[PATCH v2] ARM: uprobes need icache flush after xol write
Victor Kamensky
victor.kamensky at linaro.org
Tue Apr 8 22:58:52 PDT 2014
After instruction write into xol area, on ARM V7
architecture code need to flush dcache and icache to sync
them up for given set of addresses. Having just
'flush_dcache_page(page)' call is not enough - it is
possible to have stale instruction sitting in icache
for given xol area slot address.
Introduce arch_uprobe_flush_xol_access weak function
that by default calls 'flush_dcache_page(page)' and on
ARM define new one that calls flush_uprobe_xol_access
function.
flush_uprobe_xol_access function shares/reuses implementation
with/of flush_ptrace_access function and takes care of writing
instruction to user land address space on given variety of
different cache types on ARM CPUs. Because
flush_uprobe_xol_access does not have vma around
flush_ptrace_access was split into two parts. First that
retrieves set of condition from vma and common that receives
those conditions as flags.
Because on ARM cache flush function need kernel address
through which instruction write happened, changed
xol_get_insn_slot to explicitly map page and do memcpy
rather than use copy_to_page helper. In this case
xol_get_insn_slot knows kernel address and passes it to
arch_uprobe_flush_xol_access function.
Signed-off-by: Victor Kamensky <victor.kamensky at linaro.org>
---
arch/arm/include/asm/cacheflush.h | 2 ++
arch/arm/kernel/uprobes.c | 6 ++++++
arch/arm/mm/flush.c | 41 +++++++++++++++++++++++++++++++++------
include/linux/uprobes.h | 3 +++
kernel/events/uprobes.c | 33 +++++++++++++++++++++++++------
5 files changed, 73 insertions(+), 12 deletions(-)
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 8b8b616..e02712a 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -487,4 +487,6 @@ int set_memory_rw(unsigned long addr, int numpages);
int set_memory_x(unsigned long addr, int numpages);
int set_memory_nx(unsigned long addr, int numpages);
+void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
+ void *kaddr, unsigned long len);
#endif
diff --git a/arch/arm/kernel/uprobes.c b/arch/arm/kernel/uprobes.c
index f9bacee..a0339a6 100644
--- a/arch/arm/kernel/uprobes.c
+++ b/arch/arm/kernel/uprobes.c
@@ -113,6 +113,12 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
return 0;
}
+void arch_uprobe_flush_xol_access(struct page *page, unsigned long vaddr,
+ void *kaddr, unsigned long len)
+{
+ flush_uprobe_xol_access(page, vaddr, kaddr, len);
+}
+
int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
{
struct uprobe_task *utask = current->utask;
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 3387e60..69a0bd08 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -104,17 +104,21 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig
#define flush_icache_alias(pfn,vaddr,len) do { } while (0)
#endif
+#define FLAG_UA_IS_EXEC 1
+#define FLAG_UA_CORE_IN_MM 2
+#define FLAG_UA_BROADCAST 4
+
static void flush_ptrace_access_other(void *args)
{
__flush_icache_all();
}
-static
-void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
- unsigned long uaddr, void *kaddr, unsigned long len)
+static inline
+void __flush_ptrace_access(struct page *page, unsigned long uaddr, void *kaddr,
+ unsigned long len, unsigned int flags)
{
if (cache_is_vivt()) {
- if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+ if (flags & FLAG_UA_CORE_IN_MM) {
unsigned long addr = (unsigned long)kaddr;
__cpuc_coherent_kern_range(addr, addr + len);
}
@@ -128,18 +132,43 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
}
/* VIPT non-aliasing D-cache */
- if (vma->vm_flags & VM_EXEC) {
+ if (flags & FLAG_UA_IS_EXEC) {
unsigned long addr = (unsigned long)kaddr;
if (icache_is_vipt_aliasing())
flush_icache_alias(page_to_pfn(page), uaddr, len);
else
__cpuc_coherent_kern_range(addr, addr + len);
- if (cache_ops_need_broadcast())
+ if (flags & FLAG_UA_BROADCAST)
smp_call_function(flush_ptrace_access_other,
NULL, 1);
}
}
+static
+void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
+ unsigned long uaddr, void *kaddr, unsigned long len)
+{
+ unsigned int flags = 0;
+ if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+ flags |= FLAG_UA_CORE_IN_MM;
+ }
+ if (vma->vm_flags & VM_EXEC) {
+ flags |= FLAG_UA_IS_EXEC;
+ }
+ if (cache_ops_need_broadcast()) {
+ flags |= FLAG_UA_BROADCAST;
+ }
+ __flush_ptrace_access(page, uaddr, kaddr, len, flags);
+}
+
+void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
+ void *kaddr, unsigned long len)
+{
+ unsigned int flags = FLAG_UA_CORE_IN_MM|FLAG_UA_IS_EXEC;
+
+ __flush_ptrace_access(page, uaddr, kaddr, len, flags);
+}
+
/*
* Copy user data from/to a page which is mapped into a different
* processes address space. Really, we want to allow our "user
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index edff2b9..534e083 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -32,6 +32,7 @@ struct vm_area_struct;
struct mm_struct;
struct inode;
struct notifier_block;
+struct page;
#define UPROBE_HANDLER_REMOVE 1
#define UPROBE_HANDLER_MASK 1
@@ -127,6 +128,8 @@ extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned l
extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
extern bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs);
+extern void __weak arch_uprobe_flush_xol_access(struct page *page, unsigned long vaddr,
+ void *kaddr, unsigned long len);
#else /* !CONFIG_UPROBES */
struct uprobes_state {
};
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 04709b6..b9142d5 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1287,6 +1287,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
{
struct xol_area *area;
unsigned long xol_vaddr;
+ void *xol_page_kaddr;
area = get_xol_area();
if (!area)
@@ -1296,14 +1297,22 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
if (unlikely(!xol_vaddr))
return 0;
- /* Initialize the slot */
- copy_to_page(area->page, xol_vaddr,
- &uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
/*
- * We probably need flush_icache_user_range() but it needs vma.
- * This should work on supported architectures too.
+ * We don't use copy_to_page here because we need kernel page
+ * addr to invalidate caches correctly
*/
- flush_dcache_page(area->page);
+ xol_page_kaddr = kmap_atomic(area->page);
+
+ /* Initialize the slot */
+ memcpy(xol_page_kaddr + (xol_vaddr & ~PAGE_MASK),
+ &uprobe->arch.ixol,
+ sizeof(uprobe->arch.ixol));
+
+ arch_uprobe_flush_xol_access(area->page, xol_vaddr,
+ xol_page_kaddr + (xol_vaddr & ~PAGE_MASK),
+ sizeof(uprobe->arch.ixol));
+
+ kunmap_atomic(xol_page_kaddr);
return xol_vaddr;
}
@@ -1346,6 +1355,18 @@ static void xol_free_insn_slot(struct task_struct *tsk)
}
}
+void __weak arch_uprobe_flush_xol_access(struct page *page, unsigned long vaddr,
+ void *kaddr, unsigned long len)
+{
+ /*
+ * We probably need flush_icache_user_range() but it needs vma.
+ * This should work on most of architectures by default. If
+ * architecture needs to do something different it can define
+ * its own version of the function.
+ */
+ flush_dcache_page(page);
+}
+
/**
* uprobe_get_swbp_addr - compute address of swbp given post-swbp regs
* @regs: Reflects the saved state of the task after it has hit a breakpoint
--
1.8.1.4
More information about the linux-arm-kernel
mailing list