Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9ceacd1..c494c8c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -189,7 +189,7 @@
return pmd_k;
}
-void vmalloc_sync_all(void)
+static void vmalloc_sync(void)
{
unsigned long address;
@@ -197,7 +197,7 @@
return;
for (address = VMALLOC_START & PMD_MASK;
- address >= TASK_SIZE_MAX && address < FIXADDR_TOP;
+ address >= TASK_SIZE_MAX && address < VMALLOC_END;
address += PMD_SIZE) {
struct page *page;
@@ -216,6 +216,16 @@
}
}
+void vmalloc_sync_mappings(void)
+{
+ vmalloc_sync();
+}
+
+void vmalloc_sync_unmappings(void)
+{
+ vmalloc_sync();
+}
+
/*
* 32-bit:
*
@@ -318,11 +328,23 @@
#else /* CONFIG_X86_64: */
-void vmalloc_sync_all(void)
+void vmalloc_sync_mappings(void)
{
+ /*
+ * 64-bit mappings might allocate new p4d/pud pages
+ * that need to be propagated to all tasks' PGDs.
+ */
sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
}
+void vmalloc_sync_unmappings(void)
+{
+ /*
+ * Unmappings never allocate or free p4d/pud pages.
+ * No work is required here.
+ */
+}
+
/*
* 64-bit:
*
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index fe7a125..968d700 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -62,6 +62,7 @@
unsigned long addr, unsigned long end)
{
unsigned long next;
+ int result;
for (; addr < end; addr = next) {
p4d_t *p4d = p4d_page + p4d_index(addr);
@@ -73,13 +74,20 @@
if (p4d_present(*p4d)) {
pud = pud_offset(p4d, 0);
- ident_pud_init(info, pud, addr, next);
+ result = ident_pud_init(info, pud, addr, next);
+ if (result)
+ return result;
+
continue;
}
pud = (pud_t *)info->alloc_pgt_page(info->context);
if (!pud)
return -ENOMEM;
- ident_pud_init(info, pud, addr, next);
+
+ result = ident_pud_init(info, pud, addr, next);
+ if (result)
+ return result;
+
set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag));
}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fd10d91..af352e2 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -121,8 +121,6 @@
} else {
pfn = pgt_buf_end;
pgt_buf_end += num;
- printk(KERN_DEBUG "BRK [%#010lx, %#010lx] PGTABLE\n",
- pfn << PAGE_SHIFT, (pgt_buf_end << PAGE_SHIFT) - 1);
}
for (i = 0; i < num; i++) {
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 930edeb..0a74407 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -865,10 +865,8 @@
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct zone *zone;
- zone = page_zone(pfn_to_page(start_pfn));
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
}
#endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a6b5c65..a37ccaf 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1212,10 +1212,8 @@
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
- struct zone *zone = page_zone(page);
- __remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pages(start_pfn, nr_pages, altmap);
kernel_physical_mapping_remove(start, start + size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
@@ -1357,18 +1355,18 @@
return 0;
p4d = p4d_offset(pgd, addr);
- if (p4d_none(*p4d))
+ if (!p4d_present(*p4d))
return 0;
pud = pud_offset(p4d, addr);
- if (pud_none(*pud))
+ if (!pud_present(*pud))
return 0;
if (pud_large(*pud))
return pfn_valid(pud_pfn(*pud));
pmd = pmd_offset(pud, addr);
- if (pmd_none(*pmd))
+ if (!pmd_present(*pmd))
return 0;
if (pmd_large(*pmd))
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index a39dcdb..a353f88 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -106,6 +106,22 @@
return 0;
}
+/*
+ * The EFI runtime services data area is not covered by walk_mem_res(), but must
+ * be mapped encrypted when SEV is active.
+ */
+static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *desc)
+{
+ if (!sev_active())
+ return;
+
+ if (!IS_ENABLED(CONFIG_EFI))
+ return;
+
+ if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA)
+ desc->flags |= IORES_MAP_ENCRYPTED;
+}
+
static int __ioremap_collect_map_flags(struct resource *res, void *arg)
{
struct ioremap_desc *desc = arg;
@@ -124,6 +140,9 @@
* To avoid multiple resource walks, this function walks resources marked as
* IORESOURCE_MEM and IORESOURCE_BUSY and looking for system RAM and/or a
* resource described not as IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES).
+ *
+ * After that, deal with misc other ranges in __ioremap_check_other() which do
+ * not fall into the above category.
*/
static void __ioremap_check_mem(resource_size_t addr, unsigned long size,
struct ioremap_desc *desc)
@@ -135,6 +154,8 @@
memset(desc, 0, sizeof(struct ioremap_desc));
walk_mem_res(start, end, desc, __ioremap_collect_map_flags);
+
+ __ioremap_check_other(addr, desc);
}
/*
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 9268c12..7b55893 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -229,7 +229,7 @@
if (pgprot_val(old_prot) == pgprot_val(new_prot))
return;
- pa = pfn << page_level_shift(level);
+ pa = pfn << PAGE_SHIFT;
size = page_level_size(level);
/*
@@ -375,6 +375,7 @@
return false;
}
+EXPORT_SYMBOL_GPL(sev_active);
/* Architecture __weak replacement functions */
void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index e2b0e2a..84cda5d 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -45,8 +45,8 @@
#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
#define PMD_FLAGS_DEC PMD_FLAGS_LARGE
-#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
- (_PAGE_PAT | _PAGE_PWT))
+#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_LARGE_CACHE_MASK) | \
+ (_PAGE_PAT_LARGE | _PAGE_PWT))
#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC)
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index b8ef855..2a36902 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -372,7 +372,7 @@
int cpu;
int err;
- if (downed_cpus == NULL &&
+ if (!cpumask_available(downed_cpus) &&
!alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) {
pr_notice("Failed to allocate mask\n");
goto out;
@@ -402,7 +402,7 @@
int cpu;
int err;
- if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0)
+ if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0)
return;
pr_notice("Re-enabling CPUs...\n");
for_each_cpu(cpu, downed_cpus) {
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index abffa0b..8728225 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -321,7 +321,7 @@
u64 addr, u64 max_addr, u64 size)
{
return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size,
- 0, NULL, NUMA_NO_NODE);
+ 0, NULL, 0);
}
int __init setup_emu2phys_nid(int *dfl_phys_nid)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 0d09cc5..281e584 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -42,7 +42,8 @@
unsigned long pfn;
unsigned int flags;
unsigned int force_split : 1,
- force_static_prot : 1;
+ force_static_prot : 1,
+ force_flush_all : 1;
struct page **pages;
};
@@ -352,10 +353,10 @@
return;
}
- if (cpa->numpages <= tlb_single_page_flush_ceiling)
- on_each_cpu(__cpa_flush_tlb, cpa, 1);
- else
+ if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
flush_tlb_all();
+ else
+ on_each_cpu(__cpa_flush_tlb, cpa, 1);
if (!cache)
return;
@@ -1584,6 +1585,8 @@
alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
alias_cpa.curpage = 0;
+ cpa->force_flush_all = 1;
+
ret = __change_page_attr_set_clr(&alias_cpa, 0);
if (ret)
return ret;
@@ -1604,6 +1607,7 @@
alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
alias_cpa.curpage = 0;
+ cpa->force_flush_all = 1;
/*
* The high mapping range is imprecise, so ignore the
* return value.
@@ -2215,7 +2219,7 @@
.pgd = pgd,
.numpages = numpages,
.mask_set = __pgprot(0),
- .mask_clr = __pgprot(0),
+ .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)),
.flags = 0,
};
@@ -2224,12 +2228,6 @@
if (!(__supported_pte_mask & _PAGE_NX))
goto out;
- if (!(page_flags & _PAGE_NX))
- cpa.mask_clr = __pgprot(_PAGE_NX);
-
- if (!(page_flags & _PAGE_RW))
- cpa.mask_clr = __pgprot(_PAGE_RW);
-
if (!(page_flags & _PAGE_ENC))
cpa.mask_clr = pgprot_encrypted(cpa.mask_clr);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index d9fbd4f..35b2e35 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -1132,12 +1132,14 @@
static void *memtype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
+ kfree(v);
++*pos;
return memtype_get_idx(*pos);
}
static void memtype_seq_stop(struct seq_file *seq, void *v)
{
+ kfree(v);
}
static int memtype_seq_show(struct seq_file *seq, void *v)
@@ -1146,7 +1148,6 @@
seq_printf(seq, "%s @ 0x%Lx-0x%Lx\n", cattr_name(print_entry->type),
print_entry->start, print_entry->end);
- kfree(print_entry);
return 0;
}
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 3e4b903..7982f13 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -643,8 +643,8 @@
fixmaps_set++;
}
-void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
- pgprot_t flags)
+void native_set_fixmap(unsigned /* enum fixed_addresses */ idx,
+ phys_addr_t phys, pgprot_t flags)
{
/* Sanitize 'prot' against any unsupported bits: */
pgprot_val(flags) &= __default_kernel_pte_mask;
@@ -826,6 +826,8 @@
}
free_page((unsigned long)pmd_sv);
+
+ pgtable_pmd_page_dtor(virt_to_page(pmd));
free_page((unsigned long)pmd);
return 1;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index e6a9edc..851359b 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -327,8 +327,14 @@
/*
* The membarrier system call requires a full memory barrier and
* core serialization before returning to user-space, after
- * storing to rq->curr. Writing to CR3 provides that full
- * memory barrier and core serializing instruction.
+ * storing to rq->curr, when changing mm. This is because
+ * membarrier() sends IPIs to all CPUs that are in the target mm
+ * to make them issue memory barriers. However, if another CPU
+ * switches to/from the target mm concurrently with
+ * membarrier(), it can cause that CPU not to receive an IPI
+ * when it really should issue a memory barrier. Writing to CR3
+ * provides that full memory barrier and core serializing
+ * instruction.
*/
if (real_prev == next) {
VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=