From 285ae26716d39411eadebecef8dcd462942a8892 Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Fri, 19 Nov 2021 15:03:19 +0100 Subject: [PATCH 001/277] USB: serial: option: add Telit LE910S1 0x9200 composition commit e353f3e88720300c3d72f49a4bea54f42db1fa5e upstream. Add the following Telit LE910S1 composition: 0x9200: tty Signed-off-by: Daniele Palmas Link: https://lore.kernel.org/r/20211119140319.10448-1-dnlplm@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index f50de529445d..b385cdd20384 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1270,6 +1270,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x9010), /* Telit SBL FN980 flashing device */ .driver_info = NCTRL(0) | ZLP }, + { USB_DEVICE(TELIT_VENDOR_ID, 0x9200), /* Telit LE910S1 flashing device */ + .driver_info = NCTRL(0) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff), .driver_info = RSVD(1) }, From fc6dc7ed75448eca39f05267fbb088faaaac5336 Mon Sep 17 00:00:00 2001 From: Mingjie Zhang Date: Tue, 23 Nov 2021 21:37:57 +0800 Subject: [PATCH 002/277] USB: serial: option: add Fibocom FM101-GL variants commit 88459e3e42760abb2299bbf6cb1026491170e02a upstream. Update the USB serial option driver support for the Fibocom FM101-GL Cat.6 LTE modules as there are actually several different variants. - VID:PID 2cb7:01a2, FM101-GL are laptop M.2 cards (with MBIM interfaces for /Linux/Chrome OS) - VID:PID 2cb7:01a4, FM101-GL for laptop debug M.2 cards(with adb interface for /Linux/Chrome OS) 0x01a2: mbim, tty, tty, diag, gnss 0x01a4: mbim, diag, tty, adb, gnss, gnss Here are the outputs of lsusb -v and usb-devices: T: Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 86 Spd=5000 MxCh= 0 D: Ver= 3.20 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs= 1 P: Vendor=2cb7 ProdID=01a2 Rev= 5.04 S: Manufacturer=Fibocom Wireless Inc. S: Product=Fibocom FM101-GL Module S: SerialNumber=673326ce C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=896mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=(none) I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=(none) I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=(none) I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=40 Driver=(none) Bus 002 Device 084: ID 2cb7:01a2 Fibocom Wireless Inc. Fibocom FM101-GL Module Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 3.20 bDeviceClass 0 bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 9 idVendor 0x2cb7 idProduct 0x01a2 bcdDevice 5.04 iManufacturer 1 Fibocom Wireless Inc. iProduct 2 Fibocom FM101-GL Module iSerial 3 673326ce bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 0x015d bNumInterfaces 6 bConfigurationValue 1 iConfiguration 4 MBIM_DUN_DUN_DIAG_NMEA bmAttributes 0xa0 (Bus Powered) Remote Wakeup MaxPower 896mA Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 0 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 14 bFunctionProtocol 0 iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 14 bInterfaceProtocol 0 iInterface 5 Fibocom FM101-GL LTE Modem CDC Header: bcdCDC 1.10 CDC Union: bMasterInterface 0 bSlaveInterface 1 CDC MBIM: bcdMBIMVersion 1.00 wMaxControlMessage 4096 bNumberFilters 32 bMaxFilterSize 128 wMaxSegmentSize 2048 bmNetworkCapabilities 0x20 8-byte ntb input size CDC MBIM Extended: bcdMBIMExtendedVersion 1.00 bMaxOutstandingCommandMessages 64 wMTU 1500 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 9 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 0 bNumEndpoints 0 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 2 iInterface 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 1 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 2 iInterface 6 MBIM Data Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x8e EP 14 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 6 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x0f EP 15 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 2 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 2 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x01 EP 1 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 3 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x85 EP 5 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x84 EP 4 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 4 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 48 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x03 EP 3 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x86 EP 6 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 5 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 0 bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x88 EP 8 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x87 EP 7 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x04 EP 4 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 T: Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 85 Spd=5000 MxCh= 0 D: Ver= 3.20 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs= 1 P: Vendor=2cb7 ProdID=01a4 Rev= 5.04 S: Manufacturer=Fibocom Wireless Inc. S: Product=Fibocom FM101-GL Module S: SerialNumber=673326ce C:* #Ifs= 7 Cfg#= 1 Atr=a0 MxPwr=896mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=(none) I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=(none) I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none) I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=40 Driver=(none) I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=40 Driver=(none) Bus 002 Device 085: ID 2cb7:01a4 Fibocom Wireless Inc. Fibocom FM101-GL Module Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 3.20 bDeviceClass 0 bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 9 idVendor 0x2cb7 idProduct 0x01a4 bcdDevice 5.04 iManufacturer 1 Fibocom Wireless Inc. iProduct 2 Fibocom FM101-GL Module iSerial 3 673326ce bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 0x0180 bNumInterfaces 7 bConfigurationValue 1 iConfiguration 4 MBIM_DIAG_DUN_ADB_GNSS_GNSS bmAttributes 0xa0 (Bus Powered) Remote Wakeup MaxPower 896mA Interface Association: bLength 8 bDescriptorType 11 bFirstInterface 0 bInterfaceCount 2 bFunctionClass 2 Communications bFunctionSubClass 14 bFunctionProtocol 0 iFunction 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 14 bInterfaceProtocol 0 iInterface 5 Fibocom FM101-GL LTE Modem CDC Header: bcdCDC 1.10 CDC Union: bMasterInterface 0 bSlaveInterface 1 CDC MBIM: bcdMBIMVersion 1.00 wMaxControlMessage 4096 bNumberFilters 32 bMaxFilterSize 128 wMaxSegmentSize 2048 bmNetworkCapabilities 0x20 8-byte ntb input size CDC MBIM Extended: bcdMBIMExtendedVersion 1.00 bMaxOutstandingCommandMessages 64 wMTU 1500 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 9 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 0 bNumEndpoints 0 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 2 iInterface 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 1 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 2 iInterface 6 MBIM Data Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x8e EP 14 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 6 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x0f EP 15 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 2 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 2 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 48 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x01 EP 1 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 3 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 255 Vendor Specific Subclass bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x84 EP 4 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 4 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 66 bInterfaceProtocol 1 iInterface 8 ADB Interface Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x03 EP 3 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x85 EP 5 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 5 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 0 bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x87 EP 7 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x86 EP 6 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x04 EP 4 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 6 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 255 Vendor Specific Class bInterfaceSubClass 0 bInterfaceProtocol 64 iInterface 0 ** UNRECOGNIZED: 05 24 00 10 01 ** UNRECOGNIZED: 05 24 01 00 00 ** UNRECOGNIZED: 04 24 02 02 ** UNRECOGNIZED: 05 24 06 00 00 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x89 EP 9 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x000a 1x 10 bytes bInterval 9 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x88 EP 8 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x05 EP 5 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Signed-off-by: Mingjie Zhang Link: https://lore.kernel.org/r/20211123133757.37475-1-superzmj@fibocom.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index b385cdd20384..4e2a9852147b 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2098,6 +2098,9 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff), /* Fibocom FM101-GL (laptop MBIM) */ + .driver_info = RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ From 25481ba05861953aad492217925d898aa46286c2 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Tue, 16 Nov 2021 00:16:30 +0200 Subject: [PATCH 003/277] usb: hub: Fix usb enumeration issue due to address0 race commit 6ae6dc22d2d1ce6aa77a6da8a761e61aca216f8b upstream. xHC hardware can only have one slot in default state with address 0 waiting for a unique address at a time, otherwise "undefined behavior may occur" according to xhci spec 5.4.3.4 The address0_mutex exists to prevent this across both xhci roothubs. If hub_port_init() fails, it may unlock the mutex and exit with a xhci slot in default state. If the other xhci roothub calls hub_port_init() at this point we end up with two slots in default state. Make sure the address0_mutex protects the slot default state across hub_port_init() retries, until slot is addressed or disabled. Note, one known minor case is not fixed by this patch. If device needs to be reset during resume, but fails all hub_port_init() retries in usb_reset_and_verify_device(), then it's possible the slot is still left in default state when address0_mutex is unlocked. Cc: Fixes: 638139eb95d2 ("usb: hub: allow to process more usb hub events in parallel") Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20211115221630.871204-1-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 6c555a50646a..04eb4a137ceb 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4472,8 +4472,6 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, if (oldspeed == USB_SPEED_LOW) delay = HUB_LONG_RESET_TIME; - mutex_lock(hcd->address0_mutex); - /* Reset the device; full speed may morph to high speed */ /* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */ retval = hub_port_reset(hub, port1, udev, delay, false); @@ -4772,7 +4770,6 @@ fail: hub_port_disable(hub, port1, 0); update_devnum(udev, devnum); /* for disconnect processing */ } - mutex_unlock(hcd->address0_mutex); return retval; } @@ -4917,6 +4914,9 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, unit_load = 100; status = 0; + + mutex_lock(hcd->address0_mutex); + for (i = 0; i < SET_CONFIG_TRIES; i++) { /* reallocate for each attempt, since references @@ -4953,6 +4953,8 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, if (status < 0) goto loop; + mutex_unlock(hcd->address0_mutex); + if (udev->quirks & USB_QUIRK_DELAY_INIT) msleep(2000); @@ -5041,6 +5043,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, loop_disable: hub_port_disable(hub, port1, 1); + mutex_lock(hcd->address0_mutex); loop: usb_ep0_reinit(udev); release_devnum(udev); @@ -5067,6 +5070,8 @@ loop: } done: + mutex_unlock(hcd->address0_mutex); + hub_port_disable(hub, port1, 1); if (hcd->driver->relinquish_port && !hub->hdev->parent) { if (status != -ENOTCONN && status != -ENODEV) @@ -5608,6 +5613,8 @@ static int usb_reset_and_verify_device(struct usb_device *udev) bos = udev->bos; udev->bos = NULL; + mutex_lock(hcd->address0_mutex); + for (i = 0; i < SET_CONFIG_TRIES; ++i) { /* ep0 maxpacket size may change; let the HCD know about it. @@ -5617,6 +5624,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev) if (ret >= 0 || ret == -ENOTCONN || ret == -ENODEV) break; } + mutex_unlock(hcd->address0_mutex); if (ret < 0) goto re_enumerate; From 12eaaa639015c950fd8dc2a84e0a707ef946d76c Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Tue, 23 Nov 2021 12:16:56 +0200 Subject: [PATCH 004/277] usb: hub: Fix locking issues with address0_mutex commit 6cca13de26eea6d32a98d96d916a048d16a12822 upstream. Fix the circular lock dependency and unbalanced unlock of addess0_mutex introduced when fixing an address0_mutex enumeration retry race in commit ae6dc22d2d1 ("usb: hub: Fix usb enumeration issue due to address0 race") Make sure locking order between port_dev->status_lock and address0_mutex is correct, and that address0_mutex is not unlocked in hub_port_connect "done:" codepath which may be reached without locking address0_mutex Fixes: 6ae6dc22d2d1 ("usb: hub: Fix usb enumeration issue due to address0 race") Cc: Reported-by: Marek Szyprowski Tested-by: Hans de Goede Tested-by: Marek Szyprowski Acked-by: Hans de Goede Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20211123101656.1113518-1-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 04eb4a137ceb..56a0bd05aa2c 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4859,6 +4859,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, struct usb_port *port_dev = hub->ports[port1 - 1]; struct usb_device *udev = port_dev->child; static int unreliable_port = -1; + bool retry_locked; /* Disconnect any existing devices under this port */ if (udev) { @@ -4915,9 +4916,10 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, status = 0; - mutex_lock(hcd->address0_mutex); - for (i = 0; i < SET_CONFIG_TRIES; i++) { + usb_lock_port(port_dev); + mutex_lock(hcd->address0_mutex); + retry_locked = true; /* reallocate for each attempt, since references * to the previous one can escape in various ways @@ -4926,6 +4928,8 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, if (!udev) { dev_err(&port_dev->dev, "couldn't allocate usb_device\n"); + mutex_unlock(hcd->address0_mutex); + usb_unlock_port(port_dev); goto done; } @@ -4947,13 +4951,13 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, } /* reset (non-USB 3.0 devices) and get descriptor */ - usb_lock_port(port_dev); status = hub_port_init(hub, udev, port1, i); - usb_unlock_port(port_dev); if (status < 0) goto loop; mutex_unlock(hcd->address0_mutex); + usb_unlock_port(port_dev); + retry_locked = false; if (udev->quirks & USB_QUIRK_DELAY_INIT) msleep(2000); @@ -5043,11 +5047,14 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, loop_disable: hub_port_disable(hub, port1, 1); - mutex_lock(hcd->address0_mutex); loop: usb_ep0_reinit(udev); release_devnum(udev); hub_free_dev(udev); + if (retry_locked) { + mutex_unlock(hcd->address0_mutex); + usb_unlock_port(port_dev); + } usb_put_dev(udev); if ((status == -ENOTCONN) || (status == -ENOTSUPP)) break; @@ -5070,8 +5077,6 @@ loop: } done: - mutex_unlock(hcd->address0_mutex); - hub_port_disable(hub, port1, 1); if (hcd->driver->relinquish_port && !hub->hdev->parent) { if (status != -ENOTCONN && status != -ENODEV) From db918af2a64a892aa8eba7f9f34da3e3c96e76f3 Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Fri, 12 Nov 2021 10:07:20 -0800 Subject: [PATCH 005/277] binder: fix test regression due to sender_euid change commit c21a80ca0684ec2910344d72556c816cb8940c01 upstream. This is a partial revert of commit 29bc22ac5e5b ("binder: use euid from cred instead of using task"). Setting sender_euid using proc->cred caused some Android system test regressions that need further investigation. It is a partial reversion because subsequent patches rely on proc->cred. Fixes: 29bc22ac5e5b ("binder: use euid from cred instead of using task") Cc: stable@vger.kernel.org # 4.4+ Acked-by: Christian Brauner Signed-off-by: Todd Kjos Change-Id: I9b1769a3510fed250bb21859ef8beebabe034c66 Link: https://lore.kernel.org/r/20211112180720.2858135-1-tkjos@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index c5fd7908fc91..63bf8a7d477b 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2894,7 +2894,7 @@ static void binder_transaction(struct binder_proc *proc, t->from = thread; else t->from = NULL; - t->sender_euid = proc->cred->euid; + t->sender_euid = task_euid(proc->tsk); t->to_proc = target_proc; t->to_thread = target_thread; t->code = tr->code; From fcf9e1df5a5fcdf6df8840c7f376629ffd2713a0 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 18 Nov 2021 22:57:29 +0100 Subject: [PATCH 006/277] ALSA: ctxfi: Fix out-of-range access commit 76c47183224c86e4011048b80f0e2d0d166f01c2 upstream. The master and next_conj of rcs_ops are used for iterating the resource list entries, and currently those are supposed to return the current value. The problem is that next_conf may go over the last entry before the loop abort condition is evaluated, and it may return the "current" value that is beyond the array size. It was caught recently as a GPF, for example. Those return values are, however, never actually evaluated, hence basically we don't have to consider the current value as the return at all. By dropping those return values, the potential out-of-range access above is also fixed automatically. This patch changes the return type of master and next_conj callbacks to void and drop the superfluous code accordingly. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=214985 Cc: Link: https://lore.kernel.org/r/20211118215729.26257-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/ctxfi/ctamixer.c | 14 ++++++-------- sound/pci/ctxfi/ctdaio.c | 16 ++++++++-------- sound/pci/ctxfi/ctresource.c | 7 +++---- sound/pci/ctxfi/ctresource.h | 4 ++-- sound/pci/ctxfi/ctsrc.c | 7 +++---- 5 files changed, 22 insertions(+), 26 deletions(-) diff --git a/sound/pci/ctxfi/ctamixer.c b/sound/pci/ctxfi/ctamixer.c index 5fcbb065d870..d32685ce6c05 100644 --- a/sound/pci/ctxfi/ctamixer.c +++ b/sound/pci/ctxfi/ctamixer.c @@ -27,16 +27,15 @@ #define BLANK_SLOT 4094 -static int amixer_master(struct rsc *rsc) +static void amixer_master(struct rsc *rsc) { rsc->conj = 0; - return rsc->idx = container_of(rsc, struct amixer, rsc)->idx[0]; + rsc->idx = container_of(rsc, struct amixer, rsc)->idx[0]; } -static int amixer_next_conj(struct rsc *rsc) +static void amixer_next_conj(struct rsc *rsc) { rsc->conj++; - return container_of(rsc, struct amixer, rsc)->idx[rsc->conj]; } static int amixer_index(const struct rsc *rsc) @@ -335,16 +334,15 @@ int amixer_mgr_destroy(struct amixer_mgr *amixer_mgr) /* SUM resource management */ -static int sum_master(struct rsc *rsc) +static void sum_master(struct rsc *rsc) { rsc->conj = 0; - return rsc->idx = container_of(rsc, struct sum, rsc)->idx[0]; + rsc->idx = container_of(rsc, struct sum, rsc)->idx[0]; } -static int sum_next_conj(struct rsc *rsc) +static void sum_next_conj(struct rsc *rsc) { rsc->conj++; - return container_of(rsc, struct sum, rsc)->idx[rsc->conj]; } static int sum_index(const struct rsc *rsc) diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c index 7f089cb433e1..df326b7663a2 100644 --- a/sound/pci/ctxfi/ctdaio.c +++ b/sound/pci/ctxfi/ctdaio.c @@ -55,12 +55,12 @@ static struct daio_rsc_idx idx_20k2[NUM_DAIOTYP] = { [SPDIFIO] = {.left = 0x05, .right = 0x85}, }; -static int daio_master(struct rsc *rsc) +static void daio_master(struct rsc *rsc) { /* Actually, this is not the resource index of DAIO. * For DAO, it is the input mapper index. And, for DAI, * it is the output time-slot index. */ - return rsc->conj = rsc->idx; + rsc->conj = rsc->idx; } static int daio_index(const struct rsc *rsc) @@ -68,19 +68,19 @@ static int daio_index(const struct rsc *rsc) return rsc->conj; } -static int daio_out_next_conj(struct rsc *rsc) +static void daio_out_next_conj(struct rsc *rsc) { - return rsc->conj += 2; + rsc->conj += 2; } -static int daio_in_next_conj_20k1(struct rsc *rsc) +static void daio_in_next_conj_20k1(struct rsc *rsc) { - return rsc->conj += 0x200; + rsc->conj += 0x200; } -static int daio_in_next_conj_20k2(struct rsc *rsc) +static void daio_in_next_conj_20k2(struct rsc *rsc) { - return rsc->conj += 0x100; + rsc->conj += 0x100; } static const struct rsc_ops daio_out_rsc_ops = { diff --git a/sound/pci/ctxfi/ctresource.c b/sound/pci/ctxfi/ctresource.c index 80c4d84f9667..f05a09ed42b8 100644 --- a/sound/pci/ctxfi/ctresource.c +++ b/sound/pci/ctxfi/ctresource.c @@ -113,18 +113,17 @@ static int audio_ring_slot(const struct rsc *rsc) return (rsc->conj << 4) + offset_in_audio_slot_block[rsc->type]; } -static int rsc_next_conj(struct rsc *rsc) +static void rsc_next_conj(struct rsc *rsc) { unsigned int i; for (i = 0; (i < 8) && (!(rsc->msr & (0x1 << i))); ) i++; rsc->conj += (AUDIO_SLOT_BLOCK_NUM >> i); - return rsc->conj; } -static int rsc_master(struct rsc *rsc) +static void rsc_master(struct rsc *rsc) { - return rsc->conj = rsc->idx; + rsc->conj = rsc->idx; } static const struct rsc_ops rsc_generic_ops = { diff --git a/sound/pci/ctxfi/ctresource.h b/sound/pci/ctxfi/ctresource.h index 736d9f7e9e16..29b6fe6de659 100644 --- a/sound/pci/ctxfi/ctresource.h +++ b/sound/pci/ctxfi/ctresource.h @@ -43,8 +43,8 @@ struct rsc { }; struct rsc_ops { - int (*master)(struct rsc *rsc); /* Move to master resource */ - int (*next_conj)(struct rsc *rsc); /* Move to next conjugate resource */ + void (*master)(struct rsc *rsc); /* Move to master resource */ + void (*next_conj)(struct rsc *rsc); /* Move to next conjugate resource */ int (*index)(const struct rsc *rsc); /* Return the index of resource */ /* Return the output slot number */ int (*output_slot)(const struct rsc *rsc); diff --git a/sound/pci/ctxfi/ctsrc.c b/sound/pci/ctxfi/ctsrc.c index bb4c9c3c89ae..93d660276c82 100644 --- a/sound/pci/ctxfi/ctsrc.c +++ b/sound/pci/ctxfi/ctsrc.c @@ -594,16 +594,15 @@ int src_mgr_destroy(struct src_mgr *src_mgr) /* SRCIMP resource manager operations */ -static int srcimp_master(struct rsc *rsc) +static void srcimp_master(struct rsc *rsc) { rsc->conj = 0; - return rsc->idx = container_of(rsc, struct srcimp, rsc)->idx[0]; + rsc->idx = container_of(rsc, struct srcimp, rsc)->idx[0]; } -static int srcimp_next_conj(struct rsc *rsc) +static void srcimp_next_conj(struct rsc *rsc) { rsc->conj++; - return container_of(rsc, struct srcimp, rsc)->idx[rsc->conj]; } static int srcimp_index(const struct rsc *rsc) From e070ab1b06f80d5445ebbafb59bfe32db0a6a9da Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 2 Nov 2021 12:24:26 +0000 Subject: [PATCH 007/277] media: cec: copy sequence field for the reply commit 13cbaa4c2b7bf9f8285e1164d005dbf08244ecd5 upstream. When the reply for a non-blocking transmit arrives, the sequence field for that reply was never filled in, so userspace would have no way of associating the reply to the original transmit. Copy the sequence field to ensure that this is now possible. Signed-off-by: Hans Verkuil Fixes: 0dbacebede1e ([media] cec: move the CEC framework out of staging and to media) Cc: Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/cec/cec-adap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index 061b7824f698..2765ca732b95 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -1135,6 +1135,7 @@ void cec_received_msg_ts(struct cec_adapter *adap, if (abort) dst->rx_status |= CEC_RX_STATUS_FEATURE_ABORT; msg->flags = dst->flags; + msg->sequence = dst->sequence; /* Remove it from the wait_queue */ list_del_init(&data->list); From dde64487284dabcb33efe2e7764aa0fb0be5c67a Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Mon, 8 Nov 2021 16:31:01 -0800 Subject: [PATCH 008/277] HID: wacom: Use "Confidence" flag to prevent reporting invalid contacts commit 7fb0413baa7f8a04caef0c504df9af7e0623d296 upstream. The HID descriptor of many of Wacom's touch input devices include a "Confidence" usage that signals if a particular touch collection contains useful data. The driver does not look at this flag, however, which causes even invalid contacts to be reported to userspace. A lucky combination of kernel event filtering and device behavior (specifically: contact ID 0 == invalid, contact ID >0 == valid; and order all data so that all valid contacts are reported before any invalid contacts) spare most devices from any visibly-bad behavior. The DTH-2452 is one example of an unlucky device that misbehaves. It uses ID 0 for both the first valid contact and all invalid contacts. Because we report both the valid and invalid contacts, the kernel reports that contact 0 first goes down (valid) and then goes up (invalid) in every report. This causes ~100 clicks per second simply by touching the screen. This patch inroduces new `confidence` flag in our `hid_data` structure. The value is initially set to `true` at the start of a report and can be set to `false` if an invalid touch usage is seen. Link: https://github.com/linuxwacom/input-wacom/issues/270 Fixes: f8b6a74719b5 ("HID: wacom: generic: Support multiple tools per report") Signed-off-by: Jason Gerecke Tested-by: Joshua Dickens Cc: Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom_wac.c | 8 +++++++- drivers/hid/wacom_wac.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index df89f490e552..14373b06e63d 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2433,6 +2433,9 @@ static void wacom_wac_finger_event(struct hid_device *hdev, struct wacom_features *features = &wacom->wacom_wac.features; switch (equivalent_usage) { + case HID_DG_CONFIDENCE: + wacom_wac->hid_data.confidence = value; + break; case HID_GD_X: wacom_wac->hid_data.x = value; break; @@ -2463,7 +2466,8 @@ static void wacom_wac_finger_event(struct hid_device *hdev, if (usage->usage_index + 1 == field->report_count) { - if (equivalent_usage == wacom_wac->hid_data.last_slot_field) + if (equivalent_usage == wacom_wac->hid_data.last_slot_field && + wacom_wac->hid_data.confidence) wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input); } } @@ -2476,6 +2480,8 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev, struct hid_data* hid_data = &wacom_wac->hid_data; int i; + hid_data->confidence = true; + for (i = 0; i < report->maxfield; i++) { struct hid_field *field = report->field[i]; int j; diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index 55b542a6a66b..a61d3543b8e6 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -293,6 +293,7 @@ struct hid_data { bool inrange_state; bool invert_state; bool tipswitch; + bool confidence; int x; int y; int pressure; From c0ef0e75a858cbd8618b473f22fbca36106dcf82 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 17 Nov 2021 10:20:16 +0300 Subject: [PATCH 009/277] staging: rtl8192e: Fix use after free in _rtl92e_pci_disconnect() commit b535917c51acc97fb0761b1edec85f1f3d02bda4 upstream. The free_rtllib() function frees the "dev" pointer so there is use after free on the next line. Re-arrange things to avoid that. Fixes: 66898177e7e5 ("staging: rtl8192e: Fix unload/reload problem") Cc: stable Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20211117072016.GA5237@kili Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 811cada301ac..e1ede9fd4920 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -2582,13 +2582,14 @@ static void _rtl92e_pci_disconnect(struct pci_dev *pdev) free_irq(dev->irq, dev); priv->irq = 0; } - free_rtllib(dev); if (dev->mem_start != 0) { iounmap((void __iomem *)dev->mem_start); release_mem_region(pci_resource_start(pdev, 1), pci_resource_len(pdev, 1)); } + + free_rtllib(dev); } else { priv = rtllib_priv(dev); } From 017fc242d6ce52e16e00ffdfddf95ed75316d678 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 2 Nov 2021 11:10:37 +0100 Subject: [PATCH 010/277] fuse: fix page stealing commit 712a951025c0667ff00b25afc360f74e639dfabe upstream. It is possible to trigger a crash by splicing anon pipe bufs to the fuse device. The reason for this is that anon_pipe_buf_release() will reuse buf->page if the refcount is 1, but that page might have already been stolen and its flags modified (e.g. PG_lru added). This happens in the unlikely case of fuse_dev_splice_write() getting around to calling pipe_buf_release() after a page has been stolen, added to the page cache and removed from the page cache. Fix by calling pipe_buf_release() right after the page was inserted into the page cache. In this case the page has an elevated refcount so any release function will know that the page isn't reusable. Reported-by: Frank Dinoff Link: https://lore.kernel.org/r/CAAmZXrsGg2xsP1CK+cbuEMumtrqdvD-NKnWzhNcvn71RV3c1yw@mail.gmail.com/ Fixes: dd3bb14f44a6 ("fuse: support splice() writing to fuse device") Cc: # v2.6.35 Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/fuse/dev.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index b6f2a10663a0..4a142150e872 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -897,6 +897,12 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) goto out_put_old; } + /* + * Release while we have extra ref on stolen page. Otherwise + * anon_pipe_buf_release() might think the page can be reused. + */ + pipe_buf_release(cs->pipe, buf); + get_page(newpage); if (!(buf->flags & PIPE_BUF_FLAG_LRU)) @@ -2046,8 +2052,12 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe_lock(pipe); out_free: - for (idx = 0; idx < nbuf; idx++) - pipe_buf_release(pipe, &bufs[idx]); + for (idx = 0; idx < nbuf; idx++) { + struct pipe_buffer *buf = &bufs[idx]; + + if (buf->ops) + pipe_buf_release(pipe, buf); + } pipe_unlock(pipe); kfree(bufs); From 1dc1d3451f99ca690ebd3ef21783c2e69400fbc2 Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Mon, 15 Nov 2021 14:27:19 -0800 Subject: [PATCH 011/277] xen: don't continue xenstore initialization in case of errors commit 08f6c2b09ebd4b326dbe96d13f94fee8f9814c78 upstream. In case of errors in xenbus_init (e.g. missing xen_store_gfn parameter), we goto out_error but we forget to reset xen_store_domain_type to XS_UNKNOWN. As a consequence xenbus_probe_initcall and other initcalls will still try to initialize xenstore resulting into a crash at boot. [ 2.479830] Call trace: [ 2.482314] xb_init_comms+0x18/0x150 [ 2.486354] xs_init+0x34/0x138 [ 2.489786] xenbus_probe+0x4c/0x70 [ 2.498432] xenbus_probe_initcall+0x2c/0x7c [ 2.503944] do_one_initcall+0x54/0x1b8 [ 2.507358] kernel_init_freeable+0x1ac/0x210 [ 2.511617] kernel_init+0x28/0x130 [ 2.516112] ret_from_fork+0x10/0x20 Cc: Cc: jbeulich@suse.com Signed-off-by: Stefano Stabellini Link: https://lore.kernel.org/r/20211115222719.2558207-1-sstabellini@kernel.org Reviewed-by: Jan Beulich Signed-off-by: Boris Ostrovsky Signed-off-by: Greg Kroah-Hartman --- drivers/xen/xenbus/xenbus_probe.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 08f1ccdbe343..b7727d1f1212 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -838,7 +838,7 @@ static struct notifier_block xenbus_resume_nb = { static int __init xenbus_init(void) { - int err = 0; + int err; uint64_t v = 0; xen_store_domain_type = XS_UNKNOWN; @@ -912,8 +912,10 @@ static int __init xenbus_init(void) */ proc_create_mount_point("xen"); #endif + return 0; out_error: + xen_store_domain_type = XS_UNKNOWN; return err; } From 12dd397a6bcdb3997c0cbdf23228dde7107896e5 Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Tue, 23 Nov 2021 13:07:48 -0800 Subject: [PATCH 012/277] xen: detect uninitialized xenbus in xenbus_init commit 36e8f60f0867d3b70d398d653c17108459a04efe upstream. If the xenstore page hasn't been allocated properly, reading the value of the related hvm_param (HVM_PARAM_STORE_PFN) won't actually return error. Instead, it will succeed and return zero. Instead of attempting to xen_remap a bad guest physical address, detect this condition and return early. Note that although a guest physical address of zero for HVM_PARAM_STORE_PFN is theoretically possible, it is not a good choice and zero has never been validly used in that capacity. Also recognize all bits set as an invalid value. For 32-bit Linux, any pfn above ULONG_MAX would get truncated. Pfns above ULONG_MAX should never be passed by the Xen tools to HVM guests anyway, so check for this condition and return early. Cc: stable@vger.kernel.org Signed-off-by: Stefano Stabellini Reviewed-by: Juergen Gross Reviewed-by: Jan Beulich Link: https://lore.kernel.org/r/20211123210748.1910236-1-sstabellini@kernel.org Signed-off-by: Boris Ostrovsky Signed-off-by: Greg Kroah-Hartman --- drivers/xen/xenbus/xenbus_probe.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index b7727d1f1212..27c48c90b2ab 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -878,6 +878,29 @@ static int __init xenbus_init(void) err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); if (err) goto out_error; + /* + * Uninitialized hvm_params are zero and return no error. + * Although it is theoretically possible to have + * HVM_PARAM_STORE_PFN set to zero on purpose, in reality it is + * not zero when valid. If zero, it means that Xenstore hasn't + * been properly initialized. Instead of attempting to map a + * wrong guest physical address return error. + * + * Also recognize all bits set as an invalid value. + */ + if (!v || !~v) { + err = -ENOENT; + goto out_error; + } + /* Avoid truncation on 32-bit. */ +#if BITS_PER_LONG == 32 + if (v > ULONG_MAX) { + pr_err("%s: cannot handle HVM_PARAM_STORE_PFN=%llx > ULONG_MAX\n", + __func__, v); + err = -EINVAL; + goto out_error; + } +#endif xen_store_gfn = (unsigned long)v; xen_store_interface = xen_remap(xen_store_gfn << XEN_PAGE_SHIFT, From dae065e34596dab0011fff546db3171cd4b45de0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 26 Nov 2021 17:34:42 -0500 Subject: [PATCH 013/277] tracing: Fix pid filtering when triggers are attached commit a55f224ff5f238013de8762c4287117e47b86e22 upstream. If a event is filtered by pid and a trigger that requires processing of the event to happen is a attached to the event, the discard portion does not take the pid filtering into account, and the event will then be recorded when it should not have been. Cc: stable@vger.kernel.org Fixes: 3fdaf80f4a836 ("tracing: Implement event pid filtering") Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.h | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b5a251efd164..365bc02230a9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1363,14 +1363,26 @@ __event_trigger_test_discard(struct trace_event_file *file, if (eflags & EVENT_FILE_FL_TRIGGER_COND) *tt = event_triggers_call(file, entry); - if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) || - (unlikely(file->flags & EVENT_FILE_FL_FILTERED) && - !filter_match_preds(file->filter, entry))) { - __trace_event_discard_commit(buffer, event); - return true; - } + if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED | + EVENT_FILE_FL_FILTERED | + EVENT_FILE_FL_PID_FILTER)))) + return false; + + if (file->flags & EVENT_FILE_FL_SOFT_DISABLED) + goto discard; + + if (file->flags & EVENT_FILE_FL_FILTERED && + !filter_match_preds(file->filter, entry)) + goto discard; + + if ((file->flags & EVENT_FILE_FL_PID_FILTER) && + trace_event_ignore_this_pid(file)) + goto discard; return false; + discard: + __trace_event_discard_commit(buffer, event); + return true; } /** From c46d0975c8d7aabb79cc2d2be393be60eda8f916 Mon Sep 17 00:00:00 2001 From: yangxingwu Date: Thu, 4 Nov 2021 03:10:29 +0100 Subject: [PATCH 014/277] netfilter: ipvs: Fix reuse connection if RS weight is 0 [ Upstream commit c95c07836fa4c1767ed11d8eca0769c652760e32 ] We are changing expire_nodest_conn to work even for reused connections when conn_reuse_mode=0, just as what was done with commit dc7b3eb900aa ("ipvs: Fix reuse connection if real server is dead"). For controlled and persistent connections, the new connection will get the needed real server depending on the rules in ip_vs_check_template(). Fixes: d752c3645717 ("ipvs: allow rescheduling of new connections when port reuse is detected") Co-developed-by: Chuanqi Liu Signed-off-by: Chuanqi Liu Signed-off-by: yangxingwu Acked-by: Simon Horman Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- Documentation/networking/ipvs-sysctl.txt | 3 +-- net/netfilter/ipvs/ip_vs_core.c | 8 ++++---- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index 056898685d40..fc531c29a2e8 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -30,8 +30,7 @@ conn_reuse_mode - INTEGER 0: disable any special handling on port reuse. The new connection will be delivered to the same real server that was - servicing the previous connection. This will effectively - disable expire_nodest_conn. + servicing the previous connection. bit 1: enable rescheduling of new connections when it is safe. That is, whenever expire_nodest_conn and for TCP sockets, when diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a95fe5fe9f04..4b9cd1c1c998 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1838,7 +1838,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; - int conn_reuse_mode; struct sock *sk; /* Already marked as IPVS request or reply? */ @@ -1914,15 +1913,16 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int */ cp = pp->conn_in_get(ipvs, af, skb, &iph); - conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); - if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { + if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { + int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); - } else if (is_new_conn_expected(cp, conn_reuse_mode)) { + } else if (conn_reuse_mode && + is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; From 3e18bfe139285952b747c18a1a522a4487f45305 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 27 Oct 2021 12:37:29 -0700 Subject: [PATCH 015/277] ARM: dts: BCM5301X: Fix I2C controller interrupt [ Upstream commit 754c4050a00e802e122690112fc2c3a6abafa7e2 ] The I2C interrupt controller line is off by 32 because the datasheet describes interrupt inputs into the GIC which are for Shared Peripheral Interrupts and are starting at offset 32. The ARM GIC binding expects the SPI interrupts to be numbered from 0 relative to the SPI base. Fixes: bb097e3e0045 ("ARM: dts: BCM5301X: Add I2C support to the DT") Tested-by: Christian Lamparter Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- arch/arm/boot/dts/bcm5301x.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index 165fd1c1461a..01a493559891 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -365,7 +365,7 @@ i2c0: i2c@18009000 { compatible = "brcm,iproc-i2c"; reg = <0x18009000 0x50>; - interrupts = ; + interrupts = ; #address-cells = <1>; #size-cells = <0>; clock-frequency = <100000>; From a12e248cc0586e272758c3aaba9c139c2a9cc3bd Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 28 Oct 2021 09:46:53 -0700 Subject: [PATCH 016/277] ARM: dts: BCM5301X: Add interrupt properties to GPIO node [ Upstream commit 40f7342f0587639e5ad625adaa15efdd3cffb18f ] The GPIO controller is also an interrupt controller provider and is currently missing the appropriate 'interrupt-controller' and '#interrupt-cells' properties to denote that. Fixes: fb026d3de33b ("ARM: BCM5301X: Add Broadcom's bus-axi to the DTS file") Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- arch/arm/boot/dts/bcm5301x.dtsi | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index 01a493559891..c3b6ba4db8e3 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -246,6 +246,8 @@ gpio-controller; #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; }; pcie0: pcie@12000 { From ab6db10bde978a61345bdf40c04f5255358560cb Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 Nov 2021 08:18:12 +0100 Subject: [PATCH 017/277] ASoC: topology: Add missing rwsem around snd_ctl_remove() calls [ Upstream commit 7e567b5ae06315ef2d70666b149962e2bb4b97af ] snd_ctl_remove() has to be called with card->controls_rwsem held (when called after the card instantiation). This patch add the missing rwsem calls around it. Fixes: 8a9782346dcc ("ASoC: topology: Add topology core") Signed-off-by: Takashi Iwai Link: https://lore.kernel.org/r/20211116071812.18109-1-tiwai@suse.de Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/soc-topology.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 50aa45525be5..0fbe50502699 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -2585,6 +2585,7 @@ EXPORT_SYMBOL_GPL(snd_soc_tplg_widget_remove_all); /* remove dynamic controls from the component driver */ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index) { + struct snd_card *card = comp->card->snd_card; struct snd_soc_dobj *dobj, *next_dobj; int pass = SOC_TPLG_PASS_END; @@ -2592,6 +2593,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index) while (pass >= SOC_TPLG_PASS_START) { /* remove mixer controls */ + down_write(&card->controls_rwsem); list_for_each_entry_safe(dobj, next_dobj, &comp->dobj_list, list) { @@ -2625,6 +2627,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index) break; } } + up_write(&card->controls_rwsem); pass--; } From ec2fe9e2217339435e3ceea68f9310251c4ed3b5 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Thu, 11 Nov 2021 22:09:16 -0500 Subject: [PATCH 018/277] net: ieee802154: handle iftypes as u32 [ Upstream commit 451dc48c806a7ce9fbec5e7a24ccf4b2c936e834 ] This patch fixes an issue that an u32 netlink value is handled as a signed enum value which doesn't fit into the range of u32 netlink type. If it's handled as -1 value some BIT() evaluation ends in a shift-out-of-bounds issue. To solve the issue we set the to u32 max which is s32 "-1" value to keep backwards compatibility and let the followed enum values start counting at 0. This brings the compiler to never handle the enum as signed and a check if the value is above NL802154_IFTYPE_MAX should filter -1 out. Fixes: f3ea5e44231a ("ieee802154: add new interface command") Signed-off-by: Alexander Aring Link: https://lore.kernel.org/r/20211112030916.685793-1-aahringo@redhat.com Signed-off-by: Stefan Schmidt Signed-off-by: Sasha Levin --- include/net/nl802154.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/include/net/nl802154.h b/include/net/nl802154.h index ddcee128f5d9..145acb8f2509 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -19,6 +19,8 @@ * */ +#include + #define NL802154_GENL_NAME "nl802154" enum nl802154_commands { @@ -150,10 +152,9 @@ enum nl802154_attrs { }; enum nl802154_iftype { - /* for backwards compatibility TODO */ - NL802154_IFTYPE_UNSPEC = -1, + NL802154_IFTYPE_UNSPEC = (~(__u32)0), - NL802154_IFTYPE_NODE, + NL802154_IFTYPE_NODE = 0, NL802154_IFTYPE_MONITOR, NL802154_IFTYPE_COORD, From 9b54bc6719a71ea7f0fa82398f9468a2ca833636 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 16 Nov 2021 09:55:01 -0500 Subject: [PATCH 019/277] NFSv42: Don't fail clone() unless the OP_CLONE operation failed [ Upstream commit d3c45824ad65aebf765fcf51366d317a29538820 ] The failure to retrieve post-op attributes has no bearing on whether or not the clone operation itself was successful. We must therefore ignore the return value of decode_getfattr() when looking at the success or failure of nfs4_xdr_dec_clone(). Fixes: 36022770de6c ("nfs42: add CLONE xdr functions") Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/nfs42xdr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 5966e1e7b1f5..09c683402f95 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -625,8 +625,7 @@ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp, status = decode_clone(xdr); if (status) goto out; - status = decode_getfattr(xdr, res->dst_fattr, res->server); - + decode_getfattr(xdr, res->dst_fattr, res->server); out: res->rpc_status = status; return status; From 25bd60b9f6e820e317c0c4fb6a2451a748d6ef58 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 18 Nov 2021 15:25:08 +0100 Subject: [PATCH 020/277] ARM: socfpga: Fix crash with CONFIG_FORTIRY_SOURCE [ Upstream commit 187bea472600dcc8d2eb714335053264dd437172 ] When CONFIG_FORTIFY_SOURCE is set, memcpy() checks the potential buffer overflow and panics. The code in sofcpga bootstrapping contains the memcpy() calls are mistakenly translated as the shorter size, hence it triggers a panic as if it were overflowing. This patch changes the secondary_trampoline and *_end definitions to arrays for avoiding the false-positive crash above. Fixes: 9c4566a117a6 ("ARM: socfpga: Enable SMP for socfpga") Suggested-by: Kees Cook Buglink: https://bugzilla.suse.com/show_bug.cgi?id=1192473 Link: https://lore.kernel.org/r/20211117193244.31162-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Dinh Nguyen Signed-off-by: Sasha Levin --- arch/arm/mach-socfpga/core.h | 2 +- arch/arm/mach-socfpga/platsmp.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h index 65e1817d8afe..692a287a8712 100644 --- a/arch/arm/mach-socfpga/core.h +++ b/arch/arm/mach-socfpga/core.h @@ -48,7 +48,7 @@ extern void __iomem *sdr_ctl_base_addr; u32 socfpga_sdram_self_refresh(u32 sdr_base); extern unsigned int socfpga_sdram_self_refresh_sz; -extern char secondary_trampoline, secondary_trampoline_end; +extern char secondary_trampoline[], secondary_trampoline_end[]; extern unsigned long socfpga_cpu1start_addr; diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c index 0ee76772b507..a272999ce04b 100644 --- a/arch/arm/mach-socfpga/platsmp.c +++ b/arch/arm/mach-socfpga/platsmp.c @@ -31,14 +31,14 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) { - int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; + int trampoline_size = secondary_trampoline_end - secondary_trampoline; if (socfpga_cpu1start_addr) { /* This will put CPU #1 into reset. */ writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr + SOCFPGA_RSTMGR_MODMPURST); - memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); + memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size); writel(__pa_symbol(secondary_startup), sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff)); @@ -56,12 +56,12 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) static int socfpga_a10_boot_secondary(unsigned int cpu, struct task_struct *idle) { - int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; + int trampoline_size = secondary_trampoline_end - secondary_trampoline; if (socfpga_cpu1start_addr) { writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr + SOCFPGA_A10_RSTMGR_MODMPURST); - memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); + memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size); writel(__pa_symbol(secondary_startup), sys_manager_base_addr + (socfpga_cpu1start_addr & 0x00000fff)); From dd035ca0e7a142870a970d46b1d19276cfe2bc8c Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Wed, 17 Nov 2021 16:19:09 +0530 Subject: [PATCH 021/277] scsi: mpt3sas: Fix kernel panic during drive powercycle test [ Upstream commit 0ee4ba13e09c9d9c1cb6abb59da8295d9952328b ] While looping over shost's sdev list it is possible that one of the drives is getting removed and its sas_target object is freed but its sdev object remains intact. Consequently, a kernel panic can occur while the driver is trying to access the sas_address field of sas_target object without also checking the sas_target object for NULL. Link: https://lore.kernel.org/r/20211117104909.2069-1-sreekanth.reddy@broadcom.com Fixes: f92363d12359 ("[SCSI] mpt3sas: add new driver supporting 12GB SAS") Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 332ea3af69ec..79c5a193308f 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -2955,7 +2955,7 @@ _scsih_ublock_io_device(struct MPT3SAS_ADAPTER *ioc, u64 sas_address) shost_for_each_device(sdev, ioc->shost) { sas_device_priv_data = sdev->hostdata; - if (!sas_device_priv_data) + if (!sas_device_priv_data || !sas_device_priv_data->sas_target) continue; if (sas_device_priv_data->sas_target->sas_address != sas_address) From 93cadd96c500cef7f638f652b46ee8dfe3a53c06 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 18 Nov 2021 14:14:16 +0300 Subject: [PATCH 022/277] drm/vc4: fix error code in vc4_create_object() [ Upstream commit 96c5f82ef0a145d3e56e5b26f2bf6dcd2ffeae1c ] The ->gem_create_object() functions are supposed to return NULL if there is an error. None of the callers expect error pointers so returing one will lead to an Oops. See drm_gem_vram_create(), for example. Fixes: c826a6e10644 ("drm/vc4: Add a BO cache.") Signed-off-by: Dan Carpenter Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20211118111416.GC1147@kili Signed-off-by: Sasha Levin --- drivers/gpu/drm/vc4/vc4_bo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index eff0a8ece8bc..85abba74ed98 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -292,7 +292,7 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size) bo = kzalloc(sizeof(*bo), GFP_KERNEL); if (!bo) - return ERR_PTR(-ENOMEM); + return NULL; mutex_lock(&vc4->bo_lock); bo->label = VC4_BO_TYPE_KERNEL; From ba503f46b94396a0330a7766b33d166b9daf3df4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Nov 2021 17:37:58 -0800 Subject: [PATCH 023/277] ipv6: fix typos in __ip6_finish_output() [ Upstream commit 19d36c5f294879949c9d6f57cb61d39cc4c48553 ] We deal with IPv6 packets, so we need to use IP6CB(skb)->flags and IP6SKB_REROUTED, instead of IPCB(skb)->flags and IPSKB_REROUTED Found by code inspection, please double check that fixing this bug does not surface other bugs. Fixes: 09ee9dba9611 ("ipv6: Reinject IPv6 packets if IPsec policy matches after SNAT") Signed-off-by: Eric Dumazet Cc: Tobias Brunner Cc: Steffen Klassert Cc: David Ahern Reviewed-by: David Ahern Tested-by: Tobias Brunner Acked-by: Tobias Brunner Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/ip6_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a903d0ce7e70..f906fe2acedd 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -175,7 +175,7 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { - IPCB(skb)->flags |= IPSKB_REROUTED; + IP6CB(skb)->flags |= IP6SKB_REROUTED; return dst_output(net, sk, skb); } #endif From 107b4338ce2f96e930ec9dbd079a9c22f866bbcf Mon Sep 17 00:00:00 2001 From: Tony Lu Date: Tue, 23 Nov 2021 16:25:18 +0800 Subject: [PATCH 024/277] net/smc: Ensure the active closing peer first closes clcsock [ Upstream commit 606a63c9783a32a45bd2ef0eee393711d75b3284 ] The side that actively closed socket, it's clcsock doesn't enter TIME_WAIT state, but the passive side does it. It should show the same behavior as TCP sockets. Consider this, when client actively closes the socket, the clcsock in server enters TIME_WAIT state, which means the address is occupied and won't be reused before TIME_WAIT dismissing. If we restarted server, the service would be unavailable for a long time. To solve this issue, shutdown the clcsock in [A], perform the TCP active close progress first, before the passive closed side closing it. So that the actively closed side enters TIME_WAIT, not the passive one. Client | Server close() // client actively close | smc_release() | smc_close_active() // PEERCLOSEWAIT1 | smc_close_final() // abort or closed = 1| smc_cdc_get_slot_and_msg_send() | [A] | |smc_cdc_msg_recv_action() // ACTIVE | queue_work(smc_close_wq, &conn->close_work) | smc_close_passive_work() // PROCESSABORT or APPCLOSEWAIT1 | smc_close_passive_abort_received() // only in abort | |close() // server recv zero, close | smc_release() // PROCESSABORT or APPCLOSEWAIT1 | smc_close_active() | smc_close_abort() or smc_close_final() // CLOSED | smc_cdc_get_slot_and_msg_send() // abort or closed = 1 smc_cdc_msg_recv_action() | smc_clcsock_release() queue_work(smc_close_wq, &conn->close_work) | sock_release(tcp) // actively close clc, enter TIME_WAIT smc_close_passive_work() // PEERCLOSEWAIT1 | smc_conn_free() smc_close_passive_abort_received() // CLOSED| smc_conn_free() | smc_clcsock_release() | sock_release(tcp) // passive close clc | Link: https://www.spinics.net/lists/netdev/msg780407.html Fixes: b38d732477e4 ("smc: socket closing and linkgroup cleanup") Signed-off-by: Tony Lu Reviewed-by: Wen Gu Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/smc/smc_close.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 2427a1f3d0d1..d915907ac29a 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -215,6 +215,12 @@ again: /* send close request */ rc = smc_close_final(conn); sk->sk_state = SMC_PEERCLOSEWAIT1; + + /* actively shutdown clcsock before peer close it, + * prevent peer from entering TIME_WAIT state. + */ + if (smc->clcsock && smc->clcsock->sk) + rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } else { /* peer event has changed the state */ goto again; From 8881d8087500a5de9433f17bde2565285686394e Mon Sep 17 00:00:00 2001 From: Thomas Zeitlhofer Date: Tue, 23 Nov 2021 20:18:43 +0100 Subject: [PATCH 025/277] PM: hibernate: use correct mode for swsusp_close() [ Upstream commit cefcf24b4d351daf70ecd945324e200d3736821e ] Commit 39fbef4b0f77 ("PM: hibernate: Get block device exclusively in swsusp_check()") changed the opening mode of the block device to (FMODE_READ | FMODE_EXCL). In the corresponding calls to swsusp_close(), the mode is still just FMODE_READ which triggers the warning in blkdev_flush_mapping() on resume from hibernate. So, use the mode (FMODE_READ | FMODE_EXCL) also when closing the device. Fixes: 39fbef4b0f77 ("PM: hibernate: Get block device exclusively in swsusp_check()") Signed-off-by: Thomas Zeitlhofer Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- kernel/power/hibernate.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 02df69a8ee3c..e68b1c20ad3d 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -668,7 +668,7 @@ static int load_image_and_restore(void) goto Unlock; error = swsusp_read(&flags); - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); if (!error) hibernation_restore(flags & SF_PLATFORM_MODE); @@ -865,7 +865,7 @@ static int software_resume(void) /* The snapshot device should not be opened while we're running */ if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { error = -EBUSY; - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); goto Unlock; } @@ -901,7 +901,7 @@ static int software_resume(void) pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: - swsusp_close(FMODE_READ); + swsusp_close(FMODE_READ | FMODE_EXCL); goto Finish; } From 63e8aabe1fa8a294c6cec8fcd1f7f3e4b529511d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Nov 2021 12:25:35 -0800 Subject: [PATCH 026/277] tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows [ Upstream commit 4e1fddc98d2585ddd4792b5e44433dcee7ece001 ] While testing BIG TCP patch series, I was expecting that TCP_RR workloads with 80KB requests/answers would send one 80KB TSO packet, then being received as a single GRO packet. It turns out this was not happening, and the root cause was that cubic Hystart ACK train was triggering after a few (2 or 3) rounds of RPC. Hystart was wrongly setting CWND/SSTHRESH to 30, while my RPC needed a budget of ~20 segments. Ideally these TCP_RR flows should not exit slow start. Cubic Hystart should reset itself at each round, instead of assuming every TCP flow is a bulk one. Note that even after this patch, Hystart can still trigger, depending on scheduling artifacts, but at a higher CWND/SSTHRESH threshold, keeping optimal TSO packet sizes. Tested: ip link set dev eth0 gro_ipv6_max_size 131072 gso_ipv6_max_size 131072 nstat -n; netperf -H ... -t TCP_RR -l 5 -- -r 80000,80000 -K cubic; nstat|egrep "Ip6InReceives|Hystart|Ip6OutRequests" Before: 8605 Ip6InReceives 87541 0.0 Ip6OutRequests 129496 0.0 TcpExtTCPHystartTrainDetect 1 0.0 TcpExtTCPHystartTrainCwnd 30 0.0 After: 8760 Ip6InReceives 88514 0.0 Ip6OutRequests 87975 0.0 Fixes: ae27e98a5152 ("[TCP] CUBIC v2.3") Co-developed-by: Neal Cardwell Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Cc: Yuchung Cheng Cc: Soheil Hassas Yeganeh Link: https://lore.kernel.org/r/20211123202535.1843771-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_cubic.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 8b5ba0a5cd38..93530bd33247 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -340,8 +340,6 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; if (tcp_in_slow_start(tp)) { - if (hystart && after(ack, ca->end_seq)) - bictcp_hystart_reset(sk); acked = tcp_slow_start(tp, acked); if (!acked) return; @@ -383,6 +381,9 @@ static void hystart_update(struct sock *sk, u32 delay) if (ca->found & hystart_detect) return; + if (after(tp->snd_una, ca->end_seq)) + bictcp_hystart_reset(sk); + if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock(); From fa0255f14ae773af8248fa764c888bce6bd49799 Mon Sep 17 00:00:00 2001 From: Huang Pei Date: Thu, 25 Nov 2021 18:59:48 +0800 Subject: [PATCH 027/277] MIPS: use 3-level pgtable for 64KB page size on MIPS_VA_BITS_48 [ Upstream commit 41ce097f714401e6ad8f3f5eb30d7f91b0b5e495 ] It hangup when booting Loongson 3A1000 with BOTH CONFIG_PAGE_SIZE_64KB and CONFIG_MIPS_VA_BITS_48, that it turn out to use 2-level pgtable instead of 3-level. 64KB page size with 2-level pgtable only cover 42 bits VA, use 3-level pgtable to cover all 48 bits VA(55 bits) Fixes: 1e321fa917fb ("MIPS64: Support of at least 48 bits of SEGBITS) Signed-off-by: Huang Pei Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 85afd6b4297b..45a5801ff467 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2990,7 +2990,7 @@ config HAVE_LATENCYTOP_SUPPORT config PGTABLE_LEVELS int default 4 if PAGE_SIZE_4KB && MIPS_VA_BITS_48 - default 3 if 64BIT && !PAGE_SIZE_64KB + default 3 if 64BIT && (!PAGE_SIZE_64KB || MIPS_VA_BITS_48) default 2 source "init/Kconfig" From 8e8f9087f65a5121bc19943dffa30b6677fa0b82 Mon Sep 17 00:00:00 2001 From: Tony Lu Date: Fri, 26 Nov 2021 10:41:35 +0800 Subject: [PATCH 028/277] net/smc: Don't call clcsock shutdown twice when smc shutdown [ Upstream commit bacb6c1e47691cda4a95056c21b5487fb7199fcc ] When applications call shutdown() with SHUT_RDWR in userspace, smc_close_active() calls kernel_sock_shutdown(), and it is called twice in smc_shutdown(). This fixes this by checking sk_state before do clcsock shutdown, and avoids missing the application's call of smc_shutdown(). Link: https://lore.kernel.org/linux-s390/1f67548e-cbf6-0dce-82b5-10288a4583bd@linux.ibm.com/ Fixes: 606a63c9783a ("net/smc: Ensure the active closing peer first closes clcsock") Signed-off-by: Tony Lu Reviewed-by: Wen Gu Acked-by: Karsten Graul Link: https://lore.kernel.org/r/20211126024134.45693-1-tonylu@linux.alibaba.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/smc/af_smc.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 8c71f0929fbb..f2c907d52812 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1178,8 +1178,10 @@ static unsigned int smc_poll(struct file *file, struct socket *sock, static int smc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; + bool do_shutdown = true; struct smc_sock *smc; int rc = -EINVAL; + int old_state; int rc1 = 0; smc = smc_sk(sk); @@ -1206,7 +1208,11 @@ static int smc_shutdown(struct socket *sock, int how) } switch (how) { case SHUT_RDWR: /* shutdown in both directions */ + old_state = sk->sk_state; rc = smc_close_active(smc); + if (old_state == SMC_ACTIVE && + sk->sk_state == SMC_PEERCLOSEWAIT1) + do_shutdown = false; break; case SHUT_WR: rc = smc_close_shutdown_write(smc); @@ -1216,7 +1222,7 @@ static int smc_shutdown(struct socket *sock, int how) /* nothing more to do because peer is not involved */ break; } - if (smc->clcsock) + if (do_shutdown && smc->clcsock) rc1 = kernel_sock_shutdown(smc->clcsock, how); /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; From c98267b4fa1feeb9f60637bb48dc75baafbd9622 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Mon, 22 Nov 2021 17:35:24 +0100 Subject: [PATCH 029/277] vhost/vsock: fix incorrect used length reported to the guest commit 49d8c5ffad07ca014cfae72a1b9b8c52b6ad9cb8 upstream. The "used length" reported by calling vhost_add_used() must be the number of bytes written by the device (using "in" buffers). In vhost_vsock_handle_tx_kick() the device only reads the guest buffers (they are all "out" buffers), without writing anything, so we must pass 0 as "used length" to comply virtio spec. Fixes: 433fc58e6bf2 ("VSOCK: Introduce vhost_vsock.ko") Cc: stable@vger.kernel.org Reported-by: Halil Pasic Suggested-by: Jason Wang Signed-off-by: Stefano Garzarella Link: https://lore.kernel.org/r/20211122163525.294024-2-sgarzare@redhat.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefan Hajnoczi Reviewed-by: Halil Pasic Signed-off-by: Greg Kroah-Hartman --- drivers/vhost/vsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 27f3b471c95b..b43b4942f156 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -490,7 +490,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) virtio_transport_free_pkt(pkt); len += sizeof(pkt->hdr); - vhost_add_used(vq, head, len); + vhost_add_used(vq, head, 0); total_len += len; added = true; } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); From e5b0fbafba14c0ca82661a10896544eac32eb593 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 26 Nov 2021 13:35:26 -0500 Subject: [PATCH 030/277] tracing: Check pid filtering when creating events commit 6cb206508b621a9a0a2c35b60540e399225c8243 upstream. When pid filtering is activated in an instance, all of the events trace files for that instance has the PID_FILTER flag set. This determines whether or not pid filtering needs to be done on the event, otherwise the event is executed as normal. If pid filtering is enabled when an event is created (via a dynamic event or modules), its flag is not updated to reflect the current state, and the events are not filtered properly. Cc: stable@vger.kernel.org Fixes: 3fdaf80f4a836 ("tracing: Implement event pid filtering") Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_events.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7b4af70d9dfd..1285ef6e2d14 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2254,12 +2254,19 @@ static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) { + struct trace_pid_list *pid_list; struct trace_event_file *file; file = kmem_cache_alloc(file_cachep, GFP_TRACE); if (!file) return NULL; + pid_list = rcu_dereference_protected(tr->filtered_pids, + lockdep_is_held(&event_mutex)); + + if (pid_list) + file->flags |= EVENT_FILE_FL_PID_FILTER; + file->event_call = call; file->tr = tr; atomic_set(&file->sm_ref, 0); From 79f7c6ba9cb0b7a6d7722bf42818d58c110ed929 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 9 Sep 2021 18:22:42 +0200 Subject: [PATCH 031/277] s390/mm: validate VMA in PGSTE manipulation functions commit fe3d10024073f06f04c74b9674bd71ccc1d787cf upstream. We should not walk/touch page tables outside of VMA boundaries when holding only the mmap sem in read mode. Evil user space can modify the VMA layout just before this function runs and e.g., trigger races with page table removal code since commit dd2283f2605e ("mm: mmap: zap pages with read mmap_sem in munmap"). gfn_to_hva() will only translate using KVM memory regions, but won't validate the VMA. Further, we should not allocate page tables outside of VMA boundaries: if evil user space decides to map hugetlbfs to these ranges, bad things will happen because we suddenly have PTE or PMD page tables where we shouldn't have them. Similarly, we have to check if we suddenly find a hugetlbfs VMA, before calling get_locked_pte(). Fixes: 2d42f9477320 ("s390/kvm: Add PGSTE manipulation functions") Signed-off-by: David Hildenbrand Reviewed-by: Claudio Imbrenda Acked-by: Heiko Carstens Link: https://lore.kernel.org/r/20210909162248.14969-4-david@redhat.com Signed-off-by: Christian Borntraeger Signed-off-by: Greg Kroah-Hartman --- arch/s390/mm/pgtable.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index ae677f814bc0..aa6b9487c8bb 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -896,6 +896,7 @@ EXPORT_SYMBOL(get_guest_storage_key); int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, unsigned long *oldpte, unsigned long *oldpgste) { + struct vm_area_struct *vma; unsigned long pgstev; spinlock_t *ptl; pgste_t pgste; @@ -905,6 +906,10 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, WARN_ON_ONCE(orc > ESSA_MAX); if (unlikely(orc > ESSA_MAX)) return -EINVAL; + + vma = find_vma(mm, hva); + if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; @@ -997,10 +1002,14 @@ EXPORT_SYMBOL(pgste_perform_essa); int set_pgste_bits(struct mm_struct *mm, unsigned long hva, unsigned long bits, unsigned long value) { + struct vm_area_struct *vma; spinlock_t *ptl; pgste_t new; pte_t *ptep; + vma = find_vma(mm, hva); + if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; @@ -1025,9 +1034,13 @@ EXPORT_SYMBOL(set_pgste_bits); */ int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep) { + struct vm_area_struct *vma; spinlock_t *ptl; pte_t *ptep; + vma = find_vma(mm, hva); + if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; From 109a830c7624de534daa7a2fcc12b511f8819d09 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Wed, 24 Nov 2021 23:49:10 +0100 Subject: [PATCH 032/277] PCI: aardvark: Fix I/O space page leak MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1df3e5b3feebf29a3ecfa0c0f06f79544ca573e4 upstream. When testing the R-Car PCIe driver on the Condor board, if the PCIe PHY driver was left disabled, the kernel crashed with this BUG: kernel BUG at lib/ioremap.c:72! Internal error: Oops - BUG: 0 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 39 Comm: kworker/0:1 Not tainted 4.17.0-dirty #1092 Hardware name: Renesas Condor board based on r8a77980 (DT) Workqueue: events deferred_probe_work_func pstate: 80000005 (Nzcv daif -PAN -UAO) pc : ioremap_page_range+0x370/0x3c8 lr : ioremap_page_range+0x40/0x3c8 sp : ffff000008da39e0 x29: ffff000008da39e0 x28: 00e8000000000f07 x27: ffff7dfffee00000 x26: 0140000000000000 x25: ffff7dfffef00000 x24: 00000000000fe100 x23: ffff80007b906000 x22: ffff000008ab8000 x21: ffff000008bb1d58 x20: ffff7dfffef00000 x19: ffff800009c30fb8 x18: 0000000000000001 x17: 00000000000152d0 x16: 00000000014012d0 x15: 0000000000000000 x14: 0720072007200720 x13: 0720072007200720 x12: 0720072007200720 x11: 0720072007300730 x10: 00000000000000ae x9 : 0000000000000000 x8 : ffff7dffff000000 x7 : 0000000000000000 x6 : 0000000000000100 x5 : 0000000000000000 x4 : 000000007b906000 x3 : ffff80007c61a880 x2 : ffff7dfffeefffff x1 : 0000000040000000 x0 : 00e80000fe100f07 Process kworker/0:1 (pid: 39, stack limit = 0x (ptrval)) Call trace: ioremap_page_range+0x370/0x3c8 pci_remap_iospace+0x7c/0xac pci_parse_request_of_pci_ranges+0x13c/0x190 rcar_pcie_probe+0x4c/0xb04 platform_drv_probe+0x50/0xbc driver_probe_device+0x21c/0x308 __device_attach_driver+0x98/0xc8 bus_for_each_drv+0x54/0x94 __device_attach+0xc4/0x12c device_initial_probe+0x10/0x18 bus_probe_device+0x90/0x98 deferred_probe_work_func+0xb0/0x150 process_one_work+0x12c/0x29c worker_thread+0x200/0x3fc kthread+0x108/0x134 ret_from_fork+0x10/0x18 Code: f9004ba2 54000080 aa0003fb 17ffff48 (d4210000) It turned out that pci_remap_iospace() wasn't undone when the driver's probe failed, and since devm_phy_optional_get() returned -EPROBE_DEFER, the probe was retried, finally causing the BUG due to trying to remap already remapped pages. The Aardvark PCI controller driver has the same issue. Replace pci_remap_iospace() with its devm_ managed version to fix the bug. Fixes: 8c39d710363c ("PCI: aardvark: Add Aardvark PCI host controller driver") Signed-off-by: Sergei Shtylyov [lorenzo.pieralisi@arm.com: updated the commit log] Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Thomas Petazzoni Reviewed-by: Linus Walleij Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index a572b2fb7af8..fd605796b011 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -932,7 +932,7 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie) 0, 0xF8000000, 0, lower_32_bits(res->start), OB_PCIE_IO); - err = pci_remap_iospace(res, iobase); + err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", err, res); From db70da46ea1e158912dbf4759b48a07a89645b89 Mon Sep 17 00:00:00 2001 From: Wen Yang Date: Wed, 24 Nov 2021 23:49:11 +0100 Subject: [PATCH 033/277] PCI: aardvark: Fix a leaked reference by adding missing of_node_put() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 3842f5166bf1ef286fe7a39f262b5c9581308366 upstream. The call to of_get_next_child() returns a node pointer with refcount incremented thus it must be explicitly decremented after the last usage. irq_domain_add_linear() also calls of_node_get() to increase refcount, so irq_domain will not be affected when it is released. Detected by coccinelle with the following warnings: ./drivers/pci/controller/pci-aardvark.c:826:1-7: ERROR: missing of_node_put; acquired a node pointer with refcount incremented on line 798, but without a corresponding object release within this function. Signed-off-by: Wen Yang Signed-off-by: Lorenzo Pieralisi Cc: Thomas Petazzoni Cc: Lorenzo Pieralisi Cc: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index fd605796b011..79cd11b1c89a 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -789,6 +789,7 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie) struct device_node *node = dev->of_node; struct device_node *pcie_intc_node; struct irq_chip *irq_chip; + int ret = 0; raw_spin_lock_init(&pcie->irq_lock); @@ -803,8 +804,8 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie) irq_chip->name = devm_kasprintf(dev, GFP_KERNEL, "%s-irq", dev_name(dev)); if (!irq_chip->name) { - of_node_put(pcie_intc_node); - return -ENOMEM; + ret = -ENOMEM; + goto out_put_node; } irq_chip->irq_mask = advk_pcie_irq_mask; @@ -816,11 +817,13 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie) &advk_pcie_irq_domain_ops, pcie); if (!pcie->irq_domain) { dev_err(dev, "Failed to get a INTx IRQ domain\n"); - of_node_put(pcie_intc_node); - return -ENOMEM; + ret = -ENOMEM; + goto out_put_node; } - return 0; +out_put_node: + of_node_put(pcie_intc_node); + return ret; } static void advk_pcie_remove_irq_domain(struct advk_pcie *pcie) From fd8c33fb825038bdafbc638ba492500319a472f8 Mon Sep 17 00:00:00 2001 From: Remi Pommarel Date: Wed, 24 Nov 2021 23:49:12 +0100 Subject: [PATCH 034/277] PCI: aardvark: Wait for endpoint to be ready before training link MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f4c7d053d7f77cd5c1a1ba7c7ce085ddba13d1d7 upstream. When configuring pcie reset pin from gpio (e.g. initially set by u-boot) to pcie function this pin goes low for a brief moment asserting the PERST# signal. Thus connected device enters fundamental reset process and link configuration can only begin after a minimal 100ms delay (see [1]). Because the pin configuration comes from the "default" pinctrl it is implicitly configured before the probe callback is called: driver_probe_device() really_probe() ... pinctrl_bind_pins() /* Here pin goes from gpio to PCIE reset function and PERST# is asserted */ ... drv->probe() [1] "PCI Express Base Specification", REV. 4.0 PCI Express, February 19 2014, 6.6.1 Conventional Reset Signed-off-by: Remi Pommarel Signed-off-by: Lorenzo Pieralisi Acked-by: Thomas Petazzoni Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 79cd11b1c89a..7ee5a91e5f7f 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -362,6 +362,14 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) reg |= PIO_CTRL_ADDR_WIN_DISABLE; advk_writel(pcie, reg, PIO_CTRL); + /* + * PERST# signal could have been asserted by pinctrl subsystem before + * probe() callback has been called, making the endpoint going into + * fundamental reset. As required by PCI Express spec a delay for at + * least 100ms after such a reset before link training is needed. + */ + msleep(PCI_PM_D3COLD_WAIT); + /* Start link training */ reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG); reg |= PCIE_CORE_LINK_TRAINING; From 22244438e33075d6f64e819ef1f8eb0ca43d1e5d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:13 +0100 Subject: [PATCH 035/277] PCI: aardvark: Train link immediately after enabling training MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6964494582f56a3882c2c53b0edbfe99eb32b2e1 upstream. Adding even 100ms (PCI_PM_D3COLD_WAIT) delay between enabling link training and starting link training causes detection issues with some buggy cards (such as Compex WLE900VX). Move the code which enables link training immediately before the one which starts link traning. This fixes detection issues of Compex WLE900VX card on Turris MOX after cold boot. Link: https://lore.kernel.org/r/20200430080625.26070-2-pali@kernel.org Fixes: f4c7d053d7f7 ("PCI: aardvark: Wait for endpoint to be ready...") Tested-by: Tomasz Maciej Nowak Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Acked-by: Rob Herring Acked-by: Thomas Petazzoni Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 7ee5a91e5f7f..8373f8cc4c52 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -324,11 +324,6 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) reg |= LANE_COUNT_1; advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - /* Enable link training */ - reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); - reg |= LINK_TRAINING_EN; - advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - /* Enable MSI */ reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG); reg |= PCIE_CORE_CTRL2_MSI_ENABLE; @@ -370,7 +365,15 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) */ msleep(PCI_PM_D3COLD_WAIT); - /* Start link training */ + /* Enable link training */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg |= LINK_TRAINING_EN; + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* + * Start link training immediately after enabling it. + * This solves problems for some buggy cards. + */ reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG); reg |= PCIE_CORE_LINK_TRAINING; advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG); From 62a3dc9b65a2b24800fc4267b8cf590fad135034 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Wed, 24 Nov 2021 23:49:14 +0100 Subject: [PATCH 036/277] PCI: aardvark: Improve link training MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 43fc679ced18006b12d918d7a8a4af392b7fbfe7 upstream. Currently the aardvark driver trains link in PCIe gen2 mode. This may cause some buggy gen1 cards (such as Compex WLE900VX) to be unstable or even not detected. Moreover when ASPM code tries to retrain link second time, these cards may stop responding and link goes down. If gen1 is used this does not happen. Unconditionally forcing gen1 is not a good solution since it may have performance impact on gen2 cards. To overcome this, read 'max-link-speed' property (as defined in PCI device tree bindings) and use this as max gen mode. Then iteratively try link training at this mode or lower until successful. After successful link training choose final controller gen based on Negotiated Link Speed from Link Status register, which should match card speed. Link: https://lore.kernel.org/r/20200430080625.26070-5-pali@kernel.org Tested-by: Tomasz Maciej Nowak Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring Acked-by: Thomas Petazzoni Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 114 +++++++++++++++++++++++++------- 1 file changed, 89 insertions(+), 25 deletions(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 8373f8cc4c52..714d81462297 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -36,6 +36,7 @@ #define PCIE_CORE_LINK_CTRL_STAT_REG 0xd0 #define PCIE_CORE_LINK_L0S_ENTRY BIT(0) #define PCIE_CORE_LINK_TRAINING BIT(5) +#define PCIE_CORE_LINK_SPEED_SHIFT 16 #define PCIE_CORE_LINK_WIDTH_SHIFT 20 #define PCIE_CORE_ERR_CAPCTL_REG 0x118 #define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX BIT(5) @@ -212,6 +213,7 @@ struct advk_pcie { struct mutex msi_used_lock; u16 msi_msg; int root_bus_nr; + int link_gen; }; static inline void advk_writel(struct advk_pcie *pcie, u32 val, u64 reg) @@ -235,20 +237,16 @@ static int advk_pcie_link_up(struct advk_pcie *pcie) static int advk_pcie_wait_for_link(struct advk_pcie *pcie) { - struct device *dev = &pcie->pdev->dev; int retries; /* check if the link is up or not */ for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { - if (advk_pcie_link_up(pcie)) { - dev_info(dev, "link up\n"); + if (advk_pcie_link_up(pcie)) return 0; - } usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX); } - dev_err(dev, "link never came up\n"); return -ETIMEDOUT; } @@ -272,6 +270,85 @@ static void advk_pcie_set_ob_win(struct advk_pcie *pcie, advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num)); } +static int advk_pcie_train_at_gen(struct advk_pcie *pcie, int gen) +{ + int ret, neg_gen; + u32 reg; + + /* Setup link speed */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg &= ~PCIE_GEN_SEL_MSK; + if (gen == 3) + reg |= SPEED_GEN_3; + else if (gen == 2) + reg |= SPEED_GEN_2; + else + reg |= SPEED_GEN_1; + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* + * Enable link training. This is not needed in every call to this + * function, just once suffices, but it does not break anything either. + */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg |= LINK_TRAINING_EN; + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* + * Start link training immediately after enabling it. + * This solves problems for some buggy cards. + */ + reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG); + reg |= PCIE_CORE_LINK_TRAINING; + advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG); + + ret = advk_pcie_wait_for_link(pcie); + if (ret) + return ret; + + reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG); + neg_gen = (reg >> PCIE_CORE_LINK_SPEED_SHIFT) & 0xf; + + return neg_gen; +} + +static void advk_pcie_train_link(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + int neg_gen = -1, gen; + + /* + * Try link training at link gen specified by device tree property + * 'max-link-speed'. If this fails, iteratively train at lower gen. + */ + for (gen = pcie->link_gen; gen > 0; --gen) { + neg_gen = advk_pcie_train_at_gen(pcie, gen); + if (neg_gen > 0) + break; + } + + if (neg_gen < 0) + goto err; + + /* + * After successful training if negotiated gen is lower than requested, + * train again on negotiated gen. This solves some stability issues for + * some buggy gen1 cards. + */ + if (neg_gen < gen) { + gen = neg_gen; + neg_gen = advk_pcie_train_at_gen(pcie, gen); + } + + if (neg_gen == gen) { + dev_info(dev, "link up at gen %i\n", gen); + return; + } + +err: + dev_err(dev, "link never came up\n"); +} + static void advk_pcie_setup_hw(struct advk_pcie *pcie) { u32 reg; @@ -312,12 +389,6 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) PCIE_CORE_CTRL2_TD_ENABLE; advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG); - /* Set GEN2 */ - reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); - reg &= ~PCIE_GEN_SEL_MSK; - reg |= SPEED_GEN_2; - advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - /* Set lane X1 */ reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); reg &= ~LANE_CNT_MSK; @@ -365,20 +436,7 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) */ msleep(PCI_PM_D3COLD_WAIT); - /* Enable link training */ - reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); - reg |= LINK_TRAINING_EN; - advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - - /* - * Start link training immediately after enabling it. - * This solves problems for some buggy cards. - */ - reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG); - reg |= PCIE_CORE_LINK_TRAINING; - advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG); - - advk_pcie_wait_for_link(pcie); + advk_pcie_train_link(pcie); reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); reg |= PCIE_CORE_CMD_MEM_ACCESS_EN | @@ -1017,6 +1075,12 @@ static int advk_pcie_probe(struct platform_device *pdev) return ret; } + ret = of_pci_get_max_link_speed(dev->of_node); + if (ret <= 0 || ret > 3) + pcie->link_gen = 3; + else + pcie->link_gen = ret; + advk_pcie_setup_hw(pcie); ret = advk_pcie_init_irq_domain(pcie); From e6cd6f85942377a29ca7250d7c8ac9ebdeaa9324 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:15 +0100 Subject: [PATCH 037/277] PCI: aardvark: Issue PERST via GPIO MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 5169a9851daaa2782a7bd2bb83d5b1bd224b2879 upstream. Add support for issuing PERST via GPIO specified in 'reset-gpios' property (as described in PCI device tree bindings). Some buggy cards (e.g. Compex WLE900VX or WLE1216) are not detected after reboot when PERST is not issued during driver initialization. If bootloader already enabled link training then issuing PERST has no effect for some buggy cards (e.g. Compex WLE900VX) and these cards are not detected. We therefore clear the LINK_TRAINING_EN register before. It was observed that Compex WLE900VX card needs to be in PERST reset for at least 10ms if bootloader enabled link training. Tested on Turris MOX. Link: https://lore.kernel.org/r/20200430080625.26070-6-pali@kernel.org Tested-by: Tomasz Maciej Nowak Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Acked-by: Thomas Petazzoni Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 44 ++++++++++++++++++++++++++++++++- 1 file changed, 43 insertions(+), 1 deletion(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 714d81462297..0cfec5660c69 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -12,6 +12,7 @@ */ #include +#include #include #include #include @@ -20,6 +21,7 @@ #include #include #include +#include #include /* PCIe core registers */ @@ -214,6 +216,7 @@ struct advk_pcie { u16 msi_msg; int root_bus_nr; int link_gen; + struct gpio_desc *reset_gpio; }; static inline void advk_writel(struct advk_pcie *pcie, u32 val, u64 reg) @@ -349,6 +352,25 @@ err: dev_err(dev, "link never came up\n"); } +static void advk_pcie_issue_perst(struct advk_pcie *pcie) +{ + u32 reg; + + if (!pcie->reset_gpio) + return; + + /* PERST does not work for some cards when link training is enabled */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg &= ~LINK_TRAINING_EN; + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* 10ms delay is needed for some cards */ + dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n"); + gpiod_set_value_cansleep(pcie->reset_gpio, 1); + usleep_range(10000, 11000); + gpiod_set_value_cansleep(pcie->reset_gpio, 0); +} + static void advk_pcie_setup_hw(struct advk_pcie *pcie) { u32 reg; @@ -358,6 +380,8 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) for (i = 0; i < 8; i++) advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0); + advk_pcie_issue_perst(pcie); + /* Set to Direct mode */ reg = advk_readl(pcie, CTRL_CONFIG_REG); reg &= ~(CTRL_MODE_MASK << CTRL_MODE_SHIFT); @@ -430,7 +454,8 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) /* * PERST# signal could have been asserted by pinctrl subsystem before - * probe() callback has been called, making the endpoint going into + * probe() callback has been called or issued explicitly by reset gpio + * function advk_pcie_issue_perst(), making the endpoint going into * fundamental reset. As required by PCI Express spec a delay for at * least 100ms after such a reset before link training is needed. */ @@ -1075,6 +1100,23 @@ static int advk_pcie_probe(struct platform_device *pdev) return ret; } + pcie->reset_gpio = devm_fwnode_get_index_gpiod_from_child(dev, "reset", + 0, + dev_fwnode(dev), + GPIOD_OUT_LOW, + "pcie1-reset"); + ret = PTR_ERR_OR_ZERO(pcie->reset_gpio); + if (ret) { + if (ret == -ENOENT) { + pcie->reset_gpio = NULL; + } else { + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get reset-gpio: %i\n", + ret); + return ret; + } + } + ret = of_pci_get_max_link_speed(dev->of_node); if (ret <= 0 || ret > 3) pcie->link_gen = 3; From 36d6c809c2b1a620b7fc0e370fc13af59cbdb0c5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:16 +0100 Subject: [PATCH 038/277] PCI: aardvark: Replace custom macros by standard linux/pci_regs.h macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 96be36dbffacea0aa9e6ec4839583e79faa141a1 upstream. PCI-E capability macros are already defined in linux/pci_regs.h. Remove their reimplementation in pcie-aardvark. Link: https://lore.kernel.org/r/20200430080625.26070-9-pali@kernel.org Tested-by: Tomasz Maciej Nowak Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring Acked-by: Thomas Petazzoni Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 42 +++++++++++++++------------------ 1 file changed, 19 insertions(+), 23 deletions(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 0cfec5660c69..3ad6b6245f94 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -29,17 +29,7 @@ #define PCIE_CORE_CMD_IO_ACCESS_EN BIT(0) #define PCIE_CORE_CMD_MEM_ACCESS_EN BIT(1) #define PCIE_CORE_CMD_MEM_IO_REQ_EN BIT(2) -#define PCIE_CORE_DEV_CTRL_STATS_REG 0xc8 -#define PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE (0 << 4) -#define PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT 5 -#define PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE (0 << 11) -#define PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT 12 -#define PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ 0x2 -#define PCIE_CORE_LINK_CTRL_STAT_REG 0xd0 -#define PCIE_CORE_LINK_L0S_ENTRY BIT(0) -#define PCIE_CORE_LINK_TRAINING BIT(5) -#define PCIE_CORE_LINK_SPEED_SHIFT 16 -#define PCIE_CORE_LINK_WIDTH_SHIFT 20 +#define PCIE_CORE_PCIEXP_CAP 0xc0 #define PCIE_CORE_ERR_CAPCTL_REG 0x118 #define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX BIT(5) #define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN BIT(6) @@ -229,6 +219,11 @@ static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg) return readl(pcie->base + reg); } +static inline u16 advk_read16(struct advk_pcie *pcie, u64 reg) +{ + return advk_readl(pcie, (reg & ~0x3)) >> ((reg & 0x3) * 8); +} + static int advk_pcie_link_up(struct advk_pcie *pcie) { u32 val, ltssm_state; @@ -301,16 +296,16 @@ static int advk_pcie_train_at_gen(struct advk_pcie *pcie, int gen) * Start link training immediately after enabling it. * This solves problems for some buggy cards. */ - reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG); - reg |= PCIE_CORE_LINK_TRAINING; - advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG); + reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL); + reg |= PCI_EXP_LNKCTL_RL; + advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL); ret = advk_pcie_wait_for_link(pcie); if (ret) return ret; - reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG); - neg_gen = (reg >> PCIE_CORE_LINK_SPEED_SHIFT) & 0xf; + reg = advk_read16(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKSTA); + neg_gen = reg & PCI_EXP_LNKSTA_CLS; return neg_gen; } @@ -400,13 +395,14 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV; advk_writel(pcie, reg, PCIE_CORE_ERR_CAPCTL_REG); - /* Set PCIe Device Control and Status 1 PF0 register */ - reg = PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE | - (7 << PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT) | - PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE | - (PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ << - PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT); - advk_writel(pcie, reg, PCIE_CORE_DEV_CTRL_STATS_REG); + /* Set PCIe Device Control register */ + reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL); + reg &= ~PCI_EXP_DEVCTL_RELAX_EN; + reg &= ~PCI_EXP_DEVCTL_NOSNOOP_EN; + reg &= ~PCI_EXP_DEVCTL_READRQ; + reg |= PCI_EXP_DEVCTL_PAYLOAD; /* Set max payload size */ + reg |= PCI_EXP_DEVCTL_READRQ_512B; + advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL); /* Program PCIe Control 2 to disable strict ordering */ reg = PCIE_CORE_CTRL2_RESERVED | From eaf5b04bbb6e40562872877558e08dc7422ad452 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:17 +0100 Subject: [PATCH 039/277] PCI: aardvark: Indicate error in 'val' when config read fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b1bd5714472cc72e14409f5659b154c765a76c65 upstream. Most callers of config read do not check for return value. But most of the ones that do, checks for error indication in 'val' variable. This patch updates error handling in advk_pcie_rd_conf() function. If PIO transfer fails then 'val' variable is set to 0xffffffff which indicates failture. Link: https://lore.kernel.org/r/20200528162604.GA323482@bjorn-Precision-5520 Link: https://lore.kernel.org/r/20200601130315.18895-1-pali@kernel.org Reported-by: Bjorn Helgaas Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 3ad6b6245f94..ae67e5c3fe70 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -631,8 +631,10 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, advk_writel(pcie, 1, PIO_START); ret = advk_pcie_wait_pio(pcie); - if (ret < 0) + if (ret < 0) { + *val = 0xffffffff; return PCIBIOS_SET_FAILED; + } /* Check PIO status and get the read result */ ret = advk_pcie_check_pio_status(pcie, val); From 320dd7a99bd22aad20765577c17b4baa07a19f2c Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Wed, 24 Nov 2021 23:49:18 +0100 Subject: [PATCH 040/277] PCI: aardvark: Introduce an advk_pcie_valid_device() helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 248d4e59616c632f37f04c233eec6d5008384926 upstream. In other to mimic other PCIe host controller drivers, introduce an advk_pcie_valid_device() helper, used in the configuration read/write functions. Signed-off-by: Thomas Petazzoni [lorenzo.pieralisi@arm.com: updated host->controller dir move] Signed-off-by: Lorenzo Pieralisi Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index ae67e5c3fe70..9426715316b2 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -592,6 +592,15 @@ static bool advk_pcie_pio_is_running(struct advk_pcie *pcie) return false; } +static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus, + int devfn) +{ + if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) + return false; + + return true; +} + static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, int size, u32 *val) { @@ -599,7 +608,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, u32 reg; int ret; - if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) { + if (!advk_pcie_valid_device(pcie, bus, devfn)) { *val = 0xffffffff; return PCIBIOS_DEVICE_NOT_FOUND; } @@ -660,7 +669,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, int offset; int ret; - if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) + if (!advk_pcie_valid_device(pcie, bus, devfn)) return PCIBIOS_DEVICE_NOT_FOUND; if (where % size) From 9d6c2a50576c8cb59c9a5529b03089959c749bf9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:19 +0100 Subject: [PATCH 041/277] PCI: aardvark: Don't touch PCIe registers if no card connected MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 70e380250c3621c55ff218cbaf2272830d9dbb1d upstream. When there is no PCIe card connected and advk_pcie_rd_conf() or advk_pcie_wr_conf() is called for PCI bus which doesn't belong to emulated root bridge, the aardvark driver throws the following error message: advk-pcie d0070000.pcie: config read/write timed out Obviously accessing PCIe registers of disconnected card is not possible. Extend check in advk_pcie_valid_device() function for validating availability of PCIe bus. If PCIe link is down, then the device is marked as Not Found and the driver does not try to access these registers. This is just an optimization to prevent accessing PCIe registers when card is disconnected. Trying to access PCIe registers of disconnected card does not cause any crash, kernel just needs to wait for a timeout. So if card disappear immediately after checking for PCIe link (before accessing PCIe registers), it does not cause any problems. Link: https://lore.kernel.org/r/20200702083036.12230-1-pali@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 9426715316b2..acc04c4a37df 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -598,6 +598,13 @@ static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus, if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) return false; + /* + * If the link goes down after we check for link-up, nothing bad + * happens but the config access times out. + */ + if (bus->number != pcie->root_bus_nr && !advk_pcie_link_up(pcie)) + return false; + return true; } From 140ce57705f33744cf7e47ba2fb15e3460ef19ea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:20 +0100 Subject: [PATCH 042/277] PCI: aardvark: Fix compilation on s390 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b32c012e4b98f0126aa327be2d1f409963057643 upstream. Include linux/gpio/consumer.h instead of linux/gpio.h, as is said in the latter file. This was reported by kernel test bot when compiling for s390. drivers/pci/controller/pci-aardvark.c:350:2: error: implicit declaration of function 'gpiod_set_value_cansleep' [-Werror,-Wimplicit-function-declaration] drivers/pci/controller/pci-aardvark.c:1074:21: error: implicit declaration of function 'devm_gpiod_get_from_of_node' [-Werror,-Wimplicit-function-declaration] drivers/pci/controller/pci-aardvark.c:1076:14: error: use of undeclared identifier 'GPIOD_OUT_LOW' Link: https://lore.kernel.org/r/202006211118.LxtENQfl%25lkp@intel.com Link: https://lore.kernel.org/r/20200907111038.5811-2-pali@kernel.org Fixes: 5169a9851daa ("PCI: aardvark: Issue PERST via GPIO") Reported-by: kernel test robot Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index acc04c4a37df..b3bce506d995 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -12,7 +12,7 @@ */ #include -#include +#include #include #include #include From 7e81c76e62410f707363215ce1695ce0c92dfa6a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:21 +0100 Subject: [PATCH 043/277] PCI: aardvark: Move PCIe reset card code to advk_pcie_train_link() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit d0c6a3475b033960e85ae2bf176b14cab0a627d2 upstream. Move code which belongs to link training (delays and resets) into advk_pcie_train_link() function, so everything related to link training, including timings is at one place. After experiments it can be observed that link training in aardvark hardware is very sensitive to timings and delays, so it is a good idea to have this code at the same place as link training calls. This patch does not change behavior of aardvark initialization. Link: https://lore.kernel.org/r/20200907111038.5811-6-pali@kernel.org Tested-by: Marek Behún Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 64 +++++++++++++++++---------------- 1 file changed, 34 insertions(+), 30 deletions(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index b3bce506d995..68ab3aef0e12 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -268,6 +268,25 @@ static void advk_pcie_set_ob_win(struct advk_pcie *pcie, advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num)); } +static void advk_pcie_issue_perst(struct advk_pcie *pcie) +{ + u32 reg; + + if (!pcie->reset_gpio) + return; + + /* PERST does not work for some cards when link training is enabled */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg &= ~LINK_TRAINING_EN; + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* 10ms delay is needed for some cards */ + dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n"); + gpiod_set_value_cansleep(pcie->reset_gpio, 1); + usleep_range(10000, 11000); + gpiod_set_value_cansleep(pcie->reset_gpio, 0); +} + static int advk_pcie_train_at_gen(struct advk_pcie *pcie, int gen) { int ret, neg_gen; @@ -315,6 +334,21 @@ static void advk_pcie_train_link(struct advk_pcie *pcie) struct device *dev = &pcie->pdev->dev; int neg_gen = -1, gen; + /* + * Reset PCIe card via PERST# signal. Some cards are not detected + * during link training when they are in some non-initial state. + */ + advk_pcie_issue_perst(pcie); + + /* + * PERST# signal could have been asserted by pinctrl subsystem before + * probe() callback has been called or issued explicitly by reset gpio + * function advk_pcie_issue_perst(), making the endpoint going into + * fundamental reset. As required by PCI Express spec a delay for at + * least 100ms after such a reset before link training is needed. + */ + msleep(PCI_PM_D3COLD_WAIT); + /* * Try link training at link gen specified by device tree property * 'max-link-speed'. If this fails, iteratively train at lower gen. @@ -347,25 +381,6 @@ err: dev_err(dev, "link never came up\n"); } -static void advk_pcie_issue_perst(struct advk_pcie *pcie) -{ - u32 reg; - - if (!pcie->reset_gpio) - return; - - /* PERST does not work for some cards when link training is enabled */ - reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); - reg &= ~LINK_TRAINING_EN; - advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - - /* 10ms delay is needed for some cards */ - dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n"); - gpiod_set_value_cansleep(pcie->reset_gpio, 1); - usleep_range(10000, 11000); - gpiod_set_value_cansleep(pcie->reset_gpio, 0); -} - static void advk_pcie_setup_hw(struct advk_pcie *pcie) { u32 reg; @@ -375,8 +390,6 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) for (i = 0; i < 8; i++) advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0); - advk_pcie_issue_perst(pcie); - /* Set to Direct mode */ reg = advk_readl(pcie, CTRL_CONFIG_REG); reg &= ~(CTRL_MODE_MASK << CTRL_MODE_SHIFT); @@ -448,15 +461,6 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) reg |= PIO_CTRL_ADDR_WIN_DISABLE; advk_writel(pcie, reg, PIO_CTRL); - /* - * PERST# signal could have been asserted by pinctrl subsystem before - * probe() callback has been called or issued explicitly by reset gpio - * function advk_pcie_issue_perst(), making the endpoint going into - * fundamental reset. As required by PCI Express spec a delay for at - * least 100ms after such a reset before link training is needed. - */ - msleep(PCI_PM_D3COLD_WAIT); - advk_pcie_train_link(pcie); reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); From 14910c1f4ff475031bb4114a399d742074340f04 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:22 +0100 Subject: [PATCH 044/277] PCI: aardvark: Update comment about disabling link training MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1d1cd163d0de22a4041a6f1aeabcf78f80076539 upstream. According to PCI Express Base Specifications (rev 4.0, 6.6.1 "Conventional reset"), after fundamental reset a 100ms delay is needed prior to enabling link training. Update comment in code to reflect this requirement. Link: https://lore.kernel.org/r/20201202184659.3795-1-pali@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 68ab3aef0e12..66c4b9282420 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -275,7 +275,14 @@ static void advk_pcie_issue_perst(struct advk_pcie *pcie) if (!pcie->reset_gpio) return; - /* PERST does not work for some cards when link training is enabled */ + /* + * As required by PCI Express spec (PCI Express Base Specification, REV. + * 4.0 PCI Express, February 19 2014, 6.6.1 Conventional Reset) a delay + * for at least 100ms after de-asserting PERST# signal is needed before + * link training is enabled. So ensure that link training is disabled + * prior de-asserting PERST# signal to fulfill that PCI Express spec + * requirement. + */ reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); reg &= ~LINK_TRAINING_EN; advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); From f06d6a0875f02513da06dd9dbc43da0449806850 Mon Sep 17 00:00:00 2001 From: Evan Wang Date: Wed, 24 Nov 2021 23:49:23 +0100 Subject: [PATCH 045/277] PCI: aardvark: Remove PCIe outbound window configuration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6df6ba974a55678a2c7d9a0c06eb15cde0c4b184 upstream. Outbound window is used to translate CPU space addresses to PCIe space addresses when the CPU initiates PCIe transactions. According to the suggestion of the HW designers, the recommended solution is to use the default outbound parameters, even though the current outbound window setting does not cause any known functional issue. This patch doesn't address any known functional issue, but aligns to HW design guidelines, and removes code that isn't needed. Signed-off-by: Evan Wang [Thomas: tweak commit log.] Signed-off-by: Thomas Petazzoni [lorenzo.pieralisi@arm.com: handled host->controller dir move] Signed-off-by: Lorenzo Pieralisi Reviewed-by: Victor Gu Reviewed-by: Nadav Haklai Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 55 --------------------------------- 1 file changed, 55 deletions(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 66c4b9282420..4021c4d1c6e8 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -107,24 +107,6 @@ #define PCIE_MSI_PAYLOAD_REG (CONTROL_BASE_ADDR + 0x9C) #define PCIE_MSI_DATA_MASK GENMASK(15, 0) -/* PCIe window configuration */ -#define OB_WIN_BASE_ADDR 0x4c00 -#define OB_WIN_BLOCK_SIZE 0x20 -#define OB_WIN_REG_ADDR(win, offset) (OB_WIN_BASE_ADDR + \ - OB_WIN_BLOCK_SIZE * (win) + \ - (offset)) -#define OB_WIN_MATCH_LS(win) OB_WIN_REG_ADDR(win, 0x00) -#define OB_WIN_MATCH_MS(win) OB_WIN_REG_ADDR(win, 0x04) -#define OB_WIN_REMAP_LS(win) OB_WIN_REG_ADDR(win, 0x08) -#define OB_WIN_REMAP_MS(win) OB_WIN_REG_ADDR(win, 0x0c) -#define OB_WIN_MASK_LS(win) OB_WIN_REG_ADDR(win, 0x10) -#define OB_WIN_MASK_MS(win) OB_WIN_REG_ADDR(win, 0x14) -#define OB_WIN_ACTIONS(win) OB_WIN_REG_ADDR(win, 0x18) - -/* PCIe window types */ -#define OB_PCIE_MEM 0x0 -#define OB_PCIE_IO 0x4 - /* LMI registers base address and register offsets */ #define LMI_BASE_ADDR 0x6000 #define CFG_REG (LMI_BASE_ADDR + 0x0) @@ -248,26 +230,6 @@ static int advk_pcie_wait_for_link(struct advk_pcie *pcie) return -ETIMEDOUT; } -/* - * Set PCIe address window register which could be used for memory - * mapping. - */ -static void advk_pcie_set_ob_win(struct advk_pcie *pcie, - u32 win_num, u32 match_ms, - u32 match_ls, u32 mask_ms, - u32 mask_ls, u32 remap_ms, - u32 remap_ls, u32 action) -{ - advk_writel(pcie, match_ls, OB_WIN_MATCH_LS(win_num)); - advk_writel(pcie, match_ms, OB_WIN_MATCH_MS(win_num)); - advk_writel(pcie, mask_ms, OB_WIN_MASK_MS(win_num)); - advk_writel(pcie, mask_ls, OB_WIN_MASK_LS(win_num)); - advk_writel(pcie, remap_ms, OB_WIN_REMAP_MS(win_num)); - advk_writel(pcie, remap_ls, OB_WIN_REMAP_LS(win_num)); - advk_writel(pcie, action, OB_WIN_ACTIONS(win_num)); - advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num)); -} - static void advk_pcie_issue_perst(struct advk_pcie *pcie) { u32 reg; @@ -391,11 +353,6 @@ err: static void advk_pcie_setup_hw(struct advk_pcie *pcie) { u32 reg; - int i; - - /* Point PCIe unit MBUS decode windows to DRAM space */ - for (i = 0; i < 8; i++) - advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0); /* Set to Direct mode */ reg = advk_readl(pcie, CTRL_CONFIG_REG); @@ -1048,12 +1005,6 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie) switch (resource_type(res)) { case IORESOURCE_IO: - advk_pcie_set_ob_win(pcie, 1, - upper_32_bits(res->start), - lower_32_bits(res->start), - 0, 0xF8000000, 0, - lower_32_bits(res->start), - OB_PCIE_IO); err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", @@ -1062,12 +1013,6 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie) } break; case IORESOURCE_MEM: - advk_pcie_set_ob_win(pcie, 0, - upper_32_bits(res->start), - lower_32_bits(res->start), - 0x0, 0xF8000000, 0, - lower_32_bits(res->start), - (2 << 20) | OB_PCIE_MEM); res_valid |= !(res->flags & IORESOURCE_PREFETCH); break; case IORESOURCE_BUS: From d4c0cd553ac9ca26300c07bbdd5168d1cacc4428 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:24 +0100 Subject: [PATCH 046/277] PCI: aardvark: Configure PCIe resources from 'ranges' DT property MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 64f160e19e9264a7f6d89c516baae1473b6f8359 upstream. In commit 6df6ba974a55 ("PCI: aardvark: Remove PCIe outbound window configuration") was removed aardvark PCIe outbound window configuration and commit description said that was recommended solution by HW designers. But that commit completely removed support for configuring PCIe IO resources without removing PCIe IO 'ranges' from DTS files. After that commit PCIe IO space started to be treated as PCIe MEM space and accessing it just caused kernel crash. Moreover implementation of PCIe outbound windows prior that commit was incorrect. It completely ignored offset between CPU address and PCIe bus address and expected that in DTS is CPU address always same as PCIe bus address without doing any checks. Also it completely ignored size of every PCIe resource specified in 'ranges' DTS property and expected that every PCIe resource has size 128 MB (also for PCIe IO range). Again without any check. Apparently none of PCIe resource has in DTS specified size of 128 MB. So it was completely broken and thanks to how aardvark mask works, configuration was completely ignored. This patch reverts back support for PCIe outbound window configuration but implementation is a new without issues mentioned above. PCIe outbound window is required when DTS specify in 'ranges' property non-zero offset between CPU and PCIe address space. To address recommendation by HW designers as specified in commit description of 6df6ba974a55, set default outbound parameters as PCIe MEM access without translation and therefore for this PCIe 'ranges' it is not needed to configure PCIe outbound window. For PCIe IO space is needed to configure aardvark PCIe outbound window. This patch fixes kernel crash when trying to access PCIe IO space. Link: https://lore.kernel.org/r/20210624215546.4015-2-pali@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Lorenzo Pieralisi Cc: stable@vger.kernel.org # 6df6ba974a55 ("PCI: aardvark: Remove PCIe outbound window configuration") Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 190 +++++++++++++++++++++++++++++++- 1 file changed, 189 insertions(+), 1 deletion(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 4021c4d1c6e8..fd5155b10c1d 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -107,6 +107,46 @@ #define PCIE_MSI_PAYLOAD_REG (CONTROL_BASE_ADDR + 0x9C) #define PCIE_MSI_DATA_MASK GENMASK(15, 0) +/* PCIe window configuration */ +#define OB_WIN_BASE_ADDR 0x4c00 +#define OB_WIN_BLOCK_SIZE 0x20 +#define OB_WIN_COUNT 8 +#define OB_WIN_REG_ADDR(win, offset) (OB_WIN_BASE_ADDR + \ + OB_WIN_BLOCK_SIZE * (win) + \ + (offset)) +#define OB_WIN_MATCH_LS(win) OB_WIN_REG_ADDR(win, 0x00) +#define OB_WIN_ENABLE BIT(0) +#define OB_WIN_MATCH_MS(win) OB_WIN_REG_ADDR(win, 0x04) +#define OB_WIN_REMAP_LS(win) OB_WIN_REG_ADDR(win, 0x08) +#define OB_WIN_REMAP_MS(win) OB_WIN_REG_ADDR(win, 0x0c) +#define OB_WIN_MASK_LS(win) OB_WIN_REG_ADDR(win, 0x10) +#define OB_WIN_MASK_MS(win) OB_WIN_REG_ADDR(win, 0x14) +#define OB_WIN_ACTIONS(win) OB_WIN_REG_ADDR(win, 0x18) +#define OB_WIN_DEFAULT_ACTIONS (OB_WIN_ACTIONS(OB_WIN_COUNT-1) + 0x4) +#define OB_WIN_FUNC_NUM_MASK GENMASK(31, 24) +#define OB_WIN_FUNC_NUM_SHIFT 24 +#define OB_WIN_FUNC_NUM_ENABLE BIT(23) +#define OB_WIN_BUS_NUM_BITS_MASK GENMASK(22, 20) +#define OB_WIN_BUS_NUM_BITS_SHIFT 20 +#define OB_WIN_MSG_CODE_ENABLE BIT(22) +#define OB_WIN_MSG_CODE_MASK GENMASK(21, 14) +#define OB_WIN_MSG_CODE_SHIFT 14 +#define OB_WIN_MSG_PAYLOAD_LEN BIT(12) +#define OB_WIN_ATTR_ENABLE BIT(11) +#define OB_WIN_ATTR_TC_MASK GENMASK(10, 8) +#define OB_WIN_ATTR_TC_SHIFT 8 +#define OB_WIN_ATTR_RELAXED BIT(7) +#define OB_WIN_ATTR_NOSNOOP BIT(6) +#define OB_WIN_ATTR_POISON BIT(5) +#define OB_WIN_ATTR_IDO BIT(4) +#define OB_WIN_TYPE_MASK GENMASK(3, 0) +#define OB_WIN_TYPE_SHIFT 0 +#define OB_WIN_TYPE_MEM 0x0 +#define OB_WIN_TYPE_IO 0x4 +#define OB_WIN_TYPE_CONFIG_TYPE0 0x8 +#define OB_WIN_TYPE_CONFIG_TYPE1 0x9 +#define OB_WIN_TYPE_MSG 0xc + /* LMI registers base address and register offsets */ #define LMI_BASE_ADDR 0x6000 #define CFG_REG (LMI_BASE_ADDR + 0x0) @@ -175,6 +215,13 @@ struct advk_pcie { struct platform_device *pdev; void __iomem *base; struct list_head resources; + struct { + phys_addr_t match; + phys_addr_t remap; + phys_addr_t mask; + u32 actions; + } wins[OB_WIN_COUNT]; + u8 wins_count; struct irq_domain *irq_domain; struct irq_chip irq_chip; raw_spinlock_t irq_lock; @@ -350,9 +397,39 @@ err: dev_err(dev, "link never came up\n"); } +/* + * Set PCIe address window register which could be used for memory + * mapping. + */ +static void advk_pcie_set_ob_win(struct advk_pcie *pcie, u8 win_num, + phys_addr_t match, phys_addr_t remap, + phys_addr_t mask, u32 actions) +{ + advk_writel(pcie, OB_WIN_ENABLE | + lower_32_bits(match), OB_WIN_MATCH_LS(win_num)); + advk_writel(pcie, upper_32_bits(match), OB_WIN_MATCH_MS(win_num)); + advk_writel(pcie, lower_32_bits(remap), OB_WIN_REMAP_LS(win_num)); + advk_writel(pcie, upper_32_bits(remap), OB_WIN_REMAP_MS(win_num)); + advk_writel(pcie, lower_32_bits(mask), OB_WIN_MASK_LS(win_num)); + advk_writel(pcie, upper_32_bits(mask), OB_WIN_MASK_MS(win_num)); + advk_writel(pcie, actions, OB_WIN_ACTIONS(win_num)); +} + +static void advk_pcie_disable_ob_win(struct advk_pcie *pcie, u8 win_num) +{ + advk_writel(pcie, 0, OB_WIN_MATCH_LS(win_num)); + advk_writel(pcie, 0, OB_WIN_MATCH_MS(win_num)); + advk_writel(pcie, 0, OB_WIN_REMAP_LS(win_num)); + advk_writel(pcie, 0, OB_WIN_REMAP_MS(win_num)); + advk_writel(pcie, 0, OB_WIN_MASK_LS(win_num)); + advk_writel(pcie, 0, OB_WIN_MASK_MS(win_num)); + advk_writel(pcie, 0, OB_WIN_ACTIONS(win_num)); +} + static void advk_pcie_setup_hw(struct advk_pcie *pcie) { u32 reg; + int i; /* Set to Direct mode */ reg = advk_readl(pcie, CTRL_CONFIG_REG); @@ -416,15 +493,51 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) reg = PCIE_IRQ_ALL_MASK & (~PCIE_IRQ_ENABLE_INTS_MASK); advk_writel(pcie, reg, HOST_CTRL_INT_MASK_REG); + /* + * Enable AXI address window location generation: + * When it is enabled, the default outbound window + * configurations (Default User Field: 0xD0074CFC) + * are used to transparent address translation for + * the outbound transactions. Thus, PCIe address + * windows are not required for transparent memory + * access when default outbound window configuration + * is set for memory access. + */ reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG); reg |= PCIE_CORE_CTRL2_OB_WIN_ENABLE; advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG); - /* Bypass the address window mapping for PIO */ + /* + * Set memory access in Default User Field so it + * is not required to configure PCIe address for + * transparent memory access. + */ + advk_writel(pcie, OB_WIN_TYPE_MEM, OB_WIN_DEFAULT_ACTIONS); + + /* + * Bypass the address window mapping for PIO: + * Since PIO access already contains all required + * info over AXI interface by PIO registers, the + * address window is not required. + */ reg = advk_readl(pcie, PIO_CTRL); reg |= PIO_CTRL_ADDR_WIN_DISABLE; advk_writel(pcie, reg, PIO_CTRL); + /* + * Configure PCIe address windows for non-memory or + * non-transparent access as by default PCIe uses + * transparent memory access. + */ + for (i = 0; i < pcie->wins_count; i++) + advk_pcie_set_ob_win(pcie, i, + pcie->wins[i].match, pcie->wins[i].remap, + pcie->wins[i].mask, pcie->wins[i].actions); + + /* Disable remaining PCIe outbound windows */ + for (i = pcie->wins_count; i < OB_WIN_COUNT; i++) + advk_pcie_disable_ob_win(pcie, i); + advk_pcie_train_link(pcie); reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); @@ -1041,6 +1154,7 @@ static int advk_pcie_probe(struct platform_device *pdev) struct resource *res; struct pci_bus *bus, *child; struct pci_host_bridge *bridge; + struct resource_entry *entry; int ret, irq; bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct advk_pcie)); @@ -1070,6 +1184,80 @@ static int advk_pcie_probe(struct platform_device *pdev) return ret; } + resource_list_for_each_entry(entry, &pcie->resources) { + resource_size_t start = entry->res->start; + resource_size_t size = resource_size(entry->res); + unsigned long type = resource_type(entry->res); + u64 win_size; + + /* + * Aardvark hardware allows to configure also PCIe window + * for config type 0 and type 1 mapping, but driver uses + * only PIO for issuing configuration transfers which does + * not use PCIe window configuration. + */ + if (type != IORESOURCE_MEM && type != IORESOURCE_MEM_64 && + type != IORESOURCE_IO) + continue; + + /* + * Skip transparent memory resources. Default outbound access + * configuration is set to transparent memory access so it + * does not need window configuration. + */ + if ((type == IORESOURCE_MEM || type == IORESOURCE_MEM_64) && + entry->offset == 0) + continue; + + /* + * The n-th PCIe window is configured by tuple (match, remap, mask) + * and an access to address A uses this window if A matches the + * match with given mask. + * So every PCIe window size must be a power of two and every start + * address must be aligned to window size. Minimal size is 64 KiB + * because lower 16 bits of mask must be zero. Remapped address + * may have set only bits from the mask. + */ + while (pcie->wins_count < OB_WIN_COUNT && size > 0) { + /* Calculate the largest aligned window size */ + win_size = (1ULL << (fls64(size)-1)) | + (start ? (1ULL << __ffs64(start)) : 0); + win_size = 1ULL << __ffs64(win_size); + if (win_size < 0x10000) + break; + + dev_dbg(dev, + "Configuring PCIe window %d: [0x%llx-0x%llx] as %lu\n", + pcie->wins_count, (unsigned long long)start, + (unsigned long long)start + win_size, type); + + if (type == IORESOURCE_IO) { + pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_IO; + pcie->wins[pcie->wins_count].match = pci_pio_to_address(start); + } else { + pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_MEM; + pcie->wins[pcie->wins_count].match = start; + } + pcie->wins[pcie->wins_count].remap = start - entry->offset; + pcie->wins[pcie->wins_count].mask = ~(win_size - 1); + + if (pcie->wins[pcie->wins_count].remap & (win_size - 1)) + break; + + start += win_size; + size -= win_size; + pcie->wins_count++; + } + + if (size > 0) { + dev_err(&pcie->pdev->dev, + "Invalid PCIe region [0x%llx-0x%llx]\n", + (unsigned long long)entry->res->start, + (unsigned long long)entry->res->end + 1); + return -EINVAL; + } + } + pcie->reset_gpio = devm_fwnode_get_index_gpiod_from_child(dev, "reset", 0, dev_fwnode(dev), From 59e36d8f3418ca2ff48cb1dbcd310c0d3d3d9d56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:25 +0100 Subject: [PATCH 047/277] PCI: aardvark: Fix PCIe Max Payload Size setting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit a4e17d65dafdd3513042d8f00404c9b6068a825c upstream. Change PCIe Max Payload Size setting in PCIe Device Control register to 512 bytes to align with PCIe Link Initialization sequence as defined in Marvell Armada 3700 Functional Specification. According to the specification, maximal Max Payload Size supported by this device is 512 bytes. Without this kernel prints suspicious line: pci 0000:01:00.0: Upstream bridge's Max Payload Size set to 256 (was 16384, max 512) With this change it changes to: pci 0000:01:00.0: Upstream bridge's Max Payload Size set to 256 (was 512, max 512) Link: https://lore.kernel.org/r/20211005180952.6812-3-kabel@kernel.org Fixes: 8c39d710363c ("PCI: aardvark: Add Aardvark PCI host controller driver") Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Cc: stable@vger.kernel.org Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index fd5155b10c1d..fc198e6e7fa4 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -453,8 +453,9 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL); reg &= ~PCI_EXP_DEVCTL_RELAX_EN; reg &= ~PCI_EXP_DEVCTL_NOSNOOP_EN; + reg &= ~PCI_EXP_DEVCTL_PAYLOAD; reg &= ~PCI_EXP_DEVCTL_READRQ; - reg |= PCI_EXP_DEVCTL_PAYLOAD; /* Set max payload size */ + reg |= PCI_EXP_DEVCTL_PAYLOAD_512B; reg |= PCI_EXP_DEVCTL_READRQ_512B; advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL); From c8e76f849aed353347c5f08df575125324847834 Mon Sep 17 00:00:00 2001 From: Frederick Lawler Date: Wed, 24 Nov 2021 23:49:26 +0100 Subject: [PATCH 048/277] PCI: Add PCI_EXP_LNKCTL2_TLS* macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit c80851f6ce63a6e313f8c7b4b6eb82c67aa4497b upstream. The Link Control 2 register is missing macros for Target Link Speeds. Add those in. Signed-off-by: Frederick Lawler [bhelgaas: use "GT" instead of "GB"] Signed-off-by: Bjorn Helgaas Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/pci_regs.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index c843929e0c4f..5db024aa00e9 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -654,6 +654,11 @@ #define PCI_EXP_LNKCAP2_SLS_8_0GB 0x00000008 /* Supported Speed 8.0GT/s */ #define PCI_EXP_LNKCAP2_CROSSLINK 0x00000100 /* Crosslink supported */ #define PCI_EXP_LNKCTL2 48 /* Link Control 2 */ +#define PCI_EXP_LNKCTL2_TLS 0x000f +#define PCI_EXP_LNKCTL2_TLS_2_5GT 0x0001 /* Supported Speed 2.5GT/s */ +#define PCI_EXP_LNKCTL2_TLS_5_0GT 0x0002 /* Supported Speed 5GT/s */ +#define PCI_EXP_LNKCTL2_TLS_8_0GT 0x0003 /* Supported Speed 8GT/s */ +#define PCI_EXP_LNKCTL2_TLS_16_0GT 0x0004 /* Supported Speed 16GT/s */ #define PCI_EXP_LNKSTA2 50 /* Link Status 2 */ #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 52 /* v2 endpoints with link end here */ #define PCI_EXP_SLTCAP2 52 /* Slot Capabilities 2 */ From edefd87df15a667ba383f9e255f3808e24cf1e6f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:27 +0100 Subject: [PATCH 049/277] PCI: aardvark: Fix link training MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f76b36d40beee0a13aa8f6aa011df0d7cbbb8a7f upstream. Fix multiple link training issues in aardvark driver. The main reason of these issues was misunderstanding of what certain registers do, since their names and comments were misleading: before commit 96be36dbffac ("PCI: aardvark: Replace custom macros by standard linux/pci_regs.h macros"), the pci-aardvark.c driver used custom macros for accessing standard PCIe Root Bridge registers, and misleading comments did not help to understand what the code was really doing. After doing more tests and experiments I've come to the conclusion that the SPEED_GEN register in aardvark sets the PCIe revision / generation compliance and forces maximal link speed. Both GEN3 and GEN2 values set the read-only PCI_EXP_FLAGS_VERS bits (PCIe capabilities version of Root Bridge) to value 2, while GEN1 value sets PCI_EXP_FLAGS_VERS to 1, which matches with PCI Express specifications revisions 3, 2 and 1 respectively. Changing SPEED_GEN also sets the read-only bits PCI_EXP_LNKCAP_SLS and PCI_EXP_LNKCAP2_SLS to corresponding speed. (Note that PCI Express rev 1 specification does not define PCI_EXP_LNKCAP2 and PCI_EXP_LNKCTL2 registers and when SPEED_GEN is set to GEN1 (which also sets PCI_EXP_FLAGS_VERS set to 1), lspci cannot access PCI_EXP_LNKCAP2 and PCI_EXP_LNKCTL2 registers.) Changing PCIe link speed can be done via PCI_EXP_LNKCTL2_TLS bits of PCI_EXP_LNKCTL2 register. Armada 3700 Functional Specifications says that the default value of PCI_EXP_LNKCTL2_TLS is based on SPEED_GEN value, but tests showed that the default value is always 8.0 GT/s, independently of speed set by SPEED_GEN. So after setting SPEED_GEN, we must also set value in PCI_EXP_LNKCTL2 register via PCI_EXP_LNKCTL2_TLS bits. Triggering PCI_EXP_LNKCTL_RL bit immediately after setting LINK_TRAINING_EN bit actually doesn't do anything. Tests have shown that a delay is needed after enabling LINK_TRAINING_EN bit. As triggering PCI_EXP_LNKCTL_RL currently does nothing, remove it. Commit 43fc679ced18 ("PCI: aardvark: Improve link training") introduced code which sets SPEED_GEN register based on negotiated link speed from PCI_EXP_LNKSTA_CLS bits of PCI_EXP_LNKSTA register. This code was added to fix detection of Compex WLE900VX (Atheros QCA9880) WiFi GEN1 PCIe cards, as otherwise these cards were "invisible" on PCIe bus (probably because they crashed). But apparently more people reported the same issues with these cards also with other PCIe controllers [1] and I was able to reproduce this issue also with other "noname" WiFi cards based on Atheros QCA9890 chip (with the same PCI vendor/device ids as Atheros QCA9880). So this is not an issue in aardvark but rather an issue in Atheros QCA98xx chips. Also, this issue only exists if the kernel is compiled with PCIe ASPM support, and a generic workaround for this is to change PCIe Bridge to 2.5 GT/s link speed via PCI_EXP_LNKCTL2_TLS_2_5GT bits in PCI_EXP_LNKCTL2 register [2], before triggering PCI_EXP_LNKCTL_RL bit. This workaround also works when SPEED_GEN is set to value GEN2 (5 GT/s). So remove this hack completely in the aardvark driver and always set SPEED_GEN to value from 'max-link-speed' DT property. Fix for Atheros QCA98xx chips is handled separately by patch [2]. These two things (code for triggering PCI_EXP_LNKCTL_RL bit and changing SPEED_GEN value) also explain why commit 6964494582f5 ("PCI: aardvark: Train link immediately after enabling training") somehow fixed detection of those problematic Compex cards with Atheros chips: if triggering link retraining (via PCI_EXP_LNKCTL_RL bit) was done immediately after enabling link training (via LINK_TRAINING_EN), it did nothing. If there was a specific delay, aardvark HW already initialized PCIe link and therefore triggering link retraining caused the above issue. Compex cards triggered link down event and disappeared from the PCIe bus. Commit f4c7d053d7f7 ("PCI: aardvark: Wait for endpoint to be ready before training link") added 100ms sleep before calling 'Start link training' command and explained that it is a requirement of PCI Express specification. But the code after this 100ms sleep was not doing 'Start link training', rather it triggered PCI_EXP_LNKCTL_RL bit via PCIe Root Bridge to put link into Recovery state. The required delay after fundamental reset is already done in function advk_pcie_wait_for_link() which also checks whether PCIe link is up. So after removing the code which triggers PCI_EXP_LNKCTL_RL bit on PCIe Root Bridge, there is no need to wait 100ms again. Remove the extra msleep() call and update comment about the delay required by the PCI Express specification. According to Marvell Armada 3700 Functional Specifications, Link training should be enabled via aardvark register LINK_TRAINING_EN after selecting PCIe generation and x1 lane. There is no need to disable it prior resetting card via PERST# signal. This disabling code was introduced in commit 5169a9851daa ("PCI: aardvark: Issue PERST via GPIO") as a workaround for some Atheros cards. It turns out that this also is Atheros specific issue and affects any PCIe controller, not only aardvark. Moreover this Atheros issue was triggered by juggling with PCI_EXP_LNKCTL_RL, LINK_TRAINING_EN and SPEED_GEN bits interleaved with sleeps. Now, after removing triggering PCI_EXP_LNKCTL_RL, there is no need to explicitly disable LINK_TRAINING_EN bit. So remove this code too. The problematic Compex cards described in previous git commits are correctly detected in advk_pcie_train_link() function even after applying all these changes. Note that with this patch, and also prior this patch, some NVMe disks which support PCIe GEN3 with 8 GT/s speed are negotiated only at the lowest link speed 2.5 GT/s, independently of SPEED_GEN value. After manually triggering PCI_EXP_LNKCTL_RL bit (e.g. from userspace via setpci), these NVMe disks change link speed to 5 GT/s when SPEED_GEN was configured to GEN2. This issue first needs to be properly investigated. I will send a fix in the future. On the other hand, some other GEN2 PCIe cards with 5 GT/s speed are autonomously by HW autonegotiated at full 5 GT/s speed without need of any software interaction. Armada 3700 Functional Specifications describes the following steps for link training: set SPEED_GEN to GEN2, enable LINK_TRAINING_EN, poll until link training is complete, trigger PCI_EXP_LNKCTL_RL, poll until signal rate is 5 GT/s, poll until link training is complete, enable ASPM L0s. The requirement for triggering PCI_EXP_LNKCTL_RL can be explained by the need to achieve 5 GT/s speed (as changing link speed is done by throw to recovery state entered by PCI_EXP_LNKCTL_RL) or maybe as a part of enabling ASPM L0s (but in this case ASPM L0s should have been enabled prior PCI_EXP_LNKCTL_RL). It is unknown why the original pci-aardvark.c driver was triggering PCI_EXP_LNKCTL_RL bit before waiting for the link to be up. This does not align with neither PCIe base specifications nor with Armada 3700 Functional Specification. (Note that in older versions of aardvark, this bit was called incorrectly PCIE_CORE_LINK_TRAINING, so this may be the reason.) It is also unknown why Armada 3700 Functional Specification says that it is needed to trigger PCI_EXP_LNKCTL_RL for GEN2 mode, as according to PCIe base specification 5 GT/s speed negotiation is supposed to be entirely autonomous, even if initial speed is 2.5 GT/s. [1] - https://lore.kernel.org/linux-pci/87h7l8axqp.fsf@toke.dk/ [2] - https://lore.kernel.org/linux-pci/20210326124326.21163-1-pali@kernel.org/ Link: https://lore.kernel.org/r/20211005180952.6812-12-kabel@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 117 ++++++++++---------------------- 1 file changed, 34 insertions(+), 83 deletions(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index fc198e6e7fa4..7c3369726c87 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -248,11 +248,6 @@ static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg) return readl(pcie->base + reg); } -static inline u16 advk_read16(struct advk_pcie *pcie, u64 reg) -{ - return advk_readl(pcie, (reg & ~0x3)) >> ((reg & 0x3) * 8); -} - static int advk_pcie_link_up(struct advk_pcie *pcie) { u32 val, ltssm_state; @@ -279,23 +274,9 @@ static int advk_pcie_wait_for_link(struct advk_pcie *pcie) static void advk_pcie_issue_perst(struct advk_pcie *pcie) { - u32 reg; - if (!pcie->reset_gpio) return; - /* - * As required by PCI Express spec (PCI Express Base Specification, REV. - * 4.0 PCI Express, February 19 2014, 6.6.1 Conventional Reset) a delay - * for at least 100ms after de-asserting PERST# signal is needed before - * link training is enabled. So ensure that link training is disabled - * prior de-asserting PERST# signal to fulfill that PCI Express spec - * requirement. - */ - reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); - reg &= ~LINK_TRAINING_EN; - advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - /* 10ms delay is needed for some cards */ dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n"); gpiod_set_value_cansleep(pcie->reset_gpio, 1); @@ -303,53 +284,46 @@ static void advk_pcie_issue_perst(struct advk_pcie *pcie) gpiod_set_value_cansleep(pcie->reset_gpio, 0); } -static int advk_pcie_train_at_gen(struct advk_pcie *pcie, int gen) +static void advk_pcie_train_link(struct advk_pcie *pcie) { - int ret, neg_gen; + struct device *dev = &pcie->pdev->dev; u32 reg; + int ret; - /* Setup link speed */ + /* + * Setup PCIe rev / gen compliance based on device tree property + * 'max-link-speed' which also forces maximal link speed. + */ reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); reg &= ~PCIE_GEN_SEL_MSK; - if (gen == 3) + if (pcie->link_gen == 3) reg |= SPEED_GEN_3; - else if (gen == 2) + else if (pcie->link_gen == 2) reg |= SPEED_GEN_2; else reg |= SPEED_GEN_1; advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); /* - * Enable link training. This is not needed in every call to this - * function, just once suffices, but it does not break anything either. + * Set maximal link speed value also into PCIe Link Control 2 register. + * Armada 3700 Functional Specification says that default value is based + * on SPEED_GEN but tests showed that default value is always 8.0 GT/s. */ + reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2); + reg &= ~PCI_EXP_LNKCTL2_TLS; + if (pcie->link_gen == 3) + reg |= PCI_EXP_LNKCTL2_TLS_8_0GT; + else if (pcie->link_gen == 2) + reg |= PCI_EXP_LNKCTL2_TLS_5_0GT; + else + reg |= PCI_EXP_LNKCTL2_TLS_2_5GT; + advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2); + + /* Enable link training after selecting PCIe generation */ reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); reg |= LINK_TRAINING_EN; advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - /* - * Start link training immediately after enabling it. - * This solves problems for some buggy cards. - */ - reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL); - reg |= PCI_EXP_LNKCTL_RL; - advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL); - - ret = advk_pcie_wait_for_link(pcie); - if (ret) - return ret; - - reg = advk_read16(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKSTA); - neg_gen = reg & PCI_EXP_LNKSTA_CLS; - - return neg_gen; -} - -static void advk_pcie_train_link(struct advk_pcie *pcie) -{ - struct device *dev = &pcie->pdev->dev; - int neg_gen = -1, gen; - /* * Reset PCIe card via PERST# signal. Some cards are not detected * during link training when they are in some non-initial state. @@ -360,41 +334,18 @@ static void advk_pcie_train_link(struct advk_pcie *pcie) * PERST# signal could have been asserted by pinctrl subsystem before * probe() callback has been called or issued explicitly by reset gpio * function advk_pcie_issue_perst(), making the endpoint going into - * fundamental reset. As required by PCI Express spec a delay for at - * least 100ms after such a reset before link training is needed. + * fundamental reset. As required by PCI Express spec (PCI Express + * Base Specification, REV. 4.0 PCI Express, February 19 2014, 6.6.1 + * Conventional Reset) a delay for at least 100ms after such a reset + * before sending a Configuration Request to the device is needed. + * So wait until PCIe link is up. Function advk_pcie_wait_for_link() + * waits for link at least 900ms. */ - msleep(PCI_PM_D3COLD_WAIT); - - /* - * Try link training at link gen specified by device tree property - * 'max-link-speed'. If this fails, iteratively train at lower gen. - */ - for (gen = pcie->link_gen; gen > 0; --gen) { - neg_gen = advk_pcie_train_at_gen(pcie, gen); - if (neg_gen > 0) - break; - } - - if (neg_gen < 0) - goto err; - - /* - * After successful training if negotiated gen is lower than requested, - * train again on negotiated gen. This solves some stability issues for - * some buggy gen1 cards. - */ - if (neg_gen < gen) { - gen = neg_gen; - neg_gen = advk_pcie_train_at_gen(pcie, gen); - } - - if (neg_gen == gen) { - dev_info(dev, "link up at gen %i\n", gen); - return; - } - -err: - dev_err(dev, "link never came up\n"); + ret = advk_pcie_wait_for_link(pcie); + if (ret < 0) + dev_err(dev, "link never came up\n"); + else + dev_info(dev, "link up\n"); } /* From d490f96f86837d7216480f6e07bf550bacf69255 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 24 Nov 2021 23:49:28 +0100 Subject: [PATCH 050/277] PCI: aardvark: Fix checking for link up via LTSSM state MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 661c399a651c11aaf83c45cbfe0b4a1fb7bc3179 upstream. Current implementation of advk_pcie_link_up() is wrong as it marks also link disabled or hot reset states as link up. Fix it by marking link up only to those states which are defined in PCIe Base specification 3.0, Table 4-14: Link Status Mapped to the LTSSM. To simplify implementation, Define macros for every LTSSM state which aardvark hardware can return in CFG_REG register. Fix also checking for link training according to the same Table 4-14. Define a new function advk_pcie_link_training() for this purpose. Link: https://lore.kernel.org/r/20211005180952.6812-13-kabel@kernel.org Fixes: 8c39d710363c ("PCI: aardvark: Add Aardvark PCI host controller driver") Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Cc: stable@vger.kernel.org Cc: Remi Pommarel Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-aardvark.c | 71 +++++++++++++++++++++++++++++++-- 1 file changed, 67 insertions(+), 4 deletions(-) diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c index 7c3369726c87..9ae544e113dc 100644 --- a/drivers/pci/host/pci-aardvark.c +++ b/drivers/pci/host/pci-aardvark.c @@ -152,9 +152,50 @@ #define CFG_REG (LMI_BASE_ADDR + 0x0) #define LTSSM_SHIFT 24 #define LTSSM_MASK 0x3f -#define LTSSM_L0 0x10 #define RC_BAR_CONFIG 0x300 +/* LTSSM values in CFG_REG */ +enum { + LTSSM_DETECT_QUIET = 0x0, + LTSSM_DETECT_ACTIVE = 0x1, + LTSSM_POLLING_ACTIVE = 0x2, + LTSSM_POLLING_COMPLIANCE = 0x3, + LTSSM_POLLING_CONFIGURATION = 0x4, + LTSSM_CONFIG_LINKWIDTH_START = 0x5, + LTSSM_CONFIG_LINKWIDTH_ACCEPT = 0x6, + LTSSM_CONFIG_LANENUM_ACCEPT = 0x7, + LTSSM_CONFIG_LANENUM_WAIT = 0x8, + LTSSM_CONFIG_COMPLETE = 0x9, + LTSSM_CONFIG_IDLE = 0xa, + LTSSM_RECOVERY_RCVR_LOCK = 0xb, + LTSSM_RECOVERY_SPEED = 0xc, + LTSSM_RECOVERY_RCVR_CFG = 0xd, + LTSSM_RECOVERY_IDLE = 0xe, + LTSSM_L0 = 0x10, + LTSSM_RX_L0S_ENTRY = 0x11, + LTSSM_RX_L0S_IDLE = 0x12, + LTSSM_RX_L0S_FTS = 0x13, + LTSSM_TX_L0S_ENTRY = 0x14, + LTSSM_TX_L0S_IDLE = 0x15, + LTSSM_TX_L0S_FTS = 0x16, + LTSSM_L1_ENTRY = 0x17, + LTSSM_L1_IDLE = 0x18, + LTSSM_L2_IDLE = 0x19, + LTSSM_L2_TRANSMIT_WAKE = 0x1a, + LTSSM_DISABLED = 0x20, + LTSSM_LOOPBACK_ENTRY_MASTER = 0x21, + LTSSM_LOOPBACK_ACTIVE_MASTER = 0x22, + LTSSM_LOOPBACK_EXIT_MASTER = 0x23, + LTSSM_LOOPBACK_ENTRY_SLAVE = 0x24, + LTSSM_LOOPBACK_ACTIVE_SLAVE = 0x25, + LTSSM_LOOPBACK_EXIT_SLAVE = 0x26, + LTSSM_HOT_RESET = 0x27, + LTSSM_RECOVERY_EQUALIZATION_PHASE0 = 0x28, + LTSSM_RECOVERY_EQUALIZATION_PHASE1 = 0x29, + LTSSM_RECOVERY_EQUALIZATION_PHASE2 = 0x2a, + LTSSM_RECOVERY_EQUALIZATION_PHASE3 = 0x2b, +}; + /* PCIe core controller registers */ #define CTRL_CORE_BASE_ADDR 0x18000 #define CTRL_CONFIG_REG (CTRL_CORE_BASE_ADDR + 0x0) @@ -248,13 +289,35 @@ static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg) return readl(pcie->base + reg); } -static int advk_pcie_link_up(struct advk_pcie *pcie) +static u8 advk_pcie_ltssm_state(struct advk_pcie *pcie) { - u32 val, ltssm_state; + u32 val; + u8 ltssm_state; val = advk_readl(pcie, CFG_REG); ltssm_state = (val >> LTSSM_SHIFT) & LTSSM_MASK; - return ltssm_state >= LTSSM_L0; + return ltssm_state; +} + +static inline bool advk_pcie_link_up(struct advk_pcie *pcie) +{ + /* check if LTSSM is in normal operation - some L* state */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ltssm_state >= LTSSM_L0 && ltssm_state < LTSSM_DISABLED; +} + +static inline bool advk_pcie_link_training(struct advk_pcie *pcie) +{ + /* + * According to PCIe Base specification 3.0, Table 4-14: Link + * Status Mapped to the LTSSM is Link Training mapped to LTSSM + * Configuration and Recovery states. + */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ((ltssm_state >= LTSSM_CONFIG_LINKWIDTH_START && + ltssm_state < LTSSM_L0) || + (ltssm_state >= LTSSM_RECOVERY_EQUALIZATION_PHASE0 && + ltssm_state <= LTSSM_RECOVERY_EQUALIZATION_PHASE3)); } static int advk_pcie_wait_for_link(struct advk_pcie *pcie) From 15d3bc71e322c9591e65ae555de40669fe957f8a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Wed, 24 Nov 2021 23:49:29 +0100 Subject: [PATCH 051/277] pinctrl: armada-37xx: Correct mpp definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 823868fceae3bac07cf5eccb128d6916e7a5ae9d upstream. This is a cleanup and fix of the patch by Ken Ma . Fix the mpp definitions according to newest revision of the specification: - northbridge: fix pmic1 gpio number to 7 fix pmic0 gpio number to 6 - southbridge split pcie1 group bit mask to BIT(5) and BIT(9) fix ptp group bit mask to BIT(11) | BIT(12) | BIT(13) add smi group with bit mask BIT(4) [gregory: split the pcie group in 2, as at hardware level they can be configured separately] Signed-off-by: Marek Behún Signed-off-by: Gregory CLEMENT Tested-by: Miquel Raynal Signed-off-by: Linus Walleij Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- .../pinctrl/marvell,armada-37xx-pinctrl.txt | 18 +++++++++++++----- drivers/pinctrl/mvebu/pinctrl-armada-37xx.c | 10 ++++++---- 2 files changed, 19 insertions(+), 9 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt index f64060908d5a..79dc09ca40ed 100644 --- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt @@ -58,11 +58,11 @@ group pwm3 - functions pwm, gpio group pmic1 - - pin 17 + - pin 7 - functions pmic, gpio group pmic0 - - pin 16 + - pin 6 - functions pmic, gpio group i2c2 @@ -112,17 +112,25 @@ group usb2_drvvbus1 - functions drvbus, gpio group sdio_sb - - pins 60-64 + - pins 60-65 - functions sdio, gpio group rgmii - - pins 42-55 + - pins 42-53 - functions mii, gpio group pcie1 - - pins 39-40 + - pins 39 - functions pcie, gpio +group pcie1_clkreq + - pins 40 + - functions pcie, gpio + +group smi + - pins 54-55 + - functions smi, gpio + group ptp - pins 56-58 - functions ptp, gpio diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c index 262f591ad8a6..4b4fd4661268 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c @@ -157,8 +157,8 @@ static struct armada_37xx_pin_group armada_37xx_nb_groups[] = { PIN_GRP_GPIO("pwm1", 12, 1, BIT(4), "pwm"), PIN_GRP_GPIO("pwm2", 13, 1, BIT(5), "pwm"), PIN_GRP_GPIO("pwm3", 14, 1, BIT(6), "pwm"), - PIN_GRP_GPIO("pmic1", 17, 1, BIT(7), "pmic"), - PIN_GRP_GPIO("pmic0", 16, 1, BIT(8), "pmic"), + PIN_GRP_GPIO("pmic1", 7, 1, BIT(7), "pmic"), + PIN_GRP_GPIO("pmic0", 6, 1, BIT(8), "pmic"), PIN_GRP_GPIO("i2c2", 2, 2, BIT(9), "i2c"), PIN_GRP_GPIO("i2c1", 0, 2, BIT(10), "i2c"), PIN_GRP_GPIO("spi_cs1", 17, 1, BIT(12), "spi"), @@ -182,8 +182,10 @@ static struct armada_37xx_pin_group armada_37xx_sb_groups[] = { PIN_GRP_GPIO("usb2_drvvbus1", 1, 1, BIT(1), "drvbus"), PIN_GRP_GPIO("sdio_sb", 24, 6, BIT(2), "sdio"), PIN_GRP_GPIO("rgmii", 6, 12, BIT(3), "mii"), - PIN_GRP_GPIO("pcie1", 3, 2, BIT(4), "pcie"), - PIN_GRP_GPIO("ptp", 20, 3, BIT(5), "ptp"), + PIN_GRP_GPIO("smi", 18, 2, BIT(4), "smi"), + PIN_GRP_GPIO("pcie1", 3, 1, BIT(5), "pcie"), + PIN_GRP_GPIO("pcie1_clkreq", 4, 1, BIT(9), "pcie"), + PIN_GRP_GPIO("ptp", 20, 3, BIT(11) | BIT(12) | BIT(13), "ptp"), PIN_GRP("ptp_clk", 21, 1, BIT(6), "ptp", "mii"), PIN_GRP("ptp_trig", 22, 1, BIT(7), "ptp", "mii"), PIN_GRP_GPIO_3("mii_col", 23, 1, BIT(8) | BIT(14), 0, BIT(8), BIT(14), From 8e7acda63318607278d446a8e07f2172973a6de8 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Wed, 24 Nov 2021 23:49:30 +0100 Subject: [PATCH 052/277] pinctrl: armada-37xx: add missing pin: PCIe1 Wakeup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 4d98fbaacd79a82f408febb66a9c42fe42361b16 upstream. Declare the PCIe1 Wakeup which was initially missing. Signed-off-by: Gregory CLEMENT Tested-by: Miquel Raynal Signed-off-by: Linus Walleij Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/mvebu/pinctrl-armada-37xx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c index 4b4fd4661268..a58367909455 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c @@ -185,6 +185,7 @@ static struct armada_37xx_pin_group armada_37xx_sb_groups[] = { PIN_GRP_GPIO("smi", 18, 2, BIT(4), "smi"), PIN_GRP_GPIO("pcie1", 3, 1, BIT(5), "pcie"), PIN_GRP_GPIO("pcie1_clkreq", 4, 1, BIT(9), "pcie"), + PIN_GRP_GPIO("pcie1_wakeup", 5, 1, BIT(10), "pcie"), PIN_GRP_GPIO("ptp", 20, 3, BIT(11) | BIT(12) | BIT(13), "ptp"), PIN_GRP("ptp_clk", 21, 1, BIT(6), "ptp", "mii"), PIN_GRP("ptp_trig", 22, 1, BIT(7), "ptp", "mii"), From f84aa271aeb793144ebd3be6720b4d9651e90563 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Wed, 24 Nov 2021 23:49:31 +0100 Subject: [PATCH 053/277] pinctrl: armada-37xx: Correct PWM pins definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit baf8d6899b1e8906dc076ef26cc633e96a8bb0c3 upstream. The PWM pins on North Bridge on Armada 37xx can be configured into PWM or GPIO functions. When in PWM function, each pin can also be configured to drive low on 0 and tri-state on 1 (LED mode). The current definitions handle this by declaring two pin groups for each pin: - group "pwmN" with functions "pwm" and "gpio" - group "ledN_od" ("od" for open drain) with functions "led" and "gpio" This is semantically incorrect. The correct definition for each pin should be one group with three functions: "pwm", "led" and "gpio". Change the "pwmN" groups to support "led" function. Remove "ledN_od" groups. This cannot break backwards compatibility with older device trees: no device tree uses it since there is no PWM driver for this SOC yet. Also "ledN_od" groups are not even documented. Fixes: b835d6953009 ("pinctrl: armada-37xx: swap polarity on LED group") Signed-off-by: Marek Behún Acked-by: Rob Herring Link: https://lore.kernel.org/r/20210719112938.27594-1-kabel@kernel.org Signed-off-by: Linus Walleij Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- .../pinctrl/marvell,armada-37xx-pinctrl.txt | 8 ++++---- drivers/pinctrl/mvebu/pinctrl-armada-37xx.c | 17 ++++++++--------- 2 files changed, 12 insertions(+), 13 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt index 79dc09ca40ed..35f469c4f675 100644 --- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt @@ -43,19 +43,19 @@ group emmc_nb group pwm0 - pin 11 (GPIO1-11) - - functions pwm, gpio + - functions pwm, led, gpio group pwm1 - pin 12 - - functions pwm, gpio + - functions pwm, led, gpio group pwm2 - pin 13 - - functions pwm, gpio + - functions pwm, led, gpio group pwm3 - pin 14 - - functions pwm, gpio + - functions pwm, led, gpio group pmic1 - pin 7 diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c index a58367909455..9f7d917458c7 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c @@ -153,10 +153,14 @@ static struct armada_37xx_pin_group armada_37xx_nb_groups[] = { PIN_GRP_GPIO("jtag", 20, 5, BIT(0), "jtag"), PIN_GRP_GPIO("sdio0", 8, 3, BIT(1), "sdio"), PIN_GRP_GPIO("emmc_nb", 27, 9, BIT(2), "emmc"), - PIN_GRP_GPIO("pwm0", 11, 1, BIT(3), "pwm"), - PIN_GRP_GPIO("pwm1", 12, 1, BIT(4), "pwm"), - PIN_GRP_GPIO("pwm2", 13, 1, BIT(5), "pwm"), - PIN_GRP_GPIO("pwm3", 14, 1, BIT(6), "pwm"), + PIN_GRP_GPIO_3("pwm0", 11, 1, BIT(3) | BIT(20), 0, BIT(20), BIT(3), + "pwm", "led"), + PIN_GRP_GPIO_3("pwm1", 12, 1, BIT(4) | BIT(21), 0, BIT(21), BIT(4), + "pwm", "led"), + PIN_GRP_GPIO_3("pwm2", 13, 1, BIT(5) | BIT(22), 0, BIT(22), BIT(5), + "pwm", "led"), + PIN_GRP_GPIO_3("pwm3", 14, 1, BIT(6) | BIT(23), 0, BIT(23), BIT(6), + "pwm", "led"), PIN_GRP_GPIO("pmic1", 7, 1, BIT(7), "pmic"), PIN_GRP_GPIO("pmic0", 6, 1, BIT(8), "pmic"), PIN_GRP_GPIO("i2c2", 2, 2, BIT(9), "i2c"), @@ -170,11 +174,6 @@ static struct armada_37xx_pin_group armada_37xx_nb_groups[] = { PIN_GRP_EXTRA("uart2", 9, 2, BIT(1) | BIT(13) | BIT(14) | BIT(19), BIT(1) | BIT(13) | BIT(14), BIT(1) | BIT(19), 18, 2, "gpio", "uart"), - PIN_GRP_GPIO_2("led0_od", 11, 1, BIT(20), BIT(20), 0, "led"), - PIN_GRP_GPIO_2("led1_od", 12, 1, BIT(21), BIT(21), 0, "led"), - PIN_GRP_GPIO_2("led2_od", 13, 1, BIT(22), BIT(22), 0, "led"), - PIN_GRP_GPIO_2("led3_od", 14, 1, BIT(23), BIT(23), 0, "led"), - }; static struct armada_37xx_pin_group armada_37xx_sb_groups[] = { From c70a0e82efd7df2807a0cb2ccf2290354f26e0ab Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 24 Nov 2021 23:49:32 +0100 Subject: [PATCH 054/277] arm64: dts: marvell: armada-37xx: declare PCIe reset pin MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit a5470af981a0cc14a650af8da5186668971a4fc8 upstream. One pin can be muxed as PCIe endpoint card reset. Signed-off-by: Miquel Raynal Signed-off-by: Gregory CLEMENT Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/marvell/armada-37xx.dtsi | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index 257bfa811fe8..a4c81a1c77b7 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -239,6 +239,15 @@ function = "mii"; }; + pcie_reset_pins: pcie-reset-pins { + groups = "pcie1"; + function = "pcie"; + }; + + pcie_clkreq_pins: pcie-clkreq-pins { + groups = "pcie1_clkreq"; + function = "pcie"; + }; }; eth0: ethernet@30000 { From c755a93aa05e6e4ccdd3a5e921c0dd36f5c22c8b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Wed, 24 Nov 2021 23:49:33 +0100 Subject: [PATCH 055/277] arm64: dts: marvell: armada-37xx: Set pcie_reset_pin to gpio function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 715878016984b2617f6c1f177c50039e12e7bd5b upstream. We found out that we are unable to control the PERST# signal via the default pin dedicated to be PERST# pin (GPIO2[3] pin) on A3700 SOC when this pin is in EP_PCIE1_Resetn mode. There is a register in the PCIe register space called PERSTN_GPIO_EN (D0088004[3]), but changing the value of this register does not change the pin output when measuring with voltmeter. We do not know if this is a bug in the SOC, or if it works only when PCIe controller is in a certain state. Commit f4c7d053d7f7 ("PCI: aardvark: Wait for endpoint to be ready before training link") says that when this pin changes pinctrl mode from EP_PCIE1_Resetn to GPIO, the PERST# signal is asserted for a brief moment. So currently the situation is that on A3700 boards the PERST# signal is asserted in U-Boot (because the code in U-Boot issues reset via this pin via GPIO mode), and then in Linux by the obscure and undocumented mechanism described by the above mentioned commit. We want to issue PERST# signal in a known way, therefore this patch changes the pcie_reset_pin function from "pcie" to "gpio" and adds the reset-gpios property to the PCIe node in device tree files of EspressoBin and Armada 3720 Dev Board (Turris Mox device tree already has this property and uDPU does not have a PCIe port). Signed-off-by: Marek Behún Cc: Remi Pommarel Tested-by: Tomasz Maciej Nowak Acked-by: Thomas Petazzoni Signed-off-by: Gregory CLEMENT Signed-off-by: Marek Behún Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/marvell/armada-3720-db.dts | 3 +++ arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts | 3 +++ arch/arm64/boot/dts/marvell/armada-37xx.dtsi | 2 +- 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/marvell/armada-3720-db.dts b/arch/arm64/boot/dts/marvell/armada-3720-db.dts index 9df0f06ce607..0a0e9e19e879 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-db.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-db.dts @@ -155,6 +155,9 @@ /* CON15(V2.0)/CON17(V1.4) : PCIe / CON15(V2.0)/CON12(V1.4) :mini-PCIe */ &pcie0 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie_reset_pins &pcie_clkreq_pins>; + reset-gpios = <&gpiosb 3 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts index 13c0ec053ada..89c7385390f4 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts @@ -82,6 +82,9 @@ /* J9 */ &pcie0 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie_reset_pins &pcie_clkreq_pins>; + reset-gpios = <&gpiosb 3 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index a4c81a1c77b7..b369356e7419 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -241,7 +241,7 @@ pcie_reset_pins: pcie-reset-pins { groups = "pcie1"; - function = "pcie"; + function = "gpio"; }; pcie_clkreq_pins: pcie-clkreq-pins { From 7bf1f5cb5150b1a53f6ccaadc0bc77f8f33206c8 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sun, 21 Nov 2021 12:40:07 -0800 Subject: [PATCH 056/277] hugetlbfs: flush TLBs correctly after huge_pmd_unshare commit a4a118f2eead1d6c49e00765de89878288d4b890 upstream. When __unmap_hugepage_range() calls to huge_pmd_unshare() succeed, a TLB flush is missing. This TLB flush must be performed before releasing the i_mmap_rwsem, in order to prevent an unshared PMDs page from being released and reused before the TLB flush took place. Arguably, a comprehensive solution would use mmu_gather interface to batch the TLB flushes and the PMDs page release, however it is not an easy solution: (1) try_to_unmap_one() and try_to_migrate_one() also call huge_pmd_unshare() and they cannot use the mmu_gather interface; and (2) deferring the release of the page reference for the PMDs page until after i_mmap_rwsem is dropeed can confuse huge_pmd_unshare() into thinking PMDs are shared when they are not. Fix __unmap_hugepage_range() by adding the missing TLB flush, and forcing a flush when unshare is successful. Fixes: 24669e58477e ("hugetlb: use mmu_gather instead of a temporary linked list for accumulating pages)" # 3.6 Signed-off-by: Nadav Amit Reviewed-by: Mike Kravetz Cc: Aneesh Kumar K.V Cc: KAMEZAWA Hiroyuki Cc: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/arm/include/asm/tlb.h | 8 ++++++++ arch/ia64/include/asm/tlb.h | 10 ++++++++++ arch/s390/include/asm/tlb.h | 14 ++++++++++++++ arch/sh/include/asm/tlb.h | 10 ++++++++++ arch/um/include/asm/tlb.h | 12 ++++++++++++ include/asm-generic/tlb.h | 2 ++ mm/hugetlb.c | 19 +++++++++++++++++++ mm/memory.c | 10 ++++++++++ 8 files changed, 85 insertions(+) diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index d5562f9ce600..fd9717e9fee3 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -280,6 +280,14 @@ tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr tlb_add_flush(tlb, addr); } +static inline void +tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size) +{ + tlb_add_flush(tlb, address); + tlb_add_flush(tlb, address + size - PMD_SIZE); +} + #define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr) #define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr) #define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp) diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index 44f0ac0df308..26d49489498b 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -269,6 +269,16 @@ __tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long addre tlb->end_addr = address + PAGE_SIZE; } +static inline void +tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size) +{ + if (tlb->start_addr > address) + tlb->start_addr = address; + if (tlb->end_addr < address + size) + tlb->end_addr = address + size; +} + #define tlb_migrate_finish(mm) platform_tlb_migrate_finish(mm) #define tlb_start_vma(tlb, vma) do { } while (0) diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 457b7ba0fbb6..c216a24ddff8 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -116,6 +116,20 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, return tlb_remove_page(tlb, page); } +static inline void tlb_flush_pmd_range(struct mmu_gather *tlb, + unsigned long address, unsigned long size) +{ + /* + * the range might exceed the original range that was provided to + * tlb_gather_mmu(), so we need to update it despite the fact it is + * usually not updated. + */ + if (tlb->start > address) + tlb->start = address; + if (tlb->end < address + size) + tlb->end = address + size; +} + /* * pte_free_tlb frees a pte table and clears the CRSTE for the * page table from the tlb. diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h index 77abe192fb43..adcb0bfe238e 100644 --- a/arch/sh/include/asm/tlb.h +++ b/arch/sh/include/asm/tlb.h @@ -127,6 +127,16 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, return tlb_remove_page(tlb, page); } +static inline void +tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size) +{ + if (tlb->start > address) + tlb->start = address; + if (tlb->end < address + size) + tlb->end = address + size; +} + #define tlb_remove_check_page_size_change tlb_remove_check_page_size_change static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, unsigned int page_size) diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h index dce6db147f24..02e61f6abfca 100644 --- a/arch/um/include/asm/tlb.h +++ b/arch/um/include/asm/tlb.h @@ -130,6 +130,18 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, return tlb_remove_page(tlb, page); } +static inline void +tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size) +{ + tlb->need_flush = 1; + + if (tlb->start > address) + tlb->start = address; + if (tlb->end < address + size) + tlb->end = address + size; +} + /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index faddde44de8c..5e7e4aaf36c5 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -117,6 +117,8 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb, void tlb_flush_mmu(struct mmu_gather *tlb); void arch_tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end, bool force); +void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size); extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c765fd01f0aa..515ba949c06a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3386,6 +3386,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); const unsigned long mmun_start = start; /* For mmu_notifiers */ const unsigned long mmun_end = end; /* For mmu_notifiers */ + bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -3407,6 +3408,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, &address, ptep)) { spin_unlock(ptl); + tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); + force_flush = true; continue; } @@ -3463,6 +3466,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); tlb_end_vma(tlb, vma); + + /* + * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We + * could defer the flush until now, since by holding i_mmap_rwsem we + * guaranteed that the last refernece would not be dropped. But we must + * do the flushing before we return, as otherwise i_mmap_rwsem will be + * dropped and the last reference to the shared PMDs page might be + * dropped as well. + * + * In theory we could defer the freeing of the PMD pages as well, but + * huge_pmd_unshare() relies on the exact page_count for the PMD page to + * detect sharing, so we cannot defer the release of the page either. + * Instead, do flush now. + */ + if (force_flush) + tlb_flush_mmu(tlb); } void __unmap_hugepage_range_final(struct mmu_gather *tlb, diff --git a/mm/memory.c b/mm/memory.c index c4f142d1ff98..b001670c9615 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -335,6 +335,16 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ return false; } +void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, + unsigned long size) +{ + if (tlb->page_size != 0 && tlb->page_size != PMD_SIZE) + tlb_flush_mmu(tlb); + + tlb->page_size = PMD_SIZE; + tlb->start = min(tlb->start, address); + tlb->end = max(tlb->end, address + size); +} #endif /* HAVE_GENERIC_MMU_GATHER */ #ifdef CONFIG_HAVE_RCU_TABLE_FREE From 99d348b82bcb36171f24411d3f1a15706a2a937a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 19 Nov 2021 16:43:58 -0800 Subject: [PATCH 057/277] proc/vmcore: fix clearing user buffer by properly using clear_user() commit c1e63117711977cc4295b2ce73de29dd17066c82 upstream. To clear a user buffer we cannot simply use memset, we have to use clear_user(). With a virtio-mem device that registers a vmcore_cb and has some logically unplugged memory inside an added Linux memory block, I can easily trigger a BUG by copying the vmcore via "cp": systemd[1]: Starting Kdump Vmcore Save Service... kdump[420]: Kdump is using the default log level(3). kdump[453]: saving to /sysroot/var/crash/127.0.0.1-2021-11-11-14:59:22/ kdump[458]: saving vmcore-dmesg.txt to /sysroot/var/crash/127.0.0.1-2021-11-11-14:59:22/ kdump[465]: saving vmcore-dmesg.txt complete kdump[467]: saving vmcore BUG: unable to handle page fault for address: 00007f2374e01000 #PF: supervisor write access in kernel mode #PF: error_code(0x0003) - permissions violation PGD 7a523067 P4D 7a523067 PUD 7a528067 PMD 7a525067 PTE 800000007048f867 Oops: 0003 [#1] PREEMPT SMP NOPTI CPU: 0 PID: 468 Comm: cp Not tainted 5.15.0+ #6 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.14.0-27-g64f37cc530f1-prebuilt.qemu.org 04/01/2014 RIP: 0010:read_from_oldmem.part.0.cold+0x1d/0x86 Code: ff ff ff e8 05 ff fe ff e9 b9 e9 7f ff 48 89 de 48 c7 c7 38 3b 60 82 e8 f1 fe fe ff 83 fd 08 72 3c 49 8d 7d 08 4c 89 e9 89 e8 <49> c7 45 00 00 00 00 00 49 c7 44 05 f8 00 00 00 00 48 83 e7 f81 RSP: 0018:ffffc9000073be08 EFLAGS: 00010212 RAX: 0000000000001000 RBX: 00000000002fd000 RCX: 00007f2374e01000 RDX: 0000000000000001 RSI: 00000000ffffdfff RDI: 00007f2374e01008 RBP: 0000000000001000 R08: 0000000000000000 R09: ffffc9000073bc50 R10: ffffc9000073bc48 R11: ffffffff829461a8 R12: 000000000000f000 R13: 00007f2374e01000 R14: 0000000000000000 R15: ffff88807bd421e8 FS: 00007f2374e12140(0000) GS:ffff88807f000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2374e01000 CR3: 000000007a4aa000 CR4: 0000000000350eb0 Call Trace: read_vmcore+0x236/0x2c0 proc_reg_read+0x55/0xa0 vfs_read+0x95/0x190 ksys_read+0x4f/0xc0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae Some x86-64 CPUs have a CPU feature called "Supervisor Mode Access Prevention (SMAP)", which is used to detect wrong access from the kernel to user buffers like this: SMAP triggers a permissions violation on wrong access. In the x86-64 variant of clear_user(), SMAP is properly handled via clac()+stac(). To fix, properly use clear_user() when we're dealing with a user buffer. Link: https://lkml.kernel.org/r/20211112092750.6921-1-david@redhat.com Fixes: 997c136f518c ("fs/proc/vmcore.c: add hook to read_from_oldmem() to check for non-ram pages") Signed-off-by: David Hildenbrand Acked-by: Baoquan He Cc: Dave Young Cc: Baoquan He Cc: Vivek Goyal Cc: Philipp Rudo Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/proc/vmcore.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index aaa7486b6f0d..0bfd71bec7f2 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -105,14 +105,19 @@ static ssize_t read_from_oldmem(char *buf, size_t count, nr_bytes = count; /* If pfn is not ram, return zeros for sparse dump files */ - if (pfn_is_ram(pfn) == 0) - memset(buf, 0, nr_bytes); - else { + if (pfn_is_ram(pfn) == 0) { + tmp = 0; + if (!userbuf) + memset(buf, 0, nr_bytes); + else if (clear_user(buf, nr_bytes)) + tmp = -EFAULT; + } else { tmp = copy_oldmem_page(pfn, buf, nr_bytes, offset, userbuf); - if (tmp < 0) - return tmp; } + if (tmp < 0) + return tmp; + *ppos += nr_bytes; count -= nr_bytes; buf += nr_bytes; From 8937bfa226d4001875d8539ae811fce6d3df4c96 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Tue, 16 Nov 2021 23:27:32 +0800 Subject: [PATCH 058/277] NFC: add NCI_UNREG flag to eliminate the race commit 48b71a9e66c2eab60564b1b1c85f4928ed04e406 upstream. There are two sites that calls queue_work() after the destroy_workqueue() and lead to possible UAF. The first site is nci_send_cmd(), which can happen after the nci_close_device as below nfcmrvl_nci_unregister_dev | nfc_genl_dev_up nci_close_device | flush_workqueue | del_timer_sync | nci_unregister_device | nfc_get_device destroy_workqueue | nfc_dev_up nfc_unregister_device | nci_dev_up device_del | nci_open_device | __nci_request | nci_send_cmd | queue_work !!! Another site is nci_cmd_timer, awaked by the nci_cmd_work from the nci_send_cmd. ... | ... nci_unregister_device | queue_work destroy_workqueue | nfc_unregister_device | ... device_del | nci_cmd_work | mod_timer | ... | nci_cmd_timer | queue_work !!! For the above two UAF, the root cause is that the nfc_dev_up can race between the nci_unregister_device routine. Therefore, this patch introduce NCI_UNREG flag to easily eliminate the possible race. In addition, the mutex_lock in nci_close_device can act as a barrier. Signed-off-by: Lin Ma Fixes: 6a2968aaf50c ("NFC: basic NCI protocol implementation") Reviewed-by: Jakub Kicinski Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20211116152732.19238-1-linma@zju.edu.cn Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/nfc/nci_core.h | 1 + net/nfc/nci/core.c | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index e67564af6f93..1560ce548add 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -42,6 +42,7 @@ enum nci_flag { NCI_UP, NCI_DATA_EXCHANGE, NCI_DATA_EXCHANGE_TO, + NCI_UNREG, }; /* NCI device states */ diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index c73651faa549..c6dc82f66bd9 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -485,6 +485,11 @@ static int nci_open_device(struct nci_dev *ndev) mutex_lock(&ndev->req_lock); + if (test_bit(NCI_UNREG, &ndev->flags)) { + rc = -ENODEV; + goto done; + } + if (test_bit(NCI_UP, &ndev->flags)) { rc = -EALREADY; goto done; @@ -548,6 +553,10 @@ done: static int nci_close_device(struct nci_dev *ndev) { nci_req_cancel(ndev, ENODEV); + + /* This mutex needs to be held as a barrier for + * caller nci_unregister_device + */ mutex_lock(&ndev->req_lock); if (!test_and_clear_bit(NCI_UP, &ndev->flags)) { @@ -585,8 +594,8 @@ static int nci_close_device(struct nci_dev *ndev) /* Flush cmd wq */ flush_workqueue(ndev->cmd_wq); - /* Clear flags */ - ndev->flags = 0; + /* Clear flags except NCI_UNREG */ + ndev->flags &= BIT(NCI_UNREG); mutex_unlock(&ndev->req_lock); @@ -1270,6 +1279,12 @@ void nci_unregister_device(struct nci_dev *ndev) { struct nci_conn_info *conn_info, *n; + /* This set_bit is not protected with specialized barrier, + * However, it is fine because the mutex_lock(&ndev->req_lock); + * in nci_close_device() will help to emit one. + */ + set_bit(NCI_UNREG, &ndev->flags); + nci_close_device(ndev); destroy_workqueue(ndev->cmd_wq); From 89f4bb06cdeab8e503812170524099e5e48b2998 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 25 Nov 2021 14:05:18 +0100 Subject: [PATCH 059/277] fuse: release pipe buf after last use commit 473441720c8616dfaf4451f9c7ea14f0eb5e5d65 upstream. Checking buf->flags should be done before the pipe_buf_release() is called on the pipe buffer, since releasing the buffer might modify the flags. This is exactly what page_cache_pipe_buf_release() does, and which results in the same VM_BUG_ON_PAGE(PageLRU(page)) that the original patch was trying to fix. Reported-by: Justin Forbes Fixes: 712a951025c0 ("fuse: fix page stealing") Cc: # v2.6.35 Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/fuse/dev.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 4a142150e872..db7d746633cf 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -897,17 +897,17 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) goto out_put_old; } + get_page(newpage); + + if (!(buf->flags & PIPE_BUF_FLAG_LRU)) + lru_cache_add_file(newpage); + /* * Release while we have extra ref on stolen page. Otherwise * anon_pipe_buf_release() might think the page can be reused. */ pipe_buf_release(cs->pipe, buf); - get_page(newpage); - - if (!(buf->flags & PIPE_BUF_FLAG_LRU)) - lru_cache_add_file(newpage); - err = 0; spin_lock(&cs->req->waitq.lock); if (test_bit(FR_ABORTED, &cs->req->flags)) From f705764dfa6347331624214b8147361ac0fa0dfe Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 29 Nov 2021 08:36:21 +0100 Subject: [PATCH 060/277] xen: sync include/xen/interface/io/ring.h with Xen's newest version commit 629a5d87e26fe96bcaab44cbb81f5866af6f7008 upstream. Sync include/xen/interface/io/ring.h with Xen's newest version in order to get the RING_COPY_RESPONSE() and RING_RESPONSE_PROD_OVERFLOW() macros. Note that this will correct the wrong license info by adding the missing original copyright notice. Signed-off-by: Juergen Gross Signed-off-by: Greg Kroah-Hartman --- include/xen/interface/io/ring.h | 295 +++++++++++++++++--------------- 1 file changed, 159 insertions(+), 136 deletions(-) diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index 3f40501fc60b..b39cdbc522ec 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -1,21 +1,53 @@ -/* SPDX-License-Identifier: GPL-2.0 */ /****************************************************************************** * ring.h * * Shared producer-consumer ring macros. * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * * Tim Deegan and Andrew Warfield November 2004. */ #ifndef __XEN_PUBLIC_IO_RING_H__ #define __XEN_PUBLIC_IO_RING_H__ +/* + * When #include'ing this header, you need to provide the following + * declaration upfront: + * - standard integers types (uint8_t, uint16_t, etc) + * They are provided by stdint.h of the standard headers. + * + * In addition, if you intend to use the FLEX macros, you also need to + * provide the following, before invoking the FLEX macros: + * - size_t + * - memcpy + * - grant_ref_t + * These declarations are provided by string.h of the standard headers, + * and grant_table.h from the Xen public headers. + */ + #include typedef unsigned int RING_IDX; /* Round a 32-bit unsigned constant down to the nearest power of two. */ -#define __RD2(_x) (((_x) & 0x00000002) ? 0x2 : ((_x) & 0x1)) +#define __RD2(_x) (((_x) & 0x00000002) ? 0x2 : ((_x) & 0x1)) #define __RD4(_x) (((_x) & 0x0000000c) ? __RD2((_x)>>2)<<2 : __RD2(_x)) #define __RD8(_x) (((_x) & 0x000000f0) ? __RD4((_x)>>4)<<4 : __RD4(_x)) #define __RD16(_x) (((_x) & 0x0000ff00) ? __RD8((_x)>>8)<<8 : __RD8(_x)) @@ -27,82 +59,79 @@ typedef unsigned int RING_IDX; * A ring contains as many entries as will fit, rounded down to the nearest * power of two (so we can mask with (size-1) to loop around). */ -#define __CONST_RING_SIZE(_s, _sz) \ - (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \ - sizeof(((struct _s##_sring *)0)->ring[0]))) - +#define __CONST_RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \ + sizeof(((struct _s##_sring *)0)->ring[0]))) /* * The same for passing in an actual pointer instead of a name tag. */ -#define __RING_SIZE(_s, _sz) \ - (__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) +#define __RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - (long)(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) /* * Macros to make the correct C datatypes for a new kind of ring. * * To make a new ring datatype, you need to have two message structures, - * let's say struct request, and struct response already defined. + * let's say request_t, and response_t already defined. * * In a header where you want the ring datatype declared, you then do: * - * DEFINE_RING_TYPES(mytag, struct request, struct response); + * DEFINE_RING_TYPES(mytag, request_t, response_t); * * These expand out to give you a set of types, as you can see below. * The most important of these are: * - * struct mytag_sring - The shared ring. - * struct mytag_front_ring - The 'front' half of the ring. - * struct mytag_back_ring - The 'back' half of the ring. + * mytag_sring_t - The shared ring. + * mytag_front_ring_t - The 'front' half of the ring. + * mytag_back_ring_t - The 'back' half of the ring. * * To initialize a ring in your code you need to know the location and size * of the shared memory area (PAGE_SIZE, for instance). To initialise * the front half: * - * struct mytag_front_ring front_ring; - * SHARED_RING_INIT((struct mytag_sring *)shared_page); - * FRONT_RING_INIT(&front_ring, (struct mytag_sring *)shared_page, - * PAGE_SIZE); + * mytag_front_ring_t front_ring; + * SHARED_RING_INIT((mytag_sring_t *)shared_page); + * FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); * * Initializing the back follows similarly (note that only the front * initializes the shared ring): * - * struct mytag_back_ring back_ring; - * BACK_RING_INIT(&back_ring, (struct mytag_sring *)shared_page, - * PAGE_SIZE); + * mytag_back_ring_t back_ring; + * BACK_RING_INIT(&back_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); */ -#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \ - \ -/* Shared ring entry */ \ -union __name##_sring_entry { \ - __req_t req; \ - __rsp_t rsp; \ -}; \ - \ -/* Shared ring page */ \ -struct __name##_sring { \ - RING_IDX req_prod, req_event; \ - RING_IDX rsp_prod, rsp_event; \ - uint8_t pad[48]; \ - union __name##_sring_entry ring[1]; /* variable-length */ \ -}; \ - \ -/* "Front" end's private variables */ \ -struct __name##_front_ring { \ - RING_IDX req_prod_pvt; \ - RING_IDX rsp_cons; \ - unsigned int nr_ents; \ - struct __name##_sring *sring; \ -}; \ - \ -/* "Back" end's private variables */ \ -struct __name##_back_ring { \ - RING_IDX rsp_prod_pvt; \ - RING_IDX req_cons; \ - unsigned int nr_ents; \ - struct __name##_sring *sring; \ -}; - +#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \ + \ +/* Shared ring entry */ \ +union __name##_sring_entry { \ + __req_t req; \ + __rsp_t rsp; \ +}; \ + \ +/* Shared ring page */ \ +struct __name##_sring { \ + RING_IDX req_prod, req_event; \ + RING_IDX rsp_prod, rsp_event; \ + uint8_t __pad[48]; \ + union __name##_sring_entry ring[1]; /* variable-length */ \ +}; \ + \ +/* "Front" end's private variables */ \ +struct __name##_front_ring { \ + RING_IDX req_prod_pvt; \ + RING_IDX rsp_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; \ + \ +/* "Back" end's private variables */ \ +struct __name##_back_ring { \ + RING_IDX rsp_prod_pvt; \ + RING_IDX req_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; \ + \ /* * Macros for manipulating rings. * @@ -119,105 +148,99 @@ struct __name##_back_ring { \ */ /* Initialising empty rings */ -#define SHARED_RING_INIT(_s) do { \ - (_s)->req_prod = (_s)->rsp_prod = 0; \ - (_s)->req_event = (_s)->rsp_event = 1; \ - memset((_s)->pad, 0, sizeof((_s)->pad)); \ +#define SHARED_RING_INIT(_s) do { \ + (_s)->req_prod = (_s)->rsp_prod = 0; \ + (_s)->req_event = (_s)->rsp_event = 1; \ + (void)memset((_s)->__pad, 0, sizeof((_s)->__pad)); \ } while(0) -#define FRONT_RING_INIT(_r, _s, __size) do { \ - (_r)->req_prod_pvt = 0; \ - (_r)->rsp_cons = 0; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ - (_r)->sring = (_s); \ +#define FRONT_RING_ATTACH(_r, _s, _i, __size) do { \ + (_r)->req_prod_pvt = (_i); \ + (_r)->rsp_cons = (_i); \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ } while (0) -#define BACK_RING_INIT(_r, _s, __size) do { \ - (_r)->rsp_prod_pvt = 0; \ - (_r)->req_cons = 0; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ - (_r)->sring = (_s); \ +#define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size) + +#define BACK_RING_ATTACH(_r, _s, _i, __size) do { \ + (_r)->rsp_prod_pvt = (_i); \ + (_r)->req_cons = (_i); \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ } while (0) -/* Initialize to existing shared indexes -- for recovery */ -#define FRONT_RING_ATTACH(_r, _s, __size) do { \ - (_r)->sring = (_s); \ - (_r)->req_prod_pvt = (_s)->req_prod; \ - (_r)->rsp_cons = (_s)->rsp_prod; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ -} while (0) - -#define BACK_RING_ATTACH(_r, _s, __size) do { \ - (_r)->sring = (_s); \ - (_r)->rsp_prod_pvt = (_s)->rsp_prod; \ - (_r)->req_cons = (_s)->req_prod; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ -} while (0) +#define BACK_RING_INIT(_r, _s, __size) BACK_RING_ATTACH(_r, _s, 0, __size) /* How big is this ring? */ -#define RING_SIZE(_r) \ +#define RING_SIZE(_r) \ ((_r)->nr_ents) /* Number of free requests (for use on front side only). */ -#define RING_FREE_REQUESTS(_r) \ +#define RING_FREE_REQUESTS(_r) \ (RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons)) /* Test if there is an empty slot available on the front ring. * (This is only meaningful from the front. ) */ -#define RING_FULL(_r) \ +#define RING_FULL(_r) \ (RING_FREE_REQUESTS(_r) == 0) /* Test if there are outstanding messages to be processed on a ring. */ -#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ +#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ ((_r)->sring->rsp_prod - (_r)->rsp_cons) -#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ - ({ \ - unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ - unsigned int rsp = RING_SIZE(_r) - \ - ((_r)->req_cons - (_r)->rsp_prod_pvt); \ - req < rsp ? req : rsp; \ - }) +#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({ \ + unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ + unsigned int rsp = RING_SIZE(_r) - \ + ((_r)->req_cons - (_r)->rsp_prod_pvt); \ + req < rsp ? req : rsp; \ +}) /* Direct access to individual ring elements, by index. */ -#define RING_GET_REQUEST(_r, _idx) \ +#define RING_GET_REQUEST(_r, _idx) \ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) +#define RING_GET_RESPONSE(_r, _idx) \ + (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp)) + /* - * Get a local copy of a request. + * Get a local copy of a request/response. * - * Use this in preference to RING_GET_REQUEST() so all processing is + * Use this in preference to RING_GET_{REQUEST,RESPONSE}() so all processing is * done on a local copy that cannot be modified by the other end. * * Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this - * to be ineffective where _req is a struct which consists of only bitfields. + * to be ineffective where dest is a struct which consists of only bitfields. */ -#define RING_COPY_REQUEST(_r, _idx, _req) do { \ - /* Use volatile to force the copy into _req. */ \ - *(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx); \ +#define RING_COPY_(type, r, idx, dest) do { \ + /* Use volatile to force the copy into dest. */ \ + *(dest) = *(volatile typeof(dest))RING_GET_##type(r, idx); \ } while (0) -#define RING_GET_RESPONSE(_r, _idx) \ - (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp)) +#define RING_COPY_REQUEST(r, idx, req) RING_COPY_(REQUEST, r, idx, req) +#define RING_COPY_RESPONSE(r, idx, rsp) RING_COPY_(RESPONSE, r, idx, rsp) /* Loop termination condition: Would the specified index overflow the ring? */ -#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ +#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r)) /* Ill-behaved frontend determination: Can there be this many requests? */ -#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \ +#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \ (((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r)) +/* Ill-behaved backend determination: Can there be this many responses? */ +#define RING_RESPONSE_PROD_OVERFLOW(_r, _prod) \ + (((_prod) - (_r)->rsp_cons) > RING_SIZE(_r)) -#define RING_PUSH_REQUESTS(_r) do { \ - virt_wmb(); /* back sees requests /before/ updated producer index */ \ - (_r)->sring->req_prod = (_r)->req_prod_pvt; \ +#define RING_PUSH_REQUESTS(_r) do { \ + virt_wmb(); /* back sees requests /before/ updated producer index */\ + (_r)->sring->req_prod = (_r)->req_prod_pvt; \ } while (0) -#define RING_PUSH_RESPONSES(_r) do { \ - virt_wmb(); /* front sees responses /before/ updated producer index */ \ - (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \ +#define RING_PUSH_RESPONSES(_r) do { \ + virt_wmb(); /* front sees resps /before/ updated producer index */ \ + (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \ } while (0) /* @@ -250,40 +273,40 @@ struct __name##_back_ring { \ * field appropriately. */ -#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \ - RING_IDX __old = (_r)->sring->req_prod; \ - RING_IDX __new = (_r)->req_prod_pvt; \ - virt_wmb(); /* back sees requests /before/ updated producer index */ \ - (_r)->sring->req_prod = __new; \ - virt_mb(); /* back sees new requests /before/ we check req_event */ \ - (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \ - (RING_IDX)(__new - __old)); \ +#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->req_prod; \ + RING_IDX __new = (_r)->req_prod_pvt; \ + virt_wmb(); /* back sees requests /before/ updated producer index */\ + (_r)->sring->req_prod = __new; \ + virt_mb(); /* back sees new requests /before/ we check req_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \ + (RING_IDX)(__new - __old)); \ } while (0) -#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \ - RING_IDX __old = (_r)->sring->rsp_prod; \ - RING_IDX __new = (_r)->rsp_prod_pvt; \ - virt_wmb(); /* front sees responses /before/ updated producer index */ \ - (_r)->sring->rsp_prod = __new; \ - virt_mb(); /* front sees new responses /before/ we check rsp_event */ \ - (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \ - (RING_IDX)(__new - __old)); \ +#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->rsp_prod; \ + RING_IDX __new = (_r)->rsp_prod_pvt; \ + virt_wmb(); /* front sees resps /before/ updated producer index */ \ + (_r)->sring->rsp_prod = __new; \ + virt_mb(); /* front sees new resps /before/ we check rsp_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \ + (RING_IDX)(__new - __old)); \ } while (0) -#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \ - (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ - if (_work_to_do) break; \ - (_r)->sring->req_event = (_r)->req_cons + 1; \ - virt_mb(); \ - (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ +#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ + if (_work_to_do) break; \ + (_r)->sring->req_event = (_r)->req_cons + 1; \ + virt_mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ } while (0) -#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \ - (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ - if (_work_to_do) break; \ - (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \ - virt_mb(); \ - (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ +#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ + if (_work_to_do) break; \ + (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \ + virt_mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ } while (0) From 4ef991a05c00c59c7829b08e8a2be8f79dc6b1b1 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 29 Nov 2021 08:41:07 +0100 Subject: [PATCH 061/277] xen/blkfront: read response from backend only once MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 71b66243f9898d0e54296b4e7035fb33cdcb0707 upstream. In order to avoid problems in case the backend is modifying a response on the ring page while the frontend has already seen it, just read the response into a local buffer in one go and then operate on that buffer only. Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Acked-by: Roger Pau Monné Link: https://lore.kernel.org/r/20210730103854.12681-2-jgross@suse.com Signed-off-by: Juergen Gross Signed-off-by: Greg Kroah-Hartman --- drivers/block/xen-blkfront.c | 35 ++++++++++++++++++----------------- 1 file changed, 18 insertions(+), 17 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 7ba58c39146f..a61714f3272b 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1550,7 +1550,7 @@ static bool blkif_completion(unsigned long *id, static irqreturn_t blkif_interrupt(int irq, void *dev_id) { struct request *req; - struct blkif_response *bret; + struct blkif_response bret; RING_IDX i, rp; unsigned long flags; struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id; @@ -1567,8 +1567,9 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) for (i = rinfo->ring.rsp_cons; i != rp; i++) { unsigned long id; - bret = RING_GET_RESPONSE(&rinfo->ring, i); - id = bret->id; + RING_COPY_RESPONSE(&rinfo->ring, i, &bret); + id = bret.id; + /* * The backend has messed up and given us an id that we would * never have given to it (we stamp it up to BLK_RING_SIZE - @@ -1576,39 +1577,39 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) */ if (id >= BLK_RING_SIZE(info)) { WARN(1, "%s: response to %s has incorrect id (%ld)\n", - info->gd->disk_name, op_name(bret->operation), id); + info->gd->disk_name, op_name(bret.operation), id); /* We can't safely get the 'struct request' as * the id is busted. */ continue; } req = rinfo->shadow[id].request; - if (bret->operation != BLKIF_OP_DISCARD) { + if (bret.operation != BLKIF_OP_DISCARD) { /* * We may need to wait for an extra response if the * I/O request is split in 2 */ - if (!blkif_completion(&id, rinfo, bret)) + if (!blkif_completion(&id, rinfo, &bret)) continue; } if (add_id_to_freelist(rinfo, id)) { WARN(1, "%s: response to %s (id %ld) couldn't be recycled!\n", - info->gd->disk_name, op_name(bret->operation), id); + info->gd->disk_name, op_name(bret.operation), id); continue; } - if (bret->status == BLKIF_RSP_OKAY) + if (bret.status == BLKIF_RSP_OKAY) blkif_req(req)->error = BLK_STS_OK; else blkif_req(req)->error = BLK_STS_IOERR; - switch (bret->operation) { + switch (bret.operation) { case BLKIF_OP_DISCARD: - if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) { + if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) { struct request_queue *rq = info->rq; printk(KERN_WARNING "blkfront: %s: %s op failed\n", - info->gd->disk_name, op_name(bret->operation)); + info->gd->disk_name, op_name(bret.operation)); blkif_req(req)->error = BLK_STS_NOTSUPP; info->feature_discard = 0; info->feature_secdiscard = 0; @@ -1618,15 +1619,15 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) break; case BLKIF_OP_FLUSH_DISKCACHE: case BLKIF_OP_WRITE_BARRIER: - if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) { + if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) { printk(KERN_WARNING "blkfront: %s: %s op failed\n", - info->gd->disk_name, op_name(bret->operation)); + info->gd->disk_name, op_name(bret.operation)); blkif_req(req)->error = BLK_STS_NOTSUPP; } - if (unlikely(bret->status == BLKIF_RSP_ERROR && + if (unlikely(bret.status == BLKIF_RSP_ERROR && rinfo->shadow[id].req.u.rw.nr_segments == 0)) { printk(KERN_WARNING "blkfront: %s: empty %s op failed\n", - info->gd->disk_name, op_name(bret->operation)); + info->gd->disk_name, op_name(bret.operation)); blkif_req(req)->error = BLK_STS_NOTSUPP; } if (unlikely(blkif_req(req)->error)) { @@ -1639,9 +1640,9 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) /* fall through */ case BLKIF_OP_READ: case BLKIF_OP_WRITE: - if (unlikely(bret->status != BLKIF_RSP_OKAY)) + if (unlikely(bret.status != BLKIF_RSP_OKAY)) dev_dbg(&info->xbdev->dev, "Bad return from blkdev data " - "request: %x\n", bret->status); + "request: %x\n", bret.status); break; default: From d5406c3ba1b8e4a7edda4a3b2ca3d8e4db6f2cbe Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 29 Nov 2021 08:45:38 +0100 Subject: [PATCH 062/277] xen/blkfront: don't take local copy of a request from the ring page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 8f5a695d99000fc3aa73934d7ced33cfc64dcdab upstream. In order to avoid a malicious backend being able to influence the local copy of a request build the request locally first and then copy it to the ring page instead of doing it the other way round as today. Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Acked-by: Roger Pau Monné Link: https://lore.kernel.org/r/20210730103854.12681-3-jgross@suse.com Signed-off-by: Juergen Gross Signed-off-by: Greg Kroah-Hartman --- drivers/block/xen-blkfront.c | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index a61714f3272b..c9b055c109fe 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -537,7 +537,7 @@ static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo, rinfo->shadow[id].status = REQ_WAITING; rinfo->shadow[id].associated_id = NO_ASSOCIATED_ID; - (*ring_req)->u.rw.id = id; + rinfo->shadow[id].req.u.rw.id = id; return id; } @@ -545,11 +545,12 @@ static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo, static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_info *rinfo) { struct blkfront_info *info = rinfo->dev_info; - struct blkif_request *ring_req; + struct blkif_request *ring_req, *final_ring_req; unsigned long id; /* Fill out a communications ring structure. */ - id = blkif_ring_get_request(rinfo, req, &ring_req); + id = blkif_ring_get_request(rinfo, req, &final_ring_req); + ring_req = &rinfo->shadow[id].req; ring_req->operation = BLKIF_OP_DISCARD; ring_req->u.discard.nr_sectors = blk_rq_sectors(req); @@ -560,8 +561,8 @@ static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_inf else ring_req->u.discard.flag = 0; - /* Keep a private copy so we can reissue requests when recovering. */ - rinfo->shadow[id].req = *ring_req; + /* Copy the request to the ring page. */ + *final_ring_req = *ring_req; return 0; } @@ -694,6 +695,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri { struct blkfront_info *info = rinfo->dev_info; struct blkif_request *ring_req, *extra_ring_req = NULL; + struct blkif_request *final_ring_req, *final_extra_ring_req = NULL; unsigned long id, extra_id = NO_ASSOCIATED_ID; bool require_extra_req = false; int i; @@ -738,7 +740,8 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri } /* Fill out a communications ring structure. */ - id = blkif_ring_get_request(rinfo, req, &ring_req); + id = blkif_ring_get_request(rinfo, req, &final_ring_req); + ring_req = &rinfo->shadow[id].req; num_sg = blk_rq_map_sg(req->q, req, rinfo->shadow[id].sg); num_grant = 0; @@ -789,7 +792,9 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri ring_req->u.rw.nr_segments = num_grant; if (unlikely(require_extra_req)) { extra_id = blkif_ring_get_request(rinfo, req, - &extra_ring_req); + &final_extra_ring_req); + extra_ring_req = &rinfo->shadow[extra_id].req; + /* * Only the first request contains the scatter-gather * list. @@ -831,10 +836,10 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri if (setup.segments) kunmap_atomic(setup.segments); - /* Keep a private copy so we can reissue requests when recovering. */ - rinfo->shadow[id].req = *ring_req; + /* Copy request(s) to the ring page. */ + *final_ring_req = *ring_req; if (unlikely(require_extra_req)) - rinfo->shadow[extra_id].req = *extra_ring_req; + *final_extra_ring_req = *extra_ring_req; if (new_persistent_gnts) gnttab_free_grant_references(setup.gref_head); From 2bded27ef14c7488682068f3dc4ba1dd5a90789b Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 29 Nov 2021 11:05:28 +0100 Subject: [PATCH 063/277] xen/blkfront: don't trust the backend response data blindly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b94e4b147fd1992ad450e1fea1fdaa3738753373 upstream. Today blkfront will trust the backend to send only sane response data. In order to avoid privilege escalations or crashes in case of malicious backends verify the data to be within expected limits. Especially make sure that the response always references an outstanding request. Introduce a new state of the ring BLKIF_STATE_ERROR which will be switched to in case an inconsistency is being detected. Recovering from this state is possible only via removing and adding the virtual device again (e.g. via a suspend/resume cycle). Make all warning messages issued due to valid error responses rate limited in order to avoid message floods being triggered by a malicious backend. Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Acked-by: Roger Pau Monné Link: https://lore.kernel.org/r/20210730103854.12681-4-jgross@suse.com Signed-off-by: Juergen Gross Signed-off-by: Greg Kroah-Hartman --- drivers/block/xen-blkfront.c | 70 +++++++++++++++++++++++++++--------- 1 file changed, 53 insertions(+), 17 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index c9b055c109fe..878eb9ba06b2 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -78,6 +78,7 @@ enum blkif_state { BLKIF_STATE_DISCONNECTED, BLKIF_STATE_CONNECTED, BLKIF_STATE_SUSPENDED, + BLKIF_STATE_ERROR, }; struct grant { @@ -87,6 +88,7 @@ struct grant { }; enum blk_req_status { + REQ_PROCESSING, REQ_WAITING, REQ_DONE, REQ_ERROR, @@ -534,7 +536,7 @@ static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo, id = get_id_from_freelist(rinfo); rinfo->shadow[id].request = req; - rinfo->shadow[id].status = REQ_WAITING; + rinfo->shadow[id].status = REQ_PROCESSING; rinfo->shadow[id].associated_id = NO_ASSOCIATED_ID; rinfo->shadow[id].req.u.rw.id = id; @@ -563,6 +565,7 @@ static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_inf /* Copy the request to the ring page. */ *final_ring_req = *ring_req; + rinfo->shadow[id].status = REQ_WAITING; return 0; } @@ -838,8 +841,11 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri /* Copy request(s) to the ring page. */ *final_ring_req = *ring_req; - if (unlikely(require_extra_req)) + rinfo->shadow[id].status = REQ_WAITING; + if (unlikely(require_extra_req)) { *final_extra_ring_req = *extra_ring_req; + rinfo->shadow[extra_id].status = REQ_WAITING; + } if (new_persistent_gnts) gnttab_free_grant_references(setup.gref_head); @@ -1413,8 +1419,8 @@ static enum blk_req_status blkif_rsp_to_req_status(int rsp) static int blkif_get_final_status(enum blk_req_status s1, enum blk_req_status s2) { - BUG_ON(s1 == REQ_WAITING); - BUG_ON(s2 == REQ_WAITING); + BUG_ON(s1 < REQ_DONE); + BUG_ON(s2 < REQ_DONE); if (s1 == REQ_ERROR || s2 == REQ_ERROR) return BLKIF_RSP_ERROR; @@ -1447,7 +1453,7 @@ static bool blkif_completion(unsigned long *id, s->status = blkif_rsp_to_req_status(bret->status); /* Wait the second response if not yet here. */ - if (s2->status == REQ_WAITING) + if (s2->status < REQ_DONE) return 0; bret->status = blkif_get_final_status(s->status, @@ -1566,11 +1572,17 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) spin_lock_irqsave(&rinfo->ring_lock, flags); again: - rp = rinfo->ring.sring->rsp_prod; - rmb(); /* Ensure we see queued responses up to 'rp'. */ + rp = READ_ONCE(rinfo->ring.sring->rsp_prod); + virt_rmb(); /* Ensure we see queued responses up to 'rp'. */ + if (RING_RESPONSE_PROD_OVERFLOW(&rinfo->ring, rp)) { + pr_alert("%s: illegal number of responses %u\n", + info->gd->disk_name, rp - rinfo->ring.rsp_cons); + goto err; + } for (i = rinfo->ring.rsp_cons; i != rp; i++) { unsigned long id; + unsigned int op; RING_COPY_RESPONSE(&rinfo->ring, i, &bret); id = bret.id; @@ -1581,14 +1593,28 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) * look in get_id_from_freelist. */ if (id >= BLK_RING_SIZE(info)) { - WARN(1, "%s: response to %s has incorrect id (%ld)\n", - info->gd->disk_name, op_name(bret.operation), id); - /* We can't safely get the 'struct request' as - * the id is busted. */ - continue; + pr_alert("%s: response has incorrect id (%ld)\n", + info->gd->disk_name, id); + goto err; } + if (rinfo->shadow[id].status != REQ_WAITING) { + pr_alert("%s: response references no pending request\n", + info->gd->disk_name); + goto err; + } + + rinfo->shadow[id].status = REQ_PROCESSING; req = rinfo->shadow[id].request; + op = rinfo->shadow[id].req.operation; + if (op == BLKIF_OP_INDIRECT) + op = rinfo->shadow[id].req.u.indirect.indirect_op; + if (bret.operation != op) { + pr_alert("%s: response has wrong operation (%u instead of %u)\n", + info->gd->disk_name, bret.operation, op); + goto err; + } + if (bret.operation != BLKIF_OP_DISCARD) { /* * We may need to wait for an extra response if the @@ -1613,7 +1639,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) case BLKIF_OP_DISCARD: if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) { struct request_queue *rq = info->rq; - printk(KERN_WARNING "blkfront: %s: %s op failed\n", + + pr_warn_ratelimited("blkfront: %s: %s op failed\n", info->gd->disk_name, op_name(bret.operation)); blkif_req(req)->error = BLK_STS_NOTSUPP; info->feature_discard = 0; @@ -1625,13 +1652,13 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) case BLKIF_OP_FLUSH_DISKCACHE: case BLKIF_OP_WRITE_BARRIER: if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) { - printk(KERN_WARNING "blkfront: %s: %s op failed\n", + pr_warn_ratelimited("blkfront: %s: %s op failed\n", info->gd->disk_name, op_name(bret.operation)); blkif_req(req)->error = BLK_STS_NOTSUPP; } if (unlikely(bret.status == BLKIF_RSP_ERROR && rinfo->shadow[id].req.u.rw.nr_segments == 0)) { - printk(KERN_WARNING "blkfront: %s: empty %s op failed\n", + pr_warn_ratelimited("blkfront: %s: empty %s op failed\n", info->gd->disk_name, op_name(bret.operation)); blkif_req(req)->error = BLK_STS_NOTSUPP; } @@ -1646,8 +1673,9 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) case BLKIF_OP_READ: case BLKIF_OP_WRITE: if (unlikely(bret.status != BLKIF_RSP_OKAY)) - dev_dbg(&info->xbdev->dev, "Bad return from blkdev data " - "request: %x\n", bret.status); + dev_dbg_ratelimited(&info->xbdev->dev, + "Bad return from blkdev data request: %#x\n", + bret.status); break; default: @@ -1672,6 +1700,14 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) spin_unlock_irqrestore(&rinfo->ring_lock, flags); return IRQ_HANDLED; + + err: + info->connected = BLKIF_STATE_ERROR; + + spin_unlock_irqrestore(&rinfo->ring_lock, flags); + + pr_alert("%s disabled for further use\n", info->gd->disk_name); + return IRQ_HANDLED; } From 0ae52bcd3ec46c24c9a222edc5da6be4158cb7b5 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 29 Nov 2021 12:22:53 +0100 Subject: [PATCH 064/277] xen/netfront: read response from backend only once commit 8446066bf8c1f9f7b7412c43fbea0fb87464d75b upstream. In order to avoid problems in case the backend is modifying a response on the ring page while the frontend has already seen it, just read the response into a local buffer in one go and then operate on that buffer only. Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/xen-netfront.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 89e6a50b53da..dfb019325b08 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -389,13 +389,13 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) rmb(); /* Ensure we see responses up to 'rp'. */ for (cons = queue->tx.rsp_cons; cons != prod; cons++) { - struct xen_netif_tx_response *txrsp; + struct xen_netif_tx_response txrsp; - txrsp = RING_GET_RESPONSE(&queue->tx, cons); - if (txrsp->status == XEN_NETIF_RSP_NULL) + RING_COPY_RESPONSE(&queue->tx, cons, &txrsp); + if (txrsp.status == XEN_NETIF_RSP_NULL) continue; - id = txrsp->id; + id = txrsp.id; skb = queue->tx_skbs[id].skb; if (unlikely(gnttab_query_foreign_access( queue->grant_tx_ref[id]) != 0)) { @@ -743,7 +743,7 @@ static int xennet_get_extras(struct netfront_queue *queue, RING_IDX rp) { - struct xen_netif_extra_info *extra; + struct xen_netif_extra_info extra; struct device *dev = &queue->info->netdev->dev; RING_IDX cons = queue->rx.rsp_cons; int err = 0; @@ -759,24 +759,22 @@ static int xennet_get_extras(struct netfront_queue *queue, break; } - extra = (struct xen_netif_extra_info *) - RING_GET_RESPONSE(&queue->rx, ++cons); + RING_COPY_RESPONSE(&queue->rx, ++cons, &extra); - if (unlikely(!extra->type || - extra->type >= XEN_NETIF_EXTRA_TYPE_MAX)) { + if (unlikely(!extra.type || + extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) { if (net_ratelimit()) dev_warn(dev, "Invalid extra type: %d\n", - extra->type); + extra.type); err = -EINVAL; } else { - memcpy(&extras[extra->type - 1], extra, - sizeof(*extra)); + extras[extra.type - 1] = extra; } skb = xennet_get_rx_skb(queue, cons); ref = xennet_get_rx_ref(queue, cons); xennet_move_rx_slot(queue, skb, ref); - } while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE); + } while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE); queue->rx.rsp_cons = cons; return err; @@ -786,7 +784,7 @@ static int xennet_get_responses(struct netfront_queue *queue, struct netfront_rx_info *rinfo, RING_IDX rp, struct sk_buff_head *list) { - struct xen_netif_rx_response *rx = &rinfo->rx; + struct xen_netif_rx_response *rx = &rinfo->rx, rx_local; struct xen_netif_extra_info *extras = rinfo->extras; struct device *dev = &queue->info->netdev->dev; RING_IDX cons = queue->rx.rsp_cons; @@ -844,7 +842,8 @@ next: break; } - rx = RING_GET_RESPONSE(&queue->rx, cons + slots); + RING_COPY_RESPONSE(&queue->rx, cons + slots, &rx_local); + rx = &rx_local; skb = xennet_get_rx_skb(queue, cons + slots); ref = xennet_get_rx_ref(queue, cons + slots); slots++; @@ -899,10 +898,11 @@ static int xennet_fill_frags(struct netfront_queue *queue, struct sk_buff *nskb; while ((nskb = __skb_dequeue(list))) { - struct xen_netif_rx_response *rx = - RING_GET_RESPONSE(&queue->rx, ++cons); + struct xen_netif_rx_response rx; skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0]; + RING_COPY_RESPONSE(&queue->rx, ++cons, &rx); + if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) { unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to; @@ -917,7 +917,7 @@ static int xennet_fill_frags(struct netfront_queue *queue, skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, skb_frag_page(nfrag), - rx->offset, rx->status, PAGE_SIZE); + rx.offset, rx.status, PAGE_SIZE); skb_shinfo(nskb)->nr_frags = 0; kfree_skb(nskb); @@ -1015,7 +1015,7 @@ static int xennet_poll(struct napi_struct *napi, int budget) i = queue->rx.rsp_cons; work_done = 0; while ((i != rp) && (work_done < budget)) { - memcpy(rx, RING_GET_RESPONSE(&queue->rx, i), sizeof(*rx)); + RING_COPY_RESPONSE(&queue->rx, i, rx); memset(extras, 0, sizeof(rinfo.extras)); err = xennet_get_responses(queue, &rinfo, rp, &tmpq); From c010e30c398a5e73600bc40b006dc9d924ef3495 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 29 Nov 2021 12:23:51 +0100 Subject: [PATCH 065/277] xen/netfront: don't read data from request on the ring page commit 162081ec33c2686afa29d91bf8d302824aa846c7 upstream. In order to avoid a malicious backend being able to influence the local processing of a request build the request locally first and then copy it to the ring page. Any reading from the request influencing the processing in the frontend needs to be done on the local instance. Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/xen-netfront.c | 80 ++++++++++++++++++-------------------- 1 file changed, 37 insertions(+), 43 deletions(-) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index dfb019325b08..091f2b82a3bd 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -425,7 +425,8 @@ struct xennet_gnttab_make_txreq { struct netfront_queue *queue; struct sk_buff *skb; struct page *page; - struct xen_netif_tx_request *tx; /* Last request */ + struct xen_netif_tx_request *tx; /* Last request on ring page */ + struct xen_netif_tx_request tx_local; /* Last request local copy*/ unsigned int size; }; @@ -453,30 +454,27 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset, queue->grant_tx_page[id] = page; queue->grant_tx_ref[id] = ref; - tx->id = id; - tx->gref = ref; - tx->offset = offset; - tx->size = len; - tx->flags = 0; + info->tx_local.id = id; + info->tx_local.gref = ref; + info->tx_local.offset = offset; + info->tx_local.size = len; + info->tx_local.flags = 0; + + *tx = info->tx_local; info->tx = tx; - info->size += tx->size; + info->size += info->tx_local.size; } static struct xen_netif_tx_request *xennet_make_first_txreq( - struct netfront_queue *queue, struct sk_buff *skb, - struct page *page, unsigned int offset, unsigned int len) + struct xennet_gnttab_make_txreq *info, + unsigned int offset, unsigned int len) { - struct xennet_gnttab_make_txreq info = { - .queue = queue, - .skb = skb, - .page = page, - .size = 0, - }; + info->size = 0; - gnttab_for_one_grant(page, offset, len, xennet_tx_setup_grant, &info); + gnttab_for_one_grant(info->page, offset, len, xennet_tx_setup_grant, info); - return info.tx; + return info->tx; } static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset, @@ -489,35 +487,27 @@ static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset, xennet_tx_setup_grant(gfn, offset, len, data); } -static struct xen_netif_tx_request *xennet_make_txreqs( - struct netfront_queue *queue, struct xen_netif_tx_request *tx, - struct sk_buff *skb, struct page *page, +static void xennet_make_txreqs( + struct xennet_gnttab_make_txreq *info, + struct page *page, unsigned int offset, unsigned int len) { - struct xennet_gnttab_make_txreq info = { - .queue = queue, - .skb = skb, - .tx = tx, - }; - /* Skip unused frames from start of page */ page += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; while (len) { - info.page = page; - info.size = 0; + info->page = page; + info->size = 0; gnttab_foreach_grant_in_range(page, offset, len, xennet_make_one_txreq, - &info); + info); page++; offset = 0; - len -= info.size; + len -= info->size; } - - return info.tx; } /* @@ -570,7 +560,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats); - struct xen_netif_tx_request *tx, *first_tx; + struct xen_netif_tx_request *first_tx; unsigned int i; int notify; int slots; @@ -579,6 +569,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int len; unsigned long flags; struct netfront_queue *queue = NULL; + struct xennet_gnttab_make_txreq info = { }; unsigned int num_queues = dev->real_num_tx_queues; u16 queue_index; struct sk_buff *nskb; @@ -636,21 +627,24 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) } /* First request for the linear area. */ - first_tx = tx = xennet_make_first_txreq(queue, skb, - page, offset, len); - offset += tx->size; + info.queue = queue; + info.skb = skb; + info.page = page; + first_tx = xennet_make_first_txreq(&info, offset, len); + offset += info.tx_local.size; if (offset == PAGE_SIZE) { page++; offset = 0; } - len -= tx->size; + len -= info.tx_local.size; if (skb->ip_summed == CHECKSUM_PARTIAL) /* local packet? */ - tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated; + first_tx->flags |= XEN_NETTXF_csum_blank | + XEN_NETTXF_data_validated; else if (skb->ip_summed == CHECKSUM_UNNECESSARY) /* remote but checksummed. */ - tx->flags |= XEN_NETTXF_data_validated; + first_tx->flags |= XEN_NETTXF_data_validated; /* Optional extra info after the first request. */ if (skb_shinfo(skb)->gso_size) { @@ -659,7 +653,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) gso = (struct xen_netif_extra_info *) RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++); - tx->flags |= XEN_NETTXF_extra_info; + first_tx->flags |= XEN_NETTXF_extra_info; gso->u.gso.size = skb_shinfo(skb)->gso_size; gso->u.gso.type = (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) ? @@ -673,13 +667,13 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) } /* Requests for the rest of the linear area. */ - tx = xennet_make_txreqs(queue, tx, skb, page, offset, len); + xennet_make_txreqs(&info, page, offset, len); /* Requests for all the frags. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - tx = xennet_make_txreqs(queue, tx, skb, - skb_frag_page(frag), frag->page_offset, + xennet_make_txreqs(&info, skb_frag_page(frag), + frag->page_offset, skb_frag_size(frag)); } From 82ab9e01d4158e128cece4ab3c6b04ba436c7b28 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 29 Nov 2021 12:24:32 +0100 Subject: [PATCH 066/277] xen/netfront: disentangle tx_skb_freelist commit 21631d2d741a64a073e167c27769e73bc7844a2f upstream. The tx_skb_freelist elements are in a single linked list with the request id used as link reference. The per element link field is in a union with the skb pointer of an in use request. Move the link reference out of the union in order to enable a later reuse of it for requests which need a populated skb pointer. Rename add_id_to_freelist() and get_id_from_freelist() to add_id_to_list() and get_id_from_list() in order to prepare using those for other lists as well. Define ~0 as value to indicate the end of a list and place that value into the link for a request not being on the list. When freeing a skb zero the skb pointer in the request. Use a NULL value of the skb pointer instead of skb_entry_is_link() for deciding whether a request has a skb linked to it. Remove skb_entry_set_link() and open code it instead as it is really trivial now. Signed-off-by: Juergen Gross Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/xen-netfront.c | 61 ++++++++++++++++---------------------- 1 file changed, 25 insertions(+), 36 deletions(-) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 091f2b82a3bd..9b42f8dcae9f 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -121,17 +121,11 @@ struct netfront_queue { /* * {tx,rx}_skbs store outstanding skbuffs. Free tx_skb entries - * are linked from tx_skb_freelist through skb_entry.link. - * - * NB. Freelist index entries are always going to be less than - * PAGE_OFFSET, whereas pointers to skbs will always be equal or - * greater than PAGE_OFFSET: we use this property to distinguish - * them. + * are linked from tx_skb_freelist through tx_link. */ - union skb_entry { - struct sk_buff *skb; - unsigned long link; - } tx_skbs[NET_TX_RING_SIZE]; + struct sk_buff *tx_skbs[NET_TX_RING_SIZE]; + unsigned short tx_link[NET_TX_RING_SIZE]; +#define TX_LINK_NONE 0xffff grant_ref_t gref_tx_head; grant_ref_t grant_tx_ref[NET_TX_RING_SIZE]; struct page *grant_tx_page[NET_TX_RING_SIZE]; @@ -169,33 +163,25 @@ struct netfront_rx_info { struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1]; }; -static void skb_entry_set_link(union skb_entry *list, unsigned short id) -{ - list->link = id; -} - -static int skb_entry_is_link(const union skb_entry *list) -{ - BUILD_BUG_ON(sizeof(list->skb) != sizeof(list->link)); - return (unsigned long)list->skb < PAGE_OFFSET; -} - /* * Access macros for acquiring freeing slots in tx_skbs[]. */ -static void add_id_to_freelist(unsigned *head, union skb_entry *list, - unsigned short id) +static void add_id_to_list(unsigned *head, unsigned short *list, + unsigned short id) { - skb_entry_set_link(&list[id], *head); + list[id] = *head; *head = id; } -static unsigned short get_id_from_freelist(unsigned *head, - union skb_entry *list) +static unsigned short get_id_from_list(unsigned *head, unsigned short *list) { unsigned int id = *head; - *head = list[id].link; + + if (id != TX_LINK_NONE) { + *head = list[id]; + list[id] = TX_LINK_NONE; + } return id; } @@ -396,7 +382,8 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) continue; id = txrsp.id; - skb = queue->tx_skbs[id].skb; + skb = queue->tx_skbs[id]; + queue->tx_skbs[id] = NULL; if (unlikely(gnttab_query_foreign_access( queue->grant_tx_ref[id]) != 0)) { pr_alert("%s: warning -- grant still in use by backend domain\n", @@ -409,7 +396,7 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) &queue->gref_tx_head, queue->grant_tx_ref[id]); queue->grant_tx_ref[id] = GRANT_INVALID_REF; queue->grant_tx_page[id] = NULL; - add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, id); + add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, id); dev_kfree_skb_irq(skb); } @@ -442,7 +429,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset, struct netfront_queue *queue = info->queue; struct sk_buff *skb = info->skb; - id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs); + id = get_id_from_list(&queue->tx_skb_freelist, queue->tx_link); tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++); ref = gnttab_claim_grant_reference(&queue->gref_tx_head); WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref)); @@ -450,7 +437,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset, gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id, gfn, GNTMAP_readonly); - queue->tx_skbs[id].skb = skb; + queue->tx_skbs[id] = skb; queue->grant_tx_page[id] = page; queue->grant_tx_ref[id] = ref; @@ -1131,17 +1118,18 @@ static void xennet_release_tx_bufs(struct netfront_queue *queue) for (i = 0; i < NET_TX_RING_SIZE; i++) { /* Skip over entries which are actually freelist references */ - if (skb_entry_is_link(&queue->tx_skbs[i])) + if (!queue->tx_skbs[i]) continue; - skb = queue->tx_skbs[i].skb; + skb = queue->tx_skbs[i]; + queue->tx_skbs[i] = NULL; get_page(queue->grant_tx_page[i]); gnttab_end_foreign_access(queue->grant_tx_ref[i], GNTMAP_readonly, (unsigned long)page_address(queue->grant_tx_page[i])); queue->grant_tx_page[i] = NULL; queue->grant_tx_ref[i] = GRANT_INVALID_REF; - add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, i); + add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, i); dev_kfree_skb_irq(skb); } } @@ -1624,13 +1612,14 @@ static int xennet_init_queue(struct netfront_queue *queue) snprintf(queue->name, sizeof(queue->name), "vif%s-q%u", devid, queue->id); - /* Initialise tx_skbs as a free chain containing every entry. */ + /* Initialise tx_skb_freelist as a free chain containing every entry. */ queue->tx_skb_freelist = 0; for (i = 0; i < NET_TX_RING_SIZE; i++) { - skb_entry_set_link(&queue->tx_skbs[i], i+1); + queue->tx_link[i] = i + 1; queue->grant_tx_ref[i] = GRANT_INVALID_REF; queue->grant_tx_page[i] = NULL; } + queue->tx_link[NET_TX_RING_SIZE - 1] = TX_LINK_NONE; /* Clear out rx_skbs */ for (i = 0; i < NET_RX_RING_SIZE; i++) { From db954a52438db8d8d3c7431c6ebd37f6aa771f63 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 29 Nov 2021 12:25:17 +0100 Subject: [PATCH 067/277] xen/netfront: don't trust the backend response data blindly commit a884daa61a7d91650987e855464526aef219590f upstream. Today netfront will trust the backend to send only sane response data. In order to avoid privilege escalations or crashes in case of malicious backends verify the data to be within expected limits. Especially make sure that the response always references an outstanding request. Note that only the tx queue needs special id handling, as for the rx queue the id is equal to the index in the ring page. Introduce a new indicator for the device whether it is broken and let the device stop working when it is set. Set this indicator in case the backend sets any weird data. Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/xen-netfront.c | 80 +++++++++++++++++++++++++++++++++++--- 1 file changed, 75 insertions(+), 5 deletions(-) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 9b42f8dcae9f..ef7dd70a40a1 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -126,10 +126,12 @@ struct netfront_queue { struct sk_buff *tx_skbs[NET_TX_RING_SIZE]; unsigned short tx_link[NET_TX_RING_SIZE]; #define TX_LINK_NONE 0xffff +#define TX_PENDING 0xfffe grant_ref_t gref_tx_head; grant_ref_t grant_tx_ref[NET_TX_RING_SIZE]; struct page *grant_tx_page[NET_TX_RING_SIZE]; unsigned tx_skb_freelist; + unsigned int tx_pend_queue; spinlock_t rx_lock ____cacheline_aligned_in_smp; struct xen_netif_rx_front_ring rx; @@ -155,6 +157,9 @@ struct netfront_info { struct netfront_stats __percpu *rx_stats; struct netfront_stats __percpu *tx_stats; + /* Is device behaving sane? */ + bool broken; + atomic_t rx_gso_checksum_fixup; }; @@ -339,7 +344,7 @@ static int xennet_open(struct net_device *dev) unsigned int i = 0; struct netfront_queue *queue = NULL; - if (!np->queues) + if (!np->queues || np->broken) return -ENODEV; for (i = 0; i < num_queues; ++i) { @@ -367,11 +372,17 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) unsigned short id; struct sk_buff *skb; bool more_to_do; + const struct device *dev = &queue->info->netdev->dev; BUG_ON(!netif_carrier_ok(queue->info->netdev)); do { prod = queue->tx.sring->rsp_prod; + if (RING_RESPONSE_PROD_OVERFLOW(&queue->tx, prod)) { + dev_alert(dev, "Illegal number of responses %u\n", + prod - queue->tx.rsp_cons); + goto err; + } rmb(); /* Ensure we see responses up to 'rp'. */ for (cons = queue->tx.rsp_cons; cons != prod; cons++) { @@ -381,14 +392,27 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) if (txrsp.status == XEN_NETIF_RSP_NULL) continue; - id = txrsp.id; + id = txrsp.id; + if (id >= RING_SIZE(&queue->tx)) { + dev_alert(dev, + "Response has incorrect id (%u)\n", + id); + goto err; + } + if (queue->tx_link[id] != TX_PENDING) { + dev_alert(dev, + "Response for inactive request\n"); + goto err; + } + + queue->tx_link[id] = TX_LINK_NONE; skb = queue->tx_skbs[id]; queue->tx_skbs[id] = NULL; if (unlikely(gnttab_query_foreign_access( queue->grant_tx_ref[id]) != 0)) { - pr_alert("%s: warning -- grant still in use by backend domain\n", - __func__); - BUG(); + dev_alert(dev, + "Grant still in use by backend domain\n"); + goto err; } gnttab_end_foreign_access_ref( queue->grant_tx_ref[id], GNTMAP_readonly); @@ -406,6 +430,12 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) } while (more_to_do); xennet_maybe_wake_tx(queue); + + return; + + err: + queue->info->broken = true; + dev_alert(dev, "Disabled for further use\n"); } struct xennet_gnttab_make_txreq { @@ -449,6 +479,12 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset, *tx = info->tx_local; + /* + * Put the request in the pending queue, it will be set to be pending + * when the producer index is about to be raised. + */ + add_id_to_list(&queue->tx_pend_queue, queue->tx_link, id); + info->tx = tx; info->size += info->tx_local.size; } @@ -541,6 +577,15 @@ static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb, return queue_idx; } +static void xennet_mark_tx_pending(struct netfront_queue *queue) +{ + unsigned int i; + + while ((i = get_id_from_list(&queue->tx_pend_queue, queue->tx_link)) != + TX_LINK_NONE) + queue->tx_link[i] = TX_PENDING; +} + #define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1) static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) @@ -564,6 +609,8 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) /* Drop the packet if no queues are set up */ if (num_queues < 1) goto drop; + if (unlikely(np->broken)) + goto drop; /* Determine which queue to transmit this SKB on */ queue_index = skb_get_queue_mapping(skb); queue = &np->queues[queue_index]; @@ -667,6 +714,8 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) /* First request has the packet length. */ first_tx->size = skb->len; + xennet_mark_tx_pending(queue); + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify); if (notify) notify_remote_via_irq(queue->tx_irq); @@ -991,6 +1040,13 @@ static int xennet_poll(struct napi_struct *napi, int budget) skb_queue_head_init(&tmpq); rp = queue->rx.sring->rsp_prod; + if (RING_RESPONSE_PROD_OVERFLOW(&queue->rx, rp)) { + dev_alert(&dev->dev, "Illegal number of responses %u\n", + rp - queue->rx.rsp_cons); + queue->info->broken = true; + spin_unlock(&queue->rx_lock); + return 0; + } rmb(); /* Ensure we see queued responses up to 'rp'. */ i = queue->rx.rsp_cons; @@ -1209,6 +1265,9 @@ static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id) struct netfront_queue *queue = dev_id; unsigned long flags; + if (queue->info->broken) + return IRQ_HANDLED; + spin_lock_irqsave(&queue->tx_lock, flags); xennet_tx_buf_gc(queue); spin_unlock_irqrestore(&queue->tx_lock, flags); @@ -1221,6 +1280,9 @@ static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id) struct netfront_queue *queue = dev_id; struct net_device *dev = queue->info->netdev; + if (queue->info->broken) + return IRQ_HANDLED; + if (likely(netif_carrier_ok(dev) && RING_HAS_UNCONSUMED_RESPONSES(&queue->rx))) napi_schedule(&queue->napi); @@ -1242,6 +1304,10 @@ static void xennet_poll_controller(struct net_device *dev) struct netfront_info *info = netdev_priv(dev); unsigned int num_queues = dev->real_num_tx_queues; unsigned int i; + + if (info->broken) + return; + for (i = 0; i < num_queues; ++i) xennet_interrupt(0, &info->queues[i]); } @@ -1614,6 +1680,7 @@ static int xennet_init_queue(struct netfront_queue *queue) /* Initialise tx_skb_freelist as a free chain containing every entry. */ queue->tx_skb_freelist = 0; + queue->tx_pend_queue = TX_LINK_NONE; for (i = 0; i < NET_TX_RING_SIZE; i++) { queue->tx_link[i] = i + 1; queue->grant_tx_ref[i] = GRANT_INVALID_REF; @@ -1824,6 +1891,9 @@ static int talk_to_netback(struct xenbus_device *dev, if (info->queues) xennet_destroy_queues(info); + /* For the case of a reconnect reset the "broken" indicator. */ + info->broken = false; + err = xennet_create_queues(info, &num_queues); if (err < 0) { xenbus_dev_fatal(dev, err, "creating queues"); From 875475219ef95135e212f5fb902246cefa9fee15 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 29 Nov 2021 12:25:57 +0100 Subject: [PATCH 068/277] tty: hvc: replace BUG_ON() with negative return value commit e679004dec37566f658a255157d3aed9d762a2b7 upstream. Xen frontends shouldn't BUG() in case of illegal data received from their backends. So replace the BUG_ON()s when reading illegal data from the ring page with negative return values. Reviewed-by: Jan Beulich Signed-off-by: Juergen Gross Link: https://lore.kernel.org/r/20210707091045.460-1-jgross@suse.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/hvc/hvc_xen.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 5e87e4866bcb..858c7b4b197c 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -99,7 +99,11 @@ static int __write_console(struct xencons_info *xencons, cons = intf->out_cons; prod = intf->out_prod; mb(); /* update queue values before going on */ - BUG_ON((prod - cons) > sizeof(intf->out)); + + if ((prod - cons) > sizeof(intf->out)) { + pr_err_once("xencons: Illegal ring page indices"); + return -EINVAL; + } while ((sent < len) && ((prod - cons) < sizeof(intf->out))) intf->out[MASK_XENCONS_IDX(prod++, intf->out)] = data[sent++]; @@ -127,7 +131,10 @@ static int domU_write_console(uint32_t vtermno, const char *data, int len) */ while (len) { int sent = __write_console(cons, data, len); - + + if (sent < 0) + return sent; + data += sent; len -= sent; @@ -151,7 +158,11 @@ static int domU_read_console(uint32_t vtermno, char *buf, int len) cons = intf->in_cons; prod = intf->in_prod; mb(); /* get pointers before reading ring */ - BUG_ON((prod - cons) > sizeof(intf->in)); + + if ((prod - cons) > sizeof(intf->in)) { + pr_err_once("xencons: Illegal ring page indices"); + return -EINVAL; + } while (cons != prod && recv < len) buf[recv++] = intf->in[MASK_XENCONS_IDX(cons++, intf->in)]; From 8619236d939f19fc8e177b17e8365a3ff16f9b0e Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Fri, 19 Nov 2021 16:43:21 -0800 Subject: [PATCH 069/277] shm: extend forced shm destroy to support objects from several IPC nses commit 85b6d24646e4125c591639841169baa98a2da503 upstream. Currently, the exit_shm() function not designed to work properly when task->sysvshm.shm_clist holds shm objects from different IPC namespaces. This is a real pain when sysctl kernel.shm_rmid_forced = 1, because it leads to use-after-free (reproducer exists). This is an attempt to fix the problem by extending exit_shm mechanism to handle shm's destroy from several IPC ns'es. To achieve that we do several things: 1. add a namespace (non-refcounted) pointer to the struct shmid_kernel 2. during new shm object creation (newseg()/shmget syscall) we initialize this pointer by current task IPC ns 3. exit_shm() fully reworked such that it traverses over all shp's in task->sysvshm.shm_clist and gets IPC namespace not from current task as it was before but from shp's object itself, then call shm_destroy(shp, ns). Note: We need to be really careful here, because as it was said before (1), our pointer to IPC ns non-refcnt'ed. To be on the safe side we using special helper get_ipc_ns_not_zero() which allows to get IPC ns refcounter only if IPC ns not in the "state of destruction". Q/A Q: Why can we access shp->ns memory using non-refcounted pointer? A: Because shp object lifetime is always shorther than IPC namespace lifetime, so, if we get shp object from the task->sysvshm.shm_clist while holding task_lock(task) nobody can steal our namespace. Q: Does this patch change semantics of unshare/setns/clone syscalls? A: No. It's just fixes non-covered case when process may leave IPC namespace without getting task->sysvshm.shm_clist list cleaned up. Link: https://lkml.kernel.org/r/67bb03e5-f79c-1815-e2bf-949c67047418@colorfullife.com Link: https://lkml.kernel.org/r/20211109151501.4921-1-manfred@colorfullife.com Fixes: ab602f79915 ("shm: make exit_shm work proportional to task activity") Co-developed-by: Manfred Spraul Signed-off-by: Manfred Spraul Signed-off-by: Alexander Mikhalitsyn Cc: "Eric W. Biederman" Cc: Davidlohr Bueso Cc: Greg KH Cc: Andrei Vagin Cc: Pavel Tikhomirov Cc: Vasily Averin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/ipc_namespace.h | 15 +++ include/linux/sched/task.h | 2 +- include/linux/shm.h | 13 ++- ipc/shm.c | 184 +++++++++++++++++++++++++--------- 4 files changed, 163 insertions(+), 51 deletions(-) diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 474812abe773..e661765271ea 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -127,6 +127,16 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) return ns; } +static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) +{ + if (ns) { + if (refcount_inc_not_zero(&ns->count)) + return ns; + } + + return NULL; +} + extern void put_ipc_ns(struct ipc_namespace *ns); #else static inline struct ipc_namespace *copy_ipcs(unsigned long flags, @@ -143,6 +153,11 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) return ns; } +static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) +{ + return ns; +} + static inline void put_ipc_ns(struct ipc_namespace *ns) { } diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 11b4fba82950..c3d157a37073 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -122,7 +122,7 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and - * ->cgroup.subsys[]. And ->vfork_done. + * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), diff --git a/include/linux/shm.h b/include/linux/shm.h index 2bbafacfbfc9..3ef303df784e 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -20,9 +20,18 @@ struct shmid_kernel /* private to the kernel */ pid_t shm_lprid; struct user_struct *mlock_user; - /* The task created the shm object. NULL if the task is dead. */ + /* + * The task created the shm object, for + * task_lock(shp->shm_creator) + */ struct task_struct *shm_creator; - struct list_head shm_clist; /* list by creator */ + + /* + * List by creator. task_lock(->shm_creator) required for read/write. + * If list_empty(), then the creator is dead already. + */ + struct list_head shm_clist; + struct ipc_namespace *ns; } __randomize_layout; /* shm_mode upper byte flags */ diff --git a/ipc/shm.c b/ipc/shm.c index 44cca2529a95..d3cebe4e23e3 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -92,6 +92,7 @@ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); + WARN_ON(ns != shp->ns); if (shp->shm_nattch) { shp->shm_perm.mode |= SHM_DEST; @@ -185,10 +186,43 @@ static void shm_rcu_free(struct rcu_head *head) kvfree(shp); } -static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) +/* + * It has to be called with shp locked. + * It must be called before ipc_rmid() + */ +static inline void shm_clist_rm(struct shmid_kernel *shp) { - list_del(&s->shm_clist); - ipc_rmid(&shm_ids(ns), &s->shm_perm); + struct task_struct *creator; + + /* ensure that shm_creator does not disappear */ + rcu_read_lock(); + + /* + * A concurrent exit_shm may do a list_del_init() as well. + * Just do nothing if exit_shm already did the work + */ + if (!list_empty(&shp->shm_clist)) { + /* + * shp->shm_creator is guaranteed to be valid *only* + * if shp->shm_clist is not empty. + */ + creator = shp->shm_creator; + + task_lock(creator); + /* + * list_del_init() is a nop if the entry was already removed + * from the list. + */ + list_del_init(&shp->shm_clist); + task_unlock(creator); + } + rcu_read_unlock(); +} + +static inline void shm_rmid(struct shmid_kernel *s) +{ + shm_clist_rm(s); + ipc_rmid(&shm_ids(s->ns), &s->shm_perm); } @@ -243,7 +277,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) shm_file = shp->shm_file; shp->shm_file = NULL; ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; - shm_rmid(ns, shp); + shm_rmid(shp); shm_unlock(shp); if (!is_file_hugepages(shm_file)) shmem_lock(shm_file, 0, shp->mlock_user); @@ -264,10 +298,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) * * 2) sysctl kernel.shm_rmid_forced is set to 1. */ -static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) +static bool shm_may_destroy(struct shmid_kernel *shp) { return (shp->shm_nattch == 0) && - (ns->shm_rmid_forced || + (shp->ns->shm_rmid_forced || (shp->shm_perm.mode & SHM_DEST)); } @@ -298,7 +332,7 @@ static void shm_close(struct vm_area_struct *vma) shp->shm_lprid = task_tgid_vnr(current); shp->shm_dtim = ktime_get_real_seconds(); shp->shm_nattch--; - if (shm_may_destroy(ns, shp)) + if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); @@ -319,10 +353,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data) * * As shp->* are changed under rwsem, it's safe to skip shp locking. */ - if (shp->shm_creator != NULL) + if (!list_empty(&shp->shm_clist)) return 0; - if (shm_may_destroy(ns, shp)) { + if (shm_may_destroy(shp)) { shm_lock_by_ptr(shp); shm_destroy(ns, shp); } @@ -340,48 +374,97 @@ void shm_destroy_orphaned(struct ipc_namespace *ns) /* Locking assumes this will only be called with task == current */ void exit_shm(struct task_struct *task) { - struct ipc_namespace *ns = task->nsproxy->ipc_ns; - struct shmid_kernel *shp, *n; + for (;;) { + struct shmid_kernel *shp; + struct ipc_namespace *ns; - if (list_empty(&task->sysvshm.shm_clist)) - return; + task_lock(task); - /* - * If kernel.shm_rmid_forced is not set then only keep track of - * which shmids are orphaned, so that a later set of the sysctl - * can clean them up. - */ - if (!ns->shm_rmid_forced) { - down_read(&shm_ids(ns).rwsem); - list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist) - shp->shm_creator = NULL; - /* - * Only under read lock but we are only called on current - * so no entry on the list will be shared. - */ - list_del(&task->sysvshm.shm_clist); - up_read(&shm_ids(ns).rwsem); - return; - } - - /* - * Destroy all already created segments, that were not yet mapped, - * and mark any mapped as orphan to cover the sysctl toggling. - * Destroy is skipped if shm_may_destroy() returns false. - */ - down_write(&shm_ids(ns).rwsem); - list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) { - shp->shm_creator = NULL; - - if (shm_may_destroy(ns, shp)) { - shm_lock_by_ptr(shp); - shm_destroy(ns, shp); + if (list_empty(&task->sysvshm.shm_clist)) { + task_unlock(task); + break; } - } - /* Remove the list head from any segments still attached. */ - list_del(&task->sysvshm.shm_clist); - up_write(&shm_ids(ns).rwsem); + shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel, + shm_clist); + + /* + * 1) Get pointer to the ipc namespace. It is worth to say + * that this pointer is guaranteed to be valid because + * shp lifetime is always shorter than namespace lifetime + * in which shp lives. + * We taken task_lock it means that shp won't be freed. + */ + ns = shp->ns; + + /* + * 2) If kernel.shm_rmid_forced is not set then only keep track of + * which shmids are orphaned, so that a later set of the sysctl + * can clean them up. + */ + if (!ns->shm_rmid_forced) + goto unlink_continue; + + /* + * 3) get a reference to the namespace. + * The refcount could be already 0. If it is 0, then + * the shm objects will be free by free_ipc_work(). + */ + ns = get_ipc_ns_not_zero(ns); + if (!ns) { +unlink_continue: + list_del_init(&shp->shm_clist); + task_unlock(task); + continue; + } + + /* + * 4) get a reference to shp. + * This cannot fail: shm_clist_rm() is called before + * ipc_rmid(), thus the refcount cannot be 0. + */ + WARN_ON(!ipc_rcu_getref(&shp->shm_perm)); + + /* + * 5) unlink the shm segment from the list of segments + * created by current. + * This must be done last. After unlinking, + * only the refcounts obtained above prevent IPC_RMID + * from destroying the segment or the namespace. + */ + list_del_init(&shp->shm_clist); + + task_unlock(task); + + /* + * 6) we have all references + * Thus lock & if needed destroy shp. + */ + down_write(&shm_ids(ns).rwsem); + shm_lock_by_ptr(shp); + /* + * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's + * safe to call ipc_rcu_putref here + */ + ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); + + if (ipc_valid_object(&shp->shm_perm)) { + if (shm_may_destroy(shp)) + shm_destroy(ns, shp); + else + shm_unlock(shp); + } else { + /* + * Someone else deleted the shp from namespace + * idr/kht while we have waited. + * Just unlock and continue. + */ + shm_unlock(shp); + } + + up_write(&shm_ids(ns).rwsem); + put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */ + } } static int shm_fault(struct vm_fault *vmf) @@ -625,7 +708,11 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) if (error < 0) goto no_id; + shp->ns = ns; + + task_lock(current); list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist); + task_unlock(current); /* * shmid gets reported as "inode#" in /proc/pid/maps. @@ -1449,7 +1536,8 @@ out_nattch: down_write(&shm_ids(ns).rwsem); shp = shm_lock(ns, shmid); shp->shm_nattch--; - if (shm_may_destroy(ns, shp)) + + if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); From c537846f7270e5754324046c594a017c5f268b32 Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Fri, 19 Nov 2021 16:43:18 -0800 Subject: [PATCH 070/277] ipc: WARN if trying to remove ipc object which is absent commit 126e8bee943e9926238c891e2df5b5573aee76bc upstream. Patch series "shm: shm_rmid_forced feature fixes". Some time ago I met kernel crash after CRIU restore procedure, fortunately, it was CRIU restore, so, I had dump files and could do restore many times and crash reproduced easily. After some investigation I've constructed the minimal reproducer. It was found that it's use-after-free and it happens only if sysctl kernel.shm_rmid_forced = 1. The key of the problem is that the exit_shm() function not handles shp's object destroy when task->sysvshm.shm_clist contains items from different IPC namespaces. In most cases this list will contain only items from one IPC namespace. How can this list contain object from different namespaces? The exit_shm() function is designed to clean up this list always when process leaves IPC namespace. But we made a mistake a long time ago and did not add a exit_shm() call into the setns() syscall procedures. The first idea was just to add this call to setns() syscall but it obviously changes semantics of setns() syscall and that's userspace-visible change. So, I gave up on this idea. The first real attempt to address the issue was just to omit forced destroy if we meet shp object not from current task IPC namespace [1]. But that was not the best idea because task->sysvshm.shm_clist was protected by rwsem which belongs to current task IPC namespace. It means that list corruption may occur. Second approach is just extend exit_shm() to properly handle shp's from different IPC namespaces [2]. This is really non-trivial thing, I've put a lot of effort into that but not believed that it's possible to make it fully safe, clean and clear. Thanks to the efforts of Manfred Spraul working an elegant solution was designed. Thanks a lot, Manfred! Eric also suggested the way to address the issue in ("[RFC][PATCH] shm: In shm_exit destroy all created and never attached segments") Eric's idea was to maintain a list of shm_clists one per IPC namespace, use lock-less lists. But there is some extra memory consumption-related concerns. An alternative solution which was suggested by me was implemented in ("shm: reset shm_clist on setns but omit forced shm destroy"). The idea is pretty simple, we add exit_shm() syscall to setns() but DO NOT destroy shm segments even if sysctl kernel.shm_rmid_forced = 1, we just clean up the task->sysvshm.shm_clist list. This chages semantics of setns() syscall a little bit but in comparision to the "naive" solution when we just add exit_shm() without any special exclusions this looks like a safer option. [1] https://lkml.org/lkml/2021/7/6/1108 [2] https://lkml.org/lkml/2021/7/14/736 This patch (of 2): Let's produce a warning if we trying to remove non-existing IPC object from IPC namespace kht/idr structures. This allows us to catch possible bugs when the ipc_rmid() function was called with inconsistent struct ipc_ids*, struct kern_ipc_perm* arguments. Link: https://lkml.kernel.org/r/20211027224348.611025-1-alexander.mikhalitsyn@virtuozzo.com Link: https://lkml.kernel.org/r/20211027224348.611025-2-alexander.mikhalitsyn@virtuozzo.com Co-developed-by: Manfred Spraul Signed-off-by: Manfred Spraul Signed-off-by: Alexander Mikhalitsyn Cc: "Eric W. Biederman" Cc: Davidlohr Bueso Cc: Greg KH Cc: Andrei Vagin Cc: Pavel Tikhomirov Cc: Vasily Averin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- ipc/util.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/ipc/util.c b/ipc/util.c index 5a65b0cbae7d..198b4c1c3ad3 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -409,8 +409,8 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids, static void ipc_kht_remove(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) { if (ipcp->key != IPC_PRIVATE) - rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode, - ipc_kht_params); + WARN_ON_ONCE(rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode, + ipc_kht_params)); } /** @@ -425,7 +425,7 @@ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) { int lid = ipcid_to_idx(ipcp->id); - idr_remove(&ids->ipcs_idr, lid); + WARN_ON_ONCE(idr_remove(&ids->ipcs_idr, lid) != ipcp); ipc_kht_remove(ids, ipcp); ids->in_use--; ipcp->deleted = true; From 2387ff2f17501a208ef3524001a1df6cc151e26e Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Tue, 16 Nov 2021 10:48:13 -0500 Subject: [PATCH 071/277] NFSv42: Fix pagecache invalidation after COPY/CLONE commit 3f015d89a47cd8855cd92f71fff770095bd885a1 upstream. The mechanism in use to allow the client to see the results of COPY/CLONE is to drop those pages from the pagecache. This forces the client to read those pages once more from the server. However, truncate_pagecache_range() zeros out partial pages instead of dropping them. Let us instead use invalidate_inode_pages2_range() with full-page offsets to ensure the client properly sees the results of COPY/CLONE operations. Cc: # v4.7+ Fixes: 2e72448b07dc ("NFS: Add COPY nfs operation") Signed-off-by: Benjamin Coddington Signed-off-by: Trond Myklebust Signed-off-by: Greg Kroah-Hartman --- fs/nfs/nfs42proc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index a61792f777be..394503c79faf 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -186,8 +186,9 @@ static ssize_t _nfs42_proc_copy(struct file *src, goto out; } - truncate_pagecache_range(dst_inode, pos_dst, - pos_dst + res->write_res.count); + WARN_ON_ONCE(invalidate_inode_pages2_range(dst_inode->i_mapping, + pos_dst >> PAGE_SHIFT, + (pos_dst + res->write_res.count - 1) >> PAGE_SHIFT)); status = res->write_res.count; out: From 0b0ac11742b0d6383472b869bd3633be175d7d9e Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Oct 2018 15:51:33 -0700 Subject: [PATCH 072/277] hugetlb: take PMD sharing into account when flushing tlb/caches commit dff11abe280b47c21b804a8ace318e0638bb9a49 upstream. When fixing an issue with PMD sharing and migration, it was discovered via code inspection that other callers of huge_pmd_unshare potentially have an issue with cache and tlb flushing. Use the routine adjust_range_if_pmd_sharing_possible() to calculate worst case ranges for mmu notifiers. Ensure that this range is flushed if huge_pmd_unshare succeeds and unmaps a PUD_SUZE area. Link: http://lkml.kernel.org/r/20180823205917.16297-3-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: Kirill A. Shutemov Reviewed-by: Naoya Horiguchi Cc: Vlastimil Babka Cc: Davidlohr Bueso Cc: Michal Hocko Cc: Jerome Glisse Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- mm/hugetlb.c | 53 ++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 43 insertions(+), 10 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 515ba949c06a..c6ae9c9e360d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3384,8 +3384,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); - const unsigned long mmun_start = start; /* For mmu_notifiers */ - const unsigned long mmun_end = end; /* For mmu_notifiers */ + unsigned long mmun_start = start; /* For mmu_notifiers */ + unsigned long mmun_end = end; /* For mmu_notifiers */ bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); @@ -3398,6 +3398,11 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, */ tlb_remove_check_page_size_change(tlb, sz); tlb_start_vma(tlb, vma); + + /* + * If sharing possible, alert mmu notifiers of worst case. + */ + adjust_range_if_pmd_sharing_possible(vma, &mmun_start, &mmun_end); mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); address = start; for (; address < end; address += sz) { @@ -3508,12 +3513,23 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, { struct mm_struct *mm; struct mmu_gather tlb; + unsigned long tlb_start = start; + unsigned long tlb_end = end; + + /* + * If shared PMDs were possibly used within this vma range, adjust + * start/end for worst case tlb flushing. + * Note that we can not be sure if PMDs are shared until we try to + * unmap pages. However, we want to make sure TLB flushing covers + * the largest possible range. + */ + adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end); mm = vma->vm_mm; - tlb_gather_mmu(&tlb, mm, start, end); + tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end); __unmap_hugepage_range(&tlb, vma, start, end, ref_page); - tlb_finish_mmu(&tlb, start, end); + tlb_finish_mmu(&tlb, tlb_start, tlb_end); } /* @@ -4408,11 +4424,21 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, pte_t pte; struct hstate *h = hstate_vma(vma); unsigned long pages = 0; + unsigned long f_start = start; + unsigned long f_end = end; + bool shared_pmd = false; + + /* + * In the case of shared PMDs, the area to flush could be beyond + * start/end. Set f_start/f_end to cover the maximum possible + * range if PMD sharing is possible. + */ + adjust_range_if_pmd_sharing_possible(vma, &f_start, &f_end); BUG_ON(address >= end); - flush_cache_range(vma, address, end); + flush_cache_range(vma, f_start, f_end); - mmu_notifier_invalidate_range_start(mm, start, end); + mmu_notifier_invalidate_range_start(mm, f_start, f_end); i_mmap_lock_write(vma->vm_file->f_mapping); for (; address < end; address += huge_page_size(h)) { spinlock_t *ptl; @@ -4423,6 +4449,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, if (huge_pmd_unshare(mm, &address, ptep)) { pages++; spin_unlock(ptl); + shared_pmd = true; continue; } pte = huge_ptep_get(ptep); @@ -4458,12 +4485,18 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: * once we release i_mmap_rwsem, another task can do the final put_page - * and that page table be reused and filled with junk. + * and that page table be reused and filled with junk. If we actually + * did unshare a page of pmds, flush the range corresponding to the pud. */ - flush_hugetlb_tlb_range(vma, start, end); - mmu_notifier_invalidate_range(mm, start, end); + if (shared_pmd) { + flush_hugetlb_tlb_range(vma, f_start, f_end); + mmu_notifier_invalidate_range(mm, f_start, f_end); + } else { + flush_hugetlb_tlb_range(vma, start, end); + mmu_notifier_invalidate_range(mm, start, end); + } i_mmap_unlock_write(vma->vm_file->f_mapping); - mmu_notifier_invalidate_range_end(mm, start, end); + mmu_notifier_invalidate_range_end(mm, f_start, f_end); return pages << h->order; } From 1ce4633f9b446aa772d0788e3e9194f75c1a4ac5 Mon Sep 17 00:00:00 2001 From: liuguoqiang Date: Mon, 15 Nov 2021 16:14:48 +0800 Subject: [PATCH 073/277] net: return correct error code [ Upstream commit 6def480181f15f6d9ec812bca8cbc62451ba314c ] When kmemdup called failed and register_net_sysctl return NULL, should return ENOMEM instead of ENOBUFS Signed-off-by: liuguoqiang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/devinet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index d4d53aea2c60..d9bb3ae78560 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2324,7 +2324,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, free: kfree(t); out: - return -ENOBUFS; + return -ENOMEM; } static void __devinet_sysctl_unregister(struct net *net, From 705616ecff4ce578bafe187a74c648d3069dc3e5 Mon Sep 17 00:00:00 2001 From: Slark Xiao Date: Mon, 8 Nov 2021 14:06:48 +0800 Subject: [PATCH 074/277] platform/x86: thinkpad_acpi: Fix WWAN device disabled issue after S3 deep [ Upstream commit 39f53292181081d35174a581a98441de5da22bc9 ] When WWAN device wake from S3 deep, under thinkpad platform, WWAN would be disabled. This disable status could be checked by command 'nmcli r wwan' or 'rfkill list'. Issue analysis as below: When host resume from S3 deep, thinkpad_acpi driver would call hotkey_resume() function. Finnaly, it will use wan_get_status to check the current status of WWAN device. During this resume progress, wan_get_status would always return off even WWAN boot up completely. In patch V2, Hans said 'sw_state should be unchanged after a suspend/resume. It's better to drop the tpacpi_rfk_update_swstate call all together from the resume path'. And it's confimed by Lenovo that GWAN is no longer available from WHL generation because the design does not match with current pin control. Signed-off-by: Slark Xiao Link: https://lore.kernel.org/r/20211108060648.8212-1-slark_xiao@163.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/thinkpad_acpi.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 9d836d779d47..05b3e0f724fc 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -1180,15 +1180,6 @@ static int tpacpi_rfk_update_swstate(const struct tpacpi_rfk *tp_rfk) return status; } -/* Query FW and update rfkill sw state for all rfkill switches */ -static void tpacpi_rfk_update_swstate_all(void) -{ - unsigned int i; - - for (i = 0; i < TPACPI_RFK_SW_MAX; i++) - tpacpi_rfk_update_swstate(tpacpi_rfkill_switches[i]); -} - /* * Sync the HW-blocking state of all rfkill switches, * do notice it causes the rfkill core to schedule uevents @@ -3025,9 +3016,6 @@ static void tpacpi_send_radiosw_update(void) if (wlsw == TPACPI_RFK_RADIO_OFF) tpacpi_rfk_update_hwblock_state(true); - /* Sync sw blocking state */ - tpacpi_rfk_update_swstate_all(); - /* Sync hw blocking state last if it is hw-unblocked */ if (wlsw == TPACPI_RFK_RADIO_ON) tpacpi_rfk_update_hwblock_state(false); From 5291b6599f0aad21936e80d15bd6788368836df3 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 14 Oct 2021 13:38:17 +0200 Subject: [PATCH 075/277] s390/setup: avoid using memblock_enforce_memory_limit [ Upstream commit 5dbc4cb4667457b0c53bcd7bff11500b3c362975 ] There is a difference in how architectures treat "mem=" option. For some that is an amount of online memory, for s390 and x86 this is the limiting max address. Some memblock api like memblock_enforce_memory_limit() take limit argument and explicitly treat it as the size of online memory, and use __find_max_addr to convert it to an actual max address. Current s390 usage: memblock_enforce_memory_limit(memblock_end_of_DRAM()); yields different results depending on presence of memory holes (offline memory blocks in between online memory). If there are no memory holes limit == max_addr in memblock_enforce_memory_limit() and it does trim online memory and reserved memory regions. With memory holes present it actually does nothing. Since we already use memblock_remove() explicitly to trim online memory regions to potential limit (think mem=, kdump, addressing limits, etc.) drop the usage of memblock_enforce_memory_limit() altogether. Trimming reserved regions should not be required, since we now use memblock_set_current_limit() to limit allocations and any explicit memory reservations above the limit is an actual problem we should not hide. Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- arch/s390/kernel/setup.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ceaee215e243..e9ef093eb676 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -706,9 +706,6 @@ static void __init setup_memory(void) storage_key_init_range(reg->base, reg->base + reg->size); } psw_set_key(PAGE_DEFAULT_KEY); - - /* Only cosmetics */ - memblock_enforce_memory_limit(memblock_end_of_DRAM()); } /* From e4e7b95df3e224ff2a1f9c7bc25c5e2fa81ce7d8 Mon Sep 17 00:00:00 2001 From: Wang Yugui Date: Thu, 28 Oct 2021 06:32:54 +0800 Subject: [PATCH 076/277] btrfs: check-integrity: fix a warning on write caching disabled disk [ Upstream commit a91cf0ffbc244792e0b3ecf7d0fddb2f344b461f ] When a disk has write caching disabled, we skip submission of a bio with flush and sync requests before writing the superblock, since it's not needed. However when the integrity checker is enabled, this results in reports that there are metadata blocks referred by a superblock that were not properly flushed. So don't skip the bio submission only when the integrity checker is enabled for the sake of simplicity, since this is a debug tool and not meant for use in non-debug builds. fstests/btrfs/220 trigger a check-integrity warning like the following when CONFIG_BTRFS_FS_CHECK_INTEGRITY=y and the disk with WCE=0. btrfs: attempt to write superblock which references block M @5242880 (sdb2/5242880/0) which is not flushed out of disk's write cache (block flush_gen=1, dev->flush_gen=0)! ------------[ cut here ]------------ WARNING: CPU: 28 PID: 843680 at fs/btrfs/check-integrity.c:2196 btrfsic_process_written_superblock+0x22a/0x2a0 [btrfs] CPU: 28 PID: 843680 Comm: umount Not tainted 5.15.0-0.rc5.39.el8.x86_64 #1 Hardware name: Dell Inc. Precision T7610/0NK70N, BIOS A18 09/11/2019 RIP: 0010:btrfsic_process_written_superblock+0x22a/0x2a0 [btrfs] RSP: 0018:ffffb642afb47940 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000000 RDX: 00000000ffffffff RSI: ffff8b722fc97d00 RDI: ffff8b722fc97d00 RBP: ffff8b5601c00000 R08: 0000000000000000 R09: c0000000ffff7fff R10: 0000000000000001 R11: ffffb642afb476f8 R12: ffffffffffffffff R13: ffffb642afb47974 R14: ffff8b5499254c00 R15: 0000000000000003 FS: 00007f00a06d4080(0000) GS:ffff8b722fc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fff5cff5ff0 CR3: 00000001c0c2a006 CR4: 00000000001706e0 Call Trace: btrfsic_process_written_block+0x2f7/0x850 [btrfs] __btrfsic_submit_bio.part.19+0x310/0x330 [btrfs] ? bio_associate_blkg_from_css+0xa4/0x2c0 btrfsic_submit_bio+0x18/0x30 [btrfs] write_dev_supers+0x81/0x2a0 [btrfs] ? find_get_pages_range_tag+0x219/0x280 ? pagevec_lookup_range_tag+0x24/0x30 ? __filemap_fdatawait_range+0x6d/0xf0 ? __raw_callee_save___native_queued_spin_unlock+0x11/0x1e ? find_first_extent_bit+0x9b/0x160 [btrfs] ? __raw_callee_save___native_queued_spin_unlock+0x11/0x1e write_all_supers+0x1b3/0xa70 [btrfs] ? __raw_callee_save___native_queued_spin_unlock+0x11/0x1e btrfs_commit_transaction+0x59d/0xac0 [btrfs] close_ctree+0x11d/0x339 [btrfs] generic_shutdown_super+0x71/0x110 kill_anon_super+0x14/0x30 btrfs_kill_super+0x12/0x20 [btrfs] deactivate_locked_super+0x31/0x70 cleanup_mnt+0xb8/0x140 task_work_run+0x6d/0xb0 exit_to_user_mode_prepare+0x1f0/0x200 syscall_exit_to_user_mode+0x12/0x30 do_syscall_64+0x46/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f009f711dfb RSP: 002b:00007fff5cff7928 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 RAX: 0000000000000000 RBX: 000055b68c6c9970 RCX: 00007f009f711dfb RDX: 0000000000000001 RSI: 0000000000000000 RDI: 000055b68c6c9b50 RBP: 0000000000000000 R08: 000055b68c6ca900 R09: 00007f009f795580 R10: 0000000000000000 R11: 0000000000000246 R12: 000055b68c6c9b50 R13: 00007f00a04bf184 R14: 0000000000000000 R15: 00000000ffffffff ---[ end trace 2c4b82abcef9eec4 ]--- S-65536(sdb2/65536/1) --> M-1064960(sdb2/1064960/1) Reviewed-by: Filipe Manana Signed-off-by: Wang Yugui Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/disk-io.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ace58d6a270b..41ebc613ca4c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3339,11 +3339,23 @@ static void btrfs_end_empty_barrier(struct bio *bio) */ static void write_dev_flush(struct btrfs_device *device) { - struct request_queue *q = bdev_get_queue(device->bdev); struct bio *bio = device->flush_bio; +#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY + /* + * When a disk has write caching disabled, we skip submission of a bio + * with flush and sync requests before writing the superblock, since + * it's not needed. However when the integrity checker is enabled, this + * results in reports that there are metadata blocks referred by a + * superblock that were not properly flushed. So don't skip the bio + * submission only when the integrity checker is enabled for the sake + * of simplicity, since this is a debug tool and not meant for use in + * non-debug builds. + */ + struct request_queue *q = bdev_get_queue(device->bdev); if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) return; +#endif bio_reset(bio); bio->bi_end_io = btrfs_end_empty_barrier; From ad4d6cd6a2e3bcf409868f25be250c7b319e8a2c Mon Sep 17 00:00:00 2001 From: Manaf Meethalavalappu Pallikunhi Date: Wed, 3 Nov 2021 01:30:40 +0530 Subject: [PATCH 077/277] thermal: core: Reset previous low and high trip during thermal zone init [ Upstream commit 99b63316c39988039965693f5f43d8b4ccb1c86c ] During the suspend is in process, thermal_zone_device_update bails out thermal zone re-evaluation for any sensor trip violation without setting next valid trip to that sensor. It assumes during resume it will re-evaluate same thermal zone and update trip. But when it is in suspend temperature goes down and on resume path while updating thermal zone if temperature is less than previously violated trip, thermal zone set trip function evaluates the same previous high and previous low trip as new high and low trip. Since there is no change in high/low trip, it bails out from thermal zone set trip API without setting any trip. It leads to a case where sensor high trip or low trip is disabled forever even though thermal zone has a valid high or low trip. During thermal zone device init, reset thermal zone previous high and low trip. It resolves above mentioned scenario. Signed-off-by: Manaf Meethalavalappu Pallikunhi Reviewed-by: Thara Gopinath Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/thermal/thermal_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 94820f25a15f..8374b8078b7d 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -457,6 +457,8 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz) { struct thermal_instance *pos; tz->temperature = THERMAL_TEMP_INVALID; + tz->prev_low_trip = -INT_MAX; + tz->prev_high_trip = INT_MAX; list_for_each_entry(pos, &tz->thermal_instances, tz_node) pos->initialized = false; } From 8e618c6171bccebc6bcb07eaa29812ec4669a534 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 5 Nov 2021 17:10:47 -0500 Subject: [PATCH 078/277] scsi: iscsi: Unblock session then wake up error handler [ Upstream commit a0c2f8b6709a9a4af175497ca65f93804f57b248 ] We can race where iscsi_session_recovery_timedout() has woken up the error handler thread and it's now setting the devices to offline, and session_recovery_timedout()'s call to scsi_target_unblock() is also trying to set the device's state to transport-offline. We can then get a mix of states. For the case where we can't relogin we want the devices to be in transport-offline so when we have repaired the connection __iscsi_unblock_session() can set the state back to running. Set the device state then call into libiscsi to wake up the error handler. Link: https://lore.kernel.org/r/20211105221048.6541-2-michael.christie@oracle.com Reviewed-by: Lee Duncan Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_transport_iscsi.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index d276d84c0f7a..26c6f1b28801 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -1892,12 +1892,12 @@ static void session_recovery_timedout(struct work_struct *work) } spin_unlock_irqrestore(&session->lock, flags); - if (session->transport->session_recovery_timedout) - session->transport->session_recovery_timedout(session); - ISCSI_DBG_TRANS_SESSION(session, "Unblocking SCSI target\n"); scsi_target_unblock(&session->dev, SDEV_TRANSPORT_OFFLINE); ISCSI_DBG_TRANS_SESSION(session, "Completed unblocking SCSI target\n"); + + if (session->transport->session_recovery_timedout) + session->transport->session_recovery_timedout(session); } static void __iscsi_unblock_session(struct work_struct *work) From abbd5faa0748d0aa95d5191d56ff7a17a6275bd1 Mon Sep 17 00:00:00 2001 From: Teng Qi Date: Wed, 17 Nov 2021 11:44:53 +0800 Subject: [PATCH 079/277] ethernet: hisilicon: hns: hns_dsaf_misc: fix a possible array overflow in hns_dsaf_ge_srst_by_port() [ Upstream commit a66998e0fbf213d47d02813b9679426129d0d114 ] The if statement: if (port >= DSAF_GE_NUM) return; limits the value of port less than DSAF_GE_NUM (i.e., 8). However, if the value of port is 6 or 7, an array overflow could occur: port_rst_off = dsaf_dev->mac_cb[port]->port_rst_off; because the length of dsaf_dev->mac_cb is DSAF_MAX_PORT_NUM (i.e., 6). To fix this possible array overflow, we first check port and if it is greater than or equal to DSAF_MAX_PORT_NUM, the function returns. Reported-by: TOTE Robot Signed-off-by: Teng Qi Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 408b63faf9a8..c4e56784ed1b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -336,6 +336,10 @@ static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, return; if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) { + /* DSAF_MAX_PORT_NUM is 6, but DSAF_GE_NUM is 8. + We need check to prevent array overflow */ + if (port >= DSAF_MAX_PORT_NUM) + return; reg_val_1 = 0x1 << port; port_rst_off = dsaf_dev->mac_cb[port]->port_rst_off; /* there is difference between V1 and V2 in register.*/ From d3dedaa5a601107cfedda087209772c76e364d58 Mon Sep 17 00:00:00 2001 From: zhangyue Date: Thu, 18 Nov 2021 13:46:32 +0800 Subject: [PATCH 080/277] net: tulip: de4x5: fix the problem that the array 'lp->phy[8]' may be out of bound [ Upstream commit 61217be886b5f7402843677e4be7e7e83de9cb41 ] In line 5001, if all id in the array 'lp->phy[8]' is not 0, when the 'for' end, the 'k' is 8. At this time, the array 'lp->phy[8]' may be out of bound. Signed-off-by: zhangyue Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/dec/tulip/de4x5.c | 30 +++++++++++++++----------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 8f108a30cba6..84cf7b4582f3 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -4994,19 +4994,23 @@ mii_get_phy(struct net_device *dev) } if ((j == limit) && (i < DE4X5_MAX_MII)) { for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++); - lp->phy[k].addr = i; - lp->phy[k].id = id; - lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */ - lp->phy[k].spd.mask = GENERIC_MASK; /* 100Mb/s technologies */ - lp->phy[k].spd.value = GENERIC_VALUE; /* TX & T4, H/F Duplex */ - lp->mii_cnt++; - lp->active++; - printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name); - j = de4x5_debug; - de4x5_debug |= DEBUG_MII; - de4x5_dbg_mii(dev, k); - de4x5_debug = j; - printk("\n"); + if (k < DE4X5_MAX_PHY) { + lp->phy[k].addr = i; + lp->phy[k].id = id; + lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */ + lp->phy[k].spd.mask = GENERIC_MASK; /* 100Mb/s technologies */ + lp->phy[k].spd.value = GENERIC_VALUE; /* TX & T4, H/F Duplex */ + lp->mii_cnt++; + lp->active++; + printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name); + j = de4x5_debug; + de4x5_debug |= DEBUG_MII; + de4x5_dbg_mii(dev, k); + de4x5_debug = j; + printk("\n"); + } else { + goto purgatory; + } } } purgatory: From ae3c30ca1894ead38e39576289e5a8346621450f Mon Sep 17 00:00:00 2001 From: Teng Qi Date: Thu, 18 Nov 2021 15:01:18 +0800 Subject: [PATCH 081/277] net: ethernet: dec: tulip: de4x5: fix possible array overflows in type3_infoblock() [ Upstream commit 0fa68da72c3be09e06dd833258ee89c33374195f ] The definition of macro MOTO_SROM_BUG is: #define MOTO_SROM_BUG (lp->active == 8 && (get_unaligned_le32( dev->dev_addr) & 0x00ffffff) == 0x3e0008) and the if statement if (MOTO_SROM_BUG) lp->active = 0; using this macro indicates lp->active could be 8. If lp->active is 8 and the second comparison of this macro is false. lp->active will remain 8 in: lp->phy[lp->active].gep = (*p ? p : NULL); p += (2 * (*p) + 1); lp->phy[lp->active].rst = (*p ? p : NULL); p += (2 * (*p) + 1); lp->phy[lp->active].mc = get_unaligned_le16(p); p += 2; lp->phy[lp->active].ana = get_unaligned_le16(p); p += 2; lp->phy[lp->active].fdx = get_unaligned_le16(p); p += 2; lp->phy[lp->active].ttm = get_unaligned_le16(p); p += 2; lp->phy[lp->active].mci = *p; However, the length of array lp->phy is 8, so array overflows can occur. To fix these possible array overflows, we first check lp->active and then return -EINVAL if it is greater or equal to ARRAY_SIZE(lp->phy) (i.e. 8). Reported-by: TOTE Robot Signed-off-by: Teng Qi Reviewed-by: Arnd Bergmann Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/dec/tulip/de4x5.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 84cf7b4582f3..09a65f8f6203 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -4703,6 +4703,10 @@ type3_infoblock(struct net_device *dev, u_char count, u_char *p) lp->ibn = 3; lp->active = *p++; if (MOTO_SROM_BUG) lp->active = 0; + /* if (MOTO_SROM_BUG) statement indicates lp->active could + * be 8 (i.e. the size of array lp->phy) */ + if (WARN_ON(lp->active >= ARRAY_SIZE(lp->phy))) + return -EINVAL; lp->phy[lp->active].gep = (*p ? p : NULL); p += (2 * (*p) + 1); lp->phy[lp->active].rst = (*p ? p : NULL); p += (2 * (*p) + 1); lp->phy[lp->active].mc = get_unaligned_le16(p); p += 2; From c5c8a26c0dc69a400553245e92d741fe55f91095 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 17 Nov 2021 23:12:47 -0800 Subject: [PATCH 082/277] perf hist: Fix memory leak of a perf_hpp_fmt [ Upstream commit 0ca1f534a776cc7d42f2c33da4732b74ec2790cd ] perf_hpp__column_unregister() removes an entry from a list but doesn't free the memory causing a memory leak spotted by leak sanitizer. Add the free while at the same time reducing the scope of the function to static. Signed-off-by: Ian Rogers Reviewed-by: Kajol Jain Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20211118071247.2140392-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/ui/hist.c | 28 ++++++++++++++-------------- tools/perf/util/hist.h | 1 - 2 files changed, 14 insertions(+), 15 deletions(-) diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 706f6f1e9c7d..445a7012b117 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -468,6 +468,18 @@ struct perf_hpp_list perf_hpp_list = { #undef __HPP_SORT_ACC_FN #undef __HPP_SORT_RAW_FN +static void fmt_free(struct perf_hpp_fmt *fmt) +{ + /* + * At this point fmt should be completely + * unhooked, if not it's a bug. + */ + BUG_ON(!list_empty(&fmt->list)); + BUG_ON(!list_empty(&fmt->sort_list)); + + if (fmt->free) + fmt->free(fmt); +} void perf_hpp__init(void) { @@ -531,9 +543,10 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list, list_add(&format->sort_list, &list->sorts); } -void perf_hpp__column_unregister(struct perf_hpp_fmt *format) +static void perf_hpp__column_unregister(struct perf_hpp_fmt *format) { list_del_init(&format->list); + fmt_free(format); } void perf_hpp__cancel_cumulate(void) @@ -605,19 +618,6 @@ next: } -static void fmt_free(struct perf_hpp_fmt *fmt) -{ - /* - * At this point fmt should be completely - * unhooked, if not it's a bug. - */ - BUG_ON(!list_empty(&fmt->list)); - BUG_ON(!list_empty(&fmt->sort_list)); - - if (fmt->free) - fmt->free(fmt); -} - void perf_hpp__reset_output_field(struct perf_hpp_list *list) { struct perf_hpp_fmt *fmt, *tmp; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 595f91f46811..2eb71eeec485 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -339,7 +339,6 @@ enum { }; void perf_hpp__init(void); -void perf_hpp__column_unregister(struct perf_hpp_fmt *format); void perf_hpp__cancel_cumulate(void); void perf_hpp__setup_output_field(struct perf_hpp_list *list); void perf_hpp__reset_output_field(struct perf_hpp_list *list); From 95d61f9fd20fbab3c06bb78e3a9d31f28a444c2a Mon Sep 17 00:00:00 2001 From: Stephen Suryaputra Date: Tue, 30 Nov 2021 11:26:37 -0500 Subject: [PATCH 083/277] vrf: Reset IPCB/IP6CB when processing outbound pkts in vrf dev xmit commit ee201011c1e1563c114a55c86eb164b236f18e84 upstream. IPCB/IP6CB need to be initialized when processing outbound v4 or v6 pkts in the codepath of vrf device xmit function so that leftover garbage doesn't cause futher code that uses the CB to incorrectly process the pkt. One occasion of the issue might occur when MPLS route uses the vrf device as the outgoing device such as when the route is added using "ip -f mpls route add