Skip to contentSkip to conversation

5.15.132-rc1 review

PATCH In review Greg Kroah-Hartman 11 participants 524 messages Sep 17, 2023 – Sep 29, 2023 Page 4 of 4

Subsystems (13)
lore
Share & tools
lore
author maintainer
#422 lore raw

PATCH 421/511 perf vendor events: Update the JSON/events descriptions for power10 platform

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kajol Jain <[email protected]>

[ Upstream commit 3286f88f31da060ac2789cee247153961ba57e49 ]

Update the description for some of the JSON/events for power10 platform.

Fixes 32daa5d7899e0343 ("perf vendor events: Initial JSON/events list for power10 platform")
Cc Athira Rajeev <[email protected]>
Cc Disha Goel <[email protected]>
Cc Ian Rogers <[email protected]>
Cc Kajol Jain <[email protected]>
Cc Madhavan Srinivasan <[email protected]>
Cc Namhyung Kim <[email protected]>
---
 .../arch/powerpc/power10/cache.json           |  4 +-
 .../arch/powerpc/power10/frontend.json        | 30 ++++++------
 .../arch/powerpc/power10/marked.json          | 20 ++++----
 .../arch/powerpc/power10/memory.json          |  6 +--
 .../arch/powerpc/power10/others.json          | 48 +++++++++----------
 .../arch/powerpc/power10/pipeline.json        | 20 ++++----
 .../pmu-events/arch/powerpc/power10/pmc.json  |  4 +-
 .../arch/powerpc/power10/translation.json     |  6 +--
 8 files changed, 69 insertions(+), 69 deletions(-)
tools/perf/pmu-events/arch/powerpc/power10/cache.json +2 -2
index 605be14f441c8..9cb929bb64afd 100644
@@ -17,7 +17,7 @@
   {
     "EventCode": "0x34056",
     "EventName": "PM_EXEC_STALL_LOAD_FINISH",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the next-to-finish (NTF) instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction."
   },
   {
     "EventCode": "0x3006C",
@@ -27,7 +27,7 @@
   {
     "EventCode": "0x300F4",
     "EventName": "PM_RUN_INST_CMPL_CONC",
-    "BriefDescription": "PowerPC instructions completed by this thread when all threads in the core had the run-latch set."
+    "BriefDescription": "PowerPC instruction completed by this thread when all threads in the core had the run-latch set."
   },
   {
     "EventCode": "0x4C016",
tools/perf/pmu-events/arch/powerpc/power10/frontend.json +15 -15
index 558f9530f54ec..61e9e0222c873 100644
@@ -7,7 +7,7 @@
   {
     "EventCode": "0x10006",
     "EventName": "PM_DISP_STALL_HELD_OTHER_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any other reason."
   },
   {
     "EventCode": "0x10010",
@@ -32,12 +32,12 @@
   {
     "EventCode": "0x1D05E",
     "EventName": "PM_DISP_STALL_HELD_HALT_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of power management."
   },
   {
     "EventCode": "0x1E050",
     "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR."
   },
   {
     "EventCode": "0x1F054",
@@ -67,7 +67,7 @@
   {
     "EventCode": "0x100F6",
     "EventName": "PM_IERAT_MISS",
-    "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event."
+    "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event. This event only counts instruction demand access."
   },
   {
     "EventCode": "0x100F8",
@@ -77,7 +77,7 @@
   {
     "EventCode": "0x20006",
     "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue."
   },
   {
     "EventCode": "0x20114",
@@ -102,7 +102,7 @@
   {
     "EventCode": "0x2D01A",
     "EventName": "PM_DISP_STALL_IC_MISS",
-    "BriefDescription": "Cycles when dispatch was stalled for this thread due to an Icache Miss."
+    "BriefDescription": "Cycles when dispatch was stalled for this thread due to an instruction cache miss."
   },
   {
     "EventCode": "0x2E018",
@@ -112,7 +112,7 @@
   {
     "EventCode": "0x2E01A",
     "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the XVFC mapper/SRB was full."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the XVFC mapper/SRB was full."
   },
   {
     "EventCode": "0x2C142",
@@ -137,7 +137,7 @@
   {
     "EventCode": "0x30004",
     "EventName": "PM_DISP_STALL_FLUSH",
-    "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC."
+    "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet next-to-complete (NTC). PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC."
   },
   {
     "EventCode": "0x3000A",
@@ -157,7 +157,7 @@
   {
     "EventCode": "0x30018",
     "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together."
   },
   {
     "EventCode": "0x30026",
@@ -182,7 +182,7 @@
   {
     "EventCode": "0x3D05C",
     "EventName": "PM_DISP_STALL_HELD_RENAME_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC."
   },
   {
     "EventCode": "0x3E052",
@@ -192,7 +192,7 @@
   {
     "EventCode": "0x3E054",
     "EventName": "PM_LD_MISS_L1",
-    "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
+    "BriefDescription": "Load missed L1, counted at finish time. LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
   },
   {
     "EventCode": "0x301EA",
@@ -202,7 +202,7 @@
   {
     "EventCode": "0x300FA",
     "EventName": "PM_INST_FROM_L3MISS",
-    "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss."
+    "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss."
   },
   {
     "EventCode": "0x40006",
@@ -232,16 +232,16 @@
   {
     "EventCode": "0x4E01A",
     "EventName": "PM_DISP_STALL_HELD_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any reason."
   },
   {
     "EventCode": "0x4003C",
     "EventName": "PM_DISP_STALL_HELD_SYNC_CYC",
-    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch."
+    "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch."
   },
   {
     "EventCode": "0x44056",
     "EventName": "PM_VECTOR_ST_CMPL",
-    "BriefDescription": "Vector store instructions completed."
+    "BriefDescription": "Vector store instruction completed."
   }
 ]
tools/perf/pmu-events/arch/powerpc/power10/marked.json +10 -10
index 58b5dfe3a2731..131f8d0e88317 100644
@@ -62,7 +62,7 @@
   {
     "EventCode": "0x200FD",
     "EventName": "PM_L1_ICACHE_MISS",
-    "BriefDescription": "Demand iCache Miss."
+    "BriefDescription": "Demand instruction cache miss."
   },
   {
     "EventCode": "0x30130",
@@ -72,7 +72,7 @@
   {
     "EventCode": "0x34146",
     "EventName": "PM_MRK_LD_CMPL",
-    "BriefDescription": "Marked loads completed."
+    "BriefDescription": "Marked load instruction completed."
   },
   {
     "EventCode": "0x3E158",
@@ -82,12 +82,12 @@
   {
     "EventCode": "0x3E15A",
     "EventName": "PM_MRK_ST_FIN",
-    "BriefDescription": "The marked instruction was a store of any kind."
+    "BriefDescription": "Marked store instruction finished."
   },
   {
     "EventCode": "0x30068",
     "EventName": "PM_L1_ICACHE_RELOADED_PREF",
-    "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)."
+    "BriefDescription": "Counts all instruction cache prefetch reloads (includes demand turned into prefetch)."
   },
   {
     "EventCode": "0x301E4",
@@ -102,12 +102,12 @@
   {
     "EventCode": "0x300FE",
     "EventName": "PM_DATA_FROM_L3MISS",
-    "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss."
+    "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss."
   },
   {
     "EventCode": "0x40012",
     "EventName": "PM_L1_ICACHE_RELOADED_ALL",
-    "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch."
+    "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch."
   },
   {
     "EventCode": "0x40134",
@@ -117,22 +117,22 @@
   {
     "EventCode": "0x4505A",
     "EventName": "PM_SP_FLOP_CMPL",
-    "BriefDescription": "Single Precision floating point instructions completed."
+    "BriefDescription": "Single Precision floating point instruction completed."
   },
   {
     "EventCode": "0x4D058",
     "EventName": "PM_VECTOR_FLOP_CMPL",
-    "BriefDescription": "Vector floating point instructions completed."
+    "BriefDescription": "Vector floating point instruction completed."
   },
   {
     "EventCode": "0x4D05A",
     "EventName": "PM_NON_MATH_FLOP_CMPL",
-    "BriefDescription": "Non Math instructions completed."
+    "BriefDescription": "Non Math instruction completed."
   },
   {
     "EventCode": "0x401E0",
     "EventName": "PM_MRK_INST_CMPL",
-    "BriefDescription": "marked instruction completed."
+    "BriefDescription": "Marked instruction completed."
   },
   {
     "EventCode": "0x400FE",
tools/perf/pmu-events/arch/powerpc/power10/memory.json +3 -3
index 843b51f531e95..c4c10ca98cad7 100644
@@ -47,7 +47,7 @@
   {
     "EventCode": "0x10062",
     "EventName": "PM_LD_L3MISS_PEND_CYC",
-    "BriefDescription": "Cycles L3 miss was pending for this thread."
+    "BriefDescription": "Cycles in which an L3 miss was pending for this thread."
   },
   {
     "EventCode": "0x20010",
@@ -132,7 +132,7 @@
   {
     "EventCode": "0x300FC",
     "EventName": "PM_DTLB_MISS",
-    "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. It includes pages of all sizes for demand and prefetch activity."
+    "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. This event only counts for demand misses."
   },
   {
     "EventCode": "0x4D02C",
@@ -142,7 +142,7 @@
   {
     "EventCode": "0x4003E",
     "EventName": "PM_LD_CMPL",
-    "BriefDescription": "Loads completed."
+    "BriefDescription": "Load instruction completed."
   },
   {
     "EventCode": "0x4C040",
tools/perf/pmu-events/arch/powerpc/power10/others.json +24 -24

165 lines not on this page · raw message

tools/perf/pmu-events/arch/powerpc/power10/pipeline.json +10 -10
index b8aded6045faa..449f57e8ba6af 100644
@@ -2,7 +2,7 @@
   {
     "EventCode": "0x100FE",
     "EventName": "PM_INST_CMPL",
-    "BriefDescription": "PowerPC instructions completed."
+    "BriefDescription": "PowerPC instruction completed."
   },
   {
     "EventCode": "0x1000C",
@@ -12,7 +12,7 @@
   {
     "EventCode": "0x1000E",
     "EventName": "PM_MMA_ISSUED",
-    "BriefDescription": "MMA instructions issued."
+    "BriefDescription": "MMA instruction issued."
   },
   {
     "EventCode": "0x10012",
@@ -107,7 +107,7 @@
   {
     "EventCode": "0x2D012",
     "EventName": "PM_VSU1_ISSUE",
-    "BriefDescription": "VSU instructions issued to VSU pipe 1."
+    "BriefDescription": "VSU instruction issued to VSU pipe 1."
   },
   {
     "EventCode": "0x2D018",
@@ -122,7 +122,7 @@
   {
     "EventCode": "0x2E01E",
     "EventName": "PM_EXEC_STALL_NTC_FLUSH",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous NTF instruction is still completing and the new NTF instruction is stalled at dispatch."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous next-to-finish (NTF) instruction is still completing and the new NTF instruction is stalled at dispatch."
   },
   {
     "EventCode": "0x2013C",
@@ -137,7 +137,7 @@
   {
     "EventCode": "0x201E2",
     "EventName": "PM_MRK_LD_MISS_L1",
-    "BriefDescription": "Marked DL1 Demand Miss counted at finish time."
+    "BriefDescription": "Marked demand data load miss counted at finish time."
   },
   {
     "EventCode": "0x200F4",
@@ -172,7 +172,7 @@
   {
     "EventCode": "0x30028",
     "EventName": "PM_CMPL_STALL_MEM_ECC",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a STCX waiting for its result or a load waiting for non-critical sectors of data and ECC."
   },
   {
     "EventCode": "0x30036",
@@ -187,12 +187,12 @@
   {
     "EventCode": "0x3F044",
     "EventName": "PM_VSU2_ISSUE",
-    "BriefDescription": "VSU instructions issued to VSU pipe 2."
+    "BriefDescription": "VSU instruction issued to VSU pipe 2."
   },
   {
     "EventCode": "0x30058",
     "EventName": "PM_TLBIE_FIN",
-    "BriefDescription": "TLBIE instructions finished in the LSU. Two TLBIEs can finish each cycle. All will be counted."
+    "BriefDescription": "TLBIE instruction finished in the LSU. Two TLBIEs can finish each cycle. All will be counted."
   },
   {
     "EventCode": "0x3D058",
@@ -252,7 +252,7 @@
   {
     "EventCode": "0x4E012",
     "EventName": "PM_EXEC_STALL_UNKNOWN",
-    "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the NTF finishes and completions came too close together."
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the next-to-finish (NTF) instruction finishes and completions came too close together."
   },
   {
     "EventCode": "0x4D020",
@@ -267,7 +267,7 @@
   {
     "EventCode": "0x45058",
     "EventName": "PM_IC_MISS_CMPL",
-    "BriefDescription": "Non-speculative icache miss, counted at completion."
+    "BriefDescription": "Non-speculative instruction cache miss, counted at completion."
   },
   {
     "EventCode": "0x4D050",
tools/perf/pmu-events/arch/powerpc/power10/pmc.json +2 -2
index b5d1bd39cfb22..364fedbfb490b 100644
@@ -12,11 +12,11 @@
   {
     "EventCode": "0x45052",
     "EventName": "PM_4FLOP_CMPL",
-    "BriefDescription": "Four floating point instructions completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
+    "BriefDescription": "Four floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
   },
   {
     "EventCode": "0x4D054",
     "EventName": "PM_8FLOP_CMPL",
-    "BriefDescription": "Four Double Precision vector instructions completed."
+    "BriefDescription": "Four Double Precision vector instruction completed."
   }
 ]
tools/perf/pmu-events/arch/powerpc/power10/translation.json +3 -3
index db3766dca07c5..3e47b804a0a8f 100644
@@ -17,7 +17,7 @@
   {
     "EventCode": "0x2011C",
     "EventName": "PM_MRK_NTF_CYC",
-    "BriefDescription": "Cycles during which the marked instruction is the oldest in the pipeline (NTF or NTC)."
+    "BriefDescription": "Cycles in which the marked instruction is the oldest in the pipeline (next-to-finish or next-to-complete)."
   },
   {
     "EventCode": "0x2E01C",
@@ -37,7 +37,7 @@
   {
     "EventCode": "0x200FE",
     "EventName": "PM_DATA_FROM_L2MISS",
-    "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss."
+    "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss."
   },
   {
     "EventCode": "0x30010",
@@ -52,6 +52,6 @@
   {
     "EventCode": "0x4D05C",
     "EventName": "PM_DPP_FLOP_CMPL",
-    "BriefDescription": "Double-Precision or Quad-Precision instructions completed."
+    "BriefDescription": "Double-Precision or Quad-Precision instruction completed."
   }
 ]
Signature · 1 line
2.40.1
author maintainer
#423 lore raw

PATCH 422/511 perf vendor events: Drop some of the JSON/events for power10 platform

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kajol Jain <[email protected]>

[ Upstream commit e104df97b8dcfbab2e42de634b99bf03f0805d85 ]

Drop some of the JSON/events for power10 platform due to counter data mismatch.

Fixes 32daa5d7899e0343 ("perf vendor events: Initial JSON/events list for power10 platform")
Cc Athira Rajeev <[email protected]>
Cc Disha Goel <[email protected]>
Cc Ian Rogers <[email protected]>
Cc Kajol Jain <[email protected]>
Cc Madhavan Srinivasan <[email protected]>
Cc Namhyung Kim <[email protected]>
---
 .../arch/powerpc/power10/floating_point.json           |  7 -------
 tools/perf/pmu-events/arch/powerpc/power10/marked.json | 10 ----------
 tools/perf/pmu-events/arch/powerpc/power10/others.json |  5 -----
 .../perf/pmu-events/arch/powerpc/power10/pipeline.json | 10 ----------
 .../pmu-events/arch/powerpc/power10/translation.json   |  5 -----
 5 files changed, 37 deletions(-)
 delete mode 100644 tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
tools/perf/pmu-events/arch/powerpc/power10/floating_point.json deleted +0 -7
deleted file mode 100644
index 54acb55e2c8c6..0000000000000
@@ -1,7 +0,0 @@
-[
-  {
-    "EventCode": "0x4016E",
-    "EventName": "PM_THRESH_NOT_MET",
-    "BriefDescription": "Threshold counter did not meet threshold."
-  }
-]
tools/perf/pmu-events/arch/powerpc/power10/marked.json +0 -10
index 131f8d0e88317..f2436fc5537ce 100644
@@ -19,11 +19,6 @@
     "EventName": "PM_MRK_BR_TAKEN_CMPL",
     "BriefDescription": "Marked Branch Taken instruction completed."
   },
-  {
-    "EventCode": "0x20112",
-    "EventName": "PM_MRK_NTF_FIN",
-    "BriefDescription": "The marked instruction became the oldest in the pipeline before it finished. It excludes instructions that finish at dispatch."
-  },
   {
     "EventCode": "0x2C01C",
     "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP",
@@ -64,11 +59,6 @@
     "EventName": "PM_L1_ICACHE_MISS",
     "BriefDescription": "Demand instruction cache miss."
   },
-  {
-    "EventCode": "0x30130",
-    "EventName": "PM_MRK_INST_FIN",
-    "BriefDescription": "marked instruction finished. Excludes instructions that finish at dispatch. Note that stores always finish twice since the address gets issued to the LSU and the data gets issued to the VSU."
-  },
   {
     "EventCode": "0x34146",
     "EventName": "PM_MRK_LD_CMPL",
tools/perf/pmu-events/arch/powerpc/power10/others.json +0 -5
index e691041ee8678..36c5bbc64c3be 100644
@@ -29,11 +29,6 @@
     "EventName": "PM_DISP_SS0_2_INSTR_CYC",
     "BriefDescription": "Cycles in which Superslice 0 dispatches either 1 or 2 instructions."
   },
-  {
-    "EventCode": "0x1F15C",
-    "EventName": "PM_MRK_STCX_L2_CYC",
-    "BriefDescription": "Cycles spent in the nest portion of a marked Stcx instruction. It starts counting when the operation starts to drain to the L2 and it stops counting when the instruction retires from the Instruction Completion Table (ICT) in the Instruction Sequencing Unit (ISU)."
-  },
   {
     "EventCode": "0x10066",
     "EventName": "PM_ADJUNCT_CYC",
tools/perf/pmu-events/arch/powerpc/power10/pipeline.json +0 -10
index 449f57e8ba6af..799893c56f32b 100644
@@ -194,11 +194,6 @@
     "EventName": "PM_TLBIE_FIN",
     "BriefDescription": "TLBIE instruction finished in the LSU. Two TLBIEs can finish each cycle. All will be counted."
   },
-  {
-    "EventCode": "0x3D058",
-    "EventName": "PM_SCALAR_FSQRT_FDIV_ISSUE",
-    "BriefDescription": "Scalar versions of four floating point operations: fdiv,fsqrt (xvdivdp, xvdivsp, xvsqrtdp, xvsqrtsp)."
-  },
   {
     "EventCode": "0x30066",
     "EventName": "PM_LSU_FIN",
@@ -269,11 +264,6 @@
     "EventName": "PM_IC_MISS_CMPL",
     "BriefDescription": "Non-speculative instruction cache miss, counted at completion."
   },
-  {
-    "EventCode": "0x4D050",
-    "EventName": "PM_VSU_NON_FLOP_CMPL",
-    "BriefDescription": "Non-floating point VSU instructions completed."
-  },
   {
     "EventCode": "0x4D052",
     "EventName": "PM_2FLOP_CMPL",
tools/perf/pmu-events/arch/powerpc/power10/translation.json +0 -5
index 3e47b804a0a8f..961e2491e73f6 100644
@@ -4,11 +4,6 @@
     "EventName": "PM_MRK_START_PROBE_NOP_CMPL",
     "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed."
   },
-  {
-    "EventCode": "0x20016",
-    "EventName": "PM_ST_FIN",
-    "BriefDescription": "Store finish count. Includes speculative activity."
-  },
   {
     "EventCode": "0x20018",
     "EventName": "PM_ST_FWD",
Signature · 1 line
2.40.1
author maintainer
#424 lore raw

PATCH 423/511 perf top: Dont pass an ERR_PTR() directly to perf_session__delete()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnaldo Carvalho de Melo <[email protected]>

[ Upstream commit ef23cb593304bde0cc046fd4cc83ae7ea2e24f16 ]

While debugging a segfault on 'perf lock contention' without an available perf.data file I noticed that it was basically calling:

	perf_session__delete(ERR_PTR(-1))

Resulting in:

(gdb) run lock contention
Starting program: /root/bin/perf lock contention
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib64/libthread_db.so.1". failed to open perf.data: No such file or directory (try 'perf record' first) Initializing perf session failed

Program received signal SIGSEGV, Segmentation fault.
0x00000000005e7515 in auxtrace__free (session=0xffffffffffffffff) at util/auxtrace.c:2858
2858 if (!session->auxtrace)
(gdb) p session
$1 = (struct perf_session *) 0xffffffffffffffff
(gdb) bt

  #0  0x00000000005e7515 in auxtrace__free (session=0xffffffffffffffff) at util/auxtrace.c:2858
  #1  0x000000000057bb4d in perf_session__delete (session=0xffffffffffffffff) at util/session.c:300
  #2  0x000000000047c421 in __cmd_contention (argc=0, argv=0x7fffffffe200) at builtin-lock.c:2161
  #3  0x000000000047dc95 in cmd_lock (argc=0, argv=0x7fffffffe200) at builtin-lock.c:2604
  #4  0x0000000000501466 in run_builtin (p=0xe597a8 <commands+552>, argc=2, argv=0x7fffffffe200) at perf.c:322
  #5  0x00000000005016d5 in handle_internal_command (argc=2, argv=0x7fffffffe200) at perf.c:375
  #6  0x0000000000501824 in run_argv (argcp=0x7fffffffe02c, argv=0x7fffffffe020) at perf.c:419
  #7  0x0000000000501b11 in main (argc=2, argv=0x7fffffffe200) at perf.c:535

(gdb)

So just set it to NULL after using PTR_ERR(session) to decode the error as perf_session__delete(NULL) is supported.

The same problem was found in 'perf top' after an audit of all perf_session__new() failure handling.

Fixes 6ef81c55a2b6584c ("perf session: Return error code for perf_session__new() function on failure")
Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Alexey Budankov <[email protected]>
Cc Greg Kroah-Hartman <[email protected]>
Cc Jeremie Galarneau <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Kate Stewart <[email protected]>
Cc Mamatha Inamdar <[email protected]>
Cc Mukesh Ojha <[email protected]>
Cc Nageswara R Sastry <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Ravi Bangoria <[email protected]>
Cc Shawn Landden <[email protected]>
Cc Song Liu <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Tzvetomir Stoyanov <[email protected]>
---
 tools/perf/builtin-top.c | 1 +
 1 file changed, 1 insertion(+)
tools/perf/builtin-top.c +1 -0
index a3ae9176a83e2..6fdd401ec9c56 100644
@@ -1743,6 +1743,7 @@ int cmd_top(int argc, const char **argv)
 	top.session = perf_session__new(NULL, NULL);
 	if (IS_ERR(top.session)) {
 		status = PTR_ERR(top.session);
+		top.session = NULL;
 		goto out_delete_evlist;
 	}
 
Signature · 1 line
2.40.1
author maintainer
#425 lore raw

PATCH 424/511 watchdog: intel-mid_wdt: add MODULE_ALIAS() to allow auto-load

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Raag Jadav <[email protected]>

[ Upstream commit cf38e7691c85f1b09973b22a0b89bf1e1228d2f9 ]

When built with CONFIG_INTEL_MID_WATCHDOG=m, currently the driver needs to be loaded manually, for the lack of module alias. This causes unintended resets in cases where watchdog timer is set-up by bootloader and the driver is not explicitly loaded. Add MODULE_ALIAS() to load the driver automatically at boot and avoid this issue.

---
 drivers/watchdog/intel-mid_wdt.c | 1 +
 1 file changed, 1 insertion(+)
drivers/watchdog/intel-mid_wdt.c +1 -0
index 9b2173f765c8c..fb7fae750181b 100644
@@ -203,3 +203,4 @@ module_platform_driver(mid_wdt_driver);
 MODULE_AUTHOR("David Cohen <[email protected]>");
 MODULE_DESCRIPTION("Watchdog Driver for Intel MID platform");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:intel_mid_wdt");
Signature · 1 line
2.40.1
author maintainer
#426 lore raw

PATCH 425/511 pwm: lpc32xx: Remove handling of PWM channels

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vladimir Zapolskiy <[email protected]>

[ Upstream commit 4aae44f65827f0213a7361cf9c32cfe06114473f ]

Because LPC32xx PWM controllers have only a single output which is registered as the only PWM device/channel per controller, it is known in advance that pwm->hwpwm value is always 0. On basis of this fact simplify the code by removing operations with pwm->hwpwm, there is no controls which require channel number as input.

Even though I wasn't aware at the time when I forward ported that patch, this fixes a null pointer dereference as lpc32xx->chip.pwms is NULL before devm_pwmchip_add() is called.

Fixes 3d2813fb17e5 ("pwm: lpc32xx: Don't modify HW state in .probe() after the PWM chip was registered")
---
 drivers/pwm/pwm-lpc32xx.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)
drivers/pwm/pwm-lpc32xx.c +8 -8
index ddeab5687cb81..45b613dbc1c7b 100644
@@ -51,10 +51,10 @@ static int lpc32xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	if (duty_cycles > 255)
 		duty_cycles = 255;
 
-	val = readl(lpc32xx->base + (pwm->hwpwm << 2));
+	val = readl(lpc32xx->base);
 	val &= ~0xFFFF;
 	val |= (period_cycles << 8) | duty_cycles;
-	writel(val, lpc32xx->base + (pwm->hwpwm << 2));
+	writel(val, lpc32xx->base);
 
 	return 0;
 }
@@ -69,9 +69,9 @@ static int lpc32xx_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 	if (ret)
 		return ret;
 
-	val = readl(lpc32xx->base + (pwm->hwpwm << 2));
+	val = readl(lpc32xx->base);
 	val |= PWM_ENABLE;
-	writel(val, lpc32xx->base + (pwm->hwpwm << 2));
+	writel(val, lpc32xx->base);
 
 	return 0;
 }
@@ -81,9 +81,9 @@ static void lpc32xx_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 	struct lpc32xx_pwm_chip *lpc32xx = to_lpc32xx_pwm_chip(chip);
 	u32 val;
 
-	val = readl(lpc32xx->base + (pwm->hwpwm << 2));
+	val = readl(lpc32xx->base);
 	val &= ~PWM_ENABLE;
-	writel(val, lpc32xx->base + (pwm->hwpwm << 2));
+	writel(val, lpc32xx->base);
 
 	clk_disable_unprepare(lpc32xx->clk);
 }
@@ -118,9 +118,9 @@ static int lpc32xx_pwm_probe(struct platform_device *pdev)
 	lpc32xx->chip.npwm = 1;
 
 	/* If PWM is disabled, configure the output to the default value */
-	val = readl(lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2));
+	val = readl(lpc32xx->base);
 	val &= ~PWM_PIN_LEVEL;
-	writel(val, lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2));
+	writel(val, lpc32xx->base);
 
 	ret = devm_pwmchip_add(&pdev->dev, &lpc32xx->chip);
 	if (ret < 0) {
Signature · 1 line
2.40.1
author maintainer
#427 lore raw

PATCH 426/511 net/sched: fq_pie: avoid stalls in fq_pie_timer()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 8c21ab1bae945686c602c5bfa4e3f3352c2452c5 ]

When setting a high number of flows (limit being 65536), fq_pie_timer() is currently using too much time as syzbot reported.

Add logic to yield the cpu every 2048 flows (less than 150 usec on debug kernels).
It should also help by not blocking qdisc fast paths for too long. Worst case (65536 flows) would need 31 jiffies for a complete scan.

Relevant extract from syzbot report:

rcu: INFO: rcu_preempt detected expedited stalls on CPUs/tasks: { 0-.... } 2663 jiffies s: 873 root: 0x1/.
rcu: blocking rcu_node structures (internal RCU debug):
Sending NMI from CPU 1 to CPUs 0:
NMI backtrace for cpu 0
CPU: 0 PID: 5177 Comm: syz-executor273 Not tainted 6.5.0-syzkaller-00453-g727dbda16b83 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
RIP: 0010:check_kcov_mode kernel/kcov.c:173 [inline]
RIP: 0010:write_comp_data+0x21/0x90 kernel/kcov.c:236
Code: 2e 0f 1f 84 00 00 00 00 00 65 8b 05 01 b2 7d 7e 49 89 f1 89 c6 49 89 d2 81 e6 00 01 00 00 49 89 f8 65 48 8b 14 25 80 b9 03 00 <a9> 00 01 ff 00 74 0e 85 f6 74 59 8b 82 04 16 00 00 85 c0 74 4f 8b
RSP: 0018:ffffc90000007bb8 EFLAGS: 00000206
RAX: 0000000000000101 RBX: ffffc9000dc0d140 RCX: ffffffff885893b0
RDX: ffff88807c075940 RSI: 0000000000000100 RDI: 0000000000000001
RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffffc9000dc0d178
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
FS:  0000555555d54380(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f6b442f6130 CR3: 000000006fe1c000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <NMI>
 </NMI>
 <IRQ>
 pie_calculate_probability+0x480/0x850 net/sched/sch_pie.c:415
 fq_pie_timer+0x1da/0x4f0 net/sched/sch_fq_pie.c:387
 call_timer_fn+0x1a0/0x580 kernel/time/timer.c:1700
---
 net/sched/sch_fq_pie.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)
net/sched/sch_fq_pie.c +19 -8
index ce7833f95214f..1fb68c973f451 100644
@@ -61,6 +61,7 @@ struct fq_pie_sched_data {
 	struct pie_params p_params;
 	u32 ecn_prob;
 	u32 flows_cnt;
+	u32 flows_cursor;
 	u32 quantum;
 	u32 memory_limit;
 	u32 new_flow_count;
@@ -378,21 +379,31 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
 static void fq_pie_timer(struct timer_list *t)
 {
 	struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer);
+	unsigned long next, tupdate;
 	struct Qdisc *sch = q->sch;
 	spinlock_t *root_lock; /* to lock qdisc for probability calculations */
-	u32 idx;
+	int max_cnt, i;
 
 	root_lock = qdisc_lock(qdisc_root_sleeping(sch));
 	spin_lock(root_lock);
 
-	for (idx = 0; idx < q->flows_cnt; idx++)
-		pie_calculate_probability(&q->p_params, &q->flows[idx].vars,
-					  q->flows[idx].backlog);
-
-	/* reset the timer to fire after 'tupdate' jiffies. */
-	if (q->p_params.tupdate)
-		mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate);
+	/* Limit this expensive loop to 2048 flows per round. */
+	max_cnt = min_t(int, q->flows_cnt - q->flows_cursor, 2048);
+	for (i = 0; i < max_cnt; i++) {
+		pie_calculate_probability(&q->p_params,
+					  &q->flows[q->flows_cursor].vars,
+					  q->flows[q->flows_cursor].backlog);
+		q->flows_cursor++;
+	}
 
+	tupdate = q->p_params.tupdate;
+	next = 0;
+	if (q->flows_cursor >= q->flows_cnt) {
+		q->flows_cursor = 0;
+		next = tupdate;
+	}
+	if (tupdate)
+		mod_timer(&q->adapt_timer, jiffies + next);
 	spin_unlock(root_lock);
 }
 
Signature · 1 line
2.40.1
author maintainer
#428 lore raw

PATCH 427/511 sctp: annotate data-races around sk->sk_wmem_queued

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit dc9511dd6f37fe803f6b15b61b030728d7057417 ]

sk->sk_wmem_queued can be read locklessly from sctp_poll()

Use sk_wmem_queued_add() when the field is changed, and add READ_ONCE() annotations in sctp_writeable() and sctp_assocs_seq_show()

syzbot reported:

BUG: KCSAN: data-race in sctp_poll / sctp_wfree

read-write to 0xffff888149d77810 of 4 bytes by interrupt on cpu 0:

sctp_wfree+0x170/0x4a0 net/sctp/socket.c:9147
skb_release_head_state+0xb7/0x1a0 net/core/skbuff.c:988
skb_release_all net/core/skbuff.c:1000 [inline]
__kfree_skb+0x16/0x140 net/core/skbuff.c:1016
consume_skb+0x57/0x180 net/core/skbuff.c:1232
sctp_chunk_destroy net/sctp/sm_make_chunk.c:1503 [inline]
sctp_chunk_put+0xcd/0x130 net/sctp/sm_make_chunk.c:1530
sctp_datamsg_put+0x29a/0x300 net/sctp/chunk.c:128
sctp_chunk_free+0x34/0x50 net/sctp/sm_make_chunk.c:1515
sctp_outq_sack+0xafa/0xd70 net/sctp/outqueue.c:1381
sctp_cmd_process_sack net/sctp/sm_sideeffect.c:834 [inline]
sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1366 [inline]
sctp_side_effects net/sctp/sm_sideeffect.c:1198 [inline]
sctp_do_sm+0x12c7/0x31b0 net/sctp/sm_sideeffect.c:1169
sctp_assoc_bh_rcv+0x2b2/0x430 net/sctp/associola.c:1051
sctp_inq_push+0x108/0x120 net/sctp/inqueue.c:80
sctp_rcv+0x116e/0x1340 net/sctp/input.c:243
sctp6_rcv+0x25/0x40 net/sctp/ipv6.c:1120
ip6_protocol_deliver_rcu+0x92f/0xf30 net/ipv6/ip6_input.c:437
ip6_input_finish net/ipv6/ip6_input.c:482 [inline]
NF_HOOK include/linux/netfilter.h:303 [inline]
ip6_input+0xbd/0x1b0 net/ipv6/ip6_input.c:491
dst_input include/net/dst.h:468 [inline]
ip6_rcv_finish+0x1e2/0x2e0 net/ipv6/ip6_input.c:79
NF_HOOK include/linux/netfilter.h:303 [inline]
ipv6_rcv+0x74/0x150 net/ipv6/ip6_input.c:309
__netif_receive_skb_one_core net/core/dev.c:5452 [inline]
__netif_receive_skb+0x90/0x1b0 net/core/dev.c:5566
process_backlog+0x21f/0x380 net/core/dev.c:5894
__napi_poll+0x60/0x3b0 net/core/dev.c:6460
napi_poll net/core/dev.c:6527 [inline]
net_rx_action+0x32b/0x750 net/core/dev.c:6660
__do_softirq+0xc1/0x265 kernel/softirq.c:553
run_ksoftirqd+0x17/0x20 kernel/softirq.c:921
smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164
kthread+0x1d7/0x210 kernel/kthread.c:389
ret_from_fork+0x2e/0x40 arch/x86/kernel/process.c:145
ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304

read to 0xffff888149d77810 of 4 bytes by task 17828 on cpu 1:

sctp_writeable net/sctp/socket.c:9304 [inline]
sctp_poll+0x265/0x410 net/sctp/socket.c:8671
sock_poll+0x253/0x270 net/socket.c:1374
vfs_poll include/linux/poll.h:88 [inline]
do_pollfd fs/select.c:873 [inline]
do_poll fs/select.c:921 [inline]
do_sys_poll+0x636/0xc00 fs/select.c:1015
__do_sys_ppoll fs/select.c:1121 [inline]
__se_sys_ppoll+0x1af/0x1f0 fs/select.c:1101
__x64_sys_ppoll+0x67/0x80 fs/select.c:1101
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x00019e80 -> 0x0000cc80

Reported by Kernel Concurrency Sanitizer on:

CPU: 1 PID: 17828 Comm: syz-executor.1 Not tainted 6.5.0-rc7-syzkaller-00185-g28f20a19294d #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
---
 net/sctp/proc.c   |  2 +-
 net/sctp/socket.c | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)
net/sctp/proc.c +1 -1
index 982a87b3e11f8..963b94517ec20 100644
@@ -284,7 +284,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
 		assoc->init_retries, assoc->shutdown_retries,
 		assoc->rtx_data_chunks,
 		refcount_read(&sk->sk_wmem_alloc),
-		sk->sk_wmem_queued,
+		READ_ONCE(sk->sk_wmem_queued),
 		sk->sk_sndbuf,
 		sk->sk_rcvbuf);
 	seq_printf(seq, "\n");
net/sctp/socket.c +5 -5
index 717e2f60370b3..36a37fef27719 100644
@@ -68,7 +68,7 @@
 #include <net/sctp/stream_sched.h>
 
 /* Forward declarations for internal helper functions. */
-static bool sctp_writeable(struct sock *sk);
+static bool sctp_writeable(const struct sock *sk);
 static void sctp_wfree(struct sk_buff *skb);
 static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 				size_t msg_len);
@@ -138,7 +138,7 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk)
 
 	refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc);
 	asoc->sndbuf_used += chunk->skb->truesize + sizeof(struct sctp_chunk);
-	sk->sk_wmem_queued += chunk->skb->truesize + sizeof(struct sctp_chunk);
+	sk_wmem_queued_add(sk, chunk->skb->truesize + sizeof(struct sctp_chunk));
 	sk_mem_charge(sk, chunk->skb->truesize);
 }
 
@@ -9148,7 +9148,7 @@ static void sctp_wfree(struct sk_buff *skb)
 	struct sock *sk = asoc->base.sk;
 
 	sk_mem_uncharge(sk, skb->truesize);
-	sk->sk_wmem_queued -= skb->truesize + sizeof(struct sctp_chunk);
+	sk_wmem_queued_add(sk, -(skb->truesize + sizeof(struct sctp_chunk)));
 	asoc->sndbuf_used -= skb->truesize + sizeof(struct sctp_chunk);
 	WARN_ON(refcount_sub_and_test(sizeof(struct sctp_chunk),
 				      &sk->sk_wmem_alloc));
@@ -9303,9 +9303,9 @@ void sctp_write_space(struct sock *sk)
  * UDP-style sockets or TCP-style sockets, this code should work.
  *  - Daisy
  */
-static bool sctp_writeable(struct sock *sk)
+static bool sctp_writeable(const struct sock *sk)
 {
-	return sk->sk_sndbuf > sk->sk_wmem_queued;
+	return READ_ONCE(sk->sk_sndbuf) > READ_ONCE(sk->sk_wmem_queued);
 }
 
 /* Wait for an association to go into ESTABLISHED state. If timeout is 0,
Signature · 1 line
2.40.1
author maintainer
#429 lore raw

PATCH 428/511 ipv4: annotate data-races around fi->fib_dead

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit fce92af1c29d90184dfec638b5738831097d66e9 ]

syzbot complained about a data-race in fib_table_lookup() [1]

Add appropriate annotations to document it.

[1]

BUG: KCSAN: data-race in fib_release_info / fib_table_lookup

write to 0xffff888150f31744 of 1 bytes by task 1189 on cpu 0:

fib_release_info+0x3a0/0x460 net/ipv4/fib_semantics.c:281
fib_table_delete+0x8d2/0x900 net/ipv4/fib_trie.c:1777
fib_magic+0x1c1/0x1f0 net/ipv4/fib_frontend.c:1106
fib_del_ifaddr+0x8cf/0xa60 net/ipv4/fib_frontend.c:1317
fib_inetaddr_event+0x77/0x200 net/ipv4/fib_frontend.c:1448
notifier_call_chain kernel/notifier.c:93 [inline]
blocking_notifier_call_chain+0x90/0x200 kernel/notifier.c:388
__inet_del_ifa+0x4df/0x800 net/ipv4/devinet.c:432
inet_del_ifa net/ipv4/devinet.c:469 [inline]
inetdev_destroy net/ipv4/devinet.c:322 [inline]
inetdev_event+0x553/0xaf0 net/ipv4/devinet.c:1606
notifier_call_chain kernel/notifier.c:93 [inline]
raw_notifier_call_chain+0x6b/0x1c0 kernel/notifier.c:461
call_netdevice_notifiers_info net/core/dev.c:1962 [inline]
call_netdevice_notifiers_mtu+0xd2/0x130 net/core/dev.c:2037
dev_set_mtu_ext+0x30b/0x3e0 net/core/dev.c:8673
do_setlink+0x5be/0x2430 net/core/rtnetlink.c:2837
rtnl_setlink+0x255/0x300 net/core/rtnetlink.c:3177
rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6445
netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2549
rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6463
netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline]
netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365
netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1914
sock_sendmsg_nosec net/socket.c:725 [inline]
sock_sendmsg net/socket.c:748 [inline]
sock_write_iter+0x1aa/0x230 net/socket.c:1129
do_iter_write+0x4b4/0x7b0 fs/read_write.c:860
vfs_writev+0x1a8/0x320 fs/read_write.c:933
do_writev+0xf8/0x220 fs/read_write.c:976
__do_sys_writev fs/read_write.c:1049 [inline]
__se_sys_writev fs/read_write.c:1046 [inline]
__x64_sys_writev+0x45/0x50 fs/read_write.c:1046
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

read to 0xffff888150f31744 of 1 bytes by task 21839 on cpu 1:

fib_table_lookup+0x2bf/0xd50 net/ipv4/fib_trie.c:1585
fib_lookup include/net/ip_fib.h:383 [inline]
ip_route_output_key_hash_rcu+0x38c/0x12c0 net/ipv4/route.c:2751
ip_route_output_key_hash net/ipv4/route.c:2641 [inline]
__ip_route_output_key include/net/route.h:134 [inline]
ip_route_output_flow+0xa6/0x150 net/ipv4/route.c:2869
send4+0x1e7/0x500 drivers/net/wireguard/socket.c:61
wg_socket_send_skb_to_peer+0x94/0x130 drivers/net/wireguard/socket.c:175
wg_socket_send_buffer_to_peer+0xd6/0x100 drivers/net/wireguard/socket.c:200
wg_packet_send_handshake_initiation drivers/net/wireguard/send.c:40 [inline]
wg_packet_handshake_send_worker+0x10c/0x150 drivers/net/wireguard/send.c:51
process_one_work+0x434/0x860 kernel/workqueue.c:2600
worker_thread+0x5f2/0xa10 kernel/workqueue.c:2751
kthread+0x1d7/0x210 kernel/kthread.c:389
ret_from_fork+0x2e/0x40 arch/x86/kernel/process.c:145
ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304

value changed: 0x00 -> 0x01

Reported by Kernel Concurrency Sanitizer on:

CPU: 1 PID: 21839 Comm: kworker/u4:18 Tainted: G W 6.5.0-syzkaller #0
---
 net/ipv4/fib_semantics.c | 5 ++++-
 net/ipv4/fib_trie.c      | 3 ++-
 2 files changed, 6 insertions(+), 2 deletions(-)
net/ipv4/fib_semantics.c +4 -1
index 607a4f8161555..799370bcc70c1 100644
@@ -276,7 +276,8 @@ void fib_release_info(struct fib_info *fi)
 				hlist_del(&nexthop_nh->nh_hash);
 			} endfor_nexthops(fi)
 		}
-		fi->fib_dead = 1;
+		/* Paired with READ_ONCE() from fib_table_lookup() */
+		WRITE_ONCE(fi->fib_dead, 1);
 		fib_info_put(fi);
 	}
 	spin_unlock_bh(&fib_info_lock);
@@ -1598,6 +1599,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 link_it:
 	ofi = fib_find_info(fi);
 	if (ofi) {
+		/* fib_table_lookup() should not see @fi yet. */
 		fi->fib_dead = 1;
 		free_fib_info(fi);
 		refcount_inc(&ofi->fib_treeref);
@@ -1636,6 +1638,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 
 failure:
 	if (fi) {
+		/* fib_table_lookup() should not see @fi yet. */
 		fi->fib_dead = 1;
 		free_fib_info(fi);
 	}
net/ipv4/fib_trie.c +2 -1
index 52f9f69f57b32..22531aac0ccbf 100644
@@ -1578,7 +1578,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		}
 		if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
 			continue;
-		if (fi->fib_dead)
+		/* Paired with WRITE_ONCE() in fib_release_info() */
+		if (READ_ONCE(fi->fib_dead))
 			continue;
 		if (fa->fa_info->fib_scope < flp->flowi4_scope)
 			continue;
Signature · 1 line
2.40.1
author maintainer
#430 lore raw

PATCH 429/511 net: read sk->sk_family once in sk_mc_loop()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit a3e0fdf71bbe031de845e8e08ed7fba49f9c702c ]

syzbot is playing with IPV6_ADDRFORM quite a lot these days, and managed to hit the WARN_ON_ONCE(1) in sk_mc_loop()

We have many more similar issues to fix.

WARNING: CPU: 1 PID: 1593 at net/core/sock.c:782 sk_mc_loop+0x165/0x260
Modules linked in:
CPU: 1 PID: 1593 Comm: kworker/1:3 Not tainted 6.1.40-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
Workqueue: events_power_efficient gc_worker
RIP: 0010:sk_mc_loop+0x165/0x260 net/core/sock.c:782
Code: 34 1b fd 49 81 c7 18 05 00 00 4c 89 f8 48 c1 e8 03 42 80 3c 20 00 74 08 4c 89 ff e8 25 36 6d fd 4d 8b 37 eb 13 e8 db 33 1b fd <0f> 0b b3 01 eb 34 e8 d0 33 1b fd 45 31 f6 49 83 c6 38 4c 89 f0 48
RSP: 0018:ffffc90000388530 EFLAGS: 00010246
RAX: ffffffff846d9b55 RBX: 0000000000000011 RCX: ffff88814f884980
RDX: 0000000000000102 RSI: ffffffff87ae5160 RDI: 0000000000000011
RBP: ffffc90000388550 R08: 0000000000000003 R09: ffffffff846d9a65
R10: 0000000000000002 R11: ffff88814f884980 R12: dffffc0000000000
R13: ffff88810dbee000 R14: 0000000000000010 R15: ffff888150084000
FS: 0000000000000000(0000) GS:ffff8881f6b00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000180 CR3: 000000014ee5b000 CR4: 00000000003506e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<IRQ>
[<ffffffff8507734f>] ip6_finish_output2+0x33f/0x1ae0 net/ipv6/ip6_output.c:83
[<ffffffff85062766>] __ip6_finish_output net/ipv6/ip6_output.c:200 [inline]
[<ffffffff85062766>] ip6_finish_output+0x6c6/0xb10 net/ipv6/ip6_output.c:211
[<ffffffff85061f8c>] NF_HOOK_COND include/linux/netfilter.h:298 [inline]
[<ffffffff85061f8c>] ip6_output+0x2bc/0x3d0 net/ipv6/ip6_output.c:232
[<ffffffff852071cf>] dst_output include/net/dst.h:444 [inline]
[<ffffffff852071cf>] ip6_local_out+0x10f/0x140 net/ipv6/output_core.c:161
[<ffffffff83618fb4>] ipvlan_process_v6_outbound drivers/net/ipvlan/ipvlan_core.c:483 [inline]
[<ffffffff83618fb4>] ipvlan_process_outbound drivers/net/ipvlan/ipvlan_core.c:529 [inline]
[<ffffffff83618fb4>] ipvlan_xmit_mode_l3 drivers/net/ipvlan/ipvlan_core.c:602 [inline]
[<ffffffff83618fb4>] ipvlan_queue_xmit+0x1174/0x1be0 drivers/net/ipvlan/ipvlan_core.c:677
[<ffffffff8361ddd9>] ipvlan_start_xmit+0x49/0x100 drivers/net/ipvlan/ipvlan_main.c:229
[<ffffffff84763fc0>] netdev_start_xmit include/linux/netdevice.h:4925 [inline]
[<ffffffff84763fc0>] xmit_one net/core/dev.c:3644 [inline]
[<ffffffff84763fc0>] dev_hard_start_xmit+0x320/0x980 net/core/dev.c:3660
[<ffffffff8494c650>] sch_direct_xmit+0x2a0/0x9c0 net/sched/sch_generic.c:342
[<ffffffff8494d883>] qdisc_restart net/sched/sch_generic.c:407 [inline]
[<ffffffff8494d883>] __qdisc_run+0xb13/0x1e70 net/sched/sch_generic.c:415
[<ffffffff8478c426>] qdisc_run+0xd6/0x260 include/net/pkt_sched.h:125
[<ffffffff84796eac>] net_tx_action+0x7ac/0x940 net/core/dev.c:5247
[<ffffffff858002bd>] __do_softirq+0x2bd/0x9bd kernel/softirq.c:599
[<ffffffff814c3fe8>] invoke_softirq kernel/softirq.c:430 [inline]
[<ffffffff814c3fe8>] __irq_exit_rcu+0xc8/0x170 kernel/softirq.c:683
[<ffffffff814c3f09>] irq_exit_rcu+0x9/0x20 kernel/softirq.c:695
Fixes 7ad6848c7e81 ("ip: fix mc_loop checks for tunnels with multicast outer addresses")
---
 net/core/sock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
net/core/sock.c +2 -1
index ae1e9e2b82557..4b63478cf021a 100644
@@ -717,7 +717,8 @@ bool sk_mc_loop(struct sock *sk)
 		return false;
 	if (!sk)
 		return true;
-	switch (sk->sk_family) {
+	/* IPV6_ADDRFORM can change sk->sk_family under us. */
+	switch (READ_ONCE(sk->sk_family)) {
 	case AF_INET:
 		return inet_sk(sk)->mc_loop;
 #if IS_ENABLED(CONFIG_IPV6)
Signature · 1 line
2.40.1
author maintainer
#431 lore raw

PATCH 430/511 net: fib: avoid warn splat in flow dissector

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Westphal <[email protected]>

[ Upstream commit 8aae7625ff3f0bd5484d01f1b8d5af82e44bec2d ]

New skbs allocated via nf_send_reset() have skb->dev == NULL.

fib*_rules_early_flow_dissect helpers already have a 'struct net' argument but its not passed down to the flow dissector core, which will then WARN as it can't derive a net namespace to use:

 WARNING: CPU: 0 PID: 0 at net/core/flow_dissector.c:1016 __skb_flow_dissect+0xa91/0x1cd0
 [..]
  ip_route_me_harder+0x143/0x330
  nf_send_reset+0x17c/0x2d0 [nf_reject_ipv4]
  nft_reject_inet_eval+0xa9/0xf2 [nft_reject_inet]
  nft_do_chain+0x198/0x5d0 [nf_tables]
  nft_do_chain_inet+0xa4/0x110 [nf_tables]
  nf_hook_slow+0x41/0xc0
  ip_local_deliver+0xce/0x110
  ..
---
 include/net/ip6_fib.h | 5 ++++-
 include/net/ip_fib.h  | 5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)
include/net/ip6_fib.h +4 -1
index bbb27639f2933..d72cee4dff70b 100644
@@ -610,7 +610,10 @@ static inline bool fib6_rules_early_flow_dissect(struct net *net,
 	if (!net->ipv6.fib6_rules_require_fldissect)
 		return false;
 
-	skb_flow_dissect_flow_keys(skb, flkeys, flag);
+	memset(flkeys, 0, sizeof(*flkeys));
+	__skb_flow_dissect(net, skb, &flow_keys_dissector,
+			   flkeys, NULL, 0, 0, 0, flag);
+
 	fl6->fl6_sport = flkeys->ports.src;
 	fl6->fl6_dport = flkeys->ports.dst;
 	fl6->flowi6_proto = flkeys->basic.ip_proto;
include/net/ip_fib.h +4 -1
index 3417ba2d27ad6..c3324a1949c3a 100644
@@ -415,7 +415,10 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net,
 	if (!net->ipv4.fib_rules_require_fldissect)
 		return false;
 
-	skb_flow_dissect_flow_keys(skb, flkeys, flag);
+	memset(flkeys, 0, sizeof(*flkeys));
+	__skb_flow_dissect(net, skb, &flow_keys_dissector,
+			   flkeys, NULL, 0, 0, 0, flag);
+
 	fl4->fl4_sport = flkeys->ports.src;
 	fl4->fl4_dport = flkeys->ports.dst;
 	fl4->flowi4_proto = flkeys->basic.ip_proto;
Signature · 1 line
2.40.1
author maintainer
#432 lore raw

PATCH 431/511 xsk: Fix xsk_diag use-after-free error during socket cleanup

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Magnus Karlsson <[email protected]>

[ Upstream commit 3e019d8a05a38abb5c85d4f1e85fda964610aa14 ]

Fix a use-after-free error that is possible if the xsk_diag interface is used after the socket has been unbound from the device. This can happen either due to the socket being closed or the device disappearing. In the early days of AF_XDP, the way we tested that a socket was not bound to a device was to simply check if the netdevice pointer in the xsk socket structure was NULL. Later, a better system was introduced by having an explicit state variable in the xsk socket struct. For example, the state of a socket that is on the way to being closed and has been unbound from the device is XSK_UNBOUND.

The commit in the Fixes tag below deleted the old way of signalling that a socket is unbound, setting dev to NULL. This in the belief that all code using the old way had been exterminated. That was unfortunately not true as the xsk diagnostics code was still using the old way and thus does not work as intended when a socket is going down. Fix this by introducing a test against the state variable. If the socket is in the state XSK_UNBOUND, simply abort the diagnostic's netlink operation.

---
 net/xdp/xsk_diag.c | 3 +++
 1 file changed, 3 insertions(+)
net/xdp/xsk_diag.c +3 -0
index c014217f5fa7d..22b36c8143cfd 100644
@@ -111,6 +111,9 @@ static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb,
 	sock_diag_save_cookie(sk, msg->xdiag_cookie);
 
 	mutex_lock(&xs->mutex);
+	if (READ_ONCE(xs->state) == XSK_UNBOUND)
+		goto out_nlmsg_trim;
+
 	if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb))
 		goto out_nlmsg_trim;
 
Signature · 1 line
2.40.1
author maintainer
#433 lore raw

PATCH 432/511 ceph: make members in struct ceph_mds_request_args_ext a union

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xiubo Li <[email protected]>

[ Upstream commit 3af5ae22030cb59fab4fba35f5a2b62f47e14df9 ]

In ceph mainline it will allow to set the btime in the setattr request and just add a 'btime' member in the union 'ceph_mds_request_args' and then bump up the header version to 4. That means the total size of union 'ceph_mds_request_args' will increase sizeof(struct ceph_timespec) bytes, but in kclient it will increase the sizeof(setattr_ext) bytes for each request.

Since the MDS will always depend on the header's vesion and front_len members to decode the 'ceph_mds_request_head' struct, at the same time kclient hasn't supported the 'btime' feature yet in setattr request, so it's safe to do this change here.

This will save 48 bytes memories for each request.

Fixes 4f1ddb1ea874 ("ceph: implement updated ceph_mds_request_head structure")
---
 include/linux/ceph/ceph_fs.h | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)
include/linux/ceph/ceph_fs.h +13 -11
index bc2699feddbeb..8038279a14fa0 100644
@@ -459,17 +459,19 @@ union ceph_mds_request_args {
 } __attribute__ ((packed));
 
 union ceph_mds_request_args_ext {
-	union ceph_mds_request_args old;
-	struct {
-		__le32 mode;
-		__le32 uid;
-		__le32 gid;
-		struct ceph_timespec mtime;
-		struct ceph_timespec atime;
-		__le64 size, old_size;       /* old_size needed by truncate */
-		__le32 mask;                 /* CEPH_SETATTR_* */
-		struct ceph_timespec btime;
-	} __attribute__ ((packed)) setattr_ext;
+	union {
+		union ceph_mds_request_args old;
+		struct {
+			__le32 mode;
+			__le32 uid;
+			__le32 gid;
+			struct ceph_timespec mtime;
+			struct ceph_timespec atime;
+			__le64 size, old_size;       /* old_size needed by truncate */
+			__le32 mask;                 /* CEPH_SETATTR_* */
+			struct ceph_timespec btime;
+		} __attribute__ ((packed)) setattr_ext;
+	};
 };
 
 #define CEPH_MDS_FLAG_REPLAY		1 /* this is a replayed op */
Signature · 1 line
2.40.1
author maintainer
#434 lore raw

PATCH 433/511 drm/i915/gvt: Drop unused helper intel_vgpu_reset_gtt()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sean Christopherson <[email protected]>

[ Upstream commit a90c367e5af63880008e21dd199dac839e0e9e0f ]

Drop intel_vgpu_reset_gtt() as it no longer has any callers. In addition to eliminating dead code, this eliminates the last possible scenario where __kvmgt_protect_table_find() can be reached without holding vgpu_lock. Requiring vgpu_lock to be held when calling __kvmgt_protect_table_find() will allow a protecting the gfn hash with vgpu_lock without too much fuss.

No functional change intended.

---
 drivers/gpu/drm/i915/gvt/gtt.c | 18 ------------------
 drivers/gpu/drm/i915/gvt/gtt.h |  1 -
 2 files changed, 19 deletions(-)
drivers/gpu/drm/i915/gvt/gtt.c +0 -18
index 7ea7abef6143f..0344a0eef95c0 100644
@@ -2864,24 +2864,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old)
 	ggtt_invalidate(gvt->gt);
 }
 
-/**
- * intel_vgpu_reset_gtt - reset the all GTT related status
- * @vgpu: a vGPU
- *
- * This function is called from vfio core to reset reset all
- * GTT related status, including GGTT, PPGTT, scratch page.
- *
- */
-void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu)
-{
-	/* Shadow pages are only created when there is no page
-	 * table tracking data, so remove page tracking data after
-	 * removing the shadow pages.
-	 */
-	intel_vgpu_destroy_all_ppgtt_mm(vgpu);
-	intel_vgpu_reset_ggtt(vgpu, true);
-}
-
 /**
  * intel_gvt_restore_ggtt - restore all vGPU's ggtt entries
  * @gvt: intel gvt device
drivers/gpu/drm/i915/gvt/gtt.h +0 -1
index 3bf45672ef987..8e8fe21186243 100644
@@ -224,7 +224,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old);
 void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu);
 
 int intel_gvt_init_gtt(struct intel_gvt *gvt);
-void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu);
 void intel_gvt_clean_gtt(struct intel_gvt *gvt);
 
 struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu,
Signature · 1 line
2.40.1
author maintainer
#435 lore raw

PATCH 434/511 ipv4: ignore dst hint for multipath routes

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sriram Yagnaraman <[email protected]>

[ Upstream commit 6ac66cb03ae306c2e288a9be18226310529f5b25 ]

Route hints when the nexthop is part of a multipath group causes packets in the same receive batch to be sent to the same nexthop irrespective of the multipath hash of the packet. So, do not extract route hint for packets whose destination is part of a multipath group.

A new SKB flag IPSKB_MULTIPATH is introduced for this purpose, set the flag when route is looked up in ip_mkroute_input() and use it in ip_extract_route_hint() to check for the existence of the flag.

Fixes 02b24941619f ("ipv4: use dst hint for ipv4 list receive")
---
 include/net/ip.h    | 1 +
 net/ipv4/ip_input.c | 3 ++-
 net/ipv4/route.c    | 1 +
 3 files changed, 4 insertions(+), 1 deletion(-)
include/net/ip.h +1 -0
index fc05e016be060..e1a93c3391090 100644
@@ -56,6 +56,7 @@ struct inet_skb_parm {
 #define IPSKB_FRAG_PMTU		BIT(6)
 #define IPSKB_L3SLAVE		BIT(7)
 #define IPSKB_NOPOLICY		BIT(8)
+#define IPSKB_MULTIPATH		BIT(9)
 
 	u16			frag_max_size;
 };
net/ipv4/ip_input.c +2 -1
index 124bf8fdf924a..5d0bc0dbdb4d9 100644
@@ -581,7 +581,8 @@ static void ip_sublist_rcv_finish(struct list_head *head)
 static struct sk_buff *ip_extract_route_hint(const struct net *net,
 					     struct sk_buff *skb, int rt_type)
 {
-	if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST)
+	if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST ||
+	    IPCB(skb)->flags & IPSKB_MULTIPATH)
 		return NULL;
 
 	return skb;
net/ipv4/route.c +1 -0
index ca59b61fd3a31..bc6240d327a8f 100644
@@ -2151,6 +2151,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
 		int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys);
 
 		fib_select_multipath(res, h);
+		IPCB(skb)->flags |= IPSKB_MULTIPATH;
 	}
 #endif
 
Signature · 1 line
2.40.1
author maintainer
#436 lore raw

PATCH 435/511 igb: disable virtualization features on 82580

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Corinna Vinschen <[email protected]>

[ Upstream commit fa09bc40b21a33937872c4c4cf0f266ec9fa4869 ]

Disable virtualization features on 82580 just as on i210/i211. This avoids that virt functions are acidentally called on 82850.

Fixes 55cac248caa4 ("igb: Add full support for 82580 devices")
---
 drivers/net/ethernet/intel/igb/igb_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/net/ethernet/intel/igb/igb_main.c +3 -2
index 83daf86c1674b..c01114cabbb09 100644
@@ -3856,8 +3856,9 @@ static void igb_probe_vfs(struct igb_adapter *adapter)
 	struct pci_dev *pdev = adapter->pdev;
 	struct e1000_hw *hw = &adapter->hw;
 
-	/* Virtualization features not supported on i210 family. */
-	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211))
+	/* Virtualization features not supported on i210 and 82580 family. */
+	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211) ||
+	    (hw->mac.type == e1000_82580))
 		return;
 
 	/* Of the below we really only want the effect of getting
Signature · 1 line
2.40.1
author maintainer
#437 lore raw

PATCH 436/511 veth: Fixing transmit return status for dropped packets

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Liang Chen <[email protected]>

[ Upstream commit 151e887d8ff97e2e42110ffa1fb1e6a2128fb364 ]

The veth_xmit function returns NETDEV_TX_OK even when packets are dropped. This behavior leads to incorrect calculations of statistics counts, as well as things like txq->trans_start updates.

Fixes e314dbdc1c0d ("[NET]: Virtual ethernet device driver.")
---
 drivers/net/veth.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/veth.c +3 -1
index 45ee44f66e77d..984a153804096 100644
@@ -320,6 +320,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
 	struct veth_rq *rq = NULL;
+	int ret = NETDEV_TX_OK;
 	struct net_device *rcv;
 	int length = skb->len;
 	bool use_napi = false;
@@ -352,6 +353,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else {
 drop:
 		atomic64_inc(&priv->dropped);
+		ret = NET_XMIT_DROP;
 	}
 
 	if (use_napi)
@@ -359,7 +361,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	rcu_read_unlock();
 
-	return NETDEV_TX_OK;
+	return ret;
 }
 
 static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes)
Signature · 1 line
2.40.1
author maintainer
#438 lore raw

PATCH 437/511 net: ipv6/addrconf: avoid integer underflow in ipv6_create_tempaddr

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Henrie <[email protected]>

[ Upstream commit f31867d0d9d82af757c1e0178b659438f4c1ea3c ]

The existing code incorrectly casted a negative value (the result of a subtraction) to an unsigned value without checking. For example, if /proc/sys/net/ipv6/conf/*/temp_prefered_lft was set to 1, the preferred lifetime would jump to 4 billion seconds. On my machine and network the shortest lifetime that avoided underflow was 3 seconds.

Fixes 76506a986dc3 ("IPv6: fix DESYNC_FACTOR")
---
 net/ipv6/addrconf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/ipv6/addrconf.c +1 -1
index 0c0b7969840f5..6572174e2115f 100644
@@ -1368,7 +1368,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block)
 	 * idev->desync_factor if it's larger
 	 */
 	cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft);
-	max_desync_factor = min_t(__u32,
+	max_desync_factor = min_t(long,
 				  idev->cnf.max_desync_factor,
 				  cnf_temp_preferred_lft - regen_advance);
 
Signature · 1 line
2.40.1
author maintainer
#439 lore raw

PATCH 438/511 net: phy: micrel: Correct bit assignments for phy_device flags

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Oleksij Rempel <[email protected]>

[ Upstream commit 719c5e37e99d2fd588d1c994284d17650a66354c ]

Previously, the defines for phy_device flags in the Micrel driver were ambiguous in their representation. They were intended to be bit masks but were mistakenly defined as bit positions. This led to the following issues:

- MICREL_KSZ8_P1_ERRATA, designated for KSZ88xx switches, overlapped with MICREL_PHY_FXEN and MICREL_PHY_50MHZ_CLK.
- Due to this overlap, the code path for MICREL_PHY_FXEN, tailored for the KSZ8041 PHY, was not executed for KSZ88xx PHYs.
- Similarly, the code associated with MICREL_PHY_50MHZ_CLK wasn't triggered for KSZ88xx.

To rectify this, all three flags have now been explicitly converted to use the BIT() macro, ensuring they are defined as bit masks and preventing potential overlaps in the future.

Fixes 49011e0c1555 ("net: phy: micrel: ksz886x/ksz8081: add cabletest support")
---
 include/linux/micrel_phy.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
include/linux/micrel_phy.h +3 -3
index 3d43c60b49fa8..2d0f75ffa3233 100644
@@ -37,9 +37,9 @@
 #define	PHY_ID_KSZ9477		0x00221631
 
 /* struct phy_device dev_flags definitions */
-#define MICREL_PHY_50MHZ_CLK	0x00000001
-#define MICREL_PHY_FXEN		0x00000002
-#define MICREL_KSZ8_P1_ERRATA	0x00000003
+#define MICREL_PHY_50MHZ_CLK	BIT(0)
+#define MICREL_PHY_FXEN		BIT(1)
+#define MICREL_KSZ8_P1_ERRATA	BIT(2)
 
 #define MICREL_KSZ9021_EXTREG_CTRL	0xB
 #define MICREL_KSZ9021_EXTREG_DATA_WRITE	0xC
Signature · 1 line
2.40.1
author maintainer
#440 lore raw

PATCH 439/511 af_unix: Fix data-races around user->unix_inflight.

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit 0bc36c0650b21df36fbec8136add83936eaf0607 ]

user->unix_inflight is changed under spin_lock(unix_gc_lock), but too_many_unix_fds() reads it locklessly.

Let's annotate the write/read accesses to user->unix_inflight.

BUG: KCSAN: data-race in unix_attach_fds / unix_inflight

write to 0xffffffff8546f2d0 of 8 bytes by task 44798 on cpu 1:

 unix_inflight+0x157/0x180 net/unix/scm.c:66
 unix_attach_fds+0x147/0x1e0 net/unix/scm.c:123
 unix_scm_to_skb net/unix/af_unix.c:1827 [inline]
 unix_dgram_sendmsg+0x46a/0x14f0 net/unix/af_unix.c:1950
 unix_seqpacket_sendmsg net/unix/af_unix.c:2308 [inline]
 unix_seqpacket_sendmsg+0xba/0x130 net/unix/af_unix.c:2292
 sock_sendmsg_nosec net/socket.c:725 [inline]
 sock_sendmsg+0x148/0x160 net/socket.c:748
 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2494
 ___sys_sendmsg+0xc6/0x140 net/socket.c:2548
 __sys_sendmsg+0x94/0x140 net/socket.c:2577
 __do_sys_sendmsg net/socket.c:2586 [inline]
 __se_sys_sendmsg net/socket.c:2584 [inline]
 __x64_sys_sendmsg+0x45/0x50 net/socket.c:2584
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

read to 0xffffffff8546f2d0 of 8 bytes by task 44814 on cpu 0:

 too_many_unix_fds net/unix/scm.c:101 [inline]
 unix_attach_fds+0x54/0x1e0 net/unix/scm.c:110
 unix_scm_to_skb net/unix/af_unix.c:1827 [inline]
 unix_dgram_sendmsg+0x46a/0x14f0 net/unix/af_unix.c:1950
 unix_seqpacket_sendmsg net/unix/af_unix.c:2308 [inline]
 unix_seqpacket_sendmsg+0xba/0x130 net/unix/af_unix.c:2292
 sock_sendmsg_nosec net/socket.c:725 [inline]
 sock_sendmsg+0x148/0x160 net/socket.c:748
 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2494
 ___sys_sendmsg+0xc6/0x140 net/socket.c:2548
 __sys_sendmsg+0x94/0x140 net/socket.c:2577
 __do_sys_sendmsg net/socket.c:2586 [inline]
 __se_sys_sendmsg net/socket.c:2584 [inline]
 __x64_sys_sendmsg+0x45/0x50 net/socket.c:2584
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

value changed: 0x000000000000000c -> 0x000000000000000d

Reported by Kernel Concurrency Sanitizer on:

CPU: 0 PID: 44814 Comm: systemd-coredum Not tainted 6.4.0-11989-g6843306689af #6
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
Fixes 712f4aad406b ("unix: properly account for FDs passed over unix sockets")
---
 net/unix/scm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
net/unix/scm.c +3 -3
index aa27a02478dc1..e8e2a00bb0f58 100644
@@ -63,7 +63,7 @@ void unix_inflight(struct user_struct *user, struct file *fp)
 		/* Paired with READ_ONCE() in wait_for_unix_gc() */
 		WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1);
 	}
-	user->unix_inflight++;
+	WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1);
 	spin_unlock(&unix_gc_lock);
 }
 
@@ -84,7 +84,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
 		/* Paired with READ_ONCE() in wait_for_unix_gc() */
 		WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1);
 	}
-	user->unix_inflight--;
+	WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1);
 	spin_unlock(&unix_gc_lock);
 }
 
@@ -98,7 +98,7 @@ static inline bool too_many_unix_fds(struct task_struct *p)
 {
 	struct user_struct *user = current_user();
 
-	if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+	if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE)))
 		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
 	return false;
 }
Signature · 1 line
2.40.1
author maintainer
#441 lore raw

PATCH 440/511 af_unix: Fix data-race around unix_tot_inflight.

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit ade32bd8a738d7497ffe9743c46728db26740f78 ]

unix_tot_inflight is changed under spin_lock(unix_gc_lock), but unix_release_sock() reads it locklessly.

Let's use READ_ONCE() for unix_tot_inflight.

Note that the writer side was marked by commit 9d6d7f1cb67c ("af_unix:
annote lockless accesses to unix_tot_inflight & gc_in_progress")

BUG: KCSAN: data-race in unix_inflight / unix_release_sock

write (marked) to 0xffffffff871852b8 of 4 bytes by task 123 on cpu 1:

 unix_inflight+0x130/0x180 net/unix/scm.c:64
 unix_attach_fds+0x137/0x1b0 net/unix/scm.c:123
 unix_scm_to_skb net/unix/af_unix.c:1832 [inline]
 unix_dgram_sendmsg+0x46a/0x14f0 net/unix/af_unix.c:1955
 sock_sendmsg_nosec net/socket.c:724 [inline]
 sock_sendmsg+0x148/0x160 net/socket.c:747
 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2493
 ___sys_sendmsg+0xc6/0x140 net/socket.c:2547
 __sys_sendmsg+0x94/0x140 net/socket.c:2576
 __do_sys_sendmsg net/socket.c:2585 [inline]
 __se_sys_sendmsg net/socket.c:2583 [inline]
 __x64_sys_sendmsg+0x45/0x50 net/socket.c:2583
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x72/0xdc

read to 0xffffffff871852b8 of 4 bytes by task 4891 on cpu 0:

 unix_release_sock+0x608/0x910 net/unix/af_unix.c:671
 unix_release+0x59/0x80 net/unix/af_unix.c:1058
 __sock_release+0x7d/0x170 net/socket.c:653
 sock_close+0x19/0x30 net/socket.c:1385
 __fput+0x179/0x5e0 fs/file_table.c:321
 ____fput+0x15/0x20 fs/file_table.c:349
 task_work_run+0x116/0x1a0 kernel/task_work.c:179
 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
 exit_to_user_mode_prepare+0x174/0x180 kernel/entry/common.c:204
 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline]
 syscall_exit_to_user_mode+0x1a/0x30 kernel/entry/common.c:297
 do_syscall_64+0x4b/0x90 arch/x86/entry/common.c:86
 entry_SYSCALL_64_after_hwframe+0x72/0xdc

value changed: 0x00000000 -> 0x00000001

Reported by Kernel Concurrency Sanitizer on:

CPU: 0 PID: 4891 Comm: systemd-coredum Not tainted 6.4.0-rc5-01219-gfa0e21fa4443 #5
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
Fixes 9305cfa4443d ("[AF_UNIX]: Make unix_tot_inflight counter non-atomic")
---
 net/unix/af_unix.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/unix/af_unix.c +1 -1
index 5264fe82e6ec1..748769f4ba058 100644
@@ -603,7 +603,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 	 *	  What the above comment does talk about? --ANK(980817)
 	 */
 
-	if (unix_tot_inflight)
+	if (READ_ONCE(unix_tot_inflight))
 		unix_gc();		/* Garbage collect fds */
 }
 
Signature · 1 line
2.40.1
author maintainer
#442 lore raw

PATCH 441/511 af_unix: Fix data-races around sk->sk_shutdown.

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit afe8764f76346ba838d4f162883e23d2fcfaa90e ]

sk->sk_shutdown is changed under unix_state_lock(sk), but unix_dgram_sendmsg() calls two functions to read sk_shutdown locklessly.

sock_alloc_send_pskb
`- sock_wait_for_wmem

Let's use READ_ONCE() there.

Note that the writer side was marked by commit e1d09c2c2f57 ("af_unix:
Fix data races around sk->sk_shutdown.").

BUG: KCSAN: data-race in sock_alloc_send_pskb / unix_release_sock

write (marked) to 0xffff8880069af12c of 1 bytes by task 1 on cpu 1:

 unix_release_sock+0x75c/0x910 net/unix/af_unix.c:631
 unix_release+0x59/0x80 net/unix/af_unix.c:1053
 __sock_release+0x7d/0x170 net/socket.c:654
 sock_close+0x19/0x30 net/socket.c:1386
 __fput+0x2a3/0x680 fs/file_table.c:384
 ____fput+0x15/0x20 fs/file_table.c:412
 task_work_run+0x116/0x1a0 kernel/task_work.c:179
 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:171 [inline]
 exit_to_user_mode_prepare+0x174/0x180 kernel/entry/common.c:204
 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline]
 syscall_exit_to_user_mode+0x1a/0x30 kernel/entry/common.c:297
 do_syscall_64+0x4b/0x90 arch/x86/entry/common.c:86
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

read to 0xffff8880069af12c of 1 bytes by task 28650 on cpu 0:

 sock_alloc_send_pskb+0xd2/0x620 net/core/sock.c:2767
 unix_dgram_sendmsg+0x2f8/0x14f0 net/unix/af_unix.c:1944
 unix_seqpacket_sendmsg net/unix/af_unix.c:2308 [inline]
 unix_seqpacket_sendmsg+0xba/0x130 net/unix/af_unix.c:2292
 sock_sendmsg_nosec net/socket.c:725 [inline]
 sock_sendmsg+0x148/0x160 net/socket.c:748
 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2494
 ___sys_sendmsg+0xc6/0x140 net/socket.c:2548
 __sys_sendmsg+0x94/0x140 net/socket.c:2577
 __do_sys_sendmsg net/socket.c:2586 [inline]
 __se_sys_sendmsg net/socket.c:2584 [inline]
 __x64_sys_sendmsg+0x45/0x50 net/socket.c:2584
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

value changed: 0x00 -> 0x03

Reported by Kernel Concurrency Sanitizer on:

CPU: 0 PID: 28650 Comm: systemd-coredum Not tainted 6.4.0-11989-g6843306689af #6
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
---
 net/core/sock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
net/core/sock.c +2 -2
index 4b63478cf021a..ba669f72d7df2 100644
@@ -2464,7 +2464,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 		if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf))
 			break;
-		if (sk->sk_shutdown & SEND_SHUTDOWN)
+		if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
 			break;
 		if (sk->sk_err)
 			break;
@@ -2494,7 +2494,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 			goto failure;
 
 		err = -EPIPE;
-		if (sk->sk_shutdown & SEND_SHUTDOWN)
+		if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
 			goto failure;
 
 		if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf))
Signature · 1 line
2.40.1
author maintainer
#443 lore raw

PATCH 442/511 af_unix: Fix data race around sk->sk_err.

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit b192812905e4b134f7b7994b079eb647e9d2d37e ]

As with sk->sk_shutdown shown in the previous patch, sk->sk_err can be read locklessly by unix_dgram_sendmsg().

Let's use READ_ONCE() for sk_err as well.

Note that the writer side is marked by commit cc04410af7de ("af_unix:
annotate lockless accesses to sk->sk_err").

Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")
---
 net/core/sock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/core/sock.c +1 -1
index ba669f72d7df2..8faa0f9cc0839 100644
@@ -2466,7 +2466,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
 			break;
 		if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
 			break;
-		if (sk->sk_err)
+		if (READ_ONCE(sk->sk_err))
 			break;
 		timeo = schedule_timeout(timeo);
 	}
Signature · 1 line
2.40.1
author maintainer
#444 lore raw

PATCH 443/511 net: sched: sch_qfq: Fix UAF in qfq_dequeue()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: valis <[email protected]>

[ Upstream commit 8fc134fee27f2263988ae38920bc03da416b03d8 ]

When the plug qdisc is used as a class of the qfq qdisc it could trigger a UAF. This issue can be reproduced with following commands:

tc qdisc add dev lo root handle 1: qfq
tc class add dev lo parent 1: classid 1:1 qfq weight 1 maxpkt 512 tc qdisc add dev lo parent 1:1 handle 2: plug
tc filter add dev lo parent 1: basic classid 1:1
ping -c1 127.0.0.1

and boom:

[  285.353793] BUG: KASAN: slab-use-after-free in qfq_dequeue+0xa7/0x7f0
[  285.354910] Read of size 4 at addr ffff8880bad312a8 by task ping/144
[  285.355903]
[  285.356165] CPU: 1 PID: 144 Comm: ping Not tainted 6.5.0-rc3+ #4
[  285.357112] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
[  285.358376] Call Trace:
[  285.358773]  <IRQ>
[  285.359109]  dump_stack_lvl+0x44/0x60
[  285.359708]  print_address_description.constprop.0+0x2c/0x3c0
[  285.360611]  kasan_report+0x10c/0x120
[  285.361195]  ? qfq_dequeue+0xa7/0x7f0
[  285.361780]  qfq_dequeue+0xa7/0x7f0
[  285.362342]  __qdisc_run+0xf1/0x970
[  285.362903]  net_tx_action+0x28e/0x460
[  285.363502]  __do_softirq+0x11b/0x3de
[  285.364097]  do_softirq.part.0+0x72/0x90
[  285.364721]  </IRQ>
[  285.365072]  <TASK>
[  285.365422]  __local_bh_enable_ip+0x77/0x90
[  285.366079]  __dev_queue_xmit+0x95f/0x1550
[  285.366732]  ? __pfx_csum_and_copy_from_iter+0x10/0x10
[  285.367526]  ? __pfx___dev_queue_xmit+0x10/0x10
[  285.368259]  ? __build_skb_around+0x129/0x190
[  285.368960]  ? ip_generic_getfrag+0x12c/0x170
[  285.369653]  ? __pfx_ip_generic_getfrag+0x10/0x10
[  285.370390]  ? csum_partial+0x8/0x20
[  285.370961]  ? raw_getfrag+0xe5/0x140
[  285.371559]  ip_finish_output2+0x539/0xa40
[  285.372222]  ? __pfx_ip_finish_output2+0x10/0x10
[  285.372954]  ip_output+0x113/0x1e0
[  285.373512]  ? __pfx_ip_output+0x10/0x10
[  285.374130]  ? icmp_out_count+0x49/0x60
[  285.374739]  ? __pfx_ip_finish_output+0x10/0x10
[  285.375457]  ip_push_pending_frames+0xf3/0x100
[  285.376173]  raw_sendmsg+0xef5/0x12d0
[  285.376760]  ? do_syscall_64+0x40/0x90
[  285.377359]  ? __static_call_text_end+0x136578/0x136578
[  285.378173]  ? do_syscall_64+0x40/0x90
[  285.378772]  ? kasan_enable_current+0x11/0x20
[  285.379469]  ? __pfx_raw_sendmsg+0x10/0x10
[  285.380137]  ? __sock_create+0x13e/0x270
[  285.380673]  ? __sys_socket+0xf3/0x180
[  285.381174]  ? __x64_sys_socket+0x3d/0x50
[  285.381725]  ? entry_SYSCALL_64_after_hwframe+0x6e/0xd8
[  285.382425]  ? __rcu_read_unlock+0x48/0x70
[  285.382975]  ? ip4_datagram_release_cb+0xd8/0x380
[  285.383608]  ? __pfx_ip4_datagram_release_cb+0x10/0x10
[  285.384295]  ? preempt_count_sub+0x14/0xc0
[  285.384844]  ? __list_del_entry_valid+0x76/0x140
[  285.385467]  ? _raw_spin_lock_bh+0x87/0xe0
[  285.386014]  ? __pfx__raw_spin_lock_bh+0x10/0x10
[  285.386645]  ? release_sock+0xa0/0xd0
[  285.387148]  ? preempt_count_sub+0x14/0xc0
[  285.387712]  ? freeze_secondary_cpus+0x348/0x3c0
[  285.388341]  ? aa_sk_perm+0x177/0x390
[  285.388856]  ? __pfx_aa_sk_perm+0x10/0x10
[  285.389441]  ? check_stack_object+0x22/0x70
[  285.390032]  ? inet_send_prepare+0x2f/0x120
[  285.390603]  ? __pfx_inet_sendmsg+0x10/0x10
[  285.391172]  sock_sendmsg+0xcc/0xe0
[  285.391667]  __sys_sendto+0x190/0x230
[  285.392168]  ? __pfx___sys_sendto+0x10/0x10
[  285.392727]  ? kvm_clock_get_cycles+0x14/0x30
[  285.393328]  ? set_normalized_timespec64+0x57/0x70
[  285.393980]  ? _raw_spin_unlock_irq+0x1b/0x40
[  285.394578]  ? __x64_sys_clock_gettime+0x11c/0x160
[  285.395225]  ? __pfx___x64_sys_clock_gettime+0x10/0x10
[  285.395908]  ? _copy_to_user+0x3e/0x60
[  285.396432]  ? exit_to_user_mode_prepare+0x1a/0x120
[  285.397086]  ? syscall_exit_to_user_mode+0x22/0x50
[  285.397734]  ? do_syscall_64+0x71/0x90
[  285.398258]  __x64_sys_sendto+0x74/0x90
[  285.398786]  do_syscall_64+0x64/0x90
[  285.399273]  ? exit_to_user_mode_prepare+0x1a/0x120
[  285.399949]  ? syscall_exit_to_user_mode+0x22/0x50
[  285.400605]  ? do_syscall_64+0x71/0x90
[  285.401124]  entry_SYSCALL_64_after_hwframe+0x6e/0xd8
[  285.401807] RIP: 0033:0x495726
[  285.402233] Code: ff ff ff f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 11 b8 2c 00 00 00 0f 09
[  285.404683] RSP: 002b:00007ffcc25fb618 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
[  285.405677] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 0000000000495726
[  285.406628] RDX: 0000000000000040 RSI: 0000000002518750 RDI: 0000000000000000
[  285.407565] RBP: 00000000005205ef R08: 00000000005f8838 R09: 000000000000001c
[  285.408523] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000002517634
[  285.409460] R13: 00007ffcc25fb6f0 R14: 0000000000000003 R15: 0000000000000000
[  285.410403]  </TASK>
[  285.410704]
[  285.410929] Allocated by task 144:
[  285.411402]  kasan_save_stack+0x1e/0x40
[  285.411926]  kasan_set_track+0x21/0x30
[  285.412442]  __kasan_slab_alloc+0x55/0x70
[  285.412973]  kmem_cache_alloc_node+0x187/0x3d0
[  285.413567]  __alloc_skb+0x1b4/0x230
[  285.414060]  __ip_append_data+0x17f7/0x1b60
[  285.414633]  ip_append_data+0x97/0xf0
[  285.415144]  raw_sendmsg+0x5a8/0x12d0
[  285.415640]  sock_sendmsg+0xcc/0xe0
[  285.416117]  __sys_sendto+0x190/0x230
[  285.416626]  __x64_sys_sendto+0x74/0x90
[  285.417145]  do_syscall_64+0x64/0x90
[  285.417624]  entry_SYSCALL_64_after_hwframe+0x6e/0xd8
[  285.418306]
[  285.418531] Freed by task 144:
[  285.418960]  kasan_save_stack+0x1e/0x40
[  285.419469]  kasan_set_track+0x21/0x30
[  285.419988]  kasan_save_free_info+0x27/0x40
[  285.420556]  ____kasan_slab_free+0x109/0x1a0
[  285.421146]  kmem_cache_free+0x1c2/0x450
[  285.421680]  __netif_receive_skb_core+0x2ce/0x1870
[  285.422333]  __netif_receive_skb_one_core+0x97/0x140
[  285.423003]  process_backlog+0x100/0x2f0
[  285.423537]  __napi_poll+0x5c/0x2d0
[  285.424023]  net_rx_action+0x2be/0x560
[  285.424510]  __do_softirq+0x11b/0x3de
[  285.425034]
[  285.425254] The buggy address belongs to the object at ffff8880bad31280
[  285.425254]  which belongs to the cache skbuff_head_cache of size 224
[  285.426993] The buggy address is located 40 bytes inside of
[  285.426993]  freed 224-byte region [ffff8880bad31280, ffff8880bad31360)
[  285.428572]
[  285.428798] The buggy address belongs to the physical page:
[  285.429540] page:00000000f4b77674 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xbad31
[  285.430758] flags: 0x100000000000200(slab|node=0|zone=1)
[  285.431447] page_type: 0xffffffff()
[  285.431934] raw: 0100000000000200 ffff88810094a8c0 dead000000000122 0000000000000000
[  285.432757] raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000
[  285.433562] page dumped because: kasan: bad access detected
[  285.434144]
[  285.434320] Memory state around the buggy address:
[  285.434828]  ffff8880bad31180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  285.435580]  ffff8880bad31200: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  285.436264] >ffff8880bad31280: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  285.436777]                                   ^
[  285.437106]  ffff8880bad31300: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
[  285.437616]  ffff8880bad31380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  285.438126] ==================================================================
[  285.438662] Disabling lock debugging due to kernel taint

Fix this by:
1. Changing sch_plug's .peek handler to qdisc_peek_dequeued(), a function compatible with non-work-conserving qdiscs
2. Checking the return value of qdisc_dequeue_peeked() in sch_qfq.

Fixes 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost")
---
 net/sched/sch_plug.c |  2 +-
 net/sched/sch_qfq.c  | 22 +++++++++++++++++-----
 2 files changed, 18 insertions(+), 6 deletions(-)
net/sched/sch_plug.c +1 -1
index cbc2ebca4548c..339990bb59817 100644
@@ -210,7 +210,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = {
 	.priv_size   =       sizeof(struct plug_sched_data),
 	.enqueue     =       plug_enqueue,
 	.dequeue     =       plug_dequeue,
-	.peek        =       qdisc_peek_head,
+	.peek        =       qdisc_peek_dequeued,
 	.init        =       plug_init,
 	.change      =       plug_change,
 	.reset       =	     qdisc_reset_queue,
net/sched/sch_qfq.c +17 -5
index 905c86b50215e..b1dbe03dde1b5 100644
@@ -980,10 +980,13 @@ static void qfq_update_eligible(struct qfq_sched *q)
 }
 
 /* Dequeue head packet of the head class in the DRR queue of the aggregate. */
-static void agg_dequeue(struct qfq_aggregate *agg,
-			struct qfq_class *cl, unsigned int len)
+static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
+				   struct qfq_class *cl, unsigned int len)
 {
-	qdisc_dequeue_peeked(cl->qdisc);
+	struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc);
+
+	if (!skb)
+		return NULL;
 
 	cl->deficit -= (int) len;
 
@@ -993,6 +996,8 @@ static void agg_dequeue(struct qfq_aggregate *agg,
 		cl->deficit += agg->lmax;
 		list_move_tail(&cl->alist, &agg->active);
 	}
+
+	return skb;
 }
 
 static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg,
@@ -1138,11 +1143,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
 	if (!skb)
 		return NULL;
 
-	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;
+
+	skb = agg_dequeue(in_serv_agg, cl, len);
+
+	if (!skb) {
+		sch->q.qlen++;
+		return NULL;
+	}
+
+	qdisc_qstats_backlog_dec(sch, skb);
 	qdisc_bstats_update(sch, skb);
 
-	agg_dequeue(in_serv_agg, cl, len);
 	/* If lmax is lowered, through qfq_change_class, for a class
 	 * owning pending packets with larger size than the new value
 	 * of lmax, then the following condition may hold.
Signature · 1 line
2.40.1
author maintainer
#445 lore raw

PATCH 444/511 kcm: Destroy mutex in kcm_exit_net()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shigeru Yoshida <[email protected]>

[ Upstream commit 6ad40b36cd3b04209e2d6c89d252c873d8082a59 ]

kcm_exit_net() should call mutex_destroy() on knet->mutex. This is especially needed if CONFIG_DEBUG_MUTEXES is enabled.

Fixes ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
---
 net/kcm/kcmsock.c | 2 ++
 1 file changed, 2 insertions(+)
net/kcm/kcmsock.c +2 -0
index 9c60c0c18b4dd..43005bba2d407 100644
@@ -1982,6 +1982,8 @@ static __net_exit void kcm_exit_net(struct net *net)
 	 * that all multiplexors and psocks have been destroyed.
 	 */
 	WARN_ON(!list_empty(&knet->mux_list));
+
+	mutex_destroy(&knet->mutex);
 }
 
 static struct pernet_operations kcm_net_ops = {
Signature · 1 line
2.40.1
author maintainer
#446 lore raw

PATCH 445/511 octeontx2-af: Fix truncation of smq in CN10K NIX AQ enqueue mbox handler

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Geetha sowjanya <[email protected]>

[ Upstream commit 29fe7a1b62717d58f033009874554d99d71f7d37 ]

The smq value used in the CN10K NIX AQ instruction enqueue mailbox handler was truncated to 9-bit value from 10-bit value because of typecasting the CN10K mbox request structure to the CN9K structure. Though this hasn't caused any problems when programming the NIX SQ context to the HW because the context structure is the same size. However, this causes a problem when accessing the structure parameters. This patch reads the right smq value for each platform.

Fixes 30077d210c83 ("octeontx2-af: cn10k: Update NIX/NPA context structure")
---
 .../ethernet/marvell/octeontx2/af/rvu_nix.c   | 21 +++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)
drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +19 -2
index f5922d63e33e4..1593efc4502b5 100644
@@ -841,6 +841,21 @@ static int nix_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block,
 	return 0;
 }
 
+static void nix_get_aq_req_smq(struct rvu *rvu, struct nix_aq_enq_req *req,
+			       u16 *smq, u16 *smq_mask)
+{
+	struct nix_cn10k_aq_enq_req *aq_req;
+
+	if (!is_rvu_otx2(rvu)) {
+		aq_req = (struct nix_cn10k_aq_enq_req *)req;
+		*smq = aq_req->sq.smq;
+		*smq_mask = aq_req->sq_mask.smq;
+	} else {
+		*smq = req->sq.smq;
+		*smq_mask = req->sq_mask.smq;
+	}
+}
+
 static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 				   struct nix_aq_enq_req *req,
 				   struct nix_aq_enq_rsp *rsp)
@@ -852,6 +867,7 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 	struct rvu_block *block;
 	struct admin_queue *aq;
 	struct rvu_pfvf *pfvf;
+	u16 smq, smq_mask;
 	void *ctx, *mask;
 	bool ena;
 	u64 cfg;
@@ -923,13 +939,14 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 	if (rc)
 		return rc;
 
+	nix_get_aq_req_smq(rvu, req, &smq, &smq_mask);
 	/* Check if SQ pointed SMQ belongs to this PF/VF or not */
 	if (req->ctype == NIX_AQ_CTYPE_SQ &&
 	    ((req->op == NIX_AQ_INSTOP_INIT && req->sq.ena) ||
 	     (req->op == NIX_AQ_INSTOP_WRITE &&
-	      req->sq_mask.ena && req->sq_mask.smq && req->sq.ena))) {
+	      req->sq_mask.ena && req->sq.ena && smq_mask))) {
 		if (!is_valid_txschq(rvu, blkaddr, NIX_TXSCH_LVL_SMQ,
-				     pcifunc, req->sq.smq))
+				     pcifunc, smq))
 			return NIX_AF_ERR_AQ_ENQUEUE;
 	}
 
Signature · 1 line
2.40.1
author maintainer
#447 lore raw

PATCH 446/511 igc: Change IGC_MIN to allow set rx/tx value between 64 and 80

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Olga Zaborska <[email protected]>

[ Upstream commit 5aa48279712e1f134aac908acde4df798955a955 ]

Change the minimum value of RX/TX descriptors to 64 to enable setting the rx/tx value between 64 and 80. All igc devices can use as low as 64 descriptors. This change will unify igc with other drivers.
Based on commit 7b1be1987c1e ("e1000e: lower ring minimum size to 64")

Fixes 0507ef8a0372 ("igc: Add transmit and receive fastpath and interrupt handlers")
---
 drivers/net/ethernet/intel/igc/igc.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/intel/igc/igc.h +2 -2
index 192fee9e72b05..e09ca21b8e3fe 100644
@@ -359,11 +359,11 @@ static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc)
 /* TX/RX descriptor defines */
 #define IGC_DEFAULT_TXD		256
 #define IGC_DEFAULT_TX_WORK	128
-#define IGC_MIN_TXD		80
+#define IGC_MIN_TXD		64
 #define IGC_MAX_TXD		4096
 
 #define IGC_DEFAULT_RXD		256
-#define IGC_MIN_RXD		80
+#define IGC_MIN_RXD		64
 #define IGC_MAX_RXD		4096
 
 /* Supported Rx Buffer Sizes */
Signature · 1 line
2.40.1
author maintainer
#448 lore raw

PATCH 447/511 igbvf: Change IGBVF_MIN to allow set rx/tx value between 64 and 80

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Olga Zaborska <[email protected]>

[ Upstream commit 8360717524a24a421c36ef8eb512406dbd42160a ]

Change the minimum value of RX/TX descriptors to 64 to enable setting the rx/tx value between 64 and 80. All igbvf devices can use as low as 64 descriptors. This change will unify igbvf with other drivers.
Based on commit 7b1be1987c1e ("e1000e: lower ring minimum size to 64")

Fixes d4e0fe01a38a ("igbvf: add new driver to support 82576 virtual functions")
---
 drivers/net/ethernet/intel/igbvf/igbvf.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/intel/igbvf/igbvf.h +2 -2
index 975eb47ee04df..b39fca9827dc2 100644
@@ -39,11 +39,11 @@ enum latency_range {
 /* Tx/Rx descriptor defines */
 #define IGBVF_DEFAULT_TXD	256
 #define IGBVF_MAX_TXD		4096
-#define IGBVF_MIN_TXD		80
+#define IGBVF_MIN_TXD		64
 
 #define IGBVF_DEFAULT_RXD	256
 #define IGBVF_MAX_RXD		4096
-#define IGBVF_MIN_RXD		80
+#define IGBVF_MIN_RXD		64
 
 #define IGBVF_MIN_ITR_USECS	10 /* 100000 irq/sec */
 #define IGBVF_MAX_ITR_USECS	10000 /* 100    irq/sec */
Signature · 1 line
2.40.1
author maintainer
#449 lore raw

PATCH 448/511 igb: Change IGB_MIN to allow set rx/tx value between 64 and 80

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Olga Zaborska <[email protected]>

[ Upstream commit 6319685bdc8ad5310890add907b7c42f89302886 ]

Change the minimum value of RX/TX descriptors to 64 to enable setting the rx/tx value between 64 and 80. All igb devices can use as low as 64 descriptors. This change will unify igb with other drivers.
Based on commit 7b1be1987c1e ("e1000e: lower ring minimum size to 64")

Fixes 9d5c824399de ("igb: PCI-Express 82575 Gigabit Ethernet driver")
---
 drivers/net/ethernet/intel/igb/igb.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/intel/igb/igb.h +2 -2
index 015b781441149..a2b759531cb7b 100644
@@ -34,11 +34,11 @@ struct igb_adapter;
 /* TX/RX descriptor defines */
 #define IGB_DEFAULT_TXD		256
 #define IGB_DEFAULT_TX_WORK	128
-#define IGB_MIN_TXD		80
+#define IGB_MIN_TXD		64
 #define IGB_MAX_TXD		4096
 
 #define IGB_DEFAULT_RXD		256
-#define IGB_MIN_RXD		80
+#define IGB_MIN_RXD		64
 #define IGB_MAX_RXD		4096
 
 #define IGB_DEFAULT_ITR		3 /* dynamic */
Signature · 1 line
2.40.1
author maintainer
#450 lore raw

PATCH 449/511 s390/zcrypt: dont leak memory if dev_set_name() fails

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Shevchenko <[email protected]>

[ Upstream commit 6252f47b78031979ad919f971dc8468b893488bd ]

When dev_set_name() fails, zcdn_create() doesn't free the newly allocated resources. Do it.

Fixes 00fab2350e6b ("s390/zcrypt: multiple zcrypt device nodes support")
---
 drivers/s390/crypto/zcrypt_api.c | 1 +
 1 file changed, 1 insertion(+)
drivers/s390/crypto/zcrypt_api.c +1 -0
index 356318746dd16..17b3f1ea3a5c2 100644
@@ -398,6 +398,7 @@ static int zcdn_create(const char *name)
 			 ZCRYPT_NAME "_%d", (int) MINOR(devt));
 	nodename[sizeof(nodename)-1] = '\0';
 	if (dev_set_name(&zcdndev->device, nodename)) {
+		kfree(zcdndev);
 		rc = -EINVAL;
 		goto unlockout;
 	}
Signature · 1 line
2.40.1
author maintainer
#451 lore raw

PATCH 450/511 idr: fix param name in idr_alloc_cyclic() doc

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ariel Marcovitch <[email protected]>

[ Upstream commit 2a15de80dd0f7e04a823291aa9eb49c5294f56af ]

The relevant parameter is 'start' and not 'nextid'

Fixes 460488c58ca8 ("idr: Remove idr_alloc_ext")
---
 lib/idr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
lib/idr.c +1 -1
index 7ecdfdb5309e7..13f2758c23773 100644
@@ -100,7 +100,7 @@ EXPORT_SYMBOL_GPL(idr_alloc);
  * @end: The maximum ID (exclusive).
  * @gfp: Memory allocation flags.
  *
- * Allocates an unused ID in the range specified by @nextid and @end.  If
+ * Allocates an unused ID in the range specified by @start and @end.  If
  * @end is <= 0, it is treated as one larger than %INT_MAX.  This allows
  * callers to use @start + N as @end as long as N is within integer range.
  * The search for an unused ID will start at the last ID allocated and will
Signature · 1 line
2.40.1
author maintainer
#452 lore raw

PATCH 451/511 ip_tunnels: use DEV_STATS_INC()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 9b271ebaf9a2c5c566a54bc6cd915962e8241130 ]

syzbot/KCSAN reported data-races in iptunnel_xmit_stats() [1]

This can run from multiple cpus without mutual exclusion.

Adopt SMP safe DEV_STATS_INC() to update dev->stats fields.

[1]

BUG: KCSAN: data-race in iptunnel_xmit / iptunnel_xmit

read-write to 0xffff8881353df170 of 8 bytes by task 30263 on cpu 1:

iptunnel_xmit_stats include/net/ip_tunnels.h:493 [inline]
iptunnel_xmit+0x432/0x4a0 net/ipv4/ip_tunnel_core.c:87
ip_tunnel_xmit+0x1477/0x1750 net/ipv4/ip_tunnel.c:831
__gre_xmit net/ipv4/ip_gre.c:469 [inline]
ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:662
__netdev_start_xmit include/linux/netdevice.h:4889 [inline]
netdev_start_xmit include/linux/netdevice.h:4903 [inline]
xmit_one net/core/dev.c:3544 [inline]
dev_hard_start_xmit+0x11b/0x3f0 net/core/dev.c:3560
__dev_queue_xmit+0xeee/0x1de0 net/core/dev.c:4340
dev_queue_xmit include/linux/netdevice.h:3082 [inline]
__bpf_tx_skb net/core/filter.c:2129 [inline]
__bpf_redirect_no_mac net/core/filter.c:2159 [inline]
__bpf_redirect+0x723/0x9c0 net/core/filter.c:2182
____bpf_clone_redirect net/core/filter.c:2453 [inline]
bpf_clone_redirect+0x16c/0x1d0 net/core/filter.c:2425
___bpf_prog_run+0xd7d/0x41e0 kernel/bpf/core.c:1954
__bpf_prog_run512+0x74/0xa0 kernel/bpf/core.c:2195
bpf_dispatcher_nop_func include/linux/bpf.h:1181 [inline]
__bpf_prog_run include/linux/filter.h:609 [inline]
bpf_prog_run include/linux/filter.h:616 [inline]
bpf_test_run+0x15d/0x3d0 net/bpf/test_run.c:423
bpf_prog_test_run_skb+0x77b/0xa00 net/bpf/test_run.c:1045
bpf_prog_test_run+0x265/0x3d0 kernel/bpf/syscall.c:3996
__sys_bpf+0x3af/0x780 kernel/bpf/syscall.c:5353
__do_sys_bpf kernel/bpf/syscall.c:5439 [inline]
__se_sys_bpf kernel/bpf/syscall.c:5437 [inline]
__x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5437
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

read-write to 0xffff8881353df170 of 8 bytes by task 30249 on cpu 0:

iptunnel_xmit_stats include/net/ip_tunnels.h:493 [inline]
iptunnel_xmit+0x432/0x4a0 net/ipv4/ip_tunnel_core.c:87
ip_tunnel_xmit+0x1477/0x1750 net/ipv4/ip_tunnel.c:831
__gre_xmit net/ipv4/ip_gre.c:469 [inline]
ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:662
__netdev_start_xmit include/linux/netdevice.h:4889 [inline]
netdev_start_xmit include/linux/netdevice.h:4903 [inline]
xmit_one net/core/dev.c:3544 [inline]
dev_hard_start_xmit+0x11b/0x3f0 net/core/dev.c:3560
__dev_queue_xmit+0xeee/0x1de0 net/core/dev.c:4340
dev_queue_xmit include/linux/netdevice.h:3082 [inline]
__bpf_tx_skb net/core/filter.c:2129 [inline]
__bpf_redirect_no_mac net/core/filter.c:2159 [inline]
__bpf_redirect+0x723/0x9c0 net/core/filter.c:2182
____bpf_clone_redirect net/core/filter.c:2453 [inline]
bpf_clone_redirect+0x16c/0x1d0 net/core/filter.c:2425
___bpf_prog_run+0xd7d/0x41e0 kernel/bpf/core.c:1954
__bpf_prog_run512+0x74/0xa0 kernel/bpf/core.c:2195
bpf_dispatcher_nop_func include/linux/bpf.h:1181 [inline]
__bpf_prog_run include/linux/filter.h:609 [inline]
bpf_prog_run include/linux/filter.h:616 [inline]
bpf_test_run+0x15d/0x3d0 net/bpf/test_run.c:423
bpf_prog_test_run_skb+0x77b/0xa00 net/bpf/test_run.c:1045
bpf_prog_test_run+0x265/0x3d0 kernel/bpf/syscall.c:3996
__sys_bpf+0x3af/0x780 kernel/bpf/syscall.c:5353
__do_sys_bpf kernel/bpf/syscall.c:5439 [inline]
__se_sys_bpf kernel/bpf/syscall.c:5437 [inline]
__x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5437
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x0000000000018830 -> 0x0000000000018831

Reported by Kernel Concurrency Sanitizer on:

CPU: 0 PID: 30249 Comm: syz-executor.4 Not tainted 6.5.0-syzkaller-11704-g3f86ed6ec0b3 #0
Fixes 039f50629b7f ("ip_tunnel: Move stats update to iptunnel_xmit()")
---
 include/net/ip_tunnels.h | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)
include/net/ip_tunnels.h +7 -8
index 4eb0edc6640d9..17ec652e8f124 100644
@@ -454,15 +454,14 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
 		put_cpu_ptr(tstats);
+		return;
+	}
+
+	if (pkt_len < 0) {
+		DEV_STATS_INC(dev, tx_errors);
+		DEV_STATS_INC(dev, tx_aborted_errors);
 	} else {
-		struct net_device_stats *err_stats = &dev->stats;
-
-		if (pkt_len < 0) {
-			err_stats->tx_errors++;
-			err_stats->tx_aborted_errors++;
-		} else {
-			err_stats->tx_dropped++;
-		}
+		DEV_STATS_INC(dev, tx_dropped);
 	}
 }
 
Signature · 1 line
2.40.1
author maintainer
#453 lore raw

PATCH 452/511 net: dsa: sja1105: fix bandwidth discrepancy between tc-cbs software and offload

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vladimir Oltean <[email protected]>

[ Upstream commit 954ad9bf13c4f95a4958b5f8433301f2ab99e1f5 ]

More careful measurement of the tc-cbs bandwidth shows that the stream bandwidth (effectively idleslope) increases, there is a larger and larger discrepancy between the rate limit obtained by the software Qdisc, and the rate limit obtained by its offloaded counterpart.

The discrepancy becomes so large, that e.g. at an idleslope of 40000 (40Mbps), the offloaded cbs does not actually rate limit anything, and traffic will pass at line rate through a 100 Mbps port.

The reason for the discrepancy is that the hardware documentation I've been following is incorrect. UM11040.pdf (for SJA1105P/Q/R/S) states about IDLE_SLOPE that it is "the rate (in unit of bytes/sec) at which the credit counter is increased".

Cross-checking with UM10944.pdf (for SJA1105E/T) and UM11107.pdf (for SJA1110), the wording is different: "This field specifies the value, in bytes per second times link speed, by which the credit counter is increased".

So there's an extra scaling for link speed that the driver is currently not accounting for, and apparently (empirically), that link speed is expressed in Kbps.

I've pondered whether to pollute the sja1105_mac_link_up() implementation with CBS shaper reprogramming, but I don't think it is worth it. IMO, the UAPI exposed by tc-cbs requires user space to recalculate the sendslope anyway, since the formula for that depends on port_transmit_rate (see man tc-cbs), which is not an invariant from tc's perspective.

So we use the offload->sendslope and offload->idleslope to deduce the original port_transmit_rate from the CBS formula, and use that value to scale the offload->sendslope and offload->idleslope to values that the hardware understands.

Some numerical data points:

40Mbps stream, max interfering frame size 1500, port speed 100M
---------------------------------------------------------------

tc-cbs parameters:
idleslope 40000 sendslope -60000 locredit -900 hicredit 600

which result in hardware values:

 Before (doesn't work)           After (works)
 credit_hi    600                600
 credit_lo    900                900
 send_slope   7500000            75
 idle_slope   5000000            50

40Mbps stream, max interfering frame size 1500, port speed 1G
-------------------------------------------------------------

tc-cbs parameters:
idleslope 40000 sendslope -960000 locredit -1440 hicredit 60

which result in hardware values:

 Before (doesn't work)           After (works)
 credit_hi    60                 60
 credit_lo    1440               1440
 send_slope   120000000          120
 idle_slope   5000000            5

5.12Mbps stream, max interfering frame size 1522, port speed 100M
-----------------------------------------------------------------

tc-cbs parameters:
idleslope 5120 sendslope -94880 locredit -1444 hicredit 77

which result in hardware values:

 Before (doesn't work)           After (works)
 credit_hi    77                 77
 credit_lo    1444               1444
 send_slope   11860000           118
 idle_slope   640000             6

Tested on SJA1105T, SJA1105S and SJA1110A, at 1Gbps and 100Mbps.

Fixes 4d7525085a9b ("net: dsa: sja1105: offload the Credit-Based Shaper qdisc")
---
 drivers/net/dsa/sja1105/sja1105_main.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)
drivers/net/dsa/sja1105/sja1105_main.c +12 -3
index ef4d8d6c2bd7a..5f70773fa8201 100644
@@ -2049,6 +2049,7 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port,
 {
 	struct sja1105_private *priv = ds->priv;
 	struct sja1105_cbs_entry *cbs;
+	s64 port_transmit_rate_kbps;
 	int index;
 
 	if (!offload->enable)
@@ -2066,9 +2067,17 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port,
 	 */
 	cbs->credit_hi = offload->hicredit;
 	cbs->credit_lo = abs(offload->locredit);
-	/* User space is in kbits/sec, hardware in bytes/sec */
-	cbs->idle_slope = offload->idleslope * BYTES_PER_KBIT;
-	cbs->send_slope = abs(offload->sendslope * BYTES_PER_KBIT);
+	/* User space is in kbits/sec, while the hardware in bytes/sec times
+	 * link speed. Since the given offload->sendslope is good only for the
+	 * current link speed anyway, and user space is likely to reprogram it
+	 * when that changes, don't even bother to track the port's link speed,
+	 * but deduce the port transmit rate from idleslope - sendslope.
+	 */
+	port_transmit_rate_kbps = offload->idleslope - offload->sendslope;
+	cbs->idle_slope = div_s64(offload->idleslope * BYTES_PER_KBIT,
+				  port_transmit_rate_kbps);
+	cbs->send_slope = div_s64(abs(offload->sendslope * BYTES_PER_KBIT),
+				  port_transmit_rate_kbps);
 	/* Convert the negative values from 64-bit 2's complement
 	 * to 32-bit 2's complement (for the case of 0x80000000 whose
 	 * negative is still negative).
Signature · 1 line
2.40.1
author maintainer
#454 lore raw

PATCH 453/511 net: dsa: sja1105: fix -ENOSPC when replacing the same tc-cbs too many times

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vladimir Oltean <[email protected]>

[ Upstream commit 894cafc5c62ccced758077bd4e970dc714c42637 ]

After running command [2] too many times in a row:

[1] $ tc qdisc add dev sw2p0 root handle 1: mqprio num_tc 8 \
	map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 hw 0
[2] $ tc qdisc replace dev sw2p0 parent 1:1 cbs offload 1 \
	idleslope 120000 sendslope -880000 locredit -1320 hicredit 180

(aka more than priv->info->num_cbs_shapers times)

we start seeing the following error message:

Error: Specified device failed to setup cbs hardware offload.

This comes from the fact that ndo_setup_tc(TC_SETUP_QDISC_CBS) presents the same API for the qdisc create and replace cases, and the sja1105 driver fails to distinguish between the 2. Thus, it always thinks that it must allocate the same shaper for a {port, queue} pair, when it may instead have to replace an existing one.

Fixes 4d7525085a9b ("net: dsa: sja1105: offload the Credit-Based Shaper qdisc")
---
 drivers/net/dsa/sja1105/sja1105_main.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)
drivers/net/dsa/sja1105/sja1105_main.c +20 -3
index 5f70773fa8201..9176bd78b3d61 100644
@@ -2015,6 +2015,18 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port,
 
 #define BYTES_PER_KBIT (1000LL / 8)
 
+static int sja1105_find_cbs_shaper(struct sja1105_private *priv,
+				   int port, int prio)
+{
+	int i;
+
+	for (i = 0; i < priv->info->num_cbs_shapers; i++)
+		if (priv->cbs[i].port == port && priv->cbs[i].prio == prio)
+			return i;
+
+	return -1;
+}
+
 static int sja1105_find_unused_cbs_shaper(struct sja1105_private *priv)
 {
 	int i;
@@ -2055,9 +2067,14 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port,
 	if (!offload->enable)
 		return sja1105_delete_cbs_shaper(priv, port, offload->queue);
 
-	index = sja1105_find_unused_cbs_shaper(priv);
-	if (index < 0)
-		return -ENOSPC;
+	/* The user may be replacing an existing shaper */
+	index = sja1105_find_cbs_shaper(priv, port, offload->queue);
+	if (index < 0) {
+		/* That isn't the case - see if we can allocate a new one */
+		index = sja1105_find_unused_cbs_shaper(priv);
+		if (index < 0)
+			return -ENOSPC;
+	}
 
 	cbs = &priv->cbs[index];
 	cbs->port = port;
Signature · 1 line
2.40.1
author maintainer
#455 lore raw

PATCH 454/511 net: dsa: sja1105: complete tc-cbs offload support on SJA1110

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vladimir Oltean <[email protected]>

[ Upstream commit 180a7419fe4adc8d9c8e0ef0fd17bcdd0cf78acd ]

The blamed commit left this delta behind:

struct sja1105_cbs_entry {
- u64 port;
- u64 prio;
+ u64 port; /* Not used for SJA1110 */
+ u64 prio; /* Not used for SJA1110 */
u64 credit_hi;
u64 credit_lo;
u64 send_slope;
u64 idle_slope;
};

but did not actually implement tc-cbs offload fully for the new switch. The offload is accepted, but it doesn't work.

The difference compared to earlier switch generations is that now, the table of CBS shapers is sparse, because there are many more shapers, so the mapping between a {port, prio} and a table index is static, rather than requiring us to store the port and prio into the sja1105_cbs_entry.

So, the problem is that the code programs the CBS shaper parameters at a dynamic table index which is incorrect.

All that needs to be done for SJA1110 CBS shapers to work is to bypass the logic which allocates shapers in a dense manner, as for SJA1105, and use the fixed mapping instead.

Fixes 3e77e59bf8cf ("net: dsa: sja1105: add support for the SJA1110 switch family")
---
 drivers/net/dsa/sja1105/sja1105.h      |  2 ++
 drivers/net/dsa/sja1105/sja1105_main.c | 13 +++++++++++++
 drivers/net/dsa/sja1105/sja1105_spi.c  |  4 ++++
 3 files changed, 19 insertions(+)
drivers/net/dsa/sja1105/sja1105.h +2 -0
index 5e5d24e7c02b2..548d585256fbb 100644
@@ -111,6 +111,8 @@ struct sja1105_info {
 	int max_frame_mem;
 	int num_ports;
 	bool multiple_cascade_ports;
+	/* Every {port, TXQ} has its own CBS shaper */
+	bool fixed_cbs_mapping;
 	enum dsa_tag_protocol tag_proto;
 	const struct sja1105_dynamic_table_ops *dyn_ops;
 	const struct sja1105_table_ops *static_ops;
drivers/net/dsa/sja1105/sja1105_main.c +13 -0
index 9176bd78b3d61..d5600d0d6ef10 100644
@@ -2014,12 +2014,22 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port,
 }
 
 #define BYTES_PER_KBIT (1000LL / 8)
+/* Port 0 (the uC port) does not have CBS shapers */
+#define SJA1110_FIXED_CBS(port, prio) ((((port) - 1) * SJA1105_NUM_TC) + (prio))
 
 static int sja1105_find_cbs_shaper(struct sja1105_private *priv,
 				   int port, int prio)
 {
 	int i;
 
+	if (priv->info->fixed_cbs_mapping) {
+		i = SJA1110_FIXED_CBS(port, prio);
+		if (i >= 0 && i < priv->info->num_cbs_shapers)
+			return i;
+
+		return -1;
+	}
+
 	for (i = 0; i < priv->info->num_cbs_shapers; i++)
 		if (priv->cbs[i].port == port && priv->cbs[i].prio == prio)
 			return i;
@@ -2031,6 +2041,9 @@ static int sja1105_find_unused_cbs_shaper(struct sja1105_private *priv)
 {
 	int i;
 
+	if (priv->info->fixed_cbs_mapping)
+		return -1;
+
 	for (i = 0; i < priv->info->num_cbs_shapers; i++)
 		if (!priv->cbs[i].idle_slope && !priv->cbs[i].send_slope)
 			return i;
drivers/net/dsa/sja1105/sja1105_spi.c +4 -0
index d3c9ad6d39d46..e6b61aef4127c 100644
@@ -781,6 +781,7 @@ const struct sja1105_info sja1110a_info = {
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
+	.fixed_cbs_mapping	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
 	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
@@ -831,6 +832,7 @@ const struct sja1105_info sja1110b_info = {
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
+	.fixed_cbs_mapping	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
 	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
@@ -881,6 +883,7 @@ const struct sja1105_info sja1110c_info = {
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
+	.fixed_cbs_mapping	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
 	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
@@ -931,6 +934,7 @@ const struct sja1105_info sja1110d_info = {
 	.tag_proto		= DSA_TAG_PROTO_SJA1110,
 	.can_limit_mcast_flood	= true,
 	.multiple_cascade_ports	= true,
+	.fixed_cbs_mapping	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
 	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
Signature · 1 line
2.40.1
author maintainer
#456 lore raw

PATCH 455/511 netfilter: nftables: exthdr: fix 4-byte stack OOB write

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Westphal <[email protected]>

[ Upstream commit fd94d9dadee58e09b49075240fe83423eb1dcd36 ]

If priv->len is a multiple of 4, then dst[len / 4] can write past the destination array which leads to stack corruption.

This construct is necessary to clean the remainder of the register in case ->len is NOT a multiple of the register size, so make it conditional just like nft_payload.c does.

The bug was added in 4.1 cycle and then copied/inherited when tcp/sctp and ip option support was added.

Bug reported by Zero Day Initiative project (ZDI-CAN-21950, ZDI-CAN-21951, ZDI-CAN-21961).

Fixes 49499c3e6e18 ("netfilter: nf_tables: switch registers to 32 bit addressing")
Fixes 935b7f643018 ("netfilter: nft_exthdr: add TCP option matching")
Fixes 133dc203d77d ("netfilter: nft_exthdr: Support SCTP chunks")
Fixes dbb5281a1f84 ("netfilter: nf_tables: add support for matching IPv4 options")
---
 net/netfilter/nft_exthdr.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)
net/netfilter/nft_exthdr.c +14 -8
index 9e927ab4df151..3609680831a14 100644
@@ -35,6 +35,14 @@ static unsigned int optlen(const u8 *opt, unsigned int offset)
 		return opt[offset + 1];
 }
 
+static int nft_skb_copy_to_reg(const struct sk_buff *skb, int offset, u32 *dest, unsigned int len)
+{
+	if (len % NFT_REG32_SIZE)
+		dest[len / NFT_REG32_SIZE] = 0;
+
+	return skb_copy_bits(skb, offset, dest, len);
+}
+
 static void nft_exthdr_ipv6_eval(const struct nft_expr *expr,
 				 struct nft_regs *regs,
 				 const struct nft_pktinfo *pkt)
@@ -56,8 +64,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr,
 	}
 	offset += priv->offset;
 
-	dest[priv->len / NFT_REG32_SIZE] = 0;
-	if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0)
+	if (nft_skb_copy_to_reg(pkt->skb, offset, dest, priv->len) < 0)
 		goto err;
 	return;
 err:
@@ -153,8 +160,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr,
 	}
 	offset += priv->offset;
 
-	dest[priv->len / NFT_REG32_SIZE] = 0;
-	if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0)
+	if (nft_skb_copy_to_reg(pkt->skb, offset, dest, priv->len) < 0)
 		goto err;
 	return;
 err:
@@ -210,7 +216,8 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr,
 		if (priv->flags & NFT_EXTHDR_F_PRESENT) {
 			*dest = 1;
 		} else {
-			dest[priv->len / NFT_REG32_SIZE] = 0;
+			if (priv->len % NFT_REG32_SIZE)
+				dest[priv->len / NFT_REG32_SIZE] = 0;
 			memcpy(dest, opt + offset, priv->len);
 		}
 
@@ -335,9 +342,8 @@ static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
 			    offset + ntohs(sch->length) > pkt->skb->len)
 				break;
 
-			dest[priv->len / NFT_REG32_SIZE] = 0;
-			if (skb_copy_bits(pkt->skb, offset + priv->offset,
-					  dest, priv->len) < 0)
+			if (nft_skb_copy_to_reg(pkt->skb, offset + priv->offset,
+						dest, priv->len) < 0)
 				break;
 			return;
 		}
Signature · 1 line
2.40.1
author maintainer
#457 lore raw

PATCH 456/511 netfilter: nfnetlink_osf: avoid OOB read

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wander Lairson Costa <[email protected]>

[ Upstream commit f4f8a7803119005e87b716874bec07c751efafec ]

The opt_num field is controlled by user mode and is not currently validated inside the kernel. An attacker can take advantage of this to trigger an OOB read and potentially leak information.

BUG: KASAN: slab-out-of-bounds in nf_osf_match_one+0xbed/0xd10 net/netfilter/nfnetlink_osf.c:88
Read of size 2 at addr ffff88804bc64272 by task poc/6431

CPU: 1 PID: 6431 Comm: poc Not tainted 6.0.0-rc4 #1
Call Trace:
 nf_osf_match_one+0xbed/0xd10 net/netfilter/nfnetlink_osf.c:88
 nf_osf_find+0x186/0x2f0 net/netfilter/nfnetlink_osf.c:281
 nft_osf_eval+0x37f/0x590 net/netfilter/nft_osf.c:47
 expr_call_ops_eval net/netfilter/nf_tables_core.c:214
 nft_do_chain+0x2b0/0x1490 net/netfilter/nf_tables_core.c:264
 nft_do_chain_ipv4+0x17c/0x1f0 net/netfilter/nft_chain_filter.c:23
 [..]

Also add validation to genre, subtype and version fields.

Fixes 11eeef41d5f6 ("netfilter: passive OS fingerprint xtables match")
---
 net/netfilter/nfnetlink_osf.c | 8 ++++++++
 1 file changed, 8 insertions(+)
net/netfilter/nfnetlink_osf.c +8 -0
index 8f1bfa6ccc2d9..50723ba082890 100644
@@ -315,6 +315,14 @@ static int nfnl_osf_add_callback(struct sk_buff *skb,
 
 	f = nla_data(osf_attrs[OSF_ATTR_FINGER]);
 
+	if (f->opt_num > ARRAY_SIZE(f->opt))
+		return -EINVAL;
+
+	if (!memchr(f->genre, 0, MAXGENRELEN) ||
+	    !memchr(f->subtype, 0, MAXGENRELEN) ||
+	    !memchr(f->version, 0, MAXGENRELEN))
+		return -EINVAL;
+
 	kf = kmalloc(sizeof(struct nf_osf_finger), GFP_KERNEL);
 	if (!kf)
 		return -ENOMEM;
Signature · 1 line
2.40.1
author maintainer
#458 lore raw

PATCH 457/511 net: hns3: fix byte order conversion issue in hclge_dbg_fd_tcam_read()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hao Chen <[email protected]>

[ Upstream commit efccf655e99b6907ca07a466924e91805892e7d3 ]

req1->tcam_data is defined as "u8 tcam_data[8]", and we convert it as (u32 *) without considerring byte order conversion,
it may result in printing wrong data for tcam_data.

Convert tcam_data to (__le32 *) first to fix it.

Fixes b5a0b70d77b9 ("net: hns3: refactor dump fd tcam of debugfs")
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +7 -7
index dd8b73aebe6a5..63665e8a7c718 100644
@@ -1450,7 +1450,7 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x,
 	struct hclge_desc desc[3];
 	int pos = 0;
 	int ret, i;
-	u32 *req;
+	__le32 *req;
 
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_FD_TCAM_OP, true);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
@@ -1475,22 +1475,22 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x,
 			 tcam_msg.loc);
 
 	/* tcam_data0 ~ tcam_data1 */
-	req = (u32 *)req1->tcam_data;
+	req = (__le32 *)req1->tcam_data;
 	for (i = 0; i < 2; i++)
 		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
-				 "%08x\n", *req++);
+				 "%08x\n", le32_to_cpu(*req++));
 
 	/* tcam_data2 ~ tcam_data7 */
-	req = (u32 *)req2->tcam_data;
+	req = (__le32 *)req2->tcam_data;
 	for (i = 0; i < 6; i++)
 		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
-				 "%08x\n", *req++);
+				 "%08x\n", le32_to_cpu(*req++));
 
 	/* tcam_data8 ~ tcam_data12 */
-	req = (u32 *)req3->tcam_data;
+	req = (__le32 *)req3->tcam_data;
 	for (i = 0; i < 5; i++)
 		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
-				 "%08x\n", *req++);
+				 "%08x\n", le32_to_cpu(*req++));
 
 	return ret;
 }
Signature · 1 line
2.40.1
author maintainer
#459 lore raw

PATCH 458/511 net: hns3: fix debugfs concurrency issue between kfree buffer and read

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hao Chen <[email protected]>

[ Upstream commit c295160b1d95e885f1af4586a221cb221d232d10 ]

Now in hns3_dbg_uninit(), there may be concurrency between kfree buffer and read, it may result in memory error.

Moving debugfs_remove_recursive() in front of kfree buffer to ensure they don't happen at the same time.

Fixes 5e69ea7ee2a6 ("net: hns3: refactor the debugfs process")
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +4 -3
index 3158c08a3aa9c..45f245b1d331c 100644
@@ -1171,9 +1171,9 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 	return 0;
 
 out:
-	mutex_destroy(&handle->dbgfs_lock);
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
+	mutex_destroy(&handle->dbgfs_lock);
 	return ret;
 }
 
@@ -1181,6 +1181,9 @@ void hns3_dbg_uninit(struct hnae3_handle *handle)
 {
 	u32 i;
 
+	debugfs_remove_recursive(handle->hnae3_dbgfs);
+	handle->hnae3_dbgfs = NULL;
+
 	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++)
 		if (handle->dbgfs_buf[i]) {
 			kvfree(handle->dbgfs_buf[i]);
@@ -1188,8 +1191,6 @@ void hns3_dbg_uninit(struct hnae3_handle *handle)
 		}
 
 	mutex_destroy(&handle->dbgfs_lock);
-	debugfs_remove_recursive(handle->hnae3_dbgfs);
-	handle->hnae3_dbgfs = NULL;
 }
 
 void hns3_dbg_register_debugfs(const char *debugfs_dir_name)
Signature · 1 line
2.40.1
author maintainer
#460 lore raw

PATCH 459/511 net: hns3: fix invalid mutex between tc qdisc and dcb ets command issue

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jijie Shao <[email protected]>

[ Upstream commit fa5564945f7d15ae2390b00c08b6abaef0165cda ]

We hope that tc qdisc and dcb ets commands can not be used crosswise. If we want to use any of the commands to configure tc,
We must use the other command to clear the existing configuration.

However, when we configure a single tc with tc qdisc, we can still configure it with dcb ets.
Because we use mqprio_active as the tag of tc qdisc configuration, but with dcb ets, we do not check mqprio_active.

This patch fix this issue by check mqprio_active before executing the dcb ets command. and add dcb_ets_active to replace HCLGE_FLAG_DCB_ENABLE and HCLGE_FLAG_MQPRIO_ENABLE at the hclge layer,

Fixes cacde272dd00 ("net: hns3: Add hclge_dcb module for the support of DCB feature")
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h   |  1 +
 .../hisilicon/hns3/hns3pf/hclge_dcb.c         | 20 +++++--------------
 .../hisilicon/hns3/hns3pf/hclge_main.c        |  5 +++--
 .../hisilicon/hns3/hns3pf/hclge_main.h        |  2 --
 4 files changed, 9 insertions(+), 19 deletions(-)
drivers/net/ethernet/hisilicon/hns3/hnae3.h +1 -0
index 9204f5ecd4151..695e299f534d5 100644
@@ -757,6 +757,7 @@ struct hnae3_tc_info {
 	u16 tqp_offset[HNAE3_MAX_TC];
 	u8 num_tc; /* Total number of enabled TCs */
 	bool mqprio_active;
+	bool dcb_ets_active;
 };
 
 struct hnae3_knic_private_info {
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +5 -15
index 87640a2e1794b..a15f2ed268a8d 100644
@@ -251,7 +251,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
 	int ret;
 
 	if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
-	    hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+	    h->kinfo.tc_info.mqprio_active)
 		return -EINVAL;
 
 	ret = hclge_ets_validate(hdev, ets, &num_tc, &map_changed);
@@ -267,10 +267,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
 	}
 
 	hclge_tm_schd_info_update(hdev, num_tc);
-	if (num_tc > 1)
-		hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
-	else
-		hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
+	h->kinfo.tc_info.dcb_ets_active = num_tc > 1;
 
 	ret = hclge_ieee_ets_to_tm_info(hdev, ets);
 	if (ret)
@@ -376,7 +373,7 @@ static u8 hclge_getdcbx(struct hnae3_handle *h)
 	struct hclge_vport *vport = hclge_get_vport(h);
 	struct hclge_dev *hdev = vport->back;
 
-	if (hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+	if (h->kinfo.tc_info.mqprio_active)
 		return 0;
 
 	return hdev->dcbx_cap;
@@ -500,7 +497,8 @@ static int hclge_setup_tc(struct hnae3_handle *h,
 	if (!test_bit(HCLGE_STATE_NIC_REGISTERED, &hdev->state))
 		return -EBUSY;
 
-	if (hdev->flag & HCLGE_FLAG_DCB_ENABLE)
+	kinfo = &vport->nic.kinfo;
+	if (kinfo->tc_info.dcb_ets_active)
 		return -EINVAL;
 
 	ret = hclge_mqprio_qopt_check(hdev, mqprio_qopt);
@@ -514,7 +512,6 @@ static int hclge_setup_tc(struct hnae3_handle *h,
 	if (ret)
 		return ret;
 
-	kinfo = &vport->nic.kinfo;
 	memcpy(&old_tc_info, &kinfo->tc_info, sizeof(old_tc_info));
 	hclge_sync_mqprio_qopt(&kinfo->tc_info, mqprio_qopt);
 	kinfo->tc_info.mqprio_active = tc > 0;
@@ -523,13 +520,6 @@ static int hclge_setup_tc(struct hnae3_handle *h,
 	if (ret)
 		goto err_out;
 
-	hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
-
-	if (tc > 1)
-		hdev->flag |= HCLGE_FLAG_MQPRIO_ENABLE;
-	else
-		hdev->flag &= ~HCLGE_FLAG_MQPRIO_ENABLE;
-
 	return hclge_notify_init_up(hdev);
 
 err_out:
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +3 -2
index 1d424b1ee6cd3..a415760505ab4 100644
@@ -11187,6 +11187,7 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle,
 
 static void hclge_info_show(struct hclge_dev *hdev)
 {
+	struct hnae3_handle *handle = &hdev->vport->nic;
 	struct device *dev = &hdev->pdev->dev;
 
 	dev_info(dev, "PF info begin:\n");
@@ -11203,9 +11204,9 @@ static void hclge_info_show(struct hclge_dev *hdev)
 	dev_info(dev, "This is %s PF\n",
 		 hdev->flag & HCLGE_FLAG_MAIN ? "main" : "not main");
 	dev_info(dev, "DCB %s\n",
-		 hdev->flag & HCLGE_FLAG_DCB_ENABLE ? "enable" : "disable");
+		 handle->kinfo.tc_info.dcb_ets_active ? "enable" : "disable");
 	dev_info(dev, "MQPRIO %s\n",
-		 hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE ? "enable" : "disable");
+		 handle->kinfo.tc_info.mqprio_active ? "enable" : "disable");
 	dev_info(dev, "Default tx spare buffer size: %u\n",
 		 hdev->tx_spare_buf_size);
 
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +0 -2
index 4d6dbfe0be7a2..a716027df0ed1 100644
@@ -902,8 +902,6 @@ struct hclge_dev {
 
 #define HCLGE_FLAG_MAIN			BIT(0)
 #define HCLGE_FLAG_DCB_CAPABLE		BIT(1)
-#define HCLGE_FLAG_DCB_ENABLE		BIT(2)
-#define HCLGE_FLAG_MQPRIO_ENABLE	BIT(3)
 	u32 flag;
 
 	u32 pkt_buf_size; /* Total pf buf size for tx/rx */
Signature · 1 line
2.40.1
author maintainer
#461 lore raw

PATCH 460/511 net: hns3: fix the port information display when sfp is absent

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yisen Zhuang <[email protected]>

[ Upstream commit 674d9591a32d01df75d6b5fffed4ef942a294376 ]

When sfp is absent or unidentified, the port type should be displayed as PORT_OTHERS, rather than PORT_FIBRE.

Fixes 88d10bd6f730 ("net: hns3: add support for multiple media type")
---
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +3 -1
index 526fb56c84f24..17fa4e7684cd2 100644
@@ -739,7 +739,9 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
 		hns3_get_ksettings(h, cmd);
 		break;
 	case HNAE3_MEDIA_TYPE_FIBER:
-		if (module_type == HNAE3_MODULE_TYPE_CR)
+		if (module_type == HNAE3_MODULE_TYPE_UNKNOWN)
+			cmd->base.port = PORT_OTHER;
+		else if (module_type == HNAE3_MODULE_TYPE_CR)
 			cmd->base.port = PORT_DA;
 		else
 			cmd->base.port = PORT_FIBRE;
Signature · 1 line
2.40.1
author maintainer
#462 lore raw

PATCH 461/511 net: hns3: remove GSO partial feature bit

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jie Wang <[email protected]>

[ Upstream commit 60326634f6c54528778de18bfef1e8a7a93b3771 ]

HNS3 NIC does not support GSO partial packets segmentation. Actually tunnel packets for example NvGRE packets segment offload and checksum offload is already supported. There is no need to keep gso partial feature bit. So this patch removes it.

Fixes 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC")
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 --
 1 file changed, 2 deletions(-)
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +0 -2
index 2acf50ed6025a..3693ff55197dd 100644
@@ -3118,8 +3118,6 @@ static void hns3_set_default_feature(struct net_device *netdev)
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
-	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
-
 	netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
 		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
 		NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
Signature · 1 line
2.40.1
author maintainer
#463 lore raw

PATCH 462/511 sh: boards: Fix CEU buffer size passed to dma_declare_coherent_memory()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Petr Tesarik <[email protected]>

[ Upstream commit fb60211f377b69acffead3147578f86d0092a7a5 ]

In all these cases, the last argument to dma_declare_coherent_memory() is the buffer end address, but the expected value should be the size of the reserved region.

Fixes 39fb993038e1 ("media: arch: sh: ap325rxa: Use new renesas-ceu camera driver")
Fixes c2f9b05fd5c1 ("media: arch: sh: ecovec: Use new renesas-ceu camera driver")
Fixes f3590dc32974 ("media: arch: sh: kfr2r09: Use new renesas-ceu camera driver")
Fixes 186c446f4b84 ("media: arch: sh: migor: Use new renesas-ceu camera driver")
Fixes 1a3c230b4151 ("media: arch: sh: ms7724se: Use new renesas-ceu camera driver")
---
 arch/sh/boards/mach-ap325rxa/setup.c | 2 +-
 arch/sh/boards/mach-ecovec24/setup.c | 6 ++----
 arch/sh/boards/mach-kfr2r09/setup.c  | 2 +-
 arch/sh/boards/mach-migor/setup.c    | 2 +-
 arch/sh/boards/mach-se/7724/setup.c  | 6 ++----
 5 files changed, 7 insertions(+), 11 deletions(-)
arch/sh/boards/mach-ap325rxa/setup.c +1 -1
index bac8a058ebd7c..05bd42dde107b 100644
@@ -530,7 +530,7 @@ static int __init ap325rxa_devices_setup(void)
 	device_initialize(&ap325rxa_ceu_device.dev);
 	dma_declare_coherent_memory(&ap325rxa_ceu_device.dev,
 			ceu_dma_membase, ceu_dma_membase,
-			ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1);
+			CEU_BUFFER_MEMORY_SIZE);
 
 	platform_device_add(&ap325rxa_ceu_device);
 
arch/sh/boards/mach-ecovec24/setup.c +2 -4
index bab91a99124e1..9730a992dab33 100644
@@ -1454,15 +1454,13 @@ static int __init arch_setup(void)
 	device_initialize(&ecovec_ceu_devices[0]->dev);
 	dma_declare_coherent_memory(&ecovec_ceu_devices[0]->dev,
 				    ceu0_dma_membase, ceu0_dma_membase,
-				    ceu0_dma_membase +
-				    CEU_BUFFER_MEMORY_SIZE - 1);
+				    CEU_BUFFER_MEMORY_SIZE);
 	platform_device_add(ecovec_ceu_devices[0]);
 
 	device_initialize(&ecovec_ceu_devices[1]->dev);
 	dma_declare_coherent_memory(&ecovec_ceu_devices[1]->dev,
 				    ceu1_dma_membase, ceu1_dma_membase,
-				    ceu1_dma_membase +
-				    CEU_BUFFER_MEMORY_SIZE - 1);
+				    CEU_BUFFER_MEMORY_SIZE);
 	platform_device_add(ecovec_ceu_devices[1]);
 
 	gpiod_add_lookup_table(&cn12_power_gpiod_table);
arch/sh/boards/mach-kfr2r09/setup.c +1 -1
index eeb5ce341efdd..4a1caa3e7cf5a 100644
@@ -603,7 +603,7 @@ static int __init kfr2r09_devices_setup(void)
 	device_initialize(&kfr2r09_ceu_device.dev);
 	dma_declare_coherent_memory(&kfr2r09_ceu_device.dev,
 			ceu_dma_membase, ceu_dma_membase,
-			ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1);
+			CEU_BUFFER_MEMORY_SIZE);
 
 	platform_device_add(&kfr2r09_ceu_device);
 
arch/sh/boards/mach-migor/setup.c +1 -1
index 6703a2122c0d6..bd4ccd9f8dd06 100644
@@ -604,7 +604,7 @@ static int __init migor_devices_setup(void)
 	device_initialize(&migor_ceu_device.dev);
 	dma_declare_coherent_memory(&migor_ceu_device.dev,
 			ceu_dma_membase, ceu_dma_membase,
-			ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1);
+			CEU_BUFFER_MEMORY_SIZE);
 
 	platform_device_add(&migor_ceu_device);
 
arch/sh/boards/mach-se/7724/setup.c +2 -4
index 8d6541ba01865..edc7712e4a804 100644
@@ -940,15 +940,13 @@ static int __init devices_setup(void)
 	device_initialize(&ms7724se_ceu_devices[0]->dev);
 	dma_declare_coherent_memory(&ms7724se_ceu_devices[0]->dev,
 				    ceu0_dma_membase, ceu0_dma_membase,
-				    ceu0_dma_membase +
-				    CEU_BUFFER_MEMORY_SIZE - 1);
+				    CEU_BUFFER_MEMORY_SIZE);
 	platform_device_add(ms7724se_ceu_devices[0]);
 
 	device_initialize(&ms7724se_ceu_devices[1]->dev);
 	dma_declare_coherent_memory(&ms7724se_ceu_devices[1]->dev,
 				    ceu1_dma_membase, ceu1_dma_membase,
-				    ceu1_dma_membase +
-				    CEU_BUFFER_MEMORY_SIZE - 1);
+				    CEU_BUFFER_MEMORY_SIZE);
 	platform_device_add(ms7724se_ceu_devices[1]);
 
 	return platform_add_devices(ms7724se_devices,
Signature · 1 line
2.40.1
author maintainer
#464 lore raw

PATCH 463/511 net/mlx5: Free IRQ rmap and notifier on kernel shutdown

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Saeed Mahameed <[email protected]>

commit 314ded538e5f22e7610b1bf621402024a180ec80 upstream.

The kernel IRQ system needs the irq affinity notifier to be clear before attempting to free the irq, see WARN_ON log below.

On a normal driver unload we don't have this issue since we do the complete cleanup of the irq resources.

To fix this, put the important resources cleanup in a helper function and use it in both normal driver unload and shutdown flows.

[ 4497.498434] ------------[ cut here ]------------
[ 4497.498726] WARNING: CPU: 0 PID: 9 at kernel/irq/manage.c:2034 free_irq+0x295/0x340
[ 4497.499193] Modules linked in:
[ 4497.499386] CPU: 0 PID: 9 Comm: kworker/0:1 Tainted: G        W          6.4.0-rc4+ #10
[ 4497.499876] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-1.fc38 04/01/2014
[ 4497.500518] Workqueue: events do_poweroff
[ 4497.500849] RIP: 0010:free_irq+0x295/0x340
[ 4497.501132] Code: 85 c0 0f 84 1d ff ff ff 48 89 ef ff d0 0f 1f 00 e9 10 ff ff ff 0f 0b e9 72 ff ff ff 49 8d 7f 28 ff d0 0f 1f 00 e9 df fd ff ff <0f> 0b 48 c7 80 c0 008
[ 4497.502269] RSP: 0018:ffffc90000053da0 EFLAGS: 00010282
[ 4497.502589] RAX: ffff888100949600 RBX: ffff88810330b948 RCX: 0000000000000000
[ 4497.503035] RDX: ffff888100949600 RSI: ffff888100400490 RDI: 0000000000000023
[ 4497.503472] RBP: ffff88810330c7e0 R08: ffff8881004005d0 R09: ffffffff8273a260
[ 4497.503923] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8881009ae000
[ 4497.504359] R13: ffff8881009ae148 R14: 0000000000000000 R15: ffff888100949600
[ 4497.504804] FS:  0000000000000000(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000
[ 4497.505302] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 4497.505671] CR2: 00007fce98806298 CR3: 000000000262e005 CR4: 0000000000370ef0
[ 4497.506104] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 4497.506540] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 4497.507002] Call Trace:
[ 4497.507158]  <TASK>
[ 4497.507299]  ? free_irq+0x295/0x340
[ 4497.507522]  ? __warn+0x7c/0x130
[ 4497.507740]  ? free_irq+0x295/0x340
[ 4497.507963]  ? report_bug+0x171/0x1a0
[ 4497.508197]  ? handle_bug+0x3c/0x70
[ 4497.508417]  ? exc_invalid_op+0x17/0x70
[ 4497.508662]  ? asm_exc_invalid_op+0x1a/0x20
[ 4497.508926]  ? free_irq+0x295/0x340
[ 4497.509146]  mlx5_irq_pool_free_irqs+0x48/0x90
[ 4497.509421]  mlx5_irq_table_free_irqs+0x38/0x50
[ 4497.509714]  mlx5_core_eq_free_irqs+0x27/0x40
[ 4497.509984]  shutdown+0x7b/0x100
[ 4497.510184]  pci_device_shutdown+0x30/0x60
[ 4497.510440]  device_shutdown+0x14d/0x240
[ 4497.510698]  kernel_power_off+0x30/0x70
[ 4497.510938]  process_one_work+0x1e6/0x3e0
[ 4497.511183]  worker_thread+0x49/0x3b0
[ 4497.511407]  ? __pfx_worker_thread+0x10/0x10
[ 4497.511679]  kthread+0xe0/0x110
[ 4497.511879]  ? __pfx_kthread+0x10/0x10
[ 4497.512114]  ret_from_fork+0x29/0x50
[ 4497.512342]  </TASK>
Fixes 9c2d08010963 ("net/mlx5: Free irqs only on shutdown callback")
---
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c |   17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +11 -6
@@ -138,18 +138,23 @@ out:
 	return ret;
 }
 
-static void irq_release(struct mlx5_irq *irq)
+static void mlx5_system_free_irq(struct mlx5_irq *irq)
 {
-	struct mlx5_irq_pool *pool = irq->pool;
-
-	xa_erase(&pool->irqs, irq->index);
 	/* free_irq requires that affinity and rmap will be cleared
 	 * before calling it. This is why there is asymmetry with set_rmap
 	 * which should be called after alloc_irq but before request_irq.
 	 */
 	irq_set_affinity_hint(irq->irqn, NULL);
-	free_cpumask_var(irq->mask);
 	free_irq(irq->irqn, &irq->nh);
+}
+
+static void irq_release(struct mlx5_irq *irq)
+{
+	struct mlx5_irq_pool *pool = irq->pool;
+
+	xa_erase(&pool->irqs, irq->index);
+	mlx5_system_free_irq(irq);
+	free_cpumask_var(irq->mask);
 	kfree(irq);
 }
 
@@ -556,7 +561,7 @@ static void mlx5_irq_pool_free_irqs(stru
 	unsigned long index;
 
 	xa_for_each(&pool->irqs, index, irq)
-		free_irq(irq->irqn, &irq->nh);
+		mlx5_system_free_irq(irq);
 }
 
 static void mlx5_irq_pools_free_irqs(struct mlx5_irq_table *table)
author maintainer
#465 lore raw

PATCH 464/511 ARC: atomics: Add compiler barrier to atomic operations...

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pavel Kozlov <[email protected]>

commit 42f51fb24fd39cc547c086ab3d8a314cc603a91c upstream.

... to avoid unwanted gcc optimizations

SMP kernels fail to boot with commit 596ff4a09b89 ("cpumask: re-introduce constant-sized cpumask optimizations").

|
| percpu: BUG: failure at mm/percpu.c:2981/pcpu_build_alloc_info()!
|

The write operation performed by the SCOND instruction in the atomic inline asm code is not properly passed to the compiler. The compiler cannot correctly optimize a nested loop that runs through the cpumask in the pcpu_build_alloc_info() function.

Fix this by add a compiler barrier (memory clobber in inline asm).

Apparently atomic ops used to have memory clobber implicitly via surrounding smp_mb(). However commit b64be6836993c431e ("ARC: atomics: implement relaxed variants") removed the smp_mb() for the relaxed variants, but failed to add the explicit compiler barrier.

Cc <[email protected]> # v6.3+
Fixes b64be6836993c43 ("ARC: atomics: implement relaxed variants")
[vgupta: tweaked the changelog and added Fixes tag]
---
 arch/arc/include/asm/atomic-llsc.h    |    6 +++---
 arch/arc/include/asm/atomic64-arcv2.h |    6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)
arch/arc/include/asm/atomic-llsc.h +3 -3
@@ -18,7 +18,7 @@ static inline void arch_atomic_##op(int
 	: [val]	"=&r"	(val) /* Early clobber to prevent reg reuse */	\
 	: [ctr]	"r"	(&v->counter), /* Not "m": llock only supports reg direct addr mode */	\
 	  [i]	"ir"	(i)						\
-	: "cc");							\
+	: "cc", "memory");						\
 }									\
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
@@ -34,7 +34,7 @@ static inline int arch_atomic_##op##_ret
 	: [val]	"=&r"	(val)						\
 	: [ctr]	"r"	(&v->counter),					\
 	  [i]	"ir"	(i)						\
-	: "cc");							\
+	: "cc", "memory");						\
 									\
 	return val;							\
 }
@@ -56,7 +56,7 @@ static inline int arch_atomic_fetch_##op
 	  [orig] "=&r" (orig)						\
 	: [ctr]	"r"	(&v->counter),					\
 	  [i]	"ir"	(i)						\
-	: "cc");							\
+	: "cc", "memory");						\
 									\
 	return orig;							\
 }
arch/arc/include/asm/atomic64-arcv2.h +3 -3
@@ -60,7 +60,7 @@ static inline void arch_atomic64_##op(s6
 	"	bnz     1b		\n"				\
 	: "=&r"(val)							\
 	: "r"(&v->counter), "ir"(a)					\
-	: "cc");							\
+	: "cc", "memory");						\
 }									\
 
 #define ATOMIC64_OP_RETURN(op, op1, op2)		        	\
@@ -77,7 +77,7 @@ static inline s64 arch_atomic64_##op##_r
 	"	bnz     1b		\n"				\
 	: [val] "=&r"(val)						\
 	: "r"(&v->counter), "ir"(a)					\
-	: "cc");	/* memory clobber comes from smp_mb() */	\
+	: "cc", "memory");						\
 									\
 	return val;							\
 }
@@ -99,7 +99,7 @@ static inline s64 arch_atomic64_fetch_##
 	"	bnz     1b		\n"				\
 	: "=&r"(orig), "=&r"(val)					\
 	: "r"(&v->counter), "ir"(a)					\
-	: "cc");	/* memory clobber comes from smp_mb() */	\
+	: "cc", "memory");						\
 									\
 	return orig;							\
 }
author maintainer
#466 lore raw

PATCH 465/511 dmaengine: sh: rz-dmac: Fix destination and source data size setting

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hien Huynh <[email protected]>

commit c6ec8c83a29fb3aec3efa6fabbf5344498f57c7f upstream.

Before setting DDS and SDS values, we need to clear its value first otherwise, we get incorrect results when we change/update the DMA bus width several times due to the 'OR' expression.

---
 drivers/dma/sh/rz-dmac.c |   11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)
drivers/dma/sh/rz-dmac.c +7 -4
@@ -9,6 +9,7 @@
  * Copyright 2012 Javier Martin, Vista Silicon <[email protected]>
  */
 
+#include <linux/bitfield.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
@@ -143,8 +144,8 @@ struct rz_dmac {
 #define CHCFG_REQD			BIT(3)
 #define CHCFG_SEL(bits)			((bits) & 0x07)
 #define CHCFG_MEM_COPY			(0x80400008)
-#define CHCFG_FILL_DDS(a)		(((a) << 16) & GENMASK(19, 16))
-#define CHCFG_FILL_SDS(a)		(((a) << 12) & GENMASK(15, 12))
+#define CHCFG_FILL_DDS_MASK		GENMASK(19, 16)
+#define CHCFG_FILL_SDS_MASK		GENMASK(15, 12)
 #define CHCFG_FILL_TM(a)		(((a) & BIT(5)) << 22)
 #define CHCFG_FILL_AM(a)		(((a) & GENMASK(4, 2)) << 6)
 #define CHCFG_FILL_LVL(a)		(((a) & BIT(1)) << 5)
@@ -607,13 +608,15 @@ static int rz_dmac_config(struct dma_cha
 	if (val == CHCFG_DS_INVALID)
 		return -EINVAL;
 
-	channel->chcfg |= CHCFG_FILL_DDS(val);
+	channel->chcfg &= ~CHCFG_FILL_DDS_MASK;
+	channel->chcfg |= FIELD_PREP(CHCFG_FILL_DDS_MASK, val);
 
 	val = rz_dmac_ds_to_val_mapping(config->src_addr_width);
 	if (val == CHCFG_DS_INVALID)
 		return -EINVAL;
 
-	channel->chcfg |= CHCFG_FILL_SDS(val);
+	channel->chcfg &= ~CHCFG_FILL_SDS_MASK;
+	channel->chcfg |= FIELD_PREP(CHCFG_FILL_SDS_MASK, val);
 
 	return 0;
 }
author maintainer
#467 lore raw

PATCH 466/511 jbd2: fix checkpoint cleanup performance regression

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zhang Yi <[email protected]>

commit 373ac521799d9e97061515aca6ec6621789036bb upstream.

journal_clean_one_cp_list() has been merged into journal_shrink_one_cp_list(), but do chekpoint buffer cleanup from the committing process is just a best effort, it should stop scan once it meet a busy buffer, or else it will cause a lot of invalid buffer scan and checks. We catch a performance regression when doing fs_mark tests below.

Test cmd:
./fs_mark -d scratch -s 1024 -n 10000 -t 1 -D 100 -N 100

Before merging checkpoint buffer cleanup:

 FSUse%        Count         Size    Files/sec     App Overhead
     95        10000         1024       8304.9            49033

After merging checkpoint buffer cleanup:

 FSUse%        Count         Size    Files/sec     App Overhead
     95        10000         1024       7649.0            50012
 FSUse%        Count         Size    Files/sec     App Overhead
     95        10000         1024       2107.1            50871

After merging checkpoint buffer cleanup, the total loop count in journal_shrink_one_cp_list() could be up to 6,261,600+ (50,000+ ~ 100,000+ in general), most of them are invalid. This patch fix it through passing 'shrink_type' into journal_shrink_one_cp_list() and add a new 'SHRINK_BUSY_STOP' to indicate it should stop once meet a busy buffer. After fix, the loop count descending back to 10,000+.

After this fix:

 FSUse%        Count         Size    Files/sec     App Overhead
     95        10000         1024       8558.4            49109
---
 fs/jbd2/checkpoint.c |   20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)
fs/jbd2/checkpoint.c +14 -6
@@ -349,6 +349,8 @@ int jbd2_cleanup_journal_tail(journal_t
 
 /* Checkpoint list management */
 
+enum shrink_type {SHRINK_DESTROY, SHRINK_BUSY_STOP, SHRINK_BUSY_SKIP};
+
 /*
  * journal_shrink_one_cp_list
  *
@@ -360,7 +362,8 @@ int jbd2_cleanup_journal_tail(journal_t
  * Called with j_list_lock held.
  */
 static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
-						bool destroy, bool *released)
+						enum shrink_type type,
+						bool *released)
 {
 	struct journal_head *last_jh;
 	struct journal_head *next_jh = jh;
@@ -376,12 +379,15 @@ static unsigned long journal_shrink_one_
 		jh = next_jh;
 		next_jh = jh->b_cpnext;
 
-		if (destroy) {
+		if (type == SHRINK_DESTROY) {
 			ret = __jbd2_journal_remove_checkpoint(jh);
 		} else {
 			ret = jbd2_journal_try_remove_checkpoint(jh);
-			if (ret < 0)
-				continue;
+			if (ret < 0) {
+				if (type == SHRINK_BUSY_SKIP)
+					continue;
+				break;
+			}
 		}
 
 		nr_freed++;
@@ -445,7 +451,7 @@ again:
 		tid = transaction->t_tid;
 
 		freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list,
-						   false, &released);
+						   SHRINK_BUSY_SKIP, &released);
 		nr_freed += freed;
 		(*nr_to_scan) -= min(*nr_to_scan, freed);
 		if (*nr_to_scan == 0)
@@ -485,19 +491,21 @@ out:
 void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy)
 {
 	transaction_t *transaction, *last_transaction, *next_transaction;
+	enum shrink_type type;
 	bool released;
 
 	transaction = journal->j_checkpoint_transactions;
 	if (!transaction)
 		return;
 
+	type = destroy ? SHRINK_DESTROY : SHRINK_BUSY_STOP;
 	last_transaction = transaction->t_cpprev;
 	next_transaction = transaction;
 	do {
 		transaction = next_transaction;
 		next_transaction = transaction->t_cpnext;
 		journal_shrink_one_cp_list(transaction->t_checkpoint_list,
-					   destroy, &released);
+					   type, &released);
 		/*
 		 * This function only frees up some memory if possible so we
 		 * dont have an obligation to finish processing. Bail out if
author maintainer
#468 lore raw

PATCH 467/511 jbd2: check jh->b_transaction before removing it from checkpoint

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zhihao Cheng <[email protected]>

commit 590a809ff743e7bd890ba5fb36bc38e20a36de53 upstream.

Following process will corrupt ext4 image:
Step 1:
jbd2_journal_commit_transaction
__jbd2_journal_insert_checkpoint(jh, commit_transaction) // Put jh into trans1->t_checkpoint_list journal->j_checkpoint_transactions = commit_transaction // Put trans1 into journal->j_checkpoint_transactions

Step 2:
do_get_write_access
test_clear_buffer_dirty(bh) // clear buffer dirty,set jbd dirty __jbd2_journal_file_buffer(jh, transaction) // jh belongs to trans2

Step 3:
drop_cache
journal_shrink_one_cp_list
jbd2_journal_try_remove_checkpoint
if (!trylock_buffer(bh)) // lock bh, true
if (buffer_dirty(bh)) // buffer is not dirty
__jbd2_journal_remove_checkpoint(jh)
// remove jh from trans1->t_checkpoint_list

Step 4:
jbd2_log_do_checkpoint
trans1 = journal->j_checkpoint_transactions // jh is not in trans1->t_checkpoint_list jbd2_cleanup_journal_tail(journal) // trans1 is done

Step 5: Power cut, trans2 is not committed, jh is lost in next mounting.

Fix it by checking 'jh->b_transaction' before remove it from checkpoint.

---
 fs/jbd2/checkpoint.c | 2 ++
 1 file changed, 2 insertions(+)
fs/jbd2/checkpoint.c +2 -0
index 936c6d758a65..f033ac807013 100644
@@ -639,6 +639,8 @@ int jbd2_journal_try_remove_checkpoint(struct journal_head *jh)
 {
 	struct buffer_head *bh = jh2bh(jh);
 
+	if (jh->b_transaction)
+		return -EBUSY;
 	if (!trylock_buffer(bh))
 		return -EBUSY;
 	if (buffer_dirty(bh)) {
Signature · 1 line
2.42.0
author maintainer
#469 lore raw

PATCH 468/511 ext4: add correct group descriptors and reserved GDT blocks to system zone

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wang Jianjian <[email protected]>

commit 68228da51c9a436872a4ef4b5a7692e29f7e5bc7 upstream.

When setup_system_zone, flex_bg is not initialized so it is always 1. Use a new helper function, ext4_num_base_meta_blocks() which does not depend on sbi->s_log_groups_per_flex being initialized.

[ Squashed two patches in the Link URL's below together into a single
commit, which is simpler to review/understand. Also fix checkpatch warnings. --TYT ]

---
 fs/ext4/balloc.c         |   15 +++++++++++----
 fs/ext4/block_validity.c |    8 ++++----
 fs/ext4/ext4.h           |    2 ++
 3 files changed, 17 insertions(+), 8 deletions(-)
fs/ext4/balloc.c +11 -4
@@ -909,11 +909,11 @@ unsigned long ext4_bg_num_gdb(struct sup
 }
 
 /*
- * This function returns the number of file system metadata clusters at
+ * This function returns the number of file system metadata blocks at
  * the beginning of a block group, including the reserved gdt blocks.
  */
-static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
-				     ext4_group_t block_group)
+unsigned int ext4_num_base_meta_blocks(struct super_block *sb,
+				       ext4_group_t block_group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	unsigned num;
@@ -931,8 +931,15 @@ static unsigned ext4_num_base_meta_clust
 	} else { /* For META_BG_BLOCK_GROUPS */
 		num += ext4_bg_num_gdb(sb, block_group);
 	}
-	return EXT4_NUM_B2C(sbi, num);
+	return num;
 }
+
+static unsigned int ext4_num_base_meta_clusters(struct super_block *sb,
+						ext4_group_t block_group)
+{
+	return EXT4_NUM_B2C(EXT4_SB(sb), ext4_num_base_meta_blocks(sb, block_group));
+}
+
 /**
  *	ext4_inode_to_goal_block - return a hint for block allocation
  *	@inode: inode for block allocation
fs/ext4/block_validity.c +4 -4
@@ -215,7 +215,6 @@ int ext4_setup_system_zone(struct super_
 	struct ext4_system_blocks *system_blks;
 	struct ext4_group_desc *gdp;
 	ext4_group_t i;
-	int flex_size = ext4_flex_bg_size(sbi);
 	int ret;
 
 	system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL);
@@ -223,12 +222,13 @@ int ext4_setup_system_zone(struct super_
 		return -ENOMEM;
 
 	for (i=0; i < ngroups; i++) {
+		unsigned int meta_blks = ext4_num_base_meta_blocks(sb, i);
+
 		cond_resched();
-		if (ext4_bg_has_super(sb, i) &&
-		    ((i < 5) || ((i % flex_size) == 0))) {
+		if (meta_blks != 0) {
 			ret = add_system_zone(system_blks,
 					ext4_group_first_block_no(sb, i),
-					ext4_bg_num_gdb(sb, i) + 1, 0);
+					meta_blks, 0);
 			if (ret)
 				goto err;
 		}
fs/ext4/ext4.h +2 -0
@@ -3120,6 +3120,8 @@ extern const char *ext4_decode_error(str
 extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
 					     ext4_group_t block_group,
 					     unsigned int flags);
+extern unsigned int ext4_num_base_meta_blocks(struct super_block *sb,
+					      ext4_group_t block_group);
 
 extern __printf(7, 8)
 void __ext4_error(struct super_block *, const char *, unsigned int, bool,
author maintainer
#470 lore raw

PATCH 469/511 lib: test_scanf: Add explicit type cast to result initialization in test_number_prefix()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nathan Chancellor <[email protected]>

commit 92382d744176f230101d54f5c017bccd62770f01 upstream.

A recent change in clang allows it to consider more expressions as compile time constants, which causes it to point out an implicit conversion in the scanf tests:

  lib/test_scanf.c:661:2: warning: implicit conversion from 'int' to 'unsigned char' changes value from -168 to 88 [-Wconstant-conversion]
    661 |         test_number_prefix(unsigned char,       "0xA7", "%2hhx%hhx", 0, 0xa7, 2, check_uchar);
        |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  lib/test_scanf.c:609:29: note: expanded from macro 'test_number_prefix'
    609 |         T result[2] = {~expect[0], ~expect[1]};                                 \
        |                       ~            ^~~~~~~~~~
  1 warning generated.

The result of the bitwise negation is the type of the operand after going through the integer promotion rules, so this truncation is expected but harmless, as the initial values in the result array get overwritten by _test() anyways. Add an explicit cast to the expected type in test_number_prefix() to silence the warning. There is no functional change, as all the tests still pass with GCC 13.1.0 and clang 18.0.0.

---
 lib/test_scanf.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
lib/test_scanf.c +1 -1
@@ -606,7 +606,7 @@ static void __init numbers_slice(void)
 #define test_number_prefix(T, str, scan_fmt, expect0, expect1, n_args, fn)	\
 do {										\
 	const T expect[2] = { expect0, expect1 };				\
-	T result[2] = {~expect[0], ~expect[1]};					\
+	T result[2] = { (T)~expect[0], (T)~expect[1] };				\
 										\
 	_test(fn, &expect, str, scan_fmt, n_args, &result[0], &result[1]);	\
 } while (0)
author maintainer
#471 lore raw

PATCH 470/511 ata: pata_falcon: fix IO base selection for Q40

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michael Schmitz <[email protected]>

commit 8a1f00b753ecfdb117dc1a07e68c46d80e7923ea upstream.

With commit 44b1fbc0f5f3 ("m68k/q40: Replace q40ide driver with pata_falcon and falconide"), the Q40 IDE driver was replaced by pata_falcon.c.

Both IO and memory resources were defined for the Q40 IDE platform device, but definition of the IDE register addresses was modeled after the Falcon case, both in use of the memory resources and in including register shift and byte vs. word offset in the address.

This was correct for the Falcon case, which does not apply any address translation to the register addresses. In the Q40 case, all of device base address, byte access offset and register shift is included in the platform specific ISA access translation (in asm/mm_io.h).

As a consequence, such address translation gets applied twice, and register addresses are mangled.

Use the device base address from the platform IO resource for Q40 (the IO address translation will then add the correct ISA window base address and byte access offset), with register shift 1. Use MMIO base address and register shift 2 as before for Falcon.

Encode PIO_OFFSET into IO port addresses for all registers for Q40 except the data transfer register. Encode the MMIO offset there (pata_falcon_data_xfer() directly uses raw IO with no address translation).

---
 drivers/ata/pata_falcon.c |   50 ++++++++++++++++++++++++++--------------------
 1 file changed, 29 insertions(+), 21 deletions(-)
drivers/ata/pata_falcon.c +29 -21
@@ -123,8 +123,8 @@ static int __init pata_falcon_init_one(s
 	struct resource *base_res, *ctl_res, *irq_res;
 	struct ata_host *host;
 	struct ata_port *ap;
-	void __iomem *base;
-	int irq = 0;
+	void __iomem *base, *ctl_base;
+	int irq = 0, io_offset = 1, reg_shift = 2; /* Falcon defaults */
 
 	dev_info(&pdev->dev, "Atari Falcon and Q40/Q60 PATA controller\n");
 
@@ -165,26 +165,34 @@ static int __init pata_falcon_init_one(s
 	ap->pio_mask = ATA_PIO4;
 	ap->flags |= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_IORDY;
 
-	base = (void __iomem *)base_mem_res->start;
 	/* N.B. this assumes data_addr will be used for word-sized I/O only */
-	ap->ioaddr.data_addr		= base + 0 + 0 * 4;
-	ap->ioaddr.error_addr		= base + 1 + 1 * 4;
-	ap->ioaddr.feature_addr		= base + 1 + 1 * 4;
-	ap->ioaddr.nsect_addr		= base + 1 + 2 * 4;
-	ap->ioaddr.lbal_addr		= base + 1 + 3 * 4;
-	ap->ioaddr.lbam_addr		= base + 1 + 4 * 4;
-	ap->ioaddr.lbah_addr		= base + 1 + 5 * 4;
-	ap->ioaddr.device_addr		= base + 1 + 6 * 4;
-	ap->ioaddr.status_addr		= base + 1 + 7 * 4;
-	ap->ioaddr.command_addr		= base + 1 + 7 * 4;
-
-	base = (void __iomem *)ctl_mem_res->start;
-	ap->ioaddr.altstatus_addr	= base + 1;
-	ap->ioaddr.ctl_addr		= base + 1;
-
-	ata_port_desc(ap, "cmd 0x%lx ctl 0x%lx",
-		      (unsigned long)base_mem_res->start,
-		      (unsigned long)ctl_mem_res->start);
+	ap->ioaddr.data_addr = (void __iomem *)base_mem_res->start;
+
+	if (base_res) {		/* only Q40 has IO resources */
+		io_offset = 0x10000;
+		reg_shift = 0;
+		base = (void __iomem *)base_res->start;
+		ctl_base = (void __iomem *)ctl_res->start;
+	} else {
+		base = (void __iomem *)base_mem_res->start;
+		ctl_base = (void __iomem *)ctl_mem_res->start;
+	}
+
+	ap->ioaddr.error_addr	= base + io_offset + (1 << reg_shift);
+	ap->ioaddr.feature_addr	= base + io_offset + (1 << reg_shift);
+	ap->ioaddr.nsect_addr	= base + io_offset + (2 << reg_shift);
+	ap->ioaddr.lbal_addr	= base + io_offset + (3 << reg_shift);
+	ap->ioaddr.lbam_addr	= base + io_offset + (4 << reg_shift);
+	ap->ioaddr.lbah_addr	= base + io_offset + (5 << reg_shift);
+	ap->ioaddr.device_addr	= base + io_offset + (6 << reg_shift);
+	ap->ioaddr.status_addr	= base + io_offset + (7 << reg_shift);
+	ap->ioaddr.command_addr	= base + io_offset + (7 << reg_shift);
+
+	ap->ioaddr.altstatus_addr	= ctl_base + io_offset;
+	ap->ioaddr.ctl_addr		= ctl_base + io_offset;
+
+	ata_port_desc(ap, "cmd %px ctl %px data %px",
+		      base, ctl_base, ap->ioaddr.data_addr);
 
 	irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (irq_res && irq_res->start > 0) {
author maintainer
#472 lore raw

PATCH 471/511 ata: sata_gemini: Add missing MODULE_DESCRIPTION

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Damien Le Moal <[email protected]>

commit 8566572bf3b4d6e416a4bf2110dbb4817d11ba59 upstream.

Add the missing MODULE_DESCRIPTION() to avoid warnings such as:

WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/ata/sata_gemini.o

when compiling with W=1.

Fixes be4e456ed3a5 ("ata: Add driver for Faraday Technology FTIDE010")
---
 drivers/ata/sata_gemini.c |    1 +
 1 file changed, 1 insertion(+)
drivers/ata/sata_gemini.c +1 -0
@@ -435,6 +435,7 @@ static struct platform_driver gemini_sat
 };
 module_platform_driver(gemini_sata_driver);
 
+MODULE_DESCRIPTION("low level driver for Cortina Systems Gemini SATA bridge");
 MODULE_AUTHOR("Linus Walleij <[email protected]>");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:" DRV_NAME);
author maintainer
#473 lore raw

PATCH 472/511 ata: pata_ftide010: Add missing MODULE_DESCRIPTION

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Damien Le Moal <[email protected]>

commit 7274eef5729037300f29d14edeb334a47a098f65 upstream.

Add the missing MODULE_DESCRIPTION() to avoid warnings such as:

WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/ata/pata_ftide010.o

when compiling with W=1.

Fixes be4e456ed3a5 ("ata: Add driver for Faraday Technology FTIDE010")
---
 drivers/ata/pata_ftide010.c |    1 +
 1 file changed, 1 insertion(+)
drivers/ata/pata_ftide010.c +1 -0
@@ -570,6 +570,7 @@ static struct platform_driver pata_ftide
 };
 module_platform_driver(pata_ftide010_driver);
 
+MODULE_DESCRIPTION("low level driver for Faraday Technology FTIDE010");
 MODULE_AUTHOR("Linus Walleij <[email protected]>");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:" DRV_NAME);
author maintainer
#474 lore raw

PATCH 473/511 fuse: nlookup missing decrement in fuse_direntplus_link

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: ruanmeisi <[email protected]>

commit b8bd342d50cbf606666488488f9fea374aceb2d5 upstream.

During our debugging of glusterfs, we found an Assertion failed error:
inode_lookup >= nlookup, which was caused by the nlookup value in the kernel being greater than that in the FUSE file system.

The issue was introduced by fuse_direntplus_link, where in the function, fuse_iget increments nlookup, and if d_splice_alias returns failure, fuse_direntplus_link returns failure without decrementing nlookup
https://github.com/gluster/glusterfs/pull/4081

Fixes 0b05b18381ee ("fuse: implement NFS-like readdirplus support")
Cc <[email protected]> # v3.9
---
 fs/fuse/readdir.c |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)
fs/fuse/readdir.c +9 -1
@@ -243,8 +243,16 @@ retry:
 			dput(dentry);
 			dentry = alias;
 		}
-		if (IS_ERR(dentry))
+		if (IS_ERR(dentry)) {
+			if (!IS_ERR(inode)) {
+				struct fuse_inode *fi = get_fuse_inode(inode);
+
+				spin_lock(&fi->lock);
+				fi->nlookup--;
+				spin_unlock(&fi->lock);
+			}
 			return PTR_ERR(dentry);
+		}
 	}
 	if (fc->readdirplus_auto)
 		set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state);
author maintainer
#475 lore raw

PATCH 474/511 btrfs: free qgroup rsv on io failure

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Boris Burkov <[email protected]>

commit e28b02118b94e42be3355458a2406c6861e2dd32 upstream.

If we do a write whose bio suffers an error, we will never reclaim the qgroup reserved space for it. We allocate the space in the write_iter codepath, then release the reservation as we allocate the ordered extent, but we only create a delayed ref if the ordered extent finishes. If it has an error, we simply leak the rsv. This is apparent in running any error injecting (dmerror) fstests like btrfs/146 or btrfs/160. Such tests fail due to dmesg on umount complaining about the leaked qgroup data space.

When we clean up other aspects of space on failed ordered_extents, also free the qgroup rsv.

---
 fs/btrfs/inode.c |    7 +++++++
 1 file changed, 7 insertions(+)
fs/btrfs/inode.c +7 -0
@@ -3226,6 +3226,13 @@ out:
 			btrfs_free_reserved_extent(fs_info,
 					ordered_extent->disk_bytenr,
 					ordered_extent->disk_num_bytes, 1);
+			/*
+			 * Actually free the qgroup rsv which was released when
+			 * the ordered extent was created.
+			 */
+			btrfs_qgroup_free_refroot(fs_info, inode->root->root_key.objectid,
+						  ordered_extent->qgroup_rsv,
+						  BTRFS_QGROUP_RSV_DATA);
 		}
 	}
 
author maintainer
#476 lore raw

PATCH 475/511 btrfs: dont start transaction when joining with TRANS_JOIN_NOSTART

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Filipe Manana <[email protected]>

commit 4490e803e1fe9fab8db5025e44e23b55df54078b upstream.

When joining a transaction with TRANS_JOIN_NOSTART, if we don't find a running transaction we end up creating one. This goes against the purpose of TRANS_JOIN_NOSTART which is to join a running transaction if its state is at or below the state TRANS_STATE_COMMIT_START, otherwise return an -ENOENT error and don't start a new transaction. So fix this to not create a new transaction if there's no running transaction at or below that state.

Fixes a6d155d2e363 ("Btrfs: fix deadlock between fiemap and transaction commits")
---
 fs/btrfs/transaction.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
fs/btrfs/transaction.c +4 -3
@@ -311,10 +311,11 @@ loop:
 	spin_unlock(&fs_info->trans_lock);
 
 	/*
-	 * If we are ATTACH, we just want to catch the current transaction,
-	 * and commit it. If there is no transaction, just return ENOENT.
+	 * If we are ATTACH or TRANS_JOIN_NOSTART, we just want to catch the
+	 * current transaction, and commit it. If there is no transaction, just
+	 * return ENOENT.
 	 */
-	if (type == TRANS_ATTACH)
+	if (type == TRANS_ATTACH || type == TRANS_JOIN_NOSTART)
 		return -ENOENT;
 
 	/*
author maintainer
#477 lore raw

PATCH 476/511 btrfs: use the correct superblock to compare fsid in btrfs_validate_super

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Anand Jain <[email protected]>

commit d167aa76dc0683828588c25767da07fb549e4f48 upstream.

The function btrfs_validate_super() should verify the fsid in the provided superblock argument. Because, all its callers expect it to do that.

Such as in the following stack:

   write_all_supers()
       sb = fs_info->super_for_commit;
       btrfs_validate_write_super(.., sb)
         btrfs_validate_super(.., sb, ..)

scrub_one_super()

	btrfs_validate_super(.., sb, ..)

And
check_dev_super()

	btrfs_validate_super(.., sb, ..)

However, it currently verifies the fs_info::super_copy::fsid instead, which is not correct. Fix this using the correct fsid in the superblock argument.

---
 fs/btrfs/disk-io.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
fs/btrfs/disk-io.c +2 -3
@@ -2598,11 +2598,10 @@ int btrfs_validate_super(struct btrfs_fs
 		ret = -EINVAL;
 	}
 
-	if (memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid,
-		   BTRFS_FSID_SIZE)) {
+	if (memcmp(fs_info->fs_devices->fsid, sb->fsid, BTRFS_FSID_SIZE) != 0) {
 		btrfs_err(fs_info,
 		"superblock fsid doesn't match fsid of fs_devices: %pU != %pU",
-			fs_info->super_copy->fsid, fs_info->fs_devices->fsid);
+			  sb->fsid, fs_info->fs_devices->fsid);
 		ret = -EINVAL;
 	}
 
author maintainer
#478 lore raw

PATCH 477/511 mtd: rawnand: brcmnand: Fix crash during the panic_write

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: William Zhang <[email protected]>

commit e66dd317194daae0475fe9e5577c80aa97f16cb9 upstream.

When executing a NAND command within the panic write path, wait for any pending command instead of calling BUG_ON to avoid crashing while already crashing.

---
 drivers/mtd/nand/raw/brcmnand/brcmnand.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)
drivers/mtd/nand/raw/brcmnand/brcmnand.c +11 -1
@@ -1563,7 +1563,17 @@ static void brcmnand_send_cmd(struct brc
 
 	dev_dbg(ctrl->dev, "send native cmd %d addr 0x%llx\n", cmd, cmd_addr);
 
-	BUG_ON(ctrl->cmd_pending != 0);
+	/*
+	 * If we came here through _panic_write and there is a pending
+	 * command, try to wait for it. If it times out, rather than
+	 * hitting BUG_ON, just return so we don't crash while crashing.
+	 */
+	if (oops_in_progress) {
+		if (ctrl->cmd_pending &&
+			bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY, NAND_CTRL_RDY, 0))
+			return;
+	} else
+		BUG_ON(ctrl->cmd_pending != 0);
 	ctrl->cmd_pending = cmd;
 
 	ret = bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY, NAND_CTRL_RDY, 0);
author maintainer
#479 lore raw

PATCH 478/511 mtd: rawnand: brcmnand: Fix potential out-of-bounds access in oob write

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: William Zhang <[email protected]>

commit 5d53244186c9ac58cb88d76a0958ca55b83a15cd upstream.

When the oob buffer length is not in multiple of words, the oob write function does out-of-bounds read on the oob source buffer at the last iteration. Fix that by always checking length limit on the oob buffer read and fill with 0xff when reaching the end of the buffer to the oob registers.

Fixes 27c5b17cd1b1 ("mtd: nand: add NAND driver "library" for Broadcom STB NAND controller")
---
 drivers/mtd/nand/raw/brcmnand/brcmnand.c |   18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)
drivers/mtd/nand/raw/brcmnand/brcmnand.c +16 -2
@@ -1432,19 +1432,33 @@ static int write_oob_to_regs(struct brcm
 			     const u8 *oob, int sas, int sector_1k)
 {
 	int tbytes = sas << sector_1k;
-	int j;
+	int j, k = 0;
+	u32 last = 0xffffffff;
+	u8 *plast = (u8 *)&last;
 
 	/* Adjust OOB values for 1K sector size */
 	if (sector_1k && (i & 0x01))
 		tbytes = max(0, tbytes - (int)ctrl->max_oob);
 	tbytes = min_t(int, tbytes, ctrl->max_oob);
 
-	for (j = 0; j < tbytes; j += 4)
+	/*
+	 * tbytes may not be multiple of words. Make sure we don't read out of
+	 * the boundary and stop at last word.
+	 */
+	for (j = 0; (j + 3) < tbytes; j += 4)
 		oob_reg_write(ctrl, j,
 				(oob[j + 0] << 24) |
 				(oob[j + 1] << 16) |
 				(oob[j + 2] <<  8) |
 				(oob[j + 3] <<  0));
+
+	/* handle the remaing bytes */
+	while (j < tbytes)
+		plast[k++] = oob[j++];
+
+	if (tbytes & 0x3)
+		oob_reg_write(ctrl, (tbytes & ~0x3), (__force u32)cpu_to_be32(last));
+
 	return tbytes;
 }
 
author maintainer
#480 lore raw

PATCH 479/511 mtd: rawnand: brcmnand: Fix potential false time out warning

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: William Zhang <[email protected]>

commit 9cc0a598b944816f2968baf2631757f22721b996 upstream.

If system is busy during the command status polling function, the driver may not get the chance to poll the status register till the end of time out and return the premature status. Do a final check after time out happens to ensure reading the correct status.

Fixes 9d2ee0a60b8b ("mtd: nand: brcmnand: Check flash #WP pin status before nand erase/program")
---
 drivers/mtd/nand/raw/brcmnand/brcmnand.c |    8 ++++++++
 1 file changed, 8 insertions(+)
drivers/mtd/nand/raw/brcmnand/brcmnand.c +8 -0
@@ -1043,6 +1043,14 @@ static int bcmnand_ctrl_poll_status(stru
 		cpu_relax();
 	} while (time_after(limit, jiffies));
 
+	/*
+	 * do a final check after time out in case the CPU was busy and the driver
+	 * did not get enough time to perform the polling to avoid false alarms
+	 */
+	val = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS);
+	if ((val & mask) == expected_val)
+		return 0;
+
 	dev_warn(ctrl->dev, "timeout on status poll (expected %x got %x)\n",
 		 expected_val, val & mask);
 
author maintainer
#481 lore raw

PATCH 480/511 drm/amd/display: prevent potential division by zero errors

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hamza Mahfooz <[email protected]>

commit 07e388aab042774f284a2ad75a70a194517cdad4 upstream.

There are two places in apply_below_the_range() where it's possible for a divide by zero error to occur. So, to fix this make sure the divisor is non-zero before attempting the computation in both cases.

Fixes a463b263032f ("drm/amd/display: Fix frames_to_insert math")
Fixes ded6119e825a ("drm/amd/display: Reinstate LFC optimization")
---
 drivers/gpu/drm/amd/display/modules/freesync/freesync.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/display/modules/freesync/freesync.c +6 -3
@@ -327,7 +327,9 @@ static void apply_below_the_range(struct
 		 *  - Delta for CEIL: delta_from_mid_point_in_us_1
 		 *  - Delta for FLOOR: delta_from_mid_point_in_us_2
 		 */
-		if ((last_render_time_in_us / mid_point_frames_ceil) < in_out_vrr->min_duration_in_us) {
+		if (mid_point_frames_ceil &&
+		    (last_render_time_in_us / mid_point_frames_ceil) <
+		    in_out_vrr->min_duration_in_us) {
 			/* Check for out of range.
 			 * If using CEIL produces a value that is out of range,
 			 * then we are forced to use FLOOR.
@@ -374,8 +376,9 @@ static void apply_below_the_range(struct
 		/* Either we've calculated the number of frames to insert,
 		 * or we need to insert min duration frames
 		 */
-		if (last_render_time_in_us / frames_to_insert <
-				in_out_vrr->min_duration_in_us){
+		if (frames_to_insert &&
+		    (last_render_time_in_us / frames_to_insert) <
+		    in_out_vrr->min_duration_in_us){
 			frames_to_insert -= (frames_to_insert > 1) ?
 					1 : 0;
 		}
author maintainer
#482 lore raw

PATCH 481/511 MIPS: Fix CONFIG_CPU_DADDI_WORKAROUNDS `modules_install regression

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maciej W. Rozycki <[email protected]>

commit a79a404e6c2241ebc528b9ebf4c0832457b498c3 upstream.

Remove a build-time check for the presence of the GCC `-msym32' option. This option has been there since GCC 4.1.0, which is below the minimum required as at commit 805b2e1d427a ("kbuild: include Makefile.compiler only when compiler is needed"), when an error message:

arch/mips/Makefile:306: *** CONFIG_CPU_DADDI_WORKAROUNDS unsupported without -msym32. Stop.

started to trigger for the modules_install' target with configurations such as decstation_64_defconfig' that set CONFIG_CPU_DADDI_WORKAROUNDS, because said commit has made `cc-option-yn' an undefined function for non-build targets.

Fixes 805b2e1d427a ("kbuild: include Makefile.compiler only when compiler is needed")
Cc [email protected] # v5.13+
---
 arch/mips/Makefile |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
arch/mips/Makefile +2 -2
@@ -279,8 +279,8 @@ ifdef CONFIG_64BIT
     endif
   endif
 
-  ifeq ($(KBUILD_SYM32)$(call cc-option-yn,-msym32), yy)
-    cflags-y += -msym32 -DKBUILD_64BIT_SYM32
+  ifeq ($(KBUILD_SYM32), y)
+    cflags-$(KBUILD_SYM32) += -msym32 -DKBUILD_64BIT_SYM32
   else
     ifeq ($(CONFIG_CPU_DADDI_WORKAROUNDS), y)
       $(error CONFIG_CPU_DADDI_WORKAROUNDS unsupported without -msym32)
author maintainer
#483 lore raw

PATCH 482/511 perf hists browser: Fix hierarchy mode header

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Namhyung Kim <[email protected]>

commit e2cabf2a44791f01c21f8d5189b946926e34142e upstream.

The commit ef9ff6017e3c4593 ("perf ui browser: Move the extra title lines from the hists browser") introduced ui_browser__gotorc_title() to help moving non-title lines easily. But it missed to update the title for the hierarchy mode so it won't print the header line on TUI at all.

  $ perf report --hierarchy
Fixes ef9ff6017e3c4593 ("perf ui browser: Move the extra title lines from the hists browser")
Cc Adrian Hunter <[email protected]>
Cc Ian Rogers <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/ui/browsers/hists.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/ui/browsers/hists.c +1 -1
@@ -1779,7 +1779,7 @@ static void hists_browser__hierarchy_hea
 	hists_browser__scnprintf_hierarchy_headers(browser, headers,
 						   sizeof(headers));
 
-	ui_browser__gotorc(&browser->b, 0, 0);
+	ui_browser__gotorc_title(&browser->b, 0, 0);
 	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
 	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
 }
author maintainer
#484 lore raw

PATCH 483/511 perf tools: Handle old data in PERF_RECORD_ATTR

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Namhyung Kim <[email protected]>

commit 9bf63282ea77a531ea58acb42fb3f40d2d1e4497 upstream.

The PERF_RECORD_ATTR is used for a pipe mode to describe an event with attribute and IDs. The ID table comes after the attr and it calculate size of the table using the total record size and the attr size.

n_ids = (total_record_size - end_of_the_attr_field) / sizeof(u64)

This is fine for most use cases, but sometimes it saves the pipe output in a file and then process it later. And it becomes a problem if there is a change in attr size between the record and report.

  $ perf record -o- > perf-pipe.data  # old version
  $ perf report -i- < perf-pipe.data  # new version

For example, if the attr size is 128 and it has 4 IDs, then it would save them in 168 byte like below:

8 byte: perf event header { .type = PERF_RECORD_ATTR, .size = 168 },
128 byte: perf event attr { .size = 128, ... },
32 byte: event IDs [] = { 1234, 1235, 1236, 1237 },

But when report later, it thinks the attr size is 136 then it only read the last 3 entries as ID.

8 byte: perf event header { .type = PERF_RECORD_ATTR, .size = 168 },
136 byte: perf event attr { .size = 136, ... },
24 byte: event IDs [] = { 1235, 1236, 1237 }, // 1234 is missing

So it should use the recorded version of the attr. The attr has the size field already then it should honor the size when reading data.

Fixes 2c46dbb517a10b18 ("perf: Convert perf header attrs into attr events")
Cc Adrian Hunter <[email protected]>
Cc Ian Rogers <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Tom Zanussi <[email protected]>
---
 tools/perf/util/header.c |   11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)
tools/perf/util/header.c +6 -5
@@ -4200,7 +4200,8 @@ int perf_event__process_attr(struct perf
 			     union perf_event *event,
 			     struct evlist **pevlist)
 {
-	u32 i, ids, n_ids;
+	u32 i, n_ids;
+	u64 *ids;
 	struct evsel *evsel;
 	struct evlist *evlist = *pevlist;
 
@@ -4216,9 +4217,8 @@ int perf_event__process_attr(struct perf
 
 	evlist__add(evlist, evsel);
 
-	ids = event->header.size;
-	ids -= (void *)&event->attr.id - (void *)event;
-	n_ids = ids / sizeof(u64);
+	n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size;
+	n_ids = n_ids / sizeof(u64);
 	/*
 	 * We don't have the cpu and thread maps on the header, so
 	 * for allocating the perf_sample_id table we fake 1 cpu and
@@ -4227,8 +4227,9 @@ int perf_event__process_attr(struct perf
 	if (perf_evsel__alloc_id(&evsel->core, 1, n_ids))
 		return -ENOMEM;
 
+	ids = (void *)&event->attr.attr + event->attr.attr.size;
 	for (i = 0; i < n_ids; i++) {
-		perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]);
+		perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]);
 	}
 
 	return 0;
author maintainer
#485 lore raw

PATCH 484/511 perf hists browser: Fix the number of entries for e key

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Namhyung Kim <[email protected]>

commit f6b8436bede3e80226e8b2100279c4450c73806a upstream.

The 'e' key is to toggle expand/collapse the selected entry only. But the current code has a bug that it only increases the number of entries by 1 in the hierarchy mode so users cannot move under the current entry after the key stroke. This is due to a wrong assumption in the hist_entry__set_folding().

The commit b33f922651011eff ("perf hists browser: Put hist_entry folding logic into single function") factored out the code, but actually it should be handled separately. The hist_browser__set_folding() is to update fold state for each entry so it needs to traverse all (child) entries regardless of the current fold state. So it increases the number of entries by 1.

But the hist_entry__set_folding() only cares the currently selected entry and its all children. So it should count all unfolded child entries. This code is implemented in hist_browser__toggle_fold() already so we can just call it.

Fixes b33f922651011eff ("perf hists browser: Put hist_entry folding logic into single function")
Cc Adrian Hunter <[email protected]>
Cc Ian Rogers <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/ui/browsers/hists.c |   58 ++++++++++++++++-------------------------
 1 file changed, 24 insertions(+), 34 deletions(-)
tools/perf/ui/browsers/hists.c +24 -34
@@ -407,11 +407,6 @@ static bool hist_browser__selection_has_
 	return container_of(ms, struct callchain_list, ms)->has_children;
 }
 
-static bool hist_browser__he_selection_unfolded(struct hist_browser *browser)
-{
-	return browser->he_selection ? browser->he_selection->unfolded : false;
-}
-
 static bool hist_browser__selection_unfolded(struct hist_browser *browser)
 {
 	struct hist_entry *he = browser->he_selection;
@@ -584,8 +579,8 @@ static int hierarchy_set_folding(struct
 	return n;
 }
 
-static void __hist_entry__set_folding(struct hist_entry *he,
-				      struct hist_browser *hb, bool unfold)
+static void hist_entry__set_folding(struct hist_entry *he,
+				    struct hist_browser *hb, bool unfold)
 {
 	hist_entry__init_have_children(he);
 	he->unfolded = unfold ? he->has_children : false;
@@ -603,34 +598,12 @@ static void __hist_entry__set_folding(st
 		he->nr_rows = 0;
 }
 
-static void hist_entry__set_folding(struct hist_entry *he,
-				    struct hist_browser *browser, bool unfold)
-{
-	double percent;
-
-	percent = hist_entry__get_percent_limit(he);
-	if (he->filtered || percent < browser->min_pcnt)
-		return;
-
-	__hist_entry__set_folding(he, browser, unfold);
-
-	if (!he->depth || unfold)
-		browser->nr_hierarchy_entries++;
-	if (he->leaf)
-		browser->nr_callchain_rows += he->nr_rows;
-	else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
-		browser->nr_hierarchy_entries++;
-		he->has_no_entry = true;
-		he->nr_rows = 1;
-	} else
-		he->has_no_entry = false;
-}
-
 static void
 __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
 	struct rb_node *nd;
 	struct hist_entry *he;
+	double percent;
 
 	nd = rb_first_cached(&browser->hists->entries);
 	while (nd) {
@@ -640,6 +613,21 @@ __hist_browser__set_folding(struct hist_
 		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
 
 		hist_entry__set_folding(he, browser, unfold);
+
+		percent = hist_entry__get_percent_limit(he);
+		if (he->filtered || percent < browser->min_pcnt)
+			continue;
+
+		if (!he->depth || unfold)
+			browser->nr_hierarchy_entries++;
+		if (he->leaf)
+			browser->nr_callchain_rows += he->nr_rows;
+		else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+			browser->nr_hierarchy_entries++;
+			he->has_no_entry = true;
+			he->nr_rows = 1;
+		} else
+			he->has_no_entry = false;
 	}
 }
 
@@ -659,8 +647,10 @@ static void hist_browser__set_folding_se
 	if (!browser->he_selection)
 		return;
 
-	hist_entry__set_folding(browser->he_selection, browser, unfold);
-	browser->b.nr_entries = hist_browser__nr_entries(browser);
+	if (unfold == browser->he_selection->unfolded)
+		return;
+
+	hist_browser__toggle_fold(browser);
 }
 
 static void ui_browser__warn_lost_events(struct ui_browser *browser)
@@ -732,8 +722,8 @@ static int hist_browser__handle_hotkey(s
 		hist_browser__set_folding(browser, true);
 		break;
 	case 'e':
-		/* Expand the selected entry. */
-		hist_browser__set_folding_selected(browser, !hist_browser__he_selection_unfolded(browser));
+		/* Toggle expand/collapse the selected entry. */
+		hist_browser__toggle_fold(browser);
 		break;
 	case 'H':
 		browser->show_headers = !browser->show_headers;
author maintainer
#486 lore raw

PATCH 485/511 pcd: move the identify buffer into pcd_identify

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <[email protected]>

[ Upstream commit 7d8b72aaddd3ec5f350d3e9988d6735a7b9b18e9 ]

No need to pass it through a bunch of functions.

Stable-dep-of: 1a721de8489f ("block: don't add or resize partition on the disk with GENHD_FL_NO_PART")

---
 drivers/block/paride/pcd.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)
drivers/block/paride/pcd.c +8 -8
index f9cdd11f02f58..8903fdaa20466 100644
@@ -630,10 +630,11 @@ static int pcd_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 	return CDS_DISC_OK;
 }
 
-static int pcd_identify(struct pcd_unit *cd, char *id)
+static int pcd_identify(struct pcd_unit *cd)
 {
-	int k, s;
 	char id_cmd[12] = { 0x12, 0, 0, 0, 36, 0, 0, 0, 0, 0, 0, 0 };
+	char id[18];
+	int k, s;
 
 	pcd_bufblk = -1;
 
@@ -664,15 +665,15 @@ static int pcd_identify(struct pcd_unit *cd, char *id)
  * returns  0, with id set if drive is detected
  *	    -1, if drive detection failed
  */
-static int pcd_probe(struct pcd_unit *cd, int ms, char *id)
+static int pcd_probe(struct pcd_unit *cd, int ms)
 {
 	if (ms == -1) {
 		for (cd->drive = 0; cd->drive <= 1; cd->drive++)
-			if (!pcd_reset(cd) && !pcd_identify(cd, id))
+			if (!pcd_reset(cd) && !pcd_identify(cd))
 				return 0;
 	} else {
 		cd->drive = ms;
-		if (!pcd_reset(cd) && !pcd_identify(cd, id))
+		if (!pcd_reset(cd) && !pcd_identify(cd))
 			return 0;
 	}
 	return -1;
@@ -709,7 +710,6 @@ static void pcd_probe_capabilities(void)
 
 static int pcd_detect(void)
 {
-	char id[18];
 	int k, unit;
 	struct pcd_unit *cd;
 
@@ -727,7 +727,7 @@ static int pcd_detect(void)
 		cd = pcd;
 		if (cd->disk && pi_init(cd->pi, 1, -1, -1, -1, -1, -1,
 			    pcd_buffer, PI_PCD, verbose, cd->name)) {
-			if (!pcd_probe(cd, -1, id)) {
+			if (!pcd_probe(cd, -1)) {
 				cd->present = 1;
 				k++;
 			} else
@@ -744,7 +744,7 @@ static int pcd_detect(void)
 				     conf[D_UNI], conf[D_PRO], conf[D_DLY],
 				     pcd_buffer, PI_PCD, verbose, cd->name)) 
 				continue;
-			if (!pcd_probe(cd, conf[D_SLV], id)) {
+			if (!pcd_probe(cd, conf[D_SLV])) {
 				cd->present = 1;
 				k++;
 			} else
Signature · 1 line
2.40.1
author maintainer
#487 lore raw

PATCH 486/511 pcd: cleanup initialization

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <[email protected]>

[ Upstream commit af761f277b7fd896c27cb1100b25f11567987822 ]

Refactor the pcd initialization to have a dedicated helper to initialize a single disk.

Stable-dep-of: 1a721de8489f ("block: don't add or resize partition on the disk with GENHD_FL_NO_PART")

---
 drivers/block/paride/pcd.c | 286 ++++++++++++++++---------------------
 1 file changed, 127 insertions(+), 159 deletions(-)
drivers/block/paride/pcd.c +127 -159
index 8903fdaa20466..93ed636262328 100644
@@ -183,8 +183,6 @@ static int pcd_audio_ioctl(struct cdrom_device_info *cdi,
 static int pcd_packet(struct cdrom_device_info *cdi,
 		      struct packet_command *cgc);
 
-static int pcd_detect(void);
-static void pcd_probe_capabilities(void);
 static void do_pcd_read_drq(void);
 static blk_status_t pcd_queue_rq(struct blk_mq_hw_ctx *hctx,
 				 const struct blk_mq_queue_data *bd);
@@ -302,53 +300,6 @@ static const struct blk_mq_ops pcd_mq_ops = {
 	.queue_rq	= pcd_queue_rq,
 };
 
-static void pcd_init_units(void)
-{
-	struct pcd_unit *cd;
-	int unit;
-
-	pcd_drive_count = 0;
-	for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
-		struct gendisk *disk;
-
-		if (blk_mq_alloc_sq_tag_set(&cd->tag_set, &pcd_mq_ops, 1,
-				BLK_MQ_F_SHOULD_MERGE))
-			continue;
-
-		disk = blk_mq_alloc_disk(&cd->tag_set, cd);
-		if (IS_ERR(disk)) {
-			blk_mq_free_tag_set(&cd->tag_set);
-			continue;
-		}
-
-		INIT_LIST_HEAD(&cd->rq_list);
-		blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
-		cd->disk = disk;
-		cd->pi = &cd->pia;
-		cd->present = 0;
-		cd->last_sense = 0;
-		cd->changed = 1;
-		cd->drive = (*drives[unit])[D_SLV];
-		if ((*drives[unit])[D_PRT])
-			pcd_drive_count++;
-
-		cd->name = &cd->info.name[0];
-		snprintf(cd->name, sizeof(cd->info.name), "%s%d", name, unit);
-		cd->info.ops = &pcd_dops;
-		cd->info.handle = cd;
-		cd->info.speed = 0;
-		cd->info.capacity = 1;
-		cd->info.mask = 0;
-		disk->major = major;
-		disk->first_minor = unit;
-		disk->minors = 1;
-		strcpy(disk->disk_name, cd->name);	/* umm... */
-		disk->fops = &pcd_bdops;
-		disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-		disk->events = DISK_EVENT_MEDIA_CHANGE;
-	}
-}
-
 static int pcd_open(struct cdrom_device_info *cdi, int purpose)
 {
 	struct pcd_unit *cd = cdi->handle;
@@ -679,90 +630,31 @@ static int pcd_probe(struct pcd_unit *cd, int ms)
 	return -1;
 }
 
-static void pcd_probe_capabilities(void)
+static int pcd_probe_capabilities(struct pcd_unit *cd)
 {
-	int unit, r;
-	char buffer[32];
 	char cmd[12] = { 0x5a, 1 << 3, 0x2a, 0, 0, 0, 0, 18, 0, 0, 0, 0 };
-	struct pcd_unit *cd;
-
-	for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
-		if (!cd->present)
-			continue;
-		r = pcd_atapi(cd, cmd, 18, buffer, "mode sense capabilities");
-		if (r)
-			continue;
-		/* we should now have the cap page */
-		if ((buffer[11] & 1) == 0)
-			cd->info.mask |= CDC_CD_R;
-		if ((buffer[11] & 2) == 0)
-			cd->info.mask |= CDC_CD_RW;
-		if ((buffer[12] & 1) == 0)
-			cd->info.mask |= CDC_PLAY_AUDIO;
-		if ((buffer[14] & 1) == 0)
-			cd->info.mask |= CDC_LOCK;
-		if ((buffer[14] & 8) == 0)
-			cd->info.mask |= CDC_OPEN_TRAY;
-		if ((buffer[14] >> 6) == 0)
-			cd->info.mask |= CDC_CLOSE_TRAY;
-	}
-}
-
-static int pcd_detect(void)
-{
-	int k, unit;
-	struct pcd_unit *cd;
-
-	printk("%s: %s version %s, major %d, nice %d\n",
-	       name, name, PCD_VERSION, major, nice);
+	char buffer[32];
+	int ret;
 
-	par_drv = pi_register_driver(name);
-	if (!par_drv) {
-		pr_err("failed to register %s driver\n", name);
-		return -1;
-	}
+	ret = pcd_atapi(cd, cmd, 18, buffer, "mode sense capabilities");
+	if (ret)
+		return ret;
+
+	/* we should now have the cap page */
+	if ((buffer[11] & 1) == 0)
+		cd->info.mask |= CDC_CD_R;
+	if ((buffer[11] & 2) == 0)
+		cd->info.mask |= CDC_CD_RW;
+	if ((buffer[12] & 1) == 0)
+		cd->info.mask |= CDC_PLAY_AUDIO;
+	if ((buffer[14] & 1) == 0)
+		cd->info.mask |= CDC_LOCK;
+	if ((buffer[14] & 8) == 0)
+		cd->info.mask |= CDC_OPEN_TRAY;
+	if ((buffer[14] >> 6) == 0)
+		cd->info.mask |= CDC_CLOSE_TRAY;
 
-	k = 0;
-	if (pcd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
-		cd = pcd;
-		if (cd->disk && pi_init(cd->pi, 1, -1, -1, -1, -1, -1,
-			    pcd_buffer, PI_PCD, verbose, cd->name)) {
-			if (!pcd_probe(cd, -1)) {
-				cd->present = 1;
-				k++;
-			} else
-				pi_release(cd->pi);
-		}
-	} else {
-		for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
-			int *conf = *drives[unit];
-			if (!conf[D_PRT])
-				continue;
-			if (!cd->disk)
-				continue;
-			if (!pi_init(cd->pi, 0, conf[D_PRT], conf[D_MOD],
-				     conf[D_UNI], conf[D_PRO], conf[D_DLY],
-				     pcd_buffer, PI_PCD, verbose, cd->name)) 
-				continue;
-			if (!pcd_probe(cd, conf[D_SLV])) {
-				cd->present = 1;
-				k++;
-			} else
-				pi_release(cd->pi);
-		}
-	}
-	if (k)
-		return 0;
-
-	printk("%s: No CD-ROM drive found\n", name);
-	for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
-		if (!cd->disk)
-			continue;
-		blk_cleanup_disk(cd->disk);
-		blk_mq_free_tag_set(&cd->tag_set);
-	}
-	pi_unregister_driver(par_drv);
-	return -1;
+	return 0;
 }
 
 /* I/O request processing */
@@ -999,43 +891,121 @@ static int pcd_get_mcn(struct cdrom_device_info *cdi, struct cdrom_mcn *mcn)
 	return 0;
 }
 
+static int pcd_init_unit(struct pcd_unit *cd, bool autoprobe, int port,
+		int mode, int unit, int protocol, int delay, int ms)
+{
+	struct gendisk *disk;
+	int ret;
+
+	ret = blk_mq_alloc_sq_tag_set(&cd->tag_set, &pcd_mq_ops, 1,
+				      BLK_MQ_F_SHOULD_MERGE);
+	if (ret)
+		return ret;
+
+	disk = blk_mq_alloc_disk(&cd->tag_set, cd);
+	if (IS_ERR(disk)) {
+		ret = PTR_ERR(disk);
+		goto out_free_tag_set;
+	}
+
+	INIT_LIST_HEAD(&cd->rq_list);
+	blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
+	cd->disk = disk;
+	cd->pi = &cd->pia;
+	cd->present = 0;
+	cd->last_sense = 0;
+	cd->changed = 1;
+	cd->drive = (*drives[cd - pcd])[D_SLV];
+
+	cd->name = &cd->info.name[0];
+	snprintf(cd->name, sizeof(cd->info.name), "%s%d", name, unit);
+	cd->info.ops = &pcd_dops;
+	cd->info.handle = cd;
+	cd->info.speed = 0;
+	cd->info.capacity = 1;
+	cd->info.mask = 0;
+	disk->major = major;
+	disk->first_minor = unit;
+	disk->minors = 1;
+	strcpy(disk->disk_name, cd->name);	/* umm... */
+	disk->fops = &pcd_bdops;
+	disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+	disk->events = DISK_EVENT_MEDIA_CHANGE;
+
+	if (!pi_init(cd->pi, autoprobe, port, mode, unit, protocol, delay,
+			pcd_buffer, PI_PCD, verbose, cd->name))
+		goto out_free_disk;
+	if (pcd_probe(cd, ms))
+		goto out_pi_release;
+
+	cd->present = 1;
+	pcd_probe_capabilities(cd);
+	register_cdrom(cd->disk, &cd->info);
+	add_disk(cd->disk);
+	return 0;
+
+out_pi_release:
+	pi_release(cd->pi);
+out_free_disk:
+	blk_cleanup_disk(cd->disk);
+out_free_tag_set:
+	blk_mq_free_tag_set(&cd->tag_set);
+	return ret;
+}
+
 static int __init pcd_init(void)
 {
-	struct pcd_unit *cd;
-	int unit;
+	int found = 0, unit;
 
 	if (disable)
 		return -EINVAL;
 
-	pcd_init_units();
+	if (register_blkdev(major, name))
+		return -EBUSY;
 
-	if (pcd_detect())
-		return -ENODEV;
+	pr_info("%s: %s version %s, major %d, nice %d\n",
+		name, name, PCD_VERSION, major, nice);
 
-	/* get the atapi capabilities page */
-	pcd_probe_capabilities();
+	par_drv = pi_register_driver(name);
+	if (!par_drv) {
+		pr_err("failed to register %s driver\n", name);
+		goto out_unregister_blkdev;
+	}
 
-	if (register_blkdev(major, name)) {
-		for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
-			if (!cd->disk)
-				continue;
+	for (unit = 0; unit < PCD_UNITS; unit++) {
+		if ((*drives[unit])[D_PRT])
+			pcd_drive_count++;
+	}
 
-			blk_cleanup_queue(cd->disk->queue);
-			blk_mq_free_tag_set(&cd->tag_set);
-			put_disk(cd->disk);
+	if (pcd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
+		if (!pcd_init_unit(pcd, 1, -1, -1, -1, -1, -1, -1))
+			found++;
+	} else {
+		for (unit = 0; unit < PCD_UNITS; unit++) {
+			struct pcd_unit *cd = &pcd[unit];
+			int *conf = *drives[unit];
+
+			if (!conf[D_PRT])
+				continue;
+			if (!pcd_init_unit(cd, 0, conf[D_PRT], conf[D_MOD],
+					conf[D_UNI], conf[D_PRO], conf[D_DLY],
+					conf[D_SLV]))
+				found++;
 		}
-		return -EBUSY;
 	}
 
-	for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
-		if (cd->present) {
-			register_cdrom(cd->disk, &cd->info);
-			cd->disk->private_data = cd;
-			add_disk(cd->disk);
-		}
+	if (!found) {
+		pr_info("%s: No CD-ROM drive found\n", name);
+		goto out_unregister_pi_driver;
 	}
 
 	return 0;
+
+out_unregister_pi_driver:
+	pi_unregister_driver(par_drv);
+out_unregister_blkdev:
+	unregister_blkdev(major, name);
+	return -ENODEV;
 }
 
 static void __exit pcd_exit(void)
@@ -1044,20 +1014,18 @@ static void __exit pcd_exit(void)
 	int unit;
 
 	for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
-		if (!cd->disk)
+		if (!cd->present)
 			continue;
 
-		if (cd->present) {
-			del_gendisk(cd->disk);
-			pi_release(cd->pi);
-			unregister_cdrom(&cd->info);
-		}
-		blk_cleanup_queue(cd->disk->queue);
+		del_gendisk(cd->disk);
+		pi_release(cd->pi);
+		unregister_cdrom(&cd->info);
+		blk_cleanup_disk(cd->disk);
+
 		blk_mq_free_tag_set(&cd->tag_set);
-		put_disk(cd->disk);
 	}
-	unregister_blkdev(major, name);
 	pi_unregister_driver(par_drv);
+	unregister_blkdev(major, name);
 }
 
 MODULE_LICENSE("GPL");
Signature · 1 line
2.40.1
author maintainer
#488 lore raw

PATCH 487/511 block: move GENHD_FL_NATIVE_CAPACITY to disk->state

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <[email protected]>

[ Upstream commit 86416916466514e4ae0b7296d20133b6427c4c1f ]

The flag to indicate an unlocked native capacity is dynamic state, not a driver capability flag, so move it to disk->state.

Stable-dep-of: 1a721de8489f ("block: don't add or resize partition on the disk with GENHD_FL_NO_PART")

---
 block/partitions/core.c | 15 ++++++---------
 include/linux/genhd.h   |  8 +-------
 2 files changed, 7 insertions(+), 16 deletions(-)
block/partitions/core.c +6 -9
index b9e9af84f5188..1ead8c0015616 100644
@@ -526,18 +526,15 @@ int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start,
 
 static bool disk_unlock_native_capacity(struct gendisk *disk)
 {
-	const struct block_device_operations *bdops = disk->fops;
-
-	if (bdops->unlock_native_capacity &&
-	    !(disk->flags & GENHD_FL_NATIVE_CAPACITY)) {
-		printk(KERN_CONT "enabling native capacity\n");
-		bdops->unlock_native_capacity(disk);
-		disk->flags |= GENHD_FL_NATIVE_CAPACITY;
-		return true;
-	} else {
+	if (!disk->fops->unlock_native_capacity ||
+	    test_and_set_bit(GD_NATIVE_CAPACITY, &disk->state)) {
 		printk(KERN_CONT "truncated\n");
 		return false;
 	}
+
+	printk(KERN_CONT "enabling native capacity\n");
+	disk->fops->unlock_native_capacity(disk);
+	return true;
 }
 
 void blk_drop_partitions(struct gendisk *disk)
include/linux/genhd.h +1 -7
index 0b48a0cf42624..3234b43fefb5c 100644
@@ -60,12 +60,6 @@ struct partition_meta_info {
  * (``BLOCK_EXT_MAJOR``).
  * This affects the maximum number of partitions.
  *
- * ``GENHD_FL_NATIVE_CAPACITY`` (0x0080): based on information in the
- * partition table, the device's capacity has been extended to its
- * native capacity; i.e. the device has hidden capacity used by one
- * of the partitions (this is a flag used so that native capacity is
- * only ever unlocked once).
- *
  * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is
  * blocked whenever a writer holds an exclusive lock.
  *
@@ -86,7 +80,6 @@ struct partition_meta_info {
 #define GENHD_FL_CD				0x0008
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	0x0020
 #define GENHD_FL_EXT_DEVT			0x0040
-#define GENHD_FL_NATIVE_CAPACITY		0x0080
 #define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE	0x0100
 #define GENHD_FL_NO_PART_SCAN			0x0200
 #define GENHD_FL_HIDDEN				0x0400
@@ -140,6 +133,7 @@ struct gendisk {
 #define GD_NEED_PART_SCAN		0
 #define GD_READ_ONLY			1
 #define GD_DEAD				2
+#define GD_NATIVE_CAPACITY		3
 
 	struct mutex open_mutex;	/* open/close mutex */
 	unsigned open_partitions;	/* number of open partitions */
Signature · 1 line
2.40.1
author maintainer
#489 lore raw

PATCH 488/511 block: move GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE to disk->event_flags

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <[email protected]>

[ Upstream commit 1545e0b419ba1d9b9bee4061d4826340afe6b0aa ]

GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE is all about the event reporting mechanism, so move it to the event_flags field.

Stable-dep-of: 1a721de8489f ("block: don't add or resize partition on the disk with GENHD_FL_NO_PART")

---
 block/bdev.c               | 2 +-
 drivers/block/paride/pcd.c | 2 +-
 drivers/scsi/sr.c          | 5 +++--
 include/linux/genhd.h      | 6 ++----
 4 files changed, 7 insertions(+), 8 deletions(-)
block/bdev.c +1 -1
index 18abafb135e0b..b8599a4088843 100644
@@ -835,7 +835,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 		 * used in blkdev_get/put().
 		 */
 		if ((mode & FMODE_WRITE) && !bdev->bd_write_holder &&
-		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
+		    (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) {
 			bdev->bd_write_holder = true;
 			unblock_events = false;
 		}
drivers/block/paride/pcd.c +1 -1
index 93ed636262328..6ac716e614e30 100644
@@ -929,8 +929,8 @@ static int pcd_init_unit(struct pcd_unit *cd, bool autoprobe, int port,
 	disk->minors = 1;
 	strcpy(disk->disk_name, cd->name);	/* umm... */
 	disk->fops = &pcd_bdops;
-	disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
 	disk->events = DISK_EVENT_MEDIA_CHANGE;
+	disk->event_flags = DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE;
 
 	if (!pi_init(cd->pi, autoprobe, port, mode, unit, protocol, delay,
 			pcd_buffer, PI_PCD, verbose, cd->name))
drivers/scsi/sr.c +3 -2
index 652cd81d77753..af210910dadf2 100644
@@ -684,9 +684,10 @@ static int sr_probe(struct device *dev)
 	disk->minors = 1;
 	sprintf(disk->disk_name, "sr%d", minor);
 	disk->fops = &sr_bdops;
-	disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+	disk->flags = GENHD_FL_CD;
 	disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST;
-	disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT;
+	disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT |
+				DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE;
 
 	blk_queue_rq_timeout(sdev->request_queue, SR_TIMEOUT);
 
include/linux/genhd.h +2 -4
index 3234b43fefb5c..300f796b8773d 100644
@@ -60,9 +60,6 @@ struct partition_meta_info {
  * (``BLOCK_EXT_MAJOR``).
  * This affects the maximum number of partitions.
  *
- * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is
- * blocked whenever a writer holds an exclusive lock.
- *
  * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled.
  * Used for loop devices in their default settings and some MMC
  * devices.
@@ -80,7 +77,6 @@ struct partition_meta_info {
 #define GENHD_FL_CD				0x0008
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	0x0020
 #define GENHD_FL_EXT_DEVT			0x0040
-#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE	0x0100
 #define GENHD_FL_NO_PART_SCAN			0x0200
 #define GENHD_FL_HIDDEN				0x0400
 
@@ -94,6 +90,8 @@ enum {
 	DISK_EVENT_FLAG_POLL			= 1 << 0,
 	/* Forward events to udev */
 	DISK_EVENT_FLAG_UEVENT			= 1 << 1,
+	/* Block event polling when open for exclusive write */
+	DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE	= 1 << 2,
 };
 
 struct disk_events;
Signature · 1 line
2.40.1
author maintainer
#490 lore raw

PATCH 489/511 block: rename GENHD_FL_NO_PART_SCAN to GENHD_FL_NO_PART

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <[email protected]>

[ Upstream commit 46e7eac647b34ed4106a8262f8bedbb90801fadd ]

The GENHD_FL_NO_PART_SCAN controls more than just partitions canning, so rename it to GENHD_FL_NO_PART.

Stable-dep-of: 1a721de8489f ("block: don't add or resize partition on the disk with GENHD_FL_NO_PART")

---
 block/genhd.c            |  2 +-
 drivers/block/loop.c     |  8 ++++----
 drivers/block/n64cart.c  |  2 +-
 drivers/mmc/core/block.c |  4 ++--
 include/linux/genhd.h    | 13 ++++++-------
 5 files changed, 14 insertions(+), 15 deletions(-)
block/genhd.c +1 -1
index a1d9e785dcf70..6123f13e148e0 100644
@@ -495,7 +495,7 @@ int device_add_disk(struct device *parent, struct gendisk *disk,
 		 * and don't bother scanning for partitions either.
 		 */
 		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
-		disk->flags |= GENHD_FL_NO_PART_SCAN;
+		disk->flags |= GENHD_FL_NO_PART;
 	} else {
 		ret = bdi_register(disk->bdi, "%u:%u",
 				   disk->major, disk->first_minor);
drivers/block/loop.c +4 -4
index c96bdb3e7ac52..1d60d5ac0db80 100644
@@ -1314,7 +1314,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
 	if (partscan)
-		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
+		lo->lo_disk->flags &= ~GENHD_FL_NO_PART;
 
 	/* enable and uncork uevent now that we are done */
 	dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0);
@@ -1463,7 +1463,7 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
 	mutex_lock(&lo->lo_mutex);
 	lo->lo_flags = 0;
 	if (!part_shift)
-		lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
+		lo->lo_disk->flags |= GENHD_FL_NO_PART;
 	lo->lo_state = Lo_unbound;
 	mutex_unlock(&lo->lo_mutex);
 
@@ -1580,7 +1580,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 
 	if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) &&
 	     !(prev_lo_flags & LO_FLAGS_PARTSCAN)) {
-		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
+		lo->lo_disk->flags &= ~GENHD_FL_NO_PART;
 		partscan = true;
 	}
 out_unlock:
@@ -2410,7 +2410,7 @@ static int loop_add(int i)
 	 * userspace tools. Parameters like this in general should be avoided.
 	 */
 	if (!part_shift)
-		disk->flags |= GENHD_FL_NO_PART_SCAN;
+		disk->flags |= GENHD_FL_NO_PART;
 	disk->flags |= GENHD_FL_EXT_DEVT;
 	atomic_set(&lo->lo_refcnt, 0);
 	mutex_init(&lo->lo_mutex);
drivers/block/n64cart.c +1 -1
index bcaabf038947c..0bda4a468c660 100644
@@ -137,7 +137,7 @@ static int __init n64cart_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	disk->first_minor = 0;
-	disk->flags = GENHD_FL_NO_PART_SCAN;
+	disk->flags = GENHD_FL_NO_PART;
 	disk->fops = &n64cart_fops;
 	disk->private_data = &pdev->dev;
 	strcpy(disk->disk_name, "n64cart");
drivers/mmc/core/block.c +2 -2
index 965b44a095077..25077a1a3d821 100644
@@ -2447,8 +2447,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	set_disk_ro(md->disk, md->read_only || default_ro);
 	md->disk->flags = GENHD_FL_EXT_DEVT;
 	if (area_type & (MMC_BLK_DATA_AREA_RPMB | MMC_BLK_DATA_AREA_BOOT))
-		md->disk->flags |= GENHD_FL_NO_PART_SCAN
-				   | GENHD_FL_SUPPRESS_PARTITION_INFO;
+		md->disk->flags |= GENHD_FL_NO_PART |
+				   GENHD_FL_SUPPRESS_PARTITION_INFO;
 
 	/*
 	 * As discussed on lkml, GENHD_FL_REMOVABLE should:
include/linux/genhd.h +6 -7
index 300f796b8773d..690b7f7996d15 100644
@@ -60,15 +60,15 @@ struct partition_meta_info {
  * (``BLOCK_EXT_MAJOR``).
  * This affects the maximum number of partitions.
  *
- * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled.
- * Used for loop devices in their default settings and some MMC
- * devices.
+ * ``GENHD_FL_NO_PART`` (0x0200): partition support is disabled.
+ * The kernel will not scan for partitions from add_disk, and users
+ * can't add partitions manually.
  *
  * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it
  * doesn't produce events, doesn't appear in sysfs, and doesn't have
  * an associated ``bdev``.
  * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and
- * ``GENHD_FL_NO_PART_SCAN``.
+ * ``GENHD_FL_NO_PART``.
  * Used for multipath devices.
  */
 #define GENHD_FL_REMOVABLE			0x0001
@@ -77,7 +77,7 @@ struct partition_meta_info {
 #define GENHD_FL_CD				0x0008
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	0x0020
 #define GENHD_FL_EXT_DEVT			0x0040
-#define GENHD_FL_NO_PART_SCAN			0x0200
+#define GENHD_FL_NO_PART			0x0200
 #define GENHD_FL_HIDDEN				0x0400
 
 enum {
@@ -185,8 +185,7 @@ static inline int disk_max_parts(struct gendisk *disk)
 
 static inline bool disk_part_scan_enabled(struct gendisk *disk)
 {
-	return disk_max_parts(disk) > 1 &&
-		!(disk->flags & GENHD_FL_NO_PART_SCAN);
+	return disk_max_parts(disk) > 1 && !(disk->flags & GENHD_FL_NO_PART);
 }
 
 static inline dev_t disk_devt(struct gendisk *disk)
Signature · 1 line
2.40.1
author maintainer
#491 lore raw

PATCH 490/511 block: dont add or resize partition on the disk with GENHD_FL_NO_PART

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Li Lingfeng <[email protected]>

[ Upstream commit 1a721de8489fa559ff4471f73c58bb74ac5580d3 ]

Commit a33df75c6328 ("block: use an xarray for disk->part_tbl") remove disk_expand_part_tbl() in add_partition(), which means all kinds of devices will support extended dynamic dev_t.
However, some devices with GENHD_FL_NO_PART are not expected to add or resize partition.
Fix this by adding check of GENHD_FL_NO_PART before add or resize partition.

---
 block/ioctl.c | 2 ++
 1 file changed, 2 insertions(+)
block/ioctl.c +2 -0
index cd506a9029630..8f39e413f12a3 100644
@@ -20,6 +20,8 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 	struct blkpg_partition p;
 	long long start, length;
 
+	if (disk->flags & GENHD_FL_NO_PART)
+		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))
Signature · 1 line
2.40.1
author maintainer
#492 lore raw

PATCH 491/511 ARM: dts: samsung: exynos4210-i9100: Fix LCD screens physical size

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paul Cercueil <[email protected]>

[ Upstream commit b3f3fc32e5ff1e848555af8616318cc667457f90 ]

The previous values were completely bogus, and resulted in the computed DPI ratio being much lower than reality, causing applications and UIs to misbehave.

The new values were measured by myself with a ruler.

Fixes 8620cc2f99b7 ("ARM: dts: exynos: Add devicetree file for the Galaxy S2")
Cc <[email protected]> # v5.8+
---
 arch/arm/boot/dts/exynos4210-i9100.dts | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
arch/arm/boot/dts/exynos4210-i9100.dts +2 -2
index 5f5d9b1357365..93880bdbcad98 100644
@@ -200,8 +200,8 @@
 			power-on-delay = <10>;
 			reset-delay = <10>;
 
-			panel-width-mm = <90>;
-			panel-height-mm = <154>;
+			panel-width-mm = <56>;
+			panel-height-mm = <93>;
 
 			display-timings {
 				timing {
Signature · 1 line
2.40.1
author maintainer
#493 lore raw

PATCH 492/511 ARM: dts: BCM5301X: Extend RAM to full 256MB for Linksys EA6500 V2

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aleksey Nasibulin <[email protected]>

[ Upstream commit 91994e59079dcb455783d3f9ea338eea6f671af3 ]

Linksys ea6500-v2 have 256MB of ram. Currently we only use 128MB. Expand the definition to use all the available RAM.

---
 arch/arm/boot/dts/bcm4708-linksys-ea6500-v2.dts | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
arch/arm/boot/dts/bcm4708-linksys-ea6500-v2.dts +2 -1
index cd797b4202ad8..01c48faabfade 100644
@@ -19,7 +19,8 @@
 
 	memory@0 {
 		device_type = "memory";
-		reg = <0x00000000 0x08000000>;
+		reg = <0x00000000 0x08000000>,
+		      <0x88000000 0x08000000>;
 	};
 
 	gpio-keys {
Signature · 1 line
2.40.1
author maintainer
#494 lore raw

PATCH 493/511 net: ipv4: fix one memleak in __inet_del_ifa()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Liu Jian <[email protected]>

[ Upstream commit ac28b1ec6135649b5d78b028e47264cb3ebca5ea ]

I got the below warning when do fuzzing test:
unregister_netdevice: waiting for bond0 to become free. Usage count = 2

It can be repoduced via:

ip link add bond0 type bond
sysctl -w net.ipv4.conf.bond0.promote_secondaries=1 ip addr add 4.117.174.103/0 scope 0x40 dev bond0
ip addr add 192.168.100.111/255.255.255.254 scope 0 dev bond0 ip addr add 0.0.0.4/0 scope 0x40 secondary dev bond0 ip addr del 4.117.174.103/0 scope 0x40 dev bond0
ip link delete bond0 type bond

In this reproduction test case, an incorrect 'last_prim' is found in __inet_del_ifa(), as a result, the secondary address(0.0.0.4/0 scope 0x40) is lost. The memory of the secondary address is leaked and the reference of in_device and net_device is leaked.

Fix this problem:
Look for 'last_prim' starting at location of the deleted IP and inserting the promoted IP into the location of 'last_prim'.

Fixes 0ff60a45678e ("[IPV4]: Fix secondary IP addresses after promotion")
---
 net/ipv4/devinet.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
net/ipv4/devinet.c +5 -5
index 9ac41ffdc6344..c511751c2f41a 100644
@@ -351,14 +351,14 @@ static void __inet_del_ifa(struct in_device *in_dev,
 {
 	struct in_ifaddr *promote = NULL;
 	struct in_ifaddr *ifa, *ifa1;
-	struct in_ifaddr *last_prim;
+	struct in_ifaddr __rcu **last_prim;
 	struct in_ifaddr *prev_prom = NULL;
 	int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev);
 
 	ASSERT_RTNL();
 
 	ifa1 = rtnl_dereference(*ifap);
-	last_prim = rtnl_dereference(in_dev->ifa_list);
+	last_prim = ifap;
 	if (in_dev->dead)
 		goto no_promotions;
 
@@ -372,7 +372,7 @@ static void __inet_del_ifa(struct in_device *in_dev,
 		while ((ifa = rtnl_dereference(*ifap1)) != NULL) {
 			if (!(ifa->ifa_flags & IFA_F_SECONDARY) &&
 			    ifa1->ifa_scope <= ifa->ifa_scope)
-				last_prim = ifa;
+				last_prim = &ifa->ifa_next;
 
 			if (!(ifa->ifa_flags & IFA_F_SECONDARY) ||
 			    ifa1->ifa_mask != ifa->ifa_mask ||
@@ -436,9 +436,9 @@ static void __inet_del_ifa(struct in_device *in_dev,
 
 			rcu_assign_pointer(prev_prom->ifa_next, next_sec);
 
-			last_sec = rtnl_dereference(last_prim->ifa_next);
+			last_sec = rtnl_dereference(*last_prim);
 			rcu_assign_pointer(promote->ifa_next, last_sec);
-			rcu_assign_pointer(last_prim->ifa_next, promote);
+			rcu_assign_pointer(*last_prim, promote);
 		}
 
 		promote->ifa_flags &= ~IFA_F_SECONDARY;
Signature · 1 line
2.40.1
author maintainer
#495 lore raw

PATCH 494/511 kselftest/runner.sh: Propagate SIGTERM to runner child

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Björn Töpel <[email protected]>

[ Upstream commit 9616cb34b08ec86642b162eae75c5a7ca8debe3c ]

Timeouts in kselftest are done using the "timeout" command with the "--foreground" option. Without the "foreground" option, it is not possible for a user to cancel the runner using SIGINT, because the signal is not propagated to timeout which is running in a different process group. The "forground" options places the timeout in the same process group as its parent, but only sends the SIGTERM (on timeout) signal to the forked process. Unfortunately, this does not play nice with all kselftests, e.g. "net:fcnal-test.sh", where the child processes will linger because timeout does not send SIGTERM to the group.

Some users have noted these hangs [1].

Fix this by nesting the timeout with an additional timeout without the foreground option.

Fixes 651e0d881461 ("kselftest/runner: allow to properly deliver signals to tests")
---
 tools/testing/selftests/kselftest/runner.sh | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
tools/testing/selftests/kselftest/runner.sh +2 -1
index a9ba782d8ca0f..83616f0779a7e 100644
@@ -33,7 +33,8 @@ tap_timeout()
 {
 	# Make sure tests will time out if utility is available.
 	if [ -x /usr/bin/timeout ] ; then
-		/usr/bin/timeout --foreground "$kselftest_timeout" $1
+		/usr/bin/timeout --foreground "$kselftest_timeout" \
+			/usr/bin/timeout "$kselftest_timeout" $1
 	else
 		$1
 	fi
Signature · 1 line
2.40.1
author maintainer
#496 lore raw

PATCH 495/511 net/smc: use smc_lgr_list.lock to protect smc_lgr_list.list iterate in smcr_port_add

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Guangguan Wang <[email protected]>

[ Upstream commit f5146e3ef0a9eea405874b36178c19a4863b8989 ]

While doing smcr_port_add, there maybe linkgroup add into or delete from smc_lgr_list.list at the same time, which may result kernel crash. So, use smc_lgr_list.lock to protect smc_lgr_list.list iterate in smcr_port_add.

The crash calltrace show below:

BUG: kernel NULL pointer dereference, address: 0000000000000000
PGD 0 P4D 0
Oops: 0000 [#1] SMP NOPTI
CPU: 0 PID: 559726 Comm: kworker/0:92 Kdump: loaded Tainted: G
Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 449e491 04/01/2014
Workqueue: events smc_ib_port_event_work [smc]
RIP: 0010:smcr_port_add+0xa6/0xf0 [smc]
RSP: 0000:ffffa5a2c8f67de0 EFLAGS: 00010297
RAX: 0000000000000001 RBX: ffff9935e0650000 RCX: 0000000000000000
RDX: 0000000000000010 RSI: ffff9935e0654290 RDI: ffff9935c8560000
RBP: 0000000000000000 R08: 0000000000000000 R09: ffff9934c0401918
R10: 0000000000000000 R11: ffffffffb4a5c278 R12: ffff99364029aae4
R13: ffff99364029aa00 R14: 00000000ffffffed R15: ffff99364029ab08
FS:  0000000000000000(0000) GS:ffff994380600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 0000000f06a10003 CR4: 0000000002770ef0
PKRU: 55555554
Call Trace:
 smc_ib_port_event_work+0x18f/0x380 [smc]
 process_one_work+0x19b/0x340
 worker_thread+0x30/0x370
 ? process_one_work+0x340/0x340
 kthread+0x114/0x130
 ? __kthread_cancel_work+0x50/0x50
 ret_from_fork+0x1f/0x30
Fixes 1f90a05d9ff9 ("net/smc: add smcr_port_add() and smcr_link_up() processing")
---
 net/smc/smc_core.c | 2 ++
 1 file changed, 2 insertions(+)
net/smc/smc_core.c +2 -0
index f08fcc50fad3c..b84896acd4732 100644
@@ -1486,6 +1486,7 @@ void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport)
 {
 	struct smc_link_group *lgr, *n;
 
+	spin_lock_bh(&smc_lgr_list.lock);
 	list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) {
 		struct smc_link *link;
 
@@ -1500,6 +1501,7 @@ void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport)
 		if (link)
 			smc_llc_add_link_local(link);
 	}
+	spin_unlock_bh(&smc_lgr_list.lock);
 }
 
 /* link is down - switch connections to alternate link,
Signature · 1 line
2.40.1
author maintainer
#497 lore raw

PATCH 496/511 net: ethernet: mvpp2_main: fix possible OOB write in mvpp2_ethtool_get_rxnfc()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hangyu Hua <[email protected]>

[ Upstream commit 51fe0a470543f345e3c62b6798929de3ddcedc1d ]

rules is allocated in ethtool_get_rxnfc and the size is determined by rule_cnt from user space. So rule_cnt needs to be check before using rules to avoid OOB writing or NULL pointer dereference.

Fixes 90b509b39ac9 ("net: mvpp2: cls: Add Classification offload support")
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 5 +++++
 1 file changed, 5 insertions(+)
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +5 -0
index ddd4ed34b0f20..31b3ede563c04 100644
@@ -5572,6 +5572,11 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
 		break;
 	case ETHTOOL_GRXCLSRLALL:
 		for (i = 0; i < MVPP2_N_RFS_ENTRIES_PER_FLOW; i++) {
+			if (loc == info->rule_cnt) {
+				ret = -EMSGSIZE;
+				break;
+			}
+
 			if (port->rfs_rules[i])
 				rules[loc++] = i;
 		}
Signature · 1 line
2.40.1
author maintainer
#498 lore raw

PATCH 497/511 net: ethernet: mtk_eth_soc: fix possible NULL pointer dereference in mtk_hwlro_get_fdir_all()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hangyu Hua <[email protected]>

[ Upstream commit e4c79810755f66c9a933ca810da2724133b1165a ]

rule_locs is allocated in ethtool_get_rxnfc and the size is determined by rule_cnt from user space. So rule_cnt needs to be check before using rule_locs to avoid NULL pointer dereference.

Fixes 7aab747e5563 ("net: ethernet: mediatek: add ethtool functions to configure RX flows of HW LRO")
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/net/ethernet/mediatek/mtk_eth_soc.c +3 -0
index 50ee9d3d4c841..139dfdb1e58bd 100644
@@ -2038,6 +2038,9 @@ static int mtk_hwlro_get_fdir_all(struct net_device *dev,
 	int i;
 
 	for (i = 0; i < MTK_MAX_LRO_IP_CNT; i++) {
+		if (cnt == cmd->rule_cnt)
+			return -EMSGSIZE;
+
 		if (mac->hwlro_ip[i]) {
 			rule_locs[cnt] = i;
 			cnt++;
Signature · 1 line
2.40.1
author maintainer
#499 lore raw

PATCH 498/511 hsr: Fix uninit-value access in fill_frame_info()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ziyang Xuan <[email protected]>

[ Upstream commit 484b4833c604c0adcf19eac1ca14b60b757355b5 ]

Syzbot reports the following uninit-value access problem.

=====================================================

BUG: KMSAN: uninit-value in fill_frame_info net/hsr/hsr_forward.c:601 [inline]
BUG: KMSAN: uninit-value in hsr_forward_skb+0x9bd/0x30f0 net/hsr/hsr_forward.c:616
 fill_frame_info net/hsr/hsr_forward.c:601 [inline]
 hsr_forward_skb+0x9bd/0x30f0 net/hsr/hsr_forward.c:616
 hsr_dev_xmit+0x192/0x330 net/hsr/hsr_device.c:223
 __netdev_start_xmit include/linux/netdevice.h:4889 [inline]
 netdev_start_xmit include/linux/netdevice.h:4903 [inline]
 xmit_one net/core/dev.c:3544 [inline]
 dev_hard_start_xmit+0x247/0xa10 net/core/dev.c:3560
 __dev_queue_xmit+0x34d0/0x52a0 net/core/dev.c:4340
 dev_queue_xmit include/linux/netdevice.h:3082 [inline]
 packet_xmit+0x9c/0x6b0 net/packet/af_packet.c:276
 packet_snd net/packet/af_packet.c:3087 [inline]
 packet_sendmsg+0x8b1d/0x9f30 net/packet/af_packet.c:3119
 sock_sendmsg_nosec net/socket.c:730 [inline]
 sock_sendmsg net/socket.c:753 [inline]
 __sys_sendto+0x781/0xa30 net/socket.c:2176
 __do_sys_sendto net/socket.c:2188 [inline]
 __se_sys_sendto net/socket.c:2184 [inline]
 __ia32_sys_sendto+0x11f/0x1c0 net/socket.c:2184
 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline]
 __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178
 do_fast_syscall_32+0x37/0x80 arch/x86/entry/common.c:203
 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:246
 entry_SYSENTER_compat_after_hwframe+0x70/0x82

Uninit was created at:

 slab_post_alloc_hook+0x12f/0xb70 mm/slab.h:767
 slab_alloc_node mm/slub.c:3478 [inline]
 kmem_cache_alloc_node+0x577/0xa80 mm/slub.c:3523
 kmalloc_reserve+0x148/0x470 net/core/skbuff.c:559
 __alloc_skb+0x318/0x740 net/core/skbuff.c:644
 alloc_skb include/linux/skbuff.h:1286 [inline]
 alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6299
 sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2794
 packet_alloc_skb net/packet/af_packet.c:2936 [inline]
 packet_snd net/packet/af_packet.c:3030 [inline]
 packet_sendmsg+0x70e8/0x9f30 net/packet/af_packet.c:3119
 sock_sendmsg_nosec net/socket.c:730 [inline]
 sock_sendmsg net/socket.c:753 [inline]
 __sys_sendto+0x781/0xa30 net/socket.c:2176
 __do_sys_sendto net/socket.c:2188 [inline]
 __se_sys_sendto net/socket.c:2184 [inline]
 __ia32_sys_sendto+0x11f/0x1c0 net/socket.c:2184
 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline]
 __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178
 do_fast_syscall_32+0x37/0x80 arch/x86/entry/common.c:203
 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:246
 entry_SYSENTER_compat_after_hwframe+0x70/0x82

It is because VLAN not yet supported in hsr driver. Return error when protocol is ETH_P_8021Q in fill_frame_info() now to fix it.

Fixes 451d8123f897 ("net: prp: add packet handling support")
Reported-by [email protected]
---
 net/hsr/hsr_forward.c | 1 +
 1 file changed, 1 insertion(+)
net/hsr/hsr_forward.c +1 -0
index 35382ed686d1d..12ba43023d30e 100644
@@ -552,6 +552,7 @@ static int fill_frame_info(struct hsr_frame_info *frame,
 		proto = vlan_hdr->vlanhdr.h_vlan_encapsulated_proto;
 		/* FIXME: */
 		netdev_warn_once(skb->dev, "VLAN not yet supported");
+		return -EINVAL;
 	}
 
 	frame->is_from_san = false;
Signature · 1 line
2.40.1
author maintainer
#500 lore raw

PATCH 499/511 net: dsa: sja1105: hide all multicast addresses from "bridge fdb show"

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vladimir Oltean <[email protected]>

[ Upstream commit 02c652f5465011126152bbd93b6a582a1d0c32f1 ]

Commit 4d9423549501 ("net: dsa: sja1105: offload bridge port flags to device") has partially hidden some multicast entries from showing up in the "bridge fdb show" output, but it wasn't enough. Addresses which are added through "bridge mdb add" still show up. Hide them all.

Fixes 291d1e72b756 ("net: dsa: sja1105: Add support for FDB and MDB management")
---
 drivers/net/dsa/sja1105/sja1105_main.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)
drivers/net/dsa/sja1105/sja1105_main.c +6 -5
index d5600d0d6ef10..493192a8000c8 100644
@@ -1794,13 +1794,14 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port,
 		if (!(l2_lookup.destports & BIT(port)))
 			continue;
 
-		/* We need to hide the FDB entry for unknown multicast */
-		if (l2_lookup.macaddr == SJA1105_UNKNOWN_MULTICAST &&
-		    l2_lookup.mask_macaddr == SJA1105_UNKNOWN_MULTICAST)
-			continue;
-
 		u64_to_ether_addr(l2_lookup.macaddr, macaddr);
 
+		/* Hardware FDB is shared for fdb and mdb, "bridge fdb show"
+		 * only wants to see unicast
+		 */
+		if (is_multicast_ether_addr(macaddr))
+			continue;
+
 		/* We need to hide the dsa_8021q VLANs from the user. */
 		if (!priv->vlan_aware)
 			l2_lookup.vlanid = 0;
Signature · 1 line
2.40.1
author maintainer
#501 lore raw

PATCH 500/511 r8152: check budget for r8152_poll()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hayes Wang <[email protected]>

[ Upstream commit a7b8d60b37237680009dd0b025fe8c067aba0ee3 ]

According to the document of napi, there is no rx process when the budget is 0. Therefore, r8152_poll() has to return 0 directly when the budget is equal to 0.

Fixes d2187f8e4454 ("r8152: divide the tx and rx bottom functions")
---
 drivers/net/usb/r8152.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/net/usb/r8152.c +3 -0
index 579524cb5d9b2..4cd9bcca84c5b 100644
@@ -2625,6 +2625,9 @@ static int r8152_poll(struct napi_struct *napi, int budget)
 	struct r8152 *tp = container_of(napi, struct r8152, napi);
 	int work_done;
 
+	if (!budget)
+		return 0;
+
 	work_done = rx_bottom(tp, budget);
 
 	if (work_done < budget) {
Signature · 1 line
2.40.1
author maintainer
#502 lore raw

PATCH 501/511 kcm: Fix memory leak in error path of kcm_sendmsg()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shigeru Yoshida <[email protected]>

[ Upstream commit c821a88bd720b0046433173185fd841a100d44ad ]

syzbot reported a memory leak like below:

BUG: memory leak
unreferenced object 0xffff88810b088c00 (size 240):
  comm "syz-executor186", pid 5012, jiffies 4294943306 (age 13.680s)
  hex dump (first 32 bytes):
    00 89 08 0b 81 88 ff ff 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff83e5d5ff>] __alloc_skb+0x1ef/0x230 net/core/skbuff.c:634
    [<ffffffff84606e59>] alloc_skb include/linux/skbuff.h:1289 [inline]
    [<ffffffff84606e59>] kcm_sendmsg+0x269/0x1050 net/kcm/kcmsock.c:815
    [<ffffffff83e479c6>] sock_sendmsg_nosec net/socket.c:725 [inline]
    [<ffffffff83e479c6>] sock_sendmsg+0x56/0xb0 net/socket.c:748
    [<ffffffff83e47f55>] ____sys_sendmsg+0x365/0x470 net/socket.c:2494
    [<ffffffff83e4c389>] ___sys_sendmsg+0xc9/0x130 net/socket.c:2548
    [<ffffffff83e4c536>] __sys_sendmsg+0xa6/0x120 net/socket.c:2577
    [<ffffffff84ad7bb8>] do_syscall_x64 arch/x86/entry/common.c:50 [inline]
    [<ffffffff84ad7bb8>] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80
    [<ffffffff84c0008b>] entry_SYSCALL_64_after_hwframe+0x63/0xcd

In kcm_sendmsg(), kcm_tx_msg(head)->last_skb is used as a cursor to append newly allocated skbs to 'head'. If some bytes are copied, an error occurred, and jumped to out_error label, 'last_skb' is left unmodified. A later kcm_sendmsg() will use an obsoleted 'last_skb' reference, corrupting the 'head' frag_list and causing the leak.

This patch fixes this issue by properly updating the last allocated skb in 'last_skb'.

Fixes ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Reported-and-tested-by [email protected]
---
 net/kcm/kcmsock.c | 2 ++
 1 file changed, 2 insertions(+)
net/kcm/kcmsock.c +2 -0
index 43005bba2d407..2d06617e89891 100644
@@ -1073,6 +1073,8 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 	if (head != kcm->seq_skb)
 		kfree_skb(head);
+	else if (copied)
+		kcm_tx_msg(head)->last_skb = skb;
 
 	err = sk_stream_error(sk, msg->msg_flags, err);
 
Signature · 1 line
2.40.1
author maintainer
#503 lore raw

PATCH 502/511 platform/mellanox: mlxbf-tmfifo: Drop the Rx packet if no more descriptors

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Liming Sun <[email protected]>

[ Upstream commit 78034cbece79c2d730ad0770b3b7f23eedbbecf5 ]

This commit fixes tmfifo console stuck issue when the virtual networking interface is in down state. In such case, the network Rx descriptors runs out and causes the Rx network packet staying in the head of the tmfifo thus blocking the console packets. The fix is to drop the Rx network packet when no more Rx descriptors. Function name mlxbf_tmfifo_release_pending_pkt() is also renamed to mlxbf_tmfifo_release_pkt() to be more approperiate.

---
 drivers/platform/mellanox/mlxbf-tmfifo.c | 66 ++++++++++++++++++------
 1 file changed, 49 insertions(+), 17 deletions(-)
drivers/platform/mellanox/mlxbf-tmfifo.c +49 -17
index 64d22ecf3cddd..42fcccf06157f 100644
@@ -56,6 +56,7 @@ struct mlxbf_tmfifo;
  * @vq: pointer to the virtio virtqueue
  * @desc: current descriptor of the pending packet
  * @desc_head: head descriptor of the pending packet
+ * @drop_desc: dummy desc for packet dropping
  * @cur_len: processed length of the current descriptor
  * @rem_len: remaining length of the pending packet
  * @pkt_len: total length of the pending packet
@@ -72,6 +73,7 @@ struct mlxbf_tmfifo_vring {
 	struct virtqueue *vq;
 	struct vring_desc *desc;
 	struct vring_desc *desc_head;
+	struct vring_desc drop_desc;
 	int cur_len;
 	int rem_len;
 	u32 pkt_len;
@@ -83,6 +85,14 @@ struct mlxbf_tmfifo_vring {
 	struct mlxbf_tmfifo *fifo;
 };
 
+/* Check whether vring is in drop mode. */
+#define IS_VRING_DROP(_r) ({ \
+	typeof(_r) (r) = (_r); \
+	(r->desc_head == &r->drop_desc ? true : false); })
+
+/* A stub length to drop maximum length packet. */
+#define VRING_DROP_DESC_MAX_LEN		GENMASK(15, 0)
+
 /* Interrupt types. */
 enum {
 	MLXBF_TM_RX_LWM_IRQ,
@@ -243,6 +253,7 @@ static int mlxbf_tmfifo_alloc_vrings(struct mlxbf_tmfifo *fifo,
 		vring->align = SMP_CACHE_BYTES;
 		vring->index = i;
 		vring->vdev_id = tm_vdev->vdev.id.device;
+		vring->drop_desc.len = VRING_DROP_DESC_MAX_LEN;
 		dev = &tm_vdev->vdev.dev;
 
 		size = vring_size(vring->num, vring->align);
@@ -348,7 +359,7 @@ static u32 mlxbf_tmfifo_get_pkt_len(struct mlxbf_tmfifo_vring *vring,
 	return len;
 }
 
-static void mlxbf_tmfifo_release_pending_pkt(struct mlxbf_tmfifo_vring *vring)
+static void mlxbf_tmfifo_release_pkt(struct mlxbf_tmfifo_vring *vring)
 {
 	struct vring_desc *desc_head;
 	u32 len = 0;
@@ -577,19 +588,25 @@ static void mlxbf_tmfifo_rxtx_word(struct mlxbf_tmfifo_vring *vring,
 
 	if (vring->cur_len + sizeof(u64) <= len) {
 		/* The whole word. */
-		if (is_rx)
-			memcpy(addr + vring->cur_len, &data, sizeof(u64));
-		else
-			memcpy(&data, addr + vring->cur_len, sizeof(u64));
+		if (!IS_VRING_DROP(vring)) {
+			if (is_rx)
+				memcpy(addr + vring->cur_len, &data,
+				       sizeof(u64));
+			else
+				memcpy(&data, addr + vring->cur_len,
+				       sizeof(u64));
+		}
 		vring->cur_len += sizeof(u64);
 	} else {
 		/* Leftover bytes. */
-		if (is_rx)
-			memcpy(addr + vring->cur_len, &data,
-			       len - vring->cur_len);
-		else
-			memcpy(&data, addr + vring->cur_len,
-			       len - vring->cur_len);
+		if (!IS_VRING_DROP(vring)) {
+			if (is_rx)
+				memcpy(addr + vring->cur_len, &data,
+				       len - vring->cur_len);
+			else
+				memcpy(&data, addr + vring->cur_len,
+				       len - vring->cur_len);
+		}
 		vring->cur_len = len;
 	}
 
@@ -690,8 +707,16 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring,
 	/* Get the descriptor of the next packet. */
 	if (!vring->desc) {
 		desc = mlxbf_tmfifo_get_next_pkt(vring, is_rx);
-		if (!desc)
-			return false;
+		if (!desc) {
+			/* Drop next Rx packet to avoid stuck. */
+			if (is_rx) {
+				desc = &vring->drop_desc;
+				vring->desc_head = desc;
+				vring->desc = desc;
+			} else {
+				return false;
+			}
+		}
 	} else {
 		desc = vring->desc;
 	}
@@ -724,17 +749,24 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring,
 		vring->rem_len -= len;
 
 		/* Get the next desc on the chain. */
-		if (vring->rem_len > 0 &&
+		if (!IS_VRING_DROP(vring) && vring->rem_len > 0 &&
 		    (virtio16_to_cpu(vdev, desc->flags) & VRING_DESC_F_NEXT)) {
 			idx = virtio16_to_cpu(vdev, desc->next);
 			desc = &vr->desc[idx];
 			goto mlxbf_tmfifo_desc_done;
 		}
 
-		/* Done and release the pending packet. */
-		mlxbf_tmfifo_release_pending_pkt(vring);
+		/* Done and release the packet. */
 		desc = NULL;
 		fifo->vring[is_rx] = NULL;
+		if (!IS_VRING_DROP(vring)) {
+			mlxbf_tmfifo_release_pkt(vring);
+		} else {
+			vring->pkt_len = 0;
+			vring->desc_head = NULL;
+			vring->desc = NULL;
+			return false;
+		}
 
 		/*
 		 * Make sure the load/store are in order before
@@ -914,7 +946,7 @@ static void mlxbf_tmfifo_virtio_del_vqs(struct virtio_device *vdev)
 
 		/* Release the pending packet. */
 		if (vring->desc)
-			mlxbf_tmfifo_release_pending_pkt(vring);
+			mlxbf_tmfifo_release_pkt(vring);
 		vq = vring->vq;
 		if (vq) {
 			vring->vq = NULL;
Signature · 1 line
2.40.1
author maintainer
#504 lore raw

PATCH 503/511 platform/mellanox: mlxbf-tmfifo: Drop jumbo frames

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Liming Sun <[email protected]>

[ Upstream commit fc4c655821546239abb3cf4274d66b9747aa87dd ]

This commit drops over-sized network packets to avoid tmfifo queue stuck.

---
 drivers/platform/mellanox/mlxbf-tmfifo.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)
drivers/platform/mellanox/mlxbf-tmfifo.c +17 -7
index 42fcccf06157f..194f3205e5597 100644
@@ -205,7 +205,7 @@ static u8 mlxbf_tmfifo_net_default_mac[ETH_ALEN] = {
 static efi_char16_t mlxbf_tmfifo_efi_name[] = L"RshimMacAddr";
 
 /* Maximum L2 header length. */
-#define MLXBF_TMFIFO_NET_L2_OVERHEAD	36
+#define MLXBF_TMFIFO_NET_L2_OVERHEAD	(ETH_HLEN + VLAN_HLEN)
 
 /* Supported virtio-net features. */
 #define MLXBF_TMFIFO_NET_FEATURES \
@@ -623,13 +623,14 @@ static void mlxbf_tmfifo_rxtx_word(struct mlxbf_tmfifo_vring *vring,
  * flag is set.
  */
 static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring,
-				     struct vring_desc *desc,
+				     struct vring_desc **desc,
 				     bool is_rx, bool *vring_change)
 {
 	struct mlxbf_tmfifo *fifo = vring->fifo;
 	struct virtio_net_config *config;
 	struct mlxbf_tmfifo_msg_hdr hdr;
 	int vdev_id, hdr_len;
+	bool drop_rx = false;
 
 	/* Read/Write packet header. */
 	if (is_rx) {
@@ -649,8 +650,8 @@ static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring,
 			if (ntohs(hdr.len) >
 			    __virtio16_to_cpu(virtio_legacy_is_little_endian(),
 					      config->mtu) +
-			    MLXBF_TMFIFO_NET_L2_OVERHEAD)
-				return;
+					      MLXBF_TMFIFO_NET_L2_OVERHEAD)
+				drop_rx = true;
 		} else {
 			vdev_id = VIRTIO_ID_CONSOLE;
 			hdr_len = 0;
@@ -665,16 +666,25 @@ static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring,
 
 			if (!tm_dev2)
 				return;
-			vring->desc = desc;
+			vring->desc = *desc;
 			vring = &tm_dev2->vrings[MLXBF_TMFIFO_VRING_RX];
 			*vring_change = true;
 		}
+
+		if (drop_rx && !IS_VRING_DROP(vring)) {
+			if (vring->desc_head)
+				mlxbf_tmfifo_release_pkt(vring);
+			*desc = &vring->drop_desc;
+			vring->desc_head = *desc;
+			vring->desc = *desc;
+		}
+
 		vring->pkt_len = ntohs(hdr.len) + hdr_len;
 	} else {
 		/* Network virtio has an extra header. */
 		hdr_len = (vring->vdev_id == VIRTIO_ID_NET) ?
 			   sizeof(struct virtio_net_hdr) : 0;
-		vring->pkt_len = mlxbf_tmfifo_get_pkt_len(vring, desc);
+		vring->pkt_len = mlxbf_tmfifo_get_pkt_len(vring, *desc);
 		hdr.type = (vring->vdev_id == VIRTIO_ID_NET) ?
 			    VIRTIO_ID_NET : VIRTIO_ID_CONSOLE;
 		hdr.len = htons(vring->pkt_len - hdr_len);
@@ -723,7 +733,7 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring,
 
 	/* Beginning of a packet. Start to Rx/Tx packet header. */
 	if (vring->pkt_len == 0) {
-		mlxbf_tmfifo_rxtx_header(vring, desc, is_rx, &vring_change);
+		mlxbf_tmfifo_rxtx_header(vring, &desc, is_rx, &vring_change);
 		(*avail)--;
 
 		/* Return if new packet is for another ring. */
Signature · 1 line
2.40.1
author maintainer
#505 lore raw

PATCH 504/511 platform/mellanox: mlxbf-pmc: Fix potential buffer overflows

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shravan Kumar Ramani <[email protected]>

[ Upstream commit 80ccd40568bcd3655b0fd0be1e9b3379fd6e1056 ]

Replace sprintf with sysfs_emit where possible.
Size check in mlxbf_pmc_event_list_show should account for "\0".

---
 drivers/platform/mellanox/mlxbf-pmc.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
drivers/platform/mellanox/mlxbf-pmc.c +7 -7
index be967d797c28e..95afcae7b9fa9 100644
@@ -1008,7 +1008,7 @@ static ssize_t mlxbf_pmc_counter_show(struct device *dev,
 	} else
 		return -EINVAL;
 
-	return sprintf(buf, "0x%llx\n", value);
+	return sysfs_emit(buf, "0x%llx\n", value);
 }
 
 /* Store function for "counter" sysfs files */
@@ -1078,13 +1078,13 @@ static ssize_t mlxbf_pmc_event_show(struct device *dev,
 
 	err = mlxbf_pmc_read_event(blk_num, cnt_num, is_l3, &evt_num);
 	if (err)
-		return sprintf(buf, "No event being monitored\n");
+		return sysfs_emit(buf, "No event being monitored\n");
 
 	evt_name = mlxbf_pmc_get_event_name(pmc->block_name[blk_num], evt_num);
 	if (!evt_name)
 		return -EINVAL;
 
-	return sprintf(buf, "0x%llx: %s\n", evt_num, evt_name);
+	return sysfs_emit(buf, "0x%llx: %s\n", evt_num, evt_name);
 }
 
 /* Store function for "event" sysfs files */
@@ -1139,9 +1139,9 @@ static ssize_t mlxbf_pmc_event_list_show(struct device *dev,
 		return -EINVAL;
 
 	for (i = 0, buf[0] = '\0'; i < size; ++i) {
-		len += sprintf(e_info, "0x%x: %s\n", events[i].evt_num,
-			       events[i].evt_name);
-		if (len > PAGE_SIZE)
+		len += snprintf(e_info, sizeof(e_info), "0x%x: %s\n",
+				events[i].evt_num, events[i].evt_name);
+		if (len >= PAGE_SIZE)
 			break;
 		strcat(buf, e_info);
 		ret = len;
@@ -1168,7 +1168,7 @@ static ssize_t mlxbf_pmc_enable_show(struct device *dev,
 
 	value = FIELD_GET(MLXBF_PMC_L3C_PERF_CNT_CFG_EN, perfcnt_cfg);
 
-	return sprintf(buf, "%d\n", value);
+	return sysfs_emit(buf, "%d\n", value);
 }
 
 /* Store function for "enable" sysfs files - only for l3cache */
Signature · 1 line
2.40.1
author maintainer
#506 lore raw

PATCH 505/511 platform/mellanox: mlxbf-pmc: Fix reading of unprogrammed events

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shravan Kumar Ramani <[email protected]>

[ Upstream commit 0f5969452e162efc50bdc98968fb62b424a9874b ]

This fix involves 2 changes:
- All event regs have a reset value of 0, which is not a valid event_number as per the event_list for most blocks and hence seen as an error. Add a "disable" event with event_number 0 for all blocks.

- The enable bit for each counter need not be checked before reading the event info, and hence removed.

---
 drivers/platform/mellanox/mlxbf-pmc.c | 27 +++++++--------------------
 1 file changed, 7 insertions(+), 20 deletions(-)
drivers/platform/mellanox/mlxbf-pmc.c +7 -20
index 95afcae7b9fa9..2d4bbe99959ef 100644
@@ -191,6 +191,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_smgen_events[] = {
 };
 
 static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_1[] = {
+	{ 0x0, "DISABLE" },
 	{ 0xa0, "TPIO_DATA_BEAT" },
 	{ 0xa1, "TDMA_DATA_BEAT" },
 	{ 0xa2, "MAP_DATA_BEAT" },
@@ -214,6 +215,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_1[] = {
 };
 
 static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_2[] = {
+	{ 0x0, "DISABLE" },
 	{ 0xa0, "TPIO_DATA_BEAT" },
 	{ 0xa1, "TDMA_DATA_BEAT" },
 	{ 0xa2, "MAP_DATA_BEAT" },
@@ -246,6 +248,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_2[] = {
 };
 
 static const struct mlxbf_pmc_events mlxbf_pmc_ecc_events[] = {
+	{ 0x0, "DISABLE" },
 	{ 0x100, "ECC_SINGLE_ERROR_CNT" },
 	{ 0x104, "ECC_DOUBLE_ERROR_CNT" },
 	{ 0x114, "SERR_INJ" },
@@ -258,6 +261,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_ecc_events[] = {
 };
 
 static const struct mlxbf_pmc_events mlxbf_pmc_mss_events[] = {
+	{ 0x0, "DISABLE" },
 	{ 0xc0, "RXREQ_MSS" },
 	{ 0xc1, "RXDAT_MSS" },
 	{ 0xc2, "TXRSP_MSS" },
@@ -265,6 +269,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_mss_events[] = {
 };
 
 static const struct mlxbf_pmc_events mlxbf_pmc_hnf_events[] = {
+	{ 0x0, "DISABLE" },
 	{ 0x45, "HNF_REQUESTS" },
 	{ 0x46, "HNF_REJECTS" },
 	{ 0x47, "ALL_BUSY" },
@@ -323,6 +328,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_hnf_events[] = {
 };
 
 static const struct mlxbf_pmc_events mlxbf_pmc_hnfnet_events[] = {
+	{ 0x0, "DISABLE" },
 	{ 0x12, "CDN_REQ" },
 	{ 0x13, "DDN_REQ" },
 	{ 0x14, "NDN_REQ" },
@@ -892,7 +898,7 @@ static int mlxbf_pmc_read_event(int blk_num, uint32_t cnt_num, bool is_l3,
 				uint64_t *result)
 {
 	uint32_t perfcfg_offset, perfval_offset;
-	uint64_t perfmon_cfg, perfevt, perfctl;
+	uint64_t perfmon_cfg, perfevt;
 
 	if (cnt_num >= pmc->block[blk_num].counters)
 		return -EINVAL;
@@ -904,25 +910,6 @@ static int mlxbf_pmc_read_event(int blk_num, uint32_t cnt_num, bool is_l3,
 	perfval_offset = perfcfg_offset +
 			 pmc->block[blk_num].counters * MLXBF_PMC_REG_SIZE;
 
-	/* Set counter in "read" mode */
-	perfmon_cfg = FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_ADDR,
-				 MLXBF_PMC_PERFCTL);
-	perfmon_cfg |= FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_STROBE, 1);
-	perfmon_cfg |= FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_WR_R_B, 0);
-
-	if (mlxbf_pmc_write(pmc->block[blk_num].mmio_base + perfcfg_offset,
-			    MLXBF_PMC_WRITE_REG_64, perfmon_cfg))
-		return -EFAULT;
-
-	/* Check if the counter is enabled */
-
-	if (mlxbf_pmc_read(pmc->block[blk_num].mmio_base + perfval_offset,
-			   MLXBF_PMC_READ_REG_64, &perfctl))
-		return -EFAULT;
-
-	if (!FIELD_GET(MLXBF_PMC_PERFCTL_EN0, perfctl))
-		return -EINVAL;
-
 	/* Set counter in "read" mode */
 	perfmon_cfg = FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_ADDR,
 				 MLXBF_PMC_PERFEVT);
Signature · 1 line
2.40.1
author maintainer
#507 lore raw

PATCH 506/511 net/tls: do not free tls_rec on async operation in bpf_exec_tx_verdict()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Liu Jian <[email protected]>

[ Upstream commit cfaa80c91f6f99b9342b6557f0f0e1143e434066 ]

I got the below warning when do fuzzing test:

BUG: KASAN: null-ptr-deref in scatterwalk_copychunks+0x320/0x470
Read of size 4 at addr 0000000000000008 by task kworker/u8:1/9

CPU: 0 PID: 9 Comm: kworker/u8:1 Tainted: G           OE
Hardware name: linux,dummy-virt (DT)
Workqueue: pencrypt_parallel padata_parallel_worker
Call trace:
 dump_backtrace+0x0/0x420
 show_stack+0x34/0x44
 dump_stack+0x1d0/0x248
 __kasan_report+0x138/0x140
 kasan_report+0x44/0x6c
 __asan_load4+0x94/0xd0
 scatterwalk_copychunks+0x320/0x470
 skcipher_next_slow+0x14c/0x290
 skcipher_walk_next+0x2fc/0x480
 skcipher_walk_first+0x9c/0x110
 skcipher_walk_aead_common+0x380/0x440
 skcipher_walk_aead_encrypt+0x54/0x70
 ccm_encrypt+0x13c/0x4d0
 crypto_aead_encrypt+0x7c/0xfc
 pcrypt_aead_enc+0x28/0x84
 padata_parallel_worker+0xd0/0x2dc
 process_one_work+0x49c/0xbdc
 worker_thread+0x124/0x880
 kthread+0x210/0x260
 ret_from_fork+0x10/0x18

This is because the value of rec_seq of tls_crypto_info configured by the user program is too large, for example, 0xffffffffffffff. In addition, TLS is asynchronously accelerated. When tls_do_encryption() returns -EINPROGRESS and sk->sk_err is set to EBADMSG due to rec_seq overflow, skmsg is released before the asynchronous encryption process ends. As a result, the UAF problem occurs during the asynchronous processing of the encryption module.

If the operation is asynchronous and the encryption module returns EINPROGRESS, do not free the record information.

Fixes 635d93981786 ("net/tls: free record only on encryption error")
---
 net/tls/tls_sw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
net/tls/tls_sw.c +2 -2
index bc897ff56e789..101d231c1b610 100644
@@ -809,7 +809,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 	psock = sk_psock_get(sk);
 	if (!psock || !policy) {
 		err = tls_push_record(sk, flags, record_type);
-		if (err && sk->sk_err == EBADMSG) {
+		if (err && err != -EINPROGRESS && sk->sk_err == EBADMSG) {
 			*copied -= sk_msg_free(sk, msg);
 			tls_free_open_rec(sk);
 			err = -sk->sk_err;
@@ -838,7 +838,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 	switch (psock->eval) {
 	case __SK_PASS:
 		err = tls_push_record(sk, flags, record_type);
-		if (err && sk->sk_err == EBADMSG) {
+		if (err && err != -EINPROGRESS && sk->sk_err == EBADMSG) {
 			*copied -= sk_msg_free(sk, msg);
 			tls_free_open_rec(sk);
 			err = -sk->sk_err;
Signature · 1 line
2.40.1
author maintainer
#508 lore raw

PATCH 507/511 ipv6: fix ip6_sock_set_addr_preferences() typo

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 8cdd9f1aaedf823006449faa4e540026c692ac43 ]

ip6_sock_set_addr_preferences() second argument should be an integer.

SUNRPC attempts to set IPV6_PREFER_SRC_PUBLIC were translated to IPV6_PREFER_SRC_TMP

Fixes 18d5ad623275 ("ipv6: add ip6_sock_set_addr_preferences")
Cc Christoph Hellwig <[email protected]>
Cc Chuck Lever <[email protected]>
---
 include/net/ipv6.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
include/net/ipv6.h +1 -1
index 20930086b2288..6b3309e55dcb1 100644
@@ -1258,7 +1258,7 @@ static inline int __ip6_sock_set_addr_preferences(struct sock *sk, int val)
 	return 0;
 }
 
-static inline int ip6_sock_set_addr_preferences(struct sock *sk, bool val)
+static inline int ip6_sock_set_addr_preferences(struct sock *sk, int val)
 {
 	int ret;
 
Signature · 1 line
2.40.1
author maintainer
#509 lore raw

PATCH 508/511 ixgbe: fix timestamp configuration code

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vadim Fedorenko <[email protected]>

[ Upstream commit 3c44191dd76cf9c0cc49adaf34384cbd42ef8ad2 ]

The commit in fixes introduced flags to control the status of hardware configuration while processing packets. At the same time another structure is used to provide configuration of timestamper to user-space applications. The way it was coded makes this structures go out of sync easily. The repro is easy for 82599 chips:

[root@hostname ~]# hwstamp_ctl -i eth0 -r 12 -t 1
current settings:
tx_type 0
rx_filter 0
new settings:
tx_type 1
rx_filter 12

The eth0 device is properly configured to timestamp any PTPv2 events.

[root@hostname ~]# hwstamp_ctl -i eth0 -r 1 -t 1 current settings:
tx_type 1
rx_filter 12
SIOCSHWTSTAMP failed: Numerical result out of range
The requested time stamping mode is not supported by the hardware.

The error is properly returned because HW doesn't support all packets timestamping. But the adapter->flags is cleared of timestamp flags even though no HW configuration was done. From that point no RX timestamps are received by user-space application. But configuration shows good values:

[root@hostname ~]# hwstamp_ctl -i eth0
current settings:
tx_type 1
rx_filter 12

Fix the issue by applying new flags only when the HW was actually configured.

---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 28 +++++++++++---------
 1 file changed, 15 insertions(+), 13 deletions(-)
drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +15 -13
index 29be1d6eca436..affd132534eab 100644
@@ -989,6 +989,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 	u32 tsync_tx_ctl = IXGBE_TSYNCTXCTL_ENABLED;
 	u32 tsync_rx_ctl = IXGBE_TSYNCRXCTL_ENABLED;
 	u32 tsync_rx_mtrl = PTP_EV_PORT << 16;
+	u32 aflags = adapter->flags;
 	bool is_l2 = false;
 	u32 regval;
 
@@ -1010,20 +1011,20 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 	case HWTSTAMP_FILTER_NONE:
 		tsync_rx_ctl = 0;
 		tsync_rx_mtrl = 0;
-		adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
-				    IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
+		aflags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
+			    IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 		tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1;
 		tsync_rx_mtrl |= IXGBE_RXMTRL_V1_SYNC_MSG;
-		adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
-				   IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
+		aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
+			   IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 		tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1;
 		tsync_rx_mtrl |= IXGBE_RXMTRL_V1_DELAY_REQ_MSG;
-		adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
-				   IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
+		aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
+			   IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
@@ -1037,8 +1038,8 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 		tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2;
 		is_l2 = true;
 		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
-		adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
-				   IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
+		aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
+			   IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_NTP_ALL:
@@ -1049,7 +1050,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 		if (hw->mac.type >= ixgbe_mac_X550) {
 			tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_ALL;
 			config->rx_filter = HWTSTAMP_FILTER_ALL;
-			adapter->flags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED;
+			aflags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED;
 			break;
 		}
 		fallthrough;
@@ -1060,8 +1061,6 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 		 * Delay_Req messages and hardware does not support
 		 * timestamping all packets => return error
 		 */
-		adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
-				    IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
 		config->rx_filter = HWTSTAMP_FILTER_NONE;
 		return -ERANGE;
 	}
@@ -1093,8 +1092,8 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 			       IXGBE_TSYNCRXCTL_TYPE_ALL |
 			       IXGBE_TSYNCRXCTL_TSIP_UT_EN;
 		config->rx_filter = HWTSTAMP_FILTER_ALL;
-		adapter->flags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED;
-		adapter->flags &= ~IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER;
+		aflags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED;
+		aflags &= ~IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER;
 		is_l2 = true;
 		break;
 	default:
@@ -1127,6 +1126,9 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 
 	IXGBE_WRITE_FLUSH(hw);
 
+	/* configure adapter flags only when HW is actually configured */
+	adapter->flags = aflags;
+
 	/* clear TX/RX time stamp registers, just to be sure */
 	ixgbe_ptp_clear_tx_timestamp(adapter);
 	IXGBE_READ_REG(hw, IXGBE_RXSTMPH);
Signature · 1 line
2.40.1
author maintainer
#510 lore raw

PATCH 509/511 kcm: Fix error handling for SOCK_DGRAM in kcm_sendmsg().

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit a22730b1b4bf437c6bbfdeff5feddf54be4aeada ]

syzkaller found a memory leak in kcm_sendmsg(), and commit c821a88bd720 ("kcm: Fix memory leak in error path of kcm_sendmsg()") suppressed it by updating kcm_tx_msg(head)->last_skb if partial data is copied so that the following sendmsg() will resume from the skb.

However, we cannot know how many bytes were copied when we get the error. Thus, we could mess up the MSG_MORE queue.

When kcm_sendmsg() fails for SOCK_DGRAM, we should purge the queue as we do so for UDP by udp_flush_pending_frames().

Even without this change, when the error occurred, the following sendmsg() resumed from a wrong skb and the queue was messed up. However, we have yet to get such a report, and only syzkaller stumbled on it. So, this can be changed safely.

Note this does not change SOCK_SEQPACKET behaviour.

Fixes c821a88bd720 ("kcm: Fix memory leak in error path of kcm_sendmsg()")
Fixes ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
---
 net/kcm/kcmsock.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)
net/kcm/kcmsock.c +8 -7
index 2d06617e89891..0d1ab4149553c 100644
@@ -1064,17 +1064,18 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 out_error:
 	kcm_push(kcm);
 
-	if (copied && sock->type == SOCK_SEQPACKET) {
+	if (sock->type == SOCK_SEQPACKET) {
 		/* Wrote some bytes before encountering an
 		 * error, return partial success.
 		 */
-		goto partial_message;
-	}
-
-	if (head != kcm->seq_skb)
+		if (copied)
+			goto partial_message;
+		if (head != kcm->seq_skb)
+			kfree_skb(head);
+	} else {
 		kfree_skb(head);
-	else if (copied)
-		kcm_tx_msg(head)->last_skb = skb;
+		kcm->seq_skb = NULL;
+	}
 
 	err = sk_stream_error(sk, msg->msg_flags, err);
 
Signature · 1 line
2.40.1
author maintainer
#511 lore raw

PATCH 510/511 MIPS: Only fiddle with CHECKFLAGS if `need-compiler

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maciej W. Rozycki <[email protected]>

commit 4fe4a6374c4db9ae2b849b61e84b58685dca565a upstream.

We have originally guarded fiddling with CHECKFLAGS in our arch Makefile by checking for the CONFIG_MIPS variable, not set for targets such as distclean', etc. that neither include .config' nor use the compiler.

Starting from commit 805b2e1d427a ("kbuild: include Makefile.compiler only when compiler is needed") we have had a generic `need-compiler' variable explicitly telling us if the compiler will be used and thus its capabilities need to be checked and expressed in the form of compilation flags. If this variable is not set, then make' functions such as cc-option' are undefined, causing all kinds of weirdness to happen if we expect specific results to be returned, most recently:

cc1: error: '-mloongson-mmi' must be used with '-mhard-float'

messages with configurations such as fuloong2e_defconfig' and the modules_install' target, which does include `.config' and yet does not use the compiler.

Replace the check for CONFIG_MIPS with one for `need-compiler' instead, so as to prevent the compiler from being ever called for CHECKFLAGS when not needed.

---
 arch/mips/Makefile |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/mips/Makefile +1 -1
@@ -321,7 +321,7 @@ KBUILD_CFLAGS += -fno-asynchronous-unwin
 
 KBUILD_LDFLAGS		+= -m $(ld-emul)
 
-ifdef CONFIG_MIPS
+ifdef need-compiler
 CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \
 	egrep -vw '__GNUC_(MINOR_|PATCHLEVEL_)?_' | \
 	sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g')
author maintainer
#512 lore raw

PATCH 511/511 drm/amd/display: Fix a bug when searching for insert_above_mpcc

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wesley Chalmers <[email protected]>

commit 3d028d5d60d516c536de1ddd3ebf3d55f3f8983b upstream.

[WHY]
Currently, when insert_plane is called with insert_above_mpcc parameter that is equal to tree->opp_list, the function returns NULL.

[HOW]
Instead, the function should insert the plane at the top of the tree.

---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c +3 -2
@@ -207,8 +207,9 @@ struct mpcc *mpc1_insert_plane(
 		/* check insert_above_mpcc exist in tree->opp_list */
 		struct mpcc *temp_mpcc = tree->opp_list;
 
-		while (temp_mpcc && temp_mpcc->mpcc_bot != insert_above_mpcc)
-			temp_mpcc = temp_mpcc->mpcc_bot;
+		if (temp_mpcc != insert_above_mpcc)
+			while (temp_mpcc && temp_mpcc->mpcc_bot != insert_above_mpcc)
+				temp_mpcc = temp_mpcc->mpcc_bot;
 		if (temp_mpcc == NULL)
 			return NULL;
 	}
maintainer Tested-by on the v1 series
#513 lore raw
In reply to Greg Kroah-Hartman

Hello,

Quoted 5 lines · On Sun, 17 Sep 2023 21:07:07 +0200 Greg Kroah-Hartman…

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Quoted 8 lines

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.132-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y
and the diffstat can be found below.

This rc kernel passes DAMON functionality test[1] on my test machine. Attaching the test results summary below. Please note that I retrieved the kernel from linux-stable-rc tree[2].

[1] https://github.com/awslabs/damon-tests/tree/next/corr
[2] a8d93816a2f2 ("Linux 5.15.132-rc1")

Thanks,
SJ

[...]

---

ok 13 selftests: damon-tests: build_i386_idle_flag.sh # selftests: damon-tests: build_i386_highpte.sh
# .config:1341:warning: override: reassigning to symbol DAMON ok 14 selftests: damon-tests: build_i386_highpte.sh
# selftests: damon-tests: build_nomemcg.sh
# .config:1342:warning: override: reassigning to symbol DAMON # .config:1352:warning: override: reassigning to symbol CGROUPS ok 15 selftests: damon-tests: build_nomemcg.sh

# kselftest dir '/home/sjpark/damon-tests-cont/linux/tools/testing/selftests/damon-tests' is in dirty state.
# the log is at '/home/sjpark/log'.
 [32m
ok 1 selftests: damon: debugfs_attrs.sh
ok 1 selftests: damon-tests: kunit.sh
ok 2 selftests: damon-tests: huge_count_read_write.sh
ok 3 selftests: damon-tests: buffer_overflow.sh
ok 4 selftests: damon-tests: rm_contexts.sh
ok 5 selftests: damon-tests: record_null_deref.sh
ok 6 selftests: damon-tests: dbgfs_target_ids_read_before_terminate_race.sh
ok 7 selftests: damon-tests: dbgfs_target_ids_pid_leak.sh
ok 8 selftests: damon-tests: damo_tests.sh
ok 9 selftests: damon-tests: masim-record.sh
ok 10 selftests: damon-tests: build_i386.sh
ok 11 selftests: damon-tests: build_m68k.sh
ok 12 selftests: damon-tests: build_arm64.sh
ok 13 selftests: damon-tests: build_i386_idle_flag.sh
ok 14 selftests: damon-tests: build_i386_highpte.sh
ok 15 selftests: damon-tests: build_nomemcg.sh
 [33m
 [92mPASS [39m
_remote_run_corr.sh SUCCESS
Tested-by on the v1 series
#514 lore raw
In reply to Greg Kroah-Hartman
Quoted 9 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 8 lines
	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.132-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y
and the diffstat can be found below.

thanks,

greg k-h

Built and booted successfully on RISC-V RV64 (HiFive Unmatched).

maintainer Tested-by on the v1 series
#515 lore raw
In reply to Greg Kroah-Hartman
Quoted 9 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 8 lines
	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.132-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y
and the diffstat can be found below.

thanks,

greg k-h

All tests passing for Tegra ...

Test results for stable-v5.15:

    11 builds:	11 pass, 0 fail
    28 boots:	28 pass, 0 fail
    102 tests:	102 pass, 0 fail

Linux version: 5.15.132-rc1-gead88697522a
Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000,

                tegra194-p2972-0000, tegra194-p3509-0000+p3668-0000,
                tegra20-ventana, tegra210-p2371-2180,
                tegra210-p3450-0000, tegra30-cardhu-a04

Jon

#516 lore raw
In reply to Greg Kroah-Hartman
Quoted 8 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

ChromeOS build tests complain:

fs/ksmbd/smb2pdu.c:6256:6: error: variable 'fp' is used uninitialized whenever 'if' condition is true [-Werror,-Wsometimes-uninitialized]

        if (work->next_smb2_rcv_hdr_off) {
            ^~~~~~~~~~~~~~~~~~~~~~~~~~~
fs/ksmbd/smb2pdu.c:6367:21: note: uninitialized use occurs here
        ksmbd_fd_put(work, fp);

That is caused by

Quoted 3 lines

Namjae Jeon <[email protected]>
ksmbd: no response from compound read

The compiler suggests to initialize fp with NULL. That _might_ be a feasible solution.

Guenter

Tested-by on the v1 series
#517 lore raw
In reply to Greg Kroah-Hartman
Quoted 9 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 8 lines
	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.132-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y
and the diffstat can be found below.

thanks,

greg k-h

On ARCH_BRCMSTB using 32-bit and 64-bit ARM kernels, build tested on BMIPS_GENERIC:

Signature · 1 line
Florian
#518 lore raw
In reply to Greg Kroah-Hartman
Quoted 8 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

My tests say

Build results:

	total: 155 pass: 155 fail: 0
Qemu test results:
	total: 509 pass: 509 fail: 0

However, trying to build with clang (as done by ChromeOS) does report

fs/ksmbd/smb2pdu.c:6256:6: error: variable 'fp' is used uninitialized whenever 'if' condition is true [-Werror,-Wsometimes-uninitialized]

        if (work->next_smb2_rcv_hdr_off) {
            ^~~~~~~~~~~~~~~~~~~~~~~~~~~
fs/ksmbd/smb2pdu.c:6367:21: note: uninitialized use occurs here
        ksmbd_fd_put(work, fp);
                           ^~
fs/ksmbd/smb2pdu.c:6256:2: note: remove the 'if' if its condition is always false
        if (work->next_smb2_rcv_hdr_off) {
        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
fs/ksmbd/smb2pdu.c:6248:23: note: initialize the variable 'fp' to silence this warning
        struct ksmbd_file *fp;
                             ^
                              = NULL

I guess I should try to add clang build tests.

Anyway, smb2_write() already initializes fp with NULL, presumably to handle a similar problem, so maybe doing the same for the read function would be the easiest solution. Note that the initialization was added upstream with commit 2fd5dcb1c8ef9 ("ksmbd: smbd: fix missing client's memory region invalidation").

Guenter

author maintainer
#519 lore raw
Quoted 33 lines · Guenter Roeck
Quoted 8 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

My tests say

Build results:

	total: 155 pass: 155 fail: 0
Qemu test results:
	total: 509 pass: 509 fail: 0

However, trying to build with clang (as done by ChromeOS) does report

fs/ksmbd/smb2pdu.c:6256:6: error: variable 'fp' is used uninitialized whenever 'if' condition is true [-Werror,-Wsometimes-uninitialized]

        if (work->next_smb2_rcv_hdr_off) {
            ^~~~~~~~~~~~~~~~~~~~~~~~~~~
fs/ksmbd/smb2pdu.c:6367:21: note: uninitialized use occurs here
        ksmbd_fd_put(work, fp);
                           ^~
fs/ksmbd/smb2pdu.c:6256:2: note: remove the 'if' if its condition is always false
        if (work->next_smb2_rcv_hdr_off) {
        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
fs/ksmbd/smb2pdu.c:6248:23: note: initialize the variable 'fp' to silence this warning
        struct ksmbd_file *fp;
                             ^
                              = NULL
Quoted 6 lines

I guess I should try to add clang build tests.

Anyway, smb2_write() already initializes fp with NULL, presumably to handle a similar problem, so maybe doing the same for the read function would be the easiest solution. Note that the initialization was added upstream with commit 2fd5dcb1c8ef9 ("ksmbd: smbd: fix missing client's memory region invalidation").

Thanks for the report, I'll go fix this up in the commit that causes the build warning.

greg k-h

Tested-by on the v1 series
#520 lore raw
In reply to Greg Kroah-Hartman

Hi Greg,

Quoted 5 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

No problems seen on x86_64 and aarch64 with our testing.

Thanks,
Harshit

Quoted 12 lines

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.132-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y
and the diffstat can be found below.

thanks,

greg k-h

Tested-by Linux Kernel Functional Testing on the v1 series
#521 lore raw
In reply to Greg Kroah-Hartman
Quoted 10 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 8 lines
        https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.132-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y
and the diffstat can be found below.

thanks,

greg k-h

Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.

## Build
* kernel: 5.15.132-rc1
* git: https://gitlab.com/Linaro/lkft/mirrors/stable/linux-stable-rc
* git branch: linux-5.15.y
* git commit: ead88697522a847255e61a898bf924d37d65ee3d
* git describe: v5.15.131-512-gead88697522a
* test details:
https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.15.y/build/v5.15.131-512-gead88697522a

## Test Regressions (compared to v5.15.131)

## Metric Regressions (compared to v5.15.131)

## Test Fixes (compared to v5.15.131)

## Metric Fixes (compared to v5.15.131)

## Test result summary
total: 88627, pass: 70361, fail: 2511, skip: 15669, xfail: 86

## Build Summary
* arc: 5 total, 5 passed, 0 failed
* arm: 114 total, 114 passed, 0 failed
* arm64: 41 total, 41 passed, 0 failed
* i386: 32 total, 32 passed, 0 failed
* mips: 24 total, 24 passed, 0 failed
* parisc: 3 total, 3 passed, 0 failed
* powerpc: 24 total, 24 passed, 0 failed
* riscv: 7 total, 7 passed, 0 failed
* s390: 9 total, 9 passed, 0 failed
* sh: 12 total, 12 passed, 0 failed
* sparc: 6 total, 6 passed, 0 failed
* x86_64: 35 total, 35 passed, 0 failed

## Test suites summary
* boot
* kselftest-android
* kselftest-arm64
* kselftest-breakpoints
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-drivers-dma-buf
* kselftest-efivarfs
* kselftest-exec
* kselftest-filesystems
* kselftest-filesystems-binderfs
* kselftest-filesystems-epoll
* kselftest-firmware
* kselftest-fpu
* kselftest-ftrace
* kselftest-futex
* kselftest-gpio
* kselftest-intel_pstate
* kselftest-ipc
* kselftest-ir
* kselftest-kcmp
* kselftest-kexec
* kselftest-lib
* kselftest-membarrier
* kselftest-memfd
* kselftest-memory-hotplug
* kselftest-mincore
* kselftest-mount
* kselftest-mqueue
* kselftest-net
* kselftest-net-forwarding
* kselftest-net-mptcp
* kselftest-netfilter
* kselftest-nsfs
* kselftest-openat2
* kselftest-pid_namespace
* kselftest-pidfd
* kselftest-proc
* kselftest-pstore
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-sigaltstack
* kselftest-size
* kselftest-splice
* kselftest-static_keys
* kselftest-sync
* kselftest-sysctl
* kselftest-tc-testing
* kselftest-timens
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user
* kselftest-user_events
* kselftest-vDSO
* kselftest-vm
* kselftest-watchdog
* kselftest-x86
* kselftest-zram
* kunit
* kvm-unit-tests
* libgpiod
* log-parser-boot
* log-parser-test
* ltp-cap_bounds
* ltp-commands
* ltp-containers
* ltp-controllers
* ltp-cpuhotplug
* ltp-crypto
* ltp-cve
* ltp-dio
* ltp-fcntl-locktests
* ltp-filecaps
* ltp-fs
* ltp-fs_bind
* ltp-fs_perms_simple
* ltp-fsx
* ltp-hugetlb
* ltp-io
* ltp-ipc
* ltp-math
* ltp-mm
* ltp-nptl
* ltp-pty
* ltp-sched
* ltp-securebits
* ltp-smoke
* ltp-syscalls
* ltp-tracing
* network-basic-tests
* perf
* rcutorture
* v4l2-compliance

--
Linaro LKFT
https://lkft.linaro.org

maintainer Tested-by on the v1 series
#522 lore raw
In reply to Greg Kroah-Hartman
Quoted 9 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 9 lines
	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.132-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y
and the diffstat can be found below.

thanks,

greg k-h

Compiled and booted on my test system. No dmesg regressions.

thanks,
-- Shuah

Tested-by on the v1 series
#523 lore raw
In reply to Greg Kroah-Hartman
Quoted 9 lines

This is the start of the stable review cycle for the 5.15.132 release. There are 511 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Tue, 19 Sep 2023 19:10:04 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

Quoted 9 lines
        https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.132-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y
and the diffstat can be found below.

thanks,

greg k-h

Compiled and booted on my x86_64 and ARM64 test systems. No errors or regressions.

Thanks.