From 7230c5644188cd9e3fb380cc97dde00c464a3ba7 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 6 Mar 2012 18:27:59 +1100 Subject: powerpc: Rework lazy-interrupt handling The current implementation of lazy interrupts handling has some issues that this tries to address. We don't do the various workarounds we need to do when re-enabling interrupts in some cases such as when returning from an interrupt and thus we may still lose or get delayed decrementer or doorbell interrupts. The current scheme also makes it much harder to handle the external "edge" interrupts provided by some BookE processors when using the EPR facility (External Proxy) and the Freescale Hypervisor. Additionally, we tend to keep interrupts hard disabled in a number of cases, such as decrementer interrupts, external interrupts, or when a masked decrementer interrupt is pending. This is sub-optimal. This is an attempt at fixing it all in one go by reworking the way we do the lazy interrupt disabling from the ground up. The base idea is to replace the "hard_enabled" field with a "irq_happened" field in which we store a bit mask of what interrupt occurred while soft-disabled. When re-enabling, either via arch_local_irq_restore() or when returning from an interrupt, we can now decide what to do by testing bits in that field. We then implement replaying of the missed interrupts either by re-using the existing exception frame (in exception exit case) or via the creation of a new one from an assembly trampoline (in the arch_local_irq_enable case). This removes the need to play with the decrementer to try to create fake interrupts, among others. In addition, this adds a few refinements: - We no longer hard disable decrementer interrupts that occur while soft-disabled. We now simply bump the decrementer back to max (on BookS) or leave it stopped (on BookE) and continue with hard interrupts enabled, which means that we'll potentially get better sample quality from performance monitor interrupts. - Timer, decrementer and doorbell interrupts now hard-enable shortly after removing the source of the interrupt, which means they no longer run entirely hard disabled. Again, this will improve perf sample quality. - On Book3E 64-bit, we now make the performance monitor interrupt act as an NMI like Book3S (the necessary C code for that to work appear to already be present in the FSL perf code, notably calling nmi_enter instead of irq_enter). (This also fixes a bug where BookE perfmon interrupts could clobber r14 ... oops) - We could make "masked" decrementer interrupts act as NMIs when doing timer-based perf sampling to improve the sample quality. Signed-off-by-yet: Benjamin Herrenschmidt --- v2: - Add hard-enable to decrementer, timer and doorbells - Fix CR clobber in masked irq handling on BookE - Make embedded perf interrupt act as an NMI - Add a PACA_HAPPENED_EE_EDGE for use by FSL if they want to retrigger an interrupt without preventing hard-enable v3: - Fix or vs. ori bug on Book3E - Fix enabling of interrupts for some exceptions on Book3E v4: - Fix resend of doorbells on return from interrupt on Book3E v5: - Rebased on top of my latest series, which involves some significant rework of some aspects of the patch. v6: - 32-bit compile fix - more compile fixes with various .config combos - factor out the asm code to soft-disable interrupts - remove the C wrapper around preempt_schedule_irq v7: - Fix a bug with hard irq state tracking on native power7 --- arch/powerpc/kernel/head_64.S | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/kernel/head_64.S') diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 40759fbfb171..58bddee8e1e8 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -38,6 +38,7 @@ #include #include #include +#include /* The physical memory is laid out such that the secondary processor * spin code sits at 0x0000...0x00ff. On server, the vectors follow @@ -550,7 +551,8 @@ _GLOBAL(pmac_secondary_start) */ li r0,0 stb r0,PACASOFTIRQEN(r13) - stb r0,PACAHARDIRQEN(r13) + li r0,PACA_IRQ_HARD_DIS + stb r0,PACAIRQHAPPENED(r13) /* Create a temp kernel stack for use before relocation is on. */ ld r1,PACAEMERGSP(r13) @@ -601,9 +603,12 @@ __secondary_start: li r7,0 mtlr r7 - /* Mark interrupts both hard and soft disabled */ - stb r7,PACAHARDIRQEN(r13) + /* Mark interrupts soft and hard disabled (they might be enabled + * in the PACA when doing hotplug) + */ stb r7,PACASOFTIRQEN(r13) + li r0,PACA_IRQ_HARD_DIS + stb r0,PACAIRQHAPPENED(r13) /* enable MMU and jump to start_secondary */ LOAD_REG_ADDR(r3, .start_secondary_prolog) @@ -750,13 +755,18 @@ _INIT_GLOBAL(start_here_common) /* Load the TOC (virtual address) */ ld r2,PACATOC(r13) + /* Do more system initializations in virtual mode */ bl .setup_system - /* Load up the kernel context */ -5: li r5,0 - stb r5,PACASOFTIRQEN(r13) /* Soft Disabled */ - stb r5,PACAHARDIRQEN(r13) /* Hard Disabled on others */ + /* Mark interrupts soft and hard disabled (they might be enabled + * in the PACA when doing hotplug) + */ + li r0,0 + stb r0,PACASOFTIRQEN(r13) + li r0,PACA_IRQ_HARD_DIS + stb r0,PACAIRQHAPPENED(r13) + /* Generic kernel entry */ bl .start_kernel /* Not reached */ -- cgit v1.2.3