From 0cac21b02ba5f3095fd2dcc77c26a25a0b2432ed Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Mon, 6 Jul 2020 14:32:26 +0200 Subject: riscv: use 16KB kernel stack on 64-bit With the current 8KB stack size there are frequent overflows in a 64-bit configuration. We may split IRQ stacks off in the future, but this fixes a number of issues right now. Signed-off-by: Andreas Schwab Reviewed-by: Anup Patel [Palmer: mention irqstack in the commit text] Fixes: 7db91e57a0ac ("RISC-V: Task implementation") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/thread_info.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 1dd12a0cbb2b..464a2bbc97ea 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -12,7 +12,11 @@ #include /* thread information allocation */ +#ifdef CONFIG_64BIT +#define THREAD_SIZE_ORDER (2) +#else #define THREAD_SIZE_ORDER (1) +#endif #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) #ifndef __ASSEMBLY__ -- cgit v1.2.3 From 38b7c2a3ffb1fce8358ddc6006cfe5c038ff9963 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Thu, 16 Jul 2020 11:57:26 -0700 Subject: RISC-V: Upgrade smp_mb__after_spinlock() to iorw,iorw While digging through the recent mmiowb preemption issue it came up that we aren't actually preventing IO from crossing a scheduling boundary. While it's a bit ugly to overload smp_mb__after_spinlock() with this behavior, it's what PowerPC is doing so there's some precedent. Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/barrier.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index 3f1737f301cc..d0e24aaa2aa0 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -58,8 +58,16 @@ do { \ * The AQ/RL pair provides a RCpc critical section, but there's not really any * way we can take advantage of that here because the ordering is only enforced * on that one lock. Thus, we're just doing a full fence. + * + * Since we allow writeX to be called from preemptive regions we need at least + * an "o" in the predecessor set to ensure device writes are visible before the + * task is marked as available for scheduling on a new hart. While I don't see + * any concrete reason we need a full IO fence, it seems safer to just upgrade + * this in order to avoid any IO crossing a scheduling boundary. In both + * instances the scheduler pairs this with an mb(), so nothing is necessary on + * the new hart. */ -#define smp_mb__after_spinlock() RISCV_FENCE(rw,rw) +#define smp_mb__after_spinlock() RISCV_FENCE(iorw,iorw) #include -- cgit v1.2.3