Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton: "87 patches. Subsystems affected by this patch series: mm (pagecache and hugetlb), procfs, misc, MAINTAINERS, lib, checkpatch, binfmt, kallsyms, ramfs, init, codafs, nilfs2, hfs, crash_dump, signals, seq_file, fork, sysvfs, kcov, gdb, resource, selftests, and ipc" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (87 commits) ipc/ipc_sysctl.c: remove fallback for !CONFIG_PROC_SYSCTL ipc: check checkpoint_restore_ns_capable() to modify C/R proc files selftests/kselftest/runner/run_one(): allow running non-executable files virtio-mem: disallow mapping virtio-mem memory via /dev/mem kernel/resource: disallow access to exclusive system RAM regions kernel/resource: clean up and optimize iomem_is_exclusive() scripts/gdb: handle split debug for vmlinux kcov: replace local_irq_save() with a local_lock_t kcov: avoid enable+disable interrupts if !in_task() kcov: allocate per-CPU memory on the relevant node Documentation/kcov: define `ip' in the example Documentation/kcov: include types.h in the example sysv: use BUILD_BUG_ON instead of runtime check kernel/fork.c: unshare(): use swap() to make code cleaner seq_file: fix passing wrong private data seq_file: move seq_escape() to a header signal: remove duplicate include in signal.h crash_dump: remove duplicate include in crash_dump.h crash_dump: fix boolreturn.cocci warning hfs/hfsplus: use WARN_ON for sanity check ...
2026-01-06 11:08:10 -08:00 · 2021-11-09 10:11:53 -08:00
parent d2f38a3c65 0e9beb8a96
commit 59a2ceeef6
131 changed files with 1178 additions and 654 deletions
--- a/.mailmap
+++ b/.mailmap
@@ -73,6 +73,8 @@ Chris Chiu <chris.chiu@canonical.com> <chiu@endlessm.com>
 Chris Chiu <chris.chiu@canonical.com> <chiu@endlessos.org>
 Christophe Ricard <christophe.ricard@gmail.com>
 Christoph Hellwig <hch@lst.de>
+Colin Ian King <colin.king@intel.com> <colin.king@canonical.com>
+Colin Ian King <colin.king@intel.com> <colin.i.king@gmail.com>
 Corey Minyard <minyard@acm.org>
 Damian Hobson-Garcia <dhobsong@igel.co.jp>
 Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
--- a/Documentation/dev-tools/kcov.rst
+++ b/Documentation/dev-tools/kcov.rst
@@ -50,6 +50,7 @@ program using kcov:
    #include <sys/mman.h>
    #include <unistd.h>
    #include <fcntl.h>
+    #include <linux/types.h>

    #define KCOV_INIT_TRACE			_IOR('c', 1, unsigned long)
    #define KCOV_ENABLE			_IO('c', 100)
@@ -177,6 +178,8 @@ Comparison operands collection is similar to coverage collection:
 	/* Read number of comparisons collected. */
 	n = __atomic_load_n(&cover[0], __ATOMIC_RELAXED);
 	for (i = 0; i < n; i++) {
+		uint64_t ip;
+
 		type = cover[i * KCOV_WORDS_PER_CMP + 1];
 		/* arg1 and arg2 - operands of the comparison. */
 		arg1 = cover[i * KCOV_WORDS_PER_CMP + 2];
@@ -251,6 +254,8 @@ selectively from different subsystems.

 .. code-block:: c

+    /* Same includes and defines as above. */
+
    struct kcov_remote_arg {
 	__u32		trace_mode;
 	__u32		area_size;
--- a/21
+++ b/21
@@ -767,7 +767,7 @@ F:	drivers/crypto/allwinner/
 ALLWINNER HARDWARE SPINLOCK SUPPORT
 M:	Wilken Gottwalt <wilken.gottwalt@posteo.net>
 S:	Maintained
-F:	Documentation/devicetree/bindings/hwlock/allwinner,sun6i-hwspinlock.yaml
+F:	Documentation/devicetree/bindings/hwlock/allwinner,sun6i-a31-hwspinlock.yaml
 F:	drivers/hwspinlock/sun6i_hwspinlock.c

 ALLWINNER THERMAL DRIVER
@@ -2783,7 +2783,7 @@ F:	Documentation/devicetree/bindings/arm/toshiba.yaml
 F:	Documentation/devicetree/bindings/net/toshiba,visconti-dwmac.yaml
 F:	Documentation/devicetree/bindings/gpio/toshiba,gpio-visconti.yaml
 F:	Documentation/devicetree/bindings/pci/toshiba,visconti-pcie.yaml
-F:	Documentation/devicetree/bindings/pinctrl/toshiba,tmpv7700-pinctrl.yaml
+F:	Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml
 F:	Documentation/devicetree/bindings/watchdog/toshiba,visconti-wdt.yaml
 F:	arch/arm64/boot/dts/toshiba/
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
@@ -7119,6 +7119,20 @@ F:	include/uapi/linux/mdio.h
 F:	include/uapi/linux/mii.h
 F:	net/core/of_net.c

+EXEC & BINFMT API
+R:	Eric Biederman <ebiederm@xmission.com>
+R:	Kees Cook <keescook@chromium.org>
+F:	arch/alpha/kernel/binfmt_loader.c
+F:	arch/x86/ia32/ia32_aout.c
+F:	fs/*binfmt_*.c
+F:	fs/exec.c
+F:	include/linux/binfmts.h
+F:	include/linux/elf.h
+F:	include/uapi/linux/binfmts.h
+F:	tools/testing/selftests/exec/
+N:	asm/elf.h
+N:	binfmt
+
 EXFAT FILE SYSTEM
 M:	Namjae Jeon <linkinjeon@kernel.org>
 M:	Sungjong Seo <sj1557.seo@samsung.com>
@@ -8562,7 +8576,6 @@ M:	John Stultz <john.stultz@linaro.org>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	drivers/misc/hisi_hikey_usb.c
-F:	Documentation/devicetree/bindings/misc/hisilicon-hikey-usb.yaml

 HISILICON PMU DRIVER
 M:	Shaokun Zhang <zhangshaokun@hisilicon.com>
@@ -9621,7 +9634,7 @@ INTEL KEEM BAY DRM DRIVER
 M:	Anitha Chrisanthus <anitha.chrisanthus@intel.com>
 M:	Edmund Dea <edmund.j.dea@intel.com>
 S:	Maintained
-F:	Documentation/devicetree/bindings/display/intel,kmb_display.yaml
+F:	Documentation/devicetree/bindings/display/intel,keembay-display.yaml
 F:	drivers/gpu/drm/kmb/

 INTEL KEEM BAY OCS AES/SM4 CRYPTO DRIVER
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -129,9 +129,7 @@ dik_show_trace(unsigned long *sp, const char *loglvl)
 		extern char _stext[], _etext[];
 		unsigned long tmp = *sp;
 		sp++;
-		if (tmp < (unsigned long) &_stext)
-			continue;
-		if (tmp >= (unsigned long) &_etext)
+		if (!is_kernel_text(tmp))
 			continue;
 		printk("%s[<%lx>] %pSR\n", loglvl, tmp, (void *)tmp);
 		if (i > 40) {
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -34,6 +34,7 @@
 #include <linux/mm_types.h>
 #include <linux/pgtable.h>
 #include <linux/memblock.h>
+#include <linux/kallsyms.h>

 #include <asm/pgalloc.h>
 #include <linux/io.h>
@@ -171,7 +172,7 @@ void __init mapin_ram(void)
 	for (s = 0; s < lowmem_size; s += PAGE_SIZE) {
 		f = _PAGE_PRESENT | _PAGE_ACCESSED |
 				_PAGE_SHARED | _PAGE_HWEXEC;
-		if ((char *) v < _stext || (char *) v >= _etext)
+		if (!is_kernel_text(v))
 			f |= _PAGE_WRENABLE;
 		else
 			/* On the MicroBlaze, no user access
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -33,8 +33,6 @@

 #include <mm/mmu_decl.h>

-extern char etext[], _stext[], _sinittext[], _einittext[];
-
 static u8 early_fixmap_pagetable[FIXMAP_PTE_SIZE] __page_aligned_data;

 notrace void __init early_ioremap_init(void)
@@ -104,14 +102,13 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
 {
 	unsigned long v, s;
 	phys_addr_t p;
-	int ktext;
+	bool ktext;

 	s = offset;
 	v = PAGE_OFFSET + s;
 	p = memstart_addr + s;
 	for (; s < top; s += PAGE_SIZE) {
-		ktext = ((char *)v >= _stext && (char *)v < etext) ||
-			((char *)v >= _sinittext && (char *)v < _einittext);
+		ktext = core_kernel_text(v);
 		map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL);
 		v += PAGE_SIZE;
 		p += PAGE_SIZE;
--- a/arch/riscv/lib/delay.c
+++ b/arch/riscv/lib/delay.c
@@ -4,10 +4,14 @@
 */

 #include <linux/delay.h>
+#include <linux/math.h>
 #include <linux/param.h>
 #include <linux/timex.h>
+#include <linux/types.h>
 #include <linux/export.h>

+#include <asm/processor.h>
+
 /*
 * This is copies from arch/arm/include/asm/delay.h
 *
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -9,8 +9,12 @@
 #define __ASM_FACILITY_H

 #include <asm/facility-defs.h>
+
+#include <linux/minmax.h>
 #include <linux/string.h>
+#include <linux/types.h>
 #include <linux/preempt.h>
+
 #include <asm/lowcore.h>

 #define MAX_FACILITY_BIT (sizeof(stfle_fac_list) * 8)
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -73,12 +73,23 @@ static int gart_mem_pfn_is_ram(unsigned long pfn)
 		      (pfn >= aperture_pfn_start + aperture_page_count));
 }

+#ifdef CONFIG_PROC_VMCORE
+static bool gart_oldmem_pfn_is_ram(struct vmcore_cb *cb, unsigned long pfn)
+{
+	return !!gart_mem_pfn_is_ram(pfn);
+}
+
+static struct vmcore_cb gart_vmcore_cb = {
+	.pfn_is_ram = gart_oldmem_pfn_is_ram,
+};
+#endif
+
 static void __init exclude_from_core(u64 aper_base, u32 aper_order)
 {
 	aperture_pfn_start = aper_base >> PAGE_SHIFT;
 	aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT;
 #ifdef CONFIG_PROC_VMCORE
-	WARN_ON(register_oldmem_pfn_is_ram(&gart_mem_pfn_is_ram));
+	register_vmcore_cb(&gart_vmcore_cb);
 #endif
 #ifdef CONFIG_PROC_KCORE
 	WARN_ON(register_mem_pfn_is_ram(&gart_mem_pfn_is_ram));
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -175,7 +175,7 @@ static struct orc_entry *orc_find(unsigned long ip)
 	}

 	/* vmlinux .init slow lookup: */
-	if (init_kernel_text(ip))
+	if (is_kernel_inittext(ip))
 		return __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
 				  __stop_orc_unwind_ip - __start_orc_unwind_ip, ip);

--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -238,11 +238,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 	}
 }

-/*
- * The <linux/kallsyms.h> already defines is_kernel_text,
- * using '__' prefix not to get in conflict.
- */
-static inline int __is_kernel_text(unsigned long addr)
+static inline int is_x86_32_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end)
 		return 1;
@@ -333,8 +329,8 @@ repeat:
 				addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE +
 					PAGE_OFFSET + PAGE_SIZE-1;

-				if (__is_kernel_text(addr) ||
-				    __is_kernel_text(addr2))
+				if (is_x86_32_kernel_text(addr) ||
+				    is_x86_32_kernel_text(addr2))
 					prot = PAGE_KERNEL_LARGE_EXEC;

 				pages_2m++;
@@ -359,7 +355,7 @@ repeat:
 				 */
 				pgprot_t init_prot = __pgprot(PTE_IDENT_ATTR);

-				if (__is_kernel_text(addr))
+				if (is_x86_32_kernel_text(addr))
 					prot = PAGE_KERNEL_EXEC;

 				pages_4k++;
@@ -789,7 +785,7 @@ static void mark_nxdata_nx(void)
 	 */
 	unsigned long start = PFN_ALIGN(_etext);
 	/*
-	 * This comes from __is_kernel_text upper limit. Also HPAGE where used:
+	 * This comes from is_x86_32_kernel_text upper limit. Also HPAGE where used:
 	 */
 	unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start;

--- a/arch/x86/xen/mmu_hvm.c
+++ b/arch/x86/xen/mmu_hvm.c
@@ -9,39 +9,28 @@

 #ifdef CONFIG_PROC_VMCORE
 /*
- * This function is used in two contexts:
- * - the kdump kernel has to check whether a pfn of the crashed kernel
- *   was a ballooned page. vmcore is using this function to decide
- *   whether to access a pfn of the crashed kernel.
- * - the kexec kernel has to check whether a pfn was ballooned by the
- *   previous kernel. If the pfn is ballooned, handle it properly.
- * Returns 0 if the pfn is not backed by a RAM page, the caller may
+ * The kdump kernel has to check whether a pfn of the crashed kernel
+ * was a ballooned page. vmcore is using this function to decide
+ * whether to access a pfn of the crashed kernel.
+ * Returns "false" if the pfn is not backed by a RAM page, the caller may
 * handle the pfn special in this case.
 */
-static int xen_oldmem_pfn_is_ram(unsigned long pfn)
+static bool xen_vmcore_pfn_is_ram(struct vmcore_cb *cb, unsigned long pfn)
 {
 	struct xen_hvm_get_mem_type a = {
 		.domid = DOMID_SELF,
 		.pfn = pfn,
 	};
-	int ram;

-	if (HYPERVISOR_hvm_op(HVMOP_get_mem_type, &a))
-		return -ENXIO;
-
-	switch (a.mem_type) {
-	case HVMMEM_mmio_dm:
-		ram = 0;
-		break;
-	case HVMMEM_ram_rw:
-	case HVMMEM_ram_ro:
-	default:
-		ram = 1;
-		break;
+	if (HYPERVISOR_hvm_op(HVMOP_get_mem_type, &a)) {
+		pr_warn_once("Unexpected HVMOP_get_mem_type failure\n");
+		return true;
 	}
-
-	return ram;
+	return a.mem_type != HVMMEM_mmio_dm;
 }
+static struct vmcore_cb xen_vmcore_cb = {
+	.pfn_is_ram = xen_vmcore_pfn_is_ram,
+};
 #endif

 static void xen_hvm_exit_mmap(struct mm_struct *mm)
@@ -75,6 +64,6 @@ void __init xen_hvm_init_mmu_ops(void)
 	if (is_pagetable_dying_supported())
 		pv_ops.mmu.exit_mmap = xen_hvm_exit_mmap;
 #ifdef CONFIG_PROC_VMCORE
-	WARN_ON(register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram));
+	register_vmcore_cb(&xen_vmcore_cb);
 #endif
 }
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1668,13 +1668,10 @@ __dump_topology_ref_history(struct drm_dp_mst_topology_ref_history *history,
 	for (i = 0; i < history->len; i++) {
 		const struct drm_dp_mst_topology_ref_entry *entry =
 			&history->entries[i];
-		ulong *entries;
-		uint nr_entries;
 		u64 ts_nsec = entry->ts_nsec;
 		u32 rem_nsec = do_div(ts_nsec, 1000000000);

-		nr_entries = stack_depot_fetch(entry->backtrace, &entries);
-		stack_trace_snprint(buf, PAGE_SIZE, entries, nr_entries, 4);
+		stack_depot_snprint(entry->backtrace, buf, PAGE_SIZE, 4);

 		drm_printf(&p, "  %d %ss (last at %5llu.%06u):\n%s",
 			   entry->count,
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -118,8 +118,6 @@ static noinline void save_stack(struct drm_mm_node *node)
 static void show_leaks(struct drm_mm *mm)
 {
 	struct drm_mm_node *node;
-	unsigned long *entries;
-	unsigned int nr_entries;
 	char *buf;

 	buf = kmalloc(BUFSZ, GFP_KERNEL);
@@ -133,8 +131,7 @@ static void show_leaks(struct drm_mm *mm)
 			continue;
 		}

-		nr_entries = stack_depot_fetch(node->stack, &entries);
-		stack_trace_snprint(buf, BUFSZ, entries, nr_entries, 0);
+		stack_depot_snprint(node->stack, buf, BUFSZ, 0);
 		DRM_ERROR("node [%08llx + %08llx]: inserted at\n%s",
 			  node->start, node->size, buf);
 	}
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -56,8 +56,6 @@ void i915_vma_free(struct i915_vma *vma)

 static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 {
-	unsigned long *entries;
-	unsigned int nr_entries;
 	char buf[512];

 	if (!vma->node.stack) {
@@ -66,8 +64,7 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 		return;
 	}

-	nr_entries = stack_depot_fetch(vma->node.stack, &entries);
-	stack_trace_snprint(buf, sizeof(buf), entries, nr_entries, 0);
+	stack_depot_snprint(vma->node.stack, buf, sizeof(buf), 0);
 	DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n",
 			 vma->node.start, vma->node.size, reason, buf);
 }
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -65,16 +65,6 @@ static noinline depot_stack_handle_t __save_depot_stack(void)
 	return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN);
 }

-static void __print_depot_stack(depot_stack_handle_t stack,
-				char *buf, int sz, int indent)
-{
-	unsigned long *entries;
-	unsigned int nr_entries;
-
-	nr_entries = stack_depot_fetch(stack, &entries);
-	stack_trace_snprint(buf, sz, entries, nr_entries, indent);
-}
-
 static void init_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
 {
 	spin_lock_init(&rpm->debug.lock);
@@ -146,12 +136,12 @@ static void untrack_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm,
 		if (!buf)
 			return;

-		__print_depot_stack(stack, buf, PAGE_SIZE, 2);
+		stack_depot_snprint(stack, buf, PAGE_SIZE, 2);
 		DRM_DEBUG_DRIVER("wakeref %x from\n%s", stack, buf);

 		stack = READ_ONCE(rpm->debug.last_release);
 		if (stack) {
-			__print_depot_stack(stack, buf, PAGE_SIZE, 2);
+			stack_depot_snprint(stack, buf, PAGE_SIZE, 2);
 			DRM_DEBUG_DRIVER("wakeref last released at\n%s", buf);
 		}

@@ -183,12 +173,12 @@ __print_intel_runtime_pm_wakeref(struct drm_printer *p,
 		return;

 	if (dbg->last_acquire) {
-		__print_depot_stack(dbg->last_acquire, buf, PAGE_SIZE, 2);
+		stack_depot_snprint(dbg->last_acquire, buf, PAGE_SIZE, 2);
 		drm_printf(p, "Wakeref last acquired:\n%s", buf);
 	}

 	if (dbg->last_release) {
-		__print_depot_stack(dbg->last_release, buf, PAGE_SIZE, 2);
+		stack_depot_snprint(dbg->last_release, buf, PAGE_SIZE, 2);
 		drm_printf(p, "Wakeref last released:\n%s", buf);
 	}

@@ -203,7 +193,7 @@ __print_intel_runtime_pm_wakeref(struct drm_printer *p,
 		rep = 1;
 		while (i + 1 < dbg->count && dbg->owners[i + 1] == stack)
 			rep++, i++;
-		__print_depot_stack(stack, buf, PAGE_SIZE, 2);
+		stack_depot_snprint(stack, buf, PAGE_SIZE, 2);
 		drm_printf(p, "Wakeref x%lu taken at:\n%s", rep, buf);
 	}

--- a/drivers/media/dvb-frontends/cxd2880/cxd2880_common.h
+++ b/drivers/media/dvb-frontends/cxd2880/cxd2880_common.h
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
+#include <linux/bits.h>
 #include <linux/string.h>

 int cxd2880_convert2s_complement(u32 value, u32 bitlen);
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -111,6 +111,7 @@ config VIRTIO_MEM
 	depends on MEMORY_HOTPLUG
 	depends on MEMORY_HOTREMOVE
 	depends on CONTIG_ALLOC
+	depends on EXCLUSIVE_SYSTEM_RAM
 	help
 	 This driver provides access to virtio-mem paravirtualized memory
 	 devices, allowing to hotplug and hotunplug memory.
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -223,6 +223,9 @@ struct virtio_mem {
 	 * When this lock is held the pointers can't change, ONLINE and
 	 * OFFLINE blocks can't change the state and no subblocks will get
 	 * plugged/unplugged.
+	 *
+	 * In kdump mode, used to serialize requests, last_block_addr and
+	 * last_block_plugged.
 	 */
 	struct mutex hotplug_mutex;
 	bool hotplug_active;
@@ -230,6 +233,9 @@ struct virtio_mem {
 	/* An error occurred we cannot handle - stop processing requests. */
 	bool broken;

+	/* Cached valued of is_kdump_kernel() when the device was probed. */
+	bool in_kdump;
+
 	/* The driver is being removed. */
 	spinlock_t removal_lock;
 	bool removing;
@@ -243,6 +249,13 @@ struct virtio_mem {
 	/* Memory notifier (online/offline events). */
 	struct notifier_block memory_notifier;

+#ifdef CONFIG_PROC_VMCORE
+	/* vmcore callback for /proc/vmcore handling in kdump mode */
+	struct vmcore_cb vmcore_cb;
+	uint64_t last_block_addr;
+	bool last_block_plugged;
+#endif /* CONFIG_PROC_VMCORE */
+
 	/* Next device in the list of virtio-mem devices. */
 	struct list_head next;
 };
@@ -260,6 +273,8 @@ static void virtio_mem_fake_offline_going_offline(unsigned long pfn,
 static void virtio_mem_fake_offline_cancel_offline(unsigned long pfn,
 						   unsigned long nr_pages);
 static void virtio_mem_retry(struct virtio_mem *vm);
+static int virtio_mem_create_resource(struct virtio_mem *vm);
+static void virtio_mem_delete_resource(struct virtio_mem *vm);

 /*
 * Register a virtio-mem device so it will be considered for the online_page
@@ -2291,6 +2306,12 @@ static void virtio_mem_run_wq(struct work_struct *work)
 	uint64_t diff;
 	int rc;

+	if (unlikely(vm->in_kdump)) {
+		dev_warn_once(&vm->vdev->dev,
+			     "unexpected workqueue run in kdump kernel\n");
+		return;
+	}
+
 	hrtimer_cancel(&vm->retry_timer);

 	if (vm->broken)
@@ -2392,41 +2413,11 @@ static int virtio_mem_init_vq(struct virtio_mem *vm)
 	return 0;
 }

-static int virtio_mem_init(struct virtio_mem *vm)
+static int virtio_mem_init_hotplug(struct virtio_mem *vm)
 {
 	const struct range pluggable_range = mhp_get_pluggable_range(true);
-	uint64_t sb_size, addr;
-	uint16_t node_id;
-
-	if (!vm->vdev->config->get) {
-		dev_err(&vm->vdev->dev, "config access disabled\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * We don't want to (un)plug or reuse any memory when in kdump. The
-	 * memory is still accessible (but not mapped).
-	 */
-	if (is_kdump_kernel()) {
-		dev_warn(&vm->vdev->dev, "disabled in kdump kernel\n");
-		return -EBUSY;
-	}
-
-	/* Fetch all properties that can't change. */
-	virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
-			&vm->plugged_size);
-	virtio_cread_le(vm->vdev, struct virtio_mem_config, block_size,
-			&vm->device_block_size);
-	virtio_cread_le(vm->vdev, struct virtio_mem_config, node_id,
-			&node_id);
-	vm->nid = virtio_mem_translate_node_id(vm, node_id);
-	virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
-	virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size,
-			&vm->region_size);
-
-	/* Determine the nid for the device based on the lowest address. */
-	if (vm->nid == NUMA_NO_NODE)
-		vm->nid = memory_add_physaddr_to_nid(vm->addr);
+	uint64_t unit_pages, sb_size, addr;
+	int rc;

 	/* bad device setup - warn only */
 	if (!IS_ALIGNED(vm->addr, memory_block_size_bytes()))
@@ -2496,10 +2487,6 @@ static int virtio_mem_init(struct virtio_mem *vm)
 					      vm->offline_threshold);
 	}

-	dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr);
-	dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size);
-	dev_info(&vm->vdev->dev, "device block size: 0x%llx",
-		 (unsigned long long)vm->device_block_size);
 	dev_info(&vm->vdev->dev, "memory block size: 0x%lx",
 		 memory_block_size_bytes());
 	if (vm->in_sbm)
@@ -2508,10 +2495,170 @@ static int virtio_mem_init(struct virtio_mem *vm)
 	else
 		dev_info(&vm->vdev->dev, "big block size: 0x%llx",
 			 (unsigned long long)vm->bbm.bb_size);
+
+	/* create the parent resource for all memory */
+	rc = virtio_mem_create_resource(vm);
+	if (rc)
+		return rc;
+
+	/* use a single dynamic memory group to cover the whole memory device */
+	if (vm->in_sbm)
+		unit_pages = PHYS_PFN(memory_block_size_bytes());
+	else
+		unit_pages = PHYS_PFN(vm->bbm.bb_size);
+	rc = memory_group_register_dynamic(vm->nid, unit_pages);
+	if (rc < 0)
+		goto out_del_resource;
+	vm->mgid = rc;
+
+	/*
+	 * If we still have memory plugged, we have to unplug all memory first.
+	 * Registering our parent resource makes sure that this memory isn't
+	 * actually in use (e.g., trying to reload the driver).
+	 */
+	if (vm->plugged_size) {
+		vm->unplug_all_required = true;
+		dev_info(&vm->vdev->dev, "unplugging all memory is required\n");
+	}
+
+	/* register callbacks */
+	vm->memory_notifier.notifier_call = virtio_mem_memory_notifier_cb;
+	rc = register_memory_notifier(&vm->memory_notifier);
+	if (rc)
+		goto out_unreg_group;
+	rc = register_virtio_mem_device(vm);
+	if (rc)
+		goto out_unreg_mem;
+
+	return 0;
+out_unreg_mem:
+	unregister_memory_notifier(&vm->memory_notifier);
+out_unreg_group:
+	memory_group_unregister(vm->mgid);
+out_del_resource:
+	virtio_mem_delete_resource(vm);
+	return rc;
+}
+
+#ifdef CONFIG_PROC_VMCORE
+static int virtio_mem_send_state_request(struct virtio_mem *vm, uint64_t addr,
+					 uint64_t size)
+{
+	const uint64_t nb_vm_blocks = size / vm->device_block_size;
+	const struct virtio_mem_req req = {
+		.type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_STATE),
+		.u.state.addr = cpu_to_virtio64(vm->vdev, addr),
+		.u.state.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks),
+	};
+	int rc = -ENOMEM;
+
+	dev_dbg(&vm->vdev->dev, "requesting state: 0x%llx - 0x%llx\n", addr,
+		addr + size - 1);
+
+	switch (virtio_mem_send_request(vm, &req)) {
+	case VIRTIO_MEM_RESP_ACK:
+		return virtio16_to_cpu(vm->vdev, vm->resp.u.state.state);
+	case VIRTIO_MEM_RESP_ERROR:
+		rc = -EINVAL;
+		break;
+	default:
+		break;
+	}
+
+	dev_dbg(&vm->vdev->dev, "requesting state failed: %d\n", rc);
+	return rc;
+}
+
+static bool virtio_mem_vmcore_pfn_is_ram(struct vmcore_cb *cb,
+					 unsigned long pfn)
+{
+	struct virtio_mem *vm = container_of(cb, struct virtio_mem,
+					     vmcore_cb);
+	uint64_t addr = PFN_PHYS(pfn);
+	bool is_ram;
+	int rc;
+
+	if (!virtio_mem_contains_range(vm, addr, PAGE_SIZE))
+		return true;
+	if (!vm->plugged_size)
+		return false;
+
+	/*
+	 * We have to serialize device requests and access to the information
+	 * about the block queried last.
+	 */
+	mutex_lock(&vm->hotplug_mutex);
+
+	addr = ALIGN_DOWN(addr, vm->device_block_size);
+	if (addr != vm->last_block_addr) {
+		rc = virtio_mem_send_state_request(vm, addr,
+						   vm->device_block_size);
+		/* On any kind of error, we're going to signal !ram. */
+		if (rc == VIRTIO_MEM_STATE_PLUGGED)
+			vm->last_block_plugged = true;
+		else
+			vm->last_block_plugged = false;
+		vm->last_block_addr = addr;
+	}
+
+	is_ram = vm->last_block_plugged;
+	mutex_unlock(&vm->hotplug_mutex);
+	return is_ram;
+}
+#endif /* CONFIG_PROC_VMCORE */
+
+static int virtio_mem_init_kdump(struct virtio_mem *vm)
+{
+#ifdef CONFIG_PROC_VMCORE
+	dev_info(&vm->vdev->dev, "memory hot(un)plug disabled in kdump kernel\n");
+	vm->vmcore_cb.pfn_is_ram = virtio_mem_vmcore_pfn_is_ram;
+	register_vmcore_cb(&vm->vmcore_cb);
+	return 0;
+#else /* CONFIG_PROC_VMCORE */
+	dev_warn(&vm->vdev->dev, "disabled in kdump kernel without vmcore\n");
+	return -EBUSY;
+#endif /* CONFIG_PROC_VMCORE */
+}
+
+static int virtio_mem_init(struct virtio_mem *vm)
+{
+	uint16_t node_id;
+
+	if (!vm->vdev->config->get) {
+		dev_err(&vm->vdev->dev, "config access disabled\n");
+		return -EINVAL;
+	}
+
+	/* Fetch all properties that can't change. */
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
+			&vm->plugged_size);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, block_size,
+			&vm->device_block_size);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, node_id,
+			&node_id);
+	vm->nid = virtio_mem_translate_node_id(vm, node_id);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size,
+			&vm->region_size);
+
+	/* Determine the nid for the device based on the lowest address. */
+	if (vm->nid == NUMA_NO_NODE)
+		vm->nid = memory_add_physaddr_to_nid(vm->addr);
+
+	dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr);
+	dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size);
+	dev_info(&vm->vdev->dev, "device block size: 0x%llx",
+		 (unsigned long long)vm->device_block_size);
 	if (vm->nid != NUMA_NO_NODE && IS_ENABLED(CONFIG_NUMA))
 		dev_info(&vm->vdev->dev, "nid: %d", vm->nid);

-	return 0;
+	/*
+	 * We don't want to (un)plug or reuse any memory when in kdump. The
+	 * memory is still accessible (but not exposed to Linux).
+	 */
+	if (vm->in_kdump)
+		return virtio_mem_init_kdump(vm);
+	return virtio_mem_init_hotplug(vm);
 }

 static int virtio_mem_create_resource(struct virtio_mem *vm)
@@ -2525,8 +2672,10 @@ static int virtio_mem_create_resource(struct virtio_mem *vm)
 	if (!name)
 		return -ENOMEM;

+	/* Disallow mapping device memory via /dev/mem completely. */
 	vm->parent_resource = __request_mem_region(vm->addr, vm->region_size,
-						   name, IORESOURCE_SYSTEM_RAM);
+						   name, IORESOURCE_SYSTEM_RAM |
+						   IORESOURCE_EXCLUSIVE);
 	if (!vm->parent_resource) {
 		kfree(name);
 		dev_warn(&vm->vdev->dev, "could not reserve device region\n");
@@ -2571,7 +2720,6 @@ static bool virtio_mem_has_memory_added(struct virtio_mem *vm)
 static int virtio_mem_probe(struct virtio_device *vdev)
 {
 	struct virtio_mem *vm;
-	uint64_t unit_pages;
 	int rc;

 	BUILD_BUG_ON(sizeof(struct virtio_mem_req) != 24);
@@ -2590,6 +2738,7 @@ static int virtio_mem_probe(struct virtio_device *vdev)
 	hrtimer_init(&vm->retry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	vm->retry_timer.function = virtio_mem_timer_expired;
 	vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS;
+	vm->in_kdump = is_kdump_kernel();

 	/* register the virtqueue */
 	rc = virtio_mem_init_vq(vm);
@@ -2601,53 +2750,15 @@ static int virtio_mem_probe(struct virtio_device *vdev)
 	if (rc)
 		goto out_del_vq;

-	/* create the parent resource for all memory */
-	rc = virtio_mem_create_resource(vm);
-	if (rc)
-		goto out_del_vq;
-
-	/* use a single dynamic memory group to cover the whole memory device */
-	if (vm->in_sbm)
-		unit_pages = PHYS_PFN(memory_block_size_bytes());
-	else
-		unit_pages = PHYS_PFN(vm->bbm.bb_size);
-	rc = memory_group_register_dynamic(vm->nid, unit_pages);
-	if (rc < 0)
-		goto out_del_resource;
-	vm->mgid = rc;
-
-	/*
-	 * If we still have memory plugged, we have to unplug all memory first.
-	 * Registering our parent resource makes sure that this memory isn't
-	 * actually in use (e.g., trying to reload the driver).
-	 */
-	if (vm->plugged_size) {
-		vm->unplug_all_required = true;
-		dev_info(&vm->vdev->dev, "unplugging all memory is required\n");
-	}
-
-	/* register callbacks */
-	vm->memory_notifier.notifier_call = virtio_mem_memory_notifier_cb;
-	rc = register_memory_notifier(&vm->memory_notifier);
-	if (rc)
-		goto out_unreg_group;
-	rc = register_virtio_mem_device(vm);
-	if (rc)
-		goto out_unreg_mem;
-
 	virtio_device_ready(vdev);

 	/* trigger a config update to start processing the requested_size */
-	atomic_set(&vm->config_changed, 1);
-	queue_work(system_freezable_wq, &vm->wq);
+	if (!vm->in_kdump) {
+		atomic_set(&vm->config_changed, 1);
+		queue_work(system_freezable_wq, &vm->wq);
+	}

 	return 0;
-out_unreg_mem:
-	unregister_memory_notifier(&vm->memory_notifier);
-out_unreg_group:
-	memory_group_unregister(vm->mgid);
-out_del_resource:
-	virtio_mem_delete_resource(vm);
 out_del_vq:
 	vdev->config->del_vqs(vdev);
 out_free_vm:
@@ -2657,9 +2768,8 @@ out_free_vm:
 	return rc;
 }

-static void virtio_mem_remove(struct virtio_device *vdev)
+static void virtio_mem_deinit_hotplug(struct virtio_mem *vm)
 {
-	struct virtio_mem *vm = vdev->priv;
 	unsigned long mb_id;
 	int rc;

@@ -2706,7 +2816,8 @@ static void virtio_mem_remove(struct virtio_device *vdev)
 	 * away. Warn at least.
 	 */
 	if (virtio_mem_has_memory_added(vm)) {
-		dev_warn(&vdev->dev, "device still has system memory added\n");
+		dev_warn(&vm->vdev->dev,
+			 "device still has system memory added\n");
 	} else {
 		virtio_mem_delete_resource(vm);
 		kfree_const(vm->resource_name);
@@ -2720,6 +2831,23 @@ static void virtio_mem_remove(struct virtio_device *vdev)
 	} else {
 		vfree(vm->bbm.bb_states);
 	}
+}
+
+static void virtio_mem_deinit_kdump(struct virtio_mem *vm)
+{
+#ifdef CONFIG_PROC_VMCORE
+	unregister_vmcore_cb(&vm->vmcore_cb);
+#endif /* CONFIG_PROC_VMCORE */
+}
+
+static void virtio_mem_remove(struct virtio_device *vdev)
+{
+	struct virtio_mem *vm = vdev->priv;
+
+	if (vm->in_kdump)
+		virtio_mem_deinit_kdump(vm);
+	else
+		virtio_mem_deinit_hotplug(vm);

 	/* reset the device and cleanup the queues */
 	vdev->config->reset(vdev);
@@ -2733,6 +2861,9 @@ static void virtio_mem_config_changed(struct virtio_device *vdev)
 {
 	struct virtio_mem *vm = vdev->priv;

+	if (unlikely(vm->in_kdump))
+		return;
+
 	atomic_set(&vm->config_changed, 1);
 	virtio_mem_retry(vm);
 }
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -156,7 +156,7 @@ static int padzero(unsigned long elf_bss)
 #define STACK_ADD(sp, items) ((elf_addr_t __user *)(sp) - (items))
 #define STACK_ROUND(sp, items) \
 	(((unsigned long) (sp - items)) &~ 15UL)
-#define STACK_ALLOC(sp, len) ({ sp -= len ; sp; })
+#define STACK_ALLOC(sp, len) (sp -= len)
 #endif

 #ifndef ELF_BASE_PLATFORM
@@ -1074,20 +1074,26 @@ out_free_interp:

 		vaddr = elf_ppnt->p_vaddr;
 		/*
-		 * If we are loading ET_EXEC or we have already performed
-		 * the ET_DYN load_addr calculations, proceed normally.
+		 * The first time through the loop, load_addr_set is false:
+		 * layout will be calculated. Once set, use MAP_FIXED since
+		 * we know we've already safely mapped the entire region with
+		 * MAP_FIXED_NOREPLACE in the once-per-binary logic following.
 		 */
-		if (elf_ex->e_type == ET_EXEC || load_addr_set) {
+		if (load_addr_set) {
 			elf_flags |= MAP_FIXED;
+		} else if (elf_ex->e_type == ET_EXEC) {
+			/*
+			 * This logic is run once for the first LOAD Program
+			 * Header for ET_EXEC binaries. No special handling
+			 * is needed.
+			 */
+			elf_flags |= MAP_FIXED_NOREPLACE;
 		} else if (elf_ex->e_type == ET_DYN) {
 			/*
 			 * This logic is run once for the first LOAD Program
 			 * Header for ET_DYN binaries to calculate the
 			 * randomization (load_bias) for all the LOAD
-			 * Program Headers, and to calculate the entire
-			 * size of the ELF mapping (total_size). (Note that
-			 * load_addr_set is set to true later once the
-			 * initial mapping is performed.)
+			 * Program Headers.
 			 *
 			 * There are effectively two types of ET_DYN
 			 * binaries: programs (i.e. PIE: ET_DYN with INTERP)
@@ -1108,7 +1114,7 @@ out_free_interp:
 			 * Therefore, programs are loaded offset from
 			 * ELF_ET_DYN_BASE and loaders are loaded into the
 			 * independently randomized mmap region (0 load_bias
-			 * without MAP_FIXED).
+			 * without MAP_FIXED nor MAP_FIXED_NOREPLACE).
 			 */
 			if (interpreter) {
 				load_bias = ELF_ET_DYN_BASE;
@@ -1117,7 +1123,7 @@ out_free_interp:
 				alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
 				if (alignment)
 					load_bias &= ~(alignment - 1);
-				elf_flags |= MAP_FIXED;
+				elf_flags |= MAP_FIXED_NOREPLACE;
 			} else
 				load_bias = 0;

@@ -1129,7 +1135,14 @@ out_free_interp:
 			 * is then page aligned.
 			 */
 			load_bias = ELF_PAGESTART(load_bias - vaddr);
+		}

+		/*
+		 * Calculate the entire size of the ELF mapping (total_size).
+		 * (Note that load_addr_set is set to true later once the
+		 * initial mapping is performed.)
+		 */
+		if (!load_addr_set) {
 			total_size = total_mapping_size(elf_phdata,
 							elf_ex->e_phnum);
 			if (!total_size) {
--- a/Show More
+++ b/Show More