Merge branch 'x86/mm' into efi/core, to pick up dependencies

Signed-off-by: Ingo Molnar <mingo@kernel.org>

22 files changed, 189 insertions, 50 deletions

diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h
index 734ad4db388c..2edef8d7fa6b 100644
--- a/include/asm-generic/early_ioremap.h
+++ b/include/asm-generic/early_ioremap.h
@@ -13,6 +13,8 @@ extern void *early_memremap(resource_size_t phys_addr,
 			    unsigned long size);
 extern void *early_memremap_ro(resource_size_t phys_addr,
 			       unsigned long size);
+extern void *early_memremap_prot(resource_size_t phys_addr,
+				 unsigned long size, unsigned long prot_val);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
 extern void early_memunmap(void *addr, unsigned long size);
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 7dfa767dc680..4d7bb98f4134 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -583,6 +583,18 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 #endif /* CONFIG_MMU */
 
 /*
+ * No-op macros that just return the current protection value. Defined here
+ * because these macros can be used used even if CONFIG_MMU is not defined.
+ */
+#ifndef pgprot_encrypted
+#define pgprot_encrypted(prot)	(prot)
+#endif
+
+#ifndef pgprot_decrypted
+#define pgprot_decrypted(prot)	(prot)
+#endif
+
+/*
  * A facility to provide lazy MMU batching.  This allows PTE updates and
  * page invalidations to be delayed until a call to leave lazy MMU mode
  * is issued.  Some architectures may benefit from doing this, and it is
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index da0be9a8d1de..9623d78f8494 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -60,6 +60,22 @@
 #define ALIGN_FUNCTION()  . = ALIGN(8)
 
 /*
+ * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections, which
+ * generates .data.identifier sections, which need to be pulled in with
+ * .data. We don't want to pull in .data..other sections, which Linux
+ * has defined. Same for text and bss.
+ */
+#ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
+#define TEXT_MAIN .text .text.[0-9a-zA-Z_]*
+#define DATA_MAIN .data .data.[0-9a-zA-Z_]*
+#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]*
+#else
+#define TEXT_MAIN .text
+#define DATA_MAIN .data
+#define BSS_MAIN .bss
+#endif
+
+/*
  * Align to a 32 byte boundary equal to the
  * alignment gcc 4.5 uses for a struct
  */
@@ -198,12 +214,9 @@
 
 /*
  * .data section
- * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections generates
- * .data.identifier which needs to be pulled in with .data, but don't want to
- * pull in .data..stuff which has its own requirements. Same for bss.
  */
 #define DATA_DATA							\
-	*(.data .data.[0-9a-zA-Z_]*)					\
+	*(DATA_MAIN)							\
 	*(.ref.data)							\
 	*(.data..shared_aligned) /* percpu related */			\
 	MEM_KEEP(init.data)						\
@@ -434,16 +447,17 @@
 		VMLINUX_SYMBOL(__security_initcall_end) = .;		\
 	}
 
-/* .text section. Map to function alignment to avoid address changes
+/*
+ * .text section. Map to function alignment to avoid address changes
  * during second ld run in second ld pass when generating System.map
- * LD_DEAD_CODE_DATA_ELIMINATION option enables -ffunction-sections generates
- * .text.identifier which needs to be pulled in with .text , but some
- * architectures define .text.foo which is not intended to be pulled in here.
- * Those enabling LD_DEAD_CODE_DATA_ELIMINATION must ensure they don't have
- * conflicting section names, and must pull in .text.[0-9a-zA-Z_]* */
+ *
+ * TEXT_MAIN here will match .text.fixup and .text.unlikely if dead
+ * code elimination is enabled, so these sections should be converted
+ * to use ".." first.
+ */
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
-		*(.text.hot .text .text.fixup .text.unlikely)		\
+		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely)	\
 		*(.ref.text)						\
 	MEM_KEEP(init.text)						\
 	MEM_KEEP(exit.text)						\
@@ -613,7 +627,7 @@
 		BSS_FIRST_SECTIONS					\
 		*(.bss..page_aligned)					\
 		*(.dynbss)						\
-		*(.bss .bss.[0-9a-zA-Z_]*)				\
+		*(BSS_MAIN)						\
 		*(COMMON)						\
 	}
 
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index bdb80c4aef6e..71b86a5d3061 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -166,6 +166,8 @@
 
 #if GCC_VERSION >= 40100
 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
+
+#define __nostackprotector	__attribute__((__optimize__("no-stack-protector")))
 #endif
 
 #if GCC_VERSION >= 40300
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index eca8ad75e28b..43cac547f773 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -475,6 +475,10 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 #define __visible
 #endif
 
+#ifndef __nostackprotector
+# define __nostackprotector
+#endif
+
 /*
  * Assume alignment of return value.
  */
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 7883e901f65c..100cb4343763 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -19,7 +19,8 @@
 
 struct pts_fs_info;
 
-struct pts_fs_info *devpts_acquire(struct file *, struct vfsmount **ptsmnt);
+struct vfsmount *devpts_mntget(struct file *, struct pts_fs_info *);
+struct pts_fs_info *devpts_acquire(struct file *);
 void devpts_release(struct pts_fs_info *);
 
 int devpts_new_index(struct pts_fs_info *);
@@ -32,6 +33,15 @@ void *devpts_get_priv(struct dentry *);
 /* unlink */
 void devpts_pty_kill(struct dentry *);
 
+/* in pty.c */
+int ptm_open_peer(struct file *master, struct tty_struct *tty, int flags);
+
+#else
+static inline int
+ptm_open_peer(struct file *master, struct tty_struct *tty, int flags)
+{
+	return -EIO;
+}
 #endif
 
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 03c0196a6f24..2189c79cde5d 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -10,6 +10,7 @@
 #include <linux/scatterlist.h>
 #include <linux/kmemcheck.h>
 #include <linux/bug.h>
+#include <linux/mem_encrypt.h>
 
 /**
  * List of possible attributes associated with a DMA mapping. The semantics
@@ -572,6 +573,12 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	return 0;
 }
 
+static inline void dma_check_mask(struct device *dev, u64 mask)
+{
+	if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1)))
+		dev_warn(dev, "SME is active, device will require DMA bounce buffers\n");
+}
+
 static inline int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -588,6 +595,9 @@ static inline int dma_set_mask(struct device *dev, u64 mask)
 {
 	if (!dev->dma_mask || !dma_supported(dev, mask))
 		return -EIO;
+
+	dma_check_mask(dev, mask);
+
 	*dev->dma_mask = mask;
 	return 0;
 }
@@ -607,6 +617,9 @@ static inline int dma_set_coherent_mask(struct device *dev, u64 mask)
 {
 	if (!dma_supported(dev, mask))
 		return -EIO;
+
+	dma_check_mask(dev, mask);
+
 	dev->coherent_dma_mask = mask;
 	return 0;
 }
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 8269bcb8ccf7..4e47f78430be 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -985,7 +985,7 @@ static inline void efi_esrt_init(void) { }
 extern int efi_config_parse_tables(void *config_tables, int count, int sz,
 				   efi_config_table_type_t *arch_tables);
 extern u64 efi_get_iobase (void);
-extern u32 efi_mem_type (unsigned long phys_addr);
+extern int efi_mem_type(unsigned long phys_addr);
 extern u64 efi_mem_attributes (unsigned long phys_addr);
 extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size);
 extern int __init efi_uart_console_only (void);
@@ -1091,6 +1091,8 @@ static inline bool efi_enabled(int feature)
 	return test_bit(feature, &efi.flags) != 0;
 }
 extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused);
+
+extern bool efi_is_table_address(unsigned long phys_addr);
 #else
 static inline bool efi_enabled(int feature)
 {
@@ -1104,6 +1106,11 @@ efi_capsule_pending(int *reset_type)
 {
 	return false;
 }
+
+static inline bool efi_is_table_address(unsigned long phys_addr)
+{
+	return false;
+}
 #endif
 
 extern int efi_status_to_err(efi_status_t status);
diff --git a/include/linux/io.h b/include/linux/io.h
index 2195d9ea4aaa..32e30e8fb9db 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -157,6 +157,8 @@ enum {
 	MEMREMAP_WB = 1 << 0,
 	MEMREMAP_WT = 1 << 1,
 	MEMREMAP_WC = 1 << 2,
+	MEMREMAP_ENC = 1 << 3,
+	MEMREMAP_DEC = 1 << 4,
 };
 
 void *memremap(resource_size_t offset, size_t size, unsigned long flags);
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index dd056fab9e35..2b7590f5483a 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -327,6 +327,14 @@ static inline void *boot_phys_to_virt(unsigned long entry)
 	return phys_to_virt(boot_phys_to_phys(entry));
 }
 
+#ifndef arch_kexec_post_alloc_pages
+static inline int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp) { return 0; }
+#endif
+
+#ifndef arch_kexec_pre_free_pages
+static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { }
+#endif
+
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h
new file mode 100644
index 000000000000..1255f09f5e42
--- /dev/null
+++ b/include/linux/mem_encrypt.h
@@ -0,0 +1,48 @@
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ *
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ *
+ * 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.
+ */
+
+#ifndef __MEM_ENCRYPT_H__
+#define __MEM_ENCRYPT_H__
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_ARCH_HAS_MEM_ENCRYPT
+
+#include <asm/mem_encrypt.h>
+
+#else	/* !CONFIG_ARCH_HAS_MEM_ENCRYPT */
+
+#define sme_me_mask	0UL
+
+#endif	/* CONFIG_ARCH_HAS_MEM_ENCRYPT */
+
+static inline bool sme_active(void)
+{
+	return !!sme_me_mask;
+}
+
+static inline unsigned long sme_get_me_mask(void)
+{
+	return sme_me_mask;
+}
+
+/*
+ * The __sme_set() and __sme_clr() macros are useful for adding or removing
+ * the encryption mask from a value (e.g. when dealing with pagetable
+ * entries).
+ */
+#define __sme_set(x)		((unsigned long)(x) | sme_me_mask)
+#define __sme_clr(x)		((unsigned long)(x) & ~sme_me_mask)
+
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* __MEM_ENCRYPT_H__ */
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index e030a68ead7e..25438b2b6f22 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -126,4 +126,10 @@ static __always_inline enum lru_list page_lru(struct page *page)
 
 #define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
 
+#ifdef arch_unmap_kpfn
+extern void arch_unmap_kpfn(unsigned long pfn);
+#else
+static __always_inline void arch_unmap_kpfn(unsigned long pfn) { }
+#endif
+
 #endif
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 4d179316e431..719582744a2e 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -8,7 +8,9 @@ enum pid_type
 	PIDTYPE_PID,
 	PIDTYPE_PGID,
 	PIDTYPE_SID,
-	PIDTYPE_MAX
+	PIDTYPE_MAX,
+	/* only valid to __task_pid_nr_ns() */
+	__PIDTYPE_TGID
 };
 
 /*
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index d8c97ec8a8e6..37b4bb2545b3 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -436,9 +436,9 @@ static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r,
 	__PTR_RING_PEEK_CALL_v; \
 })
 
-static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp)
+static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp)
 {
-	return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp);
+	return kcalloc(size, sizeof(void *), gfp);
 }
 
 static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
@@ -582,7 +582,8 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
  * In particular if you consume ring in interrupt or BH context, you must
  * disable interrupts/BH when doing so.
  */
-static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
+static inline int ptr_ring_resize_multiple(struct ptr_ring **rings,
+					   unsigned int nrings,
 					   int size,
 					   gfp_t gfp, void (*destroy)(void *))
 {
@@ -590,7 +591,7 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
 	void ***queues;
 	int i;
 
-	queues = kmalloc(nrings * sizeof *queues, gfp);
+	queues = kmalloc_array(nrings, sizeof(*queues), gfp);
 	if (!queues)
 		goto noqueues;
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8337e2db0bb2..c05ac5f5aa03 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1163,13 +1163,6 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk)
 	return tsk->tgid;
 }
 
-extern pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
-
-static inline pid_t task_tgid_vnr(struct task_struct *tsk)
-{
-	return pid_vnr(task_tgid(tsk));
-}
-
 /**
  * pid_alive - check that a task structure is not stale
  * @p: Task structure to be checked.
@@ -1185,23 +1178,6 @@ static inline int pid_alive(const struct task_struct *p)
 	return p->pids[PIDTYPE_PID].pid != NULL;
 }
 
-static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
-{
-	pid_t pid = 0;
-
-	rcu_read_lock();
-	if (pid_alive(tsk))
-		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
-	rcu_read_unlock();
-
-	return pid;
-}
-
-static inline pid_t task_ppid_nr(const struct task_struct *tsk)
-{
-	return task_ppid_nr_ns(tsk, &init_pid_ns);
-}
-
 static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 {
 	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
@@ -1223,6 +1199,33 @@ static inline pid_t task_session_vnr(struct task_struct *tsk)
 	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
 }
 
+static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, ns);
+}
+
+static inline pid_t task_tgid_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, NULL);
+}
+
+static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
+{
+	pid_t pid = 0;
+
+	rcu_read_lock();
+	if (pid_alive(tsk))
+		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+static inline pid_t task_ppid_nr(const struct task_struct *tsk)
+{
+	return task_ppid_nr_ns(tsk, &init_pid_ns);
+}
+
 /* Obsolete, do not use: */
 static inline pid_t task_pgrp_nr(struct task_struct *tsk)
 {
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
index 35226cd4efb0..8621ffdeecbf 100644
--- a/include/linux/skb_array.h
+++ b/include/linux/skb_array.h
@@ -193,7 +193,8 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp)
 }
 
 static inline int skb_array_resize_multiple(struct skb_array **rings,
-					    int nrings, int size, gfp_t gfp)
+					    int nrings, unsigned int size,
+					    gfp_t gfp)
 {
 	BUILD_BUG_ON(offsetof(struct skb_array, ring));
 	return ptr_ring_resize_multiple((struct ptr_ring **)rings,
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 4ee479f2f355..15e7160751a8 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -35,6 +35,7 @@ int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
 extern unsigned long swiotlb_nr_tbl(void);
 unsigned long swiotlb_size_or_default(void);
 extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
+extern void __init swiotlb_update_mem_attributes(void);
 
 /*
  * Enumeration for sync targets
diff --git a/include/net/ip.h b/include/net/ip.h
index 821cedcc8e73..0cf7f5a65fe6 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -352,7 +352,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	    !forwarding)
 		return dst_mtu(dst);
 
-	return min(dst->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU);
 }
 
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
@@ -364,7 +364,7 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
 		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
 	}
 
-	return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
 }
 
 u32 ip_idents_reserve(u32 hash, int segs);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 1c123e2b2415..67f815e5d525 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -806,8 +806,11 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	old = *pold;
 	*pold = new;
 	if (old != NULL) {
-		qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
+		unsigned int qlen = old->q.qlen;
+		unsigned int backlog = old->qstats.backlog;
+
 		qdisc_reset(old);
+		qdisc_tree_reduce_backlog(old, qlen, backlog);
 	}
 	sch_tree_unlock(sch);
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 7c0632c7e870..aeeec62992ca 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -507,9 +507,7 @@ int sk_set_peek_off(struct sock *sk, int val);
 static inline int sk_peek_offset(struct sock *sk, int flags)
 {
 	if (unlikely(flags & MSG_PEEK)) {
-		s32 off = READ_ONCE(sk->sk_peek_off);
-		if (off >= 0)
-			return off;
+		return READ_ONCE(sk->sk_peek_off);
 	}
 
 	return 0;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b5732432bb29..88c32aba32f7 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1683,6 +1683,7 @@ struct ib_qp {
 	enum ib_qp_type		qp_type;
 	struct ib_rwq_ind_table *rwq_ind_tbl;
 	struct ib_qp_security  *qp_sec;
+	u8			port;
 };
 
 struct ib_mr {
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index a1266d318c85..6af198d8120b 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -57,6 +57,7 @@ struct scsi_pointer {
 /* for scmd->flags */
 #define SCMD_TAGGED		(1 << 0)
 #define SCMD_UNCHECKED_ISA_DMA	(1 << 1)
+#define SCMD_ZONE_WRITE_LOCK	(1 << 2)
 
 struct scsi_cmnd {
 	struct scsi_request req;