When the system runs out of enclave memory, SGX can reclaim EPC pages
by swapping to normal RAM. These backing pages are allocated via a
per-enclave shared memory area. Since SGX allows unlimited over
commit on EPC memory, the reclaimer thread can allocate a large
number of backing RAM pages in response to EPC memory pressure.
When the shared memory backing RAM allocation occurs during
the reclaimer thread context, the shared memory is charged to
the root memory control group, and the shmem usage of the enclave
is not properly accounted for, making cgroups ineffective at
limiting the amount of RAM an enclave can consume.
For example, when using a cgroup to launch a set of test
enclaves, the kernel does not properly account for 50% - 75% of
shmem page allocations on average. In the worst case, when
nearly all allocations occur during the reclaimer thread, the
kernel accounts less than a percent of the amount of shmem used
by the enclave's cgroup to the correct cgroup.
SGX stores a list of mm_structs that are associated with
an enclave. Pick one of them during reclaim and charge that
mm's memcg with the shmem allocation. The one that gets picked
is arbitrary, but this list almost always only has one mm. The
cases where there is more than one mm with different memcg's
are not worth considering.
Create a new function - sgx_encl_alloc_backing(). This function
is used whenever a new backing storage page needs to be
allocated. Previously the same function was used for page
allocation as well as retrieving a previously allocated page.
Prior to backing page allocation, if there is a mm_struct associated
with the enclave that is requesting the allocation, it is set
as the active memory control group.
[ dhansen: - fix merge conflict with ELDU fixes
- check against actual ksgxd_tsk, not ->mm ]
Cc: stable@vger.kernel.org
Signed-off-by: Kristen Carlson Accardi <kristen@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://lkml.kernel.org/r/20220520174248.4918-1-kristen@linux.intel.com
A PCMD (Paging Crypto MetaData) page contains the PCMD
structures of enclave pages that have been encrypted and
moved to the shmem backing store. When all enclave pages
sharing a PCMD page are loaded in the enclave, there is no
need for the PCMD page and it can be truncated from the
backing store.
A few issues appeared around the truncation of PCMD pages. The
known issues have been addressed but the PCMD handling code could
be made more robust by loudly complaining if any new issue appears
in this area.
Add a check that will complain with a warning if the PCMD page is not
actually empty after it has been truncated. There should never be data
in the PCMD page at this point since it is was just checked to be empty
and truncated with enclave mutex held and is updated with the
enclave mutex held.
Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Haitao Huang <haitao.huang@intel.com>
Link: https://lkml.kernel.org/r/6495120fed43fafc1496d09dd23df922b9a32709.1652389823.git.reinette.chatre@intel.com
Haitao reported encountering a WARN triggered by the ENCLS[ELDU]
instruction faulting with a #GP.
The WARN is encountered when the reclaimer evicts a range of
pages from the enclave when the same pages are faulted back right away.
Consider two enclave pages (ENCLAVE_A and ENCLAVE_B)
sharing a PCMD page (PCMD_AB). ENCLAVE_A is in the
enclave memory and ENCLAVE_B is in the backing store. PCMD_AB contains
just one entry, that of ENCLAVE_B.
Scenario proceeds where ENCLAVE_A is being evicted from the enclave
while ENCLAVE_B is faulted in.
sgx_reclaim_pages() {
...
/*
* Reclaim ENCLAVE_A
*/
mutex_lock(&encl->lock);
/*
* Get a reference to ENCLAVE_A's
* shmem page where enclave page
* encrypted data will be stored
* as well as a reference to the
* enclave page's PCMD data page,
* PCMD_AB.
* Release mutex before writing
* any data to the shmem pages.
*/
sgx_encl_get_backing(...);
encl_page->desc |= SGX_ENCL_PAGE_BEING_RECLAIMED;
mutex_unlock(&encl->lock);
/*
* Fault ENCLAVE_B
*/
sgx_vma_fault() {
mutex_lock(&encl->lock);
/*
* Get reference to
* ENCLAVE_B's shmem page
* as well as PCMD_AB.
*/
sgx_encl_get_backing(...)
/*
* Load page back into
* enclave via ELDU.
*/
/*
* Release reference to
* ENCLAVE_B' shmem page and
* PCMD_AB.
*/
sgx_encl_put_backing(...);
/*
* PCMD_AB is found empty so
* it and ENCLAVE_B's shmem page
* are truncated.
*/
/* Truncate ENCLAVE_B backing page */
sgx_encl_truncate_backing_page();
/* Truncate PCMD_AB */
sgx_encl_truncate_backing_page();
mutex_unlock(&encl->lock);
...
}
mutex_lock(&encl->lock);
encl_page->desc &=
~SGX_ENCL_PAGE_BEING_RECLAIMED;
/*
* Write encrypted contents of
* ENCLAVE_A to ENCLAVE_A shmem
* page and its PCMD data to
* PCMD_AB.
*/
sgx_encl_put_backing(...)
/*
* Reference to PCMD_AB is
* dropped and it is truncated.
* ENCLAVE_A's PCMD data is lost.
*/
mutex_unlock(&encl->lock);
}
What happens next depends on whether it is ENCLAVE_A being faulted
in or ENCLAVE_B being evicted - but both end up with ENCLS[ELDU] faulting
with a #GP.
If ENCLAVE_A is faulted then at the time sgx_encl_get_backing() is called
a new PCMD page is allocated and providing the empty PCMD data for
ENCLAVE_A would cause ENCLS[ELDU] to #GP
If ENCLAVE_B is evicted first then a new PCMD_AB would be allocated by the
reclaimer but later when ENCLAVE_A is faulted the ENCLS[ELDU] instruction
would #GP during its checks of the PCMD value and the WARN would be
encountered.
Noting that the reclaimer sets SGX_ENCL_PAGE_BEING_RECLAIMED at the time
it obtains a reference to the backing store pages of an enclave page it
is in the process of reclaiming, fix the race by only truncating the PCMD
page after ensuring that no page sharing the PCMD page is in the process
of being reclaimed.
Cc: stable@vger.kernel.org
Fixes: 08999b2489 ("x86/sgx: Free backing memory after faulting the enclave page")
Reported-by: Haitao Huang <haitao.huang@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Haitao Huang <haitao.huang@intel.com>
Link: https://lkml.kernel.org/r/ed20a5db516aa813873268e125680041ae11dfcf.1652389823.git.reinette.chatre@intel.com
Haitao reported encountering a WARN triggered by the ENCLS[ELDU]
instruction faulting with a #GP.
The WARN is encountered when the reclaimer evicts a range of
pages from the enclave when the same pages are faulted back
right away.
The SGX backing storage is accessed on two paths: when there
are insufficient free pages in the EPC the reclaimer works
to move enclave pages to the backing storage and as enclaves
access pages that have been moved to the backing storage
they are retrieved from there as part of page fault handling.
An oversubscribed SGX system will often run the reclaimer and
page fault handler concurrently and needs to ensure that the
backing store is accessed safely between the reclaimer and
the page fault handler. This is not the case because the
reclaimer accesses the backing store without the enclave mutex
while the page fault handler accesses the backing store with
the enclave mutex.
Consider the scenario where a page is faulted while a page sharing
a PCMD page with the faulted page is being reclaimed. The
consequence is a race between the reclaimer and page fault
handler, the reclaimer attempting to access a PCMD at the
same time it is truncated by the page fault handler. This
could result in lost PCMD data. Data may still be
lost if the reclaimer wins the race, this is addressed in
the following patch.
The reclaimer accesses pages from the backing storage without
holding the enclave mutex and runs the risk of concurrently
accessing the backing storage with the page fault handler that
does access the backing storage with the enclave mutex held.
In the scenario below a PCMD page is truncated from the backing
store after all its pages have been loaded in to the enclave
at the same time the PCMD page is loaded from the backing store
when one of its pages are reclaimed:
sgx_reclaim_pages() { sgx_vma_fault() {
...
mutex_lock(&encl->lock);
...
__sgx_encl_eldu() {
...
if (pcmd_page_empty) {
/*
* EPC page being reclaimed /*
* shares a PCMD page with an * PCMD page truncated
* enclave page that is being * while requested from
* faulted in. * reclaimer.
*/ */
sgx_encl_get_backing() <----------> sgx_encl_truncate_backing_page()
}
mutex_unlock(&encl->lock);
} }
In this scenario there is a race between the reclaimer and the page fault
handler when the reclaimer attempts to get access to the same PCMD page
that is being truncated. This could result in the reclaimer writing to
the PCMD page that is then truncated, causing the PCMD data to be lost,
or in a new PCMD page being allocated. The lost PCMD data may still occur
after protecting the backing store access with the mutex - this is fixed
in the next patch. By ensuring the backing store is accessed with the mutex
held the enclave page state can be made accurate with the
SGX_ENCL_PAGE_BEING_RECLAIMED flag accurately reflecting that a page
is in the process of being reclaimed.
Consistently protect the reclaimer's backing store access with the
enclave's mutex to ensure that it can safely run concurrently with the
page fault handler.
Cc: stable@vger.kernel.org
Fixes: 1728ab54b4 ("x86/sgx: Add a page reclaimer")
Reported-by: Haitao Huang <haitao.huang@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Haitao Huang <haitao.huang@intel.com>
Link: https://lkml.kernel.org/r/fa2e04c561a8555bfe1f4e7adc37d60efc77387b.1652389823.git.reinette.chatre@intel.com
SGX uses shmem backing storage to store encrypted enclave pages
and their crypto metadata when enclave pages are moved out of
enclave memory. Two shmem backing storage pages are associated with
each enclave page - one backing page to contain the encrypted
enclave page data and one backing page (shared by a few
enclave pages) to contain the crypto metadata used by the
processor to verify the enclave page when it is loaded back into
the enclave.
sgx_encl_put_backing() is used to release references to the
backing storage and, optionally, mark both backing store pages
as dirty.
Managing references and dirty status together in this way results
in both backing store pages marked as dirty, even if only one of
the backing store pages are changed.
Additionally, waiting until the page reference is dropped to set
the page dirty risks a race with the page fault handler that
may load outdated data into the enclave when a page is faulted
right after it is reclaimed.
Consider what happens if the reclaimer writes a page to the backing
store and the page is immediately faulted back, before the reclaimer
is able to set the dirty bit of the page:
sgx_reclaim_pages() { sgx_vma_fault() {
...
sgx_encl_get_backing();
... ...
sgx_reclaimer_write() {
mutex_lock(&encl->lock);
/* Write data to backing store */
mutex_unlock(&encl->lock);
}
mutex_lock(&encl->lock);
__sgx_encl_eldu() {
...
/*
* Enclave backing store
* page not released
* nor marked dirty -
* contents may not be
* up to date.
*/
sgx_encl_get_backing();
...
/*
* Enclave data restored
* from backing store
* and PCMD pages that
* are not up to date.
* ENCLS[ELDU] faults
* because of MAC or PCMD
* checking failure.
*/
sgx_encl_put_backing();
}
...
/* set page dirty */
sgx_encl_put_backing();
...
mutex_unlock(&encl->lock);
} }
Remove the option to sgx_encl_put_backing() to set the backing
pages as dirty and set the needed pages as dirty right after
receiving important data while enclave mutex is held. This ensures that
the page fault handler can get up to date data from a page and prepares
the code for a following change where only one of the backing pages
need to be marked as dirty.
Cc: stable@vger.kernel.org
Fixes: 1728ab54b4 ("x86/sgx: Add a page reclaimer")
Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Haitao Huang <haitao.huang@intel.com>
Link: https://lore.kernel.org/linux-sgx/8922e48f-6646-c7cc-6393-7c78dcf23d23@intel.com/
Link: https://lkml.kernel.org/r/fa9f98986923f43e72ef4c6702a50b2a0b3c42e3.1652389823.git.reinette.chatre@intel.com
There is a limited amount of SGX memory (EPC) on each system. When that
memory is used up, SGX has its own swapping mechanism which is similar
in concept but totally separate from the core mm/* code. Instead of
swapping to disk, SGX swaps from EPC to normal RAM. That normal RAM
comes from a shared memory pseudo-file and can itself be swapped by the
core mm code. There is a hierarchy like this:
EPC <-> shmem <-> disk
After data is swapped back in from shmem to EPC, the shmem backing
storage needs to be freed. Currently, the backing shmem is not freed.
This effectively wastes the shmem while the enclave is running. The
memory is recovered when the enclave is destroyed and the backing
storage freed.
Sort this out by freeing memory with shmem_truncate_range(), as soon as
a page is faulted back to the EPC. In addition, free the memory for
PCMD pages as soon as all PCMD's in a page have been marked as unused
by zeroing its contents.
Cc: stable@vger.kernel.org
Fixes: 1728ab54b4 ("x86/sgx: Add a page reclaimer")
Reported-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20220303223859.273187-1-jarkko@kernel.org
The SGX reclaimer code lacks page poison handling in its main
free path. This can lead to avoidable machine checks if a
poisoned page is freed and reallocated instead of being
isolated.
A troublesome scenario is:
1. Machine check (#MC) occurs (asynchronous, !MF_ACTION_REQUIRED)
2. arch_memory_failure() is eventually called
3. (SGX) page->poison set to 1
4. Page is reclaimed
5. Page added to normal free lists by sgx_reclaim_pages()
^ This is the bug (poison pages should be isolated on the
sgx_poison_page_list instead)
6. Page is reallocated by some innocent enclave, a second (synchronous)
in-kernel #MC is induced, probably during EADD instruction.
^ This is the fallout from the bug
(6) is unfortunate and can be avoided by replacing the open coded
enclave page freeing code in the reclaimer with sgx_free_epc_page()
to obtain support for poison page handling that includes placing the
poisoned page on the correct list.
Fixes: d6d261bded ("x86/sgx: Add new sgx_epc_page flag bit to mark free pages")
Fixes: 992801ae92 ("x86/sgx: Initial poison handling for dirty and free pages")
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lkml.kernel.org/r/dcc95eb2aaefb042527ac50d0a50738c7c160dac.1643830353.git.reinette.chatre@intel.com
Vijay reported that the "unclobbered_vdso_oversubscribed" selftest
triggers the softlockup detector.
Actual SGX systems have 128GB of enclave memory or more. The
"unclobbered_vdso_oversubscribed" selftest creates one enclave which
consumes all of the enclave memory on the system. Tearing down such a
large enclave takes around a minute, most of it in the loop where
the EREMOVE instruction is applied to each individual 4k enclave page.
Spending one minute in a loop triggers the softlockup detector.
Add a cond_resched() to give other tasks a chance to run and placate
the softlockup detector.
Cc: stable@vger.kernel.org
Fixes: 1728ab54b4 ("x86/sgx: Add a page reclaimer")
Reported-by: Vijay Dhanraj <vijay.dhanraj@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Tested-by: Jarkko Sakkinen <jarkko@kernel.org> (kselftest as sanity check)
Link: https://lkml.kernel.org/r/ced01cac1e75f900251b0a4ae1150aa8ebd295ec.1644345232.git.reinette.chatre@intel.com
Pull x86 core updates from Borislav Petkov:
- Get rid of all the .fixup sections because this generates
misleading/wrong stacktraces and confuse RELIABLE_STACKTRACE and
LIVEPATCH as the backtrace misses the function which is being fixed
up.
- Add Straight Line Speculation mitigation support which uses a new
compiler switch -mharden-sls= which sticks an INT3 after a RET or an
indirect branch in order to block speculation after them. Reportedly,
CPUs do speculate behind such insns.
- The usual set of cleanups and improvements
* tag 'x86_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
x86/entry_32: Fix segment exceptions
objtool: Remove .fixup handling
x86: Remove .fixup section
x86/word-at-a-time: Remove .fixup usage
x86/usercopy: Remove .fixup usage
x86/usercopy_32: Simplify __copy_user_intel_nocache()
x86/sgx: Remove .fixup usage
x86/checksum_32: Remove .fixup usage
x86/vmx: Remove .fixup usage
x86/kvm: Remove .fixup usage
x86/segment: Remove .fixup usage
x86/fpu: Remove .fixup usage
x86/xen: Remove .fixup usage
x86/uaccess: Remove .fixup usage
x86/futex: Remove .fixup usage
x86/msr: Remove .fixup usage
x86/extable: Extend extable functionality
x86/entry_32: Remove .fixup usage
x86/entry_64: Remove .fixup usage
x86/copy_mc_64: Remove .fixup usage
...
== Problem ==
Nathan Chancellor reported an oops when aceessing the
'sgx_total_bytes' sysfs file:
https://lore.kernel.org/all/YbzhBrimHGGpddDM@archlinux-ax161/
The sysfs output code accesses the sgx_numa_nodes[] array
unconditionally. However, this array is allocated during SGX
initialization, which only occurs on systems where SGX is
supported.
If the sysfs file is accessed on systems without SGX support,
sgx_numa_nodes[] is NULL and an oops occurs.
== Solution ==
To fix this, hide the entire nodeX/x86/ attribute group on
systems without SGX support using the ->is_visible attribute
group callback.
Unfortunately, SGX is initialized via a device_initcall() which
occurs _after_ the ->is_visible() callback. Instead of moving
SGX initialization earlier, call sysfs_update_group() during
SGX initialization to update the group visiblility.
This update requires moving the SGX sysfs code earlier in
sgx/main.c. There are no code changes other than the addition of
arch_update_sysfs_visibility() and a minor whitespace fixup to
arch_node_attr_is_visible() which checkpatch caught.
CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-sgx@vger.kernel.org
Cc: x86@kernel.org
Fixes: 50468e4313 ("x86/sgx: Add an attribute for the amount of SGX memory in a NUMA node")
Reported-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lkml.kernel.org/r/20220104171527.5E8416A8@davehans-spike.ostc.intel.com
== Problem ==
The amount of SGX memory on a system is determined by the BIOS and it
varies wildly between systems. It can be as small as dozens of MB's
and as large as many GB's on servers. Just like how applications need
to know how much regular RAM is available, enclave builders need to
know how much SGX memory an enclave can consume.
== Solution ==
Introduce a new sysfs file:
/sys/devices/system/node/nodeX/x86/sgx_total_bytes
to enumerate the amount of SGX memory available in each NUMA node.
This serves the same function for SGX as /proc/meminfo or
/sys/devices/system/node/nodeX/meminfo does for normal RAM.
'sgx_total_bytes' is needed today to help drive the SGX selftests.
SGX-specific swap code is exercised by creating overcommitted enclaves
which are larger than the physical SGX memory on the system. They
currently use a CPUID-based approach which can diverge from the actual
amount of SGX memory available. 'sgx_total_bytes' ensures that the
selftests can work efficiently and do not attempt stupid things like
creating a 100,000 MB enclave on a system with 128 MB of SGX memory.
== Implementation Details ==
Introduce CONFIG_HAVE_ARCH_NODE_DEV_GROUP opt-in flag to expose an
arch specific attribute group, and add an attribute for the amount of
SGX memory in bytes to each NUMA node:
== ABI Design Discussion ==
As opposed to the per-node ABI, a single, global ABI was considered.
However, this would prevent enclaves from being able to size
themselves so that they fit on a single NUMA node. Essentially, a
single value would rule out NUMA optimizations for enclaves.
Create a new "x86/" directory inside each "nodeX/" sysfs directory.
'sgx_total_bytes' is expected to be the first of at least a few
sgx-specific files to be placed in the new directory. Just scanning
/proc/meminfo, these are the no-brainers that we have for RAM, but we
need for SGX:
MemTotal: xxxx kB // sgx_total_bytes (implemented here)
MemFree: yyyy kB // sgx_free_bytes
SwapTotal: zzzz kB // sgx_swapped_bytes
So, at *least* three. I think we will eventually end up needing
something more along the lines of a dozen. A new directory (as
opposed to being in the nodeX/ "root") directory avoids cluttering the
root with several "sgx_*" files.
Place the new file in a new "nodeX/x86/" directory because SGX is
highly x86-specific. It is very unlikely that any other architecture
(or even non-Intel x86 vendor) will ever implement SGX. Using "sgx/"
as opposed to "x86/" was also considered. But, there is a real chance
this can get used for other arch-specific purposes.
[ dhansen: rewrite changelog ]
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20211116162116.93081-2-jarkko@kernel.org
The SGX driver maintains a single global free page counter,
sgx_nr_free_pages, that reflects the number of free pages available
across all NUMA nodes. Correspondingly, a list of free pages is
associated with each NUMA node and sgx_nr_free_pages is updated
every time a page is added or removed from any of the free page
lists. The main usage of sgx_nr_free_pages is by the reclaimer
that runs when it (sgx_nr_free_pages) goes below a watermark
to ensure that there are always some free pages available to, for
example, support efficient page faults.
With sgx_nr_free_pages accessed and modified from a few places
it is essential to ensure that these accesses are done safely but
this is not the case. sgx_nr_free_pages is read without any
protection and updated with inconsistent protection by any one
of the spin locks associated with the individual NUMA nodes.
For example:
CPU_A CPU_B
----- -----
spin_lock(&nodeA->lock); spin_lock(&nodeB->lock);
... ...
sgx_nr_free_pages--; /* NOT SAFE */ sgx_nr_free_pages--;
spin_unlock(&nodeA->lock); spin_unlock(&nodeB->lock);
Since sgx_nr_free_pages may be protected by different spin locks
while being modified from different CPUs, the following scenario
is possible:
CPU_A CPU_B
----- -----
{sgx_nr_free_pages = 100}
spin_lock(&nodeA->lock); spin_lock(&nodeB->lock);
sgx_nr_free_pages--; sgx_nr_free_pages--;
/* LOAD sgx_nr_free_pages = 100 */ /* LOAD sgx_nr_free_pages = 100 */
/* sgx_nr_free_pages-- */ /* sgx_nr_free_pages-- */
/* STORE sgx_nr_free_pages = 99 */ /* STORE sgx_nr_free_pages = 99 */
spin_unlock(&nodeA->lock); spin_unlock(&nodeB->lock);
In the above scenario, sgx_nr_free_pages is decremented from two CPUs
but instead of sgx_nr_free_pages ending with a value that is two less
than it started with, it was only decremented by one while the number
of free pages were actually reduced by two. The consequence of
sgx_nr_free_pages not being protected is that its value may not
accurately reflect the actual number of free pages on the system,
impacting the availability of free pages in support of many flows.
The problematic scenario is when the reclaimer does not run because it
believes there to be sufficient free pages while any attempt to allocate
a page fails because there are no free pages available. In the SGX driver
the reclaimer's watermark is only 32 pages so after encountering the
above example scenario 32 times a user space hang is possible when there
are no more free pages because of repeated page faults caused by no
free pages made available.
The following flow was encountered:
asm_exc_page_fault
...
sgx_vma_fault()
sgx_encl_load_page()
sgx_encl_eldu() // Encrypted page needs to be loaded from backing
// storage into newly allocated SGX memory page
sgx_alloc_epc_page() // Allocate a page of SGX memory
__sgx_alloc_epc_page() // Fails, no free SGX memory
...
if (sgx_should_reclaim(SGX_NR_LOW_PAGES)) // Wake reclaimer
wake_up(&ksgxd_waitq);
return -EBUSY; // Return -EBUSY giving reclaimer time to run
return -EBUSY;
return -EBUSY;
return VM_FAULT_NOPAGE;
The reclaimer is triggered in above flow with the following code:
static bool sgx_should_reclaim(unsigned long watermark)
{
return sgx_nr_free_pages < watermark &&
!list_empty(&sgx_active_page_list);
}
In the problematic scenario there were no free pages available yet the
value of sgx_nr_free_pages was above the watermark. The allocation of
SGX memory thus always failed because of a lack of free pages while no
free pages were made available because the reclaimer is never started
because of sgx_nr_free_pages' incorrect value. The consequence was that
user space kept encountering VM_FAULT_NOPAGE that caused the same
address to be accessed repeatedly with the same result.
Change the global free page counter to an atomic type that
ensures simultaneous updates are done safely. While doing so, move
the updating of the variable outside of the spin lock critical
section to which it does not belong.
Cc: stable@vger.kernel.org
Fixes: 901ddbb9ec ("x86/sgx: Add a basic NUMA allocation scheme to sgx_alloc_epc_page()")
Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Acked-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lkml.kernel.org/r/a95a40743bbd3f795b465f30922dde7f1ea9e0eb.1637004094.git.reinette.chatre@intel.com
Provide a recovery function sgx_memory_failure(). If the poison was
consumed synchronously then send a SIGBUS. Note that the virtual
address of the access is not included with the SIGBUS as is the case
for poison outside of SGX enclaves. This doesn't matter as addresses
of code/data inside an enclave is of little to no use to code executing
outside the (now dead) enclave.
Poison found in a free page results in the page being moved from the
free list to the per-node poison page list.
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/20211026220050.697075-5-tony.luck@intel.com
A memory controller patrol scrubber can report poison in a page
that isn't currently being used.
Add "poison" field in the sgx_epc_page that can be set for an
sgx_epc_page. Check for it:
1) When sanitizing dirty pages
2) When freeing epc pages
Poison is a new field separated from flags to avoid having to make all
updates to flags atomic, or integrate poison state changes into some
other locking scheme to protect flags (Currently just sgx_reclaimer_lock
which protects the SGX_EPC_PAGE_RECLAIMER_TRACKED bit in page->flags).
In both cases place the poisoned page on a per-node list of poisoned
epc pages to make sure it will not be reallocated.
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/20211026220050.697075-4-tony.luck@intel.com
X86 machine check architecture reports a physical address when there
is a memory error. Handling that error requires a method to determine
whether the physical address reported is in any of the areas reserved
for EPC pages by BIOS.
SGX EPC pages do not have Linux "struct page" associated with them.
Keep track of the mapping from ranges of EPC pages to the sections
that contain them using an xarray. N.B. adds CONFIG_XARRAY_MULTI to
the SGX dependecies. So "select" that in arch/x86/Kconfig for X86/SGX.
Create a function arch_is_platform_page() that simply reports whether an
address is an EPC page for use elsewhere in the kernel. The ACPI error
injection code needs this function and is typically built as a module,
so export it.
Note that arch_is_platform_page() will be slower than other similar
"what type is this page" functions that can simply check bits in the
"struct page". If there is some future performance critical user of
this function it may need to be implemented in a more efficient way.
Note also that the current implementation of xarray allocates a few
hundred kilobytes for this usage on a system with 4GB of SGX EPC memory
configured. This isn't ideal, but worth it for the code simplicity.
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/20211026220050.697075-3-tony.luck@intel.com
SGX EPC pages go through the following life cycle:
DIRTY ---> FREE ---> IN-USE --\
^ |
\-----------------/
Recovery action for poison for a DIRTY or FREE page is simple. Just
make sure never to allocate the page. IN-USE pages need some extra
handling.
Add a new flag bit SGX_EPC_PAGE_IS_FREE that is set when a page
is added to a free list and cleared when the page is allocated.
Notes:
1) These transitions are made while holding the node->lock so that
future code that checks the flags while holding the node->lock
can be sure that if the SGX_EPC_PAGE_IS_FREE bit is set, then the
page is on the free list.
2) Initially while the pages are on the dirty list the
SGX_EPC_PAGE_IS_FREE bit is cleared.
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Tested-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/20211026220050.697075-2-tony.luck@intel.com
For bare-metal SGX on real hardware, the hardware provides guarantees
SGX state at reboot. For instance, all pages start out uninitialized.
The vepc driver provides a similar guarantee today for freshly-opened
vepc instances, but guests such as Windows expect all pages to be in
uninitialized state on startup, including after every guest reboot.
Some userspace implementations of virtual SGX would rather avoid having
to close and reopen the /dev/sgx_vepc file descriptor and re-mmap the
virtual EPC. For example, they could sandbox themselves after the guest
starts and forbid further calls to open(), in order to mitigate exploits
from untrusted guests.
Therefore, add a ioctl that does this with EREMOVE. Userspace can
invoke the ioctl to bring its vEPC pages back to uninitialized state.
There is a possibility that some pages fail to be removed if they are
SECS pages, and the child and SECS pages could be in separate vEPC
regions. Therefore, the ioctl returns the number of EREMOVE failures,
telling userspace to try the ioctl again after it's done with all
vEPC regions. A more verbose description of the correct usage and
the possible error conditions is documented in sgx.rst.
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20211021201155.1523989-3-pbonzini@redhat.com
For bare-metal SGX on real hardware, the hardware provides guarantees
SGX state at reboot. For instance, all pages start out uninitialized.
The vepc driver provides a similar guarantee today for freshly-opened
vepc instances, but guests such as Windows expect all pages to be in
uninitialized state on startup, including after every guest reboot.
One way to do this is to simply close and reopen the /dev/sgx_vepc file
descriptor and re-mmap the virtual EPC. However, this is problematic
because it prevents sandboxing the userspace (for example forbidding
open() after the guest starts; this is doable with heavy use of SCM_RIGHTS
file descriptor passing).
In order to implement this, we will need a ioctl that performs
EREMOVE on all pages mapped by a /dev/sgx_vepc file descriptor:
other possibilities, such as closing and reopening the device,
are racy.
Start the implementation by creating a separate function with just
the __eremove wrapper.
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20211021201155.1523989-2-pbonzini@redhat.com
Merge misc updates from Andrew Morton:
"191 patches.
Subsystems affected by this patch series: kthread, ia64, scripts,
ntfs, squashfs, ocfs2, kernel/watchdog, and mm (gup, pagealloc, slab,
slub, kmemleak, dax, debug, pagecache, gup, swap, memcg, pagemap,
mprotect, bootmem, dma, tracing, vmalloc, kasan, initialization,
pagealloc, and memory-failure)"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (191 commits)
mm,hwpoison: make get_hwpoison_page() call get_any_page()
mm,hwpoison: send SIGBUS with error virutal address
mm/page_alloc: split pcp->high across all online CPUs for cpuless nodes
mm/page_alloc: allow high-order pages to be stored on the per-cpu lists
mm: replace CONFIG_FLAT_NODE_MEM_MAP with CONFIG_FLATMEM
mm: replace CONFIG_NEED_MULTIPLE_NODES with CONFIG_NUMA
docs: remove description of DISCONTIGMEM
arch, mm: remove stale mentions of DISCONIGMEM
mm: remove CONFIG_DISCONTIGMEM
m68k: remove support for DISCONTIGMEM
arc: remove support for DISCONTIGMEM
arc: update comment about HIGHMEM implementation
alpha: remove DISCONTIGMEM and NUMA
mm/page_alloc: move free_the_page
mm/page_alloc: fix counting of managed_pages
mm/page_alloc: improve memmap_pages dbg msg
mm: drop SECTION_SHIFT in code comments
mm/page_alloc: introduce vm.percpu_pagelist_high_fraction
mm/page_alloc: limit the number of pages on PCP lists when reclaim is active
mm/page_alloc: scale the number of pages that are batch freed
...
Pull x86 cleanups from Ingo Molnar:
"Misc cleanups & removal of obsolete code"
* tag 'x86-cleanups-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/sgx: Correct kernel-doc's arg name in sgx_encl_release()
doc: Remove references to IBM Calgary
x86/setup: Document that Windows reserves the first MiB
x86/crash: Remove crash_reserve_low_1M()
x86/setup: Remove CONFIG_X86_RESERVE_LOW and reservelow= options
x86/alternative: Align insn bytes vertically
x86: Fix leftover comment typos
x86/asm: Simplify __smp_mb() definition
x86/alternatives: Make the x86nops[] symbol static
Pull misc x86 cleanups from Borislav Petkov:
"Trivial cleanups and fixes all over the place"
* tag 'x86_cleanups_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
MAINTAINERS: Remove me from IDE/ATAPI section
x86/pat: Do not compile stubbed functions when X86_PAT is off
x86/asm: Ensure asm/proto.h can be included stand-alone
x86/platform/intel/quark: Fix incorrect kernel-doc comment syntax in files
x86/msr: Make locally used functions static
x86/cacheinfo: Remove unneeded dead-store initialization
x86/process/64: Move cpu_current_top_of_stack out of TSS
tools/turbostat: Unmark non-kernel-doc comment
x86/syscalls: Fix -Wmissing-prototypes warnings from COND_SYSCALL()
x86/fpu/math-emu: Fix function cast warning
x86/msr: Fix wr/rdmsr_safe_regs_on_cpu() prototypes
x86: Fix various typos in comments, take #2
x86: Remove unusual Unicode characters from comments
x86/kaslr: Return boolean values from a function returning bool
x86: Fix various typos in comments
x86/setup: Remove unused RESERVE_BRK_ARRAY()
stacktrace: Move documentation for arch_stack_walk_reliable() to header
x86: Remove duplicate TSC DEADLINE MSR definitions
The commit in Fixes: changed the SGX EPC page sanitization to end up in
sgx_free_epc_page() which puts clean and sanitized pages on the free
list.
This was done for the reason that it is best to keep the logic to assign
available-for-use EPC pages to the correct NUMA lists in a single
location.
sgx_nr_free_pages is also incremented by sgx_free_epc_pages() but those
pages which are being added there per EPC section do not belong to the
free list yet because they haven't been sanitized yet - they land on the
dirty list first and the sanitization happens later when ksgxd starts
massaging them.
So remove that addition there and have sgx_free_epc_page() do that
solely.
[ bp: Sanitize commit message too. ]
Fixes: 51ab30eb2a ("x86/sgx: Replace section->init_laundry_list with sgx_dirty_page_list")
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210408092924.7032-1-jarkko@kernel.org
And extract sgx_set_attribute() out of sgx_ioc_enclave_provision() and
export it as symbol for KVM to use.
The provisioning key is sensitive. The SGX driver only allows to create
an enclave which can access the provisioning key when the enclave
creator has permission to open /dev/sgx_provision. It should apply to
a VM as well, as the provisioning key is platform-specific, thus an
unrestricted VM can also potentially compromise the provisioning key.
Move the provisioning device creation out of sgx_drv_init() to
sgx_init() as a preparation for adding SGX virtualization support,
so that even if the SGX driver is not enabled due to flexible launch
control not being available, SGX virtualization can still be enabled,
and use it to restrict a VM's capability of being able to access the
provisioning key.
[ bp: Massage commit message. ]
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Link: https://lkml.kernel.org/r/0f4d044d621561f26d5f4ef73e8dc6cd18cc7e79.1616136308.git.kai.huang@intel.com
The host kernel must intercept ECREATE to impose policies on guests, and
intercept EINIT to be able to write guest's virtual SGX_LEPUBKEYHASH MSR
values to hardware before running guest's EINIT so it can run correctly
according to hardware behavior.
Provide wrappers around __ecreate() and __einit() to hide the ugliness
of overloading the ENCLS return value to encode multiple error formats
in a single int. KVM will trap-and-execute ECREATE and EINIT as part
of SGX virtualization, and reflect ENCLS execution result to guest by
setting up guest's GPRs, or on an exception, injecting the correct fault
based on return value of __ecreate() and __einit().
Use host userspace addresses (provided by KVM based on guest physical
address of ENCLS parameters) to execute ENCLS/EINIT when possible.
Accesses to both EPC and memory originating from ENCLS are subject to
segmentation and paging mechanisms. It's also possible to generate
kernel mappings for ENCLS parameters by resolving PFN but using
__uaccess_xx() is simpler.
[ bp: Return early if the __user memory accesses fail, use
cpu_feature_enabled(). ]
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lkml.kernel.org/r/20e09daf559aa5e9e680a0b4b5fba940f1bad86e.1616136308.git.kai.huang@intel.com
Add a misc device /dev/sgx_vepc to allow userspace to allocate "raw"
Enclave Page Cache (EPC) without an associated enclave. The intended
and only known use case for raw EPC allocation is to expose EPC to a
KVM guest, hence the 'vepc' moniker, virt.{c,h} files and X86_SGX_KVM
Kconfig.
The SGX driver uses the misc device /dev/sgx_enclave to support
userspace in creating an enclave. Each file descriptor returned from
opening /dev/sgx_enclave represents an enclave. Unlike the SGX driver,
KVM doesn't control how the guest uses the EPC, therefore EPC allocated
to a KVM guest is not associated with an enclave, and /dev/sgx_enclave
is not suitable for allocating EPC for a KVM guest.
Having separate device nodes for the SGX driver and KVM virtual EPC also
allows separate permission control for running host SGX enclaves and KVM
SGX guests.
To use /dev/sgx_vepc to allocate a virtual EPC instance with particular
size, the hypervisor opens /dev/sgx_vepc, and uses mmap() with the
intended size to get an address range of virtual EPC. Then it may use
the address range to create one KVM memory slot as virtual EPC for
a guest.
Implement the "raw" EPC allocation in the x86 core-SGX subsystem via
/dev/sgx_vepc rather than in KVM. Doing so has two major advantages:
- Does not require changes to KVM's uAPI, e.g. EPC gets handled as
just another memory backend for guests.
- EPC management is wholly contained in the SGX subsystem, e.g. SGX
does not have to export any symbols, changes to reclaim flows don't
need to be routed through KVM, SGX's dirty laundry doesn't have to
get aired out for the world to see, and so on and so forth.
The virtual EPC pages allocated to guests are currently not reclaimable.
Reclaiming an EPC page used by enclave requires a special reclaim
mechanism separate from normal page reclaim, and that mechanism is not
supported for virutal EPC pages. Due to the complications of handling
reclaim conflicts between guest and host, reclaiming virtual EPC pages
is significantly more complex than basic support for SGX virtualization.
[ bp:
- Massage commit message and comments
- use cpu_feature_enabled()
- vertically align struct members init
- massage Virtual EPC clarification text
- move Kconfig prompt to Virtualization ]
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Co-developed-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Acked-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lkml.kernel.org/r/0c38ced8c8e5a69872db4d6a1c0dabd01e07cad7.1616136308.git.kai.huang@intel.com
SGX driver can accurately track how enclave pages are used. This
enables SECS to be specifically targeted and EREMOVE'd only after all
child pages have been EREMOVE'd. This ensures that SGX driver will
never encounter SGX_CHILD_PRESENT in normal operation.
Virtual EPC is different. The host does not track how EPC pages are
used by the guest, so it cannot guarantee EREMOVE success. It might,
for instance, encounter a SECS with a non-zero child count.
Add a definition of SGX_CHILD_PRESENT. It will be used exclusively by
the SGX virtualization driver to handle recoverable EREMOVE errors when
saniziting EPC pages after they are freed.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Acked-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lkml.kernel.org/r/050b198e882afde7e6eba8e6a0d4da39161dbb5a.1616136308.git.kai.huang@intel.com
EREMOVE takes a page and removes any association between that page and
an enclave. It must be run on a page before it can be added into another
enclave. Currently, EREMOVE is run as part of pages being freed into the
SGX page allocator. It is not expected to fail, as it would indicate a
use-after-free of EPC pages. Rather than add the page back to the pool
of available EPC pages, the kernel intentionally leaks the page to avoid
additional errors in the future.
However, KVM does not track how guest pages are used, which means that
SGX virtualization use of EREMOVE might fail. Specifically, it is
legitimate that EREMOVE returns SGX_CHILD_PRESENT for EPC assigned to
KVM guest, because KVM/kernel doesn't track SECS pages.
To allow SGX/KVM to introduce a more permissive EREMOVE helper and
to let the SGX virtualization code use the allocator directly, break
out the EREMOVE call from the SGX page allocator. Rename the original
sgx_free_epc_page() to sgx_encl_free_epc_page(), indicating that
it is used to free an EPC page assigned to a host enclave. Replace
sgx_free_epc_page() with sgx_encl_free_epc_page() in all call sites so
there's no functional change.
At the same time, improve the error message when EREMOVE fails, and
add documentation to explain to the user what that failure means and
to suggest to the user what to do when this bug happens in the case it
happens.
[ bp: Massage commit message, fix typos and sanitize text, simplify. ]
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lkml.kernel.org/r/20210325093057.122834-1-kai.huang@intel.com
kmap() is inefficient and is being replaced by kmap_local_page(), if
possible. There is no readily apparent reason why initp_page needs to be
allocated and kmap'ed() except that 'sigstruct' needs to be page-aligned
and 'token' 512 byte-aligned.
Rather than change it to kmap_local_page(), use kmalloc() instead
because kmalloc() can give this alignment when allocating PAGE_SIZE
bytes.
Remove the alloc_page()/kmap() and replace with kmalloc(PAGE_SIZE, ...)
to get a page aligned kernel address.
In addition, add a comment to document the alignment requirements so that
others don't attempt to 'fix' this again.
[ bp: Massage commit message. ]
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210324182246.2484875-1-ira.weiny@intel.com
Background
==========
SGX enclave memory is enumerated by the processor in contiguous physical
ranges called Enclave Page Cache (EPC) sections. Currently, there is a
free list per section, but allocations simply target the lowest-numbered
sections. This is functional, but has no NUMA awareness.
Fortunately, EPC sections are covered by entries in the ACPI SRAT table.
These entries allow each EPC section to be associated with a NUMA node,
just like normal RAM.
Solution
========
Implement a NUMA-aware enclave page allocator. Mirror the buddy allocator
and maintain a list of enclave pages for each NUMA node. Attempt to
allocate enclave memory first from local nodes, then fall back to other
nodes.
Note that the fallback is not as sophisticated as the buddy allocator
and is itself not aware of NUMA distances. When a node's free list is
empty, it searches for the next-highest node with enclave pages (and
will wrap if necessary). This could be improved in the future.
Other
=====
NUMA_KEEP_MEMINFO dependency is required for phys_to_target_node().
[ Kai Huang: Do not return NULL from __sgx_alloc_epc_page() because
callers do not expect that and that leads to a NULL ptr deref. ]
[ dhansen: Fix an uninitialized 'nid' variable in
__sgx_alloc_epc_page() as
Reported-by: kernel test robot <lkp@intel.com>
to avoid any potential allocations from the wrong NUMA node or even
premature allocation failures. ]
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/lkml/158188326978.894464.217282995221175417.stgit@dwillia2-desk3.amr.corp.intel.com/
Link: https://lkml.kernel.org/r/20210319040602.178558-1-kai.huang@intel.com
Link: https://lkml.kernel.org/r/20210318214933.29341-1-dave.hansen@intel.com
Link: https://lkml.kernel.org/r/20210317235332.362001-2-jarkko.sakkinen@intel.com
During normal runtime, the "ksgxd" daemon behaves like a version of
kswapd just for SGX. But, before it starts acting like kswapd, its first
job is to initialize enclave memory.
Currently, the SGX boot code places each enclave page on a
epc_section->init_laundry_list. Once it starts up, the ksgxd code walks
over that list and populates the actual SGX page allocator.
However, the per-section structures are going away to make way for the
SGX NUMA allocator. There's also little need to have a per-section
structure; the enclave pages are all treated identically, and they can
be placed on the correct allocator list from metadata stored in the
enclave page (struct sgx_epc_page) itself.
Modify sgx_sanitize_section() to take a single page list instead of
taking a section and deriving the list from there.
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20210317235332.362001-1-jarkko.sakkinen@intel.com
Pull x86 SGX fixes from Borislav Petkov:
"Random small fixes which missed the initial SGX submission. Also, some
procedural clarifications"
* tag 'x86_sgx_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
MAINTAINERS: Add Dave Hansen as reviewer for INTEL SGX
x86/sgx: Drop racy follow_pfn() check
MAINTAINERS: Fix the tree location for INTEL SGX patches
x86/sgx: Fix the return type of sgx_init()
This has been shown in tests:
[ +0.000008] WARNING: CPU: 3 PID: 7620 at kernel/rcu/srcutree.c:374 cleanup_srcu_struct+0xed/0x100
This is essentially a use-after free, although SRCU notices it as
an SRCU cleanup in an invalid context.
== Background ==
SGX has a data structure (struct sgx_encl_mm) which keeps per-mm SGX
metadata. This is separate from struct sgx_encl because, in theory,
an enclave can be mapped from more than one mm. sgx_encl_mm includes
a pointer back to the sgx_encl.
This means that sgx_encl must have a longer lifetime than all of the
sgx_encl_mm's that point to it. That's usually the case: sgx_encl_mm
is freed only after the mmu_notifier is unregistered in sgx_release().
However, there's a race. If the process is exiting,
sgx_mmu_notifier_release() can be called in parallel with sgx_release()
instead of being called *by* it. The mmu_notifier path keeps encl_mm
alive past when sgx_encl can be freed. This inverts the lifetime rules
and means that sgx_mmu_notifier_release() can access a freed sgx_encl.
== Fix ==
Increase encl->refcount when encl_mm->encl is established. Release
this reference when encl_mm is freed. This ensures that encl outlives
encl_mm.
[ bp: Massage commit message. ]
Fixes: 1728ab54b4 ("x86/sgx: Add a page reclaimer")
Reported-by: Haitao Huang <haitao.huang@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lkml.kernel.org/r/20210207221401.29933-1-jarkko@kernel.org
PTE insertion is fundamentally racy, and this check doesn't do anything
useful. Quoting Sean:
"Yeah, it can be whacked. The original, never-upstreamed code asserted
that the resolved PFN matched the PFN being installed by the fault
handler as a sanity check on the SGX driver's EPC management. The
WARN assertion got dropped for whatever reason, leaving that useless
chunk."
Jason stumbled over this as a new user of follow_pfn(), and I'm trying
to get rid of unsafe callers of that function so it can be locked down
further.
This is independent prep work for the referenced patch series:
https://lore.kernel.org/dri-devel/20201127164131.2244124-1-daniel.vetter@ffwll.ch/
Fixes: 947c6e11fa ("x86/sgx: Add ptrace() support for the SGX driver")
Reported-by: Jason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Link: https://lkml.kernel.org/r/20210204184519.2809313-1-daniel.vetter@ffwll.ch
Fix
./arch/x86/kernel/cpu/sgx/ioctl.c:666: warning: Function parameter or member \
'encl' not described in 'sgx_ioc_enclave_provision'
./arch/x86/kernel/cpu/sgx/ioctl.c:666: warning: Excess function parameter \
'enclave' description in 'sgx_ioc_enclave_provision'
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20201123181922.0c009406@canb.auug.org.au
