The memcpy implementation is not completely stupid but is almost
certainly not as good as a carefully tuned and optimised one.
Building snmalloc with FreeBSD's libc memcpy + jemalloc and with this,
each 10 times, does not show a statistically significant performance
difference at 95% confidence. The snmalloc version has very slightly
lower median and worst-case times. This is in no way a sensible
benchmark, but it serves as a smoke test for significant performance
regressions.
The CI self-host job now uses the checked memcpy.
This also fixes an off-by-one error in the external bounds. This is
triggered by ninja, so we will see breakage in CI if it is reintroduced.
In debug builds, we provide a verbose error containing the address of
the allocation, the base and bounds of the allocation, and a backtrace.
The backtrace was broken by the CI cleanup moving the BACKTRACE_HEADER
macro into the SNMALLOC_ namespace. This is also fixed.
The test involves hijacking `abort`, which doesn't work everywhere. It
also requires `backtrace` to work in configurations where stack traces
are enabled. This is disabled in QEMU because `backtrace` appears to
crash reliably in QEMU user mode.
For now, in the -checks build configurations, we are hitting a slow path
in the pagemap on accesses so that the pages that are `PROT_NONE` don't
cause crashes. These need to be made read-only, but this requires a PAL
change.
David points out that we might not have a static way to get at the pagemap, so
it is potentially useful to pass pointers to state objects down from the
Allocators.
This commit splits the sizeclass meta-data to generate better cache
locality for various lookups for checking for size and start of
sizeclasses.
Also, contains some tidying including removing sizeclasses covering
large range. This is left over from an alternative design for large
classes that is no longer in use.
The code was able to use pthread destructors rather than C++ thread
local destructors. This removes the dependence on a C++ .so on linux.
However, this is not stable on other platforms such as Apple. Where the
C++ thread local state can be cleared before the pthread destructor
runs.
Instead, tell the iostream to write out hex. This avoids the CHERI compiler
warning that we're turning a provenance-free value to a pointer.
Co-authored-by: Matthew Parkinson <mattpark@microsoft.com>
This avoids the CHERI compiler warning that we're turning a provenance-free
value to a pointer.
Co-authored-by: Matthew Parkinson <mattpark@microsoft.com>
- CI merge issues:
- The malloc shim libraries are renamed.
- CMake gets very unhappy if you don't enable the C language and
tries to link with the C compiler instead of the C++ compiler if
you do enable it.
- The Ubuntu packages for QEMU install a `binfmt_misc` activator for
PowerPC64 little-endian, but set the page size to 4 KiB. We then
tried to run the tests (which expect 64 KiB pages) and became very
confused when `mmap` returned 4 KiB-aligned memory.
- Test failures:
- Fix all of the issues UBsan found.
- Underflow in `pointer_offset` when used to add negative offsets.
- `CoreAlloc`'s `LocalState` accessed on a null `CoreAlloc` pointer.
- Out of bounds access in the sizeclass list on attempts to access
more memory than fits in the VA space.
-
- There was an integer overflow in `AddressSpace` that could cause it
to try to allocate a zero-sized object, get a null pointer, and
then try to do something with 0 - {size of the real allocation}.
- The malloc tests weren't setting `errno` to 0 before doing
calling `malloc`, which should set `errno` on failure, and then
checking that `errno` was 0.
- Don't call `PAL::error` on PAL allocation failure, return `nullptr`.
The PALs were inconsistent about that and the new code expects to be
able to report address-space exhaustion.
- The malloc checks can behave differently with 0-sized allocations
on different platforms but were very fragile about their
expectations.
- The malloc test didn't report failure for all of the ways that it
could fail and so was spuriously passing on some platforms.
- The perf test for external pointer is currently very slow on
Windows. The number of loops have been reduced and a timeout added
for the Windows CI runs.
- The logic to capture `errno` across calls was using
`decltype(errno)`, which on some platforms where `errno` is a macro
evaluated to `int&` and so they captured a reference rather than
the value and failed to reset `errno`.
- The Apple PAL can set `errno` on `notify_using` if it's called with
memory that was not previously passed to `notify_not_using` but was
not adequately protected against this and so would sometimes cause
`malloc` to set `errno` to `EINVAL`.
This is the set of changes required for snmalloc2 to be usable by the
process sandboxing code and incorporates some API changes that reduce
the amount of code required to embed snmalloc. Highlights:
- Merge the config and back-end classes.
- Everything in config is now global (all methods are static)
- The GlobalState class is gone (all global state is managed by global
methods on the config class)
- LocalState is now a member of the config class, all methods are
instance methods.
- Not every configuration needs to use the lazy initialisation hooks.
They now need to be provided only if they are used. If the
configuration does not provide an `ensure_init` method, it is not
called. If it does not provide an `is_initialised` method then the
global initialisation state is not checked.
- There is now an `snmalloc::Options` class that default initialises
itself to the default behaviour. Every configuration must provide a
`constexpr` instance of this class. Each flag can be separately
overridden and new flags can be added without breaking any existing
API consumers.
The config classes are moved into the backend directory.
The Pal was providing policy for overallocating a block of memory to
achieve alignment make that part of the backend.
The backend should be responsible for layout policy.
This PR exposes a pagemap interface to specify ranges that are being
used. The overall invariant is that any memory in the address space
manager has the pagemap committed. This means that individual operations
do not need to commit entries.
This is important for Windows that does not support lazy commit. It is
also important if we want to PROT_NONE most of the pagemap to reduce the
risk of memory safety issues getting access to the pagemap.
There are minor changes to test to pull memory directly from the Pal.
There are also bug fixes in the pagemap tests.
The pagemap allocates it self directly either from
* the original fixed address range it is supplied, and returns the
remaining space after the pagemap is removed; or
* directly allocated from the PAL without using the address space
manager.
This change in layering is required for the next commit, which imposes
the invariant that the pagemap has been committed for all spaced managed
by the address space manager.
# Pagemap
The Pagemap now stores all the meta-data for the object allocation. The meta-data in the pagemap is effectively a triple of the sizeclass, the remote allocator, and a pointer to a 64 byte block of meta-data for this chunk of memory. By storing the pointer to a block, it allows the pagemap to handle multiple slab sizes without branching on the fast path. There is one entry in the pagemap per 16KiB of address space, but by using the same entry in the pagemap for 4 adjacent entries, then we can treat a 64KiB range can be treated as a single slab of allocations.
This change also means there is almost no capability amplification required by the implementation on CHERI for finding meta-data. The only amplification is required, when we change the way a chunk is used to a size of object allocation.
# Backend
There is a second major aspect of the refactor that there is now a narrow API that abstracts the Pagemap, PAL and address space management. This should better enable the compartmentalisation and makes it easier to produce alternative backends for various research directions. This is a template parameter that can be used to specialised by the front-end in different ways.
# Thread local state
The thread local state has been refactored into two components, one (called 'localalloc') that is stored directly in the TLS and is constant initialised, and one that is allocated in the address space (called 'coreallloc') which is lazily created and pooled.
# Difference
This removes Superslabs/Medium slabs as there meta-data is now part of the pagemap.
The CapPtr refactoring was largely compiler guided; unfortunately, it turns out
that the static-sized alloc function is not well exercised. As such, some type
errors and unnecessary unsafety lurked behind missing template instantiation.
Correct those and add calls to the test harness to make sure we always generate
at least one instance of each small/medium/large case. While here, it doesn't
hurt to make sure that we call all three possible dealloc() flavors as well.
This will, if nothing else, force instantiation of the static-sized dealloc
template as well.
Even if we opt not to bound these pointers internally (if they aren't headed out
to the user program or we later derive bounded pointers), they should still be
annotated as something other than CBArena, ensuring that we do not attempt to
use them for general amplification.
* The AddressSpaceManager now requests address space in specified granule
sizes and registers those allocations with an external ArenaMap.
* The DefaultArenaMap is a (somewhat erroneously named) Pagemap sparse array /
tree for these provenance roots. Nothing is stored on non-StrictProvenance
architectures.
* In the Sandbox test, give an example of a different ArenaMap structure, which
confines amplification to sandbox memory.
* Adjust some other tests to compile.
We're going to try calling (our, out-of-sandbox) ->dealloc() on pointers into
sandbox memory, so, when CHERIfied, we will need amplification authority over
that memory. Rather than asking the PAL for memory directly, ask the
out-of-sandbox snmalloc so that it will, on CHERI, go through its whole dance
with its AuthMap.
* Replace time measuring macro
The DO_TIME macro was used originally to get performance numbers. The
macro makes tests hard to debug. This commit replaces it with a proper
C++ class with destructor.
* Bug fix
If the superslab meta data is large, then the calculation for the
sizeclasses that could use the short slab was incorrect. This fixes
that calculation.
Co-authored-by: Nathaniel Wesley Filardo <nfilardo@microsoft.com>
The initial performance monitoring for snmalloc used timing of small
operations to guide the design. This feature has not been maintained or
used for several years.
This commit removes the feature.
The previous reciprocal division branch on the prime that the sizeclass
was constructed from. All sizeclasses can be represented as
2^n * {1,3,5,7}
This lead to a very small table, but some work to calculate the
appropriate shifts and multiplications to implement reciprocal division.
This commit uses a completely uniform representation for every
sizeclass using a lookup table. Due to the precise ranges that we query
the modulus and rounding on, we can do this much more efficiently.
The func-release-rounding exhaustively tests all the queries we are
interested in.
Like alloc_size, this will require amplification internally.
This patch also restores performance to the status quo ante; Clang can once
again see enough to generate the same code as it did before de-static-ing
alloc_size.
We're going to need to amplify the pointer and that's going to require access
to our AddressSpaceManager, which we only get non-statically through our
LargeAlloc.
This patch unto itself makes the world slower, perhaps because Clang can't see
the certainty of aliasing of the static and non-static paths to the same
structure. However, when we also de-static external_pointer, that goes away and
things return to the status quo ante.
This will let us use Pagemaps further down the dependency stack (specifically,
we're going to want a Pagemap inside the AddressSpaceManager) by letting us
manually tie the knot rather than rely on GlobalVirtual and
default_memory_provider() being defined by the time we want a Pagemap.
- Make GlobalPagemapTemplate and ExternalGlobalPagemap generic in the type of
the pagemap they're encapsulating.
We're going to want to use these for other kinds of pagemaps in the near
future.
- Rename snmalloc_pagemap_global_get to snmalloc_chunkmap_global_get.
- Rename GlobalPagemap to GlobalChunkmap.
MSVC has strong opinions on implicit conversions as used in CI, while Clang both
locally and in CI has weaker opinions. In an effort to avoid subsequent
roundtrips through CI, make clang more strict. Adding -Wconversion definitely
increases the strength of clang's opinions, apparently to include frowning on
some that even MSVC considers OK, so go make explicit the current implicit
behavior.
* Make LowMemoryNotification object allocated
This makes a separate allocation for the callback object. This makes
it easier for different callbacks to be used.
* Add reserve_with_leftover to address_space
The address_space now supports reserving for non-power of 2 allocations
and the space that is used for rounding up is retained by the
address_space. This means that we can more tightly pack the allocators
internal objects.
Summary of changes:
- Add a new PAL that doesn't allocate memory, which can be used with a
memory provider that is pre-initialised with a range of memory.
- Add a `NoAllocation` PAL property so that the methods on a PAL that
doesn't support dynamically reserving address space will never be
called and therefore don't need to be implemented.
- Slightly refactor the memory provider class so that it has a narrower
interface with LargeAlloc and is easier to proxy.
- Allow the address space manager and the memory provider to be
initialised with a range of memory.
This may eventually also remove the need for (or, at least, simplify)
the Open Enclave PAL.
This commit also ends up with a few other cleanups:
- The `malloc_useable_size` CMake test that checks whether the
parameter is const qualified was failing on FreeBSD where this
function is declared in `malloc_np.h` but where including
`malloc.h` raises an error. This should now be more robust.
- The BSD aligned PAL inherited from the BSD PAL, which does not
expose aligned allocation. This meant that it exposed both the
aligned and non-aligned allocation interfaces and so happily
accepted incorrect `constexpr` if blocks that expected one or
the other but accidentally required both to exist. The unaligned
function is now deleted so the same failures that appear in CI should
appear locally for anyone using this PAL.
* Add concept of natural alignment to tests.
snmalloc naturally aligns blocks very heavily, so that
the largest power-of-two in the rounded size is the alignment.
This checks that in the test, and provides a method for
finding the natural alignment of a block.
* Improve USE_MALLOC to provide alignment
snmalloc provides a lot of alginment guarantees. This ensures that when
we pass through to the system allocator we still get those alignment
guarantees.
The commit also fixes the tests to work with USE_MALLOC, and builds a
set of unit tests for ctest to check behaviour.
The pagemap was double incrementing the index level. This did not
exhibit in any use case of the pagemap as it only used 0 or 1 level of
intermediate index for all current use cases.
This commit fixes the bug, and adds a test that uses the pagemap in a
different configuration that has multiple levels of intermediate index
node.
These statistics can be maintained with effectively zero cost to
realistic applications. They do not track the precise amount of
memory used, but are an over-approximation.
