Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

1 files changed, 142 insertions, 58 deletions

diff --git a/drivers/net/wireless/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/brcm80211/brcmfmac/pcie.c
index 1831ecd0813e..3a98c4306d1d 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/pcie.c
@@ -51,6 +51,8 @@ enum brcmf_pcie_state {
 #define BRCMF_PCIE_4356_NVRAM_NAME		"brcm/brcmfmac4356-pcie.txt"
 #define BRCMF_PCIE_43570_FW_NAME		"brcm/brcmfmac43570-pcie.bin"
 #define BRCMF_PCIE_43570_NVRAM_NAME		"brcm/brcmfmac43570-pcie.txt"
+#define BRCMF_PCIE_4358_FW_NAME			"brcm/brcmfmac4358-pcie.bin"
+#define BRCMF_PCIE_4358_NVRAM_NAME		"brcm/brcmfmac4358-pcie.txt"
 
 #define BRCMF_PCIE_FW_UP_TIMEOUT		2000 /* msec */
 
@@ -110,10 +112,11 @@ enum brcmf_pcie_state {
 						 BRCMF_PCIE_MB_INT_D2H3_DB0 | \
 						 BRCMF_PCIE_MB_INT_D2H3_DB1)
 
-#define BRCMF_PCIE_MIN_SHARED_VERSION		4
+#define BRCMF_PCIE_MIN_SHARED_VERSION		5
 #define BRCMF_PCIE_MAX_SHARED_VERSION		5
 #define BRCMF_PCIE_SHARED_VERSION_MASK		0x00FF
-#define BRCMF_PCIE_SHARED_TXPUSH_SUPPORT	0x4000
+#define BRCMF_PCIE_SHARED_DMA_INDEX		0x10000
+#define BRCMF_PCIE_SHARED_DMA_2B_IDX		0x100000
 
 #define BRCMF_PCIE_FLAGS_HTOD_SPLIT		0x4000
 #define BRCMF_PCIE_FLAGS_DTOH_SPLIT		0x8000
@@ -145,6 +148,10 @@ enum brcmf_pcie_state {
 #define BRCMF_SHARED_RING_H2D_R_IDX_PTR_OFFSET	8
 #define BRCMF_SHARED_RING_D2H_W_IDX_PTR_OFFSET	12
 #define BRCMF_SHARED_RING_D2H_R_IDX_PTR_OFFSET	16
+#define BRCMF_SHARED_RING_H2D_WP_HADDR_OFFSET	20
+#define BRCMF_SHARED_RING_H2D_RP_HADDR_OFFSET	28
+#define BRCMF_SHARED_RING_D2H_WP_HADDR_OFFSET	36
+#define BRCMF_SHARED_RING_D2H_RP_HADDR_OFFSET	44
 #define BRCMF_SHARED_RING_TCM_MEMLOC_OFFSET	0
 #define BRCMF_SHARED_RING_MAX_SUB_QUEUES	52
 
@@ -189,6 +196,8 @@ MODULE_FIRMWARE(BRCMF_PCIE_4356_FW_NAME);
 MODULE_FIRMWARE(BRCMF_PCIE_4356_NVRAM_NAME);
 MODULE_FIRMWARE(BRCMF_PCIE_43570_FW_NAME);
 MODULE_FIRMWARE(BRCMF_PCIE_43570_NVRAM_NAME);
+MODULE_FIRMWARE(BRCMF_PCIE_4358_FW_NAME);
+MODULE_FIRMWARE(BRCMF_PCIE_4358_NVRAM_NAME);
 
 
 struct brcmf_pcie_console {
@@ -244,6 +253,13 @@ struct brcmf_pciedev_info {
 	bool mbdata_completed;
 	bool irq_allocated;
 	bool wowl_enabled;
+	u8 dma_idx_sz;
+	void *idxbuf;
+	u32 idxbuf_sz;
+	dma_addr_t idxbuf_dmahandle;
+	u16 (*read_ptr)(struct brcmf_pciedev_info *devinfo, u32 mem_offset);
+	void (*write_ptr)(struct brcmf_pciedev_info *devinfo, u32 mem_offset,
+			  u16 value);
 };
 
 struct brcmf_pcie_ringbuf {
@@ -273,15 +289,6 @@ static const u32 brcmf_ring_itemsize[BRCMF_NROF_COMMON_MSGRINGS] = {
 };
 
 
-/* dma flushing needs implementation for mips and arm platforms. Should
- * be put in util. Note, this is not real flushing. It is virtual non
- * cached memory. Only write buffers should have to be drained. Though
- * this may be different depending on platform......
- */
-#define brcmf_dma_flush(addr, len)
-#define brcmf_dma_invalidate_cache(addr, len)
-
-
 static u32
 brcmf_pcie_read_reg32(struct brcmf_pciedev_info *devinfo, u32 reg_offset)
 {
@@ -329,6 +336,25 @@ brcmf_pcie_write_tcm16(struct brcmf_pciedev_info *devinfo, u32 mem_offset,
 }
 
 
+static u16
+brcmf_pcie_read_idx(struct brcmf_pciedev_info *devinfo, u32 mem_offset)
+{
+	u16 *address = devinfo->idxbuf + mem_offset;
+
+	return (*(address));
+}
+
+
+static void
+brcmf_pcie_write_idx(struct brcmf_pciedev_info *devinfo, u32 mem_offset,
+		     u16 value)
+{
+	u16 *address = devinfo->idxbuf + mem_offset;
+
+	*(address) = value;
+}
+
+
 static u32
 brcmf_pcie_read_tcm32(struct brcmf_pciedev_info *devinfo, u32 mem_offset)
 {
@@ -874,7 +900,7 @@ static int brcmf_pcie_ring_mb_write_rptr(void *ctx)
 	brcmf_dbg(PCIE, "W r_ptr %d (%d), ring %d\n", commonring->r_ptr,
 		  commonring->w_ptr, ring->id);
 
-	brcmf_pcie_write_tcm16(devinfo, ring->r_idx_addr, commonring->r_ptr);
+	devinfo->write_ptr(devinfo, ring->r_idx_addr, commonring->r_ptr);
 
 	return 0;
 }
@@ -892,7 +918,7 @@ static int brcmf_pcie_ring_mb_write_wptr(void *ctx)
 	brcmf_dbg(PCIE, "W w_ptr %d (%d), ring %d\n", commonring->w_ptr,
 		  commonring->r_ptr, ring->id);
 
-	brcmf_pcie_write_tcm16(devinfo, ring->w_idx_addr, commonring->w_ptr);
+	devinfo->write_ptr(devinfo, ring->w_idx_addr, commonring->w_ptr);
 
 	return 0;
 }
@@ -921,7 +947,7 @@ static int brcmf_pcie_ring_mb_update_rptr(void *ctx)
 	if (devinfo->state != BRCMFMAC_PCIE_STATE_UP)
 		return -EIO;
 
-	commonring->r_ptr = brcmf_pcie_read_tcm16(devinfo, ring->r_idx_addr);
+	commonring->r_ptr = devinfo->read_ptr(devinfo, ring->r_idx_addr);
 
 	brcmf_dbg(PCIE, "R r_ptr %d (%d), ring %d\n", commonring->r_ptr,
 		  commonring->w_ptr, ring->id);
@@ -939,7 +965,7 @@ static int brcmf_pcie_ring_mb_update_wptr(void *ctx)
 	if (devinfo->state != BRCMFMAC_PCIE_STATE_UP)
 		return -EIO;
 
-	commonring->w_ptr = brcmf_pcie_read_tcm16(devinfo, ring->w_idx_addr);
+	commonring->w_ptr = devinfo->read_ptr(devinfo, ring->w_idx_addr);
 
 	brcmf_dbg(PCIE, "R w_ptr %d (%d), ring %d\n", commonring->w_ptr,
 		  commonring->r_ptr, ring->id);
@@ -1044,6 +1070,13 @@ static void brcmf_pcie_release_ringbuffers(struct brcmf_pciedev_info *devinfo)
 	}
 	kfree(devinfo->shared.flowrings);
 	devinfo->shared.flowrings = NULL;
+	if (devinfo->idxbuf) {
+		dma_free_coherent(&devinfo->pdev->dev,
+				  devinfo->idxbuf_sz,
+				  devinfo->idxbuf,
+				  devinfo->idxbuf_dmahandle);
+		devinfo->idxbuf = NULL;
+	}
 }
 
 
@@ -1059,19 +1092,72 @@ static int brcmf_pcie_init_ringbuffers(struct brcmf_pciedev_info *devinfo)
 	u32 addr;
 	u32 ring_mem_ptr;
 	u32 i;
+	u64 address;
+	u32 bufsz;
 	u16 max_sub_queues;
+	u8 idx_offset;
 
 	ring_addr = devinfo->shared.ring_info_addr;
 	brcmf_dbg(PCIE, "Base ring addr = 0x%08x\n", ring_addr);
+	addr = ring_addr + BRCMF_SHARED_RING_MAX_SUB_QUEUES;
+	max_sub_queues = brcmf_pcie_read_tcm16(devinfo, addr);
 
-	addr = ring_addr + BRCMF_SHARED_RING_D2H_W_IDX_PTR_OFFSET;
-	d2h_w_idx_ptr = brcmf_pcie_read_tcm32(devinfo, addr);
-	addr = ring_addr + BRCMF_SHARED_RING_D2H_R_IDX_PTR_OFFSET;
-	d2h_r_idx_ptr = brcmf_pcie_read_tcm32(devinfo, addr);
-	addr = ring_addr + BRCMF_SHARED_RING_H2D_W_IDX_PTR_OFFSET;
-	h2d_w_idx_ptr = brcmf_pcie_read_tcm32(devinfo, addr);
-	addr = ring_addr + BRCMF_SHARED_RING_H2D_R_IDX_PTR_OFFSET;
-	h2d_r_idx_ptr = brcmf_pcie_read_tcm32(devinfo, addr);
+	if (devinfo->dma_idx_sz != 0) {
+		bufsz = (BRCMF_NROF_D2H_COMMON_MSGRINGS + max_sub_queues) *
+			devinfo->dma_idx_sz * 2;
+		devinfo->idxbuf = dma_alloc_coherent(&devinfo->pdev->dev, bufsz,
+						     &devinfo->idxbuf_dmahandle,
+						     GFP_KERNEL);
+		if (!devinfo->idxbuf)
+			devinfo->dma_idx_sz = 0;
+	}
+
+	if (devinfo->dma_idx_sz == 0) {
+		addr = ring_addr + BRCMF_SHARED_RING_D2H_W_IDX_PTR_OFFSET;
+		d2h_w_idx_ptr = brcmf_pcie_read_tcm32(devinfo, addr);
+		addr = ring_addr + BRCMF_SHARED_RING_D2H_R_IDX_PTR_OFFSET;
+		d2h_r_idx_ptr = brcmf_pcie_read_tcm32(devinfo, addr);
+		addr = ring_addr + BRCMF_SHARED_RING_H2D_W_IDX_PTR_OFFSET;
+		h2d_w_idx_ptr = brcmf_pcie_read_tcm32(devinfo, addr);
+		addr = ring_addr + BRCMF_SHARED_RING_H2D_R_IDX_PTR_OFFSET;
+		h2d_r_idx_ptr = brcmf_pcie_read_tcm32(devinfo, addr);
+		idx_offset = sizeof(u32);
+		devinfo->write_ptr = brcmf_pcie_write_tcm16;
+		devinfo->read_ptr = brcmf_pcie_read_tcm16;
+		brcmf_dbg(PCIE, "Using TCM indices\n");
+	} else {
+		memset(devinfo->idxbuf, 0, bufsz);
+		devinfo->idxbuf_sz = bufsz;
+		idx_offset = devinfo->dma_idx_sz;
+		devinfo->write_ptr = brcmf_pcie_write_idx;
+		devinfo->read_ptr = brcmf_pcie_read_idx;
+
+		h2d_w_idx_ptr = 0;
+		addr = ring_addr + BRCMF_SHARED_RING_H2D_WP_HADDR_OFFSET;
+		address = (u64)devinfo->idxbuf_dmahandle;
+		brcmf_pcie_write_tcm32(devinfo, addr, address & 0xffffffff);
+		brcmf_pcie_write_tcm32(devinfo, addr + 4, address >> 32);
+
+		h2d_r_idx_ptr = h2d_w_idx_ptr + max_sub_queues * idx_offset;
+		addr = ring_addr + BRCMF_SHARED_RING_H2D_RP_HADDR_OFFSET;
+		address += max_sub_queues * idx_offset;
+		brcmf_pcie_write_tcm32(devinfo, addr, address & 0xffffffff);
+		brcmf_pcie_write_tcm32(devinfo, addr + 4, address >> 32);
+
+		d2h_w_idx_ptr = h2d_r_idx_ptr + max_sub_queues * idx_offset;
+		addr = ring_addr + BRCMF_SHARED_RING_D2H_WP_HADDR_OFFSET;
+		address += max_sub_queues * idx_offset;
+		brcmf_pcie_write_tcm32(devinfo, addr, address & 0xffffffff);
+		brcmf_pcie_write_tcm32(devinfo, addr + 4, address >> 32);
+
+		d2h_r_idx_ptr = d2h_w_idx_ptr +
+				BRCMF_NROF_D2H_COMMON_MSGRINGS * idx_offset;
+		addr = ring_addr + BRCMF_SHARED_RING_D2H_RP_HADDR_OFFSET;
+		address += BRCMF_NROF_D2H_COMMON_MSGRINGS * idx_offset;
+		brcmf_pcie_write_tcm32(devinfo, addr, address & 0xffffffff);
+		brcmf_pcie_write_tcm32(devinfo, addr + 4, address >> 32);
+		brcmf_dbg(PCIE, "Using host memory indices\n");
+	}
 
 	addr = ring_addr + BRCMF_SHARED_RING_TCM_MEMLOC_OFFSET;
 	ring_mem_ptr = brcmf_pcie_read_tcm32(devinfo, addr);
@@ -1085,8 +1171,8 @@ static int brcmf_pcie_init_ringbuffers(struct brcmf_pciedev_info *devinfo)
 		ring->id = i;
 		devinfo->shared.commonrings[i] = ring;
 
-		h2d_w_idx_ptr += sizeof(u32);
-		h2d_r_idx_ptr += sizeof(u32);
+		h2d_w_idx_ptr += idx_offset;
+		h2d_r_idx_ptr += idx_offset;
 		ring_mem_ptr += BRCMF_RING_MEM_SZ;
 	}
 
@@ -1100,13 +1186,11 @@ static int brcmf_pcie_init_ringbuffers(struct brcmf_pciedev_info *devinfo)
 		ring->id = i;
 		devinfo->shared.commonrings[i] = ring;
 
-		d2h_w_idx_ptr += sizeof(u32);
-		d2h_r_idx_ptr += sizeof(u32);
+		d2h_w_idx_ptr += idx_offset;
+		d2h_r_idx_ptr += idx_offset;
 		ring_mem_ptr += BRCMF_RING_MEM_SZ;
 	}
 
-	addr = ring_addr + BRCMF_SHARED_RING_MAX_SUB_QUEUES;
-	max_sub_queues = brcmf_pcie_read_tcm16(devinfo, addr);
 	devinfo->shared.nrof_flowrings =
 			max_sub_queues - BRCMF_NROF_H2D_COMMON_MSGRINGS;
 	rings = kcalloc(devinfo->shared.nrof_flowrings, sizeof(*ring),
@@ -1130,15 +1214,15 @@ static int brcmf_pcie_init_ringbuffers(struct brcmf_pciedev_info *devinfo)
 					     ring);
 		ring->w_idx_addr = h2d_w_idx_ptr;
 		ring->r_idx_addr = h2d_r_idx_ptr;
-		h2d_w_idx_ptr += sizeof(u32);
-		h2d_r_idx_ptr += sizeof(u32);
+		h2d_w_idx_ptr += idx_offset;
+		h2d_r_idx_ptr += idx_offset;
 	}
 	devinfo->shared.flowrings = rings;
 
 	return 0;
 
 fail:
-	brcmf_err("Allocating commonring buffers failed\n");
+	brcmf_err("Allocating ring buffers failed\n");
 	brcmf_pcie_release_ringbuffers(devinfo);
 	return -ENOMEM;
 }
@@ -1171,7 +1255,6 @@ static int brcmf_pcie_init_scratchbuffers(struct brcmf_pciedev_info *devinfo)
 		goto fail;
 
 	memset(devinfo->shared.scratch, 0, BRCMF_DMA_D2H_SCRATCH_BUF_LEN);
-	brcmf_dma_flush(devinfo->shared.scratch, BRCMF_DMA_D2H_SCRATCH_BUF_LEN);
 
 	addr = devinfo->shared.tcm_base_address +
 	       BRCMF_SHARED_DMA_SCRATCH_ADDR_OFFSET;
@@ -1189,7 +1272,6 @@ static int brcmf_pcie_init_scratchbuffers(struct brcmf_pciedev_info *devinfo)
 		goto fail;
 
 	memset(devinfo->shared.ringupd, 0, BRCMF_DMA_D2H_RINGUPD_BUF_LEN);
-	brcmf_dma_flush(devinfo->shared.ringupd, BRCMF_DMA_D2H_RINGUPD_BUF_LEN);
 
 	addr = devinfo->shared.tcm_base_address +
 	       BRCMF_SHARED_DMA_RINGUPD_ADDR_OFFSET;
@@ -1276,10 +1358,13 @@ brcmf_pcie_init_share_ram_info(struct brcmf_pciedev_info *devinfo,
 		brcmf_err("Unsupported PCIE version %d\n", version);
 		return -EINVAL;
 	}
-	if (shared->flags & BRCMF_PCIE_SHARED_TXPUSH_SUPPORT) {
-		brcmf_err("Unsupported legacy TX mode 0x%x\n",
-			  shared->flags & BRCMF_PCIE_SHARED_TXPUSH_SUPPORT);
-		return -EINVAL;
+
+	/* check firmware support dma indicies */
+	if (shared->flags & BRCMF_PCIE_SHARED_DMA_INDEX) {
+		if (shared->flags & BRCMF_PCIE_SHARED_DMA_2B_IDX)
+			devinfo->dma_idx_sz = sizeof(u16);
+		else
+			devinfo->dma_idx_sz = sizeof(u32);
 	}
 
 	addr = sharedram_addr + BRCMF_SHARED_MAX_RXBUFPOST_OFFSET;
@@ -1333,6 +1418,10 @@ static int brcmf_pcie_get_fwnames(struct brcmf_pciedev_info *devinfo)
 		fw_name = BRCMF_PCIE_43570_FW_NAME;
 		nvram_name = BRCMF_PCIE_43570_NVRAM_NAME;
 		break;
+	case BRCM_CC_4358_CHIP_ID:
+		fw_name = BRCMF_PCIE_4358_FW_NAME;
+		nvram_name = BRCMF_PCIE_4358_NVRAM_NAME;
+		break;
 	default:
 		brcmf_err("Unsupported chip 0x%04x\n", devinfo->ci->chip);
 		return -ENODEV;
@@ -1540,20 +1629,7 @@ static void brcmf_pcie_buscore_write32(void *ctx, u32 addr, u32 value)
 
 static int brcmf_pcie_buscoreprep(void *ctx)
 {
-	struct brcmf_pciedev_info *devinfo = (struct brcmf_pciedev_info *)ctx;
-	int err;
-
-	err = brcmf_pcie_get_resource(devinfo);
-	if (err == 0) {
-		/* Set CC watchdog to reset all the cores on the chip to bring
-		 * back dongle to a sane state.
-		 */
-		brcmf_pcie_buscore_write32(ctx, CORE_CC_REG(SI_ENUM_BASE,
-							    watchdog), 4);
-		msleep(100);
-	}
-
-	return err;
+	return brcmf_pcie_get_resource(ctx);
 }
 
 
@@ -1609,7 +1685,7 @@ static void brcmf_pcie_setup(struct device *dev, const struct firmware *fw,
 		bus->msgbuf->commonrings[i] =
 				&devinfo->shared.commonrings[i]->commonring;
 
-	flowrings = kcalloc(devinfo->shared.nrof_flowrings, sizeof(flowrings),
+	flowrings = kcalloc(devinfo->shared.nrof_flowrings, sizeof(*flowrings),
 			    GFP_KERNEL);
 	if (!flowrings)
 		goto fail;
@@ -1641,8 +1717,13 @@ brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct brcmf_pciedev_info *devinfo;
 	struct brcmf_pciedev *pcie_bus_dev;
 	struct brcmf_bus *bus;
+	u16 domain_nr;
+	u16 bus_nr;
 
-	brcmf_dbg(PCIE, "Enter %x:%x\n", pdev->vendor, pdev->device);
+	domain_nr = pci_domain_nr(pdev->bus) + 1;
+	bus_nr = pdev->bus->number;
+	brcmf_dbg(PCIE, "Enter %x:%x (%d/%d)\n", pdev->vendor, pdev->device,
+		  domain_nr, bus_nr);
 
 	ret = -ENOMEM;
 	devinfo = kzalloc(sizeof(*devinfo), GFP_KERNEL);
@@ -1691,10 +1772,10 @@ brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		goto fail_bus;
 
-	ret = brcmf_fw_get_firmwares(bus->dev, BRCMF_FW_REQUEST_NVRAM |
-					       BRCMF_FW_REQ_NV_OPTIONAL,
-				     devinfo->fw_name, devinfo->nvram_name,
-				     brcmf_pcie_setup);
+	ret = brcmf_fw_get_firmwares_pcie(bus->dev, BRCMF_FW_REQUEST_NVRAM |
+						    BRCMF_FW_REQ_NV_OPTIONAL,
+					  devinfo->fw_name, devinfo->nvram_name,
+					  brcmf_pcie_setup, domain_nr, bus_nr);
 	if (ret == 0)
 		return 0;
 fail_bus:
@@ -1730,6 +1811,7 @@ brcmf_pcie_remove(struct pci_dev *pdev)
 		brcmf_pcie_intr_disable(devinfo);
 
 	brcmf_detach(&pdev->dev);
+	brcmf_pcie_reset_device(devinfo);
 
 	kfree(bus->bus_priv.pcie);
 	kfree(bus->msgbuf->flowrings);
@@ -1850,9 +1932,11 @@ static struct pci_device_id brcmf_pcie_devid_table[] = {
 	BRCMF_PCIE_DEVICE(BRCM_PCIE_4356_DEVICE_ID),
 	BRCMF_PCIE_DEVICE(BRCM_PCIE_43567_DEVICE_ID),
 	BRCMF_PCIE_DEVICE(BRCM_PCIE_43570_DEVICE_ID),
+	BRCMF_PCIE_DEVICE(BRCM_PCIE_4358_DEVICE_ID),
 	BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_DEVICE_ID),
 	BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_2G_DEVICE_ID),
 	BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_5G_DEVICE_ID),
+	BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_RAW_DEVICE_ID),
 	{ /* end: all zeroes */ }
 };