From 1f9b8936f36f4a8e1d9923f5d03295d668cdf098 Mon Sep 17 00:00:00 2001
From: Julien Thierry <julien.thierry@arm.com>
Date: Fri, 4 Aug 2017 09:31:42 +0100
Subject: arm64: Decode information from ESR upon mem faults

When receiving unhandled faults from the CPU, description is very sparse.
Adding information about faults decoded from ESR.

Added defines to esr.h corresponding ESR fields. Values are based on ARM
Archtecture Reference Manual (DDI 0487B.a), section D7.2.28 ESR_ELx, Exception
Syndrome Register (ELx) (pages D7-2275 to D7-2280).

New output is of the form:
[   77.818059] Mem abort info:
[   77.820826]   Exception class = DABT (current EL), IL = 32 bits
[   77.826706]   SET = 0, FnV = 0
[   77.829742]   EA = 0, S1PTW = 0
[   77.832849] Data abort info:
[   77.835713]   ISV = 0, ISS = 0x00000070
[   77.839522]   CM = 0, WnR = 1

Signed-off-by: Julien Thierry <julien.thierry@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
[catalin.marinas@arm.com: fix "%lu" in a pr_alert() call]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/fault.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2509e4fe6992..52ee273afeec 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -82,6 +82,49 @@ static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
 }
 #endif
 
+static void data_abort_decode(unsigned int esr)
+{
+	pr_alert("Data abort info:\n");
+
+	if (esr & ESR_ELx_ISV) {
+		pr_alert("  Access size = %u byte(s)\n",
+			 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT));
+		pr_alert("  SSE = %lu, SRT = %lu\n",
+			 (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT,
+			 (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT);
+		pr_alert("  SF = %lu, AR = %lu\n",
+			 (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT,
+			 (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT);
+	} else {
+		pr_alert("  ISV = 0, ISS = 0x%08lu\n", esr & ESR_ELx_ISS_MASK);
+	}
+
+	pr_alert("  CM = %lu, WnR = %lu\n",
+		 (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT,
+		 (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT);
+}
+
+/*
+ * Decode mem abort information
+ */
+static void mem_abort_decode(unsigned int esr)
+{
+	pr_alert("Mem abort info:\n");
+
+	pr_alert("  Exception class = %s, IL = %u bits\n",
+		 esr_get_class_string(esr),
+		 (esr & ESR_ELx_IL) ? 32 : 16);
+	pr_alert("  SET = %lu, FnV = %lu\n",
+		 (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT,
+		 (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT);
+	pr_alert("  EA = %lu, S1PTW = %lu\n",
+		 (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT,
+		 (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT);
+
+	if (esr_is_data_abort(esr))
+		data_abort_decode(esr);
+}
+
 /*
  * Dump out the page tables associated with 'addr' in the currently active mm.
  */
@@ -248,6 +291,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	pr_alert("Unable to handle kernel %s at virtual address %08lx\n", msg,
 		 addr);
 
+	mem_abort_decode(esr);
+
 	show_pte(addr);
 	die("Oops", regs, esr);
 	bust_spinlocks(0);
@@ -702,6 +747,8 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 	pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
 		 inf->name, esr, addr);
 
+	mem_abort_decode(esr);
+
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
 	info.si_code  = inf->code;
-- 
cgit v1.2.3-59-g8ed1b


From d46befef4c03fb61a62b3319ff5265aaac7bc465 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 25 Jul 2017 11:55:39 +0100
Subject: arm64: Convert __inval_cache_range() to area-based

__inval_cache_range() is already the odd one out among our data cache
maintenance routines as the only remaining range-based one; as we're
going to want an invalidation routine to call from C code for the pmem
API, let's tweak the prototype and name to bring it in line with the
clean operations, and to make its relationship with __dma_inv_area()
neatly mirror that of __clean_dcache_area_poc() and __dma_clean_area().
The loop clearing the early page tables gets mildly massaged in the
process for the sake of consistency.

Reviewed-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/cacheflush.h |  1 +
 arch/arm64/kernel/head.S            | 18 +++++++++---------
 arch/arm64/mm/cache.S               | 23 ++++++++++++++---------
 3 files changed, 24 insertions(+), 18 deletions(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 4d4f650c290e..b4b43a94dffd 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -67,6 +67,7 @@
  */
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
+extern void __inval_dcache_area(void *addr, size_t len);
 extern void __clean_dcache_area_poc(void *addr, size_t len);
 extern void __clean_dcache_area_pou(void *addr, size_t len);
 extern long __flush_cache_user_range(unsigned long start, unsigned long end);
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 973df7de7bf8..73a0531e0187 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -143,8 +143,8 @@ preserve_boot_args:
 	dmb	sy				// needed before dc ivac with
 						// MMU off
 
-	add	x1, x0, #0x20			// 4 x 8 bytes
-	b	__inval_cache_range		// tail call
+	mov	x1, #0x20			// 4 x 8 bytes
+	b	__inval_dcache_area		// tail call
 ENDPROC(preserve_boot_args)
 
 /*
@@ -221,20 +221,20 @@ __create_page_tables:
 	 * dirty cache lines being evicted.
 	 */
 	adrp	x0, idmap_pg_dir
-	adrp	x1, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
-	bl	__inval_cache_range
+	ldr	x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+	bl	__inval_dcache_area
 
 	/*
 	 * Clear the idmap and swapper page tables.
 	 */
 	adrp	x0, idmap_pg_dir
-	adrp	x6, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
+	ldr	x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
 1:	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
-	cmp	x0, x6
-	b.lo	1b
+	subs	x1, x1, #64
+	b.ne	1b
 
 	mov	x7, SWAPPER_MM_MMUFLAGS
 
@@ -307,9 +307,9 @@ __create_page_tables:
 	 * tables again to remove any speculatively loaded cache lines.
 	 */
 	adrp	x0, idmap_pg_dir
-	adrp	x1, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
+	ldr	x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
 	dmb	sy
-	bl	__inval_cache_range
+	bl	__inval_dcache_area
 
 	ret	x28
 ENDPROC(__create_page_tables)
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 83c27b6e6dca..ed47fbbb4b05 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -109,20 +109,25 @@ ENTRY(__clean_dcache_area_pou)
 ENDPROC(__clean_dcache_area_pou)
 
 /*
- *	__dma_inv_area(start, size)
- *	- start   - virtual start address of region
+ *	__inval_dcache_area(kaddr, size)
+ *
+ * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	are invalidated. Any partial lines at the ends of the interval are
+ *	also cleaned to PoC to prevent data loss.
+ *
+ *	- kaddr   - kernel address
  *	- size    - size in question
  */
-__dma_inv_area:
-	add	x1, x1, x0
+ENTRY(__inval_dcache_area)
 	/* FALLTHROUGH */
 
 /*
- *	__inval_cache_range(start, end)
- *	- start   - start address of region
- *	- end     - end address of region
+ *	__dma_inv_area(start, size)
+ *	- start   - virtual start address of region
+ *	- size    - size in question
  */
-ENTRY(__inval_cache_range)
+__dma_inv_area:
+	add	x1, x1, x0
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	tst	x1, x3				// end cache line aligned?
@@ -140,7 +145,7 @@ ENTRY(__inval_cache_range)
 	b.lo	2b
 	dsb	sy
 	ret
-ENDPIPROC(__inval_cache_range)
+ENDPIPROC(__inval_dcache_area)
 ENDPROC(__dma_inv_area)
 
 /*
-- 
cgit v1.2.3-59-g8ed1b


From d50e071fdaa33c1b399c764c44fa1ce879881185 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 25 Jul 2017 11:55:42 +0100
Subject: arm64: Implement pmem API support

Add a clean-to-point-of-persistence cache maintenance helper, and wire
up the basic architectural support for the pmem driver based on it.

Reviewed-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
[catalin.marinas@arm.com: move arch_*_pmem() functions to arch/arm64/mm/flush.c]
[catalin.marinas@arm.com: change dmb(sy) to dmb(osh)]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/Kconfig                  | 11 +++++++++++
 arch/arm64/include/asm/assembler.h  |  6 ++++++
 arch/arm64/include/asm/cacheflush.h |  1 +
 arch/arm64/include/asm/cpucaps.h    |  3 ++-
 arch/arm64/kernel/cpufeature.c      | 11 +++++++++++
 arch/arm64/mm/cache.S               | 14 ++++++++++++++
 arch/arm64/mm/flush.c               | 16 ++++++++++++++++
 7 files changed, 61 insertions(+), 1 deletion(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index dfd908630631..0b0576a54724 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -960,6 +960,17 @@ config ARM64_UAO
 	  regular load/store instructions if the cpu does not implement the
 	  feature.
 
+config ARM64_PMEM
+	bool "Enable support for persistent memory"
+	select ARCH_HAS_PMEM_API
+	help
+	  Say Y to enable support for the persistent memory API based on the
+	  ARMv8.2 DCPoP feature.
+
+	  The feature is detected at runtime, and the kernel will use DC CVAC
+	  operations if DC CVAP is not supported (following the behaviour of
+	  DC CVAP itself if the system does not define a point of persistence).
+
 endmenu
 
 config ARM64_MODULE_CMODEL_LARGE
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 1b67c3782d00..5d8903c45031 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -352,6 +352,12 @@ alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
 	dc	\op, \kaddr
 alternative_else
 	dc	civac, \kaddr
+alternative_endif
+	.elseif	(\op == cvap)
+alternative_if ARM64_HAS_DCPOP
+	sys 3, c7, c12, 1, \kaddr	// dc cvap
+alternative_else
+	dc	cvac, \kaddr
 alternative_endif
 	.else
 	dc	\op, \kaddr
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index b4b43a94dffd..76d1cc85d5b1 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -69,6 +69,7 @@ extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
 extern void __inval_dcache_area(void *addr, size_t len);
 extern void __clean_dcache_area_poc(void *addr, size_t len);
+extern void __clean_dcache_area_pop(void *addr, size_t len);
 extern void __clean_dcache_area_pou(void *addr, size_t len);
 extern long __flush_cache_user_range(unsigned long start, unsigned long end);
 extern void sync_icache_aliases(void *kaddr, unsigned long len);
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 8d2272c6822c..8da621627d7c 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -39,7 +39,8 @@
 #define ARM64_WORKAROUND_QCOM_FALKOR_E1003	18
 #define ARM64_WORKAROUND_858921			19
 #define ARM64_WORKAROUND_CAVIUM_30115		20
+#define ARM64_HAS_DCPOP				21
 
-#define ARM64_NCAPS				21
+#define ARM64_NCAPS				22
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index a2542ef3ff25..cd52d365d1f0 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -889,6 +889,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.min_field_value = 0,
 		.matches = has_no_fpsimd,
 	},
+#ifdef CONFIG_ARM64_PMEM
+	{
+		.desc = "Data cache clean to Point of Persistence",
+		.capability = ARM64_HAS_DCPOP,
+		.def_scope = SCOPE_SYSTEM,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64ISAR1_EL1,
+		.field_pos = ID_AA64ISAR1_DPB_SHIFT,
+		.min_field_value = 1,
+	},
+#endif
 	{},
 };
 
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index ed47fbbb4b05..7f1dbe962cf5 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -171,6 +171,20 @@ __dma_clean_area:
 ENDPIPROC(__clean_dcache_area_poc)
 ENDPROC(__dma_clean_area)
 
+/*
+ *	__clean_dcache_area_pop(kaddr, size)
+ *
+ * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	are cleaned to the PoP.
+ *
+ *	- kaddr   - kernel address
+ *	- size    - size in question
+ */
+ENTRY(__clean_dcache_area_pop)
+	dcache_by_line_op cvap, sy, x0, x1, x2, x3
+	ret
+ENDPIPROC(__clean_dcache_area_pop)
+
 /*
  *	__dma_flush_area(start, size)
  *
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 21a8d828cbf4..280f90ff33a2 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -83,3 +83,19 @@ EXPORT_SYMBOL(flush_dcache_page);
  * Additional functions defined in assembly.
  */
 EXPORT_SYMBOL(flush_icache_range);
+
+#ifdef CONFIG_ARCH_HAS_PMEM_API
+static inline void arch_wb_cache_pmem(void *addr, size_t size)
+{
+	/* Ensure order against any prior non-cacheable writes */
+	dmb(osh);
+	__clean_dcache_area_pop(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
+
+static inline void arch_invalidate_pmem(void *addr, size_t size)
+{
+	__inval_dcache_area(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
+#endif
-- 
cgit v1.2.3-59-g8ed1b


From caf5ef7d15c511bbef691d0931adad56c2967435 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 10 Aug 2017 16:52:31 +0200
Subject: arm64: fix pmem interface definition

Defining the two functions as 'static inline' and exporting them
leads to the interesting case where we can use the interface
from loadable modules, but not from built-in drivers, as shown
in this link failure:

vers/nvdimm/claim.o: In function `nsio_rw_bytes':
claim.c:(.text+0x1b8): undefined reference to `arch_invalidate_pmem'
drivers/nvdimm/pmem.o: In function `pmem_dax_flush':
pmem.c:(.text+0x11c): undefined reference to `arch_wb_cache_pmem'
drivers/nvdimm/pmem.o: In function `pmem_make_request':
pmem.c:(.text+0x5a4): undefined reference to `arch_invalidate_pmem'
pmem.c:(.text+0x650): undefined reference to `arch_invalidate_pmem'
pmem.c:(.text+0x6d4): undefined reference to `arch_invalidate_pmem'

This removes the bogus 'static inline'.

Fixes: d50e071fdaa3 ("arm64: Implement pmem API support")
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/flush.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 280f90ff33a2..e36ed5087b5c 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -85,7 +85,7 @@ EXPORT_SYMBOL(flush_dcache_page);
 EXPORT_SYMBOL(flush_icache_range);
 
 #ifdef CONFIG_ARCH_HAS_PMEM_API
-static inline void arch_wb_cache_pmem(void *addr, size_t size)
+void arch_wb_cache_pmem(void *addr, size_t size)
 {
 	/* Ensure order against any prior non-cacheable writes */
 	dmb(osh);
@@ -93,7 +93,7 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size)
 }
 EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
 
-static inline void arch_invalidate_pmem(void *addr, size_t size)
+void arch_invalidate_pmem(void *addr, size_t size)
 {
 	__inval_dcache_area(addr, size);
 }
-- 
cgit v1.2.3-59-g8ed1b


From 3bbf7157ac66a88d94b291d4d5e2b2a9319a0f90 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 26 Jun 2017 14:27:36 +0100
Subject: arm64: Convert pte handling from inline asm to using (cmp)xchg

With the support for hardware updates of the access and dirty states,
the following pte handling functions had to be implemented using
exclusives: __ptep_test_and_clear_young(), ptep_get_and_clear(),
ptep_set_wrprotect() and ptep_set_access_flags(). To take advantage of
the LSE atomic instructions and also make the code cleaner, convert
these pte functions to use the more generic cmpxchg()/xchg().

Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/pgtable.h | 71 +++++++++++++++++++---------------------
 arch/arm64/mm/fault.c            | 24 +++++++-------
 2 files changed, 44 insertions(+), 51 deletions(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 6eae342ced6b..9127688ae775 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -39,6 +39,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/cmpxchg.h>
 #include <asm/fixmap.h>
 #include <linux/mmdebug.h>
 
@@ -173,6 +174,11 @@ static inline pte_t pte_clear_rdonly(pte_t pte)
 	return clear_pte_bit(pte, __pgprot(PTE_RDONLY));
 }
 
+static inline pte_t pte_set_rdonly(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_RDONLY));
+}
+
 static inline pte_t pte_mkpresent(pte_t pte)
 {
 	return set_pte_bit(pte, __pgprot(PTE_VALID));
@@ -593,20 +599,17 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int __ptep_test_and_clear_young(pte_t *ptep)
 {
-	pteval_t pteval;
-	unsigned int tmp, res;
+	pte_t old_pte, pte;
 
-	asm volatile("//	__ptep_test_and_clear_young\n"
-	"	prfm	pstl1strm, %2\n"
-	"1:	ldxr	%0, %2\n"
-	"	ubfx	%w3, %w0, %5, #1	// extract PTE_AF (young)\n"
-	"	and	%0, %0, %4		// clear PTE_AF\n"
-	"	stxr	%w1, %0, %2\n"
-	"	cbnz	%w1, 1b\n"
-	: "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)), "=&r" (res)
-	: "L" (~PTE_AF), "I" (ilog2(PTE_AF)));
+	pte = READ_ONCE(*ptep);
+	do {
+		old_pte = pte;
+		pte = pte_mkold(pte);
+		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
+					       pte_val(old_pte), pte_val(pte));
+	} while (pte_val(pte) != pte_val(old_pte));
 
-	return res;
+	return pte_young(pte);
 }
 
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
@@ -630,17 +633,7 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address, pte_t *ptep)
 {
-	pteval_t old_pteval;
-	unsigned int tmp;
-
-	asm volatile("//	ptep_get_and_clear\n"
-	"	prfm	pstl1strm, %2\n"
-	"1:	ldxr	%0, %2\n"
-	"	stxr	%w1, xzr, %2\n"
-	"	cbnz	%w1, 1b\n"
-	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)));
-
-	return __pte(old_pteval);
+	return __pte(xchg_relaxed(&pte_val(*ptep), 0));
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -659,21 +652,23 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
 {
-	pteval_t pteval;
-	unsigned long tmp;
-
-	asm volatile("//	ptep_set_wrprotect\n"
-	"	prfm	pstl1strm, %2\n"
-	"1:	ldxr	%0, %2\n"
-	"	tst	%0, %4			// check for hw dirty (!PTE_RDONLY)\n"
-	"	csel	%1, %3, xzr, eq		// set PTE_DIRTY|PTE_RDONLY if dirty\n"
-	"	orr	%0, %0, %1		// if !dirty, PTE_RDONLY is already set\n"
-	"	and	%0, %0, %5		// clear PTE_WRITE/PTE_DBM\n"
-	"	stxr	%w1, %0, %2\n"
-	"	cbnz	%w1, 1b\n"
-	: "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
-	: "r" (PTE_DIRTY|PTE_RDONLY), "L" (PTE_RDONLY), "L" (~PTE_WRITE)
-	: "cc");
+	pte_t old_pte, pte;
+
+	pte = READ_ONCE(*ptep);
+	do {
+		old_pte = pte;
+		/*
+		 * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
+		 * clear), set the PTE_DIRTY and PTE_RDONLY bits.
+		 */
+		if (pte_hw_dirty(pte)) {
+			pte = pte_mkdirty(pte);
+			pte = pte_set_rdonly(pte);
+		}
+		pte = pte_wrprotect(pte);
+		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
+					       pte_val(old_pte), pte_val(pte));
+	} while (pte_val(pte) != pte_val(old_pte));
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 52ee273afeec..430eaf82da49 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -34,6 +34,7 @@
 #include <linux/hugetlb.h>
 
 #include <asm/bug.h>
+#include <asm/cmpxchg.h>
 #include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
@@ -197,8 +198,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 			  unsigned long address, pte_t *ptep,
 			  pte_t entry, int dirty)
 {
-	pteval_t old_pteval;
-	unsigned int tmp;
+	pteval_t old_pteval, pteval;
 
 	if (pte_same(*ptep, entry))
 		return 0;
@@ -208,7 +208,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 
 	/* set PTE_RDONLY if actual read-only or clean PTE */
 	if (!pte_write(entry) || !pte_sw_dirty(entry))
-		pte_val(entry) |= PTE_RDONLY;
+		entry = pte_set_rdonly(entry);
 
 	/*
 	 * Setting the flags must be done atomically to avoid racing with the
@@ -217,16 +217,14 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	 * (calculated as: a & b == ~(~a | ~b)).
 	 */
 	pte_val(entry) ^= PTE_RDONLY;
-	asm volatile("//	ptep_set_access_flags\n"
-	"	prfm	pstl1strm, %2\n"
-	"1:	ldxr	%0, %2\n"
-	"	eor	%0, %0, %3		// negate PTE_RDONLY in *ptep\n"
-	"	orr	%0, %0, %4		// set flags\n"
-	"	eor	%0, %0, %3		// negate final PTE_RDONLY\n"
-	"	stxr	%w1, %0, %2\n"
-	"	cbnz	%w1, 1b\n"
-	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
-	: "L" (PTE_RDONLY), "r" (pte_val(entry)));
+	pteval = READ_ONCE(pte_val(*ptep));
+	do {
+		old_pteval = pteval;
+		pteval ^= PTE_RDONLY;
+		pteval |= pte_val(entry);
+		pteval ^= PTE_RDONLY;
+		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
+	} while (pteval != old_pteval);
 
 	flush_tlb_fix_spurious_fault(vma, address);
 	return 1;
-- 
cgit v1.2.3-59-g8ed1b


From 73e86cb03cf2ec0aa3789dc8621c6d53619cac5e Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Tue, 4 Jul 2017 19:04:18 +0100
Subject: arm64: Move PTE_RDONLY bit handling out of set_pte_at()

Currently PTE_RDONLY is treated as a hardware only bit and not handled
by the pte_mkwrite(), pte_wrprotect() or the user PAGE_* definitions.
The set_pte_at() function is responsible for setting this bit based on
the write permission or dirty state. This patch moves the PTE_RDONLY
handling out of set_pte_at into the pte_mkwrite()/pte_wrprotect()
functions. The PAGE_* definitions to need to be updated to explicitly
include PTE_RDONLY when !PTE_WRITE.

The patch also removes the redundant PAGE_COPY(_EXEC) definitions as
they are identical to the corresponding PAGE_READONLY(_EXEC).

Reviewed-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/pgtable-prot.h | 18 ++++++++----------
 arch/arm64/include/asm/pgtable.h      | 34 ++++++++++------------------------
 arch/arm64/kernel/hibernate.c         |  4 ++--
 arch/arm64/mm/fault.c                 |  6 +-----
 4 files changed, 21 insertions(+), 41 deletions(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2142c7726e76..0a5635fb0ef9 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -63,23 +63,21 @@
 #define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
 #define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
 
-#define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
+#define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
 #define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
-#define PAGE_COPY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_COPY_EXEC		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-#define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN)
+#define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
+#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
 
 #define __P000  PAGE_NONE
 #define __P001  PAGE_READONLY
-#define __P010  PAGE_COPY
-#define __P011  PAGE_COPY
+#define __P010  PAGE_READONLY
+#define __P011  PAGE_READONLY
 #define __P100  PAGE_EXECONLY
 #define __P101  PAGE_READONLY_EXEC
-#define __P110  PAGE_COPY_EXEC
-#define __P111  PAGE_COPY_EXEC
+#define __P110  PAGE_READONLY_EXEC
+#define __P111  PAGE_READONLY_EXEC
 
 #define __S000  PAGE_NONE
 #define __S001  PAGE_READONLY
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9127688ae775..a04bfb869a80 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -125,12 +125,16 @@ static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-	return clear_pte_bit(pte, __pgprot(PTE_WRITE));
+	pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
+	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+	return pte;
 }
 
 static inline pte_t pte_mkwrite(pte_t pte)
 {
-	return set_pte_bit(pte, __pgprot(PTE_WRITE));
+	pte = set_pte_bit(pte, __pgprot(PTE_WRITE));
+	pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+	return pte;
 }
 
 static inline pte_t pte_mkclean(pte_t pte)
@@ -169,16 +173,6 @@ static inline pte_t pte_mknoncont(pte_t pte)
 	return clear_pte_bit(pte, __pgprot(PTE_CONT));
 }
 
-static inline pte_t pte_clear_rdonly(pte_t pte)
-{
-	return clear_pte_bit(pte, __pgprot(PTE_RDONLY));
-}
-
-static inline pte_t pte_set_rdonly(pte_t pte)
-{
-	return set_pte_bit(pte, __pgprot(PTE_RDONLY));
-}
-
 static inline pte_t pte_mkpresent(pte_t pte)
 {
 	return set_pte_bit(pte, __pgprot(PTE_VALID));
@@ -226,14 +220,8 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
-	if (pte_present(pte)) {
-		if (pte_sw_dirty(pte) && pte_write(pte))
-			pte_val(pte) &= ~PTE_RDONLY;
-		else
-			pte_val(pte) |= PTE_RDONLY;
-		if (pte_user_exec(pte) && !pte_special(pte))
-			__sync_icache_dcache(pte, addr);
-	}
+	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
+		__sync_icache_dcache(pte, addr);
 
 	/*
 	 * If the existing pte is valid, check for potential race with
@@ -659,12 +647,10 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres
 		old_pte = pte;
 		/*
 		 * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
-		 * clear), set the PTE_DIRTY and PTE_RDONLY bits.
+		 * clear), set the PTE_DIRTY bit.
 		 */
-		if (pte_hw_dirty(pte)) {
+		if (pte_hw_dirty(pte))
 			pte = pte_mkdirty(pte);
-			pte = pte_set_rdonly(pte);
-		}
 		pte = pte_wrprotect(pte);
 		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
 					       pte_val(old_pte), pte_val(pte));
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index a44e13942d30..095d3c170f5d 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -330,7 +330,7 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
 		 * read only (code, rodata). Clear the RDONLY bit from
 		 * the temporary mappings we use during restore.
 		 */
-		set_pte(dst_pte, pte_clear_rdonly(pte));
+		set_pte(dst_pte, pte_mkwrite(pte));
 	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
 		/*
 		 * debug_pagealloc will removed the PTE_VALID bit if
@@ -343,7 +343,7 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
 		 */
 		BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-		set_pte(dst_pte, pte_mkpresent(pte_clear_rdonly(pte)));
+		set_pte(dst_pte, pte_mkpresent(pte_mkwrite(pte)));
 	}
 }
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 430eaf82da49..f75ed5c4b994 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -204,11 +204,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 		return 0;
 
 	/* only preserve the access flags and write permission */
-	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
-
-	/* set PTE_RDONLY if actual read-only or clean PTE */
-	if (!pte_write(entry) || !pte_sw_dirty(entry))
-		entry = pte_set_rdonly(entry);
+	pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;
 
 	/*
 	 * Setting the flags must be done atomically to avoid racing with the
-- 
cgit v1.2.3-59-g8ed1b


From af29678fe785ad79e7386e97b57093482f0dd7c4 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Thu, 6 Jul 2017 11:53:08 +0100
Subject: arm64: Remove the !CONFIG_ARM64_HW_AFDBM alternative code paths

Since the pte handling for hardware AF/DBM works even when the hardware
feature is not present, make the pte accessors implementation permanent
and remove the corresponding #ifdefs. The Kconfig option is kept as it
can still be used to disable the feature at the hardware level.

Reviewed-by: Will Deacon <will.deacon@arm.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/pgtable.h | 9 +--------
 arch/arm64/kvm/hyp/s2-setup.c    | 2 +-
 arch/arm64/mm/fault.c            | 2 --
 3 files changed, 2 insertions(+), 11 deletions(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 0117cbcd62d4..bc4e92337d16 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -85,11 +85,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 	(__boundary - 1 < (end) - 1) ? __boundary : (end);			\
 })
 
-#ifdef CONFIG_ARM64_HW_AFDBM
 #define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
-#else
-#define pte_hw_dirty(pte)	(0)
-#endif
 #define pte_sw_dirty(pte)	(!!(pte_val(pte) & PTE_DIRTY))
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
@@ -228,8 +224,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * hardware updates of the pte (ptep_set_access_flags safely changes
 	 * valid ptes without going through an invalid entry).
 	 */
-	if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
-	    pte_valid(*ptep) && pte_valid(pte)) {
+	if (pte_valid(*ptep) && pte_valid(pte)) {
 		VM_WARN_ONCE(!pte_young(pte),
 			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
 			     __func__, pte_val(*ptep), pte_val(pte));
@@ -565,7 +560,6 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
 }
 
-#ifdef CONFIG_ARM64_HW_AFDBM
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 extern int ptep_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pte_t *ptep,
@@ -670,7 +664,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 	ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
 }
 #endif
-#endif	/* CONFIG_ARM64_HW_AFDBM */
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
diff --git a/arch/arm64/kvm/hyp/s2-setup.c b/arch/arm64/kvm/hyp/s2-setup.c
index b81f4091c909..a81f5e10fc8c 100644
--- a/arch/arm64/kvm/hyp/s2-setup.c
+++ b/arch/arm64/kvm/hyp/s2-setup.c
@@ -70,7 +70,7 @@ u32 __hyp_text __init_stage2_translation(void)
 	 * Management in ID_AA64MMFR1_EL1 and enable the feature in VTCR_EL2.
 	 */
 	tmp = (read_sysreg(id_aa64mmfr1_el1) >> ID_AA64MMFR1_HADBS_SHIFT) & 0xf;
-	if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) && tmp)
+	if (tmp)
 		val |= VTCR_EL2_HA;
 
 	/*
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index f75ed5c4b994..778d0bb89551 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -183,7 +183,6 @@ void show_pte(unsigned long addr)
 	pr_cont("\n");
 }
 
-#ifdef CONFIG_ARM64_HW_AFDBM
 /*
  * This function sets the access flags (dirty, accessed), as well as write
  * permission, and only to a more permissive setting.
@@ -225,7 +224,6 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	flush_tlb_fix_spurious_fault(vma, address);
 	return 1;
 }
-#endif
 
 static bool is_el1_instruction_abort(unsigned int esr)
 {
-- 
cgit v1.2.3-59-g8ed1b


From 2fa59ec8ccf38bbc2193ae61aed9afa0687974e0 Mon Sep 17 00:00:00 2001
From: Vladimir Murzin <vladimir.murzin@arm.com>
Date: Mon, 14 Aug 2017 09:55:46 +0100
Subject: arm64: dma-mapping: Do not pass data to gen_pool_set_algo()

gen_pool_first_fit_order_align() does not make use of additional data,
so pass plain NULL there.

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/dma-mapping.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index f27d4dd04384..7038e1a61397 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -425,7 +425,7 @@ static int __init atomic_pool_init(void)
 
 		gen_pool_set_algo(atomic_pool,
 				  gen_pool_first_fit_order_align,
-				  (void *)PAGE_SHIFT);
+				  NULL);
 
 		pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
 			atomic_pool_size / 1024);
-- 
cgit v1.2.3-59-g8ed1b


From 8165f70648da0a4a51e5871693781b2cc29b29d6 Mon Sep 17 00:00:00 2001
From: Vladimir Murzin <vladimir.murzin@arm.com>
Date: Mon, 14 Aug 2017 09:55:47 +0100
Subject: arm64: dma-mapping: Mark atomic_pool as __ro_after_init

atomic_pool is setup once while init stage and never changed after
that, so it is good candidate for __ro_after_init

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/dma-mapping.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 7038e1a61397..614af886b7ef 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -42,7 +42,7 @@ static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
 	return prot;
 }
 
-static struct gen_pool *atomic_pool;
+static struct gen_pool *atomic_pool __ro_after_init;
 
 #define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
 static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
-- 
cgit v1.2.3-59-g8ed1b


From d3ea79527757ba65b3ee08e10c59a3c84f34e4bf Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Tue, 22 Aug 2017 11:42:41 +0100
Subject: arm64: hugetlb: set_huge_pte_at Add WARN_ON on !pte_present

This patch adds a WARN_ON to set_huge_pte_at as the accessor assumes
that entries to be written down are all present. (There are separate
accessors to clear huge ptes).

We will need to handle the !pte_present case where memory offlining
is used on hugetlb pages. swap and migration entries will be supplied
to set_huge_pte_at in this case.

Cc: David Woods <dwoods@mellanox.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/hugetlbpage.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 656e0ece2289..7b61e4833432 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -67,6 +67,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	unsigned long pfn;
 	pgprot_t hugeprot;
 
+	/*
+	 * Code needs to be expanded to handle huge swap and migration
+	 * entries. Needed for HUGETLB and MEMORY_FAILURE.
+	 */
+	WARN_ON(!pte_present(pte));
+
 	if (!pte_cont(pte)) {
 		set_pte_at(mm, addr, ptep, pte);
 		return;
-- 
cgit v1.2.3-59-g8ed1b


From b5b0be86d7181ed82cee9d8ac5073a48f038a305 Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Tue, 22 Aug 2017 11:42:42 +0100
Subject: arm64: hugetlb: Introduce pte_pgprot helper

Rather than xor pte bits in various places, use this helper function.

Cc: David Woods <dwoods@mellanox.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/hugetlbpage.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 7b61e4833432..cb84ca33bc6b 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -41,6 +41,16 @@ int pud_huge(pud_t pud)
 #endif
 }
 
+/*
+ * Select all bits except the pfn
+ */
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+	unsigned long pfn = pte_pfn(pte);
+
+	return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+}
+
 static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, size_t *pgsize)
 {
@@ -80,7 +90,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	pfn = pte_pfn(pte);
-	hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+	hugeprot = pte_pgprot(pte);
 	for (i = 0; i < ncontig; i++) {
 		pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
 			 pte_val(pfn_pte(pfn, hugeprot)));
@@ -223,9 +233,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 		size_t pgsize = 0;
 		unsigned long pfn = pte_pfn(pte);
 		/* Select all bits except the pfn */
-		pgprot_t hugeprot =
-			__pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^
-				 pte_val(pte));
+		pgprot_t hugeprot = pte_pgprot(pte);
 
 		pfn = pte_pfn(pte);
 		ncontig = find_num_contig(vma->vm_mm, addr, ptep,
-- 
cgit v1.2.3-59-g8ed1b


From 29a7287dceb76729960a15095fbbfcffa2179b07 Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Tue, 22 Aug 2017 11:42:43 +0100
Subject: arm64: hugetlb: Spring clean huge pte accessors

This patch aims to re-structure the huge pte accessors without affecting
their functionality. Control flow is changed to reduce indentation and
expanded use is made of post for loop variable modification.

It is then much easier to add break-before-make semantics in a subsequent
patch.

Cc: David Woods <dwoods@mellanox.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/hugetlbpage.c | 119 ++++++++++++++++++++------------------------
 1 file changed, 54 insertions(+), 65 deletions(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index cb84ca33bc6b..08deed7c71f0 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -74,7 +74,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	size_t pgsize;
 	int i;
 	int ncontig;
-	unsigned long pfn;
+	unsigned long pfn, dpfn;
 	pgprot_t hugeprot;
 
 	/*
@@ -90,14 +90,13 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	pfn = pte_pfn(pte);
+	dpfn = pgsize >> PAGE_SHIFT;
 	hugeprot = pte_pgprot(pte);
-	for (i = 0; i < ncontig; i++) {
+
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
 		pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
 			 pte_val(pfn_pte(pfn, hugeprot)));
 		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
-		ptep++;
-		pfn += pgsize >> PAGE_SHIFT;
-		addr += pgsize;
 	}
 }
 
@@ -195,91 +194,81 @@ pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep)
 {
-	pte_t pte;
-
-	if (pte_cont(*ptep)) {
-		int ncontig, i;
-		size_t pgsize;
-		bool is_dirty = false;
-
-		ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-		/* save the 1st pte to return */
-		pte = ptep_get_and_clear(mm, addr, ptep);
-		for (i = 1, addr += pgsize; i < ncontig; ++i, addr += pgsize) {
-			/*
-			 * If HW_AFDBM is enabled, then the HW could
-			 * turn on the dirty bit for any of the page
-			 * in the set, so check them all.
-			 */
-			++ptep;
-			if (pte_dirty(ptep_get_and_clear(mm, addr, ptep)))
-				is_dirty = true;
-		}
-		if (is_dirty)
-			return pte_mkdirty(pte);
-		else
-			return pte;
-	} else {
+	int ncontig, i;
+	size_t pgsize;
+	pte_t orig_pte = huge_ptep_get(ptep);
+
+	if (!pte_cont(orig_pte))
 		return ptep_get_and_clear(mm, addr, ptep);
+
+	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
+		/*
+		 * If HW_AFDBM is enabled, then the HW could
+		 * turn on the dirty bit for any of the page
+		 * in the set, so check them all.
+		 */
+		if (pte_dirty(ptep_get_and_clear(mm, addr, ptep)))
+			orig_pte = pte_mkdirty(orig_pte);
 	}
+
+	return orig_pte;
 }
 
 int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 			       unsigned long addr, pte_t *ptep,
 			       pte_t pte, int dirty)
 {
-	if (pte_cont(pte)) {
-		int ncontig, i, changed = 0;
-		size_t pgsize = 0;
-		unsigned long pfn = pte_pfn(pte);
-		/* Select all bits except the pfn */
-		pgprot_t hugeprot = pte_pgprot(pte);
-
-		pfn = pte_pfn(pte);
-		ncontig = find_num_contig(vma->vm_mm, addr, ptep,
-					  &pgsize);
-		for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize) {
-			changed |= ptep_set_access_flags(vma, addr, ptep,
-							pfn_pte(pfn,
-								hugeprot),
-							dirty);
-			pfn += pgsize >> PAGE_SHIFT;
-		}
-		return changed;
-	} else {
+	int ncontig, i, changed = 0;
+	size_t pgsize = 0;
+	unsigned long pfn = pte_pfn(pte), dpfn;
+	pgprot_t hugeprot;
+
+	if (!pte_cont(pte))
 		return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+
+	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+	dpfn = pgsize >> PAGE_SHIFT;
+	hugeprot = pte_pgprot(pte);
+
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
+		changed |= ptep_set_access_flags(vma, addr, ptep,
+				pfn_pte(pfn, hugeprot), dirty);
 	}
+
+	return changed;
 }
 
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 			     unsigned long addr, pte_t *ptep)
 {
-	if (pte_cont(*ptep)) {
-		int ncontig, i;
-		size_t pgsize = 0;
+	int ncontig, i;
+	size_t pgsize;
 
-		ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-		for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize)
-			ptep_set_wrprotect(mm, addr, ptep);
-	} else {
+	if (!pte_cont(*ptep)) {
 		ptep_set_wrprotect(mm, addr, ptep);
+		return;
 	}
+
+	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
+		ptep_set_wrprotect(mm, addr, ptep);
 }
 
 void huge_ptep_clear_flush(struct vm_area_struct *vma,
 			   unsigned long addr, pte_t *ptep)
 {
-	if (pte_cont(*ptep)) {
-		int ncontig, i;
-		size_t pgsize = 0;
-
-		ncontig = find_num_contig(vma->vm_mm, addr, ptep,
-					  &pgsize);
-		for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize)
-			ptep_clear_flush(vma, addr, ptep);
-	} else {
+	int ncontig, i;
+	size_t pgsize;
+
+	if (!pte_cont(*ptep)) {
 		ptep_clear_flush(vma, addr, ptep);
+		return;
 	}
+
+	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
+		ptep_clear_flush(vma, addr, ptep);
 }
 
 static __init int setup_hugepagesz(char *opt)
-- 
cgit v1.2.3-59-g8ed1b


From d8bdcff2876424d44d08a4d16a54fee518f9d5b8 Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Tue, 22 Aug 2017 11:42:44 +0100
Subject: arm64: hugetlb: Add break-before-make logic for contiguous entries

It has become apparent that one has to take special care when modifying
attributes of memory mappings that employ the contiguous bit.

Both the requirement and the architecturally correct "Break-Before-Make"
technique of updating contiguous entries can be found described in:
ARM DDI 0487A.k_iss10775, "Misprogramming of the Contiguous bit",
page D4-1762.

The huge pte accessors currently replace the attributes of contiguous
pte entries in place thus can, on certain platforms, lead to TLB
conflict aborts or even erroneous results returned from TLB lookups.

This patch adds two helper functions -

* get_clear_flush(.) - clears a contiguous entry and returns the head
  pte (whilst taking care to retain dirty bit information that could
  have been modified by DBM).

* clear_flush(.) that clears a contiguous entry

A tlb invalidate is performed to then ensure that there is no
possibility of multiple tlb entries being present for the same region.

Cc: David Woods <dwoods@mellanox.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
(Added helper clear_flush(), updated commit log, and some cleanup)
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
[catalin.marinas@arm.com: remove CONFIG_ARM64_HW_AFDBM check]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/hugetlbpage.c | 112 +++++++++++++++++++++++++++++++++++---------
 1 file changed, 91 insertions(+), 21 deletions(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 08deed7c71f0..b82df85fe920 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -68,6 +68,66 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 	return CONT_PTES;
 }
 
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step.
+ */
+static pte_t get_clear_flush(struct mm_struct *mm,
+			     unsigned long addr,
+			     pte_t *ptep,
+			     unsigned long pgsize,
+			     unsigned long ncontig)
+{
+	struct vm_area_struct vma = { .vm_mm = mm };
+	pte_t orig_pte = huge_ptep_get(ptep);
+	bool valid = pte_valid(orig_pte);
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
+		pte_t pte = ptep_get_and_clear(mm, addr, ptep);
+
+		/*
+		 * If HW_AFDBM is enabled, then the HW could turn on
+		 * the dirty bit for any page in the set, so check
+		 * them all.  All hugetlb entries are already young.
+		 */
+		if (pte_dirty(pte))
+			orig_pte = pte_mkdirty(orig_pte);
+	}
+
+	if (valid)
+		flush_tlb_range(&vma, saddr, addr);
+	return orig_pte;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step for use cases where the
+ * original pte is not needed.
+ */
+static void clear_flush(struct mm_struct *mm,
+			     unsigned long addr,
+			     pte_t *ptep,
+			     unsigned long pgsize,
+			     unsigned long ncontig)
+{
+	struct vm_area_struct vma = { .vm_mm = mm };
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		pte_clear(mm, addr, ptep);
+
+	flush_tlb_range(&vma, saddr, addr);
+}
+
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, pte_t pte)
 {
@@ -93,6 +153,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	dpfn = pgsize >> PAGE_SHIFT;
 	hugeprot = pte_pgprot(pte);
 
+	clear_flush(mm, addr, ptep, pgsize, ncontig);
+
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
 		pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
 			 pte_val(pfn_pte(pfn, hugeprot)));
@@ -194,7 +256,7 @@ pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep)
 {
-	int ncontig, i;
+	int ncontig;
 	size_t pgsize;
 	pte_t orig_pte = huge_ptep_get(ptep);
 
@@ -202,17 +264,8 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 		return ptep_get_and_clear(mm, addr, ptep);
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
-		/*
-		 * If HW_AFDBM is enabled, then the HW could
-		 * turn on the dirty bit for any of the page
-		 * in the set, so check them all.
-		 */
-		if (pte_dirty(ptep_get_and_clear(mm, addr, ptep)))
-			orig_pte = pte_mkdirty(orig_pte);
-	}
 
-	return orig_pte;
+	return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
 }
 
 int huge_ptep_set_access_flags(struct vm_area_struct *vma,
@@ -223,18 +276,25 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	size_t pgsize = 0;
 	unsigned long pfn = pte_pfn(pte), dpfn;
 	pgprot_t hugeprot;
+	pte_t orig_pte;
 
 	if (!pte_cont(pte))
 		return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
 
 	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
 	dpfn = pgsize >> PAGE_SHIFT;
-	hugeprot = pte_pgprot(pte);
 
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
-		changed |= ptep_set_access_flags(vma, addr, ptep,
-				pfn_pte(pfn, hugeprot), dirty);
-	}
+	orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+	if (!pte_same(orig_pte, pte))
+		changed = 1;
+
+	/* Make sure we don't lose the dirty state */
+	if (pte_dirty(orig_pte))
+		pte = pte_mkdirty(pte);
+
+	hugeprot = pte_pgprot(pte);
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+		set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
 
 	return changed;
 }
@@ -242,8 +302,11 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 			     unsigned long addr, pte_t *ptep)
 {
+	unsigned long pfn, dpfn;
+	pgprot_t hugeprot;
 	int ncontig, i;
 	size_t pgsize;
+	pte_t pte;
 
 	if (!pte_cont(*ptep)) {
 		ptep_set_wrprotect(mm, addr, ptep);
@@ -251,15 +314,23 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	}
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
-		ptep_set_wrprotect(mm, addr, ptep);
+	dpfn = pgsize >> PAGE_SHIFT;
+
+	pte = get_clear_flush(mm, addr, ptep, pgsize, ncontig);
+	pte = pte_wrprotect(pte);
+
+	hugeprot = pte_pgprot(pte);
+	pfn = pte_pfn(pte);
+
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
 }
 
 void huge_ptep_clear_flush(struct vm_area_struct *vma,
 			   unsigned long addr, pte_t *ptep)
 {
-	int ncontig, i;
 	size_t pgsize;
+	int ncontig;
 
 	if (!pte_cont(*ptep)) {
 		ptep_clear_flush(vma, addr, ptep);
@@ -267,8 +338,7 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma,
 	}
 
 	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
-		ptep_clear_flush(vma, addr, ptep);
+	clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
 }
 
 static __init int setup_hugepagesz(char *opt)
-- 
cgit v1.2.3-59-g8ed1b


From 30f3ac00ad2f822937839c95cbb22ce483190c4c Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 22 Aug 2017 11:42:45 +0100
Subject: arm64: hugetlb: Handle swap entries in huge_pte_offset() for
 contiguous hugepages

huge_pte_offset() was updated to correctly handle swap entries for
hugepages. With the addition of the size parameter, it is now possible
to disambiguate whether the request is for a regular hugepage or a
contiguous hugepage.

Fix huge_pte_offset() for contiguous hugepages by using the size to find
the correct page table entry.

Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Cc: David Woods <dwoods@mellanox.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/hugetlbpage.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index b82df85fe920..b91ec151e62c 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -221,19 +221,28 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return NULL;
 
 	pud = pud_offset(pgd, addr);
-	if (pud_none(*pud))
+	if (sz != PUD_SIZE && pud_none(*pud))
 		return NULL;
-	/* swap or huge page */
-	if (!pud_present(*pud) || pud_huge(*pud))
+	/* hugepage or swap? */
+	if (pud_huge(*pud) || !pud_present(*pud))
 		return (pte_t *)pud;
 	/* table; check the next level */
 
+	if (sz == CONT_PMD_SIZE)
+		addr &= CONT_PMD_MASK;
+
 	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
+	    pmd_none(*pmd))
 		return NULL;
-	if (!pmd_present(*pmd) || pmd_huge(*pmd))
+	if (pmd_huge(*pmd) || !pmd_present(*pmd))
 		return (pte_t *)pmd;
 
+	if (sz == CONT_PTE_SIZE) {
+		pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK));
+		return pte;
+	}
+
 	return NULL;
 }
 
-- 
cgit v1.2.3-59-g8ed1b


From c3e4ed5c3d5d79af940eb24c810dddcec6d2b536 Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 22 Aug 2017 11:42:46 +0100
Subject: arm64: hugetlb: Override huge_pte_clear() to support contiguous
 hugepages

The default huge_pte_clear() implementation does not clear contiguous
page table entries when it encounters contiguous hugepages that are
supported on arm64.

Fix this by overriding the default implementation to clear all the
entries associated with contiguous hugepages.

Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Cc: David Woods <dwoods@mellanox.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/hugetlb.h |  6 +++++-
 arch/arm64/mm/hugetlbpage.c      | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+), 1 deletion(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 793bd73b0d07..df8c0aea0917 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -18,7 +18,6 @@
 #ifndef __ASM_HUGETLB_H
 #define __ASM_HUGETLB_H
 
-#include <asm-generic/hugetlb.h>
 #include <asm/page.h>
 
 static inline pte_t huge_ptep_get(pte_t *ptep)
@@ -82,6 +81,11 @@ extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
 extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
 				  unsigned long addr, pte_t *ptep);
+extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+			   pte_t *ptep, unsigned long sz);
+#define huge_pte_clear huge_pte_clear
+
+#include <asm-generic/hugetlb.h>
 
 #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
 static inline bool gigantic_page_supported(void) { return true; }
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index b91ec151e62c..035c121c675b 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -68,6 +68,32 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 	return CONT_PTES;
 }
 
+static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
+{
+	int contig_ptes = 0;
+
+	*pgsize = size;
+
+	switch (size) {
+#ifdef CONFIG_ARM64_4K_PAGES
+	case PUD_SIZE:
+#endif
+	case PMD_SIZE:
+		contig_ptes = 1;
+		break;
+	case CONT_PMD_SIZE:
+		*pgsize = PMD_SIZE;
+		contig_ptes = CONT_PMDS;
+		break;
+	case CONT_PTE_SIZE:
+		*pgsize = PAGE_SIZE;
+		contig_ptes = CONT_PTES;
+		break;
+	}
+
+	return contig_ptes;
+}
+
 /*
  * Changing some bits of contiguous entries requires us to follow a
  * Break-Before-Make approach, breaking the whole contiguous set
@@ -262,6 +288,18 @@ pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 	return entry;
 }
 
+void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+		    pte_t *ptep, unsigned long sz)
+{
+	int i, ncontig;
+	size_t pgsize;
+
+	ncontig = num_contig_ptes(sz, &pgsize);
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		pte_clear(mm, addr, ptep);
+}
+
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep)
 {
-- 
cgit v1.2.3-59-g8ed1b


From a8d623eefd780288c0299f517da0845da687fbfc Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 22 Aug 2017 11:42:47 +0100
Subject: arm64: hugetlb: Override set_huge_swap_pte_at() to support contiguous
 hugepages

The default implementation of set_huge_swap_pte_at() does not support
hugepages consisting of contiguous ptes. Override it to add support for
contiguous hugepages.

Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Cc: David Woods <dwoods@mellanox.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/hugetlb.h |  3 +++
 arch/arm64/mm/hugetlbpage.c      | 12 ++++++++++++
 2 files changed, 15 insertions(+)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index df8c0aea0917..1dca41bea16a 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -84,6 +84,9 @@ extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
 extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, unsigned long sz);
 #define huge_pte_clear huge_pte_clear
+extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
+				 pte_t *ptep, pte_t pte, unsigned long sz);
+#define set_huge_swap_pte_at set_huge_swap_pte_at
 
 #include <asm-generic/hugetlb.h>
 
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 035c121c675b..76915b736b17 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -188,6 +188,18 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	}
 }
 
+void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
+			  pte_t *ptep, pte_t pte, unsigned long sz)
+{
+	int i, ncontig;
+	size_t pgsize;
+
+	ncontig = num_contig_ptes(sz, &pgsize);
+
+	for (i = 0; i < ncontig; i++, ptep++)
+		set_pte(ptep, pte);
+}
+
 pte_t *huge_pte_alloc(struct mm_struct *mm,
 		      unsigned long addr, unsigned long sz)
 {
-- 
cgit v1.2.3-59-g8ed1b


From 5cd028b9d90403bf24c8bf7915ed61c7a9bfce6c Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit.agrawal@arm.com>
Date: Tue, 22 Aug 2017 11:42:48 +0100
Subject: arm64: Re-enable support for contiguous hugepages

also known as -

Revert "Revert "Revert "commit 66b3923a1a0f ("arm64: hugetlb: add
support for PTE contiguous bit")"""

Now that our hugetlb implementation is compliant with the
break-before-make requirements of the architecture and we have addressed
some of the issues in core code required for properly dealing with
hardware poisoning of contiguous hugepages let's re-enable support for
contiguous hugepages.

This reverts commit 6ae979ab39a368c18ceb0424bf824d172d6ab56f.

Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/hugetlbpage.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 76915b736b17..3ceb4f275a1a 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -408,6 +408,10 @@ static __init int setup_hugepagesz(char *opt)
 		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
 	} else if (ps == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
+		hugetlb_add_hstate(CONT_PTE_SHIFT);
+	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
+		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
 	} else {
 		hugetlb_bad_size();
 		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
@@ -416,3 +420,13 @@ static __init int setup_hugepagesz(char *opt)
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+		hugetlb_add_hstate(CONT_PTE_SHIFT);
+	return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif
-- 
cgit v1.2.3-59-g8ed1b


From 828f193dd62a40ade5ea8b24cb8b0a22c30df673 Mon Sep 17 00:00:00 2001
From: Steve Capper <steve.capper@arm.com>
Date: Tue, 22 Aug 2017 11:42:49 +0100
Subject: arm64: hugetlb: Cleanup setup_hugepagesz

Replace a lot of if statements with switch and case labels to make it
much clearer which huge page sizes are supported.

Also, we prevent PUD_SIZE from being used on systems not running with
4KB PAGE_SIZE. Before if one supplied PUD_SIZE in these circumstances,
then unusuable huge page sizes would be in use.

Fixes: 084bd29810a5 ("ARM64: mm: HugeTLB support.")
Cc: David Woods <dwoods@mellanox.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/hugetlbpage.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

(limited to 'arch/arm64/mm')

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 3ceb4f275a1a..6cb0fa92a651 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -404,20 +404,20 @@ static __init int setup_hugepagesz(char *opt)
 {
 	unsigned long ps = memparse(opt, &opt);
 
-	if (ps == PMD_SIZE) {
-		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
-	} else if (ps == PUD_SIZE) {
-		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
-	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
-		hugetlb_add_hstate(CONT_PTE_SHIFT);
-	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
-		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
-	} else {
-		hugetlb_bad_size();
-		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
-		return 0;
+	switch (ps) {
+#ifdef CONFIG_ARM64_4K_PAGES
+	case PUD_SIZE:
+#endif
+	case PMD_SIZE * CONT_PMDS:
+	case PMD_SIZE:
+	case PAGE_SIZE * CONT_PTES:
+		hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT);
+		return 1;
 	}
-	return 1;
+
+	hugetlb_bad_size();
+	pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
+	return 0;
 }
 __setup("hugepagesz=", setup_hugepagesz);
 
-- 
cgit v1.2.3-59-g8ed1b