fche changed the topic of #systemtap to: http://sourceware.org/systemtap; email systemtap@sourceware.org if answers here not timely, conversations may be logged
sapatel has quit [Remote host closed the connection]
orivej has quit [Ping timeout: 260 seconds]
hpt has joined #systemtap
sscox has quit [Quit: sscox]
sscox has joined #systemtap
irker707 has quit [Quit: transmission timeout]
amerey_ has quit [Remote host closed the connection]
amerey_ has joined #systemtap
amerey_ has quit [Remote host closed the connection]
amerey_ has joined #systemtap
amerey_ has quit [Remote host closed the connection]
amerey_ has joined #systemtap
jhg_ has quit [Ping timeout: 246 seconds]
jhg_ has joined #systemtap
amerey_ has quit [Remote host closed the connection]
amerey_ has joined #systemtap
amerey_ has quit [Remote host closed the connection]
amerey_ has joined #systemtap
khaled has joined #systemtap
amerey_ has quit [Remote host closed the connection]
amerey_ has joined #systemtap
orivej has joined #systemtap
amerey_ has quit [Remote host closed the connection]
amerey_ has joined #systemtap
amerey_ has quit [Remote host closed the connection]
amerey_ has joined #systemtap
amerey_ has quit [Remote host closed the connection]
amerey_ has joined #systemtap
amerey_ has quit [Remote host closed the connection]
orivej has quit [Ping timeout: 256 seconds]
jhg_ has quit [Ping timeout: 240 seconds]
jhg_ has joined #systemtap
mjw has joined #systemtap
hpt has quit [Ping timeout: 265 seconds]
xlei has quit [Quit: ZNC - https://znc.in]
amerey has joined #systemtap
orivej has joined #systemtap
wcohen has quit [Remote host closed the connection]
wcohen has joined #systemtap
tromey has joined #systemtap
orivej has quit [Ping timeout: 240 seconds]
<irker745> systemtap: sapatel systemtap.git:probewrite * release-4.3-52-gc64427412 / man/stap.1.in man/stapprobes.3stap man/stapref.1: Add docs for @probewrite.
irker745 has joined #systemtap
orivej has joined #systemtap
irker745 has quit [Quit: transmission timeout]
sscox has quit [Ping timeout: 260 seconds]
<agentzh> fche: does this patch make sense at all? https://gist.github.com/agentzh/7a9095fe5f720a155b3e6eabe6a3fab3
<agentzh> some intel engineers suggested to us that we should acquire the mm sem when accessing the target memory.
<fche> is there a test case for this?\
<fche> something showing a problem with the status quo?
<agentzh> no test cases, just in the light of potential race conditions.
<agentzh> just asking for opinions.
<agentzh> not meant to be merged into the master atm.
<fche> does the kernel take the mm_sem in routine userspace access functions?
<fche> like when copying out syscall parameters or whatever?
<fche> I thought it was taken generally around *changes* to the memory map
<irker562> systemtap: amerey systemtap.git:probewrite_new * release-4.3-45-g38b8e50fd / tapset/registers.stp tapset/x86_64/registers.stp testsuite/systemtap.syscall/mkdir_probewrite.exp testsuite/systemtap.syscall/mkdir_probewrite.stp: Add functions for writing to syscall args and testcase.
irker562 has joined #systemtap
<irker562> systemtap: amerey systemtap.git:probewrite_new * release-4.3-46-gf33960c71 / testsuite/systemtap.base/sysarg_write.c testsuite/systemtap.base/sysarg_write.exp testsuite/systemtap.base/sysarg_write.stp testsuite/systemtap.syscall/mkdir_probewrite.exp testsuite/systemtap.syscall/mkdir_probewrite.stp: Fix sysarg write testcase
<irker562> systemtap: sapatel systemtap.git:probewrite_new * release-4.3-48-g9a6116de7 / NEWS elaborate.cxx elaborate.h parse.cxx staptree.cxx staptree.h testsuite/systemtap.base/probewrite.exp testsuite/systemtap.base/probewrite_1.stp testsuite/systemtap.base/probewrite_2.stp testsuite/systemtap.base/probewrite_3.c testsuite/systemtap.base/probewrite_3.stp translate.cxx: PR26015: Add @probewrite predicate.
<irker562> systemtap: sapatel systemtap.git:probewrite_new * release-4.3-49-gd0d42395e / man/stap.1.in man/stapprobes.3stap man/stapref.1: Add docs for @probewrite.
<irker562> systemtap: amerey systemtap.git:probewrite_new * release-4.3-47-gcd3dc694d / testsuite/systemtap.base/sysarg_write.c testsuite/systemtap.base/sysarg_write.exp testsuite/systemtap.base/sysarg_write.stp: Add string modification to syscall arg write test
<agentzh> fche: my hunch is that if stap can make sure no other things would ever change mm when its probe handlers are running, then it should be fine.
<agentzh> for process_vm_readv() syscall, it does acquire the mm sem when reading the remote memory. but for them, it might make more sense since the target is not stopped anyway.
<irker562> systemtap: amerey systemtap.git:probewrite_new * release-4.3-45-g38b8e50fd / tapset/registers.stp tapset/x86_64/registers.stp testsuite/systemtap.syscall/mkdir_probewrite.exp testsuite/systemtap.syscall/mkdir_probewrite.stp: Add functions for writing to syscall args and testcase.
<irker562> systemtap: amerey systemtap.git:probewrite_new * release-4.3-46-gf33960c71 / testsuite/systemtap.base/sysarg_write.c testsuite/systemtap.base/sysarg_write.exp testsuite/systemtap.base/sysarg_write.stp testsuite/systemtap.syscall/mkdir_probewrite.exp testsuite/systemtap.syscall/mkdir_probewrite.stp: Fix sysarg write testcase
<irker562> systemtap: amerey systemtap.git:probewrite_new * release-4.3-47-gcd3dc694d / testsuite/systemtap.base/sysarg_write.c testsuite/systemtap.base/sysarg_write.exp testsuite/systemtap.base/sysarg_write.stp: Add string modification to syscall arg write test
<irker562> systemtap: sapatel systemtap.git:probewrite_new * release-4.3-48-g9a6116de7 / NEWS elaborate.cxx elaborate.h parse.cxx staptree.cxx staptree.h testsuite/systemtap.base/probewrite.exp testsuite/systemtap.base/probewrite_1.stp testsuite/systemtap.base/probewrite_2.stp testsuite/systemtap.base/probewrite_3.c testsuite/systemtap.base/probewrite_3.stp translate.cxx: PR26015: Add @probewrite predicate.
<irker562> systemtap: sapatel systemtap.git:probewrite_new * release-4.3-49-gd0d42395e / man/stap.1.in man/stapprobes.3stap man/stapref.1: Add docs for @probewrite.
sapatel has joined #systemtap
<irker562> systemtap: sapatel systemtap.git:probewrite_new * release-4.3-45-gf30345c96 / NEWS elaborate.cxx elaborate.h parse.cxx staptree.cxx staptree.h testsuite/systemtap.base/probewrite.exp testsuite/systemtap.base/probewrite_1.stp testsuite/systemtap.base/probewrite_2.stp testsuite/systemtap.base/probewrite_3.c testsuite/systemtap.base/probewrite_3.stp translate.cxx: PR26015: Add @probewrite predicate.
<irker562> systemtap: sapatel systemtap.git:probewrite_new * release-4.3-46-g038cd8a3f / man/stap.1.in man/stapprobes.3stap man/stapref.1: Add docs for @probewrite.
<irker562> systemtap: amerey systemtap.git:probewrite_new * release-4.3-47-gc2573f362 / tapset/registers.stp tapset/x86_64/registers.stp testsuite/systemtap.syscall/mkdir_probewrite.exp testsuite/systemtap.syscall/mkdir_probewrite.stp: Add functions for writing to syscall args and testcase.
<irker562> systemtap: amerey systemtap.git:probewrite_new * release-4.3-48-g72bd18afe / testsuite/systemtap.base/sysarg_write.c testsuite/systemtap.base/sysarg_write.exp testsuite/systemtap.base/sysarg_write.stp testsuite/systemtap.syscall/mkdir_probewrite.exp testsuite/systemtap.syscall/mkdir_probewrite.stp: Fix sysarg write testcase
<irker562> systemtap: amerey systemtap.git:probewrite_new * release-4.3-49-g50b7a1a7c / testsuite/systemtap.base/sysarg_write.c testsuite/systemtap.base/sysarg_write.exp testsuite/systemtap.base/sysarg_write.stp: Add string modification to syscall arg write test
<irker562> systemtap: sapatel systemtap.git:PR26015 * release-4.3-45-gf30345c96 / NEWS elaborate.cxx elaborate.h parse.cxx staptree.cxx staptree.h testsuite/systemtap.base/probewrite.exp testsuite/systemtap.base/probewrite_1.stp testsuite/systemtap.base/probewrite_2.stp testsuite/systemtap.base/probewrite_3.c testsuite/systemtap.base/probewrite_3.stp translate.cxx: PR26015: Add @probewrite predicate.
<irker562> systemtap: sapatel systemtap.git:PR26015 * release-4.3-46-g038cd8a3f / man/stap.1.in man/stapprobes.3stap man/stapref.1: Add docs for @probewrite.
<irker562> systemtap: amerey systemtap.git:PR26015 * release-4.3-47-gc2573f362 / tapset/registers.stp tapset/x86_64/registers.stp testsuite/systemtap.syscall/mkdir_probewrite.exp testsuite/systemtap.syscall/mkdir_probewrite.stp: Add functions for writing to syscall args and testcase.
<irker562> systemtap: amerey systemtap.git:PR26015 * release-4.3-48-g72bd18afe / testsuite/systemtap.base/sysarg_write.c testsuite/systemtap.base/sysarg_write.exp testsuite/systemtap.base/sysarg_write.stp testsuite/systemtap.syscall/mkdir_probewrite.exp testsuite/systemtap.syscall/mkdir_probewrite.stp: Fix sysarg write testcase
<irker562> systemtap: amerey systemtap.git:PR26015 * release-4.3-49-g50b7a1a7c / testsuite/systemtap.base/sysarg_write.c testsuite/systemtap.base/sysarg_write.exp testsuite/systemtap.base/sysarg_write.stp: Add string modification to syscall arg write test
<fche> agentzh, process_vm_readv I believe applies across processes, whereas stap user-space fetches apply to the current process only
xlei has joined #systemtap
<irker562> systemtap: fche systemtap.git:master * release-4.3-64-g25012d82e / NEWS man/stap.1.in runtime/common_probe_context.h staptree.h tapsets.cxx testsuite/systemtap.base/lock-pushdown.exp testsuite/systemtap.base/lock-pushdown.stp translate.cxx: PR26296: lock pushdown optimization
sscox has joined #systemtap
<agentzh> fche: yeah, that's a difference.
tromey has quit [Quit: ERC (IRC client for Emacs 28.0.50)]
sapatel has quit [Read error: error:1408F10B:SSL routines:ssl3_get_record:wrong version number]
sapatel has joined #systemtap
irker562 has quit [Quit: transmission timeout]
orivej has quit [Ping timeout: 256 seconds]
orivej has joined #systemtap
mjw has quit [Quit: Leaving]
sapatel has quit [Remote host closed the connection]
amerey has quit [Ping timeout: 256 seconds]