[PATCH v7 0/4] Prerequisites for Cavium OCTEON-III network driver.

[PATCH v7 0/4] Prerequisites for Cavium OCTEON-III network driver.

[David Daney]

We want to add the Cavium OCTEON-III network driver.  But since
interacting with the input and output queues is done via special CPU
local memory, we also need to add support to the MIPS/Octeon
architecture code.  Aren't SoCs nice in this way?  These are the
prerequisite patches that are needed before the network driver can be
merged.

Changes in v7:

o Splitting of the patch set only.  These 4 mips patches are unchanged
  from the previous posting.

Changes in v6:

o Added back cleanup patch for previous generation SoC "staging"
  driver, as Greg K-H acked it.

o Moved FPA driver to drivers/net/ethernet/cavium/octeon as it is
  currently only used by the octeon3-ethernet driver.

o Many code formatting fixes as noted by davem.

Changes in v5:

o Removed cleanup patch for previous generation SoC "staging" driver,
  as it will be sent as a follow-on.

o Fixed kernel doc formatting in all patches.

o Removed redundant licensing text boilerplate.

o Reviewed-by: header added to 2/7.

o Rewrote locking code in 3/7 to eliminate inline asm.

Changes in v4:

o Use phy_print_status() instead of open coding the equivalent.

o Print warning on phy mode mismatch.

o Improve dt-bindings and add Acked-by.

Changes in v3:

o Fix PKI (RX path) initialization to work with little endian kernel.

Changes in v2:

o Cleanup and use of standard bindings in the device tree bindings
  document.

o Added (hopefully) clarifying comments about several OCTEON
  architectural peculiarities.

o Removed unused testing code from the driver.

o Removed some module parameters that already default to the proper
  values.

o KConfig cleanup, including testing on x86_64, arm64 and mips.

o Fixed breakage to the driver for previous generation of OCTEON SoCs (in
  the staging directory still).

o Verified bisectability of the patch set.

Carlos Munoz (2):
  MIPS: Octeon: Enable LMTDMA/LMTST operations.
  MIPS: Octeon: Add a global resource manager.

David Daney (2):
  MIPS: Octeon: Automatically provision CVMSEG space.
  staging: octeon: Remove USE_ASYNC_IOBDMA macro.

 arch/mips/cavium-octeon/Kconfig                    |  27 +-
 arch/mips/cavium-octeon/Makefile                   |   1 +
 arch/mips/cavium-octeon/resource-mgr.c             | 351 +++++++++++++++++++++
 arch/mips/cavium-octeon/setup.c                    |  22 +-
 .../asm/mach-cavium-octeon/kernel-entry-init.h     |  20 +-
 arch/mips/include/asm/mipsregs.h                   |   2 +
 arch/mips/include/asm/octeon/octeon.h              |  32 +-
 arch/mips/include/asm/processor.h                  |   2 +-
 arch/mips/kernel/octeon_switch.S                   |   2 -
 arch/mips/mm/tlbex.c                               |  29 +-
 drivers/staging/octeon/ethernet-defines.h          |   6 -
 drivers/staging/octeon/ethernet-rx.c               |  25 +-
 drivers/staging/octeon/ethernet-tx.c               |  85 ++---
 13 files changed, 472 insertions(+), 132 deletions(-)
 create mode 100644 arch/mips/cavium-octeon/resource-mgr.c

-- 
2.14.3

[PATCH v7 1/4] MIPS: Octeon: Enable LMTDMA/LMTST operations.

[David Daney]

From: Carlos Munoz <cmunoz@cavium.com>

LMTDMA/LMTST operations move data between cores and I/O devices:

* LMTST operations can send an address and a variable length
  (up to 128 bytes) of data to an I/O device.
* LMTDMA operations can send an address and a variable length
  (up to 128) of data to the I/O device and then return a
  variable length (up to 128 bytes) response from the I/O device.

For both LMTST and LMTDMA, the data sent to the device is first stored
in the CVMSEG core local memory cache line indexed by
CVMMEMCTL[LMTLINE], the data is then atomically transmitted to the
device with a store to the CVMSEG LMTDMA trigger location.

Reviewed-by: James Hogan <jhogan@kernel.org>
Signed-off-by: Carlos Munoz <cmunoz@cavium.com>
Signed-off-by: Steven J. Hill <Steven.Hill@cavium.com>
Signed-off-by: David Daney <david.daney@cavium.com>
---
 arch/mips/cavium-octeon/setup.c       |  6 ++++++
 arch/mips/include/asm/octeon/octeon.h | 12 ++++++++++--
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index a8034d0dcade..99e6a68bc652 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -609,6 +609,12 @@ void octeon_user_io_init(void)
 #else
 	cvmmemctl.s.cvmsegenak = 0;
 #endif
+	if (OCTEON_IS_OCTEON3()) {
+		/* Enable LMTDMA */
+		cvmmemctl.s.lmtena = 1;
+		/* Scratch line to use for LMT operation */
+		cvmmemctl.s.lmtline = 2;
+	}
 	/* R/W If set, CVMSEG is available for loads/stores in
 	 * supervisor mode. */
 	cvmmemctl.s.cvmsegenas = 0;
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index c99c4b6a79f4..92a17d67c1fa 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -179,7 +179,15 @@ union octeon_cvmemctl {
 		/* RO 1 = BIST fail, 0 = BIST pass */
 		__BITFIELD_FIELD(uint64_t wbfbist:1,
 		/* Reserved */
-		__BITFIELD_FIELD(uint64_t reserved:17,
+		__BITFIELD_FIELD(uint64_t reserved_52_57:6,
+		/* When set, LMTDMA/LMTST operations are permitted */
+		__BITFIELD_FIELD(uint64_t lmtena:1,
+		/* Selects the CVMSEG LM cacheline used by LMTDMA
+		 * LMTST and wide atomic store operations.
+		 */
+		__BITFIELD_FIELD(uint64_t lmtline:6,
+		/* Reserved */
+		__BITFIELD_FIELD(uint64_t reserved_41_44:4,
 		/* OCTEON II - TLB replacement policy: 0 = bitmask LRU; 1 = NLU.
 		 * This field selects between the TLB replacement policies:
 		 * bitmask LRU or NLU. Bitmask LRU maintains a mask of
@@ -275,7 +283,7 @@ union octeon_cvmemctl {
 		/* R/W Size of local memory in cache blocks, 54 (6912
 		 * bytes) is max legal value. */
 		__BITFIELD_FIELD(uint64_t lmemsz:6,
-		;)))))))))))))))))))))))))))))))))
+		;))))))))))))))))))))))))))))))))))))
 	} s;
 };
 
-- 
2.14.3

[PATCH v7 2/4] MIPS: Octeon: Automatically provision CVMSEG space.

[David Daney]

Remove CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE and automatically calculate
the amount of CVMSEG space needed.

1st 128-bytes: Use by IOBDMA
2nd 128-bytes: Reserved by kernel for scratch/TLS emulation.
3rd 128-bytes: OCTEON-III LMTLINE

New config variable CONFIG_CAVIUM_OCTEON_EXTRA_CVMSEG provisions
additional lines, defaults to zero.

Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Carlos Munoz <cmunoz@caviumnetworks.com>
---
 arch/mips/cavium-octeon/Kconfig                    | 27 ++++++++++++--------
 arch/mips/cavium-octeon/setup.c                    | 16 ++++++------
 .../asm/mach-cavium-octeon/kernel-entry-init.h     | 20 +++++++++------
 arch/mips/include/asm/mipsregs.h                   |  2 ++
 arch/mips/include/asm/octeon/octeon.h              |  2 ++
 arch/mips/include/asm/processor.h                  |  2 +-
 arch/mips/kernel/octeon_switch.S                   |  2 --
 arch/mips/mm/tlbex.c                               | 29 ++++++----------------
 drivers/staging/octeon/ethernet-defines.h          |  2 +-
 9 files changed, 50 insertions(+), 52 deletions(-)

diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig
index 204a1670fd9b..a50d1aa5863b 100644
--- a/arch/mips/cavium-octeon/Kconfig
+++ b/arch/mips/cavium-octeon/Kconfig
@@ -11,21 +11,26 @@ config CAVIUM_CN63XXP1
 	  non-CN63XXP1 hardware, so it is recommended to select "n"
 	  unless it is known the workarounds are needed.
 
-config CAVIUM_OCTEON_CVMSEG_SIZE
-	int "Number of L1 cache lines reserved for CVMSEG memory"
-	range 0 54
-	default 1
-	help
-	  CVMSEG LM is a segment that accesses portions of the dcache as a
-	  local memory; the larger CVMSEG is, the smaller the cache is.
-	  This selects the size of CVMSEG LM, which is in cache blocks. The
-	  legally range is from zero to 54 cache blocks (i.e. CVMSEG LM is
-	  between zero and 6192 bytes).
-
 endif # CPU_CAVIUM_OCTEON
 
 if CAVIUM_OCTEON_SOC
 
+config CAVIUM_OCTEON_EXTRA_CVMSEG
+	int "Number of extra L1 cache lines reserved for CVMSEG memory"
+	range 0 50
+	default 0
+	help
+	  CVMSEG LM is a segment that accesses portions of the dcache
+	  as a local memory; the larger CVMSEG is, the smaller the
+	  cache is.  The kernel uses two or three blocks (one for TLB
+	  exception handlers, one for driver IOBDMA operations, and on
+	  models that need it, one for LMTDMA operations). This
+	  selects an optional extra number of CVMSEG lines for use by
+	  other software.
+
+	  Normally no extra lines are required, and this parameter
+	  should be set to zero.
+
 config CAVIUM_OCTEON_LOCK_L2
 	bool "Lock often used kernel code in the L2"
 	default "y"
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 99e6a68bc652..51c4d3c3cada 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -68,6 +68,12 @@ extern void pci_console_init(const char *arg);
 static unsigned long long max_memory = ULLONG_MAX;
 static unsigned long long reserve_low_mem;
 
+/*
+ * modified in hernel-entry-init.h, must have an initial value to keep
+ * it from being clobbered when bss is zeroed.
+ */
+u32 octeon_cvmseg_lines = 2;
+
 DEFINE_SEMAPHORE(octeon_bootbus_sem);
 EXPORT_SYMBOL(octeon_bootbus_sem);
 
@@ -604,11 +610,7 @@ void octeon_user_io_init(void)
 
 	/* R/W If set, CVMSEG is available for loads/stores in
 	 * kernel/debug mode. */
-#if CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0
 	cvmmemctl.s.cvmsegenak = 1;
-#else
-	cvmmemctl.s.cvmsegenak = 0;
-#endif
 	if (OCTEON_IS_OCTEON3()) {
 		/* Enable LMTDMA */
 		cvmmemctl.s.lmtena = 1;
@@ -626,9 +628,9 @@ void octeon_user_io_init(void)
 
 	/* Setup of CVMSEG is done in kernel-entry-init.h */
 	if (smp_processor_id() == 0)
-		pr_notice("CVMSEG size: %d cache lines (%d bytes)\n",
-			  CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE,
-			  CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE * 128);
+		pr_notice("CVMSEG size: %u cache lines (%u bytes)\n",
+			  octeon_cvmseg_lines,
+			  octeon_cvmseg_lines * 128);
 
 	if (octeon_has_feature(OCTEON_FEATURE_FAU)) {
 		union cvmx_iob_fau_timeout fau_timeout;
diff --git a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
index c38b38ce5a3d..cdcca60978a2 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h
@@ -26,11 +26,18 @@
 	# a3 = address of boot descriptor block
 	.set push
 	.set arch=octeon
+	mfc0	v1, CP0_PRID_REG
+	andi	v1, 0xff00
+	li	v0, 0x9500		# cn78XX or later
+	subu	v1, v1, v0
+	li	t2, 2 + CONFIG_CAVIUM_OCTEON_EXTRA_CVMSEG
+	bltz	v1, 1f
+	addiu	t2, 1			# t2 has cvmseg_size
+1:
 	# Read the cavium mem control register
 	dmfc0	v0, CP0_CVMMEMCTL_REG
 	# Clear the lower 6 bits, the CVMSEG size
-	dins	v0, $0, 0, 6
-	ori	v0, CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE
+	dins	v0, t2, 0, 6
 	dmtc0	v0, CP0_CVMMEMCTL_REG	# Write the cavium mem control register
 	dmfc0	v0, CP0_CVMCTL_REG	# Read the cavium control register
 	# Disable unaligned load/store support but leave HW fixup enabled
@@ -70,7 +77,7 @@
 	# Flush dcache after config change
 	cache	9, 0($0)
 	# Zero all of CVMSEG to make sure parity is correct
-	dli	v0, CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE
+	move	v0, t2
 	dsll	v0, 7
 	beqz	v0, 2f
 1:	dsubu	v0, 8
@@ -126,12 +133,7 @@
 	LONG_L	sp, (t0)
 	# Set the SP global variable to zero so the master knows we've started
 	LONG_S	zero, (t0)
-#ifdef __OCTEON__
-	syncw
-	syncw
-#else
 	sync
-#endif
 	# Jump to the normal Linux SMP entry point
 	j   smp_bootstrap
 	nop
@@ -148,6 +150,8 @@
 
 #endif /* CONFIG_SMP */
 octeon_main_processor:
+	dla	v0, octeon_cvmseg_lines
+	sw	t2, 0(v0)
 	.set pop
 .endm
 
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 6b1f1ad0542c..0b588640b65a 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1126,6 +1126,8 @@
 #define FPU_CSR_RD	0x3	/* towards -Infinity */
 
 
+#define CAVIUM_OCTEON_SCRATCH_OFFSET (2 * 128 - 16 - 32768)
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index 92a17d67c1fa..f01af2469874 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -359,6 +359,8 @@ static inline uint32_t octeon_npi_read32(uint64_t address)
 
 extern struct cvmx_bootinfo *octeon_bootinfo;
 
+extern u32 octeon_cvmseg_lines;
+
 extern uint64_t octeon_bootloader_entry_addr;
 
 extern void (*octeon_irq_setup_secondary)(void);
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index af34afbc32d9..1a20f9c5509f 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -216,7 +216,7 @@ struct octeon_cop2_state {
 	.cp2			= {0,},
 
 struct octeon_cvmseg_state {
-	unsigned long cvmseg[CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE]
+	unsigned long cvmseg[CONFIG_CAVIUM_OCTEON_EXTRA_CVMSEG + 3]
 			    [cpu_dcache_line_size() / sizeof(unsigned long)];
 };
 
diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S
index e42113fe2762..4f56902d5ee7 100644
--- a/arch/mips/kernel/octeon_switch.S
+++ b/arch/mips/kernel/octeon_switch.S
@@ -29,7 +29,6 @@
 	cpu_save_nonscratch a0
 	LONG_S	ra, THREAD_REG31(a0)
 
-#if CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0
 	/* Check if we need to store CVMSEG state */
 	dmfc0	t0, $11,7	/* CvmMemCtl */
 	bbit0	t0, 6, 3f	/* Is user access enabled? */
@@ -58,7 +57,6 @@
 	dmfc0	t0, $11,7	/* CvmMemCtl */
 	xori	t0, t0, 0x40	/* Bit 6 is CVMSEG user enable */
 	dmtc0	t0, $11,7	/* CvmMemCtl */
-#endif
 3:
 
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 79b9f2ad3ff5..3d3dfba465ae 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -115,33 +115,17 @@ static int use_lwx_insns(void)
 		return 0;
 	}
 }
-#if defined(CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE) && \
-    CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0
-static bool scratchpad_available(void)
-{
-	return true;
-}
-static int scratchpad_offset(int i)
-{
-	/*
-	 * CVMSEG starts at address -32768 and extends for
-	 * CAVIUM_OCTEON_CVMSEG_SIZE 128 byte cache lines.
-	 */
-	i += 1; /* Kernel use starts at the top and works down. */
-	return CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE * 128 - (8 * i) - 32768;
-}
-#else
-static bool scratchpad_available(void)
-{
-	return false;
-}
+
 static int scratchpad_offset(int i)
 {
+	if (IS_ENABLED(CONFIG_CPU_CAVIUM_OCTEON))
+		return (CAVIUM_OCTEON_SCRATCH_OFFSET - (8 * i));
+
 	BUG();
 	/* Really unreachable, but evidently some GCC want this. */
 	return 0;
 }
-#endif
+
 /*
  * Found by experiment: At least some revisions of the 4kc throw under
  * some circumstances a machine check exception, triggered by invalid
@@ -1302,7 +1286,8 @@ static void build_r4000_tlb_refill_handler(void)
 	memset(relocs, 0, sizeof(relocs));
 	memset(final_handler, 0, sizeof(final_handler));
 
-	if (IS_ENABLED(CONFIG_64BIT) && (scratch_reg >= 0 || scratchpad_available()) && use_bbit_insns()) {
+	if (IS_ENABLED(CONFIG_64BIT) && use_bbit_insns() &&
+	   (scratch_reg >= 0 || IS_ENABLED(CONFIG_CPU_CAVIUM_OCTEON))) {
 		htlb_info = build_fast_tlb_refill_handler(&p, &l, &r, K0, K1,
 							  scratch_reg);
 		vmalloc_mode = refill_scratch;
diff --git a/drivers/staging/octeon/ethernet-defines.h b/drivers/staging/octeon/ethernet-defines.h
index 07bd2b87f6a0..e898df25b87f 100644
--- a/drivers/staging/octeon/ethernet-defines.h
+++ b/drivers/staging/octeon/ethernet-defines.h
@@ -32,7 +32,7 @@
 #define REUSE_SKBUFFS_WITHOUT_FREE  1
 #endif
 
-#define USE_ASYNC_IOBDMA            (CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0)
+#define USE_ASYNC_IOBDMA	1
 
 /* Maximum number of SKBs to try to free per xmit packet. */
 #define MAX_OUT_QUEUE_DEPTH 1000
-- 
2.14.3

[PATCH v7 3/4] staging: octeon: Remove USE_ASYNC_IOBDMA macro.

[David Daney]

Previous patch sets USE_ASYNC_IOBDMA to 1 unconditionally.  Remove
USE_ASYNC_IOBDMA from all if statements.  Remove dead code caused by
the change.

Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David Daney <david.daney@cavium.com>
---
 drivers/staging/octeon/ethernet-defines.h |  6 ---
 drivers/staging/octeon/ethernet-rx.c      | 25 ++++-----
 drivers/staging/octeon/ethernet-tx.c      | 85 ++++++++++---------------------
 3 files changed, 37 insertions(+), 79 deletions(-)

diff --git a/drivers/staging/octeon/ethernet-defines.h b/drivers/staging/octeon/ethernet-defines.h
index e898df25b87f..21438c804a43 100644
--- a/drivers/staging/octeon/ethernet-defines.h
+++ b/drivers/staging/octeon/ethernet-defines.h
@@ -10,10 +10,6 @@
 
 /*
  * A few defines are used to control the operation of this driver:
- *  USE_ASYNC_IOBDMA
- *      Use asynchronous IO access to hardware. This uses Octeon's asynchronous
- *      IOBDMAs to issue IO accesses without stalling. Set this to zero
- *      to disable this. Note that IOBDMAs require CVMSEG.
  *  REUSE_SKBUFFS_WITHOUT_FREE
  *      Allows the TX path to free an skbuff into the FPA hardware pool. This
  *      can significantly improve performance for forwarding and bridging, but
@@ -32,8 +28,6 @@
 #define REUSE_SKBUFFS_WITHOUT_FREE  1
 #endif
 
-#define USE_ASYNC_IOBDMA	1
-
 /* Maximum number of SKBs to try to free per xmit packet. */
 #define MAX_OUT_QUEUE_DEPTH 1000
 
diff --git a/drivers/staging/octeon/ethernet-rx.c b/drivers/staging/octeon/ethernet-rx.c
index 1a44291318ee..dd76c99d5ae0 100644
--- a/drivers/staging/octeon/ethernet-rx.c
+++ b/drivers/staging/octeon/ethernet-rx.c
@@ -201,11 +201,9 @@ static int cvm_oct_poll(struct oct_rx_group *rx_group, int budget)
 	/* Prefetch cvm_oct_device since we know we need it soon */
 	prefetch(cvm_oct_device);
 
-	if (USE_ASYNC_IOBDMA) {
-		/* Save scratch in case userspace is using it */
-		CVMX_SYNCIOBDMA;
-		old_scratch = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
-	}
+	/* Save scratch in case userspace is using it */
+	CVMX_SYNCIOBDMA;
+	old_scratch = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
 
 	/* Only allow work for our group (and preserve priorities) */
 	if (OCTEON_IS_MODEL(OCTEON_CN68XX)) {
@@ -220,10 +218,8 @@ static int cvm_oct_poll(struct oct_rx_group *rx_group, int budget)
 			       BIT(rx_group->group));
 	}
 
-	if (USE_ASYNC_IOBDMA) {
-		cvmx_pow_work_request_async(CVMX_SCR_SCRATCH, CVMX_POW_NO_WAIT);
-		did_work_request = 1;
-	}
+	cvmx_pow_work_request_async(CVMX_SCR_SCRATCH, CVMX_POW_NO_WAIT);
+	did_work_request = 1;
 
 	while (rx_count < budget) {
 		struct sk_buff *skb = NULL;
@@ -232,7 +228,7 @@ static int cvm_oct_poll(struct oct_rx_group *rx_group, int budget)
 		cvmx_wqe_t *work;
 		int port;
 
-		if (USE_ASYNC_IOBDMA && did_work_request)
+		if (did_work_request)
 			work = cvmx_pow_work_response_async(CVMX_SCR_SCRATCH);
 		else
 			work = cvmx_pow_work_request_sync(CVMX_POW_NO_WAIT);
@@ -260,7 +256,7 @@ static int cvm_oct_poll(struct oct_rx_group *rx_group, int budget)
 			sizeof(void *));
 		prefetch(pskb);
 
-		if (USE_ASYNC_IOBDMA && rx_count < (budget - 1)) {
+		if (rx_count < (budget - 1)) {
 			cvmx_pow_work_request_async_nocheck(CVMX_SCR_SCRATCH,
 							    CVMX_POW_NO_WAIT);
 			did_work_request = 1;
@@ -403,10 +399,9 @@ static int cvm_oct_poll(struct oct_rx_group *rx_group, int budget)
 		cvmx_write_csr(CVMX_POW_PP_GRP_MSKX(coreid), old_group_mask);
 	}
 
-	if (USE_ASYNC_IOBDMA) {
-		/* Restore the scratch area */
-		cvmx_scratch_write64(CVMX_SCR_SCRATCH, old_scratch);
-	}
+	/* Restore the scratch area */
+	cvmx_scratch_write64(CVMX_SCR_SCRATCH, old_scratch);
+
 	cvm_oct_rx_refill_pool(0);
 
 	return rx_count;
diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c
index 31f35025d19e..2eede0907924 100644
--- a/drivers/staging/octeon/ethernet-tx.c
+++ b/drivers/staging/octeon/ethernet-tx.c
@@ -179,23 +179,18 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 		qos = 0;
 	}
 
-	if (USE_ASYNC_IOBDMA) {
-		/* Save scratch in case userspace is using it */
-		CVMX_SYNCIOBDMA;
-		old_scratch = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
-		old_scratch2 = cvmx_scratch_read64(CVMX_SCR_SCRATCH + 8);
-
-		/*
-		 * Fetch and increment the number of packets to be
-		 * freed.
-		 */
-		cvmx_fau_async_fetch_and_add32(CVMX_SCR_SCRATCH + 8,
-					       FAU_NUM_PACKET_BUFFERS_TO_FREE,
-					       0);
-		cvmx_fau_async_fetch_and_add32(CVMX_SCR_SCRATCH,
-					       priv->fau + qos * 4,
-					       MAX_SKB_TO_FREE);
-	}
+	/* Save scratch in case userspace is using it */
+	CVMX_SYNCIOBDMA;
+	old_scratch = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
+	old_scratch2 = cvmx_scratch_read64(CVMX_SCR_SCRATCH + 8);
+
+	/* Fetch and increment the number of packets to be freed. */
+	cvmx_fau_async_fetch_and_add32(CVMX_SCR_SCRATCH + 8,
+				       FAU_NUM_PACKET_BUFFERS_TO_FREE,
+				       0);
+	cvmx_fau_async_fetch_and_add32(CVMX_SCR_SCRATCH,
+				       priv->fau + qos * 4,
+				       MAX_SKB_TO_FREE);
 
 	/*
 	 * We have space for 6 segment pointers, If there will be more
@@ -204,22 +199,11 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(skb_shinfo(skb)->nr_frags > 5)) {
 		if (unlikely(__skb_linearize(skb))) {
 			queue_type = QUEUE_DROP;
-			if (USE_ASYNC_IOBDMA) {
-				/*
-				 * Get the number of skbuffs in use
-				 * by the hardware
-				 */
-				CVMX_SYNCIOBDMA;
-				skb_to_free =
-					cvmx_scratch_read64(CVMX_SCR_SCRATCH);
-			} else {
-				/*
-				 * Get the number of skbuffs in use
-				 * by the hardware
-				 */
-				skb_to_free = cvmx_fau_fetch_and_add32(
-					priv->fau + qos * 4, MAX_SKB_TO_FREE);
-			}
+			/* Get the number of skbuffs in use by the
+			 * hardware
+			 */
+			CVMX_SYNCIOBDMA;
+			skb_to_free = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
 			skb_to_free = cvm_oct_adjust_skb_to_free(skb_to_free,
 								 priv->fau +
 								 qos * 4);
@@ -387,18 +371,10 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 		pko_command.s.ipoffp1 = skb_network_offset(skb) + 1;
 	}
 
-	if (USE_ASYNC_IOBDMA) {
-		/* Get the number of skbuffs in use by the hardware */
-		CVMX_SYNCIOBDMA;
-		skb_to_free = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
-		buffers_to_free = cvmx_scratch_read64(CVMX_SCR_SCRATCH + 8);
-	} else {
-		/* Get the number of skbuffs in use by the hardware */
-		skb_to_free = cvmx_fau_fetch_and_add32(priv->fau + qos * 4,
-						       MAX_SKB_TO_FREE);
-		buffers_to_free =
-		    cvmx_fau_fetch_and_add32(FAU_NUM_PACKET_BUFFERS_TO_FREE, 0);
-	}
+	/* Get the number of skbuffs in use by the hardware */
+	CVMX_SYNCIOBDMA;
+	skb_to_free = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
+	buffers_to_free = cvmx_scratch_read64(CVMX_SCR_SCRATCH + 8);
 
 	skb_to_free = cvm_oct_adjust_skb_to_free(skb_to_free,
 						 priv->fau + qos * 4);
@@ -416,9 +392,7 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else {
 		queue_type = QUEUE_HW;
 	}
-	if (USE_ASYNC_IOBDMA)
-		cvmx_fau_async_fetch_and_add32(
-				CVMX_SCR_SCRATCH, FAU_TOTAL_TX_TO_CLEAN, 1);
+	cvmx_fau_async_fetch_and_add32(CVMX_SCR_SCRATCH, FAU_TOTAL_TX_TO_CLEAN, 1);
 
 	spin_lock_irqsave(&priv->tx_free_list[qos].lock, flags);
 
@@ -488,16 +462,11 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 		dev_kfree_skb_any(t);
 	}
 
-	if (USE_ASYNC_IOBDMA) {
-		CVMX_SYNCIOBDMA;
-		total_to_clean = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
-		/* Restore the scratch area */
-		cvmx_scratch_write64(CVMX_SCR_SCRATCH, old_scratch);
-		cvmx_scratch_write64(CVMX_SCR_SCRATCH + 8, old_scratch2);
-	} else {
-		total_to_clean = cvmx_fau_fetch_and_add32(
-						FAU_TOTAL_TX_TO_CLEAN, 1);
-	}
+	CVMX_SYNCIOBDMA;
+	total_to_clean = cvmx_scratch_read64(CVMX_SCR_SCRATCH);
+	/* Restore the scratch area */
+	cvmx_scratch_write64(CVMX_SCR_SCRATCH, old_scratch);
+	cvmx_scratch_write64(CVMX_SCR_SCRATCH + 8, old_scratch2);
 
 	if (total_to_clean & 0x3ff) {
 		/*
-- 
2.14.3

[PATCH v7 4/4] MIPS: Octeon: Add a global resource manager.

[David Daney]

From: Carlos Munoz <cmunoz@cavium.com>

Add a global resource manager to manage tagged pointers within
bootmem allocated memory. This is used by various functional
blocks in the Octeon core like the FPA, Ethernet nexus, etc.

Signed-off-by: Carlos Munoz <cmunoz@cavium.com>
Signed-off-by: Steven J. Hill <Steven.Hill@cavium.com>
Signed-off-by: David Daney <david.daney@cavium.com>
---
 arch/mips/cavium-octeon/Makefile       |   1 +
 arch/mips/cavium-octeon/resource-mgr.c | 351 +++++++++++++++++++++++++++++++++
 arch/mips/include/asm/octeon/octeon.h  |  18 ++
 3 files changed, 370 insertions(+)
 create mode 100644 arch/mips/cavium-octeon/resource-mgr.c

diff --git a/arch/mips/cavium-octeon/Makefile b/arch/mips/cavium-octeon/Makefile
index 7c02e542959a..28c0bb75d1a4 100644
--- a/arch/mips/cavium-octeon/Makefile
+++ b/arch/mips/cavium-octeon/Makefile
@@ -10,6 +10,7 @@
 #
 
 obj-y := cpu.o setup.o octeon-platform.o octeon-irq.o csrc-octeon.o
+obj-y += resource-mgr.o
 obj-y += dma-octeon.o
 obj-y += octeon-memcpy.o
 obj-y += executive/
diff --git a/arch/mips/cavium-octeon/resource-mgr.c b/arch/mips/cavium-octeon/resource-mgr.c
new file mode 100644
index 000000000000..74efda5420ff
--- /dev/null
+++ b/arch/mips/cavium-octeon/resource-mgr.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Resource manager for Octeon.
+ *
+ * Copyright (C) 2017 Cavium, Inc.
+ */
+#include <linux/module.h>
+
+#include <asm/octeon/octeon.h>
+#include <asm/octeon/cvmx-bootmem.h>
+
+#define RESOURCE_MGR_BLOCK_NAME		"cvmx-global-resources"
+#define MAX_RESOURCES			128
+#define INST_AVAILABLE			-88
+#define OWNER				0xbadc0de
+
+struct global_resource_entry {
+	struct global_resource_tag tag;
+	u64 phys_addr;
+	u64 size;
+};
+
+struct global_resources {
+#ifdef __LITTLE_ENDIAN_BITFIELD
+	u32 rlock;
+	u32 pad;
+#else
+	u32 pad;
+	u32 rlock;
+#endif
+	u64 entry_cnt;
+	struct global_resource_entry resource_entry[];
+};
+
+static struct global_resources *res_mgr_info;
+
+
+/*
+ * The resource manager interacts with software running outside of the
+ * Linux kernel, which necessitates locking to maintain data structure
+ * consistency.  These custom locking functions implement the locking
+ * protocol, and cannot be replaced by kernel locking functions that
+ * may use different in-memory structures.
+ */
+
+static void res_mgr_lock(void)
+{
+	while (cmpxchg(&res_mgr_info->rlock, 0, 1))
+		; /* Loop while not zero */
+	rmb();
+}
+
+static void res_mgr_unlock(void)
+{
+	/* Wait until all resource operations finish before unlocking. */
+	wmb();
+	WRITE_ONCE(res_mgr_info->rlock, 0);
+	/* Force a write buffer flush. */
+	wmb();
+}
+
+static int res_mgr_find_resource(struct global_resource_tag tag)
+{
+	struct global_resource_entry *res_entry;
+	int i;
+
+	for (i = 0; i < res_mgr_info->entry_cnt; i++) {
+		res_entry = &res_mgr_info->resource_entry[i];
+		if (res_entry->tag.lo == tag.lo && res_entry->tag.hi == tag.hi)
+			return i;
+	}
+	return -1;
+}
+
+/**
+ * res_mgr_create_resource() - Create a resource.
+ * @tag: Identifies the resource.
+ * @inst_cnt: Number of resource instances to create.
+ *
+ * Returns 0 if the source was created successfully.
+ * Returns < 0 for error codes.
+ */
+int res_mgr_create_resource(struct global_resource_tag tag, int inst_cnt)
+{
+	struct global_resource_entry *res_entry;
+	u64 size;
+	u64 *res_addr;
+	int res_index, i, rc = 0;
+
+	res_mgr_lock();
+
+	/* Make sure resource doesn't already exist. */
+	res_index = res_mgr_find_resource(tag);
+	if (res_index >= 0) {
+		rc = -EEXIST;
+		goto err;
+	}
+
+	if (res_mgr_info->entry_cnt >= MAX_RESOURCES) {
+		pr_err("Resource max limit reached, not created\n");
+		rc = -ENOSPC;
+		goto err;
+	}
+
+	/*
+	 * Each instance is kept in an array of u64s. The first array element
+	 * holds the number of allocated instances.
+	 */
+	size = sizeof(u64) * (inst_cnt + 1);
+	res_addr = cvmx_bootmem_alloc_range(size, CVMX_CACHE_LINE_SIZE, 0, 0);
+	if (!res_addr) {
+		pr_err("Failed to allocate resource. not created\n");
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	/* Initialize the newly created resource. */
+	*res_addr = inst_cnt;
+	for (i = 1; i <= inst_cnt; i++)
+		res_addr[i] = INST_AVAILABLE;
+
+	res_index = res_mgr_info->entry_cnt;
+	res_entry = &res_mgr_info->resource_entry[res_index];
+	res_entry->tag = tag;
+	res_entry->phys_addr = virt_to_phys(res_addr);
+	res_entry->size = size;
+	res_mgr_info->entry_cnt++;
+
+err:
+	res_mgr_unlock();
+
+	return rc;
+}
+EXPORT_SYMBOL(res_mgr_create_resource);
+
+/**
+ * res_mgr_alloc_range() - Allocate a range of resource instances.
+ * @tag: Identifies the resource.
+ * @req_inst: Requested start of instance range to allocate.
+ *	      Range instances are guaranteed to be sequential
+ *	      (-1 for don't care).
+ * @req_cnt: Number of instances to allocate.
+ * @use_last_avail: Set to request the last available instance.
+ * @inst: Updated with the allocated instances.
+ *
+ * Returns 0 if the source was created successfully.
+ * Returns < 0 for error codes.
+ */
+int res_mgr_alloc_range(struct global_resource_tag tag, int req_inst,
+			int req_cnt, bool use_last_avail, int *inst)
+{
+	struct global_resource_entry *res_entry;
+	int res_index;
+	u64 *res_addr;
+	u64 inst_cnt;
+	int alloc_cnt, i, rc = -ENOENT;
+
+	/* Start with no instances allocated. */
+	for (i = 0; i < req_cnt; i++)
+		inst[i] = INST_AVAILABLE;
+
+	res_mgr_lock();
+
+	/* Find the resource. */
+	res_index = res_mgr_find_resource(tag);
+	if (res_index < 0) {
+		pr_err("Resource not found, can't allocate instance\n");
+		goto err;
+	}
+
+	/* Get resource data. */
+	res_entry = &res_mgr_info->resource_entry[res_index];
+	res_addr = phys_to_virt(res_entry->phys_addr);
+	inst_cnt = *res_addr;
+
+	/* Allocate the requested instances. */
+	if (req_inst >= 0) {
+		/* Specific instance range requested. */
+		if (req_inst + req_cnt >= inst_cnt) {
+			pr_err("Requested instance out of range\n");
+			goto err;
+		}
+
+		for (i = 0; i < req_cnt; i++) {
+			if (*(res_addr + req_inst + 1 + i) == INST_AVAILABLE) {
+				inst[i] = req_inst + i;
+			} else {
+				inst[0] = INST_AVAILABLE;
+				break;
+			}
+		}
+	} else if (use_last_avail) {
+		/* Last available instance requested. */
+		alloc_cnt = 0;
+		for (i = inst_cnt; i > 0; i--) {
+			if (*(res_addr + i) == INST_AVAILABLE) {
+				/*
+				 * Instance off by 1 (first element holds the
+				 * count).
+				 */
+				inst[alloc_cnt] = i - 1;
+
+				alloc_cnt++;
+				if (alloc_cnt == req_cnt)
+					break;
+			}
+		}
+
+		if (i == 0)
+			inst[0] = INST_AVAILABLE;
+	} else {
+		/* Next available instance requested. */
+		alloc_cnt = 0;
+		for (i = 1; i <= inst_cnt; i++) {
+			if (*(res_addr + i) == INST_AVAILABLE) {
+				/*
+				 * Instance off by 1 (first element holds the
+				 * count).
+				 */
+				inst[alloc_cnt] = i - 1;
+
+				alloc_cnt++;
+				if (alloc_cnt == req_cnt)
+					break;
+			}
+		}
+
+		if (i > inst_cnt)
+			inst[0] = INST_AVAILABLE;
+	}
+
+	if (inst[0] != INST_AVAILABLE) {
+		for (i = 0; i < req_cnt; i++)
+			*(res_addr + inst[i] + 1) = OWNER;
+		rc = 0;
+	}
+
+err:
+	res_mgr_unlock();
+
+	return rc;
+}
+EXPORT_SYMBOL(res_mgr_alloc_range);
+
+/**
+ * res_mgr_alloc() - Allocate a resource instance.
+ * @tag: Identifies the resource.
+ * @req_inst: Requested instance to allocate (-1 for don't care).
+ * @use_last_avail: Set to request the last available instance.
+ *
+ * Returns: Allocated resource instance if successful.
+ * Returns <0 for error codes.
+ */
+int res_mgr_alloc(struct global_resource_tag tag, int req_inst,
+		  bool use_last_avail)
+{
+	int inst, rc;
+
+	rc = res_mgr_alloc_range(tag, req_inst, 1, use_last_avail, &inst);
+	if (!rc)
+		return inst;
+	return rc;
+}
+EXPORT_SYMBOL(res_mgr_alloc);
+
+/**
+ * res_mgr_free_range() - Free a resource instance range.
+ * @tag: Identifies the resource.
+ * @inst: Requested instance to free.
+ * @req_cnt: Number of instances to free.
+ */
+void res_mgr_free_range(struct global_resource_tag tag, const int *inst,
+			int req_cnt)
+{
+	struct global_resource_entry *res_entry;
+	int res_index, i;
+	u64 *res_addr;
+
+	res_mgr_lock();
+
+	/* Find the resource. */
+	res_index = res_mgr_find_resource(tag);
+	if (res_index < 0) {
+		pr_err("Resource not found, can't free instance\n");
+		goto err;
+	}
+
+	/* Get the resource data. */
+	res_entry = &res_mgr_info->resource_entry[res_index];
+	res_addr = phys_to_virt(res_entry->phys_addr);
+
+	/* Free the resource instances. */
+	for (i = 0; i < req_cnt; i++) {
+		/* Instance off by 1 (first element holds the count). */
+		*(res_addr + inst[i] + 1) = INST_AVAILABLE;
+	}
+
+err:
+	res_mgr_unlock();
+}
+EXPORT_SYMBOL(res_mgr_free_range);
+
+/**
+ * res_mgr_free() - Free a resource instance.
+ * @tag: Identifies the resource.
+ * @req_inst: Requested instance to free.
+ */
+void res_mgr_free(struct global_resource_tag tag, int inst)
+{
+	res_mgr_free_range(tag, &inst, 1);
+}
+EXPORT_SYMBOL(res_mgr_free);
+
+static int __init res_mgr_init(void)
+{
+	struct cvmx_bootmem_named_block_desc *block;
+	int block_size;
+	u64 addr;
+
+	cvmx_bootmem_lock();
+
+	/* Search for the resource manager data in boot memory. */
+	block = cvmx_bootmem_phy_named_block_find(RESOURCE_MGR_BLOCK_NAME,
+						  CVMX_BOOTMEM_FLAG_NO_LOCKING);
+	if (block) {
+		/* Found. */
+		res_mgr_info = phys_to_virt(block->base_addr);
+	} else {
+		/* Create it. */
+		block_size = sizeof(struct global_resources) +
+			sizeof(struct global_resource_entry) * MAX_RESOURCES;
+		addr = cvmx_bootmem_phy_named_block_alloc(block_size, 0, 0,
+				CVMX_CACHE_LINE_SIZE, RESOURCE_MGR_BLOCK_NAME,
+				CVMX_BOOTMEM_FLAG_NO_LOCKING);
+		if (!addr) {
+			pr_err("Failed to allocate name block %s\n",
+			       RESOURCE_MGR_BLOCK_NAME);
+		} else {
+			res_mgr_info = phys_to_virt(addr);
+			memset(res_mgr_info, 0, block_size);
+		}
+	}
+
+	cvmx_bootmem_unlock();
+
+	return 0;
+}
+device_initcall(res_mgr_init);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Cavium, Inc. Octeon resource manager");
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index f01af2469874..4dafeaf262b5 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -346,6 +346,24 @@ void octeon_mult_restore3_end(void);
 void octeon_mult_restore2(void);
 void octeon_mult_restore2_end(void);
 
+/*
+ * This definition must be kept in sync with the one in
+ * cvmx-global-resources.c
+ */
+struct global_resource_tag {
+	uint64_t lo;
+	uint64_t hi;
+};
+
+void res_mgr_free(struct global_resource_tag tag, int inst);
+void res_mgr_free_range(struct global_resource_tag tag, const int *inst,
+			int req_cnt);
+int res_mgr_alloc(struct global_resource_tag tag, int req_inst,
+		  bool use_last_avail);
+int res_mgr_alloc_range(struct global_resource_tag tag, int req_inst,
+			int req_cnt, bool use_last_avail, int *inst);
+int res_mgr_create_resource(struct global_resource_tag tag, int inst_cnt);
+
 /**
  * Read a 32bit value from the Octeon NPI register space
  *
-- 
2.14.3