swapfile_size and arch-specific versions has
broken linking on x86 with CONFIG_SWAP=n due to undefined reference to
'generic_max_swapfile_size'. Fix it by compiling the x86-specific
max_swapfile_size() only with CONFIG_SWAP=y.
Reported-by: Tomas Pruzina <pruzinat@gmail.com> Fixes: 377eeaa8e11f ("x86/speculation/l1tf: Limit swap file size to MAX_PA/2") Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
For the L1TF workaround its necessary to limit the swap file size to below
MAX_PA/2, so that the higher bits of the swap offset inverted never point
to valid memory.
Add a mechanism for the architecture to override the swap file size check
in swapfile.c and add a x86 specific max swapfile check function that
enforces that limit.
The check is only enabled if the CPU is vulnerable to L1TF.
In VMs with 42bit MAX_PA the typical limit is 2TB now, on a native system
with 46bit PA it is 32TB. The limit is only per individual swap file, so
it's always possible to exceed these limits with multiple swap files or
partitions.
Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
[bwh: Backported to 3.16: adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
For L1TF PROT_NONE mappings are protected by inverting the PFN in the page
table entry. This sets the high bits in the CPU's address space, thus
making sure to point to not point an unmapped entry to valid cached memory.
Some server system BIOSes put the MMIO mappings high up in the physical
address space. If such an high mapping was mapped to unprivileged users
they could attack low memory by setting such a mapping to PROT_NONE. This
could happen through a special device driver which is not access
protected. Normal /dev/mem is of course access protected.
To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings.
Valid page mappings are allowed because the system is then unsafe anyways.
It's not expected that users commonly use PROT_NONE on MMIO. But to
minimize any impact this is only enforced if the mapping actually refers to
a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip
the check for root.
For mmaps this is straight forward and can be handled in vm_insert_pfn and
in remap_pfn_range().
For mprotect it's a bit trickier. At the point where the actual PTEs are
accessed a lot of state has been changed and it would be difficult to undo
on an error. Since this is a uncommon case use a separate early page talk
walk pass for MMIO PROT_NONE mappings that checks for this condition
early. For non MMIO and non PROT_NONE there are no changes.
[dwmw2: Backport to 4.9]
[groeck: Backport to 4.4]
Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Current implementation of page table walker has a fundamental problem in
vma handling, which started when we tried to handle vma(VM_HUGETLB).
Because it's done in pgd loop, considering vma boundary makes code
complicated and bug-prone.
From the users viewpoint, some user checks some vma-related condition to
determine whether the user really does page walk over the vma.
In order to solve these, this patch moves vma check outside pgd loop and
introduce a new callback ->test_walk().
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.16 as dependency of L1TF mitigation] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Currently no user of page table walker sets ->pgd_entry() or
->pud_entry(), so checking their existence in each loop is just wasting
CPU cycle. So let's remove it to reduce overhead.
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.16 as dependency of L1TF mitigation] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
This fixes a regression in all these drivers since the cache
mode tracking was fixed for mixed mappings. It uses the new
arch API to add the VRAM range to the PAT mapping tracking
tables.
Fixes: 87744ab3832 (mm: fix cache mode tracking in vm_insert_mixed()) Reviewed-by: Christian König <christian.koenig@amd.com>. Signed-off-by: Dave Airlie <airlied@redhat.com>
[bwh: Backported to 3.16:
- Drop changes in amdgpu
- In nouveau, use struct nouveau_device * and nv_device_resource_{start,len}()
- Adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
A recent change to the mm code in: 87744ab3832b mm: fix cache mode tracking in vm_insert_mixed()
started enforcing checking the memory type against the registered list for
amixed pfn insertion mappings. It happens that the drm drivers for a number
of gpus relied on this being broken. Currently the driver only inserted
VRAM mappings into the tracking table when they came from the kernel,
and userspace mappings never landed in the table. This led to a regression
where all the mapping end up as UC instead of WC now.
I've considered a number of solutions but since this needs to be fixed
in fixes and not next, and some of the solutions were going to introduce
overhead that hadn't been there before I didn't consider them viable at
this stage. These mainly concerned hooking into the TTM io reserve APIs,
but these API have a bunch of fast paths I didn't want to unwind to add
this to.
The solution I've decided on is to add a new API like the arch_phys_wc
APIs (these would have worked but wc_del didn't take a range), and
use them from the drivers to add a WC compatible mapping to the table
for all VRAM on those GPUs. This means we can then create userspace
mapping that won't get degraded to UC.
v1.1: use CONFIG_X86_PAT + add some comments in io.h
Cc: Toshi Kani <toshi.kani@hp.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Brian Gerst <brgerst@gmail.com> Cc: x86@kernel.org Cc: mcgrof@suse.com Cc: Dan Williams <dan.j.williams@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Dave Airlie <airlied@redhat.com>
[bwh: Backported to 3.16: Memory types have type unsigned long, and the
constant is named _PAGE_CACHE_WC instead of _PAGE_CACHE_MODE_WC.] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
vm_insert_mixed() unlike vm_insert_pfn_prot() and vmf_insert_pfn_pmd(),
fails to check the pgprot_t it uses for the mapping against the one
recorded in the memtype tracking tree. Add the missing call to
track_pfn_insert() to preclude cases where incompatible aliased mappings
are established for a given physical address range.
[groeck: Backport to v4.4.y]
Link: http://lkml.kernel.org/r/147328717909.35069.14256589123570653697.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Cc: David Airlie <airlied@linux.ie> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The x86 vvar vma contains pages with differing cacheability
flags. x86 currently implements this by manually inserting all
the ptes using (io_)remap_pfn_range when the vma is set up.
x86 wants to move to using .fault with VM_FAULT_NOPAGE to set up
the mappings as needed. The correct API to use to insert a pfn
in .fault is vm_insert_pfn(), but vm_insert_pfn() can't override the
vma's cache mode, and the HPET page in particular needs to be
uncached despite the fact that the rest of the VMA is cached.
Add vm_insert_pfn_prot() to support varying cacheability within
the same non-COW VMA in a more sane manner.
x86 could alternatively use multiple VMAs, but that's messy,
would break CRIU, and would create unnecessary VMAs that would
waste memory.
Signed-off-by: Andy Lutomirski <luto@kernel.org> Reviewed-by: Kees Cook <keescook@chromium.org> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/d2938d1eb37be7a5e4f86182db646551f11e45aa.1451446564.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
L1TF core kernel workarounds are cheap and normally always enabled, However
they still should be reported in sysfs if the system is vulnerable or
mitigated. Add the necessary CPU feature/bug bits.
- Extend the existing checks for Meltdowns to determine if the system is
vulnerable. All CPUs which are not vulnerable to Meltdown are also not
vulnerable to L1TF
- Check for 32bit non PAE and emit a warning as there is no practical way
for mitigation due to the limited physical address bits
- If the system has more than MAX_PA/2 physical memory the invert page
workarounds don't protect the system against the L1TF attack anymore,
because an inverted physical address will also point to valid
memory. Print a warning in this case and report that the system is
vulnerable.
Add a function which returns the PFN limit for the L1TF mitigation, which
will be used in follow up patches for sanity and range checks.
[ tglx: Renamed the CPU feature bit to L1TF_PTEINV ]
[ dwmw2: Backport to 4.9 (cpufeatures.h, E820) ]
Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16:
- Assign the next available bits from feature word 7 and bug word 0
- CONFIG_PGTABLE_LEVELS is not defined; use other config symbols in the
condition
- Adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The L1TF workaround doesn't make any attempt to mitigate speculate accesses
to the first physical page for zeroed PTEs. Normally it only contains some
data from the early real mode BIOS.
It's not entirely clear that the first page is reserved in all
configurations, so add an extra reservation call to make sure it is really
reserved. In most configurations (e.g. with the standard reservations)
it's likely a nop.
Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
When PTEs are set to PROT_NONE the kernel just clears the Present bit and
preserves the PFN, which creates attack surface for L1TF speculation
speculation attacks.
This is important inside guests, because L1TF speculation bypasses physical
page remapping. While the host has its own migitations preventing leaking
data from other VMs into the guest, this would still risk leaking the wrong
page inside the current guest.
This uses the same technique as Linus' swap entry patch: while an entry is
is in PROTNONE state invert the complete PFN part part of it. This ensures
that the the highest bit will point to non existing memory.
The invert is done by pte/pmd_modify and pfn/pmd/pud_pte for PROTNONE and
pte/pmd/pud_pfn undo it.
This assume that no code path touches the PFN part of a PTE directly
without using these primitives.
This doesn't handle the case that MMIO is on the top of the CPU physical
memory. If such an MMIO region was exposed by an unpriviledged driver for
mmap it would be possible to attack some real memory. However this
situation is all rather unlikely.
For 32bit non PAE the inversion is not done because there are really not
enough bits to protect anything.
Q: Why does the guest need to be protected when the HyperVisor already has
L1TF mitigations?
A: Here's an example:
Physical pages 1 2 get mapped into a guest as
GPA 1 -> PA 2
GPA 2 -> PA 1
through EPT.
The L1TF speculation ignores the EPT remapping.
Now the guest kernel maps GPA 1 to process A and GPA 2 to process B, and
they belong to different users and should be isolated.
A sets the GPA 1 PA 2 PTE to PROT_NONE to bypass the EPT remapping and
gets read access to the underlying physical page. Which in this case
points to PA 2, so it can read process B's data, if it happened to be in
L1, so isolation inside the guest is broken.
There's nothing the hypervisor can do about this. This mitigation has to
be done in the guest itself.
[ tglx: Massaged changelog ]
Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Dave Hansen <dave.hansen@intel.com>
[bwh: Backported to 3.16:
- s/check_pgprot/massage_pgprot/
- Keep using PTE_PFN_MASK to extract PFN from pmd_pfn() and pud_pfn(),
as we don't need to worry about the PAT bit being set here] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
With L1 terminal fault the CPU speculates into unmapped PTEs, and resulting
side effects allow to read the memory the PTE is pointing too, if its
values are still in the L1 cache.
For swapped out pages Linux uses unmapped PTEs and stores a swap entry into
them.
To protect against L1TF it must be ensured that the swap entry is not
pointing to valid memory, which requires setting higher bits (between bit
36 and bit 45) that are inside the CPUs physical address space, but outside
any real memory.
To do this invert the offset to make sure the higher bits are always set,
as long as the swap file is not too big.
Note there is no workaround for 32bit !PAE, or on systems which have more
than MAX_PA/2 worth of memory. The later case is very unlikely to happen on
real systems.
[AK: updated description and minor tweaks by. Split out from the original
patch ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Dave Hansen <dave.hansen@intel.com>
[bwh: Backported to 3.16: Bit 9 may be reserved for PAGE_BIT_NUMA here] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
If pages are swapped out, the swap entry is stored in the corresponding
PTE, which has the Present bit cleared. CPUs vulnerable to L1TF speculate
on PTE entries which have the present bit set and would treat the swap
entry as phsyical address (PFN). To mitigate that the upper bits of the PTE
must be set so the PTE points to non existent memory.
The swap entry stores the type and the offset of a swapped out page in the
PTE. type is stored in bit 9-13 and offset in bit 14-63. The hardware
ignores the bits beyond the phsyical address space limit, so to make the
mitigation effective its required to start 'offset' at the lowest possible
bit so that even large swap offsets do not reach into the physical address
space limit bits.
Move offset to bit 9-58 and type to bit 59-63 which are the bits that
hardware generally doesn't care about.
That, in turn, means that if you on desktop chip with only 40 bits of
physical addressing, now that the offset starts at bit 9, there needs to be
30 bits of offset actually *in use* until bit 39 ends up being set, which
means when inverted it will again point into existing memory.
So that's 4 terabyte of swap space (because the offset is counted in pages,
so 30 bits of offset is 42 bits of actual coverage). With bigger physical
addressing, that obviously grows further, until the limit of the offset is
hit (at 50 bits of offset - 62 bits of actual swap file coverage).
This is a preparatory change for the actual swap entry inversion to protect
against L1TF.
[ AK: Updated description and minor tweaks. Split into two parts ]
[ tglx: Massaged changelog ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Dave Hansen <dave.hansen@intel.com>
[bwh: Backported to 3.16: Bit 9 may be reserved for PAGE_BIT_NUMA here] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
_PAGE_PSE is used to distinguish between a truly non-present
(_PAGE_PRESENT=0) PMD, and a PMD which is undergoing a THP split and
should be treated as present.
But _PAGE_SWP_SOFT_DIRTY currently uses the _PAGE_PSE bit, which would
cause confusion between one of those PMDs undergoing a THP split, and a
soft-dirty PMD. Dropping _PAGE_PSE check in pmd_present() does not work
well, because it can hurt optimization of tlb handling in thp split.
Thus, we need to move the bit.
In the current kernel, bits 1-4 are not used in non-present format since
commit 00839ee3b299 ("x86/mm: Move swap offset/type up in PTE to work
around erratum"). So let's move _PAGE_SWP_SOFT_DIRTY to bit 1. Bit 7
is used as reserved (always clear), so please don't use it for other
purpose.
Link: http://lkml.kernel.org/r/20170717193955.20207-3-zi.yan@sent.com Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Zi Yan <zi.yan@cs.rutgers.edu> Acked-by: Dave Hansen <dave.hansen@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Minchan Kim <minchan@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.16: Bit 9 may be reserved for PAGE_BIT_NUMA here] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
This erratum can result in Accessed/Dirty getting set by the hardware
when we do not expect them to be (on !Present PTEs).
Instead of trying to fix them up after this happens, we just
allow the bits to get set and try to ignore them. We do this by
shifting the layout of the bits we use for swap offset/type in
our 64-bit PTEs.
Note that D was already a don't care (X) even before. We just
move TYPE up and turn its old spot (which could be hit by the
A bit) into all don't cares.
We take 5 bits away from the offset, but that still leaves us
with 50 bits which lets us index into a 62-bit swapfile (4 EiB).
I think that's probably fine for the moment. We could
theoretically reclaim 5 of the bits (1, 2, 3, 4, 7) but it
doesn't gain us anything.
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Hansen <dave@sr71.net> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: dave.hansen@intel.com Cc: linux-mm@kvack.org Cc: mhocko@suse.com Link: http://lkml.kernel.org/r/20160708001911.9A3FD2B6@viggo.jf.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
[bwh: Backported to 3.16: Bit 9 may be reserved for PAGE_BIT_NUMA, which
no longer exists upstream. Adjust the bit numbers accordingly,
incorporating commit ace7fab7a6cd "x86/mm: Fix swap entry comment and
macro".] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
L1 Terminal Fault (L1TF) is a speculation related vulnerability. The CPU
speculates on PTE entries which do not have the PRESENT bit set, if the
content of the resulting physical address is available in the L1D cache.
The OS side mitigation makes sure that a !PRESENT PTE entry points to a
physical address outside the actually existing and cachable memory
space. This is achieved by inverting the upper bits of the PTE. Due to the
address space limitations this only works for 64bit and 32bit PAE kernels,
but not for 32bit non PAE.
This mitigation applies to both host and guest kernels, but in case of a
64bit host (hypervisor) and a 32bit PAE guest, inverting the upper bits of
the PAE address space (44bit) is not enough if the host has more than 43
bits of populated memory address space, because the speculation treats the
PTE content as a physical host address bypassing EPT.
The host (hypervisor) protects itself against the guest by flushing L1D as
needed, but pages inside the guest are not protected against attacks from
other processes inside the same guest.
For the guest the inverted PTE mask has to match the host to provide the
full protection for all pages the host could possibly map into the
guest. The hosts populated address space is not known to the guest, so the
mask must cover the possible maximal host address space, i.e. 52 bit.
On 32bit PAE the maximum PTE mask is currently set to 44 bit because that
is the limit imposed by 32bit unsigned long PFNs in the VMs. This limits
the mask to be below what the host could possible use for physical pages.
The L1TF PROT_NONE protection code uses the PTE masks to determine which
bits to invert to make sure the higher bits are set for unmapped entries to
prevent L1TF speculation attacks against EPT inside guests.
In order to invert all bits that could be used by the host, increase
__PHYSICAL_PAGE_SHIFT to 52 to match 64bit.
The real limit for a 32bit PAE kernel is still 44 bits because all Linux
PTEs are created from unsigned long PFNs, so they cannot be higher than 44
bits on a 32bit kernel. So these extra PFN bits should be never set. The
only users of this macro are using it to look at PTEs, so it's safe.
[ tglx: Massaged changelog ]
Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.16: adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Jeff Dike <jdike@addtoit.com> Cc: Richard Weinberger <richard@nod.at> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
This patch also increase number of bits availble for swap offset.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
This patch also increase number of bits availble for swap offset.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Richard Kuo <rkuo@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
This patch also adjust __SWP_TYPE_SHIFT, effectively increase size of
possible swap file to 128G.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Russell King <linux@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Dan Carpenter <dan.carpenter@oracle.com> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.16: Drop changes in mm/debug.c] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
We don't create non-linear mappings anymore. Let's drop code which
handles them in rmap.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.16:
- Deleted code is slightly different
- Adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
We have to handle non-linear mappings for /proc/PID/{smaps,clear_refs}
which is unused now. Let's drop it.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.16:
- Deleted code is slightly different
- Adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
We don't create non-linear mappings anymore. Let's drop code which
handles them on page fault.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.16:
- Deleted code is slightly different
- Adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
We have remap_file_pages(2) emulation in -mm tree for few release cycles
and we plan to have it mainline in v3.20. This patchset removes rest of
VM_NONLINEAR infrastructure.
Patches 1-8 take care about generic code. They are pretty
straight-forward and can be applied without other of patches.
Rest patches removes pte_file()-related stuff from architecture-specific
code. It usually frees up one bit in non-present pte. I've tried to reuse
that bit for swap offset, where I was able to figure out how to do that.
For obvious reason I cannot test all that arch-specific code and would
like to see acks from maintainers.
In total, remap_file_pages(2) required about 1.4K lines of not-so-trivial
kernel code. That's too much for functionality nobody uses.
Tested-by: Felipe Balbi <balbi@ti.com>
This patch (of 38):
We don't create non-linear mappings anymore. Let's drop code which
handles them on unmap/zap.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.16: adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The reason is that remap_file_pages() emulation assumes that the target
vma covers whole area we want to over map. That assumption is broken by
first remap_file_pages() call: it split the area into two vma.
The solution is to check next adjacent vmas, if they map the same file
with the same flags.
Fixes: c8d78c1823f4 ("mm: replace remap_file_pages() syscall with emulation") Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Grazvydas Ignotas <notasas@gmail.com> Tested-by: Grazvydas Ignotas <notasas@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
remap_file_pages(2) was invented to be able efficiently map parts of
huge file into limited 32-bit virtual address space such as in database
workloads.
Nonlinear mappings are pain to support and it seems there's no
legitimate use-cases nowadays since 64-bit systems are widely available.
Let's drop it and get rid of all these special-cased code.
The patch replaces the syscall with emulation which creates new VMA on
each remap_file_pages(), unless they it can be merged with an adjacent
one.
I didn't find *any* real code that uses remap_file_pages(2) to test
emulation impact on. I've checked Debian code search and source of all
packages in ALT Linux. No real users: libc wrappers, mentions in
strace, gdb, valgrind and this kind of stuff.
There are few basic tests in LTP for the syscall. They work just fine
with emulation.
To test performance impact, I've written small test case which
demonstrate pretty much worst case scenario: map 4G shmfs file, write to
begin of every page pgoff of the page, remap pages in reverse order,
read every page.
The test creates 1 million of VMAs if emulation is in use, so I had to
set vm.max_map_count to 1100000 to avoid -ENOMEM.
Ben Hutchings [Thu, 27 Sep 2018 20:31:31 +0000 (21:31 +0100)]
x86/cpufeatures: Show KAISER in cpuinfo
I noticed that in the upstream kernel PTI is exposed in /proc/cpuinfo
and in the 4.4 and 4.9 stable branches KAISER is exposed similarly,
but for some reason the backport to 3.16 hid it. Change to match the
other branches.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
WARNING: possible irq lock inversion dependency detected
CPU 0/KVM/10284 just changed the state of lock: 000000000d538a88 (&st->lock){+...}, at:
speculative_store_bypass_update+0x10b/0x170
but this lock was taken by another, HARDIRQ-safe lock
in the past:
(&(&sighand->siglock)->rlock){-.-.}
and interrupts could create inverse lock ordering between them.
In svm_vcpu_run() speculative_store_bypass_update() is called with
interupts enabled via x86_virt_spec_ctrl_set_guest/host().
This is actually a false positive, because GIF=0 so interrupts are
disabled even if IF=1; however, we can easily move the invocations of
x86_virt_spec_ctrl_set_guest/host() into the interrupt disabled region to
cure it, and it's a good idea to keep the GIF=0/IF=1 area as small
and self-contained as possible.
Fixes: 1f50ddb4f418 ("x86/speculation: Handle HT correctly on AMD") Reported-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com> Cc: Joerg Roedel <joro@8bytes.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Borislav Petkov <bp@suse.de> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: kvm@vger.kernel.org Cc: x86@kernel.org Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The X86_FEATURE_SSBD is an synthetic CPU feature - that is
it bit location has no relevance to the real CPUID 0x7.EBX[31]
bit position. For that we need the new CPU feature name.
Fixes: 52817587e706 ("x86/cpufeatures: Disentangle SSBD enumeration") Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: kvm@vger.kernel.org Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Link: https://lkml.kernel.org/r/20180521215449.26423-2-konrad.wilk@oracle.com
[bwh: Backported to 3.16:
- Fix guest_cpuid_has_spec_ctrl() as well
- Adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Expose the new virtualized architectural mechanism, VIRT_SSBD, for using
speculative store bypass disable (SSBD) under SVM. This will allow guests
to use SSBD on hardware that uses non-architectural mechanisms for enabling
SSBD.
[ tglx: Folded the migration fixup from Paolo Bonzini ]
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16:
- There is no SMM support or cpu_has_high_real_mode_segbase operation
- Adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Add the necessary logic for supporting the emulated VIRT_SPEC_CTRL MSR to
x86_virt_spec_ctrl(). If either X86_FEATURE_LS_CFG_SSBD or
X86_FEATURE_VIRT_SPEC_CTRL is set then use the new guest_virt_spec_ctrl
argument to check whether the state must be modified on the host. The
update reuses speculative_store_bypass_update() so the ZEN-specific sibling
coordination can be reused.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
x86_spec_ctrL_mask is intended to mask out bits from a MSR_SPEC_CTRL value
which are not to be modified. However the implementation is not really used
and the bitmask was inverted to make a check easier, which was removed in
"x86/bugs: Remove x86_spec_ctrl_set()"
Aside of that it is missing the STIBP bit if it is supported by the
platform, so if the mask would be used in x86_virt_spec_ctrl() then it
would prevent a guest from setting STIBP.
Add the STIBP bit if supported and use the mask in x86_virt_spec_ctrl() to
sanitize the value which is supplied by the guest.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Borislav Petkov <bp@suse.de> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16: adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
x86_spec_ctrl_set() is only used in bugs.c and the extra mask checks there
provide no real value as both call sites can just write x86_spec_ctrl_base
to MSR_SPEC_CTRL. x86_spec_ctrl_base is valid and does not need any extra
masking or checking.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Borislav Petkov <bp@suse.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
x86_spec_ctrl_base is the system wide default value for the SPEC_CTRL MSR.
x86_spec_ctrl_get_default() returns x86_spec_ctrl_base and was intended to
prevent modification to that variable. Though the variable is read only
after init and globaly visible already.
Remove the function and export the variable instead.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Borislav Petkov <bp@suse.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16: adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Function bodies are very similar and are going to grow more almost
identical code. Add a bool arg to determine whether SPEC_CTRL is being set
for the guest or restored to the host.
No functional changes.
Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The upcoming support for the virtual SPEC_CTRL MSR on AMD needs to reuse
speculative_store_bypass_update() to avoid code duplication. Add an
argument for supplying a thread info (TIF) value and create a wrapper
speculative_store_bypass_update_current() which is used at the existing
call site.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Borislav Petkov <bp@suse.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Some AMD processors only support a non-architectural means of enabling
speculative store bypass disable (SSBD). To allow a simplified view of
this to a guest, an architectural definition has been created through a new
CPUID bit, 0x80000008_EBX[25], and a new MSR, 0xc001011f. With this, a
hypervisor can virtualize the existence of this definition and provide an
architectural method for using SSBD to a guest.
Add the new CPUID feature, the new MSR and update the existing SSBD
support to use this MSR when present.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Borislav Petkov <bp@suse.de> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16:
- This CPUID word is feature word 11
- Adjust filenames, context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
AMD is proposing a VIRT_SPEC_CTRL MSR to handle the Speculative Store
Bypass Disable via MSR_AMD64_LS_CFG so that guests do not have to care
about the bit position of the SSBD bit and thus facilitate migration.
Also, the sibling coordination on Family 17H CPUs can only be done on
the host.
Extend x86_spec_ctrl_set_guest() and x86_spec_ctrl_restore_host() with an
extra argument for the VIRT_SPEC_CTRL MSR.
Hand in 0 from VMX and in SVM add a new virt_spec_ctrl member to the CPU
data structure which is going to be used in later patches for the actual
implementation.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Borislav Petkov <bp@suse.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The AMD64_LS_CFG MSR is a per core MSR on Family 17H CPUs. That means when
hyperthreading is enabled the SSBD bit toggle needs to take both cores into
account. Otherwise the following situation can happen:
CPU0 CPU1
disable SSB
disable SSB
enable SSB <- Enables it for the Core, i.e. for CPU0 as well
So after the SSB enable on CPU1 the task on CPU0 runs with SSB enabled
again.
On Intel the SSBD control is per core as well, but the synchronization
logic is implemented behind the per thread SPEC_CTRL MSR. It works like
this:
i.e. if one of the threads enables a mitigation then this affects both and
the mitigation is only disabled in the core when both threads disabled it.
Add the necessary synchronization logic for AMD family 17H. Unfortunately
that requires a spinlock to serialize the access to the MSR, but the locks
are only shared between siblings.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Borislav Petkov <bp@suse.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16:
- s/topology_sibling_cpumask/topology_thread_cpumask/
- Adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Add a ZEN feature bit so family-dependent static_cpu_has() optimizations
can be built for ZEN.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Borislav Petkov <bp@suse.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16:
- Use the next available bit number in CPU feature word 7
- Adjust filename, context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The SSBD enumeration is similarly to the other bits magically shared
between Intel and AMD though the mechanisms are different.
Make X86_FEATURE_SSBD synthetic and set it depending on the vendor specific
features or family dependent setup.
Change the Intel bit to X86_FEATURE_SPEC_CTRL_SSBD to denote that SSBD is
controlled via MSR_SPEC_CTRL and fix up the usage sites.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Borislav Petkov <bp@suse.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16:
- Use the next available bit number in CPU feature word 7
- Adjust filename, context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
The availability of the SPEC_CTRL MSR is enumerated by a CPUID bit on
Intel and implied by IBRS or STIBP support on AMD. That's just confusing
and in case an AMD CPU has IBRS not supported because the underlying
problem has been fixed but has another bit valid in the SPEC_CTRL MSR,
the thing falls apart.
Add a synthetic feature bit X86_FEATURE_MSR_SPEC_CTRL to denote the
availability on both Intel and AMD.
While at it replace the boot_cpu_has() checks with static_cpu_has() where
possible. This prevents late microcode loading from exposing SPEC_CTRL, but
late loading is already very limited as it does not reevaluate the
mitigation options and other bits and pieces. Having static_cpu_has() is
the simplest and least fragile solution.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Borislav Petkov <bp@suse.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16:
- Use the next available bit number in CPU feature word 7
- Adjust filename, context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Intel and AMD have different CPUID bits hence for those use synthetic bits
which get set on the respective vendor's in init_speculation_control(). So
that debacles like what the commit message of
Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Tested-by: Jörg Otte <jrg.otte@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Link: https://lkml.kernel.org/r/20180504161815.GG9257@pd.tnic Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.16:
- Use the next available bit numbers in CPU feature word 7
- Adjust filename, context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>