Allow for the declaration of variables that trigger kvfree() when they
go out of scope.
Cc: Andrew Morton <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Signed-off-by: Dan Williams <[email protected]>
---
include/linux/slab.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 848c7c82ad5a..241025367943 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -746,6 +746,8 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla
extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
__realloc_size(3);
extern void kvfree(const void *addr);
+DEFINE_FREE(kvfree, void *, if (_T) kvfree(_T))
+
extern void kvfree_sensitive(const void *addr, size_t len);
unsigned int kmem_cache_size(struct kmem_cache *s);
On Mon, Aug 14, 2023 at 05:31:27PM +0200, Greg Kroah-Hartman wrote:
> On Mon, Aug 14, 2023 at 12:43:32AM -0700, Dan Williams wrote:
> > Allow for the declaration of variables that trigger kvfree() when they
> > go out of scope.
> >
> > Cc: Andrew Morton <[email protected]>
> > Cc: Peter Zijlstra <[email protected]>
> > Cc: Greg Kroah-Hartman <[email protected]>
> > Signed-off-by: Dan Williams <[email protected]>
> > ---
> > include/linux/slab.h | 2 ++
> > 1 file changed, 2 insertions(+)
> >
> > diff --git a/include/linux/slab.h b/include/linux/slab.h
> > index 848c7c82ad5a..241025367943 100644
> > --- a/include/linux/slab.h
> > +++ b/include/linux/slab.h
> > @@ -746,6 +746,8 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla
> > extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
> > __realloc_size(3);
> > extern void kvfree(const void *addr);
> > +DEFINE_FREE(kvfree, void *, if (_T) kvfree(_T))
>
> No need to check _T before calling this, right (as was also pointed out
> earlier).
Well, that does mean you get an unconditional call to kvfree() in the
success case. Linus argued against this.
This way the compiler sees:
buf = NULL;
if (buf)
kvfree(buf);
and goes: 'let me clean that up for you'. And all is well.
On Mon, Aug 14, 2023 at 12:43:32AM -0700, Dan Williams wrote:
> Allow for the declaration of variables that trigger kvfree() when they
> go out of scope.
>
> Cc: Andrew Morton <[email protected]>
> Cc: Peter Zijlstra <[email protected]>
> Cc: Greg Kroah-Hartman <[email protected]>
> Signed-off-by: Dan Williams <[email protected]>
> ---
> include/linux/slab.h | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/include/linux/slab.h b/include/linux/slab.h
> index 848c7c82ad5a..241025367943 100644
> --- a/include/linux/slab.h
> +++ b/include/linux/slab.h
> @@ -746,6 +746,8 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla
> extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
> __realloc_size(3);
> extern void kvfree(const void *addr);
> +DEFINE_FREE(kvfree, void *, if (_T) kvfree(_T))
No need to check _T before calling this, right (as was also pointed out
earlier).
thanks,
greg k-h
On Mon, Aug 14, 2023 at 06:17:31PM +0200, Peter Zijlstra wrote:
> On Mon, Aug 14, 2023 at 05:31:27PM +0200, Greg Kroah-Hartman wrote:
> > On Mon, Aug 14, 2023 at 12:43:32AM -0700, Dan Williams wrote:
> > > Allow for the declaration of variables that trigger kvfree() when they
> > > go out of scope.
> > >
> > > Cc: Andrew Morton <[email protected]>
> > > Cc: Peter Zijlstra <[email protected]>
> > > Cc: Greg Kroah-Hartman <[email protected]>
> > > Signed-off-by: Dan Williams <[email protected]>
> > > ---
> > > include/linux/slab.h | 2 ++
> > > 1 file changed, 2 insertions(+)
> > >
> > > diff --git a/include/linux/slab.h b/include/linux/slab.h
> > > index 848c7c82ad5a..241025367943 100644
> > > --- a/include/linux/slab.h
> > > +++ b/include/linux/slab.h
> > > @@ -746,6 +746,8 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla
> > > extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
> > > __realloc_size(3);
> > > extern void kvfree(const void *addr);
> > > +DEFINE_FREE(kvfree, void *, if (_T) kvfree(_T))
> >
> > No need to check _T before calling this, right (as was also pointed out
> > earlier).
>
> Well, that does mean you get an unconditional call to kvfree() in the
> success case. Linus argued against this.
>
> This way the compiler sees:
>
> buf = NULL;
> if (buf)
> kvfree(buf);
>
> and goes: 'let me clean that up for you'. And all is well.
Have you actually verified that assumption in the generated Assembler code?
The kernel is compiled with -fno-delete-null-pointer-checks since commit
a3ca86aea507 ("Add '-fno-delete-null-pointer-checks' to gcc CFLAGS").
So NULL pointer checks are *not* optimized away even if the compiler
knows that a pointer is NULL.
Background story:
https://lwn.net/Articles/342330/
Thanks,
Lukas
Lukas Wunner wrote:
> On Mon, Aug 14, 2023 at 06:17:31PM +0200, Peter Zijlstra wrote:
> > On Mon, Aug 14, 2023 at 05:31:27PM +0200, Greg Kroah-Hartman wrote:
> > > On Mon, Aug 14, 2023 at 12:43:32AM -0700, Dan Williams wrote:
> > > > Allow for the declaration of variables that trigger kvfree() when they
> > > > go out of scope.
> > > >
> > > > Cc: Andrew Morton <[email protected]>
> > > > Cc: Peter Zijlstra <[email protected]>
> > > > Cc: Greg Kroah-Hartman <[email protected]>
> > > > Signed-off-by: Dan Williams <[email protected]>
> > > > ---
> > > > include/linux/slab.h | 2 ++
> > > > 1 file changed, 2 insertions(+)
> > > >
> > > > diff --git a/include/linux/slab.h b/include/linux/slab.h
> > > > index 848c7c82ad5a..241025367943 100644
> > > > --- a/include/linux/slab.h
> > > > +++ b/include/linux/slab.h
> > > > @@ -746,6 +746,8 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla
> > > > extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
> > > > __realloc_size(3);
> > > > extern void kvfree(const void *addr);
> > > > +DEFINE_FREE(kvfree, void *, if (_T) kvfree(_T))
> > >
> > > No need to check _T before calling this, right (as was also pointed out
> > > earlier).
> >
> > Well, that does mean you get an unconditional call to kvfree() in the
> > success case. Linus argued against this.
> >
> > This way the compiler sees:
> >
> > buf = NULL;
> > if (buf)
> > kvfree(buf);
> >
> > and goes: 'let me clean that up for you'. And all is well.
>
> Have you actually verified that assumption in the generated Assembler code?
>
> The kernel is compiled with -fno-delete-null-pointer-checks since commit
> a3ca86aea507 ("Add '-fno-delete-null-pointer-checks' to gcc CFLAGS").
>
> So NULL pointer checks are *not* optimized away even if the compiler
> knows that a pointer is NULL.
Interesting, I am not sure how -fno-delete-null-pointer-checks plays
into this, but I can confirm that Peter's expectations are being met in
a routine with:
DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T))
...without that conditional the assembly is:
0xffffffff819ad129 <+41>: call 0xffffffff81800840 <pci_get_domain_bus_and_slot>
0xffffffff819ad12e <+46>: mov %rax,%r12
0xffffffff819ad131 <+49>: test %rax,%rax
0xffffffff819ad134 <+52>: je 0xffffffff819ad154 <cxl_cper_event_call+84>
0xffffffff819ad136 <+54>: mov %rax,%rdi
0xffffffff819ad139 <+57>: call 0xffffffff817f5f10 <pci_dev_lock>
0xffffffff819ad13e <+62>: cmpq $0xffffffff82c681c0,0x80(%r12)
0xffffffff819ad14a <+74>: je 0xffffffff819ad160 <cxl_cper_event_call+96>
0xffffffff819ad14c <+76>: mov %r12,%rdi
0xffffffff819ad14f <+79>: call 0xffffffff817f5fa0 <pci_dev_unlock>
0xffffffff819ad154 <+84>: pop %rbx
0xffffffff819ad155 <+85>: mov %r12,%rdi
0xffffffff819ad158 <+88>: pop %rbp
0xffffffff819ad159 <+89>: pop %r12
0xffffffff819ad15b <+91>: jmp 0xffffffff817fe1e0 <pci_dev_put>
...i.e. the check for NULL at 0xffffffff819ad134 jumps to do an
unnecessary pci_dev_put(). With the conditional in the macro the
sequence is:
0xffffffff819ad129 <+41>: call 0xffffffff81800840 <pci_get_domain_bus_and_slot>
0xffffffff819ad12e <+46>: test %rax,%rax
0xffffffff819ad131 <+49>: je 0xffffffff819ad18c <cxl_cper_event_call+140>
0xffffffff819ad133 <+51>: mov %rax,%r12
0xffffffff819ad136 <+54>: mov %rax,%rdi
0xffffffff819ad139 <+57>: call 0xffffffff817f5f10 <pci_dev_lock>
0xffffffff819ad13e <+62>: cmpq $0xffffffff82c681c0,0x80(%r12)
0xffffffff819ad14a <+74>: je 0xffffffff819ad160 <cxl_cper_event_call+96>
0xffffffff819ad14c <+76>: mov %r12,%rdi
0xffffffff819ad14f <+79>: call 0xffffffff817f5fa0 <pci_dev_unlock>
...
0xffffffff819ad18c <+140>: pop %rbx
0xffffffff819ad18d <+141>: pop %rbp
0xffffffff819ad18e <+142>: pop %r12
0xffffffff819ad190 <+144>: jmp 0xffffffff81efc6a0 <__x86_return_thunk>
...i.e. optimize away the pci_dev_put() and return directly when @pdev
is already known to be NULL. So empirically
-fno-delete-null-pointer-checks still allows for redundant NULL checks
to be optimized.