crypto: run qcrypto_pbkdf2_count_iters in a new thread
PATCH v2 1/1 crypto: run qcrypto_pbkdf2_count_iters in a new thread
CPU time accounting in the kernel has been demonstrated to have a sawtooth pattern[1][2]. This can cause the getrusage system call to not be as accurate as we are expecting, which can cause this calculation to stall.
The kernel discussions shows that this inaccuracy happens when CPU time gets big enough, so this patch changes qcrypto_pbkdf2_count_iters to run in a fresh thread to avoid this inaccuracy. It also adds a sanity check to fail the process if CPU time is not accounted.
[1] https://lore.kernel.org/lkml/159231011694.16989.16351419333851309713.tip-bot2@tip-bot2/
[2] https://lore.kernel.org/lkml/[email protected]/t/#m1c7f2fdc0ea742776a70fd1aa2a2e414c437f534
Resolves: #2398
--- crypto/pbkdf.c | 53 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 46 insertions(+), 7 deletions(-)
crypto/pbkdf.c +46 -7
@@ -19,6 +19,7 @@*/ #include "qemu/osdep.h" +#include "qemu/thread.h" #include "qapi/error.h" #include "crypto/pbkdf.h" #ifndef _WIN32
@@ -85,12 +86,28 @@ static int qcrypto_pbkdf2_get_thread_cpu(unsigned long long *val_ms,#endif } -uint64_t qcrypto_pbkdf2_count_iters (QCryptoHashAlgorithm hash, -const uint8_t *key,size_t nkey, -const uint8_t *salt,size_t nsalt, -size_t nout, -Error **errp) +typedef struct CountItersData { +QCryptoHashAlgorithm hash; +const uint8_t *key; +size_t nkey; +const uint8_t *salt; +size_t nsalt; +size_t nout; +uint64_t iterations; +Error **errp; +}CountItersData ; + +static void *threaded_qcrypto_pbkdf2_count_iters (void *data) { +CountItersData *iters_data = (CountItersData *) data; +QCryptoHashAlgorithm hash = iters_data->hash; +const uint8_t *key = iters_data->key; +size_t nkey = iters_data->nkey; +const uint8_t *salt = iters_data->salt; +size_t nsalt = iters_data->nsalt; +size_t nout = iters_data->nout; +Error **errp = iters_data->errp; +uint64_t ret =-1 ; g_autofree uint8_t *out = g_new(uint8_t, nout);uint64_t iterations = (1 <<15 );
@@ -114,7 +131,10 @@ uint64_t qcrypto_pbkdf2_count_iters(QCryptoHashAlgorithm hash, delta_ms = end_ms - start_ms; -if (delta_ms >500 ) { +if (delta_ms ==0 ) {/* sanity check */ +error_setg (errp,"Unable to get accurate CPU usage" ); + goto cleanup; + }else if (delta_ms >500 ) {break ; }else if (delta_ms <100 ) { iterations = iterations *10 ;
@@ -129,5 +149,24 @@ uint64_t qcrypto_pbkdf2_count_iters(QCryptoHashAlgorithm hash, cleanup:memset (out,0 , nout); -return ret; + iters_data->iterations = ret; +return NULL ; +} + +uint64_t qcrypto_pbkdf2_count_iters (QCryptoHashAlgorithm hash, +const uint8_t *key,size_t nkey, +const uint8_t *salt,size_t nsalt, +size_t nout, +Error **errp) +{ +CountItersData data = { + hash, key, nkey, salt, nsalt, nout,0 , errp + }; +QemuThread thread; + +qemu_thread_create (&thread,"pbkdf2" , threaded_qcrypto_pbkdf2_count_iters, + &data,QEMU_THREAD_JOINABLE ); +qemu_thread_join (&thread); + +return data.iterations; }
Signature · 1 line
2.43.0
Quoted 10 lines · Tiago Pasqualini
CPU time accounting in the kernel has been demonstrated to have a sawtooth pattern[1][2]. This can cause the getrusage system call to not be as accurate as we are expecting, which can cause this calculation to stall.
The kernel discussions shows that this inaccuracy happens when CPU time gets big enough, so this patch changes
qcrypto_pbkdf2_count_itersto run in a fresh thread to avoid this inaccuracy. It also adds a sanity check to fail the process if CPU time is not accounted.
Quoted 8 lines
[1] https://lore.kernel.org/lkml/159231011694.16989.16351419333851309713.tip-bot2@tip-bot2/
[2] https://lore.kernel.org/lkml/[email protected]/t/#m1c7f2fdc0ea742776a70fd1aa2a2e414c437f534Resolves: #2398
Signed-off-by Tiago Pasqualini <[email protected]>--- crypto/pbkdf.c | 53 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 46 insertions(+), 7 deletions(-)
and queued.
With regards,
Daniel
Signature · 3 lines
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :| |: https://libvirt.org -o- https://fstop138.berrange.com :| |: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
Quoted 66 lines · Tiago Pasqualini
CPU time accounting in the kernel has been demonstrated to have a sawtooth pattern[1][2]. This can cause the getrusage system call to not be as accurate as we are expecting, which can cause this calculation to stall.
The kernel discussions shows that this inaccuracy happens when CPU time gets big enough, so this patch changes
qcrypto_pbkdf2_count_itersto run in a fresh thread to avoid this inaccuracy. It also adds a sanity check to fail the process if CPU time is not accounted.[1] https://lore.kernel.org/lkml/159231011694.16989.16351419333851309713.tip-bot2@tip-bot2/
[2] https://lore.kernel.org/lkml/[email protected]/t/#m1c7f2fdc0ea742776a70fd1aa2a2e414c437f534Resolves: #2398
Signed-off-by Tiago Pasqualini <[email protected]>--- crypto/pbkdf.c | 53 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 46 insertions(+), 7 deletions(-)crypto/pbkdf.c +22
-5@@ -19,6 +19,7 @@*/ #include "qemu/osdep.h" +#include "qemu/thread.h" #include "qapi/error.h" #include "crypto/pbkdf.h" #ifndef _WIN32@@ -85,12 +86,28 @@ static int qcrypto_pbkdf2_get_thread_cpu(unsigned long long *val_ms,#endif } -uint64_t qcrypto_pbkdf2_count_iters (QCryptoHashAlgorithm hash, -const uint8_t *key,size_t nkey, -const uint8_t *salt,size_t nsalt, -size_t nout, -Error **errp) +typedef struct CountItersData { +QCryptoHashAlgorithm hash; +const uint8_t *key; +size_t nkey; +const uint8_t *salt; +size_t nsalt; +size_t nout; +uint64_t iterations; +Error **errp; +}CountItersData ; + +static void *threaded_qcrypto_pbkdf2_count_iters (void *data) { +CountItersData *iters_data = (CountItersData *) data; +QCryptoHashAlgorithm hash = iters_data->hash; +const uint8_t *key = iters_data->key; +size_t nkey = iters_data->nkey; +const uint8_t *salt = iters_data->salt; +size_t nsalt = iters_data->nsalt; +size_t nout = iters_data->nout; +Error **errp = iters_data->errp; +uint64_t ret =-1 ; g_autofree uint8_t *out = g_new(uint8_t, nout);uint64_t iterations = (1 <<15 );
crypto/pbkdf.c uint64_t qcrypto_pbkdf2_count_iters(QCryptoHashAlgorithm hash, · line 135
Quoted 6 lines
crypto/pbkdf.c +2
-1@@ -114,7 +131,10 @@ uint64_t qcrypto_pbkdf2_count_iters(QCryptoHashAlgorithm hash, delta_ms = end_ms - start_ms; -if (delta_ms >500 ) { +if (delta_ms ==0 ) {/* sanity check */ +error_setg (errp,"Unable to get accurate CPU usage" );
Hi!
While running "make check -j12 SPEED=slow" on a s390x host, I got:
3/657 qemu:unit / test-crypto-block
ERROR 0.27s killed by signal 6 SIGABRT
Quoted 1 line
Quoted 1 line
Quoted 1 line
G_TEST_SLOW=1 UBSAN_OPTIONS=halt_on_error=1:abort_on_error=1:print_summary=1:print_stacktrace=1 MALLOC_PERTURB_=150 G_TEST_BUILDDIR=/home/thuth/s390x/qemu/tests/unit MESON_TEST_ITERATION=1 MSAN_OPTIONS=halt_on_error=1:abort_on_error=1:print_summary=1:print_stacktrace=1 ASAN_OPTIONS=halt_on_error=1:abort_on_error=1:print_summary=1 G_TEST_SRCDIR=/home/thuth/devel/qemu/tests/unit
/home/thuth/s390x/qemu/tests/unit/test-crypto-block--tap -k
――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――― ✀ ――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――― stderr:
Unexpected error in threaded_qcrypto_pbkdf2_count_iters() at ../../devel/qemu/crypto/pbkdf.c:135:/home/thuth/s390x/qemu/tests/unit/test-crypto-block: Unable to get accurate CPU usage
(test program exited with status code -6)
TAP parsing error: Too few tests run (expected 27, got 1) ――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――
Could we handle this more gracefully, please? I don't think that this should fail the unit tests, should it?
Thomas
Quoted 31 lines
crypto/pbkdf.c +22
-1+ goto cleanup; + }else if (delta_ms >500 ) {break ; }else if (delta_ms <100 ) { iterations = iterations *10 ;@@ -129,5 +149,24 @@ uint64_t qcrypto_pbkdf2_count_iters(QCryptoHashAlgorithm hash, cleanup:memset (out,0 , nout); -return ret; + iters_data->iterations = ret; +return NULL ; +} + +uint64_t qcrypto_pbkdf2_count_iters (QCryptoHashAlgorithm hash, +const uint8_t *key,size_t nkey, +const uint8_t *salt,size_t nsalt, +size_t nout, +Error **errp) +{ +CountItersData data = { + hash, key, nkey, salt, nsalt, nout,0 , errp + }; +QemuThread thread; + +qemu_thread_create (&thread,"pbkdf2" , threaded_qcrypto_pbkdf2_count_iters, + &data,QEMU_THREAD_JOINABLE ); +qemu_thread_join (&thread); + +return data.iterations; }
Quoted 60 lines · Thomas Huth
Quoted 34 lines · Tiago Pasqualini
CPU time accounting in the kernel has been demonstrated to have a sawtooth pattern[1][2]. This can cause the getrusage system call to not be as accurate as we are expecting, which can cause this calculation to stall.
The kernel discussions shows that this inaccuracy happens when CPU time gets big enough, so this patch changes
qcrypto_pbkdf2_count_itersto run in a fresh thread to avoid this inaccuracy. It also adds a sanity check to fail the process if CPU time is not accounted.[1] https://lore.kernel.org/lkml/159231011694.16989.16351419333851309713.tip-bot2@tip-bot2/
[2] https://lore.kernel.org/lkml/[email protected]/t/#m1c7f2fdc0ea742776a70fd1aa2a2e414c437f534Resolves: #2398
Signed-off-by Tiago Pasqualini <[email protected]>--- crypto/pbkdf.c | 53 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 46 insertions(+), 7 deletions(-)crypto/pbkdf.c +10
-0+static void *threaded_qcrypto_pbkdf2_count_iters (void *data) { +CountItersData *iters_data = (CountItersData *) data; +QCryptoHashAlgorithm hash = iters_data->hash; +const uint8_t *key = iters_data->key; +size_t nkey = iters_data->nkey; +const uint8_t *salt = iters_data->salt; +size_t nsalt = iters_data->nsalt; +size_t nout = iters_data->nout; +Error **errp = iters_data->errp; +uint64_t ret =-1 ; g_autofree uint8_t *out = g_new(uint8_t, nout);uint64_t iterations = (1 <<15 );crypto/pbkdf.c uint64_t qcrypto_pbkdf2_count_iters(QCryptoHashAlgorithm hash, · line 133
Quoted 4 lines
crypto/pbkdf.c +2
-1@@ -114,7 +131,10 @@ uint64_t qcrypto_pbkdf2_count_iters(QCryptoHashAlgorithm hash, delta_ms = end_ms - start_ms; -if (delta_ms >500 ) { +if (delta_ms ==0 ) {/* sanity check */ +error_setg (errp,"Unable to get accurate CPU usage" );Hi!
While running "make check -j12 SPEED=slow" on a s390x host, I got:
3/657 qemu:unit / test-crypto-block ERROR 0.27s
killed by signal 6 SIGABRTQuoted 1 line
Quoted 1 line
Quoted 1 line
G_TEST_SLOW=1 UBSAN_OPTIONS=halt_on_error=1:abort_on_error=1:print_summary=1:print_stacktrace=1
MALLOC_PERTURB_=150 G_TEST_BUILDDIR=/home/thuth/s390x/qemu/tests/unit MESON_TEST_ITERATION=1 MSAN_OPTIONS=halt_on_error=1:abort_on_error=1:print_summary=1:print_stacktrace=1 ASAN_OPTIONS=halt_on_error=1:abort_on_error=1:print_summary=1 G_TEST_SRCDIR=/home/thuth/devel/qemu/tests/unit
/home/thuth/s390x/qemu/tests/unit/test-crypto-block--tap -k ―――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――
✀ ――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――― stderr:
Unexpected error inthreaded_qcrypto_pbkdf2_count_iters()at../../devel/qemu/crypto/pbkdf.c:135:/home/thuth/s390x/qemu/tests/unit/test-crypto-block: Unable to get accurate
CPU usage
Quoted 7 lines
(test program exited with status code -6)
TAP parsing error: Too few tests run (expected 27, got 1) ――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――
Could we handle this more gracefully, please? I don't think that this should fail the unit tests, should it?
This is a scenario that is not supposed to ever happen. It means we've had two calls to getrusage which returns exactly the same CPU time. This should be impossible, as we've definitely burnt lots of CPU between these two calls. Is this reliably reproducable only on s390x ?
With regards,
Daniel
Signature · 3 lines
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :| |: https://libvirt.org -o- https://fstop138.berrange.com :| |: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|