Date: Tue, 14 Apr 2015 08:42:52 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Rusty Russell <rusty@rustcorp.com.au>
Cc: Ingo Molnar <mingo@kernel.org>, mathieu.desnoyers@efficios.com,
        oleg@redhat.com, paulmck@linux.vnet.ibm.com,
        torvalds@linux-foundation.org, linux-kernel@vger.kernel.org,
        andi@firstfloor.org, rostedt@goodmis.org, tglx@linutronix.de,
        laijs@cn.fujitsu.com, linux@horizon.com
Subject: Re: [PATCH v5 10/10] module: Rework module_addr_{min,max}
Message-ID: <20150414064252.GN23123@twins.programming.kicks-ass.net>
References: <20150413141126.756350256@infradead.org>
 <20150413141213.800009335@infradead.org>
 <20150413165636.GH6040@gmail.com>
 <87y4lvs9ji.fsf@rustcorp.com.au>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <87y4lvs9ji.fsf@rustcorp.com.au>
User-Agent: Mutt/1.5.21 (2012-12-30)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1849
Lines: 47

On Tue, Apr 14, 2015 at 12:25:45PM +0930, Rusty Russell wrote:
> Ingo Molnar <mingo@kernel.org> writes:
> > * Peter Zijlstra <peterz@infradead.org> wrote:
> >
> >> __module_address() does an initial bound check before doing the 
> >> {list/tree} iteration to find the actual module. The bound variables 
> >> are nowhere near the mod_tree cacheline, in fact they're nowhere 
> >> near one another.
> >> 
> >> module_addr_min lives in .data while module_addr_max lives in .bss 
> >> (smarty pants GCC thinks the explicit 0 assignment is a mistake).
> >> 
> >> Rectify this by moving the two variables into a structure together 
> >> with the latch_tree_root to guarantee they all share the same 
> >> cacheline and avoid hitting two extra cachelines for the lookup.
> >> 
> >> While reworking the bounds code, move the bound update from 
> >> allocation to insertion time, this avoids updating the bounds for a 
> >> few error paths.
> >
> >> +static struct mod_tree_root {
> >> +	struct latch_tree_root root;
> >> +	unsigned long addr_min;
> >> +	unsigned long addr_max;
> >> +} mod_tree __cacheline_aligned = {
> >> +	.addr_min = -1UL,
> >> +};
> >> +
> >> +#define module_addr_min mod_tree.addr_min
> >> +#define module_addr_max mod_tree.addr_max
> 
> Nice catch.
> 
> Does the min/max comparison still win us anything?  (I'm guessing yes...)

Yep, while a tree iteration is much faster than the linear thing it is
still quite a bit slower than two simple compares.

> In general, I'm happy with this series.  Assume you want another
> go-round for Ingo's tweaks, then I'll take them for 4.2.

Thanks!
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/