Merge branch 'nfs-rdma'

Documentation/x86/intel_mpx.txt

@@ -45,7 +45,7 @@ is how we expect the compiler, application and kernel to work together.
    MPX-instrumented.
 3) The kernel detects that the CPU has MPX, allows the new prctl() to
    succeed, and notes the location of the bounds directory. Userspace is
-   expected to keep the bounds directory at that locationWe note it
+   expected to keep the bounds directory at that location. We note it
    instead of reading it each time because the 'xsave' operation needed
    to access the bounds directory register is an expensive operation.
 4) If the application needs to spill bounds out of the 4 registers, it
@@ -167,7 +167,7 @@ If a #BR is generated due to a bounds violation caused by MPX.
 We need to decode MPX instructions to get violation address and
 set this address into extended struct siginfo.
 
-The _sigfault feild of struct siginfo is extended as follow:
+The _sigfault field of struct siginfo is extended as follow:
 
 87		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
 88		struct {
@@ -240,5 +240,5 @@ them at the same bounds table.
 This is allowed architecturally.  See more information "Intel(R) Architecture
 Instruction Set Extensions Programming Reference" (9.3.4).
 
-However, if users did this, the kernel might be fooled in to unmaping an
+However, if users did this, the kernel might be fooled in to unmapping an
 in-use bounds table since it does not recognize sharing.

Documentation/x86/tlb.txt

@@ -5,7 +5,7 @@ memory, it has two choices:
     from areas other than the one we are trying to flush will be
     destroyed and must be refilled later, at some cost.
  2. Use the invlpg instruction to invalidate a single page at a
-    time.  This could potentialy cost many more instructions, but
+    time.  This could potentially cost many more instructions, but
     it is a much more precise operation, causing no collateral
     damage to other TLB entries.
 
@@ -19,7 +19,7 @@ Which method to do depends on a few things:
     work.
  3. The size of the TLB.  The larger the TLB, the more collateral
     damage we do with a full flush.  So, the larger the TLB, the
-    more attrative an individual flush looks.  Data and
+    more attractive an individual flush looks.  Data and
     instructions have separate TLBs, as do different page sizes.
  4. The microarchitecture.  The TLB has become a multi-level
     cache on modern CPUs, and the global flushes have become more

Documentation/x86/x86_64/machinecheck

@@ -36,7 +36,7 @@ between all CPUs.
 
 check_interval
 	How often to poll for corrected machine check errors, in seconds
-	(Note output is hexademical). Default 5 minutes.  When the poller
+	(Note output is hexadecimal). Default 5 minutes.  When the poller
 	finds MCEs it triggers an exponential speedup (poll more often) on
 	the polling interval.  When the poller stops finding MCEs, it
 	triggers an exponential backoff (poll less often) on the polling

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc7
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*

arch/arm64/include/asm/cputype.h

@@ -80,12 +80,14 @@
 #define APM_CPU_PART_POTENZA		0x000
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
+#define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
 
 #define BRCM_CPU_PART_VULCAN		0x516
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
+#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 
 #ifndef __ASSEMBLY__
 

arch/arm64/include/asm/ptrace.h

@@ -117,6 +117,8 @@ struct pt_regs {
 	};
 	u64 orig_x0;
 	u64 syscallno;
+	u64 orig_addr_limit;
+	u64 unused;	// maintain 16 byte alignment
 };
 
 #define arch_has_single_step()	(1)

arch/arm64/kernel/asm-offsets.c

@@ -60,6 +60,7 @@ int main(void)
   DEFINE(S_PC,			offsetof(struct pt_regs, pc));
   DEFINE(S_ORIG_X0,		offsetof(struct pt_regs, orig_x0));
   DEFINE(S_SYSCALLNO,		offsetof(struct pt_regs, syscallno));
+  DEFINE(S_ORIG_ADDR_LIMIT,	offsetof(struct pt_regs, orig_addr_limit));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id.counter));

arch/arm64/kernel/cpu_errata.c

@@ -98,6 +98,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_RANGE(MIDR_THUNDERX, 0x00,
 			   (1 << MIDR_VARIANT_SHIFT) | 1),
 	},
+	{
+	/* Cavium ThunderX, T81 pass 1.0 */
+		.desc = "Cavium erratum 27456",
+		.capability = ARM64_WORKAROUND_CAVIUM_27456,
+		MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00),
+	},
 #endif
 	{
 	}

arch/arm64/kernel/entry.S

@@ -28,6 +28,7 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
+#include <asm/memory.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 
@@ -97,7 +98,14 @@
 	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
-	.endif
+	get_thread_info tsk
+	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+	ldr	x20, [tsk, #TI_ADDR_LIMIT]
+	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	mov	x20, #TASK_SIZE_64
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO)
+	.endif /* \el == 0 */
 	mrs	x22, elr_el1
 	mrs	x23, spsr_el1
 	stp	lr, x21, [sp, #S_LR]
@@ -128,6 +136,14 @@
 	.endm
 
 	.macro	kernel_exit, el
+	.if	\el != 0
+	/* Restore the task's original addr_limit. */
+	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+
+	/* No need to restore UAO, it will be restored from SPSR_EL1 */
+	.endif
+
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
@@ -406,7 +422,6 @@ el1_irq:
 	bl	trace_hardirqs_off
 #endif
 
-	get_thread_info tsk
 	irq_handler
 
 #ifdef CONFIG_PREEMPT

arch/arm64/mm/fault.c

@@ -280,7 +280,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	}
 
 	if (permission_fault(esr) && (addr < USER_DS)) {
-		if (get_fs() == KERNEL_DS)
+		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
+		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
 
 		if (!search_exception_tables(regs->pc))

arch/mips/include/asm/pgtable.h

@@ -24,7 +24,7 @@ struct mm_struct;
 struct vm_area_struct;
 
 #define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_NO_READ | \
-				 _CACHE_CACHABLE_NONCOHERENT)
+				 _page_cachable_default)
 #define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_WRITE | \
 				 _page_cachable_default)
 #define PAGE_COPY	__pgprot(_PAGE_PRESENT | _PAGE_NO_EXEC | \
@@ -476,7 +476,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	pte.pte_low  &= (_PAGE_MODIFIED | _PAGE_ACCESSED | _PFNX_MASK);
 	pte.pte_high &= (_PFN_MASK | _CACHE_MASK);
 	pte.pte_low  |= pgprot_val(newprot) & ~_PFNX_MASK;
-	pte.pte_high |= pgprot_val(newprot) & ~_PFN_MASK;
+	pte.pte_high |= pgprot_val(newprot) & ~(_PFN_MASK | _CACHE_MASK);
 	return pte;
 }
 #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
@@ -491,7 +491,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #else
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) |
+		     (pgprot_val(newprot) & ~_PAGE_CHG_MASK));
 }
 #endif
 
@@ -632,7 +633,8 @@ static inline struct page *pmd_page(pmd_t pmd)
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	pmd_val(pmd) = (pmd_val(pmd) & _PAGE_CHG_MASK) | pgprot_val(newprot);
+	pmd_val(pmd) = (pmd_val(pmd) & (_PAGE_CHG_MASK | _PAGE_HUGE)) |
+		       (pgprot_val(newprot) & ~_PAGE_CHG_MASK);
 	return pmd;
 }
 

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -230,6 +230,7 @@ extern unsigned long __kernel_virt_size;
 #define KERN_VIRT_SIZE  __kernel_virt_size
 extern struct page *vmemmap;
 extern unsigned long ioremap_bot;
+extern unsigned long pci_io_base;
 #endif /* __ASSEMBLY__ */
 
 #include <asm/book3s/64/hash.h>

arch/powerpc/kernel/eeh_driver.c

@@ -647,7 +647,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 			pci_unlock_rescan_remove();
 		}
 	} else if (frozen_bus) {
-		eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data);
+		eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
 	}
 
 	/*

arch/powerpc/kernel/pci_64.c

@@ -47,7 +47,6 @@ static int __init pcibios_init(void)
 
 	printk(KERN_INFO "PCI: Probing PCI hardware\n");
 
-	pci_io_base = ISA_IO_BASE;
 	/* For now, override phys_mem_access_prot. If we need it,g
 	 * later, we may move that initialization to each ppc_md
 	 */

arch/powerpc/kernel/process.c

@@ -1505,6 +1505,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 		current->thread.regs = regs - 1;
 	}
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * Clear any transactional state, we're exec()ing. The cause is
+	 * not important as there will never be a recheckpoint so it's not
+	 * user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+#endif
+
 	memset(regs->gpr, 0, sizeof(regs->gpr));
 	regs->ctr = 0;
 	regs->link = 0;

arch/powerpc/kernel/tm.S

@@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim)
 	std	r3, STK_PARAM(R3)(r1)
 	SAVE_NVGPRS(r1)
 
-	/* We need to setup MSR for VSX register save instructions.  Here we
-	 * also clear the MSR RI since when we do the treclaim, we won't have a
-	 * valid kernel pointer for a while.  We clear RI here as it avoids
-	 * adding another mtmsr closer to the treclaim.  This makes the region
-	 * maked as non-recoverable wider than it needs to be but it saves on
-	 * inserting another mtmsrd later.
-	 */
+	/* We need to setup MSR for VSX register save instructions. */
 	mfmsr	r14
 	mr	r15, r14
 	ori	r15, r15, MSR_FP
-	li	r16, MSR_RI
+	li	r16, 0
 	ori	r16, r16, MSR_EE /* IRQs hard off */
 	andc	r15, r15, r16
 	oris	r15, r15, MSR_VEC@h
@@ -176,7 +170,17 @@ dont_backup_fp:
 1:	tdeqi   r6, 0
 	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
 
-	/* The moment we treclaim, ALL of our GPRs will switch
+	/* Clear MSR RI since we are about to change r1, EE is already off. */
+	li	r4, 0
+	mtmsrd	r4, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 *
+	 * The moment we treclaim, ALL of our GPRs will switch
 	 * to user register state.  (FPRs, CCR etc. also!)
 	 * Use an sprg and a tm_scratch in the PACA to shuffle.
 	 */
@@ -197,6 +201,11 @@ dont_backup_fp:
 
 	/* Store the PPR in r11 and reset to decent value */
 	std	r11, GPR11(r1)			/* Temporary stash */
+
+	/* Reset MSR RI so we can take SLB faults again */
+	li	r11, MSR_RI
+	mtmsrd	r11, 1
+
 	mfspr	r11, SPRN_PPR
 	HMT_MEDIUM
 
@@ -397,11 +406,6 @@ restore_gprs:
 	ld	r5, THREAD_TM_DSCR(r3)
 	ld	r6, THREAD_TM_PPR(r3)
 
-	/* Clear the MSR RI since we are about to change R1.  EE is already off
-	 */
-	li	r4, 0
-	mtmsrd	r4, 1
-
 	REST_GPR(0, r7)				/* GPR0 */
 	REST_2GPRS(2, r7)			/* GPR2-3 */
 	REST_GPR(4, r7)				/* GPR4 */
@@ -439,10 +443,33 @@ restore_gprs:
 	ld	r6, _CCR(r7)
 	mtcr    r6
 
-	REST_GPR(1, r7)				/* GPR1 */
-	REST_GPR(5, r7)				/* GPR5-7 */
 	REST_GPR(6, r7)
-	ld	r7, GPR7(r7)
+
+	/*
+	 * Store r1 and r5 on the stack so that we can access them
+	 * after we clear MSR RI.
+	 */
+
+	REST_GPR(5, r7)
+	std	r5, -8(r1)
+	ld	r5, GPR1(r7)
+	std	r5, -16(r1)
+
+	REST_GPR(7, r7)
+
+	/* Clear MSR RI since we are about to change r1. EE is already off */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 */
+
+	ld	r5, -8(r1)
+	ld	r1, -16(r1)
 
 	/* Commit register state as checkpointed state: */
 	TRECHKPT

arch/powerpc/mm/hash_utils_64.c

@@ -922,6 +922,10 @@ void __init hash__early_init_mmu(void)
 	vmemmap = (struct page *)H_VMEMMAP_BASE;
 	ioremap_bot = IOREMAP_BASE;
 
+#ifdef CONFIG_PCI
+	pci_io_base = ISA_IO_BASE;
+#endif
+
 	/* Initialize the MMU Hash table and create the linear mapping
 	 * of memory. Has to be done before SLB initialization as this is
 	 * currently where the page size encoding is obtained.

arch/powerpc/mm/pgtable-radix.c

@@ -328,6 +328,11 @@ void __init radix__early_init_mmu(void)
 	__vmalloc_end = RADIX_VMALLOC_END;
 	vmemmap = (struct page *)RADIX_VMEMMAP_BASE;
 	ioremap_bot = IOREMAP_BASE;
+
+#ifdef CONFIG_PCI
+	pci_io_base = ISA_IO_BASE;
+#endif
+
 	/*
 	 * For now radix also use the same frag size
 	 */