From 244b2c5ca8b14627e4a17755e5922221e121c771 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 09 Oct 2024 06:15:07 +0000
Subject: [PATCH] change system file
---
kernel/arch/arm64/kernel/vdso.c | 386 ++++++++++++++++++++++++++++++++----------------------
1 files changed, 227 insertions(+), 159 deletions(-)
diff --git a/kernel/arch/arm64/kernel/vdso.c b/kernel/arch/arm64/kernel/vdso.c
index 3c90b38..debb899 100644
--- a/kernel/arch/arm64/kernel/vdso.c
+++ b/kernel/arch/arm64/kernel/vdso.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* VDSO implementations.
*
* Copyright (C) 2012 ARM Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
*
* Author: Will Deacon <will.deacon@arm.com>
*/
@@ -29,6 +18,7 @@
#include <linux/sched.h>
#include <linux/signal.h>
#include <linux/slab.h>
+#include <linux/time_namespace.h>
#include <linux/timekeeper_internal.h>
#include <linux/vmalloc.h>
#include <vdso/datapage.h>
@@ -40,24 +30,20 @@
#include <asm/vdso.h>
extern char vdso_start[], vdso_end[];
-#ifdef CONFIG_COMPAT_VDSO
extern char vdso32_start[], vdso32_end[];
-#endif /* CONFIG_COMPAT_VDSO */
-/* vdso_lookup arch_index */
-enum arch_vdso_type {
- ARM64_VDSO = 0,
-#ifdef CONFIG_COMPAT_VDSO
- ARM64_VDSO32 = 1,
-#endif /* CONFIG_COMPAT_VDSO */
+enum vdso_abi {
+ VDSO_ABI_AA64,
+ VDSO_ABI_AA32,
};
-#ifdef CONFIG_COMPAT_VDSO
-#define VDSO_TYPES (ARM64_VDSO32 + 1)
-#else
-#define VDSO_TYPES (ARM64_VDSO + 1)
-#endif /* CONFIG_COMPAT_VDSO */
-struct __vdso_abi {
+enum vvar_pages {
+ VVAR_DATA_PAGE_OFFSET,
+ VVAR_TIMENS_PAGE_OFFSET,
+ VVAR_NR_PAGES,
+};
+
+struct vdso_abi_info {
const char *name;
const char *vdso_code_start;
const char *vdso_code_end;
@@ -68,14 +54,14 @@
struct vm_special_mapping *cm;
};
-static struct __vdso_abi vdso_lookup[VDSO_TYPES] __ro_after_init = {
- {
+static struct vdso_abi_info vdso_info[] __ro_after_init = {
+ [VDSO_ABI_AA64] = {
.name = "vdso",
.vdso_code_start = vdso_start,
.vdso_code_end = vdso_end,
},
#ifdef CONFIG_COMPAT_VDSO
- {
+ [VDSO_ABI_AA32] = {
.name = "vdso32",
.vdso_code_start = vdso32_start,
.vdso_code_end = vdso32_end,
@@ -92,13 +78,13 @@
} vdso_data_store __page_aligned_data;
struct vdso_data *vdso_data = vdso_data_store.data;
-static int __vdso_remap(enum arch_vdso_type arch_index,
+static int __vdso_remap(enum vdso_abi abi,
const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma)
{
unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
- unsigned long vdso_size = vdso_lookup[arch_index].vdso_code_end -
- vdso_lookup[arch_index].vdso_code_start;
+ unsigned long vdso_size = vdso_info[abi].vdso_code_end -
+ vdso_info[abi].vdso_code_start;
if (vdso_size != new_size)
return -EINVAL;
@@ -108,56 +94,156 @@
return 0;
}
-static int __vdso_init(enum arch_vdso_type arch_index)
+static int __vdso_init(enum vdso_abi abi)
{
int i;
struct page **vdso_pagelist;
unsigned long pfn;
- if (memcmp(vdso_lookup[arch_index].vdso_code_start, "\177ELF", 4)) {
+ if (memcmp(vdso_info[abi].vdso_code_start, "\177ELF", 4)) {
pr_err("vDSO is not a valid ELF object!\n");
return -EINVAL;
}
- vdso_lookup[arch_index].vdso_pages = (
- vdso_lookup[arch_index].vdso_code_end -
- vdso_lookup[arch_index].vdso_code_start) >>
+ vdso_info[abi].vdso_pages = (
+ vdso_info[abi].vdso_code_end -
+ vdso_info[abi].vdso_code_start) >>
PAGE_SHIFT;
- /* Allocate the vDSO pagelist, plus a page for the data. */
- vdso_pagelist = kcalloc(vdso_lookup[arch_index].vdso_pages + 1,
+ vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages,
sizeof(struct page *),
GFP_KERNEL);
if (vdso_pagelist == NULL)
return -ENOMEM;
- /* Grab the vDSO data page. */
- vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
-
-
/* Grab the vDSO code pages. */
- pfn = sym_to_pfn(vdso_lookup[arch_index].vdso_code_start);
+ pfn = sym_to_pfn(vdso_info[abi].vdso_code_start);
- for (i = 0; i < vdso_lookup[arch_index].vdso_pages; i++)
- vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
+ for (i = 0; i < vdso_info[abi].vdso_pages; i++)
+ vdso_pagelist[i] = pfn_to_page(pfn + i);
- vdso_lookup[arch_index].dm->pages = &vdso_pagelist[0];
- vdso_lookup[arch_index].cm->pages = &vdso_pagelist[1];
+ vdso_info[abi].cm->pages = vdso_pagelist;
return 0;
}
-static int __setup_additional_pages(enum arch_vdso_type arch_index,
+#ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+ return (struct vdso_data *)(vvar_page);
+}
+
+/*
+ * The vvar mapping contains data for a specific time namespace, so when a task
+ * changes namespace we must unmap its vvar data for the old namespace.
+ * Subsequent faults will map in data for the new namespace.
+ *
+ * For more details see timens_setup_vdso_data().
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+ struct mm_struct *mm = task->mm;
+ struct vm_area_struct *vma;
+
+ mmap_read_lock(mm);
+
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ unsigned long size = vma->vm_end - vma->vm_start;
+
+ if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm))
+ zap_page_range(vma, vma->vm_start, size);
+#ifdef CONFIG_COMPAT_VDSO
+ if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm))
+ zap_page_range(vma, vma->vm_start, size);
+#endif
+ }
+
+ mmap_read_unlock(mm);
+ return 0;
+}
+
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+ if (likely(vma->vm_mm == current->mm))
+ return current->nsproxy->time_ns->vvar_page;
+
+ /*
+ * VM_PFNMAP | VM_IO protect .fault() handler from being called
+ * through interfaces like /proc/$pid/mem or
+ * process_vm_{readv,writev}() as long as there's no .access()
+ * in special_mapping_vmops.
+ * For more details check_vma_flags() and __access_remote_vm()
+ */
+ WARN(1, "vvar_page accessed remotely");
+
+ return NULL;
+}
+#else
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+ return NULL;
+}
+#endif
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+ struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct page *timens_page = find_timens_vvar_page(vma);
+ unsigned long pfn;
+
+ switch (vmf->pgoff) {
+ case VVAR_DATA_PAGE_OFFSET:
+ if (timens_page)
+ pfn = page_to_pfn(timens_page);
+ else
+ pfn = sym_to_pfn(vdso_data);
+ break;
+#ifdef CONFIG_TIME_NS
+ case VVAR_TIMENS_PAGE_OFFSET:
+ /*
+ * If a task belongs to a time namespace then a namespace
+ * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+ * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+ * offset.
+ * See also the comment near timens_setup_vdso_data().
+ */
+ if (!timens_page)
+ return VM_FAULT_SIGBUS;
+ pfn = sym_to_pfn(vdso_data);
+ break;
+#endif /* CONFIG_TIME_NS */
+ default:
+ return VM_FAULT_SIGBUS;
+ }
+
+ return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+static int vvar_mremap(const struct vm_special_mapping *sm,
+ struct vm_area_struct *new_vma)
+{
+ unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
+
+ if (new_size != VVAR_NR_PAGES * PAGE_SIZE)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int __setup_additional_pages(enum vdso_abi abi,
struct mm_struct *mm,
struct linux_binprm *bprm,
int uses_interp)
{
unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+ unsigned long gp_flags = 0;
void *ret;
- vdso_text_len = vdso_lookup[arch_index].vdso_pages << PAGE_SHIFT;
+ BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+
+ vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT;
/* Be sure to map the data page */
- vdso_mapping_len = vdso_text_len + PAGE_SIZE;
+ vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE;
vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
if (IS_ERR_VALUE(vdso_base)) {
@@ -165,18 +251,21 @@
goto up_fail;
}
- ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
- VM_READ|VM_MAYREAD,
- vdso_lookup[arch_index].dm);
+ ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE,
+ VM_READ|VM_MAYREAD|VM_PFNMAP,
+ vdso_info[abi].dm);
if (IS_ERR(ret))
goto up_fail;
- vdso_base += PAGE_SIZE;
+ if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
+ gp_flags = VM_ARM64_BTI;
+
+ vdso_base += VVAR_NR_PAGES * PAGE_SIZE;
mm->context.vdso = (void *)vdso_base;
ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
- VM_READ|VM_EXEC|
+ VM_READ|VM_EXEC|gp_flags|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
- vdso_lookup[arch_index].cm);
+ vdso_info[abi].cm);
if (IS_ERR(ret))
goto up_fail;
@@ -191,52 +280,40 @@
/*
* Create and map the vectors page for AArch32 tasks.
*/
-#ifdef CONFIG_COMPAT_VDSO
static int aarch32_vdso_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma)
{
- return __vdso_remap(ARM64_VDSO32, sm, new_vma);
+ return __vdso_remap(VDSO_ABI_AA32, sm, new_vma);
}
-#endif /* CONFIG_COMPAT_VDSO */
-/*
- * aarch32_vdso_pages:
- * 0 - kuser helpers
- * 1 - sigreturn code
- * or (CONFIG_COMPAT_VDSO):
- * 0 - kuser helpers
- * 1 - vdso data
- * 2 - vdso code
- */
-#define C_VECTORS 0
-#ifdef CONFIG_COMPAT_VDSO
-#define C_VVAR 1
-#define C_VDSO 2
-#define C_PAGES (C_VDSO + 1)
-#else
-#define C_SIGPAGE 1
-#define C_PAGES (C_SIGPAGE + 1)
-#endif /* CONFIG_COMPAT_VDSO */
-static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init;
-static struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
- {
+enum aarch32_map {
+ AA32_MAP_VECTORS, /* kuser helpers */
+ AA32_MAP_SIGPAGE,
+ AA32_MAP_VVAR,
+ AA32_MAP_VDSO,
+};
+
+static struct page *aarch32_vectors_page __ro_after_init;
+static struct page *aarch32_sig_page __ro_after_init;
+
+static struct vm_special_mapping aarch32_vdso_maps[] = {
+ [AA32_MAP_VECTORS] = {
.name = "[vectors]", /* ABI */
- .pages = &aarch32_vdso_pages[C_VECTORS],
+ .pages = &aarch32_vectors_page,
},
-#ifdef CONFIG_COMPAT_VDSO
- {
+ [AA32_MAP_SIGPAGE] = {
+ .name = "[sigpage]", /* ABI */
+ .pages = &aarch32_sig_page,
+ },
+ [AA32_MAP_VVAR] = {
.name = "[vvar]",
+ .fault = vvar_fault,
+ .mremap = vvar_mremap,
},
- {
+ [AA32_MAP_VDSO] = {
.name = "[vdso]",
.mremap = aarch32_vdso_mremap,
},
-#else
- {
- .name = "[sigpage]", /* ABI */
- .pages = &aarch32_vdso_pages[C_SIGPAGE],
- },
-#endif /* CONFIG_COMPAT_VDSO */
};
static int aarch32_alloc_kuser_vdso_page(void)
@@ -254,52 +331,52 @@
memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
kuser_sz);
- aarch32_vdso_pages[C_VECTORS] = virt_to_page(vdso_page);
- flush_dcache_page(aarch32_vdso_pages[C_VECTORS]);
+ aarch32_vectors_page = virt_to_page(vdso_page);
+ flush_dcache_page(aarch32_vectors_page);
return 0;
}
-#ifdef CONFIG_COMPAT_VDSO
-static int __aarch32_alloc_vdso_pages(void)
-{
- int ret;
-
- vdso_lookup[ARM64_VDSO32].dm = &aarch32_vdso_spec[C_VVAR];
- vdso_lookup[ARM64_VDSO32].cm = &aarch32_vdso_spec[C_VDSO];
-
- ret = __vdso_init(ARM64_VDSO32);
- if (ret)
- return ret;
-
- return aarch32_alloc_kuser_vdso_page();
-}
-#else
-static int __aarch32_alloc_vdso_pages(void)
+static int aarch32_alloc_sigpage(void)
{
extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
unsigned long sigpage;
- int ret;
sigpage = get_zeroed_page(GFP_ATOMIC);
if (!sigpage)
return -ENOMEM;
memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
- aarch32_vdso_pages[C_SIGPAGE] = virt_to_page(sigpage);
- flush_dcache_page(aarch32_vdso_pages[C_SIGPAGE]);
-
- ret = aarch32_alloc_kuser_vdso_page();
- if (ret)
- free_page(sigpage);
-
- return ret;
+ aarch32_sig_page = virt_to_page(sigpage);
+ flush_dcache_page(aarch32_sig_page);
+ return 0;
}
-#endif /* CONFIG_COMPAT_VDSO */
+
+static int __aarch32_alloc_vdso_pages(void)
+{
+
+ if (!IS_ENABLED(CONFIG_COMPAT_VDSO))
+ return 0;
+
+ vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
+ vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
+
+ return __vdso_init(VDSO_ABI_AA32);
+}
static int __init aarch32_alloc_vdso_pages(void)
{
- return __aarch32_alloc_vdso_pages();
+ int ret;
+
+ ret = __aarch32_alloc_vdso_pages();
+ if (ret)
+ return ret;
+
+ ret = aarch32_alloc_sigpage();
+ if (ret)
+ return ret;
+
+ return aarch32_alloc_kuser_vdso_page();
}
arch_initcall(aarch32_alloc_vdso_pages);
@@ -317,12 +394,11 @@
ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
VM_READ | VM_EXEC |
VM_MAYREAD | VM_MAYEXEC,
- &aarch32_vdso_spec[C_VECTORS]);
+ &aarch32_vdso_maps[AA32_MAP_VECTORS]);
return PTR_ERR_OR_ZERO(ret);
}
-#ifndef CONFIG_COMPAT_VDSO
static int aarch32_sigreturn_setup(struct mm_struct *mm)
{
unsigned long addr;
@@ -341,40 +417,38 @@
ret = _install_special_mapping(mm, addr, PAGE_SIZE,
VM_READ | VM_EXEC | VM_MAYREAD |
VM_MAYWRITE | VM_MAYEXEC,
- &aarch32_vdso_spec[C_SIGPAGE]);
+ &aarch32_vdso_maps[AA32_MAP_SIGPAGE]);
if (IS_ERR(ret))
goto out;
- mm->context.vdso = (void *)addr;
+ mm->context.sigpage = (void *)addr;
out:
return PTR_ERR_OR_ZERO(ret);
}
-#endif /* !CONFIG_COMPAT_VDSO */
int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
struct mm_struct *mm = current->mm;
int ret;
- if (down_write_killable(&mm->mmap_sem))
+ if (mmap_write_lock_killable(mm))
return -EINTR;
ret = aarch32_kuser_helpers_setup(mm);
if (ret)
goto out;
-#ifdef CONFIG_COMPAT_VDSO
- ret = __setup_additional_pages(ARM64_VDSO32,
- mm,
- bprm,
- uses_interp);
-#else
- ret = aarch32_sigreturn_setup(mm);
-#endif /* CONFIG_COMPAT_VDSO */
+ if (IS_ENABLED(CONFIG_COMPAT_VDSO)) {
+ ret = __setup_additional_pages(VDSO_ABI_AA32, mm, bprm,
+ uses_interp);
+ if (ret)
+ goto out;
+ }
+ ret = aarch32_sigreturn_setup(mm);
out:
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
return ret;
}
#endif /* CONFIG_COMPAT */
@@ -382,22 +456,21 @@
static int vdso_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma)
{
- return __vdso_remap(ARM64_VDSO, sm, new_vma);
+ return __vdso_remap(VDSO_ABI_AA64, sm, new_vma);
}
-/*
- * aarch64_vdso_pages:
- * 0 - vvar
- * 1 - vdso
- */
-#define A_VVAR 0
-#define A_VDSO 1
-#define A_PAGES (A_VDSO + 1)
-static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = {
- {
+enum aarch64_map {
+ AA64_MAP_VVAR,
+ AA64_MAP_VDSO,
+};
+
+static struct vm_special_mapping aarch64_vdso_maps[] __ro_after_init = {
+ [AA64_MAP_VVAR] = {
.name = "[vvar]",
+ .fault = vvar_fault,
+ .mremap = vvar_mremap,
},
- {
+ [AA64_MAP_VDSO] = {
.name = "[vdso]",
.mremap = vdso_mremap,
},
@@ -405,28 +478,23 @@
static int __init vdso_init(void)
{
- vdso_lookup[ARM64_VDSO].dm = &vdso_spec[A_VVAR];
- vdso_lookup[ARM64_VDSO].cm = &vdso_spec[A_VDSO];
+ vdso_info[VDSO_ABI_AA64].dm = &aarch64_vdso_maps[AA64_MAP_VVAR];
+ vdso_info[VDSO_ABI_AA64].cm = &aarch64_vdso_maps[AA64_MAP_VDSO];
- return __vdso_init(ARM64_VDSO);
+ return __vdso_init(VDSO_ABI_AA64);
}
arch_initcall(vdso_init);
-int arch_setup_additional_pages(struct linux_binprm *bprm,
- int uses_interp)
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
struct mm_struct *mm = current->mm;
int ret;
- if (down_write_killable(&mm->mmap_sem))
+ if (mmap_write_lock_killable(mm))
return -EINTR;
- ret = __setup_additional_pages(ARM64_VDSO,
- mm,
- bprm,
- uses_interp);
-
- up_write(&mm->mmap_sem);
+ ret = __setup_additional_pages(VDSO_ABI_AA64, mm, bprm, uses_interp);
+ mmap_write_unlock(mm);
return ret;
}
--
Gitblit v1.6.2