Merge branch 'mvpp2-tx-flow-control'

Stefan Chulski says:

====================
net: mvpp2: Add TX Flow Control support

Armada hardware has a pause generation mechanism in GOP (MAC).
The GOP generate flow control frames based on an indication programmed in Ports Control 0 Register. There is a bit per port.
However assertion of the PortX Pause bits in the ports control 0 register only sends a one time pause.
To complement the function the GOP has a mechanism to periodically send pause control messages based on periodic counters.
This mechanism ensures that the pause is effective as long as the Appropriate PortX Pause is asserted.

Problem is that Packet Processor that actually can drop packets due to lack of resources not connected to the GOP flow control generation mechanism.
To solve this issue Armada has firmware running on CM3 CPU dedicated for Flow Control support.
Firmware monitors Packet Processor resources and asserts XON/XOFF by writing to Ports Control 0 Register.

MSS shared SRAM memory used to communicate between CM3 firmware and PP2 driver.
During init PP2 driver informs firmware about used BM pools, RXQs, congestion and depletion thresholds.

The pause frames are generated whenever congestion or depletion in resources is detected.
The back pressure is stopped when the resource reaches a sufficient level.
So the congestion/depletion and sufficient level implement a hysteresis that reduces the XON/XOFF toggle frequency.

Packet Processor v23 hardware introduces support for RX FIFO fill level monitor.
Patch "add PPv23 version definition" to differ between v23 and v22 hardware.
Patch "add TX FC firmware check" verifies that CM3 firmware supports Flow Control monitoring.

v12 --> v13
- Remove bm_underrun_protect module_param

v11 --> v12
- Improve warning message in "net: mvpp2: add TX FC firmware check" patch

v10 --> v11
- Improve "net: mvpp2: add CM3 SRAM memory map" comment
- Move condition check to 'net: mvpp2: always compare hw-version vs MVPP21' patch

v9 --> v10
- Add CM3 SRAM description to PPv2 documentation

v8 --> v9
- Replace generic pool allocation with devm_ioremap_resource

v7 --> v8
- Reorder "always compare hw-version vs MVPP21" and "add PPv23 version definition" commits
- Typo fixes
- Remove condition fix from "add RXQ flow control configurations"

v6 --> v7
- Reduce patch set from 18 to 15 patches
 - Documentation change combined into a single patch
 - RXQ and BM size change combined into a single patch
 - Ring size change check moved into "add RXQ flow control configurations" commit

v5 --> v6
- No change

v4 --> v5
- Add missed Signed-off
- Fix warnings in patches 3 and 12
- Add revision requirement to warning message
- Move mss_spinlock into RXQ flow control configurations patch
- Improve FCA RXQ non occupied descriptor threshold commit message

v3 --> v4
- Remove RFC tag

v2 --> v3
- Remove inline functions
- Add PPv2.3 description into marvell-pp2.txt
- Improve mvpp2_interrupts_mask/unmask procedure
- Improve FC enable/disable procedure
- Add priv->sram_pool check
- Remove gen_pool_destroy call
- Reduce Flow Control timer to x100 faster

v1 --> v2
- Add memory requirements information
- Add EPROBE_DEFER if of_gen_pool_get return NULL
- Move Flow control configuration to mvpp2_mac_link_up callback
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

Documentation/devicetree/bindings/net/marvell-pp2.txt

@@ -1,5 +1,6 @@
 * Marvell Armada 375 Ethernet Controller (PPv2.1)
   Marvell Armada 7K/8K Ethernet Controller (PPv2.2)
+  Marvell CN913X Ethernet Controller (PPv2.3)
 
 Required properties:
 
@@ -12,10 +13,11 @@ Required properties:
 	- common controller registers
 	- LMS registers
 	- one register area per Ethernet port
-  For "marvell,armada-7k-pp2", must contain the following register
+  For "marvell,armada-7k-pp2" used by 7K/8K and CN913X, must contain the following register
   sets:
 	- packet processor registers
 	- networking interfaces registers
+	- CM3 address space used for TX Flow Control
 
 - clocks: pointers to the reference clocks for this device, consequently:
 	- main controller clock (for both armada-375-pp2 and armada-7k-pp2)
@@ -81,7 +83,7 @@ Example for marvell,armada-7k-pp2:
 
 cpm_ethernet: ethernet@0 {
 	compatible = "marvell,armada-7k-pp22";
-	reg = <0x0 0x100000>, <0x129000 0xb000>;
+	reg = <0x0 0x100000>, <0x129000 0xb000>, <0x220000 0x800>;
 	clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>,
 		 <&cpm_syscon0 1 5>, <&cpm_syscon0 1 6>, <&cpm_syscon0 1 18>;
 	clock-names = "pp_clk", "gop_clk", "mg_clk", "mg_core_clk", "axi_clk";

arch/arm64/boot/dts/marvell/armada-cp11x.dtsi

@@ -59,7 +59,7 @@
 
 		CP11X_LABEL(ethernet): ethernet@0 {
 			compatible = "marvell,armada-7k-pp22";
-			reg = <0x0 0x100000>, <0x129000 0xb000>;
+			reg = <0x0 0x100000>, <0x129000 0xb000>, <0x220000 0x800>;
 			clocks = <&CP11X_LABEL(clk) 1 3>, <&CP11X_LABEL(clk) 1 9>,
 				 <&CP11X_LABEL(clk) 1 5>, <&CP11X_LABEL(clk) 1 6>,
 				 <&CP11X_LABEL(clk) 1 18>;

drivers/net/ethernet/marvell/mvpp2/mvpp2.h

@@ -60,6 +60,9 @@
 /* Top Registers */
 #define MVPP2_MH_REG(port)			(0x5040 + 4 * (port))
 #define MVPP2_DSA_EXTENDED			BIT(5)
+#define MVPP2_VER_ID_REG			0x50b0
+#define MVPP2_VER_PP22				0x10
+#define MVPP2_VER_PP23				0x11
 
 /* Parser Registers */
 #define MVPP2_PRS_INIT_LOOKUP_REG		0x1000
@@ -292,6 +295,8 @@
 #define     MVPP2_PON_CAUSE_TXP_OCCUP_DESC_ALL_MASK	0x3fc00000
 #define     MVPP2_PON_CAUSE_MISC_SUM_MASK		BIT(31)
 #define MVPP2_ISR_MISC_CAUSE_REG		0x55b0
+#define MVPP2_ISR_RX_ERR_CAUSE_REG(port)	(0x5520 + 4 * (port))
+#define     MVPP2_ISR_RX_ERR_CAUSE_NONOCC_MASK	0x00ff
 
 /* Buffer Manager registers */
 #define MVPP2_BM_POOL_BASE_REG(pool)		(0x6000 + ((pool) * 4))
@@ -319,6 +324,10 @@
 #define     MVPP2_BM_HIGH_THRESH_MASK		0x7f0000
 #define     MVPP2_BM_HIGH_THRESH_VALUE(val)	((val) << \
 						MVPP2_BM_HIGH_THRESH_OFFS)
+#define     MVPP2_BM_BPPI_HIGH_THRESH		0x1E
+#define     MVPP2_BM_BPPI_LOW_THRESH		0x1C
+#define     MVPP23_BM_BPPI_HIGH_THRESH		0x34
+#define     MVPP23_BM_BPPI_LOW_THRESH		0x28
 #define MVPP2_BM_INTR_CAUSE_REG(pool)		(0x6240 + ((pool) * 4))
 #define     MVPP2_BM_RELEASED_DELAY_MASK	BIT(0)
 #define     MVPP2_BM_ALLOC_FAILED_MASK		BIT(1)
@@ -347,6 +356,10 @@
 #define MVPP2_OVERRUN_ETH_DROP			0x7000
 #define MVPP2_CLS_ETH_DROP			0x7020
 
+#define MVPP22_BM_POOL_BASE_ADDR_HIGH_REG	0x6310
+#define     MVPP22_BM_POOL_BASE_ADDR_HIGH_MASK	0xff
+#define     MVPP23_BM_8POOL_MODE		BIT(8)
+
 /* Hit counters registers */
 #define MVPP2_CTRS_IDX				0x7040
 #define     MVPP22_CTRS_TX_CTR(port, txq)	((txq) | ((port) << 3) | BIT(7))
@@ -469,7 +482,7 @@
 #define     MVPP22_GMAC_INT_SUM_MASK_LINK_STAT	BIT(1)
 #define	    MVPP22_GMAC_INT_SUM_MASK_PTP	BIT(2)
 
-/* Per-port XGMAC registers. PPv2.2 only, only for GOP port 0,
+/* Per-port XGMAC registers. PPv2.2 and PPv2.3, only for GOP port 0,
  * relative to port->base.
  */
 #define MVPP22_XLG_CTRL0_REG			0x100
@@ -506,7 +519,7 @@
 #define     MVPP22_XLG_CTRL4_MACMODSELECT_GMAC	BIT(12)
 #define     MVPP22_XLG_CTRL4_EN_IDLE_CHECK	BIT(14)
 
-/* SMI registers. PPv2.2 only, relative to priv->iface_base. */
+/* SMI registers. PPv2.2 and PPv2.3, relative to priv->iface_base. */
 #define MVPP22_SMI_MISC_CFG_REG			0x1204
 #define     MVPP22_SMI_POLLING_EN		BIT(10)
 
@@ -582,7 +595,7 @@
 #define MVPP2_QUEUE_NEXT_DESC(q, index) \
 	(((index) < (q)->last_desc) ? ((index) + 1) : 0)
 
-/* XPCS registers. PPv2.2 only */
+/* XPCS registers.PPv2.2 and PPv2.3 */
 #define MVPP22_MPCS_BASE(port)			(0x7000 + (port) * 0x1000)
 #define MVPP22_MPCS_CTRL			0x14
 #define     MVPP22_MPCS_CTRL_FWD_ERR_CONN	BIT(10)
@@ -593,7 +606,16 @@
 #define     MVPP22_MPCS_CLK_RESET_DIV_RATIO(n)	((n) << 4)
 #define     MVPP22_MPCS_CLK_RESET_DIV_SET	BIT(11)
 
-/* XPCS registers. PPv2.2 only */
+/* FCA registers. PPv2.2 and PPv2.3 */
+#define MVPP22_FCA_BASE(port)			(0x7600 + (port) * 0x1000)
+#define MVPP22_FCA_REG_SIZE			16
+#define MVPP22_FCA_REG_MASK			0xFFFF
+#define MVPP22_FCA_CONTROL_REG			0x0
+#define MVPP22_FCA_ENABLE_PERIODIC		BIT(11)
+#define MVPP22_PERIODIC_COUNTER_LSB_REG		(0x110)
+#define MVPP22_PERIODIC_COUNTER_MSB_REG		(0x114)
+
+/* XPCS registers. PPv2.2 and PPv2.3 */
 #define MVPP22_XPCS_BASE(port)			(0x7400 + (port) * 0x1000)
 #define MVPP22_XPCS_CFG0			0x0
 #define     MVPP22_XPCS_CFG0_RESET_DIS		BIT(0)
@@ -712,8 +734,8 @@
 #define MVPP2_PORT_MAX_RXQ		32
 
 /* Max number of Rx descriptors */
-#define MVPP2_MAX_RXD_MAX		1024
-#define MVPP2_MAX_RXD_DFLT		128
+#define MVPP2_MAX_RXD_MAX		2048
+#define MVPP2_MAX_RXD_DFLT		1024
 
 /* Max number of Tx descriptors */
 #define MVPP2_MAX_TXD_MAX		2048
@@ -748,6 +770,66 @@
 #define MVPP2_TX_FIFO_THRESHOLD(kb)	\
 		((kb) * 1024 - MVPP2_TX_FIFO_THRESHOLD_MIN)
 
+/* RX FIFO threshold in 1KB granularity */
+#define MVPP23_PORT0_FIFO_TRSH	(9 * 1024)
+#define MVPP23_PORT1_FIFO_TRSH	(4 * 1024)
+#define MVPP23_PORT2_FIFO_TRSH	(2 * 1024)
+
+/* RX Flow Control Registers */
+#define MVPP2_RX_FC_REG(port)		(0x150 + 4 * (port))
+#define     MVPP2_RX_FC_EN		BIT(24)
+#define     MVPP2_RX_FC_TRSH_OFFS	16
+#define     MVPP2_RX_FC_TRSH_MASK	(0xFF << MVPP2_RX_FC_TRSH_OFFS)
+#define     MVPP2_RX_FC_TRSH_UNIT	256
+
+/* MSS Flow control */
+#define MSS_FC_COM_REG			0
+#define FLOW_CONTROL_ENABLE_BIT		BIT(0)
+#define FLOW_CONTROL_UPDATE_COMMAND_BIT	BIT(31)
+#define FC_QUANTA			0xFFFF
+#define FC_CLK_DIVIDER			100
+
+#define MSS_RXQ_TRESH_BASE		0x200
+#define MSS_RXQ_TRESH_OFFS		4
+#define MSS_RXQ_TRESH_REG(q, fq)	(MSS_RXQ_TRESH_BASE + (((q) + (fq)) \
+					* MSS_RXQ_TRESH_OFFS))
+
+#define MSS_BUF_POOL_BASE		0x40
+#define MSS_BUF_POOL_OFFS		4
+#define MSS_BUF_POOL_REG(id)		(MSS_BUF_POOL_BASE		\
+					+ (id) * MSS_BUF_POOL_OFFS)
+
+#define MSS_BUF_POOL_STOP_MASK		0xFFF
+#define MSS_BUF_POOL_START_MASK		(0xFFF << MSS_BUF_POOL_START_OFFS)
+#define MSS_BUF_POOL_START_OFFS		12
+#define MSS_BUF_POOL_PORTS_MASK		(0xF << MSS_BUF_POOL_PORTS_OFFS)
+#define MSS_BUF_POOL_PORTS_OFFS		24
+#define MSS_BUF_POOL_PORT_OFFS(id)	(0x1 <<				\
+					((id) + MSS_BUF_POOL_PORTS_OFFS))
+
+#define MSS_RXQ_TRESH_START_MASK	0xFFFF
+#define MSS_RXQ_TRESH_STOP_MASK		(0xFFFF << MSS_RXQ_TRESH_STOP_OFFS)
+#define MSS_RXQ_TRESH_STOP_OFFS		16
+
+#define MSS_RXQ_ASS_BASE	0x80
+#define MSS_RXQ_ASS_OFFS	4
+#define MSS_RXQ_ASS_PER_REG	4
+#define MSS_RXQ_ASS_PER_OFFS	8
+#define MSS_RXQ_ASS_PORTID_OFFS	0
+#define MSS_RXQ_ASS_PORTID_MASK	0x3
+#define MSS_RXQ_ASS_HOSTID_OFFS	2
+#define MSS_RXQ_ASS_HOSTID_MASK	0x3F
+
+#define MSS_RXQ_ASS_Q_BASE(q, fq) ((((q) + (fq)) % MSS_RXQ_ASS_PER_REG)	 \
+				  * MSS_RXQ_ASS_PER_OFFS)
+#define MSS_RXQ_ASS_PQ_BASE(q, fq) ((((q) + (fq)) / MSS_RXQ_ASS_PER_REG) \
+				   * MSS_RXQ_ASS_OFFS)
+#define MSS_RXQ_ASS_REG(q, fq) (MSS_RXQ_ASS_BASE + MSS_RXQ_ASS_PQ_BASE(q, fq))
+
+#define MSS_THRESHOLD_STOP	768
+#define MSS_THRESHOLD_START	1024
+#define MSS_FC_MAX_TIMEOUT	5000
+
 /* RX buffer constants */
 #define MVPP2_SKB_SHINFO_SIZE \
 	SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
@@ -845,8 +927,8 @@ enum mvpp22_ptp_packet_format {
 #define MVPP22_PTP_TIMESTAMPQUEUESELECT	BIT(18)
 
 /* BM constants */
-#define MVPP2_BM_JUMBO_BUF_NUM		512
-#define MVPP2_BM_LONG_BUF_NUM		1024
+#define MVPP2_BM_JUMBO_BUF_NUM		2048
+#define MVPP2_BM_LONG_BUF_NUM		2048
 #define MVPP2_BM_SHORT_BUF_NUM		2048
 #define MVPP2_BM_POOL_SIZE_MAX		(16*1024 - MVPP2_BM_POOL_PTR_ALIGN/4)
 #define MVPP2_BM_POOL_PTR_ALIGN		128
@@ -925,16 +1007,18 @@ struct mvpp2 {
 	/* Shared registers' base addresses */
 	void __iomem *lms_base;
 	void __iomem *iface_base;
+	void __iomem *cm3_base;
 
-	/* On PPv2.2, each "software thread" can access the base
+	/* On PPv2.2 and PPv2.3, each "software thread" can access the base
 	 * register through a separate address space, each 64 KB apart
 	 * from each other. Typically, such address spaces will be
 	 * used per CPU.
 	 */
 	void __iomem *swth_base[MVPP2_MAX_THREADS];
 
-	/* On PPv2.2, some port control registers are located into the system
-	 * controller space. These registers are accessible through a regmap.
+	/* On PPv2.2 and PPv2.3, some port control registers are located into
+	 * the system controller space. These registers are accessible
+	 * through a regmap.
 	 */
 	struct regmap *sysctrl_base;
 
@@ -976,7 +1060,7 @@ struct mvpp2 {
 	u32 tclk;
 
 	/* HW version */
-	enum { MVPP21, MVPP22 } hw_version;
+	enum { MVPP21, MVPP22, MVPP23 } hw_version;
 
 	/* Maximum number of RXQs per port */
 	unsigned int max_port_rxqs;
@@ -996,6 +1080,12 @@ struct mvpp2 {
 
 	/* page_pool allocator */
 	struct page_pool *page_pool[MVPP2_PORT_MAX_RXQ];
+
+	/* Global TX Flow Control config */
+	bool global_tx_fc;
+
+	/* Spinlocks for CM3 shared memory configuration */
+	spinlock_t mss_spinlock;
 };
 
 struct mvpp2_pcpu_stats {
@@ -1158,6 +1248,9 @@ struct mvpp2_port {
 	bool rx_hwtstamp;
 	enum hwtstamp_tx_types tx_hwtstamp_type;
 	struct mvpp2_hwtstamp_queue tx_hwtstamp_queue[2];
+
+	/* Firmware TX flow control */
+	bool tx_fc;
 };
 
 /* The mvpp2_tx_desc and mvpp2_rx_desc structures describe the
@@ -1220,7 +1313,7 @@ struct mvpp21_rx_desc {
 	__le32 reserved8;
 };
 
-/* HW TX descriptor for PPv2.2 */
+/* HW TX descriptor for PPv2.2 and PPv2.3 */
 struct mvpp22_tx_desc {
 	__le32 command;
 	u8  packet_offset;
@@ -1232,7 +1325,7 @@ struct mvpp22_tx_desc {
 	__le64 buf_cookie_misc;
 };
 
-/* HW RX descriptor for PPv2.2 */
+/* HW RX descriptor for PPv2.2 and PPv2.3 */
 struct mvpp22_rx_desc {
 	__le32 status;
 	__le16 reserved1;
@@ -1418,6 +1511,8 @@ void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name);
 
 void mvpp2_dbgfs_cleanup(struct mvpp2 *priv);
 
+void mvpp23_rx_fifo_fc_en(struct mvpp2 *priv, int port, bool en);
+
 #ifdef CONFIG_MVPP2_PTP
 int mvpp22_tai_probe(struct device *dev, struct mvpp2 *priv);
 void mvpp22_tai_tstamp(struct mvpp2_tai *tai, u32 tstamp,
@@ -1450,4 +1545,5 @@ static inline bool mvpp22_rx_hwtstamping(struct mvpp2_port *port)
 {
 	return IS_ENABLED(CONFIG_MVPP2_PTP) && port->rx_hwtstamp;
 }
+
 #endif