* [PATCH 05/15] octeontx2-af: Add mailbox IRQ and msg handlers
From: sunil.kovvuri @ 2018-09-28 6:07 UTC (permalink / raw)
To: netdev, davem; +Cc: arnd, linux-soc, Sunil Goutham
In-Reply-To: <1538114872-10820-1-git-send-email-sunil.kovvuri@gmail.com>
From: Sunil Goutham <sgoutham@marvell.com>
This patch adds support for mailbox interrupt and message
handling. Mapped mailbox region and registered a workqueue
for message handling. Enabled mailbox IRQ of RVU PFs
and registered a interrupt handler. When IRQ is triggered
work is added to the mbox workqueue for msgs to get processed.
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
---
drivers/net/ethernet/marvell/octeontx2/af/mbox.h | 14 +-
drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 254 +++++++++++++++++++++
drivers/net/ethernet/marvell/octeontx2/af/rvu.h | 22 ++
.../net/ethernet/marvell/octeontx2/af/rvu_struct.h | 22 ++
4 files changed, 309 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 8e205fd..fc593f0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -33,6 +33,8 @@
# error "incorrect mailbox area sizes"
#endif
+#define INTR_MASK(pfvfs) ((pfvfs < 64) ? (BIT_ULL(pfvfs) - 1) : (~0ull))
+
#define MBOX_RSP_TIMEOUT 1000 /* in ms, Time to wait for mbox response */
#define MBOX_MSG_ALIGN 16 /* Align mbox msg start to 16bytes */
@@ -90,8 +92,9 @@ struct mbox_msghdr {
void otx2_mbox_reset(struct otx2_mbox *mbox, int devid);
void otx2_mbox_destroy(struct otx2_mbox *mbox);
-int otx2_mbox_init(struct otx2_mbox *mbox, void *hwbase, struct pci_dev *pdev,
- void *reg_base, int direction, int ndevs);
+int otx2_mbox_init(struct otx2_mbox *mbox, void __force *hwbase,
+ struct pci_dev *pdev, void __force *reg_base,
+ int direction, int ndevs);
void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid);
int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid);
int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid);
@@ -115,7 +118,7 @@ static inline struct mbox_msghdr *otx2_mbox_alloc_msg(struct otx2_mbox *mbox,
#define MBOX_MSG_MAX 0xFFFF
#define MBOX_MESSAGES \
-M(READY, 0x001, msg_req, msg_rsp)
+M(READY, 0x001, msg_req, ready_msg_rsp)
enum {
#define M(_name, _id, _1, _2) MBOX_MSG_ ## _name = _id,
@@ -139,4 +142,9 @@ struct msg_rsp {
struct mbox_msghdr hdr;
};
+struct ready_msg_rsp {
+ struct mbox_msghdr hdr;
+ u16 sclk_feq; /* SCLK frequency */
+};
+
#endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index fa5f40b..e795c2f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -258,6 +258,245 @@ static int rvu_setup_hw_resources(struct rvu *rvu)
return 0;
}
+static int rvu_process_mbox_msg(struct rvu *rvu, int devid,
+ struct mbox_msghdr *req)
+{
+ /* Check if valid, if not reply with a invalid msg */
+ if (req->sig != OTX2_MBOX_REQ_SIG)
+ goto bad_message;
+
+ if (req->id == MBOX_MSG_READY)
+ return 0;
+
+bad_message:
+ otx2_reply_invalid_msg(&rvu->mbox, devid, req->pcifunc,
+ req->id);
+ return -ENODEV;
+}
+
+static void rvu_mbox_handler(struct work_struct *work)
+{
+ struct rvu_work *mwork = container_of(work, struct rvu_work, work);
+ struct rvu *rvu = mwork->rvu;
+ struct otx2_mbox_dev *mdev;
+ struct mbox_hdr *req_hdr;
+ struct mbox_msghdr *msg;
+ struct otx2_mbox *mbox;
+ int offset, id, err;
+ u16 pf;
+
+ mbox = &rvu->mbox;
+ pf = mwork - rvu->mbox_wrk;
+ mdev = &mbox->dev[pf];
+
+ /* Process received mbox messages */
+ req_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+ if (req_hdr->num_msgs == 0)
+ return;
+
+ offset = mbox->rx_start + ALIGN(sizeof(*req_hdr), MBOX_MSG_ALIGN);
+
+ for (id = 0; id < req_hdr->num_msgs; id++) {
+ msg = (struct mbox_msghdr *)(mdev->mbase + offset);
+
+ /* Set which PF sent this message based on mbox IRQ */
+ msg->pcifunc &= ~(RVU_PFVF_PF_MASK << RVU_PFVF_PF_SHIFT);
+ msg->pcifunc |= (pf << RVU_PFVF_PF_SHIFT);
+ err = rvu_process_mbox_msg(rvu, pf, msg);
+ if (!err) {
+ offset = mbox->rx_start + msg->next_msgoff;
+ continue;
+ }
+
+ if (msg->pcifunc & RVU_PFVF_FUNC_MASK)
+ dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d:VF%d\n",
+ err, otx2_mbox_id2name(msg->id), msg->id, pf,
+ (msg->pcifunc & RVU_PFVF_FUNC_MASK) - 1);
+ else
+ dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d\n",
+ err, otx2_mbox_id2name(msg->id), msg->id, pf);
+ }
+
+ /* Send mbox responses to PF */
+ otx2_mbox_msg_send(mbox, pf);
+}
+
+static int rvu_mbox_init(struct rvu *rvu)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+ struct rvu_work *mwork;
+ void __iomem *hwbase = NULL;
+ u64 bar4_addr;
+ int err, pf;
+
+ rvu->mbox_wq = alloc_workqueue("rvu_afpf_mailbox",
+ WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
+ hw->total_pfs);
+ if (!rvu->mbox_wq)
+ return -ENOMEM;
+
+ rvu->mbox_wrk = devm_kcalloc(rvu->dev, hw->total_pfs,
+ sizeof(struct rvu_work), GFP_KERNEL);
+ if (!rvu->mbox_wrk) {
+ err = -ENOMEM;
+ goto exit;
+ }
+
+ /* Map mbox region shared with PFs */
+ bar4_addr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PF_BAR4_ADDR);
+ /* Mailbox is a reserved memory (in RAM) region shared between
+ * RVU devices, shouldn't be mapped as device memory to allow
+ * unaligned accesses.
+ */
+ hwbase = ioremap_wc(bar4_addr, MBOX_SIZE * hw->total_pfs);
+ if (!hwbase) {
+ dev_err(rvu->dev, "Unable to map mailbox region\n");
+ err = -ENOMEM;
+ goto exit;
+ }
+
+ err = otx2_mbox_init(&rvu->mbox, hwbase, rvu->pdev, rvu->afreg_base,
+ MBOX_DIR_AFPF, hw->total_pfs);
+ if (err)
+ goto exit;
+
+ for (pf = 0; pf < hw->total_pfs; pf++) {
+ mwork = &rvu->mbox_wrk[pf];
+ mwork->rvu = rvu;
+ INIT_WORK(&mwork->work, rvu_mbox_handler);
+ }
+
+ return 0;
+exit:
+ if (hwbase)
+ iounmap((void __iomem *)hwbase);
+ destroy_workqueue(rvu->mbox_wq);
+ return err;
+}
+
+static void rvu_mbox_destroy(struct rvu *rvu)
+{
+ if (rvu->mbox_wq) {
+ flush_workqueue(rvu->mbox_wq);
+ destroy_workqueue(rvu->mbox_wq);
+ rvu->mbox_wq = NULL;
+ }
+
+ if (rvu->mbox.hwbase)
+ iounmap((void __iomem *)rvu->mbox.hwbase);
+
+ otx2_mbox_destroy(&rvu->mbox);
+}
+
+static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
+{
+ struct rvu *rvu = (struct rvu *)rvu_irq;
+ struct otx2_mbox_dev *mdev;
+ struct otx2_mbox *mbox;
+ struct mbox_hdr *hdr;
+ u64 intr;
+ u8 pf;
+
+ intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT);
+ /* Clear interrupts */
+ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT, intr);
+
+ /* Sync with mbox memory region */
+ smp_wmb();
+
+ for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+ if (intr & (1ULL << pf)) {
+ mbox = &rvu->mbox;
+ mdev = &mbox->dev[pf];
+ hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+ if (hdr->num_msgs)
+ queue_work(rvu->mbox_wq,
+ &rvu->mbox_wrk[pf].work);
+ }
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void rvu_enable_mbox_intr(struct rvu *rvu)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+
+ /* Clear spurious irqs, if any */
+ rvu_write64(rvu, BLKADDR_RVUM,
+ RVU_AF_PFAF_MBOX_INT, INTR_MASK(hw->total_pfs));
+
+ /* Enable mailbox interrupt for all PFs except PF0 i.e AF itself */
+ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT_ENA_W1S,
+ INTR_MASK(hw->total_pfs) & ~1ULL);
+}
+
+static void rvu_unregister_interrupts(struct rvu *rvu)
+{
+ int irq;
+
+ /* Disable the Mbox interrupt */
+ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT_ENA_W1C,
+ INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
+ for (irq = 0; irq < rvu->num_vec; irq++) {
+ if (rvu->irq_allocated[irq])
+ free_irq(pci_irq_vector(rvu->pdev, irq), rvu);
+ }
+
+ pci_free_irq_vectors(rvu->pdev);
+ rvu->num_vec = 0;
+}
+
+static int rvu_register_interrupts(struct rvu *rvu)
+{
+ int ret;
+
+ rvu->num_vec = pci_msix_vec_count(rvu->pdev);
+
+ rvu->irq_name = devm_kmalloc_array(rvu->dev, rvu->num_vec,
+ NAME_SIZE, GFP_KERNEL);
+ if (!rvu->irq_name)
+ return -ENOMEM;
+
+ rvu->irq_allocated = devm_kcalloc(rvu->dev, rvu->num_vec,
+ sizeof(bool), GFP_KERNEL);
+ if (!rvu->irq_allocated)
+ return -ENOMEM;
+
+ /* Enable MSI-X */
+ ret = pci_alloc_irq_vectors(rvu->pdev, rvu->num_vec,
+ rvu->num_vec, PCI_IRQ_MSIX);
+ if (ret < 0) {
+ dev_err(rvu->dev,
+ "RVUAF: Request for %d msix vectors failed, ret %d\n",
+ rvu->num_vec, ret);
+ return ret;
+ }
+
+ /* Register mailbox interrupt handler */
+ sprintf(&rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], "RVUAF Mbox");
+ ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_MBOX),
+ rvu_mbox_intr_handler, 0,
+ &rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], rvu);
+ if (ret) {
+ dev_err(rvu->dev,
+ "RVUAF: IRQ registration failed for mbox irq\n");
+ goto fail;
+ }
+
+ rvu->irq_allocated[RVU_AF_INT_VEC_MBOX] = true;
+
+ /* Enable mailbox interrupts from all PFs */
+ rvu_enable_mbox_intr(rvu);
+
+ return 0;
+
+fail:
+ pci_free_irq_vectors(rvu->pdev);
+ return ret;
+}
+
static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct device *dev = &pdev->dev;
@@ -320,8 +559,21 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (err)
goto err_release_regions;
+ err = rvu_mbox_init(rvu);
+ if (err)
+ goto err_hwsetup;
+
+ err = rvu_register_interrupts(rvu);
+ if (err)
+ goto err_mbox;
+
return 0;
+err_mbox:
+ rvu_mbox_destroy(rvu);
+err_hwsetup:
+ rvu_reset_all_blocks(rvu);
+ rvu_free_hw_resources(rvu);
err_release_regions:
pci_release_regions(pdev);
err_disable_device:
@@ -337,6 +589,8 @@ static void rvu_remove(struct pci_dev *pdev)
{
struct rvu *rvu = pci_get_drvdata(pdev);
+ rvu_unregister_interrupts(rvu);
+ rvu_mbox_destroy(rvu);
rvu_reset_all_blocks(rvu);
rvu_free_hw_resources(rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 592b820..2fb9407 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -12,6 +12,7 @@
#define RVU_H
#include "rvu_struct.h"
+#include "mbox.h"
/* PCI device IDs */
#define PCI_DEVID_OCTEONTX2_RVU_AF 0xA065
@@ -23,6 +24,17 @@
#define NAME_SIZE 32
+/* PF_FUNC */
+#define RVU_PFVF_PF_SHIFT 10
+#define RVU_PFVF_PF_MASK 0x3F
+#define RVU_PFVF_FUNC_SHIFT 0
+#define RVU_PFVF_FUNC_MASK 0x3FF
+
+struct rvu_work {
+ struct work_struct work;
+ struct rvu *rvu;
+};
+
struct rsrc_bmap {
unsigned long *bmap; /* Pointer to resource bitmap */
u16 max; /* Max resource id or count */
@@ -57,6 +69,16 @@ struct rvu {
struct pci_dev *pdev;
struct device *dev;
struct rvu_hwinfo *hw;
+
+ /* Mbox */
+ struct otx2_mbox mbox;
+ struct rvu_work *mbox_wrk;
+ struct workqueue_struct *mbox_wq;
+
+ /* MSI-X */
+ u16 num_vec;
+ char *irq_name;
+ bool *irq_allocated;
};
static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
index 9e11333..4214bc0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
@@ -31,4 +31,26 @@ enum rvu_block_addr_e {
BLK_COUNT = 0xfULL,
};
+/* RVU Admin function Interrupt Vector Enumeration */
+enum rvu_af_int_vec_e {
+ RVU_AF_INT_VEC_POISON = 0x0,
+ RVU_AF_INT_VEC_PFFLR = 0x1,
+ RVU_AF_INT_VEC_PFME = 0x2,
+ RVU_AF_INT_VEC_GEN = 0x3,
+ RVU_AF_INT_VEC_MBOX = 0x4,
+};
+
+/**
+ * RVU PF Interrupt Vector Enumeration
+ */
+enum rvu_pf_int_vec_e {
+ RVU_PF_INT_VEC_VFFLR0 = 0x0,
+ RVU_PF_INT_VEC_VFFLR1 = 0x1,
+ RVU_PF_INT_VEC_VFME0 = 0x2,
+ RVU_PF_INT_VEC_VFME1 = 0x3,
+ RVU_PF_INT_VEC_VFPF_MBOX0 = 0x4,
+ RVU_PF_INT_VEC_VFPF_MBOX1 = 0x5,
+ RVU_PF_INT_VEC_AFPF_MBOX = 0x6,
+};
+
#endif /* RVU_STRUCT_H */
--
2.7.4
^ permalink raw reply related
* [PATCH 04/15] octeontx2-af: Add mailbox support infra
From: sunil.kovvuri @ 2018-09-28 6:07 UTC (permalink / raw)
To: netdev, davem
Cc: arnd, linux-soc, Sunil Goutham, Aleksey Makarov, Lukasz Bartosik
In-Reply-To: <1538114872-10820-1-git-send-email-sunil.kovvuri@gmail.com>
From: Sunil Goutham <sgoutham@marvell.com>
This patch adds mailbox support infrastructure APIs.
Each RVU device has a dedicated 64KB mailbox region
shared with it's peer for communication. RVU AF has
a separate mailbox region shared with each of RVU PFs
and a RVU PF has a separate region shared with each of
it's VF.
These set of APIs are used by this driver (RVU AF) and
other RVU PF/VF drivers eg netdev, crypto e.t.c.
Signed-off-by: Aleksey Makarov <amakarov@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: Lukasz Bartosik <lbartosik@marvell.com>
---
drivers/net/ethernet/marvell/octeontx2/Kconfig | 4 +
drivers/net/ethernet/marvell/octeontx2/af/Makefile | 2 +
drivers/net/ethernet/marvell/octeontx2/af/mbox.c | 303 +++++++++++++++++++++
drivers/net/ethernet/marvell/octeontx2/af/mbox.h | 142 ++++++++++
.../net/ethernet/marvell/octeontx2/af/rvu_reg.h | 4 +
5 files changed, 455 insertions(+)
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/mbox.c
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/mbox.h
diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig
index 9743502..8002f9c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/Kconfig
+++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig
@@ -2,8 +2,12 @@
# Marvell OcteonTX2 drivers configuration
#
+config OCTEONTX2_MBOX
+ tristate
+
config OCTEONTX2_AF
tristate "Marvell OcteonTX2 RVU Admin Function driver"
+ select OCTEONTX2_MBOX
depends on ARM64 && PCI
help
This driver supports Marvell's OcteonTX2 Resource Virtualization
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
index dacbd16..ac17cb9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
@@ -3,6 +3,8 @@
# Makefile for Marvell's OcteonTX2 RVU Admin Function driver
#
+obj-$(CONFIG_OCTEONTX2_MBOX) += octeontx2_mbox.o
obj-$(CONFIG_OCTEONTX2_AF) += octeontx2_af.o
+octeontx2_mbox-y := mbox.o
octeontx2_af-y := rvu.o
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
new file mode 100644
index 0000000..0722fa4
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell OcteonTx2 RVU Admin Function driver
+ *
+ * Copyright (C) 2018 Marvell International Ltd.
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+
+#include "rvu_reg.h"
+#include "mbox.h"
+
+static const u16 msgs_offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
+
+void otx2_mbox_reset(struct otx2_mbox *mbox, int devid)
+{
+ struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+ struct mbox_hdr *tx_hdr =
+ (struct mbox_hdr *)(mdev->mbase + mbox->tx_start);
+ struct mbox_hdr *rx_hdr =
+ (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+
+ spin_lock(&mdev->mbox_lock);
+ mdev->msg_size = 0;
+ mdev->rsp_size = 0;
+ tx_hdr->num_msgs = 0;
+ rx_hdr->num_msgs = 0;
+ spin_unlock(&mdev->mbox_lock);
+}
+EXPORT_SYMBOL(otx2_mbox_reset);
+
+void otx2_mbox_destroy(struct otx2_mbox *mbox)
+{
+ mbox->reg_base = NULL;
+ mbox->hwbase = NULL;
+
+ kfree(mbox->dev);
+ mbox->dev = NULL;
+}
+EXPORT_SYMBOL(otx2_mbox_destroy);
+
+int otx2_mbox_init(struct otx2_mbox *mbox, void *hwbase, struct pci_dev *pdev,
+ void *reg_base, int direction, int ndevs)
+{
+ int devid;
+ struct otx2_mbox_dev *mdev;
+
+ switch (direction) {
+ case MBOX_DIR_AFPF:
+ case MBOX_DIR_PFVF:
+ mbox->tx_start = MBOX_DOWN_TX_START;
+ mbox->rx_start = MBOX_DOWN_RX_START;
+ mbox->tx_size = MBOX_DOWN_TX_SIZE;
+ mbox->rx_size = MBOX_DOWN_RX_SIZE;
+ break;
+ case MBOX_DIR_PFAF:
+ case MBOX_DIR_VFPF:
+ mbox->tx_start = MBOX_DOWN_RX_START;
+ mbox->rx_start = MBOX_DOWN_TX_START;
+ mbox->tx_size = MBOX_DOWN_RX_SIZE;
+ mbox->rx_size = MBOX_DOWN_TX_SIZE;
+ break;
+ case MBOX_DIR_AFPF_UP:
+ case MBOX_DIR_PFVF_UP:
+ mbox->tx_start = MBOX_UP_TX_START;
+ mbox->rx_start = MBOX_UP_RX_START;
+ mbox->tx_size = MBOX_UP_TX_SIZE;
+ mbox->rx_size = MBOX_UP_RX_SIZE;
+ break;
+ case MBOX_DIR_PFAF_UP:
+ case MBOX_DIR_VFPF_UP:
+ mbox->tx_start = MBOX_UP_RX_START;
+ mbox->rx_start = MBOX_UP_TX_START;
+ mbox->tx_size = MBOX_UP_RX_SIZE;
+ mbox->rx_size = MBOX_UP_TX_SIZE;
+ break;
+ default:
+ return -ENODEV;
+ }
+
+ switch (direction) {
+ case MBOX_DIR_AFPF:
+ case MBOX_DIR_AFPF_UP:
+ mbox->trigger = RVU_AF_AFPF_MBOX0;
+ mbox->tr_shift = 4;
+ break;
+ case MBOX_DIR_PFAF:
+ case MBOX_DIR_PFAF_UP:
+ mbox->trigger = RVU_PF_PFAF_MBOX1;
+ mbox->tr_shift = 0;
+ break;
+ case MBOX_DIR_PFVF:
+ case MBOX_DIR_PFVF_UP:
+ mbox->trigger = RVU_PF_VFX_PFVF_MBOX0;
+ mbox->tr_shift = 12;
+ break;
+ case MBOX_DIR_VFPF:
+ case MBOX_DIR_VFPF_UP:
+ mbox->trigger = RVU_VF_VFPF_MBOX1;
+ mbox->tr_shift = 0;
+ break;
+ default:
+ return -ENODEV;
+ }
+
+ mbox->reg_base = reg_base;
+ mbox->hwbase = hwbase;
+ mbox->pdev = pdev;
+
+ mbox->dev = kcalloc(ndevs, sizeof(struct otx2_mbox_dev), GFP_KERNEL);
+ if (!mbox->dev) {
+ otx2_mbox_destroy(mbox);
+ return -ENOMEM;
+ }
+
+ mbox->ndevs = ndevs;
+ for (devid = 0; devid < ndevs; devid++) {
+ mdev = &mbox->dev[devid];
+ mdev->mbase = mbox->hwbase + (devid * MBOX_SIZE);
+ spin_lock_init(&mdev->mbox_lock);
+ /* Init header to reset value */
+ otx2_mbox_reset(mbox, devid);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(otx2_mbox_init);
+
+int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid)
+{
+ struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+ int timeout = 0, sleep = 1;
+
+ while (mdev->num_msgs != mdev->msgs_acked) {
+ msleep(sleep);
+ timeout += sleep;
+ if (timeout >= MBOX_RSP_TIMEOUT)
+ return -EIO;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(otx2_mbox_wait_for_rsp);
+
+int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid)
+{
+ struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+ unsigned long timeout = jiffies + 1 * HZ;
+
+ while (!time_after(jiffies, timeout)) {
+ if (mdev->num_msgs == mdev->msgs_acked)
+ return 0;
+ cpu_relax();
+ }
+ return -EIO;
+}
+EXPORT_SYMBOL(otx2_mbox_busy_poll_for_rsp);
+
+void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid)
+{
+ struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+ struct mbox_hdr *tx_hdr =
+ (struct mbox_hdr *)(mdev->mbase + mbox->tx_start);
+ struct mbox_hdr *rx_hdr =
+ (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+
+ spin_lock(&mdev->mbox_lock);
+ /* Reset header for next messages */
+ mdev->msg_size = 0;
+ mdev->rsp_size = 0;
+ mdev->msgs_acked = 0;
+
+ /* Sync mbox data into memory */
+ smp_wmb();
+
+ /* num_msgs != 0 signals to the peer that the buffer has a number of
+ * messages. So this should be written after writing all the messages
+ * to the shared memory.
+ */
+ tx_hdr->num_msgs = mdev->num_msgs;
+ rx_hdr->num_msgs = 0;
+ spin_unlock(&mdev->mbox_lock);
+
+ /* The interrupt should be fired after num_msgs is written
+ * to the shared memory
+ */
+ writeq(1, (void __iomem *)mbox->reg_base +
+ (mbox->trigger | (devid << mbox->tr_shift)));
+}
+EXPORT_SYMBOL(otx2_mbox_msg_send);
+
+struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid,
+ int size, int size_rsp)
+{
+ struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+ struct mbox_msghdr *msghdr = NULL;
+
+ spin_lock(&mdev->mbox_lock);
+ size = ALIGN(size, MBOX_MSG_ALIGN);
+ size_rsp = ALIGN(size_rsp, MBOX_MSG_ALIGN);
+ /* Check if there is space in mailbox */
+ if ((mdev->msg_size + size) > mbox->tx_size - msgs_offset)
+ goto exit;
+ if ((mdev->rsp_size + size_rsp) > mbox->rx_size - msgs_offset)
+ goto exit;
+
+ if (mdev->msg_size == 0)
+ mdev->num_msgs = 0;
+ mdev->num_msgs++;
+
+ msghdr = (struct mbox_msghdr *)(mdev->mbase + mbox->tx_start +
+ msgs_offset + mdev->msg_size);
+ /* Clear the whole msg region */
+ memset(msghdr, 0, sizeof(*msghdr) + size);
+ /* Init message header with reset values */
+ msghdr->ver = OTX2_MBOX_VERSION;
+ mdev->msg_size += size;
+ mdev->rsp_size += size_rsp;
+ msghdr->next_msgoff = mdev->msg_size + msgs_offset;
+exit:
+ spin_unlock(&mdev->mbox_lock);
+
+ return msghdr;
+}
+EXPORT_SYMBOL(otx2_mbox_alloc_msg_rsp);
+
+struct mbox_msghdr *otx2_mbox_get_rsp(struct otx2_mbox *mbox, int devid,
+ struct mbox_msghdr *msg)
+{
+ struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+ unsigned long imsg = mbox->tx_start + msgs_offset;
+ unsigned long irsp = mbox->rx_start + msgs_offset;
+ u16 msgs;
+
+ if (mdev->num_msgs != mdev->msgs_acked)
+ return ERR_PTR(-ENODEV);
+
+ for (msgs = 0; msgs < mdev->msgs_acked; msgs++) {
+ struct mbox_msghdr *pmsg = mdev->mbase + imsg;
+ struct mbox_msghdr *prsp = mdev->mbase + irsp;
+
+ if (msg == pmsg) {
+ if (pmsg->id != prsp->id)
+ return ERR_PTR(-ENODEV);
+ return prsp;
+ }
+
+ imsg = pmsg->next_msgoff;
+ irsp = prsp->next_msgoff;
+ }
+
+ return ERR_PTR(-ENODEV);
+}
+EXPORT_SYMBOL(otx2_mbox_get_rsp);
+
+int
+otx2_reply_invalid_msg(struct otx2_mbox *mbox, int devid, u16 pcifunc, u16 id)
+{
+ struct msg_rsp *rsp;
+
+ rsp = (struct msg_rsp *)
+ otx2_mbox_alloc_msg(mbox, devid, sizeof(*rsp));
+ if (!rsp)
+ return -ENOMEM;
+ rsp->hdr.id = id;
+ rsp->hdr.sig = OTX2_MBOX_RSP_SIG;
+ rsp->hdr.rc = MBOX_MSG_INVALID;
+ rsp->hdr.pcifunc = pcifunc;
+ return 0;
+}
+EXPORT_SYMBOL(otx2_reply_invalid_msg);
+
+bool otx2_mbox_nonempty(struct otx2_mbox *mbox, int devid)
+{
+ struct otx2_mbox_dev *mdev = &mbox->dev[devid];
+ bool ret;
+
+ spin_lock(&mdev->mbox_lock);
+ ret = mdev->num_msgs != 0;
+ spin_unlock(&mdev->mbox_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(otx2_mbox_nonempty);
+
+const char *otx2_mbox_id2name(u16 id)
+{
+ switch (id) {
+#define M(_name, _id, _1, _2) case _id: return # _name;
+ MBOX_MESSAGES
+#undef M
+ default:
+ return "INVALID ID";
+ }
+}
+EXPORT_SYMBOL(otx2_mbox_id2name);
+
+MODULE_AUTHOR("Marvell International Ltd.");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
new file mode 100644
index 0000000..8e205fd
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -0,0 +1,142 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Marvell OcteonTx2 RVU Admin Function driver
+ *
+ * Copyright (C) 2018 Marvell International Ltd.
+ *
+ * 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.
+ */
+
+#ifndef MBOX_H
+#define MBOX_H
+
+#include <linux/etherdevice.h>
+#include <linux/sizes.h>
+
+#include "rvu_struct.h"
+
+#define MBOX_SIZE SZ_64K
+
+/* AF/PF: PF initiated, PF/VF VF initiated */
+#define MBOX_DOWN_RX_START 0
+#define MBOX_DOWN_RX_SIZE (46 * SZ_1K)
+#define MBOX_DOWN_TX_START (MBOX_DOWN_RX_START + MBOX_DOWN_RX_SIZE)
+#define MBOX_DOWN_TX_SIZE (16 * SZ_1K)
+/* AF/PF: AF initiated, PF/VF PF initiated */
+#define MBOX_UP_RX_START (MBOX_DOWN_TX_START + MBOX_DOWN_TX_SIZE)
+#define MBOX_UP_RX_SIZE SZ_1K
+#define MBOX_UP_TX_START (MBOX_UP_RX_START + MBOX_UP_RX_SIZE)
+#define MBOX_UP_TX_SIZE SZ_1K
+
+#if MBOX_UP_TX_SIZE + MBOX_UP_TX_START != MBOX_SIZE
+# error "incorrect mailbox area sizes"
+#endif
+
+#define MBOX_RSP_TIMEOUT 1000 /* in ms, Time to wait for mbox response */
+
+#define MBOX_MSG_ALIGN 16 /* Align mbox msg start to 16bytes */
+
+/* Mailbox directions */
+#define MBOX_DIR_AFPF 0 /* AF replies to PF */
+#define MBOX_DIR_PFAF 1 /* PF sends messages to AF */
+#define MBOX_DIR_PFVF 2 /* PF replies to VF */
+#define MBOX_DIR_VFPF 3 /* VF sends messages to PF */
+#define MBOX_DIR_AFPF_UP 4 /* AF sends messages to PF */
+#define MBOX_DIR_PFAF_UP 5 /* PF replies to AF */
+#define MBOX_DIR_PFVF_UP 6 /* PF sends messages to VF */
+#define MBOX_DIR_VFPF_UP 7 /* VF replies to PF */
+
+struct otx2_mbox_dev {
+ void *mbase; /* This dev's mbox region */
+ spinlock_t mbox_lock;
+ u16 msg_size; /* Total msg size to be sent */
+ u16 rsp_size; /* Total rsp size to be sure the reply is ok */
+ u16 num_msgs; /* No of msgs sent or waiting for response */
+ u16 msgs_acked; /* No of msgs for which response is received */
+};
+
+struct otx2_mbox {
+ struct pci_dev *pdev;
+ void *hwbase; /* Mbox region advertised by HW */
+ void *reg_base;/* CSR base for this dev */
+ u64 trigger; /* Trigger mbox notification */
+ u16 tr_shift; /* Mbox trigger shift */
+ u64 rx_start; /* Offset of Rx region in mbox memory */
+ u64 tx_start; /* Offset of Tx region in mbox memory */
+ u16 rx_size; /* Size of Rx region */
+ u16 tx_size; /* Size of Tx region */
+ u16 ndevs; /* The number of peers */
+ struct otx2_mbox_dev *dev;
+};
+
+/* Header which preceeds all mbox messages */
+struct mbox_hdr {
+ u16 num_msgs; /* No of msgs embedded */
+};
+
+/* Header which preceeds every msg and is also part of it */
+struct mbox_msghdr {
+ u16 pcifunc; /* Who's sending this msg */
+ u16 id; /* Mbox message ID */
+#define OTX2_MBOX_REQ_SIG (0xdead)
+#define OTX2_MBOX_RSP_SIG (0xbeef)
+ u16 sig; /* Signature, for validating corrupted msgs */
+#define OTX2_MBOX_VERSION (0x0001)
+ u16 ver; /* Version of msg's structure for this ID */
+ u16 next_msgoff; /* Offset of next msg within mailbox region */
+ int rc; /* Msg process'ed response code */
+};
+
+void otx2_mbox_reset(struct otx2_mbox *mbox, int devid);
+void otx2_mbox_destroy(struct otx2_mbox *mbox);
+int otx2_mbox_init(struct otx2_mbox *mbox, void *hwbase, struct pci_dev *pdev,
+ void *reg_base, int direction, int ndevs);
+void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid);
+int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid);
+int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid);
+struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid,
+ int size, int size_rsp);
+struct mbox_msghdr *otx2_mbox_get_rsp(struct otx2_mbox *mbox, int devid,
+ struct mbox_msghdr *msg);
+int otx2_reply_invalid_msg(struct otx2_mbox *mbox, int devid,
+ u16 pcifunc, u16 id);
+bool otx2_mbox_nonempty(struct otx2_mbox *mbox, int devid);
+const char *otx2_mbox_id2name(u16 id);
+static inline struct mbox_msghdr *otx2_mbox_alloc_msg(struct otx2_mbox *mbox,
+ int devid, int size)
+{
+ return otx2_mbox_alloc_msg_rsp(mbox, devid, size, 0);
+}
+
+/* Mailbox message types */
+#define MBOX_MSG_MASK 0xFFFF
+#define MBOX_MSG_INVALID 0xFFFE
+#define MBOX_MSG_MAX 0xFFFF
+
+#define MBOX_MESSAGES \
+M(READY, 0x001, msg_req, msg_rsp)
+
+enum {
+#define M(_name, _id, _1, _2) MBOX_MSG_ ## _name = _id,
+MBOX_MESSAGES
+#undef M
+};
+
+/* Mailbox message formats */
+
+/* Generic request msg used for those mbox messages which
+ * don't send any data in the request.
+ */
+struct msg_req {
+ struct mbox_msghdr hdr;
+};
+
+/* Generic rsponse msg used a ack or response for those mbox
+ * messages which doesn't have a specific rsp msg format.
+ */
+struct msg_rsp {
+ struct mbox_msghdr hdr;
+};
+
+#endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index bbeed77..0d69ec0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -101,6 +101,10 @@
#define RVU_PF_MSIX_VECX_CTL(a) (0x008 | (a) << 4)
#define RVU_PF_MSIX_PBAX(a) (0xF0000 | (a) << 3)
+/* RVU VF registers */
+#define RVU_VF_VFPF_MBOX0 (0x00000)
+#define RVU_VF_VFPF_MBOX1 (0x00008)
+
/* NPA block's admin function registers */
#define NPA_AF_BLK_RST (0x0000)
#define NPA_AF_CONST (0x0010)
--
2.7.4
^ permalink raw reply related
* [PATCH 03/15] octeontx2-af: Gather RVU blocks HW info
From: sunil.kovvuri @ 2018-09-28 6:07 UTC (permalink / raw)
To: netdev, davem; +Cc: arnd, linux-soc, Sunil Goutham
In-Reply-To: <1538114872-10820-1-git-send-email-sunil.kovvuri@gmail.com>
From: Sunil Goutham <sgoutham@marvell.com>
This patch gathers NPA/NIX/SSO/SSOW/TIM/CPT RVU blocks's
HW info like number of LFs. Important register offsets
saved for later use to avoid code duplication for each block.
A bitmap is allocated for each of the blocks which later
on will be used to allocate a LF for a RVU PF/VF.
Also added RVU NIX/NPA block registers and few registers
of other blocks.
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
---
drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 167 +++++++++++
drivers/net/ethernet/marvell/octeontx2/af/rvu.h | 21 ++
.../net/ethernet/marvell/octeontx2/af/rvu_reg.h | 333 ++++++++++++++++++++-
3 files changed, 517 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index d40fabf..fa5f40b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -57,6 +57,15 @@ int rvu_poll_reg(struct rvu *rvu, u64 block, u64 offset, u64 mask, bool zero)
return -EBUSY;
}
+int rvu_alloc_bitmap(struct rsrc_bmap *rsrc)
+{
+ rsrc->bmap = kcalloc(BITS_TO_LONGS(rsrc->max),
+ sizeof(long), GFP_KERNEL);
+ if (!rsrc->bmap)
+ return -ENOMEM;
+ return 0;
+}
+
static void rvu_check_block_implemented(struct rvu *rvu)
{
struct rvu_hwinfo *hw = rvu->hw;
@@ -98,6 +107,157 @@ static void rvu_reset_all_blocks(struct rvu *rvu)
rvu_block_reset(rvu, BLKADDR_NDC2, NDC_AF_BLK_RST);
}
+static void rvu_free_hw_resources(struct rvu *rvu)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+ struct rvu_block *block;
+ int id;
+
+ /* Free all bitmaps */
+ for (id = 0; id < BLK_COUNT; id++) {
+ block = &hw->block[id];
+ kfree(block->lf.bmap);
+ }
+}
+
+static int rvu_setup_hw_resources(struct rvu *rvu)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+ struct rvu_block *block;
+ int err;
+ u64 cfg;
+
+ /* Get HW supported max RVU PF & VF count */
+ cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_CONST);
+ hw->total_pfs = (cfg >> 32) & 0xFF;
+ hw->total_vfs = (cfg >> 20) & 0xFFF;
+ hw->max_vfs_per_pf = (cfg >> 40) & 0xFF;
+
+ /* Init NPA LF's bitmap */
+ block = &hw->block[BLKADDR_NPA];
+ if (!block->implemented)
+ goto nix;
+ cfg = rvu_read64(rvu, BLKADDR_NPA, NPA_AF_CONST);
+ block->lf.max = (cfg >> 16) & 0xFFF;
+ block->addr = BLKADDR_NPA;
+ block->lfshift = 8;
+ block->lookup_reg = NPA_AF_RVU_LF_CFG_DEBUG;
+ block->pf_lfcnt_reg = RVU_PRIV_PFX_NPA_CFG;
+ block->vf_lfcnt_reg = RVU_PRIV_HWVFX_NPA_CFG;
+ block->lfcfg_reg = NPA_PRIV_LFX_CFG;
+ block->msixcfg_reg = NPA_PRIV_LFX_INT_CFG;
+ block->lfreset_reg = NPA_AF_LF_RST;
+ sprintf(block->name, "NPA");
+ err = rvu_alloc_bitmap(&block->lf);
+ if (err)
+ return err;
+
+nix:
+ /* Init NIX LF's bitmap */
+ block = &hw->block[BLKADDR_NIX0];
+ if (!block->implemented)
+ goto sso;
+ cfg = rvu_read64(rvu, BLKADDR_NIX0, NIX_AF_CONST2);
+ block->lf.max = cfg & 0xFFF;
+ block->addr = BLKADDR_NIX0;
+ block->lfshift = 8;
+ block->lookup_reg = NIX_AF_RVU_LF_CFG_DEBUG;
+ block->pf_lfcnt_reg = RVU_PRIV_PFX_NIX_CFG;
+ block->vf_lfcnt_reg = RVU_PRIV_HWVFX_NIX_CFG;
+ block->lfcfg_reg = NIX_PRIV_LFX_CFG;
+ block->msixcfg_reg = NIX_PRIV_LFX_INT_CFG;
+ block->lfreset_reg = NIX_AF_LF_RST;
+ sprintf(block->name, "NIX");
+ err = rvu_alloc_bitmap(&block->lf);
+ if (err)
+ return err;
+
+sso:
+ /* Init SSO group's bitmap */
+ block = &hw->block[BLKADDR_SSO];
+ if (!block->implemented)
+ goto ssow;
+ cfg = rvu_read64(rvu, BLKADDR_SSO, SSO_AF_CONST);
+ block->lf.max = cfg & 0xFFFF;
+ block->addr = BLKADDR_SSO;
+ block->multislot = true;
+ block->lfshift = 3;
+ block->lookup_reg = SSO_AF_RVU_LF_CFG_DEBUG;
+ block->pf_lfcnt_reg = RVU_PRIV_PFX_SSO_CFG;
+ block->vf_lfcnt_reg = RVU_PRIV_HWVFX_SSO_CFG;
+ block->lfcfg_reg = SSO_PRIV_LFX_HWGRP_CFG;
+ block->msixcfg_reg = SSO_PRIV_LFX_HWGRP_INT_CFG;
+ block->lfreset_reg = SSO_AF_LF_HWGRP_RST;
+ sprintf(block->name, "SSO GROUP");
+ err = rvu_alloc_bitmap(&block->lf);
+ if (err)
+ return err;
+
+ssow:
+ /* Init SSO workslot's bitmap */
+ block = &hw->block[BLKADDR_SSOW];
+ if (!block->implemented)
+ goto tim;
+ block->lf.max = (cfg >> 56) & 0xFF;
+ block->addr = BLKADDR_SSOW;
+ block->multislot = true;
+ block->lfshift = 3;
+ block->lookup_reg = SSOW_AF_RVU_LF_HWS_CFG_DEBUG;
+ block->pf_lfcnt_reg = RVU_PRIV_PFX_SSOW_CFG;
+ block->vf_lfcnt_reg = RVU_PRIV_HWVFX_SSOW_CFG;
+ block->lfcfg_reg = SSOW_PRIV_LFX_HWS_CFG;
+ block->msixcfg_reg = SSOW_PRIV_LFX_HWS_INT_CFG;
+ block->lfreset_reg = SSOW_AF_LF_HWS_RST;
+ sprintf(block->name, "SSOWS");
+ err = rvu_alloc_bitmap(&block->lf);
+ if (err)
+ return err;
+
+tim:
+ /* Init TIM LF's bitmap */
+ block = &hw->block[BLKADDR_TIM];
+ if (!block->implemented)
+ goto cpt;
+ cfg = rvu_read64(rvu, BLKADDR_TIM, TIM_AF_CONST);
+ block->lf.max = cfg & 0xFFFF;
+ block->addr = BLKADDR_TIM;
+ block->multislot = true;
+ block->lfshift = 3;
+ block->lookup_reg = TIM_AF_RVU_LF_CFG_DEBUG;
+ block->pf_lfcnt_reg = RVU_PRIV_PFX_TIM_CFG;
+ block->vf_lfcnt_reg = RVU_PRIV_HWVFX_TIM_CFG;
+ block->lfcfg_reg = TIM_PRIV_LFX_CFG;
+ block->msixcfg_reg = TIM_PRIV_LFX_INT_CFG;
+ block->lfreset_reg = TIM_AF_LF_RST;
+ sprintf(block->name, "TIM");
+ err = rvu_alloc_bitmap(&block->lf);
+ if (err)
+ return err;
+
+cpt:
+ /* Init CPT LF's bitmap */
+ block = &hw->block[BLKADDR_CPT0];
+ if (!block->implemented)
+ return 0;
+ cfg = rvu_read64(rvu, BLKADDR_CPT0, CPT_AF_CONSTANTS0);
+ block->lf.max = cfg & 0xFF;
+ block->addr = BLKADDR_CPT0;
+ block->multislot = true;
+ block->lfshift = 3;
+ block->lookup_reg = CPT_AF_RVU_LF_CFG_DEBUG;
+ block->pf_lfcnt_reg = RVU_PRIV_PFX_CPT_CFG;
+ block->vf_lfcnt_reg = RVU_PRIV_HWVFX_CPT_CFG;
+ block->lfcfg_reg = CPT_PRIV_LFX_CFG;
+ block->msixcfg_reg = CPT_PRIV_LFX_INT_CFG;
+ block->lfreset_reg = CPT_AF_LF_RST;
+ sprintf(block->name, "CPT");
+ err = rvu_alloc_bitmap(&block->lf);
+ if (err)
+ return err;
+
+ return 0;
+}
+
static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct device *dev = &pdev->dev;
@@ -156,6 +316,10 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
rvu_reset_all_blocks(rvu);
+ err = rvu_setup_hw_resources(rvu);
+ if (err)
+ goto err_release_regions;
+
return 0;
err_release_regions:
@@ -173,6 +337,9 @@ static void rvu_remove(struct pci_dev *pdev)
{
struct rvu *rvu = pci_get_drvdata(pdev);
+ rvu_reset_all_blocks(rvu);
+ rvu_free_hw_resources(rvu);
+
pci_release_regions(pdev);
pci_disable_device(pdev);
pci_set_drvdata(pdev, NULL);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index e2c54d0..592b820 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -23,11 +23,31 @@
#define NAME_SIZE 32
+struct rsrc_bmap {
+ unsigned long *bmap; /* Pointer to resource bitmap */
+ u16 max; /* Max resource id or count */
+};
+
struct rvu_block {
+ struct rsrc_bmap lf;
+ bool multislot;
bool implemented;
+ u8 addr; /* RVU_BLOCK_ADDR_E */
+ u8 lfshift;
+ u64 lookup_reg;
+ u64 pf_lfcnt_reg;
+ u64 vf_lfcnt_reg;
+ u64 lfcfg_reg;
+ u64 msixcfg_reg;
+ u64 lfreset_reg;
+ unsigned char name[NAME_SIZE];
};
struct rvu_hwinfo {
+ u8 total_pfs; /* MAX RVU PFs HW supports */
+ u16 total_vfs; /* Max RVU VFs HW supports */
+ u16 max_vfs_per_pf; /* Max VFs that can be attached to a PF */
+
struct rvu_block block[BLK_COUNT]; /* Block info */
};
@@ -63,6 +83,7 @@ static inline u64 rvupf_read64(struct rvu *rvu, u64 offset)
* RVU
*/
+int rvu_alloc_bitmap(struct rsrc_bmap *rsrc);
int rvu_poll_reg(struct rvu *rvu, u64 block, u64 offset, u64 mask, bool zero);
#endif /* RVU_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index f4ba5a1..bbeed77 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -101,11 +101,336 @@
#define RVU_PF_MSIX_VECX_CTL(a) (0x008 | (a) << 4)
#define RVU_PF_MSIX_PBAX(a) (0xF0000 | (a) << 3)
+/* NPA block's admin function registers */
#define NPA_AF_BLK_RST (0x0000)
-#define NIX_AF_BLK_RST (0x00B0)
-#define SSO_AF_BLK_RST (0x10f8)
-#define TIM_AF_BLK_RST (0x10)
-#define CPT_AF_BLK_RST (0x46000)
+#define NPA_AF_CONST (0x0010)
+#define NPA_AF_CONST1 (0x0018)
+#define NPA_AF_LF_RST (0x0020)
+#define NPA_AF_GEN_CFG (0x0030)
+#define NPA_AF_NDC_CFG (0x0040)
+#define NPA_AF_INP_CTL (0x00D0)
+#define NPA_AF_ACTIVE_CYCLES_PC (0x00F0)
+#define NPA_AF_AVG_DELAY (0x0100)
+#define NPA_AF_GEN_INT (0x0140)
+#define NPA_AF_GEN_INT_W1S (0x0148)
+#define NPA_AF_GEN_INT_ENA_W1S (0x0150)
+#define NPA_AF_GEN_INT_ENA_W1C (0x0158)
+#define NPA_AF_RVU_INT (0x0160)
+#define NPA_AF_RVU_INT_W1S (0x0168)
+#define NPA_AF_RVU_INT_ENA_W1S (0x0170)
+#define NPA_AF_RVU_INT_ENA_W1C (0x0178)
+#define NPA_AF_ERR_INT (0x0180)
+#define NPA_AF_ERR_INT_W1S (0x0188)
+#define NPA_AF_ERR_INT_ENA_W1S (0x0190)
+#define NPA_AF_ERR_INT_ENA_W1C (0x0198)
+#define NPA_AF_RAS (0x01A0)
+#define NPA_AF_RAS_W1S (0x01A8)
+#define NPA_AF_RAS_ENA_W1S (0x01B0)
+#define NPA_AF_RAS_ENA_W1C (0x01B8)
+#define NPA_AF_BP_TEST (0x0200)
+#define NPA_AF_ECO (0x0300)
+#define NPA_AF_AQ_CFG (0x0600)
+#define NPA_AF_AQ_BASE (0x0610)
+#define NPA_AF_AQ_STATUS (0x0620)
+#define NPA_AF_AQ_DOOR (0x0630)
+#define NPA_AF_AQ_DONE_WAIT (0x0640)
+#define NPA_AF_AQ_DONE (0x0650)
+#define NPA_AF_AQ_DONE_ACK (0x0660)
+#define NPA_AF_AQ_DONE_INT (0x0680)
+#define NPA_AF_AQ_DONE_INT_W1S (0x0688)
+#define NPA_AF_AQ_DONE_ENA_W1S (0x0690)
+#define NPA_AF_AQ_DONE_ENA_W1C (0x0698)
+#define NPA_AF_LFX_AURAS_CFG(a) (0x4000 | (a) << 18)
+#define NPA_AF_LFX_LOC_AURAS_BASE(a) (0x4010 | (a) << 18)
+#define NPA_AF_LFX_QINTS_CFG(a) (0x4100 | (a) << 18)
+#define NPA_AF_LFX_QINTS_BASE(a) (0x4110 | (a) << 18)
+#define NPA_PRIV_AF_INT_CFG (0x10000)
+#define NPA_PRIV_LFX_CFG (0x10010)
+#define NPA_PRIV_LFX_INT_CFG (0x10020)
+#define NPA_AF_RVU_LF_CFG_DEBUG (0x10030)
+
+/* NIX block's admin function registers */
+#define NIX_AF_CFG (0x0000)
+#define NIX_AF_STATUS (0x0010)
+#define NIX_AF_NDC_CFG (0x0018)
+#define NIX_AF_CONST (0x0020)
+#define NIX_AF_CONST1 (0x0028)
+#define NIX_AF_CONST2 (0x0030)
+#define NIX_AF_CONST3 (0x0038)
+#define NIX_AF_SQ_CONST (0x0040)
+#define NIX_AF_CQ_CONST (0x0048)
+#define NIX_AF_RQ_CONST (0x0050)
+#define NIX_AF_PSE_CONST (0x0060)
+#define NIX_AF_TL1_CONST (0x0070)
+#define NIX_AF_TL2_CONST (0x0078)
+#define NIX_AF_TL3_CONST (0x0080)
+#define NIX_AF_TL4_CONST (0x0088)
+#define NIX_AF_MDQ_CONST (0x0090)
+#define NIX_AF_MC_MIRROR_CONST (0x0098)
+#define NIX_AF_LSO_CFG (0x00A8)
+#define NIX_AF_BLK_RST (0x00B0)
+#define NIX_AF_TX_TSTMP_CFG (0x00C0)
+#define NIX_AF_RX_CFG (0x00D0)
+#define NIX_AF_AVG_DELAY (0x00E0)
+#define NIX_AF_CINT_DELAY (0x00F0)
+#define NIX_AF_RX_MCAST_BASE (0x0100)
+#define NIX_AF_RX_MCAST_CFG (0x0110)
+#define NIX_AF_RX_MCAST_BUF_BASE (0x0120)
+#define NIX_AF_RX_MCAST_BUF_CFG (0x0130)
+#define NIX_AF_RX_MIRROR_BUF_BASE (0x0140)
+#define NIX_AF_RX_MIRROR_BUF_CFG (0x0148)
+#define NIX_AF_LF_RST (0x0150)
+#define NIX_AF_GEN_INT (0x0160)
+#define NIX_AF_GEN_INT_W1S (0x0168)
+#define NIX_AF_GEN_INT_ENA_W1S (0x0170)
+#define NIX_AF_GEN_INT_ENA_W1C (0x0178)
+#define NIX_AF_ERR_INT (0x0180)
+#define NIX_AF_ERR_INT_W1S (0x0188)
+#define NIX_AF_ERR_INT_ENA_W1S (0x0190)
+#define NIX_AF_ERR_INT_ENA_W1C (0x0198)
+#define NIX_AF_RAS (0x01A0)
+#define NIX_AF_RAS_W1S (0x01A8)
+#define NIX_AF_RAS_ENA_W1S (0x01B0)
+#define NIX_AF_RAS_ENA_W1C (0x01B8)
+#define NIX_AF_RVU_INT (0x01C0)
+#define NIX_AF_RVU_INT_W1S (0x01C8)
+#define NIX_AF_RVU_INT_ENA_W1S (0x01D0)
+#define NIX_AF_RVU_INT_ENA_W1C (0x01D8)
+#define NIX_AF_TCP_TIMER (0x01E0)
+#define NIX_AF_RX_WQE_TAG_CTL (0x01F0)
+#define NIX_AF_RX_DEF_OL2 (0x0200)
+#define NIX_AF_RX_DEF_OIP4 (0x0210)
+#define NIX_AF_RX_DEF_IIP4 (0x0220)
+#define NIX_AF_RX_DEF_OIP6 (0x0230)
+#define NIX_AF_RX_DEF_IIP6 (0x0240)
+#define NIX_AF_RX_DEF_OTCP (0x0250)
+#define NIX_AF_RX_DEF_ITCP (0x0260)
+#define NIX_AF_RX_DEF_OUDP (0x0270)
+#define NIX_AF_RX_DEF_IUDP (0x0280)
+#define NIX_AF_RX_DEF_OSCTP (0x0290)
+#define NIX_AF_RX_DEF_ISCTP (0x02A0)
+#define NIX_AF_RX_DEF_IPSECX (0x02B0)
+#define NIX_AF_RX_IPSEC_GEN_CFG (0x0300)
+#define NIX_AF_RX_CPTX_INST_ADDR (0x0310)
+#define NIX_AF_NDC_TX_SYNC (0x03F0)
+#define NIX_AF_AQ_CFG (0x0400)
+#define NIX_AF_AQ_BASE (0x0410)
+#define NIX_AF_AQ_STATUS (0x0420)
+#define NIX_AF_AQ_DOOR (0x0430)
+#define NIX_AF_AQ_DONE_WAIT (0x0440)
+#define NIX_AF_AQ_DONE (0x0450)
+#define NIX_AF_AQ_DONE_ACK (0x0460)
+#define NIX_AF_AQ_DONE_TIMER (0x0470)
+#define NIX_AF_AQ_DONE_INT (0x0480)
+#define NIX_AF_AQ_DONE_INT_W1S (0x0488)
+#define NIX_AF_AQ_DONE_ENA_W1S (0x0490)
+#define NIX_AF_AQ_DONE_ENA_W1C (0x0498)
+#define NIX_AF_RX_LINKX_SLX_SPKT_CNT (0x0500)
+#define NIX_AF_RX_LINKX_SLX_SXQE_CNT (0x0510)
+#define NIX_AF_RX_MCAST_JOBSX_SW_CNT (0x0520)
+#define NIX_AF_RX_MIRROR_JOBSX_SW_CNT (0x0530)
+#define NIX_AF_RX_LINKX_CFG(a) (0x0540 | (a) << 16)
+#define NIX_AF_RX_SW_SYNC (0x0550)
+#define NIX_AF_RX_SW_SYNC_DONE (0x0560)
+#define NIX_AF_SEB_ECO (0x0600)
+#define NIX_AF_SEB_TEST_BP (0x0610)
+#define NIX_AF_NORM_TX_FIFO_STATUS (0x0620)
+#define NIX_AF_EXPR_TX_FIFO_STATUS (0x0630)
+#define NIX_AF_SDP_TX_FIFO_STATUS (0x0640)
+#define NIX_AF_TX_NPC_CAPTURE_CONFIG (0x0660)
+#define NIX_AF_TX_NPC_CAPTURE_INFO (0x0670)
+
+#define NIX_AF_DEBUG_NPC_RESP_DATAX(a) (0x680 | (a) << 3)
+#define NIX_AF_SMQX_CFG(a) (0x700 | (a) << 16)
+#define NIX_AF_PSE_CHANNEL_LEVEL (0x800)
+#define NIX_AF_PSE_SHAPER_CFG (0x810)
+#define NIX_AF_TX_EXPR_CREDIT (0x830)
+#define NIX_AF_MARK_FORMATX_CTL(a) (0x900 | (a) << 18)
+#define NIX_AF_TX_LINKX_NORM_CREDIT(a) (0xA00 | (a) << 16)
+#define NIX_AF_TX_LINKX_EXPR_CREDIT(a) (0xA10 | (a) << 16)
+#define NIX_AF_TX_LINKX_SW_XOFF(a) (0xA20 | (a) << 16)
+#define NIX_AF_TX_LINKX_HW_XOFF(a) (0xA30 | (a) << 16)
+#define NIX_AF_SDP_LINK_CREDIT (0xa40)
+#define NIX_AF_SDP_SW_XOFFX(a) (0xA60 | (a) << 3)
+#define NIX_AF_SDP_HW_XOFFX(a) (0xAC0 | (a) << 3)
+#define NIX_AF_TL4X_BP_STATUS(a) (0xB00 | (a) << 16)
+#define NIX_AF_TL4X_SDP_LINK_CFG(a) (0xB10 | (a) << 16)
+#define NIX_AF_TL1X_SCHEDULE(a) (0xC00 | (a) << 16)
+#define NIX_AF_TL1X_SHAPE(a) (0xC10 | (a) << 16)
+#define NIX_AF_TL1X_CIR(a) (0xC20 | (a) << 16)
+#define NIX_AF_TL1X_SHAPE_STATE(a) (0xC50 | (a) << 16)
+#define NIX_AF_TL1X_SW_XOFF(a) (0xC70 | (a) << 16)
+#define NIX_AF_TL1X_TOPOLOGY(a) (0xC80 | (a) << 16)
+#define NIX_AF_TL1X_GREEN(a) (0xC90 | (a) << 16)
+#define NIX_AF_TL1X_YELLOW(a) (0xCA0 | (a) << 16)
+#define NIX_AF_TL1X_RED(a) (0xCB0 | (a) << 16)
+#define NIX_AF_TL1X_MD_DEBUG0(a) (0xCC0 | (a) << 16)
+#define NIX_AF_TL1X_MD_DEBUG1(a) (0xCC8 | (a) << 16)
+#define NIX_AF_TL1X_MD_DEBUG2(a) (0xCD0 | (a) << 16)
+#define NIX_AF_TL1X_MD_DEBUG3(a) (0xCD8 | (a) << 16)
+#define NIX_AF_TL1A_DEBUG (0xce0)
+#define NIX_AF_TL1B_DEBUG (0xcf0)
+#define NIX_AF_TL1_DEBUG_GREEN (0xd00)
+#define NIX_AF_TL1_DEBUG_NODE (0xd10)
+#define NIX_AF_TL1X_DROPPED_PACKETS(a) (0xD20 | (a) << 16)
+#define NIX_AF_TL1X_DROPPED_BYTES(a) (0xD30 | (a) << 16)
+#define NIX_AF_TL1X_RED_PACKETS(a) (0xD40 | (a) << 16)
+#define NIX_AF_TL1X_RED_BYTES(a) (0xD50 | (a) << 16)
+#define NIX_AF_TL1X_YELLOW_PACKETS(a) (0xD60 | (a) << 16)
+#define NIX_AF_TL1X_YELLOW_BYTES(a) (0xD70 | (a) << 16)
+#define NIX_AF_TL1X_GREEN_PACKETS(a) (0xD80 | (a) << 16)
+#define NIX_AF_TL1X_GREEN_BYTES(a) (0xD90 | (a) << 16)
+#define NIX_AF_TL2X_SCHEDULE(a) (0xE00 | (a) << 16)
+#define NIX_AF_TL2X_SHAPE(a) (0xE10 | (a) << 16)
+#define NIX_AF_TL2X_CIR(a) (0xE20 | (a) << 16)
+#define NIX_AF_TL2X_PIR(a) (0xE30 | (a) << 16)
+#define NIX_AF_TL2X_SCHED_STATE(a) (0xE40 | (a) << 16)
+#define NIX_AF_TL2X_SHAPE_STATE(a) (0xE50 | (a) << 16)
+#define NIX_AF_TL2X_POINTERS(a) (0xE60 | (a) << 16)
+#define NIX_AF_TL2X_SW_XOFF(a) (0xE70 | (a) << 16)
+#define NIX_AF_TL2X_TOPOLOGY(a) (0xE80 | (a) << 16)
+#define NIX_AF_TL2X_PARENT(a) (0xE88 | (a) << 16)
+#define NIX_AF_TL2X_GREEN(a) (0xE90 | (a) << 16)
+#define NIX_AF_TL2X_YELLOW(a) (0xEA0 | (a) << 16)
+#define NIX_AF_TL2X_RED(a) (0xEB0 | (a) << 16)
+#define NIX_AF_TL2X_MD_DEBUG0(a) (0xEC0 | (a) << 16)
+#define NIX_AF_TL2X_MD_DEBUG1(a) (0xEC8 | (a) << 16)
+#define NIX_AF_TL2X_MD_DEBUG2(a) (0xED0 | (a) << 16)
+#define NIX_AF_TL2X_MD_DEBUG3(a) (0xED8 | (a) << 16)
+#define NIX_AF_TL2A_DEBUG (0xee0)
+#define NIX_AF_TL2B_DEBUG (0xef0)
+#define NIX_AF_TL3X_SCHEDULE(a) (0x1000 | (a) << 16)
+#define NIX_AF_TL3X_SHAPE(a) (0x1010 | (a) << 16)
+#define NIX_AF_TL3X_CIR(a) (0x1020 | (a) << 16)
+#define NIX_AF_TL3X_PIR(a) (0x1030 | (a) << 16)
+#define NIX_AF_TL3X_SCHED_STATE(a) (0x1040 | (a) << 16)
+#define NIX_AF_TL3X_SHAPE_STATE(a) (0x1050 | (a) << 16)
+#define NIX_AF_TL3X_POINTERS(a) (0x1060 | (a) << 16)
+#define NIX_AF_TL3X_SW_XOFF(a) (0x1070 | (a) << 16)
+#define NIX_AF_TL3X_TOPOLOGY(a) (0x1080 | (a) << 16)
+#define NIX_AF_TL3X_PARENT(a) (0x1088 | (a) << 16)
+#define NIX_AF_TL3X_GREEN(a) (0x1090 | (a) << 16)
+#define NIX_AF_TL3X_YELLOW(a) (0x10A0 | (a) << 16)
+#define NIX_AF_TL3X_RED(a) (0x10B0 | (a) << 16)
+#define NIX_AF_TL3X_MD_DEBUG0(a) (0x10C0 | (a) << 16)
+#define NIX_AF_TL3X_MD_DEBUG1(a) (0x10C8 | (a) << 16)
+#define NIX_AF_TL3X_MD_DEBUG2(a) (0x10D0 | (a) << 16)
+#define NIX_AF_TL3X_MD_DEBUG3(a) (0x10D8 | (a) << 16)
+#define NIX_AF_TL3A_DEBUG (0x10e0)
+#define NIX_AF_TL3B_DEBUG (0x10f0)
+#define NIX_AF_TL4X_SCHEDULE(a) (0x1200 | (a) << 16)
+#define NIX_AF_TL4X_SHAPE(a) (0x1210 | (a) << 16)
+#define NIX_AF_TL4X_CIR(a) (0x1220 | (a) << 16)
+#define NIX_AF_TL4X_PIR(a) (0x1230 | (a) << 16)
+#define NIX_AF_TL4X_SCHED_STATE(a) (0x1240 | (a) << 16)
+#define NIX_AF_TL4X_SHAPE_STATE(a) (0x1250 | (a) << 16)
+#define NIX_AF_TL4X_POINTERS(a) (0x1260 | (a) << 16)
+#define NIX_AF_TL4X_SW_XOFF(a) (0x1270 | (a) << 16)
+#define NIX_AF_TL4X_TOPOLOGY(a) (0x1280 | (a) << 16)
+#define NIX_AF_TL4X_PARENT(a) (0x1288 | (a) << 16)
+#define NIX_AF_TL4X_GREEN(a) (0x1290 | (a) << 16)
+#define NIX_AF_TL4X_YELLOW(a) (0x12A0 | (a) << 16)
+#define NIX_AF_TL4X_RED(a) (0x12B0 | (a) << 16)
+#define NIX_AF_TL4X_MD_DEBUG0(a) (0x12C0 | (a) << 16)
+#define NIX_AF_TL4X_MD_DEBUG1(a) (0x12C8 | (a) << 16)
+#define NIX_AF_TL4X_MD_DEBUG2(a) (0x12D0 | (a) << 16)
+#define NIX_AF_TL4X_MD_DEBUG3(a) (0x12D8 | (a) << 16)
+#define NIX_AF_TL4A_DEBUG (0x12e0)
+#define NIX_AF_TL4B_DEBUG (0x12f0)
+#define NIX_AF_MDQX_SCHEDULE(a) (0x1400 | (a) << 16)
+#define NIX_AF_MDQX_SHAPE(a) (0x1410 | (a) << 16)
+#define NIX_AF_MDQX_CIR(a) (0x1420 | (a) << 16)
+#define NIX_AF_MDQX_PIR(a) (0x1430 | (a) << 16)
+#define NIX_AF_MDQX_SCHED_STATE(a) (0x1440 | (a) << 16)
+#define NIX_AF_MDQX_SHAPE_STATE(a) (0x1450 | (a) << 16)
+#define NIX_AF_MDQX_POINTERS(a) (0x1460 | (a) << 16)
+#define NIX_AF_MDQX_SW_XOFF(a) (0x1470 | (a) << 16)
+#define NIX_AF_MDQX_PARENT(a) (0x1480 | (a) << 16)
+#define NIX_AF_MDQX_MD_DEBUG(a) (0x14C0 | (a) << 16)
+#define NIX_AF_MDQX_PTR_FIFO(a) (0x14D0 | (a) << 16)
+#define NIX_AF_MDQA_DEBUG (0x14e0)
+#define NIX_AF_MDQB_DEBUG (0x14f0)
+#define NIX_AF_TL3_TL2X_CFG(a) (0x1600 | (a) << 18)
+#define NIX_AF_TL3_TL2X_BP_STATUS(a) (0x1610 | (a) << 16)
+#define NIX_AF_TL3_TL2X_LINKX_CFG(a, b) (0x1700 | (a) << 16 | (b) << 3)
+#define NIX_AF_RX_FLOW_KEY_ALGX_FIELDX(a, b) (0x1800 | (a) << 18 | (b) << 3)
+#define NIX_AF_TX_MCASTX(a) (0x1900 | (a) << 15)
+#define NIX_AF_TX_VTAG_DEFX_CTL(a) (0x1A00 | (a) << 16)
+#define NIX_AF_TX_VTAG_DEFX_DATA(a) (0x1A10 | (a) << 16)
+#define NIX_AF_RX_BPIDX_STATUS(a) (0x1A20 | (a) << 17)
+#define NIX_AF_RX_CHANX_CFG(a) (0x1A30 | (a) << 15)
+#define NIX_AF_CINT_TIMERX(a) (0x1A40 | (a) << 18)
+#define NIX_AF_LSO_FORMATX_FIELDX(a, b) (0x1B00 | (a) << 16 | (b) << 3)
+#define NIX_AF_LFX_CFG(a) (0x4000 | (a) << 17)
+#define NIX_AF_LFX_SQS_CFG(a) (0x4020 | (a) << 17)
+#define NIX_AF_LFX_TX_CFG2(a) (0x4028 | (a) << 17)
+#define NIX_AF_LFX_SQS_BASE(a) (0x4030 | (a) << 17)
+#define NIX_AF_LFX_RQS_CFG(a) (0x4040 | (a) << 17)
+#define NIX_AF_LFX_RQS_BASE(a) (0x4050 | (a) << 17)
+#define NIX_AF_LFX_CQS_CFG(a) (0x4060 | (a) << 17)
+#define NIX_AF_LFX_CQS_BASE(a) (0x4070 | (a) << 17)
+#define NIX_AF_LFX_TX_CFG(a) (0x4080 | (a) << 17)
+#define NIX_AF_LFX_TX_PARSE_CFG(a) (0x4090 | (a) << 17)
+#define NIX_AF_LFX_RX_CFG(a) (0x40A0 | (a) << 17)
+#define NIX_AF_LFX_RSS_CFG(a) (0x40C0 | (a) << 17)
+#define NIX_AF_LFX_RSS_BASE(a) (0x40D0 | (a) << 17)
+#define NIX_AF_LFX_QINTS_CFG(a) (0x4100 | (a) << 17)
+#define NIX_AF_LFX_QINTS_BASE(a) (0x4110 | (a) << 17)
+#define NIX_AF_LFX_CINTS_CFG(a) (0x4120 | (a) << 17)
+#define NIX_AF_LFX_CINTS_BASE(a) (0x4130 | (a) << 17)
+#define NIX_AF_LFX_RX_IPSEC_CFG0(a) (0x4140 | (a) << 17)
+#define NIX_AF_LFX_RX_IPSEC_CFG1(a) (0x4148 | (a) << 17)
+#define NIX_AF_LFX_RX_IPSEC_DYNO_CFG(a) (0x4150 | (a) << 17)
+#define NIX_AF_LFX_RX_IPSEC_DYNO_BASE(a) (0x4158 | (a) << 17)
+#define NIX_AF_LFX_RX_IPSEC_SA_BASE(a) (0x4170 | (a) << 17)
+#define NIX_AF_LFX_TX_STATUS(a) (0x4180 | (a) << 17)
+#define NIX_AF_LFX_RX_VTAG_TYPEX(a, b) (0x4200 | (a) << 17 | (b) << 3)
+#define NIX_AF_LFX_LOCKX(a, b) (0x4300 | (a) << 17 | (b) << 3)
+#define NIX_AF_LFX_TX_STATX(a, b) (0x4400 | (a) << 17 | (b) << 3)
+#define NIX_AF_LFX_RX_STATX(a, b) (0x4500 | (a) << 17 | (b) << 3)
+#define NIX_AF_LFX_RSS_GRPX(a, b) (0x4600 | (a) << 17 | (b) << 3)
+#define NIX_AF_RX_NPC_MC_RCV (0x4700)
+#define NIX_AF_RX_NPC_MC_DROP (0x4710)
+#define NIX_AF_RX_NPC_MIRROR_RCV (0x4720)
+#define NIX_AF_RX_NPC_MIRROR_DROP (0x4730)
+#define NIX_AF_RX_ACTIVE_CYCLES_PCX(a) (0x4800 | (a) << 16)
+
+#define NIX_PRIV_AF_INT_CFG (0x8000000)
+#define NIX_PRIV_LFX_CFG (0x8000010)
+#define NIX_PRIV_LFX_INT_CFG (0x8000020)
+#define NIX_AF_RVU_LF_CFG_DEBUG (0x8000030)
+
+/* SSO */
+#define SSO_AF_CONST (0x1000)
+#define SSO_AF_CONST1 (0x1008)
+#define SSO_AF_BLK_RST (0x10f8)
+#define SSO_AF_LF_HWGRP_RST (0x10e0)
+#define SSO_AF_RVU_LF_CFG_DEBUG (0x3800)
+#define SSO_PRIV_LFX_HWGRP_CFG (0x10000)
+#define SSO_PRIV_LFX_HWGRP_INT_CFG (0x20000)
+
+/* SSOW */
+#define SSOW_AF_RVU_LF_HWS_CFG_DEBUG (0x0010)
+#define SSOW_AF_LF_HWS_RST (0x0030)
+#define SSOW_PRIV_LFX_HWS_CFG (0x1000)
+#define SSOW_PRIV_LFX_HWS_INT_CFG (0x2000)
+
+/* TIM */
+#define TIM_AF_CONST (0x90)
+#define TIM_PRIV_LFX_CFG (0x20000)
+#define TIM_PRIV_LFX_INT_CFG (0x24000)
+#define TIM_AF_RVU_LF_CFG_DEBUG (0x30000)
+#define TIM_AF_BLK_RST (0x10)
+#define TIM_AF_LF_RST (0x20)
+
+/* CPT */
+#define CPT_AF_CONSTANTS0 (0x0000)
+#define CPT_PRIV_LFX_CFG (0x41000)
+#define CPT_PRIV_LFX_INT_CFG (0x43000)
+#define CPT_AF_RVU_LF_CFG_DEBUG (0x45000)
+#define CPT_AF_LF_RST (0x44000)
+#define CPT_AF_BLK_RST (0x46000)
+
#define NDC_AF_BLK_RST (0x002F0)
#define NPC_AF_BLK_RST (0x00040)
--
2.7.4
^ permalink raw reply related
* [PATCH 02/15] octeontx2-af: Reset all RVU blocks
From: sunil.kovvuri @ 2018-09-28 6:07 UTC (permalink / raw)
To: netdev, davem; +Cc: arnd, linux-soc, Sunil Goutham
In-Reply-To: <1538114872-10820-1-git-send-email-sunil.kovvuri@gmail.com>
From: Sunil Goutham <sgoutham@marvell.com>
Go through all BLKADDRs and check which ones are implemented
on this silicon and do a HW reset of each implemented block.
Also added all RVU AF and PF register offsets.
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
---
drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 78 ++++++++++++++
drivers/net/ethernet/marvell/octeontx2/af/rvu.h | 37 +++++++
.../net/ethernet/marvell/octeontx2/af/rvu_reg.h | 112 +++++++++++++++++++++
.../net/ethernet/marvell/octeontx2/af/rvu_struct.h | 34 +++++++
4 files changed, 261 insertions(+)
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 5af4da6..d40fabf 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -16,6 +16,7 @@
#include <linux/sysfs.h>
#include "rvu.h"
+#include "rvu_reg.h"
#define DRV_NAME "octeontx2-af"
#define DRV_STRING "Marvell OcteonTX2 RVU Admin Function Driver"
@@ -33,6 +34,70 @@ MODULE_LICENSE("GPL v2");
MODULE_VERSION(DRV_VERSION);
MODULE_DEVICE_TABLE(pci, rvu_id_table);
+/* Poll a RVU block's register 'offset', for a 'zero'
+ * or 'nonzero' at bits specified by 'mask'
+ */
+int rvu_poll_reg(struct rvu *rvu, u64 block, u64 offset, u64 mask, bool zero)
+{
+ void __iomem *reg;
+ int timeout = 100;
+ u64 reg_val;
+
+ reg = rvu->afreg_base + ((block << 28) | offset);
+ while (timeout) {
+ reg_val = readq(reg);
+ if (zero && !(reg_val & mask))
+ return 0;
+ if (!zero && (reg_val & mask))
+ return 0;
+ udelay(1);
+ cpu_relax();
+ timeout--;
+ }
+ return -EBUSY;
+}
+
+static void rvu_check_block_implemented(struct rvu *rvu)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+ struct rvu_block *block;
+ int blkid;
+ u64 cfg;
+
+ /* For each block check if 'implemented' bit is set */
+ for (blkid = 0; blkid < BLK_COUNT; blkid++) {
+ block = &hw->block[blkid];
+ cfg = rvupf_read64(rvu, RVU_PF_BLOCK_ADDRX_DISC(blkid));
+ if (cfg & BIT_ULL(11))
+ block->implemented = true;
+ }
+}
+
+static void rvu_block_reset(struct rvu *rvu, int blkaddr, u64 rst_reg)
+{
+ struct rvu_block *block = &rvu->hw->block[blkaddr];
+
+ if (!block->implemented)
+ return;
+
+ rvu_write64(rvu, blkaddr, rst_reg, BIT_ULL(0));
+ rvu_poll_reg(rvu, blkaddr, rst_reg, BIT_ULL(63), true);
+}
+
+static void rvu_reset_all_blocks(struct rvu *rvu)
+{
+ /* Do a HW reset of all RVU blocks */
+ rvu_block_reset(rvu, BLKADDR_NPA, NPA_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_NIX0, NIX_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_NPC, NPC_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_SSO, SSO_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_TIM, TIM_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_CPT0, CPT_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_NDC0, NDC_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_NDC1, NDC_AF_BLK_RST);
+ rvu_block_reset(rvu, BLKADDR_NDC2, NDC_AF_BLK_RST);
+}
+
static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct device *dev = &pdev->dev;
@@ -43,6 +108,12 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (!rvu)
return -ENOMEM;
+ rvu->hw = devm_kzalloc(dev, sizeof(struct rvu_hwinfo), GFP_KERNEL);
+ if (!rvu->hw) {
+ devm_kfree(dev, rvu);
+ return -ENOMEM;
+ }
+
pci_set_drvdata(pdev, rvu);
rvu->pdev = pdev;
rvu->dev = &pdev->dev;
@@ -80,6 +151,11 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
goto err_release_regions;
}
+ /* Check which blocks the HW supports */
+ rvu_check_block_implemented(rvu);
+
+ rvu_reset_all_blocks(rvu);
+
return 0;
err_release_regions:
@@ -88,6 +164,7 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
pci_disable_device(pdev);
err_freemem:
pci_set_drvdata(pdev, NULL);
+ devm_kfree(&pdev->dev, rvu->hw);
devm_kfree(dev, rvu);
return err;
}
@@ -100,6 +177,7 @@ static void rvu_remove(struct pci_dev *pdev)
pci_disable_device(pdev);
pci_set_drvdata(pdev, NULL);
+ devm_kfree(&pdev->dev, rvu->hw);
devm_kfree(&pdev->dev, rvu);
}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 4a4b0ad..e2c54d0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -11,6 +11,8 @@
#ifndef RVU_H
#define RVU_H
+#include "rvu_struct.h"
+
/* PCI device IDs */
#define PCI_DEVID_OCTEONTX2_RVU_AF 0xA065
@@ -21,11 +23,46 @@
#define NAME_SIZE 32
+struct rvu_block {
+ bool implemented;
+};
+
+struct rvu_hwinfo {
+ struct rvu_block block[BLK_COUNT]; /* Block info */
+};
+
struct rvu {
void __iomem *afreg_base;
void __iomem *pfreg_base;
struct pci_dev *pdev;
struct device *dev;
+ struct rvu_hwinfo *hw;
};
+static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
+{
+ writeq(val, rvu->afreg_base + ((block << 28) | offset));
+}
+
+static inline u64 rvu_read64(struct rvu *rvu, u64 block, u64 offset)
+{
+ return readq(rvu->afreg_base + ((block << 28) | offset));
+}
+
+static inline void rvupf_write64(struct rvu *rvu, u64 offset, u64 val)
+{
+ writeq(val, rvu->pfreg_base + offset);
+}
+
+static inline u64 rvupf_read64(struct rvu *rvu, u64 offset)
+{
+ return readq(rvu->pfreg_base + offset);
+}
+
+/* Function Prototypes
+ * RVU
+ */
+
+int rvu_poll_reg(struct rvu *rvu, u64 block, u64 offset, u64 mask, bool zero);
+
#endif /* RVU_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
new file mode 100644
index 0000000..f4ba5a1
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Marvell OcteonTx2 RVU Admin Function driver
+ *
+ * Copyright (C) 2018 Marvell International Ltd.
+ *
+ * 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.
+ */
+
+#ifndef RVU_REG_H
+#define RVU_REG_H
+
+/* Admin function registers */
+#define RVU_AF_MSIXTR_BASE (0x10)
+#define RVU_AF_ECO (0x20)
+#define RVU_AF_BLK_RST (0x30)
+#define RVU_AF_PF_BAR4_ADDR (0x40)
+#define RVU_AF_RAS (0x100)
+#define RVU_AF_RAS_W1S (0x108)
+#define RVU_AF_RAS_ENA_W1S (0x110)
+#define RVU_AF_RAS_ENA_W1C (0x118)
+#define RVU_AF_GEN_INT (0x120)
+#define RVU_AF_GEN_INT_W1S (0x128)
+#define RVU_AF_GEN_INT_ENA_W1S (0x130)
+#define RVU_AF_GEN_INT_ENA_W1C (0x138)
+#define RVU_AF_AFPF_MBOX0 (0x02000)
+#define RVU_AF_AFPF_MBOX1 (0x02008)
+#define RVU_AF_AFPFX_MBOXX(a, b) (0x2000 | (a) << 4 | (b) << 3)
+#define RVU_AF_PFME_STATUS (0x2800)
+#define RVU_AF_PFTRPEND (0x2810)
+#define RVU_AF_PFTRPEND_W1S (0x2820)
+#define RVU_AF_PF_RST (0x2840)
+#define RVU_AF_HWVF_RST (0x2850)
+#define RVU_AF_PFAF_MBOX_INT (0x2880)
+#define RVU_AF_PFAF_MBOX_INT_W1S (0x2888)
+#define RVU_AF_PFAF_MBOX_INT_ENA_W1S (0x2890)
+#define RVU_AF_PFAF_MBOX_INT_ENA_W1C (0x2898)
+#define RVU_AF_PFFLR_INT (0x28a0)
+#define RVU_AF_PFFLR_INT_W1S (0x28a8)
+#define RVU_AF_PFFLR_INT_ENA_W1S (0x28b0)
+#define RVU_AF_PFFLR_INT_ENA_W1C (0x28b8)
+#define RVU_AF_PFME_INT (0x28c0)
+#define RVU_AF_PFME_INT_W1S (0x28c8)
+#define RVU_AF_PFME_INT_ENA_W1S (0x28d0)
+#define RVU_AF_PFME_INT_ENA_W1C (0x28d8)
+
+/* Admin function's privileged PF/VF registers */
+#define RVU_PRIV_CONST (0x8000000)
+#define RVU_PRIV_GEN_CFG (0x8000010)
+#define RVU_PRIV_CLK_CFG (0x8000020)
+#define RVU_PRIV_ACTIVE_PC (0x8000030)
+#define RVU_PRIV_PFX_CFG(a) (0x8000100 | (a) << 16)
+#define RVU_PRIV_PFX_MSIX_CFG(a) (0x8000110 | (a) << 16)
+#define RVU_PRIV_PFX_ID_CFG(a) (0x8000120 | (a) << 16)
+#define RVU_PRIV_PFX_INT_CFG(a) (0x8000200 | (a) << 16)
+#define RVU_PRIV_PFX_NIX_CFG (0x8000300)
+#define RVU_PRIV_PFX_NPA_CFG (0x8000310)
+#define RVU_PRIV_PFX_SSO_CFG (0x8000320)
+#define RVU_PRIV_PFX_SSOW_CFG (0x8000330)
+#define RVU_PRIV_PFX_TIM_CFG (0x8000340)
+#define RVU_PRIV_PFX_CPT_CFG (0x8000350)
+#define RVU_PRIV_BLOCK_TYPEX_REV(a) (0x8000400 | (a) << 3)
+#define RVU_PRIV_HWVFX_INT_CFG(a) (0x8001280 | (a) << 16)
+#define RVU_PRIV_HWVFX_NIX_CFG (0x8001300)
+#define RVU_PRIV_HWVFX_NPA_CFG (0x8001310)
+#define RVU_PRIV_HWVFX_SSO_CFG (0x8001320)
+#define RVU_PRIV_HWVFX_SSOW_CFG (0x8001330)
+#define RVU_PRIV_HWVFX_TIM_CFG (0x8001340)
+#define RVU_PRIV_HWVFX_CPT_CFG (0x8001350)
+
+/* RVU PF registers */
+#define RVU_PF_VFX_PFVF_MBOX0 (0x00000)
+#define RVU_PF_VFX_PFVF_MBOX1 (0x00008)
+#define RVU_PF_VFX_PFVF_MBOXX(a, b) (0x0 | (a) << 12 | (b) << 3)
+#define RVU_PF_VF_BAR4_ADDR (0x10)
+#define RVU_PF_BLOCK_ADDRX_DISC(a) (0x200 | (a) << 3)
+#define RVU_PF_VFME_STATUSX(a) (0x800 | (a) << 3)
+#define RVU_PF_VFTRPENDX(a) (0x820 | (a) << 3)
+#define RVU_PF_VFTRPEND_W1SX(a) (0x840 | (a) << 3)
+#define RVU_PF_VFPF_MBOX_INTX(a) (0x880 | (a) << 3)
+#define RVU_PF_VFPF_MBOX_INT_W1SX(a) (0x8A0 | (a) << 3)
+#define RVU_PF_VFPF_MBOX_INT_ENA_W1SX(a) (0x8C0 | (a) << 3)
+#define RVU_PF_VFPF_MBOX_INT_ENA_W1CX(a) (0x8E0 | (a) << 3)
+#define RVU_PF_VFFLR_INTX(a) (0x900 | (a) << 3)
+#define RVU_PF_VFFLR_INT_W1SX(a) (0x920 | (a) << 3)
+#define RVU_PF_VFFLR_INT_ENA_W1SX(a) (0x940 | (a) << 3)
+#define RVU_PF_VFFLR_INT_ENA_W1CX(a) (0x960 | (a) << 3)
+#define RVU_PF_VFME_INTX(a) (0x980 | (a) << 3)
+#define RVU_PF_VFME_INT_W1SX(a) (0x9A0 | (a) << 3)
+#define RVU_PF_VFME_INT_ENA_W1SX(a) (0x9C0 | (a) << 3)
+#define RVU_PF_VFME_INT_ENA_W1CX(a) (0x9E0 | (a) << 3)
+#define RVU_PF_PFAF_MBOX0 (0xC00)
+#define RVU_PF_PFAF_MBOX1 (0xC08)
+#define RVU_PF_PFAF_MBOXX(a) (0xC00 | (a) << 3)
+#define RVU_PF_INT (0xc20)
+#define RVU_PF_INT_W1S (0xc28)
+#define RVU_PF_INT_ENA_W1S (0xc30)
+#define RVU_PF_INT_ENA_W1C (0xc38)
+#define RVU_PF_MSIX_VECX_ADDR(a) (0x000 | (a) << 4)
+#define RVU_PF_MSIX_VECX_CTL(a) (0x008 | (a) << 4)
+#define RVU_PF_MSIX_PBAX(a) (0xF0000 | (a) << 3)
+
+#define NPA_AF_BLK_RST (0x0000)
+#define NIX_AF_BLK_RST (0x00B0)
+#define SSO_AF_BLK_RST (0x10f8)
+#define TIM_AF_BLK_RST (0x10)
+#define CPT_AF_BLK_RST (0x46000)
+#define NDC_AF_BLK_RST (0x002F0)
+#define NPC_AF_BLK_RST (0x00040)
+
+#endif /* RVU_REG_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
new file mode 100644
index 0000000..9e11333
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Marvell OcteonTx2 RVU Admin Function driver
+ *
+ * Copyright (C) 2018 Marvell International Ltd.
+ *
+ * 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.
+ */
+
+#ifndef RVU_STRUCT_H
+#define RVU_STRUCT_H
+
+/* RVU Block Address Enumeration */
+enum rvu_block_addr_e {
+ BLKADDR_RVUM = 0x0ULL,
+ BLKADDR_LMT = 0x1ULL,
+ BLKADDR_MSIX = 0x2ULL,
+ BLKADDR_NPA = 0x3ULL,
+ BLKADDR_NIX0 = 0x4ULL,
+ BLKADDR_NIX1 = 0x5ULL,
+ BLKADDR_NPC = 0x6ULL,
+ BLKADDR_SSO = 0x7ULL,
+ BLKADDR_SSOW = 0x8ULL,
+ BLKADDR_TIM = 0x9ULL,
+ BLKADDR_CPT0 = 0xaULL,
+ BLKADDR_CPT1 = 0xbULL,
+ BLKADDR_NDC0 = 0xcULL,
+ BLKADDR_NDC1 = 0xdULL,
+ BLKADDR_NDC2 = 0xeULL,
+ BLK_COUNT = 0xfULL,
+};
+
+#endif /* RVU_STRUCT_H */
--
2.7.4
^ permalink raw reply related
* [PATCH 01/15] octeontx2-af: Add Marvell OcteonTX2 RVU AF driver
From: sunil.kovvuri @ 2018-09-28 6:07 UTC (permalink / raw)
To: netdev, davem; +Cc: arnd, linux-soc, Sunil Goutham
In-Reply-To: <1538114872-10820-1-git-send-email-sunil.kovvuri@gmail.com>
From: Sunil Goutham <sgoutham@marvell.com>
This patch adds basic template for Marvell OcteonTX2's
resource virtualization unit (RVU) admin function (AF)
driver. Just the driver registration and probe.
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
---
drivers/net/ethernet/marvell/Kconfig | 3 +
drivers/net/ethernet/marvell/Makefile | 1 +
drivers/net/ethernet/marvell/octeontx2/Kconfig | 12 ++
drivers/net/ethernet/marvell/octeontx2/Makefile | 6 +
drivers/net/ethernet/marvell/octeontx2/af/Makefile | 8 ++
drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 126 +++++++++++++++++++++
drivers/net/ethernet/marvell/octeontx2/af/rvu.h | 31 +++++
7 files changed, 187 insertions(+)
create mode 100644 drivers/net/ethernet/marvell/octeontx2/Kconfig
create mode 100644 drivers/net/ethernet/marvell/octeontx2/Makefile
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/Makefile
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/rvu.c
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/rvu.h
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index f33fd22..3238aa7 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -167,4 +167,7 @@ config SKY2_DEBUG
If unsure, say N.
+
+source "drivers/net/ethernet/marvell/octeontx2/Kconfig"
+
endif # NET_VENDOR_MARVELL
diff --git a/drivers/net/ethernet/marvell/Makefile b/drivers/net/ethernet/marvell/Makefile
index 55d4d10..89dea72 100644
--- a/drivers/net/ethernet/marvell/Makefile
+++ b/drivers/net/ethernet/marvell/Makefile
@@ -11,3 +11,4 @@ obj-$(CONFIG_MVPP2) += mvpp2/
obj-$(CONFIG_PXA168_ETH) += pxa168_eth.o
obj-$(CONFIG_SKGE) += skge.o
obj-$(CONFIG_SKY2) += sky2.o
+obj-y += octeontx2/
diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig
new file mode 100644
index 0000000..9743502
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig
@@ -0,0 +1,12 @@
+#
+# Marvell OcteonTX2 drivers configuration
+#
+
+config OCTEONTX2_AF
+ tristate "Marvell OcteonTX2 RVU Admin Function driver"
+ depends on ARM64 && PCI
+ help
+ This driver supports Marvell's OcteonTX2 Resource Virtualization
+ Unit's admin function manager which manages all RVU HW resources
+ and provides a medium to other PF/VFs to configure HW. Should be
+ enabled for other RVU device drivers to work.
diff --git a/drivers/net/ethernet/marvell/octeontx2/Makefile b/drivers/net/ethernet/marvell/octeontx2/Makefile
new file mode 100644
index 0000000..e579dcd
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Marvell OcteonTX2 device drivers.
+#
+
+obj-$(CONFIG_OCTEONTX2_AF) += af/
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
new file mode 100644
index 0000000..dacbd16
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Marvell's OcteonTX2 RVU Admin Function driver
+#
+
+obj-$(CONFIG_OCTEONTX2_AF) += octeontx2_af.o
+
+octeontx2_af-y := rvu.o
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
new file mode 100644
index 0000000..5af4da6
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell OcteonTx2 RVU Admin Function driver
+ *
+ * Copyright (C) 2018 Marvell International Ltd.
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/pci.h>
+#include <linux/sysfs.h>
+
+#include "rvu.h"
+
+#define DRV_NAME "octeontx2-af"
+#define DRV_STRING "Marvell OcteonTX2 RVU Admin Function Driver"
+#define DRV_VERSION "1.0"
+
+/* Supported devices */
+static const struct pci_device_id rvu_id_table[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_RVU_AF) },
+ { 0, } /* end of table */
+};
+
+MODULE_AUTHOR("Marvell International Ltd.");
+MODULE_DESCRIPTION(DRV_STRING);
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
+MODULE_DEVICE_TABLE(pci, rvu_id_table);
+
+static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+ struct device *dev = &pdev->dev;
+ struct rvu *rvu;
+ int err;
+
+ rvu = devm_kzalloc(dev, sizeof(*rvu), GFP_KERNEL);
+ if (!rvu)
+ return -ENOMEM;
+
+ pci_set_drvdata(pdev, rvu);
+ rvu->pdev = pdev;
+ rvu->dev = &pdev->dev;
+
+ err = pci_enable_device(pdev);
+ if (err) {
+ dev_err(dev, "Failed to enable PCI device\n");
+ goto err_freemem;
+ }
+
+ err = pci_request_regions(pdev, DRV_NAME);
+ if (err) {
+ dev_err(dev, "PCI request regions failed 0x%x\n", err);
+ goto err_disable_device;
+ }
+
+ err = pci_set_dma_mask(pdev, DMA_BIT_MASK(48));
+ if (err) {
+ dev_err(dev, "Unable to set DMA mask\n");
+ goto err_release_regions;
+ }
+
+ err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48));
+ if (err) {
+ dev_err(dev, "Unable to set consistent DMA mask\n");
+ goto err_release_regions;
+ }
+
+ /* Map Admin function CSRs */
+ rvu->afreg_base = pcim_iomap(pdev, PCI_AF_REG_BAR_NUM, 0);
+ rvu->pfreg_base = pcim_iomap(pdev, PCI_PF_REG_BAR_NUM, 0);
+ if (!rvu->afreg_base || !rvu->pfreg_base) {
+ dev_err(dev, "Unable to map admin function CSRs, aborting\n");
+ err = -ENOMEM;
+ goto err_release_regions;
+ }
+
+ return 0;
+
+err_release_regions:
+ pci_release_regions(pdev);
+err_disable_device:
+ pci_disable_device(pdev);
+err_freemem:
+ pci_set_drvdata(pdev, NULL);
+ devm_kfree(dev, rvu);
+ return err;
+}
+
+static void rvu_remove(struct pci_dev *pdev)
+{
+ struct rvu *rvu = pci_get_drvdata(pdev);
+
+ pci_release_regions(pdev);
+ pci_disable_device(pdev);
+ pci_set_drvdata(pdev, NULL);
+
+ devm_kfree(&pdev->dev, rvu);
+}
+
+static struct pci_driver rvu_driver = {
+ .name = DRV_NAME,
+ .id_table = rvu_id_table,
+ .probe = rvu_probe,
+ .remove = rvu_remove,
+};
+
+static int __init rvu_init_module(void)
+{
+ pr_info("%s: %s\n", DRV_NAME, DRV_STRING);
+
+ return pci_register_driver(&rvu_driver);
+}
+
+static void __exit rvu_cleanup_module(void)
+{
+ pci_unregister_driver(&rvu_driver);
+}
+
+module_init(rvu_init_module);
+module_exit(rvu_cleanup_module);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
new file mode 100644
index 0000000..4a4b0ad
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Marvell OcteonTx2 RVU Admin Function driver
+ *
+ * Copyright (C) 2018 Marvell International Ltd.
+ *
+ * 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.
+ */
+
+#ifndef RVU_H
+#define RVU_H
+
+/* PCI device IDs */
+#define PCI_DEVID_OCTEONTX2_RVU_AF 0xA065
+
+/* PCI BAR nos */
+#define PCI_AF_REG_BAR_NUM 0
+#define PCI_PF_REG_BAR_NUM 2
+#define PCI_MBOX_BAR_NUM 4
+
+#define NAME_SIZE 32
+
+struct rvu {
+ void __iomem *afreg_base;
+ void __iomem *pfreg_base;
+ struct pci_dev *pdev;
+ struct device *dev;
+};
+
+#endif /* RVU_H */
--
2.7.4
^ permalink raw reply related
* [PATCH 00/15] octeontx2-af: Add RVU Admin Function driver
From: sunil.kovvuri @ 2018-09-28 6:07 UTC (permalink / raw)
To: netdev, davem; +Cc: arnd, linux-soc, Sunil Goutham
From: Sunil Goutham <sgoutham@marvell.com>
Resource virtualization unit (RVU) on Marvell's OcteonTX2 SOC maps HW
resources from the network, crypto and other functional blocks into
PCI-compatible physical and virtual functions. Each functional block
again has multiple local functions (LFs) for provisioning to PCI devices.
RVU supports multiple PCIe SRIOV physical functions (PFs) and virtual
functions (VFs). PF0 is called the administrative / admin function (AF)
and has privileges to provision RVU functional block's LFs to each of the
PF/VF.
RVU managed networking functional blocks
- Network pool allocator (NPA)
- Network interface controller (NIX)
- Network parser CAM (NPC)
- Schedule/Synchronize/Order unit (SSO)
RVU managed non-networking functional blocks
- Crypto accelerator (CPT)
- Scheduled timers unit (TIM)
- Schedule/Synchronize/Order unit (SSO)
Used for both networking and non networking usecases
- Compression (upcoming in future variants of the silicons)
Resource provisioning examples
- A PF/VF with NIX-LF & NPA-LF resources works as a pure network device
- A PF/VF with CPT-LF resource works as a pure cyrpto offload device.
This admin function driver neither receives any data nor processes it i.e
no I/O, a configuration only driver.
PF/VFs communicates with AF via a shared memory region (mailbox). Upon
receiving requests from PF/VF, AF does resource provisioning and other
HW configuration. AF is always attached to host, but PF/VFs may be used
by host kernel itself, or attached to VMs or to userspace applications
like DPDK etc. So AF has to handle provisioning/configuration requests
sent by any device from any domain.
This patch series adds logic for the following
- RVU AF driver with functional blocks provisioning support.
- Mailbox infrastructure for communication between AF and PFs.
- CGX (MAC controller) driver which communicates with firmware for
managing physical ethernet interfaces. AF collects info from this
driver and forwards the same to the PF/VFs uaing these interfaces.
This is the first set of patches out of 80+ patches.
Aleksey Makarov (1):
octeontx2-af: Convert mbox msg id check to a macro
Geetha sowjanya (1):
octeontx2-af: Reconfig MSIX base with IOVA
Linu Cherian (3):
octeontx2-af: Set RVU PFs to CGX LMACs mapping
octeontx2-af: Add support for CGX link management
octeontx2-af: Register for CGX lmac events
Sunil Goutham (10):
octeontx2-af: Add Marvell OcteonTX2 RVU AF driver
octeontx2-af: Reset all RVU blocks
octeontx2-af: Gather RVU blocks HW info
octeontx2-af: Add mailbox support infra
octeontx2-af: Add mailbox IRQ and msg handlers
octeontx2-af: Scan blocks for LFs provisioned to PF/VF
octeontx2-af: Add RVU block LF provisioning support
octeontx2-af: Configure block LF's MSIX vector offset
octeontx2-af: Add Marvell OcteonTX2 CGX driver
MAINTAINERS: Add entry for Marvell OcteonTX2 Admin Function driver
MAINTAINERS | 9 +
drivers/net/ethernet/marvell/Kconfig | 3 +
drivers/net/ethernet/marvell/Makefile | 1 +
drivers/net/ethernet/marvell/octeontx2/Kconfig | 16 +
drivers/net/ethernet/marvell/octeontx2/Makefile | 6 +
drivers/net/ethernet/marvell/octeontx2/af/Makefile | 10 +
drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 515 ++++++
drivers/net/ethernet/marvell/octeontx2/af/cgx.h | 65 +
.../net/ethernet/marvell/octeontx2/af/cgx_fw_if.h | 225 +++
drivers/net/ethernet/marvell/octeontx2/af/mbox.c | 303 ++++
drivers/net/ethernet/marvell/octeontx2/af/mbox.h | 211 +++
drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 1637 ++++++++++++++++++++
drivers/net/ethernet/marvell/octeontx2/af/rvu.h | 158 ++
.../net/ethernet/marvell/octeontx2/af/rvu_cgx.c | 194 +++
.../net/ethernet/marvell/octeontx2/af/rvu_reg.h | 441 ++++++
.../net/ethernet/marvell/octeontx2/af/rvu_struct.h | 74 +
16 files changed, 3868 insertions(+)
create mode 100644 drivers/net/ethernet/marvell/octeontx2/Kconfig
create mode 100644 drivers/net/ethernet/marvell/octeontx2/Makefile
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/Makefile
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/cgx.c
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/cgx.h
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/mbox.c
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/mbox.h
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/rvu.c
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/rvu.h
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
create mode 100644 drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
--
2.7.4
^ permalink raw reply
* Re: [PATCH] netfilter: masquerade: don't flush all conntracks if only one address deleted on device
From: Pablo Neira Ayuso @ 2018-09-28 12:22 UTC (permalink / raw)
To: Tan Hu
Cc: kadlec, fw, davem, kuznet, yoshfuji, netfilter-devel, coreteam,
netdev, linux-kernel, zhong.weidong, jiang.biao2
In-Reply-To: <1536309213-19632-1-git-send-email-tan.hu@zte.com.cn>
On Fri, Sep 07, 2018 at 04:33:33PM +0800, Tan Hu wrote:
> We configured iptables as below, which only allowed incoming data on
> established connections:
>
> iptables -t mangle -A PREROUTING -m state --state ESTABLISHED -j ACCEPT
> iptables -t mangle -P PREROUTING DROP
>
> When deleting a secondary address, current masquerade implements would
> flush all conntracks on this device. All the established connections on
> primary address also be deleted, then subsequent incoming data on the
> connections would be dropped wrongly because it was identified as NEW
> connection.
>
> So when an address was delete, it should only flush connections related
> with the address.
Applied to nf-next, thanks.
^ permalink raw reply
* Re: [PATCH net-next v6 00/23] WireGuard: Secure Network Tunnel
From: Jason A. Donenfeld @ 2018-09-28 5:46 UTC (permalink / raw)
To: Eric Biggers
Cc: LKML, Netdev, Linux Crypto Mailing List, David Miller,
Greg Kroah-Hartman
In-Reply-To: <20180928045542.GA545@zzz.localdomain>
Hi Eric,
On Fri, Sep 28, 2018 at 6:55 AM Eric Biggers <ebiggers@kernel.org> wrote:
> And you still haven't answered my question about adding a new algorithm that is
> useful to have in both APIs. You're proposing that in most cases the crypto API
> part will need to go through Herbert while the implementation will need to go
> through you/Greg, right? Or will you/Greg be taking both? Or will Herbert take
> both?
If an implementation enters Zinc, it will go through my tree. If it
enters the crypto API, it will go through Herbert's tree. If there
wind up being messy tree dependency and merge timing issues, I can
work this out in the usual way with Herbert. I'll be sure to discuss
these edge cases with him when we discuss. I think there's a way to
handle that with minimum friction.
> A documentation file for Zinc is a good idea. Some of the information in your
> commit messages should be moved there too.
Will do.
> I'm not trying to "politicize" this, but rather determine your criteria for
> including algorithms in Zinc, which you haven't made clear. Since for the
> second time you've avoided answering my question about whether you'd allow the
> SM4 cipher in Zinc, and you designed WireGuard to be "cryptographically
> opinionated", and you were one of the loudest voices calling for the Speck
> cipher to be removed, and your justification for Zinc complains about cipher
> modes from "90s cryptographers", I think it's reasonable for people to wonder
> whether as the Zinc (i.e. Linux crypto library) maintainer you will restrict the
> inclusion of crypto algorithms to the ones you prefer, rather than the ones that
> users need. Note that the kernel is used by people all over the world and needs
> to support various standards, protocols, and APIs that use different crypto
> algorithms, not always the ones we'd like; and different users have different
> preferences. People need to know whether the Linux kernel's crypto library will
> meet (or be allowed to meet) their crypto needs.
WireGuard is indeed quite opinionated in its primitive choices, but I
don't think it'd be wise to apply the same design to Zinc. There are
APIs where the goal is to have a limited set of high-level functions,
and have those implemented in only a preferred set of primitives. NaCl
is a good example of this -- functions like "crypto_secretbox" that
are actually xsalsapoly under the hood. Zinc doesn't intend to become
an API like those, but rather to provide the actual primitives for use
cases where that specific primitive is used. Sometimes the kernel is
in the business of being able to pick its own crypto -- random.c, tcp
sequence numbers, big_key.c, etc -- but most of the time the kernel is
in the business of implementing other people's crypto, for specific
devices/protocols/diskformats. And for those use cases we need not
some high-level API like NaCl, but rather direct access to the
primitives that are required to implement those drivers. WireGuard is
one such example, but so would be Bluetooth, CIFS/SMB, WiFi, and so
on. We're in the business of writing drivers, after all. So, no, I
don't think I'd knock down the addition of a primitive because of a
simple preference for a different primitive, if it was clearly the
case that the driver requiring it really benefited from having
accessible via the plain Zinc function calls. Sorry if I hadn't made
this clear earlier -- I thought Ard had asked more or less the same
thing about DES and I answered accordingly, but maybe that wasn't made
clear enough there.
> > For example, check out the avx blocks function. The radix conversion
> > happens in a few different places throughout. The reason we need it
> > separately here is because, unlike userspace, it's possible the kernel
> > code will transition from 2^26 back to 2^64 as a result of the FPU
> > context changing.
>
> IOW, you had to rewrite the x86 assembly algorithm in C and make it use a
> different Poly1305 context format. That's a major change, where bugs can be
> introduced -- and at least one was introduced, in fact. I'd appreciate it if
> you were more accurate in describing your modifications and the potential risks
> involved.
A different Poly1305 context format? Not at all - it's using the exact
same context struct as the assembly. And it's making the same
conversion that the assembly is. There's not something "different"
happening; that's the whole point.
Also, this is not some process of frightfully transcribing assembly to
C and hoping it all works out. This is a careful process of reasoning
about the limbs, proving that the carries are correct, and that the
arithmetic done in C actually corresponds to what we want. And then
finally we check that what we've implemented is indeed the same as
what the assembly implemented. Finally, as I mentioned, hopefully Andy
will be folding this back into his implementations sometime soon
anyway.
> > That's a good idea. I can include some discussion about this as well in
> > the commit message that introduces the glue code, too, I guess? I've
> > been hesitant to fill these commit messages up even more, given there
> > are already so many walls of text and whatnot, but if you think that'd
> > be useful, I'll do that for v7, and also add comments.
>
> Please prefer to put information in the code or documentation rather than in
> commit messages, when appropriate.
Okay, no problem.
> > This is complete and utter garbage, and I find its insinuations insulting
> > and ridiculous. There is absolutely no lack of honesty and no double
> > standard being applied whatsoever. Your attempt to cast doubt about the
> > quality of standards applied and the integrity of the process is wholly
> > inappropriate. When I tell you that high standards were applied and that
> > due-diligence was done in developing a particular patch, I mean what I
> > say.
>
> I
> disagree that my concerns are "complete and utter garbage". And I think that
> the fact that you prefer to respond by attacking me, rather than committing to
> be more accurate in your claims and to treat all contributions fairly, is
> problematic.
I believe you have the sequence of events wrong. I've stated and made
that there isn't a double standard, that the standards intend to be
evenly rigorous, and I solicited your feedback on how I could best
communicate changes in pre-merged patch series; I did the things
you've said one should do. But your rhetoric then moved to questioning
my integrity, and I believe that was uncalled for, inappropriate, and
not a useful contribution to this mostly productive discussion --
hence garbage. In other words, I provided an acceptable defense, not
an attack. But can we move past all this schoolyard nonsense? Cut the
rhetoric, please; it's really quite overwhelming.
> It's great that you found and fixed this
> bug on your own, and of course that raises my level of confidence in your work.
Good.
> Still, the v6 patchset still includes your claim that "All implementations have
> been extensively tested and fuzzed"; so that claim was objectively wrong.
I don't think that claim is wrong. The fuzzing and testing that's been
done has been extensive, and the fuzzing and testing that continues to
occur is extensive. As mentioned, the bug was fixed pretty much right
after git-send-email. If you'd like I can try to space out the patch
submissions by a little bit longer -- that would probably have various
benefits -- but given that the netdev code is yet to receive a
thorough review, I think we've got a bit of time before this is
merged. The faster-paced patch cycles might inadvertently introduce
things that get fixed immediately after sending then, unfortunately,
but I don't think this will be the case with the final series that's
merged. Though I'm incorporating tons and tons of feedback right now,
I do look forward to the structure of the series settling down a
little bit and the pace of suggestions decreasing, so that I can focus
on auditing and verifying again. But given the dynamism and
interesting insights of the reviews so far, I think the fast pace has
actually been useful for elucidating the various expectations and
suggestions of reviewers. It's most certainly improved this patchset
in terrific ways.
> Well, it doesn't help that you yourself claim that Zinc stands for
> "Zx2c4's INsane Cryptolib"...
This expansion of the acronym was intended as a totally ridiculous
joke. I guess it wasn't received well. I'll remove it from the next
series. Sorry.
Jason
^ permalink raw reply
* Re: [PATCH v3 bpf-next 03/10] bpf: introduce per-cpu cgroup local storage
From: Daniel Borkmann @ 2018-09-28 12:03 UTC (permalink / raw)
To: Alexei Starovoitov, Roman Gushchin
Cc: netdev, Song Liu, linux-kernel, kernel-team, Alexei Starovoitov
In-Reply-To: <20180928102458.dbia6xnxkijvkld6@ast-mbp.dhcp.thefacebook.com>
On 09/28/2018 12:25 PM, Alexei Starovoitov wrote:
> On Fri, Sep 28, 2018 at 11:03:03AM +0100, Roman Gushchin wrote:
>>>> +
>>>> + if (unlikely(map_flags & BPF_EXIST))
>>>> + return -EINVAL;
>>>
>>> that should have been BPF_NOEXIST ?
>>
>> Yeah, or maybe even better s/&/!= ?
>> It's probably better to require BPF_EXIST flag to update a cgroup storage?
>> Agree? If so, let me fix this for both shared and per-cpu versions in
>> a follow-up patch.
>
> I think BPF_ANY is technically valid too.
> If we were to require strict BPF_EXIST only, we'd need to fix stable too.
> I'm fine with both (BPF_EXIST only and BPF_ANY|BPF_EXIST).
> Daniel, what do you think?
I'm okay with either option, both seem plausible.
^ permalink raw reply
* [PATCH bpf-next] bpf: fix flags check in bpf_percpu_cgroup_storage_update()
From: Roman Gushchin @ 2018-09-28 11:06 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, kernel-team, Roman Gushchin, Daniel Borkmann,
Alexei Starovoitov
Fix an issue in bpf_percpu_cgroup_storage_update(): it should return
-EINVAL on an attempt to pass BPF_NOEXIST rather than BPF_EXIST.
Cgroup local storage is automatically created on attaching of a bpf
program to a cgroup, and it can't be done from the userspace.
Fixes: 0daef9b42374 ("bpf: introduce per-cpu cgroup local storage")
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
---
kernel/bpf/local_storage.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c739f6dcc3c2..190535f6d5e2 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -191,7 +191,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key,
int cpu, off = 0;
u32 size;
- if (unlikely(map_flags & BPF_EXIST))
+ if (map_flags & BPF_NOEXIST)
return -EINVAL;
rcu_read_lock();
--
2.17.1
^ permalink raw reply related
* CONGRATULATIONS
From: YAHOO MAIL @ 2018-09-28 0:42 UTC (permalink / raw)
To: Westnet Support
Yahoo!©
We are delighted to inform you that you were drawn a winner of (USD $5,005,000.00)
in our 2018 Yahoo (email) lottery. To file for claim please contact below our (claim officer)
______________________________________
Sir. Warren Vandall
(Claims Officer)
Asian Regional Sector
_______________________________________
You are to establish contact with the Following details:
Name
Residential/Office Address
Telephone
Fax Number
Age
M/F
Thanks & Regards
Mrs. Georgina Rowland
Yahoo Asia Pte. Ltd.
YAHOO! ASIA©
-------------------------------------------------------------------------------------------------------------------
Yahoo Asia Pte. Ltd. (Co. Reg. No. 199700735D) VERIFIED BY YAHOO ASIA.
^ permalink raw reply
* Re: [PATCH v3 bpf-next 10/10] selftests/bpf: cgroup local storage-based network counters
From: Alexei Starovoitov @ 2018-09-28 10:40 UTC (permalink / raw)
To: Roman Gushchin
Cc: netdev, Song Liu, linux-kernel, kernel-team, Daniel Borkmann,
Alexei Starovoitov
In-Reply-To: <20180928103717.GA12917@castle.DHCP.thefacebook.com>
On Fri, Sep 28, 2018 at 11:37:26AM +0100, Roman Gushchin wrote:
> > > > > +
> > > > > + /* Let's check that bytes counter value is reasonable */
> > > > > + if (netcnt.bytes < packets * 500 || netcnt.bytes > packets * 1500) {
> > > >
> > > > since packet count is accurate why byte count would vary ?
> > >
> > > Tbh I'm not sure if the size of the packet here can vary depending
> > > on the environment. Is there a nice way to get the expected size?
> >
> > ping packets should be fixed size depending on v4 vs v6.
> > If 'ping -6' is used, it will force ipv6.
> >
>
> Are we ok to screw up kselftests on v4-only machines?
we already did. Some of the selftests/bpf use ping -6 already.
^ permalink raw reply
* Re: [PATCH v3 bpf-next 10/10] selftests/bpf: cgroup local storage-based network counters
From: Roman Gushchin @ 2018-09-28 10:37 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: netdev, Song Liu, linux-kernel, kernel-team, Daniel Borkmann,
Alexei Starovoitov
In-Reply-To: <20180928102814.voj6bsuslxh6ms37@ast-mbp.dhcp.thefacebook.com>
On Fri, Sep 28, 2018 at 12:28:16PM +0200, Alexei Starovoitov wrote:
> On Fri, Sep 28, 2018 at 11:08:29AM +0100, Roman Gushchin wrote:
> > > > + /* Some packets can be still in per-cpu cache, but not more than
> > > > + * MAX_PERCPU_PACKETS.
> > > > + */
> > > > + packets = netcnt.packets;
> > > > + for (cpu = 0; cpu < nproc; cpu++) {
> > > > + if (percpu_netcnt[cpu].packets > 32) {
> > >
> > > pls use MAX_PERCPU_PACKETS in the above check.
> > > could you also double check that if that #define is changed to 1k or so
> > > the exact "!= 10000" check below still works as expected?
> >
> > Do you mean adding a new test with a different MAX_PERCPU_PACKETS?
>
> good idea! If it's easy to compile the same source twice with different
> MAX_PERCPU_PACKETS that would certainly make the test stronger.
> Not sure how feasible though.
>
> >
> > >
> > > > + printf("Unexpected percpu value: %llu\n",
> > > > + percpu_netcnt[cpu].packets);
> > > > + goto err;
> > >
> > > > + }
> > > > +
> > > > + packets += percpu_netcnt[cpu].packets;
> > > > + }
> > > > +
> > > > + /* No packets should be lost */
> > > > + if (packets != 10000) {
> > > > + printf("Unexpected packet count: %lu\n", packets);
> > > > + goto err;
> > > > + }
> > > > +
> > > > + /* Let's check that bytes counter value is reasonable */
> > > > + if (netcnt.bytes < packets * 500 || netcnt.bytes > packets * 1500) {
> > >
> > > since packet count is accurate why byte count would vary ?
> >
> > Tbh I'm not sure if the size of the packet here can vary depending
> > on the environment. Is there a nice way to get the expected size?
>
> ping packets should be fixed size depending on v4 vs v6.
> If 'ping -6' is used, it will force ipv6.
>
Are we ok to screw up kselftests on v4-only machines?
Alternatively, I can send 1 packet, get the size and check that all other
are of the same size.
^ permalink raw reply
* Re: [PATCH v3 bpf-next 10/10] selftests/bpf: cgroup local storage-based network counters
From: Alexei Starovoitov @ 2018-09-28 10:28 UTC (permalink / raw)
To: Roman Gushchin
Cc: netdev, Song Liu, linux-kernel, kernel-team, Daniel Borkmann,
Alexei Starovoitov
In-Reply-To: <20180928100817.GC9018@castle.DHCP.thefacebook.com>
On Fri, Sep 28, 2018 at 11:08:29AM +0100, Roman Gushchin wrote:
> > > + /* Some packets can be still in per-cpu cache, but not more than
> > > + * MAX_PERCPU_PACKETS.
> > > + */
> > > + packets = netcnt.packets;
> > > + for (cpu = 0; cpu < nproc; cpu++) {
> > > + if (percpu_netcnt[cpu].packets > 32) {
> >
> > pls use MAX_PERCPU_PACKETS in the above check.
> > could you also double check that if that #define is changed to 1k or so
> > the exact "!= 10000" check below still works as expected?
>
> Do you mean adding a new test with a different MAX_PERCPU_PACKETS?
good idea! If it's easy to compile the same source twice with different
MAX_PERCPU_PACKETS that would certainly make the test stronger.
Not sure how feasible though.
>
> >
> > > + printf("Unexpected percpu value: %llu\n",
> > > + percpu_netcnt[cpu].packets);
> > > + goto err;
> >
> > > + }
> > > +
> > > + packets += percpu_netcnt[cpu].packets;
> > > + }
> > > +
> > > + /* No packets should be lost */
> > > + if (packets != 10000) {
> > > + printf("Unexpected packet count: %lu\n", packets);
> > > + goto err;
> > > + }
> > > +
> > > + /* Let's check that bytes counter value is reasonable */
> > > + if (netcnt.bytes < packets * 500 || netcnt.bytes > packets * 1500) {
> >
> > since packet count is accurate why byte count would vary ?
>
> Tbh I'm not sure if the size of the packet here can vary depending
> on the environment. Is there a nice way to get the expected size?
ping packets should be fixed size depending on v4 vs v6.
If 'ping -6' is used, it will force ipv6.
^ permalink raw reply
* Re: [PATCH v3 bpf-next 03/10] bpf: introduce per-cpu cgroup local storage
From: Alexei Starovoitov @ 2018-09-28 10:25 UTC (permalink / raw)
To: Roman Gushchin
Cc: netdev, Song Liu, linux-kernel, kernel-team, Daniel Borkmann,
Alexei Starovoitov
In-Reply-To: <20180928100302.GB9018@castle.DHCP.thefacebook.com>
On Fri, Sep 28, 2018 at 11:03:03AM +0100, Roman Gushchin wrote:
> > > +
> > > + if (unlikely(map_flags & BPF_EXIST))
> > > + return -EINVAL;
> >
> > that should have been BPF_NOEXIST ?
>
> Yeah, or maybe even better s/&/!= ?
> It's probably better to require BPF_EXIST flag to update a cgroup storage?
> Agree? If so, let me fix this for both shared and per-cpu versions in
> a follow-up patch.
I think BPF_ANY is technically valid too.
If we were to require strict BPF_EXIST only, we'd need to fix stable too.
I'm fine with both (BPF_EXIST only and BPF_ANY|BPF_EXIST).
Daniel, what do you think?
^ permalink raw reply
* RE: [PATCH 1/2] net: dpaa2: move DPAA2 PTP driver out of staging/
From: Ioana Ciocoi Radulescu @ 2018-09-28 10:20 UTC (permalink / raw)
To: Y.b. Lu, Andrew Lunn
Cc: devel@driverdev.osuosl.org, netdev@vger.kernel.org,
Richard Cochran, linux-kernel@vger.kernel.org, Greg Kroah-Hartman,
David S . Miller
In-Reply-To: <VI1PR0401MB223737CACE4E4064AE8325A4F8EC0@VI1PR0401MB2237.eurprd04.prod.outlook.com>
> -----Original Message-----
> From: Y.b. Lu
> Sent: Friday, September 28, 2018 11:04 AM
> To: Andrew Lunn <andrew@lunn.ch>
> Cc: linux-kernel@vger.kernel.org; devel@driverdev.osuosl.org;
> netdev@vger.kernel.org; Richard Cochran <richardcochran@gmail.com>;
> David S . Miller <davem@davemloft.net>; Ioana Ciocoi Radulescu
> <ruxandra.radulescu@nxp.com>; Greg Kroah-Hartman
> <gregkh@linuxfoundation.org>
> Subject: RE: [PATCH 1/2] net: dpaa2: move DPAA2 PTP driver out of staging/
>
> Hi Andrew,
>
> Thanks a lot for your comments.
> Please see my comments inline.
>
> Best regards,
> Yangbo Lu
>
> > -----Original Message-----
> > From: Andrew Lunn <andrew@lunn.ch>
> > Sent: Thursday, September 27, 2018 9:25 PM
> > To: Y.b. Lu <yangbo.lu@nxp.com>
> > Cc: linux-kernel@vger.kernel.org; devel@driverdev.osuosl.org;
> > netdev@vger.kernel.org; Richard Cochran <richardcochran@gmail.com>;
> > David S . Miller <davem@davemloft.net>; Ioana Ciocoi Radulescu
> > <ruxandra.radulescu@nxp.com>; Greg Kroah-Hartman
> > <gregkh@linuxfoundation.org>
> > Subject: Re: [PATCH 1/2] net: dpaa2: move DPAA2 PTP driver out of
> staging/
> >
> > On Thu, Sep 27, 2018 at 07:12:27PM +0800, Yangbo Lu wrote:
> > > This patch is to move DPAA2 PTP driver out of staging/ since the
> > > dpaa2-eth had been moved out.
> > >
> > > Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
> > > ---
> > > drivers/net/ethernet/freescale/Kconfig | 9 +--------
> > > drivers/net/ethernet/freescale/dpaa2/Kconfig | 15
> > +++++++++++++++
> > > drivers/net/ethernet/freescale/dpaa2/Makefile | 6 ++++--
> > > .../ethernet/freescale/dpaa2}/dprtc-cmd.h | 0
> > > .../rtc => net/ethernet/freescale/dpaa2}/dprtc.c | 0
> > > .../rtc => net/ethernet/freescale/dpaa2}/dprtc.h | 0
> > > .../rtc => net/ethernet/freescale/dpaa2}/rtc.c | 0
> > > .../rtc => net/ethernet/freescale/dpaa2}/rtc.h | 0
> > > drivers/staging/fsl-dpaa2/Kconfig | 8 --------
> > > drivers/staging/fsl-dpaa2/Makefile | 1 -
> > > drivers/staging/fsl-dpaa2/rtc/Makefile | 7 -------
> > > 11 files changed, 20 insertions(+), 26 deletions(-) create mode
> > > 100644 drivers/net/ethernet/freescale/dpaa2/Kconfig
> > > rename drivers/{staging/fsl-dpaa2/rtc =>
> > > net/ethernet/freescale/dpaa2}/dprtc-cmd.h (100%) rename
> > > drivers/{staging/fsl-dpaa2/rtc =>
> > > net/ethernet/freescale/dpaa2}/dprtc.c (100%) rename
> > > drivers/{staging/fsl-dpaa2/rtc =>
> > > net/ethernet/freescale/dpaa2}/dprtc.h (100%) rename
> > > drivers/{staging/fsl-dpaa2/rtc => net/ethernet/freescale/dpaa2}/rtc.c
> > > (100%) rename drivers/{staging/fsl-dpaa2/rtc =>
> > > net/ethernet/freescale/dpaa2}/rtc.h (100%)
> >
> > Hi Yangbo
> >
> > Calling a ptp driver rtc.[ch] seems rather odd. Could you fixup the name,
> > change it to ptp.[ch]. Also, some of the function names, and structures,
> > rtc_probe->ptp_probe, rtc_remove->ptp_remove, rtc_match_id_table->
> > ptp_match_id_table, etc.
>
> [Y.b. Lu] Indeed, it's odd and confusing...
> For dpaa2, all hardware resources are allocated and configured through the
> Management Complex (MC) portals.
> MC abstracts most of these resources as DPAA2 objects and exposes ABIs
> through which they can be configured and controlled.
> This ptp timer was named as rtc in MC firmware and APIs as you saw in
> dprtc.*.
> So initially I wrote this driver using rtc as name.
>
> No worries, let me change it in next version.
>
> >
> > ptp_dpaa2_adjfreq() probably should return err, not 0.
> > ptp_dpaa2_gettime() again does not return the error.
> > If fact, it seems like all the main functions ignore errors.
>
> [Y.b. Lu] Will fix the returns in next version.
>
> >
> > kzalloc() could be changed to devm_kzalloc() to simplify the cleanup
>
> [Y.b. Lu] Will use devm_kzalloc() in next version.
>
> Can
> > ptp_dpaa2_caps be made const?
>
> [Y.b. Lu] Yes. Will change it in next version.
>
> > dpaa2_phc_index does not appear to be used.
>
> [Y.b. Lu] It's used in dpaa2-ethtool.c for .get_ts_info interface of
> ethtool_ops.
>
> > dev_set_drvdata(dev, NULL); is not needed.
>
> [Y.b. Lu] Will remove it in next version.
>
> > Can rtc_drv be made const?
>
> [Y.b. Lu] Will use const in next version.
>
> > Is rtc.h used by anything other than rtc.c? It seems like it can be removed.
>
> [Y.b. Lu] Let me remove it in next version.
>
> >
> > It seems like there is a lot of code in dprtc.c which is unused. rtc.c does
> nothing
> > with interrupts for example. Do you plan to make use of this extra code? Or
> > can it be removed leaving just what is needed?
>
> [Y.b. Lu] Currently the ptp/rtc driver is not full-featured. The extra code is
> being planed to be used.
Are there any interrupts associated to the real time clock module that will
actually be used by the driver? Also, I don't think the create/destroy functions
are meant to be used by the PTP kernel driver, even though MC exposes the
APIs for them.
Generally speaking, I think it's better to remove unused code from the current
driver and re-add it along with the feature actually using it.
>
> >
> > struct dprtc_cmd_get_irq - Putting pad at the beginning of a struct seems
> very
> > odd. And it is not the only example.
>
> [Y.b. Lu] This should depended on MC firmware and APIs I think. Once the
> MC improves this, the APIs could be updated to fix this.
These structures map the command format expected by the MC firmware. I
agree that some of the command layouts are less than inspired, but I'm not
sure we can expect MC to "improve" them without a good reason, as this would
break backward compatibility.
I also want to bring up the question of where the dpaa2 ptp driver should be
located. The qoriq_ptp driver (which targets previous gen Freescale/NXP
architectures) is located in drivers/ptp. I'm not sure if the dpaa2 ptp driver should
be moved there as well or it's better suited for the currently proposed location.
Thanks,
Ioana
^ permalink raw reply
* [PATCH net 8/8] rxrpc: Fix error distribution
From: David Howells @ 2018-09-28 10:10 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <153812939111.10469.179989653628053410.stgit@warthog.procyon.org.uk>
Fix error distribution by immediately delivering the errors to all the
affected calls rather than deferring them to a worker thread. The problem
with the latter is that retries and things can happen in the meantime when we
want to stop that sooner.
To this end:
(1) Stop the error distributor from removing calls from the error_targets
list so that peer->lock isn't needed to synchronise against other adds
and removals.
(2) Require the peer's error_targets list to be accessed with RCU, thereby
avoiding the need to take peer->lock over distribution.
(3) Don't attempt to affect a call's state if it is already marked complete.
Signed-off-by: David Howells <dhowells@redhat.com>
---
include/trace/events/rxrpc.h | 4 +---
net/rxrpc/ar-internal.h | 5 -----
net/rxrpc/call_object.c | 2 +-
net/rxrpc/conn_client.c | 4 ++--
net/rxrpc/conn_object.c | 2 +-
net/rxrpc/peer_event.c | 46 ++++++++++--------------------------------
net/rxrpc/peer_object.c | 17 ----------------
7 files changed, 16 insertions(+), 64 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 196587b8f204..837393fa897b 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -56,7 +56,6 @@ enum rxrpc_peer_trace {
rxrpc_peer_new,
rxrpc_peer_processing,
rxrpc_peer_put,
- rxrpc_peer_queued_error,
};
enum rxrpc_conn_trace {
@@ -257,8 +256,7 @@ enum rxrpc_tx_point {
EM(rxrpc_peer_got, "GOT") \
EM(rxrpc_peer_new, "NEW") \
EM(rxrpc_peer_processing, "PRO") \
- EM(rxrpc_peer_put, "PUT") \
- E_(rxrpc_peer_queued_error, "QER")
+ E_(rxrpc_peer_put, "PUT")
#define rxrpc_conn_traces \
EM(rxrpc_conn_got, "GOT") \
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index c72686193d83..ef9554131434 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -288,7 +288,6 @@ struct rxrpc_peer {
struct hlist_node hash_link;
struct rxrpc_local *local;
struct hlist_head error_targets; /* targets for net error distribution */
- struct work_struct error_distributor;
struct rb_root service_conns; /* Service connections */
struct list_head keepalive_link; /* Link in net->peer_keepalive[] */
time64_t last_tx_at; /* Last time packet sent here */
@@ -299,8 +298,6 @@ struct rxrpc_peer {
unsigned int maxdata; /* data size (MTU - hdrsize) */
unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */
int debug_id; /* debug ID for printks */
- int error_report; /* Net (+0) or local (+1000000) to distribute */
-#define RXRPC_LOCAL_ERROR_OFFSET 1000000
struct sockaddr_rxrpc srx; /* remote address */
/* calculated RTT cache */
@@ -1039,7 +1036,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
* peer_event.c
*/
void rxrpc_error_report(struct sock *);
-void rxrpc_peer_error_distributor(struct work_struct *);
void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
void rxrpc_peer_keepalive_worker(struct work_struct *);
@@ -1057,7 +1053,6 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *);
struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *);
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *);
void rxrpc_put_peer(struct rxrpc_peer *);
-void __rxrpc_queue_peer_error(struct rxrpc_peer *);
/*
* proc.c
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 9486293fef5c..799f75b6900d 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -400,7 +400,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
rcu_assign_pointer(conn->channels[chan].call, call);
spin_lock(&conn->params.peer->lock);
- hlist_add_head(&call->error_link, &conn->params.peer->error_targets);
+ hlist_add_head_rcu(&call->error_link, &conn->params.peer->error_targets);
spin_unlock(&conn->params.peer->lock);
_net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index f8f37188a932..8acf74fe24c0 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -710,8 +710,8 @@ int rxrpc_connect_call(struct rxrpc_call *call,
}
spin_lock_bh(&call->conn->params.peer->lock);
- hlist_add_head(&call->error_link,
- &call->conn->params.peer->error_targets);
+ hlist_add_head_rcu(&call->error_link,
+ &call->conn->params.peer->error_targets);
spin_unlock_bh(&call->conn->params.peer->lock);
out:
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index b4438f98dc5c..885dae829f4a 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -216,7 +216,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
call->peer->cong_cwnd = call->cong_cwnd;
spin_lock_bh(&conn->params.peer->lock);
- hlist_del_init(&call->error_link);
+ hlist_del_rcu(&call->error_link);
spin_unlock_bh(&conn->params.peer->lock);
if (rxrpc_is_client_call(call))
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 4f9da2f51c69..f3e6fc670da2 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -23,6 +23,8 @@
#include "ar-internal.h"
static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
+static void rxrpc_distribute_error(struct rxrpc_peer *, int,
+ enum rxrpc_call_completion);
/*
* Find the peer associated with an ICMP packet.
@@ -194,8 +196,6 @@ void rxrpc_error_report(struct sock *sk)
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
- /* The ref we obtained is passed off to the work item */
- __rxrpc_queue_peer_error(peer);
_leave("");
}
@@ -205,6 +205,7 @@ void rxrpc_error_report(struct sock *sk)
static void rxrpc_store_error(struct rxrpc_peer *peer,
struct sock_exterr_skb *serr)
{
+ enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR;
struct sock_extended_err *ee;
int err;
@@ -255,7 +256,7 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
case SO_EE_ORIGIN_NONE:
case SO_EE_ORIGIN_LOCAL:
_proto("Rx Received local error { error=%d }", err);
- err += RXRPC_LOCAL_ERROR_OFFSET;
+ compl = RXRPC_CALL_LOCAL_ERROR;
break;
case SO_EE_ORIGIN_ICMP6:
@@ -264,48 +265,23 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
break;
}
- peer->error_report = err;
+ rxrpc_distribute_error(peer, err, compl);
}
/*
- * Distribute an error that occurred on a peer
+ * Distribute an error that occurred on a peer.
*/
-void rxrpc_peer_error_distributor(struct work_struct *work)
+static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
+ enum rxrpc_call_completion compl)
{
- struct rxrpc_peer *peer =
- container_of(work, struct rxrpc_peer, error_distributor);
struct rxrpc_call *call;
- enum rxrpc_call_completion compl;
- int error;
-
- _enter("");
-
- error = READ_ONCE(peer->error_report);
- if (error < RXRPC_LOCAL_ERROR_OFFSET) {
- compl = RXRPC_CALL_NETWORK_ERROR;
- } else {
- compl = RXRPC_CALL_LOCAL_ERROR;
- error -= RXRPC_LOCAL_ERROR_OFFSET;
- }
- _debug("ISSUE ERROR %s %d", rxrpc_call_completions[compl], error);
-
- spin_lock_bh(&peer->lock);
-
- while (!hlist_empty(&peer->error_targets)) {
- call = hlist_entry(peer->error_targets.first,
- struct rxrpc_call, error_link);
- hlist_del_init(&call->error_link);
+ hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) {
rxrpc_see_call(call);
-
- if (rxrpc_set_call_completion(call, compl, 0, -error))
+ if (call->state < RXRPC_CALL_COMPLETE &&
+ rxrpc_set_call_completion(call, compl, 0, -error))
rxrpc_notify_socket(call);
}
-
- spin_unlock_bh(&peer->lock);
-
- rxrpc_put_peer(peer);
- _leave("");
}
/*
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 70083e8fb6e5..01a9febfa367 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -220,8 +220,6 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
atomic_set(&peer->usage, 1);
peer->local = local;
INIT_HLIST_HEAD(&peer->error_targets);
- INIT_WORK(&peer->error_distributor,
- &rxrpc_peer_error_distributor);
peer->service_conns = RB_ROOT;
seqlock_init(&peer->service_conn_lock);
spin_lock_init(&peer->lock);
@@ -402,21 +400,6 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
return peer;
}
-/*
- * Queue a peer record. This passes the caller's ref to the workqueue.
- */
-void __rxrpc_queue_peer_error(struct rxrpc_peer *peer)
-{
- const void *here = __builtin_return_address(0);
- int n;
-
- n = atomic_read(&peer->usage);
- if (rxrpc_queue_work(&peer->error_distributor))
- trace_rxrpc_peer(peer, rxrpc_peer_queued_error, n, here);
- else
- rxrpc_put_peer(peer);
-}
-
/*
* Discard a peer record.
*/
^ permalink raw reply related
* [PATCH net 7/8] rxrpc: Fix transport sockopts to get IPv4 errors on an IPv6 socket
From: David Howells @ 2018-09-28 10:10 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <153812939111.10469.179989653628053410.stgit@warthog.procyon.org.uk>
It seems that enabling IPV6_RECVERR on an IPv6 socket doesn't also turn on
IP_RECVERR, so neither local errors nor ICMP-transported remote errors from
IPv4 peer addresses are returned to the AF_RXRPC protocol.
Make the sockopt setting code in rxrpc_open_socket() fall through from the
AF_INET6 case to the AF_INET case to turn on all the AF_INET options too in
the AF_INET6 case.
Fixes: f2aeed3a591f ("rxrpc: Fix error reception on AF_INET6 sockets")
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/local_object.c | 23 +++++++++++++----------
1 file changed, 13 insertions(+), 10 deletions(-)
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 81de7d889ffa..94d234e9c685 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -135,10 +135,10 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
}
switch (local->srx.transport.family) {
- case AF_INET:
- /* we want to receive ICMP errors */
+ case AF_INET6:
+ /* we want to receive ICMPv6 errors */
opt = 1;
- ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
@@ -146,19 +146,22 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
}
/* we want to set the don't fragment bit */
- opt = IP_PMTUDISC_DO;
- ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+ opt = IPV6_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
goto error;
}
- break;
- case AF_INET6:
+ /* Fall through and set IPv4 options too otherwise we don't get
+ * errors from IPv4 packets sent through the IPv6 socket.
+ */
+
+ case AF_INET:
/* we want to receive ICMP errors */
opt = 1;
- ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
+ ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
@@ -166,8 +169,8 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
}
/* we want to set the don't fragment bit */
- opt = IPV6_PMTUDISC_DO;
- ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
+ opt = IP_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
^ permalink raw reply related
* [PATCH net 6/8] rxrpc: Make service call handling more robust
From: David Howells @ 2018-09-28 10:10 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <153812939111.10469.179989653628053410.stgit@warthog.procyon.org.uk>
Make the following changes to improve the robustness of the code that sets
up a new service call:
(1) Cache the rxrpc_sock struct obtained in rxrpc_data_ready() to do a
service ID check and pass that along to rxrpc_new_incoming_call().
This means that I can remove the check from rxrpc_new_incoming_call()
without the need to worry about the socket attached to the local
endpoint getting replaced - which would invalidate the check.
(2) Cache the rxrpc_peer struct, thereby allowing the peer search to be
done once. The peer is passed to rxrpc_new_incoming_call(), thereby
saving the need to repeat the search.
This also reduces the possibility of rxrpc_publish_service_conn()
BUG()'ing due to the detection of a duplicate connection, despite the
initial search done by rxrpc_find_connection_rcu() having turned up
nothing.
This BUG() shouldn't ever get hit since rxrpc_data_ready() *should* be
non-reentrant and the result of the initial search should still hold
true, but it has proven possible to hit.
I *think* this may be due to __rxrpc_lookup_peer_rcu() cutting short
the iteration over the hash table if it finds a matching peer with a
zero usage count, but I don't know for sure since it's only ever been
hit once that I know of.
Another possibility is that a bug in rxrpc_data_ready() that checked
the wrong byte in the header for the RXRPC_CLIENT_INITIATED flag
might've let through a packet that caused a spurious and invalid call
to be set up. That is addressed in another patch.
(3) Fix __rxrpc_lookup_peer_rcu() to skip peer records that have a zero
usage count rather than stopping and returning not found, just in case
there's another peer record behind it in the bucket.
(4) Don't search the peer records in rxrpc_alloc_incoming_call(), but
rather either use the peer cached in (2) or, if one wasn't found,
preemptively install a new one.
Fixes: 8496af50eb38 ("rxrpc: Use RCU to access a peer's service connection tree")
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/ar-internal.h | 8 +++++---
net/rxrpc/call_accept.c | 41 ++++++++++++-----------------------------
net/rxrpc/conn_object.c | 7 ++++++-
net/rxrpc/input.c | 7 ++++---
net/rxrpc/peer_object.c | 35 +++++++++++------------------------
5 files changed, 38 insertions(+), 60 deletions(-)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index e8861cb78070..c72686193d83 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -722,6 +722,8 @@ extern struct workqueue_struct *rxrpc_workqueue;
int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t);
void rxrpc_discard_prealloc(struct rxrpc_sock *);
struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *,
+ struct rxrpc_sock *,
+ struct rxrpc_peer *,
struct rxrpc_connection *,
struct sk_buff *);
void rxrpc_accept_incoming_calls(struct rxrpc_local *);
@@ -913,7 +915,8 @@ extern unsigned int rxrpc_closed_conn_expiry;
struct rxrpc_connection *rxrpc_alloc_connection(gfp_t);
struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *,
- struct sk_buff *);
+ struct sk_buff *,
+ struct rxrpc_peer **);
void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *);
void rxrpc_disconnect_call(struct rxrpc_call *);
void rxrpc_kill_connection(struct rxrpc_connection *);
@@ -1049,8 +1052,7 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *,
struct sockaddr_rxrpc *, gfp_t);
struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t);
-struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *,
- struct rxrpc_peer *);
+void rxrpc_new_incoming_peer(struct rxrpc_local *, struct rxrpc_peer *);
void rxrpc_destroy_all_peers(struct rxrpc_net *);
struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *);
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *);
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index e88f131c1d7f..9c7f26d06a52 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -249,11 +249,11 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
*/
static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
struct rxrpc_local *local,
+ struct rxrpc_peer *peer,
struct rxrpc_connection *conn,
struct sk_buff *skb)
{
struct rxrpc_backlog *b = rx->backlog;
- struct rxrpc_peer *peer, *xpeer;
struct rxrpc_call *call;
unsigned short call_head, conn_head, peer_head;
unsigned short call_tail, conn_tail, peer_tail;
@@ -276,21 +276,18 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
return NULL;
if (!conn) {
- /* No connection. We're going to need a peer to start off
- * with. If one doesn't yet exist, use a spare from the
- * preallocation set. We dump the address into the spare in
- * anticipation - and to save on stack space.
- */
- xpeer = b->peer_backlog[peer_tail];
- if (rxrpc_extract_addr_from_skb(local, &xpeer->srx, skb) < 0)
- return NULL;
-
- peer = rxrpc_lookup_incoming_peer(local, xpeer);
- if (peer == xpeer) {
+ if (peer && !rxrpc_get_peer_maybe(peer))
+ peer = NULL;
+ if (!peer) {
+ peer = b->peer_backlog[peer_tail];
+ if (rxrpc_extract_addr_from_skb(local, &peer->srx, skb) < 0)
+ return NULL;
b->peer_backlog[peer_tail] = NULL;
smp_store_release(&b->peer_backlog_tail,
(peer_tail + 1) &
(RXRPC_BACKLOG_MAX - 1));
+
+ rxrpc_new_incoming_peer(local, peer);
}
/* Now allocate and set up the connection */
@@ -335,30 +332,16 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
* The call is returned with the user access mutex held.
*/
struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
+ struct rxrpc_sock *rx,
+ struct rxrpc_peer *peer,
struct rxrpc_connection *conn,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- struct rxrpc_sock *rx;
struct rxrpc_call *call;
- u16 service_id = sp->hdr.serviceId;
_enter("");
- /* Get the socket providing the service */
- rx = rcu_dereference(local->service);
- if (rx && (service_id == rx->srx.srx_service ||
- service_id == rx->second_service))
- goto found_service;
-
- trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EOPNOTSUPP);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = RX_INVALID_OPERATION;
- _leave(" = NULL [service]");
- return NULL;
-
-found_service:
spin_lock(&rx->incoming_lock);
if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
rx->sk.sk_state == RXRPC_CLOSE) {
@@ -371,7 +354,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
goto out;
}
- call = rxrpc_alloc_incoming_call(rx, local, conn, skb);
+ call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb);
if (!call) {
skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
_leave(" = NULL [busy]");
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 390ba50cfab4..b4438f98dc5c 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -69,10 +69,14 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
* If successful, a pointer to the connection is returned, but no ref is taken.
* NULL is returned if there is no match.
*
+ * When searching for a service call, if we find a peer but no connection, we
+ * return that through *_peer in case we need to create a new service call.
+ *
* The caller must be holding the RCU read lock.
*/
struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ struct rxrpc_peer **_peer)
{
struct rxrpc_connection *conn;
struct rxrpc_conn_proto k;
@@ -104,6 +108,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
peer = rxrpc_lookup_peer_rcu(local, &srx);
if (!peer)
goto not_found;
+ *_peer = peer;
conn = rxrpc_find_service_conn_rcu(peer, skb);
if (!conn || atomic_read(&conn->usage) == 0)
goto not_found;
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index a569e9e010d1..800f5b8a1baa 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1128,7 +1128,8 @@ void rxrpc_data_ready(struct sock *udp_sk)
struct rxrpc_call *call = NULL;
struct rxrpc_skb_priv *sp;
struct rxrpc_local *local = udp_sk->sk_user_data;
- struct rxrpc_sock *rx;
+ struct rxrpc_peer *peer = NULL;
+ struct rxrpc_sock *rx = NULL;
struct sk_buff *skb;
unsigned int channel;
int ret, skew = 0;
@@ -1250,7 +1251,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
}
}
- conn = rxrpc_find_connection_rcu(local, skb);
+ conn = rxrpc_find_connection_rcu(local, skb, &peer);
if (conn) {
if (sp->hdr.securityIndex != conn->security_ix)
goto wrong_security;
@@ -1339,7 +1340,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
goto bad_message_unlock;
if (sp->hdr.seq != 1)
goto discard_unlock;
- call = rxrpc_new_incoming_call(local, conn, skb);
+ call = rxrpc_new_incoming_call(local, rx, peer, conn, skb);
if (!call) {
rcu_read_unlock();
goto reject_packet;
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 1dc7648e3eff..70083e8fb6e5 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -124,11 +124,9 @@ static struct rxrpc_peer *__rxrpc_lookup_peer_rcu(
struct rxrpc_net *rxnet = local->rxnet;
hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) {
- if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) {
- if (atomic_read(&peer->usage) == 0)
- return NULL;
+ if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0 &&
+ atomic_read(&peer->usage) > 0)
return peer;
- }
}
return NULL;
@@ -299,34 +297,23 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
}
/*
- * Set up a new incoming peer. The address is prestored in the preallocated
- * peer.
+ * Set up a new incoming peer. There shouldn't be any other matching peers
+ * since we've already done a search in the list from the non-reentrant context
+ * (the data_ready handler) that is the only place we can add new peers.
*/
-struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local,
- struct rxrpc_peer *prealloc)
+void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
{
- struct rxrpc_peer *peer;
struct rxrpc_net *rxnet = local->rxnet;
unsigned long hash_key;
- hash_key = rxrpc_peer_hash_key(local, &prealloc->srx);
- prealloc->local = local;
- rxrpc_init_peer(prealloc, hash_key);
+ hash_key = rxrpc_peer_hash_key(local, &peer->srx);
+ peer->local = local;
+ rxrpc_init_peer(peer, hash_key);
spin_lock(&rxnet->peer_hash_lock);
-
- /* Need to check that we aren't racing with someone else */
- peer = __rxrpc_lookup_peer_rcu(local, &prealloc->srx, hash_key);
- if (peer && !rxrpc_get_peer_maybe(peer))
- peer = NULL;
- if (!peer) {
- peer = prealloc;
- hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
- list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
- }
-
+ hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
+ list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
spin_unlock(&rxnet->peer_hash_lock);
- return peer;
}
/*
^ permalink raw reply related
* [PATCH net 5/8] rxrpc: Improve up-front incoming packet checking
From: David Howells @ 2018-09-28 10:10 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <153812939111.10469.179989653628053410.stgit@warthog.procyon.org.uk>
Do more up-front checking on incoming packets to weed out invalid ones and
also ones aimed at services that we don't support.
Whilst we're at it, replace the clearing of call and skew if we don't find
a connection with just initialising the variables to zero at the top of the
function.
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/input.c | 63 ++++++++++++++++++++++++++++++++++++++++----------
net/rxrpc/protocol.h | 15 ------------
2 files changed, 50 insertions(+), 28 deletions(-)
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index b0f12471f5e7..a569e9e010d1 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1125,12 +1125,13 @@ void rxrpc_data_ready(struct sock *udp_sk)
{
struct rxrpc_connection *conn;
struct rxrpc_channel *chan;
- struct rxrpc_call *call;
+ struct rxrpc_call *call = NULL;
struct rxrpc_skb_priv *sp;
struct rxrpc_local *local = udp_sk->sk_user_data;
+ struct rxrpc_sock *rx;
struct sk_buff *skb;
unsigned int channel;
- int ret, skew;
+ int ret, skew = 0;
_enter("%p", udp_sk);
@@ -1181,12 +1182,6 @@ void rxrpc_data_ready(struct sock *udp_sk)
trace_rxrpc_rx_packet(sp);
- if (sp->hdr.type >= RXRPC_N_PACKET_TYPES ||
- !((RXRPC_SUPPORTED_PACKET_TYPES >> sp->hdr.type) & 1)) {
- _proto("Rx Bad Packet Type %u", sp->hdr.type);
- goto bad_message;
- }
-
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_VERSION:
if (rxrpc_to_client(sp))
@@ -1198,24 +1193,63 @@ void rxrpc_data_ready(struct sock *udp_sk)
if (rxrpc_to_server(sp))
goto discard;
/* Fall through */
+ case RXRPC_PACKET_TYPE_ACK:
+ case RXRPC_PACKET_TYPE_ACKALL:
+ if (sp->hdr.callNumber == 0)
+ goto bad_message;
+ /* Fall through */
+ case RXRPC_PACKET_TYPE_ABORT:
+ break;
case RXRPC_PACKET_TYPE_DATA:
- if (sp->hdr.callNumber == 0)
+ if (sp->hdr.callNumber == 0 ||
+ sp->hdr.seq == 0)
goto bad_message;
if (sp->hdr.flags & RXRPC_JUMBO_PACKET &&
!rxrpc_validate_jumbo(skb))
goto bad_message;
break;
+ case RXRPC_PACKET_TYPE_CHALLENGE:
+ if (rxrpc_to_server(sp))
+ goto discard;
+ break;
+ case RXRPC_PACKET_TYPE_RESPONSE:
+ if (rxrpc_to_client(sp))
+ goto discard;
+ break;
+
/* Packet types 9-11 should just be ignored. */
case RXRPC_PACKET_TYPE_PARAMS:
case RXRPC_PACKET_TYPE_10:
case RXRPC_PACKET_TYPE_11:
goto discard;
+
+ default:
+ _proto("Rx Bad Packet Type %u", sp->hdr.type);
+ goto bad_message;
}
+ if (sp->hdr.serviceId == 0)
+ goto bad_message;
+
rcu_read_lock();
+ if (rxrpc_to_server(sp)) {
+ /* Weed out packets to services we're not offering. Packets
+ * that would begin a call are explicitly rejected and the rest
+ * are just discarded.
+ */
+ rx = rcu_dereference(local->service);
+ if (!rx || (sp->hdr.serviceId != rx->srx.srx_service &&
+ sp->hdr.serviceId != rx->second_service)) {
+ if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
+ sp->hdr.seq == 1)
+ goto unsupported_service;
+ goto discard_unlock;
+ }
+ }
+
conn = rxrpc_find_connection_rcu(local, skb);
if (conn) {
if (sp->hdr.securityIndex != conn->security_ix)
@@ -1297,14 +1331,10 @@ void rxrpc_data_ready(struct sock *udp_sk)
if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags))
set_bit(RXRPC_CALL_RX_HEARD, &call->flags);
}
- } else {
- skew = 0;
- call = NULL;
}
if (!call || atomic_read(&call->usage) == 0) {
if (rxrpc_to_client(sp) ||
- sp->hdr.callNumber == 0 ||
sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
goto bad_message_unlock;
if (sp->hdr.seq != 1)
@@ -1340,6 +1370,13 @@ void rxrpc_data_ready(struct sock *udp_sk)
skb->priority = RXKADINCONSISTENCY;
goto post_abort;
+unsupported_service:
+ rcu_read_unlock();
+ trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ RX_INVALID_OPERATION, EOPNOTSUPP);
+ skb->priority = RX_INVALID_OPERATION;
+ goto post_abort;
+
reupgrade:
rcu_read_unlock();
trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h
index 93da73bf7098..f9cb83c938f3 100644
--- a/net/rxrpc/protocol.h
+++ b/net/rxrpc/protocol.h
@@ -50,7 +50,6 @@ struct rxrpc_wire_header {
#define RXRPC_PACKET_TYPE_10 10 /* Ignored */
#define RXRPC_PACKET_TYPE_11 11 /* Ignored */
#define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */
-#define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */
uint8_t flags; /* packet flags */
#define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */
@@ -72,20 +71,6 @@ struct rxrpc_wire_header {
} __packed;
-#define RXRPC_SUPPORTED_PACKET_TYPES ( \
- (1 << RXRPC_PACKET_TYPE_DATA) | \
- (1 << RXRPC_PACKET_TYPE_ACK) | \
- (1 << RXRPC_PACKET_TYPE_BUSY) | \
- (1 << RXRPC_PACKET_TYPE_ABORT) | \
- (1 << RXRPC_PACKET_TYPE_ACKALL) | \
- (1 << RXRPC_PACKET_TYPE_CHALLENGE) | \
- (1 << RXRPC_PACKET_TYPE_RESPONSE) | \
- /*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \
- (1 << RXRPC_PACKET_TYPE_PARAMS) | \
- (1 << RXRPC_PACKET_TYPE_10) | \
- (1 << RXRPC_PACKET_TYPE_11) | \
- (1 << RXRPC_PACKET_TYPE_VERSION))
-
/*****************************************************************************/
/*
* jumbo packet secondary header
^ permalink raw reply related
* [PATCH net 3/8] rxrpc: Fix RTT gathering
From: David Howells @ 2018-09-28 10:10 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <153812939111.10469.179989653628053410.stgit@warthog.procyon.org.uk>
Fix RTT information gathering in AF_RXRPC by the following means:
(1) Enable Rx timestamping on the transport socket with SO_TIMESTAMPNS.
(2) If the sk_buff doesn't have a timestamp set when rxrpc_data_ready()
collects it, set it at that point.
(3) Allow ACKs to be requested on the last packet of a client call, but
not a service call. We need to be careful lest we undo:
bf7d620abf22c321208a4da4f435e7af52551a21
Author: David Howells <dhowells@redhat.com>
Date: Thu Oct 6 08:11:51 2016 +0100
rxrpc: Don't request an ACK on the last DATA packet of a call's Tx phase
but that only really applies to service calls that we're handling,
since the client side gets to send the final ACK (or not).
(4) When about to transmit an ACK or DATA packet, record the Tx timestamp
before only; don't update the timestamp afterwards.
(5) Switch the ordering between recording the serial and recording the
timestamp to always set the serial number first. The serial number
shouldn't be seen referenced by an ACK packet until we've transmitted
the packet bearing it - so in the Rx path, we don't need the timestamp
until we've checked the serial number.
Fixes: cf1a6474f807 ("rxrpc: Add per-peer RTT tracker")
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/input.c | 8 ++++++--
net/rxrpc/local_object.c | 9 +++++++++
net/rxrpc/output.c | 31 ++++++++++++++++++-------------
3 files changed, 33 insertions(+), 15 deletions(-)
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index ec299c627f77..7f9ed3a60b9a 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -622,13 +622,14 @@ static void rxrpc_input_requested_ack(struct rxrpc_call *call,
if (!skb)
continue;
+ sent_at = skb->tstamp;
+ smp_rmb(); /* Read timestamp before serial. */
sp = rxrpc_skb(skb);
if (sp->hdr.serial != orig_serial)
continue;
- smp_rmb();
- sent_at = skb->tstamp;
goto found;
}
+
return;
found:
@@ -1143,6 +1144,9 @@ void rxrpc_data_ready(struct sock *udp_sk)
return;
}
+ if (skb->tstamp == 0)
+ skb->tstamp = ktime_get_real();
+
rxrpc_new_skb(skb, rxrpc_skb_rx_received);
_net("recv skb %p", skb);
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 777c3ed4cfc0..81de7d889ffa 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -173,6 +173,15 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
_debug("setsockopt failed");
goto error;
}
+
+ /* We want receive timestamps. */
+ opt = 1;
+ ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS,
+ (char *)&opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
break;
default:
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index ccf5de160444..8a4da3fe96df 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -124,7 +124,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
struct kvec iov[2];
rxrpc_serial_t serial;
rxrpc_seq_t hard_ack, top;
- ktime_t now;
size_t len, n;
int ret;
u8 reason;
@@ -196,9 +195,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
/* We need to stick a time in before we send the packet in case
* the reply gets back before kernel_sendmsg() completes - but
* asking UDP to send the packet can take a relatively long
- * time, so we update the time after, on the assumption that
- * the packet transmission is more likely to happen towards the
- * end of the kernel_sendmsg() call.
+ * time.
*/
call->ping_time = ktime_get_real();
set_bit(RXRPC_CALL_PINGING, &call->flags);
@@ -206,9 +203,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
}
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
- now = ktime_get_real();
- if (ping)
- call->ping_time = now;
conn->params.peer->last_tx_at = ktime_get_seconds();
if (ret < 0)
trace_rxrpc_tx_fail(call->debug_id, serial, ret,
@@ -363,8 +357,14 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
/* If our RTT cache needs working on, request an ACK. Also request
* ACKs if a DATA packet appears to have been lost.
+ *
+ * However, we mustn't request an ACK on the last reply packet of a
+ * service call, lest OpenAFS incorrectly send us an ACK with some
+ * soft-ACKs in it and then never follow up with a proper hard ACK.
*/
- if (!(sp->hdr.flags & RXRPC_LAST_PACKET) &&
+ if ((!(sp->hdr.flags & RXRPC_LAST_PACKET) ||
+ rxrpc_to_server(sp)
+ ) &&
(test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
retrans ||
call->cong_mode == RXRPC_CALL_SLOW_START ||
@@ -390,6 +390,11 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
goto send_fragmentable;
down_read(&conn->params.local->defrag_sem);
+
+ sp->hdr.serial = serial;
+ smp_wmb(); /* Set serial before timestamp */
+ skb->tstamp = ktime_get_real();
+
/* send the packet by UDP
* - returns -EMSGSIZE if UDP would have to fragment the packet
* to go out of the interface
@@ -413,12 +418,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags,
retrans, lost);
if (ret >= 0) {
- ktime_t now = ktime_get_real();
- skb->tstamp = now;
- smp_wmb();
- sp->hdr.serial = serial;
if (whdr.flags & RXRPC_REQUEST_ACK) {
- call->peer->rtt_last_req = now;
+ call->peer->rtt_last_req = skb->tstamp;
trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
if (call->peer->rtt_usage > 1) {
unsigned long nowj = jiffies, ack_lost_at;
@@ -457,6 +458,10 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
down_write(&conn->params.local->defrag_sem);
+ sp->hdr.serial = serial;
+ smp_wmb(); /* Set serial before timestamp */
+ skb->tstamp = ktime_get_real();
+
switch (conn->params.local->srx.transport.family) {
case AF_INET:
opt = IP_PMTUDISC_DONT;
^ permalink raw reply related
* [PATCH net 2/8] rxrpc: Fix checks as to whether we should set up a new call
From: David Howells @ 2018-09-28 10:10 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <153812939111.10469.179989653628053410.stgit@warthog.procyon.org.uk>
There's a check in rxrpc_data_ready() that's checking the CLIENT_INITIATED
flag in the packet type field rather than in the packet flags field.
Fix this by creating a pair of helper functions to check whether the packet
is going to the client or to the server and use them generally.
Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code")
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/ar-internal.h | 10 ++++++++++
net/rxrpc/conn_object.c | 2 +-
net/rxrpc/input.c | 12 ++++--------
3 files changed, 15 insertions(+), 9 deletions(-)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index c97558710421..9fcb3e197b14 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -463,6 +463,16 @@ struct rxrpc_connection {
u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */
};
+static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp)
+{
+ return sp->hdr.flags & RXRPC_CLIENT_INITIATED;
+}
+
+static inline bool rxrpc_to_client(const struct rxrpc_skb_priv *sp)
+{
+ return !rxrpc_to_server(sp);
+}
+
/*
* Flags in call->flags.
*/
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 1746b48cb165..390ba50cfab4 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -96,7 +96,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
k.epoch = sp->hdr.epoch;
k.cid = sp->hdr.cid & RXRPC_CIDMASK;
- if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) {
+ if (rxrpc_to_server(sp)) {
/* We need to look up service connections by the full protocol
* parameter set. We look up the peer first as an intermediate
* step and then the connection from the peer's tree.
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index cfdc199c6351..ec299c627f77 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1177,10 +1177,6 @@ void rxrpc_data_ready(struct sock *udp_sk)
trace_rxrpc_rx_packet(sp);
- _net("Rx RxRPC %s ep=%x call=%x:%x",
- sp->hdr.flags & RXRPC_CLIENT_INITIATED ? "ToServer" : "ToClient",
- sp->hdr.epoch, sp->hdr.cid, sp->hdr.callNumber);
-
if (sp->hdr.type >= RXRPC_N_PACKET_TYPES ||
!((RXRPC_SUPPORTED_PACKET_TYPES >> sp->hdr.type) & 1)) {
_proto("Rx Bad Packet Type %u", sp->hdr.type);
@@ -1189,13 +1185,13 @@ void rxrpc_data_ready(struct sock *udp_sk)
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_VERSION:
- if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED))
+ if (rxrpc_to_client(sp))
goto discard;
rxrpc_post_packet_to_local(local, skb);
goto out;
case RXRPC_PACKET_TYPE_BUSY:
- if (sp->hdr.flags & RXRPC_CLIENT_INITIATED)
+ if (rxrpc_to_server(sp))
goto discard;
/* Fall through */
@@ -1280,7 +1276,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
call = rcu_dereference(chan->call);
if (sp->hdr.callNumber > chan->call_id) {
- if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) {
+ if (rxrpc_to_client(sp)) {
rcu_read_unlock();
goto reject_packet;
}
@@ -1303,7 +1299,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
}
if (!call || atomic_read(&call->usage) == 0) {
- if (!(sp->hdr.type & RXRPC_CLIENT_INITIATED) ||
+ if (rxrpc_to_client(sp) ||
sp->hdr.callNumber == 0 ||
sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
goto bad_message_unlock;
^ permalink raw reply related
* [PATCH net 1/8] rxrpc: Remove dup code from rxrpc_find_connection_rcu()
From: David Howells @ 2018-09-28 10:10 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <153812939111.10469.179989653628053410.stgit@warthog.procyon.org.uk>
rxrpc_find_connection_rcu() initialises variable k twice with the same
information. Remove one of the initialisations.
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/conn_object.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 77440a356b14..1746b48cb165 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -85,9 +85,6 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0)
goto not_found;
- k.epoch = sp->hdr.epoch;
- k.cid = sp->hdr.cid & RXRPC_CIDMASK;
-
/* We may have to handle mixing IPv4 and IPv6 */
if (srx.transport.family != local->srx.transport.family) {
pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n",
^ permalink raw reply related
* [PATCH net 0/8] rxrpc: Fixes
From: David Howells @ 2018-09-28 10:09 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
Here are some miscellaneous fixes for AF_RXRPC:
(1) Remove a duplicate variable initialisation.
(2) Fix one of the checks made when we decide to set up a new incoming
service call in which a flag is being checked in the wrong field of
the packet header. This check is abstracted out into helper
functions.
(3) Fix RTT gathering. The code has been trying to make use of socket
timestamps, but wasn't actually enabling them. The code has also been
recording a transmit time for the outgoing packet for which we're
going to measure the RTT after sending the message - but we can get
the incoming packet before we get to that and record a negative RTT.
(4) Fix the emission of BUSY packets (we are emitting ABORTs instead).
(5) Improve error checking on incoming packets.
(6) Try to fix a bug in new service call handling whereby a BUG we should
never be able to reach somehow got triggered. Do this by moving much
of the checking as early as possible and not repeating it later
(depends on (5) above).
(7) Fix the sockopts set on a UDP6 socket to include the ones set on a
UDP4 socket so that we receive UDP4 errors and packet-too-large
notifications too.
(8) Fix the distribution of errors so that we do it at the point of
receiving an error in the UDP callback rather than deferring it
thereby cutting short any transmissions that would otherwise occur in
the window.
The patches are tagged here:
git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs.git
rxrpc-fixes-20180928
and can also be found on the following branch:
http://git.kernel.org/cgit/linux/kernel/git/dhowells/linux-fs.git/log/?h=rxrpc-fixes
David
---
David Howells (8):
rxrpc: Remove dup code from rxrpc_find_connection_rcu()
rxrpc: Fix checks as to whether we should set up a new call
rxrpc: Fix RTT gathering
rxrpc: Emit BUSY packets when supposed to rather than ABORTs
rxrpc: Improve up-front incoming packet checking
rxrpc: Make service call handling more robust
rxrpc: Fix transport sockopts to get IPv4 errors on an IPv6 socket
rxrpc: Fix error distribution
include/trace/events/rxrpc.h | 4 --
net/rxrpc/ar-internal.h | 36 +++++++++--------
net/rxrpc/call_accept.c | 45 +++++++--------------
net/rxrpc/call_object.c | 2 -
net/rxrpc/conn_client.c | 4 +-
net/rxrpc/conn_object.c | 14 ++++---
net/rxrpc/input.c | 90 ++++++++++++++++++++++++++++++------------
net/rxrpc/local_object.c | 32 ++++++++++-----
net/rxrpc/output.c | 54 +++++++++++++++++--------
net/rxrpc/peer_event.c | 46 +++++----------------
net/rxrpc/peer_object.c | 52 +++++-------------------
net/rxrpc/protocol.h | 15 -------
12 files changed, 189 insertions(+), 205 deletions(-)
^ permalink raw reply
* Re: [PATCH v3 bpf-next 10/10] selftests/bpf: cgroup local storage-based network counters
From: Roman Gushchin @ 2018-09-28 10:08 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: netdev, Song Liu, linux-kernel, kernel-team, Daniel Borkmann,
Alexei Starovoitov
In-Reply-To: <20180928085356.56xe7javtd6cdfz6@ast-mbp.dhcp.thefacebook.com>
On Fri, Sep 28, 2018 at 10:53:58AM +0200, Alexei Starovoitov wrote:
> On Wed, Sep 26, 2018 at 12:33:26PM +0100, Roman Gushchin wrote:
> > This commit adds a bpf kselftest, which demonstrates how percpu
> > and shared cgroup local storage can be used for efficient lookup-free
> > network accounting.
> >
> > Cgroup local storage provides generic memory area with a very efficient
> > lookup free access. To avoid expensive atomic operations for each
> > packet, per-cpu cgroup local storage is used. Each packet is initially
> > charged to a per-cpu counter, and only if the counter reaches certain
> > value (32 in this case), the charge is moved into the global atomic
> > counter. This allows to amortize atomic operations, keeping reasonable
> > accuracy.
> >
> > The test also implements a naive network traffic throttling, mostly to
> > demonstrate the possibility of bpf cgroup--based network bandwidth
> > control.
> >
> > Expected output:
> > ./test_netcnt
> > test_netcnt:PASS
> >
> > Signed-off-by: Roman Gushchin <guro@fb.com>
> > Acked-by: Song Liu <songliubraving@fb.com>
> > Cc: Daniel Borkmann <daniel@iogearbox.net>
> > Cc: Alexei Starovoitov <ast@kernel.org>
> > ---
> > tools/testing/selftests/bpf/Makefile | 6 +-
> > tools/testing/selftests/bpf/netcnt_common.h | 23 +++
> > tools/testing/selftests/bpf/netcnt_prog.c | 71 +++++++++
> > tools/testing/selftests/bpf/test_netcnt.c | 153 ++++++++++++++++++++
> > 4 files changed, 251 insertions(+), 2 deletions(-)
> > create mode 100644 tools/testing/selftests/bpf/netcnt_common.h
> > create mode 100644 tools/testing/selftests/bpf/netcnt_prog.c
> > create mode 100644 tools/testing/selftests/bpf/test_netcnt.c
> >
> > diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
> > index fd3851d5c079..5443399dd3a1 100644
> > --- a/tools/testing/selftests/bpf/Makefile
> > +++ b/tools/testing/selftests/bpf/Makefile
> > @@ -23,7 +23,8 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
> > TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
> > test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
> > test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
> > - test_socket_cookie test_cgroup_storage test_select_reuseport
> > + test_socket_cookie test_cgroup_storage test_select_reuseport \
> > + test_netcnt
> >
> > TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
> > test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
> > @@ -35,7 +36,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
> > test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
> > test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
> > get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
> > - test_skb_cgroup_id_kern.o bpf_flow.o
> > + test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o
> >
> > # Order correspond to 'make run_tests' order
> > TEST_PROGS := test_kmod.sh \
> > @@ -72,6 +73,7 @@ $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
> > $(OUTPUT)/test_progs: trace_helpers.c
> > $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
> > $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
> > +$(OUTPUT)/test_netcnt: cgroup_helpers.c
> >
> > .PHONY: force
> >
> > diff --git a/tools/testing/selftests/bpf/netcnt_common.h b/tools/testing/selftests/bpf/netcnt_common.h
> > new file mode 100644
> > index 000000000000..0e10fc276c2a
> > --- /dev/null
> > +++ b/tools/testing/selftests/bpf/netcnt_common.h
> > @@ -0,0 +1,23 @@
> > +#ifndef __NETCNT_COMMON_H
> > +#define __NETCNT_COMMON_H
> > +
> > +#include <linux/types.h>
> > +
> > +#define MAX_PERCPU_PACKETS 32
> > +
> > +struct percpu_net_cnt {
> > + __u64 packets;
> > + __u64 bytes;
> > +
> > + __u64 prev_ts;
> > +
> > + __u64 prev_packets;
> > + __u64 prev_bytes;
> > +};
> > +
> > +struct net_cnt {
> > + __u64 packets;
> > + __u64 bytes;
> > +};
> > +
> > +#endif
> > diff --git a/tools/testing/selftests/bpf/netcnt_prog.c b/tools/testing/selftests/bpf/netcnt_prog.c
> > new file mode 100644
> > index 000000000000..1198abca1360
> > --- /dev/null
> > +++ b/tools/testing/selftests/bpf/netcnt_prog.c
> > @@ -0,0 +1,71 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +#include <linux/bpf.h>
> > +#include <linux/version.h>
> > +
> > +#include "bpf_helpers.h"
> > +#include "netcnt_common.h"
> > +
> > +#define MAX_BPS (3 * 1024 * 1024)
> > +
> > +#define REFRESH_TIME_NS 100000000
> > +#define NS_PER_SEC 1000000000
> > +
> > +struct bpf_map_def SEC("maps") percpu_netcnt = {
> > + .type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
> > + .key_size = sizeof(struct bpf_cgroup_storage_key),
> > + .value_size = sizeof(struct percpu_net_cnt),
> > +};
> > +
> > +struct bpf_map_def SEC("maps") netcnt = {
> > + .type = BPF_MAP_TYPE_CGROUP_STORAGE,
> > + .key_size = sizeof(struct bpf_cgroup_storage_key),
> > + .value_size = sizeof(struct net_cnt),
> > +};
> > +
> > +SEC("cgroup/skb")
> > +int bpf_nextcnt(struct __sk_buff *skb)
> > +{
> > + struct percpu_net_cnt *percpu_cnt;
> > + char fmt[] = "%d %llu %llu\n";
> > + struct net_cnt *cnt;
> > + __u64 ts, dt;
> > + int ret;
> > +
> > + cnt = bpf_get_local_storage(&netcnt, 0);
> > + percpu_cnt = bpf_get_local_storage(&percpu_netcnt, 0);
> > +
> > + percpu_cnt->packets++;
> > + percpu_cnt->bytes += skb->len;
> > +
> > + if (percpu_cnt->packets > MAX_PERCPU_PACKETS) {
> > + __sync_fetch_and_add(&cnt->packets,
> > + percpu_cnt->packets);
> > + percpu_cnt->packets = 0;
> > +
> > + __sync_fetch_and_add(&cnt->bytes,
> > + percpu_cnt->bytes);
> > + percpu_cnt->bytes = 0;
> > + }
> > +
> > + ts = bpf_ktime_get_ns();
> > + dt = ts - percpu_cnt->prev_ts;
> > +
> > + dt *= MAX_BPS;
> > + dt /= NS_PER_SEC;
> > +
> > + if (cnt->bytes + percpu_cnt->bytes - percpu_cnt->prev_bytes < dt)
> > + ret = 1;
> > + else
> > + ret = 0;
> > +
> > + if (dt > REFRESH_TIME_NS) {
> > + percpu_cnt->prev_ts = ts;
> > + percpu_cnt->prev_packets = cnt->packets;
> > + percpu_cnt->prev_bytes = cnt->bytes;
> > + }
> > +
> > + return !!ret;
> > +}
> > +
> > +char _license[] SEC("license") = "GPL";
> > +__u32 _version SEC("version") = LINUX_VERSION_CODE;
> > diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c
> > new file mode 100644
> > index 000000000000..aa424f8db466
> > --- /dev/null
> > +++ b/tools/testing/selftests/bpf/test_netcnt.c
> > @@ -0,0 +1,153 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +#include <stdio.h>
> > +#include <stdlib.h>
> > +#include <string.h>
> > +#include <errno.h>
> > +#include <assert.h>
> > +#include <sys/sysinfo.h>
> > +#include <sys/time.h>
> > +
> > +#include <linux/bpf.h>
> > +#include <bpf/bpf.h>
> > +#include <bpf/libbpf.h>
> > +
> > +#include "cgroup_helpers.h"
> > +#include "bpf_rlimit.h"
> > +#include "netcnt_common.h"
> > +
> > +#define BPF_PROG "./netcnt_prog.o"
> > +#define TEST_CGROUP "/test-network-counters/"
> > +
> > +static int bpf_find_map(const char *test, struct bpf_object *obj,
> > + const char *name)
> > +{
> > + struct bpf_map *map;
> > +
> > + map = bpf_object__find_map_by_name(obj, name);
> > + if (!map) {
> > + printf("%s:FAIL:map '%s' not found\n", test, name);
> > + return -1;
> > + }
> > + return bpf_map__fd(map);
> > +}
> > +
> > +int main(int argc, char **argv)
> > +{
> > + struct percpu_net_cnt *percpu_netcnt;
> > + struct bpf_cgroup_storage_key key;
> > + int map_fd, percpu_map_fd;
> > + int error = EXIT_FAILURE;
> > + struct net_cnt netcnt;
> > + struct bpf_object *obj;
> > + int prog_fd, cgroup_fd;
> > + unsigned long packets;
> > + int cpu, nproc;
> > + __u32 prog_cnt;
> > +
> > + nproc = get_nprocs_conf();
> > + percpu_netcnt = malloc(sizeof(*percpu_netcnt) * nproc);
> > + if (!percpu_netcnt) {
> > + printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
> > + goto err;
> > + }
> > +
> > + if (bpf_prog_load(BPF_PROG, BPF_PROG_TYPE_CGROUP_SKB,
> > + &obj, &prog_fd)) {
> > + printf("Failed to load bpf program\n");
> > + goto out;
> > + }
> > +
> > + if (setup_cgroup_environment()) {
> > + printf("Failed to load bpf program\n");
> > + goto err;
> > + }
> > +
> > + /* Create a cgroup, get fd, and join it */
> > + cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
> > + if (!cgroup_fd) {
> > + printf("Failed to create test cgroup\n");
> > + goto err;
> > + }
> > +
> > + if (join_cgroup(TEST_CGROUP)) {
> > + printf("Failed to join cgroup\n");
> > + goto err;
> > + }
> > +
> > + /* Attach bpf program */
> > + if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
> > + printf("Failed to attach bpf program");
> > + goto err;
> > + }
> > +
> > + assert(system("ping localhost -s 500 -c 10000 -f -q > /dev/null") == 0);
> > +
> > + if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL,
> > + &prog_cnt)) {
> > + printf("Failed to query attached programs");
> > + goto err;
> > + }
> > +
> > + map_fd = bpf_find_map(__func__, obj, "netcnt");
> > + if (map_fd < 0) {
> > + printf("Failed to find bpf map with net counters");
> > + goto err;
> > + }
> > +
> > + percpu_map_fd = bpf_find_map(__func__, obj, "percpu_netcnt");
> > + if (percpu_map_fd < 0) {
> > + printf("Failed to find bpf map with percpu net counters");
> > + goto err;
> > + }
> > +
> > + if (bpf_map_get_next_key(map_fd, NULL, &key)) {
> > + printf("Failed to get key in cgroup storage\n");
> > + goto err;
> > + }
> > +
> > + if (bpf_map_lookup_elem(map_fd, &key, &netcnt)) {
> > + printf("Failed to lookup cgroup storage\n");
> > + goto err;
> > + }
> > +
> > + if (bpf_map_lookup_elem(percpu_map_fd, &key, &percpu_netcnt[0])) {
> > + printf("Failed to lookup percpu cgroup storage\n");
> > + goto err;
> > + }
> > +
> > + /* Some packets can be still in per-cpu cache, but not more than
> > + * MAX_PERCPU_PACKETS.
> > + */
> > + packets = netcnt.packets;
> > + for (cpu = 0; cpu < nproc; cpu++) {
> > + if (percpu_netcnt[cpu].packets > 32) {
>
> pls use MAX_PERCPU_PACKETS in the above check.
> could you also double check that if that #define is changed to 1k or so
> the exact "!= 10000" check below still works as expected?
Do you mean adding a new test with a different MAX_PERCPU_PACKETS?
>
> > + printf("Unexpected percpu value: %llu\n",
> > + percpu_netcnt[cpu].packets);
> > + goto err;
>
> > + }
> > +
> > + packets += percpu_netcnt[cpu].packets;
> > + }
> > +
> > + /* No packets should be lost */
> > + if (packets != 10000) {
> > + printf("Unexpected packet count: %lu\n", packets);
> > + goto err;
> > + }
> > +
> > + /* Let's check that bytes counter value is reasonable */
> > + if (netcnt.bytes < packets * 500 || netcnt.bytes > packets * 1500) {
>
> since packet count is accurate why byte count would vary ?
Tbh I'm not sure if the size of the packet here can vary depending
on the environment. Is there a nice way to get the expected size?
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox