Merge tag 'mips_4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux

Pull MIPS updates from Paul Burton:
 "Here's the main MIPS pull for Linux 4.21. Core architecture changes
  include:

   - Syscall tables & definitions for unistd.h are now generated by
     scripts, providing greater consistency with other architectures &
     making it easier to add new syscalls.

   - Support for building kernels with no floating point support, upon
     which any userland attempting to use floating point instructions
     will receive a SIGILL. Mostly useful to shrink the kernel & as
     preparation for nanoMIPS support which does not yet include FP.

   - MIPS SIMD Architecture (MSA) vector register context is now exposed
     by ptrace via a new NT_MIPS_MSA regset.

   - ASIDs are now stored as 64b values even for MIPS32 kernels,
     expanding the ASID version field sufficiently that we don't need to
     worry about overflow & avoiding rare issues with reused ASIDs that
     have been observed in the wild.

   - The branch delay slot "emulation" page is now mapped without write
     permission for the user, preventing its use as a nice location for
     attacks to execute malicious code from.

   - Support for ioremap_prot(), primarily to allow gdb or other ptrace
     users the ability to view their tracee's memory using the same
     cache coherency attribute.

   - Optimizations to more cpu_has_* macros, allowing more to be
     compile-time constant where possible.

   - Enable building the whole kernel with UBSAN instrumentation.

   - Enable building the kernel with link-time dead code & data
     elimination.

  Platform specific changes include:

   - The Boston board gains a workaround for DMA prefetching issues with
     the EG20T Platform Controller Hub that it uses.

   - Cleanups to Cavium Octeon code removing about 20k lines of
     redundant code, mostly unused or duplicate register definitions in
     headers.

   - defconfig updates for the DECstation machines, including new
     defconfigs for r4k & 64b machines.

   - Further work on Loongson 3 support.

   - DMA fixes for SiByte machines"

* tag 'mips_4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux: (95 commits)
  MIPS: math-emu: Write-protect delay slot emulation pages
  MIPS: Remove struct mm_context_t fp_mode_switching field
  mips: generate uapi header and system call table files
  mips: add system call table generation support
  mips: remove syscall table entries
  mips: add +1 to __NR_syscalls in uapi header
  mips: rename scall64-64.S to scall64-n64.S
  mips: remove unused macros
  mips: add __NR_syscalls along with __NR_Linux_syscalls
  MIPS: Expand MIPS32 ASIDs to 64 bits
  MIPS: OCTEON: delete redundant register definitions
  MIPS: OCTEON: cvmx_gmxx_inf_mode: use oldest forward compatible definition
  MIPS: OCTEON: cvmx_mio_fus_dat3: use oldest forward compatible definition
  MIPS: OCTEON: cvmx_pko_mem_debug8: use oldest forward compatible definition
  MIPS: OCTEON: octeon-usb: use common gpio_bit definition
  MIPS: OCTEON: enable all OCTEON drivers in defconfig
  mips: annotate implicit fall throughs
  MIPS: Hardcode cpu_has_mips* where target ISA allows
  MIPS: MT: Remove norps command line parameter
  MIPS: Only include mmzone.h when CONFIG_NEED_MULTIPLE_NODES=y
  ...

3 files changed, 42 insertions, 9 deletions

diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c
index 3466fcdae0ca..01848cdf2074 100644
--- a/arch/mips/mm/c-r3k.c
+++ b/arch/mips/mm/c-r3k.c
@@ -245,7 +245,7 @@ static void r3k_flush_cache_page(struct vm_area_struct *vma,
 	pmd_t *pmdp;
 	pte_t *ptep;
 
-	pr_debug("cpage[%08lx,%08lx]\n",
+	pr_debug("cpage[%08llx,%08lx]\n",
 		 cpu_context(smp_processor_id(), mm), addr);
 
 	/* No ASID => no such page in the cache.  */
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 05bd77727fb9..d0b64df51eb2 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -459,11 +459,28 @@ static void r4k_blast_scache_setup(void)
 		r4k_blast_scache = blast_scache128;
 }
 
+static void (*r4k_blast_scache_node)(long node);
+
+static void r4k_blast_scache_node_setup(void)
+{
+	unsigned long sc_lsize = cpu_scache_line_size();
+
+	if (current_cpu_type() != CPU_LOONGSON3)
+		r4k_blast_scache_node = (void *)cache_noop;
+	else if (sc_lsize == 16)
+		r4k_blast_scache_node = blast_scache16_node;
+	else if (sc_lsize == 32)
+		r4k_blast_scache_node = blast_scache32_node;
+	else if (sc_lsize == 64)
+		r4k_blast_scache_node = blast_scache64_node;
+	else if (sc_lsize == 128)
+		r4k_blast_scache_node = blast_scache128_node;
+}
+
 static inline void local_r4k___flush_cache_all(void * args)
 {
 	switch (current_cpu_type()) {
 	case CPU_LOONGSON2:
-	case CPU_LOONGSON3:
 	case CPU_R4000SC:
 	case CPU_R4000MC:
 	case CPU_R4400SC:
@@ -480,6 +497,11 @@ static inline void local_r4k___flush_cache_all(void * args)
 		r4k_blast_scache();
 		break;
 
+	case CPU_LOONGSON3:
+		/* Use get_ebase_cpunum() for both NUMA=y/n */
+		r4k_blast_scache_node(get_ebase_cpunum() >> 2);
+		break;
+
 	case CPU_BMIPS5000:
 		r4k_blast_scache();
 		__sync();
@@ -840,10 +862,14 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
-		if (size >= scache_size)
-			r4k_blast_scache();
-		else
+		if (size >= scache_size) {
+			if (current_cpu_type() != CPU_LOONGSON3)
+				r4k_blast_scache();
+			else
+				r4k_blast_scache_node(pa_to_nid(addr));
+		} else {
 			blast_scache_range(addr, addr + size);
+		}
 		preempt_enable();
 		__sync();
 		return;
@@ -877,9 +903,12 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
-		if (size >= scache_size)
-			r4k_blast_scache();
-		else {
+		if (size >= scache_size) {
+			if (current_cpu_type() != CPU_LOONGSON3)
+				r4k_blast_scache();
+			else
+				r4k_blast_scache_node(pa_to_nid(addr));
+		} else {
 			/*
 			 * There is no clearly documented alignment requirement
 			 * for the cache instruction on MIPS processors and
@@ -1251,6 +1280,7 @@ static void probe_pcache(void)
 
 	case CPU_VR4133:
 		write_c0_config(config & ~VR41_CONF_P4K);
+		/* fall through */
 	case CPU_VR4131:
 		/* Workaround for cache instruction bug of VR4131 */
 		if (c->processor_id == 0x0c80U || c->processor_id == 0x0c81U ||
@@ -1352,7 +1382,7 @@ static void probe_pcache(void)
 					  c->dcache.ways *
 					  c->dcache.linesz;
 		c->dcache.waybit = 0;
-		if ((prid & PRID_REV_MASK) >= PRID_REV_LOONGSON3A_R2)
+		if ((prid & PRID_REV_MASK) >= PRID_REV_LOONGSON3A_R2_0)
 			c->options |= MIPS_CPU_PREFETCH;
 		break;
 
@@ -1498,6 +1528,7 @@ static void probe_pcache(void)
 			c->dcache.flags |= MIPS_CACHE_PINDEX;
 			break;
 		}
+		/* fall through */
 	default:
 		if (has_74k_erratum || c->dcache.waysize > PAGE_SIZE)
 			c->dcache.flags |= MIPS_CACHE_ALIASES;
@@ -1918,6 +1949,7 @@ void r4k_cache_init(void)
 	r4k_blast_scache_page_setup();
 	r4k_blast_scache_page_indexed_setup();
 	r4k_blast_scache_setup();
+	r4k_blast_scache_node_setup();
 #ifdef CONFIG_EVA
 	r4k_blast_dcache_user_page_setup();
 	r4k_blast_icache_user_page_setup();
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 067714291643..37b1cb246332 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -576,6 +576,7 @@ void build_tlb_write_entry(u32 **p, struct uasm_label **l,
 	case CPU_R5500:
 		if (m4kc_tlbp_war())
 			uasm_i_nop(p);
+		/* fall through */
 	case CPU_ALCHEMY:
 		tlbw(p);
 		break;