s390/ftrace: implement hotpatching

s390 allows hotpatching the mask of a conditional jump instruction.
Make use of this feature in order to avoid the expensive stop_machine()
call.

The new trampolines are split in 3 stages:

- A first stage is a 6-byte relative conditional long branch located at
  each function's entry point. Its offset always points to the second
  stage for the corresponding function, and its mask is either all 0s
  (ftrace off) or all 1s (ftrace on). The code for flipping the mask is
  borrowed from ftrace_{enable,disable}_ftrace_graph_caller. After
  flipping, ftrace_arch_code_modify_post_process() syncs with all the
  other CPUs by sending SIGPs.

- Second stages for vmlinux are stored in a separate part of the .text
  section reserved by the linker script, and in dynamically allocated
  memory for modules. This prevents the icache pollution. The total
  size of second stages is about 1.5% of that of the kernel image.

  Putting second stages in the .bss section is possible and decreases
  the size of the non-compressed vmlinux, but splits the kernel 1:1
  mapping, which is a bad tradeoff.

  Each second stage contains a call to the third stage, a pointer to
  the part of the intercepted function right after the first stage, and
  a pointer to an interceptor function (e.g. ftrace_caller).

  Second stages are 8-byte aligned for the future direct calls
  implementation.

- There are only two copies of the third stage: in the .text section
  for vmlinux and in dynamically allocated memory for modules. It can be
  an expoline, which is relatively large, so inlining it into each
  second stage is prohibitively expensive.

As a result of this organization, phoronix-test-suite with ftrace off
does not show any performance degradation.

Suggested-by: Sven Schnelle <svens@linux.ibm.com>
Suggested-by: Vasily Gorbik <gor@linux.ibm.com>
Co-developed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Link: https://lore.kernel.org/r/20210728212546.128248-3-iii@linux.ibm.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>

1 files changed, 45 insertions, 0 deletions

diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 4055f1c49814..b01ba460b7ca 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -14,6 +14,7 @@
 #include <linux/elf.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
+#include <linux/ftrace.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/kasan.h>
@@ -23,6 +24,8 @@
 #include <asm/alternative.h>
 #include <asm/nospec-branch.h>
 #include <asm/facility.h>
+#include <asm/ftrace.lds.h>
+#include <asm/set_memory.h>
 
 #if 0
 #define DEBUGP printk
@@ -48,6 +51,13 @@ void *module_alloc(unsigned long size)
 	return p;
 }
 
+#ifdef CONFIG_FUNCTION_TRACER
+void module_arch_cleanup(struct module *mod)
+{
+	module_memfree(mod->arch.trampolines_start);
+}
+#endif
+
 void module_arch_freeing_init(struct module *mod)
 {
 	if (is_livepatch_module(mod) &&
@@ -466,6 +476,30 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 				    write);
 }
 
+#ifdef CONFIG_FUNCTION_TRACER
+static int module_alloc_ftrace_hotpatch_trampolines(struct module *me,
+						    const Elf_Shdr *s)
+{
+	char *start, *end;
+	int numpages;
+	size_t size;
+
+	size = FTRACE_HOTPATCH_TRAMPOLINES_SIZE(s->sh_size);
+	numpages = DIV_ROUND_UP(size, PAGE_SIZE);
+	start = module_alloc(numpages * PAGE_SIZE);
+	if (!start)
+		return -ENOMEM;
+	set_memory_ro((unsigned long)start, numpages);
+	end = start + size;
+
+	me->arch.trampolines_start = (struct ftrace_hotpatch_trampoline *)start;
+	me->arch.trampolines_end = (struct ftrace_hotpatch_trampoline *)end;
+	me->arch.next_trampoline = me->arch.trampolines_start;
+
+	return 0;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+
 int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
@@ -473,6 +507,9 @@ int module_finalize(const Elf_Ehdr *hdr,
 	const Elf_Shdr *s;
 	char *secstrings, *secname;
 	void *aseg;
+#ifdef CONFIG_FUNCTION_TRACER
+	int ret;
+#endif
 
 	if (IS_ENABLED(CONFIG_EXPOLINE) &&
 	    !nospec_disable && me->arch.plt_size) {
@@ -507,6 +544,14 @@ int module_finalize(const Elf_Ehdr *hdr,
 		if (IS_ENABLED(CONFIG_EXPOLINE) &&
 		    (str_has_prefix(secname, ".s390_return")))
 			nospec_revert(aseg, aseg + s->sh_size);
+
+#ifdef CONFIG_FUNCTION_TRACER
+		if (!strcmp(FTRACE_CALLSITE_SECTION, secname)) {
+			ret = module_alloc_ftrace_hotpatch_trampolines(me, s);
+			if (ret < 0)
+				return ret;
+		}
+#endif /* CONFIG_FUNCTION_TRACER */
 	}
 
 	jump_label_apply_nops(me);