Merge: x86/kaslr: Expose and use the end of the physical memory address space

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/5273

JIRA: https://issues.redhat.com/browse/RHEL-55130    
JIRA: https://issues.redhat.com/browse/RHEL-55196    
JIRA: https://issues.redhat.com/browse/RHEL-58584

commit ea72ce5da22806d5713f3ffb39a6d5ae73841f93    
Author: Thomas Gleixner <tglx@linutronix.de>    
Date:   Wed, 14 Aug 2024 00:29:36 +0200

    x86/kaslr: Expose and use the end of the physical memory address space

    iounmap() on x86 occasionally fails to unmap because the provided valid
    ioremap address is not below high_memory. It turned out that this
    happens due to KASLR.

    KASLR uses the full address space between PAGE_OFFSET and vaddr_end to
    randomize the starting points of the direct map, vmalloc and vmemmap
    regions.  It thereby limits the size of the direct map by using the
    installed memory size plus an extra configurable margin for hot-plug
    memory.  This limitation is done to gain more randomization space
    because otherwise only the holes between the direct map, vmalloc,
    vmemmap and vaddr_end would be usable for randomizing.

    The limited direct map size is not exposed to the rest of the kernel, so
    the memory hot-plug and resource management related code paths still
    operate under the assumption that the available address space can be
    determined with MAX_PHYSMEM_BITS.

    request_free_mem_region() allocates from (1 << MAX_PHYSMEM_BITS) - 1
    downwards.  That means the first allocation happens past the end of the
    direct map and if unlucky this address is in the vmalloc space, which
    causes high_memory to become greater than VMALLOC_START and consequently
    causes iounmap() to fail for valid ioremap addresses.

    MAX_PHYSMEM_BITS cannot be changed for that because the randomization
    does not align with address bit boundaries and there are other places
    which actually require to know the maximum number of address bits.  All
    remaining usage sites of MAX_PHYSMEM_BITS have been analyzed and found
    to be correct.

    Cure this by exposing the end of the direct map via PHYSMEM_END and use
    that for the memory hot-plug and resource management related places
    instead of relying on MAX_PHYSMEM_BITS. In the KASLR case PHYSMEM_END
    maps to a variable which is initialized by the KASLR initialization and
    otherwise it is based on MAX_PHYSMEM_BITS as before.

    To prevent future hickups add a check into add_pages() to catch callers
    trying to add memory above PHYSMEM_END.

    Fixes: 0483e1fa6e ("x86/mm: Implement ASLR for kernel memory regions")
    Reported-by: Max Ramanouski <max8rr8@gmail.com>
    Reported-by: Alistair Popple <apopple@nvidia.com>
    Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
    Tested-By: Max Ramanouski <max8rr8@gmail.com>
    Tested-by: Alistair Popple <apopple@nvidia.com>
    Reviewed-by: Dan Williams <dan.j.williams@intel.com>
    Reviewed-by: Alistair Popple <apopple@nvidia.com>
    Reviewed-by: Kees Cook <kees@kernel.org>
    Cc: stable@vger.kernel.org
    Link: https://lore.kernel.org/all/87ed6soy3z.ffs@tglx

Signed-off-by: Waiman Long <longman@redhat.com>

Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: Chris von Recklinghausen <crecklin@redhat.com>
Approved-by: David Arcari <darcari@redhat.com>
Approved-by: Lenny Szubowicz <lszubowi@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Rado Vrbovsky <rvrbovsk@redhat.com>

arch/x86/include/asm/page_64.h

@@ -17,6 +17,7 @@ extern unsigned long phys_base;
 extern unsigned long page_offset_base;
 extern unsigned long vmalloc_base;
 extern unsigned long vmemmap_base;
+extern unsigned long physmem_end;
 
 static __always_inline unsigned long __phys_addr_nodebug(unsigned long x)
 {

arch/x86/include/asm/pgtable_64_types.h

@@ -140,6 +140,10 @@ extern unsigned int ptrs_per_p4d;
 # define VMEMMAP_START		__VMEMMAP_BASE_L4
 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
 
+#ifdef CONFIG_RANDOMIZE_MEMORY
+# define PHYSMEM_END		physmem_end
+#endif
+
 /*
  * End of the region for which vmalloc page tables are pre-allocated.
  * For non-KMSAN builds, this is the same as VMALLOC_END.

arch/x86/mm/init_64.c

@@ -950,8 +950,12 @@ static void update_end_of_memory_vars(u64 start, u64 size)
 int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	      struct mhp_params *params)
 {
+	unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1;
 	int ret;
 
+	if (WARN_ON_ONCE(end > PHYSMEM_END))
+		return -ERANGE;
+
 	ret = __add_pages(nid, start_pfn, nr_pages, params);
 	WARN_ON_ONCE(ret);
 

arch/x86/mm/kaslr.c

@@ -47,13 +47,24 @@ static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE;
  */
 static __initdata struct kaslr_memory_region {
 	unsigned long *base;
+	unsigned long *end;
 	unsigned long size_tb;
 } kaslr_regions[] = {
-	{ &page_offset_base, 0 },
-	{ &vmalloc_base, 0 },
-	{ &vmemmap_base, 0 },
+	{
+		.base	= &page_offset_base,
+		.end	= &physmem_end,
+	},
+	{
+		.base	= &vmalloc_base,
+	},
+	{
+		.base	= &vmemmap_base,
+	},
 };
 
+/* The end of the possible address space for physical memory */
+unsigned long physmem_end __ro_after_init;
+
 /* Get size in bytes used by the memory region */
 static inline unsigned long get_padding(struct kaslr_memory_region *region)
 {
@@ -82,6 +93,8 @@ void __init kernel_randomize_memory(void)
 	BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE);
 	BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
 
+	/* Preset the end of the possible address space for physical memory */
+	physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1);
 	if (!kaslr_memory_enabled())
 		return;
 
@@ -128,11 +141,18 @@ void __init kernel_randomize_memory(void)
 		vaddr += entropy;
 		*kaslr_regions[i].base = vaddr;
 
-		/*
-		 * Jump the region and add a minimum padding based on
-		 * randomization alignment.
-		 */
+		/* Calculate the end of the region */
 		vaddr += get_padding(&kaslr_regions[i]);
+		/*
+		 * KASLR trims the maximum possible size of the
+		 * direct-map. Update the physmem_end boundary.
+		 * No rounding required as the region starts
+		 * PUD aligned and size is in units of TB.
+		 */
+		if (kaslr_regions[i].end)
+			*kaslr_regions[i].end = __pa_nodebug(vaddr - 1);
+
+		/* Add a minimum padding based on randomization alignment. */
 		vaddr = round_up(vaddr + 1, PUD_SIZE);
 		remain_entropy -= entropy;
 	}

include/linux/mm.h

@@ -95,6 +95,10 @@ extern const int mmap_rnd_compat_bits_max;
 extern int mmap_rnd_compat_bits __read_mostly;
 #endif
 
+#ifndef PHYSMEM_END
+# define PHYSMEM_END	((1ULL << MAX_PHYSMEM_BITS) - 1)
+#endif
+
 #include <asm/page.h>
 #include <asm/processor.h>
 

kernel/resource.c

@@ -1826,8 +1826,7 @@ static resource_size_t gfr_start(struct resource *base, resource_size_t size,
 	if (flags & GFR_DESCENDING) {
 		resource_size_t end;
 
-		end = min_t(resource_size_t, base->end,
-			    (1ULL << MAX_PHYSMEM_BITS) - 1);
+		end = min_t(resource_size_t, base->end, PHYSMEM_END);
 		return end - size + 1;
 	}
 
@@ -1844,8 +1843,7 @@ static bool gfr_continue(struct resource *base, resource_size_t addr,
 	 * @size did not wrap 0.
 	 */
 	return addr > addr - size &&
-	       addr <= min_t(resource_size_t, base->end,
-			     (1ULL << MAX_PHYSMEM_BITS) - 1);
+	       addr <= min_t(resource_size_t, base->end, PHYSMEM_END);
 }
 
 static resource_size_t gfr_next(resource_size_t addr, resource_size_t size,

mm/memory_hotplug.c

@@ -1670,7 +1670,7 @@ struct range __weak arch_get_mappable_range(void)
 
 struct range mhp_get_pluggable_range(bool need_mapping)
 {
-	const u64 max_phys = (1ULL << MAX_PHYSMEM_BITS) - 1;
+	const u64 max_phys = PHYSMEM_END;
 	struct range mhp_range;
 
 	if (need_mapping) {

mm/sparse.c

@@ -129,7 +129,7 @@ static inline int sparse_early_nid(struct mem_section *section)
 static void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
 						unsigned long *end_pfn)
 {
-	unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);
+	unsigned long max_sparsemem_pfn = (PHYSMEM_END + 1) >> PAGE_SHIFT;
 
 	/*
 	 * Sanity checks - do not allow an architecture to pass