[PATCH 35/35] x86: Add entry trampolines to kcore

From: Arnaldo Carvalho de Melo
Date: Wed Aug 15 2018 - 11:08:58 EST


From: Adrian Hunter <adrian.hunter@xxxxxxxxx>

Without program headers for PTI entry trampoline pages, the trampoline
virtual addresses do not map to anything.

Example before:

sudo gdb --quiet vmlinux /proc/kcore
Reading symbols from vmlinux...done.
[New process 1]
Core was generated by `BOOT_IMAGE=/boot/vmlinuz-4.16.0 root=UUID=a6096b83-b763-4101-807e-f33daff63233'.
#0 0x0000000000000000 in irq_stack_union ()
(gdb) x /21ib 0xfffffe0000006000
0xfffffe0000006000: Cannot access memory at address 0xfffffe0000006000
(gdb) quit

After:

sudo gdb --quiet vmlinux /proc/kcore
[sudo] password for ahunter:
Reading symbols from vmlinux...done.
[New process 1]
Core was generated by `BOOT_IMAGE=/boot/vmlinuz-4.16.0-fix-4-00005-gd6e65a8b4072 root=UUID=a6096b83-b7'.
#0 0x0000000000000000 in irq_stack_union ()
(gdb) x /21ib 0xfffffe0000006000
0xfffffe0000006000: swapgs
0xfffffe0000006003: mov %rsp,-0x3e12(%rip) # 0xfffffe00000021f8
0xfffffe000000600a: xchg %ax,%ax
0xfffffe000000600c: mov %cr3,%rsp
0xfffffe000000600f: bts $0x3f,%rsp
0xfffffe0000006014: and $0xffffffffffffe7ff,%rsp
0xfffffe000000601b: mov %rsp,%cr3
0xfffffe000000601e: mov -0x3019(%rip),%rsp # 0xfffffe000000300c
0xfffffe0000006025: pushq $0x2b
0xfffffe0000006027: pushq -0x3e35(%rip) # 0xfffffe00000021f8
0xfffffe000000602d: push %r11
0xfffffe000000602f: pushq $0x33
0xfffffe0000006031: push %rcx
0xfffffe0000006032: push %rdi
0xfffffe0000006033: mov $0xffffffff91a00010,%rdi
0xfffffe000000603a: callq 0xfffffe0000006046
0xfffffe000000603f: pause
0xfffffe0000006041: lfence
0xfffffe0000006044: jmp 0xfffffe000000603f
0xfffffe0000006046: mov %rdi,(%rsp)
0xfffffe000000604a: retq
(gdb) quit

In addition, entry trampolines all map to the same page. Represent that
by giving the corresponding program headers in kcore the same offset.

This has the benefit that, when perf tools uses /proc/kcore as a source
for kernel object code, samples from different CPU trampolines are
aggregated together. Note, such aggregation is normal for profiling
i.e. people want to profile the object code, not every different virtual
address the object code might be mapped to (across different processes
for example).

Notes by PeterZ:

This also adds the KCORE_REMAP functionality.

Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Acked-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Joerg Roedel <joro@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: x86@xxxxxxxxxx
Link: http://lkml.kernel.org/r/1528289651-4113-4-git-send-email-adrian.hunter@xxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
arch/x86/mm/cpu_entry_area.c | 10 ++++++++++
fs/proc/kcore.c | 7 +++++--
include/linux/kcore.h | 13 +++++++++++++
3 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index fab49fd5190f..076ebdce9bd4 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -3,6 +3,7 @@
#include <linux/spinlock.h>
#include <linux/percpu.h>
#include <linux/kallsyms.h>
+#include <linux/kcore.h>

#include <asm/cpu_entry_area.h>
#include <asm/pgtable.h>
@@ -14,6 +15,7 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage)
#ifdef CONFIG_X86_64
static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+static DEFINE_PER_CPU(struct kcore_list, kcore_entry_trampoline);
#endif

struct cpu_entry_area *get_cpu_entry_area(int cpu)
@@ -147,6 +149,14 @@ static void __init setup_cpu_entry_area(int cpu)

cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline,
__pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
+ /*
+ * The cpu_entry_area alias addresses are not in the kernel binary
+ * so they do not show up in /proc/kcore normally. This adds entries
+ * for them manually.
+ */
+ kclist_add_remap(&per_cpu(kcore_entry_trampoline, cpu),
+ _entry_trampoline,
+ &get_cpu_entry_area(cpu)->entry_trampoline, PAGE_SIZE);
#endif
percpu_setup_debug_store(cpu);
}
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index e64ecb9f2720..00282f134336 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -383,8 +383,11 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
phdr->p_type = PT_LOAD;
phdr->p_flags = PF_R|PF_W|PF_X;
phdr->p_offset = kc_vaddr_to_offset(m->addr) + dataoff;
- phdr->p_vaddr = (size_t)m->addr;
- if (m->type == KCORE_RAM || m->type == KCORE_TEXT)
+ if (m->type == KCORE_REMAP)
+ phdr->p_vaddr = (size_t)m->vaddr;
+ else
+ phdr->p_vaddr = (size_t)m->addr;
+ if (m->type == KCORE_RAM || m->type == KCORE_TEXT || m->type == KCORE_REMAP)
phdr->p_paddr = __pa(m->addr);
else
phdr->p_paddr = (elf_addr_t)-1;
diff --git a/include/linux/kcore.h b/include/linux/kcore.h
index 8de55e4b5ee9..bc088ef96358 100644
--- a/include/linux/kcore.h
+++ b/include/linux/kcore.h
@@ -12,11 +12,13 @@ enum kcore_type {
KCORE_VMEMMAP,
KCORE_USER,
KCORE_OTHER,
+ KCORE_REMAP,
};

struct kcore_list {
struct list_head list;
unsigned long addr;
+ unsigned long vaddr;
size_t size;
int type;
};
@@ -36,11 +38,22 @@ struct vmcoredd_node {

#ifdef CONFIG_PROC_KCORE
extern void kclist_add(struct kcore_list *, void *, size_t, int type);
+static inline
+void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz)
+{
+ m->vaddr = (unsigned long)vaddr;
+ kclist_add(m, addr, sz, KCORE_REMAP);
+}
#else
static inline
void kclist_add(struct kcore_list *new, void *addr, size_t size, int type)
{
}
+
+static inline
+void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz)
+{
+}
#endif

#endif /* _LINUX_KCORE_H */
--
2.14.4