lkml.org 
[lkml]   [2019]   [Apr]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[tip:x86/alternatives] x86/alternative: Batch of patch operations
Commit-ID:  76ec759ad71c1fa0c4b327367e82b2650109a22f
Gitweb: https://git.kernel.org/tip/76ec759ad71c1fa0c4b327367e82b2650109a22f
Author: Daniel Bristot de Oliveira <bristot@redhat.com>
AuthorDate: Fri, 21 Dec 2018 11:27:32 +0100
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Fri, 19 Apr 2019 19:37:35 +0200

x86/alternative: Batch of patch operations

Currently, the patch of an address is done in three steps:

-- Pseudo-code #1 - Current implementation ---
1) add an int3 trap to the address that will be patched
sync cores (send IPI to all other CPUs)
2) update all but the first byte of the patched range
sync cores (send IPI to all other CPUs)
3) replace the first byte (int3) by the first byte of replacing opcode
sync cores (send IPI to all other CPUs)
-- Pseudo-code #1 ---

When a static key has more than one entry, these steps are called once for
each entry. The number of IPIs then is linear with regard to the number 'n' of
entries of a key: O(n*3), which is O(n).

This algorithm works fine for the update of a single key. But we think
it is possible to optimize the case in which a static key has more than
one entry. For instance, the sched_schedstats jump label has 56 entries
in my (updated) fedora kernel, resulting in 168 IPIs for each CPU in
which the thread that is enabling the key is _not_ running.

With this patch, rather than receiving a single patch to be processed, a vector
of patches is passed, enabling the rewrite of the pseudo-code #1 in this
way:

-- Pseudo-code #2 - This patch ---
1) for each patch in the vector:
add an int3 trap to the address that will be patched

sync cores (send IPI to all other CPUs)

2) for each patch in the vector:
update all but the first byte of the patched range

sync cores (send IPI to all other CPUs)

3) for each patch in the vector:
replace the first byte (int3) by the first byte of replacing opcode

sync cores (send IPI to all other CPUs)
-- Pseudo-code #2 - This patch ---

Doing the update in this way, the number of IPI becomes O(3) with regard
to the number of keys, which is O(1).

The batch mode is done with the function text_poke_bp_batch(), that receives
two arguments: a vector of "struct text_to_poke", and the number of entries
in the vector.

The vector must be sorted by the addr field of the text_to_poke structure,
enabling the binary search of a handler in the poke_int3_handler function
(a fast path).

Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Chris von Recklinghausen <crecklin@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Wood <swood@redhat.com>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/e3057f0d0bddd625de6d4e7c631faf734e28628b.1545228276.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/include/asm/text-patching.h | 15 +++++
arch/x86/kernel/alternative.c | 108 +++++++++++++++++++++++++++++++++--
2 files changed, 117 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index e85ff65c43c3..42ea7846df33 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -18,6 +18,20 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
#define __parainstructions_end NULL
#endif

+/*
+ * Currently, the max observed size in the kernel code is
+ * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5.
+ * Raise it if needed.
+ */
+#define POKE_MAX_OPCODE_SIZE 5
+
+struct text_to_poke {
+ void *handler;
+ void *addr;
+ size_t len;
+ const char opcode[POKE_MAX_OPCODE_SIZE];
+};
+
extern void *text_poke_early(void *addr, const void *opcode, size_t len);

/*
@@ -37,6 +51,7 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
extern void *text_poke(void *addr, const void *opcode, size_t len);
extern int poke_int3_handler(struct pt_regs *regs);
extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern void text_poke_bp_batch(struct text_to_poke *tp, unsigned int nr_entries);
extern int after_bootmem;

#endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 7fce844017f1..0048fd953596 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -22,6 +22,7 @@
#include <asm/tlbflush.h>
#include <asm/io.h>
#include <asm/fixmap.h>
+#include <linux/bsearch.h>

int __read_mostly alternatives_patched;

@@ -739,10 +740,32 @@ static void do_sync_core(void *info)
}

static bool bp_patching_in_progress;
+/*
+ * Single poke.
+ */
static void *bp_int3_handler, *bp_int3_addr;
+/*
+ * Batching poke.
+ */
+static struct text_to_poke *bp_int3_tpv;
+static unsigned int bp_int3_tpv_nr;
+
+static int text_bp_batch_bsearch(const void *key, const void *elt)
+{
+ struct text_to_poke *tp = (struct text_to_poke *) elt;
+
+ if (key < tp->addr)
+ return -1;
+ if (key > tp->addr)
+ return 1;
+ return 0;
+}

int poke_int3_handler(struct pt_regs *regs)
{
+ void *ip;
+ struct text_to_poke *tp;
+
/*
* Having observed our INT3 instruction, we now must observe
* bp_patching_in_progress.
@@ -758,21 +781,41 @@ int poke_int3_handler(struct pt_regs *regs)
if (likely(!bp_patching_in_progress))
return 0;

- if (user_mode(regs) || regs->ip != (unsigned long)bp_int3_addr)
+ if (user_mode(regs))
return 0;

- /* set up the specified breakpoint handler */
- regs->ip = (unsigned long) bp_int3_handler;
+ /*
+ * Single poke first.
+ */
+ if (bp_int3_addr) {
+ if (regs->ip == (unsigned long) bp_int3_addr) {
+ regs->ip = (unsigned long) bp_int3_handler;
+ return 1;
+ }
+ return 0;
+ }

- return 1;
+ /*
+ * Batch mode.
+ */
+ if (bp_int3_tpv_nr) {
+ ip = (void *) regs->ip - sizeof(unsigned char);
+ tp = bsearch(ip, bp_int3_tpv, bp_int3_tpv_nr,
+ sizeof(struct text_to_poke),
+ text_bp_batch_bsearch);
+ if (tp) {
+ /* set up the specified breakpoint handler */
+ regs->ip = (unsigned long) tp->handler;
+ return 1;
+ }
+ }
+ return 0;
}
NOKPROBE_SYMBOL(poke_int3_handler);

static void text_poke_bp_set_handler(void *addr, void *handler,
unsigned char int3)
{
- bp_int3_handler = handler;
- bp_int3_addr = (u8 *)addr + sizeof(int3);
text_poke(addr, &int3, sizeof(int3));
}

@@ -817,6 +860,9 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)

lockdep_assert_held(&text_mutex);

+ bp_int3_handler = handler;
+ bp_int3_addr = (u8 *)addr + sizeof(int3);
+
bp_patching_in_progress = true;
/*
* Corresponding read barrier in int3 notifier for making sure the
@@ -847,6 +893,56 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
*/
bp_patching_in_progress = false;

+ bp_int3_handler = bp_int3_addr = 0;
return addr;
}

+void text_poke_bp_batch(struct text_to_poke *tp, unsigned int nr_entries)
+{
+ unsigned int i;
+ unsigned char int3 = 0xcc;
+ int patched_all_but_first = 0;
+
+ bp_int3_tpv = tp;
+ bp_int3_tpv_nr = nr_entries;
+ bp_patching_in_progress = true;
+ /*
+ * Corresponding read barrier in int3 notifier for making sure the
+ * in_progress and handler are correctly ordered wrt. patching.
+ */
+ smp_wmb();
+
+ for (i = 0; i < nr_entries; i++)
+ text_poke_bp_set_handler(tp[i].addr, tp[i].handler, int3);
+
+ on_each_cpu(do_sync_core, NULL, 1);
+
+ for (i = 0; i < nr_entries; i++) {
+ if (tp[i].len - sizeof(int3) > 0) {
+ patch_all_but_first_byte(tp[i].addr, tp[i].opcode,
+ tp[i].len, int3);
+ patched_all_but_first++;
+ }
+ }
+
+ if (patched_all_but_first) {
+ /*
+ * According to Intel, this core syncing is very likely
+ * not necessary and we'd be safe even without it. But
+ * better safe than sorry (plus there's not only Intel).
+ */
+ on_each_cpu(do_sync_core, NULL, 1);
+ }
+
+ for (i = 0; i < nr_entries; i++)
+ patch_first_byte(tp[i].addr, tp[i].opcode, int3);
+
+ on_each_cpu(do_sync_core, NULL, 1);
+ /*
+ * sync_core() implies an smp_mb() and orders this store against
+ * the writing of the new instruction.
+ */
+ bp_int3_tpv_nr = 0;
+ bp_int3_tpv = NULL;
+ bp_patching_in_progress = false;
+}
\
 
 \ /
  Last update: 2019-04-19 20:44    [W:0.336 / U:0.100 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site