Merge tag 'v5.1-rc7' into x86/mm, to pick up fixes

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

Documentation/sysctl/vm.txt

@@ -866,14 +866,14 @@ The intent is that compaction has less work to do in the future and to
 increase the success rate of future high-order allocations such as SLUB
 allocations, THP and hugetlbfs pages.
 
-To make it sensible with respect to the watermark_scale_factor parameter,
-the unit is in fractions of 10,000. The default value of 15,000 means
-that up to 150% of the high watermark will be reclaimed in the event of
-a pageblock being mixed due to fragmentation. The level of reclaim is
-determined by the number of fragmentation events that occurred in the
-recent past. If this value is smaller than a pageblock then a pageblocks
-worth of pages will be reclaimed (e.g.  2MB on 64-bit x86). A boost factor
-of 0 will disable the feature.
+To make it sensible with respect to the watermark_scale_factor
+parameter, the unit is in fractions of 10,000. The default value of
+15,000 on !DISCONTIGMEM configurations means that up to 150% of the high
+watermark will be reclaimed in the event of a pageblock being mixed due
+to fragmentation. The level of reclaim is determined by the number of
+fragmentation events that occurred in the recent past. If this value is
+smaller than a pageblock then a pageblocks worth of pages will be reclaimed
+(e.g.  2MB on 64-bit x86). A boost factor of 0 will disable the feature.
 
 =============================================================
 

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Shy Crocodile
 
 # *DOCUMENTATION*

arch/arm/Kconfig

@@ -73,7 +73,7 @@ config ARM
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
 	select HAVE_EXIT_THREAD
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
-	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL
+	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)

arch/arm/Kconfig.debug

@@ -47,8 +47,8 @@ config DEBUG_WX
 
 choice
 	prompt "Choose kernel unwinder"
-	default UNWINDER_ARM if AEABI && !FUNCTION_GRAPH_TRACER
-	default UNWINDER_FRAME_POINTER if !AEABI || FUNCTION_GRAPH_TRACER
+	default UNWINDER_ARM if AEABI
+	default UNWINDER_FRAME_POINTER if !AEABI
 	help
 	  This determines which method will be used for unwinding kernel stack
 	  traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack,
@@ -65,7 +65,7 @@ config UNWINDER_FRAME_POINTER
 
 config UNWINDER_ARM
 	bool "ARM EABI stack unwinder"
-	depends on AEABI
+	depends on AEABI && !FUNCTION_GRAPH_TRACER
 	select ARM_UNWIND
 	help
 	  This option enables stack unwinding support in the kernel

arch/arm/boot/compressed/head.S

@@ -1438,7 +1438,21 @@ ENTRY(efi_stub_entry)
 
 		@ Preserve return value of efi_entry() in r4
 		mov	r4, r0
-		bl	cache_clean_flush
+
+		@ our cache maintenance code relies on CP15 barrier instructions
+		@ but since we arrived here with the MMU and caches configured
+		@ by UEFI, we must check that the CP15BEN bit is set in SCTLR.
+		@ Note that this bit is RAO/WI on v6 and earlier, so the ISB in
+		@ the enable path will be executed on v7+ only.
+		mrc	p15, 0, r1, c1, c0, 0	@ read SCTLR
+		tst	r1, #(1 << 5)		@ CP15BEN bit set?
+		bne	0f
+		orr	r1, r1, #(1 << 5)	@ CP15 barrier instructions
+		mcr	p15, 0, r1, c1, c0, 0	@ write SCTLR
+ ARM(		.inst	0xf57ff06f		@ v7+ isb	)
+ THUMB(		isb						)
+
+0:		bl	cache_clean_flush
 		bl	cache_off
 
 		@ Set parameters for booting zImage according to boot protocol

arch/arm/kernel/head-nommu.S

@@ -133,9 +133,9 @@ __secondary_data:
  */
 	.text
 __after_proc_init:
-#ifdef CONFIG_ARM_MPU
 M_CLASS(movw	r12, #:lower16:BASEADDR_V7M_SCB)
 M_CLASS(movt	r12, #:upper16:BASEADDR_V7M_SCB)
+#ifdef CONFIG_ARM_MPU
 M_CLASS(ldr	r3, [r12, 0x50])
 AR_CLASS(mrc	p15, 0, r3, c0, c1, 4)          @ Read ID_MMFR0
 	and	r3, r3, #(MMFR0_PMSA)           @ PMSA field

arch/arm64/kernel/ftrace.c

@@ -103,10 +103,15 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		 * to be revisited if support for multiple ftrace entry points
 		 * is added in the future, but for now, the pr_err() below
 		 * deals with a theoretical issue only.
+		 *
+		 * Note that PLTs are place relative, and plt_entries_equal()
+		 * checks whether they point to the same target. Here, we need
+		 * to check if the actual opcodes are in fact identical,
+		 * regardless of the offset in memory so use memcmp() instead.
 		 */
 		trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
-		if (!plt_entries_equal(mod->arch.ftrace_trampoline,
-				       &trampoline)) {
+		if (memcmp(mod->arch.ftrace_trampoline, &trampoline,
+			   sizeof(trampoline))) {
 			if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
 				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
 				return -EINVAL;

arch/arm64/mm/init.c

@@ -363,7 +363,7 @@ void __init arm64_memblock_init(void)
 		 * Otherwise, this is a no-op
 		 */
 		u64 base = phys_initrd_start & PAGE_MASK;
-		u64 size = PAGE_ALIGN(phys_initrd_size);
+		u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base;
 
 		/*
 		 * We can only add back the initrd memory if we don't end up

arch/powerpc/configs/skiroot_defconfig

@@ -266,6 +266,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_HUGETLBFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_NLS=y

arch/powerpc/mm/mmu_context_iommu.c

@@ -95,28 +95,15 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 			      unsigned long entries, unsigned long dev_hpa,
 			      struct mm_iommu_table_group_mem_t **pmem)
 {
-	struct mm_iommu_table_group_mem_t *mem;
-	long i, ret, locked_entries = 0;
+	struct mm_iommu_table_group_mem_t *mem, *mem2;
+	long i, ret, locked_entries = 0, pinned = 0;
 	unsigned int pageshift;
-
-	mutex_lock(&mem_list_mutex);
-
-	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
-			next) {
-		/* Overlap? */
-		if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
-				(ua < (mem->ua +
-				       (mem->entries << PAGE_SHIFT)))) {
-			ret = -EINVAL;
-			goto unlock_exit;
-		}
-
-	}
+	unsigned long entry, chunk;
 
 	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
 		ret = mm_iommu_adjust_locked_vm(mm, entries, true);
 		if (ret)
-			goto unlock_exit;
+			return ret;
 
 		locked_entries = entries;
 	}
@@ -148,17 +135,27 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	}
 
 	down_read(&mm->mmap_sem);
-	ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+	chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) /
+			sizeof(struct vm_area_struct *);
+	chunk = min(chunk, entries);
+	for (entry = 0; entry < entries; entry += chunk) {
+		unsigned long n = min(entries - entry, chunk);
+
+		ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n,
+				FOLL_WRITE, mem->hpages + entry, NULL);
+		if (ret == n) {
+			pinned += n;
+			continue;
+		}
+		if (ret > 0)
+			pinned += ret;
+		break;
+	}
 	up_read(&mm->mmap_sem);
-	if (ret != entries) {
-		/* free the reference taken */
-		for (i = 0; i < ret; i++)
-			put_page(mem->hpages[i]);
-
-		vfree(mem->hpas);
-		kfree(mem);
-		ret = -EFAULT;
-		goto unlock_exit;
+	if (pinned != entries) {
+		if (!ret)
+			ret = -EFAULT;
+		goto free_exit;
 	}
 
 	pageshift = PAGE_SHIFT;
@@ -183,21 +180,43 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	}
 
 good_exit:
-	ret = 0;
 	atomic64_set(&mem->mapped, 1);
 	mem->used = 1;
 	mem->ua = ua;
 	mem->entries = entries;
-	*pmem = mem;
 
-	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
+	mutex_lock(&mem_list_mutex);
 
-unlock_exit:
-	if (locked_entries && ret)
-		mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+	list_for_each_entry_rcu(mem2, &mm->context.iommu_group_mem_list, next) {
+		/* Overlap? */
+		if ((mem2->ua < (ua + (entries << PAGE_SHIFT))) &&
+				(ua < (mem2->ua +
+				       (mem2->entries << PAGE_SHIFT)))) {
+			ret = -EINVAL;
+			mutex_unlock(&mem_list_mutex);
+			goto free_exit;
+		}
+	}
+
+	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
 
 	mutex_unlock(&mem_list_mutex);
 
+	*pmem = mem;
+
+	return 0;
+
+free_exit:
+	/* free the reference taken */
+	for (i = 0; i < pinned; i++)
+		put_page(mem->hpages[i]);
+
+	vfree(mem->hpas);
+	kfree(mem);
+
+unlock_exit:
+	mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+
 	return ret;
 }
 
@@ -266,7 +285,7 @@ static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
 long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 {
 	long ret = 0;
-	unsigned long entries, dev_hpa;
+	unsigned long unlock_entries = 0;
 
 	mutex_lock(&mem_list_mutex);
 
@@ -287,17 +306,17 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 		goto unlock_exit;
 	}
 
+	if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+		unlock_entries = mem->entries;
+
 	/* @mapped became 0 so now mappings are disabled, release the region */
-	entries = mem->entries;
-	dev_hpa = mem->dev_hpa;
 	mm_iommu_release(mem);
 
-	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
-		mm_iommu_adjust_locked_vm(mm, entries, false);
-
 unlock_exit:
 	mutex_unlock(&mem_list_mutex);
 
+	mm_iommu_adjust_locked_vm(mm, unlock_entries, false);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mm_iommu_put);

arch/powerpc/platforms/Kconfig.cputype

@@ -324,7 +324,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 
 config PPC_RADIX_MMU
 	bool "Radix MMU Support"
-	depends on PPC_BOOK3S_64
+	depends on PPC_BOOK3S_64 && HUGETLB_PAGE
 	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
 	default y
 	help

arch/x86/boot/compressed/misc.c

@@ -352,7 +352,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	boot_params->hdr.loadflags &= ~KASLR_FLAG;
 
 	/* Save RSDP address for later use. */
-	boot_params->acpi_rsdp_addr = get_rsdp_addr();
+	/* boot_params->acpi_rsdp_addr = get_rsdp_addr(); */
 
 	sanitize_boot_params(boot_params);
 

arch/x86/events/intel/cstate.c

@@ -76,15 +76,15 @@
  *			       Scope: Package (physical package)
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
- *			       Available model: HSW ULT,CNL
+ *			       Available model: HSW ULT,KBL,CNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
- *			       Available model: HSW ULT,CNL
+ *			       Available model: HSW ULT,KBL,CNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,GLM,CNL
+ *			       Available model: HSW ULT,KBL,GLM,CNL
  *			       Scope: Package (physical package)
  *
  */
@@ -566,8 +566,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  hswult_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, hswult_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates),
 

arch/x86/mm/init.c

@@ -5,6 +5,7 @@
 #include <linux/memblock.h>
 #include <linux/swapfile.h>
 #include <linux/swapops.h>
+#include <linux/kmemleak.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>
@@ -766,6 +767,11 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
 	if (debug_pagealloc_enabled()) {
 		pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n",
 			begin, end - 1);
+		/*
+		 * Inform kmemleak about the hole in the memory since the
+		 * corresponding pages will be unmapped.
+		 */
+		kmemleak_free_part((void *)begin, end - begin);
 		set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
 	} else {
 		/*

drivers/block/zram/zram_drv.c

@@ -774,18 +774,18 @@ struct zram_work {
 	struct zram *zram;
 	unsigned long entry;
 	struct bio *bio;
+	struct bio_vec bvec;
 };
 
 #if PAGE_SIZE != 4096
 static void zram_sync_read(struct work_struct *work)
 {
-	struct bio_vec bvec;
 	struct zram_work *zw = container_of(work, struct zram_work, work);
 	struct zram *zram = zw->zram;
 	unsigned long entry = zw->entry;
 	struct bio *bio = zw->bio;
 
-	read_from_bdev_async(zram, &bvec, entry, bio);
+	read_from_bdev_async(zram, &zw->bvec, entry, bio);
 }
 
 /*
@@ -798,6 +798,7 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
 {
 	struct zram_work work;
 
+	work.bvec = *bvec;
 	work.zram = zram;
 	work.entry = entry;
 	work.bio = bio;

drivers/dma/bcm2835-dma.c

@@ -671,7 +671,7 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_slave_sg(
 	d = bcm2835_dma_create_cb_chain(chan, direction, false,
 					info, extra,
 					frames, src, dst, 0, 0,
-					GFP_KERNEL);
+					GFP_NOWAIT);
 	if (!d)
 		return NULL;
 

drivers/dma/mediatek/mtk-cqdma.c

@@ -253,7 +253,7 @@ static void mtk_cqdma_start(struct mtk_cqdma_pchan *pc,
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 	mtk_dma_set(pc, MTK_CQDMA_DST2, cvd->dest >> MTK_CQDMA_ADDR2_SHFIT);
 #else
-	mtk_dma_set(pc, MTK_CQDMA_SRC2, 0);
+	mtk_dma_set(pc, MTK_CQDMA_DST2, 0);
 #endif
 
 	/* setup the length */

drivers/dma/sh/rcar-dmac.c

@@ -1282,6 +1282,9 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	enum dma_status status;
 	unsigned int residue = 0;
 	unsigned int dptr = 0;
+	unsigned int chcrb;
+	unsigned int tcrb;
+	unsigned int i;
 
 	if (!desc)
 		return 0;
@@ -1329,6 +1332,24 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 		return 0;
 	}
 
+	/*
+	 * We need to read two registers.
+	 * Make sure the control register does not skip to next chunk
+	 * while reading the counter.
+	 * Trying it 3 times should be enough: Initial read, retry, retry
+	 * for the paranoid.
+	 */
+	for (i = 0; i < 3; i++) {
+		chcrb = rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+					    RCAR_DMACHCRB_DPTR_MASK;
+		tcrb = rcar_dmac_chan_read(chan, RCAR_DMATCRB);
+		/* Still the same? */
+		if (chcrb == (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+			      RCAR_DMACHCRB_DPTR_MASK))
+			break;
+	}
+	WARN_ONCE(i >= 3, "residue might be not continuous!");
+
 	/*
 	 * In descriptor mode the descriptor running pointer is not maintained
 	 * by the interrupt handler, find the running descriptor from the
@@ -1336,8 +1357,7 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	 * mode just use the running descriptor pointer.
 	 */
 	if (desc->hwdescs.use) {
-		dptr = (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
-			RCAR_DMACHCRB_DPTR_MASK) >> RCAR_DMACHCRB_DPTR_SHIFT;
+		dptr = chcrb >> RCAR_DMACHCRB_DPTR_SHIFT;
 		if (dptr == 0)
 			dptr = desc->nchunks;
 		dptr--;
@@ -1355,7 +1375,7 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	}
 
 	/* Add the residue for the current chunk. */
-	residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;
+	residue += tcrb << desc->xfer_shift;
 
 	return residue;
 }
@@ -1368,6 +1388,7 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
 	enum dma_status status;
 	unsigned long flags;
 	unsigned int residue;
+	bool cyclic;
 
 	status = dma_cookie_status(chan, cookie, txstate);
 	if (status == DMA_COMPLETE || !txstate)
@@ -1375,10 +1396,11 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
 
 	spin_lock_irqsave(&rchan->lock, flags);
 	residue = rcar_dmac_chan_get_residue(rchan, cookie);
+	cyclic = rchan->desc.running ? rchan->desc.running->cyclic : false;
 	spin_unlock_irqrestore(&rchan->lock, flags);
 
 	/* if there's no residue, the cookie is complete */
-	if (!residue)
+	if (!residue && !cyclic)
 		return DMA_COMPLETE;
 
 	dma_set_residue(txstate, residue);

drivers/gpio/gpio-eic-sprd.c

@@ -414,6 +414,7 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_BOTH:
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;

drivers/gpio/gpiolib.c

@@ -1379,7 +1379,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 
 	status = gpiochip_add_irqchip(chip, lock_key, request_key);
 	if (status)
-		goto err_remove_chip;
+		goto err_free_gpiochip_mask;
 
 	status = of_gpiochip_add(chip);
 	if (status)
@@ -1387,7 +1387,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 
 	status = gpiochip_init_valid_mask(chip);
 	if (status)
-		goto err_remove_chip;
+		goto err_remove_of_chip;
 
 	for (i = 0; i < chip->ngpio; i++) {
 		struct gpio_desc *desc = &gdev->descs[i];
@@ -1415,14 +1415,18 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 	if (gpiolib_initialized) {
 		status = gpiochip_setup_dev(gdev);
 		if (status)
-			goto err_remove_chip;
+			goto err_remove_acpi_chip;
 	}
 	return 0;
 
-err_remove_chip:
+err_remove_acpi_chip:
 	acpi_gpiochip_remove(chip);
+err_remove_of_chip:
 	gpiochip_free_hogs(chip);
 	of_gpiochip_remove(chip);
+err_remove_chip:
+	gpiochip_irqchip_remove(chip);
+err_free_gpiochip_mask:
 	gpiochip_free_valid_mask(chip);
 err_remove_irqchip_mask:
 	gpiochip_irqchip_free_valid_mask(chip);