Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Catalin Marinas:
 "These are primarily bug fixes with a performance improvement patch for
  the GHASH crypto algorithm (which went in during this merging window)
  and dts/defconfig/Kconfig updates.

   - ftrace_return_addr() macro fix for arm (introduced earlier via the
     arm64 tree)
   - stack alignment exception entry code fix
   - GHASH crypto algorithm fix and performance improvement
   - CMA buffer limited to 32-bit (until a better way to describe the
     system topology in DT)
   - UAPI sigcontext.h build fix
   - __kernel_old_{gid,uid}_t definitions fix (affecting 32-bit LTP)
   - ptrace fixes (kernel fault and 32-bit arm core dump)
   - pte_mknotpresent() fix
   - dts updates (APM SoC)
   - defconfig and Kconfig update"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: mm: remove broken &= operator from pmd_mknotpresent
  arm64: fix build error in sigcontext.h
  arm64: dts: Add more serial port nodes in APM X-Gene device tree
  arm64/dma: Removing ARCH_HAS_DMA_GET_REQUIRED_MASK macro
  arm64: ptrace: fix empty registers set in prstatus of aarch32 process core
  arm64: uid16: fix __kernel_old_{gid,uid}_t definitions
  arm64: ptrace: change fs when passing kernel pointer to regset code
  arm64: Limit the CMA buffer to 32-bit if ZONE_DMA
  arm/ftrace: fix ftrace_return_addr() to ftrace_return_address()
  arm64/crypto: improve performance of GHASH algorithm
  arm64/crypto: fix data corruption bug in GHASH algorithm
  arm64: defconfig update for LTP
  arm64: ftrace: Fix comment typo 'CONFIG_FUNCTION_GRAPH_FP_TEST'
  arm64: add ARCH_HAS_OPP to allow enabling OPP library
  arm64: restore alphabetic order in Kconfig
  arm64: Bug fix in stack alignment exception

arch/arm/include/asm/ftrace.h

@@ -52,7 +52,7 @@ extern inline void *return_address(unsigned int level)
 
 #endif
 
-#define ftrace_return_addr(n) return_address(n)
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* ifndef __ASSEMBLY__ */
 

arch/arm64/Kconfig

 config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_HAS_OPP
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS

arch/arm64/boot/dts/apm-mustang.dts

@@ -24,3 +24,7 @@ memory {
 		reg = < 0x1 0x00000000 0x0 0x80000000 >; /* Updated by bootloader */
 	};
 };
+
+&serial0 {
+	status = "ok";
+};

arch/arm64/boot/dts/apm-storm.dtsi

@@ -273,8 +273,9 @@ rtcclk: rtcclk@17000000 {
 		};
 
 		serial0: serial@1c020000 {
+			status = "disabled";
 			device_type = "serial";
-			compatible = "ns16550";
+			compatible = "ns16550a";
 			reg = <0 0x1c020000 0x0 0x1000>;
 			reg-shift = <2>;
 			clock-frequency = <10000000>; /* Updated by bootloader */
@@ -282,6 +283,39 @@ serial0: serial@1c020000 {
 			interrupts = <0x0 0x4c 0x4>;
 		};
 
+		serial1: serial@1c021000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c021000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4d 0x4>;
+		};
+
+		serial2: serial@1c022000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c022000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4e 0x4>;
+		};
+
+		serial3: serial@1c023000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c023000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4f 0x4>;
+		};
+
 		phy1: phy@1f21a000 {
 			compatible = "apm,xgene-phy";
 			reg = <0x0 0x1f21a000 0x0 0x100>;

arch/arm64/configs/defconfig

@@ -6,9 +6,18 @@ CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
+CONFIG_RESOURCE_COUNTERS=y
+CONFIG_MEMCG=y
+CONFIG_MEMCG_SWAP=y
+CONFIG_MEMCG_KMEM=y
+CONFIG_CGROUP_HUGETLB=y
 # CONFIG_UTS_NS is not set
 # CONFIG_IPC_NS is not set
 # CONFIG_PID_NS is not set
@@ -27,6 +36,7 @@ CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_XGENE=y
 CONFIG_SMP=y
 CONFIG_PREEMPT=y
+CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
 CONFIG_CMDLINE="console=ttyAMA0"
@@ -45,6 +55,7 @@ CONFIG_IP_PNP_BOOTP=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DMA_CMA=y
+CONFIG_BLK_DEV_LOOP=y
 CONFIG_VIRTIO_BLK=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
@@ -53,6 +64,7 @@ CONFIG_ATA=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
+CONFIG_TUN=y
 CONFIG_SMC91X=y
 CONFIG_SMSC911X=y
 # CONFIG_WLAN is not set
@@ -85,6 +97,8 @@ CONFIG_EXT3_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
+CONFIG_FANOTIFY=y
+CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_FUSE_FS=y
 CONFIG_CUSE=y
 CONFIG_VFAT_FS=y
@@ -104,6 +118,7 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_LOCKUP_DETECTOR=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_FTRACE is not set
+CONFIG_SECURITY=y
 CONFIG_CRYPTO_ANSI_CPRNG=y
 CONFIG_ARM64_CRYPTO=y
 CONFIG_CRYPTO_SHA1_ARM64_CE=y

arch/arm64/crypto/ghash-ce-core.S

@@ -3,14 +3,6 @@
  *
  * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
- * Based on arch/x86/crypto/ghash-pmullni-intel_asm.S
- *
- * Copyright (c) 2009 Intel Corp.
- *   Author: Huang Ying <ying.huang@intel.com>
- *           Vinodh Gopal
- *           Erdinc Ozturk
- *           Deniz Karakoyunlu
- *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published
  * by the Free Software Foundation.
@@ -19,13 +11,15 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-	DATA	.req	v0
-	SHASH	.req	v1
-	IN1	.req	v2
+	SHASH	.req	v0
+	SHASH2	.req	v1
 	T1	.req	v2
 	T2	.req	v3
-	T3	.req	v4
-	VZR	.req	v5
+	MASK	.req	v4
+	XL	.req	v5
+	XM	.req	v6
+	XH	.req	v7
+	IN1	.req	v7
 
 	.text
 	.arch		armv8-a+crypto
@@ -35,61 +29,51 @@
 	 *			   struct ghash_key const *k, const char *head)
 	 */
 ENTRY(pmull_ghash_update)
-	ld1		{DATA.16b}, [x1]
 	ld1		{SHASH.16b}, [x3]
-	eor		VZR.16b, VZR.16b, VZR.16b
+	ld1		{XL.16b}, [x1]
+	movi		MASK.16b, #0xe1
+	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
+	shl		MASK.2d, MASK.2d, #57
+	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	/* do the head block first, if supplied */
 	cbz		x4, 0f
-	ld1		{IN1.2d}, [x4]
+	ld1		{T1.2d}, [x4]
 	b		1f
 
-0:	ld1		{IN1.2d}, [x2], #16
+0:	ld1		{T1.2d}, [x2], #16
 	sub		w0, w0, #1
-1:	ext		IN1.16b, IN1.16b, IN1.16b, #8
-CPU_LE(	rev64		IN1.16b, IN1.16b	)
-	eor		DATA.16b, DATA.16b, IN1.16b
 
-	/* multiply DATA by SHASH in GF(2^128) */
-	ext		T2.16b, DATA.16b, DATA.16b, #8
-	ext		T3.16b, SHASH.16b, SHASH.16b, #8
-	eor		T2.16b, T2.16b, DATA.16b
-	eor		T3.16b, T3.16b, SHASH.16b
+1:	/* multiply XL by SHASH in GF(2^128) */
+CPU_LE(	rev64		T1.16b, T1.16b	)
 
-	pmull2		T1.1q, SHASH.2d, DATA.2d	// a1 * b1
-	pmull		DATA.1q, SHASH.1d, DATA.1d	// a0 * b0
-	pmull		T2.1q, T2.1d, T3.1d		// (a1 + a0)(b1 + b0)
-	eor		T2.16b, T2.16b, T1.16b		// (a0 * b1) + (a1 * b0)
-	eor		T2.16b, T2.16b, DATA.16b
+	ext		T2.16b, XL.16b, XL.16b, #8
+	ext		IN1.16b, T1.16b, T1.16b, #8
+	eor		T1.16b, T1.16b, T2.16b
+	eor		XL.16b, XL.16b, IN1.16b
 
-	ext		T3.16b, VZR.16b, T2.16b, #8
-	ext		T2.16b, T2.16b, VZR.16b, #8
-	eor		DATA.16b, DATA.16b, T3.16b
-	eor		T1.16b, T1.16b, T2.16b	// <T1:DATA> is result of
-						// carry-less multiplication
+	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
+	eor		T1.16b, T1.16b, XL.16b
+	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
+	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
 
-	/* first phase of the reduction */
-	shl		T3.2d, DATA.2d, #1
-	eor		T3.16b, T3.16b, DATA.16b
-	shl		T3.2d, T3.2d, #5
-	eor		T3.16b, T3.16b, DATA.16b
-	shl		T3.2d, T3.2d, #57
-	ext		T2.16b, VZR.16b, T3.16b, #8
-	ext		T3.16b, T3.16b, VZR.16b, #8
-	eor		DATA.16b, DATA.16b, T2.16b
-	eor		T1.16b, T1.16b, T3.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		T2.16b, XL.16b, XH.16b
+	eor		XM.16b, XM.16b, T1.16b
+	eor		XM.16b, XM.16b, T2.16b
+	pmull		T2.1q, XL.1d, MASK.1d
 
-	/* second phase of the reduction */
-	ushr		T2.2d, DATA.2d, #5
-	eor		T2.16b, T2.16b, DATA.16b
-	ushr		T2.2d, T2.2d, #1
-	eor		T2.16b, T2.16b, DATA.16b
-	ushr		T2.2d, T2.2d, #1
-	eor		T1.16b, T1.16b, T2.16b
-	eor		DATA.16b, DATA.16b, T1.16b
+	mov		XH.d[0], XM.d[1]
+	mov		XM.d[1], XL.d[0]
+
+	eor		XL.16b, XM.16b, T2.16b
+	ext		T2.16b, XL.16b, XL.16b, #8
+	pmull		XL.1q, XL.1d, MASK.1d
+	eor		T2.16b, T2.16b, XH.16b
+	eor		XL.16b, XL.16b, T2.16b
 
 	cbnz		w0, 0b
 
-	st1		{DATA.16b}, [x1]
+	st1		{XL.16b}, [x1]
 	ret
 ENDPROC(pmull_ghash_update)

arch/arm64/crypto/ghash-ce-glue.c

@@ -67,11 +67,12 @@ static int ghash_update(struct shash_desc *desc, const u8 *src,
 		blocks = len / GHASH_BLOCK_SIZE;
 		len %= GHASH_BLOCK_SIZE;
 
-		kernel_neon_begin_partial(6);
+		kernel_neon_begin_partial(8);
 		pmull_ghash_update(blocks, ctx->digest, src, key,
 				   partial ? ctx->buf : NULL);
 		kernel_neon_end();
 		src += blocks * GHASH_BLOCK_SIZE;
+		partial = 0;
 	}
 	if (len)
 		memcpy(ctx->buf + partial, src, len);
@@ -88,7 +89,7 @@ static int ghash_final(struct shash_desc *desc, u8 *dst)
 
 		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
 
-		kernel_neon_begin_partial(6);
+		kernel_neon_begin_partial(8);
 		pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL);
 		kernel_neon_end();
 	}

arch/arm64/include/asm/Kbuild

@@ -30,7 +30,6 @@ generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += pci.h
 generic-y += poll.h
-generic-y += posix_types.h
 generic-y += preempt.h
 generic-y += resource.h
 generic-y += rwsem.h

arch/arm64/include/asm/dma-mapping.h

@@ -26,8 +26,6 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define ARCH_HAS_DMA_GET_REQUIRED_MASK
-
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
 extern struct dma_map_ops coherent_swiotlb_dma_ops;

arch/arm64/include/asm/pgtable.h

@@ -246,7 +246,7 @@ static inline pmd_t pte_pmd(pte_t pte)
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) &= ~PMD_TYPE_MASK))
+#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))

arch/arm64/include/uapi/asm/posix_types.h

+#ifndef __ASM_POSIX_TYPES_H
+#define __ASM_POSIX_TYPES_H
+
+typedef unsigned short __kernel_old_uid_t;
+typedef unsigned short __kernel_old_gid_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
+
+#include <asm-generic/posix_types.h>
+
+#endif /*  __ASM_POSIX_TYPES_H */

arch/arm64/include/uapi/asm/sigcontext.h

@@ -58,7 +58,7 @@ struct fpsimd_context {
 
 struct esr_context {
 	struct _aarch64_ctx head;
-	u64 esr;
+	__u64 esr;
 };
 
 #endif /* _UAPI__ASM_SIGCONTEXT_H */

arch/arm64/kernel/entry-ftrace.S

@@ -205,7 +205,7 @@ ENDPROC(ftrace_graph_caller)
  *
  * Run ftrace_return_to_handler() before going back to parent.
  * @fp is checked against the value passed by ftrace_graph_caller()
- * only when CONFIG_FUNCTION_GRAPH_FP_TEST is enabled.
+ * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled.
  */
 ENTRY(return_to_handler)
 	str	x0, [sp, #-16]!

arch/arm64/kernel/entry.S

@@ -279,7 +279,6 @@ el1_sp_pc:
 	 */
 	mrs	x0, far_el1
 	enable_dbg
-	mov	x1, x25
 	mov	x2, sp
 	b	do_sp_pc_abort
 el1_undef:

arch/arm64/kernel/ptrace.c

@@ -655,12 +655,17 @@ static int compat_gpr_get(struct task_struct *target,
 			reg = task_pt_regs(target)->regs[idx];
 		}
 
+		if (kbuf) {
+			memcpy(kbuf, &reg, sizeof(reg));
+			kbuf += sizeof(reg);
+		} else {
 			ret = copy_to_user(ubuf, &reg, sizeof(reg));
 			if (ret)
 				break;
 
 			ubuf += sizeof(reg);
 		}
+	}
 
 	return ret;
 }
@@ -689,11 +694,16 @@ static int compat_gpr_set(struct task_struct *target,
 		unsigned int idx = start + i;
 		compat_ulong_t reg;
 
+		if (kbuf) {
+			memcpy(&reg, kbuf, sizeof(reg));
+			kbuf += sizeof(reg);
+		} else {
 			ret = copy_from_user(&reg, ubuf, sizeof(reg));
 			if (ret)
 				return ret;
 
 			ubuf += sizeof(reg);
+		}
 
 		switch (idx) {
 		case 15:
@@ -827,6 +837,7 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off,
 				    compat_ulong_t val)
 {
 	int ret;
+	mm_segment_t old_fs = get_fs();
 
 	if (off & 3 || off >= COMPAT_USER_SZ)
 		return -EIO;
@@ -834,10 +845,13 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off,
 	if (off >= sizeof(compat_elf_gregset_t))
 		return 0;
 
+	set_fs(KERNEL_DS);
 	ret = copy_regset_from_user(tsk, &user_aarch32_view,
 				    REGSET_COMPAT_GPR, off,
 				    sizeof(compat_ulong_t),
 				    &val);
+	set_fs(old_fs);
+
 	return ret;
 }
 

arch/arm64/mm/init.c

@@ -71,7 +71,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	/* 4GB maximum for 32-bit only capable devices */
 	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
 		unsigned long max_dma_phys =
-			(unsigned long)dma_to_phys(NULL, DMA_BIT_MASK(32) + 1);
+			(unsigned long)(dma_to_phys(NULL, DMA_BIT_MASK(32)) + 1);
 		max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
 		zone_size[ZONE_DMA] = max_dma - min;
 	}
@@ -126,6 +126,8 @@ static void arm64_memory_present(void)
 
 void __init arm64_memblock_init(void)
 {
+	phys_addr_t dma_phys_limit = 0;
+
 	/* Register the kernel text, kernel data and initrd with memblock */
 	memblock_reserve(__pa(_text), _end - _text);
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -141,7 +143,11 @@ void __init arm64_memblock_init(void)
 	memblock_reserve(__pa(idmap_pg_dir), IDMAP_DIR_SIZE);
 
 	early_init_fdt_scan_reserved_mem();
-	dma_contiguous_reserve(0);
+
+	/* 4GB maximum for 32-bit only capable devices */
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		dma_phys_limit = dma_to_phys(NULL, DMA_BIT_MASK(32)) + 1;
+	dma_contiguous_reserve(dma_phys_limit);
 
 	memblock_allow_resize();
 	memblock_dump_all();