From 059c5e918f6613d7062f27705488e5bd72cd09bd Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Mon, 8 Aug 2016 16:00:25 -0600 Subject: docs: create a new dev-tools directory This directory will be a collecting point for documentation oriented around development tools. As a step toward ordering Documentation/ it's a small one, but we have to start somewhere... Signed-off-by: Jonathan Corbet --- Documentation/dev-tools/tools.rst | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 Documentation/dev-tools/tools.rst (limited to 'Documentation/dev-tools') diff --git a/Documentation/dev-tools/tools.rst b/Documentation/dev-tools/tools.rst new file mode 100644 index 000000000000..60ddb9ea6ef9 --- /dev/null +++ b/Documentation/dev-tools/tools.rst @@ -0,0 +1,16 @@ +================================ +Development tools for the kernel +================================ + +This document is a collection of documents about development tools that can +be used to work on the kernel. For now, the documents have been pulled +together without any significant effot to integrate them into a coherent +whole; patches welcome! + +.. class:: toc-title + + Table of contents + +.. toctree:: + :maxdepth: 2 + -- cgit v1.2.3 From 4b9033a33494ec9154d63e706e9e47f7eb3fd59e Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Mon, 8 Aug 2016 16:03:14 -0600 Subject: docs: sphinxify coccinelle.txt and add it to dev-tools No textual changes have been made, but the formatting has obviously been tweaked. Cc: Michal Marek Cc: Gilles Muller Acked-by: Nicolas Palix Acked-by: Julia Lawall Signed-off-by: Jonathan Corbet --- Documentation/dev-tools/coccinelle.rst | 491 +++++++++++++++++++++++++++++++++ Documentation/dev-tools/tools.rst | 1 + 2 files changed, 492 insertions(+) create mode 100644 Documentation/dev-tools/coccinelle.rst (limited to 'Documentation/dev-tools') diff --git a/Documentation/dev-tools/coccinelle.rst b/Documentation/dev-tools/coccinelle.rst new file mode 100644 index 000000000000..4a64b4c69d3f --- /dev/null +++ b/Documentation/dev-tools/coccinelle.rst @@ -0,0 +1,491 @@ +.. Copyright 2010 Nicolas Palix +.. Copyright 2010 Julia Lawall +.. Copyright 2010 Gilles Muller + +.. highlight:: none + +Coccinelle +========== + +Coccinelle is a tool for pattern matching and text transformation that has +many uses in kernel development, including the application of complex, +tree-wide patches and detection of problematic programming patterns. + +Getting Coccinelle +------------------- + +The semantic patches included in the kernel use features and options +which are provided by Coccinelle version 1.0.0-rc11 and above. +Using earlier versions will fail as the option names used by +the Coccinelle files and coccicheck have been updated. + +Coccinelle is available through the package manager +of many distributions, e.g. : + + - Debian + - Fedora + - Ubuntu + - OpenSUSE + - Arch Linux + - NetBSD + - FreeBSD + +You can get the latest version released from the Coccinelle homepage at +http://coccinelle.lip6.fr/ + +Information and tips about Coccinelle are also provided on the wiki +pages at http://cocci.ekstranet.diku.dk/wiki/doku.php + +Once you have it, run the following command:: + + ./configure + make + +as a regular user, and install it with:: + + sudo make install + +Supplemental documentation +--------------------------- + +For supplemental documentation refer to the wiki: + +https://bottest.wiki.kernel.org/coccicheck + +The wiki documentation always refers to the linux-next version of the script. + +Using Coccinelle on the Linux kernel +------------------------------------ + +A Coccinelle-specific target is defined in the top level +Makefile. This target is named ``coccicheck`` and calls the ``coccicheck`` +front-end in the ``scripts`` directory. + +Four basic modes are defined: ``patch``, ``report``, ``context``, and +``org``. The mode to use is specified by setting the MODE variable with +``MODE=``. + +- ``patch`` proposes a fix, when possible. + +- ``report`` generates a list in the following format: + file:line:column-column: message + +- ``context`` highlights lines of interest and their context in a + diff-like style.Lines of interest are indicated with ``-``. + +- ``org`` generates a report in the Org mode format of Emacs. + +Note that not all semantic patches implement all modes. For easy use +of Coccinelle, the default mode is "report". + +Two other modes provide some common combinations of these modes. + +- ``chain`` tries the previous modes in the order above until one succeeds. + +- ``rep+ctxt`` runs successively the report mode and the context mode. + It should be used with the C option (described later) + which checks the code on a file basis. + +Examples +~~~~~~~~ + +To make a report for every semantic patch, run the following command:: + + make coccicheck MODE=report + +To produce patches, run:: + + make coccicheck MODE=patch + + +The coccicheck target applies every semantic patch available in the +sub-directories of ``scripts/coccinelle`` to the entire Linux kernel. + +For each semantic patch, a commit message is proposed. It gives a +description of the problem being checked by the semantic patch, and +includes a reference to Coccinelle. + +As any static code analyzer, Coccinelle produces false +positives. Thus, reports must be carefully checked, and patches +reviewed. + +To enable verbose messages set the V= variable, for example:: + + make coccicheck MODE=report V=1 + +Coccinelle parallelization +--------------------------- + +By default, coccicheck tries to run as parallel as possible. To change +the parallelism, set the J= variable. For example, to run across 4 CPUs:: + + make coccicheck MODE=report J=4 + +As of Coccinelle 1.0.2 Coccinelle uses Ocaml parmap for parallelization, +if support for this is detected you will benefit from parmap parallelization. + +When parmap is enabled coccicheck will enable dynamic load balancing by using +``--chunksize 1`` argument, this ensures we keep feeding threads with work +one by one, so that we avoid the situation where most work gets done by only +a few threads. With dynamic load balancing, if a thread finishes early we keep +feeding it more work. + +When parmap is enabled, if an error occurs in Coccinelle, this error +value is propagated back, the return value of the ``make coccicheck`` +captures this return value. + +Using Coccinelle with a single semantic patch +--------------------------------------------- + +The optional make variable COCCI can be used to check a single +semantic patch. In that case, the variable must be initialized with +the name of the semantic patch to apply. + +For instance:: + + make coccicheck COCCI= MODE=patch + +or:: + + make coccicheck COCCI= MODE=report + + +Controlling Which Files are Processed by Coccinelle +--------------------------------------------------- + +By default the entire kernel source tree is checked. + +To apply Coccinelle to a specific directory, ``M=`` can be used. +For example, to check drivers/net/wireless/ one may write:: + + make coccicheck M=drivers/net/wireless/ + +To apply Coccinelle on a file basis, instead of a directory basis, the +following command may be used:: + + make C=1 CHECK="scripts/coccicheck" + +To check only newly edited code, use the value 2 for the C flag, i.e.:: + + make C=2 CHECK="scripts/coccicheck" + +In these modes, which works on a file basis, there is no information +about semantic patches displayed, and no commit message proposed. + +This runs every semantic patch in scripts/coccinelle by default. The +COCCI variable may additionally be used to only apply a single +semantic patch as shown in the previous section. + +The "report" mode is the default. You can select another one with the +MODE variable explained above. + +Debugging Coccinelle SmPL patches +--------------------------------- + +Using coccicheck is best as it provides in the spatch command line +include options matching the options used when we compile the kernel. +You can learn what these options are by using V=1, you could then +manually run Coccinelle with debug options added. + +Alternatively you can debug running Coccinelle against SmPL patches +by asking for stderr to be redirected to stderr, by default stderr +is redirected to /dev/null, if you'd like to capture stderr you +can specify the ``DEBUG_FILE="file.txt"`` option to coccicheck. For +instance:: + + rm -f cocci.err + make coccicheck COCCI=scripts/coccinelle/free/kfree.cocci MODE=report DEBUG_FILE=cocci.err + cat cocci.err + +You can use SPFLAGS to add debugging flags, for instance you may want to +add both --profile --show-trying to SPFLAGS when debugging. For instance +you may want to use:: + + rm -f err.log + export COCCI=scripts/coccinelle/misc/irqf_oneshot.cocci + make coccicheck DEBUG_FILE="err.log" MODE=report SPFLAGS="--profile --show-trying" M=./drivers/mfd/arizona-irq.c + +err.log will now have the profiling information, while stdout will +provide some progress information as Coccinelle moves forward with +work. + +DEBUG_FILE support is only supported when using coccinelle >= 1.2. + +.cocciconfig support +-------------------- + +Coccinelle supports reading .cocciconfig for default Coccinelle options that +should be used every time spatch is spawned, the order of precedence for +variables for .cocciconfig is as follows: + +- Your current user's home directory is processed first +- Your directory from which spatch is called is processed next +- The directory provided with the --dir option is processed last, if used + +Since coccicheck runs through make, it naturally runs from the kernel +proper dir, as such the second rule above would be implied for picking up a +.cocciconfig when using ``make coccicheck``. + +``make coccicheck`` also supports using M= targets.If you do not supply +any M= target, it is assumed you want to target the entire kernel. +The kernel coccicheck script has:: + + if [ "$KBUILD_EXTMOD" = "" ] ; then + OPTIONS="--dir $srctree $COCCIINCLUDE" + else + OPTIONS="--dir $KBUILD_EXTMOD $COCCIINCLUDE" + fi + +KBUILD_EXTMOD is set when an explicit target with M= is used. For both cases +the spatch --dir argument is used, as such third rule applies when whether M= +is used or not, and when M= is used the target directory can have its own +.cocciconfig file. When M= is not passed as an argument to coccicheck the +target directory is the same as the directory from where spatch was called. + +If not using the kernel's coccicheck target, keep the above precedence +order logic of .cocciconfig reading. If using the kernel's coccicheck target, +override any of the kernel's .coccicheck's settings using SPFLAGS. + +We help Coccinelle when used against Linux with a set of sensible defaults +options for Linux with our own Linux .cocciconfig. This hints to coccinelle +git can be used for ``git grep`` queries over coccigrep. A timeout of 200 +seconds should suffice for now. + +The options picked up by coccinelle when reading a .cocciconfig do not appear +as arguments to spatch processes running on your system, to confirm what +options will be used by Coccinelle run:: + + spatch --print-options-only + +You can override with your own preferred index option by using SPFLAGS. Take +note that when there are conflicting options Coccinelle takes precedence for +the last options passed. Using .cocciconfig is possible to use idutils, however +given the order of precedence followed by Coccinelle, since the kernel now +carries its own .cocciconfig, you will need to use SPFLAGS to use idutils if +desired. See below section "Additional flags" for more details on how to use +idutils. + +Additional flags +---------------- + +Additional flags can be passed to spatch through the SPFLAGS +variable. This works as Coccinelle respects the last flags +given to it when options are in conflict. :: + + make SPFLAGS=--use-glimpse coccicheck + +Coccinelle supports idutils as well but requires coccinelle >= 1.0.6. +When no ID file is specified coccinelle assumes your ID database file +is in the file .id-utils.index on the top level of the kernel, coccinelle +carries a script scripts/idutils_index.sh which creates the database with:: + + mkid -i C --output .id-utils.index + +If you have another database filename you can also just symlink with this +name. :: + + make SPFLAGS=--use-idutils coccicheck + +Alternatively you can specify the database filename explicitly, for +instance:: + + make SPFLAGS="--use-idutils /full-path/to/ID" coccicheck + +See ``spatch --help`` to learn more about spatch options. + +Note that the ``--use-glimpse`` and ``--use-idutils`` options +require external tools for indexing the code. None of them is +thus active by default. However, by indexing the code with +one of these tools, and according to the cocci file used, +spatch could proceed the entire code base more quickly. + +SmPL patch specific options +--------------------------- + +SmPL patches can have their own requirements for options passed +to Coccinelle. SmPL patch specific options can be provided by +providing them at the top of the SmPL patch, for instance:: + + // Options: --no-includes --include-headers + +SmPL patch Coccinelle requirements +---------------------------------- + +As Coccinelle features get added some more advanced SmPL patches +may require newer versions of Coccinelle. If an SmPL patch requires +at least a version of Coccinelle, this can be specified as follows, +as an example if requiring at least Coccinelle >= 1.0.5:: + + // Requires: 1.0.5 + +Proposing new semantic patches +------------------------------- + +New semantic patches can be proposed and submitted by kernel +developers. For sake of clarity, they should be organized in the +sub-directories of ``scripts/coccinelle/``. + + +Detailed description of the ``report`` mode +------------------------------------------- + +``report`` generates a list in the following format:: + + file:line:column-column: message + +Example +~~~~~~~ + +Running:: + + make coccicheck MODE=report COCCI=scripts/coccinelle/api/err_cast.cocci + +will execute the following part of the SmPL script:: + + + @r depends on !context && !patch && (org || report)@ + expression x; + position p; + @@ + + ERR_PTR@p(PTR_ERR(x)) + + @script:python depends on report@ + p << r.p; + x << r.x; + @@ + + msg="ERR_CAST can be used with %s" % (x) + coccilib.report.print_report(p[0], msg) + + +This SmPL excerpt generates entries on the standard output, as +illustrated below:: + + /home/user/linux/crypto/ctr.c:188:9-16: ERR_CAST can be used with alg + /home/user/linux/crypto/authenc.c:619:9-16: ERR_CAST can be used with auth + /home/user/linux/crypto/xts.c:227:9-16: ERR_CAST can be used with alg + + +Detailed description of the ``patch`` mode +------------------------------------------ + +When the ``patch`` mode is available, it proposes a fix for each problem +identified. + +Example +~~~~~~~ + +Running:: + + make coccicheck MODE=patch COCCI=scripts/coccinelle/api/err_cast.cocci + +will execute the following part of the SmPL script:: + + + @ depends on !context && patch && !org && !report @ + expression x; + @@ + + - ERR_PTR(PTR_ERR(x)) + + ERR_CAST(x) + + +This SmPL excerpt generates patch hunks on the standard output, as +illustrated below:: + + diff -u -p a/crypto/ctr.c b/crypto/ctr.c + --- a/crypto/ctr.c 2010-05-26 10:49:38.000000000 +0200 + +++ b/crypto/ctr.c 2010-06-03 23:44:49.000000000 +0200 + @@ -185,7 +185,7 @@ static struct crypto_instance *crypto_ct + alg = crypto_attr_alg(tb[1], CRYPTO_ALG_TYPE_CIPHER, + CRYPTO_ALG_TYPE_MASK); + if (IS_ERR(alg)) + - return ERR_PTR(PTR_ERR(alg)); + + return ERR_CAST(alg); + + /* Block size must be >= 4 bytes. */ + err = -EINVAL; + +Detailed description of the ``context`` mode +-------------------------------------------- + +``context`` highlights lines of interest and their context +in a diff-like style. + + **NOTE**: The diff-like output generated is NOT an applicable patch. The + intent of the ``context`` mode is to highlight the important lines + (annotated with minus, ``-``) and gives some surrounding context + lines around. This output can be used with the diff mode of + Emacs to review the code. + +Example +~~~~~~~ + +Running:: + + make coccicheck MODE=context COCCI=scripts/coccinelle/api/err_cast.cocci + +will execute the following part of the SmPL script:: + + + @ depends on context && !patch && !org && !report@ + expression x; + @@ + + * ERR_PTR(PTR_ERR(x)) + + +This SmPL excerpt generates diff hunks on the standard output, as +illustrated below:: + + diff -u -p /home/user/linux/crypto/ctr.c /tmp/nothing + --- /home/user/linux/crypto/ctr.c 2010-05-26 10:49:38.000000000 +0200 + +++ /tmp/nothing + @@ -185,7 +185,6 @@ static struct crypto_instance *crypto_ct + alg = crypto_attr_alg(tb[1], CRYPTO_ALG_TYPE_CIPHER, + CRYPTO_ALG_TYPE_MASK); + if (IS_ERR(alg)) + - return ERR_PTR(PTR_ERR(alg)); + + /* Block size must be >= 4 bytes. */ + err = -EINVAL; + +Detailed description of the ``org`` mode +---------------------------------------- + +``org`` generates a report in the Org mode format of Emacs. + +Example +~~~~~~~ + +Running:: + + make coccicheck MODE=org COCCI=scripts/coccinelle/api/err_cast.cocci + +will execute the following part of the SmPL script:: + + + @r depends on !context && !patch && (org || report)@ + expression x; + position p; + @@ + + ERR_PTR@p(PTR_ERR(x)) + + @script:python depends on org@ + p << r.p; + x << r.x; + @@ + + msg="ERR_CAST can be used with %s" % (x) + msg_safe=msg.replace("[","@(").replace("]",")") + coccilib.org.print_todo(p[0], msg_safe) + + +This SmPL excerpt generates Org entries on the standard output, as +illustrated below:: + + * TODO [[view:/home/user/linux/crypto/ctr.c::face=ovl-face1::linb=188::colb=9::cole=16][ERR_CAST can be used with alg]] + * TODO [[view:/home/user/linux/crypto/authenc.c::face=ovl-face1::linb=619::colb=9::cole=16][ERR_CAST can be used with auth]] + * TODO [[view:/home/user/linux/crypto/xts.c::face=ovl-face1::linb=227::colb=9::cole=16][ERR_CAST can be used with alg]] diff --git a/Documentation/dev-tools/tools.rst b/Documentation/dev-tools/tools.rst index 60ddb9ea6ef9..ae0c58c784db 100644 --- a/Documentation/dev-tools/tools.rst +++ b/Documentation/dev-tools/tools.rst @@ -14,3 +14,4 @@ whole; patches welcome! .. toctree:: :maxdepth: 2 + coccinelle -- cgit v1.2.3 From d228af5bcb60fda50f8b3a100c0539c4994df040 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sun, 7 Aug 2016 15:09:14 -0600 Subject: docs: sphinxify sparse.txt and move to dev-tools Fold the sparse document into the development tools set; no changes to the text itself beyond formatting. Signed-off-by: Jonathan Corbet --- Documentation/dev-tools/sparse.rst | 117 +++++++++++++++++++++++++++++++++++++ Documentation/dev-tools/tools.rst | 1 + 2 files changed, 118 insertions(+) create mode 100644 Documentation/dev-tools/sparse.rst (limited to 'Documentation/dev-tools') diff --git a/Documentation/dev-tools/sparse.rst b/Documentation/dev-tools/sparse.rst new file mode 100644 index 000000000000..8c250e8a2105 --- /dev/null +++ b/Documentation/dev-tools/sparse.rst @@ -0,0 +1,117 @@ +.. Copyright 2004 Linus Torvalds +.. Copyright 2004 Pavel Machek +.. Copyright 2006 Bob Copeland + +Sparse +====== + +Sparse is a semantic checker for C programs; it can be used to find a +number of potential problems with kernel code. See +https://lwn.net/Articles/689907/ for an overview of sparse; this document +contains some kernel-specific sparse information. + + +Using sparse for typechecking +----------------------------- + +"__bitwise" is a type attribute, so you have to do something like this:: + + typedef int __bitwise pm_request_t; + + enum pm_request { + PM_SUSPEND = (__force pm_request_t) 1, + PM_RESUME = (__force pm_request_t) 2 + }; + +which makes PM_SUSPEND and PM_RESUME "bitwise" integers (the "__force" is +there because sparse will complain about casting to/from a bitwise type, +but in this case we really _do_ want to force the conversion). And because +the enum values are all the same type, now "enum pm_request" will be that +type too. + +And with gcc, all the "__bitwise"/"__force stuff" goes away, and it all +ends up looking just like integers to gcc. + +Quite frankly, you don't need the enum there. The above all really just +boils down to one special "int __bitwise" type. + +So the simpler way is to just do:: + + typedef int __bitwise pm_request_t; + + #define PM_SUSPEND ((__force pm_request_t) 1) + #define PM_RESUME ((__force pm_request_t) 2) + +and you now have all the infrastructure needed for strict typechecking. + +One small note: the constant integer "0" is special. You can use a +constant zero as a bitwise integer type without sparse ever complaining. +This is because "bitwise" (as the name implies) was designed for making +sure that bitwise types don't get mixed up (little-endian vs big-endian +vs cpu-endian vs whatever), and there the constant "0" really _is_ +special. + +__bitwise__ - to be used for relatively compact stuff (gfp_t, etc.) that +is mostly warning-free and is supposed to stay that way. Warnings will +be generated without __CHECK_ENDIAN__. + +__bitwise - noisy stuff; in particular, __le*/__be* are that. We really +don't want to drown in noise unless we'd explicitly asked for it. + +Using sparse for lock checking +------------------------------ + +The following macros are undefined for gcc and defined during a sparse +run to use the "context" tracking feature of sparse, applied to +locking. These annotations tell sparse when a lock is held, with +regard to the annotated function's entry and exit. + +__must_hold - The specified lock is held on function entry and exit. + +__acquires - The specified lock is held on function exit, but not entry. + +__releases - The specified lock is held on function entry, but not exit. + +If the function enters and exits without the lock held, acquiring and +releasing the lock inside the function in a balanced way, no +annotation is needed. The tree annotations above are for cases where +sparse would otherwise report a context imbalance. + +Getting sparse +-------------- + +You can get latest released versions from the Sparse homepage at +https://sparse.wiki.kernel.org/index.php/Main_Page + +Alternatively, you can get snapshots of the latest development version +of sparse using git to clone:: + + git://git.kernel.org/pub/scm/devel/sparse/sparse.git + +DaveJ has hourly generated tarballs of the git tree available at:: + + http://www.codemonkey.org.uk/projects/git-snapshots/sparse/ + + +Once you have it, just do:: + + make + make install + +as a regular user, and it will install sparse in your ~/bin directory. + +Using sparse +------------ + +Do a kernel make with "make C=1" to run sparse on all the C files that get +recompiled, or use "make C=2" to run sparse on the files whether they need to +be recompiled or not. The latter is a fast way to check the whole tree if you +have already built it. + +The optional make variable CF can be used to pass arguments to sparse. The +build system passes -Wbitwise to sparse automatically. To perform endianness +checks, you may define __CHECK_ENDIAN__:: + + make C=2 CF="-D__CHECK_ENDIAN__" + +These checks are disabled by default as they generate a host of warnings. diff --git a/Documentation/dev-tools/tools.rst b/Documentation/dev-tools/tools.rst index ae0c58c784db..d4bbda319e79 100644 --- a/Documentation/dev-tools/tools.rst +++ b/Documentation/dev-tools/tools.rst @@ -15,3 +15,4 @@ whole; patches welcome! :maxdepth: 2 coccinelle + sparse -- cgit v1.2.3 From 758f726e7f7c5a09d8627e6e6ad914e568b31a5c Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sun, 7 Aug 2016 15:13:00 -0600 Subject: docs: sphinxify kcov.txt and move to dev-tools Another document added to the dev-tools collection. Cc: Dmitry Vyukov Signed-off-by: Jonathan Corbet --- Documentation/dev-tools/kcov.rst | 111 ++++++++++++++++++++++++++++++++++++++ Documentation/dev-tools/tools.rst | 1 + 2 files changed, 112 insertions(+) create mode 100644 Documentation/dev-tools/kcov.rst (limited to 'Documentation/dev-tools') diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst new file mode 100644 index 000000000000..aca0e27ca197 --- /dev/null +++ b/Documentation/dev-tools/kcov.rst @@ -0,0 +1,111 @@ +kcov: code coverage for fuzzing +=============================== + +kcov exposes kernel code coverage information in a form suitable for coverage- +guided fuzzing (randomized testing). Coverage data of a running kernel is +exported via the "kcov" debugfs file. Coverage collection is enabled on a task +basis, and thus it can capture precise coverage of a single system call. + +Note that kcov does not aim to collect as much coverage as possible. It aims +to collect more or less stable coverage that is function of syscall inputs. +To achieve this goal it does not collect coverage in soft/hard interrupts +and instrumentation of some inherently non-deterministic parts of kernel is +disbled (e.g. scheduler, locking). + +Usage +----- + +Configure the kernel with:: + + CONFIG_KCOV=y + +CONFIG_KCOV requires gcc built on revision 231296 or later. +Profiling data will only become accessible once debugfs has been mounted:: + + mount -t debugfs none /sys/kernel/debug + +The following program demonstrates kcov usage from within a test program:: + + #include + #include + #include + #include + #include + #include + #include + #include + #include + #include + + #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) + #define KCOV_ENABLE _IO('c', 100) + #define KCOV_DISABLE _IO('c', 101) + #define COVER_SIZE (64<<10) + + int main(int argc, char **argv) + { + int fd; + unsigned long *cover, n, i; + + /* A single fd descriptor allows coverage collection on a single + * thread. + */ + fd = open("/sys/kernel/debug/kcov", O_RDWR); + if (fd == -1) + perror("open"), exit(1); + /* Setup trace mode and trace size. */ + if (ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE)) + perror("ioctl"), exit(1); + /* Mmap buffer shared between kernel- and user-space. */ + cover = (unsigned long*)mmap(NULL, COVER_SIZE * sizeof(unsigned long), + PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if ((void*)cover == MAP_FAILED) + perror("mmap"), exit(1); + /* Enable coverage collection on the current thread. */ + if (ioctl(fd, KCOV_ENABLE, 0)) + perror("ioctl"), exit(1); + /* Reset coverage from the tail of the ioctl() call. */ + __atomic_store_n(&cover[0], 0, __ATOMIC_RELAXED); + /* That's the target syscal call. */ + read(-1, NULL, 0); + /* Read number of PCs collected. */ + n = __atomic_load_n(&cover[0], __ATOMIC_RELAXED); + for (i = 0; i < n; i++) + printf("0x%lx\n", cover[i + 1]); + /* Disable coverage collection for the current thread. After this call + * coverage can be enabled for a different thread. + */ + if (ioctl(fd, KCOV_DISABLE, 0)) + perror("ioctl"), exit(1); + /* Free resources. */ + if (munmap(cover, COVER_SIZE * sizeof(unsigned long))) + perror("munmap"), exit(1); + if (close(fd)) + perror("close"), exit(1); + return 0; + } + +After piping through addr2line output of the program looks as follows:: + + SyS_read + fs/read_write.c:562 + __fdget_pos + fs/file.c:774 + __fget_light + fs/file.c:746 + __fget_light + fs/file.c:750 + __fget_light + fs/file.c:760 + __fdget_pos + fs/file.c:784 + SyS_read + fs/read_write.c:562 + +If a program needs to collect coverage from several threads (independently), +it needs to open /sys/kernel/debug/kcov in each thread separately. + +The interface is fine-grained to allow efficient forking of test processes. +That is, a parent process opens /sys/kernel/debug/kcov, enables trace mode, +mmaps coverage buffer and then forks child processes in a loop. Child processes +only need to enable coverage (disable happens automatically on thread end). diff --git a/Documentation/dev-tools/tools.rst b/Documentation/dev-tools/tools.rst index d4bbda319e79..9dcd0236a1ff 100644 --- a/Documentation/dev-tools/tools.rst +++ b/Documentation/dev-tools/tools.rst @@ -16,3 +16,4 @@ whole; patches welcome! coccinelle sparse + kcov -- cgit v1.2.3 From 2584bab2f990281244d3f39dc15cd9bd6d69f51d Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sun, 7 Aug 2016 15:26:20 -0600 Subject: docs: sphinixfy gcov.txt and move to dev-tools No textual changes beyond formatting. Cc: Peter Oberparleiter Signed-off-by: Jonathan Corbet --- Documentation/dev-tools/gcov.rst | 256 ++++++++++++++++++++++++++++++++++++++ Documentation/dev-tools/tools.rst | 1 + 2 files changed, 257 insertions(+) create mode 100644 Documentation/dev-tools/gcov.rst (limited to 'Documentation/dev-tools') diff --git a/Documentation/dev-tools/gcov.rst b/Documentation/dev-tools/gcov.rst new file mode 100644 index 000000000000..19eedfea8800 --- /dev/null +++ b/Documentation/dev-tools/gcov.rst @@ -0,0 +1,256 @@ +Using gcov with the Linux kernel +================================ + +gcov profiling kernel support enables the use of GCC's coverage testing +tool gcov_ with the Linux kernel. Coverage data of a running kernel +is exported in gcov-compatible format via the "gcov" debugfs directory. +To get coverage data for a specific file, change to the kernel build +directory and use gcov with the ``-o`` option as follows (requires root):: + + # cd /tmp/linux-out + # gcov -o /sys/kernel/debug/gcov/tmp/linux-out/kernel spinlock.c + +This will create source code files annotated with execution counts +in the current directory. In addition, graphical gcov front-ends such +as lcov_ can be used to automate the process of collecting data +for the entire kernel and provide coverage overviews in HTML format. + +Possible uses: + +* debugging (has this line been reached at all?) +* test improvement (how do I change my test to cover these lines?) +* minimizing kernel configurations (do I need this option if the + associated code is never run?) + +.. _gcov: http://gcc.gnu.org/onlinedocs/gcc/Gcov.html +.. _lcov: http://ltp.sourceforge.net/coverage/lcov.php + + +Preparation +----------- + +Configure the kernel with:: + + CONFIG_DEBUG_FS=y + CONFIG_GCOV_KERNEL=y + +select the gcc's gcov format, default is autodetect based on gcc version:: + + CONFIG_GCOV_FORMAT_AUTODETECT=y + +and to get coverage data for the entire kernel:: + + CONFIG_GCOV_PROFILE_ALL=y + +Note that kernels compiled with profiling flags will be significantly +larger and run slower. Also CONFIG_GCOV_PROFILE_ALL may not be supported +on all architectures. + +Profiling data will only become accessible once debugfs has been +mounted:: + + mount -t debugfs none /sys/kernel/debug + + +Customization +------------- + +To enable profiling for specific files or directories, add a line +similar to the following to the respective kernel Makefile: + +- For a single file (e.g. main.o):: + + GCOV_PROFILE_main.o := y + +- For all files in one directory:: + + GCOV_PROFILE := y + +To exclude files from being profiled even when CONFIG_GCOV_PROFILE_ALL +is specified, use:: + + GCOV_PROFILE_main.o := n + +and:: + + GCOV_PROFILE := n + +Only files which are linked to the main kernel image or are compiled as +kernel modules are supported by this mechanism. + + +Files +----- + +The gcov kernel support creates the following files in debugfs: + +``/sys/kernel/debug/gcov`` + Parent directory for all gcov-related files. + +``/sys/kernel/debug/gcov/reset`` + Global reset file: resets all coverage data to zero when + written to. + +``/sys/kernel/debug/gcov/path/to/compile/dir/file.gcda`` + The actual gcov data file as understood by the gcov + tool. Resets file coverage data to zero when written to. + +``/sys/kernel/debug/gcov/path/to/compile/dir/file.gcno`` + Symbolic link to a static data file required by the gcov + tool. This file is generated by gcc when compiling with + option ``-ftest-coverage``. + + +Modules +------- + +Kernel modules may contain cleanup code which is only run during +module unload time. The gcov mechanism provides a means to collect +coverage data for such code by keeping a copy of the data associated +with the unloaded module. This data remains available through debugfs. +Once the module is loaded again, the associated coverage counters are +initialized with the data from its previous instantiation. + +This behavior can be deactivated by specifying the gcov_persist kernel +parameter:: + + gcov_persist=0 + +At run-time, a user can also choose to discard data for an unloaded +module by writing to its data file or the global reset file. + + +Separated build and test machines +--------------------------------- + +The gcov kernel profiling infrastructure is designed to work out-of-the +box for setups where kernels are built and run on the same machine. In +cases where the kernel runs on a separate machine, special preparations +must be made, depending on where the gcov tool is used: + +a) gcov is run on the TEST machine + + The gcov tool version on the test machine must be compatible with the + gcc version used for kernel build. Also the following files need to be + copied from build to test machine: + + from the source tree: + - all C source files + headers + + from the build tree: + - all C source files + headers + - all .gcda and .gcno files + - all links to directories + + It is important to note that these files need to be placed into the + exact same file system location on the test machine as on the build + machine. If any of the path components is symbolic link, the actual + directory needs to be used instead (due to make's CURDIR handling). + +b) gcov is run on the BUILD machine + + The following files need to be copied after each test case from test + to build machine: + + from the gcov directory in sysfs: + - all .gcda files + - all links to .gcno files + + These files can be copied to any location on the build machine. gcov + must then be called with the -o option pointing to that directory. + + Example directory setup on the build machine:: + + /tmp/linux: kernel source tree + /tmp/out: kernel build directory as specified by make O= + /tmp/coverage: location of the files copied from the test machine + + [user@build] cd /tmp/out + [user@build] gcov -o /tmp/coverage/tmp/out/init main.c + + +Troubleshooting +--------------- + +Problem + Compilation aborts during linker step. + +Cause + Profiling flags are specified for source files which are not + linked to the main kernel or which are linked by a custom + linker procedure. + +Solution + Exclude affected source files from profiling by specifying + ``GCOV_PROFILE := n`` or ``GCOV_PROFILE_basename.o := n`` in the + corresponding Makefile. + +Problem + Files copied from sysfs appear empty or incomplete. + +Cause + Due to the way seq_file works, some tools such as cp or tar + may not correctly copy files from sysfs. + +Solution + Use ``cat``' to read ``.gcda`` files and ``cp -d`` to copy links. + Alternatively use the mechanism shown in Appendix B. + + +Appendix A: gather_on_build.sh +------------------------------ + +Sample script to gather coverage meta files on the build machine +(see 6a):: + + #!/bin/bash + + KSRC=$1 + KOBJ=$2 + DEST=$3 + + if [ -z "$KSRC" ] || [ -z "$KOBJ" ] || [ -z "$DEST" ]; then + echo "Usage: $0 " >&2 + exit 1 + fi + + KSRC=$(cd $KSRC; printf "all:\n\t@echo \${CURDIR}\n" | make -f -) + KOBJ=$(cd $KOBJ; printf "all:\n\t@echo \${CURDIR}\n" | make -f -) + + find $KSRC $KOBJ \( -name '*.gcno' -o -name '*.[ch]' -o -type l \) -a \ + -perm /u+r,g+r | tar cfz $DEST -P -T - + + if [ $? -eq 0 ] ; then + echo "$DEST successfully created, copy to test system and unpack with:" + echo " tar xfz $DEST -P" + else + echo "Could not create file $DEST" + fi + + +Appendix B: gather_on_test.sh +----------------------------- + +Sample script to gather coverage data files on the test machine +(see 6b):: + + #!/bin/bash -e + + DEST=$1 + GCDA=/sys/kernel/debug/gcov + + if [ -z "$DEST" ] ; then + echo "Usage: $0 " >&2 + exit 1 + fi + + TEMPDIR=$(mktemp -d) + echo Collecting data.. + find $GCDA -type d -exec mkdir -p $TEMPDIR/\{\} \; + find $GCDA -name '*.gcda' -exec sh -c 'cat < $0 > '$TEMPDIR'/$0' {} \; + find $GCDA -name '*.gcno' -exec sh -c 'cp -d $0 '$TEMPDIR'/$0' {} \; + tar czf $DEST -C $TEMPDIR sys + rm -rf $TEMPDIR + + echo "$DEST successfully created, copy to build system and unpack with:" + echo " tar xfz $DEST" diff --git a/Documentation/dev-tools/tools.rst b/Documentation/dev-tools/tools.rst index 9dcd0236a1ff..404d044c8518 100644 --- a/Documentation/dev-tools/tools.rst +++ b/Documentation/dev-tools/tools.rst @@ -17,3 +17,4 @@ whole; patches welcome! coccinelle sparse kcov + gcov -- cgit v1.2.3 From 2757aafad9ee7b8740042e5540b59422337344ab Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sun, 7 Aug 2016 15:31:03 -0600 Subject: docs: sphinxify kasan.txt and move to dev-tools No textual changes beyond formatting. Acked-by: Andrey Ryabinin Acked-by: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Jonathan Corbet --- Documentation/dev-tools/kasan.rst | 173 ++++++++++++++++++++++++++++++++++++++ Documentation/dev-tools/tools.rst | 1 + 2 files changed, 174 insertions(+) create mode 100644 Documentation/dev-tools/kasan.rst (limited to 'Documentation/dev-tools') diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst new file mode 100644 index 000000000000..948d243bed86 --- /dev/null +++ b/Documentation/dev-tools/kasan.rst @@ -0,0 +1,173 @@ +The Kernel Address Sanitizer (KASAN) +==================================== + +Overview +-------- + +KernelAddressSANitizer (KASAN) is a dynamic memory error detector. It provides +a fast and comprehensive solution for finding use-after-free and out-of-bounds +bugs. + +KASAN uses compile-time instrumentation for checking every memory access, +therefore you will need a GCC version 4.9.2 or later. GCC 5.0 or later is +required for detection of out-of-bounds accesses to stack or global variables. + +Currently KASAN is supported only for x86_64 architecture. + +Usage +----- + +To enable KASAN configure kernel with:: + + CONFIG_KASAN = y + +and choose between CONFIG_KASAN_OUTLINE and CONFIG_KASAN_INLINE. Outline and +inline are compiler instrumentation types. The former produces smaller binary +the latter is 1.1 - 2 times faster. Inline instrumentation requires a GCC +version 5.0 or later. + +KASAN works with both SLUB and SLAB memory allocators. +For better bug detection and nicer reporting, enable CONFIG_STACKTRACE. + +To disable instrumentation for specific files or directories, add a line +similar to the following to the respective kernel Makefile: + +- For a single file (e.g. main.o):: + + KASAN_SANITIZE_main.o := n + +- For all files in one directory:: + + KASAN_SANITIZE := n + +Error reports +~~~~~~~~~~~~~ + +A typical out of bounds access report looks like this:: + + ================================================================== + BUG: AddressSanitizer: out of bounds access in kmalloc_oob_right+0x65/0x75 [test_kasan] at addr ffff8800693bc5d3 + Write of size 1 by task modprobe/1689 + ============================================================================= + BUG kmalloc-128 (Not tainted): kasan error + ----------------------------------------------------------------------------- + + Disabling lock debugging due to kernel taint + INFO: Allocated in kmalloc_oob_right+0x3d/0x75 [test_kasan] age=0 cpu=0 pid=1689 + __slab_alloc+0x4b4/0x4f0 + kmem_cache_alloc_trace+0x10b/0x190 + kmalloc_oob_right+0x3d/0x75 [test_kasan] + init_module+0x9/0x47 [test_kasan] + do_one_initcall+0x99/0x200 + load_module+0x2cb3/0x3b20 + SyS_finit_module+0x76/0x80 + system_call_fastpath+0x12/0x17 + INFO: Slab 0xffffea0001a4ef00 objects=17 used=7 fp=0xffff8800693bd728 flags=0x100000000004080 + INFO: Object 0xffff8800693bc558 @offset=1368 fp=0xffff8800693bc720 + + Bytes b4 ffff8800693bc548: 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ + Object ffff8800693bc558: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk + Object ffff8800693bc568: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk + Object ffff8800693bc578: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk + Object ffff8800693bc588: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk + Object ffff8800693bc598: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk + Object ffff8800693bc5a8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk + Object ffff8800693bc5b8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk + Object ffff8800693bc5c8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b a5 kkkkkkkkkkkkkkk. + Redzone ffff8800693bc5d8: cc cc cc cc cc cc cc cc ........ + Padding ffff8800693bc718: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ + CPU: 0 PID: 1689 Comm: modprobe Tainted: G B 3.18.0-rc1-mm1+ #98 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014 + ffff8800693bc000 0000000000000000 ffff8800693bc558 ffff88006923bb78 + ffffffff81cc68ae 00000000000000f3 ffff88006d407600 ffff88006923bba8 + ffffffff811fd848 ffff88006d407600 ffffea0001a4ef00 ffff8800693bc558 + Call Trace: + [] dump_stack+0x46/0x58 + [] print_trailer+0xf8/0x160 + [] ? kmem_cache_oob+0xc3/0xc3 [test_kasan] + [] object_err+0x35/0x40 + [] ? kmalloc_oob_right+0x65/0x75 [test_kasan] + [] kasan_report_error+0x38a/0x3f0 + [] ? kasan_poison_shadow+0x2f/0x40 + [] ? kasan_unpoison_shadow+0x14/0x40 + [] ? kasan_poison_shadow+0x2f/0x40 + [] ? kmem_cache_oob+0xc3/0xc3 [test_kasan] + [] __asan_store1+0x75/0xb0 + [] ? kmem_cache_oob+0x1d/0xc3 [test_kasan] + [] ? kmalloc_oob_right+0x65/0x75 [test_kasan] + [] kmalloc_oob_right+0x65/0x75 [test_kasan] + [] init_module+0x9/0x47 [test_kasan] + [] do_one_initcall+0x99/0x200 + [] ? __vunmap+0xec/0x160 + [] load_module+0x2cb3/0x3b20 + [] ? m_show+0x240/0x240 + [] SyS_finit_module+0x76/0x80 + [] system_call_fastpath+0x12/0x17 + Memory state around the buggy address: + ffff8800693bc300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc + ffff8800693bc380: fc fc 00 00 00 00 00 00 00 00 00 00 00 00 00 fc + ffff8800693bc400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc + ffff8800693bc480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc + ffff8800693bc500: fc fc fc fc fc fc fc fc fc fc fc 00 00 00 00 00 + >ffff8800693bc580: 00 00 00 00 00 00 00 00 00 00 03 fc fc fc fc fc + ^ + ffff8800693bc600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc + ffff8800693bc680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc + ffff8800693bc700: fc fc fc fc fb fb fb fb fb fb fb fb fb fb fb fb + ffff8800693bc780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb + ffff8800693bc800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb + ================================================================== + +The header of the report discribe what kind of bug happened and what kind of +access caused it. It's followed by the description of the accessed slub object +(see 'SLUB Debug output' section in Documentation/vm/slub.txt for details) and +the description of the accessed memory page. + +In the last section the report shows memory state around the accessed address. +Reading this part requires some understanding of how KASAN works. + +The state of each 8 aligned bytes of memory is encoded in one shadow byte. +Those 8 bytes can be accessible, partially accessible, freed or be a redzone. +We use the following encoding for each shadow byte: 0 means that all 8 bytes +of the corresponding memory region are accessible; number N (1 <= N <= 7) means +that the first N bytes are accessible, and other (8 - N) bytes are not; +any negative value indicates that the entire 8-byte word is inaccessible. +We use different negative values to distinguish between different kinds of +inaccessible memory like redzones or freed memory (see mm/kasan/kasan.h). + +In the report above the arrows point to the shadow byte 03, which means that +the accessed address is partially accessible. + + +Implementation details +---------------------- + +From a high level, our approach to memory error detection is similar to that +of kmemcheck: use shadow memory to record whether each byte of memory is safe +to access, and use compile-time instrumentation to check shadow memory on each +memory access. + +AddressSanitizer dedicates 1/8 of kernel memory to its shadow memory +(e.g. 16TB to cover 128TB on x86_64) and uses direct mapping with a scale and +offset to translate a memory address to its corresponding shadow address. + +Here is the function which translates an address to its corresponding shadow +address:: + + static inline void *kasan_mem_to_shadow(const void *addr) + { + return ((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT) + + KASAN_SHADOW_OFFSET; + } + +where ``KASAN_SHADOW_SCALE_SHIFT = 3``. + +Compile-time instrumentation used for checking memory accesses. Compiler inserts +function calls (__asan_load*(addr), __asan_store*(addr)) before each memory +access of size 1, 2, 4, 8 or 16. These functions check whether memory access is +valid or not by checking corresponding shadow memory. + +GCC 5.0 has possibility to perform inline instrumentation. Instead of making +function calls GCC directly inserts the code to check the shadow memory. +This option significantly enlarges kernel but it gives x1.1-x2 performance +boost over outline instrumented kernel. diff --git a/Documentation/dev-tools/tools.rst b/Documentation/dev-tools/tools.rst index 404d044c8518..0500e6500255 100644 --- a/Documentation/dev-tools/tools.rst +++ b/Documentation/dev-tools/tools.rst @@ -18,3 +18,4 @@ whole; patches welcome! sparse kcov gcov + kasan -- cgit v1.2.3 From 1ead009cd622bc4c3c2cf1036d8e71d7f063838e Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sun, 7 Aug 2016 15:35:42 -0600 Subject: docs: sphinxify ubsan.txt and move it to dev-tools Acked-by: Andrey Ryabinin Signed-off-by: Jonathan Corbet --- Documentation/dev-tools/tools.rst | 1 + Documentation/dev-tools/ubsan.rst | 88 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 89 insertions(+) create mode 100644 Documentation/dev-tools/ubsan.rst (limited to 'Documentation/dev-tools') diff --git a/Documentation/dev-tools/tools.rst b/Documentation/dev-tools/tools.rst index 0500e6500255..2d1129789753 100644 --- a/Documentation/dev-tools/tools.rst +++ b/Documentation/dev-tools/tools.rst @@ -19,3 +19,4 @@ whole; patches welcome! kcov gcov kasan + ubsan diff --git a/Documentation/dev-tools/ubsan.rst b/Documentation/dev-tools/ubsan.rst new file mode 100644 index 000000000000..655e6b63c227 --- /dev/null +++ b/Documentation/dev-tools/ubsan.rst @@ -0,0 +1,88 @@ +The Undefined Behavior Sanitizer - UBSAN +======================================== + +UBSAN is a runtime undefined behaviour checker. + +UBSAN uses compile-time instrumentation to catch undefined behavior (UB). +Compiler inserts code that perform certain kinds of checks before operations +that may cause UB. If check fails (i.e. UB detected) __ubsan_handle_* +function called to print error message. + +GCC has that feature since 4.9.x [1_] (see ``-fsanitize=undefined`` option and +its suboptions). GCC 5.x has more checkers implemented [2_]. + +Report example +-------------- + +:: + + ================================================================================ + UBSAN: Undefined behaviour in ../include/linux/bitops.h:110:33 + shift exponent 32 is to large for 32-bit type 'unsigned int' + CPU: 0 PID: 0 Comm: swapper Not tainted 4.4.0-rc1+ #26 + 0000000000000000 ffffffff82403cc8 ffffffff815e6cd6 0000000000000001 + ffffffff82403cf8 ffffffff82403ce0 ffffffff8163a5ed 0000000000000020 + ffffffff82403d78 ffffffff8163ac2b ffffffff815f0001 0000000000000002 + Call Trace: + [] dump_stack+0x45/0x5f + [] ubsan_epilogue+0xd/0x40 + [] __ubsan_handle_shift_out_of_bounds+0xeb/0x130 + [] ? radix_tree_gang_lookup_slot+0x51/0x150 + [] _mix_pool_bytes+0x1e6/0x480 + [] ? dmi_walk_early+0x48/0x5c + [] add_device_randomness+0x61/0x130 + [] ? dmi_save_one_device+0xaa/0xaa + [] dmi_walk_early+0x48/0x5c + [] dmi_scan_machine+0x278/0x4b4 + [] ? vprintk_default+0x1a/0x20 + [] ? early_idt_handler_array+0x120/0x120 + [] setup_arch+0x405/0xc2c + [] ? early_idt_handler_array+0x120/0x120 + [] start_kernel+0x83/0x49a + [] ? early_idt_handler_array+0x120/0x120 + [] x86_64_start_reservations+0x2a/0x2c + [] x86_64_start_kernel+0x16b/0x17a + ================================================================================ + +Usage +----- + +To enable UBSAN configure kernel with:: + + CONFIG_UBSAN=y + +and to check the entire kernel:: + + CONFIG_UBSAN_SANITIZE_ALL=y + +To enable instrumentation for specific files or directories, add a line +similar to the following to the respective kernel Makefile: + +- For a single file (e.g. main.o):: + + UBSAN_SANITIZE_main.o := y + +- For all files in one directory:: + + UBSAN_SANITIZE := y + +To exclude files from being instrumented even if +``CONFIG_UBSAN_SANITIZE_ALL=y``, use:: + + UBSAN_SANITIZE_main.o := n + +and:: + + UBSAN_SANITIZE := n + +Detection of unaligned accesses controlled through the separate option - +CONFIG_UBSAN_ALIGNMENT. It's off by default on architectures that support +unaligned accesses (CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y). One could +still enable it in config, just note that it will produce a lot of UBSAN +reports. + +References +---------- + +.. _1: https://gcc.gnu.org/onlinedocs/gcc-4.9.0/gcc/Debugging-Options.html +.. _2: https://gcc.gnu.org/onlinedocs/gcc/Debugging-Options.html -- cgit v1.2.3 From ca90a7a38741adf5ce450572952fbbda35055ea4 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sun, 7 Aug 2016 15:46:10 -0600 Subject: docs: sphinxify kmemleak.txt and move it to dev-tools Acked-by: Catalin Marinas Signed-off-by: Jonathan Corbet --- Documentation/dev-tools/kmemleak.rst | 210 +++++++++++++++++++++++++++++++++++ Documentation/dev-tools/tools.rst | 1 + 2 files changed, 211 insertions(+) create mode 100644 Documentation/dev-tools/kmemleak.rst (limited to 'Documentation/dev-tools') diff --git a/Documentation/dev-tools/kmemleak.rst b/Documentation/dev-tools/kmemleak.rst new file mode 100644 index 000000000000..1788722d5495 --- /dev/null +++ b/Documentation/dev-tools/kmemleak.rst @@ -0,0 +1,210 @@ +Kernel Memory Leak Detector +=========================== + +Kmemleak provides a way of detecting possible kernel memory leaks in a +way similar to a tracing garbage collector +(https://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors), +with the difference that the orphan objects are not freed but only +reported via /sys/kernel/debug/kmemleak. A similar method is used by the +Valgrind tool (``memcheck --leak-check``) to detect the memory leaks in +user-space applications. +Kmemleak is supported on x86, arm, powerpc, sparc, sh, microblaze, ppc, mips, s390, metag and tile. + +Usage +----- + +CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel +thread scans the memory every 10 minutes (by default) and prints the +number of new unreferenced objects found. To display the details of all +the possible memory leaks:: + + # mount -t debugfs nodev /sys/kernel/debug/ + # cat /sys/kernel/debug/kmemleak + +To trigger an intermediate memory scan:: + + # echo scan > /sys/kernel/debug/kmemleak + +To clear the list of all current possible memory leaks:: + + # echo clear > /sys/kernel/debug/kmemleak + +New leaks will then come up upon reading ``/sys/kernel/debug/kmemleak`` +again. + +Note that the orphan objects are listed in the order they were allocated +and one object at the beginning of the list may cause other subsequent +objects to be reported as orphan. + +Memory scanning parameters can be modified at run-time by writing to the +``/sys/kernel/debug/kmemleak`` file. The following parameters are supported: + +- off + disable kmemleak (irreversible) +- stack=on + enable the task stacks scanning (default) +- stack=off + disable the tasks stacks scanning +- scan=on + start the automatic memory scanning thread (default) +- scan=off + stop the automatic memory scanning thread +- scan= + set the automatic memory scanning period in seconds + (default 600, 0 to stop the automatic scanning) +- scan + trigger a memory scan +- clear + clear list of current memory leak suspects, done by + marking all current reported unreferenced objects grey, + or free all kmemleak objects if kmemleak has been disabled. +- dump= + dump information about the object found at + +Kmemleak can also be disabled at boot-time by passing ``kmemleak=off`` on +the kernel command line. + +Memory may be allocated or freed before kmemleak is initialised and +these actions are stored in an early log buffer. The size of this buffer +is configured via the CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE option. + +If CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF are enabled, the kmemleak is +disabled by default. Passing ``kmemleak=on`` on the kernel command +line enables the function. + +Basic Algorithm +--------------- + +The memory allocations via :c:func:`kmalloc`, :c:func:`vmalloc`, +:c:func:`kmem_cache_alloc` and +friends are traced and the pointers, together with additional +information like size and stack trace, are stored in a rbtree. +The corresponding freeing function calls are tracked and the pointers +removed from the kmemleak data structures. + +An allocated block of memory is considered orphan if no pointer to its +start address or to any location inside the block can be found by +scanning the memory (including saved registers). This means that there +might be no way for the kernel to pass the address of the allocated +block to a freeing function and therefore the block is considered a +memory leak. + +The scanning algorithm steps: + + 1. mark all objects as white (remaining white objects will later be + considered orphan) + 2. scan the memory starting with the data section and stacks, checking + the values against the addresses stored in the rbtree. If + a pointer to a white object is found, the object is added to the + gray list + 3. scan the gray objects for matching addresses (some white objects + can become gray and added at the end of the gray list) until the + gray set is finished + 4. the remaining white objects are considered orphan and reported via + /sys/kernel/debug/kmemleak + +Some allocated memory blocks have pointers stored in the kernel's +internal data structures and they cannot be detected as orphans. To +avoid this, kmemleak can also store the number of values pointing to an +address inside the block address range that need to be found so that the +block is not considered a leak. One example is __vmalloc(). + +Testing specific sections with kmemleak +--------------------------------------- + +Upon initial bootup your /sys/kernel/debug/kmemleak output page may be +quite extensive. This can also be the case if you have very buggy code +when doing development. To work around these situations you can use the +'clear' command to clear all reported unreferenced objects from the +/sys/kernel/debug/kmemleak output. By issuing a 'scan' after a 'clear' +you can find new unreferenced objects; this should help with testing +specific sections of code. + +To test a critical section on demand with a clean kmemleak do:: + + # echo clear > /sys/kernel/debug/kmemleak + ... test your kernel or modules ... + # echo scan > /sys/kernel/debug/kmemleak + +Then as usual to get your report with:: + + # cat /sys/kernel/debug/kmemleak + +Freeing kmemleak internal objects +--------------------------------- + +To allow access to previously found memory leaks after kmemleak has been +disabled by the user or due to an fatal error, internal kmemleak objects +won't be freed when kmemleak is disabled, and those objects may occupy +a large part of physical memory. + +In this situation, you may reclaim memory with:: + + # echo clear > /sys/kernel/debug/kmemleak + +Kmemleak API +------------ + +See the include/linux/kmemleak.h header for the functions prototype. + +- ``kmemleak_init`` - initialize kmemleak +- ``kmemleak_alloc`` - notify of a memory block allocation +- ``kmemleak_alloc_percpu`` - notify of a percpu memory block allocation +- ``kmemleak_free`` - notify of a memory block freeing +- ``kmemleak_free_part`` - notify of a partial memory block freeing +- ``kmemleak_free_percpu`` - notify of a percpu memory block freeing +- ``kmemleak_update_trace`` - update object allocation stack trace +- ``kmemleak_not_leak`` - mark an object as not a leak +- ``kmemleak_ignore`` - do not scan or report an object as leak +- ``kmemleak_scan_area`` - add scan areas inside a memory block +- ``kmemleak_no_scan`` - do not scan a memory block +- ``kmemleak_erase`` - erase an old value in a pointer variable +- ``kmemleak_alloc_recursive`` - as kmemleak_alloc but checks the recursiveness +- ``kmemleak_free_recursive`` - as kmemleak_free but checks the recursiveness + +Dealing with false positives/negatives +-------------------------------------- + +The false negatives are real memory leaks (orphan objects) but not +reported by kmemleak because values found during the memory scanning +point to such objects. To reduce the number of false negatives, kmemleak +provides the kmemleak_ignore, kmemleak_scan_area, kmemleak_no_scan and +kmemleak_erase functions (see above). The task stacks also increase the +amount of false negatives and their scanning is not enabled by default. + +The false positives are objects wrongly reported as being memory leaks +(orphan). For objects known not to be leaks, kmemleak provides the +kmemleak_not_leak function. The kmemleak_ignore could also be used if +the memory block is known not to contain other pointers and it will no +longer be scanned. + +Some of the reported leaks are only transient, especially on SMP +systems, because of pointers temporarily stored in CPU registers or +stacks. Kmemleak defines MSECS_MIN_AGE (defaulting to 1000) representing +the minimum age of an object to be reported as a memory leak. + +Limitations and Drawbacks +------------------------- + +The main drawback is the reduced performance of memory allocation and +freeing. To avoid other penalties, the memory scanning is only performed +when the /sys/kernel/debug/kmemleak file is read. Anyway, this tool is +intended for debugging purposes where the performance might not be the +most important requirement. + +To keep the algorithm simple, kmemleak scans for values pointing to any +address inside a block's address range. This may lead to an increased +number of false negatives. However, it is likely that a real memory leak +will eventually become visible. + +Another source of false negatives is the data stored in non-pointer +values. In a future version, kmemleak could only scan the pointer +members in the allocated structures. This feature would solve many of +the false negative cases described above. + +The tool can report false positives. These are cases where an allocated +block doesn't need to be freed (some cases in the init_call functions), +the pointer is calculated by other methods than the usual container_of +macro or the pointer is stored in a location not scanned by kmemleak. + +Page allocations and ioremap are not tracked. diff --git a/Documentation/dev-tools/tools.rst b/Documentation/dev-tools/tools.rst index 2d1129789753..3b6382a58301 100644 --- a/Documentation/dev-tools/tools.rst +++ b/Documentation/dev-tools/tools.rst @@ -20,3 +20,4 @@ whole; patches welcome! gcov kasan ubsan + kmemleak -- cgit v1.2.3 From 9c296b46c67ed323538bca80a8be1f0b10e570a0 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sun, 7 Aug 2016 16:12:28 -0600 Subject: docs: sphinxify kmemcheck.txt and move to dev-tools Cc: Vegard Nossum Cc: Pekka Enberg Signed-off-by: Jonathan Corbet --- Documentation/dev-tools/kmemcheck.rst | 733 ++++++++++++++++++++++++++++++++++ Documentation/dev-tools/tools.rst | 1 + 2 files changed, 734 insertions(+) create mode 100644 Documentation/dev-tools/kmemcheck.rst (limited to 'Documentation/dev-tools') diff --git a/Documentation/dev-tools/kmemcheck.rst b/Documentation/dev-tools/kmemcheck.rst new file mode 100644 index 000000000000..7f3d1985de74 --- /dev/null +++ b/Documentation/dev-tools/kmemcheck.rst @@ -0,0 +1,733 @@ +Getting started with kmemcheck +============================== + +Vegard Nossum + + +Introduction +------------ + +kmemcheck is a debugging feature for the Linux Kernel. More specifically, it +is a dynamic checker that detects and warns about some uses of uninitialized +memory. + +Userspace programmers might be familiar with Valgrind's memcheck. The main +difference between memcheck and kmemcheck is that memcheck works for userspace +programs only, and kmemcheck works for the kernel only. The implementations +are of course vastly different. Because of this, kmemcheck is not as accurate +as memcheck, but it turns out to be good enough in practice to discover real +programmer errors that the compiler is not able to find through static +analysis. + +Enabling kmemcheck on a kernel will probably slow it down to the extent that +the machine will not be usable for normal workloads such as e.g. an +interactive desktop. kmemcheck will also cause the kernel to use about twice +as much memory as normal. For this reason, kmemcheck is strictly a debugging +feature. + + +Downloading +----------- + +As of version 2.6.31-rc1, kmemcheck is included in the mainline kernel. + + +Configuring and compiling +------------------------- + +kmemcheck only works for the x86 (both 32- and 64-bit) platform. A number of +configuration variables must have specific settings in order for the kmemcheck +menu to even appear in "menuconfig". These are: + +- ``CONFIG_CC_OPTIMIZE_FOR_SIZE=n`` + This option is located under "General setup" / "Optimize for size". + + Without this, gcc will use certain optimizations that usually lead to + false positive warnings from kmemcheck. An example of this is a 16-bit + field in a struct, where gcc may load 32 bits, then discard the upper + 16 bits. kmemcheck sees only the 32-bit load, and may trigger a + warning for the upper 16 bits (if they're uninitialized). + +- ``CONFIG_SLAB=y`` or ``CONFIG_SLUB=y`` + This option is located under "General setup" / "Choose SLAB + allocator". + +- ``CONFIG_FUNCTION_TRACER=n`` + This option is located under "Kernel hacking" / "Tracers" / "Kernel + Function Tracer" + + When function tracing is compiled in, gcc emits a call to another + function at the beginning of every function. This means that when the + page fault handler is called, the ftrace framework will be called + before kmemcheck has had a chance to handle the fault. If ftrace then + modifies memory that was tracked by kmemcheck, the result is an + endless recursive page fault. + +- ``CONFIG_DEBUG_PAGEALLOC=n`` + This option is located under "Kernel hacking" / "Memory Debugging" + / "Debug page memory allocations". + +In addition, I highly recommend turning on ``CONFIG_DEBUG_INFO=y``. This is also +located under "Kernel hacking". With this, you will be able to get line number +information from the kmemcheck warnings, which is extremely valuable in +debugging a problem. This option is not mandatory, however, because it slows +down the compilation process and produces a much bigger kernel image. + +Now the kmemcheck menu should be visible (under "Kernel hacking" / "Memory +Debugging" / "kmemcheck: trap use of uninitialized memory"). Here follows +a description of the kmemcheck configuration variables: + +- ``CONFIG_KMEMCHECK`` + This must be enabled in order to use kmemcheck at all... + +- ``CONFIG_KMEMCHECK_``[``DISABLED`` | ``ENABLED`` | ``ONESHOT``]``_BY_DEFAULT`` + This option controls the status of kmemcheck at boot-time. "Enabled" + will enable kmemcheck right from the start, "disabled" will boot the + kernel as normal (but with the kmemcheck code compiled in, so it can + be enabled at run-time after the kernel has booted), and "one-shot" is + a special mode which will turn kmemcheck off automatically after + detecting the first use of uninitialized memory. + + If you are using kmemcheck to actively debug a problem, then you + probably want to choose "enabled" here. + + The one-shot mode is mostly useful in automated test setups because it + can prevent floods of warnings and increase the chances of the machine + surviving in case something is really wrong. In other cases, the one- + shot mode could actually be counter-productive because it would turn + itself off at the very first error -- in the case of a false positive + too -- and this would come in the way of debugging the specific + problem you were interested in. + + If you would like to use your kernel as normal, but with a chance to + enable kmemcheck in case of some problem, it might be a good idea to + choose "disabled" here. When kmemcheck is disabled, most of the run- + time overhead is not incurred, and the kernel will be almost as fast + as normal. + +- ``CONFIG_KMEMCHECK_QUEUE_SIZE`` + Select the maximum number of error reports to store in an internal + (fixed-size) buffer. Since errors can occur virtually anywhere and in + any context, we need a temporary storage area which is guaranteed not + to generate any other page faults when accessed. The queue will be + emptied as soon as a tasklet may be scheduled. If the queue is full, + new error reports will be lost. + + The default value of 64 is probably fine. If some code produces more + than 64 errors within an irqs-off section, then the code is likely to + produce many, many more, too, and these additional reports seldom give + any more information (the first report is usually the most valuable + anyway). + + This number might have to be adjusted if you are not using serial + console or similar to capture the kernel log. If you are using the + "dmesg" command to save the log, then getting a lot of kmemcheck + warnings might overflow the kernel log itself, and the earlier reports + will get lost in that way instead. Try setting this to 10 or so on + such a setup. + +- ``CONFIG_KMEMCHECK_SHADOW_COPY_SHIFT`` + Select the number of shadow bytes to save along with each entry of the + error-report queue. These bytes indicate what parts of an allocation + are initialized, uninitialized, etc. and will be displayed when an + error is detected to help the debugging of a particular problem. + + The number entered here is actually the logarithm of the number of + bytes that will be saved. So if you pick for example 5 here, kmemcheck + will save 2^5 = 32 bytes. + + The default value should be fine for debugging most problems. It also + fits nicely within 80 columns. + +- ``CONFIG_KMEMCHECK_PARTIAL_OK`` + This option (when enabled) works around certain GCC optimizations that + produce 32-bit reads from 16-bit variables where the upper 16 bits are + thrown away afterwards. + + The default value (enabled) is recommended. This may of course hide + some real errors, but disabling it would probably produce a lot of + false positives. + +- ``CONFIG_KMEMCHECK_BITOPS_OK`` + This option silences warnings that would be generated for bit-field + accesses where not all the bits are initialized at the same time. This + may also hide some real bugs. + + This option is probably obsolete, or it should be replaced with + the kmemcheck-/bitfield-annotations for the code in question. The + default value is therefore fine. + +Now compile the kernel as usual. + + +How to use +---------- + +Booting +~~~~~~~ + +First some information about the command-line options. There is only one +option specific to kmemcheck, and this is called "kmemcheck". It can be used +to override the default mode as chosen by the ``CONFIG_KMEMCHECK_*_BY_DEFAULT`` +option. Its possible settings are: + +- ``kmemcheck=0`` (disabled) +- ``kmemcheck=1`` (enabled) +- ``kmemcheck=2`` (one-shot mode) + +If SLUB debugging has been enabled in the kernel, it may take precedence over +kmemcheck in such a way that the slab caches which are under SLUB debugging +will not be tracked by kmemcheck. In order to ensure that this doesn't happen +(even though it shouldn't by default), use SLUB's boot option ``slub_debug``, +like this: ``slub_debug=-`` + +In fact, this option may also be used for fine-grained control over SLUB vs. +kmemcheck. For example, if the command line includes +``kmemcheck=1 slub_debug=,dentry``, then SLUB debugging will be used only +for the "dentry" slab cache, and with kmemcheck tracking all the other +caches. This is advanced usage, however, and is not generally recommended. + + +Run-time enable/disable +~~~~~~~~~~~~~~~~~~~~~~~ + +When the kernel has booted, it is possible to enable or disable kmemcheck at +run-time. WARNING: This feature is still experimental and may cause false +positive warnings to appear. Therefore, try not to use this. If you find that +it doesn't work properly (e.g. you see an unreasonable amount of warnings), I +will be happy to take bug reports. + +Use the file ``/proc/sys/kernel/kmemcheck`` for this purpose, e.g.:: + + $ echo 0 > /proc/sys/kernel/kmemcheck # disables kmemcheck + +The numbers are the same as for the ``kmemcheck=`` command-line option. + + +Debugging +~~~~~~~~~ + +A typical report will look something like this:: + + WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (ffff88003e4a2024) + 80000000000000000000000000000000000000000088ffff0000000000000000 + i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u + ^ + + Pid: 1856, comm: ntpdate Not tainted 2.6.29-rc5 #264 945P-A + RIP: 0010:[] [] __dequeue_signal+0xc8/0x190 + RSP: 0018:ffff88003cdf7d98 EFLAGS: 00210002 + RAX: 0000000000000030 RBX: ffff88003d4ea968 RCX: 0000000000000009 + RDX: ffff88003e5d6018 RSI: ffff88003e5d6024 RDI: ffff88003cdf7e84 + RBP: ffff88003cdf7db8 R08: ffff88003e5d6000 R09: 0000000000000000 + R10: 0000000000000080 R11: 0000000000000000 R12: 000000000000000e + R13: ffff88003cdf7e78 R14: ffff88003d530710 R15: ffff88003d5a98c8 + FS: 0000000000000000(0000) GS:ffff880001982000(0063) knlGS:00000 + CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 + CR2: ffff88003f806ea0 CR3: 000000003c036000 CR4: 00000000000006a0 + DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 + DR3: 0000000000000000 DR6: 00000000ffff4ff0 DR7: 0000000000000400 + [] dequeue_signal+0x8e/0x170 + [] get_signal_to_deliver+0x98/0x390 + [] do_notify_resume+0xad/0x7d0 + [] int_signal+0x12/0x17 + [] 0xffffffffffffffff + +The single most valuable information in this report is the RIP (or EIP on 32- +bit) value. This will help us pinpoint exactly which instruction that caused +the warning. + +If your kernel was compiled with ``CONFIG_DEBUG_INFO=y``, then all we have to do +is give this address to the addr2line program, like this:: + + $ addr2line -e vmlinux -i ffffffff8104ede8 + arch/x86/include/asm/string_64.h:12 + include/asm-generic/siginfo.h:287 + kernel/signal.c:380 + kernel/signal.c:410 + +The "``-e vmlinux``" tells addr2line which file to look in. **IMPORTANT:** +This must be the vmlinux of the kernel that produced the warning in the +first place! If not, the line number information will almost certainly be +wrong. + +The "``-i``" tells addr2line to also print the line numbers of inlined +functions. In this case, the flag was very important, because otherwise, +it would only have printed the first line, which is just a call to +``memcpy()``, which could be called from a thousand places in the kernel, and +is therefore not very useful. These inlined functions would not show up in +the stack trace above, simply because the kernel doesn't load the extra +debugging information. This technique can of course be used with ordinary +kernel oopses as well. + +In this case, it's the caller of ``memcpy()`` that is interesting, and it can be +found in ``include/asm-generic/siginfo.h``, line 287:: + + 281 static inline void copy_siginfo(struct siginfo *to, struct siginfo *from) + 282 { + 283 if (from->si_code < 0) + 284 memcpy(to, from, sizeof(*to)); + 285 else + 286 /* _sigchld is currently the largest know union member */ + 287 memcpy(to, from, __ARCH_SI_PREAMBLE_SIZE + sizeof(from->_sifields._sigchld)); + 288 } + +Since this was a read (kmemcheck usually warns about reads only, though it can +warn about writes to unallocated or freed memory as well), it was probably the +"from" argument which contained some uninitialized bytes. Following the chain +of calls, we move upwards to see where "from" was allocated or initialized, +``kernel/signal.c``, line 380:: + + 359 static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) + 360 { + ... + 367 list_for_each_entry(q, &list->list, list) { + 368 if (q->info.si_signo == sig) { + 369 if (first) + 370 goto still_pending; + 371 first = q; + ... + 377 if (first) { + 378 still_pending: + 379 list_del_init(&first->list); + 380 copy_siginfo(info, &first->info); + 381 __sigqueue_free(first); + ... + 392 } + 393 } + +Here, it is ``&first->info`` that is being passed on to ``copy_siginfo()``. The +variable ``first`` was found on a list -- passed in as the second argument to +``collect_signal()``. We continue our journey through the stack, to figure out +where the item on "list" was allocated or initialized. We move to line 410:: + + 395 static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, + 396 siginfo_t *info) + 397 { + ... + 410 collect_signal(sig, pending, info); + ... + 414 } + +Now we need to follow the ``pending`` pointer, since that is being passed on to +``collect_signal()`` as ``list``. At this point, we've run out of lines from the +"addr2line" output. Not to worry, we just paste the next addresses from the +kmemcheck stack dump, i.e.:: + + [] dequeue_signal+0x8e/0x170 + [] get_signal_to_deliver+0x98/0x390 + [] do_notify_resume+0xad/0x7d0 + [] int_signal+0x12/0x17 + + $ addr2line -e vmlinux -i ffffffff8104f04e ffffffff81050bd8 \ + ffffffff8100b87d ffffffff8100c7b5 + kernel/signal.c:446 + kernel/signal.c:1806 + arch/x86/kernel/signal.c:805 + arch/x86/kernel/signal.c:871 + arch/x86/kernel/entry_64.S:694 + +Remember that since these addresses were found on the stack and not as the +RIP value, they actually point to the _next_ instruction (they are return +addresses). This becomes obvious when we look at the code for line 446:: + + 422 int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) + 423 { + ... + 431 signr = __dequeue_signal(&tsk->signal->shared_pending, + 432 mask, info); + 433 /* + 434 * itimer signal ? + 435 * + 436 * itimers are process shared and we restart periodic + 437 * itimers in the signal delivery path to prevent DoS + 438 * attacks in the high resolution timer case. This is + 439 * compliant with the old way of self restarting + 440 * itimers, as the SIGALRM is a legacy signal and only + 441 * queued once. Changing the restart behaviour to + 442 * restart the timer in the signal dequeue path is + 443 * reducing the timer noise on heavy loaded !highres + 444 * systems too. + 445 */ + 446 if (unlikely(signr == SIGALRM)) { + ... + 489 } + +So instead of looking at 446, we should be looking at 431, which is the line +that executes just before 446. Here we see that what we are looking for is +``&tsk->signal->shared_pending``. + +Our next task is now to figure out which function that puts items on this +``shared_pending`` list. A crude, but efficient tool, is ``git grep``:: + + $ git grep -n 'shared_pending' kernel/ + ... + kernel/signal.c:828: pending = group ? &t->signal->shared_pending : &t->pending; + kernel/signal.c:1339: pending = group ? &t->signal->shared_pending : &t->pending; + ... + +There were more results, but none of them were related to list operations, +and these were the only assignments. We inspect the line numbers more closely +and find that this is indeed where items are being added to the list:: + + 816 static int send_signal(int sig, struct siginfo *info, struct task_struct *t, + 817 int group) + 818 { + ... + 828 pending = group ? &t->signal->shared_pending : &t->pending; + ... + 851 q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN && + 852 (is_si_special(info) || + 853 info->si_code >= 0))); + 854 if (q) { + 855 list_add_tail(&q->list, &pending->list); + ... + 890 } + +and:: + + 1309 int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group) + 1310 { + .... + 1339 pending = group ? &t->signal->shared_pending : &t->pending; + 1340 list_add_tail(&q->list, &pending->list); + .... + 1347 } + +In the first case, the list element we are looking for, ``q``, is being +returned from the function ``__sigqueue_alloc()``, which looks like an +allocation function. Let's take a look at it:: + + 187 static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, + 188 int override_rlimit) + 189 { + 190 struct sigqueue *q = NULL; + 191 struct user_struct *user; + 192 + 193 /* + 194 * We won't get problems with the target's UID changing under us + 195 * because changing it requires RCU be used, and if t != current, the + 196 * caller must be holding the RCU readlock (by way of a spinlock) and + 197 * we use RCU protection here + 198 */ + 199 user = get_uid(__task_cred(t)->user); + 200 atomic_inc(&user->sigpending); + 201 if (override_rlimit || + 202 atomic_read(&user->sigpending) <= + 203 t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) + 204 q = kmem_cache_alloc(sigqueue_cachep, flags); + 205 if (unlikely(q == NULL)) { + 206 atomic_dec(&user->sigpending); + 207 free_uid(user); + 208 } else { + 209 INIT_LIST_HEAD(&q->list); + 210 q->flags = 0; + 211 q->user = user; + 212 } + 213 + 214 return q; + 215 } + +We see that this function initializes ``q->list``, ``q->flags``, and +``q->user``. It seems that now is the time to look at the definition of +``struct sigqueue``, e.g.:: + + 14 struct sigqueue { + 15 struct list_head list; + 16 int flags; + 17 siginfo_t info; + 18 struct user_struct *user; + 19 }; + +And, you might remember, it was a ``memcpy()`` on ``&first->info`` that +caused the warning, so this makes perfect sense. It also seems reasonable +to assume that it is the caller of ``__sigqueue_alloc()`` that has the +responsibility of filling out (initializing) this member. + +But just which fields of the struct were uninitialized? Let's look at +kmemcheck's report again:: + + WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (ffff88003e4a2024) + 80000000000000000000000000000000000000000088ffff0000000000000000 + i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u + ^ + +These first two lines are the memory dump of the memory object itself, and +the shadow bytemap, respectively. The memory object itself is in this case +``&first->info``. Just beware that the start of this dump is NOT the start +of the object itself! The position of the caret (^) corresponds with the +address of the read (ffff88003e4a2024). + +The shadow bytemap dump legend is as follows: + +- i: initialized +- u: uninitialized +- a: unallocated (memory has been allocated by the slab layer, but has not + yet been handed off to anybody) +- f: freed (memory has been allocated by the slab layer, but has been freed + by the previous owner) + +In order to figure out where (relative to the start of the object) the +uninitialized memory was located, we have to look at the disassembly. For +that, we'll need the RIP address again:: + + RIP: 0010:[] [] __dequeue_signal+0xc8/0x190 + + $ objdump -d --no-show-raw-insn vmlinux | grep -C 8 ffffffff8104ede8: + ffffffff8104edc8: mov %r8,0x8(%r8) + ffffffff8104edcc: test %r10d,%r10d + ffffffff8104edcf: js ffffffff8104ee88 <__dequeue_signal+0x168> + ffffffff8104edd5: mov %rax,%rdx + ffffffff8104edd8: mov $0xc,%ecx + ffffffff8104eddd: mov %r13,%rdi + ffffffff8104ede0: mov $0x30,%eax + ffffffff8104ede5: mov %rdx,%rsi + ffffffff8104ede8: rep movsl %ds:(%rsi),%es:(%rdi) + ffffffff8104edea: test $0x2,%al + ffffffff8104edec: je ffffffff8104edf0 <__dequeue_signal+0xd0> + ffffffff8104edee: movsw %ds:(%rsi),%es:(%rdi) + ffffffff8104edf0: test $0x1,%al + ffffffff8104edf2: je ffffffff8104edf5 <__dequeue_signal+0xd5> + ffffffff8104edf4: movsb %ds:(%rsi),%es:(%rdi) + ffffffff8104edf5: mov %r8,%rdi + ffffffff8104edf8: callq ffffffff8104de60 <__sigqueue_free> + +As expected, it's the "``rep movsl``" instruction from the ``memcpy()`` +that causes the warning. We know about ``REP MOVSL`` that it uses the register +``RCX`` to count the number of remaining iterations. By taking a look at the +register dump again (from the kmemcheck report), we can figure out how many +bytes were left to copy:: + + RAX: 0000000000000030 RBX: ffff88003d4ea968 RCX: 0000000000000009 + +By looking at the disassembly, we also see that ``%ecx`` is being loaded +with the value ``$0xc`` just before (ffffffff8104edd8), so we are very +lucky. Keep in mind that this is the number of iterations, not bytes. And +since this is a "long" operation, we need to multiply by 4 to get the +number of bytes. So this means that the uninitialized value was encountered +at 4 * (0xc - 0x9) = 12 bytes from the start of the object. + +We can now try to figure out which field of the "``struct siginfo``" that +was not initialized. This is the beginning of the struct:: + + 40 typedef struct siginfo { + 41 int si_signo; + 42 int si_errno; + 43 int si_code; + 44 + 45 union { + .. + 92 } _sifields; + 93 } siginfo_t; + +On 64-bit, the int is 4 bytes long, so it must the union member that has +not been initialized. We can verify this using gdb:: + + $ gdb vmlinux + ... + (gdb) p &((struct siginfo *) 0)->_sifields + $1 = (union {...} *) 0x10 + +Actually, it seems that the union member is located at offset 0x10 -- which +means that gcc has inserted 4 bytes of padding between the members ``si_code`` +and ``_sifields``. We can now get a fuller picture of the memory dump:: + + _----------------------------=> si_code + / _--------------------=> (padding) + | / _------------=> _sifields(._kill._pid) + | | / _----=> _sifields(._kill._uid) + | | | / + -------|-------|-------|-------| + 80000000000000000000000000000000000000000088ffff0000000000000000 + i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u + +This allows us to realize another important fact: ``si_code`` contains the +value 0x80. Remember that x86 is little endian, so the first 4 bytes +"80000000" are really the number 0x00000080. With a bit of research, we +find that this is actually the constant ``SI_KERNEL`` defined in +``include/asm-generic/siginfo.h``:: + + 144 #define SI_KERNEL 0x80 /* sent by the kernel from somewhere */ + +This macro is used in exactly one place in the x86 kernel: In ``send_signal()`` +in ``kernel/signal.c``:: + + 816 static int send_signal(int sig, struct siginfo *info, struct task_struct *t, + 817 int group) + 818 { + ... + 828 pending = group ? &t->signal->shared_pending : &t->pending; + ... + 851 q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN && + 852 (is_si_special(info) || + 853 info->si_code >= 0))); + 854 if (q) { + 855 list_add_tail(&q->list, &pending->list); + 856 switch ((unsigned long) info) { + ... + 865 case (unsigned long) SEND_SIG_PRIV: + 866 q->info.si_signo = sig; + 867 q->info.si_errno = 0; + 868 q->info.si_code = SI_KERNEL; + 869 q->info.si_pid = 0; + 870 q->info.si_uid = 0; + 871 break; + ... + 890 } + +Not only does this match with the ``.si_code`` member, it also matches the place +we found earlier when looking for where siginfo_t objects are enqueued on the +``shared_pending`` list. + +So to sum up: It seems that it is the padding introduced by the compiler +between two struct fields that is uninitialized, and this gets reported when +we do a ``memcpy()`` on the struct. This means that we have identified a false +positive warning. + +Normally, kmemcheck will not report uninitialized accesses in ``memcpy()`` calls +when both the source and destination addresses are tracked. (Instead, we copy +the shadow bytemap as well). In this case, the destination address clearly +was not tracked. We can dig a little deeper into the stack trace from above:: + + arch/x86/kernel/signal.c:805 + arch/x86/kernel/signal.c:871 + arch/x86/kernel/entry_64.S:694 + +And we clearly see that the destination siginfo object is located on the +stack:: + + 782 static void do_signal(struct pt_regs *regs) + 783 { + 784 struct k_sigaction ka; + 785 siginfo_t info; + ... + 804 signr = get_signal_to_deliver(&info, &ka, regs, NULL); + ... + 854 } + +And this ``&info`` is what eventually gets passed to ``copy_siginfo()`` as the +destination argument. + +Now, even though we didn't find an actual error here, the example is still a +good one, because it shows how one would go about to find out what the report +was all about. + + +Annotating false positives +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +There are a few different ways to make annotations in the source code that +will keep kmemcheck from checking and reporting certain allocations. Here +they are: + +- ``__GFP_NOTRACK_FALSE_POSITIVE`` + This flag can be passed to ``kmalloc()`` or ``kmem_cache_alloc()`` + (therefore also to other functions that end up calling one of + these) to indicate that the allocation should not be tracked + because it would lead to a false positive report. This is a "big + hammer" way of silencing kmemcheck; after all, even if the false + positive pertains to particular field in a struct, for example, we + will now lose the ability to find (real) errors in other parts of + the same struct. + + Example:: + + /* No warnings will ever trigger on accessing any part of x */ + x = kmalloc(sizeof *x, GFP_KERNEL | __GFP_NOTRACK_FALSE_POSITIVE); + +- ``kmemcheck_bitfield_begin(name)``/``kmemcheck_bitfield_end(name)`` and + ``kmemcheck_annotate_bitfield(ptr, name)`` + The first two of these three macros can be used inside struct + definitions to signal, respectively, the beginning and end of a + bitfield. Additionally, this will assign the bitfield a name, which + is given as an argument to the macros. + + Having used these markers, one can later use + kmemcheck_annotate_bitfield() at the point of allocation, to indicate + which parts of the allocation is part of a bitfield. + + Example:: + + struct foo { + int x; + + kmemcheck_bitfield_begin(flags); + int flag_a:1; + int flag_b:1; + kmemcheck_bitfield_end(flags); + + int y; + }; + + struct foo *x = kmalloc(sizeof *x); + + /* No warnings will trigger on accessing the bitfield of x */ + kmemcheck_annotate_bitfield(x, flags); + + Note that ``kmemcheck_annotate_bitfield()`` can be used even before the + return value of ``kmalloc()`` is checked -- in other words, passing NULL + as the first argument is legal (and will do nothing). + + +Reporting errors +---------------- + +As we have seen, kmemcheck will produce false positive reports. Therefore, it +is not very wise to blindly post kmemcheck warnings to mailing lists and +maintainers. Instead, I encourage maintainers and developers to find errors +in their own code. If you get a warning, you can try to work around it, try +to figure out if it's a real error or not, or simply ignore it. Most +developers know their own code and will quickly and efficiently determine the +root cause of a kmemcheck report. This is therefore also the most efficient +way to work with kmemcheck. + +That said, we (the kmemcheck maintainers) will always be on the lookout for +false positives that we can annotate and silence. So whatever you find, +please drop us a note privately! Kernel configs and steps to reproduce (if +available) are of course a great help too. + +Happy hacking! + + +Technical description +--------------------- + +kmemcheck works by marking memory pages non-present. This means that whenever +somebody attempts to access the page, a page fault is generated. The page +fault handler notices that the page was in fact only hidden, and so it calls +on the kmemcheck code to make further investigations. + +When the investigations are completed, kmemcheck "shows" the page by marking +it present (as it would be under normal circumstances). This way, the +interrupted code can continue as usual. + +But after the instruction has been executed, we should hide the page again, so +that we can catch the next access too! Now kmemcheck makes use of a debugging +feature of the processor, namely single-stepping. When the processor has +finished the one instruction that generated the memory access, a debug +exception is raised. From here, we simply hide the page again and continue +execution, this time with the single-stepping feature turned off. + +kmemcheck requires some assistance from the memory allocator in order to work. +The memory allocator needs to + + 1. Tell kmemcheck about newly allocated pages and pages that are about to + be freed. This allows kmemcheck to set up and tear down the shadow memory + for the pages in question. The shadow memory stores the status of each + byte in the allocation proper, e.g. whether it is initialized or + uninitialized. + + 2. Tell kmemcheck which parts of memory should be marked uninitialized. + There are actually a few more states, such as "not yet allocated" and + "recently freed". + +If a slab cache is set up using the SLAB_NOTRACK flag, it will never return +memory that can take page faults because of kmemcheck. + +If a slab cache is NOT set up using the SLAB_NOTRACK flag, callers can still +request memory with the __GFP_NOTRACK or __GFP_NOTRACK_FALSE_POSITIVE flags. +This does not prevent the page faults from occurring, however, but marks the +object in question as being initialized so that no warnings will ever be +produced for this object. + +Currently, the SLAB and SLUB allocators are supported by kmemcheck. diff --git a/Documentation/dev-tools/tools.rst b/Documentation/dev-tools/tools.rst index 3b6382a58301..43f7deeccae4 100644 --- a/Documentation/dev-tools/tools.rst +++ b/Documentation/dev-tools/tools.rst @@ -21,3 +21,4 @@ whole; patches welcome! kasan ubsan kmemleak + kmemcheck -- cgit v1.2.3 From 5f0962748d46c63aaf5c46dcb1c8f52dfb7b717f Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Mon, 8 Aug 2016 15:55:49 -0600 Subject: docs: Sphinxify gdb-kernel-debugging.txt and move to dev-tools Acked-by: Jan Kiszka Signed-off-by: Jonathan Corbet --- Documentation/dev-tools/gdb-kernel-debugging.rst | 173 +++++++++++++++++++++++ Documentation/dev-tools/tools.rst | 1 + 2 files changed, 174 insertions(+) create mode 100644 Documentation/dev-tools/gdb-kernel-debugging.rst (limited to 'Documentation/dev-tools') diff --git a/Documentation/dev-tools/gdb-kernel-debugging.rst b/Documentation/dev-tools/gdb-kernel-debugging.rst new file mode 100644 index 000000000000..5e93c9bc6619 --- /dev/null +++ b/Documentation/dev-tools/gdb-kernel-debugging.rst @@ -0,0 +1,173 @@ +.. highlight:: none + +Debugging kernel and modules via gdb +==================================== + +The kernel debugger kgdb, hypervisors like QEMU or JTAG-based hardware +interfaces allow to debug the Linux kernel and its modules during runtime +using gdb. Gdb comes with a powerful scripting interface for python. The +kernel provides a collection of helper scripts that can simplify typical +kernel debugging steps. This is a short tutorial about how to enable and use +them. It focuses on QEMU/KVM virtual machines as target, but the examples can +be transferred to the other gdb stubs as well. + + +Requirements +------------ + +- gdb 7.2+ (recommended: 7.4+) with python support enabled (typically true + for distributions) + + +Setup +----- + +- Create a virtual Linux machine for QEMU/KVM (see www.linux-kvm.org and + www.qemu.org for more details). For cross-development, + http://landley.net/aboriginal/bin keeps a pool of machine images and + toolchains that can be helpful to start from. + +- Build the kernel with CONFIG_GDB_SCRIPTS enabled, but leave + CONFIG_DEBUG_INFO_REDUCED off. If your architecture supports + CONFIG_FRAME_POINTER, keep it enabled. + +- Install that kernel on the guest. + Alternatively, QEMU allows to boot the kernel directly using -kernel, + -append, -initrd command line switches. This is generally only useful if + you do not depend on modules. See QEMU documentation for more details on + this mode. + +- Enable the gdb stub of QEMU/KVM, either + + - at VM startup time by appending "-s" to the QEMU command line + + or + + - during runtime by issuing "gdbserver" from the QEMU monitor + console + +- cd /path/to/linux-build + +- Start gdb: gdb vmlinux + + Note: Some distros may restrict auto-loading of gdb scripts to known safe + directories. In case gdb reports to refuse loading vmlinux-gdb.py, add:: + + add-auto-load-safe-path /path/to/linux-build + + to ~/.gdbinit. See gdb help for more details. + +- Attach to the booted guest:: + + (gdb) target remote :1234 + + +Examples of using the Linux-provided gdb helpers +------------------------------------------------ + +- Load module (and main kernel) symbols:: + + (gdb) lx-symbols + loading vmlinux + scanning for modules in /home/user/linux/build + loading @0xffffffffa0020000: /home/user/linux/build/net/netfilter/xt_tcpudp.ko + loading @0xffffffffa0016000: /home/user/linux/build/net/netfilter/xt_pkttype.ko + loading @0xffffffffa0002000: /home/user/linux/build/net/netfilter/xt_limit.ko + loading @0xffffffffa00ca000: /home/user/linux/build/net/packet/af_packet.ko + loading @0xffffffffa003c000: /home/user/linux/build/fs/fuse/fuse.ko + ... + loading @0xffffffffa0000000: /home/user/linux/build/drivers/ata/ata_generic.ko + +- Set a breakpoint on some not yet loaded module function, e.g.:: + + (gdb) b btrfs_init_sysfs + Function "btrfs_init_sysfs" not defined. + Make breakpoint pending on future shared library load? (y or [n]) y + Breakpoint 1 (btrfs_init_sysfs) pending. + +- Continue the target:: + + (gdb) c + +- Load the module on the target and watch the symbols being loaded as well as + the breakpoint hit:: + + loading @0xffffffffa0034000: /home/user/linux/build/lib/libcrc32c.ko + loading @0xffffffffa0050000: /home/user/linux/build/lib/lzo/lzo_compress.ko + loading @0xffffffffa006e000: /home/user/linux/build/lib/zlib_deflate/zlib_deflate.ko + loading @0xffffffffa01b1000: /home/user/linux/build/fs/btrfs/btrfs.ko + + Breakpoint 1, btrfs_init_sysfs () at /home/user/linux/fs/btrfs/sysfs.c:36 + 36 btrfs_kset = kset_create_and_add("btrfs", NULL, fs_kobj); + +- Dump the log buffer of the target kernel:: + + (gdb) lx-dmesg + [ 0.000000] Initializing cgroup subsys cpuset + [ 0.000000] Initializing cgroup subsys cpu + [ 0.000000] Linux version 3.8.0-rc4-dbg+ (... + [ 0.000000] Command line: root=/dev/sda2 resume=/dev/sda1 vga=0x314 + [ 0.000000] e820: BIOS-provided physical RAM map: + [ 0.000000] BIOS-e820: [mem 0x0000000000000000-0x000000000009fbff] usable + [ 0.000000] BIOS-e820: [mem 0x000000000009fc00-0x000000000009ffff] reserved + .... + +- Examine fields of the current task struct:: + + (gdb) p $lx_current().pid + $1 = 4998 + (gdb) p $lx_current().comm + $2 = "modprobe\000\000\000\000\000\000\000" + +- Make use of the per-cpu function for the current or a specified CPU:: + + (gdb) p $lx_per_cpu("runqueues").nr_running + $3 = 1 + (gdb) p $lx_per_cpu("runqueues", 2).nr_running + $4 = 0 + +- Dig into hrtimers using the container_of helper:: + + (gdb) set $next = $lx_per_cpu("hrtimer_bases").clock_base[0].active.next + (gdb) p *$container_of($next, "struct hrtimer", "node") + $5 = { + node = { + node = { + __rb_parent_color = 18446612133355256072, + rb_right = 0x0 , + rb_left = 0x0 + }, + expires = { + tv64 = 1835268000000 + } + }, + _softexpires = { + tv64 = 1835268000000 + }, + function = 0xffffffff81078232 , + base = 0xffff88003fd0d6f0, + state = 1, + start_pid = 0, + start_site = 0xffffffff81055c1f , + start_comm = "swapper/2\000\000\000\000\000\000" + } + + +List of commands and functions +------------------------------ + +The number of commands and convenience functions may evolve over the time, +this is just a snapshot of the initial version:: + + (gdb) apropos lx + function lx_current -- Return current task + function lx_module -- Find module by name and return the module variable + function lx_per_cpu -- Return per-cpu variable + function lx_task_by_pid -- Find Linux task by PID and return the task_struct variable + function lx_thread_info -- Calculate Linux thread_info from task variable + lx-dmesg -- Print Linux kernel log buffer + lx-lsmod -- List currently loaded modules + lx-symbols -- (Re-)load symbols of Linux kernel and currently loaded modules + +Detailed help can be obtained via "help " for commands and "help +function " for convenience functions. diff --git a/Documentation/dev-tools/tools.rst b/Documentation/dev-tools/tools.rst index 43f7deeccae4..824ae8e54dd5 100644 --- a/Documentation/dev-tools/tools.rst +++ b/Documentation/dev-tools/tools.rst @@ -22,3 +22,4 @@ whole; patches welcome! ubsan kmemleak kmemcheck + gdb-kernel-debugging -- cgit v1.2.3