| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Not to be impacted by packets sent between sub-tests.
Signed-off-by: Matthieu Baerts <[email protected]>
Signed-off-by: Mat Martineau <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
'mptcp_connect' already has a timeout for poll() but in some cases, it
is not enough.
With "timeout" tool, we will force the command to fail if it doesn't
finish on time. Thanks to that, the script will continue and display
details about the current state before marking the test as failed.
Displaying this state is very important to be able to understand the
issue. Best to have our CI reporting the issue than just "the test
hanged".
Note that in mptcp_connect.sh, we were using a long timeout to validate
the fact we cannot create a socket if a sysctl is set. We don't need
this timeout.
In diag.sh, we want to send signals to mptcp_connect instances that have
been started in the netns. But we cannot send this signal to 'timeout'
otherwise that will stop the timeout and messages telling us SIGUSR1 has
been received will be printed. Instead of trying to find the right PID
and storing them in an array, we can simply use the output of
'ip netns pids' which is all the PIDs we want to send signal to.
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/160
Signed-off-by: Matthieu Baerts <[email protected]>
Signed-off-by: Mat Martineau <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
TL;DR
$ ./tools/testing/kunit/kunit.py run --kunitconfig=lib/kunit
Per suggestion from Ted [1], we can reduce the amount of typing by
assuming a convention that these files are named '.kunitconfig'.
In the case of [1], we now have
$ ./tools/testing/kunit/kunit.py run --kunitconfig=fs/ext4
Also add in such a fragment for kunit itself so we can give that as an
example more close to home (and thus less likely to be accidentally
broken).
[1] https://lore.kernel.org/linux-ext4/[email protected]/
Signed-off-by: Daniel Latypov <[email protected]>
Reviewed-by: David Gow <[email protected]>
Reviewed-by: Brendan Higgins <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Create .gitignore to hold the test file resctrl_tests generated after
compiling.
Suggested-by: Shuah Khan <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Dan reported following static checker warnings
tools/testing/selftests/resctrl/resctrl_val.c:545 measure_vals()
warn: 'bw_imc' unsigned <= 0
tools/testing/selftests/resctrl/resctrl_val.c:549 measure_vals()
warn: 'bw_resc_end' unsigned <= 0
These warnings are reported because
1. measure_vals() declares 'bw_imc' and 'bw_resc_end' as unsigned long
variables
2. Return value of get_mem_bw_imc() and get_mem_bw_resctrl() are assigned
to 'bw_imc' and 'bw_resc_end' respectively
3. The returned values are checked for <= 0 to see if the calls failed
Checking for < 0 for an unsigned value doesn't make any sense.
Fix this issue by changing the implementation of get_mem_bw_imc() and
get_mem_bw_resctrl() such that they now accept reference to a variable
and set the variable appropriately upon success and return 0, else return
< 0 on error.
Reported-by: Dan Carpenter <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
iMC (Integrated Memory Controller) counters are usually at
"/sys/bus/event_source/devices/" and are named as "uncore_imc_<n>".
num_of_imcs() function tries to count number of such iMC counters so that
it could appropriately initialize required number of perf_attr structures
that could be used to read these iMC counters.
num_of_imcs() function assumes that all the directories under this path
that start with "uncore_imc" are iMC counters. But, on some systems there
could be directories named as "uncore_imc_free_running" which aren't iMC
counters. Trying to read from such directories will result in "not found
file" errors and MBM/MBA tests will fail.
Hence, fix the logic in num_of_imcs() such that it looks at the first
character after "uncore_imc_" to check if it's a numerical digit or not. If
it's a digit then the directory represents an iMC counter, else, skip the
directory.
Reported-by: Reinette Chatre <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
umount_resctrlfs() directly attempts to unmount resctrl file system without
checking if resctrl FS is already mounted or not. It returns 0 on success
and on failure it prints an error message and returns an error status.
Calling umount_resctrlfs() when resctrl FS isn't mounted will return an
error status.
There could be situations where-in the caller might not know if resctrl
FS is already mounted or not and the caller might still want to unmount
resctrl FS if it's already mounted (For example during teardown).
To support above use cases, change umount_resctrlfs() such that it now
first checks if resctrl FS is already mounted or not and unmounts resctrl
FS only if it's already mounted.
unmount resctrl FS upon exit. For example, running only mba test on a
Broadwell (BDW) machine (MBA isn't supported on BDW CPU).
This happens because validate_resctrl_feature_request() would mount resctrl
FS to check if mba is enabled on the platform or not and finds that the H/W
doesn't support mba and hence will return false to run_mba_test(). This in
turn makes the main() function return without unmounting resctrl FS.
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
There could be two reasons why a resctrl feature might not be enabled on
the platform
1. H/W might not support the feature
2. Even if the H/W supports it, the user might have disabled the feature
through kernel command line arguments
Hence, any resctrl unit test (like cmt, cat, mbm and mba) before starting
the test will first check if the feature is enabled on the platform or not.
If the feature isn't enabled, then the test returns with an error status.
For example, if MBA isn't supported on a platform and if the user tries to
run MBA, the output will look like this
ok mounting resctrl to "/sys/fs/resctrl"
not ok MBA: schemata change
But, not supporting a feature isn't a test failure. So, instead of treating
it as an error, use the SKIP directive of the TAP protocol. With the
change, the output will look as below
ok MBA # SKIP Hardware does not support MBA or MBA is disabled
Suggested-by: Reinette Chatre <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Resctrl test suite main() function does the following things
1. Parses command line arguments passed by user
2. Some setup checks
3. Logic that calls into each unit test
4. Print result and clean up after running each unit test
Introduce wrapper functions for steps 3 and 4 to modularize the main()
function. Adding these wrapper functions makes it easier to add any logic
to each individual test.
Please note that this is a preparatory patch for the next one and no
functional changes are intended.
Suggested-by: Reinette Chatre <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Cache related tests (like CAT and CMT) depend on a variable called
no_of_bits to run. no_of_bits defines the number of contiguous bits
that should be set in the CBM mask and a user can pass a value for
no_of_bits using -n command line argument. If a user hasn't passed any
value, it defaults to 5 (randomly chosen value).
Hard coding no_of_bits to 5 will make the cache tests fail to run on
systems that support maximum cbm mask that is less than or equal to 5 bits.
Hence, don't hard code no_of_bits value.
If a user passes a value for "no_of_bits" using -n option, use it.
Otherwise, no_of_bits is equal to half of the maximum number of bits in
the cbm mask.
Please note that CMT test is still hard coded to 5 bits. It will change in
subsequent patches that change CMT test.
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
MBM unit test starts fill_buf (default built-in benchmark) in a new con_mon
group (c1, m1) and records resctrl reported mbm values and iMC (Integrated
Memory Controller) values every second. It does this for five seconds
(randomly chosen value) in total. It then calculates average of resctrl_mbm
values and imc_mbm values and if the difference is greater than 300 MB/sec
(randomly chosen value), the test treats it as a failure. MBA unit test is
similar to MBM but after every run it changes schemata.
Checking for a difference of 300 MB/sec doesn't look very meaningful when
the mbm values are changing over a wide range. For example, below are the
values running MBA test on SKL with different allocations
1. With 10% as schemata both iMC and resctrl mbm_values are around 2000
MB/sec
2. With 100% as schemata both iMC and resctrl mbm_values are around 10000
MB/sec
A 300 MB/sec difference between resctrl_mbm and imc_mbm values is
acceptable at 100% schemata but it isn't acceptable at 10% schemata because
that's a huge difference.
So, fix this by checking for percentage difference instead of absolute
difference i.e. check if the difference between resctrl_mbm value and
imc_mbm value is within 5% (randomly chosen value) of imc_mbm value. If the
difference is greater than 5% of imc_mbm value, treat it is a failure.
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Resctrl test suite before running any unit test (like cmt, cat, mbm and
mba) should first check if the feature is enabled (by kernel and not just
supported by H/W) on the platform or not.
validate_resctrl_feature_request() is supposed to do that. This function
intends to grep for relevant flags in /proc/cpuinfo but there are several
issues here
1. validate_resctrl_feature_request() calls fgrep() to get flags from
/proc/cpuinfo. But, fgrep() can only return a string with maximum of 255
characters and hence the complete cpu flags are never returned.
2. The substring search logic is also busted. If strstr() finds requested
resctrl feature in the cpu flags, it returns pointer to the first
occurrence. But, the logic negates the return value of strstr() and
hence validate_resctrl_feature_request() returns false if the feature is
present in the cpu flags and returns true if the feature is not present.
3. validate_resctrl_feature_request() checks if a resctrl feature is
reported in /proc/cpuinfo flags or not. Having a cpu flag means that the
H/W supports the feature, but it doesn't mean that the kernel enabled
it. A user could selectively enable only a subset of resctrl features
using kernel command line arguments. Hence, /proc/cpuinfo isn't a
reliable source to check if a feature is enabled or not.
The 3rd issue being the major one and fixing it requires changing the way
validate_resctrl_feature_request() works. Since, /proc/cpuinfo isn't the
right place to check if a resctrl feature is enabled or not, a more
appropriate place is /sys/fs/resctrl/info directory. Change
validate_resctrl_feature_request() such that,
1. For cat, check if /sys/fs/resctrl/info/L3 directory is present or not
2. For mba, check if /sys/fs/resctrl/info/MB directory is present or not
3. For cmt, check if /sys/fs/resctrl/info/L3_MON directory is present and
check if /sys/fs/resctrl/info/L3_MON/mon_features has llc_occupancy
4. For mbm, check if /sys/fs/resctrl/info/L3_MON directory is present and
check if /sys/fs/resctrl/info/L3_MON/mon_features has
mbm_<total/local>_bytes
Please note that only L3_CAT, L3_CMT, MBA and MBM are supported. CDP and L2
variants can be added later.
Reported-by: Reinette Chatre <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
check_resctrlfs_support() does the following
1. Checks if the platform supports resctrl file system or not by looking
for resctrl in /proc/filesystems
2. Calls opendir() on default resctrl file system path
(i.e. /sys/fs/resctrl)
3. Checks if resctrl file system is mounted or not by looking at
/proc/mounts
Steps 2 and 3 will fail if the platform does not support resctrl file
system. So, there is no need to check for them if step 1 fails.
Fix this by returning immediately if the platform does not support
resctrl file system.
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Add the config file for test dependencies.
Suggested-by: Shuah Khan <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Add a missing newline to the printed help text to improve readability.
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Reinette Chatre <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
show_cache_info() functions are defined separately in CAT and CMT
tests. But the functions are same for the tests and unnecessary
to be defined separately. Share the function by the tests.
Suggested-by: Shuah Khan <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Call kselftest APIs instead of using printf() to log test results
for cleaner code and better future extension.
Suggested-by: Shuah Khan <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
CMT (Cache Monitoring Technology) [1] is a H/W feature that reports cache
occupancy of a process. resctrl selftest suite has a unit test to test CMT
for LLC but the test is named as CQM (Cache Quality Monitoring).
Furthermore, the unit test source file is named as cqm_test.c and several
functions, variables, comments, preprocessors and statements widely use
"cqm" as either suffix or prefix. This rampant misusage of CQM for CMT
might confuse someone who is newly looking at resctrl selftests because
this feature is named CMT in the Intel Software Developer's Manual.
Hence, rename all the occurrences (unit test source file name, functions,
variables, comments and preprocessors) of cqm with cmt.
[1] Please see Intel SDM, Volume 3, chapter 17 and section 18 for more
information on CMT: https://software.intel.com/content/www/us/en/develop/articles/intel-sdm.html
Suggested-by: Reinette Chatre <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
resctrl test suite accepts command line arguments (like -b, -t, -n and -p)
as documented in the help. But passing -n and -p throws an invalid option
error. This happens because -n and -p are missing in the list of
characters that getopt() recognizes as valid arguments. Hence, they are
treated as invalid options.
Fix this by adding them to the list of characters that getopt() recognizes
as valid arguments. Please note that the main() function already has the
logic to deal with the values passed as part of these arguments and hence
no changes are needed there.
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
The resctrl tests can accept a CPU on which the tests are run and use
default of CPU #1 if it is not provided. In the CAT test a "sibling CPU"
is determined that is from the same package where another thread will be
run.
The current algorithm with which a "sibling CPU" is determined does not
take the provided/default CPU into account and when that CPU is the
first CPU in a package then the "sibling CPU" will be selected to be the
same CPU since it starts by picking the first CPU from core_siblings_list.
Fix the "sibling CPU" selection by taking the provided/default CPU into
account and ensuring a sibling that is a different CPU is selected.
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Reinette Chatre <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Checking resctrl features call strcmp() to compare feature strings
(e.g. "mba", "cat" etc). The checkings are error prone and don't have
good coding style. Define the constant strings in macros and call
strncmp() to solve the potential issues.
Suggested-by: Shuah Khan <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Reinette reported following compilation issue on Fedora 32, gcc version
10.1.1
/usr/bin/ld: resctrl_tests.o:<src_dir>/resctrl.h:65: multiple definition
of `bm_pid'; cache.o:<src_dir>/resctrl.h:65: first defined here
Other variables are ppid, tests_run, llc_occup_path, is_amd. Compiler
isn't happy because these variables are defined globally in two .c files
but are not declared as extern.
To fix issues for the global variables, declare them as extern.
Chang Log:
- Split this patch from v4's patch 1 (Shuah).
Reported-by: Reinette Chatre <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Reinette reported following compilation issue on Fedora 32, gcc version
10.1.1
/usr/bin/ld: cqm_test.o:<src_dir>/cqm_test.c:22: multiple definition of
`cache_size'; cat_test.o:<src_dir>/cat_test.c:23: first defined here
The same issue is reported for long_mask, cbm_mask, count_of_bits etc
variables as well. Compiler isn't happy because these variables are
defined globally in two .c files namely cqm_test.c and cat_test.c and
the compiler during compilation finds that the variable is already
defined (multiple definition error).
Taking a closer look at the usage of these variables reveals that these
variables are used only locally in functions such as cqm_resctrl_val()
(defined in cqm_test.c) and cat_perf_miss_val() (defined in cat_test.c).
These variables are not shared between those functions. So, there is no
need for these variables to be global. Hence, fix this issue by making
them static variables.
Reported-by: Reinette Chatre <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
David reported a buffer overflow error in the check_results() function of
the cmt unit test and he suggested enabling _FORTIFY_SOURCE gcc compiler
option to automatically detect any such errors.
Feature Test Macros man page describes_FORTIFY_SOURCE as below
"Defining this macro causes some lightweight checks to be performed to
detect some buffer overflow errors when employing various string and memory
manipulation functions (for example, memcpy, memset, stpcpy, strcpy,
strncpy, strcat, strncat, sprintf, snprintf, vsprintf, vsnprintf, gets, and
wide character variants thereof). For some functions, argument consistency
is checked; for example, a check is made that open has been supplied with a
mode argument when the specified flags include O_CREAT. Not all problems
are detected, just some common cases.
If _FORTIFY_SOURCE is set to 1, with compiler optimization level 1 (gcc
-O1) and above, checks that shouldn't change the behavior of conforming
programs are performed.
With _FORTIFY_SOURCE set to 2, some more checking is added, but some
conforming programs might fail.
Some of the checks can be performed at compile time (via macros logic
implemented in header files), and result in compiler warnings; other checks
take place at run time, and result in a run-time error if the check fails.
Use of this macro requires compiler support, available with gcc since
version 4.0."
Fix the buffer overflow error in the check_results() function of the cmt
unit test and enable _FORTIFY_SOURCE gcc check to catch any future buffer
overflow errors.
Reported-by: David Binderman <[email protected]>
Suggested-by: David Binderman <[email protected]>
Tested-by: Babu Moger <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
|
|
Alexei Starovoitov says:
====================
pull-request: bpf-next 2021-04-01
The following pull-request contains BPF updates for your *net-next* tree.
We've added 68 non-merge commits during the last 7 day(s) which contain
a total of 70 files changed, 2944 insertions(+), 1139 deletions(-).
The main changes are:
1) UDP support for sockmap, from Cong.
2) Verifier merge conflict resolution fix, from Daniel.
3) xsk selftests enhancements, from Maciej.
4) Unstable helpers aka kernel func calling, from Martin.
5) Batches ops for LPM map, from Pedro.
6) Fix race in bpf_get_local_storage, from Yonghong.
====================
Signed-off-by: David S. Miller <[email protected]>
|
|
Alexei Starovoitov says:
====================
pull-request: bpf 2021-04-01
The following pull-request contains BPF updates for your *net* tree.
We've added 11 non-merge commits during the last 8 day(s) which contain
a total of 10 files changed, 151 insertions(+), 26 deletions(-).
The main changes are:
1) xsk creation fixes, from Ciara.
2) bpf_get_task_stack fix, from Dave.
3) trampoline in modules fix, from Jiri.
4) bpf_obj_get fix for links and progs, from Lorenz.
5) struct_ops progs must be gpl compatible fix, from Toke.
====================
Signed-off-by: David S. Miller <[email protected]>
|
|
When the compiler emits: "CALL __x86_indirect_thunk_\reg" for an
indirect call, have objtool rewrite it to:
ALTERNATIVE "call __x86_indirect_thunk_\reg",
"call *%reg", ALT_NOT(X86_FEATURE_RETPOLINE)
Additionally, in order to not emit endless identical
.altinst_replacement chunks, use a global symbol for them, see
__x86_indirect_alt_*.
This also avoids objtool from having to do code generation.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
When the .altinstr_replacement is a retpoline, skip the alternative.
We already special case retpolines anyway.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Track the reloc of instructions in the new instruction->reloc field
to avoid having to look them up again later.
( Technically x86 instructions can have two relocations, but not jumps
and calls, for which we're using this. )
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Provide infrastructure for architectures to rewrite/augment compiler
generated retpoline calls. Similar to what we do for static_call()s,
keep track of the instructions that are retpoline calls.
Use the same list_head, since a retpoline call cannot also be a
static_call.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Allow objtool to create undefined symbols; this allows creating
relocations to symbols not currently in the symbol table.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Create a common helper to add symbols.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Create a common helper to append strings to a strtab.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Have elf_add_reloc() create the relocation section implicitly.
Suggested-by: Josh Poimboeuf <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
We have 4 instances of adding a relocation. Create a common helper
to avoid growing even more.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Instead of manually calling elf_rebuild_reloc_section() on sections
we've called elf_add_reloc() on, have elf_write() DTRT.
This makes it easier to add random relocations in places without
carefully tracking when we're done and need to flush what section.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Currently, objtool generates tail call entries in add_jump_destination()
but waits until validate_branch() to generate the regular call entries.
Move these to add_call_destination() for consistency.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
The __x86_indirect_ naming is obviously not generic. Shorten to allow
matching some additional magic names later.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Just like JMP handling, convert a direct CALL to a retpoline thunk
into a retpoline safe indirect CALL.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Miroslav Benes <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Due to:
c9c324dc22aa ("objtool: Support stack layout changes in alternatives")
it is now possible to simplify the retpolines.
Currently our retpolines consist of 2 symbols:
- __x86_indirect_thunk_\reg: the compiler target
- __x86_retpoline_\reg: the actual retpoline.
Both are consecutive in code and aligned such that for any one register
they both live in the same cacheline:
0000000000000000 <__x86_indirect_thunk_rax>:
0: ff e0 jmpq *%rax
2: 90 nop
3: 90 nop
4: 90 nop
0000000000000005 <__x86_retpoline_rax>:
5: e8 07 00 00 00 callq 11 <__x86_retpoline_rax+0xc>
a: f3 90 pause
c: 0f ae e8 lfence
f: eb f9 jmp a <__x86_retpoline_rax+0x5>
11: 48 89 04 24 mov %rax,(%rsp)
15: c3 retq
16: 66 2e 0f 1f 84 00 00 00 00 00 nopw %cs:0x0(%rax,%rax,1)
The thunk is an alternative_2, where one option is a JMP to the
retpoline. This was done so that objtool didn't need to deal with
alternatives with stack ops. But that problem has been solved, so now
it is possible to fold the entire retpoline into the alternative to
simplify and consolidate unused bytes:
0000000000000000 <__x86_indirect_thunk_rax>:
0: ff e0 jmpq *%rax
2: 90 nop
3: 90 nop
4: 90 nop
5: 90 nop
6: 90 nop
7: 90 nop
8: 90 nop
9: 90 nop
a: 90 nop
b: 90 nop
c: 90 nop
d: 90 nop
e: 90 nop
f: 90 nop
10: 90 nop
11: 66 66 2e 0f 1f 84 00 00 00 00 00 data16 nopw %cs:0x0(%rax,%rax,1)
1c: 0f 1f 40 00 nopl 0x0(%rax)
Notice that since the longest alternative sequence is now:
0: e8 07 00 00 00 callq c <.altinstr_replacement+0xc>
5: f3 90 pause
7: 0f ae e8 lfence
a: eb f9 jmp 5 <.altinstr_replacement+0x5>
c: 48 89 04 24 mov %rax,(%rsp)
10: c3 retq
17 bytes, we have 15 bytes NOP at the end of our 32 byte slot. (IOW, if
we can shrink the retpoline by 1 byte we can pack it more densely).
[ bp: Massage commit message. ]
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
Currently, optimize_nops() scans to see if the alternative starts with
NOPs. However, the emit pattern is:
141: \oldinstr
142: .skip (len-(142b-141b)), 0x90
That is, when 'oldinstr' is short, the tail is padded with NOPs. This case
never gets optimized.
Rewrite optimize_nops() to replace any trailing string of NOPs inside
the alternative to larger NOPs. Also run it irrespective of patching,
replacing NOPs in both the original and replaced code.
A direct consequence is that 'padlen' becomes superfluous, so remove it.
[ bp:
- Adjust commit message
- remove a stale comment about needing to pad
- add a comment in optimize_nops()
- exit early if the NOP verif. loop catches a mismatch - function
should not not add NOPs in that case
- fix the "optimized NOPs" offsets output ]
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
|
|
a semantic conflict
Conflict-merge this main commit in essence:
a89dfde3dc3c: ("x86: Remove dynamic NOP selection")
With this upstream commit:
b90829704780: ("bpf: Use NOP_ATOMIC5 instead of emit_nops(&prog, 5) for BPF_TRAMP_F_CALL_ORIG")
Semantic merge conflict:
arch/x86/net/bpf_jit_comp.c
- memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
+ memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
Signed-off-by: Ingo Molnar <[email protected]>
|
|
In particular we want to have this upstream commit:
b90829704780: ("bpf: Use NOP_ATOMIC5 instead of emit_nops(&prog, 5) for BPF_TRAMP_F_CALL_ORIG")
... before merging in x86/cpu changes and the removal of the NOP optimizations, and
applying PeterZ's !retpoline objtool series.
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Prior to this commit xsk_socket__create(_shared) always attempted to create
the rx and tx rings for the socket. However this causes an issue when the
socket being setup is that which shares the fd with the UMEM. If a
previous call to this function failed with this socket after the rings were
set up, a subsequent call would always fail because the rings are not torn
down after the first call and when we try to set them up again we encounter
an error because they already exist. Solve this by remembering whether the
rings were set up by introducing new bools to struct xsk_umem which
represent the ring setup status and using them to determine whether or
not to set up the rings.
Fixes: 1cad07884239 ("libbpf: add support for using AF_XDP sockets")
Signed-off-by: Ciara Loftus <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]
|
|
If the call to xsk_socket__create fails, the user may want to retry the
socket creation using the same umem. Ensure that the umem is in the
same state on exit if the call fails by:
1. ensuring the umem _save pointers are unmodified.
2. not unmapping the set of umem rings that were set up with the umem
during xsk_umem__create, since those maps existed before the call to
xsk_socket__create and should remain in tact even in the event of
failure.
Fixes: 2f6324a3937f ("libbpf: Support shared umems between queues and devices")
Signed-off-by: Ciara Loftus <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]
|
|
Calls to xsk_socket__create dereference the umem to access the
fill_save and comp_save pointers. Make sure the umem is non-NULL
before doing this.
Fixes: 2f6324a3937f ("libbpf: Support shared umems between queues and devices")
Signed-off-by: Ciara Loftus <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Acked-by: Magnus Karlsson <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]
|
|
Pull kvm fixes from Paolo Bonzini:
"It's a bit larger than I (and probably you) would like by the time we
get to -rc6, but perhaps not entirely unexpected since the changes in
the last merge window were larger than usual.
x86:
- Fixes for missing TLB flushes with TDP MMU
- Fixes for race conditions in nested SVM
- Fixes for lockdep splat with Xen emulation
- Fix for kvmclock underflow
- Fix srcdir != builddir builds
- Other small cleanups
ARM:
- Fix GICv3 MMIO compatibility probing
- Prevent guests from using the ARMv8.4 self-hosted tracing
extension"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
selftests: kvm: Check that TSC page value is small after KVM_SET_CLOCK(0)
KVM: x86: Prevent 'hv_clock->system_time' from going negative in kvm_guest_time_update()
KVM: x86: disable interrupts while pvclock_gtod_sync_lock is taken
KVM: x86: reduce pvclock_gtod_sync_lock critical sections
KVM: SVM: ensure that EFER.SVME is set when running nested guest or on nested vmexit
KVM: SVM: load control fields from VMCB12 before checking them
KVM: x86/mmu: Don't allow TDP MMU to yield when recovering NX pages
KVM: x86/mmu: Ensure TLBs are flushed for TDP MMU during NX zapping
KVM: x86/mmu: Ensure TLBs are flushed when yielding during GFN range zap
KVM: make: Fix out-of-source module builds
selftests: kvm: make hardware_disable_test less verbose
KVM: x86/vPMU: Forbid writing to MSR_F15H_PERF MSRs when guest doesn't have X86_FEATURE_PERFCTR_CORE
KVM: x86: remove unused declaration of kvm_write_tsc()
KVM: clean up the unused argument
tools/kvm_stat: Add restart delay
KVM: arm64: Fix CPU interface MMIO compatibility detection
KVM: arm64: Disable guest access to trace filter controls
KVM: arm64: Hide system instruction access to Trace registers
|
|
This adds a test case to ensure BPF_SK_SKB_VERDICT and
BPF_SK_STREAM_VERDICT will never be attached at the same time.
Signed-off-by: Cong Wang <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]
|
|
Add a test case to ensure redirection between two UDP sockets work.
Signed-off-by: Cong Wang <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]
|
|
Reusing BPF_SK_SKB_STREAM_VERDICT is possible but its name is
confusing and more importantly we still want to distinguish them
from user-space. So we can just reuse the stream verdict code but
introduce a new type of eBPF program, skb_verdict. Users are not
allowed to attach stream_verdict and skb_verdict programs to the
same map.
Signed-off-by: Cong Wang <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Acked-by: John Fastabend <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]
|