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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 --- drivers/nvme/host/fabrics.c | 10 +++++----- drivers/nvme/host/fabrics.h | 2 +- include/linux/nvme.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 020302c6ea57..be0b1067c9fa 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -56,7 +56,7 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn) kref_init(&host->ref); memcpy(host->nqn, hostnqn, NVMF_NQN_SIZE); - uuid_le_gen(&host->id); + uuid_be_gen(&host->id); list_add_tail(&host->list, &nvmf_hosts); out_unlock: @@ -73,9 +73,9 @@ static struct nvmf_host *nvmf_host_default(void) return NULL; kref_init(&host->ref); - uuid_le_gen(&host->id); + uuid_be_gen(&host->id); snprintf(host->nqn, NVMF_NQN_SIZE, - "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUl", &host->id); + "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUb", &host->id); mutex_lock(&nvmf_hosts_mutex); list_add_tail(&host->list, &nvmf_hosts); @@ -382,7 +382,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) if (!data) return -ENOMEM; - memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le)); + memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be)); data->cntlid = cpu_to_le16(0xffff); strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); @@ -441,7 +441,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) if (!data) return -ENOMEM; - memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le)); + memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be)); data->cntlid = cpu_to_le16(ctrl->cntlid); strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 89df52c8be97..46e460aee52d 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -34,7 +34,7 @@ struct nvmf_host { struct kref ref; struct list_head list; char nqn[NVMF_NQN_SIZE]; - uuid_le id; + uuid_be id; }; /** 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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 --- drivers/iio/adc/ti_am335x_adc.c | 2 +- include/linux/mfd/ti_am335x_tscadc.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index bed9977a1863..c3cfacca2541 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -381,7 +381,7 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, am335x_tsc_se_set_once(adc_dev->mfd_tscadc, step_en); - timeout = jiffies + usecs_to_jiffies + timeout = jiffies + msecs_to_jiffies (IDLE_TIMEOUT * adc_dev->channels); /* Wait for Fifo threshold interrupt */ while (1) { 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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 --- .../media/uapi/cec/cec-ioc-adap-g-log-addrs.rst | 21 ++++++++++++++++++++- drivers/staging/media/cec/cec-adap.c | 4 ++++ drivers/staging/media/cec/cec-api.c | 2 +- include/linux/cec.h | 5 ++++- 4 files changed, 29 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst index 04ee90099676..201d4839931c 100644 --- a/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst +++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst @@ -144,7 +144,7 @@ logical address types are already defined will return with error ``EBUSY``. - ``flags`` - - Flags. No flags are defined yet, so set this to 0. + - Flags. See :ref:`cec-log-addrs-flags` for a list of available flags. - .. row 7 @@ -201,6 +201,25 @@ logical address types are already defined will return with error ``EBUSY``. give the CEC framework more information about the device type, even though the framework won't use it directly in the CEC message. +.. _cec-log-addrs-flags: + +.. flat-table:: Flags for struct cec_log_addrs + :header-rows: 0 + :stub-columns: 0 + :widths: 3 1 4 + + + - .. _`CEC-LOG-ADDRS-FL-ALLOW-UNREG-FALLBACK`: + + - ``CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK`` + + - 1 + + - By default if no logical address of the requested type can be claimed, then + it will go back to the unconfigured state. If this flag is set, then it will + fallback to the Unregistered logical address. Note that if the Unregistered + logical address was explicitly requested, then this flag has no effect. + .. _cec-versions: .. flat-table:: CEC Versions diff --git a/drivers/staging/media/cec/cec-adap.c b/drivers/staging/media/cec/cec-adap.c index 9dcb784b8d6a..2458a6c87642 100644 --- a/drivers/staging/media/cec/cec-adap.c +++ b/drivers/staging/media/cec/cec-adap.c @@ -1047,6 +1047,10 @@ static int cec_config_thread_func(void *arg) dprintk(1, "could not claim LA %d\n", i); } + if (adap->log_addrs.log_addr_mask == 0 && + !(las->flags & CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK)) + goto unconfigure; + configured: if (adap->log_addrs.log_addr_mask == 0) { /* Fall back to unregistered */ diff --git a/drivers/staging/media/cec/cec-api.c b/drivers/staging/media/cec/cec-api.c index 4e2696a34ddb..6f58ee85eea4 100644 --- a/drivers/staging/media/cec/cec-api.c +++ b/drivers/staging/media/cec/cec-api.c @@ -162,7 +162,7 @@ static long cec_adap_s_log_addrs(struct cec_adapter *adap, struct cec_fh *fh, return -ENOTTY; if (copy_from_user(&log_addrs, parg, sizeof(log_addrs))) return -EFAULT; - log_addrs.flags = 0; + log_addrs.flags &= CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK; mutex_lock(&adap->lock); if (!adap->is_configuring && (!log_addrs.num_log_addrs || !adap->is_configured) && 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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 --- fs/iomap.c | 5 ++++- include/linux/iomap.h | 8 +++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap.c b/fs/iomap.c index 0342254646e3..706270f21b35 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -428,9 +428,12 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi, break; } + if (iomap->flags & IOMAP_F_MERGED) + flags |= FIEMAP_EXTENT_MERGED; + return fiemap_fill_next_extent(fi, iomap->offset, iomap->blkno != IOMAP_NULL_BLOCK ? iomap->blkno << 9: 0, - iomap->length, flags | FIEMAP_EXTENT_MERGED); + iomap->length, flags); } 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 v1.3-14-g43fede 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 --- arch/parisc/Kconfig | 1 - arch/parisc/configs/c8000_defconfig | 1 - arch/parisc/configs/generic-64bit_defconfig | 1 - arch/parisc/include/asm/uaccess.h | 22 ++++----- arch/s390/Kconfig | 1 - arch/s390/configs/default_defconfig | 1 - arch/s390/configs/gcov_defconfig | 1 - arch/s390/configs/performance_defconfig | 1 - arch/s390/defconfig | 1 - arch/s390/include/asm/uaccess.h | 19 +++++--- arch/tile/Kconfig | 1 - arch/tile/include/asm/uaccess.h | 22 +++++---- arch/x86/Kconfig | 1 - arch/x86/include/asm/uaccess.h | 69 ++++------------------------- include/asm-generic/uaccess.h | 1 + include/linux/compiler-gcc.h | 2 +- lib/Kconfig.debug | 18 -------- lib/Makefile | 1 - lib/usercopy.c | 9 ---- 19 files changed, 45 insertions(+), 128 deletions(-) delete mode 100644 lib/usercopy.c (limited to 'include/linux') diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index cd8778103165..af12c2db9bb8 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -1,6 +1,5 @@ config PARISC def_bool y - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_IDE select HAVE_OPROFILE diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig index 1a8f6f95689e..f6a4c016304b 100644 --- a/arch/parisc/configs/c8000_defconfig +++ b/arch/parisc/configs/c8000_defconfig @@ -245,7 +245,6 @@ CONFIG_DEBUG_RT_MUTEXES=y CONFIG_PROVE_RCU_DELAY=y CONFIG_DEBUG_BLOCK_EXT_DEVT=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_KEYS=y # CONFIG_CRYPTO_HW is not set CONFIG_FONTS=y diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index 7e0792658952..c564e6e1fa23 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -291,7 +291,6 @@ CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y # CONFIG_SCHED_DEBUG is not set CONFIG_TIMER_STATS=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 0f59fd9ca205..e9150487e20d 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -208,13 +208,13 @@ unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned lo #define __copy_to_user_inatomic __copy_to_user #define __copy_from_user_inatomic __copy_from_user -extern void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS - __compiletime_error("copy_from_user() buffer size is not provably correct") -#else - __compiletime_warning("copy_from_user() buffer size is not provably correct") -#endif -; +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, @@ -223,10 +223,12 @@ static inline unsigned long __must_check copy_from_user(void *to, int sz = __compiletime_object_size(to); int ret = -EFAULT; - if (likely(sz == -1 || !__builtin_constant_p(n) || sz >= n)) + if (likely(sz == -1 || sz >= n)) ret = __copy_from_user(to, from, n); - else - copy_from_user_overflow(); + else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); return ret; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e751fe25d6ab..c109f073d454 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -68,7 +68,6 @@ config DEBUG_RODATA config S390 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 26e0c7f08814..412b1bd21029 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -602,7 +602,6 @@ CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_IRQSOFF_TRACER=y CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index 24879dab47bc..bec279eb4b93 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -552,7 +552,6 @@ CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_CPU_NOTIFIER_ERROR_INJECT=m CONFIG_PM_NOTIFIER_ERROR_INJECT=m CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_BLK_DEV_IO_TRACE=y # CONFIG_KPROBE_EVENT is not set CONFIG_TRACE_ENUM_MAP_FILE=y diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index a5c1e5f2a0ca..1751446a5bbb 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -549,7 +549,6 @@ CONFIG_TIMER_STATS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_STACK_TRACER=y diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 73610f2e3b4f..2d40ef0a6295 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -172,7 +172,6 @@ CONFIG_DEBUG_NOTIFIERS=y CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_RCU_TRACE=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 9b49cf1daa8f..95aefdba4be2 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -311,6 +311,14 @@ int __get_user_bad(void) __attribute__((noreturn)); #define __put_user_unaligned __put_user #define __get_user_unaligned __get_user +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} + /** * copy_to_user: - Copy a block of data into user space. * @to: Destination address, in user space. @@ -332,12 +340,6 @@ copy_to_user(void __user *to, const void *from, unsigned long n) return __copy_to_user(to, from, n); } -void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -__compiletime_warning("copy_from_user() buffer size is not provably correct") -#endif -; - /** * copy_from_user: - Copy a block of data from user space. * @to: Destination address, in kernel space. @@ -362,7 +364,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n) might_fault(); if (unlikely(sz != -1 && sz < n)) { - copy_from_user_overflow(); + if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); return n; } return __copy_from_user(to, from, n); diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 4820a02838ac..78da75b670bc 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -4,7 +4,6 @@ config TILE def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_WANT_FRAME_POINTERS diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h index 0a9c4265763b..a77369e91e54 100644 --- a/arch/tile/include/asm/uaccess.h +++ b/arch/tile/include/asm/uaccess.h @@ -416,14 +416,13 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) return n; } -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -/* - * There are still unprovable places in the generic code as of 2.6.34, so this - * option is not really compatible with -Werror, which is more useful in - * general. - */ -extern void copy_from_user_overflow(void) - __compiletime_warning("copy_from_user() size is not provably correct"); +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, @@ -433,14 +432,13 @@ static inline unsigned long __must_check copy_from_user(void *to, if (likely(sz == -1 || sz >= n)) n = _copy_from_user(to, from, n); + else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - copy_from_user_overflow(); + __bad_copy_user(); return n; } -#else -#define copy_from_user _copy_from_user -#endif #ifdef __tilegx__ /** diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c580d8c33562..2a1f0ce7c59a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -24,7 +24,6 @@ config X86 select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a0ae610b9280..c3f291195294 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -697,43 +697,14 @@ unsigned long __must_check _copy_from_user(void *to, const void __user *from, unsigned long __must_check _copy_to_user(void __user *to, const void *from, unsigned n); -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -# define copy_user_diag __compiletime_error -#else -# define copy_user_diag __compiletime_warning -#endif - -extern void copy_user_diag("copy_from_user() buffer size is too small") -copy_from_user_overflow(void); -extern void copy_user_diag("copy_to_user() buffer size is too small") -copy_to_user_overflow(void) __asm__("copy_from_user_overflow"); - -#undef copy_user_diag - -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS - -extern void -__compiletime_warning("copy_from_user() buffer size is not provably correct") -__copy_from_user_overflow(void) __asm__("copy_from_user_overflow"); -#define __copy_from_user_overflow(size, count) __copy_from_user_overflow() - -extern void -__compiletime_warning("copy_to_user() buffer size is not provably correct") -__copy_to_user_overflow(void) __asm__("copy_from_user_overflow"); -#define __copy_to_user_overflow(size, count) __copy_to_user_overflow() - -#else +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); -static inline void -__copy_from_user_overflow(int size, unsigned long count) +static inline void copy_user_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } -#define __copy_to_user_overflow __copy_from_user_overflow - -#endif - static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { @@ -743,31 +714,13 @@ copy_from_user(void *to, const void __user *from, unsigned long n) kasan_check_write(to, n); - /* - * While we would like to have the compiler do the checking for us - * even in the non-constant size case, any false positives there are - * a problem (especially when DEBUG_STRICT_USER_COPY_CHECKS, but even - * without - the [hopefully] dangerous looking nature of the warning - * would make people go look at the respecitive call sites over and - * over again just to find that there's no problem). - * - * And there are cases where it's just not realistic for the compiler - * to prove the count to be in range. For example when multiple call - * sites of a helper function - perhaps in different source files - - * all doing proper range checking, yet the helper function not doing - * so again. - * - * Therefore limit the compile time checking to the constant size - * case, and do only runtime checking for non-constant sizes. - */ - if (likely(sz < 0 || sz >= n)) { check_object_size(to, n, false); n = _copy_from_user(to, from, n); - } else if (__builtin_constant_p(n)) - copy_from_user_overflow(); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - __copy_from_user_overflow(sz, n); + __bad_copy_user(); return n; } @@ -781,21 +734,17 @@ copy_to_user(void __user *to, const void *from, unsigned long n) might_fault(); - /* See the comment in copy_from_user() above. */ if (likely(sz < 0 || sz >= n)) { check_object_size(from, n, true); n = _copy_to_user(to, from, n); - } else if (__builtin_constant_p(n)) - copy_to_user_overflow(); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - __copy_to_user_overflow(sz, n); + __bad_copy_user(); return n; } -#undef __copy_from_user_overflow -#undef __copy_to_user_overflow - /* * We rely on the nested NMI work to allow atomic faults from the NMI path; the * nested NMI paths are careful to preserve CR2. diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index 1bfa602958f2..5dea1fb6979c 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -72,6 +72,7 @@ struct exception_table_entry /* Returns 0 if exception not found and fixup otherwise. */ extern unsigned long search_exception_table(unsigned long); + /* * architectures with an MMU should override these two */ 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 diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2307d7c89dac..2e2cca509231 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1686,24 +1686,6 @@ config LATENCYTOP Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. -config ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS - bool - -config DEBUG_STRICT_USER_COPY_CHECKS - bool "Strict user copy size checks" - depends on ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS - depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING - help - Enabling this option turns a certain set of sanity checks for user - copy operations into compile time failures. - - The copy_from_user() etc checks are there to help test if there - are sufficient security checks on the length argument of - the copy operation, by having gcc prove that the argument is - within bounds. - - If unsure, say N. - source kernel/trace/Kconfig menu "Runtime Testing" diff --git a/lib/Makefile b/lib/Makefile index cfa68eb269e4..5dc77a8ec297 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -24,7 +24,6 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o -obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o lib-$(CONFIG_HAS_DMA) += dma-noop.o diff --git a/lib/usercopy.c b/lib/usercopy.c deleted file mode 100644 index 4f5b1ddbcd25..000000000000 --- a/lib/usercopy.c +++ /dev/null @@ -1,9 +0,0 @@ -#include -#include -#include - -void copy_from_user_overflow(void) -{ - WARN(1, "Buffer overflow detected!\n"); -} -EXPORT_SYMBOL(copy_from_user_overflow); -- cgit v1.3-14-g43fede 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 --- Documentation/devicetree/bindings/serial/8250.txt | 19 ------------ drivers/tty/serial/8250/8250.h | 35 +---------------------- drivers/tty/serial/8250/8250_core.c | 9 ------ drivers/tty/serial/8250/8250_omap.c | 31 +++++++++----------- drivers/tty/serial/8250/8250_port.c | 7 +---- drivers/tty/serial/8250/Kconfig | 1 - include/linux/serial_8250.h | 1 - 7 files changed, 15 insertions(+), 88 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/serial/8250.txt b/Documentation/devicetree/bindings/serial/8250.txt index f5561ac7e17e..936ab5b87324 100644 --- a/Documentation/devicetree/bindings/serial/8250.txt +++ b/Documentation/devicetree/bindings/serial/8250.txt @@ -42,9 +42,6 @@ Optional properties: - auto-flow-control: one way to enable automatic flow control support. The driver is allowed to detect support for the capability even without this property. -- {rts,cts,dtr,dsr,rng,dcd}-gpios: specify a GPIO for RTS/CTS/DTR/DSR/RI/DCD - line respectively. It will use specified GPIO instead of the peripheral - function pin for the UART feature. If unsure, don't specify this property. Note: * fsl,ns16550: @@ -66,19 +63,3 @@ Example: interrupts = <10>; reg-shift = <2>; }; - -Example for OMAP UART using GPIO-based modem control signals: - - uart4: serial@49042000 { - compatible = "ti,omap3-uart"; - reg = <0x49042000 0x400>; - interrupts = <80>; - ti,hwmods = "uart4"; - clock-frequency = <48000000>; - cts-gpios = <&gpio3 5 GPIO_ACTIVE_LOW>; - rts-gpios = <&gpio3 6 GPIO_ACTIVE_LOW>; - dtr-gpios = <&gpio1 12 GPIO_ACTIVE_LOW>; - dsr-gpios = <&gpio1 13 GPIO_ACTIVE_LOW>; - dcd-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; - rng-gpios = <&gpio1 15 GPIO_ACTIVE_LOW>; - }; diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 122e0e4029fe..1a16feac9a36 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -15,8 +15,6 @@ #include #include -#include "../serial_mctrl_gpio.h" - struct uart_8250_dma { int (*tx_dma)(struct uart_8250_port *p); int (*rx_dma)(struct uart_8250_port *p); @@ -133,43 +131,12 @@ void serial8250_em485_destroy(struct uart_8250_port *p); static inline void serial8250_out_MCR(struct uart_8250_port *up, int value) { - int mctrl_gpio = 0; - serial_out(up, UART_MCR, value); - - if (value & UART_MCR_RTS) - mctrl_gpio |= TIOCM_RTS; - if (value & UART_MCR_DTR) - mctrl_gpio |= TIOCM_DTR; - - mctrl_gpio_set(up->gpios, mctrl_gpio); } static inline int serial8250_in_MCR(struct uart_8250_port *up) { - int mctrl, mctrl_gpio = 0; - - mctrl = serial_in(up, UART_MCR); - - /* save current MCR values */ - if (mctrl & UART_MCR_RTS) - mctrl_gpio |= TIOCM_RTS; - if (mctrl & UART_MCR_DTR) - mctrl_gpio |= TIOCM_DTR; - - mctrl_gpio = mctrl_gpio_get_outputs(up->gpios, &mctrl_gpio); - - if (mctrl_gpio & TIOCM_RTS) - mctrl |= UART_MCR_RTS; - else - mctrl &= ~UART_MCR_RTS; - - if (mctrl_gpio & TIOCM_DTR) - mctrl |= UART_MCR_DTR; - else - mctrl &= ~UART_MCR_DTR; - - return mctrl; + return serial_in(up, UART_MCR); } #if defined(__alpha__) && !defined(CONFIG_PCI) diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 13ad5c3d2e68..dcf43f66404f 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -974,8 +974,6 @@ int serial8250_register_8250_port(struct uart_8250_port *up) uart = serial8250_find_match_or_unused(&up->port); if (uart && uart->port.type != PORT_8250_CIR) { - struct mctrl_gpios *gpios; - if (uart->port.dev) uart_remove_one_port(&serial8250_reg, &uart->port); @@ -1013,13 +1011,6 @@ int serial8250_register_8250_port(struct uart_8250_port *up) if (up->port.flags & UPF_FIXED_TYPE) uart->port.type = up->port.type; - gpios = mctrl_gpio_init(&uart->port, 0); - if (IS_ERR(gpios)) { - if (PTR_ERR(gpios) != -ENOSYS) - return PTR_ERR(gpios); - } else - uart->gpios = gpios; - serial8250_set_defaults(uart); /* Possibly override default I/O functions. */ diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index e14982f36a04..61ad6c3b20a0 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -134,21 +134,18 @@ static void omap8250_set_mctrl(struct uart_port *port, unsigned int mctrl) serial8250_do_set_mctrl(port, mctrl); - if (IS_ERR_OR_NULL(mctrl_gpio_to_gpiod(up->gpios, - UART_GPIO_RTS))) { - /* - * Turn off autoRTS if RTS is lowered and restore autoRTS - * setting if RTS is raised - */ - lcr = serial_in(up, UART_LCR); - serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); - if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS)) - priv->efr |= UART_EFR_RTS; - else - priv->efr &= ~UART_EFR_RTS; - serial_out(up, UART_EFR, priv->efr); - serial_out(up, UART_LCR, lcr); - } + /* + * Turn off autoRTS if RTS is lowered and restore autoRTS setting + * if RTS is raised + */ + lcr = serial_in(up, UART_LCR); + serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); + if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS)) + priv->efr |= UART_EFR_RTS; + else + priv->efr &= ~UART_EFR_RTS; + serial_out(up, UART_EFR, priv->efr); + serial_out(up, UART_LCR, lcr); } /* @@ -449,9 +446,7 @@ static void omap_8250_set_termios(struct uart_port *port, priv->efr = 0; up->port.status &= ~(UPSTAT_AUTOCTS | UPSTAT_AUTORTS | UPSTAT_AUTOXOFF); - if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW - && IS_ERR_OR_NULL(mctrl_gpio_to_gpiod(up->gpios, - UART_GPIO_RTS))) { + if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW) { /* Enable AUTOCTS (autoRTS is enabled when RTS is raised) */ up->port.status |= UPSTAT_AUTOCTS | UPSTAT_AUTORTS; priv->efr |= UART_EFR_CTS; diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 7481b95c6d84..bdfa659b9606 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1618,8 +1618,6 @@ static void serial8250_disable_ms(struct uart_port *port) if (up->bugs & UART_BUG_NOMSR) return; - mctrl_gpio_disable_ms(up->gpios); - up->ier &= ~UART_IER_MSI; serial_port_out(port, UART_IER, up->ier); } @@ -1632,8 +1630,6 @@ static void serial8250_enable_ms(struct uart_port *port) if (up->bugs & UART_BUG_NOMSR) return; - mctrl_gpio_enable_ms(up->gpios); - up->ier |= UART_IER_MSI; serial8250_rpm_get(up); @@ -1917,8 +1913,7 @@ unsigned int serial8250_do_get_mctrl(struct uart_port *port) ret |= TIOCM_DSR; if (status & UART_MSR_CTS) ret |= TIOCM_CTS; - - return mctrl_gpio_get(up->gpios, &ret); + return ret; } EXPORT_SYMBOL_GPL(serial8250_do_get_mctrl); diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig index c9ec839a5ddf..7c6f7afca5dd 100644 --- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -6,7 +6,6 @@ config SERIAL_8250 tristate "8250/16550 and compatible serial support" select SERIAL_CORE - select SERIAL_MCTRL_GPIO if GPIOLIB ---help--- This selects whether you want to include the driver for the standard serial ports. The standard answer is Y. People who might say N 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 v1.3-14-g43fede 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 --- fs/proc/base.c | 7 +------ include/linux/mm.h | 1 + kernel/fork.c | 23 +++++++++++++++++++++++ 3 files changed, 25 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/base.c b/fs/proc/base.c index 0d163a84082d..da8b1943ba04 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1552,18 +1552,13 @@ static const struct file_operations proc_pid_set_comm_operations = { static int proc_exe_link(struct dentry *dentry, struct path *exe_path) { struct task_struct *task; - struct mm_struct *mm; struct file *exe_file; task = get_proc_task(d_inode(dentry)); if (!task) return -ENOENT; - mm = get_task_mm(task); + exe_file = get_task_exe_file(task); put_task_struct(task); - if (!mm) - return -ENOENT; - exe_file = get_mm_exe_file(mm); - mmput(mm); if (exe_file) { *exe_path = exe_file->f_path; path_get(&exe_file->f_path); 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); diff --git a/kernel/fork.c b/kernel/fork.c index d277e83ed3e0..42451aeb245f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -773,6 +773,29 @@ struct file *get_mm_exe_file(struct mm_struct *mm) } EXPORT_SYMBOL(get_mm_exe_file); +/** + * get_task_exe_file - acquire a reference to the task's executable file + * + * Returns %NULL if task's mm (if any) has no associated executable file or + * this is a kernel thread with borrowed mm (see the comment above get_task_mm). + * User must release file via fput(). + */ +struct file *get_task_exe_file(struct task_struct *task) +{ + struct file *exe_file = NULL; + struct mm_struct *mm; + + task_lock(task); + mm = task->mm; + if (mm) { + if (!(task->flags & PF_KTHREAD)) + exe_file = get_mm_exe_file(mm); + } + task_unlock(task); + return exe_file; +} +EXPORT_SYMBOL(get_task_exe_file); + /** * get_task_mm - acquire a reference to the task's mm * -- cgit v1.3-14-g43fede 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 --- fs/overlayfs/inode.c | 3 +++ include/linux/fs.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d50d1ead1b6f..47a4f33df47b 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -416,6 +416,9 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode) inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_flags |= S_NOCMTIME; +#ifdef CONFIG_FS_POSIX_ACL + inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE; +#endif mode &= S_IFMT; switch (mode) { 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 v1.3-14-g43fede 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 ++++++++++++++-- mm/page_alloc.c | 4 ++-- mm/vmscan.c | 22 +++++++++++----------- 3 files changed, 27 insertions(+), 15 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; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7791a03f8deb..a2214c64ed3c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4360,7 +4360,7 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, do { zone_type--; zone = pgdat->node_zones + zone_type; - if (populated_zone(zone)) { + if (managed_zone(zone)) { zoneref_set_zone(zone, &zonelist->_zonerefs[nr_zones++]); check_highest_zone(zone_type); @@ -4598,7 +4598,7 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) for (j = 0; j < nr_nodes; j++) { node = node_order[j]; z = &NODE_DATA(node)->node_zones[zone_type]; - if (populated_zone(z)) { + if (managed_zone(z)) { zoneref_set_zone(z, &zonelist->_zonerefs[pos++]); check_highest_zone(zone_type); diff --git a/mm/vmscan.c b/mm/vmscan.c index 374d95d04178..b1e12a1ea9cf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1665,7 +1665,7 @@ static bool inactive_reclaimable_pages(struct lruvec *lruvec, for (zid = sc->reclaim_idx; zid >= 0; zid--) { zone = &pgdat->node_zones[zid]; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE + @@ -2036,7 +2036,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, struct zone *zone = &pgdat->node_zones[zid]; unsigned long inactive_zone, active_zone; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; inactive_zone = zone_page_state(zone, @@ -2171,7 +2171,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = &pgdat->node_zones[z]; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; total_high_wmark += high_wmark_pages(zone); @@ -2510,7 +2510,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, /* If compaction would go ahead or the allocation would succeed, stop */ for (z = 0; z <= sc->reclaim_idx; z++) { struct zone *zone = &pgdat->node_zones[z]; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { @@ -2840,7 +2840,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; - if (!populated_zone(zone) || + if (!managed_zone(zone) || pgdat_reclaimable_pages(pgdat) == 0) continue; @@ -3141,7 +3141,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) for (i = 0; i <= classzone_idx; i++) { struct zone *zone = pgdat->node_zones + i; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (!zone_balanced(zone, order, classzone_idx)) @@ -3169,7 +3169,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, sc->nr_to_reclaim = 0; for (z = 0; z <= sc->reclaim_idx; z++) { zone = pgdat->node_zones + z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); @@ -3242,7 +3242,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; sc.reclaim_idx = i; @@ -3262,7 +3262,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) */ for (i = classzone_idx; i >= 0; i--) { zone = pgdat->node_zones + i; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (zone_balanced(zone, sc.order, classzone_idx)) @@ -3508,7 +3508,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) pg_data_t *pgdat; int z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) @@ -3522,7 +3522,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) /* Only wake kswapd if all zones are unbalanced */ for (z = 0; z <= classzone_idx; z++) { zone = pgdat->node_zones + z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (zone_balanced(zone, order, classzone_idx)) -- cgit v1.3-14-g43fede 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 --- Documentation/PCI/pci.txt | 1 - include/linux/pci.h | 9 --------- scripts/checkpatch.pl | 9 --------- scripts/tags.sh | 1 - 4 files changed, 20 deletions(-) (limited to 'include/linux') diff --git a/Documentation/PCI/pci.txt b/Documentation/PCI/pci.txt index 123881f62219..77f49dc5be23 100644 --- a/Documentation/PCI/pci.txt +++ b/Documentation/PCI/pci.txt @@ -124,7 +124,6 @@ initialization with a pointer to a structure describing the driver The ID table is an array of struct pci_device_id entries ending with an all-zero entry. Definitions with static const are generally preferred. -Use of the deprecated macro DEFINE_PCI_DEVICE_TABLE should be avoided. Each entry consists of: 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 diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 4de3cc42fc50..206a6b346a8d 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3570,15 +3570,6 @@ sub process { } } -# check for uses of DEFINE_PCI_DEVICE_TABLE - if ($line =~ /\bDEFINE_PCI_DEVICE_TABLE\s*\(\s*(\w+)\s*\)\s*=/) { - if (WARN("DEFINE_PCI_DEVICE_TABLE", - "Prefer struct pci_device_id over deprecated DEFINE_PCI_DEVICE_TABLE\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b(?:static\s+|)DEFINE_PCI_DEVICE_TABLE\s*\(\s*(\w+)\s*\)\s*=\s*/static const struct pci_device_id $1\[\] = /; - } - } - # check for new typedefs, only function parameters and sparse annotations # make sense. if ($line =~ /\btypedef\s/ && diff --git a/scripts/tags.sh b/scripts/tags.sh index ed7eef24ef89..b3775a9604ea 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -206,7 +206,6 @@ regex_c=( '/\ 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 ++++ kernel/exit.c | 7 +------ mm/mempolicy.c | 17 +++++++++++++++++ 3 files changed, 22 insertions(+), 6 deletions(-) (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 diff --git a/kernel/exit.c b/kernel/exit.c index 2f974ae042a6..091a78be3b09 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -848,12 +848,7 @@ void do_exit(long code) TASKS_RCU(preempt_enable()); exit_notify(tsk, group_dead); proc_exit_connector(tsk); -#ifdef CONFIG_NUMA - task_lock(tsk); - mpol_put(tsk->mempolicy); - tsk->mempolicy = NULL; - task_unlock(tsk); -#endif + mpol_put_task_policy(tsk); #ifdef CONFIG_FUTEX if (unlikely(current->pi_state_cache)) kfree(current->pi_state_cache); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d8c4e38fb5f4..2da72a5b6ecc 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2336,6 +2336,23 @@ out: return ret; } +/* + * Drop the (possibly final) reference to task->mempolicy. It needs to be + * dropped after task->mempolicy is set to NULL so that any allocation done as + * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed + * policy. + */ +void mpol_put_task_policy(struct task_struct *task) +{ + struct mempolicy *pol; + + task_lock(task); + pol = task->mempolicy; + task->mempolicy = NULL; + task_unlock(task); + mpol_put(pol); +} + static void sp_delete(struct shared_policy *sp, struct sp_node *n) { pr_debug("deleting %lx-l%lx\n", n->start, n->end); -- cgit v1.3-14-g43fede 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 v1.3-14-g43fede From 3f37ec79dd21fbdbbab8143a48a87272b22fef22 Mon Sep 17 00:00:00 2001 From: RafaÅ‚ MiÅ‚ecki 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: RafaÅ‚ MiÅ‚ecki Signed-off-by: Kalle Valo --- drivers/bcma/driver_chipcommon.c | 32 +++++++++++++++++++++++++++++--- include/linux/bcma/bcma.h | 3 +++ 2 files changed, 32 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c index 921ce1834673..b4f6520e74f0 100644 --- a/drivers/bcma/driver_chipcommon.c +++ b/drivers/bcma/driver_chipcommon.c @@ -36,12 +36,31 @@ u32 bcma_chipco_get_alp_clock(struct bcma_drv_cc *cc) } EXPORT_SYMBOL_GPL(bcma_chipco_get_alp_clock); +static bool bcma_core_cc_has_pmu_watchdog(struct bcma_drv_cc *cc) +{ + struct bcma_bus *bus = cc->core->bus; + + if (cc->capabilities & BCMA_CC_CAP_PMU) { + if (bus->chipinfo.id == BCMA_CHIP_ID_BCM53573) { + WARN(bus->chipinfo.rev <= 1, "No watchdog available\n"); + /* 53573B0 and 53573B1 have bugged PMU watchdog. It can + * be enabled but timer can't be bumped. Use CC one + * instead. + */ + return false; + } + return true; + } else { + return false; + } +} + static u32 bcma_chipco_watchdog_get_max_timer(struct bcma_drv_cc *cc) { struct bcma_bus *bus = cc->core->bus; u32 nb; - if (cc->capabilities & BCMA_CC_CAP_PMU) { + if (bcma_core_cc_has_pmu_watchdog(cc)) { if (bus->chipinfo.id == BCMA_CHIP_ID_BCM4706) nb = 32; else if (cc->core->id.rev < 26) @@ -95,9 +114,16 @@ static int bcma_chipco_watchdog_ticks_per_ms(struct bcma_drv_cc *cc) int bcma_chipco_watchdog_register(struct bcma_drv_cc *cc) { + struct bcma_bus *bus = cc->core->bus; struct bcm47xx_wdt wdt = {}; struct platform_device *pdev; + if (bus->chipinfo.id == BCMA_CHIP_ID_BCM53573 && + bus->chipinfo.rev <= 1) { + pr_debug("No watchdog on 53573A0 / 53573A1\n"); + return 0; + } + wdt.driver_data = cc; wdt.timer_set = bcma_chipco_watchdog_timer_set_wdt; wdt.timer_set_ms = bcma_chipco_watchdog_timer_set_ms_wdt; @@ -105,7 +131,7 @@ int bcma_chipco_watchdog_register(struct bcma_drv_cc *cc) bcma_chipco_watchdog_get_max_timer(cc) / cc->ticks_per_ms; pdev = platform_device_register_data(NULL, "bcm47xx-wdt", - cc->core->bus->num, &wdt, + bus->num, &wdt, sizeof(wdt)); if (IS_ERR(pdev)) return PTR_ERR(pdev); @@ -217,7 +243,7 @@ u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks) u32 maxt; maxt = bcma_chipco_watchdog_get_max_timer(cc); - if (cc->capabilities & BCMA_CC_CAP_PMU) { + if (bcma_core_cc_has_pmu_watchdog(cc)) { if (ticks == 1) ticks = 2; else if (ticks > maxt) 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 v1.3-14-g43fede 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 --- drivers/net/bonding/bond_main.c | 7 ++++--- include/linux/netdevice.h | 1 + net/core/dev.c | 16 ++++++++++++++++ 3 files changed, 21 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 217e8da0628c..9599ed6f1213 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1341,9 +1341,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) slave_dev->name); } - /* already enslaved */ - if (slave_dev->flags & IFF_SLAVE) { - netdev_dbg(bond_dev, "Error: Device was already enslaved\n"); + /* already in-use? */ + if (netdev_is_rx_handler_busy(slave_dev)) { + netdev_err(bond_dev, + "Error: Device is in use and cannot be enslaved\n"); return -EBUSY; } 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); diff --git a/net/core/dev.c b/net/core/dev.c index dd6ce598de89..ea6312057a71 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3974,6 +3974,22 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, return skb; } +/** + * netdev_is_rx_handler_busy - check if receive handler is registered + * @dev: device to check + * + * Check if a receive handler is already registered for a given device. + * Return true if there one. + * + * The caller must hold the rtnl_mutex. + */ +bool netdev_is_rx_handler_busy(struct net_device *dev) +{ + ASSERT_RTNL(); + return dev && rtnl_dereference(dev->rx_handler); +} +EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy); + /** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for -- cgit v1.3-14-g43fede 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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 --- arch/x86/boot/compressed/eboot.c | 20 ++++-- drivers/firmware/efi/libstub/efi-stub-helper.c | 96 ++++++++++++++++++-------- drivers/firmware/efi/libstub/fdt.c | 17 +++-- drivers/firmware/efi/libstub/random.c | 12 +++- include/linux/efi.h | 15 ++-- 5 files changed, 111 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ff574dad95cc..c5b7c7b4f0d7 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1008,7 +1008,7 @@ static efi_status_t exit_boot(struct boot_params *boot_params, void *handle, bool is64) { struct efi_info *efi = &boot_params->efi_info; - unsigned long map_sz, key, desc_size; + unsigned long map_sz, key, desc_size, buff_size; efi_memory_desc_t *mem_map; struct setup_data *e820ext; const char *signature; @@ -1019,14 +1019,20 @@ static efi_status_t exit_boot(struct boot_params *boot_params, bool called_exit = false; u8 nr_entries; int i; - - nr_desc = 0; - e820ext = NULL; - e820ext_size = 0; + struct efi_boot_memmap map; + + nr_desc = 0; + e820ext = NULL; + e820ext_size = 0; + map.map = &mem_map; + map.map_size = &map_sz; + map.desc_size = &desc_size; + map.desc_ver = &desc_version; + map.key_ptr = &key; + map.buff_size = &buff_size; get_map: - status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size, - &desc_version, &key); + status = efi_get_memory_map(sys_table, &map); if (status != EFI_SUCCESS) return status; diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 3bd127f95315..29368ac69221 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -41,6 +41,8 @@ static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE; #define EFI_ALLOC_ALIGN EFI_PAGE_SIZE #endif +#define EFI_MMAP_NR_SLACK_SLOTS 8 + struct file_info { efi_file_handle_t *handle; u64 size; @@ -63,49 +65,62 @@ void efi_printk(efi_system_table_t *sys_table_arg, char *str) } } +static inline bool mmap_has_headroom(unsigned long buff_size, + unsigned long map_size, + unsigned long desc_size) +{ + unsigned long slack = buff_size - map_size; + + return slack / desc_size >= EFI_MMAP_NR_SLACK_SLOTS; +} + 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_memory_desc_t *m = NULL; efi_status_t status; unsigned long key; u32 desc_version; - *map_size = sizeof(*m) * 32; + *map->desc_size = sizeof(*m); + *map->map_size = *map->desc_size * 32; + *map->buff_size = *map->map_size; again: - /* - * Add an additional efi_memory_desc_t because we're doing an - * allocation which may be in a new descriptor region. - */ - *map_size += sizeof(*m); status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - *map_size, (void **)&m); + *map->map_size, (void **)&m); if (status != EFI_SUCCESS) goto fail; - *desc_size = 0; + *map->desc_size = 0; key = 0; - status = efi_call_early(get_memory_map, map_size, m, - &key, desc_size, &desc_version); - if (status == EFI_BUFFER_TOO_SMALL) { + status = efi_call_early(get_memory_map, map->map_size, m, + &key, map->desc_size, &desc_version); + if (status == EFI_BUFFER_TOO_SMALL || + !mmap_has_headroom(*map->buff_size, *map->map_size, + *map->desc_size)) { efi_call_early(free_pool, m); + /* + * Make sure there is some entries of headroom so that the + * buffer can be reused for a new map after allocations are + * no longer permitted. Its unlikely that the map will grow to + * exceed this headroom once we are ready to trigger + * ExitBootServices() + */ + *map->map_size += *map->desc_size * EFI_MMAP_NR_SLACK_SLOTS; + *map->buff_size = *map->map_size; goto again; } if (status != EFI_SUCCESS) efi_call_early(free_pool, m); - if (key_ptr && status == EFI_SUCCESS) - *key_ptr = key; - if (desc_ver && status == EFI_SUCCESS) - *desc_ver = desc_version; + if (map->key_ptr && status == EFI_SUCCESS) + *map->key_ptr = key; + if (map->desc_ver && status == EFI_SUCCESS) + *map->desc_ver = desc_version; fail: - *map = m; + *map->map = m; return status; } @@ -113,13 +128,20 @@ fail: unsigned long get_dram_base(efi_system_table_t *sys_table_arg) { efi_status_t status; - unsigned long map_size; + unsigned long map_size, buff_size; unsigned long membase = EFI_ERROR; struct efi_memory_map map; efi_memory_desc_t *md; + struct efi_boot_memmap boot_map; - status = efi_get_memory_map(sys_table_arg, (efi_memory_desc_t **)&map.map, - &map_size, &map.desc_size, NULL, NULL); + boot_map.map = (efi_memory_desc_t **)&map.map; + boot_map.map_size = &map_size; + boot_map.desc_size = &map.desc_size; + boot_map.desc_ver = NULL; + boot_map.key_ptr = NULL; + boot_map.buff_size = &buff_size; + + status = efi_get_memory_map(sys_table_arg, &boot_map); if (status != EFI_SUCCESS) return membase; @@ -144,15 +166,22 @@ efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, unsigned long *addr, unsigned long max) { - unsigned long map_size, desc_size; + unsigned long map_size, desc_size, buff_size; efi_memory_desc_t *map; efi_status_t status; unsigned long nr_pages; u64 max_addr = 0; int i; + struct efi_boot_memmap boot_map; + + boot_map.map = ↦ + boot_map.map_size = &map_size; + boot_map.desc_size = &desc_size; + boot_map.desc_ver = NULL; + boot_map.key_ptr = NULL; + boot_map.buff_size = &buff_size; - status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size, - NULL, NULL); + status = efi_get_memory_map(sys_table_arg, &boot_map); if (status != EFI_SUCCESS) goto fail; @@ -230,14 +259,21 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, unsigned long *addr) { - unsigned long map_size, desc_size; + unsigned long map_size, desc_size, buff_size; efi_memory_desc_t *map; efi_status_t status; unsigned long nr_pages; int i; + struct efi_boot_memmap boot_map; + + boot_map.map = ↦ + boot_map.map_size = &map_size; + boot_map.desc_size = &desc_size; + boot_map.desc_ver = NULL; + boot_map.key_ptr = NULL; + boot_map.buff_size = &buff_size; - status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size, - NULL, NULL); + status = efi_get_memory_map(sys_table_arg, &boot_map); if (status != EFI_SUCCESS) goto fail; diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index e58abfa953cc..bec0fa8d8746 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -175,13 +175,21 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, unsigned long fdt_addr, unsigned long fdt_size) { - unsigned long map_size, desc_size; + unsigned long map_size, desc_size, buff_size; u32 desc_ver; unsigned long mmap_key; efi_memory_desc_t *memory_map, *runtime_map; unsigned long new_fdt_size; efi_status_t status; int runtime_entry_count = 0; + struct efi_boot_memmap map; + + map.map = &runtime_map; + map.map_size = &map_size; + map.desc_size = &desc_size; + map.desc_ver = &desc_ver; + map.key_ptr = &mmap_key; + map.buff_size = &buff_size; /* * Get a copy of the current memory map that we will use to prepare @@ -189,8 +197,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, * subsequent allocations adding entries, since they could not affect * the number of EFI_MEMORY_RUNTIME regions. */ - status = efi_get_memory_map(sys_table, &runtime_map, &map_size, - &desc_size, &desc_ver, &mmap_key); + status = efi_get_memory_map(sys_table, &map); if (status != EFI_SUCCESS) { pr_efi_err(sys_table, "Unable to retrieve UEFI memory map.\n"); return status; @@ -199,6 +206,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, pr_efi(sys_table, "Exiting boot services and installing virtual address map...\n"); + map.map = &memory_map; /* * Estimate size of new FDT, and allocate memory for it. We * will allocate a bigger buffer if this ends up being too @@ -218,8 +226,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, * we can get the memory map key needed for * exit_boot_services(). */ - status = efi_get_memory_map(sys_table, &memory_map, &map_size, - &desc_size, &desc_ver, &mmap_key); + status = efi_get_memory_map(sys_table, &map); if (status != EFI_SUCCESS) goto fail_free_new_fdt; diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c index 53f6d3fe6d86..0c9f58c5ba50 100644 --- a/drivers/firmware/efi/libstub/random.c +++ b/drivers/firmware/efi/libstub/random.c @@ -73,12 +73,20 @@ efi_status_t efi_random_alloc(efi_system_table_t *sys_table_arg, unsigned long random_seed) { unsigned long map_size, desc_size, total_slots = 0, target_slot; + unsigned long buff_size; efi_status_t status; efi_memory_desc_t *memory_map; int map_offset; + struct efi_boot_memmap map; - status = efi_get_memory_map(sys_table_arg, &memory_map, &map_size, - &desc_size, NULL, NULL); + map.map = &memory_map; + map.map_size = &map_size; + map.desc_size = &desc_size; + map.desc_ver = NULL; + map.key_ptr = NULL; + map.buff_size = &buff_size; + + status = efi_get_memory_map(sys_table_arg, &map); if (status != EFI_SUCCESS) return status; 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 v1.3-14-g43fede 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 --- drivers/firmware/efi/libstub/efi-stub-helper.c | 73 ++++++++++++++++++++++++++ include/linux/efi.h | 10 ++++ 2 files changed, 83 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 29368ac69221..aded10662020 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -740,3 +740,76 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, *cmd_line_len = options_bytes; return (char *)cmdline_addr; } + +/* + * Handle calling ExitBootServices according to the requirements set out by the + * spec. Obtains the current memory map, and returns that info after calling + * ExitBootServices. The client must specify a function to perform any + * processing of the memory map data prior to ExitBootServices. A client + * specific structure may be passed to the function via priv. The client + * function may be called multiple times. + */ +efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table_arg, + void *handle, + struct efi_boot_memmap *map, + void *priv, + efi_exit_boot_map_processing priv_func) +{ + efi_status_t status; + + status = efi_get_memory_map(sys_table_arg, map); + + if (status != EFI_SUCCESS) + goto fail; + + status = priv_func(sys_table_arg, map, priv); + if (status != EFI_SUCCESS) + goto free_map; + + status = efi_call_early(exit_boot_services, handle, *map->key_ptr); + + if (status == EFI_INVALID_PARAMETER) { + /* + * The memory map changed between efi_get_memory_map() and + * exit_boot_services(). Per the UEFI Spec v2.6, Section 6.4: + * EFI_BOOT_SERVICES.ExitBootServices we need to get the + * updated map, and try again. The spec implies one retry + * should be sufficent, which is confirmed against the EDK2 + * implementation. Per the spec, we can only invoke + * get_memory_map() and exit_boot_services() - we cannot alloc + * so efi_get_memory_map() cannot be used, and we must reuse + * the buffer. For all practical purposes, the headroom in the + * buffer should account for any changes in the map so the call + * to get_memory_map() is expected to succeed here. + */ + *map->map_size = *map->buff_size; + status = efi_call_early(get_memory_map, + map->map_size, + *map->map, + map->key_ptr, + map->desc_size, + map->desc_ver); + + /* exit_boot_services() was called, thus cannot free */ + if (status != EFI_SUCCESS) + goto fail; + + status = priv_func(sys_table_arg, map, priv); + /* exit_boot_services() was called, thus cannot free */ + if (status != EFI_SUCCESS) + goto fail; + + status = efi_call_early(exit_boot_services, handle, *map->key_ptr); + } + + /* exit_boot_services() was called, thus cannot free */ + if (status != EFI_SUCCESS) + goto fail; + + return EFI_SUCCESS; + +free_map: + efi_call_early(free_pool, *map->map); +fail: + return status; +} 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 v1.3-14-g43fede 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 --- arch/ia64/include/asm/uaccess.h | 12 ++++-------- arch/powerpc/include/asm/uaccess.h | 19 +++++++------------ arch/sparc/include/asm/uaccess_32.h | 9 +++------ arch/sparc/include/asm/uaccess_64.h | 7 +++---- include/linux/thread_info.h | 3 ++- 5 files changed, 19 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h index 465c70982f40..0472927ebb9b 100644 --- a/arch/ia64/include/asm/uaccess.h +++ b/arch/ia64/include/asm/uaccess.h @@ -241,8 +241,7 @@ extern unsigned long __must_check __copy_user (void __user *to, const void __use static inline unsigned long __copy_to_user (void __user *to, const void *from, unsigned long count) { - if (!__builtin_constant_p(count)) - check_object_size(from, count, true); + check_object_size(from, count, true); return __copy_user(to, (__force void __user *) from, count); } @@ -250,8 +249,7 @@ __copy_to_user (void __user *to, const void *from, unsigned long count) static inline unsigned long __copy_from_user (void *to, const void __user *from, unsigned long count) { - if (!__builtin_constant_p(count)) - check_object_size(to, count, false); + check_object_size(to, count, false); return __copy_user((__force void __user *) to, from, count); } @@ -265,8 +263,7 @@ __copy_from_user (void *to, const void __user *from, unsigned long count) long __cu_len = (n); \ \ if (__access_ok(__cu_to, __cu_len, get_fs())) { \ - if (!__builtin_constant_p(n)) \ - check_object_size(__cu_from, __cu_len, true); \ + check_object_size(__cu_from, __cu_len, true); \ __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \ } \ __cu_len; \ @@ -280,8 +277,7 @@ __copy_from_user (void *to, const void __user *from, unsigned long count) \ __chk_user_ptr(__cu_from); \ if (__access_ok(__cu_from, __cu_len, get_fs())) { \ - if (!__builtin_constant_p(n)) \ - check_object_size(__cu_to, __cu_len, false); \ + check_object_size(__cu_to, __cu_len, false); \ __cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len); \ } \ __cu_len; \ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index c1dc6c14deb8..f1e382498bbb 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -311,14 +311,12 @@ static inline unsigned long copy_from_user(void *to, unsigned long over; if (access_ok(VERIFY_READ, from, n)) { - if (!__builtin_constant_p(n)) - check_object_size(to, n, false); + check_object_size(to, n, false); return __copy_tofrom_user((__force void __user *)to, from, n); } if ((unsigned long)from < TASK_SIZE) { over = (unsigned long)from + n - TASK_SIZE; - if (!__builtin_constant_p(n - over)) - check_object_size(to, n - over, false); + check_object_size(to, n - over, false); return __copy_tofrom_user((__force void __user *)to, from, n - over) + over; } @@ -331,14 +329,12 @@ static inline unsigned long copy_to_user(void __user *to, unsigned long over; if (access_ok(VERIFY_WRITE, to, n)) { - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + check_object_size(from, n, true); return __copy_tofrom_user(to, (__force void __user *)from, n); } if ((unsigned long)to < TASK_SIZE) { over = (unsigned long)to + n - TASK_SIZE; - if (!__builtin_constant_p(n)) - check_object_size(from, n - over, true); + check_object_size(from, n - over, true); return __copy_tofrom_user(to, (__force void __user *)from, n - over) + over; } @@ -383,8 +379,7 @@ static inline unsigned long __copy_from_user_inatomic(void *to, return 0; } - if (!__builtin_constant_p(n)) - check_object_size(to, n, false); + check_object_size(to, n, false); return __copy_tofrom_user((__force void __user *)to, from, n); } @@ -412,8 +407,8 @@ static inline unsigned long __copy_to_user_inatomic(void __user *to, if (ret == 0) return 0; } - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + + check_object_size(from, n, true); return __copy_tofrom_user(to, (__force const void __user *)from, n); } diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h index 341a5a133f48..e722c510bb1b 100644 --- a/arch/sparc/include/asm/uaccess_32.h +++ b/arch/sparc/include/asm/uaccess_32.h @@ -249,8 +249,7 @@ unsigned long __copy_user(void __user *to, const void __user *from, unsigned lon static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n) { if (n && __access_ok((unsigned long) to, n)) { - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); } else return n; @@ -258,16 +257,14 @@ static inline unsigned long copy_to_user(void __user *to, const void *from, unsi static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { - if (!__builtin_constant_p(n)) - check_object_size(from, n, true); + check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); } static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { if (n && __access_ok((unsigned long) from, n)) { - if (!__builtin_constant_p(n)) - check_object_size(to, n, false); + check_object_size(to, n, false); return __copy_user((__force void __user *) to, from, n); } else return n; diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index 8bda94fab8e8..37a315d0ddd4 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -212,8 +212,7 @@ copy_from_user(void *to, const void __user *from, unsigned long size) { unsigned long ret; - if (!__builtin_constant_p(size)) - check_object_size(to, size, false); + check_object_size(to, size, false); ret = ___copy_from_user(to, from, size); if (unlikely(ret)) @@ -233,8 +232,8 @@ copy_to_user(void __user *to, const void *from, unsigned long size) { unsigned long ret; - if (!__builtin_constant_p(size)) - check_object_size(from, size, true); + check_object_size(from, size, true); + ret = ___copy_to_user(to, from, size); if (unlikely(ret)) ret = copy_to_user_fixup(to, from, size); 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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 --- drivers/net/ethernet/qlogic/qed/Makefile | 2 +- drivers/net/ethernet/qlogic/qed/qed.h | 20 + drivers/net/ethernet/qlogic/qed/qed_debug.c | 6898 ++++++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_debug.h | 54 + drivers/net/ethernet/qlogic/qed/qed_hsi.h | 1056 +++- drivers/net/ethernet/qlogic/qed/qed_main.c | 4 + drivers/net/ethernet/qlogic/qed/qed_reg_addr.h | 894 +++ include/linux/qed/common_hsi.h | 3 + 8 files changed, 8919 insertions(+), 12 deletions(-) create mode 100644 drivers/net/ethernet/qlogic/qed/qed_debug.c create mode 100644 drivers/net/ethernet/qlogic/qed/qed_debug.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile index d1f157e439cf..86a5b4f5f870 100644 --- a/drivers/net/ethernet/qlogic/qed/Makefile +++ b/drivers/net/ethernet/qlogic/qed/Makefile @@ -2,5 +2,5 @@ obj-$(CONFIG_QED) := qed.o qed-y := qed_cxt.o qed_dev.o qed_hw.o qed_init_fw_funcs.o qed_init_ops.o \ qed_int.o qed_main.o qed_mcp.o qed_sp_commands.o qed_spq.o qed_l2.o \ - qed_selftest.o qed_dcbx.o + qed_selftest.o qed_dcbx.o qed_debug.o qed-$(CONFIG_QED_SRIOV) += qed_sriov.o qed_vf.o diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 2d67469eb8f6..0929582fc82b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -23,6 +23,7 @@ #include #include #include +#include "qed_debug.h" #include "qed_hsi.h" extern const struct qed_common_ops qed_common_ops_pass; @@ -395,6 +396,8 @@ struct qed_hwfn { /* Buffer for unzipping firmware data */ void *unzip_buf; + struct dbg_tools_data dbg_info; + struct qed_simd_fp_handler simd_proto_handler[64]; #ifdef CONFIG_QED_SRIOV @@ -430,6 +433,19 @@ struct qed_int_params { u8 fp_msix_cnt; }; +struct qed_dbg_feature { + struct dentry *dentry; + u8 *dump_buf; + u32 buf_size; + u32 dumped_dwords; +}; + +struct qed_dbg_params { + struct qed_dbg_feature features[DBG_FEATURE_NUM]; + u8 engine_for_debug; + bool print_data; +}; + struct qed_dev { u32 dp_module; u8 dp_level; @@ -444,6 +460,8 @@ struct qed_dev { CHIP_REV_IS_A0(dev)) #define QED_IS_BB_B0(dev) (QED_IS_BB(dev) && \ CHIP_REV_IS_B0(dev)) +#define QED_IS_AH(dev) ((dev)->type == QED_DEV_TYPE_AH) +#define QED_IS_K2(dev) QED_IS_AH(dev) #define QED_GET_TYPE(dev) (QED_IS_BB_A0(dev) ? CHIP_BB_A0 : \ QED_IS_BB_B0(dev) ? CHIP_BB_B0 : CHIP_K2) @@ -544,6 +562,8 @@ struct qed_dev { } protocol_ops; void *ops_cookie; + struct qed_dbg_params dbg_params; + const struct firmware *firmware; }; diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c new file mode 100644 index 000000000000..88e7d5bef909 --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -0,0 +1,6898 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#include +#include +#include +#include "qed.h" +#include "qed_hsi.h" +#include "qed_hw.h" +#include "qed_mcp.h" +#include "qed_reg_addr.h" + +/* Chip IDs enum */ +enum chip_ids { + CHIP_RESERVED, + CHIP_BB_B0, + CHIP_K2, + MAX_CHIP_IDS +}; + +/* Memory groups enum */ +enum mem_groups { + MEM_GROUP_PXP_MEM, + MEM_GROUP_DMAE_MEM, + MEM_GROUP_CM_MEM, + MEM_GROUP_QM_MEM, + MEM_GROUP_TM_MEM, + MEM_GROUP_BRB_RAM, + MEM_GROUP_BRB_MEM, + MEM_GROUP_PRS_MEM, + MEM_GROUP_SDM_MEM, + MEM_GROUP_PBUF, + MEM_GROUP_IOR, + MEM_GROUP_RAM, + MEM_GROUP_BTB_RAM, + MEM_GROUP_RDIF_CTX, + MEM_GROUP_TDIF_CTX, + MEM_GROUP_CONN_CFC_MEM, + MEM_GROUP_TASK_CFC_MEM, + MEM_GROUP_CAU_PI, + MEM_GROUP_CAU_MEM, + MEM_GROUP_PXP_ILT, + MEM_GROUP_MULD_MEM, + MEM_GROUP_BTB_MEM, + MEM_GROUP_IGU_MEM, + MEM_GROUP_IGU_MSIX, + MEM_GROUP_CAU_SB, + MEM_GROUP_BMB_RAM, + MEM_GROUP_BMB_MEM, + MEM_GROUPS_NUM +}; + +/* Memory groups names */ +static const char * const s_mem_group_names[] = { + "PXP_MEM", + "DMAE_MEM", + "CM_MEM", + "QM_MEM", + "TM_MEM", + "BRB_RAM", + "BRB_MEM", + "PRS_MEM", + "SDM_MEM", + "PBUF", + "IOR", + "RAM", + "BTB_RAM", + "RDIF_CTX", + "TDIF_CTX", + "CONN_CFC_MEM", + "TASK_CFC_MEM", + "CAU_PI", + "CAU_MEM", + "PXP_ILT", + "MULD_MEM", + "BTB_MEM", + "IGU_MEM", + "IGU_MSIX", + "CAU_SB", + "BMB_RAM", + "BMB_MEM", +}; + +/* Idle check conditions */ +static u32 cond4(const u32 *r, const u32 *imm) +{ + return ((r[0] & imm[0]) != imm[1]) && ((r[1] & imm[2]) != imm[3]); +} + +static u32 cond6(const u32 *r, const u32 *imm) +{ + return ((r[0] >> imm[0]) & imm[1]) != imm[2]; +} + +static u32 cond5(const u32 *r, const u32 *imm) +{ + return (r[0] & imm[0]) != imm[1]; +} + +static u32 cond8(const u32 *r, const u32 *imm) +{ + return ((r[0] & imm[0]) >> imm[1]) != + (((r[0] & imm[2]) >> imm[3]) | ((r[1] & imm[4]) << imm[5])); +} + +static u32 cond9(const u32 *r, const u32 *imm) +{ + return ((r[0] & imm[0]) >> imm[1]) != (r[0] & imm[2]); +} + +static u32 cond1(const u32 *r, const u32 *imm) +{ + return (r[0] & ~imm[0]) != imm[1]; +} + +static u32 cond0(const u32 *r, const u32 *imm) +{ + return r[0] != imm[0]; +} + +static u32 cond10(const u32 *r, const u32 *imm) +{ + return r[0] != r[1] && r[2] == imm[0]; +} + +static u32 cond11(const u32 *r, const u32 *imm) +{ + return r[0] != r[1] && r[2] > imm[0]; +} + +static u32 cond3(const u32 *r, const u32 *imm) +{ + return r[0] != r[1]; +} + +static u32 cond12(const u32 *r, const u32 *imm) +{ + return r[0] & imm[0]; +} + +static u32 cond7(const u32 *r, const u32 *imm) +{ + return r[0] < (r[1] - imm[0]); +} + +static u32 cond2(const u32 *r, const u32 *imm) +{ + return r[0] > imm[0]; +} + +/* Array of Idle Check conditions */ +static u32(*cond_arr[]) (const u32 *r, const u32 *imm) = { + cond0, + cond1, + cond2, + cond3, + cond4, + cond5, + cond6, + cond7, + cond8, + cond9, + cond10, + cond11, + cond12, +}; + +/******************************* Data Types **********************************/ + +enum platform_ids { + PLATFORM_ASIC, + PLATFORM_RESERVED, + PLATFORM_RESERVED2, + PLATFORM_RESERVED3, + MAX_PLATFORM_IDS +}; + +struct dbg_array { + const u32 *ptr; + u32 size_in_dwords; +}; + +/* Chip constant definitions */ +struct chip_defs { + const char *name; + struct { + u8 num_ports; + u8 num_pfs; + } per_platform[MAX_PLATFORM_IDS]; +}; + +/* Platform constant definitions */ +struct platform_defs { + const char *name; + u32 delay_factor; +}; + +/* Storm constant definitions */ +struct storm_defs { + char letter; + enum block_id block_id; + enum dbg_bus_clients dbg_client_id[MAX_CHIP_IDS]; + bool has_vfc; + u32 sem_fast_mem_addr; + u32 sem_frame_mode_addr; + u32 sem_slow_enable_addr; + u32 sem_slow_mode_addr; + u32 sem_slow_mode1_conf_addr; + u32 sem_sync_dbg_empty_addr; + u32 sem_slow_dbg_empty_addr; + u32 cm_ctx_wr_addr; + u32 cm_conn_ag_ctx_lid_size; /* In quad-regs */ + u32 cm_conn_ag_ctx_rd_addr; + u32 cm_conn_st_ctx_lid_size; /* In quad-regs */ + u32 cm_conn_st_ctx_rd_addr; + u32 cm_task_ag_ctx_lid_size; /* In quad-regs */ + u32 cm_task_ag_ctx_rd_addr; + u32 cm_task_st_ctx_lid_size; /* In quad-regs */ + u32 cm_task_st_ctx_rd_addr; +}; + +/* Block constant definitions */ +struct block_defs { + const char *name; + bool has_dbg_bus[MAX_CHIP_IDS]; + bool associated_to_storm; + u32 storm_id; /* Valid only if associated_to_storm is true */ + enum dbg_bus_clients dbg_client_id[MAX_CHIP_IDS]; + u32 dbg_select_addr; + u32 dbg_cycle_enable_addr; + u32 dbg_shift_addr; + u32 dbg_force_valid_addr; + u32 dbg_force_frame_addr; + bool has_reset_bit; + bool unreset; /* If true, the block is taken out of reset before dump */ + enum dbg_reset_regs reset_reg; + u8 reset_bit_offset; /* Bit offset in reset register */ +}; + +/* Reset register definitions */ +struct reset_reg_defs { + u32 addr; + u32 unreset_val; + bool exists[MAX_CHIP_IDS]; +}; + +struct grc_param_defs { + u32 default_val[MAX_CHIP_IDS]; + u32 min; + u32 max; + bool is_preset; + u32 exclude_all_preset_val; + u32 crash_preset_val; +}; + +struct rss_mem_defs { + const char *mem_name; + const char *type_name; + u32 addr; /* In 128b units */ + u32 num_entries[MAX_CHIP_IDS]; + u32 entry_width[MAX_CHIP_IDS]; /* In bits */ +}; + +struct vfc_ram_defs { + const char *mem_name; + const char *type_name; + u32 base_row; + u32 num_rows; +}; + +struct big_ram_defs { + const char *instance_name; + enum mem_groups mem_group_id; + enum mem_groups ram_mem_group_id; + enum dbg_grc_params grc_param; + u32 addr_reg_addr; + u32 data_reg_addr; + u32 num_of_blocks[MAX_CHIP_IDS]; +}; + +struct phy_defs { + const char *phy_name; + u32 base_addr; + u32 tbus_addr_lo_addr; + u32 tbus_addr_hi_addr; + u32 tbus_data_lo_addr; + u32 tbus_data_hi_addr; +}; + +/******************************** Constants **********************************/ + +#define MAX_LCIDS 320 +#define MAX_LTIDS 320 +#define NUM_IOR_SETS 2 +#define IORS_PER_SET 176 +#define IOR_SET_OFFSET(set_id) ((set_id) * 256) +#define BYTES_IN_DWORD sizeof(u32) + +/* In the macros below, size and offset are specified in bits */ +#define CEIL_DWORDS(size) DIV_ROUND_UP(size, 32) +#define FIELD_BIT_OFFSET(type, field) type ## _ ## field ## _ ## OFFSET +#define FIELD_BIT_SIZE(type, field) type ## _ ## field ## _ ## SIZE +#define FIELD_DWORD_OFFSET(type, field) \ + (int)(FIELD_BIT_OFFSET(type, field) / 32) +#define FIELD_DWORD_SHIFT(type, field) (FIELD_BIT_OFFSET(type, field) % 32) +#define FIELD_BIT_MASK(type, field) \ + (((1 << FIELD_BIT_SIZE(type, field)) - 1) << \ + FIELD_DWORD_SHIFT(type, field)) +#define SET_VAR_FIELD(var, type, field, val) \ + do { \ + var[FIELD_DWORD_OFFSET(type, field)] &= \ + (~FIELD_BIT_MASK(type, field)); \ + var[FIELD_DWORD_OFFSET(type, field)] |= \ + (val) << FIELD_DWORD_SHIFT(type, field); \ + } while (0) +#define ARR_REG_WR(dev, ptt, addr, arr, arr_size) \ + do { \ + for (i = 0; i < (arr_size); i++) \ + qed_wr(dev, ptt, addr, (arr)[i]); \ + } while (0) +#define ARR_REG_RD(dev, ptt, addr, arr, arr_size) \ + do { \ + for (i = 0; i < (arr_size); i++) \ + (arr)[i] = qed_rd(dev, ptt, addr); \ + } while (0) + +#define DWORDS_TO_BYTES(dwords) ((dwords) * BYTES_IN_DWORD) +#define BYTES_TO_DWORDS(bytes) ((bytes) / BYTES_IN_DWORD) +#define RAM_LINES_TO_DWORDS(lines) ((lines) * 2) +#define RAM_LINES_TO_BYTES(lines) \ + DWORDS_TO_BYTES(RAM_LINES_TO_DWORDS(lines)) +#define REG_DUMP_LEN_SHIFT 24 +#define MEM_DUMP_ENTRY_SIZE_DWORDS \ + BYTES_TO_DWORDS(sizeof(struct dbg_dump_mem)) +#define IDLE_CHK_RULE_SIZE_DWORDS \ + BYTES_TO_DWORDS(sizeof(struct dbg_idle_chk_rule)) +#define IDLE_CHK_RESULT_HDR_DWORDS \ + BYTES_TO_DWORDS(sizeof(struct dbg_idle_chk_result_hdr)) +#define IDLE_CHK_RESULT_REG_HDR_DWORDS \ + BYTES_TO_DWORDS(sizeof(struct dbg_idle_chk_result_reg_hdr)) +#define IDLE_CHK_MAX_ENTRIES_SIZE 32 + +/* The sizes and offsets below are specified in bits */ +#define VFC_CAM_CMD_STRUCT_SIZE 64 +#define VFC_CAM_CMD_ROW_OFFSET 48 +#define VFC_CAM_CMD_ROW_SIZE 9 +#define VFC_CAM_ADDR_STRUCT_SIZE 16 +#define VFC_CAM_ADDR_OP_OFFSET 0 +#define VFC_CAM_ADDR_OP_SIZE 4 +#define VFC_CAM_RESP_STRUCT_SIZE 256 +#define VFC_RAM_ADDR_STRUCT_SIZE 16 +#define VFC_RAM_ADDR_OP_OFFSET 0 +#define VFC_RAM_ADDR_OP_SIZE 2 +#define VFC_RAM_ADDR_ROW_OFFSET 2 +#define VFC_RAM_ADDR_ROW_SIZE 10 +#define VFC_RAM_RESP_STRUCT_SIZE 256 +#define VFC_CAM_CMD_DWORDS CEIL_DWORDS(VFC_CAM_CMD_STRUCT_SIZE) +#define VFC_CAM_ADDR_DWORDS CEIL_DWORDS(VFC_CAM_ADDR_STRUCT_SIZE) +#define VFC_CAM_RESP_DWORDS CEIL_DWORDS(VFC_CAM_RESP_STRUCT_SIZE) +#define VFC_RAM_CMD_DWORDS VFC_CAM_CMD_DWORDS +#define VFC_RAM_ADDR_DWORDS CEIL_DWORDS(VFC_RAM_ADDR_STRUCT_SIZE) +#define VFC_RAM_RESP_DWORDS CEIL_DWORDS(VFC_RAM_RESP_STRUCT_SIZE) +#define NUM_VFC_RAM_TYPES 4 +#define VFC_CAM_NUM_ROWS 512 +#define VFC_OPCODE_CAM_RD 14 +#define VFC_OPCODE_RAM_RD 0 +#define NUM_RSS_MEM_TYPES 5 +#define NUM_BIG_RAM_TYPES 3 +#define BIG_RAM_BLOCK_SIZE_BYTES 128 +#define BIG_RAM_BLOCK_SIZE_DWORDS \ + BYTES_TO_DWORDS(BIG_RAM_BLOCK_SIZE_BYTES) +#define NUM_PHY_TBUS_ADDRESSES 2048 +#define PHY_DUMP_SIZE_DWORDS (NUM_PHY_TBUS_ADDRESSES / 2) +#define RESET_REG_UNRESET_OFFSET 4 +#define STALL_DELAY_MS 500 +#define STATIC_DEBUG_LINE_DWORDS 9 +#define NUM_DBG_BUS_LINES 256 +#define NUM_COMMON_GLOBAL_PARAMS 8 +#define FW_IMG_MAIN 1 +#define REG_FIFO_DEPTH_ELEMENTS 32 +#define REG_FIFO_ELEMENT_DWORDS 2 +#define REG_FIFO_DEPTH_DWORDS \ + (REG_FIFO_ELEMENT_DWORDS * REG_FIFO_DEPTH_ELEMENTS) +#define IGU_FIFO_DEPTH_ELEMENTS 64 +#define IGU_FIFO_ELEMENT_DWORDS 4 +#define IGU_FIFO_DEPTH_DWORDS \ + (IGU_FIFO_ELEMENT_DWORDS * IGU_FIFO_DEPTH_ELEMENTS) +#define PROTECTION_OVERRIDE_DEPTH_ELEMENTS 20 +#define PROTECTION_OVERRIDE_ELEMENT_DWORDS 2 +#define PROTECTION_OVERRIDE_DEPTH_DWORDS \ + (PROTECTION_OVERRIDE_DEPTH_ELEMENTS * \ + PROTECTION_OVERRIDE_ELEMENT_DWORDS) +#define MCP_SPAD_TRACE_OFFSIZE_ADDR \ + (MCP_REG_SCRATCH + \ + offsetof(struct static_init, sections[SPAD_SECTION_TRACE])) +#define MCP_TRACE_META_IMAGE_SIGNATURE 0x669955aa +#define EMPTY_FW_VERSION_STR "???_???_???_???" +#define EMPTY_FW_IMAGE_STR "???????????????" + +/***************************** Constant Arrays *******************************/ + +/* Debug arrays */ +static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {0} }; + +/* Chip constant definitions array */ +static struct chip_defs s_chip_defs[MAX_CHIP_IDS] = { + { "reserved", { {0, 0}, {0, 0}, {0, 0}, {0, 0} } }, + { "bb_b0", + { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB}, {0, 0}, {0, 0}, {0, 0} } }, + { "k2", { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2}, {0, 0}, {0, 0}, {0, 0} } } +}; + +/* Storm constant definitions array */ +static struct storm_defs s_storm_defs[] = { + /* Tstorm */ + {'T', BLOCK_TSEM, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, + DBG_BUS_CLIENT_RBCT}, true, + TSEM_REG_FAST_MEMORY, + TSEM_REG_DBG_FRAME_MODE, TSEM_REG_SLOW_DBG_ACTIVE, + TSEM_REG_SLOW_DBG_MODE, TSEM_REG_DBG_MODE1_CFG, + TSEM_REG_SYNC_DBG_EMPTY, TSEM_REG_SLOW_DBG_EMPTY, + TCM_REG_CTX_RBC_ACCS, + 4, TCM_REG_AGG_CON_CTX, + 16, TCM_REG_SM_CON_CTX, + 2, TCM_REG_AGG_TASK_CTX, + 4, TCM_REG_SM_TASK_CTX}, + /* Mstorm */ + {'M', BLOCK_MSEM, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, + DBG_BUS_CLIENT_RBCM}, false, + MSEM_REG_FAST_MEMORY, + MSEM_REG_DBG_FRAME_MODE, MSEM_REG_SLOW_DBG_ACTIVE, + MSEM_REG_SLOW_DBG_MODE, MSEM_REG_DBG_MODE1_CFG, + MSEM_REG_SYNC_DBG_EMPTY, MSEM_REG_SLOW_DBG_EMPTY, + MCM_REG_CTX_RBC_ACCS, + 1, MCM_REG_AGG_CON_CTX, + 10, MCM_REG_SM_CON_CTX, + 2, MCM_REG_AGG_TASK_CTX, + 7, MCM_REG_SM_TASK_CTX}, + /* Ustorm */ + {'U', BLOCK_USEM, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, + DBG_BUS_CLIENT_RBCU}, false, + USEM_REG_FAST_MEMORY, + USEM_REG_DBG_FRAME_MODE, USEM_REG_SLOW_DBG_ACTIVE, + USEM_REG_SLOW_DBG_MODE, USEM_REG_DBG_MODE1_CFG, + USEM_REG_SYNC_DBG_EMPTY, USEM_REG_SLOW_DBG_EMPTY, + UCM_REG_CTX_RBC_ACCS, + 2, UCM_REG_AGG_CON_CTX, + 13, UCM_REG_SM_CON_CTX, + 3, UCM_REG_AGG_TASK_CTX, + 3, UCM_REG_SM_TASK_CTX}, + /* Xstorm */ + {'X', BLOCK_XSEM, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, + DBG_BUS_CLIENT_RBCX}, false, + XSEM_REG_FAST_MEMORY, + XSEM_REG_DBG_FRAME_MODE, XSEM_REG_SLOW_DBG_ACTIVE, + XSEM_REG_SLOW_DBG_MODE, XSEM_REG_DBG_MODE1_CFG, + XSEM_REG_SYNC_DBG_EMPTY, XSEM_REG_SLOW_DBG_EMPTY, + XCM_REG_CTX_RBC_ACCS, + 9, XCM_REG_AGG_CON_CTX, + 15, XCM_REG_SM_CON_CTX, + 0, 0, + 0, 0}, + /* Ystorm */ + {'Y', BLOCK_YSEM, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, + DBG_BUS_CLIENT_RBCY}, false, + YSEM_REG_FAST_MEMORY, + YSEM_REG_DBG_FRAME_MODE, YSEM_REG_SLOW_DBG_ACTIVE, + YSEM_REG_SLOW_DBG_MODE, YSEM_REG_DBG_MODE1_CFG, + YSEM_REG_SYNC_DBG_EMPTY, TSEM_REG_SLOW_DBG_EMPTY, + YCM_REG_CTX_RBC_ACCS, + 2, YCM_REG_AGG_CON_CTX, + 3, YCM_REG_SM_CON_CTX, + 2, YCM_REG_AGG_TASK_CTX, + 12, YCM_REG_SM_TASK_CTX}, + /* Pstorm */ + {'P', BLOCK_PSEM, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, + DBG_BUS_CLIENT_RBCS}, true, + PSEM_REG_FAST_MEMORY, + PSEM_REG_DBG_FRAME_MODE, PSEM_REG_SLOW_DBG_ACTIVE, + PSEM_REG_SLOW_DBG_MODE, PSEM_REG_DBG_MODE1_CFG, + PSEM_REG_SYNC_DBG_EMPTY, PSEM_REG_SLOW_DBG_EMPTY, + PCM_REG_CTX_RBC_ACCS, + 0, 0, + 10, PCM_REG_SM_CON_CTX, + 0, 0, + 0, 0} +}; + +/* Block definitions array */ +static struct block_defs block_grc_defs = { + "grc", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN}, + GRC_REG_DBG_SELECT, GRC_REG_DBG_DWORD_ENABLE, + GRC_REG_DBG_SHIFT, GRC_REG_DBG_FORCE_VALID, + GRC_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISC_PL_UA, 1 +}; + +static struct block_defs block_miscs_defs = { + "miscs", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_misc_defs = { + "misc", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_dbu_defs = { + "dbu", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_pglue_b_defs = { + "pglue_b", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH}, + PGLUE_B_REG_DBG_SELECT, PGLUE_B_REG_DBG_DWORD_ENABLE, + PGLUE_B_REG_DBG_SHIFT, PGLUE_B_REG_DBG_FORCE_VALID, + PGLUE_B_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISCS_PL_HV, 1 +}; + +static struct block_defs block_cnig_defs = { + "cnig", {false, false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, + CNIG_REG_DBG_SELECT_K2, CNIG_REG_DBG_DWORD_ENABLE_K2, + CNIG_REG_DBG_SHIFT_K2, CNIG_REG_DBG_FORCE_VALID_K2, + CNIG_REG_DBG_FORCE_FRAME_K2, + true, false, DBG_RESET_REG_MISCS_PL_HV, 0 +}; + +static struct block_defs block_cpmu_defs = { + "cpmu", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, false, DBG_RESET_REG_MISCS_PL_HV, 8 +}; + +static struct block_defs block_ncsi_defs = { + "ncsi", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ}, + NCSI_REG_DBG_SELECT, NCSI_REG_DBG_DWORD_ENABLE, + NCSI_REG_DBG_SHIFT, NCSI_REG_DBG_FORCE_VALID, + NCSI_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISCS_PL_HV, 5 +}; + +static struct block_defs block_opte_defs = { + "opte", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, false, DBG_RESET_REG_MISCS_PL_HV, 4 +}; + +static struct block_defs block_bmb_defs = { + "bmb", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB}, + BMB_REG_DBG_SELECT, BMB_REG_DBG_DWORD_ENABLE, + BMB_REG_DBG_SHIFT, BMB_REG_DBG_FORCE_VALID, + BMB_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISCS_PL_UA, 7 +}; + +static struct block_defs block_pcie_defs = { + "pcie", {false, false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, + PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE, + PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID, + PCIE_REG_DBG_COMMON_FORCE_FRAME, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_mcp_defs = { + "mcp", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_mcp2_defs = { + "mcp2", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ}, + MCP2_REG_DBG_SELECT, MCP2_REG_DBG_DWORD_ENABLE, + MCP2_REG_DBG_SHIFT, MCP2_REG_DBG_FORCE_VALID, + MCP2_REG_DBG_FORCE_FRAME, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_pswhst_defs = { + "pswhst", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + PSWHST_REG_DBG_SELECT, PSWHST_REG_DBG_DWORD_ENABLE, + PSWHST_REG_DBG_SHIFT, PSWHST_REG_DBG_FORCE_VALID, + PSWHST_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISC_PL_HV, 0 +}; + +static struct block_defs block_pswhst2_defs = { + "pswhst2", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + PSWHST2_REG_DBG_SELECT, PSWHST2_REG_DBG_DWORD_ENABLE, + PSWHST2_REG_DBG_SHIFT, PSWHST2_REG_DBG_FORCE_VALID, + PSWHST2_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISC_PL_HV, 0 +}; + +static struct block_defs block_pswrd_defs = { + "pswrd", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + PSWRD_REG_DBG_SELECT, PSWRD_REG_DBG_DWORD_ENABLE, + PSWRD_REG_DBG_SHIFT, PSWRD_REG_DBG_FORCE_VALID, + PSWRD_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISC_PL_HV, 2 +}; + +static struct block_defs block_pswrd2_defs = { + "pswrd2", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + PSWRD2_REG_DBG_SELECT, PSWRD2_REG_DBG_DWORD_ENABLE, + PSWRD2_REG_DBG_SHIFT, PSWRD2_REG_DBG_FORCE_VALID, + PSWRD2_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISC_PL_HV, 2 +}; + +static struct block_defs block_pswwr_defs = { + "pswwr", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + PSWWR_REG_DBG_SELECT, PSWWR_REG_DBG_DWORD_ENABLE, + PSWWR_REG_DBG_SHIFT, PSWWR_REG_DBG_FORCE_VALID, + PSWWR_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISC_PL_HV, 3 +}; + +static struct block_defs block_pswwr2_defs = { + "pswwr2", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, false, DBG_RESET_REG_MISC_PL_HV, 3 +}; + +static struct block_defs block_pswrq_defs = { + "pswrq", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + PSWRQ_REG_DBG_SELECT, PSWRQ_REG_DBG_DWORD_ENABLE, + PSWRQ_REG_DBG_SHIFT, PSWRQ_REG_DBG_FORCE_VALID, + PSWRQ_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISC_PL_HV, 1 +}; + +static struct block_defs block_pswrq2_defs = { + "pswrq2", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + PSWRQ2_REG_DBG_SELECT, PSWRQ2_REG_DBG_DWORD_ENABLE, + PSWRQ2_REG_DBG_SHIFT, PSWRQ2_REG_DBG_FORCE_VALID, + PSWRQ2_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISC_PL_HV, 1 +}; + +static struct block_defs block_pglcs_defs = { + "pglcs", {false, false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, + PGLCS_REG_DBG_SELECT, PGLCS_REG_DBG_DWORD_ENABLE, + PGLCS_REG_DBG_SHIFT, PGLCS_REG_DBG_FORCE_VALID, + PGLCS_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISCS_PL_HV, 2 +}; + +static struct block_defs block_ptu_defs = { + "ptu", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + PTU_REG_DBG_SELECT, PTU_REG_DBG_DWORD_ENABLE, + PTU_REG_DBG_SHIFT, PTU_REG_DBG_FORCE_VALID, + PTU_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 20 +}; + +static struct block_defs block_dmae_defs = { + "dmae", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + DMAE_REG_DBG_SELECT, DMAE_REG_DBG_DWORD_ENABLE, + DMAE_REG_DBG_SHIFT, DMAE_REG_DBG_FORCE_VALID, + DMAE_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 28 +}; + +static struct block_defs block_tcm_defs = { + "tcm", {true, true, true}, true, DBG_TSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + TCM_REG_DBG_SELECT, TCM_REG_DBG_DWORD_ENABLE, + TCM_REG_DBG_SHIFT, TCM_REG_DBG_FORCE_VALID, + TCM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 5 +}; + +static struct block_defs block_mcm_defs = { + "mcm", {true, true, true}, true, DBG_MSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + MCM_REG_DBG_SELECT, MCM_REG_DBG_DWORD_ENABLE, + MCM_REG_DBG_SHIFT, MCM_REG_DBG_FORCE_VALID, + MCM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 3 +}; + +static struct block_defs block_ucm_defs = { + "ucm", {true, true, true}, true, DBG_USTORM_ID, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + UCM_REG_DBG_SELECT, UCM_REG_DBG_DWORD_ENABLE, + UCM_REG_DBG_SHIFT, UCM_REG_DBG_FORCE_VALID, + UCM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 8 +}; + +static struct block_defs block_xcm_defs = { + "xcm", {true, true, true}, true, DBG_XSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + XCM_REG_DBG_SELECT, XCM_REG_DBG_DWORD_ENABLE, + XCM_REG_DBG_SHIFT, XCM_REG_DBG_FORCE_VALID, + XCM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 19 +}; + +static struct block_defs block_ycm_defs = { + "ycm", {true, true, true}, true, DBG_YSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + YCM_REG_DBG_SELECT, YCM_REG_DBG_DWORD_ENABLE, + YCM_REG_DBG_SHIFT, YCM_REG_DBG_FORCE_VALID, + YCM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 5 +}; + +static struct block_defs block_pcm_defs = { + "pcm", {true, true, true}, true, DBG_PSTORM_ID, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + PCM_REG_DBG_SELECT, PCM_REG_DBG_DWORD_ENABLE, + PCM_REG_DBG_SHIFT, PCM_REG_DBG_FORCE_VALID, + PCM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 4 +}; + +static struct block_defs block_qm_defs = { + "qm", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ}, + QM_REG_DBG_SELECT, QM_REG_DBG_DWORD_ENABLE, + QM_REG_DBG_SHIFT, QM_REG_DBG_FORCE_VALID, + QM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 16 +}; + +static struct block_defs block_tm_defs = { + "tm", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + TM_REG_DBG_SELECT, TM_REG_DBG_DWORD_ENABLE, + TM_REG_DBG_SHIFT, TM_REG_DBG_FORCE_VALID, + TM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 17 +}; + +static struct block_defs block_dorq_defs = { + "dorq", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + DORQ_REG_DBG_SELECT, DORQ_REG_DBG_DWORD_ENABLE, + DORQ_REG_DBG_SHIFT, DORQ_REG_DBG_FORCE_VALID, + DORQ_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 18 +}; + +static struct block_defs block_brb_defs = { + "brb", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR}, + BRB_REG_DBG_SELECT, BRB_REG_DBG_DWORD_ENABLE, + BRB_REG_DBG_SHIFT, BRB_REG_DBG_FORCE_VALID, + BRB_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 0 +}; + +static struct block_defs block_src_defs = { + "src", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + SRC_REG_DBG_SELECT, SRC_REG_DBG_DWORD_ENABLE, + SRC_REG_DBG_SHIFT, SRC_REG_DBG_FORCE_VALID, + SRC_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 2 +}; + +static struct block_defs block_prs_defs = { + "prs", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR}, + PRS_REG_DBG_SELECT, PRS_REG_DBG_DWORD_ENABLE, + PRS_REG_DBG_SHIFT, PRS_REG_DBG_FORCE_VALID, + PRS_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 1 +}; + +static struct block_defs block_tsdm_defs = { + "tsdm", {true, true, true}, true, DBG_TSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + TSDM_REG_DBG_SELECT, TSDM_REG_DBG_DWORD_ENABLE, + TSDM_REG_DBG_SHIFT, TSDM_REG_DBG_FORCE_VALID, + TSDM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 3 +}; + +static struct block_defs block_msdm_defs = { + "msdm", {true, true, true}, true, DBG_MSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + MSDM_REG_DBG_SELECT, MSDM_REG_DBG_DWORD_ENABLE, + MSDM_REG_DBG_SHIFT, MSDM_REG_DBG_FORCE_VALID, + MSDM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 6 +}; + +static struct block_defs block_usdm_defs = { + "usdm", {true, true, true}, true, DBG_USTORM_ID, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + USDM_REG_DBG_SELECT, USDM_REG_DBG_DWORD_ENABLE, + USDM_REG_DBG_SHIFT, USDM_REG_DBG_FORCE_VALID, + USDM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 7 +}; + +static struct block_defs block_xsdm_defs = { + "xsdm", {true, true, true}, true, DBG_XSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + XSDM_REG_DBG_SELECT, XSDM_REG_DBG_DWORD_ENABLE, + XSDM_REG_DBG_SHIFT, XSDM_REG_DBG_FORCE_VALID, + XSDM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 20 +}; + +static struct block_defs block_ysdm_defs = { + "ysdm", {true, true, true}, true, DBG_YSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + YSDM_REG_DBG_SELECT, YSDM_REG_DBG_DWORD_ENABLE, + YSDM_REG_DBG_SHIFT, YSDM_REG_DBG_FORCE_VALID, + YSDM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 8 +}; + +static struct block_defs block_psdm_defs = { + "psdm", {true, true, true}, true, DBG_PSTORM_ID, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + PSDM_REG_DBG_SELECT, PSDM_REG_DBG_DWORD_ENABLE, + PSDM_REG_DBG_SHIFT, PSDM_REG_DBG_FORCE_VALID, + PSDM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 7 +}; + +static struct block_defs block_tsem_defs = { + "tsem", {true, true, true}, true, DBG_TSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + TSEM_REG_DBG_SELECT, TSEM_REG_DBG_DWORD_ENABLE, + TSEM_REG_DBG_SHIFT, TSEM_REG_DBG_FORCE_VALID, + TSEM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 4 +}; + +static struct block_defs block_msem_defs = { + "msem", {true, true, true}, true, DBG_MSTORM_ID, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + MSEM_REG_DBG_SELECT, MSEM_REG_DBG_DWORD_ENABLE, + MSEM_REG_DBG_SHIFT, MSEM_REG_DBG_FORCE_VALID, + MSEM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 9 +}; + +static struct block_defs block_usem_defs = { + "usem", {true, true, true}, true, DBG_USTORM_ID, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + USEM_REG_DBG_SELECT, USEM_REG_DBG_DWORD_ENABLE, + USEM_REG_DBG_SHIFT, USEM_REG_DBG_FORCE_VALID, + USEM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 9 +}; + +static struct block_defs block_xsem_defs = { + "xsem", {true, true, true}, true, DBG_XSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + XSEM_REG_DBG_SELECT, XSEM_REG_DBG_DWORD_ENABLE, + XSEM_REG_DBG_SHIFT, XSEM_REG_DBG_FORCE_VALID, + XSEM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 21 +}; + +static struct block_defs block_ysem_defs = { + "ysem", {true, true, true}, true, DBG_YSTORM_ID, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, + YSEM_REG_DBG_SELECT, YSEM_REG_DBG_DWORD_ENABLE, + YSEM_REG_DBG_SHIFT, YSEM_REG_DBG_FORCE_VALID, + YSEM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 11 +}; + +static struct block_defs block_psem_defs = { + "psem", {true, true, true}, true, DBG_PSTORM_ID, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + PSEM_REG_DBG_SELECT, PSEM_REG_DBG_DWORD_ENABLE, + PSEM_REG_DBG_SHIFT, PSEM_REG_DBG_FORCE_VALID, + PSEM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 10 +}; + +static struct block_defs block_rss_defs = { + "rss", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, + RSS_REG_DBG_SELECT, RSS_REG_DBG_DWORD_ENABLE, + RSS_REG_DBG_SHIFT, RSS_REG_DBG_FORCE_VALID, + RSS_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 18 +}; + +static struct block_defs block_tmld_defs = { + "tmld", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + TMLD_REG_DBG_SELECT, TMLD_REG_DBG_DWORD_ENABLE, + TMLD_REG_DBG_SHIFT, TMLD_REG_DBG_FORCE_VALID, + TMLD_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 13 +}; + +static struct block_defs block_muld_defs = { + "muld", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + MULD_REG_DBG_SELECT, MULD_REG_DBG_DWORD_ENABLE, + MULD_REG_DBG_SHIFT, MULD_REG_DBG_FORCE_VALID, + MULD_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 14 +}; + +static struct block_defs block_yuld_defs = { + "yuld", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, + YULD_REG_DBG_SELECT, YULD_REG_DBG_DWORD_ENABLE, + YULD_REG_DBG_SHIFT, YULD_REG_DBG_FORCE_VALID, + YULD_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 15 +}; + +static struct block_defs block_xyld_defs = { + "xyld", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, + XYLD_REG_DBG_SELECT, XYLD_REG_DBG_DWORD_ENABLE, + XYLD_REG_DBG_SHIFT, XYLD_REG_DBG_FORCE_VALID, + XYLD_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 12 +}; + +static struct block_defs block_prm_defs = { + "prm", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + PRM_REG_DBG_SELECT, PRM_REG_DBG_DWORD_ENABLE, + PRM_REG_DBG_SHIFT, PRM_REG_DBG_FORCE_VALID, + PRM_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 21 +}; + +static struct block_defs block_pbf_pb1_defs = { + "pbf_pb1", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, + PBF_PB1_REG_DBG_SELECT, PBF_PB1_REG_DBG_DWORD_ENABLE, + PBF_PB1_REG_DBG_SHIFT, PBF_PB1_REG_DBG_FORCE_VALID, + PBF_PB1_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, + 11 +}; + +static struct block_defs block_pbf_pb2_defs = { + "pbf_pb2", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, + PBF_PB2_REG_DBG_SELECT, PBF_PB2_REG_DBG_DWORD_ENABLE, + PBF_PB2_REG_DBG_SHIFT, PBF_PB2_REG_DBG_FORCE_VALID, + PBF_PB2_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, + 12 +}; + +static struct block_defs block_rpb_defs = { + "rpb", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + RPB_REG_DBG_SELECT, RPB_REG_DBG_DWORD_ENABLE, + RPB_REG_DBG_SHIFT, RPB_REG_DBG_FORCE_VALID, + RPB_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 13 +}; + +static struct block_defs block_btb_defs = { + "btb", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV}, + BTB_REG_DBG_SELECT, BTB_REG_DBG_DWORD_ENABLE, + BTB_REG_DBG_SHIFT, BTB_REG_DBG_FORCE_VALID, + BTB_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 10 +}; + +static struct block_defs block_pbf_defs = { + "pbf", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV}, + PBF_REG_DBG_SELECT, PBF_REG_DBG_DWORD_ENABLE, + PBF_REG_DBG_SHIFT, PBF_REG_DBG_FORCE_VALID, + PBF_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 15 +}; + +static struct block_defs block_rdif_defs = { + "rdif", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, + RDIF_REG_DBG_SELECT, RDIF_REG_DBG_DWORD_ENABLE, + RDIF_REG_DBG_SHIFT, RDIF_REG_DBG_FORCE_VALID, + RDIF_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 16 +}; + +static struct block_defs block_tdif_defs = { + "tdif", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, + TDIF_REG_DBG_SELECT, TDIF_REG_DBG_DWORD_ENABLE, + TDIF_REG_DBG_SHIFT, TDIF_REG_DBG_FORCE_VALID, + TDIF_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 17 +}; + +static struct block_defs block_cdu_defs = { + "cdu", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + CDU_REG_DBG_SELECT, CDU_REG_DBG_DWORD_ENABLE, + CDU_REG_DBG_SHIFT, CDU_REG_DBG_FORCE_VALID, + CDU_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 23 +}; + +static struct block_defs block_ccfc_defs = { + "ccfc", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + CCFC_REG_DBG_SELECT, CCFC_REG_DBG_DWORD_ENABLE, + CCFC_REG_DBG_SHIFT, CCFC_REG_DBG_FORCE_VALID, + CCFC_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 24 +}; + +static struct block_defs block_tcfc_defs = { + "tcfc", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF}, + TCFC_REG_DBG_SELECT, TCFC_REG_DBG_DWORD_ENABLE, + TCFC_REG_DBG_SHIFT, TCFC_REG_DBG_FORCE_VALID, + TCFC_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 25 +}; + +static struct block_defs block_igu_defs = { + "igu", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + IGU_REG_DBG_SELECT, IGU_REG_DBG_DWORD_ENABLE, + IGU_REG_DBG_SHIFT, IGU_REG_DBG_FORCE_VALID, + IGU_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, 27 +}; + +static struct block_defs block_cau_defs = { + "cau", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP}, + CAU_REG_DBG_SELECT, CAU_REG_DBG_DWORD_ENABLE, + CAU_REG_DBG_SHIFT, CAU_REG_DBG_FORCE_VALID, + CAU_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, 19 +}; + +static struct block_defs block_umac_defs = { + "umac", {false, false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, + UMAC_REG_DBG_SELECT, UMAC_REG_DBG_DWORD_ENABLE, + UMAC_REG_DBG_SHIFT, UMAC_REG_DBG_FORCE_VALID, + UMAC_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISCS_PL_HV, 6 +}; + +static struct block_defs block_xmac_defs = { + "xmac", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_dbg_defs = { + "dbg", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, true, DBG_RESET_REG_MISC_PL_PDA_VAUX, 3 +}; + +static struct block_defs block_nig_defs = { + "nig", {true, true, true}, false, 0, + {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN}, + NIG_REG_DBG_SELECT, NIG_REG_DBG_DWORD_ENABLE, + NIG_REG_DBG_SHIFT, NIG_REG_DBG_FORCE_VALID, + NIG_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VAUX, 0 +}; + +static struct block_defs block_wol_defs = { + "wol", {false, false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ}, + WOL_REG_DBG_SELECT, WOL_REG_DBG_DWORD_ENABLE, + WOL_REG_DBG_SHIFT, WOL_REG_DBG_FORCE_VALID, + WOL_REG_DBG_FORCE_FRAME, + true, true, DBG_RESET_REG_MISC_PL_PDA_VAUX, 7 +}; + +static struct block_defs block_bmbn_defs = { + "bmbn", {false, false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB}, + BMBN_REG_DBG_SELECT, BMBN_REG_DBG_DWORD_ENABLE, + BMBN_REG_DBG_SHIFT, BMBN_REG_DBG_FORCE_VALID, + BMBN_REG_DBG_FORCE_FRAME, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_ipc_defs = { + "ipc", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, false, DBG_RESET_REG_MISCS_PL_UA, 8 +}; + +static struct block_defs block_nwm_defs = { + "nwm", {false, false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW}, + NWM_REG_DBG_SELECT, NWM_REG_DBG_DWORD_ENABLE, + NWM_REG_DBG_SHIFT, NWM_REG_DBG_FORCE_VALID, + NWM_REG_DBG_FORCE_FRAME, + true, false, DBG_RESET_REG_MISCS_PL_HV_2, 0 +}; + +static struct block_defs block_nws_defs = { + "nws", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, false, DBG_RESET_REG_MISCS_PL_HV, 12 +}; + +static struct block_defs block_ms_defs = { + "ms", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, false, DBG_RESET_REG_MISCS_PL_HV, 13 +}; + +static struct block_defs block_phy_pcie_defs = { + "phy_pcie", {false, false, true}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH}, + PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE, + PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID, + PCIE_REG_DBG_COMMON_FORCE_FRAME, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_led_defs = { + "led", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + true, true, DBG_RESET_REG_MISCS_PL_HV, 14 +}; + +static struct block_defs block_misc_aeu_defs = { + "misc_aeu", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs block_bar0_map_defs = { + "bar0_map", {false, false, false}, false, 0, + {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS}, + 0, 0, 0, 0, 0, + false, false, MAX_DBG_RESET_REGS, 0 +}; + +static struct block_defs *s_block_defs[MAX_BLOCK_ID] = { + &block_grc_defs, + &block_miscs_defs, + &block_misc_defs, + &block_dbu_defs, + &block_pglue_b_defs, + &block_cnig_defs, + &block_cpmu_defs, + &block_ncsi_defs, + &block_opte_defs, + &block_bmb_defs, + &block_pcie_defs, + &block_mcp_defs, + &block_mcp2_defs, + &block_pswhst_defs, + &block_pswhst2_defs, + &block_pswrd_defs, + &block_pswrd2_defs, + &block_pswwr_defs, + &block_pswwr2_defs, + &block_pswrq_defs, + &block_pswrq2_defs, + &block_pglcs_defs, + &block_dmae_defs, + &block_ptu_defs, + &block_tcm_defs, + &block_mcm_defs, + &block_ucm_defs, + &block_xcm_defs, + &block_ycm_defs, + &block_pcm_defs, + &block_qm_defs, + &block_tm_defs, + &block_dorq_defs, + &block_brb_defs, + &block_src_defs, + &block_prs_defs, + &block_tsdm_defs, + &block_msdm_defs, + &block_usdm_defs, + &block_xsdm_defs, + &block_ysdm_defs, + &block_psdm_defs, + &block_tsem_defs, + &block_msem_defs, + &block_usem_defs, + &block_xsem_defs, + &block_ysem_defs, + &block_psem_defs, + &block_rss_defs, + &block_tmld_defs, + &block_muld_defs, + &block_yuld_defs, + &block_xyld_defs, + &block_prm_defs, + &block_pbf_pb1_defs, + &block_pbf_pb2_defs, + &block_rpb_defs, + &block_btb_defs, + &block_pbf_defs, + &block_rdif_defs, + &block_tdif_defs, + &block_cdu_defs, + &block_ccfc_defs, + &block_tcfc_defs, + &block_igu_defs, + &block_cau_defs, + &block_umac_defs, + &block_xmac_defs, + &block_dbg_defs, + &block_nig_defs, + &block_wol_defs, + &block_bmbn_defs, + &block_ipc_defs, + &block_nwm_defs, + &block_nws_defs, + &block_ms_defs, + &block_phy_pcie_defs, + &block_led_defs, + &block_misc_aeu_defs, + &block_bar0_map_defs, +}; + +static struct platform_defs s_platform_defs[] = { + {"asic", 1}, + {"reserved", 0}, + {"reserved2", 0}, + {"reserved3", 0} +}; + +static struct grc_param_defs s_grc_param_defs[] = { + {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_TSTORM */ + {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_MSTORM */ + {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_USTORM */ + {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_XSTORM */ + {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_YSTORM */ + {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_PSTORM */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_REGS */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RAM */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PBUF */ + {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IOR */ + {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_VFC */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM_CTX */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_ILT */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RSS */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CAU */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_QM */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MCP */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_RESERVED */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CFC */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IGU */ + {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BRB */ + {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BTB */ + {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BMB */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_NIG */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MULD */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PRS */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DMAE */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_TM */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_SDM */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DIF */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_STATIC */ + {{0, 0, 0}, 0, 1, false, 0, 0}, /* DBG_GRC_PARAM_UNSTALL */ + {{MAX_LCIDS, MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS, + MAX_LCIDS}, /* DBG_GRC_PARAM_NUM_LCIDS */ + {{MAX_LTIDS, MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS, + MAX_LTIDS}, /* DBG_GRC_PARAM_NUM_LTIDS */ + {{0, 0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_EXCLUDE_ALL */ + {{0, 0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_CRASH */ + {{0, 0, 0}, 0, 1, false, 1, 0}, /* DBG_GRC_PARAM_PARITY_SAFE */ + {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM */ + {{1, 1, 1}, 0, 1, false, 0, 1} /* DBG_GRC_PARAM_DUMP_PHY */ +}; + +static struct rss_mem_defs s_rss_mem_defs[] = { + { "rss_mem_cid", "rss_cid", 0, + {256, 256, 320}, + {32, 32, 32} }, + { "rss_mem_key_msb", "rss_key", 1024, + {128, 128, 208}, + {256, 256, 256} }, + { "rss_mem_key_lsb", "rss_key", 2048, + {128, 128, 208}, + {64, 64, 64} }, + { "rss_mem_info", "rss_info", 3072, + {128, 128, 208}, + {16, 16, 16} }, + { "rss_mem_ind", "rss_ind", 4096, + {(128 * 128), (128 * 128), (128 * 208)}, + {16, 16, 16} } +}; + +static struct vfc_ram_defs s_vfc_ram_defs[] = { + {"vfc_ram_tt1", "vfc_ram", 0, 512}, + {"vfc_ram_mtt2", "vfc_ram", 512, 128}, + {"vfc_ram_stt2", "vfc_ram", 640, 32}, + {"vfc_ram_ro_vect", "vfc_ram", 672, 32} +}; + +static struct big_ram_defs s_big_ram_defs[] = { + { "BRB", MEM_GROUP_BRB_MEM, MEM_GROUP_BRB_RAM, DBG_GRC_PARAM_DUMP_BRB, + BRB_REG_BIG_RAM_ADDRESS, BRB_REG_BIG_RAM_DATA, + {4800, 4800, 5632} }, + { "BTB", MEM_GROUP_BTB_MEM, MEM_GROUP_BTB_RAM, DBG_GRC_PARAM_DUMP_BTB, + BTB_REG_BIG_RAM_ADDRESS, BTB_REG_BIG_RAM_DATA, + {2880, 2880, 3680} }, + { "BMB", MEM_GROUP_BMB_MEM, MEM_GROUP_BMB_RAM, DBG_GRC_PARAM_DUMP_BMB, + BMB_REG_BIG_RAM_ADDRESS, BMB_REG_BIG_RAM_DATA, + {1152, 1152, 1152} } +}; + +static struct reset_reg_defs s_reset_regs_defs[] = { + { MISCS_REG_RESET_PL_UA, 0x0, + {true, true, true} }, /* DBG_RESET_REG_MISCS_PL_UA */ + { MISCS_REG_RESET_PL_HV, 0x0, + {true, true, true} }, /* DBG_RESET_REG_MISCS_PL_HV */ + { MISCS_REG_RESET_PL_HV_2, 0x0, + {false, false, true} }, /* DBG_RESET_REG_MISCS_PL_HV_2 */ + { MISC_REG_RESET_PL_UA, 0x0, + {true, true, true} }, /* DBG_RESET_REG_MISC_PL_UA */ + { MISC_REG_RESET_PL_HV, 0x0, + {true, true, true} }, /* DBG_RESET_REG_MISC_PL_HV */ + { MISC_REG_RESET_PL_PDA_VMAIN_1, 0x4404040, + {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */ + { MISC_REG_RESET_PL_PDA_VMAIN_2, 0x7c00007, + {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */ + { MISC_REG_RESET_PL_PDA_VAUX, 0x2, + {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VAUX */ +}; + +static struct phy_defs s_phy_defs[] = { + {"nw_phy", NWS_REG_NWS_CMU, PHY_NW_IP_REG_PHY0_TOP_TBUS_ADDR_7_0, + PHY_NW_IP_REG_PHY0_TOP_TBUS_ADDR_15_8, + PHY_NW_IP_REG_PHY0_TOP_TBUS_DATA_7_0, + PHY_NW_IP_REG_PHY0_TOP_TBUS_DATA_11_8}, + {"sgmii_phy", MS_REG_MS_CMU, PHY_SGMII_IP_REG_AHB_CMU_CSR_0_X132, + PHY_SGMII_IP_REG_AHB_CMU_CSR_0_X133, + PHY_SGMII_IP_REG_AHB_CMU_CSR_0_X130, + PHY_SGMII_IP_REG_AHB_CMU_CSR_0_X131}, + {"pcie_phy0", PHY_PCIE_REG_PHY0, PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X132, + PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X133, + PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X130, + PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X131}, + {"pcie_phy1", PHY_PCIE_REG_PHY1, PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X132, + PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X133, + PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X130, + PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X131}, +}; + +/**************************** Private Functions ******************************/ + +/* Reads and returns a single dword from the specified unaligned buffer */ +static u32 qed_read_unaligned_dword(u8 *buf) +{ + u32 dword; + + memcpy((u8 *)&dword, buf, sizeof(dword)); + return dword; +} + +/* Initializes debug data for the specified device */ +static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + + if (dev_data->initialized) + return DBG_STATUS_OK; + + if (QED_IS_K2(p_hwfn->cdev)) { + dev_data->chip_id = CHIP_K2; + dev_data->mode_enable[MODE_K2] = 1; + } else if (QED_IS_BB_B0(p_hwfn->cdev)) { + dev_data->chip_id = CHIP_BB_B0; + dev_data->mode_enable[MODE_BB_B0] = 1; + } else { + return DBG_STATUS_UNKNOWN_CHIP; + } + + dev_data->platform_id = PLATFORM_ASIC; + dev_data->mode_enable[MODE_ASIC] = 1; + dev_data->initialized = true; + return DBG_STATUS_OK; +} + +/* Reads the FW info structure for the specified Storm from the chip, + * and writes it to the specified fw_info pointer. + */ +static void qed_read_fw_info(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u8 storm_id, struct fw_info *fw_info) +{ + /* Read first the address that points to fw_info location. + * The address is located in the last line of the Storm RAM. + */ + u32 addr = s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_INT_RAM + + DWORDS_TO_BYTES(SEM_FAST_REG_INT_RAM_SIZE) - + sizeof(struct fw_info_location); + struct fw_info_location fw_info_location; + u32 *dest = (u32 *)&fw_info_location; + u32 i; + + memset(&fw_info_location, 0, sizeof(fw_info_location)); + memset(fw_info, 0, sizeof(*fw_info)); + for (i = 0; i < BYTES_TO_DWORDS(sizeof(fw_info_location)); + i++, addr += BYTES_IN_DWORD) + dest[i] = qed_rd(p_hwfn, p_ptt, addr); + if (fw_info_location.size > 0 && fw_info_location.size <= + sizeof(*fw_info)) { + /* Read FW version info from Storm RAM */ + addr = fw_info_location.grc_addr; + dest = (u32 *)fw_info; + for (i = 0; i < BYTES_TO_DWORDS(fw_info_location.size); + i++, addr += BYTES_IN_DWORD) + dest[i] = qed_rd(p_hwfn, p_ptt, addr); + } +} + +/* Dumps the specified string to the specified buffer. Returns the dumped size + * in bytes (actual length + 1 for the null character termination). + */ +static u32 qed_dump_str(char *dump_buf, bool dump, const char *str) +{ + if (dump) + strcpy(dump_buf, str); + return (u32)strlen(str) + 1; +} + +/* Dumps zeros to align the specified buffer to dwords. Returns the dumped size + * in bytes. + */ +static u32 qed_dump_align(char *dump_buf, bool dump, u32 byte_offset) +{ + u8 offset_in_dword = (u8)(byte_offset & 0x3), align_size; + + align_size = offset_in_dword ? BYTES_IN_DWORD - offset_in_dword : 0; + + if (dump && align_size) + memset(dump_buf, 0, align_size); + return align_size; +} + +/* Writes the specified string param to the specified buffer. + * Returns the dumped size in dwords. + */ +static u32 qed_dump_str_param(u32 *dump_buf, + bool dump, + const char *param_name, const char *param_val) +{ + char *char_buf = (char *)dump_buf; + u32 offset = 0; + + /* Dump param name */ + offset += qed_dump_str(char_buf + offset, dump, param_name); + + /* Indicate a string param value */ + if (dump) + *(char_buf + offset) = 1; + offset++; + + /* Dump param value */ + offset += qed_dump_str(char_buf + offset, dump, param_val); + + /* Align buffer to next dword */ + offset += qed_dump_align(char_buf + offset, dump, offset); + return BYTES_TO_DWORDS(offset); +} + +/* Writes the specified numeric param to the specified buffer. + * Returns the dumped size in dwords. + */ +static u32 qed_dump_num_param(u32 *dump_buf, + bool dump, const char *param_name, u32 param_val) +{ + char *char_buf = (char *)dump_buf; + u32 offset = 0; + + /* Dump param name */ + offset += qed_dump_str(char_buf + offset, dump, param_name); + + /* Indicate a numeric param value */ + if (dump) + *(char_buf + offset) = 0; + offset++; + + /* Align buffer to next dword */ + offset += qed_dump_align(char_buf + offset, dump, offset); + + /* Dump param value (and change offset from bytes to dwords) */ + offset = BYTES_TO_DWORDS(offset); + if (dump) + *(dump_buf + offset) = param_val; + offset++; + return offset; +} + +/* Reads the FW version and writes it as a param to the specified buffer. + * Returns the dumped size in dwords. + */ +static u32 qed_dump_fw_ver_param(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + char fw_ver_str[16] = EMPTY_FW_VERSION_STR; + char fw_img_str[16] = EMPTY_FW_IMAGE_STR; + struct fw_info fw_info = { {0}, {0} }; + int printed_chars; + u32 offset = 0; + + if (dump) { + /* Read FW image/version from PRAM in a non-reset SEMI */ + bool found = false; + u8 storm_id; + + for (storm_id = 0; storm_id < MAX_DBG_STORMS && !found; + storm_id++) { + /* Read FW version/image */ + if (!dev_data->block_in_reset + [s_storm_defs[storm_id].block_id]) { + /* read FW info for the current Storm */ + qed_read_fw_info(p_hwfn, + p_ptt, storm_id, &fw_info); + + /* Create FW version/image strings */ + printed_chars = + snprintf(fw_ver_str, + sizeof(fw_ver_str), + "%d_%d_%d_%d", + fw_info.ver.num.major, + fw_info.ver.num.minor, + fw_info.ver.num.rev, + fw_info.ver.num.eng); + if (printed_chars < 0 || printed_chars >= + sizeof(fw_ver_str)) + DP_NOTICE(p_hwfn, + "Unexpected debug error: invalid FW version string\n"); + switch (fw_info.ver.image_id) { + case FW_IMG_MAIN: + strcpy(fw_img_str, "main"); + break; + default: + strcpy(fw_img_str, "unknown"); + break; + } + + found = true; + } + } + } + + /* Dump FW version, image and timestamp */ + offset += qed_dump_str_param(dump_buf + offset, + dump, "fw-version", fw_ver_str); + offset += qed_dump_str_param(dump_buf + offset, + dump, "fw-image", fw_img_str); + offset += qed_dump_num_param(dump_buf + offset, + dump, + "fw-timestamp", fw_info.ver.timestamp); + return offset; +} + +/* Reads the MFW version and writes it as a param to the specified buffer. + * Returns the dumped size in dwords. + */ +static u32 qed_dump_mfw_ver_param(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump) +{ + char mfw_ver_str[16] = EMPTY_FW_VERSION_STR; + + if (dump) { + u32 global_section_offsize, global_section_addr, mfw_ver; + u32 public_data_addr, global_section_offsize_addr; + int printed_chars; + + /* Find MCP public data GRC address. + * Needs to be ORed with MCP_REG_SCRATCH due to a HW bug. + */ + public_data_addr = qed_rd(p_hwfn, p_ptt, + MISC_REG_SHARED_MEM_ADDR) | + MCP_REG_SCRATCH; + + /* Find MCP public global section offset */ + global_section_offsize_addr = public_data_addr + + offsetof(struct mcp_public_data, + sections) + + sizeof(offsize_t) * PUBLIC_GLOBAL; + global_section_offsize = qed_rd(p_hwfn, p_ptt, + global_section_offsize_addr); + global_section_addr = MCP_REG_SCRATCH + + (global_section_offsize & + OFFSIZE_OFFSET_MASK) * 4; + + /* Read MFW version from MCP public global section */ + mfw_ver = qed_rd(p_hwfn, p_ptt, + global_section_addr + + offsetof(struct public_global, mfw_ver)); + + /* Dump MFW version param */ + printed_chars = snprintf(mfw_ver_str, sizeof(mfw_ver_str), + "%d_%d_%d_%d", + (u8) (mfw_ver >> 24), + (u8) (mfw_ver >> 16), + (u8) (mfw_ver >> 8), + (u8) mfw_ver); + if (printed_chars < 0 || printed_chars >= sizeof(mfw_ver_str)) + DP_NOTICE(p_hwfn, + "Unexpected debug error: invalid MFW version string\n"); + } + + return qed_dump_str_param(dump_buf, dump, "mfw-version", mfw_ver_str); +} + +/* Writes a section header to the specified buffer. + * Returns the dumped size in dwords. + */ +static u32 qed_dump_section_hdr(u32 *dump_buf, + bool dump, const char *name, u32 num_params) +{ + return qed_dump_num_param(dump_buf, dump, name, num_params); +} + +/* Writes the common global params to the specified buffer. + * Returns the dumped size in dwords. + */ +static u32 qed_dump_common_global_params(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + bool dump, + u8 num_specific_global_params) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 offset = 0; + + /* Find platform string and dump global params section header */ + offset += qed_dump_section_hdr(dump_buf + offset, + dump, + "global_params", + NUM_COMMON_GLOBAL_PARAMS + + num_specific_global_params); + + /* Store params */ + offset += qed_dump_fw_ver_param(p_hwfn, p_ptt, dump_buf + offset, dump); + offset += qed_dump_mfw_ver_param(p_hwfn, + p_ptt, dump_buf + offset, dump); + offset += qed_dump_num_param(dump_buf + offset, + dump, "tools-version", TOOLS_VERSION); + offset += qed_dump_str_param(dump_buf + offset, + dump, + "chip", + s_chip_defs[dev_data->chip_id].name); + offset += qed_dump_str_param(dump_buf + offset, + dump, + "platform", + s_platform_defs[dev_data->platform_id]. + name); + offset += + qed_dump_num_param(dump_buf + offset, dump, "pci-func", + p_hwfn->abs_pf_id); + return offset; +} + +/* Writes the last section to the specified buffer at the given offset. + * Returns the dumped size in dwords. + */ +static u32 qed_dump_last_section(u32 *dump_buf, u32 offset, bool dump) +{ + u32 start_offset = offset, crc = ~0; + + /* Dump CRC section header */ + offset += qed_dump_section_hdr(dump_buf + offset, dump, "last", 0); + + /* Calculate CRC32 and add it to the dword following the "last" section. + */ + if (dump) + *(dump_buf + offset) = ~crc32(crc, (u8 *)dump_buf, + DWORDS_TO_BYTES(offset)); + offset++; + return offset - start_offset; +} + +/* Update blocks reset state */ +static void qed_update_blocks_reset_state(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 reg_val[MAX_DBG_RESET_REGS] = { 0 }; + u32 i; + + /* Read reset registers */ + for (i = 0; i < MAX_DBG_RESET_REGS; i++) + if (s_reset_regs_defs[i].exists[dev_data->chip_id]) + reg_val[i] = qed_rd(p_hwfn, + p_ptt, s_reset_regs_defs[i].addr); + + /* Check if blocks are in reset */ + for (i = 0; i < MAX_BLOCK_ID; i++) + dev_data->block_in_reset[i] = + s_block_defs[i]->has_reset_bit && + !(reg_val[s_block_defs[i]->reset_reg] & + BIT(s_block_defs[i]->reset_bit_offset)); +} + +/* Enable / disable the Debug block */ +static void qed_bus_enable_dbg_block(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, bool enable) +{ + qed_wr(p_hwfn, p_ptt, DBG_REG_DBG_BLOCK_ON, enable ? 1 : 0); +} + +/* Resets the Debug block */ +static void qed_bus_reset_dbg_block(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + u32 dbg_reset_reg_addr, old_reset_reg_val, new_reset_reg_val; + + dbg_reset_reg_addr = + s_reset_regs_defs[s_block_defs[BLOCK_DBG]->reset_reg].addr; + old_reset_reg_val = qed_rd(p_hwfn, p_ptt, dbg_reset_reg_addr); + new_reset_reg_val = old_reset_reg_val & + ~BIT(s_block_defs[BLOCK_DBG]->reset_bit_offset); + + qed_wr(p_hwfn, p_ptt, dbg_reset_reg_addr, new_reset_reg_val); + qed_wr(p_hwfn, p_ptt, dbg_reset_reg_addr, old_reset_reg_val); +} + +static void qed_bus_set_framing_mode(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + enum dbg_bus_frame_modes mode) +{ + qed_wr(p_hwfn, p_ptt, DBG_REG_FRAMING_MODE, (u8)mode); +} + +/* Enable / disable Debug Bus clients according to the specified mask. + * (1 = enable, 0 = disable) + */ +static void qed_bus_enable_clients(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 client_mask) +{ + qed_wr(p_hwfn, p_ptt, DBG_REG_CLIENT_ENABLE, client_mask); +} + +static bool qed_is_mode_match(struct qed_hwfn *p_hwfn, u16 *modes_buf_offset) +{ + const u32 *ptr = s_dbg_arrays[BIN_BUF_DBG_MODE_TREE].ptr; + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u8 tree_val = ((u8 *)ptr)[(*modes_buf_offset)++]; + bool arg1, arg2; + + switch (tree_val) { + case INIT_MODE_OP_NOT: + return !qed_is_mode_match(p_hwfn, modes_buf_offset); + case INIT_MODE_OP_OR: + case INIT_MODE_OP_AND: + arg1 = qed_is_mode_match(p_hwfn, modes_buf_offset); + arg2 = qed_is_mode_match(p_hwfn, modes_buf_offset); + return (tree_val == INIT_MODE_OP_OR) ? (arg1 || + arg2) : (arg1 && arg2); + default: + return dev_data->mode_enable[tree_val - MAX_INIT_MODE_OPS] > 0; + } +} + +/* Returns the value of the specified GRC param */ +static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn, + enum dbg_grc_params grc_param) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + + return dev_data->grc.param_val[grc_param]; +} + +/* Clear all GRC params */ +static void qed_dbg_grc_clear_params(struct qed_hwfn *p_hwfn) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 i; + + for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) + dev_data->grc.param_set_by_user[i] = 0; +} + +/* Assign default GRC param values */ +static void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 i; + + for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) + if (!dev_data->grc.param_set_by_user[i]) + dev_data->grc.param_val[i] = + s_grc_param_defs[i].default_val[dev_data->chip_id]; +} + +/* Returns true if the specified entity (indicated by GRC param) should be + * included in the dump, false otherwise. + */ +static bool qed_grc_is_included(struct qed_hwfn *p_hwfn, + enum dbg_grc_params grc_param) +{ + return qed_grc_get_param(p_hwfn, grc_param) > 0; +} + +/* Returns true of the specified Storm should be included in the dump, false + * otherwise. + */ +static bool qed_grc_is_storm_included(struct qed_hwfn *p_hwfn, + enum dbg_storms storm) +{ + return qed_grc_get_param(p_hwfn, (enum dbg_grc_params)storm) > 0; +} + +/* Returns true if the specified memory should be included in the dump, false + * otherwise. + */ +static bool qed_grc_is_mem_included(struct qed_hwfn *p_hwfn, + enum block_id block_id, u8 mem_group_id) +{ + u8 i; + + /* Check Storm match */ + if (s_block_defs[block_id]->associated_to_storm && + !qed_grc_is_storm_included(p_hwfn, + (enum dbg_storms)s_block_defs[block_id]->storm_id)) + return false; + + for (i = 0; i < NUM_BIG_RAM_TYPES; i++) + if (mem_group_id == s_big_ram_defs[i].mem_group_id || + mem_group_id == s_big_ram_defs[i].ram_mem_group_id) + return qed_grc_is_included(p_hwfn, + s_big_ram_defs[i].grc_param); + if (mem_group_id == MEM_GROUP_PXP_ILT || mem_group_id == + MEM_GROUP_PXP_MEM) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_PXP); + if (mem_group_id == MEM_GROUP_RAM) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_RAM); + if (mem_group_id == MEM_GROUP_PBUF) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_PBUF); + if (mem_group_id == MEM_GROUP_CAU_MEM || + mem_group_id == MEM_GROUP_CAU_SB || + mem_group_id == MEM_GROUP_CAU_PI) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_CAU); + if (mem_group_id == MEM_GROUP_QM_MEM) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_QM); + if (mem_group_id == MEM_GROUP_CONN_CFC_MEM || + mem_group_id == MEM_GROUP_TASK_CFC_MEM) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_CFC); + if (mem_group_id == MEM_GROUP_IGU_MEM || mem_group_id == + MEM_GROUP_IGU_MSIX) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_IGU); + if (mem_group_id == MEM_GROUP_MULD_MEM) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_MULD); + if (mem_group_id == MEM_GROUP_PRS_MEM) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_PRS); + if (mem_group_id == MEM_GROUP_DMAE_MEM) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_DMAE); + if (mem_group_id == MEM_GROUP_TM_MEM) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_TM); + if (mem_group_id == MEM_GROUP_SDM_MEM) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_SDM); + if (mem_group_id == MEM_GROUP_TDIF_CTX || mem_group_id == + MEM_GROUP_RDIF_CTX) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_DIF); + if (mem_group_id == MEM_GROUP_CM_MEM) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_CM); + if (mem_group_id == MEM_GROUP_IOR) + return qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_IOR); + + return true; +} + +/* Stalls all Storms */ +static void qed_grc_stall_storms(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, bool stall) +{ + u8 reg_val = stall ? 1 : 0; + u8 storm_id; + + for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { + if (qed_grc_is_storm_included(p_hwfn, + (enum dbg_storms)storm_id)) { + u32 reg_addr = + s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_STALL_0; + + qed_wr(p_hwfn, p_ptt, reg_addr, reg_val); + } + } + + msleep(STALL_DELAY_MS); +} + +/* Takes all blocks out of reset */ +static void qed_grc_unreset_blocks(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 reg_val[MAX_DBG_RESET_REGS] = { 0 }; + u32 i; + + /* Fill reset regs values */ + for (i = 0; i < MAX_BLOCK_ID; i++) + if (s_block_defs[i]->has_reset_bit && s_block_defs[i]->unreset) + reg_val[s_block_defs[i]->reset_reg] |= + BIT(s_block_defs[i]->reset_bit_offset); + + /* Write reset registers */ + for (i = 0; i < MAX_DBG_RESET_REGS; i++) { + if (s_reset_regs_defs[i].exists[dev_data->chip_id]) { + reg_val[i] |= s_reset_regs_defs[i].unreset_val; + if (reg_val[i]) + qed_wr(p_hwfn, + p_ptt, + s_reset_regs_defs[i].addr + + RESET_REG_UNRESET_OFFSET, reg_val[i]); + } + } +} + +/* Returns the attention name offsets of the specified block */ +static const struct dbg_attn_block_type_data * +qed_get_block_attn_data(enum block_id block_id, enum dbg_attn_type attn_type) +{ + const struct dbg_attn_block *base_attn_block_arr = + (const struct dbg_attn_block *) + s_dbg_arrays[BIN_BUF_DBG_ATTN_BLOCKS].ptr; + + return &base_attn_block_arr[block_id].per_type_data[attn_type]; +} + +/* Returns the attention registers of the specified block */ +static const struct dbg_attn_reg * +qed_get_block_attn_regs(enum block_id block_id, enum dbg_attn_type attn_type, + u8 *num_attn_regs) +{ + const struct dbg_attn_block_type_data *block_type_data = + qed_get_block_attn_data(block_id, attn_type); + + *num_attn_regs = block_type_data->num_regs; + return &((const struct dbg_attn_reg *) + s_dbg_arrays[BIN_BUF_DBG_ATTN_REGS].ptr)[block_type_data-> + regs_offset]; +} + +/* For each block, clear the status of all parities */ +static void qed_grc_clear_all_prty(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u8 reg_idx, num_attn_regs; + u32 block_id; + + for (block_id = 0; block_id < MAX_BLOCK_ID; block_id++) { + const struct dbg_attn_reg *attn_reg_arr; + + if (dev_data->block_in_reset[block_id]) + continue; + + attn_reg_arr = qed_get_block_attn_regs((enum block_id)block_id, + ATTN_TYPE_PARITY, + &num_attn_regs); + for (reg_idx = 0; reg_idx < num_attn_regs; reg_idx++) { + const struct dbg_attn_reg *reg_data = + &attn_reg_arr[reg_idx]; + + /* Check mode */ + bool eval_mode = GET_FIELD(reg_data->mode.data, + DBG_MODE_HDR_EVAL_MODE) > 0; + u16 modes_buf_offset = + GET_FIELD(reg_data->mode.data, + DBG_MODE_HDR_MODES_BUF_OFFSET); + + if (!eval_mode || + qed_is_mode_match(p_hwfn, &modes_buf_offset)) + /* Mode match - read parity status read-clear + * register. + */ + qed_rd(p_hwfn, p_ptt, + DWORDS_TO_BYTES(reg_data-> + sts_clr_address)); + } + } +} + +/* Dumps GRC registers section header. Returns the dumped size in dwords. + * The following parameters are dumped: + * - 'count' = num_dumped_entries + * - 'split' = split_type + * - 'id'i = split_id (dumped only if split_id >= 0) + * - 'param_name' = param_val (user param, dumped only if param_name != NULL and + * param_val != NULL) + */ +static u32 qed_grc_dump_regs_hdr(u32 *dump_buf, + bool dump, + u32 num_reg_entries, + const char *split_type, + int split_id, + const char *param_name, const char *param_val) +{ + u8 num_params = 2 + (split_id >= 0 ? 1 : 0) + (param_name ? 1 : 0); + u32 offset = 0; + + offset += qed_dump_section_hdr(dump_buf + offset, + dump, "grc_regs", num_params); + offset += qed_dump_num_param(dump_buf + offset, + dump, "count", num_reg_entries); + offset += qed_dump_str_param(dump_buf + offset, + dump, "split", split_type); + if (split_id >= 0) + offset += qed_dump_num_param(dump_buf + offset, + dump, "id", split_id); + if (param_name && param_val) + offset += qed_dump_str_param(dump_buf + offset, + dump, param_name, param_val); + return offset; +} + +/* Dumps GRC register/memory. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_reg_entry(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, + bool dump, u32 addr, u32 len) +{ + u32 offset = 0, i; + + if (dump) { + *(dump_buf + offset++) = addr | (len << REG_DUMP_LEN_SHIFT); + for (i = 0; i < len; i++, addr++, offset++) + *(dump_buf + offset) = qed_rd(p_hwfn, + p_ptt, + DWORDS_TO_BYTES(addr)); + } else { + offset += len + 1; + } + + return offset; +} + +/* Dumps GRC registers entries. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_regs_entries(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct dbg_array input_regs_arr, + u32 *dump_buf, + bool dump, + bool block_enable[MAX_BLOCK_ID], + u32 *num_dumped_reg_entries) +{ + u32 i, offset = 0, input_offset = 0; + bool mode_match = true; + + *num_dumped_reg_entries = 0; + while (input_offset < input_regs_arr.size_in_dwords) { + const struct dbg_dump_cond_hdr *cond_hdr = + (const struct dbg_dump_cond_hdr *) + &input_regs_arr.ptr[input_offset++]; + bool eval_mode = GET_FIELD(cond_hdr->mode.data, + DBG_MODE_HDR_EVAL_MODE) > 0; + + /* Check mode/block */ + if (eval_mode) { + u16 modes_buf_offset = + GET_FIELD(cond_hdr->mode.data, + DBG_MODE_HDR_MODES_BUF_OFFSET); + mode_match = qed_is_mode_match(p_hwfn, + &modes_buf_offset); + } + + if (mode_match && block_enable[cond_hdr->block_id]) { + for (i = 0; i < cond_hdr->data_size; + i++, input_offset++) { + const struct dbg_dump_reg *reg = + (const struct dbg_dump_reg *) + &input_regs_arr.ptr[input_offset]; + + offset += + qed_grc_dump_reg_entry(p_hwfn, p_ptt, + dump_buf + offset, dump, + GET_FIELD(reg->data, + DBG_DUMP_REG_ADDRESS), + GET_FIELD(reg->data, + DBG_DUMP_REG_LENGTH)); + (*num_dumped_reg_entries)++; + } + } else { + input_offset += cond_hdr->data_size; + } + } + + return offset; +} + +/* Dumps GRC registers entries. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_split_data(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct dbg_array input_regs_arr, + u32 *dump_buf, + bool dump, + bool block_enable[MAX_BLOCK_ID], + const char *split_type_name, + u32 split_id, + const char *param_name, + const char *param_val) +{ + u32 num_dumped_reg_entries, offset; + + /* Calculate register dump header size (and skip it for now) */ + offset = qed_grc_dump_regs_hdr(dump_buf, + false, + 0, + split_type_name, + split_id, param_name, param_val); + + /* Dump registers */ + offset += qed_grc_dump_regs_entries(p_hwfn, + p_ptt, + input_regs_arr, + dump_buf + offset, + dump, + block_enable, + &num_dumped_reg_entries); + + /* Write register dump header */ + if (dump && num_dumped_reg_entries > 0) + qed_grc_dump_regs_hdr(dump_buf, + dump, + num_dumped_reg_entries, + split_type_name, + split_id, param_name, param_val); + + return num_dumped_reg_entries > 0 ? offset : 0; +} + +/* Dumps registers according to the input registers array. + * Returns the dumped size in dwords. + */ +static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + bool dump, + bool block_enable[MAX_BLOCK_ID], + const char *param_name, const char *param_val) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 offset = 0, input_offset = 0; + u8 port_id, pf_id; + + if (dump) + DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, "Dumping registers...\n"); + while (input_offset < + s_dbg_arrays[BIN_BUF_DBG_DUMP_REG].size_in_dwords) { + const struct dbg_dump_split_hdr *split_hdr = + (const struct dbg_dump_split_hdr *) + &s_dbg_arrays[BIN_BUF_DBG_DUMP_REG].ptr[input_offset++]; + u8 split_type_id = GET_FIELD(split_hdr->hdr, + DBG_DUMP_SPLIT_HDR_SPLIT_TYPE_ID); + u32 split_data_size = GET_FIELD(split_hdr->hdr, + DBG_DUMP_SPLIT_HDR_DATA_SIZE); + struct dbg_array curr_input_regs_arr = { + &s_dbg_arrays[BIN_BUF_DBG_DUMP_REG].ptr[input_offset], + split_data_size}; + + switch (split_type_id) { + case SPLIT_TYPE_NONE: + case SPLIT_TYPE_VF: + offset += qed_grc_dump_split_data(p_hwfn, + p_ptt, + curr_input_regs_arr, + dump_buf + offset, + dump, + block_enable, + "eng", + (u32)(-1), + param_name, + param_val); + break; + case SPLIT_TYPE_PORT: + for (port_id = 0; + port_id < + s_chip_defs[dev_data->chip_id]. + per_platform[dev_data->platform_id].num_ports; + port_id++) { + if (dump) + qed_port_pretend(p_hwfn, p_ptt, + port_id); + offset += + qed_grc_dump_split_data(p_hwfn, p_ptt, + curr_input_regs_arr, + dump_buf + offset, + dump, block_enable, + "port", port_id, + param_name, + param_val); + } + break; + case SPLIT_TYPE_PF: + case SPLIT_TYPE_PORT_PF: + for (pf_id = 0; + pf_id < + s_chip_defs[dev_data->chip_id]. + per_platform[dev_data->platform_id].num_pfs; + pf_id++) { + if (dump) + qed_fid_pretend(p_hwfn, p_ptt, pf_id); + offset += qed_grc_dump_split_data(p_hwfn, + p_ptt, + curr_input_regs_arr, + dump_buf + offset, + dump, block_enable, + "pf", pf_id, param_name, + param_val); + } + break; + default: + break; + } + + input_offset += split_data_size; + } + + /* Pretend to original PF */ + if (dump) + qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id); + return offset; +} + +/* Dump reset registers. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_reset_regs(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 i, offset = 0, num_regs = 0; + + /* Calculate header size */ + offset += qed_grc_dump_regs_hdr(dump_buf, + false, 0, "eng", -1, NULL, NULL); + + /* Write reset registers */ + for (i = 0; i < MAX_DBG_RESET_REGS; i++) { + if (s_reset_regs_defs[i].exists[dev_data->chip_id]) { + offset += qed_grc_dump_reg_entry(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + BYTES_TO_DWORDS + (s_reset_regs_defs + [i].addr), 1); + num_regs++; + } + } + + /* Write header */ + if (dump) + qed_grc_dump_regs_hdr(dump_buf, + true, num_regs, "eng", -1, NULL, NULL); + return offset; +} + +/* Dump registers that are modified during GRC Dump and therefore must be dumped + * first. Returns the dumped size in dwords. + */ +static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 offset = 0, num_reg_entries = 0, block_id; + u8 storm_id, reg_idx, num_attn_regs; + + /* Calculate header size */ + offset += qed_grc_dump_regs_hdr(dump_buf, + false, 0, "eng", -1, NULL, NULL); + + /* Write parity registers */ + for (block_id = 0; block_id < MAX_BLOCK_ID; block_id++) { + const struct dbg_attn_reg *attn_reg_arr; + + if (dev_data->block_in_reset[block_id] && dump) + continue; + + attn_reg_arr = qed_get_block_attn_regs((enum block_id)block_id, + ATTN_TYPE_PARITY, + &num_attn_regs); + for (reg_idx = 0; reg_idx < num_attn_regs; reg_idx++) { + const struct dbg_attn_reg *reg_data = + &attn_reg_arr[reg_idx]; + u16 modes_buf_offset; + bool eval_mode; + + /* Check mode */ + eval_mode = GET_FIELD(reg_data->mode.data, + DBG_MODE_HDR_EVAL_MODE) > 0; + modes_buf_offset = + GET_FIELD(reg_data->mode.data, + DBG_MODE_HDR_MODES_BUF_OFFSET); + if (!eval_mode || + qed_is_mode_match(p_hwfn, &modes_buf_offset)) { + /* Mode match - read and dump registers */ + offset += qed_grc_dump_reg_entry(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + reg_data->mask_address, + 1); + offset += qed_grc_dump_reg_entry(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + GET_FIELD(reg_data->data, + DBG_ATTN_REG_STS_ADDRESS), + 1); + num_reg_entries += 2; + } + } + } + + /* Write storm stall status registers */ + for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { + if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id] && + dump) + continue; + + offset += qed_grc_dump_reg_entry(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + BYTES_TO_DWORDS(s_storm_defs[storm_id]. + sem_fast_mem_addr + + SEM_FAST_REG_STALLED), + 1); + num_reg_entries++; + } + + /* Write header */ + if (dump) + qed_grc_dump_regs_hdr(dump_buf, + true, + num_reg_entries, "eng", -1, NULL, NULL); + return offset; +} + +/* Dumps a GRC memory header (section and params). + * The following parameters are dumped: + * name - name is dumped only if it's not NULL. + * addr - byte_addr is dumped only if name is NULL. + * len - dword_len is always dumped. + * width - bit_width is dumped if it's not zero. + * packed - packed=1 is dumped if it's not false. + * mem_group - mem_group is always dumped. + * is_storm - true only if the memory is related to a Storm. + * storm_letter - storm letter (valid only if is_storm is true). + * Returns the dumped size in dwords. + */ +static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + bool dump, + const char *name, + u32 byte_addr, + u32 dword_len, + u32 bit_width, + bool packed, + const char *mem_group, + bool is_storm, char storm_letter) +{ + u8 num_params = 3; + u32 offset = 0; + char buf[64]; + + if (!dword_len) + DP_NOTICE(p_hwfn, + "Unexpected GRC Dump error: dumped memory size must be non-zero\n"); + if (bit_width) + num_params++; + if (packed) + num_params++; + + /* Dump section header */ + offset += qed_dump_section_hdr(dump_buf + offset, + dump, "grc_mem", num_params); + if (name) { + /* Dump name */ + if (is_storm) { + strcpy(buf, "?STORM_"); + buf[0] = storm_letter; + strcpy(buf + strlen(buf), name); + } else { + strcpy(buf, name); + } + + offset += qed_dump_str_param(dump_buf + offset, + dump, "name", buf); + if (dump) + DP_VERBOSE(p_hwfn, + QED_MSG_DEBUG, + "Dumping %d registers from %s...\n", + dword_len, buf); + } else { + /* Dump address */ + offset += qed_dump_num_param(dump_buf + offset, + dump, "addr", byte_addr); + if (dump && dword_len > 64) + DP_VERBOSE(p_hwfn, + QED_MSG_DEBUG, + "Dumping %d registers from address 0x%x...\n", + dword_len, byte_addr); + } + + /* Dump len */ + offset += qed_dump_num_param(dump_buf + offset, dump, "len", dword_len); + + /* Dump bit width */ + if (bit_width) + offset += qed_dump_num_param(dump_buf + offset, + dump, "width", bit_width); + + /* Dump packed */ + if (packed) + offset += qed_dump_num_param(dump_buf + offset, + dump, "packed", 1); + + /* Dump reg type */ + if (is_storm) { + strcpy(buf, "?STORM_"); + buf[0] = storm_letter; + strcpy(buf + strlen(buf), mem_group); + } else { + strcpy(buf, mem_group); + } + + offset += qed_dump_str_param(dump_buf + offset, dump, "type", buf); + return offset; +} + +/* Dumps a single GRC memory. If name is NULL, the memory is stored by address. + * Returns the dumped size in dwords. + */ +static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + bool dump, + const char *name, + u32 byte_addr, + u32 dword_len, + u32 bit_width, + bool packed, + const char *mem_group, + bool is_storm, char storm_letter) +{ + u32 offset = 0; + + offset += qed_grc_dump_mem_hdr(p_hwfn, + dump_buf + offset, + dump, + name, + byte_addr, + dword_len, + bit_width, + packed, + mem_group, is_storm, storm_letter); + if (dump) { + u32 i; + + for (i = 0; i < dword_len; + i++, byte_addr += BYTES_IN_DWORD, offset++) + *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr); + } else { + offset += dword_len; + } + + return offset; +} + +/* Dumps GRC memories entries. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct dbg_array input_mems_arr, + u32 *dump_buf, bool dump) +{ + u32 i, offset = 0, input_offset = 0; + bool mode_match = true; + + while (input_offset < input_mems_arr.size_in_dwords) { + const struct dbg_dump_cond_hdr *cond_hdr; + u32 num_entries; + bool eval_mode; + + cond_hdr = (const struct dbg_dump_cond_hdr *) + &input_mems_arr.ptr[input_offset++]; + eval_mode = GET_FIELD(cond_hdr->mode.data, + DBG_MODE_HDR_EVAL_MODE) > 0; + + /* Check required mode */ + if (eval_mode) { + u16 modes_buf_offset = + GET_FIELD(cond_hdr->mode.data, + DBG_MODE_HDR_MODES_BUF_OFFSET); + + mode_match = qed_is_mode_match(p_hwfn, + &modes_buf_offset); + } + + if (!mode_match) { + input_offset += cond_hdr->data_size; + continue; + } + + num_entries = cond_hdr->data_size / MEM_DUMP_ENTRY_SIZE_DWORDS; + for (i = 0; i < num_entries; + i++, input_offset += MEM_DUMP_ENTRY_SIZE_DWORDS) { + const struct dbg_dump_mem *mem = + (const struct dbg_dump_mem *) + &input_mems_arr.ptr[input_offset]; + u8 mem_group_id; + + mem_group_id = GET_FIELD(mem->dword0, + DBG_DUMP_MEM_MEM_GROUP_ID); + if (mem_group_id >= MEM_GROUPS_NUM) { + DP_NOTICE(p_hwfn, "Invalid mem_group_id\n"); + return 0; + } + + if (qed_grc_is_mem_included(p_hwfn, + (enum block_id)cond_hdr->block_id, + mem_group_id)) { + u32 mem_byte_addr = + DWORDS_TO_BYTES(GET_FIELD(mem->dword0, + DBG_DUMP_MEM_ADDRESS)); + u32 mem_len = GET_FIELD(mem->dword1, + DBG_DUMP_MEM_LENGTH); + char storm_letter = 'a'; + bool is_storm = false; + + /* Update memory length for CCFC/TCFC memories + * according to number of LCIDs/LTIDs. + */ + if (mem_group_id == MEM_GROUP_CONN_CFC_MEM) + mem_len = qed_grc_get_param(p_hwfn, + DBG_GRC_PARAM_NUM_LCIDS) + * (mem_len / MAX_LCIDS); + else if (mem_group_id == MEM_GROUP_TASK_CFC_MEM) + mem_len = qed_grc_get_param(p_hwfn, + DBG_GRC_PARAM_NUM_LTIDS) + * (mem_len / MAX_LTIDS); + + /* If memory is associated with Storm, update + * Storm details. + */ + if (s_block_defs[cond_hdr->block_id]-> + associated_to_storm) { + is_storm = true; + storm_letter = + s_storm_defs[s_block_defs[ + cond_hdr->block_id]-> + storm_id].letter; + } + + /* Dump memory */ + offset += qed_grc_dump_mem(p_hwfn, p_ptt, + dump_buf + offset, dump, NULL, + mem_byte_addr, mem_len, 0, + false, + s_mem_group_names[mem_group_id], + is_storm, storm_letter); + } + } + } + + return offset; +} + +/* Dumps GRC memories according to the input array dump_mem. + * Returns the dumped size in dwords. + */ +static u32 qed_grc_dump_memories(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump) +{ + u32 offset = 0, input_offset = 0; + + while (input_offset < + s_dbg_arrays[BIN_BUF_DBG_DUMP_MEM].size_in_dwords) { + const struct dbg_dump_split_hdr *split_hdr = + (const struct dbg_dump_split_hdr *) + &s_dbg_arrays[BIN_BUF_DBG_DUMP_MEM].ptr[input_offset++]; + u8 split_type_id = GET_FIELD(split_hdr->hdr, + DBG_DUMP_SPLIT_HDR_SPLIT_TYPE_ID); + u32 split_data_size = GET_FIELD(split_hdr->hdr, + DBG_DUMP_SPLIT_HDR_DATA_SIZE); + struct dbg_array curr_input_mems_arr = { + &s_dbg_arrays[BIN_BUF_DBG_DUMP_MEM].ptr[input_offset], + split_data_size}; + + switch (split_type_id) { + case SPLIT_TYPE_NONE: + offset += qed_grc_dump_mem_entries(p_hwfn, + p_ptt, + curr_input_mems_arr, + dump_buf + offset, + dump); + break; + default: + DP_NOTICE(p_hwfn, + "Dumping split memories is currently not supported\n"); + break; + } + + input_offset += split_data_size; + } + + return offset; +} + +/* Dumps GRC context data for the specified Storm. + * Returns the dumped size in dwords. + */ +static u32 qed_grc_dump_ctx_data(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + bool dump, + const char *name, + u32 num_lids, + u32 lid_size, + u32 rd_reg_addr, + u8 storm_id) +{ + u32 i, lid, total_size; + u32 offset = 0; + + if (!lid_size) + return 0; + lid_size *= BYTES_IN_DWORD; + total_size = num_lids * lid_size; + offset += qed_grc_dump_mem_hdr(p_hwfn, + dump_buf + offset, + dump, + name, + 0, + total_size, + lid_size * 32, + false, + name, + true, s_storm_defs[storm_id].letter); + + /* Dump context data */ + if (dump) { + for (lid = 0; lid < num_lids; lid++) { + for (i = 0; i < lid_size; i++, offset++) { + qed_wr(p_hwfn, + p_ptt, + s_storm_defs[storm_id].cm_ctx_wr_addr, + BIT(9) | lid); + *(dump_buf + offset) = qed_rd(p_hwfn, + p_ptt, + rd_reg_addr); + } + } + } else { + offset += total_size; + } + + return offset; +} + +/* Dumps GRC contexts. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_ctx(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) +{ + u32 offset = 0; + u8 storm_id; + + for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { + if (!qed_grc_is_storm_included(p_hwfn, + (enum dbg_storms)storm_id)) + continue; + + /* Dump Conn AG context size */ + offset += + qed_grc_dump_ctx_data(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + "CONN_AG_CTX", + qed_grc_get_param(p_hwfn, + DBG_GRC_PARAM_NUM_LCIDS), + s_storm_defs[storm_id]. + cm_conn_ag_ctx_lid_size, + s_storm_defs[storm_id]. + cm_conn_ag_ctx_rd_addr, + storm_id); + + /* Dump Conn ST context size */ + offset += + qed_grc_dump_ctx_data(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + "CONN_ST_CTX", + qed_grc_get_param(p_hwfn, + DBG_GRC_PARAM_NUM_LCIDS), + s_storm_defs[storm_id]. + cm_conn_st_ctx_lid_size, + s_storm_defs[storm_id]. + cm_conn_st_ctx_rd_addr, + storm_id); + + /* Dump Task AG context size */ + offset += + qed_grc_dump_ctx_data(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + "TASK_AG_CTX", + qed_grc_get_param(p_hwfn, + DBG_GRC_PARAM_NUM_LTIDS), + s_storm_defs[storm_id]. + cm_task_ag_ctx_lid_size, + s_storm_defs[storm_id]. + cm_task_ag_ctx_rd_addr, + storm_id); + + /* Dump Task ST context size */ + offset += + qed_grc_dump_ctx_data(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + "TASK_ST_CTX", + qed_grc_get_param(p_hwfn, + DBG_GRC_PARAM_NUM_LTIDS), + s_storm_defs[storm_id]. + cm_task_st_ctx_lid_size, + s_storm_defs[storm_id]. + cm_task_st_ctx_rd_addr, + storm_id); + } + + return offset; +} + +/* Dumps GRC IORs data. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_iors(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) +{ + char buf[10] = "IOR_SET_?"; + u8 storm_id, set_id; + u32 offset = 0; + + for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { + if (qed_grc_is_storm_included(p_hwfn, + (enum dbg_storms)storm_id)) { + for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) { + u32 addr = + s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_STORM_REG_FILE + + DWORDS_TO_BYTES(IOR_SET_OFFSET(set_id)); + + buf[strlen(buf) - 1] = '0' + set_id; + offset += qed_grc_dump_mem(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + buf, + addr, + IORS_PER_SET, + 32, + false, + "ior", + true, + s_storm_defs + [storm_id].letter); + } + } + } + + return offset; +} + +/* Dump VFC CAM. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_vfc_cam(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump, u8 storm_id) +{ + u32 total_size = VFC_CAM_NUM_ROWS * VFC_CAM_RESP_DWORDS; + u32 cam_addr[VFC_CAM_ADDR_DWORDS] = { 0 }; + u32 cam_cmd[VFC_CAM_CMD_DWORDS] = { 0 }; + u32 offset = 0; + u32 row, i; + + offset += qed_grc_dump_mem_hdr(p_hwfn, + dump_buf + offset, + dump, + "vfc_cam", + 0, + total_size, + 256, + false, + "vfc_cam", + true, s_storm_defs[storm_id].letter); + if (dump) { + /* Prepare CAM address */ + SET_VAR_FIELD(cam_addr, VFC_CAM_ADDR, OP, VFC_OPCODE_CAM_RD); + for (row = 0; row < VFC_CAM_NUM_ROWS; + row++, offset += VFC_CAM_RESP_DWORDS) { + /* Write VFC CAM command */ + SET_VAR_FIELD(cam_cmd, VFC_CAM_CMD, ROW, row); + ARR_REG_WR(p_hwfn, + p_ptt, + s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_VFC_DATA_WR, + cam_cmd, VFC_CAM_CMD_DWORDS); + + /* Write VFC CAM address */ + ARR_REG_WR(p_hwfn, + p_ptt, + s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_VFC_ADDR, + cam_addr, VFC_CAM_ADDR_DWORDS); + + /* Read VFC CAM read response */ + ARR_REG_RD(p_hwfn, + p_ptt, + s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_VFC_DATA_RD, + dump_buf + offset, VFC_CAM_RESP_DWORDS); + } + } else { + offset += total_size; + } + + return offset; +} + +/* Dump VFC RAM. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_vfc_ram(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + bool dump, + u8 storm_id, struct vfc_ram_defs *ram_defs) +{ + u32 total_size = ram_defs->num_rows * VFC_RAM_RESP_DWORDS; + u32 ram_addr[VFC_RAM_ADDR_DWORDS] = { 0 }; + u32 ram_cmd[VFC_RAM_CMD_DWORDS] = { 0 }; + u32 offset = 0; + u32 row, i; + + offset += qed_grc_dump_mem_hdr(p_hwfn, + dump_buf + offset, + dump, + ram_defs->mem_name, + 0, + total_size, + 256, + false, + ram_defs->type_name, + true, s_storm_defs[storm_id].letter); + + /* Prepare RAM address */ + SET_VAR_FIELD(ram_addr, VFC_RAM_ADDR, OP, VFC_OPCODE_RAM_RD); + + if (!dump) + return offset + total_size; + + for (row = ram_defs->base_row; + row < ram_defs->base_row + ram_defs->num_rows; + row++, offset += VFC_RAM_RESP_DWORDS) { + /* Write VFC RAM command */ + ARR_REG_WR(p_hwfn, + p_ptt, + s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_VFC_DATA_WR, + ram_cmd, VFC_RAM_CMD_DWORDS); + + /* Write VFC RAM address */ + SET_VAR_FIELD(ram_addr, VFC_RAM_ADDR, ROW, row); + ARR_REG_WR(p_hwfn, + p_ptt, + s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_VFC_ADDR, + ram_addr, VFC_RAM_ADDR_DWORDS); + + /* Read VFC RAM read response */ + ARR_REG_RD(p_hwfn, + p_ptt, + s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_VFC_DATA_RD, + dump_buf + offset, VFC_RAM_RESP_DWORDS); + } + + return offset; +} + +/* Dumps GRC VFC data. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_vfc(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u8 storm_id, i; + u32 offset = 0; + + for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { + if (qed_grc_is_storm_included(p_hwfn, + (enum dbg_storms)storm_id) && + s_storm_defs[storm_id].has_vfc && + (storm_id != DBG_PSTORM_ID || + dev_data->platform_id == PLATFORM_ASIC)) { + /* Read CAM */ + offset += qed_grc_dump_vfc_cam(p_hwfn, + p_ptt, + dump_buf + offset, + dump, storm_id); + + /* Read RAM */ + for (i = 0; i < NUM_VFC_RAM_TYPES; i++) + offset += qed_grc_dump_vfc_ram(p_hwfn, + p_ptt, + dump_buf + + offset, + dump, + storm_id, + &s_vfc_ram_defs + [i]); + } + } + + return offset; +} + +/* Dumps GRC RSS data. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_rss(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 offset = 0; + u8 rss_mem_id; + + for (rss_mem_id = 0; rss_mem_id < NUM_RSS_MEM_TYPES; rss_mem_id++) { + struct rss_mem_defs *rss_defs = &s_rss_mem_defs[rss_mem_id]; + u32 num_entries = rss_defs->num_entries[dev_data->chip_id]; + u32 entry_width = rss_defs->entry_width[dev_data->chip_id]; + u32 total_size = (num_entries * entry_width) / 32; + bool packed = (entry_width == 16); + u32 addr = rss_defs->addr; + u32 i, j; + + offset += qed_grc_dump_mem_hdr(p_hwfn, + dump_buf + offset, + dump, + rss_defs->mem_name, + addr, + total_size, + entry_width, + packed, + rss_defs->type_name, false, 0); + + if (!dump) { + offset += total_size; + continue; + } + + /* Dump RSS data */ + for (i = 0; i < BYTES_TO_DWORDS(total_size); i++, addr++) { + qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, addr); + for (j = 0; j < BYTES_IN_DWORD; j++, offset++) + *(dump_buf + offset) = + qed_rd(p_hwfn, p_ptt, + RSS_REG_RSS_RAM_DATA + + DWORDS_TO_BYTES(j)); + } + } + + return offset; +} + +/* Dumps GRC Big RAM. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump, u8 big_ram_id) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + char mem_name[12] = "???_BIG_RAM"; + char type_name[8] = "???_RAM"; + u32 ram_size, total_blocks; + u32 offset = 0, i, j; + + total_blocks = + s_big_ram_defs[big_ram_id].num_of_blocks[dev_data->chip_id]; + ram_size = total_blocks * BIG_RAM_BLOCK_SIZE_DWORDS; + + strncpy(type_name, s_big_ram_defs[big_ram_id].instance_name, + strlen(s_big_ram_defs[big_ram_id].instance_name)); + strncpy(mem_name, s_big_ram_defs[big_ram_id].instance_name, + strlen(s_big_ram_defs[big_ram_id].instance_name)); + + /* Dump memory header */ + offset += qed_grc_dump_mem_hdr(p_hwfn, + dump_buf + offset, + dump, + mem_name, + 0, + ram_size, + BIG_RAM_BLOCK_SIZE_BYTES * 8, + false, type_name, false, 0); + + if (!dump) + return offset + ram_size; + + /* Read and dump Big RAM data */ + for (i = 0; i < total_blocks / 2; i++) { + qed_wr(p_hwfn, p_ptt, s_big_ram_defs[big_ram_id].addr_reg_addr, + i); + for (j = 0; j < 2 * BIG_RAM_BLOCK_SIZE_DWORDS; j++, offset++) + *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, + s_big_ram_defs[big_ram_id]. + data_reg_addr + + DWORDS_TO_BYTES(j)); + } + + return offset; +} + +static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) +{ + bool block_enable[MAX_BLOCK_ID] = { 0 }; + bool halted = false; + u32 offset = 0; + + /* Halt MCP */ + if (dump) { + halted = !qed_mcp_halt(p_hwfn, p_ptt); + if (!halted) + DP_NOTICE(p_hwfn, "MCP halt failed!\n"); + } + + /* Dump MCP scratchpad */ + offset += qed_grc_dump_mem(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + NULL, + MCP_REG_SCRATCH, + MCP_REG_SCRATCH_SIZE, + 0, false, "MCP", false, 0); + + /* Dump MCP cpu_reg_file */ + offset += qed_grc_dump_mem(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + NULL, + MCP_REG_CPU_REG_FILE, + MCP_REG_CPU_REG_FILE_SIZE, + 0, false, "MCP", false, 0); + + /* Dump MCP registers */ + block_enable[BLOCK_MCP] = true; + offset += qed_grc_dump_registers(p_hwfn, + p_ptt, + dump_buf + offset, + dump, block_enable, "block", "MCP"); + + /* Dump required non-MCP registers */ + offset += qed_grc_dump_regs_hdr(dump_buf + offset, + dump, 1, "eng", -1, "block", "MCP"); + offset += qed_grc_dump_reg_entry(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + BYTES_TO_DWORDS + (MISC_REG_SHARED_MEM_ADDR), 1); + + /* Release MCP */ + if (halted && qed_mcp_resume(p_hwfn, p_ptt)) + DP_NOTICE(p_hwfn, "Failed to resume MCP after halt!\n"); + return offset; +} + +/* Dumps the tbus indirect memory for all PHYs. */ +static u32 qed_grc_dump_phy(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) +{ + u32 offset = 0, tbus_lo_offset, tbus_hi_offset; + char mem_name[32]; + u8 phy_id; + + for (phy_id = 0; phy_id < ARRAY_SIZE(s_phy_defs); phy_id++) { + struct phy_defs *phy_defs = &s_phy_defs[phy_id]; + int printed_chars; + + printed_chars = snprintf(mem_name, sizeof(mem_name), "tbus_%s", + phy_defs->phy_name); + if (printed_chars < 0 || printed_chars >= sizeof(mem_name)) + DP_NOTICE(p_hwfn, + "Unexpected debug error: invalid PHY memory name\n"); + offset += qed_grc_dump_mem_hdr(p_hwfn, + dump_buf + offset, + dump, + mem_name, + 0, + PHY_DUMP_SIZE_DWORDS, + 16, true, mem_name, false, 0); + if (dump) { + u32 addr_lo_addr = phy_defs->base_addr + + phy_defs->tbus_addr_lo_addr; + u32 addr_hi_addr = phy_defs->base_addr + + phy_defs->tbus_addr_hi_addr; + u32 data_lo_addr = phy_defs->base_addr + + phy_defs->tbus_data_lo_addr; + u32 data_hi_addr = phy_defs->base_addr + + phy_defs->tbus_data_hi_addr; + u8 *bytes_buf = (u8 *)(dump_buf + offset); + + for (tbus_hi_offset = 0; + tbus_hi_offset < (NUM_PHY_TBUS_ADDRESSES >> 8); + tbus_hi_offset++) { + qed_wr(p_hwfn, + p_ptt, addr_hi_addr, tbus_hi_offset); + for (tbus_lo_offset = 0; tbus_lo_offset < 256; + tbus_lo_offset++) { + qed_wr(p_hwfn, + p_ptt, + addr_lo_addr, tbus_lo_offset); + *(bytes_buf++) = + (u8)qed_rd(p_hwfn, p_ptt, + data_lo_addr); + *(bytes_buf++) = + (u8)qed_rd(p_hwfn, p_ptt, + data_hi_addr); + } + } + } + + offset += PHY_DUMP_SIZE_DWORDS; + } + + return offset; +} + +static void qed_config_dbg_line(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + enum block_id block_id, + u8 line_id, + u8 cycle_en, + u8 right_shift, u8 force_valid, u8 force_frame) +{ + struct block_defs *p_block_defs = s_block_defs[block_id]; + + qed_wr(p_hwfn, p_ptt, p_block_defs->dbg_select_addr, line_id); + qed_wr(p_hwfn, p_ptt, p_block_defs->dbg_cycle_enable_addr, cycle_en); + qed_wr(p_hwfn, p_ptt, p_block_defs->dbg_shift_addr, right_shift); + qed_wr(p_hwfn, p_ptt, p_block_defs->dbg_force_valid_addr, force_valid); + qed_wr(p_hwfn, p_ptt, p_block_defs->dbg_force_frame_addr, force_frame); +} + +/* Dumps Static Debug data. Returns the dumped size in dwords. */ +static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump) +{ + u32 block_dwords = NUM_DBG_BUS_LINES * STATIC_DEBUG_LINE_DWORDS; + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 offset = 0, block_id, line_id, addr, i; + struct block_defs *p_block_defs; + + if (dump) { + DP_VERBOSE(p_hwfn, + QED_MSG_DEBUG, "Dumping static debug data...\n"); + + /* Disable all blocks debug output */ + for (block_id = 0; block_id < MAX_BLOCK_ID; block_id++) { + p_block_defs = s_block_defs[block_id]; + + if (p_block_defs->has_dbg_bus[dev_data->chip_id]) + qed_wr(p_hwfn, p_ptt, + p_block_defs->dbg_cycle_enable_addr, 0); + } + + qed_bus_reset_dbg_block(p_hwfn, p_ptt); + qed_bus_set_framing_mode(p_hwfn, + p_ptt, DBG_BUS_FRAME_MODE_8HW_0ST); + qed_wr(p_hwfn, + p_ptt, DBG_REG_DEBUG_TARGET, DBG_BUS_TARGET_ID_INT_BUF); + qed_wr(p_hwfn, p_ptt, DBG_REG_FULL_MODE, 1); + qed_bus_enable_dbg_block(p_hwfn, p_ptt, true); + } + + /* Dump all static debug lines for each relevant block */ + for (block_id = 0; block_id < MAX_BLOCK_ID; block_id++) { + p_block_defs = s_block_defs[block_id]; + + if (!p_block_defs->has_dbg_bus[dev_data->chip_id]) + continue; + + /* Dump static section params */ + offset += qed_grc_dump_mem_hdr(p_hwfn, + dump_buf + offset, + dump, + p_block_defs->name, 0, + block_dwords, 32, false, + "STATIC", false, 0); + + if (dump && !dev_data->block_in_reset[block_id]) { + u8 dbg_client_id = + p_block_defs->dbg_client_id[dev_data->chip_id]; + + /* Enable block's client */ + qed_bus_enable_clients(p_hwfn, p_ptt, + BIT(dbg_client_id)); + + for (line_id = 0; line_id < NUM_DBG_BUS_LINES; + line_id++) { + /* Configure debug line ID */ + qed_config_dbg_line(p_hwfn, + p_ptt, + (enum block_id)block_id, + (u8)line_id, + 0xf, 0, 0, 0); + + /* Read debug line info */ + for (i = 0, addr = DBG_REG_CALENDAR_OUT_DATA; + i < STATIC_DEBUG_LINE_DWORDS; + i++, offset++, addr += BYTES_IN_DWORD) + dump_buf[offset] = qed_rd(p_hwfn, p_ptt, + addr); + } + + /* Disable block's client and debug output */ + qed_bus_enable_clients(p_hwfn, p_ptt, 0); + qed_wr(p_hwfn, p_ptt, + p_block_defs->dbg_cycle_enable_addr, 0); + } else { + /* All lines are invalid - dump zeros */ + if (dump) + memset(dump_buf + offset, 0, + DWORDS_TO_BYTES(block_dwords)); + offset += block_dwords; + } + } + + if (dump) { + qed_bus_enable_dbg_block(p_hwfn, p_ptt, false); + qed_bus_enable_clients(p_hwfn, p_ptt, 0); + } + + return offset; +} + +/* Performs GRC Dump to the specified buffer. + * Returns the dumped size in dwords. + */ +static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + bool dump, u32 *num_dumped_dwords) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + bool parities_masked = false; + u8 i, port_mode = 0; + u32 offset = 0; + + /* Check if emulation platform */ + *num_dumped_dwords = 0; + + /* Fill GRC parameters that were not set by the user with their default + * value. + */ + qed_dbg_grc_set_params_default(p_hwfn); + + /* Find port mode */ + if (dump) { + switch (qed_rd(p_hwfn, p_ptt, MISC_REG_PORT_MODE)) { + case 0: + port_mode = 1; + break; + case 1: + port_mode = 2; + break; + case 2: + port_mode = 4; + break; + } + } + + /* Update reset state */ + if (dump) + qed_update_blocks_reset_state(p_hwfn, p_ptt); + + /* Dump global params */ + offset += qed_dump_common_global_params(p_hwfn, + p_ptt, + dump_buf + offset, dump, 4); + offset += qed_dump_str_param(dump_buf + offset, + dump, "dump-type", "grc-dump"); + offset += qed_dump_num_param(dump_buf + offset, + dump, + "num-lcids", + qed_grc_get_param(p_hwfn, + DBG_GRC_PARAM_NUM_LCIDS)); + offset += qed_dump_num_param(dump_buf + offset, + dump, + "num-ltids", + qed_grc_get_param(p_hwfn, + DBG_GRC_PARAM_NUM_LTIDS)); + offset += qed_dump_num_param(dump_buf + offset, + dump, "num-ports", port_mode); + + /* Dump reset registers (dumped before taking blocks out of reset ) */ + if (qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_REGS)) + offset += qed_grc_dump_reset_regs(p_hwfn, + p_ptt, + dump_buf + offset, dump); + + /* Take all blocks out of reset (using reset registers) */ + if (dump) { + qed_grc_unreset_blocks(p_hwfn, p_ptt); + qed_update_blocks_reset_state(p_hwfn, p_ptt); + } + + /* Disable all parities using MFW command */ + if (dump) { + parities_masked = !qed_mcp_mask_parities(p_hwfn, p_ptt, 1); + if (!parities_masked) { + if (qed_grc_get_param + (p_hwfn, DBG_GRC_PARAM_PARITY_SAFE)) + return DBG_STATUS_MCP_COULD_NOT_MASK_PRTY; + else + DP_NOTICE(p_hwfn, + "Failed to mask parities using MFW\n"); + } + } + + /* Dump modified registers (dumped before modifying them) */ + if (qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_REGS)) + offset += qed_grc_dump_modified_regs(p_hwfn, + p_ptt, + dump_buf + offset, dump); + + /* Stall storms */ + if (dump && + (qed_grc_is_included(p_hwfn, + DBG_GRC_PARAM_DUMP_IOR) || + qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_VFC))) + qed_grc_stall_storms(p_hwfn, p_ptt, true); + + /* Dump all regs */ + if (qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_REGS)) { + /* Dump all blocks except MCP */ + bool block_enable[MAX_BLOCK_ID]; + + for (i = 0; i < MAX_BLOCK_ID; i++) + block_enable[i] = true; + block_enable[BLOCK_MCP] = false; + offset += qed_grc_dump_registers(p_hwfn, + p_ptt, + dump_buf + + offset, + dump, + block_enable, NULL, NULL); + } + + /* Dump memories */ + offset += qed_grc_dump_memories(p_hwfn, p_ptt, dump_buf + offset, dump); + + /* Dump MCP */ + if (qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_MCP)) + offset += qed_grc_dump_mcp(p_hwfn, + p_ptt, dump_buf + offset, dump); + + /* Dump context */ + if (qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_CM_CTX)) + offset += qed_grc_dump_ctx(p_hwfn, + p_ptt, dump_buf + offset, dump); + + /* Dump RSS memories */ + if (qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_RSS)) + offset += qed_grc_dump_rss(p_hwfn, + p_ptt, dump_buf + offset, dump); + + /* Dump Big RAM */ + for (i = 0; i < NUM_BIG_RAM_TYPES; i++) + if (qed_grc_is_included(p_hwfn, s_big_ram_defs[i].grc_param)) + offset += qed_grc_dump_big_ram(p_hwfn, + p_ptt, + dump_buf + offset, + dump, i); + + /* Dump IORs */ + if (qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_IOR)) + offset += qed_grc_dump_iors(p_hwfn, + p_ptt, dump_buf + offset, dump); + + /* Dump VFC */ + if (qed_grc_is_included(p_hwfn, DBG_GRC_PARAM_DUMP_VFC)) + offset += qed_grc_dump_vfc(p_hwfn, + p_ptt, dump_buf + offset, dump); + + /* Dump PHY tbus */ + if (qed_grc_is_included(p_hwfn, + DBG_GRC_PARAM_DUMP_PHY) && dev_data->chip_id == + CHIP_K2 && dev_data->platform_id == PLATFORM_ASIC) + offset += qed_grc_dump_phy(p_hwfn, + p_ptt, dump_buf + offset, dump); + + /* Dump static debug data */ + if (qed_grc_is_included(p_hwfn, + DBG_GRC_PARAM_DUMP_STATIC) && + dev_data->bus.state == DBG_BUS_STATE_IDLE) + offset += qed_grc_dump_static_debug(p_hwfn, + p_ptt, + dump_buf + offset, dump); + + /* Dump last section */ + offset += qed_dump_last_section(dump_buf, offset, dump); + if (dump) { + /* Unstall storms */ + if (qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_UNSTALL)) + qed_grc_stall_storms(p_hwfn, p_ptt, false); + + /* Clear parity status */ + qed_grc_clear_all_prty(p_hwfn, p_ptt); + + /* Enable all parities using MFW command */ + if (parities_masked) + qed_mcp_mask_parities(p_hwfn, p_ptt, 0); + } + + *num_dumped_dwords = offset; + + return DBG_STATUS_OK; +} + +/* Writes the specified failing Idle Check rule to the specified buffer. + * Returns the dumped size in dwords. + */ +static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 * + dump_buf, + bool dump, + u16 rule_id, + const struct dbg_idle_chk_rule *rule, + u16 fail_entry_id, u32 *cond_reg_values) +{ + const union dbg_idle_chk_reg *regs = &((const union dbg_idle_chk_reg *) + s_dbg_arrays + [BIN_BUF_DBG_IDLE_CHK_REGS]. + ptr)[rule->reg_offset]; + const struct dbg_idle_chk_cond_reg *cond_regs = ®s[0].cond_reg; + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + struct dbg_idle_chk_result_hdr *hdr = + (struct dbg_idle_chk_result_hdr *)dump_buf; + const struct dbg_idle_chk_info_reg *info_regs = + ®s[rule->num_cond_regs].info_reg; + u32 next_reg_offset = 0, i, offset = 0; + u8 reg_id; + + /* Dump rule data */ + if (dump) { + memset(hdr, 0, sizeof(*hdr)); + hdr->rule_id = rule_id; + hdr->mem_entry_id = fail_entry_id; + hdr->severity = rule->severity; + hdr->num_dumped_cond_regs = rule->num_cond_regs; + } + + offset += IDLE_CHK_RESULT_HDR_DWORDS; + + /* Dump condition register values */ + for (reg_id = 0; reg_id < rule->num_cond_regs; reg_id++) { + const struct dbg_idle_chk_cond_reg *reg = &cond_regs[reg_id]; + + /* Write register header */ + if (dump) { + struct dbg_idle_chk_result_reg_hdr *reg_hdr = + (struct dbg_idle_chk_result_reg_hdr *)(dump_buf + + offset); + offset += IDLE_CHK_RESULT_REG_HDR_DWORDS; + memset(reg_hdr, 0, + sizeof(struct dbg_idle_chk_result_reg_hdr)); + reg_hdr->start_entry = reg->start_entry; + reg_hdr->size = reg->entry_size; + SET_FIELD(reg_hdr->data, + DBG_IDLE_CHK_RESULT_REG_HDR_IS_MEM, + reg->num_entries > 1 || reg->start_entry > 0 + ? 1 : 0); + SET_FIELD(reg_hdr->data, + DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID, reg_id); + + /* Write register values */ + for (i = 0; i < reg_hdr->size; + i++, next_reg_offset++, offset++) + dump_buf[offset] = + cond_reg_values[next_reg_offset]; + } else { + offset += IDLE_CHK_RESULT_REG_HDR_DWORDS + + reg->entry_size; + } + } + + /* Dump info register values */ + for (reg_id = 0; reg_id < rule->num_info_regs; reg_id++) { + const struct dbg_idle_chk_info_reg *reg = &info_regs[reg_id]; + u32 block_id; + + if (!dump) { + offset += IDLE_CHK_RESULT_REG_HDR_DWORDS + reg->size; + continue; + } + + /* Check if register's block is in reset */ + block_id = GET_FIELD(reg->data, DBG_IDLE_CHK_INFO_REG_BLOCK_ID); + if (block_id >= MAX_BLOCK_ID) { + DP_NOTICE(p_hwfn, "Invalid block_id\n"); + return 0; + } + + if (!dev_data->block_in_reset[block_id]) { + bool eval_mode = GET_FIELD(reg->mode.data, + DBG_MODE_HDR_EVAL_MODE) > 0; + bool mode_match = true; + + /* Check mode */ + if (eval_mode) { + u16 modes_buf_offset = + GET_FIELD(reg->mode.data, + DBG_MODE_HDR_MODES_BUF_OFFSET); + mode_match = + qed_is_mode_match(p_hwfn, + &modes_buf_offset); + } + + if (mode_match) { + u32 grc_addr = + DWORDS_TO_BYTES(GET_FIELD(reg->data, + DBG_IDLE_CHK_INFO_REG_ADDRESS)); + + /* Write register header */ + struct dbg_idle_chk_result_reg_hdr *reg_hdr = + (struct dbg_idle_chk_result_reg_hdr *) + (dump_buf + offset); + + offset += IDLE_CHK_RESULT_REG_HDR_DWORDS; + hdr->num_dumped_info_regs++; + memset(reg_hdr, 0, sizeof(*reg_hdr)); + reg_hdr->size = reg->size; + SET_FIELD(reg_hdr->data, + DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID, + rule->num_cond_regs + reg_id); + + /* Write register values */ + for (i = 0; i < reg->size; + i++, offset++, grc_addr += 4) + dump_buf[offset] = + qed_rd(p_hwfn, p_ptt, grc_addr); + } + } + } + + return offset; +} + +/* Dumps idle check rule entries. Returns the dumped size in dwords. */ +static u32 +qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u32 *dump_buf, bool dump, + const struct dbg_idle_chk_rule *input_rules, + u32 num_input_rules, u32 *num_failing_rules) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + u32 cond_reg_values[IDLE_CHK_MAX_ENTRIES_SIZE]; + u32 i, j, offset = 0; + u16 entry_id; + u8 reg_id; + + *num_failing_rules = 0; + for (i = 0; i < num_input_rules; i++) { + const struct dbg_idle_chk_cond_reg *cond_regs; + const struct dbg_idle_chk_rule *rule; + const union dbg_idle_chk_reg *regs; + u16 num_reg_entries = 1; + bool check_rule = true; + const u32 *imm_values; + + rule = &input_rules[i]; + regs = &((const union dbg_idle_chk_reg *) + s_dbg_arrays[BIN_BUF_DBG_IDLE_CHK_REGS].ptr) + [rule->reg_offset]; + cond_regs = ®s[0].cond_reg; + imm_values = &s_dbg_arrays[BIN_BUF_DBG_IDLE_CHK_IMMS].ptr + [rule->imm_offset]; + + /* Check if all condition register blocks are out of reset, and + * find maximal number of entries (all condition registers that + * are memories must have the same size, which is > 1). + */ + for (reg_id = 0; reg_id < rule->num_cond_regs && check_rule; + reg_id++) { + u32 block_id = GET_FIELD(cond_regs[reg_id].data, + DBG_IDLE_CHK_COND_REG_BLOCK_ID); + + if (block_id >= MAX_BLOCK_ID) { + DP_NOTICE(p_hwfn, "Invalid block_id\n"); + return 0; + } + + check_rule = !dev_data->block_in_reset[block_id]; + if (cond_regs[reg_id].num_entries > num_reg_entries) + num_reg_entries = cond_regs[reg_id].num_entries; + } + + if (!check_rule && dump) + continue; + + /* Go over all register entries (number of entries is the same + * for all condition registers). + */ + for (entry_id = 0; entry_id < num_reg_entries; entry_id++) { + /* Read current entry of all condition registers */ + if (dump) { + u32 next_reg_offset = 0; + + for (reg_id = 0; + reg_id < rule->num_cond_regs; + reg_id++) { + const struct dbg_idle_chk_cond_reg + *reg = &cond_regs[reg_id]; + + /* Find GRC address (if it's a memory, + * the address of the specific entry is + * calculated). + */ + u32 grc_addr = + DWORDS_TO_BYTES( + GET_FIELD(reg->data, + DBG_IDLE_CHK_COND_REG_ADDRESS)); + + if (reg->num_entries > 1 || + reg->start_entry > 0) { + u32 padded_entry_size = + reg->entry_size > 1 ? + roundup_pow_of_two + (reg->entry_size) : 1; + + grc_addr += + DWORDS_TO_BYTES( + (reg->start_entry + + entry_id) + * padded_entry_size); + } + + /* Read registers */ + if (next_reg_offset + reg->entry_size >= + IDLE_CHK_MAX_ENTRIES_SIZE) { + DP_NOTICE(p_hwfn, + "idle check registers entry is too large\n"); + return 0; + } + + for (j = 0; j < reg->entry_size; + j++, next_reg_offset++, + grc_addr += 4) + cond_reg_values[next_reg_offset] = + qed_rd(p_hwfn, p_ptt, grc_addr); + } + } + + /* Call rule's condition function - a return value of + * true indicates failure. + */ + if ((*cond_arr[rule->cond_id])(cond_reg_values, + imm_values) || !dump) { + offset += + qed_idle_chk_dump_failure(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + rule->rule_id, + rule, + entry_id, + cond_reg_values); + (*num_failing_rules)++; + break; + } + } + } + + return offset; +} + +/* Performs Idle Check Dump to the specified buffer. + * Returns the dumped size in dwords. + */ +static u32 qed_idle_chk_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) +{ + u32 offset = 0, input_offset = 0, num_failing_rules = 0; + u32 num_failing_rules_offset; + + /* Dump global params */ + offset += qed_dump_common_global_params(p_hwfn, + p_ptt, + dump_buf + offset, dump, 1); + offset += qed_dump_str_param(dump_buf + offset, + dump, "dump-type", "idle-chk"); + + /* Dump idle check section header with a single parameter */ + offset += qed_dump_section_hdr(dump_buf + offset, dump, "idle_chk", 1); + num_failing_rules_offset = offset; + offset += qed_dump_num_param(dump_buf + offset, dump, "num_rules", 0); + while (input_offset < + s_dbg_arrays[BIN_BUF_DBG_IDLE_CHK_RULES].size_in_dwords) { + const struct dbg_idle_chk_cond_hdr *cond_hdr = + (const struct dbg_idle_chk_cond_hdr *) + &s_dbg_arrays[BIN_BUF_DBG_IDLE_CHK_RULES].ptr + [input_offset++]; + bool eval_mode = GET_FIELD(cond_hdr->mode.data, + DBG_MODE_HDR_EVAL_MODE) > 0; + bool mode_match = true; + + /* Check mode */ + if (eval_mode) { + u16 modes_buf_offset = + GET_FIELD(cond_hdr->mode.data, + DBG_MODE_HDR_MODES_BUF_OFFSET); + + mode_match = qed_is_mode_match(p_hwfn, + &modes_buf_offset); + } + + if (mode_match) { + u32 curr_failing_rules; + + offset += + qed_idle_chk_dump_rule_entries(p_hwfn, + p_ptt, + dump_buf + offset, + dump, + (const struct dbg_idle_chk_rule *) + &s_dbg_arrays[BIN_BUF_DBG_IDLE_CHK_RULES]. + ptr[input_offset], + cond_hdr->data_size / IDLE_CHK_RULE_SIZE_DWORDS, + &curr_failing_rules); + num_failing_rules += curr_failing_rules; + } + + input_offset += cond_hdr->data_size; + } + + /* Overwrite num_rules parameter */ + if (dump) + qed_dump_num_param(dump_buf + num_failing_rules_offset, + dump, "num_rules", num_failing_rules); + + return offset; +} + +/* Finds the meta data image in NVRAM. */ +static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 image_type, + u32 *nvram_offset_bytes, + u32 *nvram_size_bytes) +{ + u32 ret_mcp_resp, ret_mcp_param, ret_txn_size; + struct mcp_file_att file_att; + + /* Call NVRAM get file command */ + if (qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_NVM_GET_FILE_ATT, + image_type, &ret_mcp_resp, &ret_mcp_param, + &ret_txn_size, (u32 *)&file_att) != 0) + return DBG_STATUS_NVRAM_GET_IMAGE_FAILED; + + /* Check response */ + if ((ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK) + return DBG_STATUS_NVRAM_GET_IMAGE_FAILED; + + /* Update return values */ + *nvram_offset_bytes = file_att.nvm_start_addr; + *nvram_size_bytes = file_att.len; + DP_VERBOSE(p_hwfn, + QED_MSG_DEBUG, + "find_nvram_image: found NVRAM image of type %d in NVRAM offset %d bytes with size %d bytes\n", + image_type, *nvram_offset_bytes, *nvram_size_bytes); + + /* Check alignment */ + if (*nvram_size_bytes & 0x3) + return DBG_STATUS_NON_ALIGNED_NVRAM_IMAGE; + return DBG_STATUS_OK; +} + +static enum dbg_status qed_nvram_read(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 nvram_offset_bytes, + u32 nvram_size_bytes, u32 *ret_buf) +{ + u32 ret_mcp_resp, ret_mcp_param, ret_read_size; + u32 bytes_to_copy, read_offset = 0; + s32 bytes_left = nvram_size_bytes; + + DP_VERBOSE(p_hwfn, + QED_MSG_DEBUG, + "nvram_read: reading image of size %d bytes from NVRAM\n", + nvram_size_bytes); + do { + bytes_to_copy = + (bytes_left > + MCP_DRV_NVM_BUF_LEN) ? MCP_DRV_NVM_BUF_LEN : bytes_left; + + /* Call NVRAM read command */ + if (qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt, + DRV_MSG_CODE_NVM_READ_NVRAM, + (nvram_offset_bytes + + read_offset) | + (bytes_to_copy << + DRV_MB_PARAM_NVM_LEN_SHIFT), + &ret_mcp_resp, &ret_mcp_param, + &ret_read_size, + (u32 *)((u8 *)ret_buf + + read_offset)) != 0) + return DBG_STATUS_NVRAM_READ_FAILED; + + /* Check response */ + if ((ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK) + return DBG_STATUS_NVRAM_READ_FAILED; + + /* Update read offset */ + read_offset += ret_read_size; + bytes_left -= ret_read_size; + } while (bytes_left > 0); + + return DBG_STATUS_OK; +} + +/* Get info on the MCP Trace data in the scratchpad: + * - trace_data_grc_addr - the GRC address of the trace data + * - trace_data_size_bytes - the size in bytes of the MCP Trace data (without + * the header) + */ +static enum dbg_status qed_mcp_trace_get_data_info(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *trace_data_grc_addr, + u32 *trace_data_size_bytes) +{ + /* Read MCP trace section offsize structure from MCP scratchpad */ + u32 spad_trace_offsize = qed_rd(p_hwfn, + p_ptt, + MCP_SPAD_TRACE_OFFSIZE_ADDR); + u32 signature; + + /* Extract MCP trace section GRC address from offsize structure (within + * scratchpad). + */ + *trace_data_grc_addr = + MCP_REG_SCRATCH + SECTION_OFFSET(spad_trace_offsize); + + /* Read signature from MCP trace section */ + signature = qed_rd(p_hwfn, p_ptt, + *trace_data_grc_addr + + offsetof(struct mcp_trace, signature)); + if (signature != MFW_TRACE_SIGNATURE) + return DBG_STATUS_INVALID_TRACE_SIGNATURE; + + /* Read trace size from MCP trace section */ + *trace_data_size_bytes = qed_rd(p_hwfn, + p_ptt, + *trace_data_grc_addr + + offsetof(struct mcp_trace, size)); + return DBG_STATUS_OK; +} + +/* Reads MCP trace meta data image from NVRAM. + * - running_bundle_id (OUT) - the running bundle ID (invalid when loaded from + * file) + * - trace_meta_offset_bytes (OUT) - the NVRAM offset in bytes in which the MCP + * Trace meta data starts (invalid when loaded from file) + * - trace_meta_size_bytes (OUT) - the size in bytes of the MCP Trace meta data + */ +static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 trace_data_size_bytes, + u32 *running_bundle_id, + u32 *trace_meta_offset_bytes, + u32 *trace_meta_size_bytes) +{ + /* Read MCP trace section offsize structure from MCP scratchpad */ + u32 spad_trace_offsize = qed_rd(p_hwfn, + p_ptt, + MCP_SPAD_TRACE_OFFSIZE_ADDR); + + /* Find running bundle ID */ + u32 running_mfw_addr = + MCP_REG_SCRATCH + SECTION_OFFSET(spad_trace_offsize) + + QED_SECTION_SIZE(spad_trace_offsize) + trace_data_size_bytes; + enum dbg_status status; + u32 nvram_image_type; + + *running_bundle_id = qed_rd(p_hwfn, p_ptt, running_mfw_addr); + if (*running_bundle_id > 1) + return DBG_STATUS_INVALID_NVRAM_BUNDLE; + + /* Find image in NVRAM */ + nvram_image_type = + (*running_bundle_id == + DIR_ID_1) ? NVM_TYPE_MFW_TRACE1 : NVM_TYPE_MFW_TRACE2; + status = qed_find_nvram_image(p_hwfn, + p_ptt, + nvram_image_type, + trace_meta_offset_bytes, + trace_meta_size_bytes); + + return status; +} + +/* Reads the MCP Trace data from the specified GRC address into the specified + * buffer. + */ +static void qed_mcp_trace_read_data(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 grc_addr, u32 size_in_dwords, u32 *buf) +{ + u32 i; + + DP_VERBOSE(p_hwfn, + QED_MSG_DEBUG, + "mcp_trace_read_data: reading trace data of size %d dwords from GRC address 0x%x\n", + size_in_dwords, grc_addr); + for (i = 0; i < size_in_dwords; i++, grc_addr += BYTES_IN_DWORD) + buf[i] = qed_rd(p_hwfn, p_ptt, grc_addr); +} + +/* Reads the MCP Trace meta data (from NVRAM or buffer) into the specified + * buffer. + */ +static enum dbg_status qed_mcp_trace_read_meta(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 nvram_offset_in_bytes, + u32 size_in_bytes, u32 *buf) +{ + u8 *byte_buf = (u8 *)buf; + u8 modules_num, i; + u32 signature; + + /* Read meta data from NVRAM */ + enum dbg_status status = qed_nvram_read(p_hwfn, + p_ptt, + nvram_offset_in_bytes, + size_in_bytes, + buf); + + if (status != DBG_STATUS_OK) + return status; + + /* Extract and check first signature */ + signature = qed_read_unaligned_dword(byte_buf); + byte_buf += sizeof(u32); + if (signature != MCP_TRACE_META_IMAGE_SIGNATURE) + return DBG_STATUS_INVALID_TRACE_SIGNATURE; + + /* Extract number of modules */ + modules_num = *(byte_buf++); + + /* Skip all modules */ + for (i = 0; i < modules_num; i++) { + u8 module_len = *(byte_buf++); + + byte_buf += module_len; + } + + /* Extract and check second signature */ + signature = qed_read_unaligned_dword(byte_buf); + byte_buf += sizeof(u32); + if (signature != MCP_TRACE_META_IMAGE_SIGNATURE) + return DBG_STATUS_INVALID_TRACE_SIGNATURE; + return DBG_STATUS_OK; +} + +/* Dump MCP Trace */ +enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + bool dump, u32 *num_dumped_dwords) +{ + u32 trace_data_grc_addr, trace_data_size_bytes, trace_data_size_dwords; + u32 trace_meta_size_dwords, running_bundle_id, offset = 0; + u32 trace_meta_offset_bytes, trace_meta_size_bytes; + enum dbg_status status; + int halted = 0; + + *num_dumped_dwords = 0; + + /* Get trace data info */ + status = qed_mcp_trace_get_data_info(p_hwfn, + p_ptt, + &trace_data_grc_addr, + &trace_data_size_bytes); + if (status != DBG_STATUS_OK) + return status; + + /* Dump global params */ + offset += qed_dump_common_global_params(p_hwfn, + p_ptt, + dump_buf + offset, dump, 1); + offset += qed_dump_str_param(dump_buf + offset, + dump, "dump-type", "mcp-trace"); + + /* Halt MCP while reading from scratchpad so the read data will be + * consistent if halt fails, MCP trace is taken anyway, with a small + * risk that it may be corrupt. + */ + if (dump) { + halted = !qed_mcp_halt(p_hwfn, p_ptt); + if (!halted) + DP_NOTICE(p_hwfn, "MCP halt failed!\n"); + } + + /* Find trace data size */ + trace_data_size_dwords = + DIV_ROUND_UP(trace_data_size_bytes + sizeof(struct mcp_trace), + BYTES_IN_DWORD); + + /* Dump trace data section header and param */ + offset += qed_dump_section_hdr(dump_buf + offset, + dump, "mcp_trace_data", 1); + offset += qed_dump_num_param(dump_buf + offset, + dump, "size", trace_data_size_dwords); + + /* Read trace data from scratchpad into dump buffer */ + if (dump) + qed_mcp_trace_read_data(p_hwfn, + p_ptt, + trace_data_grc_addr, + trace_data_size_dwords, + dump_buf + offset); + offset += trace_data_size_dwords; + + /* Resume MCP (only if halt succeeded) */ + if (halted && qed_mcp_resume(p_hwfn, p_ptt) != 0) + DP_NOTICE(p_hwfn, "Failed to resume MCP after halt!\n"); + + /* Dump trace meta section header */ + offset += qed_dump_section_hdr(dump_buf + offset, + dump, "mcp_trace_meta", 1); + + /* Read trace meta info */ + status = qed_mcp_trace_get_meta_info(p_hwfn, + p_ptt, + trace_data_size_bytes, + &running_bundle_id, + &trace_meta_offset_bytes, + &trace_meta_size_bytes); + if (status != DBG_STATUS_OK) + return status; + + /* Dump trace meta size param (trace_meta_size_bytes is always + * dword-aligned). + */ + trace_meta_size_dwords = BYTES_TO_DWORDS(trace_meta_size_bytes); + offset += qed_dump_num_param(dump_buf + offset, dump, "size", + trace_meta_size_dwords); + + /* Read trace meta image into dump buffer */ + if (dump) { + status = qed_mcp_trace_read_meta(p_hwfn, + p_ptt, + trace_meta_offset_bytes, + trace_meta_size_bytes, + dump_buf + offset); + if (status != DBG_STATUS_OK) + return status; + } + + offset += trace_meta_size_dwords; + + *num_dumped_dwords = offset; + + return DBG_STATUS_OK; +} + +/* Dump GRC FIFO */ +enum dbg_status qed_reg_fifo_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + bool dump, u32 *num_dumped_dwords) +{ + u32 offset = 0, dwords_read, size_param_offset; + bool fifo_has_data; + + *num_dumped_dwords = 0; + + /* Dump global params */ + offset += qed_dump_common_global_params(p_hwfn, + p_ptt, + dump_buf + offset, dump, 1); + offset += qed_dump_str_param(dump_buf + offset, + dump, "dump-type", "reg-fifo"); + + /* Dump fifo data section header and param. The size param is 0 for now, + * and is overwritten after reading the FIFO. + */ + offset += qed_dump_section_hdr(dump_buf + offset, + dump, "reg_fifo_data", 1); + size_param_offset = offset; + offset += qed_dump_num_param(dump_buf + offset, dump, "size", 0); + + if (!dump) { + /* FIFO max size is REG_FIFO_DEPTH_DWORDS. There is no way to + * test how much data is available, except for reading it. + */ + offset += REG_FIFO_DEPTH_DWORDS; + *num_dumped_dwords = offset; + return DBG_STATUS_OK; + } + + fifo_has_data = qed_rd(p_hwfn, p_ptt, + GRC_REG_TRACE_FIFO_VALID_DATA) > 0; + + /* Pull available data from fifo. Use DMAE since this is widebus memory + * and must be accessed atomically. Test for dwords_read not passing + * buffer size since more entries could be added to the buffer as we are + * emptying it. + */ + for (dwords_read = 0; + fifo_has_data && dwords_read < REG_FIFO_DEPTH_DWORDS; + dwords_read += REG_FIFO_ELEMENT_DWORDS, offset += + REG_FIFO_ELEMENT_DWORDS) { + if (qed_dmae_grc2host(p_hwfn, p_ptt, GRC_REG_TRACE_FIFO, + (u64)(uintptr_t)(&dump_buf[offset]), + REG_FIFO_ELEMENT_DWORDS, 0)) + return DBG_STATUS_DMAE_FAILED; + fifo_has_data = qed_rd(p_hwfn, p_ptt, + GRC_REG_TRACE_FIFO_VALID_DATA) > 0; + } + + qed_dump_num_param(dump_buf + size_param_offset, dump, "size", + dwords_read); + + *num_dumped_dwords = offset; + return DBG_STATUS_OK; +} + +/* Dump IGU FIFO */ +enum dbg_status qed_igu_fifo_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + bool dump, u32 *num_dumped_dwords) +{ + u32 offset = 0, dwords_read, size_param_offset; + bool fifo_has_data; + + *num_dumped_dwords = 0; + + /* Dump global params */ + offset += qed_dump_common_global_params(p_hwfn, + p_ptt, + dump_buf + offset, dump, 1); + offset += qed_dump_str_param(dump_buf + offset, + dump, "dump-type", "igu-fifo"); + + /* Dump fifo data section header and param. The size param is 0 for now, + * and is overwritten after reading the FIFO. + */ + offset += qed_dump_section_hdr(dump_buf + offset, + dump, "igu_fifo_data", 1); + size_param_offset = offset; + offset += qed_dump_num_param(dump_buf + offset, dump, "size", 0); + + if (!dump) { + /* FIFO max size is IGU_FIFO_DEPTH_DWORDS. There is no way to + * test how much data is available, except for reading it. + */ + offset += IGU_FIFO_DEPTH_DWORDS; + *num_dumped_dwords = offset; + return DBG_STATUS_OK; + } + + fifo_has_data = qed_rd(p_hwfn, p_ptt, + IGU_REG_ERROR_HANDLING_DATA_VALID) > 0; + + /* Pull available data from fifo. Use DMAE since this is widebus memory + * and must be accessed atomically. Test for dwords_read not passing + * buffer size since more entries could be added to the buffer as we are + * emptying it. + */ + for (dwords_read = 0; + fifo_has_data && dwords_read < IGU_FIFO_DEPTH_DWORDS; + dwords_read += IGU_FIFO_ELEMENT_DWORDS, offset += + IGU_FIFO_ELEMENT_DWORDS) { + if (qed_dmae_grc2host(p_hwfn, p_ptt, + IGU_REG_ERROR_HANDLING_MEMORY, + (u64)(uintptr_t)(&dump_buf[offset]), + IGU_FIFO_ELEMENT_DWORDS, 0)) + return DBG_STATUS_DMAE_FAILED; + fifo_has_data = qed_rd(p_hwfn, p_ptt, + IGU_REG_ERROR_HANDLING_DATA_VALID) > 0; + } + + qed_dump_num_param(dump_buf + size_param_offset, dump, "size", + dwords_read); + + *num_dumped_dwords = offset; + return DBG_STATUS_OK; +} + +/* Protection Override dump */ +enum dbg_status qed_protection_override_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + bool dump, u32 *num_dumped_dwords) +{ + u32 offset = 0, size_param_offset, override_window_dwords; + + *num_dumped_dwords = 0; + + /* Dump global params */ + offset += qed_dump_common_global_params(p_hwfn, + p_ptt, + dump_buf + offset, dump, 1); + offset += qed_dump_str_param(dump_buf + offset, + dump, "dump-type", "protection-override"); + + /* Dump data section header and param. The size param is 0 for now, and + * is overwritten after reading the data. + */ + offset += qed_dump_section_hdr(dump_buf + offset, + dump, "protection_override_data", 1); + size_param_offset = offset; + offset += qed_dump_num_param(dump_buf + offset, dump, "size", 0); + + if (!dump) { + offset += PROTECTION_OVERRIDE_DEPTH_DWORDS; + *num_dumped_dwords = offset; + return DBG_STATUS_OK; + } + + /* Add override window info to buffer */ + override_window_dwords = + qed_rd(p_hwfn, p_ptt, + GRC_REG_NUMBER_VALID_OVERRIDE_WINDOW) * + PROTECTION_OVERRIDE_ELEMENT_DWORDS; + if (qed_dmae_grc2host(p_hwfn, p_ptt, + GRC_REG_PROTECTION_OVERRIDE_WINDOW, + (u64)(uintptr_t)(dump_buf + offset), + override_window_dwords, 0)) + return DBG_STATUS_DMAE_FAILED; + offset += override_window_dwords; + qed_dump_num_param(dump_buf + size_param_offset, dump, "size", + override_window_dwords); + + *num_dumped_dwords = offset; + return DBG_STATUS_OK; +} + +/* Performs FW Asserts Dump to the specified buffer. + * Returns the dumped size in dwords. + */ +static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, bool dump) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + char storm_letter_str[2] = "?"; + struct fw_info fw_info; + u32 offset = 0, i; + u8 storm_id; + + /* Dump global params */ + offset += qed_dump_common_global_params(p_hwfn, + p_ptt, + dump_buf + offset, dump, 1); + offset += qed_dump_str_param(dump_buf + offset, + dump, "dump-type", "fw-asserts"); + for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) { + u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx, + last_list_idx, element_addr; + + if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id]) + continue; + + /* Read FW info for the current Storm */ + qed_read_fw_info(p_hwfn, p_ptt, storm_id, &fw_info); + + /* Dump FW Asserts section header and params */ + storm_letter_str[0] = s_storm_defs[storm_id].letter; + offset += qed_dump_section_hdr(dump_buf + offset, dump, + "fw_asserts", 2); + offset += qed_dump_str_param(dump_buf + offset, dump, "storm", + storm_letter_str); + offset += qed_dump_num_param(dump_buf + offset, dump, "size", + fw_info.fw_asserts_section. + list_element_dword_size); + + if (!dump) { + offset += fw_info.fw_asserts_section. + list_element_dword_size; + continue; + } + + /* Read and dump FW Asserts data */ + fw_asserts_section_addr = + s_storm_defs[storm_id].sem_fast_mem_addr + + SEM_FAST_REG_INT_RAM + + RAM_LINES_TO_BYTES(fw_info.fw_asserts_section. + section_ram_line_offset); + next_list_idx_addr = + fw_asserts_section_addr + + DWORDS_TO_BYTES(fw_info.fw_asserts_section. + list_next_index_dword_offset); + next_list_idx = qed_rd(p_hwfn, p_ptt, next_list_idx_addr); + last_list_idx = (next_list_idx > 0 + ? next_list_idx + : fw_info.fw_asserts_section.list_num_elements) + - 1; + element_addr = + fw_asserts_section_addr + + DWORDS_TO_BYTES(fw_info.fw_asserts_section. + list_dword_offset) + + last_list_idx * + DWORDS_TO_BYTES(fw_info.fw_asserts_section. + list_element_dword_size); + for (i = 0; + i < fw_info.fw_asserts_section.list_element_dword_size; + i++, offset++, element_addr += BYTES_IN_DWORD) + dump_buf[offset] = qed_rd(p_hwfn, p_ptt, element_addr); + } + + /* Dump last section */ + offset += qed_dump_section_hdr(dump_buf + offset, dump, "last", 0); + return offset; +} + +/***************************** Public Functions *******************************/ + +enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr) +{ + /* Convert binary data to debug arrays */ + u32 num_of_buffers = *(u32 *)bin_ptr; + struct bin_buffer_hdr *buf_array; + u8 buf_id; + + buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1); + + for (buf_id = 0; buf_id < num_of_buffers; buf_id++) { + s_dbg_arrays[buf_id].ptr = + (u32 *)(bin_ptr + buf_array[buf_id].offset); + s_dbg_arrays[buf_id].size_in_dwords = + BYTES_TO_DWORDS(buf_array[buf_id].length); + } + + return DBG_STATUS_OK; +} + +enum dbg_status qed_dbg_grc_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size) +{ + enum dbg_status status = qed_dbg_dev_init(p_hwfn, p_ptt); + + *buf_size = 0; + if (status != DBG_STATUS_OK) + return status; + if (!s_dbg_arrays[BIN_BUF_DBG_MODE_TREE].ptr || + !s_dbg_arrays[BIN_BUF_DBG_DUMP_REG].ptr || + !s_dbg_arrays[BIN_BUF_DBG_DUMP_MEM].ptr || + !s_dbg_arrays[BIN_BUF_DBG_ATTN_BLOCKS].ptr || + !s_dbg_arrays[BIN_BUF_DBG_ATTN_REGS].ptr) + return DBG_STATUS_DBG_ARRAY_NOT_SET; + return qed_grc_dump(p_hwfn, p_ptt, NULL, false, buf_size); +} + +enum dbg_status qed_dbg_grc_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords) +{ + u32 needed_buf_size_in_dwords; + enum dbg_status status; + + status = qed_dbg_grc_get_dump_buf_size(p_hwfn, p_ptt, + &needed_buf_size_in_dwords); + + *num_dumped_dwords = 0; + if (status != DBG_STATUS_OK) + return status; + if (buf_size_in_dwords < needed_buf_size_in_dwords) + return DBG_STATUS_DUMP_BUF_TOO_SMALL; + + /* GRC Dump */ + status = qed_grc_dump(p_hwfn, p_ptt, dump_buf, true, num_dumped_dwords); + + /* Clear all GRC params */ + qed_dbg_grc_clear_params(p_hwfn); + return status; +} + +enum dbg_status qed_dbg_idle_chk_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size) +{ + enum dbg_status status = qed_dbg_dev_init(p_hwfn, p_ptt); + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + + *buf_size = 0; + if (status != DBG_STATUS_OK) + return status; + if (!s_dbg_arrays[BIN_BUF_DBG_MODE_TREE].ptr || + !s_dbg_arrays[BIN_BUF_DBG_IDLE_CHK_REGS].ptr || + !s_dbg_arrays[BIN_BUF_DBG_IDLE_CHK_IMMS].ptr || + !s_dbg_arrays[BIN_BUF_DBG_IDLE_CHK_RULES].ptr) + return DBG_STATUS_DBG_ARRAY_NOT_SET; + if (!dev_data->idle_chk.buf_size_set) { + dev_data->idle_chk.buf_size = qed_idle_chk_dump(p_hwfn, + p_ptt, + NULL, false); + dev_data->idle_chk.buf_size_set = true; + } + + *buf_size = dev_data->idle_chk.buf_size; + return DBG_STATUS_OK; +} + +enum dbg_status qed_dbg_idle_chk_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords) +{ + u32 needed_buf_size_in_dwords; + enum dbg_status status; + + status = qed_dbg_idle_chk_get_dump_buf_size(p_hwfn, p_ptt, + &needed_buf_size_in_dwords); + + *num_dumped_dwords = 0; + if (status != DBG_STATUS_OK) + return status; + if (buf_size_in_dwords < needed_buf_size_in_dwords) + return DBG_STATUS_DUMP_BUF_TOO_SMALL; + + /* Update reset state */ + qed_update_blocks_reset_state(p_hwfn, p_ptt); + + /* Idle Check Dump */ + *num_dumped_dwords = qed_idle_chk_dump(p_hwfn, p_ptt, dump_buf, true); + return DBG_STATUS_OK; +} + +enum dbg_status qed_dbg_mcp_trace_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size) +{ + enum dbg_status status = qed_dbg_dev_init(p_hwfn, p_ptt); + + *buf_size = 0; + if (status != DBG_STATUS_OK) + return status; + return qed_mcp_trace_dump(p_hwfn, p_ptt, NULL, false, buf_size); +} + +enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords) +{ + u32 needed_buf_size_in_dwords; + enum dbg_status status; + + status = qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt, + &needed_buf_size_in_dwords); + + if (status != DBG_STATUS_OK) + return status; + if (buf_size_in_dwords < needed_buf_size_in_dwords) + return DBG_STATUS_DUMP_BUF_TOO_SMALL; + + /* Update reset state */ + qed_update_blocks_reset_state(p_hwfn, p_ptt); + + /* Perform dump */ + return qed_mcp_trace_dump(p_hwfn, + p_ptt, dump_buf, true, num_dumped_dwords); +} + +enum dbg_status qed_dbg_reg_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size) +{ + enum dbg_status status = qed_dbg_dev_init(p_hwfn, p_ptt); + + *buf_size = 0; + if (status != DBG_STATUS_OK) + return status; + return qed_reg_fifo_dump(p_hwfn, p_ptt, NULL, false, buf_size); +} + +enum dbg_status qed_dbg_reg_fifo_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords) +{ + u32 needed_buf_size_in_dwords; + enum dbg_status status; + + status = qed_dbg_reg_fifo_get_dump_buf_size(p_hwfn, p_ptt, + &needed_buf_size_in_dwords); + + *num_dumped_dwords = 0; + if (status != DBG_STATUS_OK) + return status; + if (buf_size_in_dwords < needed_buf_size_in_dwords) + return DBG_STATUS_DUMP_BUF_TOO_SMALL; + + /* Update reset state */ + qed_update_blocks_reset_state(p_hwfn, p_ptt); + return qed_reg_fifo_dump(p_hwfn, + p_ptt, dump_buf, true, num_dumped_dwords); +} + +enum dbg_status qed_dbg_igu_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size) +{ + enum dbg_status status = qed_dbg_dev_init(p_hwfn, p_ptt); + + *buf_size = 0; + if (status != DBG_STATUS_OK) + return status; + return qed_igu_fifo_dump(p_hwfn, p_ptt, NULL, false, buf_size); +} + +enum dbg_status qed_dbg_igu_fifo_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords) +{ + u32 needed_buf_size_in_dwords; + enum dbg_status status; + + status = qed_dbg_igu_fifo_get_dump_buf_size(p_hwfn, p_ptt, + &needed_buf_size_in_dwords); + + *num_dumped_dwords = 0; + if (status != DBG_STATUS_OK) + return status; + if (buf_size_in_dwords < needed_buf_size_in_dwords) + return DBG_STATUS_DUMP_BUF_TOO_SMALL; + + /* Update reset state */ + qed_update_blocks_reset_state(p_hwfn, p_ptt); + return qed_igu_fifo_dump(p_hwfn, + p_ptt, dump_buf, true, num_dumped_dwords); +} + +enum dbg_status +qed_dbg_protection_override_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size) +{ + enum dbg_status status = qed_dbg_dev_init(p_hwfn, p_ptt); + + *buf_size = 0; + if (status != DBG_STATUS_OK) + return status; + return qed_protection_override_dump(p_hwfn, + p_ptt, NULL, false, buf_size); +} + +enum dbg_status qed_dbg_protection_override_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords) +{ + u32 needed_buf_size_in_dwords; + enum dbg_status status; + + status = qed_dbg_protection_override_get_dump_buf_size(p_hwfn, p_ptt, + &needed_buf_size_in_dwords); + + *num_dumped_dwords = 0; + if (status != DBG_STATUS_OK) + return status; + if (buf_size_in_dwords < needed_buf_size_in_dwords) + return DBG_STATUS_DUMP_BUF_TOO_SMALL; + + /* Update reset state */ + qed_update_blocks_reset_state(p_hwfn, p_ptt); + return qed_protection_override_dump(p_hwfn, + p_ptt, + dump_buf, true, num_dumped_dwords); +} + +enum dbg_status qed_dbg_fw_asserts_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size) +{ + enum dbg_status status = qed_dbg_dev_init(p_hwfn, p_ptt); + + *buf_size = 0; + if (status != DBG_STATUS_OK) + return status; + + /* Update reset state */ + qed_update_blocks_reset_state(p_hwfn, p_ptt); + *buf_size = qed_fw_asserts_dump(p_hwfn, p_ptt, NULL, false); + return DBG_STATUS_OK; +} + +enum dbg_status qed_dbg_fw_asserts_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords) +{ + u32 needed_buf_size_in_dwords; + enum dbg_status status; + + status = qed_dbg_fw_asserts_get_dump_buf_size(p_hwfn, p_ptt, + &needed_buf_size_in_dwords); + + *num_dumped_dwords = 0; + if (status != DBG_STATUS_OK) + return status; + if (buf_size_in_dwords < needed_buf_size_in_dwords) + return DBG_STATUS_DUMP_BUF_TOO_SMALL; + + *num_dumped_dwords = qed_fw_asserts_dump(p_hwfn, p_ptt, dump_buf, true); + return DBG_STATUS_OK; +} + +/******************************* Data Types **********************************/ + +struct mcp_trace_format { + u32 data; +#define MCP_TRACE_FORMAT_MODULE_MASK 0x0000ffff +#define MCP_TRACE_FORMAT_MODULE_SHIFT 0 +#define MCP_TRACE_FORMAT_LEVEL_MASK 0x00030000 +#define MCP_TRACE_FORMAT_LEVEL_SHIFT 16 +#define MCP_TRACE_FORMAT_P1_SIZE_MASK 0x000c0000 +#define MCP_TRACE_FORMAT_P1_SIZE_SHIFT 18 +#define MCP_TRACE_FORMAT_P2_SIZE_MASK 0x00300000 +#define MCP_TRACE_FORMAT_P2_SIZE_SHIFT 20 +#define MCP_TRACE_FORMAT_P3_SIZE_MASK 0x00c00000 +#define MCP_TRACE_FORMAT_P3_SIZE_SHIFT 22 +#define MCP_TRACE_FORMAT_LEN_MASK 0xff000000 +#define MCP_TRACE_FORMAT_LEN_SHIFT 24 + char *format_str; +}; + +struct mcp_trace_meta { + u32 modules_num; + char **modules; + u32 formats_num; + struct mcp_trace_format *formats; +}; + +/* Reg fifo element */ +struct reg_fifo_element { + u64 data; +#define REG_FIFO_ELEMENT_ADDRESS_SHIFT 0 +#define REG_FIFO_ELEMENT_ADDRESS_MASK 0x7fffff +#define REG_FIFO_ELEMENT_ACCESS_SHIFT 23 +#define REG_FIFO_ELEMENT_ACCESS_MASK 0x1 +#define REG_FIFO_ELEMENT_PF_SHIFT 24 +#define REG_FIFO_ELEMENT_PF_MASK 0xf +#define REG_FIFO_ELEMENT_VF_SHIFT 28 +#define REG_FIFO_ELEMENT_VF_MASK 0xff +#define REG_FIFO_ELEMENT_PORT_SHIFT 36 +#define REG_FIFO_ELEMENT_PORT_MASK 0x3 +#define REG_FIFO_ELEMENT_PRIVILEGE_SHIFT 38 +#define REG_FIFO_ELEMENT_PRIVILEGE_MASK 0x3 +#define REG_FIFO_ELEMENT_PROTECTION_SHIFT 40 +#define REG_FIFO_ELEMENT_PROTECTION_MASK 0x7 +#define REG_FIFO_ELEMENT_MASTER_SHIFT 43 +#define REG_FIFO_ELEMENT_MASTER_MASK 0xf +#define REG_FIFO_ELEMENT_ERROR_SHIFT 47 +#define REG_FIFO_ELEMENT_ERROR_MASK 0x1f +}; + +/* IGU fifo element */ +struct igu_fifo_element { + u32 dword0; +#define IGU_FIFO_ELEMENT_DWORD0_FID_SHIFT 0 +#define IGU_FIFO_ELEMENT_DWORD0_FID_MASK 0xff +#define IGU_FIFO_ELEMENT_DWORD0_IS_PF_SHIFT 8 +#define IGU_FIFO_ELEMENT_DWORD0_IS_PF_MASK 0x1 +#define IGU_FIFO_ELEMENT_DWORD0_SOURCE_SHIFT 9 +#define IGU_FIFO_ELEMENT_DWORD0_SOURCE_MASK 0xf +#define IGU_FIFO_ELEMENT_DWORD0_ERR_TYPE_SHIFT 13 +#define IGU_FIFO_ELEMENT_DWORD0_ERR_TYPE_MASK 0xf +#define IGU_FIFO_ELEMENT_DWORD0_CMD_ADDR_SHIFT 17 +#define IGU_FIFO_ELEMENT_DWORD0_CMD_ADDR_MASK 0x7fff + u32 dword1; + u32 dword2; +#define IGU_FIFO_ELEMENT_DWORD12_IS_WR_CMD_SHIFT 0 +#define IGU_FIFO_ELEMENT_DWORD12_IS_WR_CMD_MASK 0x1 +#define IGU_FIFO_ELEMENT_DWORD12_WR_DATA_SHIFT 1 +#define IGU_FIFO_ELEMENT_DWORD12_WR_DATA_MASK 0xffffffff + u32 reserved; +}; + +struct igu_fifo_wr_data { + u32 data; +#define IGU_FIFO_WR_DATA_PROD_CONS_SHIFT 0 +#define IGU_FIFO_WR_DATA_PROD_CONS_MASK 0xffffff +#define IGU_FIFO_WR_DATA_UPDATE_FLAG_SHIFT 24 +#define IGU_FIFO_WR_DATA_UPDATE_FLAG_MASK 0x1 +#define IGU_FIFO_WR_DATA_EN_DIS_INT_FOR_SB_SHIFT 25 +#define IGU_FIFO_WR_DATA_EN_DIS_INT_FOR_SB_MASK 0x3 +#define IGU_FIFO_WR_DATA_SEGMENT_SHIFT 27 +#define IGU_FIFO_WR_DATA_SEGMENT_MASK 0x1 +#define IGU_FIFO_WR_DATA_TIMER_MASK_SHIFT 28 +#define IGU_FIFO_WR_DATA_TIMER_MASK_MASK 0x1 +#define IGU_FIFO_WR_DATA_CMD_TYPE_SHIFT 31 +#define IGU_FIFO_WR_DATA_CMD_TYPE_MASK 0x1 +}; + +struct igu_fifo_cleanup_wr_data { + u32 data; +#define IGU_FIFO_CLEANUP_WR_DATA_RESERVED_SHIFT 0 +#define IGU_FIFO_CLEANUP_WR_DATA_RESERVED_MASK 0x7ffffff +#define IGU_FIFO_CLEANUP_WR_DATA_CLEANUP_VAL_SHIFT 27 +#define IGU_FIFO_CLEANUP_WR_DATA_CLEANUP_VAL_MASK 0x1 +#define IGU_FIFO_CLEANUP_WR_DATA_CLEANUP_TYPE_SHIFT 28 +#define IGU_FIFO_CLEANUP_WR_DATA_CLEANUP_TYPE_MASK 0x7 +#define IGU_FIFO_CLEANUP_WR_DATA_CMD_TYPE_SHIFT 31 +#define IGU_FIFO_CLEANUP_WR_DATA_CMD_TYPE_MASK 0x1 +}; + +/* Protection override element */ +struct protection_override_element { + u64 data; +#define PROTECTION_OVERRIDE_ELEMENT_ADDRESS_SHIFT 0 +#define PROTECTION_OVERRIDE_ELEMENT_ADDRESS_MASK 0x7fffff +#define PROTECTION_OVERRIDE_ELEMENT_WINDOW_SIZE_SHIFT 23 +#define PROTECTION_OVERRIDE_ELEMENT_WINDOW_SIZE_MASK 0xffffff +#define PROTECTION_OVERRIDE_ELEMENT_READ_SHIFT 47 +#define PROTECTION_OVERRIDE_ELEMENT_READ_MASK 0x1 +#define PROTECTION_OVERRIDE_ELEMENT_WRITE_SHIFT 48 +#define PROTECTION_OVERRIDE_ELEMENT_WRITE_MASK 0x1 +#define PROTECTION_OVERRIDE_ELEMENT_READ_PROTECTION_SHIFT 49 +#define PROTECTION_OVERRIDE_ELEMENT_READ_PROTECTION_MASK 0x7 +#define PROTECTION_OVERRIDE_ELEMENT_WRITE_PROTECTION_SHIFT 52 +#define PROTECTION_OVERRIDE_ELEMENT_WRITE_PROTECTION_MASK 0x7 +}; + +enum igu_fifo_sources { + IGU_SRC_PXP0, + IGU_SRC_PXP1, + IGU_SRC_PXP2, + IGU_SRC_PXP3, + IGU_SRC_PXP4, + IGU_SRC_PXP5, + IGU_SRC_PXP6, + IGU_SRC_PXP7, + IGU_SRC_CAU, + IGU_SRC_ATTN, + IGU_SRC_GRC +}; + +enum igu_fifo_addr_types { + IGU_ADDR_TYPE_MSIX_MEM, + IGU_ADDR_TYPE_WRITE_PBA, + IGU_ADDR_TYPE_WRITE_INT_ACK, + IGU_ADDR_TYPE_WRITE_ATTN_BITS, + IGU_ADDR_TYPE_READ_INT, + IGU_ADDR_TYPE_WRITE_PROD_UPDATE, + IGU_ADDR_TYPE_RESERVED +}; + +struct igu_fifo_addr_data { + u16 start_addr; + u16 end_addr; + char *desc; + char *vf_desc; + enum igu_fifo_addr_types type; +}; + +/******************************** Constants **********************************/ + +#define MAX_MSG_LEN 1024 +#define MCP_TRACE_MAX_MODULE_LEN 8 +#define MCP_TRACE_FORMAT_MAX_PARAMS 3 +#define MCP_TRACE_FORMAT_PARAM_WIDTH \ + (MCP_TRACE_FORMAT_P2_SIZE_SHIFT - MCP_TRACE_FORMAT_P1_SIZE_SHIFT) +#define REG_FIFO_ELEMENT_ADDR_FACTOR 4 +#define REG_FIFO_ELEMENT_IS_PF_VF_VAL 127 +#define PROTECTION_OVERRIDE_ELEMENT_ADDR_FACTOR 4 + +/********************************* Macros ************************************/ + +#define BYTES_TO_DWORDS(bytes) ((bytes) / BYTES_IN_DWORD) + +/***************************** Constant Arrays *******************************/ + +/* Status string array */ +static const char * const s_status_str[] = { + "Operation completed successfully", + "Debug application version wasn't set", + "Unsupported debug application version", + "The debug block wasn't reset since the last recording", + "Invalid arguments", + "The debug output was already set", + "Invalid PCI buffer size", + "PCI buffer allocation failed", + "A PCI buffer wasn't allocated", + "Too many inputs were enabled. Enabled less inputs, or set 'unifyInputs' to true", + "GRC/Timestamp input overlap in cycle dword 0", + "Cannot record Storm data since the entire recording cycle is used by HW", + "The Storm was already enabled", + "The specified Storm wasn't enabled", + "The block was already enabled", + "The specified block wasn't enabled", + "No input was enabled for recording", + "Filters and triggers are not allowed when recording in 64b units", + "The filter was already enabled", + "The trigger was already enabled", + "The trigger wasn't enabled", + "A constraint can be added only after a filter was enabled or a trigger state was added", + "Cannot add more than 3 trigger states", + "Cannot add more than 4 constraints per filter or trigger state", + "The recording wasn't started", + "A trigger was configured, but it didn't trigger", + "No data was recorded", + "Dump buffer is too small", + "Dumped data is not aligned to chunks", + "Unknown chip", + "Failed allocating virtual memory", + "The input block is in reset", + "Invalid MCP trace signature found in NVRAM", + "Invalid bundle ID found in NVRAM", + "Failed getting NVRAM image", + "NVRAM image is not dword-aligned", + "Failed reading from NVRAM", + "Idle check parsing failed", + "MCP Trace data is corrupt", + "Dump doesn't contain meta data - it must be provided in an image file", + "Failed to halt MCP", + "Failed to resume MCP after halt", + "DMAE transaction failed", + "Failed to empty SEMI sync FIFO", + "IGU FIFO data is corrupt", + "MCP failed to mask parities", + "FW Asserts parsing failed", + "GRC FIFO data is corrupt", + "Protection Override data is corrupt", + "Debug arrays were not set (when using binary files, dbg_set_bin_ptr must be called)", + "When a block is filtered, no other blocks can be recorded unless inputs are unified (due to a HW bug)" +}; + +/* Idle check severity names array */ +static const char * const s_idle_chk_severity_str[] = { + "Error", + "Error if no traffic", + "Warning" +}; + +/* MCP Trace level names array */ +static const char * const s_mcp_trace_level_str[] = { + "ERROR", + "TRACE", + "DEBUG" +}; + +/* Parsing strings */ +static const char * const s_access_strs[] = { + "read", + "write" +}; + +static const char * const s_privilege_strs[] = { + "VF", + "PDA", + "HV", + "UA" +}; + +static const char * const s_protection_strs[] = { + "(default)", + "(default)", + "(default)", + "(default)", + "override VF", + "override PDA", + "override HV", + "override UA" +}; + +static const char * const s_master_strs[] = { + "???", + "pxp", + "mcp", + "msdm", + "psdm", + "ysdm", + "usdm", + "tsdm", + "xsdm", + "dbu", + "dmae", + "???", + "???", + "???", + "???", + "???" +}; + +static const char * const s_reg_fifo_error_strs[] = { + "grc timeout", + "address doesn't belong to any block", + "reserved address in block or write to read-only address", + "privilege/protection mismatch", + "path isolation error" +}; + +static const char * const s_igu_fifo_source_strs[] = { + "TSTORM", + "MSTORM", + "USTORM", + "XSTORM", + "YSTORM", + "PSTORM", + "PCIE", + "NIG_QM_PBF", + "CAU", + "ATTN", + "GRC", +}; + +static const char * const s_igu_fifo_error_strs[] = { + "no error", + "length error", + "function disabled", + "VF sent command to attnetion address", + "host sent prod update command", + "read of during interrupt register while in MIMD mode", + "access to PXP BAR reserved address", + "producer update command to attention index", + "unknown error", + "SB index not valid", + "SB relative index and FID not found", + "FID not match", + "command with error flag asserted (PCI error or CAU discard)", + "VF sent cleanup and RF cleanup is disabled", + "cleanup command on type bigger than 4" +}; + +/* IGU FIFO address data */ +static const struct igu_fifo_addr_data s_igu_fifo_addr_data[] = { + {0x0, 0x101, "MSI-X Memory", NULL, IGU_ADDR_TYPE_MSIX_MEM}, + {0x102, 0x1ff, "reserved", NULL, IGU_ADDR_TYPE_RESERVED}, + {0x200, 0x200, "Write PBA[0:63]", NULL, IGU_ADDR_TYPE_WRITE_PBA}, + {0x201, 0x201, "Write PBA[64:127]", "reserved", + IGU_ADDR_TYPE_WRITE_PBA}, + {0x202, 0x202, "Write PBA[128]", "reserved", IGU_ADDR_TYPE_WRITE_PBA}, + {0x203, 0x3ff, "reserved", NULL, IGU_ADDR_TYPE_RESERVED}, + {0x400, 0x5ef, "Write interrupt acknowledgment", NULL, + IGU_ADDR_TYPE_WRITE_INT_ACK}, + {0x5f0, 0x5f0, "Attention bits update", NULL, + IGU_ADDR_TYPE_WRITE_ATTN_BITS}, + {0x5f1, 0x5f1, "Attention bits set", NULL, + IGU_ADDR_TYPE_WRITE_ATTN_BITS}, + {0x5f2, 0x5f2, "Attention bits clear", NULL, + IGU_ADDR_TYPE_WRITE_ATTN_BITS}, + {0x5f3, 0x5f3, "Read interrupt 0:63 with mask", NULL, + IGU_ADDR_TYPE_READ_INT}, + {0x5f4, 0x5f4, "Read interrupt 0:31 with mask", NULL, + IGU_ADDR_TYPE_READ_INT}, + {0x5f5, 0x5f5, "Read interrupt 32:63 with mask", NULL, + IGU_ADDR_TYPE_READ_INT}, + {0x5f6, 0x5f6, "Read interrupt 0:63 without mask", NULL, + IGU_ADDR_TYPE_READ_INT}, + {0x5f7, 0x5ff, "reserved", NULL, IGU_ADDR_TYPE_RESERVED}, + {0x600, 0x7ff, "Producer update", NULL, IGU_ADDR_TYPE_WRITE_PROD_UPDATE} +}; + +/******************************** Variables **********************************/ + +/* MCP Trace meta data - used in case the dump doesn't contain the meta data + * (e.g. due to no NVRAM access). + */ +static struct dbg_array s_mcp_trace_meta = { NULL, 0 }; + +/* Temporary buffer, used for print size calculations */ +static char s_temp_buf[MAX_MSG_LEN]; + +/***************************** Public Functions *******************************/ + +enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr) +{ + /* Convert binary data to debug arrays */ + u32 num_of_buffers = *(u32 *)bin_ptr; + struct bin_buffer_hdr *buf_array; + u8 buf_id; + + buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1); + + for (buf_id = 0; buf_id < num_of_buffers; buf_id++) { + s_dbg_arrays[buf_id].ptr = + (u32 *)(bin_ptr + buf_array[buf_id].offset); + s_dbg_arrays[buf_id].size_in_dwords = + BYTES_TO_DWORDS(buf_array[buf_id].length); + } + + return DBG_STATUS_OK; +} + +static u32 qed_cyclic_add(u32 a, u32 b, u32 size) +{ + return (a + b) % size; +} + +static u32 qed_cyclic_sub(u32 a, u32 b, u32 size) +{ + return (size + a - b) % size; +} + +/* Reads the specified number of bytes from the specified cyclic buffer (up to 4 + * bytes) and returns them as a dword value. the specified buffer offset is + * updated. + */ +static u32 qed_read_from_cyclic_buf(void *buf, + u32 *offset, + u32 buf_size, u8 num_bytes_to_read) +{ + u8 *bytes_buf = (u8 *)buf; + u8 *val_ptr; + u32 val = 0; + u8 i; + + val_ptr = (u8 *)&val; + + for (i = 0; i < num_bytes_to_read; i++) { + val_ptr[i] = bytes_buf[*offset]; + *offset = qed_cyclic_add(*offset, 1, buf_size); + } + + return val; +} + +/* Reads and returns the next byte from the specified buffer. + * The specified buffer offset is updated. + */ +static u8 qed_read_byte_from_buf(void *buf, u32 *offset) +{ + return ((u8 *)buf)[(*offset)++]; +} + +/* Reads and returns the next dword from the specified buffer. + * The specified buffer offset is updated. + */ +static u32 qed_read_dword_from_buf(void *buf, u32 *offset) +{ + u32 dword_val = *(u32 *)&((u8 *)buf)[*offset]; + + *offset += 4; + return dword_val; +} + +/* Reads the next string from the specified buffer, and copies it to the + * specified pointer. The specified buffer offset is updated. + */ +static void qed_read_str_from_buf(void *buf, u32 *offset, u32 size, char *dest) +{ + const char *source_str = &((const char *)buf)[*offset]; + + strncpy(dest, source_str, size); + dest[size - 1] = '\0'; + *offset += size; +} + +/* Returns a pointer to the specified offset (in bytes) of the specified buffer. + * If the specified buffer in NULL, a temporary buffer pointer is returned. + */ +static char *qed_get_buf_ptr(void *buf, u32 offset) +{ + return buf ? (char *)buf + offset : s_temp_buf; +} + +/* Reads a param from the specified buffer. Returns the number of dwords read. + * If the returned str_param is NULL, the param is numeric and its value is + * returned in num_param. + * Otheriwise, the param is a string and its pointer is returned in str_param. + */ +static u32 qed_read_param(u32 *dump_buf, + const char **param_name, + const char **param_str_val, u32 *param_num_val) +{ + char *char_buf = (char *)dump_buf; + u32 offset = 0; /* In bytes */ + + /* Extract param name */ + *param_name = char_buf; + offset += strlen(*param_name) + 1; + + /* Check param type */ + if (*(char_buf + offset++)) { + /* String param */ + *param_str_val = char_buf + offset; + offset += strlen(*param_str_val) + 1; + if (offset & 0x3) + offset += (4 - (offset & 0x3)); + } else { + /* Numeric param */ + *param_str_val = NULL; + if (offset & 0x3) + offset += (4 - (offset & 0x3)); + *param_num_val = *(u32 *)(char_buf + offset); + offset += 4; + } + + return offset / 4; +} + +/* Reads a section header from the specified buffer. + * Returns the number of dwords read. + */ +static u32 qed_read_section_hdr(u32 *dump_buf, + const char **section_name, + u32 *num_section_params) +{ + const char *param_str_val; + + return qed_read_param(dump_buf, + section_name, ¶m_str_val, num_section_params); +} + +/* Reads section params from the specified buffer and prints them to the results + * buffer. Returns the number of dwords read. + */ +static u32 qed_print_section_params(u32 *dump_buf, + u32 num_section_params, + char *results_buf, u32 *num_chars_printed) +{ + u32 i, dump_offset = 0, results_offset = 0; + + for (i = 0; i < num_section_params; i++) { + const char *param_name; + const char *param_str_val; + u32 param_num_val = 0; + + dump_offset += qed_read_param(dump_buf + dump_offset, + ¶m_name, + ¶m_str_val, ¶m_num_val); + if (param_str_val) + /* String param */ + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "%s: %s\n", param_name, param_str_val); + else if (strcmp(param_name, "fw-timestamp")) + /* Numeric param */ + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "%s: %d\n", param_name, param_num_val); + } + + results_offset += + sprintf(qed_get_buf_ptr(results_buf, results_offset), "\n"); + *num_chars_printed = results_offset; + return dump_offset; +} + +const char *qed_dbg_get_status_str(enum dbg_status status) +{ + return (status < + MAX_DBG_STATUS) ? s_status_str[status] : "Invalid debug status"; +} + +/* Parses the idle check rules and returns the number of characters printed. + * In case of parsing error, returns 0. + */ +static u32 qed_parse_idle_chk_dump_rules(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 *dump_buf_end, + u32 num_rules, + bool print_fw_idle_chk, + char *results_buf, + u32 *num_errors, u32 *num_warnings) +{ + u32 rule_idx, results_offset = 0; /* Offset in results_buf in bytes */ + u16 i, j; + + *num_errors = 0; + *num_warnings = 0; + + /* Go over dumped results */ + for (rule_idx = 0; rule_idx < num_rules && dump_buf < dump_buf_end; + rule_idx++) { + const struct dbg_idle_chk_rule_parsing_data *rule_parsing_data; + struct dbg_idle_chk_result_hdr *hdr; + const char *parsing_str; + u32 parsing_str_offset; + const char *lsi_msg; + u8 curr_reg_id = 0; + bool has_fw_msg; + + hdr = (struct dbg_idle_chk_result_hdr *)dump_buf; + rule_parsing_data = + (const struct dbg_idle_chk_rule_parsing_data *) + &s_dbg_arrays[BIN_BUF_DBG_IDLE_CHK_PARSING_DATA]. + ptr[hdr->rule_id]; + parsing_str_offset = + GET_FIELD(rule_parsing_data->data, + DBG_IDLE_CHK_RULE_PARSING_DATA_STR_OFFSET); + has_fw_msg = + GET_FIELD(rule_parsing_data->data, + DBG_IDLE_CHK_RULE_PARSING_DATA_HAS_FW_MSG) > 0; + parsing_str = &((const char *) + s_dbg_arrays[BIN_BUF_DBG_PARSING_STRINGS].ptr) + [parsing_str_offset]; + lsi_msg = parsing_str; + + if (hdr->severity >= MAX_DBG_IDLE_CHK_SEVERITY_TYPES) + return 0; + + /* Skip rule header */ + dump_buf += (sizeof(struct dbg_idle_chk_result_hdr) / 4); + + /* Update errors/warnings count */ + if (hdr->severity == IDLE_CHK_SEVERITY_ERROR || + hdr->severity == IDLE_CHK_SEVERITY_ERROR_NO_TRAFFIC) + (*num_errors)++; + else + (*num_warnings)++; + + /* Print rule severity */ + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), "%s: ", + s_idle_chk_severity_str[hdr->severity]); + + /* Print rule message */ + if (has_fw_msg) + parsing_str += strlen(parsing_str) + 1; + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), "%s.", + has_fw_msg && + print_fw_idle_chk ? parsing_str : lsi_msg); + parsing_str += strlen(parsing_str) + 1; + + /* Print register values */ + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), " Registers:"); + for (i = 0; + i < hdr->num_dumped_cond_regs + hdr->num_dumped_info_regs; + i++) { + struct dbg_idle_chk_result_reg_hdr *reg_hdr + = (struct dbg_idle_chk_result_reg_hdr *) + dump_buf; + bool is_mem = + GET_FIELD(reg_hdr->data, + DBG_IDLE_CHK_RESULT_REG_HDR_IS_MEM); + u8 reg_id = + GET_FIELD(reg_hdr->data, + DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID); + + /* Skip reg header */ + dump_buf += + (sizeof(struct dbg_idle_chk_result_reg_hdr) / 4); + + /* Skip register names until the required reg_id is + * reached. + */ + for (; reg_id > curr_reg_id; + curr_reg_id++, + parsing_str += strlen(parsing_str) + 1); + + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), " %s", + parsing_str); + if (i < hdr->num_dumped_cond_regs && is_mem) + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "[%d]", hdr->mem_entry_id + + reg_hdr->start_entry); + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), "="); + for (j = 0; j < reg_hdr->size; j++, dump_buf++) { + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "0x%x", *dump_buf); + if (j < reg_hdr->size - 1) + results_offset += + sprintf(qed_get_buf_ptr + (results_buf, + results_offset), ","); + } + } + + results_offset += + sprintf(qed_get_buf_ptr(results_buf, results_offset), "\n"); + } + + /* Check if end of dump buffer was exceeded */ + if (dump_buf > dump_buf_end) + return 0; + return results_offset; +} + +/* Parses an idle check dump buffer. + * If result_buf is not NULL, the idle check results are printed to it. + * In any case, the required results buffer size is assigned to + * parsed_results_bytes. + * The parsing status is returned. + */ +static enum dbg_status qed_parse_idle_chk_dump(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf, + u32 *parsed_results_bytes, + u32 *num_errors, + u32 *num_warnings) +{ + const char *section_name, *param_name, *param_str_val; + u32 *dump_buf_end = dump_buf + num_dumped_dwords; + u32 num_section_params = 0, num_rules; + u32 results_offset = 0; /* Offset in results_buf in bytes */ + + *parsed_results_bytes = 0; + *num_errors = 0; + *num_warnings = 0; + if (!s_dbg_arrays[BIN_BUF_DBG_PARSING_STRINGS].ptr || + !s_dbg_arrays[BIN_BUF_DBG_IDLE_CHK_PARSING_DATA].ptr) + return DBG_STATUS_DBG_ARRAY_NOT_SET; + + /* Read global_params section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "global_params")) + return DBG_STATUS_IDLE_CHK_PARSE_FAILED; + + /* Print global params */ + dump_buf += qed_print_section_params(dump_buf, + num_section_params, + results_buf, &results_offset); + + /* Read idle_chk section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "idle_chk") || num_section_params != 1) + return DBG_STATUS_IDLE_CHK_PARSE_FAILED; + + dump_buf += qed_read_param(dump_buf, + ¶m_name, ¶m_str_val, &num_rules); + if (strcmp(param_name, "num_rules") != 0) + return DBG_STATUS_IDLE_CHK_PARSE_FAILED; + + if (num_rules) { + u32 rules_print_size; + + /* Print FW output */ + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "FW_IDLE_CHECK:\n"); + rules_print_size = + qed_parse_idle_chk_dump_rules(p_hwfn, dump_buf, + dump_buf_end, num_rules, + true, + results_buf ? + results_buf + + results_offset : NULL, + num_errors, num_warnings); + results_offset += rules_print_size; + if (rules_print_size == 0) + return DBG_STATUS_IDLE_CHK_PARSE_FAILED; + + /* Print LSI output */ + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "\nLSI_IDLE_CHECK:\n"); + rules_print_size = + qed_parse_idle_chk_dump_rules(p_hwfn, dump_buf, + dump_buf_end, num_rules, + false, + results_buf ? + results_buf + + results_offset : NULL, + num_errors, num_warnings); + results_offset += rules_print_size; + if (rules_print_size == 0) + return DBG_STATUS_IDLE_CHK_PARSE_FAILED; + } + + /* Print errors/warnings count */ + if (*num_errors) { + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "\nIdle Check failed!!! (with %d errors and %d warnings)\n", + *num_errors, *num_warnings); + } else if (*num_warnings) { + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "\nIdle Check completed successfuly (with %d warnings)\n", + *num_warnings); + } else { + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "\nIdle Check completed successfuly\n"); + } + + /* Add 1 for string NULL termination */ + *parsed_results_bytes = results_offset + 1; + return DBG_STATUS_OK; +} + +enum dbg_status qed_get_idle_chk_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size) +{ + u32 num_errors, num_warnings; + + return qed_parse_idle_chk_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + NULL, + results_buf_size, + &num_errors, &num_warnings); +} + +enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf, + u32 *num_errors, u32 *num_warnings) +{ + u32 parsed_buf_size; + + return qed_parse_idle_chk_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + results_buf, + &parsed_buf_size, + num_errors, num_warnings); +} + +/* Frees the specified MCP Trace meta data */ +static void qed_mcp_trace_free_meta(struct qed_hwfn *p_hwfn, + struct mcp_trace_meta *meta) +{ + u32 i; + + /* Release modules */ + if (meta->modules) { + for (i = 0; i < meta->modules_num; i++) + kfree(meta->modules[i]); + kfree(meta->modules); + } + + /* Release formats */ + if (meta->formats) { + for (i = 0; i < meta->formats_num; i++) + kfree(meta->formats[i].format_str); + kfree(meta->formats); + } +} + +/* Allocates and fills MCP Trace meta data based on the specified meta data + * dump buffer. + * Returns debug status code. + */ +static enum dbg_status qed_mcp_trace_alloc_meta(struct qed_hwfn *p_hwfn, + const u32 *meta_buf, + struct mcp_trace_meta *meta) +{ + u8 *meta_buf_bytes = (u8 *)meta_buf; + u32 offset = 0, signature, i; + + memset(meta, 0, sizeof(*meta)); + + /* Read first signature */ + signature = qed_read_dword_from_buf(meta_buf_bytes, &offset); + if (signature != MCP_TRACE_META_IMAGE_SIGNATURE) + return DBG_STATUS_INVALID_TRACE_SIGNATURE; + + /* Read number of modules and allocate memory for all the modules + * pointers. + */ + meta->modules_num = qed_read_byte_from_buf(meta_buf_bytes, &offset); + meta->modules = kzalloc(meta->modules_num * sizeof(char *), GFP_KERNEL); + if (!meta->modules) + return DBG_STATUS_VIRT_MEM_ALLOC_FAILED; + + /* Allocate and read all module strings */ + for (i = 0; i < meta->modules_num; i++) { + u8 module_len = qed_read_byte_from_buf(meta_buf_bytes, &offset); + + *(meta->modules + i) = kzalloc(module_len, GFP_KERNEL); + if (!(*(meta->modules + i))) { + /* Update number of modules to be released */ + meta->modules_num = i ? i - 1 : 0; + return DBG_STATUS_VIRT_MEM_ALLOC_FAILED; + } + + qed_read_str_from_buf(meta_buf_bytes, &offset, module_len, + *(meta->modules + i)); + if (module_len > MCP_TRACE_MAX_MODULE_LEN) + (*(meta->modules + i))[MCP_TRACE_MAX_MODULE_LEN] = '\0'; + } + + /* Read second signature */ + signature = qed_read_dword_from_buf(meta_buf_bytes, &offset); + if (signature != MCP_TRACE_META_IMAGE_SIGNATURE) + return DBG_STATUS_INVALID_TRACE_SIGNATURE; + + /* Read number of formats and allocate memory for all formats */ + meta->formats_num = qed_read_dword_from_buf(meta_buf_bytes, &offset); + meta->formats = kzalloc(meta->formats_num * + sizeof(struct mcp_trace_format), + GFP_KERNEL); + if (!meta->formats) + return DBG_STATUS_VIRT_MEM_ALLOC_FAILED; + + /* Allocate and read all strings */ + for (i = 0; i < meta->formats_num; i++) { + struct mcp_trace_format *format_ptr = &meta->formats[i]; + u8 format_len; + + format_ptr->data = qed_read_dword_from_buf(meta_buf_bytes, + &offset); + format_len = + (format_ptr->data & + MCP_TRACE_FORMAT_LEN_MASK) >> MCP_TRACE_FORMAT_LEN_SHIFT; + format_ptr->format_str = kzalloc(format_len, GFP_KERNEL); + if (!format_ptr->format_str) { + /* Update number of modules to be released */ + meta->formats_num = i ? i - 1 : 0; + return DBG_STATUS_VIRT_MEM_ALLOC_FAILED; + } + + qed_read_str_from_buf(meta_buf_bytes, + &offset, + format_len, format_ptr->format_str); + } + + return DBG_STATUS_OK; +} + +/* Parses an MCP Trace dump buffer. + * If result_buf is not NULL, the MCP Trace results are printed to it. + * In any case, the required results buffer size is assigned to + * parsed_results_bytes. + * The parsing status is returned. + */ +static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf, + u32 *parsed_results_bytes) +{ + u32 results_offset = 0, param_mask, param_shift, param_num_val; + u32 num_section_params, offset, end_offset, bytes_left; + const char *section_name, *param_name, *param_str_val; + u32 trace_data_dwords, trace_meta_dwords; + struct mcp_trace_meta meta; + struct mcp_trace *trace; + enum dbg_status status; + const u32 *meta_buf; + u8 *trace_buf; + + *parsed_results_bytes = 0; + + /* Read global_params section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "global_params")) + return DBG_STATUS_MCP_TRACE_BAD_DATA; + + /* Print global params */ + dump_buf += qed_print_section_params(dump_buf, + num_section_params, + results_buf, &results_offset); + + /* Read trace_data section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "mcp_trace_data") || num_section_params != 1) + return DBG_STATUS_MCP_TRACE_BAD_DATA; + dump_buf += qed_read_param(dump_buf, + ¶m_name, ¶m_str_val, ¶m_num_val); + if (strcmp(param_name, "size")) + return DBG_STATUS_MCP_TRACE_BAD_DATA; + trace_data_dwords = param_num_val; + + /* Prepare trace info */ + trace = (struct mcp_trace *)dump_buf; + trace_buf = (u8 *)dump_buf + sizeof(struct mcp_trace); + offset = trace->trace_oldest; + end_offset = trace->trace_prod; + bytes_left = qed_cyclic_sub(end_offset, offset, trace->size); + dump_buf += trace_data_dwords; + + /* Read meta_data section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "mcp_trace_meta")) + return DBG_STATUS_MCP_TRACE_BAD_DATA; + dump_buf += qed_read_param(dump_buf, + ¶m_name, ¶m_str_val, ¶m_num_val); + if (strcmp(param_name, "size") != 0) + return DBG_STATUS_MCP_TRACE_BAD_DATA; + trace_meta_dwords = param_num_val; + + /* Choose meta data buffer */ + if (!trace_meta_dwords) { + /* Dump doesn't include meta data */ + if (!s_mcp_trace_meta.ptr) + return DBG_STATUS_MCP_TRACE_NO_META; + meta_buf = s_mcp_trace_meta.ptr; + } else { + /* Dump includes meta data */ + meta_buf = dump_buf; + } + + /* Allocate meta data memory */ + status = qed_mcp_trace_alloc_meta(p_hwfn, meta_buf, &meta); + if (status != DBG_STATUS_OK) + goto free_mem; + + /* Ignore the level and modules masks - just print everything that is + * already in the buffer. + */ + while (bytes_left) { + struct mcp_trace_format *format_ptr; + u8 format_level, format_module; + u32 params[3] = { 0, 0, 0 }; + u32 header, format_idx, i; + + if (bytes_left < MFW_TRACE_ENTRY_SIZE) { + status = DBG_STATUS_MCP_TRACE_BAD_DATA; + goto free_mem; + } + + header = qed_read_from_cyclic_buf(trace_buf, + &offset, + trace->size, + MFW_TRACE_ENTRY_SIZE); + bytes_left -= MFW_TRACE_ENTRY_SIZE; + format_idx = header & MFW_TRACE_EVENTID_MASK; + + /* Skip message if its index doesn't exist in the meta data */ + if (format_idx > meta.formats_num) { + u8 format_size = + (u8)((header & + MFW_TRACE_PRM_SIZE_MASK) >> + MFW_TRACE_PRM_SIZE_SHIFT); + + if (bytes_left < format_size) { + status = DBG_STATUS_MCP_TRACE_BAD_DATA; + goto free_mem; + } + + offset = qed_cyclic_add(offset, + format_size, trace->size); + bytes_left -= format_size; + continue; + } + + format_ptr = &meta.formats[format_idx]; + for (i = 0, + param_mask = MCP_TRACE_FORMAT_P1_SIZE_MASK, param_shift = + MCP_TRACE_FORMAT_P1_SIZE_SHIFT; + i < MCP_TRACE_FORMAT_MAX_PARAMS; + i++, param_mask <<= MCP_TRACE_FORMAT_PARAM_WIDTH, + param_shift += MCP_TRACE_FORMAT_PARAM_WIDTH) { + /* Extract param size (0..3) */ + u8 param_size = + (u8)((format_ptr->data & + param_mask) >> param_shift); + + /* If the param size is zero, there are no other + * parameters. + */ + if (!param_size) + break; + + /* Size is encoded using 2 bits, where 3 is used to + * encode 4. + */ + if (param_size == 3) + param_size = 4; + if (bytes_left < param_size) { + status = DBG_STATUS_MCP_TRACE_BAD_DATA; + goto free_mem; + } + + params[i] = qed_read_from_cyclic_buf(trace_buf, + &offset, + trace->size, + param_size); + bytes_left -= param_size; + } + + format_level = + (u8)((format_ptr->data & + MCP_TRACE_FORMAT_LEVEL_MASK) >> + MCP_TRACE_FORMAT_LEVEL_SHIFT); + format_module = + (u8)((format_ptr->data & + MCP_TRACE_FORMAT_MODULE_MASK) >> + MCP_TRACE_FORMAT_MODULE_SHIFT); + if (format_level >= ARRAY_SIZE(s_mcp_trace_level_str)) { + status = DBG_STATUS_MCP_TRACE_BAD_DATA; + goto free_mem; + } + + /* Print current message to results buffer */ + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), "%s %-8s: ", + s_mcp_trace_level_str[format_level], + meta.modules[format_module]); + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + format_ptr->format_str, params[0], params[1], + params[2]); + } + +free_mem: + *parsed_results_bytes = results_offset + 1; + qed_mcp_trace_free_meta(p_hwfn, &meta); + return status; +} + +enum dbg_status qed_get_mcp_trace_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size) +{ + return qed_parse_mcp_trace_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + NULL, results_buf_size); +} + +enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf) +{ + u32 parsed_buf_size; + + return qed_parse_mcp_trace_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + results_buf, &parsed_buf_size); +} + +/* Parses a Reg FIFO dump buffer. + * If result_buf is not NULL, the Reg FIFO results are printed to it. + * In any case, the required results buffer size is assigned to + * parsed_results_bytes. + * The parsing status is returned. + */ +static enum dbg_status qed_parse_reg_fifo_dump(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf, + u32 *parsed_results_bytes) +{ + u32 results_offset = 0, param_num_val, num_section_params, num_elements; + const char *section_name, *param_name, *param_str_val; + struct reg_fifo_element *elements; + u8 i, j, err_val, vf_val; + char vf_str[4]; + + /* Read global_params section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "global_params")) + return DBG_STATUS_REG_FIFO_BAD_DATA; + + /* Print global params */ + dump_buf += qed_print_section_params(dump_buf, + num_section_params, + results_buf, &results_offset); + + /* Read reg_fifo_data section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "reg_fifo_data")) + return DBG_STATUS_REG_FIFO_BAD_DATA; + dump_buf += qed_read_param(dump_buf, + ¶m_name, ¶m_str_val, ¶m_num_val); + if (strcmp(param_name, "size")) + return DBG_STATUS_REG_FIFO_BAD_DATA; + if (param_num_val % REG_FIFO_ELEMENT_DWORDS) + return DBG_STATUS_REG_FIFO_BAD_DATA; + num_elements = param_num_val / REG_FIFO_ELEMENT_DWORDS; + elements = (struct reg_fifo_element *)dump_buf; + + /* Decode elements */ + for (i = 0; i < num_elements; i++) { + bool err_printed = false; + + /* Discover if element belongs to a VF or a PF */ + vf_val = GET_FIELD(elements[i].data, REG_FIFO_ELEMENT_VF); + if (vf_val == REG_FIFO_ELEMENT_IS_PF_VF_VAL) + sprintf(vf_str, "%s", "N/A"); + else + sprintf(vf_str, "%d", vf_val); + + /* Add parsed element to parsed buffer */ + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "raw: 0x%016llx, address: 0x%07llx, access: %-5s, pf: %2lld, vf: %s, port: %lld, privilege: %-3s, protection: %-12s, master: %-4s, errors: ", + elements[i].data, + GET_FIELD(elements[i].data, + REG_FIFO_ELEMENT_ADDRESS) * + REG_FIFO_ELEMENT_ADDR_FACTOR, + s_access_strs[GET_FIELD(elements[i].data, + REG_FIFO_ELEMENT_ACCESS)], + GET_FIELD(elements[i].data, + REG_FIFO_ELEMENT_PF), vf_str, + GET_FIELD(elements[i].data, + REG_FIFO_ELEMENT_PORT), + s_privilege_strs[GET_FIELD(elements[i]. + data, + REG_FIFO_ELEMENT_PRIVILEGE)], + s_protection_strs[GET_FIELD(elements[i].data, + REG_FIFO_ELEMENT_PROTECTION)], + s_master_strs[GET_FIELD(elements[i].data, + REG_FIFO_ELEMENT_MASTER)]); + + /* Print errors */ + for (j = 0, + err_val = GET_FIELD(elements[i].data, + REG_FIFO_ELEMENT_ERROR); + j < ARRAY_SIZE(s_reg_fifo_error_strs); + j++, err_val >>= 1) { + if (!(err_val & 0x1)) + continue; + if (err_printed) + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + ", "); + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), "%s", + s_reg_fifo_error_strs[j]); + err_printed = true; + } + + results_offset += + sprintf(qed_get_buf_ptr(results_buf, results_offset), "\n"); + } + + results_offset += sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "fifo contained %d elements", num_elements); + + /* Add 1 for string NULL termination */ + *parsed_results_bytes = results_offset + 1; + return DBG_STATUS_OK; +} + +enum dbg_status qed_get_reg_fifo_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size) +{ + return qed_parse_reg_fifo_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + NULL, results_buf_size); +} + +enum dbg_status qed_print_reg_fifo_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf) +{ + u32 parsed_buf_size; + + return qed_parse_reg_fifo_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + results_buf, &parsed_buf_size); +} + +/* Parses an IGU FIFO dump buffer. + * If result_buf is not NULL, the IGU FIFO results are printed to it. + * In any case, the required results buffer size is assigned to + * parsed_results_bytes. + * The parsing status is returned. + */ +static enum dbg_status qed_parse_igu_fifo_dump(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf, + u32 *parsed_results_bytes) +{ + u32 results_offset = 0, param_num_val, num_section_params, num_elements; + const char *section_name, *param_name, *param_str_val; + struct igu_fifo_element *elements; + char parsed_addr_data[32]; + char parsed_wr_data[256]; + u8 i, j; + + /* Read global_params section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "global_params")) + return DBG_STATUS_IGU_FIFO_BAD_DATA; + + /* Print global params */ + dump_buf += qed_print_section_params(dump_buf, + num_section_params, + results_buf, &results_offset); + + /* Read igu_fifo_data section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "igu_fifo_data")) + return DBG_STATUS_IGU_FIFO_BAD_DATA; + dump_buf += qed_read_param(dump_buf, + ¶m_name, ¶m_str_val, ¶m_num_val); + if (strcmp(param_name, "size")) + return DBG_STATUS_IGU_FIFO_BAD_DATA; + if (param_num_val % IGU_FIFO_ELEMENT_DWORDS) + return DBG_STATUS_IGU_FIFO_BAD_DATA; + num_elements = param_num_val / IGU_FIFO_ELEMENT_DWORDS; + elements = (struct igu_fifo_element *)dump_buf; + + /* Decode elements */ + for (i = 0; i < num_elements; i++) { + /* dword12 (dword index 1 and 2) contains bits 32..95 of the + * FIFO element. + */ + u64 dword12 = + ((u64)elements[i].dword2 << 32) | elements[i].dword1; + bool is_wr_cmd = GET_FIELD(dword12, + IGU_FIFO_ELEMENT_DWORD12_IS_WR_CMD); + bool is_pf = GET_FIELD(elements[i].dword0, + IGU_FIFO_ELEMENT_DWORD0_IS_PF); + u16 cmd_addr = GET_FIELD(elements[i].dword0, + IGU_FIFO_ELEMENT_DWORD0_CMD_ADDR); + u8 source = GET_FIELD(elements[i].dword0, + IGU_FIFO_ELEMENT_DWORD0_SOURCE); + u8 err_type = GET_FIELD(elements[i].dword0, + IGU_FIFO_ELEMENT_DWORD0_ERR_TYPE); + const struct igu_fifo_addr_data *addr_data = NULL; + + if (source >= ARRAY_SIZE(s_igu_fifo_source_strs)) + return DBG_STATUS_IGU_FIFO_BAD_DATA; + if (err_type >= ARRAY_SIZE(s_igu_fifo_error_strs)) + return DBG_STATUS_IGU_FIFO_BAD_DATA; + + /* Find address data */ + for (j = 0; j < ARRAY_SIZE(s_igu_fifo_addr_data) && !addr_data; + j++) + if (cmd_addr >= s_igu_fifo_addr_data[j].start_addr && + cmd_addr <= s_igu_fifo_addr_data[j].end_addr) + addr_data = &s_igu_fifo_addr_data[j]; + if (!addr_data) + return DBG_STATUS_IGU_FIFO_BAD_DATA; + + /* Prepare parsed address data */ + switch (addr_data->type) { + case IGU_ADDR_TYPE_MSIX_MEM: + sprintf(parsed_addr_data, + " vector_num=0x%x", cmd_addr / 2); + break; + case IGU_ADDR_TYPE_WRITE_INT_ACK: + case IGU_ADDR_TYPE_WRITE_PROD_UPDATE: + sprintf(parsed_addr_data, + " SB=0x%x", cmd_addr - addr_data->start_addr); + break; + default: + parsed_addr_data[0] = '\0'; + } + + /* Prepare parsed write data */ + if (is_wr_cmd) { + u32 wr_data = GET_FIELD(dword12, + IGU_FIFO_ELEMENT_DWORD12_WR_DATA); + u32 prod_cons = GET_FIELD(wr_data, + IGU_FIFO_WR_DATA_PROD_CONS); + u8 is_cleanup = GET_FIELD(wr_data, + IGU_FIFO_WR_DATA_CMD_TYPE); + + if (source == IGU_SRC_ATTN) { + sprintf(parsed_wr_data, + "prod: 0x%x, ", prod_cons); + } else { + if (is_cleanup) { + u8 cleanup_val = GET_FIELD(wr_data, + IGU_FIFO_CLEANUP_WR_DATA_CLEANUP_VAL); + u8 cleanup_type = GET_FIELD(wr_data, + IGU_FIFO_CLEANUP_WR_DATA_CLEANUP_TYPE); + + sprintf(parsed_wr_data, + "cmd_type: cleanup, cleanup_val: %s, cleanup_type: %d, ", + cleanup_val ? "set" : "clear", + cleanup_type); + } else { + u8 update_flag = GET_FIELD(wr_data, + IGU_FIFO_WR_DATA_UPDATE_FLAG); + u8 en_dis_int_for_sb = + GET_FIELD(wr_data, + IGU_FIFO_WR_DATA_EN_DIS_INT_FOR_SB); + u8 segment = GET_FIELD(wr_data, + IGU_FIFO_WR_DATA_SEGMENT); + u8 timer_mask = GET_FIELD(wr_data, + IGU_FIFO_WR_DATA_TIMER_MASK); + + sprintf(parsed_wr_data, + "cmd_type: prod/cons update, prod/cons: 0x%x, update_flag: %s, en_dis_int_for_sb: %s, segment: %s, timer_mask=%d, ", + prod_cons, + update_flag ? "update" : "nop", + en_dis_int_for_sb + ? (en_dis_int_for_sb == + 1 ? "disable" : "nop") : + "enable", + segment ? "attn" : "regular", + timer_mask); + } + } + } else { + parsed_wr_data[0] = '\0'; + } + + /* Add parsed element to parsed buffer */ + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "raw: 0x%01x%08x%08x, %s: %d, source: %s, type: %s, cmd_addr: 0x%x (%s%s), %serror: %s\n", + elements[i].dword2, elements[i].dword1, + elements[i].dword0, + is_pf ? "pf" : "vf", + GET_FIELD(elements[i].dword0, + IGU_FIFO_ELEMENT_DWORD0_FID), + s_igu_fifo_source_strs[source], + is_wr_cmd ? "wr" : "rd", cmd_addr, + (!is_pf && addr_data->vf_desc) + ? addr_data->vf_desc : addr_data->desc, + parsed_addr_data, parsed_wr_data, + s_igu_fifo_error_strs[err_type]); + } + + results_offset += sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "fifo contained %d elements", num_elements); + + /* Add 1 for string NULL termination */ + *parsed_results_bytes = results_offset + 1; + return DBG_STATUS_OK; +} + +enum dbg_status qed_get_igu_fifo_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size) +{ + return qed_parse_igu_fifo_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + NULL, results_buf_size); +} + +enum dbg_status qed_print_igu_fifo_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf) +{ + u32 parsed_buf_size; + + return qed_parse_igu_fifo_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + results_buf, &parsed_buf_size); +} + +static enum dbg_status +qed_parse_protection_override_dump(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf, + u32 *parsed_results_bytes) +{ + u32 results_offset = 0, param_num_val, num_section_params, num_elements; + const char *section_name, *param_name, *param_str_val; + struct protection_override_element *elements; + u8 i; + + /* Read global_params section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "global_params")) + return DBG_STATUS_PROTECTION_OVERRIDE_BAD_DATA; + + /* Print global params */ + dump_buf += qed_print_section_params(dump_buf, + num_section_params, + results_buf, &results_offset); + + /* Read protection_override_data section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "protection_override_data")) + return DBG_STATUS_PROTECTION_OVERRIDE_BAD_DATA; + dump_buf += qed_read_param(dump_buf, + ¶m_name, ¶m_str_val, ¶m_num_val); + if (strcmp(param_name, "size")) + return DBG_STATUS_PROTECTION_OVERRIDE_BAD_DATA; + if (param_num_val % PROTECTION_OVERRIDE_ELEMENT_DWORDS != 0) + return DBG_STATUS_PROTECTION_OVERRIDE_BAD_DATA; + num_elements = param_num_val / PROTECTION_OVERRIDE_ELEMENT_DWORDS; + elements = (struct protection_override_element *)dump_buf; + + /* Decode elements */ + for (i = 0; i < num_elements; i++) { + u32 address = GET_FIELD(elements[i].data, + PROTECTION_OVERRIDE_ELEMENT_ADDRESS) * + PROTECTION_OVERRIDE_ELEMENT_ADDR_FACTOR; + + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "window %2d, address: 0x%07x, size: %7lld regs, read: %lld, write: %lld, read protection: %-12s, write protection: %-12s\n", + i, address, + GET_FIELD(elements[i].data, + PROTECTION_OVERRIDE_ELEMENT_WINDOW_SIZE), + GET_FIELD(elements[i].data, + PROTECTION_OVERRIDE_ELEMENT_READ), + GET_FIELD(elements[i].data, + PROTECTION_OVERRIDE_ELEMENT_WRITE), + s_protection_strs[GET_FIELD(elements[i].data, + PROTECTION_OVERRIDE_ELEMENT_READ_PROTECTION)], + s_protection_strs[GET_FIELD(elements[i].data, + PROTECTION_OVERRIDE_ELEMENT_WRITE_PROTECTION)]); + } + + results_offset += sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "protection override contained %d elements", + num_elements); + + /* Add 1 for string NULL termination */ + *parsed_results_bytes = results_offset + 1; + return DBG_STATUS_OK; +} + +enum dbg_status +qed_get_protection_override_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size) +{ + return qed_parse_protection_override_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + NULL, results_buf_size); +} + +enum dbg_status qed_print_protection_override_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf) +{ + u32 parsed_buf_size; + + return qed_parse_protection_override_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + results_buf, + &parsed_buf_size); +} + +/* Parses a FW Asserts dump buffer. + * If result_buf is not NULL, the FW Asserts results are printed to it. + * In any case, the required results buffer size is assigned to + * parsed_results_bytes. + * The parsing status is returned. + */ +static enum dbg_status qed_parse_fw_asserts_dump(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf, + u32 *parsed_results_bytes) +{ + u32 results_offset = 0, num_section_params, param_num_val, i; + const char *param_name, *param_str_val, *section_name; + bool last_section_found = false; + + *parsed_results_bytes = 0; + + /* Read global_params section */ + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, &num_section_params); + if (strcmp(section_name, "global_params")) + return DBG_STATUS_FW_ASSERTS_PARSE_FAILED; + + /* Print global params */ + dump_buf += qed_print_section_params(dump_buf, + num_section_params, + results_buf, &results_offset); + while (!last_section_found) { + const char *storm_letter = NULL; + u32 storm_dump_size = 0; + + dump_buf += qed_read_section_hdr(dump_buf, + §ion_name, + &num_section_params); + if (!strcmp(section_name, "last")) { + last_section_found = true; + continue; + } else if (strcmp(section_name, "fw_asserts")) { + return DBG_STATUS_FW_ASSERTS_PARSE_FAILED; + } + + /* Extract params */ + for (i = 0; i < num_section_params; i++) { + dump_buf += qed_read_param(dump_buf, + ¶m_name, + ¶m_str_val, + ¶m_num_val); + if (!strcmp(param_name, "storm")) + storm_letter = param_str_val; + else if (!strcmp(param_name, "size")) + storm_dump_size = param_num_val; + else + return DBG_STATUS_FW_ASSERTS_PARSE_FAILED; + } + + if (!storm_letter || !storm_dump_size) + return DBG_STATUS_FW_ASSERTS_PARSE_FAILED; + + /* Print data */ + results_offset += sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "\n%sSTORM_ASSERT: size=%d\n", + storm_letter, storm_dump_size); + for (i = 0; i < storm_dump_size; i++, dump_buf++) + results_offset += + sprintf(qed_get_buf_ptr(results_buf, + results_offset), + "%08x\n", *dump_buf); + } + + /* Add 1 for string NULL termination */ + *parsed_results_bytes = results_offset + 1; + return DBG_STATUS_OK; +} + +enum dbg_status qed_get_fw_asserts_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size) +{ + return qed_parse_fw_asserts_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + NULL, results_buf_size); +} + +enum dbg_status qed_print_fw_asserts_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf) +{ + u32 parsed_buf_size; + + return qed_parse_fw_asserts_dump(p_hwfn, + dump_buf, + num_dumped_dwords, + results_buf, &parsed_buf_size); +} + +/* Wrapper for unifying the idle_chk and mcp_trace api */ +enum dbg_status qed_print_idle_chk_results_wrapper(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf) +{ + u32 num_errors, num_warnnings; + + return qed_print_idle_chk_results(p_hwfn, dump_buf, num_dumped_dwords, + results_buf, &num_errors, + &num_warnnings); +} + +/* Feature meta data lookup table */ +static struct { + char *name; + enum dbg_status (*get_size)(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *size); + enum dbg_status (*perform_dump)(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *dump_buf, + u32 buf_size, u32 *dumped_dwords); + enum dbg_status (*print_results)(struct qed_hwfn *p_hwfn, + u32 *dump_buf, u32 num_dumped_dwords, + char *results_buf); + enum dbg_status (*results_buf_size)(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size); +} qed_features_lookup[] = { + { + "grc", qed_dbg_grc_get_dump_buf_size, + qed_dbg_grc_dump, NULL, NULL}, { + "idle_chk", + qed_dbg_idle_chk_get_dump_buf_size, + qed_dbg_idle_chk_dump, + qed_print_idle_chk_results_wrapper, + qed_get_idle_chk_results_buf_size}, { + "mcp_trace", + qed_dbg_mcp_trace_get_dump_buf_size, + qed_dbg_mcp_trace_dump, qed_print_mcp_trace_results, + qed_get_mcp_trace_results_buf_size}, { + "reg_fifo", + qed_dbg_reg_fifo_get_dump_buf_size, + qed_dbg_reg_fifo_dump, qed_print_reg_fifo_results, + qed_get_reg_fifo_results_buf_size}, { + "igu_fifo", + qed_dbg_igu_fifo_get_dump_buf_size, + qed_dbg_igu_fifo_dump, qed_print_igu_fifo_results, + qed_get_igu_fifo_results_buf_size}, { + "protection_override", + qed_dbg_protection_override_get_dump_buf_size, + qed_dbg_protection_override_dump, + qed_print_protection_override_results, + qed_get_protection_override_results_buf_size}, { + "fw_asserts", + qed_dbg_fw_asserts_get_dump_buf_size, + qed_dbg_fw_asserts_dump, + qed_print_fw_asserts_results, + qed_get_fw_asserts_results_buf_size},}; + +static void qed_dbg_print_feature(u8 *p_text_buf, u32 text_size) +{ + u32 i, precision = 80; + + if (!p_text_buf) + return; + + pr_notice("\n%.*s", precision, p_text_buf); + for (i = precision; i < text_size; i += precision) + pr_cont("%.*s", precision, p_text_buf + i); + pr_cont("\n"); +} + +#define QED_RESULTS_BUF_MIN_SIZE 16 +/* Generic function for decoding debug feature info */ +enum dbg_status format_feature(struct qed_hwfn *p_hwfn, + enum qed_dbg_features feature_idx) +{ + struct qed_dbg_feature *feature = + &p_hwfn->cdev->dbg_params.features[feature_idx]; + u32 text_size_bytes, null_char_pos, i; + enum dbg_status rc; + char *text_buf; + + /* Check if feature supports formatting capability */ + if (!qed_features_lookup[feature_idx].results_buf_size) + return DBG_STATUS_OK; + + /* Obtain size of formatted output */ + rc = qed_features_lookup[feature_idx]. + results_buf_size(p_hwfn, (u32 *)feature->dump_buf, + feature->dumped_dwords, &text_size_bytes); + if (rc != DBG_STATUS_OK) + return rc; + + /* Make sure that the allocated size is a multiple of dword (4 bytes) */ + null_char_pos = text_size_bytes - 1; + text_size_bytes = (text_size_bytes + 3) & ~0x3; + + if (text_size_bytes < QED_RESULTS_BUF_MIN_SIZE) { + DP_NOTICE(p_hwfn->cdev, + "formatted size of feature was too small %d. Aborting\n", + text_size_bytes); + return DBG_STATUS_INVALID_ARGS; + } + + /* Allocate temp text buf */ + text_buf = vzalloc(text_size_bytes); + if (!text_buf) + return DBG_STATUS_VIRT_MEM_ALLOC_FAILED; + + /* Decode feature opcodes to string on temp buf */ + rc = qed_features_lookup[feature_idx]. + print_results(p_hwfn, (u32 *)feature->dump_buf, + feature->dumped_dwords, text_buf); + if (rc != DBG_STATUS_OK) { + vfree(text_buf); + return rc; + } + + /* Replace the original null character with a '\n' character. + * The bytes that were added as a result of the dword alignment are also + * padded with '\n' characters. + */ + for (i = null_char_pos; i < text_size_bytes; i++) + text_buf[i] = '\n'; + + /* Dump printable feature to log */ + if (p_hwfn->cdev->dbg_params.print_data) + qed_dbg_print_feature(text_buf, text_size_bytes); + + /* Free the old dump_buf and point the dump_buf to the newly allocagted + * and formatted text buffer. + */ + vfree(feature->dump_buf); + feature->dump_buf = text_buf; + feature->buf_size = text_size_bytes; + feature->dumped_dwords = text_size_bytes / 4; + return rc; +} + +/* Generic function for performing the dump of a debug feature. */ +enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + enum qed_dbg_features feature_idx) +{ + struct qed_dbg_feature *feature = + &p_hwfn->cdev->dbg_params.features[feature_idx]; + u32 buf_size_dwords; + enum dbg_status rc; + + DP_NOTICE(p_hwfn->cdev, "Collecting a debug feature [\"%s\"]\n", + qed_features_lookup[feature_idx].name); + + /* Dump_buf was already allocated need to free (this can happen if dump + * was called but file was never read). + * We can't use the buffer as is since size may have changed. + */ + if (feature->dump_buf) { + vfree(feature->dump_buf); + feature->dump_buf = NULL; + } + + /* Get buffer size from hsi, allocate accordingly, and perform the + * dump. + */ + rc = qed_features_lookup[feature_idx].get_size(p_hwfn, p_ptt, + &buf_size_dwords); + if (rc != DBG_STATUS_OK) + return rc; + feature->buf_size = buf_size_dwords * sizeof(u32); + feature->dump_buf = vmalloc(feature->buf_size); + if (!feature->dump_buf) + return DBG_STATUS_VIRT_MEM_ALLOC_FAILED; + + rc = qed_features_lookup[feature_idx]. + perform_dump(p_hwfn, p_ptt, (u32 *)feature->dump_buf, + feature->buf_size / sizeof(u32), + &feature->dumped_dwords); + + /* If mcp is stuck we get DBG_STATUS_NVRAM_GET_IMAGE_FAILED error. + * In this case the buffer holds valid binary data, but we wont able + * to parse it (since parsing relies on data in NVRAM which is only + * accessible when MFW is responsive). skip the formatting but return + * success so that binary data is provided. + */ + if (rc == DBG_STATUS_NVRAM_GET_IMAGE_FAILED) + return DBG_STATUS_OK; + + if (rc != DBG_STATUS_OK) + return rc; + + /* Format output */ + rc = format_feature(p_hwfn, feature_idx); + return rc; +} + +int qed_dbg_grc(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes) +{ + return qed_dbg_feature(cdev, buffer, DBG_FEATURE_GRC, num_dumped_bytes); +} + +int qed_dbg_grc_size(struct qed_dev *cdev) +{ + return qed_dbg_feature_size(cdev, DBG_FEATURE_GRC); +} + +int qed_dbg_idle_chk(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes) +{ + return qed_dbg_feature(cdev, buffer, DBG_FEATURE_IDLE_CHK, + num_dumped_bytes); +} + +int qed_dbg_idle_chk_size(struct qed_dev *cdev) +{ + return qed_dbg_feature_size(cdev, DBG_FEATURE_IDLE_CHK); +} + +int qed_dbg_reg_fifo(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes) +{ + return qed_dbg_feature(cdev, buffer, DBG_FEATURE_REG_FIFO, + num_dumped_bytes); +} + +int qed_dbg_reg_fifo_size(struct qed_dev *cdev) +{ + return qed_dbg_feature_size(cdev, DBG_FEATURE_REG_FIFO); +} + +int qed_dbg_igu_fifo(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes) +{ + return qed_dbg_feature(cdev, buffer, DBG_FEATURE_IGU_FIFO, + num_dumped_bytes); +} + +int qed_dbg_igu_fifo_size(struct qed_dev *cdev) +{ + return qed_dbg_feature_size(cdev, DBG_FEATURE_IGU_FIFO); +} + +int qed_dbg_protection_override(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes) +{ + return qed_dbg_feature(cdev, buffer, DBG_FEATURE_PROTECTION_OVERRIDE, + num_dumped_bytes); +} + +int qed_dbg_protection_override_size(struct qed_dev *cdev) +{ + return qed_dbg_feature_size(cdev, DBG_FEATURE_PROTECTION_OVERRIDE); +} + +int qed_dbg_fw_asserts(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes) +{ + return qed_dbg_feature(cdev, buffer, DBG_FEATURE_FW_ASSERTS, + num_dumped_bytes); +} + +int qed_dbg_fw_asserts_size(struct qed_dev *cdev) +{ + return qed_dbg_feature_size(cdev, DBG_FEATURE_FW_ASSERTS); +} + +int qed_dbg_mcp_trace(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes) +{ + return qed_dbg_feature(cdev, buffer, DBG_FEATURE_MCP_TRACE, + num_dumped_bytes); +} + +int qed_dbg_mcp_trace_size(struct qed_dev *cdev) +{ + return qed_dbg_feature_size(cdev, DBG_FEATURE_MCP_TRACE); +} + +/* Defines the amount of bytes allocated for recording the length of debugfs + * feature buffer. + */ +#define REGDUMP_HEADER_SIZE sizeof(u32) +#define REGDUMP_HEADER_FEATURE_SHIFT 24 +#define REGDUMP_HEADER_ENGINE_SHIFT 31 +#define REGDUMP_HEADER_OMIT_ENGINE_SHIFT 30 +enum debug_print_features { + OLD_MODE = 0, + IDLE_CHK = 1, + GRC_DUMP = 2, + MCP_TRACE = 3, + REG_FIFO = 4, + PROTECTION_OVERRIDE = 5, + IGU_FIFO = 6, + PHY = 7, + FW_ASSERTS = 8, +}; + +static u32 qed_calc_regdump_header(enum debug_print_features feature, + int engine, u32 feature_size, u8 omit_engine) +{ + /* Insert the engine, feature and mode inside the header and combine it + * with feature size. + */ + return feature_size | (feature << REGDUMP_HEADER_FEATURE_SHIFT) | + (omit_engine << REGDUMP_HEADER_OMIT_ENGINE_SHIFT) | + (engine << REGDUMP_HEADER_ENGINE_SHIFT); +} + +int qed_dbg_all_data(struct qed_dev *cdev, void *buffer) +{ + u8 cur_engine, omit_engine = 0, org_engine; + u32 offset = 0, feature_size; + int rc; + + if (cdev->num_hwfns == 1) + omit_engine = 1; + + org_engine = qed_get_debug_engine(cdev); + for (cur_engine = 0; cur_engine < cdev->num_hwfns; cur_engine++) { + /* Collect idle_chks and grcDump for each hw function */ + DP_VERBOSE(cdev, QED_MSG_DEBUG, + "obtaining idle_chk and grcdump for current engine\n"); + qed_set_debug_engine(cdev, cur_engine); + + /* First idle_chk */ + rc = qed_dbg_idle_chk(cdev, (u8 *)buffer + offset + + REGDUMP_HEADER_SIZE, &feature_size); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(IDLE_CHK, cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else { + DP_ERR(cdev, "qed_dbg_idle_chk failed. rc = %d\n", rc); + } + + /* Second idle_chk */ + rc = qed_dbg_idle_chk(cdev, (u8 *)buffer + offset + + REGDUMP_HEADER_SIZE, &feature_size); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(IDLE_CHK, cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else { + DP_ERR(cdev, "qed_dbg_idle_chk failed. rc = %d\n", rc); + } + + /* reg_fifo dump */ + rc = qed_dbg_reg_fifo(cdev, (u8 *)buffer + offset + + REGDUMP_HEADER_SIZE, &feature_size); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(REG_FIFO, cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else { + DP_ERR(cdev, "qed_dbg_reg_fifo failed. rc = %d\n", rc); + } + + /* igu_fifo dump */ + rc = qed_dbg_igu_fifo(cdev, (u8 *)buffer + offset + + REGDUMP_HEADER_SIZE, &feature_size); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(IGU_FIFO, cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else { + DP_ERR(cdev, "qed_dbg_igu_fifo failed. rc = %d", rc); + } + + /* protection_override dump */ + rc = qed_dbg_protection_override(cdev, (u8 *)buffer + offset + + REGDUMP_HEADER_SIZE, + &feature_size); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(PROTECTION_OVERRIDE, + cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else { + DP_ERR(cdev, + "qed_dbg_protection_override failed. rc = %d\n", + rc); + } + + /* fw_asserts dump */ + rc = qed_dbg_fw_asserts(cdev, (u8 *)buffer + offset + + REGDUMP_HEADER_SIZE, &feature_size); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(FW_ASSERTS, cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else { + DP_ERR(cdev, "qed_dbg_fw_asserts failed. rc = %d\n", + rc); + } + + /* GRC dump - must be last because when mcp stuck it will + * clutter idle_chk, reg_fifo, ... + */ + rc = qed_dbg_grc(cdev, (u8 *)buffer + offset + + REGDUMP_HEADER_SIZE, &feature_size); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(GRC_DUMP, cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else { + DP_ERR(cdev, "qed_dbg_grc failed. rc = %d", rc); + } + } + + /* mcp_trace */ + rc = qed_dbg_mcp_trace(cdev, (u8 *)buffer + offset + + REGDUMP_HEADER_SIZE, &feature_size); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(MCP_TRACE, cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else { + DP_ERR(cdev, "qed_dbg_mcp_trace failed. rc = %d\n", rc); + } + + qed_set_debug_engine(cdev, org_engine); + + return 0; +} + +int qed_dbg_all_data_size(struct qed_dev *cdev) +{ + u8 cur_engine, org_engine; + u32 regs_len = 0; + + org_engine = qed_get_debug_engine(cdev); + for (cur_engine = 0; cur_engine < cdev->num_hwfns; cur_engine++) { + /* Engine specific */ + DP_VERBOSE(cdev, QED_MSG_DEBUG, + "calculating idle_chk and grcdump register length for current engine\n"); + qed_set_debug_engine(cdev, cur_engine); + regs_len += REGDUMP_HEADER_SIZE + qed_dbg_idle_chk_size(cdev) + + REGDUMP_HEADER_SIZE + qed_dbg_idle_chk_size(cdev) + + REGDUMP_HEADER_SIZE + qed_dbg_grc_size(cdev) + + REGDUMP_HEADER_SIZE + qed_dbg_reg_fifo_size(cdev) + + REGDUMP_HEADER_SIZE + qed_dbg_igu_fifo_size(cdev) + + REGDUMP_HEADER_SIZE + + qed_dbg_protection_override_size(cdev) + + REGDUMP_HEADER_SIZE + qed_dbg_fw_asserts_size(cdev); + } + + /* Engine common */ + regs_len += REGDUMP_HEADER_SIZE + qed_dbg_mcp_trace_size(cdev); + qed_set_debug_engine(cdev, org_engine); + + return regs_len; +} + +int qed_dbg_feature(struct qed_dev *cdev, void *buffer, + enum qed_dbg_features feature, u32 *num_dumped_bytes) +{ + struct qed_hwfn *p_hwfn = + &cdev->hwfns[cdev->dbg_params.engine_for_debug]; + struct qed_dbg_feature *qed_feature = + &cdev->dbg_params.features[feature]; + enum dbg_status dbg_rc; + struct qed_ptt *p_ptt; + int rc = 0; + + /* Acquire ptt */ + p_ptt = qed_ptt_acquire(p_hwfn); + if (!p_ptt) + return -EINVAL; + + /* Get dump */ + dbg_rc = qed_dbg_dump(p_hwfn, p_ptt, feature); + if (dbg_rc != DBG_STATUS_OK) { + DP_VERBOSE(cdev, QED_MSG_DEBUG, "%s\n", + qed_dbg_get_status_str(dbg_rc)); + *num_dumped_bytes = 0; + rc = -EINVAL; + goto out; + } + + DP_VERBOSE(cdev, QED_MSG_DEBUG, + "copying debugfs feature to external buffer\n"); + memcpy(buffer, qed_feature->dump_buf, qed_feature->buf_size); + *num_dumped_bytes = cdev->dbg_params.features[feature].dumped_dwords * + 4; + +out: + qed_ptt_release(p_hwfn, p_ptt); + return rc; +} + +int qed_dbg_feature_size(struct qed_dev *cdev, enum qed_dbg_features feature) +{ + struct qed_hwfn *p_hwfn = + &cdev->hwfns[cdev->dbg_params.engine_for_debug]; + struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn); + struct qed_dbg_feature *qed_feature = + &cdev->dbg_params.features[feature]; + u32 buf_size_dwords; + enum dbg_status rc; + + if (!p_ptt) + return -EINVAL; + + rc = qed_features_lookup[feature].get_size(p_hwfn, p_ptt, + &buf_size_dwords); + if (rc != DBG_STATUS_OK) + buf_size_dwords = 0; + + qed_ptt_release(p_hwfn, p_ptt); + qed_feature->buf_size = buf_size_dwords * sizeof(u32); + return qed_feature->buf_size; +} + +u8 qed_get_debug_engine(struct qed_dev *cdev) +{ + return cdev->dbg_params.engine_for_debug; +} + +void qed_set_debug_engine(struct qed_dev *cdev, int engine_number) +{ + DP_VERBOSE(cdev, QED_MSG_DEBUG, "set debug engine to %d\n", + engine_number); + cdev->dbg_params.engine_for_debug = engine_number; +} + +void qed_dbg_pf_init(struct qed_dev *cdev) +{ + const u8 *dbg_values; + + /* Debug values are after init values. + * The offset is the first dword of the file. + */ + dbg_values = cdev->firmware->data + *(u32 *)cdev->firmware->data; + qed_dbg_set_bin_ptr((u8 *)dbg_values); + qed_dbg_user_set_bin_ptr((u8 *)dbg_values); +} + +void qed_dbg_pf_exit(struct qed_dev *cdev) +{ + struct qed_dbg_feature *feature = NULL; + enum qed_dbg_features feature_idx; + + /* Debug features' buffers may be allocated if debug feature was used + * but dump wasn't called. + */ + for (feature_idx = 0; feature_idx < DBG_FEATURE_NUM; feature_idx++) { + feature = &cdev->dbg_params.features[feature_idx]; + if (feature->dump_buf) { + vfree(feature->dump_buf); + feature->dump_buf = NULL; + } + } +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.h b/drivers/net/ethernet/qlogic/qed/qed_debug.h new file mode 100644 index 000000000000..f872d7324814 --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.h @@ -0,0 +1,54 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QED_DEBUGFS_H +#define _QED_DEBUGFS_H + +enum qed_dbg_features { + DBG_FEATURE_GRC, + DBG_FEATURE_IDLE_CHK, + DBG_FEATURE_MCP_TRACE, + DBG_FEATURE_REG_FIFO, + DBG_FEATURE_IGU_FIFO, + DBG_FEATURE_PROTECTION_OVERRIDE, + DBG_FEATURE_FW_ASSERTS, + DBG_FEATURE_NUM +}; + +int qed_dbg_grc(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes); +int qed_dbg_grc_size(struct qed_dev *cdev); +int qed_dbg_idle_chk(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes); +int qed_dbg_idle_chk_size(struct qed_dev *cdev); +int qed_dbg_reg_fifo(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes); +int qed_dbg_reg_fifo_size(struct qed_dev *cdev); +int qed_dbg_igu_fifo(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes); +int qed_dbg_igu_fifo_size(struct qed_dev *cdev); +int qed_dbg_protection_override(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes); +int qed_dbg_protection_override_size(struct qed_dev *cdev); +int qed_dbg_fw_asserts(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes); +int qed_dbg_fw_asserts_size(struct qed_dev *cdev); +int qed_dbg_mcp_trace(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes); +int qed_dbg_mcp_trace_size(struct qed_dev *cdev); +int qed_dbg_all_data(struct qed_dev *cdev, void *buffer); +int qed_dbg_all_data_size(struct qed_dev *cdev); +u8 qed_get_debug_engine(struct qed_dev *cdev); +void qed_set_debug_engine(struct qed_dev *cdev, int engine_number); +int qed_dbg_feature(struct qed_dev *cdev, void *buffer, + enum qed_dbg_features feature, u32 *num_dumped_bytes); +int qed_dbg_feature_size(struct qed_dev *cdev, enum qed_dbg_features feature); + +void qed_dbg_pf_init(struct qed_dev *cdev); +void qed_dbg_pf_exit(struct qed_dev *cdev); + +#endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 855691f18412..2777d5bb4380 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -1728,13 +1728,6 @@ enum bin_dbg_buffer_type { MAX_BIN_DBG_BUFFER_TYPE }; -/* Chip IDs */ -enum chip_ids { - CHIP_RESERVED, - CHIP_BB_B0, - CHIP_RESERVED2, - MAX_CHIP_IDS -}; /* Attention bit mapping */ struct dbg_attn_bit_mapping { @@ -1813,6 +1806,371 @@ enum dbg_attn_type { MAX_DBG_ATTN_TYPE }; +/* condition header for registers dump */ +struct dbg_dump_cond_hdr { + struct dbg_mode_hdr mode; /* Mode header */ + u8 block_id; /* block ID */ + u8 data_size; /* size in dwords of the data following this header */ +}; + +/* memory data for registers dump */ +struct dbg_dump_mem { + __le32 dword0; +#define DBG_DUMP_MEM_ADDRESS_MASK 0xFFFFFF +#define DBG_DUMP_MEM_ADDRESS_SHIFT 0 +#define DBG_DUMP_MEM_MEM_GROUP_ID_MASK 0xFF +#define DBG_DUMP_MEM_MEM_GROUP_ID_SHIFT 24 + __le32 dword1; +#define DBG_DUMP_MEM_LENGTH_MASK 0xFFFFFF +#define DBG_DUMP_MEM_LENGTH_SHIFT 0 +#define DBG_DUMP_MEM_RESERVED_MASK 0xFF +#define DBG_DUMP_MEM_RESERVED_SHIFT 24 +}; + +/* register data for registers dump */ +struct dbg_dump_reg { + __le32 data; +#define DBG_DUMP_REG_ADDRESS_MASK 0xFFFFFF /* register address (in dwords) */ +#define DBG_DUMP_REG_ADDRESS_SHIFT 0 +#define DBG_DUMP_REG_LENGTH_MASK 0xFF /* register size (in dwords) */ +#define DBG_DUMP_REG_LENGTH_SHIFT 24 +}; + +/* split header for registers dump */ +struct dbg_dump_split_hdr { + __le32 hdr; +#define DBG_DUMP_SPLIT_HDR_DATA_SIZE_MASK 0xFFFFFF +#define DBG_DUMP_SPLIT_HDR_DATA_SIZE_SHIFT 0 +#define DBG_DUMP_SPLIT_HDR_SPLIT_TYPE_ID_MASK 0xFF +#define DBG_DUMP_SPLIT_HDR_SPLIT_TYPE_ID_SHIFT 24 +}; + +/* condition header for idle check */ +struct dbg_idle_chk_cond_hdr { + struct dbg_mode_hdr mode; /* Mode header */ + __le16 data_size; /* size in dwords of the data following this header */ +}; + +/* Idle Check condition register */ +struct dbg_idle_chk_cond_reg { + __le32 data; +#define DBG_IDLE_CHK_COND_REG_ADDRESS_MASK 0xFFFFFF +#define DBG_IDLE_CHK_COND_REG_ADDRESS_SHIFT 0 +#define DBG_IDLE_CHK_COND_REG_BLOCK_ID_MASK 0xFF +#define DBG_IDLE_CHK_COND_REG_BLOCK_ID_SHIFT 24 + __le16 num_entries; /* number of registers entries to check */ + u8 entry_size; /* size of registers entry (in dwords) */ + u8 start_entry; /* index of the first entry to check */ +}; + +/* Idle Check info register */ +struct dbg_idle_chk_info_reg { + __le32 data; +#define DBG_IDLE_CHK_INFO_REG_ADDRESS_MASK 0xFFFFFF +#define DBG_IDLE_CHK_INFO_REG_ADDRESS_SHIFT 0 +#define DBG_IDLE_CHK_INFO_REG_BLOCK_ID_MASK 0xFF +#define DBG_IDLE_CHK_INFO_REG_BLOCK_ID_SHIFT 24 + __le16 size; /* register size in dwords */ + struct dbg_mode_hdr mode; /* Mode header */ +}; + +/* Idle Check register */ +union dbg_idle_chk_reg { + struct dbg_idle_chk_cond_reg cond_reg; /* condition register */ + struct dbg_idle_chk_info_reg info_reg; /* info register */ +}; + +/* Idle Check result header */ +struct dbg_idle_chk_result_hdr { + __le16 rule_id; /* Failing rule index */ + __le16 mem_entry_id; /* Failing memory entry index */ + u8 num_dumped_cond_regs; /* number of dumped condition registers */ + u8 num_dumped_info_regs; /* number of dumped condition registers */ + u8 severity; /* from dbg_idle_chk_severity_types enum */ + u8 reserved; +}; + +/* Idle Check result register header */ +struct dbg_idle_chk_result_reg_hdr { + u8 data; +#define DBG_IDLE_CHK_RESULT_REG_HDR_IS_MEM_MASK 0x1 +#define DBG_IDLE_CHK_RESULT_REG_HDR_IS_MEM_SHIFT 0 +#define DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID_MASK 0x7F +#define DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID_SHIFT 1 + u8 start_entry; /* index of the first checked entry */ + __le16 size; /* register size in dwords */ +}; + +/* Idle Check rule */ +struct dbg_idle_chk_rule { + __le16 rule_id; /* Idle Check rule ID */ + u8 severity; /* value from dbg_idle_chk_severity_types enum */ + u8 cond_id; /* Condition ID */ + u8 num_cond_regs; /* number of condition registers */ + u8 num_info_regs; /* number of info registers */ + u8 num_imms; /* number of immediates in the condition */ + u8 reserved1; + __le16 reg_offset; /* offset of this rules registers in the idle check + * register array (in dbg_idle_chk_reg units). + */ + __le16 imm_offset; /* offset of this rules immediate values in the + * immediate values array (in dwords). + */ +}; + +/* Idle Check rule parsing data */ +struct dbg_idle_chk_rule_parsing_data { + __le32 data; +#define DBG_IDLE_CHK_RULE_PARSING_DATA_HAS_FW_MSG_MASK 0x1 +#define DBG_IDLE_CHK_RULE_PARSING_DATA_HAS_FW_MSG_SHIFT 0 +#define DBG_IDLE_CHK_RULE_PARSING_DATA_STR_OFFSET_MASK 0x7FFFFFFF +#define DBG_IDLE_CHK_RULE_PARSING_DATA_STR_OFFSET_SHIFT 1 +}; + +/* idle check severity types */ +enum dbg_idle_chk_severity_types { + /* idle check failure should cause an error */ + IDLE_CHK_SEVERITY_ERROR, + /* idle check failure should cause an error only if theres no traffic */ + IDLE_CHK_SEVERITY_ERROR_NO_TRAFFIC, + /* idle check failure should cause a warning */ + IDLE_CHK_SEVERITY_WARNING, + MAX_DBG_IDLE_CHK_SEVERITY_TYPES +}; + +/* Debug Bus block data */ +struct dbg_bus_block_data { + u8 enabled; /* Indicates if the block is enabled for recording (0/1) */ + u8 hw_id; /* HW ID associated with the block */ + u8 line_num; /* Debug line number to select */ + u8 right_shift; /* Number of units to right the debug data (0-3) */ + u8 cycle_en; /* 4-bit value: bit i set -> unit i is enabled. */ + u8 force_valid; /* 4-bit value: bit i set -> unit i is forced valid. */ + u8 force_frame; /* 4-bit value: bit i set -> unit i frame bit is forced. + */ + u8 reserved; +}; + +/* Debug Bus Clients */ +enum dbg_bus_clients { + DBG_BUS_CLIENT_RBCN, + DBG_BUS_CLIENT_RBCP, + DBG_BUS_CLIENT_RBCR, + DBG_BUS_CLIENT_RBCT, + DBG_BUS_CLIENT_RBCU, + DBG_BUS_CLIENT_RBCF, + DBG_BUS_CLIENT_RBCX, + DBG_BUS_CLIENT_RBCS, + DBG_BUS_CLIENT_RBCH, + DBG_BUS_CLIENT_RBCZ, + DBG_BUS_CLIENT_OTHER_ENGINE, + DBG_BUS_CLIENT_TIMESTAMP, + DBG_BUS_CLIENT_CPU, + DBG_BUS_CLIENT_RBCY, + DBG_BUS_CLIENT_RBCQ, + DBG_BUS_CLIENT_RBCM, + DBG_BUS_CLIENT_RBCB, + DBG_BUS_CLIENT_RBCW, + DBG_BUS_CLIENT_RBCV, + MAX_DBG_BUS_CLIENTS +}; + +/* Debug Bus memory address */ +struct dbg_bus_mem_addr { + __le32 lo; + __le32 hi; +}; + +/* Debug Bus PCI buffer data */ +struct dbg_bus_pci_buf_data { + struct dbg_bus_mem_addr phys_addr; /* PCI buffer physical address */ + struct dbg_bus_mem_addr virt_addr; /* PCI buffer virtual address */ + __le32 size; /* PCI buffer size in bytes */ +}; + +/* Debug Bus Storm EID range filter params */ +struct dbg_bus_storm_eid_range_params { + u8 min; /* Minimal event ID to filter on */ + u8 max; /* Maximal event ID to filter on */ +}; + +/* Debug Bus Storm EID mask filter params */ +struct dbg_bus_storm_eid_mask_params { + u8 val; /* Event ID value */ + u8 mask; /* Event ID mask. 1s in the mask = dont care bits. */ +}; + +/* Debug Bus Storm EID filter params */ +union dbg_bus_storm_eid_params { + struct dbg_bus_storm_eid_range_params range; + struct dbg_bus_storm_eid_mask_params mask; +}; + +/* Debug Bus Storm data */ +struct dbg_bus_storm_data { + u8 fast_enabled; + u8 fast_mode; + u8 slow_enabled; + u8 slow_mode; + u8 hw_id; + u8 eid_filter_en; + u8 eid_range_not_mask; + u8 cid_filter_en; + union dbg_bus_storm_eid_params eid_filter_params; + __le16 reserved; + __le32 cid; +}; + +/* Debug Bus data */ +struct dbg_bus_data { + __le32 app_version; /* The tools version number of the application */ + u8 state; /* The current debug bus state */ + u8 hw_dwords; /* HW dwords per cycle */ + u8 next_hw_id; /* Next HW ID to be associated with an input */ + u8 num_enabled_blocks; /* Number of blocks enabled for recording */ + u8 num_enabled_storms; /* Number of Storms enabled for recording */ + u8 target; /* Output target */ + u8 next_trigger_state; /* ID of next trigger state to be added */ + u8 next_constraint_id; /* ID of next filter/trigger constraint to be + * added. + */ + u8 one_shot_en; /* Indicates if one-shot mode is enabled (0/1) */ + u8 grc_input_en; /* Indicates if GRC recording is enabled (0/1) */ + u8 timestamp_input_en; /* Indicates if timestamp recording is enabled + * (0/1). + */ + u8 filter_en; /* Indicates if the recording filter is enabled (0/1) */ + u8 trigger_en; /* Indicates if the recording trigger is enabled (0/1) */ + u8 adding_filter; /* If true, the next added constraint belong to the + * filter. Otherwise, it belongs to the last added + * trigger state. Valid only if either filter or + * triggers are enabled. + */ + u8 filter_pre_trigger; /* Indicates if the recording filter should be + * applied before the trigger. Valid only if both + * filter and trigger are enabled (0/1). + */ + u8 filter_post_trigger; /* Indicates if the recording filter should be + * applied after the trigger. Valid only if both + * filter and trigger are enabled (0/1). + */ + u8 unify_inputs; /* If true, all inputs are associated with HW ID 0. + * Otherwise, each input is assigned a different HW ID + * (0/1). + */ + u8 rcv_from_other_engine; /* Indicates if the other engine sends it NW + * recording to this engine (0/1). + */ + struct dbg_bus_pci_buf_data pci_buf; /* Debug Bus PCI buffer data. Valid + * only when the target is + * DBG_BUS_TARGET_ID_PCI. + */ + __le16 reserved; + struct dbg_bus_block_data blocks[80];/* Debug Bus data for each block */ + struct dbg_bus_storm_data storms[6]; /* Debug Bus data for each block */ +}; + +/* Debug bus frame modes */ +enum dbg_bus_frame_modes { + DBG_BUS_FRAME_MODE_0HW_4ST = 0, /* 0 HW dwords, 4 Storm dwords */ + DBG_BUS_FRAME_MODE_4HW_0ST = 3, /* 4 HW dwords, 0 Storm dwords */ + DBG_BUS_FRAME_MODE_8HW_0ST = 4, /* 8 HW dwords, 0 Storm dwords */ + MAX_DBG_BUS_FRAME_MODES +}; + +/* Debug bus states */ +enum dbg_bus_states { + DBG_BUS_STATE_IDLE, /* debug bus idle state (not recording) */ + DBG_BUS_STATE_READY, /* debug bus is ready for configuration and + * recording. + */ + DBG_BUS_STATE_RECORDING, /* debug bus is currently recording */ + DBG_BUS_STATE_STOPPED, /* debug bus recording has stopped */ + MAX_DBG_BUS_STATES +}; + +/* Debug bus target IDs */ +enum dbg_bus_targets { + /* records debug bus to DBG block internal buffer */ + DBG_BUS_TARGET_ID_INT_BUF, + /* records debug bus to the NW */ + DBG_BUS_TARGET_ID_NIG, + /* records debug bus to a PCI buffer */ + DBG_BUS_TARGET_ID_PCI, + MAX_DBG_BUS_TARGETS +}; + +/* GRC Dump data */ +struct dbg_grc_data { + __le32 param_val[40]; /* Value of each GRC parameter. Array size must + * match the enum dbg_grc_params. + */ + u8 param_set_by_user[40]; /* Indicates for each GRC parameter if it was + * set by the user (0/1). Array size must + * match the enum dbg_grc_params. + */ +}; + +/* Debug GRC params */ +enum dbg_grc_params { + DBG_GRC_PARAM_DUMP_TSTORM, /* dump Tstorm memories (0/1) */ + DBG_GRC_PARAM_DUMP_MSTORM, /* dump Mstorm memories (0/1) */ + DBG_GRC_PARAM_DUMP_USTORM, /* dump Ustorm memories (0/1) */ + DBG_GRC_PARAM_DUMP_XSTORM, /* dump Xstorm memories (0/1) */ + DBG_GRC_PARAM_DUMP_YSTORM, /* dump Ystorm memories (0/1) */ + DBG_GRC_PARAM_DUMP_PSTORM, /* dump Pstorm memories (0/1) */ + DBG_GRC_PARAM_DUMP_REGS, /* dump non-memory registers (0/1) */ + DBG_GRC_PARAM_DUMP_RAM, /* dump Storm internal RAMs (0/1) */ + DBG_GRC_PARAM_DUMP_PBUF, /* dump Storm passive buffer (0/1) */ + DBG_GRC_PARAM_DUMP_IOR, /* dump Storm IORs (0/1) */ + DBG_GRC_PARAM_DUMP_VFC, /* dump VFC memories (0/1) */ + DBG_GRC_PARAM_DUMP_CM_CTX, /* dump CM contexts (0/1) */ + DBG_GRC_PARAM_DUMP_PXP, /* dump PXP memories (0/1) */ + DBG_GRC_PARAM_DUMP_RSS, /* dump RSS memories (0/1) */ + DBG_GRC_PARAM_DUMP_CAU, /* dump CAU memories (0/1) */ + DBG_GRC_PARAM_DUMP_QM, /* dump QM memories (0/1) */ + DBG_GRC_PARAM_DUMP_MCP, /* dump MCP memories (0/1) */ + DBG_GRC_PARAM_RESERVED, /* reserved */ + DBG_GRC_PARAM_DUMP_CFC, /* dump CFC memories (0/1) */ + DBG_GRC_PARAM_DUMP_IGU, /* dump IGU memories (0/1) */ + DBG_GRC_PARAM_DUMP_BRB, /* dump BRB memories (0/1) */ + DBG_GRC_PARAM_DUMP_BTB, /* dump BTB memories (0/1) */ + DBG_GRC_PARAM_DUMP_BMB, /* dump BMB memories (0/1) */ + DBG_GRC_PARAM_DUMP_NIG, /* dump NIG memories (0/1) */ + DBG_GRC_PARAM_DUMP_MULD, /* dump MULD memories (0/1) */ + DBG_GRC_PARAM_DUMP_PRS, /* dump PRS memories (0/1) */ + DBG_GRC_PARAM_DUMP_DMAE, /* dump PRS memories (0/1) */ + DBG_GRC_PARAM_DUMP_TM, /* dump TM (timers) memories (0/1) */ + DBG_GRC_PARAM_DUMP_SDM, /* dump SDM memories (0/1) */ + DBG_GRC_PARAM_DUMP_DIF, /* dump DIF memories (0/1) */ + DBG_GRC_PARAM_DUMP_STATIC, /* dump static debug data (0/1) */ + DBG_GRC_PARAM_UNSTALL, /* un-stall Storms after dump (0/1) */ + DBG_GRC_PARAM_NUM_LCIDS, /* number of LCIDs (0..320) */ + DBG_GRC_PARAM_NUM_LTIDS, /* number of LTIDs (0..320) */ + /* preset: exclude all memories from dump (1 only) */ + DBG_GRC_PARAM_EXCLUDE_ALL, + /* preset: include memories for crash dump (1 only) */ + DBG_GRC_PARAM_CRASH, + /* perform dump only if MFW is responding (0/1) */ + DBG_GRC_PARAM_PARITY_SAFE, + DBG_GRC_PARAM_DUMP_CM, /* dump CM memories (0/1) */ + DBG_GRC_PARAM_DUMP_PHY, /* dump PHY memories (0/1) */ + MAX_DBG_GRC_PARAMS +}; + +/* Debug reset registers */ +enum dbg_reset_regs { + DBG_RESET_REG_MISCS_PL_UA, + DBG_RESET_REG_MISCS_PL_HV, + DBG_RESET_REG_MISCS_PL_HV_2, + DBG_RESET_REG_MISC_PL_UA, + DBG_RESET_REG_MISC_PL_HV, + DBG_RESET_REG_MISC_PL_PDA_VMAIN_1, + DBG_RESET_REG_MISC_PL_PDA_VMAIN_2, + DBG_RESET_REG_MISC_PL_PDA_VAUX, + MAX_DBG_RESET_REGS +}; + /* Debug status codes */ enum dbg_status { DBG_STATUS_OK, @@ -1869,6 +2227,41 @@ enum dbg_status { MAX_DBG_STATUS }; +/* Debug Storms IDs */ +enum dbg_storms { + DBG_TSTORM_ID, + DBG_MSTORM_ID, + DBG_USTORM_ID, + DBG_XSTORM_ID, + DBG_YSTORM_ID, + DBG_PSTORM_ID, + MAX_DBG_STORMS +}; + +/* Idle Check data */ +struct idle_chk_data { + __le32 buf_size; /* Idle check buffer size in dwords */ + u8 buf_size_set; /* Indicates if the idle check buffer size was set + * (0/1). + */ + u8 reserved1; + __le16 reserved2; +}; + +/* Debug Tools data (per HW function) */ +struct dbg_tools_data { + struct dbg_grc_data grc; /* GRC Dump data */ + struct dbg_bus_data bus; /* Debug Bus data */ + struct idle_chk_data idle_chk; /* Idle Check data */ + u8 mode_enable[40]; /* Indicates if a mode is enabled (0/1) */ + u8 block_in_reset[80]; /* Indicates if a block is in reset state (0/1). + */ + u8 chip_id; /* Chip ID (from enum chip_ids) */ + u8 platform_id; /* Platform ID (from enum platform_ids) */ + u8 initialized; /* Indicates if the data was initialized */ + u8 reserved; +}; + /********************************/ /* HSI Init Functions constants */ /********************************/ @@ -1948,15 +2341,50 @@ struct init_qm_vport_params { /* Max size in dwords of a zipped array */ #define MAX_ZIPPED_SIZE 8192 +struct fw_asserts_ram_section { + __le16 section_ram_line_offset; + __le16 section_ram_line_size; + u8 list_dword_offset; + u8 list_element_dword_size; + u8 list_num_elements; + u8 list_next_index_dword_offset; +}; + +struct fw_ver_num { + u8 major; /* Firmware major version number */ + u8 minor; /* Firmware minor version number */ + u8 rev; /* Firmware revision version number */ + u8 eng; /* Firmware engineering version number (for bootleg versions) */ +}; + +struct fw_ver_info { + __le16 tools_ver; /* Tools version number */ + u8 image_id; /* FW image ID (e.g. main) */ + u8 reserved1; + struct fw_ver_num num; /* FW version number */ + __le32 timestamp; /* FW Timestamp in unix time (sec. since 1970) */ + __le32 reserved2; +}; + +struct fw_info { + struct fw_ver_info ver; + struct fw_asserts_ram_section fw_asserts_section; +}; + +struct fw_info_location { + __le32 grc_addr; + __le32 size; +}; + enum init_modes { MODE_RESERVED, MODE_BB_B0, - MODE_RESERVED2, + MODE_K2, MODE_ASIC, + MODE_RESERVED2, MODE_RESERVED3, MODE_RESERVED4, MODE_RESERVED5, - MODE_RESERVED6, MODE_SF, MODE_MF_SD, MODE_MF_SI, @@ -1965,7 +2393,7 @@ enum init_modes { MODE_PORTS_PER_ENG_4, MODE_100G, MODE_40G, - MODE_RESERVED7, + MODE_RESERVED6, MAX_INIT_MODES }; @@ -2223,8 +2651,276 @@ struct iro { __le16 size; }; +/***************************** Public Functions *******************************/ +/** + * @brief qed_dbg_set_bin_ptr - Sets a pointer to the binary data with debug + * arrays. + * + * @param bin_ptr - a pointer to the binary data with debug arrays. + */ +enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr); +/** + * @brief qed_dbg_grc_get_dump_buf_size - Returns the required buffer size for + * GRC Dump. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param buf_size - OUT: required buffer size (in dwords) for the GRC Dump + * data. + * + * @return error if one of the following holds: + * - the version wasn't set + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_grc_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size); +/** + * @brief qed_dbg_grc_dump - Dumps GRC data into the specified buffer. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param dump_buf - Pointer to write the collected GRC data into. + * @param buf_size_in_dwords - Size of the specified buffer in dwords. + * @param num_dumped_dwords - OUT: number of dumped dwords. + * + * @return error if one of the following holds: + * - the version wasn't set + * - the specified dump buffer is too small + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_grc_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords); +/** + * @brief qed_dbg_idle_chk_get_dump_buf_size - Returns the required buffer size + * for idle check results. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param buf_size - OUT: required buffer size (in dwords) for the idle check + * data. + * + * @return error if one of the following holds: + * - the version wasn't set + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_idle_chk_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size); +/** + * @brief qed_dbg_idle_chk_dump - Performs idle check and writes the results + * into the specified buffer. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param dump_buf - Pointer to write the idle check data into. + * @param buf_size_in_dwords - Size of the specified buffer in dwords. + * @param num_dumped_dwords - OUT: number of dumped dwords. + * + * @return error if one of the following holds: + * - the version wasn't set + * - the specified buffer is too small + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_idle_chk_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords); +/** + * @brief qed_dbg_mcp_trace_get_dump_buf_size - Returns the required buffer size + * for mcp trace results. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param buf_size - OUT: required buffer size (in dwords) for mcp trace data. + * + * @return error if one of the following holds: + * - the version wasn't set + * - the trace data in MCP scratchpad contain an invalid signature + * - the bundle ID in NVRAM is invalid + * - the trace meta data cannot be found (in NVRAM or image file) + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_mcp_trace_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size); +/** + * @brief qed_dbg_mcp_trace_dump - Performs mcp trace and writes the results + * into the specified buffer. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param dump_buf - Pointer to write the mcp trace data into. + * @param buf_size_in_dwords - Size of the specified buffer in dwords. + * @param num_dumped_dwords - OUT: number of dumped dwords. + * + * @return error if one of the following holds: + * - the version wasn't set + * - the specified buffer is too small + * - the trace data in MCP scratchpad contain an invalid signature + * - the bundle ID in NVRAM is invalid + * - the trace meta data cannot be found (in NVRAM or image file) + * - the trace meta data cannot be read (from NVRAM or image file) + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords); +/** + * @brief qed_dbg_reg_fifo_get_dump_buf_size - Returns the required buffer size + * for grc trace fifo results. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param buf_size - OUT: required buffer size (in dwords) for reg fifo data. + * + * @return error if one of the following holds: + * - the version wasn't set + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_reg_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size); +/** + * @brief qed_dbg_reg_fifo_dump - Reads the reg fifo and writes the results into + * the specified buffer. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param dump_buf - Pointer to write the reg fifo data into. + * @param buf_size_in_dwords - Size of the specified buffer in dwords. + * @param num_dumped_dwords - OUT: number of dumped dwords. + * + * @return error if one of the following holds: + * - the version wasn't set + * - the specified buffer is too small + * - DMAE transaction failed + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_reg_fifo_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords); +/** + * @brief qed_dbg_igu_fifo_get_dump_buf_size - Returns the required buffer size + * for the IGU fifo results. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param buf_size - OUT: required buffer size (in dwords) for the IGU fifo + * data. + * + * @return error if one of the following holds: + * - the version wasn't set + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_igu_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size); +/** + * @brief qed_dbg_igu_fifo_dump - Reads the IGU fifo and writes the results into + * the specified buffer. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param dump_buf - Pointer to write the IGU fifo data into. + * @param buf_size_in_dwords - Size of the specified buffer in dwords. + * @param num_dumped_dwords - OUT: number of dumped dwords. + * + * @return error if one of the following holds: + * - the version wasn't set + * - the specified buffer is too small + * - DMAE transaction failed + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_igu_fifo_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords); +/** + * @brief qed_dbg_protection_override_get_dump_buf_size - Returns the required + * buffer size for protection override window results. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param buf_size - OUT: required buffer size (in dwords) for protection + * override data. + * + * @return error if one of the following holds: + * - the version wasn't set + * Otherwise, returns ok. + */ +enum dbg_status +qed_dbg_protection_override_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size); +/** + * @brief qed_dbg_protection_override_dump - Reads protection override window + * entries and writes the results into the specified buffer. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param dump_buf - Pointer to write the protection override data into. + * @param buf_size_in_dwords - Size of the specified buffer in dwords. + * @param num_dumped_dwords - OUT: number of dumped dwords. + * + * @return error if one of the following holds: + * - the version wasn't set + * - the specified buffer is too small + * - DMAE transaction failed + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_protection_override_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords); +/** + * @brief qed_dbg_fw_asserts_get_dump_buf_size - Returns the required buffer + * size for FW Asserts results. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param buf_size - OUT: required buffer size (in dwords) for FW Asserts data. + * + * @return error if one of the following holds: + * - the version wasn't set + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_fw_asserts_get_dump_buf_size(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *buf_size); +/** + * @brief qed_dbg_fw_asserts_dump - Reads the FW Asserts and writes the results + * into the specified buffer. + * + * @param p_hwfn - HW device data + * @param p_ptt - Ptt window used for writing the registers. + * @param dump_buf - Pointer to write the FW Asserts data into. + * @param buf_size_in_dwords - Size of the specified buffer in dwords. + * @param num_dumped_dwords - OUT: number of dumped dwords. + * + * @return error if one of the following holds: + * - the version wasn't set + * - the specified buffer is too small + * Otherwise, returns ok. + */ +enum dbg_status qed_dbg_fw_asserts_dump(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *dump_buf, + u32 buf_size_in_dwords, + u32 *num_dumped_dwords); /** - * @brief qed_dbg_print_attn - Prints attention registers values in the specified results struct. + * @brief qed_dbg_print_attn - Prints attention registers values in the + * specified results struct. * * @param p_hwfn * @param results - Pointer to the attention read results @@ -2236,8 +2932,212 @@ struct iro { enum dbg_status qed_dbg_print_attn(struct qed_hwfn *p_hwfn, struct dbg_attn_block_result *results); +/******************************** Constants **********************************/ + #define MAX_NAME_LEN 16 +/***************************** Public Functions *******************************/ +/** + * @brief qed_dbg_user_set_bin_ptr - Sets a pointer to the binary data with + * debug arrays. + * + * @param bin_ptr - a pointer to the binary data with debug arrays. + */ +enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr); +/** + * @brief qed_dbg_get_status_str - Returns a string for the specified status. + * + * @param status - a debug status code. + * + * @return a string for the specified status + */ +const char *qed_dbg_get_status_str(enum dbg_status status); +/** + * @brief qed_get_idle_chk_results_buf_size - Returns the required buffer size + * for idle check results (in bytes). + * + * @param p_hwfn - HW device data + * @param dump_buf - idle check dump buffer. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed + * results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_get_idle_chk_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size); +/** + * @brief qed_print_idle_chk_results - Prints idle check results + * + * @param p_hwfn - HW device data + * @param dump_buf - idle check dump buffer. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf - buffer for printing the idle check results. + * @param num_errors - OUT: number of errors found in idle check. + * @param num_warnings - OUT: number of warnings found in idle check. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf, + u32 *num_errors, + u32 *num_warnings); +/** + * @brief qed_get_mcp_trace_results_buf_size - Returns the required buffer size + * for MCP Trace results (in bytes). + * + * @param p_hwfn - HW device data + * @param dump_buf - MCP Trace dump buffer. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed + * results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_get_mcp_trace_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size); +/** + * @brief qed_print_mcp_trace_results - Prints MCP Trace results + * + * @param p_hwfn - HW device data + * @param dump_buf - mcp trace dump buffer, starting from the header. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf - buffer for printing the mcp trace results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf); +/** + * @brief qed_get_reg_fifo_results_buf_size - Returns the required buffer size + * for reg_fifo results (in bytes). + * + * @param p_hwfn - HW device data + * @param dump_buf - reg fifo dump buffer. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed + * results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_get_reg_fifo_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size); +/** + * @brief qed_print_reg_fifo_results - Prints reg fifo results + * + * @param p_hwfn - HW device data + * @param dump_buf - reg fifo dump buffer, starting from the header. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf - buffer for printing the reg fifo results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_print_reg_fifo_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf); +/** + * @brief qed_get_igu_fifo_results_buf_size - Returns the required buffer size + * for igu_fifo results (in bytes). + * + * @param p_hwfn - HW device data + * @param dump_buf - IGU fifo dump buffer. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed + * results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_get_igu_fifo_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size); +/** + * @brief qed_print_igu_fifo_results - Prints IGU fifo results + * + * @param p_hwfn - HW device data + * @param dump_buf - IGU fifo dump buffer, starting from the header. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf - buffer for printing the IGU fifo results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_print_igu_fifo_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf); +/** + * @brief qed_get_protection_override_results_buf_size - Returns the required + * buffer size for protection override results (in bytes). + * + * @param p_hwfn - HW device data + * @param dump_buf - protection override dump buffer. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed + * results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status +qed_get_protection_override_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size); +/** + * @brief qed_print_protection_override_results - Prints protection override + * results. + * + * @param p_hwfn - HW device data + * @param dump_buf - protection override dump buffer, starting from the header. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf - buffer for printing the reg fifo results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_print_protection_override_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf); +/** + * @brief qed_get_fw_asserts_results_buf_size - Returns the required buffer size + * for FW Asserts results (in bytes). + * + * @param p_hwfn - HW device data + * @param dump_buf - FW Asserts dump buffer. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed + * results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_get_fw_asserts_results_buf_size(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + u32 *results_buf_size); +/** + * @brief qed_print_fw_asserts_results - Prints FW Asserts results + * + * @param p_hwfn - HW device data + * @param dump_buf - FW Asserts dump buffer, starting from the header. + * @param num_dumped_dwords - number of dwords that were dumped. + * @param results_buf - buffer for printing the FW Asserts results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_print_fw_asserts_results(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + u32 num_dumped_dwords, + char *results_buf); /* Win 2 */ #define GTT_BAR0_MAP_REG_IGU_CMD 0x00f000UL @@ -7039,6 +7939,35 @@ struct ystorm_iscsi_conn_ag_ctx { __le32 reg2; __le32 reg3; }; + +#define MFW_TRACE_SIGNATURE 0x25071946 + +/* The trace in the buffer */ +#define MFW_TRACE_EVENTID_MASK 0x00ffff +#define MFW_TRACE_PRM_SIZE_MASK 0x0f0000 +#define MFW_TRACE_PRM_SIZE_SHIFT 16 +#define MFW_TRACE_ENTRY_SIZE 3 + +struct mcp_trace { + u32 signature; /* Help to identify that the trace is valid */ + u32 size; /* the size of the trace buffer in bytes */ + u32 curr_level; /* 2 - all will be written to the buffer + * 1 - debug trace will not be written + * 0 - just errors will be written to the buffer + */ + u32 modules_mask[2]; /* a bit per module, 1 means write it, 0 means + * mask it. + */ + + /* Warning: the following pointers are assumed to be 32bits as they are + * used only in the MFW. + */ + u32 trace_prod; /* The next trace will be written to this offset */ + u32 trace_oldest; /* The oldest valid trace starts at this offset + * (usually very close after the current producer). + */ +}; + #define VF_MAX_STATIC 192 #define MCP_GLOB_PATH_MAX 2 @@ -7046,6 +7975,7 @@ struct ystorm_iscsi_conn_ag_ctx { #define MCP_GLOB_PORT_MAX 4 #define MCP_GLOB_FUNC_MAX 16 +typedef u32 offsize_t; /* In DWORDS !!! */ /* Offset from the beginning of the MCP scratchpad */ #define OFFSIZE_OFFSET_SHIFT 0 #define OFFSIZE_OFFSET_MASK 0x0000ffff @@ -7636,6 +8566,8 @@ struct public_drv_mb { #define DRV_MSG_CODE_NIG_DRAIN 0x30000000 #define DRV_MSG_CODE_VF_DISABLED_DONE 0xc0000000 #define DRV_MSG_CODE_CFG_VF_MSIX 0xc0010000 +#define DRV_MSG_CODE_NVM_GET_FILE_ATT 0x00030000 +#define DRV_MSG_CODE_NVM_READ_NVRAM 0x00050000 #define DRV_MSG_CODE_MCP_RESET 0x00090000 #define DRV_MSG_CODE_SET_VERSION 0x000f0000 #define DRV_MSG_CODE_MCP_HALT 0x00100000 @@ -7657,6 +8589,9 @@ struct public_drv_mb { #define DRV_MB_PARAM_UNLOAD_WOL_MCP 0x00000001 #define DRV_MB_PARAM_DCBX_NOTIFY_MASK 0x000000FF #define DRV_MB_PARAM_DCBX_NOTIFY_SHIFT 3 + +#define DRV_MB_PARAM_NVM_LEN_SHIFT 24 + #define DRV_MB_PARAM_CFG_VF_MSIX_VF_ID_SHIFT 0 #define DRV_MB_PARAM_CFG_VF_MSIX_VF_ID_MASK 0x000000FF #define DRV_MB_PARAM_CFG_VF_MSIX_SB_NUM_SHIFT 8 @@ -7694,6 +8629,8 @@ struct public_drv_mb { #define FW_MSG_CODE_DRV_UNLOAD_FUNCTION 0x20130000 #define FW_MSG_CODE_DRV_UNLOAD_DONE 0x21100000 #define FW_MSG_CODE_DRV_CFG_VF_MSIX_DONE 0xb0010000 + +#define FW_MSG_CODE_NVM_OK 0x00010000 #define FW_MSG_CODE_OK 0x00160000 #define FW_MSG_SEQ_NUMBER_MASK 0x0000ffff @@ -7930,4 +8867,101 @@ struct nvm_cfg1 { struct nvm_cfg1_port port[MCP_GLOB_PORT_MAX]; struct nvm_cfg1_func func[MCP_GLOB_FUNC_MAX]; }; + +enum spad_sections { + SPAD_SECTION_TRACE, + SPAD_SECTION_NVM_CFG, + SPAD_SECTION_PUBLIC, + SPAD_SECTION_PRIVATE, + SPAD_SECTION_MAX +}; + +#define MCP_TRACE_SIZE 2048 /* 2kb */ + +/* This section is located at a fixed location in the beginning of the + * scratchpad, to ensure that the MCP trace is not run over during MFW upgrade. + * All the rest of data has a floating location which differs from version to + * version, and is pointed by the mcp_meta_data below. + * Moreover, the spad_layout section is part of the MFW firmware, and is loaded + * with it from nvram in order to clear this portion. + */ +struct static_init { + u32 num_sections; + offsize_t sections[SPAD_SECTION_MAX]; +#define SECTION(_sec_) (*((offsize_t *)(STRUCT_OFFSET(sections[_sec_])))) + + struct mcp_trace trace; +#define MCP_TRACE_P ((struct mcp_trace *)(STRUCT_OFFSET(trace))) + u8 trace_buffer[MCP_TRACE_SIZE]; +#define MCP_TRACE_BUF ((u8 *)(STRUCT_OFFSET(trace_buffer))) + /* running_mfw has the same definition as in nvm_map.h. + * This bit indicate both the running dir, and the running bundle. + * It is set once when the LIM is loaded. + */ + u32 running_mfw; +#define RUNNING_MFW (*((u32 *)(STRUCT_OFFSET(running_mfw)))) + u32 build_time; +#define MFW_BUILD_TIME (*((u32 *)(STRUCT_OFFSET(build_time)))) + u32 reset_type; +#define RESET_TYPE (*((u32 *)(STRUCT_OFFSET(reset_type)))) + u32 mfw_secure_mode; +#define MFW_SECURE_MODE (*((u32 *)(STRUCT_OFFSET(mfw_secure_mode)))) + u16 pme_status_pf_bitmap; +#define PME_STATUS_PF_BITMAP (*((u16 *)(STRUCT_OFFSET(pme_status_pf_bitmap)))) + u16 pme_enable_pf_bitmap; +#define PME_ENABLE_PF_BITMAP (*((u16 *)(STRUCT_OFFSET(pme_enable_pf_bitmap)))) + u32 mim_nvm_addr; + u32 mim_start_addr; + u32 ah_pcie_link_params; +#define AH_PCIE_LINK_PARAMS_LINK_SPEED_MASK (0x000000ff) +#define AH_PCIE_LINK_PARAMS_LINK_SPEED_SHIFT (0) +#define AH_PCIE_LINK_PARAMS_LINK_WIDTH_MASK (0x0000ff00) +#define AH_PCIE_LINK_PARAMS_LINK_WIDTH_SHIFT (8) +#define AH_PCIE_LINK_PARAMS_ASPM_MODE_MASK (0x00ff0000) +#define AH_PCIE_LINK_PARAMS_ASPM_MODE_SHIFT (16) +#define AH_PCIE_LINK_PARAMS_ASPM_CAP_MASK (0xff000000) +#define AH_PCIE_LINK_PARAMS_ASPM_CAP_SHIFT (24) +#define AH_PCIE_LINK_PARAMS (*((u32 *)(STRUCT_OFFSET(ah_pcie_link_params)))) + + u32 rsrv_persist[5]; /* Persist reserved for MFW upgrades */ +}; + +enum nvm_image_type { + NVM_TYPE_TIM1 = 0x01, + NVM_TYPE_TIM2 = 0x02, + NVM_TYPE_MIM1 = 0x03, + NVM_TYPE_MIM2 = 0x04, + NVM_TYPE_MBA = 0x05, + NVM_TYPE_MODULES_PN = 0x06, + NVM_TYPE_VPD = 0x07, + NVM_TYPE_MFW_TRACE1 = 0x08, + NVM_TYPE_MFW_TRACE2 = 0x09, + NVM_TYPE_NVM_CFG1 = 0x0a, + NVM_TYPE_L2B = 0x0b, + NVM_TYPE_DIR1 = 0x0c, + NVM_TYPE_EAGLE_FW1 = 0x0d, + NVM_TYPE_FALCON_FW1 = 0x0e, + NVM_TYPE_PCIE_FW1 = 0x0f, + NVM_TYPE_HW_SET = 0x10, + NVM_TYPE_LIM = 0x11, + NVM_TYPE_AVS_FW1 = 0x12, + NVM_TYPE_DIR2 = 0x13, + NVM_TYPE_CCM = 0x14, + NVM_TYPE_EAGLE_FW2 = 0x15, + NVM_TYPE_FALCON_FW2 = 0x16, + NVM_TYPE_PCIE_FW2 = 0x17, + NVM_TYPE_AVS_FW2 = 0x18, + NVM_TYPE_INIT_HW = 0x19, + NVM_TYPE_DEFAULT_CFG = 0x1a, + NVM_TYPE_MDUMP = 0x1b, + NVM_TYPE_META = 0x1c, + NVM_TYPE_ISCSI_CFG = 0x1d, + NVM_TYPE_FCOE_CFG = 0x1f, + NVM_TYPE_ETH_PHY_FW1 = 0x20, + NVM_TYPE_ETH_PHY_FW2 = 0x21, + NVM_TYPE_MAX, +}; + +#define DIR_ID_1 (0) + #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index d22e3f8816ae..250efd1d270d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -588,6 +588,8 @@ static int qed_nic_stop(struct qed_dev *cdev) } } + qed_dbg_pf_exit(cdev); + return rc; } @@ -846,6 +848,8 @@ static int qed_slowpath_start(struct qed_dev *cdev, /* First Dword used to diffrentiate between various sources */ data = cdev->firmware->data + sizeof(u32); + + qed_dbg_pf_init(cdev); } memset(&tunn_info, 0, sizeof(tunn_info)); diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index b44f09b18eb1..759cb04e02b0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -528,9 +528,903 @@ #define QM_REG_WFQPFWEIGHT 0x2f4e80UL #define QM_REG_WFQVPWEIGHT 0x2fa000UL +#define PGLCS_REG_DBG_SELECT \ + 0x001d14UL +#define PGLCS_REG_DBG_DWORD_ENABLE \ + 0x001d18UL +#define PGLCS_REG_DBG_SHIFT \ + 0x001d1cUL +#define PGLCS_REG_DBG_FORCE_VALID \ + 0x001d20UL +#define PGLCS_REG_DBG_FORCE_FRAME \ + 0x001d24UL +#define MISC_REG_RESET_PL_PDA_VMAIN_1 \ + 0x008070UL +#define MISC_REG_RESET_PL_PDA_VMAIN_2 \ + 0x008080UL +#define MISC_REG_RESET_PL_PDA_VAUX \ + 0x008090UL +#define MISCS_REG_RESET_PL_UA \ + 0x009050UL +#define MISCS_REG_RESET_PL_HV \ + 0x009060UL +#define MISCS_REG_RESET_PL_HV_2 \ + 0x009150UL +#define DMAE_REG_DBG_SELECT \ + 0x00c510UL +#define DMAE_REG_DBG_DWORD_ENABLE \ + 0x00c514UL +#define DMAE_REG_DBG_SHIFT \ + 0x00c518UL +#define DMAE_REG_DBG_FORCE_VALID \ + 0x00c51cUL +#define DMAE_REG_DBG_FORCE_FRAME \ + 0x00c520UL +#define NCSI_REG_DBG_SELECT \ + 0x040474UL +#define NCSI_REG_DBG_DWORD_ENABLE \ + 0x040478UL +#define NCSI_REG_DBG_SHIFT \ + 0x04047cUL +#define NCSI_REG_DBG_FORCE_VALID \ + 0x040480UL +#define NCSI_REG_DBG_FORCE_FRAME \ + 0x040484UL +#define GRC_REG_DBG_SELECT \ + 0x0500a4UL +#define GRC_REG_DBG_DWORD_ENABLE \ + 0x0500a8UL +#define GRC_REG_DBG_SHIFT \ + 0x0500acUL +#define GRC_REG_DBG_FORCE_VALID \ + 0x0500b0UL +#define GRC_REG_DBG_FORCE_FRAME \ + 0x0500b4UL +#define UMAC_REG_DBG_SELECT \ + 0x051094UL +#define UMAC_REG_DBG_DWORD_ENABLE \ + 0x051098UL +#define UMAC_REG_DBG_SHIFT \ + 0x05109cUL +#define UMAC_REG_DBG_FORCE_VALID \ + 0x0510a0UL +#define UMAC_REG_DBG_FORCE_FRAME \ + 0x0510a4UL +#define MCP2_REG_DBG_SELECT \ + 0x052400UL +#define MCP2_REG_DBG_DWORD_ENABLE \ + 0x052404UL +#define MCP2_REG_DBG_SHIFT \ + 0x052408UL +#define MCP2_REG_DBG_FORCE_VALID \ + 0x052440UL +#define MCP2_REG_DBG_FORCE_FRAME \ + 0x052444UL +#define PCIE_REG_DBG_SELECT \ + 0x0547e8UL +#define PCIE_REG_DBG_DWORD_ENABLE \ + 0x0547ecUL +#define PCIE_REG_DBG_SHIFT \ + 0x0547f0UL +#define PCIE_REG_DBG_FORCE_VALID \ + 0x0547f4UL +#define PCIE_REG_DBG_FORCE_FRAME \ + 0x0547f8UL +#define DORQ_REG_DBG_SELECT \ + 0x100ad0UL +#define DORQ_REG_DBG_DWORD_ENABLE \ + 0x100ad4UL +#define DORQ_REG_DBG_SHIFT \ + 0x100ad8UL +#define DORQ_REG_DBG_FORCE_VALID \ + 0x100adcUL +#define DORQ_REG_DBG_FORCE_FRAME \ + 0x100ae0UL +#define IGU_REG_DBG_SELECT \ + 0x181578UL +#define IGU_REG_DBG_DWORD_ENABLE \ + 0x18157cUL +#define IGU_REG_DBG_SHIFT \ + 0x181580UL +#define IGU_REG_DBG_FORCE_VALID \ + 0x181584UL +#define IGU_REG_DBG_FORCE_FRAME \ + 0x181588UL +#define CAU_REG_DBG_SELECT \ + 0x1c0ea8UL +#define CAU_REG_DBG_DWORD_ENABLE \ + 0x1c0eacUL +#define CAU_REG_DBG_SHIFT \ + 0x1c0eb0UL +#define CAU_REG_DBG_FORCE_VALID \ + 0x1c0eb4UL +#define CAU_REG_DBG_FORCE_FRAME \ + 0x1c0eb8UL +#define PRS_REG_DBG_SELECT \ + 0x1f0b6cUL +#define PRS_REG_DBG_DWORD_ENABLE \ + 0x1f0b70UL +#define PRS_REG_DBG_SHIFT \ + 0x1f0b74UL +#define PRS_REG_DBG_FORCE_VALID \ + 0x1f0ba0UL +#define PRS_REG_DBG_FORCE_FRAME \ + 0x1f0ba4UL +#define CNIG_REG_DBG_SELECT_K2 \ + 0x218254UL +#define CNIG_REG_DBG_DWORD_ENABLE_K2 \ + 0x218258UL +#define CNIG_REG_DBG_SHIFT_K2 \ + 0x21825cUL +#define CNIG_REG_DBG_FORCE_VALID_K2 \ + 0x218260UL +#define CNIG_REG_DBG_FORCE_FRAME_K2 \ + 0x218264UL +#define PRM_REG_DBG_SELECT \ + 0x2306a8UL +#define PRM_REG_DBG_DWORD_ENABLE \ + 0x2306acUL +#define PRM_REG_DBG_SHIFT \ + 0x2306b0UL +#define PRM_REG_DBG_FORCE_VALID \ + 0x2306b4UL +#define PRM_REG_DBG_FORCE_FRAME \ + 0x2306b8UL +#define SRC_REG_DBG_SELECT \ + 0x238700UL +#define SRC_REG_DBG_DWORD_ENABLE \ + 0x238704UL +#define SRC_REG_DBG_SHIFT \ + 0x238708UL +#define SRC_REG_DBG_FORCE_VALID \ + 0x23870cUL +#define SRC_REG_DBG_FORCE_FRAME \ + 0x238710UL +#define RSS_REG_DBG_SELECT \ + 0x238c4cUL +#define RSS_REG_DBG_DWORD_ENABLE \ + 0x238c50UL +#define RSS_REG_DBG_SHIFT \ + 0x238c54UL +#define RSS_REG_DBG_FORCE_VALID \ + 0x238c58UL +#define RSS_REG_DBG_FORCE_FRAME \ + 0x238c5cUL +#define RPB_REG_DBG_SELECT \ + 0x23c728UL +#define RPB_REG_DBG_DWORD_ENABLE \ + 0x23c72cUL +#define RPB_REG_DBG_SHIFT \ + 0x23c730UL +#define RPB_REG_DBG_FORCE_VALID \ + 0x23c734UL +#define RPB_REG_DBG_FORCE_FRAME \ + 0x23c738UL +#define PSWRQ2_REG_DBG_SELECT \ + 0x240100UL +#define PSWRQ2_REG_DBG_DWORD_ENABLE \ + 0x240104UL +#define PSWRQ2_REG_DBG_SHIFT \ + 0x240108UL +#define PSWRQ2_REG_DBG_FORCE_VALID \ + 0x24010cUL +#define PSWRQ2_REG_DBG_FORCE_FRAME \ + 0x240110UL +#define PSWRQ_REG_DBG_SELECT \ + 0x280020UL +#define PSWRQ_REG_DBG_DWORD_ENABLE \ + 0x280024UL +#define PSWRQ_REG_DBG_SHIFT \ + 0x280028UL +#define PSWRQ_REG_DBG_FORCE_VALID \ + 0x28002cUL +#define PSWRQ_REG_DBG_FORCE_FRAME \ + 0x280030UL +#define PSWWR_REG_DBG_SELECT \ + 0x29a084UL +#define PSWWR_REG_DBG_DWORD_ENABLE \ + 0x29a088UL +#define PSWWR_REG_DBG_SHIFT \ + 0x29a08cUL +#define PSWWR_REG_DBG_FORCE_VALID \ + 0x29a090UL +#define PSWWR_REG_DBG_FORCE_FRAME \ + 0x29a094UL +#define PSWRD_REG_DBG_SELECT \ + 0x29c040UL +#define PSWRD_REG_DBG_DWORD_ENABLE \ + 0x29c044UL +#define PSWRD_REG_DBG_SHIFT \ + 0x29c048UL +#define PSWRD_REG_DBG_FORCE_VALID \ + 0x29c04cUL +#define PSWRD_REG_DBG_FORCE_FRAME \ + 0x29c050UL +#define PSWRD2_REG_DBG_SELECT \ + 0x29d400UL +#define PSWRD2_REG_DBG_DWORD_ENABLE \ + 0x29d404UL +#define PSWRD2_REG_DBG_SHIFT \ + 0x29d408UL +#define PSWRD2_REG_DBG_FORCE_VALID \ + 0x29d40cUL +#define PSWRD2_REG_DBG_FORCE_FRAME \ + 0x29d410UL +#define PSWHST2_REG_DBG_SELECT \ + 0x29e058UL +#define PSWHST2_REG_DBG_DWORD_ENABLE \ + 0x29e05cUL +#define PSWHST2_REG_DBG_SHIFT \ + 0x29e060UL +#define PSWHST2_REG_DBG_FORCE_VALID \ + 0x29e064UL +#define PSWHST2_REG_DBG_FORCE_FRAME \ + 0x29e068UL +#define PSWHST_REG_DBG_SELECT \ + 0x2a0100UL +#define PSWHST_REG_DBG_DWORD_ENABLE \ + 0x2a0104UL +#define PSWHST_REG_DBG_SHIFT \ + 0x2a0108UL +#define PSWHST_REG_DBG_FORCE_VALID \ + 0x2a010cUL +#define PSWHST_REG_DBG_FORCE_FRAME \ + 0x2a0110UL +#define PGLUE_B_REG_DBG_SELECT \ + 0x2a8400UL +#define PGLUE_B_REG_DBG_DWORD_ENABLE \ + 0x2a8404UL +#define PGLUE_B_REG_DBG_SHIFT \ + 0x2a8408UL +#define PGLUE_B_REG_DBG_FORCE_VALID \ + 0x2a840cUL +#define PGLUE_B_REG_DBG_FORCE_FRAME \ + 0x2a8410UL +#define TM_REG_DBG_SELECT \ + 0x2c07a8UL +#define TM_REG_DBG_DWORD_ENABLE \ + 0x2c07acUL +#define TM_REG_DBG_SHIFT \ + 0x2c07b0UL +#define TM_REG_DBG_FORCE_VALID \ + 0x2c07b4UL +#define TM_REG_DBG_FORCE_FRAME \ + 0x2c07b8UL +#define TCFC_REG_DBG_SELECT \ + 0x2d0500UL +#define TCFC_REG_DBG_DWORD_ENABLE \ + 0x2d0504UL +#define TCFC_REG_DBG_SHIFT \ + 0x2d0508UL +#define TCFC_REG_DBG_FORCE_VALID \ + 0x2d050cUL +#define TCFC_REG_DBG_FORCE_FRAME \ + 0x2d0510UL +#define CCFC_REG_DBG_SELECT \ + 0x2e0500UL +#define CCFC_REG_DBG_DWORD_ENABLE \ + 0x2e0504UL +#define CCFC_REG_DBG_SHIFT \ + 0x2e0508UL +#define CCFC_REG_DBG_FORCE_VALID \ + 0x2e050cUL +#define CCFC_REG_DBG_FORCE_FRAME \ + 0x2e0510UL +#define QM_REG_DBG_SELECT \ + 0x2f2e74UL +#define QM_REG_DBG_DWORD_ENABLE \ + 0x2f2e78UL +#define QM_REG_DBG_SHIFT \ + 0x2f2e7cUL +#define QM_REG_DBG_FORCE_VALID \ + 0x2f2e80UL +#define QM_REG_DBG_FORCE_FRAME \ + 0x2f2e84UL +#define RDIF_REG_DBG_SELECT \ + 0x300500UL +#define RDIF_REG_DBG_DWORD_ENABLE \ + 0x300504UL +#define RDIF_REG_DBG_SHIFT \ + 0x300508UL +#define RDIF_REG_DBG_FORCE_VALID \ + 0x30050cUL +#define RDIF_REG_DBG_FORCE_FRAME \ + 0x300510UL +#define TDIF_REG_DBG_SELECT \ + 0x310500UL +#define TDIF_REG_DBG_DWORD_ENABLE \ + 0x310504UL +#define TDIF_REG_DBG_SHIFT \ + 0x310508UL +#define TDIF_REG_DBG_FORCE_VALID \ + 0x31050cUL +#define TDIF_REG_DBG_FORCE_FRAME \ + 0x310510UL +#define BRB_REG_DBG_SELECT \ + 0x340ed0UL +#define BRB_REG_DBG_DWORD_ENABLE \ + 0x340ed4UL +#define BRB_REG_DBG_SHIFT \ + 0x340ed8UL +#define BRB_REG_DBG_FORCE_VALID \ + 0x340edcUL +#define BRB_REG_DBG_FORCE_FRAME \ + 0x340ee0UL +#define XYLD_REG_DBG_SELECT \ + 0x4c1600UL +#define XYLD_REG_DBG_DWORD_ENABLE \ + 0x4c1604UL +#define XYLD_REG_DBG_SHIFT \ + 0x4c1608UL +#define XYLD_REG_DBG_FORCE_VALID \ + 0x4c160cUL +#define XYLD_REG_DBG_FORCE_FRAME \ + 0x4c1610UL +#define YULD_REG_DBG_SELECT \ + 0x4c9600UL +#define YULD_REG_DBG_DWORD_ENABLE \ + 0x4c9604UL +#define YULD_REG_DBG_SHIFT \ + 0x4c9608UL +#define YULD_REG_DBG_FORCE_VALID \ + 0x4c960cUL +#define YULD_REG_DBG_FORCE_FRAME \ + 0x4c9610UL +#define TMLD_REG_DBG_SELECT \ + 0x4d1600UL +#define TMLD_REG_DBG_DWORD_ENABLE \ + 0x4d1604UL +#define TMLD_REG_DBG_SHIFT \ + 0x4d1608UL +#define TMLD_REG_DBG_FORCE_VALID \ + 0x4d160cUL +#define TMLD_REG_DBG_FORCE_FRAME \ + 0x4d1610UL +#define MULD_REG_DBG_SELECT \ + 0x4e1600UL +#define MULD_REG_DBG_DWORD_ENABLE \ + 0x4e1604UL +#define MULD_REG_DBG_SHIFT \ + 0x4e1608UL +#define MULD_REG_DBG_FORCE_VALID \ + 0x4e160cUL +#define MULD_REG_DBG_FORCE_FRAME \ + 0x4e1610UL +#define NIG_REG_DBG_SELECT \ + 0x502140UL +#define NIG_REG_DBG_DWORD_ENABLE \ + 0x502144UL +#define NIG_REG_DBG_SHIFT \ + 0x502148UL +#define NIG_REG_DBG_FORCE_VALID \ + 0x50214cUL +#define NIG_REG_DBG_FORCE_FRAME \ + 0x502150UL +#define BMB_REG_DBG_SELECT \ + 0x540a7cUL +#define BMB_REG_DBG_DWORD_ENABLE \ + 0x540a80UL +#define BMB_REG_DBG_SHIFT \ + 0x540a84UL +#define BMB_REG_DBG_FORCE_VALID \ + 0x540a88UL +#define BMB_REG_DBG_FORCE_FRAME \ + 0x540a8cUL +#define PTU_REG_DBG_SELECT \ + 0x560100UL +#define PTU_REG_DBG_DWORD_ENABLE \ + 0x560104UL +#define PTU_REG_DBG_SHIFT \ + 0x560108UL +#define PTU_REG_DBG_FORCE_VALID \ + 0x56010cUL +#define PTU_REG_DBG_FORCE_FRAME \ + 0x560110UL +#define CDU_REG_DBG_SELECT \ + 0x580704UL +#define CDU_REG_DBG_DWORD_ENABLE \ + 0x580708UL +#define CDU_REG_DBG_SHIFT \ + 0x58070cUL +#define CDU_REG_DBG_FORCE_VALID \ + 0x580710UL +#define CDU_REG_DBG_FORCE_FRAME \ + 0x580714UL +#define WOL_REG_DBG_SELECT \ + 0x600140UL +#define WOL_REG_DBG_DWORD_ENABLE \ + 0x600144UL +#define WOL_REG_DBG_SHIFT \ + 0x600148UL +#define WOL_REG_DBG_FORCE_VALID \ + 0x60014cUL +#define WOL_REG_DBG_FORCE_FRAME \ + 0x600150UL +#define BMBN_REG_DBG_SELECT \ + 0x610140UL +#define BMBN_REG_DBG_DWORD_ENABLE \ + 0x610144UL +#define BMBN_REG_DBG_SHIFT \ + 0x610148UL +#define BMBN_REG_DBG_FORCE_VALID \ + 0x61014cUL +#define BMBN_REG_DBG_FORCE_FRAME \ + 0x610150UL +#define NWM_REG_DBG_SELECT \ + 0x8000ecUL +#define NWM_REG_DBG_DWORD_ENABLE \ + 0x8000f0UL +#define NWM_REG_DBG_SHIFT \ + 0x8000f4UL +#define NWM_REG_DBG_FORCE_VALID \ + 0x8000f8UL +#define NWM_REG_DBG_FORCE_FRAME \ + 0x8000fcUL +#define PBF_REG_DBG_SELECT \ + 0xd80060UL +#define PBF_REG_DBG_DWORD_ENABLE \ + 0xd80064UL +#define PBF_REG_DBG_SHIFT \ + 0xd80068UL +#define PBF_REG_DBG_FORCE_VALID \ + 0xd8006cUL +#define PBF_REG_DBG_FORCE_FRAME \ + 0xd80070UL +#define PBF_PB1_REG_DBG_SELECT \ + 0xda0728UL +#define PBF_PB1_REG_DBG_DWORD_ENABLE \ + 0xda072cUL +#define PBF_PB1_REG_DBG_SHIFT \ + 0xda0730UL +#define PBF_PB1_REG_DBG_FORCE_VALID \ + 0xda0734UL +#define PBF_PB1_REG_DBG_FORCE_FRAME \ + 0xda0738UL +#define PBF_PB2_REG_DBG_SELECT \ + 0xda4728UL +#define PBF_PB2_REG_DBG_DWORD_ENABLE \ + 0xda472cUL +#define PBF_PB2_REG_DBG_SHIFT \ + 0xda4730UL +#define PBF_PB2_REG_DBG_FORCE_VALID \ + 0xda4734UL +#define PBF_PB2_REG_DBG_FORCE_FRAME \ + 0xda4738UL +#define BTB_REG_DBG_SELECT \ + 0xdb08c8UL +#define BTB_REG_DBG_DWORD_ENABLE \ + 0xdb08ccUL +#define BTB_REG_DBG_SHIFT \ + 0xdb08d0UL +#define BTB_REG_DBG_FORCE_VALID \ + 0xdb08d4UL +#define BTB_REG_DBG_FORCE_FRAME \ + 0xdb08d8UL +#define XSDM_REG_DBG_SELECT \ + 0xf80e28UL +#define XSDM_REG_DBG_DWORD_ENABLE \ + 0xf80e2cUL +#define XSDM_REG_DBG_SHIFT \ + 0xf80e30UL +#define XSDM_REG_DBG_FORCE_VALID \ + 0xf80e34UL +#define XSDM_REG_DBG_FORCE_FRAME \ + 0xf80e38UL +#define YSDM_REG_DBG_SELECT \ + 0xf90e28UL +#define YSDM_REG_DBG_DWORD_ENABLE \ + 0xf90e2cUL +#define YSDM_REG_DBG_SHIFT \ + 0xf90e30UL +#define YSDM_REG_DBG_FORCE_VALID \ + 0xf90e34UL +#define YSDM_REG_DBG_FORCE_FRAME \ + 0xf90e38UL +#define PSDM_REG_DBG_SELECT \ + 0xfa0e28UL +#define PSDM_REG_DBG_DWORD_ENABLE \ + 0xfa0e2cUL +#define PSDM_REG_DBG_SHIFT \ + 0xfa0e30UL +#define PSDM_REG_DBG_FORCE_VALID \ + 0xfa0e34UL +#define PSDM_REG_DBG_FORCE_FRAME \ + 0xfa0e38UL +#define TSDM_REG_DBG_SELECT \ + 0xfb0e28UL +#define TSDM_REG_DBG_DWORD_ENABLE \ + 0xfb0e2cUL +#define TSDM_REG_DBG_SHIFT \ + 0xfb0e30UL +#define TSDM_REG_DBG_FORCE_VALID \ + 0xfb0e34UL +#define TSDM_REG_DBG_FORCE_FRAME \ + 0xfb0e38UL +#define MSDM_REG_DBG_SELECT \ + 0xfc0e28UL +#define MSDM_REG_DBG_DWORD_ENABLE \ + 0xfc0e2cUL +#define MSDM_REG_DBG_SHIFT \ + 0xfc0e30UL +#define MSDM_REG_DBG_FORCE_VALID \ + 0xfc0e34UL +#define MSDM_REG_DBG_FORCE_FRAME \ + 0xfc0e38UL +#define USDM_REG_DBG_SELECT \ + 0xfd0e28UL +#define USDM_REG_DBG_DWORD_ENABLE \ + 0xfd0e2cUL +#define USDM_REG_DBG_SHIFT \ + 0xfd0e30UL +#define USDM_REG_DBG_FORCE_VALID \ + 0xfd0e34UL +#define USDM_REG_DBG_FORCE_FRAME \ + 0xfd0e38UL +#define XCM_REG_DBG_SELECT \ + 0x1000040UL +#define XCM_REG_DBG_DWORD_ENABLE \ + 0x1000044UL +#define XCM_REG_DBG_SHIFT \ + 0x1000048UL +#define XCM_REG_DBG_FORCE_VALID \ + 0x100004cUL +#define XCM_REG_DBG_FORCE_FRAME \ + 0x1000050UL +#define YCM_REG_DBG_SELECT \ + 0x1080040UL +#define YCM_REG_DBG_DWORD_ENABLE \ + 0x1080044UL +#define YCM_REG_DBG_SHIFT \ + 0x1080048UL +#define YCM_REG_DBG_FORCE_VALID \ + 0x108004cUL +#define YCM_REG_DBG_FORCE_FRAME \ + 0x1080050UL +#define PCM_REG_DBG_SELECT \ + 0x1100040UL +#define PCM_REG_DBG_DWORD_ENABLE \ + 0x1100044UL +#define PCM_REG_DBG_SHIFT \ + 0x1100048UL +#define PCM_REG_DBG_FORCE_VALID \ + 0x110004cUL +#define PCM_REG_DBG_FORCE_FRAME \ + 0x1100050UL +#define TCM_REG_DBG_SELECT \ + 0x1180040UL +#define TCM_REG_DBG_DWORD_ENABLE \ + 0x1180044UL +#define TCM_REG_DBG_SHIFT \ + 0x1180048UL +#define TCM_REG_DBG_FORCE_VALID \ + 0x118004cUL +#define TCM_REG_DBG_FORCE_FRAME \ + 0x1180050UL +#define MCM_REG_DBG_SELECT \ + 0x1200040UL +#define MCM_REG_DBG_DWORD_ENABLE \ + 0x1200044UL +#define MCM_REG_DBG_SHIFT \ + 0x1200048UL +#define MCM_REG_DBG_FORCE_VALID \ + 0x120004cUL +#define MCM_REG_DBG_FORCE_FRAME \ + 0x1200050UL +#define UCM_REG_DBG_SELECT \ + 0x1280050UL +#define UCM_REG_DBG_DWORD_ENABLE \ + 0x1280054UL +#define UCM_REG_DBG_SHIFT \ + 0x1280058UL +#define UCM_REG_DBG_FORCE_VALID \ + 0x128005cUL +#define UCM_REG_DBG_FORCE_FRAME \ + 0x1280060UL +#define XSEM_REG_DBG_SELECT \ + 0x1401528UL +#define XSEM_REG_DBG_DWORD_ENABLE \ + 0x140152cUL +#define XSEM_REG_DBG_SHIFT \ + 0x1401530UL +#define XSEM_REG_DBG_FORCE_VALID \ + 0x1401534UL +#define XSEM_REG_DBG_FORCE_FRAME \ + 0x1401538UL +#define YSEM_REG_DBG_SELECT \ + 0x1501528UL +#define YSEM_REG_DBG_DWORD_ENABLE \ + 0x150152cUL +#define YSEM_REG_DBG_SHIFT \ + 0x1501530UL +#define YSEM_REG_DBG_FORCE_VALID \ + 0x1501534UL +#define YSEM_REG_DBG_FORCE_FRAME \ + 0x1501538UL +#define PSEM_REG_DBG_SELECT \ + 0x1601528UL +#define PSEM_REG_DBG_DWORD_ENABLE \ + 0x160152cUL +#define PSEM_REG_DBG_SHIFT \ + 0x1601530UL +#define PSEM_REG_DBG_FORCE_VALID \ + 0x1601534UL +#define PSEM_REG_DBG_FORCE_FRAME \ + 0x1601538UL +#define TSEM_REG_DBG_SELECT \ + 0x1701528UL +#define TSEM_REG_DBG_DWORD_ENABLE \ + 0x170152cUL +#define TSEM_REG_DBG_SHIFT \ + 0x1701530UL +#define TSEM_REG_DBG_FORCE_VALID \ + 0x1701534UL +#define TSEM_REG_DBG_FORCE_FRAME \ + 0x1701538UL +#define MSEM_REG_DBG_SELECT \ + 0x1801528UL +#define MSEM_REG_DBG_DWORD_ENABLE \ + 0x180152cUL +#define MSEM_REG_DBG_SHIFT \ + 0x1801530UL +#define MSEM_REG_DBG_FORCE_VALID \ + 0x1801534UL +#define MSEM_REG_DBG_FORCE_FRAME \ + 0x1801538UL +#define USEM_REG_DBG_SELECT \ + 0x1901528UL +#define USEM_REG_DBG_DWORD_ENABLE \ + 0x190152cUL +#define USEM_REG_DBG_SHIFT \ + 0x1901530UL +#define USEM_REG_DBG_FORCE_VALID \ + 0x1901534UL +#define USEM_REG_DBG_FORCE_FRAME \ + 0x1901538UL +#define PCIE_REG_DBG_COMMON_SELECT \ + 0x054398UL +#define PCIE_REG_DBG_COMMON_DWORD_ENABLE \ + 0x05439cUL +#define PCIE_REG_DBG_COMMON_SHIFT \ + 0x0543a0UL +#define PCIE_REG_DBG_COMMON_FORCE_VALID \ + 0x0543a4UL +#define PCIE_REG_DBG_COMMON_FORCE_FRAME \ + 0x0543a8UL +#define MISC_REG_RESET_PL_UA \ + 0x008050UL +#define MISC_REG_RESET_PL_HV \ + 0x008060UL +#define XCM_REG_CTX_RBC_ACCS \ + 0x1001800UL +#define XCM_REG_AGG_CON_CTX \ + 0x1001804UL +#define XCM_REG_SM_CON_CTX \ + 0x1001808UL +#define YCM_REG_CTX_RBC_ACCS \ + 0x1081800UL +#define YCM_REG_AGG_CON_CTX \ + 0x1081804UL +#define YCM_REG_AGG_TASK_CTX \ + 0x1081808UL +#define YCM_REG_SM_CON_CTX \ + 0x108180cUL +#define YCM_REG_SM_TASK_CTX \ + 0x1081810UL +#define PCM_REG_CTX_RBC_ACCS \ + 0x1101440UL +#define PCM_REG_SM_CON_CTX \ + 0x1101444UL +#define TCM_REG_CTX_RBC_ACCS \ + 0x11814c0UL +#define TCM_REG_AGG_CON_CTX \ + 0x11814c4UL +#define TCM_REG_AGG_TASK_CTX \ + 0x11814c8UL +#define TCM_REG_SM_CON_CTX \ + 0x11814ccUL +#define TCM_REG_SM_TASK_CTX \ + 0x11814d0UL +#define MCM_REG_CTX_RBC_ACCS \ + 0x1201800UL +#define MCM_REG_AGG_CON_CTX \ + 0x1201804UL +#define MCM_REG_AGG_TASK_CTX \ + 0x1201808UL +#define MCM_REG_SM_CON_CTX \ + 0x120180cUL +#define MCM_REG_SM_TASK_CTX \ + 0x1201810UL +#define UCM_REG_CTX_RBC_ACCS \ + 0x1281700UL +#define UCM_REG_AGG_CON_CTX \ + 0x1281704UL +#define UCM_REG_AGG_TASK_CTX \ + 0x1281708UL +#define UCM_REG_SM_CON_CTX \ + 0x128170cUL +#define UCM_REG_SM_TASK_CTX \ + 0x1281710UL +#define XSEM_REG_SLOW_DBG_EMPTY \ + 0x1401140UL +#define XSEM_REG_SYNC_DBG_EMPTY \ + 0x1401160UL +#define XSEM_REG_SLOW_DBG_ACTIVE \ + 0x1401400UL +#define XSEM_REG_SLOW_DBG_MODE \ + 0x1401404UL +#define XSEM_REG_DBG_FRAME_MODE \ + 0x1401408UL +#define XSEM_REG_DBG_MODE1_CFG \ + 0x1401420UL +#define XSEM_REG_FAST_MEMORY \ + 0x1440000UL +#define YSEM_REG_SYNC_DBG_EMPTY \ + 0x1501160UL +#define YSEM_REG_SLOW_DBG_ACTIVE \ + 0x1501400UL +#define YSEM_REG_SLOW_DBG_MODE \ + 0x1501404UL +#define YSEM_REG_DBG_FRAME_MODE \ + 0x1501408UL +#define YSEM_REG_DBG_MODE1_CFG \ + 0x1501420UL +#define YSEM_REG_FAST_MEMORY \ + 0x1540000UL +#define PSEM_REG_SLOW_DBG_EMPTY \ + 0x1601140UL +#define PSEM_REG_SYNC_DBG_EMPTY \ + 0x1601160UL +#define PSEM_REG_SLOW_DBG_ACTIVE \ + 0x1601400UL +#define PSEM_REG_SLOW_DBG_MODE \ + 0x1601404UL +#define PSEM_REG_DBG_FRAME_MODE \ + 0x1601408UL +#define PSEM_REG_DBG_MODE1_CFG \ + 0x1601420UL +#define PSEM_REG_FAST_MEMORY \ + 0x1640000UL +#define TSEM_REG_SLOW_DBG_EMPTY \ + 0x1701140UL +#define TSEM_REG_SYNC_DBG_EMPTY \ + 0x1701160UL +#define TSEM_REG_SLOW_DBG_ACTIVE \ + 0x1701400UL +#define TSEM_REG_SLOW_DBG_MODE \ + 0x1701404UL +#define TSEM_REG_DBG_FRAME_MODE \ + 0x1701408UL +#define TSEM_REG_DBG_MODE1_CFG \ + 0x1701420UL +#define TSEM_REG_FAST_MEMORY \ + 0x1740000UL +#define MSEM_REG_SLOW_DBG_EMPTY \ + 0x1801140UL +#define MSEM_REG_SYNC_DBG_EMPTY \ + 0x1801160UL +#define MSEM_REG_SLOW_DBG_ACTIVE \ + 0x1801400UL +#define MSEM_REG_SLOW_DBG_MODE \ + 0x1801404UL +#define MSEM_REG_DBG_FRAME_MODE \ + 0x1801408UL +#define MSEM_REG_DBG_MODE1_CFG \ + 0x1801420UL +#define MSEM_REG_FAST_MEMORY \ + 0x1840000UL +#define USEM_REG_SLOW_DBG_EMPTY \ + 0x1901140UL +#define USEM_REG_SYNC_DBG_EMPTY \ + 0x1901160UL +#define USEM_REG_SLOW_DBG_ACTIVE \ + 0x1901400UL +#define USEM_REG_SLOW_DBG_MODE \ + 0x1901404UL +#define USEM_REG_DBG_FRAME_MODE \ + 0x1901408UL +#define USEM_REG_DBG_MODE1_CFG \ + 0x1901420UL +#define USEM_REG_FAST_MEMORY \ + 0x1940000UL +#define SEM_FAST_REG_INT_RAM \ + 0x020000UL +#define SEM_FAST_REG_INT_RAM_SIZE \ + 20480 +#define GRC_REG_TRACE_FIFO_VALID_DATA \ + 0x050064UL +#define GRC_REG_NUMBER_VALID_OVERRIDE_WINDOW \ + 0x05040cUL +#define GRC_REG_PROTECTION_OVERRIDE_WINDOW \ + 0x050500UL +#define IGU_REG_ERROR_HANDLING_MEMORY \ + 0x181520UL #define MCP_REG_CPU_MODE \ 0xe05000UL #define MCP_REG_CPU_MODE_SOFT_HALT \ (0x1 << 10) +#define BRB_REG_BIG_RAM_ADDRESS \ + 0x340800UL +#define BRB_REG_BIG_RAM_DATA \ + 0x341500UL +#define SEM_FAST_REG_STALL_0 \ + 0x000488UL +#define SEM_FAST_REG_STALLED \ + 0x000494UL +#define BTB_REG_BIG_RAM_ADDRESS \ + 0xdb0800UL +#define BTB_REG_BIG_RAM_DATA \ + 0xdb0c00UL +#define BMB_REG_BIG_RAM_ADDRESS \ + 0x540800UL +#define BMB_REG_BIG_RAM_DATA \ + 0x540f00UL +#define SEM_FAST_REG_STORM_REG_FILE \ + 0x008000UL +#define RSS_REG_RSS_RAM_ADDR \ + 0x238c30UL +#define MISCS_REG_BLOCK_256B_EN \ + 0x009074UL +#define MCP_REG_SCRATCH_SIZE \ + 57344 +#define MCP_REG_CPU_REG_FILE \ + 0xe05200UL +#define MCP_REG_CPU_REG_FILE_SIZE \ + 32 +#define DBG_REG_DEBUG_TARGET \ + 0x01005cUL +#define DBG_REG_FULL_MODE \ + 0x010060UL +#define DBG_REG_CALENDAR_OUT_DATA \ + 0x010480UL +#define GRC_REG_TRACE_FIFO \ + 0x050068UL +#define IGU_REG_ERROR_HANDLING_DATA_VALID \ + 0x181530UL +#define DBG_REG_DBG_BLOCK_ON \ + 0x010454UL +#define DBG_REG_FRAMING_MODE \ + 0x010058UL +#define SEM_FAST_REG_VFC_DATA_WR \ + 0x000b40UL +#define SEM_FAST_REG_VFC_ADDR \ + 0x000b44UL +#define SEM_FAST_REG_VFC_DATA_RD \ + 0x000b48UL +#define RSS_REG_RSS_RAM_DATA \ + 0x238c20UL +#define MISC_REG_BLOCK_256B_EN \ + 0x008c14UL +#define NWS_REG_NWS_CMU \ + 0x720000UL +#define PHY_NW_IP_REG_PHY0_TOP_TBUS_ADDR_7_0 \ + 0x000680UL +#define PHY_NW_IP_REG_PHY0_TOP_TBUS_ADDR_15_8 \ + 0x000684UL +#define PHY_NW_IP_REG_PHY0_TOP_TBUS_DATA_7_0 \ + 0x0006c0UL +#define PHY_NW_IP_REG_PHY0_TOP_TBUS_DATA_11_8 \ + 0x0006c4UL +#define MS_REG_MS_CMU \ + 0x6a4000UL +#define PHY_SGMII_IP_REG_AHB_CMU_CSR_0_X130 \ + 0x000208UL +#define PHY_SGMII_IP_REG_AHB_CMU_CSR_0_X132 \ + 0x000210UL +#define PHY_SGMII_IP_REG_AHB_CMU_CSR_0_X131 \ + 0x00020cUL +#define PHY_SGMII_IP_REG_AHB_CMU_CSR_0_X133 \ + 0x000214UL +#define PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X130 \ + 0x000208UL +#define PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X131 \ + 0x00020cUL +#define PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X132 \ + 0x000210UL +#define PHY_PCIE_IP_REG_AHB_CMU_CSR_0_X133 \ + 0x000214UL +#define PHY_PCIE_REG_PHY0 \ + 0x620000UL +#define PHY_PCIE_REG_PHY1 \ + 0x624000UL #endif 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 v1.3-14-g43fede 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 --- drivers/net/ethernet/qlogic/qed/qed_main.c | 2 ++ drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 24 ++++++++++++++++++++++++ include/linux/qed/qed_if.h | 4 ++++ 3 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 250efd1d270d..b730a632c383 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -1398,6 +1398,8 @@ const struct qed_common_ops qed_common_ops_pass = { .get_link = &qed_get_current_link, .drain = &qed_drain, .update_msglvl = &qed_init_dp, + .dbg_all_data = &qed_dbg_all_data, + .dbg_all_data_size = &qed_dbg_all_data_size, .chain_alloc = &qed_chain_alloc, .chain_free = &qed_chain_free, .get_coalesce = &qed_get_coalesce, diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 14d5328e6ac9..25a9b293ee8f 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -695,6 +695,28 @@ static int qede_set_pauseparam(struct net_device *dev, return 0; } +static void qede_get_regs(struct net_device *ndev, + struct ethtool_regs *regs, void *buffer) +{ + struct qede_dev *edev = netdev_priv(ndev); + + regs->version = 0; + memset(buffer, 0, regs->len); + + if (edev->ops && edev->ops->common) + edev->ops->common->dbg_all_data(edev->cdev, buffer); +} + +static int qede_get_regs_len(struct net_device *ndev) +{ + struct qede_dev *edev = netdev_priv(ndev); + + if (edev->ops && edev->ops->common) + return edev->ops->common->dbg_all_data_size(edev->cdev); + else + return -EINVAL; +} + static void qede_update_mtu(struct qede_dev *edev, union qede_reload_args *args) { edev->ndev->mtu = args->mtu; @@ -1395,6 +1417,8 @@ static const struct ethtool_ops qede_ethtool_ops = { .get_link_ksettings = qede_get_link_ksettings, .set_link_ksettings = qede_set_link_ksettings, .get_drvinfo = qede_get_drvinfo, + .get_regs_len = qede_get_regs_len, + .get_regs = qede_get_regs, .get_msglevel = qede_get_msglevel, .set_msglevel = qede_set_msglevel, .nway_reset = qede_nway_reset, 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 v1.3-14-g43fede 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 ++-- include/uapi/linux/inet_diag.h | 1 + net/ipv4/inet_diag.c | 49 ++++++++++++++++++++++++++++-------------- net/ipv4/udp_diag.c | 10 +++++---- net/sctp/sctp_diag.c | 20 +++++++++++------ 5 files changed, 56 insertions(+), 28 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); diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 5581206a08ae..b5c366f87b3e 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -123,6 +123,7 @@ enum { INET_DIAG_LOCALS, INET_DIAG_PEERS, INET_DIAG_PAD, + INET_DIAG_MARK, __INET_DIAG_MAX, }; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index abfbe492ebfe..e4d16fc5bbb3 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -99,6 +99,7 @@ static size_t inet_sk_attr_size(void) + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(4) /* INET_DIAG_MARK */ + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) @@ -109,7 +110,8 @@ static size_t inet_sk_attr_size(void) 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) { const struct inet_sock *inet = inet_sk(sk); @@ -136,6 +138,9 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, } #endif + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) + goto errout; + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); @@ -149,7 +154,8 @@ 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 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { const struct tcp_congestion_ops *ca_ops; const struct inet_diag_handler *handler; @@ -175,7 +181,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_timer = 0; r->idiag_retrans = 0; - if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns)) + if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) goto errout; if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { @@ -274,10 +280,11 @@ static int inet_csk_diag_fill(struct sock *sk, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { - return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, - user_ns, portid, seq, nlmsg_flags, unlh); + return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns, + portid, seq, nlmsg_flags, unlh, net_admin); } static int inet_twsk_diag_fill(struct sock *sk, @@ -319,8 +326,9 @@ static int inet_twsk_diag_fill(struct sock *sk, static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, bool net_admin) { + struct request_sock *reqsk = inet_reqsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; @@ -334,7 +342,7 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, inet_diag_msg_common_fill(r, sk); r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; - r->idiag_retrans = inet_reqsk(sk)->num_retrans; + r->idiag_retrans = reqsk->num_retrans; BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != offsetof(struct sock, sk_cookie)); @@ -346,6 +354,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, r->idiag_uid = 0; r->idiag_inode = 0; + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, + inet_rsk(reqsk)->ir_mark)) + return -EMSGSIZE; + nlmsg_end(skb, nlh); return 0; } @@ -354,7 +366,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct inet_diag_req_v2 *r, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, bool net_admin) { if (sk->sk_state == TCP_TIME_WAIT) return inet_twsk_diag_fill(sk, skb, portid, seq, @@ -362,10 +374,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, if (sk->sk_state == TCP_NEW_SYN_RECV) return inet_req_diag_fill(sk, skb, portid, seq, - nlmsg_flags, unlh); + nlmsg_flags, unlh, net_admin); return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, - nlmsg_flags, unlh); + nlmsg_flags, unlh, net_admin); } struct sock *inet_diag_find_one_icsk(struct net *net, @@ -435,7 +447,8 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, err = sk_diag_fill(sk, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); nlmsg_free(rep); @@ -796,7 +809,8 @@ static int inet_csk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, - const struct nlattr *bc) + const struct nlattr *bc, + bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; @@ -804,7 +818,8 @@ static int inet_csk_diag_dump(struct sock *sk, return inet_csk_diag_fill(sk, skb, r, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, + net_admin); } static void twsk_build_assert(void) @@ -840,6 +855,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, struct net *net = sock_net(skb->sk); int i, num, s_i, s_num; u32 idiag_states = r->idiag_states; + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); if (idiag_states & TCPF_SYN_RECV) idiag_states |= TCPF_NEW_SYN_RECV; @@ -880,7 +896,8 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, cb->args[3] > 0) goto next_listen; - if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) { + if (inet_csk_diag_dump(sk, skb, cb, r, + bc, net_admin) < 0) { spin_unlock_bh(&ilb->lock); goto done; } @@ -948,7 +965,7 @@ skip_listen_ht: sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->nlh); + cb->nlh, net_admin); if (res < 0) { spin_unlock_bh(lock); goto done; diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 58b79c0c0d69..9a89c10a55f0 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -20,7 +20,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *req, - struct nlattr *bc) + struct nlattr *bc, bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; @@ -28,7 +28,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, return inet_sk_diag_fill(sk, NULL, skb, req, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, net_admin); } static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, @@ -76,7 +76,8 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, err = inet_sk_diag_fill(sk, NULL, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(rep); @@ -97,6 +98,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, struct nlattr *bc) { + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct net *net = sock_net(skb->sk); int num, s_num, slot, s_slot; @@ -132,7 +134,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, r->id.idiag_dport) goto next; - if (sk_diag_dump(sk, skb, cb, r, bc) < 0) { + if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) { spin_unlock_bh(&hslot->lock); goto done; } diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index f3508aa75815..807158e32f5f 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -106,7 +106,8 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, int portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + const struct nlmsghdr *unlh, + bool net_admin) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct list_head *addr_list; @@ -133,7 +134,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, r->idiag_retrans = 0; } - if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns)) + if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) goto errout; if (ext & (1 << (INET_DIAG_SKMEMINFO - 1))) { @@ -203,6 +204,7 @@ struct sctp_comm_param { struct netlink_callback *cb; const struct inet_diag_req_v2 *r; const struct nlmsghdr *nlh; + bool net_admin; }; static size_t inet_assoc_attr_size(struct sctp_association *asoc) @@ -219,6 +221,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(4) /* INET_DIAG_MARK */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) + nla_total_size(sizeof(struct inet_diag_meminfo)) @@ -256,7 +259,8 @@ static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p) err = inet_sctp_diag_fill(sk, assoc, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh); + nlh->nlmsg_seq, 0, nlh, + commp->net_admin); release_sock(sk); if (err < 0) { WARN_ON(err == -EMSGSIZE); @@ -310,7 +314,8 @@ static int sctp_tsp_dump(struct sctp_transport *tsp, void *p) sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI, cb->nlh) < 0) { + NLM_F_MULTI, cb->nlh, + commp->net_admin) < 0) { cb->args[3] = 1; err = 2; goto release; @@ -320,7 +325,8 @@ static int sctp_tsp_dump(struct sctp_transport *tsp, void *p) if (inet_sctp_diag_fill(sk, assoc, skb, r, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, cb->nlh) < 0) { + cb->nlh->nlmsg_seq, 0, cb->nlh, + commp->net_admin) < 0) { err = 2; goto release; } @@ -375,7 +381,7 @@ static int sctp_ep_dump(struct sctp_endpoint *ep, void *p) sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->nlh) < 0) { + cb->nlh, commp->net_admin) < 0) { err = 2; goto out; } @@ -412,6 +418,7 @@ static int sctp_diag_dump_one(struct sk_buff *in_skb, .skb = in_skb, .r = req, .nlh = nlh, + .net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN), }; if (req->sdiag_family == AF_INET) { @@ -447,6 +454,7 @@ static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, .skb = skb, .cb = cb, .r = r, + .net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN), }; /* eps hashtable dumps -- cgit v1.3-14-g43fede 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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 +- include/net/tcp.h | 2 +- net/core/skbuff.c | 19 +++ net/ipv4/tcp.c | 4 +- net/ipv4/tcp_input.c | 330 +++++++++++++++++++++++++++-------------------- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 1 - 8 files changed, 218 insertions(+), 149 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 */ diff --git a/include/net/tcp.h b/include/net/tcp.h index d6ae36512429..fdfbedd61c67 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -640,7 +640,7 @@ static inline void tcp_fast_path_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - if (skb_queue_empty(&tp->out_of_order_queue) && + if (RB_EMPTY_ROOT(&tp->out_of_order_queue) && tp->rcv_wnd && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && !tp->urg_data) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3864b4b68fa1..1e329d411242 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2444,6 +2444,25 @@ void skb_queue_purge(struct sk_buff_head *list) } EXPORT_SYMBOL(skb_queue_purge); +/** + * skb_rbtree_purge - empty a skb rbtree + * @root: root of the rbtree to empty + * + * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from + * the list and one reference dropped. This function does not take + * any lock. Synchronization should be handled by the caller (e.g., TCP + * out-of-order queue is protected by the socket lock). + */ +void skb_rbtree_purge(struct rb_root *root) +{ + struct sk_buff *skb, *next; + + rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode) + kfree_skb(skb); + + *root = RB_ROOT; +} + /** * skb_queue_head - queue a buffer at the list head * @list: list to use diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 77311a92275c..a13fcb369f52 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -380,7 +380,7 @@ void tcp_init_sock(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - __skb_queue_head_init(&tp->out_of_order_queue); + tp->out_of_order_queue = RB_ROOT; tcp_init_xmit_timers(sk); tcp_prequeue_init(tp); INIT_LIST_HEAD(&tp->tsq_node); @@ -2243,7 +2243,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); tcp_write_queue_purge(sk); - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); inet->inet_dport = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8cd02c0b056c..a5934c4c8cd4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4108,7 +4108,7 @@ void tcp_fin(struct sock *sk) /* It _is_ possible, that we have something out-of-order _after_ FIN. * Probably, we should reset in this case. For now drop them. */ - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); if (tcp_is_sack(tp)) tcp_sack_reset(&tp->rx_opt); sk_mem_reclaim(sk); @@ -4268,7 +4268,7 @@ static void tcp_sack_remove(struct tcp_sock *tp) int this_sack; /* Empty ofo queue, hence, all the SACKs are eaten. Clear. */ - if (skb_queue_empty(&tp->out_of_order_queue)) { + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tp->rx_opt.num_sacks = 0; return; } @@ -4344,10 +4344,13 @@ static void tcp_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); __u32 dsack_high = tp->rcv_nxt; + bool fin, fragstolen, eaten; struct sk_buff *skb, *tail; - bool fragstolen, eaten; + struct rb_node *p; - while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) { + p = rb_first(&tp->out_of_order_queue); + while (p) { + skb = rb_entry(p, struct sk_buff, rbnode); if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; @@ -4357,9 +4360,10 @@ static void tcp_ofo_queue(struct sock *sk) dsack_high = TCP_SKB_CB(skb)->end_seq; tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack); } + p = rb_next(p); + rb_erase(&skb->rbnode, &tp->out_of_order_queue); - __skb_unlink(skb, &tp->out_of_order_queue); - if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { + if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) { SOCK_DEBUG(sk, "ofo packet was already received\n"); tcp_drop(sk, skb); continue; @@ -4371,12 +4375,19 @@ static void tcp_ofo_queue(struct sock *sk) tail = skb_peek_tail(&sk->sk_receive_queue); eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); + fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) __skb_queue_tail(&sk->sk_receive_queue, skb); - if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) - tcp_fin(sk); - if (eaten) + else kfree_skb_partial(skb, fragstolen); + + if (unlikely(fin)) { + tcp_fin(sk); + /* tcp_fin() purges tp->out_of_order_queue, + * so we must end this loop right now. + */ + break; + } } } @@ -4403,8 +4414,10 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + struct rb_node **p, *q, *parent; struct sk_buff *skb1; u32 seq, end_seq; + bool fragstolen; tcp_ecn_check_ce(tp, skb); @@ -4419,88 +4432,85 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) inet_csk_schedule_ack(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); + seq = TCP_SKB_CB(skb)->seq; + end_seq = TCP_SKB_CB(skb)->end_seq; SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", - tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); + tp->rcv_nxt, seq, end_seq); - skb1 = skb_peek_tail(&tp->out_of_order_queue); - if (!skb1) { + p = &tp->out_of_order_queue.rb_node; + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) { /* Initial out of order segment, build 1 SACK. */ if (tcp_is_sack(tp)) { tp->rx_opt.num_sacks = 1; - tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq; - tp->selective_acks[0].end_seq = - TCP_SKB_CB(skb)->end_seq; + tp->selective_acks[0].start_seq = seq; + tp->selective_acks[0].end_seq = end_seq; } - __skb_queue_head(&tp->out_of_order_queue, skb); + rb_link_node(&skb->rbnode, NULL, p); + rb_insert_color(&skb->rbnode, &tp->out_of_order_queue); + tp->ooo_last_skb = skb; goto end; } - seq = TCP_SKB_CB(skb)->seq; - end_seq = TCP_SKB_CB(skb)->end_seq; - - if (seq == TCP_SKB_CB(skb1)->end_seq) { - bool fragstolen; - - if (!tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); - } else { - tcp_grow_window(sk, skb); - kfree_skb_partial(skb, fragstolen); - skb = NULL; + /* In the typical case, we are adding an skb to the end of the list. + * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. + */ + if (tcp_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { +coalesce_done: + tcp_grow_window(sk, skb); + kfree_skb_partial(skb, fragstolen); + skb = NULL; + goto add_sack; + } + + /* Find place to insert this segment. Handle overlaps on the way. */ + parent = NULL; + while (*p) { + parent = *p; + skb1 = rb_entry(parent, struct sk_buff, rbnode); + if (before(seq, TCP_SKB_CB(skb1)->seq)) { + p = &parent->rb_left; + continue; } - - if (!tp->rx_opt.num_sacks || - tp->selective_acks[0].end_seq != seq) - goto add_sack; - - /* Common case: data arrive in order after hole. */ - tp->selective_acks[0].end_seq = end_seq; - goto end; - } - - /* Find place to insert this segment. */ - while (1) { - if (!after(TCP_SKB_CB(skb1)->seq, seq)) - break; - if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) { - skb1 = NULL; - break; + if (before(seq, TCP_SKB_CB(skb1)->end_seq)) { + if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { + /* All the bits are present. Drop. */ + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPOFOMERGE); + __kfree_skb(skb); + skb = NULL; + tcp_dsack_set(sk, seq, end_seq); + goto add_sack; + } + if (after(seq, TCP_SKB_CB(skb1)->seq)) { + /* Partial overlap. */ + tcp_dsack_set(sk, seq, TCP_SKB_CB(skb1)->end_seq); + } else { + /* skb's seq == skb1's seq and skb covers skb1. + * Replace skb1 with skb. + */ + rb_replace_node(&skb1->rbnode, &skb->rbnode, + &tp->out_of_order_queue); + tcp_dsack_extend(sk, + TCP_SKB_CB(skb1)->seq, + TCP_SKB_CB(skb1)->end_seq); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPOFOMERGE); + __kfree_skb(skb1); + goto add_sack; + } + } else if (tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { + goto coalesce_done; } - skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1); + p = &parent->rb_right; } - /* Do skb overlap to previous one? */ - if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { - if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { - /* All the bits are present. Drop. */ - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - tcp_drop(sk, skb); - skb = NULL; - tcp_dsack_set(sk, seq, end_seq); - goto add_sack; - } - if (after(seq, TCP_SKB_CB(skb1)->seq)) { - /* Partial overlap. */ - tcp_dsack_set(sk, seq, - TCP_SKB_CB(skb1)->end_seq); - } else { - if (skb_queue_is_first(&tp->out_of_order_queue, - skb1)) - skb1 = NULL; - else - skb1 = skb_queue_prev( - &tp->out_of_order_queue, - skb1); - } - } - if (!skb1) - __skb_queue_head(&tp->out_of_order_queue, skb); - else - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); + /* Insert segment into RB tree. */ + rb_link_node(&skb->rbnode, parent, p); + rb_insert_color(&skb->rbnode, &tp->out_of_order_queue); - /* And clean segments covered by new one as whole. */ - while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) { - skb1 = skb_queue_next(&tp->out_of_order_queue, skb); + /* Remove other segments covered by skb. */ + while ((q = rb_next(&skb->rbnode)) != NULL) { + skb1 = rb_entry(q, struct sk_buff, rbnode); if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) break; @@ -4509,12 +4519,15 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) end_seq); break; } - __skb_unlink(skb1, &tp->out_of_order_queue); + rb_erase(&skb1->rbnode, &tp->out_of_order_queue); tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); tcp_drop(sk, skb1); } + /* If there is no skb after us, we are the last_skb ! */ + if (!q) + tp->ooo_last_skb = skb; add_sack: if (tcp_is_sack(tp)) @@ -4651,13 +4664,13 @@ queue_and_out: if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) tcp_fin(sk); - if (!skb_queue_empty(&tp->out_of_order_queue)) { + if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tcp_ofo_queue(sk); /* RFC2581. 4.2. SHOULD send immediate ACK, when * gap in queue is filled. */ - if (skb_queue_empty(&tp->out_of_order_queue)) + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) inet_csk(sk)->icsk_ack.pingpong = 0; } @@ -4711,48 +4724,76 @@ drop: tcp_data_queue_ofo(sk, skb); } +static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *list) +{ + if (list) + return !skb_queue_is_last(list, skb) ? skb->next : NULL; + + return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode); +} + static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, - struct sk_buff_head *list) + struct sk_buff_head *list, + struct rb_root *root) { - struct sk_buff *next = NULL; + struct sk_buff *next = tcp_skb_next(skb, list); - if (!skb_queue_is_last(list, skb)) - next = skb_queue_next(list, skb); + if (list) + __skb_unlink(skb, list); + else + rb_erase(&skb->rbnode, root); - __skb_unlink(skb, list); __kfree_skb(skb); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVCOLLAPSED); return next; } +/* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */ +static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct sk_buff *skb1; + + while (*p) { + parent = *p; + skb1 = rb_entry(parent, struct sk_buff, rbnode); + if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq)) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + rb_link_node(&skb->rbnode, parent, p); + rb_insert_color(&skb->rbnode, root); +} + /* Collapse contiguous sequence of skbs head..tail with * sequence numbers start..end. * - * If tail is NULL, this means until the end of the list. + * If tail is NULL, this means until the end of the queue. * * Segments with FIN/SYN are not collapsed (only because this * simplifies code) */ static void -tcp_collapse(struct sock *sk, struct sk_buff_head *list, - struct sk_buff *head, struct sk_buff *tail, - u32 start, u32 end) +tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, + struct sk_buff *head, struct sk_buff *tail, u32 start, u32 end) { - struct sk_buff *skb, *n; + struct sk_buff *skb = head, *n; + struct sk_buff_head tmp; bool end_of_skbs; /* First, check that queue is collapsible and find - * the point where collapsing can be useful. */ - skb = head; + * the point where collapsing can be useful. + */ restart: - end_of_skbs = true; - skb_queue_walk_from_safe(list, skb, n) { - if (skb == tail) - break; + for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) { + n = tcp_skb_next(skb, list); + /* No new bits? It is possible on ofo queue. */ if (!before(start, TCP_SKB_CB(skb)->end_seq)) { - skb = tcp_collapse_one(sk, skb, list); + skb = tcp_collapse_one(sk, skb, list, root); if (!skb) break; goto restart; @@ -4770,13 +4811,10 @@ restart: break; } - if (!skb_queue_is_last(list, skb)) { - struct sk_buff *next = skb_queue_next(list, skb); - if (next != tail && - TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(next)->seq) { - end_of_skbs = false; - break; - } + if (n && n != tail && + TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { + end_of_skbs = false; + break; } /* Decided to skip this, advance start seq. */ @@ -4786,17 +4824,22 @@ restart: (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) return; + __skb_queue_head_init(&tmp); + while (before(start, end)) { int copy = min_t(int, SKB_MAX_ORDER(0, 0), end - start); struct sk_buff *nskb; nskb = alloc_skb(copy, GFP_ATOMIC); if (!nskb) - return; + break; memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start; - __skb_queue_before(list, skb, nskb); + if (list) + __skb_queue_before(list, skb, nskb); + else + __skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */ skb_set_owner_r(nskb, sk); /* Copy data, releasing collapsed skbs. */ @@ -4814,14 +4857,17 @@ restart: start += size; } if (!before(start, TCP_SKB_CB(skb)->end_seq)) { - skb = tcp_collapse_one(sk, skb, list); + skb = tcp_collapse_one(sk, skb, list, root); if (!skb || skb == tail || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) - return; + goto end; } } } +end: + skb_queue_walk_safe(&tmp, skb, n) + tcp_rbtree_insert(root, skb); } /* Collapse ofo queue. Algorithm: select contiguous sequence of skbs @@ -4830,43 +4876,43 @@ restart: static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = skb_peek(&tp->out_of_order_queue); - struct sk_buff *head; + struct sk_buff *skb, *head; + struct rb_node *p; u32 start, end; - if (!skb) + p = rb_first(&tp->out_of_order_queue); + skb = rb_entry_safe(p, struct sk_buff, rbnode); +new_range: + if (!skb) { + p = rb_last(&tp->out_of_order_queue); + /* Note: This is possible p is NULL here. We do not + * use rb_entry_safe(), as ooo_last_skb is valid only + * if rbtree is not empty. + */ + tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode); return; - + } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; - head = skb; - - for (;;) { - struct sk_buff *next = NULL; - if (!skb_queue_is_last(&tp->out_of_order_queue, skb)) - next = skb_queue_next(&tp->out_of_order_queue, skb); - skb = next; + for (head = skb;;) { + skb = tcp_skb_next(skb, NULL); - /* Segment is terminated when we see gap or when - * we are at the end of all the queue. */ + /* Range is terminated when we see a gap or when + * we are at the queue end. + */ if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { - tcp_collapse(sk, &tp->out_of_order_queue, + tcp_collapse(sk, NULL, &tp->out_of_order_queue, head, skb, start, end); - head = skb; - if (!skb) - break; - /* Start new segment */ + goto new_range; + } + + if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; + if (after(TCP_SKB_CB(skb)->end_seq, end)) end = TCP_SKB_CB(skb)->end_seq; - } else { - if (before(TCP_SKB_CB(skb)->seq, start)) - start = TCP_SKB_CB(skb)->seq; - if (after(TCP_SKB_CB(skb)->end_seq, end)) - end = TCP_SKB_CB(skb)->end_seq; - } } } @@ -4883,20 +4929,24 @@ static void tcp_collapse_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; + struct rb_node *node, *prev; - if (skb_queue_empty(&tp->out_of_order_queue)) + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); - - while ((skb = __skb_dequeue_tail(&tp->out_of_order_queue)) != NULL) { - tcp_drop(sk, skb); + node = &tp->ooo_last_skb->rbnode; + do { + prev = rb_prev(node); + rb_erase(node, &tp->out_of_order_queue); + tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode)); sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) break; - } + node = prev; + } while (node); + tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode); /* Reset SACK state. A conforming SACK implementation will * do the same at a timeout based retransmit. When a connection @@ -4930,7 +4980,7 @@ static int tcp_prune_queue(struct sock *sk) tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) - tcp_collapse(sk, &sk->sk_receive_queue, + tcp_collapse(sk, &sk->sk_receive_queue, NULL, skb_peek(&sk->sk_receive_queue), NULL, tp->copied_seq, tp->rcv_nxt); @@ -5035,7 +5085,7 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) /* We ACK each frame or... */ tcp_in_quickack_mode(sk) || /* We have out of order data. */ - (ofo_possible && skb_peek(&tp->out_of_order_queue))) { + (ofo_possible && !RB_EMPTY_ROOT(&tp->out_of_order_queue))) { /* Then ack it now */ tcp_send_ack(sk); } else { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a75bf48d7950..04b989328558 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1845,7 +1845,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_write_queue_purge(sk); /* Cleans up our, hopefully empty, out_of_order_queue. */ - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4b95ec4ed2c8..f63c73dc0acb 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -488,7 +488,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->snd_cwnd_cnt = 0; tcp_init_xmit_timers(newsk); - __skb_queue_head_init(&newtp->out_of_order_queue); newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; newtp->rx_opt.saw_tstamp = 0; -- cgit v1.3-14-g43fede 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 v1.3-14-g43fede 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 --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c | 1 + drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c | 3 ++- include/linux/mmc/sdio_ids.h | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index f549c25608d6..03404cbe9237 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -1101,6 +1101,7 @@ static const struct sdio_device_id brcmf_sdmmc_ids[] = { BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_43341), BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_43362), BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4335_4339), + BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4339), BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_43430), BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4345), BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4354), diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 68ab3ac15650..589a49cd9cd5 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -3757,7 +3757,8 @@ static u32 brcmf_sdio_buscore_read32(void *ctx, u32 addr) u32 val, rev; val = brcmf_sdiod_regrl(sdiodev, addr, NULL); - if (sdiodev->func[0]->device == SDIO_DEVICE_ID_BROADCOM_4335_4339 && + if ((sdiodev->func[0]->device == SDIO_DEVICE_ID_BROADCOM_4335_4339 || + sdiodev->func[0]->device == SDIO_DEVICE_ID_BROADCOM_4339) && addr == CORE_CC_REG(SI_ENUM_BASE, chipid)) { rev = (val & CID_REV_MASK) >> CID_REV_SHIFT; if (rev >= 2) { 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 v1.3-14-g43fede 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 ++++++++++++++ kernel/trace/bpf_trace.c | 12 ++++++------ net/core/filter.c | 15 +++++++-------- 3 files changed, 27 insertions(+), 14 deletions(-) (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 { diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d3869b03d9fe..e63d7d435796 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -583,18 +583,18 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, int dst_reg, switch (ctx_off) { case offsetof(struct bpf_perf_event_data, sample_period): BUILD_BUG_ON(FIELD_SIZEOF(struct perf_sample_data, period) != sizeof(u64)); - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct bpf_perf_event_data_kern, data)), - dst_reg, src_reg, + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, + data), dst_reg, src_reg, offsetof(struct bpf_perf_event_data_kern, data)); *insn++ = BPF_LDX_MEM(BPF_DW, dst_reg, dst_reg, offsetof(struct perf_sample_data, period)); break; default: - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct bpf_perf_event_data_kern, regs)), - dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, + regs), dst_reg, src_reg, offsetof(struct bpf_perf_event_data_kern, regs)); - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(sizeof(long)), - dst_reg, dst_reg, ctx_off); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(long), dst_reg, dst_reg, ctx_off); break; } diff --git a/net/core/filter.c b/net/core/filter.c index 628ed8c7d38d..120c813ef030 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -233,9 +233,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_HATYPE: BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); - BUILD_BUG_ON(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)) < 0); - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, dev)); /* if (tmp != 0) goto pc + 1 */ @@ -2685,7 +2684,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, case offsetof(struct __sk_buff, ifindex): BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), dst_reg, src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); @@ -2750,7 +2749,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, break; case offsetof(struct __sk_buff, data): - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, data)), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), dst_reg, src_reg, offsetof(struct sk_buff, data)); break; @@ -2759,8 +2758,8 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, ctx_off -= offsetof(struct __sk_buff, data_end); ctx_off += offsetof(struct sk_buff, cb); ctx_off += offsetof(struct bpf_skb_data_end, data_end); - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(sizeof(void *)), - dst_reg, src_reg, ctx_off); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), dst_reg, src_reg, + ctx_off); break; case offsetof(struct __sk_buff, tc_index): @@ -2795,12 +2794,12 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, int dst_reg, switch (ctx_off) { case offsetof(struct xdp_md, data): - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct xdp_buff, data)), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data), dst_reg, src_reg, offsetof(struct xdp_buff, data)); break; case offsetof(struct xdp_md, data_end): - *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct xdp_buff, data_end)), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), dst_reg, src_reg, offsetof(struct xdp_buff, data_end)); break; -- cgit v1.3-14-g43fede 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 ++++++++++++++++++ kernel/bpf/core.c | 2 +- kernel/bpf/helpers.c | 46 +++++------------ kernel/bpf/stackmap.c | 5 +- kernel/trace/bpf_trace.c | 75 +++++++++++++-------------- net/core/filter.c | 129 ++++++++++++++++++----------------------------- 6 files changed, 149 insertions(+), 158 deletions(-) (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 { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 03fd23d4d587..7b7baaed9ed4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1018,7 +1018,7 @@ void bpf_user_rnd_init_once(void) prandom_init_once(&bpf_user_rnd_state); } -u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_0(bpf_user_rnd_u32) { /* Should someone ever have the rather unwise idea to use some * of the registers passed into this function, then note that diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6df73bd1ba34..a5b8bf8cfcfd 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -16,6 +16,7 @@ #include #include #include +#include /* If kernel subsystem is allowing eBPF programs to call this function, * inside its own verifier_ops->get_func_proto() callback it should return @@ -26,24 +27,10 @@ * if program is allowed to access maps, so check rcu_read_lock_held in * all three functions. */ -static u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key) { - /* verifier checked that R1 contains a valid pointer to bpf_map - * and R2 points to a program stack and map->key_size bytes were - * initialized - */ - struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; - void *key = (void *) (unsigned long) r2; - void *value; - WARN_ON_ONCE(!rcu_read_lock_held()); - - value = map->ops->map_lookup_elem(map, key); - - /* lookup() returns either pointer to element value or NULL - * which is the meaning of PTR_TO_MAP_VALUE_OR_NULL type - */ - return (unsigned long) value; + return (unsigned long) map->ops->map_lookup_elem(map, key); } const struct bpf_func_proto bpf_map_lookup_elem_proto = { @@ -54,15 +41,11 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = { .arg2_type = ARG_PTR_TO_MAP_KEY, }; -static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key, + void *, value, u64, flags) { - struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; - void *key = (void *) (unsigned long) r2; - void *value = (void *) (unsigned long) r3; - WARN_ON_ONCE(!rcu_read_lock_held()); - - return map->ops->map_update_elem(map, key, value, r4); + return map->ops->map_update_elem(map, key, value, flags); } const struct bpf_func_proto bpf_map_update_elem_proto = { @@ -75,13 +58,9 @@ const struct bpf_func_proto bpf_map_update_elem_proto = { .arg4_type = ARG_ANYTHING, }; -static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key) { - struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; - void *key = (void *) (unsigned long) r2; - WARN_ON_ONCE(!rcu_read_lock_held()); - return map->ops->map_delete_elem(map, key); } @@ -99,7 +78,7 @@ const struct bpf_func_proto bpf_get_prandom_u32_proto = { .ret_type = RET_INTEGER, }; -static u64 bpf_get_smp_processor_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_0(bpf_get_smp_processor_id) { return smp_processor_id(); } @@ -110,7 +89,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto = { .ret_type = RET_INTEGER, }; -static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_0(bpf_ktime_get_ns) { /* NMI safe access to clock monotonic */ return ktime_get_mono_fast_ns(); @@ -122,7 +101,7 @@ const struct bpf_func_proto bpf_ktime_get_ns_proto = { .ret_type = RET_INTEGER, }; -static u64 bpf_get_current_pid_tgid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_0(bpf_get_current_pid_tgid) { struct task_struct *task = current; @@ -138,7 +117,7 @@ const struct bpf_func_proto bpf_get_current_pid_tgid_proto = { .ret_type = RET_INTEGER, }; -static u64 bpf_get_current_uid_gid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_0(bpf_get_current_uid_gid) { struct task_struct *task = current; kuid_t uid; @@ -158,10 +137,9 @@ const struct bpf_func_proto bpf_get_current_uid_gid_proto = { .ret_type = RET_INTEGER, }; -static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5) +BPF_CALL_2(bpf_get_current_comm, char *, buf, u32, size) { struct task_struct *task = current; - char *buf = (char *) (long) r1; if (unlikely(!task)) goto err_clear; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index bf4495fcd25d..732ae16d12b7 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -116,10 +116,9 @@ free_smap: return ERR_PTR(err); } -u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, + u64, flags) { - struct pt_regs *regs = (struct pt_regs *) (long) r1; - struct bpf_map *map = (struct bpf_map *) (long) r2; struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct perf_callchain_entry *trace; struct stack_map_bucket *bucket, *new_bucket, *old_bucket; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e63d7d435796..5dcb99281259 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -61,11 +61,9 @@ unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx) } EXPORT_SYMBOL_GPL(trace_call_bpf); -static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr) { - void *dst = (void *) (long) r1; - int ret, size = (int) r2; - void *unsafe_ptr = (void *) (long) r3; + int ret; ret = probe_kernel_read(dst, unsafe_ptr, size); if (unlikely(ret < 0)) @@ -83,12 +81,9 @@ static const struct bpf_func_proto bpf_probe_read_proto = { .arg3_type = ARG_ANYTHING, }; -static u64 bpf_probe_write_user(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, + u32, size) { - void *unsafe_ptr = (void *) (long) r1; - void *src = (void *) (long) r2; - int size = (int) r3; - /* * Ensure we're in user context which is safe for the helper to * run. This helper has no business in a kthread. @@ -130,9 +125,9 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void) * limited trace_printk() * only %d %u %x %ld %lu %lx %lld %llu %llx %p %s conversion specifiers allowed */ -static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5) +BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, + u64, arg2, u64, arg3) { - char *fmt = (char *) (long) r1; bool str_seen = false; int mod[3] = {}; int fmt_cnt = 0; @@ -178,16 +173,16 @@ static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5) switch (fmt_cnt) { case 1: - unsafe_addr = r3; - r3 = (long) buf; + unsafe_addr = arg1; + arg1 = (long) buf; break; case 2: - unsafe_addr = r4; - r4 = (long) buf; + unsafe_addr = arg2; + arg2 = (long) buf; break; case 3: - unsafe_addr = r5; - r5 = (long) buf; + unsafe_addr = arg3; + arg3 = (long) buf; break; } buf[0] = 0; @@ -209,9 +204,9 @@ static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5) } return __trace_printk(1/* fake ip will not be printed */, fmt, - mod[0] == 2 ? r3 : mod[0] == 1 ? (long) r3 : (u32) r3, - mod[1] == 2 ? r4 : mod[1] == 1 ? (long) r4 : (u32) r4, - mod[2] == 2 ? r5 : mod[2] == 1 ? (long) r5 : (u32) r5); + mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1, + mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2, + mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3); } static const struct bpf_func_proto bpf_trace_printk_proto = { @@ -233,9 +228,8 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -static u64 bpf_perf_event_read(u64 r1, u64 flags, u64 r3, u64 r4, u64 r5) +BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) { - struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; @@ -312,11 +306,9 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, return 0; } -static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size) +BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, + u64, flags, void *, data, u64, size) { - struct pt_regs *regs = (struct pt_regs *)(long) r1; - struct bpf_map *map = (struct bpf_map *)(long) r2; - void *data = (void *)(long) r4; struct perf_raw_record raw = { .frag = { .size = size, @@ -367,7 +359,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, return __bpf_perf_event_output(regs, map, flags, &raw); } -static u64 bpf_get_current_task(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_0(bpf_get_current_task) { return (long) current; } @@ -378,16 +370,13 @@ static const struct bpf_func_proto bpf_get_current_task_proto = { .ret_type = RET_INTEGER, }; -static u64 bpf_current_task_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) { - struct bpf_map *map = (struct bpf_map *)(long)r1; struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; - u32 idx = (u32)r2; if (unlikely(in_interrupt())) return -EINVAL; - if (unlikely(idx >= array->map.max_entries)) return -E2BIG; @@ -481,16 +470,17 @@ static struct bpf_prog_type_list kprobe_tl = { .type = BPF_PROG_TYPE_KPROBE, }; -static u64 bpf_perf_event_output_tp(u64 r1, u64 r2, u64 index, u64 r4, u64 size) +BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map, + u64, flags, void *, data, u64, size) { + struct pt_regs *regs = *(struct pt_regs **)tp_buff; + /* * r1 points to perf tracepoint buffer where first 8 bytes are hidden * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it - * from there and call the same bpf_perf_event_output() helper + * from there and call the same bpf_perf_event_output() helper inline. */ - u64 ctx = *(long *)(uintptr_t)r1; - - return bpf_perf_event_output(ctx, r2, index, r4, size); + return ____bpf_perf_event_output(regs, map, flags, data, size); } static const struct bpf_func_proto bpf_perf_event_output_proto_tp = { @@ -504,11 +494,18 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = { .arg5_type = ARG_CONST_STACK_SIZE, }; -static u64 bpf_get_stackid_tp(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_3(bpf_get_stackid_tp, void *, tp_buff, struct bpf_map *, map, + u64, flags) { - u64 ctx = *(long *)(uintptr_t)r1; + struct pt_regs *regs = *(struct pt_regs **)tp_buff; - return bpf_get_stackid(ctx, r2, r3, r4, r5); + /* + * Same comment as in bpf_perf_event_output_tp(), only that this time + * the other helper's function body cannot be inlined due to being + * external, thus we need to call raw helper function. + */ + return bpf_get_stackid((unsigned long) regs, (unsigned long) map, + flags, 0, 0); } static const struct bpf_func_proto bpf_get_stackid_proto_tp = { diff --git a/net/core/filter.c b/net/core/filter.c index d6d9bb89ce3a..298b146b47e7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -94,14 +94,13 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) } EXPORT_SYMBOL(sk_filter_trim_cap); -static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +BPF_CALL_1(__skb_get_pay_offset, struct sk_buff *, skb) { - return skb_get_poff((struct sk_buff *)(unsigned long) ctx); + return skb_get_poff(skb); } -static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) { - struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; struct nlattr *nla; if (skb_is_nonlinear(skb)) @@ -120,9 +119,8 @@ static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) return 0; } -static u64 __skb_get_nlattr_nest(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) { - struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; struct nlattr *nla; if (skb_is_nonlinear(skb)) @@ -145,7 +143,7 @@ static u64 __skb_get_nlattr_nest(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) return 0; } -static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +BPF_CALL_0(__get_raw_cpu_id) { return raw_smp_processor_id(); } @@ -1376,12 +1374,9 @@ static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len); } -static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) +BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset, + const void *, from, u32, len, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - unsigned int offset = (unsigned int) r2; - void *from = (void *) (long) r3; - unsigned int len = (unsigned int) r4; void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) @@ -1416,12 +1411,9 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .arg5_type = ARG_ANYTHING, }; -static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset, + void *, to, u32, len) { - const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1; - unsigned int offset = (unsigned int) r2; - void *to = (void *)(unsigned long) r3; - unsigned int len = (unsigned int) r4; void *ptr; if (unlikely(offset > 0xffff)) @@ -1449,10 +1441,9 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .arg4_type = ARG_CONST_STACK_SIZE, }; -static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) +BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, + u64, from, u64, to, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - unsigned int offset = (unsigned int) r2; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) @@ -1494,12 +1485,11 @@ static const struct bpf_func_proto bpf_l3_csum_replace_proto = { .arg5_type = ARG_ANYTHING, }; -static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) +BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, + u64, from, u64, to, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; - unsigned int offset = (unsigned int) r2; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR | @@ -1547,12 +1537,11 @@ static const struct bpf_func_proto bpf_l4_csum_replace_proto = { .arg5_type = ARG_ANYTHING, }; -static u64 bpf_csum_diff(u64 r1, u64 from_size, u64 r3, u64 to_size, u64 seed) +BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, + __be32 *, to, u32, to_size, __wsum, seed) { struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); - u64 diff_size = from_size + to_size; - __be32 *from = (__be32 *) (long) r1; - __be32 *to = (__be32 *) (long) r3; + u32 diff_size = from_size + to_size; int i, j = 0; /* This is quite flexible, some examples: @@ -1610,9 +1599,8 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) return ret; } -static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) +BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; struct net_device *dev; if (unlikely(flags & ~(BPF_F_INGRESS))) @@ -1648,7 +1636,7 @@ struct redirect_info { static DEFINE_PER_CPU(struct redirect_info, redirect_info); -static u64 bpf_redirect(u64 ifindex, u64 flags, u64 r3, u64 r4, u64 r5) +BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); @@ -1687,9 +1675,9 @@ static const struct bpf_func_proto bpf_redirect_proto = { .arg2_type = ARG_ANYTHING, }; -static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { - return task_get_classid((struct sk_buff *) (unsigned long) r1); + return task_get_classid(skb); } static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { @@ -1699,9 +1687,9 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_1(bpf_get_route_realm, const struct sk_buff *, skb) { - return dst_tclassid((struct sk_buff *) (unsigned long) r1); + return dst_tclassid(skb); } static const struct bpf_func_proto bpf_get_route_realm_proto = { @@ -1711,14 +1699,14 @@ static const struct bpf_func_proto bpf_get_route_realm_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -static u64 bpf_get_hash_recalc(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_1(bpf_get_hash_recalc, struct sk_buff *, skb) { /* If skb_clear_hash() was called due to mangling, we can * trigger SW recalculation here. Later access to hash * can then use the inline skb->hash via context directly * instead of calling this helper again. */ - return skb_get_hash((struct sk_buff *) (unsigned long) r1); + return skb_get_hash(skb); } static const struct bpf_func_proto bpf_get_hash_recalc_proto = { @@ -1728,10 +1716,9 @@ static const struct bpf_func_proto bpf_get_hash_recalc_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, + u16, vlan_tci) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - __be16 vlan_proto = (__force __be16) r2; int ret; if (unlikely(vlan_proto != htons(ETH_P_8021Q) && @@ -1756,9 +1743,8 @@ const struct bpf_func_proto bpf_skb_vlan_push_proto = { }; EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto); -static u64 bpf_skb_vlan_pop(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; int ret; bpf_push_mac_rcsum(skb); @@ -1933,10 +1919,9 @@ static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) return -ENOTSUPP; } -static u64 bpf_skb_change_proto(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, + u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - __be16 proto = (__force __be16) r2; int ret; if (unlikely(flags)) @@ -1973,11 +1958,8 @@ static const struct bpf_func_proto bpf_skb_change_proto_proto = { .arg3_type = ARG_ANYTHING, }; -static u64 bpf_skb_change_type(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_2(bpf_skb_change_type, struct sk_buff *, skb, u32, pkt_type) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - u32 pkt_type = r2; - /* We only allow a restricted subset to be changed for now. */ if (unlikely(!skb_pkt_type_ok(skb->pkt_type) || !skb_pkt_type_ok(pkt_type))) @@ -2028,12 +2010,11 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) return __skb_trim_rcsum(skb, new_len); } -static u64 bpf_skb_change_tail(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, + u64, flags) { - struct sk_buff *skb = (struct sk_buff *)(long) r1; u32 max_len = __bpf_skb_max_len(skb); u32 min_len = __bpf_skb_min_len(skb); - u32 new_len = (u32) r2; int ret; if (unlikely(flags || new_len > max_len || new_len < min_len)) @@ -2113,13 +2094,10 @@ static unsigned long bpf_skb_copy(void *dst_buff, const void *skb, return 0; } -static u64 bpf_skb_event_output(u64 r1, u64 r2, u64 flags, u64 r4, - u64 meta_size) +BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map, + u64, flags, void *, meta, u64, meta_size) { - struct sk_buff *skb = (struct sk_buff *)(long) r1; - struct bpf_map *map = (struct bpf_map *)(long) r2; u64 skb_size = (flags & BPF_F_CTXLEN_MASK) >> 32; - void *meta = (void *)(long) r4; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; @@ -2146,10 +2124,9 @@ static unsigned short bpf_tunnel_key_af(u64 flags) return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET; } -static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) +BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key *, to, + u32, size, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - struct bpf_tunnel_key *to = (struct bpf_tunnel_key *) (long) r2; const struct ip_tunnel_info *info = skb_tunnel_info(skb); u8 compat[sizeof(struct bpf_tunnel_key)]; void *to_orig = to; @@ -2214,10 +2191,8 @@ static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; -static u64 bpf_skb_get_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - u8 *to = (u8 *) (long) r2; const struct ip_tunnel_info *info = skb_tunnel_info(skb); int err; @@ -2252,10 +2227,9 @@ static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { static struct metadata_dst __percpu *md_dst; -static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) +BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, + const struct bpf_tunnel_key *, from, u32, size, u64, flags) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - struct bpf_tunnel_key *from = (struct bpf_tunnel_key *) (long) r2; struct metadata_dst *md = this_cpu_ptr(md_dst); u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; @@ -2273,7 +2247,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) */ memcpy(compat, from, size); memset(compat + size, 0, sizeof(compat) - size); - from = (struct bpf_tunnel_key *)compat; + from = (const struct bpf_tunnel_key *) compat; break; default: return -EINVAL; @@ -2323,10 +2297,9 @@ static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; -static u64 bpf_skb_set_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, + const u8 *, from, u32, size) { - struct sk_buff *skb = (struct sk_buff *) (long) r1; - u8 *from = (u8 *) (long) r2; struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct metadata_dst *md = this_cpu_ptr(md_dst); @@ -2372,23 +2345,20 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) } } -static u64 bpf_skb_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +BPF_CALL_3(bpf_skb_under_cgroup, struct sk_buff *, skb, struct bpf_map *, map, + u32, idx) { - struct sk_buff *skb = (struct sk_buff *)(long)r1; - struct bpf_map *map = (struct bpf_map *)(long)r2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; struct sock *sk; - u32 i = (u32)r3; sk = skb->sk; if (!sk || !sk_fullsock(sk)) return -ENOENT; - - if (unlikely(i >= array->map.max_entries)) + if (unlikely(idx >= array->map.max_entries)) return -E2BIG; - cgrp = READ_ONCE(array->ptrs[i]); + cgrp = READ_ONCE(array->ptrs[idx]); if (unlikely(!cgrp)) return -EAGAIN; @@ -2411,13 +2381,10 @@ static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, return 0; } -static u64 bpf_xdp_event_output(u64 r1, u64 r2, u64 flags, u64 r4, - u64 meta_size) +BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, + u64, flags, void *, meta, u64, meta_size) { - struct xdp_buff *xdp = (struct xdp_buff *)(long) r1; - struct bpf_map *map = (struct bpf_map *)(long) r2; u64 xdp_size = (flags & BPF_F_CTXLEN_MASK) >> 32; - void *meta = (void *)(long) r4; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; -- cgit v1.3-14-g43fede 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 --- fs/crypto/policy.c | 38 +++++++++++++++++++++++++------------- fs/ext4/ioctl.c | 2 +- fs/f2fs/file.c | 9 +-------- include/linux/fscrypto.h | 5 ++--- 4 files changed, 29 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index f96547f83cab..ed115acb5dee 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -11,6 +11,7 @@ #include #include #include +#include static int inode_has_encryption_context(struct inode *inode) { @@ -92,31 +93,42 @@ static int create_encryption_context_from_policy(struct inode *inode, return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL); } -int fscrypt_process_policy(struct inode *inode, +int fscrypt_process_policy(struct file *filp, const struct fscrypt_policy *policy) { + struct inode *inode = file_inode(filp); + int ret; + if (!inode_owner_or_capable(inode)) return -EACCES; if (policy->version != 0) return -EINVAL; + ret = mnt_want_write_file(filp); + if (ret) + return ret; + if (!inode_has_encryption_context(inode)) { if (!S_ISDIR(inode->i_mode)) - return -EINVAL; - if (!inode->i_sb->s_cop->empty_dir) - return -EOPNOTSUPP; - if (!inode->i_sb->s_cop->empty_dir(inode)) - return -ENOTEMPTY; - return create_encryption_context_from_policy(inode, policy); + ret = -EINVAL; + else if (!inode->i_sb->s_cop->empty_dir) + ret = -EOPNOTSUPP; + else if (!inode->i_sb->s_cop->empty_dir(inode)) + ret = -ENOTEMPTY; + else + ret = create_encryption_context_from_policy(inode, + policy); + } else if (!is_encryption_context_consistent_with_policy(inode, + policy)) { + printk(KERN_WARNING + "%s: Policy inconsistent with encryption context\n", + __func__); + ret = -EINVAL; } - if (is_encryption_context_consistent_with_policy(inode, policy)) - return 0; - - printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n", - __func__); - return -EINVAL; + mnt_drop_write_file(filp); + return ret; } EXPORT_SYMBOL(fscrypt_process_policy); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 10686fd67fb4..1bb7df5e4536 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -776,7 +776,7 @@ resizefs_out: (struct fscrypt_policy __user *)arg, sizeof(policy))) return -EFAULT; - return fscrypt_process_policy(inode, &policy); + return fscrypt_process_policy(filp, &policy); #else return -EOPNOTSUPP; #endif diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 47abb96098e4..28f4f4cbb8d8 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1757,21 +1757,14 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) { struct fscrypt_policy policy; struct inode *inode = file_inode(filp); - int ret; if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg, sizeof(policy))) return -EFAULT; - ret = mnt_want_write_file(filp); - if (ret) - return ret; - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); - ret = fscrypt_process_policy(inode, &policy); - mnt_drop_write_file(filp); - return ret; + return fscrypt_process_policy(filp, &policy); } static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg) 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 v1.3-14-g43fede 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 --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 12 +- .../net/ethernet/mellanox/mlx5/core/mlx5_core.h | 2 + drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 216 +++++++++------------ include/linux/mlx5/driver.h | 2 - 4 files changed, 101 insertions(+), 131 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c132ef1faefe..baba53fb58b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1180,8 +1180,7 @@ out: return 0; err_sriov: - if (mlx5_sriov_cleanup(dev)) - dev_err(&dev->pdev->dev, "sriov cleanup failed\n"); + mlx5_sriov_cleanup(dev); #ifdef CONFIG_MLX5_CORE_EN mlx5_eswitch_cleanup(dev->priv.eswitch); @@ -1241,19 +1240,14 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) { int err = 0; - err = mlx5_sriov_cleanup(dev); - if (err) { - dev_warn(&dev->pdev->dev, "%s: sriov cleanup failed - abort\n", - __func__); - return err; - } - mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n", __func__); goto out; } + + mlx5_sriov_cleanup(dev); mlx5_unregister_device(dev); #ifdef CONFIG_MLX5_CORE_EN mlx5_eswitch_cleanup(dev->priv.eswitch); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 714b71bed2be..7dd14cf73181 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -89,6 +89,8 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); void mlx5_enter_error_state(struct mlx5_core_dev *dev); void mlx5_disable_device(struct mlx5_core_dev *dev); +int mlx5_sriov_init(struct mlx5_core_dev *dev); +void mlx5_sriov_cleanup(struct mlx5_core_dev *dev); int mlx5_core_sriov_configure(struct pci_dev *dev, int num_vfs); bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev); int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 78e789245183..72a8215a2d02 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -44,108 +44,132 @@ bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev) return !!sriov->num_vfs; } -static void enable_vfs(struct mlx5_core_dev *dev, int num_vfs) +static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) { struct mlx5_core_sriov *sriov = &dev->priv.sriov; int err; int vf; - for (vf = 1; vf <= num_vfs; vf++) { - err = mlx5_core_enable_hca(dev, vf); + if (sriov->enabled_vfs) { + mlx5_core_warn(dev, + "failed to enable SRIOV on device, already enabled with %d vfs\n", + sriov->enabled_vfs); + return -EBUSY; + } + +#ifdef CONFIG_MLX5_CORE_EN + err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY); + if (err) { + mlx5_core_warn(dev, + "failed to enable eswitch SRIOV (%d)\n", err); + return err; + } +#endif + + for (vf = 0; vf < num_vfs; vf++) { + err = mlx5_core_enable_hca(dev, vf + 1); if (err) { - mlx5_core_warn(dev, "failed to enable VF %d\n", vf - 1); - } else { - sriov->vfs_ctx[vf - 1].enabled = 1; - mlx5_core_dbg(dev, "successfully enabled VF %d\n", vf - 1); + mlx5_core_warn(dev, "failed to enable VF %d (%d)\n", vf, err); + continue; } + sriov->vfs_ctx[vf].enabled = 1; + sriov->enabled_vfs++; + mlx5_core_dbg(dev, "successfully enabled VF* %d\n", vf); + } + + return 0; } -static void disable_vfs(struct mlx5_core_dev *dev, int num_vfs) +static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev) { struct mlx5_core_sriov *sriov = &dev->priv.sriov; + int err; int vf; - for (vf = 1; vf <= num_vfs; vf++) { - if (sriov->vfs_ctx[vf - 1].enabled) { - if (mlx5_core_disable_hca(dev, vf)) - mlx5_core_warn(dev, "failed to disable VF %d\n", vf - 1); - else - sriov->vfs_ctx[vf - 1].enabled = 0; + if (!sriov->enabled_vfs) + return; + + for (vf = 0; vf < sriov->num_vfs; vf++) { + if (!sriov->vfs_ctx[vf].enabled) + continue; + err = mlx5_core_disable_hca(dev, vf + 1); + if (err) { + mlx5_core_warn(dev, "failed to disable VF %d\n", vf); + continue; } + sriov->vfs_ctx[vf].enabled = 0; + sriov->enabled_vfs--; } + +#ifdef CONFIG_MLX5_CORE_EN + mlx5_eswitch_disable_sriov(dev->priv.eswitch); +#endif + + if (mlx5_wait_for_vf_pages(dev)) + mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } -static int mlx5_core_create_vfs(struct pci_dev *pdev, int num_vfs) +static int mlx5_pci_enable_sriov(struct pci_dev *pdev, int num_vfs) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); - int err; - - if (pci_num_vf(pdev)) - pci_disable_sriov(pdev); - - enable_vfs(dev, num_vfs); + int err = 0; - err = pci_enable_sriov(pdev, num_vfs); - if (err) { - dev_warn(&pdev->dev, "enable sriov failed %d\n", err); - goto ex; + if (pci_num_vf(pdev)) { + mlx5_core_warn(dev, "Unable to enable pci sriov, already enabled\n"); + return -EBUSY; } - return 0; + err = pci_enable_sriov(pdev, num_vfs); + if (err) + mlx5_core_warn(dev, "pci_enable_sriov failed : %d\n", err); -ex: - disable_vfs(dev, num_vfs); return err; } -static int mlx5_core_sriov_enable(struct pci_dev *pdev, int num_vfs) +static void mlx5_pci_disable_sriov(struct pci_dev *pdev) +{ + pci_disable_sriov(pdev); +} + +static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct mlx5_core_sriov *sriov = &dev->priv.sriov; - int err; + int err = 0; - kfree(sriov->vfs_ctx); - sriov->vfs_ctx = kcalloc(num_vfs, sizeof(*sriov->vfs_ctx), GFP_ATOMIC); - if (!sriov->vfs_ctx) - return -ENOMEM; + err = mlx5_device_enable_sriov(dev, num_vfs); + if (err) { + mlx5_core_warn(dev, "mlx5_device_enable_sriov failed : %d\n", err); + return err; + } - sriov->enabled_vfs = num_vfs; - err = mlx5_core_create_vfs(pdev, num_vfs); + err = mlx5_pci_enable_sriov(pdev, num_vfs); if (err) { - kfree(sriov->vfs_ctx); - sriov->vfs_ctx = NULL; + mlx5_core_warn(dev, "mlx5_pci_enable_sriov failed : %d\n", err); + mlx5_device_disable_sriov(dev); return err; } + sriov->num_vfs = num_vfs; + return 0; } -static void mlx5_core_init_vfs(struct mlx5_core_dev *dev, int num_vfs) +static void mlx5_sriov_disable(struct pci_dev *pdev) { + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct mlx5_core_sriov *sriov = &dev->priv.sriov; - sriov->num_vfs = num_vfs; -} - -static void mlx5_core_cleanup_vfs(struct mlx5_core_dev *dev) -{ - struct mlx5_core_sriov *sriov; - - sriov = &dev->priv.sriov; - disable_vfs(dev, sriov->num_vfs); - - if (mlx5_wait_for_vf_pages(dev)) - mlx5_core_warn(dev, "timeout claiming VFs pages\n"); - + mlx5_pci_disable_sriov(pdev); + mlx5_device_disable_sriov(dev); sriov->num_vfs = 0; } int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); - struct mlx5_core_sriov *sriov = &dev->priv.sriov; - int err; + int err = 0; mlx5_core_dbg(dev, "requested num_vfs %d\n", num_vfs); if (!mlx5_core_is_pf(dev)) @@ -156,92 +180,44 @@ int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs) return -EINVAL; } - mlx5_core_cleanup_vfs(dev); - - if (!num_vfs) { -#ifdef CONFIG_MLX5_CORE_EN - mlx5_eswitch_disable_sriov(dev->priv.eswitch); -#endif - kfree(sriov->vfs_ctx); - sriov->vfs_ctx = NULL; - if (!pci_vfs_assigned(pdev)) - pci_disable_sriov(pdev); - else - mlx5_core_info(dev, "unloading PF driver while leaving orphan VFs\n"); - return 0; - } - - err = mlx5_core_sriov_enable(pdev, num_vfs); - if (err) { - mlx5_core_warn(dev, "mlx5_core_sriov_enable failed %d\n", err); - return err; - } + if (num_vfs) + err = mlx5_sriov_enable(pdev, num_vfs); + else + mlx5_sriov_disable(pdev); - mlx5_core_init_vfs(dev, num_vfs); -#ifdef CONFIG_MLX5_CORE_EN - mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY); -#endif - - return num_vfs; -} - -static int sync_required(struct pci_dev *pdev) -{ - struct mlx5_core_dev *dev = pci_get_drvdata(pdev); - struct mlx5_core_sriov *sriov = &dev->priv.sriov; - int cur_vfs = pci_num_vf(pdev); - - if (cur_vfs != sriov->num_vfs) { - mlx5_core_warn(dev, "current VFs %d, registered %d - sync needed\n", - cur_vfs, sriov->num_vfs); - return 1; - } - - return 0; + return err ? err : num_vfs; } int mlx5_sriov_init(struct mlx5_core_dev *dev) { struct mlx5_core_sriov *sriov = &dev->priv.sriov; struct pci_dev *pdev = dev->pdev; - int cur_vfs; + int total_vfs; if (!mlx5_core_is_pf(dev)) return 0; - if (!sync_required(dev->pdev)) - return 0; - - cur_vfs = pci_num_vf(pdev); - sriov->vfs_ctx = kcalloc(cur_vfs, sizeof(*sriov->vfs_ctx), GFP_KERNEL); + total_vfs = pci_sriov_get_totalvfs(pdev); + sriov->num_vfs = pci_num_vf(pdev); + sriov->vfs_ctx = kcalloc(total_vfs, sizeof(*sriov->vfs_ctx), GFP_KERNEL); if (!sriov->vfs_ctx) return -ENOMEM; - sriov->enabled_vfs = cur_vfs; - - mlx5_core_init_vfs(dev, cur_vfs); -#ifdef CONFIG_MLX5_CORE_EN - if (cur_vfs) - mlx5_eswitch_enable_sriov(dev->priv.eswitch, cur_vfs, - SRIOV_LEGACY); -#endif - - enable_vfs(dev, cur_vfs); + /* If sriov VFs exist in PCI level, enable them in device level */ + if (!sriov->num_vfs) + return 0; + mlx5_device_enable_sriov(dev, sriov->num_vfs); return 0; } -int mlx5_sriov_cleanup(struct mlx5_core_dev *dev) +void mlx5_sriov_cleanup(struct mlx5_core_dev *dev) { - struct pci_dev *pdev = dev->pdev; - int err; + struct mlx5_core_sriov *sriov = &dev->priv.sriov; if (!mlx5_core_is_pf(dev)) - return 0; + return; - err = mlx5_core_sriov_configure(pdev, 0); - if (err) - return err; - - return 0; + mlx5_device_disable_sriov(dev); + kfree(sriov->vfs_ctx); } 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 v1.3-14-g43fede 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 --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 149 +++++++++++++++++++++---- include/linux/mlx5/driver.h | 2 + 2 files changed, 131 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index baba53fb58b7..108d8f2e73e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -81,6 +81,7 @@ struct mlx5_device_context { struct list_head list; struct mlx5_interface *intf; void *context; + unsigned long state; }; enum { @@ -778,6 +779,11 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) return -ENOTSUPP; } +enum { + MLX5_INTERFACE_ADDED, + MLX5_INTERFACE_ATTACHED, +}; + static void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) { struct mlx5_device_context *dev_ctx; @@ -786,12 +792,15 @@ static void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) if (!mlx5_lag_intf_add(intf, priv)) return; - dev_ctx = kmalloc(sizeof(*dev_ctx), GFP_KERNEL); + dev_ctx = kzalloc(sizeof(*dev_ctx), GFP_KERNEL); if (!dev_ctx) return; - dev_ctx->intf = intf; + dev_ctx->intf = intf; dev_ctx->context = intf->add(dev); + set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); + if (intf->attach) + set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); if (dev_ctx->context) { spin_lock_irq(&priv->ctx_lock); @@ -802,21 +811,114 @@ static void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) } } +static struct mlx5_device_context *mlx5_get_device(struct mlx5_interface *intf, + struct mlx5_priv *priv) +{ + struct mlx5_device_context *dev_ctx; + + list_for_each_entry(dev_ctx, &priv->ctx_list, list) + if (dev_ctx->intf == intf) + return dev_ctx; + return NULL; +} + static void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv) { struct mlx5_device_context *dev_ctx; struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); - list_for_each_entry(dev_ctx, &priv->ctx_list, list) - if (dev_ctx->intf == intf) { - spin_lock_irq(&priv->ctx_lock); - list_del(&dev_ctx->list); - spin_unlock_irq(&priv->ctx_lock); + dev_ctx = mlx5_get_device(intf, priv); + if (!dev_ctx) + return; + + spin_lock_irq(&priv->ctx_lock); + list_del(&dev_ctx->list); + spin_unlock_irq(&priv->ctx_lock); + + if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) + intf->remove(dev, dev_ctx->context); - intf->remove(dev, dev_ctx->context); - kfree(dev_ctx); + kfree(dev_ctx); +} + +static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv *priv) +{ + struct mlx5_device_context *dev_ctx; + struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); + + dev_ctx = mlx5_get_device(intf, priv); + if (!dev_ctx) + return; + + if (intf->attach) { + if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)) return; - } + intf->attach(dev, dev_ctx->context); + set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); + } else { + if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) + return; + dev_ctx->context = intf->add(dev); + set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); + } +} + +static void mlx5_attach_device(struct mlx5_core_dev *dev) +{ + struct mlx5_priv *priv = &dev->priv; + struct mlx5_interface *intf; + + mutex_lock(&mlx5_intf_mutex); + list_for_each_entry(intf, &intf_list, list) + mlx5_attach_interface(intf, priv); + mutex_unlock(&mlx5_intf_mutex); +} + +static void mlx5_detach_interface(struct mlx5_interface *intf, struct mlx5_priv *priv) +{ + struct mlx5_device_context *dev_ctx; + struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); + + dev_ctx = mlx5_get_device(intf, priv); + if (!dev_ctx) + return; + + if (intf->detach) { + if (!test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)) + return; + intf->detach(dev, dev_ctx->context); + clear_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); + } else { + if (!test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) + return; + intf->remove(dev, dev_ctx->context); + clear_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); + } +} + +static void mlx5_detach_device(struct mlx5_core_dev *dev) +{ + struct mlx5_priv *priv = &dev->priv; + struct mlx5_interface *intf; + + mutex_lock(&mlx5_intf_mutex); + list_for_each_entry(intf, &intf_list, list) + mlx5_detach_interface(intf, priv); + mutex_unlock(&mlx5_intf_mutex); +} + +static bool mlx5_device_registered(struct mlx5_core_dev *dev) +{ + struct mlx5_priv *priv; + bool found = false; + + mutex_lock(&mlx5_intf_mutex); + list_for_each_entry(priv, &mlx5_dev_list, dev_list) + if (priv == &dev->priv) + found = true; + mutex_unlock(&mlx5_intf_mutex); + + return found; } static int mlx5_register_device(struct mlx5_core_dev *dev) @@ -1162,16 +1264,16 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) goto err_sriov; } - err = mlx5_register_device(dev); - if (err) { - dev_err(&pdev->dev, "mlx5_register_device failed %d\n", err); - goto err_reg_dev; + if (mlx5_device_registered(dev)) { + mlx5_attach_device(dev); + } else { + err = mlx5_register_device(dev); + if (err) { + dev_err(&pdev->dev, "mlx5_register_device failed %d\n", err); + goto err_reg_dev; + } } - err = request_module_nowait(MLX5_IB_MOD); - if (err) - pr_info("failed request module on %s\n", MLX5_IB_MOD); - clear_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state); set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); out: @@ -1247,12 +1349,13 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) goto out; } + if (mlx5_device_registered(dev)) + mlx5_detach_device(dev); + mlx5_sriov_cleanup(dev); - mlx5_unregister_device(dev); #ifdef CONFIG_MLX5_CORE_EN mlx5_eswitch_cleanup(dev->priv.eswitch); #endif - mlx5_cleanup_rl_table(dev); mlx5_cleanup_fs(dev); mlx5_cleanup_mkey_table(dev); @@ -1364,6 +1467,9 @@ static int init_one(struct pci_dev *pdev, dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err); goto clean_health; } + err = request_module_nowait(MLX5_IB_MOD); + if (err) + pr_info("failed request module on %s\n", MLX5_IB_MOD); err = devlink_register(devlink, &pdev->dev); if (err) @@ -1391,11 +1497,14 @@ static void remove_one(struct pci_dev *pdev) struct mlx5_priv *priv = &dev->priv; devlink_unregister(devlink); + mlx5_unregister_device(dev); + if (mlx5_unload_one(dev, priv)) { dev_err(&dev->pdev->dev, "mlx5_unload_one failed\n"); mlx5_health_cleanup(dev); return; } + mlx5_health_cleanup(dev); mlx5_pci_close(dev, priv); pci_set_drvdata(pdev, NULL); 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 v1.3-14-g43fede 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 --- drivers/net/hyperv/netvsc.c | 85 +-------------------------------------------- include/linux/hyperv.h | 84 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 85 insertions(+), 84 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 2a9ccc4d9e3c..ff05b9b0837f 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -33,89 +33,6 @@ #include "hyperv_net.h" -/* - * An API to support in-place processing of incoming VMBUS packets. - */ -#define VMBUS_PKT_TRAILER 8 - -static 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 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; - - BUG_ON((read_loc + packetlen + VMBUS_PKT_TRAILER) > dsize); - - /* - * 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 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); -} - /* * Switch the data path from the synthetic interface to the VF * interface. @@ -840,7 +757,7 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device, return msg_size; } -static int netvsc_send_pkt( +static inline int netvsc_send_pkt( struct hv_device *device, struct hv_netvsc_packet *packet, struct netvsc_device *net_device, 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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 +- lib/iov_iter.c | 24 ++---------------------- 2 files changed, 3 insertions(+), 23 deletions(-) (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); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 9e8c7386b3a0..7e3138cfc8c9 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -290,26 +290,6 @@ done: return wanted - bytes; } -/* - * Fault in the first iovec of the given iov_iter, to a maximum length - * of bytes. Returns 0 on success, or non-zero if the memory could not be - * accessed (ie. because it is an invalid address). - * - * writev-intensive code may want this to prefault several iovecs -- that - * would be possible (callers must not rely on the fact that _only_ the - * first iovec will be faulted with the current implementation). - */ -int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) -{ - if (!(i->type & (ITER_BVEC|ITER_KVEC))) { - char __user *buf = i->iov->iov_base + i->iov_offset; - bytes = min(bytes, i->iov->iov_len - i->iov_offset); - return fault_in_pages_readable(buf, bytes); - } - return 0; -} -EXPORT_SYMBOL(iov_iter_fault_in_readable); - /* * Fault in one or more iovecs of the given iov_iter, to a maximum length of * bytes. For each iovec, fault in each page that constitutes the iovec. @@ -317,7 +297,7 @@ EXPORT_SYMBOL(iov_iter_fault_in_readable); * Return 0 on success, or non-zero if the memory could not be accessed (i.e. * because it is an invalid address). */ -int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes) +int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) { size_t skip = i->iov_offset; const struct iovec *iov; @@ -334,7 +314,7 @@ int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes) } return 0; } -EXPORT_SYMBOL(iov_iter_fault_in_multipages_readable); +EXPORT_SYMBOL(iov_iter_fault_in_readable); void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, -- cgit v1.3-14-g43fede 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 v1.3-14-g43fede 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 ++ net/netfilter/core.c | 51 ++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 48 insertions(+), 5 deletions(-) (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! */ diff --git a/net/netfilter/core.c b/net/netfilter/core.c index f39276d1c2d7..2c5327e43a88 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -188,19 +188,17 @@ EXPORT_SYMBOL(nf_unregister_net_hooks); static LIST_HEAD(nf_hook_list); -int nf_register_hook(struct nf_hook_ops *reg) +static int _nf_register_hook(struct nf_hook_ops *reg) { struct net *net, *last; int ret; - rtnl_lock(); for_each_net(net) { ret = nf_register_net_hook(net, reg); if (ret && ret != -ENOENT) goto rollback; } list_add_tail(®->list, &nf_hook_list); - rtnl_unlock(); return 0; rollback: @@ -210,19 +208,34 @@ rollback: break; nf_unregister_net_hook(net, reg); } + return ret; +} + +int nf_register_hook(struct nf_hook_ops *reg) +{ + int ret; + + rtnl_lock(); + ret = _nf_register_hook(reg); rtnl_unlock(); + return ret; } EXPORT_SYMBOL(nf_register_hook); -void nf_unregister_hook(struct nf_hook_ops *reg) +static void _nf_unregister_hook(struct nf_hook_ops *reg) { struct net *net; - rtnl_lock(); list_del(®->list); for_each_net(net) nf_unregister_net_hook(net, reg); +} + +void nf_unregister_hook(struct nf_hook_ops *reg) +{ + rtnl_lock(); + _nf_unregister_hook(reg); rtnl_unlock(); } EXPORT_SYMBOL(nf_unregister_hook); @@ -246,6 +259,26 @@ err: } EXPORT_SYMBOL(nf_register_hooks); +/* Caller MUST take rtnl_lock() */ +int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < n; i++) { + err = _nf_register_hook(®[i]); + if (err) + goto err; + } + return err; + +err: + if (i > 0) + _nf_unregister_hooks(reg, i); + return err; +} +EXPORT_SYMBOL(_nf_register_hooks); + void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) { while (n-- > 0) @@ -253,6 +286,14 @@ void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) } EXPORT_SYMBOL(nf_unregister_hooks); +/* Caller MUST take rtnl_lock */ +void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) +{ + while (n-- > 0) + _nf_unregister_hook(®[n]); +} +EXPORT_SYMBOL(_nf_unregister_hooks); + unsigned int nf_iterate(struct list_head *head, struct sk_buff *skb, struct nf_hook_state *state, -- cgit v1.3-14-g43fede 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 --- fs/notify/group.c | 19 +++++++++++++++++++ fs/notify/notification.c | 8 +++++++- include/linux/fsnotify_backend.h | 3 +++ 3 files changed, 29 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/notify/group.c b/fs/notify/group.c index 3e2dd85be5dd..b47f7cfdcaa4 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -39,6 +39,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) kfree(group); } +/* + * Stop queueing new events for this group. Once this function returns + * fsnotify_add_event() will not add any new events to the group's queue. + */ +void fsnotify_group_stop_queueing(struct fsnotify_group *group) +{ + mutex_lock(&group->notification_mutex); + group->shutdown = true; + mutex_unlock(&group->notification_mutex); +} + /* * Trying to get rid of a group. Remove all marks, flush all events and release * the group reference. @@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) */ void fsnotify_destroy_group(struct fsnotify_group *group) { + /* + * Stop queueing new events. The code below is careful enough to not + * require this but fanotify needs to stop queuing events even before + * fsnotify_destroy_group() is called and this makes the other callers + * of fsnotify_destroy_group() to see the same behavior. + */ + fsnotify_group_stop_queueing(group); + /* clear all inode marks for this group, attach them to destroy_list */ fsnotify_detach_group_marks(group); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index a95d8e037aeb..3d76e65ff84f 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -82,7 +82,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group, * Add an event to the group notification queue. The group can later pull this * event off the queue to deal with. The function returns 0 if the event was * added to the queue, 1 if the event was merged with some other queued event, - * 2 if the queue of events has overflown. + * 2 if the event was not queued - either the queue of events has overflown + * or the group is shutting down. */ int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, @@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group, mutex_lock(&group->notification_mutex); + if (group->shutdown) { + mutex_unlock(&group->notification_mutex); + return 2; + } + if (group->q_len >= group->max_events) { ret = 2; /* Queue overflow event only if it isn't already queued */ 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 v1.3-14-g43fede 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 --- fs/notify/fanotify/fanotify.c | 13 +------------ fs/notify/fanotify/fanotify_user.c | 36 ++++++++++++++++++++++++------------ fs/notify/notification.c | 15 --------------- include/linux/fsnotify_backend.h | 3 --- 4 files changed, 25 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index d2f97ecca6a5..e0e5f7c3c99f 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - wait_event(group->fanotify_data.access_waitq, event->response || - atomic_read(&group->fanotify_data.bypass_perm)); - - if (!event->response) { /* bypass_perm set */ - /* - * Event was canceled because group is being destroyed. Remove - * it from group's event list because we are responsible for - * freeing the permission event. - */ - fsnotify_remove_event(group, &event->fae.fse); - return 0; - } + wait_event(group->fanotify_data.access_waitq, event->response); /* userspace responded, convert to something usable */ switch (event->response) { diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 8e8e6bcd1d43..a64313868d3a 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS struct fanotify_perm_event_info *event, *next; + struct fsnotify_event *fsn_event; /* - * There may be still new events arriving in the notification queue - * but since userspace cannot use fanotify fd anymore, no event can - * enter or leave access_list by now. + * Stop new events from arriving in the notification queue. since + * userspace cannot use fanotify fd anymore, no event can enter or + * leave access_list by now either. */ - spin_lock(&group->fanotify_data.access_lock); - - atomic_inc(&group->fanotify_data.bypass_perm); + fsnotify_group_stop_queueing(group); + /* + * Process all permission events on access_list and notification queue + * and simulate reply from userspace. + */ + spin_lock(&group->fanotify_data.access_lock); list_for_each_entry_safe(event, next, &group->fanotify_data.access_list, fae.fse.list) { pr_debug("%s: found group=%p event=%p\n", __func__, group, @@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file) spin_unlock(&group->fanotify_data.access_lock); /* - * Since bypass_perm is set, newly queued events will not wait for - * access response. Wake up the already sleeping ones now. - * synchronize_srcu() in fsnotify_destroy_group() will wait for all - * processes sleeping in fanotify_handle_event() waiting for access - * response and thus also for all permission events to be freed. + * Destroy all non-permission events. For permission events just + * dequeue them and set the response. They will be freed once the + * response is consumed and fanotify_get_response() returns. */ + mutex_lock(&group->notification_mutex); + while (!fsnotify_notify_queue_is_empty(group)) { + fsn_event = fsnotify_remove_first_event(group); + if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) + fsnotify_destroy_event(group, fsn_event); + else + FANOTIFY_PE(fsn_event)->response = FAN_ALLOW; + } + mutex_unlock(&group->notification_mutex); + + /* Response for all permission events it set, wakeup waiters */ wake_up(&group->fanotify_data.access_waitq); #endif @@ -755,7 +768,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) spin_lock_init(&group->fanotify_data.access_lock); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); - atomic_set(&group->fanotify_data.bypass_perm, 0); #endif switch (flags & FAN_ALL_CLASS_BITS) { case FAN_CLASS_NOTIF: diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 3d76e65ff84f..e455e83ceeeb 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -131,21 +131,6 @@ queue: return ret; } -/* - * Remove @event from group's notification queue. It is the responsibility of - * the caller to destroy the event. - */ -void fsnotify_remove_event(struct fsnotify_group *group, - struct fsnotify_event *event) -{ - mutex_lock(&group->notification_mutex); - if (!list_empty(&event->list)) { - list_del_init(&event->list); - group->q_len--; - } - mutex_unlock(&group->notification_mutex); -} - /* * Remove and return the first event from the notification list. It is the * responsibility of the caller to destroy the obtained event 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 v1.3-14-g43fede 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 ++++++++++++++++++++++++++++++++++----------- lib/rhashtable.c | 258 +++++++++++++++++++----- 2 files changed, 583 insertions(+), 166 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 */ diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 06c28728bb53..32d0ad058380 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -378,22 +378,8 @@ static void rht_deferred_worker(struct work_struct *work) schedule_work(&ht->run_work); } -static bool rhashtable_check_elasticity(struct rhashtable *ht, - struct bucket_table *tbl, - unsigned int hash) -{ - unsigned int elasticity = ht->elasticity; - struct rhash_head *head; - - rht_for_each(head, tbl, hash) - if (!--elasticity) - return true; - - return false; -} - -int rhashtable_insert_rehash(struct rhashtable *ht, - struct bucket_table *tbl) +static int rhashtable_insert_rehash(struct rhashtable *ht, + struct bucket_table *tbl) { struct bucket_table *old_tbl; struct bucket_table *new_tbl; @@ -439,57 +425,165 @@ fail: return err; } -EXPORT_SYMBOL_GPL(rhashtable_insert_rehash); -struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht, - const void *key, - struct rhash_head *obj, - struct bucket_table *tbl, - void **data) +static void *rhashtable_lookup_one(struct rhashtable *ht, + struct bucket_table *tbl, unsigned int hash, + const void *key, struct rhash_head *obj) { + struct rhashtable_compare_arg arg = { + .ht = ht, + .key = key, + }; + struct rhash_head __rcu **pprev; struct rhash_head *head; - unsigned int hash; - int err; + int elasticity; - tbl = rhashtable_last_table(ht, tbl); - hash = head_hashfn(ht, tbl, obj); - spin_lock_nested(rht_bucket_lock(tbl, hash), SINGLE_DEPTH_NESTING); - - err = -EEXIST; - if (key) { - *data = rhashtable_lookup_fast(ht, key, ht->p); - if (*data) - goto exit; + elasticity = ht->elasticity; + pprev = &tbl->buckets[hash]; + rht_for_each(head, tbl, hash) { + struct rhlist_head *list; + struct rhlist_head *plist; + + elasticity--; + if (!key || + (ht->p.obj_cmpfn ? + ht->p.obj_cmpfn(&arg, rht_obj(ht, head)) : + rhashtable_compare(&arg, rht_obj(ht, head)))) + continue; + + if (!ht->rhlist) + return rht_obj(ht, head); + + list = container_of(obj, struct rhlist_head, rhead); + plist = container_of(head, struct rhlist_head, rhead); + + 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); + + return NULL; } - err = -E2BIG; - if (unlikely(rht_grow_above_max(ht, tbl))) - goto exit; + if (elasticity <= 0) + return ERR_PTR(-EAGAIN); + + return ERR_PTR(-ENOENT); +} + +static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, + struct bucket_table *tbl, + unsigned int hash, + struct rhash_head *obj, + void *data) +{ + struct bucket_table *new_tbl; + struct rhash_head *head; + + if (!IS_ERR_OR_NULL(data)) + return ERR_PTR(-EEXIST); - err = -EAGAIN; - if (rhashtable_check_elasticity(ht, tbl, hash) || - rht_grow_above_100(ht, tbl)) - goto exit; + if (PTR_ERR(data) != -EAGAIN && PTR_ERR(data) != -ENOENT) + return ERR_CAST(data); - err = 0; + new_tbl = rcu_dereference(tbl->future_tbl); + if (new_tbl) + return new_tbl; + + if (PTR_ERR(data) != -ENOENT) + return ERR_CAST(data); + + if (unlikely(rht_grow_above_max(ht, tbl))) + return ERR_PTR(-E2BIG); + + if (unlikely(rht_grow_above_100(ht, tbl))) + return ERR_PTR(-EAGAIN); head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); RCU_INIT_POINTER(obj->next, head); + if (ht->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); atomic_inc(&ht->nelems); + if (rht_grow_above_75(ht, tbl)) + schedule_work(&ht->run_work); -exit: - spin_unlock(rht_bucket_lock(tbl, hash)); + return NULL; +} - if (err == 0) - return NULL; - else if (err == -EAGAIN) - return tbl; - else - return ERR_PTR(err); +static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, + struct rhash_head *obj) +{ + struct bucket_table *new_tbl; + struct bucket_table *tbl; + unsigned int hash; + spinlock_t *lock; + void *data; + + tbl = rcu_dereference(ht->tbl); + + /* 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, ht->p); + lock = rht_bucket_lock(tbl, hash); + spin_lock_bh(lock); + + if (tbl->rehash <= hash) + break; + + spin_unlock_bh(lock); + tbl = rcu_dereference(tbl->future_tbl); + } + + data = rhashtable_lookup_one(ht, tbl, hash, key, obj); + new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data); + if (PTR_ERR(new_tbl) != -EEXIST) + data = ERR_CAST(new_tbl); + + while (!IS_ERR_OR_NULL(new_tbl)) { + tbl = new_tbl; + hash = rht_head_hashfn(ht, tbl, obj, ht->p); + spin_lock_nested(rht_bucket_lock(tbl, hash), + SINGLE_DEPTH_NESTING); + + data = rhashtable_lookup_one(ht, tbl, hash, key, obj); + new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data); + if (PTR_ERR(new_tbl) != -EEXIST) + data = ERR_CAST(new_tbl); + + spin_unlock(rht_bucket_lock(tbl, hash)); + } + + spin_unlock_bh(lock); + + if (PTR_ERR(data) == -EAGAIN) + data = ERR_PTR(rhashtable_insert_rehash(ht, tbl) ?: + -EAGAIN); + + return data; +} + +void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, + struct rhash_head *obj) +{ + void *data; + + do { + rcu_read_lock(); + data = rhashtable_try_insert(ht, key, obj); + rcu_read_unlock(); + } while (PTR_ERR(data) == -EAGAIN); + + return data; } EXPORT_SYMBOL_GPL(rhashtable_insert_slow); @@ -593,11 +687,16 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_start); void *rhashtable_walk_next(struct rhashtable_iter *iter) { struct bucket_table *tbl = iter->walker.tbl; + struct rhlist_head *list = iter->list; struct rhashtable *ht = iter->ht; struct rhash_head *p = iter->p; + bool rhlist = ht->rhlist; if (p) { - p = rht_dereference_bucket_rcu(p->next, tbl, iter->slot); + if (!rhlist || !(list = rcu_dereference(list->next))) { + p = rcu_dereference(p->next); + list = container_of(p, struct rhlist_head, rhead); + } goto next; } @@ -605,6 +704,18 @@ void *rhashtable_walk_next(struct rhashtable_iter *iter) int skip = iter->skip; rht_for_each_rcu(p, tbl, iter->slot) { + if (rhlist) { + list = container_of(p, struct rhlist_head, + rhead); + do { + if (!skip) + goto next; + skip--; + list = rcu_dereference(list->next); + } while (list); + + continue; + } if (!skip) break; skip--; @@ -614,7 +725,8 @@ next: if (!rht_is_a_nulls(p)) { iter->skip++; iter->p = p; - return rht_obj(ht, p); + iter->list = list; + return rht_obj(ht, rhlist ? &list->rhead : p); } iter->skip = 0; @@ -802,6 +914,48 @@ int rhashtable_init(struct rhashtable *ht, } EXPORT_SYMBOL_GPL(rhashtable_init); +/** + * rhltable_init - initialize a new hash list table + * @hlt: hash list table to be initialized + * @params: configuration parameters + * + * Initializes a new hash list table. + * + * See documentation for rhashtable_init. + */ +int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params) +{ + int err; + + /* No rhlist NULLs marking for now. */ + if (params->nulls_base) + return -EINVAL; + + err = rhashtable_init(&hlt->ht, params); + hlt->ht.rhlist = true; + return err; +} +EXPORT_SYMBOL_GPL(rhltable_init); + +static void rhashtable_free_one(struct rhashtable *ht, struct rhash_head *obj, + void (*free_fn)(void *ptr, void *arg), + void *arg) +{ + struct rhlist_head *list; + + if (!ht->rhlist) { + free_fn(rht_obj(ht, obj), arg); + return; + } + + list = container_of(obj, struct rhlist_head, rhead); + do { + obj = &list->rhead; + list = rht_dereference(list->next, ht); + free_fn(rht_obj(ht, obj), arg); + } while (list); +} + /** * rhashtable_free_and_destroy - free elements and destroy hash table * @ht: the hash table to destroy @@ -839,7 +993,7 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, pos = next, next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL) - free_fn(rht_obj(ht, pos), arg); + rhashtable_free_one(ht, pos, free_fn, arg); } } -- cgit v1.3-14-g43fede 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 v1.3-14-g43fede 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 ++++- include/uapi/linux/bpf.h | 21 ++++++++ kernel/bpf/helpers.c | 3 ++ kernel/bpf/verifier.c | 54 ++++++++++++++----- net/core/filter.c | 134 +++++++++++++++++++++++++++++++++++++++++------ 6 files changed, 196 insertions(+), 34 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 diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f896dfac4ac0..e07432b9f8b8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -398,6 +398,27 @@ enum bpf_func_id { */ BPF_FUNC_skb_change_tail, + /** + * bpf_skb_pull_data(skb, len) + * The helper will pull in non-linear data in case the + * skb is non-linear and not all of len are part of the + * linear section. Only needed for read/write with direct + * packet access. + * @skb: pointer to skb + * @len: len to make read/writeable + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_pull_data, + + /** + * bpf_csum_update(skb, csum) + * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. + * @skb: pointer to skb + * @csum: csum to add + * Return: csum on success or negative error + */ + BPF_FUNC_csum_update, + __BPF_FUNC_MAX_ID, }; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a5b8bf8cfcfd..39918402e6e9 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -36,6 +36,7 @@ BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key) const struct bpf_func_proto bpf_map_lookup_elem_proto = { .func = bpf_map_lookup_elem, .gpl_only = false, + .pkt_access = true, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, @@ -51,6 +52,7 @@ BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key, const struct bpf_func_proto bpf_map_update_elem_proto = { .func = bpf_map_update_elem, .gpl_only = false, + .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, @@ -67,6 +69,7 @@ BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key) const struct bpf_func_proto bpf_map_delete_elem_proto = { .func = bpf_map_delete_elem, .gpl_only = false, + .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bc138f34e38c..3a75ee3bdcd1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -196,6 +196,7 @@ struct verifier_env { 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; }; #define BPF_COMPLEXITY_LIMIT_INSNS 65536 @@ -204,6 +205,7 @@ struct verifier_env { struct bpf_call_arg_meta { struct bpf_map *map_ptr; bool raw_mode; + bool pkt_access; int regno; int access_size; }; @@ -654,10 +656,17 @@ static int check_map_access(struct verifier_env *env, u32 regno, int off, #define MAX_PACKET_OFF 0xffff -static bool may_write_pkt_data(enum bpf_prog_type type) +static bool may_access_direct_pkt_data(struct verifier_env *env, + const struct bpf_call_arg_meta *meta) { - switch (type) { + switch (env->prog->type) { + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: + if (meta) + return meta->pkt_access; + + env->seen_direct_write = true; return true; default: return false; @@ -817,7 +826,7 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, err = check_stack_read(state, off, size, value_regno); } } else if (state->regs[regno].type == PTR_TO_PACKET) { - if (t == BPF_WRITE && !may_write_pkt_data(env->prog->type)) { + if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL)) { verbose("cannot write into packet\n"); return -EACCES; } @@ -950,8 +959,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno, return 0; } - if (type == PTR_TO_PACKET && !may_write_pkt_data(env->prog->type)) { - verbose("helper access to the packet is not allowed for clsact\n"); + if (type == PTR_TO_PACKET && !may_access_direct_pkt_data(env, meta)) { + verbose("helper access to the packet is not allowed\n"); return -EACCES; } @@ -1191,6 +1200,7 @@ static int check_call(struct verifier_env *env, int func_id) changes_data = bpf_helper_changes_skb_data(fn->func); memset(&meta, 0, sizeof(meta)); + meta.pkt_access = fn->pkt_access; /* We only support one arg being in raw mode at the moment, which * is sufficient for the helper functions we have right now. @@ -2675,18 +2685,35 @@ static void convert_pseudo_ld_imm64(struct verifier_env *env) */ static int convert_ctx_accesses(struct verifier_env *env) { - struct bpf_insn *insn = env->prog->insnsi; - int insn_cnt = env->prog->len; - struct bpf_insn insn_buf[16]; + const struct bpf_verifier_ops *ops = env->prog->aux->ops; + struct bpf_insn insn_buf[16], *insn; struct bpf_prog *new_prog; enum bpf_access_type type; - int i; + int i, insn_cnt, cnt; - if (!env->prog->aux->ops->convert_ctx_access) + if (ops->gen_prologue) { + cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, + env->prog); + if (cnt >= ARRAY_SIZE(insn_buf)) { + verbose("bpf verifier is misconfigured\n"); + return -EINVAL; + } else if (cnt) { + new_prog = bpf_patch_insn_single(env->prog, 0, + insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + env->prog = new_prog; + } + } + + if (!ops->convert_ctx_access) return 0; + insn_cnt = env->prog->len; + insn = env->prog->insnsi; + for (i = 0; i < insn_cnt; i++, insn++) { - u32 insn_delta, cnt; + u32 insn_delta; if (insn->code == (BPF_LDX | BPF_MEM | BPF_W) || insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) @@ -2703,9 +2730,8 @@ static int convert_ctx_accesses(struct verifier_env *env) continue; } - cnt = env->prog->aux->ops-> - convert_ctx_access(type, insn->dst_reg, insn->src_reg, - insn->off, insn_buf, env->prog); + cnt = ops->convert_ctx_access(type, insn->dst_reg, insn->src_reg, + insn->off, insn_buf, env->prog); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { verbose("bpf verifier is misconfigured\n"); return -EINVAL; diff --git a/net/core/filter.c b/net/core/filter.c index 298b146b47e7..0920c2ac1d00 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1362,6 +1362,11 @@ static inline int bpf_try_make_writable(struct sk_buff *skb, return err; } +static int bpf_try_make_head_writable(struct sk_buff *skb) +{ + return bpf_try_make_writable(skb, skb_headlen(skb)); +} + static inline void bpf_push_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) @@ -1441,6 +1446,28 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .arg4_type = ARG_CONST_STACK_SIZE, }; +BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) +{ + /* Idea is the following: should the needed direct read/write + * test fail during runtime, we can pull in more data and redo + * again, since implicitly, we invalidate previous checks here. + * + * Or, since we know how much we need to make read/writeable, + * this can be done once at the program beginning for direct + * access case. By this we overcome limitations of only current + * headroom being accessible. + */ + return bpf_try_make_writable(skb, len ? : skb_headlen(skb)); +} + +static const struct bpf_func_proto bpf_skb_pull_data_proto = { + .func = bpf_skb_pull_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { @@ -1567,6 +1594,7 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, static const struct bpf_func_proto bpf_csum_diff_proto = { .func = bpf_csum_diff, .gpl_only = false, + .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_STACK, .arg2_type = ARG_CONST_STACK_SIZE_OR_ZERO, @@ -1575,6 +1603,26 @@ static const struct bpf_func_proto bpf_csum_diff_proto = { .arg5_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_csum_update, struct sk_buff *, skb, __wsum, csum) +{ + /* The interface is to be used in combination with bpf_csum_diff() + * for direct packet writes. csum rotation for alignment as well + * as emulating csum_sub() can be done from the eBPF program. + */ + if (skb->ip_summed == CHECKSUM_COMPLETE) + return (skb->csum = csum_add(skb->csum, csum)); + + return -ENOTSUPP; +} + +static const struct bpf_func_proto bpf_csum_update_proto = { + .func = bpf_csum_update, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { return dev_forward_skb(dev, skb); @@ -1602,6 +1650,8 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; + struct sk_buff *clone; + int ret; if (unlikely(flags & ~(BPF_F_INGRESS))) return -EINVAL; @@ -1610,14 +1660,25 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) if (unlikely(!dev)) return -EINVAL; - skb = skb_clone(skb, GFP_ATOMIC); - if (unlikely(!skb)) + clone = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!clone)) return -ENOMEM; - bpf_push_mac_rcsum(skb); + /* For direct write, we need to keep the invariant that the skbs + * we're dealing with need to be uncloned. Should uncloning fail + * here, we need to free the just generated clone to unclone once + * again. + */ + ret = bpf_try_make_head_writable(skb); + if (unlikely(ret)) { + kfree_skb(clone); + return -ENOMEM; + } + + bpf_push_mac_rcsum(clone); return flags & BPF_F_INGRESS ? - __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); + __bpf_rx_skb(dev, clone) : __bpf_tx_skb(dev, clone); } static const struct bpf_func_proto bpf_clone_redirect_proto = { @@ -2063,19 +2124,14 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { bool bpf_helper_changes_skb_data(void *func) { - if (func == bpf_skb_vlan_push) - return true; - if (func == bpf_skb_vlan_pop) - return true; - if (func == bpf_skb_store_bytes) - return true; - if (func == bpf_skb_change_proto) - return true; - if (func == bpf_skb_change_tail) - return true; - if (func == bpf_l3_csum_replace) - return true; - if (func == bpf_l4_csum_replace) + if (func == bpf_skb_vlan_push || + func == bpf_skb_vlan_pop || + func == bpf_skb_store_bytes || + func == bpf_skb_change_proto || + func == bpf_skb_change_tail || + func == bpf_skb_pull_data || + func == bpf_l3_csum_replace || + func == bpf_l4_csum_replace) return true; return false; @@ -2440,8 +2496,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_pull_data: + return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; + case BPF_FUNC_csum_update: + return &bpf_csum_update_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: @@ -2533,6 +2593,45 @@ static bool sk_filter_is_valid_access(int off, int size, return __is_valid_access(off, size, type); } +static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, + const struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + + if (!direct_write) + return 0; + + /* if (!skb->cloned) + * goto start; + * + * (Fast-path, otherwise approximation that we might be + * a clone, do the rest in helper.) + */ + *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET()); + *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK); + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7); + + /* ret = bpf_skb_pull_data(skb, 0); */ + *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); + *insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2); + *insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_pull_data); + /* if (!ret) + * goto restore; + * return TC_ACT_SHOT; + */ + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2); + *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, TC_ACT_SHOT); + *insn++ = BPF_EXIT_INSN(); + + /* restore: */ + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + /* start: */ + *insn++ = prog->insnsi[0]; + + return insn - insn_buf; +} + static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type, enum bpf_reg_type *reg_type) @@ -2810,6 +2909,7 @@ static const struct bpf_verifier_ops tc_cls_act_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, + .gen_prologue = tc_cls_act_prologue, }; static const struct bpf_verifier_ops xdp_ops = { -- cgit v1.3-14-g43fede 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 +++++++++++++++++ lib/Makefile | 2 +- lib/win_minmax.c | 98 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 136 insertions(+), 1 deletion(-) create mode 100644 include/linux/win_minmax.h create mode 100644 lib/win_minmax.c (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 diff --git a/lib/Makefile b/lib/Makefile index 5dc77a8ec297..df747e5eeb7a 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -22,7 +22,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ sha1.o chacha20.o md5.o irq_regs.o argv_split.o \ flex_proportions.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ - earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o + earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o win_minmax.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o diff --git a/lib/win_minmax.c b/lib/win_minmax.c new file mode 100644 index 000000000000..c8420d404926 --- /dev/null +++ b/lib/win_minmax.c @@ -0,0 +1,98 @@ +/** + * lib/minmax.c: windowed min/max tracker + * + * Kathleen Nichols' algorithm for tracking the minimum (or maximum) + * value of a data stream over some fixed time interval. (E.g., + * the minimum RTT over the past five minutes.) It uses constant + * space and constant time per update yet almost always delivers + * the same minimum as an implementation that has to keep all the + * data in the window. + * + * The algorithm keeps track of the best, 2nd best & 3rd best min + * values, maintaining an invariant that the measurement time of + * the n'th best >= n-1'th best. It also makes sure that the three + * values are widely separated in the time window since that bounds + * the worse case error when that data is monotonically increasing + * over the window. + * + * Upon getting a new min, we can forget everything earlier because + * it has no value - the new min is <= everything else in the window + * by definition and it's the most recent. So we restart fresh on + * every new min and overwrites 2nd & 3rd choices. The same property + * holds for 2nd & 3rd best. + */ +#include +#include + +/* As time advances, update the 1st, 2nd, and 3rd choices. */ +static u32 minmax_subwin_update(struct minmax *m, u32 win, + const struct minmax_sample *val) +{ + u32 dt = val->t - m->s[0].t; + + if (unlikely(dt > win)) { + /* + * Passed entire window without a new val so make 2nd + * choice the new val & 3rd choice the new 2nd choice. + * we may have to iterate this since our 2nd choice + * may also be outside the window (we checked on entry + * that the third choice was in the window). + */ + m->s[0] = m->s[1]; + m->s[1] = m->s[2]; + m->s[2] = *val; + if (unlikely(val->t - m->s[0].t > win)) { + m->s[0] = m->s[1]; + m->s[1] = m->s[2]; + m->s[2] = *val; + } + } else if (unlikely(m->s[1].t == m->s[0].t) && dt > win/4) { + /* + * We've passed a quarter of the window without a new val + * so take a 2nd choice from the 2nd quarter of the window. + */ + m->s[2] = m->s[1] = *val; + } else if (unlikely(m->s[2].t == m->s[1].t) && dt > win/2) { + /* + * We've passed half the window without finding a new val + * so take a 3rd choice from the last half of the window + */ + m->s[2] = *val; + } + return m->s[0].v; +} + +/* Check if new measurement updates the 1st, 2nd or 3rd choice max. */ +u32 minmax_running_max(struct minmax *m, u32 win, u32 t, u32 meas) +{ + struct minmax_sample val = { .t = t, .v = meas }; + + if (unlikely(val.v >= m->s[0].v) || /* found new max? */ + unlikely(val.t - m->s[2].t > win)) /* nothing left in window? */ + return minmax_reset(m, t, meas); /* forget earlier samples */ + + if (unlikely(val.v >= m->s[1].v)) + m->s[2] = m->s[1] = val; + else if (unlikely(val.v >= m->s[2].v)) + m->s[2] = val; + + return minmax_subwin_update(m, win, &val); +} +EXPORT_SYMBOL(minmax_running_max); + +/* Check if new measurement updates the 1st, 2nd or 3rd choice min. */ +u32 minmax_running_min(struct minmax *m, u32 win, u32 t, u32 meas) +{ + struct minmax_sample val = { .t = t, .v = meas }; + + if (unlikely(val.v <= m->s[0].v) || /* found new min? */ + unlikely(val.t - m->s[2].t > win)) /* nothing left in window? */ + return minmax_reset(m, t, meas); /* forget earlier samples */ + + if (unlikely(val.v <= m->s[1].v)) + m->s[2] = m->s[1] = val; + else if (unlikely(val.v <= m->s[2].v)) + m->s[2] = val; + + return minmax_subwin_update(m, win, &val); +} -- cgit v1.3-14-g43fede 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 ++-- include/net/tcp.h | 2 +- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_input.c | 64 ++++-------------------------------------------- net/ipv4/tcp_minisocks.c | 2 +- 5 files changed, 10 insertions(+), 65 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 */ diff --git a/include/net/tcp.h b/include/net/tcp.h index fdfbedd61c67..2f1648af4d12 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -671,7 +671,7 @@ static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) /* Minimum RTT in usec. ~0 means not available. */ static inline u32 tcp_min_rtt(const struct tcp_sock *tp) { - return tp->rtt_min[0].rtt; + return minmax_get(&tp->rtt_min); } /* Compute the actual receive window we are currently advertising. diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7dae800092e6..e79ed17ccfd6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -387,7 +387,7 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - tp->rtt_min[0].rtt = ~0U; + minmax_reset(&tp->rtt_min, tcp_time_stamp, ~0U); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index dad3e7eeed94..6886f386464f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2879,67 +2879,13 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, *rexmit = REXMIT_LOST; } -/* Kathleen Nichols' algorithm for tracking the minimum value of - * a data stream over some fixed time interval. (E.g., the minimum - * RTT over the past five minutes.) It uses constant space and constant - * time per update yet almost always delivers the same minimum as an - * implementation that has to keep all the data in the window. - * - * The algorithm keeps track of the best, 2nd best & 3rd best min - * values, maintaining an invariant that the measurement time of the - * n'th best >= n-1'th best. It also makes sure that the three values - * are widely separated in the time window since that bounds the worse - * case error when that data is monotonically increasing over the window. - * - * Upon getting a new min, we can forget everything earlier because it - * has no value - the new min is <= everything else in the window by - * definition and it's the most recent. So we restart fresh on every new min - * and overwrites 2nd & 3rd choices. The same property holds for 2nd & 3rd - * best. - */ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) { - const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ; - struct rtt_meas *m = tcp_sk(sk)->rtt_min; - struct rtt_meas rttm = { - .rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1), - .ts = now, - }; - u32 elapsed; - - /* Check if the new measurement updates the 1st, 2nd, or 3rd choices */ - if (unlikely(rttm.rtt <= m[0].rtt)) - m[0] = m[1] = m[2] = rttm; - else if (rttm.rtt <= m[1].rtt) - m[1] = m[2] = rttm; - else if (rttm.rtt <= m[2].rtt) - m[2] = rttm; - - elapsed = now - m[0].ts; - if (unlikely(elapsed > wlen)) { - /* Passed entire window without a new min so make 2nd choice - * the new min & 3rd choice the new 2nd. So forth and so on. - */ - m[0] = m[1]; - m[1] = m[2]; - m[2] = rttm; - if (now - m[0].ts > wlen) { - m[0] = m[1]; - m[1] = rttm; - if (now - m[0].ts > wlen) - m[0] = rttm; - } - } else if (m[1].ts == m[0].ts && elapsed > wlen / 4) { - /* Passed a quarter of the window without a new min so - * take 2nd choice from the 2nd quarter of the window. - */ - m[2] = m[1] = rttm; - } else if (m[2].ts == m[1].ts && elapsed > wlen / 2) { - /* Passed half the window without a new min so take the 3rd - * choice from the last half of the window. - */ - m[2] = rttm; - } + struct tcp_sock *tp = tcp_sk(sk); + u32 wlen = sysctl_tcp_min_rtt_wlen * HZ; + + minmax_running_min(&tp->rtt_min, wlen, tcp_time_stamp, + rtt_us ? : jiffies_to_usecs(1)); } static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f63c73dc0acb..568947110b60 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -464,7 +464,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->srtt_us = 0; newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - newtp->rtt_min[0].rtt = ~0U; + minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U); newicsk->icsk_rto = TCP_TIMEOUT_INIT; newtp->packets_out = 0; -- cgit v1.3-14-g43fede 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 + net/ipv4/tcp_input.c | 25 ++++++++++++++++++++++++- 2 files changed, 25 insertions(+), 1 deletion(-) (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 */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6886f386464f..9413288c2778 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -899,12 +899,29 @@ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb) tp->retransmit_high = TCP_SKB_CB(skb)->end_seq; } +/* Sum the number of packets on the wire we have marked as lost. + * There are two cases we care about here: + * a) Packet hasn't been marked lost (nor retransmitted), + * and this is the first loss. + * b) Packet has been marked both lost and retransmitted, + * and this means we think it was lost again. + */ +static void tcp_sum_lost(struct tcp_sock *tp, struct sk_buff *skb) +{ + __u8 sacked = TCP_SKB_CB(skb)->sacked; + + if (!(sacked & TCPCB_LOST) || + ((sacked & TCPCB_LOST) && (sacked & TCPCB_SACKED_RETRANS))) + tp->lost += tcp_skb_pcount(skb); +} + static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb) { if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) { tcp_verify_retransmit_hint(tp, skb); tp->lost_out += tcp_skb_pcount(skb); + tcp_sum_lost(tp, skb); TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; } } @@ -913,6 +930,7 @@ void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) { tcp_verify_retransmit_hint(tp, skb); + tcp_sum_lost(tp, skb); if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) { tp->lost_out += tcp_skb_pcount(skb); TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; @@ -1890,6 +1908,7 @@ void tcp_enter_loss(struct sock *sk) struct sk_buff *skb; bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; bool is_reneg; /* is receiver reneging on SACKs? */ + bool mark_lost; /* Reduce ssthresh if it has not yet been made inside this window. */ if (icsk->icsk_ca_state <= TCP_CA_Disorder || @@ -1923,8 +1942,12 @@ void tcp_enter_loss(struct sock *sk) if (skb == tcp_send_head(sk)) break; + mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || + is_reneg); + if (mark_lost) + tcp_sum_lost(tp, skb); TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; - if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || is_reneg) { + if (mark_lost) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; tp->lost_out += tcp_skb_pcount(skb); -- cgit v1.3-14-g43fede 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 + include/net/tcp.h | 35 +++++++++++- net/ipv4/Makefile | 2 +- net/ipv4/tcp_input.c | 46 +++++++++++----- net/ipv4/tcp_output.c | 4 ++ net/ipv4/tcp_rate.c | 149 ++++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 222 insertions(+), 16 deletions(-) create mode 100644 net/ipv4/tcp_rate.c (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 */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 2f1648af4d12..b261c892605a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -763,8 +763,14 @@ struct tcp_skb_cb { __u32 ack_seq; /* Sequence number ACK'd */ union { struct { - /* There is space for up to 20 bytes */ + /* There is space for up to 24 bytes */ __u32 in_flight;/* Bytes in flight when packet sent */ + /* pkts S/ACKed so far upon tx of skb, incl retrans: */ + __u32 delivered; + /* start of send pipeline phase */ + struct skb_mstamp first_tx_mstamp; + /* when we reached the "delivered" count */ + struct skb_mstamp delivered_mstamp; } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; @@ -860,6 +866,26 @@ struct ack_sample { u32 in_flight; }; +/* A rate sample measures the number of (original/retransmitted) data + * packets delivered "delivered" over an interval of time "interval_us". + * The tcp_rate.c code fills in the rate sample, and congestion + * control modules that define a cong_control function to run at the end + * of ACK processing can optionally chose to consult this sample when + * setting cwnd and pacing rate. + * A sample is invalid if "delivered" or "interval_us" is negative. + */ +struct rate_sample { + struct skb_mstamp prior_mstamp; /* starting timestamp for interval */ + u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ + s32 delivered; /* number of packets delivered over interval */ + long interval_us; /* time for tp->delivered to incr "delivered" */ + long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ + int losses; /* number of packets marked lost upon ACK */ + u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ + u32 prior_in_flight; /* in flight before this ACK */ + bool is_retrans; /* is sample from retransmission? */ +}; + struct tcp_congestion_ops { struct list_head list; u32 key; @@ -946,6 +972,13 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) icsk->icsk_ca_ops->cwnd_event(sk, event); } +/* From tcp_rate.c */ +void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); +void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, + struct rate_sample *rs); +void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, + struct skb_mstamp *now, struct rate_sample *rs); + /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 24629b6f57cc..9cfff1a0bf71 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -8,7 +8,7 @@ obj-y := route.o inetpeer.o protocol.o \ inet_timewait_sock.o inet_connection_sock.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ - tcp_recovery.o \ + tcp_rate.o tcp_recovery.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o \ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9413288c2778..d9ed4bb96f74 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1112,6 +1112,7 @@ struct tcp_sacktag_state { */ struct skb_mstamp first_sackt; struct skb_mstamp last_sackt; + struct rate_sample *rate; int flag; }; @@ -1279,6 +1280,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, &skb->skb_mstamp); + tcp_rate_skb_delivered(sk, skb, state->rate); if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1329,6 +1331,9 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_advance_highest_sack(sk, skb); tcp_skb_collapse_tstamp(prev, skb); + if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp.v64)) + TCP_SKB_CB(prev)->tx.delivered_mstamp.v64 = 0; + tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); @@ -1558,6 +1563,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, dup_sack, tcp_skb_pcount(skb), &skb->skb_mstamp); + tcp_rate_skb_delivered(sk, skb, state->rate); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1640,8 +1646,10 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire, num_sacks, prior_snd_una); - if (found_dup_sack) + if (found_dup_sack) { state->flag |= FLAG_DSACKING_ACK; + tp->delivered++; /* A spurious retransmission is delivered */ + } /* Eliminate too old ACKs, but take into * account more or less fresh ones, they can @@ -3071,10 +3079,11 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, u32 prior_snd_una, int *acked, - struct tcp_sacktag_state *sack) + struct tcp_sacktag_state *sack, + struct skb_mstamp *now) { const struct inet_connection_sock *icsk = inet_csk(sk); - struct skb_mstamp first_ackt, last_ackt, now; + struct skb_mstamp first_ackt, last_ackt; struct tcp_sock *tp = tcp_sk(sk); u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; @@ -3106,7 +3115,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, acked_pcount = tcp_tso_acked(sk, skb); if (!acked_pcount) break; - fully_acked = false; } else { /* Speedup tcp_unlink_write_queue() and next loop */ @@ -3142,6 +3150,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->packets_out -= acked_pcount; pkts_acked += acked_pcount; + tcp_rate_skb_delivered(sk, skb, sack->rate); /* Initial outgoing SYN's get put onto the write_queue * just like anything else we transmit. It is not @@ -3174,16 +3183,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - skb_mstamp_get(&now); if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) { - seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt); - ca_rtt_us = skb_mstamp_us_delta(&now, &last_ackt); + seq_rtt_us = skb_mstamp_us_delta(now, &first_ackt); + ca_rtt_us = skb_mstamp_us_delta(now, &last_ackt); } if (sack->first_sackt.v64) { - sack_rtt_us = skb_mstamp_us_delta(&now, &sack->first_sackt); - ca_rtt_us = skb_mstamp_us_delta(&now, &sack->last_sackt); + sack_rtt_us = skb_mstamp_us_delta(now, &sack->first_sackt); + ca_rtt_us = skb_mstamp_us_delta(now, &sack->last_sackt); } - + sack->rate->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet, or -1 */ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us, ca_rtt_us); @@ -3211,7 +3219,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); } else if (skb && rtt_update && sack_rtt_us >= 0 && - sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) { + sack_rtt_us > skb_mstamp_us_delta(now, &skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3548,17 +3556,21 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_sacktag_state sack_state; + struct rate_sample rs = { .prior_delivered = 0 }; u32 prior_snd_una = tp->snd_una; u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; u32 prior_fackets; int prior_packets = tp->packets_out; - u32 prior_delivered = tp->delivered; + u32 delivered = tp->delivered; + u32 lost = tp->lost; int acked = 0; /* Number of packets newly acked */ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ + struct skb_mstamp now; sack_state.first_sackt.v64 = 0; + sack_state.rate = &rs; /* We very likely will need to access write queue head. */ prefetchw(sk->sk_write_queue.next); @@ -3581,6 +3593,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, tp->snd_nxt)) goto invalid_ack; + skb_mstamp_get(&now); + if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); @@ -3591,6 +3605,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) } prior_fackets = tp->fackets_out; + rs.prior_in_flight = tcp_packets_in_flight(tp); /* ts_recent update must be made after we are sure that the packet * is in window. @@ -3646,7 +3661,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked, - &sack_state); + &sack_state, &now); if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); @@ -3663,7 +3678,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (icsk->icsk_pending == ICSK_TIME_RETRANS) tcp_schedule_loss_probe(sk); - tcp_cong_control(sk, ack, tp->delivered - prior_delivered, flag); + delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */ + lost = tp->lost - lost; /* freshly marked lost */ + tcp_rate_gen(sk, delivered, lost, &now, &rs); + tcp_cong_control(sk, ack, delivered, flag); tcp_xmit_recovery(sk, rexmit); return 1; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8b45794eb6b2..e02c8ebf3ed4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -918,6 +918,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_mstamp_get(&skb->skb_mstamp); TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; + tcp_rate_skb_sent(sk, skb); if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); @@ -1213,6 +1214,9 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); + /* Update delivered info for the new segment */ + TCP_SKB_CB(buff)->tx = TCP_SKB_CB(skb)->tx; + /* If this packet has been sent out already, we must * adjust the various packet counters. */ diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c new file mode 100644 index 000000000000..1daed6af6e80 --- /dev/null +++ b/net/ipv4/tcp_rate.c @@ -0,0 +1,149 @@ +#include + +/* The bandwidth estimator estimates the rate at which the network + * can currently deliver outbound data packets for this flow. At a high + * level, it operates by taking a delivery rate sample for each ACK. + * + * A rate sample records the rate at which the network delivered packets + * for this flow, calculated over the time interval between the transmission + * of a data packet and the acknowledgment of that packet. + * + * Specifically, over the interval between each transmit and corresponding ACK, + * the estimator generates a delivery rate sample. Typically it uses the rate + * at which packets were acknowledged. However, the approach of using only the + * acknowledgment rate faces a challenge under the prevalent ACK decimation or + * compression: packets can temporarily appear to be delivered much quicker + * than the bottleneck rate. Since it is physically impossible to do that in a + * sustained fashion, when the estimator notices that the ACK rate is faster + * than the transmit rate, it uses the latter: + * + * send_rate = #pkts_delivered/(last_snd_time - first_snd_time) + * ack_rate = #pkts_delivered/(last_ack_time - first_ack_time) + * bw = min(send_rate, ack_rate) + * + * Notice the estimator essentially estimates the goodput, not always the + * network bottleneck link rate when the sending or receiving is limited by + * other factors like applications or receiver window limits. The estimator + * deliberately avoids using the inter-packet spacing approach because that + * approach requires a large number of samples and sophisticated filtering. + */ + + +/* Snapshot the current delivery information in the skb, to generate + * a rate sample later when the skb is (s)acked in tcp_rate_skb_delivered(). + */ +void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + + /* In general we need to start delivery rate samples from the + * time we received the most recent ACK, to ensure we include + * the full time the network needs to deliver all in-flight + * packets. If there are no packets in flight yet, then we + * know that any ACKs after now indicate that the network was + * able to deliver those packets completely in the sampling + * interval between now and the next ACK. + * + * Note that we use packets_out instead of tcp_packets_in_flight(tp) + * because the latter is a guess based on RTO and loss-marking + * heuristics. We don't want spurious RTOs or loss markings to cause + * a spuriously small time interval, causing a spuriously high + * bandwidth estimate. + */ + if (!tp->packets_out) { + tp->first_tx_mstamp = skb->skb_mstamp; + tp->delivered_mstamp = skb->skb_mstamp; + } + + TCP_SKB_CB(skb)->tx.first_tx_mstamp = tp->first_tx_mstamp; + TCP_SKB_CB(skb)->tx.delivered_mstamp = tp->delivered_mstamp; + TCP_SKB_CB(skb)->tx.delivered = tp->delivered; +} + +/* When an skb is sacked or acked, we fill in the rate sample with the (prior) + * delivery information when the skb was last transmitted. + * + * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is + * called multiple times. We favor the information from the most recently + * sent skb, i.e., the skb with the highest prior_delivered count. + */ +void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, + struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + + if (!scb->tx.delivered_mstamp.v64) + return; + + if (!rs->prior_delivered || + after(scb->tx.delivered, rs->prior_delivered)) { + rs->prior_delivered = scb->tx.delivered; + rs->prior_mstamp = scb->tx.delivered_mstamp; + rs->is_retrans = scb->sacked & TCPCB_RETRANS; + + /* Find the duration of the "send phase" of this window: */ + rs->interval_us = skb_mstamp_us_delta( + &skb->skb_mstamp, + &scb->tx.first_tx_mstamp); + + /* Record send time of most recently ACKed packet: */ + tp->first_tx_mstamp = skb->skb_mstamp; + } + /* Mark off the skb delivered once it's sacked to avoid being + * used again when it's cumulatively acked. For acked packets + * we don't need to reset since it'll be freed soon. + */ + if (scb->sacked & TCPCB_SACKED_ACKED) + scb->tx.delivered_mstamp.v64 = 0; +} + +/* Update the connection delivery information and generate a rate sample. */ +void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, + struct skb_mstamp *now, struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + u32 snd_us, ack_us; + + /* TODO: there are multiple places throughout tcp_ack() to get + * current time. Refactor the code using a new "tcp_acktag_state" + * to carry current time, flags, stats like "tcp_sacktag_state". + */ + if (delivered) + tp->delivered_mstamp = *now; + + rs->acked_sacked = delivered; /* freshly ACKed or SACKed */ + rs->losses = lost; /* freshly marked lost */ + /* Return an invalid sample if no timing information is available. */ + if (!rs->prior_mstamp.v64) { + rs->delivered = -1; + rs->interval_us = -1; + return; + } + rs->delivered = tp->delivered - rs->prior_delivered; + + /* Model sending data and receiving ACKs as separate pipeline phases + * for a window. Usually the ACK phase is longer, but with ACK + * compression the send phase can be longer. To be safe we use the + * longer phase. + */ + snd_us = rs->interval_us; /* send phase */ + ack_us = skb_mstamp_us_delta(now, &rs->prior_mstamp); /* ack phase */ + rs->interval_us = max(snd_us, ack_us); + + /* Normally we expect interval_us >= min-rtt. + * Note that rate may still be over-estimated when a spuriously + * retransmistted skb was first (s)acked because "interval_us" + * is under-estimated (up to an RTT). However continuously + * measuring the delivery rate during loss recovery is crucial + * for connections suffer heavy or prolonged losses. + */ + if (unlikely(rs->interval_us < tcp_min_rtt(tp))) { + rs->interval_us = -1; + if (!rs->is_retrans) + pr_debug("tcp rate: %ld %d %u %u %u\n", + rs->interval_us, rs->delivered, + inet_csk(sk)->icsk_ca_state, + tp->rx_opt.sack_ok, tcp_min_rtt(tp)); + } +} -- cgit v1.3-14-g43fede 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 + include/net/tcp.h | 6 +++++- net/ipv4/tcp.c | 8 ++++++++ net/ipv4/tcp_minisocks.c | 3 +++ net/ipv4/tcp_rate.c | 29 ++++++++++++++++++++++++++++- 5 files changed, 45 insertions(+), 2 deletions(-) (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" */ diff --git a/include/net/tcp.h b/include/net/tcp.h index b261c892605a..a69ed7f0030c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -764,7 +764,9 @@ struct tcp_skb_cb { union { struct { /* There is space for up to 24 bytes */ - __u32 in_flight;/* Bytes in flight when packet sent */ + __u32 in_flight:30,/* Bytes in flight at transmit */ + is_app_limited:1, /* cwnd not fully used? */ + unused:1; /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ @@ -883,6 +885,7 @@ struct rate_sample { int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ + bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ }; @@ -978,6 +981,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs); void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, struct skb_mstamp *now, struct rate_sample *rs); +void tcp_rate_check_app_limited(struct sock *sk); /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index de02fb4b1349..2250f891f931 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -396,6 +396,9 @@ void tcp_init_sock(struct sock *sk) */ tp->snd_cwnd = TCP_INIT_CWND; + /* There's a bubble in the pipe until at least the first ACK. */ + tp->app_limited = ~0U; + /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. */ @@ -1014,6 +1017,9 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, flags); lock_sock(sk); + + tcp_rate_check_app_limited(sk); /* is sending application-limited? */ + res = do_tcp_sendpages(sk, page, offset, size, flags); release_sock(sk); return res; @@ -1115,6 +1121,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + tcp_rate_check_app_limited(sk); /* is sending application-limited? */ + /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 568947110b60..6234ebaa7db1 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -487,6 +487,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->snd_cwnd = TCP_INIT_CWND; newtp->snd_cwnd_cnt = 0; + /* There's a bubble in the pipe until at least the first ACK. */ + newtp->app_limited = ~0U; + tcp_init_xmit_timers(newsk); newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index 1daed6af6e80..52ff84be59ab 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -26,9 +26,13 @@ * other factors like applications or receiver window limits. The estimator * deliberately avoids using the inter-packet spacing approach because that * approach requires a large number of samples and sophisticated filtering. + * + * TCP flows can often be application-limited in request/response workloads. + * The estimator marks a bandwidth sample as application-limited if there + * was some moment during the sampled window of packets when there was no data + * ready to send in the write queue. */ - /* Snapshot the current delivery information in the skb, to generate * a rate sample later when the skb is (s)acked in tcp_rate_skb_delivered(). */ @@ -58,6 +62,7 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tx.first_tx_mstamp = tp->first_tx_mstamp; TCP_SKB_CB(skb)->tx.delivered_mstamp = tp->delivered_mstamp; TCP_SKB_CB(skb)->tx.delivered = tp->delivered; + TCP_SKB_CB(skb)->tx.is_app_limited = tp->app_limited ? 1 : 0; } /* When an skb is sacked or acked, we fill in the rate sample with the (prior) @@ -80,6 +85,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, after(scb->tx.delivered, rs->prior_delivered)) { rs->prior_delivered = scb->tx.delivered; rs->prior_mstamp = scb->tx.delivered_mstamp; + rs->is_app_limited = scb->tx.is_app_limited; rs->is_retrans = scb->sacked & TCPCB_RETRANS; /* Find the duration of the "send phase" of this window: */ @@ -105,6 +111,10 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, struct tcp_sock *tp = tcp_sk(sk); u32 snd_us, ack_us; + /* Clear app limited if bubble is acked and gone. */ + if (tp->app_limited && after(tp->delivered, tp->app_limited)) + tp->app_limited = 0; + /* TODO: there are multiple places throughout tcp_ack() to get * current time. Refactor the code using a new "tcp_acktag_state" * to carry current time, flags, stats like "tcp_sacktag_state". @@ -147,3 +157,20 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, tp->rx_opt.sack_ok, tcp_min_rtt(tp)); } } + +/* If a gap is detected between sends, mark the socket application-limited. */ +void tcp_rate_check_app_limited(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (/* We have less than one packet to send. */ + tp->write_seq - tp->snd_nxt < tp->mss_cache && + /* Nothing in sending host's qdisc queues or NIC tx queue. */ + sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) && + /* We are not limited by CWND. */ + tcp_packets_in_flight(tp) < tp->snd_cwnd && + /* All lost packets have been retransmitted. */ + tp->lost_out <= tp->retrans_out) + tp->app_limited = + (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; +} -- cgit v1.3-14-g43fede 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 ++++- include/uapi/linux/tcp.h | 3 +++ net/ipv4/tcp.c | 11 ++++++++++- net/ipv4/tcp_rate.c | 12 +++++++++++- 4 files changed, 28 insertions(+), 3 deletions(-) (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 */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 482898fc433a..73ac0db487f8 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -167,6 +167,7 @@ struct tcp_info { __u8 tcpi_backoff; __u8 tcpi_options; __u8 tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4; + __u8 tcpi_delivery_rate_app_limited:1; __u32 tcpi_rto; __u32 tcpi_ato; @@ -211,6 +212,8 @@ struct tcp_info { __u32 tcpi_min_rtt; __u32 tcpi_data_segs_in; /* RFC4898 tcpEStatsDataSegsIn */ __u32 tcpi_data_segs_out; /* RFC4898 tcpEStatsDataSegsOut */ + + __u64 tcpi_delivery_rate; }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2250f891f931..f253e5019d22 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2712,7 +2712,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_time_stamp, intv; unsigned int start; int notsent_bytes; u64 rate64; @@ -2802,6 +2802,15 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_min_rtt = tcp_min_rtt(tp); info->tcpi_data_segs_in = tp->data_segs_in; info->tcpi_data_segs_out = tp->data_segs_out; + + info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0; + rate = READ_ONCE(tp->rate_delivered); + intv = READ_ONCE(tp->rate_interval_us); + if (rate && intv) { + rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC; + do_div(rate64, intv); + put_unaligned(rate64, &info->tcpi_delivery_rate); + } } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index 52ff84be59ab..9be1581a5a08 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -149,12 +149,22 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, * for connections suffer heavy or prolonged losses. */ if (unlikely(rs->interval_us < tcp_min_rtt(tp))) { - rs->interval_us = -1; if (!rs->is_retrans) pr_debug("tcp rate: %ld %d %u %u %u\n", rs->interval_us, rs->delivered, inet_csk(sk)->icsk_ca_state, tp->rx_opt.sack_ok, tcp_min_rtt(tp)); + rs->interval_us = -1; + return; + } + + /* Record the last non-app-limited or the highest app-limited bw */ + if (!rs->is_app_limited || + ((u64)rs->delivered * tp->rate_interval_us >= + (u64)tp->rate_delivered * rs->interval_us)) { + tp->rate_delivered = rs->delivered; + tp->rate_interval_us = rs->interval_us; + tp->rate_app_limited = rs->is_app_limited; } } -- cgit v1.3-14-g43fede 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 ++ include/net/pkt_cls.h | 14 ++++++++++ net/sched/cls_bpf.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 86 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; }; }; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a459be5fe1c2..41e8071dff87 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -486,4 +486,18 @@ struct tc_cls_matchall_offload { unsigned long cookie; }; +enum tc_clsbpf_command { + TC_CLSBPF_ADD, + TC_CLSBPF_REPLACE, + TC_CLSBPF_DESTROY, +}; + +struct tc_cls_bpf_offload { + enum tc_clsbpf_command command; + struct tcf_exts *exts; + struct bpf_prog *prog; + const char *name; + bool exts_integrated; +}; + #endif diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index c6f7a47541eb..6523c5b4c0a5 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -39,6 +39,7 @@ struct cls_bpf_prog { struct list_head link; struct tcf_result res; bool exts_integrated; + bool offloaded; struct tcf_exts exts; u32 handle; union { @@ -138,6 +139,71 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) return !prog->bpf_ops; } +static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, + enum tc_clsbpf_command cmd) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct tc_cls_bpf_offload bpf_offload = {}; + struct tc_to_netdev offload; + + offload.type = TC_SETUP_CLSBPF; + offload.cls_bpf = &bpf_offload; + + bpf_offload.command = cmd; + bpf_offload.exts = &prog->exts; + bpf_offload.prog = prog->filter; + bpf_offload.name = prog->bpf_name; + bpf_offload.exts_integrated = prog->exts_integrated; + + return dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, + tp->protocol, &offload); +} + +static void cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, + struct cls_bpf_prog *oldprog) +{ + struct net_device *dev = tp->q->dev_queue->dev; + struct cls_bpf_prog *obj = prog; + enum tc_clsbpf_command cmd; + + if (oldprog && oldprog->offloaded) { + if (tc_should_offload(dev, tp, 0)) { + cmd = TC_CLSBPF_REPLACE; + } else { + obj = oldprog; + cmd = TC_CLSBPF_DESTROY; + } + } else { + if (!tc_should_offload(dev, tp, 0)) + return; + cmd = TC_CLSBPF_ADD; + } + + if (cls_bpf_offload_cmd(tp, obj, cmd)) + return; + + obj->offloaded = true; + if (oldprog) + oldprog->offloaded = false; +} + +static void cls_bpf_stop_offload(struct tcf_proto *tp, + struct cls_bpf_prog *prog) +{ + int err; + + if (!prog->offloaded) + return; + + err = cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); + if (err) { + pr_err("Stopping hardware offload failed: %d\n", err); + return; + } + + prog->offloaded = false; +} + static int cls_bpf_init(struct tcf_proto *tp) { struct cls_bpf_head *head; @@ -177,6 +243,7 @@ static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg) { struct cls_bpf_prog *prog = (struct cls_bpf_prog *) arg; + cls_bpf_stop_offload(tp, prog); list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); call_rcu(&prog->rcu, __cls_bpf_delete_prog); @@ -193,6 +260,7 @@ static bool cls_bpf_destroy(struct tcf_proto *tp, bool force) return false; list_for_each_entry_safe(prog, tmp, &head->plist, link) { + cls_bpf_stop_offload(tp, prog); list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); call_rcu(&prog->rcu, __cls_bpf_delete_prog); @@ -415,6 +483,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, if (ret < 0) goto errout; + cls_bpf_offload(tp, prog, oldprog); + if (oldprog) { list_replace_rcu(&oldprog->link, &prog->link); tcf_unbind_filter(tp, &oldprog->res); -- cgit v1.3-14-g43fede 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 +++++++++++++ kernel/bpf/verifier.c | 266 +++++++++++++++++-------------------------- 2 files changed, 182 insertions(+), 163 deletions(-) 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 */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a9542d89f293..dca2b9b1d02e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -126,82 +127,16 @@ * are set to NOT_INIT to indicate that they are no longer readable. */ -struct 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 verifier_state { - struct reg_state regs[MAX_BPF_REG]; - u8 stack_slot_type[MAX_BPF_STACK]; - struct reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE]; -}; - -/* linked list of verifier states used to prune search */ -struct verifier_state_list { - struct verifier_state state; - struct verifier_state_list *next; -}; - /* verifier_state + insn_idx are pushed to stack when branch is encountered */ -struct verifier_stack_elem { +struct bpf_verifier_stack_elem { /* verifer state is 'st' * before processing instruction 'insn_idx' * and after processing instruction 'prev_insn_idx' */ - struct verifier_state st; + struct bpf_verifier_state st; int insn_idx; int prev_insn_idx; - struct verifier_stack_elem *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 verifier_env { - struct bpf_prog *prog; /* eBPF program being verified */ - struct verifier_stack_elem *head; /* stack of verifier states to be processed */ - int stack_size; /* number of states to be processed */ - struct verifier_state cur_state; /* current verifier state */ - struct 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 */ + struct bpf_verifier_stack_elem *next; }; #define BPF_COMPLEXITY_LIMIT_INSNS 65536 @@ -254,9 +189,9 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET_END] = "pkt_end", }; -static void print_verifier_state(struct verifier_state *state) +static void print_verifier_state(struct bpf_verifier_state *state) { - struct reg_state *reg; + struct bpf_reg_state *reg; enum bpf_reg_type t; int i; @@ -432,9 +367,9 @@ static void print_bpf_insn(struct bpf_insn *insn) } } -static int pop_stack(struct verifier_env *env, int *prev_insn_idx) +static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx) { - struct verifier_stack_elem *elem; + struct bpf_verifier_stack_elem *elem; int insn_idx; if (env->head == NULL) @@ -451,12 +386,12 @@ static int pop_stack(struct verifier_env *env, int *prev_insn_idx) return insn_idx; } -static struct verifier_state *push_stack(struct verifier_env *env, int insn_idx, - int prev_insn_idx) +static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, + int insn_idx, int prev_insn_idx) { - struct verifier_stack_elem *elem; + struct bpf_verifier_stack_elem *elem; - elem = kmalloc(sizeof(struct verifier_stack_elem), GFP_KERNEL); + elem = kmalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); if (!elem) goto err; @@ -482,7 +417,7 @@ static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -static void init_reg_state(struct reg_state *regs) +static void init_reg_state(struct bpf_reg_state *regs) { int i; @@ -498,7 +433,7 @@ static void init_reg_state(struct reg_state *regs) regs[BPF_REG_1].type = PTR_TO_CTX; } -static void mark_reg_unknown_value(struct reg_state *regs, u32 regno) +static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno) { BUG_ON(regno >= MAX_BPF_REG); regs[regno].type = UNKNOWN_VALUE; @@ -511,7 +446,7 @@ enum reg_arg_type { DST_OP_NO_MARK /* same as above, check only, don't mark */ }; -static int check_reg_arg(struct reg_state *regs, u32 regno, +static int check_reg_arg(struct bpf_reg_state *regs, u32 regno, enum reg_arg_type t) { if (regno >= MAX_BPF_REG) { @@ -571,8 +506,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type) /* check_stack_read/write functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ -static int check_stack_write(struct verifier_state *state, int off, int size, - int value_regno) +static int check_stack_write(struct bpf_verifier_state *state, int off, + int size, int value_regno) { int i; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, @@ -597,7 +532,7 @@ static int check_stack_write(struct verifier_state *state, int off, int size, } else { /* regular write of data into stack */ state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] = - (struct reg_state) {}; + (struct bpf_reg_state) {}; for (i = 0; i < size; i++) state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC; @@ -605,7 +540,7 @@ static int check_stack_write(struct verifier_state *state, int off, int size, return 0; } -static int check_stack_read(struct verifier_state *state, int off, int size, +static int check_stack_read(struct bpf_verifier_state *state, int off, int size, int value_regno) { u8 *slot_type; @@ -646,7 +581,7 @@ static int check_stack_read(struct verifier_state *state, int off, int size, } /* check read/write into map element returned by bpf_map_lookup_elem() */ -static int check_map_access(struct verifier_env *env, u32 regno, int off, +static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size) { struct bpf_map *map = env->cur_state.regs[regno].map_ptr; @@ -661,7 +596,7 @@ static int check_map_access(struct verifier_env *env, u32 regno, int off, #define MAX_PACKET_OFF 0xffff -static bool may_access_direct_pkt_data(struct verifier_env *env, +static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta) { switch (env->prog->type) { @@ -678,11 +613,11 @@ static bool may_access_direct_pkt_data(struct verifier_env *env, } } -static int check_packet_access(struct verifier_env *env, u32 regno, int off, +static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, int size) { - struct reg_state *regs = env->cur_state.regs; - struct reg_state *reg = ®s[regno]; + struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *reg = ®s[regno]; off += reg->off; if (off < 0 || size <= 0 || off + size > reg->range) { @@ -694,7 +629,7 @@ static int check_packet_access(struct verifier_env *env, u32 regno, int off, } /* check access to 'struct bpf_context' fields */ -static int check_ctx_access(struct verifier_env *env, int off, int size, +static int check_ctx_access(struct bpf_verifier_env *env, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type) { if (env->prog->aux->ops->is_valid_access && @@ -709,7 +644,7 @@ static int check_ctx_access(struct verifier_env *env, int off, int size, return -EACCES; } -static bool is_pointer_value(struct verifier_env *env, int regno) +static bool is_pointer_value(struct bpf_verifier_env *env, int regno) { if (env->allow_ptr_leaks) return false; @@ -723,12 +658,13 @@ static bool is_pointer_value(struct verifier_env *env, int regno) } } -static int check_ptr_alignment(struct verifier_env *env, struct reg_state *reg, - int off, int size) +static int check_ptr_alignment(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, int off, int size) { if (reg->type != PTR_TO_PACKET) { if (off % size != 0) { - verbose("misaligned access off %d size %d\n", off, size); + verbose("misaligned access off %d size %d\n", + off, size); return -EACCES; } else { return 0; @@ -769,12 +705,12 @@ static int check_ptr_alignment(struct verifier_env *env, struct reg_state *reg, * if t==write && value_regno==-1, some unknown value is stored into memory * if t==read && value_regno==-1, don't care what we read from memory */ -static int check_mem_access(struct verifier_env *env, u32 regno, int off, +static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, int bpf_size, enum bpf_access_type t, int value_regno) { - struct verifier_state *state = &env->cur_state; - struct reg_state *reg = &state->regs[regno]; + struct bpf_verifier_state *state = &env->cur_state; + struct bpf_reg_state *reg = &state->regs[regno]; int size, err = 0; if (reg->type == PTR_TO_STACK) @@ -860,9 +796,9 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, return err; } -static int check_xadd(struct verifier_env *env, struct bpf_insn *insn) +static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = env->cur_state.regs; int err; if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) || @@ -896,12 +832,12 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn) * bytes from that pointer, make sure that it's within stack boundary * and all elements of stack are initialized */ -static int check_stack_boundary(struct verifier_env *env, int regno, +static int check_stack_boundary(struct bpf_verifier_env *env, int regno, int access_size, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { - struct verifier_state *state = &env->cur_state; - struct reg_state *regs = state->regs; + struct bpf_verifier_state *state = &env->cur_state; + struct bpf_reg_state *regs = state->regs; int off, i; if (regs[regno].type != PTR_TO_STACK) { @@ -940,11 +876,11 @@ static int check_stack_boundary(struct verifier_env *env, int regno, return 0; } -static int check_func_arg(struct verifier_env *env, u32 regno, +static int check_func_arg(struct bpf_verifier_env *env, u32 regno, enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta) { - struct reg_state *regs = env->cur_state.regs, *reg = ®s[regno]; + struct bpf_reg_state *regs = env->cur_state.regs, *reg = ®s[regno]; enum bpf_reg_type expected_type, type = reg->type; int err = 0; @@ -1149,10 +1085,10 @@ static int check_raw_mode(const struct bpf_func_proto *fn) return count > 1 ? -EINVAL : 0; } -static void clear_all_pkt_pointers(struct verifier_env *env) +static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { - struct verifier_state *state = &env->cur_state; - struct reg_state *regs = state->regs, *reg; + struct bpf_verifier_state *state = &env->cur_state; + struct bpf_reg_state *regs = state->regs, *reg; int i; for (i = 0; i < MAX_BPF_REG; i++) @@ -1172,12 +1108,12 @@ static void clear_all_pkt_pointers(struct verifier_env *env) } } -static int check_call(struct verifier_env *env, int func_id) +static int check_call(struct bpf_verifier_env *env, int func_id) { - struct verifier_state *state = &env->cur_state; + struct bpf_verifier_state *state = &env->cur_state; const struct bpf_func_proto *fn = NULL; - struct reg_state *regs = state->regs; - struct reg_state *reg; + struct bpf_reg_state *regs = state->regs; + struct bpf_reg_state *reg; struct bpf_call_arg_meta meta; bool changes_data; int i, err; @@ -1280,12 +1216,13 @@ static int check_call(struct verifier_env *env, int func_id) return 0; } -static int check_packet_ptr_add(struct verifier_env *env, struct bpf_insn *insn) +static int check_packet_ptr_add(struct bpf_verifier_env *env, + struct bpf_insn *insn) { - struct reg_state *regs = env->cur_state.regs; - struct reg_state *dst_reg = ®s[insn->dst_reg]; - struct reg_state *src_reg = ®s[insn->src_reg]; - struct reg_state tmp_reg; + struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *dst_reg = ®s[insn->dst_reg]; + struct bpf_reg_state *src_reg = ®s[insn->src_reg]; + struct bpf_reg_state tmp_reg; s32 imm; if (BPF_SRC(insn->code) == BPF_K) { @@ -1353,10 +1290,10 @@ add_imm: return 0; } -static int evaluate_reg_alu(struct verifier_env *env, struct bpf_insn *insn) +static int evaluate_reg_alu(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct reg_state *regs = env->cur_state.regs; - struct reg_state *dst_reg = ®s[insn->dst_reg]; + struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *dst_reg = ®s[insn->dst_reg]; u8 opcode = BPF_OP(insn->code); s64 imm_log2; @@ -1366,7 +1303,7 @@ static int evaluate_reg_alu(struct verifier_env *env, struct bpf_insn *insn) */ if (BPF_SRC(insn->code) == BPF_X) { - struct reg_state *src_reg = ®s[insn->src_reg]; + struct bpf_reg_state *src_reg = ®s[insn->src_reg]; if (src_reg->type == UNKNOWN_VALUE && src_reg->imm > 0 && dst_reg->imm && opcode == BPF_ADD) { @@ -1455,11 +1392,12 @@ static int evaluate_reg_alu(struct verifier_env *env, struct bpf_insn *insn) return 0; } -static int evaluate_reg_imm_alu(struct verifier_env *env, struct bpf_insn *insn) +static int evaluate_reg_imm_alu(struct bpf_verifier_env *env, + struct bpf_insn *insn) { - struct reg_state *regs = env->cur_state.regs; - struct reg_state *dst_reg = ®s[insn->dst_reg]; - struct reg_state *src_reg = ®s[insn->src_reg]; + struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *dst_reg = ®s[insn->dst_reg]; + struct bpf_reg_state *src_reg = ®s[insn->src_reg]; u8 opcode = BPF_OP(insn->code); /* dst_reg->type == CONST_IMM here, simulate execution of 'add' insn. @@ -1476,9 +1414,9 @@ static int evaluate_reg_imm_alu(struct verifier_env *env, struct bpf_insn *insn) } /* check validity of 32-bit and 64-bit arithmetic operations */ -static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn) +static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct reg_state *regs = env->cur_state.regs, *dst_reg; + struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg; u8 opcode = BPF_OP(insn->code); int err; @@ -1652,10 +1590,10 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn) return 0; } -static void find_good_pkt_pointers(struct verifier_state *state, - const struct reg_state *dst_reg) +static void find_good_pkt_pointers(struct bpf_verifier_state *state, + struct bpf_reg_state *dst_reg) { - struct reg_state *regs = state->regs, *reg; + struct bpf_reg_state *regs = state->regs, *reg; int i; /* LLVM can generate two kind of checks: @@ -1701,11 +1639,11 @@ static void find_good_pkt_pointers(struct verifier_state *state, } } -static int check_cond_jmp_op(struct verifier_env *env, +static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { - struct verifier_state *other_branch, *this_branch = &env->cur_state; - struct reg_state *regs = this_branch->regs, *dst_reg; + struct bpf_verifier_state *other_branch, *this_branch = &env->cur_state; + struct bpf_reg_state *regs = this_branch->regs, *dst_reg; u8 opcode = BPF_OP(insn->code); int err; @@ -1767,7 +1705,7 @@ static int check_cond_jmp_op(struct verifier_env *env, if (!other_branch) return -EFAULT; - /* detect if R == 0 where R is returned value from bpf_map_lookup_elem() */ + /* detect if R == 0 where R is returned from bpf_map_lookup_elem() */ if (BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { @@ -1809,9 +1747,9 @@ static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn) } /* verify BPF_LD_IMM64 instruction */ -static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn) +static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = env->cur_state.regs; int err; if (BPF_SIZE(insn->code) != BPF_DW) { @@ -1866,11 +1804,11 @@ static bool may_access_skb(enum bpf_prog_type type) * Output: * R0 - 8/16/32-bit skb data converted to cpu endianness */ -static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn) +static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = env->cur_state.regs; u8 mode = BPF_MODE(insn->code); - struct reg_state *reg; + struct bpf_reg_state *reg; int i, err; if (!may_access_skb(env->prog->type)) { @@ -1956,7 +1894,7 @@ enum { BRANCH = 2, }; -#define STATE_LIST_MARK ((struct verifier_state_list *) -1L) +#define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L) static int *insn_stack; /* stack of insns to process */ static int cur_stack; /* current stack index */ @@ -1967,7 +1905,7 @@ static int *insn_state; * w - next instruction * e - edge */ -static int push_insn(int t, int w, int e, struct verifier_env *env) +static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) { if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) return 0; @@ -2008,7 +1946,7 @@ static int push_insn(int t, int w, int e, struct verifier_env *env) /* non-recursive depth-first-search to detect loops in BPF program * loop == back-edge in directed graph */ -static int check_cfg(struct verifier_env *env) +static int check_cfg(struct bpf_verifier_env *env) { struct bpf_insn *insns = env->prog->insnsi; int insn_cnt = env->prog->len; @@ -2117,7 +2055,8 @@ err_free: /* the following conditions reduce the number of explored insns * from ~140k to ~80k for ultra large programs that use a lot of ptr_to_packet */ -static bool compare_ptrs_to_packet(struct reg_state *old, struct reg_state *cur) +static bool compare_ptrs_to_packet(struct bpf_reg_state *old, + struct bpf_reg_state *cur) { if (old->id != cur->id) return false; @@ -2192,9 +2131,10 @@ static bool compare_ptrs_to_packet(struct reg_state *old, struct reg_state *cur) * whereas register type in current state is meaningful, it means that * the current state will reach 'bpf_exit' instruction safely */ -static bool states_equal(struct verifier_state *old, struct verifier_state *cur) +static bool states_equal(struct bpf_verifier_state *old, + struct bpf_verifier_state *cur) { - struct reg_state *rold, *rcur; + struct bpf_reg_state *rold, *rcur; int i; for (i = 0; i < MAX_BPF_REG; i++) { @@ -2234,9 +2174,9 @@ static bool states_equal(struct verifier_state *old, struct verifier_state *cur) * the same, check that stored pointers types * are the same as well. * Ex: explored safe path could have stored - * (struct reg_state) {.type = PTR_TO_STACK, .imm = -8} + * (bpf_reg_state) {.type = PTR_TO_STACK, .imm = -8} * but current path has stored: - * (struct reg_state) {.type = PTR_TO_STACK, .imm = -16} + * (bpf_reg_state) {.type = PTR_TO_STACK, .imm = -16} * such verifier states are not equivalent. * return false to continue verification of this path */ @@ -2247,10 +2187,10 @@ static bool states_equal(struct verifier_state *old, struct verifier_state *cur) return true; } -static int is_state_visited(struct verifier_env *env, int insn_idx) +static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { - struct verifier_state_list *new_sl; - struct verifier_state_list *sl; + struct bpf_verifier_state_list *new_sl; + struct bpf_verifier_state_list *sl; sl = env->explored_states[insn_idx]; if (!sl) @@ -2274,7 +2214,7 @@ static int is_state_visited(struct verifier_env *env, int insn_idx) * it will be rejected. Since there are no loops, we won't be * seeing this 'insn_idx' instruction again on the way to bpf_exit */ - new_sl = kmalloc(sizeof(struct verifier_state_list), GFP_USER); + new_sl = kmalloc(sizeof(struct bpf_verifier_state_list), GFP_USER); if (!new_sl) return -ENOMEM; @@ -2285,11 +2225,11 @@ static int is_state_visited(struct verifier_env *env, int insn_idx) return 0; } -static int do_check(struct verifier_env *env) +static int do_check(struct bpf_verifier_env *env) { - struct verifier_state *state = &env->cur_state; + struct bpf_verifier_state *state = &env->cur_state; struct bpf_insn *insns = env->prog->insnsi; - struct reg_state *regs = state->regs; + struct bpf_reg_state *regs = state->regs; int insn_cnt = env->prog->len; int insn_idx, prev_insn_idx = 0; int insn_processed = 0; @@ -2572,7 +2512,7 @@ static int check_map_prog_compatibility(struct bpf_map *map, /* look for pseudo eBPF instructions that access map FDs and * replace them with actual map pointers */ -static int replace_map_fd_with_map_ptr(struct verifier_env *env) +static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; @@ -2669,7 +2609,7 @@ next_insn: } /* drop refcnt of maps used by the rejected program */ -static void release_maps(struct verifier_env *env) +static void release_maps(struct bpf_verifier_env *env) { int i; @@ -2678,7 +2618,7 @@ static void release_maps(struct verifier_env *env) } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ -static void convert_pseudo_ld_imm64(struct verifier_env *env) +static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; @@ -2692,7 +2632,7 @@ static void convert_pseudo_ld_imm64(struct verifier_env *env) /* convert load instructions that access fields of 'struct __sk_buff' * into sequence of instructions that access fields of 'struct sk_buff' */ -static int convert_ctx_accesses(struct verifier_env *env) +static int convert_ctx_accesses(struct bpf_verifier_env *env) { const struct bpf_verifier_ops *ops = env->prog->aux->ops; const int insn_cnt = env->prog->len; @@ -2757,9 +2697,9 @@ static int convert_ctx_accesses(struct verifier_env *env) return 0; } -static void free_states(struct verifier_env *env) +static void free_states(struct bpf_verifier_env *env) { - struct verifier_state_list *sl, *sln; + struct bpf_verifier_state_list *sl, *sln; int i; if (!env->explored_states) @@ -2782,16 +2722,16 @@ static void free_states(struct verifier_env *env) int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) { char __user *log_ubuf = NULL; - struct verifier_env *env; + struct bpf_verifier_env *env; int ret = -EINVAL; if ((*prog)->len <= 0 || (*prog)->len > BPF_MAXINSNS) return -E2BIG; - /* 'struct verifier_env' can be global, but since it's not small, + /* 'struct bpf_verifier_env' can be global, but since it's not small, * allocate/free it every time bpf_check() is called */ - env = kzalloc(sizeof(struct verifier_env), GFP_KERNEL); + env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; @@ -2833,7 +2773,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) goto skip_full_check; env->explored_states = kcalloc(env->prog->len, - sizeof(struct verifier_state_list *), + sizeof(struct bpf_verifier_state_list *), GFP_USER); ret = -ENOMEM; if (!env->explored_states) -- cgit v1.3-14-g43fede 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 +++++++ kernel/bpf/verifier.c | 68 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 79 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 */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index dca2b9b1d02e..ee86a77dc40b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -632,6 +632,10 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, static int check_ctx_access(struct bpf_verifier_env *env, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type) { + /* for analyzer ctx accesses are already validated and converted */ + if (env->analyzer_ops) + return 0; + if (env->prog->aux->ops->is_valid_access && env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) { /* remember the offset of last byte accessed in ctx */ @@ -2225,6 +2229,15 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return 0; } +static int ext_analyzer_insn_hook(struct bpf_verifier_env *env, + int insn_idx, int prev_insn_idx) +{ + if (!env->analyzer_ops || !env->analyzer_ops->insn_hook) + return 0; + + return env->analyzer_ops->insn_hook(env, insn_idx, prev_insn_idx); +} + static int do_check(struct bpf_verifier_env *env) { struct bpf_verifier_state *state = &env->cur_state; @@ -2283,6 +2296,10 @@ static int do_check(struct bpf_verifier_env *env) print_bpf_insn(insn); } + err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx); + if (err) + return err; + if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); if (err) @@ -2845,3 +2862,54 @@ err_free_env: kfree(env); return ret; } + +int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, + void *priv) +{ + struct bpf_verifier_env *env; + int ret; + + env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); + if (!env) + return -ENOMEM; + + env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) * + prog->len); + ret = -ENOMEM; + if (!env->insn_aux_data) + goto err_free_env; + env->prog = prog; + env->analyzer_ops = ops; + env->analyzer_priv = priv; + + /* grab the mutex to protect few globals used by verifier */ + mutex_lock(&bpf_verifier_lock); + + log_level = 0; + + env->explored_states = kcalloc(env->prog->len, + sizeof(struct bpf_verifier_state_list *), + GFP_KERNEL); + ret = -ENOMEM; + if (!env->explored_states) + goto skip_full_check; + + ret = check_cfg(env); + if (ret < 0) + goto skip_full_check; + + env->allow_ptr_leaks = capable(CAP_SYS_ADMIN); + + ret = do_check(env); + +skip_full_check: + while (pop_stack(env, NULL) >= 0); + free_states(env); + + mutex_unlock(&bpf_verifier_lock); + vfree(env->insn_aux_data); +err_free_env: + kfree(env); + return ret; +} +EXPORT_SYMBOL_GPL(bpf_analyzer); -- cgit v1.3-14-g43fede 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 + net/core/skbuff.c | 7 +++++-- 2 files changed, 6 insertions(+), 2 deletions(-) (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, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7bf82a28e10a..6c22351bd519 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4522,8 +4522,10 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len) } EXPORT_SYMBOL(skb_ensure_writable); -/* remove VLAN header from packet and update csum accordingly. */ -static int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci) +/* remove VLAN header from packet and update csum accordingly. + * expects a non skb_vlan_tag_present skb with a vlan tag payload + */ +int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci) { struct vlan_hdr *vhdr; unsigned int offset = skb->data - skb_mac_header(skb); @@ -4554,6 +4556,7 @@ pull: return err; } +EXPORT_SYMBOL(__skb_vlan_pop); int skb_vlan_pop(struct sk_buff *skb) { -- cgit v1.3-14-g43fede 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 --- drivers/net/ethernet/intel/e1000e/ptp.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_ptp.c | 2 +- drivers/net/ethernet/intel/igb/igb_ptp.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_clock.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 2 +- drivers/net/ethernet/sfc/ptp.c | 14 +++++++------- drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 2 +- include/linux/ptp_clock_kernel.h | 5 +++++ 9 files changed, 19 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 2e1b17ad52a3..ad03763e009a 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -334,7 +334,7 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) if (IS_ERR(adapter->ptp_clock)) { adapter->ptp_clock = NULL; e_err("ptp_clock_register failed\n"); - } else { + } else if (adapter->ptp_clock) { e_info("registered PHC clock\n"); } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index ed39cbad24bd..f1feceab758a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -669,7 +669,7 @@ void i40e_ptp_init(struct i40e_pf *pf) pf->ptp_clock = NULL; dev_err(&pf->pdev->dev, "%s: ptp_clock_register failed\n", __func__); - } else { + } else if (pf->ptp_clock) { struct timespec64 ts; u32 regval; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 66dfa2085cc7..1dd14e166dc8 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -1159,7 +1159,7 @@ void igb_ptp_init(struct igb_adapter *adapter) if (IS_ERR(adapter->ptp_clock)) { adapter->ptp_clock = NULL; dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n"); - } else { + } else if (adapter->ptp_clock) { dev_info(&adapter->pdev->dev, "added PHC on %s\n", adapter->netdev->name); adapter->ptp_flags |= IGB_PTP_ENABLED; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index e5431bfe3339..a92277683a64 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -1254,7 +1254,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter) adapter->ptp_clock = NULL; e_dev_err("ptp_clock_register failed\n"); return err; - } else + } else if (adapter->ptp_clock) e_dev_info("registered PHC device on %s\n", netdev->name); /* set default timestamp mode to disabled here. We do this in diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 1494997c4f7e..08fc5fc56d43 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -298,7 +298,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) if (IS_ERR(mdev->ptp_clock)) { mdev->ptp_clock = NULL; mlx4_err(mdev, "ptp_clock_register failed\n"); - } else { + } else if (mdev->ptp_clock) { mlx4_info(mdev, "registered PHC clock\n"); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c index 847a8f3ac2b2..13dc388667b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c @@ -273,7 +273,7 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv) tstamp->ptp = ptp_clock_register(&tstamp->ptp_info, &priv->mdev->pdev->dev); - if (IS_ERR_OR_NULL(tstamp->ptp)) { + if (IS_ERR(tstamp->ptp)) { mlx5_core_warn(priv->mdev, "ptp_clock_register failed %ld\n", PTR_ERR(tstamp->ptp)); tstamp->ptp = NULL; diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index dd204d9704c6..77a5364f7a10 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -1269,13 +1269,13 @@ int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel) if (IS_ERR(ptp->phc_clock)) { rc = PTR_ERR(ptp->phc_clock); goto fail3; - } - - INIT_WORK(&ptp->pps_work, efx_ptp_pps_worker); - ptp->pps_workwq = create_singlethread_workqueue("sfc_pps"); - if (!ptp->pps_workwq) { - rc = -ENOMEM; - goto fail4; + } else if (ptp->phc_clock) { + INIT_WORK(&ptp->pps_work, efx_ptp_pps_worker); + ptp->pps_workwq = create_singlethread_workqueue("sfc_pps"); + if (!ptp->pps_workwq) { + rc = -ENOMEM; + goto fail4; + } } } ptp->nic_ts_enabled = false; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 170a18b61281..6e3b82972ce8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -187,7 +187,7 @@ int stmmac_ptp_register(struct stmmac_priv *priv) if (IS_ERR(priv->ptp_clock)) { priv->ptp_clock = NULL; pr_err("ptp_clock_register() failed on %s\n", priv->dev->name); - } else + } else if (priv->ptp_clock) pr_debug("Added PTP HW clock successfully on %s\n", priv->dev->name); 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 v1.3-14-g43fede 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 v1.3-14-g43fede 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 --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 2 ++ drivers/net/ethernet/mediatek/mtk_eth_soc.h | 3 +++ include/linux/phy.h | 3 +++ 3 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 2909372c4da0..e873e21fd20e 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -244,6 +244,8 @@ static int mtk_phy_connect(struct mtk_mac *mac) return -ENODEV; switch (of_get_phy_mode(np)) { + case PHY_INTERFACE_MODE_TRGMII: + mac->trgmii = true; case PHY_INTERFACE_MODE_RGMII_TXID: case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_ID: diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 7c5e534d2120..e3b9525f94c6 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -529,6 +529,8 @@ struct mtk_eth { * @hw: Backpointer to our main datastruture * @hw_stats: Packet statistics counter * @phy_dev: The attached PHY if available + * @trgmii Indicate if the MAC uses TRGMII connected to internal + switch */ struct mtk_mac { int id; @@ -539,6 +541,7 @@ struct mtk_mac { struct phy_device *phy_dev; __be32 hwlro_ip[MTK_MAX_LRO_IP_CNT]; int hwlro_ip_cnt; + bool trgmii; }; /* the struct describing the SoC. these are declared in the soc_xyz.c files */ 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 v1.3-14-g43fede 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 --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 7 ++++ drivers/net/ethernet/mellanox/mlx4/fw.c | 37 ++++++++++++++++---- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 2 ++ .../net/ethernet/mellanox/mlx4/resource_tracker.c | 40 ++++++++++++++++++---- include/linux/mlx4/device.h | 3 ++ include/linux/mlx4/qp.h | 2 ++ 6 files changed, 78 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index a58d96cf1ed1..09c969420eac 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1851,6 +1851,7 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv, if (vp_oper->state.default_vlan == vp_admin->default_vlan && vp_oper->state.default_qos == vp_admin->default_qos && + vp_oper->state.vlan_proto == vp_admin->vlan_proto && vp_oper->state.link_state == vp_admin->link_state && vp_oper->state.qos_vport == vp_admin->qos_vport) return 0; @@ -1909,6 +1910,7 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv, vp_oper->state.default_vlan = vp_admin->default_vlan; vp_oper->state.default_qos = vp_admin->default_qos; + vp_oper->state.vlan_proto = vp_admin->vlan_proto; vp_oper->state.link_state = vp_admin->link_state; vp_oper->state.qos_vport = vp_admin->qos_vport; @@ -1922,6 +1924,7 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv, work->qos_vport = vp_oper->state.qos_vport; work->vlan_id = vp_oper->state.default_vlan; work->vlan_ix = vp_oper->vlan_idx; + work->vlan_proto = vp_oper->state.vlan_proto; work->priv = priv; INIT_WORK(&work->work, mlx4_vf_immed_vlan_work_handler); queue_work(priv->mfunc.master.comm_wq, &work->work); @@ -2012,6 +2015,8 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave) vp_admin->default_vlan, &(vp_oper->vlan_idx)); if (err) { vp_oper->vlan_idx = NO_INDX; + vp_oper->state.default_vlan = MLX4_VGT; + vp_oper->state.vlan_proto = htons(ETH_P_8021Q); mlx4_warn(&priv->dev, "No vlan resources slave %d, port %d\n", slave, port); @@ -2388,6 +2393,8 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) admin_vport->qos_vport = MLX4_VPP_DEFAULT_VPORT; oper_vport->qos_vport = MLX4_VPP_DEFAULT_VPORT; + admin_vport->vlan_proto = htons(ETH_P_8021Q); + oper_vport->vlan_proto = htons(ETH_P_8021Q); vf_oper->vport[port].vlan_idx = NO_INDX; vf_oper->vport[port].mac_idx = NO_INDX; mlx4_set_random_admin_guid(dev, i, port); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index c7523307b41a..7dc9d38a51f8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -158,7 +158,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [31] = "Modifying loopback source checks using UPDATE_QP support", [32] = "Loopback source checks support", [33] = "RoCEv2 support", - [34] = "DMFS Sniffer support (UC & MC)" + [34] = "DMFS Sniffer support (UC & MC)", + [35] = "QinQ VST mode support", }; int i; @@ -313,12 +314,15 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, #define QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID 0x80 #define QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS (1 << 31) #define QUERY_FUNC_CAP_PHV_BIT 0x40 +#define QUERY_FUNC_CAP_VLAN_OFFLOAD_DISABLE 0x20 if (vhcr->op_modifier == 1) { struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave); int converted_port = mlx4_slave_convert_port( dev, slave, vhcr->in_modifier); + struct mlx4_vport_oper_state *vp_oper = + &priv->mfunc.master.vf_oper[slave].vport[vhcr->in_modifier]; if (converted_port < 0) return -EINVAL; @@ -357,11 +361,12 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, MLX4_PUT(outbox->buf, dev->caps.phys_port_id[vhcr->in_modifier], QUERY_FUNC_CAP_PHYS_PORT_ID); - if (dev->caps.phv_bit[port]) { - field = QUERY_FUNC_CAP_PHV_BIT; - MLX4_PUT(outbox->buf, field, - QUERY_FUNC_CAP_FLAGS0_OFFSET); - } + field = 0; + if (dev->caps.phv_bit[port]) + field |= QUERY_FUNC_CAP_PHV_BIT; + if (vp_oper->state.vlan_proto == htons(ETH_P_8021AD)) + field |= QUERY_FUNC_CAP_VLAN_OFFLOAD_DISABLE; + MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS0_OFFSET); } else if (vhcr->op_modifier == 0) { struct mlx4_active_ports actv_ports = @@ -689,6 +694,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_MAX_DESC_SZ_SQ_OFFSET 0x52 #define QUERY_DEV_CAP_MAX_SG_RQ_OFFSET 0x55 #define QUERY_DEV_CAP_MAX_DESC_SZ_RQ_OFFSET 0x56 +#define QUERY_DEV_CAP_SVLAN_BY_QP_OFFSET 0x5D #define QUERY_DEV_CAP_MAX_QP_MCG_OFFSET 0x61 #define QUERY_DEV_CAP_RSVD_MCG_OFFSET 0x62 #define QUERY_DEV_CAP_MAX_MCG_OFFSET 0x63 @@ -856,6 +862,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) MLX4_GET(size, outbox, QUERY_DEV_CAP_MAX_DESC_SZ_SQ_OFFSET); dev_cap->max_sq_desc_sz = size; + MLX4_GET(field, outbox, QUERY_DEV_CAP_SVLAN_BY_QP_OFFSET); + if (field & 0x1) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP; MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_QP_MCG_OFFSET); dev_cap->max_qp_per_mcg = 1 << field; MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_MCG_OFFSET); @@ -2937,6 +2946,22 @@ int set_phv_bit(struct mlx4_dev *dev, u8 port, int new_val) } EXPORT_SYMBOL(set_phv_bit); +int mlx4_get_is_vlan_offload_disabled(struct mlx4_dev *dev, u8 port, + bool *vlan_offload_disabled) +{ + struct mlx4_func_cap func_cap; + int err; + + memset(&func_cap, 0, sizeof(func_cap)); + err = mlx4_QUERY_FUNC_CAP(dev, port, &func_cap); + if (!err) + *vlan_offload_disabled = + !!(func_cap.flags0 & + QUERY_FUNC_CAP_VLAN_OFFLOAD_DISABLE); + return err; +} +EXPORT_SYMBOL(mlx4_get_is_vlan_offload_disabled); + void mlx4_replace_zero_macs(struct mlx4_dev *dev) { int i; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index c128ba3ef014..fdfe1ace07d7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -508,6 +508,7 @@ struct mlx4_vport_state { u64 mac; u16 default_vlan; u8 default_qos; + __be16 vlan_proto; u32 tx_rate; bool spoofchk; u32 link_state; @@ -657,6 +658,7 @@ struct mlx4_vf_immed_vlan_work { u8 qos_vport; u16 vlan_id; u16 orig_vlan_id; + __be16 vlan_proto; }; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 8b81114bdc72..84d7857ccc27 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -790,10 +790,22 @@ static int update_vport_qp_param(struct mlx4_dev *dev, MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED | MLX4_VLAN_CTRL_ETH_RX_BLOCK_TAGGED; } else if (0 != vp_oper->state.default_vlan) { - qpc->pri_path.vlan_control |= - MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED | - MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED | - MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED; + if (vp_oper->state.vlan_proto == htons(ETH_P_8021AD)) { + /* vst QinQ should block untagged on TX, + * but cvlan is in payload and phv is set so + * hw see it as untagged. Block tagged instead. + */ + qpc->pri_path.vlan_control |= + MLX4_VLAN_CTRL_ETH_TX_BLOCK_PRIO_TAGGED | + MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED | + MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED | + MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED; + } else { /* vst 802.1Q */ + qpc->pri_path.vlan_control |= + MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED | + MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED | + MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED; + } } else { /* priority tagged */ qpc->pri_path.vlan_control |= MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED | @@ -802,7 +814,11 @@ static int update_vport_qp_param(struct mlx4_dev *dev, qpc->pri_path.fvl_rx |= MLX4_FVL_RX_FORCE_ETH_VLAN; qpc->pri_path.vlan_index = vp_oper->vlan_idx; - qpc->pri_path.fl |= MLX4_FL_CV | MLX4_FL_ETH_HIDE_CQE_VLAN; + qpc->pri_path.fl |= MLX4_FL_ETH_HIDE_CQE_VLAN; + if (vp_oper->state.vlan_proto == htons(ETH_P_8021AD)) + qpc->pri_path.fl |= MLX4_FL_SV; + else + qpc->pri_path.fl |= MLX4_FL_CV; qpc->pri_path.feup |= MLX4_FEUP_FORCE_ETH_UP | MLX4_FVL_FORCE_ETH_VLAN; qpc->pri_path.sched_queue &= 0xC7; qpc->pri_path.sched_queue |= (vp_oper->state.default_qos) << 3; @@ -5238,6 +5254,7 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work) u64 qp_path_mask = ((1ULL << MLX4_UPD_QP_PATH_MASK_VLAN_INDEX) | (1ULL << MLX4_UPD_QP_PATH_MASK_FVL) | (1ULL << MLX4_UPD_QP_PATH_MASK_CV) | + (1ULL << MLX4_UPD_QP_PATH_MASK_SV) | (1ULL << MLX4_UPD_QP_PATH_MASK_ETH_HIDE_CQE_VLAN) | (1ULL << MLX4_UPD_QP_PATH_MASK_FEUP) | (1ULL << MLX4_UPD_QP_PATH_MASK_FVL_RX) | @@ -5266,7 +5283,12 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work) else if (!work->vlan_id) vlan_control = MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED | MLX4_VLAN_CTRL_ETH_RX_BLOCK_TAGGED; - else + else if (work->vlan_proto == htons(ETH_P_8021AD)) + vlan_control = MLX4_VLAN_CTRL_ETH_TX_BLOCK_PRIO_TAGGED | + MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED | + MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED | + MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED; + else /* vst 802.1Q */ vlan_control = MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED | MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED | MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED; @@ -5311,7 +5333,11 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work) upd_context->qp_context.pri_path.fvl_rx = qp->fvl_rx | MLX4_FVL_RX_FORCE_ETH_VLAN; upd_context->qp_context.pri_path.fl = - qp->pri_path_fl | MLX4_FL_CV | MLX4_FL_ETH_HIDE_CQE_VLAN; + qp->pri_path_fl | MLX4_FL_ETH_HIDE_CQE_VLAN; + if (work->vlan_proto == htons(ETH_P_8021AD)) + upd_context->qp_context.pri_path.fl |= MLX4_FL_SV; + else + upd_context->qp_context.pri_path.fl |= MLX4_FL_CV; upd_context->qp_context.pri_path.feup = qp->feup | MLX4_FEUP_FORCE_ETH_UP | MLX4_FVL_FORCE_ETH_VLAN; upd_context->qp_context.pri_path.sched_queue = 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 v1.3-14-g43fede 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 --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 3 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 9 ++- drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 6 +- drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h | 2 +- drivers/net/ethernet/emulex/benet/be_main.c | 6 +- drivers/net/ethernet/intel/fm10k/fm10k.h | 2 +- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 6 +- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 11 ++- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 4 +- drivers/net/ethernet/intel/igb/igb_main.c | 9 ++- drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 5 +- drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h | 2 +- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 6 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 +- drivers/net/ethernet/qlogic/qede/qede_main.c | 6 +- drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h | 2 +- .../net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c | 5 +- drivers/net/ethernet/sfc/sriov.c | 5 +- drivers/net/ethernet/sfc/sriov.h | 2 +- include/linux/if_link.h | 1 + include/linux/netdevice.h | 6 +- include/uapi/linux/if_link.h | 19 ++++- net/core/rtnetlink.c | 80 ++++++++++++++++++---- 23 files changed, 161 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 0e68fadecfdb..243cb9748d35 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -492,7 +492,8 @@ int __bnx2x_setup_tc(struct net_device *dev, u32 handle, __be16 proto, int bnx2x_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi); int bnx2x_set_vf_mac(struct net_device *dev, int queue, u8 *mac); -int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos); +int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto); /* select_queue callback */ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 6c586b045d1d..3f77d0863543 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -2521,7 +2521,8 @@ void bnx2x_pf_set_vfs_vlan(struct bnx2x *bp) for_each_vf(bp, vfidx) { bulletin = BP_VF_BULLETIN(bp, vfidx); if (bulletin->valid_bitmap & (1 << VLAN_VALID)) - bnx2x_set_vf_vlan(bp->dev, vfidx, bulletin->vlan, 0); + bnx2x_set_vf_vlan(bp->dev, vfidx, bulletin->vlan, 0, + htons(ETH_P_8021Q)); } } @@ -2781,7 +2782,8 @@ static int bnx2x_set_vf_vlan_filter(struct bnx2x *bp, struct bnx2x_virtf *vf, return 0; } -int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos) +int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos, + __be16 vlan_proto) { struct pf_vf_bulletin_content *bulletin = NULL; struct bnx2x *bp = netdev_priv(dev); @@ -2796,6 +2798,9 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos) return -EINVAL; } + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + DP(BNX2X_MSG_IOV, "configuring VF %d with VLAN %d qos %d\n", vfidx, vlan, 0); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 8be718508600..ec6cd18842c3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -174,7 +174,8 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac) return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); } -int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos) +int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos, + __be16 vlan_proto) { struct hwrm_func_cfg_input req = {0}; struct bnxt *bp = netdev_priv(dev); @@ -185,6 +186,9 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos) if (bp->hwrm_spec_code < 0x10201) return -ENOTSUPP; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + rc = bnxt_vf_ndo_prep(bp, vf_id); if (rc) return rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index 0392670ab49c..1ab72e4820af 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -12,7 +12,7 @@ int bnxt_get_vf_config(struct net_device *, int, struct ifla_vf_info *); int bnxt_set_vf_mac(struct net_device *, int, u8 *); -int bnxt_set_vf_vlan(struct net_device *, int, u16, u8); +int bnxt_set_vf_vlan(struct net_device *, int, u16, u8, __be16); int bnxt_set_vf_bw(struct net_device *, int, int, int); int bnxt_set_vf_link_state(struct net_device *, int, int); int bnxt_set_vf_spoofchk(struct net_device *, int, bool); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 9a94840c5757..ac513e6627d1 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1895,7 +1895,8 @@ static int be_clear_vf_tvt(struct be_adapter *adapter, int vf) return 0; } -static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) +static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) { struct be_adapter *adapter = netdev_priv(netdev); struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf]; @@ -1907,6 +1908,9 @@ static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) if (vf >= adapter->num_vfs || vlan > 4095 || qos > 7) return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + if (vlan || qos) { vlan |= qos << VLAN_PRIO_SHIFT; status = be_set_vf_tvt(adapter, vf, vlan); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 67ff01aeb11a..4d19e46f7c55 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -507,7 +507,7 @@ int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs); s32 fm10k_iov_update_pvid(struct fm10k_intfc *interface, u16 glort, u16 pvid); int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac); int fm10k_ndo_set_vf_vlan(struct net_device *netdev, - int vf_idx, u16 vid, u8 qos); + int vf_idx, u16 vid, u8 qos, __be16 vlan_proto); int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, int rate, int unused); int fm10k_ndo_get_vf_config(struct net_device *netdev, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index d9dec81f6b6d..5f4dac0d36ef 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -445,7 +445,7 @@ int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac) } int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid, - u8 qos) + u8 qos, __be16 vlan_proto) { struct fm10k_intfc *interface = netdev_priv(netdev); struct fm10k_iov_data *iov_data = interface->iov_data; @@ -460,6 +460,10 @@ int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid, if (qos || (vid > (VLAN_VID_MASK - 1))) return -EINVAL; + /* VF VLAN Protocol part to default is unsupported */ + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + vf_info = &iov_data->vf_info[vf_idx]; /* exit if there is nothing to do */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index da3423561b3a..724d8740d4cc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2747,11 +2747,12 @@ error_param: * @vf_id: VF identifier * @vlan_id: mac address * @qos: priority setting + * @vlan_proto: vlan protocol * * program VF vlan id and/or qos **/ -int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, - int vf_id, u16 vlan_id, u8 qos) +int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, + u16 vlan_id, u8 qos, __be16 vlan_proto) { u16 vlanprio = vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT); struct i40e_netdev_priv *np = netdev_priv(netdev); @@ -2774,6 +2775,12 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, goto error_pvid; } + if (vlan_proto != htons(ETH_P_8021Q)) { + dev_err(&pf->pdev->dev, "VF VLAN protocol is not supported\n"); + ret = -EPROTONOSUPPORT; + goto error_pvid; + } + vf = &(pf->vf[vf_id]); vsi = pf->vsi[vf->lan_vsi_idx]; if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 875174141451..4012d069939a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -129,8 +129,8 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf); /* VF configuration related iplink handlers */ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac); -int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, - int vf_id, u16 vlan_id, u8 qos); +int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, + u16 vlan_id, u8 qos, __be16 vlan_proto); int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, int max_tx_rate); int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index af75eac5fa16..a83aa13a5bf4 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -169,7 +169,7 @@ static int igb_set_vf_mac(struct igb_adapter *, int, unsigned char *); static void igb_restore_vf_multicasts(struct igb_adapter *adapter); static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac); static int igb_ndo_set_vf_vlan(struct net_device *netdev, - int vf, u16 vlan, u8 qos); + int vf, u16 vlan, u8 qos, __be16 vlan_proto); static int igb_ndo_set_vf_bw(struct net_device *, int, int, int); static int igb_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting); @@ -6222,14 +6222,17 @@ static int igb_disable_port_vlan(struct igb_adapter *adapter, int vf) return 0; } -static int igb_ndo_set_vf_vlan(struct net_device *netdev, - int vf, u16 vlan, u8 qos) +static int igb_ndo_set_vf_vlan(struct net_device *netdev, int vf, + u16 vlan, u8 qos, __be16 vlan_proto) { struct igb_adapter *adapter = netdev_priv(netdev); if ((vf >= adapter->vfs_allocated_count) || (vlan > 4095) || (qos > 7)) return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + return (vlan || qos) ? igb_enable_port_vlan(adapter, vf, vlan, qos) : igb_disable_port_vlan(adapter, vf); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 8618599dfd6f..b18590a995db 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -1354,13 +1354,16 @@ static int ixgbe_disable_port_vlan(struct ixgbe_adapter *adapter, int vf) return err; } -int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) +int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, + u8 qos, __be16 vlan_proto) { int err = 0; struct ixgbe_adapter *adapter = netdev_priv(netdev); if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7)) return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; if (vlan || qos) { /* Check if there is already a port VLAN set, if so * we have to delete the old one first before we diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h index 47e65e2f886a..0c7977d27b71 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h @@ -43,7 +43,7 @@ void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter); void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter); int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int queue, u8 *mac); int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int queue, u16 vlan, - u8 qos); + u8 qos, __be16 vlan_proto); int ixgbe_link_mbps(struct ixgbe_adapter *adapter); int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, int max_tx_rate); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index a94f8a3f026c..132eeeafcdc4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2400,11 +2400,15 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac) return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64); } -static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos) +static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) { struct mlx4_en_priv *en_priv = netdev_priv(dev); struct mlx4_en_dev *mdev = en_priv->mdev; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index c12792314be7..b58cfe37dead 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2917,11 +2917,15 @@ static int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac) return mlx5_eswitch_set_vport_mac(mdev->priv.eswitch, vf + 1, mac); } -static int mlx5e_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos) +static int mlx5e_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_core_dev *mdev = priv->mdev; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + return mlx5_eswitch_set_vport_vlan(mdev->priv.eswitch, vf + 1, vlan, qos); } diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index cd23a2946db7..0e198fe89d1a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -100,7 +100,8 @@ static int qede_alloc_rx_buffer(struct qede_dev *edev, static void qede_link_update(void *dev, struct qed_link_output *link); #ifdef CONFIG_QED_SRIOV -static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos) +static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) { struct qede_dev *edev = netdev_priv(ndev); @@ -109,6 +110,9 @@ static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos) return -EINVAL; } + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + DP_VERBOSE(edev, QED_MSG_IOV, "Setting Vlan 0x%04x to VF [%d]\n", vlan, vf); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h index 24061b9b92e8..5f327659efa7 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h @@ -238,7 +238,7 @@ int qlcnic_sriov_set_vf_mac(struct net_device *, int, u8 *); int qlcnic_sriov_set_vf_tx_rate(struct net_device *, int, int, int); int qlcnic_sriov_get_vf_config(struct net_device *, int , struct ifla_vf_info *); -int qlcnic_sriov_set_vf_vlan(struct net_device *, int, u16, u8); +int qlcnic_sriov_set_vf_vlan(struct net_device *, int, u16, u8, __be16); int qlcnic_sriov_set_vf_spoofchk(struct net_device *, int, bool); #else static inline void qlcnic_sriov_pf_disable(struct qlcnic_adapter *adapter) {} diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c index afd687e5e779..50eaafa3eaba 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c @@ -1915,7 +1915,7 @@ int qlcnic_sriov_set_vf_tx_rate(struct net_device *netdev, int vf, } int qlcnic_sriov_set_vf_vlan(struct net_device *netdev, int vf, - u16 vlan, u8 qos) + u16 vlan, u8 qos, __be16 vlan_proto) { struct qlcnic_adapter *adapter = netdev_priv(netdev); struct qlcnic_sriov *sriov = adapter->ahw->sriov; @@ -1928,6 +1928,9 @@ int qlcnic_sriov_set_vf_vlan(struct net_device *netdev, int vf, if (vf >= sriov->num_vfs || qos > 7) return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + if (vlan > MAX_VLAN_ID) { netdev_err(netdev, "Invalid VLAN ID, allowed range is [0 - %d]\n", diff --git a/drivers/net/ethernet/sfc/sriov.c b/drivers/net/ethernet/sfc/sriov.c index 816c44689e67..9abcf4aded30 100644 --- a/drivers/net/ethernet/sfc/sriov.c +++ b/drivers/net/ethernet/sfc/sriov.c @@ -22,7 +22,7 @@ int efx_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac) } int efx_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i, u16 vlan, - u8 qos) + u8 qos, __be16 vlan_proto) { struct efx_nic *efx = netdev_priv(net_dev); @@ -31,6 +31,9 @@ int efx_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i, u16 vlan, (qos & ~(VLAN_PRIO_MASK >> VLAN_PRIO_SHIFT))) return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + return efx->type->sriov_set_vf_vlan(efx, vf_i, vlan, qos); } else { return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/sfc/sriov.h b/drivers/net/ethernet/sfc/sriov.h index 400df526586d..ba1762e7f216 100644 --- a/drivers/net/ethernet/sfc/sriov.h +++ b/drivers/net/ethernet/sfc/sriov.h @@ -16,7 +16,7 @@ int efx_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac); int efx_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i, u16 vlan, - u8 qos); + u8 qos, __be16 vlan_proto); int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf_i, bool spoofchk); int efx_sriov_get_vf_config(struct net_device *net_dev, int vf_i, 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); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7ec9e99d5491..b4fba662cd32 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -619,7 +619,7 @@ enum { enum { IFLA_VF_UNSPEC, IFLA_VF_MAC, /* Hardware queue specific attributes */ - IFLA_VF_VLAN, + IFLA_VF_VLAN, /* VLAN ID and QoS */ IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */ IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */ IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */ @@ -631,6 +631,7 @@ enum { IFLA_VF_TRUST, /* Trust VF */ IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ + IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ __IFLA_VF_MAX, }; @@ -647,6 +648,22 @@ struct ifla_vf_vlan { __u32 qos; }; +enum { + IFLA_VF_VLAN_INFO_UNSPEC, + IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */ + __IFLA_VF_VLAN_INFO_MAX, +}; + +#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1) +#define MAX_VLAN_LIST_LEN 1 + +struct ifla_vf_vlan_info { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; + __be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */ +}; + struct ifla_vf_tx_rate { __u32 vf; __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 0dbae4244a89..3ac8946bf244 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -843,7 +843,10 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, size += nla_total_size(num_vfs * sizeof(struct nlattr)); size += num_vfs * (nla_total_size(sizeof(struct ifla_vf_mac)) + - nla_total_size(sizeof(struct ifla_vf_vlan)) + + nla_total_size(MAX_VLAN_LIST_LEN * + sizeof(struct nlattr)) + + nla_total_size(MAX_VLAN_LIST_LEN * + sizeof(struct ifla_vf_vlan_info)) + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + nla_total_size(sizeof(struct ifla_vf_rate)) + nla_total_size(sizeof(struct ifla_vf_link_state)) + @@ -1111,14 +1114,15 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, struct nlattr *vfinfo) { struct ifla_vf_rss_query_en vf_rss_query_en; + struct nlattr *vf, *vfstats, *vfvlanlist; struct ifla_vf_link_state vf_linkstate; + struct ifla_vf_vlan_info vf_vlan_info; struct ifla_vf_spoofchk vf_spoofchk; struct ifla_vf_tx_rate vf_tx_rate; struct ifla_vf_stats vf_stats; struct ifla_vf_trust vf_trust; struct ifla_vf_vlan vf_vlan; struct ifla_vf_rate vf_rate; - struct nlattr *vf, *vfstats; struct ifla_vf_mac vf_mac; struct ifla_vf_info ivi; @@ -1135,11 +1139,14 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, * IFLA_VF_LINK_STATE_AUTO which equals zero */ ivi.linkstate = 0; + /* VLAN Protocol by default is 802.1Q */ + ivi.vlan_proto = htons(ETH_P_8021Q); if (dev->netdev_ops->ndo_get_vf_config(dev, vfs_num, &ivi)) return 0; vf_mac.vf = vf_vlan.vf = + vf_vlan_info.vf = vf_rate.vf = vf_tx_rate.vf = vf_spoofchk.vf = @@ -1150,6 +1157,9 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; vf_vlan.qos = ivi.qos; + vf_vlan_info.vlan = ivi.vlan; + vf_vlan_info.qos = ivi.qos; + vf_vlan_info.vlan_proto = ivi.vlan_proto; vf_tx_rate.rate = ivi.max_tx_rate; vf_rate.min_tx_rate = ivi.min_tx_rate; vf_rate.max_tx_rate = ivi.max_tx_rate; @@ -1158,10 +1168,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, vf_rss_query_en.setting = ivi.rss_query_en; vf_trust.setting = ivi.trusted; vf = nla_nest_start(skb, IFLA_VF_INFO); - if (!vf) { - nla_nest_cancel(skb, vfinfo); - return -EMSGSIZE; - } + if (!vf) + goto nla_put_vfinfo_failure; if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), @@ -1177,17 +1185,23 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, &vf_rss_query_en) || nla_put(skb, IFLA_VF_TRUST, sizeof(vf_trust), &vf_trust)) - return -EMSGSIZE; + goto nla_put_vf_failure; + vfvlanlist = nla_nest_start(skb, IFLA_VF_VLAN_LIST); + if (!vfvlanlist) + goto nla_put_vf_failure; + if (nla_put(skb, IFLA_VF_VLAN_INFO, sizeof(vf_vlan_info), + &vf_vlan_info)) { + nla_nest_cancel(skb, vfvlanlist); + goto nla_put_vf_failure; + } + nla_nest_end(skb, vfvlanlist); memset(&vf_stats, 0, sizeof(vf_stats)); if (dev->netdev_ops->ndo_get_vf_stats) dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num, &vf_stats); vfstats = nla_nest_start(skb, IFLA_VF_STATS); - if (!vfstats) { - nla_nest_cancel(skb, vf); - nla_nest_cancel(skb, vfinfo); - return -EMSGSIZE; - } + if (!vfstats) + goto nla_put_vf_failure; if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS, vf_stats.rx_packets, IFLA_VF_STATS_PAD) || nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS, @@ -1199,11 +1213,19 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST, vf_stats.broadcast, IFLA_VF_STATS_PAD) || nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST, - vf_stats.multicast, IFLA_VF_STATS_PAD)) - return -EMSGSIZE; + vf_stats.multicast, IFLA_VF_STATS_PAD)) { + nla_nest_cancel(skb, vfstats); + goto nla_put_vf_failure; + } nla_nest_end(skb, vfstats); nla_nest_end(skb, vf); return 0; + +nla_put_vf_failure: + nla_nest_cancel(skb, vf); +nla_put_vfinfo_failure: + nla_nest_cancel(skb, vfinfo); + return -EMSGSIZE; } static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) @@ -1448,6 +1470,7 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) }, [IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) }, + [IFLA_VF_VLAN_LIST] = { .type = NLA_NESTED }, [IFLA_VF_TX_RATE] = { .len = sizeof(struct ifla_vf_tx_rate) }, [IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) }, [IFLA_VF_RATE] = { .len = sizeof(struct ifla_vf_rate) }, @@ -1704,7 +1727,34 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) err = -EOPNOTSUPP; if (ops->ndo_set_vf_vlan) err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, - ivv->qos); + ivv->qos, + htons(ETH_P_8021Q)); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_VLAN_LIST]) { + struct ifla_vf_vlan_info *ivvl[MAX_VLAN_LIST_LEN]; + struct nlattr *attr; + int rem, len = 0; + + err = -EOPNOTSUPP; + if (!ops->ndo_set_vf_vlan) + return err; + + nla_for_each_nested(attr, tb[IFLA_VF_VLAN_LIST], rem) { + if (nla_type(attr) != IFLA_VF_VLAN_INFO || + nla_len(attr) < NLA_HDRLEN) { + return -EINVAL; + } + if (len >= MAX_VLAN_LIST_LEN) + return -EOPNOTSUPP; + ivvl[len] = nla_data(attr); + + len++; + } + err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan, + ivvl[0]->qos, ivvl[0]->vlan_proto); if (err < 0) return err; } -- cgit v1.3-14-g43fede 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 --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 51 ++++++++++++++- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 6 +- drivers/net/ethernet/mellanox/mlx4/fw.c | 89 ++++++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 1 + include/linux/mlx4/cmd.h | 3 +- 5 files changed, 138 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 09c969420eac..b1cef7a0f7ca 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1995,6 +1995,8 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave) int port, err; struct mlx4_vport_state *vp_admin; struct mlx4_vport_oper_state *vp_oper; + struct mlx4_slave_state *slave_state = + &priv->mfunc.master.slave_state[slave]; struct mlx4_active_ports actv_ports = mlx4_get_active_ports( &priv->dev, slave); int min_port = find_first_bit(actv_ports.ports, @@ -2009,7 +2011,19 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave) priv->mfunc.master.vf_admin[slave].enable_smi[port]; vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port]; - vp_oper->state = *vp_admin; + if (vp_admin->vlan_proto != htons(ETH_P_8021AD) || + slave_state->vst_qinq_supported) { + vp_oper->state.vlan_proto = vp_admin->vlan_proto; + vp_oper->state.default_vlan = vp_admin->default_vlan; + vp_oper->state.default_qos = vp_admin->default_qos; + } + vp_oper->state.link_state = vp_admin->link_state; + vp_oper->state.mac = vp_admin->mac; + vp_oper->state.spoofchk = vp_admin->spoofchk; + vp_oper->state.tx_rate = vp_admin->tx_rate; + vp_oper->state.qos_vport = vp_admin->qos_vport; + vp_oper->state.guid = vp_admin->guid; + if (MLX4_VGT != vp_admin->default_vlan) { err = __mlx4_register_vlan(&priv->dev, port, vp_admin->default_vlan, &(vp_oper->vlan_idx)); @@ -2097,6 +2111,7 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, mlx4_warn(dev, "Received reset from slave:%d\n", slave); slave_state[slave].active = false; slave_state[slave].old_vlan_api = false; + slave_state[slave].vst_qinq_supported = false; mlx4_master_deactivate_admin_state(priv, slave); for (i = 0; i < MLX4_EVENT_TYPES_NUM; ++i) { slave_state[slave].event_eq[i].eqn = -1; @@ -2364,6 +2379,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) vf_oper = &priv->mfunc.master.vf_oper[i]; s_state = &priv->mfunc.master.slave_state[i]; s_state->last_cmd = MLX4_COMM_CMD_RESET; + s_state->vst_qinq_supported = false; mutex_init(&priv->mfunc.master.gen_eqe_mutex[i]); for (j = 0; j < MLX4_EVENT_TYPES_NUM; ++j) s_state->event_eq[j].eqn = -1; @@ -2955,10 +2971,13 @@ int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac) EXPORT_SYMBOL_GPL(mlx4_set_vf_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) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_vport_state *vf_admin; + struct mlx4_slave_state *slave_state; + struct mlx4_vport_oper_state *vf_oper; int slave; if ((!mlx4_is_master(dev)) || @@ -2968,12 +2987,31 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos) if ((vlan > 4095) || (qos > 7)) return -EINVAL; + if (proto == htons(ETH_P_8021AD) && + !(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP)) + return -EPROTONOSUPPORT; + + if (proto != htons(ETH_P_8021Q) && + proto != htons(ETH_P_8021AD)) + return -EINVAL; + + if ((proto == htons(ETH_P_8021AD)) && + ((vlan == 0) || (vlan == MLX4_VGT))) + return -EINVAL; + slave = mlx4_get_slave_indx(dev, vf); if (slave < 0) return -EINVAL; + slave_state = &priv->mfunc.master.slave_state[slave]; + if ((proto == htons(ETH_P_8021AD)) && (slave_state->active) && + (!slave_state->vst_qinq_supported)) { + mlx4_err(dev, "vf %d does not support VST QinQ mode\n", vf); + return -EPROTONOSUPPORT; + } port = mlx4_slaves_closest_port(dev, slave, port); vf_admin = &priv->mfunc.master.vf_admin[slave].vport[port]; + vf_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; if (!mlx4_valid_vf_state_change(dev, port, vf_admin, vlan, qos)) return -EPERM; @@ -2983,6 +3021,7 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos) else vf_admin->default_vlan = vlan; vf_admin->default_qos = qos; + vf_admin->vlan_proto = proto; /* If rate was configured prior to VST, we saved the configured rate * in vf_admin->rate and now, if priority supported we enforce the QoS @@ -2991,7 +3030,12 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos) vf_admin->tx_rate) vf_admin->qos_vport = slave; - if (mlx4_master_immediate_activate_vlan_qos(priv, slave, port)) + /* Try to activate new vf state without restart, + * this option is not supported while moving to VST QinQ mode. + */ + if ((proto == htons(ETH_P_8021AD) && + vf_oper->state.vlan_proto != proto) || + mlx4_master_immediate_activate_vlan_qos(priv, slave, port)) mlx4_info(dev, "updating vf %d port %d config will take effect on next VF restart\n", vf, port); @@ -3135,6 +3179,7 @@ int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_in ivf->vlan = s_info->default_vlan; ivf->qos = s_info->default_qos; + ivf->vlan_proto = s_info->vlan_proto; if (mlx4_is_vf_vst_and_prio_qos(dev, port, s_info)) ivf->max_tx_rate = s_info->tx_rate; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 132eeeafcdc4..7e703bed7b82 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2406,10 +2406,8 @@ static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, struct mlx4_en_priv *en_priv = netdev_priv(dev); struct mlx4_en_dev *mdev = en_priv->mdev; - if (vlan_proto != htons(ETH_P_8021Q)) - return -EPROTONOSUPPORT; - - return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos); + return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos, + vlan_proto); } static int mlx4_en_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 7dc9d38a51f8..090bf81076e8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -249,6 +249,72 @@ out: return err; } +static int mlx4_activate_vst_qinq(struct mlx4_priv *priv, int slave, int port) +{ + struct mlx4_vport_oper_state *vp_oper; + struct mlx4_vport_state *vp_admin; + int err; + + vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; + vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port]; + + if (vp_admin->default_vlan != vp_oper->state.default_vlan) { + err = __mlx4_register_vlan(&priv->dev, port, + vp_admin->default_vlan, + &vp_oper->vlan_idx); + if (err) { + vp_oper->vlan_idx = NO_INDX; + mlx4_warn(&priv->dev, + "No vlan resources slave %d, port %d\n", + slave, port); + return err; + } + mlx4_dbg(&priv->dev, "alloc vlan %d idx %d slave %d port %d\n", + (int)(vp_oper->state.default_vlan), + vp_oper->vlan_idx, slave, port); + } + vp_oper->state.vlan_proto = vp_admin->vlan_proto; + vp_oper->state.default_vlan = vp_admin->default_vlan; + vp_oper->state.default_qos = vp_admin->default_qos; + + return 0; +} + +static int mlx4_handle_vst_qinq(struct mlx4_priv *priv, int slave, int port) +{ + struct mlx4_vport_oper_state *vp_oper; + struct mlx4_slave_state *slave_state; + struct mlx4_vport_state *vp_admin; + int err; + + vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; + vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port]; + slave_state = &priv->mfunc.master.slave_state[slave]; + + if ((vp_admin->vlan_proto != htons(ETH_P_8021AD)) || + (!slave_state->active)) + return 0; + + if (vp_oper->state.vlan_proto == vp_admin->vlan_proto && + vp_oper->state.default_vlan == vp_admin->default_vlan && + vp_oper->state.default_qos == vp_admin->default_qos) + return 0; + + if (!slave_state->vst_qinq_supported) { + /* Warn and revert the request to set vst QinQ mode */ + vp_admin->vlan_proto = vp_oper->state.vlan_proto; + vp_admin->default_vlan = vp_oper->state.default_vlan; + vp_admin->default_qos = vp_oper->state.default_qos; + + mlx4_warn(&priv->dev, + "Slave %d does not support VST QinQ mode\n", slave); + return 0; + } + + err = mlx4_activate_vst_qinq(priv, slave, port); + return err; +} + int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, @@ -312,17 +378,18 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, #define QUERY_FUNC_CAP_VF_ENABLE_QP0 0x08 #define QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID 0x80 -#define QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS (1 << 31) #define QUERY_FUNC_CAP_PHV_BIT 0x40 #define QUERY_FUNC_CAP_VLAN_OFFLOAD_DISABLE 0x20 +#define QUERY_FUNC_CAP_SUPPORTS_VST_QINQ BIT(30) +#define QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS BIT(31) + if (vhcr->op_modifier == 1) { struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave); int converted_port = mlx4_slave_convert_port( dev, slave, vhcr->in_modifier); - struct mlx4_vport_oper_state *vp_oper = - &priv->mfunc.master.vf_oper[slave].vport[vhcr->in_modifier]; + struct mlx4_vport_oper_state *vp_oper; if (converted_port < 0) return -EINVAL; @@ -361,6 +428,11 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, MLX4_PUT(outbox->buf, dev->caps.phys_port_id[vhcr->in_modifier], QUERY_FUNC_CAP_PHYS_PORT_ID); + vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; + err = mlx4_handle_vst_qinq(priv, slave, port); + if (err) + return err; + field = 0; if (dev->caps.phv_bit[port]) field |= QUERY_FUNC_CAP_PHV_BIT; @@ -371,6 +443,9 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, } else if (vhcr->op_modifier == 0) { struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave); + struct mlx4_slave_state *slave_state = + &priv->mfunc.master.slave_state[slave]; + /* enable rdma and ethernet interfaces, new quota locations, * and reserved lkey */ @@ -444,6 +519,10 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, size = dev->caps.reserved_lkey + ((slave << 8) & 0xFF00); MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP_RESD_LKEY_OFFSET); + + if (vhcr->in_modifier & QUERY_FUNC_CAP_SUPPORTS_VST_QINQ) + slave_state->vst_qinq_supported = true; + } else err = -EINVAL; @@ -459,10 +538,12 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port, u32 size, qkey; int err = 0, quotas = 0; u32 in_modifier; + u32 slave_caps; op_modifier = !!gen_or_port; /* 0 = general, 1 = logical port */ - in_modifier = op_modifier ? gen_or_port : + slave_caps = QUERY_FUNC_CAP_SUPPORTS_VST_QINQ | QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS; + in_modifier = op_modifier ? gen_or_port : slave_caps; mailbox = mlx4_alloc_cmd_mailbox(dev); if (IS_ERR(mailbox)) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index fdfe1ace07d7..e4878f31e45d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -483,6 +483,7 @@ struct mlx4_slave_state { u8 init_port_mask; bool active; bool old_vlan_api; + bool vst_qinq_supported; u8 function; dma_addr_t vhcr_dma; u16 mtu[MLX4_MAX_PORTS + 1]; 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 v1.3-14-g43fede