| Age | Commit message (Collapse) | Author |
|---|
|
Due to comparison as a signed integer, when getting an unsigned atomic
in the range 2^63-1..2^64-1 (when the most significant bit was set), the
heap could get corrupted when the integer was retrieved: hsz would get
set to zero, but the code proceeded to build a bignum.
Steps to reproduce (at least on x86_64):
$ erl
1> A = atomics:new(1,[{signed,false}]).
2> atomics:put(A,1,18446744073709551615).
3> atomics:get(A,1).
At the last step, the shell would print some garbage and hang.
|
|
for set_permission and set_owner.
|
|
When seq_trace:reset_trace could be called while a
process was doing a dirty GC. This triggered a race
where all signals was moved to the internal signal
queue during the GC which in turn caused the a heap
overrun problem.
This fix makes it so that the main and msgq lock are
taken before the clear. This will make sure that we
are allowed to do the clear.
|
|
|
|
Dispatching a function and return never use the next instruction.
It's unlikely for raw_raise to use the next instruction.
|
|
Simplify implementation of GC BIFs
|
|
Summary: This commit simplifies the implementation of the "GC BIFs" so
that they no longer need to do a garbage collection, removing duplicate
code for all GC BIFs in the runtime system, as well as potentially
reducing the size of the loaded BEAM code by using shorter
instructions calling those BIFs.
A GC BIF is a guard BIF that will do a garbage
collection if it needs to build anything on the heap.
For example, `abs/1` is a GC BIF because it might need to
allocate space on the heap (if the result is a floating point
number or the resulting integer is a bignum).
Before R12, a guard BIF (such as `abs/1`) that need to allocate
heap space would allocate outside of process's main heap, in
a heap fragment.
GC BIFs were introduced in R12B to support literals. During garbage
collection it become necessary to quickly test whether a term was
a literal. To make the check simple, guards BIFs were no longer
allowed to create heap fragments. Instead GC BIFs were introduced.
In OTP 19, the implementation of literals was changed to support
storing messages in heap fragments outside of the main heap for a
process. That change again made it allowed for guard BIFs to create
heap fragments when they need to build terms on the heap.
It would even be possible for the guard BIFs to build directly
on the main heap if there is room there, because the compiler
assumes that a new `test_heap/2` instruction must be emitted
when building anything after calling a GC BIF. (We don't do that
in this commit; see below.)
This commit simplifies the implementation of the GC BIFs in
the runtime system.
Each GC BIF had a dual implementation: one that was used when the GC
BIF was called directly and one used when it was called via
`apply/3`. For example, `abs/1` was implemented in `abs_1()` and
`erts_gc_abs_1()`. This commit removes the GC version of each BIF. The
other version that allocates heap space using `HAlloc()` is updated to
use the new `HeapFragOnlyAlloc()` macro that will allocate heap
space in a heap fragment outside of the main heap.
Because the BIFs will allocate outside of the main heap, the same
`bif` instructions used by nonbuilding BIFs can be used for the
(former) GC BIFs. Those instructions don't use the macros that save
and restore the heap and stack pointers (SWAPOUT/SWAPIN). If the
former GC BIFs would build on the main heap, either new instructions
would be needed, or SWAPOUT/SWAPIN instructions would need to be added
to the `bif` instructions.
Instructions that call the former GC BIFs don't need the operand
that specifies the number of live X registers. Therefore, the
instructions that call the BIFs are usually one word shorter.
|
|
* bjorn/erts/remove-faulty-assertion:
erl_bif_list: Remove faulty assertion
|
|
* maint:
Fix reading beyond end of bignum in integer squaring
|
|
The multiplication of two bignums is specially optimized when the two
operands have the same address, because squaring can be done more
efficiently than multiplication of two arbitrary integers. That is,
expressions such as `I * I` will be calculated by squaring the value
of `I`.
The optimized function for squaring would read one word beyond the
end of the bignum in the last iteration of a loop. The garbage
value would never be used. In almost all circumstances that would
be harmless. Only if the read word happened to fall on the start
of an unmapped page would the runtime crash. That is unlikely
to happen because most bignums are stored on a process heap, and
since the stack is located at the other end of the block that the
heap is located in, the word beyond the end of bignum is guaranteed
to be readable.
|
|
* sverker/erts/ets-debug-test-cuddle:
erts: Fix volatile ets test case failures on debug VM
|
|
The variable can be an empty list.
|
|
Without this fix asserts would trigger in debug build
but nothing else would break.
|
|
jhogberg/john/erts/mark-pooled-free-blocks-unused/OTP-15075
Mark free blocks in pooled carriers as unused
|
|
This lets the OS reclaim the physical memory associated with these
blocks which reduces the impact of long-lived awkward allocations.
A small allocated block will still keep a huge carrier alive, but
the unused part of the carrier will now be available to the OS.
Co-authored-by: Dmytro Lytovchenko <[email protected]>
|
|
Conflicts:
erts/emulator/beam/erl_process.c
|
|
* lukas/OTP-21.1.1/scheduler_pollset/OTP-15475:
erts: Move fds with active true behaviour to own pollset
erts: Fix lists_member_2 reduction count
erts: Allow code_model_small to be set in xcomp setting
erts: Implement delay_send using timer instead of poll
erts: Optimize driver_set_timer(0) to fire at once
erts: Optimize the inet driver multi timers for one timer
erts: Move all inet tcp CONNECTED timers to multi timer
erts: Add erts_io_notify_port_task_executed to check_io msacc state
erts: Add pre-alloc to ALLOC msacc state
erts: Make thr prgr wakeup current or sched 1
erts: Pass thread progress data where possible
|
|
At start of the VM a poll-set that the schedulers
will check is created where fds that have triggered
many (at the moment, many means 10) times without
being deselected inbetween. In this scheduler specific
poll-set fds do not use ONESHOT, which means that the
number of syscalls goes down dramatically for such fds.
This pollset is introduced in order to handle fds that
are used by the erlang distribution and that never
change their state from {active, true}.
This pollset only handles ready_input events,
ready_output is still handled by the poll threads.
During overload, polling the scheduler poll-set is done
on a 10ms timer.
|
|
On a 32-bit machine, `beam_makeops` would generate incorrect
pack instructions for instructions such as:
i_plus x x j? d
See the added comment block for a detailed description of the
problem and its fix.
|
|
Symptom:
Test cases with small key ranges sometimes failed on debug VM with:
"No routing nodes in table?
Debug feature 'ets_force_split' does not seem to work."
Solution:
Don't provoke randomly joins when force_split is set.
|
|
|
|
|
|
A copy has to be made of the message as there is
a trace token. There was a bug where the actual
message was incorrectly modified even if it was a
literal.
|
|
|
|
* lukas/erts/CFLAGS-O-check/OTP-15465:
erts: Fix some 32-bit gcc warnings
erts: Add check that a -O flag is present in CFLAGS
|
|
|
|
OTP-15474
|
|
The previous implementation uses a round-trip in the poll-set
to simulate a yield of the port context. With the poll thread
implementation this is no longer a good idea as it generated a
lot more work for the system. So this commit changes the
implementation to use a timer instead.
OTP-15471
|
|
By optimizing driver_set_timer for 0 we can use it
instead of select to do a yield in the driver.
Use full for delay_send in the inet driver.
OTP-15472
|
|
The most common case for any socket is to have zero or one
timer, so we optimize for the one case. The only case when
we have more than one timer is when the multi accept feature
is used.
|
|
|
|
OTP-15450
|
|
OTP-15450
|
|
|
|
* sverker/erts/sendfile-error-bug/ERL-784/OTP-15461:
erts: Fix hanging sendfile bugs when socket closes unexpectedly
erts: Fix unexpected inet_reply message from failing file:sendfile
erts: Fix bug in sendfile for active socket
|
|
|
|
* sverker/erts/cuddle-driver_SUITE:
erts: Fix faulty assert in driver_SUITE
erts: Improve driver_SUITE:smp_select
|
|
|
|
* john/erts/assert-dirty-aux-work:
Abort when aux work runs on a dirty scheduler
|
|
A failing file:sendfile call would often send a message
{inet_reply, Port, {error, Reason}} that would pollute the mailbox
of the calling process.
TCP_REQ_SENDFILE has its own reply messages format
{sendfile, _, _} and does not expect an inet_reply message.
Solution: Suppress inet_reply error message if TCP_ADDF_SENDFILE
is set.
|
|
driver_select() was called after port had been killed
by tcp_inet_sendfile() calling tcp_send_error().
|
|
|
|
* lukas/erts/fix-msacc-gc-states/OTP-15450:
erts: Fix msacc GC states on dirty scheds
|
|
While the system will keep working, the aux work will never run
and the affected scheduler never goes to sleep. OTP-15446 is a
good example of this.
As this error easily flies under the radar it's best to make it
immediately visible. The assertions we had in debug builds were
clearly not enough to catch all sources of this problem.
|
|
* maint:
erts: fix attempt to start timer when executing on dirty scheduler
|
|
erts: fix attempt to start timer when executing on dirty scheduler
OTP-15446
|
|
Since OTP R20, there is a possibility for MAJOR garbage collection to
run on dirty scheduler. So DistEntry destructor is being called on
dirty scheduler as well. This, in turn, leads to an attempt to schedule
timer on a dirty scheduler too, which is impossible (and will assert
on debug build, but does succeed for release build, creating an
infinite busy loop, since aux work wakes scheduler up, but dirty
scheduler cannot execute aus work).
There is a similar method in erl_hl_timer, see erts_start_timer_callback.
|
|
|
|
* sverker/erts/atomics-counters/OTP-13468:
erts: Fix bug in counters
erts: Refactor erl_bif_counters.c
|
|
Wow, that could have been embarrassing.
|
