Merge remote-tracking branch 'stable/linux-4.14.y' into rpi-4.14.y

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 14
-SUBLEVEL = 33
+SUBLEVEL = 34
 EXTRAVERSION =
 NAME = Petit Gorille
 

arch/arm/boot/dts/ls1021a.dtsi

@@ -155,7 +155,7 @@
 		};
 
 		esdhc: esdhc@1560000 {
-			compatible = "fsl,esdhc";
+			compatible = "fsl,ls1021a-esdhc", "fsl,esdhc";
 			reg = <0x0 0x1560000 0x0 0x10000>;
 			interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <0>;

arch/arm64/crypto/Makefile

@@ -24,7 +24,7 @@ obj-$(CONFIG_CRYPTO_CRC32_ARM64_CE) += crc32-ce.o
 crc32-ce-y:= crc32-ce-core.o crc32-ce-glue.o
 
 obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
-CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
+aes-ce-cipher-y := aes-ce-core.o aes-ce-glue.o
 
 obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
 aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o

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

@@ -0,0 +1,87 @@
+/*
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.arch		armv8-a+crypto
+
+ENTRY(__aes_ce_encrypt)
+	sub		w3, w3, #2
+	ld1		{v0.16b}, [x2]
+	ld1		{v1.4s}, [x0], #16
+	cmp		w3, #10
+	bmi		0f
+	bne		3f
+	mov		v3.16b, v1.16b
+	b		2f
+0:	mov		v2.16b, v1.16b
+	ld1		{v3.4s}, [x0], #16
+1:	aese		v0.16b, v2.16b
+	aesmc		v0.16b, v0.16b
+2:	ld1		{v1.4s}, [x0], #16
+	aese		v0.16b, v3.16b
+	aesmc		v0.16b, v0.16b
+3:	ld1		{v2.4s}, [x0], #16
+	subs		w3, w3, #3
+	aese		v0.16b, v1.16b
+	aesmc		v0.16b, v0.16b
+	ld1		{v3.4s}, [x0], #16
+	bpl		1b
+	aese		v0.16b, v2.16b
+	eor		v0.16b, v0.16b, v3.16b
+	st1		{v0.16b}, [x1]
+	ret
+ENDPROC(__aes_ce_encrypt)
+
+ENTRY(__aes_ce_decrypt)
+	sub		w3, w3, #2
+	ld1		{v0.16b}, [x2]
+	ld1		{v1.4s}, [x0], #16
+	cmp		w3, #10
+	bmi		0f
+	bne		3f
+	mov		v3.16b, v1.16b
+	b		2f
+0:	mov		v2.16b, v1.16b
+	ld1		{v3.4s}, [x0], #16
+1:	aesd		v0.16b, v2.16b
+	aesimc		v0.16b, v0.16b
+2:	ld1		{v1.4s}, [x0], #16
+	aesd		v0.16b, v3.16b
+	aesimc		v0.16b, v0.16b
+3:	ld1		{v2.4s}, [x0], #16
+	subs		w3, w3, #3
+	aesd		v0.16b, v1.16b
+	aesimc		v0.16b, v0.16b
+	ld1		{v3.4s}, [x0], #16
+	bpl		1b
+	aesd		v0.16b, v2.16b
+	eor		v0.16b, v0.16b, v3.16b
+	st1		{v0.16b}, [x1]
+	ret
+ENDPROC(__aes_ce_decrypt)
+
+/*
+ * __aes_ce_sub() - use the aese instruction to perform the AES sbox
+ *                  substitution on each byte in 'input'
+ */
+ENTRY(__aes_ce_sub)
+	dup		v1.4s, w0
+	movi		v0.16b, #0
+	aese		v0.16b, v1.16b
+	umov		w0, v0.s[0]
+	ret
+ENDPROC(__aes_ce_sub)
+
+ENTRY(__aes_ce_invert)
+	ld1		{v0.4s}, [x1]
+	aesimc		v1.16b, v0.16b
+	st1		{v1.4s}, [x0]
+	ret
+ENDPROC(__aes_ce_invert)

arch/arm64/crypto/aes-ce-cipher.c → arch/arm64/crypto/aes-ce-glue.c

@@ -29,6 +29,13 @@ struct aes_block {
 	u8 b[AES_BLOCK_SIZE];
 };
 
+asmlinkage void __aes_ce_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+asmlinkage void __aes_ce_decrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
+asmlinkage u32 __aes_ce_sub(u32 l);
+asmlinkage void __aes_ce_invert(struct aes_block *out,
+				const struct aes_block *in);
+
 static int num_rounds(struct crypto_aes_ctx *ctx)
 {
 	/*
@@ -44,123 +51,31 @@ static int num_rounds(struct crypto_aes_ctx *ctx)
 static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct aes_block *out = (struct aes_block *)dst;
-	struct aes_block const *in = (struct aes_block *)src;
-	void *dummy0;
-	int dummy1;
 
 	if (!may_use_simd()) {
 		__aes_arm64_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
 		return;
 	}
 
 	kernel_neon_begin();
-
-	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.4s}, [%[key]], #16		;"
-		"	cmp	%w[rounds], #10			;"
-		"	bmi	0f				;"
-		"	bne	3f				;"
-		"	mov	v3.16b, v1.16b			;"
-		"	b	2f				;"
-		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"1:	aese	v0.16b, v2.16b			;"
-		"	aesmc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.4s}, [%[key]], #16		;"
-		"	aese	v0.16b, v3.16b			;"
-		"	aesmc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.4s}, [%[key]], #16		;"
-		"	subs	%w[rounds], %w[rounds], #3	;"
-		"	aese	v0.16b, v1.16b			;"
-		"	aesmc	v0.16b, v0.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"	bpl	1b				;"
-		"	aese	v0.16b, v2.16b			;"
-		"	eor	v0.16b, v0.16b, v3.16b		;"
-		"	st1	{v0.16b}, %[out]		;"
-
-	:	[out]		"=Q"(*out),
-		[key]		"=r"(dummy0),
-		[rounds]	"=r"(dummy1)
-	:	[in]		"Q"(*in),
-				"1"(ctx->key_enc),
-				"2"(num_rounds(ctx) - 2)
-	:	"cc");
-
+	__aes_ce_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
 	kernel_neon_end();
 }
 
 static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct aes_block *out = (struct aes_block *)dst;
-	struct aes_block const *in = (struct aes_block *)src;
-	void *dummy0;
-	int dummy1;
 
 	if (!may_use_simd()) {
 		__aes_arm64_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
 		return;
 	}
 
 	kernel_neon_begin();
-
-	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.4s}, [%[key]], #16		;"
-		"	cmp	%w[rounds], #10			;"
-		"	bmi	0f				;"
-		"	bne	3f				;"
-		"	mov	v3.16b, v1.16b			;"
-		"	b	2f				;"
-		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"1:	aesd	v0.16b, v2.16b			;"
-		"	aesimc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.4s}, [%[key]], #16		;"
-		"	aesd	v0.16b, v3.16b			;"
-		"	aesimc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.4s}, [%[key]], #16		;"
-		"	subs	%w[rounds], %w[rounds], #3	;"
-		"	aesd	v0.16b, v1.16b			;"
-		"	aesimc	v0.16b, v0.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"	bpl	1b				;"
-		"	aesd	v0.16b, v2.16b			;"
-		"	eor	v0.16b, v0.16b, v3.16b		;"
-		"	st1	{v0.16b}, %[out]		;"
-
-	:	[out]		"=Q"(*out),
-		[key]		"=r"(dummy0),
-		[rounds]	"=r"(dummy1)
-	:	[in]		"Q"(*in),
-				"1"(ctx->key_dec),
-				"2"(num_rounds(ctx) - 2)
-	:	"cc");
-
+	__aes_ce_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
 	kernel_neon_end();
 }
 
-/*
- * aes_sub() - use the aese instruction to perform the AES sbox substitution
- *             on each byte in 'input'
- */
-static u32 aes_sub(u32 input)
-{
-	u32 ret;
-
-	__asm__("dup	v1.4s, %w[in]		;"
-		"movi	v0.16b, #0		;"
-		"aese	v0.16b, v1.16b		;"
-		"umov	%w[out], v0.4s[0]	;"
-
-	:	[out]	"=r"(ret)
-	:	[in]	"r"(input)
-	:		"v0","v1");
-
-	return ret;
-}
-
 int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		     unsigned int key_len)
 {
@@ -189,7 +104,7 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		u32 *rki = ctx->key_enc + (i * kwords);
 		u32 *rko = rki + kwords;
 
-		rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+		rko[0] = ror32(__aes_ce_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
 		rko[1] = rko[0] ^ rki[1];
 		rko[2] = rko[1] ^ rki[2];
 		rko[3] = rko[2] ^ rki[3];
@@ -202,7 +117,7 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		} else if (key_len == AES_KEYSIZE_256) {
 			if (i >= 6)
 				break;
-			rko[4] = aes_sub(rko[3]) ^ rki[4];
+			rko[4] = __aes_ce_sub(rko[3]) ^ rki[4];
 			rko[5] = rko[4] ^ rki[5];
 			rko[6] = rko[5] ^ rki[6];
 			rko[7] = rko[6] ^ rki[7];
@@ -221,13 +136,7 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 
 	key_dec[0] = key_enc[j];
 	for (i = 1, j--; j > 0; i++, j--)
-		__asm__("ld1	{v0.4s}, %[in]		;"
-			"aesimc	v1.16b, v0.16b		;"
-			"st1	{v1.4s}, %[out]	;"
-
-		:	[out]	"=Q"(key_dec[i])
-		:	[in]	"Q"(key_enc[j])
-		:		"v0","v1");
+		__aes_ce_invert(key_dec + i, key_enc + j);
 	key_dec[i] = key_enc[0];
 
 	kernel_neon_end();

arch/x86/include/asm/microcode.h

@@ -37,7 +37,13 @@ struct cpu_signature {
 
 struct device;
 
-enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND };
+enum ucode_state {
+	UCODE_OK	= 0,
+	UCODE_NEW,
+	UCODE_UPDATED,
+	UCODE_NFOUND,
+	UCODE_ERROR,
+};
 
 struct microcode_ops {
 	enum ucode_state (*request_microcode_user) (int cpu,
@@ -54,7 +60,7 @@ struct microcode_ops {
 	 * are being called.
 	 * See also the "Synchronization" section in microcode_core.c.
 	 */
-	int (*apply_microcode) (int cpu);
+	enum ucode_state (*apply_microcode) (int cpu);
 	int (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
 };
 

arch/x86/include/asm/processor.h

@@ -968,4 +968,5 @@ bool xen_set_default_idle(void);
 
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
+void microcode_check(void);
 #endif /* _ASM_X86_PROCESSOR_H */

arch/x86/kernel/aperture_64.c

@@ -30,6 +30,7 @@
 #include <asm/dma.h>
 #include <asm/amd_nb.h>
 #include <asm/x86_init.h>
+#include <linux/crash_dump.h>
 
 /*
  * Using 512M as goal, in case kexec will load kernel_big
@@ -56,6 +57,33 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
+#ifdef CONFIG_PROC_VMCORE
+/*
+ * If the first kernel maps the aperture over e820 RAM, the kdump kernel will
+ * use the same range because it will remain configured in the northbridge.
+ * Trying to dump this area via /proc/vmcore may crash the machine, so exclude
+ * it from vmcore.
+ */
+static unsigned long aperture_pfn_start, aperture_page_count;
+
+static int gart_oldmem_pfn_is_ram(unsigned long pfn)
+{
+	return likely((pfn < aperture_pfn_start) ||
+		      (pfn >= aperture_pfn_start + aperture_page_count));
+}
+
+static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+{
+	aperture_pfn_start = aper_base >> PAGE_SHIFT;
+	aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT;
+	WARN_ON(register_oldmem_pfn_is_ram(&gart_oldmem_pfn_is_ram));
+}
+#else
+static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+{
+}
+#endif
+
 /* This code runs before the PCI subsystem is initialized, so just
    access the northbridge directly. */
 
@@ -435,8 +463,16 @@ int __init gart_iommu_hole_init(void)
 
 out:
 	if (!fix && !fallback_aper_force) {
-		if (last_aper_base)
+		if (last_aper_base) {
+			/*
+			 * If this is the kdump kernel, the first kernel
+			 * may have allocated the range over its e820 RAM
+			 * and fixed up the northbridge
+			 */
+			exclude_from_vmcore(last_aper_base, last_aper_order);
+
 			return 1;
+		}
 		return 0;
 	}
 
@@ -473,6 +509,14 @@ int __init gart_iommu_hole_init(void)
 		return 0;
 	}
 
+	/*
+	 * If this is the kdump kernel _and_ the first kernel did not
+	 * configure the aperture in the northbridge, this range may
+	 * overlap with the first kernel's memory. We can't access the
+	 * range through vmcore even though it should be part of the dump.
+	 */
+	exclude_from_vmcore(aper_alloc, aper_order);
+
 	/* Fix up the north bridges */
 	for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
 		int bus, dev_base, dev_limit;