Skip to content

K
Kernel

openeuler / Kernel
接近 2 年 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 13 8月, 2020 11 次提交
  3. 10 8月, 2020 2 次提交
    • M
      kbuild: trace functions in subdirectories of lib/ · b16838c6
      由 Masahiro Yamada 提交于 
      ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)

exists here in sub-directories of lib/ to keep the behavior of
commit 2464a609 ("ftrace: do not trace library functions").

Since that commit, not only the objects in lib/ but also the ones in
the sub-directories are excluded from ftrace (although the commit
description did not explicitly mention this).

However, most of library functions in sub-directories are not so hot.
Re-add them to ftrace.

Going forward, only the objects right under lib/ will be excluded.

Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: NMasahiro Yamada <masahiroy@kernel.org>
Acked-by: NSteven Rostedt (VMware) <rostedt@goodmis.org>
      b16838c6
    • M
      kbuild: introduce ccflags-remove-y and asflags-remove-y · 15d5761a
      由 Masahiro Yamada 提交于 
      CFLAGS_REMOVE_<file>.o filters out flags when compiling a particular
object, but there is no convenient way to do that for every object in
a directory.

Add ccflags-remove-y and asflags-remove-y to make it easily.

Use ccflags-remove-y to clean up some Makefiles.

The add/remove order works as follows:

 [1] KBUILD_CFLAGS specifies compiler flags used globally

 [2] ccflags-y adds compiler flags for all objects in the
     current Makefile

 [3] ccflags-remove-y removes compiler flags for all objects in the
     current Makefile (New feature)

 [4] CFLAGS_<file> adds compiler flags per file.

 [5] CFLAGS_REMOVE_<file> removes compiler flags per file.

Having [3] before [4] allows us to remove flags from most (but not all)
objects in the current Makefile.

For example, kernel/trace/Makefile removes $(CC_FLAGS_FTRACE)
from all objects in the directory, then adds it back to
trace_selftest_dynamic.o and CFLAGS_trace_kprobe_selftest.o

The same applies to lib/livepatch/Makefile.

Please note ccflags-remove-y has no effect to the sub-directories.
In contrast, the previous notation got rid of compiler flags also from
all the sub-directories.

The following are not affected because they have no sub-directories:

  arch/arm/boot/compressed/
  arch/powerpc/xmon/
  arch/sh/
  kernel/trace/

However, lib/ has several sub-directories.

To keep the behavior, I added ccflags-remove-y to all Makefiles
in subdirectories of lib/, except the following:

  lib/vdso/Makefile        - Kbuild does not descend into this Makefile
  lib/raid/test/Makefile   - This is not used for the kernel build

I think commit 2464a609 ("ftrace: do not trace library functions")
excluded too much. In the next commit, I will remove ccflags-remove-y
from the sub-directories of lib/.
Suggested-by: NSami Tolvanen <samitolvanen@google.com>
Signed-off-by: NMasahiro Yamada <masahiroy@kernel.org>
Acked-by: NSteven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Acked-by: Brendan Higgins <brendanhiggins@google.com> (KUnit)
Tested-by: NAnders Roxell <anders.roxell@linaro.org>
      15d5761a
  5. 08 8月, 2020 8 次提交
  7. 04 8月, 2020 1 次提交
  9. 01 8月, 2020 3 次提交
  11. 31 7月, 2020 3 次提交
  13. 30 7月, 2020 2 次提交
    • L
      random32: remove net_rand_state from the latent entropy gcc plugin · 83bdc727
      由 Linus Torvalds 提交于 
      It turns out that the plugin right now ends up being really unhappy
about the change from 'static' to 'extern' storage that happened in
commit f227e3ec ("random32: update the net random state on interrupt
and activity").

This is probably a trivial fix for the latent_entropy plugin, but for
now, just remove net_rand_state from the list of things the plugin
worries about.
Reported-by: NStephen Rothwell <sfr@canb.auug.org.au>
Cc: Emese Revfy <re.emese@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Willy Tarreau <w@1wt.eu>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      83bdc727
    • W
      random32: update the net random state on interrupt and activity · f227e3ec
      由 Willy Tarreau 提交于 
      This modifies the first 32 bits out of the 128 bits of a random CPU's
net_rand_state on interrupt or CPU activity to complicate remote
observations that could lead to guessing the network RNG's internal
state.

Note that depending on some network devices' interrupt rate moderation
or binding, this re-seeding might happen on every packet or even almost
never.

In addition, with NOHZ some CPUs might not even get timer interrupts,
leaving their local state rarely updated, while they are running
networked processes making use of the random state.  For this reason, we
also perform this update in update_process_times() in order to at least
update the state when there is user or system activity, since it's the
only case we care about.
Reported-by: NAmit Klein <aksecurity@gmail.com>
Suggested-by: NLinus Torvalds <torvalds@linux-foundation.org>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: NWilly Tarreau <w@1wt.eu>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      f227e3ec
  15. 29 7月, 2020 5 次提交
  17. 27 7月, 2020 2 次提交
  19. 25 7月, 2020 1 次提交
  21. 24 7月, 2020 2 次提交
    • J
      dyndbg: export ddebug_exec_queries · 4c0d7782
      由 Jim Cromie 提交于 
      Export ddebug_exec_queries() for use by modules.

This will allow module authors to control all their *pr_debug*s
dynamically.  And since ddebug_exec_queries() is what implements
"echo $query >control", it gives the same per-callsite control.

Virtues of this:
- simplicity. just an export.
- full control over any/all subsets of callsites.
- same "query/command-string" in code and console
- full callsite selectivity with module file line format

Format in particular deserves special attention; it is where
low-hanging fruit will be found.

Consider: drivers/gpu/drm/amd/display/include/logger_types.h:

  #define DC_LOG_SURFACE(...)          pr_debug("[SURFACE]:"__VA_ARGS__)
  #define DC_LOG_HW_LINK_TRAINING(...) pr_debug("[HW_LINK_TRAINING]:"__VA_ARGS__)
  .. 9 more ..

Thats 11 string prefixes, used in 804 places in drivers/gpu/**
Clearly this is a systematized classification of those callsites.
And one I'd expect to see repeated often.

Using ddebug_exec_queries(), authors can select on those prefixes
as a unitary set, equivalent to:

    echo "module=MODULE_NAME format=^[SURFACE]: +p" >control

Trivially, those sets can be subsected with the other query terms too,
say file=foo, should the author see fit.

Perhaps as important, users can modify the set of enabled callsites,
presumably to aid debugging by enabling helpful debug callsites, and
disabling those that just clutter the info.

Authors could even alter [fmlt] flags, though I dont see a good reason
why they would.  Perhaps harnessed by bug-logging automation to get
fuller, or more minimal bug-reports.

DRM

drm has both drm.debug, which defines 32 categories of drm_printk
logging, and entirely separate uses of pr_debug, which are dynamic on
this i915 laptop, running mainline.  So I can observe and report on
both.

The i915 driver has 118 dyndbg callsites, with following
"classifications" defined in drivers/gpu/drm/i915/gvt/**

$ grep 915 /proc/dynamic_debug/control | cut -d= -f2 | cut -d: -f1,2 | sort -u
_ "gvt: cmd
_ "gvt: core
_ "gvt: dpy
_ "gvt: el
_ "gvt: irq
_ "gvt: mm
_ "gvt: mmio
_ "gvt: render
_ "gvt: sched
_ "%s for root hub!\012"
_ "Vendor defined info completion code %u\012"

This classification is entirely out-of-band for control by drm.debug,
and is only available to root user at the console.  But module authors
can activate them with ddebug_exec_queries(sprintf("format=^%s +p")),
and then decide how to expose the groups to the user for max utility.

drm.debug

drm.debug has 32 bit-flags, and matching enum drm_debug_category
values to classify the ~2943 DRM_DEBUG*() callsites in drivers/gpu

The drm.debug callback could invoke ddebug_exec_queries() with 32
different hardcoded query strings, needing only (bit) ? " +p" : " -p"
added.

I briefly enabled drm.debug=0xff on my i915 laptop, which yielded
these unique prefixes: (dmesg | cut -c17- | cut -d\] -f1 | sort -u)

[drm:drm_atomic_check_only [drm
[drm:drm_atomic_get_crtc_state [drm
[drm:drm_atomic_get_plane_state [drm
[drm:drm_atomic_nonblocking_commit [drm
[drm:drm_atomic_set_fb_for_plane [drm
[drm:drm_atomic_state_default_clear [drm
[drm:__drm_atomic_state_free [drm
[drm:drm_atomic_state_init [drm
[drm:drm_crtc_vblank_helper_get_vblank_timestamp_internal [drm
[drm:drm_handle_vblank [drm
[drm:drm_ioctl [drm
[drm:drm_mode_addfb2 [drm
[drm:drm_mode_object_get [drm
[drm:drm_mode_object_put.part.0 [drm
[drm:drm_update_vblank_count [drm
[drm:drm_vblank_enable [drm
[drm:drm_vblank_restore [drm
[drm:vblank_disable_fn [drm
i915 0000:00:02.0: [drm:gen9_set_dc_state [i915
i915 0000:00:02.0: [drm:intel_atomic_get_global_obj_state [i915
i915 0000:00:02.0: [drm:__intel_display_power_get_domain.part.0 [i915
i915 0000:00:02.0: [drm:__intel_display_power_put_domain [i915
i915 0000:00:02.0: [drm:intel_plane_atomic_calc_changes [i915
i915 0000:00:02.0: [drm:skl_enable_dc6 [i915

Several good format=^prefixes are apparent there, and some misses.

 ^[drm:drm_atomic_	# misses: [drm:__drm_atomic_state_free [drm
 ^[drm:drm_ioctl
 ^[drm:drm_mode
 ^[drm:drm_vblank_	# misses: [drm:drm_update_vblank_count & [drm:vblank_disable_fn

Its not a perfect 1:1 single format-match per class, but the misses
above can be covered with 1 & 2 additional queries, which can be
concatenated together with ";" separators and submitted with 1 call.

Benefits:

For drm, adapting DRM_DEBUG to use dynamic-debug inside could
replicate (and thereby obsolete) lots of bit-checking in current
DRM_DEBUG callsites, at least with JUMP_LABEL optimized code.
ddebug_exec_queries() and a handful of fixed query-strings can select
and thereby control the already classified callsites.

With the classes mapped to queries, the enum type and parameter can be
eliminated (folded away with macro magic), at least for DYNAMIC_DEBUG
& JUMP_LABEL builds.

Is it safe ?

ddebug_exec_queries() is currently exposed to user space in
several limited ways;

1 it is called from module-load callback, where it implements the
  $modname.dyndbg=+p "fake" parameter provided to all modules.

2 it handles query input via >control directly

IOW, it is "fully" exposed to local root user; exposing the same
functionality to other kernel modules is no additional risk.

The other standard issue to check is locking:

dyndbg has a single mutex, taken by ddebug_change to handle >control,
and by ddebug_proc_(start|stop) to span `cat control`.  Queries
submitted via export will typically have module specified, which
dramatically cuts the scan by ddebug_change vs "module=* +p".
ISTM this proposed export presents no locking problems.

TLDR;

It would be interesting to see how drm.dyndbg=$QUERY and
drm.debug=$HEXY would interact; it might be order dependent, as
if given as modprobe args or in /etc/modprobe.d/

Acked-by: <jbaron@akamai.com>
Signed-off-by: NJim Cromie <jim.cromie@gmail.com>
Link: https://lore.kernel.org/r/20200719231058.1586423-19-jim.cromie@gmail.comSigned-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      4c0d7782
    • J
      dyndbg: shorten our logging prefix, drop __func__ · 5aa9ffbb
      由 Jim Cromie 提交于 
      For log-message output, reduce column space consumed by current
pr_fmt by dropping __func__ and shortening "dynamic_debug" to
"dyndbg".  This improves readability on narrow consoles, and better
matches other kernel boot info messages.

Acked-by: <jbaron@akamai.com>
Signed-off-by: NJim Cromie <jim.cromie@gmail.com>
Link: https://lore.kernel.org/r/20200719231058.1586423-18-jim.cromie@gmail.comSigned-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
      5aa9ffbb