From cd85fc58cd71bf6b89612efafb9a84e655ed7d66 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 8 Dec 2010 17:42:22 +0100 Subject: taskstats: Use this_cpu_ops Use this_cpu_inc_return in one place and avoid ugly __raw_get_cpu in another. V3->V4: - Fix off by one. V4-V4f: - Use &listener_array Cc: Michael Holzheu Acked-by: H. Peter Anvin Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- kernel/taskstats.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel/taskstats.c') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index c8231fb1570..5f82ccd1039 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -89,8 +89,7 @@ static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, return -ENOMEM; if (!info) { - int seq = get_cpu_var(taskstats_seqnum)++; - put_cpu_var(taskstats_seqnum); + int seq = this_cpu_inc_return(taskstats_seqnum) - 1; reply = genlmsg_put(skb, 0, seq, &family, 0, cmd); } else @@ -581,7 +580,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead) fill_tgid_exit(tsk); } - listeners = &__raw_get_cpu_var(listener_array); + listeners = __this_cpu_ptr(&listener_array); if (list_empty(&listeners->list)) return; -- cgit v1.2.3-70-g09d2 From 4be2c95d1f7706ca0e74499f2bd118e1cee19669 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Tue, 21 Dec 2010 17:24:30 -0800 Subject: taskstats: pad taskstats netlink response for aligment issues on ia64 The taskstats structure is internally aligned on 8 byte boundaries but the layout of the aggregrate reply, with two NLA headers and the pid (each 4 bytes), actually force the entire structure to be unaligned. This causes the kernel to issue unaligned access warnings on some architectures like ia64. Unfortunately, some software out there doesn't properly unroll the NLA packet and assumes that the start of the taskstats structure will always be 20 bytes from the start of the netlink payload. Aligning the start of the taskstats structure breaks this software, which we don't want. So, for now the alignment only happens on architectures that require it and those users will have to update to fixed versions of those packages. Space is reserved in the packet only when needed. This ifdef should be removed in several years e.g. 2012 once we can be confident that fixed versions are installed on most systems. We add the padding before the aggregate since the aggregate is already a defined type. Commit 85893120 ("delayacct: align to 8 byte boundary on 64-bit systems") previously addressed the alignment issues by padding out the pid field. This was supposed to be a compatible change but the circumstances described above mean that it wasn't. This patch backs out that change, since it was a hack, and introduces a new NULL attribute type to provide the padding. Padding the response with 4 bytes avoids allocating an aligned taskstats structure and copying it back. Since the structure weighs in at 328 bytes, it's too big to do it on the stack. Signed-off-by: Jeff Mahoney Reported-by: Brian Rogers Cc: Jeff Mahoney Cc: Guillaume Chazarain Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/accounting/getdelays.c | 1 + include/linux/taskstats.h | 3 +- kernel/taskstats.c | 57 ++++++++++++++++++++++++++++-------- 3 files changed, 47 insertions(+), 14 deletions(-) (limited to 'kernel/taskstats.c') diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c index a2976a6de03..e9c77788a39 100644 --- a/Documentation/accounting/getdelays.c +++ b/Documentation/accounting/getdelays.c @@ -516,6 +516,7 @@ int main(int argc, char *argv[]) default: fprintf(stderr, "Unknown nla_type %d\n", na->nla_type); + case TASKSTATS_TYPE_NULL: break; } na = (struct nlattr *) (GENLMSG_DATA(&msg) + len); diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index 341dddb5509..2466e550a41 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -33,7 +33,7 @@ */ -#define TASKSTATS_VERSION 7 +#define TASKSTATS_VERSION 8 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -188,6 +188,7 @@ enum { TASKSTATS_TYPE_STATS, /* taskstats structure */ TASKSTATS_TYPE_AGGR_PID, /* contains pid + stats */ TASKSTATS_TYPE_AGGR_TGID, /* contains tgid + stats */ + TASKSTATS_TYPE_NULL, /* contains nothing */ __TASKSTATS_TYPE_MAX, }; diff --git a/kernel/taskstats.c b/kernel/taskstats.c index c8231fb1570..3308fd7f1b5 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -349,25 +349,47 @@ static int parse(struct nlattr *na, struct cpumask *mask) return ret; } +#ifdef CONFIG_IA64 +#define TASKSTATS_NEEDS_PADDING 1 +#endif + static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) { struct nlattr *na, *ret; int aggr; - /* If we don't pad, we end up with alignment on a 4 byte boundary. - * This causes lots of runtime warnings on systems requiring 8 byte - * alignment */ - u32 pids[2] = { pid, 0 }; - int pid_size = ALIGN(sizeof(pid), sizeof(long)); - aggr = (type == TASKSTATS_TYPE_PID) ? TASKSTATS_TYPE_AGGR_PID : TASKSTATS_TYPE_AGGR_TGID; + /* + * The taskstats structure is internally aligned on 8 byte + * boundaries but the layout of the aggregrate reply, with + * two NLA headers and the pid (each 4 bytes), actually + * force the entire structure to be unaligned. This causes + * the kernel to issue unaligned access warnings on some + * architectures like ia64. Unfortunately, some software out there + * doesn't properly unroll the NLA packet and assumes that the start + * of the taskstats structure will always be 20 bytes from the start + * of the netlink payload. Aligning the start of the taskstats + * structure breaks this software, which we don't want. So, for now + * the alignment only happens on architectures that require it + * and those users will have to update to fixed versions of those + * packages. Space is reserved in the packet only when needed. + * This ifdef should be removed in several years e.g. 2012 once + * we can be confident that fixed versions are installed on most + * systems. We add the padding before the aggregate since the + * aggregate is already a defined type. + */ +#ifdef TASKSTATS_NEEDS_PADDING + if (nla_put(skb, TASKSTATS_TYPE_NULL, 0, NULL) < 0) + goto err; +#endif na = nla_nest_start(skb, aggr); if (!na) goto err; - if (nla_put(skb, type, pid_size, pids) < 0) + + if (nla_put(skb, type, sizeof(pid), &pid) < 0) goto err; ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats)); if (!ret) @@ -456,6 +478,18 @@ out: return rc; } +static size_t taskstats_packet_size(void) +{ + size_t size; + + size = nla_total_size(sizeof(u32)) + + nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); +#ifdef TASKSTATS_NEEDS_PADDING + size += nla_total_size(0); /* Padding for alignment */ +#endif + return size; +} + static int cmd_attr_pid(struct genl_info *info) { struct taskstats *stats; @@ -464,8 +498,7 @@ static int cmd_attr_pid(struct genl_info *info) u32 pid; int rc; - size = nla_total_size(sizeof(u32)) + - nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); + size = taskstats_packet_size(); rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) @@ -494,8 +527,7 @@ static int cmd_attr_tgid(struct genl_info *info) u32 tgid; int rc; - size = nla_total_size(sizeof(u32)) + - nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); + size = taskstats_packet_size(); rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) @@ -570,8 +602,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead) /* * Size includes space for nested attributes */ - size = nla_total_size(sizeof(u32)) + - nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); + size = taskstats_packet_size(); is_thread_group = !!taskstats_tgid_alloc(tsk); if (is_thread_group) { -- cgit v1.2.3-70-g09d2 From 9ab020cf07e457a8b425bf5af17e704f90f86d8b Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Wed, 12 Jan 2011 17:00:48 -0800 Subject: taskstats: use better ifdef for alignment Commit 4be2c95d ("taskstats: pad taskstats netlink response for aligment issues on ia64") added a null field to align the taskstats structure but the discussion centered around ia64. The issue exists on other platforms with inefficient unaligned access and adding them piecemeal would be an unmaintainable mess. This patch uses Dave Miller's suggestion of using a combination of CONFIG_64BIT && !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS to determine whether alignment is needed. Note that this will cause breakage on those platforms with applications like iotop which had hard-coded offsets into the packet to access the taskstats structure. The message seen on systems without the alignment fixes looks like: kernel unaligned access to 0xe000023879dca9bc, ip=0xa000000100133d10 The addresses may vary but resolve to locations inside __delayacct_add_tsk. iotop makes what I'd call unreasonable assumptions about the contents of a netlink genetlink packet containing generic attributes. They're typed and have headers that specify value lengths, so the client can (should) identify and skip the ones the client doesn't understand. The kernel, as of version 2.6.36, presented a packet like so: +--------------------------------+ | genlmsghdr - 4 bytes | +--------------------------------+ | NLA header - 4 bytes | /* Aggregate header */ +-+------------------------------+ | | NLA header - 4 bytes | /* PID header */ | +------------------------------+ | | pid/tgid - 4 bytes | | +------------------------------+ | | NLA header - 4 bytes | /* stats header */ | + -----------------------------+ <- oops. aligned on 4 byte boundary | | struct taskstats - 328 bytes | +-+------------------------------+ The iotop code expects that the kernel will behave as it did then, assuming that the packet format is set in stone. The format is set in stone, but the packet offsets are not. There's nothing in the packet format that guarantees that the packet will be sent in exactly the same way. The attribute contents are set (or versioned) and the aggregate contents are set but they can be anywhere in the packet. The issue here isn't that an unaligned structure gets passed to userspace, it's that the NLA infrastructure has something of a weakness: The 4 byte attribute header may force the payload to be unaligned. The taskstats structure is created at an unaligned location and then 64-bit values are operated on inside the kernel, so the unaligned access warnings gets spewed everywhere. It's possible to use the unaligned access API to operate on the structure in the kernel but it seems like a wasted effort to work around userspace code that isn't following the packet format. Any new additions would also need the be worked around. It's a maintenance nightmare. The conclusion of the earlier discussion seemed to be "ok fine, if we have to break it, don't break it on arches that don't have the problem." Dave pointed out that the unaligned access problem doesn't only exist on ia64, but also on other 64-bit arches that don't have efficient unaligned access and it should be fixed there as well. The committed version of the patch and this addition keep with the conclusion of that discussion not to break it unnecessarily, which the pid padding and the packet padding fixes did do. x86_64 and powerpc don't suffer this problem so they shouldn't suffer the solution. Other 64-bit architectures do and will, though. Signed-off-by: Jeff Mahoney Reported-by: David S. Miller Acked-by: David S. Miller Cc: Dan Carpenter Cc: Balbir Singh Cc: Florian Mickler Cc: Guillaume Chazarain Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/taskstats.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/taskstats.c') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 69691eb4b71..3971c6b9d58 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -348,7 +348,7 @@ static int parse(struct nlattr *na, struct cpumask *mask) return ret; } -#ifdef CONFIG_IA64 +#if defined(CONFIG_64BIT) && !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) #define TASKSTATS_NEEDS_PADDING 1 #endif -- cgit v1.2.3-70-g09d2