diff options
27 files changed, 1555 insertions, 598 deletions
diff --git a/Documentation/networking/timestamping/txtimestamp.c b/Documentation/networking/timestamping/txtimestamp.c index 876f71c5625a..8778e684d482 100644 --- a/Documentation/networking/timestamping/txtimestamp.c +++ b/Documentation/networking/timestamping/txtimestamp.c @@ -59,14 +59,6 @@ #include <time.h> #include <unistd.h> -/* ugly hack to work around netinet/in.h and linux/ipv6.h conflicts */ -#ifndef in6_pktinfo -struct in6_pktinfo { - struct in6_addr ipi6_addr; - int ipi6_ifindex; -}; -#endif - /* command line parameters */ static int cfg_proto = SOCK_STREAM; static int cfg_ipproto = IPPROTO_TCP; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index 327d362fe275..009abd69385d 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -67,7 +67,6 @@ phy-mode = "rgmii"; interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_HIGH>, <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>; - fsl,magic-packet; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi index 6bfd0bc6e658..f1cd2147421d 100644 --- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi @@ -160,7 +160,6 @@ pinctrl-0 = <&pinctrl_enet>; phy-mode = "rgmii"; phy-reset-gpios = <&gpio1 25 0>; - fsl,magic-packet; status = "okay"; }; diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c index 2f7616889c3f..5057d61298b7 100644 --- a/arch/arm/mach-imx/mach-imx6q.c +++ b/arch/arm/mach-imx/mach-imx6q.c @@ -31,8 +31,6 @@ #include <linux/micrel_phy.h> #include <linux/mfd/syscon.h> #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h> -#include <linux/fec.h> -#include <linux/netdevice.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> #include <asm/system_misc.h> @@ -41,35 +39,6 @@ #include "cpuidle.h" #include "hardware.h" -static struct fec_platform_data fec_pdata; - -static void imx6q_fec_sleep_enable(int enabled) -{ - struct regmap *gpr; - - gpr = syscon_regmap_lookup_by_compatible("fsl,imx6q-iomuxc-gpr"); - if (!IS_ERR(gpr)) { - if (enabled) - regmap_update_bits(gpr, IOMUXC_GPR13, - IMX6Q_GPR13_ENET_STOP_REQ, - IMX6Q_GPR13_ENET_STOP_REQ); - - else - regmap_update_bits(gpr, IOMUXC_GPR13, - IMX6Q_GPR13_ENET_STOP_REQ, 0); - } else - pr_err("failed to find fsl,imx6q-iomux-gpr regmap\n"); -} - -static void __init imx6q_enet_plt_init(void) -{ - struct device_node *np; - - np = of_find_node_by_path("/soc/aips-bus@02100000/ethernet@02188000"); - if (np && of_get_property(np, "fsl,magic-packet", NULL)) - fec_pdata.sleep_mode_enable = imx6q_fec_sleep_enable; -} - /* For imx6q sabrelite board: set KSZ9021RN RGMII pad skew */ static int ksz9021rn_phy_fixup(struct phy_device *phydev) { @@ -292,12 +261,6 @@ static void __init imx6q_axi_init(void) } } -/* Add auxdata to pass platform data */ -static const struct of_dev_auxdata imx6q_auxdata_lookup[] __initconst = { - OF_DEV_AUXDATA("fsl,imx6q-fec", 0x02188000, NULL, &fec_pdata), - { /* sentinel */ } -}; - static void __init imx6q_init_machine(void) { struct device *parent; @@ -311,13 +274,11 @@ static void __init imx6q_init_machine(void) imx6q_enet_phy_init(); - of_platform_populate(NULL, of_default_bus_match_table, - imx6q_auxdata_lookup, parent); + of_platform_populate(NULL, of_default_bus_match_table, NULL, parent); imx_anatop_init(); cpu_is_imx6q() ? imx6q_pm_init() : imx6dl_pm_init(); imx6q_1588_init(); - imx6q_enet_plt_init(); imx6q_axi_init(); } diff --git a/arch/arm/mach-imx/mach-imx6sx.c b/arch/arm/mach-imx/mach-imx6sx.c index 747b012665f5..7a96c6577234 100644 --- a/arch/arm/mach-imx/mach-imx6sx.c +++ b/arch/arm/mach-imx/mach-imx6sx.c @@ -12,62 +12,12 @@ #include <linux/regmap.h> #include <linux/mfd/syscon.h> #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h> -#include <linux/fec.h> -#include <linux/netdevice.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> #include "common.h" #include "cpuidle.h" -static struct fec_platform_data fec_pdata[2]; - -static void imx6sx_fec1_sleep_enable(int enabled) -{ - struct regmap *gpr; - - gpr = syscon_regmap_lookup_by_compatible("fsl,imx6sx-iomuxc-gpr"); - if (!IS_ERR(gpr)) { - if (enabled) - regmap_update_bits(gpr, IOMUXC_GPR4, - IMX6SX_GPR4_FEC_ENET1_STOP_REQ, - IMX6SX_GPR4_FEC_ENET1_STOP_REQ); - else - regmap_update_bits(gpr, IOMUXC_GPR4, - IMX6SX_GPR4_FEC_ENET1_STOP_REQ, 0); - } else - pr_err("failed to find fsl,imx6sx-iomux-gpr regmap\n"); -} - -static void imx6sx_fec2_sleep_enable(int enabled) -{ - struct regmap *gpr; - - gpr = syscon_regmap_lookup_by_compatible("fsl,imx6sx-iomuxc-gpr"); - if (!IS_ERR(gpr)) { - if (enabled) - regmap_update_bits(gpr, IOMUXC_GPR4, - IMX6SX_GPR4_FEC_ENET2_STOP_REQ, - IMX6SX_GPR4_FEC_ENET2_STOP_REQ); - else - regmap_update_bits(gpr, IOMUXC_GPR4, - IMX6SX_GPR4_FEC_ENET2_STOP_REQ, 0); - } else - pr_err("failed to find fsl,imx6sx-iomux-gpr regmap\n"); -} - -static void __init imx6sx_enet_plt_init(void) -{ - struct device_node *np; - - np = of_find_node_by_path("/soc/aips-bus@02100000/ethernet@02188000"); - if (np && of_get_property(np, "fsl,magic-packet", NULL)) - fec_pdata[0].sleep_mode_enable = imx6sx_fec1_sleep_enable; - np = of_find_node_by_path("/soc/aips-bus@02100000/ethernet@021b4000"); - if (np && of_get_property(np, "fsl,magic-packet", NULL)) - fec_pdata[1].sleep_mode_enable = imx6sx_fec2_sleep_enable; -} - static int ar8031_phy_fixup(struct phy_device *dev) { u16 val; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 5ab5c3133acd..7c785b5e7757 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -290,11 +290,21 @@ enum chip_type { T5_LAST_REV = T5_A1, }; +struct devlog_params { + u32 memtype; /* which memory (EDC0, EDC1, MC) */ + u32 start; /* start of log in firmware memory */ + u32 size; /* size of log */ +}; + struct adapter_params { struct sge_params sge; struct tp_params tp; struct vpd_params vpd; struct pci_params pci; + struct devlog_params devlog; + enum pcie_memwin drv_memwin; + + unsigned int cim_la_size; unsigned int sf_size; /* serial flash size in bytes */ unsigned int sf_nsec; /* # of flash sectors */ @@ -1026,6 +1036,12 @@ int t4_mc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *parity); int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *parity); +int t4_cim_read(struct adapter *adap, unsigned int addr, unsigned int n, + unsigned int *valp); +int t4_cim_write(struct adapter *adap, unsigned int addr, unsigned int n, + const unsigned int *valp); +int t4_cim_read_la(struct adapter *adap, u32 *la_buf, unsigned int *wrptr); +void t4_read_cimq_cfg(struct adapter *adap, u16 *base, u16 *size, u16 *thres); const char *t4_get_port_type_description(enum fw_port_type port_type); void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p); void t4_read_mtu_tbl(struct adapter *adap, u16 *mtus, u8 *mtu_log); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index c98a350d857e..e9f348942eb0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -43,6 +43,526 @@ #include "cxgb4_debugfs.h" #include "l2t.h" +/* generic seq_file support for showing a table of size rows x width. */ +static void *seq_tab_get_idx(struct seq_tab *tb, loff_t pos) +{ + pos -= tb->skip_first; + return pos >= tb->rows ? NULL : &tb->data[pos * tb->width]; +} + +static void *seq_tab_start(struct seq_file *seq, loff_t *pos) +{ + struct seq_tab *tb = seq->private; + + if (tb->skip_first && *pos == 0) + return SEQ_START_TOKEN; + + return seq_tab_get_idx(tb, *pos); +} + +static void *seq_tab_next(struct seq_file *seq, void *v, loff_t *pos) +{ + v = seq_tab_get_idx(seq->private, *pos + 1); + if (v) + ++*pos; + return v; +} + +static void seq_tab_stop(struct seq_file *seq, void *v) +{ +} + +static int seq_tab_show(struct seq_file *seq, void *v) +{ + const struct seq_tab *tb = seq->private; + + return tb->show(seq, v, ((char *)v - tb->data) / tb->width); +} + +static const struct seq_operations seq_tab_ops = { + .start = seq_tab_start, + .next = seq_tab_next, + .stop = seq_tab_stop, + .show = seq_tab_show +}; + +struct seq_tab *seq_open_tab(struct file *f, unsigned int rows, + unsigned int width, unsigned int have_header, + int (*show)(struct seq_file *seq, void *v, int i)) +{ + struct seq_tab *p; + + p = __seq_open_private(f, &seq_tab_ops, sizeof(*p) + rows * width); + if (p) { + p->show = show; + p->rows = rows; + p->width = width; + p->skip_first = have_header != 0; + } + return p; +} + +static int cim_la_show(struct seq_file *seq, void *v, int idx) +{ + if (v == SEQ_START_TOKEN) + seq_puts(seq, "Status Data PC LS0Stat LS0Addr " + " LS0Data\n"); + else { + const u32 *p = v; + + seq_printf(seq, + " %02x %x%07x %x%07x %08x %08x %08x%08x%08x%08x\n", + (p[0] >> 4) & 0xff, p[0] & 0xf, p[1] >> 4, + p[1] & 0xf, p[2] >> 4, p[2] & 0xf, p[3], p[4], p[5], + p[6], p[7]); + } + return 0; +} + +static int cim_la_show_3in1(struct seq_file *seq, void *v, int idx) +{ + if (v == SEQ_START_TOKEN) { + seq_puts(seq, "Status Data PC\n"); + } else { + const u32 *p = v; + + seq_printf(seq, " %02x %08x %08x\n", p[5] & 0xff, p[6], + p[7]); + seq_printf(seq, " %02x %02x%06x %02x%06x\n", + (p[3] >> 8) & 0xff, p[3] & 0xff, p[4] >> 8, + p[4] & 0xff, p[5] >> 8); + seq_printf(seq, " %02x %x%07x %x%07x\n", (p[0] >> 4) & 0xff, + p[0] & 0xf, p[1] >> 4, p[1] & 0xf, p[2] >> 4); + } + return 0; +} + +static int cim_la_open(struct inode *inode, struct file *file) +{ + int ret; + unsigned int cfg; + struct seq_tab *p; + struct adapter *adap = inode->i_private; + + ret = t4_cim_read(adap, UP_UP_DBG_LA_CFG_A, 1, &cfg); + if (ret) + return ret; + + p = seq_open_tab(file, adap->params.cim_la_size / 8, 8 * sizeof(u32), 1, + cfg & UPDBGLACAPTPCONLY_F ? + cim_la_show_3in1 : cim_la_show); + if (!p) + return -ENOMEM; + + ret = t4_cim_read_la(adap, (u32 *)p->data, NULL); + if (ret) + seq_release_private(inode, file); + return ret; +} + +static const struct file_operations cim_la_fops = { + .owner = THIS_MODULE, + .open = cim_la_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private +}; + +static int cim_qcfg_show(struct seq_file *seq, void *v) +{ + static const char * const qname[] = { + "TP0", "TP1", "ULP", "SGE0", "SGE1", "NC-SI", + "ULP0", "ULP1", "ULP2", "ULP3", "SGE", "NC-SI", + "SGE0-RX", "SGE1-RX" + }; + + int i; + struct adapter *adap = seq->private; + u16 base[CIM_NUM_IBQ + CIM_NUM_OBQ_T5]; + u16 size[CIM_NUM_IBQ + CIM_NUM_OBQ_T5]; + u32 stat[(4 * (CIM_NUM_IBQ + CIM_NUM_OBQ_T5))]; + u16 thres[CIM_NUM_IBQ]; + u32 obq_wr_t4[2 * CIM_NUM_OBQ], *wr; + u32 obq_wr_t5[2 * CIM_NUM_OBQ_T5]; + u32 *p = stat; + int cim_num_obq = is_t4(adap->params.chip) ? + CIM_NUM_OBQ : CIM_NUM_OBQ_T5; + + i = t4_cim_read(adap, is_t4(adap->params.chip) ? UP_IBQ_0_RDADDR_A : + UP_IBQ_0_SHADOW_RDADDR_A, + ARRAY_SIZE(stat), stat); + if (!i) { + if (is_t4(adap->params.chip)) { + i = t4_cim_read(adap, UP_OBQ_0_REALADDR_A, + ARRAY_SIZE(obq_wr_t4), obq_wr_t4); + wr = obq_wr_t4; + } else { + i = t4_cim_read(adap, UP_OBQ_0_SHADOW_REALADDR_A, + ARRAY_SIZE(obq_wr_t5), obq_wr_t5); + wr = obq_wr_t5; + } + } + if (i) + return i; + + t4_read_cimq_cfg(adap, base, size, thres); + + seq_printf(seq, + " Queue Base Size Thres RdPtr WrPtr SOP EOP Avail\n"); + for (i = 0; i < CIM_NUM_IBQ; i++, p += 4) + seq_printf(seq, "%7s %5x %5u %5u %6x %4x %4u %4u %5u\n", + qname[i], base[i], size[i], thres[i], + IBQRDADDR_G(p[0]), IBQWRADDR_G(p[1]), + QUESOPCNT_G(p[3]), QUEEOPCNT_G(p[3]), + QUEREMFLITS_G(p[2]) * 16); + for ( ; i < CIM_NUM_IBQ + cim_num_obq; i++, p += 4, wr += 2) + seq_printf(seq, "%7s %5x %5u %12x %4x %4u %4u %5u\n", + qname[i], base[i], size[i], + QUERDADDR_G(p[0]) & 0x3fff, wr[0] - base[i], + QUESOPCNT_G(p[3]), QUEEOPCNT_G(p[3]), + QUEREMFLITS_G(p[2]) * 16); + return 0; +} + +static int cim_qcfg_open(struct inode *inode, struct file *file) +{ + return single_open(file, cim_qcfg_show, inode->i_private); +} + +static const struct file_operations cim_qcfg_fops = { + .owner = THIS_MODULE, + .open = cim_qcfg_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +/* Firmware Device Log dump. */ +static const char * const devlog_level_strings[] = { + [FW_DEVLOG_LEVEL_EMERG] = "EMERG", + [FW_DEVLOG_LEVEL_CRIT] = "CRIT", + [FW_DEVLOG_LEVEL_ERR] = "ERR", + [FW_DEVLOG_LEVEL_NOTICE] = "NOTICE", + [FW_DEVLOG_LEVEL_INFO] = "INFO", + [FW_DEVLOG_LEVEL_DEBUG] = "DEBUG" +}; + +static const char * const devlog_facility_strings[] = { + [FW_DEVLOG_FACILITY_CORE] = "CORE", + [FW_DEVLOG_FACILITY_SCHED] = "SCHED", + [FW_DEVLOG_FACILITY_TIMER] = "TIMER", + [FW_DEVLOG_FACILITY_RES] = "RES", + [FW_DEVLOG_FACILITY_HW] = "HW", + [FW_DEVLOG_FACILITY_FLR] = "FLR", + [FW_DEVLOG_FACILITY_DMAQ] = "DMAQ", + [FW_DEVLOG_FACILITY_PHY] = "PHY", + [FW_DEVLOG_FACILITY_MAC] = "MAC", + [FW_DEVLOG_FACILITY_PORT] = "PORT", + [FW_DEVLOG_FACILITY_VI] = "VI", + [FW_DEVLOG_FACILITY_FILTER] = "FILTER", + [FW_DEVLOG_FACILITY_ACL] = "ACL", + [FW_DEVLOG_FACILITY_TM] = "TM", + [FW_DEVLOG_FACILITY_QFC] = "QFC", + [FW_DEVLOG_FACILITY_DCB] = "DCB", + [FW_DEVLOG_FACILITY_ETH] = "ETH", + [FW_DEVLOG_FACILITY_OFLD] = "OFLD", + [FW_DEVLOG_FACILITY_RI] = "RI", + [FW_DEVLOG_FACILITY_ISCSI] = "ISCSI", + [FW_DEVLOG_FACILITY_FCOE] = "FCOE", + [FW_DEVLOG_FACILITY_FOISCSI] = "FOISCSI", + [FW_DEVLOG_FACILITY_FOFCOE] = "FOFCOE" +}; + +/* Information gathered by Device Log Open routine for the display routine. + */ +struct devlog_info { + unsigned int nentries; /* number of entries in log[] */ + unsigned int first; /* first [temporal] entry in log[] */ + struct fw_devlog_e log[0]; /* Firmware Device Log */ +}; + +/* Dump a Firmaware Device Log entry. + */ +static int devlog_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) + seq_printf(seq, "%10s %15s %8s %8s %s\n", + "Seq#", "Tstamp", "Level", "Facility", "Message"); + else { + struct devlog_info *dinfo = seq->private; + int fidx = (uintptr_t)v - 2; + unsigned long index; + struct fw_devlog_e *e; + + /* Get a pointer to the log entry to display. Skip unused log + * entries. + */ + index = dinfo->first + fidx; + if (index >= dinfo->nentries) + index -= dinfo->nentries; + e = &dinfo->log[index]; + if (e->timestamp == 0) + return 0; + + /* Print the message. This depends on the firmware using + * exactly the same formating strings as the kernel so we may + * eventually have to put a format interpreter in here ... + */ + seq_printf(seq, "%10d %15llu %8s %8s ", + e->seqno, e->timestamp, + (e->level < ARRAY_SIZE(devlog_level_strings) + ? devlog_level_strings[e->level] + : "UNKNOWN"), + (e->facility < ARRAY_SIZE(devlog_facility_strings) + ? devlog_facility_strings[e->facility] + : "UNKNOWN")); + seq_printf(seq, e->fmt, e->params[0], e->params[1], + e->params[2], e->params[3], e->params[4], + e->params[5], e->params[6], e->params[7]); + } + return 0; +} + +/* Sequential File Operations for Device Log. + */ +static inline void *devlog_get_idx(struct devlog_info *dinfo, loff_t pos) +{ + if (pos > dinfo->nentries) + return NULL; + + return (void *)(uintptr_t)(pos + 1); +} + +static void *devlog_start(struct seq_file *seq, loff_t *pos) +{ + struct devlog_info *dinfo = seq->private; + + return (*pos + ? devlog_get_idx(dinfo, *pos) + : SEQ_START_TOKEN); +} + +static void *devlog_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct devlog_info *dinfo = seq->private; + + (*pos)++; + return devlog_get_idx(dinfo, *pos); +} + +static void devlog_stop(struct seq_file *seq, void *v) +{ +} + +static const struct seq_operations devlog_seq_ops = { + .start = devlog_start, + .next = devlog_next, + .stop = devlog_stop, + .show = devlog_show +}; + +/* Set up for reading the firmware's device log. We read the entire log here + * and then display it incrementally in devlog_show(). + */ +static int devlog_open(struct inode *inode, struct file *file) +{ + struct adapter *adap = inode->i_private; + struct devlog_params *dparams = &adap->params.devlog; + struct devlog_info *dinfo; + unsigned int index; + u32 fseqno; + int ret; + + /* If we don't know where the log is we can't do anything. + */ + if (dparams->start == 0) + return -ENXIO; + + /* Allocate the space to read in the firmware's device log and set up + * for the iterated call to our display function. + */ + dinfo = __seq_open_private(file, &devlog_seq_ops, + sizeof(*dinfo) + dparams->size); + if (!dinfo) + return -ENOMEM; + + /* Record the basic log buffer information and read in the raw log. + */ + dinfo->nentries = (dparams->size / sizeof(struct fw_devlog_e)); + dinfo->first = 0; + spin_lock(&adap->win0_lock); + ret = t4_memory_rw(adap, adap->params.drv_memwin, dparams->memtype, + dparams->start, dparams->size, (__be32 *)dinfo->log, + T4_MEMORY_READ); + spin_unlock(&adap->win0_lock); + if (ret) { + seq_release_private(inode, file); + return ret; + } + + /* Translate log multi-byte integral elements into host native format + * and determine where the first entry in the log is. + */ + for (fseqno = ~((u32)0), index = 0; index < dinfo->nentries; index++) { + struct fw_devlog_e *e = &dinfo->log[index]; + int i; + __u32 seqno; + + if (e->timestamp == 0) + continue; + + e->timestamp = (__force __be64)be64_to_cpu(e->timestamp); + seqno = be32_to_cpu(e->seqno); + for (i = 0; i < 8; i++) + e->params[i] = + (__force __be32)be32_to_cpu(e->params[i]); + + if (seqno < fseqno) { + fseqno = seqno; + dinfo->first = index; + } + } + return 0; +} + +static const struct file_operations devlog_fops = { + .owner = THIS_MODULE, + .open = devlog_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private +}; + +static inline void tcamxy2valmask(u64 x, u64 y, u8 *addr, u64 *mask) +{ + *mask = x | y; + y = (__force u64)cpu_to_be64(y); + memcpy(addr, (char *)&y + 2, ETH_ALEN); +} + +static int mps_tcam_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) + seq_puts(seq, "Idx Ethernet address Mask Vld Ports PF" + " VF Replication " + "P0 P1 P2 P3 ML\n"); + else { + u64 mask; + u8 addr[ETH_ALEN]; + struct adapter *adap = seq->private; + unsigned int idx = (uintptr_t)v - 2; + u64 tcamy = t4_read_reg64(adap, MPS_CLS_TCAM_Y_L(idx)); + u64 tcamx = t4_read_reg64(adap, MPS_CLS_TCAM_X_L(idx)); + u32 cls_lo = t4_read_reg(adap, MPS_CLS_SRAM_L(idx)); + u32 cls_hi = t4_read_reg(adap, MPS_CLS_SRAM_H(idx)); + u32 rplc[4] = {0, 0, 0, 0}; + + if (tcamx & tcamy) { + seq_printf(seq, "%3u -\n", idx); + goto out; + } + + if (cls_lo & REPLICATE_F) { + struct fw_ldst_cmd ldst_cmd; + int ret; + + memset(&ldst_cmd, 0, sizeof(ldst_cmd)); + ldst_cmd.op_to_addrspace = + htonl(FW_CMD_OP_V(FW_LDST_CMD) | + FW_CMD_REQUEST_F | + FW_CMD_READ_F | + FW_LDST_CMD_ADDRSPACE_V( + FW_LDST_ADDRSPC_MPS)); + ldst_cmd.cycles_to_len16 = htonl(FW_LEN16(ldst_cmd)); + ldst_cmd.u.mps.fid_ctl = + htons(FW_LDST_CMD_FID_V(FW_LDST_MPS_RPLC) | + FW_LDST_CMD_CTL_V(idx)); + ret = t4_wr_mbox(adap, adap->mbox, &ldst_cmd, + sizeof(ldst_cmd), &ldst_cmd); + if (ret) + dev_warn(adap->pdev_dev, "Can't read MPS " + "replication map for idx %d: %d\n", + idx, -ret); + else { + rplc[0] = ntohl(ldst_cmd.u.mps.rplc31_0); + rplc[1] = ntohl(ldst_cmd.u.mps.rplc63_32); + rplc[2] = ntohl(ldst_cmd.u.mps.rplc95_64); + rplc[3] = ntohl(ldst_cmd.u.mps.rplc127_96); + } + } + + tcamxy2valmask(tcamx, tcamy, addr, &mask); + seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x %012llx" + "%3c %#x%4u%4d", + idx, addr[0], addr[1], addr[2], addr[3], addr[4], + addr[5], (unsigned long long)mask, + (cls_lo & SRAM_VLD_F) ? 'Y' : 'N', PORTMAP_G(cls_hi), + PF_G(cls_lo), + (cls_lo & VF_VALID_F) ? VF_G(cls_lo) : -1); + if (cls_lo & REPLICATE_F) + seq_printf(seq, " %08x %08x %08x %08x", + rplc[3], rplc[2], rplc[1], rplc[0]); + else + seq_printf(seq, "%36c", ' '); + seq_printf(seq, "%4u%3u%3u%3u %#x\n", + SRAM_PRIO0_G(cls_lo), SRAM_PRIO1_G(cls_lo), + SRAM_PRIO2_G(cls_lo), SRAM_PRIO3_G(cls_lo), + (cls_lo >> MULTILISTEN0_S) & 0xf); + } +out: return 0; +} + +static inline void *mps_tcam_get_idx(struct seq_file *seq, loff_t pos) +{ + struct adapter *adap = seq->private; + int max_mac_addr = is_t4(adap->params.chip) ? + NUM_MPS_CLS_SRAM_L_INSTANCES : + NUM_MPS_T5_CLS_SRAM_L_INSTANCES; + return ((pos <= max_mac_addr) ? (void *)(uintptr_t)(pos + 1) : NULL); +} + +static void *mps_tcam_start(struct seq_file *seq, loff_t *pos) +{ + return *pos ? mps_tcam_get_idx(seq, *pos) : SEQ_START_TOKEN; +} + +static void *mps_tcam_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + return mps_tcam_get_idx(seq, *pos); +} + +static void mps_tcam_stop(struct seq_file *seq, void *v) +{ +} + +static const struct seq_operations mps_tcam_seq_ops = { + .start = mps_tcam_start, + .next = mps_tcam_next, + .stop = mps_tcam_stop, + .show = mps_tcam_show +}; + +static int mps_tcam_open(struct inode *inode, struct file *file) +{ + int res = seq_open(file, &mps_tcam_seq_ops); + + if (!res) { + struct seq_file *seq = file->private_data; + + seq->private = inode->i_private; + } + return res; +} + +static const struct file_operations mps_tcam_debugfs_fops = { + .owner = THIS_MODULE, + .open = mps_tcam_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + static ssize_t mem_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -121,7 +641,11 @@ int t4_setup_debugfs(struct adapter *adap) u32 size; static struct t4_debugfs_entry t4_debugfs_files[] = { + { "cim_la", &cim_la_fops, S_IRUSR, 0 }, + { "cim_qcfg", &cim_qcfg_fops, S_IRUSR, 0 }, + { "devlog", &devlog_fops, S_IRUSR, 0 }, { "l2t", &t4_l2t_fops, S_IRUSR, 0}, + { "mps_tcam", &mps_tcam_debugfs_fops, S_IRUSR, 0 }, }; add_debugfs_files(adap, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h index a3d8867efd3d..70fcbc930826 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h @@ -44,6 +44,18 @@ struct t4_debugfs_entry { unsigned char data; }; +struct seq_tab { + int (*show)(struct seq_file *seq, void *v, int idx); + unsigned int rows; /* # of entries */ + unsigned char width; /* size in bytes of each entry */ + unsigned char skip_first; /* whether the first line is a header */ + char data[0]; /* the table data */ +}; + +struct seq_tab *seq_open_tab(struct file *f, unsigned int rows, + unsigned int width, unsigned int have_header, + int (*show)(struct seq_file *seq, void *v, int i)); + int t4_setup_debugfs(struct adapter *adap); void add_debugfs_files(struct adapter *adap, struct t4_debugfs_entry *files, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 04e675b8218a..6de41cc6687e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -5541,6 +5541,8 @@ static int adap_init0(struct adapter *adap) enum dev_state state; u32 params[7], val[7]; struct fw_caps_config_cmd caps_cmd; + struct fw_devlog_cmd devlog_cmd; + u32 devlog_meminfo; int reset = 1; /* Contact FW, advertising Master capability */ @@ -5621,6 +5623,30 @@ static int adap_init0(struct adapter *adap) if (ret < 0) goto bye; + /* Read firmware device log parameters. We really need to find a way + * to get these parameters initialized with some default values (which + * are likely to be correct) for the case where we either don't + * attache to the firmware or it's crashed when we probe the adapter. + * That way we'll still be able to perform early firmware startup + * debugging ... If the request to get the Firmware's Device Log + * parameters fails, we'll live so we don't make that a fatal error. + */ + memset(&devlog_cmd, 0, sizeof(devlog_cmd)); + devlog_cmd.op_to_write = htonl(FW_CMD_OP_V(FW_DEVLOG_CMD) | + FW_CMD_REQUEST_F | FW_CMD_READ_F); + devlog_cmd.retval_len16 = htonl(FW_LEN16(devlog_cmd)); + ret = t4_wr_mbox(adap, adap->mbox, &devlog_cmd, sizeof(devlog_cmd), + &devlog_cmd); + if (ret == 0) { + devlog_meminfo = + ntohl(devlog_cmd.memtype_devlog_memaddr16_devlog); + adap->params.devlog.memtype = + FW_DEVLOG_CMD_MEMTYPE_DEVLOG_G(devlog_meminfo); + adap->params.devlog.start = + FW_DEVLOG_CMD_MEMADDR16_DEVLOG_G(devlog_meminfo) << 4; + adap->params.devlog.size = ntohl(devlog_cmd.memsize_devlog); + } + /* * Find out what ports are available to us. Note that we need to do * this before calling adap_init0_no_config() since it needs nports diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 3776279337c8..734d33e3f53b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -4031,6 +4031,7 @@ int t4_prep_adapter(struct adapter *adapter) return -EINVAL; } + adapter->params.cim_la_size = CIMLA_SIZE; init_cong_ctrl(adapter->params.a_wnd, adapter->params.b_wnd); /* @@ -4323,3 +4324,157 @@ int t4_port_init(struct adapter *adap, int mbox, int pf, int vf) } return 0; } + +/** + * t4_read_cimq_cfg - read CIM queue configuration + * @adap: the adapter + * @base: holds the queue base addresses in bytes + * @size: holds the queue sizes in bytes + * @thres: holds the queue full thresholds in bytes + * + * Returns the current configuration of the CIM queues, starting with + * the IBQs, then the OBQs. + */ +void t4_read_cimq_cfg(struct adapter *adap, u16 *base, u16 *size, u16 *thres) +{ + unsigned int i, v; + int cim_num_obq = is_t4(adap->params.chip) ? + CIM_NUM_OBQ : CIM_NUM_OBQ_T5; + + for (i = 0; i < CIM_NUM_IBQ; i++) { + t4_write_reg(adap, CIM_QUEUE_CONFIG_REF_A, IBQSELECT_F | + QUENUMSELECT_V(i)); + v = t4_read_reg(adap, CIM_QUEUE_CONFIG_CTRL_A); + /* value is in 256-byte units */ + *base++ = CIMQBASE_G(v) * 256; + *size++ = CIMQSIZE_G(v) * 256; + *thres++ = QUEFULLTHRSH_G(v) * 8; /* 8-byte unit */ + } + for (i = 0; i < cim_num_obq; i++) { + t4_write_reg(adap, CIM_QUEUE_CONFIG_REF_A, OBQSELECT_F | + QUENUMSELECT_V(i)); + v = t4_read_reg(adap, CIM_QUEUE_CONFIG_CTRL_A); + /* value is in 256-byte units */ + *base++ = CIMQBASE_G(v) * 256; + *size++ = CIMQSIZE_G(v) * 256; + } +} + +/** + * t4_cim_read - read a block from CIM internal address space + * @adap: the adapter + * @addr: the start address within the CIM address space + * @n: number of words to read + * @valp: where to store the result + * + * Reads a block of 4-byte words from the CIM intenal address space. + */ +int t4_cim_read(struct adapter *adap, unsigned int addr, unsigned int n, + unsigned int *valp) +{ + int ret = 0; + + if (t4_read_reg(adap, CIM_HOST_ACC_CTRL_A) & HOSTBUSY_F) + return -EBUSY; + + for ( ; !ret && n--; addr += 4) { + t4_write_reg(adap, CIM_HOST_ACC_CTRL_A, addr); + ret = t4_wait_op_done(adap, CIM_HOST_ACC_CTRL_A, HOSTBUSY_F, + 0, 5, 2); + if (!ret) + *valp++ = t4_read_reg(adap, CIM_HOST_ACC_DATA_A); + } + return ret; +} + +/** + * t4_cim_write - write a block into CIM internal address space + * @adap: the adapter + * @addr: the start address within the CIM address space + * @n: number of words to write + * @valp: set of values to write + * + * Writes a block of 4-byte words into the CIM intenal address space. + */ +int t4_cim_write(struct adapter *adap, unsigned int addr, unsigned int n, + const unsigned int *valp) +{ + int ret = 0; + + if (t4_read_reg(adap, CIM_HOST_ACC_CTRL_A) & HOSTBUSY_F) + return -EBUSY; + + for ( ; !ret && n--; addr += 4) { + t4_write_reg(adap, CIM_HOST_ACC_DATA_A, *valp++); + t4_write_reg(adap, CIM_HOST_ACC_CTRL_A, addr | HOSTWRITE_F); + ret = t4_wait_op_done(adap, CIM_HOST_ACC_CTRL_A, HOSTBUSY_F, + 0, 5, 2); + } + return ret; +} + +static int t4_cim_write1(struct adapter *adap, unsigned int addr, + unsigned int val) +{ + return t4_cim_write(adap, addr, 1, &val); +} + +/** + * t4_cim_read_la - read CIM LA capture buffer + * @adap: the adapter + * @la_buf: where to store the LA data + * @wrptr: the HW write pointer within the capture buffer + * + * Reads the contents of the CIM LA buffer with the most recent entry at + * the end of the returned data and with the entry at @wrptr first. + * We try to leave the LA in the running state we find it in. + */ +int t4_cim_read_la(struct adapter *adap, u32 *la_buf, unsigned int *wrptr) +{ + int i, ret; + unsigned int cfg, val, idx; + + ret = t4_cim_read(adap, UP_UP_DBG_LA_CFG_A, 1, &cfg); + if (ret) + return ret; + + if (cfg & UPDBGLAEN_F) { /* LA is running, freeze it */ + ret = t4_cim_write1(adap, UP_UP_DBG_LA_CFG_A, 0); + if (ret) + return ret; + } + + ret = t4_cim_read(adap, UP_UP_DBG_LA_CFG_A, 1, &val); + if (ret) + goto restart; + + idx = UPDBGLAWRPTR_G(val); + if (wrptr) + *wrptr = idx; + + for (i = 0; i < adap->params.cim_la_size; i++) { + ret = t4_cim_write1(adap, UP_UP_DBG_LA_CFG_A, + UPDBGLARDPTR_V(idx) | UPDBGLARDEN_F); + if (ret) + break; + ret = t4_cim_read(adap, UP_UP_DBG_LA_CFG_A, 1, &val); + if (ret) + break; + if (val & UPDBGLARDEN_F) { + ret = -ETIMEDOUT; + break; + } + ret = t4_cim_read(adap, UP_UP_DBG_LA_DATA_A, 1, &la_buf[i]); + if (ret) + break; + idx = (idx + 1) & UPDBGLARDPTR_M; + } +restart: + if (cfg & UPDBGLAEN_F) { + int r = t4_cim_write1(adap, UP_UP_DBG_LA_CFG_A, + cfg & ~UPDBGLARDEN_F); + if (!ret) + ret = r; + } + return ret; +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h index c19a90e7f7d1..f6b82da350e2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h @@ -56,6 +56,13 @@ enum { }; enum { + CIM_NUM_IBQ = 6, /* # of CIM IBQs */ + CIM_NUM_OBQ = 6, /* # of CIM OBQs */ + CIM_NUM_OBQ_T5 = 8, /* # of CIM OBQs for T5 adapter */ + CIMLA_SIZE = 2048, /* # of 32-bit words in CIM LA */ +}; + +enum { SF_PAGE_SIZE = 256, /* serial flash page size */ SF_SEC_SIZE = 64 * 1024, /* serial flash sector size */ }; @@ -110,6 +117,18 @@ enum { SGE_INGPADBOUNDARY_SHIFT = 5,/* ingress queue pad boundary */ }; +/* PCI-e memory window access */ +enum pcie_memwin { + MEMWIN_NIC = 0, + MEMWIN_RSVD1 = 1, + MEMWIN_RSVD2 = 2, + MEMWIN_RDMA = 3, + MEMWIN_RSVD4 = 4, + MEMWIN_FOISCSI = 5, + MEMWIN_CSIOSTOR = 6, + MEMWIN_RSVD7 = 7, +}; + struct sge_qstat { /* data written to SGE queue status entries */ __be32 qid; __be16 cidx; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index 4077227b5cea..7ce55f9be9d4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -1708,6 +1708,66 @@ #define MPS_RX_PERR_INT_CAUSE_A 0x11074 +#define MPS_CLS_TCAM_Y_L_A 0xf000 +#define MPS_CLS_TCAM_X_L_A 0xf008 + +#define MPS_CLS_TCAM_Y_L(idx) (MPS_CLS_TCAM_Y_L_A + (idx) * 16) +#define NUM_MPS_CLS_TCAM_Y_L_INSTANCES 512 + +#define MPS_CLS_TCAM_X_L(idx) (MPS_CLS_TCAM_X_L_A + (idx) * 16) +#define NUM_MPS_CLS_TCAM_X_L_INSTANCES 512 + +#define MPS_CLS_SRAM_L_A 0xe000 +#define MPS_CLS_SRAM_H_A 0xe004 + +#define MPS_CLS_SRAM_L(idx) (MPS_CLS_SRAM_L_A + (idx) * 8) +#define NUM_MPS_CLS_SRAM_L_INSTANCES 336 + +#define MPS_CLS_SRAM_H(idx) (MPS_CLS_SRAM_H_A + (idx) * 8) +#define NUM_MPS_CLS_SRAM_H_INSTANCES 336 + +#define MULTILISTEN0_S 25 + +#define REPLICATE_S 11 +#define REPLICATE_V(x) ((x) << REPLICATE_S) +#define REPLICATE_F REPLICATE_V(1U) + +#define PF_S 8 +#define PF_M 0x7U +#define PF_G(x) (((x) >> PF_S) & PF_M) + +#define VF_VALID_S 7 +#define VF_VALID_V(x) ((x) << VF_VALID_S) +#define VF_VALID_F VF_VALID_V(1U) + +#define VF_S 0 +#define VF_M 0x7fU +#define VF_G(x) (((x) >> VF_S) & VF_M) + +#define SRAM_PRIO3_S 22 +#define SRAM_PRIO3_M 0x7U +#define SRAM_PRIO3_G(x) (((x) >> SRAM_PRIO3_S) & SRAM_PRIO3_M) + +#define SRAM_PRIO2_S 19 +#define SRAM_PRIO2_M 0x7U +#define SRAM_PRIO2_G(x) (((x) >> SRAM_PRIO2_S) & SRAM_PRIO2_M) + +#define SRAM_PRIO1_S 16 +#define SRAM_PRIO1_M 0x7U +#define SRAM_PRIO1_G(x) (((x) >> SRAM_PRIO1_S) & SRAM_PRIO1_M) + +#define SRAM_PRIO0_S 13 +#define SRAM_PRIO0_M 0x7U +#define SRAM_PRIO0_G(x) (((x) >> SRAM_PRIO0_S) & SRAM_PRIO0_M) + +#define SRAM_VLD_S 12 +#define SRAM_VLD_V(x) ((x) << SRAM_VLD_S) +#define SRAM_VLD_F SRAM_VLD_V(1U) + +#define PORTMAP_S 0 +#define PORTMAP_M 0xfU +#define PORTMAP_G(x) (((x) >> PORTMAP_S) & PORTMAP_M) + #define CPL_INTR_CAUSE_A 0x19054 #define CIM_OP_MAP_PERR_S 5 @@ -2062,4 +2122,93 @@ #define PL_VF_WHOAMI_A 0x0 #define PL_VF_REVISION_A 0x8 +/* registers for module CIM */ +#define CIM_HOST_ACC_CTRL_A 0x7b50 +#define CIM_HOST_ACC_DATA_A 0x7b54 +#define UP_UP_DBG_LA_CFG_A 0x140 +#define UP_UP_DBG_LA_DATA_A 0x144 + +#define HOSTBUSY_S 17 +#define HOSTBUSY_V(x) ((x) << HOSTBUSY_S) +#define HOSTBUSY_F HOSTBUSY_V(1U) + +#define HOSTWRITE_S 16 +#define HOSTWRITE_V(x) ((x) << HOSTWRITE_S) +#define HOSTWRITE_F HOSTWRITE_V(1U) + +#define UPDBGLARDEN_S 1 +#define UPDBGLARDEN_V(x) ((x) << UPDBGLARDEN_S) +#define UPDBGLARDEN_F UPDBGLARDEN_V(1U) + +#define UPDBGLAEN_S 0 +#define UPDBGLAEN_V(x) ((x) << UPDBGLAEN_S) +#define UPDBGLAEN_F UPDBGLAEN_V(1U) + +#define UPDBGLARDPTR_S 2 +#define UPDBGLARDPTR_M 0xfffU +#define UPDBGLARDPTR_V(x) ((x) << UPDBGLARDPTR_S) + +#define UPDBGLAWRPTR_S 16 +#define UPDBGLAWRPTR_M 0xfffU +#define UPDBGLAWRPTR_G(x) (((x) >> UPDBGLAWRPTR_S) & UPDBGLAWRPTR_M) + +#define UPDBGLACAPTPCONLY_S 30 +#define UPDBGLACAPTPCONLY_V(x) ((x) << UPDBGLACAPTPCONLY_S) +#define UPDBGLACAPTPCONLY_F UPDBGLACAPTPCONLY_V(1U) + +#define CIM_QUEUE_CONFIG_REF_A 0x7b48 +#define CIM_QUEUE_CONFIG_CTRL_A 0x7b4c + +#define CIMQSIZE_S 24 +#define CIMQSIZE_M 0x3fU +#define CIMQSIZE_G(x) (((x) >> CIMQSIZE_S) & CIMQSIZE_M) + +#define CIMQBASE_S 16 +#define CIMQBASE_M 0x3fU +#define CIMQBASE_G(x) (((x) >> CIMQBASE_S) & CIMQBASE_M) + +#define QUEFULLTHRSH_S 0 +#define QUEFULLTHRSH_M 0x1ffU +#define QUEFULLTHRSH_G(x) (((x) >> QUEFULLTHRSH_S) & QUEFULLTHRSH_M) + +#define UP_IBQ_0_RDADDR_A 0x10 +#define UP_IBQ_0_SHADOW_RDADDR_A 0x280 +#define UP_OBQ_0_REALADDR_A 0x104 +#define UP_OBQ_0_SHADOW_REALADDR_A 0x394 + +#define IBQRDADDR_S 0 +#define IBQRDADDR_M 0x1fffU +#define IBQRDADDR_G(x) (((x) >> IBQRDADDR_S) & IBQRDADDR_M) + +#define IBQWRADDR_S 0 +#define IBQWRADDR_M 0x1fffU +#define IBQWRADDR_G(x) (((x) >> IBQWRADDR_S) & IBQWRADDR_M) + +#define QUERDADDR_S 0 +#define QUERDADDR_M 0x7fffU +#define QUERDADDR_G(x) (((x) >> QUERDADDR_S) & QUERDADDR_M) + +#define QUEREMFLITS_S 0 +#define QUEREMFLITS_M 0x7ffU +#define QUEREMFLITS_G(x) (((x) >> QUEREMFLITS_S) & QUEREMFLITS_M) + +#define QUEEOPCNT_S 16 +#define QUEEOPCNT_M 0xfffU +#define QUEEOPCNT_G(x) (((x) >> QUEEOPCNT_S) & QUEEOPCNT_M) + +#define QUESOPCNT_S 0 +#define QUESOPCNT_M 0xfffU +#define QUESOPCNT_G(x) (((x) >> QUESOPCNT_S) & QUESOPCNT_M) + +#define OBQSELECT_S 4 +#define OBQSELECT_V(x) ((x) << OBQSELECT_S) +#define OBQSELECT_F OBQSELECT_V(1U) + +#define IBQSELECT_S 3 +#define IBQSELECT_V(x) ((x) << IBQSELECT_S) +#define IBQSELECT_F IBQSELECT_V(1U) + +#define QUENUMSELECT_S 0 +#define QUENUMSELECT_V(x) ((x) << QUENUMSELECT_S) + #endif /* __T4_REGS_H */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 7c0aec85137a..de8283324f1f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -673,6 +673,7 @@ enum fw_cmd_opcodes { FW_RSS_IND_TBL_CMD = 0x20, FW_RSS_GLB_CONFIG_CMD = 0x22, FW_RSS_VI_CONFIG_CMD = 0x23, + FW_DEVLOG_CMD = 0x25, FW_CLIP_CMD = 0x28, FW_LASTC2E_CMD = 0x40, FW_ERROR_CMD = 0x80, @@ -3038,4 +3039,84 @@ enum fw_hdr_flags { FW_HDR_FLAGS_RESET_HALT = 0x00000001, }; +/* length of the formatting string */ +#define FW_DEVLOG_FMT_LEN 192 + +/* maximum number of the formatting string parameters */ +#define FW_DEVLOG_FMT_PARAMS_NUM 8 + +/* priority levels */ +enum fw_devlog_level { + FW_DEVLOG_LEVEL_EMERG = 0x0, + FW_DEVLOG_LEVEL_CRIT = 0x1, + FW_DEVLOG_LEVEL_ERR = 0x2, + FW_DEVLOG_LEVEL_NOTICE = 0x3, + FW_DEVLOG_LEVEL_INFO = 0x4, + FW_DEVLOG_LEVEL_DEBUG = 0x5, + FW_DEVLOG_LEVEL_MAX = 0x5, +}; + +/* facilities that may send a log message */ +enum fw_devlog_facility { + FW_DEVLOG_FACILITY_CORE = 0x00, + FW_DEVLOG_FACILITY_CF = 0x01, + FW_DEVLOG_FACILITY_SCHED = 0x02, + FW_DEVLOG_FACILITY_TIMER = 0x04, + FW_DEVLOG_FACILITY_RES = 0x06, + FW_DEVLOG_FACILITY_HW = 0x08, + FW_DEVLOG_FACILITY_FLR = 0x10, + FW_DEVLOG_FACILITY_DMAQ = 0x12, + FW_DEVLOG_FACILITY_PHY = 0x14, + FW_DEVLOG_FACILITY_MAC = 0x16, + FW_DEVLOG_FACILITY_PORT = 0x18, + FW_DEVLOG_FACILITY_VI = 0x1A, + FW_DEVLOG_FACILITY_FILTER = 0x1C, + FW_DEVLOG_FACILITY_ACL = 0x1E, + FW_DEVLOG_FACILITY_TM = 0x20, + FW_DEVLOG_FACILITY_QFC = 0x22, + FW_DEVLOG_FACILITY_DCB = 0x24, + FW_DEVLOG_FACILITY_ETH = 0x26, + FW_DEVLOG_FACILITY_OFLD = 0x28, + FW_DEVLOG_FACILITY_RI = 0x2A, + FW_DEVLOG_FACILITY_ISCSI = 0x2C, + FW_DEVLOG_FACILITY_FCOE = 0x2E, + FW_DEVLOG_FACILITY_FOISCSI = 0x30, + FW_DEVLOG_FACILITY_FOFCOE = 0x32, + FW_DEVLOG_FACILITY_MAX = 0x32, +}; + +/* log message format */ +struct fw_devlog_e { + __be64 timestamp; + __be32 seqno; + __be16 reserved1; + __u8 level; + __u8 facility; + __u8 fmt[FW_DEVLOG_FMT_LEN]; + __be32 params[FW_DEVLOG_FMT_PARAMS_NUM]; + __be32 reserved3[4]; +}; + +struct fw_devlog_cmd { + __be32 op_to_write; + __be32 retval_len16; + __u8 level; + __u8 r2[7]; + __be32 memtype_devlog_memaddr16_devlog; + __be32 memsize_devlog; + __be32 r3[2]; +}; + +#define FW_DEVLOG_CMD_MEMTYPE_DEVLOG_S 28 +#define FW_DEVLOG_CMD_MEMTYPE_DEVLOG_M 0xf +#define FW_DEVLOG_CMD_MEMTYPE_DEVLOG_G(x) \ + (((x) >> FW_DEVLOG_CMD_MEMTYPE_DEVLOG_S) & \ + FW_DEVLOG_CMD_MEMTYPE_DEVLOG_M) + +#define FW_DEVLOG_CMD_MEMADDR16_DEVLOG_S 0 +#define FW_DEVLOG_CMD_MEMADDR16_DEVLOG_M 0xfffffff +#define FW_DEVLOG_CMD_MEMADDR16_DEVLOG_G(x) \ + (((x) >> FW_DEVLOG_CMD_MEMADDR16_DEVLOG_S) & \ + FW_DEVLOG_CMD_MEMADDR16_DEVLOG_M) + #endif /* _T4FW_INTERFACE_H_ */ diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 14a1c5cec3a5..3a280598a15a 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -7049,6 +7049,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, u32 status, len; u32 opts[2]; int frags; + bool stop_queue; if (unlikely(!TX_FRAGS_READY_FOR(tp, skb_shinfo(skb)->nr_frags))) { netif_err(tp, drv, dev, "BUG! Tx Ring full when queue awake!\n"); @@ -7105,11 +7106,16 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, tp->cur_tx += frags + 1; - RTL_W8(TxPoll, NPQ); + stop_queue = !TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS); - mmiowb(); + if (!skb->xmit_more || stop_queue || + netif_xmit_stopped(netdev_get_tx_queue(dev, 0))) { + RTL_W8(TxPoll, NPQ); + + mmiowb(); + } - if (!TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS)) { + if (stop_queue) { /* Avoid wrongly optimistic queue wake-up: rtl_tx thread must * not miss a ring update when it notices a stopped queue. */ diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c index 660283528ada..b70c15fb1e97 100644 --- a/drivers/scsi/csiostor/csio_hw.c +++ b/drivers/scsi/csiostor/csio_hw.c @@ -682,43 +682,6 @@ csio_hw_get_tp_version(struct csio_hw *hw, u32 *vers) } /* - * csio_hw_check_fw_version - check if the FW is compatible with - * this driver - * @hw: HW module - * - * Checks if an adapter's FW is compatible with the driver. Returns 0 - * if there's exact match, a negative error if the version could not be - * read or there's a major/minor version mismatch/minor. - */ -static int -csio_hw_check_fw_version(struct csio_hw *hw) -{ - int ret, major, minor, micro; - - ret = csio_hw_get_fw_version(hw, &hw->fwrev); - if (!ret) - ret = csio_hw_get_tp_version(hw, &hw->tp_vers); - if (ret) - return ret; - - major = FW_HDR_FW_VER_MAJOR_G(hw->fwrev); - minor = FW_HDR_FW_VER_MINOR_G(hw->fwrev); - micro = FW_HDR_FW_VER_MICRO_G(hw->fwrev); - - if (major != FW_VERSION_MAJOR(hw)) { /* major mismatch - fail */ - csio_err(hw, "card FW has major version %u, driver wants %u\n", - major, FW_VERSION_MAJOR(hw)); - return -EINVAL; - } - - if (minor == FW_VERSION_MINOR(hw) && micro == FW_VERSION_MICRO(hw)) - return 0; /* perfect match */ - - /* Minor/micro version mismatch */ - return -EINVAL; -} - -/* * csio_hw_fw_dload - download firmware. * @hw: HW module * @fw_data: firmware image to write. @@ -1967,6 +1930,170 @@ out: return rv; } +/* Is the given firmware API compatible with the one the driver was compiled + * with? + */ +static int fw_compatible(const struct fw_hdr *hdr1, const struct fw_hdr *hdr2) +{ + + /* short circuit if it's the exact same firmware version */ + if (hdr1->chip == hdr2->chip && hdr1->fw_ver == hdr2->fw_ver) + return 1; + +#define SAME_INTF(x) (hdr1->intfver_##x == hdr2->intfver_##x) + if (hdr1->chip == hdr2->chip && SAME_INTF(nic) && SAME_INTF(vnic) && + SAME_INTF(ri) && SAME_INTF(iscsi) && SAME_INTF(fcoe)) + return 1; +#undef SAME_INTF + + return 0; +} + +/* The firmware in the filesystem is usable, but should it be installed? + * This routine explains itself in detail if it indicates the filesystem + * firmware should be installed. + */ +static int csio_should_install_fs_fw(struct csio_hw *hw, int card_fw_usable, + int k, int c) +{ + const char *reason; + + if (!card_fw_usable) { + reason = "incompatible or unusable"; + goto install; + } + + if (k > c) { + reason = "older than the version supported with this driver"; + goto install; + } + + return 0; + +install: + csio_err(hw, "firmware on card (%u.%u.%u.%u) is %s, " + "installing firmware %u.%u.%u.%u on card.\n", + FW_HDR_FW_VER_MAJOR_G(c), FW_HDR_FW_VER_MINOR_G(c), + FW_HDR_FW_VER_MICRO_G(c), FW_HDR_FW_VER_BUILD_G(c), reason, + FW_HDR_FW_VER_MAJOR_G(k), FW_HDR_FW_VER_MINOR_G(k), + FW_HDR_FW_VER_MICRO_G(k), FW_HDR_FW_VER_BUILD_G(k)); + + return 1; +} + +static struct fw_info fw_info_array[] = { + { + .chip = CHELSIO_T5, + .fs_name = FW_CFG_NAME_T5, + .fw_mod_name = FW_FNAME_T5, + .fw_hdr = { + .chip = FW_HDR_CHIP_T5, + .fw_ver = __cpu_to_be32(FW_VERSION(T5)), + .intfver_nic = FW_INTFVER(T5, NIC), + .intfver_vnic = FW_INTFVER(T5, VNIC), + .intfver_ri = FW_INTFVER(T5, RI), + .intfver_iscsi = FW_INTFVER(T5, ISCSI), + .intfver_fcoe = FW_INTFVER(T5, FCOE), + }, + } +}; + +static struct fw_info *find_fw_info(int chip) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(fw_info_array); i++) { + if (fw_info_array[i].chip == chip) + return &fw_info_array[i]; + } + return NULL; +} + +int csio_hw_prep_fw(struct csio_hw *hw, struct fw_info *fw_info, + const u8 *fw_data, unsigned int fw_size, + struct fw_hdr *card_fw, enum csio_dev_state state, + int *reset) +{ + int ret, card_fw_usable, fs_fw_usable; + const struct fw_hdr *fs_fw; + const struct fw_hdr *drv_fw; + + drv_fw = &fw_info->fw_hdr; + + /* Read the header of the firmware on the card */ + ret = csio_hw_read_flash(hw, FLASH_FW_START, + sizeof(*card_fw) / sizeof(uint32_t), + (uint32_t *)card_fw, 1); + if (ret == 0) { + card_fw_usable = fw_compatible(drv_fw, (const void *)card_fw); + } else { + csio_err(hw, + "Unable to read card's firmware header: %d\n", ret); + card_fw_usable = 0; + } + + if (fw_data != NULL) { + fs_fw = (const void *)fw_data; + fs_fw_usable = fw_compatible(drv_fw, fs_fw); + } else { + fs_fw = NULL; + fs_fw_usable = 0; + } + + if (card_fw_usable && card_fw->fw_ver == drv_fw->fw_ver && + (!fs_fw_usable || fs_fw->fw_ver == drv_fw->fw_ver)) { + /* Common case: the firmware on the card is an exact match and + * the filesystem one is an exact match too, or the filesystem + * one is absent/incompatible. + */ + } else if (fs_fw_usable && state == CSIO_DEV_STATE_UNINIT && + csio_should_install_fs_fw(hw, card_fw_usable, + be32_to_cpu(fs_fw->fw_ver), + be32_to_cpu(card_fw->fw_ver))) { + ret = csio_hw_fw_upgrade(hw, hw->pfn, fw_data, + fw_size, 0); + if (ret != 0) { + csio_err(hw, + "failed to install firmware: %d\n", ret); + goto bye; + } + + /* Installed successfully, update the cached header too. */ + memcpy(card_fw, fs_fw, sizeof(*card_fw)); + card_fw_usable = 1; + *reset = 0; /* already reset as part of load_fw */ + } + + if (!card_fw_usable) { + uint32_t d, c, k; + + d = be32_to_cpu(drv_fw->fw_ver); + c = be32_to_cpu(card_fw->fw_ver); + k = fs_fw ? be32_to_cpu(fs_fw->fw_ver) : 0; + + csio_err(hw, "Cannot find a usable firmware: " + "chip state %d, " + "driver compiled with %d.%d.%d.%d, " + "card has %d.%d.%d.%d, filesystem has %d.%d.%d.%d\n", + state, + FW_HDR_FW_VER_MAJOR_G(d), FW_HDR_FW_VER_MINOR_G(d), + FW_HDR_FW_VER_MICRO_G(d), FW_HDR_FW_VER_BUILD_G(d), + FW_HDR_FW_VER_MAJOR_G(c), FW_HDR_FW_VER_MINOR_G(c), + FW_HDR_FW_VER_MICRO_G(c), FW_HDR_FW_VER_BUILD_G(c), + FW_HDR_FW_VER_MAJOR_G(k), FW_HDR_FW_VER_MINOR_G(k), + FW_HDR_FW_VER_MICRO_G(k), FW_HDR_FW_VER_BUILD_G(k)); + ret = EINVAL; + goto bye; + } + + /* We're using whatever's on the card and it's known to be good. */ + hw->fwrev = be32_to_cpu(card_fw->fw_ver); + hw->tp_vers = be32_to_cpu(card_fw->tp_microcode_ver); + +bye: + return ret; +} + /* * Returns -EINVAL if attempts to flash the firmware failed * else returns 0, @@ -1974,14 +2101,27 @@ out: * latest firmware ECANCELED is returned */ static int -csio_hw_flash_fw(struct csio_hw *hw) +csio_hw_flash_fw(struct csio_hw *hw, int *reset) { int ret = -ECANCELED; const struct firmware *fw; - const struct fw_hdr *hdr; - u32 fw_ver; + struct fw_info *fw_info; + struct fw_hdr *card_fw; struct pci_dev *pci_dev = hw->pdev; struct device *dev = &pci_dev->dev ; + const u8 *fw_data = NULL; + unsigned int fw_size = 0; + + /* This is the firmware whose headers the driver was compiled + * against + */ + fw_info = find_fw_info(CHELSIO_CHIP_VERSION(hw->chip_id)); + if (fw_info == NULL) { + csio_err(hw, + "unable to get firmware info for chip %d.\n", + CHELSIO_CHIP_VERSION(hw->chip_id)); + return -EINVAL; + } if (request_firmware(&fw, CSIO_FW_FNAME(hw), dev) < 0) { csio_err(hw, "could not find firmware image %s, err: %d\n", @@ -1989,33 +2129,25 @@ csio_hw_flash_fw(struct csio_hw *hw) return -EINVAL; } - hdr = (const struct fw_hdr *)fw->data; - fw_ver = ntohl(hdr->fw_ver); - if (FW_HDR_FW_VER_MAJOR_G(fw_ver) != FW_VERSION_MAJOR(hw)) - return -EINVAL; /* wrong major version, won't do */ - - /* - * If the flash FW is unusable or we found something newer, load it. + /* allocate memory to read the header of the firmware on the + * card */ - if (FW_HDR_FW_VER_MAJOR_G(hw->fwrev) != FW_VERSION_MAJOR(hw) || - fw_ver > hw->fwrev) { - ret = csio_hw_fw_upgrade(hw, hw->pfn, fw->data, fw->size, - /*force=*/false); - if (!ret) - csio_info(hw, - "firmware upgraded to version %pI4 from %s\n", - &hdr->fw_ver, CSIO_FW_FNAME(hw)); - else - csio_err(hw, "firmware upgrade failed! err=%d\n", ret); - } else - ret = -EINVAL; + card_fw = kmalloc(sizeof(*card_fw), GFP_KERNEL); - release_firmware(fw); + fw_data = fw->data; + fw_size = fw->size; + /* upgrade FW logic */ + ret = csio_hw_prep_fw(hw, fw_info, fw_data, fw_size, card_fw, + hw->fw_state, reset); + + /* Cleaning up */ + if (fw != NULL) + release_firmware(fw); + kfree(card_fw); return ret; } - /* * csio_hw_configure - Configure HW * @hw - HW module @@ -2071,25 +2203,18 @@ csio_hw_configure(struct csio_hw *hw) if (rv != 0) goto out; + csio_hw_get_fw_version(hw, &hw->fwrev); + csio_hw_get_tp_version(hw, &hw->tp_vers); if (csio_is_hw_master(hw) && hw->fw_state != CSIO_DEV_STATE_INIT) { - rv = csio_hw_check_fw_version(hw); - if (rv == -EINVAL) { /* Do firmware update */ - spin_unlock_irq(&hw->lock); - rv = csio_hw_flash_fw(hw); - spin_lock_irq(&hw->lock); + spin_unlock_irq(&hw->lock); + rv = csio_hw_flash_fw(hw, &reset); + spin_lock_irq(&hw->lock); + + if (rv != 0) + goto out; - if (rv == 0) { - reset = 0; - /* - * Note that the chip was reset as part of the - * firmware upgrade so we don't reset it again - * below and grab the new firmware version. - */ - rv = csio_hw_check_fw_version(hw); - } - } /* * If the firmware doesn't support Configuration * Files, use the old Driver-based, hard-wired diff --git a/drivers/scsi/csiostor/csio_hw.h b/drivers/scsi/csiostor/csio_hw.h index bd9720467aa3..1fe8fdee70fa 100644 --- a/drivers/scsi/csiostor/csio_hw.h +++ b/drivers/scsi/csiostor/csio_hw.h @@ -201,9 +201,8 @@ enum { SF_ERASE_SECTOR = 0xd8, /* erase sector */ FW_START_SEC = 8, /* first flash sector for FW */ - FW_END_SEC = 15, /* last flash sector for FW */ FW_IMG_START = FW_START_SEC * SF_SEC_SIZE, - FW_MAX_SIZE = (FW_END_SEC - FW_START_SEC + 1) * SF_SEC_SIZE, + FW_MAX_SIZE = 16 * SF_SEC_SIZE, FLASH_CFG_MAX_SIZE = 0x10000 , /* max size of the flash config file*/ FLASH_CFG_OFFSET = 0x1f0000, @@ -221,7 +220,7 @@ enum { * Location of firmware image in FLASH. */ FLASH_FW_START_SEC = 8, - FLASH_FW_NSECS = 8, + FLASH_FW_NSECS = 16, FLASH_FW_START = FLASH_START(FLASH_FW_START_SEC), FLASH_FW_MAX_SIZE = FLASH_MAX_SIZE(FLASH_FW_NSECS), diff --git a/drivers/scsi/csiostor/csio_hw_chip.h b/drivers/scsi/csiostor/csio_hw_chip.h index 70c0bdd7c796..eec98f523ec9 100644 --- a/drivers/scsi/csiostor/csio_hw_chip.h +++ b/drivers/scsi/csiostor/csio_hw_chip.h @@ -50,6 +50,36 @@ #define FW_CFG_NAME_T4 "cxgb4/t4-config.txt" #define FW_CFG_NAME_T5 "cxgb4/t5-config.txt" +#define T4FW_VERSION_MAJOR 0x01 +#define T4FW_VERSION_MINOR 0x0B +#define T4FW_VERSION_MICRO 0x1B +#define T4FW_VERSION_BUILD 0x00 + +#define T5FW_VERSION_MAJOR 0x01 +#define T5FW_VERSION_MINOR 0x0B +#define T5FW_VERSION_MICRO 0x1B +#define T5FW_VERSION_BUILD 0x00 + +#define CHELSIO_CHIP_CODE(version, revision) (((version) << 4) | (revision)) +#define CHELSIO_CHIP_FPGA 0x100 +#define CHELSIO_CHIP_VERSION(code) (((code) >> 12) & 0xf) +#define CHELSIO_CHIP_RELEASE(code) ((code) & 0xf) + +#define CHELSIO_T4 0x4 +#define CHELSIO_T5 0x5 + +enum chip_type { + T4_A1 = CHELSIO_CHIP_CODE(CHELSIO_T4, 1), + T4_A2 = CHELSIO_CHIP_CODE(CHELSIO_T4, 2), + T4_FIRST_REV = T4_A1, + T4_LAST_REV = T4_A2, + + T5_A0 = CHELSIO_CHIP_CODE(CHELSIO_T5, 0), + T5_A1 = CHELSIO_CHIP_CODE(CHELSIO_T5, 1), + T5_FIRST_REV = T5_A0, + T5_LAST_REV = T5_A1, +}; + /* Define static functions */ static inline int csio_is_t4(uint16_t chip) { @@ -80,10 +110,21 @@ static inline int csio_is_t5(uint16_t chip) (csio_is_t4(hw->chip_id) ? (PORT_REG(port, XGMAC_PORT_INT_CAUSE_A)) : \ (T5_PORT_REG(port, MAC_PORT_INT_CAUSE_A))) -#define FW_VERSION_MAJOR(hw) (csio_is_t4(hw->chip_id) ? 1 : 0) -#define FW_VERSION_MINOR(hw) (csio_is_t4(hw->chip_id) ? 2 : 0) -#define FW_VERSION_MICRO(hw) (csio_is_t4(hw->chip_id) ? 8 : 0) +#include "t4fw_api.h" +#define FW_VERSION(chip) ( \ + FW_HDR_FW_VER_MAJOR_G(chip##FW_VERSION_MAJOR) | \ + FW_HDR_FW_VER_MINOR_G(chip##FW_VERSION_MINOR) | \ + FW_HDR_FW_VER_MICRO_G(chip##FW_VERSION_MICRO) | \ + FW_HDR_FW_VER_BUILD_G(chip##FW_VERSION_BUILD)) +#define FW_INTFVER(chip, intf) (FW_HDR_INTFVER_##intf) + +struct fw_info { + u8 chip; + char *fs_name; + char *fw_mod_name; + struct fw_hdr fw_hdr; +}; #define CSIO_FW_FNAME(hw) \ (csio_is_t4(hw->chip_id) ? FW_FNAME_T4 : FW_FNAME_T5) diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index de1459c74c4d..326acd8c2e9f 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -113,7 +113,7 @@ struct rhashtable { struct bucket_table __rcu *tbl; struct bucket_table __rcu *future_tbl; atomic_t nelems; - size_t shift; + atomic_t shift; struct rhashtable_params p; struct delayed_work run_work; struct mutex mutex; @@ -168,6 +168,7 @@ int rhashtable_shrink(struct rhashtable *ht); void *rhashtable_lookup(struct rhashtable *ht, const void *key); void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key, bool (*compare)(void *, void *), void *arg); +bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj); void rhashtable_destroy(struct rhashtable *ht); diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index e863d088b9a5..b9b1b7d1c839 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -15,16 +15,19 @@ * *under construction* */ - +#if __UAPI_DEF_IN6_PKTINFO struct in6_pktinfo { struct in6_addr ipi6_addr; int ipi6_ifindex; }; +#endif +#if __UAPI_DEF_IP6_MTUINFO struct ip6_mtuinfo { struct sockaddr_in6 ip6m_addr; __u32 ip6m_mtu; }; +#endif struct in6_ifreq { struct in6_addr ifr6_addr; diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index e28807ad17fa..fa673e9cc040 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -70,6 +70,8 @@ #define __UAPI_DEF_IPV6_MREQ 0 #define __UAPI_DEF_IPPROTO_V6 0 #define __UAPI_DEF_IPV6_OPTIONS 0 +#define __UAPI_DEF_IN6_PKTINFO 0 +#define __UAPI_DEF_IP6_MTUINFO 0 #else @@ -84,6 +86,8 @@ #define __UAPI_DEF_IPV6_MREQ 1 #define __UAPI_DEF_IPPROTO_V6 1 #define __UAPI_DEF_IPV6_OPTIONS 1 +#define __UAPI_DEF_IN6_PKTINFO 1 +#define __UAPI_DEF_IP6_MTUINFO 1 #endif /* _NETINET_IN_H */ @@ -106,6 +110,8 @@ #define __UAPI_DEF_IPV6_MREQ 1 #define __UAPI_DEF_IPPROTO_V6 1 #define __UAPI_DEF_IPV6_OPTIONS 1 +#define __UAPI_DEF_IN6_PKTINFO 1 +#define __UAPI_DEF_IP6_MTUINFO 1 /* Definitions for xattr.h */ #define __UAPI_DEF_XATTR 1 diff --git a/lib/rhashtable.c b/lib/rhashtable.c index cbad192d3b3d..8023b554905c 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -199,7 +199,8 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size) { /* Expand table when exceeding 75% load */ - return atomic_read(&ht->nelems) > (new_size / 4 * 3); + return atomic_read(&ht->nelems) > (new_size / 4 * 3) && + (ht->p.max_shift && atomic_read(&ht->shift) < ht->p.max_shift); } EXPORT_SYMBOL_GPL(rht_grow_above_75); @@ -211,7 +212,8 @@ EXPORT_SYMBOL_GPL(rht_grow_above_75); bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size) { /* Shrink table beneath 30% load */ - return atomic_read(&ht->nelems) < (new_size * 3 / 10); + return atomic_read(&ht->nelems) < (new_size * 3 / 10) && + (atomic_read(&ht->shift) > ht->p.min_shift); } EXPORT_SYMBOL_GPL(rht_shrink_below_30); @@ -318,14 +320,11 @@ int rhashtable_expand(struct rhashtable *ht) ASSERT_RHT_MUTEX(ht); - if (ht->p.max_shift && ht->shift >= ht->p.max_shift) - return 0; - new_tbl = bucket_table_alloc(ht, old_tbl->size * 2); if (new_tbl == NULL) return -ENOMEM; - ht->shift++; + atomic_inc(&ht->shift); /* Make insertions go into the new, empty table right away. Deletions * and lookups will be attempted in both tables until we synchronize. @@ -421,9 +420,6 @@ int rhashtable_shrink(struct rhashtable *ht) ASSERT_RHT_MUTEX(ht); - if (ht->shift <= ht->p.min_shift) - return 0; - new_tbl = bucket_table_alloc(ht, tbl->size / 2); if (new_tbl == NULL) return -ENOMEM; @@ -462,7 +458,7 @@ int rhashtable_shrink(struct rhashtable *ht) /* Publish the new, valid hash table */ rcu_assign_pointer(ht->tbl, new_tbl); - ht->shift--; + atomic_dec(&ht->shift); /* Wait for readers. No new readers will have references to the * old hash table. @@ -492,8 +488,39 @@ static void rht_deferred_worker(struct work_struct *work) mutex_unlock(&ht->mutex); } +static void rhashtable_wakeup_worker(struct rhashtable *ht) +{ + struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); + struct bucket_table *new_tbl = rht_dereference_rcu(ht->future_tbl, ht); + size_t size = tbl->size; + + /* Only adjust the table if no resizing is currently in progress. */ + if (tbl == new_tbl && + ((ht->p.grow_decision && ht->p.grow_decision(ht, size)) || + (ht->p.shrink_decision && ht->p.shrink_decision(ht, size)))) + schedule_delayed_work(&ht->run_work, 0); +} + +static void __rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj, + struct bucket_table *tbl, u32 hash) +{ + struct rhash_head *head = rht_dereference_bucket(tbl->buckets[hash], + tbl, hash); + + if (rht_is_a_nulls(head)) + INIT_RHT_NULLS_HEAD(obj->next, ht, hash); + else + RCU_INIT_POINTER(obj->next, head); + + rcu_assign_pointer(tbl->buckets[hash], obj); + + atomic_inc(&ht->nelems); + + rhashtable_wakeup_worker(ht); +} + /** - * rhashtable_insert - insert object into hash hash table + * rhashtable_insert - insert object into hash table * @ht: hash table * @obj: pointer to hash head inside object * @@ -510,7 +537,6 @@ static void rht_deferred_worker(struct work_struct *work) void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj) { struct bucket_table *tbl; - struct rhash_head *head; spinlock_t *lock; unsigned hash; @@ -521,22 +547,9 @@ void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj) lock = bucket_lock(tbl, hash); spin_lock_bh(lock); - head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); - if (rht_is_a_nulls(head)) - INIT_RHT_NULLS_HEAD(obj->next, ht, hash); - else - RCU_INIT_POINTER(obj->next, head); - - rcu_assign_pointer(tbl->buckets[hash], obj); + __rhashtable_insert(ht, obj, tbl, hash); spin_unlock_bh(lock); - atomic_inc(&ht->nelems); - - /* Only grow the table if no resizing is currently in progress. */ - if (ht->tbl != ht->future_tbl && - ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size)) - schedule_delayed_work(&ht->run_work, 0); - rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rhashtable_insert); @@ -550,7 +563,7 @@ EXPORT_SYMBOL_GPL(rhashtable_insert); * walk the bucket chain upon removal. The removal operation is thus * considerable slow if the hash table is not correctly sized. * - * Will automatically shrink the table via rhashtable_expand() if the the + * Will automatically shrink the table via rhashtable_expand() if the * shrink_decision function specified at rhashtable_init() returns true. * * The caller must ensure that no concurrent table mutations occur. It is @@ -584,20 +597,17 @@ restart: spin_unlock_bh(lock); - if (ht->tbl != ht->future_tbl && - ht->p.shrink_decision && - ht->p.shrink_decision(ht, tbl->size)) - schedule_delayed_work(&ht->run_work, 0); + rhashtable_wakeup_worker(ht); rcu_read_unlock(); return true; } - if (tbl != rht_dereference_rcu(ht->tbl, ht)) { + if (tbl != rht_dereference_rcu(ht->future_tbl, ht)) { spin_unlock_bh(lock); - tbl = rht_dereference_rcu(ht->tbl, ht); + tbl = rht_dereference_rcu(ht->future_tbl, ht); hash = head_hashfn(ht, tbl, obj); lock = bucket_lock(tbl, hash); @@ -612,6 +622,19 @@ restart: } EXPORT_SYMBOL_GPL(rhashtable_remove); +struct rhashtable_compare_arg { + struct rhashtable *ht; + const void *key; +}; + +static bool rhashtable_compare(void *ptr, void *arg) +{ + struct rhashtable_compare_arg *x = arg; + struct rhashtable *ht = x->ht; + + return !memcmp(ptr + ht->p.key_offset, x->key, ht->p.key_len); +} + /** * rhashtable_lookup - lookup key in hash table * @ht: hash table @@ -621,38 +644,20 @@ EXPORT_SYMBOL_GPL(rhashtable_remove); * for a entry with an identical key. The first matching entry is returned. * * This lookup function may only be used for fixed key hash table (key_len - * paramter set). It will BUG() if used inappropriately. + * parameter set). It will BUG() if used inappropriately. * * Lookups may occur in parallel with hashtable mutations and resizing. */ void *rhashtable_lookup(struct rhashtable *ht, const void *key) { - const struct bucket_table *tbl, *old_tbl; - struct rhash_head *he; - u32 hash; + struct rhashtable_compare_arg arg = { + .ht = ht, + .key = key, + }; BUG_ON(!ht->p.key_len); - rcu_read_lock(); - old_tbl = rht_dereference_rcu(ht->tbl, ht); - tbl = rht_dereference_rcu(ht->future_tbl, ht); - hash = key_hashfn(ht, key, ht->p.key_len); -restart: - rht_for_each_rcu(he, tbl, rht_bucket_index(tbl, hash)) { - if (memcmp(rht_obj(ht, he) + ht->p.key_offset, key, - ht->p.key_len)) - continue; - rcu_read_unlock(); - return rht_obj(ht, he); - } - - if (unlikely(tbl != old_tbl)) { - tbl = old_tbl; - goto restart; - } - - rcu_read_unlock(); - return NULL; + return rhashtable_lookup_compare(ht, key, &rhashtable_compare, &arg); } EXPORT_SYMBOL_GPL(rhashtable_lookup); @@ -700,6 +705,66 @@ restart: } EXPORT_SYMBOL_GPL(rhashtable_lookup_compare); +/** + * rhashtable_lookup_insert - lookup and insert object into hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * + * Locks down the bucket chain in both the old and new table if a resize + * is in progress to ensure that writers can't remove from the old table + * and can't insert to the new table during the atomic operation of search + * and insertion. Searches for duplicates in both the old and new table if + * a resize is in progress. + * + * This lookup function may only be used for fixed key hash table (key_len + * parameter set). It will BUG() if used inappropriately. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + */ +bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj) +{ + struct bucket_table *new_tbl, *old_tbl; + spinlock_t *new_bucket_lock, *old_bucket_lock; + u32 new_hash, old_hash; + bool success = true; + + BUG_ON(!ht->p.key_len); + + rcu_read_lock(); + + old_tbl = rht_dereference_rcu(ht->tbl, ht); + old_hash = head_hashfn(ht, old_tbl, obj); + old_bucket_lock = bucket_lock(old_tbl, old_hash); + spin_lock_bh(old_bucket_lock); + + new_tbl = rht_dereference_rcu(ht->future_tbl, ht); + new_hash = head_hashfn(ht, new_tbl, obj); + new_bucket_lock = bucket_lock(new_tbl, new_hash); + if (unlikely(old_tbl != new_tbl)) + spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED); + + if (rhashtable_lookup(ht, rht_obj(ht, obj) + ht->p.key_offset)) { + success = false; + goto exit; + } + + __rhashtable_insert(ht, obj, new_tbl, new_hash); + +exit: + if (unlikely(old_tbl != new_tbl)) + spin_unlock_bh(new_bucket_lock); + spin_unlock_bh(old_bucket_lock); + + rcu_read_unlock(); + + return success; +} +EXPORT_SYMBOL_GPL(rhashtable_lookup_insert); + static size_t rounded_hashtable_size(struct rhashtable_params *params) { return max(roundup_pow_of_two(params->nelem_hint * 4 / 3), @@ -782,7 +847,8 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params) if (tbl == NULL) return -ENOMEM; - ht->shift = ilog2(tbl->size); + atomic_set(&ht->nelems, 0); + atomic_set(&ht->shift, ilog2(tbl->size)); RCU_INIT_POINTER(ht->tbl, tbl); RCU_INIT_POINTER(ht->future_tbl, tbl); diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index c890848f9d56..91c8a8e031db 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -20,18 +20,6 @@ menuconfig TIPC If in doubt, say N. -config TIPC_PORTS - int "Maximum number of ports in a node" - depends on TIPC - range 127 65535 - default "8191" - help - Specifies how many ports can be supported by a node. - Can range from 127 to 65535 ports; default is 8191. - - Setting this to a smaller value saves some memory, - setting it to higher allows for more ports. - config TIPC_MEDIA_IB bool "InfiniBand media type support" depends on TIPC && INFINIBAND_IPOIB diff --git a/net/tipc/config.c b/net/tipc/config.c index 876f4c6a2631..0b3a90ecab6d 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -183,22 +183,6 @@ static struct sk_buff *cfg_set_own_addr(void) return tipc_cfg_reply_error_string("cannot change to network mode"); } -static struct sk_buff *cfg_set_max_ports(void) -{ - u32 value; - - if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) - return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value == tipc_max_ports) - return tipc_cfg_reply_none(); - if (value < 127 || value > 65535) - return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE - " (max ports must be 127-65535)"); - return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED - " (cannot change max ports while TIPC is active)"); -} - static struct sk_buff *cfg_set_netid(void) { u32 value; @@ -285,15 +269,9 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SET_NODE_ADDR: rep_tlv_buf = cfg_set_own_addr(); break; - case TIPC_CMD_SET_MAX_PORTS: - rep_tlv_buf = cfg_set_max_ports(); - break; case TIPC_CMD_SET_NETID: rep_tlv_buf = cfg_set_netid(); break; - case TIPC_CMD_GET_MAX_PORTS: - rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_ports); - break; case TIPC_CMD_GET_NETID: rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_net_id); break; @@ -317,6 +295,8 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SET_REMOTE_MNG: case TIPC_CMD_GET_REMOTE_MNG: case TIPC_CMD_DUMP_LOG: + case TIPC_CMD_SET_MAX_PORTS: + case TIPC_CMD_GET_MAX_PORTS: rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (obsolete command)"); break; diff --git a/net/tipc/core.c b/net/tipc/core.c index a5737b8407dd..71b2ada0f5ab 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -34,6 +34,8 @@ * POSSIBILITY OF SUCH DAMAGE. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include "core.h" #include "name_table.h" #include "subscr.h" @@ -47,7 +49,6 @@ int tipc_random __read_mostly; /* configurable TIPC parameters */ u32 tipc_own_addr __read_mostly; -int tipc_max_ports __read_mostly; int tipc_net_id __read_mostly; int sysctl_tipc_rmem[3] __read_mostly; /* min/default/max */ @@ -84,9 +85,9 @@ static void tipc_core_stop(void) tipc_netlink_stop(); tipc_subscr_stop(); tipc_nametbl_stop(); - tipc_sk_ref_table_stop(); tipc_socket_stop(); tipc_unregister_sysctl(); + tipc_sk_rht_destroy(); } /** @@ -98,7 +99,7 @@ static int tipc_core_start(void) get_random_bytes(&tipc_random, sizeof(tipc_random)); - err = tipc_sk_ref_table_init(tipc_max_ports, tipc_random); + err = tipc_sk_rht_init(); if (err) goto out_reftbl; @@ -138,7 +139,7 @@ out_socket: out_netlink: tipc_nametbl_stop(); out_nametbl: - tipc_sk_ref_table_stop(); + tipc_sk_rht_destroy(); out_reftbl: return err; } @@ -150,7 +151,6 @@ static int __init tipc_init(void) pr_info("Activated (version " TIPC_MOD_VER ")\n"); tipc_own_addr = 0; - tipc_max_ports = CONFIG_TIPC_PORTS; tipc_net_id = 4711; sysctl_tipc_rmem[0] = TIPC_CONN_OVERLOAD_LIMIT >> 4 << diff --git a/net/tipc/core.h b/net/tipc/core.h index 84602137ce20..56fe4229fc5e 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -37,8 +37,6 @@ #ifndef _TIPC_CORE_H #define _TIPC_CORE_H -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include <linux/tipc.h> #include <linux/tipc_config.h> #include <linux/tipc_netlink.h> @@ -79,7 +77,6 @@ int tipc_snprintf(char *buf, int len, const char *fmt, ...); * Global configuration variables */ extern u32 tipc_own_addr __read_mostly; -extern int tipc_max_ports __read_mostly; extern int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 4731cad99d1c..701f31bbbbfb 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -34,22 +34,25 @@ * POSSIBILITY OF SUCH DAMAGE. */ +#include <linux/rhashtable.h> +#include <linux/jhash.h> #include "core.h" #include "name_table.h" #include "node.h" #include "link.h" -#include <linux/export.h> #include "config.h" #include "socket.h" -#define SS_LISTENING -1 /* socket is listening */ -#define SS_READY -2 /* socket is connectionless */ +#define SS_LISTENING -1 /* socket is listening */ +#define SS_READY -2 /* socket is connectionless */ -#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ -#define CONN_PROBING_INTERVAL 3600000 /* [ms] => 1 h */ -#define TIPC_FWD_MSG 1 -#define TIPC_CONN_OK 0 -#define TIPC_CONN_PROBING 1 +#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ +#define CONN_PROBING_INTERVAL 3600000 /* [ms] => 1 h */ +#define TIPC_FWD_MSG 1 +#define TIPC_CONN_OK 0 +#define TIPC_CONN_PROBING 1 +#define TIPC_MAX_PORT 0xffffffff +#define TIPC_MIN_PORT 1 /** * struct tipc_sock - TIPC socket structure @@ -59,7 +62,7 @@ * @conn_instance: TIPC instance used when connection was established * @published: non-zero if port has one or more associated names * @max_pkt: maximum packet size "hint" used when building messages sent by port - * @ref: unique reference to port in TIPC object registry + * @portid: unique port identity in TIPC socket hash table * @phdr: preformatted message header used when sending messages * @port_list: adjacent ports in TIPC's global list of ports * @publications: list of publications for port @@ -74,6 +77,8 @@ * @link_cong: non-zero if owner must sleep because of link congestion * @sent_unacked: # messages sent by socket, and not yet acked by peer * @rcv_unacked: # messages read by user, but not yet acked back to peer + * @node: hash table node + * @rcu: rcu struct for tipc_sock */ struct tipc_sock { struct sock sk; @@ -82,7 +87,7 @@ struct tipc_sock { u32 conn_instance; int published; u32 max_pkt; - u32 ref; + u32 portid; struct tipc_msg phdr; struct list_head sock_list; struct list_head publications; @@ -95,6 +100,8 @@ struct tipc_sock { bool link_cong; uint sent_unacked; uint rcv_unacked; + struct rhash_head node; + struct rcu_head rcu; }; static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb); @@ -103,16 +110,14 @@ static void tipc_write_space(struct sock *sk); static int tipc_release(struct socket *sock); static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags); static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p); -static void tipc_sk_timeout(unsigned long ref); +static void tipc_sk_timeout(unsigned long portid); static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); -static u32 tipc_sk_ref_acquire(struct tipc_sock *tsk); -static void tipc_sk_ref_discard(u32 ref); -static struct tipc_sock *tipc_sk_get(u32 ref); -static struct tipc_sock *tipc_sk_get_next(u32 *ref); -static void tipc_sk_put(struct tipc_sock *tsk); +static struct tipc_sock *tipc_sk_lookup(u32 portid); +static int tipc_sk_insert(struct tipc_sock *tsk); +static void tipc_sk_remove(struct tipc_sock *tsk); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -174,6 +179,9 @@ static const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = { * - port reference */ +/* Protects tipc socket hash table mutations */ +static struct rhashtable tipc_sk_rht; + static u32 tsk_peer_node(struct tipc_sock *tsk) { return msg_destnode(&tsk->phdr); @@ -305,7 +313,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock, struct sock *sk; struct tipc_sock *tsk; struct tipc_msg *msg; - u32 ref; /* Validate arguments */ if (unlikely(protocol != 0)) @@ -339,24 +346,22 @@ static int tipc_sk_create(struct net *net, struct socket *sock, return -ENOMEM; tsk = tipc_sk(sk); - ref = tipc_sk_ref_acquire(tsk); - if (!ref) { - pr_warn("Socket create failed; reference table exhausted\n"); - return -ENOMEM; - } tsk->max_pkt = MAX_PKT_DEFAULT; - tsk->ref = ref; INIT_LIST_HEAD(&tsk->publications); msg = &tsk->phdr; tipc_msg_init(msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG, NAMED_H_SIZE, 0); - msg_set_origport(msg, ref); /* Finish initializing socket data structures */ sock->ops = ops; sock->state = state; sock_init_data(sock, sk); - k_init_timer(&tsk->timer, (Handler)tipc_sk_timeout, ref); + if (tipc_sk_insert(tsk)) { + pr_warn("Socket create failed; port numbrer exhausted\n"); + return -EINVAL; + } + msg_set_origport(msg, tsk->portid); + k_init_timer(&tsk->timer, (Handler)tipc_sk_timeout, tsk->portid); sk->sk_backlog_rcv = tipc_backlog_rcv; sk->sk_rcvbuf = sysctl_tipc_rmem[1]; sk->sk_data_ready = tipc_data_ready; @@ -442,6 +447,13 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, return ret; } +static void tipc_sk_callback(struct rcu_head *head) +{ + struct tipc_sock *tsk = container_of(head, struct tipc_sock, rcu); + + sock_put(&tsk->sk); +} + /** * tipc_release - destroy a TIPC socket * @sock: socket to destroy @@ -491,7 +503,7 @@ static int tipc_release(struct socket *sock) (sock->state == SS_CONNECTED)) { sock->state = SS_DISCONNECTING; tsk->connected = 0; - tipc_node_remove_conn(dnode, tsk->ref); + tipc_node_remove_conn(dnode, tsk->portid); } if (tipc_msg_reverse(skb, &dnode, TIPC_ERR_NO_PORT)) tipc_link_xmit_skb(skb, dnode, 0); @@ -499,16 +511,16 @@ static int tipc_release(struct socket *sock) } tipc_sk_withdraw(tsk, 0, NULL); - tipc_sk_ref_discard(tsk->ref); k_cancel_timer(&tsk->timer); + tipc_sk_remove(tsk); if (tsk->connected) { skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode, tipc_own_addr, tsk_peer_port(tsk), - tsk->ref, TIPC_ERR_NO_PORT); + tsk->portid, TIPC_ERR_NO_PORT); if (skb) - tipc_link_xmit_skb(skb, dnode, tsk->ref); - tipc_node_remove_conn(dnode, tsk->ref); + tipc_link_xmit_skb(skb, dnode, tsk->portid); + tipc_node_remove_conn(dnode, tsk->portid); } k_term_timer(&tsk->timer); @@ -518,7 +530,8 @@ static int tipc_release(struct socket *sock) /* Reject any messages that accumulated in backlog queue */ sock->state = SS_DISCONNECTING; release_sock(sk); - sock_put(sk); + + call_rcu(&tsk->rcu, tipc_sk_callback); sock->sk = NULL; return 0; @@ -611,7 +624,7 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr, addr->addr.id.ref = tsk_peer_port(tsk); addr->addr.id.node = tsk_peer_node(tsk); } else { - addr->addr.id.ref = tsk->ref; + addr->addr.id.ref = tsk->portid; addr->addr.id.node = tipc_own_addr; } @@ -946,7 +959,7 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, } new_mtu: - mtu = tipc_node_get_mtu(dnode, tsk->ref); + mtu = tipc_node_get_mtu(dnode, tsk->portid); __skb_queue_head_init(&head); rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &head); if (rc < 0) @@ -955,7 +968,7 @@ new_mtu: do { skb = skb_peek(&head); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_link_xmit(&head, dnode, tsk->ref); + rc = tipc_link_xmit(&head, dnode, tsk->portid); if (likely(rc >= 0)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; @@ -1028,7 +1041,7 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, struct tipc_msg *mhdr = &tsk->phdr; struct sk_buff_head head; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); - u32 ref = tsk->ref; + u32 portid = tsk->portid; int rc = -EINVAL; long timeo; u32 dnode; @@ -1067,7 +1080,7 @@ next: goto exit; do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_link_xmit(&head, dnode, ref); + rc = tipc_link_xmit(&head, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; @@ -1076,7 +1089,7 @@ next: goto next; } if (rc == -EMSGSIZE) { - tsk->max_pkt = tipc_node_get_mtu(dnode, ref); + tsk->max_pkt = tipc_node_get_mtu(dnode, portid); goto next; } if (rc != -ELINKCONG) @@ -1130,8 +1143,8 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port, tsk->probing_state = TIPC_CONN_OK; tsk->connected = 1; k_start_timer(&tsk->timer, tsk->probing_interval); - tipc_node_add_conn(peer_node, tsk->ref, peer_port); - tsk->max_pkt = tipc_node_get_mtu(peer_node, tsk->ref); + tipc_node_add_conn(peer_node, tsk->portid, peer_port); + tsk->max_pkt = tipc_node_get_mtu(peer_node, tsk->portid); } /** @@ -1238,7 +1251,7 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack) if (!tsk->connected) return; skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0, dnode, - tipc_own_addr, peer_port, tsk->ref, TIPC_OK); + tipc_own_addr, peer_port, tsk->portid, TIPC_OK); if (!skb) return; msg = buf_msg(skb); @@ -1552,7 +1565,7 @@ static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf) tsk->connected = 0; /* let timer expire on it's own */ tipc_node_remove_conn(tsk_peer_node(tsk), - tsk->ref); + tsk->portid); } retval = TIPC_OK; } @@ -1743,7 +1756,7 @@ int tipc_sk_rcv(struct sk_buff *skb) u32 dnode; /* Validate destination and message */ - tsk = tipc_sk_get(dport); + tsk = tipc_sk_lookup(dport); if (unlikely(!tsk)) { rc = tipc_msg_eval(skb, &dnode); goto exit; @@ -1763,7 +1776,7 @@ int tipc_sk_rcv(struct sk_buff *skb) rc = -TIPC_ERR_OVERLOAD; } spin_unlock_bh(&sk->sk_lock.slock); - tipc_sk_put(tsk); + sock_put(sk); if (likely(!rc)) return 0; exit: @@ -2050,20 +2063,20 @@ restart: goto restart; } if (tipc_msg_reverse(skb, &dnode, TIPC_CONN_SHUTDOWN)) - tipc_link_xmit_skb(skb, dnode, tsk->ref); - tipc_node_remove_conn(dnode, tsk->ref); + tipc_link_xmit_skb(skb, dnode, tsk->portid); + tipc_node_remove_conn(dnode, tsk->portid); } else { dnode = tsk_peer_node(tsk); skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode, tipc_own_addr, tsk_peer_port(tsk), - tsk->ref, TIPC_CONN_SHUTDOWN); - tipc_link_xmit_skb(skb, dnode, tsk->ref); + tsk->portid, TIPC_CONN_SHUTDOWN); + tipc_link_xmit_skb(skb, dnode, tsk->portid); } tsk->connected = 0; sock->state = SS_DISCONNECTING; - tipc_node_remove_conn(dnode, tsk->ref); + tipc_node_remove_conn(dnode, tsk->portid); /* fall through */ case SS_DISCONNECTING: @@ -2084,14 +2097,14 @@ restart: return res; } -static void tipc_sk_timeout(unsigned long ref) +static void tipc_sk_timeout(unsigned long portid) { struct tipc_sock *tsk; struct sock *sk; struct sk_buff *skb = NULL; u32 peer_port, peer_node; - tsk = tipc_sk_get(ref); + tsk = tipc_sk_lookup(portid); if (!tsk) return; @@ -2108,20 +2121,20 @@ static void tipc_sk_timeout(unsigned long ref) /* Previous probe not answered -> self abort */ skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, 0, tipc_own_addr, - peer_node, ref, peer_port, + peer_node, portid, peer_port, TIPC_ERR_NO_PORT); } else { skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE, INT_H_SIZE, 0, peer_node, tipc_own_addr, - peer_port, ref, TIPC_OK); + peer_port, portid, TIPC_OK); tsk->probing_state = TIPC_CONN_PROBING; k_start_timer(&tsk->timer, tsk->probing_interval); } bh_unlock_sock(sk); if (skb) - tipc_link_xmit_skb(skb, peer_node, ref); + tipc_link_xmit_skb(skb, peer_node, portid); exit: - tipc_sk_put(tsk); + sock_put(sk); } static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, @@ -2132,12 +2145,12 @@ static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, if (tsk->connected) return -EINVAL; - key = tsk->ref + tsk->pub_count + 1; - if (key == tsk->ref) + key = tsk->portid + tsk->pub_count + 1; + if (key == tsk->portid) return -EADDRINUSE; publ = tipc_nametbl_publish(seq->type, seq->lower, seq->upper, - scope, tsk->ref, key); + scope, tsk->portid, key); if (unlikely(!publ)) return -EINVAL; @@ -2188,9 +2201,9 @@ static int tipc_sk_show(struct tipc_sock *tsk, char *buf, ret = tipc_snprintf(buf, len, "<%u.%u.%u:%u>:", tipc_zone(tipc_own_addr), tipc_cluster(tipc_own_addr), - tipc_node(tipc_own_addr), tsk->ref); + tipc_node(tipc_own_addr), tsk->portid); else - ret = tipc_snprintf(buf, len, "%-10u:", tsk->ref); + ret = tipc_snprintf(buf, len, "%-10u:", tsk->portid); if (tsk->connected) { u32 dport = tsk_peer_port(tsk); @@ -2224,13 +2237,15 @@ static int tipc_sk_show(struct tipc_sock *tsk, char *buf, struct sk_buff *tipc_sk_socks_show(void) { + const struct bucket_table *tbl; + struct rhash_head *pos; struct sk_buff *buf; struct tlv_desc *rep_tlv; char *pb; int pb_len; struct tipc_sock *tsk; int str_len = 0; - u32 ref = 0; + int i; buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN)); if (!buf) @@ -2239,14 +2254,18 @@ struct sk_buff *tipc_sk_socks_show(void) pb = TLV_DATA(rep_tlv); pb_len = ULTRA_STRING_MAX_LEN; - tsk = tipc_sk_get_next(&ref); - for (; tsk; tsk = tipc_sk_get_next(&ref)) { - lock_sock(&tsk->sk); - str_len += tipc_sk_show(tsk, pb + str_len, - pb_len - str_len, 0); - release_sock(&tsk->sk); - tipc_sk_put(tsk); + rcu_read_lock(); + tbl = rht_dereference_rcu((&tipc_sk_rht)->tbl, &tipc_sk_rht); + for (i = 0; i < tbl->size; i++) { + rht_for_each_entry_rcu(tsk, pos, tbl, i, node) { + spin_lock_bh(&tsk->sk.sk_lock.slock); + str_len += tipc_sk_show(tsk, pb + str_len, + pb_len - str_len, 0); + spin_unlock_bh(&tsk->sk.sk_lock.slock); + } } + rcu_read_unlock(); + str_len += 1; /* for "\0" */ skb_put(buf, TLV_SPACE(str_len)); TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); @@ -2259,255 +2278,91 @@ struct sk_buff *tipc_sk_socks_show(void) */ void tipc_sk_reinit(void) { + const struct bucket_table *tbl; + struct rhash_head *pos; + struct tipc_sock *tsk; struct tipc_msg *msg; - u32 ref = 0; - struct tipc_sock *tsk = tipc_sk_get_next(&ref); + int i; - for (; tsk; tsk = tipc_sk_get_next(&ref)) { - lock_sock(&tsk->sk); - msg = &tsk->phdr; - msg_set_prevnode(msg, tipc_own_addr); - msg_set_orignode(msg, tipc_own_addr); - release_sock(&tsk->sk); - tipc_sk_put(tsk); + rcu_read_lock(); + tbl = rht_dereference_rcu((&tipc_sk_rht)->tbl, &tipc_sk_rht); + for (i = 0; i < tbl->size; i++) { + rht_for_each_entry_rcu(tsk, pos, tbl, i, node) { + spin_lock_bh(&tsk->sk.sk_lock.slock); + msg = &tsk->phdr; + msg_set_prevnode(msg, tipc_own_addr); + msg_set_orignode(msg, tipc_own_addr); + spin_unlock_bh(&tsk->sk.sk_lock.slock); + } } + rcu_read_unlock(); } -/** - * struct reference - TIPC socket reference entry - * @tsk: pointer to socket associated with reference entry - * @ref: reference value for socket (combines instance & array index info) - */ -struct reference { - struct tipc_sock *tsk; - u32 ref; -}; - -/** - * struct tipc_ref_table - table of TIPC socket reference entries - * @entries: pointer to array of reference entries - * @capacity: array index of first unusable entry - * @init_point: array index of first uninitialized entry - * @first_free: array index of first unused socket reference entry - * @last_free: array index of last unused socket reference entry - * @index_mask: bitmask for array index portion of reference values - * @start_mask: initial value for instance value portion of reference values - */ -struct ref_table { - struct reference *entries; - u32 capacity; - u32 init_point; - u32 first_free; - u32 last_free; - u32 index_mask; - u32 start_mask; -}; - -/* Socket reference table consists of 2**N entries. - * - * State Socket ptr Reference - * ----- ---------- --------- - * In use non-NULL XXXX|own index - * (XXXX changes each time entry is acquired) - * Free NULL YYYY|next free index - * (YYYY is one more than last used XXXX) - * Uninitialized NULL 0 - * - * Entry 0 is not used; this allows index 0 to denote the end of the free list. - * - * Note that a reference value of 0 does not necessarily indicate that an - * entry is uninitialized, since the last entry in the free list could also - * have a reference value of 0 (although this is unlikely). - */ - -static struct ref_table tipc_ref_table; - -static DEFINE_RWLOCK(ref_table_lock); - -/** - * tipc_ref_table_init - create reference table for sockets - */ -int tipc_sk_ref_table_init(u32 req_sz, u32 start) +static struct tipc_sock *tipc_sk_lookup(u32 portid) { - struct reference *table; - u32 actual_sz; - - /* account for unused entry, then round up size to a power of 2 */ - - req_sz++; - for (actual_sz = 16; actual_sz < req_sz; actual_sz <<= 1) { - /* do nothing */ - }; - - /* allocate table & mark all entries as uninitialized */ - table = vzalloc(actual_sz * sizeof(struct reference)); - if (table == NULL) - return -ENOMEM; - - tipc_ref_table.entries = table; - tipc_ref_table.capacity = req_sz; - tipc_ref_table.init_point = 1; - tipc_ref_table.first_free = 0; - tipc_ref_table.last_free = 0; - tipc_ref_table.index_mask = actual_sz - 1; - tipc_ref_table.start_mask = start & ~tipc_ref_table.index_mask; + struct tipc_sock *tsk; - return 0; -} + rcu_read_lock(); + tsk = rhashtable_lookup(&tipc_sk_rht, &portid); + if (tsk) + sock_hold(&tsk->sk); + rcu_read_unlock(); -/** - * tipc_ref_table_stop - destroy reference table for sockets - */ -void tipc_sk_ref_table_stop(void) -{ - if (!tipc_ref_table.entries) - return; - vfree(tipc_ref_table.entries); - tipc_ref_table.entries = NULL; + return tsk; } -/* tipc_ref_acquire - create reference to a socket - * - * Register an socket pointer in the reference table. - * Returns a unique reference value that is used from then on to retrieve the - * socket pointer, or to determine if the socket has been deregistered. - */ -u32 tipc_sk_ref_acquire(struct tipc_sock *tsk) +static int tipc_sk_insert(struct tipc_sock *tsk) { - u32 index; - u32 index_mask; - u32 next_plus_upper; - u32 ref = 0; - struct reference *entry; - - if (unlikely(!tsk)) { - pr_err("Attempt to acquire ref. to non-existent obj\n"); - return 0; - } - if (unlikely(!tipc_ref_table.entries)) { - pr_err("Ref. table not found in acquisition attempt\n"); - return 0; - } - - /* Take a free entry, if available; otherwise initialize a new one */ - write_lock_bh(&ref_table_lock); - index = tipc_ref_table.first_free; - entry = &tipc_ref_table.entries[index]; + u32 remaining = (TIPC_MAX_PORT - TIPC_MIN_PORT) + 1; + u32 portid = prandom_u32() % remaining + TIPC_MIN_PORT; - if (likely(index)) { - index = tipc_ref_table.first_free; - entry = &tipc_ref_table.entries[index]; - index_mask = tipc_ref_table.index_mask; - next_plus_upper = entry->ref; - tipc_ref_table.first_free = next_plus_upper & index_mask; - ref = (next_plus_upper & ~index_mask) + index; - entry->tsk = tsk; - } else if (tipc_ref_table.init_point < tipc_ref_table.capacity) { - index = tipc_ref_table.init_point++; - entry = &tipc_ref_table.entries[index]; - ref = tipc_ref_table.start_mask + index; + while (remaining--) { + portid++; + if ((portid < TIPC_MIN_PORT) || (portid > TIPC_MAX_PORT)) + portid = TIPC_MIN_PORT; + tsk->portid = portid; + sock_hold(&tsk->sk); + if (rhashtable_lookup_insert(&tipc_sk_rht, &tsk->node)) + return 0; + sock_put(&tsk->sk); } - if (ref) { - entry->ref = ref; - entry->tsk = tsk; - } - write_unlock_bh(&ref_table_lock); - return ref; + return -1; } -/* tipc_sk_ref_discard - invalidate reference to an socket - * - * Disallow future references to an socket and free up the entry for re-use. - */ -void tipc_sk_ref_discard(u32 ref) +static void tipc_sk_remove(struct tipc_sock *tsk) { - struct reference *entry; - u32 index; - u32 index_mask; - - if (unlikely(!tipc_ref_table.entries)) { - pr_err("Ref. table not found during discard attempt\n"); - return; - } - - index_mask = tipc_ref_table.index_mask; - index = ref & index_mask; - entry = &tipc_ref_table.entries[index]; - - write_lock_bh(&ref_table_lock); + struct sock *sk = &tsk->sk; - if (unlikely(!entry->tsk)) { - pr_err("Attempt to discard ref. to non-existent socket\n"); - goto exit; - } - if (unlikely(entry->ref != ref)) { - pr_err("Attempt to discard non-existent reference\n"); - goto exit; + if (rhashtable_remove(&tipc_sk_rht, &tsk->node)) { + WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + __sock_put(sk); } - - /* Mark entry as unused; increment instance part of entry's - * reference to invalidate any subsequent references - */ - - entry->tsk = NULL; - entry->ref = (ref & ~index_mask) + (index_mask + 1); - - /* Append entry to free entry list */ - if (unlikely(tipc_ref_table.first_free == 0)) - tipc_ref_table.first_free = index; - else - tipc_ref_table.entries[tipc_ref_table.last_free].ref |= index; - tipc_ref_table.last_free = index; -exit: - write_unlock_bh(&ref_table_lock); } -/* tipc_sk_get - find referenced socket and return pointer to it - */ -struct tipc_sock *tipc_sk_get(u32 ref) +int tipc_sk_rht_init(void) { - struct reference *entry; - struct tipc_sock *tsk; + struct rhashtable_params rht_params = { + .nelem_hint = 192, + .head_offset = offsetof(struct tipc_sock, node), + .key_offset = offsetof(struct tipc_sock, portid), + .key_len = sizeof(u32), /* portid */ + .hashfn = jhash, + .max_shift = 20, /* 1M */ + .min_shift = 8, /* 256 */ + .grow_decision = rht_grow_above_75, + .shrink_decision = rht_shrink_below_30, + }; - if (unlikely(!tipc_ref_table.entries)) - return NULL; - read_lock_bh(&ref_table_lock); - entry = &tipc_ref_table.entries[ref & tipc_ref_table.index_mask]; - tsk = entry->tsk; - if (likely(tsk && (entry->ref == ref))) - sock_hold(&tsk->sk); - else - tsk = NULL; - read_unlock_bh(&ref_table_lock); - return tsk; + return rhashtable_init(&tipc_sk_rht, &rht_params); } -/* tipc_sk_get_next - lock & return next socket after referenced one -*/ -struct tipc_sock *tipc_sk_get_next(u32 *ref) +void tipc_sk_rht_destroy(void) { - struct reference *entry; - struct tipc_sock *tsk = NULL; - uint index = *ref & tipc_ref_table.index_mask; + /* Wait for socket readers to complete */ + synchronize_net(); - read_lock_bh(&ref_table_lock); - while (++index < tipc_ref_table.capacity) { - entry = &tipc_ref_table.entries[index]; - if (!entry->tsk) - continue; - tsk = entry->tsk; - sock_hold(&tsk->sk); - *ref = entry->ref; - break; - } - read_unlock_bh(&ref_table_lock); - return tsk; -} - -static void tipc_sk_put(struct tipc_sock *tsk) -{ - sock_put(&tsk->sk); + rhashtable_destroy(&tipc_sk_rht); } /** @@ -2829,7 +2684,7 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb, attrs = nla_nest_start(skb, TIPC_NLA_SOCK); if (!attrs) goto genlmsg_cancel; - if (nla_put_u32(skb, TIPC_NLA_SOCK_REF, tsk->ref)) + if (nla_put_u32(skb, TIPC_NLA_SOCK_REF, tsk->portid)) goto attr_msg_cancel; if (nla_put_u32(skb, TIPC_NLA_SOCK_ADDR, tipc_own_addr)) goto attr_msg_cancel; @@ -2859,22 +2714,29 @@ int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; struct tipc_sock *tsk; - u32 prev_ref = cb->args[0]; - u32 ref = prev_ref; - - tsk = tipc_sk_get_next(&ref); - for (; tsk; tsk = tipc_sk_get_next(&ref)) { - lock_sock(&tsk->sk); - err = __tipc_nl_add_sk(skb, cb, tsk); - release_sock(&tsk->sk); - tipc_sk_put(tsk); - if (err) - break; + const struct bucket_table *tbl; + struct rhash_head *pos; + u32 prev_portid = cb->args[0]; + u32 portid = prev_portid; + int i; - prev_ref = ref; + rcu_read_lock(); + tbl = rht_dereference_rcu((&tipc_sk_rht)->tbl, &tipc_sk_rht); + for (i = 0; i < tbl->size; i++) { + rht_for_each_entry_rcu(tsk, pos, tbl, i, node) { + spin_lock_bh(&tsk->sk.sk_lock.slock); + portid = tsk->portid; + err = __tipc_nl_add_sk(skb, cb, tsk); + spin_unlock_bh(&tsk->sk.sk_lock.slock); + if (err) + break; + + prev_portid = portid; + } } + rcu_read_unlock(); - cb->args[0] = prev_ref; + cb->args[0] = prev_portid; return skb->len; } @@ -2962,12 +2824,12 @@ static int __tipc_nl_list_sk_publ(struct sk_buff *skb, int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; - u32 tsk_ref = cb->args[0]; + u32 tsk_portid = cb->args[0]; u32 last_publ = cb->args[1]; u32 done = cb->args[2]; struct tipc_sock *tsk; - if (!tsk_ref) { + if (!tsk_portid) { struct nlattr **attrs; struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1]; @@ -2984,13 +2846,13 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!sock[TIPC_NLA_SOCK_REF]) return -EINVAL; - tsk_ref = nla_get_u32(sock[TIPC_NLA_SOCK_REF]); + tsk_portid = nla_get_u32(sock[TIPC_NLA_SOCK_REF]); } if (done) return 0; - tsk = tipc_sk_get(tsk_ref); + tsk = tipc_sk_lookup(tsk_portid); if (!tsk) return -EINVAL; @@ -2999,9 +2861,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!err) done = 1; release_sock(&tsk->sk); - tipc_sk_put(tsk); + sock_put(&tsk->sk); - cb->args[0] = tsk_ref; + cb->args[0] = tsk_portid; cb->args[1] = last_publ; cb->args[2] = done; diff --git a/net/tipc/socket.h b/net/tipc/socket.h index d34089387006..c7d46d069d89 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -46,8 +46,8 @@ int tipc_sk_rcv(struct sk_buff *buf); struct sk_buff *tipc_sk_socks_show(void); void tipc_sk_mcast_rcv(struct sk_buff *buf); void tipc_sk_reinit(void); -int tipc_sk_ref_table_init(u32 requested_size, u32 start); -void tipc_sk_ref_table_stop(void); +int tipc_sk_rht_init(void); +void tipc_sk_rht_destroy(void); int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb); |