Skip to contentSkip to conversation

6.16.1-rc1 review

PATCH In review Greg Kroah-Hartman 24 participants 676 messages Aug 12, 2025 – Aug 17, 2025 Page 2 of 5

Subsystems (7)
lore
Share & tools
lore
author maintainer
#132 lore raw

PATCH 126/627 riscv: dts: sophgo: sg2044: Add missing riscv,cbop-block-size property

In reply to Greg Kroah-Hartman

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

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

From: Inochi Amaoto <[email protected]>

[ Upstream commit 02d548e553d161813b7d3702a311b9067806057d ]

The kernel complains no "riscv,cbop-block-size" and disables the Zicbop extension. Add the missing property to keep it functional.

Fixes ae5bac370ed4 ("riscv: dts: sophgo: Add initial device tree of Sophgo SRD3-10")
---
 arch/riscv/boot/dts/sophgo/sg2044-cpus.dtsi | 64 +++++++++++++++++++++
 1 file changed, 64 insertions(+)
arch/riscv/boot/dts/sophgo/sg2044-cpus.dtsi +64 -0
index 2a4267078ce6..6a35ed8f253c 100644
@@ -38,6 +38,7 @@ cpu0: cpu@0 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu0_intc: interrupt-controller {
@@ -73,6 +74,7 @@ cpu1: cpu@1 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu1_intc: interrupt-controller {
@@ -108,6 +110,7 @@ cpu2: cpu@2 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu2_intc: interrupt-controller {
@@ -143,6 +146,7 @@ cpu3: cpu@3 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu3_intc: interrupt-controller {
@@ -178,6 +182,7 @@ cpu4: cpu@4 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu4_intc: interrupt-controller {
@@ -213,6 +218,7 @@ cpu5: cpu@5 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu5_intc: interrupt-controller {
@@ -248,6 +254,7 @@ cpu6: cpu@6 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu6_intc: interrupt-controller {
@@ -283,6 +290,7 @@ cpu7: cpu@7 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu7_intc: interrupt-controller {
@@ -318,6 +326,7 @@ cpu8: cpu@8 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu8_intc: interrupt-controller {
@@ -353,6 +362,7 @@ cpu9: cpu@9 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu9_intc: interrupt-controller {
@@ -388,6 +398,7 @@ cpu10: cpu@10 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu10_intc: interrupt-controller {
@@ -423,6 +434,7 @@ cpu11: cpu@11 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu11_intc: interrupt-controller {
@@ -458,6 +470,7 @@ cpu12: cpu@12 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu12_intc: interrupt-controller {
@@ -493,6 +506,7 @@ cpu13: cpu@13 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu13_intc: interrupt-controller {
@@ -528,6 +542,7 @@ cpu14: cpu@14 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu14_intc: interrupt-controller {
@@ -563,6 +578,7 @@ cpu15: cpu@15 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu15_intc: interrupt-controller {
@@ -598,6 +614,7 @@ cpu16: cpu@16 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu16_intc: interrupt-controller {
@@ -633,6 +650,7 @@ cpu17: cpu@17 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu17_intc: interrupt-controller {
@@ -668,6 +686,7 @@ cpu18: cpu@18 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu18_intc: interrupt-controller {
@@ -703,6 +722,7 @@ cpu19: cpu@19 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu19_intc: interrupt-controller {
@@ -738,6 +758,7 @@ cpu20: cpu@20 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu20_intc: interrupt-controller {
@@ -773,6 +794,7 @@ cpu21: cpu@21 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu21_intc: interrupt-controller {
@@ -808,6 +830,7 @@ cpu22: cpu@22 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu22_intc: interrupt-controller {
@@ -843,6 +866,7 @@ cpu23: cpu@23 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu23_intc: interrupt-controller {
@@ -878,6 +902,7 @@ cpu24: cpu@24 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu24_intc: interrupt-controller {
@@ -913,6 +938,7 @@ cpu25: cpu@25 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu25_intc: interrupt-controller {
@@ -948,6 +974,7 @@ cpu26: cpu@26 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu26_intc: interrupt-controller {
@@ -983,6 +1010,7 @@ cpu27: cpu@27 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu27_intc: interrupt-controller {
@@ -1018,6 +1046,7 @@ cpu28: cpu@28 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu28_intc: interrupt-controller {
@@ -1053,6 +1082,7 @@ cpu29: cpu@29 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu29_intc: interrupt-controller {
@@ -1088,6 +1118,7 @@ cpu30: cpu@30 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu30_intc: interrupt-controller {
@@ -1123,6 +1154,7 @@ cpu31: cpu@31 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu31_intc: interrupt-controller {
@@ -1158,6 +1190,7 @@ cpu32: cpu@32 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu32_intc: interrupt-controller {
@@ -1193,6 +1226,7 @@ cpu33: cpu@33 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu33_intc: interrupt-controller {
@@ -1228,6 +1262,7 @@ cpu34: cpu@34 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu34_intc: interrupt-controller {
@@ -1263,6 +1298,7 @@ cpu35: cpu@35 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu35_intc: interrupt-controller {
@@ -1298,6 +1334,7 @@ cpu36: cpu@36 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu36_intc: interrupt-controller {
@@ -1333,6 +1370,7 @@ cpu37: cpu@37 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu37_intc: interrupt-controller {
@@ -1368,6 +1406,7 @@ cpu38: cpu@38 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu38_intc: interrupt-controller {
@@ -1403,6 +1442,7 @@ cpu39: cpu@39 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu39_intc: interrupt-controller {
@@ -1438,6 +1478,7 @@ cpu40: cpu@40 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu40_intc: interrupt-controller {
@@ -1473,6 +1514,7 @@ cpu41: cpu@41 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu41_intc: interrupt-controller {
@@ -1508,6 +1550,7 @@ cpu42: cpu@42 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu42_intc: interrupt-controller {
@@ -1543,6 +1586,7 @@ cpu43: cpu@43 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu43_intc: interrupt-controller {
@@ -1578,6 +1622,7 @@ cpu44: cpu@44 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu44_intc: interrupt-controller {
@@ -1613,6 +1658,7 @@ cpu45: cpu@45 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu45_intc: interrupt-controller {
@@ -1648,6 +1694,7 @@ cpu46: cpu@46 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu46_intc: interrupt-controller {
@@ -1683,6 +1730,7 @@ cpu47: cpu@47 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu47_intc: interrupt-controller {
@@ -1718,6 +1766,7 @@ cpu48: cpu@48 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu48_intc: interrupt-controller {
@@ -1753,6 +1802,7 @@ cpu49: cpu@49 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu49_intc: interrupt-controller {
@@ -1788,6 +1838,7 @@ cpu50: cpu@50 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu50_intc: interrupt-controller {
@@ -1823,6 +1874,7 @@ cpu51: cpu@51 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu51_intc: interrupt-controller {
@@ -1858,6 +1910,7 @@ cpu52: cpu@52 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu52_intc: interrupt-controller {
@@ -1893,6 +1946,7 @@ cpu53: cpu@53 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu53_intc: interrupt-controller {
@@ -1928,6 +1982,7 @@ cpu54: cpu@54 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu54_intc: interrupt-controller {
@@ -1963,6 +2018,7 @@ cpu55: cpu@55 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu55_intc: interrupt-controller {
@@ -1998,6 +2054,7 @@ cpu56: cpu@56 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu56_intc: interrupt-controller {
@@ -2033,6 +2090,7 @@ cpu57: cpu@57 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu57_intc: interrupt-controller {
@@ -2068,6 +2126,7 @@ cpu58: cpu@58 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu58_intc: interrupt-controller {
@@ -2103,6 +2162,7 @@ cpu59: cpu@59 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu59_intc: interrupt-controller {
@@ -2138,6 +2198,7 @@ cpu60: cpu@60 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu60_intc: interrupt-controller {
@@ -2173,6 +2234,7 @@ cpu61: cpu@61 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu61_intc: interrupt-controller {
@@ -2208,6 +2270,7 @@ cpu62: cpu@62 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu62_intc: interrupt-controller {
@@ -2243,6 +2306,7 @@ cpu63: cpu@63 {
 					       "zvfbfmin", "zvfbfwma", "zvfh",
 					       "zvfhmin";
 			riscv,cbom-block-size = <64>;
+			riscv,cbop-block-size = <64>;
 			riscv,cboz-block-size = <64>;
 
 			cpu63_intc: interrupt-controller {
Signature · 1 line
2.39.5
author maintainer
#133 lore raw

PATCH 127/627 staging: nvec: Fix incorrect null termination of battery manufacturer

In reply to Greg Kroah-Hartman

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

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

From: Alok Tiwari <[email protected]>

[ Upstream commit a8934352ba01081c51d2df428e9d540aae0e88b5 ]

The battery manufacturer string was incorrectly null terminated using bat_model instead of bat_manu. This could result in an unintended write to the wrong field and potentially incorrect behavior.

fixe the issue by correctly null terminating the bat_manu string.

---
 drivers/staging/nvec/nvec_power.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/staging/nvec/nvec_power.c +1 -1
index e0e67a3eb722..2faab9fdedef 100644
@@ -194,7 +194,7 @@ static int nvec_power_bat_notifier(struct notifier_block *nb,
 		break;
 	case MANUFACTURER:
 		memcpy(power->bat_manu, &res->plc, res->length - 2);
-		power->bat_model[res->length - 2] = '\0';
+		power->bat_manu[res->length - 2] = '\0';
 		break;
 	case MODEL:
 		memcpy(power->bat_model, &res->plc, res->length - 2);
Signature · 1 line
2.39.5
author maintainer
#134 lore raw

PATCH 128/627 selftests/tracing: Fix false failure of subsystem event test

In reply to Greg Kroah-Hartman

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

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

From: Steven Rostedt <[email protected]>

[ Upstream commit 213879061a9c60200ba971330dbefec6df3b4a30 ]

The subsystem event test enables all "sched" events and makes sure there's at least 3 different events in the output. It used to cat the entire trace file to | wc -l, but on slow machines, that could last a very long time. To solve that, it was changed to just read the first 100 lines of the trace file. This can cause false failures as some events repeat so often, that the 100 lines that are examined could possibly be of only one event.

Instead, create an awk script that looks for 3 different events and will exit out after it finds them. This will find the 3 events the test looks for (eventually if it works), and still exit out after the test is satisfied and not cause slower machines to run forever.

---
 .../ftrace/test.d/event/subsystem-enable.tc   | 28 +++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)
tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc +26 -2
index b7c8f29c09a9..65916bb55dfb 100644
@@ -14,11 +14,35 @@ fail() { #msg
     exit_fail
 }
 
+# As reading trace can last forever, simply look for 3 different
+# events then exit out of reading the file. If there's not 3 different
+# events, then the test has failed.
+check_unique() {
+    cat trace | grep -v '^#' | awk '
+	BEGIN { cnt = 0; }
+	{
+	    for (i = 0; i < cnt; i++) {
+		if (event[i] == $5) {
+		    break;
+		}
+	    }
+	    if (i == cnt) {
+		event[cnt++] = $5;
+		if (cnt > 2) {
+		    exit;
+		}
+	    }
+	}
+	END {
+	    printf "%d", cnt;
+	}'
+}
+
 echo 'sched:*' > set_event
 
 yield
 
-count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+count=`check_unique`
 if [ $count -lt 3 ]; then
     fail "at least fork, exec and exit events should be recorded"
 fi
@@ -29,7 +53,7 @@ echo 1 > events/sched/enable
 
 yield
 
-count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+count=`check_unique`
 if [ $count -lt 3 ]; then
     fail "at least fork, exec and exit events should be recorded"
 fi
Signature · 1 line
2.39.5
author maintainer
#135 lore raw

PATCH 129/627 MIPS: alchemy: gpio: use new GPIO line value setter callbacks for the remaining chips

In reply to Greg Kroah-Hartman

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

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

From: Bartosz Golaszewski <[email protected]>

[ Upstream commit 6b94bf976f9f9e6d4a6bf3218968a506c049702e ]

Previous commit missed two other places that need converting, it only came out in tests on autobuilders now. Convert the rest of the driver.

Fixes 68bdc4dc1130 ("MIPS: alchemy: gpio: use new line value setter callbacks")
---
 arch/mips/alchemy/common/gpiolib.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)
arch/mips/alchemy/common/gpiolib.c +8 -4
index 411f70ceb762..194034eba75f 100644
@@ -40,9 +40,11 @@ static int gpio2_get(struct gpio_chip *chip, unsigned offset)
 	return !!alchemy_gpio2_get_value(offset + ALCHEMY_GPIO2_BASE);
 }
 
-static void gpio2_set(struct gpio_chip *chip, unsigned offset, int value)
+static int gpio2_set(struct gpio_chip *chip, unsigned offset, int value)
 {
 	alchemy_gpio2_set_value(offset + ALCHEMY_GPIO2_BASE, value);
+
+	return 0;
 }
 
 static int gpio2_direction_input(struct gpio_chip *chip, unsigned offset)
@@ -68,10 +70,12 @@ static int gpio1_get(struct gpio_chip *chip, unsigned offset)
 	return !!alchemy_gpio1_get_value(offset + ALCHEMY_GPIO1_BASE);
 }
 
-static void gpio1_set(struct gpio_chip *chip,
+static int gpio1_set(struct gpio_chip *chip,
 				unsigned offset, int value)
 {
 	alchemy_gpio1_set_value(offset + ALCHEMY_GPIO1_BASE, value);
+
+	return 0;
 }
 
 static int gpio1_direction_input(struct gpio_chip *chip, unsigned offset)
@@ -97,7 +101,7 @@ struct gpio_chip alchemy_gpio_chip[] = {
 		.direction_input	= gpio1_direction_input,
 		.direction_output	= gpio1_direction_output,
 		.get			= gpio1_get,
-		.set			= gpio1_set,
+		.set_rv			= gpio1_set,
 		.to_irq			= gpio1_to_irq,
 		.base			= ALCHEMY_GPIO1_BASE,
 		.ngpio			= ALCHEMY_GPIO1_NUM,
@@ -107,7 +111,7 @@ struct gpio_chip alchemy_gpio_chip[] = {
 		.direction_input	= gpio2_direction_input,
 		.direction_output	= gpio2_direction_output,
 		.get			= gpio2_get,
-		.set			= gpio2_set,
+		.set_rv			= gpio2_set,
 		.to_irq			= gpio2_to_irq,
 		.base			= ALCHEMY_GPIO2_BASE,
 		.ngpio			= ALCHEMY_GPIO2_NUM,
Signature · 1 line
2.39.5
author maintainer
#136 lore raw

PATCH 130/627 Revert "udmabuf: fix vmap_udmabuf error page set"

In reply to Greg Kroah-Hartman

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

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

From: Huan Yang <[email protected]>

[ Upstream commit ceb7b62eaaaacfcf87473bd2e99ac73a758620cb ]

This reverts commit 18d7de823b7150344d242c3677e65d68c5271b04.

We cannot use vmap_pfn() in vmap_udmabuf() as it would fail the pfn_valid() check in vmap_pfn_apply(). This is because vmap_pfn() is intended to be used for mapping non-struct-page memory such as PCIe BARs. Since, udmabuf mostly works with pages/folios backed by shmem/hugetlbfs/THP, vmap_pfn() is not the right tool or API to invoke for implementing vmap.

Stable-dep-of: a26fd92b7223 ("udmabuf: fix vmap missed offset page")

---
 drivers/dma-buf/Kconfig   |  1 -
 drivers/dma-buf/udmabuf.c | 22 +++++++---------------
 2 files changed, 7 insertions(+), 16 deletions(-)
drivers/dma-buf/Kconfig +0 -1
index fee04fdb0822..b46eb8a552d7 100644
@@ -36,7 +36,6 @@ config UDMABUF
 	depends on DMA_SHARED_BUFFER
 	depends on MEMFD_CREATE || COMPILE_TEST
 	depends on MMU
-	select VMAP_PFN
 	help
 	  A driver to let userspace turn memfd regions into dma-bufs.
 	  Qemu can use this to create host dmabufs for guest framebuffers.
drivers/dma-buf/udmabuf.c +7 -15
index c9d0c68d2fcb..4cc342fb28f4 100644
@@ -109,29 +109,21 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma)
 static int vmap_udmabuf(struct dma_buf *buf, struct iosys_map *map)
 {
 	struct udmabuf *ubuf = buf->priv;
-	unsigned long *pfns;
+	struct page **pages;
 	void *vaddr;
 	pgoff_t pg;
 
 	dma_resv_assert_held(buf->resv);
 
-	/**
-	 * HVO may free tail pages, so just use pfn to map each folio
-	 * into vmalloc area.
-	 */
-	pfns = kvmalloc_array(ubuf->pagecount, sizeof(*pfns), GFP_KERNEL);
-	if (!pfns)
+	pages = kvmalloc_array(ubuf->pagecount, sizeof(*pages), GFP_KERNEL);
+	if (!pages)
 		return -ENOMEM;
 
-	for (pg = 0; pg < ubuf->pagecount; pg++) {
-		unsigned long pfn = folio_pfn(ubuf->folios[pg]);
-
-		pfn += ubuf->offsets[pg] >> PAGE_SHIFT;
-		pfns[pg] = pfn;
-	}
+	for (pg = 0; pg < ubuf->pagecount; pg++)
+		pages[pg] = &ubuf->folios[pg]->page;
 
-	vaddr = vmap_pfn(pfns, ubuf->pagecount, PAGE_KERNEL);
-	kvfree(pfns);
+	vaddr = vm_map_ram(pages, ubuf->pagecount, -1);
+	kvfree(pages);
 	if (!vaddr)
 		return -EINVAL;
 
Signature · 1 line
2.39.5
author maintainer
#137 lore raw

PATCH 131/627 udmabuf: fix vmap missed offset page

In reply to Greg Kroah-Hartman

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

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

From: Huan Yang <[email protected]>

[ Upstream commit a26fd92b7223160ad31c3e2971b63178faed9cf5 ]

Before invoke vmap, we need offer a pages pointer array which each page need to map in vmalloc area.

But currently vmap_udmabuf only set each folio's head page into pages, missed each offset pages when iter.

This patch set the correctly offset page in each folio into array.

Fixes 5e72b2b41a21 ("udmabuf: convert udmabuf driver to use folios")
---
 drivers/dma-buf/udmabuf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/dma-buf/udmabuf.c +2 -1
index 4cc342fb28f4..40399c26e6be 100644
@@ -120,7 +120,8 @@ static int vmap_udmabuf(struct dma_buf *buf, struct iosys_map *map)
 		return -ENOMEM;
 
 	for (pg = 0; pg < ubuf->pagecount; pg++)
-		pages[pg] = &ubuf->folios[pg]->page;
+		pages[pg] = folio_page(ubuf->folios[pg],
+				       ubuf->offsets[pg] >> PAGE_SHIFT);
 
 	vaddr = vm_map_ram(pages, ubuf->pagecount, -1);
 	kvfree(pages);
Signature · 1 line
2.39.5
author maintainer
#138 lore raw

PATCH 132/627 drm/rockchip: cleanup fb when drm_gem_fb_afbc_init failed

In reply to Greg Kroah-Hartman

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

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

From: Andy Yan <[email protected]>

[ Upstream commit 099593a28138b48feea5be8ce700e5bc4565e31d ]

In the function drm_gem_fb_init_with_funcs, the framebuffer (fb) and its corresponding object ID have already been registered.

So we need to cleanup the drm framebuffer if the subsequent execution of drm_gem_fb_afbc_init fails.

Directly call drm_framebuffer_put to ensure that all fb related resources are cleanup.

Fixes 7707f7227f09 ("drm/rockchip: Add support for afbc")
---
 drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)
drivers/gpu/drm/rockchip/rockchip_drm_fb.c +1 -8
index dcc1f07632c3..5829ee061c61 100644
@@ -52,16 +52,9 @@ rockchip_fb_create(struct drm_device *dev, struct drm_file *file,
 	}
 
 	if (drm_is_afbc(mode_cmd->modifier[0])) {
-		int ret, i;
-
 		ret = drm_gem_fb_afbc_init(dev, mode_cmd, afbc_fb);
 		if (ret) {
-			struct drm_gem_object **obj = afbc_fb->base.obj;
-
-			for (i = 0; i < info->num_planes; ++i)
-				drm_gem_object_put(obj[i]);
-
-			kfree(afbc_fb);
+			drm_framebuffer_put(&afbc_fb->base);
 			return ERR_PTR(ret);
 		}
 	}
Signature · 1 line
2.39.5
author maintainer
#139 lore raw

PATCH 133/627 drm/sitronix: Remove broken backwards-compatibility layer

In reply to Greg Kroah-Hartman

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

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

From: Geert Uytterhoeven <[email protected]>

[ Upstream commit a3f7d26dfce9e2d547a58f4941881843a391a6cc ]

When moving the Sitronix DRM drivers and renaming their Kconfig symbols, the old symbols were kept, aiming to provide a seamless migration path when running "make olddefconfig" or "make oldconfig".

However, the old compatibility symbols are not visible. Hence unless they are selected by another symbol (which they are not), they can never be enabled, and no backwards compatibility is provided.

Drop the broken mechanism and the old symbols.

---
 drivers/gpu/drm/sitronix/Kconfig | 10 ----------
 1 file changed, 10 deletions(-)
drivers/gpu/drm/sitronix/Kconfig +0 -10
index 741d1bb4b83f..6de7d92d9b74 100644
@@ -11,10 +11,6 @@ config DRM_ST7571_I2C
 
 	  if M is selected the module will be called st7571-i2c.
 
-config TINYDRM_ST7586
-	tristate
-	default n
-
 config DRM_ST7586
 	tristate "DRM support for Sitronix ST7586 display panels"
 	depends on DRM && SPI
@@ -22,17 +18,12 @@ config DRM_ST7586
 	select DRM_KMS_HELPER
 	select DRM_GEM_DMA_HELPER
 	select DRM_MIPI_DBI
-	default TINYDRM_ST7586
 	help
 	  DRM driver for the following Sitronix ST7586 panels:
 	  * LEGO MINDSTORMS EV3
 
 	  If M is selected the module will be called st7586.
 
-config TINYDRM_ST7735R
-	tristate
-	default n
-
 config DRM_ST7735R
 	tristate "DRM support for Sitronix ST7715R/ST7735R display panels"
 	depends on DRM && SPI
@@ -41,7 +32,6 @@ config DRM_ST7735R
 	select DRM_GEM_DMA_HELPER
 	select DRM_MIPI_DBI
 	select BACKLIGHT_CLASS_DEVICE
-	default TINYDRM_ST7735R
 	help
 	  DRM driver for Sitronix ST7715R/ST7735R with one of the following
 	  LCDs:
Signature · 1 line
2.39.5
author maintainer
#140 lore raw

PATCH 134/627 drm/connector: hdmi: Evaluate limited range after computing format

In reply to Greg Kroah-Hartman

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

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

From: Cristian Ciocaltea <[email protected]>

[ Upstream commit 21f627139652dd8329a88e281df6600f3866d238 ]

Evaluating the requirement to use a limited RGB quantization range involves a verification of the output format, among others, but this is currently performed before actually computing the format, hence relying on the old connector state.

Move the call to hdmi_is_limited_range() after hdmi_compute_config() to ensure the verification is done on the updated output format.

Fixes 027d43590649 ("drm/connector: hdmi: Add RGB Quantization Range to the connector state")
---
 drivers/gpu/drm/display/drm_hdmi_state_helper.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/display/drm_hdmi_state_helper.c +2 -2
index d9d9948b29e9..45b154c8abb2 100644
@@ -798,12 +798,12 @@ int drm_atomic_helper_connector_hdmi_check(struct drm_connector *connector,
 	if (!new_conn_state->crtc || !new_conn_state->best_encoder)
 		return 0;
 
-	new_conn_state->hdmi.is_limited_range = hdmi_is_limited_range(connector, new_conn_state);
-
 	ret = hdmi_compute_config(connector, new_conn_state, mode);
 	if (ret)
 		return ret;
 
+	new_conn_state->hdmi.is_limited_range = hdmi_is_limited_range(connector, new_conn_state);
+
 	ret = hdmi_generate_infoframes(connector, new_conn_state);
 	if (ret)
 		return ret;
Signature · 1 line
2.39.5
author maintainer
#141 lore raw

PATCH 135/627 drm/panfrost: Fix panfrost device variable name in devfreq

In reply to Greg Kroah-Hartman

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

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

From: Adrián Larumbe <[email protected]>

[ Upstream commit 6048f5587614bb4919c54966913452c1a0a43138 ]

Commit 64111a0e22a9 ("drm/panfrost: Fix incorrect updating of current device frequency") was a Panfrost port of a similar fix in Panthor.

Fix the Panfrost device pointer variable name so that it follows Panfrost naming conventions.

Fixes 64111a0e22a9 ("drm/panfrost: Fix incorrect updating of current device frequency")
---
 drivers/gpu/drm/panfrost/panfrost_devfreq.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/panfrost/panfrost_devfreq.c +2 -2
index 3385fd3ef41a..5d0dce10336b 100644
@@ -29,7 +29,7 @@ static void panfrost_devfreq_update_utilization(struct panfrost_devfreq *pfdevfr
 static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 				   u32 flags)
 {
-	struct panfrost_device *ptdev = dev_get_drvdata(dev);
+	struct panfrost_device *pfdev = dev_get_drvdata(dev);
 	struct dev_pm_opp *opp;
 	int err;
 
@@ -40,7 +40,7 @@ static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 
 	err = dev_pm_opp_set_rate(dev, *freq);
 	if (!err)
-		ptdev->pfdevfreq.current_frequency = *freq;
+		pfdev->pfdevfreq.current_frequency = *freq;
 
 	return err;
 }
Signature · 1 line
2.39.5
author maintainer
#142 lore raw

PATCH 136/627 drm/panthor: Add missing explicit padding in drm_panthor_gpu_info

In reply to Greg Kroah-Hartman

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

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

From: Boris Brezillon <[email protected]>

[ Upstream commit 95cbab48782bf62e4093837dc15ac6133902c12f ]

drm_panthor_gpu_info::shader_present is currently automatically offset by 4 byte to meet Arm's 32-bit/64-bit field alignment rules, but those constraints don't stand on 32-bit x86 and cause a mismatch when running an x86 binary in a user emulated environment like FEX. It's also generally agreed that uAPIs should explicitly pad their struct fields, which we originally intended to do, but a mistake slipped through during the submission process, leading drm_panthor_gpu_info::shader_present to be misaligned.

This uAPI change doesn't break any of the existing users of panthor which are either arm32 or arm64 where the 64-bit alignment of u64 fields is already enforced a the compiler level.

Changes in v2:
- Rename the garbage field into pad0 and adjust the comment accordingly
- Add Liviu's A-b

Changes in v3:
- Add R-bs

---
 include/uapi/drm/panthor_drm.h | 3 +++
 1 file changed, 3 insertions(+)
include/uapi/drm/panthor_drm.h +3 -0
index ad9a70afea6c..3a76c4f2882b 100644
@@ -296,6 +296,9 @@ struct drm_panthor_gpu_info {
 	/** @as_present: Bitmask encoding the number of address-space exposed by the MMU. */
 	__u32 as_present;
 
+	/** @pad0: MBZ. */
+	__u32 pad0;
+
 	/** @shader_present: Bitmask encoding the shader cores exposed by the GPU. */
 	__u64 shader_present;
 
Signature · 1 line
2.39.5
author maintainer
#143 lore raw

PATCH 137/627 wifi: rtw89: mcc: prevent shift wrapping in rtw89_core_mlsr_switch()

In reply to Greg Kroah-Hartman

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

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

From: Dan Carpenter <[email protected]>

[ Upstream commit 53cf488927a0f79968f9c03c4d1e00d2a79731c3 ]

The "link_id" value comes from the user via debugfs. If it's larger than BITS_PER_LONG then that would result in shift wrapping and potentially an out of bounds access later. In fact, we can limit it to IEEE80211_MLD_MAX_NUM_LINKS (15).

Fortunately, only root can write to debugfs files so the security impact is minimal.

---
 drivers/net/wireless/realtek/rtw89/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/wireless/realtek/rtw89/core.c +2 -1
index 49447668cbf3..3604a8e15df0 100644
@@ -5239,7 +5239,8 @@ int rtw89_core_mlsr_switch(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 	if (unlikely(!ieee80211_vif_is_mld(vif)))
 		return -EOPNOTSUPP;
 
-	if (unlikely(!(usable_links & BIT(link_id)))) {
+	if (unlikely(link_id >= IEEE80211_MLD_MAX_NUM_LINKS ||
+		     !(usable_links & BIT(link_id)))) {
 		rtw89_warn(rtwdev, "%s: link id %u is not usable\n", __func__,
 			   link_id);
 		return -ENOLINK;
Signature · 1 line
2.39.5
author maintainer
#144 lore raw

PATCH 138/627 wifi: rtw89: sar: drop lockdep assertion in rtw89_set_sar_from_acpi

In reply to Greg Kroah-Hartman

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

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

From: Fedor Pchelkin <[email protected]>

[ Upstream commit 6fe21445f7e801de5527d420f8e25e97b0cdd7e2 ]

The following assertion is triggered on the rtw89 driver startup. It looks meaningless to hold wiphy lock on the early init stage so drop the assertion.

 WARNING: CPU: 7 PID: 629 at drivers/net/wireless/realtek/rtw89/sar.c:502 rtw89_set_sar_from_acpi+0x365/0x4d0 [rtw89_core]
 CPU: 7 UID: 0 PID: 629 Comm: (udev-worker) Not tainted 6.15.0+ #29 PREEMPT(lazy)
 Hardware name: LENOVO 21D0/LNVNB161216, BIOS J6CN50WW 09/27/2024
 RIP: 0010:rtw89_set_sar_from_acpi+0x365/0x4d0 [rtw89_core]
 Call Trace:
  <TASK>
  rtw89_sar_init+0x68/0x2c0 [rtw89_core]
  rtw89_core_init+0x188e/0x1e50 [rtw89_core]
  rtw89_pci_probe+0x530/0xb50 [rtw89_pci]
  local_pci_probe+0xd9/0x190
  pci_call_probe+0x183/0x540
  pci_device_probe+0x171/0x2c0
  really_probe+0x1e1/0x890
  __driver_probe_device+0x18c/0x390
  driver_probe_device+0x4a/0x120
  __driver_attach+0x1a0/0x530
  bus_for_each_dev+0x10b/0x190
  bus_add_driver+0x2eb/0x540
  driver_register+0x1a3/0x3a0
  do_one_initcall+0xd5/0x450
  do_init_module+0x2cc/0x8f0
  init_module_from_file+0xe1/0x150
  idempotent_init_module+0x226/0x760
  __x64_sys_finit_module+0xcd/0x150
  do_syscall_64+0x94/0x380
  entry_SYSCALL_64_after_hwframe+0x76/0x7e

Found by Linux Verification Center (linuxtesting.org).

Fixes 88ca3107d2ce ("wifi: rtw89: sar: add skeleton for SAR configuration via ACPI")
---
 drivers/net/wireless/realtek/rtw89/sar.c | 2 --
 1 file changed, 2 deletions(-)
drivers/net/wireless/realtek/rtw89/sar.c +0 -2
index 517b66022f18..33a4b5c23fe7 100644
@@ -499,8 +499,6 @@ static void rtw89_set_sar_from_acpi(struct rtw89_dev *rtwdev)
 	struct rtw89_sar_cfg_acpi *cfg;
 	int ret;
 
-	lockdep_assert_wiphy(rtwdev->hw->wiphy);
-
 	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
 	if (!cfg)
 		return;
Signature · 1 line
2.39.5
author maintainer
#145 lore raw

PATCH 139/627 wifi: rtw89: sar: do not assert wiphy lock held until probing is done

In reply to Greg Kroah-Hartman

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

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

From: Fedor Pchelkin <[email protected]>

[ Upstream commit dad7aafa5216e307b357b801668451a3b8945810 ]

rtw89_sar_set_src() may be called at driver early init phase when applying SAR configuration via ACPI. wiphy lock is not held there.

Since the assertion was initially added for rtw89_apply_sar_common() call path and may be helpful for other places in future changes, keep it but move it under RTW89_FLAG_PROBE_DONE test.

Found by Linux Verification Center (linuxtesting.org).

Fixes 88ca3107d2ce ("wifi: rtw89: sar: add skeleton for SAR configuration via ACPI")
---
 drivers/net/wireless/realtek/rtw89/sar.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/wireless/realtek/rtw89/sar.c +2 -1
index 33a4b5c23fe7..7f568ffb3766 100644
@@ -199,7 +199,8 @@ struct rtw89_sar_handler rtw89_sar_handlers[RTW89_SAR_SOURCE_NR] = {
 		typeof(_dev) _d = (_dev);				\
 		BUILD_BUG_ON(!rtw89_sar_handlers[_s].descr_sar_source);	\
 		BUILD_BUG_ON(!rtw89_sar_handlers[_s].query_sar_config);	\
-		lockdep_assert_wiphy(_d->hw->wiphy);			\
+		if (test_bit(RTW89_FLAG_PROBE_DONE, _d->flags))		\
+			lockdep_assert_wiphy(_d->hw->wiphy);		\
 		_d->sar._cfg_name = *(_cfg_data);			\
 		_d->sar.src = _s;					\
 	} while (0)
Signature · 1 line
2.39.5
author maintainer
#146 lore raw

PATCH 140/627 wifi: rtw89: fix EHT 20MHz TX rate for non-AP STA

In reply to Greg Kroah-Hartman

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

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

From: Kuan-Chung Chen <[email protected]>

[ Upstream commit fe30a8ae853bade282fce63e740b5f34bdc55f6e ]

The 4-octet EHT MCS/NSS subfield is only used for 20 MHz-only non-AP STA. Correct the interpretation of this subfield to prevent improper rate limitations.

Fixes f1dfcee2eae9 ("wifi: rtw89: Correct EHT TX rate on 20MHz connection")
---
 drivers/net/wireless/realtek/rtw89/phy.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)
drivers/net/wireless/realtek/rtw89/phy.c +7 -5
index 76a2e26d4a10..e45e5dd5ca0a 100644
@@ -119,10 +119,12 @@ static u64 get_eht_mcs_ra_mask(u8 *max_nss, u8 start_mcs, u8 n_nss)
 	return mask;
 }
 
-static u64 get_eht_ra_mask(struct ieee80211_link_sta *link_sta)
+static u64 get_eht_ra_mask(struct rtw89_vif_link *rtwvif_link,
+			   struct ieee80211_link_sta *link_sta)
 {
-	struct ieee80211_sta_eht_cap *eht_cap = &link_sta->eht_cap;
+	struct ieee80211_vif *vif = rtwvif_link_to_vif(rtwvif_link);
 	struct ieee80211_eht_mcs_nss_supp_20mhz_only *mcs_nss_20mhz;
+	struct ieee80211_sta_eht_cap *eht_cap = &link_sta->eht_cap;
 	struct ieee80211_eht_mcs_nss_supp_bw *mcs_nss;
 	u8 *he_phy_cap = link_sta->he_cap.he_cap_elem.phy_cap_info;
 
@@ -136,8 +138,8 @@ static u64 get_eht_ra_mask(struct ieee80211_link_sta *link_sta)
 		/* MCS 9, 11, 13 */
 		return get_eht_mcs_ra_mask(mcs_nss->rx_tx_max_nss, 9, 3);
 	case IEEE80211_STA_RX_BW_20:
-		if (!(he_phy_cap[0] &
-		      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) {
+		if (vif->type == NL80211_IFTYPE_AP &&
+		    !(he_phy_cap[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) {
 			mcs_nss_20mhz = &eht_cap->eht_mcs_nss_supp.only_20mhz;
 			/* MCS 7, 9, 11, 13 */
 			return get_eht_mcs_ra_mask(mcs_nss_20mhz->rx_tx_max_nss, 7, 4);
@@ -332,7 +334,7 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev,
 	/* Set the ra mask from sta's capability */
 	if (link_sta->eht_cap.has_eht) {
 		mode |= RTW89_RA_MODE_EHT;
-		ra_mask |= get_eht_ra_mask(link_sta);
+		ra_mask |= get_eht_ra_mask(rtwvif_link, link_sta);
 
 		if (rtwdev->hal.no_mcs_12_13)
 			high_rate_masks = rtw89_ra_mask_eht_mcs0_11;
Signature · 1 line
2.39.5
author maintainer
#147 lore raw

PATCH 141/627 bpf, sockmap: Fix psock incorrectly pointing to sk

In reply to Greg Kroah-Hartman

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

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

From: Jiayuan Chen <[email protected]>

[ Upstream commit 76be5fae32febb1fdb848ba09f78c4b2c76cb337 ]

We observed an issue from the latest selftest: sockmap_redir where sk_psock(psock->sk) != psock in the backlog. The root cause is the special behavior in sockmap_redir - it frequently performs map_update() and map_delete() on the same socket. During map_update(), we create a new psock and during map_delete(), we eventually free the psock via rcu_work in sk_psock_drop(). However, pending workqueues might still exist and not be processed yet. If users immediately perform another map_update(), a new psock will be allocated for the same sk, resulting in two psocks pointing to the same sk.

When the pending workqueue is later triggered, it uses the old psock to access sk for I/O operations, which is incorrect.

Timing Diagram:

cpu0 cpu1

map_update(sk):

    sk->psock = psock1
    psock1->sk = sk

map_delete(sk):
rcu_work_free(psock1)

map_update(sk):
sk->psock = psock2
psock2->sk = sk
workqueue:
wakeup with psock1, but the sk of psock1 doesn't belong to psock1
rcu_handler:
clean psock1
free(psock1)

Previously, we used reference counting to address the concurrency issue between backlog and sock_map_close(). This logic remains necessary as it prevents the sk from being freed while processing the backlog. But this patch prevents pending backlogs from using a psock after it has been stopped.

Note: We cannot call cancel_delayed_work_sync() in map_delete() since this might be invoked in BPF context by BPF helper, and the function may sleep.

Fixes 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
---
 net/core/skmsg.c | 7 +++++++
 1 file changed, 7 insertions(+)
net/core/skmsg.c +7 -0
index 34c51eb1a14f..83c78379932e 100644
@@ -656,6 +656,13 @@ static void sk_psock_backlog(struct work_struct *work)
 	bool ingress;
 	int ret;
 
+	/* If sk is quickly removed from the map and then added back, the old
+	 * psock should not be scheduled, because there are now two psocks
+	 * pointing to the same sk.
+	 */
+	if (!sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+		return;
+
 	/* Increment the psock refcnt to synchronize with close(fd) path in
 	 * sock_map_close(), ensuring we wait for backlog thread completion
 	 * before sk_socket freed. If refcnt increment fails, it indicates
Signature · 1 line
2.39.5
author maintainer
#148 lore raw

PATCH 142/627 netconsole: Only register console drivers when targets are configured

In reply to Greg Kroah-Hartman

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

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

From: Breno Leitao <[email protected]>

[ Upstream commit bc0cb64db1c765a81f69997d5a28f539e1731bc0 ]

The netconsole driver currently registers the basic console driver unconditionally during initialization, even when only extended targets are configured. This results in unnecessary console registration and performance overhead, as the write_msg() callback is invoked for every log message only to return early when no matching targets are found.

Optimize the driver by conditionally registering console drivers based on the actual target configuration. The basic console driver is now registered only when non-extended targets exist, same as the extended console. The implementation also handles dynamic target creation through the configfs interface.

This change eliminates unnecessary console driver registrations, redundant write_msg() callbacks for unused console types, and associated lock contention and target list iterations. The optimization is particularly beneficial for systems using only the most common extended console type.

Fixes e2f15f9a79201 ("netconsole: implement extended console support")
---
 drivers/net/netconsole.c | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)
drivers/net/netconsole.c +22 -8
index 176935a8645f..a35b1fd4337b 100644
@@ -86,10 +86,10 @@ static DEFINE_SPINLOCK(target_list_lock);
 static DEFINE_MUTEX(target_cleanup_list_lock);
 
 /*
- * Console driver for extended netconsoles.  Registered on the first use to
- * avoid unnecessarily enabling ext message formatting.
+ * Console driver for netconsoles.  Register only consoles that have
+ * an associated target of the same type.
  */
-static struct console netconsole_ext;
+static struct console netconsole_ext, netconsole;
 
 struct netconsole_target_stats  {
 	u64_stats_t xmit_drop_count;
@@ -97,6 +97,11 @@ struct netconsole_target_stats  {
 	struct u64_stats_sync syncp;
 };
 
+enum console_type {
+	CONS_BASIC = BIT(0),
+	CONS_EXTENDED = BIT(1),
+};
+
 /* Features enabled in sysdata. Contrary to userdata, this data is populated by
  * the kernel. The fields are designed as bitwise flags, allowing multiple
  * features to be set in sysdata_fields.
@@ -491,6 +496,12 @@ static ssize_t enabled_store(struct config_item *item,
 		if (nt->extended && !console_is_registered(&netconsole_ext))
 			register_console(&netconsole_ext);
 
+		/* User might be enabling the basic format target for the very
+		 * first time, make sure the console is registered.
+		 */
+		if (!nt->extended && !console_is_registered(&netconsole))
+			register_console(&netconsole);
+
 		/*
 		 * Skip netpoll_parse_options() -- all the attributes are
 		 * already configured via configfs. Just print them out.
@@ -1690,8 +1701,8 @@ static int __init init_netconsole(void)
 {
 	int err;
 	struct netconsole_target *nt, *tmp;
+	u32 console_type_needed = 0;
 	unsigned int count = 0;
-	bool extended = false;
 	unsigned long flags;
 	char *target_config;
 	char *input = config;
@@ -1707,9 +1718,10 @@ static int __init init_netconsole(void)
 			}
 			/* Dump existing printks when we register */
 			if (nt->extended) {
-				extended = true;
+				console_type_needed |= CONS_EXTENDED;
 				netconsole_ext.flags |= CON_PRINTBUFFER;
 			} else {
+				console_type_needed |= CONS_BASIC;
 				netconsole.flags |= CON_PRINTBUFFER;
 			}
 
@@ -1728,9 +1740,10 @@ static int __init init_netconsole(void)
 	if (err)
 		goto undonotifier;
 
-	if (extended)
+	if (console_type_needed & CONS_EXTENDED)
 		register_console(&netconsole_ext);
-	register_console(&netconsole);
+	if (console_type_needed & CONS_BASIC)
+		register_console(&netconsole);
 	pr_info("network logging started\n");
 
 	return err;
@@ -1760,7 +1773,8 @@ static void __exit cleanup_netconsole(void)
 
 	if (console_is_registered(&netconsole_ext))
 		unregister_console(&netconsole_ext);
-	unregister_console(&netconsole);
+	if (console_is_registered(&netconsole))
+		unregister_console(&netconsole);
 	dynamic_netconsole_exit();
 	unregister_netdevice_notifier(&netconsole_netdev_notifier);
 
Signature · 1 line
2.39.5
author maintainer
#149 lore raw

PATCH 143/627 bpf, ktls: Fix data corruption when using bpf_msg_pop_data() in ktls

In reply to Greg Kroah-Hartman

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

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

From: Jiayuan Chen <[email protected]>

[ Upstream commit 178f6a5c8cb3b6be1602de0964cd440243f493c9 ]

When sending plaintext data, we initially calculated the corresponding ciphertext length. However, if we later reduced the plaintext data length via socket policy, we failed to recalculate the ciphertext length.

This results in transmitting buffers containing uninitialized data during ciphertext transmission.

This causes uninitialized bytes to be appended after a complete "Application Data" packet, leading to errors on the receiving end when parsing TLS record.

---
 net/tls/tls_sw.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)
net/tls/tls_sw.c +13 -0
index fc88e34b7f33..549d1ea01a72 100644
@@ -872,6 +872,19 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 		delta = msg->sg.size;
 		psock->eval = sk_psock_msg_verdict(sk, psock, msg);
 		delta -= msg->sg.size;
+
+		if ((s32)delta > 0) {
+			/* It indicates that we executed bpf_msg_pop_data(),
+			 * causing the plaintext data size to decrease.
+			 * Therefore the encrypted data size also needs to
+			 * correspondingly decrease. We only need to subtract
+			 * delta to calculate the new ciphertext length since
+			 * ktls does not support block encryption.
+			 */
+			struct sk_msg *enc = &ctx->open_rec->msg_encrypted;
+
+			sk_msg_trim(sk, enc, enc->sg.size - delta);
+		}
 	}
 	if (msg->cork_bytes && msg->cork_bytes > msg->sg.size &&
 	    !enospc && !full_record) {
Signature · 1 line
2.39.5
author maintainer
#150 lore raw

PATCH 144/627 net, bpf: Fix RCU usage in task_cls_state() for BPF programs

In reply to Greg Kroah-Hartman

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

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

From: Charalampos Mitrodimas <[email protected]>

[ Upstream commit 7f12c33850482521c961c5c15a50ebe9b9a88d1e ]

The commit ee971630f20f ("bpf: Allow some trace helpers for all prog types") made bpf_get_cgroup_classid_curr helper available to all BPF program types, not just networking programs.

This helper calls __task_get_classid() which internally calls task_cls_state() requiring rcu_read_lock_bh_held(). This works in networking/tc context where RCU BH is held, but triggers an RCU warning when called from other contexts like BPF syscall programs that run under rcu_read_lock_trace():

WARNING: suspicious RCU usage 6.15.0-rc4-syzkaller-g079e5c56a5c4 #0 Not tainted
-----------------------------
net/core/netclassid_cgroup.c:24 suspicious rcu_dereference_check() usage!

Fix this by also accepting rcu_read_lock_held() and rcu_read_lock_trace_held() as valid RCU contexts in the task_cls_state() function. This ensures the helper works correctly in all needed RCU contexts where it might be called, regular RCU, RCU BH (for networking), and RCU trace (for BPF syscall programs).

---
 net/core/netclassid_cgroup.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
net/core/netclassid_cgroup.c +3 -1
index d22f0919821e..dff66d8fb325 100644
@@ -21,7 +21,9 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state
 struct cgroup_cls_state *task_cls_state(struct task_struct *p)
 {
 	return css_cls_state(task_css_check(p, net_cls_cgrp_id,
-					    rcu_read_lock_bh_held()));
+					    rcu_read_lock_held() ||
+					    rcu_read_lock_bh_held() ||
+					    rcu_read_lock_trace_held()));
 }
 EXPORT_SYMBOL_GPL(task_cls_state);
 
Signature · 1 line
2.39.5
author maintainer
#151 lore raw

PATCH 145/627 selftests/bpf: fix signedness bug in redir_partial()

In reply to Greg Kroah-Hartman

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

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

From: Fushuai Wang <[email protected]>

[ Upstream commit 6a4bd31f680a1d1cf06492fe6dc4f08da09769e6 ]

When xsend() returns -1 (error), the check 'n < sizeof(buf)' incorrectly treats it as success due to unsigned promotion. Explicitly check for -1 first.

Fixes a4b7193d8efd ("selftests/bpf: Add sockmap test for redirecting partial skb data")
---
 tools/testing/selftests/bpf/prog_tests/sockmap_listen.c | 2 ++
 1 file changed, 2 insertions(+)
tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +2 -0
index 1d98eee7a2c3..f1bdccc7e4e7 100644
@@ -924,6 +924,8 @@ static void redir_partial(int family, int sotype, int sock_map, int parser_map)
 		goto close;
 
 	n = xsend(c1, buf, sizeof(buf), 0);
+	if (n == -1)
+		goto close;
 	if (n < sizeof(buf))
 		FAIL("incomplete write");
 
Signature · 1 line
2.39.5
author maintainer
#152 lore raw

PATCH 146/627 bpf: handle jset (if a & b ...) as a jump in CFG computation

In reply to Greg Kroah-Hartman

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

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

From: Eduard Zingerman <[email protected]>

[ Upstream commit 3157f7e2999616ac91f4d559a8566214f74000a5 ]

BPF_JSET is a conditional jump and currently verifier.c:can_jump() does not know about that. This can lead to incorrect live registers and SCC computation.

E.g. in the following example:

   1: r0 = 1;
   2: r2 = 2;
   3: if r1 & 0x7 goto +1;
   4: exit;
   5: r0 = r2;
   6: exit;

W/o this fix insn_successors(3) will return only (4), a jump to (5) would be missed and r2 won't be marked as alive at (3).

---
 kernel/bpf/verifier.c | 1 +
 1 file changed, 1 insertion(+)
kernel/bpf/verifier.c +1 -0
index 169845710c7e..97e07eb31fec 100644
@@ -23671,6 +23671,7 @@ static bool can_jump(struct bpf_insn *insn)
 	case BPF_JSLT:
 	case BPF_JSLE:
 	case BPF_JCOND:
+	case BPF_JSET:
 		return true;
 	}
 
Signature · 1 line
2.39.5
author maintainer
#153 lore raw

PATCH 147/627 selftests/bpf: Fix unintentional switch case fall through

In reply to Greg Kroah-Hartman

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

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

From: Mykyta Yatsenko <[email protected]>

[ Upstream commit 66ab68c9de89672366fdc474f4f185bb58cecf2d ]

Break from switch expression after parsing -n CLI argument in veristat, instead of falling through and enabling comparison mode.

Fixes a5c57f81eb2b ("veristat: add ability to set BPF_F_TEST_SANITY_STRICT flag with -r flag")
---
 tools/testing/selftests/bpf/veristat.c | 1 +
 1 file changed, 1 insertion(+)
tools/testing/selftests/bpf/veristat.c +1 -0
index b2bb20b00952..adf948fff211 100644
@@ -344,6 +344,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 			fprintf(stderr, "invalid top N specifier: %s\n", arg);
 			argp_usage(state);
 		}
+		break;
 	case 'C':
 		env.comparison_mode = true;
 		break;
Signature · 1 line
2.39.5
author maintainer
#154 lore raw

PATCH 148/627 net: ipv6: ip6mr: Fix in/out netdev to pass to the FORWARD chain

In reply to Greg Kroah-Hartman

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

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

From: Petr Machata <[email protected]>

[ Upstream commit 3365afd3abda5f6a54f4a822dad5c9314e94c3fc ]

The netfilter hook is invoked with skb->dev for input netdevice, and vif_dev for output netdevice. However at the point of invocation, skb->dev is already set to vif_dev, and MR-forwarded packets are reported with in=out:

 # ip6tables -A FORWARD -j LOG --log-prefix '[forw]'
 # cd tools/testing/selftests/net/forwarding
 # ./router_multicast.sh
 # dmesg | fgrep '[forw]'
 [ 1670.248245] [forw]IN=v5 OUT=v5 [...]

For reference, IPv4 MR code shows in and out as appropriate. Fix by caching skb->dev and using the updated value for output netdev.

---
 net/ipv6/ip6mr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
net/ipv6/ip6mr.c +2 -1
index 9db31e5b998c..426859cd3409 100644
@@ -2039,6 +2039,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt,
 			  struct sk_buff *skb, int vifi)
 {
 	struct vif_device *vif = &mrt->vif_table[vifi];
+	struct net_device *indev = skb->dev;
 	struct net_device *vif_dev;
 	struct ipv6hdr *ipv6h;
 	struct dst_entry *dst;
@@ -2101,7 +2102,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt,
 	IP6CB(skb)->flags |= IP6SKB_FORWARDED;
 
 	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
-		       net, NULL, skb, skb->dev, vif_dev,
+		       net, NULL, skb, indev, skb->dev,
 		       ip6mr_forward2_finish);
 
 out_free:
Signature · 1 line
2.39.5
author maintainer
#155 lore raw

PATCH 149/627 drm/vmwgfx: Fix Host-Backed userspace on Guest-Backed kernel

In reply to Greg Kroah-Hartman

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

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

From: Ian Forbes <[email protected]>

[ Upstream commit 7872997c048e989c7689c2995d230fdca7798000 ]

Running 3D applications with SVGA_FORCE_HOST_BACKED=1 or using an ancient version of mesa was broken because the buffer was pinned in VMW_BO_DOMAIN_SYS and could not be moved to VMW_BO_DOMAIN_MOB during validation.

The compat_shader buffer should not pinned.

Fixes 668b206601c5 ("drm/vmwgfx: Stop using raw ttm_buffer_object's")
---
 drivers/gpu/drm/vmwgfx/vmwgfx_shader.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +1 -1
index 7fb1c88bcc47..69dfe69ce0f8 100644
@@ -896,7 +896,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 		.busy_domain = VMW_BO_DOMAIN_SYS,
 		.bo_type = ttm_bo_type_device,
 		.size = size,
-		.pin = true,
+		.pin = false,
 		.keep_resv = true,
 	};
 
Signature · 1 line
2.39.5
author maintainer
#156 lore raw

PATCH 150/627 slub: Fix a documentation build error for krealloc()

In reply to Greg Kroah-Hartman

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

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

From: Jonathan Corbet <[email protected]>

[ Upstream commit e8a45f198e3ae2434108f815bc28f37f6fe6742b ]

The kerneldoc comment for krealloc() contains an unmarked literal block, leading to these warnings in the docs build:

./mm/slub.c:4936: WARNING: Block quote ends without a blank line; unexpected unindent. [docutils] ./mm/slub.c:4936: ERROR: Undefined substitution referenced: "--------". [docutils]

Mark up and indent the block properly to bring a bit of peace to our build logs.

---
 mm/slub.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
mm/slub.c +5 -5
index 31e11ef256f9..45a963e363d3 100644
@@ -4930,12 +4930,12 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags)
  * When slub_debug_orig_size() is off, krealloc() only knows about the bucket
  * size of an allocation (but not the exact size it was allocated with) and
  * hence implements the following semantics for shrinking and growing buffers
- * with __GFP_ZERO.
+ * with __GFP_ZERO::
  *
- *         new             bucket
- * 0       size             size
- * |--------|----------------|
- * |  keep  |      zero      |
+ *           new             bucket
+ *   0       size             size
+ *   |--------|----------------|
+ *   |  keep  |      zero      |
  *
  * Otherwise, the original allocation size 'orig_size' could be used to
  * precisely clear the requested size, and the new size will also be stored
Signature · 1 line
2.39.5
author maintainer
#157 lore raw

PATCH 151/627 drm/amdgpu: Remove nbiov7.9 replay count reporting

In reply to Greg Kroah-Hartman

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

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

From: Lijo Lazar <[email protected]>

[ Upstream commit 0f566f0e9c614aa3d95082246f5b8c9e8a09c8b3 ]

Direct pcie replay count reporting is not available on nbio v7.9. Reporting is done through firmware.

Fixes 50709d18f4a6 ("drm/amdgpu: Add pci replay count to nbio v7.9")
---
 drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c | 20 --------------------
 1 file changed, 20 deletions(-)
drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c +0 -20
index a376f072700d..1c22bc11c1f8 100644
@@ -31,9 +31,6 @@
 
 #define NPS_MODE_MASK 0x000000FFL
 
-/* Core 0 Port 0 counter */
-#define smnPCIEP_NAK_COUNTER 0x1A340218
-
 static void nbio_v7_9_remap_hdp_registers(struct amdgpu_device *adev)
 {
 	WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL,
@@ -467,22 +464,6 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev)
 	}
 }
 
-static u64 nbio_v7_9_get_pcie_replay_count(struct amdgpu_device *adev)
-{
-	u32 val, nak_r, nak_g;
-
-	if (adev->flags & AMD_IS_APU)
-		return 0;
-
-	/* Get the number of NAKs received and generated */
-	val = RREG32_PCIE(smnPCIEP_NAK_COUNTER);
-	nak_r = val & 0xFFFF;
-	nak_g = val >> 16;
-
-	/* Add the total number of NAKs, i.e the number of replays */
-	return (nak_r + nak_g);
-}
-
 #define MMIO_REG_HOLE_OFFSET 0x1A000
 
 static void nbio_v7_9_set_reg_remap(struct amdgpu_device *adev)
@@ -524,7 +505,6 @@ const struct amdgpu_nbio_funcs nbio_v7_9_funcs = {
 	.get_memory_partition_mode = nbio_v7_9_get_memory_partition_mode,
 	.is_nps_switch_requested = nbio_v7_9_is_nps_switch_requested,
 	.init_registers = nbio_v7_9_init_registers,
-	.get_pcie_replay_count = nbio_v7_9_get_pcie_replay_count,
 	.set_reg_remap = nbio_v7_9_set_reg_remap,
 };
 
Signature · 1 line
2.39.5
author maintainer
#158 lore raw

PATCH 152/627 drm/amdgpu/sdma: handle paging queues in amdgpu_sdma_reset_engine()

In reply to Greg Kroah-Hartman

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

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

From: Alex Deucher <[email protected]>

[ Upstream commit 9a9e87d15297ce72507178e93cbb773510c061cd ]

Need to properly start and stop paging queues if they are present.

This is not an issue today since we don't support a paging queue on any chips with queue reset.

Fixes b22659d5d352 ("drm/amdgpu: switch amdgpu_sdma_reset_engine to use the new sdma function pointers")
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +8 -2
index 9b54a1ece447..f7decf533bae 100644
@@ -597,8 +597,11 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
 		page_sched_stopped = true;
 	}
 
-	if (sdma_instance->funcs->stop_kernel_queue)
+	if (sdma_instance->funcs->stop_kernel_queue) {
 		sdma_instance->funcs->stop_kernel_queue(gfx_ring);
+		if (adev->sdma.has_page_queue)
+			sdma_instance->funcs->stop_kernel_queue(page_ring);
+	}
 
 	/* Perform the SDMA reset for the specified instance */
 	ret = amdgpu_sdma_soft_reset(adev, instance_id);
@@ -607,8 +610,11 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
 		goto exit;
 	}
 
-	if (sdma_instance->funcs->start_kernel_queue)
+	if (sdma_instance->funcs->start_kernel_queue) {
 		sdma_instance->funcs->start_kernel_queue(gfx_ring);
+		if (adev->sdma.has_page_queue)
+			sdma_instance->funcs->start_kernel_queue(page_ring);
+	}
 
 exit:
 	/* Restart the scheduler's work queue for the GFX and page rings
Signature · 1 line
2.39.5
author maintainer
#159 lore raw

PATCH 153/627 net: mana: Fix potential deadlocks in mana napi ops

In reply to Greg Kroah-Hartman

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

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

From: Erni Sri Satya Vennela <[email protected]>

[ Upstream commit d5c8f0e4e0cb0ac2a4a4e015f2f5b1ba39e5e583 ]

When net_shaper_ops are enabled for MANA, netdev_ops_lock becomes active.

MANA VF setup/teardown by netvsc follows this call chain:

netvsc_vf_setup()

        dev_change_flags()
		...
         __dev_open() OR __dev_close()

dev_change_flags() holds the netdev mutex via netdev_lock_ops.

Meanwhile, mana_create_txq() and mana_create_rxq() in mana_open() path call NAPI APIs (netif_napi_add_tx(), netif_napi_add_weight(), napi_enable()), which also try to acquire the same lock, risking deadlock.

Similarly in the teardown path (mana_close()), netif_napi_disable() and netif_napi_del(), contend for the same lock.

Switch to the _locked variants of these APIs to avoid deadlocks when the netdev_ops_lock is held.

---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 28 +++++++++++++------
 1 file changed, 19 insertions(+), 9 deletions(-)
drivers/net/ethernet/microsoft/mana/mana_en.c +19 -9
index faad1cb880f8..2dd14d97cc98 100644
@@ -1912,8 +1912,10 @@ static void mana_destroy_txq(struct mana_port_context *apc)
 		napi = &apc->tx_qp[i].tx_cq.napi;
 		if (apc->tx_qp[i].txq.napi_initialized) {
 			napi_synchronize(napi);
-			napi_disable(napi);
-			netif_napi_del(napi);
+			netdev_lock_ops_to_full(napi->dev);
+			napi_disable_locked(napi);
+			netif_napi_del_locked(napi);
+			netdev_unlock_full_to_ops(napi->dev);
 			apc->tx_qp[i].txq.napi_initialized = false;
 		}
 		mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object);
@@ -2065,8 +2067,11 @@ static int mana_create_txq(struct mana_port_context *apc,
 
 		mana_create_txq_debugfs(apc, i);
 
-		netif_napi_add_tx(net, &cq->napi, mana_poll);
-		napi_enable(&cq->napi);
+		set_bit(NAPI_STATE_NO_BUSY_POLL, &cq->napi.state);
+		netdev_lock_ops_to_full(net);
+		netif_napi_add_locked(net, &cq->napi, mana_poll);
+		napi_enable_locked(&cq->napi);
+		netdev_unlock_full_to_ops(net);
 		txq->napi_initialized = true;
 
 		mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
@@ -2102,9 +2107,10 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
 	if (napi_initialized) {
 		napi_synchronize(napi);
 
-		napi_disable(napi);
-
-		netif_napi_del(napi);
+		netdev_lock_ops_to_full(napi->dev);
+		napi_disable_locked(napi);
+		netif_napi_del_locked(napi);
+		netdev_unlock_full_to_ops(napi->dev);
 	}
 	xdp_rxq_info_unreg(&rxq->xdp_rxq);
 
@@ -2355,14 +2361,18 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 
 	gc->cq_table[cq->gdma_id] = cq->gdma_cq;
 
-	netif_napi_add_weight(ndev, &cq->napi, mana_poll, 1);
+	netdev_lock_ops_to_full(ndev);
+	netif_napi_add_weight_locked(ndev, &cq->napi, mana_poll, 1);
+	netdev_unlock_full_to_ops(ndev);
 
 	WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx,
 				 cq->napi.napi_id));
 	WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, MEM_TYPE_PAGE_POOL,
 					   rxq->page_pool));
 
-	napi_enable(&cq->napi);
+	netdev_lock_ops_to_full(ndev);
+	napi_enable_locked(&cq->napi);
+	netdev_unlock_full_to_ops(ndev);
 
 	mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
 out:
Signature · 1 line
2.39.5
author maintainer
#160 lore raw

PATCH 154/627 wifi: mac80211: Fix bssid_indicator for MBSSID in AP mode

In reply to Greg Kroah-Hartman

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

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

From: Rameshkumar Sundaram <[email protected]>

[ Upstream commit 2eb7c1baf46aea134e908cd6d37907d92f823251 ]

Currently, in ieee80211_assign_beacon() mbssid count is updated as link's bssid_indicator. mbssid count is the total number of MBSSID elements in the beacon instead of Max BSSID indicator of the Multiple BSS set. This will result in drivers obtaining an invalid bssid_indicator for BSSes in a Multiple BSS set.
Fix this by updating link's bssid_indicator from MBSSID element for Transmitting BSS and update the same for all of its Non-Transmitting BSSes.

Fixes dde78aa52015 ("mac80211: update bssid_indicator in ieee80211_assign_beacon")
---
 net/mac80211/cfg.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
net/mac80211/cfg.c +6 -2
index 954795b0fe48..bc64c1b83a6e 100644
@@ -178,6 +178,7 @@ static int ieee80211_set_ap_mbssid_options(struct ieee80211_sub_if_data *sdata,
 
 		link_conf->nontransmitted = true;
 		link_conf->bssid_index = params->index;
+		link_conf->bssid_indicator = tx_bss_conf->bssid_indicator;
 	}
 	if (params->ema)
 		link_conf->ema_ap = true;
@@ -1218,8 +1219,11 @@ ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
 			ieee80211_copy_rnr_beacon(pos, new->rnr_ies, rnr);
 		}
 		/* update bssid_indicator */
-		link_conf->bssid_indicator =
-			ilog2(__roundup_pow_of_two(mbssid->cnt + 1));
+		if (new->mbssid_ies->cnt && new->mbssid_ies->elem[0].len > 2)
+			link_conf->bssid_indicator =
+					*(new->mbssid_ies->elem[0].data + 2);
+		else
+			link_conf->bssid_indicator = 0;
 	}
 
 	if (csa) {
Signature · 1 line
2.39.5
author maintainer
#161 lore raw

PATCH 155/627 bpftool: Fix memory leak in dump_xx_nlmsg on realloc failure

In reply to Greg Kroah-Hartman

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

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

From: Yuan Chen <[email protected]>

[ Upstream commit 99fe8af069a9fa5b09140518b1364e35713a642e ]

In function dump_xx_nlmsg(), when realloc() fails to allocate memory, the original pointer to the buffer is overwritten with NULL. This causes a memory leak because the previously allocated buffer becomes unreachable without being freed.

Fixes 7900efc19214 ("tools/bpf: bpftool: improve output format for bpftool net")
---
 tools/bpf/bpftool/net.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)
tools/bpf/bpftool/net.c +9 -6
index 64f958f437b0..cfc6f944f7c3 100644
@@ -366,17 +366,18 @@ static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 {
 	struct bpf_netdev_t *netinfo = cookie;
 	struct ifinfomsg *ifinfo = msg;
+	struct ip_devname_ifindex *tmp;
 
 	if (netinfo->filter_idx > 0 && netinfo->filter_idx != ifinfo->ifi_index)
 		return 0;
 
 	if (netinfo->used_len == netinfo->array_len) {
-		netinfo->devices = realloc(netinfo->devices,
-			(netinfo->array_len + 16) *
-			sizeof(struct ip_devname_ifindex));
-		if (!netinfo->devices)
+		tmp = realloc(netinfo->devices,
+			(netinfo->array_len + 16) * sizeof(struct ip_devname_ifindex));
+		if (!tmp)
 			return -ENOMEM;
 
+		netinfo->devices = tmp;
 		netinfo->array_len += 16;
 	}
 	netinfo->devices[netinfo->used_len].ifindex = ifinfo->ifi_index;
@@ -395,6 +396,7 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 {
 	struct bpf_tcinfo_t *tcinfo = cookie;
 	struct tcmsg *info = msg;
+	struct tc_kind_handle *tmp;
 
 	if (tcinfo->is_qdisc) {
 		/* skip clsact qdisc */
@@ -406,11 +408,12 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	}
 
 	if (tcinfo->used_len == tcinfo->array_len) {
-		tcinfo->handle_array = realloc(tcinfo->handle_array,
+		tmp = realloc(tcinfo->handle_array,
 			(tcinfo->array_len + 16) * sizeof(struct tc_kind_handle));
-		if (!tcinfo->handle_array)
+		if (!tmp)
 			return -ENOMEM;
 
+		tcinfo->handle_array = tmp;
 		tcinfo->array_len += 16;
 	}
 	tcinfo->handle_array[tcinfo->used_len].handle = info->tcm_handle;
Signature · 1 line
2.39.5
author maintainer
#162 lore raw

PATCH 156/627 powerpc/pseries/dlpar: Search DRC index from ibm,drc-indexes for IO add

In reply to Greg Kroah-Hartman

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

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

From: Haren Myneni <[email protected]>

[ Upstream commit 41a1452759a8b1121df9cf7310acf31d766ba70b ]

IO hotplug add event is handled in the user space with drmgr tool. After the device is enabled, the user space uses /sys/kernel/dlpar interface with “dt add index <drc_index>” to update the device tree. The kernel interface (dlpar_hp_dt_add()) finds the parent node for the specified ‘drc_index’ from ibm,drc-info property. The recent FW provides this property from 2017 onwards. But KVM guest code in some releases is still using the older SLOF firmware which has ibm,drc-indexes property instead of ibm,drc-info.

If the ibm,drc-info is not available, this patch adds changes to search ‘drc_index’ from the indexes array in ibm,drc-indexes property to support old FW.

---
 arch/powerpc/platforms/pseries/dlpar.c | 52 +++++++++++++++++++++++++-
 1 file changed, 50 insertions(+), 2 deletions(-)
arch/powerpc/platforms/pseries/dlpar.c +50 -2
index 213aa26dc8b3..979487da6522 100644
@@ -404,6 +404,45 @@ get_device_node_with_drc_info(u32 index)
 	return NULL;
 }
 
+static struct device_node *
+get_device_node_with_drc_indexes(u32 drc_index)
+{
+	struct device_node *np = NULL;
+	u32 nr_indexes, index;
+	int i, rc;
+
+	for_each_node_with_property(np, "ibm,drc-indexes") {
+		/*
+		 * First element in the array is the total number of
+		 * DRC indexes returned.
+		 */
+		rc = of_property_read_u32_index(np, "ibm,drc-indexes",
+				0, &nr_indexes);
+		if (rc)
+			goto out_put_np;
+
+		/*
+		 * Retrieve DRC index from the list and return the
+		 * device node if matched with the specified index.
+		 */
+		for (i = 0; i < nr_indexes; i++) {
+			rc = of_property_read_u32_index(np, "ibm,drc-indexes",
+							i+1, &index);
+			if (rc)
+				goto out_put_np;
+
+			if (drc_index == index)
+				return np;
+		}
+	}
+
+	return NULL;
+
+out_put_np:
+	of_node_put(np);
+	return NULL;
+}
+
 static int dlpar_hp_dt_add(u32 index)
 {
 	struct device_node *np, *nodes;
@@ -423,10 +462,19 @@ static int dlpar_hp_dt_add(u32 index)
 		goto out;
 	}
 
+	/*
+	 * Recent FW provides ibm,drc-info property. So search
+	 * for the user specified DRC index from ibm,drc-info
+	 * property. If this property is not available, search
+	 * in the indexes array from ibm,drc-indexes property.
+	 */
 	np = get_device_node_with_drc_info(index);
 
-	if (!np)
-		return -EIO;
+	if (!np) {
+		np = get_device_node_with_drc_indexes(index);
+		if (!np)
+			return -EIO;
+	}
 
 	/* Next, configure the connector. */
 	nodes = dlpar_configure_connector(cpu_to_be32(index), np);
Signature · 1 line
2.39.5
author maintainer
#163 lore raw

PATCH 157/627 wifi: ath12k: Avoid accessing uninitialized arvif->ar during beacon miss

In reply to Greg Kroah-Hartman

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

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

From: Rameshkumar Sundaram <[email protected]>

[ Upstream commit 36670b67de18f1e5d34900c5d2ac60a8970c293c ]

During beacon miss handling, ath12k driver iterates over active virtual interfaces (vifs) and attempts to access the radio object (ar) via arvif->deflink->ar.

However, after commit aa80f12f3bed ("wifi: ath12k: defer vdev creation for MLO"), arvif is linked to a radio only after vdev creation, typically when a channel is assigned or a scan is requested.
For P2P capable devices, a default P2P interface is created by wpa_supplicant along with regular station interfaces, these serve as dummy interfaces for P2P-capable stations, lack an associated netdev and initiate frequent scans to discover neighbor p2p devices. When a scan is initiated on such P2P vifs, driver selects destination radio (ar) based on scan frequency, creates a scan vdev, and attaches arvif to the radio. Once the scan completes or is aborted, the scan vdev is deleted, detaching arvif from the radio and leaving arvif->ar uninitialized.

While handling beacon miss for station interfaces, P2P interface is also encountered in the vif iteration and ath12k_mac_handle_beacon_miss_iter() tries to dereference the uninitialized arvif->deflink->ar.

Fix this by verifying that vdev is created for the arvif before accessing its ar during beacon miss handling and similar vif iterator callbacks.

==========================================================================
wlp6s0: detected beacon loss from AP (missed 7 beacons) - probing

 KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017]

 CPU: 5 UID: 0 PID: 0 Comm: swapper/5 Not tainted 6.16.0-rc1-wt-ath+ #2 PREEMPT(full)
 RIP: 0010:ath12k_mac_handle_beacon_miss_iter+0xb5/0x1a0 [ath12k]
 Call Trace:
  __iterate_interfaces+0x11a/0x410 [mac80211]
  ieee80211_iterate_active_interfaces_atomic+0x61/0x140 [mac80211]
  ath12k_mac_handle_beacon_miss+0xa1/0xf0 [ath12k]
  ath12k_roam_event+0x393/0x560 [ath12k]
  ath12k_wmi_op_rx+0x1486/0x28c0 [ath12k]
  ath12k_htc_process_trailer.isra.0+0x2fb/0x620 [ath12k]
  ath12k_htc_rx_completion_handler+0x448/0x830 [ath12k]
  ath12k_ce_recv_process_cb+0x549/0x9e0 [ath12k]
  ath12k_ce_per_engine_service+0xbe/0xf0 [ath12k]
  ath12k_pci_ce_workqueue+0x69/0x120 [ath12k]
  process_one_work+0xe3a/0x1430

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284.1-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

---
 drivers/net/wireless/ath/ath12k/mac.c | 15 +++++++++------
 drivers/net/wireless/ath/ath12k/p2p.c |  3 ++-
 2 files changed, 11 insertions(+), 7 deletions(-)
drivers/net/wireless/ath/ath12k/mac.c +9 -6
index 59ec422992d3..5be7b79db341 100644
@@ -693,6 +693,9 @@ static void ath12k_get_arvif_iter(void *data, u8 *mac,
 		if (WARN_ON(!arvif))
 			continue;
 
+		if (!arvif->is_created)
+			continue;
+
 		if (arvif->vdev_id == arvif_iter->vdev_id &&
 		    arvif->ar == arvif_iter->ar) {
 			arvif_iter->arvif = arvif;
@@ -1755,7 +1758,7 @@ static void ath12k_mac_handle_beacon_iter(void *data, u8 *mac,
 	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
 	struct ath12k_link_vif *arvif = &ahvif->deflink;
 
-	if (vif->type != NL80211_IFTYPE_STATION)
+	if (vif->type != NL80211_IFTYPE_STATION || !arvif->is_created)
 		return;
 
 	if (!ether_addr_equal(mgmt->bssid, vif->bss_conf.bssid))
@@ -1778,16 +1781,16 @@ static void ath12k_mac_handle_beacon_miss_iter(void *data, u8 *mac,
 	u32 *vdev_id = data;
 	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
 	struct ath12k_link_vif *arvif = &ahvif->deflink;
-	struct ath12k *ar = arvif->ar;
-	struct ieee80211_hw *hw = ath12k_ar_to_hw(ar);
+	struct ieee80211_hw *hw;
 
-	if (arvif->vdev_id != *vdev_id)
+	if (!arvif->is_created || arvif->vdev_id != *vdev_id)
 		return;
 
 	if (!arvif->is_up)
 		return;
 
 	ieee80211_beacon_loss(vif);
+	hw = ath12k_ar_to_hw(arvif->ar);
 
 	/* Firmware doesn't report beacon loss events repeatedly. If AP probe
 	 * (done by mac80211) succeeds but beacons do not resume then it
@@ -9818,7 +9821,7 @@ ath12k_mac_change_chanctx_cnt_iter(void *data, u8 *mac,
 		if (WARN_ON(!arvif))
 			continue;
 
-		if (arvif->ar != arg->ar)
+		if (!arvif->is_created || arvif->ar != arg->ar)
 			continue;
 
 		link_conf = wiphy_dereference(ahvif->ah->hw->wiphy,
@@ -9853,7 +9856,7 @@ ath12k_mac_change_chanctx_fill_iter(void *data, u8 *mac,
 		if (WARN_ON(!arvif))
 			continue;
 
-		if (arvif->ar != arg->ar)
+		if (!arvif->is_created || arvif->ar != arg->ar)
 			continue;
 
 		link_conf = wiphy_dereference(ahvif->ah->hw->wiphy,
drivers/net/wireless/ath/ath12k/p2p.c +2 -1
index 84cccf7d91e7..59589748f1a8 100644
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #include <net/mac80211.h>
@@ -124,7 +125,7 @@ static void ath12k_p2p_noa_update_vdev_iter(void *data, u8 *mac,
 
 	WARN_ON(!rcu_read_lock_any_held());
 	arvif = &ahvif->deflink;
-	if (arvif->ar != arg->ar || arvif->vdev_id != arg->vdev_id)
+	if (!arvif->is_created || arvif->ar != arg->ar || arvif->vdev_id != arg->vdev_id)
 		return;
 
 	ath12k_p2p_noa_update(arvif, arg->noa);
Signature · 1 line
2.39.5
author maintainer
#164 lore raw

PATCH 158/627 wifi: ath12k: update channel list in worker when wait flag is set

In reply to Greg Kroah-Hartman

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

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

From: Kang Yang <[email protected]>

[ Upstream commit 437c7a2db6a34db2a9048920694a2bf9b0169726 ]

With previous patch [1], ath12k_reg_update_chan_list() will be called during reg_process_self_managed_hint().

reg_process_self_managed_hint() will hold rtnl_lock all the time. But ath12k_reg_update_chan_list() may increase the occupation time of rtnl_lock, because when wait flag is set, wait_for_completion_timeout() will be called during 11d/hw scan.

Should minimize the occupation time of rtnl_lock as much as possible to avoid interfering with rest of the system. So move the update channel list operation to a new worker, so that wait_for_completion_timeout() won't be called with the rtnl_lock held.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Fixes f335295aa29c ("wifi: ath12k: avoid deadlock during regulatory update in ath12k_regd_update()") #[1]
---
 drivers/net/wireless/ath/ath12k/core.c |  1 +
 drivers/net/wireless/ath/ath12k/core.h |  4 +-
 drivers/net/wireless/ath/ath12k/mac.c  | 13 ++++
 drivers/net/wireless/ath/ath12k/reg.c  | 85 ++++++++++++++++++--------
 drivers/net/wireless/ath/ath12k/reg.h  |  1 +
 drivers/net/wireless/ath/ath12k/wmi.h  |  1 +
 6 files changed, 78 insertions(+), 27 deletions(-)
drivers/net/wireless/ath/ath12k/core.c +1 -0
index 89ae80934b30..cd58ab9c2322 100644
@@ -1409,6 +1409,7 @@ void ath12k_core_halt(struct ath12k *ar)
 	ath12k_mac_peer_cleanup_all(ar);
 	cancel_delayed_work_sync(&ar->scan.timeout);
 	cancel_work_sync(&ar->regd_update_work);
+	cancel_work_sync(&ar->regd_channel_update_work);
 	cancel_work_sync(&ab->rfkill_work);
 	cancel_work_sync(&ab->update_11d_work);
 
drivers/net/wireless/ath/ath12k/core.h +3 -1
index 7bcd9c70309f..289998585fcb 100644
@@ -719,7 +719,7 @@ struct ath12k {
 
 	/* protects the radio specific data like debug stats, ppdu_stats_info stats,
 	 * vdev_stop_status info, scan data, ath12k_sta info, ath12k_link_vif info,
-	 * channel context data, survey info, test mode data.
+	 * channel context data, survey info, test mode data, regd_channel_update_queue.
 	 */
 	spinlock_t data_lock;
 
@@ -778,6 +778,8 @@ struct ath12k {
 	struct completion bss_survey_done;
 
 	struct work_struct regd_update_work;
+	struct work_struct regd_channel_update_work;
+	struct list_head regd_channel_update_queue;
 
 	struct wiphy_work wmi_mgmt_tx_work;
 	struct sk_buff_head wmi_mgmt_tx_queue;
drivers/net/wireless/ath/ath12k/mac.c +13 -0
index 5be7b79db341..3616269538e6 100644
@@ -8289,6 +8289,7 @@ static void ath12k_mac_stop(struct ath12k *ar)
 {
 	struct ath12k_hw *ah = ar->ah;
 	struct htt_ppdu_stats_info *ppdu_stats, *tmp;
+	struct ath12k_wmi_scan_chan_list_arg *arg;
 	int ret;
 
 	lockdep_assert_held(&ah->hw_mutex);
@@ -8303,6 +8304,7 @@ static void ath12k_mac_stop(struct ath12k *ar)
 
 	cancel_delayed_work_sync(&ar->scan.timeout);
 	wiphy_work_cancel(ath12k_ar_to_hw(ar)->wiphy, &ar->scan.vdev_clean_wk);
+	cancel_work_sync(&ar->regd_channel_update_work);
 	cancel_work_sync(&ar->regd_update_work);
 	cancel_work_sync(&ar->ab->rfkill_work);
 	cancel_work_sync(&ar->ab->update_11d_work);
@@ -8310,10 +8312,18 @@ static void ath12k_mac_stop(struct ath12k *ar)
 	complete(&ar->completed_11d_scan);
 
 	spin_lock_bh(&ar->data_lock);
+
 	list_for_each_entry_safe(ppdu_stats, tmp, &ar->ppdu_stats_info, list) {
 		list_del(&ppdu_stats->list);
 		kfree(ppdu_stats);
 	}
+
+	while ((arg = list_first_entry_or_null(&ar->regd_channel_update_queue,
+					       struct ath12k_wmi_scan_chan_list_arg,
+					       list))) {
+		list_del(&arg->list);
+		kfree(arg);
+	}
 	spin_unlock_bh(&ar->data_lock);
 
 	rcu_assign_pointer(ar->ab->pdevs_active[ar->pdev_idx], NULL);
@@ -12207,6 +12217,7 @@ static void ath12k_mac_hw_unregister(struct ath12k_hw *ah)
 	int i;
 
 	for_each_ar(ah, ar, i) {
+		cancel_work_sync(&ar->regd_channel_update_work);
 		cancel_work_sync(&ar->regd_update_work);
 		ath12k_debugfs_unregister(ar);
 		ath12k_fw_stats_reset(ar);
@@ -12567,6 +12578,8 @@ static void ath12k_mac_setup(struct ath12k *ar)
 
 	INIT_DELAYED_WORK(&ar->scan.timeout, ath12k_scan_timeout_work);
 	wiphy_work_init(&ar->scan.vdev_clean_wk, ath12k_scan_vdev_clean_work);
+	INIT_WORK(&ar->regd_channel_update_work, ath12k_regd_update_chan_list_work);
+	INIT_LIST_HEAD(&ar->regd_channel_update_queue);
 	INIT_WORK(&ar->regd_update_work, ath12k_regd_update_work);
 
 	wiphy_work_init(&ar->wmi_mgmt_tx_work, ath12k_mgmt_over_wmi_tx_work);
drivers/net/wireless/ath/ath12k/reg.c +59 -26

103 lines not on this page · raw message

drivers/net/wireless/ath/ath12k/reg.h +1 -0
index 8af8e9ba462e..0aeba06182c5 100644
@@ -113,6 +113,7 @@ int ath12k_reg_handle_chan_list(struct ath12k_base *ab,
 				struct ath12k_reg_info *reg_info,
 				enum wmi_vdev_type vdev_type,
 				enum ieee80211_ap_reg_power power_type);
+void ath12k_regd_update_chan_list_work(struct work_struct *work);
 enum wmi_reg_6g_ap_type
 ath12k_reg_ap_pwr_convert(enum ieee80211_ap_reg_power power_type);
 enum ath12k_reg_status ath12k_reg_validate_reg_info(struct ath12k_base *ab,
drivers/net/wireless/ath/ath12k/wmi.h +1 -0
index c640ffa180c8..117150220b99 100644
@@ -3948,6 +3948,7 @@ struct wmi_stop_scan_cmd {
 } __packed;
 
 struct ath12k_wmi_scan_chan_list_arg {
+	struct list_head list;
 	u32 pdev_id;
 	u16 nallchans;
 	struct ath12k_wmi_channel_arg channel[];
Signature · 1 line
2.39.5
author maintainer
#165 lore raw

PATCH 159/627 wifi: ath12k: Fix double budget decrement while reaping monitor ring

In reply to Greg Kroah-Hartman

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

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

From: P Praneesh <[email protected]>

[ Upstream commit 54c350055b1da2767f18a49c11e4fcc42cf33ff8 ]

Currently, the budget for monitor ring is reduced during each ring entry reaping and again when the end reason is HAL_MON_END_OF_PPDU, leading to inefficient budget use. The below mentioned commit intended to decrement the budget only for HAL_MON_END_OF_PPDU but did not remove the other decrement. Fix this by eliminating the budget decrement for each ring entry reaping, ensuring the driver always reaps one full PPDU worth of entries from the monitor destination ring.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Fixes 394a3fa7c538 ("wifi: ath12k: Optimize NAPI budget by adjusting PPDU processing")
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 1 -
 1 file changed, 1 deletion(-)
drivers/net/wireless/ath/ath12k/dp_mon.c +0 -1
index 28cadc4167f7..91f4e3aff74c 100644
@@ -3761,7 +3761,6 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 	ath12k_hal_srng_access_begin(ab, srng);
 
 	while (likely(*budget)) {
-		*budget -= 1;
 		mon_dst_desc = ath12k_hal_srng_dst_peek(ab, srng);
 		if (unlikely(!mon_dst_desc))
 			break;
Signature · 1 line
2.39.5
author maintainer
#166 lore raw

PATCH 160/627 wifi: ath12k: Pass ab pointer directly to ath12k_dp_tx_get_encap_type()

In reply to Greg Kroah-Hartman

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

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

From: Tamizh Chelvam Raja <[email protected]>

[ Upstream commit 05062834350f0bf7ad1abcebc2807220e90220eb ]

In ath12k_dp_tx_get_encap_type(), the arvif parameter is only used to retrieve the ab pointer. In vdev delete sequence the arvif->ar could become NULL and that would trigger kernel panic.
Since the caller ath12k_dp_tx() already has a valid ab pointer, pass it directly to avoid panic and unnecessary dereferencing.

PC points to "ath12k_dp_tx+0x228/0x988 [ath12k]"
LR points to "ath12k_dp_tx+0xc8/0x988 [ath12k]".
The Backtrace obtained is as follows:

ath12k_dp_tx+0x228/0x988 [ath12k]
ath12k_mac_tx_check_max_limit+0x608/0x920 [ath12k]
ieee80211_process_measurement_req+0x320/0x348 [mac80211]
ieee80211_tx_dequeue+0x9ac/0x1518 [mac80211]
ieee80211_tx_dequeue+0xb14/0x1518 [mac80211]
ieee80211_tx_prepare_skb+0x224/0x254 [mac80211]
ieee80211_xmit+0xec/0x100 [mac80211]
__ieee80211_subif_start_xmit+0xc50/0xf40 [mac80211]
ieee80211_subif_start_xmit+0x2e8/0x308 [mac80211]
netdev_start_xmit+0x150/0x18c
dev_hard_start_xmit+0x74/0xc0

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Fixes e93bbd65547e ("wifi: ath12k: fix packets are sent in native wifi mode while we set raw mode")
---
 drivers/net/wireless/ath/ath12k/dp_tx.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/net/wireless/ath/ath12k/dp_tx.c +2 -3
index b6816b6c2c04..075912eacfaa 100644
@@ -13,10 +13,9 @@
 #include "mac.h"
 
 static enum hal_tcl_encap_type
-ath12k_dp_tx_get_encap_type(struct ath12k_link_vif *arvif, struct sk_buff *skb)
+ath12k_dp_tx_get_encap_type(struct ath12k_base *ab, struct sk_buff *skb)
 {
 	struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb);
-	struct ath12k_base *ab = arvif->ar->ab;
 
 	if (test_bit(ATH12K_FLAG_RAW_MODE, &ab->dev_flags))
 		return HAL_TCL_ENCAP_TYPE_RAW;
@@ -305,7 +304,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_link_vif *arvif,
 			u32_encode_bits(mcbc_gsn, HTT_TCL_META_DATA_GLOBAL_SEQ_NUM);
 	}
 
-	ti.encap_type = ath12k_dp_tx_get_encap_type(arvif, skb);
+	ti.encap_type = ath12k_dp_tx_get_encap_type(ab, skb);
 	ti.addr_search_flags = arvif->hal_addr_search_flags;
 	ti.search_type = arvif->search_type;
 	ti.type = HAL_TCL_DESC_TYPE_BUFFER;
Signature · 1 line
2.39.5
author maintainer
#167 lore raw

PATCH 161/627 caif: reduce stack size, again

In reply to Greg Kroah-Hartman

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

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

From: Arnd Bergmann <[email protected]>

[ Upstream commit b630c781bcf6ff87657146661816d0d30a902139 ]

I tried to fix the stack usage in this function a couple of years ago, but there is still a problem with the latest gcc versions in some configurations:

net/caif/cfctrl.c:553:1: error: the frame size of 1296 bytes is larger than 1280 bytes [-Werror=frame-larger-than=]

Reduce this once again, with a separate cfctrl_link_setup() function that holds the bulk of all the local variables. It also turns out that the param[] array that takes up a large portion of the stack is write-only and can be left out here.

Fixes ce6289661b14 ("caif: reduce stack size with KASAN")
---
 net/caif/cfctrl.c | 294 +++++++++++++++++++++++-----------------------
 1 file changed, 144 insertions(+), 150 deletions(-)
net/caif/cfctrl.c +144 -150
index 20139fa1be1f..06b604cf9d58 100644
@@ -351,17 +351,154 @@ int cfctrl_cancel_req(struct cflayer *layr, struct cflayer *adap_layer)
 	return found;
 }
 
+static int cfctrl_link_setup(struct cfctrl *cfctrl, struct cfpkt *pkt, u8 cmdrsp)
+{
+	u8 len;
+	u8 linkid = 0;
+	enum cfctrl_srv serv;
+	enum cfctrl_srv servtype;
+	u8 endpoint;
+	u8 physlinkid;
+	u8 prio;
+	u8 tmp;
+	u8 *cp;
+	int i;
+	struct cfctrl_link_param linkparam;
+	struct cfctrl_request_info rsp, *req;
+
+	memset(&linkparam, 0, sizeof(linkparam));
+
+	tmp = cfpkt_extr_head_u8(pkt);
+
+	serv = tmp & CFCTRL_SRV_MASK;
+	linkparam.linktype = serv;
+
+	servtype = tmp >> 4;
+	linkparam.chtype = servtype;
+
+	tmp = cfpkt_extr_head_u8(pkt);
+	physlinkid = tmp & 0x07;
+	prio = tmp >> 3;
+
+	linkparam.priority = prio;
+	linkparam.phyid = physlinkid;
+	endpoint = cfpkt_extr_head_u8(pkt);
+	linkparam.endpoint = endpoint & 0x03;
+
+	switch (serv) {
+	case CFCTRL_SRV_VEI:
+	case CFCTRL_SRV_DBG:
+		if (CFCTRL_ERR_BIT & cmdrsp)
+			break;
+		/* Link ID */
+		linkid = cfpkt_extr_head_u8(pkt);
+		break;
+	case CFCTRL_SRV_VIDEO:
+		tmp = cfpkt_extr_head_u8(pkt);
+		linkparam.u.video.connid = tmp;
+		if (CFCTRL_ERR_BIT & cmdrsp)
+			break;
+		/* Link ID */
+		linkid = cfpkt_extr_head_u8(pkt);
+		break;
+
+	case CFCTRL_SRV_DATAGRAM:
+		linkparam.u.datagram.connid = cfpkt_extr_head_u32(pkt);
+		if (CFCTRL_ERR_BIT & cmdrsp)
+			break;
+		/* Link ID */
+		linkid = cfpkt_extr_head_u8(pkt);
+		break;
+	case CFCTRL_SRV_RFM:
+		/* Construct a frame, convert
+		 * DatagramConnectionID
+		 * to network format long and copy it out...
+		 */
+		linkparam.u.rfm.connid = cfpkt_extr_head_u32(pkt);
+		cp = (u8 *) linkparam.u.rfm.volume;
+		for (tmp = cfpkt_extr_head_u8(pkt);
+		     cfpkt_more(pkt) && tmp != '\0';
+		     tmp = cfpkt_extr_head_u8(pkt))
+			*cp++ = tmp;
+		*cp = '\0';
+
+		if (CFCTRL_ERR_BIT & cmdrsp)
+			break;
+		/* Link ID */
+		linkid = cfpkt_extr_head_u8(pkt);
+
+		break;
+	case CFCTRL_SRV_UTIL:
+		/* Construct a frame, convert
+		 * DatagramConnectionID
+		 * to network format long and copy it out...
+		 */
+		/* Fifosize KB */
+		linkparam.u.utility.fifosize_kb = cfpkt_extr_head_u16(pkt);
+		/* Fifosize bufs */
+		linkparam.u.utility.fifosize_bufs = cfpkt_extr_head_u16(pkt);
+		/* name */
+		cp = (u8 *) linkparam.u.utility.name;
+		caif_assert(sizeof(linkparam.u.utility.name)
+			     >= UTILITY_NAME_LENGTH);
+		for (i = 0; i < UTILITY_NAME_LENGTH && cfpkt_more(pkt); i++) {
+			tmp = cfpkt_extr_head_u8(pkt);
+			*cp++ = tmp;
+		}
+		/* Length */
+		len = cfpkt_extr_head_u8(pkt);
+		linkparam.u.utility.paramlen = len;
+		/* Param Data */
+		cp = linkparam.u.utility.params;
+		while (cfpkt_more(pkt) && len--) {
+			tmp = cfpkt_extr_head_u8(pkt);
+			*cp++ = tmp;
+		}
+		if (CFCTRL_ERR_BIT & cmdrsp)
+			break;
+		/* Link ID */
+		linkid = cfpkt_extr_head_u8(pkt);
+		/* Length */
+		len = cfpkt_extr_head_u8(pkt);
+		/* Param Data */
+		cfpkt_extr_head(pkt, NULL, len);
+		break;
+	default:
+		pr_warn("Request setup, invalid type (%d)\n", serv);
+		return -1;
+	}
+
+	rsp.cmd = CFCTRL_CMD_LINK_SETUP;
+	rsp.param = linkparam;
+	spin_lock_bh(&cfctrl->info_list_lock);
+	req = cfctrl_remove_req(cfctrl, &rsp);
+
+	if (CFCTRL_ERR_BIT == (CFCTRL_ERR_BIT & cmdrsp) ||
+		cfpkt_erroneous(pkt)) {
+		pr_err("Invalid O/E bit or parse error "
+				"on CAIF control channel\n");
+		cfctrl->res.reject_rsp(cfctrl->serv.layer.up, 0,
+				       req ? req->client_layer : NULL);
+	} else {
+		cfctrl->res.linksetup_rsp(cfctrl->serv.layer.up, linkid,
+					  serv, physlinkid,
+					  req ?  req->client_layer : NULL);
+	}
+
+	kfree(req);
+
+	spin_unlock_bh(&cfctrl->info_list_lock);
+
+	return 0;
+}
+
 static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt)
 {
 	u8 cmdrsp;
 	u8 cmd;
-	int ret = -1;
-	u8 len;
-	u8 param[255];
+	int ret = 0;
 	u8 linkid = 0;
 	struct cfctrl *cfctrl = container_obj(layer);
-	struct cfctrl_request_info rsp, *req;
-
 
 	cmdrsp = cfpkt_extr_head_u8(pkt);
 	cmd = cmdrsp & CFCTRL_CMD_MASK;
@@ -374,150 +511,7 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt)
 
 	switch (cmd) {
 	case CFCTRL_CMD_LINK_SETUP:
-		{
-			enum cfctrl_srv serv;
-			enum cfctrl_srv servtype;
-			u8 endpoint;
-			u8 physlinkid;
-			u8 prio;
-			u8 tmp;
-			u8 *cp;
-			int i;
-			struct cfctrl_link_param linkparam;
-			memset(&linkparam, 0, sizeof(linkparam));
-
-			tmp = cfpkt_extr_head_u8(pkt);
-
-			serv = tmp & CFCTRL_SRV_MASK;
-			linkparam.linktype = serv;
-
-			servtype = tmp >> 4;
-			linkparam.chtype = servtype;
-
-			tmp = cfpkt_extr_head_u8(pkt);
-			physlinkid = tmp & 0x07;
-			prio = tmp >> 3;
-
-			linkparam.priority = prio;
-			linkparam.phyid = physlinkid;
-			endpoint = cfpkt_extr_head_u8(pkt);
-			linkparam.endpoint = endpoint & 0x03;
-
-			switch (serv) {
-			case CFCTRL_SRV_VEI:
-			case CFCTRL_SRV_DBG:
-				if (CFCTRL_ERR_BIT & cmdrsp)
-					break;
-				/* Link ID */
-				linkid = cfpkt_extr_head_u8(pkt);
-				break;
-			case CFCTRL_SRV_VIDEO:
-				tmp = cfpkt_extr_head_u8(pkt);
-				linkparam.u.video.connid = tmp;
-				if (CFCTRL_ERR_BIT & cmdrsp)
-					break;
-				/* Link ID */
-				linkid = cfpkt_extr_head_u8(pkt);
-				break;
-
-			case CFCTRL_SRV_DATAGRAM:
-				linkparam.u.datagram.connid =
-				    cfpkt_extr_head_u32(pkt);
-				if (CFCTRL_ERR_BIT & cmdrsp)
-					break;
-				/* Link ID */
-				linkid = cfpkt_extr_head_u8(pkt);
-				break;
-			case CFCTRL_SRV_RFM:
-				/* Construct a frame, convert
-				 * DatagramConnectionID
-				 * to network format long and copy it out...
-				 */
-				linkparam.u.rfm.connid =
-				    cfpkt_extr_head_u32(pkt);
-				cp = (u8 *) linkparam.u.rfm.volume;
-				for (tmp = cfpkt_extr_head_u8(pkt);
-				     cfpkt_more(pkt) && tmp != '\0';
-				     tmp = cfpkt_extr_head_u8(pkt))
-					*cp++ = tmp;
-				*cp = '\0';
-
-				if (CFCTRL_ERR_BIT & cmdrsp)
-					break;
-				/* Link ID */
-				linkid = cfpkt_extr_head_u8(pkt);
-
-				break;
-			case CFCTRL_SRV_UTIL:
-				/* Construct a frame, convert
-				 * DatagramConnectionID
-				 * to network format long and copy it out...
-				 */
-				/* Fifosize KB */
-				linkparam.u.utility.fifosize_kb =
-				    cfpkt_extr_head_u16(pkt);
-				/* Fifosize bufs */
-				linkparam.u.utility.fifosize_bufs =
-				    cfpkt_extr_head_u16(pkt);
-				/* name */
-				cp = (u8 *) linkparam.u.utility.name;
-				caif_assert(sizeof(linkparam.u.utility.name)
-					     >= UTILITY_NAME_LENGTH);
-				for (i = 0;
-				     i < UTILITY_NAME_LENGTH
-				     && cfpkt_more(pkt); i++) {
-					tmp = cfpkt_extr_head_u8(pkt);
-					*cp++ = tmp;
-				}
-				/* Length */
-				len = cfpkt_extr_head_u8(pkt);
-				linkparam.u.utility.paramlen = len;
-				/* Param Data */
-				cp = linkparam.u.utility.params;
-				while (cfpkt_more(pkt) && len--) {
-					tmp = cfpkt_extr_head_u8(pkt);
-					*cp++ = tmp;
-				}
-				if (CFCTRL_ERR_BIT & cmdrsp)
-					break;
-				/* Link ID */
-				linkid = cfpkt_extr_head_u8(pkt);
-				/* Length */
-				len = cfpkt_extr_head_u8(pkt);
-				/* Param Data */
-				cfpkt_extr_head(pkt, &param, len);
-				break;
-			default:
-				pr_warn("Request setup, invalid type (%d)\n",
-					serv);
-				goto error;
-			}
-
-			rsp.cmd = cmd;
-			rsp.param = linkparam;
-			spin_lock_bh(&cfctrl->info_list_lock);
-			req = cfctrl_remove_req(cfctrl, &rsp);
-
-			if (CFCTRL_ERR_BIT == (CFCTRL_ERR_BIT & cmdrsp) ||
-				cfpkt_erroneous(pkt)) {
-				pr_err("Invalid O/E bit or parse error "
-						"on CAIF control channel\n");
-				cfctrl->res.reject_rsp(cfctrl->serv.layer.up,
-						       0,
-						       req ? req->client_layer
-						       : NULL);
-			} else {
-				cfctrl->res.linksetup_rsp(cfctrl->serv.
-							  layer.up, linkid,
-							  serv, physlinkid,
-							  req ? req->
-							  client_layer : NULL);
-			}
-
-			kfree(req);
-
-			spin_unlock_bh(&cfctrl->info_list_lock);
-		}
+		ret = cfctrl_link_setup(cfctrl, pkt, cmdrsp);
 		break;
 	case CFCTRL_CMD_LINK_DESTROY:
 		linkid = cfpkt_extr_head_u8(pkt);
@@ -544,9 +538,9 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt)
 		break;
 	default:
 		pr_err("Unrecognized Control Frame\n");
+		ret = -1;
 		goto error;
 	}
-	ret = 0;
 error:
 	cfpkt_destroy(pkt);
 	return ret;
Signature · 1 line
2.39.5
author maintainer
#168 lore raw

PATCH 162/627 net: annotate races around sk->sk_uid

In reply to Greg Kroah-Hartman

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit e84a4927a404f369c842c19de93b216627fcc690 ]

sk->sk_uid can be read while another thread changes its value in sockfs_setattr().

Add sk_uid(const struct sock *sk) helper to factorize the needed READ_ONCE() annotations, and add corresponding WRITE_ONCE() where needed.

Fixes 86741ec25462 ("net: core: Add a UID field to struct sock.")
Cc Lorenzo Colitti <[email protected]>
---
 include/net/route.h              |  4 ++--
 include/net/sock.h               | 12 ++++++++++--
 net/ipv4/inet_connection_sock.c  |  4 ++--
 net/ipv4/ping.c                  |  2 +-
 net/ipv4/raw.c                   |  2 +-
 net/ipv4/route.c                 |  3 ++-
 net/ipv4/syncookies.c            |  3 ++-
 net/ipv4/udp.c                   |  3 ++-
 net/ipv6/af_inet6.c              |  2 +-
 net/ipv6/datagram.c              |  2 +-
 net/ipv6/inet6_connection_sock.c |  4 ++--
 net/ipv6/ping.c                  |  2 +-
 net/ipv6/raw.c                   |  2 +-
 net/ipv6/route.c                 |  4 ++--
 net/ipv6/syncookies.c            |  2 +-
 net/ipv6/tcp_ipv6.c              |  2 +-
 net/ipv6/udp.c                   |  5 +++--
 net/l2tp/l2tp_ip6.c              |  2 +-
 net/mptcp/protocol.c             |  2 +-
 net/socket.c                     |  8 +++++---
 20 files changed, 42 insertions(+), 28 deletions(-)
include/net/route.h +2 -2
index 8e39aa822cf9..3d3d6048ffca 100644
@@ -153,7 +153,7 @@ static inline void inet_sk_init_flowi4(const struct inet_sock *inet,
 			   ip_sock_rt_tos(sk), ip_sock_rt_scope(sk),
 			   sk->sk_protocol, inet_sk_flowi_flags(sk), daddr,
 			   inet->inet_saddr, inet->inet_dport,
-			   inet->inet_sport, sk->sk_uid);
+			   inet->inet_sport, sk_uid(sk));
 	security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 }
 
@@ -331,7 +331,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
 
 	flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk),
 			   ip_sock_rt_scope(sk), protocol, flow_flags, dst,
-			   src, dport, sport, sk->sk_uid);
+			   src, dport, sport, sk_uid(sk));
 }
 
 static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst,
include/net/sock.h +10 -2
index 4c37015b7cf7..e3ab20345685 100644
@@ -2076,6 +2076,7 @@ static inline void sock_orphan(struct sock *sk)
 	sock_set_flag(sk, SOCK_DEAD);
 	sk_set_socket(sk, NULL);
 	sk->sk_wq  = NULL;
+	/* Note: sk_uid is unchanged. */
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
@@ -2086,18 +2087,25 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 	rcu_assign_pointer(sk->sk_wq, &parent->wq);
 	parent->sk = sk;
 	sk_set_socket(sk, parent);
-	sk->sk_uid = SOCK_INODE(parent)->i_uid;
+	WRITE_ONCE(sk->sk_uid, SOCK_INODE(parent)->i_uid);
 	security_sock_graft(sk, parent);
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
 kuid_t sock_i_uid(struct sock *sk);
+
+static inline kuid_t sk_uid(const struct sock *sk)
+{
+	/* Paired with WRITE_ONCE() in sockfs_setattr() */
+	return READ_ONCE(sk->sk_uid);
+}
+
 unsigned long __sock_i_ino(struct sock *sk);
 unsigned long sock_i_ino(struct sock *sk);
 
 static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
 {
-	return sk ? sk->sk_uid : make_kuid(net->user_ns, 0);
+	return sk ? sk_uid(sk) : make_kuid(net->user_ns, 0);
 }
 
 static inline u32 net_tx_rndhash(void)
net/ipv4/inet_connection_sock.c +2 -2
index 6906bedad19a..46750c96d08e 100644
@@ -812,7 +812,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, ireq->ir_rmt_port,
-			   htons(ireq->ir_num), sk->sk_uid);
+			   htons(ireq->ir_num), sk_uid(sk));
 	security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -849,7 +849,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, ireq->ir_rmt_port,
-			   htons(ireq->ir_num), sk->sk_uid);
+			   htons(ireq->ir_num), sk_uid(sk));
 	security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
net/ipv4/ping.c +1 -1
index c14baa6589c7..4eacaf00e2e9 100644
@@ -781,7 +781,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark,
 			   ipc.tos & INET_DSCP_MASK, scope,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk), faddr,
-			   saddr, 0, 0, sk->sk_uid);
+			   saddr, 0, 0, sk_uid(sk));
 
 	fl4.fl4_icmp_type = user_icmph.type;
 	fl4.fl4_icmp_code = user_icmph.code;
net/ipv4/raw.c +1 -1
index 6aace4d55733..32f942d0f944 100644
@@ -610,7 +610,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			   hdrincl ? ipc.protocol : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) |
 			    (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
-			   daddr, saddr, 0, 0, sk->sk_uid);
+			   daddr, saddr, 0, 0, sk_uid(sk));
 
 	fl4.fl4_icmp_type = 0;
 	fl4.fl4_icmp_code = 0;
net/ipv4/route.c +2 -1
index fccb05fb3a79..64ac20c27f1b 100644
@@ -556,7 +556,8 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
 			   inet_test_bit(HDRINCL, sk) ?
 				IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk),
-			   daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
+			   daddr, inet->inet_saddr, 0, 0,
+			   sk_uid(sk));
 	rcu_read_unlock();
 }
 
net/ipv4/syncookies.c +2 -1
index 5459a78b9809..eb0819463fae 100644
@@ -454,7 +454,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 			   ip_sock_rt_tos(sk), ip_sock_rt_scope(sk),
 			   IPPROTO_TCP, inet_sk_flowi_flags(sk),
 			   opt->srr ? opt->faddr : ireq->ir_rmt_addr,
-			   ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
+			   ireq->ir_loc_addr, th->source, th->dest,
+			   sk_uid(sk));
 	security_req_classify_flow(req, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt)) {
net/ipv4/udp.c +2 -1
index dde52b8050b8..f94bb222aa2d 100644
@@ -1445,7 +1445,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark,
 				   ipc.tos & INET_DSCP_MASK, scope,
 				   sk->sk_protocol, flow_flags, faddr, saddr,
-				   dport, inet->inet_sport, sk->sk_uid);
+				   dport, inet->inet_sport,
+				   sk_uid(sk));
 
 		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 		rt = ip_route_output_flow(net, fl4, sk);
net/ipv6/af_inet6.c +1 -1
index acaff1296783..1992621e3f3f 100644
@@ -842,7 +842,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.flowi6_mark = sk->sk_mark;
 		fl6.fl6_dport = inet->inet_dport;
 		fl6.fl6_sport = inet->inet_sport;
-		fl6.flowi6_uid = sk->sk_uid;
+		fl6.flowi6_uid = sk_uid(sk);
 		security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 		rcu_read_lock();
net/ipv6/datagram.c +1 -1
index fff78496803d..83f5aa5e133a 100644
@@ -53,7 +53,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6,
 	fl6->fl6_dport = inet->inet_dport;
 	fl6->fl6_sport = inet->inet_sport;
 	fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
-	fl6->flowi6_uid = sk->sk_uid;
+	fl6->flowi6_uid = sk_uid(sk);
 
 	if (!oif)
 		oif = np->sticky_pktinfo.ipi6_ifindex;
net/ipv6/inet6_connection_sock.c +2 -2
index 8f500eaf33cf..333e43434dd7 100644
@@ -45,7 +45,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 	fl6->flowi6_mark = ireq->ir_mark;
 	fl6->fl6_dport = ireq->ir_rmt_port;
 	fl6->fl6_sport = htons(ireq->ir_num);
-	fl6->flowi6_uid = sk->sk_uid;
+	fl6->flowi6_uid = sk_uid(sk);
 	security_req_classify_flow(req, flowi6_to_flowi_common(fl6));
 
 	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
@@ -79,7 +79,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	fl6->flowi6_mark = sk->sk_mark;
 	fl6->fl6_sport = inet->inet_sport;
 	fl6->fl6_dport = inet->inet_dport;
-	fl6->flowi6_uid = sk->sk_uid;
+	fl6->flowi6_uid = sk_uid(sk);
 	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
 
 	rcu_read_lock();
net/ipv6/ping.c +1 -1
index 84d90dd8b3f0..82b0492923d4 100644
@@ -142,7 +142,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.saddr = np->saddr;
 	fl6.daddr = *daddr;
 	fl6.flowi6_mark = ipc6.sockc.mark;
-	fl6.flowi6_uid = sk->sk_uid;
+	fl6.flowi6_uid = sk_uid(sk);
 	fl6.fl6_icmp_type = user_icmph.icmp6_type;
 	fl6.fl6_icmp_code = user_icmph.icmp6_code;
 	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
net/ipv6/raw.c +1 -1
index fda640ebd53f..4c3f8245c40f 100644
@@ -777,7 +777,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	memset(&fl6, 0, sizeof(fl6));
 
 	fl6.flowi6_mark = ipc6.sockc.mark;
-	fl6.flowi6_uid = sk->sk_uid;
+	fl6.flowi6_uid = sk_uid(sk);
 
 	if (sin6) {
 		if (addr_len < SIN6_LEN_RFC2133)
net/ipv6/route.c +2 -2
index 79c8f1acf8a3..7b9e49be7164 100644
@@ -3010,7 +3010,7 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 		oif = l3mdev_master_ifindex(skb->dev);
 
 	ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark),
-			sk->sk_uid);
+			sk_uid(sk));
 
 	dst = __sk_dst_get(sk);
 	if (!dst || !dst->obsolete ||
@@ -3232,7 +3232,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif)
 void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk)
 {
 	ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if,
-		     READ_ONCE(sk->sk_mark), sk->sk_uid);
+		     READ_ONCE(sk->sk_mark), sk_uid(sk));
 }
 EXPORT_SYMBOL_GPL(ip6_sk_redirect);
 
net/ipv6/syncookies.c +1 -1
index 9d83eadd308b..f0ee1a909771 100644
@@ -236,7 +236,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		fl6.flowi6_mark = ireq->ir_mark;
 		fl6.fl6_dport = ireq->ir_rmt_port;
 		fl6.fl6_sport = inet_sk(sk)->inet_sport;
-		fl6.flowi6_uid = sk->sk_uid;
+		fl6.flowi6_uid = sk_uid(sk);
 		security_req_classify_flow(req, flowi6_to_flowi_common(&fl6));
 
 		dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p);
net/ipv6/tcp_ipv6.c +1 -1
index e8e68a142649..f61b0396ef6b 100644
@@ -269,7 +269,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_sport = inet->inet_sport;
 	if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !fl6.fl6_sport)
 		fl6.flowi6_flags = FLOWI_FLAG_ANY_SPORT;
-	fl6.flowi6_uid = sk->sk_uid;
+	fl6.flowi6_uid = sk_uid(sk);
 
 	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
 	final_p = fl6_update_dst(&fl6, opt, &final);
net/ipv6/udp.c +3 -2
index 7317f8e053f1..ebb95d8bc681 100644
@@ -750,7 +750,8 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (type == NDISC_REDIRECT) {
 		if (tunnel) {
 			ip6_redirect(skb, sock_net(sk), inet6_iif(skb),
-				     READ_ONCE(sk->sk_mark), sk->sk_uid);
+				     READ_ONCE(sk->sk_mark),
+				     sk_uid(sk));
 		} else {
 			ip6_sk_redirect(skb, sk);
 		}
@@ -1620,7 +1621,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (!fl6->flowi6_oif)
 		fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
 
-	fl6->flowi6_uid = sk->sk_uid;
+	fl6->flowi6_uid = sk_uid(sk);
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
net/l2tp/l2tp_ip6.c +1 -1
index b98d13584c81..ea232f338dcb 100644
@@ -545,7 +545,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	memset(&fl6, 0, sizeof(fl6));
 
 	fl6.flowi6_mark = READ_ONCE(sk->sk_mark);
-	fl6.flowi6_uid = sk->sk_uid;
+	fl6.flowi6_uid = sk_uid(sk);
 
 	ipcm6_init_sk(&ipc6, sk);
 
net/mptcp/protocol.c +1 -1
index 6a817a13b154..76cb699885b3 100644
@@ -3537,7 +3537,7 @@ void mptcp_sock_graft(struct sock *sk, struct socket *parent)
 	write_lock_bh(&sk->sk_callback_lock);
 	rcu_assign_pointer(sk->sk_wq, &parent->wq);
 	sk_set_socket(sk, parent);
-	sk->sk_uid = SOCK_INODE(parent)->i_uid;
+	WRITE_ONCE(sk->sk_uid, SOCK_INODE(parent)->i_uid);
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
net/socket.c +5 -3
index 9a0e720f0859..c706601a4c16 100644
@@ -592,10 +592,12 @@ static int sockfs_setattr(struct mnt_idmap *idmap,
 	if (!err && (iattr->ia_valid & ATTR_UID)) {
 		struct socket *sock = SOCKET_I(d_inode(dentry));
 
-		if (sock->sk)
-			sock->sk->sk_uid = iattr->ia_uid;
-		else
+		if (sock->sk) {
+			/* Paired with READ_ONCE() in sk_uid() */
+			WRITE_ONCE(sock->sk->sk_uid, iattr->ia_uid);
+		} else {
 			err = -ENOENT;
+		}
 	}
 
 	return err;
Signature · 1 line
2.39.5
author maintainer
#169 lore raw

PATCH 163/627 wifi: rtw89: avoid NULL dereference when RX problematic packet on unsupported 6 GHz band

In reply to Greg Kroah-Hartman

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

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

From: Zong-Zhe Yang <[email protected]>

[ Upstream commit 7e04f01bb94fe61c73cc59f0495c3b6c16a83231 ]

With a quite rare chance, RX report might be problematic to make SW think a packet is received on 6 GHz band even if the chip does not support 6 GHz band actually. Since SW won't initialize stuffs for unsupported bands, NULL dereference will happen then in the sequence, rtw89_vif_rx_stats_iter() -> rtw89_core_cancel_6ghz_probe_tx(). So, add a check to avoid it.

The following is a crash log for this case.

 BUG: kernel NULL pointer dereference, address: 0000000000000032
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: 0000 [#1] PREEMPT SMP NOPTI
 CPU: 1 PID: 1907 Comm: irq/131-rtw89_p Tainted: G     U             6.6.56-05896-g89f5fb0eb30b #1 (HASH:1400 4)
 Hardware name: Google Telith/Telith, BIOS Google_Telith.15217.747.0 11/12/2024
 RIP: 0010:rtw89_vif_rx_stats_iter+0xd2/0x310 [rtw89_core]
 Code: 4c 89 7d c8 48 89 55 c0 49 8d 44 24 02 48 89 45 b8 45 31 ff eb 11
 41 c6 45 3a 01 41 b7 01 4d 8b 6d 00 4d 39 f5 74 42 8b 43 10 <41> 33 45
 32 0f b7 4b 14 66 41 33 4d 36 0f b7 c9 09 c1 74 d8 4d 85
 RSP: 0018:ffff9f3080138ca0 EFLAGS: 00010246
 RAX: 00000000b8bf5770 RBX: ffff91b5e8c639c0 RCX: 0000000000000011
 RDX: ffff91b582de1be8 RSI: 0000000000000000 RDI: ffff91b5e8c639e6
 RBP: ffff9f3080138d00 R08: 0000000000000000 R09: 0000000000000000
 R10: ffff91b59de70000 R11: ffffffffc069be50 R12: ffff91b5e8c639e4
 R13: 0000000000000000 R14: ffff91b5828020b8 R15: 0000000000000000
 FS:  0000000000000000(0000) GS:ffff91b8efa40000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000032 CR3: 00000002bf838000 CR4: 0000000000750ee0
 PKRU: 55555554
 Call Trace:
  <IRQ>
  ? __die_body+0x68/0xb0
  ? page_fault_oops+0x379/0x3e0
  ? exc_page_fault+0x4f/0xa0
  ? asm_exc_page_fault+0x22/0x30
  ? __pfx_rtw89_vif_rx_stats_iter+0x10/0x10 [rtw89_core (HASH:1400 5)]
  ? rtw89_vif_rx_stats_iter+0xd2/0x310 [rtw89_core (HASH:1400 5)]
  __iterate_interfaces+0x59/0x110 [mac80211 (HASH:1400 6)]
  ? __pfx_rtw89_vif_rx_stats_iter+0x10/0x10 [rtw89_core (HASH:1400 5)]
  ? __pfx_rtw89_vif_rx_stats_iter+0x10/0x10 [rtw89_core (HASH:1400 5)]
  ieee80211_iterate_active_interfaces_atomic+0x36/0x50 [mac80211 (HASH:1400 6)]
  rtw89_core_rx_to_mac80211+0xfd/0x1b0 [rtw89_core (HASH:1400 5)]
  rtw89_core_rx+0x43a/0x980 [rtw89_core (HASH:1400 5)]
Fixes c6aa9a9c4725 ("wifi: rtw89: add RNR support for 6 GHz scan")
---
 drivers/net/wireless/realtek/rtw89/core.c | 5 +++++
 1 file changed, 5 insertions(+)
drivers/net/wireless/realtek/rtw89/core.c +5 -0
index 3604a8e15df0..c886dd2a73b4 100644
@@ -2158,6 +2158,11 @@ static void rtw89_core_cancel_6ghz_probe_tx(struct rtw89_dev *rtwdev,
 	if (rx_status->band != NL80211_BAND_6GHZ)
 		return;
 
+	if (unlikely(!(rtwdev->chip->support_bands & BIT(NL80211_BAND_6GHZ)))) {
+		rtw89_debug(rtwdev, RTW89_DBG_UNEXP, "invalid rx on unsupported 6 GHz\n");
+		return;
+	}
+
 	ssid_ie = cfg80211_find_ie(WLAN_EID_SSID, ies, skb->len);
 
 	list_for_each_entry(info, &pkt_list[NL80211_BAND_6GHZ], list) {
Signature · 1 line
2.39.5
author maintainer
#170 lore raw

PATCH 164/627 wifi: rtl818x: Kill URBs before clearing tx status queue

In reply to Greg Kroah-Hartman

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

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

From: Daniil Dulov <[email protected]>

[ Upstream commit 16d8fd74dbfca0ea58645cd2fca13be10cae3cdd ]

In rtl8187_stop() move the call of usb_kill_anchored_urbs() before clearing b_tx_status.queue. This change prevents callbacks from using already freed skb due to anchor was not killed before freeing such skb.

 BUG: kernel NULL pointer dereference, address: 0000000000000080
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: Oops: 0000 [#1] SMP NOPTI
 CPU: 7 UID: 0 PID: 0 Comm: swapper/7 Not tainted 6.15.0 #8 PREEMPT(voluntary)
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.0.0 02/06/2015
 RIP: 0010:ieee80211_tx_status_irqsafe+0x21/0xc0 [mac80211]
 Call Trace:
  <IRQ>
  rtl8187_tx_cb+0x116/0x150 [rtl8187]
  __usb_hcd_giveback_urb+0x9d/0x120
  usb_giveback_urb_bh+0xbb/0x140
  process_one_work+0x19b/0x3c0
  bh_worker+0x1a7/0x210
  tasklet_action+0x10/0x30
  handle_softirqs+0xf0/0x340
  __irq_exit_rcu+0xcd/0xf0
  common_interrupt+0x85/0xa0
  </IRQ>

Tested on RTL8187BvE device.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes c1db52b9d27e ("rtl8187: Use usb anchor facilities to manage urbs")
---
 drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c +2 -1
index 220ac5bdf279..8a57d6c72335 100644
@@ -1041,10 +1041,11 @@ static void rtl8187_stop(struct ieee80211_hw *dev, bool suspend)
 	rtl818x_iowrite8(priv, &priv->map->CONFIG4, reg | RTL818X_CONFIG4_VCOOFF);
 	rtl818x_iowrite8(priv, &priv->map->EEPROM_CMD, RTL818X_EEPROM_CMD_NORMAL);
 
+	usb_kill_anchored_urbs(&priv->anchored);
+
 	while ((skb = skb_dequeue(&priv->b_tx_status.queue)))
 		dev_kfree_skb_any(skb);
 
-	usb_kill_anchored_urbs(&priv->anchored);
 	mutex_unlock(&priv->conf_mutex);
 
 	if (!priv->is_rtl8187b)
Signature · 1 line
2.39.5
author maintainer
#171 lore raw

PATCH 165/627 drm/amdgpu: fix slab-use-after-free in amdgpu_userq_mgr_fini+0x70c

In reply to Greg Kroah-Hartman

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

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

From: Vitaly Prosyak <[email protected]>

[ Upstream commit 5fb90421fa0fbe0a968274912101fe917bf1c47b ]

The issue was reproduced on NV10 using IGT pci_unplug test.
It is expected that amdgpu_driver_postclose_kms() is called prior to amdgpu_drm_release(). However, the bug is that amdgpu_fpriv was freed in amdgpu_driver_postclose_kms(), and then later accessed in amdgpu_drm_release() via a call to amdgpu_userq_mgr_fini(). As a result, KASAN detected a use-after-free condition, as shown in the log below. The proposed fix is to move the calls to amdgpu_eviction_fence_destroy() and amdgpu_userq_mgr_fini() into amdgpu_driver_postclose_kms(), so they are invoked before amdgpu_fpriv is freed.

This also ensures symmetry with the initialization path in amdgpu_driver_open_kms(), where the following components are initialized:
- amdgpu_userq_mgr_init()
- amdgpu_eviction_fence_init()
- amdgpu_ctx_mgr_init()

Correspondingly, in amdgpu_driver_postclose_kms() we should clean up using:
- amdgpu_userq_mgr_fini()
- amdgpu_eviction_fence_destroy()
- amdgpu_ctx_mgr_fini()

This change eliminates the use-after-free and improves consistency in resource management between open and close paths.

[  +0.094367] ==================================================================
[  +0.000026] BUG: KASAN: slab-use-after-free in amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu]
[  +0.000866] Write of size 8 at addr ffff88811c068c60 by task amd_pci_unplug/1737
[  +0.000026] CPU: 3 UID: 0 PID: 1737 Comm: amd_pci_unplug Not tainted 6.14.0+ #2
[  +0.000008] Hardware name: ASUS System Product Name/ROG STRIX B550-F GAMING (WI-FI), BIOS 1401 12/03/2020
[  +0.000004] Call Trace:
[  +0.000004]  <TASK>
[  +0.000003]  dump_stack_lvl+0x76/0xa0
[  +0.000010]  print_report+0xce/0x600
[  +0.000009]  ? amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu]
[  +0.000790]  ? srso_return_thunk+0x5/0x5f
[  +0.000007]  ? kasan_complete_mode_report_info+0x76/0x200
[  +0.000008]  ? amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu]
[  +0.000684]  kasan_report+0xbe/0x110
[  +0.000007]  ? amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu]
[  +0.000601]  __asan_report_store8_noabort+0x17/0x30
[  +0.000007]  amdgpu_userq_mgr_fini+0x70c/0x730 [amdgpu]
[  +0.000801]  ? __pfx_amdgpu_userq_mgr_fini+0x10/0x10 [amdgpu]
[  +0.000819]  ? srso_return_thunk+0x5/0x5f
[  +0.000008]  amdgpu_drm_release+0xa3/0xe0 [amdgpu]
[  +0.000604]  __fput+0x354/0xa90
[  +0.000010]  __fput_sync+0x59/0x80
[  +0.000005]  __x64_sys_close+0x7d/0xe0
[  +0.000006]  x64_sys_call+0x2505/0x26f0
[  +0.000006]  do_syscall_64+0x7c/0x170
[  +0.000004]  ? kasan_record_aux_stack+0xae/0xd0
[  +0.000005]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? kmem_cache_free+0x398/0x580
[  +0.000006]  ? __fput+0x543/0xa90
[  +0.000006]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? __fput+0x543/0xa90
[  +0.000004]  ? __kasan_check_read+0x11/0x20
[  +0.000007]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? __kasan_check_read+0x11/0x20
[  +0.000003]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? fpregs_assert_state_consistent+0x21/0xb0
[  +0.000006]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? syscall_exit_to_user_mode+0x4e/0x240
[  +0.000005]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? do_syscall_64+0x88/0x170
[  +0.000003]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? do_syscall_64+0x88/0x170
[  +0.000004]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? irqentry_exit+0x43/0x50
[  +0.000004]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? exc_page_fault+0x7c/0x110
[  +0.000006]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  +0.000005] RIP: 0033:0x7ffff7b14f67
[  +0.000005] Code: ff e8 0d 16 02 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 41 c3 48 83 ec 18 89 7c 24 0c e8 73 ba f7 ff
[  +0.000004] RSP: 002b:00007fffffffe358 EFLAGS: 00000246 ORIG_RAX: 0000000000000003
[  +0.000006] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007ffff7b14f67
[  +0.000003] RDX: 0000000000000000 RSI: 00007ffff7f5755a RDI: 0000000000000003
[  +0.000003] RBP: 00007fffffffe380 R08: 0000555555568170 R09: 0000000000000000
[  +0.000003] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fffffffe5c8
[  +0.000003] R13: 00005555555552a9 R14: 0000555555557d48 R15: 00007ffff7ffd040
[  +0.000007]  </TASK>
[  +0.000286] Allocated by task 425 on cpu 11 at 29.751192s:
[  +0.000013]  kasan_save_stack+0x28/0x60
[  +0.000008]  kasan_save_track+0x18/0x70
[  +0.000006]  kasan_save_alloc_info+0x38/0x60
[  +0.000006]  __kasan_kmalloc+0xc1/0xd0
[  +0.000005]  __kmalloc_cache_noprof+0x1bd/0x430
[  +0.000006]  amdgpu_driver_open_kms+0x172/0x760 [amdgpu]
[  +0.000521]  drm_file_alloc+0x569/0x9a0
[  +0.000008]  drm_client_init+0x1b7/0x410
[  +0.000007]  drm_fbdev_client_setup+0x174/0x470
[  +0.000007]  drm_client_setup+0x8a/0xf0
[  +0.000006]  amdgpu_pci_probe+0x50b/0x10d0 [amdgpu]
[  +0.000482]  local_pci_probe+0xe7/0x1b0
[  +0.000008]  pci_device_probe+0x5bf/0x890
[  +0.000005]  really_probe+0x1fd/0x950
[  +0.000007]  __driver_probe_device+0x307/0x410
[  +0.000005]  driver_probe_device+0x4e/0x150
[  +0.000006]  __driver_attach+0x223/0x510
[  +0.000005]  bus_for_each_dev+0x102/0x1a0
[  +0.000006]  driver_attach+0x3d/0x60
[  +0.000005]  bus_add_driver+0x309/0x650
[  +0.000005]  driver_register+0x13d/0x490
[  +0.000006]  __pci_register_driver+0x1ee/0x2b0
[  +0.000006]  xfrm_ealg_get_byidx+0x43/0x50 [xfrm_algo]
[  +0.000008]  do_one_initcall+0x9c/0x3e0
[  +0.000007]  do_init_module+0x29e/0x7f0
[  +0.000006]  load_module+0x5c75/0x7c80
[  +0.000006]  init_module_from_file+0x106/0x180
[  +0.000007]  idempotent_init_module+0x377/0x740
[  +0.000006]  __x64_sys_finit_module+0xd7/0x180
[  +0.000006]  x64_sys_call+0x1f0b/0x26f0
[  +0.000006]  do_syscall_64+0x7c/0x170
[  +0.000005]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  +0.000013] Freed by task 1737 on cpu 9 at 76.455063s:
[  +0.000010]  kasan_save_stack+0x28/0x60
[  +0.000006]  kasan_save_track+0x18/0x70
[  +0.000005]  kasan_save_free_info+0x3b/0x60
[  +0.000006]  __kasan_slab_free+0x54/0x80
[  +0.000005]  kfree+0x127/0x470
[  +0.000006]  amdgpu_driver_postclose_kms+0x455/0x760 [amdgpu]
[  +0.000485]  drm_file_free.part.0+0x5b1/0xba0
[  +0.000007]  drm_file_free+0x13/0x30
[  +0.000006]  drm_client_release+0x1c4/0x2b0
[  +0.000006]  drm_fbdev_ttm_fb_destroy+0xd2/0x120 [drm_ttm_helper]
[  +0.000007]  put_fb_info+0x97/0xe0
[  +0.000006]  unregister_framebuffer+0x197/0x380
[  +0.000005]  drm_fb_helper_unregister_info+0x94/0x100
[  +0.000005]  drm_fbdev_client_unregister+0x3c/0x80
[  +0.000007]  drm_client_dev_unregister+0x144/0x330
[  +0.000006]  drm_dev_unregister+0x49/0x1b0
[  +0.000006]  drm_dev_unplug+0x4c/0xd0
[  +0.000006]  amdgpu_pci_remove+0x58/0x130 [amdgpu]
[  +0.000482]  pci_device_remove+0xae/0x1e0
[  +0.000006]  device_remove+0xc7/0x180
[  +0.000006]  device_release_driver_internal+0x3d4/0x5a0
[  +0.000007]  device_release_driver+0x12/0x20
[  +0.000006]  pci_stop_bus_device+0x104/0x150
[  +0.000006]  pci_stop_and_remove_bus_device_locked+0x1b/0x40
[  +0.000005]  remove_store+0xd7/0xf0
[  +0.000007]  dev_attr_store+0x3f/0x80
[  +0.000006]  sysfs_kf_write+0x125/0x1d0
[  +0.000005]  kernfs_fop_write_iter+0x2ea/0x490
[  +0.000007]  vfs_write+0x90d/0xe70
[  +0.000006]  ksys_write+0x119/0x220
[  +0.000006]  __x64_sys_write+0x72/0xc0
[  +0.000006]  x64_sys_call+0x18ab/0x26f0
[  +0.000005]  do_syscall_64+0x7c/0x170
[  +0.000005]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

[ +0.000013] The buggy address belongs to the object at ffff88811c068000
which belongs to the cache kmalloc-rnd-01-4k of size 4096
[ +0.000016] The buggy address is located 3168 bytes inside of

               freed 4096-byte region [ffff88811c068000, ffff88811c069000)
[  +0.000022] The buggy address belongs to the physical page:
[  +0.000010] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff88811c06e000 pfn:0x11c068
[  +0.000006] head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
[  +0.000006] flags: 0x17ffffc0000040(head|node=0|zone=2|lastcpupid=0x1fffff)
[  +0.000007] page_type: f5(slab)
[  +0.000007] raw: 0017ffffc0000040 ffff88810004c140 dead000000000122 0000000000000000
[  +0.000005] raw: ffff88811c06e000 0000000080040002 00000000f5000000 0000000000000000
[  +0.000006] head: 0017ffffc0000040 ffff88810004c140 dead000000000122 0000000000000000
[  +0.000005] head: ffff88811c06e000 0000000080040002 00000000f5000000 0000000000000000
[  +0.000006] head: 0017ffffc0000003 ffffea0004701a01 ffffffffffffffff 0000000000000000
[  +0.000005] head: 0000000000000008 0000000000000000 00000000ffffffff 0000000000000000
[  +0.000004] page dumped because: kasan: bad access detected
[  +0.000011] Memory state around the buggy address:
[  +0.000009]  ffff88811c068b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000012]  ffff88811c068b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011] >ffff88811c068c00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011]                                                        ^
[  +0.000010]  ffff88811c068c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011]  ffff88811c068d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011] ==================================================================
Cc Alex Deucher <[email protected]>
Cc Christian König <[email protected]>
Cc Lijo Lazar <[email protected]>
Cc Jesse Zhang <[email protected]>
Cc Arvind Yadav <[email protected]>

v2: drop amdgpu_drm_release() and assign drm_release()
as the callback directly.(Alex)

Fixes adba0929736a ("drm/amdgpu: Fix Illegal opcode in command stream Error")
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 16 +---------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c |  3 +++
 2 files changed, 4 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +1 -15
index 4db92e0a60da..501bb82f2a37 100644
@@ -2906,20 +2906,6 @@ static int amdgpu_pmops_runtime_idle(struct device *dev)
 	return ret;
 }
 
-static int amdgpu_drm_release(struct inode *inode, struct file *filp)
-{
-	struct drm_file *file_priv = filp->private_data;
-	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
-
-	if (fpriv) {
-		fpriv->evf_mgr.fd_closing = true;
-		amdgpu_eviction_fence_destroy(&fpriv->evf_mgr);
-		amdgpu_userq_mgr_fini(&fpriv->userq_mgr);
-	}
-
-	return drm_release(inode, filp);
-}
-
 long amdgpu_drm_ioctl(struct file *filp,
 		      unsigned int cmd, unsigned long arg)
 {
@@ -2971,7 +2957,7 @@ static const struct file_operations amdgpu_driver_kms_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
 	.flush = amdgpu_flush,
-	.release = amdgpu_drm_release,
+	.release = drm_release,
 	.unlocked_ioctl = amdgpu_drm_ioctl,
 	.mmap = drm_gem_mmap,
 	.poll = drm_poll,
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +3 -0
index d2ce7d86dbc8..195ed81d39ff 100644
@@ -1501,6 +1501,9 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 		amdgpu_vm_bo_del(adev, fpriv->prt_va);
 		amdgpu_bo_unreserve(pd);
 	}
+	fpriv->evf_mgr.fd_closing = true;
+	amdgpu_eviction_fence_destroy(&fpriv->evf_mgr);
+	amdgpu_userq_mgr_fini(&fpriv->userq_mgr);
 
 	amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr);
 	amdgpu_vm_fini(adev, &fpriv->vm);
Signature · 1 line
2.39.5
author maintainer
#172 lore raw

PATCH 166/627 wifi: iwlwifi: Fix memory leak in iwl_mvm_init()

In reply to Greg Kroah-Hartman

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

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

From: Xiu Jianfeng <[email protected]>

[ Upstream commit ed2e916c890944633d6826dce267579334f63ea5 ]

When iwl_opmode_register() fails, it does not unregster rate control, which will cause a memory leak issue, this patch fixes it.

Fixes 9f66a397c877 ("iwlwifi: mvm: rs: add ops for the new rate scaling in the FW")
---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/wireless/intel/iwlwifi/mvm/ops.c +3 -1
index a2dc5c3b0596..1c05a3d8e424 100644
@@ -61,8 +61,10 @@ static int __init iwl_mvm_init(void)
 	}
 
 	ret = iwl_opmode_register("iwlmvm", &iwl_mvm_ops);
-	if (ret)
+	if (ret) {
 		pr_err("Unable to register MVM op_mode: %d\n", ret);
+		iwl_mvm_rate_control_unregister();
+	}
 
 	return ret;
 }
Signature · 1 line
2.39.5
author maintainer
#173 lore raw

PATCH 167/627 iwlwifi: Add missing check for alloc_ordered_workqueue

In reply to Greg Kroah-Hartman

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

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

From: Jiasheng Jiang <[email protected]>

[ Upstream commit 90a0d9f339960448a3acc1437a46730f975efd6a ]

Add check for the return value of alloc_ordered_workqueue since it may return NULL pointer.

Fixes b481de9ca074 ("[IWLWIFI]: add iwlwifi wireless drivers")
---
 drivers/net/wireless/intel/iwlwifi/dvm/main.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
drivers/net/wireless/intel/iwlwifi/dvm/main.c +9 -2
index 66211426aa3a..e015b83bb6e9 100644
@@ -1049,9 +1049,11 @@ static void iwl_bg_restart(struct work_struct *data)
  *
  *****************************************************************************/
 
-static void iwl_setup_deferred_work(struct iwl_priv *priv)
+static int iwl_setup_deferred_work(struct iwl_priv *priv)
 {
 	priv->workqueue = alloc_ordered_workqueue(DRV_NAME, 0);
+	if (!priv->workqueue)
+		return -ENOMEM;
 
 	INIT_WORK(&priv->restart, iwl_bg_restart);
 	INIT_WORK(&priv->beacon_update, iwl_bg_beacon_update);
@@ -1068,6 +1070,8 @@ static void iwl_setup_deferred_work(struct iwl_priv *priv)
 	timer_setup(&priv->statistics_periodic, iwl_bg_statistics_periodic, 0);
 
 	timer_setup(&priv->ucode_trace, iwl_bg_ucode_trace, 0);
+
+	return 0;
 }
 
 void iwl_cancel_deferred_work(struct iwl_priv *priv)
@@ -1463,7 +1467,9 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 	/********************
 	 * 6. Setup services
 	 ********************/
-	iwl_setup_deferred_work(priv);
+	if (iwl_setup_deferred_work(priv))
+		goto out_uninit_drv;
+
 	iwl_setup_rx_handlers(priv);
 
 	iwl_power_initialize(priv);
@@ -1502,6 +1508,7 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 	iwl_cancel_deferred_work(priv);
 	destroy_workqueue(priv->workqueue);
 	priv->workqueue = NULL;
+out_uninit_drv:
 	iwl_uninit_drv(priv);
 out_free_eeprom_blob:
 	kfree(priv->eeprom_blob);
Signature · 1 line
2.39.5
author maintainer
#174 lore raw

PATCH 168/627 drm/xe/uapi: Correct sync type definition in comments

In reply to Greg Kroah-Hartman

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

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

From: Shuicheng Lin <[email protected]>

[ Upstream commit 771f002ef1d6f6c2b9bddf779abd31da6b9ccd25 ]

Commit 37d078e51b4c ("drm/xe/uapi: Split xe_sync types from flags") renamed some DRM_XE_SYNC_* defines but later commits kept using the old names. Correct them with the new definition.

v2: correct fixes tag and update commit message to explain why (Lucas)

Fixes 9329f0667215 ("drm/xe/uapi: Use LR abbrev for long-running vms")
Fixes 4b437893a826 ("drm/xe/uapi: More uAPI documentation additions and cosmetic updates")
Cc Rodrigo Vivi <[email protected]>
Cc Francois Dugast <[email protected]>
Cc Zongyao Bai <[email protected]>
---
 include/uapi/drm/xe_drm.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
include/uapi/drm/xe_drm.h +4 -4
index 6a702ba7817c..5f1524f466a7 100644
@@ -925,9 +925,9 @@ struct drm_xe_gem_mmap_offset {
  *  - %DRM_XE_VM_CREATE_FLAG_LR_MODE - An LR, or Long Running VM accepts
  *    exec submissions to its exec_queues that don't have an upper time
  *    limit on the job execution time. But exec submissions to these
- *    don't allow any of the flags DRM_XE_SYNC_FLAG_SYNCOBJ,
- *    DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ, DRM_XE_SYNC_FLAG_DMA_BUF,
- *    used as out-syncobjs, that is, together with DRM_XE_SYNC_FLAG_SIGNAL.
+ *    don't allow any of the sync types DRM_XE_SYNC_TYPE_SYNCOBJ,
+ *    DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ, used as out-syncobjs, that is,
+ *    together with sync flag DRM_XE_SYNC_FLAG_SIGNAL.
  *    LR VMs can be created in recoverable page-fault mode using
  *    DRM_XE_VM_CREATE_FLAG_FAULT_MODE, if the device supports it.
  *    If that flag is omitted, the UMD can not rely on the slightly
@@ -1394,7 +1394,7 @@ struct drm_xe_sync {
 
 	/**
 	 * @timeline_value: Input for the timeline sync object. Needs to be
-	 * different than 0 when used with %DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ.
+	 * different than 0 when used with %DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ.
 	 */
 	__u64 timeline_value;
 
Signature · 1 line
2.39.5
author maintainer
#175 lore raw

PATCH 169/627 team: replace team lock with rtnl lock

In reply to Greg Kroah-Hartman

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

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

From: Stanislav Fomichev <[email protected]>

[ Upstream commit bfb4fb77f9a8ce33ce357224569eae5564eec573 ]

syszbot reports various ordering issues for lower instance locks and team lock. Switch to using rtnl lock for protecting team device, similar to bonding. Based on the patch by Tetsuo Handa.

---
 drivers/net/team/team_core.c              | 96 +++++++++++------------
 drivers/net/team/team_mode_activebackup.c |  3 +-
 drivers/net/team/team_mode_loadbalance.c  | 13 ++-
 include/linux/if_team.h                   |  3 -
 4 files changed, 50 insertions(+), 65 deletions(-)
drivers/net/team/team_core.c +44 -52
index 8bc56186b2a3..17f07eb0ee52 100644
@@ -933,7 +933,7 @@ static bool team_port_find(const struct team *team,
  * Enable/disable port by adding to enabled port hashlist and setting
  * port->index (Might be racy so reader could see incorrect ifindex when
  * processing a flying packet, but that is not a problem). Write guarded
- * by team->lock.
+ * by RTNL.
  */
 static void team_port_enable(struct team *team,
 			     struct team_port *port)
@@ -1660,8 +1660,6 @@ static int team_init(struct net_device *dev)
 		goto err_options_register;
 	netif_carrier_off(dev);
 
-	lockdep_register_key(&team->team_lock_key);
-	__mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key);
 	netdev_lockdep_set_classes(dev);
 
 	return 0;
@@ -1682,7 +1680,8 @@ static void team_uninit(struct net_device *dev)
 	struct team_port *port;
 	struct team_port *tmp;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	list_for_each_entry_safe(port, tmp, &team->port_list, list)
 		team_port_del(team, port->dev);
 
@@ -1691,9 +1690,7 @@ static void team_uninit(struct net_device *dev)
 	team_mcast_rejoin_fini(team);
 	team_notify_peers_fini(team);
 	team_queue_override_fini(team);
-	mutex_unlock(&team->lock);
 	netdev_change_features(dev);
-	lockdep_unregister_key(&team->team_lock_key);
 }
 
 static void team_destructor(struct net_device *dev)
@@ -1778,7 +1775,8 @@ static void team_change_rx_flags(struct net_device *dev, int change)
 	struct team_port *port;
 	int inc;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	list_for_each_entry(port, &team->port_list, list) {
 		if (change & IFF_PROMISC) {
 			inc = dev->flags & IFF_PROMISC ? 1 : -1;
@@ -1789,7 +1787,6 @@ static void team_change_rx_flags(struct net_device *dev, int change)
 			dev_set_allmulti(port->dev, inc);
 		}
 	}
-	mutex_unlock(&team->lock);
 }
 
 static void team_set_rx_mode(struct net_device *dev)
@@ -1811,14 +1808,14 @@ static int team_set_mac_address(struct net_device *dev, void *p)
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
+	ASSERT_RTNL();
+
 	if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 	dev_addr_set(dev, addr->sa_data);
-	mutex_lock(&team->lock);
 	list_for_each_entry(port, &team->port_list, list)
 		if (team->ops.port_change_dev_addr)
 			team->ops.port_change_dev_addr(team, port);
-	mutex_unlock(&team->lock);
 	return 0;
 }
 
@@ -1828,11 +1825,8 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 	struct team_port *port;
 	int err;
 
-	/*
-	 * Alhough this is reader, it's guarded by team lock. It's not possible
-	 * to traverse list in reverse under rcu_read_lock
-	 */
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	team->port_mtu_change_allowed = true;
 	list_for_each_entry(port, &team->port_list, list) {
 		err = dev_set_mtu(port->dev, new_mtu);
@@ -1843,7 +1837,6 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 		}
 	}
 	team->port_mtu_change_allowed = false;
-	mutex_unlock(&team->lock);
 
 	WRITE_ONCE(dev->mtu, new_mtu);
 
@@ -1853,7 +1846,6 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		dev_set_mtu(port->dev, dev->mtu);
 	team->port_mtu_change_allowed = false;
-	mutex_unlock(&team->lock);
 
 	return err;
 }
@@ -1903,24 +1895,19 @@ static int team_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
 	struct team_port *port;
 	int err;
 
-	/*
-	 * Alhough this is reader, it's guarded by team lock. It's not possible
-	 * to traverse list in reverse under rcu_read_lock
-	 */
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	list_for_each_entry(port, &team->port_list, list) {
 		err = vlan_vid_add(port->dev, proto, vid);
 		if (err)
 			goto unwind;
 	}
-	mutex_unlock(&team->lock);
 
 	return 0;
 
 unwind:
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	mutex_unlock(&team->lock);
 
 	return err;
 }
@@ -1930,10 +1917,10 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	list_for_each_entry(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	mutex_unlock(&team->lock);
 
 	return 0;
 }
@@ -1955,9 +1942,9 @@ static void team_netpoll_cleanup(struct net_device *dev)
 {
 	struct team *team = netdev_priv(dev);
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	__team_netpoll_cleanup(team);
-	mutex_unlock(&team->lock);
 }
 
 static int team_netpoll_setup(struct net_device *dev)
@@ -1966,7 +1953,8 @@ static int team_netpoll_setup(struct net_device *dev)
 	struct team_port *port;
 	int err = 0;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	list_for_each_entry(port, &team->port_list, list) {
 		err = __team_port_enable_netpoll(port);
 		if (err) {
@@ -1974,7 +1962,6 @@ static int team_netpoll_setup(struct net_device *dev)
 			break;
 		}
 	}
-	mutex_unlock(&team->lock);
 	return err;
 }
 #endif
@@ -1985,9 +1972,9 @@ static int team_add_slave(struct net_device *dev, struct net_device *port_dev,
 	struct team *team = netdev_priv(dev);
 	int err;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	err = team_port_add(team, port_dev, extack);
-	mutex_unlock(&team->lock);
 
 	if (!err)
 		netdev_change_features(dev);
@@ -2000,18 +1987,13 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev)
 	struct team *team = netdev_priv(dev);
 	int err;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	err = team_port_del(team, port_dev);
-	mutex_unlock(&team->lock);
 
 	if (err)
 		return err;
 
-	if (netif_is_team_master(port_dev)) {
-		lockdep_unregister_key(&team->team_lock_key);
-		lockdep_register_key(&team->team_lock_key);
-		lockdep_set_class(&team->lock, &team->team_lock_key);
-	}
 	netdev_change_features(dev);
 
 	return err;
@@ -2304,9 +2286,10 @@ int team_nl_noop_doit(struct sk_buff *skb, struct genl_info *info)
 static struct team *team_nl_team_get(struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
-	int ifindex;
 	struct net_device *dev;
-	struct team *team;
+	int ifindex;
+
+	ASSERT_RTNL();
 
 	if (!info->attrs[TEAM_ATTR_TEAM_IFINDEX])
 		return NULL;
@@ -2318,14 +2301,11 @@ static struct team *team_nl_team_get(struct genl_info *info)
 		return NULL;
 	}
 
-	team = netdev_priv(dev);
-	mutex_lock(&team->lock);
-	return team;
+	return netdev_priv(dev);
 }
 
 static void team_nl_team_put(struct team *team)
 {
-	mutex_unlock(&team->lock);
 	dev_put(team->dev);
 }
 
@@ -2515,9 +2495,13 @@ int team_nl_options_get_doit(struct sk_buff *skb, struct genl_info *info)
 	int err;
 	LIST_HEAD(sel_opt_inst_list);
 
+	rtnl_lock();
+
 	team = team_nl_team_get(info);
-	if (!team)
-		return -EINVAL;
+	if (!team) {
+		err = -EINVAL;
+		goto rtnl_unlock;
+	}
 
 	list_for_each_entry(opt_inst, &team->option_inst_list, list)
 		list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list);
@@ -2527,6 +2511,9 @@ int team_nl_options_get_doit(struct sk_buff *skb, struct genl_info *info)
 
 	team_nl_team_put(team);
 
+rtnl_unlock:
+	rtnl_unlock();
+
 	return err;
 }
 
@@ -2805,15 +2792,22 @@ int team_nl_port_list_get_doit(struct sk_buff *skb,
 	struct team *team;
 	int err;
 
+	rtnl_lock();
+
 	team = team_nl_team_get(info);
-	if (!team)
-		return -EINVAL;
+	if (!team) {
+		err = -EINVAL;
+		goto rtnl_unlock;
+	}
 
 	err = team_nl_send_port_list_get(team, info->snd_portid, info->snd_seq,
 					 NLM_F_ACK, team_nl_send_unicast, NULL);
 
 	team_nl_team_put(team);
 
+rtnl_unlock:
+	rtnl_unlock();
+
 	return err;
 }
 
@@ -2961,11 +2955,9 @@ static void __team_port_change_port_removed(struct team_port *port)
 
 static void team_port_change_check(struct team_port *port, bool linkup)
 {
-	struct team *team = port->team;
+	ASSERT_RTNL();
 
-	mutex_lock(&team->lock);
 	__team_port_change_check(port, linkup);
-	mutex_unlock(&team->lock);
 }
 
 
drivers/net/team/team_mode_activebackup.c +1 -2
index e0f599e2a51d..1c3336c7a1b2 100644
@@ -67,8 +67,7 @@ static void ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx)
 {
 	struct team_port *active_port;
 
-	active_port = rcu_dereference_protected(ab_priv(team)->active_port,
-						lockdep_is_held(&team->lock));
+	active_port = rtnl_dereference(ab_priv(team)->active_port);
 	if (active_port)
 		ctx->data.u32_val = active_port->dev->ifindex;
 	else
drivers/net/team/team_mode_loadbalance.c +5 -8
index 00f8989c29c0..b14538bde2f8 100644
@@ -301,8 +301,7 @@ static int lb_bpf_func_set(struct team *team, struct team_gsetter_ctx *ctx)
 	if (lb_priv->ex->orig_fprog) {
 		/* Clear old filter data */
 		__fprog_destroy(lb_priv->ex->orig_fprog);
-		orig_fp = rcu_dereference_protected(lb_priv->fp,
-						lockdep_is_held(&team->lock));
+		orig_fp = rtnl_dereference(lb_priv->fp);
 	}
 
 	rcu_assign_pointer(lb_priv->fp, fp);
@@ -324,8 +323,7 @@ static void lb_bpf_func_free(struct team *team)
 		return;
 
 	__fprog_destroy(lb_priv->ex->orig_fprog);
-	fp = rcu_dereference_protected(lb_priv->fp,
-				       lockdep_is_held(&team->lock));
+	fp = rtnl_dereference(lb_priv->fp);
 	bpf_prog_destroy(fp);
 }
 
@@ -335,8 +333,7 @@ static void lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx)
 	lb_select_tx_port_func_t *func;
 	char *name;
 
-	func = rcu_dereference_protected(lb_priv->select_tx_port_func,
-					 lockdep_is_held(&team->lock));
+	func = rtnl_dereference(lb_priv->select_tx_port_func);
 	name = lb_select_tx_port_get_name(func);
 	BUG_ON(!name);
 	ctx->data.str_val = name;
@@ -478,7 +475,7 @@ static void lb_stats_refresh(struct work_struct *work)
 	team = lb_priv_ex->team;
 	lb_priv = get_lb_priv(team);
 
-	if (!mutex_trylock(&team->lock)) {
+	if (!rtnl_trylock()) {
 		schedule_delayed_work(&lb_priv_ex->stats.refresh_dw, 0);
 		return;
 	}
@@ -515,7 +512,7 @@ static void lb_stats_refresh(struct work_struct *work)
 	schedule_delayed_work(&lb_priv_ex->stats.refresh_dw,
 			      (lb_priv_ex->stats.refresh_interval * HZ) / 10);
 
-	mutex_unlock(&team->lock);
+	rtnl_unlock();
 }
 
 static void lb_stats_refresh_interval_get(struct team *team,
include/linux/if_team.h +0 -3
index cdc684e04a2f..ce97d891cf72 100644
@@ -191,8 +191,6 @@ struct team {
 
 	const struct header_ops *header_ops_cache;
 
-	struct mutex lock; /* used for overall locking, e.g. port lists write */
-
 	/*
 	 * List of enabled ports and their count
 	 */
@@ -223,7 +221,6 @@ struct team {
 		atomic_t count_pending;
 		struct delayed_work dw;
 	} mcast_rejoin;
-	struct lock_class_key team_lock_key;
 	long mode_priv[TEAM_MODE_PRIV_LONGS];
 };
 
Signature · 1 line
2.39.5
author maintainer
#176 lore raw

PATCH 170/627 wifi: ath11k: clear initialized flag for deinit-ed srng lists

In reply to Greg Kroah-Hartman

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

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

From: Sergey Senozhatsky <[email protected]>

[ Upstream commit a5b46aa7cf5f05c213316a018e49a8e086efd98e ]

In a number of cases we see kernel panics on resume due to ath11k kernel page fault, which happens under the following circumstances:

1) First ath11k_hal_dump_srng_stats() call

Last interrupt received for each group:
ath11k_pci 0000:01:00.0: group_id 0 22511ms before
ath11k_pci 0000:01:00.0: group_id 1 14440788ms before
[..]
ath11k_pci 0000:01:00.0: failed to receive control response completion, polling.. ath11k_pci 0000:01:00.0: Service connect timeout
ath11k_pci 0000:01:00.0: failed to connect to HTT: -110
ath11k_pci 0000:01:00.0: failed to start core: -110
ath11k_pci 0000:01:00.0: firmware crashed: MHI_CB_EE_RDDM
ath11k_pci 0000:01:00.0: already resetting count 2
ath11k_pci 0000:01:00.0: failed to wait wlan mode request (mode 4): -110 ath11k_pci 0000:01:00.0: qmi failed to send wlan mode off: -110 ath11k_pci 0000:01:00.0: failed to reconfigure driver on crash recovery [..]

2) At this point reconfiguration fails (we have 2 resets) and ath11k_core_reconfigure_on_crash() calls ath11k_hal_srng_deinit() which destroys srng lists. However, it does not reset per-list ->initialized flag.

3) Second ath11k_hal_dump_srng_stats() call sees stale ->initialized flag and attempts to dump srng stats:

Last interrupt received for each group:
ath11k_pci 0000:01:00.0: group_id 0 66785ms before ath11k_pci 0000:01:00.0: group_id 1 14485062ms before ath11k_pci 0000:01:00.0: group_id 2 14485062ms before ath11k_pci 0000:01:00.0: group_id 3 14485062ms before ath11k_pci 0000:01:00.0: group_id 4 14780845ms before ath11k_pci 0000:01:00.0: group_id 5 14780845ms before ath11k_pci 0000:01:00.0: group_id 6 14485062ms before ath11k_pci 0000:01:00.0: group_id 7 66814ms before ath11k_pci 0000:01:00.0: group_id 8 68997ms before ath11k_pci 0000:01:00.0: group_id 9 67588ms before ath11k_pci 0000:01:00.0: group_id 10 69511ms before

 BUG: unable to handle page fault for address: ffffa007404eb010
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 100000067 P4D 100000067 PUD 10022d067 PMD 100b01067 PTE 0
 Oops: 0000 [#1] PREEMPT SMP NOPTI
 RIP: 0010:ath11k_hal_dump_srng_stats+0x2b4/0x3b0 [ath11k]
 Call Trace:
 <TASK>
 ? __die_body+0xae/0xb0
 ? page_fault_oops+0x381/0x3e0
 ? exc_page_fault+0x69/0xa0
 ? asm_exc_page_fault+0x22/0x30
 ? ath11k_hal_dump_srng_stats+0x2b4/0x3b0 [ath11k (HASH:6cea 4)]
 ath11k_qmi_driver_event_work+0xbd/0x1050 [ath11k (HASH:6cea 4)]
 worker_thread+0x389/0x930
 kthread+0x149/0x170

Clear per-list ->initialized flag in ath11k_hal_srng_deinit().

---
 drivers/net/wireless/ath/ath11k/hal.c | 4 ++++
 1 file changed, 4 insertions(+)
drivers/net/wireless/ath/ath11k/hal.c +4 -0
index 8cb1505a5a0c..cab11a35f911 100644
@@ -1346,6 +1346,10 @@ EXPORT_SYMBOL(ath11k_hal_srng_init);
 void ath11k_hal_srng_deinit(struct ath11k_base *ab)
 {
 	struct ath11k_hal *hal = &ab->hal;
+	int i;
+
+	for (i = 0; i < HAL_SRNG_RING_ID_MAX; i++)
+		ab->hal.srng_list[i].initialized = 0;
 
 	ath11k_hal_unregister_srng_key(ab);
 	ath11k_hal_free_cont_rdp(ab);
Signature · 1 line
2.39.5
author maintainer
#177 lore raw

PATCH 171/627 wifi: ath12k: Clear auth flag only for actual association in security mode

In reply to Greg Kroah-Hartman

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

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

From: Thiraviyam Mariyappan <[email protected]>

[ Upstream commit c27bb624b3d789a337df3bbcc020a575680555cc ]

When setting a new bitrate, WMI peer association command is sent from the host without the peer authentication bit set in peer_flags for security mode, which causes ping failure.

The firmware handles peer_flags when the client is associating, as the peer authentication bit in peer_flags is set after the key exchange. When the WMI peer association command is sent from the host to update the new bitrate for an associated STA, the firmware expects the WMI peer authentication bit to be set in peer_flags.

Fix this issue by ensuring that the WMI peer auth bit is set in peer_flags in WMI peer association command when updating the new bitrate.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Fixes d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
---
 drivers/net/wireless/ath/ath12k/mac.c | 4 ++++
 drivers/net/wireless/ath/ath12k/wmi.c | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/wireless/ath/ath12k/mac.c +4 -0
index 3616269538e6..0feb800a4921 100644
@@ -3235,6 +3235,7 @@ static void ath12k_bss_assoc(struct ath12k *ar,
 
 	rcu_read_unlock();
 
+	peer_arg->is_assoc = true;
 	ret = ath12k_wmi_send_peer_assoc_cmd(ar, peer_arg);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to run peer assoc for %pM vdev %i: %d\n",
@@ -5165,6 +5166,8 @@ static int ath12k_mac_station_assoc(struct ath12k *ar,
 			    "invalid peer NSS %d\n", peer_arg->peer_nss);
 		return -EINVAL;
 	}
+
+	peer_arg->is_assoc = true;
 	ret = ath12k_wmi_send_peer_assoc_cmd(ar, peer_arg);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to run peer assoc for STA %pM vdev %i: %d\n",
@@ -5411,6 +5414,7 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk)
 			ath12k_peer_assoc_prepare(ar, arvif, arsta,
 						  peer_arg, true);
 
+			peer_arg->is_assoc = false;
 			err = ath12k_wmi_send_peer_assoc_cmd(ar, peer_arg);
 			if (err)
 				ath12k_warn(ar->ab, "failed to run peer assoc for STA %pM vdev %i: %d\n",
drivers/net/wireless/ath/ath12k/wmi.c +1 -1
index 465f877fc0fb..e19803bfba75 100644
@@ -2152,7 +2152,7 @@ static void ath12k_wmi_copy_peer_flags(struct wmi_peer_assoc_complete_cmd *cmd,
 		cmd->peer_flags |= cpu_to_le32(WMI_PEER_AUTH);
 	if (arg->need_ptk_4_way) {
 		cmd->peer_flags |= cpu_to_le32(WMI_PEER_NEED_PTK_4_WAY);
-		if (!hw_crypto_disabled)
+		if (!hw_crypto_disabled && arg->is_assoc)
 			cmd->peer_flags &= cpu_to_le32(~WMI_PEER_AUTH);
 	}
 	if (arg->need_gtk_2_way)
Signature · 1 line
2.39.5
author maintainer
#178 lore raw

PATCH 172/627 tcp: fix tcp_ofo_queue() to avoid including too much DUP SACK range

In reply to Greg Kroah-Hartman

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

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

From: xin.guo <[email protected]>

[ Upstream commit a041f70e573e185d5d5fdbba53f0db2fbe7257ad ]

If the new coming segment covers more than one skbs in the ofo queue, and which seq is equal to rcv_nxt, then the sequence range that is duplicated will be sent as DUP SACK, the detail as below, in step6, the {501,2001} range is clearly including too much DUP SACK range, in violation of RFC 2883 rules.

1. client > server: Flags [.], seq 501:1001, ack 1325288529, win 20000, length 500
2. server > client: Flags [.], ack 1, [nop,nop,sack 1 {501:1001}], length 0
3. client > server: Flags [.], seq 1501:2001, ack 1325288529, win 20000, length 500
4. server > client: Flags [.], ack 1, [nop,nop,sack 2 {1501:2001} {501:1001}], length 0
5. client > server: Flags [.], seq 1:2001, ack 1325288529, win 20000, length 2000
6. server > client: Flags [.], ack 2001, [nop,nop,sack 1 {501:2001}], length 0

After this fix, the final ACK is as below:

6. server > client: Flags [.], ack 2001, options [nop,nop,sack 1 {501:1001}], length 0

[edumazet] added a new packetdrill test in the following patch.

---
 net/ipv4/tcp_input.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
net/ipv4/tcp_input.c +2 -1
index 68bc79eb9019..76b01df70e56 100644
@@ -4985,8 +4985,9 @@ static void tcp_ofo_queue(struct sock *sk)
 
 		if (before(TCP_SKB_CB(skb)->seq, dsack_high)) {
 			__u32 dsack = dsack_high;
+
 			if (before(TCP_SKB_CB(skb)->end_seq, dsack_high))
-				dsack_high = TCP_SKB_CB(skb)->end_seq;
+				dsack = TCP_SKB_CB(skb)->end_seq;
 			tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack);
 		}
 		p = rb_next(p);
Signature · 1 line
2.39.5
author maintainer
#179 lore raw

PATCH 173/627 net/mlx5: Check device memory pointer before usage

In reply to Greg Kroah-Hartman

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

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

From: Stav Aviram <[email protected]>

[ Upstream commit 70f238c902b8c0461ae6fbb8d1a0bbddc4350eea ]

Add a NULL check before accessing device memory to prevent a crash if dev->dm allocation in mlx5_init_once() fails.

---
 drivers/infiniband/hw/mlx5/dm.c                  | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/main.c   | 3 ---
 3 files changed, 3 insertions(+), 6 deletions(-)
drivers/infiniband/hw/mlx5/dm.c +1 -1
index b4c97fb62abf..9ded2b7c1e31 100644
@@ -282,7 +282,7 @@ static struct ib_dm *handle_alloc_dm_memic(struct ib_ucontext *ctx,
 	int err;
 	u64 address;
 
-	if (!MLX5_CAP_DEV_MEM(dm_db->dev, memic))
+	if (!dm_db || !MLX5_CAP_DEV_MEM(dm_db->dev, memic))
 		return ERR_PTR(-EOPNOTSUPP);
 
 	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c +2 -2
index 7c5516b0a844..8115071c34a4 100644
@@ -30,7 +30,7 @@ struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev)
 
 	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
 	if (!dm)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	spin_lock_init(&dm->lock);
 
@@ -96,7 +96,7 @@ struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev)
 err_steering:
 	kfree(dm);
 
-	return ERR_PTR(-ENOMEM);
+	return NULL;
 }
 
 void mlx5_dm_cleanup(struct mlx5_core_dev *dev)
drivers/net/ethernet/mellanox/mlx5/core/main.c +0 -3
index 9c1504d29d34..e7bcd0f0a709 100644
@@ -1102,9 +1102,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	}
 
 	dev->dm = mlx5_dm_create(dev);
-	if (IS_ERR(dev->dm))
-		mlx5_core_warn(dev, "Failed to init device memory %ld\n", PTR_ERR(dev->dm));
-
 	dev->tracer = mlx5_fw_tracer_create(dev);
 	dev->hv_vhca = mlx5_hv_vhca_create(dev);
 	dev->rsc_dump = mlx5_rsc_dump_create(dev);
Signature · 1 line
2.39.5
author maintainer
#180 lore raw

PATCH 174/627 net: dst: annotate data-races around dst->input

In reply to Greg Kroah-Hartman

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit f1c5fd34891a1c242885f48c2e4dc52df180f311 ]

dst_dev_put() can overwrite dst->input while other cpus might read this field (for instance from dst_input())

Add READ_ONCE()/WRITE_ONCE() annotations to suppress potential issues.

We will likely need full RCU protection later.

---
 include/net/dst.h      | 2 +-
 include/net/lwtunnel.h | 4 ++--
 net/core/dst.c         | 2 +-
 net/ipv4/route.c       | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)
include/net/dst.h +1 -1
index 78c78cdce0e9..65d81116d6bf 100644
@@ -466,7 +466,7 @@ INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *));
 /* Input packet from network to transport.  */
 static inline int dst_input(struct sk_buff *skb)
 {
-	return INDIRECT_CALL_INET(skb_dst(skb)->input,
+	return INDIRECT_CALL_INET(READ_ONCE(skb_dst(skb)->input),
 				  ip6_input, ip_local_deliver, skb);
 }
 
include/net/lwtunnel.h +2 -2
index c306ebe379a0..eaac07d50595 100644
@@ -142,8 +142,8 @@ static inline void lwtunnel_set_redirect(struct dst_entry *dst)
 		dst->output = lwtunnel_output;
 	}
 	if (lwtunnel_input_redirect(dst->lwtstate)) {
-		dst->lwtstate->orig_input = dst->input;
-		dst->input = lwtunnel_input;
+		dst->lwtstate->orig_input = READ_ONCE(dst->input);
+		WRITE_ONCE(dst->input, lwtunnel_input);
 	}
 }
 #else
net/core/dst.c +1 -1
index 795ca07e28a4..b46f7722a1b6 100644
@@ -148,7 +148,7 @@ void dst_dev_put(struct dst_entry *dst)
 	dst->obsolete = DST_OBSOLETE_DEAD;
 	if (dst->ops->ifdown)
 		dst->ops->ifdown(dst, dev);
-	dst->input = dst_discard;
+	WRITE_ONCE(dst->input, dst_discard);
 	dst->output = dst_discard_out;
 	dst->dev = blackhole_netdev;
 	netdev_ref_replace(dev, blackhole_netdev, &dst->dev_tracker,
net/ipv4/route.c +1 -1
index 64ac20c27f1b..2cc88f8c3bc6 100644
@@ -1685,7 +1685,7 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt)
 		else if (rt->rt_gw_family == AF_INET6)
 			new_rt->rt_gw6 = rt->rt_gw6;
 
-		new_rt->dst.input = rt->dst.input;
+		new_rt->dst.input = READ_ONCE(rt->dst.input);
 		new_rt->dst.output = rt->dst.output;
 		new_rt->dst.error = rt->dst.error;
 		new_rt->dst.lastuse = jiffies;
Signature · 1 line
2.39.5
author maintainer
#181 lore raw

PATCH 175/627 net: dst: annotate data-races around dst->output

In reply to Greg Kroah-Hartman

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 2dce8c52a98995c4719def6f88629ab1581c0b82 ]

dst_dev_put() can overwrite dst->output while other cpus might read this field (for instance from dst_output())

Add READ_ONCE()/WRITE_ONCE() annotations to suppress potential issues.

We will likely need RCU protection in the future.

---
 include/net/dst.h      | 2 +-
 include/net/lwtunnel.h | 4 ++--
 net/core/dst.c         | 2 +-
 net/ipv4/route.c       | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)
include/net/dst.h +1 -1
index 65d81116d6bf..2caf85e2ce86 100644
@@ -456,7 +456,7 @@ INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *,
 /* Output packet to network from transport.  */
 static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	return INDIRECT_CALL_INET(skb_dst(skb)->output,
+	return INDIRECT_CALL_INET(READ_ONCE(skb_dst(skb)->output),
 				  ip6_output, ip_output,
 				  net, sk, skb);
 }
include/net/lwtunnel.h +2 -2
index eaac07d50595..26232f603e33 100644
@@ -138,8 +138,8 @@ int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len,
 static inline void lwtunnel_set_redirect(struct dst_entry *dst)
 {
 	if (lwtunnel_output_redirect(dst->lwtstate)) {
-		dst->lwtstate->orig_output = dst->output;
-		dst->output = lwtunnel_output;
+		dst->lwtstate->orig_output = READ_ONCE(dst->output);
+		WRITE_ONCE(dst->output, lwtunnel_output);
 	}
 	if (lwtunnel_input_redirect(dst->lwtstate)) {
 		dst->lwtstate->orig_input = READ_ONCE(dst->input);
net/core/dst.c +1 -1
index b46f7722a1b6..e483daf17666 100644
@@ -149,7 +149,7 @@ void dst_dev_put(struct dst_entry *dst)
 	if (dst->ops->ifdown)
 		dst->ops->ifdown(dst, dev);
 	WRITE_ONCE(dst->input, dst_discard);
-	dst->output = dst_discard_out;
+	WRITE_ONCE(dst->output, dst_discard_out);
 	dst->dev = blackhole_netdev;
 	netdev_ref_replace(dev, blackhole_netdev, &dst->dev_tracker,
 			   GFP_ATOMIC);
net/ipv4/route.c +1 -1
index 2cc88f8c3bc6..bd5d48fdd62a 100644
@@ -1686,7 +1686,7 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt)
 			new_rt->rt_gw6 = rt->rt_gw6;
 
 		new_rt->dst.input = READ_ONCE(rt->dst.input);
-		new_rt->dst.output = rt->dst.output;
+		new_rt->dst.output = READ_ONCE(rt->dst.output);
 		new_rt->dst.error = rt->dst.error;
 		new_rt->dst.lastuse = jiffies;
 		new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate);
Signature · 1 line
2.39.5
author maintainer
#182 lore raw

PATCH 176/627 net: dst: add four helpers to annotate data-races around dst->dev

In reply to Greg Kroah-Hartman

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 88fe14253e181878c2ddb51a298ae8c468a63010 ]

dst->dev is read locklessly in many contexts,
and written in dst_dev_put().

Fixing all the races is going to need many changes.

We probably will have to add full RCU protection.

Add three helpers to ease this painful process.

static inline struct net_device *dst_dev(const struct dst_entry *dst)

{
       return READ_ONCE(dst->dev);
}

static inline struct net_device *skb_dst_dev(const struct sk_buff *skb)

{
       return dst_dev(skb_dst(skb));
}

static inline struct net *skb_dst_dev_net(const struct sk_buff *skb)

{
       return dev_net(skb_dst_dev(skb));
}

static inline struct net *skb_dst_dev_net_rcu(const struct sk_buff *skb)

{
       return dev_net_rcu(skb_dst_dev(skb));
}
---
 include/net/dst.h | 20 ++++++++++++++++++++
 net/core/dst.c    |  4 ++--
 net/core/sock.c   |  8 ++++----
 3 files changed, 26 insertions(+), 6 deletions(-)
include/net/dst.h +20 -0
index 2caf85e2ce86..32dafbab4cd0 100644
@@ -561,6 +561,26 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
 		dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
 }
 
+static inline struct net_device *dst_dev(const struct dst_entry *dst)
+{
+	return READ_ONCE(dst->dev);
+}
+
+static inline struct net_device *skb_dst_dev(const struct sk_buff *skb)
+{
+	return dst_dev(skb_dst(skb));
+}
+
+static inline struct net *skb_dst_dev_net(const struct sk_buff *skb)
+{
+	return dev_net(skb_dst_dev(skb));
+}
+
+static inline struct net *skb_dst_dev_net_rcu(const struct sk_buff *skb)
+{
+	return dev_net_rcu(skb_dst_dev(skb));
+}
+
 struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie);
 void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
 			       struct sk_buff *skb, u32 mtu, bool confirm_neigh);
net/core/dst.c +2 -2
index e483daf17666..b3a12c7c08af 100644
@@ -150,7 +150,7 @@ void dst_dev_put(struct dst_entry *dst)
 		dst->ops->ifdown(dst, dev);
 	WRITE_ONCE(dst->input, dst_discard);
 	WRITE_ONCE(dst->output, dst_discard_out);
-	dst->dev = blackhole_netdev;
+	WRITE_ONCE(dst->dev, blackhole_netdev);
 	netdev_ref_replace(dev, blackhole_netdev, &dst->dev_tracker,
 			   GFP_ATOMIC);
 }
@@ -263,7 +263,7 @@ unsigned int dst_blackhole_mtu(const struct dst_entry *dst)
 {
 	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
 
-	return mtu ? : dst->dev->mtu;
+	return mtu ? : dst_dev(dst)->mtu;
 }
 EXPORT_SYMBOL_GPL(dst_blackhole_mtu);
 
net/core/sock.c +4 -4
index 3b409bc8ef6d..9fae9239f939 100644
@@ -2602,8 +2602,8 @@ static u32 sk_dst_gso_max_size(struct sock *sk, struct dst_entry *dst)
 		   !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr));
 #endif
 	/* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */
-	max_size = is_ipv6 ? READ_ONCE(dst->dev->gso_max_size) :
-			READ_ONCE(dst->dev->gso_ipv4_max_size);
+	max_size = is_ipv6 ? READ_ONCE(dst_dev(dst)->gso_max_size) :
+			READ_ONCE(dst_dev(dst)->gso_ipv4_max_size);
 	if (max_size > GSO_LEGACY_MAX_SIZE && !sk_is_tcp(sk))
 		max_size = GSO_LEGACY_MAX_SIZE;
 
@@ -2614,7 +2614,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
 	u32 max_segs = 1;
 
-	sk->sk_route_caps = dst->dev->features;
+	sk->sk_route_caps = dst_dev(dst)->features;
 	if (sk_is_tcp(sk)) {
 		struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -2632,7 +2632,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
 			sk->sk_gso_max_size = sk_dst_gso_max_size(sk, dst);
 			/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */
-			max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1);
+			max_segs = max_t(u32, READ_ONCE(dst_dev(dst)->gso_max_segs), 1);
 		}
 	}
 	sk->sk_gso_max_segs = max_segs;
Signature · 1 line
2.39.5
author maintainer
#183 lore raw

PATCH 177/627 wifi: iwlwifi: Fix error code in iwl_op_mode_dvm_start()

In reply to Greg Kroah-Hartman

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

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

From: Dan Carpenter <[email protected]>

[ Upstream commit cf80c02a9fdb6c5bc8508beb6a0f6a1294fc32f6 ]

Preserve the error code if iwl_setup_deferred_work() fails. The current code returns ERR_PTR(0) (which is NULL) on this path. I believe the missing error code potentially leads to a use after free involving debugfs.

Fixes 90a0d9f33996 ("iwlwifi: Add missing check for alloc_ordered_workqueue")
---
 drivers/net/wireless/intel/iwlwifi/dvm/main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/wireless/intel/iwlwifi/dvm/main.c +2 -1
index e015b83bb6e9..2b4dbebc71c2 100644
@@ -1467,7 +1467,8 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 	/********************
 	 * 6. Setup services
 	 ********************/
-	if (iwl_setup_deferred_work(priv))
+	err = iwl_setup_deferred_work(priv);
+	if (err)
 		goto out_uninit_drv;
 
 	iwl_setup_rx_handlers(priv);
Signature · 1 line
2.39.5
author maintainer
#184 lore raw

PATCH 178/627 kselftest/arm64: Fix check for setting new VLs in sve-ptrace

In reply to Greg Kroah-Hartman

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

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

From: Mark Brown <[email protected]>

[ Upstream commit 867446f090589626497638f70b10be5e61a0b925 ]

The check that the new vector length we set was the expected one was typoed to an assignment statement which for some reason the compilers didn't spot, most likely due to the macros involved.

---
 tools/testing/selftests/arm64/fp/sve-ptrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/arm64/fp/sve-ptrace.c +1 -1
index 577b6e05e860..c499d5789dd5 100644
@@ -253,7 +253,7 @@ static void ptrace_set_get_vl(pid_t child, const struct vec_type *type,
 		return;
 	}
 
-	ksft_test_result(new_sve->vl = prctl_vl, "Set %s VL %u\n",
+	ksft_test_result(new_sve->vl == prctl_vl, "Set %s VL %u\n",
 			 type->name, vl);
 
 	free(new_sve);
Signature · 1 line
2.39.5
author maintainer
#185 lore raw

PATCH 179/627 wifi: mt76: mt7925: fix off by one in mt7925_mcu_hw_scan()

In reply to Greg Kroah-Hartman

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

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

From: Dan Carpenter <[email protected]>

[ Upstream commit b3a431fe2e399b2e0cc5f43f7e9d63d63d3710ee ]

The ssid->ssids[] and sreq->ssids[] arrays have MT7925_RNR_SCAN_MAX_BSSIDS elements so this >= needs to be > to prevent an out of bounds access.

Fixes 8284815ca161 ("wifi: mt76: mt7925: add RNR scan support for 6GHz")
---
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +2 -2
index 8ac6fbb736ab..300c863f0e3e 100644
@@ -2916,7 +2916,7 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 	for (i = 0; i < sreq->n_ssids; i++) {
 		if (!sreq->ssids[i].ssid_len)
 			continue;
-		if (i > MT7925_RNR_SCAN_MAX_BSSIDS)
+		if (i >= MT7925_RNR_SCAN_MAX_BSSIDS)
 			break;
 
 		ssid->ssids[n_ssids].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len);
@@ -2933,7 +2933,7 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 		mt76_connac_mcu_build_rnr_scan_param(mdev, sreq);
 
 		for (j = 0; j < mdev->rnr.bssid_num; j++) {
-			if (j > MT7925_RNR_SCAN_MAX_BSSIDS)
+			if (j >= MT7925_RNR_SCAN_MAX_BSSIDS)
 				break;
 
 			tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_BSSID,
Signature · 1 line
2.39.5
author maintainer
#186 lore raw

PATCH 180/627 bpf: Ensure RCU lock is held around bpf_prog_ksym_find

In reply to Greg Kroah-Hartman

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

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

From: Kumar Kartikeya Dwivedi <[email protected]>

[ Upstream commit d090326860096df9dac6f27cff76d3f8df44d4f1 ]

Add a warning to ensure RCU lock is held around tree lookup, and then fix one of the invocations in bpf_stack_walker. The program has an active stack frame and won't disappear. Use the opportunity to remove unneeded invocation of is_bpf_text_address.

---
 kernel/bpf/core.c    |  5 ++++-
 kernel/bpf/helpers.c | 11 +++++++++--
 2 files changed, 13 insertions(+), 3 deletions(-)
kernel/bpf/core.c +4 -1
index c20babbf998f..93e49b0c218b 100644
@@ -778,7 +778,10 @@ bool is_bpf_text_address(unsigned long addr)
 
 struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
 {
-	struct bpf_ksym *ksym = bpf_ksym_find(addr);
+	struct bpf_ksym *ksym;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	ksym = bpf_ksym_find(addr);
 
 	return ksym && ksym->prog ?
 	       container_of(ksym, struct bpf_prog_aux, ksym)->prog :
kernel/bpf/helpers.c +9 -2
index ad6df48b540c..fdf8737542ac 100644
@@ -2943,9 +2943,16 @@ static bool bpf_stack_walker(void *cookie, u64 ip, u64 sp, u64 bp)
 	struct bpf_throw_ctx *ctx = cookie;
 	struct bpf_prog *prog;
 
-	if (!is_bpf_text_address(ip))
-		return !ctx->cnt;
+	/*
+	 * The RCU read lock is held to safely traverse the latch tree, but we
+	 * don't need its protection when accessing the prog, since it has an
+	 * active stack frame on the current stack trace, and won't disappear.
+	 */
+	rcu_read_lock();
 	prog = bpf_prog_ksym_find(ip);
+	rcu_read_unlock();
+	if (!prog)
+		return !ctx->cnt;
 	ctx->cnt++;
 	if (bpf_is_subprog(prog))
 		return true;
Signature · 1 line
2.39.5
author maintainer
#187 lore raw

PATCH 181/627 drm/msm/dpu: Fill in min_prefill_lines for SC8180X

In reply to Greg Kroah-Hartman

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

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

From: Konrad Dybcio <[email protected]>

[ Upstream commit 5136acc40afc0261802e5cb01b04f871bf6d876b ]

Based on the downstream release, predictably same value as for SM8150.

Fixes f3af2d6ee9ab ("drm/msm/dpu: Add SC8180x to hw catalog")

Patchwork: https://patchwork.freedesktop.org/patch/657794/

---
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h | 1 +
 1 file changed, 1 insertion(+)
drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +1 -0
index d6f8b1030c68..6c04f41f9bac 100644
@@ -383,6 +383,7 @@ static const struct dpu_perf_cfg sc8180x_perf_data = {
 	.min_core_ib = 2400000,
 	.min_llcc_ib = 800000,
 	.min_dram_ib = 800000,
+	.min_prefill_lines = 24,
 	.danger_lut_tbl = {0xf, 0xffff, 0x0},
 	.safe_lut_tbl = {0xfff0, 0xf000, 0xffff},
 	.qos_lut_tbl = {
Signature · 1 line
2.39.5
author maintainer
#188 lore raw

PATCH 182/627 m68k: Dont unregister boot console needlessly

In reply to Greg Kroah-Hartman

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

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

From: Finn Thain <[email protected]>

[ Upstream commit 83f672a7f69ec38b1bbb27221e342937f68c11c7 ]

When MACH_IS_MVME147, the boot console calls mvme147_scc_write() to generate console output. That will continue to work even after debug_cons_nputs() becomes unavailable so there's no need to unregister the boot console.

Take the opportunity to remove a repeated MACH_IS_* test. Use the actual .write method (instead of a wrapper) and test that pointer instead. This means adding an unused parameter to debug_cons_nputs() for consistency with the struct console API.

early_printk.c is only built when CONFIG_EARLY_PRINTK=y. As of late, head.S is only built when CONFIG_MMU_MOTOROLA=y. So let the former symbol depend on the latter, to obviate some ifdef conditionals.

---
 arch/m68k/Kconfig.debug         |  2 +-
 arch/m68k/kernel/early_printk.c | 42 +++++++++++----------------------
 arch/m68k/kernel/head.S         |  8 +++----
 3 files changed, 19 insertions(+), 33 deletions(-)
arch/m68k/Kconfig.debug +1 -1
index 30638a6e8edc..d036f903864c 100644
@@ -10,7 +10,7 @@ config BOOTPARAM_STRING
 
 config EARLY_PRINTK
 	bool "Early printk"
-	depends on !(SUN3 || M68000 || COLDFIRE)
+	depends on MMU_MOTOROLA
 	help
 	  Write kernel log output directly to a serial port.
 	  Where implemented, output goes to the framebuffer as well.
arch/m68k/kernel/early_printk.c +14 -28

65 lines not on this page · raw message

arch/m68k/kernel/head.S +4 -4
index 852255cf60de..ba22bc2f3d6d 100644
@@ -3263,8 +3263,8 @@ func_return	putn
  *	turns around and calls the internal routines.  This routine
  *	is used by the boot console.
  *
- *	The calling parameters are:
- *		void debug_cons_nputs(const char *str, unsigned length)
+ *	The function signature is -
+ *		void debug_cons_nputs(struct console *c, const char *s, unsigned int n)
  *
  *	This routine does NOT understand variable arguments only
  *	simple strings!
@@ -3273,8 +3273,8 @@ ENTRY(debug_cons_nputs)
 	moveml	%d0/%d1/%a0,%sp@-
 	movew	%sr,%sp@-
 	ori	#0x0700,%sr
-	movel	%sp@(18),%a0		/* fetch parameter */
-	movel	%sp@(22),%d1		/* fetch parameter */
+	movel	%sp@(22),%a0		/* char *s */
+	movel	%sp@(26),%d1		/* unsigned int n */
 	jra	2f
 1:
 #ifdef CONSOLE_DEBUG
Signature · 1 line
2.39.5
author maintainer
#189 lore raw

PATCH 183/627 refscale: Check that nreaders and loops multiplication doesnt overflow

In reply to Greg Kroah-Hartman

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

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

From: Artem Sadovnikov <[email protected]>

[ Upstream commit 005b6187705bc9723518ce19c5cb911fc1f7ef07 ]

The nreaders and loops variables are exposed as module parameters, which, in certain combinations, can lead to multiplication overflow.

Besides, loops parameter is defined as long, while through the code is used as int, which can cause truncation on 64-bit kernels and possible zeroes where they shouldn't appear.

Since code uses result of multiplication as int anyway, it only makes sense to replace loops with int. Multiplication overflow check is also added due to possible multiplication between two very big numbers.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes 653ed64b01dc ("refperf: Add a test to measure performance of read-side synchronization")
---
 kernel/rcu/refscale.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
kernel/rcu/refscale.c +7 -3
index f11a7c2af778..ab7fcdc94cc0 100644
@@ -85,7 +85,7 @@ torture_param(int, holdoff, IS_BUILTIN(CONFIG_RCU_REF_SCALE_TEST) ? 10 : 0,
 // Number of typesafe_lookup structures, that is, the degree of concurrency.
 torture_param(long, lookup_instances, 0, "Number of typesafe_lookup structures.");
 // Number of loops per experiment, all readers execute operations concurrently.
-torture_param(long, loops, 10000, "Number of loops per experiment.");
+torture_param(int, loops, 10000, "Number of loops per experiment.");
 // Number of readers, with -1 defaulting to about 75% of the CPUs.
 torture_param(int, nreaders, -1, "Number of readers, -1 for 75% of CPUs.");
 // Number of runs.
@@ -1140,7 +1140,7 @@ static void
 ref_scale_print_module_parms(const struct ref_scale_ops *cur_ops, const char *tag)
 {
 	pr_alert("%s" SCALE_FLAG
-		 "--- %s:  verbose=%d verbose_batched=%d shutdown=%d holdoff=%d lookup_instances=%ld loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
+		 "--- %s:  verbose=%d verbose_batched=%d shutdown=%d holdoff=%d lookup_instances=%ld loops=%d nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
 		 verbose, verbose_batched, shutdown, holdoff, lookup_instances, loops, nreaders, nruns, readdelay);
 }
 
@@ -1238,12 +1238,16 @@ ref_scale_init(void)
 	// Reader tasks (default to ~75% of online CPUs).
 	if (nreaders < 0)
 		nreaders = (num_online_cpus() >> 1) + (num_online_cpus() >> 2);
-	if (WARN_ONCE(loops <= 0, "%s: loops = %ld, adjusted to 1\n", __func__, loops))
+	if (WARN_ONCE(loops <= 0, "%s: loops = %d, adjusted to 1\n", __func__, loops))
 		loops = 1;
 	if (WARN_ONCE(nreaders <= 0, "%s: nreaders = %d, adjusted to 1\n", __func__, nreaders))
 		nreaders = 1;
 	if (WARN_ONCE(nruns <= 0, "%s: nruns = %d, adjusted to 1\n", __func__, nruns))
 		nruns = 1;
+	if (WARN_ONCE(loops > INT_MAX / nreaders,
+		      "%s: nreaders * loops will overflow, adjusted loops to %d",
+		      __func__, INT_MAX / nreaders))
+		loops = INT_MAX / nreaders;
 	reader_tasks = kcalloc(nreaders, sizeof(reader_tasks[0]),
 			       GFP_KERNEL);
 	if (!reader_tasks) {
Signature · 1 line
2.39.5
author maintainer
#190 lore raw

PATCH 184/627 wifi: mt76: mt7996: Fix secondary link lookup in mt7996_mcu_sta_mld_setup_tlv()

In reply to Greg Kroah-Hartman

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

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

From: Lorenzo Bianconi <[email protected]>

[ Upstream commit e8d7eef07199887161cd6f3c062406628781f8b6 ]

Use proper link_id value for secondary link lookup in mt7996_mcu_sta_mld_setup_tlv routine.

Fixes 00cef41d9d8f5 ("wifi: mt76: mt7996: Add mt7996_mcu_sta_mld_setup_tlv() and mt7996_mcu_sta_eht_mld_tlv()")
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +1 -2
index 994526c65bfc..dd4b7b8c34ea 100644
@@ -2326,8 +2326,7 @@ mt7996_mcu_sta_mld_setup_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 
 	if (nlinks > 1) {
 		link_id = __ffs(links & ~BIT(msta->deflink_id));
-		msta_link = mt76_dereference(msta->link[msta->deflink_id],
-					     &dev->mt76);
+		msta_link = mt76_dereference(msta->link[link_id], &dev->mt76);
 		if (!msta_link)
 			return;
 	}
Signature · 1 line
2.39.5
author maintainer
#191 lore raw

PATCH 185/627 wifi: mt76: mt7996: Fix possible OOB access in mt7996_tx()

In reply to Greg Kroah-Hartman

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

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

From: Lorenzo Bianconi <[email protected]>

[ Upstream commit 64cbf0d7ce9afe20666da90ec6ecaec6ba5ac64b ]

Fis possible Out-Of-Boundary access in mt7996_tx routine if link_id is set to IEEE80211_LINK_UNSPECIFIED

Fixes 3ce8acb86b661 ("wifi: mt76: mt7996: Update mt7996_tx to MLO support")
---
 .../net/wireless/mediatek/mt76/mt7996/main.c    | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)
drivers/net/wireless/mediatek/mt76/mt7996/main.c +12 -5
index 07dd75ce94a5..44b4e48e499d 100644
@@ -1216,10 +1216,17 @@ static void mt7996_tx(struct ieee80211_hw *hw,
 
 	if (vif) {
 		struct mt7996_vif *mvif = (void *)vif->drv_priv;
-		struct mt76_vif_link *mlink;
+		struct mt76_vif_link *mlink = &mvif->deflink.mt76;
 
-		mlink = rcu_dereference(mvif->mt76.link[link_id]);
-		if (mlink && mlink->wcid)
+		if (link_id < IEEE80211_LINK_UNSPECIFIED)
+			mlink = rcu_dereference(mvif->mt76.link[link_id]);
+
+		if (!mlink) {
+			ieee80211_free_txskb(hw, skb);
+			goto unlock;
+		}
+
+		if (mlink->wcid)
 			wcid = mlink->wcid;
 
 		if (mvif->mt76.roc_phy &&
@@ -1228,7 +1235,7 @@ static void mt7996_tx(struct ieee80211_hw *hw,
 			if (mphy->roc_link)
 				wcid = mphy->roc_link->wcid;
 		} else {
-			mphy = mt76_vif_link_phy(&mvif->deflink.mt76);
+			mphy = mt76_vif_link_phy(mlink);
 		}
 	}
 
@@ -1237,7 +1244,7 @@ static void mt7996_tx(struct ieee80211_hw *hw,
 		goto unlock;
 	}
 
-	if (control->sta) {
+	if (control->sta && link_id < IEEE80211_LINK_UNSPECIFIED) {
 		struct mt7996_sta *msta = (void *)control->sta->drv_priv;
 		struct mt7996_sta_link *msta_link;
 
Signature · 1 line
2.39.5
author maintainer
#192 lore raw

PATCH 186/627 wifi: mt76: mt7996: Fix valid_links bitmask in mt7996_mac_sta_{add,remove}

In reply to Greg Kroah-Hartman

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

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

From: Lorenzo Bianconi <[email protected]>

[ Upstream commit a59650a2270190905fdab79431140371feb35251 ]

sta->valid_links bitmask can be set even for non-MLO client.

Fixes dd82a9e02c054 ("wifi: mt76: mt7996: Rely on mt7996_sta_link in sta_add/sta_remove callbacks")
---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/wireless/mediatek/mt76/mt7996/main.c +2 -2
index 44b4e48e499d..f41b2c98bc45 100644
@@ -1061,7 +1061,7 @@ mt7996_mac_sta_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	unsigned long links = sta->mlo ? sta->valid_links : BIT(0);
+	unsigned long links = sta->valid_links ? sta->valid_links : BIT(0);
 	int err;
 
 	mutex_lock(&mdev->mutex);
@@ -1155,7 +1155,7 @@ mt7996_mac_sta_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 {
 	struct mt76_dev *mdev = mphy->dev;
 	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
-	unsigned long links = sta->mlo ? sta->valid_links : BIT(0);
+	unsigned long links = sta->valid_links ? sta->valid_links : BIT(0);
 
 	mutex_lock(&mdev->mutex);
 
Signature · 1 line
2.39.5
author maintainer
#193 lore raw

PATCH 187/627 drm/amdkfd: Move the process suspend and resume out of full access

In reply to Greg Kroah-Hartman

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

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

From: Emily Deng <[email protected]>

[ Upstream commit 54f7a24e1437d66c9ff36d727a9dff1beeeab429 ]

For the suspend and resume process, exclusive access is not required. Therefore, it can be moved out of the full access section to reduce the duration of exclusive access.

v3:
Move suspend processes before hardware fini.
Remove twice call for bare metal.

v4:
Refine code

Stable-dep-of: 14b2d71a9a24 ("drm/amdgpu/gfx10: fix KGQ reset sequence")

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c    | 24 +++++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h    | 25 ++++++---
 .../drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c   |  4 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c    | 11 ++--
 drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c      |  4 +-
 drivers/gpu/drm/amd/amdkfd/kfd_device.c       | 54 ++++++++++++-------
 6 files changed, 86 insertions(+), 36 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +20 -4
index d8ac4b1051a8..fe282b855734 100644
@@ -248,18 +248,34 @@ void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 		kgd2kfd_interrupt(adev->kfd.dev, ih_ring_entry);
 }
 
-void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm)
+void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool suspend_proc)
 {
 	if (adev->kfd.dev)
-		kgd2kfd_suspend(adev->kfd.dev, run_pm);
+		kgd2kfd_suspend(adev->kfd.dev, suspend_proc);
 }
 
-int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm)
+int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool resume_proc)
 {
 	int r = 0;
 
 	if (adev->kfd.dev)
-		r = kgd2kfd_resume(adev->kfd.dev, run_pm);
+		r = kgd2kfd_resume(adev->kfd.dev, resume_proc);
+
+	return r;
+}
+
+void amdgpu_amdkfd_suspend_process(struct amdgpu_device *adev)
+{
+	if (adev->kfd.dev)
+		kgd2kfd_suspend_process(adev->kfd.dev);
+}
+
+int amdgpu_amdkfd_resume_process(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd.dev)
+		r = kgd2kfd_resume_process(adev->kfd.dev);
 
 	return r;
 }
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +19 -6
index b6ca41859b53..b7c3ec483407 100644
@@ -154,8 +154,10 @@ struct amdkfd_process_info {
 int amdgpu_amdkfd_init(void);
 void amdgpu_amdkfd_fini(void);
 
-void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm);
-int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm);
+void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool suspend_proc);
+int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool resume_proc);
+void amdgpu_amdkfd_suspend_process(struct amdgpu_device *adev);
+int amdgpu_amdkfd_resume_process(struct amdgpu_device *adev);
 void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 			const void *ih_ring_entry);
 void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev);
@@ -411,8 +413,10 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf);
 bool kgd2kfd_device_init(struct kfd_dev *kfd,
 			 const struct kgd2kfd_shared_resources *gpu_resources);
 void kgd2kfd_device_exit(struct kfd_dev *kfd);
-void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
-int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
+void kgd2kfd_suspend(struct kfd_dev *kfd, bool suspend_proc);
+int kgd2kfd_resume(struct kfd_dev *kfd, bool resume_proc);
+void kgd2kfd_suspend_process(struct kfd_dev *kfd);
+int kgd2kfd_resume_process(struct kfd_dev *kfd);
 int kgd2kfd_pre_reset(struct kfd_dev *kfd,
 		      struct amdgpu_reset_context *reset_context);
 int kgd2kfd_post_reset(struct kfd_dev *kfd);
@@ -454,11 +458,20 @@ static inline void kgd2kfd_device_exit(struct kfd_dev *kfd)
 {
 }
 
-static inline void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
+static inline void kgd2kfd_suspend(struct kfd_dev *kfd, bool suspend_proc)
 {
 }
 
-static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
+static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool resume_proc)
+{
+	return 0;
+}
+
+static inline void kgd2kfd_suspend_process(struct kfd_dev *kfd)
+{
+}
+
+static inline int kgd2kfd_resume_process(struct kfd_dev *kfd)
 {
 	return 0;
 }
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c +2 -2
index ffbaa8bc5eea..1105a09e55dc 100644
@@ -320,7 +320,7 @@ static void set_barrier_auto_waitcnt(struct amdgpu_device *adev, bool enable_wai
 	if (!down_read_trylock(&adev->reset_domain->sem))
 		return;
 
-	amdgpu_amdkfd_suspend(adev, false);
+	amdgpu_amdkfd_suspend(adev, true);
 
 	if (suspend_resume_compute_scheduler(adev, true))
 		goto out;
@@ -333,7 +333,7 @@ static void set_barrier_auto_waitcnt(struct amdgpu_device *adev, bool enable_wai
 out:
 	suspend_resume_compute_scheduler(adev, false);
 
-	amdgpu_amdkfd_resume(adev, false);
+	amdgpu_amdkfd_resume(adev, true);
 
 	up_read(&adev->reset_domain->sem);
 }
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +8 -3
index aa32df7e2fb2..54ea8e8d7812 100644
@@ -3518,7 +3518,7 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 
-	amdgpu_amdkfd_suspend(adev, false);
+	amdgpu_amdkfd_suspend(adev, true);
 	amdgpu_userq_suspend(adev);
 
 	/* Workaround for ASICs need to disable SMC first */
@@ -5055,6 +5055,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients)
 	adev->in_suspend = true;
 
 	if (amdgpu_sriov_vf(adev)) {
+		if (!adev->in_s0ix && !adev->in_runpm)
+			amdgpu_amdkfd_suspend_process(adev);
 		amdgpu_virt_fini_data_exchange(adev);
 		r = amdgpu_virt_request_full_gpu(adev, false);
 		if (r)
@@ -5074,7 +5076,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients)
 	amdgpu_device_ip_suspend_phase1(adev);
 
 	if (!adev->in_s0ix) {
-		amdgpu_amdkfd_suspend(adev, adev->in_runpm);
+		amdgpu_amdkfd_suspend(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm);
 		amdgpu_userq_suspend(adev);
 	}
 
@@ -5140,7 +5142,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool notify_clients)
 	}
 
 	if (!adev->in_s0ix) {
-		r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
+		r = amdgpu_amdkfd_resume(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm);
 		if (r)
 			goto exit;
 
@@ -5159,6 +5161,9 @@ int amdgpu_device_resume(struct drm_device *dev, bool notify_clients)
 	if (amdgpu_sriov_vf(adev)) {
 		amdgpu_virt_init_data_exchange(adev);
 		amdgpu_virt_release_full_gpu(adev, true);
+
+		if (!adev->in_s0ix && !r && !adev->in_runpm)
+			r = amdgpu_amdkfd_resume_process(adev);
 	}
 
 	if (r)
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +2 -2
index bb82c652e4c0..5de2f047c534 100644
@@ -1681,9 +1681,9 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 	if (!(adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
 		return -EOPNOTSUPP;
 
-	amdgpu_amdkfd_suspend(adev, false);
+	amdgpu_amdkfd_suspend(adev, true);
 	r = amdgpu_sdma_reset_engine(adev, id);
-	amdgpu_amdkfd_resume(adev, false);
+	amdgpu_amdkfd_resume(adev, true);
 
 	return r;
 }
drivers/gpu/drm/amd/amdkfd/kfd_device.c +35 -19

84 lines not on this page · raw message

Signature · 1 line
2.39.5
author maintainer
#194 lore raw

PATCH 188/627 drm/amdgpu: rework queue reset scheduler interaction

In reply to Greg Kroah-Hartman

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

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

From: Christian König <[email protected]>

[ Upstream commit 821aacb2dcf0d1fbc3c0f7803b6089b01addb8bf ]

Stopping the scheduler for queue reset is generally a good idea because it prevents any worker from touching the ring buffer.

Stable-dep-of: 14b2d71a9a24 ("drm/amdgpu/gfx10: fix KGQ reset sequence")

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 35 ++++++++++++++-----------
 1 file changed, 20 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +20 -15
index ddb9d3269357..9ea3bce01faf 100644
@@ -91,8 +91,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	struct amdgpu_job *job = to_amdgpu_job(s_job);
 	struct amdgpu_task_info *ti;
 	struct amdgpu_device *adev = ring->adev;
-	int idx;
-	int r;
+	bool set_error = false;
+	int idx, r;
 
 	if (!drm_dev_enter(adev_to_drm(adev), &idx)) {
 		dev_info(adev->dev, "%s - device unplugged skipping recovery on scheduler:%s",
@@ -136,10 +136,12 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	} else if (amdgpu_gpu_recovery && ring->funcs->reset) {
 		bool is_guilty;
 
-		dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name);
-		/* stop the scheduler, but don't mess with the
-		 * bad job yet because if ring reset fails
-		 * we'll fall back to full GPU reset.
+		dev_err(adev->dev, "Starting %s ring reset\n",
+			s_job->sched->name);
+
+		/*
+		 * Stop the scheduler to prevent anybody else from touching the
+		 * ring buffer.
 		 */
 		drm_sched_wqueue_stop(&ring->sched);
 
@@ -152,26 +154,29 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 		else
 			is_guilty = true;
 
-		if (is_guilty)
+		if (is_guilty) {
 			dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
+			set_error = true;
+		}
 
 		r = amdgpu_ring_reset(ring, job->vmid);
 		if (!r) {
-			if (amdgpu_ring_sched_ready(ring))
-				drm_sched_stop(&ring->sched, s_job);
 			if (is_guilty) {
 				atomic_inc(&ring->adev->gpu_reset_counter);
 				amdgpu_fence_driver_force_completion(ring);
 			}
-			if (amdgpu_ring_sched_ready(ring))
-				drm_sched_start(&ring->sched, 0);
-			dev_err(adev->dev, "Ring %s reset succeeded\n", ring->sched.name);
-			drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE);
+			drm_sched_wqueue_start(&ring->sched);
+			dev_err(adev->dev, "Ring %s reset succeeded\n",
+				ring->sched.name);
+			drm_dev_wedged_event(adev_to_drm(adev),
+					     DRM_WEDGE_RECOVERY_NONE);
 			goto exit;
 		}
-		dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name);
+		dev_err(adev->dev, "Ring %s reset failed\n", ring->sched.name);
 	}
-	dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
+
+	if (!set_error)
+		dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
 
 	if (amdgpu_device_should_recover_gpu(ring->adev)) {
 		struct amdgpu_reset_context reset_context;
Signature · 1 line
2.39.5
author maintainer
#195 lore raw

PATCH 189/627 drm/amdgpu: move force completion into ring resets

In reply to Greg Kroah-Hartman

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

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

From: Alex Deucher <[email protected]>

[ Upstream commit 2dee58ca471dae05c473270d0fb74efe01a78ccb ]

Move the force completion handling into each ring reset function so that each engine can determine whether or not it needs to force completion on the jobs in the ring.

Stable-dep-of: 14b2d71a9a24 ("drm/amdgpu/gfx10: fix KGQ reset sequence")

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c  |  4 +--
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c   | 12 +++++++--
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c   | 12 +++++++--
 drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c   | 12 +++++++--
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c    |  7 +++++-
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c  |  7 +++++-
 drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c   |  8 +++++-
 drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c   |  8 +++++-
 drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c   |  8 +++++-
 drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c   |  8 +++++-
 drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c |  8 +++++-
 drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c |  8 +++++-
 drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 31 +++++++++++++++++++++---
 drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c   |  5 +++-
 drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c   |  5 +++-
 drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c   |  6 ++++-
 drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c   |  6 ++++-
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c    |  7 +++++-
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c  |  6 +++--
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c  |  7 +++++-
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c  |  7 +++++-
 21 files changed, 152 insertions(+), 30 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +1 -3
index 9ea3bce01faf..3528a27c7c1d 100644
@@ -161,10 +161,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 
 		r = amdgpu_ring_reset(ring, job->vmid);
 		if (!r) {
-			if (is_guilty) {
+			if (is_guilty)
 				atomic_inc(&ring->adev->gpu_reset_counter);
-				amdgpu_fence_driver_force_completion(ring);
-			}
 			drm_sched_wqueue_start(&ring->sched);
 			dev_err(adev->dev, "Ring %s reset succeeded\n",
 				ring->sched.name);
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +10 -2
index 75ea071744eb..777e383d75e2 100644
@@ -9575,7 +9575,11 @@ static int gfx_v10_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
 		return r;
 	}
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
@@ -9647,7 +9651,11 @@ static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static void gfx_v10_ip_print(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +10 -2
index ec9b84f92d46..e632e97d63be 100644
@@ -6840,7 +6840,11 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
 		return r;
 	}
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int gfx_v11_0_reset_compute_pipe(struct amdgpu_ring *ring)
@@ -7000,7 +7004,11 @@ static int gfx_v11_0_reset_kcq(struct amdgpu_ring *ring, unsigned int vmid)
 		return r;
 	}
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static void gfx_v11_ip_print(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +10 -2
index 1234c8d64e20..50f04c2c0b8c 100644
@@ -5335,7 +5335,11 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
 		return r;
 	}
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int gfx_v12_0_reset_compute_pipe(struct amdgpu_ring *ring)
@@ -5448,7 +5452,11 @@ static int gfx_v12_0_reset_kcq(struct amdgpu_ring *ring, unsigned int vmid)
 		return r;
 	}
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static void gfx_v12_0_ring_begin_use(struct amdgpu_ring *ring)
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +6 -1
index ad9be3656653..23f998181561 100644
@@ -7286,7 +7286,12 @@ static int gfx_v9_0_reset_kcq(struct amdgpu_ring *ring,
 		DRM_ERROR("fail to remap queue\n");
 		return r;
 	}
-	return amdgpu_ring_test_ring(ring);
+
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static void gfx_v9_ip_print(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +6 -1
index c233edf60569..264b37e85696 100644
@@ -3619,7 +3619,12 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
 		dev_err(adev->dev, "fail to remap queue\n");
 		return r;
 	}
-	return amdgpu_ring_test_ring(ring);
+
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 enum amdgpu_gfx_cp_ras_mem_id {
drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +7 -1
index 4cde8a8bcc83..49620fbf6c7a 100644
@@ -766,9 +766,15 @@ static int jpeg_v2_0_process_interrupt(struct amdgpu_device *adev,
 
 static int jpeg_v2_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 {
+	int r;
+
 	jpeg_v2_0_stop(ring->adev);
 	jpeg_v2_0_start(ring->adev);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v2_0_ip_funcs = {
drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +7 -1
index 8b39e114f3be..98ae9c0e83f7 100644
@@ -645,9 +645,15 @@ static int jpeg_v2_5_process_interrupt(struct amdgpu_device *adev,
 
 static int jpeg_v2_5_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 {
+	int r;
+
 	jpeg_v2_5_stop_inst(ring->adev, ring->me);
 	jpeg_v2_5_start_inst(ring->adev, ring->me);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v2_5_ip_funcs = {
drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +7 -1
index 2f8510c2986b..7fb599430365 100644
@@ -557,9 +557,15 @@ static int jpeg_v3_0_process_interrupt(struct amdgpu_device *adev,
 
 static int jpeg_v3_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 {
+	int r;
+
 	jpeg_v3_0_stop(ring->adev);
 	jpeg_v3_0_start(ring->adev);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v3_0_ip_funcs = {
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +7 -1
index f17ec5414fd6..a6612c942b93 100644
@@ -722,12 +722,18 @@ static int jpeg_v4_0_process_interrupt(struct amdgpu_device *adev,
 
 static int jpeg_v4_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 {
+	int r;
+
 	if (amdgpu_sriov_vf(ring->adev))
 		return -EINVAL;
 
 	jpeg_v4_0_stop(ring->adev);
 	jpeg_v4_0_start(ring->adev);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v4_0_ip_funcs = {
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +7 -1
index 79e342d5ab28..90d773dbe337 100644
@@ -1145,12 +1145,18 @@ static void jpeg_v4_0_3_core_stall_reset(struct amdgpu_ring *ring)
 
 static int jpeg_v4_0_3_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 {
+	int r;
+
 	if (amdgpu_sriov_vf(ring->adev))
 		return -EOPNOTSUPP;
 
 	jpeg_v4_0_3_core_stall_reset(ring);
 	jpeg_v4_0_3_start_jrbc(ring);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v4_0_3_ip_funcs = {
drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c +7 -1
index 3b6f65a25646..7cad77a968f1 100644
@@ -836,12 +836,18 @@ static void jpeg_v5_0_1_core_stall_reset(struct amdgpu_ring *ring)
 
 static int jpeg_v5_0_1_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 {
+	int r;
+
 	if (amdgpu_sriov_vf(ring->adev))
 		return -EOPNOTSUPP;
 
 	jpeg_v5_0_1_core_stall_reset(ring);
 	jpeg_v5_0_1_init_jrbc(ring);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v5_0_1_ip_funcs = {
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +27 -4
index 5de2f047c534..9f0ad1199431 100644
@@ -1674,6 +1674,7 @@ static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring)
 
 static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 {
+	bool is_guilty = ring->funcs->is_guilty(ring);
 	struct amdgpu_device *adev = ring->adev;
 	u32 id = ring->me;
 	int r;
@@ -1684,8 +1685,13 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 	amdgpu_amdkfd_suspend(adev, true);
 	r = amdgpu_sdma_reset_engine(adev, id);
 	amdgpu_amdkfd_resume(adev, true);
+	if (r)
+		return r;
 
-	return r;
+	if (is_guilty)
+		amdgpu_fence_driver_force_completion(ring);
+
+	return 0;
 }
 
 static int sdma_v4_4_2_stop_queue(struct amdgpu_ring *ring)
@@ -1729,8 +1735,8 @@ static int sdma_v4_4_2_stop_queue(struct amdgpu_ring *ring)
 static int sdma_v4_4_2_restore_queue(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u32 inst_mask;
-	int i;
+	u32 inst_mask, tmp_mask;
+	int i, r;
 
 	inst_mask = 1 << ring->me;
 	udelay(50);
@@ -1747,7 +1753,24 @@ static int sdma_v4_4_2_restore_queue(struct amdgpu_ring *ring)
 		return -ETIMEDOUT;
 	}
 
-	return sdma_v4_4_2_inst_start(adev, inst_mask, true);
+	r = sdma_v4_4_2_inst_start(adev, inst_mask, true);
+	if (r)
+		return r;
+
+	tmp_mask = inst_mask;
+	for_each_inst(i, tmp_mask) {
+		ring = &adev->sdma.instance[i].ring;
+
+		amdgpu_fence_driver_force_completion(ring);
+
+		if (adev->sdma.has_page_queue) {
+			struct amdgpu_ring *page = &adev->sdma.instance[i].page;
+
+			amdgpu_fence_driver_force_completion(page);
+		}
+	}
+
+	return r;
 }
 
 static int sdma_v4_4_2_set_trap_irq_state(struct amdgpu_device *adev,
drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +4 -1
index 37f4b5b4a098..b43d6cb8a0d4 100644
@@ -1616,7 +1616,10 @@ static int sdma_v5_0_restore_queue(struct amdgpu_ring *ring)
 
 	r = sdma_v5_0_gfx_resume_instance(adev, inst_id, true);
 	amdgpu_gfx_rlc_exit_safe_mode(adev, 0);
-	return r;
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int sdma_v5_0_ring_preempt_ib(struct amdgpu_ring *ring)
drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +4 -1
index 0b40411b92a0..a88aa53e887c 100644
@@ -1532,7 +1532,10 @@ static int sdma_v5_2_restore_queue(struct amdgpu_ring *ring)
 	r = sdma_v5_2_gfx_resume_instance(adev, inst_id, true);
 
 	amdgpu_gfx_rlc_exit_safe_mode(adev, 0);
-	return r;
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int sdma_v5_2_ring_preempt_ib(struct amdgpu_ring *ring)
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +5 -1
index a9bdf8d61d6c..041bca58add5 100644
@@ -1572,7 +1572,11 @@ static int sdma_v6_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 	if (r)
 		return r;
 
-	return sdma_v6_0_gfx_resume_instance(adev, i, true);
+	r = sdma_v6_0_gfx_resume_instance(adev, i, true);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int sdma_v6_0_set_trap_irq_state(struct amdgpu_device *adev,
drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +5 -1
index 86903eccbd4e..b4167f23c02d 100644
@@ -824,7 +824,11 @@ static int sdma_v7_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 	if (r)
 		return r;
 
-	return sdma_v7_0_gfx_resume_instance(adev, i, true);
+	r = sdma_v7_0_gfx_resume_instance(adev, i, true);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 /**
drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +6 -1
index b5071f77f78d..46c329a1b2f5 100644
@@ -1971,6 +1971,7 @@ static int vcn_v4_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];
+	int r;
 
 	if (!(adev->vcn.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
 		return -EOPNOTSUPP;
@@ -1978,7 +1979,11 @@ static int vcn_v4_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 	vcn_v4_0_stop(vinst);
 	vcn_v4_0_start(vinst);
 
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = {
drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +4 -2
index 5a33140f5723..faba11166efb 100644
@@ -1621,8 +1621,10 @@ static int vcn_v4_0_3_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 	vcn_v4_0_3_hw_init_inst(vinst);
 	vcn_v4_0_3_start_dpg_mode(vinst, adev->vcn.inst[ring->me].indirect_sram);
 	r = amdgpu_ring_test_helper(ring);
-
-	return r;
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = {
drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +6 -1
index 16ade84facc7..af29a8e141a4 100644
@@ -1469,6 +1469,7 @@ static int vcn_v4_0_5_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];
+	int r;
 
 	if (!(adev->vcn.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
 		return -EOPNOTSUPP;
@@ -1476,7 +1477,11 @@ static int vcn_v4_0_5_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 	vcn_v4_0_5_stop(vinst);
 	vcn_v4_0_5_start(vinst);
 
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = {
drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +6 -1
index f8e3f0b882da..216324f6da85 100644
@@ -1196,6 +1196,7 @@ static int vcn_v5_0_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];
+	int r;
 
 	if (!(adev->vcn.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
 		return -EOPNOTSUPP;
@@ -1203,7 +1204,11 @@ static int vcn_v5_0_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
 	vcn_v5_0_0_stop(vinst);
 	vcn_v5_0_0_start(vinst);
 
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amdgpu_ring_funcs vcn_v5_0_0_unified_ring_vm_funcs = {
Signature · 1 line
2.39.5
author maintainer
#196 lore raw

PATCH 190/627 drm/amdgpu/gfx10: fix KGQ reset sequence

In reply to Greg Kroah-Hartman

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

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

From: Alex Deucher <[email protected]>

[ Upstream commit 14b2d71a9a24727f1b9f2131ed5eb2e345840a3a ]

Need to reinit the ring before remapping it and all of the KIQ handling needs to be within the kiq lock.

Fixes 1741281a157f ("drm/amdgpu/gfx10: add ring reset callbacks")
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +15 -5
index 777e383d75e2..e7df0487eaae 100644
@@ -9540,7 +9540,7 @@ static int gfx_v10_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
 
 	spin_lock_irqsave(&kiq->ring_lock, flags);
 
-	if (amdgpu_ring_alloc(kiq_ring, 5 + 7 + 7 + kiq->pmf->map_queues_size)) {
+	if (amdgpu_ring_alloc(kiq_ring, 5 + 7 + 7)) {
 		spin_unlock_irqrestore(&kiq->ring_lock, flags);
 		return -ENOMEM;
 	}
@@ -9560,12 +9560,9 @@ static int gfx_v10_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
 			       0, 1, 0x20);
 	gfx_v10_0_ring_emit_reg_wait(kiq_ring,
 				     SOC15_REG_OFFSET(GC, 0, mmCP_VMID_RESET), 0, 0xffffffff);
-	kiq->pmf->kiq_map_queues(kiq_ring, ring);
 	amdgpu_ring_commit(kiq_ring);
-
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
-
 	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r)
 		return r;
 
@@ -9575,6 +9572,19 @@ static int gfx_v10_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
 		return r;
 	}
 
+	spin_lock_irqsave(&kiq->ring_lock, flags);
+
+	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->map_queues_size)) {
+		spin_unlock_irqrestore(&kiq->ring_lock, flags);
+		return -ENOMEM;
+	}
+	kiq->pmf->kiq_map_queues(kiq_ring, ring);
+	amdgpu_ring_commit(kiq_ring);
+	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
+	if (r)
+		return r;
+
 	r = amdgpu_ring_test_ring(ring);
 	if (r)
 		return r;
Signature · 1 line
2.39.5
author maintainer
#197 lore raw

PATCH 191/627 drm/amd/pm/powerplay/hwmgr/smu_helper: fix order of mask and value

In reply to Greg Kroah-Hartman

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

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

From: Fedor Pchelkin <[email protected]>

[ Upstream commit a54e4639c4ef37a0241bac7d2a77f2e6ffb57099 ]

There is a small typo in phm_wait_on_indirect_register().

Swap mask and value arguments provided to phm_wait_on_register() so that they satisfy the function signature and actual usage scheme.

Found by Linux Verification Center (linuxtesting.org) with Svace static analysis tool.

In practice this doesn't fix any issues because the only place this function is used uses the same value for the value and mask.

Fixes 3bace3591493 ("drm/amd/powerplay: add hardware manager sub-component")
---
 drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c +1 -1
index 79a566f3564a..c305ea4ec17d 100644
@@ -149,7 +149,7 @@ int phm_wait_on_indirect_register(struct pp_hwmgr *hwmgr,
 	}
 
 	cgs_write_register(hwmgr->device, indirect_port, index);
-	return phm_wait_on_register(hwmgr, indirect_port + 1, mask, value);
+	return phm_wait_on_register(hwmgr, indirect_port + 1, value, mask);
 }
 
 int phm_wait_for_register_unequal(struct pp_hwmgr *hwmgr,
Signature · 1 line
2.39.5
author maintainer
#198 lore raw

PATCH 192/627 Revert "drm/amdgpu: fix slab-use-after-free in amdgpu_userq_mgr_fini"

In reply to Greg Kroah-Hartman

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

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

From: Vitaly Prosyak <[email protected]>

[ Upstream commit a73345b866ff8bbd93135af667c973a8fb4b2c40 ]

This reverts commit 5fb90421fa0fbe0a968274912101fe917bf1c47b.

The original patch moved amdgpu_userq_mgr_fini() to the driver's postclose callback, which is called after drm_gem_release() in the DRM file cleanup sequence.If a user application crashes or aborts without cleaning up its user queues, 'drm_gem_release()` may free GEM objects that are still referenced by active user queues, leading to use-after-free. By reverting, we ensure that user queues are disabled and cleaned up before any GEM objects are released, preventing this class of bug. However, this reintroduces a race during PCI hot-unplug, where device removal can race with per-file cleanup, leading to use-after-free in suspend/unplug paths. This will be fixed in the next patch.

Fixes 5fb90421fa0f ("drm/amdgpu: fix slab-use-after-free in amdgpu_userq_mgr_fini+0x70c")
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 16 +++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c |  3 ---
 2 files changed, 15 insertions(+), 4 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +15 -1
index 501bb82f2a37..4db92e0a60da 100644
@@ -2906,6 +2906,20 @@ static int amdgpu_pmops_runtime_idle(struct device *dev)
 	return ret;
 }
 
+static int amdgpu_drm_release(struct inode *inode, struct file *filp)
+{
+	struct drm_file *file_priv = filp->private_data;
+	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
+
+	if (fpriv) {
+		fpriv->evf_mgr.fd_closing = true;
+		amdgpu_eviction_fence_destroy(&fpriv->evf_mgr);
+		amdgpu_userq_mgr_fini(&fpriv->userq_mgr);
+	}
+
+	return drm_release(inode, filp);
+}
+
 long amdgpu_drm_ioctl(struct file *filp,
 		      unsigned int cmd, unsigned long arg)
 {
@@ -2957,7 +2971,7 @@ static const struct file_operations amdgpu_driver_kms_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
 	.flush = amdgpu_flush,
-	.release = drm_release,
+	.release = amdgpu_drm_release,
 	.unlocked_ioctl = amdgpu_drm_ioctl,
 	.mmap = drm_gem_mmap,
 	.poll = drm_poll,
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +0 -3
index 195ed81d39ff..d2ce7d86dbc8 100644
@@ -1501,9 +1501,6 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 		amdgpu_vm_bo_del(adev, fpriv->prt_va);
 		amdgpu_bo_unreserve(pd);
 	}
-	fpriv->evf_mgr.fd_closing = true;
-	amdgpu_eviction_fence_destroy(&fpriv->evf_mgr);
-	amdgpu_userq_mgr_fini(&fpriv->userq_mgr);
 
 	amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr);
 	amdgpu_vm_fini(adev, &fpriv->vm);
Signature · 1 line
2.39.5
author maintainer
#199 lore raw

PATCH 193/627 drm/amdgpu: fix use-after-free in amdgpu_userq_suspend+0x51a/0x5a0

In reply to Greg Kroah-Hartman

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

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

From: Vitaly Prosyak <[email protected]>

[ Upstream commit a886d26f2c8f9e3f3c1869ae368d09c75daac553 ]

[ +0.000020] BUG: KASAN: slab-use-after-free in amdgpu_userq_suspend+0x51a/0x5a0 [amdgpu] [ +0.000817] Read of size 8 at addr ffff88812eec8c58 by task amd_pci_unplug/1733

[  +0.000027] CPU: 10 UID: 0 PID: 1733 Comm: amd_pci_unplug Tainted: G        W          6.14.0+ #2
[  +0.000009] Tainted: [W]=WARN
[  +0.000003] Hardware name: ASUS System Product Name/ROG STRIX B550-F GAMING (WI-FI), BIOS 1401 12/03/2020
[  +0.000004] Call Trace:
[  +0.000004]  <TASK>
[  +0.000003]  dump_stack_lvl+0x76/0xa0
[  +0.000011]  print_report+0xce/0x600
[  +0.000009]  ? srso_return_thunk+0x5/0x5f
[  +0.000006]  ? kasan_complete_mode_report_info+0x76/0x200
[  +0.000007]  ? kasan_addr_to_slab+0xd/0xb0
[  +0.000006]  ? amdgpu_userq_suspend+0x51a/0x5a0 [amdgpu]
[  +0.000707]  kasan_report+0xbe/0x110
[  +0.000006]  ? amdgpu_userq_suspend+0x51a/0x5a0 [amdgpu]
[  +0.000541]  __asan_report_load8_noabort+0x14/0x30
[  +0.000005]  amdgpu_userq_suspend+0x51a/0x5a0 [amdgpu]
[  +0.000535]  ? stop_cpsch+0x396/0x600 [amdgpu]
[  +0.000556]  ? stop_cpsch+0x429/0x600 [amdgpu]
[  +0.000536]  ? __pfx_amdgpu_userq_suspend+0x10/0x10 [amdgpu]
[  +0.000536]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? kgd2kfd_suspend+0x132/0x1d0 [amdgpu]
[  +0.000542]  amdgpu_device_fini_hw+0x581/0xe90 [amdgpu]
[  +0.000485]  ? down_write+0xbb/0x140
[  +0.000007]  ? __mutex_unlock_slowpath.constprop.0+0x317/0x360
[  +0.000005]  ? __pfx_amdgpu_device_fini_hw+0x10/0x10 [amdgpu]
[  +0.000482]  ? __kasan_check_write+0x14/0x30
[  +0.000004]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? up_write+0x55/0xb0
[  +0.000007]  ? srso_return_thunk+0x5/0x5f
[  +0.000005]  ? blocking_notifier_chain_unregister+0x6c/0xc0
[  +0.000008]  amdgpu_driver_unload_kms+0x69/0x90 [amdgpu]
[  +0.000484]  amdgpu_pci_remove+0x93/0x130 [amdgpu]
[  +0.000482]  pci_device_remove+0xae/0x1e0
[  +0.000008]  device_remove+0xc7/0x180
[  +0.000008]  device_release_driver_internal+0x3d4/0x5a0
[  +0.000007]  device_release_driver+0x12/0x20
[  +0.000004]  pci_stop_bus_device+0x104/0x150
[  +0.000006]  pci_stop_and_remove_bus_device_locked+0x1b/0x40
[  +0.000005]  remove_store+0xd7/0xf0
[  +0.000005]  ? __pfx_remove_store+0x10/0x10
[  +0.000006]  ? __pfx__copy_from_iter+0x10/0x10
[  +0.000006]  ? __pfx_dev_attr_store+0x10/0x10
[  +0.000006]  dev_attr_store+0x3f/0x80
[  +0.000006]  sysfs_kf_write+0x125/0x1d0
[  +0.000004]  ? srso_return_thunk+0x5/0x5f
[  +0.000005]  ? __kasan_check_write+0x14/0x30
[  +0.000005]  kernfs_fop_write_iter+0x2ea/0x490
[  +0.000005]  ? rw_verify_area+0x70/0x420
[  +0.000005]  ? __pfx_kernfs_fop_write_iter+0x10/0x10
[  +0.000006]  vfs_write+0x90d/0xe70
[  +0.000005]  ? srso_return_thunk+0x5/0x5f
[  +0.000005]  ? __pfx_vfs_write+0x10/0x10
[  +0.000004]  ? local_clock+0x15/0x30
[  +0.000008]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? __kasan_slab_free+0x5f/0x80
[  +0.000005]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? __kasan_check_read+0x11/0x20
[  +0.000004]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? fdget_pos+0x1d3/0x500
[  +0.000007]  ksys_write+0x119/0x220
[  +0.000005]  ? putname+0x1c/0x30
[  +0.000006]  ? __pfx_ksys_write+0x10/0x10
[  +0.000007]  __x64_sys_write+0x72/0xc0
[  +0.000006]  x64_sys_call+0x18ab/0x26f0
[  +0.000006]  do_syscall_64+0x7c/0x170
[  +0.000004]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? __pfx___x64_sys_openat+0x10/0x10
[  +0.000006]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? __kasan_check_read+0x11/0x20
[  +0.000003]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? fpregs_assert_state_consistent+0x21/0xb0
[  +0.000006]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? syscall_exit_to_user_mode+0x4e/0x240
[  +0.000005]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? do_syscall_64+0x88/0x170
[  +0.000003]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? irqentry_exit+0x43/0x50
[  +0.000004]  ? srso_return_thunk+0x5/0x5f
[  +0.000004]  ? exc_page_fault+0x7c/0x110
[  +0.000006]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  +0.000006] RIP: 0033:0x7480c0b14887
[  +0.000005] Code: 10 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24
[  +0.000005] RSP: 002b:00007fff142b0058 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[  +0.000006] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007480c0b14887
[  +0.000003] RDX: 0000000000000001 RSI: 00007480c0e7365a RDI: 0000000000000004
[  +0.000003] RBP: 00007fff142b0080 R08: 0000563b2e73c170 R09: 0000000000000000
[  +0.000003] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fff142b02f8
[  +0.000003] R13: 0000563b159a72a9 R14: 0000563b159a9d48 R15: 00007480c0f19040
[  +0.000008]  </TASK>
[  +0.000445] Allocated by task 427 on cpu 5 at 29.342331s:
[  +0.000011]  kasan_save_stack+0x28/0x60
[  +0.000006]  kasan_save_track+0x18/0x70
[  +0.000006]  kasan_save_alloc_info+0x38/0x60
[  +0.000005]  __kasan_kmalloc+0xc1/0xd0
[  +0.000006]  __kmalloc_cache_noprof+0x1bd/0x430
[  +0.000007]  amdgpu_driver_open_kms+0x172/0x760 [amdgpu]
[  +0.000493]  drm_file_alloc+0x569/0x9a0
[  +0.000007]  drm_client_init+0x1b7/0x410
[  +0.000007]  drm_fbdev_client_setup+0x174/0x470
[  +0.000006]  drm_client_setup+0x8a/0xf0
[  +0.000006]  amdgpu_pci_probe+0x510/0x10c0 [amdgpu]
[  +0.000483]  local_pci_probe+0xe7/0x1b0
[  +0.000006]  pci_device_probe+0x5bf/0x890
[  +0.000006]  really_probe+0x1fd/0x950
[  +0.000005]  __driver_probe_device+0x307/0x410
[  +0.000006]  driver_probe_device+0x4e/0x150
[  +0.000005]  __driver_attach+0x223/0x510
[  +0.000006]  bus_for_each_dev+0x102/0x1a0
[  +0.000005]  driver_attach+0x3d/0x60
[  +0.000006]  bus_add_driver+0x309/0x650
[  +0.000005]  driver_register+0x13d/0x490
[  +0.000006]  __pci_register_driver+0x1ee/0x2b0
[  +0.000006]  rfcomm_dlc_clear_state+0x69/0x220 [rfcomm]
[  +0.000011]  do_one_initcall+0x9c/0x3e0
[  +0.000007]  do_init_module+0x29e/0x7f0
[  +0.000006]  load_module+0x5c75/0x7c80
[  +0.000006]  init_module_from_file+0x106/0x180
[  +0.000006]  idempotent_init_module+0x377/0x740
[  +0.000006]  __x64_sys_finit_module+0xd7/0x180
[  +0.000006]  x64_sys_call+0x1f0b/0x26f0
[  +0.000006]  do_syscall_64+0x7c/0x170
[  +0.000005]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  +0.000013] Freed by task 1733 on cpu 5 at 59.907086s:
[  +0.000011]  kasan_save_stack+0x28/0x60
[  +0.000006]  kasan_save_track+0x18/0x70
[  +0.000005]  kasan_save_free_info+0x3b/0x60
[  +0.000005]  __kasan_slab_free+0x54/0x80
[  +0.000006]  kfree+0x127/0x470
[  +0.000006]  amdgpu_driver_postclose_kms+0x455/0x760 [amdgpu]
[  +0.000493]  drm_file_free.part.0+0x5b1/0xba0
[  +0.000006]  drm_file_free+0x13/0x30
[  +0.000006]  drm_client_release+0x1c4/0x2b0
[  +0.000006]  drm_fbdev_ttm_fb_destroy+0xd2/0x120 [drm_ttm_helper]
[  +0.000007]  put_fb_info+0x97/0xe0
[  +0.000007]  unregister_framebuffer+0x197/0x380
[  +0.000005]  drm_fb_helper_unregister_info+0x94/0x100
[  +0.000005]  drm_fbdev_client_unregister+0x3c/0x80
[  +0.000007]  drm_client_dev_unregister+0x144/0x330
[  +0.000006]  drm_dev_unregister+0x49/0x1b0
[  +0.000006]  drm_dev_unplug+0x4c/0xd0
[  +0.000006]  amdgpu_pci_remove+0x58/0x130 [amdgpu]
[  +0.000484]  pci_device_remove+0xae/0x1e0
[  +0.000008]  device_remove+0xc7/0x180
[  +0.000007]  device_release_driver_internal+0x3d4/0x5a0
[  +0.000006]  device_release_driver+0x12/0x20
[  +0.000007]  pci_stop_bus_device+0x104/0x150
[  +0.000006]  pci_stop_and_remove_bus_device_locked+0x1b/0x40
[  +0.000006]  remove_store+0xd7/0xf0
[  +0.000006]  dev_attr_store+0x3f/0x80
[  +0.000005]  sysfs_kf_write+0x125/0x1d0
[  +0.000006]  kernfs_fop_write_iter+0x2ea/0x490
[  +0.000006]  vfs_write+0x90d/0xe70
[  +0.000006]  ksys_write+0x119/0x220
[  +0.000006]  __x64_sys_write+0x72/0xc0
[  +0.000006]  x64_sys_call+0x18ab/0x26f0
[  +0.000005]  do_syscall_64+0x7c/0x170
[  +0.000006]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

[ +0.000012] The buggy address belongs to the object at ffff88812eec8000
which belongs to the cache kmalloc-rnd-07-4k of size 4096
[ +0.000016] The buggy address is located 3160 bytes inside of

               freed 4096-byte region [ffff88812eec8000, ffff88812eec9000)
[  +0.000023] The buggy address belongs to the physical page:
[  +0.000009] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x12eec8
[  +0.000007] head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
[  +0.000005] flags: 0x17ffffc0000040(head|node=0|zone=2|lastcpupid=0x1fffff)
[  +0.000007] page_type: f5(slab)
[  +0.000008] raw: 0017ffffc0000040 ffff888100054500 dead000000000122 0000000000000000
[  +0.000005] raw: 0000000000000000 0000000080040004 00000000f5000000 0000000000000000
[  +0.000006] head: 0017ffffc0000040 ffff888100054500 dead000000000122 0000000000000000
[  +0.000005] head: 0000000000000000 0000000080040004 00000000f5000000 0000000000000000
[  +0.000006] head: 0017ffffc0000003 ffffea0004bbb201 ffffffffffffffff 0000000000000000
[  +0.000005] head: 0000000000000008 0000000000000000 00000000ffffffff 0000000000000000
[  +0.000005] page dumped because: kasan: bad access detected
[  +0.000010] Memory state around the buggy address:
[  +0.000009]  ffff88812eec8b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000012]  ffff88812eec8b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011] >ffff88812eec8c00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011]                                                     ^
[  +0.000010]  ffff88812eec8c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011]  ffff88812eec8d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  +0.000011] ==================================================================

The use-after-free occurs because a delayed work item (suspend_work) may still be pending or running when resources it accesses are freed during device removal or file close. The previous code used flush_work(&fpriv->evf_mgr.suspend_work.work), which does not wait for delayed work that has not yet started. As a result, the delayed work could run after its memory was freed, causing a use-after-free. By switching to flush_delayed_work(&fpriv->evf_mgr.suspend_work), we ensure that the kernel waits for both queued and delayed work to finish before freeing memory, closing this race.

Fixes adba0929736a ("drm/amdgpu: Fix Illegal opcode in command stream Error")
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +1 -1
index 295e7186e156..aac0de86f3e8 100644
@@ -664,7 +664,7 @@ static void amdgpu_userq_restore_worker(struct work_struct *work)
 	struct amdgpu_fpriv *fpriv = uq_mgr_to_fpriv(uq_mgr);
 	int ret;
 
-	flush_work(&fpriv->evf_mgr.suspend_work.work);
+	flush_delayed_work(&fpriv->evf_mgr.suspend_work);
 
 	mutex_lock(&uq_mgr->userq_mutex);
 
Signature · 1 line
2.39.5
author maintainer
#200 lore raw

PATCH 194/627 wifi: ath12k: Block radio bring-up in FTM mode

In reply to Greg Kroah-Hartman

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

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

From: Aaradhana Sahu <[email protected]>

[ Upstream commit 80570587e418f361e7ce3f9200477f728b38c94b ]

Ensure that all radios remain down when the driver operates in Factory Test Mode (FTM). Reject any userspace attempts to bring up an interface in this mode.

Currently, the driver allows userspace to bring up the interface even though it operates in FTM mode, which violates FTM constraints and leads to FTM command failures.

Hence, block the radio start when the driver is in FTM mode. Also, remove ath12k_ftm_mode check from ath12k_drain_tx() because FTM mode check is already handled in the caller function (ath12k_mac_op_start()).

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

---
 drivers/net/wireless/ath/ath12k/mac.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)
drivers/net/wireless/ath/ath12k/mac.c +4 -6
index 0feb800a4921..43464853a01d 100644
@@ -8167,14 +8167,9 @@ static int ath12k_mac_start(struct ath12k *ar)
 
 static void ath12k_drain_tx(struct ath12k_hw *ah)
 {
-	struct ath12k *ar = ah->radio;
+	struct ath12k *ar;
 	int i;
 
-	if (ath12k_ftm_mode) {
-		ath12k_err(ar->ab, "fail to start mac operations in ftm mode\n");
-		return;
-	}
-
 	lockdep_assert_wiphy(ah->hw->wiphy);
 
 	for_each_ar(ah, ar, i)
@@ -8187,6 +8182,9 @@ static int ath12k_mac_op_start(struct ieee80211_hw *hw)
 	struct ath12k *ar;
 	int ret, i;
 
+	if (ath12k_ftm_mode)
+		return -EPERM;
+
 	lockdep_assert_wiphy(hw->wiphy);
 
 	ath12k_drain_tx(ah);
Signature · 1 line
2.39.5
author maintainer
#201 lore raw

PATCH 195/627 arm64: fix unnecessary rebuilding when CONFIG_DEBUG_EFI=y

In reply to Greg Kroah-Hartman

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

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

From: Masahiro Yamada <[email protected]>

[ Upstream commit 344b6580472451390d070c65c27f59716a1deecb ]

When CONFIG_DEBUG_EFI is enabled, some objects are needlessly rebuilt.

[Steps to reproduce]

Enable CONFIG_DEBUG_EFI and run 'make' twice in a clean source tree. On the second run, arch/arm64/kernel/head.o is rebuilt even though no files have changed.

  $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- clean
  $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu-
     [ snip ]
  $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu-
    CALL    scripts/checksyscalls.sh
    AS      arch/arm64/kernel/head.o
    AR      arch/arm64/kernel/built-in.a
    AR      arch/arm64/built-in.a
    AR      built-in.a
     [ snip ]

The issue is caused by the use of the $(realpath ...) function.

At the time arch/arm64/kernel/Makefile is parsed on the first run, $(objtree)/vmlinux does not exist. As a result, $(realpath $(objtree)/vmlinux) expands to an empty string.

On the second run of Make, $(objtree)/vmlinux already exists, so $(realpath $(objtree)/vmlinux) expands to the absolute path of vmlinux. However, this change in the command line causes arch/arm64/kernel/head.o to be rebuilt.

To address this issue, use $(abspath ...) instead, which does not require the file to exist. While $(abspath ...) does not resolve symlinks, this should be fine from a debugging perspective.

The GNU Make manual [1] clearly explains the difference between the two:

$(realpath names...)
For each file name in names return the canonical absolute name. A canonical name does not contain any . or .. components, nor any repeated path separators (/) or symlinks. In case of a failure the empty string is returned. Consult the realpath(3) documentation for a list of possible failure causes.

$(abspath namees...)
For each file name in names return an absolute name that does not contain any . or .. components, nor any repeated path separators (/). Note that, in contrast to realpath function, abspath does not resolve symlinks and does not require the file names to refer to an existing file or directory. Use the wildcard function to test for existence.

The same problem exists in drivers/firmware/efi/libstub/Makefile.zboot. On the first run of Make, $(obj)/vmlinuz.efi.elf does not exist when the Makefile is parsed, so -DZBOOT_EFI_PATH is set to an empty string. Replace $(realpath ...) with $(abspath ...) there as well.

[1]: https://www.gnu.org/software/make/manual/make.html#File-Name-Functions

Fixes 757b435aaabe ("efi: arm64: Add vmlinux debug link to the Image binary")
Fixes a050910972bb ("efi/libstub: implement generic EFI zboot")
---
 arch/arm64/kernel/Makefile                  | 2 +-
 drivers/firmware/efi/libstub/Makefile.zboot | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
arch/arm64/kernel/Makefile +1 -1
index a2faf0049dab..76f32e424065 100644
@@ -80,7 +80,7 @@ obj-y					+= head.o
 always-$(KBUILD_BUILTIN)		+= vmlinux.lds
 
 ifeq ($(CONFIG_DEBUG_EFI),y)
-AFLAGS_head.o += -DVMLINUX_PATH="\"$(realpath $(objtree)/vmlinux)\""
+AFLAGS_head.o += -DVMLINUX_PATH="\"$(abspath vmlinux)\""
 endif
 
 # for cleaning
drivers/firmware/efi/libstub/Makefile.zboot +1 -1
index 92e3c73502ba..832deee36e48 100644
@@ -36,7 +36,7 @@ aflags-zboot-header-$(EFI_ZBOOT_FORWARD_CFI) := \
 		-DPE_DLL_CHAR_EX=IMAGE_DLLCHARACTERISTICS_EX_FORWARD_CFI_COMPAT
 
 AFLAGS_zboot-header.o += -DMACHINE_TYPE=IMAGE_FILE_MACHINE_$(EFI_ZBOOT_MACH_TYPE) \
-			 -DZBOOT_EFI_PATH="\"$(realpath $(obj)/vmlinuz.efi.elf)\"" \
+			 -DZBOOT_EFI_PATH="\"$(abspath $(obj)/vmlinuz.efi.elf)\"" \
 			 -DZBOOT_SIZE_LEN=$(zboot-size-len-y) \
 			 -DCOMP_TYPE="\"$(comp-type-y)\"" \
 			 $(aflags-zboot-header-y)
Signature · 1 line
2.39.5
author maintainer
#202 lore raw

PATCH 196/627 drm/rockchip: vop2: fail cleanly if missing a primary plane for a video-port

In reply to Greg Kroah-Hartman

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

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

From: Heiko Stuebner <[email protected]>

[ Upstream commit f9f68bf1d0efeadb6c427c9dbb30f307a7def19b ]

Each window of a vop2 is usable by a specific set of video ports, so while binding the vop2, we look through the list of available windows trying to find one designated as primary-plane and usable by that specific port.

The code later wants to use drm_crtc_init_with_planes with that found primary plane, but nothing has checked so far if a primary plane was actually found.

For whatever reason, the rk3576 vp2 does not have a usable primary window (if vp0 is also in use) which brought the issue to light and ended in a null-pointer dereference further down.

As we expect a primary-plane to exist for a video-port, add a check at the end of the window-iteration and fail probing if none was found.

---
 drivers/gpu/drm/rockchip/rockchip_drm_vop2.c | 4 ++++
 1 file changed, 4 insertions(+)
drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +4 -0
index d0f5fea15e21..6b37ce3ee60b 100644
@@ -2422,6 +2422,10 @@ static int vop2_create_crtcs(struct vop2 *vop2)
 				break;
 			}
 		}
+
+		if (!vp->primary_plane)
+			return dev_err_probe(drm->dev, -ENOENT,
+					     "no primary plane for vp %d\n", i);
 	}
 
 	/* Register all unused window as overlay plane */
Signature · 1 line
2.39.5
author maintainer
#203 lore raw

PATCH 197/627 drm/rockchip: vop2: Fix the update of LAYER/PORT select registers when there are multi display output on rk3588/rk3568

In reply to Greg Kroah-Hartman

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

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

From: Andy Yan <[email protected]>

[ Upstream commit 3e89a8c6835476aa782da80585dee9ddae651eea ]

The all video ports of rk3568/rk3588 share the same OVL_LAYER_SEL and OVL_PORT_SEL registers, and the configuration of these two registers can be set to take effect when the vsync signal arrives at a certain Video Port.

If two threads for two display output choose to update these two registers simultaneously to meet their own plane adjustment requirements(change plane zpos or switch plane from one crtc to another), then no matter which Video Port'svsync signal we choose to follow for these two registers, the display output of the other Video Port will be abnormal.
This is because the configuration of this Video Port does not take effect at the right time (its configuration should take effect when its VSYNC signal arrives).

In order to solve this problem, when performing plane migration or change the zpos of planes, there are two things to be observed and followed:

1. When a plane is migrated from one VP to another, the configuration of the layer can only take effect after the Port mux configuration is enabled.

2. When change the zpos of planes, we must ensure that the change for the previous VP takes effect before we proceed to change the next VP. Otherwise, the new configuration might overwrite the previous one for the previous VP, or it could lead to the configuration of the previous VP being take effect along with the VSYNC of the new VP.

This issue only occurs in scenarios where multi-display output is enabled.

Fixes c5996e4ab109 ("drm/rockchip: vop2: Make overlay layer select register configuration take effect by vsync")
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop2.c | 25 ++----
 drivers/gpu/drm/rockchip/rockchip_drm_vop2.h | 33 ++++++++
 drivers/gpu/drm/rockchip/rockchip_vop2_reg.c | 89 ++++++++++++++++++--
 3 files changed, 122 insertions(+), 25 deletions(-)
drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +6 -19
index 6b37ce3ee60b..186f6452a7d3 100644
@@ -146,25 +146,6 @@ static void vop2_unlock(struct vop2 *vop2)
 	mutex_unlock(&vop2->vop2_lock);
 }
 
-/*
- * Note:
- * The write mask function is documented but missing on rk3566/8, writes
- * to these bits have no effect. For newer soc(rk3588 and following) the
- * write mask is needed for register writes.
- *
- * GLB_CFG_DONE_EN has no write mask bit.
- *
- */
-static void vop2_cfg_done(struct vop2_video_port *vp)
-{
-	struct vop2 *vop2 = vp->vop2;
-	u32 val = RK3568_REG_CFG_DONE__GLB_CFG_DONE_EN;
-
-	val |= BIT(vp->id) | (BIT(vp->id) << 16);
-
-	regmap_set_bits(vop2->map, RK3568_REG_CFG_DONE, val);
-}
-
 static void vop2_win_disable(struct vop2_win *win)
 {
 	vop2_win_write(win, VOP2_WIN_ENABLE, 0);
@@ -854,6 +835,11 @@ static void vop2_enable(struct vop2 *vop2)
 	if (vop2->version == VOP_VERSION_RK3588)
 		rk3588_vop2_power_domain_enable_all(vop2);
 
+	if (vop2->version <= VOP_VERSION_RK3588) {
+		vop2->old_layer_sel = vop2_readl(vop2, RK3568_OVL_LAYER_SEL);
+		vop2->old_port_sel = vop2_readl(vop2, RK3568_OVL_PORT_SEL);
+	}
+
 	vop2_writel(vop2, RK3568_REG_CFG_DONE, RK3568_REG_CFG_DONE__GLB_CFG_DONE_EN);
 
 	/*
@@ -2728,6 +2714,7 @@ static int vop2_bind(struct device *dev, struct device *master, void *data)
 		return dev_err_probe(drm->dev, vop2->irq, "cannot find irq for vop2\n");
 
 	mutex_init(&vop2->vop2_lock);
+	mutex_init(&vop2->ovl_lock);
 
 	ret = devm_request_irq(dev, vop2->irq, vop2_isr, IRQF_SHARED, dev_name(dev), vop2);
 	if (ret)
drivers/gpu/drm/rockchip/rockchip_drm_vop2.h +33 -0
index fc3ecb9fcd95..fa5c56f16047 100644
@@ -334,6 +334,19 @@ struct vop2 {
 	/* optional internal rgb encoder */
 	struct rockchip_rgb *rgb;
 
+	/*
+	 * Used to record layer selection configuration on rk356x/rk3588
+	 * as register RK3568_OVL_LAYER_SEL and RK3568_OVL_PORT_SEL are
+	 * shared for all the Video Ports.
+	 */
+	u32 old_layer_sel;
+	u32 old_port_sel;
+	/*
+	 * Ensure that the updates to these two registers(RKK3568_OVL_LAYER_SEL/RK3568_OVL_PORT_SEL)
+	 * take effect in sequence.
+	 */
+	struct mutex ovl_lock;
+
 	/* must be put at the end of the struct */
 	struct vop2_win win[];
 };
@@ -727,6 +740,7 @@ enum dst_factor_mode {
 #define RK3588_OVL_PORT_SEL__CLUSTER2			GENMASK(21, 20)
 #define RK3568_OVL_PORT_SEL__CLUSTER1			GENMASK(19, 18)
 #define RK3568_OVL_PORT_SEL__CLUSTER0			GENMASK(17, 16)
+#define RK3588_OVL_PORT_SET__PORT3_MUX			GENMASK(15, 12)
 #define RK3568_OVL_PORT_SET__PORT2_MUX			GENMASK(11, 8)
 #define RK3568_OVL_PORT_SET__PORT1_MUX			GENMASK(7, 4)
 #define RK3568_OVL_PORT_SET__PORT0_MUX			GENMASK(3, 0)
@@ -831,4 +845,23 @@ static inline struct vop2_win *to_vop2_win(struct drm_plane *p)
 	return container_of(p, struct vop2_win, base);
 }
 
+/*
+ * Note:
+ * The write mask function is documented but missing on rk3566/8, writes
+ * to these bits have no effect. For newer soc(rk3588 and following) the
+ * write mask is needed for register writes.
+ *
+ * GLB_CFG_DONE_EN has no write mask bit.
+ *
+ */
+static inline void vop2_cfg_done(struct vop2_video_port *vp)
+{
+	struct vop2 *vop2 = vp->vop2;
+	u32 val = RK3568_REG_CFG_DONE__GLB_CFG_DONE_EN;
+
+	val |= BIT(vp->id) | (BIT(vp->id) << 16);
+
+	regmap_set_bits(vop2->map, RK3568_REG_CFG_DONE, val);
+}
+
 #endif /* _ROCKCHIP_DRM_VOP2_H */
drivers/gpu/drm/rockchip/rockchip_vop2_reg.c +83 -6

129 lines not on this page · raw message

Signature · 1 line
2.39.5
author maintainer
#204 lore raw

PATCH 198/627 sched/psi: Optimize psi_group_change() cpu_clock() usage

In reply to Greg Kroah-Hartman

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

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

From: Peter Zijlstra <[email protected]>

[ Upstream commit 570c8efd5eb79c3725ba439ce105ed1bedc5acd9 ]

Dietmar reported that commit 3840cbe24cf0 ("sched: psi: fix bogus pressure spikes from aggregation race") caused a regression for him on a high context switch rate benchmark (schbench) due to the now repeating cpu_clock() calls.

In particular the problem is that get_recent_times() will extrapolate the current state to 'now'. But if an update uses a timestamp from before the start of the update, it is possible to get two reads with inconsistent results. It is effectively back-dating an update.

(note that this all hard-relies on the clock being synchronized across CPUs -- if this is not the case, all bets are off).

Combine this problem with the fact that there are per-group-per-cpu seqcounts, the commit in question pushed the clock read into the group iteration, causing tree-depth cpu_clock() calls. On architectures where cpu_clock() has appreciable overhead, this hurts.

Instead move to a per-cpu seqcount, which allows us to have a single clock read for all group updates, increasing internal consistency and lowering update overhead. This comes at the cost of a longer update side (proportional to the tree depth) which can cause the read side to retry more often.

---
 include/linux/psi_types.h |   6 +-
 kernel/sched/psi.c        | 121 +++++++++++++++++++++-----------------
 2 files changed, 68 insertions(+), 59 deletions(-)
include/linux/psi_types.h +2 -4
index f1fd3a8044e0..dd10c22299ab 100644
@@ -84,11 +84,9 @@ enum psi_aggregators {
 struct psi_group_cpu {
 	/* 1st cacheline updated by the scheduler */
 
-	/* Aggregator needs to know of concurrent changes */
-	seqcount_t seq ____cacheline_aligned_in_smp;
-
 	/* States of the tasks belonging to this group */
-	unsigned int tasks[NR_PSI_TASK_COUNTS];
+	unsigned int tasks[NR_PSI_TASK_COUNTS]
+			____cacheline_aligned_in_smp;
 
 	/* Aggregate pressure state derived from the tasks */
 	u32 state_mask;
kernel/sched/psi.c +66 -55

255 lines not on this page · raw message

Signature · 1 line
2.39.5
author maintainer
#205 lore raw

PATCH 199/627 sched/deadline: Less agressive dl_server handling

In reply to Greg Kroah-Hartman

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

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

From: Peter Zijlstra <[email protected]>

[ Upstream commit cccb45d7c4295bbfeba616582d0249f2d21e6df5 ]

Chris reported that commit 5f6bd380c7bd ("sched/rt: Remove default bandwidth control") caused a significant dip in his favourite benchmark of the day. Simply disabling dl_server cured things.

His workload hammers the 0->1, 1->0 transitions, and the dl_server_{start,stop}() overhead kills it -- fairly obviously a bad idea in hind sight and all that.

Change things around to only disable the dl_server when there has not been a fair task around for a whole period. Since the default period is 1 second, this ensures the benchmark never trips this, overhead gone.

---
 include/linux/sched.h   |  1 +
 kernel/sched/deadline.c | 25 ++++++++++++++++++++++---
 kernel/sched/fair.c     |  9 ---------
 3 files changed, 23 insertions(+), 12 deletions(-)
include/linux/sched.h +1 -0
index aa9c5be7a632..ae75562cca59 100644
@@ -701,6 +701,7 @@ struct sched_dl_entity {
 	unsigned int			dl_defer	  : 1;
 	unsigned int			dl_defer_armed	  : 1;
 	unsigned int			dl_defer_running  : 1;
+	unsigned int			dl_server_idle    : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
kernel/sched/deadline.c +22 -3
index 89019a140826..094134c9b135 100644
@@ -1215,6 +1215,8 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
 /* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */
 static const u64 dl_server_min_res = 1 * NSEC_PER_MSEC;
 
+static bool dl_server_stopped(struct sched_dl_entity *dl_se);
+
 static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_dl_entity *dl_se)
 {
 	struct rq *rq = rq_of_dl_se(dl_se);
@@ -1234,6 +1236,7 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
 
 		if (!dl_se->server_has_tasks(dl_se)) {
 			replenish_dl_entity(dl_se);
+			dl_server_stopped(dl_se);
 			return HRTIMER_NORESTART;
 		}
 
@@ -1639,8 +1642,10 @@ void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
 void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
 {
 	/* 0 runtime = fair server disabled */
-	if (dl_se->dl_runtime)
+	if (dl_se->dl_runtime) {
+		dl_se->dl_server_idle = 0;
 		update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
+	}
 }
 
 void dl_server_start(struct sched_dl_entity *dl_se)
@@ -1663,7 +1668,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
 		setup_new_dl_entity(dl_se);
 	}
 
-	if (!dl_se->dl_runtime)
+	if (!dl_se->dl_runtime || dl_se->dl_server_active)
 		return;
 
 	dl_se->dl_server_active = 1;
@@ -1684,6 +1689,20 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
 	dl_se->dl_server_active = 0;
 }
 
+static bool dl_server_stopped(struct sched_dl_entity *dl_se)
+{
+	if (!dl_se->dl_server_active)
+		return false;
+
+	if (dl_se->dl_server_idle) {
+		dl_server_stop(dl_se);
+		return true;
+	}
+
+	dl_se->dl_server_idle = 1;
+	return false;
+}
+
 void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 		    dl_server_has_tasks_f has_tasks,
 		    dl_server_pick_f pick_task)
@@ -2435,7 +2454,7 @@ static struct task_struct *__pick_task_dl(struct rq *rq)
 	if (dl_server(dl_se)) {
 		p = dl_se->server_pick_task(dl_se);
 		if (!p) {
-			if (dl_server_active(dl_se)) {
+			if (!dl_server_stopped(dl_se)) {
 				dl_se->dl_yielded = 1;
 				update_curr_dl_se(rq, dl_se, 0);
 			}
kernel/sched/fair.c +0 -9
index 7a14da5396fb..3ab8d4765edd 100644
@@ -5889,7 +5889,6 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long queued_delta, runnable_delta, idle_delta, dequeue = 1;
-	long rq_h_nr_queued = rq->cfs.h_nr_queued;
 
 	raw_spin_lock(&cfs_b->lock);
 	/* This will start the period timer if necessary */
@@ -5973,10 +5972,6 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 	/* At this point se is NULL and we are at root level*/
 	sub_nr_running(rq, queued_delta);
-
-	/* Stop the fair server if throttling resulted in no runnable tasks */
-	if (rq_h_nr_queued && !rq->cfs.h_nr_queued)
-		dl_server_stop(&rq->fair_server);
 done:
 	/*
 	 * Note: distribution will already see us throttled via the
@@ -7070,7 +7065,6 @@ static void set_next_buddy(struct sched_entity *se);
 static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 {
 	bool was_sched_idle = sched_idle_rq(rq);
-	int rq_h_nr_queued = rq->cfs.h_nr_queued;
 	bool task_sleep = flags & DEQUEUE_SLEEP;
 	bool task_delayed = flags & DEQUEUE_DELAYED;
 	struct task_struct *p = NULL;
@@ -7154,9 +7148,6 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 
 	sub_nr_running(rq, h_nr_queued);
 
-	if (rq_h_nr_queued && !rq->cfs.h_nr_queued)
-		dl_server_stop(&rq->fair_server);
-
 	/* balance early to pull high priority tasks */
 	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
 		rq->next_balance = jiffies;
Signature · 1 line
2.39.5
#206 lore raw

Re: [PATCH 6.16 199/627] sched/deadline: Less agressive dl_server handling

Hi,

Quoted 12 lines · Greg Kroah-Hartman

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

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

From: Peter Zijlstra <[email protected]>

[ Upstream commit cccb45d7c4295bbfeba616582d0249f2d21e6df5 ]

Chris reported that commit 5f6bd380c7bd ("sched/rt: Remove default bandwidth control") caused a significant dip in his favourite benchmark of the day. Simply disabling dl_server cured things.

Quoted 8 lines

His workload hammers the 0->1, 1->0 transitions, and the dl_server_{start,stop}() overhead kills it -- fairly obviously a bad idea in hind sight and all that.

Change things around to only disable the dl_server when there has not been a fair task around for a whole period. Since the default period is 1 second, this ensures the benchmark never trips this, overhead gone.

This causes:
sched: DL replenish lagged too much

Maybe some prereq missing?

Quoted 7 lines

thanks,

Signature · 2 lines
js
suse labs
#207 lore raw

Re: [PATCH 6.16 199/627] sched/deadline: Less agressive dl_server handling

Quoted 25 lines · Jiri Slaby

Hi,

Quoted 12 lines · Greg Kroah-Hartman

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

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

From: Peter Zijlstra <[email protected]>

[ Upstream commit cccb45d7c4295bbfeba616582d0249f2d21e6df5 ]

Chris reported that commit 5f6bd380c7bd ("sched/rt: Remove default bandwidth control") caused a significant dip in his favourite benchmark of the day. Simply disabling dl_server cured things.

Quoted 8 lines

His workload hammers the 0->1, 1->0 transitions, and the dl_server_{start,stop}() overhead kills it -- fairly obviously a bad idea in hind sight and all that.

Change things around to only disable the dl_server when there has not been a fair task around for a whole period. Since the default period is 1 second, this ensures the benchmark never trips this, overhead gone.

Quoted 4 lines

This causes:
sched: DL replenish lagged too much

Maybe some prereq missing?

Not really, this is present both in linus/master and tip/master.

Quoted 9 lines
Quoted 7 lines

thanks,

Signature · 2 lines
js
suse labs
#208 lore raw

Re: [PATCH 6.16 199/627] sched/deadline: Less agressive dl_server handling

Hi,

Quoted 27 lines · Jiri Slaby
Quoted 26 lines · Jiri Slaby

Hi,

Quoted 21 lines · Greg Kroah-Hartman

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

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

From: Peter Zijlstra <[email protected]>

[ Upstream commit cccb45d7c4295bbfeba616582d0249f2d21e6df5 ]

Chris reported that commit 5f6bd380c7bd ("sched/rt: Remove default bandwidth control") caused a significant dip in his favourite benchmark of the day. Simply disabling dl_server cured things.

His workload hammers the 0->1, 1->0 transitions, and the dl_server_{start,stop}() overhead kills it -- fairly obviously a bad idea in hind sight and all that.

Change things around to only disable the dl_server when there has not been a fair task around for a whole period. Since the default period is 1 second, this ensures the benchmark never trips this, overhead gone.

Quoted 6 lines
Quoted 4 lines

This causes:
sched: DL replenish lagged too much

Maybe some prereq missing?

Not really, this is present both in linus/master and tip/master.

https://lore.kernel.org/lkml/[email protected]/
should be addressing it, but still under review.

Thanks,
Juri

author maintainer
#209 lore raw

Re: [PATCH 6.16 199/627] sched/deadline: Less agressive dl_server handling

In reply to Jiri Slaby
Quoted 27 lines · Jiri Slaby
Quoted 26 lines · Jiri Slaby

Hi,

Quoted 21 lines · Greg Kroah-Hartman

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

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

From: Peter Zijlstra <[email protected]>

[ Upstream commit cccb45d7c4295bbfeba616582d0249f2d21e6df5 ]

Chris reported that commit 5f6bd380c7bd ("sched/rt: Remove default bandwidth control") caused a significant dip in his favourite benchmark of the day. Simply disabling dl_server cured things.

His workload hammers the 0->1, 1->0 transitions, and the dl_server_{start,stop}() overhead kills it -- fairly obviously a bad idea in hind sight and all that.

Change things around to only disable the dl_server when there has not been a fair task around for a whole period. Since the default period is 1 second, this ensures the benchmark never trips this, overhead gone.

Quoted 15 lines
Quoted 4 lines

This causes:
sched: DL replenish lagged too much

Maybe some prereq missing?

Not really, this is present both in linus/master and tip/master.

Quoted 9 lines
Quoted 7 lines

thanks,

Ok, I'll move this out of this release and queue it up for the "next one".

thanks,

greg k-h

author maintainer
#210 lore raw

PATCH 200/627 fbcon: Fix outdated registered_fb reference in comment

In reply to Greg Kroah-Hartman

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

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

From: Shixiong Ou <[email protected]>

[ Upstream commit 0f168e7be696a17487e83d1d47e5a408a181080f ]

The variable was renamed to fbcon_registered_fb, but this comment was not updated along with the change. Correct it to avoid confusion.

Fixes efc3acbc105a ("fbcon: Maintain a private array of fb_info")
[sima: Add Fixes: line.]
---
 drivers/video/fbdev/core/fbcon.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/video/fbdev/core/fbcon.c +2 -2
index 2df48037688d..2b2d36c021ba 100644
@@ -952,13 +952,13 @@ static const char *fbcon_startup(void)
 	int rows, cols;
 
 	/*
-	 *  If num_registered_fb is zero, this is a call for the dummy part.
+	 *  If fbcon_num_registered_fb is zero, this is a call for the dummy part.
 	 *  The frame buffer devices weren't initialized yet.
 	 */
 	if (!fbcon_num_registered_fb || info_idx == -1)
 		return display_desc;
 	/*
-	 * Instead of blindly using registered_fb[0], we use info_idx, set by
+	 * Instead of blindly using fbcon_registered_fb[0], we use info_idx, set by
 	 * fbcon_fb_registered();
 	 */
 	info = fbcon_registered_fb[info_idx];
Signature · 1 line
2.39.5
author maintainer
#211 lore raw

PATCH 201/627 netfilter: nf_tables: Drop dead code from fill_*_info routines

In reply to Greg Kroah-Hartman

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

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

From: Phil Sutter <[email protected]>

[ Upstream commit 8080357a8c6cf4905bbd8969412c19d34be3395e ]

This practically reverts commit 28339b21a365 ("netfilter: nf_tables: do not send complete notification of deletions"): The feature was never effective, due to prior modification of 'event' variable the conditional early return never happened.

User space also relies upon the current behaviour, so better reintroduce the shortened deletion notifications once it is fixed.

Fixes 28339b21a365 ("netfilter: nf_tables: do not send complete notification of deletions")
---
 net/netfilter/nf_tables_api.c | 25 -------------------------
 1 file changed, 25 deletions(-)
net/netfilter/nf_tables_api.c +0 -25
index a7240736f98e..9ebda0248d20 100644
@@ -1165,11 +1165,6 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 			 NFTA_TABLE_PAD))
 		goto nla_put_failure;
 
-	if (event == NFT_MSG_DELTABLE) {
-		nlmsg_end(skb, nlh);
-		return 0;
-	}
-
 	if (nla_put_be32(skb, NFTA_TABLE_FLAGS,
 			 htonl(table->flags & NFT_TABLE_F_MASK)))
 		goto nla_put_failure;
@@ -2028,11 +2023,6 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 			 NFTA_CHAIN_PAD))
 		goto nla_put_failure;
 
-	if (event == NFT_MSG_DELCHAIN && !hook_list) {
-		nlmsg_end(skb, nlh);
-		return 0;
-	}
-
 	if (nft_is_base_chain(chain)) {
 		const struct nft_base_chain *basechain = nft_base_chain(chain);
 		struct nft_stats __percpu *stats;
@@ -4859,11 +4849,6 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			 NFTA_SET_PAD))
 		goto nla_put_failure;
 
-	if (event == NFT_MSG_DELSET) {
-		nlmsg_end(skb, nlh);
-		return 0;
-	}
-
 	if (set->flags != 0)
 		if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(set->flags)))
 			goto nla_put_failure;
@@ -8350,11 +8335,6 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
 			 NFTA_OBJ_PAD))
 		goto nla_put_failure;
 
-	if (event == NFT_MSG_DELOBJ) {
-		nlmsg_end(skb, nlh);
-		return 0;
-	}
-
 	if (nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) ||
 	    nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) ||
 	    nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset))
@@ -9394,11 +9374,6 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 			 NFTA_FLOWTABLE_PAD))
 		goto nla_put_failure;
 
-	if (event == NFT_MSG_DELFLOWTABLE && !hook_list) {
-		nlmsg_end(skb, nlh);
-		return 0;
-	}
-
 	if (nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) ||
 	    nla_put_be32(skb, NFTA_FLOWTABLE_FLAGS, htonl(flowtable->data.flags)))
 		goto nla_put_failure;
Signature · 1 line
2.39.5
author maintainer
#212 lore raw

PATCH 202/627 netfilter: nf_tables: adjust lockdep assertions handling

In reply to Greg Kroah-Hartman

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

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

From: Fedor Pchelkin <[email protected]>

[ Upstream commit 8df1b40de76979bb8e975201d07b71103d5de820 ]

It's needed to check the return value of lockdep_commit_lock_is_held(), otherwise there's no point in this assertion as it doesn't print any debug information on itself.

Found by Linux Verification Center (linuxtesting.org) with Svace static analysis tool.

Fixes b04df3da1b5c ("netfilter: nf_tables: do not defer rule destruction via call_rcu")
---
 net/netfilter/nf_tables_api.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
net/netfilter/nf_tables_api.c +2 -2
index 9ebda0248d20..064f18792d98 100644
@@ -4029,7 +4029,7 @@ void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule)
 /* can only be used if rule is no longer visible to dumps */
 static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule)
 {
-	lockdep_commit_lock_is_held(ctx->net);
+	WARN_ON_ONCE(!lockdep_commit_lock_is_held(ctx->net));
 
 	nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE);
 	nf_tables_rule_destroy(ctx, rule);
@@ -5844,7 +5844,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
 			      struct nft_set_binding *binding,
 			      enum nft_trans_phase phase)
 {
-	lockdep_commit_lock_is_held(ctx->net);
+	WARN_ON_ONCE(!lockdep_commit_lock_is_held(ctx->net));
 
 	switch (phase) {
 	case NFT_TRANS_PREPARE_ERROR:
Signature · 1 line
2.39.5
author maintainer
#213 lore raw

PATCH 203/627 drm/panthor: Fix UAF in panthor_gem_create_with_handle() debugfs code

In reply to Greg Kroah-Hartman

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

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

From: Simona Vetter <[email protected]>

[ Upstream commit fe69a391808404977b1f002a6e7447de3de7a88e ]

The object is potentially already gone after the drm_gem_object_put(). In general the object should be fully constructed before calling drm_gem_handle_create(), except the debugfs tracking uses a separate lock and list and separate flag to denotate whether the object is actually initialized.

Since I'm touching this all anyway simplify this by only adding the object to the debugfs when it's ready for that, which allows us to delete that separate flag. panthor_gem_debugfs_bo_rm() already checks whether we've actually been added to the list or this is some error path cleanup.

v2: Fix build issues for !CONFIG_DEBUGFS (Adrián)

v3: Add linebreak and remove outdated comment (Liviu)

Fixes a3707f53eb3f ("drm/panthor: show device-wide list of DRM GEM objects over DebugFS")
Cc Adrián Larumbe <[email protected]>
Cc Boris Brezillon <[email protected]>
Cc Steven Price <[email protected]>
Cc Liviu Dudau <[email protected]>
---
 drivers/gpu/drm/panthor/panthor_gem.c | 31 +++++++++++++--------------
 drivers/gpu/drm/panthor/panthor_gem.h |  3 ---
 2 files changed, 15 insertions(+), 19 deletions(-)
drivers/gpu/drm/panthor/panthor_gem.c +15 -16
index 7c00fd77758b..a123bc740ba1 100644
@@ -16,10 +16,15 @@
 #include "panthor_mmu.h"
 
 #ifdef CONFIG_DEBUG_FS
-static void panthor_gem_debugfs_bo_add(struct panthor_device *ptdev,
-				       struct panthor_gem_object *bo)
+static void panthor_gem_debugfs_bo_init(struct panthor_gem_object *bo)
 {
 	INIT_LIST_HEAD(&bo->debugfs.node);
+}
+
+static void panthor_gem_debugfs_bo_add(struct panthor_gem_object *bo)
+{
+	struct panthor_device *ptdev = container_of(bo->base.base.dev,
+						    struct panthor_device, base);
 
 	bo->debugfs.creator.tgid = current->group_leader->pid;
 	get_task_comm(bo->debugfs.creator.process_name, current->group_leader);
@@ -44,14 +49,13 @@ static void panthor_gem_debugfs_bo_rm(struct panthor_gem_object *bo)
 
 static void panthor_gem_debugfs_set_usage_flags(struct panthor_gem_object *bo, u32 usage_flags)
 {
-	bo->debugfs.flags = usage_flags | PANTHOR_DEBUGFS_GEM_USAGE_FLAG_INITIALIZED;
+	bo->debugfs.flags = usage_flags;
+	panthor_gem_debugfs_bo_add(bo);
 }
 #else
-static void panthor_gem_debugfs_bo_add(struct panthor_device *ptdev,
-				       struct panthor_gem_object *bo)
-{}
 static void panthor_gem_debugfs_bo_rm(struct panthor_gem_object *bo) {}
 static void panthor_gem_debugfs_set_usage_flags(struct panthor_gem_object *bo, u32 usage_flags) {}
+static void panthor_gem_debugfs_bo_init(struct panthor_gem_object *bo) {}
 #endif
 
 static void panthor_gem_free_object(struct drm_gem_object *obj)
@@ -246,7 +250,7 @@ struct drm_gem_object *panthor_gem_create_object(struct drm_device *ddev, size_t
 	drm_gem_gpuva_set_lock(&obj->base.base, &obj->gpuva_list_lock);
 	mutex_init(&obj->label.lock);
 
-	panthor_gem_debugfs_bo_add(ptdev, obj);
+	panthor_gem_debugfs_bo_init(obj);
 
 	return &obj->base.base;
 }
@@ -285,6 +289,8 @@ panthor_gem_create_with_handle(struct drm_file *file,
 		bo->base.base.resv = bo->exclusive_vm_root_gem->resv;
 	}
 
+	panthor_gem_debugfs_set_usage_flags(bo, 0);
+
 	/*
 	 * Allocate an id of idr table where the obj is registered
 	 * and handle has the id what user can see.
@@ -296,12 +302,6 @@ panthor_gem_create_with_handle(struct drm_file *file,
 	/* drop reference from allocate - handle holds it now. */
 	drm_gem_object_put(&shmem->base);
 
-	/*
-	 * No explicit flags are needed in the call below, since the
-	 * function internally sets the INITIALIZED bit for us.
-	 */
-	panthor_gem_debugfs_set_usage_flags(bo, 0);
-
 	return ret;
 }
 
@@ -387,7 +387,7 @@ static void panthor_gem_debugfs_bo_print(struct panthor_gem_object *bo,
 	unsigned int refcount = kref_read(&bo->base.base.refcount);
 	char creator_info[32] = {};
 	size_t resident_size;
-	u32 gem_usage_flags = bo->debugfs.flags & (u32)~PANTHOR_DEBUGFS_GEM_USAGE_FLAG_INITIALIZED;
+	u32 gem_usage_flags = bo->debugfs.flags;
 	u32 gem_state_flags = 0;
 
 	/* Skip BOs being destroyed. */
@@ -436,8 +436,7 @@ void panthor_gem_debugfs_print_bos(struct panthor_device *ptdev,
 
 	scoped_guard(mutex, &ptdev->gems.lock) {
 		list_for_each_entry(bo, &ptdev->gems.node, debugfs.node) {
-			if (bo->debugfs.flags & PANTHOR_DEBUGFS_GEM_USAGE_FLAG_INITIALIZED)
-				panthor_gem_debugfs_bo_print(bo, m, &totals);
+			panthor_gem_debugfs_bo_print(bo, m, &totals);
 		}
 	}
 
drivers/gpu/drm/panthor/panthor_gem.h +0 -3
index 4dd732dcd59f..8fc7215e9b90 100644
@@ -35,9 +35,6 @@ enum panthor_debugfs_gem_usage_flags {
 
 	/** @PANTHOR_DEBUGFS_GEM_USAGE_FLAG_FW_MAPPED: BO is mapped on the FW VM. */
 	PANTHOR_DEBUGFS_GEM_USAGE_FLAG_FW_MAPPED = BIT(PANTHOR_DEBUGFS_GEM_USAGE_FW_MAPPED_BIT),
-
-	/** @PANTHOR_DEBUGFS_GEM_USAGE_FLAG_INITIALIZED: BO is ready for DebugFS display. */
-	PANTHOR_DEBUGFS_GEM_USAGE_FLAG_INITIALIZED = BIT(31),
 };
 
 /**
Signature · 1 line
2.39.5
author maintainer
#214 lore raw

PATCH 204/627 wifi: ath12k: update unsupported bandwidth flags in reg rules

In reply to Greg Kroah-Hartman

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

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

From: Harshitha Prem <[email protected]>

[ Upstream commit 2109e98503bc1c01c399feac68cc8b7faf6d0a4a ]

The maximum bandwidth an interface can operate in is defined by the configured country. However, currently, it is able to operate in bandwidths greater than the allowed bandwidth. For example, the Central African Republic (CF) supports a maximum bandwidth of 40 MHz in both the 2 GHz and 5 GHz bands, but an interface is still able to operate in bandwidths higher than 40 MHz. This issue arises because the regulatory rules in the regd are not updated with these restrictions received from firmware on the maximum bandwidth.

Hence, update the regulatory rules with unsupported bandwidth flags based on the maximum bandwidth to ensure compliance with country-specific regulations.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

---
 drivers/net/wireless/ath/ath12k/reg.c | 31 ++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)
drivers/net/wireless/ath/ath12k/reg.c +28 -3
index 0fc7f209956d..743552abf149 100644
@@ -398,6 +398,29 @@ ath12k_map_fw_dfs_region(enum ath12k_dfs_region dfs_region)
 	}
 }
 
+static u32 ath12k_get_bw_reg_flags(u16 max_bw)
+{
+	switch (max_bw) {
+	case 20:
+		return NL80211_RRF_NO_HT40 |
+			NL80211_RRF_NO_80MHZ |
+			NL80211_RRF_NO_160MHZ |
+			NL80211_RRF_NO_320MHZ;
+	case 40:
+		return NL80211_RRF_NO_80MHZ |
+			NL80211_RRF_NO_160MHZ |
+			NL80211_RRF_NO_320MHZ;
+	case 80:
+		return NL80211_RRF_NO_160MHZ |
+			NL80211_RRF_NO_320MHZ;
+	case 160:
+		return NL80211_RRF_NO_320MHZ;
+	case 320:
+	default:
+		return 0;
+	}
+}
+
 static u32 ath12k_map_fw_reg_flags(u16 reg_flags)
 {
 	u32 flags = 0;
@@ -676,7 +699,7 @@ ath12k_reg_build_regd(struct ath12k_base *ab,
 			reg_rule = reg_info->reg_rules_2g_ptr + i;
 			max_bw = min_t(u16, reg_rule->max_bw,
 				       reg_info->max_bw_2g);
-			flags = 0;
+			flags = ath12k_get_bw_reg_flags(reg_info->max_bw_2g);
 			ath12k_reg_update_freq_range(&ab->reg_freq_2ghz, reg_rule);
 		} else if (reg_info->num_5g_reg_rules &&
 			   (j < reg_info->num_5g_reg_rules)) {
@@ -690,13 +713,15 @@ ath12k_reg_build_regd(struct ath12k_base *ab,
 			 * BW correction if required and applies flags as
 			 * per other BW rule flags we pass from here
 			 */
-			flags = NL80211_RRF_AUTO_BW;
+			flags = NL80211_RRF_AUTO_BW |
+				ath12k_get_bw_reg_flags(reg_info->max_bw_5g);
 			ath12k_reg_update_freq_range(&ab->reg_freq_5ghz, reg_rule);
 		} else if (reg_info->is_ext_reg_event && reg_6ghz_number &&
 			   (k < reg_6ghz_number)) {
 			reg_rule = reg_rule_6ghz + k++;
 			max_bw = min_t(u16, reg_rule->max_bw, max_bw_6ghz);
-			flags = NL80211_RRF_AUTO_BW;
+			flags = NL80211_RRF_AUTO_BW |
+				ath12k_get_bw_reg_flags(max_bw_6ghz);
 			if (reg_rule->psd_flag)
 				flags |= NL80211_RRF_PSD;
 			ath12k_reg_update_freq_range(&ab->reg_freq_6ghz, reg_rule);
Signature · 1 line
2.39.5
author maintainer
#215 lore raw

PATCH 205/627 wifi: ath12k: pack HTT pdev rate stats structs

In reply to Greg Kroah-Hartman

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

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

From: Jeff Johnson <[email protected]>

[ Upstream commit fee9b1f6691120182136edacf590f52d62d9de7f ]

In order to ensure the HTT DebugFS structs shared with firmware have matching alignment, the structs should be packed. Most of the structs are correctly packed, however the following are not:

ath12k_htt_tx_pdev_rate_stats_tlv
ath12k_htt_rx_pdev_rate_stats_tlv
ath12k_htt_rx_pdev_rate_ext_stats_tlv

So pack those structs.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Fixes ba42b22aa336 ("wifi: ath12k: Dump PDEV transmit rate HTT stats")
Fixes a24cd7583003 ("wifi: ath12k: Dump PDEV receive rate HTT stats")
Fixes 7a3e8eec8d18 ("wifi: ath12k: Dump additional PDEV receive rate HTT stats")
---
 drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h +3 -3
index c2a02cf8a38b..db9532c39cbf 100644
@@ -470,7 +470,7 @@ struct ath12k_htt_tx_pdev_rate_stats_tlv {
 			   [ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
 	__le32 tx_mcs_ext_2[ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA2_MCS_COUNTERS];
 	__le32 tx_bw_320mhz;
-};
+} __packed;
 
 #define ATH12K_HTT_RX_PDEV_STATS_NUM_LEGACY_CCK_STATS		4
 #define ATH12K_HTT_RX_PDEV_STATS_NUM_LEGACY_OFDM_STATS		8
@@ -550,7 +550,7 @@ struct ath12k_htt_rx_pdev_rate_stats_tlv {
 	__le32 rx_ulofdma_non_data_nusers[ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER];
 	__le32 rx_ulofdma_data_nusers[ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER];
 	__le32 rx_mcs_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
-};
+} __packed;
 
 #define ATH12K_HTT_RX_PDEV_STATS_NUM_BW_EXT_COUNTERS		4
 #define ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT		14
@@ -580,7 +580,7 @@ struct ath12k_htt_rx_pdev_rate_ext_stats_tlv {
 	__le32 rx_gi_ext_2[ATH12K_HTT_RX_PDEV_STATS_NUM_GI_COUNTERS]
 		[ATH12K_HTT_RX_PDEV_STATS_NUM_EXTRA2_MCS_COUNTERS];
 	__le32 rx_su_punctured_mode[ATH12K_HTT_RX_PDEV_STATS_NUM_PUNCTURED_MODE_COUNTERS];
-};
+} __packed;
 
 #define ATH12K_HTT_TX_PDEV_STATS_SCHED_PER_TXQ_MAC_ID	GENMASK(7, 0)
 #define ATH12K_HTT_TX_PDEV_STATS_SCHED_PER_TXQ_ID	GENMASK(15, 8)
Signature · 1 line
2.39.5
author maintainer
#216 lore raw

PATCH 206/627 arch: powerpc: defconfig: Drop obsolete CONFIG_NET_CLS_TCINDEX

In reply to Greg Kroah-Hartman

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

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

From: Johan Korsnes <[email protected]>

[ Upstream commit 75cd37c5f28b85979fd5a65174013010f6b78f27 ]

This option was removed from the Kconfig in commit 8c710f75256b ("net/sched: Retire tcindex classifier") but it was not removed from the defconfigs.

---
 arch/powerpc/configs/ppc6xx_defconfig | 1 -
 1 file changed, 1 deletion(-)
arch/powerpc/configs/ppc6xx_defconfig +0 -1
index f96f8ed9856c..bb359643ddc1 100644
@@ -252,7 +252,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
Signature · 1 line
2.39.5
author maintainer
#217 lore raw

PATCH 207/627 um: rtc: Avoid shadowing err in uml_rtc_start()

In reply to Greg Kroah-Hartman

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

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

From: Tiwei Bie <[email protected]>

[ Upstream commit 4c916e3b224a02019b3cc3983a15f32bfd9a22df ]

Remove the declaration of 'err' inside the 'if (timetravel)' block, as it would otherwise be unavailable outside that block, potentially leading to uml_rtc_start() returning an uninitialized value.

---
 arch/um/drivers/rtc_user.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/um/drivers/rtc_user.c +1 -1
index 51e79f3148cd..67912fcf7b28 100644
@@ -28,7 +28,7 @@ int uml_rtc_start(bool timetravel)
 	int err;
 
 	if (timetravel) {
-		int err = os_pipe(uml_rtc_irq_fds, 1, 1);
+		err = os_pipe(uml_rtc_irq_fds, 1, 1);
 		if (err)
 			goto fail;
 	} else {
Signature · 1 line
2.39.5
author maintainer
#218 lore raw

PATCH 208/627 iommu/amd: Enable PASID and ATS capabilities in the correct order

In reply to Greg Kroah-Hartman

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

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

From: Easwar Hariharan <[email protected]>

[ Upstream commit c694bc8b612ddd0dd70e122a00f39cb1e2e6927f ]

Per the PCIe spec, behavior of the PASID capability is undefined if the value of the PASID Enable bit changes while the Enable bit of the function's ATS control register is Set. Unfortunately, pdev_enable_caps() does exactly that by ordering enabling ATS for the device before enabling PASID.

Cc Suravee Suthikulpanit <[email protected]>
Cc Vasant Hegde <[email protected]>
Cc Jason Gunthorpe <[email protected]>
Cc Jerry Snitselaar <[email protected]>
Fixes eda8c2860ab679 ("iommu/amd: Enable device ATS/PASID/PRI capabilities independently")
---
 drivers/iommu/amd/iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/iommu/amd/iommu.c +1 -1
index 3117d99cf83d..8b8d3e843743 100644
@@ -634,8 +634,8 @@ static inline void pdev_disable_cap_pasid(struct pci_dev *pdev)
 
 static void pdev_enable_caps(struct pci_dev *pdev)
 {
-	pdev_enable_cap_ats(pdev);
 	pdev_enable_cap_pasid(pdev);
+	pdev_enable_cap_ats(pdev);
 	pdev_enable_cap_pri(pdev);
 }
 
Signature · 1 line
2.39.5
author maintainer
#219 lore raw

PATCH 209/627 spi: spi-nxp-fspi: Check return value of devm_mutex_init()

In reply to Greg Kroah-Hartman

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

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

From: Thomas Weißschuh <[email protected]>

[ Upstream commit d24a54e032021cf381af3c3cf119cc5cf6b3c1be ]

devm_mutex_init() can fail. With CONFIG_DEBUG_MUTEXES=y the mutex will be marked as unusable and trigger errors on usage.

Add the missed check.

---
 drivers/spi/spi-nxp-fspi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/spi/spi-nxp-fspi.c +3 -1
index e63c77e41823..f3d576505413 100644
@@ -1273,7 +1273,9 @@ static int nxp_fspi_probe(struct platform_device *pdev)
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to request irq\n");
 
-	devm_mutex_init(dev, &f->lock);
+	ret = devm_mutex_init(dev, &f->lock);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to initialize lock\n");
 
 	ctlr->bus_num = -1;
 	ctlr->num_chipselect = NXP_FSPI_MAX_CHIPSELECT;
Signature · 1 line
2.39.5
author maintainer
#220 lore raw

PATCH 210/627 leds: lp8860: Check return value of devm_mutex_init()

In reply to Greg Kroah-Hartman

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

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

From: Thomas Weißschuh <[email protected]>

[ Upstream commit 3b07bb900af7f43f13f9ff398b4c6ca1dee217cd ]

devm_mutex_init() can fail. With CONFIG_DEBUG_MUTEXES=y the mutex will be marked as unusable and trigger errors on usage.

Add the missed check.

---
 drivers/leds/leds-lp8860.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/leds/leds-lp8860.c +3 -1
index 52b97c9f2a03..0962c00c215a 100644
@@ -307,7 +307,9 @@ static int lp8860_probe(struct i2c_client *client)
 	led->client = client;
 	led->led_dev.brightness_set_blocking = lp8860_brightness_set;
 
-	devm_mutex_init(&client->dev, &led->lock);
+	ret = devm_mutex_init(&client->dev, &led->lock);
+	if (ret)
+		return dev_err_probe(&client->dev, ret, "Failed to initialize lock\n");
 
 	led->regmap = devm_regmap_init_i2c(client, &lp8860_regmap_config);
 	if (IS_ERR(led->regmap)) {
Signature · 1 line
2.39.5
author maintainer
#221 lore raw

PATCH 211/627 net/sched: Restrict conditions for adding duplicating netems to qdisc tree

In reply to Greg Kroah-Hartman

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

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

From: William Liu <[email protected]>

[ Upstream commit ec8e0e3d7adef940cdf9475e2352c0680189d14e ]

netem_enqueue's duplication prevention logic breaks when a netem resides in a qdisc tree with other netems - this can lead to a soft lockup and OOM loop in netem_dequeue, as seen in [1]. Ensure that a duplicating netem cannot exist in a tree with other netems.

Previous approaches suggested in discussions in chronological order:

1) Track duplication status or ttl in the sk_buff struct. Considered too specific a use case to extend such a struct, though this would be a resilient fix and address other previous and potential future DOS bugs like the one described in loopy fun [2].

2) Restrict netem_enqueue recursion depth like in act_mirred with a per cpu variable. However, netem_dequeue can call enqueue on its child, and the depth restriction could be bypassed if the child is a netem.

3) Use the same approach as in 2, but add metadata in netem_skb_cb to handle the netem_dequeue case and track a packet's involvement in duplication. This is an overly complex approach, and Jamal notes that the skb cb can be overwritten to circumvent this safeguard.

4) Prevent the addition of a netem to a qdisc tree if its ancestral path contains a netem. However, filters and actions can cause a packet to change paths when re-enqueued to the root from netem duplication, leading us to the current solution: prevent a duplicating netem from inhabiting the same tree as other netems.

[1] https://lore.kernel.org/netdev/8DuRWwfqjoRDLDmBMlIfbrsZg9Gx50DHJc1ilxsEBNe2D6NMoigR_eIRIG0LOjMc3r10nUUZtArXx4oZBIdUfZQrwjcQhdinnMis_0G7VEk=@willsroot.io/
[2] https://lwn.net/Articles/719297/

---
 net/sched/sch_netem.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)
net/sched/sch_netem.c +40 -0
index fdd79d3ccd8c..eafc316ae319 100644
@@ -973,6 +973,41 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
 	return 0;
 }
 
+static const struct Qdisc_class_ops netem_class_ops;
+
+static int check_netem_in_tree(struct Qdisc *sch, bool duplicates,
+			       struct netlink_ext_ack *extack)
+{
+	struct Qdisc *root, *q;
+	unsigned int i;
+
+	root = qdisc_root_sleeping(sch);
+
+	if (sch != root && root->ops->cl_ops == &netem_class_ops) {
+		if (duplicates ||
+		    ((struct netem_sched_data *)qdisc_priv(root))->duplicate)
+			goto err;
+	}
+
+	if (!qdisc_dev(root))
+		return 0;
+
+	hash_for_each(qdisc_dev(root)->qdisc_hash, i, q, hash) {
+		if (sch != q && q->ops->cl_ops == &netem_class_ops) {
+			if (duplicates ||
+			    ((struct netem_sched_data *)qdisc_priv(q))->duplicate)
+				goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	NL_SET_ERR_MSG(extack,
+		       "netem: cannot mix duplicating netems with other netems in tree");
+	return -EINVAL;
+}
+
 /* Parse netlink message to set options */
 static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 			struct netlink_ext_ack *extack)
@@ -1031,6 +1066,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 	q->gap = qopt->gap;
 	q->counter = 0;
 	q->loss = qopt->loss;
+
+	ret = check_netem_in_tree(sch, qopt->duplicate, extack);
+	if (ret)
+		goto unlock;
+
 	q->duplicate = qopt->duplicate;
 
 	/* for compatibility with earlier versions.
Signature · 1 line
2.39.5
author maintainer
#222 lore raw

PATCH 212/627 net_sched: act_ctinfo: use atomic64_t for three counters

In reply to Greg Kroah-Hartman

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit d300335b4e18672913dd792ff9f49e6cccf41d26 ]

Commit 21c167aa0ba9 ("net/sched: act_ctinfo: use percpu stats") missed that stats_dscp_set, stats_dscp_error and stats_cpmark_set might be written (and read) locklessly.

Use atomic64_t for these three fields, I doubt act_ctinfo is used heavily on big SMP hosts anyway.

Fixes 24ec483cec98 ("net: sched: Introduce act_ctinfo action")
Cc Pedro Tammela <[email protected]>
---
 include/net/tc_act/tc_ctinfo.h |  6 +++---
 net/sched/act_ctinfo.c         | 19 +++++++++++--------
 2 files changed, 14 insertions(+), 11 deletions(-)
include/net/tc_act/tc_ctinfo.h +3 -3
index f071c1d70a25..a04bcac7adf4 100644
@@ -18,9 +18,9 @@ struct tcf_ctinfo_params {
 struct tcf_ctinfo {
 	struct tc_action common;
 	struct tcf_ctinfo_params __rcu *params;
-	u64 stats_dscp_set;
-	u64 stats_dscp_error;
-	u64 stats_cpmark_set;
+	atomic64_t stats_dscp_set;
+	atomic64_t stats_dscp_error;
+	atomic64_t stats_cpmark_set;
 };
 
 enum {
net/sched/act_ctinfo.c +11 -8
index 5b1241ddc758..93ab3bcd6d31 100644
@@ -44,9 +44,9 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca,
 				ipv4_change_dsfield(ip_hdr(skb),
 						    INET_ECN_MASK,
 						    newdscp);
-				ca->stats_dscp_set++;
+				atomic64_inc(&ca->stats_dscp_set);
 			} else {
-				ca->stats_dscp_error++;
+				atomic64_inc(&ca->stats_dscp_error);
 			}
 		}
 		break;
@@ -57,9 +57,9 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca,
 				ipv6_change_dsfield(ipv6_hdr(skb),
 						    INET_ECN_MASK,
 						    newdscp);
-				ca->stats_dscp_set++;
+				atomic64_inc(&ca->stats_dscp_set);
 			} else {
-				ca->stats_dscp_error++;
+				atomic64_inc(&ca->stats_dscp_error);
 			}
 		}
 		break;
@@ -72,7 +72,7 @@ static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca,
 				  struct tcf_ctinfo_params *cp,
 				  struct sk_buff *skb)
 {
-	ca->stats_cpmark_set++;
+	atomic64_inc(&ca->stats_cpmark_set);
 	skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask;
 }
 
@@ -323,15 +323,18 @@ static int tcf_ctinfo_dump(struct sk_buff *skb, struct tc_action *a,
 	}
 
 	if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_SET,
-			      ci->stats_dscp_set, TCA_CTINFO_PAD))
+			      atomic64_read(&ci->stats_dscp_set),
+			      TCA_CTINFO_PAD))
 		goto nla_put_failure;
 
 	if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_ERROR,
-			      ci->stats_dscp_error, TCA_CTINFO_PAD))
+			      atomic64_read(&ci->stats_dscp_error),
+			      TCA_CTINFO_PAD))
 		goto nla_put_failure;
 
 	if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_CPMARK_SET,
-			      ci->stats_cpmark_set, TCA_CTINFO_PAD))
+			      atomic64_read(&ci->stats_cpmark_set),
+			      TCA_CTINFO_PAD))
 		goto nla_put_failure;
 
 	spin_unlock_bh(&ci->tcf_lock);
Signature · 1 line
2.39.5
author maintainer
#223 lore raw

PATCH 213/627 RDMA/mlx5: Fix UMR modifying of mkey page size

In reply to Greg Kroah-Hartman

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

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

From: Edward Srouji <[email protected]>

[ Upstream commit c4f96972c3c206ac8f6770b5ecd5320b561d0058 ]

When changing the page size on an mkey, the driver needs to set the appropriate bits in the mkey mask to indicate which fields are being modified.
The 6th bit of a page size in mlx5 driver is considered an extension, and this bit has a dedicated capability and mask bits.

Previously, the driver was not setting this mask in the mkey mask when performing page size changes, regardless of its hardware support, potentially leading to an incorrect page size updates.

This fixes the issue by setting the relevant bit in the mkey mask when performing page size changes on an mkey and the 6th bit of this field is supported by the hardware.

---
 drivers/infiniband/hw/mlx5/umr.c | 6 ++++--
 include/linux/mlx5/device.h      | 1 +
 2 files changed, 5 insertions(+), 2 deletions(-)
drivers/infiniband/hw/mlx5/umr.c +4 -2
index 5be4426a2884..25601dea9e30 100644
@@ -32,13 +32,15 @@ static __be64 get_umr_disable_mr_mask(void)
 	return cpu_to_be64(result);
 }
 
-static __be64 get_umr_update_translation_mask(void)
+static __be64 get_umr_update_translation_mask(struct mlx5_ib_dev *dev)
 {
 	u64 result;
 
 	result = MLX5_MKEY_MASK_LEN |
 		 MLX5_MKEY_MASK_PAGE_SIZE |
 		 MLX5_MKEY_MASK_START_ADDR;
+	if (MLX5_CAP_GEN_2(dev->mdev, umr_log_entity_size_5))
+		result |= MLX5_MKEY_MASK_PAGE_SIZE_5;
 
 	return cpu_to_be64(result);
 }
@@ -654,7 +656,7 @@ static void mlx5r_umr_final_update_xlt(struct mlx5_ib_dev *dev,
 		flags & MLX5_IB_UPD_XLT_ENABLE || flags & MLX5_IB_UPD_XLT_ADDR;
 
 	if (update_translation) {
-		wqe->ctrl_seg.mkey_mask |= get_umr_update_translation_mask();
+		wqe->ctrl_seg.mkey_mask |= get_umr_update_translation_mask(dev);
 		if (!mr->ibmr.length)
 			MLX5_SET(mkc, &wqe->mkey_seg, length64, 1);
 	}
include/linux/mlx5/device.h +1 -0
index 6822cfa5f4ad..9d2467f982ad 100644
@@ -280,6 +280,7 @@ enum {
 	MLX5_MKEY_MASK_SMALL_FENCE	= 1ull << 23,
 	MLX5_MKEY_MASK_RELAXED_ORDERING_WRITE	= 1ull << 25,
 	MLX5_MKEY_MASK_FREE			= 1ull << 29,
+	MLX5_MKEY_MASK_PAGE_SIZE_5		= 1ull << 42,
 	MLX5_MKEY_MASK_RELAXED_ORDERING_READ	= 1ull << 47,
 };
 
Signature · 1 line
2.39.5
author maintainer
#224 lore raw

PATCH 214/627 xen: fix UAF in dmabuf_exp_from_pages()

In reply to Greg Kroah-Hartman

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

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

From: Al Viro <[email protected]>

[ Upstream commit 532c8b51b3a8676cbf533a291f8156774f30ea87 ]

[dma_buf_fd() fixes; no preferences regarding the tree it goes through - up to xen folks]

As soon as we'd inserted a file reference into descriptor table, another thread could close it. That's fine for the case when all we are doing is returning that descriptor to userland (it's a race, but it's a userland race and there's nothing the kernel can do about it). However, if we follow fd_install() with any kind of access to objects that would be destroyed on close (be it the struct file itself or anything destroyed by its ->release()), we have a UAF.

dma_buf_fd() is a combination of reserving a descriptor and fd_install(). gntdev dmabuf_exp_from_pages() calls it and then proceeds to access the objects destroyed on close - starting with gntdev_dmabuf itself.

Fix that by doing reserving descriptor before anything else and do fd_install() only when everything had been set up.

Fixes a240d6e42e28 ("xen/gntdev: Implement dma-buf export functionality")

Message-ID: <20250712050916.GY1880847@ZenIV>

---
 drivers/xen/gntdev-dmabuf.c | 28 ++++++++++------------------
 1 file changed, 10 insertions(+), 18 deletions(-)
drivers/xen/gntdev-dmabuf.c +10 -18
index 5453d86324f6..82855105ab85 100644
@@ -357,8 +357,11 @@ struct gntdev_dmabuf_export_args {
 static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args)
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
-	struct gntdev_dmabuf *gntdev_dmabuf;
-	int ret;
+	struct gntdev_dmabuf *gntdev_dmabuf __free(kfree) = NULL;
+	CLASS(get_unused_fd, ret)(O_CLOEXEC);
+
+	if (ret < 0)
+		return ret;
 
 	gntdev_dmabuf = kzalloc(sizeof(*gntdev_dmabuf), GFP_KERNEL);
 	if (!gntdev_dmabuf)
@@ -383,32 +386,21 @@ static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args)
 	exp_info.priv = gntdev_dmabuf;
 
 	gntdev_dmabuf->dmabuf = dma_buf_export(&exp_info);
-	if (IS_ERR(gntdev_dmabuf->dmabuf)) {
-		ret = PTR_ERR(gntdev_dmabuf->dmabuf);
-		gntdev_dmabuf->dmabuf = NULL;
-		goto fail;
-	}
-
-	ret = dma_buf_fd(gntdev_dmabuf->dmabuf, O_CLOEXEC);
-	if (ret < 0)
-		goto fail;
+	if (IS_ERR(gntdev_dmabuf->dmabuf))
+		return PTR_ERR(gntdev_dmabuf->dmabuf);
 
 	gntdev_dmabuf->fd = ret;
 	args->fd = ret;
 
 	pr_debug("Exporting DMA buffer with fd %d\n", ret);
 
+	get_file(gntdev_dmabuf->priv->filp);
 	mutex_lock(&args->dmabuf_priv->lock);
 	list_add(&gntdev_dmabuf->next, &args->dmabuf_priv->exp_list);
 	mutex_unlock(&args->dmabuf_priv->lock);
-	get_file(gntdev_dmabuf->priv->filp);
-	return 0;
 
-fail:
-	if (gntdev_dmabuf->dmabuf)
-		dma_buf_put(gntdev_dmabuf->dmabuf);
-	kfree(gntdev_dmabuf);
-	return ret;
+	fd_install(take_fd(ret), no_free_ptr(gntdev_dmabuf)->dmabuf->file);
+	return 0;
 }
 
 static struct gntdev_grant_map *
Signature · 1 line
2.39.5
author maintainer
#225 lore raw

PATCH 215/627 sched/deadline: Initialize dl_servers after SMP

In reply to Greg Kroah-Hartman

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

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

From: Juri Lelli <[email protected]>

[ Upstream commit 9f239df55546ee1d28f0976130136ffd1cad0fd7 ]

dl-servers are currently initialized too early at boot when CPUs are not fully up (only boot CPU is). This results in miscalculation of per runqueue DEADLINE variables like extra_bw (which needs a stable CPU count).

Move initialization of dl-servers later on after SMP has been initialized and CPUs are all online, so that CPU count is stable and DEADLINE variables can be computed correctly.

---
 kernel/sched/core.c     |  2 ++
 kernel/sched/deadline.c | 48 +++++++++++++++++++++++++----------------
 kernel/sched/sched.h    |  1 +
 3 files changed, 33 insertions(+), 18 deletions(-)
kernel/sched/core.c +2 -0
index 81c6df746df1..deb6a8cce1ab 100644
@@ -8470,6 +8470,8 @@ void __init sched_init_smp(void)
 	init_sched_rt_class();
 	init_sched_dl_class();
 
+	sched_init_dl_servers();
+
 	sched_smp_initialized = true;
 }
 
kernel/sched/deadline.c +30 -18

72 lines not on this page · raw message

kernel/sched/sched.h +1 -0
index 83e3aa917142..e8e6011fe0d8 100644
@@ -384,6 +384,7 @@ extern void dl_server_stop(struct sched_dl_entity *dl_se);
 extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 		    dl_server_has_tasks_f has_tasks,
 		    dl_server_pick_f pick_task);
+extern void sched_init_dl_servers(void);
 
 extern void dl_server_update_idle_time(struct rq *rq,
 		    struct task_struct *p);
Signature · 1 line
2.39.5
author maintainer
#226 lore raw

PATCH 216/627 sched/deadline: Reset extra_bw to max_bw when clearing root domains

In reply to Greg Kroah-Hartman

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

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

From: Juri Lelli <[email protected]>

[ Upstream commit fcc9276c4d331cd1fe9319d793e80b02e09727f5 ]

dl_clear_root_domain() doesn't take into account the fact that per-rq extra_bw variables retain values computed before root domain changes, resulting in broken accounting.

Fix it by resetting extra_bw to max_bw before restoring back dl-servers contributions.

---
 kernel/sched/deadline.c | 7 +++++++
 1 file changed, 7 insertions(+)
kernel/sched/deadline.c +7 -0
index ef5b5c045769..135580a41e14 100644
@@ -3007,7 +3007,14 @@ void dl_clear_root_domain(struct root_domain *rd)
 	int i;
 
 	guard(raw_spinlock_irqsave)(&rd->dl_bw.lock);
+
+	/*
+	 * Reset total_bw to zero and extra_bw to max_bw so that next
+	 * loop will add dl-servers contributions back properly,
+	 */
 	rd->dl_bw.total_bw = 0;
+	for_each_cpu(i, rd->span)
+		cpu_rq(i)->dl.extra_bw = cpu_rq(i)->dl.max_bw;
 
 	/*
 	 * dl_servers are not tasks. Since dl_add_task_root_domain ignores
Signature · 1 line
2.39.5
author maintainer
#227 lore raw

PATCH 217/627 iommu/vt-d: Do not wipe out the page table NID when devices detach

In reply to Greg Kroah-Hartman

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

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

From: Jason Gunthorpe <[email protected]>

[ Upstream commit 5c3687d5789cfff8d285a2c76bceb47f145bf01f ]

The NID is used to control which NUMA node memory for the page table is allocated it from. It should be a permanent property of the page table when it was allocated and not change during attach/detach of devices.

---
 drivers/iommu/intel/iommu.c | 1 -
 1 file changed, 1 deletion(-)
drivers/iommu/intel/iommu.c +0 -1
index 148b944143b8..72b477911fdb 100644
@@ -1391,7 +1391,6 @@ void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 	if (--info->refcnt == 0) {
 		ida_free(&iommu->domain_ida, info->did);
 		xa_erase(&domain->iommu_array, iommu->seq_id);
-		domain->nid = NUMA_NO_NODE;
 		kfree(info);
 	}
 }
Signature · 1 line
2.39.5
author maintainer
#228 lore raw

PATCH 218/627 iommu/vt-d: Fix missing PASID in dev TLB flush with cache_tag_flush_all

In reply to Greg Kroah-Hartman

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

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

From: Ethan Milon <[email protected]>

[ Upstream commit 3141153816bf4f0257747bd4dda176d38f1a9a49 ]

The function cache_tag_flush_all() was originally implemented with incorrect device TLB invalidation logic that does not handle PASID, in commit c4d27ffaa8eb ("iommu/vt-d: Add cache tag invalidation helpers")

This causes regressions where full address space TLB invalidations occur with a PASID attached, such as during transparent hugepage unmapping in SVA configurations or when calling iommu_flush_iotlb_all(). In these cases, the device receives a TLB invalidation that lacks PASID.

This incorrect logic was later extracted into cache_tag_flush_devtlb_all(), in commit 3297d047cd7f ("iommu/vt-d:
Refactor IOTLB and Dev-IOTLB flush for batching")

The fix replaces the call to cache_tag_flush_devtlb_all() with cache_tag_flush_devtlb_psi(), which properly handles PASID.

Fixes 4f609dbff51b ("iommu/vt-d: Use cache helpers in arch_invalidate_secondary_tlbs")
Fixes 4e589a53685c ("iommu/vt-d: Use cache_tag_flush_all() in flush_iotlb_all")
---
 drivers/iommu/intel/cache.c | 18 +-----------------
 1 file changed, 1 insertion(+), 17 deletions(-)
drivers/iommu/intel/cache.c +1 -17
index 47692cbfaabd..c8b79de84d3f 100644
@@ -422,22 +422,6 @@ static void cache_tag_flush_devtlb_psi(struct dmar_domain *domain, struct cache_
 					     domain->qi_batch);
 }
 
-static void cache_tag_flush_devtlb_all(struct dmar_domain *domain, struct cache_tag *tag)
-{
-	struct intel_iommu *iommu = tag->iommu;
-	struct device_domain_info *info;
-	u16 sid;
-
-	info = dev_iommu_priv_get(tag->dev);
-	sid = PCI_DEVID(info->bus, info->devfn);
-
-	qi_batch_add_dev_iotlb(iommu, sid, info->pfsid, info->ats_qdep, 0,
-			       MAX_AGAW_PFN_WIDTH, domain->qi_batch);
-	if (info->dtlb_extra_inval)
-		qi_batch_add_dev_iotlb(iommu, sid, info->pfsid, info->ats_qdep, 0,
-				       MAX_AGAW_PFN_WIDTH, domain->qi_batch);
-}
-
 /*
  * Invalidates a range of IOVA from @start (inclusive) to @end (inclusive)
  * when the memory mappings in the target domain have been modified.
@@ -508,7 +492,7 @@ void cache_tag_flush_all(struct dmar_domain *domain)
 			break;
 		case CACHE_TAG_DEVTLB:
 		case CACHE_TAG_NESTING_DEVTLB:
-			cache_tag_flush_devtlb_all(domain, tag);
+			cache_tag_flush_devtlb_psi(domain, tag, 0, MAX_AGAW_PFN_WIDTH);
 			break;
 		}
 
Signature · 1 line
2.39.5
author maintainer
#229 lore raw

PATCH 219/627 iommu/arm-smmu: disable PRR on SM8250

In reply to Greg Kroah-Hartman

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

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

From: Dmitry Baryshkov <[email protected]>

[ Upstream commit b9bb7e814cd0c3633791327a96749a1f9b7f3ef4 ]

On SM8250 / QRB5165-RB5 using PRR bits resets the device, most likely because of the hyp limitations. Disable PRR support on that platform.

---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +2 -1
index 62874b18f645..53d88646476e 100644
@@ -355,7 +355,8 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 	priv->set_prr_addr = NULL;
 
 	if (of_device_is_compatible(np, "qcom,smmu-500") &&
-			of_device_is_compatible(np, "qcom,adreno-smmu")) {
+	    !of_device_is_compatible(np, "qcom,sm8250-smmu-500") &&
+	    of_device_is_compatible(np, "qcom,adreno-smmu")) {
 		priv->set_prr_bit = qcom_adreno_smmu_set_prr_bit;
 		priv->set_prr_addr = qcom_adreno_smmu_set_prr_addr;
 	}
Signature · 1 line
2.39.5
author maintainer
#230 lore raw

PATCH 220/627 xen/gntdev: remove struct gntdev_copy_batch from stack

In reply to Greg Kroah-Hartman

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

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

From: Juergen Gross <[email protected]>

[ Upstream commit 70045cf6593cbf0740956ea9b7b4269142c6ee38 ]

When compiling the kernel with LLVM, the following warning was issued:

drivers/xen/gntdev.c:991: warning: stack frame size (1160) exceeds limit (1024) in function 'gntdev_ioctl'

The main reason is struct gntdev_copy_batch which is located on the stack and has a size of nearly 1kb.

For performance reasons it shouldn't by just dynamically allocated instead, so allocate a new instance when needed and instead of freeing it put it into a list of free structs anchored in struct gntdev_priv.

Fixes a4cdb556cae0 ("xen/gntdev: add ioctl for grant copy")

Message-ID: <[email protected]>

---
 drivers/xen/gntdev-common.h |  4 +++
 drivers/xen/gntdev.c        | 71 ++++++++++++++++++++++++++-----------
 2 files changed, 54 insertions(+), 21 deletions(-)
drivers/xen/gntdev-common.h +4 -0
index 9c286b2a1900..ac8ce3179ba2 100644
@@ -26,6 +26,10 @@ struct gntdev_priv {
 	/* lock protects maps and freeable_maps. */
 	struct mutex lock;
 
+	/* Free instances of struct gntdev_copy_batch. */
+	struct gntdev_copy_batch *batch;
+	struct mutex batch_lock;
+
 #ifdef CONFIG_XEN_GRANT_DMA_ALLOC
 	/* Device for which DMA memory is allocated. */
 	struct device *dma_dev;
drivers/xen/gntdev.c +50 -21

127 lines not on this page · raw message

Signature · 1 line
2.39.5
author maintainer
#231 lore raw

PATCH 221/627 tcp: call tcp_measure_rcv_mss() for ooo packets

In reply to Greg Kroah-Hartman

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 38d7e444336567bae1c7b21fc18b7ceaaa5643a0 ]

tcp_measure_rcv_mss() is used to update icsk->icsk_ack.rcv_mss (tcpi_rcv_mss in tcp_info) and tp->scaling_ratio.

Calling it from tcp_data_queue_ofo() makes sure these fields are updated, and permits a better tuning of sk->sk_rcvbuf, in the case a new flow receives many ooo packets.

---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)
net/ipv4/tcp_input.c +1 -0
index 76b01df70e56..94391f32a5d8 100644
@@ -5055,6 +5055,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		return;
 	}
 
+	tcp_measure_rcv_mss(sk, skb);
 	/* Disable header prediction. */
 	tp->pred_flags = 0;
 	inet_csk_schedule_ack(sk);
Signature · 1 line
2.39.5
author maintainer
#232 lore raw

PATCH 222/627 wifi: rtl8xxxu: Fix RX skb size for aggregation disabled

In reply to Greg Kroah-Hartman

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

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

From: Martin Kaistra <[email protected]>

[ Upstream commit d76a1abcf57734d2bcd4a7ec051617edd4513d7f ]

Commit 1e5b3b3fe9e0 ("rtl8xxxu: Adjust RX skb size to include space for phystats") increased the skb size when aggregation is enabled but decreased it for the aggregation disabled case.

As a result, if a frame near the maximum size is received, rtl8xxxu_rx_complete() is called with status -EOVERFLOW and then the driver starts to malfunction and no further communication is possible.

Restore the skb size in the aggregation disabled case.

Fixes 1e5b3b3fe9e0 ("rtl8xxxu: Adjust RX skb size to include space for phystats")
---
 drivers/net/wireless/realtek/rtl8xxxu/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/wireless/realtek/rtl8xxxu/core.c +1 -1
index 569856ca677f..c6f69d87c38d 100644
@@ -6617,7 +6617,7 @@ static int rtl8xxxu_submit_rx_urb(struct rtl8xxxu_priv *priv,
 		skb_size = fops->rx_agg_buf_size;
 		skb_size += (rx_desc_sz + sizeof(struct rtl8723au_phy_stats));
 	} else {
-		skb_size = IEEE80211_MAX_FRAME_LEN;
+		skb_size = IEEE80211_MAX_FRAME_LEN + rx_desc_sz;
 	}
 
 	skb = __netdev_alloc_skb(NULL, skb_size, GFP_KERNEL);
Signature · 1 line
2.39.5
author maintainer
#233 lore raw

PATCH 223/627 wifi: rtw88: Fix macid assigned to TDLS station

In reply to Greg Kroah-Hartman

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

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

From: Bitterblue Smith <[email protected]>

[ Upstream commit 526b000991b557c40ea53e64ba24bb9e0fff0071 ]

When working in station mode, TDLS peers are assigned macid 0, even though 0 was already assigned to the AP. This causes the connection with the AP to stop working after the TDLS connection is torn down.

Assign the next available macid to TDLS peers, same as client stations in AP mode.

Fixes 902cb7b11f9a ("wifi: rtw88: assign mac_id for vif/sta and update to TX desc")
---
 drivers/net/wireless/realtek/rtw88/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/wireless/realtek/rtw88/main.c +2 -2
index c4de5d114eda..8be6e70d92d1 100644
@@ -349,7 +349,7 @@ int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
 	struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv;
 	int i;
 
-	if (vif->type == NL80211_IFTYPE_STATION) {
+	if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls) {
 		si->mac_id = rtwvif->mac_id;
 	} else {
 		si->mac_id = rtw_acquire_macid(rtwdev);
@@ -386,7 +386,7 @@ void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
 
 	cancel_work_sync(&si->rc_work);
 
-	if (vif->type != NL80211_IFTYPE_STATION)
+	if (vif->type != NL80211_IFTYPE_STATION || sta->tdls)
 		rtw_release_macid(rtwdev, si->mac_id);
 	if (fw_exist)
 		rtw_fw_media_status_report(rtwdev, si->mac_id, false);
Signature · 1 line
2.39.5
author maintainer
#234 lore raw

PATCH 224/627 mwl8k: Add missing check after DMA map

In reply to Greg Kroah-Hartman

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 50459501b9a212dbe7a673727589ee105a8a9954 ]

The DMA map functions can fail and should be tested for errors. If the mapping fails, unmap and return an error.

Fixes 788838ebe8a4 ("mwl8k: use pci_unmap_addr{,set}() to keep track of unmap addresses on rx")
---
 drivers/net/wireless/marvell/mwl8k.c | 4 ++++
 1 file changed, 4 insertions(+)
drivers/net/wireless/marvell/mwl8k.c +4 -0
index bab9ef37a1ab..8bcb1d0dd618 100644
@@ -1227,6 +1227,10 @@ static int rxq_refill(struct ieee80211_hw *hw, int index, int limit)
 
 		addr = dma_map_single(&priv->pdev->dev, skb->data,
 				      MWL8K_RX_MAXSZ, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&priv->pdev->dev, addr)) {
+			kfree_skb(skb);
+			break;
+		}
 
 		rxq->rxd_count++;
 		rx = rxq->tail++;
Signature · 1 line
2.39.5
author maintainer
#235 lore raw

PATCH 225/627 wifi: mac80211: use RCU-safe iteration in ieee80211_csa_finish

In reply to Greg Kroah-Hartman

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

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

From: Maharaja Kennadyrajan <[email protected]>

[ Upstream commit 9975aeebe2908cdd552ee59607754755459fad52 ]

The ieee80211_csa_finish() function currently uses for_each_sdata_link() to iterate over links of sdata. However, this macro internally uses wiphy_dereference(), which expects the wiphy->mtx lock to be held. When ieee80211_csa_finish() is invoked under an RCU read-side critical section (e.g., under rcu_read_lock()), this leads to a warning from the RCU debugging framework.

WARNING: suspicious RCU usage
net/mac80211/cfg.c:3830 suspicious rcu_dereference_protected() usage!

This warning is triggered because wiphy_dereference() is not safe to use without holding the wiphy mutex, and it is being used in an RCU context without the required locking.

Fix this by introducing and using a new macro, for_each_sdata_link_rcu(), which performs RCU-safe iteration over sdata links using list_for_each_entry_rcu() and rcu_dereference(). This ensures that the link pointers are accessed safely under RCU and eliminates the warning.

Fixes f600832794c9 ("wifi: mac80211: restructure tx profile retrieval for MLO MBSSID")
[unindent like the non-RCU macro]
---
 net/mac80211/cfg.c         |  2 +-
 net/mac80211/ieee80211_i.h | 15 +++++++++++++++
 2 files changed, 16 insertions(+), 1 deletion(-)
net/mac80211/cfg.c +1 -1
index bc64c1b83a6e..18ad7ab1bb8c 100644
@@ -3760,7 +3760,7 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id)
 		 */
 		struct ieee80211_link_data *iter;
 
-		for_each_sdata_link(local, iter) {
+		for_each_sdata_link_rcu(local, iter) {
 			if (iter->sdata == sdata ||
 			    rcu_access_pointer(iter->conf->tx_bss_conf) != tx_bss_conf)
 				continue;
net/mac80211/ieee80211_i.h +15 -0
index 30809f0b35f7..f71d9eeb8abc 100644
@@ -1226,6 +1226,21 @@ struct ieee80211_sub_if_data *vif_to_sdata(struct ieee80211_vif *p)
 	if ((_link = wiphy_dereference((_local)->hw.wiphy,		\
 				       ___sdata->link[___link_id])))
 
+/*
+ * for_each_sdata_link_rcu() must be used under RCU read lock.
+ */
+#define for_each_sdata_link_rcu(_local, _link)						\
+	/* outer loop just to define the variables ... */				\
+	for (struct ieee80211_sub_if_data *___sdata = NULL;				\
+	     !___sdata;									\
+	     ___sdata = (void *)~0 /* always stop */)					\
+	list_for_each_entry_rcu(___sdata, &(_local)->interfaces, list)			\
+	if (ieee80211_sdata_running(___sdata))						\
+	for (int ___link_id = 0;							\
+	     ___link_id < ARRAY_SIZE((___sdata)->link);					\
+	     ___link_id++)								\
+	if ((_link = rcu_dereference((___sdata)->link[___link_id])))
+
 #define for_each_link_data(sdata, __link)					\
 	struct ieee80211_sub_if_data *__sdata = sdata;				\
 	for (int __link_id = 0;							\
Signature · 1 line
2.39.5
author maintainer
#236 lore raw

PATCH 226/627 wifi: ath12k: Use HTT_TCL_METADATA_VER_V1 in FTM mode

In reply to Greg Kroah-Hartman

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

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

From: Aaradhana Sahu <[email protected]>

[ Upstream commit 66b3ebc77d23d6574a965bdbfe41de8aeb7f384e ]

Currently host sends HTT_TCL_METADATA_VER_V2 to the firmware regardless of the operating mode (Mission or FTM).

Firmware expects additional software information (like peer ID, vdev ID, and link ID) in Tx packets when HTT_TCL_METADATA_VER_V2 is set. However, in FTM (Factory Test Mode) mode, no vdev is created on the host side (this is expected). As a result, the firmware fails to find the expected vdev during packet processing and ends up dropping packets.

To fix this, send HTT_TCL_METADATA_VER_V1 in FTM mode because FTM mode doesn't support HTT_TCL_METADATA_VER_V2.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.5-01651-QCAHKSWPL_SILICONZ-1

Fixes 5d964966bd3f ("wifi: ath12k: Update HTT_TCL_METADATA version and bit mask definitions")
---
 drivers/net/wireless/ath/ath12k/dp.h    | 1 +
 drivers/net/wireless/ath/ath12k/dp_tx.c | 5 ++++-
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/wireless/ath/ath12k/dp.h +1 -0
index a353333f83b6..2f0718edabd2 100644
@@ -469,6 +469,7 @@ enum htt_h2t_msg_type {
 };
 
 #define HTT_VER_REQ_INFO_MSG_ID		GENMASK(7, 0)
+#define HTT_OPTION_TCL_METADATA_VER_V1	1
 #define HTT_OPTION_TCL_METADATA_VER_V2	2
 #define HTT_OPTION_TAG			GENMASK(7, 0)
 #define HTT_OPTION_LEN			GENMASK(15, 8)
drivers/net/wireless/ath/ath12k/dp_tx.c +4 -1
index 075912eacfaa..7470731eb830 100644
@@ -1182,6 +1182,7 @@ int ath12k_dp_tx_htt_h2t_ver_req_msg(struct ath12k_base *ab)
 	struct sk_buff *skb;
 	struct htt_ver_req_cmd *cmd;
 	int len = sizeof(*cmd);
+	u32 metadata_version;
 	int ret;
 
 	init_completion(&dp->htt_tgt_version_received);
@@ -1194,12 +1195,14 @@ int ath12k_dp_tx_htt_h2t_ver_req_msg(struct ath12k_base *ab)
 	cmd = (struct htt_ver_req_cmd *)skb->data;
 	cmd->ver_reg_info = le32_encode_bits(HTT_H2T_MSG_TYPE_VERSION_REQ,
 					     HTT_OPTION_TAG);
+	metadata_version = ath12k_ftm_mode ? HTT_OPTION_TCL_METADATA_VER_V1 :
+			   HTT_OPTION_TCL_METADATA_VER_V2;
 
 	cmd->tcl_metadata_version = le32_encode_bits(HTT_TAG_TCL_METADATA_VERSION,
 						     HTT_OPTION_TAG) |
 				    le32_encode_bits(HTT_TCL_METADATA_VER_SZ,
 						     HTT_OPTION_LEN) |
-				    le32_encode_bits(HTT_OPTION_TCL_METADATA_VER_V2,
+				    le32_encode_bits(metadata_version,
 						     HTT_OPTION_VALUE);
 
 	ret = ath12k_htc_send(&ab->htc, dp->eid, skb);
Signature · 1 line
2.39.5
author maintainer
#237 lore raw

PATCH 227/627 wifi: ath11k: fix sleeping-in-atomic in ath11k_mac_op_set_bitrate_mask()

In reply to Greg Kroah-Hartman

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

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

From: Baochen Qiang <[email protected]>

[ Upstream commit 65c12b104cb942d588a1a093acc4537fb3d3b129 ]

ath11k_mac_disable_peer_fixed_rate() is passed as the iterator to ieee80211_iterate_stations_atomic(). Note in this case the iterator is required to be atomic, however ath11k_mac_disable_peer_fixed_rate() does not follow it as it might sleep. Consequently below warning is seen:

BUG: sleeping function called from invalid context at wmi.c:304
Call Trace:
 <TASK>
 dump_stack_lvl
 __might_resched.cold
 ath11k_wmi_cmd_send
 ath11k_wmi_set_peer_param
 ath11k_mac_disable_peer_fixed_rate
 ieee80211_iterate_stations_atomic
 ath11k_mac_op_set_bitrate_mask.cold

Change to ieee80211_iterate_stations_mtx() to fix this issue.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30

---
 drivers/net/wireless/ath/ath11k/mac.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
drivers/net/wireless/ath/ath11k/mac.c +6 -6
index 13301ca317a5..977f370fd6de 100644
@@ -8740,9 +8740,9 @@ ath11k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw,
 				    arvif->vdev_id, ret);
 			return ret;
 		}
-		ieee80211_iterate_stations_atomic(ar->hw,
-						  ath11k_mac_disable_peer_fixed_rate,
-						  arvif);
+		ieee80211_iterate_stations_mtx(ar->hw,
+					       ath11k_mac_disable_peer_fixed_rate,
+					       arvif);
 	} else if (ath11k_mac_bitrate_mask_get_single_nss(ar, arvif, band, mask,
 							  &single_nss)) {
 		rate = WMI_FIXED_RATE_NONE;
@@ -8809,9 +8809,9 @@ ath11k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw,
 		}
 
 		mutex_lock(&ar->conf_mutex);
-		ieee80211_iterate_stations_atomic(ar->hw,
-						  ath11k_mac_disable_peer_fixed_rate,
-						  arvif);
+		ieee80211_iterate_stations_mtx(ar->hw,
+					       ath11k_mac_disable_peer_fixed_rate,
+					       arvif);
 
 		arvif->bitrate_mask = *mask;
 		ieee80211_iterate_stations_atomic(ar->hw,
Signature · 1 line
2.39.5
author maintainer
#238 lore raw

PATCH 228/627 drm/amdgpu/gfx9: fix kiq locking in KCQ reset

In reply to Greg Kroah-Hartman

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

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

From: Alex Deucher <[email protected]>

[ Upstream commit 730ea5074dac1b105717316be5d9c18b09829385 ]

The ring test needs to be inside the lock.

Fixes fdbd69486b46 ("drm/amdgpu/gfx9: wait for reset done before remap")
Cc Jiadong Zhu <[email protected]>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +1 -1
index 23f998181561..f768c407771a 100644
@@ -7280,8 +7280,8 @@ static int gfx_v9_0_reset_kcq(struct amdgpu_ring *ring,
 	}
 	kiq->pmf->kiq_map_queues(kiq_ring, ring);
 	amdgpu_ring_commit(kiq_ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r) {
 		DRM_ERROR("fail to remap queue\n");
 		return r;
Signature · 1 line
2.39.5
author maintainer
#239 lore raw

PATCH 229/627 drm/amdgpu/gfx9.4.3: fix kiq locking in KCQ reset

In reply to Greg Kroah-Hartman

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

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

From: Alex Deucher <[email protected]>

[ Upstream commit 08f116c59310728ea8b7e9dc3086569006c861cf ]

The ring test needs to be inside the lock.

Fixes 4c953e53cc34 ("drm/amdgpu/gfx_9.4.3: wait for reset done before remap")
Cc Jiadong Zhu <[email protected]>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +1 -2
index 264b37e85696..b3c842ec17ee 100644
@@ -3612,9 +3612,8 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
 	}
 	kiq->pmf->kiq_map_queues(kiq_ring, ring);
 	amdgpu_ring_commit(kiq_ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
-
 	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r) {
 		dev_err(adev->dev, "fail to remap queue\n");
 		return r;
Signature · 1 line
2.39.5
author maintainer
#240 lore raw

PATCH 230/627 drm/amdgpu/gfx10: fix kiq locking in KCQ reset

In reply to Greg Kroah-Hartman

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

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

From: Alex Deucher <[email protected]>

[ Upstream commit a4b2ba8f631d3e44b30b9b46ee290fbfe608b7d0 ]

The ring test needs to be inside the lock.

Fixes 097af47d3cfb ("drm/amdgpu/gfx10: wait for reset done before remap")
Cc Jiadong Zhu <[email protected]>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +2 -4
index e7df0487eaae..961d5e0af052 100644
@@ -9617,9 +9617,8 @@ static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
 	kiq->pmf->kiq_unmap_queues(kiq_ring, ring, RESET_QUEUES,
 				   0, 0);
 	amdgpu_ring_commit(kiq_ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
-
 	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r)
 		return r;
 
@@ -9655,9 +9654,8 @@ static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
 	}
 	kiq->pmf->kiq_map_queues(kiq_ring, ring);
 	amdgpu_ring_commit(kiq_ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
-
 	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r)
 		return r;
 
Signature · 1 line
2.39.5
author maintainer
#241 lore raw

PATCH 231/627 selftests/bpf: fix implementation of smp_mb()

In reply to Greg Kroah-Hartman

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

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

From: Puranjay Mohan <[email protected]>

[ Upstream commit 0769857a07b4451a1dc1c3ad1f1c86a6f4ce136a ]

As BPF doesn't include any barrier instructions, smp_mb() is implemented by doing a dummy value returning atomic operation. Such an operation acts a full barrier as enforced by LKMM and also by the work in progress BPF memory model.

If the returned value is not used, clang[1] can optimize the value returning atomic instruction in to a normal atomic instruction which provides no ordering guarantees.

Mark the variable as volatile so the above optimization is never performed and smp_mb() works as expected.

[1] https://godbolt.org/z/qzze7bG6z

Fixes 88d706ba7cc5 ("selftests/bpf: Introduce arena spin lock")
---
 tools/testing/selftests/bpf/bpf_atomic.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/bpf/bpf_atomic.h +1 -1
index a9674e544322..c550e5711967 100644
@@ -61,7 +61,7 @@ extern bool CONFIG_X86_64 __kconfig __weak;
 
 #define smp_mb()                                 \
 	({                                       \
-		unsigned long __val;             \
+		volatile unsigned long __val;    \
 		__sync_fetch_and_add(&__val, 0); \
 	})
 
Signature · 1 line
2.39.5
author maintainer
#242 lore raw

PATCH 232/627 iommu/amd: Fix geometry.aperture_end for V2 tables

In reply to Greg Kroah-Hartman

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

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

From: Jason Gunthorpe <[email protected]>

[ Upstream commit 8637afa79cfa6123f602408cfafe8c9a73620ff1 ]

The AMD IOMMU documentation seems pretty clear that the V2 table follows the normal CPU expectation of sign extension. This is shown in

Figure 25: AMD64 Long Mode 4-Kbyte Page Address Translation

Where bits Sign-Extend [63:57] == [56]. This is typical for x86 which would have three regions in the page table: lower, non-canonical, upper.

The manual describes that the V1 table does not sign extend in section 2.2.4 Sharing AMD64 Processor and IOMMU Page Tables GPA-to-SPA

Further, Vasant has checked this and indicates the HW has an addtional behavior that the manual does not yet describe. The AMDv2 table does not have the sign extended behavior when attached to PASID 0, which may explain why this has gone unnoticed.

The iommu domain geometry does not directly support sign extended page tables. The driver should report only one of the lower/upper spaces. Solve this by removing the top VA bit from the geometry to use only the lower space.

This will also make the iommu_domain work consistently on all PASID 0 and PASID != 1.

Adjust dma_max_address() to remove the top VA bit. It now returns:

5 Level:
Before 0x1ffffffffffffff
After 0x0ffffffffffffff
4 Level:
Before 0xffffffffffff
After 0x7fffffffffff

---
 drivers/iommu/amd/iommu.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)
drivers/iommu/amd/iommu.c +15 -2
index 8b8d3e843743..aea061f26de3 100644
@@ -2526,8 +2526,21 @@ static inline u64 dma_max_address(enum protection_domain_mode pgtable)
 	if (pgtable == PD_MODE_V1)
 		return ~0ULL;
 
-	/* V2 with 4/5 level page table */
-	return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1);
+	/*
+	 * V2 with 4/5 level page table. Note that "2.2.6.5 AMD64 4-Kbyte Page
+	 * Translation" shows that the V2 table sign extends the top of the
+	 * address space creating a reserved region in the middle of the
+	 * translation, just like the CPU does. Further Vasant says the docs are
+	 * incomplete and this only applies to non-zero PASIDs. If the AMDv2
+	 * page table is assigned to the 0 PASID then there is no sign extension
+	 * check.
+	 *
+	 * Since the IOMMU must have a fixed geometry, and the core code does
+	 * not understand sign extended addressing, we have to chop off the high
+	 * bit to get consistent behavior with attachments of the domain to any
+	 * PASID.
+	 */
+	return ((1ULL << (PM_LEVEL_SHIFT(amd_iommu_gpt_level) - 1)) - 1);
 }
 
 static bool amd_iommu_hd_support(struct amd_iommu *iommu)
Signature · 1 line
2.39.5
author maintainer
#243 lore raw

PATCH 233/627 rcu: Fix delayed execution of hurry callbacks

In reply to Greg Kroah-Hartman

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

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

From: Tze-nan Wu <[email protected]>

[ Upstream commit 463d46044f04013306a4893242f65788b8a16b2e ]

We observed a regression in our customer’s environment after enabling CONFIG_LAZY_RCU. In the Android Update Engine scenario, where ioctl() is used heavily, we found that callbacks queued via call_rcu_hurry (such as percpu_ref_switch_to_atomic_rcu) can sometimes be delayed by up to 5 seconds before execution. This occurs because the new grace period does not start immediately after the previous one completes.

The root cause is that the wake_nocb_gp_defer() function now checks "rdp->nocb_defer_wakeup" instead of "rdp_gp->nocb_defer_wakeup". On CPUs that are not rcuog, "rdp->nocb_defer_wakeup" may always be RCU_NOCB_WAKE_NOT. This can cause "rdp_gp->nocb_defer_wakeup" to be downgraded and the "rdp_gp->nocb_timer" to be postponed by up to 10 seconds, delaying the execution of hurry RCU callbacks.

The trace log of one scenario we encountered is as follow:
// previous GP ends at this point

  rcu_preempt   [000] d..1.   137.240210: rcu_grace_period: rcu_preempt 8369 end
  rcu_preempt   [000] .....   137.240212: rcu_grace_period: rcu_preempt 8372 reqwait
  // call_rcu_hurry enqueues "percpu_ref_switch_to_atomic_rcu", the callback waited on by UpdateEngine
  update_engine [002] d..1.   137.301593: __call_rcu_common: wyy: unlikely p_ref = 00000000********. lazy = 0
  // FirstQ on cpu 2 rdp_gp->nocb_timer is set to fire after 1 jiffy (4ms)
  // and the rdp_gp->nocb_defer_wakeup is set to RCU_NOCB_WAKE
  update_engine [002] d..2.   137.301595: rcu_nocb_wake: rcu_preempt 2 FirstQ on cpu2 with rdp_gp (cpu0).
  // FirstBQ event on cpu2 during the 1 jiffy, make the timer postpond 10 seconds later.
  // also, the rdp_gp->nocb_defer_wakeup is overwrite to RCU_NOCB_WAKE_LAZY
  update_engine [002] d..1.   137.301601: rcu_nocb_wake: rcu_preempt 2 WakeEmptyIsDeferred
  ...
  ...
  ...
  // before the 10 seconds timeout, cpu0 received another call_rcu_hurry
  // reset the timer to jiffies+1 and set the waketype = RCU_NOCB_WAKE.
  kworker/u32:0 [000] d..2.   142.557564: rcu_nocb_wake: rcu_preempt 0 FirstQ
  kworker/u32:0 [000] d..1.   142.557576: rcu_nocb_wake: rcu_preempt 0 WakeEmptyIsDeferred
  kworker/u32:0 [000] d..1.   142.558296: rcu_nocb_wake: rcu_preempt 0 WakeNot
  kworker/u32:0 [000] d..1.   142.558562: rcu_nocb_wake: rcu_preempt 0 WakeNot
  // idle(do_nocb_deferred_wakeup) wake rcuog due to waketype == RCU_NOCB_WAKE
  <idle>        [000] d..1.   142.558786: rcu_nocb_wake: rcu_preempt 0 DoWake
  <idle>        [000] dN.1.   142.558839: rcu_nocb_wake: rcu_preempt 0 DeferredWake
  rcuog/0       [000] .....   142.558871: rcu_nocb_wake: rcu_preempt 0 EndSleep
  rcuog/0       [000] .....   142.558877: rcu_nocb_wake: rcu_preempt 0 Check
  // finally rcuog request a new GP at this point (5 seconds after the FirstQ event)
  rcuog/0       [000] d..2.   142.558886: rcu_grace_period: rcu_preempt 8372 newreq
  rcu_preempt   [001] d..1.   142.559458: rcu_grace_period: rcu_preempt 8373 start
  ...
  rcu_preempt   [000] d..1.   142.564258: rcu_grace_period: rcu_preempt 8373 end
  rcuop/2       [000] D..1.   142.566337: rcu_batch_start: rcu_preempt CBs=219 bl=10

// the hurry CB is invoked at this point
rcuop/2 [000] b.... 142.566352: blk_queue_usage_counter_release: wyy: wakeup. p_ref = 00000000********.

This patch changes the condition to check "rdp_gp->nocb_defer_wakeup" in the lazy path. This prevents an already scheduled "rdp_gp->nocb_timer" from being postponed and avoids overwriting "rdp_gp->nocb_defer_wakeup" when it is not RCU_NOCB_WAKE_NOT.

Fixes 3cb278e73be5 ("rcu: Make call_rcu() lazy to save power")
Co-developed-by [email protected]
Signed-off-by [email protected]
Signed-off-by [email protected]
---
 kernel/rcu/tree_nocb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/rcu/tree_nocb.h +1 -1
index b473ff056f49..711043e4eb54 100644
@@ -276,7 +276,7 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
 	 * callback storms, no need to wake up too early.
 	 */
 	if (waketype == RCU_NOCB_WAKE_LAZY &&
-	    rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) {
+	    rdp_gp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) {
 		mod_timer(&rdp_gp->nocb_timer, jiffies + rcu_get_jiffies_lazy_flush());
 		WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype);
 	} else if (waketype == RCU_NOCB_WAKE_BYPASS) {
Signature · 1 line
2.39.5
author maintainer
#244 lore raw

PATCH 234/627 wifi: mac80211: reject TDLS operations when station is not associated

In reply to Greg Kroah-Hartman

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

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

From: Moon Hee Lee <[email protected]>

[ Upstream commit 16ecdab5446f15a61ec88eb0d23d25d009821db0 ]

syzbot triggered a WARN in ieee80211_tdls_oper() by sending NL80211_TDLS_ENABLE_LINK immediately after NL80211_CMD_CONNECT, before association completed and without prior TDLS setup.

This left internal state like sdata->u.mgd.tdls_peer uninitialized, leading to a WARN_ON() in code paths that assumed it was valid.

Reject the operation early if not in station mode or not associated.

---
 net/mac80211/tdls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/mac80211/tdls.c +1 -1
index 94714f8ffd22..ba5fbacbeeda 100644
@@ -1422,7 +1422,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
 	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
 		return -EOPNOTSUPP;
 
-	if (sdata->vif.type != NL80211_IFTYPE_STATION)
+	if (sdata->vif.type != NL80211_IFTYPE_STATION || !sdata->vif.cfg.assoc)
 		return -EINVAL;
 
 	switch (oper) {
Signature · 1 line
2.39.5
author maintainer
#245 lore raw

PATCH 235/627 wifi: plfxlc: Fix error handling in usb driver probe

In reply to Greg Kroah-Hartman

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

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

From: Murad Masimov <[email protected]>

[ Upstream commit 3fe79a25c3cd54d25d30bc235c0c57f8a123d9d5 ]

If probe fails before ieee80211_register_hw() is successfully done, ieee80211_unregister_hw() will be called anyway. This may lead to various bugs as the implementation of ieee80211_unregister_hw() assumes that ieee80211_register_hw() has been called.

Divide error handling section into relevant subsections, so that ieee80211_unregister_hw() is called only when it is appropriate. Correct the order of the calls: ieee80211_unregister_hw() should go before plfxlc_mac_release(). Also move ieee80211_free_hw() to plfxlc_mac_release() as it supposed to be the opposite to plfxlc_mac_alloc_hw() that calls ieee80211_alloc_hw().

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes 68d57a07bfe5 ("wireless: add plfxlc driver for pureLiFi X, XL, XC devices")
---
 drivers/net/wireless/purelifi/plfxlc/mac.c | 11 ++++----
 drivers/net/wireless/purelifi/plfxlc/mac.h |  2 +-
 drivers/net/wireless/purelifi/plfxlc/usb.c | 29 +++++++++++-----------
 3 files changed, 21 insertions(+), 21 deletions(-)
drivers/net/wireless/purelifi/plfxlc/mac.c +6 -5
index 82d1bf7edba2..a7f5d287e369 100644
@@ -99,11 +99,6 @@ int plfxlc_mac_init_hw(struct ieee80211_hw *hw)
 	return r;
 }
 
-void plfxlc_mac_release(struct plfxlc_mac *mac)
-{
-	plfxlc_chip_release(&mac->chip);
-}
-
 int plfxlc_op_start(struct ieee80211_hw *hw)
 {
 	plfxlc_hw_mac(hw)->chip.usb.initialized = 1;
@@ -755,3 +750,9 @@ struct ieee80211_hw *plfxlc_mac_alloc_hw(struct usb_interface *intf)
 	SET_IEEE80211_DEV(hw, &intf->dev);
 	return hw;
 }
+
+void plfxlc_mac_release_hw(struct ieee80211_hw *hw)
+{
+	plfxlc_chip_release(&plfxlc_hw_mac(hw)->chip);
+	ieee80211_free_hw(hw);
+}
drivers/net/wireless/purelifi/plfxlc/mac.h +1 -1
index 9384acddcf26..56da502999c1 100644
@@ -168,7 +168,7 @@ static inline u8 *plfxlc_mac_get_perm_addr(struct plfxlc_mac *mac)
 }
 
 struct ieee80211_hw *plfxlc_mac_alloc_hw(struct usb_interface *intf);
-void plfxlc_mac_release(struct plfxlc_mac *mac);
+void plfxlc_mac_release_hw(struct ieee80211_hw *hw);
 
 int plfxlc_mac_preinit_hw(struct ieee80211_hw *hw, const u8 *hw_address);
 int plfxlc_mac_init_hw(struct ieee80211_hw *hw);
drivers/net/wireless/purelifi/plfxlc/usb.c +14 -15
index d8b0b79dea1a..711902a809db 100644
@@ -604,7 +604,7 @@ static int probe(struct usb_interface *intf,
 	r = plfxlc_upload_mac_and_serial(intf, hw_address, serial_number);
 	if (r) {
 		dev_err(&intf->dev, "MAC and Serial upload failed (%d)\n", r);
-		goto error;
+		goto error_free_hw;
 	}
 
 	chip->unit_type = STA;
@@ -613,13 +613,13 @@ static int probe(struct usb_interface *intf,
 	r = plfxlc_mac_preinit_hw(hw, hw_address);
 	if (r) {
 		dev_err(&intf->dev, "Init mac failed (%d)\n", r);
-		goto error;
+		goto error_free_hw;
 	}
 
 	r = ieee80211_register_hw(hw);
 	if (r) {
 		dev_err(&intf->dev, "Register device failed (%d)\n", r);
-		goto error;
+		goto error_free_hw;
 	}
 
 	if ((le16_to_cpu(interface_to_usbdev(intf)->descriptor.idVendor) ==
@@ -632,7 +632,7 @@ static int probe(struct usb_interface *intf,
 	}
 	if (r != 0) {
 		dev_err(&intf->dev, "FPGA download failed (%d)\n", r);
-		goto error;
+		goto error_unreg_hw;
 	}
 
 	tx->mac_fifo_full = 0;
@@ -642,21 +642,21 @@ static int probe(struct usb_interface *intf,
 	r = plfxlc_usb_init_hw(usb);
 	if (r < 0) {
 		dev_err(&intf->dev, "usb_init_hw failed (%d)\n", r);
-		goto error;
+		goto error_unreg_hw;
 	}
 
 	msleep(PLF_MSLEEP_TIME);
 	r = plfxlc_chip_switch_radio(chip, PLFXLC_RADIO_ON);
 	if (r < 0) {
 		dev_dbg(&intf->dev, "chip_switch_radio_on failed (%d)\n", r);
-		goto error;
+		goto error_unreg_hw;
 	}
 
 	msleep(PLF_MSLEEP_TIME);
 	r = plfxlc_chip_set_rate(chip, 8);
 	if (r < 0) {
 		dev_dbg(&intf->dev, "chip_set_rate failed (%d)\n", r);
-		goto error;
+		goto error_unreg_hw;
 	}
 
 	msleep(PLF_MSLEEP_TIME);
@@ -664,7 +664,7 @@ static int probe(struct usb_interface *intf,
 			    hw_address, ETH_ALEN, USB_REQ_MAC_WR);
 	if (r < 0) {
 		dev_dbg(&intf->dev, "MAC_WR failure (%d)\n", r);
-		goto error;
+		goto error_unreg_hw;
 	}
 
 	plfxlc_chip_enable_rxtx(chip);
@@ -691,12 +691,12 @@ static int probe(struct usb_interface *intf,
 	plfxlc_mac_init_hw(hw);
 	usb->initialized = true;
 	return 0;
+
+error_unreg_hw:
+	ieee80211_unregister_hw(hw);
+error_free_hw:
+	plfxlc_mac_release_hw(hw);
 error:
-	if (hw) {
-		plfxlc_mac_release(plfxlc_hw_mac(hw));
-		ieee80211_unregister_hw(hw);
-		ieee80211_free_hw(hw);
-	}
 	dev_err(&intf->dev, "pureLifi:Device error");
 	return r;
 }
@@ -730,8 +730,7 @@ static void disconnect(struct usb_interface *intf)
 	 */
 	usb_reset_device(interface_to_usbdev(intf));
 
-	plfxlc_mac_release(mac);
-	ieee80211_free_hw(hw);
+	plfxlc_mac_release_hw(hw);
 }
 
 static void plfxlc_usb_resume(struct plfxlc_usb *usb)
Signature · 1 line
2.39.5
author maintainer
#246 lore raw

PATCH 236/627 wifi: cfg80211: Add missing lock in cfg80211_check_and_end_cac()

In reply to Greg Kroah-Hartman

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

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

From: Alexander Wetzel <[email protected]>

[ Upstream commit 2c5dee15239f3f3e31aa5c8808f18996c039e2c1 ]

Callers of wdev_chandef() must hold the wiphy mutex.

But the worker cfg80211_propagate_cac_done_wk() never takes the lock. Which triggers the warning below with the mesh_peer_connected_dfs test from hostapd and not (yet) released mac80211 code changes:

WARNING: CPU: 0 PID: 495 at net/wireless/chan.c:1552 wdev_chandef+0x60/0x165
Modules linked in:
CPU: 0 UID: 0 PID: 495 Comm: kworker/u4:2 Not tainted 6.14.0-rc5-wt-g03960e6f9d47 #33 13c287eeabfe1efea01c0bcc863723ab082e17cf
Workqueue: cfg80211 cfg80211_propagate_cac_done_wk
Stack:
 00000000 00000001 ffffff00 6093267c
 00000000 6002ec30 6d577c50 60037608
 00000000 67e8d108 6063717b 00000000
Call Trace:
 [<6002ec30>] ? _printk+0x0/0x98
 [<6003c2b3>] show_stack+0x10e/0x11a
 [<6002ec30>] ? _printk+0x0/0x98
 [<60037608>] dump_stack_lvl+0x71/0xb8
 [<6063717b>] ? wdev_chandef+0x60/0x165
 [<6003766d>] dump_stack+0x1e/0x20
 [<6005d1b7>] __warn+0x101/0x20f
 [<6005d3a8>] warn_slowpath_fmt+0xe3/0x15d
 [<600b0c5c>] ? mark_lock.part.0+0x0/0x4ec
 [<60751191>] ? __this_cpu_preempt_check+0x0/0x16
 [<600b11a2>] ? mark_held_locks+0x5a/0x6e
 [<6005d2c5>] ? warn_slowpath_fmt+0x0/0x15d
 [<60052e53>] ? unblock_signals+0x3a/0xe7
 [<60052f2d>] ? um_set_signals+0x2d/0x43
 [<60751191>] ? __this_cpu_preempt_check+0x0/0x16
 [<607508b2>] ? lock_is_held_type+0x207/0x21f
 [<6063717b>] wdev_chandef+0x60/0x165
 [<605f89b4>] regulatory_propagate_dfs_state+0x247/0x43f
 [<60052f00>] ? um_set_signals+0x0/0x43
 [<605e6bfd>] cfg80211_propagate_cac_done_wk+0x3a/0x4a
 [<6007e460>] process_scheduled_works+0x3bc/0x60e
 [<6007d0ec>] ? move_linked_works+0x4d/0x81
 [<6007d120>] ? assign_work+0x0/0xaa
 [<6007f81f>] worker_thread+0x220/0x2dc
 [<600786ef>] ? set_pf_worker+0x0/0x57
 [<60087c96>] ? to_kthread+0x0/0x43
 [<6008ab3c>] kthread+0x2d3/0x2e2
 [<6007f5ff>] ? worker_thread+0x0/0x2dc
 [<6006c05b>] ? calculate_sigpending+0x0/0x56
 [<6003b37d>] new_thread_handler+0x4a/0x64
irq event stamp: 614611
hardirqs last  enabled at (614621): [<00000000600bc96b>] __up_console_sem+0x82/0xaf
hardirqs last disabled at (614630): [<00000000600bc92c>] __up_console_sem+0x43/0xaf
softirqs last  enabled at (614268): [<00000000606c55c6>] __ieee80211_wake_queue+0x933/0x985
softirqs last disabled at (614266): [<00000000606c52d6>] __ieee80211_wake_queue+0x643/0x985
Fixes 26ec17a1dc5e ("cfg80211: Fix radar event during another phy CAC")
---
 net/wireless/reg.c | 2 ++
 1 file changed, 2 insertions(+)
net/wireless/reg.c +2 -0
index c1752b31734f..92e04370fa63 100644
@@ -4229,6 +4229,8 @@ static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev)
 	struct wireless_dev *wdev;
 	unsigned int link_id;
 
+	guard(wiphy)(&rdev->wiphy);
+
 	/* If we finished CAC or received radar, we should end any
 	 * CAC running on the same channels.
 	 * the check !cfg80211_chandef_dfs_usable contain 2 options:
Signature · 1 line
2.39.5
author maintainer
#247 lore raw

PATCH 237/627 wifi: mac80211: Do not schedule stopped TXQs

In reply to Greg Kroah-Hartman

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

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

From: Alexander Wetzel <[email protected]>

[ Upstream commit 11e3e22fa533f5d7cf04e32343b05a27eda3c7a5 ]

Ignore TXQs with the flag IEEE80211_TXQ_STOP when scheduling a queue.

The flag is only set after all fragments have been dequeued and won't allow dequeueing other frames as long as the flag is set.

For drivers using ieee80211_txq_schedule_start() this prevents an loop trying to push the queued frames while IEEE80211_TXQ_STOP is set:

After setting IEEE80211_TXQ_STOP the driver will call ieee80211_return_txq(). Which calls __ieee80211_schedule_txq(), detects that there sill are frames in the queue and immediately restarts the stopped TXQ. Which can't dequeue any frame and thus starts over the loop.

Fixes ba8c3d6f16a1 ("mac80211: add an intermediate software queue implementation")
---
 net/mac80211/tx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
net/mac80211/tx.c +3 -1
index d58b80813bdd..4a9b258300fe 100644
@@ -4098,7 +4098,9 @@ void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
 
 	spin_lock_bh(&local->active_txq_lock[txq->ac]);
 
-	has_queue = force || txq_has_queue(txq);
+	has_queue = force ||
+		    (!test_bit(IEEE80211_TXQ_STOP, &txqi->flags) &&
+		     txq_has_queue(txq));
 	if (list_empty(&txqi->schedule_order) &&
 	    (has_queue || ieee80211_txq_keep_active(txqi))) {
 		/* If airtime accounting is active, always enqueue STAs at the
Signature · 1 line
2.39.5
author maintainer
#248 lore raw

PATCH 238/627 wifi: mac80211: Dont call fq_flow_idx() for management frames

In reply to Greg Kroah-Hartman

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

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

From: Alexander Wetzel <[email protected]>

[ Upstream commit cb3bb3d88dfcd177a1050c0a009a3ee147b2e5b9 ]

skb_get_hash() can only be used when the skb is linked to a netdev device.

Fixes 73bc9e0af594 ("mac80211: don't apply flow control on management frames")
---
 net/mac80211/tx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
net/mac80211/tx.c +2 -1
index 4a9b258300fe..04f4d574401f 100644
@@ -1428,7 +1428,7 @@ static void ieee80211_txq_enqueue(struct ieee80211_local *local,
 {
 	struct fq *fq = &local->fq;
 	struct fq_tin *tin = &txqi->tin;
-	u32 flow_idx = fq_flow_idx(fq, skb);
+	u32 flow_idx;
 
 	ieee80211_set_skb_enqueue_time(skb);
 
@@ -1444,6 +1444,7 @@ static void ieee80211_txq_enqueue(struct ieee80211_local *local,
 			IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 		__skb_queue_tail(&txqi->frags, skb);
 	} else {
+		flow_idx = fq_flow_idx(fq, skb);
 		fq_tin_enqueue(fq, tin, flow_idx, skb,
 			       fq_skb_free_func);
 	}
Signature · 1 line
2.39.5
author maintainer
#249 lore raw

PATCH 239/627 wifi: mac80211: Check 802.11 encaps offloading in ieee80211_tx_h_select_key()

In reply to Greg Kroah-Hartman

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

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

From: Remi Pommarel <[email protected]>

[ Upstream commit 4037c468d1b3c508d69e6df0ef47fdee3d440e39 ]

With 802.11 encapsulation offloading, ieee80211_tx_h_select_key() is called on 802.3 frames. In that case do not try to use skb data as valid 802.11 headers.

---
 net/mac80211/tx.c | 6 ++++++
 1 file changed, 6 insertions(+)
net/mac80211/tx.c +6 -0
index 04f4d574401f..73304a5cf6fc 100644
@@ -612,6 +612,12 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 	else
 		tx->key = NULL;
 
+	if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) {
+		if (tx->key && tx->key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)
+			info->control.hw_key = &tx->key->conf;
+		return TX_CONTINUE;
+	}
+
 	if (tx->key) {
 		bool skip_hw = false;
 
Signature · 1 line
2.39.5
author maintainer
#250 lore raw

PATCH 240/627 Reapply "wifi: mac80211: Update skbs control block key in ieee80211_tx_dequeue()"

In reply to Greg Kroah-Hartman

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

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

From: Remi Pommarel <[email protected]>

[ Upstream commit 754fe848b3b297fc85ec24cd959bad22b6df8cb8 ]

This reverts commit 0937cb5f345c ("Revert "wifi: mac80211: Update skb's control block key in ieee80211_tx_dequeue()"").

This commit broke TX with 802.11 encapsulation HW offloading, now that this is fixed, reapply it.

---
 net/mac80211/tx.c | 1 +
 1 file changed, 1 insertion(+)
net/mac80211/tx.c +1 -0
index 73304a5cf6fc..8aaa59a27bc4 100644
@@ -3883,6 +3883,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 	 * The key can be removed while the packet was queued, so need to call
 	 * this here to get the current key.
 	 */
+	info->control.hw_key = NULL;
 	r = ieee80211_tx_h_select_key(&tx);
 	if (r != TX_CONTINUE) {
 		ieee80211_free_txskb(&local->hw, skb);
Signature · 1 line
2.39.5
author maintainer
#251 lore raw

PATCH 241/627 wifi: ath12k: fix endianness handling while accessing wmi service bit

In reply to Greg Kroah-Hartman

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

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

From: Tamizh Chelvam Raja <[email protected]>

[ Upstream commit 8f1a078842d4af4877fb686f3907788024d0d1b7 ]

Currently there is no endian conversion in ath12k_wmi_tlv_services_parser() so the service bit parsing will be incorrect on a big endian platform and to fix this by using appropriate endian conversion.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00217-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Fixes 342527f35338 ("wifi: ath12k: Add support to parse new WMI event for 6 GHz regulatory")
---
 drivers/net/wireless/ath/ath12k/wmi.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)
drivers/net/wireless/ath/ath12k/wmi.c +7 -5
index e19803bfba75..745d017c5aa8 100644
@@ -7491,7 +7491,7 @@ static int ath12k_wmi_tlv_services_parser(struct ath12k_base *ab,
 					  void *data)
 {
 	const struct wmi_service_available_event *ev;
-	u32 *wmi_ext2_service_bitmap;
+	__le32 *wmi_ext2_service_bitmap;
 	int i, j;
 	u16 expected_len;
 
@@ -7523,12 +7523,12 @@ static int ath12k_wmi_tlv_services_parser(struct ath12k_base *ab,
 			   ev->wmi_service_segment_bitmap[3]);
 		break;
 	case WMI_TAG_ARRAY_UINT32:
-		wmi_ext2_service_bitmap = (u32 *)ptr;
+		wmi_ext2_service_bitmap = (__le32 *)ptr;
 		for (i = 0, j = WMI_MAX_EXT_SERVICE;
 		     i < WMI_SERVICE_SEGMENT_BM_SIZE32 && j < WMI_MAX_EXT2_SERVICE;
 		     i++) {
 			do {
-				if (wmi_ext2_service_bitmap[i] &
+				if (__le32_to_cpu(wmi_ext2_service_bitmap[i]) &
 				    BIT(j % WMI_AVAIL_SERVICE_BITS_IN_SIZE32))
 					set_bit(j, ab->wmi_ab.svc_map);
 			} while (++j % WMI_AVAIL_SERVICE_BITS_IN_SIZE32);
@@ -7536,8 +7536,10 @@ static int ath12k_wmi_tlv_services_parser(struct ath12k_base *ab,
 
 		ath12k_dbg(ab, ATH12K_DBG_WMI,
 			   "wmi_ext2_service_bitmap 0x%04x 0x%04x 0x%04x 0x%04x",
-			   wmi_ext2_service_bitmap[0], wmi_ext2_service_bitmap[1],
-			   wmi_ext2_service_bitmap[2], wmi_ext2_service_bitmap[3]);
+			   __le32_to_cpu(wmi_ext2_service_bitmap[0]),
+			   __le32_to_cpu(wmi_ext2_service_bitmap[1]),
+			   __le32_to_cpu(wmi_ext2_service_bitmap[2]),
+			   __le32_to_cpu(wmi_ext2_service_bitmap[3]));
 		break;
 	}
 	return 0;
Signature · 1 line
2.39.5
author maintainer
#252 lore raw

PATCH 242/627 wifi: brcmfmac: fix P2P discovery failure in P2P peer due to missing P2P IE

In reply to Greg Kroah-Hartman

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

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

From: Gokul Sivakumar <[email protected]>

[ Upstream commit 579bf8037b70b644a674c126a32bbb2212cf5c21 ]

After commit bd99a3013bdc ("brcmfmac: move configuration of probe request IEs"), the probe request MGMT IE addition operation brcmf_vif_set_mgmt_ie() got moved from the brcmf_p2p_scan_prep() to the brcmf_cfg80211_scan().

Because of this, as part of the scan request handler for the P2P Discovery, vif struct used for adding the Probe Request P2P IE in firmware got changed from the P2PAPI_BSSCFG_DEVICE vif to P2PAPI_BSSCFG_PRIMARY vif incorrectly. So the firmware stopped adding P2P IE to the outgoing P2P Discovery probe requests frames and the other P2P peers were unable to discover this device causing a regression on the P2P feature.

To fix this, while setting the P2P IE in firmware, properly use the vif of the P2P discovery wdev on which the driver received the P2P scan request. This is done by not changing the vif pointer, until brcmf_vif_set_mgmt_ie() is completed.

Fixes bd99a3013bdc ("brcmfmac: move configuration of probe request IEs")
---
 .../net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c   | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +4 -4
index b94c3619526c..086b9157292a 100644
@@ -1544,10 +1544,6 @@ brcmf_cfg80211_scan(struct wiphy *wiphy, struct cfg80211_scan_request *request)
 		return -EAGAIN;
 	}
 
-	/* If scan req comes for p2p0, send it over primary I/F */
-	if (vif == cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif)
-		vif = cfg->p2p.bss_idx[P2PAPI_BSSCFG_PRIMARY].vif;
-
 	brcmf_dbg(SCAN, "START ESCAN\n");
 
 	cfg->scan_request = request;
@@ -1563,6 +1559,10 @@ brcmf_cfg80211_scan(struct wiphy *wiphy, struct cfg80211_scan_request *request)
 	if (err)
 		goto scan_out;
 
+	/* If scan req comes for p2p0, send it over primary I/F */
+	if (vif == cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif)
+		vif = cfg->p2p.bss_idx[P2PAPI_BSSCFG_PRIMARY].vif;
+
 	err = brcmf_do_escan(vif->ifp, request);
 	if (err)
 		goto scan_out;
Signature · 1 line
2.39.5
author maintainer
#253 lore raw

PATCH 243/627 PM: cpufreq: powernv/tracing: Move powernv_throttle trace event

In reply to Greg Kroah-Hartman

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

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

From: Steven Rostedt <[email protected]>

[ Upstream commit 647fe16b46999258ce1aec41f4bdeabb4f0cc8e7 ]

As the trace event powernv_throttle is only used by the powernv code, move it to a separate include file and have that code directly enable it.

Trace events can take up around 5K of memory when they are defined regardless if they are used or not. It wastes memory to have them defined in configurations where the tracepoint is not used.

Cc Masami Hiramatsu <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Mathieu Desnoyers <[email protected]>
Cc Andrew Morton <[email protected]>
Cc Madhavan Srinivasan <[email protected]>
Cc Michael Ellerman <[email protected]>
Fixes 0306e481d479a ("cpufreq: powernv/tracing: Add powernv_throttle tracepoint")
---
 drivers/cpufreq/Makefile          |  1 +
 drivers/cpufreq/powernv-cpufreq.c |  4 ++-
 drivers/cpufreq/powernv-trace.h   | 44 +++++++++++++++++++++++++++++++
 include/trace/events/power.h      | 22 ----------------
 kernel/trace/power-traces.c       |  1 -
 5 files changed, 48 insertions(+), 24 deletions(-)
 create mode 100644 drivers/cpufreq/powernv-trace.h
drivers/cpufreq/Makefile +1 -0
index d38526b8e063..681d687b5a18 100644
@@ -21,6 +21,7 @@ obj-$(CONFIG_CPUFREQ_VIRT)		+= virtual-cpufreq.o
 
 # Traces
 CFLAGS_amd-pstate-trace.o               := -I$(src)
+CFLAGS_powernv-cpufreq.o                := -I$(src)
 amd_pstate-y				:= amd-pstate.o amd-pstate-trace.o
 
 ##################################################################################
drivers/cpufreq/powernv-cpufreq.c +3 -1
index a8943e2a93be..7d9a5f656de8 100644
@@ -21,7 +21,6 @@
 #include <linux/string_choices.h>
 #include <linux/cpu.h>
 #include <linux/hashtable.h>
-#include <trace/events/power.h>
 
 #include <asm/cputhreads.h>
 #include <asm/firmware.h>
@@ -30,6 +29,9 @@
 #include <asm/opal.h>
 #include <linux/timer.h>
 
+#define CREATE_TRACE_POINTS
+#include "powernv-trace.h"
+
 #define POWERNV_MAX_PSTATES_ORDER  8
 #define POWERNV_MAX_PSTATES	(1UL << (POWERNV_MAX_PSTATES_ORDER))
 #define PMSR_PSAFE_ENABLE	(1UL << 30)
drivers/cpufreq/powernv-trace.h new file +44 -0

44 lines not on this page · raw message

include/trace/events/power.h +0 -22
index 6c631eec23e3..913181cebfe9 100644
@@ -99,28 +99,6 @@ DEFINE_EVENT(psci_domain_idle, psci_domain_idle_exit,
 	TP_ARGS(cpu_id, state, s2idle)
 );
 
-TRACE_EVENT(powernv_throttle,
-
-	TP_PROTO(int chip_id, const char *reason, int pmax),
-
-	TP_ARGS(chip_id, reason, pmax),
-
-	TP_STRUCT__entry(
-		__field(int, chip_id)
-		__string(reason, reason)
-		__field(int, pmax)
-	),
-
-	TP_fast_assign(
-		__entry->chip_id = chip_id;
-		__assign_str(reason);
-		__entry->pmax = pmax;
-	),
-
-	TP_printk("Chip %d Pmax %d %s", __entry->chip_id,
-		  __entry->pmax, __get_str(reason))
-);
-
 TRACE_EVENT(pstate_sample,
 
 	TP_PROTO(u32 core_busy,
kernel/trace/power-traces.c +0 -1
index 21bb161c2316..f2fe33573e54 100644
@@ -17,5 +17,4 @@
 EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
 EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
 EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_frequency);
-EXPORT_TRACEPOINT_SYMBOL_GPL(powernv_throttle);
 
Signature · 1 line
2.39.5
author maintainer
#254 lore raw

PATCH 244/627 wifi: mac80211: Write cnt before copying in ieee80211_copy_rnr_beacon()

In reply to Greg Kroah-Hartman

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

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

From: Kees Cook <[email protected]>

[ Upstream commit a37192c432adaec9e8ef29e4ddb319ea2f443aa6 ]

While I caught the need for setting cnt early in nl80211_parse_rnr_elems() in the original annotation of struct cfg80211_rnr_elems with __counted_by, I missed a similar pattern in ieee80211_copy_rnr_beacon(). Fix this by moving the cnt assignment to before the loop.

Fixes 7b6d7087031b ("wifi: cfg80211: Annotate struct cfg80211_rnr_elems with __counted_by")
---
 net/mac80211/cfg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/mac80211/cfg.c +1 -1
index 18ad7ab1bb8c..7b17591a8610 100644
@@ -1122,13 +1122,13 @@ ieee80211_copy_rnr_beacon(u8 *pos, struct cfg80211_rnr_elems *dst,
 {
 	int i, offset = 0;
 
+	dst->cnt = src->cnt;
 	for (i = 0; i < src->cnt; i++) {
 		memcpy(pos + offset, src->elem[i].data, src->elem[i].len);
 		dst->elem[i].len = src->elem[i].len;
 		dst->elem[i].data = pos + offset;
 		offset += dst->elem[i].len;
 	}
-	dst->cnt = src->cnt;
 
 	return offset;
 }
Signature · 1 line
2.39.5
author maintainer
#255 lore raw

PATCH 245/627 wifi: nl80211: Set num_sub_specs before looping through sub_specs

In reply to Greg Kroah-Hartman

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

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

From: Kees Cook <[email protected]>

[ Upstream commit 2ed9a9fc9976262109d04f1a3c75c46de8ce4f22 ]

The processing of the struct cfg80211_sar_specs::sub_specs flexible array requires its counter, num_sub_specs, to be assigned before the loop in nl80211_set_sar_specs(). Leave the final assignment after the loop in place in case fewer ended up in the array.

Fixes aa4ec06c455d ("wifi: cfg80211: use __counted_by where appropriate")
---
 net/wireless/nl80211.c | 1 +
 1 file changed, 1 insertion(+)
net/wireless/nl80211.c +1 -0
index 50202d170f3a..bcdccd7dea06 100644
@@ -16932,6 +16932,7 @@ static int nl80211_set_sar_specs(struct sk_buff *skb, struct genl_info *info)
 	if (!sar_spec)
 		return -ENOMEM;
 
+	sar_spec->num_sub_specs = specs;
 	sar_spec->type = type;
 	specs = 0;
 	nla_for_each_nested(spec_list, tb[NL80211_SAR_ATTR_SPECS], rem) {
Signature · 1 line
2.39.5
author maintainer
#256 lore raw

PATCH 246/627 ring-buffer: Remove ring_buffer_read_prepare_sync()

In reply to Greg Kroah-Hartman

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

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

From: Steven Rostedt <[email protected]>

[ Upstream commit 119a5d573622ae90ba730d18acfae9bb75d77b9a ]

When the ring buffer was first introduced, reading the non-consuming "trace" file required disabling the writing of the ring buffer. To make sure the writing was fully disabled before iterating the buffer with a non-consuming read, it would set the disable flag of the buffer and then call an RCU synchronization to make sure all the buffers were synchronized.

The function ring_buffer_read_start() originally would initialize the iterator and call an RCU synchronization, but this was for each individual per CPU buffer where this would get called many times on a machine with many CPUs before the trace file could be read. The commit 72c9ddfd4c5bf ("ring-buffer: Make non-consuming read less expensive with lots of cpus.") separated ring_buffer_read_start into ring_buffer_read_prepare(), ring_buffer_read_sync() and then ring_buffer_read_start() to allow each of the per CPU buffers to be prepared, call the read_buffer_read_sync() once, and then the ring_buffer_read_start() for each of the CPUs which made things much faster.

The commit 1039221cc278 ("ring-buffer: Do not disable recording when there is an iterator") removed the requirement of disabling the recording of the ring buffer in order to iterate it, but it did not remove the synchronization that was happening that was required to wait for all the buffers to have no more writers. It's now OK for the buffers to have writers and no synchronization is needed.

Remove the synchronization and put back the interface for the ring buffer iterator back before commit 72c9ddfd4c5bf was applied.

Cc Mathieu Desnoyers <[email protected]>
Fixes 1039221cc278 ("ring-buffer: Do not disable recording when there is an iterator")
---
 include/linux/ring_buffer.h |  4 +--
 kernel/trace/ring_buffer.c  | 63 ++++++-------------------------------
 kernel/trace/trace.c        | 14 +++------
 kernel/trace/trace_kdb.c    |  8 ++---
 4 files changed, 18 insertions(+), 71 deletions(-)
include/linux/ring_buffer.h +1 -3
index cd7f0ae26615..bc90c3c7b5fd 100644
@@ -152,9 +152,7 @@ ring_buffer_consume(struct trace_buffer *buffer, int cpu, u64 *ts,
 		    unsigned long *lost_events);
 
 struct ring_buffer_iter *
-ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags);
-void ring_buffer_read_prepare_sync(void);
-void ring_buffer_read_start(struct ring_buffer_iter *iter);
+ring_buffer_read_start(struct trace_buffer *buffer, int cpu, gfp_t flags);
 void ring_buffer_read_finish(struct ring_buffer_iter *iter);
 
 struct ring_buffer_event *
kernel/trace/ring_buffer.c +10 -53

85 lines not on this page · raw message

kernel/trace/trace.c +4 -10
index 95ae7c4e5835..7996f26c3f46 100644
@@ -4735,21 +4735,15 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 	if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
 		for_each_tracing_cpu(cpu) {
 			iter->buffer_iter[cpu] =
-				ring_buffer_read_prepare(iter->array_buffer->buffer,
-							 cpu, GFP_KERNEL);
-		}
-		ring_buffer_read_prepare_sync();
-		for_each_tracing_cpu(cpu) {
-			ring_buffer_read_start(iter->buffer_iter[cpu]);
+				ring_buffer_read_start(iter->array_buffer->buffer,
+						       cpu, GFP_KERNEL);
 			tracing_iter_reset(iter, cpu);
 		}
 	} else {
 		cpu = iter->cpu_file;
 		iter->buffer_iter[cpu] =
-			ring_buffer_read_prepare(iter->array_buffer->buffer,
-						 cpu, GFP_KERNEL);
-		ring_buffer_read_prepare_sync();
-		ring_buffer_read_start(iter->buffer_iter[cpu]);
+			ring_buffer_read_start(iter->array_buffer->buffer,
+					       cpu, GFP_KERNEL);
 		tracing_iter_reset(iter, cpu);
 	}
 
kernel/trace/trace_kdb.c +3 -5
index d7b135de958a..896ff78b8349 100644
@@ -43,17 +43,15 @@ static void ftrace_dump_buf(int skip_entries, long cpu_file)
 	if (cpu_file == RING_BUFFER_ALL_CPUS) {
 		for_each_tracing_cpu(cpu) {
 			iter.buffer_iter[cpu] =
-			ring_buffer_read_prepare(iter.array_buffer->buffer,
-						 cpu, GFP_ATOMIC);
-			ring_buffer_read_start(iter.buffer_iter[cpu]);
+			ring_buffer_read_start(iter.array_buffer->buffer,
+					       cpu, GFP_ATOMIC);
 			tracing_iter_reset(&iter, cpu);
 		}
 	} else {
 		iter.cpu_file = cpu_file;
 		iter.buffer_iter[cpu_file] =
-			ring_buffer_read_prepare(iter.array_buffer->buffer,
+			ring_buffer_read_start(iter.array_buffer->buffer,
 						 cpu_file, GFP_ATOMIC);
-		ring_buffer_read_start(iter.buffer_iter[cpu_file]);
 		tracing_iter_reset(&iter, cpu_file);
 	}
 
Signature · 1 line
2.39.5
author maintainer
#257 lore raw

PATCH 247/627 kcsan: test: Initialize dummy variable

In reply to Greg Kroah-Hartman

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

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

From: Marco Elver <[email protected]>

[ Upstream commit 9872916ad1a1a5e7d089e05166c85dbd65e5b0e8 ]

Newer compiler versions rightfully point out:

kernel/kcsan/kcsan_test.c:591:41: error: variable 'dummy' is uninitialized when passed as a const pointer argument here [-Werror,-Wuninitialized-const-pointer]
591 | KCSAN_EXPECT_READ_BARRIER(atomic_read(&dummy), false);
| ^~~~~
1 error generated.

Although this particular test does not care about the value stored in the dummy atomic variable, let's silence the warning.

---
 kernel/kcsan/kcsan_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/kcsan/kcsan_test.c +1 -1
index c2871180edcc..49ab81faaed9 100644
@@ -533,7 +533,7 @@ static void test_barrier_nothreads(struct kunit *test)
 	struct kcsan_scoped_access *reorder_access = NULL;
 #endif
 	arch_spinlock_t arch_spinlock = __ARCH_SPIN_LOCK_UNLOCKED;
-	atomic_t dummy;
+	atomic_t dummy = ATOMIC_INIT(0);
 
 	KCSAN_TEST_REQUIRES(test, reorder_access != NULL);
 	KCSAN_TEST_REQUIRES(test, IS_ENABLED(CONFIG_SMP));
Signature · 1 line
2.39.5
author maintainer
#258 lore raw

PATCH 248/627 memcg_slabinfo: Fix use of PG_slab

In reply to Greg Kroah-Hartman

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

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

From: Matthew Wilcox (Oracle) <[email protected]>

[ Upstream commit 7f770e94d7936e8e35d4b4d5fa4618301b03ea33 ]

Check PGTY_slab instead of PG_slab.

---
 tools/cgroup/memcg_slabinfo.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
tools/cgroup/memcg_slabinfo.py +2 -2
index 270c28a0d098..6bf4bde77903 100644
@@ -146,11 +146,11 @@ def detect_kernel_config():
 
 
 def for_each_slab(prog):
-    PGSlab = ~prog.constant('PG_slab')
+    slabtype = prog.constant('PGTY_slab')
 
     for page in for_each_page(prog):
         try:
-            if page.page_type.value_() == PGSlab:
+            if (page.page_type.value_() >> 24) == slabtype:
                 yield cast('struct slab *', page)
         except FaultError:
             pass
Signature · 1 line
2.39.5