Re: [PATCH v3 2/2] lib/test_vmalloc.c: Add vm_map_ram()/vm_unmap_ram() test case

[Uladzislau Rezki]

> On Mon, Mar 27, 2023 at 07:01:26PM +0200, Uladzislau Rezki (Sony) wrote:
> > Add vm_map_ram()/vm_unmap_ram() test case to our stress test-suite.
> >
> > Signed-off-by: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
> > ---
> >  lib/test_vmalloc.c | 41 +++++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 41 insertions(+)
> >
> > diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
> > index cd2bdba6d3ed..6633eda4cd4d 100644
> > --- a/lib/test_vmalloc.c
> > +++ b/lib/test_vmalloc.c
> > @@ -53,6 +53,7 @@ __param(int, run_test_mask, INT_MAX,
> >  		"\t\tid: 128,  name: pcpu_alloc_test\n"
> >  		"\t\tid: 256,  name: kvfree_rcu_1_arg_vmalloc_test\n"
> >  		"\t\tid: 512,  name: kvfree_rcu_2_arg_vmalloc_test\n"
> > +		"\t\tid: 1024, name: vm_map_ram_test\n"
> >  		/* Add a new test case description here. */
> >  );
> >
> > @@ -358,6 +359,45 @@ kvfree_rcu_2_arg_vmalloc_test(void)
> >  	return 0;
> >  }
> >
> > +static int
> > +vm_map_ram_test(void)
> > +{
> > +	unsigned int map_nr_pages;
> > +	unsigned char *v_ptr;
> > +	unsigned char *p_ptr;
> > +	struct page **pages;
> > +	struct page *page;
> > +	int i;
> > +
> > +	map_nr_pages = nr_pages > 0 ? nr_pages:1;
> > +	pages = kmalloc(map_nr_pages * sizeof(*page), GFP_KERNEL);
> > +	if (!pages)
> > +		return -1;
> > +
> > +	for (i = 0; i < map_nr_pages; i++) {
> > +		page = alloc_pages(GFP_KERNEL, 1);
> 
> Pedantry, but given I literally patched this pedantically the other day,
> this could be alloc_page(GFP_KERNEL) :)
> 
> > +		if (!page)
> > +			return -1;
> 
> We're leaking memory here right? Should jump to cleanup below.
> 
> > +
> > +		pages[i] = page;
> > +	}
> 
> 
> You should be able to replace this with something like:-
> 
> unsigned long nr_allocated;
> 
> ...
> 
> nr_allocated = alloc_pages_bulk_array(GFP_KERNEL, map_nr_pages, pages);
> if (nr_allocated != map_nr_pages)
> 	goto cleanup;
> 
> > +
> > +	/* Run the test loop. */
> > +	for (i = 0; i < test_loop_count; i++) {
> > +		v_ptr = vm_map_ram(pages, map_nr_pages, -1);
> 
> NIT: The -1 would be clearer as NUMA_NO_NODE
> 
> > +		*v_ptr = 'a';
> > +		vm_unmap_ram(v_ptr, map_nr_pages);
> > +	}
> > +
> 
> Reference to the above you'd add the cleanup label here:-
> 
> cleanup:
> 
> > +	for (i = 0; i < map_nr_pages; i++) {
> > +		p_ptr = page_address(pages[i]);
> > +		free_pages((unsigned long)p_ptr, 1);
> 
> Nit, can be free_page((unsigned long)p_ptr);
> 
Thank you. Will fix all comments, especially switching to the
alloc_page() new API :)

--
Uladzislau Rezki