- 07 Jan, 2016 2 commits
-
-
Qiu Peiyang authored
We hit ftrace_bug report when booting Android on a 64bit ATOM SOC chip. Basically, there is a race between insmod and ftrace_run_update_code. After load_module=>ftrace_module_init, another thread jumps in to call ftrace_run_update_code=>ftrace_arch_code_modify_prepare =>set_all_modules_text_rw, to change all modules as RW. Since the new module is at MODULE_STATE_UNFORMED, the text attribute is not changed. Then, the 2nd thread goes ahead to change codes. However, load_module continues to call complete_formation=>set_section_ro_nx, then 2nd thread would fail when probing the module's TEXT. The patch fixes it by using notifier to delay the enabling of ftrace records to the time when module is at state MODULE_STATE_COMING. Link: http://lkml.kernel.org/r/567CE628.3000609@intel.comSigned-off-by:Qiu Peiyang <peiyangx.qiu@intel.com> Signed-off-by:
Zhang Yanmin <yanmin.zhang@intel.com> Signed-off-by:
Steven Rostedt <rostedt@goodmis.org>
-
Steven Rostedt (Red Hat) authored
Qiu Peiyang pointed out that there's a race when enabling function tracing and loading a module. In order to make the modifications of converting nops in the prologue of functions into callbacks, the text needs to be converted from read-only to read-write. When enabling function tracing, the text permission is updated, the functions are modified, and then they are put back. When loading a module, the updates to convert function calls to mcount is done before the module text is set to read-only. But after it is done, the module text is visible by the function tracer. Thus we have the following race: CPU 0 CPU 1 ----- ----- start function tracing set text to read-write load_module add functions to ftrace set module text read-only update all functions to callbacks modify module functions too < Can't it's read-only > When this happens, ftrace detects the issue and disables itself till the next reboot. To fix this, a new DISABLED flag is added for ftrace records, which all module functions get when they are added. Then later, after the module code is all set, the records will have the DISABLED flag cleared, and they will be enabled if any callback wants all functions to be traced. Note, this doesn't add the delay to later. It simply changes the ftrace_module_init() to do both the setting of DISABLED records, and then immediately calls the enable code. This helps with testing this new code as it has the same behavior as previously. Another change will come after this to have the ftrace_module_enable() called after the text is set to read-only. Cc: Qiu Peiyang <peiyangx.qiu@intel.com> Signed-off-by:
-
- 04 Jan, 2016 1 commit
-
-
Li Bin authored
There is no need to worry about module and __init text disappearing case, because that ftrace has a module notifier that is called when a module is being unloaded and before the text goes away and this code grabs the ftrace_lock mutex and removes the module functions from the ftrace list, such that it will no longer do any modifications to that module's text, the update to make functions be traced or not is done under the ftrace_lock mutex as well. And by now, __init section codes should not been modified by ftrace, because it is black listed in recordmcount.c and ignored by ftrace. Link: http://lkml.kernel.org/r/1449367378-29430-6-git-send-email-huawei.libin@huawei.comReviewed-by:
Thomas Gleixner <tglx@linutronix.de> Suggested-by:
Li Bin <huawei.libin@huawei.com> Signed-off-by:
-
- 23 Dec, 2015 13 commits
-
-
Chuyu Hu authored
The file tracing_enable is obsolete and does not exist anymore. Replace the comment that references it with the proper tracing_on file. Link: http://lkml.kernel.org/r/1450787141-45544-1-git-send-email-chuhu@redhat.comSigned-off-by:
Chuyu Hu <chuhu@redhat.com> Signed-off-by:
-
Li Bin authored
There is no need to worry about module and __init text disappearing case, because that ftrace has a module notifier that is called when a module is being unloaded and before the text goes away and this code grabs the ftrace_lock mutex and removes the module functions from the ftrace list, such that it will no longer do any modifications to that module's text, the update to make functions be traced or not is done under the ftrace_lock mutex as well. And by now, __init section codes should not been modified by ftrace, because it is black listed in recordmcount.c and ignored by ftrace. Link: http://lkml.kernel.org/r/1449367378-29430-3-git-send-email-huawei.libin@huawei.com Cc: linux-metag@vger.kernel.org Acked-by:
James Hogan <james.hogan@imgtec.com> Suggested-by:
-
Li Bin authored
There is no need to worry about module and __init text disappearing case, because that ftrace has a module notifier that is called when a module is being unloaded and before the text goes away and this code grabs the ftrace_lock mutex and removes the module functions from the ftrace list, such that it will no longer do any modifications to that module's text, the update to make functions be traced or not is done under the ftrace_lock mutex as well. And by now, __init section codes should not been modified by ftrace, because it is black listed in recordmcount.c and ignored by ftrace. Link: http://lkml.kernel.org/r/1449367378-29430-5-git-send-email-huawei.libin@huawei.com Cc: linux-sh@vger.kernel.org Suggested-by:
-
Li Bin authored
There is no need to worry about module and __init text disappearing case, because that ftrace has a module notifier that is called when a module is being unloaded and before the text goes away and this code grabs the ftrace_lock mutex and removes the module functions from the ftrace list, such that it will no longer do any modifications to that module's text, the update to make functions be traced or not is done under the ftrace_lock mutex as well. And by now, __init section codes should not been modified by ftrace, because it is black listed in recordmcount.c and ignored by ftrace. Link: http://lkml.kernel.org/r/1449214067-12177-2-git-send-email-huawei.libin@huawei.com Cc: linux-ia64@vger.kernel.org Acked-by:
Tony Luck <tony.luck@intel.com> Suggested-by:
-
Steven Rostedt (Red Hat) authored
The start and end variables were only used when ftrace_module_init() was split up into multiple functions. No need to keep them around after the merger. Signed-off-by: -
Abel Vesa authored
Simple cleanup. No need for two functions here. The whole work can simply be done inside 'ftrace_module_init'. Link: http://lkml.kernel.org/r/1449067197-5718-1-git-send-email-abelvesa@linux.comSigned-off-by:
Abel Vesa <abelvesa@linux.com> Signed-off-by:
-
Denis Kirjanov authored
TRACE_EVENT_FN can't be used in some circumstances like invoking trace functions from offlined CPU due to RCU usage. This patch adds the TRACE_EVENT_FN_COND macro to make such trace points conditional. Link: http://lkml.kernel.org/r/1450124286-4822-1-git-send-email-kda@linux-powerpc.orgSigned-off-by:
Denis Kirjanov <kda@linux-powerpc.org> Signed-off-by:
-
Jerry Snitselaar authored
commit 5ac48378 ("tracing: Use trace_seq_used() and seq_buf_used() instead of len") changed the tracing code to use trace_seq_used() and seq_buf_used() instead of using the seq_buf len directly to avoid overflow issues, but missed a spot in seq_buf_to_user() that makes use of s->len. Cleaned up the code a bit as well per suggestion of Steve Rostedt. Link: http://lkml.kernel.org/r/1447703848-2951-1-git-send-email-jsnitsel@redhat.comSigned-off-by:
Jerry Snitselaar <jsnitsel@redhat.com> Signed-off-by:
-
Julia Lawall authored
This bpf_verifier_ops structure is never modified, like the other bpf_verifier_ops structures, so declare it as const. Done with the help of Coccinelle. Link: http://lkml.kernel.org/r/1449855359-13724-1-git-send-email-Julia.Lawall@lip6.frSigned-off-by:
Julia Lawall <Julia.Lawall@lip6.fr> Signed-off-by:
-
Steven Rostedt (Red Hat) authored
Jiri Olsa noted that the change to replace the control_ops did not update the trampoline for when running perf on a single CPU and with CONFIG_PREEMPT disabled (where dynamic ops, like perf, can use trampolines directly). The result was that perf function could be called when RCU is not watching as well as not handle the ftrace_local_disable(). Modify the ftrace_ops_get_func() to also check the RCU and PER_CPU ops flags and use the recursive function if they are set. The recursive function is modified to check those flags and execute the appropriate checks if they are set. Link: http://lkml.kernel.org/r/20151201134213.GA14155@krava.brq.redhat.comReported-by:
Jiri Olsa <jolsa@redhat.com> Patch-fixed-up-by:
Jiri Olsa <jolsa@kernel.org> Signed-off-by:
-
Steven Rostedt (Red Hat) authored
Currently perf has its own list function within the ftrace infrastructure that seems to be used only to allow for it to have per-cpu disabling as well as a check to make sure that it's not called while RCU is not watching. It uses something called the "control_ops" which is used to iterate over ops under it with the control_list_func(). The problem is that this control_ops and control_list_func unnecessarily complicates the code. By replacing FTRACE_OPS_FL_CONTROL with two new flags (FTRACE_OPS_FL_RCU and FTRACE_OPS_FL_PER_CPU) we can remove all the code that is special with the control ops and add the needed checks within the generic ftrace_list_func(). Signed-off-by: -
Steven Rostedt (Red Hat) authored
When showing all tramps registered to a ftrace record in the file enabled_functions, it exits the loop with ops == NULL. But then it is suppose to show the function on the ops->trampoline and add_trampoline_func() is called with the given ops. But because ops is now NULL (to exit the loop), it always shows the static trampoline instead of the one that is really registered to the record. The call to add_trampoline_func() that shows the trampoline for the given ops needs to be called at every iteration. Fixes: 39daa7b9 "ftrace: Show all tramps registered to a record on ftrace_bug()" Signed-off-by:
-
Li Bin authored
s/ARCH_SUPPORT_FTARCE_OPS/ARCH_SUPPORTS_FTRACE_OPS/ Link: http://lkml.kernel.org/r/1448879016-8659-1-git-send-email-huawei.libin@huawei.comSigned-off-by:
-
- 25 Nov, 2015 5 commits
-
-
Steven Rostedt (Red Hat) authored
When an anomaly is detected in the function call modification code, ftrace_bug() is called to disable function tracing as well as give any information that may help debug the problem. Currently, only the first found trampoline that is attached to the failed record is reported. Instead, show all trampolines that are hooked to it. Also, not only show the ops pointer but also report the function it calls. While at it, add this info to the enabled_functions debug file too. Signed-off-by: -
Steven Rostedt (Red Hat) authored
When an anomaly is found while modifying function code, ftrace_bug() is called which disables the function tracing infrastructure and reports information about what failed. If the code that is to be replaced does not match what is expected, then actual code is shown. Currently there is no arch generic way to show what was expected. Add a new variable pointer calld ftrace_expected that the arch code can set to point to what it expected so that ftrace_bug() can report the actual text as well as the text that was expected to be there. Signed-off-by: -
Steven Rostedt (Red Hat) authored
The ftrace function hook utility has several internal checks to make sure that whatever it modifies is exactly what it expects to be modifying. This is essential as modifying running code can be extremely dangerous to the system. When an anomaly is detected, ftrace_bug() is called which sends a splat to the console and disables function tracing. There's some extra information that is printed to help diagnose the issue. One thing that is missing though is output of what ftrace was doing at the time of the crash. Was it updating a call site or perhaps converting a call site to a nop? A new global enum variable is created to state what ftrace was doing at the time of the anomaly, and this is reported in ftrace_bug(). Signed-off-by: -
Tom Zanussi authored
When a trigger is enabled, the cond flag should be set beforehand, otherwise a trigger that's expecting to process a trace record (e.g. one with post_trigger set) could be invoked without one. Likewise a trigger's cond flag should be reset after it's disabled, not before. Link: http://lkml.kernel.org/r/a420b52a67b1c2d3cab017914362d153255acb99.1448303214.git.tom.zanussi@linux.intel.comSigned-off-by:
Tom Zanussi <tom.zanussi@linux.intel.com> Signed-off-by:
Daniel Wagner <daniel.wagner@bmw-carit.de> Reviewed-by:
Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Reviewed-by:
Namhyung Kim <namhyung@kernel.org> Tested-by:
-
Steven Rostedt (Red Hat) authored
When crossing over to a new page, commit the current work. This will allow readers to get data with less latency, and also simplifies the work to get timestamps working for interrupted events. Signed-off-by:
-
- 24 Nov, 2015 5 commits
-
-
Steven Rostedt (Red Hat) authored
The first commit of a buffer page updates the timestamp of that page. No need to have the update to the next page add the timestamp too. It will only be replaced by the first commit on that page anyway. Only update to a page if it contains an event. Signed-off-by: -
Steven Rostedt (Red Hat) authored
As cpu_buffer->tail_page may be modified by interrupts at almost any time, the flow of logic is very important. Do not let gcc get smart with re-reading cpu_buffer->tail_page by adding READ_ONCE() around most of its accesses. Signed-off-by: -
Steven Rostedt (Red Hat) authored
Create a test to test instance creation and deletion. Several tasks are created that create 3 directories and delete them. The tasks all create the same directories. This places a stress on the code that creates and deletes instances. Signed-off-by: -
Steven Rostedt (Red Hat) authored
Commit fcc742ea "ring-buffer: Add event descriptor to simplify passing data" added a descriptor that holds various data instead of passing around several variables through parameters. The problem was that one of the parameters was modified in a function and the code was designed not to have an effect on that modified parameter. Now that the parameter is a descriptor and any modifications to it are non-volatile, the size of the data could be unnecessarily expanded. Remove the extra space added if a timestamp was added and the event went across the page. Cc: stable@vger.kernel.org # 4.3+ Fixes: fcc742ea "ring-buffer: Add event descriptor to simplify passing data" Signed-off-by:
-
Steven Rostedt (Red Hat) authored
Do not update the read stamp after swapping out the reader page from the write buffer. If the reader page is swapped out of the buffer before an event is written to it, then the read_stamp may get an out of date timestamp, as the page timestamp is updated on the first commit to that page. rb_get_reader_page() only returns a page if it has an event on it, otherwise it will return NULL. At that point, check if the page being returned has events and has not been read yet. Then at that point update the read_stamp to match the time stamp of the reader page. Cc: stable@vger.kernel.org # 2.6.30+ Signed-off-by:
-
- 23 Nov, 2015 1 commit
-
-
Linus Torvalds authored
-
- 22 Nov, 2015 13 commits
-
-
Linus Torvalds authored
Merge slub bulk allocator updates from Andrew Morton: "This missed the merge window because I was waiting for some repairs to come in. Nothing actually uses the bulk allocator yet and the changes to other code paths are pretty small. And the net guys are waiting for this so they can start merging the client code" More comments from Jesper Dangaard Brouer: "The kmem_cache_alloc_bulk() call, in mm/slub.c, were included in previous kernel. The present version contains a bug. Vladimir Davydov noticed it contained a bug, when kernel is compiled with CONFIG_MEMCG_KMEM (see commit 03ec0ed5: "slub: fix kmem cgroup bug in kmem_cache_alloc_bulk"). Plus the mem cgroup counterpart in kmem_cache_free_bulk() were missing (see commit 03374518 "slub: add missing kmem cgroup support to kmem_cache_free_bulk"). I don't consider the fix stable-material because there are no in-tree users of the API. But with known bugs (for memcg) I cannot start using the API in the net-tree" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: slab/slub: adjust kmem_cache_alloc_bulk API slub: add missing kmem cgroup support to kmem_cache_free_bulk slub: fix kmem cgroup bug in kmem_cache_alloc_bulk slub: optimize bulk slowpath free by detached freelist slub: support for bulk free with SLUB freelists
-
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/ttyLinus Torvalds authored
Pull tty/serial fixes from Greg KH: "Here are a few small tty/serial driver fixes for 4.4-rc2 that resolve some reported problems. All have been in linux-next, full details are in the shortlog below" * tag 'tty-4.4-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty: serial: export fsl8250_handle_irq serial: 8250_mid: Add missing dependency tty: audit: Fix audit source serial: etraxfs-uart: Fix crash serial: fsl_lpuart: Fix earlycon support bcm63xx_uart: Use the device name when registering an interrupt tty: Fix direct use of tty buffer work tty: Fix tty_send_xchar() lock order inversion
-
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/stagingLinus Torvalds authored
Pull staging/IIO fixes from Greg KH: "Here are some staging and iio driver fixes for 4.4-rc2. All of these are in response to issues that have been reported and have been in linux-next for a while" * tag 'staging-4.4-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging: Revert "Staging: wilc1000: coreconfigurator: Drop unneeded wrapper functions" iio: adc: xilinx: Fix VREFN scale iio: si7020: Swap data byte order iio: adc: vf610_adc: Fix division by zero error iio:ad7793: Fix ad7785 product ID iio: ad5064: Fix ad5629/ad5669 shift iio:ad5064: Make sure ad5064_i2c_write() returns 0 on success iio: lpc32xx_adc: fix warnings caused by enabling unprepared clock staging: iio: select IRQ_WORK for IIO_DUMMY_EVGEN vf610_adc: Fix internal temperature calculation
-
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usbLinus Torvalds authored
Pull USB fixes from Greg KH: "Here are a number of USB fixes and new device ids for 4.4-rc2. All have been in linux-next and the details are in the shortlog" * tag 'usb-4.4-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb: (28 commits) usblp: do not set TASK_INTERRUPTIBLE before lock USB: MAINTAINERS: cxacru usb: kconfig: fix warning of select USB_OTG USB: option: add XS Stick W100-2 from 4G Systems xhci: Fix a race in usb2 LPM resume, blocking U3 for usb2 devices usb: xhci: fix checking ep busy for CFC xhci: Workaround to get Intel xHCI reset working more reliably usb: chipidea: imx: fix a possible NULL dereference usb: chipidea: usbmisc_imx: fix a possible NULL dereference usb: chipidea: otg: gadget module load and unload support usb: chipidea: debug: disable usb irq while role switch ARM: dts: imx27.dtsi: change the clock information for usb usb: chipidea: imx: refine clock operations to adapt for all platforms usb: gadget: atmel_usba_udc: Expose correct device speed usb: musb: enable usb_dma parameter usb: phy: phy-mxs-usb: fix a possible NULL dereference usb: dwc3: gadget: let us set lower max_speed usb: musb: fix tx fifo flush handling usb: gadget: f_loopback: fix the warning during the enumeration usb: dwc2: host: Fix remote wakeup when not in DWC2_L2 ...
-
git://git.linux-mips.org/pub/scm/ralf/upstream-linusLinus Torvalds authored
Pull MIPS fixes from Ralf Baechle: - Fix a flood of annoying build warnings - A number of fixes for Atheros 79xx platforms * 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: MIPS: ath79: Add a machine entry for booting OF machines MIPS: ath79: Fix the size of the MISC INTC registers in ar9132.dtsi MIPS: ath79: Fix the DDR control initialization on ar71xx and ar934x MIPS: Fix flood of warnings about comparsion being always true.
-
git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linuxLinus Torvalds authored
Pull parisc update from Helge Deller: "This patchset adds Huge Page and HUGETLBFS support for parisc" Honestly, the hugepage support should have gone through in the merge window, and is not really an rc-time fix. But it only touches arch/parisc, and I cannot find it in myself to care. If one of the three parisc users notices a breakage, I will point at Helge and make rude farting noises. * 'parisc-4.4-2' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux: parisc: Map kernel text and data on huge pages parisc: Add Huge Page and HUGETLBFS support parisc: Use long branch to do_syscall_trace_exit parisc: Increase initial kernel mapping to 32MB on 64bit kernel parisc: Initialize the fault vector earlier in the boot process. parisc: Add defines for Huge page support parisc: Drop unused MADV_xxxK_PAGES flags from asm/mman.h parisc: Drop definition of start_thread_som for HP-UX SOM binaries parisc: Fix wrong comment regarding first pmd entry flags
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull perf tool fixes from Thomas Gleixner: "A couple of fixes for perf tools: - Build system updates - Plug a memory leak in an error path of perf probe - Tear down probes correctly when adding fails - Fixes to the perf symbol handling - Fix ordering of event processing in buildid-list - Fix per DSO filtering in the histogram browser" * 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: perf probe: Clear probe_trace_event when add_probe_trace_event() fails perf probe: Fix memory leaking on failure by clearing all probe_trace_events perf inject: Also re-pipe lost_samples event perf buildid-list: Requires ordered events perf symbols: Fix dso lookup by long name and missing buildids perf symbols: Allow forcing reading of non-root owned files by root perf hists browser: The dso can be obtained from popup_action->ms.map->dso perf hists browser: Fix 'd' hotkey action to filter by DSO perf symbols: Rebuild rbtree when adjusting symbols for kcore tools: Add a "make all" rule tools: Actually install tmon in the install rule
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 fixes from Thomas Gleixner: "This update contains: - MPX updates for handling 32bit processes - A fix for a long standing bug in 32bit signal frame handling related to FPU/XSAVE state - Handle get_xsave_addr() correctly in KVM - Fix SMAP check under paravirtualization - Add a comment to the static function trace entry to avoid further confusion about the difference to dynamic tracing" * 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/cpu: Fix SMAP check in PVOPS environments x86/ftrace: Add comment on static function tracing x86/fpu: Fix get_xsave_addr() behavior under virtualization x86/fpu: Fix 32-bit signal frame handling x86/mpx: Fix 32-bit address space calculation x86/mpx: Do proper get_user() when running 32-bit binaries on 64-bit kernels -
Jesper Dangaard Brouer authored
Adjust kmem_cache_alloc_bulk API before we have any real users. Adjust API to return type 'int' instead of previously type 'bool'. This is done to allow future extension of the bulk alloc API. A future extension could be to allow SLUB to stop at a page boundary, when specified by a flag, and then return the number of objects. The advantage of this approach, would make it easier to make bulk alloc run without local IRQs disabled. With an approach of cmpxchg "stealing" the entire c->freelist or page->freelist. To avoid overshooting we would stop processing at a slab-page boundary. Else we always end up returning some objects at the cost of another cmpxchg. To keep compatible with future users of this API linking against an older kernel when using the new flag, we need to return the number of allocated objects with this API change. Signed-off-by:
Jesper Dangaard Brouer <brouer@redhat.com> Cc: Vladimir Davydov <vdavydov@virtuozzo.com> Acked-by:
Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Jesper Dangaard Brouer authored
Initial implementation missed support for kmem cgroup support in kmem_cache_free_bulk() call, add this. If CONFIG_MEMCG_KMEM is not enabled, the compiler should be smart enough to not add any asm code. Incoming bulk free objects can belong to different kmem cgroups, and object free call can happen at a later point outside memcg context. Thus, we need to keep the orig kmem_cache, to correctly verify if a memcg object match against its "root_cache" (s->memcg_params.root_cache). Signed-off-by:
Vladimir Davydov <vdavydov@virtuozzo.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by:
-
Jesper Dangaard Brouer authored
The call slab_pre_alloc_hook() interacts with kmemgc and is not allowed to be called several times inside the bulk alloc for loop, due to the call to memcg_kmem_get_cache(). This would result in hitting the VM_BUG_ON in __memcg_kmem_get_cache. As suggested by Vladimir Davydov, change slab_post_alloc_hook() to be able to handle an array of objects. A subtle detail is, loop iterator "i" in slab_post_alloc_hook() must have same type (size_t) as size argument. This helps the compiler to easier realize that it can remove the loop, when all debug statements inside loop evaluates to nothing. Note, this is only an issue because the kernel is compiled with GCC option: -fno-strict-overflow In slab_alloc_node() the compiler inlines and optimizes the invocation of slab_post_alloc_hook(s, flags, 1, &object) by removing the loop and access object directly. Signed-off-by:
-
Jesper Dangaard Brouer authored
This change focus on improving the speed of object freeing in the "slowpath" of kmem_cache_free_bulk. The calls slab_free (fastpath) and __slab_free (slowpath) have been extended with support for bulk free, which amortize the overhead of the (locked) cmpxchg_double. To use the new bulking feature, we build what I call a detached freelist. The detached freelist takes advantage of three properties: 1) the free function call owns the object that is about to be freed, thus writing into this memory is synchronization-free. 2) many freelist's can co-exist side-by-side in the same slab-page each with a separate head pointer. 3) it is the visibility of the head pointer that needs synchronization. Given these properties, the brilliant part is that the detached freelist can be constructed without any need for synchronization. The freelist is constructed directly in the page objects, without any synchronization needed. The detached freelist is allocated on the stack of the function call kmem_cache_free_bulk. Thus, the freelist head pointer is not visible to other CPUs. All objects in a SLUB freelist must belong to the same slab-page. Thus, constructing the detached freelist is about matching objects that belong to the same slab-page. The bulk free array is scanned is a progressive manor with a limited look-ahead facility. Kmem debug support is handled in call of slab_free(). Notice kmem_cache_free_bulk no longer need to disable IRQs. This only slowed down single free bulk with approx 3 cycles. Performance data: Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns To get stable and comparable numbers, the kernel have been booted with "slab_merge" (this also improve performance for larger bulk sizes). Performance data, compared against fallback bulking: bulk - fallback bulk - improvement with this patch 1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0% 2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5% 3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6% 4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5% 8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0% 16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3% 30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3% 32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0% 34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0% 48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7% 64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0% 128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0% 158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7% 250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4% Performance data, compared current in-kernel bulking: bulk - curr in-kernel - improvement with this patch 1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5% 2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1% 3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5% 4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1% 8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9% 16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6% 30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0% 32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0% 34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5% 48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0% 64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2% 128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9% 158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0% 250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0% Performance with normal SLUB merging is significantly slower for larger bulking. This is believed to (primarily) be an effect of not having to share the per-CPU data-structures, as tuning per-CPU size can achieve similar performance. bulk - slab_nomerge - normal SLUB merge 1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0 2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0 3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0 4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0 8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0 16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0 30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5 32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4 34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1 48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1 64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28 128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30 158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29 250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19 Joint work with Alexander Duyck. [1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c [akpm@linux-foundation.org: BUG_ON -> WARN_ON;return] Signed-off-by:Alexander Duyck <alexander.h.duyck@redhat.com> Acked-by:
-
Jesper Dangaard Brouer authored
Make it possible to free a freelist with several objects by adjusting API of slab_free() and __slab_free() to have head, tail and an objects counter (cnt). Tail being NULL indicate single object free of head object. This allow compiler inline constant propagation in slab_free() and slab_free_freelist_hook() to avoid adding any overhead in case of single object free. This allows a freelist with several objects (all within the same slab-page) to be free'ed using a single locked cmpxchg_double in __slab_free() and with an unlocked cmpxchg_double in slab_free(). Object debugging on the free path is also extended to handle these freelists. When CONFIG_SLUB_DEBUG is enabled it will also detect if objects don't belong to the same slab-page. These changes are needed for the next patch to bulk free the detached freelists it introduces and constructs. Micro benchmarking showed no performance reduction due to this change, when debugging is turned off (compiled with CONFIG_SLUB_DEBUG). Signed-off-by:
-
