parisc: Add alternative coding infrastructure

This patch adds the necessary code to patch a running kernel at runtime
to improve performance.

The current implementation offers a few optimizations variants:

- When running a SMP kernel on a single UP processor, unwanted assembler
  statements like locking functions are overwritten with NOPs. When
  multiple instructions shall be skipped, one branch instruction is used
  instead of multiple nop instructions.

- In the UP case, some pdtlb and pitlb instructions are patched to
  become pdtlb,l and pitlb,l which only flushes the CPU-local tlb
  entries instead of broadcasting the flush to other CPUs in the system
  and thus may improve performance.

- fic and fdc instructions are skipped if no I- or D-caches are
  installed.  This should speed up qemu emulation and cacheless systems.

- If no cache coherence is needed for IO operations, the relevant fdc
  and sync instructions in the sba and ccio drivers are replaced by
  nops.

- On systems which share I- and D-TLBs and thus don't have a seperate
  instruction TLB, the pitlb instruction is replaced by a nop.

Live-patching is done early in the boot process, just after having run
the system inventory. No drivers are running and thus no external
interrupts should arrive. So the hope is that no TLB exceptions will
occur during the patching. If this turns out to be wrong we will
probably need to do the patching in real-mode.

Signed-off-by: Helge Deller <deller@gmx.de>

1 files changed, 81 insertions, 0 deletions

diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 4e87c35c22b7..db6e7957f9a3 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -305,6 +305,86 @@ static int __init parisc_init_resources(void)
 	return 0;
 }
 
+static int no_alternatives __initdata;
+static int __init setup_no_alternatives(char *str)
+{
+	no_alternatives = 1;
+	return 1;
+}
+__setup("no-alternatives", setup_no_alternatives);
+
+static void __init apply_alternatives_all(void)
+{
+	struct alt_instr *entry;
+	int index = 0, applied = 0;
+
+
+	pr_info("alternatives: %spatching kernel code\n",
+		no_alternatives ? "NOT " : "");
+	if (no_alternatives)
+		return;
+
+	set_kernel_text_rw(1);
+
+	for (entry = (struct alt_instr *) &__alt_instructions;
+		entry < (struct alt_instr *) &__alt_instructions_end;
+		entry++, index++) {
+
+		u32 *from, len, cond, replacement;
+
+		from = (u32 *)((ulong)&entry->orig_offset + entry->orig_offset);
+		len = entry->len;
+		cond = entry->cond;
+		replacement = entry->replacement;
+
+		WARN_ON(!cond);
+		pr_debug("Check %d: Cond 0x%x, Replace %02d instructions @ 0x%px with 0x%08x\n",
+			index, cond, len, from, replacement);
+
+		if ((cond & ALT_COND_NO_SMP) && (num_online_cpus() != 1))
+			continue;
+		if ((cond & ALT_COND_NO_DCACHE) && (cache_info.dc_size != 0))
+			continue;
+		if ((cond & ALT_COND_NO_ICACHE) && (cache_info.ic_size != 0))
+			continue;
+
+		/*
+		 * If the PDC_MODEL capabilities has Non-coherent IO-PDIR bit
+		 * set (bit #61, big endian), we have to flush and sync every
+		 * time IO-PDIR is changed in Ike/Astro.
+		 */
+		if ((cond & ALT_COND_NO_IOC_FDC) &&
+			(boot_cpu_data.pdc.capabilities & PDC_MODEL_IOPDIR_FDC))
+			continue;
+
+		/* Want to replace pdtlb by a pdtlb,l instruction? */
+		if (replacement == INSN_PxTLB) {
+			replacement = *from;
+			if (boot_cpu_data.cpu_type >= pcxu) /* >= pa2.0 ? */
+				replacement |= (1 << 10); /* set el bit */
+		}
+
+		/*
+		 * Replace instruction with NOPs?
+		 * For long distance insert a branch instruction instead.
+		 */
+		if (replacement == INSN_NOP && len > 1)
+			replacement = 0xe8000002 + (len-2)*8; /* "b,n .+8" */
+
+		pr_debug("Do    %d: Cond 0x%x, Replace %02d instructions @ 0x%px with 0x%08x\n",
+			index, cond, len, from, replacement);
+
+		/* Replace instruction */
+		*from = replacement;
+		applied++;
+	}
+
+	pr_info("alternatives: applied %d out of %d patches\n", applied, index);
+
+	set_kernel_text_rw(0);
+}
+
+
 extern void gsc_init(void);
 extern void processor_init(void);
 extern void ccio_init(void);
@@ -346,6 +426,7 @@ static int __init parisc_init(void)
 			boot_cpu_data.cpu_hz / 1000000,
 			boot_cpu_data.cpu_hz % 1000000	);
 
+	apply_alternatives_all();
 	parisc_setup_cache_timing();
 
 	/* These are in a non-obvious order, will fix when we have an iotree */