net: wwan: t7xx: Split 64bit accesses to fix alignment issues

Some of the registers are aligned on a 32bit boundary, causing
alignment faults on 64bit platforms.

 Unable to handle kernel paging request at virtual address ffffffc084a1d004
 Mem abort info:
 ESR = 0x0000000096000061
 EC = 0x25: DABT (current EL), IL = 32 bits
 SET = 0, FnV = 0
 EA = 0, S1PTW = 0
 FSC = 0x21: alignment fault
 Data abort info:
 ISV = 0, ISS = 0x00000061, ISS2 = 0x00000000
 CM = 0, WnR = 1, TnD = 0, TagAccess = 0
 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
 swapper pgtable: 4k pages, 39-bit VAs, pgdp=0000000046ad6000
 [ffffffc084a1d004] pgd=100000013ffff003, p4d=100000013ffff003, pud=100000013ffff003, pmd=0068000020a00711
 Internal error: Oops: 0000000096000061 [#1] SMP
 Modules linked in: mtk_t7xx(+) qcserial pppoe ppp_async option nft_fib_inet nf_flow_table_inet mt7921u(O) mt7921s(O) mt7921e(O) mt7921_common(O) iwlmvm(O) iwldvm(O) usb_wwan rndis_host qmi_wwan pppox ppp_generic nft_reject_ipv6 nft_reject_ipv4 nft_reject_inet nft_reject nft_redir nft_quota nft_numgen nft_nat nft_masq nft_log nft_limit nft_hash nft_flow_offload nft_fib_ipv6 nft_fib_ipv4 nft_fib nft_ct nft_chain_nat nf_tables nf_nat nf_flow_table nf_conntrack mt7996e(O) mt792x_usb(O) mt792x_lib(O) mt7915e(O) mt76_usb(O) mt76_sdio(O) mt76_connac_lib(O) mt76(O) mac80211(O) iwlwifi(O) huawei_cdc_ncm cfg80211(O) cdc_ncm cdc_ether wwan usbserial usbnet slhc sfp rtc_pcf8563 nfnetlink nf_reject_ipv6 nf_reject_ipv4 nf_log_syslog nf_defrag_ipv6 nf_defrag_ipv4 mt6577_auxadc mdio_i2c libcrc32c compat(O) cdc_wdm cdc_acm at24 crypto_safexcel pwm_fan i2c_gpio i2c_smbus industrialio i2c_algo_bit i2c_mux_reg i2c_mux_pca954x i2c_mux_pca9541 i2c_mux_gpio i2c_mux dummy oid_registry tun sha512_arm64 sha1_ce sha1_generic seqiv
 md5 geniv des_generic libdes cbc authencesn authenc leds_gpio xhci_plat_hcd xhci_pci xhci_mtk_hcd xhci_hcd nvme nvme_core gpio_button_hotplug(O) dm_mirror dm_region_hash dm_log dm_crypt dm_mod dax usbcore usb_common ptp aquantia pps_core mii tpm encrypted_keys trusted
 CPU: 3 PID: 5266 Comm: kworker/u9:1 Tainted: G O 6.6.22 #0
 Hardware name: Bananapi BPI-R4 (DT)
 Workqueue: md_hk_wq t7xx_fsm_uninit [mtk_t7xx]
 pstate: 804000c5 (Nzcv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : t7xx_cldma_hw_set_start_addr+0x1c/0x3c [mtk_t7xx]
 lr : t7xx_cldma_start+0xac/0x13c [mtk_t7xx]
 sp : ffffffc085d63d30
 x29: ffffffc085d63d30 x28: 0000000000000000 x27: 0000000000000000
 x26: 0000000000000000 x25: ffffff80c804f2c0 x24: ffffff80ca196c05
 x23: 0000000000000000 x22: ffffff80c814b9b8 x21: ffffff80c814b128
 x20: 0000000000000001 x19: ffffff80c814b080 x18: 0000000000000014
 x17: 0000000055c9806b x16: 000000007c5296d0 x15: 000000000f6bca68
 x14: 00000000dbdbdce4 x13: 000000001aeaf72a x12: 0000000000000001
 x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000
 x8 : ffffff80ca1ef6b4 x7 : ffffff80c814b818 x6 : 0000000000000018
 x5 : 0000000000000870 x4 : 0000000000000000 x3 : 0000000000000000
 x2 : 000000010a947000 x1 : ffffffc084a1d004 x0 : ffffffc084a1d004
 Call trace:
 t7xx_cldma_hw_set_start_addr+0x1c/0x3c [mtk_t7xx]
 t7xx_fsm_uninit+0x578/0x5ec [mtk_t7xx]
 process_one_work+0x154/0x2a0
 worker_thread+0x2ac/0x488
 kthread+0xe0/0xec
 ret_from_fork+0x10/0x20
 Code: f9400800 91001000 8b214001 d50332bf (f9000022)
 ---[ end trace 0000000000000000 ]---

The inclusion of io-64-nonatomic-lo-hi.h indicates that all 64bit
accesses can be replaced by pairs of nonatomic 32bit access.  Fix
alignment by forcing all accesses to be 32bit on 64bit platforms.

Link: https://forum.openwrt.org/t/fibocom-fm350-gl-support/142682/72
Fixes: 39d4390 ("net: wwan: t7xx: Add control DMA interface")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Reviewed-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Tested-by: Liviu Dudau <liviu@dudau.co.uk>
Link: https://lore.kernel.org/r/20240322144000.1683822-1-bjorn@mork.no
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: bmork

drivers/net/wwan/t7xx/t7xx_cldma.c

@@ -106,7 +106,7 @@ bool t7xx_cldma_tx_addr_is_set(struct t7xx_cldma_hw *hw_info, unsigned int qno)
 {
 	u32 offset = REG_CLDMA_UL_START_ADDRL_0 + qno * ADDR_SIZE;
 
-	return ioread64(hw_info->ap_pdn_base + offset);
+	return ioread64_lo_hi(hw_info->ap_pdn_base + offset);
 }
 
 void t7xx_cldma_hw_set_start_addr(struct t7xx_cldma_hw *hw_info, unsigned int qno, u64 address,
@@ -117,7 +117,7 @@ void t7xx_cldma_hw_set_start_addr(struct t7xx_cldma_hw *hw_info, unsigned int qn
 
 	reg = tx_rx == MTK_RX ? hw_info->ap_ao_base + REG_CLDMA_DL_START_ADDRL_0 :
 				hw_info->ap_pdn_base + REG_CLDMA_UL_START_ADDRL_0;
-	iowrite64(address, reg + offset);
+	iowrite64_lo_hi(address, reg + offset);
 }
 
 void t7xx_cldma_hw_resume_queue(struct t7xx_cldma_hw *hw_info, unsigned int qno,

drivers/net/wwan/t7xx/t7xx_hif_cldma.c

@@ -137,8 +137,9 @@ static int t7xx_cldma_gpd_rx_from_q(struct cldma_queue *queue, int budget, bool
 				return -ENODEV;
 			}
 
-			gpd_addr = ioread64(hw_info->ap_pdn_base + REG_CLDMA_DL_CURRENT_ADDRL_0 +
-					    queue->index * sizeof(u64));
+			gpd_addr = ioread64_lo_hi(hw_info->ap_pdn_base +
+						  REG_CLDMA_DL_CURRENT_ADDRL_0 +
+						  queue->index * sizeof(u64));
 			if (req->gpd_addr == gpd_addr || hwo_polling_count++ >= 100)
 				return 0;
 
@@ -316,8 +317,8 @@ static void t7xx_cldma_txq_empty_hndl(struct cldma_queue *queue)
 		struct t7xx_cldma_hw *hw_info = &md_ctrl->hw_info;
 
 		/* Check current processing TGPD, 64-bit address is in a table by Q index */
-		ul_curr_addr = ioread64(hw_info->ap_pdn_base + REG_CLDMA_UL_CURRENT_ADDRL_0 +
-					queue->index * sizeof(u64));
+		ul_curr_addr = ioread64_lo_hi(hw_info->ap_pdn_base + REG_CLDMA_UL_CURRENT_ADDRL_0 +
+					      queue->index * sizeof(u64));
 		if (req->gpd_addr != ul_curr_addr) {
 			spin_unlock_irqrestore(&md_ctrl->cldma_lock, flags);
 			dev_err(md_ctrl->dev, "CLDMA%d queue %d is not empty\n",

drivers/net/wwan/t7xx/t7xx_pcie_mac.c

@@ -75,7 +75,7 @@ static void t7xx_pcie_mac_atr_tables_dis(void __iomem *pbase, enum t7xx_atr_src_
 	for (i = 0; i < ATR_TABLE_NUM_PER_ATR; i++) {
 		offset = ATR_PORT_OFFSET * port + ATR_TABLE_OFFSET * i;
 		reg = pbase + ATR_PCIE_WIN0_T0_ATR_PARAM_SRC_ADDR + offset;
-		iowrite64(0, reg);
+		iowrite64_lo_hi(0, reg);
 	}
 }
 
@@ -112,17 +112,17 @@ static int t7xx_pcie_mac_atr_cfg(struct t7xx_pci_dev *t7xx_dev, struct t7xx_atr_
 
 	reg = pbase + ATR_PCIE_WIN0_T0_TRSL_ADDR + offset;
 	value = cfg->trsl_addr & ATR_PCIE_WIN0_ADDR_ALGMT;
-	iowrite64(value, reg);
+	iowrite64_lo_hi(value, reg);
 
 	reg = pbase + ATR_PCIE_WIN0_T0_TRSL_PARAM + offset;
 	iowrite32(cfg->trsl_id, reg);
 
 	reg = pbase + ATR_PCIE_WIN0_T0_ATR_PARAM_SRC_ADDR + offset;
 	value = (cfg->src_addr & ATR_PCIE_WIN0_ADDR_ALGMT) | (atr_size << 1) | BIT(0);
-	iowrite64(value, reg);
+	iowrite64_lo_hi(value, reg);
 
 	/* Ensure ATR is set */
-	ioread64(reg);
+	ioread64_lo_hi(reg);
 	return 0;
 }