From 1766e7b3763a0707c2fda9689a7866dceed07b7a Mon Sep 17 00:00:00 2001 From: David Lechner Date: Wed, 10 Aug 2016 18:49:27 +0530 Subject: mfd: da8xx-cfgchip: New header file for CFGCHIP registers Create a new header file for TI DA8XX SoC CFGCHIPx registers. This will be used by a number of planned drivers including a new USB PHY driver and common clock framework drivers. The same defines *will* be removed from the platform_data header, once all the users start using the new syscon device header. This also fixes the following compiler error caused due to a dependent patch not merged. drivers/phy/phy-da8xx-usb.c:19:37: fatal error: linux/mfd/da8xx-cfgchip.h: No such file or directory #include Signed-off-by: David Lechner Acked-by: Lee Jones Reported-by: Arnd Bergmann Signed-off-by: Kishon Vijay Abraham I --- include/linux/mfd/da8xx-cfgchip.h | 153 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 153 insertions(+) create mode 100644 include/linux/mfd/da8xx-cfgchip.h (limited to 'include/linux') diff --git a/include/linux/mfd/da8xx-cfgchip.h b/include/linux/mfd/da8xx-cfgchip.h new file mode 100644 index 000000000000..304985e288d2 --- /dev/null +++ b/include/linux/mfd/da8xx-cfgchip.h @@ -0,0 +1,153 @@ +/* + * TI DaVinci DA8xx CHIPCFGx registers for syscon consumers. + * + * Copyright (C) 2016 David Lechner + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_MFD_DA8XX_CFGCHIP_H +#define __LINUX_MFD_DA8XX_CFGCHIP_H + +#include + +/* register offset (32-bit registers) */ +#define CFGCHIP(n) ((n) * 4) + +/* CFGCHIP0 (PLL0/EDMA3_0) register bits */ +#define CFGCHIP0_PLL_MASTER_LOCK BIT(4) +#define CFGCHIP0_EDMA30TC1DBS(n) ((n) << 2) +#define CFGCHIP0_EDMA30TC1DBS_MASK CFGCHIP0_EDMA30TC1DBS(0x3) +#define CFGCHIP0_EDMA30TC1DBS_16 CFGCHIP0_EDMA30TC1DBS(0x0) +#define CFGCHIP0_EDMA30TC1DBS_32 CFGCHIP0_EDMA30TC1DBS(0x1) +#define CFGCHIP0_EDMA30TC1DBS_64 CFGCHIP0_EDMA30TC1DBS(0x2) +#define CFGCHIP0_EDMA30TC0DBS(n) ((n) << 0) +#define CFGCHIP0_EDMA30TC0DBS_MASK CFGCHIP0_EDMA30TC0DBS(0x3) +#define CFGCHIP0_EDMA30TC0DBS_16 CFGCHIP0_EDMA30TC0DBS(0x0) +#define CFGCHIP0_EDMA30TC0DBS_32 CFGCHIP0_EDMA30TC0DBS(0x1) +#define CFGCHIP0_EDMA30TC0DBS_64 CFGCHIP0_EDMA30TC0DBS(0x2) + +/* CFGCHIP1 (eCAP/HPI/EDMA3_1/eHRPWM TBCLK/McASP0 AMUTEIN) register bits */ +#define CFGCHIP1_CAP2SRC(n) ((n) << 27) +#define CFGCHIP1_CAP2SRC_MASK CFGCHIP1_CAP2SRC(0x1f) +#define CFGCHIP1_CAP2SRC_ECAP_PIN CFGCHIP1_CAP2SRC(0x0) +#define CFGCHIP1_CAP2SRC_MCASP0_TX CFGCHIP1_CAP2SRC(0x1) +#define CFGCHIP1_CAP2SRC_MCASP0_RX CFGCHIP1_CAP2SRC(0x2) +#define CFGCHIP1_CAP2SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP2SRC(0x7) +#define CFGCHIP1_CAP2SRC_EMAC_C0_RX CFGCHIP1_CAP2SRC(0x8) +#define CFGCHIP1_CAP2SRC_EMAC_C0_TX CFGCHIP1_CAP2SRC(0x9) +#define CFGCHIP1_CAP2SRC_EMAC_C0_MISC CFGCHIP1_CAP2SRC(0xa) +#define CFGCHIP1_CAP2SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP2SRC(0xb) +#define CFGCHIP1_CAP2SRC_EMAC_C1_RX CFGCHIP1_CAP2SRC(0xc) +#define CFGCHIP1_CAP2SRC_EMAC_C1_TX CFGCHIP1_CAP2SRC(0xd) +#define CFGCHIP1_CAP2SRC_EMAC_C1_MISC CFGCHIP1_CAP2SRC(0xe) +#define CFGCHIP1_CAP2SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP2SRC(0xf) +#define CFGCHIP1_CAP2SRC_EMAC_C2_RX CFGCHIP1_CAP2SRC(0x10) +#define CFGCHIP1_CAP2SRC_EMAC_C2_TX CFGCHIP1_CAP2SRC(0x11) +#define CFGCHIP1_CAP2SRC_EMAC_C2_MISC CFGCHIP1_CAP2SRC(0x12) +#define CFGCHIP1_CAP1SRC(n) ((n) << 22) +#define CFGCHIP1_CAP1SRC_MASK CFGCHIP1_CAP1SRC(0x1f) +#define CFGCHIP1_CAP1SRC_ECAP_PIN CFGCHIP1_CAP1SRC(0x0) +#define CFGCHIP1_CAP1SRC_MCASP0_TX CFGCHIP1_CAP1SRC(0x1) +#define CFGCHIP1_CAP1SRC_MCASP0_RX CFGCHIP1_CAP1SRC(0x2) +#define CFGCHIP1_CAP1SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP1SRC(0x7) +#define CFGCHIP1_CAP1SRC_EMAC_C0_RX CFGCHIP1_CAP1SRC(0x8) +#define CFGCHIP1_CAP1SRC_EMAC_C0_TX CFGCHIP1_CAP1SRC(0x9) +#define CFGCHIP1_CAP1SRC_EMAC_C0_MISC CFGCHIP1_CAP1SRC(0xa) +#define CFGCHIP1_CAP1SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP1SRC(0xb) +#define CFGCHIP1_CAP1SRC_EMAC_C1_RX CFGCHIP1_CAP1SRC(0xc) +#define CFGCHIP1_CAP1SRC_EMAC_C1_TX CFGCHIP1_CAP1SRC(0xd) +#define CFGCHIP1_CAP1SRC_EMAC_C1_MISC CFGCHIP1_CAP1SRC(0xe) +#define CFGCHIP1_CAP1SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP1SRC(0xf) +#define CFGCHIP1_CAP1SRC_EMAC_C2_RX CFGCHIP1_CAP1SRC(0x10) +#define CFGCHIP1_CAP1SRC_EMAC_C2_TX CFGCHIP1_CAP1SRC(0x11) +#define CFGCHIP1_CAP1SRC_EMAC_C2_MISC CFGCHIP1_CAP1SRC(0x12) +#define CFGCHIP1_CAP0SRC(n) ((n) << 17) +#define CFGCHIP1_CAP0SRC_MASK CFGCHIP1_CAP0SRC(0x1f) +#define CFGCHIP1_CAP0SRC_ECAP_PIN CFGCHIP1_CAP0SRC(0x0) +#define CFGCHIP1_CAP0SRC_MCASP0_TX CFGCHIP1_CAP0SRC(0x1) +#define CFGCHIP1_CAP0SRC_MCASP0_RX CFGCHIP1_CAP0SRC(0x2) +#define CFGCHIP1_CAP0SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP0SRC(0x7) +#define CFGCHIP1_CAP0SRC_EMAC_C0_RX CFGCHIP1_CAP0SRC(0x8) +#define CFGCHIP1_CAP0SRC_EMAC_C0_TX CFGCHIP1_CAP0SRC(0x9) +#define CFGCHIP1_CAP0SRC_EMAC_C0_MISC CFGCHIP1_CAP0SRC(0xa) +#define CFGCHIP1_CAP0SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP0SRC(0xb) +#define CFGCHIP1_CAP0SRC_EMAC_C1_RX CFGCHIP1_CAP0SRC(0xc) +#define CFGCHIP1_CAP0SRC_EMAC_C1_TX CFGCHIP1_CAP0SRC(0xd) +#define CFGCHIP1_CAP0SRC_EMAC_C1_MISC CFGCHIP1_CAP0SRC(0xe) +#define CFGCHIP1_CAP0SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP0SRC(0xf) +#define CFGCHIP1_CAP0SRC_EMAC_C2_RX CFGCHIP1_CAP0SRC(0x10) +#define CFGCHIP1_CAP0SRC_EMAC_C2_TX CFGCHIP1_CAP0SRC(0x11) +#define CFGCHIP1_CAP0SRC_EMAC_C2_MISC CFGCHIP1_CAP0SRC(0x12) +#define CFGCHIP1_HPIBYTEAD BIT(16) +#define CFGCHIP1_HPIENA BIT(15) +#define CFGCHIP0_EDMA31TC0DBS(n) ((n) << 13) +#define CFGCHIP0_EDMA31TC0DBS_MASK CFGCHIP0_EDMA31TC0DBS(0x3) +#define CFGCHIP0_EDMA31TC0DBS_16 CFGCHIP0_EDMA31TC0DBS(0x0) +#define CFGCHIP0_EDMA31TC0DBS_32 CFGCHIP0_EDMA31TC0DBS(0x1) +#define CFGCHIP0_EDMA31TC0DBS_64 CFGCHIP0_EDMA31TC0DBS(0x2) +#define CFGCHIP1_TBCLKSYNC BIT(12) +#define CFGCHIP1_AMUTESEL0(n) ((n) << 0) +#define CFGCHIP1_AMUTESEL0_MASK CFGCHIP1_AMUTESEL0(0xf) +#define CFGCHIP1_AMUTESEL0_LOW CFGCHIP1_AMUTESEL0(0x0) +#define CFGCHIP1_AMUTESEL0_BANK_0 CFGCHIP1_AMUTESEL0(0x1) +#define CFGCHIP1_AMUTESEL0_BANK_1 CFGCHIP1_AMUTESEL0(0x2) +#define CFGCHIP1_AMUTESEL0_BANK_2 CFGCHIP1_AMUTESEL0(0x3) +#define CFGCHIP1_AMUTESEL0_BANK_3 CFGCHIP1_AMUTESEL0(0x4) +#define CFGCHIP1_AMUTESEL0_BANK_4 CFGCHIP1_AMUTESEL0(0x5) +#define CFGCHIP1_AMUTESEL0_BANK_5 CFGCHIP1_AMUTESEL0(0x6) +#define CFGCHIP1_AMUTESEL0_BANK_6 CFGCHIP1_AMUTESEL0(0x7) +#define CFGCHIP1_AMUTESEL0_BANK_7 CFGCHIP1_AMUTESEL0(0x8) + +/* CFGCHIP2 (USB PHY) register bits */ +#define CFGCHIP2_PHYCLKGD BIT(17) +#define CFGCHIP2_VBUSSENSE BIT(16) +#define CFGCHIP2_RESET BIT(15) +#define CFGCHIP2_OTGMODE(n) ((n) << 13) +#define CFGCHIP2_OTGMODE_MASK CFGCHIP2_OTGMODE(0x3) +#define CFGCHIP2_OTGMODE_NO_OVERRIDE CFGCHIP2_OTGMODE(0x0) +#define CFGCHIP2_OTGMODE_FORCE_HOST CFGCHIP2_OTGMODE(0x1) +#define CFGCHIP2_OTGMODE_FORCE_DEVICE CFGCHIP2_OTGMODE(0x2) +#define CFGCHIP2_OTGMODE_FORCE_HOST_VBUS_LOW CFGCHIP2_OTGMODE(0x3) +#define CFGCHIP2_USB1PHYCLKMUX BIT(12) +#define CFGCHIP2_USB2PHYCLKMUX BIT(11) +#define CFGCHIP2_PHYPWRDN BIT(10) +#define CFGCHIP2_OTGPWRDN BIT(9) +#define CFGCHIP2_DATPOL BIT(8) +#define CFGCHIP2_USB1SUSPENDM BIT(7) +#define CFGCHIP2_PHY_PLLON BIT(6) +#define CFGCHIP2_SESENDEN BIT(5) +#define CFGCHIP2_VBDTCTEN BIT(4) +#define CFGCHIP2_REFFREQ(n) ((n) << 0) +#define CFGCHIP2_REFFREQ_MASK CFGCHIP2_REFFREQ(0xf) +#define CFGCHIP2_REFFREQ_12MHZ CFGCHIP2_REFFREQ(0x1) +#define CFGCHIP2_REFFREQ_24MHZ CFGCHIP2_REFFREQ(0x2) +#define CFGCHIP2_REFFREQ_48MHZ CFGCHIP2_REFFREQ(0x3) +#define CFGCHIP2_REFFREQ_19_2MHZ CFGCHIP2_REFFREQ(0x4) +#define CFGCHIP2_REFFREQ_38_4MHZ CFGCHIP2_REFFREQ(0x5) +#define CFGCHIP2_REFFREQ_13MHZ CFGCHIP2_REFFREQ(0x6) +#define CFGCHIP2_REFFREQ_26MHZ CFGCHIP2_REFFREQ(0x7) +#define CFGCHIP2_REFFREQ_20MHZ CFGCHIP2_REFFREQ(0x8) +#define CFGCHIP2_REFFREQ_40MHZ CFGCHIP2_REFFREQ(0x9) + +/* CFGCHIP3 (EMAC/uPP/PLL1/ASYNC3/PRU/DIV4.5/EMIFA) register bits */ +#define CFGCHIP3_RMII_SEL BIT(8) +#define CFGCHIP3_UPP_TX_CLKSRC BIT(6) +#define CFGCHIP3_PLL1_MASTER_LOCK BIT(5) +#define CFGCHIP3_ASYNC3_CLKSRC BIT(4) +#define CFGCHIP3_PRUEVTSEL BIT(3) +#define CFGCHIP3_DIV45PENA BIT(2) +#define CFGCHIP3_EMA_CLKSRC BIT(1) + +/* CFGCHIP4 (McASP0 AMUNTEIN) register bits */ +#define CFGCHIP4_AMUTECLR0 BIT(0) + +#endif /* __LINUX_MFD_DA8XX_CFGCHIP_H */ -- cgit v1.2.3 From b2f0c09664b72b2f8c581383a9337ac3092e42c8 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 11 Jul 2016 13:50:01 +0200 Subject: iio: sw-trigger: Fix config group initialization Use the IS_ENABLED() helper macro to ensure that the configfs group is initialized either when configfs is built-in or when configfs is built as a module. Otherwise software trigger creation will result in undefined behaviour when configfs is built as a mdoule since the configfs group for the trigger is not properly initialized. Fixes: b662f809d410 ("iio: core: Introduce IIO software triggers") Signed-off-by: Lars-Peter Clausen Acked-by: Daniel Baluta Cc: Signed-off-by: Jonathan Cameron --- include/linux/iio/sw_trigger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/sw_trigger.h b/include/linux/iio/sw_trigger.h index 5198f8ed08a4..c97eab67558f 100644 --- a/include/linux/iio/sw_trigger.h +++ b/include/linux/iio/sw_trigger.h @@ -62,7 +62,7 @@ void iio_swt_group_init_type_name(struct iio_sw_trigger *t, const char *name, struct config_item_type *type) { -#ifdef CONFIG_CONFIGFS_FS +#if IS_ENABLED(CONFIG_CONFIGFS_FS) config_group_init_type_name(&t->group, name, type); #endif } -- cgit v1.2.3 From 7a665d2f60b457c0d77b3e4f01e21c55ffc57069 Mon Sep 17 00:00:00 2001 From: Daniel Verkamp Date: Tue, 28 Jun 2016 11:20:23 -0700 Subject: nvme-fabrics: change NQN UUID to big-endian format NVM Express 1.2.1 section 7.9, NVMe Qualified Names, specifies that the UUID format of NQN uses a UUID based on RFC 4122. RFC 4122 specifies that the UUID is encoded in big-endian byte order. Switch the NVMe over Fabrics host ID field from little-endian UUID to big-endian UUID to match the specification. Signed-off-by: Daniel Verkamp Reviewed-by: Jay Freyensee Signed-off-by: Sagi Grimberg --- include/linux/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index d8b37bab2887..7676557ce357 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -794,7 +794,7 @@ struct nvmf_connect_command { }; struct nvmf_connect_data { - uuid_le hostid; + uuid_be hostid; __le16 cntlid; char resv4[238]; char subsysnqn[NVMF_NQN_FIELD_LEN]; -- cgit v1.2.3 From c0678b2d6648ab65b68703044709e367799ba9f9 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 15 Aug 2016 15:52:23 -0700 Subject: include/linux: fix excess fence.h kernel-doc notation Fix excess fields in kernel-doc notation in after some struct fields were removed. Fixes these kernel-doc warnings: ..//include/linux/fence.h:85: warning: Excess struct/union/enum/typedef member 'child_list' description in 'fence' ..//include/linux/fence.h:85: warning: Excess struct/union/enum/typedef member 'active_list' description in 'fence' Fixes: 0431b9065f28 ("staging/android: bring struct sync_pt back") Cc: Daniel Vetter Cc: Sumit Semwal Cc: Luis de Bethencourt Signed-off-by: Randy Dunlap Reviewed-by: Gustavo Padovan Signed-off-by: Greg Kroah-Hartman --- include/linux/fence.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fence.h b/include/linux/fence.h index 8cc719a63728..2ac6fa5f4712 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -49,8 +49,6 @@ struct fence_cb; * @timestamp: Timestamp when the fence was signaled. * @status: Optional, only valid if < 0, must be set before calling * fence_signal, indicates that the fence has completed with an error. - * @child_list: list of children fences - * @active_list: list of active fences * * the flags member must be manipulated and read using the appropriate * atomic ops (bit_*), so taking the spinlock will not be needed most -- cgit v1.2.3 From 7175cce1c3f1d8c8840d2004f78f96a3904249b5 Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Wed, 17 Aug 2016 17:43:01 +0530 Subject: iio: adc: ti_am335x_adc: Increase timeout value waiting for ADC sample Now that open delay and sample delay for each channel is configurable via DT, the default IDLE_TIMEOUT value is not enough as this is calculated based on hardcoded macros. This results in driver returning EBUSY sometimes. Fix this by increasing the timeout value based on maximum value possible to open delay and sample delays for each channel. Fixes: 5dc11e810676e ("iio: adc: ti_am335x_adc: make sample delay, open delay, averaging DT parameters") Signed-off-by: Vignesh R Acked-by: Lee Jones Cc: Signed-off-by: Jonathan Cameron --- include/linux/mfd/ti_am335x_tscadc.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 2567a87872b0..7f55b8b41032 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -138,16 +138,16 @@ /* * time in us for processing a single channel, calculated as follows: * - * num cycles = open delay + (sample delay + conv time) * averaging + * max num cycles = open delay + (sample delay + conv time) * averaging * - * num cycles: 152 + (1 + 13) * 16 = 376 + * max num cycles: 262143 + (255 + 13) * 16 = 266431 * * clock frequency: 26MHz / 8 = 3.25MHz * clock period: 1 / 3.25MHz = 308ns * - * processing time: 376 * 308ns = 116us + * max processing time: 266431 * 308ns = 83ms(approx) */ -#define IDLE_TIMEOUT 116 /* microsec */ +#define IDLE_TIMEOUT 83 /* milliseconds */ #define TSCADC_CELLS 2 -- cgit v1.2.3 From 9ebf1945d757433a089ab3ee940673503e3e11ec Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 1 Aug 2016 07:29:34 -0300 Subject: [media] cec-funcs.h: fix typo: && should be & Fix typo where logical AND was used instead of bitwise AND. Reported-by: David Binderman Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec-funcs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h index 82c3d3b7269d..9e054aa168f3 100644 --- a/include/linux/cec-funcs.h +++ b/include/linux/cec-funcs.h @@ -227,7 +227,7 @@ static inline void cec_set_digital_service_id(__u8 *msg, if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) { *msg++ = (digital->channel.channel_number_fmt << 2) | (digital->channel.major >> 8); - *msg++ = digital->channel.major && 0xff; + *msg++ = digital->channel.major & 0xff; *msg++ = digital->channel.minor >> 8; *msg++ = digital->channel.minor & 0xff; *msg++ = 0; @@ -1277,7 +1277,7 @@ static inline void cec_msg_user_control_pressed(struct cec_msg *msg, msg->len += 4; msg->msg[3] = (ui_cmd->channel_identifier.channel_number_fmt << 2) | (ui_cmd->channel_identifier.major >> 8); - msg->msg[4] = ui_cmd->channel_identifier.major && 0xff; + msg->msg[4] = ui_cmd->channel_identifier.major & 0xff; msg->msg[5] = ui_cmd->channel_identifier.minor >> 8; msg->msg[6] = ui_cmd->channel_identifier.minor & 0xff; break; -- cgit v1.2.3 From 31dc8b7302f1e48952ec8e90cd49dca843146cd0 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 10 Aug 2016 08:01:38 -0300 Subject: [media] cec-funcs.h: add reply argument for Record On/Off A reply parameter is added to the cec_msg_record_on/off functions in cec-funcs.h. The standard mandates that Record Status shall be replied to Record On, and it may be replied to Record Off. Signed-off-by: Johan Fjeldtvedt Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec-funcs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h index 9e054aa168f3..8af613e67633 100644 --- a/include/linux/cec-funcs.h +++ b/include/linux/cec-funcs.h @@ -162,10 +162,11 @@ static inline void cec_msg_standby(struct cec_msg *msg) /* One Touch Record Feature */ -static inline void cec_msg_record_off(struct cec_msg *msg) +static inline void cec_msg_record_off(struct cec_msg *msg, bool reply) { msg->len = 2; msg->msg[1] = CEC_MSG_RECORD_OFF; + msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0; } struct cec_op_arib_data { @@ -323,6 +324,7 @@ static inline void cec_msg_record_on_phys_addr(struct cec_msg *msg, } static inline void cec_msg_record_on(struct cec_msg *msg, + bool reply, const struct cec_op_record_src *rec_src) { switch (rec_src->type) { @@ -346,6 +348,7 @@ static inline void cec_msg_record_on(struct cec_msg *msg, rec_src->ext_phys_addr.phys_addr); break; } + msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0; } static inline void cec_ops_record_on(const struct cec_msg *msg, -- cgit v1.2.3 From dcceb1eaf210096831b14471bc87678375b086ed Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 10 Aug 2016 09:24:45 -0300 Subject: [media] cec: add CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK flag Currently if none of the requested logical addresses can be claimed, the framework will fall back to the Unregistered logical address. Add a flag to enable this explicitly. By default it will just go back to the unconfigured state. Usually Unregistered is not something you want since the functionality is very limited. Unless the application has support for this, it will fail to work correctly. So require that the application explicitly requests this. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cec.h b/include/linux/cec.h index b3e22893a002..851968e803fa 100644 --- a/include/linux/cec.h +++ b/include/linux/cec.h @@ -364,7 +364,7 @@ struct cec_caps { * @num_log_addrs: how many logical addresses should be claimed. Set by the * caller. * @vendor_id: the vendor ID of the device. Set by the caller. - * @flags: set to 0. + * @flags: flags. * @osd_name: the OSD name of the device. Set by the caller. * @primary_device_type: the primary device type for each logical address. * Set by the caller. @@ -389,6 +389,9 @@ struct cec_log_addrs { __u8 features[CEC_MAX_LOG_ADDRS][12]; }; +/* Allow a fallback to unregistered */ +#define CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK (1 << 0) + /* Events */ /* Event that occurs when the adapter state changes */ -- cgit v1.2.3 From 4808f721627c2a23b5d749f9bbd20d4529ea2b8d Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 20 Aug 2016 07:54:38 -0300 Subject: [media] cec-funcs.h: add missing vendor-specific messages The cec-funcs.h header was missing support for these three vendor-specific messages: CEC_MSG_VENDOR_COMMAND CEC_MSG_VENDOR_COMMAND_WITH_ID CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN Add wrappers for these messages. I originally postponed adding these wrappers due to the fact that the argument is just a byte array which cec-ctl couldn't handle at the time, and then I just forgot to add them once the CEC framework was finalized. It wasn't until an attempt to transmit a vendor specific command was made that I realized that these wrappers were missing. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec-funcs.h | 69 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h index 8af613e67633..138bbf721e70 100644 --- a/include/linux/cec-funcs.h +++ b/include/linux/cec-funcs.h @@ -1144,6 +1144,75 @@ static inline void cec_msg_give_device_vendor_id(struct cec_msg *msg, msg->reply = reply ? CEC_MSG_DEVICE_VENDOR_ID : 0; } +static inline void cec_msg_vendor_command(struct cec_msg *msg, + __u8 size, const __u8 *vendor_cmd) +{ + if (size > 14) + size = 14; + msg->len = 2 + size; + msg->msg[1] = CEC_MSG_VENDOR_COMMAND; + memcpy(msg->msg + 2, vendor_cmd, size); +} + +static inline void cec_ops_vendor_command(const struct cec_msg *msg, + __u8 *size, + const __u8 **vendor_cmd) +{ + *size = msg->len - 2; + + if (*size > 14) + *size = 14; + *vendor_cmd = msg->msg + 2; +} + +static inline void cec_msg_vendor_command_with_id(struct cec_msg *msg, + __u32 vendor_id, __u8 size, + const __u8 *vendor_cmd) +{ + if (size > 11) + size = 11; + msg->len = 5 + size; + msg->msg[1] = CEC_MSG_VENDOR_COMMAND_WITH_ID; + msg->msg[2] = vendor_id >> 16; + msg->msg[3] = (vendor_id >> 8) & 0xff; + msg->msg[4] = vendor_id & 0xff; + memcpy(msg->msg + 5, vendor_cmd, size); +} + +static inline void cec_ops_vendor_command_with_id(const struct cec_msg *msg, + __u32 *vendor_id, __u8 *size, + const __u8 **vendor_cmd) +{ + *size = msg->len - 5; + + if (*size > 11) + *size = 11; + *vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4]; + *vendor_cmd = msg->msg + 5; +} + +static inline void cec_msg_vendor_remote_button_down(struct cec_msg *msg, + __u8 size, + const __u8 *rc_code) +{ + if (size > 14) + size = 14; + msg->len = 2 + size; + msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN; + memcpy(msg->msg + 2, rc_code, size); +} + +static inline void cec_ops_vendor_remote_button_down(const struct cec_msg *msg, + __u8 *size, + const __u8 **rc_code) +{ + *size = msg->len - 2; + + if (*size > 14) + *size = 14; + *rc_code = msg->msg + 2; +} + static inline void cec_msg_vendor_remote_button_up(struct cec_msg *msg) { msg->len = 2; -- cgit v1.2.3 From 17de0a9ff3df8f54f2f47746d118112d4e61d973 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Aug 2016 11:33:58 +1000 Subject: iomap: don't set FIEMAP_EXTENT_MERGED for extent based filesystems Filesystems like XFS that use extents should not set the FIEMAP_EXTENT_MERGED flag in the fiemap extent structures. To allow for both behaviors for the upcoming gfs2 usage split the iomap type field into type and flags, and only set FIEMAP_EXTENT_MERGED if the IOMAP_F_MERGED flag is set. The flags field will also come in handy for future features such as shared extents on reflink-enabled file systems. Reported-by: Andreas Gruenbacher Signed-off-by: Christoph Hellwig Acked-by: Darrick J. Wong Signed-off-by: Dave Chinner --- include/linux/iomap.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 3267df461012..3d70ece10313 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -18,6 +18,11 @@ struct vm_fault; #define IOMAP_MAPPED 0x03 /* blocks allocated @blkno */ #define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */ +/* + * Flags for iomap mappings: + */ +#define IOMAP_F_MERGED 0x01 /* contains multiple blocks/extents */ + /* * Magic value for blkno: */ @@ -27,7 +32,8 @@ struct iomap { sector_t blkno; /* 1st sector of mapping, 512b units */ loff_t offset; /* file offset of mapping, bytes */ u64 length; /* length of mapping, bytes */ - int type; /* type of mapping */ + u16 type; /* type of mapping */ + u16 flags; /* flags for mapping */ struct block_device *bdev; /* block device for I/O */ }; -- cgit v1.2.3 From 0d025d271e55f3de21f0aaaf54b42d20404d2b23 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 30 Aug 2016 08:04:16 -0500 Subject: mm/usercopy: get rid of CONFIG_DEBUG_STRICT_USER_COPY_CHECKS There are three usercopy warnings which are currently being silenced for gcc 4.6 and newer: 1) "copy_from_user() buffer size is too small" compile warning/error This is a static warning which happens when object size and copy size are both const, and copy size > object size. I didn't see any false positives for this one. So the function warning attribute seems to be working fine here. Note this scenario is always a bug and so I think it should be changed to *always* be an error, regardless of CONFIG_DEBUG_STRICT_USER_COPY_CHECKS. 2) "copy_from_user() buffer size is not provably correct" compile warning This is another static warning which happens when I enable __compiletime_object_size() for new compilers (and CONFIG_DEBUG_STRICT_USER_COPY_CHECKS). It happens when object size is const, but copy size is *not*. In this case there's no way to compare the two at build time, so it gives the warning. (Note the warning is a byproduct of the fact that gcc has no way of knowing whether the overflow function will be called, so the call isn't dead code and the warning attribute is activated.) So this warning seems to only indicate "this is an unusual pattern, maybe you should check it out" rather than "this is a bug". I get 102(!) of these warnings with allyesconfig and the __compiletime_object_size() gcc check removed. I don't know if there are any real bugs hiding in there, but from looking at a small sample, I didn't see any. According to Kees, it does sometimes find real bugs. But the false positive rate seems high. 3) "Buffer overflow detected" runtime warning This is a runtime warning where object size is const, and copy size > object size. All three warnings (both static and runtime) were completely disabled for gcc 4.6 with the following commit: 2fb0815c9ee6 ("gcc4: disable __compiletime_object_size for GCC 4.6+") That commit mistakenly assumed that the false positives were caused by a gcc bug in __compiletime_object_size(). But in fact, __compiletime_object_size() seems to be working fine. The false positives were instead triggered by #2 above. (Though I don't have an explanation for why the warnings supposedly only started showing up in gcc 4.6.) So remove warning #2 to get rid of all the false positives, and re-enable warnings #1 and #3 by reverting the above commit. Furthermore, since #1 is a real bug which is detected at compile time, upgrade it to always be an error. Having done all that, CONFIG_DEBUG_STRICT_USER_COPY_CHECKS is no longer needed. Signed-off-by: Josh Poimboeuf Cc: Kees Cook Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H . Peter Anvin" Cc: Andy Lutomirski Cc: Steven Rostedt Cc: Brian Gerst Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: Byungchul Park Cc: Nilay Vaish Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 8dbc8929a6a0..573c5a18908f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -158,7 +158,7 @@ #define __compiler_offsetof(a, b) \ __builtin_offsetof(a, b) -#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 +#if GCC_VERSION >= 40100 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #endif -- cgit v1.2.3 From 5db4f7f80d165fc9725f356e99feec409e446baa Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 16 Aug 2016 15:06:54 +0300 Subject: Revert "tty/serial/8250: use mctrl_gpio helpers" Serial console is broken in v4.8-rcX. Mika and I independently bisected down to commit 4ef03d328769 ("tty/serial/8250: use mctrl_gpio helpers"). Since neither author nor anyone else didn't propose a solution we better revert it for now. This reverts commit 4ef03d328769eddbfeca1f1c958fdb181a69c341. Link: https://lkml.kernel.org/r/20160809130229.GN1729@lahna.fi.intel.com Signed-off-by: Andy Shevchenko Tested-by: Heikki Krogerus Tested-by: Mika Westerberg Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 923266cd294a..48ec7651989b 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -111,7 +111,6 @@ struct uart_8250_port { * if no_console_suspend */ unsigned char probe; - struct mctrl_gpios *gpios; #define UART_PROBE_RSA (1 << 0) /* -- cgit v1.2.3 From cd81a9170e69e018bbaba547c1fd85a585f5697a Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Tue, 23 Aug 2016 16:20:38 +0200 Subject: mm: introduce get_task_exe_file For more convenient access if one has a pointer to the task. As a minor nit take advantage of the fact that only task lock + rcu are needed to safely grab ->exe_file. This saves mm refcount dance. Use the helper in proc_exe_link. Signed-off-by: Mateusz Guzik Acked-by: Konstantin Khlebnikov Acked-by: Richard Guy Briggs Cc: # 4.3.x Signed-off-by: Paul Moore --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8f468e0d2534..004c73a988b7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1987,6 +1987,7 @@ extern void mm_drop_all_locks(struct mm_struct *mm); extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); +extern struct file *get_task_exe_file(struct task_struct *task); extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); -- cgit v1.2.3 From 2a3a2a3f35249412e35fbb48b743348c40373409 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 1 Sep 2016 11:11:59 +0200 Subject: ovl: don't cache acl on overlay layer Some operations (setxattr/chmod) can make the cached acl stale. We either need to clear overlay's acl cache for the affected inode or prevent acl caching on the overlay altogether. Preventing caching has the following advantages: - no double caching, less memory used - overlay cache doesn't go stale when fs clears it's own cache Possible disadvantage is performance loss. If that becomes a problem get_acl() can be optimized for overlayfs. This patch disables caching by pre setting i_*acl to a value that - has bit 0 set, so is_uncached_acl() will return true - is not equal to ACL_NOT_CACHED, so get_acl() will not overwrite it The constant -3 was chosen for this purpose. Fixes: 39a25b2b3762 ("ovl: define ->get_acl() for overlay inodes") Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3523bf62f328..901e25d495cc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -574,6 +574,7 @@ static inline void mapping_allow_writable(struct address_space *mapping) struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) +#define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) -- cgit v1.2.3 From 6aa303defb7454a2520c4ddcdf6b081f62a15890 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 1 Sep 2016 16:14:55 -0700 Subject: mm, vmscan: only allocate and reclaim from zones with pages managed by the buddy allocator Firmware Assisted Dump (FA_DUMP) on ppc64 reserves substantial amounts of memory when booting a secondary kernel. Srikar Dronamraju reported that multiple nodes may have no memory managed by the buddy allocator but still return true for populated_zone(). Commit 1d82de618ddd ("mm, vmscan: make kswapd reclaim in terms of nodes") was reported to cause kswapd to spin at 100% CPU usage when fadump was enabled. The old code happened to deal with the situation of a populated node with zero free pages by co-incidence but the current code tries to reclaim populated zones without realising that is impossible. We cannot just convert populated_zone() as many existing users really need to check for present_pages. This patch introduces a managed_zone() helper and uses it in the few cases where it is critical that the check is made for managed pages -- zonelist construction and page reclaim. Link: http://lkml.kernel.org/r/20160831195104.GB8119@techsingularity.net Signed-off-by: Mel Gorman Reported-by: Srikar Dronamraju Tested-by: Srikar Dronamraju Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d572b78b65e1..7f2ae99e5daf 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -828,9 +828,21 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) -static inline int populated_zone(struct zone *zone) +/* + * Returns true if a zone has pages managed by the buddy allocator. + * All the reclaim decisions have to use this function rather than + * populated_zone(). If the whole zone is reserved then we can easily + * end up with populated_zone() && !managed_zone(). + */ +static inline bool managed_zone(struct zone *zone) +{ + return zone->managed_pages; +} + +/* Returns true if a zone has memory */ +static inline bool populated_zone(struct zone *zone) { - return (!!zone->present_pages); + return zone->present_pages; } extern int movable_zone; -- cgit v1.2.3 From 7e932159901183283cd82d797bc9a7c681e48e9c Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 1 Sep 2016 16:15:01 -0700 Subject: treewide: remove references to the now unnecessary DEFINE_PCI_DEVICE_TABLE It's been eliminated from the sources, remove it from everywhere else. Link: http://lkml.kernel.org/r/076eff466fd7edb550c25c8b25d76924ca0eba62.1472660229.git.joe@perches.com Signed-off-by: Joe Perches Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Bjorn Helgaas Cc: Andy Whitcroft Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index fbc1fa625c3e..0ab835965669 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -682,15 +682,6 @@ struct pci_driver { #define to_pci_driver(drv) container_of(drv, struct pci_driver, driver) -/** - * DEFINE_PCI_DEVICE_TABLE - macro used to describe a pci device table - * @_table: device table name - * - * This macro is deprecated and should not be used in new code. - */ -#define DEFINE_PCI_DEVICE_TABLE(_table) \ - const struct pci_device_id _table[] - /** * PCI_DEVICE - macro used to describe a specific pci device * @vend: the 16 bit PCI Vendor ID -- cgit v1.2.3 From c11600e4fed67ae4cd6a8096936afd445410e8ed Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 1 Sep 2016 16:15:07 -0700 Subject: mm, mempolicy: task->mempolicy must be NULL before dropping final reference KASAN allocates memory from the page allocator as part of kmem_cache_free(), and that can reference current->mempolicy through any number of allocation functions. It needs to be NULL'd out before the final reference is dropped to prevent a use-after-free bug: BUG: KASAN: use-after-free in alloc_pages_current+0x363/0x370 at addr ffff88010b48102c CPU: 0 PID: 15425 Comm: trinity-c2 Not tainted 4.8.0-rc2+ #140 ... Call Trace: dump_stack kasan_object_err kasan_report_error __asan_report_load2_noabort alloc_pages_current <-- use after free depot_save_stack save_stack kasan_slab_free kmem_cache_free __mpol_put <-- free do_exit This patch sets current->mempolicy to NULL before dropping the final reference. Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1608301442180.63329@chino.kir.corp.google.com Fixes: cd11016e5f52 ("mm, kasan: stackdepot implementation. Enable stackdepot for SLAB") Signed-off-by: David Rientjes Reported-by: Vegard Nossum Acked-by: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: [4.6+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 4429d255c8ab..5e5b2969d931 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -195,6 +195,7 @@ static inline bool vma_migratable(struct vm_area_struct *vma) } extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); +extern void mpol_put_task_policy(struct task_struct *); #else @@ -297,5 +298,8 @@ static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma, return -1; /* no node preference */ } +static inline void mpol_put_task_policy(struct task_struct *task) +{ +} #endif /* CONFIG_NUMA */ #endif -- cgit v1.2.3 From 3feab13c919f99b0a17d0ca22ae00cf90f5d3fd1 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 16 Aug 2016 16:59:52 +0100 Subject: ACPI / drivers: fix typo in ACPI_DECLARE_PROBE_ENTRY macro When the ACPI_DECLARE_PROBE_ENTRY macro was added in commit e647b532275b ("ACPI: Add early device probing infrastructure"), a stub macro adding an unused entry was added for the !CONFIG_ACPI Kconfig option case to make sure kernel code making use of the macro did not require to be guarded within CONFIG_ACPI in order to be compiled. The stub macro was never used since all kernel code that defines ACPI_DECLARE_PROBE_ENTRY entries is currently guarded within CONFIG_ACPI; it contains a typo that should be nonetheless fixed. Fix the typo in the stub (ie !CONFIG_ACPI) ACPI_DECLARE_PROBE_ENTRY() macro so that it can actually be used if needed. Signed-off-by: Lorenzo Pieralisi Fixes: e647b532275b (ACPI: Add early device probing infrastructure) Cc: 4.4+ # 4.4+ Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 4d8452c2384b..c5eaf2f80a4c 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1056,7 +1056,7 @@ static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev, return NULL; } -#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, validate, data, fn) \ +#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ static const void * __acpi_table_##name[] \ __attribute__((unused)) \ = { (void *) table_id, \ -- cgit v1.2.3 From 3f37ec79dd21fbdbbab8143a48a87272b22fef22 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Mon, 25 Jul 2016 20:33:56 +0200 Subject: bcma: support BCM53573 series of wireless SoCs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit BCM53573 seems to be the first series of Northstar family with wireless on the chip. The base models are BCM53573-s (A0, A1) and there is also BCM47189B0 which seems to be some small modification. The only problem with these chipsets seems to be watchdog. It's totally unavailable on 53573A0 / 53573A1 and preferable PMU watchdog is broken on 53573B0 / 53573B1. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 3db25df396cb..8eeedb2db924 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -205,6 +205,9 @@ struct bcma_host_ops { #define BCMA_PKG_ID_BCM4709 0 #define BCMA_CHIP_ID_BCM47094 53030 #define BCMA_CHIP_ID_BCM53018 53018 +#define BCMA_CHIP_ID_BCM53573 53573 +#define BCMA_PKG_ID_BCM53573 0 +#define BCMA_PKG_ID_BCM47189 1 /* Board types (on PCI usually equals to the subsystem dev id) */ /* BCM4313 */ -- cgit v1.2.3 From 24b27fc4cdf9e10c5e79e5923b6b7c2c5c95096c Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Thu, 1 Sep 2016 22:18:34 -0700 Subject: bonding: Fix bonding crash Following few steps will crash kernel - (a) Create bonding master > modprobe bonding miimon=50 (b) Create macvlan bridge on eth2 > ip link add link eth2 dev mvl0 address aa:0:0:0:0:01 \ type macvlan (c) Now try adding eth2 into the bond > echo +eth2 > /sys/class/net/bond0/bonding/slaves Bonding does lots of things before checking if the device enslaved is busy or not. In this case when the notifier call-chain sends notifications, the bond_netdev_event() assumes that the rx_handler /rx_handler_data is registered while the bond_enslave() hasn't progressed far enough to register rx_handler for the new slave. This patch adds a rx_handler check that can be performed right at the beginning of the enslave code to avoid getting into this situation. Signed-off-by: Mahesh Bandewar Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3a788bf0affd..e8d79d4ebcfe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3267,6 +3267,7 @@ static inline void napi_free_frags(struct napi_struct *napi) napi->skb = NULL; } +bool netdev_is_rx_handler_busy(struct net_device *dev); int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data); -- cgit v1.2.3 From d7127b5e5fa0551be21b86640f1648b224e36d43 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 26 Aug 2016 08:16:00 +0200 Subject: locking/barriers: Don't use sizeof(void) in lockless_dereference() My previous commit: 112dc0c8069e ("locking/barriers: Suppress sparse warnings in lockless_dereference()") caused sparse to complain that (in radix-tree.h) we use sizeof(void) since that rcu_dereference()s a void *. Really, all we need is to have the expression *p in here somewhere to make sure p is a pointer type, and sizeof(*p) was the thing that came to my mind first to make sure that's done without really doing anything at runtime. Another thing I had considered was using typeof(*p), but obviously we can't just declare a typeof(*p) variable either, since that may end up being void. Declaring a variable as typeof(*p)* gets around that, and still checks that typeof(*p) is valid, so do that. This type construction can't be done for _________p1 because that will actually be used and causes sparse address space warnings, so keep a separate unused variable for it. Reported-by: Fengguang Wu Signed-off-by: Johannes Berg Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Paul E . McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kbuild-all@01.org Fixes: 112dc0c8069e ("locking/barriers: Suppress sparse warnings in lockless_dereference()") Link: http://lkml.kernel.org/r/1472192160-4049-1-git-send-email-johannes@sipsolutions.net Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 436aa4e42221..668569844d37 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -527,13 +527,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * object's lifetime is managed by something other than RCU. That * "something other" might be reference counting or simple immortality. * - * The seemingly unused size_t variable is to validate @p is indeed a pointer - * type by making sure it can be dereferenced. + * The seemingly unused variable ___typecheck_p validates that @p is + * indeed a pointer type by using a pointer to typeof(*p) as the type. + * Taking a pointer to typeof(*p) again is needed in case p is void *. */ #define lockless_dereference(p) \ ({ \ typeof(p) _________p1 = READ_ONCE(p); \ - size_t __maybe_unused __size_of_ptr = sizeof(*(p)); \ + typeof(*(p)) *___typecheck_p __maybe_unused; \ smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ (_________p1); \ }) -- cgit v1.2.3 From d4c4fed08f31f3746000c46cb1b20bed2959547a Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 15 Aug 2016 09:05:45 -0600 Subject: efi: Make for_each_efi_memory_desc_in_map() cope with running on Xen While commit 55f1ea15216 ("efi: Fix for_each_efi_memory_desc_in_map() for empty memmaps") made an attempt to deal with empty memory maps, it didn't address the case where the map field never gets set, as is apparently the case when running under Xen. Reported-by: Tested-by: Cc: Vitaly Kuznetsov Cc: Jiri Slaby Cc: Mark Rutland Cc: # v4.7+ Signed-off-by: Jan Beulich [ Guard the loop with a NULL check instead of pointer underflow ] Signed-off-by: Matt Fleming --- include/linux/efi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 7f5a58225385..23cd3ced8c1a 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -946,7 +946,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm, /* Iterate through an efi_memory_map */ #define for_each_efi_memory_desc_in_map(m, md) \ for ((md) = (m)->map; \ - ((void *)(md) + (m)->desc_size) <= (m)->map_end; \ + (md) && ((void *)(md) + (m)->desc_size) <= (m)->map_end; \ (md) = (void *)(md) + (m)->desc_size) /** -- cgit v1.2.3 From dadb57abc37499f565b23933dbf49b435c3ba8af Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Mon, 29 Aug 2016 14:38:51 -0600 Subject: efi/libstub: Allocate headspace in efi_get_memory_map() efi_get_memory_map() allocates a buffer to store the memory map that it retrieves. This buffer may need to be reused by the client after ExitBootServices() is called, at which point allocations are not longer permitted. To support this usecase, provide the allocated buffer size back to the client, and allocate some additional headroom to account for any reasonable growth in the map that is likely to happen between the call to efi_get_memory_map() and the client reusing the buffer. Signed-off-by: Jeffrey Hugo Cc: Ard Biesheuvel Cc: Mark Rutland Cc: Leif Lindholm Cc: Ingo Molnar Cc: Signed-off-by: Matt Fleming --- include/linux/efi.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 23cd3ced8c1a..943fee524176 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -118,6 +118,15 @@ typedef struct { u32 imagesize; } efi_capsule_header_t; +struct efi_boot_memmap { + efi_memory_desc_t **map; + unsigned long *map_size; + unsigned long *desc_size; + u32 *desc_ver; + unsigned long *key_ptr; + unsigned long *buff_size; +}; + /* * EFI capsule flags */ @@ -1371,11 +1380,7 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, efi_loaded_image_t *image, int *cmd_line_len); efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, - efi_memory_desc_t **map, - unsigned long *map_size, - unsigned long *desc_size, - u32 *desc_ver, - unsigned long *key_ptr); + struct efi_boot_memmap *map); efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, -- cgit v1.2.3 From fc07716ba803483be91bc4b2344f9c84985e6f07 Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Mon, 29 Aug 2016 14:38:52 -0600 Subject: efi/libstub: Introduce ExitBootServices helper The spec allows ExitBootServices to fail with EFI_INVALID_PARAMETER if a race condition has occurred where the EFI has updated the memory map after the stub grabbed a reference to the map. The spec defines a retry proceedure with specific requirements to handle this scenario. This scenario was previously observed on x86 - commit d3768d885c6c ("x86, efi: retry ExitBootServices() on failure") but the current fix is not spec compliant and the scenario is now observed on the Qualcomm Technologies QDF2432 via the FDT stub which does not handle the error and thus causes boot failures. The user will notice the boot failure as the kernel is not executed and the system may drop back to a UEFI shell, but will be unresponsive to input and the system will require a power cycle to recover. Add a helper to the stub library that correctly adheres to the spec in the case of EFI_INVALID_PARAMETER from ExitBootServices and can be universally used across all stub implementations. Signed-off-by: Jeffrey Hugo Cc: Ard Biesheuvel Cc: Mark Rutland Cc: Leif Lindholm Cc: Ingo Molnar Cc: Signed-off-by: Matt Fleming --- include/linux/efi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 943fee524176..0148a3046b48 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1462,4 +1462,14 @@ extern void efi_call_virt_check_flags(unsigned long flags, const char *call); arch_efi_call_virt_teardown(); \ }) +typedef efi_status_t (*efi_exit_boot_map_processing)( + efi_system_table_t *sys_table_arg, + struct efi_boot_memmap *map, + void *priv); + +efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table, + void *handle, + struct efi_boot_memmap *map, + void *priv, + efi_exit_boot_map_processing priv_func); #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 81409e9e28058811c9ea865345e1753f8f677e44 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 31 Aug 2016 16:04:21 -0700 Subject: usercopy: fold builtin_const check into inline function Instead of having each caller of check_object_size() need to remember to check for a const size parameter, move the check into check_object_size() itself. This actually matches the original implementation in PaX, though this commit cleans up the now-redundant builtin_const() calls in the various architectures. Signed-off-by: Kees Cook --- include/linux/thread_info.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index cbd8990e2e77..10c9e601398b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -121,7 +121,8 @@ extern void __check_object_size(const void *ptr, unsigned long n, static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { - __check_object_size(ptr, n, to_user); + if (!__builtin_constant_p(n)) + __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, -- cgit v1.2.3 From a85d6b8242dc78ef3f4542a0f979aebcbe77fc4e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 7 Sep 2016 09:39:32 -0700 Subject: usercopy: force check_object_size() inline Just for good measure, make sure that check_object_size() is always inlined too, as already done for copy_*_user() and __copy_*_user(). Suggested-by: Linus Torvalds Signed-off-by: Kees Cook --- include/linux/thread_info.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 10c9e601398b..2b5b10eed74f 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -118,8 +118,8 @@ static inline int arch_within_stack_frames(const void * const stack, extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); -static inline void check_object_size(const void *ptr, unsigned long n, - bool to_user) +static __always_inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); -- cgit v1.2.3 From c965db44462919f613973aa618271f6c3f5a1e64 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Wed, 7 Sep 2016 16:36:24 +0300 Subject: qed: Add support for debug data collection This patch adds the support for dumping and formatting the HW/FW debug data. Signed-off-by: Tomer Tayar Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 70b30e4d3cc4..19027635df0d 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -143,6 +143,9 @@ #define GTT_BYTE_SIZE_BITS (GTT_DWORD_SIZE_BITS + 2) #define GTT_DWORD_SIZE BIT(GTT_DWORD_SIZE_BITS) +/* Tools Version */ +#define TOOLS_VERSION 10 + /*****************/ /* CDU CONSTANTS */ /*****************/ -- cgit v1.2.3 From e0971c832af4cd906ab931c9f6e9e1791a62fc98 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Wed, 7 Sep 2016 16:36:25 +0300 Subject: qed*: Add support for the ethtool get_regs operation Signed-off-by: Tomer Tayar Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index d8dc5c2243d5..e4546abcea08 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -455,6 +455,10 @@ struct qed_common_ops { void (*simd_handler_clean)(struct qed_dev *cdev, int index); + int (*dbg_all_data) (struct qed_dev *cdev, void *buffer); + + int (*dbg_all_data_size) (struct qed_dev *cdev); + /** * @brief can_link_change - can the instance change the link or not * -- cgit v1.2.3 From d545caca827b65aab557a9e9dcdcf1e5a3823c2d Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Thu, 8 Sep 2016 00:42:25 +0900 Subject: net: inet: diag: expose the socket mark to privileged processes. This adds the capability for a process that has CAP_NET_ADMIN on a socket to see the socket mark in socket dumps. Commit a52e95abf772 ("net: diag: allow socket bytecode filters to match socket marks") recently gave privileged processes the ability to filter socket dumps based on mark. This patch is complementary: it ensures that the mark is also passed to userspace in the socket's netlink attributes. It is useful for tools like ss which display information about sockets. Tested: https://android-review.googlesource.com/270210 Signed-off-by: Lorenzo Colitti Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index feb04ea20f11..65da430e260f 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -37,7 +37,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 pid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh); + const struct nlmsghdr *unlh, bool net_admin); void inet_diag_dump_icsk(struct inet_hashinfo *h, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, @@ -56,7 +56,7 @@ void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk); int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, - struct user_namespace *user_ns); + struct user_namespace *user_ns, bool net_admin); extern int inet_diag_register(const struct inet_diag_handler *handler); extern void inet_diag_unregister(const struct inet_diag_handler *handler); -- cgit v1.2.3 From e7e31ca43d6bedf1c551b1f9c7e78d51c9a45790 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Wed, 7 Sep 2016 19:07:58 +0300 Subject: net/mlx5e: Move an_disable_cap bit to a new position Previous an_disable_cap position bit31 is deprecated to be use in driver with newer firmware. New firmware will advertise the same capability in bit29. Old capability didn't allow setting more than one protocol for a specific speed when autoneg is off, while newer firmware will allow this and it is indicated in the new capability location. Signed-off-by: Bodong Wang Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 21bc4557b67a..d1f9a581aca8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -6710,9 +6710,10 @@ struct mlx5_ifc_pude_reg_bits { }; struct mlx5_ifc_ptys_reg_bits { - u8 an_disable_cap[0x1]; + u8 reserved_at_0[0x1]; u8 an_disable_admin[0x1]; - u8 reserved_at_2[0x6]; + u8 an_disable_cap[0x1]; + u8 reserved_at_3[0x5]; u8 local_port[0x8]; u8 reserved_at_10[0xd]; u8 proto_mask[0x3]; -- cgit v1.2.3 From fe19c4f971a55cea3be442d8032a5f6021702791 Mon Sep 17 00:00:00 2001 From: Eric Garver Date: Wed, 7 Sep 2016 12:56:58 -0400 Subject: vlan: Check for vlan ethernet types for 8021.q or 802.1ad This is to simplify using double tagged vlans. This function allows all valid vlan ethertypes to be checked in a single function call. Also replace some instances that check for both ETH_P_8021Q and ETH_P_8021AD. Patch based on one originally by Thomas F Herbert. Signed-off-by: Thomas F Herbert Signed-off-by: Eric Garver Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 49d4aef1f789..3319d97d789d 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -272,6 +272,23 @@ static inline int vlan_get_encap_level(struct net_device *dev) } #endif +/** + * eth_type_vlan - check for valid vlan ether type. + * @ethertype: ether type to check + * + * Returns true if the ether type is a vlan ether type. + */ +static inline bool eth_type_vlan(__be16 ethertype) +{ + switch (ethertype) { + case htons(ETH_P_8021Q): + case htons(ETH_P_8021AD): + return true; + default: + return false; + } +} + static inline bool vlan_hw_offload_capable(netdev_features_t features, __be16 proto) { @@ -425,8 +442,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb->data; - if (veth->h_vlan_proto != htons(ETH_P_8021Q) && - veth->h_vlan_proto != htons(ETH_P_8021AD)) + if (!eth_type_vlan(veth->h_vlan_proto)) return -EINVAL; *vlan_tci = ntohs(veth->h_vlan_TCI); @@ -488,7 +504,7 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, * present at mac_len - VLAN_HLEN (if mac_len > 0), or at * ETH_HLEN otherwise */ - if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { + if (eth_type_vlan(type)) { if (vlan_depth) { if (WARN_ON(vlan_depth < VLAN_HLEN)) return 0; @@ -506,8 +522,7 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, vh = (struct vlan_hdr *)(skb->data + vlan_depth); type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; - } while (type == htons(ETH_P_8021Q) || - type == htons(ETH_P_8021AD)); + } while (eth_type_vlan(type)); } if (depth) @@ -572,8 +587,7 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, static inline bool skb_vlan_tagged(const struct sk_buff *skb) { if (!skb_vlan_tag_present(skb) && - likely(skb->protocol != htons(ETH_P_8021Q) && - skb->protocol != htons(ETH_P_8021AD))) + likely(!eth_type_vlan(skb->protocol))) return false; return true; @@ -593,15 +607,14 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) if (!skb_vlan_tag_present(skb)) { struct vlan_ethhdr *veh; - if (likely(protocol != htons(ETH_P_8021Q) && - protocol != htons(ETH_P_8021AD))) + if (likely(!eth_type_vlan(protocol))) return false; veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } - if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) + if (!eth_type_vlan(protocol)) return false; return true; -- cgit v1.2.3 From 9f5afeae51526b3ad7b7cb21ee8b145ce6ea7a7a Mon Sep 17 00:00:00 2001 From: Yaogong Wang Date: Wed, 7 Sep 2016 14:49:28 -0700 Subject: tcp: use an RB tree for ooo receive queue MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Over the years, TCP BDP has increased by several orders of magnitude, and some people are considering to reach the 2 Gbytes limit. Even with current window scale limit of 14, ~1 Gbytes maps to ~740,000 MSS. In presence of packet losses (or reorders), TCP stores incoming packets into an out of order queue, and number of skbs sitting there waiting for the missing packets to be received can be in the 10^5 range. Most packets are appended to the tail of this queue, and when packets can finally be transferred to receive queue, we scan the queue from its head. However, in presence of heavy losses, we might have to find an arbitrary point in this queue, involving a linear scan for every incoming packet, throwing away cpu caches. This patch converts it to a RB tree, to get bounded latencies. Yaogong wrote a preliminary patch about 2 years ago. Eric did the rebase, added ofo_last_skb cache, polishing and tests. Tested with network dropping between 1 and 10 % packets, with good success (about 30 % increase of throughput in stress tests) Next step would be to also use an RB tree for the write queue at sender side ;) Signed-off-by: Yaogong Wang Signed-off-by: Eric Dumazet Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Ilpo Järvinen Acked-By: Ilpo Järvinen Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ include/linux/tcp.h | 7 +++---- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cfb7219be665..4c5662f05bda 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2402,6 +2402,8 @@ static inline void __skb_queue_purge(struct sk_buff_head *list) kfree_skb(skb); } +void skb_rbtree_purge(struct rb_root *root); + void *netdev_alloc_frag(unsigned int fragsz); struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 7be9b1242354..c723a465125d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -281,10 +281,9 @@ struct tcp_sock { struct sk_buff* lost_skb_hint; struct sk_buff *retransmit_skb_hint; - /* OOO segments go in this list. Note that socket lock must be held, - * as we do not use sk_buff_head lock. - */ - struct sk_buff_head out_of_order_queue; + /* OOO segments go in this rbtree. Socket lock must be held. */ + struct rb_root out_of_order_queue; + struct sk_buff *ooo_last_skb; /* cache rb_last(out_of_order_queue) */ /* SACKs data, these 2 need to be together (see tcp_options_write) */ struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */ -- cgit v1.2.3 From 3e9b3112ec74f192eaab976c3889e34255cae940 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 31 Aug 2016 12:46:44 +0100 Subject: add basic register-field manipulation macros Common approach to accessing register fields is to define structures or sets of macros containing mask and shift pair. Operations on the register are then performed as follows: field = (reg >> shift) & mask; reg &= ~(mask << shift); reg |= (field & mask) << shift; Defining shift and mask separately is tedious. Ivo van Doorn came up with an idea of computing them at compilation time based on a single shifted mask (later refined by Felix) which can be used like this: #define REG_FIELD 0x000ff000 field = FIELD_GET(REG_FIELD, reg); reg &= ~REG_FIELD; reg |= FIELD_PREP(REG_FIELD, field); FIELD_{GET,PREP} macros take care of finding out what the appropriate shift is based on compilation time ffs operation. GENMASK can be used to define registers (which is usually less error-prone and easier to match with datasheets). This approach is the most convenient I've seen so to limit code multiplication let's move the macros to a global header file. Attempts to use static inlines instead of macros failed due to false positive triggering of BUILD_BUG_ON()s, especially with GCC < 6.0. Signed-off-by: Jakub Kicinski Reviewed-by: Dinan Gunawardena Signed-off-by: Kalle Valo --- include/linux/bitfield.h | 93 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/bug.h | 3 ++ 2 files changed, 96 insertions(+) create mode 100644 include/linux/bitfield.h (limited to 'include/linux') diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h new file mode 100644 index 000000000000..f6505d83069d --- /dev/null +++ b/include/linux/bitfield.h @@ -0,0 +1,93 @@ +/* + * Copyright (C) 2014 Felix Fietkau + * Copyright (C) 2004 - 2009 Ivo van Doorn + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_BITFIELD_H +#define _LINUX_BITFIELD_H + +#include + +/* + * Bitfield access macros + * + * FIELD_{GET,PREP} macros take as first parameter shifted mask + * from which they extract the base mask and shift amount. + * Mask must be a compilation time constant. + * + * Example: + * + * #define REG_FIELD_A GENMASK(6, 0) + * #define REG_FIELD_B BIT(7) + * #define REG_FIELD_C GENMASK(15, 8) + * #define REG_FIELD_D GENMASK(31, 16) + * + * Get: + * a = FIELD_GET(REG_FIELD_A, reg); + * b = FIELD_GET(REG_FIELD_B, reg); + * + * Set: + * reg = FIELD_PREP(REG_FIELD_A, 1) | + * FIELD_PREP(REG_FIELD_B, 0) | + * FIELD_PREP(REG_FIELD_C, c) | + * FIELD_PREP(REG_FIELD_D, 0x40); + * + * Modify: + * reg &= ~REG_FIELD_C; + * reg |= FIELD_PREP(REG_FIELD_C, c); + */ + +#define __bf_shf(x) (__builtin_ffsll(x) - 1) + +#define __BF_FIELD_CHECK(_mask, _reg, _val, _pfx) \ + ({ \ + BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask), \ + _pfx "mask is not constant"); \ + BUILD_BUG_ON_MSG(!(_mask), _pfx "mask is zero"); \ + BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ? \ + ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \ + _pfx "value too large for the field"); \ + BUILD_BUG_ON_MSG((_mask) > (typeof(_reg))~0ull, \ + _pfx "type of reg too small for mask"); \ + __BUILD_BUG_ON_NOT_POWER_OF_2((_mask) + \ + (1ULL << __bf_shf(_mask))); \ + }) + +/** + * FIELD_PREP() - prepare a bitfield element + * @_mask: shifted mask defining the field's length and position + * @_val: value to put in the field + * + * FIELD_PREP() masks and shifts up the value. The result should + * be combined with other fields of the bitfield using logical OR. + */ +#define FIELD_PREP(_mask, _val) \ + ({ \ + __BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_PREP: "); \ + ((typeof(_mask))(_val) << __bf_shf(_mask)) & (_mask); \ + }) + +/** + * FIELD_GET() - extract a bitfield element + * @_mask: shifted mask defining the field's length and position + * @_reg: 32bit value of entire bitfield + * + * FIELD_GET() extracts the field specified by @_mask from the + * bitfield passed in as @_reg by masking and shifting it down. + */ +#define FIELD_GET(_mask, _reg) \ + ({ \ + __BF_FIELD_CHECK(_mask, _reg, 0U, "FIELD_GET: "); \ + (typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \ + }) + +#endif diff --git a/include/linux/bug.h b/include/linux/bug.h index e51b0709e78d..292d6a10b0c2 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -13,6 +13,7 @@ enum bug_trap_type { struct pt_regs; #ifdef __CHECKER__ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) #define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) #define BUILD_BUG_ON_ZERO(e) (0) #define BUILD_BUG_ON_NULL(e) ((void*)0) @@ -24,6 +25,8 @@ struct pt_regs; #else /* __CHECKER__ */ /* Force a compilation error if a constant expression is not a power of 2 */ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON(((n) & ((n) - 1)) != 0) #define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) -- cgit v1.2.3 From 634faf3686900ccdee87b77e2c56df8b2159912b Mon Sep 17 00:00:00 2001 From: Arend Van Spriel Date: Mon, 5 Sep 2016 11:42:12 +0100 Subject: brcmfmac: add support for bcm4339 chip with modalias sdio:c00v02D0d4339 The driver already supports the bcm4339 chipset but only for the variant that shares the same modalias as the bcm4335, ie. sdio:c00v02D0d4335. It turns out that there are also bcm4339 devices out there that have a more distiguishable modalias sdio:c00v02D0d4339. Reported-by: Steve deRosier Reviewed-by: Hante Meuleman Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Franky Lin Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- include/linux/mmc/sdio_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 0d126aeb3ec0..d43ef96bf075 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -32,6 +32,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43340 0xa94c #define SDIO_DEVICE_ID_BROADCOM_43341 0xa94d #define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335 +#define SDIO_DEVICE_ID_BROADCOM_4339 0x4339 #define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 #define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 #define SDIO_DEVICE_ID_BROADCOM_4345 0x4345 -- cgit v1.2.3 From f035a51536af9802f55d8c79bd87f184ebffb093 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 9 Sep 2016 02:45:29 +0200 Subject: bpf: add BPF_SIZEOF and BPF_FIELD_SIZEOF macros Add BPF_SIZEOF() and BPF_FIELD_SIZEOF() macros to improve the code a bit which otherwise often result in overly long bytes_to_bpf_size(sizeof()) and bytes_to_bpf_size(FIELD_SIZEOF()) lines. So place them into a macro helper instead. Moreover, we currently have a BUILD_BUG_ON(BPF_FIELD_SIZEOF()) check in convert_bpf_extensions(), but we should rather make that generic as well and add a BUILD_BUG_ON() test in all BPF_SIZEOF()/BPF_FIELD_SIZEOF() users to detect any rewriter size issues at compile time. Note, there are currently none, but we want to assert that it stays this way. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index a16439b99fd9..7fabad8dc3fc 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -314,6 +314,20 @@ struct bpf_prog_aux; bpf_size; \ }) +#define BPF_SIZEOF(type) \ + ({ \ + const int __size = bytes_to_bpf_size(sizeof(type)); \ + BUILD_BUG_ON(__size < 0); \ + __size; \ + }) + +#define BPF_FIELD_SIZEOF(type, field) \ + ({ \ + const int __size = bytes_to_bpf_size(FIELD_SIZEOF(type, field)); \ + BUILD_BUG_ON(__size < 0); \ + __size; \ + }) + #ifdef CONFIG_COMPAT /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { -- cgit v1.2.3 From f3694e00123802d688180e7ae90b240669910e3c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 9 Sep 2016 02:45:31 +0200 Subject: bpf: add BPF_CALL_x macros for declaring helpers This work adds BPF_CALL_() macros and converts all the eBPF helper functions to use them, in a similar fashion like we do with SYSCALL_DEFINE() macros that are used today. Motivation for this is to hide all the register handling and all necessary casts from the user, so that it is done automatically in the background when adding a BPF_CALL_() call. This makes current helpers easier to review, eases to write future helpers, avoids getting the casting mess wrong, and allows for extending all helpers at once (f.e. build time checks, etc). It also helps detecting more easily in code reviews that unused registers are not instrumented in the code by accident, breaking compatibility with existing programs. BPF_CALL_() internals are quite similar to SYSCALL_DEFINE() ones with some fundamental differences, for example, for generating the actual helper function that carries all u64 regs, we need to fill unused regs, so that we always end up with 5 u64 regs as an argument. I reviewed several 0-5 generated BPF_CALL_() variants of the .i results and they look all as expected. No sparse issue spotted. We let this also sit for a few days with Fengguang's kbuild test robot, and there were no issues seen. On s390, it barked on the "uses dynamic stack allocation" notice, which is an old one from bpf_perf_event_output{,_tp}() reappearing here due to the conversion to the call wrapper, just telling that the perf raw record/frag sits on stack (gcc with s390's -mwarn-dynamicstack), but that's all. Did various runtime tests and they were fine as well. All eBPF helpers are now converted to use these macros, getting rid of a good chunk of all the raw castings. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7fabad8dc3fc..1f09c521adfe 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -328,6 +328,56 @@ struct bpf_prog_aux; __size; \ }) +#define __BPF_MAP_0(m, v, ...) v +#define __BPF_MAP_1(m, v, t, a, ...) m(t, a) +#define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__) +#define __BPF_MAP_3(m, v, t, a, ...) m(t, a), __BPF_MAP_2(m, v, __VA_ARGS__) +#define __BPF_MAP_4(m, v, t, a, ...) m(t, a), __BPF_MAP_3(m, v, __VA_ARGS__) +#define __BPF_MAP_5(m, v, t, a, ...) m(t, a), __BPF_MAP_4(m, v, __VA_ARGS__) + +#define __BPF_REG_0(...) __BPF_PAD(5) +#define __BPF_REG_1(...) __BPF_MAP(1, __VA_ARGS__), __BPF_PAD(4) +#define __BPF_REG_2(...) __BPF_MAP(2, __VA_ARGS__), __BPF_PAD(3) +#define __BPF_REG_3(...) __BPF_MAP(3, __VA_ARGS__), __BPF_PAD(2) +#define __BPF_REG_4(...) __BPF_MAP(4, __VA_ARGS__), __BPF_PAD(1) +#define __BPF_REG_5(...) __BPF_MAP(5, __VA_ARGS__) + +#define __BPF_MAP(n, ...) __BPF_MAP_##n(__VA_ARGS__) +#define __BPF_REG(n, ...) __BPF_REG_##n(__VA_ARGS__) + +#define __BPF_CAST(t, a) \ + (__force t) \ + (__force \ + typeof(__builtin_choose_expr(sizeof(t) == sizeof(unsigned long), \ + (unsigned long)0, (t)0))) a +#define __BPF_V void +#define __BPF_N + +#define __BPF_DECL_ARGS(t, a) t a +#define __BPF_DECL_REGS(t, a) u64 a + +#define __BPF_PAD(n) \ + __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ + u64, __ur_3, u64, __ur_4, u64, __ur_5) + +#define BPF_CALL_x(x, name, ...) \ + static __always_inline \ + u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ + u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ + u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ + { \ + return ____##name(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ + } \ + static __always_inline \ + u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) + +#define BPF_CALL_0(name, ...) BPF_CALL_x(0, name, __VA_ARGS__) +#define BPF_CALL_1(name, ...) BPF_CALL_x(1, name, __VA_ARGS__) +#define BPF_CALL_2(name, ...) BPF_CALL_x(2, name, __VA_ARGS__) +#define BPF_CALL_3(name, ...) BPF_CALL_x(3, name, __VA_ARGS__) +#define BPF_CALL_4(name, ...) BPF_CALL_x(4, name, __VA_ARGS__) +#define BPF_CALL_5(name, ...) BPF_CALL_x(5, name, __VA_ARGS__) + #ifdef CONFIG_COMPAT /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { -- cgit v1.2.3 From ba63f23d69a3a10e7e527a02702023da68ef8a6d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 8 Sep 2016 14:20:38 -0700 Subject: fscrypto: require write access to mount to set encryption policy Since setting an encryption policy requires writing metadata to the filesystem, it should be guarded by mnt_want_write/mnt_drop_write. Otherwise, a user could cause a write to a frozen or readonly filesystem. This was handled correctly by f2fs but not by ext4. Make fscrypt_process_policy() handle it rather than relying on the filesystem to get it right. Signed-off-by: Eric Biggers Cc: stable@vger.kernel.org # 4.1+; check fs/{ext4,f2fs} Signed-off-by: Theodore Ts'o Acked-by: Jaegeuk Kim --- include/linux/fscrypto.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index cfa6cde25f8e..76cff18bb032 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -274,8 +274,7 @@ extern void fscrypt_restore_control_page(struct page *); extern int fscrypt_zeroout_range(struct inode *, pgoff_t, sector_t, unsigned int); /* policy.c */ -extern int fscrypt_process_policy(struct inode *, - const struct fscrypt_policy *); +extern int fscrypt_process_policy(struct file *, const struct fscrypt_policy *); extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *); extern int fscrypt_has_permitted_context(struct inode *, struct inode *); extern int fscrypt_inherit_context(struct inode *, struct inode *, @@ -345,7 +344,7 @@ static inline int fscrypt_notsupp_zeroout_range(struct inode *i, pgoff_t p, } /* policy.c */ -static inline int fscrypt_notsupp_process_policy(struct inode *i, +static inline int fscrypt_notsupp_process_policy(struct file *f, const struct fscrypt_policy *p) { return -EOPNOTSUPP; -- cgit v1.2.3 From 6b6adee3dad25bbe568ee24fc843372d02fb425f Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia Date: Fri, 9 Sep 2016 17:35:18 +0300 Subject: net/mlx5: SRIOV core code refactoring Simplify the code and makes it look modular and symmetric. Split sriov enable/disable to two levels: device level and pci level. When user enable/disable sriov (via sriov_configure driver callback) we will enable/disable both device and pci sriov. When driver load/unload we will enable/disable (on demand) only device sriov while keeping the PCI sriov enabled for next driver load. On internal/pci error, VFs will be kept enabled on PCI and the reset is done only in device level. Signed-off-by: Mohamad Haj Yahia Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5cb9fa7aec61..0d7aedfce1d7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -828,8 +828,6 @@ void mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); int mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); -int mlx5_sriov_init(struct mlx5_core_dev *dev); -int mlx5_sriov_cleanup(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, s32 npages); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); -- cgit v1.2.3 From 737a234bb6384800a5b632be85c6b0ad6221d137 Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia Date: Fri, 9 Sep 2016 17:35:19 +0300 Subject: net/mlx5: Introduce attach/detach to interface API Add attach/detach callbacks to interface API. This is crucial for implementing seamless reset flow which releases the hardware and it's resources upon detach while keeping software structures and state (e.g netdev) then reset and reallocate the hardware needed resources upon attach. Signed-off-by: Mohamad Haj Yahia Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 0d7aedfce1d7..85c4786427e4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -930,6 +930,8 @@ enum { struct mlx5_interface { void * (*add)(struct mlx5_core_dev *dev); void (*remove)(struct mlx5_core_dev *dev, void *context); + int (*attach)(struct mlx5_core_dev *dev, void *context); + void (*detach)(struct mlx5_core_dev *dev, void *context); void (*event)(struct mlx5_core_dev *dev, void *context, enum mlx5_dev_event event, unsigned long param); void * (*get_dev)(void *context); -- cgit v1.2.3 From 3a8963acc70e69606729404713cfa9a03b58b18c Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 9 Sep 2016 12:45:24 -0700 Subject: Revert "hv_netvsc: make inline functions static" These functions are used by other code misc-next tree. This reverts commit 30d1de08c87ddde6f73936c3350e7e153988fe02. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/hyperv.h | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b01c8c3dd531..5df444b1ac18 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1429,4 +1429,88 @@ static inline bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi) return false; } +/* + * An API to support in-place processing of incoming VMBUS packets. + */ +#define VMBUS_PKT_TRAILER 8 + +static inline struct vmpacket_descriptor * +get_next_pkt_raw(struct vmbus_channel *channel) +{ + struct hv_ring_buffer_info *ring_info = &channel->inbound; + u32 read_loc = ring_info->priv_read_index; + void *ring_buffer = hv_get_ring_buffer(ring_info); + struct vmpacket_descriptor *cur_desc; + u32 packetlen; + u32 dsize = ring_info->ring_datasize; + u32 delta = read_loc - ring_info->ring_buffer->read_index; + u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta); + + if (bytes_avail_toread < sizeof(struct vmpacket_descriptor)) + return NULL; + + if ((read_loc + sizeof(*cur_desc)) > dsize) + return NULL; + + cur_desc = ring_buffer + read_loc; + packetlen = cur_desc->len8 << 3; + + /* + * If the packet under consideration is wrapping around, + * return failure. + */ + if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > (dsize - 1)) + return NULL; + + return cur_desc; +} + +/* + * A helper function to step through packets "in-place" + * This API is to be called after each successful call + * get_next_pkt_raw(). + */ +static inline void put_pkt_raw(struct vmbus_channel *channel, + struct vmpacket_descriptor *desc) +{ + struct hv_ring_buffer_info *ring_info = &channel->inbound; + u32 read_loc = ring_info->priv_read_index; + u32 packetlen = desc->len8 << 3; + u32 dsize = ring_info->ring_datasize; + + if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > dsize) + BUG(); + /* + * Include the packet trailer. + */ + ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER; +} + +/* + * This call commits the read index and potentially signals the host. + * Here is the pattern for using the "in-place" consumption APIs: + * + * while (get_next_pkt_raw() { + * process the packet "in-place"; + * put_pkt_raw(); + * } + * if (packets processed in place) + * commit_rd_index(); + */ +static inline void commit_rd_index(struct vmbus_channel *channel) +{ + struct hv_ring_buffer_info *ring_info = &channel->inbound; + /* + * Make sure all reads are done before we update the read index since + * the writer may start writing to the read area once the read index + * is updated. + */ + virt_rmb(); + ring_info->ring_buffer->read_index = ring_info->priv_read_index; + + if (hv_need_to_signal_on_read(ring_info)) + vmbus_set_event(channel); +} + + #endif /* _HYPERV_H */ -- cgit v1.2.3 From ebf9ff753c041b296241990aef76163bbb2cc9c8 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 13 Sep 2016 15:58:28 +0200 Subject: genirq: Provide irq_gc_{lock_irqsave,unlock_irqrestore}() helpers Some irqchip drivers need to take the generic chip lock outside of the irq context. Provide the irq_gc_{lock_irqsave,unlock_irqrestore}() helpers to allow one to disable irqs while entering a critical section protected by gc->lock. Note that we do not provide optimized version of these helpers for !SMP, because they are not called from the hot-path. [ tglx: Added a comment when these helpers should be [not] used ] Signed-off-by: Boris Brezillon Cc: Jason Cooper Cc: Marc Zyngier Cc: Nicolas Ferre Cc: stable@vger.kernel.org Cc: Alexandre Belloni Link: http://lkml.kernel.org/r/1473775109-4192-1-git-send-email-boris.brezillon@free-electrons.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index b52424eaa0ed..0ac26c892fe2 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -945,6 +945,16 @@ static inline void irq_gc_lock(struct irq_chip_generic *gc) { } static inline void irq_gc_unlock(struct irq_chip_generic *gc) { } #endif +/* + * The irqsave variants are for usage in non interrupt code. Do not use + * them in irq_chip callbacks. Use irq_gc_lock() instead. + */ +#define irq_gc_lock_irqsave(gc, flags) \ + raw_spin_lock_irqsave(&(gc)->lock, flags) + +#define irq_gc_unlock_irqrestore(gc, flags) \ + raw_spin_unlock_irqrestore(&(gc)->lock, flags) + static inline void irq_reg_writel(struct irq_chip_generic *gc, u32 val, int reg_offset) { -- cgit v1.2.3 From 6cfeaf5125d425043d44002d0a1a8a147be582bf Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Wed, 14 Sep 2016 11:00:26 +0100 Subject: cpu/hotplug: Include linux/types.h in linux/cpuhotplug.h The linux/cpuhotplug.h header makes use of the bool type, but wasn't including linux/types.h to ensure that type has been defined. Fix this by including linux/types.h in preparation for including linux/cpuhotplug.h in a file that doesn't do so already. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Cc: Richard Cochran Cc: Sebastian Andrzej Siewior Cc: Ralf Baechle Cc: Anna-Maria Gleixner Link: http://lkml.kernel.org/r/20160914100027.20945-1-paul.burton@imgtec.com Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 242bf530edfc..34bd80512a0c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -1,6 +1,8 @@ #ifndef __CPUHOTPLUG_H #define __CPUHOTPLUG_H +#include + enum cpuhp_state { CPUHP_OFFLINE, CPUHP_CREATE_THREADS, -- cgit v1.2.3 From d4690f1e1cdabb4d61207b6787b1605a0dc0aeab Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 16 Sep 2016 00:11:45 +0100 Subject: fix iov_iter_fault_in_readable() ... by turning it into what used to be multipages counterpart Cc: stable@vger.kernel.org Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/uio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 1b5d1cd796e2..75b4aaf31a9d 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -76,7 +76,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); -int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes); +#define iov_iter_fault_in_multipages_readable iov_iter_fault_in_readable size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); -- cgit v1.2.3 From 2c9d85d4d82d9e0a62aad08bf50650804e68ed30 Mon Sep 17 00:00:00 2001 From: Nogah Frankel Date: Fri, 16 Sep 2016 15:05:36 +0200 Subject: netdevice: Add offload statistics ndo Add a new ndo to return statistics for offloaded operation. Since there can be many different offloaded operation with many stats types, the ndo gets an attribute id by which it knows which stats are wanted. The ndo also gets a void pointer to be cast according to the attribute id. Signed-off-by: Nogah Frankel Signed-off-by: Jiri Pirko Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2095b6ab3661..a10d8d18ce19 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -924,6 +924,14 @@ struct netdev_xdp { * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * + * bool (*ndo_has_offload_stats)(int attr_id) + * Return true if this device supports offload stats of this attr_id. + * + * int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, + * void *attr_data) + * Get statistics for offload operations by attr_id. Write it into the + * attr_data pointer. + * * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device supports VLAN filtering this function is called when a * VLAN id is registered. @@ -1155,6 +1163,10 @@ struct net_device_ops { struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, struct rtnl_link_stats64 *storage); + bool (*ndo_has_offload_stats)(int attr_id); + int (*ndo_get_offload_stats)(int attr_id, + const struct net_device *dev, + void *attr_data); struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); int (*ndo_vlan_rx_add_vid)(struct net_device *dev, -- cgit v1.2.3 From e8bffe0cf964f0330595bb376b74921cccdaac88 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Fri, 16 Sep 2016 12:59:13 -0700 Subject: net: Add _nf_(un)register_hooks symbols Add _nf_register_hooks() and _nf_unregister_hooks() calls which allow caller to hold RTNL mutex. Signed-off-by: Mahesh Bandewar CC: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 9230f9aee896..e82b76781bf6 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -133,6 +133,8 @@ int nf_register_hook(struct nf_hook_ops *reg); void nf_unregister_hook(struct nf_hook_ops *reg); int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); +int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); +void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ -- cgit v1.2.3 From 12703dbfeb15402260e7554d32a34ac40c233990 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 19 Sep 2016 14:44:27 -0700 Subject: fsnotify: add a way to stop queueing events on group shutdown Implement a function that can be called when a group is being shutdown to stop queueing new events to the group. Fanotify will use this. Fixes: 5838d4442bd5 ("fanotify: fix double free of pending permission events") Link: http://lkml.kernel.org/r/1473797711-14111-2-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reviewed-by: Miklos Szeredi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fsnotify_backend.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 58205f33af02..40a9e99de703 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -148,6 +148,7 @@ struct fsnotify_group { #define FS_PRIO_1 1 /* fanotify content based access control */ #define FS_PRIO_2 2 /* fanotify pre-content access */ unsigned int priority; + bool shutdown; /* group is being shut down, don't queue more events */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ @@ -292,6 +293,8 @@ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *op extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); +/* group destruction begins, stop queuing new events */ +extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ -- cgit v1.2.3 From 96d41019e3ac55f6f0115b0ce97e4f24a3d636d2 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 19 Sep 2016 14:44:30 -0700 Subject: fanotify: fix list corruption in fanotify_get_response() fanotify_get_response() calls fsnotify_remove_event() when it finds that group is being released from fanotify_release() (bypass_perm is set). However the event it removes need not be only in the group's notification queue but it can have already moved to access_list (userspace read the event before closing the fanotify instance fd) which is protected by a different lock. Thus when fsnotify_remove_event() races with fanotify_release() operating on access_list, the list can get corrupted. Fix the problem by moving all the logic removing permission events from the lists to one place - fanotify_release(). Fixes: 5838d4442bd5 ("fanotify: fix double free of pending permission events") Link: http://lkml.kernel.org/r/1473797711-14111-3-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Reported-by: Miklos Szeredi Tested-by: Miklos Szeredi Reviewed-by: Miklos Szeredi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fsnotify_backend.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 40a9e99de703..7268ed076be8 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -180,7 +180,6 @@ struct fsnotify_group { spinlock_t access_lock; struct list_head access_list; wait_queue_head_t access_waitq; - atomic_t bypass_perm; #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ int f_flags; unsigned int max_marks; @@ -307,8 +306,6 @@ extern int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct list_head *, struct fsnotify_event *)); -/* Remove passed event from groups notification queue */ -extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event); /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ -- cgit v1.2.3 From ca26893f05e86497a86732768ec53cd38c0819ca Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 19 Sep 2016 19:00:09 +0800 Subject: rhashtable: Add rhlist interface The insecure_elasticity setting is an ugly wart brought out by users who need to insert duplicate objects (that is, distinct objects with identical keys) into the same table. In fact, those users have a much bigger problem. Once those duplicate objects are inserted, they don't have an interface to find them (unless you count the walker interface which walks over the entire table). Some users have resorted to doing a manual walk over the hash table which is of course broken because they don't handle the potential existence of multiple hash tables. The result is that they will break sporadically when they encounter a hash table resize/rehash. This patch provides a way out for those users, at the expense of an extra pointer per object. Essentially each object is now a list of objects carrying the same key. The hash table will only see the lists so nothing changes as far as rhashtable is concerned. To use this new interface, you need to insert a struct rhlist_head into your objects instead of struct rhash_head. While the hash table is unchanged, for type-safety you'll need to use struct rhltable instead of struct rhashtable. All the existing interfaces have been duplicated for rhlist, including the hash table walker. One missing feature is nulls marking because AFAIK the only potential user of it does not need duplicate objects. Should anyone need this it shouldn't be too hard to add. Signed-off-by: Herbert Xu Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 491 ++++++++++++++++++++++++++++++++++----------- 1 file changed, 377 insertions(+), 114 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index fd82584acd48..5c132d3188be 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -1,7 +1,7 @@ /* * Resizable, Scalable, Concurrent Hash Table * - * Copyright (c) 2015 Herbert Xu + * Copyright (c) 2015-2016 Herbert Xu * Copyright (c) 2014-2015 Thomas Graf * Copyright (c) 2008-2014 Patrick McHardy * @@ -53,6 +53,11 @@ struct rhash_head { struct rhash_head __rcu *next; }; +struct rhlist_head { + struct rhash_head rhead; + struct rhlist_head __rcu *next; +}; + /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets @@ -137,6 +142,7 @@ struct rhashtable_params { * @key_len: Key length for hashfn * @elasticity: Maximum chain length before rehash * @p: Configuration parameters + * @rhlist: True if this is an rhltable * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping * @lock: Spin lock to protect walker list @@ -147,11 +153,20 @@ struct rhashtable { unsigned int key_len; unsigned int elasticity; struct rhashtable_params p; + bool rhlist; struct work_struct run_work; struct mutex mutex; spinlock_t lock; }; +/** + * struct rhltable - Hash table with duplicate objects in a list + * @ht: Underlying rhtable + */ +struct rhltable { + struct rhashtable ht; +}; + /** * struct rhashtable_walker - Hash table walker * @list: List entry on list of walkers @@ -163,9 +178,10 @@ struct rhashtable_walker { }; /** - * struct rhashtable_iter - Hash table iterator, fits into netlink cb + * struct rhashtable_iter - Hash table iterator * @ht: Table to iterate through * @p: Current pointer + * @list: Current hash list pointer * @walker: Associated rhashtable walker * @slot: Current slot * @skip: Number of entries to skip in slot @@ -173,6 +189,7 @@ struct rhashtable_walker { struct rhashtable_iter { struct rhashtable *ht; struct rhash_head *p; + struct rhlist_head *list; struct rhashtable_walker walker; unsigned int slot; unsigned int skip; @@ -339,13 +356,11 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, int rhashtable_init(struct rhashtable *ht, const struct rhashtable_params *params); +int rhltable_init(struct rhltable *hlt, + const struct rhashtable_params *params); -struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht, - const void *key, - struct rhash_head *obj, - struct bucket_table *old_tbl, - void **data); -int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl); +void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, + struct rhash_head *obj); void rhashtable_walk_enter(struct rhashtable *ht, struct rhashtable_iter *iter); @@ -507,6 +522,31 @@ void rhashtable_destroy(struct rhashtable *ht); rht_for_each_entry_rcu_continue(tpos, pos, (tbl)->buckets[hash],\ tbl, hash, member) +/** + * rhl_for_each_rcu - iterate over rcu hash table list + * @pos: the &struct rlist_head to use as a loop cursor. + * @list: the head of the list + * + * This hash chain list-traversal primitive should be used on the + * list returned by rhltable_lookup. + */ +#define rhl_for_each_rcu(pos, list) \ + for (pos = list; pos; pos = rcu_dereference_raw(pos->next)) + +/** + * rhl_for_each_entry_rcu - iterate over rcu hash table list of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rlist_head to use as a loop cursor. + * @list: the head of the list + * @member: name of the &struct rlist_head within the hashable struct. + * + * This hash chain list-traversal primitive should be used on the + * list returned by rhltable_lookup. + */ +#define rhl_for_each_entry_rcu(tpos, pos, list, member) \ + for (pos = list; pos && rht_entry(tpos, pos, member); \ + pos = rcu_dereference_raw(pos->next)) + static inline int rhashtable_compare(struct rhashtable_compare_arg *arg, const void *obj) { @@ -516,18 +556,8 @@ static inline int rhashtable_compare(struct rhashtable_compare_arg *arg, return memcmp(ptr + ht->p.key_offset, arg->key, ht->p.key_len); } -/** - * rhashtable_lookup_fast - search hash table, inlined version - * @ht: hash table - * @key: the pointer to the key - * @params: hash table parameters - * - * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. - * - * Returns the first entry on which the compare function returned true. - */ -static inline void *rhashtable_lookup_fast( +/* Internal function, do not use. */ +static inline struct rhash_head *__rhashtable_lookup( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { @@ -539,8 +569,6 @@ static inline void *rhashtable_lookup_fast( struct rhash_head *he; unsigned int hash; - rcu_read_lock(); - tbl = rht_dereference_rcu(ht->tbl, ht); restart: hash = rht_key_hashfn(ht, tbl, key, params); @@ -549,8 +577,7 @@ restart: params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) continue; - rcu_read_unlock(); - return rht_obj(ht, he); + return he; } /* Ensure we see any new tables. */ @@ -559,96 +586,165 @@ restart: tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(tbl)) goto restart; - rcu_read_unlock(); return NULL; } +/** + * rhashtable_lookup - search hash table + * @ht: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * This must only be called under the RCU read lock. + * + * Returns the first entry on which the compare function returned true. + */ +static inline void *rhashtable_lookup( + struct rhashtable *ht, const void *key, + const struct rhashtable_params params) +{ + struct rhash_head *he = __rhashtable_lookup(ht, key, params); + + return he ? rht_obj(ht, he) : NULL; +} + +/** + * rhashtable_lookup_fast - search hash table, without RCU read lock + * @ht: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * Only use this function when you have other mechanisms guaranteeing + * that the object won't go away after the RCU read lock is released. + * + * Returns the first entry on which the compare function returned true. + */ +static inline void *rhashtable_lookup_fast( + struct rhashtable *ht, const void *key, + const struct rhashtable_params params) +{ + void *obj; + + rcu_read_lock(); + obj = rhashtable_lookup(ht, key, params); + rcu_read_unlock(); + + return obj; +} + +/** + * rhltable_lookup - search hash list table + * @hlt: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. All matching entries are returned + * in a list. + * + * This must only be called under the RCU read lock. + * + * Returns the list of entries that match the given key. + */ +static inline struct rhlist_head *rhltable_lookup( + struct rhltable *hlt, const void *key, + const struct rhashtable_params params) +{ + struct rhash_head *he = __rhashtable_lookup(&hlt->ht, key, params); + + return he ? container_of(he, struct rhlist_head, rhead) : NULL; +} + /* Internal function, please use rhashtable_insert_fast() instead. This * function returns the existing element already in hashes in there is a clash, * otherwise it returns an error via ERR_PTR(). */ static inline void *__rhashtable_insert_fast( struct rhashtable *ht, const void *key, struct rhash_head *obj, - const struct rhashtable_params params) + const struct rhashtable_params params, bool rhlist) { struct rhashtable_compare_arg arg = { .ht = ht, .key = key, }; - struct bucket_table *tbl, *new_tbl; + struct rhash_head __rcu **pprev; + struct bucket_table *tbl; struct rhash_head *head; spinlock_t *lock; - unsigned int elasticity; unsigned int hash; - void *data = NULL; - int err; + int elasticity; + void *data; -restart: rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); + hash = rht_head_hashfn(ht, tbl, obj, params); + lock = rht_bucket_lock(tbl, hash); + spin_lock_bh(lock); - /* All insertions must grab the oldest table containing - * the hashed bucket that is yet to be rehashed. - */ - for (;;) { - hash = rht_head_hashfn(ht, tbl, obj, params); - lock = rht_bucket_lock(tbl, hash); - spin_lock_bh(lock); - - if (tbl->rehash <= hash) - break; - + if (unlikely(rht_dereference_bucket(tbl->future_tbl, tbl, hash))) { +slow_path: spin_unlock_bh(lock); - tbl = rht_dereference_rcu(tbl->future_tbl, ht); + rcu_read_unlock(); + return rhashtable_insert_slow(ht, key, obj); } - new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); - if (unlikely(new_tbl)) { - tbl = rhashtable_insert_slow(ht, key, obj, new_tbl, &data); - if (!IS_ERR_OR_NULL(tbl)) - goto slow_path; + elasticity = ht->elasticity; + pprev = &tbl->buckets[hash]; + rht_for_each(head, tbl, hash) { + struct rhlist_head *plist; + struct rhlist_head *list; + + elasticity--; + if (!key || + (params.obj_cmpfn ? + params.obj_cmpfn(&arg, rht_obj(ht, head)) : + rhashtable_compare(&arg, rht_obj(ht, head)))) + continue; + + data = rht_obj(ht, head); - err = PTR_ERR(tbl); - if (err == -EEXIST) - err = 0; + if (!rhlist) + goto out; - goto out; - } - err = -E2BIG; - if (unlikely(rht_grow_above_max(ht, tbl))) - goto out; + list = container_of(obj, struct rhlist_head, rhead); + plist = container_of(head, struct rhlist_head, rhead); - if (unlikely(rht_grow_above_100(ht, tbl))) { -slow_path: - spin_unlock_bh(lock); - err = rhashtable_insert_rehash(ht, tbl); - rcu_read_unlock(); - if (err) - return ERR_PTR(err); + RCU_INIT_POINTER(list->next, plist); + head = rht_dereference_bucket(head->next, tbl, hash); + RCU_INIT_POINTER(list->rhead.next, head); + rcu_assign_pointer(*pprev, obj); - goto restart; + goto good; } - err = 0; - elasticity = ht->elasticity; - rht_for_each(head, tbl, hash) { - if (key && - unlikely(!(params.obj_cmpfn ? - params.obj_cmpfn(&arg, rht_obj(ht, head)) : - rhashtable_compare(&arg, rht_obj(ht, head))))) { - data = rht_obj(ht, head); - goto out; - } - if (!--elasticity) - goto slow_path; - } + if (elasticity <= 0) + goto slow_path; + + data = ERR_PTR(-E2BIG); + if (unlikely(rht_grow_above_max(ht, tbl))) + goto out; + + if (unlikely(rht_grow_above_100(ht, tbl))) + goto slow_path; head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); RCU_INIT_POINTER(obj->next, head); + if (rhlist) { + struct rhlist_head *list; + + list = container_of(obj, struct rhlist_head, rhead); + RCU_INIT_POINTER(list->next, NULL); + } rcu_assign_pointer(tbl->buckets[hash], obj); @@ -656,11 +752,14 @@ slow_path: if (rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); +good: + data = NULL; + out: spin_unlock_bh(lock); rcu_read_unlock(); - return err ? ERR_PTR(err) : data; + return data; } /** @@ -685,13 +784,65 @@ static inline int rhashtable_insert_fast( { void *ret; - ret = __rhashtable_insert_fast(ht, NULL, obj, params); + ret = __rhashtable_insert_fast(ht, NULL, obj, params, false); if (IS_ERR(ret)) return PTR_ERR(ret); return ret == NULL ? 0 : -EEXIST; } +/** + * rhltable_insert_key - insert object into hash list table + * @hlt: hash list table + * @key: the pointer to the key + * @list: pointer to hash list head inside object + * @params: hash table parameters + * + * Will take a per bucket spinlock to protect against mutual mutations + * on the same bucket. Multiple insertions may occur in parallel unless + * they map to the same bucket lock. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + */ +static inline int rhltable_insert_key( + struct rhltable *hlt, const void *key, struct rhlist_head *list, + const struct rhashtable_params params) +{ + return PTR_ERR(__rhashtable_insert_fast(&hlt->ht, key, &list->rhead, + params, true)); +} + +/** + * rhltable_insert - insert object into hash list table + * @hlt: hash list table + * @list: pointer to hash list head inside object + * @params: hash table parameters + * + * Will take a per bucket spinlock to protect against mutual mutations + * on the same bucket. Multiple insertions may occur in parallel unless + * they map to the same bucket lock. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + */ +static inline int rhltable_insert( + struct rhltable *hlt, struct rhlist_head *list, + const struct rhashtable_params params) +{ + const char *key = rht_obj(&hlt->ht, &list->rhead); + + key += params.key_offset; + + return rhltable_insert_key(hlt, key, list, params); +} + /** * rhashtable_lookup_insert_fast - lookup and insert object into hash table * @ht: hash table @@ -722,7 +873,8 @@ static inline int rhashtable_lookup_insert_fast( BUG_ON(ht->p.obj_hashfn); - ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params); + ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params, + false); if (IS_ERR(ret)) return PTR_ERR(ret); @@ -759,7 +911,7 @@ static inline int rhashtable_lookup_insert_key( BUG_ON(!ht->p.obj_hashfn || !key); - ret = __rhashtable_insert_fast(ht, key, obj, params); + ret = __rhashtable_insert_fast(ht, key, obj, params, false); if (IS_ERR(ret)) return PTR_ERR(ret); @@ -783,13 +935,14 @@ static inline void *rhashtable_lookup_get_insert_key( { BUG_ON(!ht->p.obj_hashfn || !key); - return __rhashtable_insert_fast(ht, key, obj, params); + return __rhashtable_insert_fast(ht, key, obj, params, false); } /* Internal function, please use rhashtable_remove_fast() instead */ -static inline int __rhashtable_remove_fast( +static inline int __rhashtable_remove_fast_one( struct rhashtable *ht, struct bucket_table *tbl, - struct rhash_head *obj, const struct rhashtable_params params) + struct rhash_head *obj, const struct rhashtable_params params, + bool rhlist) { struct rhash_head __rcu **pprev; struct rhash_head *he; @@ -804,39 +957,66 @@ static inline int __rhashtable_remove_fast( pprev = &tbl->buckets[hash]; rht_for_each(he, tbl, hash) { + struct rhlist_head *list; + + list = container_of(he, struct rhlist_head, rhead); + if (he != obj) { + struct rhlist_head __rcu **lpprev; + pprev = &he->next; - continue; + + if (!rhlist) + continue; + + do { + lpprev = &list->next; + list = rht_dereference_bucket(list->next, + tbl, hash); + } while (list && obj != &list->rhead); + + if (!list) + continue; + + list = rht_dereference_bucket(list->next, tbl, hash); + RCU_INIT_POINTER(*lpprev, list); + err = 0; + break; } - rcu_assign_pointer(*pprev, obj->next); - err = 0; + obj = rht_dereference_bucket(obj->next, tbl, hash); + err = 1; + + if (rhlist) { + list = rht_dereference_bucket(list->next, tbl, hash); + if (list) { + RCU_INIT_POINTER(list->rhead.next, obj); + obj = &list->rhead; + err = 0; + } + } + + rcu_assign_pointer(*pprev, obj); break; } spin_unlock_bh(lock); + if (err > 0) { + atomic_dec(&ht->nelems); + if (unlikely(ht->p.automatic_shrinking && + rht_shrink_below_30(ht, tbl))) + schedule_work(&ht->run_work); + err = 0; + } + return err; } -/** - * rhashtable_remove_fast - remove object from hash table - * @ht: hash table - * @obj: pointer to hash head inside object - * @params: hash table parameters - * - * Since the hash chain is single linked, the removal operation needs to - * walk the bucket chain upon removal. The removal operation is thus - * considerable slow if the hash table is not correctly sized. - * - * Will automatically shrink the table via rhashtable_expand() if the - * shrink_decision function specified at rhashtable_init() returns true. - * - * Returns zero on success, -ENOENT if the entry could not be found. - */ -static inline int rhashtable_remove_fast( +/* Internal function, please use rhashtable_remove_fast() instead */ +static inline int __rhashtable_remove_fast( struct rhashtable *ht, struct rhash_head *obj, - const struct rhashtable_params params) + const struct rhashtable_params params, bool rhlist) { struct bucket_table *tbl; int err; @@ -850,24 +1030,60 @@ static inline int rhashtable_remove_fast( * visible then that guarantees the entry to still be in * the old tbl if it exists. */ - while ((err = __rhashtable_remove_fast(ht, tbl, obj, params)) && + while ((err = __rhashtable_remove_fast_one(ht, tbl, obj, params, + rhlist)) && (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) ; - if (err) - goto out; - - atomic_dec(&ht->nelems); - if (unlikely(ht->p.automatic_shrinking && - rht_shrink_below_30(ht, tbl))) - schedule_work(&ht->run_work); - -out: rcu_read_unlock(); return err; } +/** + * rhashtable_remove_fast - remove object from hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Since the hash chain is single linked, the removal operation needs to + * walk the bucket chain upon removal. The removal operation is thus + * considerable slow if the hash table is not correctly sized. + * + * Will automatically shrink the table via rhashtable_expand() if the + * shrink_decision function specified at rhashtable_init() returns true. + * + * Returns zero on success, -ENOENT if the entry could not be found. + */ +static inline int rhashtable_remove_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + return __rhashtable_remove_fast(ht, obj, params, false); +} + +/** + * rhltable_remove - remove object from hash list table + * @hlt: hash list table + * @list: pointer to hash list head inside object + * @params: hash table parameters + * + * Since the hash chain is single linked, the removal operation needs to + * walk the bucket chain upon removal. The removal operation is thus + * considerable slow if the hash table is not correctly sized. + * + * Will automatically shrink the table via rhashtable_expand() if the + * shrink_decision function specified at rhashtable_init() returns true. + * + * Returns zero on success, -ENOENT if the entry could not be found. + */ +static inline int rhltable_remove( + struct rhltable *hlt, struct rhlist_head *list, + const struct rhashtable_params params) +{ + return __rhashtable_remove_fast(&hlt->ht, &list->rhead, params, true); +} + /* Internal function, please use rhashtable_replace_fast() instead */ static inline int __rhashtable_replace_fast( struct rhashtable *ht, struct bucket_table *tbl, @@ -958,4 +1174,51 @@ static inline int rhashtable_walk_init(struct rhashtable *ht, return 0; } +/** + * rhltable_walk_enter - Initialise an iterator + * @hlt: Table to walk over + * @iter: Hash table Iterator + * + * This function prepares a hash table walk. + * + * Note that if you restart a walk after rhashtable_walk_stop you + * may see the same object twice. Also, you may miss objects if + * there are removals in between rhashtable_walk_stop and the next + * call to rhashtable_walk_start. + * + * For a completely stable walk you should construct your own data + * structure outside the hash table. + * + * This function may sleep so you must not call it from interrupt + * context or with spin locks held. + * + * You must call rhashtable_walk_exit after this function returns. + */ +static inline void rhltable_walk_enter(struct rhltable *hlt, + struct rhashtable_iter *iter) +{ + return rhashtable_walk_enter(&hlt->ht, iter); +} + +/** + * rhltable_free_and_destroy - free elements and destroy hash list table + * @hlt: the hash list table to destroy + * @free_fn: callback to release resources of element + * @arg: pointer passed to free_fn + * + * See documentation for rhashtable_free_and_destroy. + */ +static inline void rhltable_free_and_destroy(struct rhltable *hlt, + void (*free_fn)(void *ptr, + void *arg), + void *arg) +{ + return rhashtable_free_and_destroy(&hlt->ht, free_fn, arg); +} + +static inline void rhltable_destroy(struct rhltable *hlt) +{ + return rhltable_free_and_destroy(hlt, NULL, NULL); +} + #endif /* _LINUX_RHASHTABLE_H */ -- cgit v1.2.3 From e23d4159b109167126e5bcd7f3775c95de7fee47 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 20 Sep 2016 20:07:42 +0100 Subject: fix fault_in_multipages_...() on architectures with no-op access_ok() Switching iov_iter fault-in to multipages variants has exposed an old bug in underlying fault_in_multipages_...(); they break if the range passed to them wraps around. Normally access_ok() done by callers will prevent such (and it's a guaranteed EFAULT - ERR_PTR() values fall into such a range and they should not point to any valid objects). However, on architectures where userland and kernel live in different MMU contexts (e.g. s390) access_ok() is a no-op and on those a range with a wraparound can reach fault_in_multipages_...(). Since any wraparound means EFAULT there, the fix is trivial - turn those while (uaddr <= end) ... into if (unlikely(uaddr > end)) return -EFAULT; do ... while (uaddr <= end); Reported-by: Jan Stancek Tested-by: Jan Stancek Cc: stable@vger.kernel.org # v3.5+ Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 66a1260b33de..7e3d53753612 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -571,56 +571,56 @@ static inline int fault_in_pages_readable(const char __user *uaddr, int size) */ static inline int fault_in_multipages_writeable(char __user *uaddr, int size) { - int ret = 0; char __user *end = uaddr + size - 1; if (unlikely(size == 0)) - return ret; + return 0; + if (unlikely(uaddr > end)) + return -EFAULT; /* * Writing zeroes into userspace here is OK, because we know that if * the zero gets there, we'll be overwriting it. */ - while (uaddr <= end) { - ret = __put_user(0, uaddr); - if (ret != 0) - return ret; + do { + if (unlikely(__put_user(0, uaddr) != 0)) + return -EFAULT; uaddr += PAGE_SIZE; - } + } while (uaddr <= end); /* Check whether the range spilled into the next page. */ if (((unsigned long)uaddr & PAGE_MASK) == ((unsigned long)end & PAGE_MASK)) - ret = __put_user(0, end); + return __put_user(0, end); - return ret; + return 0; } static inline int fault_in_multipages_readable(const char __user *uaddr, int size) { volatile char c; - int ret = 0; const char __user *end = uaddr + size - 1; if (unlikely(size == 0)) - return ret; + return 0; - while (uaddr <= end) { - ret = __get_user(c, uaddr); - if (ret != 0) - return ret; + if (unlikely(uaddr > end)) + return -EFAULT; + + do { + if (unlikely(__get_user(c, uaddr) != 0)) + return -EFAULT; uaddr += PAGE_SIZE; - } + } while (uaddr <= end); /* Check whether the range spilled into the next page. */ if (((unsigned long)uaddr & PAGE_MASK) == ((unsigned long)end & PAGE_MASK)) { - ret = __get_user(c, end); - (void)c; + return __get_user(c, end); } - return ret; + return 0; } int add_to_page_cache_locked(struct page *page, struct address_space *mapping, -- cgit v1.2.3 From 36bbef52c7eb646ed6247055a2acd3851e317857 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 20 Sep 2016 00:26:13 +0200 Subject: bpf: direct packet write and access for helpers for clsact progs This work implements direct packet access for helpers and direct packet write in a similar fashion as already available for XDP types via commits 4acf6c0b84c9 ("bpf: enable direct packet data write for xdp progs") and 6841de8b0d03 ("bpf: allow helpers access the packet directly"), and as a complementary feature to the already available direct packet read for tc (cls/act) programs. For enabling this, we need to introduce two helpers, bpf_skb_pull_data() and bpf_csum_update(). The first is generally needed for both, read and write, because they would otherwise only be limited to the current linear skb head. Usually, when the data_end test fails, programs just bail out, or, in the direct read case, use bpf_skb_load_bytes() as an alternative to overcome this limitation. If such data sits in non-linear parts, we can just pull them in once with the new helper, retest and eventually access them. At the same time, this also makes sure the skb is uncloned, which is, of course, a necessary condition for direct write. As this needs to be an invariant for the write part only, the verifier detects writes and adds a prologue that is calling bpf_skb_pull_data() to effectively unclone the skb from the very beginning in case it is indeed cloned. The heuristic makes use of a similar trick that was done in 233577a22089 ("net: filter: constify detection of pkt_type_offset"). This comes at zero cost for other programs that do not use the direct write feature. Should a program use this feature only sparsely and has read access for the most parts with, for example, drop return codes, then such write action can be delegated to a tail called program for mitigating this cost of potential uncloning to a late point in time where it would have been paid similarly with the bpf_skb_store_bytes() as well. Advantage of direct write is that the writes are inlined whereas the helper cannot make any length assumptions and thus needs to generate a call to memcpy() also for small sizes, as well as cost of helper call itself with sanity checks are avoided. Plus, when direct read is already used, we don't need to cache or perform rechecks on the data boundaries (due to verifier invalidating previous checks for helpers that change skb->data), so more complex programs using rewrites can benefit from switching to direct read plus write. For direct packet access to helpers, we save the otherwise needed copy into a temp struct sitting on stack memory when use-case allows. Both facilities are enabled via may_access_direct_pkt_data() in verifier. For now, we limit this to map helpers and csum_diff, and can successively enable other helpers where we find it makes sense. Helpers that definitely cannot be allowed for this are those part of bpf_helper_changes_skb_data() since they can change underlying data, and those that write into memory as this could happen for packet typed args when still cloned. bpf_csum_update() helper accommodates for the fact that we need to fixup checksum_complete when using direct write instead of bpf_skb_store_bytes(), meaning the programs can use available helpers like bpf_csum_diff(), and implement csum_add(), csum_sub(), csum_block_add(), csum_block_sub() equivalents in eBPF together with the new helper. A usage example will be provided for iproute2's examples/bpf/ directory. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 4 +++- include/linux/skbuff.h | 14 ++++++++++++-- 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9a904f63f8c1..5691fdc83819 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -96,6 +96,7 @@ enum bpf_return_type { struct bpf_func_proto { u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool gpl_only; + bool pkt_access; enum bpf_return_type ret_type; enum bpf_arg_type arg1_type; enum bpf_arg_type arg2_type; @@ -151,7 +152,8 @@ struct bpf_verifier_ops { */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type, enum bpf_reg_type *reg_type); - + int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, + const struct bpf_prog *prog); u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, struct bpf_insn *insn, struct bpf_prog *prog); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4c5662f05bda..c6dab3f7457c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -676,13 +676,23 @@ struct sk_buff { */ kmemcheck_bitfield_begin(flags1); __u16 queue_mapping; + +/* if you move cloned around you also must adapt those constants */ +#ifdef __BIG_ENDIAN_BITFIELD +#define CLONED_MASK (1 << 7) +#else +#define CLONED_MASK 1 +#endif +#define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) + + __u8 __cloned_offset[0]; __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, - xmit_more:1; - /* one bit hole */ + xmit_more:1, + __unused:1; /* one bit hole */ kmemcheck_bitfield_end(flags1); /* fields enclosed in headers_start/headers_end are copied -- cgit v1.2.3 From a4f1f9ac8153e22869b6408832b5a9bb9c762bf6 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Mon, 19 Sep 2016 23:39:09 -0400 Subject: lib/win_minmax: windowed min or max estimator This commit introduces a generic library to estimate either the min or max value of a time-varying variable over a recent time window. This is code originally from Kathleen Nichols. The current form of the code is from Van Jacobson. A single struct minmax_sample will track the estimated windowed-max value of the series if you call minmax_running_max() or the estimated windowed-min value of the series if you call minmax_running_min(). Nearly equivalent code is already in place for minimum RTT estimation in the TCP stack. This commit extracts that code and generalizes it to handle both min and max. Moving the code here reduces the footprint and complexity of the TCP code base and makes the filter generally available for other parts of the codebase, including an upcoming TCP congestion control module. This library works well for time series where the measurements are smoothly increasing or decreasing. Signed-off-by: Van Jacobson Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/win_minmax.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 include/linux/win_minmax.h (limited to 'include/linux') diff --git a/include/linux/win_minmax.h b/include/linux/win_minmax.h new file mode 100644 index 000000000000..56569604278f --- /dev/null +++ b/include/linux/win_minmax.h @@ -0,0 +1,37 @@ +/** + * lib/minmax.c: windowed min/max tracker by Kathleen Nichols. + * + */ +#ifndef MINMAX_H +#define MINMAX_H + +#include + +/* A single data point for our parameterized min-max tracker */ +struct minmax_sample { + u32 t; /* time measurement was taken */ + u32 v; /* value measured */ +}; + +/* State for the parameterized min-max tracker */ +struct minmax { + struct minmax_sample s[3]; +}; + +static inline u32 minmax_get(const struct minmax *m) +{ + return m->s[0].v; +} + +static inline u32 minmax_reset(struct minmax *m, u32 t, u32 meas) +{ + struct minmax_sample val = { .t = t, .v = meas }; + + m->s[2] = m->s[1] = m->s[0] = val; + return m->s[0].v; +} + +u32 minmax_running_max(struct minmax *m, u32 win, u32 t, u32 meas); +u32 minmax_running_min(struct minmax *m, u32 win, u32 t, u32 meas); + +#endif -- cgit v1.2.3 From 6403389211e1f4d40ed963fe47a96fce1a3ba7a9 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Mon, 19 Sep 2016 23:39:10 -0400 Subject: tcp: use windowed min filter library for TCP min_rtt estimation Refactor the TCP min_rtt code to reuse the new win_minmax library in lib/win_minmax.c to simplify the TCP code. This is a pure refactor: the functionality is exactly the same. We just moved the windowed min code to make TCP easier to read and maintain, and to allow other parts of the kernel to use the windowed min/max filter code. Signed-off-by: Van Jacobson Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/tcp.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index c723a465125d..6433cc8b4667 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -19,6 +19,7 @@ #include +#include #include #include #include @@ -234,9 +235,7 @@ struct tcp_sock { u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ u32 rtt_seq; /* sequence number to update rttvar */ - struct rtt_meas { - u32 rtt, ts; /* RTT in usec and sampling time in jiffies. */ - } rtt_min[3]; + struct minmax rtt_min; u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ -- cgit v1.2.3 From 0682e6902a52aca7caf6ad42551b16ea0f87bc31 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Mon, 19 Sep 2016 23:39:13 -0400 Subject: tcp: count packets marked lost for a TCP connection Count the number of packets that a TCP connection marks lost. Congestion control modules can use this loss rate information for more intelligent decisions about how fast to send. Specifically, this is used in TCP BBR policer detection. BBR uses a high packet loss rate as one signal in its policer detection and policer bandwidth estimation algorithm. The BBR policer detection algorithm cannot simply track retransmits, because a retransmit can be (and often is) an indicator of packets lost long, long ago. This is particularly true in a long CA_Loss period that repairs the initial massive losses when a policer kicks in. Signed-off-by: Van Jacobson Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 6433cc8b4667..38590fbc0ac5 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -267,6 +267,7 @@ struct tcp_sock { * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 delivered; /* Total data packets delivered incl. rexmits */ + u32 lost; /* Total data packets lost incl. rexmits */ u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ -- cgit v1.2.3 From b9f64820fb226a4e8ab10591f46cecd91ca56b30 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Mon, 19 Sep 2016 23:39:14 -0400 Subject: tcp: track data delivery rate for a TCP connection This patch generates data delivery rate (throughput) samples on a per-ACK basis. These rate samples can be used by congestion control modules, and specifically will be used by TCP BBR in later patches in this series. Key state: tp->delivered: Tracks the total number of data packets (original or not) delivered so far. This is an already-existing field. tp->delivered_mstamp: the last time tp->delivered was updated. Algorithm: A rate sample is calculated as (d1 - d0)/(t1 - t0) on a per-ACK basis: d1: the current tp->delivered after processing the ACK t1: the current time after processing the ACK d0: the prior tp->delivered when the acked skb was transmitted t0: the prior tp->delivered_mstamp when the acked skb was transmitted When an skb is transmitted, we snapshot d0 and t0 in its control block in tcp_rate_skb_sent(). When an ACK arrives, it may SACK and ACK some skbs. For each SACKed or ACKed skb, tcp_rate_skb_delivered() updates the rate_sample struct to reflect the latest (d0, t0). Finally, tcp_rate_gen() generates a rate sample by storing (d1 - d0) in rs->delivered and (t1 - t0) in rs->interval_us. One caveat: if an skb was sent with no packets in flight, then tp->delivered_mstamp may be either invalid (if the connection is starting) or outdated (if the connection was idle). In that case, we'll re-stamp tp->delivered_mstamp. At first glance it seems t0 should always be the time when an skb was transmitted, but actually this could over-estimate the rate due to phase mismatch between transmit and ACK events. To track the delivery rate, we ensure that if packets are in flight then t0 and and t1 are times at which packets were marked delivered. If the initial and final RTTs are different then one may be corrupted by some sort of noise. The noise we see most often is sending gaps caused by delayed, compressed, or stretched acks. This either affects both RTTs equally or artificially reduces the final RTT. We approach this by recording the info we need to compute the initial RTT (duration of the "send phase" of the window) when we recorded the associated inflight. Then, for a filter to avoid bandwidth overestimates, we generalize the per-sample bandwidth computation from: bw = delivered / ack_phase_rtt to the following: bw = delivered / max(send_phase_rtt, ack_phase_rtt) In large-scale experiments, this filtering approach incorporating send_phase_rtt is effective at avoiding bandwidth overestimates due to ACK compression or stretched ACKs. Signed-off-by: Van Jacobson Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 38590fbc0ac5..c50e6aec005a 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -268,6 +268,8 @@ struct tcp_sock { u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 delivered; /* Total data packets delivered incl. rexmits */ u32 lost; /* Total data packets lost incl. rexmits */ + struct skb_mstamp first_tx_mstamp; /* start of window send phase */ + struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */ u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ -- cgit v1.2.3 From d7722e8570fc0f1e003cee7cf37694041828918b Mon Sep 17 00:00:00 2001 From: Soheil Hassas Yeganeh Date: Mon, 19 Sep 2016 23:39:15 -0400 Subject: tcp: track application-limited rate samples This commit adds code to track whether the delivery rate represented by each rate_sample was limited by the application. Upon each transmit, we store in the is_app_limited field in the skb a boolean bit indicating whether there is a known "bubble in the pipe": a point in the rate sample interval where the sender was application-limited, and did not transmit even though the cwnd and pacing rate allowed it. This logic marks the flow app-limited on a write if *all* of the following are true: 1) There is less than 1 MSS of unsent data in the write queue available to transmit. 2) There is no packet in the sender's queues (e.g. in fq or the NIC tx queue). 3) The connection is not limited by cwnd. 4) There are no lost packets to retransmit. The tcp_rate_check_app_limited() code in tcp_rate.c determines whether the connection is application-limited at the moment. If the flow is application-limited, it sets the tp->app_limited field. If the flow is application-limited then that means there is effectively a "bubble" of silence in the pipe now, and this silence will be reflected in a lower bandwidth sample for any rate samples from now until we get an ACK indicating this bubble has exited the pipe: specifically, until we get an ACK for the next packet we transmit. When we send every skb we record in scb->tx.is_app_limited whether the resulting rate sample will be application-limited. The code in tcp_rate_gen() checks to see when it is safe to mark all known application-limited bubbles of silence as having exited the pipe. It does this by checking to see when the delivered count moves past the tp->app_limited marker. At this point it zeroes the tp->app_limited marker, as all known bubbles are out of the pipe. We make room for the tx.is_app_limited bit in the skb by borrowing a bit from the in_flight field used by NV to record the number of bytes in flight. The receive window in the TCP header is 16 bits, and the max receive window scaling shift factor is 14 (RFC 1323). So the max receive window offered by the TCP protocol is 2^(16+14) = 2^30. So we only need 30 bits for the tx.in_flight used by NV. Signed-off-by: Van Jacobson Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index c50e6aec005a..fdcd00ffcb66 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -268,6 +268,7 @@ struct tcp_sock { u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 delivered; /* Total data packets delivered incl. rexmits */ u32 lost; /* Total data packets lost incl. rexmits */ + u32 app_limited; /* limited until "delivered" reaches this val */ struct skb_mstamp first_tx_mstamp; /* start of window send phase */ struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */ -- cgit v1.2.3 From eb8329e0a04db0061f714f033b4454326ba147f4 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Mon, 19 Sep 2016 23:39:16 -0400 Subject: tcp: export data delivery rate This commit export two new fields in struct tcp_info: tcpi_delivery_rate: The most recent goodput, as measured by tcp_rate_gen(). If the socket is limited by the sending application (e.g., no data to send), it reports the highest measurement instead of the most recent. The unit is bytes per second (like other rate fields in tcp_info). tcpi_delivery_rate_app_limited: A boolean indicating if the goodput was measured when the socket's throughput was limited by the sending application. This delivery rate information can be useful for applications that want to know the current throughput the TCP connection is seeing, e.g. adaptive bitrate video streaming. It can also be very useful for debugging or troubleshooting. Signed-off-by: Van Jacobson Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/tcp.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fdcd00ffcb66..a17ae7b85218 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -213,7 +213,8 @@ struct tcp_sock { u8 reord; /* reordering detected */ } rack; u16 advmss; /* Advertised MSS */ - u8 unused; + u8 rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ + unused:7; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ thin_dupack : 1,/* Fast retransmit on first dupack */ @@ -271,6 +272,8 @@ struct tcp_sock { u32 app_limited; /* limited until "delivered" reaches this val */ struct skb_mstamp first_tx_mstamp; /* start of window send phase */ struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */ + u32 rate_delivered; /* saved rate sample: packets delivered */ + u32 rate_interval_us; /* saved rate sample: time elapsed */ u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ -- cgit v1.2.3 From 332ae8e2f6ecda5e50c5c62ed62894963e3a83f5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 21 Sep 2016 11:43:53 +0100 Subject: net: cls_bpf: add hardware offload This patch adds hardware offload capability to cls_bpf classifier, similar to what have been done with U32 and flower. Signed-off-by: Jakub Kicinski Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a10d8d18ce19..69f242c71865 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -789,6 +789,7 @@ enum { TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, TC_SETUP_MATCHALL, + TC_SETUP_CLSBPF, }; struct tc_cls_u32_offload; @@ -800,6 +801,7 @@ struct tc_to_netdev { struct tc_cls_u32_offload *cls_u32; struct tc_cls_flower_offload *cls_flower; struct tc_cls_matchall_offload *cls_mall; + struct tc_cls_bpf_offload *cls_bpf; }; }; -- cgit v1.2.3 From 58e2af8b3a6b587e4ac8414343581da4349d3c0f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 21 Sep 2016 11:43:57 +0100 Subject: bpf: expose internal verfier structures Move verifier's internal structures to a header file and prefix their names with bpf_ to avoid potential namespace conflicts. Those structures will soon be used by external analyzers. Signed-off-by: Jakub Kicinski Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 79 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 79 insertions(+) create mode 100644 include/linux/bpf_verifier.h (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h new file mode 100644 index 000000000000..9457a22fc6e0 --- /dev/null +++ b/include/linux/bpf_verifier.h @@ -0,0 +1,79 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _LINUX_BPF_VERIFIER_H +#define _LINUX_BPF_VERIFIER_H 1 + +#include /* for enum bpf_reg_type */ +#include /* for MAX_BPF_STACK */ + +struct bpf_reg_state { + enum bpf_reg_type type; + union { + /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ + s64 imm; + + /* valid when type == PTR_TO_PACKET* */ + struct { + u32 id; + u16 off; + u16 range; + }; + + /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | + * PTR_TO_MAP_VALUE_OR_NULL + */ + struct bpf_map *map_ptr; + }; +}; + +enum bpf_stack_slot_type { + STACK_INVALID, /* nothing was stored in this stack slot */ + STACK_SPILL, /* register spilled into stack */ + STACK_MISC /* BPF program wrote some data into this slot */ +}; + +#define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ + +/* state of the program: + * type of all registers and stack info + */ +struct bpf_verifier_state { + struct bpf_reg_state regs[MAX_BPF_REG]; + u8 stack_slot_type[MAX_BPF_STACK]; + struct bpf_reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE]; +}; + +/* linked list of verifier states used to prune search */ +struct bpf_verifier_state_list { + struct bpf_verifier_state state; + struct bpf_verifier_state_list *next; +}; + +struct bpf_insn_aux_data { + enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ +}; + +#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ + +/* single container for all structs + * one verifier_env per bpf_check() call + */ +struct bpf_verifier_env { + struct bpf_prog *prog; /* eBPF program being verified */ + struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ + int stack_size; /* number of states to be processed */ + struct bpf_verifier_state cur_state; /* current verifier state */ + struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ + struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ + u32 used_map_cnt; /* number of used maps */ + u32 id_gen; /* used to generate unique reg IDs */ + bool allow_ptr_leaks; + bool seen_direct_write; + struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ +}; + +#endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From 13a27dfc669724564aafa2699976ee756029fed2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 21 Sep 2016 11:43:58 +0100 Subject: bpf: enable non-core use of the verfier Advanced JIT compilers and translators may want to use eBPF verifier as a base for parsers or to perform custom checks and validations. Add ability for external users to invoke the verifier and provide callbacks to be invoked for every intruction checked. For now only add most basic callback for per-instruction pre-interpretation checks is added. More advanced users may also like to have per-instruction post callback and state comparison callback. Signed-off-by: Jakub Kicinski Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 9457a22fc6e0..c5cb661712c9 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -59,6 +59,12 @@ struct bpf_insn_aux_data { #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ +struct bpf_verifier_env; +struct bpf_ext_analyzer_ops { + int (*insn_hook)(struct bpf_verifier_env *env, + int insn_idx, int prev_insn_idx); +}; + /* single container for all structs * one verifier_env per bpf_check() call */ @@ -68,6 +74,8 @@ struct bpf_verifier_env { int stack_size; /* number of states to be processed */ struct bpf_verifier_state cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ + const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */ + void *analyzer_priv; /* pointer to external analyzer's private data */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ u32 used_map_cnt; /* number of used maps */ u32 id_gen; /* used to generate unique reg IDs */ @@ -76,4 +84,7 @@ struct bpf_verifier_env { struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ }; +int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, + void *priv); + #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From bfca4c520f7ea78138ddccea2de18dc062b0fefd Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Mon, 19 Sep 2016 19:11:09 +0300 Subject: net: skbuff: Export __skb_vlan_pop This exports the functionality of extracting the tag from the payload, without moving next vlan tag into hw accel tag. Signed-off-by: Shmulik Ladkani Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c6dab3f7457c..9bf60b556bd2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3085,6 +3085,7 @@ bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, int write_len); +int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, -- cgit v1.2.3 From efee95f42b5dddedcaff0a0eaa44e170fc7522e8 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 20 Sep 2016 19:25:58 -0400 Subject: ptp_clock: future-proofing drivers against PTP subsystem becoming optional Drivers must be ready to accept NULL from ptp_clock_register() if the PTP clock subsystem is configured out. This patch documents that and ensures that all drivers cope well with a NULL return. Signed-off-by: Nicolas Pitre Reviewed-by: Eugenia Emantayev Acked-by: Richard Cochran Acked-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 6b15e168148a..5ad54fc66cf0 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -127,6 +127,11 @@ struct ptp_clock; * * @info: Structure describing the new clock. * @parent: Pointer to the parent device of the new clock. + * + * Returns a valid pointer on success or PTR_ERR on failure. If PHC + * support is missing at the configuration level, this function + * returns NULL, and drivers are expected to gracefully handle that + * case separately. */ extern struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, -- cgit v1.2.3 From 77f2efcbdd7133466060198e02c6e8a170c3cd14 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 22 Sep 2016 00:29:01 +0100 Subject: rxrpc: Add ktime_sub_ms() Add a ktime_sub_ms() to go with ktime_add_ms() and co. for use in AF_RXRPC RTT determination. Signed-off-by: David Howells --- include/linux/ktime.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 2b6a204bd8d4..aa118bad1407 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -231,6 +231,11 @@ static inline ktime_t ktime_sub_us(const ktime_t kt, const u64 usec) return ktime_sub_ns(kt, usec * NSEC_PER_USEC); } +static inline ktime_t ktime_sub_ms(const ktime_t kt, const u64 msec) +{ + return ktime_sub_ns(kt, msec * NSEC_PER_MSEC); +} + extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); /** -- cgit v1.2.3 From 572de608e36279f249c9a6350f142e69f23dacab Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Thu, 22 Sep 2016 10:33:54 +0800 Subject: net: ethernet: mediatek: add extension of phy-mode for TRGMII adds PHY-mode "trgmii" as an extension for the operation mode of the PHY interface for PHY_INTERFACE_MODE_TRGMII. and adds a variable trgmii inside mtk_mac as the indication to make the difference between the MAC connected to internal switch or connected to external PHY by the given configuration on the board and then to perform the corresponding setup on TRGMII hardware module. Signed-off-by: Sean Wang Cc: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 2d24b283aa2d..e25f1830fbcf 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -80,6 +80,7 @@ typedef enum { PHY_INTERFACE_MODE_XGMII, PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_QSGMII, + PHY_INTERFACE_MODE_TRGMII, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -123,6 +124,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "moca"; case PHY_INTERFACE_MODE_QSGMII: return "qsgmii"; + case PHY_INTERFACE_MODE_TRGMII: + return "trgmii"; default: return "unknown"; } -- cgit v1.2.3 From 7c3d21c8153c6bfb5690e35e086b0522c42442d9 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Thu, 22 Sep 2016 12:11:13 +0300 Subject: net/mlx4_core: Preparation for VF vlan protocol 802.1ad Check device capability to support VF vlan protocol 802.1ad mode. Add vport attribute vlan protocol. Init vport vlan protocol by default to 802.1Q. Add update QP support for VF vlan protocol 802.1ad. Add func capability vlan_offload_disable to disable all vlan HW acceleration on VF while the VF is set to VF vlan protocol 802.1ad mode. No change in VF vlan protocol 802.1Q (VST) mode. Signed-off-by: Moshe Shemesh Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 3 +++ include/linux/mlx4/qp.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 42da3552f7cb..59b50d3eedb4 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -221,6 +221,7 @@ enum { MLX4_DEV_CAP_FLAG2_ROCE_V1_V2 = 1ULL << 33, MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER = 1ULL << 34, MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT = 1ULL << 35, + MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP = 1ULL << 36, }; enum { @@ -1371,6 +1372,8 @@ int mlx4_SET_PORT_fcs_check(struct mlx4_dev *dev, u8 port, int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering, int enable); int set_phv_bit(struct mlx4_dev *dev, u8 port, int new_val); int get_phv_bit(struct mlx4_dev *dev, u8 port, int *phv); +int mlx4_get_is_vlan_offload_disabled(struct mlx4_dev *dev, u8 port, + bool *vlan_offload_disabled); int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx); int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index deaa2217214d..b4ee8f62ce8d 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -160,6 +160,7 @@ struct mlx4_qp_path { enum { /* fl */ MLX4_FL_CV = 1 << 6, + MLX4_FL_SV = 1 << 5, MLX4_FL_ETH_HIDE_CQE_VLAN = 1 << 2, MLX4_FL_ETH_SRC_CHECK_MC_LB = 1 << 1, MLX4_FL_ETH_SRC_CHECK_UC_LB = 1 << 0, @@ -267,6 +268,7 @@ enum { MLX4_UPD_QP_PATH_MASK_FVL_RX = 16 + 32, MLX4_UPD_QP_PATH_MASK_ETH_SRC_CHECK_UC_LB = 18 + 32, MLX4_UPD_QP_PATH_MASK_ETH_SRC_CHECK_MC_LB = 19 + 32, + MLX4_UPD_QP_PATH_MASK_SV = 22 + 32, }; enum { /* param3 */ -- cgit v1.2.3 From 79aab093a0b5370d7fc4e99df75996f4744dc03f Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Thu, 22 Sep 2016 12:11:15 +0300 Subject: net: Update API for VF vlan protocol 802.1ad support Introduce new rtnl UAPI that exposes a list of vlans per VF, giving the ability for user-space application to specify it for the VF, as an option to support 802.1ad. We adjusted IP Link tool to support this option. For future use cases, the new UAPI supports multiple vlans. For now we limit the list size to a single vlan in kernel. Add IFLA_VF_VLAN_LIST in addition to IFLA_VF_VLAN to keep backward compatibility with older versions of IP Link tool. Add a vlan protocol parameter to the ndo_set_vf_vlan callback. We kept 802.1Q as the drivers' default vlan protocol. Suitable ip link tool command examples: Set vf vlan protocol 802.1ad: ip link set eth0 vf 1 vlan 100 proto 802.1ad Set vf to VST (802.1Q) mode: ip link set eth0 vf 1 vlan 100 proto 802.1Q Or by omitting the new parameter ip link set eth0 vf 1 vlan 100 Signed-off-by: Moshe Shemesh Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/if_link.h | 1 + include/linux/netdevice.h | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index f923d15b432c..0b17c585b5cd 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -25,5 +25,6 @@ struct ifla_vf_info { __u32 max_tx_rate; __u32 rss_query_en; __u32 trusted; + __be16 vlan_proto; }; #endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 69f242c71865..1e8a5c734d72 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -946,7 +946,8 @@ struct netdev_xdp { * * SR-IOV management functions. * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); - * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos); + * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, + * u8 qos, __be16 proto); * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); @@ -1187,7 +1188,8 @@ struct net_device_ops { int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, - int queue, u16 vlan, u8 qos); + int queue, u16 vlan, + u8 qos, __be16 proto); int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate); -- cgit v1.2.3 From b42959dc35a533a531dd698b581193a65a5da831 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Thu, 22 Sep 2016 12:11:16 +0300 Subject: net/mlx4: Add VF vlan protocol 802.1ad support Move the vf to VST 802.1ad mode (mlx4 VST QinQ mode) by setting vf vlan protocol to 802.1ad. VST 802.1ad mode in mlx4, is used for STAG strip/insertion by PF, while the CTAG is set by the VF. Read current vlan protocol as part of the vf configuration state. Upon setting vf vlan protocol to 802.1ad, we use a mechanism of handshake to verify that both the vf and the pf driver version support it. The handshake uses the command QUERY_FUNC_CAP: - The vf sets a pre-defined support bit in input modifier. - A pf that supports the feature sends the request to the vf through a pre-defined field in the output mailbox. - In case vf does not support the feature, the pf will fail the control command (in this case, IP link tool command to set the vf vlan protocol to 802.1ad). No change in VST 802.1Q mode. Signed-off-by: Moshe Shemesh Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 116b284bc4ce..1f3568694a57 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -309,7 +309,8 @@ int mlx4_get_vf_stats(struct mlx4_dev *dev, int port, int vf_idx, struct ifla_vf_stats *vf_stats); u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); -int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); +int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, + u8 qos, __be16 proto); int mlx4_set_vf_rate(struct mlx4_dev *dev, int port, int vf, int min_tx_rate, int max_tx_rate); int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting); -- cgit v1.2.3