Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 364 insertions, 0 deletions

diff --git a/net/ethtool/fec.c b/net/ethtool/fec.c
new file mode 100644
index 000000000..e2d539271
--- /dev/null
+++ b/net/ethtool/fec.c
@@ -0,0 +1,364 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "bitset.h"
+#include "common.h"
+#include "netlink.h"
+
+struct fec_req_info {
+	struct ethnl_req_info		base;
+};
+
+struct fec_reply_data {
+	struct ethnl_reply_data		base;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(fec_link_modes);
+	u32 active_fec;
+	u8 fec_auto;
+	struct fec_stat_grp {
+		u64 stats[1 + ETHTOOL_MAX_LANES];
+		u8 cnt;
+	} corr, uncorr, corr_bits;
+	struct ethtool_fec_hist fec_stat_hist;
+};
+
+#define FEC_REPDATA(__reply_base) \
+	container_of(__reply_base, struct fec_reply_data, base)
+
+#define ETHTOOL_FEC_MASK	((ETHTOOL_FEC_LLRS << 1) - 1)
+
+const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1] = {
+	[ETHTOOL_A_FEC_HEADER]	= NLA_POLICY_NESTED(ethnl_header_policy_stats),
+};
+
+static void
+ethtool_fec_to_link_modes(u32 fec, unsigned long *link_modes, u8 *fec_auto)
+{
+	if (fec_auto)
+		*fec_auto = !!(fec & ETHTOOL_FEC_AUTO);
+
+	if (fec & ETHTOOL_FEC_OFF)
+		__set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, link_modes);
+	if (fec & ETHTOOL_FEC_RS)
+		__set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, link_modes);
+	if (fec & ETHTOOL_FEC_BASER)
+		__set_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, link_modes);
+	if (fec & ETHTOOL_FEC_LLRS)
+		__set_bit(ETHTOOL_LINK_MODE_FEC_LLRS_BIT, link_modes);
+}
+
+static int
+ethtool_link_modes_to_fecparam(struct ethtool_fecparam *fec,
+			       unsigned long *link_modes, u8 fec_auto)
+{
+	memset(fec, 0, sizeof(*fec));
+
+	if (fec_auto)
+		fec->fec |= ETHTOOL_FEC_AUTO;
+
+	if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, link_modes))
+		fec->fec |= ETHTOOL_FEC_OFF;
+	if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, link_modes))
+		fec->fec |= ETHTOOL_FEC_RS;
+	if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, link_modes))
+		fec->fec |= ETHTOOL_FEC_BASER;
+	if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_LLRS_BIT, link_modes))
+		fec->fec |= ETHTOOL_FEC_LLRS;
+
+	if (!bitmap_empty(link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void
+fec_stats_recalc(struct fec_stat_grp *grp, struct ethtool_fec_stat *stats)
+{
+	int i;
+
+	if (stats->lanes[0] == ETHTOOL_STAT_NOT_SET) {
+		grp->stats[0] = stats->total;
+		grp->cnt = stats->total != ETHTOOL_STAT_NOT_SET;
+		return;
+	}
+
+	grp->cnt = 1;
+	grp->stats[0] = 0;
+	for (i = 0; i < ETHTOOL_MAX_LANES; i++) {
+		if (stats->lanes[i] == ETHTOOL_STAT_NOT_SET)
+			break;
+
+		grp->stats[0] += stats->lanes[i];
+		grp->stats[grp->cnt++] = stats->lanes[i];
+	}
+}
+
+static int fec_prepare_data(const struct ethnl_req_info *req_base,
+			    struct ethnl_reply_data *reply_base,
+			    const struct genl_info *info)
+{
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(active_fec_modes) = {};
+	struct fec_reply_data *data = FEC_REPDATA(reply_base);
+	struct net_device *dev = reply_base->dev;
+	struct ethtool_fecparam fec = {};
+	int ret;
+
+	if (!dev->ethtool_ops->get_fecparam)
+		return -EOPNOTSUPP;
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		return ret;
+	ret = dev->ethtool_ops->get_fecparam(dev, &fec);
+	if (ret)
+		goto out_complete;
+	if (req_base->flags & ETHTOOL_FLAG_STATS &&
+	    dev->ethtool_ops->get_fec_stats) {
+		struct ethtool_fec_stats stats;
+
+		ethtool_stats_init((u64 *)&stats, sizeof(stats) / 8);
+		ethtool_stats_init((u64 *)data->fec_stat_hist.values,
+				   sizeof(data->fec_stat_hist.values) / 8);
+		dev->ethtool_ops->get_fec_stats(dev, &stats,
+						&data->fec_stat_hist);
+
+		fec_stats_recalc(&data->corr, &stats.corrected_blocks);
+		fec_stats_recalc(&data->uncorr, &stats.uncorrectable_blocks);
+		fec_stats_recalc(&data->corr_bits, &stats.corrected_bits);
+	}
+
+	WARN_ON_ONCE(fec.reserved);
+
+	ethtool_fec_to_link_modes(fec.fec, data->fec_link_modes,
+				  &data->fec_auto);
+
+	ethtool_fec_to_link_modes(fec.active_fec, active_fec_modes, NULL);
+	data->active_fec = find_first_bit(active_fec_modes,
+					  __ETHTOOL_LINK_MODE_MASK_NBITS);
+	/* Don't report attr if no FEC mode set. Note that
+	 * ethtool_fecparam_to_link_modes() ignores NONE and AUTO.
+	 */
+	if (data->active_fec == __ETHTOOL_LINK_MODE_MASK_NBITS)
+		data->active_fec = 0;
+
+out_complete:
+	ethnl_ops_complete(dev);
+	return ret;
+}
+
+static int fec_reply_size(const struct ethnl_req_info *req_base,
+			  const struct ethnl_reply_data *reply_base)
+{
+	bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS;
+	const struct fec_reply_data *data = FEC_REPDATA(reply_base);
+	int len = 0;
+	int ret;
+
+	ret = ethnl_bitset_size(data->fec_link_modes, NULL,
+				__ETHTOOL_LINK_MODE_MASK_NBITS,
+				link_mode_names, compact);
+	if (ret < 0)
+		return ret;
+	len += ret;
+
+	len += nla_total_size(sizeof(u8)) +	/* _FEC_AUTO */
+	       nla_total_size(sizeof(u32));	/* _FEC_ACTIVE */
+
+	if (req_base->flags & ETHTOOL_FLAG_STATS) {
+		len += 3 * nla_total_size_64bit(sizeof(u64) *
+						(1 + ETHTOOL_MAX_LANES));
+		/* add FEC bins information */
+		len += (nla_total_size(0) +  /* _A_FEC_HIST */
+			nla_total_size(4) +  /* _A_FEC_HIST_BIN_LOW */
+			nla_total_size(4) +  /* _A_FEC_HIST_BIN_HI */
+			/* _A_FEC_HIST_BIN_VAL + per-lane values */
+			nla_total_size_64bit(sizeof(u64)) +
+			nla_total_size_64bit(sizeof(u64) * ETHTOOL_MAX_LANES)) *
+			ETHTOOL_FEC_HIST_MAX;
+	}
+
+	return len;
+}
+
+static int fec_put_hist(struct sk_buff *skb,
+			const struct ethtool_fec_hist *hist)
+{
+	const struct ethtool_fec_hist_range *ranges = hist->ranges;
+	const struct ethtool_fec_hist_value *values = hist->values;
+	struct nlattr *nest;
+	int i, j;
+	u64 sum;
+
+	if (!ranges)
+		return 0;
+
+	for (i = 0; i < ETHTOOL_FEC_HIST_MAX; i++) {
+		if (i && !ranges[i].low && !ranges[i].high)
+			break;
+
+		if (WARN_ON_ONCE(values[i].sum == ETHTOOL_STAT_NOT_SET &&
+				 values[i].per_lane[0] == ETHTOOL_STAT_NOT_SET))
+			break;
+
+		nest = nla_nest_start(skb, ETHTOOL_A_FEC_STAT_HIST);
+		if (!nest)
+			return -EMSGSIZE;
+
+		if (nla_put_u32(skb, ETHTOOL_A_FEC_HIST_BIN_LOW,
+				ranges[i].low) ||
+		    nla_put_u32(skb, ETHTOOL_A_FEC_HIST_BIN_HIGH,
+				ranges[i].high))
+			goto err_cancel_hist;
+		sum = 0;
+		for (j = 0; j < ETHTOOL_MAX_LANES; j++) {
+			if (values[i].per_lane[j] == ETHTOOL_STAT_NOT_SET)
+				break;
+			sum += values[i].per_lane[j];
+		}
+		if (nla_put_uint(skb, ETHTOOL_A_FEC_HIST_BIN_VAL,
+				 values[i].sum == ETHTOOL_STAT_NOT_SET ?
+				 sum : values[i].sum))
+			goto err_cancel_hist;
+		if (j && nla_put_64bit(skb, ETHTOOL_A_FEC_HIST_BIN_VAL_PER_LANE,
+				       sizeof(u64) * j,
+				       values[i].per_lane,
+				       ETHTOOL_A_FEC_HIST_PAD))
+			goto err_cancel_hist;
+
+		nla_nest_end(skb, nest);
+	}
+
+	return 0;
+
+err_cancel_hist:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int fec_put_stats(struct sk_buff *skb, const struct fec_reply_data *data)
+{
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, ETHTOOL_A_FEC_STATS);
+	if (!nest)
+		return -EMSGSIZE;
+
+	if (nla_put_64bit(skb, ETHTOOL_A_FEC_STAT_CORRECTED,
+			  sizeof(u64) * data->corr.cnt,
+			  data->corr.stats, ETHTOOL_A_FEC_STAT_PAD) ||
+	    nla_put_64bit(skb, ETHTOOL_A_FEC_STAT_UNCORR,
+			  sizeof(u64) * data->uncorr.cnt,
+			  data->uncorr.stats, ETHTOOL_A_FEC_STAT_PAD) ||
+	    nla_put_64bit(skb, ETHTOOL_A_FEC_STAT_CORR_BITS,
+			  sizeof(u64) * data->corr_bits.cnt,
+			  data->corr_bits.stats, ETHTOOL_A_FEC_STAT_PAD))
+		goto err_cancel;
+
+	if (fec_put_hist(skb, &data->fec_stat_hist))
+		goto err_cancel;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+err_cancel:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int fec_fill_reply(struct sk_buff *skb,
+			  const struct ethnl_req_info *req_base,
+			  const struct ethnl_reply_data *reply_base)
+{
+	bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS;
+	const struct fec_reply_data *data = FEC_REPDATA(reply_base);
+	int ret;
+
+	ret = ethnl_put_bitset(skb, ETHTOOL_A_FEC_MODES,
+			       data->fec_link_modes, NULL,
+			       __ETHTOOL_LINK_MODE_MASK_NBITS,
+			       link_mode_names, compact);
+	if (ret < 0)
+		return ret;
+
+	if (nla_put_u8(skb, ETHTOOL_A_FEC_AUTO, data->fec_auto) ||
+	    (data->active_fec &&
+	     nla_put_u32(skb, ETHTOOL_A_FEC_ACTIVE, data->active_fec)))
+		return -EMSGSIZE;
+
+	if (req_base->flags & ETHTOOL_FLAG_STATS && fec_put_stats(skb, data))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+/* FEC_SET */
+
+const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1] = {
+	[ETHTOOL_A_FEC_HEADER]	= NLA_POLICY_NESTED(ethnl_header_policy),
+	[ETHTOOL_A_FEC_MODES]	= { .type = NLA_NESTED },
+	[ETHTOOL_A_FEC_AUTO]	= NLA_POLICY_MAX(NLA_U8, 1),
+};
+
+static int
+ethnl_set_fec_validate(struct ethnl_req_info *req_info, struct genl_info *info)
+{
+	const struct ethtool_ops *ops = req_info->dev->ethtool_ops;
+
+	return ops->get_fecparam && ops->set_fecparam ? 1 : -EOPNOTSUPP;
+}
+
+static int
+ethnl_set_fec(struct ethnl_req_info *req_info, struct genl_info *info)
+{
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(fec_link_modes) = {};
+	struct net_device *dev = req_info->dev;
+	struct nlattr **tb = info->attrs;
+	struct ethtool_fecparam fec = {};
+	bool mod = false;
+	u8 fec_auto;
+	int ret;
+
+	ret = dev->ethtool_ops->get_fecparam(dev, &fec);
+	if (ret < 0)
+		return ret;
+
+	ethtool_fec_to_link_modes(fec.fec, fec_link_modes, &fec_auto);
+
+	ret = ethnl_update_bitset(fec_link_modes,
+				  __ETHTOOL_LINK_MODE_MASK_NBITS,
+				  tb[ETHTOOL_A_FEC_MODES],
+				  link_mode_names, info->extack, &mod);
+	if (ret < 0)
+		return ret;
+	ethnl_update_u8(&fec_auto, tb[ETHTOOL_A_FEC_AUTO], &mod);
+	if (!mod)
+		return 0;
+
+	ret = ethtool_link_modes_to_fecparam(&fec, fec_link_modes, fec_auto);
+	if (ret) {
+		NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_FEC_MODES],
+				    "invalid FEC modes requested");
+		return ret;
+	}
+	if (!fec.fec) {
+		NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_FEC_MODES],
+				    "no FEC modes set");
+		return -EINVAL;
+	}
+
+	ret = dev->ethtool_ops->set_fecparam(dev, &fec);
+	return ret < 0 ? ret : 1;
+}
+
+const struct ethnl_request_ops ethnl_fec_request_ops = {
+	.request_cmd		= ETHTOOL_MSG_FEC_GET,
+	.reply_cmd		= ETHTOOL_MSG_FEC_GET_REPLY,
+	.hdr_attr		= ETHTOOL_A_FEC_HEADER,
+	.req_info_size		= sizeof(struct fec_req_info),
+	.reply_data_size	= sizeof(struct fec_reply_data),
+
+	.prepare_data		= fec_prepare_data,
+	.reply_size		= fec_reply_size,
+	.fill_reply		= fec_fill_reply,
+
+	.set_validate		= ethnl_set_fec_validate,
+	.set			= ethnl_set_fec,
+	.set_ntf_cmd		= ETHTOOL_MSG_FEC_NTF,
+};