KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
endif
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/cc-can-link.sh $(CC)), y)
- CC_CAN_LINK := y
- export CC_CAN_LINK
-endif
-
# The expansion should be delayed until arch/$(SRCARCH)/Makefile is included.
# Some architectures define CROSS_COMPILE in arch/$(SRCARCH)/Makefile.
# CC_VERSION_TEXT is referenced from Kconfig (so it needs export),
obj-$(CONFIG_TRUSTED_FOUNDATIONS) += trusted_foundations.o
+
+# tf_generic_smc() fails to build with -fsanitize-coverage=trace-pc
+KCOV_INSTRUMENT := n
/* there are 2 passes here */
bpf_jit_dump(prog->len, image_size, 2, ctx.target);
- set_memory_ro((unsigned long)header, header->pages);
+ bpf_jit_binary_lock_ro(header);
prog->bpf_func = (void *)ctx.target;
prog->jited = 1;
prog->jited_len = image_size;
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page,
unsigned long address)
{
+ pgtable_page_dtor(page);
__free_page(page);
}
return page;
}
-extern inline void pte_free(struct mm_struct *mm, struct page *page)
+static inline void pte_free(struct mm_struct *mm, struct page *page)
{
+ pgtable_page_dtor(page);
__free_page(page);
}
__free_page(pte);
}
+#define __pte_free_tlb(tlb, pte, addr) \
+do { \
+ pgtable_page_dtor(pte); \
+ tlb_remove_page((tlb), (pte)); \
+} while (0)
-#define __pte_free_tlb(tlb, pte, addr) tlb_remove_page((tlb), (pte))
#define pmd_pgtable(pmd) pmd_page(pmd)
#define check_pgt_cache() do { } while (0)
l.addi r3,r1,0 // pt_regs
/* r4 set be EXCEPTION_HANDLE */ // effective address of fault
- /*
- * __PHX__: TODO
- *
- * all this can be written much simpler. look at
- * DTLB miss handler in the CONFIG_GUARD_PROTECTED_CORE part
- */
#ifdef CONFIG_OPENRISC_NO_SPR_SR_DSX
l.lwz r6,PT_PC(r3) // address of an offending insn
l.lwz r6,0(r6) // instruction that caused pf
#else
- l.lwz r6,PT_SR(r3) // SR
+ l.mfspr r6,r0,SPR_SR // SR
l.andi r6,r6,SPR_SR_DSX // check for delay slot exception
l.sfne r6,r0 // exception happened in delay slot
l.bnf 7f
* r4 - EEAR exception EA
* r10 - current pointing to current_thread_info struct
* r12 - syscall 0, since we didn't come from syscall
- * r13 - temp it actually contains new SR, not needed anymore
- * r31 - handler address of the handler we'll jump to
+ * r30 - handler address of the handler we'll jump to
*
* handler has to save remaining registers to the exception
* ksp frame *before* tainting them!
/* r1 is KSP, r30 is __pa(KSP) */ ;\
tophys (r30,r1) ;\
l.sw PT_GPR12(r30),r12 ;\
+ /* r4 use for tmp before EA */ ;\
l.mfspr r12,r0,SPR_EPCR_BASE ;\
l.sw PT_PC(r30),r12 ;\
l.mfspr r12,r0,SPR_ESR_BASE ;\
/* r12 == 1 if we come from syscall */ ;\
CLEAR_GPR(r12) ;\
/* ----- turn on MMU ----- */ ;\
- l.ori r30,r0,(EXCEPTION_SR) ;\
+ /* Carry DSX into exception SR */ ;\
+ l.mfspr r30,r0,SPR_SR ;\
+ l.andi r30,r30,SPR_SR_DSX ;\
+ l.ori r30,r30,(EXCEPTION_SR) ;\
l.mtspr r0,r30,SPR_ESR_BASE ;\
/* r30: EA address of handler */ ;\
LOAD_SYMBOL_2_GPR(r30,handler) ;\
return 0;
}
#else
- return regs->sr & SPR_SR_DSX;
+ return mfspr(SPR_SR) & SPR_SR_DSX;
#endif
}
select GENERIC_LIB_ASHLDI3
select GENERIC_LIB_ASHRDI3
select GENERIC_LIB_LSHRDI3
+ select GENERIC_LIB_UCMPDI2
config ARCH_RV64I
bool "RV64I"
typedef union __riscv_fp_state elf_fpregset_t;
-#define ELF_RISCV_R_SYM(r_info) ((r_info) >> 32)
-#define ELF_RISCV_R_TYPE(r_info) ((r_info) & 0xffffffff)
+#if __riscv_xlen == 64
+#define ELF_RISCV_R_SYM(r_info) ELF64_R_SYM(r_info)
+#define ELF_RISCV_R_TYPE(r_info) ELF64_R_TYPE(r_info)
+#else
+#define ELF_RISCV_R_SYM(r_info) ELF32_R_SYM(r_info)
+#define ELF_RISCV_R_TYPE(r_info) ELF32_R_TYPE(r_info)
+#endif
/*
* RISC-V relocation types
#include <linux/irqchip.h>
#include <linux/irqdomain.h>
-#ifdef CONFIG_RISCV_INTC
-#include <linux/irqchip/irq-riscv-intc.h>
-#endif
-
void __init init_IRQ(void)
{
irqchip_init();
static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
u32 imm12 = (offset & 0x1000) << (31 - 12);
u32 imm11 = (offset & 0x800) >> (11 - 7);
u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
u32 imm20 = (offset & 0x100000) << (31 - 20);
u32 imm19_12 = (offset & 0xff000);
u32 imm11 = (offset & 0x800) << (20 - 11);
static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
u16 imm8 = (offset & 0x100) << (12 - 8);
u16 imm7_6 = (offset & 0xc0) >> (6 - 5);
u16 imm5 = (offset & 0x20) >> (5 - 2);
static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
u16 imm11 = (offset & 0x800) << (12 - 11);
u16 imm10 = (offset & 0x400) >> (10 - 8);
u16 imm9_8 = (offset & 0x300) << (12 - 11);
static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
s32 hi20;
if (offset != (s32)offset) {
static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
s32 hi20;
/* Always emit the got entry */
static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
s32 fill_v = offset;
u32 hi20, lo12;
static int apply_r_riscv_call_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- s64 offset = (void *)v - (void *)location;
+ ptrdiff_t offset = (void *)v - (void *)location;
s32 fill_v = offset;
u32 hi20, lo12;
static int apply_r_riscv_add32_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- *(u32 *)location += (*(u32 *)v);
+ *(u32 *)location += (u32)v;
return 0;
}
static int apply_r_riscv_sub32_rela(struct module *me, u32 *location,
Elf_Addr v)
{
- *(u32 *)location -= (*(u32 *)v);
+ *(u32 *)location -= (u32)v;
return 0;
}
unsigned int j;
for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
- u64 hi20_loc =
+ unsigned long hi20_loc =
sechdrs[sechdrs[relsec].sh_info].sh_addr
+ rel[j].r_offset;
u32 hi20_type = ELF_RISCV_R_TYPE(rel[j].r_info);
Elf_Sym *hi20_sym =
(Elf_Sym *)sechdrs[symindex].sh_addr
+ ELF_RISCV_R_SYM(rel[j].r_info);
- u64 hi20_sym_val =
+ unsigned long hi20_sym_val =
hi20_sym->st_value
+ rel[j].r_addend;
/* Calculate lo12 */
- u64 offset = hi20_sym_val - hi20_loc;
+ size_t offset = hi20_sym_val - hi20_loc;
if (IS_ENABLED(CONFIG_MODULE_SECTIONS)
&& hi20_type == R_RISCV_GOT_HI20) {
offset = module_emit_got_entry(
struct pt_regs *regs;
regs = task_pt_regs(target);
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0, -1);
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
return ret;
}
riscv_fill_hwcap();
}
-static int __init riscv_device_init(void)
-{
- return of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-subsys_initcall_sync(riscv_device_init);
{
unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
+#ifdef CONFIG_ZONE_DMA32
max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn));
+#endif
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
free_area_init_nodes(max_zone_pfns);
goto free_addrs;
}
if (bpf_jit_prog(&jit, fp)) {
+ bpf_jit_binary_free(header);
fp = orig_fp;
goto free_addrs;
}
skb_queue_head_init(&iadev->rx_dma_q);
iadev->rx_free_desc_qhead = NULL;
- iadev->rx_open = kcalloc(4, iadev->num_vc, GFP_KERNEL);
+ iadev->rx_open = kcalloc(iadev->num_vc, sizeof(void *), GFP_KERNEL);
if (!iadev->rx_open) {
printk(KERN_ERR DEV_LABEL "itf %d couldn't get free page\n",
dev->number);
return -EFAULT;
if (pool < 0 || pool > ZATM_LAST_POOL)
return -EINVAL;
+ pool = array_index_nospec(pool,
+ ZATM_LAST_POOL + 1);
if (copy_from_user(&info,
&((struct zatm_pool_req __user *) arg)->info,
sizeof(info))) return -EFAULT;
dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
MLX5_CAP_GEN(mdev, num_vhca_ports));
- if (MLX5_VPORT_MANAGER(mdev) &&
+ if (MLX5_ESWITCH_MANAGER(mdev) &&
mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0);
else
pr_warn("md: personality for level %s is not loaded!\n",
mddev->clevel);
- return -EINVAL;
+ err = -EINVAL;
+ goto abort;
}
spin_unlock(&pers_lock);
if (mddev->level != pers->level) {
pers->start_reshape == NULL) {
/* This personality cannot handle reshaping... */
module_put(pers->owner);
- return -EINVAL;
+ err = -EINVAL;
+ goto abort;
}
if (pers->sync_request) {
mddev->private = NULL;
module_put(pers->owner);
bitmap_destroy(mddev);
- return err;
+ goto abort;
}
if (mddev->queue) {
bool nonrot = true;
disk->rdev->saved_raid_disk < 0)
conf->fullsync = 1;
}
+
+ if (disk->replacement &&
+ !test_bit(In_sync, &disk->replacement->flags) &&
+ disk->replacement->saved_raid_disk < 0) {
+ conf->fullsync = 1;
+ }
+
disk->recovery_disabled = mddev->recovery_disabled - 1;
}
bpf_prog_array_free(rcdev->raw->progs);
}
-int lirc_prog_attach(const union bpf_attr *attr)
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
- struct bpf_prog *prog;
struct rc_dev *rcdev;
int ret;
if (attr->attach_flags)
return -EINVAL;
- prog = bpf_prog_get_type(attr->attach_bpf_fd,
- BPF_PROG_TYPE_LIRC_MODE2);
- if (IS_ERR(prog))
- return PTR_ERR(prog);
-
rcdev = rc_dev_get_from_fd(attr->target_fd);
- if (IS_ERR(rcdev)) {
- bpf_prog_put(prog);
+ if (IS_ERR(rcdev))
return PTR_ERR(rcdev);
- }
ret = lirc_bpf_attach(rcdev, prog);
- if (ret)
- bpf_prog_put(prog);
put_device(&rcdev->dev);
struct pci_dev *pdev = to_pci_dev(dev);
struct alx_priv *alx = pci_get_drvdata(pdev);
struct alx_hw *hw = &alx->hw;
+ int err;
alx_reset_phy(hw);
if (!netif_running(alx->dev))
return 0;
netif_device_attach(alx->dev);
- return __alx_open(alx, true);
+
+ rtnl_lock();
+ err = __alx_open(alx, true);
+ rtnl_unlock();
+
+ return err;
}
static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume);
struct link_vars link_vars;
u32 link_cnt;
struct bnx2x_link_report_data last_reported_link;
+ bool force_link_down;
struct mdio_if_info mdio;
{
struct bnx2x_link_report_data cur_data;
+ if (bp->force_link_down) {
+ bp->link_vars.link_up = 0;
+ return;
+ }
+
/* reread mf_cfg */
if (IS_PF(bp) && !CHIP_IS_E1(bp))
bnx2x_read_mf_cfg(bp);
bp->pending_max = 0;
}
+ bp->force_link_down = false;
if (bp->port.pmf) {
rc = bnx2x_initial_phy_init(bp, load_mode);
if (rc)
bp->sp_rtnl_state = 0;
smp_mb();
+ /* Immediately indicate link as down */
+ bp->link_vars.link_up = 0;
+ bp->force_link_down = true;
+ netif_carrier_off(bp->dev);
+ BNX2X_ERR("Indicating link is down due to Tx-timeout\n");
+
bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
/* When ret value shows failure of allocation failure,
* the nic is rebooted again. If open still fails, a error
id_tbl->max = size;
id_tbl->next = next;
spin_lock_init(&id_tbl->lock);
- id_tbl->table = kcalloc(DIV_ROUND_UP(size, 32), 4, GFP_KERNEL);
+ id_tbl->table = kcalloc(BITS_TO_LONGS(size), sizeof(long), GFP_KERNEL);
if (!id_tbl->table)
return -ENOMEM;
int err;
u32 reg;
+ bp->queues[0].bp = bp;
+
dev->netdev_ops = &at91ether_netdev_ops;
dev->ethtool_ops = &macb_ethtool_ops;
/* Default alignment for start of data in an Rx FD */
#define DPAA_FD_DATA_ALIGNMENT 16
+/* The DPAA requires 256 bytes reserved and mapped for the SGT */
+#define DPAA_SGT_SIZE 256
+
/* Values for the L3R field of the FM Parse Results
*/
/* L3 Type field: First IP Present IPv4 */
if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) {
nr_frags = skb_shinfo(skb)->nr_frags;
- dma_unmap_single(dev, addr, qm_fd_get_offset(fd) +
- sizeof(struct qm_sg_entry) * (1 + nr_frags),
+ dma_unmap_single(dev, addr,
+ qm_fd_get_offset(fd) + DPAA_SGT_SIZE,
dma_dir);
/* The sgt buffer has been allocated with netdev_alloc_frag(),
void *sgt_buf;
/* get a page frag to store the SGTable */
- sz = SKB_DATA_ALIGN(priv->tx_headroom +
- sizeof(struct qm_sg_entry) * (1 + nr_frags));
+ sz = SKB_DATA_ALIGN(priv->tx_headroom + DPAA_SGT_SIZE);
sgt_buf = netdev_alloc_frag(sz);
if (unlikely(!sgt_buf)) {
netdev_err(net_dev, "netdev_alloc_frag() failed for size %d\n",
skbh = (struct sk_buff **)buffer_start;
*skbh = skb;
- addr = dma_map_single(dev, buffer_start, priv->tx_headroom +
- sizeof(struct qm_sg_entry) * (1 + nr_frags),
- dma_dir);
+ addr = dma_map_single(dev, buffer_start,
+ priv->tx_headroom + DPAA_SGT_SIZE, dma_dir);
if (unlikely(dma_mapping_error(dev, addr))) {
dev_err(dev, "DMA mapping failed");
err = -EINVAL;
#define HWP_HXS_PHE_REPORT 0x00000800
#define HWP_HXS_PCAC_PSTAT 0x00000100
#define HWP_HXS_PCAC_PSTOP 0x00000001
+#define HWP_HXS_TCP_OFFSET 0xA
+#define HWP_HXS_UDP_OFFSET 0xB
+#define HWP_HXS_SH_PAD_REM 0x80000000
+
struct fman_port_hwp_regs {
struct {
u32 ssa; /* Soft Sequence Attachment */
iowrite32be(0xffffffff, ®s->pmda[i].lcv);
}
+ /* Short packet padding removal from checksum calculation */
+ iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_TCP_OFFSET].ssa);
+ iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_UDP_OFFSET].ssa);
+
start_port_hwp(port);
}
{
struct hinic_rq *rq = rxq->rq;
+ irq_set_affinity_hint(rq->irq, NULL);
free_irq(rq->irq, rxq);
rx_del_napi(rxq);
}
return true;
}
-#define I40E_XDP_PASS 0
-#define I40E_XDP_CONSUMED 1
-#define I40E_XDP_TX 2
+#define I40E_XDP_PASS 0
+#define I40E_XDP_CONSUMED BIT(0)
+#define I40E_XDP_TX BIT(1)
+#define I40E_XDP_REDIR BIT(2)
static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
struct i40e_ring *xdp_ring);
break;
case XDP_REDIRECT:
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- result = !err ? I40E_XDP_TX : I40E_XDP_CONSUMED;
+ result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
break;
default:
bpf_warn_invalid_xdp_action(act);
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
struct sk_buff *skb = rx_ring->skb;
u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
- bool failure = false, xdp_xmit = false;
+ unsigned int xdp_xmit = 0;
+ bool failure = false;
struct xdp_buff xdp;
xdp.rxq = &rx_ring->xdp_rxq;
}
if (IS_ERR(skb)) {
- if (PTR_ERR(skb) == -I40E_XDP_TX) {
- xdp_xmit = true;
+ unsigned int xdp_res = -PTR_ERR(skb);
+
+ if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
+ xdp_xmit |= xdp_res;
i40e_rx_buffer_flip(rx_ring, rx_buffer, size);
} else {
rx_buffer->pagecnt_bias++;
total_rx_packets++;
}
- if (xdp_xmit) {
+ if (xdp_xmit & I40E_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_xmit & I40E_XDP_TX) {
struct i40e_ring *xdp_ring =
rx_ring->vsi->xdp_rings[rx_ring->queue_index];
i40e_xdp_ring_update_tail(xdp_ring);
- xdp_do_flush_map();
}
rx_ring->skb = skb;
return skb;
}
-#define IXGBE_XDP_PASS 0
-#define IXGBE_XDP_CONSUMED 1
-#define IXGBE_XDP_TX 2
+#define IXGBE_XDP_PASS 0
+#define IXGBE_XDP_CONSUMED BIT(0)
+#define IXGBE_XDP_TX BIT(1)
+#define IXGBE_XDP_REDIR BIT(2)
static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
struct xdp_frame *xdpf);
case XDP_REDIRECT:
err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
if (!err)
- result = IXGBE_XDP_TX;
+ result = IXGBE_XDP_REDIR;
else
result = IXGBE_XDP_CONSUMED;
break;
unsigned int mss = 0;
#endif /* IXGBE_FCOE */
u16 cleaned_count = ixgbe_desc_unused(rx_ring);
- bool xdp_xmit = false;
+ unsigned int xdp_xmit = 0;
struct xdp_buff xdp;
xdp.rxq = &rx_ring->xdp_rxq;
}
if (IS_ERR(skb)) {
- if (PTR_ERR(skb) == -IXGBE_XDP_TX) {
- xdp_xmit = true;
+ unsigned int xdp_res = -PTR_ERR(skb);
+
+ if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
+ xdp_xmit |= xdp_res;
ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
} else {
rx_buffer->pagecnt_bias++;
total_rx_packets++;
}
- if (xdp_xmit) {
+ if (xdp_xmit & IXGBE_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_xmit & IXGBE_XDP_TX) {
struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
/* Force memory writes to complete before letting h/w
*/
wmb();
writel(ring->next_to_use, ring->tail);
-
- xdp_do_flush_map();
}
u64_stats_update_begin(&rx_ring->syncp);
unsigned long flags;
bool poll_cmd = ent->polling;
int alloc_ret;
+ int cmd_mode;
sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
down(sem);
set_signature(ent, !cmd->checksum_disabled);
dump_command(dev, ent, 1);
ent->ts1 = ktime_get_ns();
+ cmd_mode = cmd->mode;
if (ent->callback)
schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
mmiowb();
/* if not in polling don't use ent after this point */
- if (cmd->mode == CMD_MODE_POLLING || poll_cmd) {
+ if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
poll_timeout(ent);
/* make sure we read the descriptor after ownership is SW */
rmb();
{
struct mlx5_core_dev *dev = filp->private_data;
struct mlx5_cmd_debug *dbg = &dev->cmd.dbg;
- char outlen_str[8];
+ char outlen_str[8] = {0};
int outlen;
void *ptr;
int err;
if (copy_from_user(outlen_str, buf, count))
return -EFAULT;
- outlen_str[7] = 0;
-
err = sscanf(outlen_str, "%d", &outlen);
if (err < 0)
return err;
mlx5e_activate_channels(&priv->channels);
netif_tx_start_all_queues(priv->netdev);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_add_sqs_fwd_rules(priv);
mlx5e_wait_channels_min_rx_wqes(&priv->channels);
{
mlx5e_redirect_rqts_to_drop(priv);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_remove_sqs_fwd_rules(priv);
/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
mlx5e_set_netdev_dev_addr(netdev);
#if IS_ENABLED(CONFIG_MLX5_ESWITCH)
- if (MLX5_VPORT_MANAGER(mdev))
+ if (MLX5_ESWITCH_MANAGER(mdev))
netdev->switchdev_ops = &mlx5e_switchdev_ops;
#endif
mlx5e_enable_async_events(priv);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_register_vport_reps(priv);
if (netdev->reg_state != NETREG_REGISTERED)
queue_work(priv->wq, &priv->set_rx_mode_work);
- if (MLX5_VPORT_MANAGER(priv->mdev))
+ if (MLX5_ESWITCH_MANAGER(priv->mdev))
mlx5e_unregister_vport_reps(priv);
mlx5e_disable_async_events(priv);
return NULL;
#ifdef CONFIG_MLX5_ESWITCH
- if (MLX5_VPORT_MANAGER(mdev)) {
+ if (MLX5_ESWITCH_MANAGER(mdev)) {
rpriv = mlx5e_alloc_nic_rep_priv(mdev);
if (!rpriv) {
mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct mlx5_eswitch_rep *rep;
- if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+ if (!MLX5_ESWITCH_MANAGER(priv->mdev))
return false;
rep = rpriv->rep;
static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
{
struct mlx5e_rep_priv *rpriv = priv->ppriv;
- struct mlx5_eswitch_rep *rep = rpriv->rep;
+ struct mlx5_eswitch_rep *rep;
+ if (!MLX5_ESWITCH_MANAGER(priv->mdev))
+ return false;
+
+ rep = rpriv->rep;
if (rep && rep->vport != FDB_UPLINK_VPORT)
return true;
}
/* Public E-Switch API */
-#define ESW_ALLOWED(esw) ((esw) && MLX5_VPORT_MANAGER((esw)->dev))
+#define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
+
int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
{
int err;
int i, enabled_events;
- if (!ESW_ALLOWED(esw))
- return 0;
-
- if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) ||
+ if (!ESW_ALLOWED(esw) ||
!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
return -EOPNOTSUPP;
u64 node_guid;
int err = 0;
- if (!ESW_ALLOWED(esw))
+ if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
return -EPERM;
if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
return -EINVAL;
{
struct mlx5_vport *evport;
- if (!ESW_ALLOWED(esw))
+ if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
return -EPERM;
if (!LEGAL_VPORT(esw, vport))
return -EINVAL;
if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
return -EOPNOTSUPP;
- if (!MLX5_CAP_GEN(dev, vport_group_manager))
- return -EOPNOTSUPP;
+ if(!MLX5_ESWITCH_MANAGER(dev))
+ return -EPERM;
if (dev->priv.eswitch->mode == SRIOV_NONE)
return -EOPNOTSUPP;
#include <linux/mutex.h>
#include <linux/mlx5/driver.h>
+#include <linux/mlx5/eswitch.h>
#include "mlx5_core.h"
#include "fs_core.h"
goto err;
}
- if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+ if (MLX5_ESWITCH_MANAGER(dev)) {
if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) {
err = init_fdb_root_ns(steering);
if (err)
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cmd.h>
+#include <linux/mlx5/eswitch.h>
#include <linux/module.h>
#include "mlx5_core.h"
#include "../../mlxfw/mlxfw.h"
}
if (MLX5_CAP_GEN(dev, vport_group_manager) &&
- MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+ MLX5_ESWITCH_MANAGER(dev)) {
err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE);
if (err)
return err;
}
- if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+ if (MLX5_ESWITCH_MANAGER(dev)) {
err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH);
if (err)
return err;
#include <linux/etherdevice.h>
#include <linux/mlx5/driver.h>
#include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/eswitch.h>
#include "mlx5_core.h"
#include "lib/mpfs.h"
int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table);
struct mlx5_mpfs *mpfs;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return 0;
mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL);
{
struct mlx5_mpfs *mpfs = dev->priv.mpfs;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return;
WARN_ON(!hlist_empty(mpfs->hash));
u32 index;
int err;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return 0;
mutex_lock(&mpfs->lock);
int err = 0;
u32 index;
- if (!MLX5_VPORT_MANAGER(dev))
+ if (!MLX5_ESWITCH_MANAGER(dev))
return 0;
mutex_lock(&mpfs->lock);
static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
int inlen)
{
- u32 out[MLX5_ST_SZ_DW(qtct_reg)];
+ u32 out[MLX5_ST_SZ_DW(qetc_reg)];
if (!MLX5_CAP_GEN(mdev, ets))
return -EOPNOTSUPP;
static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out,
int outlen)
{
- u32 in[MLX5_ST_SZ_DW(qtct_reg)];
+ u32 in[MLX5_ST_SZ_DW(qetc_reg)];
if (!MLX5_CAP_GEN(mdev, ets))
return -EOPNOTSUPP;
return -EBUSY;
}
+ if (!MLX5_ESWITCH_MANAGER(dev))
+ goto enable_vfs_hca;
+
err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
if (err) {
mlx5_core_warn(dev,
return err;
}
+enable_vfs_hca:
for (vf = 0; vf < num_vfs; vf++) {
err = mlx5_core_enable_hca(dev, vf + 1);
if (err) {
}
out:
- mlx5_eswitch_disable_sriov(dev->priv.eswitch);
+ if (MLX5_ESWITCH_MANAGER(dev))
+ mlx5_eswitch_disable_sriov(dev->priv.eswitch);
if (mlx5_wait_for_vf_pages(dev))
mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
return -EINVAL;
if (!MLX5_CAP_GEN(mdev, vport_group_manager))
return -EACCES;
- if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify))
- return -EOPNOTSUPP;
in = kvzalloc(inlen, GFP_KERNEL);
if (!in)
ret = nfp_net_bpf_offload(nn, prog, running, extack);
/* Stop offload if replace not possible */
- if (ret && prog)
- nfp_bpf_xdp_offload(app, nn, NULL, extack);
+ if (ret)
+ return ret;
- nn->dp.bpf_offload_xdp = prog && !ret;
+ nn->dp.bpf_offload_xdp = !!prog;
return ret;
}
if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
return -EOPNOTSUPP;
+ if (tcf_block_shared(f->block))
+ return -EOPNOTSUPP;
+
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block,
NFP_FLOWER_MASK_MPLS_Q;
frame->mpls_lse = cpu_to_be32(t_mpls);
+ } else if (dissector_uses_key(flow->dissector,
+ FLOW_DISSECTOR_KEY_BASIC)) {
+ /* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q
+ * bit, which indicates an mpls ether type but without any
+ * mpls fields.
+ */
+ struct flow_dissector_key_basic *key_basic;
+
+ key_basic = skb_flow_dissector_target(flow->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ flow->key);
+ if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
+ key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC))
+ frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
}
}
case cpu_to_be16(ETH_P_ARP):
return -EOPNOTSUPP;
+ case cpu_to_be16(ETH_P_MPLS_UC):
+ case cpu_to_be16(ETH_P_MPLS_MC):
+ if (!(key_layer & NFP_FLOWER_LAYER_MAC)) {
+ key_layer |= NFP_FLOWER_LAYER_MAC;
+ key_size += sizeof(struct nfp_flower_mac_mpls);
+ }
+ break;
+
/* Will be included in layer 2. */
case cpu_to_be16(ETH_P_8021Q):
break;
if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
return -EOPNOTSUPP;
+ if (tcf_block_shared(f->block))
+ return -EOPNOTSUPP;
+
switch (f->command) {
case TC_BLOCK_BIND:
return tcf_block_cb_register(f->block,
err = nfp_cpp_read(cpp, nfp_resource_cpp_id(state->res),
nfp_resource_address(state->res),
fwinf, sizeof(*fwinf));
- if (err < sizeof(*fwinf))
+ if (err < (int)sizeof(*fwinf))
goto err_release;
if (!nffw_res_flg_init_get(fwinf))
p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE];
memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id,
- ARRAY_SIZE(p_local->local_chassis_id));
+ sizeof(p_local->local_chassis_id));
memcpy(params->lldp_local.local_port_id, p_local->local_port_id,
- ARRAY_SIZE(p_local->local_port_id));
+ sizeof(p_local->local_port_id));
}
static void
p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE];
memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id,
- ARRAY_SIZE(p_remote->peer_chassis_id));
+ sizeof(p_remote->peer_chassis_id));
memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id,
- ARRAY_SIZE(p_remote->peer_port_id));
+ sizeof(p_remote->peer_port_id));
}
static int
DP_INFO(p_hwfn, "Failed to update driver state\n");
rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt,
- QED_OV_ESWITCH_VEB);
+ QED_OV_ESWITCH_NONE);
if (rc)
DP_INFO(p_hwfn, "Failed to update eswitch mode\n");
}
/* We want a minimum of one slowpath and one fastpath vector per hwfn */
cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2;
+ if (is_kdump_kernel()) {
+ DP_INFO(cdev,
+ "Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n",
+ cdev->int_params.in.min_msix_cnt);
+ cdev->int_params.in.num_vectors =
+ cdev->int_params.in.min_msix_cnt;
+ }
+
rc = qed_set_int_mode(cdev, false);
if (rc) {
DP_ERR(cdev, "qed_slowpath_setup_int ERR\n");
static int qed_sriov_enable(struct qed_dev *cdev, int num)
{
struct qed_iov_vf_init_params params;
+ struct qed_hwfn *hwfn;
+ struct qed_ptt *ptt;
int i, j, rc;
if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) {
/* Initialize HW for VF access */
for_each_hwfn(cdev, j) {
- struct qed_hwfn *hwfn = &cdev->hwfns[j];
- struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
+ hwfn = &cdev->hwfns[j];
+ ptt = qed_ptt_acquire(hwfn);
/* Make sure not to use more than 16 queues per VF */
params.num_queues = min_t(int,
goto err;
}
+ hwfn = QED_LEADING_HWFN(cdev);
+ ptt = qed_ptt_acquire(hwfn);
+ if (!ptt) {
+ DP_ERR(hwfn, "Failed to acquire ptt\n");
+ rc = -EBUSY;
+ goto err;
+ }
+
+ rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB);
+ if (rc)
+ DP_INFO(cdev, "Failed to update eswitch mode\n");
+ qed_ptt_release(hwfn, ptt);
+
return num;
err:
{
struct qede_ptp *ptp = edev->ptp;
- if (!ptp)
- return -EIO;
+ if (!ptp) {
+ info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE;
+ info->phc_index = -1;
+
+ return 0;
+ }
info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
SOF_TIMESTAMPING_RX_SOFTWARE |
if (!state)
return -ENOMEM;
efx->filter_state = state;
+ init_rwsem(&state->lock);
table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
table->id = EFX_FARCH_FILTER_TABLE_RX_IP;
}
}
+static void dwmac4_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan)
+{
+ u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
+
+ value &= ~DMA_RBSZ_MASK;
+ value |= (bfsize << DMA_RBSZ_SHIFT) & DMA_RBSZ_MASK;
+
+ writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
+}
+
const struct stmmac_dma_ops dwmac4_dma_ops = {
.reset = dwmac4_dma_reset,
.init = dwmac4_dma_init,
.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
.enable_tso = dwmac4_enable_tso,
+ .set_bfsize = dwmac4_set_bfsize,
};
const struct stmmac_dma_ops dwmac410_dma_ops = {
.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
.enable_tso = dwmac4_enable_tso,
+ .set_bfsize = dwmac4_set_bfsize,
};
/* DMA Rx Channel X Control register defines */
#define DMA_CONTROL_SR BIT(0)
+#define DMA_RBSZ_MASK GENMASK(14, 1)
+#define DMA_RBSZ_SHIFT 1
/* Interrupt status per channel */
#define DMA_CHAN_STATUS_REB GENMASK(21, 19)
void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
+ void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan);
};
#define stmmac_reset(__priv, __args...) \
stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args)
#define stmmac_enable_tso(__priv, __args...) \
stmmac_do_void_callback(__priv, dma, enable_tso, __args)
+#define stmmac_set_dma_bfsize(__priv, __args...) \
+ stmmac_do_void_callback(__priv, dma, set_bfsize, __args)
struct mac_device_info;
struct net_device;
stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan,
rxfifosz, qmode);
+ stmmac_set_dma_bfsize(priv, priv->ioaddr, priv->dma_buf_sz,
+ chan);
}
for (chan = 0; chan < tx_channels_count; chan++) {
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
void netvsc_channel_cb(void *context);
int netvsc_poll(struct napi_struct *napi, int budget);
-void rndis_set_subchannel(struct work_struct *w);
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev);
int rndis_filter_open(struct netvsc_device *nvdev);
int rndis_filter_close(struct netvsc_device *nvdev);
struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
VM_PKT_DATA_INBAND, 0);
}
+/* Worker to setup sub channels on initial setup
+ * Initial hotplug event occurs in softirq context
+ * and can't wait for channels.
+ */
+static void netvsc_subchan_work(struct work_struct *w)
+{
+ struct netvsc_device *nvdev =
+ container_of(w, struct netvsc_device, subchan_work);
+ struct rndis_device *rdev;
+ int i, ret;
+
+ /* Avoid deadlock with device removal already under RTNL */
+ if (!rtnl_trylock()) {
+ schedule_work(w);
+ return;
+ }
+
+ rdev = nvdev->extension;
+ if (rdev) {
+ ret = rndis_set_subchannel(rdev->ndev, nvdev);
+ if (ret == 0) {
+ netif_device_attach(rdev->ndev);
+ } else {
+ /* fallback to only primary channel */
+ for (i = 1; i < nvdev->num_chn; i++)
+ netif_napi_del(&nvdev->chan_table[i].napi);
+
+ nvdev->max_chn = 1;
+ nvdev->num_chn = 1;
+ }
+ }
+
+ rtnl_unlock();
+}
+
static struct netvsc_device *alloc_net_device(void)
{
struct netvsc_device *net_device;
init_completion(&net_device->channel_init_wait);
init_waitqueue_head(&net_device->subchan_open);
- INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
+ INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);
return net_device;
}
if (IS_ERR(nvdev))
return PTR_ERR(nvdev);
- /* Note: enable and attach happen when sub-channels setup */
+ if (nvdev->num_chn > 1) {
+ ret = rndis_set_subchannel(ndev, nvdev);
+
+ /* if unavailable, just proceed with one queue */
+ if (ret) {
+ nvdev->max_chn = 1;
+ nvdev->num_chn = 1;
+ }
+ }
+
+ /* In any case device is now ready */
+ netif_device_attach(ndev);
+ /* Note: enable and attach happen when sub-channels setup */
netif_carrier_off(ndev);
if (netif_running(ndev)) {
memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
+ if (nvdev->num_chn > 1)
+ schedule_work(&nvdev->subchan_work);
+
/* hw_features computed in rndis_netdev_set_hwcaps() */
net->features = net->hw_features |
NETIF_F_HIGHDMA | NETIF_F_SG |
* This breaks overlap of processing the host message for the
* new primary channel with the initialization of sub-channels.
*/
-void rndis_set_subchannel(struct work_struct *w)
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev)
{
- struct netvsc_device *nvdev
- = container_of(w, struct netvsc_device, subchan_work);
struct nvsp_message *init_packet = &nvdev->channel_init_pkt;
- struct net_device_context *ndev_ctx;
- struct rndis_device *rdev;
- struct net_device *ndev;
- struct hv_device *hv_dev;
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
+ struct hv_device *hv_dev = ndev_ctx->device_ctx;
+ struct rndis_device *rdev = nvdev->extension;
int i, ret;
- if (!rtnl_trylock()) {
- schedule_work(w);
- return;
- }
-
- rdev = nvdev->extension;
- if (!rdev)
- goto unlock; /* device was removed */
-
- ndev = rdev->ndev;
- ndev_ctx = netdev_priv(ndev);
- hv_dev = ndev_ctx->device_ctx;
+ ASSERT_RTNL();
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret) {
netdev_err(ndev, "sub channel allocate send failed: %d\n", ret);
- goto failed;
+ return ret;
}
wait_for_completion(&nvdev->channel_init_wait);
if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
netdev_err(ndev, "sub channel request failed\n");
- goto failed;
+ return -EIO;
}
nvdev->num_chn = 1 +
for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
ndev_ctx->tx_table[i] = i % nvdev->num_chn;
- netif_device_attach(ndev);
- rtnl_unlock();
- return;
-
-failed:
- /* fallback to only primary channel */
- for (i = 1; i < nvdev->num_chn; i++)
- netif_napi_del(&nvdev->chan_table[i].napi);
-
- nvdev->max_chn = 1;
- nvdev->num_chn = 1;
-
- netif_device_attach(ndev);
-unlock:
- rtnl_unlock();
+ return 0;
}
static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
netif_napi_add(net, &net_device->chan_table[i].napi,
netvsc_poll, NAPI_POLL_WEIGHT);
- if (net_device->num_chn > 1)
- schedule_work(&net_device->subchan_work);
+ return net_device;
out:
- /* if unavailable, just proceed with one queue */
- if (ret) {
- net_device->max_chn = 1;
- net_device->num_chn = 1;
- }
-
- /* No sub channels, device is ready */
- if (net_device->num_chn == 1)
- netif_device_attach(net);
-
- return net_device;
+ /* setting up multiple channels failed */
+ net_device->max_chn = 1;
+ net_device->num_chn = 1;
err_dev_remv:
rndis_filter_device_remove(dev, net_device);
{
struct ipvl_dev *ipvlan;
struct net_device *mdev = port->dev;
- int err = 0;
+ unsigned int flags;
+ int err;
ASSERT_RTNL();
if (port->mode != nval) {
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+ flags = ipvlan->dev->flags;
+ if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) {
+ err = dev_change_flags(ipvlan->dev,
+ flags | IFF_NOARP);
+ } else {
+ err = dev_change_flags(ipvlan->dev,
+ flags & ~IFF_NOARP);
+ }
+ if (unlikely(err))
+ goto fail;
+ }
if (nval == IPVLAN_MODE_L3S) {
/* New mode is L3S */
err = ipvlan_register_nf_hook(read_pnet(&port->pnet));
mdev->l3mdev_ops = &ipvl_l3mdev_ops;
mdev->priv_flags |= IFF_L3MDEV_MASTER;
} else
- return err;
+ goto fail;
} else if (port->mode == IPVLAN_MODE_L3S) {
/* Old mode was L3S */
mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
mdev->l3mdev_ops = NULL;
}
- list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
- if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S)
- ipvlan->dev->flags |= IFF_NOARP;
- else
- ipvlan->dev->flags &= ~IFF_NOARP;
- }
port->mode = nval;
}
+ return 0;
+
+fail:
+ /* Undo the flags changes that have been done so far. */
+ list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) {
+ flags = ipvlan->dev->flags;
+ if (port->mode == IPVLAN_MODE_L3 ||
+ port->mode == IPVLAN_MODE_L3S)
+ dev_change_flags(ipvlan->dev, flags | IFF_NOARP);
+ else
+ dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP);
+ }
+
return err;
}
if (err < 0)
return err;
- err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
+ err = phy_write(phydev, MII_DP83811_INT_STAT2, 0);
}
return err;
#define DEFAULT_RX_CSUM_ENABLE (true)
#define DEFAULT_TSO_CSUM_ENABLE (true)
#define DEFAULT_VLAN_FILTER_ENABLE (true)
+#define DEFAULT_VLAN_RX_OFFLOAD (true)
#define TX_OVERHEAD (8)
#define RXW_PADDING 2
if ((ll_mtu % dev->maxpacket) == 0)
return -EDOM;
- ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + ETH_HLEN);
+ ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN);
netdev->mtu = new_mtu;
}
if (features & NETIF_F_HW_VLAN_CTAG_RX)
+ pdata->rfe_ctl |= RFE_CTL_VLAN_STRIP_;
+ else
+ pdata->rfe_ctl &= ~RFE_CTL_VLAN_STRIP_;
+
+ if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_;
else
pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_;
buf |= FCT_TX_CTL_EN_;
ret = lan78xx_write_reg(dev, FCT_TX_CTL, buf);
- ret = lan78xx_set_rx_max_frame_length(dev, dev->net->mtu + ETH_HLEN);
+ ret = lan78xx_set_rx_max_frame_length(dev,
+ dev->net->mtu + VLAN_ETH_HLEN);
ret = lan78xx_read_reg(dev, MAC_RX, &buf);
buf |= MAC_RX_RXEN_;
if (DEFAULT_TSO_CSUM_ENABLE)
dev->net->features |= NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_SG;
+ if (DEFAULT_VLAN_RX_OFFLOAD)
+ dev->net->features |= NETIF_F_HW_VLAN_CTAG_RX;
+
+ if (DEFAULT_VLAN_FILTER_ENABLE)
+ dev->net->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
dev->net->hw_features = dev->net->features;
ret = lan78xx_setup_irq_domain(dev);
struct sk_buff *skb,
u32 rx_cmd_a, u32 rx_cmd_b)
{
+ /* HW Checksum offload appears to be flawed if used when not stripping
+ * VLAN headers. Drop back to S/W checksums under these conditions.
+ */
if (!(dev->net->features & NETIF_F_RXCSUM) ||
- unlikely(rx_cmd_a & RX_CMD_A_ICSM_)) {
+ unlikely(rx_cmd_a & RX_CMD_A_ICSM_) ||
+ ((rx_cmd_a & RX_CMD_A_FVTG_) &&
+ !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) {
skb->ip_summed = CHECKSUM_NONE;
} else {
skb->csum = ntohs((u16)(rx_cmd_b >> RX_CMD_B_CSUM_SHIFT_));
}
}
+static void lan78xx_rx_vlan_offload(struct lan78xx_net *dev,
+ struct sk_buff *skb,
+ u32 rx_cmd_a, u32 rx_cmd_b)
+{
+ if ((dev->net->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+ (rx_cmd_a & RX_CMD_A_FVTG_))
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+ (rx_cmd_b & 0xffff));
+}
+
static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb)
{
int status;
if (skb->len == size) {
lan78xx_rx_csum_offload(dev, skb,
rx_cmd_a, rx_cmd_b);
+ lan78xx_rx_vlan_offload(dev, skb,
+ rx_cmd_a, rx_cmd_b);
skb_trim(skb, skb->len - 4); /* remove fcs */
skb->truesize = size + sizeof(struct sk_buff);
skb_set_tail_pointer(skb2, size);
lan78xx_rx_csum_offload(dev, skb2, rx_cmd_a, rx_cmd_b);
+ lan78xx_rx_vlan_offload(dev, skb2, rx_cmd_a, rx_cmd_b);
skb_trim(skb2, skb2->len - 4); /* remove fcs */
skb2->truesize = size + sizeof(struct sk_buff);
#ifdef CONFIG_PM_SLEEP
unregister_pm_notifier(&tp->pm_notifier);
#endif
- napi_disable(&tp->napi);
+ if (!test_bit(RTL8152_UNPLUG, &tp->flags))
+ napi_disable(&tp->napi);
clear_bit(WORK_ENABLE, &tp->flags);
usb_kill_urb(tp->intr_urb);
cancel_delayed_work_sync(&tp->schedule);
/* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */
#define VIRTIO_XDP_HEADROOM 256
+/* Separating two types of XDP xmit */
+#define VIRTIO_XDP_TX BIT(0)
+#define VIRTIO_XDP_REDIR BIT(1)
+
/* RX packet size EWMA. The average packet size is used to determine the packet
* buffer size when refilling RX rings. As the entire RX ring may be refilled
* at once, the weight is chosen so that the EWMA will be insensitive to short-
struct receive_queue *rq,
void *buf, void *ctx,
unsigned int len,
- bool *xdp_xmit)
+ unsigned int *xdp_xmit)
{
struct sk_buff *skb;
struct bpf_prog *xdp_prog;
trace_xdp_exception(vi->dev, xdp_prog, act);
goto err_xdp;
}
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_TX;
rcu_read_unlock();
goto xdp_xmit;
case XDP_REDIRECT:
err = xdp_do_redirect(dev, &xdp, xdp_prog);
if (err)
goto err_xdp;
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_REDIR;
rcu_read_unlock();
goto xdp_xmit;
default:
void *buf,
void *ctx,
unsigned int len,
- bool *xdp_xmit)
+ unsigned int *xdp_xmit)
{
struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
put_page(xdp_page);
goto err_xdp;
}
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_TX;
if (unlikely(xdp_page != page))
put_page(page);
rcu_read_unlock();
put_page(xdp_page);
goto err_xdp;
}
- *xdp_xmit = true;
+ *xdp_xmit |= VIRTIO_XDP_REDIR;
if (unlikely(xdp_page != page))
put_page(page);
rcu_read_unlock();
}
static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
- void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
+ void *buf, unsigned int len, void **ctx,
+ unsigned int *xdp_xmit)
{
struct net_device *dev = vi->dev;
struct sk_buff *skb;
}
}
-static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
+static int virtnet_receive(struct receive_queue *rq, int budget,
+ unsigned int *xdp_xmit)
{
struct virtnet_info *vi = rq->vq->vdev->priv;
unsigned int len, received = 0, bytes = 0;
struct virtnet_info *vi = rq->vq->vdev->priv;
struct send_queue *sq;
unsigned int received, qp;
- bool xdp_xmit = false;
+ unsigned int xdp_xmit = 0;
virtnet_poll_cleantx(rq);
if (received < budget)
virtqueue_napi_complete(napi, rq->vq, received);
- if (xdp_xmit) {
+ if (xdp_xmit & VIRTIO_XDP_REDIR)
+ xdp_do_flush_map();
+
+ if (xdp_xmit & VIRTIO_XDP_TX) {
qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
smp_processor_id();
sq = &vi->sq[qp];
virtqueue_kick(sq->vq);
- xdp_do_flush_map();
}
return received;
flush = 0;
out:
- skb_gro_remcsum_cleanup(skb, &grc);
- skb->remcsum_offload = 0;
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
return pp;
}
/*some helper functions*/
#define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "")
+static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf,
+ unsigned int elements)
+{
+ unsigned int i;
+
+ for (i = 0; i < elements; i++)
+ memset(&buf->element[i], 0, sizeof(struct qdio_buffer_element));
+ buf->element[14].sflags = 0;
+ buf->element[15].sflags = 0;
+}
+
/**
* qeth_get_elements_for_range() - find number of SBALEs to cover range.
* @start: Start of the address range.
__u16, __u16,
enum qeth_prot_versions);
int qeth_set_features(struct net_device *, netdev_features_t);
-void qeth_recover_features(struct net_device *dev);
+void qeth_enable_hw_features(struct net_device *dev);
netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
netdev_features_t qeth_features_check(struct sk_buff *skb,
struct net_device *dev,
struct qeth_qdio_out_buffer *buf,
enum iucv_tx_notify notification);
static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf);
-static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
- struct qeth_qdio_out_buffer *buf,
- enum qeth_qdio_buffer_states newbufstate);
static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int);
struct workqueue_struct *qeth_wq;
struct qaob *aob;
struct qeth_qdio_out_buffer *buffer;
enum iucv_tx_notify notification;
+ unsigned int i;
aob = (struct qaob *) phys_to_virt(phys_aob_addr);
QETH_CARD_TEXT(card, 5, "haob");
qeth_notify_skbs(buffer->q, buffer, notification);
buffer->aob = NULL;
- qeth_clear_output_buffer(buffer->q, buffer,
- QETH_QDIO_BUF_HANDLED_DELAYED);
+ /* Free dangling allocations. The attached skbs are handled by
+ * qeth_cleanup_handled_pending().
+ */
+ for (i = 0;
+ i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card);
+ i++) {
+ if (aob->sba[i] && buffer->is_header[i])
+ kmem_cache_free(qeth_core_header_cache,
+ (void *) aob->sba[i]);
+ }
+ atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED);
- /* from here on: do not touch buffer anymore */
qdio_release_aob(aob);
}
QETH_CARD_TEXT(queue->card, 5, "aob");
QETH_CARD_TEXT_(queue->card, 5, "%lx",
virt_to_phys(buffer->aob));
+
+ /* prepare the queue slot for re-use: */
+ qeth_scrub_qdio_buffer(buffer->buffer,
+ QETH_MAX_BUFFER_ELEMENTS(card));
if (qeth_init_qdio_out_buf(queue, bidx)) {
QETH_CARD_TEXT(card, 2, "outofbuf");
qeth_schedule_recovery(card);
goto out;
}
- ccw_device_get_id(CARD_RDEV(card), &id);
+ ccw_device_get_id(CARD_DDEV(card), &id);
request->resp_buf_len = sizeof(*response);
request->resp_version = DIAG26C_VERSION2;
request->op_code = DIAG26C_GET_MAC;
#define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO | \
NETIF_F_IPV6_CSUM)
/**
- * qeth_recover_features() - Restore device features after recovery
- * @dev: the recovering net_device
- *
- * Caller must hold rtnl lock.
+ * qeth_enable_hw_features() - (Re-)Enable HW functions for device features
+ * @dev: a net_device
*/
-void qeth_recover_features(struct net_device *dev)
+void qeth_enable_hw_features(struct net_device *dev)
{
- netdev_features_t features = dev->features;
struct qeth_card *card = dev->ml_priv;
+ netdev_features_t features;
+ rtnl_lock();
+ features = dev->features;
/* force-off any feature that needs an IPA sequence.
* netdev_update_features() will restart them.
*/
dev->features &= ~QETH_HW_FEATURES;
netdev_update_features(dev);
-
- if (features == dev->features)
- return;
- dev_warn(&card->gdev->dev,
- "Device recovery failed to restore all offload features\n");
+ if (features != dev->features)
+ dev_warn(&card->gdev->dev,
+ "Device recovery failed to restore all offload features\n");
+ rtnl_unlock();
}
-EXPORT_SYMBOL_GPL(qeth_recover_features);
+EXPORT_SYMBOL_GPL(qeth_enable_hw_features);
int qeth_set_features(struct net_device *dev, netdev_features_t features)
{
static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
{
- enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+ enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
IPA_CMD_SETGMAC : IPA_CMD_SETVMAC;
int rc;
static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac)
{
- enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+ enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
IPA_CMD_DELGMAC : IPA_CMD_DELVMAC;
int rc;
return -ERESTARTSYS;
}
+ /* avoid racing against concurrent state change: */
+ if (!mutex_trylock(&card->conf_mutex))
+ return -EAGAIN;
+
if (!qeth_card_hw_is_reachable(card)) {
ether_addr_copy(dev->dev_addr, addr->sa_data);
- return 0;
+ goto out_unlock;
}
/* don't register the same address twice */
if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) &&
(card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
- return 0;
+ goto out_unlock;
/* add the new address, switch over, drop the old */
rc = qeth_l2_send_setmac(card, addr->sa_data);
if (rc)
- return rc;
+ goto out_unlock;
ether_addr_copy(old_addr, dev->dev_addr);
ether_addr_copy(dev->dev_addr, addr->sa_data);
if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)
qeth_l2_remove_mac(card, old_addr);
card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
- return 0;
+
+out_unlock:
+ mutex_unlock(&card->conf_mutex);
+ return rc;
}
static void qeth_promisc_to_bridge(struct qeth_card *card)
netif_carrier_off(card->dev);
qeth_set_allowed_threads(card, 0xffffffff, 0);
+
+ qeth_enable_hw_features(card->dev);
if (recover_flag == CARD_STATE_RECOVER) {
if (recovery_mode &&
card->info.type != QETH_CARD_TYPE_OSN) {
}
/* this also sets saved unicast addresses */
qeth_l2_set_rx_mode(card->dev);
- rtnl_lock();
- qeth_recover_features(card->dev);
- rtnl_unlock();
}
/* let user_space know that device is online */
kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
netif_carrier_on(card->dev);
else
netif_carrier_off(card->dev);
+
+ qeth_enable_hw_features(card->dev);
if (recover_flag == CARD_STATE_RECOVER) {
rtnl_lock();
if (recovery_mode)
else
dev_open(card->dev);
qeth_l3_set_rx_mode(card->dev);
- qeth_recover_features(card->dev);
rtnl_unlock();
}
qeth_trace_features(card);
unsigned long reason)
{
struct mm_struct *mm = ctx->mm;
- pte_t *pte;
+ pte_t *ptep, pte;
bool ret = true;
VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
- pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
- if (!pte)
+ ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
+
+ if (!ptep)
goto out;
ret = false;
+ pte = huge_ptep_get(ptep);
/*
* Lockless access: we're in a wait_event so it's ok if it
* changes under us.
*/
- if (huge_pte_none(*pte))
+ if (huge_pte_none(pte))
ret = true;
- if (!huge_pte_write(*pte) && (reason & VM_UFFD_WP))
+ if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
ret = true;
out:
return ret;
\
__ret; \
})
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype, struct bpf_prog *prog);
+int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype);
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
#else
+struct bpf_prog;
struct cgroup_bpf {};
static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
+static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype,
+ struct bpf_prog *prog)
+{
+ return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype)
+{
+ return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return -EINVAL;
+}
+
#define cgroup_bpf_enabled (0)
#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key);
int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog);
#else
static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
{
{
return -EOPNOTSUPP;
}
+
+static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ return -EINVAL;
+}
#endif
#if defined(CONFIG_XDP_SOCKETS)
#include <uapi/linux/bpf.h>
#ifdef CONFIG_BPF_LIRC_MODE2
-int lirc_prog_attach(const union bpf_attr *attr);
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
int lirc_prog_detach(const union bpf_attr *attr);
int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
#else
-static inline int lirc_prog_attach(const union bpf_attr *attr)
+static inline int lirc_prog_attach(const union bpf_attr *attr,
+ struct bpf_prog *prog)
{
return -EINVAL;
}
};
struct bpf_binary_header {
- u16 pages;
- u16 locked:1;
-
+ u32 pages;
/* Some arches need word alignment for their instructions */
u8 image[] __aligned(4);
};
u16 pages; /* Number of allocated pages */
u16 jited:1, /* Is our filter JIT'ed? */
jit_requested:1,/* archs need to JIT the prog */
- locked:1, /* Program image locked? */
+ undo_set_mem:1, /* Passed set_memory_ro() checkpoint */
gpl_compatible:1, /* Is filter GPL compatible? */
cb_access:1, /* Is control block accessed? */
dst_needed:1, /* Do we need dst entry? */
static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
{
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
- fp->locked = 1;
- if (set_memory_ro((unsigned long)fp, fp->pages))
- fp->locked = 0;
-#endif
+ fp->undo_set_mem = 1;
+ set_memory_ro((unsigned long)fp, fp->pages);
}
static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
{
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
- if (fp->locked) {
- WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
- /* In case set_memory_rw() fails, we want to be the first
- * to crash here instead of some random place later on.
- */
- fp->locked = 0;
- }
-#endif
+ if (fp->undo_set_mem)
+ set_memory_rw((unsigned long)fp, fp->pages);
}
static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
{
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
- hdr->locked = 1;
- if (set_memory_ro((unsigned long)hdr, hdr->pages))
- hdr->locked = 0;
-#endif
+ set_memory_ro((unsigned long)hdr, hdr->pages);
}
static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
{
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
- if (hdr->locked) {
- WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
- /* In case set_memory_rw() fails, we want to be the first
- * to crash here instead of some random place later on.
- */
- hdr->locked = 0;
- }
-#endif
+ set_memory_rw((unsigned long)hdr, hdr->pages);
}
static inline struct bpf_binary_header *
return (void *)addr;
}
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp)
-{
- if (!fp->locked)
- return -ENOLCK;
- if (fp->jited) {
- const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
-
- if (!hdr->locked)
- return -ENOLCK;
- }
-
- return 0;
-}
-#endif
-
int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
{
#include <linux/mlx5/driver.h>
+#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
+
enum {
SRIOV_NONE,
SRIOV_LEGACY,
u8 vnic_env_queue_counters[0x1];
u8 ets[0x1];
u8 nic_flow_table[0x1];
- u8 eswitch_flow_table[0x1];
+ u8 eswitch_manager[0x1];
u8 device_memory[0x1];
u8 mcam_reg[0x1];
u8 pcam_reg[0x1];
if (PTR_ERR(pp) != -EINPROGRESS)
NAPI_GRO_CB(skb)->flush |= flush;
}
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+ struct sk_buff **pp,
+ int flush,
+ struct gro_remcsum *grc)
+{
+ if (PTR_ERR(pp) != -EINPROGRESS) {
+ NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_remcsum_cleanup(skb, grc);
+ skb->remcsum_offload = 0;
+ }
+}
#else
static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
{
NAPI_GRO_CB(skb)->flush |= flush;
}
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+ struct sk_buff **pp,
+ int flush,
+ struct gro_remcsum *grc)
+{
+ NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_remcsum_cleanup(skb, grc);
+ skb->remcsum_offload = 0;
+}
#endif
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
#endif
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
struct netns_nf_frag nf_frag;
+ struct ctl_table_header *nf_frag_frags_hdr;
#endif
struct sock *nfnl;
struct sock *nfnl_stash;
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
struct netns_nf_frag {
- struct netns_sysctl_ipv6 sysctl;
struct netns_frags frags;
};
#endif
{
}
+static inline bool tcf_block_shared(struct tcf_block *block)
+{
+ return false;
+}
+
static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
{
return NULL;
* is resolved), the nexthop address is returned in ipv4_dst
* or ipv6_dst based on family, smac is set to mac address of
* egress device, dmac is set to nexthop mac address, rt_metric
- * is set to metric from route (IPv4/IPv6 only).
+ * is set to metric from route (IPv4/IPv6 only), and ifindex
+ * is set to the device index of the nexthop from the FIB lookup.
*
* *plen* argument is the size of the passed in struct.
* *flags* argument can be a combination of one or more of the
* *ctx* is either **struct xdp_md** for XDP programs or
* **struct sk_buff** tc cls_act programs.
* Return
- * Egress device index on success, 0 if packet needs to continue
- * up the stack for further processing or a negative error in case
- * of failure.
+ * * < 0 if any input argument is invalid
+ * * 0 on success (packet is forwarded, nexthop neighbor exists)
+ * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ * * packet is not forwarded or needs assist from full stack
*
* int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
* Description
#define BPF_FIB_LOOKUP_DIRECT BIT(0)
#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
+enum {
+ BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
+ BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */
+ BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */
+ BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */
+ BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */
+ BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+ BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
+ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
+ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+};
+
struct bpf_fib_lookup {
/* input: network family for lookup (AF_INET, AF_INET6)
* output: network family of egress nexthop
/* total length of packet from network header - used for MTU check */
__u16 tot_len;
- __u32 ifindex; /* L3 device index for lookup */
+
+ /* input: L3 device index for lookup
+ * output: device index from FIB lookup
+ */
+ __u32 ifindex;
union {
/* inputs to lookup */
return ret;
}
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype, struct bpf_prog *prog)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+ attr->attach_flags);
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+ struct bpf_prog *prog;
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ prog = NULL;
+
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+ if (prog)
+ bpf_prog_put(prog);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->query.target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_query(cgrp, attr, uattr);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
/**
* __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socket sending or receiving traffic
bpf_fill_ill_insns(hdr, size);
hdr->pages = size / PAGE_SIZE;
- hdr->locked = 0;
-
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
start = (get_random_int() % hole) & ~(alignment - 1);
return 0;
}
-static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp)
-{
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
- int i, err;
-
- for (i = 0; i < fp->aux->func_cnt; i++) {
- err = bpf_prog_check_pages_ro_single(fp->aux->func[i]);
- if (err)
- return err;
- }
-
- return bpf_prog_check_pages_ro_single(fp);
-#endif
- return 0;
-}
-
static void bpf_prog_select_func(struct bpf_prog *fp)
{
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
* all eBPF JITs might immediately support all features.
*/
*err = bpf_check_tail_call(fp);
- if (*err)
- return fp;
-
- /* Checkpoint: at this point onwards any cBPF -> eBPF or
- * native eBPF program is read-only. If we failed to change
- * the page attributes (e.g. allocation failure from
- * splitting large pages), then reject the whole program
- * in order to guarantee not ending up with any W+X pages
- * from BPF side in kernel.
- */
- *err = bpf_prog_check_pages_ro_locked(fp);
+
return fp;
}
EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
u32 n_buckets;
u32 elem_size;
struct bpf_sock_progs progs;
+ struct rcu_head rcu;
};
struct htab_elem {
struct smap_psock_map_entry {
struct list_head list;
struct sock **entry;
- struct htab_elem *hash_link;
- struct bpf_htab *htab;
+ struct htab_elem __rcu *hash_link;
+ struct bpf_htab __rcu *htab;
};
struct smap_psock {
struct bpf_prog *bpf_parse;
struct bpf_prog *bpf_verdict;
struct list_head maps;
+ spinlock_t maps_lock;
/* Back reference used when sock callback trigger sockmap operations */
struct sock *sock;
static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
+static void bpf_tcp_close(struct sock *sk, long timeout);
static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
{
return !empty;
}
-static struct proto tcp_bpf_proto;
+enum {
+ SOCKMAP_IPV4,
+ SOCKMAP_IPV6,
+ SOCKMAP_NUM_PROTS,
+};
+
+enum {
+ SOCKMAP_BASE,
+ SOCKMAP_TX,
+ SOCKMAP_NUM_CONFIGS,
+};
+
+static struct proto *saved_tcpv6_prot __read_mostly;
+static DEFINE_SPINLOCK(tcpv6_prot_lock);
+static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS];
+static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
+ struct proto *base)
+{
+ prot[SOCKMAP_BASE] = *base;
+ prot[SOCKMAP_BASE].close = bpf_tcp_close;
+ prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg;
+ prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read;
+
+ prot[SOCKMAP_TX] = prot[SOCKMAP_BASE];
+ prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg;
+ prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage;
+}
+
+static void update_sk_prot(struct sock *sk, struct smap_psock *psock)
+{
+ int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4;
+ int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE;
+
+ sk->sk_prot = &bpf_tcp_prots[family][conf];
+}
+
static int bpf_tcp_init(struct sock *sk)
{
struct smap_psock *psock;
psock->save_close = sk->sk_prot->close;
psock->sk_proto = sk->sk_prot;
- if (psock->bpf_tx_msg) {
- tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
- tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
- tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
- tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
+ /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */
+ if (sk->sk_family == AF_INET6 &&
+ unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+ spin_lock_bh(&tcpv6_prot_lock);
+ if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot);
+ smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+ }
+ spin_unlock_bh(&tcpv6_prot_lock);
}
-
- sk->sk_prot = &tcp_bpf_proto;
+ update_sk_prot(sk, psock);
rcu_read_unlock();
return 0;
}
rcu_read_unlock();
}
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+ u32 hash, void *key, u32 key_size)
+{
+ struct htab_elem *l;
+
+ hlist_for_each_entry_rcu(l, head, hash_node) {
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+ }
+
+ return NULL;
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &__select_bucket(htab, hash)->head;
+}
+
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
atomic_dec(&htab->count);
kfree_rcu(l, rcu);
}
+static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
+ struct smap_psock *psock)
+{
+ struct smap_psock_map_entry *e;
+
+ spin_lock_bh(&psock->maps_lock);
+ e = list_first_entry_or_null(&psock->maps,
+ struct smap_psock_map_entry,
+ list);
+ if (e)
+ list_del(&e->list);
+ spin_unlock_bh(&psock->maps_lock);
+ return e;
+}
+
static void bpf_tcp_close(struct sock *sk, long timeout)
{
void (*close_fun)(struct sock *sk, long timeout);
- struct smap_psock_map_entry *e, *tmp;
+ struct smap_psock_map_entry *e;
struct sk_msg_buff *md, *mtmp;
struct smap_psock *psock;
struct sock *osk;
*/
close_fun = psock->save_close;
- write_lock_bh(&sk->sk_callback_lock);
if (psock->cork) {
free_start_sg(psock->sock, psock->cork);
kfree(psock->cork);
kfree(md);
}
- list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ e = psock_map_pop(sk, psock);
+ while (e) {
if (e->entry) {
osk = cmpxchg(e->entry, sk, NULL);
if (osk == sk) {
- list_del(&e->list);
smap_release_sock(psock, sk);
}
} else {
- hlist_del_rcu(&e->hash_link->hash_node);
- smap_release_sock(psock, e->hash_link->sk);
- free_htab_elem(e->htab, e->hash_link);
+ struct htab_elem *link = rcu_dereference(e->hash_link);
+ struct bpf_htab *htab = rcu_dereference(e->htab);
+ struct hlist_head *head;
+ struct htab_elem *l;
+ struct bucket *b;
+
+ b = __select_bucket(htab, link->hash);
+ head = &b->head;
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head,
+ link->hash, link->key,
+ htab->map.key_size);
+ /* If another thread deleted this object skip deletion.
+ * The refcnt on psock may or may not be zero.
+ */
+ if (l) {
+ hlist_del_rcu(&link->hash_node);
+ smap_release_sock(psock, link->sk);
+ free_htab_elem(htab, link);
+ }
+ raw_spin_unlock_bh(&b->lock);
}
+ e = psock_map_pop(sk, psock);
}
- write_unlock_bh(&sk->sk_callback_lock);
rcu_read_unlock();
close_fun(sk, timeout);
}
static int bpf_tcp_ulp_register(void)
{
- tcp_bpf_proto = tcp_prot;
- tcp_bpf_proto.close = bpf_tcp_close;
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot);
/* Once BPF TX ULP is registered it is never unregistered. It
* will be in the ULP list for the lifetime of the system. Doing
* duplicate registers is not a problem.
{
if (refcount_dec_and_test(&psock->refcnt)) {
tcp_cleanup_ulp(sock);
+ write_lock_bh(&sock->sk_callback_lock);
smap_stop_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
clear_bit(SMAP_TX_RUNNING, &psock->state);
rcu_assign_sk_user_data(sock, NULL);
call_rcu_sched(&psock->rcu, smap_destroy_psock);
INIT_LIST_HEAD(&psock->maps);
INIT_LIST_HEAD(&psock->ingress);
refcount_set(&psock->refcnt, 1);
+ spin_lock_init(&psock->maps_lock);
rcu_assign_sk_user_data(sock, psock);
sock_hold(sock);
return ERR_PTR(err);
}
-static void smap_list_remove(struct smap_psock *psock,
- struct sock **entry,
- struct htab_elem *hash_link)
+static void smap_list_map_remove(struct smap_psock *psock,
+ struct sock **entry)
{
struct smap_psock_map_entry *e, *tmp;
+ spin_lock_bh(&psock->maps_lock);
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- if (e->entry == entry || e->hash_link == hash_link) {
+ if (e->entry == entry)
list_del(&e->list);
- break;
- }
}
+ spin_unlock_bh(&psock->maps_lock);
+}
+
+static void smap_list_hash_remove(struct smap_psock *psock,
+ struct htab_elem *hash_link)
+{
+ struct smap_psock_map_entry *e, *tmp;
+
+ spin_lock_bh(&psock->maps_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ struct htab_elem *c = rcu_dereference(e->hash_link);
+
+ if (c == hash_link)
+ list_del(&e->list);
+ }
+ spin_unlock_bh(&psock->maps_lock);
}
static void sock_map_free(struct bpf_map *map)
if (!sock)
continue;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[i]);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
}
rcu_read_unlock();
if (!sock)
return -EINVAL;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
if (!psock)
goto out;
if (psock->bpf_parse)
smap_stop_sock(psock, sock);
- smap_list_remove(psock, &stab->sock_map[k], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[k]);
smap_release_sock(psock, sock);
out:
- write_unlock_bh(&sock->sk_callback_lock);
return 0;
}
}
}
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* 2. Do not allow inheriting programs if psock exists and has
if (err)
goto out_free;
smap_init_progs(psock, verdict, parse);
+ write_lock_bh(&sock->sk_callback_lock);
smap_start_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
}
/* 4. Place psock in sockmap for use and stop any programs on
*/
if (map_link) {
e->entry = map_link;
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
}
- write_unlock_bh(&sock->sk_callback_lock);
return err;
out_free:
smap_release_sock(psock, sock);
}
if (tx_msg)
bpf_prog_put(tx_msg);
- write_unlock_bh(&sock->sk_callback_lock);
kfree(e);
return err;
}
if (osock) {
struct smap_psock *opsock = smap_psock_sk(osock);
- write_lock_bh(&osock->sk_callback_lock);
- smap_list_remove(opsock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(opsock, &stab->sock_map[i]);
smap_release_sock(opsock, osock);
- write_unlock_bh(&osock->sk_callback_lock);
}
out:
return err;
return 0;
}
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ int ufd = attr->target_fd;
+ struct bpf_map *map;
+ struct fd f;
+ int err;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = sock_map_prog(map, prog, attr->attach_type);
+ fdput(f);
+ return err;
+}
+
static void *sock_map_lookup(struct bpf_map *map, void *key)
{
return NULL;
return ERR_PTR(err);
}
-static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+static void __bpf_htab_free(struct rcu_head *rcu)
{
- return &htab->buckets[hash & (htab->n_buckets - 1)];
-}
+ struct bpf_htab *htab;
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
-{
- return &__select_bucket(htab, hash)->head;
+ htab = container_of(rcu, struct bpf_htab, rcu);
+ bpf_map_area_free(htab->buckets);
+ kfree(htab);
}
static void sock_hash_free(struct bpf_map *map)
*/
rcu_read_lock();
for (i = 0; i < htab->n_buckets; i++) {
- struct hlist_head *head = select_bucket(htab, i);
+ struct bucket *b = __select_bucket(htab, i);
+ struct hlist_head *head;
struct hlist_node *n;
struct htab_elem *l;
+ raw_spin_lock_bh(&b->lock);
+ head = &b->head;
hlist_for_each_entry_safe(l, n, head, hash_node) {
struct sock *sock = l->sk;
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get
* the sk_callback_lock before this case but after xchg
* (psock) to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
- kfree(l);
+ free_htab_elem(htab, l);
}
+ raw_spin_unlock_bh(&b->lock);
}
rcu_read_unlock();
- bpf_map_area_free(htab->buckets);
- kfree(htab);
+ call_rcu(&htab->rcu, __bpf_htab_free);
}
static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
return l_new;
}
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
- u32 hash, void *key, u32 key_size)
-{
- struct htab_elem *l;
-
- hlist_for_each_entry_rcu(l, head, hash_node) {
- if (l->hash == hash && !memcmp(&l->key, key, key_size))
- return l;
- }
-
- return NULL;
-}
-
static inline u32 htab_map_hash(const void *key, u32 key_len)
{
return jhash(key, key_len, 0);
goto bucket_err;
}
- e->hash_link = l_new;
- e->htab = container_of(map, struct bpf_htab, map);
+ rcu_assign_pointer(e->hash_link, l_new);
+ rcu_assign_pointer(e->htab,
+ container_of(map, struct bpf_htab, map));
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
/* add new element to the head of the list, so that
* concurrent search will find it before old elem
psock = smap_psock_sk(l_old->sk);
hlist_del_rcu(&l_old->hash_node);
- smap_list_remove(psock, NULL, l_old);
+ smap_list_hash_remove(psock, l_old);
smap_release_sock(psock, l_old->sk);
free_htab_elem(htab, l_old);
}
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
free_htab_elem(htab, l);
ret = 0;
}
.map_get_next_key = sock_hash_get_next_key,
.map_update_elem = sock_hash_update_elem,
.map_delete_elem = sock_hash_delete_elem,
+ .map_release_uref = sock_map_release,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
return err;
}
-#ifdef CONFIG_CGROUP_BPF
-
static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
enum bpf_attach_type attach_type)
{
#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
-static int sockmap_get_from_fd(const union bpf_attr *attr,
- int type, bool attach)
-{
- struct bpf_prog *prog = NULL;
- int ufd = attr->target_fd;
- struct bpf_map *map;
- struct fd f;
- int err;
-
- f = fdget(ufd);
- map = __bpf_map_get(f);
- if (IS_ERR(map))
- return PTR_ERR(map);
-
- if (attach) {
- prog = bpf_prog_get_type(attr->attach_bpf_fd, type);
- if (IS_ERR(prog)) {
- fdput(f);
- return PTR_ERR(prog);
- }
- }
-
- err = sock_map_prog(map, prog, attr->attach_type);
- if (err) {
- fdput(f);
- if (prog)
- bpf_prog_put(prog);
- return err;
- }
-
- fdput(f);
- return 0;
-}
-
#define BPF_F_ATTACH_MASK \
(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
{
enum bpf_prog_type ptype;
struct bpf_prog *prog;
- struct cgroup *cgrp;
int ret;
if (!capable(CAP_NET_ADMIN))
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true);
+ ptype = BPF_PROG_TYPE_SK_MSG;
+ break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true);
+ ptype = BPF_PROG_TYPE_SK_SKB;
+ break;
case BPF_LIRC_MODE2:
- return lirc_prog_attach(attr);
+ ptype = BPF_PROG_TYPE_LIRC_MODE2;
+ break;
default:
return -EINVAL;
}
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp)) {
- bpf_prog_put(prog);
- return PTR_ERR(cgrp);
+ switch (ptype) {
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_SK_MSG:
+ ret = sockmap_get_from_fd(attr, ptype, prog);
+ break;
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ ret = lirc_prog_attach(attr, prog);
+ break;
+ default:
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
}
- ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
- attr->attach_flags);
if (ret)
bpf_prog_put(prog);
- cgroup_put(cgrp);
-
return ret;
}
static int bpf_prog_detach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
- struct bpf_prog *prog;
- struct cgroup *cgrp;
- int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL);
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL);
case BPF_LIRC_MODE2:
return lirc_prog_detach(attr);
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
-
- prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
- if (IS_ERR(prog))
- prog = NULL;
-
- ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
- if (prog)
- bpf_prog_put(prog);
- cgroup_put(cgrp);
- return ret;
+ return cgroup_bpf_prog_detach(attr, ptype);
}
#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
- struct cgroup *cgrp;
- int ret;
-
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (CHECK_ATTR(BPF_PROG_QUERY))
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->query.target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
- ret = cgroup_bpf_query(cgrp, attr, uattr);
- cgroup_put(cgrp);
- return ret;
+
+ return cgroup_bpf_prog_query(attr, uattr);
}
-#endif /* CONFIG_CGROUP_BPF */
#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
case BPF_OBJ_GET:
err = bpf_obj_get(&attr);
break;
-#ifdef CONFIG_CGROUP_BPF
case BPF_PROG_ATTACH:
err = bpf_prog_attach(&attr);
break;
case BPF_PROG_QUERY:
err = bpf_prog_query(&attr, uattr);
break;
-#endif
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
break;
{ /* Mainly checking JIT here. */
"BPF_MAXINSNS: Ctx heavy transformations",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_EXPECTED_FAIL,
+#else
CLASSIC,
+#endif
{ },
{
{ 1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) },
{ 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }
},
.fill_helper = bpf_fill_maxinsns6,
+ .expected_errcode = -ENOTSUPP,
},
{ /* Mainly checking JIT here. */
"BPF_MAXINSNS: Call heavy transformations",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+#else
CLASSIC | FLAG_NO_DATA,
+#endif
{ },
{ { 1, 0 }, { 10, 0 } },
.fill_helper = bpf_fill_maxinsns7,
+ .expected_errcode = -ENOTSUPP,
},
{ /* Mainly checking JIT here. */
"BPF_MAXINSNS: Jump heavy test",
{
"BPF_MAXINSNS: exec all MSH",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_EXPECTED_FAIL,
+#else
CLASSIC,
+#endif
{ 0xfa, 0xfb, 0xfc, 0xfd, },
{ { 4, 0xababab83 } },
.fill_helper = bpf_fill_maxinsns13,
+ .expected_errcode = -ENOTSUPP,
},
{
"BPF_MAXINSNS: ld_abs+get_processor_id",
{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+ CLASSIC | FLAG_EXPECTED_FAIL,
+#else
CLASSIC,
+#endif
{ },
{ { 1, 0xbee } },
.fill_helper = bpf_fill_ld_abs_get_processor_id,
+ .expected_errcode = -ENOTSUPP,
},
/*
* LD_IND / LD_ABS on fragmented SKBs
void __dump_page(struct page *page, const char *reason)
{
+ bool page_poisoned = PagePoisoned(page);
+ int mapcount;
+
+ /*
+ * If struct page is poisoned don't access Page*() functions as that
+ * leads to recursive loop. Page*() check for poisoned pages, and calls
+ * dump_page() when detected.
+ */
+ if (page_poisoned) {
+ pr_emerg("page:%px is uninitialized and poisoned", page);
+ goto hex_only;
+ }
+
/*
* Avoid VM_BUG_ON() in page_mapcount().
* page->_mapcount space in struct page is used by sl[aou]b pages to
* encode own info.
*/
- int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
+ mapcount = PageSlab(page) ? 0 : page_mapcount(page);
pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx",
page, page_ref_count(page), mapcount,
pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags);
+hex_only:
print_hex_dump(KERN_ALERT, "raw: ", DUMP_PREFIX_NONE, 32,
sizeof(unsigned long), page,
sizeof(struct page), false);
pr_alert("page dumped because: %s\n", reason);
#ifdef CONFIG_MEMCG
- if (page->mem_cgroup)
+ if (!page_poisoned && page->mem_cgroup)
pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup);
#endif
}
*/
if (hstate_is_gigantic(h))
adjust_managed_page_count(page, 1 << h->order);
+ cond_resched();
}
}
int kasan_module_alloc(void *addr, size_t size)
{
void *ret;
+ size_t scaled_size;
size_t shadow_size;
unsigned long shadow_start;
shadow_start = (unsigned long)kasan_mem_to_shadow(addr);
- shadow_size = round_up(size >> KASAN_SHADOW_SCALE_SHIFT,
- PAGE_SIZE);
+ scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT;
+ shadow_size = round_up(scaled_size, PAGE_SIZE);
if (WARN_ON(!PAGE_ALIGNED(shadow_start)))
return -EINVAL;
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
obj-$(CONFIG_XFRM) += xfrm/
obj-$(CONFIG_UNIX) += unix/
obj-$(CONFIG_NET) += ipv6/
-ifneq ($(CC_CAN_LINK),y)
-$(warning CC cannot link executables. Skipping bpfilter.)
-else
obj-$(CONFIG_BPFILTER) += bpfilter/
-endif
obj-$(CONFIG_PACKET) += packet/
obj-$(CONFIG_NET_KEY) += key/
obj-$(CONFIG_BRIDGE) += bridge/
menuconfig BPFILTER
bool "BPF based packet filtering framework (BPFILTER)"
- default n
depends on NET && BPF && INET
help
This builds experimental bpfilter framework that is aiming to
if BPFILTER
config BPFILTER_UMH
tristate "bpfilter kernel module with user mode helper"
+ depends on $(success,$(srctree)/scripts/cc-can-link.sh $(CC))
default m
help
This builds bpfilter kernel module with embedded user mode helper
HOSTLDFLAGS += -static
endif
-# a bit of elf magic to convert bpfilter_umh binary into a binary blob
-# inside bpfilter_umh.o elf file referenced by
-# _binary_net_bpfilter_bpfilter_umh_start symbol
-# which bpfilter_kern.c passes further into umh blob loader at run-time
-quiet_cmd_copy_umh = GEN $@
- cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \
- $(OBJCOPY) -I binary \
- `LC_ALL=C $(OBJDUMP) -f net/bpfilter/bpfilter_umh \
- |awk -F' |,' '/file format/{print "-O",$$NF} \
- /^architecture:/{print "-B",$$2}'` \
- --rename-section .data=.init.rodata $< $@
-
-$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh
- $(call cmd,copy_umh)
+$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
-bpfilter-objs += bpfilter_kern.o bpfilter_umh.o
+bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o
#include <linux/file.h>
#include "msgfmt.h"
-#define UMH_start _binary_net_bpfilter_bpfilter_umh_start
-#define UMH_end _binary_net_bpfilter_bpfilter_umh_end
-
-extern char UMH_start;
-extern char UMH_end;
+extern char bpfilter_umh_start;
+extern char bpfilter_umh_end;
static struct umh_info info;
/* since ip_getsockopt() can run in parallel, serialize access to umh */
int err;
/* fork usermode process */
- err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info);
+ err = fork_usermode_blob(&bpfilter_umh_start,
+ &bpfilter_umh_end - &bpfilter_umh_start,
+ &info);
if (err)
return err;
pr_info("Loaded bpfilter_umh pid %d\n", info.pid);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+ .section .init.rodata, "a"
+ .global bpfilter_umh_start
+bpfilter_umh_start:
+ .incbin "net/bpfilter/bpfilter_umh"
+ .global bpfilter_umh_end
+bpfilter_umh_end:
if (ifr->ifr_qlen < 0)
return -EINVAL;
if (dev->tx_queue_len ^ ifr->ifr_qlen) {
- unsigned int orig_len = dev->tx_queue_len;
-
- dev->tx_queue_len = ifr->ifr_qlen;
- err = call_netdevice_notifiers(
- NETDEV_CHANGE_TX_QUEUE_LEN, dev);
- err = notifier_to_errno(err);
- if (err) {
- dev->tx_queue_len = orig_len;
+ err = dev_change_tx_queue_len(dev, ifr->ifr_qlen);
+ if (err)
return err;
- }
}
return 0;
if (rule->mark && r->mark != rule->mark)
continue;
+ if (rule->suppress_ifgroup != -1 &&
+ r->suppress_ifgroup != rule->suppress_ifgroup)
+ continue;
+
+ if (rule->suppress_prefixlen != -1 &&
+ r->suppress_prefixlen != rule->suppress_prefixlen)
+ continue;
+
if (rule->mark_mask && r->mark_mask != rule->mark_mask)
continue;
if (rule->ip_proto && r->ip_proto != rule->ip_proto)
continue;
+ if (rule->proto && r->proto != rule->proto)
+ continue;
+
if (fib_rule_port_range_set(&rule->sport_range) &&
!fib_rule_port_range_compare(&r->sport_range,
&rule->sport_range))
return err;
}
+static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
+ struct nlattr **tb, struct fib_rule *rule)
+{
+ struct fib_rule *r;
+
+ list_for_each_entry(r, &ops->rules_list, list) {
+ if (r->action != rule->action)
+ continue;
+
+ if (r->table != rule->table)
+ continue;
+
+ if (r->pref != rule->pref)
+ continue;
+
+ if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
+ continue;
+
+ if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
+ continue;
+
+ if (r->mark != rule->mark)
+ continue;
+
+ if (r->suppress_ifgroup != rule->suppress_ifgroup)
+ continue;
+
+ if (r->suppress_prefixlen != rule->suppress_prefixlen)
+ continue;
+
+ if (r->mark_mask != rule->mark_mask)
+ continue;
+
+ if (r->tun_id != rule->tun_id)
+ continue;
+
+ if (r->fr_net != rule->fr_net)
+ continue;
+
+ if (r->l3mdev != rule->l3mdev)
+ continue;
+
+ if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
+ !uid_eq(r->uid_range.end, rule->uid_range.end))
+ continue;
+
+ if (r->ip_proto != rule->ip_proto)
+ continue;
+
+ if (r->proto != rule->proto)
+ continue;
+
+ if (!fib_rule_port_range_compare(&r->sport_range,
+ &rule->sport_range))
+ continue;
+
+ if (!fib_rule_port_range_compare(&r->dport_range,
+ &rule->dport_range))
+ continue;
+
+ if (!ops->compare(r, frh, tb))
+ continue;
+ return 1;
+ }
+ return 0;
+}
+
int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
goto errout;
if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
- rule_find(ops, frh, tb, rule, user_priority)) {
+ rule_exists(ops, frh, tb, rule)) {
err = -EEXIST;
goto errout_free;
}
memcpy(params->smac, dev->dev_addr, ETH_ALEN);
params->h_vlan_TCI = 0;
params->h_vlan_proto = 0;
+ params->ifindex = dev->ifindex;
- return dev->ifindex;
+ return 0;
}
#endif
/* verify forwarding is enabled on this interface */
in_dev = __in_dev_get_rcu(dev);
if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
- return 0;
+ return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
fl4.flowi4_iif = 1;
tb = fib_get_table(net, tbid);
if (unlikely(!tb))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
} else {
err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
}
- if (err || res.type != RTN_UNICAST)
- return 0;
+ if (err) {
+ /* map fib lookup errors to RTN_ type */
+ if (err == -EINVAL)
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ if (err == -EHOSTUNREACH)
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ if (err == -EACCES)
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
+
+ if (res.type != RTN_UNICAST)
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
if (res.fi->fib_nhs > 1)
fib_select_path(net, &res, &fl4, NULL);
if (check_mtu) {
mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
if (params->tot_len > mtu)
- return 0;
+ return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
nh = &res.fi->fib_nh[res.nh_sel];
/* do not handle lwt encaps right now */
if (nh->nh_lwtstate)
- return 0;
+ return BPF_FIB_LKUP_RET_UNSUPP_LWT;
dev = nh->nh_dev;
- if (unlikely(!dev))
- return 0;
-
if (nh->nh_gw)
params->ipv4_dst = nh->nh_gw;
* rcu_read_lock_bh is not needed here
*/
neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
- if (neigh)
- return bpf_fib_set_fwd_params(params, neigh, dev);
+ if (!neigh)
+ return BPF_FIB_LKUP_RET_NO_NEIGH;
- return 0;
+ return bpf_fib_set_fwd_params(params, neigh, dev);
}
#endif
/* link local addresses are never forwarded */
if (rt6_need_strict(dst) || rt6_need_strict(src))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
dev = dev_get_by_index_rcu(net, params->ifindex);
if (unlikely(!dev))
idev = __in6_dev_get_safely(dev);
if (unlikely(!idev || !net->ipv6.devconf_all->forwarding))
- return 0;
+ return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
fl6.flowi6_iif = 1;
tb = ipv6_stub->fib6_get_table(net, tbid);
if (unlikely(!tb))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
} else {
}
if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+
+ if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
+ switch (f6i->fib6_type) {
+ case RTN_BLACKHOLE:
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ case RTN_UNREACHABLE:
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ case RTN_PROHIBIT:
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+ default:
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
+ }
- if (unlikely(f6i->fib6_flags & RTF_REJECT ||
- f6i->fib6_type != RTN_UNICAST))
- return 0;
+ if (f6i->fib6_type != RTN_UNICAST)
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
if (check_mtu) {
mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
if (params->tot_len > mtu)
- return 0;
+ return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
if (f6i->fib6_nh.nh_lwtstate)
- return 0;
+ return BPF_FIB_LKUP_RET_UNSUPP_LWT;
if (f6i->fib6_flags & RTF_GATEWAY)
*dst = f6i->fib6_nh.nh_gw;
*/
neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
ndisc_hashfn, dst, dev);
- if (neigh)
- return bpf_fib_set_fwd_params(params, neigh, dev);
+ if (!neigh)
+ return BPF_FIB_LKUP_RET_NO_NEIGH;
- return 0;
+ return bpf_fib_set_fwd_params(params, neigh, dev);
}
#endif
struct bpf_fib_lookup *, params, int, plen, u32, flags)
{
struct net *net = dev_net(skb->dev);
- int index = -EAFNOSUPPORT;
+ int rc = -EAFNOSUPPORT;
if (plen < sizeof(*params))
return -EINVAL;
switch (params->family) {
#if IS_ENABLED(CONFIG_INET)
case AF_INET:
- index = bpf_ipv4_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv4_fib_lookup(net, params, flags, false);
break;
#endif
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
- index = bpf_ipv6_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv6_fib_lookup(net, params, flags, false);
break;
#endif
}
- if (index > 0) {
+ if (!rc) {
struct net_device *dev;
- dev = dev_get_by_index_rcu(net, index);
+ dev = dev_get_by_index_rcu(net, params->ifindex);
if (!is_skb_forwardable(dev, skb))
- index = 0;
+ rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
- return index;
+ return rc;
}
static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
if (npages >= 1 << order) {
page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
__GFP_COMP |
- __GFP_NOWARN |
- __GFP_NORETRY,
+ __GFP_NOWARN,
order);
if (page)
goto fill_page;
rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
rsk_prot->obj_size, 0,
- prot->slab_flags, NULL);
+ SLAB_ACCOUNT | prot->slab_flags,
+ NULL);
if (!rsk_prot->slab) {
pr_crit("%s: Can't create request sock SLAB cache!\n",
if (alloc_slab) {
prot->slab = kmem_cache_create_usercopy(prot->name,
prot->obj_size, 0,
- SLAB_HWCACHE_ALIGN | prot->slab_flags,
+ SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT |
+ prot->slab_flags,
prot->useroffset, prot->usersize,
NULL);
kmem_cache_create(prot->twsk_prot->twsk_slab_name,
prot->twsk_prot->twsk_obj_size,
0,
+ SLAB_ACCOUNT |
prot->slab_flags,
NULL);
if (prot->twsk_prot->twsk_slab == NULL)
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
- skb_gro_remcsum_cleanup(skb, &grc);
- skb->remcsum_offload = 0;
+ skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
return pp;
}
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
ipv4.sysctl_tcp_fastopen);
struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
struct tcp_fastopen_context *ctxt;
- int ret;
u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
+ __le32 key[4];
+ int ret, i;
tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
if (!tbl.data)
rcu_read_lock();
ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
if (ctxt)
- memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+ memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
else
- memset(user_key, 0, sizeof(user_key));
+ memset(key, 0, sizeof(key));
rcu_read_unlock();
+ for (i = 0; i < ARRAY_SIZE(key); i++)
+ user_key[i] = le32_to_cpu(key[i]);
+
snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
user_key[0], user_key[1], user_key[2], user_key[3]);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
ret = -EINVAL;
goto bad_key;
}
- tcp_fastopen_reset_cipher(net, NULL, user_key,
+
+ for (i = 0; i < ARRAY_SIZE(user_key); i++)
+ key[i] = cpu_to_le32(user_key[i]);
+
+ tcp_fastopen_reset_cipher(net, NULL, key,
TCP_FASTOPEN_KEY_LENGTH);
}
bad_key:
pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
- user_key[0], user_key[1], user_key[2], user_key[3],
+ user_key[0], user_key[1], user_key[2], user_key[3],
(char *)tbl.data, ret);
kfree(tbl.data);
return ret;
* it is probably a retransmit.
*/
if (tp->ecn_flags & TCP_ECN_SEEN)
- tcp_enter_quickack_mode(sk, 1);
+ tcp_enter_quickack_mode(sk, 2);
break;
case INET_ECN_CE:
if (tcp_ca_needs_ecn(sk))
if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
/* Better not delay acks, sender can have a very low cwnd */
- tcp_enter_quickack_mode(sk, 1);
+ tcp_enter_quickack_mode(sk, 2);
tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
}
tp->ecn_flags |= TCP_ECN_SEEN;
if (tcp_is_reno(tp)) {
tcp_remove_reno_sacks(sk, pkts_acked);
+
+ /* If any of the cumulatively ACKed segments was
+ * retransmitted, non-SACK case cannot confirm that
+ * progress was due to original transmission due to
+ * lack of TCPCB_SACKED_ACKED bits even if some of
+ * the packets may have been never retransmitted.
+ */
+ if (flag & FLAG_RETRANS_DATA_ACKED)
+ flag &= ~FLAG_ORIG_SACK_ACKED;
} else {
int delta;
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
EXPORT_SYMBOL(udp_gro_receive);
unsigned long expires, u32 flags)
{
struct fib6_info *f6i;
+ u32 prio;
f6i = addrconf_get_prefix_route(&ifp->addr,
ifp->prefix_len,
if (!f6i)
return -ENOENT;
- if (f6i->fib6_metric != ifp->rt_priority) {
+ prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF;
+ if (f6i->fib6_metric != prio) {
+ /* delete old one */
+ ip6_del_rt(dev_net(ifp->idev->dev), f6i);
+
/* add new one */
addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
ifp->rt_priority, ifp->idev->dev,
expires, flags, GFP_KERNEL);
- /* delete old one */
- ip6_del_rt(dev_net(ifp->idev->dev), f6i);
} else {
if (!expires)
fib6_clean_expires(f6i);
if (hdr == NULL)
goto err_reg;
- net->nf_frag.sysctl.frags_hdr = hdr;
+ net->nf_frag_frags_hdr = hdr;
return 0;
err_reg:
{
struct ctl_table *table;
- table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg;
- unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr);
+ table = net->nf_frag_frags_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->nf_frag_frags_hdr);
if (!net_eq(net, &init_net))
kfree(table);
}
return -ENOMEM;
for_each_possible_cpu(cpu) {
- tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL);
+ tfm = crypto_alloc_shash(algo->name, 0, 0);
if (IS_ERR(tfm))
return PTR_ERR(tfm);
p_tfm = per_cpu_ptr(algo->tfms, cpu);
skb_reset_network_header(skb);
skb_reset_mac_header(skb);
+ local_bh_disable();
__ieee80211_subif_start_xmit(skb, skb->dev, flags);
+ local_bh_enable();
return 0;
}
struct hlist_node node;
struct nf_conntrack_tuple tuple;
struct nf_conntrack_zone zone;
+ int cpu;
+ u32 jiffies32;
};
struct nf_conncount_rb {
return false;
conn->tuple = *tuple;
conn->zone = *zone;
+ conn->cpu = raw_smp_processor_id();
+ conn->jiffies32 = (u32)jiffies;
hlist_add_head(&conn->node, head);
return true;
}
EXPORT_SYMBOL_GPL(nf_conncount_add);
+static const struct nf_conntrack_tuple_hash *
+find_or_evict(struct net *net, struct nf_conncount_tuple *conn)
+{
+ const struct nf_conntrack_tuple_hash *found;
+ unsigned long a, b;
+ int cpu = raw_smp_processor_id();
+ __s32 age;
+
+ found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
+ if (found)
+ return found;
+ b = conn->jiffies32;
+ a = (u32)jiffies;
+
+ /* conn might have been added just before by another cpu and
+ * might still be unconfirmed. In this case, nf_conntrack_find()
+ * returns no result. Thus only evict if this cpu added the
+ * stale entry or if the entry is older than two jiffies.
+ */
+ age = a - b;
+ if (conn->cpu == cpu || age >= 2) {
+ hlist_del(&conn->node);
+ kmem_cache_free(conncount_conn_cachep, conn);
+ return ERR_PTR(-ENOENT);
+ }
+
+ return ERR_PTR(-EAGAIN);
+}
+
unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
const struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_zone *zone,
{
const struct nf_conntrack_tuple_hash *found;
struct nf_conncount_tuple *conn;
- struct hlist_node *n;
struct nf_conn *found_ct;
+ struct hlist_node *n;
unsigned int length = 0;
*addit = tuple ? true : false;
/* check the saved connections */
hlist_for_each_entry_safe(conn, n, head, node) {
- found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
- if (found == NULL) {
- hlist_del(&conn->node);
- kmem_cache_free(conncount_conn_cachep, conn);
+ found = find_or_evict(net, conn);
+ if (IS_ERR(found)) {
+ /* Not found, but might be about to be confirmed */
+ if (PTR_ERR(found) == -EAGAIN) {
+ length++;
+ if (!tuple)
+ continue;
+
+ if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
+ nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
+ nf_ct_zone_id(zone, zone->dir))
+ *addit = false;
+ }
continue;
}
nf_ct_expect_iterate_destroy(expect_iter_me, NULL);
nf_ct_iterate_destroy(unhelp, me);
+
+ /* Maybe someone has gotten the helper already when unhelp above.
+ * So need to wait it.
+ */
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
if (write) {
struct ctl_table tmp = *table;
+ /* proc_dostring() can append to existing strings, so we need to
+ * initialize it as an empty string.
+ */
+ buf[0] = '\0';
tmp.data = buf;
r = proc_dostring(&tmp, write, buffer, lenp, ppos);
if (r)
rcu_assign_pointer(net->nf.nf_loggers[tindex], logger);
mutex_unlock(&nf_log_mutex);
} else {
+ struct ctl_table tmp = *table;
+
+ tmp.data = buf;
mutex_lock(&nf_log_mutex);
logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
if (!logger)
- table->data = "NONE";
+ strlcpy(buf, "NONE", sizeof(buf));
else
- table->data = logger->name;
- r = proc_dostring(table, write, buffer, lenp, ppos);
+ strlcpy(buf, logger->name, sizeof(buf));
mutex_unlock(&nf_log_mutex);
+ r = proc_dostring(&tmp, write, buffer, lenp, ppos);
}
return r;
static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
[NFQA_CFG_CMD] = { .len = sizeof(struct nfqnl_msg_config_cmd) },
[NFQA_CFG_PARAMS] = { .len = sizeof(struct nfqnl_msg_config_params) },
+ [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 },
+ [NFQA_CFG_MASK] = { .type = NLA_U32 },
+ [NFQA_CFG_FLAGS] = { .type = NLA_U32 },
};
static const struct nf_queue_handler nfqh = {
int rds_conn_init(void)
{
+ int ret;
+
+ ret = rds_loop_net_init(); /* register pernet callback */
+ if (ret)
+ return ret;
+
rds_conn_slab = kmem_cache_create("rds_connection",
sizeof(struct rds_connection),
0, 0, NULL);
- if (!rds_conn_slab)
+ if (!rds_conn_slab) {
+ rds_loop_net_exit();
return -ENOMEM;
+ }
rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info);
rds_info_register_func(RDS_INFO_SEND_MESSAGES,
void rds_conn_exit(void)
{
+ rds_loop_net_exit(); /* unregister pernet callback */
rds_loop_exit();
WARN_ON(!hlist_empty(rds_conn_hash));
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/in.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
#include "rds_single_path.h"
#include "rds.h"
static DEFINE_SPINLOCK(loop_conns_lock);
static LIST_HEAD(loop_conns);
+static atomic_t rds_loop_unloading = ATOMIC_INIT(0);
+
+static void rds_loop_set_unloading(void)
+{
+ atomic_set(&rds_loop_unloading, 1);
+}
+
+static bool rds_loop_is_unloading(struct rds_connection *conn)
+{
+ return atomic_read(&rds_loop_unloading) != 0;
+}
/*
* This 'loopback' transport is a special case for flows that originate
struct rds_loop_connection *lc, *_lc;
LIST_HEAD(tmp_list);
+ rds_loop_set_unloading();
+ synchronize_rcu();
/* avoid calling conn_destroy with irqs off */
spin_lock_irq(&loop_conns_lock);
list_splice(&loop_conns, &tmp_list);
}
}
+static void rds_loop_kill_conns(struct net *net)
+{
+ struct rds_loop_connection *lc, *_lc;
+ LIST_HEAD(tmp_list);
+
+ spin_lock_irq(&loop_conns_lock);
+ list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node) {
+ struct net *c_net = read_pnet(&lc->conn->c_net);
+
+ if (net != c_net)
+ continue;
+ list_move_tail(&lc->loop_node, &tmp_list);
+ }
+ spin_unlock_irq(&loop_conns_lock);
+
+ list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) {
+ WARN_ON(lc->conn->c_passive);
+ rds_conn_destroy(lc->conn);
+ }
+}
+
+static void __net_exit rds_loop_exit_net(struct net *net)
+{
+ rds_loop_kill_conns(net);
+}
+
+static struct pernet_operations rds_loop_net_ops = {
+ .exit = rds_loop_exit_net,
+};
+
+int rds_loop_net_init(void)
+{
+ return register_pernet_device(&rds_loop_net_ops);
+}
+
+void rds_loop_net_exit(void)
+{
+ unregister_pernet_device(&rds_loop_net_ops);
+}
+
/*
* This is missing .xmit_* because loop doesn't go through generic
* rds_send_xmit() and doesn't call rds_recv_incoming(). .listen_stop and
.inc_free = rds_loop_inc_free,
.t_name = "loopback",
.t_type = RDS_TRANS_LOOP,
+ .t_unloading = rds_loop_is_unloading,
};
/* loop.c */
extern struct rds_transport rds_loop_transport;
+int rds_loop_net_init(void);
+void rds_loop_net_exit(void);
void rds_loop_exit(void);
#endif
*/
static void smc_tcp_listen_work(struct work_struct *);
+static void smc_connect_work(struct work_struct *);
static void smc_set_keepalive(struct sock *sk, int val)
{
goto out;
smc = smc_sk(sk);
+
+ /* cleanup for a dangling non-blocking connect */
+ flush_work(&smc->connect_work);
+ kfree(smc->connect_info);
+ smc->connect_info = NULL;
+
if (sk->sk_state == SMC_LISTEN)
/* smc_close_non_accepted() is called and acquires
* sock lock for child sockets again
sk->sk_protocol = protocol;
smc = smc_sk(sk);
INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
+ INIT_WORK(&smc->connect_work, smc_connect_work);
INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
INIT_LIST_HEAD(&smc->accept_q);
spin_lock_init(&smc->accept_q_lock);
return 0;
}
+static void smc_connect_work(struct work_struct *work)
+{
+ struct smc_sock *smc = container_of(work, struct smc_sock,
+ connect_work);
+ int rc;
+
+ lock_sock(&smc->sk);
+ rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
+ smc->connect_info->alen, smc->connect_info->flags);
+ if (smc->clcsock->sk->sk_err) {
+ smc->sk.sk_err = smc->clcsock->sk->sk_err;
+ goto out;
+ }
+ if (rc < 0) {
+ smc->sk.sk_err = -rc;
+ goto out;
+ }
+
+ rc = __smc_connect(smc);
+ if (rc < 0)
+ smc->sk.sk_err = -rc;
+
+out:
+ smc->sk.sk_state_change(&smc->sk);
+ kfree(smc->connect_info);
+ smc->connect_info = NULL;
+ release_sock(&smc->sk);
+}
+
static int smc_connect(struct socket *sock, struct sockaddr *addr,
int alen, int flags)
{
smc_copy_sock_settings_to_clc(smc);
tcp_sk(smc->clcsock->sk)->syn_smc = 1;
- rc = kernel_connect(smc->clcsock, addr, alen, flags);
- if (rc)
- goto out;
+ if (flags & O_NONBLOCK) {
+ if (smc->connect_info) {
+ rc = -EALREADY;
+ goto out;
+ }
+ smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
+ if (!smc->connect_info) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ smc->connect_info->alen = alen;
+ smc->connect_info->flags = flags ^ O_NONBLOCK;
+ memcpy(&smc->connect_info->addr, addr, alen);
+ schedule_work(&smc->connect_work);
+ rc = -EINPROGRESS;
+ } else {
+ rc = kernel_connect(smc->clcsock, addr, alen, flags);
+ if (rc)
+ goto out;
- rc = __smc_connect(smc);
- if (rc < 0)
- goto out;
- else
- rc = 0; /* success cases including fallback */
+ rc = __smc_connect(smc);
+ if (rc < 0)
+ goto out;
+ else
+ rc = 0; /* success cases including fallback */
+ }
out:
release_sock(sk);
struct sock *sk = sock->sk;
__poll_t mask = 0;
struct smc_sock *smc;
- int rc;
if (!sk)
return EPOLLNVAL;
smc = smc_sk(sock->sk);
- sock_hold(sk);
- lock_sock(sk);
if ((sk->sk_state == SMC_INIT) || smc->use_fallback) {
/* delegate to CLC child sock */
- release_sock(sk);
mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
- lock_sock(sk);
sk->sk_err = smc->clcsock->sk->sk_err;
- if (sk->sk_err) {
+ if (sk->sk_err)
mask |= EPOLLERR;
- } else {
- /* if non-blocking connect finished ... */
- if (sk->sk_state == SMC_INIT &&
- mask & EPOLLOUT &&
- smc->clcsock->sk->sk_state != TCP_CLOSE) {
- rc = __smc_connect(smc);
- if (rc < 0)
- mask |= EPOLLERR;
- /* success cases including fallback */
- mask |= EPOLLOUT | EPOLLWRNORM;
- }
- }
} else {
- if (sk->sk_state != SMC_CLOSED) {
- release_sock(sk);
+ if (sk->sk_state != SMC_CLOSED)
sock_poll_wait(file, sk_sleep(sk), wait);
- lock_sock(sk);
- }
if (sk->sk_err)
mask |= EPOLLERR;
if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
}
if (smc->conn.urg_state == SMC_URG_VALID)
mask |= EPOLLPRI;
-
}
- release_sock(sk);
- sock_put(sk);
return mask;
}
struct work_struct close_work; /* peer sent some closing */
};
+struct smc_connect_info {
+ int flags;
+ int alen;
+ struct sockaddr addr;
+};
+
struct smc_sock { /* smc sock container */
struct sock sk;
struct socket *clcsock; /* internal tcp socket */
struct smc_connection conn; /* smc connection */
struct smc_sock *listen_smc; /* listen parent */
+ struct smc_connect_info *connect_info; /* connect address & flags */
+ struct work_struct connect_work; /* handle non-blocking connect*/
struct work_struct tcp_listen_work;/* handle tcp socket accepts */
struct work_struct smc_listen_work;/* prepare new accept socket */
struct list_head accept_q; /* sockets to be accepted */
*/
struct strp_msg strp;
int accum_len;
- int early_eaten;
};
static inline struct _strp_msg *_strp_msg(struct sk_buff *skb)
head = strp->skb_head;
if (head) {
/* Message already in progress */
-
- stm = _strp_msg(head);
- if (unlikely(stm->early_eaten)) {
- /* Already some number of bytes on the receive sock
- * data saved in skb_head, just indicate they
- * are consumed.
- */
- eaten = orig_len <= stm->early_eaten ?
- orig_len : stm->early_eaten;
- stm->early_eaten -= eaten;
-
- return eaten;
- }
-
if (unlikely(orig_offset)) {
/* Getting data with a non-zero offset when a message is
* in progress is not expected. If it does happen, we
}
stm->accum_len += cand_len;
+ eaten += cand_len;
strp->need_bytes = stm->strp.full_len -
stm->accum_len;
- stm->early_eaten = cand_len;
STRP_STATS_ADD(strp->stats.bytes, cand_len);
desc->count = 0; /* Stop reading socket */
break;
nl80211_check_s32);
/*
* Check HT operation mode based on
- * IEEE 802.11 2012 8.4.2.59 HT Operation element.
+ * IEEE 802.11-2016 9.4.2.57 HT Operation element.
*/
if (tb[NL80211_MESHCONF_HT_OPMODE]) {
ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]);
IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
return -EINVAL;
- if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) &&
- (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
- return -EINVAL;
+ /* NON_HT_STA bit is reserved, but some programs set it */
+ ht_opmode &= ~IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT;
- switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) {
- case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
- case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
- if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)
- return -EINVAL;
- break;
- case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
- case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
- if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
- return -EINVAL;
- break;
- }
cfg->ht_opmode = ht_opmode;
mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1));
}
rem) {
u8 *mask_pat;
- nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
- nl80211_packet_pattern_policy,
- info->extack);
+ err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+ nl80211_packet_pattern_policy,
+ info->extack);
+ if (err)
+ goto error;
+
err = -EINVAL;
if (!pat_tb[NL80211_PKTPAT_MASK] ||
!pat_tb[NL80211_PKTPAT_PATTERN])
rem) {
u8 *mask_pat;
- nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
- nl80211_packet_pattern_policy, NULL);
+ err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+ nl80211_packet_pattern_policy, NULL);
+ if (err)
+ return err;
+
if (!pat_tb[NL80211_PKTPAT_MASK] ||
!pat_tb[NL80211_PKTPAT_PATTERN])
return -EINVAL;
struct ethhdr *eth = data;
struct ipv6hdr *ip6h;
struct iphdr *iph;
- int out_index;
u16 h_proto;
u64 nh_off;
+ int rc;
nh_off = sizeof(*eth);
if (data + nh_off > data_end)
fib_params.ifindex = ctx->ingress_ifindex;
- out_index = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
+ rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
/* verify egress index has xdp support
* TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with
* NOTE: without verification that egress index supports XDP
* forwarding packets are dropped.
*/
- if (out_index > 0) {
+ if (rc == 0) {
if (h_proto == htons(ETH_P_IP))
ip_decrease_ttl(iph);
else if (h_proto == htons(ETH_P_IPV6))
memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
- return bpf_redirect_map(&tx_port, out_index, 0);
+ return bpf_redirect_map(&tx_port, fib_params.ifindex, 0);
}
return XDP_PASS;
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
-cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1 && echo "y"
+cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1
#include <stdio.h>
int main(void)
{
return -1;
}
- if (do_pin_fd(prog_fd, argv[1])) {
- p_err("failed to pin program");
- return -1;
- }
+ if (do_pin_fd(prog_fd, argv[1]))
+ goto err_close_obj;
if (json_output)
jsonw_null(json_wtr);
+ bpf_object__close(obj);
+
return 0;
+
+err_close_obj:
+ bpf_object__close(obj);
+ return -1;
}
static int do_help(int argc, char **argv)
CONFIG_CGROUP_BPF=y
CONFIG_NETDEVSIM=m
CONFIG_NET_CLS_ACT=y
+CONFIG_NET_SCHED=y
CONFIG_NET_SCH_INGRESS=y
CONFIG_NET_IPIP=y
CONFIG_IPV6=y
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ "$(id -u)" != "0" ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
+fi
+
SRC_TREE=../../../../
test_run()
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
+fi
+
GREEN='\033[0;92m'
RED='\033[0;31m'
NC='\033[0m' # No Color
# An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
# datagram can be read on NS6 when binding to fb00::6.
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
+fi
+
TMP_FILE="/tmp/selftest_lwt_seg6local.txt"
cleanup()
int main(int argc, char **argv)
{
- struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
int iov_count = 1, length = 1024, rate = 1;
struct sockmap_options options = {0};
int opt, longindex, err, cg_fd = 0;
char *bpf_file = BPF_SOCKMAP_FILENAME;
int test = PING_PONG;
- if (setrlimit(RLIMIT_MEMLOCK, &r)) {
- perror("setrlimit(RLIMIT_MEMLOCK)");
- return 1;
- }
-
if (argc < 2)
return test_suite();
projects / linux-2.6-block.git / commitdiff