qemu_vfree() is the companion free function to qemu_memalign(); put
it in memalign.c so the allocation and free functions are together.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20220226180723.1706285-9-peter.maydell@linaro.org
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
The qemu_try_memalign() functions for POSIX and Windows used to be
significantly different, but these days they are identical except for
the actual allocation function called, and the POSIX version already
has to have ifdeffery for different allocation functions.
Move to a single implementation in memalign.c, which uses the Windows
_aligned_malloc if we detect that function in meson.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20220226180723.1706285-7-peter.maydell@linaro.org
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Currently qemu_try_memalign()'s behaviour if asked to allocate
0 bytes is rather variable:
* on Windows, we will assert
* on POSIX platforms, we get the underlying behaviour of
the posix_memalign() or equivalent function, which may be
either "return a valid non-NULL pointer" or "return NULL"
Explictly check for 0 byte allocations, so we get consistent
behaviour across platforms. We handle them by incrementing the size
so that we return a valid non-NULL pointer that can later be passed
to qemu_vfree(). This is permitted behaviour for the
posix_memalign() API and is the most usual way that underlying
malloc() etc implementations handle a zero-sized allocation request,
because it won't trip up calling code that assumes NULL means an
error. (This includes our own qemu_memalign(), which will abort on
NULL.)
This change is a preparation for sharing the qemu_try_memalign() code
between Windows and POSIX.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
We implement qemu_memalign() in both oslib-posix.c and oslib-win32.c,
but the two versions are essentially the same: they call
qemu_try_memalign(), and abort() after printing an error message if
it fails. The only difference is that the win32 version prints the
GetLastError() value whereas the POSIX version prints
strerror(errno). However, this is a bug in the win32 version: in
commit dfbd0b873a in 2020 we changed the implementation of
qemu_try_memalign() from using VirtualAlloc() (which sets the
GetLastError() value) to using _aligned_malloc() (which sets errno),
but didn't update the error message to match.
Replace the two separate functions with a single version in a
new memalign.c file, which drops the unnecessary extra qemu_oom_check()
function and instead prints a more useful message including the
requested size and alignment as well as the errno string.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20220226180723.1706285-4-peter.maydell@linaro.org
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
The qemu_oom_check() function, which we define in both oslib-posix.c
and oslib-win32.c, is now used only locally in that file; make it
static.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20220226180723.1706285-3-peter.maydell@linaro.org
The function qemu_madvise() and the QEMU_MADV_* constants associated
with it are used in only 10 files. Move them out of osdep.h to a new
qemu/madvise.h header that is included where it is needed.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20220208200856.3558249-2-peter.maydell@linaro.org
We're missing an unlock in case installing the signal handler failed.
Fortunately, we barely see this error in real life.
Fixes: a960d6642d ("util/oslib-posix: Support concurrent os_mem_prealloc() invocation")
Fixes: CID 1468941
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta@ionos.com>
Cc: Daniel P. Berrangé <berrange@redhat.com>
Cc: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20220111120830.119912-1-david@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@ionos.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Temporarily modifying the SIGBUS handler is really nasty, as we might be
unlucky and receive an MCE SIGBUS while having our handler registered.
Unfortunately, there is no way around messing with SIGBUS when
MADV_POPULATE_WRITE is not applicable or not around.
Let's forward SIGBUS that don't belong to us to the already registered
handler and document the situation.
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20211217134611.31172-8-david@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Add a mutex to protect the SIGBUS case, as we cannot mess concurrently
with the sigbus handler and we have to manage the global variable
sigbus_memset_context. The MADV_POPULATE_WRITE path can run
concurrently.
Note that page_mutex and page_cond are shared between concurrent
invocations, which shouldn't be a problem.
This is a preparation for future virtio-mem prealloc code, which will call
os_mem_prealloc() asynchronously from an iothread when handling guest
requests.
Reviewed-by: Pankaj Gupta <pankaj.gupta@ionos.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20211217134611.31172-7-david@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Let's simplify the case when we only want a single thread and don't have
to mess with signal handlers.
Reviewed-by: Pankaj Gupta <pankaj.gupta@ionos.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20211217134611.31172-6-david@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Let's limit the number of threads to something sane, especially that
- We don't have more threads than the number of pages we have
- We don't have threads that initialize small (< 64 MiB) memory
Reviewed-by: Pankaj Gupta <pankaj.gupta@ionos.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20211217134611.31172-5-david@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Let's minimize the number of global variables to prepare for
os_mem_prealloc() getting called concurrently and make the code a bit
easier to read.
The only consumer that really needs a global variable is the sigbus
handler, which will require protection via a mutex in the future either way
as we cannot concurrently mess with the SIGBUS handler.
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20211217134611.31172-4-david@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Let's sense support and use it for preallocation. MADV_POPULATE_WRITE
does not require a SIGBUS handler, doesn't actually touch page content,
and avoids context switches; it is, therefore, faster and easier to handle
than our current approach.
While MADV_POPULATE_WRITE is, in general, faster than manual
prefaulting, and especially faster with 4k pages, there is still value in
prefaulting using multiple threads to speed up preallocation.
More details on MADV_POPULATE_WRITE can be found in the Linux commits
4ca9b3859dac ("mm/madvise: introduce MADV_POPULATE_(READ|WRITE) to prefault
page tables") and eb2faa513c24 ("mm/madvise: report SIGBUS as -EFAULT for
MADV_POPULATE_(READ|WRITE)"), and in the man page proposal [1].
This resolves the TODO in do_touch_pages().
In the future, we might want to look into using fallocate(), eventually
combined with MADV_POPULATE_READ, when dealing with shared file/fd
mappings and not caring about memory bindings.
[1] https://lkml.kernel.org/r/20210816081922.5155-1-david@redhat.com
Reviewed-by: Pankaj Gupta <pankaj.gupta@ionos.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20211217134611.31172-3-david@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Let's prepare touch_all_pages() for returning differing errors. Return
an error from the thread and report the last processed error.
Translate SIGBUS to -EFAULT, as a SIGBUS can mean all different kind of
things (memory error, read error, out of memory). When allocating memory
fails via the current SIGBUS-based mechanism, we'll get:
os_mem_prealloc: preallocating memory failed: Bad address
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20211217134611.31172-2-david@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Let's introduce RAM_NORESERVE, allowing mmap'ing with MAP_NORESERVE. The
new flag has the following semantics:
"
RAM is mmap-ed with MAP_NORESERVE. When set, reserving swap space (or huge
pages if applicable) is skipped: will bail out if not supported. When not
set, the OS will do the reservation, if supported for the memory type.
"
Allow passing it into:
- memory_region_init_ram_nomigrate()
- memory_region_init_resizeable_ram()
- memory_region_init_ram_from_file()
... and teach qemu_ram_mmap() and qemu_anon_ram_alloc() about the flag.
Bail out if the flag is not supported, which is the case right now for
both, POSIX and win32. We will add Linux support next and allow specifying
RAM_NORESERVE via memory backends.
The target use case is virtio-mem, which dynamically exposes memory
inside a large, sparse memory area to the VM.
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Acked-by: Eduardo Habkost <ehabkost@redhat.com> for memory backend and machine core
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210510114328.21835-9-david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Let's pass flags instead of bools to prepare for passing other flags and
update the documentation of qemu_ram_mmap(). Introduce new QEMU_MAP_
flags that abstract the mmap() PROT_ and MAP_ flag handling and simplify
it.
We expose only flags that are currently supported by qemu_ram_mmap().
Maybe, we'll see qemu_mmap() in the future as well that can implement these
flags.
Note: We don't use MAP_ flags as some flags (e.g., MAP_SYNC) are only
defined for some systems and we want to always be able to identify
these flags reliably inside qemu_ram_mmap() -- for example, to properly
warn when some future flags are not available or effective on a system.
Also, this way we can simplify PROT_ handling as well.
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Acked-by: Eduardo Habkost <ehabkost@redhat.com> for memory backend and machine core
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210510114328.21835-8-david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
OpenBSD prior to 6.3 required a workaround to utilize fcntl(F_SETFL) on memory
devices.
Since modern verions of OpenBSD that are only officialy supported and buildable
on do not have this issue I am garbage collecting this workaround.
Signed-off-by: Brad Smith <brad@comstyle.com>
Message-Id: <YGYECGXQhdamEJgC@humpty.home.comstyle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Allow RAM MemoryRegion to be created from an offset in a file, instead
of allocating at offset of 0 by default. This is needed to synchronize
RAM between QEMU & remote process.
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 609996697ad8617e3b01df38accc5c208c24d74e.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
There is currently no way to open(O_RDONLY) and mmap(PROT_READ) when
creating a memory region from a file. This functionality is needed since
the underlying host file may not allow writing.
Add a bool readonly argument to memory_region_init_ram_from_file() and
the APIs it calls.
Extend memory_region_init_ram_from_file() rather than introducing a
memory_region_init_rom_from_file() API so that callers can easily make a
choice between read/write and read-only at runtime without calling
different APIs.
No new RAMBlock flag is introduced for read-only because it's unclear
whether RAMBlocks need to know that they are read-only. Pass a bool
readonly argument instead.
Both of these design decisions can be changed in the future. It just
seemed like the simplest approach to me.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Message-Id: <20210104171320.575838-2-stefanha@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
qemu_try_memalign() expects a power of 2 alignment:
- posix_memalign(3):
The address of the allocated memory will be a multiple of alignment,
which must be a power of two and a multiple of sizeof(void *).
- _aligned_malloc()
The alignment value, which must be an integer power of 2.
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20201021173803.2619054-3-philmd@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
LLVM/Clang, supports runtime checks for forward-edge Control-Flow
Integrity (CFI).
CFI on indirect function calls (cfi-icall) ensures that, in indirect
function calls, the function called is of the right signature for the
pointer type defined at compile time.
For this check to work, the code must always respect the function
signature when using function pointer, the function must be defined
at compile time, and be compiled with link-time optimization.
This rules out, for example, shared libraries that are dynamically loaded
(given that functions are not known at compile time), and code that is
dynamically generated at run-time.
This patch:
1) Introduces the CONFIG_CFI flag to support cfi in QEMU
2) Introduces a decorator to allow the definition of "sensitive"
functions, where a non-instrumented function may be called at runtime
through a pointer. The decorator will take care of disabling cfi-icall
checks on such functions, when cfi is enabled.
3) Marks functions currently in QEMU that exhibit such behavior,
in particular:
- The function in TCG that calls pre-compiled TBs
- The function in TCI that interprets instructions
- Functions in the plugin infrastructures that jump to callbacks
- Functions in util that directly call a signal handler
Signed-off-by: Daniele Buono <dbuono@linux.vnet.ibm.com>
Acked-by: Alex Bennée <alex.bennee@linaro.org
Message-Id: <20201204230615.2392-3-dbuono@linux.vnet.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If the exec_dir cannot be retrieved, just assume it's the installation
directory that was specified at configure time. This makes it simpler
to reason about what the callers will do if they get back an empty
path.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Just return the directory without requiring the caller to free it.
This also removes a bogus check for NULL in os_find_datadir and
module_load_one; g_strdup of a static variable cannot return NULL.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We want to introduce a new version of qemu_open() that uses an Error
object for reporting problems and make this it the preferred interface.
Rename the existing method to release the namespace for the new impl.
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
This will be used in a future patch. For POSIX systems _SC_PHYS_PAGES
isn't standardised but at least appears in the man pages for
Open/FreeBSD. The result is advisory so any users of it shouldn't just
fail if we can't work it out.
The win32 stub currently returns 0 until someone with a Windows system
can develop and test a patch.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Cc: BALATON Zoltan <balaton@eik.bme.hu>
Cc: Christian Ehrhardt <christian.ehrhardt@canonical.com>
Message-Id: <20200724064509.331-5-alex.bennee@linaro.org>
Implement qemu_get_thread_id() for OpenBSD hosts, using
getthrid().
Signed-off-by: David Carlier <devnexen@gmail.com>
Reviewed-by: Brad Smith <brad@comstyle.com>
Message-id: CA+XhMqxD6gQDBaj8tX0CMEj3si7qYKsM8u1km47e_-U7MC37Pg@mail.gmail.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
[PMM: tidied up commit message]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
qemu_set_nonblock() checks that the file descriptor can be used and, if
not, crashes QEMU. An assert() is used for that. The use of assert() is
used to detect programming error and the coredump will allow to debug
the problem.
But in the case of the tap device, this assert() can be triggered by
a misconfiguration by the user. At startup, it's not a real problem, but it
can also happen during the hot-plug of a new device, and here it's a
problem because we can crash a perfectly healthy system.
For instance:
# ip link add link virbr0 name macvtap0 type macvtap mode bridge
# ip link set macvtap0 up
# TAP=/dev/tap$(ip -o link show macvtap0 | cut -d: -f1)
# qemu-system-x86_64 -machine q35 -device pcie-root-port,id=pcie-root-port-0 -monitor stdio 9<> $TAP
(qemu) netdev_add type=tap,id=hostnet0,vhost=on,fd=9
(qemu) device_add driver=virtio-net-pci,netdev=hostnet0,id=net0,bus=pcie-root-port-0
(qemu) device_del net0
(qemu) netdev_del hostnet0
(qemu) netdev_add type=tap,id=hostnet1,vhost=on,fd=9
qemu-system-x86_64: .../util/oslib-posix.c:247: qemu_set_nonblock: Assertion `f != -1' failed.
Aborted (core dumped)
To avoid that, add a function, qemu_try_set_nonblock(), that allows to report the
problem without crashing.
In the same way, we also update the function for vhostfd in net_init_tap_one() and
for fd in net_init_socket() (both descriptors are provided by the user and can
be wrong).
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
This function offers operating system agnostic way to fetch host
name. It is implemented for both POSIX-like and Windows systems.
Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
The qemu_init_exec_dir() function is inherently non-portable;
provide an implementation for Haiku hosts.
Signed-off-by: David Carlier <devnexen@gmail.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20200703145614.16684-9-peter.maydell@linaro.org
[PMM: Expanded commit message]
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Regularize our handling of <sys/signal.h>: currently we include it in
osdep.h, but only for OpenBSD, and we include it without an ifdef
guard in a couple of C files. This causes problems for Haiku, which
doesn't have that header.
Instead, check in configure whether sys/signal.h exists, and if it
does then always include it from osdep.h.
Signed-off-by: David Carlier <devnexen@gmail.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20200703145614.16684-5-peter.maydell@linaro.org
[PMM: Expanded commit message; rename to HAVE_SYS_SIGNAL_H]
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
From 3025a0ce3fdf7d3559fc35a52c659f635f5c750c Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Tue, 26 May 2020 21:35:27 +0100
Subject: [PATCH] util/oslib-posix : qemu_init_exec_dir implementation for Mac
Using dyld API to get the full path of the current process.
Signed-off-by: David Carlier <devnexen@gmail.com>
Message-id: CA+XhMqxwC10XHVs4Z-JfE0-WLAU3ztDuU9QKVi31mjr59HWCxg@mail.gmail.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
getpid is good enough in a mono thread context, however thr_self/_lwp_self
reflects the real current thread identifier from a given process.
Signed-off-by: David Carlier <devnexen@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: David Carlier <devnexen@gmail.com>
In touch_all_pages, if the mutex is not taken around qemu_cond_broadcast,
qemu_cond_broadcast may be called before all touch page threads enter
qemu_cond_wait. In this case, the touch page threads wait forever for the
main thread to wake them up, causing a deadlock.
Signed-off-by: Bauerchen <bauerchen@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The mutex and condition variable were never initialized, causing
-mem-prealloc to abort with an assertion failure.
Fixes: 037fb5eb39
Reported-by: Marc Hartmayer <mhartmay@linux.ibm.com>
Cc: bauerchen <bauerchen@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
[desc]:
Large memory VM starts slowly when using -mem-prealloc, and
there are some areas to optimize in current method;
1、mmap will be used to alloc threads stack during create page
clearing threads, and it will attempt mm->mmap_sem for write
lock, but clearing threads have hold read lock, this competition
will cause threads createion very slow;
2、methods of calcuating pages for per threads is not well;if we use
64 threads to split 160 hugepage,63 threads clear 2page,1 thread
clear 34 page,so the entire speed is very slow;
to solve the first problem,we add a mutex in thread function,and
start all threads when all threads finished createion;
and the second problem, we spread remainder to other threads,in
situation that 160 hugepage and 64 threads, there are 32 threads
clear 3 pages,and 32 threads clear 2 pages.
[test]:
320G 84c VM start time can be reduced to 10s
680G 84c VM start time can be reduced to 18s
Signed-off-by: bauerchen <bauerchen@tencent.com>
Reviewed-by: Pan Rui <ruippan@tencent.com>
Reviewed-by: Ivan Ren <ivanren@tencent.com>
[Simplify computation of the number of pages per thread. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
There are three page size in qemu:
real host page size
host page size
target page size
All of them have dedicate variable to represent. For the last two, we
use the same form in the whole qemu project, while for the first one we
use two forms: qemu_real_host_page_size and getpagesize().
qemu_real_host_page_size is defined to be a replacement of
getpagesize(), so let it serve the role.
[Note] Not fully tested for some arch or device.
Signed-off-by: Wei Yang <richardw.yang@linux.intel.com>
Message-Id: <20191013021145.16011-3-richardw.yang@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Neither stat(2) nor lseek(2) report the size of Linux devdax pmem
character device nodes. Commit 314aec4a6e
("hostmem-file: reject invalid pmem file sizes") added code to
hostmem-file.c to fetch the size from sysfs and compare against the
user-provided size=NUM parameter:
if (backend->size > size) {
error_setg(errp, "size property %" PRIu64 " is larger than "
"pmem file \"%s\" size %" PRIu64, backend->size,
fb->mem_path, size);
return;
}
It turns out that exec.c:qemu_ram_alloc_from_fd() already has an
equivalent size check but it skips devdax pmem character devices because
lseek(2) returns 0:
if (file_size > 0 && file_size < size) {
error_setg(errp, "backing store %s size 0x%" PRIx64
" does not match 'size' option 0x" RAM_ADDR_FMT,
mem_path, file_size, size);
return NULL;
}
This patch moves the devdax pmem file size code into get_file_size() so
that we check the memory size in a single place:
qemu_ram_alloc_from_fd(). This simplifies the code and makes it more
general.
This also fixes the problem that hostmem-file only checks the devdax
pmem file size when the pmem=on parameter is given. An unchecked
size=NUM parameter can lead to SIGBUS in QEMU so we must always fetch
the file size for Linux devdax pmem character device nodes.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20190830093056.12572-1-stefanha@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In my "build everything" tree, changing qemu/main-loop.h triggers a
recompile of some 5600 out of 6600 objects (not counting tests and
objects that don't depend on qemu/osdep.h). It includes block/aio.h,
which in turn includes qemu/event_notifier.h, qemu/notify.h,
qemu/processor.h, qemu/qsp.h, qemu/queue.h, qemu/thread-posix.h,
qemu/thread.h, qemu/timer.h, and a few more.
Include qemu/main-loop.h only where it's needed. Touching it now
recompiles only some 1700 objects. For block/aio.h and
qemu/event_notifier.h, these numbers drop from 5600 to 2800. For the
others, they shrink only slightly.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20190812052359.30071-21-armbru@redhat.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com>
No header includes qemu-common.h after this commit, as prescribed by
qemu-common.h's file comment.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20190523143508.25387-5-armbru@redhat.com>
[Rebased with conflicts resolved automatically, except for
include/hw/arm/xlnx-zynqmp.h hw/arm/nrf51_soc.c hw/arm/msf2-soc.c
block/qcow2-refcount.c block/qcow2-cluster.c block/qcow2-cache.c
target/arm/cpu.h target/lm32/cpu.h target/m68k/cpu.h target/mips/cpu.h
target/moxie/cpu.h target/nios2/cpu.h target/openrisc/cpu.h
target/riscv/cpu.h target/tilegx/cpu.h target/tricore/cpu.h
target/unicore32/cpu.h target/xtensa/cpu.h; bsd-user/main.c and
net/tap-bsd.c fixed up]
besides the existing 'shared' flags, we are going to add
'is_pmem' to qemu_ram_mmap(), which indicated the memory backend
file is a persist memory.
Signed-off-by: Haozhong Zhang <haozhong.zhang@intel.com>
Signed-off-by: Zhang Yi <yi.z.zhang@linux.intel.com>
Reviewed-by: Pankaj Gupta <pagupta@redhat.com>
Message-Id: <786c46862cfeb253ee0ea2f44d62ffe76edb7fa4.1549555521.git.yi.z.zhang@linux.intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Pankaj Gupta <pagupta@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Previous to OpenBSD 6.3 [1], fcntl(F_SETFL) is not permitted on
memory devices.
Trying this call sets errno to ENODEV ("not a memory device"):
19 ENODEV Operation not supported by device.
An attempt was made to apply an inappropriate function to a device,
for example, trying to read a write-only device such as a printer.
Do not assert fcntl failures in this specific case (errno set to ENODEV)
on OpenBSD. This fixes:
$ lm32-softmmu/qemu-system-lm32
assertion "f != -1" failed: file "util/oslib-posix.c", line 247, function "qemu_set_nonblock"
Abort trap (core dumped)
[1] The fix seems https://github.com/openbsd/src/commit/c2a35b387f9d3c
"fcntl(F_SETFL) invokes the FIONBIO and FIOASYNC ioctls internally, so
the memory devices (/dev/null, /dev/zero, etc) need to permit them."
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20190307142822.8531-2-philmd@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Guests started with NVDIMMs larger than the underlying host file produce
confusing errors inside the guest. This happens because the guest
accesses pages beyond the end of the file.
Check the pmem file size on startup and print a clear error message if
the size is invalid.
Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1669053
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Zhang Yi <yi.z.zhang@linux.intel.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20190214031004.32522-3-stefanha@redhat.com>
Reviewed-by: Wei Yang <richardw.yang@linux.intel.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Pankaj Gupta <pagupta@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
The commit 7197fb4058 ("util/mmap-alloc:
fix hugetlb support on ppc64") fixed Huge TLB mappings on ppc64.
However, we still need to consider the underlying huge page size
during munmap() because it requires that both address and length be a
multiple of the underlying huge page size for Huge TLB mappings.
Quote from "Huge page (Huge TLB) mappings" paragraph under NOTES
section of the munmap(2) manual:
"For munmap(), addr and length must both be a multiple of the
underlying huge page size."
On ppc64, the munmap() in qemu_ram_munmap() does not work for Huge TLB
mappings because the mapped segment can be aligned with the underlying
huge page size, not aligned with the native system page size, as
returned by getpagesize().
This has the side effect of not releasing huge pages back to the pool
after a hugetlbfs file-backed memory device is hot-unplugged.
This patch fixes the situation in qemu_ram_mmap() and
qemu_ram_munmap() by considering the underlying page size on ppc64.
After this patch, memory hot-unplug releases huge pages back to the
pool.
Fixes: 7197fb4058
Signed-off-by: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
Reviewed-by: Greg Kurz <groug@kaod.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Assert that the return value is not an error. This is like commit
7e6478e7d4 for qemu_set_cloexec.
Signed-off-by: Li Qiang <liq3ea@163.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Use MAP_STACK in qemu_alloc_stack() on OpenBSD.
Added to our 6.4 release.
MAP_STACK Indicate that the mapping is used as a stack. This
flag must be used in combination with MAP_ANON and
MAP_PRIVATE.
Implement MAP_STACK option for mmap(). Synchronous faults (pagefault and
syscall) confirm the stack register points at MAP_STACK memory, otherwise
SIGSEGV is delivered. sigaltstack() and pthread_attr_setstack() are modified
to create a MAP_STACK sub-region which satisfies alignment requirements.
Observe that MAP_STACK can only be set/cleared by mmap(), which zeroes the
contents of the region -- there is no mprotect() equivalent operation, so
there is no MAP_STACK-adding gadget.
Signed-off-by: Brad Smith <brad@comstyle.com>
Reviewed-by: Kamil Rytarowski <n54@gmx.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20181019125239.GA13884@humpty.home.comstyle.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Currently only file backed memory backend can
be created with a "share" flag in order to allow
sharing guest RAM with other processes in the host.
Add the "share" flag also to RAM Memory Backend
in order to allow remapping parts of the guest RAM
to different host virtual addresses. This is needed
by the RDMA devices in order to remap non-contiguous
QEMU virtual addresses to a contiguous virtual address range.
Moved the "share" flag to the Host Memory base class,
modified phys_mem_alloc to include the new parameter
and a new interface memory_region_init_ram_shared_nomigrate.
There are no functional changes if the new flag is not used.
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
