MIPS: Consistently declare TLB functions

Since at least the beginning of the git era we've declared our TLB
exception handling functions inconsistently. They're actually functions,
but we declare them as arrays of u32 where each u32 is an encoded
instruction. This has always been the case for arch/mips/mm/tlbex.c, and
has also been true for arch/mips/kernel/traps.c since commit
86a1708a9d54 ("MIPS: Make tlb exception handler definitions and
declarations match.") which aimed for consistency but did so by
consistently making the our C code inconsistent with our assembly.

This is all usually harmless, but when using GCC 7 or newer to build a
kernel targeting microMIPS (ie. CONFIG_CPU_MICROMIPS=y) it becomes
problematic. With microMIPS bit 0 of the program counter indicates the
ISA mode. When bit 0 is zero instructions are decoded using the standard
MIPS32 or MIPS64 ISA. When bit 0 is one instructions are decoded using
microMIPS. This means that function pointers become odd - their least
significant bit is one for microMIPS code. We work around this in cases
where we need to access code using loads & stores with our
msk_isa16_mode() macro which simply clears bit 0 of the value it is
given:

  #define msk_isa16_mode(x) ((x) & ~0x1)

For example we do this for our TLB load handler in
build_r4000_tlb_load_handler():

  u32 *p = (u32 *)msk_isa16_mode((ulong)handle_tlbl);

We then write code to p, expecting it to be suitably aligned (our LEAF
macro aligns functions on 4 byte boundaries, so (ulong)handle_tlbl will
give a value one greater than a multiple of 4 - ie. the start of a
function on a 4 byte boundary, with the ISA mode bit 0 set).

This worked fine up to GCC 6, but GCC 7 & onwards is smart enough to
presume that handle_tlbl which we declared as an array of u32s must be
aligned sufficiently that bit 0 of its address will never be set, and as
a result optimize out msk_isa16_mode(). This leads to p having an
address with bit 0 set, and when we go on to attempt to store code at
that address we take an address error exception due to the unaligned
memory access.

This leads to an exception prior to the kernel having configured its own
exception handlers, so we jump to whatever handlers the bootloader
configured. In the case of QEMU this results in a silent hang, since it
has no useful general exception vector.

Fix this by consistently declaring our TLB-related functions as
functions. For handle_tlbl(), handle_tlbs() & handle_tlbm() we do this
in asm/tlbex.h & we make use of the existing declaration of
tlbmiss_handler_setup_pgd() in asm/mmu_context.h. Our TLB handler
generation code in arch/mips/mm/tlbex.c is adjusted to deal with these
definitions, in most cases simply by casting the function pointers to
u32 pointers.

This allows us to include asm/mmu_context.h in arch/mips/mm/tlbex.c to
get the definitions of tlbmiss_handler_setup_pgd & pgd_current, removing
some needless duplication. Consistently using msk_isa16_mode() on
function pointers means we no longer need the
tlbmiss_handler_setup_pgd_start symbol so that is removed entirely.

Now that we're declaring our functions as functions GCC stops optimizing
out msk_isa16_mode() & a microMIPS kernel built with either GCC 7.3.0 or
8.1.0 boots successfully.

Signed-off-by: Paul Burton <paul.burton@mips.com>

2 files changed, 40 insertions, 61 deletions

diff --git a/arch/mips/mm/tlb-funcs.S b/arch/mips/mm/tlb-funcs.S
index ae34361b6060..00fef578c8cd 100644
--- a/arch/mips/mm/tlb-funcs.S
+++ b/arch/mips/mm/tlb-funcs.S
@@ -17,7 +17,6 @@
 
 #define FASTPATH_SIZE	128
 
-EXPORT(tlbmiss_handler_setup_pgd_start)
 LEAF(tlbmiss_handler_setup_pgd)
 1:	j	1b		/* Dummy, will be replaced. */
 	.space	64
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 2223620fb573..067714291643 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -31,6 +31,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/cpu-type.h>
+#include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/war.h>
 #include <asm/uasm.h>
@@ -253,8 +254,10 @@ static void output_pgtable_bits_defines(void)
 	pr_debug("\n");
 }
 
-static inline void dump_handler(const char *symbol, const u32 *handler, int count)
+static inline void dump_handler(const char *symbol, const void *start, const void *end)
 {
+	unsigned int count = (end - start) / sizeof(u32);
+	const u32 *handler = start;
 	int i;
 
 	pr_debug("LEAF(%s)\n", symbol);
@@ -402,12 +405,6 @@ static void build_restore_work_registers(u32 **p)
  * CONFIG_MIPS_PGD_C0_CONTEXT implies 64 bit and lack of pgd_current,
  * we cannot do r3000 under these circumstances.
  *
- * Declare pgd_current here instead of including mmu_context.h to avoid type
- * conflicts for tlbmiss_handler_setup_pgd
- */
-extern unsigned long pgd_current[];
-
-/*
  * The R3000 TLB handler is simple.
  */
 static void build_r3000_tlb_refill_handler(void)
@@ -444,8 +441,7 @@ static void build_r3000_tlb_refill_handler(void)
 
 	memcpy((void *)ebase, tlb_handler, 0x80);
 	local_flush_icache_range(ebase, ebase + 0x80);
-
-	dump_handler("r3000_tlb_refill", (u32 *)ebase, 32);
+	dump_handler("r3000_tlb_refill", (u32 *)ebase, (u32 *)(ebase + 0x80));
 }
 #endif /* CONFIG_MIPS_PGD_C0_CONTEXT */
 
@@ -1465,8 +1461,7 @@ static void build_r4000_tlb_refill_handler(void)
 
 	memcpy((void *)ebase, final_handler, 0x100);
 	local_flush_icache_range(ebase, ebase + 0x100);
-
-	dump_handler("r4000_tlb_refill", (u32 *)ebase, 64);
+	dump_handler("r4000_tlb_refill", (u32 *)ebase, (u32 *)(ebase + 0x100));
 }
 
 static void setup_pw(void)
@@ -1568,30 +1563,21 @@ static void build_loongson3_tlb_refill_handler(void)
 	uasm_resolve_relocs(relocs, labels);
 	memcpy((void *)(ebase + 0x80), tlb_handler, 0x80);
 	local_flush_icache_range(ebase + 0x80, ebase + 0x100);
-	dump_handler("loongson3_tlb_refill", (u32 *)(ebase + 0x80), 32);
+	dump_handler("loongson3_tlb_refill",
+		     (u32 *)(ebase + 0x80), (u32 *)(ebase + 0x100));
 }
 
-extern u32 handle_tlbl[], handle_tlbl_end[];
-extern u32 handle_tlbs[], handle_tlbs_end[];
-extern u32 handle_tlbm[], handle_tlbm_end[];
-extern u32 tlbmiss_handler_setup_pgd_start[];
-extern u32 tlbmiss_handler_setup_pgd[];
-extern u32 tlbmiss_handler_setup_pgd_end[];
-
 static void build_setup_pgd(void)
 {
 	const int a0 = 4;
 	const int __maybe_unused a1 = 5;
 	const int __maybe_unused a2 = 6;
-	u32 *p = tlbmiss_handler_setup_pgd_start;
-	const int tlbmiss_handler_setup_pgd_size =
-		tlbmiss_handler_setup_pgd_end - tlbmiss_handler_setup_pgd_start;
+	u32 *p = (u32 *)msk_isa16_mode((ulong)tlbmiss_handler_setup_pgd);
 #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
 	long pgdc = (long)pgd_current;
 #endif
 
-	memset(tlbmiss_handler_setup_pgd, 0, tlbmiss_handler_setup_pgd_size *
-					sizeof(tlbmiss_handler_setup_pgd[0]));
+	memset(p, 0, tlbmiss_handler_setup_pgd_end - (char *)p);
 	memset(labels, 0, sizeof(labels));
 	memset(relocs, 0, sizeof(relocs));
 	pgd_reg = allocate_kscratch();
@@ -1644,15 +1630,15 @@ static void build_setup_pgd(void)
 	else
 		uasm_i_nop(&p);
 #endif
-	if (p >= tlbmiss_handler_setup_pgd_end)
+	if (p >= (u32 *)tlbmiss_handler_setup_pgd_end)
 		panic("tlbmiss_handler_setup_pgd space exceeded");
 
 	uasm_resolve_relocs(relocs, labels);
 	pr_debug("Wrote tlbmiss_handler_setup_pgd (%u instructions).\n",
-		 (unsigned int)(p - tlbmiss_handler_setup_pgd));
+		 (unsigned int)(p - (u32 *)tlbmiss_handler_setup_pgd));
 
 	dump_handler("tlbmiss_handler", tlbmiss_handler_setup_pgd,
-					tlbmiss_handler_setup_pgd_size);
+					tlbmiss_handler_setup_pgd_end);
 }
 
 static void
@@ -1921,12 +1907,11 @@ build_r3000_tlbchange_handler_head(u32 **p, unsigned int pte,
 
 static void build_r3000_tlb_load_handler(void)
 {
-	u32 *p = handle_tlbl;
-	const int handle_tlbl_size = handle_tlbl_end - handle_tlbl;
+	u32 *p = (u32 *)handle_tlbl;
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 
-	memset(handle_tlbl, 0, handle_tlbl_size * sizeof(handle_tlbl[0]));
+	memset(p, 0, handle_tlbl_end - (char *)p);
 	memset(labels, 0, sizeof(labels));
 	memset(relocs, 0, sizeof(relocs));
 
@@ -1940,24 +1925,23 @@ static void build_r3000_tlb_load_handler(void)
 	uasm_i_j(&p, (unsigned long)tlb_do_page_fault_0 & 0x0fffffff);
 	uasm_i_nop(&p);
 
-	if (p >= handle_tlbl_end)
+	if (p >= (u32 *)handle_tlbl_end)
 		panic("TLB load handler fastpath space exceeded");
 
 	uasm_resolve_relocs(relocs, labels);
 	pr_debug("Wrote TLB load handler fastpath (%u instructions).\n",
-		 (unsigned int)(p - handle_tlbl));
+		 (unsigned int)(p - (u32 *)handle_tlbl));
 
-	dump_handler("r3000_tlb_load", handle_tlbl, handle_tlbl_size);
+	dump_handler("r3000_tlb_load", handle_tlbl, handle_tlbl_end);
 }
 
 static void build_r3000_tlb_store_handler(void)
 {
-	u32 *p = handle_tlbs;
-	const int handle_tlbs_size = handle_tlbs_end - handle_tlbs;
+	u32 *p = (u32 *)handle_tlbs;
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 
-	memset(handle_tlbs, 0, handle_tlbs_size * sizeof(handle_tlbs[0]));
+	memset(p, 0, handle_tlbs_end - (char *)p);
 	memset(labels, 0, sizeof(labels));
 	memset(relocs, 0, sizeof(relocs));
 
@@ -1971,24 +1955,23 @@ static void build_r3000_tlb_store_handler(void)
 	uasm_i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff);
 	uasm_i_nop(&p);
 
-	if (p >= handle_tlbs_end)
+	if (p >= (u32 *)handle_tlbs_end)
 		panic("TLB store handler fastpath space exceeded");
 
 	uasm_resolve_relocs(relocs, labels);
 	pr_debug("Wrote TLB store handler fastpath (%u instructions).\n",
-		 (unsigned int)(p - handle_tlbs));
+		 (unsigned int)(p - (u32 *)handle_tlbs));
 
-	dump_handler("r3000_tlb_store", handle_tlbs, handle_tlbs_size);
+	dump_handler("r3000_tlb_store", handle_tlbs, handle_tlbs_end);
 }
 
 static void build_r3000_tlb_modify_handler(void)
 {
-	u32 *p = handle_tlbm;
-	const int handle_tlbm_size = handle_tlbm_end - handle_tlbm;
+	u32 *p = (u32 *)handle_tlbm;
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 
-	memset(handle_tlbm, 0, handle_tlbm_size * sizeof(handle_tlbm[0]));
+	memset(p, 0, handle_tlbm_end - (char *)p);
 	memset(labels, 0, sizeof(labels));
 	memset(relocs, 0, sizeof(relocs));
 
@@ -2002,14 +1985,14 @@ static void build_r3000_tlb_modify_handler(void)
 	uasm_i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff);
 	uasm_i_nop(&p);
 
-	if (p >= handle_tlbm_end)
+	if (p >= (u32 *)handle_tlbm_end)
 		panic("TLB modify handler fastpath space exceeded");
 
 	uasm_resolve_relocs(relocs, labels);
 	pr_debug("Wrote TLB modify handler fastpath (%u instructions).\n",
-		 (unsigned int)(p - handle_tlbm));
+		 (unsigned int)(p - (u32 *)handle_tlbm));
 
-	dump_handler("r3000_tlb_modify", handle_tlbm, handle_tlbm_size);
+	dump_handler("r3000_tlb_modify", handle_tlbm, handle_tlbm_end);
 }
 #endif /* CONFIG_MIPS_PGD_C0_CONTEXT */
 
@@ -2101,12 +2084,11 @@ build_r4000_tlbchange_handler_tail(u32 **p, struct uasm_label **l,
 static void build_r4000_tlb_load_handler(void)
 {
 	u32 *p = (u32 *)msk_isa16_mode((ulong)handle_tlbl);
-	const int handle_tlbl_size = handle_tlbl_end - handle_tlbl;
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 	struct work_registers wr;
 
-	memset(handle_tlbl, 0, handle_tlbl_size * sizeof(handle_tlbl[0]));
+	memset(p, 0, handle_tlbl_end - (char *)p);
 	memset(labels, 0, sizeof(labels));
 	memset(relocs, 0, sizeof(relocs));
 
@@ -2287,25 +2269,24 @@ static void build_r4000_tlb_load_handler(void)
 	uasm_i_j(&p, (unsigned long)tlb_do_page_fault_0 & 0x0fffffff);
 	uasm_i_nop(&p);
 
-	if (p >= handle_tlbl_end)
+	if (p >= (u32 *)handle_tlbl_end)
 		panic("TLB load handler fastpath space exceeded");
 
 	uasm_resolve_relocs(relocs, labels);
 	pr_debug("Wrote TLB load handler fastpath (%u instructions).\n",
-		 (unsigned int)(p - handle_tlbl));
+		 (unsigned int)(p - (u32 *)handle_tlbl));
 
-	dump_handler("r4000_tlb_load", handle_tlbl, handle_tlbl_size);
+	dump_handler("r4000_tlb_load", handle_tlbl, handle_tlbl_end);
 }
 
 static void build_r4000_tlb_store_handler(void)
 {
 	u32 *p = (u32 *)msk_isa16_mode((ulong)handle_tlbs);
-	const int handle_tlbs_size = handle_tlbs_end - handle_tlbs;
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 	struct work_registers wr;
 
-	memset(handle_tlbs, 0, handle_tlbs_size * sizeof(handle_tlbs[0]));
+	memset(p, 0, handle_tlbs_end - (char *)p);
 	memset(labels, 0, sizeof(labels));
 	memset(relocs, 0, sizeof(relocs));
 
@@ -2342,25 +2323,24 @@ static void build_r4000_tlb_store_handler(void)
 	uasm_i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff);
 	uasm_i_nop(&p);
 
-	if (p >= handle_tlbs_end)
+	if (p >= (u32 *)handle_tlbs_end)
 		panic("TLB store handler fastpath space exceeded");
 
 	uasm_resolve_relocs(relocs, labels);
 	pr_debug("Wrote TLB store handler fastpath (%u instructions).\n",
-		 (unsigned int)(p - handle_tlbs));
+		 (unsigned int)(p - (u32 *)handle_tlbs));
 
-	dump_handler("r4000_tlb_store", handle_tlbs, handle_tlbs_size);
+	dump_handler("r4000_tlb_store", handle_tlbs, handle_tlbs_end);
 }
 
 static void build_r4000_tlb_modify_handler(void)
 {
 	u32 *p = (u32 *)msk_isa16_mode((ulong)handle_tlbm);
-	const int handle_tlbm_size = handle_tlbm_end - handle_tlbm;
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 	struct work_registers wr;
 
-	memset(handle_tlbm, 0, handle_tlbm_size * sizeof(handle_tlbm[0]));
+	memset(p, 0, handle_tlbm_end - (char *)p);
 	memset(labels, 0, sizeof(labels));
 	memset(relocs, 0, sizeof(relocs));
 
@@ -2398,14 +2378,14 @@ static void build_r4000_tlb_modify_handler(void)
 	uasm_i_j(&p, (unsigned long)tlb_do_page_fault_1 & 0x0fffffff);
 	uasm_i_nop(&p);
 
-	if (p >= handle_tlbm_end)
+	if (p >= (u32 *)handle_tlbm_end)
 		panic("TLB modify handler fastpath space exceeded");
 
 	uasm_resolve_relocs(relocs, labels);
 	pr_debug("Wrote TLB modify handler fastpath (%u instructions).\n",
-		 (unsigned int)(p - handle_tlbm));
+		 (unsigned int)(p - (u32 *)handle_tlbm));
 
-	dump_handler("r4000_tlb_modify", handle_tlbm, handle_tlbm_size);
+	dump_handler("r4000_tlb_modify", handle_tlbm, handle_tlbm_end);
 }
 
 static void flush_tlb_handlers(void)