Skip to contentSkip to conversation

x86: simplify interrupt dispatch table

PATCH In review Denys Vlasenko 4 participants 4 messages Apr 3, 2015 – Apr 8, 2015 x86

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 x86: simplify interrupt dispatch table

Interrupt entry points are handled with the following code:
Each 32-byte code block contains seven entry points

		...
		[push][jump 22] // 4 bytes
		[push][jump 18] // 4 bytes
		[push][jump 14] // 4 bytes
		[push][jump 10] // 4 bytes
		[push][jump  6] // 4 bytes
		[push][jump  2] // 4 bytes
		[push][jump common_interrupt][padding] // 8 bytes

		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump common_interrupt][padding]

		[padding_2]
	common_interrupt:

And there is a table which holds pointers to every entry point,
IOW: to every push.

In cold cache, two jumps are still costlier than one, even though we get the benefit of them residing in the same cacheline.

This change replaces short jumps with near ones to common_interrupt, and pads every push+jump pair to 8 bytes. This way, each interrupt takes only one jump.

This change replaces ".p2align CONFIG_X86_L1_CACHE_SHIFT" before dispatch table with ".align 8" - we do not need anything stronger than that.

The table of entry addresses (the interrupt[] array) is no longer necessary, the address of entries can be easily calculated as (irq_entries_start + i*8).

text data bss dec hex filename

  12546	      0	      0	  12546	   3102	entry_64.o.before
  11626	      0	      0	  11626	   2d6a	entry_64.o

The size decrease is because 1656 bytes of .init.rodata are gone. That's initdata, though. The resident size does go up a bit.

Run-tested (32 and 64 bits).

CC Linus Torvalds <[email protected]>
CC Steven Rostedt <[email protected]>
CC Ingo Molnar <[email protected]>
CC Borislav Petkov <[email protected]>
CC "H. Peter Anvin" <[email protected]>
CC Andy Lutomirski <[email protected]>
CC Oleg Nesterov <[email protected]>
CC Frederic Weisbecker <[email protected]>
CC Alexei Starovoitov <[email protected]>
CC Will Drewry <[email protected]>
CC Kees Cook <[email protected]>
---
 arch/x86/include/asm/hw_irq.h |  5 ++---
 arch/x86/kernel/entry_32.S    | 41 ++++++++++-------------------------------
 arch/x86/kernel/entry_64.S    | 41 ++++++++++-------------------------------
 arch/x86/kernel/irqinit.c     |  3 ++-
 arch/x86/lguest/boot.c        |  3 ++-
 5 files changed, 26 insertions(+), 67 deletions(-)
arch/x86/include/asm/hw_irq.h +2 -3
index 9662290..e9571dd 100644
@@ -181,10 +181,9 @@ extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
 extern __visible void smp_invalidate_interrupt(struct pt_regs *);
 #endif
 
-extern void (*__initconst interrupt[FIRST_SYSTEM_VECTOR
-				    - FIRST_EXTERNAL_VECTOR])(void);
+extern char irq_entries_start[];
 #ifdef CONFIG_TRACING
-#define trace_interrupt interrupt
+#define trace_irq_entries_start irq_entries_start
 #endif
 
 #define VECTOR_UNDEFINED	(-1)
arch/x86/kernel/entry_32.S +10 -31

53 lines not on this page · raw message

arch/x86/kernel/entry_64.S +10 -31

54 lines not on this page · raw message

arch/x86/kernel/irqinit.c +2 -1
index 70e181e..cd10a64 100644
@@ -178,7 +178,8 @@ void __init native_init_IRQ(void)
 #endif
 	for_each_clear_bit_from(i, used_vectors, first_system_vector) {
 		/* IA32_SYSCALL_VECTOR could be used in trap_init already. */
-		set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]);
+		set_intr_gate(i, irq_entries_start +
+				8 * (i - FIRST_EXTERNAL_VECTOR));
 	}
 #ifdef CONFIG_X86_LOCAL_APIC
 	for_each_clear_bit_from(i, used_vectors, NR_VECTORS)
arch/x86/lguest/boot.c +2 -1
index 8561585..717908b 100644
@@ -868,7 +868,8 @@ static void __init lguest_init_IRQ(void)
 		/* Some systems map "vectors" to interrupts weirdly.  Not us! */
 		__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
 		if (i != SYSCALL_VECTOR)
-			set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]);
+			set_intr_gate(i, irq_entries_start +
+					8 * (i - FIRST_EXTERNAL_VECTOR));
 	}
 
 	/*
Signature · 1 line
1.8.1.4
#1 lore raw
Quoted 39 lines · Denys Vlasenko

Interrupt entry points are handled with the following code:
Each 32-byte code block contains seven entry points

		...
		[push][jump 22] // 4 bytes
		[push][jump 18] // 4 bytes
		[push][jump 14] // 4 bytes
		[push][jump 10] // 4 bytes
		[push][jump  6] // 4 bytes
		[push][jump  2] // 4 bytes
		[push][jump common_interrupt][padding] // 8 bytes

		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump common_interrupt][padding]

		[padding_2]
	common_interrupt:

And there is a table which holds pointers to every entry point,
IOW: to every push.

In cold cache, two jumps are still costlier than one, even though we get the benefit of them residing in the same cacheline.

This change replaces short jumps with near ones to common_interrupt, and pads every push+jump pair to 8 bytes. This way, each interrupt takes only one jump.

This change replaces ".p2align CONFIG_X86_L1_CACHE_SHIFT" before dispatch table with ".align 8" - we do not need anything stronger than that.

The table of entry addresses (the interrupt[] array) is no longer necessary, the address of entries can be easily calculated as (irq_entries_start + i*8).

Quoted 6 lines

text data bss dec hex filename

  12546	      0	      0	  12546	   3102	entry_64.o.before
  11626	      0	      0	  11626	   2d6a	entry_64.o

The size decrease is because 1656 bytes of .init.rodata are gone. That's initdata, though. The resident size does go up a bit.

So I like this a lot, as it's straight, simple and obvious, both to hardware and to humans as well. (This is btw. quite close to the irq entry code layout we used to have historically.)

We could do three other changes that would probably help a lot more in practice than the addition or elimination of a single instruction:

1)

We could try to not spread vectors, as modern APICs seem to handle clustered vectors a lot better and we don't actually use irq priority levels like other OSs so we are free to choose our vectors.

This compresses the I$ footprint a bit more if lots of related irq sources are firing towards the same CPUs that share one or more caches (HT threads, cores, node local siblings).

Even on single-node systems this would still compress the IDT and the entry code cache footprint a bit.

2)

We could allocate the IDT per CPU (or per node), lowering the D$ cache miss costs on NUMA systems. (This, if we allowed the IDTs to diverge, would also allow more irq sources sent to separate vectors.)

The simplest model of this, where each IDT is just a copy of each other, is relatively easy to implement, as the IDT is page aligned and ro mapped already.

3)

We could allocate the entry code itself too per cpu (or per node), lowering the I$ cache miss costs on NUMA systems. This would be a bit trickier to implement, as that part of the image has to be relinked during bootup, but is doable.

I'd do 3) only once we are done with the current audit/cleanup/rewrite of the entry code.

Thanks,

Ingo

maintainer
#2 lore raw
In reply to Denys Vlasenko
Quoted 62 lines · Denys Vlasenko

Interrupt entry points are handled with the following code:
Each 32-byte code block contains seven entry points

		...
		[push][jump 22] // 4 bytes
		[push][jump 18] // 4 bytes
		[push][jump 14] // 4 bytes
		[push][jump 10] // 4 bytes
		[push][jump  6] // 4 bytes
		[push][jump  2] // 4 bytes
		[push][jump common_interrupt][padding] // 8 bytes

		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump common_interrupt][padding]

		[padding_2]
	common_interrupt:

And there is a table which holds pointers to every entry point,
IOW: to every push.

In cold cache, two jumps are still costlier than one, even though we get the benefit of them residing in the same cacheline.

This change replaces short jumps with near ones to common_interrupt, and pads every push+jump pair to 8 bytes. This way, each interrupt takes only one jump.

This change replaces ".p2align CONFIG_X86_L1_CACHE_SHIFT" before dispatch table with ".align 8" - we do not need anything stronger than that.

The table of entry addresses (the interrupt[] array) is no longer necessary, the address of entries can be easily calculated as (irq_entries_start + i*8).

text data bss dec hex filename

  12546	      0	      0	  12546	   3102	entry_64.o.before
  11626	      0	      0	  11626	   2d6a	entry_64.o

The size decrease is because 1656 bytes of .init.rodata are gone. That's initdata, though. The resident size does go up a bit.

Run-tested (32 and 64 bits).

CC Linus Torvalds <[email protected]>
CC Steven Rostedt <[email protected]>
CC Ingo Molnar <[email protected]>
CC Borislav Petkov <[email protected]>
CC "H. Peter Anvin" <[email protected]>
CC Andy Lutomirski <[email protected]>
CC Oleg Nesterov <[email protected]>
CC Frederic Weisbecker <[email protected]>
CC Alexei Starovoitov <[email protected]>
CC Will Drewry <[email protected]>
CC Kees Cook <[email protected]>
Quoted 7 lines
---
 arch/x86/include/asm/hw_irq.h |  5 ++---
 arch/x86/kernel/entry_32.S    | 41 ++++++++++-------------------------------
 arch/x86/kernel/entry_64.S    | 41 ++++++++++-------------------------------
 arch/x86/kernel/irqinit.c     |  3 ++-
 arch/x86/lguest/boot.c        |  3 ++-
 5 files changed, 26 insertions(+), 67 deletions(-)
Signature · 5 lines
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.
--
#3 lore raw

[tip:x86/asm] x86/asm/entry/irq: Simplify interrupt dispatch table (IDT) layout

In reply to Denys Vlasenko
x86/asm/entry/irq: Simplify interrupt dispatch table (IDT) layout
Commit-ID:  3304c9c37bef30ebd2ef71d986e6568372ce80f8
Gitweb:     http://git.kernel.org/tip/3304c9c37bef30ebd2ef71d986e6568372ce80f8
Author:     Denys Vlasenko <[email protected]>
AuthorDate: Fri, 3 Apr 2015 21:49:13 +0200
Committer:  Ingo Molnar <[email protected]>
CommitDate: Wed, 8 Apr 2015 09:02:13 +0200

x86/asm/entry/irq: Simplify interrupt dispatch table (IDT) layout

Interrupt entry points are handled with the following code, each 32-byte code block contains seven entry points:

		...
		[push][jump 22] // 4 bytes
		[push][jump 18] // 4 bytes
		[push][jump 14] // 4 bytes
		[push][jump 10] // 4 bytes
		[push][jump  6] // 4 bytes
		[push][jump  2] // 4 bytes
		[push][jump common_interrupt][padding] // 8 bytes

		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump]
		[push][jump common_interrupt][padding]

		[padding_2]
	common_interrupt:

And there is a table which holds pointers to every entry point,
IOW: to every push.

In cold cache, two jumps are still costlier than one, even though we get the benefit of them residing in the same cacheline.

This change replaces short jumps with near ones to 'common_interrupt', and pads every push+jump pair to 8 bytes. This way, each interrupt takes only one jump.

This change replaces ".p2align CONFIG_X86_L1_CACHE_SHIFT" before dispatch table with ".align 8" - we do not need anything stronger than that.

The table of entry addresses (the interrupt[] array) is no longer necessary, the address of entries can be easily calculated as (irq_entries_start + i*8).

text data bss dec hex filename

  12546	      0	      0	  12546	   3102	entry_64.o.before
  11626	      0	      0	  11626	   2d6a	entry_64.o

The size decrease is because 1656 bytes of .init.rodata are gone. That's initdata, though. The resident size does go up a bit.

Run-tested (32 and 64 bits).

Cc Alexei Starovoitov <[email protected]>
Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc Frederic Weisbecker <[email protected]>
Cc H. Peter Anvin <[email protected]>
Cc Kees Cook <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Oleg Nesterov <[email protected]>
Cc Steven Rostedt <[email protected]>
Cc Will Drewry <[email protected]>
---
 arch/x86/include/asm/hw_irq.h |  5 ++---
 arch/x86/kernel/entry_32.S    | 41 ++++++++++-------------------------------
 arch/x86/kernel/entry_64.S    | 41 ++++++++++-------------------------------
 arch/x86/kernel/irqinit.c     |  3 ++-
 arch/x86/lguest/boot.c        |  3 ++-
 5 files changed, 26 insertions(+), 67 deletions(-)
arch/x86/include/asm/hw_irq.h +2 -3
index 9662290..e9571dd 100644
@@ -181,10 +181,9 @@ extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
 extern __visible void smp_invalidate_interrupt(struct pt_regs *);
 #endif
 
-extern void (*__initconst interrupt[FIRST_SYSTEM_VECTOR
-				    - FIRST_EXTERNAL_VECTOR])(void);
+extern char irq_entries_start[];
 #ifdef CONFIG_TRACING
-#define trace_interrupt interrupt
+#define trace_irq_entries_start irq_entries_start
 #endif
 
 #define VECTOR_UNDEFINED	(-1)
arch/x86/kernel/entry_32.S +10 -31

53 lines not on this page · raw message

arch/x86/kernel/entry_64.S +10 -31

54 lines not on this page · raw message

arch/x86/kernel/irqinit.c +2 -1
index 70e181e..cd10a64 100644
@@ -178,7 +178,8 @@ void __init native_init_IRQ(void)
 #endif
 	for_each_clear_bit_from(i, used_vectors, first_system_vector) {
 		/* IA32_SYSCALL_VECTOR could be used in trap_init already. */
-		set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]);
+		set_intr_gate(i, irq_entries_start +
+				8 * (i - FIRST_EXTERNAL_VECTOR));
 	}
 #ifdef CONFIG_X86_LOCAL_APIC
 	for_each_clear_bit_from(i, used_vectors, NR_VECTORS)
arch/x86/lguest/boot.c +2 -1
index 8561585..717908b 100644
@@ -868,7 +868,8 @@ static void __init lguest_init_IRQ(void)
 		/* Some systems map "vectors" to interrupts weirdly.  Not us! */
 		__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
 		if (i != SYSCALL_VECTOR)
-			set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]);
+			set_intr_gate(i, irq_entries_start +
+					8 * (i - FIRST_EXTERNAL_VECTOR));
 	}
 
 	/*