[lttng-dev] [PATCH lttng-modules 1/3] Fix: signal: Distinguish between kernel_siginfo and siginfo (v4.20)

[Michael Jeanson]

See upstream commit :

commit ae7795bc6187a15ec51cf258abae656a625f9980
Author: Eric W. Biederman <***@xmission.com>
Date: Tue Sep 25 11:27:20 2018 +0200

signal: Distinguish between kernel_siginfo and siginfo

Linus recently observed that if we did not worry about the padding
member in struct siginfo it is only about 48 bytes, and 48 bytes is
much nicer than 128 bytes for allocating on the stack and copying
around in the kernel.

The obvious thing of only adding the padding when userspace is
including siginfo.h won't work as there are sigframe definitions in
the kernel that embed struct siginfo.

So split siginfo in two; kernel_siginfo and siginfo. Keeping the
traditional name for the userspace definition. While the version that
is used internally to the kernel and ultimately will not be padded to
128 bytes is called kernel_siginfo.

The definition of struct kernel_siginfo I have put in include/signal_types.h

A set of buildtime checks has been added to verify the two structures have
the same field offsets.

To make it easy to verify the change kernel_siginfo retains the same
size as siginfo. The reduction in size comes in a following change.

Signed-off-by: Michael Jeanson <***@efficios.com>
---
instrumentation/events/lttng-module/signal.h | 41 ++++++++++++++++++--
1 file changed, 37 insertions(+), 4 deletions(-)

diff --git a/instrumentation/events/lttng-module/signal.h b/instrumentation/events/lttng-module/signal.h
index 68045ce..6c484ba 100644
--- a/instrumentation/events/lttng-module/signal.h
+++ b/instrumentation/events/lttng-module/signal.h
@@ -36,21 +36,24 @@
* SEND_SIG_NOINFO means that si_code is SI_USER, and SEND_SIG_PRIV
* means that si_code is SI_KERNEL.
*/
-#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,4,0))
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4,20,0))
LTTNG_TRACEPOINT_EVENT(signal_generate,

- TP_PROTO(int sig, struct siginfo *info, struct task_struct *task),
+ TP_PROTO(int sig, struct kernel_siginfo *info, struct task_struct *task,
+ int group, int result),

- TP_ARGS(sig, info, task),
+ TP_ARGS(sig, info, task, group, result),

TP_FIELDS(
ctf_integer(int, sig, sig)
LTTNG_FIELDS_SIGINFO(info)
ctf_array_text(char, comm, task->comm, TASK_COMM_LEN)
ctf_integer(pid_t, pid, task->pid)
+ ctf_integer(int, group, group)
+ ctf_integer(int, result, result)
)
)
-#else
+#elif (LINUX_VERSION_CODE >= KERNEL_VERSION(3,4,0))
LTTNG_TRACEPOINT_EVENT(signal_generate,

TP_PROTO(int sig, struct siginfo *info, struct task_struct *task,
@@ -67,6 +70,20 @@ LTTNG_TRACEPOINT_EVENT(signal_generate,
ctf_integer(int, result, result)
)
)
+#else
+LTTNG_TRACEPOINT_EVENT(signal_generate,
+
+ TP_PROTO(int sig, struct siginfo *info, struct task_struct *task),
+
+ TP_ARGS(sig, info, task),
+
+ TP_FIELDS(
+ ctf_integer(int, sig, sig)
+ LTTNG_FIELDS_SIGINFO(info)
+ ctf_array_text(char, comm, task->comm, TASK_COMM_LEN)
+ ctf_integer(pid_t, pid, task->pid)
+ )
+)
#endif

/**
@@ -83,6 +100,21 @@ LTTNG_TRACEPOINT_EVENT(signal_generate,
* This means, this can show which signals are actually delivered, but
* matching generated signals and delivered signals may not be correct.
*/
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4,20,0))
+LTTNG_TRACEPOINT_EVENT(signal_deliver,
+
+ TP_PROTO(int sig, struct kernel_siginfo *info, struct k_sigaction *ka),
+
+ TP_ARGS(sig, info, ka),
+
+ TP_FIELDS(
+ ctf_integer(int, sig, sig)
+ LTTNG_FIELDS_SIGINFO(info)
+ ctf_integer(unsigned long, sa_handler, (unsigned long) ka->sa.sa_handler)
+ ctf_integer(unsigned long, sa_flags, ka->sa.sa_flags)
+ )
+)
+#else
LTTNG_TRACEPOINT_EVENT(signal_deliver,

TP_PROTO(int sig, struct siginfo *info, struct k_sigaction *ka),
@@ -96,6 +128,7 @@ LTTNG_TRACEPOINT_EVENT(signal_deliver,
ctf_integer(unsigned long, sa_flags, ka->sa.sa_flags)
)
)
+#endif

#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,4,0))
LTTNG_TRACEPOINT_EVENT_CLASS(signal_queue_overflow,

[Michael Jeanson]

See upstream commit :

commit 4ff4c31a6e85f4c49fbeebeaa28018d002884b5a
Author: Eric W. Biederman <***@xmission.com>
Date: Mon Sep 3 10:39:04 2018 +0200

signal: Remove SEND_SIG_FORCED

There are no more users of SEND_SIG_FORCED so it may be safely removed.

Remove the definition of SEND_SIG_FORCED, it's use in is_si_special,
it's use in TP_STORE_SIGINFO, and it's use in __send_signal as without
any users the uses of SEND_SIG_FORCED are now unncessary.

This makes the code simpler, easier to understand and use. Users of
signal sending functions now no longer need to ask themselves do I
need to use SEND_SIG_FORCED.

Signed-off-by: Michael Jeanson <***@efficios.com>
---
instrumentation/events/lttng-module/signal.h | 12 ++++++++++++
1 file changed, 12 insertions(+)

diff --git a/instrumentation/events/lttng-module/signal.h b/instrumentation/events/lttng-module/signal.h
index 6c484ba..7e9631d 100644
--- a/instrumentation/events/lttng-module/signal.h
+++ b/instrumentation/events/lttng-module/signal.h
@@ -13,6 +13,17 @@
#include <linux/signal.h>
#include <linux/sched.h>
#undef LTTNG_FIELDS_SIGINFO
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4,20,0))
+#define LTTNG_FIELDS_SIGINFO(info) \
+ ctf_integer(int, errno, \
+ (info == SEND_SIG_NOINFO || info == SEND_SIG_PRIV) ? \
+ 0 : \
+ info->si_errno) \
+ ctf_integer(int, code, \
+ (info == SEND_SIG_NOINFO) ? \
+ SI_USER : \
+ ((info == SEND_SIG_PRIV) ? SI_KERNEL : info->si_code))
+#else /* LINUX_VERSION_CODE >= KERNEL_VERSION(4,20,0) */
#define LTTNG_FIELDS_SIGINFO(info) \
ctf_integer(int, errno, \
(info == SEND_SIG_NOINFO || info == SEND_SIG_FORCED || info == SEND_SIG_PRIV) ? \
@@ -22,6 +33,7 @@
(info == SEND_SIG_NOINFO || info == SEND_SIG_FORCED) ? \
SI_USER : \
((info == SEND_SIG_PRIV) ? SI_KERNEL : info->si_code))
+#endif /* LINUX_VERSION_CODE >= KERNEL_VERSION(4,20,0) */
#endif /* _TRACE_SIGNAL_DEF */

/**

[Michael Jeanson]

See upstream commit :

commit 9fe671496b6c286f9033aedfc1718d67721da0ae
Author: Eric Whitney <***@gmail.com>
Date: Mon Oct 1 14:25:08 2018 -0400

ext4: adjust reserved cluster count when removing extents

Modify ext4_ext_remove_space() and the code it calls to correct the
reserved cluster count for pending reservations (delayed allocated
clusters shared with allocated blocks) when a block range is removed
from the extent tree. Pending reservations may be found for the clusters
at the ends of written or unwritten extents when a block range is removed.
If a physical cluster at the end of an extent is freed, it's necessary
to increment the reserved cluster count to maintain correct accounting
if the corresponding logical cluster is shared with at least one
delayed and unwritten extent as found in the extents status tree.

Add a new function, ext4_rereserve_cluster(), to reapply a reservation
on a delayed allocated cluster sharing blocks with a freed allocated
cluster. To avoid ENOSPC on reservation, a flag is applied to
ext4_free_blocks() to briefly defer updating the freeclusters counter
when an allocated cluster is freed. This prevents another thread
from allocating the freed block before the reservation can be reapplied.

Redefine the partial cluster object as a struct to carry more state
information and to clarify the code using it.

Adjust the conditional code structure in ext4_ext_remove_space to
reduce the indentation level in the main body of the code to improve
readability.

Signed-off-by: Michael Jeanson <***@efficios.com>
---
instrumentation/events/lttng-module/ext4.h | 72 +++++++++++++++++++++-
1 file changed, 69 insertions(+), 3 deletions(-)

diff --git a/instrumentation/events/lttng-module/ext4.h b/instrumentation/events/lttng-module/ext4.h
index 740f288..307021a 100644
--- a/instrumentation/events/lttng-module/ext4.h
+++ b/instrumentation/events/lttng-module/ext4.h
@@ -1603,7 +1603,30 @@ LTTNG_TRACEPOINT_EVENT(ext4_ext_show_extent,
)
)

-#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,11,0))
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4,20,0))
+
+LTTNG_TRACEPOINT_EVENT(ext4_remove_blocks,
+ TP_PROTO(struct inode *inode, struct ext4_extent *ex,
+ ext4_lblk_t from, ext4_fsblk_t to,
+ struct partial_cluster *pc),
+
+ TP_ARGS(inode, ex, from, to, pc),
+
+ TP_FIELDS(
+ ctf_integer(dev_t, dev, inode->i_sb->s_dev)
+ ctf_integer(ino_t, ino, inode->i_ino)
+ ctf_integer(ext4_lblk_t, from, from)
+ ctf_integer(ext4_lblk_t, to, to)
+ ctf_integer(ext4_fsblk_t, ee_pblk, ext4_ext_pblock(ex))
+ ctf_integer(ext4_lblk_t, ee_lblk, le32_to_cpu(ex->ee_block))
+ ctf_integer(unsigned short, ee_len, ext4_ext_get_actual_len(ex))
+ ctf_integer(ext4_fsblk_t, pc_pclu, pc->pclu)
+ ctf_integer(ext4_lblk_t, pc_lblk, pc->lblk)
+ ctf_integer(int, pc_state, pc->state)
+ )
+)
+
+#elif (LINUX_VERSION_CODE >= KERNEL_VERSION(3,11,0))

LTTNG_TRACEPOINT_EVENT(ext4_remove_blocks,
TP_PROTO(struct inode *inode, struct ext4_extent *ex,
@@ -1647,7 +1670,29 @@ LTTNG_TRACEPOINT_EVENT(ext4_remove_blocks,

#endif

-#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,11,0))
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4,20,0))
+
+LTTNG_TRACEPOINT_EVENT(ext4_ext_rm_leaf,
+ TP_PROTO(struct inode *inode, ext4_lblk_t start,
+ struct ext4_extent *ex,
+ struct partial_cluster *pc),
+
+ TP_ARGS(inode, start, ex, pc),
+
+ TP_FIELDS(
+ ctf_integer(dev_t, dev, inode->i_sb->s_dev)
+ ctf_integer(ino_t, ino, inode->i_ino)
+ ctf_integer(ext4_lblk_t, start, start)
+ ctf_integer(ext4_lblk_t, ee_lblk, le32_to_cpu(ex->ee_block))
+ ctf_integer(ext4_fsblk_t, ee_pblk, ext4_ext_pblock(ex))
+ ctf_integer(short, ee_len, ext4_ext_get_actual_len(ex))
+ ctf_integer(ext4_fsblk_t, pc_pclu, pc->pclu)
+ ctf_integer(ext4_lblk_t, pc_lblk, pc->lblk)
+ ctf_integer(int, pc_state, pc->state)
+ )
+)
+
+#elif (LINUX_VERSION_CODE >= KERNEL_VERSION(3,11,0))

LTTNG_TRACEPOINT_EVENT(ext4_ext_rm_leaf,
TP_PROTO(struct inode *inode, ext4_lblk_t start,
@@ -1734,7 +1779,28 @@ LTTNG_TRACEPOINT_EVENT(ext4_ext_remove_space,

#endif

-#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,11,0))
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4,20,0))
+
+LTTNG_TRACEPOINT_EVENT(ext4_ext_remove_space_done,
+ TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end,
+ int depth, struct partial_cluster *pc, __le16 eh_entries),
+
+ TP_ARGS(inode, start, end, depth, pc, eh_entries),
+
+ TP_FIELDS(
+ ctf_integer(dev_t, dev, inode->i_sb->s_dev)
+ ctf_integer(ino_t, ino, inode->i_ino)
+ ctf_integer(ext4_lblk_t, start, start)
+ ctf_integer(ext4_lblk_t, end, end)
+ ctf_integer(int, depth, depth)
+ ctf_integer(unsigned short, eh_entries, le16_to_cpu(eh_entries))
+ ctf_integer(ext4_fsblk_t, pc_pclu, pc->pclu)
+ ctf_integer(ext4_lblk_t, pc_lblk, pc->lblk)
+ ctf_integer(int, pc_state, pc->state)
+ )
+)
+
+#elif (LINUX_VERSION_CODE >= KERNEL_VERSION(3,11,0))

LTTNG_TRACEPOINT_EVENT(ext4_ext_remove_space_done,
TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end,