From 54a0ade6d4f9dc1f3e4c13c8c9a83c755f0b1045 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 17 Jan 2019 17:08:01 +0200
Subject: [PATCH 01/55] clang-format: add configuration file

The codebase of iproute2 follows Linux kernel coding style,
so it will be very helpful to reuse existing clang configuration
file to reliably format code.

For more information see kernel commit d4ef8d3ff005
("clang-format: add configuration file").

Updated upto commit v5.0-rc1 with small number of ForEachMacros.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 .clang-format | 130 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 130 insertions(+)
 create mode 100644 .clang-format

diff --git a/.clang-format b/.clang-format
new file mode 100644
index 00000000..901467bd
--- /dev/null
+++ b/.clang-format
@@ -0,0 +1,130 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# clang-format configuration file. Intended for clang-format >= 4.
+#
+# For more information, see:
+#
+#   Documentation/process/clang-format.rst
+#   https://clang.llvm.org/docs/ClangFormat.html
+#   https://clang.llvm.org/docs/ClangFormatStyleOptions.html
+#
+---
+AccessModifierOffset: -4
+AlignAfterOpenBracket: Align
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+#AlignEscapedNewlines: Left # Unknown to clang-format-4.0
+AlignOperands: true
+AlignTrailingComments: false
+AllowAllParametersOfDeclarationOnNextLine: false
+AllowShortBlocksOnASingleLine: false
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: None
+AllowShortIfStatementsOnASingleLine: false
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakAfterDefinitionReturnType: None
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: false
+AlwaysBreakTemplateDeclarations: false
+BinPackArguments: true
+BinPackParameters: true
+BraceWrapping:
+  AfterClass: false
+  AfterControlStatement: false
+  AfterEnum: false
+  AfterFunction: true
+  AfterNamespace: true
+  AfterObjCDeclaration: false
+  AfterStruct: false
+  AfterUnion: false
+  #AfterExternBlock: false # Unknown to clang-format-5.0
+  BeforeCatch: false
+  BeforeElse: false
+  IndentBraces: false
+  #SplitEmptyFunction: true # Unknown to clang-format-4.0
+  #SplitEmptyRecord: true # Unknown to clang-format-4.0
+  #SplitEmptyNamespace: true # Unknown to clang-format-4.0
+BreakBeforeBinaryOperators: None
+BreakBeforeBraces: Custom
+#BreakBeforeInheritanceComma: false # Unknown to clang-format-4.0
+BreakBeforeTernaryOperators: false
+BreakConstructorInitializersBeforeComma: false
+#BreakConstructorInitializers: BeforeComma # Unknown to clang-format-4.0
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: false
+ColumnLimit: 80
+CommentPragmas: '^ IWYU pragma:'
+#CompactNamespaces: false # Unknown to clang-format-4.0
+ConstructorInitializerAllOnOneLineOrOnePerLine: false
+ConstructorInitializerIndentWidth: 8
+ContinuationIndentWidth: 8
+Cpp11BracedListStyle: false
+DerivePointerAlignment: false
+DisableFormat: false
+ExperimentalAutoDetectBinPacking: false
+#FixNamespaceComments: false # Unknown to clang-format-4.0
+
+# Taken from:
+#   git grep -h '^#define [^[:space:]]*for_each[^[:space:]]*(' include/ \
+#   | sed "s,^#define \([^[:space:]]*for_each[^[:space:]]*\)(.*$,  - '\1'," \
+#   | sort | uniq
+ForEachMacros:
+  - 'list_for_each_entry'
+  - 'list_for_each_entry_safe'
+  - 'mnl_attr_for_each_nested'
+  - 'hlist_for_each'
+  - 'hlist_for_each_safe'
+  - 'hlist_for_each_entry'
+
+#IncludeBlocks: Preserve # Unknown to clang-format-5.0
+IncludeCategories:
+  - Regex: '.*'
+    Priority: 1
+IncludeIsMainRegex: '(Test)?$'
+IndentCaseLabels: false
+#IndentPPDirectives: None # Unknown to clang-format-5.0
+IndentWidth: 8
+IndentWrappedFunctionNames: false
+JavaScriptQuotes: Leave
+JavaScriptWrapImports: true
+KeepEmptyLinesAtTheStartOfBlocks: false
+MacroBlockBegin: ''
+MacroBlockEnd: ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: Inner
+#ObjCBinPackProtocolList: Auto # Unknown to clang-format-5.0
+ObjCBlockIndentWidth: 8
+ObjCSpaceAfterProperty: true
+ObjCSpaceBeforeProtocolList: true
+
+# Taken from git's rules
+#PenaltyBreakAssignment: 10 # Unknown to clang-format-4.0
+PenaltyBreakBeforeFirstCallParameter: 30
+PenaltyBreakComment: 10
+PenaltyBreakFirstLessLess: 0
+PenaltyBreakString: 10
+PenaltyExcessCharacter: 100
+PenaltyReturnTypeOnItsOwnLine: 60
+
+PointerAlignment: Right
+ReflowComments: false
+SortIncludes: false
+#SortUsingDeclarations: false # Unknown to clang-format-4.0
+SpaceAfterCStyleCast: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeAssignmentOperators: true
+#SpaceBeforeCtorInitializerColon: true # Unknown to clang-format-5.0
+#SpaceBeforeInheritanceColon: true # Unknown to clang-format-5.0
+SpaceBeforeParens: ControlStatements
+#SpaceBeforeRangeBasedForLoopColon: true # Unknown to clang-format-5.0
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 1
+SpacesInAngles: false
+SpacesInContainerLiterals: false
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+Standard: Cpp03
+TabWidth: 8
+UseTab: Always
+...

From b058f969dfe2de3d8c973f2a8f009845ee55cfb0 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 17 Jan 2019 17:14:43 +0200
Subject: [PATCH 02/55] rdma: Add unbound workqueue to list of poll context
 types

Kernel commit f794809a7259 ("IB/core: Add an unbound WQ type to the new CQ API")
added new CQ poll context type, reflect this change in rdmatool.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rdma/res.c b/rdma/res.c
index cbb2efe6..6b0f5fe3 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -703,7 +703,7 @@ static void print_users(struct rd *rd, uint64_t val)
 static const char *poll_ctx_to_str(uint8_t idx)
 {
 	static const char * const cm_id_states_str[] = {
-		"DIRECT", "SOFTIRQ", "WORKQUEUE"};
+		"DIRECT", "SOFTIRQ", "WORKQUEUE", "UNBOUND_WORKQUEUE"};
 
 	if (idx < ARRAY_SIZE(cm_id_states_str))
 		return cm_id_states_str[idx];

From dad02ef47803d4d1e24dfadb6ff7b1764622daa5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 21 Jan 2019 08:29:26 -0800
Subject: [PATCH 03/55] Update kernel headers

Update kernel headers to commit
28f9d1a3d4fe ("Merge branch 'mlxsw-spectrum_router-Add-GRE-tunnel-support-for-Spectrum-2'")

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/uapi/linux/devlink.h | 25 +++++++++++++++++++++++++
 include/uapi/linux/pkt_cls.h | 13 +++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index d0a33d79..6d0fad90 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -89,6 +89,13 @@ enum devlink_command {
 	DEVLINK_CMD_REGION_DEL,
 	DEVLINK_CMD_REGION_READ,
 
+	DEVLINK_CMD_HEALTH_REPORTER_GET,
+	DEVLINK_CMD_HEALTH_REPORTER_SET,
+	DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+	DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
+	DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
+	DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -285,6 +292,24 @@ enum devlink_attr {
 	DEVLINK_ATTR_REGION_CHUNK_ADDR,         /* u64 */
 	DEVLINK_ATTR_REGION_CHUNK_LEN,          /* u64 */
 
+	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT,		/* nested */
+	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR,		/* nested */
+	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME,		/* string */
+	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE,	/* nested */
+	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY,	/* nested */
+	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE,	/* u8 */
+	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA,	/* dynamic */
+
+	DEVLINK_ATTR_HEALTH_REPORTER,			/* nested */
+	DEVLINK_ATTR_HEALTH_REPORTER_NAME,		/* string */
+	DEVLINK_ATTR_HEALTH_REPORTER_STATE,		/* u8 */
+	DEVLINK_ATTR_HEALTH_REPORTER_ERR,		/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_RECOVER,		/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_DUMP_AVAIL,	/* u8 */
+	DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS,		/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD,	/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,	/* u8 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 95d0db2a..02ac251b 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -333,12 +333,19 @@ enum {
 
 /* Basic filter */
 
+struct tc_basic_pcnt {
+	__u64 rcnt;
+	__u64 rhit;
+};
+
 enum {
 	TCA_BASIC_UNSPEC,
 	TCA_BASIC_CLASSID,
 	TCA_BASIC_EMATCHES,
 	TCA_BASIC_ACT,
 	TCA_BASIC_POLICE,
+	TCA_BASIC_PCNT,
+	TCA_BASIC_PAD,
 	__TCA_BASIC_MAX
 };
 
@@ -527,11 +534,17 @@ enum {
 
 /* Match-all classifier */
 
+struct tc_matchall_pcnt {
+	__u64 rhit;
+};
+
 enum {
 	TCA_MATCHALL_UNSPEC,
 	TCA_MATCHALL_CLASSID,
 	TCA_MATCHALL_ACT,
 	TCA_MATCHALL_FLAGS,
+	TCA_MATCHALL_PCNT,
+	TCA_MATCHALL_PAD,
 	__TCA_MATCHALL_MAX,
 };
 

From b0ca46a1f8b1c8f4d252583820d6ad7369186d45 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 17 Jan 2019 13:18:55 -0800
Subject: [PATCH 04/55] tc: add hit counter for matchall

Cc: Martin Olsson <martin.olsson+netdev@sentorsecurity.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 tc/f_matchall.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tc/f_matchall.c b/tc/f_matchall.c
index 5ebd0415..03dd51de 100644
--- a/tc/f_matchall.c
+++ b/tc/f_matchall.c
@@ -114,6 +114,7 @@ static int matchall_print_opt(struct filter_util *qu, FILE *f,
 			   struct rtattr *opt, __u32 handle)
 {
 	struct rtattr *tb[TCA_MATCHALL_MAX+1];
+	struct tc_matchall_pcnt *pf = NULL;
 
 	if (opt == NULL)
 		return 0;
@@ -143,6 +144,19 @@ static int matchall_print_opt(struct filter_util *qu, FILE *f,
 			print_bool(PRINT_ANY, "not_in_hw", "\n  not_in_hw", true);
 	}
 
+	if (tb[TCA_MATCHALL_PCNT]) {
+		if (RTA_PAYLOAD(tb[TCA_MATCHALL_PCNT])  < sizeof(*pf)) {
+			print_string(PRINT_FP, NULL, "Broken perf counters\n", NULL);
+			return -1;
+		}
+		pf = RTA_DATA(tb[TCA_MATCHALL_PCNT]);
+	}
+
+	if (show_stats && NULL != pf)
+		print_u64(PRINT_ANY, "rule_hit", " (rule hit %llu)",
+			(unsigned long long) pf->rhit);
+
+
 	if (tb[TCA_MATCHALL_ACT])
 		tc_print_action(f, tb[TCA_MATCHALL_ACT], 0);
 

From a6af9f2e6195dc67d5355d6cb94fc8512c6fba1c Mon Sep 17 00:00:00 2001
From: Benedict Wong <benedictwong@google.com>
Date: Fri, 18 Jan 2019 11:12:17 -0800
Subject: [PATCH 05/55] xfrm: add option to hide keys in state output

ip xfrm state show currently dumps keys unconditionally. This limits its
use in logging, as security information can be leaked.

This patch adds a nokeys option to ip xfrm ( state show | monitor ), which
prevents the printing of keys. This allows ip xfrm state show to be used
in logging without exposing keys.

Signed-off-by: Benedict Wong <benedictwong@google.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 ip/ipxfrm.c        | 49 +++++++++++++++++++++++++---------------------
 ip/xfrm.h          |  5 +++--
 ip/xfrm_monitor.c  |  7 +++++--
 ip/xfrm_state.c    | 27 ++++++++++++++++++++-----
 man/man8/ip-xfrm.8 | 15 +++++++++++++-
 5 files changed, 71 insertions(+), 32 deletions(-)

diff --git a/ip/ipxfrm.c b/ip/ipxfrm.c
index 2dea4e37..b153b863 100644
--- a/ip/ipxfrm.c
+++ b/ip/ipxfrm.c
@@ -497,7 +497,8 @@ void xfrm_selector_print(struct xfrm_selector *sel, __u16 family,
 }
 
 static void __xfrm_algo_print(struct xfrm_algo *algo, int type, int len,
-			      FILE *fp, const char *prefix, int newline)
+			      FILE *fp, const char *prefix, int newline,
+			      bool nokeys)
 {
 	int keylen;
 	int i;
@@ -521,7 +522,9 @@ static void __xfrm_algo_print(struct xfrm_algo *algo, int type, int len,
 		goto fin;
 	}
 
-	if (keylen > 0) {
+	if (nokeys)
+		fprintf(fp, "<<Keys hidden>>");
+	else if (keylen > 0) {
 		fprintf(fp, "0x");
 		for (i = 0; i < keylen; i++)
 			fprintf(fp, "%.2x", (unsigned char)algo->alg_key[i]);
@@ -536,13 +539,13 @@ static void __xfrm_algo_print(struct xfrm_algo *algo, int type, int len,
 }
 
 static inline void xfrm_algo_print(struct xfrm_algo *algo, int type, int len,
-				   FILE *fp, const char *prefix)
+				   FILE *fp, const char *prefix, bool nokeys)
 {
-	return __xfrm_algo_print(algo, type, len, fp, prefix, 1);
+	return __xfrm_algo_print(algo, type, len, fp, prefix, 1, nokeys);
 }
 
 static void xfrm_aead_print(struct xfrm_algo_aead *algo, int len,
-			    FILE *fp, const char *prefix)
+			    FILE *fp, const char *prefix, bool nokeys)
 {
 	struct xfrm_algo *base_algo = alloca(sizeof(*base_algo) + algo->alg_key_len / 8);
 
@@ -550,7 +553,8 @@ static void xfrm_aead_print(struct xfrm_algo_aead *algo, int len,
 	base_algo->alg_key_len = algo->alg_key_len;
 	memcpy(base_algo->alg_key, algo->alg_key, algo->alg_key_len / 8);
 
-	__xfrm_algo_print(base_algo, XFRMA_ALG_AEAD, len, fp, prefix, 0);
+	__xfrm_algo_print(base_algo, XFRMA_ALG_AEAD, len, fp, prefix, 0,
+			  nokeys);
 
 	fprintf(fp, " %d", algo->alg_icv_len);
 
@@ -558,7 +562,7 @@ static void xfrm_aead_print(struct xfrm_algo_aead *algo, int len,
 }
 
 static void xfrm_auth_trunc_print(struct xfrm_algo_auth *algo, int len,
-				  FILE *fp, const char *prefix)
+				  FILE *fp, const char *prefix, bool nokeys)
 {
 	struct xfrm_algo *base_algo = alloca(sizeof(*base_algo) + algo->alg_key_len / 8);
 
@@ -566,7 +570,8 @@ static void xfrm_auth_trunc_print(struct xfrm_algo_auth *algo, int len,
 	base_algo->alg_key_len = algo->alg_key_len;
 	memcpy(base_algo->alg_key, algo->alg_key, algo->alg_key_len / 8);
 
-	__xfrm_algo_print(base_algo, XFRMA_ALG_AUTH_TRUNC, len, fp, prefix, 0);
+	__xfrm_algo_print(base_algo, XFRMA_ALG_AUTH_TRUNC, len, fp, prefix, 0,
+			  nokeys);
 
 	fprintf(fp, " %d", algo->alg_trunc_len);
 
@@ -679,7 +684,7 @@ done:
 }
 
 void xfrm_xfrma_print(struct rtattr *tb[], __u16 family,
-		      FILE *fp, const char *prefix)
+		      FILE *fp, const char *prefix, bool nokeys)
 {
 	if (tb[XFRMA_MARK]) {
 		struct rtattr *rta = tb[XFRMA_MARK];
@@ -700,36 +705,36 @@ void xfrm_xfrma_print(struct rtattr *tb[], __u16 family,
 	if (tb[XFRMA_ALG_AUTH] && !tb[XFRMA_ALG_AUTH_TRUNC]) {
 		struct rtattr *rta = tb[XFRMA_ALG_AUTH];
 
-		xfrm_algo_print(RTA_DATA(rta),
-				XFRMA_ALG_AUTH, RTA_PAYLOAD(rta), fp, prefix);
+		xfrm_algo_print(RTA_DATA(rta), XFRMA_ALG_AUTH, RTA_PAYLOAD(rta),
+				fp, prefix, nokeys);
 	}
 
 	if (tb[XFRMA_ALG_AUTH_TRUNC]) {
 		struct rtattr *rta = tb[XFRMA_ALG_AUTH_TRUNC];
 
-		xfrm_auth_trunc_print(RTA_DATA(rta),
-				      RTA_PAYLOAD(rta), fp, prefix);
+		xfrm_auth_trunc_print(RTA_DATA(rta), RTA_PAYLOAD(rta), fp,
+				      prefix, nokeys);
 	}
 
 	if (tb[XFRMA_ALG_AEAD]) {
 		struct rtattr *rta = tb[XFRMA_ALG_AEAD];
 
-		xfrm_aead_print(RTA_DATA(rta),
-				RTA_PAYLOAD(rta), fp, prefix);
+		xfrm_aead_print(RTA_DATA(rta), RTA_PAYLOAD(rta), fp, prefix,
+				nokeys);
 	}
 
 	if (tb[XFRMA_ALG_CRYPT]) {
 		struct rtattr *rta = tb[XFRMA_ALG_CRYPT];
 
-		xfrm_algo_print(RTA_DATA(rta),
-				XFRMA_ALG_CRYPT, RTA_PAYLOAD(rta), fp, prefix);
+		xfrm_algo_print(RTA_DATA(rta), XFRMA_ALG_CRYPT,
+				RTA_PAYLOAD(rta), fp, prefix, nokeys);
 	}
 
 	if (tb[XFRMA_ALG_COMP]) {
 		struct rtattr *rta = tb[XFRMA_ALG_COMP];
 
-		xfrm_algo_print(RTA_DATA(rta),
-				XFRMA_ALG_COMP, RTA_PAYLOAD(rta), fp, prefix);
+		xfrm_algo_print(RTA_DATA(rta), XFRMA_ALG_COMP, RTA_PAYLOAD(rta),
+				fp, prefix, nokeys);
 	}
 
 	if (tb[XFRMA_ENCAP]) {
@@ -897,7 +902,7 @@ static int xfrm_selector_iszero(struct xfrm_selector *s)
 
 void xfrm_state_info_print(struct xfrm_usersa_info *xsinfo,
 			    struct rtattr *tb[], FILE *fp, const char *prefix,
-			    const char *title)
+			    const char *title, bool nokeys)
 {
 	char buf[STRBUF_SIZE] = {};
 	int force_spi = xfrm_xfrmproto_is_ipsec(xsinfo->id.proto);
@@ -943,7 +948,7 @@ void xfrm_state_info_print(struct xfrm_usersa_info *xsinfo,
 		fprintf(fp, " (0x%s)", strxf_mask8(xsinfo->flags));
 	fprintf(fp, "%s", _SL_);
 
-	xfrm_xfrma_print(tb, xsinfo->family, fp, buf);
+	xfrm_xfrma_print(tb, xsinfo->family, fp, buf, nokeys);
 
 	if (!xfrm_selector_iszero(&xsinfo->sel)) {
 		char sbuf[STRBUF_SIZE];
@@ -1071,7 +1076,7 @@ void xfrm_policy_info_print(struct xfrm_userpolicy_info *xpinfo,
 	if (show_stats > 0)
 		xfrm_lifetime_print(&xpinfo->lft, &xpinfo->curlft, fp, buf);
 
-	xfrm_xfrma_print(tb, xpinfo->sel.family, fp, buf);
+	xfrm_xfrma_print(tb, xpinfo->sel.family, fp, buf, false);
 }
 
 int xfrm_id_parse(xfrm_address_t *saddr, struct xfrm_id *id, __u16 *family,
diff --git a/ip/xfrm.h b/ip/xfrm.h
index 72390d79..9ba5ca61 100644
--- a/ip/xfrm.h
+++ b/ip/xfrm.h
@@ -105,6 +105,7 @@ struct xfrm_filter {
 extern struct xfrm_filter filter;
 
 int xfrm_state_print(struct nlmsghdr *n, void *arg);
+int xfrm_state_print_nokeys(struct nlmsghdr *n, void *arg);
 int xfrm_policy_print(struct nlmsghdr *n, void *arg);
 int do_xfrm_state(int argc, char **argv);
 int do_xfrm_policy(int argc, char **argv);
@@ -124,10 +125,10 @@ const char *strxf_ptype(__u8 ptype);
 void xfrm_selector_print(struct xfrm_selector *sel, __u16 family,
 			 FILE *fp, const char *prefix);
 void xfrm_xfrma_print(struct rtattr *tb[], __u16 family,
-		      FILE *fp, const char *prefix);
+		      FILE *fp, const char *prefix, bool nokeys);
 void xfrm_state_info_print(struct xfrm_usersa_info *xsinfo,
 			    struct rtattr *tb[], FILE *fp, const char *prefix,
-			   const char *title);
+			   const char *title, bool nokeys);
 void xfrm_policy_info_print(struct xfrm_userpolicy_info *xpinfo,
 			    struct rtattr *tb[], FILE *fp, const char *prefix,
 			    const char *title);
diff --git a/ip/xfrm_monitor.c b/ip/xfrm_monitor.c
index 76905ed3..17117f41 100644
--- a/ip/xfrm_monitor.c
+++ b/ip/xfrm_monitor.c
@@ -35,10 +35,11 @@
 
 static void usage(void) __attribute__((noreturn));
 static int listen_all_nsid;
+static bool nokeys;
 
 static void usage(void)
 {
-	fprintf(stderr, "Usage: ip xfrm monitor [all-nsid] [ all | OBJECTS | help ]\n");
+	fprintf(stderr, "Usage: ip xfrm monitor [ nokeys ] [ all-nsid ] [ all | OBJECTS | help ]\n");
 	fprintf(stderr, "OBJECTS := { acquire | expire | SA | aevent | policy | report }\n");
 	exit(-1);
 }
@@ -197,7 +198,7 @@ static int xfrm_report_print(struct nlmsghdr *n, void *arg)
 
 	parse_rtattr(tb, XFRMA_MAX, XFRMREP_RTA(xrep), len);
 
-	xfrm_xfrma_print(tb, family, fp, "  ");
+	xfrm_xfrma_print(tb, family, fp, "  ", nokeys);
 
 	if (oneline)
 		fprintf(fp, "\n");
@@ -352,6 +353,8 @@ int do_xfrm_monitor(int argc, char **argv)
 		if (matches(*argv, "file") == 0) {
 			NEXT_ARG();
 			file = *argv;
+		} else if (strcmp(*argv, "nokeys") == 0) {
+			nokeys = true;
 		} else if (strcmp(*argv, "all") == 0) {
 			/* fall out */
 		} else if (matches(*argv, "all-nsid") == 0) {
diff --git a/ip/xfrm_state.c b/ip/xfrm_state.c
index e8c01746..09292da9 100644
--- a/ip/xfrm_state.c
+++ b/ip/xfrm_state.c
@@ -65,7 +65,9 @@ static void usage(void)
 	fprintf(stderr, "Usage: ip xfrm state allocspi ID [ mode MODE ] [ mark MARK [ mask MASK ] ]\n");
 	fprintf(stderr, "        [ reqid REQID ] [ seq SEQ ] [ min SPI max SPI ]\n");
 	fprintf(stderr, "Usage: ip xfrm state { delete | get } ID [ mark MARK [ mask MASK ] ]\n");
-	fprintf(stderr, "Usage: ip xfrm state { deleteall | list } [ ID ] [ mode MODE ] [ reqid REQID ]\n");
+	fprintf(stderr, "Usage: ip xfrm state deleteall [ ID ] [ mode MODE ] [ reqid REQID ]\n");
+	fprintf(stderr, "        [ flag FLAG-LIST ]\n");
+	fprintf(stderr, "Usage: ip xfrm state list [ nokeys ] [ ID ] [ mode MODE ] [ reqid REQID ]\n");
 	fprintf(stderr, "        [ flag FLAG-LIST ]\n");
 	fprintf(stderr, "Usage: ip xfrm state flush [ proto XFRM-PROTO ]\n");
 	fprintf(stderr, "Usage: ip xfrm state count\n");
@@ -908,7 +910,7 @@ static int xfrm_state_filter_match(struct xfrm_usersa_info *xsinfo)
 	return 1;
 }
 
-int xfrm_state_print(struct nlmsghdr *n, void *arg)
+static int __do_xfrm_state_print(struct nlmsghdr *n, void *arg, bool nokeys)
 {
 	FILE *fp = (FILE *)arg;
 	struct rtattr *tb[XFRMA_MAX+1];
@@ -979,7 +981,7 @@ int xfrm_state_print(struct nlmsghdr *n, void *arg)
 		xsinfo = RTA_DATA(tb[XFRMA_SA]);
 	}
 
-	xfrm_state_info_print(xsinfo, tb, fp, NULL, NULL);
+	xfrm_state_info_print(xsinfo, tb, fp, NULL, NULL, nokeys);
 
 	if (n->nlmsg_type == XFRM_MSG_EXPIRE) {
 		fprintf(fp, "\t");
@@ -994,6 +996,16 @@ int xfrm_state_print(struct nlmsghdr *n, void *arg)
 	return 0;
 }
 
+int xfrm_state_print(struct nlmsghdr *n, void *arg)
+{
+	return __do_xfrm_state_print(n, arg, false);
+}
+
+int xfrm_state_print_nokeys(struct nlmsghdr *n, void *arg)
+{
+	return __do_xfrm_state_print(n, arg, true);
+}
+
 static int xfrm_state_get_or_delete(int argc, char **argv, int delete)
 {
 	struct rtnl_handle rth;
@@ -1145,13 +1157,16 @@ static int xfrm_state_list_or_deleteall(int argc, char **argv, int deleteall)
 {
 	char *idp = NULL;
 	struct rtnl_handle rth;
+	bool nokeys = false;
 
 	if (argc > 0)
 		filter.use = 1;
 	filter.xsinfo.family = preferred_family;
 
 	while (argc > 0) {
-		if (strcmp(*argv, "mode") == 0) {
+		if (strcmp(*argv, "nokeys") == 0) {
+			nokeys = true;
+		} else if (strcmp(*argv, "mode") == 0) {
 			NEXT_ARG();
 			xfrm_mode_parse(&filter.xsinfo.mode, &argc, &argv);
 
@@ -1267,7 +1282,9 @@ static int xfrm_state_list_or_deleteall(int argc, char **argv, int deleteall)
 			exit(1);
 		}
 
-		if (rtnl_dump_filter(&rth, xfrm_state_print, stdout) < 0) {
+		rtnl_filter_t filter = nokeys ?
+				xfrm_state_print_nokeys : xfrm_state_print;
+		if (rtnl_dump_filter(&rth, filter, stdout) < 0) {
 			fprintf(stderr, "Dump terminated\n");
 			exit(1);
 		}
diff --git a/man/man8/ip-xfrm.8 b/man/man8/ip-xfrm.8
index 839e06aa..95478085 100644
--- a/man/man8/ip-xfrm.8
+++ b/man/man8/ip-xfrm.8
@@ -89,7 +89,7 @@ ip-xfrm \- transform configuration
 .IR MASK " ] ]"
 
 .ti -8
-.BR "ip xfrm state" " { " deleteall " | " list " } ["
+.BR "ip xfrm state " deleteall " ["
 .IR ID " ]"
 .RB "[ " mode
 .IR MODE " ]"
@@ -98,6 +98,17 @@ ip-xfrm \- transform configuration
 .RB "[ " flag
 .IR FLAG-LIST " ]"
 
+.ti -8
+.BR "ip xfrm state " list " ["
+.IR ID " ]"
+.RB "[ " nokeys " ]"
+.RB "[ " mode
+.IR MODE " ]"
+.RB "[ " reqid
+.IR REQID " ]"
+.RB "[ " flag
+.IR FLAG-LIST " ]"
+
 .ti -8
 .BR "ip xfrm state flush" " [ " proto
 .IR XFRM-PROTO " ]"
@@ -381,6 +392,8 @@ ip-xfrm \- transform configuration
 .BR "ip xfrm monitor" " ["
 .BI all-nsid
 ] [
+.BI nokeys
+] [
 .BI all
  |
 .IR LISTofXFRM-OBJECTS " ]"

From 6f1940da8ec18288560579c8114efb32fc2425f0 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Fri, 25 Jan 2019 09:30:14 +1300
Subject: [PATCH 06/55] tc: replace left side comparison

The kernel (and iproute2) don't use the if (NULL == x) style
and instead prefer if (!x)

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 tc/m_action.c | 2 +-
 tc/m_ipt.c    | 3 +--
 tc/m_xt_old.c | 3 +--
 tc/tc_util.c  | 2 +-
 4 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/tc/m_action.c b/tc/m_action.c
index d5fd5aff..b5aff3ab 100644
--- a/tc/m_action.c
+++ b/tc/m_action.c
@@ -363,7 +363,7 @@ tc_print_action(FILE *f, const struct rtattr *arg, unsigned short tot_acts)
 
 	parse_rtattr_nested(tb, tot_acts, arg);
 
-	if (tab_flush && NULL != tb[0]  && NULL == tb[1])
+	if (tab_flush && tb[0] && !tb[1])
 		return tc_print_action_flush(f, tb[0]);
 
 	open_json_array(PRINT_JSON, "actions");
diff --git a/tc/m_ipt.c b/tc/m_ipt.c
index b48cc0a9..1d73cb98 100644
--- a/tc/m_ipt.c
+++ b/tc/m_ipt.c
@@ -299,9 +299,8 @@ static int parse_ipt(struct action_util *a, int *argc_p,
 		int i;
 
 		for (i = 0; i < rargc; i++) {
-			if (NULL == argv[i] || 0 == strcmp(argv[i], "action")) {
+			if (!argv[i] || strcmp(argv[i], "action") == 0)
 				break;
-			}
 		}
 		iargc = argc = i;
 	}
diff --git a/tc/m_xt_old.c b/tc/m_xt_old.c
index 313bea61..25d36778 100644
--- a/tc/m_xt_old.c
+++ b/tc/m_xt_old.c
@@ -224,9 +224,8 @@ static int parse_ipt(struct action_util *a, int *argc_p,
 		int i;
 
 		for (i = 0; i < rargc; i++) {
-			if (NULL == argv[i] || 0 == strcmp(argv[i], "action")) {
+			if (!argv[i] || strcmp(argv[i], "action") == 0)
 				break;
-			}
 		}
 		iargc = argc = i;
 	}
diff --git a/tc/tc_util.c b/tc/tc_util.c
index ab717890..1dfdae14 100644
--- a/tc/tc_util.c
+++ b/tc/tc_util.c
@@ -857,7 +857,7 @@ void print_tcstats_attr(FILE *fp, struct rtattr *tb[], char *prefix, struct rtat
 
 	if (tb[TCA_STATS2]) {
 		print_tcstats2_attr(fp, tb[TCA_STATS2], prefix, xstats);
-		if (xstats && NULL == *xstats)
+		if (xstats && !*xstats)
 			goto compat_xstats;
 		return;
 	}

From e3dbcb2a12ab1bda3de6f9f61f4dfca182ec8a4c Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Tue, 29 Jan 2019 16:01:15 +0100
Subject: [PATCH 07/55] netns: add subcommand to attach an existing network
 namespace

ip tracks namespaces with dummy files in /var/run/netns/, but can't see
namespaces created with other tools.
Creating the dummy file and bind mounting the correct procfs entry will
make ip aware of that namespace.
Add an ip netns subcommand to automate this task.

Signed-off-by: Matteo Croce <mcroce@redhat.com>
Reviewed-by: Andrea Claudi <aclaudi@redhat.com>
Tested-by: Andrea Claudi <aclaudi@redhat.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 ip/ipnetns.c        | 62 ++++++++++++++++++++++++++++++++++-----------
 man/man8/ip-netns.8 | 10 ++++++++
 2 files changed, 57 insertions(+), 15 deletions(-)

diff --git a/ip/ipnetns.c b/ip/ipnetns.c
index 03879b49..430d8844 100644
--- a/ip/ipnetns.c
+++ b/ip/ipnetns.c
@@ -28,6 +28,7 @@ static int usage(void)
 {
 	fprintf(stderr, "Usage: ip netns list\n");
 	fprintf(stderr, "       ip netns add NAME\n");
+	fprintf(stderr, "       ip netns attach NAME PID\n");
 	fprintf(stderr, "       ip netns set NAME NETNSID\n");
 	fprintf(stderr, "       ip [-all] netns delete [NAME]\n");
 	fprintf(stderr, "       ip netns identify [PID]\n");
@@ -632,24 +633,40 @@ static int create_netns_dir(void)
 	return 0;
 }
 
-static int netns_add(int argc, char **argv)
+static int netns_add(int argc, char **argv, bool create)
 {
 	/* This function creates a new network namespace and
 	 * a new mount namespace and bind them into a well known
 	 * location in the filesystem based on the name provided.
 	 *
+	 * If create is true, a new namespace will be created,
+	 * otherwise an existing one will be attached to the file.
+	 *
 	 * The mount namespace is created so that any necessary
 	 * userspace tweaks like remounting /sys, or bind mounting
-	 * a new /etc/resolv.conf can be shared between uers.
+	 * a new /etc/resolv.conf can be shared between users.
 	 */
-	char netns_path[PATH_MAX];
+	char netns_path[PATH_MAX], proc_path[PATH_MAX];
 	const char *name;
+	pid_t pid;
 	int fd;
 	int made_netns_run_dir_mount = 0;
 
-	if (argc < 1) {
-		fprintf(stderr, "No netns name specified\n");
-		return -1;
+	if (create) {
+		if (argc < 1) {
+			fprintf(stderr, "No netns name specified\n");
+			return -1;
+		}
+	} else {
+		if (argc < 2) {
+			fprintf(stderr, "No netns name and PID specified\n");
+			return -1;
+		}
+
+		if (get_s32(&pid, argv[1], 0) || !pid) {
+			fprintf(stderr, "Invalid PID: %s\n", argv[1]);
+			return -1;
+		}
 	}
 	name = argv[0];
 
@@ -689,21 +706,33 @@ static int netns_add(int argc, char **argv)
 		return -1;
 	}
 	close(fd);
-	if (unshare(CLONE_NEWNET) < 0) {
-		fprintf(stderr, "Failed to create a new network namespace \"%s\": %s\n",
-			name, strerror(errno));
-		goto out_delete;
+
+	if (create) {
+		if (unshare(CLONE_NEWNET) < 0) {
+			fprintf(stderr, "Failed to create a new network namespace \"%s\": %s\n",
+				name, strerror(errno));
+			goto out_delete;
+		}
+
+		strcpy(proc_path, "/proc/self/ns/net");
+	} else {
+		snprintf(proc_path, sizeof(proc_path), "/proc/%d/ns/net", pid);
 	}
 
 	/* Bind the netns last so I can watch for it */
-	if (mount("/proc/self/ns/net", netns_path, "none", MS_BIND, NULL) < 0) {
-		fprintf(stderr, "Bind /proc/self/ns/net -> %s failed: %s\n",
-			netns_path, strerror(errno));
+	if (mount(proc_path, netns_path, "none", MS_BIND, NULL) < 0) {
+		fprintf(stderr, "Bind %s -> %s failed: %s\n",
+			proc_path, netns_path, strerror(errno));
 		goto out_delete;
 	}
 	return 0;
 out_delete:
-	netns_delete(argc, argv);
+	if (create) {
+		netns_delete(argc, argv);
+	} else if (unlink(netns_path) < 0) {
+		fprintf(stderr, "Cannot remove namespace file \"%s\": %s\n",
+			netns_path, strerror(errno));
+	}
 	return -1;
 }
 
@@ -846,7 +875,7 @@ int do_netns(int argc, char **argv)
 		return usage();
 
 	if (matches(*argv, "add") == 0)
-		return netns_add(argc-1, argv+1);
+		return netns_add(argc-1, argv+1, true);
 
 	if (matches(*argv, "set") == 0)
 		return netns_set(argc-1, argv+1);
@@ -866,6 +895,9 @@ int do_netns(int argc, char **argv)
 	if (matches(*argv, "monitor") == 0)
 		return netns_monitor(argc-1, argv+1);
 
+	if (matches(*argv, "attach") == 0)
+		return netns_add(argc-1, argv+1, false);
+
 	fprintf(stderr, "Command \"%s\" is unknown, try \"ip netns help\".\n", *argv);
 	exit(-1);
 }
diff --git a/man/man8/ip-netns.8 b/man/man8/ip-netns.8
index d539f18b..39a10e76 100644
--- a/man/man8/ip-netns.8
+++ b/man/man8/ip-netns.8
@@ -19,6 +19,10 @@ ip-netns \- process network namespace management
 .B ip netns add
 .I NETNSNAME
 
+.ti -8
+.B ip netns attach
+.I NETNSNAME PID
+
 .ti -8
 .B ip [-all] netns del
 .RI "[ " NETNSNAME " ]"
@@ -89,6 +93,12 @@ This command displays all of the network namespaces in /var/run/netns
 If NAME is available in /var/run/netns/ this command creates a new
 network namespace and assigns NAME.
 
+.TP
+.B ip netns attach NAME PID - create a new named network namespace
+.sp
+If NAME is available in /var/run/netns/ this command attaches the network
+namespace of the process PID to NAME as if it were created with ip netns.
+
 .TP
 .B ip [-all] netns delete [ NAME ] - delete the name of a network namespace(s)
 .sp

From f79b7733b40c41c697709d04b342fbae596fc6de Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 29 Jan 2019 18:34:40 -0800
Subject: [PATCH 08/55] Update kernel headers and add xdp_diag.h

Update kernel headers to commit:
c829f5f52db9 ("cxgb4: cxgb4_tc_u32: use struct_size() in kvzalloc()")

and import xdp_diag.h for the next patch.

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/uapi/linux/bpf.h        |  2 +
 include/uapi/linux/devlink.h    | 25 ------------
 include/uapi/linux/icmpv6.h     |  2 +
 include/uapi/linux/if_bonding.h | 24 +++++++++++
 include/uapi/linux/if_link.h    |  1 +
 include/uapi/linux/in.h         |  9 +++--
 include/uapi/linux/xdp_diag.h   | 72 +++++++++++++++++++++++++++++++++
 7 files changed, 106 insertions(+), 29 deletions(-)
 create mode 100644 include/uapi/linux/xdp_diag.h

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index fb541e16..9fdd9c74 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -14,6 +14,7 @@
 /* Extended instruction set based on top of classic BPF */
 
 /* instruction classes */
+#define BPF_JMP32	0x06	/* jmp mode in word width */
 #define BPF_ALU64	0x07	/* alu mode in double word width */
 
 /* ld/ldx fields */
@@ -2540,6 +2541,7 @@ struct __sk_buff {
 	__bpf_md_ptr(struct bpf_flow_keys *, flow_keys);
 	__u64 tstamp;
 	__u32 wire_len;
+	__u32 gso_segs;
 };
 
 struct bpf_tunnel_key {
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 6d0fad90..d0a33d79 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -89,13 +89,6 @@ enum devlink_command {
 	DEVLINK_CMD_REGION_DEL,
 	DEVLINK_CMD_REGION_READ,
 
-	DEVLINK_CMD_HEALTH_REPORTER_GET,
-	DEVLINK_CMD_HEALTH_REPORTER_SET,
-	DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
-	DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
-	DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
-	DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
-
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -292,24 +285,6 @@ enum devlink_attr {
 	DEVLINK_ATTR_REGION_CHUNK_ADDR,         /* u64 */
 	DEVLINK_ATTR_REGION_CHUNK_LEN,          /* u64 */
 
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT,		/* nested */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR,		/* nested */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME,		/* string */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE,	/* nested */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY,	/* nested */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE,	/* u8 */
-	DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA,	/* dynamic */
-
-	DEVLINK_ATTR_HEALTH_REPORTER,			/* nested */
-	DEVLINK_ATTR_HEALTH_REPORTER_NAME,		/* string */
-	DEVLINK_ATTR_HEALTH_REPORTER_STATE,		/* u8 */
-	DEVLINK_ATTR_HEALTH_REPORTER_ERR,		/* u64 */
-	DEVLINK_ATTR_HEALTH_REPORTER_RECOVER,		/* u64 */
-	DEVLINK_ATTR_HEALTH_REPORTER_DUMP_AVAIL,	/* u8 */
-	DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS,		/* u64 */
-	DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD,	/* u64 */
-	DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,	/* u8 */
-
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h
index cb247a5d..cf8d5d47 100644
--- a/include/uapi/linux/icmpv6.h
+++ b/include/uapi/linux/icmpv6.h
@@ -108,6 +108,8 @@ struct icmp6hdr {
 #define ICMPV6_MOBILE_PREFIX_SOL	146
 #define ICMPV6_MOBILE_PREFIX_ADV	147
 
+#define ICMPV6_MRDISC_ADV		151
+
 /*
  *	Codes for Destination Unreachable
  */
diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h
index 61a1bf6e..790585f0 100644
--- a/include/uapi/linux/if_bonding.h
+++ b/include/uapi/linux/if_bonding.h
@@ -117,6 +117,30 @@ struct ad_info {
 	__u8 partner_system[ETH_ALEN];
 };
 
+/* Embedded inside LINK_XSTATS_TYPE_BOND */
+enum {
+	BOND_XSTATS_UNSPEC,
+	BOND_XSTATS_3AD,
+	__BOND_XSTATS_MAX
+};
+#define BOND_XSTATS_MAX (__BOND_XSTATS_MAX - 1)
+
+/* Embedded inside BOND_XSTATS_3AD */
+enum {
+	BOND_3AD_STAT_LACPDU_RX,
+	BOND_3AD_STAT_LACPDU_TX,
+	BOND_3AD_STAT_LACPDU_UNKNOWN_RX,
+	BOND_3AD_STAT_LACPDU_ILLEGAL_RX,
+	BOND_3AD_STAT_MARKER_RX,
+	BOND_3AD_STAT_MARKER_TX,
+	BOND_3AD_STAT_MARKER_RESP_RX,
+	BOND_3AD_STAT_MARKER_RESP_TX,
+	BOND_3AD_STAT_MARKER_UNKNOWN_RX,
+	BOND_3AD_STAT_PAD,
+	__BOND_3AD_STAT_MAX
+};
+#define BOND_3AD_STAT_MAX (__BOND_3AD_STAT_MAX - 1)
+
 #endif /* _LINUX_IF_BONDING_H */
 
 /*
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 484ddf83..bfe7f9e6 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -923,6 +923,7 @@ enum {
 enum {
 	LINK_XSTATS_TYPE_UNSPEC,
 	LINK_XSTATS_TYPE_BRIDGE,
+	LINK_XSTATS_TYPE_BOND,
 	__LINK_XSTATS_TYPE_MAX
 };
 #define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1)
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 1d30d797..ac079abc 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -292,10 +292,11 @@ struct sockaddr_in {
 #define	IN_LOOPBACK(a)		((((long int) (a)) & 0xff000000) == 0x7f000000)
 
 /* Defines for Multicast INADDR */
-#define INADDR_UNSPEC_GROUP   	0xe0000000U	/* 224.0.0.0   */
-#define INADDR_ALLHOSTS_GROUP 	0xe0000001U	/* 224.0.0.1   */
-#define INADDR_ALLRTRS_GROUP    0xe0000002U	/* 224.0.0.2 */
-#define INADDR_MAX_LOCAL_GROUP  0xe00000ffU	/* 224.0.0.255 */
+#define INADDR_UNSPEC_GROUP		0xe0000000U	/* 224.0.0.0   */
+#define INADDR_ALLHOSTS_GROUP		0xe0000001U	/* 224.0.0.1   */
+#define INADDR_ALLRTRS_GROUP		0xe0000002U	/* 224.0.0.2 */
+#define INADDR_ALLSNOOPERS_GROUP	0xe000006aU	/* 224.0.0.106 */
+#define INADDR_MAX_LOCAL_GROUP		0xe00000ffU	/* 224.0.0.255 */
 #endif
 
 /* <asm/byteorder.h> contains the htonl type stuff.. */
diff --git a/include/uapi/linux/xdp_diag.h b/include/uapi/linux/xdp_diag.h
new file mode 100644
index 00000000..78b2591a
--- /dev/null
+++ b/include/uapi/linux/xdp_diag.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * xdp_diag: interface for query/monitor XDP sockets
+ * Copyright(c) 2019 Intel Corporation.
+ */
+
+#ifndef _LINUX_XDP_DIAG_H
+#define _LINUX_XDP_DIAG_H
+
+#include <linux/types.h>
+
+struct xdp_diag_req {
+	__u8	sdiag_family;
+	__u8	sdiag_protocol;
+	__u16	pad;
+	__u32	xdiag_ino;
+	__u32	xdiag_show;
+	__u32	xdiag_cookie[2];
+};
+
+struct xdp_diag_msg {
+	__u8	xdiag_family;
+	__u8	xdiag_type;
+	__u16	pad;
+	__u32	xdiag_ino;
+	__u32	xdiag_cookie[2];
+};
+
+#define XDP_SHOW_INFO		(1 << 0) /* Basic information */
+#define XDP_SHOW_RING_CFG	(1 << 1)
+#define XDP_SHOW_UMEM		(1 << 2)
+#define XDP_SHOW_MEMINFO	(1 << 3)
+
+enum {
+	XDP_DIAG_NONE,
+	XDP_DIAG_INFO,
+	XDP_DIAG_UID,
+	XDP_DIAG_RX_RING,
+	XDP_DIAG_TX_RING,
+	XDP_DIAG_UMEM,
+	XDP_DIAG_UMEM_FILL_RING,
+	XDP_DIAG_UMEM_COMPLETION_RING,
+	XDP_DIAG_MEMINFO,
+	__XDP_DIAG_MAX,
+};
+
+#define XDP_DIAG_MAX (__XDP_DIAG_MAX - 1)
+
+struct xdp_diag_info {
+	__u32	ifindex;
+	__u32	queue_id;
+};
+
+struct xdp_diag_ring {
+	__u32	entries; /*num descs */
+};
+
+#define XDP_DU_F_ZEROCOPY (1 << 0)
+
+struct xdp_diag_umem {
+	__u64	size;
+	__u32	id;
+	__u32	num_pages;
+	__u32	chunk_size;
+	__u32	headroom;
+	__u32	ifindex;
+	__u32	queue_id;
+	__u32	flags;
+	__u32	refs;
+};
+
+#endif /* _LINUX_XDP_DIAG_H */

From 2abc3d76e310494774d3c2f0a0335965680e4b85 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn.topel@intel.com>
Date: Wed, 30 Jan 2019 07:57:32 +0100
Subject: [PATCH 09/55] ss: add AF_XDP support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

AF_XDP is an address family that is optimized for high performance
packet processing.

This patch adds AF_XDP support to ss(8) so that sockets can be queried
and monitored.

Example:
$ sudo ss --xdp -e -p -m
Recv-Q      Send-Q           Local Address:Port             Peer Address:Port

0           0                   enp134s0f0:q20                          *
 users:(("xdpsock",pid=17787,fd=3)) ino:39424 sk:4
        rx(entries:2048)
        tx(entries:2048)
        umem(id:1,size:8388608,num_pages:2048,chunk_size:2048,headroom:0,ifindex:7,
qid:20,zc:0,refs:1)
        fr(entries:2048)
        cr(entries:2048) skmem:(r0,rb212992,t0,tb212992,f0,w0,o0,bl0,d0)
0           0                    enp24s0f0:q0                           *
 users:(("xdpsock",pid=17780,fd=3)) ino:37384 sk:5
        rx(entries:2048)
        tx(entries:2048)
        umem(id:0,size:8388608,num_pages:2048,chunk_size:2048,headroom:0,ifindex:6,
qid:0,zc:1,refs:1)
        fr(entries:2048)
        cr(entries:2048) skmem:(r0,rb212992,t0,tb212992,f0,w0,o0,bl0,d0)

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/utils.h |   8 +++
 man/man8/ss.8   |   9 ++-
 misc/ss.c       | 168 +++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 180 insertions(+), 5 deletions(-)

diff --git a/include/utils.h b/include/utils.h
index 92bbe82d..8a9c3020 100644
--- a/include/utils.h
+++ b/include/utils.h
@@ -127,6 +127,14 @@ struct dn_naddr
 # define CLOCK_TAI 11
 #endif
 
+#ifndef AF_XDP
+# define AF_XDP 44
+# if AF_MAX < 45
+#  undef AF_MAX
+#  define AF_MAX 45
+# endif
+#endif
+
 __u32 get_addr32(const char *name);
 int get_addr_1(inet_prefix *dst, const char *arg, int family);
 int get_prefix_1(inet_prefix *dst, char *arg, int family);
diff --git a/man/man8/ss.8 b/man/man8/ss.8
index 553a6cf4..bc120fd7 100644
--- a/man/man8/ss.8
+++ b/man/man8/ss.8
@@ -324,16 +324,19 @@ Display SCTP sockets.
 .B \-\-vsock
 Display vsock sockets (alias for -f vsock).
 .TP
+.B \-\-xdp
+Display XDP sockets (alias for -f xdp).
+.TP
 .B \-f FAMILY, \-\-family=FAMILY
 Display sockets of type FAMILY.
-Currently the following families are supported: unix, inet, inet6, link, netlink, vsock.
+Currently the following families are supported: unix, inet, inet6, link, netlink, vsock, xdp.
 .TP
 .B \-A QUERY, \-\-query=QUERY, \-\-socket=QUERY
 List of socket tables to dump, separated by commas. The following identifiers
 are understood: all, inet, tcp, udp, raw, unix, packet, netlink, unix_dgram,
 unix_stream, unix_seqpacket, packet_raw, packet_dgram, dccp, sctp,
-vsock_stream, vsock_dgram. Any item in the list may optionally be prefixed by
-an exclamation mark
+vsock_stream, vsock_dgram, xdp Any item in the list may optionally be
+prefixed by an exclamation mark
 .RB ( ! )
 to exclude that socket table from being dumped.
 .TP
diff --git a/misc/ss.c b/misc/ss.c
index 3589ebed..8e5cc16b 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -42,6 +42,7 @@
 #include <linux/unix_diag.h>
 #include <linux/netdevice.h>	/* for MAX_ADDR_LEN */
 #include <linux/filter.h>
+#include <linux/xdp_diag.h>
 #include <linux/packet_diag.h>
 #include <linux/netlink_diag.h>
 #include <linux/sctp.h>
@@ -198,6 +199,7 @@ enum {
 	VSOCK_ST_DB,
 	VSOCK_DG_DB,
 	TIPC_DB,
+	XDP_DB,
 	MAX_DB
 };
 
@@ -309,6 +311,10 @@ static const struct filter default_dbs[MAX_DB] = {
 		.states   = TIPC_SS_CONN,
 		.families = FAMILY_MASK(AF_TIPC),
 	},
+	[XDP_DB] = {
+		.states   = (1 << SS_CLOSE),
+		.families = FAMILY_MASK(AF_XDP),
+	},
 };
 
 static const struct filter default_afs[AF_MAX] = {
@@ -340,6 +346,10 @@ static const struct filter default_afs[AF_MAX] = {
 		.dbs    = (1 << TIPC_DB),
 		.states = TIPC_SS_CONN,
 	},
+	[AF_XDP] = {
+		.dbs    = (1 << XDP_DB),
+		.states = (1 << SS_CLOSE),
+	},
 };
 
 static int do_default = 1;
@@ -366,7 +376,7 @@ static int filter_db_parse(struct filter *f, const char *s)
 		ENTRY(all, UDP_DB, DCCP_DB, TCP_DB, RAW_DB,
 			   UNIX_ST_DB, UNIX_DG_DB, UNIX_SQ_DB,
 			   PACKET_R_DB, PACKET_DG_DB, NETLINK_DB,
-			   SCTP_DB, VSOCK_ST_DB, VSOCK_DG_DB),
+			   SCTP_DB, VSOCK_ST_DB, VSOCK_DG_DB, XDP_DB),
 		ENTRY(inet, UDP_DB, DCCP_DB, TCP_DB, SCTP_DB, RAW_DB),
 		ENTRY(udp, UDP_DB),
 		ENTRY(dccp, DCCP_DB),
@@ -391,6 +401,7 @@ static int filter_db_parse(struct filter *f, const char *s)
 		ENTRY(v_str, VSOCK_ST_DB),	/* alias for vsock_stream */
 		ENTRY(vsock_dgram, VSOCK_DG_DB),
 		ENTRY(v_dgr, VSOCK_DG_DB),	/* alias for vsock_dgram */
+		ENTRY(xdp, XDP_DB),
 #undef ENTRY
 	};
 	bool enable = true;
@@ -1331,6 +1342,9 @@ static void sock_state_print(struct sockstat *s)
 	case AF_VSOCK:
 		sock_name = vsock_netid_name(s->type);
 		break;
+	case AF_XDP:
+		sock_name = "xdp";
+		break;
 	default:
 		sock_name = "unknown";
 	}
@@ -4055,6 +4069,142 @@ static int packet_show(struct filter *f)
 	return rc;
 }
 
+static int xdp_stats_print(struct sockstat *s, const struct filter *f)
+{
+	const char *addr, *port;
+	char q_str[16];
+
+	s->local.family = s->remote.family = AF_XDP;
+
+	if (f->f) {
+		if (run_ssfilter(f->f, s) == 0)
+			return 1;
+	}
+
+	sock_state_print(s);
+
+	if (s->iface) {
+		addr = xll_index_to_name(s->iface);
+		snprintf(q_str, sizeof(q_str), "q%d", s->lport);
+		port = q_str;
+		sock_addr_print(addr, ":", port, NULL);
+	} else {
+		sock_addr_print("", "*", "", NULL);
+	}
+
+	sock_addr_print("", "*", "", NULL);
+
+	proc_ctx_print(s);
+
+	if (show_details)
+		sock_details_print(s);
+
+	return 0;
+}
+
+static void xdp_show_ring(const char *name, struct xdp_diag_ring *ring)
+{
+	out("\n\t%s(", name);
+	out("entries:%u", ring->entries);
+	out(")");
+}
+
+static void xdp_show_umem(struct xdp_diag_umem *umem, struct xdp_diag_ring *fr,
+			  struct xdp_diag_ring *cr)
+{
+	out("\n\tumem(");
+	out("id:%u", umem->id);
+	out(",size:%llu", umem->size);
+	out(",num_pages:%u", umem->num_pages);
+	out(",chunk_size:%u", umem->chunk_size);
+	out(",headroom:%u", umem->headroom);
+	out(",ifindex:%u", umem->ifindex);
+	out(",qid:%u", umem->queue_id);
+	out(",zc:%u", umem->flags & XDP_DU_F_ZEROCOPY);
+	out(",refs:%u", umem->refs);
+	out(")");
+
+	if (fr)
+		xdp_show_ring("fr", fr);
+	if (cr)
+		xdp_show_ring("cr", cr);
+}
+
+static int xdp_show_sock(struct nlmsghdr *nlh, void *arg)
+{
+	struct xdp_diag_ring *rx = NULL, *tx = NULL, *fr = NULL, *cr = NULL;
+	struct xdp_diag_msg *msg = NLMSG_DATA(nlh);
+	struct rtattr *tb[XDP_DIAG_MAX + 1];
+	struct xdp_diag_info *info = NULL;
+	struct xdp_diag_umem *umem = NULL;
+	const struct filter *f = arg;
+	struct sockstat stat = {};
+
+	parse_rtattr(tb, XDP_DIAG_MAX, (struct rtattr *)(msg + 1),
+		     nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*msg)));
+
+	stat.type = msg->xdiag_type;
+	stat.ino = msg->xdiag_ino;
+	stat.state = SS_CLOSE;
+	stat.sk = cookie_sk_get(&msg->xdiag_cookie[0]);
+
+	if (tb[XDP_DIAG_INFO]) {
+		info = RTA_DATA(tb[XDP_DIAG_INFO]);
+		stat.iface = info->ifindex;
+		stat.lport = info->queue_id;
+	}
+
+	if (tb[XDP_DIAG_UID])
+		stat.uid = rta_getattr_u32(tb[XDP_DIAG_UID]);
+	if (tb[XDP_DIAG_RX_RING])
+		rx = RTA_DATA(tb[XDP_DIAG_RX_RING]);
+	if (tb[XDP_DIAG_TX_RING])
+		tx = RTA_DATA(tb[XDP_DIAG_TX_RING]);
+	if (tb[XDP_DIAG_UMEM])
+		umem = RTA_DATA(tb[XDP_DIAG_UMEM]);
+	if (tb[XDP_DIAG_UMEM_FILL_RING])
+		fr = RTA_DATA(tb[XDP_DIAG_UMEM_FILL_RING]);
+	if (tb[XDP_DIAG_UMEM_COMPLETION_RING])
+		cr = RTA_DATA(tb[XDP_DIAG_UMEM_COMPLETION_RING]);
+	if (tb[XDP_DIAG_MEMINFO]) {
+		__u32 *skmeminfo = RTA_DATA(tb[XDP_DIAG_MEMINFO]);
+
+		stat.rq = skmeminfo[SK_MEMINFO_RMEM_ALLOC];
+	}
+
+	if (xdp_stats_print(&stat, f))
+		return 0;
+
+	if (show_details) {
+		if (rx)
+			xdp_show_ring("rx", rx);
+		if (tx)
+			xdp_show_ring("tx", tx);
+		if (umem)
+			xdp_show_umem(umem, fr, cr);
+	}
+
+	if (show_mem)
+		print_skmeminfo(tb, XDP_DIAG_MEMINFO); // really?
+
+
+	return 0;
+}
+
+static int xdp_show(struct filter *f)
+{
+	DIAG_REQUEST(req, struct xdp_diag_req r);
+
+	if (!filter_af_get(f, AF_XDP) || !(f->states & (1 << SS_CLOSE)))
+		return 0;
+
+	req.r.sdiag_family = AF_XDP;
+	req.r.xdiag_show = XDP_SHOW_INFO | XDP_SHOW_RING_CFG | XDP_SHOW_UMEM |
+			   XDP_SHOW_MEMINFO;
+
+	return handle_netlink_request(f, &req.nlh, sizeof(req), xdp_show_sock);
+}
+
 static int netlink_show_one(struct filter *f,
 				int prot, int pid, unsigned int groups,
 				int state, int dst_pid, unsigned int dst_group,
@@ -4442,6 +4592,9 @@ static int generic_show_sock(struct nlmsghdr *nlh, void *arg)
 	case AF_VSOCK:
 		ret = vsock_show_sock(nlh, arg);
 		break;
+	case AF_XDP:
+		ret = xdp_show_sock(nlh, arg);
+		break;
 	default:
 		ret = -1;
 	}
@@ -4679,7 +4832,7 @@ static void _usage(FILE *dest)
 "       --tipc          display only TIPC sockets\n"
 "       --vsock         display only vsock sockets\n"
 "   -f, --family=FAMILY display sockets of type FAMILY\n"
-"       FAMILY := {inet|inet6|link|unix|netlink|vsock|tipc|help}\n"
+"       FAMILY := {inet|inet6|link|unix|netlink|vsock|tipc|xdp|help}\n"
 "\n"
 "   -K, --kill          forcibly close sockets, display what was closed\n"
 "   -H, --no-header     Suppress header line\n"
@@ -4765,6 +4918,9 @@ static int scan_state(const char *state)
 #define OPT_TIPCSOCK 257
 #define OPT_TIPCINFO 258
 
+/* Values of 'x' are already used so a non-character is used */
+#define OPT_XDPSOCK 259
+
 static const struct option long_opts[] = {
 	{ "numeric", 0, 0, 'n' },
 	{ "resolve", 0, 0, 'r' },
@@ -4802,6 +4958,7 @@ static const struct option long_opts[] = {
 	{ "tipcinfo", 0, 0, OPT_TIPCINFO},
 	{ "kill", 0, 0, 'K' },
 	{ "no-header", 0, 0, 'H' },
+	{ "xdp", 0, 0, OPT_XDPSOCK},
 	{ 0 }
 
 };
@@ -4889,6 +5046,9 @@ int main(int argc, char *argv[])
 		case '0':
 			filter_af_set(&current_filter, AF_PACKET);
 			break;
+		case OPT_XDPSOCK:
+			filter_af_set(&current_filter, AF_XDP);
+			break;
 		case 'f':
 			if (strcmp(optarg, "inet") == 0)
 				filter_af_set(&current_filter, AF_INET);
@@ -4904,6 +5064,8 @@ int main(int argc, char *argv[])
 				filter_af_set(&current_filter, AF_TIPC);
 			else if (strcmp(optarg, "vsock") == 0)
 				filter_af_set(&current_filter, AF_VSOCK);
+			else if (strcmp(optarg, "xdp") == 0)
+				filter_af_set(&current_filter, AF_XDP);
 			else if (strcmp(optarg, "help") == 0)
 				help();
 			else {
@@ -5101,6 +5263,8 @@ int main(int argc, char *argv[])
 		vsock_show(&current_filter);
 	if (current_filter.dbs & (1<<TIPC_DB))
 		tipc_show(&current_filter);
+	if (current_filter.dbs & (1<<XDP_DB))
+		xdp_show(&current_filter);
 
 	if (show_users || show_proc_ctx || show_sock_ctx)
 		user_ent_destroy();

From 52d57f6bbdf799c2b54307a70c256e0c127e9663 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 31 Jan 2019 18:58:09 +0100
Subject: [PATCH 10/55] tc: full JSON support for 'bpf' actions

Add full JSON output support in the dump of 'act_bpf'.

Example using eBPF:

 # tc actions flush action bpf
 # tc action add action bpf object bpf/action.o section 'action-ok'
 # tc -j action list action bpf | jq
 [
   {
     "total acts": 1
   },
   {
     "actions": [
       {
         "order": 0,
         "kind": "bpf",
         "bpf_name": "action.o:[action-ok]",
         "prog": {
           "id": 33,
           "tag": "a04f5eef06a7f555",
           "jited": 1
         },
         "control_action": {
           "type": "pipe"
         },
         "index": 1,
         "ref": 1,
         "bind": 0
       }
     ]
   }
 ]

Example using cBPF:

 # tc actions flush action bpf
 # a=$(mktemp)
 # tcpdump -ddd not ether proto 0x888e >$a
 # tc action add action bpf bytecode-file $a index 42
 # rm $a
 # tc -j action list action bpf | jq
 [
   {
     "total acts": 1
   },
   {
     "actions": [
       {
         "order": 0,
         "kind": "bpf",
         "bytecode": {
           "length": 4,
           "insns": [
             {
               "code": 40,
               "jt": 0,
               "jf": 0,
               "k": 12
             },
             {
               "code": 21,
               "jt": 0,
               "jf": 1,
               "k": 34958
             },
             {
               "code": 6,
               "jt": 0,
               "jf": 0,
               "k": 0
             },
             {
               "code": 6,
               "jt": 0,
               "jf": 0,
               "k": 262144
             }
           ]
         },
         "control_action": {
           "type": "pipe"
         },
         "index": 42,
         "ref": 1,
         "bind": 0
       }
     ]
   }
 ]

Tested with:
 # ./tdc.py -c bpf

Cc: Andrea Claudi <aclaudi@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/bpf_util.h |  2 +-
 lib/bpf.c          | 24 +++++++++++++++++-------
 tc/f_bpf.c         |  2 +-
 tc/m_bpf.c         | 32 +++++++++++++++++---------------
 4 files changed, 36 insertions(+), 24 deletions(-)

diff --git a/include/bpf_util.h b/include/bpf_util.h
index 63837a04..63db07ca 100644
--- a/include/bpf_util.h
+++ b/include/bpf_util.h
@@ -272,7 +272,7 @@ const char *bpf_prog_to_default_section(enum bpf_prog_type type);
 int bpf_graft_map(const char *map_path, uint32_t *key, int argc, char **argv);
 int bpf_trace_pipe(void);
 
-void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len);
+void bpf_print_ops(struct rtattr *bpf_ops, __u16 len);
 
 int bpf_prog_load(enum bpf_prog_type type, const struct bpf_insn *insns,
 		  size_t size_insns, const char *license, char *log,
diff --git a/lib/bpf.c b/lib/bpf.c
index 5e85cfc0..dfc4f4f5 100644
--- a/lib/bpf.c
+++ b/lib/bpf.c
@@ -339,7 +339,7 @@ out:
 	return ret;
 }
 
-void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len)
+void bpf_print_ops(struct rtattr *bpf_ops, __u16 len)
 {
 	struct sock_filter *ops = RTA_DATA(bpf_ops);
 	int i;
@@ -347,14 +347,24 @@ void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len)
 	if (len == 0)
 		return;
 
-	fprintf(f, "bytecode \'%u,", len);
+	open_json_object("bytecode");
+	print_uint(PRINT_ANY, "length", "bytecode \'%u,", len);
+	open_json_array(PRINT_JSON, "insns");
 
-	for (i = 0; i < len - 1; i++)
-		fprintf(f, "%hu %hhu %hhu %u,", ops[i].code, ops[i].jt,
-			ops[i].jf, ops[i].k);
+	for (i = 0; i < len; i++) {
+		open_json_object(NULL);
+		print_uint(PRINT_ANY, "code", "%hu ", ops[i].code);
+		print_uint(PRINT_ANY, "jt", "%hhu ", ops[i].jt);
+		print_uint(PRINT_ANY, "jf", "%hhu ", ops[i].jf);
+		if (i == len - 1)
+			print_uint(PRINT_ANY, "k", "%u\'", ops[i].k);
+		else
+			print_uint(PRINT_ANY, "k", "%u,", ops[i].k);
+		close_json_object();
+	}
 
-	fprintf(f, "%hu %hhu %hhu %u\'", ops[i].code, ops[i].jt,
-		ops[i].jf, ops[i].k);
+	close_json_array(PRINT_JSON, NULL);
+	close_json_object();
 }
 
 static void bpf_map_pin_report(const struct bpf_elf_map *pin,
diff --git a/tc/f_bpf.c b/tc/f_bpf.c
index 5906f8bb..948d9051 100644
--- a/tc/f_bpf.c
+++ b/tc/f_bpf.c
@@ -235,7 +235,7 @@ static int bpf_print_opt(struct filter_util *qu, FILE *f,
 	}
 
 	if (tb[TCA_BPF_OPS] && tb[TCA_BPF_OPS_LEN])
-		bpf_print_ops(f, tb[TCA_BPF_OPS],
+		bpf_print_ops(tb[TCA_BPF_OPS],
 			      rta_getattr_u16(tb[TCA_BPF_OPS_LEN]));
 
 	if (tb[TCA_BPF_ID])
diff --git a/tc/m_bpf.c b/tc/m_bpf.c
index 7c6f8c29..3e8468c6 100644
--- a/tc/m_bpf.c
+++ b/tc/m_bpf.c
@@ -157,7 +157,7 @@ static int bpf_print_opt(struct action_util *au, FILE *f, struct rtattr *arg)
 {
 	struct rtattr *tb[TCA_ACT_BPF_MAX + 1];
 	struct tc_act_bpf *parm;
-	int dump_ok = 0;
+	int d_ok = 0;
 
 	if (arg == NULL)
 		return -1;
@@ -170,31 +170,33 @@ static int bpf_print_opt(struct action_util *au, FILE *f, struct rtattr *arg)
 	}
 
 	parm = RTA_DATA(tb[TCA_ACT_BPF_PARMS]);
-	fprintf(f, "bpf ");
+	print_string(PRINT_ANY, "kind", "%s ", "bpf");
 
 	if (tb[TCA_ACT_BPF_NAME])
-		fprintf(f, "%s ", rta_getattr_str(tb[TCA_ACT_BPF_NAME]));
-
+		print_string(PRINT_ANY, "bpf_name", "%s ",
+			     rta_getattr_str(tb[TCA_ACT_BPF_NAME]));
 	if (tb[TCA_ACT_BPF_OPS] && tb[TCA_ACT_BPF_OPS_LEN]) {
-		bpf_print_ops(f, tb[TCA_ACT_BPF_OPS],
+		bpf_print_ops(tb[TCA_ACT_BPF_OPS],
 			      rta_getattr_u16(tb[TCA_ACT_BPF_OPS_LEN]));
-		fprintf(f, " ");
+		print_string(PRINT_FP, NULL, "%s", " ");
 	}
 
 	if (tb[TCA_ACT_BPF_ID])
-		dump_ok = bpf_dump_prog_info(f, rta_getattr_u32(tb[TCA_ACT_BPF_ID]));
-	if (!dump_ok && tb[TCA_ACT_BPF_TAG]) {
+		d_ok = bpf_dump_prog_info(f,
+					  rta_getattr_u32(tb[TCA_ACT_BPF_ID]));
+	if (!d_ok && tb[TCA_ACT_BPF_TAG]) {
 		SPRINT_BUF(b);
 
-		fprintf(f, "tag %s ",
-			hexstring_n2a(RTA_DATA(tb[TCA_ACT_BPF_TAG]),
-				      RTA_PAYLOAD(tb[TCA_ACT_BPF_TAG]),
-				      b, sizeof(b)));
+		print_string(PRINT_ANY, "tag", "tag %s ",
+			     hexstring_n2a(RTA_DATA(tb[TCA_ACT_BPF_TAG]),
+			     RTA_PAYLOAD(tb[TCA_ACT_BPF_TAG]),
+			     b, sizeof(b)));
 	}
 
-	print_action_control(f, "default-action ", parm->action, "\n");
-	fprintf(f, "\tindex %u ref %d bind %d", parm->index, parm->refcnt,
-		parm->bindcnt);
+	print_action_control(f, "default-action ", parm->action, _SL_);
+	print_uint(PRINT_ANY, "index", "\t index %u", parm->index);
+	print_int(PRINT_ANY, "ref", " ref %d", parm->refcnt);
+	print_int(PRINT_ANY, "bind", " bind %d", parm->bindcnt);
 
 	if (show_stats) {
 		if (tb[TCA_ACT_BPF_TM]) {

From e8a3d76919263b9e5dbb71a1c80373eae3484ecc Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 31 Jan 2019 18:58:41 +0100
Subject: [PATCH 11/55] tc: add 'kind' property to 'csum' action

unlike other TC actions already supporting JSON printout, 'csum' does not
print the value of TCA_KIND in the 'kind' property: remove 'csum' word
from 'csum' property, and add a separate 'kind' property containing the
action name. The human-readable printout is preserved.

Tested with:
 # ./tdc.py -c csum

Cc: Andrea Claudi <aclaudi@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 tc/m_csum.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tc/m_csum.c b/tc/m_csum.c
index 752269d1..84396d6a 100644
--- a/tc/m_csum.c
+++ b/tc/m_csum.c
@@ -199,10 +199,11 @@ print_csum(struct action_util *au, FILE *f, struct rtattr *arg)
 		uflag_1 = "?empty";
 	}
 
+	print_string(PRINT_ANY, "kind", "%s ", "csum");
 	snprintf(buf, sizeof(buf), "%s%s%s%s%s%s%s",
 		 uflag_1, uflag_2, uflag_3,
 		 uflag_4, uflag_5, uflag_6, uflag_7);
-	print_string(PRINT_ANY, "csum", "csum (%s) ", buf);
+	print_string(PRINT_ANY, "csum", "(%s) ", buf);
 
 	print_action_control(f, "action ", sel->action, "\n");
 	print_uint(PRINT_ANY, "index", "\tindex %u", sel->index);

From 6b2d60bdfc77103baa29f4c3be8e64dd5ea57a93 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 6 Feb 2019 08:45:41 -0800
Subject: [PATCH 12/55] Update kernel headers

Update kernel headers to commit:
bfbae2eafe05 ("Merge branch '1GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue")

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/uapi/linux/bpf.h     |  8 +++++++-
 include/uapi/linux/devlink.h | 17 +++++++++++++++++
 include/uapi/linux/sctp.h    |  4 ++++
 3 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9fdd9c74..031c4b4c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -267,6 +267,7 @@ enum bpf_attach_type {
 #define BPF_ANY		0 /* create new element or update existing */
 #define BPF_NOEXIST	1 /* create new element if it didn't exist */
 #define BPF_EXIST	2 /* update existing element */
+#define BPF_F_LOCK	4 /* spin_lock-ed map_lookup/map_update */
 
 /* flags for BPF_MAP_CREATE command */
 #define BPF_F_NO_PREALLOC	(1U << 0)
@@ -2422,7 +2423,9 @@ union bpf_attr {
 	FN(map_peek_elem),		\
 	FN(msg_push_data),		\
 	FN(msg_pop_data),		\
-	FN(rc_pointer_rel),
+	FN(rc_pointer_rel),		\
+	FN(spin_lock),			\
+	FN(spin_unlock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3056,4 +3059,7 @@ struct bpf_line_info {
 	__u32	line_col;
 };
 
+struct bpf_spin_lock {
+	__u32	val;
+};
 #endif /* __LINUX_BPF_H__ */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index d0a33d79..d51b59a7 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -89,6 +89,13 @@ enum devlink_command {
 	DEVLINK_CMD_REGION_DEL,
 	DEVLINK_CMD_REGION_READ,
 
+	DEVLINK_CMD_PORT_PARAM_GET,	/* can dump */
+	DEVLINK_CMD_PORT_PARAM_SET,
+	DEVLINK_CMD_PORT_PARAM_NEW,
+	DEVLINK_CMD_PORT_PARAM_DEL,
+
+	DEVLINK_CMD_INFO_GET,		/* can dump */
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -285,6 +292,16 @@ enum devlink_attr {
 	DEVLINK_ATTR_REGION_CHUNK_ADDR,         /* u64 */
 	DEVLINK_ATTR_REGION_CHUNK_LEN,          /* u64 */
 
+	DEVLINK_ATTR_INFO_DRIVER_NAME,		/* string */
+	DEVLINK_ATTR_INFO_SERIAL_NUMBER,	/* string */
+	DEVLINK_ATTR_INFO_VERSION_FIXED,	/* nested */
+	DEVLINK_ATTR_INFO_VERSION_RUNNING,	/* nested */
+	DEVLINK_ATTR_INFO_VERSION_STORED,	/* nested */
+	DEVLINK_ATTR_INFO_VERSION_NAME,		/* string */
+	DEVLINK_ATTR_INFO_VERSION_VALUE,	/* string */
+
+	DEVLINK_ATTR_SB_POOL_CELL_SIZE,		/* u32 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index e9970b69..c4bce0a2 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -59,6 +59,10 @@
 
 typedef __s32 sctp_assoc_t;
 
+#define SCTP_FUTURE_ASSOC	0
+#define SCTP_CURRENT_ASSOC	1
+#define SCTP_ALL_ASSOC		2
+
 /* The following symbols come from the Sockets API Extensions for
  * SCTP <draft-ietf-tsvwg-sctpsocket-07.txt>.
  */

From 9d886c66092818f51fc1ddc4030f050b390d2ce9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 4 Feb 2019 07:28:59 -0800
Subject: [PATCH 13/55] devlink: report cell size

Print the value of DEVLINK_ATTR_SB_POOL_CELL_SIZE, if reported.

Example:
pci/0000:82:00.0:
  sb 1 pool 0 type egress size 40945664 thtype static cell_size 2048
  sb 2 pool 0 type egress size 258867200 thtype static cell_size 10240
...

v3: - don't double space.
v2: - fix spelling.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c     |  3 +++
 man/man8/devlink-sb.8 | 10 ++++++++++
 2 files changed, 13 insertions(+)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index 3651e90c..4c44c3be 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -2722,6 +2722,9 @@ static void pr_out_sb_pool(struct dl *dl, struct nlattr **tb)
 		    mnl_attr_get_u32(tb[DEVLINK_ATTR_SB_POOL_SIZE]));
 	pr_out_str(dl, "thtype",
 		   threshold_type_name(mnl_attr_get_u8(tb[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE])));
+	if (tb[DEVLINK_ATTR_SB_POOL_CELL_SIZE])
+		pr_out_uint(dl, "cell_size",
+			    mnl_attr_get_u32(tb[DEVLINK_ATTR_SB_POOL_CELL_SIZE]));
 	pr_out_handle_end(dl);
 }
 
diff --git a/man/man8/devlink-sb.8 b/man/man8/devlink-sb.8
index 1882833a..91b68189 100644
--- a/man/man8/devlink-sb.8
+++ b/man/man8/devlink-sb.8
@@ -128,6 +128,16 @@ Behaviour of this argument it the same for every command.
 - specifies the devlink device to show pools.
 If this argument is omitted all pools of all devices are listed.
 
+Display available pools listing their
+.B type, size, thtype
+and
+.B cell_size. cell_size
+is the allocation granularity of memory within the shared buffer. Drivers
+may round up, round down or reject
+.B size
+passed to the set command if it is not multiple of
+.B cell_size.
+
 .SS devlink sb pool set - set attributes of pool
 
 .PP

From 05bc89e95ef6887ccb0ec143171760352112c7a6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 4 Feb 2019 08:10:11 -0800
Subject: [PATCH 14/55] devlink: add info subcommand

Add support for reading the device serial number, driver name
and various versions.  Example:

$ devlink dev info pci/0000:82:00.0
pci/0000:82:00.0:
  driver nfp
  serial_number 16240145
  versions:
      fixed:
        board.id AMDA0081-0001
        board.rev 15
        board.vendor SMA
        board.model hydrogen
      running:
        fw.mgmt 010181.010181.0101d4
        fw.cpld 0x1030000
        fw.app abm-d372b6
        fw.undi 0.0.2
        chip.init AMDA-0081-0001  20160318164536
      stored:
        fw.mgmt 010181.010181.0101d4
        fw.app abm-d372b6
        fw.undi 0.0.2
        chip.init AMDA-0081-0001  20160318164536

$ devlink -jp dev info pci/0000:82:00.0
{
    "info": {
        "pci/0000:82:00.0": {
            "driver": "nfp",
            "serial_number": "16240145",
            "versions": {
                "fixed": {
                    "board.id": "AMDA0081-0001",
                    "board.rev": "15",
                    "board.vendor": "SMA",
                    "board.model": "hydrogen"
                },
                "running": {
                    "fw.mgmt": "010181.010181.0101d4",
                    "fw.cpld": "0x1030000",
                    "fw.app": "abm-d372b6",
                    "fw.undi": "0.0.2",
                    "chip.init": "AMDA-0081-0001  20160318164536"
                },
                "stored": {
                    "fw.mgmt": "010181.010181.0101d4",
                    "fw.app": "abm-d372b6",
                    "fw.undi": "0.0.2",
                    "chip.init": "AMDA-0081-0001  20160318164536"
                }
            }
        }
    }
}

v5:
 - remove spurious new line.
v4:
 - more commit message improvements.
v3:
 - show up-to-date output in the commit message.
v2 (Jiri):
 - remove filtering;
 - add example in the commit message.
RFCv2:
 - make info subcommand of dev.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c      | 171 +++++++++++++++++++++++++++++++++++++++++
 man/man8/devlink-dev.8 |  26 +++++++
 2 files changed, 197 insertions(+)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index 4c44c3be..d823512a 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -383,6 +383,13 @@ static const enum mnl_attr_data_type devlink_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_REGION_CHUNK_DATA] = MNL_TYPE_BINARY,
 	[DEVLINK_ATTR_REGION_CHUNK_ADDR] = MNL_TYPE_U64,
 	[DEVLINK_ATTR_REGION_CHUNK_LEN] = MNL_TYPE_U64,
+	[DEVLINK_ATTR_INFO_DRIVER_NAME] = MNL_TYPE_STRING,
+	[DEVLINK_ATTR_INFO_SERIAL_NUMBER] = MNL_TYPE_STRING,
+	[DEVLINK_ATTR_INFO_VERSION_FIXED] = MNL_TYPE_NESTED,
+	[DEVLINK_ATTR_INFO_VERSION_RUNNING] = MNL_TYPE_NESTED,
+	[DEVLINK_ATTR_INFO_VERSION_STORED] = MNL_TYPE_NESTED,
+	[DEVLINK_ATTR_INFO_VERSION_NAME] = MNL_TYPE_STRING,
+	[DEVLINK_ATTR_INFO_VERSION_VALUE] = MNL_TYPE_STRING,
 };
 
 static int attr_cb(const struct nlattr *attr, void *data)
@@ -1443,6 +1450,7 @@ static void cmd_dev_help(void)
 	pr_err("       devlink dev param set DEV name PARAMETER value VALUE cmode { permanent | driverinit | runtime }\n");
 	pr_err("       devlink dev param show [DEV name PARAMETER]\n");
 	pr_err("       devlink dev reload DEV\n");
+	pr_err("       devlink dev info [ DEV ]\n");
 }
 
 static bool cmp_arr_last_handle(struct dl *dl, const char *bus_name,
@@ -1775,6 +1783,30 @@ static void pr_out_array_end(struct dl *dl)
 	}
 }
 
+static void pr_out_object_start(struct dl *dl, const char *name)
+{
+	if (dl->json_output) {
+		jsonw_name(dl->jw, name);
+		jsonw_start_object(dl->jw);
+	} else {
+		__pr_out_indent_inc();
+		__pr_out_newline();
+		pr_out("%s:", name);
+		__pr_out_indent_inc();
+		__pr_out_newline();
+	}
+}
+
+static void pr_out_object_end(struct dl *dl)
+{
+	if (dl->json_output) {
+		jsonw_end_object(dl->jw);
+	} else {
+		__pr_out_indent_dec();
+		__pr_out_indent_dec();
+	}
+}
+
 static void pr_out_entry_start(struct dl *dl)
 {
 	if (dl->json_output)
@@ -2415,6 +2447,142 @@ static int cmd_dev_reload(struct dl *dl)
 	return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
 }
 
+static void pr_out_versions_single(struct dl *dl, const struct nlmsghdr *nlh,
+				   const char *name, int type)
+{
+	struct nlattr *version;
+
+	mnl_attr_for_each(version, nlh, sizeof(struct genlmsghdr)) {
+		struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+		const char *ver_value;
+		const char *ver_name;
+		int err;
+
+		if (mnl_attr_get_type(version) != type)
+			continue;
+
+		err = mnl_attr_parse_nested(version, attr_cb, tb);
+		if (err != MNL_CB_OK)
+			continue;
+
+		if (!tb[DEVLINK_ATTR_INFO_VERSION_NAME] ||
+		    !tb[DEVLINK_ATTR_INFO_VERSION_VALUE])
+			continue;
+
+		if (name) {
+			pr_out_object_start(dl, name);
+			name = NULL;
+		}
+
+		ver_name = mnl_attr_get_str(tb[DEVLINK_ATTR_INFO_VERSION_NAME]);
+		ver_value = mnl_attr_get_str(tb[DEVLINK_ATTR_INFO_VERSION_VALUE]);
+
+		pr_out_str(dl, ver_name, ver_value);
+		if (!dl->json_output)
+			__pr_out_newline();
+	}
+
+	if (!name)
+		pr_out_object_end(dl);
+}
+
+static void pr_out_info(struct dl *dl, const struct nlmsghdr *nlh,
+			struct nlattr **tb, bool has_versions)
+{
+	__pr_out_handle_start(dl, tb, true, false);
+
+	__pr_out_indent_inc();
+	if (tb[DEVLINK_ATTR_INFO_DRIVER_NAME]) {
+		struct nlattr *nla_drv = tb[DEVLINK_ATTR_INFO_DRIVER_NAME];
+
+		if (!dl->json_output)
+			__pr_out_newline();
+		pr_out_str(dl, "driver", mnl_attr_get_str(nla_drv));
+	}
+
+	if (tb[DEVLINK_ATTR_INFO_SERIAL_NUMBER]) {
+		struct nlattr *nla_sn = tb[DEVLINK_ATTR_INFO_SERIAL_NUMBER];
+
+		if (!dl->json_output)
+			__pr_out_newline();
+		pr_out_str(dl, "serial_number", mnl_attr_get_str(nla_sn));
+	}
+	__pr_out_indent_dec();
+
+	if (has_versions) {
+		pr_out_object_start(dl, "versions");
+
+		pr_out_versions_single(dl, nlh, "fixed",
+				       DEVLINK_ATTR_INFO_VERSION_FIXED);
+		pr_out_versions_single(dl, nlh, "running",
+				       DEVLINK_ATTR_INFO_VERSION_RUNNING);
+		pr_out_versions_single(dl, nlh, "stored",
+				       DEVLINK_ATTR_INFO_VERSION_STORED);
+
+		pr_out_object_end(dl);
+	}
+
+	pr_out_handle_end(dl);
+}
+
+static int cmd_versions_show_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+	struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+	bool has_versions, has_info;
+	struct dl *dl = data;
+
+	mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+
+	if (!tb[DEVLINK_ATTR_BUS_NAME] || !tb[DEVLINK_ATTR_DEV_NAME])
+		return MNL_CB_ERROR;
+
+	has_versions = tb[DEVLINK_ATTR_INFO_VERSION_FIXED] ||
+		tb[DEVLINK_ATTR_INFO_VERSION_RUNNING] ||
+		tb[DEVLINK_ATTR_INFO_VERSION_STORED];
+	has_info = tb[DEVLINK_ATTR_INFO_DRIVER_NAME] ||
+		tb[DEVLINK_ATTR_INFO_SERIAL_NUMBER] ||
+		has_versions;
+
+	if (has_info)
+		pr_out_info(dl, nlh, tb, has_versions);
+
+	return MNL_CB_OK;
+}
+
+static void cmd_dev_info_help(void)
+{
+	pr_err("Usage: devlink dev info [ DEV ]\n");
+}
+
+static int cmd_dev_info(struct dl *dl)
+{
+	struct nlmsghdr *nlh;
+	uint16_t flags = NLM_F_REQUEST | NLM_F_ACK;
+	int err;
+
+	if (dl_argv_match(dl, "help")) {
+		cmd_dev_info_help();
+		return 0;
+	}
+
+	if (dl_argc(dl) == 0)
+		flags |= NLM_F_DUMP;
+
+	nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_INFO_GET, flags);
+
+	if (dl_argc(dl) > 0) {
+		err = dl_argv_parse_put(nlh, dl, DL_OPT_HANDLE, 0);
+		if (err)
+			return err;
+	}
+
+	pr_out_section_start(dl, "info");
+	err = _mnlg_socket_sndrcv(dl->nlg, nlh, cmd_versions_show_cb, dl);
+	pr_out_section_end(dl);
+	return err;
+}
+
 static int cmd_dev(struct dl *dl)
 {
 	if (dl_argv_match(dl, "help")) {
@@ -2433,6 +2601,9 @@ static int cmd_dev(struct dl *dl)
 	} else if (dl_argv_match(dl, "param")) {
 		dl_arg_inc(dl);
 		return cmd_dev_param(dl);
+	} else if (dl_argv_match(dl, "info")) {
+		dl_arg_inc(dl);
+		return cmd_dev_info(dl);
 	}
 	pr_err("Command \"%s\" not found\n", dl_argv(dl));
 	return -ENOENT;
diff --git a/man/man8/devlink-dev.8 b/man/man8/devlink-dev.8
index d985da17..47838371 100644
--- a/man/man8/devlink-dev.8
+++ b/man/man8/devlink-dev.8
@@ -63,6 +63,12 @@ devlink-dev \- devlink device configuration
 .BR "devlink dev reload"
 .IR DEV
 
+.ti -8
+.BR "devlink dev info"
+.RI "[ "
+.IR DEV
+.RI "]"
+
 .SH "DESCRIPTION"
 .SS devlink dev show - display devlink device attributes
 
@@ -151,6 +157,26 @@ If this argument is omitted all parameters supported by devlink devices are list
 .I "DEV"
 - Specifies the devlink device to reload.
 
+.SS devlink dev info - display device information.
+Display device information provided by the driver. This command can be used
+to query versions of the hardware components or device components which
+can't be updated (
+.I fixed
+) as well as device firmware which can be updated. For firmware components
+.I running
+displays the versions of firmware currently loaded into the device, while
+.I stored
+reports the versions in device's flash.
+.I Running
+and
+.I stored
+versions may differ after flash has been updated, but before reboot.
+
+.PP
+.I "DEV"
+- specifies the devlink device to show.
+If this argument is omitted all devices are listed.
+
 .SH "EXAMPLES"
 .PP
 devlink dev show

From ca81444303e3dc2cdcb65606b7e8e28fc3ba2a08 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 7 Feb 2019 11:51:27 +0100
Subject: [PATCH 15/55] use print_{,h}hu instead of print_uint when format
 specifier is %{,h}hu

in this way, a useless cast to unsigned int is avoided in bpf_print_ops()
and print_tunnel().

Tested with:
 # ./tdc.py -c bpf

Suggested-by: Stephen Hemminger <stephen@networkplumber.org>
Cc: Andrea Claudi <aclaudi@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 ip/ipl2tp.c | 4 ++--
 lib/bpf.c   | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/ip/ipl2tp.c b/ip/ipl2tp.c
index f699b258..77bc3249 100644
--- a/ip/ipl2tp.c
+++ b/ip/ipl2tp.c
@@ -237,9 +237,9 @@ static void print_tunnel(const struct l2tp_data *data)
 		print_string(PRINT_FP, NULL,
 			     "  UDP source / dest ports:", NULL);
 
-		print_uint(PRINT_ANY, "local_port", " %hu",
+		print_hu(PRINT_ANY, "local_port", " %hu",
 			   p->local_udp_port);
-		print_uint(PRINT_ANY, "peer_port", "/%hu",
+		print_hu(PRINT_ANY, "peer_port", "/%hu",
 			   p->peer_udp_port);
 		print_nl();
 
diff --git a/lib/bpf.c b/lib/bpf.c
index dfc4f4f5..c7b3ee1e 100644
--- a/lib/bpf.c
+++ b/lib/bpf.c
@@ -353,9 +353,9 @@ void bpf_print_ops(struct rtattr *bpf_ops, __u16 len)
 
 	for (i = 0; i < len; i++) {
 		open_json_object(NULL);
-		print_uint(PRINT_ANY, "code", "%hu ", ops[i].code);
-		print_uint(PRINT_ANY, "jt", "%hhu ", ops[i].jt);
-		print_uint(PRINT_ANY, "jf", "%hhu ", ops[i].jf);
+		print_hu(PRINT_ANY, "code", "%hu ", ops[i].code);
+		print_hhu(PRINT_ANY, "jt", "%hhu ", ops[i].jt);
+		print_hhu(PRINT_ANY, "jf", "%hhu ", ops[i].jf);
 		if (i == len - 1)
 			print_uint(PRINT_ANY, "k", "%u\'", ops[i].k);
 		else

From 25c6339b223f17d1603702c0c87f06b252bb4949 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 7 Jan 2019 14:29:15 -0800
Subject: [PATCH 16/55] ll_map: Add function to remove link cache entry by
 index

Add ll_drop_by_index to remove an entry from the link cache.

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/ll_map.h |  1 +
 lib/ll_map.c     | 14 ++++++++++++++
 2 files changed, 15 insertions(+)

diff --git a/include/ll_map.h b/include/ll_map.h
index 511fe00b..4de1041e 100644
--- a/include/ll_map.h
+++ b/include/ll_map.h
@@ -9,6 +9,7 @@ unsigned ll_name_to_index(const char *name);
 const char *ll_index_to_name(unsigned idx);
 int ll_index_to_type(unsigned idx);
 int ll_index_to_flags(unsigned idx);
+void ll_drop_by_index(unsigned index);
 unsigned namehash(const char *str);
 
 const char *ll_idx_n2a(unsigned int idx);
diff --git a/lib/ll_map.c b/lib/ll_map.c
index 1ab8ef07..8e8a0b1e 100644
--- a/lib/ll_map.c
+++ b/lib/ll_map.c
@@ -210,6 +210,20 @@ unsigned ll_name_to_index(const char *name)
 	return idx;
 }
 
+void ll_drop_by_index(unsigned index)
+{
+	struct ll_cache *im;
+
+	im = ll_get_by_index(index);
+	if (!im)
+		return;
+
+	hlist_del(&im->idx_hash);
+	hlist_del(&im->name_hash);
+
+	free(im);
+}
+
 void ll_init_map(struct rtnl_handle *rth)
 {
 	static int initialized;

From db1aafd883262752304064a5afc06b41417d5c84 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 13 Feb 2019 15:53:21 -0800
Subject: [PATCH 17/55] ip link: Drop cache entry on any changes

Remove any entry from the link cache when the link is modified.

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 ip/iplink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/ip/iplink.c b/ip/iplink.c
index 3a0cf459..5a3c9613 100644
--- a/ip/iplink.c
+++ b/ip/iplink.c
@@ -1083,6 +1083,9 @@ static int iplink_modify(int cmd, unsigned int flags, int argc, char **argv)
 	if (rtnl_talk(&rth, &req.n, NULL) < 0)
 		return -2;
 
+	/* remove device from cache; next use can refresh with new data */
+	ll_drop_by_index(req.i.ifi_index);
+
 	return 0;
 }
 

From 55870dfe7f8b1d14c4b52fb689f6d91cbf28a60c Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 13 Feb 2019 15:56:30 -0800
Subject: [PATCH 18/55] Improve batch and dump times by caching link lookups

ip route uses ll_name_to_index and ll_index_to_name to convert between
device names and indices. At the moment both use for the ioctl based glibc
functions if_nametoindex and if_indextoname and does not cache the result.
When using a batch file or dumping large number of routes this means the
same device lookups can be done repeatedly adding unnecessary overhead
(socket + ioctl + close for each device lookup).

Add a new function, ll_link_get, to send a netlink based RTM_GETLINK. If
successful, cache the result in idx_head and name_head so future lookups
can re-use the entry. Update ll_name_to_index and ll_index_to_name to use
ll_link_get and only fallback to the glibc functions if it fails.

With this change the time to install 720,022 routes with 2 ecmp nexthops
where the nexthop device is given is reduced from 31.4 seconds to 19.2
seconds. A dump of those routes drops from 13.3 to 2.8 seconds.

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 lib/ll_map.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 51 insertions(+), 1 deletion(-)

diff --git a/lib/ll_map.c b/lib/ll_map.c
index 8e8a0b1e..2d7b65dc 100644
--- a/lib/ll_map.c
+++ b/lib/ll_map.c
@@ -152,6 +152,48 @@ static unsigned int ll_idx_a2n(const char *name)
 	return idx;
 }
 
+static int ll_link_get(const char *name, int index)
+{
+	struct {
+		struct nlmsghdr		n;
+		struct ifinfomsg	ifm;
+		char			buf[1024];
+	} req = {
+		.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
+		.n.nlmsg_flags = NLM_F_REQUEST,
+		.n.nlmsg_type = RTM_GETLINK,
+		.ifm.ifi_index = index,
+	};
+	__u32 filt_mask = RTEXT_FILTER_VF | RTEXT_FILTER_SKIP_STATS;
+	struct rtnl_handle rth = {};
+	struct nlmsghdr *answer;
+	int rc = 0;
+
+	if (rtnl_open(&rth, 0) < 0)
+		return 0;
+
+	addattr32(&req.n, sizeof(req), IFLA_EXT_MASK, filt_mask);
+	if (name)
+		addattr_l(&req.n, sizeof(req), IFLA_IFNAME, name,
+			  strlen(name) + 1);
+
+	if (rtnl_talk(&rth, &req.n, &answer) < 0)
+		goto out;
+
+	/* add entry to cache */
+	rc  = ll_remember_index(answer, NULL);
+	if (!rc) {
+		struct ifinfomsg *ifm = NLMSG_DATA(answer);
+
+		rc = ifm->ifi_index;
+	}
+
+	free(answer);
+out:
+	rtnl_close(&rth);
+	return rc;
+}
+
 const char *ll_index_to_name(unsigned int idx)
 {
 	static char buf[IFNAMSIZ];
@@ -164,6 +206,12 @@ const char *ll_index_to_name(unsigned int idx)
 	if (im)
 		return im->name;
 
+	if (ll_link_get(NULL, idx) == idx) {
+		im = ll_get_by_index(idx);
+		if (im)
+			return im->name;
+	}
+
 	if (if_indextoname(idx, buf) == NULL)
 		snprintf(buf, IFNAMSIZ, "if%u", idx);
 
@@ -204,7 +252,9 @@ unsigned ll_name_to_index(const char *name)
 	if (im)
 		return im->index;
 
-	idx = if_nametoindex(name);
+	idx = ll_link_get(name, 0);
+	if (idx == 0)
+		idx = if_nametoindex(name);
 	if (idx == 0)
 		idx = ll_idx_a2n(name);
 	return idx;

From a985cc06bd38a174d698b04129e7ea43a91225cc Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:10 +0200
Subject: [PATCH 19/55] rdma: update uapi headers

Update rdma_netlink.h file upto kernel commit
f2a0e45f36b0 RDMA/nldev: Don't expose number of not-visible entries

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/include/uapi/rdma/rdma_netlink.h | 64 +++++++++++++++++++++------
 1 file changed, 50 insertions(+), 14 deletions(-)

diff --git a/rdma/include/uapi/rdma/rdma_netlink.h b/rdma/include/uapi/rdma/rdma_netlink.h
index 04c80ceb..5027c627 100644
--- a/rdma/include/uapi/rdma/rdma_netlink.h
+++ b/rdma/include/uapi/rdma/rdma_netlink.h
@@ -5,8 +5,7 @@
 #include <linux/types.h>
 
 enum {
-	RDMA_NL_RDMA_CM = 1,
-	RDMA_NL_IWCM,
+	RDMA_NL_IWCM = 2,
 	RDMA_NL_RSVD,
 	RDMA_NL_LS,	/* RDMA Local Services */
 	RDMA_NL_NLDEV,	/* RDMA device interface */
@@ -14,8 +13,7 @@ enum {
 };
 
 enum {
-	RDMA_NL_GROUP_CM = 1,
-	RDMA_NL_GROUP_IWPM,
+	RDMA_NL_GROUP_IWPM = 2,
 	RDMA_NL_GROUP_LS,
 	RDMA_NL_NUM_GROUPS
 };
@@ -24,15 +22,17 @@ enum {
 #define RDMA_NL_GET_OP(type) (type & ((1 << 10) - 1))
 #define RDMA_NL_GET_TYPE(client, op) ((client << 10) + op)
 
-enum {
-	RDMA_NL_RDMA_CM_ID_STATS = 0,
-	RDMA_NL_RDMA_CM_NUM_OPS
-};
+/* The minimum version that the iwpm kernel supports */
+#define IWPM_UABI_VERSION_MIN	3
 
+/* The latest version that the iwpm kernel supports */
+#define IWPM_UABI_VERSION	4
+
+/* iwarp port mapper message flags */
 enum {
-	RDMA_NL_RDMA_CM_ATTR_SRC_ADDR = 1,
-	RDMA_NL_RDMA_CM_ATTR_DST_ADDR,
-	RDMA_NL_RDMA_CM_NUM_ATTR,
+
+	/* Do not map the port for this IWPM request */
+	IWPM_FLAGS_NO_PORT_MAP = (1 << 0),
 };
 
 /* iwarp port mapper op-codes */
@@ -45,6 +45,7 @@ enum {
 	RDMA_NL_IWPM_HANDLE_ERR,
 	RDMA_NL_IWPM_MAPINFO,
 	RDMA_NL_IWPM_MAPINFO_NUM,
+	RDMA_NL_IWPM_HELLO,
 	RDMA_NL_IWPM_NUM_OPS
 };
 
@@ -83,20 +84,38 @@ enum {
 	IWPM_NLA_MANAGE_MAPPING_UNSPEC = 0,
 	IWPM_NLA_MANAGE_MAPPING_SEQ,
 	IWPM_NLA_MANAGE_ADDR,
-	IWPM_NLA_MANAGE_MAPPED_LOC_ADDR,
+	IWPM_NLA_MANAGE_FLAGS,
+	IWPM_NLA_MANAGE_MAPPING_MAX
+};
+
+enum {
+	IWPM_NLA_RMANAGE_MAPPING_UNSPEC = 0,
+	IWPM_NLA_RMANAGE_MAPPING_SEQ,
+	IWPM_NLA_RMANAGE_ADDR,
+	IWPM_NLA_RMANAGE_MAPPED_LOC_ADDR,
+	/* The following maintains bisectability of rdma-core */
+	IWPM_NLA_MANAGE_MAPPED_LOC_ADDR = IWPM_NLA_RMANAGE_MAPPED_LOC_ADDR,
 	IWPM_NLA_RMANAGE_MAPPING_ERR,
 	IWPM_NLA_RMANAGE_MAPPING_MAX
 };
 
-#define IWPM_NLA_MANAGE_MAPPING_MAX 3
-#define IWPM_NLA_QUERY_MAPPING_MAX  4
 #define IWPM_NLA_MAPINFO_SEND_MAX   3
+#define IWPM_NLA_REMOVE_MAPPING_MAX 3
 
 enum {
 	IWPM_NLA_QUERY_MAPPING_UNSPEC = 0,
 	IWPM_NLA_QUERY_MAPPING_SEQ,
 	IWPM_NLA_QUERY_LOCAL_ADDR,
 	IWPM_NLA_QUERY_REMOTE_ADDR,
+	IWPM_NLA_QUERY_FLAGS,
+	IWPM_NLA_QUERY_MAPPING_MAX,
+};
+
+enum {
+	IWPM_NLA_RQUERY_MAPPING_UNSPEC = 0,
+	IWPM_NLA_RQUERY_MAPPING_SEQ,
+	IWPM_NLA_RQUERY_LOCAL_ADDR,
+	IWPM_NLA_RQUERY_REMOTE_ADDR,
 	IWPM_NLA_RQUERY_MAPPED_LOC_ADDR,
 	IWPM_NLA_RQUERY_MAPPED_REM_ADDR,
 	IWPM_NLA_RQUERY_MAPPING_ERR,
@@ -114,6 +133,7 @@ enum {
 	IWPM_NLA_MAPINFO_UNSPEC = 0,
 	IWPM_NLA_MAPINFO_LOCAL_ADDR,
 	IWPM_NLA_MAPINFO_MAPPED_ADDR,
+	IWPM_NLA_MAPINFO_FLAGS,
 	IWPM_NLA_MAPINFO_MAX
 };
 
@@ -132,6 +152,12 @@ enum {
 	IWPM_NLA_ERR_MAX
 };
 
+enum {
+	IWPM_NLA_HELLO_UNSPEC = 0,
+	IWPM_NLA_HELLO_ABI_VERSION,
+	IWPM_NLA_HELLO_MAX
+};
+
 /*
  * Local service operations:
  *   RESOLVE - The client requests the local service to resolve a path.
@@ -430,6 +456,16 @@ enum rdma_nldev_attr {
 	RDMA_NLDEV_ATTR_DRIVER_S64,		/* s64 */
 	RDMA_NLDEV_ATTR_DRIVER_U64,		/* u64 */
 
+	/*
+	 * Indexes to get/set secific entry,
+	 * for QP use RDMA_NLDEV_ATTR_RES_LQPN
+	 */
+	RDMA_NLDEV_ATTR_RES_PDN,               /* u32 */
+	RDMA_NLDEV_ATTR_RES_CQN,               /* u32 */
+	RDMA_NLDEV_ATTR_RES_MRN,               /* u32 */
+	RDMA_NLDEV_ATTR_RES_CM_IDN,            /* u32 */
+	RDMA_NLDEV_ATTR_RES_CTXN,	       /* u32 */
+
 	/*
 	 * Always the end
 	 */

From beac6a399068159d31d919d16f28b2d030ffa0d0 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:11 +0200
Subject: [PATCH 20/55] rdma: Remove duplicated print code

There is no need to keep same print functions for
uint32_t and uint64_t, unify them into one function.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res.c | 22 +++++++---------------
 1 file changed, 7 insertions(+), 15 deletions(-)

diff --git a/rdma/res.c b/rdma/res.c
index 6b0f5fe3..87865ec8 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -808,28 +808,20 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
-static void print_key(struct rd *rd, const char *name, uint32_t val)
+static void print_key(struct rd *rd, const char *name, uint64_t val)
 {
 	if (rd->json_output)
 		jsonw_xint_field(rd->jw, name, val);
 	else
-		pr_out("%s 0x%x ", name, val);
+		pr_out("%s 0x%" PRIx64 " ", name, val);
 }
 
-static void print_iova(struct rd *rd, uint64_t val)
+static void res_print_uint(struct rd *rd, const char *name, uint64_t val)
 {
 	if (rd->json_output)
-		jsonw_xint_field(rd->jw, "iova", val);
+		jsonw_uint_field(rd->jw, name, val);
 	else
-		pr_out("iova 0x%" PRIx64 " ", val);
-}
-
-static void print_mrlen(struct rd *rd, uint64_t val)
-{
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, "mrlen", val);
-	else
-		pr_out("mrlen %" PRIu64 " ", val);
+		pr_out("%s %" PRIu64 " ", name, val);
 }
 
 static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
@@ -907,8 +899,8 @@ static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 		if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
 			print_key(rd, "lkey", lkey);
 		if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
-			print_iova(rd, iova);
-		print_mrlen(rd, mrlen);
+			print_key(rd, "iova", iova);
+		res_print_uint(rd, "mrlen", mrlen);
 		print_pid(rd, pid);
 		print_comm(rd, comm, nla_line);
 

From 1dc035865d1f0a9d82cd34e416abe1cf98acad12 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:12 +0200
Subject: [PATCH 21/55] rdma: Provide unique indexes for all visible objects

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res.c | 83 +++++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 63 insertions(+), 20 deletions(-)

diff --git a/rdma/res.c b/rdma/res.c
index 87865ec8..f941de5c 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -549,6 +549,22 @@ static int ss_ntop(struct nlattr *nla_line, char *addr_str, uint16_t *port)
 	return 0;
 }
 
+static void print_key(struct rd *rd, const char *name, uint64_t val)
+{
+	if (rd->json_output)
+		jsonw_xint_field(rd->jw, name, val);
+	else
+		pr_out("%s 0x%" PRIx64 " ", name, val);
+}
+
+static void res_print_uint(struct rd *rd, const char *name, uint64_t val)
+{
+	if (rd->json_output)
+		jsonw_uint_field(rd->jw, name, val);
+	else
+		pr_out("%s %" PRIu64 " ", name, val);
+}
+
 static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
@@ -574,6 +590,7 @@ static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 		uint32_t port = 0, pid = 0;
 		uint8_t type = 0, state;
 		uint32_t lqpn = 0, ps;
+		uint32_t cm_idn = 0;
 		char *comm = NULL;
 		int err;
 
@@ -651,6 +668,12 @@ static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 			continue;
 		}
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
+			cm_idn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN]);
+		if (rd_check_is_filtered(rd, "cm-idn", cm_idn))
+			continue;
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]) {
 			/* discard const from mnl_attr_get_str */
 			comm = (char *)mnl_attr_get_str(
@@ -669,6 +692,8 @@ static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 		print_ps(rd, ps);
 		print_pid(rd, pid);
 		print_comm(rd, comm, nla_line);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
+			res_print_uint(rd, "cm-idn", cm_idn);
 
 		if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR])
 			print_ipaddr(rd, "src-addr", src_addr_str, src_port);
@@ -743,6 +768,7 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 		char *comm = NULL;
 		uint32_t pid = 0;
 		uint8_t poll_ctx = 0;
+		uint32_t cqn = 0;
 		uint64_t users;
 		uint32_t cqe;
 		int err;
@@ -783,6 +809,12 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 			continue;
 		}
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
+			cqn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_CQN]);
+		if (rd_check_is_filtered(rd, "cqn", cqn))
+			continue;
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
 			/* discard const from mnl_attr_get_str */
 			comm = (char *)mnl_attr_get_str(
@@ -799,6 +831,9 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 		print_pid(rd, pid);
 		print_comm(rd, comm, nla_line);
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
+			res_print_uint(rd, "cqn", cqn);
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
 			free(comm);
 
@@ -808,22 +843,6 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
-static void print_key(struct rd *rd, const char *name, uint64_t val)
-{
-	if (rd->json_output)
-		jsonw_xint_field(rd->jw, name, val);
-	else
-		pr_out("%s 0x%" PRIx64 " ", name, val);
-}
-
-static void res_print_uint(struct rd *rd, const char *name, uint64_t val)
-{
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, name, val);
-	else
-		pr_out("%s %" PRIu64 " ", name, val);
-}
-
 static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
@@ -847,6 +866,7 @@ static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 		uint32_t rkey = 0, lkey = 0;
 		uint64_t iova = 0, mrlen;
 		char *comm = NULL;
+		uint32_t mrn = 0;
 		uint32_t pid = 0;
 		int err;
 
@@ -885,6 +905,12 @@ static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 			continue;
 		}
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
+			mrn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_MRN]);
+		if (rd_check_is_filtered(rd, "mrn", mrn))
+			continue;
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
 			/* discard const from mnl_attr_get_str */
 			comm = (char *)mnl_attr_get_str(
@@ -904,6 +930,9 @@ static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 		print_pid(rd, pid);
 		print_comm(rd, comm, nla_line);
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
+			res_print_uint(rd, "mrn", mrn);
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
 			free(comm);
 
@@ -936,6 +965,7 @@ static int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 		char *comm = NULL;
 		uint32_t pid = 0;
+		uint32_t pdn = 0;
 		uint64_t users;
 		int err;
 
@@ -970,6 +1000,12 @@ static int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 		if (rd_check_is_filtered(rd, "pid", pid))
 			continue;
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			pdn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+		if (rd_check_is_filtered(rd, "pdn", pdn))
+			continue;
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
 			/* discard const from mnl_attr_get_str */
 			comm = (char *)mnl_attr_get_str(
@@ -987,6 +1023,9 @@ static int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 		print_pid(rd, pid);
 		print_comm(rd, comm, nla_line);
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			res_print_uint(rd, "pdn", pdn);
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
 			free(comm);
 
@@ -1033,7 +1072,8 @@ struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "src-addr", .is_number = false },
 	{ .name = "src-port", .is_number = true },
 	{ .name = "dst-addr", .is_number = false },
-	{ .name = "dst-port", .is_number = true }
+	{ .name = "dst-port", .is_number = true },
+	{ .name = "cm-idn", .is_number = true }
 };
 
 RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false);
@@ -1043,7 +1083,8 @@ struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "dev", .is_number = false },
 	{ .name = "users", .is_number = true },
 	{ .name = "poll-ctx", .is_number = false },
-	{ .name = "pid", .is_number = true }
+	{ .name = "pid", .is_number = true },
+	{ .name = "cqn", .is_number = true }
 };
 
 RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
@@ -1054,7 +1095,8 @@ struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "rkey", .is_number = true },
 	{ .name = "lkey", .is_number = true },
 	{ .name = "mrlen", .is_number = true },
-	{ .name = "pid", .is_number = true }
+	{ .name = "pid", .is_number = true },
+	{ .name = "mrn", .is_number = true }
 };
 
 RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
@@ -1063,7 +1105,8 @@ static const
 struct filters pd_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "dev", .is_number = false },
 	{ .name = "users", .is_number = true },
-	{ .name = "pid", .is_number = true }
+	{ .name = "pid", .is_number = true },
+	{ .name = "pdn", .is_number = true }
 };
 
 RES_FUNC(res_pd, RDMA_NLDEV_CMD_RES_PD_GET, pd_valid_filters, true);

From 96f59e7fdcf8e70d13fa5a94234661633e5f71e8 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:13 +0200
Subject: [PATCH 22/55] rdma: Provide parent context index for all objects
 except CM_ID

Allow users to correlate allocated object with relevant parent

[leonro@server ~]$ rdma res show pd
dev mlx5_0 users 5 pid 0 comm [ib_core] pdn 1
dev mlx5_0 users 7 pid 0 comm [ib_ipoib] pdn 2
dev mlx5_0 users 0 pid 0 comm [mlx5_ib] pdn 3
dev mlx5_0 users 2 pid 548 comm ibv_rc_pingpong ctxn 0 pdn 4

[leonro@server ~]$ rdma res show cq cqn 0-100
dev mlx5_0 cqe 2047 users 6 poll-ctx UNBOUND_WORKQUEUE pid 0 comm [ib_core] cqn 2
dev mlx5_0 cqe 255 users 2 poll-ctx SOFTIRQ pid 0 comm [mlx5_ib] cqn 3
dev mlx5_0 cqe 511 users 1 poll-ctx DIRECT pid 0 comm [ib_ipoib] cqn 4
dev mlx5_0 cqe 255 users 1 poll-ctx DIRECT pid 0 comm [ib_ipoib] cqn 5
dev mlx5_0 cqe 255 users 0 poll-ctx SOFTIRQ pid 0 comm [mlx5_ib] cqn 6
dev mlx5_0 cqe 511 users 2 pid 548 comm ibv_rc_pingpong cqn 7 ctxn 0

[leonro@server ~]$ rdma res show mr
dev mlx5_0 mrlen 4096 pid 548 comm ibv_rc_pingpong mrn 4 pdn 0

[leonro@nps-server-14-015 ~]$ /images/leonro/src/iproute2/rdma/rdma res show qp
link mlx5_0/1 lqpn 0 type SMI state RTS sq-psn 0 pid 0 comm [ib_core]
link mlx5_0/1 lqpn 1 type GSI state RTS sq-psn 0 pid 0 comm [ib_core]
link mlx5_0/1 lqpn 7 type UD state RTS sq-psn 0 pid 0 comm [ib_core]
link mlx5_0/1 lqpn 8 type UD state RTS sq-psn 0 pid 0 comm [ib_ipoib]
link mlx5_0/1 lqpn 9 pdn 4 rqpn 0 type RC state INIT rq-psn 0 sq-psn 0 path-mig-state MIGRATED pid 548 comm ibv_rc_pingpong

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res.c | 110 +++++++++++++++++++++++++++++++++++------------------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/rdma/res.c b/rdma/res.c
index f941de5c..308f66c0 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -320,6 +320,22 @@ static char *get_task_name(uint32_t pid)
 	return comm;
 }
 
+static void print_key(struct rd *rd, const char *name, uint64_t val)
+{
+	if (rd->json_output)
+		jsonw_xint_field(rd->jw, name, val);
+	else
+		pr_out("%s 0x%" PRIx64 " ", name, val);
+}
+
+static void res_print_uint(struct rd *rd, const char *name, uint64_t val)
+{
+	if (rd->json_output)
+		jsonw_uint_field(rd->jw, name, val);
+	else
+		pr_out("%s %" PRIu64 " ", name, val);
+}
+
 static int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
@@ -343,6 +359,7 @@ static int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 		uint32_t lqpn, rqpn = 0, rq_psn = 0, sq_psn;
 		uint8_t type, state, path_mig_state = 0;
 		uint32_t port = 0, pid = 0;
+		uint32_t pdn = 0;
 		char *comm = NULL;
 		int err;
 
@@ -369,6 +386,11 @@ static int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 		if (rd_check_is_filtered(rd, "lqpn", lqpn))
 			continue;
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			pdn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+		if (rd_check_is_filtered(rd, "pdn", pdn))
+			continue;
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_RQPN]) {
 			rqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_RQPN]);
 			if (rd_check_is_filtered(rd, "rqpn", rqpn))
@@ -428,6 +450,8 @@ static int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 		print_link(rd, idx, name, port, nla_line);
 
 		print_lqpn(rd, lqpn);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			res_print_uint(rd, "pdn", pdn);
 		print_rqpn(rd, rqpn, nla_line);
 
 		print_type(rd, type);
@@ -549,22 +573,6 @@ static int ss_ntop(struct nlattr *nla_line, char *addr_str, uint16_t *port)
 	return 0;
 }
 
-static void print_key(struct rd *rd, const char *name, uint64_t val)
-{
-	if (rd->json_output)
-		jsonw_xint_field(rd->jw, name, val);
-	else
-		pr_out("%s 0x%" PRIx64 " ", name, val);
-}
-
-static void res_print_uint(struct rd *rd, const char *name, uint64_t val)
-{
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, name, val);
-	else
-		pr_out("%s %" PRIu64 " ", name, val);
-}
-
 static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
@@ -768,6 +776,7 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 		char *comm = NULL;
 		uint32_t pid = 0;
 		uint8_t poll_ctx = 0;
+		uint32_t ctxn = 0;
 		uint32_t cqn = 0;
 		uint64_t users;
 		uint32_t cqe;
@@ -815,6 +824,12 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 		if (rd_check_is_filtered(rd, "cqn", cqn))
 			continue;
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+			ctxn = mnl_attr_get_u32(
+				 nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
+		if (rd_check_is_filtered(rd, "ctxn", ctxn))
+			continue;
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
 			/* discard const from mnl_attr_get_str */
 			comm = (char *)mnl_attr_get_str(
@@ -833,6 +848,8 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 
 		if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
 			res_print_uint(rd, "cqn", cqn);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+			res_print_uint(rd, "ctxn", ctxn);
 
 		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
 			free(comm);
@@ -866,6 +883,7 @@ static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 		uint32_t rkey = 0, lkey = 0;
 		uint64_t iova = 0, mrlen;
 		char *comm = NULL;
+		uint32_t pdn = 0;
 		uint32_t mrn = 0;
 		uint32_t pid = 0;
 		int err;
@@ -911,6 +929,12 @@ static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 		if (rd_check_is_filtered(rd, "mrn", mrn))
 			continue;
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			pdn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+		if (rd_check_is_filtered(rd, "pdn", pdn))
+			continue;
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
 			/* discard const from mnl_attr_get_str */
 			comm = (char *)mnl_attr_get_str(
@@ -933,6 +957,9 @@ static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 		if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
 			res_print_uint(rd, "mrn", mrn);
 
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			res_print_uint(rd, "pdn", pdn);
+
 		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
 			free(comm);
 
@@ -964,6 +991,7 @@ static int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 		uint32_t local_dma_lkey = 0, unsafe_global_rkey = 0;
 		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 		char *comm = NULL;
+		uint32_t ctxn = 0;
 		uint32_t pid = 0;
 		uint32_t pdn = 0;
 		uint64_t users;
@@ -997,7 +1025,13 @@ static int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 			comm = get_task_name(pid);
 		}
 
-		if (rd_check_is_filtered(rd, "pid", pid))
+                if (rd_check_is_filtered(rd, "pid", pid))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+			ctxn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
+
+		if (rd_check_is_filtered(rd, "ctxn", ctxn))
 			continue;
 
 		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
@@ -1022,6 +1056,8 @@ static int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 			print_key(rd, "unsafe_global_rkey", unsafe_global_rkey);
 		print_pid(rd, pid);
 		print_comm(rd, comm, nla_line);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+			res_print_uint(rd, "ctxn", ctxn);
 
 		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
 			res_print_uint(rd, "pdn", pdn);
@@ -1038,24 +1074,18 @@ static int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
 
 static const struct
-filters qp_valid_filters[MAX_NUMBER_OF_FILTERS] = {{ .name = "link",
-						   .is_number = false },
-						   { .name = "lqpn",
-						   .is_number = true },
-						   { .name = "rqpn",
-						   .is_number = true },
-						   { .name = "pid",
-						   .is_number = true },
-						   { .name = "sq-psn",
-						   .is_number = true },
-						   { .name = "rq-psn",
-						   .is_number = true },
-						   { .name = "type",
-						   .is_number = false },
-						   { .name = "path-mig-state",
-						   .is_number = false },
-						   { .name = "state",
-						   .is_number = false } };
+filters qp_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "link", .is_number = false },
+	{ .name = "lqpn", .is_number = true },
+	{ .name = "rqpn", .is_number = true },
+	{ .name = "pid",  .is_number = true },
+	{ .name = "sq-psn", .is_number = true },
+	{ .name = "rq-psn", .is_number = true },
+	{ .name = "type", .is_number = false },
+	{ .name = "path-mig-state", .is_number = false },
+	{ .name = "state", .is_number = false },
+	{ .name = "pdn", .is_number = true },
+};
 
 RES_FUNC(res_qp,	RDMA_NLDEV_CMD_RES_QP_GET, qp_valid_filters, false);
 
@@ -1084,7 +1114,8 @@ struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "users", .is_number = true },
 	{ .name = "poll-ctx", .is_number = false },
 	{ .name = "pid", .is_number = true },
-	{ .name = "cqn", .is_number = true }
+	{ .name = "cqn", .is_number = true },
+	{ .name = "ctxn", .is_number = true }
 };
 
 RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
@@ -1096,7 +1127,8 @@ struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "lkey", .is_number = true },
 	{ .name = "mrlen", .is_number = true },
 	{ .name = "pid", .is_number = true },
-	{ .name = "mrn", .is_number = true }
+	{ .name = "mrn", .is_number = true },
+	{ .name = "pdn", .is_number = true }
 };
 
 RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
@@ -1106,7 +1138,9 @@ struct filters pd_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "dev", .is_number = false },
 	{ .name = "users", .is_number = true },
 	{ .name = "pid", .is_number = true },
-	{ .name = "pdn", .is_number = true }
+	{ .name = "ctxn", .is_number = true },
+	{ .name = "pdn", .is_number = true },
+	{ .name = "ctxn", .is_number = true }
 };
 
 RES_FUNC(res_pd, RDMA_NLDEV_CMD_RES_PD_GET, pd_valid_filters, true);

From cc6131276c52b8f090a678567ea25559c886bece Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:14 +0200
Subject: [PATCH 23/55] rdma: Move resource PD logic to separate file

Logically separate resource PD logic to separate file,
in order to make PD specific logic self-contained.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/Makefile |   2 +-
 rdma/res-pd.c | 110 ++++++++++++++++++++++++++++++++++++
 rdma/res.c    | 154 +++-----------------------------------------------
 rdma/res.h    |  55 ++++++++++++++++++
 4 files changed, 175 insertions(+), 146 deletions(-)
 create mode 100644 rdma/res-pd.c
 create mode 100644 rdma/res.h

diff --git a/rdma/Makefile b/rdma/Makefile
index 0498994f..9c2fb203 100644
--- a/rdma/Makefile
+++ b/rdma/Makefile
@@ -6,7 +6,7 @@ TARGETS :=
 ifeq ($(HAVE_MNL),y)
 CFLAGS += -I./include/uapi/
 
-RDMA_OBJ = rdma.o utils.o dev.o link.o res.o
+RDMA_OBJ = rdma.o utils.o dev.o link.o res.o res-pd.o
 
 TARGETS += rdma
 endif
diff --git a/rdma/res-pd.c b/rdma/res-pd.c
new file mode 100644
index 00000000..d879a21a
--- /dev/null
+++ b/rdma/res-pd.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * res-pd.c	RDMA tool
+ * Authors:     Leon Romanovsky <leonro@mellanox.com>
+ */
+
+#include "res.h"
+#include <inttypes.h>
+
+int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_RES_PD])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	nla_table = tb[RDMA_NLDEV_ATTR_RES_PD];
+
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		uint32_t local_dma_lkey = 0, unsafe_global_rkey = 0;
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+		char *comm = NULL;
+		uint32_t ctxn = 0;
+		uint32_t pid = 0;
+		uint32_t pdn = 0;
+		uint64_t users;
+		int err;
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (err != MNL_CB_OK)
+			return MNL_CB_ERROR;
+
+		if (!nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
+		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+			return MNL_CB_ERROR;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
+			local_dma_lkey = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY]);
+
+		users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
+		if (rd_check_is_filtered(rd, "users", users))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
+			unsafe_global_rkey = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY]);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+			pid = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+			comm = get_task_name(pid);
+		}
+
+		if (rd_check_is_filtered(rd, "pid", pid))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+			ctxn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
+
+		if (rd_check_is_filtered(rd, "ctxn", ctxn))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			pdn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+		if (rd_check_is_filtered(rd, "pdn", pdn))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+			/* discard const from mnl_attr_get_str */
+			comm = (char *)mnl_attr_get_str(
+				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+		if (rd->json_output)
+			jsonw_start_array(rd->jw);
+
+		print_dev(rd, idx, name);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
+			print_key(rd, "local_dma_lkey", local_dma_lkey);
+		print_users(rd, users);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
+			print_key(rd, "unsafe_global_rkey", unsafe_global_rkey);
+		print_pid(rd, pid);
+		print_comm(rd, comm, nla_line);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+			res_print_uint(rd, "ctxn", ctxn);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			res_print_uint(rd, "pdn", pdn);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+			free(comm);
+
+		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
+		newline(rd);
+	}
+	return MNL_CB_OK;
+}
diff --git a/rdma/res.c b/rdma/res.c
index 308f66c0..494a82e4 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -9,7 +9,7 @@
  * Authors:     Leon Romanovsky <leonro@mellanox.com>
  */
 
-#include "rdma.h"
+#include "res.h"
 #include <inttypes.h>
 
 static int res_help(struct rd *rd)
@@ -92,7 +92,7 @@ static int res_no_args_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
-static int _res_send_msg(struct rd *rd, uint32_t command, mnl_cb_t callback)
+int _res_send_msg(struct rd *rd, uint32_t command, mnl_cb_t callback)
 {
 	uint32_t flags = NLM_F_REQUEST | NLM_F_ACK;
 	uint32_t seq;
@@ -119,27 +119,6 @@ static int _res_send_msg(struct rd *rd, uint32_t command, mnl_cb_t callback)
 	return ret;
 }
 
-#define RES_FUNC(name, command, valid_filters, strict_port) \
-	static int _##name(struct rd *rd)\
-	{ \
-		return _res_send_msg(rd, command, name##_parse_cb); \
-	} \
-	static int name(struct rd *rd) \
-	{\
-		int ret = rd_build_filter(rd, valid_filters); \
-		if (ret) \
-			return ret; \
-		if ((uintptr_t)valid_filters != (uintptr_t)NULL) { \
-			ret = rd_set_arg_to_devname(rd); \
-			if (ret) \
-				return ret;\
-		} \
-		if (strict_port) \
-			return rd_exec_dev(rd, _##name); \
-		else \
-			return rd_exec_link(rd, _##name, strict_port); \
-	}
-
 static const char *path_mig_to_str(uint8_t idx)
 {
 	static const char * const path_mig_str[] = { "MIGRATED",
@@ -244,7 +223,7 @@ static void print_pathmig(struct rd *rd, uint32_t val,
 		pr_out("path-mig-state %s ", path_mig_to_str(val));
 }
 
-static void print_pid(struct rd *rd, uint32_t val)
+void print_pid(struct rd *rd, uint32_t val)
 {
 	if (rd->json_output)
 		jsonw_uint_field(rd->jw, "pid", val);
@@ -252,8 +231,7 @@ static void print_pid(struct rd *rd, uint32_t val)
 		pr_out("pid %u ", val);
 }
 
-static void print_comm(struct rd *rd, const char *str,
-		       struct nlattr **nla_line)
+void print_comm(struct rd *rd, const char *str, struct nlattr **nla_line)
 {
 	char tmp[18];
 
@@ -271,7 +249,7 @@ static void print_comm(struct rd *rd, const char *str,
 	pr_out("comm %s ", tmp);
 }
 
-static void print_dev(struct rd *rd, uint32_t idx, const char *name)
+void print_dev(struct rd *rd, uint32_t idx, const char *name)
 {
 	if (rd->json_output) {
 		jsonw_uint_field(rd->jw, "ifindex", idx);
@@ -299,7 +277,7 @@ static void print_link(struct rd *rd, uint32_t idx, const char *name,
 	}
 }
 
-static char *get_task_name(uint32_t pid)
+char *get_task_name(uint32_t pid)
 {
 	char *comm;
 	FILE *f;
@@ -320,7 +298,7 @@ static char *get_task_name(uint32_t pid)
 	return comm;
 }
 
-static void print_key(struct rd *rd, const char *name, uint64_t val)
+void print_key(struct rd *rd, const char *name, uint64_t val)
 {
 	if (rd->json_output)
 		jsonw_xint_field(rd->jw, name, val);
@@ -328,7 +306,7 @@ static void print_key(struct rd *rd, const char *name, uint64_t val)
 		pr_out("%s 0x%" PRIx64 " ", name, val);
 }
 
-static void res_print_uint(struct rd *rd, const char *name, uint64_t val)
+void res_print_uint(struct rd *rd, const char *name, uint64_t val)
 {
 	if (rd->json_output)
 		jsonw_uint_field(rd->jw, name, val);
@@ -725,7 +703,7 @@ static void print_cqe(struct rd *rd, uint32_t val)
 		pr_out("cqe %u ", val);
 }
 
-static void print_users(struct rd *rd, uint64_t val)
+void print_users(struct rd *rd, uint64_t val)
 {
 	if (rd->json_output)
 		jsonw_uint_field(rd->jw, "users", val);
@@ -969,108 +947,6 @@ static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
-static int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
-{
-	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
-	struct nlattr *nla_table, *nla_entry;
-	struct rd *rd = data;
-	const char *name;
-	uint32_t idx;
-
-	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
-	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
-	    !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
-	    !tb[RDMA_NLDEV_ATTR_RES_PD])
-		return MNL_CB_ERROR;
-
-	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
-	idx =  mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
-	nla_table = tb[RDMA_NLDEV_ATTR_RES_PD];
-
-	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		uint32_t local_dma_lkey = 0, unsafe_global_rkey = 0;
-		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		char *comm = NULL;
-		uint32_t ctxn = 0;
-		uint32_t pid = 0;
-		uint32_t pdn = 0;
-		uint64_t users;
-		int err;
-
-		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-		if (err != MNL_CB_OK)
-			return MNL_CB_ERROR;
-
-		if (!nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
-		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
-		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
-			return MNL_CB_ERROR;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
-			local_dma_lkey = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY]);
-
-		users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
-		if (rd_check_is_filtered(rd, "users", users))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
-			unsafe_global_rkey = mnl_attr_get_u32(
-			      nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY]);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
-			pid = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
-			comm = get_task_name(pid);
-		}
-
-                if (rd_check_is_filtered(rd, "pid", pid))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
-			ctxn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
-
-		if (rd_check_is_filtered(rd, "ctxn", ctxn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			pdn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
-		if (rd_check_is_filtered(rd, "pdn", pdn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
-			/* discard const from mnl_attr_get_str */
-			comm = (char *)mnl_attr_get_str(
-				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
-
-		if (rd->json_output)
-			jsonw_start_array(rd->jw);
-
-		print_dev(rd, idx, name);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
-			print_key(rd, "local_dma_lkey", local_dma_lkey);
-		print_users(rd, users);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
-			print_key(rd, "unsafe_global_rkey", unsafe_global_rkey);
-		print_pid(rd, pid);
-		print_comm(rd, comm, nla_line);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
-			res_print_uint(rd, "ctxn", ctxn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			res_print_uint(rd, "pdn", pdn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
-			free(comm);
-
-		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
-		newline(rd);
-	}
-	return MNL_CB_OK;
-}
-
 RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
 
 static const struct
@@ -1133,18 +1009,6 @@ struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
 
-static const
-struct filters pd_valid_filters[MAX_NUMBER_OF_FILTERS] = {
-	{ .name = "dev", .is_number = false },
-	{ .name = "users", .is_number = true },
-	{ .name = "pid", .is_number = true },
-	{ .name = "ctxn", .is_number = true },
-	{ .name = "pdn", .is_number = true },
-	{ .name = "ctxn", .is_number = true }
-};
-
-RES_FUNC(res_pd, RDMA_NLDEV_CMD_RES_PD_GET, pd_valid_filters, true);
-
 static int res_show(struct rd *rd)
 {
 	const struct rd_cmd cmds[] = {
diff --git a/rdma/res.h b/rdma/res.h
new file mode 100644
index 00000000..dd01b803
--- /dev/null
+++ b/rdma/res.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * res.h	RDMA tool
+ * Authors:     Leon Romanovsky <leonro@mellanox.com>
+ */
+#ifndef _RDMA_TOOL_RES_H_
+#define _RDMA_TOOL_RES_H_
+
+#include "rdma.h"
+
+int _res_send_msg(struct rd *rd, uint32_t command, mnl_cb_t callback);
+int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data);
+
+#define RES_FUNC(name, command, valid_filters, strict_port) \
+	static inline int _##name(struct rd *rd)\
+	{ \
+		return _res_send_msg(rd, command, name##_parse_cb); \
+	} \
+	static inline int name(struct rd *rd) \
+	{\
+		int ret = rd_build_filter(rd, valid_filters); \
+		if (ret) \
+			return ret; \
+		if ((uintptr_t)valid_filters != (uintptr_t)NULL) { \
+			ret = rd_set_arg_to_devname(rd); \
+			if (ret) \
+				return ret;\
+		} \
+		if (strict_port) \
+			return rd_exec_dev(rd, _##name); \
+		else \
+			return rd_exec_link(rd, _##name, strict_port); \
+	}
+
+static const
+struct filters pd_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "dev", .is_number = false },
+	{ .name = "users", .is_number = true },
+	{ .name = "pid", .is_number = true },
+	{ .name = "ctxn", .is_number = true },
+	{ .name = "pdn", .is_number = true },
+	{ .name = "ctxn", .is_number = true }
+};
+
+RES_FUNC(res_pd, RDMA_NLDEV_CMD_RES_PD_GET, pd_valid_filters, true);
+
+char *get_task_name(uint32_t pid);
+void print_dev(struct rd *rd, uint32_t idx, const char *name);
+void print_users(struct rd *rd, uint64_t val);
+void print_key(struct rd *rd, const char *name, uint64_t val);
+void res_print_uint(struct rd *rd, const char *name, uint64_t val);
+void print_pid(struct rd *rd, uint32_t val);
+void print_comm(struct rd *rd, const char *str, struct nlattr **nla_line);
+
+#endif /* _RDMA_TOOL_RES_H_ */

From 42ed283e4a90cb1d0c8c63368aa4920fca32bcb5 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:15 +0200
Subject: [PATCH 24/55] rdma: Refactor out resource MR logic to separate file

Logically separate resource MR logic to separate file,
in order to make MR specific logic self-contained.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/Makefile |   2 +-
 rdma/res-mr.c | 117 +++++++++++++++++++++++++++++++++++++++++++++++
 rdma/res.c    | 122 --------------------------------------------------
 rdma/res.h    |  14 ++++++
 4 files changed, 132 insertions(+), 123 deletions(-)
 create mode 100644 rdma/res-mr.c

diff --git a/rdma/Makefile b/rdma/Makefile
index 9c2fb203..0b4e1eef 100644
--- a/rdma/Makefile
+++ b/rdma/Makefile
@@ -6,7 +6,7 @@ TARGETS :=
 ifeq ($(HAVE_MNL),y)
 CFLAGS += -I./include/uapi/
 
-RDMA_OBJ = rdma.o utils.o dev.o link.o res.o res-pd.o
+RDMA_OBJ = rdma.o utils.o dev.o link.o res.o res-pd.o res-mr.o
 
 TARGETS += rdma
 endif
diff --git a/rdma/res-mr.c b/rdma/res-mr.c
new file mode 100644
index 00000000..dae5def2
--- /dev/null
+++ b/rdma/res-mr.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * res-mr.c	RDMA tool
+ * Authors:     Leon Romanovsky <leonro@mellanox.com>
+ */
+
+#include "res.h"
+#include <inttypes.h>
+
+int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_RES_MR])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	nla_table = tb[RDMA_NLDEV_ATTR_RES_MR];
+
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+		uint32_t rkey = 0, lkey = 0;
+		uint64_t iova = 0, mrlen;
+		char *comm = NULL;
+		uint32_t pdn = 0;
+		uint32_t mrn = 0;
+		uint32_t pid = 0;
+		int err;
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (err != MNL_CB_OK)
+			return MNL_CB_ERROR;
+
+		if (!nla_line[RDMA_NLDEV_ATTR_RES_MRLEN] ||
+		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+			return MNL_CB_ERROR;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
+			rkey = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_RKEY]);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
+			lkey = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_LKEY]);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
+			iova = mnl_attr_get_u64(
+				nla_line[RDMA_NLDEV_ATTR_RES_IOVA]);
+
+		mrlen = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_MRLEN]);
+		if (rd_check_is_filtered(rd, "mrlen", mrlen))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+			pid = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+			comm = get_task_name(pid);
+		}
+
+		if (rd_check_is_filtered(rd, "pid", pid)) {
+			free(comm);
+			continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
+			mrn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_MRN]);
+		if (rd_check_is_filtered(rd, "mrn", mrn))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			pdn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+		if (rd_check_is_filtered(rd, "pdn", pdn))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+			/* discard const from mnl_attr_get_str */
+			comm = (char *)mnl_attr_get_str(
+				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+		if (rd->json_output)
+			jsonw_start_array(rd->jw);
+
+		print_dev(rd, idx, name);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
+			print_key(rd, "rkey", rkey);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
+			print_key(rd, "lkey", lkey);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
+			print_key(rd, "iova", iova);
+		res_print_uint(rd, "mrlen", mrlen);
+		print_pid(rd, pid);
+		print_comm(rd, comm, nla_line);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
+			res_print_uint(rd, "mrn", mrn);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			res_print_uint(rd, "pdn", pdn);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+			free(comm);
+
+		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
+		newline(rd);
+	}
+	return MNL_CB_OK;
+}
+
diff --git a/rdma/res.c b/rdma/res.c
index 494a82e4..1de8c797 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -838,115 +838,6 @@ static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
-static int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
-{
-	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
-	struct nlattr *nla_table, *nla_entry;
-	struct rd *rd = data;
-	const char *name;
-	uint32_t idx;
-
-	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
-	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
-	    !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
-	    !tb[RDMA_NLDEV_ATTR_RES_MR])
-		return MNL_CB_ERROR;
-
-	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
-	idx =  mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
-	nla_table = tb[RDMA_NLDEV_ATTR_RES_MR];
-
-	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		uint32_t rkey = 0, lkey = 0;
-		uint64_t iova = 0, mrlen;
-		char *comm = NULL;
-		uint32_t pdn = 0;
-		uint32_t mrn = 0;
-		uint32_t pid = 0;
-		int err;
-
-		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-		if (err != MNL_CB_OK)
-			return MNL_CB_ERROR;
-
-		if (!nla_line[RDMA_NLDEV_ATTR_RES_MRLEN] ||
-		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
-		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
-			return MNL_CB_ERROR;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
-			rkey = mnl_attr_get_u32(
-					nla_line[RDMA_NLDEV_ATTR_RES_RKEY]);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
-			lkey = mnl_attr_get_u32(
-					nla_line[RDMA_NLDEV_ATTR_RES_LKEY]);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
-			iova = mnl_attr_get_u64(
-					nla_line[RDMA_NLDEV_ATTR_RES_IOVA]);
-
-		mrlen = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_MRLEN]);
-		if (rd_check_is_filtered(rd, "mrlen", mrlen))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
-			pid = mnl_attr_get_u32(
-					nla_line[RDMA_NLDEV_ATTR_RES_PID]);
-			comm = get_task_name(pid);
-		}
-
-		if (rd_check_is_filtered(rd, "pid", pid)) {
-			free(comm);
-			continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
-			mrn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_MRN]);
-		if (rd_check_is_filtered(rd, "mrn", mrn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			pdn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
-		if (rd_check_is_filtered(rd, "pdn", pdn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
-			/* discard const from mnl_attr_get_str */
-			comm = (char *)mnl_attr_get_str(
-				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
-
-		if (rd->json_output)
-			jsonw_start_array(rd->jw);
-
-		print_dev(rd, idx, name);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
-			print_key(rd, "rkey", rkey);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
-			print_key(rd, "lkey", lkey);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
-			print_key(rd, "iova", iova);
-		res_print_uint(rd, "mrlen", mrlen);
-		print_pid(rd, pid);
-		print_comm(rd, comm, nla_line);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
-			res_print_uint(rd, "mrn", mrn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			res_print_uint(rd, "pdn", pdn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
-			free(comm);
-
-		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
-		newline(rd);
-	}
-	return MNL_CB_OK;
-}
-
 RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
 
 static const struct
@@ -996,19 +887,6 @@ struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
 
-static const
-struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
-	{ .name = "dev", .is_number = false },
-	{ .name = "rkey", .is_number = true },
-	{ .name = "lkey", .is_number = true },
-	{ .name = "mrlen", .is_number = true },
-	{ .name = "pid", .is_number = true },
-	{ .name = "mrn", .is_number = true },
-	{ .name = "pdn", .is_number = true }
-};
-
-RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
-
 static int res_show(struct rd *rd)
 {
 	const struct rd_cmd cmds[] = {
diff --git a/rdma/res.h b/rdma/res.h
index dd01b803..e3619773 100644
--- a/rdma/res.h
+++ b/rdma/res.h
@@ -10,6 +10,7 @@
 
 int _res_send_msg(struct rd *rd, uint32_t command, mnl_cb_t callback);
 int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data);
 
 #define RES_FUNC(name, command, valid_filters, strict_port) \
 	static inline int _##name(struct rd *rd)\
@@ -44,6 +45,19 @@ struct filters pd_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_pd, RDMA_NLDEV_CMD_RES_PD_GET, pd_valid_filters, true);
 
+static const
+struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "dev", .is_number = false },
+	{ .name = "rkey", .is_number = true },
+	{ .name = "lkey", .is_number = true },
+	{ .name = "mrlen", .is_number = true },
+	{ .name = "pid", .is_number = true },
+	{ .name = "mrn", .is_number = true },
+	{ .name = "pdn", .is_number = true }
+};
+
+RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
+
 char *get_task_name(uint32_t pid);
 void print_dev(struct rd *rd, uint32_t idx, const char *name);
 void print_users(struct rd *rd, uint64_t val);

From fcdd2e0c68f2589e5d5c325f07f0e38afddbab6c Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:16 +0200
Subject: [PATCH 25/55] rdma: Move out resource CQ logic to separate file

Logically separate resource CQ logic to separate file,
in order to make CQ specific logic self-contained.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/Makefile |   2 +-
 rdma/res-cq.c | 143 ++++++++++++++++++++++++++++++++++++++++++++++++
 rdma/res.c    | 147 --------------------------------------------------
 rdma/res.h    |  13 +++++
 4 files changed, 157 insertions(+), 148 deletions(-)
 create mode 100644 rdma/res-cq.c

diff --git a/rdma/Makefile b/rdma/Makefile
index 0b4e1eef..e32ccd18 100644
--- a/rdma/Makefile
+++ b/rdma/Makefile
@@ -6,7 +6,7 @@ TARGETS :=
 ifeq ($(HAVE_MNL),y)
 CFLAGS += -I./include/uapi/
 
-RDMA_OBJ = rdma.o utils.o dev.o link.o res.o res-pd.o res-mr.o
+RDMA_OBJ = rdma.o utils.o dev.o link.o res.o res-pd.o res-mr.o res-cq.o
 
 TARGETS += rdma
 endif
diff --git a/rdma/res-cq.c b/rdma/res-cq.c
new file mode 100644
index 00000000..fbfe593b
--- /dev/null
+++ b/rdma/res-cq.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * res-cq.c	RDMA tool
+ * Authors:     Leon Romanovsky <leonro@mellanox.com>
+ */
+
+#include "res.h"
+#include <inttypes.h>
+
+static void print_cqe(struct rd *rd, uint32_t val)
+{
+	if (rd->json_output)
+		jsonw_uint_field(rd->jw, "cqe", val);
+	else
+		pr_out("cqe %u ", val);
+}
+
+static const char *poll_ctx_to_str(uint8_t idx)
+{
+	static const char * const cm_id_states_str[] = {
+		"DIRECT", "SOFTIRQ", "WORKQUEUE", "UNBOUND_WORKQUEUE"};
+
+	if (idx < ARRAY_SIZE(cm_id_states_str))
+		return cm_id_states_str[idx];
+	return "UNKNOWN";
+}
+
+static void print_poll_ctx(struct rd *rd, uint8_t poll_ctx)
+{
+	if (rd->json_output) {
+		jsonw_string_field(rd->jw, "poll-ctx",
+				   poll_ctx_to_str(poll_ctx));
+		return;
+	}
+	pr_out("poll-ctx %s ", poll_ctx_to_str(poll_ctx));
+}
+
+int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_RES_CQ])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	nla_table = tb[RDMA_NLDEV_ATTR_RES_CQ];
+
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+		char *comm = NULL;
+		uint32_t pid = 0;
+		uint8_t poll_ctx = 0;
+		uint32_t ctxn = 0;
+		uint32_t cqn = 0;
+		uint64_t users;
+		uint32_t cqe;
+		int err;
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (err != MNL_CB_OK)
+			return MNL_CB_ERROR;
+
+		if (!nla_line[RDMA_NLDEV_ATTR_RES_CQE] ||
+		    !nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
+		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+			return MNL_CB_ERROR;
+		}
+
+		cqe = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CQE]);
+
+		users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
+		if (rd_check_is_filtered(rd, "users", users))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]) {
+			poll_ctx = mnl_attr_get_u8(
+				nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]);
+			if (rd_check_is_string_filtered(
+				    rd, "poll-ctx", poll_ctx_to_str(poll_ctx)))
+				continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+			pid = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+			comm = get_task_name(pid);
+		}
+
+		if (rd_check_is_filtered(rd, "pid", pid)) {
+			free(comm);
+			continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
+			cqn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_CQN]);
+		if (rd_check_is_filtered(rd, "cqn", cqn))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+			ctxn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
+		if (rd_check_is_filtered(rd, "ctxn", ctxn))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+			/* discard const from mnl_attr_get_str */
+			comm = (char *)mnl_attr_get_str(
+				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+		if (rd->json_output)
+			jsonw_start_array(rd->jw);
+
+		print_dev(rd, idx, name);
+		print_cqe(rd, cqe);
+		print_users(rd, users);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX])
+			print_poll_ctx(rd, poll_ctx);
+		print_pid(rd, pid);
+		print_comm(rd, comm, nla_line);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
+			res_print_uint(rd, "cqn", cqn);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+			res_print_uint(rd, "ctxn", ctxn);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+			free(comm);
+
+		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
+		newline(rd);
+	}
+	return MNL_CB_OK;
+}
+
diff --git a/rdma/res.c b/rdma/res.c
index 1de8c797..7956882e 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -695,14 +695,6 @@ static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
-static void print_cqe(struct rd *rd, uint32_t val)
-{
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, "cqe", val);
-	else
-		pr_out("cqe %u ", val);
-}
-
 void print_users(struct rd *rd, uint64_t val)
 {
 	if (rd->json_output)
@@ -711,133 +703,6 @@ void print_users(struct rd *rd, uint64_t val)
 		pr_out("users %" PRIu64 " ", val);
 }
 
-static const char *poll_ctx_to_str(uint8_t idx)
-{
-	static const char * const cm_id_states_str[] = {
-		"DIRECT", "SOFTIRQ", "WORKQUEUE", "UNBOUND_WORKQUEUE"};
-
-	if (idx < ARRAY_SIZE(cm_id_states_str))
-		return cm_id_states_str[idx];
-	return "UNKNOWN";
-}
-
-static void print_poll_ctx(struct rd *rd, uint8_t poll_ctx)
-{
-	if (rd->json_output) {
-		jsonw_string_field(rd->jw, "poll-ctx",
-				   poll_ctx_to_str(poll_ctx));
-		return;
-	}
-	pr_out("poll-ctx %s ", poll_ctx_to_str(poll_ctx));
-}
-
-static int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
-{
-	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
-	struct nlattr *nla_table, *nla_entry;
-	struct rd *rd = data;
-	const char *name;
-	uint32_t idx;
-
-	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
-	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
-	    !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
-	    !tb[RDMA_NLDEV_ATTR_RES_CQ])
-		return MNL_CB_ERROR;
-
-	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
-	idx =  mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
-	nla_table = tb[RDMA_NLDEV_ATTR_RES_CQ];
-
-	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		char *comm = NULL;
-		uint32_t pid = 0;
-		uint8_t poll_ctx = 0;
-		uint32_t ctxn = 0;
-		uint32_t cqn = 0;
-		uint64_t users;
-		uint32_t cqe;
-		int err;
-
-		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-		if (err != MNL_CB_OK)
-			return MNL_CB_ERROR;
-
-		if (!nla_line[RDMA_NLDEV_ATTR_RES_CQE] ||
-		    !nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
-		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
-		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
-			return MNL_CB_ERROR;
-		}
-
-		cqe = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CQE]);
-
-		users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
-		if (rd_check_is_filtered(rd, "users", users))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]) {
-			poll_ctx = mnl_attr_get_u8(
-					nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]);
-			if (rd_check_is_string_filtered(rd, "poll-ctx",
-						poll_ctx_to_str(poll_ctx)))
-				continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
-			pid = mnl_attr_get_u32(
-					nla_line[RDMA_NLDEV_ATTR_RES_PID]);
-			comm = get_task_name(pid);
-		}
-
-		if (rd_check_is_filtered(rd, "pid", pid)) {
-			free(comm);
-			continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
-			cqn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_CQN]);
-		if (rd_check_is_filtered(rd, "cqn", cqn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
-			ctxn = mnl_attr_get_u32(
-				 nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
-		if (rd_check_is_filtered(rd, "ctxn", ctxn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
-			/* discard const from mnl_attr_get_str */
-			comm = (char *)mnl_attr_get_str(
-				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
-
-		if (rd->json_output)
-			jsonw_start_array(rd->jw);
-
-		print_dev(rd, idx, name);
-		print_cqe(rd, cqe);
-		print_users(rd, users);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX])
-			print_poll_ctx(rd, poll_ctx);
-		print_pid(rd, pid);
-		print_comm(rd, comm, nla_line);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
-			res_print_uint(rd, "cqn", cqn);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
-			res_print_uint(rd, "ctxn", ctxn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
-			free(comm);
-
-		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
-		newline(rd);
-	}
-	return MNL_CB_OK;
-}
-
 RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
 
 static const struct
@@ -875,18 +740,6 @@ struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false);
 
-static const
-struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
-	{ .name = "dev", .is_number = false },
-	{ .name = "users", .is_number = true },
-	{ .name = "poll-ctx", .is_number = false },
-	{ .name = "pid", .is_number = true },
-	{ .name = "cqn", .is_number = true },
-	{ .name = "ctxn", .is_number = true }
-};
-
-RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
-
 static int res_show(struct rd *rd)
 {
 	const struct rd_cmd cmds[] = {
diff --git a/rdma/res.h b/rdma/res.h
index e3619773..19f0d420 100644
--- a/rdma/res.h
+++ b/rdma/res.h
@@ -11,6 +11,7 @@
 int _res_send_msg(struct rd *rd, uint32_t command, mnl_cb_t callback);
 int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data);
 int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data);
 
 #define RES_FUNC(name, command, valid_filters, strict_port) \
 	static inline int _##name(struct rd *rd)\
@@ -58,6 +59,18 @@ struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
 
+static const
+struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "dev", .is_number = false },
+	{ .name = "users", .is_number = true },
+	{ .name = "poll-ctx", .is_number = false },
+	{ .name = "pid", .is_number = true },
+	{ .name = "cqn", .is_number = true },
+	{ .name = "ctxn", .is_number = true }
+};
+
+RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
+
 char *get_task_name(uint32_t pid);
 void print_dev(struct rd *rd, uint32_t idx, const char *name);
 void print_users(struct rd *rd, uint64_t val);

From 438fac3a250e68895bb8cb3e3be942ffe4e7cb0f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:17 +0200
Subject: [PATCH 26/55] rdma: Move out resource CM-ID logic to separate file

Logically separate resource CM-ID logic to separate file,
in order to make CM-ID specific logic self-contained.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/Makefile   |   3 +-
 rdma/res-cmid.c | 252 ++++++++++++++++++++++++++++++++++++++++++++
 rdma/res.c      | 271 +-----------------------------------------------
 rdma/res.h      |  24 +++++
 4 files changed, 282 insertions(+), 268 deletions(-)
 create mode 100644 rdma/res-cmid.c

diff --git a/rdma/Makefile b/rdma/Makefile
index e32ccd18..ef240404 100644
--- a/rdma/Makefile
+++ b/rdma/Makefile
@@ -6,7 +6,8 @@ TARGETS :=
 ifeq ($(HAVE_MNL),y)
 CFLAGS += -I./include/uapi/
 
-RDMA_OBJ = rdma.o utils.o dev.o link.o res.o res-pd.o res-mr.o res-cq.o
+RDMA_OBJ = rdma.o utils.o dev.o link.o res.o res-pd.o res-mr.o res-cq.o \
+	   res-cmid.o
 
 TARGETS += rdma
 endif
diff --git a/rdma/res-cmid.c b/rdma/res-cmid.c
new file mode 100644
index 00000000..b63634a3
--- /dev/null
+++ b/rdma/res-cmid.c
@@ -0,0 +1,252 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * res-cmid.c	RDMA tool
+ * Authors:     Leon Romanovsky <leonro@mellanox.com>
+ */
+
+#include "res.h"
+#include <inttypes.h>
+
+static void print_qp_type(struct rd *rd, uint32_t val)
+{
+	if (rd->json_output)
+		jsonw_string_field(rd->jw, "qp-type", qp_types_to_str(val));
+	else
+		pr_out("qp-type %s ", qp_types_to_str(val));
+}
+
+static const char *cm_id_state_to_str(uint8_t idx)
+{
+	static const char *const cm_id_states_str[] = {
+		"IDLE",		  "ADDR_QUERY",     "ADDR_RESOLVED",
+		"ROUTE_QUERY",    "ROUTE_RESOLVED", "CONNECT",
+		"DISCONNECT",     "ADDR_BOUND",     "LISTEN",
+		"DEVICE_REMOVAL", "DESTROYING"
+	};
+
+	if (idx < ARRAY_SIZE(cm_id_states_str))
+		return cm_id_states_str[idx];
+	return "UNKNOWN";
+}
+
+static const char *cm_id_ps_to_str(uint32_t ps)
+{
+	switch (ps) {
+	case RDMA_PS_IPOIB:
+		return "IPoIB";
+	case RDMA_PS_IB:
+		return "IPoIB";
+	case RDMA_PS_TCP:
+		return "TCP";
+	case RDMA_PS_UDP:
+		return "UDP";
+	default:
+		return "---";
+	}
+}
+
+static void print_cm_id_state(struct rd *rd, uint8_t state)
+{
+	if (rd->json_output) {
+		jsonw_string_field(rd->jw, "state", cm_id_state_to_str(state));
+		return;
+	}
+	pr_out("state %s ", cm_id_state_to_str(state));
+}
+
+static void print_ps(struct rd *rd, uint32_t ps)
+{
+	if (rd->json_output) {
+		jsonw_string_field(rd->jw, "ps", cm_id_ps_to_str(ps));
+		return;
+	}
+	pr_out("ps %s ", cm_id_ps_to_str(ps));
+}
+
+static void print_ipaddr(struct rd *rd, const char *key, char *addrstr,
+			 uint16_t port)
+{
+	if (rd->json_output) {
+		int name_size = INET6_ADDRSTRLEN + strlen(":65535");
+		char json_name[name_size];
+
+		snprintf(json_name, name_size, "%s:%u", addrstr, port);
+		jsonw_string_field(rd->jw, key, json_name);
+		return;
+	}
+	pr_out("%s %s:%u ", key, addrstr, port);
+}
+
+static int ss_ntop(struct nlattr *nla_line, char *addr_str, uint16_t *port)
+{
+	struct __kernel_sockaddr_storage *addr;
+
+	addr = (struct __kernel_sockaddr_storage *)mnl_attr_get_payload(
+		nla_line);
+	switch (addr->ss_family) {
+	case AF_INET: {
+		struct sockaddr_in *sin = (struct sockaddr_in *)addr;
+
+		if (!inet_ntop(AF_INET, (const void *)&sin->sin_addr, addr_str,
+			       INET6_ADDRSTRLEN))
+			return -EINVAL;
+		*port = ntohs(sin->sin_port);
+		break;
+	}
+	case AF_INET6: {
+		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
+
+		if (!inet_ntop(AF_INET6, (const void *)&sin6->sin6_addr,
+			       addr_str, INET6_ADDRSTRLEN))
+			return -EINVAL;
+		*port = ntohs(sin6->sin6_port);
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	const char *name;
+	int idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_RES_CM_ID])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	nla_table = tb[RDMA_NLDEV_ATTR_RES_CM_ID];
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+		char src_addr_str[INET6_ADDRSTRLEN];
+		char dst_addr_str[INET6_ADDRSTRLEN];
+		uint16_t src_port, dst_port;
+		uint32_t port = 0, pid = 0;
+		uint8_t type = 0, state;
+		uint32_t lqpn = 0, ps;
+		uint32_t cm_idn = 0;
+		char *comm = NULL;
+		int err;
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (err != MNL_CB_OK)
+			return -EINVAL;
+
+		if (!nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
+		    !nla_line[RDMA_NLDEV_ATTR_RES_PS] ||
+		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+			return MNL_CB_ERROR;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
+			port = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
+
+		if (port && port != rd->port_idx)
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN]) {
+			lqpn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
+			if (rd_check_is_filtered(rd, "lqpn", lqpn))
+				continue;
+		}
+		if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE]) {
+			type = mnl_attr_get_u8(
+				nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
+			if (rd_check_is_string_filtered(rd, "qp-type",
+							qp_types_to_str(type)))
+				continue;
+		}
+
+		ps = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PS]);
+		if (rd_check_is_string_filtered(rd, "ps", cm_id_ps_to_str(ps)))
+			continue;
+
+		state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
+		if (rd_check_is_string_filtered(rd, "state",
+						cm_id_state_to_str(state)))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR]) {
+			if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR],
+				    src_addr_str, &src_port))
+				continue;
+			if (rd_check_is_string_filtered(rd, "src-addr",
+							src_addr_str))
+				continue;
+			if (rd_check_is_filtered(rd, "src-port", src_port))
+				continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR]) {
+			if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR],
+				    dst_addr_str, &dst_port))
+				continue;
+			if (rd_check_is_string_filtered(rd, "dst-addr",
+							dst_addr_str))
+				continue;
+			if (rd_check_is_filtered(rd, "dst-port", dst_port))
+				continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+			pid = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+			comm = get_task_name(pid);
+		}
+
+		if (rd_check_is_filtered(rd, "pid", pid)) {
+			free(comm);
+			continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
+			cm_idn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN]);
+		if (rd_check_is_filtered(rd, "cm-idn", cm_idn))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]) {
+			/* discard const from mnl_attr_get_str */
+			comm = (char *)mnl_attr_get_str(
+				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+		}
+
+		if (rd->json_output)
+			jsonw_start_array(rd->jw);
+
+		print_link(rd, idx, name, port, nla_line);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN])
+			print_lqpn(rd, lqpn);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE])
+			print_qp_type(rd, type);
+		print_cm_id_state(rd, state);
+		print_ps(rd, ps);
+		print_pid(rd, pid);
+		print_comm(rd, comm, nla_line);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
+			res_print_uint(rd, "cm-idn", cm_idn);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR])
+			print_ipaddr(rd, "src-addr", src_addr_str, src_port);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR])
+			print_ipaddr(rd, "dst-addr", dst_addr_str, dst_port);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+			free(comm);
+
+		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
+		newline(rd);
+	}
+	return MNL_CB_OK;
+}
diff --git a/rdma/res.c b/rdma/res.c
index 7956882e..d5ae60e1 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -140,7 +140,7 @@ static const char *qp_states_to_str(uint8_t idx)
 	return "UNKNOWN";
 }
 
-static const char *qp_types_to_str(uint8_t idx)
+const char *qp_types_to_str(uint8_t idx)
 {
 	static const char * const qp_types_str[] = { "SMI", "GSI", "RC",
 						     "UC", "UD", "RAW_IPV6",
@@ -153,7 +153,7 @@ static const char *qp_types_to_str(uint8_t idx)
 	return "UNKNOWN";
 }
 
-static void print_lqpn(struct rd *rd, uint32_t val)
+void print_lqpn(struct rd *rd, uint32_t val)
 {
 	if (rd->json_output)
 		jsonw_uint_field(rd->jw, "lqpn", val);
@@ -259,8 +259,8 @@ void print_dev(struct rd *rd, uint32_t idx, const char *name)
 	}
 }
 
-static void print_link(struct rd *rd, uint32_t idx, const char *name,
-		       uint32_t port, struct nlattr **nla_line)
+void print_link(struct rd *rd, uint32_t idx, const char *name, uint32_t port,
+		struct nlattr **nla_line)
 {
 	if (rd->json_output) {
 		jsonw_uint_field(rd->jw, "ifindex", idx);
@@ -451,250 +451,6 @@ static int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
-static void print_qp_type(struct rd *rd, uint32_t val)
-{
-	if (rd->json_output)
-		jsonw_string_field(rd->jw, "qp-type",
-				   qp_types_to_str(val));
-	else
-		pr_out("qp-type %s ", qp_types_to_str(val));
-}
-
-static const char *cm_id_state_to_str(uint8_t idx)
-{
-	static const char * const cm_id_states_str[] = {
-		"IDLE", "ADDR_QUERY", "ADDR_RESOLVED", "ROUTE_QUERY",
-		"ROUTE_RESOLVED", "CONNECT", "DISCONNECT", "ADDR_BOUND",
-		"LISTEN", "DEVICE_REMOVAL", "DESTROYING" };
-
-	if (idx < ARRAY_SIZE(cm_id_states_str))
-		return cm_id_states_str[idx];
-	return "UNKNOWN";
-}
-
-static const char *cm_id_ps_to_str(uint32_t ps)
-{
-	switch (ps) {
-	case RDMA_PS_IPOIB:
-		return "IPoIB";
-	case RDMA_PS_IB:
-		return "IPoIB";
-	case RDMA_PS_TCP:
-		return "TCP";
-	case RDMA_PS_UDP:
-		return "UDP";
-	default:
-		return "---";
-	}
-}
-
-static void print_cm_id_state(struct rd *rd, uint8_t state)
-{
-	if (rd->json_output) {
-		jsonw_string_field(rd->jw, "state", cm_id_state_to_str(state));
-		return;
-	}
-	pr_out("state %s ", cm_id_state_to_str(state));
-}
-
-static void print_ps(struct rd *rd, uint32_t ps)
-{
-	if (rd->json_output) {
-		jsonw_string_field(rd->jw, "ps", cm_id_ps_to_str(ps));
-		return;
-	}
-	pr_out("ps %s ", cm_id_ps_to_str(ps));
-}
-
-static void print_ipaddr(struct rd *rd, const char *key, char *addrstr,
-			 uint16_t port)
-{
-	if (rd->json_output) {
-		int name_size = INET6_ADDRSTRLEN+strlen(":65535");
-		char json_name[name_size];
-
-		snprintf(json_name, name_size, "%s:%u", addrstr, port);
-		jsonw_string_field(rd->jw, key, json_name);
-		return;
-	}
-	pr_out("%s %s:%u ", key, addrstr, port);
-}
-
-static int ss_ntop(struct nlattr *nla_line, char *addr_str, uint16_t *port)
-{
-	struct __kernel_sockaddr_storage *addr;
-
-	addr = (struct __kernel_sockaddr_storage *)
-						mnl_attr_get_payload(nla_line);
-	switch (addr->ss_family) {
-	case AF_INET: {
-		struct sockaddr_in *sin = (struct sockaddr_in *)addr;
-
-		if (!inet_ntop(AF_INET, (const void *)&sin->sin_addr, addr_str,
-			       INET6_ADDRSTRLEN))
-			return -EINVAL;
-		*port = ntohs(sin->sin_port);
-		break;
-	}
-	case AF_INET6: {
-		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
-
-		if (!inet_ntop(AF_INET6, (const void *)&sin6->sin6_addr,
-			       addr_str, INET6_ADDRSTRLEN))
-			return -EINVAL;
-		*port = ntohs(sin6->sin6_port);
-		break;
-	}
-	default:
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
-{
-	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
-	struct nlattr *nla_table, *nla_entry;
-	struct rd *rd = data;
-	const char *name;
-	int idx;
-
-	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
-	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
-	    !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
-	    !tb[RDMA_NLDEV_ATTR_RES_CM_ID])
-		return MNL_CB_ERROR;
-
-	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
-	idx =  mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
-	nla_table = tb[RDMA_NLDEV_ATTR_RES_CM_ID];
-	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		char src_addr_str[INET6_ADDRSTRLEN];
-		char dst_addr_str[INET6_ADDRSTRLEN];
-		uint16_t src_port, dst_port;
-		uint32_t port = 0, pid = 0;
-		uint8_t type = 0, state;
-		uint32_t lqpn = 0, ps;
-		uint32_t cm_idn = 0;
-		char *comm = NULL;
-		int err;
-
-		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-		if (err != MNL_CB_OK)
-			return -EINVAL;
-
-		if (!nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
-		    !nla_line[RDMA_NLDEV_ATTR_RES_PS] ||
-		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
-		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
-			return MNL_CB_ERROR;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
-			port = mnl_attr_get_u32(
-					nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
-
-		if (port && port != rd->port_idx)
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN]) {
-			lqpn = mnl_attr_get_u32(
-					nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
-			if (rd_check_is_filtered(rd, "lqpn", lqpn))
-				continue;
-		}
-		if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE]) {
-			type = mnl_attr_get_u8(
-					nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
-			if (rd_check_is_string_filtered(rd, "qp-type",
-							qp_types_to_str(type)))
-				continue;
-		}
-
-		ps = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PS]);
-		if (rd_check_is_string_filtered(rd, "ps", cm_id_ps_to_str(ps)))
-			continue;
-
-		state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
-		if (rd_check_is_string_filtered(rd, "state",
-						cm_id_state_to_str(state)))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR]) {
-			if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR],
-				    src_addr_str, &src_port))
-				continue;
-			if (rd_check_is_string_filtered(rd, "src-addr",
-							src_addr_str))
-				continue;
-			if (rd_check_is_filtered(rd, "src-port", src_port))
-				continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR]) {
-			if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR],
-				    dst_addr_str, &dst_port))
-				continue;
-			if (rd_check_is_string_filtered(rd, "dst-addr",
-							dst_addr_str))
-				continue;
-			if (rd_check_is_filtered(rd, "dst-port", dst_port))
-				continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
-			pid = mnl_attr_get_u32(
-					nla_line[RDMA_NLDEV_ATTR_RES_PID]);
-			comm = get_task_name(pid);
-		}
-
-		if (rd_check_is_filtered(rd, "pid", pid)) {
-			free(comm);
-			continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
-			cm_idn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN]);
-		if (rd_check_is_filtered(rd, "cm-idn", cm_idn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]) {
-			/* discard const from mnl_attr_get_str */
-			comm = (char *)mnl_attr_get_str(
-				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
-		}
-
-		if (rd->json_output)
-			jsonw_start_array(rd->jw);
-
-		print_link(rd, idx, name, port, nla_line);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN])
-			print_lqpn(rd, lqpn);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE])
-			print_qp_type(rd, type);
-		print_cm_id_state(rd, state);
-		print_ps(rd, ps);
-		print_pid(rd, pid);
-		print_comm(rd, comm, nla_line);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
-			res_print_uint(rd, "cm-idn", cm_idn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR])
-			print_ipaddr(rd, "src-addr", src_addr_str, src_port);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR])
-			print_ipaddr(rd, "dst-addr", dst_addr_str, dst_port);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
-			free(comm);
-
-		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
-		newline(rd);
-	}
-	return MNL_CB_OK;
-}
-
 void print_users(struct rd *rd, uint64_t val)
 {
 	if (rd->json_output)
@@ -721,25 +477,6 @@ filters qp_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_qp,	RDMA_NLDEV_CMD_RES_QP_GET, qp_valid_filters, false);
 
-static const
-struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
-	{ .name = "link", .is_number = false },
-	{ .name = "lqpn", .is_number = true },
-	{ .name = "qp-type", .is_number = false },
-	{ .name = "state", .is_number = false },
-	{ .name = "ps", .is_number = false },
-	{ .name = "dev-type", .is_number = false },
-	{ .name = "transport-type", .is_number = false },
-	{ .name = "pid", .is_number = true },
-	{ .name = "src-addr", .is_number = false },
-	{ .name = "src-port", .is_number = true },
-	{ .name = "dst-addr", .is_number = false },
-	{ .name = "dst-port", .is_number = true },
-	{ .name = "cm-idn", .is_number = true }
-};
-
-RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false);
-
 static int res_show(struct rd *rd)
 {
 	const struct rd_cmd cmds[] = {
diff --git a/rdma/res.h b/rdma/res.h
index 19f0d420..e9d0d12e 100644
--- a/rdma/res.h
+++ b/rdma/res.h
@@ -12,6 +12,7 @@ int _res_send_msg(struct rd *rd, uint32_t command, mnl_cb_t callback);
 int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data);
 int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data);
 int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data);
 
 #define RES_FUNC(name, command, valid_filters, strict_port) \
 	static inline int _##name(struct rd *rd)\
@@ -71,12 +72,35 @@ struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
 
+static const
+struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "link", .is_number = false },
+	{ .name = "lqpn", .is_number = true },
+	{ .name = "qp-type", .is_number = false },
+	{ .name = "state", .is_number = false },
+	{ .name = "ps", .is_number = false },
+	{ .name = "dev-type", .is_number = false },
+	{ .name = "transport-type", .is_number = false },
+	{ .name = "pid", .is_number = true },
+	{ .name = "src-addr", .is_number = false },
+	{ .name = "src-port", .is_number = true },
+	{ .name = "dst-addr", .is_number = false },
+	{ .name = "dst-port", .is_number = true },
+	{ .name = "cm-idn", .is_number = true }
+};
+
+RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false);
+
 char *get_task_name(uint32_t pid);
 void print_dev(struct rd *rd, uint32_t idx, const char *name);
+void print_link(struct rd *rd, uint32_t idx, const char *name, uint32_t port,
+		struct nlattr **nla_line);
 void print_users(struct rd *rd, uint64_t val);
 void print_key(struct rd *rd, const char *name, uint64_t val);
 void res_print_uint(struct rd *rd, const char *name, uint64_t val);
 void print_pid(struct rd *rd, uint32_t val);
 void print_comm(struct rd *rd, const char *str, struct nlattr **nla_line);
+const char *qp_types_to_str(uint8_t idx);
+void print_lqpn(struct rd *rd, uint32_t val);
 
 #endif /* _RDMA_TOOL_RES_H_ */

From 687daf98f917cfa6793eea61485b5a0e533f3cf5 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:18 +0200
Subject: [PATCH 27/55] rdma: Move resource QP logic to separate file

Logically separate resource QP logic to separate file,
in order to make PD specific logic self-contained.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/Makefile |   2 +-
 rdma/res-qp.c | 234 +++++++++++++++++++++++++++++++++++++++++++++++++
 rdma/res.c    | 236 --------------------------------------------------
 rdma/res.h    |  17 ++++
 4 files changed, 252 insertions(+), 237 deletions(-)
 create mode 100644 rdma/res-qp.c

diff --git a/rdma/Makefile b/rdma/Makefile
index ef240404..ad7f4177 100644
--- a/rdma/Makefile
+++ b/rdma/Makefile
@@ -7,7 +7,7 @@ ifeq ($(HAVE_MNL),y)
 CFLAGS += -I./include/uapi/
 
 RDMA_OBJ = rdma.o utils.o dev.o link.o res.o res-pd.o res-mr.o res-cq.o \
-	   res-cmid.o
+	   res-cmid.o res-qp.o
 
 TARGETS += rdma
 endif
diff --git a/rdma/res-qp.c b/rdma/res-qp.c
new file mode 100644
index 00000000..85725fea
--- /dev/null
+++ b/rdma/res-qp.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * res-qp.c	RDMA tool
+ * Authors:     Leon Romanovsky <leonro@mellanox.com>
+ */
+
+#include "res.h"
+#include <inttypes.h>
+
+static const char *path_mig_to_str(uint8_t idx)
+{
+	static const char *const path_mig_str[] = { "MIGRATED", "REARM",
+						    "ARMED" };
+
+	if (idx < ARRAY_SIZE(path_mig_str))
+		return path_mig_str[idx];
+	return "UNKNOWN";
+}
+
+static const char *qp_states_to_str(uint8_t idx)
+{
+	static const char *const qp_states_str[] = { "RESET", "INIT", "RTR",
+						     "RTS",   "SQD",  "SQE",
+						     "ERR" };
+
+	if (idx < ARRAY_SIZE(qp_states_str))
+		return qp_states_str[idx];
+	return "UNKNOWN";
+}
+
+static void print_rqpn(struct rd *rd, uint32_t val, struct nlattr **nla_line)
+{
+	if (!nla_line[RDMA_NLDEV_ATTR_RES_RQPN])
+		return;
+
+	if (rd->json_output)
+		jsonw_uint_field(rd->jw, "rqpn", val);
+	else
+		pr_out("rqpn %u ", val);
+}
+
+static void print_type(struct rd *rd, uint32_t val)
+{
+	if (rd->json_output)
+		jsonw_string_field(rd->jw, "type", qp_types_to_str(val));
+	else
+		pr_out("type %s ", qp_types_to_str(val));
+}
+
+static void print_state(struct rd *rd, uint32_t val)
+{
+	if (rd->json_output)
+		jsonw_string_field(rd->jw, "state", qp_states_to_str(val));
+	else
+		pr_out("state %s ", qp_states_to_str(val));
+}
+
+static void print_rqpsn(struct rd *rd, uint32_t val, struct nlattr **nla_line)
+{
+	if (!nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN])
+		return;
+
+	if (rd->json_output)
+		jsonw_uint_field(rd->jw, "rq-psn", val);
+	else
+		pr_out("rq-psn %u ", val);
+}
+
+static void print_sqpsn(struct rd *rd, uint32_t val)
+{
+	if (rd->json_output)
+		jsonw_uint_field(rd->jw, "sq-psn", val);
+	else
+		pr_out("sq-psn %u ", val);
+}
+
+static void print_pathmig(struct rd *rd, uint32_t val, struct nlattr **nla_line)
+{
+	if (!nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE])
+		return;
+
+	if (rd->json_output)
+		jsonw_string_field(rd->jw, "path-mig-state",
+				   path_mig_to_str(val));
+	else
+		pr_out("path-mig-state %s ", path_mig_to_str(val));
+}
+
+int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct nlattr *nla_table, *nla_entry;
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_RES_QP])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	nla_table = tb[RDMA_NLDEV_ATTR_RES_QP];
+
+	mnl_attr_for_each_nested(nla_entry, nla_table) {
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+		uint32_t lqpn, rqpn = 0, rq_psn = 0, sq_psn;
+		uint8_t type, state, path_mig_state = 0;
+		uint32_t port = 0, pid = 0;
+		uint32_t pdn = 0;
+		char *comm = NULL;
+		int err;
+
+		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (err != MNL_CB_OK)
+			return MNL_CB_ERROR;
+
+		if (!nla_line[RDMA_NLDEV_ATTR_RES_LQPN] ||
+		    !nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN] ||
+		    !nla_line[RDMA_NLDEV_ATTR_RES_TYPE] ||
+		    !nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
+		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+			return MNL_CB_ERROR;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
+			port = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
+
+		if (port != rd->port_idx)
+			continue;
+
+		lqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
+		if (rd_check_is_filtered(rd, "lqpn", lqpn))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			pdn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+		if (rd_check_is_filtered(rd, "pdn", pdn))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_RQPN]) {
+			rqpn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_RQPN]);
+			if (rd_check_is_filtered(rd, "rqpn", rqpn))
+				continue;
+		} else {
+			if (rd_check_is_key_exist(rd, "rqpn"))
+				continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]) {
+			rq_psn = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]);
+			if (rd_check_is_filtered(rd, "rq-psn", rq_psn))
+				continue;
+		} else {
+			if (rd_check_is_key_exist(rd, "rq-psn"))
+				continue;
+		}
+
+		sq_psn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN]);
+		if (rd_check_is_filtered(rd, "sq-psn", sq_psn))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]) {
+			path_mig_state = mnl_attr_get_u8(
+				nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]);
+			if (rd_check_is_string_filtered(
+				    rd, "path-mig-state",
+				    path_mig_to_str(path_mig_state)))
+				continue;
+		} else {
+			if (rd_check_is_key_exist(rd, "path-mig-state"))
+				continue;
+		}
+
+		type = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
+		if (rd_check_is_string_filtered(rd, "type",
+						qp_types_to_str(type)))
+			continue;
+
+		state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
+		if (rd_check_is_string_filtered(rd, "state",
+						qp_states_to_str(state)))
+			continue;
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+			pid = mnl_attr_get_u32(
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+			comm = get_task_name(pid);
+		}
+
+		if (rd_check_is_filtered(rd, "pid", pid)) {
+			free(comm);
+			continue;
+		}
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+			/* discard const from mnl_attr_get_str */
+			comm = (char *)mnl_attr_get_str(
+				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+		if (rd->json_output)
+			jsonw_start_array(rd->jw);
+
+		print_link(rd, idx, name, port, nla_line);
+
+		print_lqpn(rd, lqpn);
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+			res_print_uint(rd, "pdn", pdn);
+		print_rqpn(rd, rqpn, nla_line);
+
+		print_type(rd, type);
+		print_state(rd, state);
+
+		print_rqpsn(rd, rq_psn, nla_line);
+		print_sqpsn(rd, sq_psn);
+
+		print_pathmig(rd, path_mig_state, nla_line);
+		print_pid(rd, pid);
+		print_comm(rd, comm, nla_line);
+
+		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+			free(comm);
+
+		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
+		newline(rd);
+	}
+	return MNL_CB_OK;
+}
diff --git a/rdma/res.c b/rdma/res.c
index d5ae60e1..6d4da38c 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -119,27 +119,6 @@ int _res_send_msg(struct rd *rd, uint32_t command, mnl_cb_t callback)
 	return ret;
 }
 
-static const char *path_mig_to_str(uint8_t idx)
-{
-	static const char * const path_mig_str[] = { "MIGRATED",
-						     "REARM", "ARMED" };
-
-	if (idx < ARRAY_SIZE(path_mig_str))
-		return path_mig_str[idx];
-	return "UNKNOWN";
-}
-
-static const char *qp_states_to_str(uint8_t idx)
-{
-	static const char * const qp_states_str[] = { "RESET", "INIT",
-						      "RTR", "RTS", "SQD",
-						      "SQE", "ERR" };
-
-	if (idx < ARRAY_SIZE(qp_states_str))
-		return qp_states_str[idx];
-	return "UNKNOWN";
-}
-
 const char *qp_types_to_str(uint8_t idx)
 {
 	static const char * const qp_types_str[] = { "SMI", "GSI", "RC",
@@ -161,68 +140,6 @@ void print_lqpn(struct rd *rd, uint32_t val)
 		pr_out("lqpn %u ", val);
 }
 
-static void print_rqpn(struct rd *rd, uint32_t val, struct nlattr **nla_line)
-{
-	if (!nla_line[RDMA_NLDEV_ATTR_RES_RQPN])
-		return;
-
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, "rqpn", val);
-	else
-		pr_out("rqpn %u ", val);
-}
-
-static void print_type(struct rd *rd, uint32_t val)
-{
-	if (rd->json_output)
-		jsonw_string_field(rd->jw, "type",
-				   qp_types_to_str(val));
-	else
-		pr_out("type %s ", qp_types_to_str(val));
-}
-
-static void print_state(struct rd *rd, uint32_t val)
-{
-	if (rd->json_output)
-		jsonw_string_field(rd->jw, "state",
-				   qp_states_to_str(val));
-	else
-		pr_out("state %s ", qp_states_to_str(val));
-}
-
-static void print_rqpsn(struct rd *rd, uint32_t val, struct nlattr **nla_line)
-{
-	if (!nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN])
-		return;
-
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, "rq-psn", val);
-	else
-		pr_out("rq-psn %u ", val);
-}
-
-static void print_sqpsn(struct rd *rd, uint32_t val)
-{
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, "sq-psn", val);
-	else
-		pr_out("sq-psn %u ", val);
-}
-
-static void print_pathmig(struct rd *rd, uint32_t val,
-			  struct nlattr **nla_line)
-{
-	if (!nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE])
-		return;
-
-	if (rd->json_output)
-		jsonw_string_field(rd->jw,
-				   "path-mig-state",
-				   path_mig_to_str(val));
-	else
-		pr_out("path-mig-state %s ", path_mig_to_str(val));
-}
-
 void print_pid(struct rd *rd, uint32_t val)
 {
 	if (rd->json_output)
@@ -314,143 +231,6 @@ void res_print_uint(struct rd *rd, const char *name, uint64_t val)
 		pr_out("%s %" PRIu64 " ", name, val);
 }
 
-static int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
-{
-	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
-	struct nlattr *nla_table, *nla_entry;
-	struct rd *rd = data;
-	const char *name;
-	uint32_t idx;
-
-	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
-	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
-	    !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
-	    !tb[RDMA_NLDEV_ATTR_RES_QP])
-		return MNL_CB_ERROR;
-
-	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
-	idx =  mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
-	nla_table = tb[RDMA_NLDEV_ATTR_RES_QP];
-
-	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		uint32_t lqpn, rqpn = 0, rq_psn = 0, sq_psn;
-		uint8_t type, state, path_mig_state = 0;
-		uint32_t port = 0, pid = 0;
-		uint32_t pdn = 0;
-		char *comm = NULL;
-		int err;
-
-		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-		if (err != MNL_CB_OK)
-			return MNL_CB_ERROR;
-
-		if (!nla_line[RDMA_NLDEV_ATTR_RES_LQPN] ||
-		    !nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN] ||
-		    !nla_line[RDMA_NLDEV_ATTR_RES_TYPE] ||
-		    !nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
-		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
-		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
-			return MNL_CB_ERROR;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
-			port = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
-
-		if (port != rd->port_idx)
-			continue;
-
-		lqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
-		if (rd_check_is_filtered(rd, "lqpn", lqpn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			pdn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
-		if (rd_check_is_filtered(rd, "pdn", pdn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_RQPN]) {
-			rqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_RQPN]);
-			if (rd_check_is_filtered(rd, "rqpn", rqpn))
-				continue;
-		} else {
-			if (rd_check_is_key_exist(rd, "rqpn"))
-				continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]) {
-			rq_psn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]);
-			if (rd_check_is_filtered(rd, "rq-psn", rq_psn))
-				continue;
-		} else {
-			if (rd_check_is_key_exist(rd, "rq-psn"))
-				continue;
-		}
-
-		sq_psn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN]);
-		if (rd_check_is_filtered(rd, "sq-psn", sq_psn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]) {
-			path_mig_state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]);
-			if (rd_check_is_string_filtered(rd, "path-mig-state", path_mig_to_str(path_mig_state)))
-				continue;
-		} else {
-			if (rd_check_is_key_exist(rd, "path-mig-state"))
-				continue;
-		}
-
-		type = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
-		if (rd_check_is_string_filtered(rd, "type", qp_types_to_str(type)))
-			continue;
-
-		state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
-		if (rd_check_is_string_filtered(rd, "state", qp_states_to_str(state)))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
-			pid = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PID]);
-			comm = get_task_name(pid);
-		}
-
-		if (rd_check_is_filtered(rd, "pid", pid)) {
-			free(comm);
-			continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
-			/* discard const from mnl_attr_get_str */
-			comm = (char *)mnl_attr_get_str(nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
-
-		if (rd->json_output)
-			jsonw_start_array(rd->jw);
-
-		print_link(rd, idx, name, port, nla_line);
-
-		print_lqpn(rd, lqpn);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			res_print_uint(rd, "pdn", pdn);
-		print_rqpn(rd, rqpn, nla_line);
-
-		print_type(rd, type);
-		print_state(rd, state);
-
-		print_rqpsn(rd, rq_psn, nla_line);
-		print_sqpsn(rd, sq_psn);
-
-		print_pathmig(rd, path_mig_state, nla_line);
-		print_pid(rd, pid);
-		print_comm(rd, comm, nla_line);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
-			free(comm);
-
-		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
-		newline(rd);
-	}
-	return MNL_CB_OK;
-}
-
 void print_users(struct rd *rd, uint64_t val)
 {
 	if (rd->json_output)
@@ -461,22 +241,6 @@ void print_users(struct rd *rd, uint64_t val)
 
 RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
 
-static const struct
-filters qp_valid_filters[MAX_NUMBER_OF_FILTERS] = {
-	{ .name = "link", .is_number = false },
-	{ .name = "lqpn", .is_number = true },
-	{ .name = "rqpn", .is_number = true },
-	{ .name = "pid",  .is_number = true },
-	{ .name = "sq-psn", .is_number = true },
-	{ .name = "rq-psn", .is_number = true },
-	{ .name = "type", .is_number = false },
-	{ .name = "path-mig-state", .is_number = false },
-	{ .name = "state", .is_number = false },
-	{ .name = "pdn", .is_number = true },
-};
-
-RES_FUNC(res_qp,	RDMA_NLDEV_CMD_RES_QP_GET, qp_valid_filters, false);
-
 static int res_show(struct rd *rd)
 {
 	const struct rd_cmd cmds[] = {
diff --git a/rdma/res.h b/rdma/res.h
index e9d0d12e..95d88a3a 100644
--- a/rdma/res.h
+++ b/rdma/res.h
@@ -13,6 +13,7 @@ int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data);
 int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data);
 int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data);
 int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data);
 
 #define RES_FUNC(name, command, valid_filters, strict_port) \
 	static inline int _##name(struct rd *rd)\
@@ -91,6 +92,22 @@ struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 
 RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false);
 
+static const struct
+filters qp_valid_filters[MAX_NUMBER_OF_FILTERS] = {
+	{ .name = "link", .is_number = false },
+	{ .name = "lqpn", .is_number = true },
+	{ .name = "rqpn", .is_number = true },
+	{ .name = "pid",  .is_number = true },
+	{ .name = "sq-psn", .is_number = true },
+	{ .name = "rq-psn", .is_number = true },
+	{ .name = "type", .is_number = false },
+	{ .name = "path-mig-state", .is_number = false },
+	{ .name = "state", .is_number = false },
+	{ .name = "pdn", .is_number = true },
+};
+
+RES_FUNC(res_qp,	RDMA_NLDEV_CMD_RES_QP_GET, qp_valid_filters, false);
+
 char *get_task_name(uint32_t pid);
 void print_dev(struct rd *rd, uint32_t idx, const char *name);
 void print_link(struct rd *rd, uint32_t idx, const char *name, uint32_t port,

From 835d83216bbac5e9eaaf30f16f87e48a83ec0efc Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:19 +0200
Subject: [PATCH 28/55] rdma: Properly mark RDMAtool license

RDMA subsystem is dual-licensed with "GPL-2.0 OR Linux-OpenIB" proper
license and Mellanox submission are supposed to have this type of license.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/Makefile | 2 +-
 rdma/dev.c    | 7 +------
 rdma/link.c   | 7 +------
 rdma/rdma.c   | 7 +------
 rdma/rdma.h   | 7 +------
 rdma/res.c    | 7 +------
 rdma/utils.c  | 7 +------
 7 files changed, 7 insertions(+), 37 deletions(-)

diff --git a/rdma/Makefile b/rdma/Makefile
index ad7f4177..6a424234 100644
--- a/rdma/Makefile
+++ b/rdma/Makefile
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 include ../config.mk
 
 TARGETS :=
diff --git a/rdma/dev.c b/rdma/dev.c
index 60ff4b31..954e0015 100644
--- a/rdma/dev.c
+++ b/rdma/dev.c
@@ -1,11 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /*
  * dev.c	RDMA tool
- *
- *              This program is free software; you can redistribute it and/or
- *              modify it under the terms of the GNU General Public License
- *              as published by the Free Software Foundation; either version
- *              2 of the License, or (at your option) any later version.
- *
  * Authors:     Leon Romanovsky <leonro@mellanox.com>
  */
 
diff --git a/rdma/link.c b/rdma/link.c
index c064be62..89e81b84 100644
--- a/rdma/link.c
+++ b/rdma/link.c
@@ -1,11 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /*
  * link.c	RDMA tool
- *
- *              This program is free software; you can redistribute it and/or
- *              modify it under the terms of the GNU General Public License
- *              as published by the Free Software Foundation; either version
- *              2 of the License, or (at your option) any later version.
- *
  * Authors:     Leon Romanovsky <leonro@mellanox.com>
  */
 
diff --git a/rdma/rdma.c b/rdma/rdma.c
index 010e9837..676e03c2 100644
--- a/rdma/rdma.c
+++ b/rdma/rdma.c
@@ -1,11 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /*
  * rdma.c	RDMA tool
- *
- *              This program is free software; you can redistribute it and/or
- *              modify it under the terms of the GNU General Public License
- *              as published by the Free Software Foundation; either version
- *              2 of the License, or (at your option) any later version.
- *
  * Authors:     Leon Romanovsky <leonro@mellanox.com>
  */
 
diff --git a/rdma/rdma.h b/rdma/rdma.h
index 547bb574..d2559e7c 100644
--- a/rdma/rdma.h
+++ b/rdma/rdma.h
@@ -1,11 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
 /*
  * rdma.c	RDMA tool
- *
- *              This program is free software; you can redistribute it and/or
- *              modify it under the terms of the GNU General Public License
- *              as published by the Free Software Foundation; either version
- *              2 of the License, or (at your option) any later version.
- *
  * Authors:     Leon Romanovsky <leonro@mellanox.com>
  */
 #ifndef _RDMA_TOOL_H_
diff --git a/rdma/res.c b/rdma/res.c
index 6d4da38c..f621afa8 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -1,11 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /*
  * res.c	RDMA tool
- *
- *              This program is free software; you can redistribute it and/or
- *              modify it under the terms of the GNU General Public License
- *              as published by the Free Software Foundation; either version
- *              2 of the License, or (at your option) any later version.
- *
  * Authors:     Leon Romanovsky <leonro@mellanox.com>
  */
 
diff --git a/rdma/utils.c b/rdma/utils.c
index 069d44fe..bce052d5 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -1,11 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /*
  * utils.c	RDMA tool
- *
- *              This program is free software; you can redistribute it and/or
- *              modify it under the terms of the GNU General Public License
- *              as published by the Free Software Foundation; either version
- *              2 of the License, or (at your option) any later version.
- *
  * Authors:     Leon Romanovsky <leonro@mellanox.com>
  */
 

From 05846c9cd3d7bfe47345c8de7471237307467e56 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:20 +0200
Subject: [PATCH 29/55] rdma: Simplify code to reuse existing functions

Remove duplicated functions in favour general res_print_uint() call.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res-cmid.c |  4 ++--
 rdma/res-cq.c   | 14 +++-----------
 rdma/res-mr.c   |  2 +-
 rdma/res-pd.c   |  4 ++--
 rdma/res-qp.c   | 14 +++-----------
 rdma/res.c      | 34 ++--------------------------------
 rdma/res.h      |  3 ---
 7 files changed, 13 insertions(+), 62 deletions(-)

diff --git a/rdma/res-cmid.c b/rdma/res-cmid.c
index b63634a3..5eea7a6b 100644
--- a/rdma/res-cmid.c
+++ b/rdma/res-cmid.c
@@ -227,12 +227,12 @@ int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 
 		print_link(rd, idx, name, port, nla_line);
 		if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN])
-			print_lqpn(rd, lqpn);
+			res_print_uint(rd, "lqpn", lqpn);
 		if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE])
 			print_qp_type(rd, type);
 		print_cm_id_state(rd, state);
 		print_ps(rd, ps);
-		print_pid(rd, pid);
+		res_print_uint(rd, "pid", pid);
 		print_comm(rd, comm, nla_line);
 		if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
 			res_print_uint(rd, "cm-idn", cm_idn);
diff --git a/rdma/res-cq.c b/rdma/res-cq.c
index fbfe593b..93c18251 100644
--- a/rdma/res-cq.c
+++ b/rdma/res-cq.c
@@ -7,14 +7,6 @@
 #include "res.h"
 #include <inttypes.h>
 
-static void print_cqe(struct rd *rd, uint32_t val)
-{
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, "cqe", val);
-	else
-		pr_out("cqe %u ", val);
-}
-
 static const char *poll_ctx_to_str(uint8_t idx)
 {
 	static const char * const cm_id_states_str[] = {
@@ -120,11 +112,11 @@ int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 			jsonw_start_array(rd->jw);
 
 		print_dev(rd, idx, name);
-		print_cqe(rd, cqe);
-		print_users(rd, users);
+		res_print_uint(rd, "cqe", cqe);
+		res_print_uint(rd, "users", users);
 		if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX])
 			print_poll_ctx(rd, poll_ctx);
-		print_pid(rd, pid);
+		res_print_uint(rd, "pid", pid);
 		print_comm(rd, comm, nla_line);
 
 		if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
diff --git a/rdma/res-mr.c b/rdma/res-mr.c
index dae5def2..e373035a 100644
--- a/rdma/res-mr.c
+++ b/rdma/res-mr.c
@@ -97,7 +97,7 @@ int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 		if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
 			print_key(rd, "iova", iova);
 		res_print_uint(rd, "mrlen", mrlen);
-		print_pid(rd, pid);
+		res_print_uint(rd, "pid", pid);
 		print_comm(rd, comm, nla_line);
 
 		if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
diff --git a/rdma/res-pd.c b/rdma/res-pd.c
index d879a21a..24ac7f1b 100644
--- a/rdma/res-pd.c
+++ b/rdma/res-pd.c
@@ -89,10 +89,10 @@ int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 		print_dev(rd, idx, name);
 		if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
 			print_key(rd, "local_dma_lkey", local_dma_lkey);
-		print_users(rd, users);
+		res_print_uint(rd, "users", users);
 		if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
 			print_key(rd, "unsafe_global_rkey", unsafe_global_rkey);
-		print_pid(rd, pid);
+		res_print_uint(rd, "pid", pid);
 		print_comm(rd, comm, nla_line);
 		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
 			res_print_uint(rd, "ctxn", ctxn);
diff --git a/rdma/res-qp.c b/rdma/res-qp.c
index 85725fea..ecd2cbd6 100644
--- a/rdma/res-qp.c
+++ b/rdma/res-qp.c
@@ -66,14 +66,6 @@ static void print_rqpsn(struct rd *rd, uint32_t val, struct nlattr **nla_line)
 		pr_out("rq-psn %u ", val);
 }
 
-static void print_sqpsn(struct rd *rd, uint32_t val)
-{
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, "sq-psn", val);
-	else
-		pr_out("sq-psn %u ", val);
-}
-
 static void print_pathmig(struct rd *rd, uint32_t val, struct nlattr **nla_line)
 {
 	if (!nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE])
@@ -209,7 +201,7 @@ int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 
 		print_link(rd, idx, name, port, nla_line);
 
-		print_lqpn(rd, lqpn);
+		res_print_uint(rd, "lqpn", lqpn);
 		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
 			res_print_uint(rd, "pdn", pdn);
 		print_rqpn(rd, rqpn, nla_line);
@@ -218,10 +210,10 @@ int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 		print_state(rd, state);
 
 		print_rqpsn(rd, rq_psn, nla_line);
-		print_sqpsn(rd, sq_psn);
+		res_print_uint(rd, "sq-psn", sq_psn);
 
 		print_pathmig(rd, path_mig_state, nla_line);
-		print_pid(rd, pid);
+		res_print_uint(rd, "pid", pid);
 		print_comm(rd, comm, nla_line);
 
 		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
diff --git a/rdma/res.c b/rdma/res.c
index f621afa8..140c0908 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -35,7 +35,6 @@ static int res_print_summary(struct rd *rd, struct nlattr **tb)
 
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
 		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		char json_name[32];
 
 		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
 		if (err != MNL_CB_OK)
@@ -48,12 +47,7 @@ static int res_print_summary(struct rd *rd, struct nlattr **tb)
 
 		name = mnl_attr_get_str(nla_line[RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_NAME]);
 		curr = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_CURR]);
-		if (rd->json_output) {
-			snprintf(json_name, 32, "%s", name);
-			jsonw_lluint_field(rd->jw, json_name, curr);
-		} else {
-			pr_out("%s %"PRId64 " ", name, curr);
-		}
+		res_print_uint(rd, name, curr);
 	}
 	return 0;
 }
@@ -127,22 +121,6 @@ const char *qp_types_to_str(uint8_t idx)
 	return "UNKNOWN";
 }
 
-void print_lqpn(struct rd *rd, uint32_t val)
-{
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, "lqpn", val);
-	else
-		pr_out("lqpn %u ", val);
-}
-
-void print_pid(struct rd *rd, uint32_t val)
-{
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, "pid", val);
-	else
-		pr_out("pid %u ", val);
-}
-
 void print_comm(struct rd *rd, const char *str, struct nlattr **nla_line)
 {
 	char tmp[18];
@@ -221,19 +199,11 @@ void print_key(struct rd *rd, const char *name, uint64_t val)
 void res_print_uint(struct rd *rd, const char *name, uint64_t val)
 {
 	if (rd->json_output)
-		jsonw_uint_field(rd->jw, name, val);
+		jsonw_u64_field(rd->jw, name, val);
 	else
 		pr_out("%s %" PRIu64 " ", name, val);
 }
 
-void print_users(struct rd *rd, uint64_t val)
-{
-	if (rd->json_output)
-		jsonw_uint_field(rd->jw, "users", val);
-	else
-		pr_out("users %" PRIu64 " ", val);
-}
-
 RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
 
 static int res_show(struct rd *rd)
diff --git a/rdma/res.h b/rdma/res.h
index 95d88a3a..89dd818a 100644
--- a/rdma/res.h
+++ b/rdma/res.h
@@ -112,12 +112,9 @@ char *get_task_name(uint32_t pid);
 void print_dev(struct rd *rd, uint32_t idx, const char *name);
 void print_link(struct rd *rd, uint32_t idx, const char *name, uint32_t port,
 		struct nlattr **nla_line);
-void print_users(struct rd *rd, uint64_t val);
 void print_key(struct rd *rd, const char *name, uint64_t val);
 void res_print_uint(struct rd *rd, const char *name, uint64_t val);
-void print_pid(struct rd *rd, uint32_t val);
 void print_comm(struct rd *rd, const char *str, struct nlattr **nla_line);
 const char *qp_types_to_str(uint8_t idx);
-void print_lqpn(struct rd *rd, uint32_t val);
 
 #endif /* _RDMA_TOOL_RES_H_ */

From 7d06b31f0e4d71f55a80f4cc3cb0afa214994f2f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:21 +0200
Subject: [PATCH 30/55] rdma: Simplify CM_ID print code

Refactor our the CM_ID print code.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res-cmid.c | 246 ++++++++++++++++++++++++------------------------
 1 file changed, 124 insertions(+), 122 deletions(-)

diff --git a/rdma/res-cmid.c b/rdma/res-cmid.c
index 5eea7a6b..12d1acee 100644
--- a/rdma/res-cmid.c
+++ b/rdma/res-cmid.c
@@ -108,11 +108,130 @@ static int ss_ntop(struct nlattr *nla_line, char *addr_str, uint16_t *port)
 	return 0;
 }
 
+static int res_cm_id_line(struct rd *rd, const char *name, int idx,
+			  struct nlattr *nla_entry)
+{
+	struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+	char src_addr_str[INET6_ADDRSTRLEN];
+	char dst_addr_str[INET6_ADDRSTRLEN];
+	uint16_t src_port, dst_port;
+	uint32_t port = 0, pid = 0;
+	uint8_t type = 0, state;
+	uint32_t lqpn = 0, ps;
+	uint32_t cm_idn = 0;
+	char *comm = NULL;
+	int err;
+
+	err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+	if (err != MNL_CB_OK)
+		return MNL_CB_ERROR;
+
+	if (!nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
+	    !nla_line[RDMA_NLDEV_ATTR_RES_PS] ||
+	    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+	     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+		return MNL_CB_ERROR;
+	}
+
+	if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
+		port = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
+
+	if (port && port != rd->port_idx)
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN]) {
+		lqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
+		if (rd_check_is_filtered(rd, "lqpn", lqpn))
+			goto out;
+	}
+	if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE]) {
+		type = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
+		if (rd_check_is_string_filtered(rd, "qp-type",
+						qp_types_to_str(type)))
+			goto out;
+	}
+
+	ps = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PS]);
+	if (rd_check_is_string_filtered(rd, "ps", cm_id_ps_to_str(ps)))
+		goto out;
+
+	state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
+	if (rd_check_is_string_filtered(rd, "state", cm_id_state_to_str(state)))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR]) {
+		if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR],
+			    src_addr_str, &src_port))
+			goto out;
+		if (rd_check_is_string_filtered(rd, "src-addr", src_addr_str))
+			goto out;
+		if (rd_check_is_filtered(rd, "src-port", src_port))
+			goto out;
+	}
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR]) {
+		if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR],
+			    dst_addr_str, &dst_port))
+			goto out;
+		if (rd_check_is_string_filtered(rd, "dst-addr", dst_addr_str))
+			goto out;
+		if (rd_check_is_filtered(rd, "dst-port", dst_port))
+			goto out;
+	}
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+		pid = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+		comm = get_task_name(pid);
+	}
+
+	if (rd_check_is_filtered(rd, "pid", pid))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
+		cm_idn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN]);
+	if (rd_check_is_filtered(rd, "cm-idn", cm_idn))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]) {
+		/* discard const from mnl_attr_get_str */
+		comm = (char *)mnl_attr_get_str(
+			nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+	}
+
+	if (rd->json_output)
+		jsonw_start_array(rd->jw);
+
+	print_link(rd, idx, name, port, nla_line);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN])
+		res_print_uint(rd, "lqpn", lqpn);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE])
+		print_qp_type(rd, type);
+	print_cm_id_state(rd, state);
+	print_ps(rd, ps);
+	res_print_uint(rd, "pid", pid);
+	print_comm(rd, comm, nla_line);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
+		res_print_uint(rd, "cm-idn", cm_idn);
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR])
+		print_ipaddr(rd, "src-addr", src_addr_str, src_port);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR])
+		print_ipaddr(rd, "dst-addr", dst_addr_str, dst_port);
+
+	print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
+	newline(rd);
+
+out:	if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+		free(comm);
+	return MNL_CB_OK;
+}
+
 int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
 	struct nlattr *nla_table, *nla_entry;
 	struct rd *rd = data;
+	int ret = MNL_CB_OK;
 	const char *name;
 	int idx;
 
@@ -124,129 +243,12 @@ int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
 	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
 	nla_table = tb[RDMA_NLDEV_ATTR_RES_CM_ID];
+
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		char src_addr_str[INET6_ADDRSTRLEN];
-		char dst_addr_str[INET6_ADDRSTRLEN];
-		uint16_t src_port, dst_port;
-		uint32_t port = 0, pid = 0;
-		uint8_t type = 0, state;
-		uint32_t lqpn = 0, ps;
-		uint32_t cm_idn = 0;
-		char *comm = NULL;
-		int err;
+		ret = res_cm_id_line(rd, name, idx, nla_entry);
 
-		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-		if (err != MNL_CB_OK)
-			return -EINVAL;
-
-		if (!nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
-		    !nla_line[RDMA_NLDEV_ATTR_RES_PS] ||
-		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
-		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
-			return MNL_CB_ERROR;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
-			port = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
-
-		if (port && port != rd->port_idx)
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN]) {
-			lqpn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
-			if (rd_check_is_filtered(rd, "lqpn", lqpn))
-				continue;
-		}
-		if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE]) {
-			type = mnl_attr_get_u8(
-				nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
-			if (rd_check_is_string_filtered(rd, "qp-type",
-							qp_types_to_str(type)))
-				continue;
-		}
-
-		ps = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PS]);
-		if (rd_check_is_string_filtered(rd, "ps", cm_id_ps_to_str(ps)))
-			continue;
-
-		state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
-		if (rd_check_is_string_filtered(rd, "state",
-						cm_id_state_to_str(state)))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR]) {
-			if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR],
-				    src_addr_str, &src_port))
-				continue;
-			if (rd_check_is_string_filtered(rd, "src-addr",
-							src_addr_str))
-				continue;
-			if (rd_check_is_filtered(rd, "src-port", src_port))
-				continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR]) {
-			if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR],
-				    dst_addr_str, &dst_port))
-				continue;
-			if (rd_check_is_string_filtered(rd, "dst-addr",
-							dst_addr_str))
-				continue;
-			if (rd_check_is_filtered(rd, "dst-port", dst_port))
-				continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
-			pid = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
-			comm = get_task_name(pid);
-		}
-
-		if (rd_check_is_filtered(rd, "pid", pid)) {
-			free(comm);
-			continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
-			cm_idn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN]);
-		if (rd_check_is_filtered(rd, "cm-idn", cm_idn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]) {
-			/* discard const from mnl_attr_get_str */
-			comm = (char *)mnl_attr_get_str(
-				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
-		}
-
-		if (rd->json_output)
-			jsonw_start_array(rd->jw);
-
-		print_link(rd, idx, name, port, nla_line);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN])
-			res_print_uint(rd, "lqpn", lqpn);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE])
-			print_qp_type(rd, type);
-		print_cm_id_state(rd, state);
-		print_ps(rd, ps);
-		res_print_uint(rd, "pid", pid);
-		print_comm(rd, comm, nla_line);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
-			res_print_uint(rd, "cm-idn", cm_idn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR])
-			print_ipaddr(rd, "src-addr", src_addr_str, src_port);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR])
-			print_ipaddr(rd, "dst-addr", dst_addr_str, dst_port);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
-			free(comm);
-
-		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
-		newline(rd);
+		if (ret != MNL_CB_OK)
+			break;
 	}
-	return MNL_CB_OK;
+	return ret;
 }

From 83ea72289e0bc5c0abc0a66d1410c0abf34dac72 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:22 +0200
Subject: [PATCH 31/55] rdma: Refactor CQ prints

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res-cq.c | 175 ++++++++++++++++++++++++++------------------------
 1 file changed, 90 insertions(+), 85 deletions(-)

diff --git a/rdma/res-cq.c b/rdma/res-cq.c
index 93c18251..e50d76ce 100644
--- a/rdma/res-cq.c
+++ b/rdma/res-cq.c
@@ -27,11 +27,97 @@ static void print_poll_ctx(struct rd *rd, uint8_t poll_ctx)
 	pr_out("poll-ctx %s ", poll_ctx_to_str(poll_ctx));
 }
 
+static int res_cq_line(struct rd *rd, const char *name, int idx,
+		       struct nlattr *nla_entry)
+{
+	struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+	char *comm = NULL;
+	uint32_t pid = 0;
+	uint8_t poll_ctx = 0;
+	uint32_t ctxn = 0;
+	uint32_t cqn = 0;
+	uint64_t users;
+	uint32_t cqe;
+	int err;
+
+	err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+	if (err != MNL_CB_OK)
+		return MNL_CB_ERROR;
+
+	if (!nla_line[RDMA_NLDEV_ATTR_RES_CQE] ||
+	    !nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
+	    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+	     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+		return MNL_CB_ERROR;
+	}
+
+	cqe = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CQE]);
+
+	users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
+	if (rd_check_is_filtered(rd, "users", users))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]) {
+		poll_ctx =
+			mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]);
+		if (rd_check_is_string_filtered(rd, "poll-ctx",
+						poll_ctx_to_str(poll_ctx)))
+			goto out;
+	}
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+		pid = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+		comm = get_task_name(pid);
+	}
+
+	if (rd_check_is_filtered(rd, "pid", pid))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
+		cqn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CQN]);
+	if (rd_check_is_filtered(rd, "cqn", cqn))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+		ctxn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
+	if (rd_check_is_filtered(rd, "ctxn", ctxn))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+		/* discard const from mnl_attr_get_str */
+		comm = (char *)mnl_attr_get_str(
+			nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+	if (rd->json_output)
+		jsonw_start_array(rd->jw);
+
+	print_dev(rd, idx, name);
+	res_print_uint(rd, "cqe", cqe);
+	res_print_uint(rd, "users", users);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX])
+		print_poll_ctx(rd, poll_ctx);
+	res_print_uint(rd, "pid", pid);
+	print_comm(rd, comm, nla_line);
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
+		res_print_uint(rd, "cqn", cqn);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+		res_print_uint(rd, "ctxn", ctxn);
+
+	print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
+	newline(rd);
+
+out:	if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+		free(comm);
+	return MNL_CB_OK;
+}
+
 int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
 	struct nlattr *nla_table, *nla_entry;
 	struct rd *rd = data;
+	int ret = MNL_CB_OK;
 	const char *name;
 	uint32_t idx;
 
@@ -45,91 +131,10 @@ int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 	nla_table = tb[RDMA_NLDEV_ATTR_RES_CQ];
 
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		char *comm = NULL;
-		uint32_t pid = 0;
-		uint8_t poll_ctx = 0;
-		uint32_t ctxn = 0;
-		uint32_t cqn = 0;
-		uint64_t users;
-		uint32_t cqe;
-		int err;
+		ret = res_cq_line(rd, name, idx, nla_entry);
 
-		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-		if (err != MNL_CB_OK)
-			return MNL_CB_ERROR;
-
-		if (!nla_line[RDMA_NLDEV_ATTR_RES_CQE] ||
-		    !nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
-		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
-		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
-			return MNL_CB_ERROR;
-		}
-
-		cqe = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CQE]);
-
-		users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
-		if (rd_check_is_filtered(rd, "users", users))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]) {
-			poll_ctx = mnl_attr_get_u8(
-				nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]);
-			if (rd_check_is_string_filtered(
-				    rd, "poll-ctx", poll_ctx_to_str(poll_ctx)))
-				continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
-			pid = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
-			comm = get_task_name(pid);
-		}
-
-		if (rd_check_is_filtered(rd, "pid", pid)) {
-			free(comm);
-			continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
-			cqn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_CQN]);
-		if (rd_check_is_filtered(rd, "cqn", cqn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
-			ctxn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
-		if (rd_check_is_filtered(rd, "ctxn", ctxn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
-			/* discard const from mnl_attr_get_str */
-			comm = (char *)mnl_attr_get_str(
-				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
-
-		if (rd->json_output)
-			jsonw_start_array(rd->jw);
-
-		print_dev(rd, idx, name);
-		res_print_uint(rd, "cqe", cqe);
-		res_print_uint(rd, "users", users);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX])
-			print_poll_ctx(rd, poll_ctx);
-		res_print_uint(rd, "pid", pid);
-		print_comm(rd, comm, nla_line);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
-			res_print_uint(rd, "cqn", cqn);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
-			res_print_uint(rd, "ctxn", ctxn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
-			free(comm);
-
-		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
-		newline(rd);
+		if (ret != MNL_CB_OK)
+			break;
 	}
-	return MNL_CB_OK;
+	return ret;
 }
-

From 46695227d63e687a9af3ce174708cc9909105aea Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:23 +0200
Subject: [PATCH 32/55] rdma: Move MR code to be suitable for per-line parsing

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res-mr.c | 176 +++++++++++++++++++++++++-------------------------
 1 file changed, 89 insertions(+), 87 deletions(-)

diff --git a/rdma/res-mr.c b/rdma/res-mr.c
index e373035a..36993b5e 100644
--- a/rdma/res-mr.c
+++ b/rdma/res-mr.c
@@ -7,11 +7,96 @@
 #include "res.h"
 #include <inttypes.h>
 
+static int res_mr_line(struct rd *rd, const char *name, int idx,
+		       struct nlattr *nla_entry)
+{
+	struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+	uint32_t rkey = 0, lkey = 0;
+	uint64_t iova = 0, mrlen;
+	char *comm = NULL;
+	uint32_t pdn = 0;
+	uint32_t mrn = 0;
+	uint32_t pid = 0;
+	int err;
+
+	err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+	if (err != MNL_CB_OK)
+		return MNL_CB_ERROR;
+
+	if (!nla_line[RDMA_NLDEV_ATTR_RES_MRLEN] ||
+	    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+	     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+		return MNL_CB_ERROR;
+	}
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
+		rkey = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_RKEY]);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
+		lkey = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_LKEY]);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
+		iova = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_IOVA]);
+
+	mrlen = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_MRLEN]);
+	if (rd_check_is_filtered(rd, "mrlen", mrlen))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+		pid = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+		comm = get_task_name(pid);
+	}
+
+	if (rd_check_is_filtered(rd, "pid", pid))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
+		mrn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_MRN]);
+	if (rd_check_is_filtered(rd, "mrn", mrn))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+		pdn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+	if (rd_check_is_filtered(rd, "pdn", pdn))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+		/* discard const from mnl_attr_get_str */
+		comm = (char *)mnl_attr_get_str(
+			nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+	if (rd->json_output)
+		jsonw_start_array(rd->jw);
+
+	print_dev(rd, idx, name);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
+		print_key(rd, "rkey", rkey);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
+		print_key(rd, "lkey", lkey);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
+		print_key(rd, "iova", iova);
+	res_print_uint(rd, "mrlen", mrlen);
+	res_print_uint(rd, "pid", pid);
+	print_comm(rd, comm, nla_line);
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
+		res_print_uint(rd, "mrn", mrn);
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+		res_print_uint(rd, "pdn", pdn);
+
+	print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
+	newline(rd);
+
+out:
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+		free(comm);
+	return MNL_CB_OK;
+}
 int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
 	struct nlattr *nla_table, *nla_entry;
 	struct rd *rd = data;
+	int ret = MNL_CB_OK;
 	const char *name;
 	uint32_t idx;
 
@@ -25,93 +110,10 @@ int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 	nla_table = tb[RDMA_NLDEV_ATTR_RES_MR];
 
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		uint32_t rkey = 0, lkey = 0;
-		uint64_t iova = 0, mrlen;
-		char *comm = NULL;
-		uint32_t pdn = 0;
-		uint32_t mrn = 0;
-		uint32_t pid = 0;
-		int err;
+		ret = res_mr_line(rd, name, idx, nla_entry);
 
-		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-		if (err != MNL_CB_OK)
-			return MNL_CB_ERROR;
-
-		if (!nla_line[RDMA_NLDEV_ATTR_RES_MRLEN] ||
-		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
-		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
-			return MNL_CB_ERROR;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
-			rkey = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_RKEY]);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
-			lkey = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_LKEY]);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
-			iova = mnl_attr_get_u64(
-				nla_line[RDMA_NLDEV_ATTR_RES_IOVA]);
-
-		mrlen = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_MRLEN]);
-		if (rd_check_is_filtered(rd, "mrlen", mrlen))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
-			pid = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
-			comm = get_task_name(pid);
-		}
-
-		if (rd_check_is_filtered(rd, "pid", pid)) {
-			free(comm);
-			continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
-			mrn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_MRN]);
-		if (rd_check_is_filtered(rd, "mrn", mrn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			pdn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
-		if (rd_check_is_filtered(rd, "pdn", pdn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
-			/* discard const from mnl_attr_get_str */
-			comm = (char *)mnl_attr_get_str(
-				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
-
-		if (rd->json_output)
-			jsonw_start_array(rd->jw);
-
-		print_dev(rd, idx, name);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
-			print_key(rd, "rkey", rkey);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
-			print_key(rd, "lkey", lkey);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
-			print_key(rd, "iova", iova);
-		res_print_uint(rd, "mrlen", mrlen);
-		res_print_uint(rd, "pid", pid);
-		print_comm(rd, comm, nla_line);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
-			res_print_uint(rd, "mrn", mrn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			res_print_uint(rd, "pdn", pdn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
-			free(comm);
-
-		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
-		newline(rd);
+		if (ret != MNL_CB_OK)
+			break;
 	}
-	return MNL_CB_OK;
+	return ret;
 }
-

From f9a73796d1c083db5f01409328b9eca3f207de49 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:24 +0200
Subject: [PATCH 33/55] rdma: Place PD parsing print routine into separate
 function

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res-pd.c | 168 ++++++++++++++++++++++++++------------------------
 1 file changed, 88 insertions(+), 80 deletions(-)

diff --git a/rdma/res-pd.c b/rdma/res-pd.c
index 24ac7f1b..3c9ffa4e 100644
--- a/rdma/res-pd.c
+++ b/rdma/res-pd.c
@@ -7,11 +7,95 @@
 #include "res.h"
 #include <inttypes.h>
 
+static int res_pd_line(struct rd *rd, const char *name, int idx,
+		       struct nlattr *nla_entry)
+{
+	uint32_t local_dma_lkey = 0, unsafe_global_rkey = 0;
+	struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+	char *comm = NULL;
+	uint32_t ctxn = 0;
+	uint32_t pid = 0;
+	uint32_t pdn = 0;
+	uint64_t users;
+	int err;
+
+	err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+	if (err != MNL_CB_OK)
+		return MNL_CB_ERROR;
+
+	if (!nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
+	    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+	     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+		return MNL_CB_ERROR;
+	}
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
+		local_dma_lkey = mnl_attr_get_u32(
+			nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY]);
+
+	users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
+	if (rd_check_is_filtered(rd, "users", users))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
+		unsafe_global_rkey = mnl_attr_get_u32(
+			nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY]);
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+		pid = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+		comm = get_task_name(pid);
+	}
+
+	if (rd_check_is_filtered(rd, "pid", pid))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+		ctxn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
+
+	if (rd_check_is_filtered(rd, "ctxn", ctxn))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+		pdn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+	if (rd_check_is_filtered(rd, "pdn", pdn))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+		/* discard const from mnl_attr_get_str */
+		comm = (char *)mnl_attr_get_str(
+			nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+	if (rd->json_output)
+		jsonw_start_array(rd->jw);
+
+	print_dev(rd, idx, name);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
+		print_key(rd, "local_dma_lkey", local_dma_lkey);
+	res_print_uint(rd, "users", users);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
+		print_key(rd, "unsafe_global_rkey", unsafe_global_rkey);
+	res_print_uint(rd, "pid", pid);
+	print_comm(rd, comm, nla_line);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
+		res_print_uint(rd, "ctxn", ctxn);
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+		res_print_uint(rd, "pdn", pdn);
+
+	print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
+	newline(rd);
+
+out:	if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+		free(comm);
+	return MNL_CB_OK;
+}
+
 int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
 	struct nlattr *nla_table, *nla_entry;
 	struct rd *rd = data;
+	int ret = MNL_CB_OK;
 	const char *name;
 	uint32_t idx;
 
@@ -25,86 +109,10 @@ int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 	nla_table = tb[RDMA_NLDEV_ATTR_RES_PD];
 
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		uint32_t local_dma_lkey = 0, unsafe_global_rkey = 0;
-		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		char *comm = NULL;
-		uint32_t ctxn = 0;
-		uint32_t pid = 0;
-		uint32_t pdn = 0;
-		uint64_t users;
-		int err;
+		ret = res_pd_line(rd, name, idx, nla_entry);
 
-		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-		if (err != MNL_CB_OK)
-			return MNL_CB_ERROR;
-
-		if (!nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
-		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
-		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
-			return MNL_CB_ERROR;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
-			local_dma_lkey = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY]);
-
-		users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
-		if (rd_check_is_filtered(rd, "users", users))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
-			unsafe_global_rkey = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY]);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
-			pid = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
-			comm = get_task_name(pid);
-		}
-
-		if (rd_check_is_filtered(rd, "pid", pid))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
-			ctxn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
-
-		if (rd_check_is_filtered(rd, "ctxn", ctxn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			pdn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
-		if (rd_check_is_filtered(rd, "pdn", pdn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
-			/* discard const from mnl_attr_get_str */
-			comm = (char *)mnl_attr_get_str(
-				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
-
-		if (rd->json_output)
-			jsonw_start_array(rd->jw);
-
-		print_dev(rd, idx, name);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
-			print_key(rd, "local_dma_lkey", local_dma_lkey);
-		res_print_uint(rd, "users", users);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
-			print_key(rd, "unsafe_global_rkey", unsafe_global_rkey);
-		res_print_uint(rd, "pid", pid);
-		print_comm(rd, comm, nla_line);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
-			res_print_uint(rd, "ctxn", ctxn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			res_print_uint(rd, "pdn", pdn);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
-			free(comm);
-
-		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
-		newline(rd);
+		if (ret != MNL_CB_OK)
+			break;
 	}
-	return MNL_CB_OK;
+	return ret;
 }

From 6da9d2517c56bea101050d9ffb062866c9bbd385 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:25 +0200
Subject: [PATCH 34/55] rdma: Move QP code to separate function

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res-qp.c | 251 +++++++++++++++++++++++++-------------------------
 1 file changed, 126 insertions(+), 125 deletions(-)

diff --git a/rdma/res-qp.c b/rdma/res-qp.c
index ecd2cbd6..e74c8b01 100644
--- a/rdma/res-qp.c
+++ b/rdma/res-qp.c
@@ -78,11 +78,133 @@ static void print_pathmig(struct rd *rd, uint32_t val, struct nlattr **nla_line)
 		pr_out("path-mig-state %s ", path_mig_to_str(val));
 }
 
+static int res_qp_line(struct rd *rd, const char *name, int idx,
+		       struct nlattr *nla_entry)
+{
+	struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+	uint32_t lqpn, rqpn = 0, rq_psn = 0, sq_psn;
+	uint8_t type, state, path_mig_state = 0;
+	uint32_t port = 0, pid = 0;
+	uint32_t pdn = 0;
+	char *comm = NULL;
+	int err;
+
+	err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+	if (err != MNL_CB_OK)
+		return MNL_CB_ERROR;
+
+	if (!nla_line[RDMA_NLDEV_ATTR_RES_LQPN] ||
+	    !nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN] ||
+	    !nla_line[RDMA_NLDEV_ATTR_RES_TYPE] ||
+	    !nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
+	    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
+	     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
+		return MNL_CB_ERROR;
+	}
+
+	if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
+		port = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
+
+	if (port != rd->port_idx)
+		goto out;
+
+	lqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
+	if (rd_check_is_filtered(rd, "lqpn", lqpn))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+		pdn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+	if (rd_check_is_filtered(rd, "pdn", pdn))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_RQPN]) {
+		rqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_RQPN]);
+		if (rd_check_is_filtered(rd, "rqpn", rqpn))
+			goto out;
+	} else {
+		if (rd_check_is_key_exist(rd, "rqpn"))
+			goto out;
+	}
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]) {
+		rq_psn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]);
+		if (rd_check_is_filtered(rd, "rq-psn", rq_psn))
+			goto out;
+	} else {
+		if (rd_check_is_key_exist(rd, "rq-psn"))
+			goto out;
+	}
+
+	sq_psn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN]);
+	if (rd_check_is_filtered(rd, "sq-psn", sq_psn))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]) {
+		path_mig_state = mnl_attr_get_u8(
+			nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]);
+		if (rd_check_is_string_filtered(rd, "path-mig-state",
+						path_mig_to_str(path_mig_state)))
+			goto out;
+	} else {
+		if (rd_check_is_key_exist(rd, "path-mig-state"))
+			goto out;
+	}
+
+	type = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
+	if (rd_check_is_string_filtered(rd, "type", qp_types_to_str(type)))
+		goto out;
+
+	state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
+	if (rd_check_is_string_filtered(rd, "state", qp_states_to_str(state)))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
+		pid = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PID]);
+		comm = get_task_name(pid);
+	}
+
+	if (rd_check_is_filtered(rd, "pid", pid))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
+		/* discard const from mnl_attr_get_str */
+		comm = (char *)mnl_attr_get_str(
+			nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
+
+	if (rd->json_output)
+		jsonw_start_array(rd->jw);
+
+	print_link(rd, idx, name, port, nla_line);
+
+	res_print_uint(rd, "lqpn", lqpn);
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
+		res_print_uint(rd, "pdn", pdn);
+	print_rqpn(rd, rqpn, nla_line);
+
+	print_type(rd, type);
+	print_state(rd, state);
+
+	print_rqpsn(rd, rq_psn, nla_line);
+	res_print_uint(rd, "sq-psn", sq_psn);
+
+	print_pathmig(rd, path_mig_state, nla_line);
+	res_print_uint(rd, "pid", pid);
+	print_comm(rd, comm, nla_line);
+
+	print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
+	newline(rd);
+out:
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
+		free(comm);
+	return MNL_CB_OK;
+}
+
 int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
 	struct nlattr *nla_table, *nla_entry;
 	struct rd *rd = data;
+	int ret = MNL_CB_OK;
 	const char *name;
 	uint32_t idx;
 
@@ -96,131 +218,10 @@ int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 	nla_table = tb[RDMA_NLDEV_ATTR_RES_QP];
 
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
-		uint32_t lqpn, rqpn = 0, rq_psn = 0, sq_psn;
-		uint8_t type, state, path_mig_state = 0;
-		uint32_t port = 0, pid = 0;
-		uint32_t pdn = 0;
-		char *comm = NULL;
-		int err;
+		ret = res_qp_line(rd, name, idx, nla_entry);
 
-		err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-		if (err != MNL_CB_OK)
-			return MNL_CB_ERROR;
-
-		if (!nla_line[RDMA_NLDEV_ATTR_RES_LQPN] ||
-		    !nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN] ||
-		    !nla_line[RDMA_NLDEV_ATTR_RES_TYPE] ||
-		    !nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
-		    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
-		     !nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])) {
-			return MNL_CB_ERROR;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_PORT_INDEX])
-			port = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_PORT_INDEX]);
-
-		if (port != rd->port_idx)
-			continue;
-
-		lqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
-		if (rd_check_is_filtered(rd, "lqpn", lqpn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			pdn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
-		if (rd_check_is_filtered(rd, "pdn", pdn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_RQPN]) {
-			rqpn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_RQPN]);
-			if (rd_check_is_filtered(rd, "rqpn", rqpn))
-				continue;
-		} else {
-			if (rd_check_is_key_exist(rd, "rqpn"))
-				continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]) {
-			rq_psn = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]);
-			if (rd_check_is_filtered(rd, "rq-psn", rq_psn))
-				continue;
-		} else {
-			if (rd_check_is_key_exist(rd, "rq-psn"))
-				continue;
-		}
-
-		sq_psn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN]);
-		if (rd_check_is_filtered(rd, "sq-psn", sq_psn))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]) {
-			path_mig_state = mnl_attr_get_u8(
-				nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]);
-			if (rd_check_is_string_filtered(
-				    rd, "path-mig-state",
-				    path_mig_to_str(path_mig_state)))
-				continue;
-		} else {
-			if (rd_check_is_key_exist(rd, "path-mig-state"))
-				continue;
-		}
-
-		type = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
-		if (rd_check_is_string_filtered(rd, "type",
-						qp_types_to_str(type)))
-			continue;
-
-		state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
-		if (rd_check_is_string_filtered(rd, "state",
-						qp_states_to_str(state)))
-			continue;
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
-			pid = mnl_attr_get_u32(
-				nla_line[RDMA_NLDEV_ATTR_RES_PID]);
-			comm = get_task_name(pid);
-		}
-
-		if (rd_check_is_filtered(rd, "pid", pid)) {
-			free(comm);
-			continue;
-		}
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
-			/* discard const from mnl_attr_get_str */
-			comm = (char *)mnl_attr_get_str(
-				nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]);
-
-		if (rd->json_output)
-			jsonw_start_array(rd->jw);
-
-		print_link(rd, idx, name, port, nla_line);
-
-		res_print_uint(rd, "lqpn", lqpn);
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-			res_print_uint(rd, "pdn", pdn);
-		print_rqpn(rd, rqpn, nla_line);
-
-		print_type(rd, type);
-		print_state(rd, state);
-
-		print_rqpsn(rd, rq_psn, nla_line);
-		res_print_uint(rd, "sq-psn", sq_psn);
-
-		print_pathmig(rd, path_mig_state, nla_line);
-		res_print_uint(rd, "pid", pid);
-		print_comm(rd, comm, nla_line);
-
-		if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
-			free(comm);
-
-		print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
-		newline(rd);
+		if (ret != MNL_CB_OK)
+			break;
 	}
-	return MNL_CB_OK;
+	return ret;
 }

From 127ff95610636aaff24e22b5b0909f16bb5cd2dd Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:26 +0200
Subject: [PATCH 35/55] rdma: Unify netlink attribute checks prior to prints

Place check if netlink attribute available in general place,
instead of doing the same check in many paces.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/res-cmid.c |  9 ++++-----
 rdma/res-cq.c   | 22 +++++++++++-----------
 rdma/res-mr.c   | 21 +++++++--------------
 rdma/res-pd.c   | 20 +++++++++-----------
 rdma/res-qp.c   | 10 +++++-----
 rdma/res.c      | 16 +++++++++++++---
 rdma/res.h      |  6 ++++--
 7 files changed, 53 insertions(+), 51 deletions(-)

diff --git a/rdma/res-cmid.c b/rdma/res-cmid.c
index 12d1acee..22d99a8b 100644
--- a/rdma/res-cmid.c
+++ b/rdma/res-cmid.c
@@ -202,16 +202,15 @@ static int res_cm_id_line(struct rd *rd, const char *name, int idx,
 		jsonw_start_array(rd->jw);
 
 	print_link(rd, idx, name, port, nla_line);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN])
-		res_print_uint(rd, "lqpn", lqpn);
+	res_print_uint(rd, "cm-idn", cm_idn,
+		       nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN]);
+	res_print_uint(rd, "lqpn", lqpn, nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
 	if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE])
 		print_qp_type(rd, type);
 	print_cm_id_state(rd, state);
 	print_ps(rd, ps);
-	res_print_uint(rd, "pid", pid);
+	res_print_uint(rd, "pid", pid, nla_line[RDMA_NLDEV_ATTR_RES_PID]);
 	print_comm(rd, comm, nla_line);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
-		res_print_uint(rd, "cm-idn", cm_idn);
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR])
 		print_ipaddr(rd, "src-addr", src_addr_str, src_port);
diff --git a/rdma/res-cq.c b/rdma/res-cq.c
index e50d76ce..cea4f6bd 100644
--- a/rdma/res-cq.c
+++ b/rdma/res-cq.c
@@ -17,8 +17,11 @@ static const char *poll_ctx_to_str(uint8_t idx)
 	return "UNKNOWN";
 }
 
-static void print_poll_ctx(struct rd *rd, uint8_t poll_ctx)
+static void print_poll_ctx(struct rd *rd, uint8_t poll_ctx, struct nlattr *attr)
 {
+	if (!attr)
+		return;
+
 	if (rd->json_output) {
 		jsonw_string_field(rd->jw, "poll-ctx",
 				   poll_ctx_to_str(poll_ctx));
@@ -92,18 +95,15 @@ static int res_cq_line(struct rd *rd, const char *name, int idx,
 		jsonw_start_array(rd->jw);
 
 	print_dev(rd, idx, name);
-	res_print_uint(rd, "cqe", cqe);
-	res_print_uint(rd, "users", users);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX])
-		print_poll_ctx(rd, poll_ctx);
-	res_print_uint(rd, "pid", pid);
+	res_print_uint(rd, "cqn", cqn, nla_line[RDMA_NLDEV_ATTR_RES_CQN]);
+	res_print_uint(rd, "cqe", cqe, nla_line[RDMA_NLDEV_ATTR_RES_CQE]);
+	res_print_uint(rd, "users", users,
+		       nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
+	print_poll_ctx(rd, poll_ctx, nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]);
+	res_print_uint(rd, "ctxn", ctxn, nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
+	res_print_uint(rd, "pid", pid, nla_line[RDMA_NLDEV_ATTR_RES_PID]);
 	print_comm(rd, comm, nla_line);
 
-	if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
-		res_print_uint(rd, "cqn", cqn);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
-		res_print_uint(rd, "ctxn", ctxn);
-
 	print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
 	newline(rd);
 
diff --git a/rdma/res-mr.c b/rdma/res-mr.c
index 36993b5e..82e6d150 100644
--- a/rdma/res-mr.c
+++ b/rdma/res-mr.c
@@ -67,22 +67,15 @@ static int res_mr_line(struct rd *rd, const char *name, int idx,
 		jsonw_start_array(rd->jw);
 
 	print_dev(rd, idx, name);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_RKEY])
-		print_key(rd, "rkey", rkey);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_LKEY])
-		print_key(rd, "lkey", lkey);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_IOVA])
-		print_key(rd, "iova", iova);
-	res_print_uint(rd, "mrlen", mrlen);
-	res_print_uint(rd, "pid", pid);
+	res_print_uint(rd, "mrn", mrn, nla_line[RDMA_NLDEV_ATTR_RES_MRN]);
+	print_key(rd, "rkey", rkey, nla_line[RDMA_NLDEV_ATTR_RES_RKEY]);
+	print_key(rd, "lkey", lkey, nla_line[RDMA_NLDEV_ATTR_RES_LKEY]);
+	print_key(rd, "iova", iova, nla_line[RDMA_NLDEV_ATTR_RES_IOVA]);
+	res_print_uint(rd, "mrlen", mrlen, nla_line[RDMA_NLDEV_ATTR_RES_MRLEN]);
+	res_print_uint(rd, "pdn", pdn, nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+	res_print_uint(rd, "pid", pid, nla_line[RDMA_NLDEV_ATTR_RES_PID]);
 	print_comm(rd, comm, nla_line);
 
-	if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
-		res_print_uint(rd, "mrn", mrn);
-
-	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-		res_print_uint(rd, "pdn", pdn);
-
 	print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
 	newline(rd);
 
diff --git a/rdma/res-pd.c b/rdma/res-pd.c
index 3c9ffa4e..e8c042dc 100644
--- a/rdma/res-pd.c
+++ b/rdma/res-pd.c
@@ -69,18 +69,16 @@ static int res_pd_line(struct rd *rd, const char *name, int idx,
 		jsonw_start_array(rd->jw);
 
 	print_dev(rd, idx, name);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY])
-		print_key(rd, "local_dma_lkey", local_dma_lkey);
-	res_print_uint(rd, "users", users);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
-		print_key(rd, "unsafe_global_rkey", unsafe_global_rkey);
-	res_print_uint(rd, "pid", pid);
+	res_print_uint(rd, "pdn", pdn, nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+	print_key(rd, "local_dma_lkey", local_dma_lkey,
+		  nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY]);
+	res_print_uint(rd, "users", users,
+		       nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
+	print_key(rd, "unsafe_global_rkey", unsafe_global_rkey,
+		  nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY]);
+	res_print_uint(rd, "ctxn", ctxn, nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
+	res_print_uint(rd, "pid", pid, nla_line[RDMA_NLDEV_ATTR_RES_PID]);
 	print_comm(rd, comm, nla_line);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
-		res_print_uint(rd, "ctxn", ctxn);
-
-	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-		res_print_uint(rd, "pdn", pdn);
 
 	print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
 	newline(rd);
diff --git a/rdma/res-qp.c b/rdma/res-qp.c
index e74c8b01..5d5ef27b 100644
--- a/rdma/res-qp.c
+++ b/rdma/res-qp.c
@@ -176,19 +176,19 @@ static int res_qp_line(struct rd *rd, const char *name, int idx,
 
 	print_link(rd, idx, name, port, nla_line);
 
-	res_print_uint(rd, "lqpn", lqpn);
-	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
-		res_print_uint(rd, "pdn", pdn);
+	res_print_uint(rd, "lqpn", lqpn, nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
 	print_rqpn(rd, rqpn, nla_line);
 
 	print_type(rd, type);
 	print_state(rd, state);
 
 	print_rqpsn(rd, rq_psn, nla_line);
-	res_print_uint(rd, "sq-psn", sq_psn);
+	res_print_uint(rd, "sq-psn", sq_psn,
+		       nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN]);
 
 	print_pathmig(rd, path_mig_state, nla_line);
-	res_print_uint(rd, "pid", pid);
+	res_print_uint(rd, "pdn", pdn, nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
+	res_print_uint(rd, "pid", pid, nla_line[RDMA_NLDEV_ATTR_RES_PID]);
 	print_comm(rd, comm, nla_line);
 
 	print_driver_table(rd, nla_line[RDMA_NLDEV_ATTR_DRIVER]);
diff --git a/rdma/res.c b/rdma/res.c
index 140c0908..564af9b4 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -47,7 +47,9 @@ static int res_print_summary(struct rd *rd, struct nlattr **tb)
 
 		name = mnl_attr_get_str(nla_line[RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_NAME]);
 		curr = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_CURR]);
-		res_print_uint(rd, name, curr);
+		res_print_uint(
+			rd, name, curr,
+			nla_line[RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_CURR]);
 	}
 	return 0;
 }
@@ -188,16 +190,24 @@ char *get_task_name(uint32_t pid)
 	return comm;
 }
 
-void print_key(struct rd *rd, const char *name, uint64_t val)
+void print_key(struct rd *rd, const char *name, uint64_t val,
+	       struct nlattr *nlattr)
 {
+	if (!nlattr)
+		return;
+
 	if (rd->json_output)
 		jsonw_xint_field(rd->jw, name, val);
 	else
 		pr_out("%s 0x%" PRIx64 " ", name, val);
 }
 
-void res_print_uint(struct rd *rd, const char *name, uint64_t val)
+void res_print_uint(struct rd *rd, const char *name, uint64_t val,
+		    struct nlattr *nlattr)
 {
+	if (!nlattr)
+		return;
+
 	if (rd->json_output)
 		jsonw_u64_field(rd->jw, name, val);
 	else
diff --git a/rdma/res.h b/rdma/res.h
index 89dd818a..575e1192 100644
--- a/rdma/res.h
+++ b/rdma/res.h
@@ -112,8 +112,10 @@ char *get_task_name(uint32_t pid);
 void print_dev(struct rd *rd, uint32_t idx, const char *name);
 void print_link(struct rd *rd, uint32_t idx, const char *name, uint32_t port,
 		struct nlattr **nla_line);
-void print_key(struct rd *rd, const char *name, uint64_t val);
-void res_print_uint(struct rd *rd, const char *name, uint64_t val);
+void print_key(struct rd *rd, const char *name, uint64_t val,
+	       struct nlattr *nlattr);
+void res_print_uint(struct rd *rd, const char *name, uint64_t val,
+		    struct nlattr *nlattr);
 void print_comm(struct rd *rd, const char *str, struct nlattr **nla_line);
 const char *qp_types_to_str(uint8_t idx);
 

From 5a823593d65e946afe5d62f2146bed47fb145fa6 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:27 +0200
Subject: [PATCH 36/55] rdma: Perform single .doit call to query specific
 objects

If user provides specific index, we can speedup query
by using .doit callback and save full dump and filtering
after that.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/rdma.h     | 10 +++++-
 rdma/res-cmid.c | 33 ++++++++++++-----
 rdma/res-cq.c   | 34 +++++++++++++-----
 rdma/res-mr.c   | 33 ++++++++++++-----
 rdma/res-pd.c   | 32 ++++++++++++-----
 rdma/res-qp.c   | 32 ++++++++++++-----
 rdma/res.c      | 34 +++++++++++++++++-
 rdma/res.h      | 94 +++++++++++++++++++++++++++++++------------------
 rdma/utils.c    | 20 +++++++++++
 9 files changed, 244 insertions(+), 78 deletions(-)

diff --git a/rdma/rdma.h b/rdma/rdma.h
index d2559e7c..e86c7f21 100644
--- a/rdma/rdma.h
+++ b/rdma/rdma.h
@@ -30,13 +30,20 @@
 #define MAX_NUMBER_OF_FILTERS 64
 struct filters {
 	const char *name;
-	bool is_number;
+	uint8_t is_number:1;
+	uint8_t is_doit:1;
 };
 
 struct filter_entry {
 	struct list_head list;
 	char *key;
 	char *value;
+	/*
+	 * This field menas that we can try to issue .doit calback
+	 * on value above. This value can be converted to integer
+	 * with simple atoi(). Otherwise "is_doit" will be false.
+	 */
+	uint8_t is_doit:1;
 };
 
 struct dev_map {
@@ -101,6 +108,7 @@ struct dev_map *dev_map_lookup(struct rd *rd, bool allow_port_index);
 /*
  * Filter manipulation
  */
+bool rd_doit_index(struct rd *rd, uint32_t *idx);
 int rd_build_filter(struct rd *rd, const struct filters valid_filters[]);
 bool rd_check_is_filtered(struct rd *rd, const char *key, uint32_t val);
 bool rd_check_is_string_filtered(struct rd *rd, const char *key, const char *val);
diff --git a/rdma/res-cmid.c b/rdma/res-cmid.c
index 22d99a8b..0b61e433 100644
--- a/rdma/res-cmid.c
+++ b/rdma/res-cmid.c
@@ -107,11 +107,9 @@ static int ss_ntop(struct nlattr *nla_line, char *addr_str, uint16_t *port)
 	}
 	return 0;
 }
-
 static int res_cm_id_line(struct rd *rd, const char *name, int idx,
-			  struct nlattr *nla_entry)
+		       struct nlattr **nla_line)
 {
-	struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 	char src_addr_str[INET6_ADDRSTRLEN];
 	char dst_addr_str[INET6_ADDRSTRLEN];
 	uint16_t src_port, dst_port;
@@ -120,11 +118,6 @@ static int res_cm_id_line(struct rd *rd, const char *name, int idx,
 	uint32_t lqpn = 0, ps;
 	uint32_t cm_idn = 0;
 	char *comm = NULL;
-	int err;
-
-	err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-	if (err != MNL_CB_OK)
-		return MNL_CB_ERROR;
 
 	if (!nla_line[RDMA_NLDEV_ATTR_RES_STATE] ||
 	    !nla_line[RDMA_NLDEV_ATTR_RES_PS] ||
@@ -225,6 +218,23 @@ out:	if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
 	return MNL_CB_OK;
 }
 
+int res_cm_id_idx_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct rd *rd = data;
+	const char *name;
+	int idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+
+	return res_cm_id_line(rd, name, idx, tb);
+}
+
 int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
@@ -244,8 +254,13 @@ int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data)
 	nla_table = tb[RDMA_NLDEV_ATTR_RES_CM_ID];
 
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		ret = res_cm_id_line(rd, name, idx, nla_entry);
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 
+		ret = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (ret != MNL_CB_OK)
+			break;
+
+		ret = res_cm_id_line(rd, name, idx, nla_line);
 		if (ret != MNL_CB_OK)
 			break;
 	}
diff --git a/rdma/res-cq.c b/rdma/res-cq.c
index cea4f6bd..c14637e6 100644
--- a/rdma/res-cq.c
+++ b/rdma/res-cq.c
@@ -31,9 +31,8 @@ static void print_poll_ctx(struct rd *rd, uint8_t poll_ctx, struct nlattr *attr)
 }
 
 static int res_cq_line(struct rd *rd, const char *name, int idx,
-		       struct nlattr *nla_entry)
+		       struct nlattr **nla_line)
 {
-	struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 	char *comm = NULL;
 	uint32_t pid = 0;
 	uint8_t poll_ctx = 0;
@@ -41,11 +40,6 @@ static int res_cq_line(struct rd *rd, const char *name, int idx,
 	uint32_t cqn = 0;
 	uint64_t users;
 	uint32_t cqe;
-	int err;
-
-	err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-	if (err != MNL_CB_OK)
-		return MNL_CB_ERROR;
 
 	if (!nla_line[RDMA_NLDEV_ATTR_RES_CQE] ||
 	    !nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
@@ -80,7 +74,6 @@ static int res_cq_line(struct rd *rd, const char *name, int idx,
 		cqn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CQN]);
 	if (rd_check_is_filtered(rd, "cqn", cqn))
 		goto out;
-
 	if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
 		ctxn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
 	if (rd_check_is_filtered(rd, "ctxn", ctxn))
@@ -112,6 +105,23 @@ out:	if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
 	return MNL_CB_OK;
 }
 
+int res_cq_idx_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+
+	return res_cq_line(rd, name, idx, tb);
+}
+
 int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
@@ -131,7 +141,13 @@ int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data)
 	nla_table = tb[RDMA_NLDEV_ATTR_RES_CQ];
 
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		ret = res_cq_line(rd, name, idx, nla_entry);
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
+
+		ret = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (ret != MNL_CB_OK)
+			break;
+
+		ret = res_cq_line(rd, name, idx, nla_line);
 
 		if (ret != MNL_CB_OK)
 			break;
diff --git a/rdma/res-mr.c b/rdma/res-mr.c
index 82e6d150..d42e8d81 100644
--- a/rdma/res-mr.c
+++ b/rdma/res-mr.c
@@ -8,20 +8,14 @@
 #include <inttypes.h>
 
 static int res_mr_line(struct rd *rd, const char *name, int idx,
-		       struct nlattr *nla_entry)
+		       struct nlattr **nla_line)
 {
-	struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 	uint32_t rkey = 0, lkey = 0;
 	uint64_t iova = 0, mrlen;
 	char *comm = NULL;
 	uint32_t pdn = 0;
 	uint32_t mrn = 0;
 	uint32_t pid = 0;
-	int err;
-
-	err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-	if (err != MNL_CB_OK)
-		return MNL_CB_ERROR;
 
 	if (!nla_line[RDMA_NLDEV_ATTR_RES_MRLEN] ||
 	    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
@@ -84,6 +78,24 @@ out:
 		free(comm);
 	return MNL_CB_OK;
 }
+
+int res_mr_idx_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+
+	return res_mr_line(rd, name, idx, tb);
+}
+
 int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
@@ -103,8 +115,13 @@ int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data)
 	nla_table = tb[RDMA_NLDEV_ATTR_RES_MR];
 
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		ret = res_mr_line(rd, name, idx, nla_entry);
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 
+		ret = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (ret != MNL_CB_OK)
+			break;
+
+		ret = res_mr_line(rd, name, idx, nla_line);
 		if (ret != MNL_CB_OK)
 			break;
 	}
diff --git a/rdma/res-pd.c b/rdma/res-pd.c
index e8c042dc..956d4d9f 100644
--- a/rdma/res-pd.c
+++ b/rdma/res-pd.c
@@ -8,20 +8,14 @@
 #include <inttypes.h>
 
 static int res_pd_line(struct rd *rd, const char *name, int idx,
-		       struct nlattr *nla_entry)
+		       struct nlattr **nla_line)
 {
 	uint32_t local_dma_lkey = 0, unsafe_global_rkey = 0;
-	struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 	char *comm = NULL;
 	uint32_t ctxn = 0;
 	uint32_t pid = 0;
 	uint32_t pdn = 0;
 	uint64_t users;
-	int err;
-
-	err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-	if (err != MNL_CB_OK)
-		return MNL_CB_ERROR;
 
 	if (!nla_line[RDMA_NLDEV_ATTR_RES_USECNT] ||
 	    (!nla_line[RDMA_NLDEV_ATTR_RES_PID] &&
@@ -88,6 +82,23 @@ out:	if (nla_line[RDMA_NLDEV_ATTR_RES_PID])
 	return MNL_CB_OK;
 }
 
+int res_pd_idx_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+
+	return res_pd_line(rd, name, idx, tb);
+}
+
 int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
@@ -107,8 +118,13 @@ int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data)
 	nla_table = tb[RDMA_NLDEV_ATTR_RES_PD];
 
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		ret = res_pd_line(rd, name, idx, nla_entry);
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 
+		ret = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (ret != MNL_CB_OK)
+			break;
+
+		ret = res_pd_line(rd, name, idx, nla_line);
 		if (ret != MNL_CB_OK)
 			break;
 	}
diff --git a/rdma/res-qp.c b/rdma/res-qp.c
index 5d5ef27b..ac9976fc 100644
--- a/rdma/res-qp.c
+++ b/rdma/res-qp.c
@@ -79,19 +79,13 @@ static void print_pathmig(struct rd *rd, uint32_t val, struct nlattr **nla_line)
 }
 
 static int res_qp_line(struct rd *rd, const char *name, int idx,
-		       struct nlattr *nla_entry)
+		       struct nlattr **nla_line)
 {
-	struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 	uint32_t lqpn, rqpn = 0, rq_psn = 0, sq_psn;
 	uint8_t type, state, path_mig_state = 0;
 	uint32_t port = 0, pid = 0;
 	uint32_t pdn = 0;
 	char *comm = NULL;
-	int err;
-
-	err = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
-	if (err != MNL_CB_OK)
-		return MNL_CB_ERROR;
 
 	if (!nla_line[RDMA_NLDEV_ATTR_RES_LQPN] ||
 	    !nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN] ||
@@ -199,6 +193,23 @@ out:
 	return MNL_CB_OK;
 }
 
+int res_qp_idx_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
+	struct rd *rd = data;
+	const char *name;
+	uint32_t idx;
+
+	mnl_attr_parse(nlh, 0, rd_attr_cb, tb);
+	if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME])
+		return MNL_CB_ERROR;
+
+	name = mnl_attr_get_str(tb[RDMA_NLDEV_ATTR_DEV_NAME]);
+	idx = mnl_attr_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+
+	return res_qp_line(rd, name, idx, tb);
+}
+
 int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
@@ -218,8 +229,13 @@ int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data)
 	nla_table = tb[RDMA_NLDEV_ATTR_RES_QP];
 
 	mnl_attr_for_each_nested(nla_entry, nla_table) {
-		ret = res_qp_line(rd, name, idx, nla_entry);
+		struct nlattr *nla_line[RDMA_NLDEV_ATTR_MAX] = {};
 
+		ret = mnl_attr_parse_nested(nla_entry, rd_attr_cb, nla_line);
+		if (ret != MNL_CB_OK)
+			break;
+
+		ret = res_qp_line(rd, name, idx, nla_line);
 		if (ret != MNL_CB_OK)
 			break;
 	}
diff --git a/rdma/res.c b/rdma/res.c
index 564af9b4..ef863f14 100644
--- a/rdma/res.c
+++ b/rdma/res.c
@@ -54,6 +54,11 @@ static int res_print_summary(struct rd *rd, struct nlattr **tb)
 	return 0;
 }
 
+static int res_no_args_idx_parse_cb(const struct nlmsghdr *nlh, void *data)
+{
+	return MNL_CB_OK;
+}
+
 static int res_no_args_parse_cb(const struct nlmsghdr *nlh, void *data)
 {
 	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX] = {};
@@ -83,6 +88,33 @@ static int res_no_args_parse_cb(const struct nlmsghdr *nlh, void *data)
 	return MNL_CB_OK;
 }
 
+int _res_send_idx_msg(struct rd *rd, uint32_t command, mnl_cb_t callback,
+		      uint32_t idx, uint32_t id)
+{
+	uint32_t flags = NLM_F_REQUEST | NLM_F_ACK;
+	uint32_t seq;
+	int ret;
+
+	rd_prepare_msg(rd, command, &seq, flags);
+	mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_DEV_INDEX, rd->dev_idx);
+	if (rd->port_idx)
+		mnl_attr_put_u32(rd->nlh,
+				 RDMA_NLDEV_ATTR_PORT_INDEX, rd->port_idx);
+
+	mnl_attr_put_u32(rd->nlh, id, idx);
+
+	ret = rd_send_msg(rd);
+	if (ret)
+		return ret;
+
+	if (rd->json_output)
+		jsonw_start_object(rd->jw);
+	ret = rd_recv_msg(rd, callback, rd, seq);
+	if (rd->json_output)
+		jsonw_end_object(rd->jw);
+	return ret;
+}
+
 int _res_send_msg(struct rd *rd, uint32_t command, mnl_cb_t callback)
 {
 	uint32_t flags = NLM_F_REQUEST | NLM_F_ACK;
@@ -214,7 +246,7 @@ void res_print_uint(struct rd *rd, const char *name, uint64_t val,
 		pr_out("%s %" PRIu64 " ", name, val);
 }
 
-RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true);
+RES_FUNC(res_no_args,	RDMA_NLDEV_CMD_RES_GET,	NULL, true, 0);
 
 static int res_show(struct rd *rd)
 {
diff --git a/rdma/res.h b/rdma/res.h
index 575e1192..b4a7e552 100644
--- a/rdma/res.h
+++ b/rdma/res.h
@@ -9,31 +9,52 @@
 #include "rdma.h"
 
 int _res_send_msg(struct rd *rd, uint32_t command, mnl_cb_t callback);
-int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data);
-int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data);
-int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data);
-int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data);
-int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data);
+int _res_send_idx_msg(struct rd *rd, uint32_t command, mnl_cb_t callback,
+		      uint32_t idx, uint32_t id);
 
-#define RES_FUNC(name, command, valid_filters, strict_port) \
-	static inline int _##name(struct rd *rd)\
-	{ \
-		return _res_send_msg(rd, command, name##_parse_cb); \
-	} \
-	static inline int name(struct rd *rd) \
-	{\
-		int ret = rd_build_filter(rd, valid_filters); \
-		if (ret) \
-			return ret; \
-		if ((uintptr_t)valid_filters != (uintptr_t)NULL) { \
-			ret = rd_set_arg_to_devname(rd); \
-			if (ret) \
-				return ret;\
-		} \
-		if (strict_port) \
-			return rd_exec_dev(rd, _##name); \
-		else \
-			return rd_exec_link(rd, _##name, strict_port); \
+int res_pd_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_pd_idx_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_mr_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_mr_idx_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_cq_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_cq_idx_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_cm_id_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_cm_id_idx_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_qp_parse_cb(const struct nlmsghdr *nlh, void *data);
+int res_qp_idx_parse_cb(const struct nlmsghdr *nlh, void *data);
+
+#define RES_FUNC(name, command, valid_filters, strict_port, id)                        \
+	static inline int _##name(struct rd *rd)                                       \
+	{                                                                              \
+		uint32_t idx;                                                          \
+		int ret;                                                               \
+		if (id) {                                                              \
+			ret = rd_doit_index(rd, &idx);                                 \
+			if (ret) {                                                     \
+				ret = _res_send_idx_msg(rd, command,                   \
+							name##_idx_parse_cb,           \
+							idx, id);                      \
+				if (!ret)                                              \
+					return ret;                                    \
+				/* Fallback for old systems without .doit callbacks */ \
+			}                                                              \
+		}                                                                      \
+		return _res_send_msg(rd, command, name##_parse_cb);                    \
+	}                                                                              \
+	static inline int name(struct rd *rd)                                          \
+	{                                                                              \
+		int ret = rd_build_filter(rd, valid_filters);                          \
+		if (ret)                                                               \
+			return ret;                                                    \
+		if ((uintptr_t)valid_filters != (uintptr_t)NULL) {                     \
+			ret = rd_set_arg_to_devname(rd);                               \
+			if (ret)                                                       \
+				return ret;                                            \
+		}                                                                      \
+		if (strict_port)                                                       \
+			return rd_exec_dev(rd, _##name);                               \
+		else                                                                   \
+			return rd_exec_link(rd, _##name, strict_port);                 \
 	}
 
 static const
@@ -42,11 +63,12 @@ struct filters pd_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "users", .is_number = true },
 	{ .name = "pid", .is_number = true },
 	{ .name = "ctxn", .is_number = true },
-	{ .name = "pdn", .is_number = true },
+	{ .name = "pdn", .is_number = true, .is_doit = true },
 	{ .name = "ctxn", .is_number = true }
 };
 
-RES_FUNC(res_pd, RDMA_NLDEV_CMD_RES_PD_GET, pd_valid_filters, true);
+RES_FUNC(res_pd, RDMA_NLDEV_CMD_RES_PD_GET, pd_valid_filters, true,
+	 RDMA_NLDEV_ATTR_RES_PDN);
 
 static const
 struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
@@ -55,11 +77,12 @@ struct filters mr_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "lkey", .is_number = true },
 	{ .name = "mrlen", .is_number = true },
 	{ .name = "pid", .is_number = true },
-	{ .name = "mrn", .is_number = true },
+	{ .name = "mrn", .is_number = true, .is_doit = true },
 	{ .name = "pdn", .is_number = true }
 };
 
-RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true);
+RES_FUNC(res_mr, RDMA_NLDEV_CMD_RES_MR_GET, mr_valid_filters, true,
+	 RDMA_NLDEV_ATTR_RES_MRN);
 
 static const
 struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
@@ -67,11 +90,12 @@ struct filters cq_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "users", .is_number = true },
 	{ .name = "poll-ctx", .is_number = false },
 	{ .name = "pid", .is_number = true },
-	{ .name = "cqn", .is_number = true },
+	{ .name = "cqn", .is_number = true, .is_doit = true },
 	{ .name = "ctxn", .is_number = true }
 };
 
-RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true);
+RES_FUNC(res_cq, RDMA_NLDEV_CMD_RES_CQ_GET, cq_valid_filters, true,
+	 RDMA_NLDEV_ATTR_RES_CQN);
 
 static const
 struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
@@ -87,15 +111,16 @@ struct filters cm_id_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "src-port", .is_number = true },
 	{ .name = "dst-addr", .is_number = false },
 	{ .name = "dst-port", .is_number = true },
-	{ .name = "cm-idn", .is_number = true }
+	{ .name = "cm-idn", .is_number = true, .is_doit = true }
 };
 
-RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false);
+RES_FUNC(res_cm_id, RDMA_NLDEV_CMD_RES_CM_ID_GET, cm_id_valid_filters, false,
+	 RDMA_NLDEV_ATTR_RES_CM_IDN);
 
 static const struct
 filters qp_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "link", .is_number = false },
-	{ .name = "lqpn", .is_number = true },
+	{ .name = "lqpn", .is_number = true, .is_doit = true },
 	{ .name = "rqpn", .is_number = true },
 	{ .name = "pid",  .is_number = true },
 	{ .name = "sq-psn", .is_number = true },
@@ -106,7 +131,8 @@ filters qp_valid_filters[MAX_NUMBER_OF_FILTERS] = {
 	{ .name = "pdn", .is_number = true },
 };
 
-RES_FUNC(res_qp,	RDMA_NLDEV_CMD_RES_QP_GET, qp_valid_filters, false);
+RES_FUNC(res_qp, RDMA_NLDEV_CMD_RES_QP_GET, qp_valid_filters, false,
+	 RDMA_NLDEV_ATTR_RES_LQPN);
 
 char *get_task_name(uint32_t pid);
 void print_dev(struct rd *rd, uint32_t idx, const char *name);
diff --git a/rdma/utils.c b/rdma/utils.c
index bce052d5..cff5297d 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -121,6 +121,7 @@ static int add_filter(struct rd *rd, char *key, char *value,
 	struct filter_entry *fe;
 	bool key_found = false;
 	int idx = 0;
+	char *endp;
 	int ret;
 
 	fe = calloc(1, sizeof(*fe));
@@ -163,6 +164,11 @@ static int add_filter(struct rd *rd, char *key, char *value,
 		goto err_alloc;
 	}
 
+	errno = 0;
+	strtol(fe->value, &endp, 10);
+	if (valid_filters[idx].is_doit && !errno && *endp == '\0')
+		fe->is_doit = true;
+
 	for (idx = 0; idx < strlen(fe->value); idx++)
 		fe->value[idx] = tolower(fe->value[idx]);
 
@@ -177,6 +183,20 @@ err:
 	return ret;
 }
 
+bool rd_doit_index(struct rd *rd, uint32_t *idx)
+{
+	struct filter_entry *fe;
+
+	list_for_each_entry(fe, &rd->filter_list, list) {
+		if (fe->is_doit) {
+			*idx = atoi(fe->value);
+			return true;
+		}
+	}
+
+	return false;
+}
+
 int rd_build_filter(struct rd *rd, const struct filters valid_filters[])
 {
 	int ret = 0;

From 78728b7ee0fe3ca449080095ac237e125a44dd27 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 23 Feb 2019 11:15:28 +0200
Subject: [PATCH 37/55] rdma: Provide and reuse filter functions

Globally replace all filter function in safer variants of those
is_filtered functions, which take into account the availability/lack
of netlink attributes.

Such conversion allowed to fix a number of places in the code, where
the previous implementation didn't honor filter requests if netlink
attribute wasn't present.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/rdma.h     |  7 +++---
 rdma/res-cmid.c | 57 +++++++++++++++++++++++++++----------------------
 rdma/res-cq.c   | 22 +++++++++++--------
 rdma/res-mr.c   | 12 +++++++----
 rdma/res-pd.c   | 12 +++++++----
 rdma/res-qp.c   | 53 ++++++++++++++++++++++-----------------------
 rdma/utils.c    | 26 ++++++++++++++++++----
 7 files changed, 112 insertions(+), 77 deletions(-)

diff --git a/rdma/rdma.h b/rdma/rdma.h
index e86c7f21..1022e9a2 100644
--- a/rdma/rdma.h
+++ b/rdma/rdma.h
@@ -110,9 +110,10 @@ struct dev_map *dev_map_lookup(struct rd *rd, bool allow_port_index);
  */
 bool rd_doit_index(struct rd *rd, uint32_t *idx);
 int rd_build_filter(struct rd *rd, const struct filters valid_filters[]);
-bool rd_check_is_filtered(struct rd *rd, const char *key, uint32_t val);
-bool rd_check_is_string_filtered(struct rd *rd, const char *key, const char *val);
-bool rd_check_is_key_exist(struct rd *rd, const char *key);
+bool rd_is_filtered_attr(struct rd *rd, const char *key, uint32_t val,
+			 struct nlattr *attr);
+bool rd_is_string_filtered_attr(struct rd *rd, const char *key, const char *val,
+				struct nlattr *attr);
 /*
  * Netlink
  */
diff --git a/rdma/res-cmid.c b/rdma/res-cmid.c
index 0b61e433..0b830088 100644
--- a/rdma/res-cmid.c
+++ b/rdma/res-cmid.c
@@ -132,57 +132,64 @@ static int res_cm_id_line(struct rd *rd, const char *name, int idx,
 	if (port && port != rd->port_idx)
 		goto out;
 
-	if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN]) {
+	if (nla_line[RDMA_NLDEV_ATTR_RES_LQPN])
 		lqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
-		if (rd_check_is_filtered(rd, "lqpn", lqpn))
-			goto out;
-	}
-	if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE]) {
+
+	if (rd_is_filtered_attr(rd, "lqpn", lqpn,
+				nla_line[RDMA_NLDEV_ATTR_RES_LQPN]))
+		goto out;
+
+	if (nla_line[RDMA_NLDEV_ATTR_RES_TYPE])
 		type = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
-		if (rd_check_is_string_filtered(rd, "qp-type",
-						qp_types_to_str(type)))
-			goto out;
-	}
+	if (rd_is_string_filtered_attr(rd, "qp-type", qp_types_to_str(type),
+				       nla_line[RDMA_NLDEV_ATTR_RES_TYPE]))
+		goto out;
 
 	ps = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PS]);
-	if (rd_check_is_string_filtered(rd, "ps", cm_id_ps_to_str(ps)))
+	if (rd_is_string_filtered_attr(rd, "ps", cm_id_ps_to_str(ps),
+				       nla_line[RDMA_NLDEV_ATTR_RES_PS]))
 		goto out;
 
 	state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
-	if (rd_check_is_string_filtered(rd, "state", cm_id_state_to_str(state)))
+	if (rd_is_string_filtered_attr(rd, "state", cm_id_state_to_str(state),
+				       nla_line[RDMA_NLDEV_ATTR_RES_STATE]))
 		goto out;
 
-	if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR]) {
+	if (nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR])
 		if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR],
 			    src_addr_str, &src_port))
 			goto out;
-		if (rd_check_is_string_filtered(rd, "src-addr", src_addr_str))
-			goto out;
-		if (rd_check_is_filtered(rd, "src-port", src_port))
-			goto out;
-	}
+	if (rd_is_string_filtered_attr(rd, "src-addr", src_addr_str,
+				       nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR]))
+		goto out;
+	if (rd_is_filtered_attr(rd, "src-port", src_port,
+				nla_line[RDMA_NLDEV_ATTR_RES_SRC_ADDR]))
+		goto out;
 
-	if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR]) {
+	if (nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR])
 		if (ss_ntop(nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR],
 			    dst_addr_str, &dst_port))
 			goto out;
-		if (rd_check_is_string_filtered(rd, "dst-addr", dst_addr_str))
-			goto out;
-		if (rd_check_is_filtered(rd, "dst-port", dst_port))
-			goto out;
-	}
+	if (rd_is_string_filtered_attr(rd, "dst-addr", dst_addr_str,
+				       nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR]))
+		goto out;
+	if (rd_is_filtered_attr(rd, "dst-port", dst_port,
+				nla_line[RDMA_NLDEV_ATTR_RES_DST_ADDR]))
+		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
 		pid = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PID]);
 		comm = get_task_name(pid);
 	}
 
-	if (rd_check_is_filtered(rd, "pid", pid))
+	if (rd_is_filtered_attr(rd, "pid", pid,
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN])
 		cm_idn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN]);
-	if (rd_check_is_filtered(rd, "cm-idn", cm_idn))
+	if (rd_is_filtered_attr(rd, "cm-idn", cm_idn,
+				nla_line[RDMA_NLDEV_ATTR_RES_CM_IDN]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME]) {
diff --git a/rdma/res-cq.c b/rdma/res-cq.c
index c14637e6..5afb97c5 100644
--- a/rdma/res-cq.c
+++ b/rdma/res-cq.c
@@ -51,32 +51,36 @@ static int res_cq_line(struct rd *rd, const char *name, int idx,
 	cqe = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CQE]);
 
 	users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
-	if (rd_check_is_filtered(rd, "users", users))
+	if (rd_is_filtered_attr(rd, "users", users,
+				nla_line[RDMA_NLDEV_ATTR_RES_USECNT]))
 		goto out;
 
-	if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]) {
+	if (nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX])
 		poll_ctx =
 			mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]);
-		if (rd_check_is_string_filtered(rd, "poll-ctx",
-						poll_ctx_to_str(poll_ctx)))
-			goto out;
-	}
+	if (rd_is_string_filtered_attr(rd, "poll-ctx",
+				       poll_ctx_to_str(poll_ctx),
+				       nla_line[RDMA_NLDEV_ATTR_RES_POLL_CTX]))
+		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
 		pid = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PID]);
 		comm = get_task_name(pid);
 	}
 
-	if (rd_check_is_filtered(rd, "pid", pid))
+	if (rd_is_filtered_attr(rd, "pid", pid,
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_CQN])
 		cqn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CQN]);
-	if (rd_check_is_filtered(rd, "cqn", cqn))
+	if (rd_is_filtered_attr(rd, "cqn", cqn,
+				nla_line[RDMA_NLDEV_ATTR_RES_CQN]))
 		goto out;
 	if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
 		ctxn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
-	if (rd_check_is_filtered(rd, "ctxn", ctxn))
+	if (rd_is_filtered_attr(rd, "ctxn", ctxn,
+				nla_line[RDMA_NLDEV_ATTR_RES_CTXN]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
diff --git a/rdma/res-mr.c b/rdma/res-mr.c
index d42e8d81..f4a24dc1 100644
--- a/rdma/res-mr.c
+++ b/rdma/res-mr.c
@@ -31,7 +31,8 @@ static int res_mr_line(struct rd *rd, const char *name, int idx,
 		iova = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_IOVA]);
 
 	mrlen = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_MRLEN]);
-	if (rd_check_is_filtered(rd, "mrlen", mrlen))
+	if (rd_is_filtered_attr(rd, "mrlen", mrlen,
+				nla_line[RDMA_NLDEV_ATTR_RES_MRLEN]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
@@ -39,17 +40,20 @@ static int res_mr_line(struct rd *rd, const char *name, int idx,
 		comm = get_task_name(pid);
 	}
 
-	if (rd_check_is_filtered(rd, "pid", pid))
+	if (rd_is_filtered_attr(rd, "pid", pid,
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_MRN])
 		mrn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_MRN]);
-	if (rd_check_is_filtered(rd, "mrn", mrn))
+	if (rd_is_filtered_attr(rd, "mrn", mrn,
+				nla_line[RDMA_NLDEV_ATTR_RES_MRN]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
 		pdn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
-	if (rd_check_is_filtered(rd, "pdn", pdn))
+	if (rd_is_filtered_attr(rd, "pdn", pdn,
+				nla_line[RDMA_NLDEV_ATTR_RES_PDN]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
diff --git a/rdma/res-pd.c b/rdma/res-pd.c
index 956d4d9f..07c836e8 100644
--- a/rdma/res-pd.c
+++ b/rdma/res-pd.c
@@ -28,7 +28,8 @@ static int res_pd_line(struct rd *rd, const char *name, int idx,
 			nla_line[RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY]);
 
 	users = mnl_attr_get_u64(nla_line[RDMA_NLDEV_ATTR_RES_USECNT]);
-	if (rd_check_is_filtered(rd, "users", users))
+	if (rd_is_filtered_attr(rd, "users", users,
+				nla_line[RDMA_NLDEV_ATTR_RES_USECNT]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY])
@@ -40,18 +41,21 @@ static int res_pd_line(struct rd *rd, const char *name, int idx,
 		comm = get_task_name(pid);
 	}
 
-	if (rd_check_is_filtered(rd, "pid", pid))
+	if (rd_is_filtered_attr(rd, "pid", pid,
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_CTXN])
 		ctxn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_CTXN]);
 
-	if (rd_check_is_filtered(rd, "ctxn", ctxn))
+	if (rd_is_filtered_attr(rd, "ctxn", ctxn,
+				nla_line[RDMA_NLDEV_ATTR_RES_CTXN]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
 		pdn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
-	if (rd_check_is_filtered(rd, "pdn", pdn))
+	if (rd_is_filtered_attr(rd, "pdn", pdn,
+				nla_line[RDMA_NLDEV_ATTR_RES_PDN]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
diff --git a/rdma/res-qp.c b/rdma/res-qp.c
index ac9976fc..954e465d 100644
--- a/rdma/res-qp.c
+++ b/rdma/res-qp.c
@@ -103,53 +103,49 @@ static int res_qp_line(struct rd *rd, const char *name, int idx,
 		goto out;
 
 	lqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_LQPN]);
-	if (rd_check_is_filtered(rd, "lqpn", lqpn))
+	if (rd_is_filtered_attr(rd, "lqpn", lqpn,
+				nla_line[RDMA_NLDEV_ATTR_RES_LQPN]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_PDN])
 		pdn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_PDN]);
-	if (rd_check_is_filtered(rd, "pdn", pdn))
+	if (rd_is_filtered_attr(rd, "pdn", pdn,
+				nla_line[RDMA_NLDEV_ATTR_RES_PDN]))
 		goto out;
 
-	if (nla_line[RDMA_NLDEV_ATTR_RES_RQPN]) {
+	if (nla_line[RDMA_NLDEV_ATTR_RES_RQPN])
 		rqpn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_RQPN]);
-		if (rd_check_is_filtered(rd, "rqpn", rqpn))
-			goto out;
-	} else {
-		if (rd_check_is_key_exist(rd, "rqpn"))
-			goto out;
-	}
+	if (rd_is_filtered_attr(rd, "rqpn", rqpn,
+				nla_line[RDMA_NLDEV_ATTR_RES_RQPN]))
+		goto out;
 
-	if (nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]) {
+	if (nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN])
 		rq_psn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]);
-		if (rd_check_is_filtered(rd, "rq-psn", rq_psn))
-			goto out;
-	} else {
-		if (rd_check_is_key_exist(rd, "rq-psn"))
-			goto out;
-	}
+	if (rd_is_filtered_attr(rd, "rq-psn", rq_psn,
+				nla_line[RDMA_NLDEV_ATTR_RES_RQ_PSN]))
+		goto out;
 
 	sq_psn = mnl_attr_get_u32(nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN]);
-	if (rd_check_is_filtered(rd, "sq-psn", sq_psn))
+	if (rd_is_filtered_attr(rd, "sq-psn", sq_psn,
+				nla_line[RDMA_NLDEV_ATTR_RES_SQ_PSN]))
 		goto out;
 
-	if (nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]) {
+	if (nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE])
 		path_mig_state = mnl_attr_get_u8(
 			nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]);
-		if (rd_check_is_string_filtered(rd, "path-mig-state",
-						path_mig_to_str(path_mig_state)))
-			goto out;
-	} else {
-		if (rd_check_is_key_exist(rd, "path-mig-state"))
-			goto out;
-	}
+	if (rd_is_string_filtered_attr(
+		    rd, "path-mig-state", path_mig_to_str(path_mig_state),
+		    nla_line[RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE]))
+		goto out;
 
 	type = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_TYPE]);
-	if (rd_check_is_string_filtered(rd, "type", qp_types_to_str(type)))
+	if (rd_is_string_filtered_attr(rd, "type", qp_types_to_str(type),
+				       nla_line[RDMA_NLDEV_ATTR_RES_TYPE]))
 		goto out;
 
 	state = mnl_attr_get_u8(nla_line[RDMA_NLDEV_ATTR_RES_STATE]);
-	if (rd_check_is_string_filtered(rd, "state", qp_states_to_str(state)))
+	if (rd_is_string_filtered_attr(rd, "state", qp_states_to_str(state),
+				       nla_line[RDMA_NLDEV_ATTR_RES_STATE]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_PID]) {
@@ -157,7 +153,8 @@ static int res_qp_line(struct rd *rd, const char *name, int idx,
 		comm = get_task_name(pid);
 	}
 
-	if (rd_check_is_filtered(rd, "pid", pid))
+	if (rd_is_filtered_attr(rd, "pid", pid,
+				nla_line[RDMA_NLDEV_ATTR_RES_PID]))
 		goto out;
 
 	if (nla_line[RDMA_NLDEV_ATTR_RES_KERN_NAME])
diff --git a/rdma/utils.c b/rdma/utils.c
index cff5297d..6bc14cd5 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -233,7 +233,7 @@ out:
 	return ret;
 }
 
-bool rd_check_is_key_exist(struct rd *rd, const char *key)
+static bool rd_check_is_key_exist(struct rd *rd, const char *key)
 {
 	struct filter_entry *fe;
 
@@ -249,8 +249,8 @@ bool rd_check_is_key_exist(struct rd *rd, const char *key)
  * Check if string entry is filtered:
  *  * key doesn't exist -> user didn't request -> not filtered
  */
-bool rd_check_is_string_filtered(struct rd *rd,
-				 const char *key, const char *val)
+static bool rd_check_is_string_filtered(struct rd *rd, const char *key,
+					const char *val)
 {
 	bool key_is_filtered = false;
 	struct filter_entry *fe;
@@ -300,7 +300,7 @@ out:
  * Check if key is filtered:
  * key doesn't exist -> user didn't request -> not filtered
  */
-bool rd_check_is_filtered(struct rd *rd, const char *key, uint32_t val)
+static bool rd_check_is_filtered(struct rd *rd, const char *key, uint32_t val)
 {
 	bool key_is_filtered = false;
 	struct filter_entry *fe;
@@ -349,6 +349,24 @@ out:
 	return key_is_filtered;
 }
 
+bool rd_is_filtered_attr(struct rd *rd, const char *key, uint32_t val,
+			 struct nlattr *attr)
+{
+	if (!attr)
+		return rd_check_is_key_exist(rd, key);
+
+	return rd_check_is_filtered(rd, key, val);
+}
+
+bool rd_is_string_filtered_attr(struct rd *rd, const char *key, const char *val,
+				struct nlattr *attr)
+{
+	if (!attr)
+		rd_check_is_key_exist(rd, key);
+
+	return rd_check_is_string_filtered(rd, key, val);
+}
+
 static void filters_cleanup(struct rd *rd)
 {
 	struct filter_entry *fe, *tmp;

From 41fda879a1d6477d06cc215b2eb694c1de8681e2 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Feb 2019 08:23:22 -0800
Subject: [PATCH 38/55] Update kernel headers

Update kernel headers to commit:
    ff8285f81822 ("net: sched: pie: fix 64-bit division")

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/uapi/linux/bpf.h                  | 98 ++++++++++++++++++++---
 include/uapi/linux/devlink.h              | 30 +++++++
 include/uapi/linux/pkt_cls.h              | 45 ++++++++++-
 include/uapi/linux/pkt_sched.h            |  2 +-
 include/uapi/linux/tc_act/tc_bpf.h        |  2 -
 include/uapi/linux/tc_act/tc_connmark.h   |  2 -
 include/uapi/linux/tc_act/tc_csum.h       |  2 -
 include/uapi/linux/tc_act/tc_gact.h       |  1 -
 include/uapi/linux/tc_act/tc_ife.h        |  1 -
 include/uapi/linux/tc_act/tc_ipt.h        |  3 -
 include/uapi/linux/tc_act/tc_mirred.h     |  1 -
 include/uapi/linux/tc_act/tc_nat.h        |  2 -
 include/uapi/linux/tc_act/tc_pedit.h      |  2 -
 include/uapi/linux/tc_act/tc_sample.h     |  2 -
 include/uapi/linux/tc_act/tc_skbedit.h    |  2 -
 include/uapi/linux/tc_act/tc_skbmod.h     |  2 -
 include/uapi/linux/tc_act/tc_tunnel_key.h |  2 -
 include/uapi/linux/tc_act/tc_vlan.h       |  2 -
 18 files changed, 161 insertions(+), 40 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 031c4b4c..b7b748f1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2016,6 +2016,19 @@ union bpf_attr {
  *			Only works if *skb* contains an IPv6 packet. Insert a
  *			Segment Routing Header (**struct ipv6_sr_hdr**) inside
  *			the IPv6 header.
+ *		**BPF_LWT_ENCAP_IP**
+ *			IP encapsulation (GRE/GUE/IPIP/etc). The outer header
+ *			must be IPv4 or IPv6, followed by zero or more
+ *			additional headers, up to LWT_BPF_MAX_HEADROOM total
+ *			bytes in all prepended headers. Please note that
+ *			if skb_is_gso(skb) is true, no more than two headers
+ *			can be prepended, and the inner header, if present,
+ *			should be either GRE or UDP/GUE.
+ *
+ *		BPF_LWT_ENCAP_SEG6*** types can be called by bpf programs of
+ *		type BPF_PROG_TYPE_LWT_IN; BPF_LWT_ENCAP_IP type can be called
+ *		by bpf programs of types BPF_PROG_TYPE_LWT_IN and
+ *		BPF_PROG_TYPE_LWT_XMIT.
  *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
@@ -2329,6 +2342,23 @@ union bpf_attr {
  *		"**y**".
  *	Return
  *		0
+ *
+ * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
+ *	Description
+ *		This helper gets a **struct bpf_sock** pointer such
+ *		that all the fields in bpf_sock can be accessed.
+ *	Return
+ *		A **struct bpf_sock** pointer on success, or NULL in
+ *		case of failure.
+ *
+ * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
+ *	Description
+ *		This helper gets a **struct bpf_tcp_sock** pointer from a
+ *		**struct bpf_sock** pointer.
+ *
+ *	Return
+ *		A **struct bpf_tcp_sock** pointer on success, or NULL in
+ *		case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2425,7 +2455,9 @@ union bpf_attr {
 	FN(msg_pop_data),		\
 	FN(rc_pointer_rel),		\
 	FN(spin_lock),			\
-	FN(spin_unlock),
+	FN(spin_unlock),		\
+	FN(sk_fullsock),		\
+	FN(tcp_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2498,7 +2530,8 @@ enum bpf_hdr_start_off {
 /* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */
 enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_SEG6,
-	BPF_LWT_ENCAP_SEG6_INLINE
+	BPF_LWT_ENCAP_SEG6_INLINE,
+	BPF_LWT_ENCAP_IP,
 };
 
 #define __bpf_md_ptr(type, name)	\
@@ -2545,6 +2578,7 @@ struct __sk_buff {
 	__u64 tstamp;
 	__u32 wire_len;
 	__u32 gso_segs;
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 struct bpf_tunnel_key {
@@ -2586,7 +2620,15 @@ enum bpf_ret_code {
 	BPF_DROP = 2,
 	/* 3-6 reserved */
 	BPF_REDIRECT = 7,
-	/* >127 are reserved for prog type specific return codes */
+	/* >127 are reserved for prog type specific return codes.
+	 *
+	 * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and
+	 *    BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been
+	 *    changed and should be routed based on its new L3 header.
+	 *    (This is an L3 redirect, as opposed to L2 redirect
+	 *    represented by BPF_REDIRECT above).
+	 */
+	BPF_LWT_REROUTE = 128,
 };
 
 struct bpf_sock {
@@ -2596,14 +2638,52 @@ struct bpf_sock {
 	__u32 protocol;
 	__u32 mark;
 	__u32 priority;
-	__u32 src_ip4;		/* Allows 1,2,4-byte read.
-				 * Stored in network byte order.
+	/* IP address also allows 1 and 2 bytes access */
+	__u32 src_ip4;
+	__u32 src_ip6[4];
+	__u32 src_port;		/* host byte order */
+	__u32 dst_port;		/* network byte order */
+	__u32 dst_ip4;
+	__u32 dst_ip6[4];
+	__u32 state;
+};
+
+struct bpf_tcp_sock {
+	__u32 snd_cwnd;		/* Sending congestion window		*/
+	__u32 srtt_us;		/* smoothed round trip time << 3 in usecs */
+	__u32 rtt_min;
+	__u32 snd_ssthresh;	/* Slow start size threshold		*/
+	__u32 rcv_nxt;		/* What we want to receive next		*/
+	__u32 snd_nxt;		/* Next sequence we send		*/
+	__u32 snd_una;		/* First byte we want an ack for	*/
+	__u32 mss_cache;	/* Cached effective mss, not including SACKS */
+	__u32 ecn_flags;	/* ECN status bits.			*/
+	__u32 rate_delivered;	/* saved rate sample: packets delivered */
+	__u32 rate_interval_us;	/* saved rate sample: time elapsed */
+	__u32 packets_out;	/* Packets which are "in flight"	*/
+	__u32 retrans_out;	/* Retransmitted packets out		*/
+	__u32 total_retrans;	/* Total retransmits for entire connection */
+	__u32 segs_in;		/* RFC4898 tcpEStatsPerfSegsIn
+				 * total number of segments in.
 				 */
-	__u32 src_ip6[4];	/* Allows 1,2,4-byte read.
-				 * Stored in network byte order.
+	__u32 data_segs_in;	/* RFC4898 tcpEStatsPerfDataSegsIn
+				 * total number of data segments in.
 				 */
-	__u32 src_port;		/* Allows 4-byte read.
-				 * Stored in host byte order
+	__u32 segs_out;		/* RFC4898 tcpEStatsPerfSegsOut
+				 * The total number of segments sent.
+				 */
+	__u32 data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
+				 * total number of data segments sent.
+				 */
+	__u32 lost_out;		/* Lost packets			*/
+	__u32 sacked_out;	/* SACK'd packets			*/
+	__u64 bytes_received;	/* RFC4898 tcpEStatsAppHCThruOctetsReceived
+				 * sum(delta(rcv_nxt)), or how many bytes
+				 * were acked.
+				 */
+	__u64 bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
+				 * sum(delta(snd_una)), or how many bytes
+				 * were acked.
 				 */
 };
 
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index d51b59a7..3b6a9e6b 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -96,6 +96,15 @@ enum devlink_command {
 
 	DEVLINK_CMD_INFO_GET,		/* can dump */
 
+	DEVLINK_CMD_HEALTH_REPORTER_GET,
+	DEVLINK_CMD_HEALTH_REPORTER_SET,
+	DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+	DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
+	DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
+	DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
+
+	DEVLINK_CMD_FLASH_UPDATE,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -302,6 +311,27 @@ enum devlink_attr {
 
 	DEVLINK_ATTR_SB_POOL_CELL_SIZE,		/* u32 */
 
+	DEVLINK_ATTR_FMSG,			/* nested */
+	DEVLINK_ATTR_FMSG_OBJ_NEST_START,	/* flag */
+	DEVLINK_ATTR_FMSG_PAIR_NEST_START,	/* flag */
+	DEVLINK_ATTR_FMSG_ARR_NEST_START,	/* flag */
+	DEVLINK_ATTR_FMSG_NEST_END,		/* flag */
+	DEVLINK_ATTR_FMSG_OBJ_NAME,		/* string */
+	DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE,	/* u8 */
+	DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA,	/* dynamic */
+
+	DEVLINK_ATTR_HEALTH_REPORTER,			/* nested */
+	DEVLINK_ATTR_HEALTH_REPORTER_NAME,		/* string */
+	DEVLINK_ATTR_HEALTH_REPORTER_STATE,		/* u8 */
+	DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT,		/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT,	/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS,		/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD,	/* u64 */
+	DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,	/* u8 */
+
+	DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME,	/* string */
+	DEVLINK_ATTR_FLASH_UPDATE_COMPONENT,	/* string */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 02ac251b..51a0496f 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -63,12 +63,49 @@ enum {
 #define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
 #define TC_ACT_EXT_OPCODE_MAX	TC_ACT_GOTO_CHAIN
 
+/* These macros are put here for binary compatibility with userspace apps that
+ * make use of them. For kernel code and new userspace apps, use the TCA_ID_*
+ * versions.
+ */
+#define TCA_ACT_GACT 5
+#define TCA_ACT_IPT 6
+#define TCA_ACT_PEDIT 7
+#define TCA_ACT_MIRRED 8
+#define TCA_ACT_NAT 9
+#define TCA_ACT_XT 10
+#define TCA_ACT_SKBEDIT 11
+#define TCA_ACT_VLAN 12
+#define TCA_ACT_BPF 13
+#define TCA_ACT_CONNMARK 14
+#define TCA_ACT_SKBMOD 15
+#define TCA_ACT_CSUM 16
+#define TCA_ACT_TUNNEL_KEY 17
+#define TCA_ACT_SIMP 22
+#define TCA_ACT_IFE 25
+#define TCA_ACT_SAMPLE 26
+
 /* Action type identifiers*/
-enum {
-	TCA_ID_UNSPEC=0,
-	TCA_ID_POLICE=1,
+enum tca_id {
+	TCA_ID_UNSPEC = 0,
+	TCA_ID_POLICE = 1,
+	TCA_ID_GACT = TCA_ACT_GACT,
+	TCA_ID_IPT = TCA_ACT_IPT,
+	TCA_ID_PEDIT = TCA_ACT_PEDIT,
+	TCA_ID_MIRRED = TCA_ACT_MIRRED,
+	TCA_ID_NAT = TCA_ACT_NAT,
+	TCA_ID_XT = TCA_ACT_XT,
+	TCA_ID_SKBEDIT = TCA_ACT_SKBEDIT,
+	TCA_ID_VLAN = TCA_ACT_VLAN,
+	TCA_ID_BPF = TCA_ACT_BPF,
+	TCA_ID_CONNMARK = TCA_ACT_CONNMARK,
+	TCA_ID_SKBMOD = TCA_ACT_SKBMOD,
+	TCA_ID_CSUM = TCA_ACT_CSUM,
+	TCA_ID_TUNNEL_KEY = TCA_ACT_TUNNEL_KEY,
+	TCA_ID_SIMP = TCA_ACT_SIMP,
+	TCA_ID_IFE = TCA_ACT_IFE,
+	TCA_ID_SAMPLE = TCA_ACT_SAMPLE,
 	/* other actions go here */
-	__TCA_ID_MAX=255
+	__TCA_ID_MAX = 255
 };
 
 #define TCA_ID_MAX __TCA_ID_MAX
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 0d18b1d1..1eb572ef 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -954,7 +954,7 @@ enum {
 #define TCA_PIE_MAX   (__TCA_PIE_MAX - 1)
 
 struct tc_pie_xstats {
-	__u32 prob;             /* current probability */
+	__u64 prob;             /* current probability */
 	__u32 delay;            /* current delay in ms */
 	__u32 avg_dq_rate;      /* current average dq_rate in bits/pie_time */
 	__u32 packets_in;       /* total number of packets enqueued */
diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h
index 6e89a5df..653c4f94 100644
--- a/include/uapi/linux/tc_act/tc_bpf.h
+++ b/include/uapi/linux/tc_act/tc_bpf.h
@@ -13,8 +13,6 @@
 
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_BPF 13
-
 struct tc_act_bpf {
 	tc_gen;
 };
diff --git a/include/uapi/linux/tc_act/tc_connmark.h b/include/uapi/linux/tc_act/tc_connmark.h
index 80caa47b..9f8f6f70 100644
--- a/include/uapi/linux/tc_act/tc_connmark.h
+++ b/include/uapi/linux/tc_act/tc_connmark.h
@@ -5,8 +5,6 @@
 #include <linux/types.h>
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_CONNMARK 14
-
 struct tc_connmark {
 	tc_gen;
 	__u16 zone;
diff --git a/include/uapi/linux/tc_act/tc_csum.h b/include/uapi/linux/tc_act/tc_csum.h
index 0ecf4d29..94b20449 100644
--- a/include/uapi/linux/tc_act/tc_csum.h
+++ b/include/uapi/linux/tc_act/tc_csum.h
@@ -5,8 +5,6 @@
 #include <linux/types.h>
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_CSUM 16
-
 enum {
 	TCA_CSUM_UNSPEC,
 	TCA_CSUM_PARMS,
diff --git a/include/uapi/linux/tc_act/tc_gact.h b/include/uapi/linux/tc_act/tc_gact.h
index 94273c3b..37e5392e 100644
--- a/include/uapi/linux/tc_act/tc_gact.h
+++ b/include/uapi/linux/tc_act/tc_gact.h
@@ -5,7 +5,6 @@
 #include <linux/types.h>
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_GACT 5
 struct tc_gact {
 	tc_gen;
 
diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h
index 2f48490e..8c401f18 100644
--- a/include/uapi/linux/tc_act/tc_ife.h
+++ b/include/uapi/linux/tc_act/tc_ife.h
@@ -6,7 +6,6 @@
 #include <linux/pkt_cls.h>
 #include <linux/ife.h>
 
-#define TCA_ACT_IFE 25
 /* Flag bits for now just encoding/decoding; mutually exclusive */
 #define IFE_ENCODE 1
 #define IFE_DECODE 0
diff --git a/include/uapi/linux/tc_act/tc_ipt.h b/include/uapi/linux/tc_act/tc_ipt.h
index b743c8bd..c48d7da6 100644
--- a/include/uapi/linux/tc_act/tc_ipt.h
+++ b/include/uapi/linux/tc_act/tc_ipt.h
@@ -4,9 +4,6 @@
 
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_IPT 6
-#define TCA_ACT_XT 10
-
 enum {
 	TCA_IPT_UNSPEC,
 	TCA_IPT_TABLE,
diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h
index 5dd671cf..2500a000 100644
--- a/include/uapi/linux/tc_act/tc_mirred.h
+++ b/include/uapi/linux/tc_act/tc_mirred.h
@@ -5,7 +5,6 @@
 #include <linux/types.h>
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_MIRRED 8
 #define TCA_EGRESS_REDIR 1  /* packet redirect to EGRESS*/
 #define TCA_EGRESS_MIRROR 2 /* mirror packet to EGRESS */
 #define TCA_INGRESS_REDIR 3  /* packet redirect to INGRESS*/
diff --git a/include/uapi/linux/tc_act/tc_nat.h b/include/uapi/linux/tc_act/tc_nat.h
index 086be842..21399c2c 100644
--- a/include/uapi/linux/tc_act/tc_nat.h
+++ b/include/uapi/linux/tc_act/tc_nat.h
@@ -5,8 +5,6 @@
 #include <linux/pkt_cls.h>
 #include <linux/types.h>
 
-#define TCA_ACT_NAT 9
-
 enum {
 	TCA_NAT_UNSPEC,
 	TCA_NAT_PARMS,
diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h
index 24ec792d..f3e61b04 100644
--- a/include/uapi/linux/tc_act/tc_pedit.h
+++ b/include/uapi/linux/tc_act/tc_pedit.h
@@ -5,8 +5,6 @@
 #include <linux/types.h>
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_PEDIT 7
-
 enum {
 	TCA_PEDIT_UNSPEC,
 	TCA_PEDIT_TM,
diff --git a/include/uapi/linux/tc_act/tc_sample.h b/include/uapi/linux/tc_act/tc_sample.h
index bd7e9f03..fee1bcc2 100644
--- a/include/uapi/linux/tc_act/tc_sample.h
+++ b/include/uapi/linux/tc_act/tc_sample.h
@@ -6,8 +6,6 @@
 #include <linux/pkt_cls.h>
 #include <linux/if_ether.h>
 
-#define TCA_ACT_SAMPLE 26
-
 struct tc_sample {
 	tc_gen;
 };
diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h
index 6de6071e..800e9337 100644
--- a/include/uapi/linux/tc_act/tc_skbedit.h
+++ b/include/uapi/linux/tc_act/tc_skbedit.h
@@ -23,8 +23,6 @@
 
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_SKBEDIT 11
-
 #define SKBEDIT_F_PRIORITY		0x1
 #define SKBEDIT_F_QUEUE_MAPPING		0x2
 #define SKBEDIT_F_MARK			0x4
diff --git a/include/uapi/linux/tc_act/tc_skbmod.h b/include/uapi/linux/tc_act/tc_skbmod.h
index 38c072f6..c525b350 100644
--- a/include/uapi/linux/tc_act/tc_skbmod.h
+++ b/include/uapi/linux/tc_act/tc_skbmod.h
@@ -13,8 +13,6 @@
 
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_SKBMOD 15
-
 #define SKBMOD_F_DMAC	0x1
 #define SKBMOD_F_SMAC	0x2
 #define SKBMOD_F_ETYPE	0x4
diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h
index be384d63..41c8b462 100644
--- a/include/uapi/linux/tc_act/tc_tunnel_key.h
+++ b/include/uapi/linux/tc_act/tc_tunnel_key.h
@@ -14,8 +14,6 @@
 
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_TUNNEL_KEY 17
-
 #define TCA_TUNNEL_KEY_ACT_SET	    1
 #define TCA_TUNNEL_KEY_ACT_RELEASE  2
 
diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h
index 0d7b5fd6..168995b5 100644
--- a/include/uapi/linux/tc_act/tc_vlan.h
+++ b/include/uapi/linux/tc_act/tc_vlan.h
@@ -13,8 +13,6 @@
 
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_VLAN 12
-
 #define TCA_VLAN_ACT_POP	1
 #define TCA_VLAN_ACT_PUSH	2
 #define TCA_VLAN_ACT_MODIFY	3

From d326d79c223b66a841471472c9421c334fd6d167 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 26 Feb 2019 12:20:14 -0800
Subject: [PATCH 39/55] devlink: add support for updating device flash

Add new command for updating flash of devices via devlink API.
Example:

$ cp flash-boot.bin /lib/firmware/
$ devlink dev flash pci/0000:05:00.0 file flash-boot.bin

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c      | 54 ++++++++++++++++++++++++++++++++++++++++++
 man/man8/devlink-dev.8 | 32 +++++++++++++++++++++++++
 2 files changed, 86 insertions(+)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index 960cdda9..5c6cac1f 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -199,6 +199,8 @@ static void ifname_map_free(struct ifname_map *ifname_map)
 #define DL_OPT_REGION_SNAPSHOT_ID	BIT(22)
 #define DL_OPT_REGION_ADDRESS		BIT(23)
 #define DL_OPT_REGION_LENGTH		BIT(24)
+#define DL_OPT_FLASH_FILE_NAME	BIT(25)
+#define DL_OPT_FLASH_COMPONENT	BIT(26)
 
 struct dl_opts {
 	uint32_t present; /* flags of present items */
@@ -230,6 +232,8 @@ struct dl_opts {
 	uint32_t region_snapshot_id;
 	uint64_t region_address;
 	uint64_t region_length;
+	const char *flash_file_name;
+	const char *flash_component;
 };
 
 struct dl {
@@ -1185,6 +1189,20 @@ static int dl_argv_parse(struct dl *dl, uint32_t o_required,
 			if (err)
 				return err;
 			o_found |= DL_OPT_REGION_LENGTH;
+		} else if (dl_argv_match(dl, "file") &&
+			   (o_all & DL_OPT_FLASH_FILE_NAME)) {
+			dl_arg_inc(dl);
+			err = dl_argv_str(dl, &opts->flash_file_name);
+			if (err)
+				return err;
+			o_found |= DL_OPT_FLASH_FILE_NAME;
+		} else if (dl_argv_match(dl, "component") &&
+			   (o_all & DL_OPT_FLASH_COMPONENT)) {
+			dl_arg_inc(dl);
+			err = dl_argv_str(dl, &opts->flash_component);
+			if (err)
+				return err;
+			o_found |= DL_OPT_FLASH_COMPONENT;
 		} else {
 			pr_err("Unknown option \"%s\"\n", dl_argv(dl));
 			return -EINVAL;
@@ -1389,6 +1407,12 @@ static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)
 	if (opts->present & DL_OPT_REGION_LENGTH)
 		mnl_attr_put_u64(nlh, DEVLINK_ATTR_REGION_CHUNK_LEN,
 				 opts->region_length);
+	if (opts->present & DL_OPT_FLASH_FILE_NAME)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME,
+				  opts->flash_file_name);
+	if (opts->present & DL_OPT_FLASH_COMPONENT)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT,
+				  opts->flash_component);
 }
 
 static int dl_argv_parse_put(struct nlmsghdr *nlh, struct dl *dl,
@@ -1451,6 +1475,7 @@ static void cmd_dev_help(void)
 	pr_err("       devlink dev param show [DEV name PARAMETER]\n");
 	pr_err("       devlink dev reload DEV\n");
 	pr_err("       devlink dev info [ DEV ]\n");
+	pr_err("       devlink dev flash DEV file PATH [ component NAME ]\n");
 }
 
 static bool cmp_arr_last_handle(struct dl *dl, const char *bus_name,
@@ -2583,6 +2608,32 @@ static int cmd_dev_info(struct dl *dl)
 	return err;
 }
 
+static void cmd_dev_flash_help(void)
+{
+	pr_err("Usage: devlink dev flash DEV file PATH [ component NAME ]\n");
+}
+
+static int cmd_dev_flash(struct dl *dl)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	if (dl_argv_match(dl, "help") || dl_no_arg(dl)) {
+		cmd_dev_flash_help();
+		return 0;
+	}
+
+	nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_FLASH_UPDATE,
+			       NLM_F_REQUEST | NLM_F_ACK);
+
+	err = dl_argv_parse_put(nlh, dl, DL_OPT_HANDLE | DL_OPT_FLASH_FILE_NAME,
+				DL_OPT_FLASH_COMPONENT);
+	if (err)
+		return err;
+
+	return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
+}
+
 static int cmd_dev(struct dl *dl)
 {
 	if (dl_argv_match(dl, "help")) {
@@ -2604,6 +2655,9 @@ static int cmd_dev(struct dl *dl)
 	} else if (dl_argv_match(dl, "info")) {
 		dl_arg_inc(dl);
 		return cmd_dev_info(dl);
+	} else if (dl_argv_match(dl, "flash")) {
+		dl_arg_inc(dl);
+		return cmd_dev_flash(dl);
 	}
 	pr_err("Command \"%s\" not found\n", dl_argv(dl));
 	return -ENOENT;
diff --git a/man/man8/devlink-dev.8 b/man/man8/devlink-dev.8
index 47838371..1804463b 100644
--- a/man/man8/devlink-dev.8
+++ b/man/man8/devlink-dev.8
@@ -69,6 +69,16 @@ devlink-dev \- devlink device configuration
 .IR DEV
 .RI "]"
 
+.ti -8
+.BR "devlink dev flash"
+.IR DEV
+.BR file
+.IR PATH
+.RI "["
+.BR target
+.IR ID
+.RI "]"
+
 .SH "DESCRIPTION"
 .SS devlink dev show - display devlink device attributes
 
@@ -177,6 +187,28 @@ versions may differ after flash has been updated, but before reboot.
 - specifies the devlink device to show.
 If this argument is omitted all devices are listed.
 
+.SS devlink dev flash - write device's non-volatile memory.
+
+.PP
+.I "DEV"
+- specifies the devlink device to write to.
+
+.BR file
+.I PATH
+- Path to the file which will be written into device's flash. The path needs
+to be relative to one of the directories searched by the kernel firmware loaded,
+such as /lib/firmware.
+
+.BR component
+.I NAME
+- If device stores multiple firmware images in non-volatile memory, this
+parameter may be used to indicate which firmware image should be written.
+The value of
+.I NAME
+should match the component names from
+.B "devlink dev info"
+and may be driver-dependent.
+
 .SH "EXAMPLES"
 .PP
 devlink dev show

From 359f69f76ffb6029d37c49a95c2d08b5d48fc947 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 27 Feb 2019 08:41:51 +0200
Subject: [PATCH 40/55] rdma: Add the prefix for driver attributes

There is a need to distinguish between driver vs. general exposed
attributes. The most common use case is to expose some internal
garbage under extremely common and sexy name, e.g. pi, ci e.t.c

In order to achieve that, we will add "drv_" prefix to all strings
which were received through RDMA_NLDEV_ATTR_DRIVER_* attributes.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>a
Tested-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 rdma/utils.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/rdma/utils.c b/rdma/utils.c
index 6bc14cd5..1f6bf330 100644
--- a/rdma/utils.c
+++ b/rdma/utils.c
@@ -829,27 +829,37 @@ static int print_driver_entry(struct rd *rd, struct nlattr *key_attr,
 				struct nlattr *val_attr,
 				enum rdma_nldev_print_type print_type)
 {
-	const char *key_str = mnl_attr_get_str(key_attr);
 	int attr_type = nla_type(val_attr);
+	int ret = -EINVAL;
+	char *key_str;
+
+	if (asprintf(&key_str, "drv_%s", mnl_attr_get_str(key_attr)) == -1)
+		return -ENOMEM;
 
 	switch (attr_type) {
 	case RDMA_NLDEV_ATTR_DRIVER_STRING:
-		return print_driver_string(rd, key_str,
-				mnl_attr_get_str(val_attr));
+		ret = print_driver_string(rd, key_str,
+					  mnl_attr_get_str(val_attr));
+		break;
 	case RDMA_NLDEV_ATTR_DRIVER_S32:
-		return print_driver_s32(rd, key_str,
-				mnl_attr_get_u32(val_attr), print_type);
+		ret = print_driver_s32(rd, key_str, mnl_attr_get_u32(val_attr),
+				       print_type);
+		break;
 	case RDMA_NLDEV_ATTR_DRIVER_U32:
-		return print_driver_u32(rd, key_str,
-				mnl_attr_get_u32(val_attr), print_type);
+		ret = print_driver_u32(rd, key_str, mnl_attr_get_u32(val_attr),
+				       print_type);
+		break;
 	case RDMA_NLDEV_ATTR_DRIVER_S64:
-		return print_driver_s64(rd, key_str,
-				mnl_attr_get_u64(val_attr), print_type);
+		ret = print_driver_s64(rd, key_str, mnl_attr_get_u64(val_attr),
+				       print_type);
+		break;
 	case RDMA_NLDEV_ATTR_DRIVER_U64:
-		return print_driver_u64(rd, key_str,
-				mnl_attr_get_u64(val_attr), print_type);
+		ret = print_driver_u64(rd, key_str, mnl_attr_get_u64(val_attr),
+				       print_type);
+		break;
 	}
-	return -EINVAL;
+	free(key_str);
+	return ret;
 }
 
 void print_driver_table(struct rd *rd, struct nlattr *tb)

From ae72e655183b6f6872826360d855607d3d0a5617 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:12:54 +0200
Subject: [PATCH 41/55] devlink: Refactor validation of finding required
 arguments

Introducing argument's metadata structure matching a bitmap flag per
required argument and an error message if missing. Using this static
array to refactor validation of finding required arguments in devlink
command line and to ease further maintenance.

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c | 153 ++++++++++++++--------------------------------
 1 file changed, 45 insertions(+), 108 deletions(-)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index 5c6cac1f..a774b196 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -39,6 +39,7 @@
 #define PARAM_CMODE_RUNTIME_STR "runtime"
 #define PARAM_CMODE_DRIVERINIT_STR "driverinit"
 #define PARAM_CMODE_PERMANENT_STR "permanent"
+#define DL_ARGS_REQUIRED_MAX_ERR_LEN 80
 
 static int g_new_line_count;
 
@@ -954,6 +955,49 @@ static int param_cmode_get(const char *cmodestr,
 	return 0;
 }
 
+struct dl_args_metadata {
+	uint32_t o_flag;
+	char err_msg[DL_ARGS_REQUIRED_MAX_ERR_LEN];
+};
+
+static const struct dl_args_metadata dl_args_required[] = {
+	{DL_OPT_PORT_TYPE,	      "Port type not set."},
+	{DL_OPT_PORT_COUNT,	      "Port split count option expected."},
+	{DL_OPT_SB_POOL,	      "Pool index option expected."},
+	{DL_OPT_SB_SIZE,	      "Pool size option expected."},
+	{DL_OPT_SB_TYPE,	      "Pool type option expected."},
+	{DL_OPT_SB_THTYPE,	      "Pool threshold type option expected."},
+	{DL_OPT_SB_TH,		      "Threshold option expected."},
+	{DL_OPT_SB_TC,		      "TC index option expected."},
+	{DL_OPT_ESWITCH_MODE,	      "E-Switch mode option expected."},
+	{DL_OPT_ESWITCH_INLINE_MODE,  "E-Switch inline-mode option expected."},
+	{DL_OPT_DPIPE_TABLE_NAME,     "Dpipe table name expected."},
+	{DL_OPT_DPIPE_TABLE_COUNTERS, "Dpipe table counter state expected."},
+	{DL_OPT_ESWITCH_ENCAP_MODE,   "E-Switch encapsulation option expected."},
+	{DL_OPT_PARAM_NAME,	      "Parameter name expected."},
+	{DL_OPT_PARAM_VALUE,	      "Value to set expected."},
+	{DL_OPT_PARAM_CMODE,	      "Configuration mode expected."},
+	{DL_OPT_REGION_SNAPSHOT_ID,   "Region snapshot id expected."},
+	{DL_OPT_REGION_ADDRESS,	      "Region address value expected."},
+	{DL_OPT_REGION_LENGTH,	      "Region length value expected."},
+};
+
+static int dl_args_finding_required_validate(uint32_t o_required,
+					     uint32_t o_found)
+{
+	uint32_t o_flag;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dl_args_required); i++) {
+		o_flag = dl_args_required[i].o_flag;
+		if ((o_required & o_flag) && !(o_found & o_flag)) {
+			pr_err("%s\n", dl_args_required[i].err_msg);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
 static int dl_argv_parse(struct dl *dl, uint32_t o_required,
 			 uint32_t o_optional)
 {
@@ -1216,114 +1260,7 @@ static int dl_argv_parse(struct dl *dl, uint32_t o_required,
 		opts->present |= DL_OPT_SB;
 	}
 
-	if ((o_required & DL_OPT_PORT_TYPE) && !(o_found & DL_OPT_PORT_TYPE)) {
-		pr_err("Port type option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_PORT_COUNT) &&
-	    !(o_found & DL_OPT_PORT_COUNT)) {
-		pr_err("Port split count option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_SB_POOL) && !(o_found & DL_OPT_SB_POOL)) {
-		pr_err("Pool index option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_SB_SIZE) && !(o_found & DL_OPT_SB_SIZE)) {
-		pr_err("Pool size option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_SB_TYPE) && !(o_found & DL_OPT_SB_TYPE)) {
-		pr_err("Pool type option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_SB_THTYPE) && !(o_found & DL_OPT_SB_THTYPE)) {
-		pr_err("Pool threshold type option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_SB_TH) && !(o_found & DL_OPT_SB_TH)) {
-		pr_err("Threshold option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_SB_TC) && !(o_found & DL_OPT_SB_TC)) {
-		pr_err("TC index option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_ESWITCH_MODE) &&
-	    !(o_found & DL_OPT_ESWITCH_MODE)) {
-		pr_err("E-Switch mode option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_ESWITCH_INLINE_MODE) &&
-	    !(o_found & DL_OPT_ESWITCH_INLINE_MODE)) {
-		pr_err("E-Switch inline-mode option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_DPIPE_TABLE_NAME) &&
-	    !(o_found & DL_OPT_DPIPE_TABLE_NAME)) {
-		pr_err("Dpipe table name expected\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_DPIPE_TABLE_COUNTERS) &&
-	    !(o_found & DL_OPT_DPIPE_TABLE_COUNTERS)) {
-		pr_err("Dpipe table counter state expected\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_ESWITCH_ENCAP_MODE) &&
-	    !(o_found & DL_OPT_ESWITCH_ENCAP_MODE)) {
-		pr_err("E-Switch encapsulation option expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_PARAM_NAME) &&
-	    !(o_found & DL_OPT_PARAM_NAME)) {
-		pr_err("Parameter name expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_PARAM_VALUE) &&
-	    !(o_found & DL_OPT_PARAM_VALUE)) {
-		pr_err("Value to set expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_PARAM_CMODE) &&
-	    !(o_found & DL_OPT_PARAM_CMODE)) {
-		pr_err("Configuration mode expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_REGION_SNAPSHOT_ID) &&
-	    !(o_found & DL_OPT_REGION_SNAPSHOT_ID)) {
-		pr_err("Region snapshot id expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_REGION_ADDRESS) &&
-	    !(o_found & DL_OPT_REGION_ADDRESS)) {
-		pr_err("Region address value expected.\n");
-		return -EINVAL;
-	}
-
-	if ((o_required & DL_OPT_REGION_LENGTH) &&
-	    !(o_found & DL_OPT_REGION_LENGTH)) {
-		pr_err("Region length value expected.\n");
-		return -EINVAL;
-	}
-
-	return 0;
+	return dl_args_finding_required_validate(o_required, o_found);
 }
 
 static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)

From 86648a196066a533f7b1841d4430f6ba6387c480 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:12:55 +0200
Subject: [PATCH 42/55] devlink: Fix print of uint64_t

This patch prints uint64_t with its corresponding format and avoid implicit
cast to uint32_t.

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index a774b196..8a28b5d5 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -1651,7 +1651,14 @@ static void pr_out_u64(struct dl *dl, const char *name, uint64_t val)
 	if (val == (uint64_t) -1)
 		return pr_out_str(dl, name, "unlimited");
 
-	return pr_out_uint(dl, name, val);
+	if (dl->json_output) {
+		jsonw_u64_field(dl->jw, name, val);
+	} else {
+		if (g_indent_newline)
+			pr_out("%s %lu", name, val);
+		else
+			pr_out(" %s %lu", name, val);
+	}
 }
 
 static void pr_out_region_chunk_start(struct dl *dl, uint64_t addr)

From 8257e6c49cca9847e01262f6e749c6e88e2ddb72 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:12:56 +0200
Subject: [PATCH 43/55] devlink: Fix boolean JSON print

This patch removes the inverted commas from boolean values in JSON
format: true/false instead of "true"/"false".

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index 8a28b5d5..4b7e8ec2 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -1628,10 +1628,10 @@ static void pr_out_str(struct dl *dl, const char *name, const char *val)
 
 static void pr_out_bool(struct dl *dl, const char *name, bool val)
 {
-	if (val)
-		pr_out_str(dl, name, "true");
+	if (dl->json_output)
+		jsonw_bool_field(dl->jw, name, val);
 	else
-		pr_out_str(dl, name, "false");
+		pr_out_str(dl, name, val ? "true" : "false");
 }
 
 static void pr_out_uint(struct dl *dl, const char *name, unsigned int val)

From 844a61764c6f7e6d83c77b318142aaa3a26ef355 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:12:57 +0200
Subject: [PATCH 44/55] devlink: Add helper functions for name and value
 separately

Add a new helper functions which outputs only values (without name
label) for different types: boolean, uint, uint64, string and binary.
In addition add a helper function which prints only the name label.

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c | 65 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index 4b7e8ec2..c3f87456 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -1661,6 +1661,71 @@ static void pr_out_u64(struct dl *dl, const char *name, uint64_t val)
 	}
 }
 
+static void pr_out_bool_value(struct dl *dl, bool value)
+{
+	if (dl->json_output)
+		jsonw_bool(dl->jw, value);
+	else
+		pr_out(" %s", value ? "true" : "false");
+}
+
+static void pr_out_uint_value(struct dl *dl, unsigned int value)
+{
+	if (dl->json_output)
+		jsonw_uint(dl->jw, value);
+	else
+		pr_out(" %u", value);
+}
+
+static void pr_out_uint64_value(struct dl *dl, uint64_t value)
+{
+	if (dl->json_output)
+		jsonw_u64(dl->jw, value);
+	else
+		pr_out(" %lu", value);
+}
+
+static void pr_out_binary_value(struct dl *dl, uint8_t *data, uint32_t len)
+{
+	int i = 1;
+
+	if (dl->json_output)
+		jsonw_start_array(dl->jw);
+	else
+		pr_out("\n");
+
+	while (i < len) {
+		if (dl->json_output) {
+			jsonw_printf(dl->jw, "%d", data[i]);
+		} else {
+			pr_out(" %02x", data[i]);
+			if (!(i % 16))
+				pr_out("\n");
+		}
+		i++;
+	}
+	if (dl->json_output)
+		jsonw_end_array(dl->jw);
+	else if ((i - 1) % 16)
+		pr_out("\n");
+}
+
+static void pr_out_str_value(struct dl *dl, const char *value)
+{
+	if (dl->json_output)
+		jsonw_string(dl->jw, value);
+	else
+		pr_out(" %s", value);
+}
+
+static void pr_out_name(struct dl *dl, const char *name)
+{
+	if (dl->json_output)
+		jsonw_name(dl->jw, name);
+	else
+		pr_out(" %s:", name);
+}
+
 static void pr_out_region_chunk_start(struct dl *dl, uint64_t addr)
 {
 	if (dl->json_output) {

From 2f1242efe9d054b82d240dc8b152d2a48dcb0b48 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:12:58 +0200
Subject: [PATCH 45/55] devlink: Add devlink health show command

Add devlink health show command which displays status and configuration
info on a specific reporter on a device or dump the info on all
reporters on all devices. Add helper functions to display status and
dump's time stamp.
Example:
$ devlink health show pci/0000:00:09.0 reporter tx
pci/0000:00:09.0:
 name tx
  state healthy error 0 recover 1 last_dump_date 2019-02-14 last_dump_time 10:10:10 grace_period 600 auto_recover true
$ devlink health show pci/0000:00:09.0 reporter tx -jp
{
 "health":{
  "pci/0000:00:0a.0":[
     {
     "name":"tx",
     "state":"healthy",
     "error":0,
     "recover":1,
     "last_dump_date":"2019-Feb-14",
     "last_dump_time":"10:10:10",
     "grace_period":600,
     "auto_recover":true
    }
  ]
}

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c | 185 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 184 insertions(+), 1 deletion(-)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index c3f87456..37eb2054 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -22,6 +22,7 @@
 #include <linux/devlink.h>
 #include <libmnl/libmnl.h>
 #include <netinet/ether.h>
+#include <sys/sysinfo.h>
 
 #include "SNAPSHOT.h"
 #include "list.h"
@@ -41,6 +42,10 @@
 #define PARAM_CMODE_PERMANENT_STR "permanent"
 #define DL_ARGS_REQUIRED_MAX_ERR_LEN 80
 
+#define HEALTH_REPORTER_STATE_HEALTHY_STR "healthy"
+#define HEALTH_REPORTER_STATE_ERROR_STR "error"
+#define HEALTH_REPORTER_TIMESTAMP_FMT_LEN 80
+
 static int g_new_line_count;
 
 #define pr_err(args...) fprintf(stderr, ##args)
@@ -202,6 +207,7 @@ static void ifname_map_free(struct ifname_map *ifname_map)
 #define DL_OPT_REGION_LENGTH		BIT(24)
 #define DL_OPT_FLASH_FILE_NAME	BIT(25)
 #define DL_OPT_FLASH_COMPONENT	BIT(26)
+#define DL_OPT_HEALTH_REPORTER_NAME	BIT(27)
 
 struct dl_opts {
 	uint32_t present; /* flags of present items */
@@ -235,6 +241,7 @@ struct dl_opts {
 	uint64_t region_length;
 	const char *flash_file_name;
 	const char *flash_component;
+	const char *reporter_name;
 };
 
 struct dl {
@@ -395,6 +402,13 @@ static const enum mnl_attr_data_type devlink_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_INFO_VERSION_STORED] = MNL_TYPE_NESTED,
 	[DEVLINK_ATTR_INFO_VERSION_NAME] = MNL_TYPE_STRING,
 	[DEVLINK_ATTR_INFO_VERSION_VALUE] = MNL_TYPE_STRING,
+	[DEVLINK_ATTR_HEALTH_REPORTER] = MNL_TYPE_NESTED,
+	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = MNL_TYPE_STRING,
+	[DEVLINK_ATTR_HEALTH_REPORTER_STATE] = MNL_TYPE_U8,
+	[DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT] = MNL_TYPE_U64,
+	[DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT] = MNL_TYPE_U64,
+	[DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS] = MNL_TYPE_U64,
+	[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = MNL_TYPE_U64,
 };
 
 static int attr_cb(const struct nlattr *attr, void *data)
@@ -980,6 +994,7 @@ static const struct dl_args_metadata dl_args_required[] = {
 	{DL_OPT_REGION_SNAPSHOT_ID,   "Region snapshot id expected."},
 	{DL_OPT_REGION_ADDRESS,	      "Region address value expected."},
 	{DL_OPT_REGION_LENGTH,	      "Region length value expected."},
+	{DL_OPT_HEALTH_REPORTER_NAME, "Reporter's name is expected."},
 };
 
 static int dl_args_finding_required_validate(uint32_t o_required,
@@ -1247,6 +1262,13 @@ static int dl_argv_parse(struct dl *dl, uint32_t o_required,
 			if (err)
 				return err;
 			o_found |= DL_OPT_FLASH_COMPONENT;
+		} else if (dl_argv_match(dl, "reporter") &&
+			   (o_all & DL_OPT_HEALTH_REPORTER_NAME)) {
+			dl_arg_inc(dl);
+			err = dl_argv_str(dl, &opts->reporter_name);
+			if (err)
+				return err;
+			o_found |= DL_OPT_HEALTH_REPORTER_NAME;
 		} else {
 			pr_err("Unknown option \"%s\"\n", dl_argv(dl));
 			return -EINVAL;
@@ -1350,6 +1372,9 @@ static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)
 	if (opts->present & DL_OPT_FLASH_COMPONENT)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT,
 				  opts->flash_component);
+	if (opts->present & DL_OPT_HEALTH_REPORTER_NAME)
+		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME,
+				  opts->reporter_name);
 }
 
 static int dl_argv_parse_put(struct nlmsghdr *nlh, struct dl *dl,
@@ -5790,11 +5815,166 @@ static int cmd_region(struct dl *dl)
 	return -ENOENT;
 }
 
+enum devlink_health_reporter_state {
+	DEVLINK_HEALTH_REPORTER_STATE_HEALTHY,
+	DEVLINK_HEALTH_REPORTER_STATE_ERROR,
+};
+
+static const char *health_state_name(uint8_t state)
+{
+	switch (state) {
+	case DEVLINK_HEALTH_REPORTER_STATE_HEALTHY:
+		return HEALTH_REPORTER_STATE_HEALTHY_STR;
+	case DEVLINK_HEALTH_REPORTER_STATE_ERROR:
+		return HEALTH_REPORTER_STATE_ERROR_STR;
+	default:
+		return "<unknown state>";
+	}
+}
+
+static void format_logtime(uint64_t time_ms, char *ts_date, char *ts_time)
+{
+	struct sysinfo s_info;
+	struct tm *info;
+	time_t now, sec;
+	int err;
+
+	time(&now);
+	info = localtime(&now);
+	err = sysinfo(&s_info);
+	if (err)
+		goto out;
+	/* Subtract uptime in sec from now yields the time of system
+	 * uptime. To this, add time_ms which is the amount of
+	 * milliseconds elapsed between uptime and the dump taken.
+	 */
+	sec = now - s_info.uptime + time_ms / 1000;
+	info = localtime(&sec);
+out:
+	strftime(ts_date, HEALTH_REPORTER_TIMESTAMP_FMT_LEN, "%Y-%m-%d", info);
+	strftime(ts_time, HEALTH_REPORTER_TIMESTAMP_FMT_LEN, "%H:%M:%S", info);
+}
+
+static void pr_out_health(struct dl *dl, struct nlattr **tb_health)
+{
+	struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+	enum devlink_health_reporter_state state;
+	const struct nlattr *attr;
+	uint64_t time_ms;
+	int err;
+
+	err = mnl_attr_parse_nested(tb_health[DEVLINK_ATTR_HEALTH_REPORTER],
+				    attr_cb, tb);
+	if (err != MNL_CB_OK)
+		return;
+
+	if (!tb[DEVLINK_ATTR_HEALTH_REPORTER_NAME] ||
+	    !tb[DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT] ||
+	    !tb[DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT] ||
+	    !tb[DEVLINK_ATTR_HEALTH_REPORTER_STATE])
+		return;
+
+	pr_out_handle_start_arr(dl, tb_health);
+
+	pr_out_str(dl, "name",
+		   mnl_attr_get_str(tb[DEVLINK_ATTR_HEALTH_REPORTER_NAME]));
+	if (!dl->json_output) {
+		__pr_out_newline();
+		__pr_out_indent_inc();
+	}
+	state = mnl_attr_get_u8(tb[DEVLINK_ATTR_HEALTH_REPORTER_STATE]);
+	pr_out_str(dl, "state", health_state_name(state));
+	pr_out_u64(dl, "error",
+		   mnl_attr_get_u64(tb[DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT]));
+	pr_out_u64(dl, "recover",
+		   mnl_attr_get_u64(tb[DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT]));
+	if (tb[DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS]) {
+		char dump_date[HEALTH_REPORTER_TIMESTAMP_FMT_LEN];
+		char dump_time[HEALTH_REPORTER_TIMESTAMP_FMT_LEN];
+
+		attr = tb[DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS];
+		time_ms = mnl_attr_get_u64(attr);
+		format_logtime(time_ms, dump_date, dump_time);
+
+		pr_out_str(dl, "last_dump_date", dump_date);
+		pr_out_str(dl, "last_dump_time", dump_time);
+	}
+	if (tb[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD])
+		pr_out_u64(dl, "grace_period",
+			   mnl_attr_get_u64(tb[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]));
+	if (tb[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])
+		pr_out_bool(dl, "auto_recover",
+			    mnl_attr_get_u8(tb[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]));
+
+	__pr_out_indent_dec();
+	pr_out_handle_end(dl);
+}
+
+static int cmd_health_show_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+	struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+	struct dl *dl = data;
+
+	mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+	if (!tb[DEVLINK_ATTR_BUS_NAME] || !tb[DEVLINK_ATTR_DEV_NAME] ||
+	    !tb[DEVLINK_ATTR_HEALTH_REPORTER])
+		return MNL_CB_ERROR;
+
+	pr_out_health(dl, tb);
+
+	return MNL_CB_OK;
+}
+
+static int cmd_health_show(struct dl *dl)
+{
+	struct nlmsghdr *nlh;
+	uint16_t flags = NLM_F_REQUEST | NLM_F_ACK;
+	int err;
+
+	if (dl_argc(dl) == 0)
+		flags |= NLM_F_DUMP;
+	nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_HEALTH_REPORTER_GET,
+			       flags);
+
+	if (dl_argc(dl) > 0) {
+		err = dl_argv_parse_put(nlh, dl,
+					DL_OPT_HANDLE |
+					DL_OPT_HEALTH_REPORTER_NAME, 0);
+		if (err)
+			return err;
+	}
+	pr_out_section_start(dl, "health");
+
+	err = _mnlg_socket_sndrcv(dl->nlg, nlh, cmd_health_show_cb, dl);
+	pr_out_section_end(dl);
+	return err;
+}
+
+static void cmd_health_help(void)
+{
+	pr_err("Usage: devlink health show [ dev DEV reporter REPORTER_NAME ]\n");
+}
+
+static int cmd_health(struct dl *dl)
+{
+	if (dl_argv_match(dl, "help")) {
+		cmd_health_help();
+		return 0;
+	} else if (dl_argv_match(dl, "show") ||
+		   dl_argv_match(dl, "list") || dl_no_arg(dl)) {
+		dl_arg_inc(dl);
+		return cmd_health_show(dl);
+	}
+	pr_err("Command \"%s\" not found\n", dl_argv(dl));
+	return -ENOENT;
+}
+
 static void help(void)
 {
 	pr_err("Usage: devlink [ OPTIONS ] OBJECT { COMMAND | help }\n"
 	       "       devlink [ -f[orce] ] -b[atch] filename\n"
-	       "where  OBJECT := { dev | port | sb | monitor | dpipe | resource | region }\n"
+	       "where  OBJECT := { dev | port | sb | monitor | dpipe | resource | region | health }\n"
 	       "       OPTIONS := { -V[ersion] | -n[o-nice-names] | -j[son] | -p[retty] | -v[erbose] }\n");
 }
 
@@ -5827,6 +6007,9 @@ static int dl_cmd(struct dl *dl, int argc, char **argv)
 	} else if (dl_argv_match(dl, "region")) {
 		dl_arg_inc(dl);
 		return cmd_region(dl);
+	} else if (dl_argv_match(dl, "health")) {
+		dl_arg_inc(dl);
+		return cmd_health(dl);
 	}
 	pr_err("Object \"%s\" not found\n", dl_argv(dl));
 	return -ENOENT;

From 9083a1344d8cbdd4282c22eec6a1f629059221f1 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:12:59 +0200
Subject: [PATCH 46/55] devlink: Add devlink health recover command

Add devlink health recover command which enables the user to initiate a
recovery on a reporter (if a recovery cb was supplied by the reporter).
This operation will increment the recoveries counter displayed in the
show command.
Example:
$ devlink health recover pci/0000:00:09.0 reporter tx

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index 37eb2054..c77f80c8 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -5815,6 +5815,23 @@ static int cmd_region(struct dl *dl)
 	return -ENOENT;
 }
 
+static int cmd_health_recover(struct dl *dl)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+			       NLM_F_REQUEST | NLM_F_ACK);
+
+	err = dl_argv_parse_put(nlh, dl,
+				DL_OPT_HANDLE | DL_OPT_HEALTH_REPORTER_NAME, 0);
+	if (err)
+		return err;
+
+	dl_opts_put(nlh, dl);
+	return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
+}
+
 enum devlink_health_reporter_state {
 	DEVLINK_HEALTH_REPORTER_STATE_HEALTHY,
 	DEVLINK_HEALTH_REPORTER_STATE_ERROR,
@@ -5954,6 +5971,7 @@ static int cmd_health_show(struct dl *dl)
 static void cmd_health_help(void)
 {
 	pr_err("Usage: devlink health show [ dev DEV reporter REPORTER_NAME ]\n");
+	pr_err("       devlink health recover DEV reporter REPORTER_NAME\n");
 }
 
 static int cmd_health(struct dl *dl)
@@ -5965,6 +5983,9 @@ static int cmd_health(struct dl *dl)
 		   dl_argv_match(dl, "list") || dl_no_arg(dl)) {
 		dl_arg_inc(dl);
 		return cmd_health_show(dl);
+	} else if (dl_argv_match(dl, "recover")) {
+		dl_arg_inc(dl);
+		return cmd_health_recover(dl);
 	}
 	pr_err("Command \"%s\" not found\n", dl_argv(dl));
 	return -ENOENT;

From 7b8baf834d5e95303ed1063a7ef52e81f65a7645 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:13:00 +0200
Subject: [PATCH 47/55] devlink: Add devlink health diagnose command

Add devlink health diagnose command: enabling retrieval of diagnostics data
by the user on a reporter on a device. The command's output is a
free text defined by the reporter.

This patch also introduces an infra structure for flexible format
output. This allow the command to display different data fields
according to the reporter.
Example:
$ devlink health diagnose pci/0000:00:0a.0 reporter tx
SQs:
  sqn: 4403 HW state: 1 stopped: false
  sqn: 4408 HW state: 1 stopped: false
  sqn: 4413 HW state: 1 stopped: false
  sqn: 4418 HW state: 1 stopped: false
  sqn: 4423 HW state: 1 stopped: false

$ devlink health diagnose pci/0000:00:0a.0 reporter tx -jp
{
 "SQs":[
      {
       "sqn":4403,
       "HW state":1,
       "stopped":false
     },
      {
       "sqn":4408,
       "HW state":1,
       "stopped":false
     },
      {
       "sqn":4413,
       "HW state":1,
       "stopped":false
     },
      {
       "sqn":4418,
       "HW state":1,
       "stopped":false
     },
      {
       "sqn":4423,
       "HW state":1,
       "stopped":false
     }
   ]
}

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c | 187 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 187 insertions(+)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index c77f80c8..8490fffd 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -23,6 +23,7 @@
 #include <libmnl/libmnl.h>
 #include <netinet/ether.h>
 #include <sys/sysinfo.h>
+#include <sys/queue.h>
 
 #include "SNAPSHOT.h"
 #include "list.h"
@@ -5815,6 +5816,188 @@ static int cmd_region(struct dl *dl)
 	return -ENOENT;
 }
 
+static int fmsg_value_show(struct dl *dl, int type, struct nlattr *nl_data)
+{
+	uint8_t *data;
+	uint32_t len;
+
+	switch (type) {
+	case MNL_TYPE_FLAG:
+		pr_out_bool_value(dl, mnl_attr_get_u8(nl_data));
+		break;
+	case MNL_TYPE_U8:
+		pr_out_uint_value(dl, mnl_attr_get_u8(nl_data));
+		break;
+	case MNL_TYPE_U16:
+		pr_out_uint_value(dl, mnl_attr_get_u16(nl_data));
+		break;
+	case MNL_TYPE_U32:
+		pr_out_uint_value(dl, mnl_attr_get_u32(nl_data));
+		break;
+	case MNL_TYPE_U64:
+		pr_out_uint64_value(dl, mnl_attr_get_u64(nl_data));
+		break;
+	case MNL_TYPE_NUL_STRING:
+		pr_out_str_value(dl, mnl_attr_get_str(nl_data));
+		break;
+	case MNL_TYPE_BINARY:
+		len = mnl_attr_get_payload_len(nl_data);
+		data = mnl_attr_get_payload(nl_data);
+		pr_out_binary_value(dl, data, len);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return MNL_CB_OK;
+}
+
+struct nest_qentry {
+	int attr_type;
+	TAILQ_ENTRY(nest_qentry) nest_entries;
+};
+
+struct fmsg_cb_data {
+	struct dl *dl;
+	uint8_t value_type;
+	TAILQ_HEAD(, nest_qentry) qhead;
+};
+
+static int cmd_fmsg_nest_queue(struct fmsg_cb_data *fmsg_data,
+			       uint8_t *attr_value, bool insert)
+{
+	struct nest_qentry *entry = NULL;
+
+	if (insert) {
+		entry = malloc(sizeof(struct nest_qentry));
+		if (!entry)
+			return -ENOMEM;
+
+		entry->attr_type = *attr_value;
+		TAILQ_INSERT_HEAD(&fmsg_data->qhead, entry, nest_entries);
+	} else {
+		if (TAILQ_EMPTY(&fmsg_data->qhead))
+			return MNL_CB_ERROR;
+		entry = TAILQ_FIRST(&fmsg_data->qhead);
+		*attr_value = entry->attr_type;
+		TAILQ_REMOVE(&fmsg_data->qhead, entry, nest_entries);
+		free(entry);
+	}
+	return MNL_CB_OK;
+}
+
+static int cmd_fmsg_nest(struct fmsg_cb_data *fmsg_data, uint8_t nest_value,
+			 bool start)
+{
+	struct dl *dl = fmsg_data->dl;
+	uint8_t value = nest_value;
+	int err;
+
+	err = cmd_fmsg_nest_queue(fmsg_data, &value, start);
+	if (err != MNL_CB_OK)
+		return err;
+
+	switch (value) {
+	case DEVLINK_ATTR_FMSG_OBJ_NEST_START:
+		if (start)
+			pr_out_entry_start(dl);
+		else
+			pr_out_entry_end(dl);
+		break;
+	case DEVLINK_ATTR_FMSG_PAIR_NEST_START:
+		break;
+	case DEVLINK_ATTR_FMSG_ARR_NEST_START:
+		if (dl->json_output) {
+			if (start)
+				jsonw_start_array(dl->jw);
+			else
+				jsonw_end_array(dl->jw);
+		} else {
+			if (start) {
+				__pr_out_newline();
+				__pr_out_indent_inc();
+			} else {
+				__pr_out_indent_dec();
+			}
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	return MNL_CB_OK;
+}
+
+static int cmd_fmsg_object_cb(const struct nlmsghdr *nlh, void *data)
+{
+	struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+	struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+	struct fmsg_cb_data *fmsg_data = data;
+	struct dl *dl = fmsg_data->dl;
+	struct nlattr *nla_object;
+	int attr_type;
+	int err;
+
+	mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+	if (!tb[DEVLINK_ATTR_FMSG])
+		return MNL_CB_ERROR;
+
+	mnl_attr_for_each_nested(nla_object, tb[DEVLINK_ATTR_FMSG]) {
+		attr_type = mnl_attr_get_type(nla_object);
+		switch (attr_type) {
+		case DEVLINK_ATTR_FMSG_OBJ_NEST_START:
+		case DEVLINK_ATTR_FMSG_PAIR_NEST_START:
+		case DEVLINK_ATTR_FMSG_ARR_NEST_START:
+			err = cmd_fmsg_nest(fmsg_data, attr_type, true);
+			if (err != MNL_CB_OK)
+				return err;
+			break;
+		case DEVLINK_ATTR_FMSG_NEST_END:
+			err = cmd_fmsg_nest(fmsg_data, attr_type, false);
+			if (err != MNL_CB_OK)
+				return err;
+			break;
+		case DEVLINK_ATTR_FMSG_OBJ_NAME:
+			pr_out_name(dl, mnl_attr_get_str(nla_object));
+			break;
+		case DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE:
+			fmsg_data->value_type = mnl_attr_get_u8(nla_object);
+			break;
+		case DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA:
+			err = fmsg_value_show(dl, fmsg_data->value_type,
+					      nla_object);
+			if (err != MNL_CB_OK)
+				return err;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+	return MNL_CB_OK;
+}
+
+static int cmd_health_object_common(struct dl *dl, uint8_t cmd)
+{
+	struct fmsg_cb_data data;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = mnlg_msg_prepare(dl->nlg, cmd,  NLM_F_REQUEST | NLM_F_ACK);
+
+	err = dl_argv_parse_put(nlh, dl,
+				DL_OPT_HANDLE | DL_OPT_HEALTH_REPORTER_NAME, 0);
+	if (err)
+		return err;
+
+	data.dl = dl;
+	TAILQ_INIT(&data.qhead);
+	err = _mnlg_socket_sndrcv(dl->nlg, nlh, cmd_fmsg_object_cb, &data);
+	return err;
+}
+
+static int cmd_health_diagnose(struct dl *dl)
+{
+	return cmd_health_object_common(dl, DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE);
+}
+
 static int cmd_health_recover(struct dl *dl)
 {
 	struct nlmsghdr *nlh;
@@ -5972,6 +6155,7 @@ static void cmd_health_help(void)
 {
 	pr_err("Usage: devlink health show [ dev DEV reporter REPORTER_NAME ]\n");
 	pr_err("       devlink health recover DEV reporter REPORTER_NAME\n");
+	pr_err("       devlink health diagnose DEV reporter REPORTER_NAME\n");
 }
 
 static int cmd_health(struct dl *dl)
@@ -5986,6 +6170,9 @@ static int cmd_health(struct dl *dl)
 	} else if (dl_argv_match(dl, "recover")) {
 		dl_arg_inc(dl);
 		return cmd_health_recover(dl);
+	} else if (dl_argv_match(dl, "diagnose")) {
+		dl_arg_inc(dl);
+		return cmd_health_diagnose(dl);
 	}
 	pr_err("Command \"%s\" not found\n", dl_argv(dl));
 	return -ENOENT;

From 041e6e651a8ef9b0d0cb770ef0bd01f5ccda2e2f Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:13:01 +0200
Subject: [PATCH 48/55] devlink: Add devlink health dump show command

Add devlink dump show command which displays the last saved dump.
Devlink health saves a single dump. If a dump is not already stored
by the devlink for this reporter, devlink generates a new dump. The dump
can be generated automatically when a reporter reports on an
error or manually by user's request.
The dump's output is defined by the reporter. The command uses the
infra structure for flexible format output introduced in previous patch.
Example:
$ devlink health dump show pci/0000:00:09.0 reporter tx

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index 8490fffd..30076d25 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -5993,6 +5993,11 @@ static int cmd_health_object_common(struct dl *dl, uint8_t cmd)
 	return err;
 }
 
+static int cmd_health_dump_show(struct dl *dl)
+{
+	return cmd_health_object_common(dl, DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET);
+}
+
 static int cmd_health_diagnose(struct dl *dl)
 {
 	return cmd_health_object_common(dl, DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE);
@@ -6156,6 +6161,7 @@ static void cmd_health_help(void)
 	pr_err("Usage: devlink health show [ dev DEV reporter REPORTER_NAME ]\n");
 	pr_err("       devlink health recover DEV reporter REPORTER_NAME\n");
 	pr_err("       devlink health diagnose DEV reporter REPORTER_NAME\n");
+	pr_err("       devlink health dump show DEV reporter REPORTER_NAME\n");
 }
 
 static int cmd_health(struct dl *dl)
@@ -6173,6 +6179,12 @@ static int cmd_health(struct dl *dl)
 	} else if (dl_argv_match(dl, "diagnose")) {
 		dl_arg_inc(dl);
 		return cmd_health_diagnose(dl);
+	} else if (dl_argv_match(dl, "dump")) {
+		dl_arg_inc(dl);
+		if (dl_argv_match(dl, "show")) {
+			dl_arg_inc(dl);
+			return cmd_health_dump_show(dl);
+		}
 	}
 	pr_err("Command \"%s\" not found\n", dl_argv(dl));
 	return -ENOENT;

From 04b583d0fff3496c5f5cd9aa3b2fb1fc23398909 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:13:02 +0200
Subject: [PATCH 49/55] devlink: Add devlink health dump clear command

Add devlink dump clear command which deletes the last saved dump file.
Clearing the last saved dump enables a new dump file to be saved.
Example:
$ devlink health dump clear pci/0000:00:09.0 reporter tx

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index 30076d25..f6405824 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -5816,6 +5816,23 @@ static int cmd_region(struct dl *dl)
 	return -ENOENT;
 }
 
+static int cmd_health_dump_clear(struct dl *dl)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
+			       NLM_F_REQUEST | NLM_F_ACK);
+
+	err = dl_argv_parse_put(nlh, dl,
+				DL_OPT_HANDLE | DL_OPT_HEALTH_REPORTER_NAME, 0);
+	if (err)
+		return err;
+
+	dl_opts_put(nlh, dl);
+	return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
+}
+
 static int fmsg_value_show(struct dl *dl, int type, struct nlattr *nl_data)
 {
 	uint8_t *data;
@@ -6162,6 +6179,7 @@ static void cmd_health_help(void)
 	pr_err("       devlink health recover DEV reporter REPORTER_NAME\n");
 	pr_err("       devlink health diagnose DEV reporter REPORTER_NAME\n");
 	pr_err("       devlink health dump show DEV reporter REPORTER_NAME\n");
+	pr_err("       devlink health dump clear DEV reporter REPORTER_NAME\n");
 }
 
 static int cmd_health(struct dl *dl)
@@ -6184,6 +6202,9 @@ static int cmd_health(struct dl *dl)
 		if (dl_argv_match(dl, "show")) {
 			dl_arg_inc(dl);
 			return cmd_health_dump_show(dl);
+		} else if (dl_argv_match(dl, "clear")) {
+			dl_arg_inc(dl);
+			return cmd_health_dump_clear(dl);
 		}
 	}
 	pr_err("Command \"%s\" not found\n", dl_argv(dl));

From b18d89195b164b3eee5b7090686fe4d4fad3248f Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:13:03 +0200
Subject: [PATCH 50/55] devlink: Add devlink health set command

Add devlink set command which enables the user to configure parameters
related to the devlink health mechanism per reporter.
1) grace_period [msec] time interval between auto recoveries.
2) auto_recover [true/false] whether the devlink should execute automatic
recover on error.
Add a helper function to retrieve a boolean value as an input parameter.
Example:
$ devlink health set pci/0000:00:09.0 reporter tx grace_period 3500
$ devlink health set pci/0000:00:09.0 reporter tx auto_recover false

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 devlink/devlink.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

diff --git a/devlink/devlink.c b/devlink/devlink.c
index f6405824..dc6e73fe 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -209,6 +209,8 @@ static void ifname_map_free(struct ifname_map *ifname_map)
 #define DL_OPT_FLASH_FILE_NAME	BIT(25)
 #define DL_OPT_FLASH_COMPONENT	BIT(26)
 #define DL_OPT_HEALTH_REPORTER_NAME	BIT(27)
+#define DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD	BIT(27)
+#define DL_OPT_HEALTH_REPORTER_AUTO_RECOVER	BIT(28)
 
 struct dl_opts {
 	uint32_t present; /* flags of present items */
@@ -243,6 +245,8 @@ struct dl_opts {
 	const char *flash_file_name;
 	const char *flash_component;
 	const char *reporter_name;
+	uint64_t reporter_graceful_period;
+	bool reporter_auto_recover;
 };
 
 struct dl {
@@ -841,6 +845,24 @@ static int dl_argv_uint16_t(struct dl *dl, uint16_t *p_val)
 	return 0;
 }
 
+static int dl_argv_bool(struct dl *dl, bool *p_val)
+{
+	char *str = dl_argv_next(dl);
+	int err;
+
+	if (!str) {
+		pr_err("Boolean argument expected\n");
+		return -EINVAL;
+	}
+
+	err = strtobool(str, p_val);
+	if (err) {
+		pr_err("\"%s\" is not a valid boolean value\n", str);
+		return err;
+	}
+	return 0;
+}
+
 static int dl_argv_str(struct dl *dl, const char **p_str)
 {
 	const char *str = dl_argv_next(dl);
@@ -1270,6 +1292,21 @@ static int dl_argv_parse(struct dl *dl, uint32_t o_required,
 			if (err)
 				return err;
 			o_found |= DL_OPT_HEALTH_REPORTER_NAME;
+		} else if (dl_argv_match(dl, "grace_period") &&
+			   (o_all & DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD)) {
+			dl_arg_inc(dl);
+			err = dl_argv_uint64_t(dl,
+					       &opts->reporter_graceful_period);
+			if (err)
+				return err;
+			o_found |= DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD;
+		} else if (dl_argv_match(dl, "auto_recover") &&
+			(o_all & DL_OPT_HEALTH_REPORTER_AUTO_RECOVER)) {
+			dl_arg_inc(dl);
+			err = dl_argv_bool(dl, &opts->reporter_auto_recover);
+			if (err)
+				return err;
+			o_found |= DL_OPT_HEALTH_REPORTER_AUTO_RECOVER;
 		} else {
 			pr_err("Unknown option \"%s\"\n", dl_argv(dl));
 			return -EINVAL;
@@ -1376,6 +1413,14 @@ static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)
 	if (opts->present & DL_OPT_HEALTH_REPORTER_NAME)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME,
 				  opts->reporter_name);
+	if (opts->present & DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD)
+		mnl_attr_put_u64(nlh,
+				 DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD,
+				 opts->reporter_graceful_period);
+	if (opts->present & DL_OPT_HEALTH_REPORTER_AUTO_RECOVER)
+		mnl_attr_put_u8(nlh, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,
+				opts->reporter_auto_recover);
+
 }
 
 static int dl_argv_parse_put(struct nlmsghdr *nlh, struct dl *dl,
@@ -5816,6 +5861,23 @@ static int cmd_region(struct dl *dl)
 	return -ENOENT;
 }
 
+static int cmd_health_set_params(struct dl *dl)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_HEALTH_REPORTER_SET,
+			       NLM_F_REQUEST | NLM_F_ACK);
+	err = dl_argv_parse(dl, DL_OPT_HANDLE | DL_OPT_HEALTH_REPORTER_NAME,
+			    DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD |
+			    DL_OPT_HEALTH_REPORTER_AUTO_RECOVER);
+	if (err)
+		return err;
+
+	dl_opts_put(nlh, dl);
+	return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
+}
+
 static int cmd_health_dump_clear(struct dl *dl)
 {
 	struct nlmsghdr *nlh;
@@ -6180,6 +6242,7 @@ static void cmd_health_help(void)
 	pr_err("       devlink health diagnose DEV reporter REPORTER_NAME\n");
 	pr_err("       devlink health dump show DEV reporter REPORTER_NAME\n");
 	pr_err("       devlink health dump clear DEV reporter REPORTER_NAME\n");
+	pr_err("       devlink health set DEV reporter REPORTER_NAME { grace_period | auto_recover } { msec | boolean }\n");
 }
 
 static int cmd_health(struct dl *dl)
@@ -6206,6 +6269,9 @@ static int cmd_health(struct dl *dl)
 			dl_arg_inc(dl);
 			return cmd_health_dump_clear(dl);
 		}
+	} else if (dl_argv_match(dl, "set")) {
+		dl_arg_inc(dl);
+		return cmd_health_set_params(dl);
 	}
 	pr_err("Command \"%s\" not found\n", dl_argv(dl));
 	return -ENOENT;

From 3147e0d37248f201d9b5ebcfb443e1f93e4f4bd3 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 28 Feb 2019 14:13:04 +0200
Subject: [PATCH 51/55] devlink: Add devlink-health man page

Add a man page describing devlink health's command set. Also add a
reference link from devlink main man page.

Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 man/man8/devlink-health.8 | 197 ++++++++++++++++++++++++++++++++++++++
 man/man8/devlink.8        |   7 +-
 2 files changed, 203 insertions(+), 1 deletion(-)
 create mode 100644 man/man8/devlink-health.8

diff --git a/man/man8/devlink-health.8 b/man/man8/devlink-health.8
new file mode 100644
index 00000000..7ed0ae45
--- /dev/null
+++ b/man/man8/devlink-health.8
@@ -0,0 +1,197 @@
+.TH DEVLINK\-HEALTH 8 "20 Feb 2019" "iproute2" "Linux"
+.SH NAME
+devlink-health \- devlink health reporting and recovery
+.SH SYNOPSIS
+.sp
+.ad l
+.in +8
+.ti -8
+.B devlink
+.RI "[ " OPTIONS " ]"
+.B health
+.RI  " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.IR OPTIONS " := { "
+\fB\-V\fR[\fIersion\fR] }
+
+.ti -8
+.BR "devlink health show"
+.RI "[ " DEV ""
+.B reporter
+.RI ""REPORTER " ] "
+
+.ti -8
+.BR "devlink health recover"
+.RI "" DEV ""
+.B reporter
+.RI "" REPORTER ""
+
+.ti -8
+.BR "devlink health diagnose"
+.RI "" DEV ""
+.B reporter
+.RI "" REPORTER ""
+
+.ti -8
+.BR "devlink health dump show"
+.RI "" DEV ""
+.B  reporter
+.RI "" REPORTER ""
+
+.ti -8
+.BR "devlink health dump clear"
+.RI "" DEV ""
+.B reporter
+.RI "" REPORTER ""
+
+.ti -8
+.BR "devlink health set"
+.RI "" DEV ""
+.B reporter
+.RI "" REPORTER ""
+.RI " { "
+.B grace_period | auto_recover
+.RI " } { "
+.RI "" msec ""
+.RI "|"
+.RI "" boolean ""
+.RI " } "
+.ti -8
+.B devlink health help
+
+.SH "DESCRIPTION"
+.SS devlink health show - Show status and configuration on all supported reporters on all devlink devices.
+
+.PP
+.I "DEV"
+- specifies the devlink device.
+
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+
+.SS devlink health recover - Initiate a recovery operation on a reporter.
+This action performs a recovery and increases the recoveries counter on success.
+
+.PP
+.I "DEV"
+- specifies the devlink device.
+
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+
+.SS devlink health diagnose - Retrieve diagnostics data on a reporter.
+
+.PP
+.I "DEV"
+- specifies the devlink device.
+
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+
+.SS devlink health dump show - Display the last saved dump.
+
+.PD 0
+.P
+devlink health saves a single dump per reporter. If an dump is
+.P
+not already stored by the Devlink, this command will generate a new
+.P
+dump. The dump can be generated either automatically when a
+.P
+reporter reports on an error or manually at the user's request.
+.PD
+
+.PP
+.I "DEV"
+- specifies the devlink device.
+
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+
+.SS devlink health dump clear - Delete the saved dump.
+Deleting the saved dump enables a generation of a new dump on
+.PD 0
+.P
+the next "devlink health dump show" command.
+.PD
+
+.PP
+.I "DEV"
+- specifies the devlink device.
+
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+
+.SS devlink health set - Enable the user to configure:
+.PD 0
+1) grace_period [msec] - Time interval between consecutive auto recoveries.
+.P
+2) auto_recover [true/false] - Indicates whether the devlink should execute automatic recover on error.
+.P
+Please note that this command is not supported on a reporter which
+doesn't support a recovery method.
+.PD
+
+.PP
+.I "DEV"
+- specifies the devlink device.
+
+.PP
+.I "REPORTER"
+- specifies the reporter's name registered on the devlink device.
+
+.SH "EXAMPLES"
+.PP
+devlink health show
+.RS 4
+List status and configuration of available reporters on devices.
+.RE
+.PP
+devlink health recover pci/0000:00:09.0 reporter tx
+.RS 4
+Initiate recovery on tx reporter registered on pci/0000:00:09.0.
+.RE
+.PP
+devlink health diagnose pci/0000:00:09.0 reporter tx
+.RS 4
+List diagnostics data on the specified device and reporter.
+.RE
+.PP
+devlink health dump show pci/0000:00:09.0 reporter tx
+.RS 4
+Display the last saved dump on the specified device and reporter.
+.RE
+.PP
+devlink health dump clear pci/0000:00:09.0 reporter tx
+.RS 4
+Delete saved dump on the specified device and reporter.
+.RE
+.PP
+devlink health set pci/0000:00:09.0 reporter tx grace_period 3500
+.RS 4
+Set time interval between auto recoveries to minimum of 3500 msec on
+the specified device and reporter.
+.RE
+.PP
+devlink health set pci/0000:00:09.0 reporter tx auto_recover false
+.RS 4
+Turn off auto recovery on the specified device and reporter.
+.RE
+.SH SEE ALSO
+.BR devlink (8),
+.BR devlink-dev (8),
+.BR devlink-port (8),
+.BR devlink-param (8),
+.BR devlink-region (8),
+.br
+
+.SH AUTHOR
+Aya Levin <ayal@mellanox.com>
diff --git a/man/man8/devlink.8 b/man/man8/devlink.8
index 8d527e7e..13d4dcd9 100644
--- a/man/man8/devlink.8
+++ b/man/man8/devlink.8
@@ -7,7 +7,7 @@ devlink \- Devlink tool
 .in +8
 .ti -8
 .B devlink
-.RI "[ " OPTIONS " ] { " dev | port | monitor | sb | resource | region " } { " COMMAND " | "
+.RI "[ " OPTIONS " ] { " dev | port | monitor | sb | resource | region | health " } { " COMMAND " | "
 .BR help " }"
 .sp
 
@@ -78,6 +78,10 @@ Turn on verbose output.
 .B region
 - devlink address region access
 
+.TP
+.B health
+- devlink reporting and recovery
+
 .SS
 .I COMMAND
 
@@ -109,6 +113,7 @@ Exit status is 0 if command was successful or a positive integer upon failure.
 .BR devlink-sb (8),
 .BR devlink-resource (8),
 .BR devlink-region (8),
+.BR devlink-health (8),
 .br
 
 .SH REPORTING BUGS

From c5b176e5ba1f51336350b4ad36039aaef9f4af07 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Sun, 3 Mar 2019 21:26:32 -0800
Subject: [PATCH 52/55] bridge: fdb: add support for src_vni option

We already print src_vni for a fdb entry when present.
This patch adds the ability to set src_vni on a fdb
entry. When not specified, kernel will use vni specified
on the vxlan device. This can be used on a vxlan fdb entry
when the vxlan device is in external or collect metadata
mode.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 bridge/fdb.c      | 10 ++++++++++
 man/man8/bridge.8 |  9 +++++++++
 2 files changed, 19 insertions(+)

diff --git a/bridge/fdb.c b/bridge/fdb.c
index c4bf4039..941ce2d5 100644
--- a/bridge/fdb.c
+++ b/bridge/fdb.c
@@ -39,6 +39,7 @@ static void usage(void)
 		"              [ self ] [ master ] [ use ] [ router ] [ extern_learn ]\n"
 		"              [ sticky ] [ local | static | dynamic ] [ dst IPADDR ]\n"
 		"              [ vlan VID ] [ port PORT] [ vni VNI ] [ via DEV ]\n"
+		"              [ src_vni VNI ]\n"
 		"       bridge fdb [ show [ br BRDEV ] [ brport DEV ] [ vlan VID ] [ state STATE ] ]\n");
 	exit(-1);
 }
@@ -383,6 +384,7 @@ static int fdb_modify(int cmd, int flags, int argc, char **argv)
 	inet_prefix dst;
 	unsigned long port = 0;
 	unsigned long vni = ~0;
+	unsigned long src_vni = ~0;
 	unsigned int via = 0;
 	char *endptr;
 	short vid = -1;
@@ -416,6 +418,12 @@ static int fdb_modify(int cmd, int flags, int argc, char **argv)
 			if ((endptr && *endptr) ||
 			    (vni >> 24) || vni == ULONG_MAX)
 				invarg("invalid VNI\n", *argv);
+		} else if (strcmp(*argv, "src_vni") == 0) {
+			NEXT_ARG();
+			src_vni = strtoul(*argv, &endptr, 0);
+			if ((endptr && *endptr) ||
+			    (src_vni >> 24) || src_vni == ULONG_MAX)
+				invarg("invalid src VNI\n", *argv);
 		} else if (strcmp(*argv, "via") == 0) {
 			NEXT_ARG();
 			via = ll_name_to_index(*argv);
@@ -495,6 +503,8 @@ static int fdb_modify(int cmd, int flags, int argc, char **argv)
 	}
 	if (vni != ~0)
 		addattr32(&req.n, sizeof(req), NDA_VNI, vni);
+	if (src_vni != ~0)
+		addattr32(&req.n, sizeof(req), NDA_SRC_VNI, src_vni);
 	if (via)
 		addattr32(&req.n, sizeof(req), NDA_IFINDEX, via);
 
diff --git a/man/man8/bridge.8 b/man/man8/bridge.8
index 13c46386..c9af20e8 100644
--- a/man/man8/bridge.8
+++ b/man/man8/bridge.8
@@ -69,6 +69,8 @@ bridge \- show / manipulate bridge addresses and devices
 .BR self " ] [ " master " ] [ " router " ] [ " use " ] [ " extern_learn " ] [ " sticky " ] [ "
 .B dst
 .IR IPADDR " ] [ "
+.B src_vni
+.IR SRC_VNI " ] ["
 .B vni
 .IR VNI " ] ["
 .B port
@@ -473,6 +475,13 @@ is of type VXLAN.
 the IP address of the destination
 VXLAN tunnel endpoint where the Ethernet MAC ADDRESS resides.
 
+.TP
+.BI src_vni " SRC VNI"
+the src VNI Network Identifier (or VXLAN Segment ID)
+this entry belongs to. Used only when the vxlan device is in
+external or collect metadata mode. If omitted the value specified at
+vxlan device creation will be used.
+
 .TP
 .BI vni " VNI"
 the VXLAN VNI Network Identifier (or VXLAN Segment ID)

From 8ff3d1d3a33537088fa184a9c74bb8eb063720b2 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 12 Mar 2019 18:41:26 +0200
Subject: [PATCH 53/55] ip: xstats: add json output support

This adds only initial object support if json argument is specified.
Later patches convert the current xstats users to json.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 ip/iplink_xstats.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/ip/iplink_xstats.c b/ip/iplink_xstats.c
index 908d9228..c64e6885 100644
--- a/ip/iplink_xstats.c
+++ b/ip/iplink_xstats.c
@@ -70,10 +70,13 @@ int iplink_ifla_xstats(int argc, char **argv)
 		return -1;
 	}
 
+	new_json_obj(json);
 	if (rtnl_dump_filter(&rth, lu->print_ifla_xstats, stdout) < 0) {
+		delete_json_obj();
 		fprintf(stderr, "Dump terminated\n");
 		return -1;
 	}
+	delete_json_obj();
 
 	return 0;
 }

From a9bc23a79227acbf8f11010e5ab3fc28da4b1aaa Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 12 Mar 2019 18:41:27 +0200
Subject: [PATCH 54/55] ip: bridge: add xstats json support

Add json support for bridge's xstats output.
The plain text output format should remain the same.
Note that this patch pulls the interface out of the attribute
loop, this was an oversight when the set was upstreamed. This does not
change the output format, but fixes it when new xstats attributes show
up.

Example:
$ ip -p -j link xstats type bridge
  [ {
        "ifname": "br0",
        "multicast": {
            "igmp_queries": {
                "rx_v1": 0,
                "rx_v2": 32,
                "rx_v3": 0,
                "tx_v1": 0,
                "tx_v2": 0,
                "tx_v3": 0
            },
            "igmp_reports": {
                "rx_v1": 0,
                "rx_v2": 32,
                "rx_v3": 0,
                "tx_v1": 0,
                "tx_v2": 0,
                "tx_v3": 0
            },
            "igmp_leaves": {
                "rx": 0,
                "tx": 0
            },
            "igmp_parse_errors": 0,
            "mld_queries": {
                "rx_v1": 33,
                "rx_v2": 0,
                "tx_v1": 0,
                "tx_v2": 0
            },
            "mld_reports": {
                "rx_v1": 66,
                "rx_v2": 2,
                "tx_v1": 0,
                "tx_v2": 0
            },
            "mld_leaves": {
                "rx": 0,
                "tx": 0
            },
            "mld_parse_errors": 0
        }
    } ]

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 ip/iplink_bridge.c | 155 ++++++++++++++++++++++++++++-----------------
 1 file changed, 97 insertions(+), 58 deletions(-)

diff --git a/ip/iplink_bridge.c b/ip/iplink_bridge.c
index fbf8a79b..e9b77fdf 100644
--- a/ip/iplink_bridge.c
+++ b/ip/iplink_bridge.c
@@ -670,7 +670,7 @@ static void bridge_print_xstats_help(struct link_util *lu, FILE *f)
 	fprintf(f, "Usage: ... %s [ igmp ] [ dev DEVICE ]\n", lu->id);
 }
 
-static void bridge_print_stats_attr(FILE *f, struct rtattr *attr, int ifindex)
+static void bridge_print_stats_attr(struct rtattr *attr, int ifindex)
 {
 	struct rtattr *brtb[LINK_XSTATS_TYPE_MAX+1];
 	struct br_mcast_stats *mstats;
@@ -685,76 +685,116 @@ static void bridge_print_stats_attr(FILE *f, struct rtattr *attr, int ifindex)
 
 	list = brtb[LINK_XSTATS_TYPE_BRIDGE];
 	rem = RTA_PAYLOAD(list);
+	open_json_object(NULL);
+	ifname = ll_index_to_name(ifindex);
+	print_string(PRINT_ANY, "ifname", "%-16s\n", ifname);
 	for (i = RTA_DATA(list); RTA_OK(i, rem); i = RTA_NEXT(i, rem)) {
 		if (xstats_print_attr && i->rta_type != xstats_print_attr)
 			continue;
 		switch (i->rta_type) {
 		case BRIDGE_XSTATS_MCAST:
 			mstats = RTA_DATA(i);
-			ifname = ll_index_to_name(ifindex);
-			fprintf(f, "%-16s\n", ifname);
-			fprintf(f, "%-16s    IGMP queries:\n", "");
-			fprintf(f, "%-16s      RX: v1 %llu v2 %llu v3 %llu\n",
-				"",
-				mstats->igmp_v1queries[BR_MCAST_DIR_RX],
-				mstats->igmp_v2queries[BR_MCAST_DIR_RX],
-				mstats->igmp_v3queries[BR_MCAST_DIR_RX]);
-			fprintf(f, "%-16s      TX: v1 %llu v2 %llu v3 %llu\n",
-				"",
-				mstats->igmp_v1queries[BR_MCAST_DIR_TX],
-				mstats->igmp_v2queries[BR_MCAST_DIR_TX],
-				mstats->igmp_v3queries[BR_MCAST_DIR_TX]);
+			open_json_object("multicast");
+			open_json_object("igmp_queries");
+			print_string(PRINT_FP, NULL,
+				     "%-16s    IGMP queries:\n", "");
+			print_string(PRINT_FP, NULL, "%-16s      ", "");
+			print_u64(PRINT_ANY, "rx_v1", "RX: v1 %llu ",
+				  mstats->igmp_v1queries[BR_MCAST_DIR_RX]);
+			print_u64(PRINT_ANY, "rx_v2", "v2 %llu ",
+				  mstats->igmp_v2queries[BR_MCAST_DIR_RX]);
+			print_u64(PRINT_ANY, "rx_v3", "v3 %llu\n",
+				  mstats->igmp_v3queries[BR_MCAST_DIR_RX]);
+			print_string(PRINT_FP, NULL, "%-16s      ", "");
+			print_u64(PRINT_ANY, "tx_v1", "TX: v1 %llu ",
+				  mstats->igmp_v1queries[BR_MCAST_DIR_TX]);
+			print_u64(PRINT_ANY, "tx_v2", "v2 %llu ",
+				  mstats->igmp_v2queries[BR_MCAST_DIR_TX]);
+			print_u64(PRINT_ANY, "tx_v3", "v3 %llu\n",
+				  mstats->igmp_v3queries[BR_MCAST_DIR_TX]);
+			close_json_object();
 
-			fprintf(f, "%-16s    IGMP reports:\n", "");
-			fprintf(f, "%-16s      RX: v1 %llu v2 %llu v3 %llu\n",
-				"",
-				mstats->igmp_v1reports[BR_MCAST_DIR_RX],
-				mstats->igmp_v2reports[BR_MCAST_DIR_RX],
-				mstats->igmp_v3reports[BR_MCAST_DIR_RX]);
-			fprintf(f, "%-16s      TX: v1 %llu v2 %llu v3 %llu\n",
-				"",
-				mstats->igmp_v1reports[BR_MCAST_DIR_TX],
-				mstats->igmp_v2reports[BR_MCAST_DIR_TX],
-				mstats->igmp_v3reports[BR_MCAST_DIR_TX]);
+			open_json_object("igmp_reports");
+			print_string(PRINT_FP, NULL,
+				     "%-16s    IGMP reports:\n", "");
+			print_string(PRINT_FP, NULL, "%-16s      ", "");
+			print_u64(PRINT_ANY, "rx_v1", "RX: v1 %llu ",
+				  mstats->igmp_v1reports[BR_MCAST_DIR_RX]);
+			print_u64(PRINT_ANY, "rx_v2", "v2 %llu ",
+				  mstats->igmp_v2reports[BR_MCAST_DIR_RX]);
+			print_u64(PRINT_ANY, "rx_v3", "v3 %llu\n",
+				  mstats->igmp_v3reports[BR_MCAST_DIR_RX]);
+			print_string(PRINT_FP, NULL, "%-16s      ", "");
+			print_u64(PRINT_ANY, "tx_v1", "TX: v1 %llu ",
+				  mstats->igmp_v1reports[BR_MCAST_DIR_TX]);
+			print_u64(PRINT_ANY, "tx_v2", "v2 %llu",
+				  mstats->igmp_v2reports[BR_MCAST_DIR_TX]);
+			print_u64(PRINT_ANY, "tx_v3", "v3 %llu\n",
+				  mstats->igmp_v3reports[BR_MCAST_DIR_TX]);
+			close_json_object();
 
-			fprintf(f, "%-16s    IGMP leaves: RX: %llu TX: %llu\n",
-				"",
-				mstats->igmp_leaves[BR_MCAST_DIR_RX],
-				mstats->igmp_leaves[BR_MCAST_DIR_TX]);
+			open_json_object("igmp_leaves");
+			print_string(PRINT_FP, NULL,
+				     "%-16s    IGMP leaves: ", "");
+			print_u64(PRINT_ANY, "rx", "RX: %llu ",
+				  mstats->igmp_leaves[BR_MCAST_DIR_RX]);
+			print_u64(PRINT_ANY, "tx", "TX: %llu\n",
+				  mstats->igmp_leaves[BR_MCAST_DIR_TX]);
+			close_json_object();
 
-			fprintf(f, "%-16s    IGMP parse errors: %llu\n",
-				"", mstats->igmp_parse_errors);
+			print_string(PRINT_FP, NULL,
+				     "%-16s    IGMP parse errors: ", "");
+			print_u64(PRINT_ANY, "igmp_parse_errors", "%llu\n",
+				  mstats->igmp_parse_errors);
 
-			fprintf(f, "%-16s    MLD queries:\n", "");
-			fprintf(f, "%-16s      RX: v1 %llu v2 %llu\n",
-				"",
-				mstats->mld_v1queries[BR_MCAST_DIR_RX],
-				mstats->mld_v2queries[BR_MCAST_DIR_RX]);
-			fprintf(f, "%-16s      TX: v1 %llu v2 %llu\n",
-				"",
-				mstats->mld_v1queries[BR_MCAST_DIR_TX],
-				mstats->mld_v2queries[BR_MCAST_DIR_TX]);
+			open_json_object("mld_queries");
+			print_string(PRINT_FP, NULL,
+				     "%-16s    MLD queries:\n", "");
+			print_string(PRINT_FP, NULL, "%-16s      ", "");
+			print_u64(PRINT_ANY, "rx_v1", "RX: v1 %llu ",
+				  mstats->mld_v1queries[BR_MCAST_DIR_RX]);
+			print_u64(PRINT_ANY, "rx_v2", "v2 %llu\n",
+				  mstats->mld_v2queries[BR_MCAST_DIR_RX]);
+			print_string(PRINT_FP, NULL, "%-16s      ", "");
+			print_u64(PRINT_ANY, "tx_v1", "TX: v1 %llu ",
+				  mstats->mld_v1queries[BR_MCAST_DIR_TX]);
+			print_u64(PRINT_ANY, "tx_v2", "v2 %llu\n",
+				  mstats->mld_v2queries[BR_MCAST_DIR_TX]);
+			close_json_object();
 
-			fprintf(f, "%-16s    MLD reports:\n", "");
-			fprintf(f, "%-16s      RX: v1 %llu v2 %llu\n",
-				"",
-				mstats->mld_v1reports[BR_MCAST_DIR_RX],
-				mstats->mld_v2reports[BR_MCAST_DIR_RX]);
-			fprintf(f, "%-16s      TX: v1 %llu v2 %llu\n",
-				"",
-				mstats->mld_v1reports[BR_MCAST_DIR_TX],
-				mstats->mld_v2reports[BR_MCAST_DIR_TX]);
+			open_json_object("mld_reports");
+			print_string(PRINT_FP, NULL,
+				     "%-16s    MLD reports:\n", "");
+			print_string(PRINT_FP, NULL, "%-16s      ", "");
+			print_u64(PRINT_ANY, "rx_v1", "RX: v1 %llu ",
+				  mstats->mld_v1reports[BR_MCAST_DIR_RX]);
+			print_u64(PRINT_ANY, "rx_v2", "v2 %llu\n",
+				  mstats->mld_v2reports[BR_MCAST_DIR_RX]);
+			print_string(PRINT_FP, NULL, "%-16s      ", "");
+			print_u64(PRINT_ANY, "tx_v1", "TX: v1 %llu ",
+				  mstats->mld_v1reports[BR_MCAST_DIR_TX]);
+			print_u64(PRINT_ANY, "tx_v2", "v2 %llu\n",
+				  mstats->mld_v2reports[BR_MCAST_DIR_TX]);
+			close_json_object();
 
-			fprintf(f, "%-16s    MLD leaves: RX: %llu TX: %llu\n",
-				"",
-				mstats->mld_leaves[BR_MCAST_DIR_RX],
-				mstats->mld_leaves[BR_MCAST_DIR_TX]);
+			open_json_object("mld_leaves");
+			print_string(PRINT_FP, NULL,
+				     "%-16s    MLD leaves: ", "");
+			print_u64(PRINT_ANY, "rx", "RX: %llu ",
+				  mstats->mld_leaves[BR_MCAST_DIR_RX]);
+			print_u64(PRINT_ANY, "tx", "TX: %llu\n",
+				  mstats->mld_leaves[BR_MCAST_DIR_TX]);
+			close_json_object();
 
-			fprintf(f, "%-16s    MLD parse errors: %llu\n",
-				"", mstats->mld_parse_errors);
+			print_string(PRINT_FP, NULL,
+				     "%-16s    MLD parse errors: ", "");
+			print_u64(PRINT_ANY, "mld_parse_errors", "%llu\n",
+				  mstats->mld_parse_errors);
+			close_json_object();
 			break;
 		}
 	}
+	close_json_object();
 }
 
 int bridge_print_xstats(struct nlmsghdr *n, void *arg)
@@ -762,7 +802,6 @@ int bridge_print_xstats(struct nlmsghdr *n, void *arg)
 	struct if_stats_msg *ifsm = NLMSG_DATA(n);
 	struct rtattr *tb[IFLA_STATS_MAX+1];
 	int len = n->nlmsg_len;
-	FILE *fp = arg;
 
 	len -= NLMSG_LENGTH(sizeof(*ifsm));
 	if (len < 0) {
@@ -774,11 +813,11 @@ int bridge_print_xstats(struct nlmsghdr *n, void *arg)
 
 	parse_rtattr(tb, IFLA_STATS_MAX, IFLA_STATS_RTA(ifsm), len);
 	if (tb[IFLA_STATS_LINK_XSTATS])
-		bridge_print_stats_attr(fp, tb[IFLA_STATS_LINK_XSTATS],
+		bridge_print_stats_attr(tb[IFLA_STATS_LINK_XSTATS],
 					ifsm->ifindex);
 
 	if (tb[IFLA_STATS_LINK_XSTATS_SLAVE])
-		bridge_print_stats_attr(fp, tb[IFLA_STATS_LINK_XSTATS_SLAVE],
+		bridge_print_stats_attr(tb[IFLA_STATS_LINK_XSTATS_SLAVE],
 					ifsm->ifindex);
 
 	return 0;

From 440c5075d66291335d4e074f142453625a2f8c1f Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 12 Mar 2019 18:41:28 +0200
Subject: [PATCH 55/55] ip: bond: add xstats support

Add bond and bond_slave xstats support with optional json output.
Example:
- Plain text:
$ ip link xstats type bond 802.3ad
 bond0
                    LACPDU Rx 2017
                    LACPDU Tx 2038
                    LACPDU Unknown type Rx 0
                    LACPDU Illegal Rx 0
                    Marker Rx 0
                    Marker Tx 0
                    Marker response Rx 0
                    Marker response Tx 0
                    Marker unknown type Rx 0

- JSON:
$ ip -j -p link xstats type bond 802.3ad
  [ {
        "ifname": "bond0",
        "802.3ad": {
            "lacpdu_rx": 219,
            "lacpdu_tx": 241,
            "lacpdu_unknown_rx": 0,
            "lacpdu_illegal_rx": 0,
            "marker_rx": 0,
            "marker_tx": 0,
            "marker_response_rx": 0,
            "marker_response_tx": 0,
            "marker_unknown_rx": 0
        }
    } ]

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
 ip/ip_common.h         |   3 +
 ip/iplink_bond.c       | 167 ++++++++++++++++++++++++++++++++++++++++-
 ip/iplink_bond_slave.c |   2 +
 3 files changed, 169 insertions(+), 3 deletions(-)

diff --git a/ip/ip_common.h b/ip/ip_common.h
index d67575c6..b4aa34a7 100644
--- a/ip/ip_common.h
+++ b/ip/ip_common.h
@@ -130,6 +130,9 @@ void br_dump_bridge_id(const struct ifla_bridge_id *id, char *buf, size_t len);
 int bridge_parse_xstats(struct link_util *lu, int argc, char **argv);
 int bridge_print_xstats(struct nlmsghdr *n, void *arg);
 
+int bond_parse_xstats(struct link_util *lu, int argc, char **argv);
+int bond_print_xstats(struct nlmsghdr *n, void *arg);
+
 /* iproute_lwtunnel.c */
 int lwt_parse_encap(struct rtattr *rta, size_t len, int *argcp, char ***argvp);
 void lwt_print_encap(FILE *fp, struct rtattr *encap_type, struct rtattr *encap);
diff --git a/ip/iplink_bond.c b/ip/iplink_bond.c
index f906e7f1..c60f0e8a 100644
--- a/ip/iplink_bond.c
+++ b/ip/iplink_bond.c
@@ -13,16 +13,18 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <linux/if_link.h>
-#include <linux/if_ether.h>
-#include <net/if.h>
+#include <linux/if_bonding.h>
 
 #include "rt_names.h"
 #include "utils.h"
 #include "ip_common.h"
+#include "json_print.h"
 
 #define BOND_MAX_ARP_TARGETS    16
 
+static unsigned int xstats_print_attr;
+static int filter_index;
+
 static const char *mode_tbl[] = {
 	"balance-rr",
 	"active-backup",
@@ -649,10 +651,169 @@ static void bond_print_help(struct link_util *lu, int argc, char **argv,
 	print_explain(f);
 }
 
+static void bond_print_xstats_help(struct link_util *lu, FILE *f)
+{
+	fprintf(f, "Usage: ... %s [ 802.3ad ] [ dev DEVICE ]\n", lu->id);
+}
+
+static void bond_print_3ad_stats(struct rtattr *lacpattr)
+{
+	struct rtattr *lacptb[BOND_3AD_STAT_MAX+1];
+	__u64 val;
+
+	parse_rtattr(lacptb, BOND_3AD_STAT_MAX, RTA_DATA(lacpattr),
+		     RTA_PAYLOAD(lacpattr));
+	open_json_object("802.3ad");
+	if (lacptb[BOND_3AD_STAT_LACPDU_RX]) {
+		print_string(PRINT_FP, NULL, "%-16s    ", "");
+		print_u64(PRINT_ANY, "lacpdu_rx", "LACPDU Rx %llu\n",
+			  rta_getattr_u64(lacptb[BOND_3AD_STAT_LACPDU_RX]));
+	}
+	if (lacptb[BOND_3AD_STAT_LACPDU_TX]) {
+		print_string(PRINT_FP, NULL, "%-16s    ", "");
+		print_u64(PRINT_ANY, "lacpdu_tx", "LACPDU Tx %llu\n",
+			  rta_getattr_u64(lacptb[BOND_3AD_STAT_LACPDU_TX]));
+	}
+	if (lacptb[BOND_3AD_STAT_LACPDU_UNKNOWN_RX]) {
+		print_string(PRINT_FP, NULL, "%-16s    ", "");
+		val = rta_getattr_u64(lacptb[BOND_3AD_STAT_LACPDU_UNKNOWN_RX]);
+		print_u64(PRINT_ANY,
+			  "lacpdu_unknown_rx",
+			  "LACPDU Unknown type Rx %llu\n",
+			  val);
+	}
+	if (lacptb[BOND_3AD_STAT_LACPDU_ILLEGAL_RX]) {
+		print_string(PRINT_FP, NULL, "%-16s    ", "");
+		val = rta_getattr_u64(lacptb[BOND_3AD_STAT_LACPDU_ILLEGAL_RX]);
+		print_u64(PRINT_ANY,
+			  "lacpdu_illegal_rx",
+			  "LACPDU Illegal Rx %llu\n",
+			  val);
+	}
+	if (lacptb[BOND_3AD_STAT_MARKER_RX]) {
+		print_string(PRINT_FP, NULL, "%-16s    ", "");
+		print_u64(PRINT_ANY, "marker_rx", "Marker Rx %llu\n",
+			  rta_getattr_u64(lacptb[BOND_3AD_STAT_MARKER_RX]));
+	}
+	if (lacptb[BOND_3AD_STAT_MARKER_TX]) {
+		print_string(PRINT_FP, NULL, "%-16s    ", "");
+		print_u64(PRINT_ANY, "marker_tx", "Marker Tx %llu\n",
+			  rta_getattr_u64(lacptb[BOND_3AD_STAT_MARKER_TX]));
+	}
+	if (lacptb[BOND_3AD_STAT_MARKER_RESP_RX]) {
+		print_string(PRINT_FP, NULL, "%-16s    ", "");
+		val = rta_getattr_u64(lacptb[BOND_3AD_STAT_MARKER_RESP_RX]);
+		print_u64(PRINT_ANY,
+			  "marker_response_rx",
+			  "Marker response Rx %llu\n",
+			  val);
+	}
+	if (lacptb[BOND_3AD_STAT_MARKER_RESP_TX]) {
+		print_string(PRINT_FP, NULL, "%-16s    ", "");
+		val = rta_getattr_u64(lacptb[BOND_3AD_STAT_MARKER_RESP_TX]);
+		print_u64(PRINT_ANY,
+			  "marker_response_tx",
+			  "Marker response Tx %llu\n",
+			  val);
+	}
+	if (lacptb[BOND_3AD_STAT_MARKER_UNKNOWN_RX]) {
+		print_string(PRINT_FP, NULL, "%-16s    ", "");
+		val = rta_getattr_u64(lacptb[BOND_3AD_STAT_MARKER_UNKNOWN_RX]);
+		print_u64(PRINT_ANY,
+			  "marker_unknown_rx",
+			  "Marker unknown type Rx %llu\n",
+			  val);
+	}
+	close_json_object();
+}
+
+static void bond_print_stats_attr(struct rtattr *attr, int ifindex)
+{
+	struct rtattr *bondtb[LINK_XSTATS_TYPE_MAX+1];
+	struct rtattr *i, *list;
+	const char *ifname = "";
+	int rem;
+
+	parse_rtattr(bondtb, LINK_XSTATS_TYPE_MAX+1, RTA_DATA(attr),
+	RTA_PAYLOAD(attr));
+	if (!bondtb[LINK_XSTATS_TYPE_BOND])
+		return;
+
+	list = bondtb[LINK_XSTATS_TYPE_BOND];
+	rem = RTA_PAYLOAD(list);
+	open_json_object(NULL);
+	ifname = ll_index_to_name(ifindex);
+	print_string(PRINT_ANY, "ifname", "%-16s\n", ifname);
+	for (i = RTA_DATA(list); RTA_OK(i, rem); i = RTA_NEXT(i, rem)) {
+		if (xstats_print_attr && i->rta_type != xstats_print_attr)
+			continue;
+
+		switch (i->rta_type) {
+		case BOND_XSTATS_3AD:
+			bond_print_3ad_stats(i);
+			break;
+		}
+		break;
+	}
+	close_json_object();
+}
+
+int bond_print_xstats(struct nlmsghdr *n, void *arg)
+{
+	struct if_stats_msg *ifsm = NLMSG_DATA(n);
+	struct rtattr *tb[IFLA_STATS_MAX+1];
+	int len = n->nlmsg_len;
+
+	len -= NLMSG_LENGTH(sizeof(*ifsm));
+	if (len < 0) {
+		fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+		return -1;
+	}
+	if (filter_index && filter_index != ifsm->ifindex)
+		return 0;
+
+	parse_rtattr(tb, IFLA_STATS_MAX, IFLA_STATS_RTA(ifsm), len);
+	if (tb[IFLA_STATS_LINK_XSTATS])
+		bond_print_stats_attr(tb[IFLA_STATS_LINK_XSTATS],
+				      ifsm->ifindex);
+
+	if (tb[IFLA_STATS_LINK_XSTATS_SLAVE])
+		bond_print_stats_attr(tb[IFLA_STATS_LINK_XSTATS_SLAVE],
+				      ifsm->ifindex);
+
+	return 0;
+}
+
+int bond_parse_xstats(struct link_util *lu, int argc, char **argv)
+{
+	while (argc > 0) {
+		if (strcmp(*argv, "lacp") == 0 ||
+		    strcmp(*argv, "802.3ad") == 0) {
+			xstats_print_attr = BOND_XSTATS_3AD;
+		} else if (strcmp(*argv, "dev") == 0) {
+			NEXT_ARG();
+			filter_index = ll_name_to_index(*argv);
+			if (!filter_index)
+				return nodev(*argv);
+		} else if (strcmp(*argv, "help") == 0) {
+			bond_print_xstats_help(lu, stdout);
+			exit(0);
+		} else {
+			invarg("unknown attribute", *argv);
+		}
+		argc--; argv++;
+	}
+
+	return 0;
+}
+
+
 struct link_util bond_link_util = {
 	.id		= "bond",
 	.maxattr	= IFLA_BOND_MAX,
 	.parse_opt	= bond_parse_opt,
 	.print_opt	= bond_print_opt,
 	.print_help	= bond_print_help,
+	.parse_ifla_xstats = bond_parse_xstats,
+	.print_ifla_xstats = bond_print_xstats,
 };
diff --git a/ip/iplink_bond_slave.c b/ip/iplink_bond_slave.c
index 67219c67..4eaf72b8 100644
--- a/ip/iplink_bond_slave.c
+++ b/ip/iplink_bond_slave.c
@@ -156,4 +156,6 @@ struct link_util bond_slave_link_util = {
 	.print_opt	= bond_slave_print_opt,
 	.parse_opt	= bond_slave_parse_opt,
 	.print_help	= bond_slave_print_help,
+	.parse_ifla_xstats = bond_parse_xstats,
+	.print_ifla_xstats = bond_print_xstats,
 };