From: Brian Gerst <brgerst@gmail.com>
To: linux-kernel@vger.kernel.org, x86@kernel.org
Cc: Ingo Molnar <mingo@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Borislav Petkov <bp@alien8.de>, "H . Peter Anvin" <hpa@zytor.com>,
Uros Bizjak <ubizjak@gmail.com>,
David.Laight@aculab.com, Brian Gerst <brgerst@gmail.com>
Subject: [PATCH v4 09/16] x86/percpu/64: Use relative percpu offsets
Date: Fri, 22 Mar 2024 12:52:26 -0400 [thread overview]
Message-ID: <20240322165233.71698-10-brgerst@gmail.com> (raw)
In-Reply-To: <20240322165233.71698-1-brgerst@gmail.com>
The percpu section is currently linked at virtual address 0, because
older compilers hardcoded the stack protector canary value at a fixed
offset from the start of the GS segment. Now that the canary is a
normal percpu variable, the percpu section does not need to be linked
at a specific virtual address. This means that x86-64 will calculate
percpu offsets like most other architectures, as the delta between the
initial percpu address and the dynamically allocated memory.
Signed-off-by: Brian Gerst <brgerst@gmail.com>
---
arch/x86/include/asm/processor.h | 6 +++++-
arch/x86/kernel/head_64.S | 19 +++++++++----------
arch/x86/kernel/setup_percpu.c | 12 ++----------
arch/x86/kernel/vmlinux.lds.S | 29 +----------------------------
arch/x86/platform/pvh/head.S | 5 ++---
arch/x86/tools/relocs.c | 10 +++-------
arch/x86/xen/xen-head.S | 9 ++++-----
init/Kconfig | 2 +-
8 files changed, 27 insertions(+), 65 deletions(-)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 946bebce396f..40d6add8ff31 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -396,7 +396,11 @@ DECLARE_INIT_PER_CPU(fixed_percpu_data);
static inline unsigned long cpu_kernelmode_gs_base(int cpu)
{
- return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
+#ifdef CONFIG_SMP
+ return per_cpu_offset(cpu);
+#else
+ return 0;
+#endif
}
extern asmlinkage void entry_SYSCALL32_ignore(void);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index cfbf0486d424..5b2cc711feec 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -68,11 +68,14 @@ SYM_CODE_START_NOALIGN(startup_64)
/* Set up the stack for verify_cpu() */
leaq __top_init_kernel_stack(%rip), %rsp
- /* Setup GSBASE to allow stack canary access for C code */
+ /*
+ * Set up GSBASE.
+ * Note that, on SMP, the boot cpu uses init data section until
+ * the per cpu areas are set up.
+ */
movl $MSR_GS_BASE, %ecx
- leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
- movl %edx, %eax
- shrq $32, %rdx
+ xorl %eax, %eax
+ xorl %edx, %edx
wrmsr
call startup_64_setup_gdt_idt
@@ -359,16 +362,12 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
movl %eax,%fs
movl %eax,%gs
- /* Set up %gs.
- *
- * The base of %gs always points to fixed_percpu_data.
+ /*
+ * Set up GSBASE.
* Note that, on SMP, the boot cpu uses init data section until
* the per cpu areas are set up.
*/
movl $MSR_GS_BASE,%ecx
-#ifndef CONFIG_SMP
- leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-#endif
movl %edx, %eax
shrq $32, %rdx
wrmsr
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index b30d6e180df7..1e7be9409aa2 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -23,18 +23,10 @@
#include <asm/cpumask.h>
#include <asm/cpu.h>
-#ifdef CONFIG_X86_64
-#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
-#else
-#define BOOT_PERCPU_OFFSET 0
-#endif
-
-DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
EXPORT_PER_CPU_SYMBOL(this_cpu_off);
-unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
- [0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
-};
+unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init;
EXPORT_SYMBOL(__per_cpu_offset);
/*
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3509afc6a672..0b152f96c24e 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -99,12 +99,6 @@ const_pcpu_hot = pcpu_hot;
PHDRS {
text PT_LOAD FLAGS(5); /* R_E */
data PT_LOAD FLAGS(6); /* RW_ */
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_SMP
- percpu PT_LOAD FLAGS(6); /* RW_ */
-#endif
- init PT_LOAD FLAGS(7); /* RWE */
-#endif
note PT_NOTE FLAGS(0); /* ___ */
}
@@ -222,21 +216,7 @@ SECTIONS
__init_begin = .; /* paired with __init_end */
}
-#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
- /*
- * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
- * output PHDR, so the next output section - .init.text - should
- * start another segment - init.
- */
- PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
- ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START,
- "per-CPU data too large - increase CONFIG_PHYSICAL_START")
-#endif
-
INIT_TEXT_SECTION(PAGE_SIZE)
-#ifdef CONFIG_X86_64
- :init
-#endif
/*
* Section for code used exclusively before alternatives are run. All
@@ -353,9 +333,7 @@ SECTIONS
EXIT_DATA
}
-#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
PERCPU_SECTION(INTERNODE_CACHE_BYTES)
-#endif
. = ALIGN(PAGE_SIZE);
@@ -493,16 +471,11 @@ SECTIONS
* Per-cpu symbols which need to be offset from __per_cpu_load
* for the boot processor.
*/
-#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
+#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x)
INIT_PER_CPU(gdt_page);
INIT_PER_CPU(fixed_percpu_data);
INIT_PER_CPU(irq_stack_backing_store);
-#ifdef CONFIG_SMP
-. = ASSERT((fixed_percpu_data == 0),
- "fixed_percpu_data is not at start of per-cpu area");
-#endif
-
#ifdef CONFIG_MITIGATION_UNRET_ENTRY
. = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
#endif
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 1f1c3230b27b..7e3e07c6170f 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -101,9 +101,8 @@ SYM_CODE_START_LOCAL(pvh_start_xen)
* the per cpu areas are set up.
*/
mov $MSR_GS_BASE,%ecx
- lea INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
- mov %edx, %eax
- shr $32, %rdx
+ xor %eax, %eax
+ xor %edx, %edx
wrmsr
call xen_prepare_pvh
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index adf11a48ec70..016650ddaf7f 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -839,12 +839,7 @@ static void percpu_init(void)
*/
static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
{
- int shndx = sym_index(sym);
-
- return (shndx == per_cpu_shndx) &&
- strcmp(symname, "__init_begin") &&
- strcmp(symname, "__per_cpu_load") &&
- strncmp(symname, "init_per_cpu_", 13);
+ return 0;
}
@@ -1068,7 +1063,8 @@ static int cmp_relocs(const void *va, const void *vb)
static void sort_relocs(struct relocs *r)
{
- qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
+ if (r->count)
+ qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
}
static int write32(uint32_t v, FILE *f)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index ae4672ea00bb..1796884b727d 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -51,15 +51,14 @@ SYM_CODE_START(startup_xen)
leaq __top_init_kernel_stack(%rip), %rsp
- /* Set up %gs.
- *
- * The base of %gs always points to fixed_percpu_data.
+ /*
+ * Set up GSBASE.
* Note that, on SMP, the boot cpu uses init data section until
* the per cpu areas are set up.
*/
movl $MSR_GS_BASE,%ecx
- movq $INIT_PER_CPU_VAR(fixed_percpu_data),%rax
- cdq
+ xorl %eax, %eax
+ xorl %edx, %edx
wrmsr
mov %rsi, %rdi
diff --git a/init/Kconfig b/init/Kconfig
index f3ea5dea9c85..0f928f82dc7a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1784,7 +1784,7 @@ config KALLSYMS_ALL
config KALLSYMS_ABSOLUTE_PERCPU
bool
depends on KALLSYMS
- default X86_64 && SMP
+ default n
config KALLSYMS_BASE_RELATIVE
bool
--
2.44.0
next prev parent reply other threads:[~2024-03-22 16:52 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-22 16:52 [PATCH v4 00/16] x86-64: Stack protector and percpu improvements Brian Gerst
2024-03-22 16:52 ` [PATCH v4 01/16] x86/stackprotector/32: Remove stack protector test script Brian Gerst
2024-03-23 17:00 ` Uros Bizjak
2024-03-22 16:52 ` [PATCH v4 02/16] x86/stackprotector/64: " Brian Gerst
2024-03-23 17:01 ` Uros Bizjak
2024-03-22 16:52 ` [PATCH v4 03/16] x86/boot: Disable stack protector for early boot code Brian Gerst
2024-03-22 16:52 ` [PATCH v4 04/16] x86/pvh: Use fixed_percpu_data for early boot GSBASE Brian Gerst
2024-03-22 16:52 ` [PATCH v4 05/16] x86/relocs: Handle R_X86_64_REX_GOTPCRELX relocations Brian Gerst
2024-03-22 16:52 ` [PATCH v4 06/16] objtool: Allow adding relocations to an existing section Brian Gerst
2024-03-22 16:52 ` [PATCH v4 07/16] objtool: Convert fixed location stack protector accesses Brian Gerst
2024-03-22 16:52 ` [PATCH v4 08/16] x86/stackprotector/64: Convert to normal percpu variable Brian Gerst
2024-03-23 17:11 ` Uros Bizjak
2024-03-22 16:52 ` Brian Gerst [this message]
2024-03-23 17:14 ` [PATCH v4 09/16] x86/percpu/64: Use relative percpu offsets Uros Bizjak
2024-03-22 16:52 ` [PATCH v4 10/16] x86/percpu/64: Remove fixed_percpu_data Brian Gerst
2024-03-23 17:14 ` Uros Bizjak
2024-03-22 16:52 ` [PATCH v4 11/16] x86/boot/64: Remove inverse relocations Brian Gerst
2024-03-22 16:52 ` [PATCH v4 12/16] x86/percpu/64: Remove INIT_PER_CPU macros Brian Gerst
2024-03-23 17:15 ` Uros Bizjak
2024-03-22 16:52 ` [PATCH v4 13/16] percpu: Remove PER_CPU_FIRST_SECTION Brian Gerst
2024-03-23 17:17 ` Uros Bizjak
2024-03-22 16:52 ` [PATCH v4 14/16] percpu: Remove PERCPU_VADDR() Brian Gerst
2024-03-22 16:52 ` [PATCH v4 15/16] percpu: Remove __per_cpu_load Brian Gerst
2024-03-22 16:52 ` [PATCH v4 16/16] kallsyms: Remove KALLSYMS_ABSOLUTE_PERCPU Brian Gerst
2024-03-23 11:39 ` [PATCH v4 00/16] x86-64: Stack protector and percpu improvements Uros Bizjak
2024-03-23 13:22 ` Brian Gerst
2024-03-23 16:16 ` Linus Torvalds
2024-03-23 17:06 ` Linus Torvalds
2024-03-24 19:09 ` David Laight
2024-03-25 14:51 ` Arnd Bergmann
2024-03-25 15:26 ` Takashi Iwai
2024-03-25 18:08 ` Arnd Bergmann
2024-03-26 7:02 ` Uros Bizjak
2024-03-23 22:55 ` Arnd Bergmann
2024-03-25 15:14 ` Ard Biesheuvel
2024-03-24 2:25 ` Ingo Molnar
2024-03-24 3:51 ` Brian Gerst
2024-03-24 4:05 ` Ingo Molnar
2024-03-24 5:43 ` Brian Gerst
2024-03-24 10:53 ` Ingo Molnar
2024-03-24 12:34 ` Brian Gerst
2024-03-24 18:14 ` Ingo Molnar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240322165233.71698-10-brgerst@gmail.com \
--to=brgerst@gmail.com \
--cc=David.Laight@aculab.com \
--cc=bp@alien8.de \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=tglx@linutronix.de \
--cc=ubizjak@gmail.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.