| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1232115396-26367-3-git-send-email-brgerst@gmail.com>
Date: Fri, 16 Jan 2009 09:16:22 -0500
From: Brian Gerst <brgerst@...il.com>
To: Tejun Heo <tj@...nel.org>
Cc: Ingo Molnar <mingo@...e.hu>, linux-kernel@...r.kernel.org,
Brian Gerst <brgerst@...il.com>
Subject: [PATCH 03/17] x86-64: Convert irqstacks to per-cpu
Move the irqstackptr variable from the PDA to per-cpu.
Make the stacks themselves per-cpu, removing some specific allocation code.
Add a seperate flag (is_boot_cpu) to simplify the per-cpu boot adjustments.
Signed-off-by: Brian Gerst <brgerst@...il.com>
---
arch/x86/include/asm/pda.h | 1 -
arch/x86/include/asm/processor.h | 3 +++
arch/x86/kernel/asm-offsets_64.c | 1 -
arch/x86/kernel/cpu/common.c | 14 ++------------
arch/x86/kernel/dumpstack_64.c | 6 +++---
arch/x86/kernel/entry_64.S | 6 +++---
arch/x86/kernel/head_64.S | 16 +++++-----------
arch/x86/kernel/setup_percpu.c | 3 ++-
arch/x86/kernel/smpboot.c | 3 +++
9 files changed, 21 insertions(+), 32 deletions(-)
diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h
index 8ee835e..09965f7 100644
--- a/arch/x86/include/asm/pda.h
+++ b/arch/x86/include/asm/pda.h
@@ -22,7 +22,6 @@ struct x8664_pda {
/* gcc-ABI: this canary MUST be at
offset 40!!! */
#endif
- char *irqstackptr;
short nodenumber; /* number of current node (32k max) */
short in_bootmem; /* pda lives in bootmem */
short isidle;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 091cd88..e32ee80 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -378,6 +378,9 @@ union thread_xstate {
#ifdef CONFIG_X86_64
DECLARE_PER_CPU(struct orig_ist, orig_ist);
+
+DECLARE_PER_CPU(char, irqstack[IRQSTACKSIZE]);
+DECLARE_PER_CPU(char *, irqstackptr);
#endif
extern void print_cpu_info(struct cpuinfo_x86 *);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index f4cc81b..5b821fb 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -54,7 +54,6 @@ int main(void)
ENTRY(pcurrent);
ENTRY(irqcount);
ENTRY(cpunumber);
- ENTRY(irqstackptr);
DEFINE(pda_size, sizeof(struct x8664_pda));
BLANK();
#undef ENTRY
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 3d0cc6f..5ddbca0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -881,7 +881,8 @@ __setup("clearcpuid=", setup_disablecpuid);
#ifdef CONFIG_X86_64
struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
-static char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
+DEFINE_PER_CPU_PAGE_ALIGNED(char, irqstack[IRQSTACKSIZE]) __aligned(PAGE_SIZE);
+DEFINE_PER_CPU(char *, irqstackptr) = per_cpu_var(irqstack) + IRQSTACKSIZE - 64;
void __cpuinit pda_init(int cpu)
{
@@ -901,18 +902,7 @@ void __cpuinit pda_init(int cpu)
if (cpu == 0) {
/* others are initialized in smpboot.c */
pda->pcurrent = &init_task;
- pda->irqstackptr = boot_cpu_stack;
- pda->irqstackptr += IRQSTACKSIZE - 64;
} else {
- if (!pda->irqstackptr) {
- pda->irqstackptr = (char *)
- __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
- if (!pda->irqstackptr)
- panic("cannot allocate irqstack for cpu %d",
- cpu);
- pda->irqstackptr += IRQSTACKSIZE - 64;
- }
-
if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
pda->nodenumber = cpu_to_node(cpu);
}
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index c302d07..46c6bf0 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -106,7 +106,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
const struct stacktrace_ops *ops, void *data)
{
const unsigned cpu = get_cpu();
- unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr;
+ unsigned long *irqstack_end = (unsigned long *)per_cpu(irqstackptr, cpu);
unsigned used = 0;
struct thread_info *tinfo;
int graph = 0;
@@ -200,9 +200,9 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
int i;
const int cpu = smp_processor_id();
unsigned long *irqstack_end =
- (unsigned long *) (cpu_pda(cpu)->irqstackptr);
+ (unsigned long *) (per_cpu(irqstackptr, cpu));
unsigned long *irqstack =
- (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
+ (unsigned long *) (per_cpu(irqstackptr, cpu) - IRQSTACKSIZE);
/*
* debugging aid: "show_stack(NULL, NULL);" prints the
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 4833f3a..5cd892f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -345,7 +345,7 @@ ENTRY(save_args)
1: incl %gs:pda_irqcount
jne 2f
popq_cfi %rax /* move return address... */
- mov %gs:pda_irqstackptr,%rsp
+ mov PER_CPU_VAR(irqstackptr),%rsp
EMPTY_FRAME 0
pushq_cfi %rax /* ... to the new stack */
/*
@@ -1261,7 +1261,7 @@ ENTRY(call_softirq)
mov %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
incl %gs:pda_irqcount
- cmove %gs:pda_irqstackptr,%rsp
+ cmove PER_CPU_VAR(irqstackptr),%rsp
push %rbp # backlink for old unwinder
call __do_softirq
leaveq
@@ -1300,7 +1300,7 @@ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs)
11: incl %gs:pda_irqcount
movq %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
- cmovzq %gs:pda_irqstackptr,%rsp
+ cmovzq PER_CPU_VAR(irqstackptr),%rsp
pushq %rbp # backlink for old unwinder
call xen_evtchn_do_upcall
popq %rsp
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index c8ace88..b565719 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -211,15 +211,13 @@ ENTRY(secondary_startup_64)
* data area. Computing this requires two symbols - __per_cpu_load
* and per_cpu__gdt_page. As linker can't do no such relocation, do
* it by hand. As early_gdt_descr is manipulated by C code for
- * secondary CPUs, this should be done only once for the boot CPU
- * when early_gdt_descr_base contains zero.
+ * secondary CPUs, this should be done only once for the boot CPU.
*/
- movq early_gdt_descr_base(%rip), %rax
- testq %rax, %rax
- jnz 1f
+ cmpb $0, is_boot_cpu(%rip)
+ je 1f
movq $__per_cpu_load, %rax
- addq $per_cpu__gdt_page, %rax
- movq %rax, early_gdt_descr_base(%rip)
+ addq %rax, early_gdt_descr_base(%rip)
+ addq %rax, per_cpu__irqstackptr(%rax)
1:
#endif
/*
@@ -431,12 +429,8 @@ NEXT_PAGE(level2_spare_pgt)
.globl early_gdt_descr
early_gdt_descr:
.word GDT_ENTRIES*8-1
-#ifdef CONFIG_SMP
early_gdt_descr_base:
- .quad 0x0000000000000000
-#else
.quad per_cpu__gdt_page
-#endif
ENTRY(phys_base)
/* This must match the first entry in level2_kernel_pgt */
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index b5c35af..e3d399f 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -192,7 +192,9 @@ void __init setup_per_cpu_areas(void)
memcpy(ptr, __per_cpu_load, __per_cpu_end - __per_cpu_start);
per_cpu_offset(cpu) = ptr - __per_cpu_start;
+ per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
#ifdef CONFIG_X86_64
+ per_cpu(irqstackptr, cpu) = per_cpu(irqstack, cpu) + IRQSTACKSIZE - 64;
/*
* CPU0 modified pda in the init data area, reload pda
* offset for CPU0 and clear the area for others.
@@ -202,7 +204,6 @@ void __init setup_per_cpu_areas(void)
else
memset(cpu_pda(cpu), 0, sizeof(*cpu_pda(cpu)));
#endif
- per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
DBG("PERCPU: cpu %4d %p\n", cpu, ptr);
}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 2f0e0f1..a33da98 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -73,6 +73,8 @@ u8 apicid_2_node[MAX_APICID];
static int low_mappings;
#endif
+unsigned char is_boot_cpu = 1;
+
/* State of each CPU */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
@@ -800,6 +802,7 @@ do_rest:
clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
initial_gs = per_cpu_offset(cpu);
#endif
+ is_boot_cpu = 0;
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
stack_start.sp = (void *) c_idle.idle->thread.sp;
--
1.6.1.rc1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists