Re: [PATCH 3/3] powerpc/pseries/cpuhp: delete add/remove_by_count code
Hi Nathan,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on powerpc/next]
[also build test ERROR on linus/master v5.15-rc2 next-20210920]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url:
https://github.com/0day-ci/linux/commits/Nathan-Lynch/CPU-DLPAR-hotplug-for-v5-16/20210920-215907
base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-allmodconfig (attached as .config)
compiler: powerpc64-linux-gcc (GCC) 11.2.0
reproduce (this is a W=1 build):
wget
https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O
~/bin/make.cross
chmod +x ~/bin/make.cross
#
https://github.com/0day-ci/linux/commit/72ea4c8a5398a4a72da34051a66f260ab0154f57
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review
Nathan-Lynch/CPU-DLPAR-hotplug-for-v5-16/20210920-215907
git checkout 72ea4c8a5398a4a72da34051a66f260ab0154f57
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-11.2.0 make.cross
ARCH=powerpc
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot
All errors (new ones prefixed by >>):
arch/powerpc/platforms/pseries/hotplug-cpu.c: In function 'dlpar_cpu':
>> arch/powerpc/platforms/pseries/hotplug-cpu.c:746:13: error: variable 'count'
>> set but not used [-Werror=unused-but-set-variable]
746 | u32 count, drc_index;
| ^
cc1: all warnings being treated as errors
vim +/count +746 arch/powerpc/platforms/pseries/hotplug-cpu.c
ac71380071d19d Nathan Fontenot 2015-12-16 743
ac71380071d19d Nathan Fontenot 2015-12-16 744 int dlpar_cpu(struct
pseries_hp_errorlog *hp_elog)
ac71380071d19d Nathan Fontenot 2015-12-16 745 {
ac71380071d19d Nathan Fontenot 2015-12-16 @746 u32 count,
drc_index;
ac71380071d19d Nathan Fontenot 2015-12-16 747 int rc;
ac71380071d19d Nathan Fontenot 2015-12-16 748
ac71380071d19d Nathan Fontenot 2015-12-16 749 count =
hp_elog->_drc_u.drc_count;
ac71380071d19d Nathan Fontenot 2015-12-16 750 drc_index =
hp_elog->_drc_u.drc_index;
ac71380071d19d Nathan Fontenot 2015-12-16 751
ac71380071d19d Nathan Fontenot 2015-12-16 752
lock_device_hotplug();
ac71380071d19d Nathan Fontenot 2015-12-16 753
ac71380071d19d Nathan Fontenot 2015-12-16 754 switch
(hp_elog->action) {
ac71380071d19d Nathan Fontenot 2015-12-16 755 case
PSERIES_HP_ELOG_ACTION_REMOVE:
72ea4c8a5398a4 Nathan Lynch2021-09-20 756 if
(hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) {
ac71380071d19d Nathan Fontenot 2015-12-16 757
rc = dlpar_cpu_remove_by_index(drc_index);
29c9a2699e71a7 Daniel Henrique Barboza 2021-04-16 758
/*
29c9a2699e71a7 Daniel Henrique Barboza 2021-04-16 759
* Setting the isolation state of an UNISOLATED/CONFIGURED
29c9a2699e71a7 Daniel Henrique Barboza 2021-04-16 760
* device to UNISOLATE is a no-op, but the hypervisor can
29c9a2699e71a7 Daniel Henrique Barboza 2021-04-16 761
* use it as a hint that the CPU removal failed.
29c9a2699e71a7 Daniel Henrique Barboza 2021-04-16 762
*/
29c9a2699e71a7 Daniel Henrique Barboza 2021-04-16 763
if (rc)
29c9a2699e71a7 Daniel Henrique Barboza 2021-04-16 764
dlpar_unisolate_drc(drc_index);
29c9a2699e71a7 Daniel Henrique Barboza 2021-04-16 765 }
ac71380071d19d Nathan Fontenot 2015-12-16 766 else
ac71380071d19d Nathan Fontenot 2015-12-16 767
rc = -EINVAL;
ac71380071d19d Nathan Fontenot 2015-12-16 768 break;
90edf184b9b727 Nathan Fontenot 2015-12-16 769 case
PSERIES_HP_ELOG_ACTION_ADD:
72ea4c8a5398a4 Nathan Lynch2021-09-20 770 if
(hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX)
90edf184b9b727 Nathan Fontenot 2015-12-16 771
rc = dlpar_cpu_add(drc_index);
90edf184b9b727 Nathan Fontenot 2015-12-16 772 else
90edf184b9b727 Nathan Fontenot 2015-12-16 773
rc = -EINVAL;
90edf184b9b727 Nathan Fontenot 2015-12-16 774 break;
ac71380071d19d Nathan Fontenot 2015-12-16 775 default:
ac71380071d19d Nathan Fontenot 2015-12-16 776
pr_err("Invalid action (%d) specified\n", hp_elog->action);
[PATCH v1] powerpc/64s: Fix unrecoverable MCE crash
The machine check handler is not considered NMI on 64s. The early
handler is the true NMI handler, and then it schedules the
machine_check_exception handler to run when interrupts are enabled.
This works fine except the case of an unrecoverable MCE, where the true
NMI is taken when MSR[RI] is clear, it can not recover to schedule the
next handler, so it calls machine_check_exception directly so something
might be done about it.
Calling an async handler from NMI context can result in irq state and
other things getting corrupted. This can also trigger the BUG at
arch/powerpc/include/asm/interrupt.h:168.
Fix this by just making the 64s machine_check_exception handler an NMI
like it is on other subarchs.
Signed-off-by: Nicholas Piggin
---
arch/powerpc/include/asm/interrupt.h | 4
arch/powerpc/kernel/traps.c | 23 +++
2 files changed, 7 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/include/asm/interrupt.h
b/arch/powerpc/include/asm/interrupt.h
index 6b800d3e2681..b32ed910a8cf 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -524,11 +524,7 @@ static __always_inline long ##func(struct pt_regs
*regs)
/* Interrupt handlers */
/* kernel/traps.c */
DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception);
-#ifdef CONFIG_PPC_BOOK3S_64
-DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception);
-#else
DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception);
-#endif
DECLARE_INTERRUPT_HANDLER(SMIException);
DECLARE_INTERRUPT_HANDLER(handle_hmi_exception);
DECLARE_INTERRUPT_HANDLER(unknown_exception);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index aac8c0412ff9..b21450c655d2 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -790,24 +790,19 @@ void die_mce(const char *str, struct pt_regs *regs, long
err)
* do_exit() checks for in_interrupt() and panics in that case, so
* exit the irq/nmi before calling die.
*/
- if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
- irq_exit();
- else
- nmi_exit();
+ nmi_exit();
die(str, regs, err);
}
/*
- * BOOK3S_64 does not call this handler as a non-maskable interrupt
- * (it uses its own early real-mode handler to handle the MCE proper
- * and then raises irq_work to call this handler when interrupts are
- * enabled).
+ * BOOK3S_64 does not call this handler as a non-maskable interrupt (it uses
+ * its own early real-mode handler to handle the MCE proper and then raises
+ * irq_work to call this handler when interrupts are enabled), except in the
+ * case of unrecoverable_mce. If unrecoverable_mce was a separate NMI handler,
+ * then this could be ASYNC on 64s. However it should all work okay as an NMI
+ * handler (and it is NMI on other platforms) so just make it an NMI.
*/
-#ifdef CONFIG_PPC_BOOK3S_64
-DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception)
-#else
DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
-#endif
{
int recover = 0;
@@ -842,11 +837,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
if (regs_is_unrecoverable(regs))
die_mce("Unrecoverable Machine check", regs, SIGBUS);
-#ifdef CONFIG_PPC_BOOK3S_64
- return;
-#else
return 0;
-#endif
}
DEFINE_INTERRUPT_HANDLER(SMIException) /* async? */
--
2.23.0
Re: [PATCH 1/4] crypto: nintendo-aes - add a new AES driver
On Tue, 21 Sept 2021 at 21:47, Emmanuel Gil Peyrot
wrote:
>
> This engine implements AES in CBC mode, using 128-bit keys only. It is
> present on both the Wii and the Wii U, and is apparently identical in
> both consoles.
>
> The hardware is capable of firing an interrupt when the operation is
> done, but this driver currently uses a busy loop, I’m not too sure
> whether it would be preferable to switch, nor how to achieve that.
>
> It also supports a mode where no operation is done, and thus could be
> used as a DMA copy engine, but I don’t know how to expose that to the
> kernel or whether it would even be useful.
>
> In my testing, on a Wii U, this driver reaches 80.7 MiB/s, while the
> aes-generic driver only reaches 30.9 MiB/s, so it is a quite welcome
> speedup.
>
> This driver was written based on reversed documentation, see:
> https://wiibrew.org/wiki/Hardware/AES
>
> Signed-off-by: Emmanuel Gil Peyrot
> Tested-by: Emmanuel Gil Peyrot # on Wii U
> ---
> drivers/crypto/Kconfig| 11 ++
> drivers/crypto/Makefile | 1 +
> drivers/crypto/nintendo-aes.c | 273 ++
> 3 files changed, 285 insertions(+)
> create mode 100644 drivers/crypto/nintendo-aes.c
>
> diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
> index 9a4c275a1335..adc94ad7462d 100644
> --- a/drivers/crypto/Kconfig
> +++ b/drivers/crypto/Kconfig
> @@ -871,4 +871,15 @@ config CRYPTO_DEV_SA2UL
>
> source "drivers/crypto/keembay/Kconfig"
>
> +config CRYPTO_DEV_NINTENDO
> + tristate "Support for the Nintendo Wii U AES engine"
> + depends on WII || WIIU || COMPILE_TEST
This current seteup will allow the driver to be compile tested for
non-powerpc, which will fail on the dcbf instructions.
Perhaps use this instead:
depends on WII || WIIU || (COMPILE_TEST && PPC)
> + select CRYPTO_AES
> + help
> + Say 'Y' here to use the Nintendo Wii or Wii U on-board AES
> + engine for the CryptoAPI AES algorithm.
> +
> + To compile this driver as a module, choose M here: the module
> + will be called nintendo-aes.
> +
> endif # CRYPTO_HW
> diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
> index fa22cb19e242..004dae7bbf39 100644
> --- a/drivers/crypto/Makefile
> +++ b/drivers/crypto/Makefile
> @@ -22,6 +22,7 @@ obj-$(CONFIG_CRYPTO_DEV_MARVELL) += marvell/
> obj-$(CONFIG_CRYPTO_DEV_MXS_DCP) += mxs-dcp.o
> obj-$(CONFIG_CRYPTO_DEV_NIAGARA2) += n2_crypto.o
> n2_crypto-y := n2_core.o n2_asm.o
> +obj-$(CONFIG_CRYPTO_DEV_NINTENDO) += nintendo-aes.o
> obj-$(CONFIG_CRYPTO_DEV_NX) += nx/
> obj-$(CONFIG_CRYPTO_DEV_OMAP) += omap-crypto.o
> obj-$(CONFIG_CRYPTO_DEV_OMAP_AES) += omap-aes-driver.o
> diff --git a/drivers/crypto/nintendo-aes.c b/drivers/crypto/nintendo-aes.c
> new file mode 100644
> index ..79ae77500999
> --- /dev/null
> +++ b/drivers/crypto/nintendo-aes.c
> @@ -0,0 +1,273 @@
> +/*
> + * Copyright (C) 2021 Emmanuel Gil Peyrot
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 and
> + * only version 2 as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
> + * GNU General Public License for more details.
The kernel uses the SDPX header instead of pasting the text.
> +static int
> +do_crypt(const void *src, void *dst, u32 len, u32 flags)
> +{
> + u32 blocks = ((len >> 4) - 1) & AES_CTRL_BLOCK;
> + u32 status;
> + u32 counter = OP_TIMEOUT;
> + u32 i;
> +
> + /* Flush out all of src, we can’t know whether any of it is in cache
> */
> + for (i = 0; i < len; i += 32)
> + __asm__("dcbf 0, %0" : : "r" (src + i));
> + __asm__("sync" : : : "memory");
This could be flush_dcache_range, from asm/cacheflush.h
> +
> + /* Set the addresses for DMA */
> + iowrite32be(virt_to_phys((void *)src), base + AES_SRC);
> + iowrite32be(virt_to_phys(dst), base + AES_DEST);
> +
> + /* Start the operation */
> + iowrite32be(flags | blocks, base + AES_CTRL);
> +
> + /* TODO: figure out how to use interrupts here, this will probably
> +* lower throughput but let the CPU do other things while the AES
> +* engine is doing its work. */
> + do {
> + status = ioread32be(base + AES_CTRL);
> + cpu_relax();
> + } while ((status & AES_CTRL_EXEC) && --counter);
You could add a msleep in here?
Consider using readl_poll_timeout().
Cheers,
Joel
> +
> + /* Do we ever get called with dst ≠ src? If so we have to invalidate
> +* dst in addition to the earlier flush of src. */
> + if (unlikely(dst != src)) {
> + for (i = 0; i < len; i += 32)
> +
Re: [PATCH v2 01/16] ASoC: eureka-tlv320: Update to modern clocking terminology
On Tue, Sep 21, 2021 at 6:36 PM Mark Brown wrote: > > As part of moving to remove the old style defines for the bus clocks update > the eureka-tlv320 driver to use more modern terminology for clocking. > > Signed-off-by: Mark Brown For the whole series: Reviewed-by: Fabio Estevam
Re: [PATCH 7/7] ocxl: Use pci core's DVSEC functionality
On Tue, Sep 21, 2021 at 3:05 PM Ben Widawsky wrote:
>
> Reduce maintenance burden of DVSEC query implementation by using the
> centralized PCI core implementation.
>
> Cc: linuxppc-dev@lists.ozlabs.org
> Cc: Frederic Barrat
> Cc: Andrew Donnellan
> Signed-off-by: Ben Widawsky
> ---
> drivers/misc/ocxl/config.c | 13 +
> 1 file changed, 1 insertion(+), 12 deletions(-)
>
> diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c
> index a68738f38252..e401a51596b9 100644
> --- a/drivers/misc/ocxl/config.c
> +++ b/drivers/misc/ocxl/config.c
> @@ -33,18 +33,7 @@
>
> static int find_dvsec(struct pci_dev *dev, int dvsec_id)
> {
> - int vsec = 0;
> - u16 vendor, id;
> -
> - while ((vsec = pci_find_next_ext_capability(dev, vsec,
> - OCXL_EXT_CAP_ID_DVSEC))) {
> - pci_read_config_word(dev, vsec + OCXL_DVSEC_VENDOR_OFFSET,
> - );
> - pci_read_config_word(dev, vsec + OCXL_DVSEC_ID_OFFSET, );
> - if (vendor == PCI_VENDOR_ID_IBM && id == dvsec_id)
> - return vsec;
> - }
> - return 0;
> + return pci_find_dvsec_capability(dev, PCI_VENDOR_ID_IBM, dvsec_id);
> }
What about:
arch/powerpc/platforms/powernv/ocxl.c::find_dvsec_from_pos()
...? With that converted the redundant definitions below:
OCXL_EXT_CAP_ID_DVSEC
OCXL_DVSEC_VENDOR_OFFSET
OCXL_DVSEC_ID_OFFSET
...can be cleaned up in favor of the core definitions.
Re: [PATCH] mm: Remove HARDENED_USERCOPY_FALLBACK
On Tue, 21 Sept 2021 at 09:50, Stephen Kitt wrote:
>
> This has served its purpose and is no longer used. All usercopy
> violations appear to have been handled by now, any remaining
> instances (or new bugs) will cause copies to be rejected.
>
> This isn't a direct revert of commit 2d891fbc3bb6 ("usercopy: Allow
> strict enforcement of whitelists"); since usercopy_fallback is
> effectively 0, the fallback handling is removed too.
>
> This also removes the usercopy_fallback module parameter on
> slab_common.
>
> Link: https://github.com/KSPP/linux/issues/153
> Signed-off-by: Stephen Kitt
> Suggested-by: Kees Cook
> ---
> arch/powerpc/configs/skiroot_defconfig | 1 -
For the defconfig change:
Reviewed-by: Joel Stanley
Cheers,
Joel
> include/linux/slab.h | 2 --
> mm/slab.c | 13 -
> mm/slab_common.c | 8
> mm/slub.c | 14 --
> security/Kconfig | 14 --
> 6 files changed, 52 deletions(-)
>
> diff --git a/arch/powerpc/configs/skiroot_defconfig
> b/arch/powerpc/configs/skiroot_defconfig
> index b806a5d3a695..c3ba614c973d 100644
> --- a/arch/powerpc/configs/skiroot_defconfig
> +++ b/arch/powerpc/configs/skiroot_defconfig
> @@ -275,7 +275,6 @@ CONFIG_NLS_UTF8=y
> CONFIG_ENCRYPTED_KEYS=y
> CONFIG_SECURITY=y
> CONFIG_HARDENED_USERCOPY=y
> -# CONFIG_HARDENED_USERCOPY_FALLBACK is not set
> CONFIG_HARDENED_USERCOPY_PAGESPAN=y
> CONFIG_FORTIFY_SOURCE=y
> CONFIG_SECURITY_LOCKDOWN_LSM=y
> diff --git a/include/linux/slab.h b/include/linux/slab.h
> index 0c97d788762c..5b21515afae0 100644
> --- a/include/linux/slab.h
> +++ b/include/linux/slab.h
> @@ -142,8 +142,6 @@ struct mem_cgroup;
> void __init kmem_cache_init(void);
> bool slab_is_available(void);
>
> -extern bool usercopy_fallback;
> -
> struct kmem_cache *kmem_cache_create(const char *name, unsigned int size,
> unsigned int align, slab_flags_t flags,
> void (*ctor)(void *));
> diff --git a/mm/slab.c b/mm/slab.c
> index d0f725637663..4d826394ffcb 100644
> --- a/mm/slab.c
> +++ b/mm/slab.c
> @@ -4207,19 +4207,6 @@ void __check_heap_object(const void *ptr, unsigned
> long n, struct page *page,
> n <= cachep->useroffset - offset + cachep->usersize)
> return;
>
> - /*
> -* If the copy is still within the allocated object, produce
> -* a warning instead of rejecting the copy. This is intended
> -* to be a temporary method to find any missing usercopy
> -* whitelists.
> -*/
> - if (usercopy_fallback &&
> - offset <= cachep->object_size &&
> - n <= cachep->object_size - offset) {
> - usercopy_warn("SLAB object", cachep->name, to_user, offset,
> n);
> - return;
> - }
> -
> usercopy_abort("SLAB object", cachep->name, to_user, offset, n);
> }
> #endif /* CONFIG_HARDENED_USERCOPY */
> diff --git a/mm/slab_common.c b/mm/slab_common.c
> index a4a571428c51..925b00c1d4e8 100644
> --- a/mm/slab_common.c
> +++ b/mm/slab_common.c
> @@ -37,14 +37,6 @@ LIST_HEAD(slab_caches);
> DEFINE_MUTEX(slab_mutex);
> struct kmem_cache *kmem_cache;
>
> -#ifdef CONFIG_HARDENED_USERCOPY
> -bool usercopy_fallback __ro_after_init =
> - IS_ENABLED(CONFIG_HARDENED_USERCOPY_FALLBACK);
> -module_param(usercopy_fallback, bool, 0400);
> -MODULE_PARM_DESC(usercopy_fallback,
> - "WARN instead of reject usercopy whitelist violations");
> -#endif
> -
> static LIST_HEAD(slab_caches_to_rcu_destroy);
> static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work);
> static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
> diff --git a/mm/slub.c b/mm/slub.c
> index 3f96e099817a..77f53e76a3c3 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -4125,7 +4125,6 @@ void __check_heap_object(const void *ptr, unsigned long
> n, struct page *page,
> {
> struct kmem_cache *s;
> unsigned int offset;
> - size_t object_size;
> bool is_kfence = is_kfence_address(ptr);
>
> ptr = kasan_reset_tag(ptr);
> @@ -4158,19 +4157,6 @@ void __check_heap_object(const void *ptr, unsigned
> long n, struct page *page,
> n <= s->useroffset - offset + s->usersize)
> return;
>
> - /*
> -* If the copy is still within the allocated object, produce
> -* a warning instead of rejecting the copy. This is intended
> -* to be a temporary method to find any missing usercopy
> -* whitelists.
> -*/
> - object_size = slab_ksize(s);
> - if (usercopy_fallback &&
> - offset <= object_size && n <= object_size - offset) {
> - usercopy_warn("SLUB object", s->name, to_user, offset, n);
> - return;
> - }
> -
> usercopy_abort("SLUB object", s->name, to_user, offset, n);
> }
>
Re: [PATCH 0/4] crypto: nintendo-aes - add a new AES driver
On Tue, Sep 21, 2021 at 02:59:37PM -0700, Eric Biggers wrote: > On Tue, Sep 21, 2021 at 11:39:26PM +0200, Emmanuel Gil Peyrot wrote: > > This engine implements AES in CBC mode, using 128-bit keys only. It is > > present on both the Wii and the Wii U, and is apparently identical in > > both consoles. > > > > The hardware is capable of firing an interrupt when the operation is > > done, but this driver currently uses a busy loop, I’m not too sure > > whether it would be preferable to switch, nor how to achieve that. > > > > It also supports a mode where no operation is done, and thus could be > > used as a DMA copy engine, but I don’t know how to expose that to the > > kernel or whether it would even be useful. > > > > In my testing, on a Wii U, this driver reaches 80.7 MiB/s, while the > > aes-generic driver only reaches 30.9 MiB/s, so it is a quite welcome > > speedup. > > > > This driver was written based on reversed documentation, see: > > https://wiibrew.org/wiki/Hardware/AES > > > > Emmanuel Gil Peyrot (4): > > crypto: nintendo-aes - add a new AES driver > > dt-bindings: nintendo-aes: Document the Wii and Wii U AES support > > powerpc: wii.dts: Expose the AES engine on this platform > > powerpc: wii_defconfig: Enable AES by default > > Does this pass the self-tests, including the fuzz tests which are enabled by > CONFIG_CRYPTO_MANAGER_EXTRA_TESTS=y? I wasn’t aware of those, and indeed it doesn’t pass them yet: [0.680164] alg: skcipher: cbc-aes-nintendo encryption overran dst buffer on test vector 0, cfg="out-of-place" [0.680201] fbcon: Taking over console [0.680219] [ cut here ] [0.680222] alg: self-tests for cbc-aes-nintendo (cbc(aes)) failed (rc=-75) I’ll try to figure out how to debug this and I’ll send a v2, thanks for the hint! > > - Eric -- Emmanuel Gil Peyrot signature.asc Description: PGP signature
[PATCH 7/7] ocxl: Use pci core's DVSEC functionality
Reduce maintenance burden of DVSEC query implementation by using the
centralized PCI core implementation.
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Frederic Barrat
Cc: Andrew Donnellan
Signed-off-by: Ben Widawsky
---
drivers/misc/ocxl/config.c | 13 +
1 file changed, 1 insertion(+), 12 deletions(-)
diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c
index a68738f38252..e401a51596b9 100644
--- a/drivers/misc/ocxl/config.c
+++ b/drivers/misc/ocxl/config.c
@@ -33,18 +33,7 @@
static int find_dvsec(struct pci_dev *dev, int dvsec_id)
{
- int vsec = 0;
- u16 vendor, id;
-
- while ((vsec = pci_find_next_ext_capability(dev, vsec,
- OCXL_EXT_CAP_ID_DVSEC))) {
- pci_read_config_word(dev, vsec + OCXL_DVSEC_VENDOR_OFFSET,
- );
- pci_read_config_word(dev, vsec + OCXL_DVSEC_ID_OFFSET, );
- if (vendor == PCI_VENDOR_ID_IBM && id == dvsec_id)
- return vsec;
- }
- return 0;
+ return pci_find_dvsec_capability(dev, PCI_VENDOR_ID_IBM, dvsec_id);
}
static int find_dvsec_afu_ctrl(struct pci_dev *dev, u8 afu_idx)
--
2.33.0
[PATCH 5/7] PCI: Add pci_find_dvsec_capability to find designated VSEC
Add pci_find_dvsec_capability to locate a Designated Vendor-Specific
Extended Capability with the specified DVSEC ID.
The Designated Vendor-Specific Extended Capability (DVSEC) allows one or
more vendor specific capabilities that aren't tied to the vendor ID of
the PCI component.
DVSEC is critical for both the Compute Express Link (CXL) driver as well
as the driver for OpenCAPI coherent accelerator (OCXL).
Cc: David E. Box
Cc: Jonathan Cameron
Cc: Bjorn Helgaas
Cc: Dan Williams
Cc: linux-...@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Frederic Barrat
Cc: Andrew Donnellan
Signed-off-by: Ben Widawsky
---
drivers/pci/pci.c | 32
include/linux/pci.h | 1 +
2 files changed, 33 insertions(+)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index ce2ab62b64cf..94ac86ff28b0 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -732,6 +732,38 @@ u16 pci_find_vsec_capability(struct pci_dev *dev, u16
vendor, int cap)
}
EXPORT_SYMBOL_GPL(pci_find_vsec_capability);
+/**
+ * pci_find_dvsec_capability - Find DVSEC for vendor
+ * @dev: PCI device to query
+ * @vendor: Vendor ID to match for the DVSEC
+ * @dvsec: Designated Vendor-specific capability ID
+ *
+ * If DVSEC has Vendor ID @vendor and DVSEC ID @dvsec return the capability
+ * offset in config space; otherwise return 0.
+ */
+u16 pci_find_dvsec_capability(struct pci_dev *dev, u16 vendor, u16 dvsec)
+{
+ int pos;
+
+ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_DVSEC);
+ if (!pos)
+ return 0;
+
+ while (pos) {
+ u16 v, id;
+
+ pci_read_config_word(dev, pos + PCI_DVSEC_HEADER1, );
+ pci_read_config_word(dev, pos + PCI_DVSEC_HEADER2, );
+ if (vendor == v && dvsec == id)
+ return pos;
+
+ pos = pci_find_next_ext_capability(dev, pos,
PCI_EXT_CAP_ID_DVSEC);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pci_find_dvsec_capability);
+
/**
* pci_find_parent_resource - return resource region of parent bus of given
* region
diff --git a/include/linux/pci.h b/include/linux/pci.h
index cd8aa6fce204..c93ccfa4571b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1130,6 +1130,7 @@ u16 pci_find_ext_capability(struct pci_dev *dev, int cap);
u16 pci_find_next_ext_capability(struct pci_dev *dev, u16 pos, int cap);
struct pci_bus *pci_find_next_bus(const struct pci_bus *from);
u16 pci_find_vsec_capability(struct pci_dev *dev, u16 vendor, int cap);
+u16 pci_find_dvsec_capability(struct pci_dev *dev, u16 vendor, u16 dvsec);
u64 pci_get_dsn(struct pci_dev *dev);
--
2.33.0
Re: [PATCH 0/4] crypto: nintendo-aes - add a new AES driver
On Tue, Sep 21, 2021 at 11:39:26PM +0200, Emmanuel Gil Peyrot wrote: > This engine implements AES in CBC mode, using 128-bit keys only. It is > present on both the Wii and the Wii U, and is apparently identical in > both consoles. > > The hardware is capable of firing an interrupt when the operation is > done, but this driver currently uses a busy loop, I’m not too sure > whether it would be preferable to switch, nor how to achieve that. > > It also supports a mode where no operation is done, and thus could be > used as a DMA copy engine, but I don’t know how to expose that to the > kernel or whether it would even be useful. > > In my testing, on a Wii U, this driver reaches 80.7 MiB/s, while the > aes-generic driver only reaches 30.9 MiB/s, so it is a quite welcome > speedup. > > This driver was written based on reversed documentation, see: > https://wiibrew.org/wiki/Hardware/AES > > Emmanuel Gil Peyrot (4): > crypto: nintendo-aes - add a new AES driver > dt-bindings: nintendo-aes: Document the Wii and Wii U AES support > powerpc: wii.dts: Expose the AES engine on this platform > powerpc: wii_defconfig: Enable AES by default Does this pass the self-tests, including the fuzz tests which are enabled by CONFIG_CRYPTO_MANAGER_EXTRA_TESTS=y? - Eric
Re: [PATCH v3 5/8] x86/sme: Replace occurrences of sme_active() with cc_platform_has()
On Tue, Sep 21, 2021 at 04:43:59PM -0500, Tom Lendacky wrote: > On 9/21/21 4:34 PM, Kirill A. Shutemov wrote: > > On Tue, Sep 21, 2021 at 11:27:17PM +0200, Borislav Petkov wrote: > > > On Wed, Sep 22, 2021 at 12:20:59AM +0300, Kirill A. Shutemov wrote: > > > > I still believe calling cc_platform_has() from __startup_64() is totally > > > > broken as it lacks proper wrapping while accessing global variables. > > > > > > Well, one of the issues on the AMD side was using boot_cpu_data too > > > early and the Intel side uses it too. Can you replace those checks with > > > is_tdx_guest() or whatever was the helper's name which would check > > > whether the the kernel is running as a TDX guest, and see if that helps? > > > > There's no need in Intel check this early. Only AMD need it. Maybe just > > opencode them? > > Any way you can put a gzipped/bzipped copy of your vmlinux file somewhere I > can grab it from and take a look at it? You can find broken vmlinux and bzImage here: https://drive.google.com/drive/folders/1n74vUQHOGebnF70Im32qLFY8iS3wvjIs?usp=sharing Let me know when I can remove it. -- Kirill A. Shutemov
Re: [PATCH v3 5/8] x86/sme: Replace occurrences of sme_active() with cc_platform_has()
On 9/21/21 4:34 PM, Kirill A. Shutemov wrote: On Tue, Sep 21, 2021 at 11:27:17PM +0200, Borislav Petkov wrote: On Wed, Sep 22, 2021 at 12:20:59AM +0300, Kirill A. Shutemov wrote: I still believe calling cc_platform_has() from __startup_64() is totally broken as it lacks proper wrapping while accessing global variables. Well, one of the issues on the AMD side was using boot_cpu_data too early and the Intel side uses it too. Can you replace those checks with is_tdx_guest() or whatever was the helper's name which would check whether the the kernel is running as a TDX guest, and see if that helps? There's no need in Intel check this early. Only AMD need it. Maybe just opencode them? Any way you can put a gzipped/bzipped copy of your vmlinux file somewhere I can grab it from and take a look at it? Thanks, Tom
[PATCH 4/4] powerpc: wii_defconfig: Enable AES by default
This selects the nintendo-aes module when building for this platform. Signed-off-by: Emmanuel Gil Peyrot --- arch/powerpc/configs/wii_defconfig | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig index 379c171f3ddd..752e081d28d0 100644 --- a/arch/powerpc/configs/wii_defconfig +++ b/arch/powerpc/configs/wii_defconfig @@ -123,4 +123,6 @@ CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_DMA_API_DEBUG=y CONFIG_PPC_EARLY_DEBUG=y -# CONFIG_CRYPTO_HW is not set +CONFIG_CRYPTO_HW=y +CONFIG_CRYPTO_DEV_NINTENDO=y +CONFIG_CRYPTO_USER_API_SKCIPHER=y -- 2.33.0
[PATCH 2/4] dt-bindings: nintendo-aes: Document the Wii and Wii U AES support
Both of these consoles use the exact same AES engine, which only supports CBC mode with 128-bit keys. Signed-off-by: Emmanuel Gil Peyrot --- .../bindings/crypto/nintendo-aes.yaml | 34 +++ 1 file changed, 34 insertions(+) create mode 100644 Documentation/devicetree/bindings/crypto/nintendo-aes.yaml diff --git a/Documentation/devicetree/bindings/crypto/nintendo-aes.yaml b/Documentation/devicetree/bindings/crypto/nintendo-aes.yaml new file mode 100644 index ..e62a2bfc571c --- /dev/null +++ b/Documentation/devicetree/bindings/crypto/nintendo-aes.yaml @@ -0,0 +1,34 @@ +# SPDX-License-Identifier: GPL-2.0 +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/crypto/nintendo-aes.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Nintendo Wii and Wii U AES engine + +maintainers: + - Emmanuel Gil Peyrot + +description: |+ + The AES engine in the Nintendo Wii and Wii U supports the following: + -- Advanced Encryption Standard (AES) in CBC mode, with 128-bit keys + +properties: + compatible: +items: + - const: nintendo,hollywood-aes + - const: nintendo,latte-aes + + reg: +maxItems: 1 + + interrupts: +description: Not supported yet. +maxItems: 1 + +required: + - compatible + - reg + - interrupts + +additionalProperties: false -- 2.33.0
[PATCH 3/4] powerpc: wii.dts: Expose the AES engine on this platform
This can be used by the newly-added nintendo-aes crypto module.
Signed-off-by: Emmanuel Gil Peyrot
---
arch/powerpc/boot/dts/wii.dts | 7 +++
1 file changed, 7 insertions(+)
diff --git a/arch/powerpc/boot/dts/wii.dts b/arch/powerpc/boot/dts/wii.dts
index aaa381da1906..c5720fdd0686 100644
--- a/arch/powerpc/boot/dts/wii.dts
+++ b/arch/powerpc/boot/dts/wii.dts
@@ -113,6 +113,13 @@ exi@d006800 {
interrupts = <4>;
};
+ aes@d02 {
+ compatible = "nintendo,hollywood-aes";
+ reg = <0x0d02 0x14>;
+ interrupts = <2>;
+ interrupt-parent = <>;
+ };
+
usb@d04 {
compatible = "nintendo,hollywood-usb-ehci",
"usb-ehci";
--
2.33.0
[PATCH 1/4] crypto: nintendo-aes - add a new AES driver
This engine implements AES in CBC mode, using 128-bit keys only. It is
present on both the Wii and the Wii U, and is apparently identical in
both consoles.
The hardware is capable of firing an interrupt when the operation is
done, but this driver currently uses a busy loop, I’m not too sure
whether it would be preferable to switch, nor how to achieve that.
It also supports a mode where no operation is done, and thus could be
used as a DMA copy engine, but I don’t know how to expose that to the
kernel or whether it would even be useful.
In my testing, on a Wii U, this driver reaches 80.7 MiB/s, while the
aes-generic driver only reaches 30.9 MiB/s, so it is a quite welcome
speedup.
This driver was written based on reversed documentation, see:
https://wiibrew.org/wiki/Hardware/AES
Signed-off-by: Emmanuel Gil Peyrot
Tested-by: Emmanuel Gil Peyrot # on Wii U
---
drivers/crypto/Kconfig| 11 ++
drivers/crypto/Makefile | 1 +
drivers/crypto/nintendo-aes.c | 273 ++
3 files changed, 285 insertions(+)
create mode 100644 drivers/crypto/nintendo-aes.c
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 9a4c275a1335..adc94ad7462d 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -871,4 +871,15 @@ config CRYPTO_DEV_SA2UL
source "drivers/crypto/keembay/Kconfig"
+config CRYPTO_DEV_NINTENDO
+ tristate "Support for the Nintendo Wii U AES engine"
+ depends on WII || WIIU || COMPILE_TEST
+ select CRYPTO_AES
+ help
+ Say 'Y' here to use the Nintendo Wii or Wii U on-board AES
+ engine for the CryptoAPI AES algorithm.
+
+ To compile this driver as a module, choose M here: the module
+ will be called nintendo-aes.
+
endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index fa22cb19e242..004dae7bbf39 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_CRYPTO_DEV_MARVELL) += marvell/
obj-$(CONFIG_CRYPTO_DEV_MXS_DCP) += mxs-dcp.o
obj-$(CONFIG_CRYPTO_DEV_NIAGARA2) += n2_crypto.o
n2_crypto-y := n2_core.o n2_asm.o
+obj-$(CONFIG_CRYPTO_DEV_NINTENDO) += nintendo-aes.o
obj-$(CONFIG_CRYPTO_DEV_NX) += nx/
obj-$(CONFIG_CRYPTO_DEV_OMAP) += omap-crypto.o
obj-$(CONFIG_CRYPTO_DEV_OMAP_AES) += omap-aes-driver.o
diff --git a/drivers/crypto/nintendo-aes.c b/drivers/crypto/nintendo-aes.c
new file mode 100644
index ..79ae77500999
--- /dev/null
+++ b/drivers/crypto/nintendo-aes.c
@@ -0,0 +1,273 @@
+/*
+ * Copyright (C) 2021 Emmanuel Gil Peyrot
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+#include
+#include
+
+/* Addresses of the registers */
+#define AES_CTRL 0
+#define AES_SRC 4
+#define AES_DEST 8
+#define AES_KEY 12
+#define AES_IV 16
+
+#define AES_CTRL_EXEC 0x8000
+#define AES_CTRL_EXEC_RESET 0x
+#define AES_CTRL_EXEC_INIT 0x8000
+#define AES_CTRL_IRQ0x4000
+#define AES_CTRL_ERR0x2000
+#define AES_CTRL_ENA0x1000
+#define AES_CTRL_DEC0x0800
+#define AES_CTRL_IV 0x1000
+#define AES_CTRL_BLOCK 0x0fff
+
+#define OP_TIMEOUT 0x1000
+
+#define AES_DIR_DECRYPT 0
+#define AES_DIR_ENCRYPT 1
+
+static void __iomem *base;
+static spinlock_t lock;
+
+/* Write a 128 bit field (either a writable key or IV) */
+static inline void
+writefield(u32 reg, const void *_value)
+{
+ const u32 *value = _value;
+ int i;
+
+ for (i = 0; i < 4; i++)
+ iowrite32be(value[i], base + reg);
+}
+
+static int
+do_crypt(const void *src, void *dst, u32 len, u32 flags)
+{
+ u32 blocks = ((len >> 4) - 1) & AES_CTRL_BLOCK;
+ u32 status;
+ u32 counter = OP_TIMEOUT;
+ u32 i;
+
+ /* Flush out all of src, we can’t know whether any of it is in cache */
+ for (i = 0; i < len; i += 32)
+ __asm__("dcbf 0, %0" : : "r" (src + i));
+ __asm__("sync" : : : "memory");
+
+ /* Set the addresses for DMA */
+ iowrite32be(virt_to_phys((void *)src), base + AES_SRC);
+ iowrite32be(virt_to_phys(dst), base + AES_DEST);
+
+ /* Start the operation */
+ iowrite32be(flags | blocks, base + AES_CTRL);
+
+ /* TODO: figure out how to use interrupts here, this will probably
+* lower throughput but let the CPU do other things while the AES
+* engine is doing its work. */
+ do {
+ status = ioread32be(base +
[PATCH 0/4] crypto: nintendo-aes - add a new AES driver
This engine implements AES in CBC mode, using 128-bit keys only. It is present on both the Wii and the Wii U, and is apparently identical in both consoles. The hardware is capable of firing an interrupt when the operation is done, but this driver currently uses a busy loop, I’m not too sure whether it would be preferable to switch, nor how to achieve that. It also supports a mode where no operation is done, and thus could be used as a DMA copy engine, but I don’t know how to expose that to the kernel or whether it would even be useful. In my testing, on a Wii U, this driver reaches 80.7 MiB/s, while the aes-generic driver only reaches 30.9 MiB/s, so it is a quite welcome speedup. This driver was written based on reversed documentation, see: https://wiibrew.org/wiki/Hardware/AES Emmanuel Gil Peyrot (4): crypto: nintendo-aes - add a new AES driver dt-bindings: nintendo-aes: Document the Wii and Wii U AES support powerpc: wii.dts: Expose the AES engine on this platform powerpc: wii_defconfig: Enable AES by default .../bindings/crypto/nintendo-aes.yaml | 34 +++ arch/powerpc/boot/dts/wii.dts | 7 + arch/powerpc/configs/wii_defconfig| 4 +- drivers/crypto/Kconfig| 11 + drivers/crypto/Makefile | 1 + drivers/crypto/nintendo-aes.c | 273 ++ 6 files changed, 329 insertions(+), 1 deletion(-) create mode 100644 Documentation/devicetree/bindings/crypto/nintendo-aes.yaml create mode 100644 drivers/crypto/nintendo-aes.c -- 2.33.0
[PATCH v2 16/16] ASoC: pl1022_rdk: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the pl1022_rdk driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/p1022_rdk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/p1022_rdk.c b/sound/soc/fsl/p1022_rdk.c index 714515b8081f..b395adabe823 100644 --- a/sound/soc/fsl/p1022_rdk.c +++ b/sound/soc/fsl/p1022_rdk.c @@ -265,7 +265,7 @@ static int p1022_rdk_probe(struct platform_device *pdev) * only one way to configure the SSI. */ mdata->dai_format = SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBM_CFM; + SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBP_CFP; mdata->codec_clk_direction = SND_SOC_CLOCK_OUT; mdata->cpu_clk_direction = SND_SOC_CLOCK_IN; -- 2.20.1
[PATCH v2 15/16] ASoC: pl1022_ds: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the pl1022_ds driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/p1022_ds.c | 16
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/sound/soc/fsl/p1022_ds.c b/sound/soc/fsl/p1022_ds.c
index 317c767b0099..b45742931b0d 100644
--- a/sound/soc/fsl/p1022_ds.c
+++ b/sound/soc/fsl/p1022_ds.c
@@ -275,7 +275,7 @@ static int p1022_ds_probe(struct platform_device *pdev)
if (strcasecmp(sprop, "i2s-slave") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBP_CFP;
mdata->codec_clk_direction = SND_SOC_CLOCK_OUT;
mdata->cpu_clk_direction = SND_SOC_CLOCK_IN;
@@ -293,37 +293,37 @@ static int p1022_ds_probe(struct platform_device *pdev)
mdata->clk_frequency = be32_to_cpup(iprop);
} else if (strcasecmp(sprop, "i2s-master") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBC_CFC;
mdata->codec_clk_direction = SND_SOC_CLOCK_IN;
mdata->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "lj-slave") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBP_CFP;
mdata->codec_clk_direction = SND_SOC_CLOCK_OUT;
mdata->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "lj-master") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBC_CFC;
mdata->codec_clk_direction = SND_SOC_CLOCK_IN;
mdata->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "rj-slave") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBP_CFP;
mdata->codec_clk_direction = SND_SOC_CLOCK_OUT;
mdata->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "rj-master") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBC_CFC;
mdata->codec_clk_direction = SND_SOC_CLOCK_IN;
mdata->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "ac97-slave") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBP_CFP;
mdata->codec_clk_direction = SND_SOC_CLOCK_OUT;
mdata->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "ac97-master") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBC_CFC;
mdata->codec_clk_direction = SND_SOC_CLOCK_IN;
mdata->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else {
--
2.20.1
[PATCH v2 14/16] ASoC: mpc8610_hpcd: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the mpc8610_hpcd driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/mpc8610_hpcd.c | 16
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/sound/soc/fsl/mpc8610_hpcd.c b/sound/soc/fsl/mpc8610_hpcd.c
index 58b9ca3c4da0..e71a992fbf93 100644
--- a/sound/soc/fsl/mpc8610_hpcd.c
+++ b/sound/soc/fsl/mpc8610_hpcd.c
@@ -264,7 +264,7 @@ static int mpc8610_hpcd_probe(struct platform_device *pdev)
if (strcasecmp(sprop, "i2s-slave") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBP_CFP;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
@@ -282,37 +282,37 @@ static int mpc8610_hpcd_probe(struct platform_device
*pdev)
machine_data->clk_frequency = be32_to_cpup(iprop);
} else if (strcasecmp(sprop, "i2s-master") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBC_CFC;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "lj-slave") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBP_CFP;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "lj-master") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBC_CFC;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "rj-slave") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBP_CFP;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "rj-master") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBC_CFC;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "ac97-slave") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBP_CFP;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "ac97-master") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBC_CFC;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else {
--
2.20.1
[PATCH v2 13/16] ASoC: imx-sgtl5000: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the imx-sgtl5000 driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/imx-sgtl5000.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/imx-sgtl5000.c b/sound/soc/fsl/imx-sgtl5000.c index f45cb4bbb6c4..2f1acd011042 100644 --- a/sound/soc/fsl/imx-sgtl5000.c +++ b/sound/soc/fsl/imx-sgtl5000.c @@ -153,7 +153,7 @@ static int imx_sgtl5000_probe(struct platform_device *pdev) data->dai.platforms->of_node = ssi_np; data->dai.init = _sgtl5000_dai_init; data->dai.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_CBM_CFM; + SND_SOC_DAIFMT_CBP_CFP; data->card.dev = >dev; ret = snd_soc_of_parse_card_name(>card, "model"); -- 2.20.1
[PATCH v2 12/16] ASoC: imx-rpmsg: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the imx-rpmsg driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/imx-rpmsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/imx-rpmsg.c b/sound/soc/fsl/imx-rpmsg.c index f96fe4ff8425..2e117311e582 100644 --- a/sound/soc/fsl/imx-rpmsg.c +++ b/sound/soc/fsl/imx-rpmsg.c @@ -64,7 +64,7 @@ static int imx_rpmsg_probe(struct platform_device *pdev) data->dai.stream_name = "rpmsg hifi"; data->dai.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_CBS_CFS; + SND_SOC_DAIFMT_CBC_CFC; /* Optional codec node */ ret = of_parse_phandle_with_fixed_args(np, "audio-codec", 0, 0, ); -- 2.20.1
[PATCH v2 11/16] ASoC: imx-hdmi: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the imx-hdmi driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/imx-hdmi.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sound/soc/fsl/imx-hdmi.c b/sound/soc/fsl/imx-hdmi.c
index 34a0dceae621..c15e930fa2a6 100644
--- a/sound/soc/fsl/imx-hdmi.c
+++ b/sound/soc/fsl/imx-hdmi.c
@@ -171,7 +171,7 @@ static int imx_hdmi_probe(struct platform_device *pdev)
data->dai.codecs->name = "hdmi-audio-codec.1";
data->dai.dai_fmt = data->dai_fmt |
SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_CBC_CFC;
}
if (hdmi_in) {
@@ -181,7 +181,7 @@ static int imx_hdmi_probe(struct platform_device *pdev)
data->dai.codecs->name = "hdmi-audio-codec.2";
data->dai.dai_fmt = data->dai_fmt |
SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_CBP_CFP;
}
data->card.dapm_widgets = imx_hdmi_widgets;
--
2.20.1
[PATCH v2 10/16] ASoC: imx-es8328: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the imx-es8328 driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/imx-es8328.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/imx-es8328.c b/sound/soc/fsl/imx-es8328.c index 1981dcd7e930..09c674ee79f1 100644 --- a/sound/soc/fsl/imx-es8328.c +++ b/sound/soc/fsl/imx-es8328.c @@ -174,7 +174,7 @@ static int imx_es8328_probe(struct platform_device *pdev) data->dai.platforms->of_node = ssi_np; data->dai.init = _es8328_dai_init; data->dai.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_CBM_CFM; + SND_SOC_DAIFMT_CBP_CFP; data->card.dev = dev; data->card.dapm_widgets = imx_es8328_dapm_widgets; -- 2.20.1
[PATCH v2 09/16] ASoC: imx-card: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the imx-card driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/imx-card.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c index 58fd0639a069..e9fe3fc2f261 100644 --- a/sound/soc/fsl/imx-card.c +++ b/sound/soc/fsl/imx-card.c @@ -652,7 +652,7 @@ static int imx_card_parse_of(struct imx_card_data *data) NULL, >dai_fmt); if (ret) link->dai_fmt = SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_CBS_CFS | + SND_SOC_DAIFMT_CBC_CFC | SND_SOC_DAIFMT_I2S; /* Get tdm slot */ -- 2.20.1
[PATCH v2 08/16] ASoC: imx-audmix: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the imx-audmix driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/imx-audmix.c | 8 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c index a364e2415de0..e8b438a0329e 100644 --- a/sound/soc/fsl/imx-audmix.c +++ b/sound/soc/fsl/imx-audmix.c @@ -80,8 +80,8 @@ static int imx_audmix_fe_hw_params(struct snd_pcm_substream *substream, u32 channels = params_channels(params); int ret, dir; - /* For playback the AUDMIX is slave, and for record is master */ - fmt |= tx ? SND_SOC_DAIFMT_CBS_CFS : SND_SOC_DAIFMT_CBM_CFM; + /* For playback the AUDMIX is consumer, and for record is provider */ + fmt |= tx ? SND_SOC_DAIFMT_CBC_CFC : SND_SOC_DAIFMT_CBP_CFP; dir = tx ? SND_SOC_CLOCK_OUT : SND_SOC_CLOCK_IN; /* set DAI configuration */ @@ -121,8 +121,8 @@ static int imx_audmix_be_hw_params(struct snd_pcm_substream *substream, if (!tx) return 0; - /* For playback the AUDMIX is slave */ - fmt |= SND_SOC_DAIFMT_CBM_CFM; + /* For playback the AUDMIX is consumer */ + fmt |= SND_SOC_DAIFMT_CBP_CFP; /* set AUDMIX DAI configuration */ ret = snd_soc_dai_set_fmt(asoc_rtd_to_cpu(rtd, 0), fmt); -- 2.20.1
[PATCH v2 07/16] ASoC: fsl_ssi: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl_ssi driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl_ssi.c | 38 +++---
1 file changed, 19 insertions(+), 19 deletions(-)
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index ecbc1c365d5b..1169d1104b9e 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -350,16 +350,16 @@ static bool fsl_ssi_is_ac97(struct fsl_ssi *ssi)
SND_SOC_DAIFMT_AC97;
}
-static bool fsl_ssi_is_i2s_master(struct fsl_ssi *ssi)
+static bool fsl_ssi_is_i2s_clock_provider(struct fsl_ssi *ssi)
{
- return (ssi->dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) ==
- SND_SOC_DAIFMT_CBS_CFS;
+ return (ssi->dai_fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) ==
+ SND_SOC_DAIFMT_CBC_CFC;
}
-static bool fsl_ssi_is_i2s_cbm_cfs(struct fsl_ssi *ssi)
+static bool fsl_ssi_is_i2s_cbp_cfc(struct fsl_ssi *ssi)
{
- return (ssi->dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) ==
- SND_SOC_DAIFMT_CBM_CFS;
+ return (ssi->dai_fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) ==
+ SND_SOC_DAIFMT_CBP_CFC;
}
/**
@@ -808,7 +808,7 @@ static int fsl_ssi_hw_params(struct snd_pcm_substream
*substream,
u32 wl = SSI_SxCCR_WL(sample_size);
int ret;
- if (fsl_ssi_is_i2s_master(ssi)) {
+ if (fsl_ssi_is_i2s_clock_provider(ssi)) {
ret = fsl_ssi_set_bclk(substream, dai, hw_params);
if (ret)
return ret;
@@ -841,7 +841,7 @@ static int fsl_ssi_hw_params(struct snd_pcm_substream
*substream,
u8 i2s_net = ssi->i2s_net;
/* Normal + Network mode to send 16-bit data in 32-bit frames */
- if (fsl_ssi_is_i2s_cbm_cfs(ssi) && sample_size == 16)
+ if (fsl_ssi_is_i2s_cbp_cfc(ssi) && sample_size == 16)
i2s_net = SSI_SCR_I2S_MODE_NORMAL | SSI_SCR_NET;
/* Use Normal mode to send mono data at 1st slot of 2 slots */
@@ -865,7 +865,7 @@ static int fsl_ssi_hw_free(struct snd_pcm_substream
*substream,
struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
struct fsl_ssi *ssi = snd_soc_dai_get_drvdata(asoc_rtd_to_cpu(rtd, 0));
- if (fsl_ssi_is_i2s_master(ssi) &&
+ if (fsl_ssi_is_i2s_clock_provider(ssi) &&
ssi->baudclk_streams & BIT(substream->stream)) {
clk_disable_unprepare(ssi->baudclk);
ssi->baudclk_streams &= ~BIT(substream->stream);
@@ -891,18 +891,18 @@ static int _fsl_ssi_set_dai_fmt(struct fsl_ssi *ssi,
unsigned int fmt)
ssi->i2s_net = SSI_SCR_NET;
switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
case SND_SOC_DAIFMT_I2S:
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBS_CFS:
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBC_CFC:
if (IS_ERR(ssi->baudclk)) {
dev_err(ssi->dev,
"missing baudclk for master mode\n");
return -EINVAL;
}
fallthrough;
- case SND_SOC_DAIFMT_CBM_CFS:
+ case SND_SOC_DAIFMT_CBP_CFC:
ssi->i2s_net |= SSI_SCR_I2S_MODE_MASTER;
break;
- case SND_SOC_DAIFMT_CBM_CFM:
+ case SND_SOC_DAIFMT_CBP_CFP:
ssi->i2s_net |= SSI_SCR_I2S_MODE_SLAVE;
break;
default:
@@ -962,17 +962,17 @@ static int _fsl_ssi_set_dai_fmt(struct fsl_ssi *ssi,
unsigned int fmt)
return -EINVAL;
}
- /* DAI clock master masks */
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBS_CFS:
+ /* DAI clock provider masks */
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBC_CFC:
/* Output bit and frame sync clocks */
strcr |= SSI_STCR_TFDIR | SSI_STCR_TXDIR;
scr |= SSI_SCR_SYS_CLK_EN;
break;
- case SND_SOC_DAIFMT_CBM_CFM:
+ case SND_SOC_DAIFMT_CBP_CFP:
/* Input bit or frame sync clocks */
break;
- case SND_SOC_DAIFMT_CBM_CFS:
+ case SND_SOC_DAIFMT_CBP_CFC:
/* Input bit clock but output frame sync clock */
strcr |= SSI_STCR_TFDIR;
break;
@@ -1341,7 +1341,7 @@ static int fsl_ssi_imx_probe(struct platform_device *pdev,
}
}
- /* Do not error out for slave cases that live without a baud clock */
+ /* Do not error out for consumer cases that live without a baud clock */
ssi->baudclk =
[PATCH v2 06/16] ASoC: fsl_sai: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl_sai driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl_sai.c | 34 +-
sound/soc/fsl/fsl_sai.h | 2 +-
2 files changed, 18 insertions(+), 18 deletions(-)
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index 38f6362099d5..10544fa27dc0 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -297,23 +297,23 @@ static int fsl_sai_set_dai_fmt_tr(struct snd_soc_dai
*cpu_dai,
return -EINVAL;
}
- /* DAI clock master masks */
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBS_CFS:
+ /* DAI clock provider masks */
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBC_CFC:
val_cr2 |= FSL_SAI_CR2_BCD_MSTR;
val_cr4 |= FSL_SAI_CR4_FSD_MSTR;
- sai->is_slave_mode = false;
+ sai->is_consumer_mode = false;
break;
- case SND_SOC_DAIFMT_CBM_CFM:
- sai->is_slave_mode = true;
+ case SND_SOC_DAIFMT_CBP_CFP:
+ sai->is_consumer_mode = true;
break;
- case SND_SOC_DAIFMT_CBS_CFM:
+ case SND_SOC_DAIFMT_CBC_CFP:
val_cr2 |= FSL_SAI_CR2_BCD_MSTR;
- sai->is_slave_mode = false;
+ sai->is_consumer_mode = false;
break;
- case SND_SOC_DAIFMT_CBM_CFS:
+ case SND_SOC_DAIFMT_CBP_CFC:
val_cr4 |= FSL_SAI_CR4_FSD_MSTR;
- sai->is_slave_mode = true;
+ sai->is_consumer_mode = true;
break;
default:
return -EINVAL;
@@ -356,8 +356,8 @@ static int fsl_sai_set_bclk(struct snd_soc_dai *dai, bool
tx, u32 freq)
u32 id;
int ret = 0;
- /* Don't apply to slave mode */
- if (sai->is_slave_mode)
+ /* Don't apply to consumer mode */
+ if (sai->is_consumer_mode)
return 0;
/*
@@ -462,7 +462,7 @@ static int fsl_sai_hw_params(struct snd_pcm_substream
*substream,
pins = DIV_ROUND_UP(channels, slots);
- if (!sai->is_slave_mode) {
+ if (!sai->is_consumer_mode) {
if (sai->bclk_ratio)
ret = fsl_sai_set_bclk(cpu_dai, tx,
sai->bclk_ratio *
@@ -502,12 +502,12 @@ static int fsl_sai_hw_params(struct snd_pcm_substream
*substream,
val_cr4 |= FSL_SAI_CR4_CHMOD;
/*
-* For SAI master mode, when Tx(Rx) sync with Rx(Tx) clock, Rx(Tx) will
+* For SAI provider mode, when Tx(Rx) sync with Rx(Tx) clock, Rx(Tx)
will
* generate bclk and frame clock for Tx(Rx), we should set RCR4(TCR4),
* RCR5(TCR5) for playback(capture), or there will be sync error.
*/
- if (!sai->is_slave_mode && fsl_sai_dir_is_synced(sai, adir)) {
+ if (!sai->is_consumer_mode && fsl_sai_dir_is_synced(sai, adir)) {
regmap_update_bits(sai->regmap, FSL_SAI_xCR4(!tx, ofs),
FSL_SAI_CR4_SYWD_MASK |
FSL_SAI_CR4_FRSZ_MASK |
FSL_SAI_CR4_CHMOD_MASK,
@@ -543,7 +543,7 @@ static int fsl_sai_hw_free(struct snd_pcm_substream
*substream,
regmap_update_bits(sai->regmap, FSL_SAI_xCR3(tx, ofs),
FSL_SAI_CR3_TRCE_MASK, 0);
- if (!sai->is_slave_mode &&
+ if (!sai->is_consumer_mode &&
sai->mclk_streams & BIT(substream->stream)) {
clk_disable_unprepare(sai->mclk_clk[sai->mclk_id[tx]]);
sai->mclk_streams &= ~BIT(substream->stream);
@@ -577,7 +577,7 @@ static void fsl_sai_config_disable(struct fsl_sai *sai, int
dir)
* This is a hardware bug, and will be fix in the
* next sai version.
*/
- if (!sai->is_slave_mode) {
+ if (!sai->is_consumer_mode) {
/* Software Reset */
regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs),
FSL_SAI_CSR_SR);
/* Clear SR bit to finish the reset */
diff --git a/sound/soc/fsl/fsl_sai.h b/sound/soc/fsl/fsl_sai.h
index bc60030967dd..9aaf231bc024 100644
--- a/sound/soc/fsl/fsl_sai.h
+++ b/sound/soc/fsl/fsl_sai.h
@@ -259,7 +259,7 @@ struct fsl_sai {
struct clk *bus_clk;
struct clk *mclk_clk[FSL_SAI_MCLK_MAX];
- bool is_slave_mode;
+ bool is_consumer_mode;
bool is_lsb_first;
bool is_dsp_mode;
bool synchronous[2];
--
2.20.1
[PATCH v2 05/16] ASoC: fsl-mqs: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl-mqs driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl_mqs.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sound/soc/fsl/fsl_mqs.c b/sound/soc/fsl/fsl_mqs.c
index 69aeb0e71844..27b4536dce44 100644
--- a/sound/soc/fsl/fsl_mqs.c
+++ b/sound/soc/fsl/fsl_mqs.c
@@ -102,8 +102,8 @@ static int fsl_mqs_set_dai_fmt(struct snd_soc_dai *dai,
unsigned int fmt)
return -EINVAL;
}
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBS_CFS:
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBC_CFC:
break;
default:
return -EINVAL;
--
2.20.1
[PATCH v2 04/16] ASoC: fsl-esai: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl-esai driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl_esai.c | 28 ++--
1 file changed, 14 insertions(+), 14 deletions(-)
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index bda66b30e063..3a9e2df4e16f 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -52,7 +52,7 @@ struct fsl_esai_soc_data {
* @sck_rate: clock rate of desired SCKx clock
* @hck_dir: the direction of HCKx pads
* @sck_div: if using PSR/PM dividers for SCKx clock
- * @slave_mode: if fully using DAI slave mode
+ * @consumer_mode: if fully using DAI clock consumer mode
* @synchronous: if using tx/rx synchronous mode
* @name: driver name
*/
@@ -78,7 +78,7 @@ struct fsl_esai {
u32 sck_rate[2];
bool hck_dir[2];
bool sck_div[2];
- bool slave_mode;
+ bool consumer_mode;
bool synchronous;
char name[32];
};
@@ -366,8 +366,8 @@ static int fsl_esai_set_bclk(struct snd_soc_dai *dai, bool
tx, u32 freq)
u32 sub, ratio = hck_rate / freq;
int ret;
- /* Don't apply for fully slave mode or unchanged bclk */
- if (esai_priv->slave_mode || esai_priv->sck_rate[tx] == freq)
+ /* Don't apply for fully consumer mode or unchanged bclk */
+ if (esai_priv->consumer_mode || esai_priv->sck_rate[tx] == freq)
return 0;
if (ratio * freq > hck_rate)
@@ -476,20 +476,20 @@ static int fsl_esai_set_dai_fmt(struct snd_soc_dai *dai,
unsigned int fmt)
return -EINVAL;
}
- esai_priv->slave_mode = false;
+ esai_priv->consumer_mode = false;
- /* DAI clock master masks */
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBM_CFM:
- esai_priv->slave_mode = true;
+ /* DAI clock provider masks */
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBP_CFP:
+ esai_priv->consumer_mode = true;
break;
- case SND_SOC_DAIFMT_CBS_CFM:
+ case SND_SOC_DAIFMT_CBC_CFP:
xccr |= ESAI_xCCR_xCKD;
break;
- case SND_SOC_DAIFMT_CBM_CFS:
+ case SND_SOC_DAIFMT_CBP_CFC:
xccr |= ESAI_xCCR_xFSD;
break;
- case SND_SOC_DAIFMT_CBS_CFS:
+ case SND_SOC_DAIFMT_CBC_CFC:
xccr |= ESAI_xCCR_xFSD | ESAI_xCCR_xCKD;
break;
default:
@@ -1016,8 +1016,8 @@ static int fsl_esai_probe(struct platform_device *pdev)
/* Set a default slot number */
esai_priv->slots = 2;
- /* Set a default master/slave state */
- esai_priv->slave_mode = true;
+ /* Set a default clock provider state */
+ esai_priv->consumer_mode = true;
/* Determine the FIFO depth */
iprop = of_get_property(np, "fsl,fifo-depth", NULL);
--
2.20.1
[PATCH v2 03/16] ASoC: fsl-audmix: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl-audmix driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl_audmix.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/sound/soc/fsl/fsl_audmix.c b/sound/soc/fsl/fsl_audmix.c
index f931288e256c..6dbb8c99f626 100644
--- a/sound/soc/fsl/fsl_audmix.c
+++ b/sound/soc/fsl/fsl_audmix.c
@@ -257,10 +257,10 @@ static int fsl_audmix_dai_set_fmt(struct snd_soc_dai
*dai, unsigned int fmt)
return -EINVAL;
}
- /* For playback the AUDMIX is slave, and for record is master */
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBM_CFM:
- case SND_SOC_DAIFMT_CBS_CFS:
+ /* For playback the AUDMIX is consumer, and for record is provider */
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBP_CFP:
+ case SND_SOC_DAIFMT_CBC_CFC:
break;
default:
return -EINVAL;
--
2.20.1
[PATCH v2 02/16] ASoC: fsl-asoc-card: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl-asoc-card driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl-asoc-card.c | 54 +--
1 file changed, 27 insertions(+), 27 deletions(-)
diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index 06107ae46e20..6e6494f9f399 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -356,8 +356,8 @@ static int fsl_asoc_card_audmux_init(struct device_node *np,
* If only 4 wires are needed, just set SSI into
* synchronous mode and enable 4 PADs in IOMUX.
*/
- switch (priv->dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBM_CFM:
+ switch (priv->dai_fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBP_CFP:
int_ptcr = IMX_AUDMUX_V2_PTCR_RFSEL(8 | ext_port) |
IMX_AUDMUX_V2_PTCR_RCSEL(8 | ext_port) |
IMX_AUDMUX_V2_PTCR_TFSEL(ext_port) |
@@ -367,7 +367,7 @@ static int fsl_asoc_card_audmux_init(struct device_node *np,
IMX_AUDMUX_V2_PTCR_TFSDIR |
IMX_AUDMUX_V2_PTCR_TCLKDIR;
break;
- case SND_SOC_DAIFMT_CBM_CFS:
+ case SND_SOC_DAIFMT_CBP_CFC:
int_ptcr = IMX_AUDMUX_V2_PTCR_RCSEL(8 | ext_port) |
IMX_AUDMUX_V2_PTCR_TCSEL(ext_port) |
IMX_AUDMUX_V2_PTCR_RCLKDIR |
@@ -377,7 +377,7 @@ static int fsl_asoc_card_audmux_init(struct device_node *np,
IMX_AUDMUX_V2_PTCR_RFSDIR |
IMX_AUDMUX_V2_PTCR_TFSDIR;
break;
- case SND_SOC_DAIFMT_CBS_CFM:
+ case SND_SOC_DAIFMT_CBC_CFP:
int_ptcr = IMX_AUDMUX_V2_PTCR_RFSEL(8 | ext_port) |
IMX_AUDMUX_V2_PTCR_TFSEL(ext_port) |
IMX_AUDMUX_V2_PTCR_RFSDIR |
@@ -387,7 +387,7 @@ static int fsl_asoc_card_audmux_init(struct device_node *np,
IMX_AUDMUX_V2_PTCR_RCLKDIR |
IMX_AUDMUX_V2_PTCR_TCLKDIR;
break;
- case SND_SOC_DAIFMT_CBS_CFS:
+ case SND_SOC_DAIFMT_CBC_CFC:
ext_ptcr = IMX_AUDMUX_V2_PTCR_RFSEL(8 | int_port) |
IMX_AUDMUX_V2_PTCR_RCSEL(8 | int_port) |
IMX_AUDMUX_V2_PTCR_TFSEL(int_port) |
@@ -533,8 +533,8 @@ static int fsl_asoc_card_probe(struct platform_device *pdev)
struct device_node *cpu_np, *codec_np, *asrc_np;
struct device_node *np = pdev->dev.of_node;
struct platform_device *asrc_pdev = NULL;
- struct device_node *bitclkmaster = NULL;
- struct device_node *framemaster = NULL;
+ struct device_node *bitclkprovider = NULL;
+ struct device_node *frameprovider = NULL;
struct platform_device *cpu_pdev;
struct fsl_asoc_card_priv *priv;
struct device *codec_dev = NULL;
@@ -617,29 +617,29 @@ static int fsl_asoc_card_probe(struct platform_device
*pdev)
priv->cpu_priv.sysclk_dir[TX] = SND_SOC_CLOCK_OUT;
priv->cpu_priv.sysclk_dir[RX] = SND_SOC_CLOCK_OUT;
priv->cpu_priv.slot_width = 32;
- priv->dai_fmt |= SND_SOC_DAIFMT_CBS_CFS;
+ priv->dai_fmt |= SND_SOC_DAIFMT_CBC_CFC;
} else if (of_device_is_compatible(np, "fsl,imx-audio-cs427x")) {
codec_dai_name = "cs4271-hifi";
priv->codec_priv.mclk_id = CS427x_SYSCLK_MCLK;
- priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+ priv->dai_fmt |= SND_SOC_DAIFMT_CBP_CFP;
} else if (of_device_is_compatible(np, "fsl,imx-audio-sgtl5000")) {
codec_dai_name = "sgtl5000";
priv->codec_priv.mclk_id = SGTL5000_SYSCLK;
- priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+ priv->dai_fmt |= SND_SOC_DAIFMT_CBP_CFP;
} else if (of_device_is_compatible(np, "fsl,imx-audio-tlv320aic32x4")) {
codec_dai_name = "tlv320aic32x4-hifi";
- priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+ priv->dai_fmt |= SND_SOC_DAIFMT_CBP_CFP;
} else if (of_device_is_compatible(np, "fsl,imx-audio-wm8962")) {
codec_dai_name = "wm8962";
priv->codec_priv.mclk_id = WM8962_SYSCLK_MCLK;
priv->codec_priv.fll_id = WM8962_SYSCLK_FLL;
priv->codec_priv.pll_id = WM8962_FLL;
- priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+ priv->dai_fmt |= SND_SOC_DAIFMT_CBP_CFP;
} else if (of_device_is_compatible(np, "fsl,imx-audio-wm8960")) {
codec_dai_name = "wm8960-hifi";
priv->codec_priv.fll_id = WM8960_SYSCLK_AUTO;
priv->codec_priv.pll_id = WM8960_SYSCLK_AUTO;
-
[PATCH v2 01/16] ASoC: eureka-tlv320: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the eureka-tlv320 driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/eukrea-tlv320.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sound/soc/fsl/eukrea-tlv320.c b/sound/soc/fsl/eukrea-tlv320.c
index e13271ea84de..8b61582753c8 100644
--- a/sound/soc/fsl/eukrea-tlv320.c
+++ b/sound/soc/fsl/eukrea-tlv320.c
@@ -70,7 +70,7 @@ static struct snd_soc_dai_link eukrea_tlv320_dai = {
.name = "tlv320aic23",
.stream_name= "TLV320AIC23",
.dai_fmt= SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_CBM_CFM,
+ SND_SOC_DAIFMT_CBP_CFP,
.ops= _tlv320_snd_ops,
SND_SOC_DAILINK_REG(hifi),
};
--
2.20.1
Re: [PATCH v3 5/8] x86/sme: Replace occurrences of sme_active() with cc_platform_has()
On Tue, Sep 21, 2021 at 11:27:17PM +0200, Borislav Petkov wrote: > On Wed, Sep 22, 2021 at 12:20:59AM +0300, Kirill A. Shutemov wrote: > > I still believe calling cc_platform_has() from __startup_64() is totally > > broken as it lacks proper wrapping while accessing global variables. > > Well, one of the issues on the AMD side was using boot_cpu_data too > early and the Intel side uses it too. Can you replace those checks with > is_tdx_guest() or whatever was the helper's name which would check > whether the the kernel is running as a TDX guest, and see if that helps? There's no need in Intel check this early. Only AMD need it. Maybe just opencode them? -- Kirill A. Shutemov
Re: [PATCH v3 5/8] x86/sme: Replace occurrences of sme_active() with cc_platform_has()
On Wed, Sep 22, 2021 at 12:20:59AM +0300, Kirill A. Shutemov wrote: > I still believe calling cc_platform_has() from __startup_64() is totally > broken as it lacks proper wrapping while accessing global variables. Well, one of the issues on the AMD side was using boot_cpu_data too early and the Intel side uses it too. Can you replace those checks with is_tdx_guest() or whatever was the helper's name which would check whether the the kernel is running as a TDX guest, and see if that helps? Thx. -- Regards/Gruss, Boris.
Re: [PATCH 03/16] ASoC: fsl-audmix: Update to modern clocking terminology
On Tue, Sep 21, 2021 at 06:22:51PM -0300, Fabio Estevam wrote: > On Tue, Sep 21, 2021 at 6:11 PM Mark Brown wrote: > > - /* For playback the AUDMIX is slave, and for record is master */ > > + /* For playback the AUDMIX is provider, and for record is consumer > > */ > I think the comment should be the other way around: >/* For playback the AUDMIX is consumer, and for record is provider */ > Other than that, the series looks good. Right, yes. signature.asc Description: PGP signature
Re: [PATCH 03/16] ASoC: fsl-audmix: Update to modern clocking terminology
On Tue, Sep 21, 2021 at 6:11 PM Mark Brown wrote:
>
> As part of moving to remove the old style defines for the bus clocks update
> the fsl-audmix driver to use more modern terminology for clocking.
>
> Signed-off-by: Mark Brown
> ---
> sound/soc/fsl/fsl_audmix.c | 8
> 1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/sound/soc/fsl/fsl_audmix.c b/sound/soc/fsl/fsl_audmix.c
> index f931288e256c..db2dde597edc 100644
> --- a/sound/soc/fsl/fsl_audmix.c
> +++ b/sound/soc/fsl/fsl_audmix.c
> @@ -257,10 +257,10 @@ static int fsl_audmix_dai_set_fmt(struct snd_soc_dai
> *dai, unsigned int fmt)
> return -EINVAL;
> }
>
> - /* For playback the AUDMIX is slave, and for record is master */
> - switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
> - case SND_SOC_DAIFMT_CBM_CFM:
> - case SND_SOC_DAIFMT_CBS_CFS:
> + /* For playback the AUDMIX is provider, and for record is consumer */
> + switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
I think the comment should be the other way around:
/* For playback the AUDMIX is consumer, and for record is provider */
Other than that, the series looks good.
Re: [PATCH v3 5/8] x86/sme: Replace occurrences of sme_active() with cc_platform_has()
On Tue, Sep 21, 2021 at 07:47:15PM +0200, Borislav Petkov wrote:
> On Tue, Sep 21, 2021 at 12:04:58PM -0500, Tom Lendacky wrote:
> > Looks like instrumentation during early boot. I worked with Boris offline to
> > exclude arch/x86/kernel/cc_platform.c from some of the instrumentation and
> > that allowed an allyesconfig to boot.
>
> And here's the lineup I have so far, I'd appreciate it if ppc and s390 folks
> could run it too:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git/log/?h=rc2-cc
Still broken for me with allyesconfig.
gcc version 11.2.0 (Gentoo 11.2.0 p1)
GNU ld (Gentoo 2.37_p1 p0) 2.37
I still believe calling cc_platform_has() from __startup_64() is totally
broken as it lacks proper wrapping while accessing global variables.
I think sme_get_me_mask() has the same problem. I just happened to work
(until next compiler update).
This hack makes kernel boot again:
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index f98c76a1d16c..e9110a44bf1b 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -285,7 +285,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
* there is no need to zero it after changing the memory encryption
* attribute.
*/
- if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+ if (0 && cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
vaddr = (unsigned long)__start_bss_decrypted;
vaddr_end = (unsigned long)__end_bss_decrypted;
for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
diff --git a/arch/x86/mm/mem_encrypt_identity.c
b/arch/x86/mm/mem_encrypt_identity.c
index eff4d19f9cb4..91638ed0b1db 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -288,7 +288,7 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
unsigned long pgtable_area_len;
unsigned long decrypted_base;
- if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+ if (1 || !cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
return;
/*
--
Kirill A. Shutemov
[PATCH 16/16] ASoC: pl1022_rdk: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the pl1022_rdk driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/p1022_rdk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/p1022_rdk.c b/sound/soc/fsl/p1022_rdk.c index 714515b8081f..b395adabe823 100644 --- a/sound/soc/fsl/p1022_rdk.c +++ b/sound/soc/fsl/p1022_rdk.c @@ -265,7 +265,7 @@ static int p1022_rdk_probe(struct platform_device *pdev) * only one way to configure the SSI. */ mdata->dai_format = SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBM_CFM; + SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBP_CFP; mdata->codec_clk_direction = SND_SOC_CLOCK_OUT; mdata->cpu_clk_direction = SND_SOC_CLOCK_IN; -- 2.20.1
[PATCH 15/16] ASoC: pl1022_ds: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the pl1022_ds driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/p1022_ds.c | 16
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/sound/soc/fsl/p1022_ds.c b/sound/soc/fsl/p1022_ds.c
index 317c767b0099..b45742931b0d 100644
--- a/sound/soc/fsl/p1022_ds.c
+++ b/sound/soc/fsl/p1022_ds.c
@@ -275,7 +275,7 @@ static int p1022_ds_probe(struct platform_device *pdev)
if (strcasecmp(sprop, "i2s-slave") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBP_CFP;
mdata->codec_clk_direction = SND_SOC_CLOCK_OUT;
mdata->cpu_clk_direction = SND_SOC_CLOCK_IN;
@@ -293,37 +293,37 @@ static int p1022_ds_probe(struct platform_device *pdev)
mdata->clk_frequency = be32_to_cpup(iprop);
} else if (strcasecmp(sprop, "i2s-master") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBC_CFC;
mdata->codec_clk_direction = SND_SOC_CLOCK_IN;
mdata->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "lj-slave") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBP_CFP;
mdata->codec_clk_direction = SND_SOC_CLOCK_OUT;
mdata->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "lj-master") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBC_CFC;
mdata->codec_clk_direction = SND_SOC_CLOCK_IN;
mdata->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "rj-slave") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBP_CFP;
mdata->codec_clk_direction = SND_SOC_CLOCK_OUT;
mdata->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "rj-master") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBC_CFC;
mdata->codec_clk_direction = SND_SOC_CLOCK_IN;
mdata->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "ac97-slave") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBP_CFP;
mdata->codec_clk_direction = SND_SOC_CLOCK_OUT;
mdata->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "ac97-master") == 0) {
mdata->dai_format = SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBC_CFC;
mdata->codec_clk_direction = SND_SOC_CLOCK_IN;
mdata->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else {
--
2.20.1
[PATCH 14/16] ASoC: mpc8610_hpcd: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the mpc8610_hpcd driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/mpc8610_hpcd.c | 16
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/sound/soc/fsl/mpc8610_hpcd.c b/sound/soc/fsl/mpc8610_hpcd.c
index 58b9ca3c4da0..e71a992fbf93 100644
--- a/sound/soc/fsl/mpc8610_hpcd.c
+++ b/sound/soc/fsl/mpc8610_hpcd.c
@@ -264,7 +264,7 @@ static int mpc8610_hpcd_probe(struct platform_device *pdev)
if (strcasecmp(sprop, "i2s-slave") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBP_CFP;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
@@ -282,37 +282,37 @@ static int mpc8610_hpcd_probe(struct platform_device
*pdev)
machine_data->clk_frequency = be32_to_cpup(iprop);
} else if (strcasecmp(sprop, "i2s-master") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBC_CFC;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "lj-slave") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBP_CFP;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "lj-master") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBC_CFC;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "rj-slave") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBP_CFP;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "rj-master") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBC_CFC;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else if (strcasecmp(sprop, "ac97-slave") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBP_CFP;
machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
} else if (strcasecmp(sprop, "ac97-master") == 0) {
machine_data->dai_format =
- SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBC_CFC;
machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
} else {
--
2.20.1
[PATCH 13/16] ASoC: imx-sgtl5000: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the imx-sgtl5000 driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/imx-sgtl5000.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/imx-sgtl5000.c b/sound/soc/fsl/imx-sgtl5000.c index f45cb4bbb6c4..2f1acd011042 100644 --- a/sound/soc/fsl/imx-sgtl5000.c +++ b/sound/soc/fsl/imx-sgtl5000.c @@ -153,7 +153,7 @@ static int imx_sgtl5000_probe(struct platform_device *pdev) data->dai.platforms->of_node = ssi_np; data->dai.init = _sgtl5000_dai_init; data->dai.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_CBM_CFM; + SND_SOC_DAIFMT_CBP_CFP; data->card.dev = >dev; ret = snd_soc_of_parse_card_name(>card, "model"); -- 2.20.1
[PATCH 12/16] ASoC: imx-rpmsg: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the imx-rpmsg driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/imx-rpmsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/imx-rpmsg.c b/sound/soc/fsl/imx-rpmsg.c index f96fe4ff8425..2e117311e582 100644 --- a/sound/soc/fsl/imx-rpmsg.c +++ b/sound/soc/fsl/imx-rpmsg.c @@ -64,7 +64,7 @@ static int imx_rpmsg_probe(struct platform_device *pdev) data->dai.stream_name = "rpmsg hifi"; data->dai.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_CBS_CFS; + SND_SOC_DAIFMT_CBC_CFC; /* Optional codec node */ ret = of_parse_phandle_with_fixed_args(np, "audio-codec", 0, 0, ); -- 2.20.1
[PATCH 11/16] ASoC: imx-hdmi: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the imx-hdmi driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/imx-hdmi.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sound/soc/fsl/imx-hdmi.c b/sound/soc/fsl/imx-hdmi.c
index 34a0dceae621..c15e930fa2a6 100644
--- a/sound/soc/fsl/imx-hdmi.c
+++ b/sound/soc/fsl/imx-hdmi.c
@@ -171,7 +171,7 @@ static int imx_hdmi_probe(struct platform_device *pdev)
data->dai.codecs->name = "hdmi-audio-codec.1";
data->dai.dai_fmt = data->dai_fmt |
SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_CBS_CFS;
+ SND_SOC_DAIFMT_CBC_CFC;
}
if (hdmi_in) {
@@ -181,7 +181,7 @@ static int imx_hdmi_probe(struct platform_device *pdev)
data->dai.codecs->name = "hdmi-audio-codec.2";
data->dai.dai_fmt = data->dai_fmt |
SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_CBM_CFM;
+ SND_SOC_DAIFMT_CBP_CFP;
}
data->card.dapm_widgets = imx_hdmi_widgets;
--
2.20.1
[PATCH 10/16] ASoC: imx-es8328: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the imx-es8328 driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/imx-es8328.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/imx-es8328.c b/sound/soc/fsl/imx-es8328.c index 1981dcd7e930..09c674ee79f1 100644 --- a/sound/soc/fsl/imx-es8328.c +++ b/sound/soc/fsl/imx-es8328.c @@ -174,7 +174,7 @@ static int imx_es8328_probe(struct platform_device *pdev) data->dai.platforms->of_node = ssi_np; data->dai.init = _es8328_dai_init; data->dai.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_CBM_CFM; + SND_SOC_DAIFMT_CBP_CFP; data->card.dev = dev; data->card.dapm_widgets = imx_es8328_dapm_widgets; -- 2.20.1
[PATCH 09/16] ASoC: imx-card: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the imx-card driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/imx-card.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c index 58fd0639a069..e9fe3fc2f261 100644 --- a/sound/soc/fsl/imx-card.c +++ b/sound/soc/fsl/imx-card.c @@ -652,7 +652,7 @@ static int imx_card_parse_of(struct imx_card_data *data) NULL, >dai_fmt); if (ret) link->dai_fmt = SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_CBS_CFS | + SND_SOC_DAIFMT_CBC_CFC | SND_SOC_DAIFMT_I2S; /* Get tdm slot */ -- 2.20.1
[PATCH 08/16] ASoC: imx-audmix: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update the imx-audmix driver to use more modern terminology for clocking. Signed-off-by: Mark Brown --- sound/soc/fsl/imx-audmix.c | 8 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c index a364e2415de0..e8b438a0329e 100644 --- a/sound/soc/fsl/imx-audmix.c +++ b/sound/soc/fsl/imx-audmix.c @@ -80,8 +80,8 @@ static int imx_audmix_fe_hw_params(struct snd_pcm_substream *substream, u32 channels = params_channels(params); int ret, dir; - /* For playback the AUDMIX is slave, and for record is master */ - fmt |= tx ? SND_SOC_DAIFMT_CBS_CFS : SND_SOC_DAIFMT_CBM_CFM; + /* For playback the AUDMIX is consumer, and for record is provider */ + fmt |= tx ? SND_SOC_DAIFMT_CBC_CFC : SND_SOC_DAIFMT_CBP_CFP; dir = tx ? SND_SOC_CLOCK_OUT : SND_SOC_CLOCK_IN; /* set DAI configuration */ @@ -121,8 +121,8 @@ static int imx_audmix_be_hw_params(struct snd_pcm_substream *substream, if (!tx) return 0; - /* For playback the AUDMIX is slave */ - fmt |= SND_SOC_DAIFMT_CBM_CFM; + /* For playback the AUDMIX is consumer */ + fmt |= SND_SOC_DAIFMT_CBP_CFP; /* set AUDMIX DAI configuration */ ret = snd_soc_dai_set_fmt(asoc_rtd_to_cpu(rtd, 0), fmt); -- 2.20.1
[PATCH 07/16] ASoC: fsl_ssi: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl_ssi driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl_ssi.c | 38 +++---
1 file changed, 19 insertions(+), 19 deletions(-)
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index ecbc1c365d5b..1169d1104b9e 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -350,16 +350,16 @@ static bool fsl_ssi_is_ac97(struct fsl_ssi *ssi)
SND_SOC_DAIFMT_AC97;
}
-static bool fsl_ssi_is_i2s_master(struct fsl_ssi *ssi)
+static bool fsl_ssi_is_i2s_clock_provider(struct fsl_ssi *ssi)
{
- return (ssi->dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) ==
- SND_SOC_DAIFMT_CBS_CFS;
+ return (ssi->dai_fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) ==
+ SND_SOC_DAIFMT_CBC_CFC;
}
-static bool fsl_ssi_is_i2s_cbm_cfs(struct fsl_ssi *ssi)
+static bool fsl_ssi_is_i2s_cbp_cfc(struct fsl_ssi *ssi)
{
- return (ssi->dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) ==
- SND_SOC_DAIFMT_CBM_CFS;
+ return (ssi->dai_fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) ==
+ SND_SOC_DAIFMT_CBP_CFC;
}
/**
@@ -808,7 +808,7 @@ static int fsl_ssi_hw_params(struct snd_pcm_substream
*substream,
u32 wl = SSI_SxCCR_WL(sample_size);
int ret;
- if (fsl_ssi_is_i2s_master(ssi)) {
+ if (fsl_ssi_is_i2s_clock_provider(ssi)) {
ret = fsl_ssi_set_bclk(substream, dai, hw_params);
if (ret)
return ret;
@@ -841,7 +841,7 @@ static int fsl_ssi_hw_params(struct snd_pcm_substream
*substream,
u8 i2s_net = ssi->i2s_net;
/* Normal + Network mode to send 16-bit data in 32-bit frames */
- if (fsl_ssi_is_i2s_cbm_cfs(ssi) && sample_size == 16)
+ if (fsl_ssi_is_i2s_cbp_cfc(ssi) && sample_size == 16)
i2s_net = SSI_SCR_I2S_MODE_NORMAL | SSI_SCR_NET;
/* Use Normal mode to send mono data at 1st slot of 2 slots */
@@ -865,7 +865,7 @@ static int fsl_ssi_hw_free(struct snd_pcm_substream
*substream,
struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
struct fsl_ssi *ssi = snd_soc_dai_get_drvdata(asoc_rtd_to_cpu(rtd, 0));
- if (fsl_ssi_is_i2s_master(ssi) &&
+ if (fsl_ssi_is_i2s_clock_provider(ssi) &&
ssi->baudclk_streams & BIT(substream->stream)) {
clk_disable_unprepare(ssi->baudclk);
ssi->baudclk_streams &= ~BIT(substream->stream);
@@ -891,18 +891,18 @@ static int _fsl_ssi_set_dai_fmt(struct fsl_ssi *ssi,
unsigned int fmt)
ssi->i2s_net = SSI_SCR_NET;
switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
case SND_SOC_DAIFMT_I2S:
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBS_CFS:
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBC_CFC:
if (IS_ERR(ssi->baudclk)) {
dev_err(ssi->dev,
"missing baudclk for master mode\n");
return -EINVAL;
}
fallthrough;
- case SND_SOC_DAIFMT_CBM_CFS:
+ case SND_SOC_DAIFMT_CBP_CFC:
ssi->i2s_net |= SSI_SCR_I2S_MODE_MASTER;
break;
- case SND_SOC_DAIFMT_CBM_CFM:
+ case SND_SOC_DAIFMT_CBP_CFP:
ssi->i2s_net |= SSI_SCR_I2S_MODE_SLAVE;
break;
default:
@@ -962,17 +962,17 @@ static int _fsl_ssi_set_dai_fmt(struct fsl_ssi *ssi,
unsigned int fmt)
return -EINVAL;
}
- /* DAI clock master masks */
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBS_CFS:
+ /* DAI clock provider masks */
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBC_CFC:
/* Output bit and frame sync clocks */
strcr |= SSI_STCR_TFDIR | SSI_STCR_TXDIR;
scr |= SSI_SCR_SYS_CLK_EN;
break;
- case SND_SOC_DAIFMT_CBM_CFM:
+ case SND_SOC_DAIFMT_CBP_CFP:
/* Input bit or frame sync clocks */
break;
- case SND_SOC_DAIFMT_CBM_CFS:
+ case SND_SOC_DAIFMT_CBP_CFC:
/* Input bit clock but output frame sync clock */
strcr |= SSI_STCR_TFDIR;
break;
@@ -1341,7 +1341,7 @@ static int fsl_ssi_imx_probe(struct platform_device *pdev,
}
}
- /* Do not error out for slave cases that live without a baud clock */
+ /* Do not error out for consumer cases that live without a baud clock */
ssi->baudclk =
[PATCH 06/16] ASoC: fsl_sai: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl_sai driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl_sai.c | 34 +-
sound/soc/fsl/fsl_sai.h | 2 +-
2 files changed, 18 insertions(+), 18 deletions(-)
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index 38f6362099d5..10544fa27dc0 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -297,23 +297,23 @@ static int fsl_sai_set_dai_fmt_tr(struct snd_soc_dai
*cpu_dai,
return -EINVAL;
}
- /* DAI clock master masks */
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBS_CFS:
+ /* DAI clock provider masks */
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBC_CFC:
val_cr2 |= FSL_SAI_CR2_BCD_MSTR;
val_cr4 |= FSL_SAI_CR4_FSD_MSTR;
- sai->is_slave_mode = false;
+ sai->is_consumer_mode = false;
break;
- case SND_SOC_DAIFMT_CBM_CFM:
- sai->is_slave_mode = true;
+ case SND_SOC_DAIFMT_CBP_CFP:
+ sai->is_consumer_mode = true;
break;
- case SND_SOC_DAIFMT_CBS_CFM:
+ case SND_SOC_DAIFMT_CBC_CFP:
val_cr2 |= FSL_SAI_CR2_BCD_MSTR;
- sai->is_slave_mode = false;
+ sai->is_consumer_mode = false;
break;
- case SND_SOC_DAIFMT_CBM_CFS:
+ case SND_SOC_DAIFMT_CBP_CFC:
val_cr4 |= FSL_SAI_CR4_FSD_MSTR;
- sai->is_slave_mode = true;
+ sai->is_consumer_mode = true;
break;
default:
return -EINVAL;
@@ -356,8 +356,8 @@ static int fsl_sai_set_bclk(struct snd_soc_dai *dai, bool
tx, u32 freq)
u32 id;
int ret = 0;
- /* Don't apply to slave mode */
- if (sai->is_slave_mode)
+ /* Don't apply to consumer mode */
+ if (sai->is_consumer_mode)
return 0;
/*
@@ -462,7 +462,7 @@ static int fsl_sai_hw_params(struct snd_pcm_substream
*substream,
pins = DIV_ROUND_UP(channels, slots);
- if (!sai->is_slave_mode) {
+ if (!sai->is_consumer_mode) {
if (sai->bclk_ratio)
ret = fsl_sai_set_bclk(cpu_dai, tx,
sai->bclk_ratio *
@@ -502,12 +502,12 @@ static int fsl_sai_hw_params(struct snd_pcm_substream
*substream,
val_cr4 |= FSL_SAI_CR4_CHMOD;
/*
-* For SAI master mode, when Tx(Rx) sync with Rx(Tx) clock, Rx(Tx) will
+* For SAI provider mode, when Tx(Rx) sync with Rx(Tx) clock, Rx(Tx)
will
* generate bclk and frame clock for Tx(Rx), we should set RCR4(TCR4),
* RCR5(TCR5) for playback(capture), or there will be sync error.
*/
- if (!sai->is_slave_mode && fsl_sai_dir_is_synced(sai, adir)) {
+ if (!sai->is_consumer_mode && fsl_sai_dir_is_synced(sai, adir)) {
regmap_update_bits(sai->regmap, FSL_SAI_xCR4(!tx, ofs),
FSL_SAI_CR4_SYWD_MASK |
FSL_SAI_CR4_FRSZ_MASK |
FSL_SAI_CR4_CHMOD_MASK,
@@ -543,7 +543,7 @@ static int fsl_sai_hw_free(struct snd_pcm_substream
*substream,
regmap_update_bits(sai->regmap, FSL_SAI_xCR3(tx, ofs),
FSL_SAI_CR3_TRCE_MASK, 0);
- if (!sai->is_slave_mode &&
+ if (!sai->is_consumer_mode &&
sai->mclk_streams & BIT(substream->stream)) {
clk_disable_unprepare(sai->mclk_clk[sai->mclk_id[tx]]);
sai->mclk_streams &= ~BIT(substream->stream);
@@ -577,7 +577,7 @@ static void fsl_sai_config_disable(struct fsl_sai *sai, int
dir)
* This is a hardware bug, and will be fix in the
* next sai version.
*/
- if (!sai->is_slave_mode) {
+ if (!sai->is_consumer_mode) {
/* Software Reset */
regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs),
FSL_SAI_CSR_SR);
/* Clear SR bit to finish the reset */
diff --git a/sound/soc/fsl/fsl_sai.h b/sound/soc/fsl/fsl_sai.h
index bc60030967dd..9aaf231bc024 100644
--- a/sound/soc/fsl/fsl_sai.h
+++ b/sound/soc/fsl/fsl_sai.h
@@ -259,7 +259,7 @@ struct fsl_sai {
struct clk *bus_clk;
struct clk *mclk_clk[FSL_SAI_MCLK_MAX];
- bool is_slave_mode;
+ bool is_consumer_mode;
bool is_lsb_first;
bool is_dsp_mode;
bool synchronous[2];
--
2.20.1
[PATCH 05/16] ASoC: fsl-mqs: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl-mqs driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl_mqs.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sound/soc/fsl/fsl_mqs.c b/sound/soc/fsl/fsl_mqs.c
index 69aeb0e71844..27b4536dce44 100644
--- a/sound/soc/fsl/fsl_mqs.c
+++ b/sound/soc/fsl/fsl_mqs.c
@@ -102,8 +102,8 @@ static int fsl_mqs_set_dai_fmt(struct snd_soc_dai *dai,
unsigned int fmt)
return -EINVAL;
}
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBS_CFS:
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBC_CFC:
break;
default:
return -EINVAL;
--
2.20.1
[PATCH 04/16] ASoC: fsl-esai: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl-esai driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl_esai.c | 28 ++--
1 file changed, 14 insertions(+), 14 deletions(-)
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index bda66b30e063..3a9e2df4e16f 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -52,7 +52,7 @@ struct fsl_esai_soc_data {
* @sck_rate: clock rate of desired SCKx clock
* @hck_dir: the direction of HCKx pads
* @sck_div: if using PSR/PM dividers for SCKx clock
- * @slave_mode: if fully using DAI slave mode
+ * @consumer_mode: if fully using DAI clock consumer mode
* @synchronous: if using tx/rx synchronous mode
* @name: driver name
*/
@@ -78,7 +78,7 @@ struct fsl_esai {
u32 sck_rate[2];
bool hck_dir[2];
bool sck_div[2];
- bool slave_mode;
+ bool consumer_mode;
bool synchronous;
char name[32];
};
@@ -366,8 +366,8 @@ static int fsl_esai_set_bclk(struct snd_soc_dai *dai, bool
tx, u32 freq)
u32 sub, ratio = hck_rate / freq;
int ret;
- /* Don't apply for fully slave mode or unchanged bclk */
- if (esai_priv->slave_mode || esai_priv->sck_rate[tx] == freq)
+ /* Don't apply for fully consumer mode or unchanged bclk */
+ if (esai_priv->consumer_mode || esai_priv->sck_rate[tx] == freq)
return 0;
if (ratio * freq > hck_rate)
@@ -476,20 +476,20 @@ static int fsl_esai_set_dai_fmt(struct snd_soc_dai *dai,
unsigned int fmt)
return -EINVAL;
}
- esai_priv->slave_mode = false;
+ esai_priv->consumer_mode = false;
- /* DAI clock master masks */
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBM_CFM:
- esai_priv->slave_mode = true;
+ /* DAI clock provider masks */
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBP_CFP:
+ esai_priv->consumer_mode = true;
break;
- case SND_SOC_DAIFMT_CBS_CFM:
+ case SND_SOC_DAIFMT_CBC_CFP:
xccr |= ESAI_xCCR_xCKD;
break;
- case SND_SOC_DAIFMT_CBM_CFS:
+ case SND_SOC_DAIFMT_CBP_CFC:
xccr |= ESAI_xCCR_xFSD;
break;
- case SND_SOC_DAIFMT_CBS_CFS:
+ case SND_SOC_DAIFMT_CBC_CFC:
xccr |= ESAI_xCCR_xFSD | ESAI_xCCR_xCKD;
break;
default:
@@ -1016,8 +1016,8 @@ static int fsl_esai_probe(struct platform_device *pdev)
/* Set a default slot number */
esai_priv->slots = 2;
- /* Set a default master/slave state */
- esai_priv->slave_mode = true;
+ /* Set a default clock provider state */
+ esai_priv->consumer_mode = true;
/* Determine the FIFO depth */
iprop = of_get_property(np, "fsl,fifo-depth", NULL);
--
2.20.1
[PATCH 03/16] ASoC: fsl-audmix: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl-audmix driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl_audmix.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/sound/soc/fsl/fsl_audmix.c b/sound/soc/fsl/fsl_audmix.c
index f931288e256c..db2dde597edc 100644
--- a/sound/soc/fsl/fsl_audmix.c
+++ b/sound/soc/fsl/fsl_audmix.c
@@ -257,10 +257,10 @@ static int fsl_audmix_dai_set_fmt(struct snd_soc_dai
*dai, unsigned int fmt)
return -EINVAL;
}
- /* For playback the AUDMIX is slave, and for record is master */
- switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBM_CFM:
- case SND_SOC_DAIFMT_CBS_CFS:
+ /* For playback the AUDMIX is provider, and for record is consumer */
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBP_CFP:
+ case SND_SOC_DAIFMT_CBC_CFC:
break;
default:
return -EINVAL;
--
2.20.1
[PATCH 02/16] ASoC: fsl-asoc-card: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the fsl-asoc-card driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/fsl-asoc-card.c | 54 +--
1 file changed, 27 insertions(+), 27 deletions(-)
diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index 06107ae46e20..6e6494f9f399 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -356,8 +356,8 @@ static int fsl_asoc_card_audmux_init(struct device_node *np,
* If only 4 wires are needed, just set SSI into
* synchronous mode and enable 4 PADs in IOMUX.
*/
- switch (priv->dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) {
- case SND_SOC_DAIFMT_CBM_CFM:
+ switch (priv->dai_fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBP_CFP:
int_ptcr = IMX_AUDMUX_V2_PTCR_RFSEL(8 | ext_port) |
IMX_AUDMUX_V2_PTCR_RCSEL(8 | ext_port) |
IMX_AUDMUX_V2_PTCR_TFSEL(ext_port) |
@@ -367,7 +367,7 @@ static int fsl_asoc_card_audmux_init(struct device_node *np,
IMX_AUDMUX_V2_PTCR_TFSDIR |
IMX_AUDMUX_V2_PTCR_TCLKDIR;
break;
- case SND_SOC_DAIFMT_CBM_CFS:
+ case SND_SOC_DAIFMT_CBP_CFC:
int_ptcr = IMX_AUDMUX_V2_PTCR_RCSEL(8 | ext_port) |
IMX_AUDMUX_V2_PTCR_TCSEL(ext_port) |
IMX_AUDMUX_V2_PTCR_RCLKDIR |
@@ -377,7 +377,7 @@ static int fsl_asoc_card_audmux_init(struct device_node *np,
IMX_AUDMUX_V2_PTCR_RFSDIR |
IMX_AUDMUX_V2_PTCR_TFSDIR;
break;
- case SND_SOC_DAIFMT_CBS_CFM:
+ case SND_SOC_DAIFMT_CBC_CFP:
int_ptcr = IMX_AUDMUX_V2_PTCR_RFSEL(8 | ext_port) |
IMX_AUDMUX_V2_PTCR_TFSEL(ext_port) |
IMX_AUDMUX_V2_PTCR_RFSDIR |
@@ -387,7 +387,7 @@ static int fsl_asoc_card_audmux_init(struct device_node *np,
IMX_AUDMUX_V2_PTCR_RCLKDIR |
IMX_AUDMUX_V2_PTCR_TCLKDIR;
break;
- case SND_SOC_DAIFMT_CBS_CFS:
+ case SND_SOC_DAIFMT_CBC_CFC:
ext_ptcr = IMX_AUDMUX_V2_PTCR_RFSEL(8 | int_port) |
IMX_AUDMUX_V2_PTCR_RCSEL(8 | int_port) |
IMX_AUDMUX_V2_PTCR_TFSEL(int_port) |
@@ -533,8 +533,8 @@ static int fsl_asoc_card_probe(struct platform_device *pdev)
struct device_node *cpu_np, *codec_np, *asrc_np;
struct device_node *np = pdev->dev.of_node;
struct platform_device *asrc_pdev = NULL;
- struct device_node *bitclkmaster = NULL;
- struct device_node *framemaster = NULL;
+ struct device_node *bitclkprovider = NULL;
+ struct device_node *frameprovider = NULL;
struct platform_device *cpu_pdev;
struct fsl_asoc_card_priv *priv;
struct device *codec_dev = NULL;
@@ -617,29 +617,29 @@ static int fsl_asoc_card_probe(struct platform_device
*pdev)
priv->cpu_priv.sysclk_dir[TX] = SND_SOC_CLOCK_OUT;
priv->cpu_priv.sysclk_dir[RX] = SND_SOC_CLOCK_OUT;
priv->cpu_priv.slot_width = 32;
- priv->dai_fmt |= SND_SOC_DAIFMT_CBS_CFS;
+ priv->dai_fmt |= SND_SOC_DAIFMT_CBC_CFC;
} else if (of_device_is_compatible(np, "fsl,imx-audio-cs427x")) {
codec_dai_name = "cs4271-hifi";
priv->codec_priv.mclk_id = CS427x_SYSCLK_MCLK;
- priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+ priv->dai_fmt |= SND_SOC_DAIFMT_CBP_CFP;
} else if (of_device_is_compatible(np, "fsl,imx-audio-sgtl5000")) {
codec_dai_name = "sgtl5000";
priv->codec_priv.mclk_id = SGTL5000_SYSCLK;
- priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+ priv->dai_fmt |= SND_SOC_DAIFMT_CBP_CFP;
} else if (of_device_is_compatible(np, "fsl,imx-audio-tlv320aic32x4")) {
codec_dai_name = "tlv320aic32x4-hifi";
- priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+ priv->dai_fmt |= SND_SOC_DAIFMT_CBP_CFP;
} else if (of_device_is_compatible(np, "fsl,imx-audio-wm8962")) {
codec_dai_name = "wm8962";
priv->codec_priv.mclk_id = WM8962_SYSCLK_MCLK;
priv->codec_priv.fll_id = WM8962_SYSCLK_FLL;
priv->codec_priv.pll_id = WM8962_FLL;
- priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+ priv->dai_fmt |= SND_SOC_DAIFMT_CBP_CFP;
} else if (of_device_is_compatible(np, "fsl,imx-audio-wm8960")) {
codec_dai_name = "wm8960-hifi";
priv->codec_priv.fll_id = WM8960_SYSCLK_AUTO;
priv->codec_priv.pll_id = WM8960_SYSCLK_AUTO;
-
[PATCH 01/16] ASoC: eureka-tlv320: Update to modern clocking terminology
As part of moving to remove the old style defines for the bus clocks update
the eureka-tlv320 driver to use more modern terminology for clocking.
Signed-off-by: Mark Brown
---
sound/soc/fsl/eukrea-tlv320.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sound/soc/fsl/eukrea-tlv320.c b/sound/soc/fsl/eukrea-tlv320.c
index e13271ea84de..8b61582753c8 100644
--- a/sound/soc/fsl/eukrea-tlv320.c
+++ b/sound/soc/fsl/eukrea-tlv320.c
@@ -70,7 +70,7 @@ static struct snd_soc_dai_link eukrea_tlv320_dai = {
.name = "tlv320aic23",
.stream_name= "TLV320AIC23",
.dai_fmt= SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
- SND_SOC_DAIFMT_CBM_CFM,
+ SND_SOC_DAIFMT_CBP_CFP,
.ops= _tlv320_snd_ops,
SND_SOC_DAILINK_REG(hifi),
};
--
2.20.1
coherency issue observed after hotplug on POWER8
Hi, there. We have been investigating an issue we have observed on POWER8 POWERNV systems. When running the kernel selftests reuseport_bpf_cpu after a CPU hotplug, we see crashes, in different forms. [1] I managed to get xmon on that trap, and did some debugging. [2] I tried to dump the BPF JIT code, and it looks different when dumped from CPU#0 and CPU#0x9f (the one that was hotplugged, offlined, then onlined). Here is my partial analysis [3]. Basically, the BPF JIT fills a page with invalid instructions (traps, in ppc64 case), and puts the BPF program in a random offset of the page. In the case of the hotplugged CPU, which was the one that compiled the program, the page had the expected contents (BPF program started at the offset used to run the program). On the other CPU (in many cases, CPU #0), the same memory address/page had different contents, with the program starting at a different offset. Is this a case of a bug in the micro-architecture or the firmware when doing the hotplug? Can someone chime in? Notice that we can't reproduce the same issue on a POWER9 system. Thanks. Cascardo. [1] https://bugs.launchpad.net/ubuntu-kernel-tests/+bug/1927076 [2] https://bugs.launchpad.net/ubuntu-kernel-tests/+bug/1927076/comments/29 [3] https://bugs.launchpad.net/ubuntu-kernel-tests/+bug/1927076/comments/30
Re: [PATCH] mm: Remove HARDENED_USERCOPY_FALLBACK
On Tue, Sep 21, 2021 at 08:11:49AM +0200, Stephen Kitt wrote:
> This has served its purpose and is no longer used. All usercopy
> violations appear to have been handled by now, any remaining
> instances (or new bugs) will cause copies to be rejected.
>
> This isn't a direct revert of commit 2d891fbc3bb6 ("usercopy: Allow
> strict enforcement of whitelists"); since usercopy_fallback is
> effectively 0, the fallback handling is removed too.
>
> This also removes the usercopy_fallback module parameter on
> slab_common.
>
> Link: https://github.com/KSPP/linux/issues/153
> Signed-off-by: Stephen Kitt
> Suggested-by: Kees Cook
Thanks for doing this!
Acked-by: Kees Cook
--
Kees Cook
Re: [PATCH v3 5/8] x86/sme: Replace occurrences of sme_active() with cc_platform_has()
On Tue, Sep 21, 2021 at 12:04:58PM -0500, Tom Lendacky wrote: > Looks like instrumentation during early boot. I worked with Boris offline to > exclude arch/x86/kernel/cc_platform.c from some of the instrumentation and > that allowed an allyesconfig to boot. And here's the lineup I have so far, I'd appreciate it if ppc and s390 folks could run it too: https://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git/log/?h=rc2-cc Thx. -- Regards/Gruss, Boris. https://people.kernel.org/tglx/notes-about-netiquette
Re: [PATCH] ASoC: fsl: Constify static snd_soc_ops
On Mon, 20 Sep 2021 21:39:47 +0200, Rikard Falkeborn wrote: > These are only assigned to the ops field in the snd_soc_dai_link struct > which is a pointer to const struct snd_soc_ops. Make them const to allow > the compiler to put them in read-only memory. > > Applied to https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-next Thanks! [1/1] ASoC: fsl: Constify static snd_soc_ops commit: 815b55e1101f074e737c084e996d086dcb454399 All being well this means that it will be integrated into the linux-next tree (usually sometime in the next 24 hours) and sent to Linus during the next merge window (or sooner if it is a bug fix), however if problems are discovered then the patch may be dropped or reverted. You may get further e-mails resulting from automated or manual testing and review of the tree, please engage with people reporting problems and send followup patches addressing any issues that are reported if needed. If any updates are required or you are submitting further changes they should be sent as incremental updates against current git, existing patches will not be replaced. Please add any relevant lists and maintainers to the CCs when replying to this mail. Thanks, Mark
Re: [PATCH] swiotlb: set IO TLB segment size via cmdline
Hi Robin, >> I use Xen PV display. In my case, PV display backend(Dom0) allocates >> contiguous buffer via DMA-API to >> to implement zero-copy between Dom0 and DomU. >> > Well, something's gone badly wrong there - if you have to shadow the > entire thing in a bounce buffer to import it then it's hardly zero-copy, > is it? If you want to do buffer sharing the buffer really needs to be > allocated appropriately to begin with, such that all relevant devices > can access it directly. That might be something which needs fixing in Xen. > Right, in case when we want to use a zero-copy approach need to avoid using swiotlb bounce buffer for all devices which is potentially using this buffer. The root of the problem is that this buffer mapped to foreign pages and when I tried to retrieve dma_addr for this buffer I got a foreign MFN that bigger than 32 bit and swiotlb tries to use bounce buffer. I understood, that, need to find a way to avoid using swiotlb in this case. At the moment, it's unclear how to do this properly. But, this is another story... I guess, we can have the situation when some device like rcar-du needs to use a sufficiently large buffer which is greater than 256 KB (128(CURRENT_IO_TLB_SEGMENT * 2048) and need to adjust this parameter during boot time, not compilation time. In order to this point, this patch was created. Thanks, Roman пт, 17 сент. 2021 г. в 12:44, Robin Murphy : > > On 2021-09-17 10:36, Roman Skakun wrote: > > Hi, Christoph > > > > I use Xen PV display. In my case, PV display backend(Dom0) allocates > > contiguous buffer via DMA-API to > > to implement zero-copy between Dom0 and DomU. > > Well, something's gone badly wrong there - if you have to shadow the > entire thing in a bounce buffer to import it then it's hardly zero-copy, > is it? If you want to do buffer sharing the buffer really needs to be > allocated appropriately to begin with, such that all relevant devices > can access it directly. That might be something which needs fixing in Xen. > > Robin. > > > When I start Weston under DomU, I got the next log in Dom0: > > ``` > > [ 112.554471] CPU: 0 PID: 367 Comm: weston Tainted: G O > > 5.10.0-yocto-standard+ #312 > > [ 112.575149] Call trace: > > [ 112.577666] dump_backtrace+0x0/0x1b0 > > [ 112.581373] show_stack+0x18/0x70 > > [ 112.584746] dump_stack+0xd0/0x12c > > [ 112.588200] swiotlb_tbl_map_single+0x234/0x360 > > [ 112.592781] xen_swiotlb_map_page+0xe4/0x4c0 > > [ 112.597095] xen_swiotlb_map_sg+0x84/0x12c > > [ 112.601249] dma_map_sg_attrs+0x54/0x60 > > [ 112.605138] vsp1_du_map_sg+0x30/0x60 > > [ 112.608851] rcar_du_vsp_map_fb+0x134/0x170 > > [ 112.613082] rcar_du_vsp_plane_prepare_fb+0x44/0x64 > > [ 112.618007] drm_atomic_helper_prepare_planes+0xac/0x160 > > [ 112.623362] drm_atomic_helper_commit+0x88/0x390 > > [ 112.628029] drm_atomic_nonblocking_commit+0x4c/0x60 > > [ 112.633043] drm_mode_atomic_ioctl+0x9a8/0xb0c > > [ 112.637532] drm_ioctl_kernel+0xc4/0x11c > > [ 112.641506] drm_ioctl+0x21c/0x460 > > [ 112.644967] __arm64_sys_ioctl+0xa8/0xf0 > > [ 112.648939] el0_svc_common.constprop.0+0x78/0x1a0 > > [ 112.653775] do_el0_svc+0x24/0x90 > > [ 112.657148] el0_svc+0x14/0x20 > > [ 112.660254] el0_sync_handler+0x1a4/0x1b0 > > [ 112.664315] el0_sync+0x174/0x180 > > [ 112.668145] rcar-fcp fea2f000.fcp: swiotlb buffer is full (sz: > > 3686400 bytes), total 65536 (slots), used 112 (slots) > > ``` > > The problem is happened here: > > https://elixir.bootlin.com/linux/v5.14.4/source/drivers/gpu/drm/rcar-du/rcar_du_vsp.c#L202 > > > > Sgt was created in dma_get_sgtable() by dma_common_get_sgtable() and > > includes a single page chunk > > as shown here: > > https://elixir.bootlin.com/linux/v5.14.5/source/kernel/dma/ops_helpers.c#L18 > > > > After creating a new sgt, we tried to map this sgt through vsp1_du_map_sg(). > > Internally, vsp1_du_map_sg() using ops->map_sg (e.g > > xen_swiotlb_map_sg) to perform > > mapping. > > > > I realized that required segment is too big to be fitted to default > > swiotlb segment and condition > > https://elixir.bootlin.com/linux/latest/source/kernel/dma/swiotlb.c#L474 > > is always false. > > > > I know that I use a large buffer, but why can't I map this buffer in one > > chunk? > > > > Thanks! > > > > ср, 15 сент. 2021 г. в 16:53, Christoph Hellwig : > >> > >> On Wed, Sep 15, 2021 at 03:49:52PM +0200, Jan Beulich wrote: > >>> But the question remains: Why does the framebuffer need to be mapped > >>> in a single giant chunk? > >> > >> More importantly: if you use dynamic dma mappings for your framebuffer > >> you're doing something wrong. > > > > > > -- Best Regards, Roman.
Re: [PATCH v4 1/3] powerpc/bitops: Use immediate operand when possible
Le 20/09/2021 à 23:23, Segher Boessenkool a écrit :
Hi!
On Mon, Sep 20, 2021 at 10:31:17AM +0200, Christophe Leroy wrote:
Today we get the following code generation for bitops like
set or clear bit:
c0009fe0: 39 40 08 00 li r10,2048
c0009fe4: 7c e0 40 28 lwarx r7,0,r8
c0009fe8: 7c e7 53 78 or r7,r7,r10
c0009fec: 7c e0 41 2d stwcx. r7,0,r8
c000d568: 39 00 18 00 li r8,6144
c000d56c: 7c c0 38 28 lwarx r6,0,r7
c000d570: 7c c6 40 78 andcr6,r6,r8
c000d574: 7c c0 39 2d stwcx. r6,0,r7
Most set bits are constant on lower 16 bits, so it can easily
be replaced by the "immediate" version of the operation. Allow
GCC to choose between the normal or immediate form.
You can also handle the second sixteen bits (the "shifted" half), by
using oris etc. The "%eN" output modifier prints an "s" for this:
/* If the low 16 bits are 0, but some other bit is set, write 's'. */
But this doesn't handle non-constant arguments, so you're likely better
off using what you have noe.
For clear bits, on 32 bits 'rlwinm' can be used instead of 'andc' for
when all bits to be cleared are consecutive.
Or when all you want to keep are consecutive (you do handle that now :-) )
On 64 bits we don't have any equivalent single operation for clearing,
single bits or a few bits, we'd need two 'rldicl' so it is not
worth it, the li/andc sequence is doing the same.
You can use rlwinm whenever you want to clear all top 32 bits.
A sometimes nice idiom is ori x,x,N ; xori x,x,N to clear the bits N
(or oris/xoris). But it's two insns no matter what (but no spare
register is needed).
Could be a candidate for a follow-up change if someone want to focus on
PPC64.
Signed-off-by: Christophe Leroy
+static inline unsigned long test_and_clear_bits(unsigned long mask, volatile
unsigned long *_p)
+{
+ unsigned long old, t;
+ unsigned long *p = (unsigned long *)_p;
+
+ if (IS_ENABLED(CONFIG_PPC32) &&
+ __builtin_constant_p(mask) && is_rlwinm_mask_valid(mask)) {
is_rlwinm_mask_valid(~mask)? So that test_and_clear_bits(0, ...) will
work with rlwinm, and test_and_clear_bits(0x, ...) will not make
gas scream bloody murder ("illegal bitmask"). Tha mask you pass to the
instruction is ~mask after all.
Ok, fixed in v5.
Looks great except that one nit. Thanks :-)
Reviewed-by: Segher Boessenkool
Thanks
Christophe
[PATCH v5 2/3] powerpc/atomics: Use immediate operand when possible
Today we get the following code generation for atomic operations:
c001bb2c: 39 20 00 01 li r9,1
c001bb30: 7d 40 18 28 lwarx r10,0,r3
c001bb34: 7d 09 50 50 subfr8,r9,r10
c001bb38: 7d 00 19 2d stwcx. r8,0,r3
c001c7a8: 39 40 00 01 li r10,1
c001c7ac: 7d 00 18 28 lwarx r8,0,r3
c001c7b0: 7c ea 42 14 add r7,r10,r8
c001c7b4: 7c e0 19 2d stwcx. r7,0,r3
By allowing GCC to choose between immediate or regular operation,
we get:
c001bb2c: 7d 20 18 28 lwarx r9,0,r3
c001bb30: 39 49 ff ff addir10,r9,-1
c001bb34: 7d 40 19 2d stwcx. r10,0,r3
--
c001c7a4: 7d 40 18 28 lwarx r10,0,r3
c001c7a8: 39 0a 00 01 addir8,r10,1
c001c7ac: 7d 00 19 2d stwcx. r8,0,r3
For "and", the dot form has to be used because "andi" doesn't exist.
For logical operations we use unsigned 16 bits immediate.
For arithmetic operations we use signed 16 bits immediate.
On pmac32_defconfig, it reduces the text by approx another 8 kbytes.
Signed-off-by: Christophe Leroy
Acked-by: Segher Boessenkool
---
v4: Rebased
v2: Use "addc/addic"
Signed-off-by: Christophe Leroy
---
arch/powerpc/include/asm/atomic.h | 56 +++
1 file changed, 28 insertions(+), 28 deletions(-)
diff --git a/arch/powerpc/include/asm/atomic.h
b/arch/powerpc/include/asm/atomic.h
index 6a53ef178bfd..ce0d5a013c58 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -37,62 +37,62 @@ static __inline__ void arch_atomic_set(atomic_t *v, int i)
__asm__ __volatile__("stw%U0%X0 %1,%0" : "=m"UPD_CONSTR(v->counter) :
"r"(i));
}
-#define ATOMIC_OP(op, asm_op) \
+#define ATOMIC_OP(op, asm_op, suffix, sign, ...) \
static __inline__ void arch_atomic_##op(int a, atomic_t *v)\
{ \
int t; \
\
__asm__ __volatile__( \
"1:lwarx %0,0,%3 # atomic_" #op "\n" \
- #asm_op " %0,%2,%0\n" \
+ #asm_op "%I2" suffix " %0,%0,%2\n" \
" stwcx. %0,0,%3 \n" \
" bne-1b\n" \
: "=" (t), "+m" (v->counter) \
- : "r" (a), "r" (>counter)\
- : "cc");\
+ : "r"#sign (a), "r" (>counter) \
+ : "cc", ##__VA_ARGS__); \
} \
-#define ATOMIC_OP_RETURN_RELAXED(op, asm_op) \
+#define ATOMIC_OP_RETURN_RELAXED(op, asm_op, suffix, sign, ...)
\
static inline int arch_atomic_##op##_return_relaxed(int a, atomic_t *v)
\
{ \
int t; \
\
__asm__ __volatile__( \
"1:lwarx %0,0,%3 # atomic_" #op "_return_relaxed\n" \
- #asm_op " %0,%2,%0\n" \
+ #asm_op "%I2" suffix " %0,%0,%2\n" \
" stwcx. %0,0,%3\n" \
" bne-1b\n" \
: "=" (t), "+m" (v->counter) \
- : "r" (a), "r" (>counter)\
- : "cc");\
+ : "r"#sign (a), "r" (>counter) \
+ : "cc", ##__VA_ARGS__); \
\
return t; \
}
-#define ATOMIC_FETCH_OP_RELAXED(op, asm_op)\
+#define ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign, ...) \
static inline int arch_atomic_fetch_##op##_relaxed(int a, atomic_t *v) \
{ \
int res, t; \
[PATCH v5 1/3] powerpc/bitops: Use immediate operand when possible
Today we get the following code generation for bitops like
set or clear bit:
c0009fe0: 39 40 08 00 li r10,2048
c0009fe4: 7c e0 40 28 lwarx r7,0,r8
c0009fe8: 7c e7 53 78 or r7,r7,r10
c0009fec: 7c e0 41 2d stwcx. r7,0,r8
c000d568: 39 00 18 00 li r8,6144
c000d56c: 7c c0 38 28 lwarx r6,0,r7
c000d570: 7c c6 40 78 andcr6,r6,r8
c000d574: 7c c0 39 2d stwcx. r6,0,r7
Most set bits are constant on lower 16 bits, so it can easily
be replaced by the "immediate" version of the operation. Allow
GCC to choose between the normal or immediate form.
For clear bits, on 32 bits 'rlwinm' can be used instead of 'andc' for
when all bits to be cleared are consecutive.
On 64 bits we don't have any equivalent single operation for clearing,
single bits or a few bits, we'd need two 'rldicl' so it is not
worth it, the li/andc sequence is doing the same.
With this patch we get:
c0009fe0: 7d 00 50 28 lwarx r8,0,r10
c0009fe4: 61 08 08 00 ori r8,r8,2048
c0009fe8: 7d 00 51 2d stwcx. r8,0,r10
c000d558: 7c e0 40 28 lwarx r7,0,r8
c000d55c: 54 e7 05 64 rlwinm r7,r7,0,21,18
c000d560: 7c e0 41 2d stwcx. r7,0,r8
On pmac32_defconfig, it reduces the text by approx 10 kbytes.
Signed-off-by: Christophe Leroy
Reviewed-by: Segher Boessenkool
---
v5: Fixed the argument of is_rlwinm_mask_valid() in test_and_clear_bits()
v4: Rebased
v3:
- Using the mask validation proposed by Segher
v2:
- Use "n" instead of "i" as constraint for the rlwinm mask
- Improve mask verification to handle more than single bit masks
Signed-off-by: Christophe Leroy
---
arch/powerpc/include/asm/bitops.h | 89 ---
1 file changed, 81 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/include/asm/bitops.h
b/arch/powerpc/include/asm/bitops.h
index 11847b6a244e..a05d8c62cbea 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -71,19 +71,61 @@ static inline void fn(unsigned long mask, \
__asm__ __volatile__ ( \
prefix \
"1:" PPC_LLARX "%0,0,%3,0\n" \
- stringify_in_c(op) "%0,%0,%2\n" \
+ #op "%I2 %0,%0,%2\n"\
PPC_STLCX "%0,0,%3\n" \
"bne- 1b\n" \
: "=" (old), "+m" (*p)\
- : "r" (mask), "r" (p) \
+ : "rK" (mask), "r" (p) \
: "cc", "memory"); \
}
DEFINE_BITOP(set_bits, or, "")
-DEFINE_BITOP(clear_bits, andc, "")
-DEFINE_BITOP(clear_bits_unlock, andc, PPC_RELEASE_BARRIER)
DEFINE_BITOP(change_bits, xor, "")
+static __always_inline bool is_rlwinm_mask_valid(unsigned long x)
+{
+ if (!x)
+ return false;
+ if (x & 1)
+ x = ~x; // make the mask non-wrapping
+ x += x & -x;// adding the low set bit results in at most one bit set
+
+ return !(x & (x - 1));
+}
+
+#define DEFINE_CLROP(fn, prefix) \
+static inline void fn(unsigned long mask, volatile unsigned long *_p) \
+{ \
+ unsigned long old; \
+ unsigned long *p = (unsigned long *)_p; \
+ \
+ if (IS_ENABLED(CONFIG_PPC32) && \
+ __builtin_constant_p(mask) && is_rlwinm_mask_valid(~mask)) {\
+ asm volatile ( \
+ prefix \
+ "1:""lwarx %0,0,%3\n" \
+ "rlwinm %0,%0,0,%2\n" \
+ "stwcx. %0,0,%3\n" \
+ "bne- 1b\n" \
+ : "=" (old), "+m" (*p)\
+ : "n" (~mask), "r" (p) \
+ : "cc", "memory"); \
+ } else {\
+ asm volatile ( \
+ prefix \
+ "1:"PPC_LLARX "%0,0,%3,0\n" \
+ "andc %0,%0,%2\n" \
+ PPC_STLCX "%0,0,%3\n" \
+ "bne- 1b\n"
[PATCH v5 3/3] powerpc/atomics: Remove atomic_inc()/atomic_dec() and friends
Now that atomic_add() and atomic_sub() handle immediate operands,
atomic_inc() and atomic_dec() have no added value compared to the
generic fallback which calls atomic_add(1) and atomic_sub(1).
Also remove atomic_inc_not_zero() which fallsback to
atomic_add_unless() which itself fallsback to
atomic_fetch_add_unless() which now handles immediate operands.
Signed-off-by: Christophe Leroy
---
v4: rebased
v2: New
Signed-off-by: Christophe Leroy
---
arch/powerpc/include/asm/atomic.h | 95 ---
1 file changed, 95 deletions(-)
diff --git a/arch/powerpc/include/asm/atomic.h
b/arch/powerpc/include/asm/atomic.h
index ce0d5a013c58..395d1feb5790 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -118,71 +118,6 @@ ATOMIC_OPS(xor, xor, "", K)
#undef ATOMIC_OP_RETURN_RELAXED
#undef ATOMIC_OP
-static __inline__ void arch_atomic_inc(atomic_t *v)
-{
- int t;
-
- __asm__ __volatile__(
-"1:lwarx %0,0,%2 # atomic_inc\n\
- addic %0,%0,1\n"
-" stwcx. %0,0,%2 \n\
- bne-1b"
- : "=" (t), "+m" (v->counter)
- : "r" (>counter)
- : "cc", "xer");
-}
-#define arch_atomic_inc arch_atomic_inc
-
-static __inline__ int arch_atomic_inc_return_relaxed(atomic_t *v)
-{
- int t;
-
- __asm__ __volatile__(
-"1:lwarx %0,0,%2 # atomic_inc_return_relaxed\n"
-" addic %0,%0,1\n"
-" stwcx. %0,0,%2\n"
-" bne-1b"
- : "=" (t), "+m" (v->counter)
- : "r" (>counter)
- : "cc", "xer");
-
- return t;
-}
-
-static __inline__ void arch_atomic_dec(atomic_t *v)
-{
- int t;
-
- __asm__ __volatile__(
-"1:lwarx %0,0,%2 # atomic_dec\n\
- addic %0,%0,-1\n"
-" stwcx. %0,0,%2\n\
- bne-1b"
- : "=" (t), "+m" (v->counter)
- : "r" (>counter)
- : "cc", "xer");
-}
-#define arch_atomic_dec arch_atomic_dec
-
-static __inline__ int arch_atomic_dec_return_relaxed(atomic_t *v)
-{
- int t;
-
- __asm__ __volatile__(
-"1:lwarx %0,0,%2 # atomic_dec_return_relaxed\n"
-" addic %0,%0,-1\n"
-" stwcx. %0,0,%2\n"
-" bne-1b"
- : "=" (t), "+m" (v->counter)
- : "r" (>counter)
- : "cc", "xer");
-
- return t;
-}
-
-#define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed
-#define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed
-
#define arch_atomic_cmpxchg(v, o, n) \
(arch_cmpxchg(&((v)->counter), (o), (n)))
#define arch_atomic_cmpxchg_relaxed(v, o, n) \
@@ -255,36 +190,6 @@ static __inline__ int
arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
}
#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless
-/**
- * atomic_inc_not_zero - increment unless the number is zero
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1, so long as @v is non-zero.
- * Returns non-zero if @v was non-zero, and zero otherwise.
- */
-static __inline__ int arch_atomic_inc_not_zero(atomic_t *v)
-{
- int t1, t2;
-
- __asm__ __volatile__ (
- PPC_ATOMIC_ENTRY_BARRIER
-"1:lwarx %0,0,%2 # atomic_inc_not_zero\n\
- cmpwi 0,%0,0\n\
- beq-2f\n\
- addic %1,%0,1\n"
-" stwcx. %1,0,%2\n\
- bne-1b\n"
- PPC_ATOMIC_EXIT_BARRIER
- "\n\
-2:"
- : "=" (t1), "=" (t2)
- : "r" (>counter)
- : "cc", "xer", "memory");
-
- return t1;
-}
-#define arch_atomic_inc_not_zero(v) arch_atomic_inc_not_zero((v))
-
/*
* Atomically test *v and decrement if it is greater than 0.
* The function returns the old value of *v minus 1, even if
--
2.31.1
Re: [PATCH v3 8/8] bpf ppc32: Access only if addr is kernel address
Le 21/09/2021 à 15:29, Hari Bathini a écrit :
With KUAP enabled, any kernel code which wants to access userspace
needs to be surrounded by disable-enable KUAP. But that is not
happening for BPF_PROBE_MEM load instruction. Though PPC32 does not
support read protection, considering the fact that PTR_TO_BTF_ID
(which uses BPF_PROBE_MEM mode) could either be a valid kernel pointer
or NULL but should never be a pointer to userspace address, execute
BPF_PROBE_MEM load only if addr is kernel address, otherwise set
dst_reg=0 and move on.
This will catch NULL, valid or invalid userspace pointers. Only bad
kernel pointer will be handled by BPF exception table.
[Alexei suggested for x86]
Suggested-by: Alexei Starovoitov
Signed-off-by: Hari Bathini
---
Changes in v3:
* Updated jump for PPC_BCC to always be the same while emitting
a NOP instruction when needed.
arch/powerpc/net/bpf_jit_comp32.c | 35 +++
1 file changed, 35 insertions(+)
diff --git a/arch/powerpc/net/bpf_jit_comp32.c
b/arch/powerpc/net/bpf_jit_comp32.c
index 1239643f532c..59849e1230d2 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -825,6 +825,41 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src +
off) */
fallthrough;
case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+ /*
+* As PTR_TO_BTF_ID that uses BPF_PROBE_MEM mode could
either be a valid
+* kernel pointer or NULL but not a userspace address,
execute BPF_PROBE_MEM
+* load only if addr is kernel address (see
is_kernel_addr()), otherwise
+* set dst_reg=0 and move on.
+*/
+ if (BPF_MODE(code) == BPF_PROBE_MEM) {
+ EMIT(PPC_RAW_ADDI(b2p[TMP_REG], src_reg, off));
+ PPC_LI32(_R0, TASK_SIZE);
+ EMIT(PPC_RAW_CMPLW(b2p[TMP_REG], _R0));
You may drop the ADDI and do:
PPC_LI32(_R0, TASK_SIZE - off);
EMIT(PPC_RAW_CMPLW(src_reg, _R0));
It will likely be the same number of instructions because now the
PPC_LI32 will generate two instruction, but it avoids the use of TMP_REG.
+ PPC_BCC(COND_GT, (ctx->idx + 5) * 4);
+ EMIT(PPC_RAW_LI(dst_reg, 0));
+ /*
+* For BPF_DW case, "li reg_h,0" would be
needed when
+* !fp->aux->verifier_zext. Emit NOP otherwise.
+*
+* Note that "li reg_h,0" is emitted for
BPF_B/H/W case,
+* if necessary. So, jump there insted of
emitting an
+* additional "li reg_h,0" instruction.
+*/
+ if (size == BPF_DW && !fp->aux->verifier_zext)
+ EMIT(PPC_RAW_LI(dst_reg_h, 0));
+ else
+ EMIT(PPC_RAW_NOP());
+ /*
+* Need to jump two instructions instead of one
for BPF_DW case
+* as there are two load instructions for dst_reg_h
& dst_reg
+* respectively.
+*/
+ if (size == BPF_DW)
+ PPC_JMP((ctx->idx + 3) * 4);
+ else
+ PPC_JMP((ctx->idx + 2) * 4);
+ }
+
switch (size) {
case BPF_B:
EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
Re: [PATCH v3 7/8] bpf ppc32: Add BPF_PROBE_MEM support for JIT
Le 21/09/2021 à 15:29, Hari Bathini a écrit :
BPF load instruction with BPF_PROBE_MEM mode can cause a fault
inside kernel. Append exception table for such instructions
within BPF program.
Unlike other archs which uses extable 'fixup' field to pass dest_reg
and nip, BPF exception table on PowerPC follows the generic PowerPC
exception table design, where it populates both fixup and extable
sections within BPF program. fixup section contains 3 instructions,
first 2 instructions clear dest_reg (lower & higher 32-bit registers)
and last instruction jumps to next instruction in the BPF code.
extable 'insn' field contains relative offset of the instruction and
'fixup' field contains relative offset of the fixup entry. Example
layout of BPF program with extable present:
+--+
| |
| |
0x4020 -->| lwz r28,4(r4) |
| |
| |
0x40ac -->| lwz r3,0(r24) |
| lwz r4,4(r24) |
| |
| |
|--|
0x4278 -->| li r28,0| \
| li r27,0| | fixup entry
| b 0x4024 | /
0x4284 -->| li r4,0 |
| li r3,0 |
| b 0x40b4 |
|--|
0x4290 -->| insn=0xfd90 | \ extable entry
| fixup=0xffe4 | /
0x4298 -->| insn=0xfe14 |
| fixup=0xffe8 |
+--+
(Addresses shown here are chosen random, not real)
Signed-off-by: Hari Bathini
---
Changes in v3:
* Changed how BPF_FIXUP_LEN is defined based on Chris' suggestion.
arch/powerpc/net/bpf_jit.h| 4
arch/powerpc/net/bpf_jit_comp.c | 2 ++
arch/powerpc/net/bpf_jit_comp32.c | 34 +++
3 files changed, 40 insertions(+)
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 561689a2abdf..800734056200 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -144,7 +144,11 @@ struct codegen_context {
unsigned int exentry_idx;
};
+#ifdef CONFIG_PPC32
+#define BPF_FIXUP_LEN 3 /* Three instructions => 12 bytes */
+#else
#define BPF_FIXUP_LEN 2 /* Two instructions => 8 bytes */
+#endif
static inline void bpf_flush_icache(void *start, void *end)
{
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index f02457c6b54f..1a0041997050 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -297,6 +297,8 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image,
int pass, struct code
(ctx->exentry_idx * BPF_FIXUP_LEN * 4);
fixup[0] = PPC_RAW_LI(dst_reg, 0);
+ if (IS_ENABLED(CONFIG_PPC32))
+ fixup[1] = PPC_RAW_LI(dst_reg - 1, 0); /* clear higher 32-bit
register too */
fixup[BPF_FIXUP_LEN - 1] =
PPC_RAW_BRANCH((long)(pc + jmp_off) -
(long)[BPF_FIXUP_LEN - 1]);
diff --git a/arch/powerpc/net/bpf_jit_comp32.c
b/arch/powerpc/net/bpf_jit_comp32.c
index 820c7848434e..1239643f532c 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -812,11 +812,19 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
*/
case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src +
off) */
fallthrough;
+ case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+ fallthrough;
Same comment about the fallthroughs
case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src +
off) */
fallthrough;
+ case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src +
off) */
fallthrough;
+ case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src +
off) */
+ fallthrough;
+ case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
switch (size) {
case BPF_B:
EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
@@ -841,6 +849,32 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
if (size != BPF_DW && !fp->aux->verifier_zext)
EMIT(PPC_RAW_LI(dst_reg_h, 0));
+
+ if (BPF_MODE(code) == BPF_PROBE_MEM) {
+ int insn_idx = ctx->idx - 1;
+ int jmp_off = 4;
+
+ /*
+* In case of BPF_DW, two lwz instructions are
Re: [PATCH v3 6/8] bpf ppc64: Access only if addr is kernel address
Le 21/09/2021 à 15:29, Hari Bathini a écrit :
From: Ravi Bangoria
On PPC64 with KUAP enabled, any kernel code which wants to
access userspace needs to be surrounded by disable-enable KUAP.
But that is not happening for BPF_PROBE_MEM load instruction.
So, when BPF program tries to access invalid userspace address,
page-fault handler considers it as bad KUAP fault:
Kernel attempted to read user page (d000) - exploit attempt? (uid: 0)
Considering the fact that PTR_TO_BTF_ID (which uses BPF_PROBE_MEM
mode) could either be a valid kernel pointer or NULL but should
never be a pointer to userspace address, execute BPF_PROBE_MEM load
only if addr is kernel address, otherwise set dst_reg=0 and move on.
This will catch NULL, valid or invalid userspace pointers. Only bad
kernel pointer will be handled by BPF exception table.
[Alexei suggested for x86]
Suggested-by: Alexei Starovoitov
Signed-off-by: Ravi Bangoria
Signed-off-by: Hari Bathini
---
Changes in v3:
* Used is_kernel_addr() logic instead of using TASK_SIZE_MAX check
all the time.
* Addressed other comments from Christophe.
arch/powerpc/net/bpf_jit_comp64.c | 29 +
1 file changed, 29 insertions(+)
diff --git a/arch/powerpc/net/bpf_jit_comp64.c
b/arch/powerpc/net/bpf_jit_comp64.c
index 506934c13ef7..06e1206a4266 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -734,6 +734,35 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
case BPF_LDX | BPF_MEM | BPF_DW:
fallthrough;
case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+ /*
+* As PTR_TO_BTF_ID that uses BPF_PROBE_MEM mode could
either be a valid
+* kernel pointer or NULL but not a userspace address,
execute BPF_PROBE_MEM
+* load only if addr is kernel address (see
is_kernel_addr()), otherwise
+* set dst_reg=0 and move on.
+*/
+ if (BPF_MODE(code) == BPF_PROBE_MEM) {
+ EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg,
off));
+#ifdef CONFIG_PPC_BOOK3E_64
It is better to use IS_ENABLED() whenever possible,
if (IS_ENABLED((CONFIG_PPC_BOOK3E_64))
PPC_LI64(b2p[TMP_REG_2], 0x8000ul);
else
PPC_LI64(b2p[TMP_REG_2], PAGE_OFFSET);
+ PPC_LI64(b2p[TMP_REG_2], 0x8000ul);
+#elif defined(CONFIG_PPC_BOOK3S_64)
+ PPC_LI64(b2p[TMP_REG_2], PAGE_OFFSET);
+#else
+ PPC_LI64(b2p[TMP_REG_2], TASK_SIZE);
+#endif
PPC64 is either CONFIG_PPC_BOOK3S_64 or CONFIG_PPC_BOOK3E_64. The else
is PPC32.
+ EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1],
b2p[TMP_REG_2]));
+ PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+ EMIT(PPC_RAW_LI(dst_reg, 0));
+ /*
+* Check if 'off' is word aligned because
PPC_BPF_LL()
+* (BPF_DW case) generates two instructions if
'off' is not
+* word-aligned and one instruction otherwise.
+*/
+ if (BPF_SIZE(code) == BPF_DW && (off & 3))
+ PPC_JMP((ctx->idx + 3) * 4);
+ else
+ PPC_JMP((ctx->idx + 2) * 4);
+ }
+
switch (size) {
case BPF_B:
EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
Re: [PATCH v3 5/8] bpf ppc64: Add BPF_PROBE_MEM support for JIT
Le 21/09/2021 à 15:29, Hari Bathini a écrit :
From: Ravi Bangoria
BPF load instruction with BPF_PROBE_MEM mode can cause a fault
inside kernel. Append exception table for such instructions
within BPF program.
Unlike other archs which uses extable 'fixup' field to pass dest_reg
and nip, BPF exception table on PowerPC follows the generic PowerPC
exception table design, where it populates both fixup and extable
sections within BPF program. fixup section contains two instructions,
first instruction clears dest_reg and 2nd jumps to next instruction
in the BPF code. extable 'insn' field contains relative offset of
the instruction and 'fixup' field contains relative offset of the
fixup entry. Example layout of BPF program with extable present:
+--+
| |
| |
0x4020 -->| ld r27,4(r3) |
| |
| |
0x40ac -->| lwz r3,0(r4)|
| |
| |
|--|
0x4280 -->| li r27,0| \ fixup entry
| b 0x4024 | /
0x4288 -->| li r3,0 |
| b 0x40b0 |
|--|
0x4290 -->| insn=0xfd90 | \ extable entry
| fixup=0xffec | /
0x4298 -->| insn=0xfe14 |
| fixup=0xffec |
+--+
(Addresses shown here are chosen random, not real)
Signed-off-by: Ravi Bangoria
Signed-off-by: Hari Bathini
---
Changes in v3:
* Made all changes for bpf_add_extable_entry() in this patch instead
of updating it again in patch #7.
* Fixed a coding style issue.
arch/powerpc/net/bpf_jit.h| 8 +++-
arch/powerpc/net/bpf_jit_comp.c | 70 ---
arch/powerpc/net/bpf_jit_comp32.c | 2 +-
arch/powerpc/net/bpf_jit_comp64.c | 17 +++-
4 files changed, 88 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 0c8f885b8f48..561689a2abdf 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -141,8 +141,11 @@ struct codegen_context {
unsigned int idx;
unsigned int stack_size;
int b2p[ARRAY_SIZE(b2p)];
+ unsigned int exentry_idx;
};
+#define BPF_FIXUP_LEN 2 /* Two instructions => 8 bytes */
+
static inline void bpf_flush_icache(void *start, void *end)
{
smp_wmb(); /* smp write barrier */
@@ -166,11 +169,14 @@ static inline void bpf_clear_seen_register(struct
codegen_context *ctx, int i)
void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func);
int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct
codegen_context *ctx,
- u32 *addrs);
+ u32 *addrs, int pass);
void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx);
void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx);
void bpf_jit_realloc_regs(struct codegen_context *ctx);
+int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct codegen_context *ctx,
+ int insn_idx, int jmp_off, int dst_reg);
+
#endif
#endif
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index c5c9e8ad1de7..f02457c6b54f 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -101,6 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
struct bpf_prog *tmp_fp;
bool bpf_blinded = false;
bool extra_pass = false;
+ u32 extable_len;
+ u32 fixup_len;
if (!fp->jit_requested)
return org_fp;
@@ -131,7 +133,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
image = jit_data->image;
bpf_hdr = jit_data->header;
proglen = jit_data->proglen;
- alloclen = proglen + FUNCTION_DESCR_SIZE;
extra_pass = true;
goto skip_init_ctx;
}
@@ -149,7 +150,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
/* Scouting faux-generate pass 0 */
- if (bpf_jit_build_body(fp, 0, , addrs)) {
+ if (bpf_jit_build_body(fp, 0, , addrs, 0)) {
/* We hit something illegal or unsupported. */
fp = org_fp;
goto out_addrs;
@@ -162,7 +163,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
*/
if (cgctx.seen & SEEN_TAILCALL) {
cgctx.idx = 0;
- if (bpf_jit_build_body(fp, 0, , addrs)) {
+ if (bpf_jit_build_body(fp, 0, , addrs, 0)) {
fp = org_fp;
goto out_addrs;
}
@@ -177,8 +178,11 @@ struct bpf_prog
Re: [PATCH v3 3/8] bpf powerpc: refactor JIT compiler code
Le 21/09/2021 à 15:29, Hari Bathini a écrit :
Refactor powerpc LDX JITing code to simplify adding BPF_PROBE_MEM
support.
Signed-off-by: Hari Bathini
---
Changes in v3:
* Dropped ST(X) JITing coderefactoring and ensured the changes are
minimal and relevant to BPF_PROBE_MEM support.
* Added a default for size switch case to ensure compiler would
not complain.
arch/powerpc/net/bpf_jit_comp32.c | 42 ---
arch/powerpc/net/bpf_jit_comp64.c | 40 +++--
2 files changed, 55 insertions(+), 27 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit_comp32.c
b/arch/powerpc/net/bpf_jit_comp32.c
index b60b59426a24..6e4956cd52e7 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -282,6 +282,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
u32 src_reg = bpf_to_ppc(ctx, insn[i].src_reg);
u32 src_reg_h = src_reg - 1;
u32 tmp_reg = bpf_to_ppc(ctx, TMP_REG);
+ u32 size = BPF_SIZE(code);
s16 off = insn[i].off;
s32 imm = insn[i].imm;
bool func_addr_fixed;
@@ -810,23 +811,36 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
* BPF_LDX
*/
case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
- if (!fp->aux->verifier_zext)
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
- break;
+ fallthrough;
I know I commented to add 'fallthrough' ... In fact I missinterpreted
what I saw.
fallthrough is required only if you have code inbetween two 'case'.
When you have two following 'case' without code, you don't need
'fallthrough' I think.
case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
- if (!fp->aux->verifier_zext)
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
- break;
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
- if (!fp->aux->verifier_zext)
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
- break;
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
- EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
+ switch (size) {
+ case BPF_B:
+ EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+ break;
+ case BPF_H:
+ EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
+ break;
+ case BPF_W:
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+ break;
+ case BPF_DW:
+ EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
+ break;
+ /*
+* With size not being an enum and BPF_B/H/W/DW being
macros, ensure no
+* compiler warning/error by adding a default case that
never reaches.
+*/
+ default:
+ break;
+ }
+
+ if (size != BPF_DW && !fp->aux->verifier_zext)
+ EMIT(PPC_RAW_LI(dst_reg_h, 0));
break;
/*
diff --git a/arch/powerpc/net/bpf_jit_comp64.c
b/arch/powerpc/net/bpf_jit_comp64.c
index 2a87da50d9a4..991eb43d4cd2 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -285,6 +285,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
u32 code = insn[i].code;
u32 dst_reg = b2p[insn[i].dst_reg];
u32 src_reg = b2p[insn[i].src_reg];
+ u32 size = BPF_SIZE(code);
s16 off = insn[i].off;
s32 imm = insn[i].imm;
bool func_addr_fixed;
@@ -716,25 +717,38 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
*/
/* dst = *(u8 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_B:
- EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
-
Re: [PATCH v3 3/8] bpf powerpc: refactor JIT compiler code
Le 21/09/2021 à 15:29, Hari Bathini a écrit :
Refactor powerpc LDX JITing code to simplify adding BPF_PROBE_MEM
support.
Signed-off-by: Hari Bathini
---
Changes in v3:
* Dropped ST(X) JITing coderefactoring and ensured the changes are
minimal and relevant to BPF_PROBE_MEM support.
* Added a default for size switch case to ensure compiler would
not complain.
arch/powerpc/net/bpf_jit_comp32.c | 42 ---
arch/powerpc/net/bpf_jit_comp64.c | 40 +++--
2 files changed, 55 insertions(+), 27 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit_comp32.c
b/arch/powerpc/net/bpf_jit_comp32.c
index b60b59426a24..6e4956cd52e7 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -282,6 +282,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
u32 src_reg = bpf_to_ppc(ctx, insn[i].src_reg);
u32 src_reg_h = src_reg - 1;
u32 tmp_reg = bpf_to_ppc(ctx, TMP_REG);
+ u32 size = BPF_SIZE(code);
s16 off = insn[i].off;
s32 imm = insn[i].imm;
bool func_addr_fixed;
@@ -810,23 +811,36 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
* BPF_LDX
*/
case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
- if (!fp->aux->verifier_zext)
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
- break;
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
- if (!fp->aux->verifier_zext)
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
- break;
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
- if (!fp->aux->verifier_zext)
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
- break;
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
- EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
+ switch (size) {
+ case BPF_B:
+ EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+ break;
+ case BPF_H:
+ EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
+ break;
+ case BPF_W:
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+ break;
+ case BPF_DW:
+ EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
+ break;
+ /*
+* With size not being an enum and BPF_B/H/W/DW being
macros, ensure no
+* compiler warning/error by adding a default case that
never reaches.
+*/
Thinking about it once more, in fact this is already bounded by the
upper switch/case, so there is no possibility to end up here with
something else than the 4 cases and that's probably the reason why GCC
says nothing about it, so I now think that a default is unnecessary and
should not be added. Sorry for that.
+ default:
+ break;
+ }
+
+ if (size != BPF_DW && !fp->aux->verifier_zext)
+ EMIT(PPC_RAW_LI(dst_reg_h, 0));
break;
/*
diff --git a/arch/powerpc/net/bpf_jit_comp64.c
b/arch/powerpc/net/bpf_jit_comp64.c
index 2a87da50d9a4..991eb43d4cd2 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -285,6 +285,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
u32 code = insn[i].code;
u32 dst_reg = b2p[insn[i].dst_reg];
u32 src_reg = b2p[insn[i].src_reg];
+ u32 size = BPF_SIZE(code);
s16 off = insn[i].off;
s32 imm = insn[i].imm;
bool func_addr_fixed;
@@ -716,25 +717,38 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
*/
/* dst = *(u8 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_B:
-
[PATCH v3 8/8] bpf ppc32: Access only if addr is kernel address
With KUAP enabled, any kernel code which wants to access userspace
needs to be surrounded by disable-enable KUAP. But that is not
happening for BPF_PROBE_MEM load instruction. Though PPC32 does not
support read protection, considering the fact that PTR_TO_BTF_ID
(which uses BPF_PROBE_MEM mode) could either be a valid kernel pointer
or NULL but should never be a pointer to userspace address, execute
BPF_PROBE_MEM load only if addr is kernel address, otherwise set
dst_reg=0 and move on.
This will catch NULL, valid or invalid userspace pointers. Only bad
kernel pointer will be handled by BPF exception table.
[Alexei suggested for x86]
Suggested-by: Alexei Starovoitov
Signed-off-by: Hari Bathini
---
Changes in v3:
* Updated jump for PPC_BCC to always be the same while emitting
a NOP instruction when needed.
arch/powerpc/net/bpf_jit_comp32.c | 35 +++
1 file changed, 35 insertions(+)
diff --git a/arch/powerpc/net/bpf_jit_comp32.c
b/arch/powerpc/net/bpf_jit_comp32.c
index 1239643f532c..59849e1230d2 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -825,6 +825,41 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src +
off) */
fallthrough;
case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+ /*
+* As PTR_TO_BTF_ID that uses BPF_PROBE_MEM mode could
either be a valid
+* kernel pointer or NULL but not a userspace address,
execute BPF_PROBE_MEM
+* load only if addr is kernel address (see
is_kernel_addr()), otherwise
+* set dst_reg=0 and move on.
+*/
+ if (BPF_MODE(code) == BPF_PROBE_MEM) {
+ EMIT(PPC_RAW_ADDI(b2p[TMP_REG], src_reg, off));
+ PPC_LI32(_R0, TASK_SIZE);
+ EMIT(PPC_RAW_CMPLW(b2p[TMP_REG], _R0));
+ PPC_BCC(COND_GT, (ctx->idx + 5) * 4);
+ EMIT(PPC_RAW_LI(dst_reg, 0));
+ /*
+* For BPF_DW case, "li reg_h,0" would be
needed when
+* !fp->aux->verifier_zext. Emit NOP otherwise.
+*
+* Note that "li reg_h,0" is emitted for
BPF_B/H/W case,
+* if necessary. So, jump there insted of
emitting an
+* additional "li reg_h,0" instruction.
+*/
+ if (size == BPF_DW && !fp->aux->verifier_zext)
+ EMIT(PPC_RAW_LI(dst_reg_h, 0));
+ else
+ EMIT(PPC_RAW_NOP());
+ /*
+* Need to jump two instructions instead of one
for BPF_DW case
+* as there are two load instructions for
dst_reg_h & dst_reg
+* respectively.
+*/
+ if (size == BPF_DW)
+ PPC_JMP((ctx->idx + 3) * 4);
+ else
+ PPC_JMP((ctx->idx + 2) * 4);
+ }
+
switch (size) {
case BPF_B:
EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
--
2.31.1
[PATCH v3 7/8] bpf ppc32: Add BPF_PROBE_MEM support for JIT
BPF load instruction with BPF_PROBE_MEM mode can cause a fault
inside kernel. Append exception table for such instructions
within BPF program.
Unlike other archs which uses extable 'fixup' field to pass dest_reg
and nip, BPF exception table on PowerPC follows the generic PowerPC
exception table design, where it populates both fixup and extable
sections within BPF program. fixup section contains 3 instructions,
first 2 instructions clear dest_reg (lower & higher 32-bit registers)
and last instruction jumps to next instruction in the BPF code.
extable 'insn' field contains relative offset of the instruction and
'fixup' field contains relative offset of the fixup entry. Example
layout of BPF program with extable present:
+--+
| |
| |
0x4020 -->| lwz r28,4(r4) |
| |
| |
0x40ac -->| lwz r3,0(r24) |
| lwz r4,4(r24) |
| |
| |
|--|
0x4278 -->| li r28,0| \
| li r27,0| | fixup entry
| b 0x4024 | /
0x4284 -->| li r4,0 |
| li r3,0 |
| b 0x40b4 |
|--|
0x4290 -->| insn=0xfd90 | \ extable entry
| fixup=0xffe4 | /
0x4298 -->| insn=0xfe14 |
| fixup=0xffe8 |
+--+
(Addresses shown here are chosen random, not real)
Signed-off-by: Hari Bathini
---
Changes in v3:
* Changed how BPF_FIXUP_LEN is defined based on Chris' suggestion.
arch/powerpc/net/bpf_jit.h| 4
arch/powerpc/net/bpf_jit_comp.c | 2 ++
arch/powerpc/net/bpf_jit_comp32.c | 34 +++
3 files changed, 40 insertions(+)
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 561689a2abdf..800734056200 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -144,7 +144,11 @@ struct codegen_context {
unsigned int exentry_idx;
};
+#ifdef CONFIG_PPC32
+#define BPF_FIXUP_LEN 3 /* Three instructions => 12 bytes */
+#else
#define BPF_FIXUP_LEN 2 /* Two instructions => 8 bytes */
+#endif
static inline void bpf_flush_icache(void *start, void *end)
{
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index f02457c6b54f..1a0041997050 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -297,6 +297,8 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image,
int pass, struct code
(ctx->exentry_idx * BPF_FIXUP_LEN * 4);
fixup[0] = PPC_RAW_LI(dst_reg, 0);
+ if (IS_ENABLED(CONFIG_PPC32))
+ fixup[1] = PPC_RAW_LI(dst_reg - 1, 0); /* clear higher 32-bit
register too */
fixup[BPF_FIXUP_LEN - 1] =
PPC_RAW_BRANCH((long)(pc + jmp_off) -
(long)[BPF_FIXUP_LEN - 1]);
diff --git a/arch/powerpc/net/bpf_jit_comp32.c
b/arch/powerpc/net/bpf_jit_comp32.c
index 820c7848434e..1239643f532c 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -812,11 +812,19 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
*/
case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src +
off) */
fallthrough;
+ case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src +
off) */
fallthrough;
+ case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src +
off) */
fallthrough;
+ case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src +
off) */
+ fallthrough;
+ case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
switch (size) {
case BPF_B:
EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
@@ -841,6 +849,32 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
if (size != BPF_DW && !fp->aux->verifier_zext)
EMIT(PPC_RAW_LI(dst_reg_h, 0));
+
+ if (BPF_MODE(code) == BPF_PROBE_MEM) {
+ int insn_idx = ctx->idx - 1;
+ int jmp_off = 4;
+
+ /*
+* In case of BPF_DW, two lwz instructions are
emitted, one
+* for higher 32-bit and another for lower
32-bit. So, set
+
[PATCH v3 6/8] bpf ppc64: Access only if addr is kernel address
From: Ravi Bangoria
On PPC64 with KUAP enabled, any kernel code which wants to
access userspace needs to be surrounded by disable-enable KUAP.
But that is not happening for BPF_PROBE_MEM load instruction.
So, when BPF program tries to access invalid userspace address,
page-fault handler considers it as bad KUAP fault:
Kernel attempted to read user page (d000) - exploit attempt? (uid: 0)
Considering the fact that PTR_TO_BTF_ID (which uses BPF_PROBE_MEM
mode) could either be a valid kernel pointer or NULL but should
never be a pointer to userspace address, execute BPF_PROBE_MEM load
only if addr is kernel address, otherwise set dst_reg=0 and move on.
This will catch NULL, valid or invalid userspace pointers. Only bad
kernel pointer will be handled by BPF exception table.
[Alexei suggested for x86]
Suggested-by: Alexei Starovoitov
Signed-off-by: Ravi Bangoria
Signed-off-by: Hari Bathini
---
Changes in v3:
* Used is_kernel_addr() logic instead of using TASK_SIZE_MAX check
all the time.
* Addressed other comments from Christophe.
arch/powerpc/net/bpf_jit_comp64.c | 29 +
1 file changed, 29 insertions(+)
diff --git a/arch/powerpc/net/bpf_jit_comp64.c
b/arch/powerpc/net/bpf_jit_comp64.c
index 506934c13ef7..06e1206a4266 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -734,6 +734,35 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
case BPF_LDX | BPF_MEM | BPF_DW:
fallthrough;
case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+ /*
+* As PTR_TO_BTF_ID that uses BPF_PROBE_MEM mode could
either be a valid
+* kernel pointer or NULL but not a userspace address,
execute BPF_PROBE_MEM
+* load only if addr is kernel address (see
is_kernel_addr()), otherwise
+* set dst_reg=0 and move on.
+*/
+ if (BPF_MODE(code) == BPF_PROBE_MEM) {
+ EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg,
off));
+#ifdef CONFIG_PPC_BOOK3E_64
+ PPC_LI64(b2p[TMP_REG_2], 0x8000ul);
+#elif defined(CONFIG_PPC_BOOK3S_64)
+ PPC_LI64(b2p[TMP_REG_2], PAGE_OFFSET);
+#else
+ PPC_LI64(b2p[TMP_REG_2], TASK_SIZE);
+#endif
+ EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1],
b2p[TMP_REG_2]));
+ PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+ EMIT(PPC_RAW_LI(dst_reg, 0));
+ /*
+* Check if 'off' is word aligned because
PPC_BPF_LL()
+* (BPF_DW case) generates two instructions if
'off' is not
+* word-aligned and one instruction otherwise.
+*/
+ if (BPF_SIZE(code) == BPF_DW && (off & 3))
+ PPC_JMP((ctx->idx + 3) * 4);
+ else
+ PPC_JMP((ctx->idx + 2) * 4);
+ }
+
switch (size) {
case BPF_B:
EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
--
2.31.1
[PATCH v3 5/8] bpf ppc64: Add BPF_PROBE_MEM support for JIT
From: Ravi Bangoria
BPF load instruction with BPF_PROBE_MEM mode can cause a fault
inside kernel. Append exception table for such instructions
within BPF program.
Unlike other archs which uses extable 'fixup' field to pass dest_reg
and nip, BPF exception table on PowerPC follows the generic PowerPC
exception table design, where it populates both fixup and extable
sections within BPF program. fixup section contains two instructions,
first instruction clears dest_reg and 2nd jumps to next instruction
in the BPF code. extable 'insn' field contains relative offset of
the instruction and 'fixup' field contains relative offset of the
fixup entry. Example layout of BPF program with extable present:
+--+
| |
| |
0x4020 -->| ld r27,4(r3) |
| |
| |
0x40ac -->| lwz r3,0(r4)|
| |
| |
|--|
0x4280 -->| li r27,0| \ fixup entry
| b 0x4024 | /
0x4288 -->| li r3,0 |
| b 0x40b0 |
|--|
0x4290 -->| insn=0xfd90 | \ extable entry
| fixup=0xffec | /
0x4298 -->| insn=0xfe14 |
| fixup=0xffec |
+--+
(Addresses shown here are chosen random, not real)
Signed-off-by: Ravi Bangoria
Signed-off-by: Hari Bathini
---
Changes in v3:
* Made all changes for bpf_add_extable_entry() in this patch instead
of updating it again in patch #7.
* Fixed a coding style issue.
arch/powerpc/net/bpf_jit.h| 8 +++-
arch/powerpc/net/bpf_jit_comp.c | 70 ---
arch/powerpc/net/bpf_jit_comp32.c | 2 +-
arch/powerpc/net/bpf_jit_comp64.c | 17 +++-
4 files changed, 88 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 0c8f885b8f48..561689a2abdf 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -141,8 +141,11 @@ struct codegen_context {
unsigned int idx;
unsigned int stack_size;
int b2p[ARRAY_SIZE(b2p)];
+ unsigned int exentry_idx;
};
+#define BPF_FIXUP_LEN 2 /* Two instructions => 8 bytes */
+
static inline void bpf_flush_icache(void *start, void *end)
{
smp_wmb(); /* smp write barrier */
@@ -166,11 +169,14 @@ static inline void bpf_clear_seen_register(struct
codegen_context *ctx, int i)
void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64
func);
int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context
*ctx,
- u32 *addrs);
+ u32 *addrs, int pass);
void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx);
void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx);
void bpf_jit_realloc_regs(struct codegen_context *ctx);
+int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct
codegen_context *ctx,
+ int insn_idx, int jmp_off, int dst_reg);
+
#endif
#endif
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index c5c9e8ad1de7..f02457c6b54f 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -101,6 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
struct bpf_prog *tmp_fp;
bool bpf_blinded = false;
bool extra_pass = false;
+ u32 extable_len;
+ u32 fixup_len;
if (!fp->jit_requested)
return org_fp;
@@ -131,7 +133,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
image = jit_data->image;
bpf_hdr = jit_data->header;
proglen = jit_data->proglen;
- alloclen = proglen + FUNCTION_DESCR_SIZE;
extra_pass = true;
goto skip_init_ctx;
}
@@ -149,7 +150,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
/* Scouting faux-generate pass 0 */
- if (bpf_jit_build_body(fp, 0, , addrs)) {
+ if (bpf_jit_build_body(fp, 0, , addrs, 0)) {
/* We hit something illegal or unsupported. */
fp = org_fp;
goto out_addrs;
@@ -162,7 +163,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
*/
if (cgctx.seen & SEEN_TAILCALL) {
cgctx.idx = 0;
- if (bpf_jit_build_body(fp, 0, , addrs)) {
+ if (bpf_jit_build_body(fp, 0, , addrs, 0)) {
fp = org_fp;
goto out_addrs;
}
@@ -177,8 +178,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
bpf_jit_build_prologue(0, );
[PATCH v3 4/8] powerpc/ppc-opcode: introduce PPC_RAW_BRANCH() macro
Define and use PPC_RAW_BRANCH() macro instead of open coding it. This macro is used while adding BPF_PROBE_MEM support. Signed-off-by: Hari Bathini Reviewed-by: Christophe Leroy --- Changes in v3: * Added Reviewed-by tag from Chris. arch/powerpc/include/asm/ppc-opcode.h | 2 ++ arch/powerpc/net/bpf_jit.h| 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index baea657bc868..f50213e2a3e0 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -566,6 +566,8 @@ #define PPC_RAW_MTSPR(spr, d) (0x7c0003a6 | ___PPC_RS(d) | __PPC_SPR(spr)) #define PPC_RAW_EIEIO()(0x7c0006ac) +#define PPC_RAW_BRANCH(addr) (PPC_INST_BRANCH | ((addr) & 0x03fc)) + /* Deal with instructions that older assemblers aren't aware of */ #definePPC_BCCTR_FLUSH stringify_in_c(.long PPC_INST_BCCTR_FLUSH) #definePPC_CP_ABORTstringify_in_c(.long PPC_RAW_CP_ABORT) diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 411c63d945c7..0c8f885b8f48 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -24,8 +24,8 @@ #define EMIT(instr)PLANT_INSTR(image, ctx->idx, instr) /* Long jump; (unconditional 'branch') */ -#define PPC_JMP(dest) EMIT(PPC_INST_BRANCH |\ -(((dest) - (ctx->idx * 4)) & 0x03fc)) +#define PPC_JMP(dest) EMIT(PPC_RAW_BRANCH((dest) - (ctx->idx * 4))) + /* blr; (unconditional 'branch' with link) to absolute address */ #define PPC_BL_ABS(dest) EMIT(PPC_INST_BL |\ (((dest) - (unsigned long)(image + ctx->idx)) & 0x03fc)) -- 2.31.1
[PATCH v3 3/8] bpf powerpc: refactor JIT compiler code
Refactor powerpc LDX JITing code to simplify adding BPF_PROBE_MEM
support.
Signed-off-by: Hari Bathini
---
Changes in v3:
* Dropped ST(X) JITing coderefactoring and ensured the changes are
minimal and relevant to BPF_PROBE_MEM support.
* Added a default for size switch case to ensure compiler would
not complain.
arch/powerpc/net/bpf_jit_comp32.c | 42 ---
arch/powerpc/net/bpf_jit_comp64.c | 40 +++--
2 files changed, 55 insertions(+), 27 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit_comp32.c
b/arch/powerpc/net/bpf_jit_comp32.c
index b60b59426a24..6e4956cd52e7 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -282,6 +282,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
u32 src_reg = bpf_to_ppc(ctx, insn[i].src_reg);
u32 src_reg_h = src_reg - 1;
u32 tmp_reg = bpf_to_ppc(ctx, TMP_REG);
+ u32 size = BPF_SIZE(code);
s16 off = insn[i].off;
s32 imm = insn[i].imm;
bool func_addr_fixed;
@@ -810,23 +811,36 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
* BPF_LDX
*/
case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
- if (!fp->aux->verifier_zext)
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
- break;
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
- if (!fp->aux->verifier_zext)
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
- break;
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
- if (!fp->aux->verifier_zext)
- EMIT(PPC_RAW_LI(dst_reg_h, 0));
- break;
+ fallthrough;
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src +
off) */
- EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
- EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
+ switch (size) {
+ case BPF_B:
+ EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+ break;
+ case BPF_H:
+ EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
+ break;
+ case BPF_W:
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+ break;
+ case BPF_DW:
+ EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
+ EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
+ break;
+ /*
+* With size not being an enum and BPF_B/H/W/DW being
macros, ensure no
+* compiler warning/error by adding a default case that
never reaches.
+*/
+ default:
+ break;
+ }
+
+ if (size != BPF_DW && !fp->aux->verifier_zext)
+ EMIT(PPC_RAW_LI(dst_reg_h, 0));
break;
/*
diff --git a/arch/powerpc/net/bpf_jit_comp64.c
b/arch/powerpc/net/bpf_jit_comp64.c
index 2a87da50d9a4..991eb43d4cd2 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -285,6 +285,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
u32 code = insn[i].code;
u32 dst_reg = b2p[insn[i].dst_reg];
u32 src_reg = b2p[insn[i].src_reg];
+ u32 size = BPF_SIZE(code);
s16 off = insn[i].off;
s32 imm = insn[i].imm;
bool func_addr_fixed;
@@ -716,25 +717,38 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
*/
/* dst = *(u8 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_B:
- EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
- if (insn_is_zext([i + 1]))
- addrs[++i] = ctx->idx * 4;
- break;
+ fallthrough;
/* dst = *(u16 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_H:
-
[PATCH v3 2/8] bpf powerpc: Remove extra_pass from bpf_jit_build_body()
From: Ravi Bangoria
In case of extra_pass, usual JIT passes are always skipped. So,
extra_pass is always false while calling bpf_jit_build_body() and
can be removed.
Signed-off-by: Ravi Bangoria
---
Changes in v3:
* Updated the changelog wording a bit.
arch/powerpc/net/bpf_jit.h| 2 +-
arch/powerpc/net/bpf_jit_comp.c | 6 +++---
arch/powerpc/net/bpf_jit_comp32.c | 4 ++--
arch/powerpc/net/bpf_jit_comp64.c | 4 ++--
4 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index d6267e93027a..411c63d945c7 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -166,7 +166,7 @@ static inline void bpf_clear_seen_register(struct
codegen_context *ctx, int i)
void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64
func);
int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context
*ctx,
- u32 *addrs, bool extra_pass);
+ u32 *addrs);
void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx);
void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx);
void bpf_jit_realloc_regs(struct codegen_context *ctx);
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 53aefee3fe70..c5c9e8ad1de7 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -149,7 +149,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
/* Scouting faux-generate pass 0 */
- if (bpf_jit_build_body(fp, 0, , addrs, false)) {
+ if (bpf_jit_build_body(fp, 0, , addrs)) {
/* We hit something illegal or unsupported. */
fp = org_fp;
goto out_addrs;
@@ -162,7 +162,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
*/
if (cgctx.seen & SEEN_TAILCALL) {
cgctx.idx = 0;
- if (bpf_jit_build_body(fp, 0, , addrs, false)) {
+ if (bpf_jit_build_body(fp, 0, , addrs)) {
fp = org_fp;
goto out_addrs;
}
@@ -210,7 +210,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
/* Now build the prologue, body code & epilogue for real. */
cgctx.idx = 0;
bpf_jit_build_prologue(code_base, );
- bpf_jit_build_body(fp, code_base, , addrs, extra_pass);
+ bpf_jit_build_body(fp, code_base, , addrs);
bpf_jit_build_epilogue(code_base, );
if (bpf_jit_enable > 1)
diff --git a/arch/powerpc/net/bpf_jit_comp32.c
b/arch/powerpc/net/bpf_jit_comp32.c
index beb12cbc8c29..b60b59426a24 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -266,7 +266,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct
codegen_context *ctx, u32
/* Assemble the body code between the prologue & epilogue */
int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context
*ctx,
- u32 *addrs, bool extra_pass)
+ u32 *addrs)
{
const struct bpf_insn *insn = fp->insnsi;
int flen = fp->len;
@@ -860,7 +860,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
case BPF_JMP | BPF_CALL:
ctx->seen |= SEEN_FUNC;
- ret = bpf_jit_get_func_addr(fp, [i], extra_pass,
+ ret = bpf_jit_get_func_addr(fp, [i], false,
_addr,
_addr_fixed);
if (ret < 0)
return ret;
diff --git a/arch/powerpc/net/bpf_jit_comp64.c
b/arch/powerpc/net/bpf_jit_comp64.c
index b87a63dba9c8..2a87da50d9a4 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -272,7 +272,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct
codegen_context *ctx, u32
/* Assemble the body code between the prologue & epilogue */
int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context
*ctx,
- u32 *addrs, bool extra_pass)
+ u32 *addrs)
{
const struct bpf_insn *insn = fp->insnsi;
int flen = fp->len;
@@ -769,7 +769,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *
case BPF_JMP | BPF_CALL:
ctx->seen |= SEEN_FUNC;
- ret = bpf_jit_get_func_addr(fp, [i], extra_pass,
+ ret = bpf_jit_get_func_addr(fp, [i], false,
_addr,
_addr_fixed);
if (ret < 0)
return ret;
--
2.31.1
[PATCH v3 1/8] bpf powerpc: Remove unused SEEN_STACK
From: Ravi Bangoria SEEN_STACK is unused on PowerPC. Remove it. Also, have SEEN_TAILCALL use 0x4000. Signed-off-by: Ravi Bangoria Reviewed-by: Christophe Leroy --- Changes in v3: * Added Reviewed-by tag from Chris. arch/powerpc/net/bpf_jit.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 99fad093f43e..d6267e93027a 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -116,8 +116,7 @@ static inline bool is_nearbranch(int offset) #define COND_LE(CR0_GT | COND_CMP_FALSE) #define SEEN_FUNC 0x2000 /* might call external helpers */ -#define SEEN_STACK 0x4000 /* uses BPF stack */ -#define SEEN_TAILCALL 0x8000 /* uses tail calls */ +#define SEEN_TAILCALL 0x4000 /* uses tail calls */ #define SEEN_VREG_MASK 0x1ff8 /* Volatile registers r3-r12 */ #define SEEN_NVREG_MASK0x0003 /* Non volatile registers r14-r31 */ -- 2.31.1
[PATCH v3 0/8] bpf powerpc: Add BPF_PROBE_MEM support in powerpc JIT compiler
Patch #1 & #2 are simple cleanup patches. Patch #3 refactors JIT compiler code with the aim to simplify adding BPF_PROBE_MEM support. Patch #4 introduces PPC_RAW_BRANCH() macro instead of open coding branch instruction. Patch #5 & #7 add BPF_PROBE_MEM support for PPC64 & PPC32 JIT compilers respectively. Patch #6 & #8 handle bad userspace pointers for PPC64 & PPC32 cases respectively. Changes in v3: * Addressed all the review comments from Christophe. Hari Bathini (4): bpf powerpc: refactor JIT compiler code powerpc/ppc-opcode: introduce PPC_RAW_BRANCH() macro bpf ppc32: Add BPF_PROBE_MEM support for JIT bpf ppc32: Access only if addr is kernel address Ravi Bangoria (4): bpf powerpc: Remove unused SEEN_STACK bpf powerpc: Remove extra_pass from bpf_jit_build_body() bpf ppc64: Add BPF_PROBE_MEM support for JIT bpf ppc64: Access only if addr is kernel address arch/powerpc/include/asm/ppc-opcode.h | 2 + arch/powerpc/net/bpf_jit.h| 19 +++-- arch/powerpc/net/bpf_jit_comp.c | 72 ++-- arch/powerpc/net/bpf_jit_comp32.c | 115 ++ arch/powerpc/net/bpf_jit_comp64.c | 88 5 files changed, 254 insertions(+), 42 deletions(-) -- 2.31.1
Re: [RFC PATCH 5/8] sched: move CPU field back into thread_info if THREAD_INFO_IN_TASK=y
On Tue, Sep 14, 2021 at 02:10:33PM +0200, Ard Biesheuvel wrote: > THREAD_INFO_IN_TASK moved the CPU field out of thread_info, but this > causes some issues on architectures that define raw_smp_processor_id() > in terms of this field, due to the fact that #include'ing linux/sched.h > to get at struct task_struct is problematic in terms of circular > dependencies. > > Given that thread_info and task_struct are the same data structure > anyway when THREAD_INFO_IN_TASK=y, let's move it back so that having > access to the type definition of struct thread_info is sufficient to > reference the CPU number of the current task. > > Signed-off-by: Ard Biesheuvel Acked-by: Catalin Marinas
Re: [RFC PATCH 2/8] x86: add CPU field to struct thread_info
On Tue, Sep 14, 2021 at 02:10:30PM +0200, Ard Biesheuvel wrote:
> The CPU field will be moved back into thread_info even when
> THREAD_INFO_IN_TASK is enabled, so add it back to x86's definition of
> struct thread_info.
>
> Signed-off-by: Ard Biesheuvel
> ---
> arch/x86/include/asm/thread_info.h | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/arch/x86/include/asm/thread_info.h
> b/arch/x86/include/asm/thread_info.h
> index cf132663c219..ebec69c35e95 100644
> --- a/arch/x86/include/asm/thread_info.h
> +++ b/arch/x86/include/asm/thread_info.h
> @@ -57,6 +57,9 @@ struct thread_info {
> unsigned long flags; /* low level flags */
> unsigned long syscall_work; /* SYSCALL_WORK_ flags */
> u32 status; /* thread synchronous flags */
> +#ifdef CONFIG_SMP
> + u32 cpu;/* current CPU */
> +#endif
> };
>
> #define INIT_THREAD_INFO(tsk)\
> --
Acked-by: Borislav Petkov
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
Re: [RFC PATCH 0/8] Move task_struct::cpu back into thread_info
On Tue, 14 Sept 2021 at 15:55, Mark Rutland wrote:
>
> On Tue, Sep 14, 2021 at 02:10:28PM +0200, Ard Biesheuvel wrote:
> > Commit c65eacbe290b ("sched/core: Allow putting thread_info into
> > task_struct") mentions that, along with moving thread_info into
> > task_struct, the cpu field is moved out of the former into the latter,
> > but does not explain why.
>
> From what I recall of talking to Andy around that time, when converting
> arm64 over, the theory was that over time we'd move more and more out of
> thread_info and into task_struct or thread_struct, until task_struct
> supplanted thread_info entirely, and that all became generic.
>
> I think the key gain there was making things more *generic*, and there
> are other ways we could do that in future without moving more into
> task_struct (e.g. with a geenric thread_info and arch_thread_info inside
> that).
>
> With that in mind, and given the diffstat, I think this is worthwhile.
>
> FWIW, for the series:
>
> Acked-by: Mark Rutland
>
Thanks.
Any comments on this from the various arch maintainers? Especially
power, as Christophe seems happy with this but there are 3 different
patches affecting power that need a maintainer ack.
Re: [RFC PATCH 1/8] arm64: add CPU field to struct thread_info
On Thu, 16 Sept 2021 at 16:41, Catalin Marinas wrote: > > On Tue, Sep 14, 2021 at 02:10:29PM +0200, Ard Biesheuvel wrote: > > The CPU field will be moved back into thread_info even when > > THREAD_INFO_IN_TASK is enabled, so add it back to arm64's definition of > > struct thread_info. > > > > Signed-off-by: Ard Biesheuvel > > Acked-by: Catalin Marinas Thanks. I take it this applies to patch #5 as well?
Re: [PATCH v3] lib/zlib_inflate/inffast: Check config in C to avoid unused function warning
Dear Linux folks,
Am 20.09.21 um 17:45 schrieb Nathan Chancellor:
On Mon, Sep 20, 2021 at 10:43:33AM +0200, Paul Menzel wrote:
Building Linux for ppc64le with Ubuntu clang version 12.0.0-3ubuntu1~21.04.1
shows the warning below.
arch/powerpc/boot/inffast.c:20:1: warning: unused function
'get_unaligned16' [-Wunused-function]
get_unaligned16(const unsigned short *p)
^
1 warning generated.
Fix it, by moving the check from the preprocessor to C, so the compiler
sees the use.
Signed-off-by: Paul Menzel
Reviewed-by: Nathan Chancellor
Tested-by: Nathan Chancellor
---
v2: Use IS_ENABLED
v3: Use if statement over ternary operator as requested by Christophe
lib/zlib_inflate/inffast.c | 13 ++---
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/lib/zlib_inflate/inffast.c b/lib/zlib_inflate/inffast.c
index f19c4fbe1be7..2843f9bb42ac 100644
--- a/lib/zlib_inflate/inffast.c
+++ b/lib/zlib_inflate/inffast.c
@@ -253,13 +253,12 @@ void inflate_fast(z_streamp strm, unsigned start)
sfrom = (unsigned short *)(from);
loops = len >> 1;
- do
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
- *sout++ = *sfrom++;
-#else
- *sout++ = get_unaligned16(sfrom++);
-#endif
- while (--loops);
+ do {
+ if
(IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+ *sout++ = *sfrom++;
+ else
+ *sout++ = get_unaligned16(sfrom++);
+ } while (--loops);
out = (unsigned char *)sout;
from = (unsigned char *)sfrom;
} else { /* dist == 1 or dist == 2 */
--
2.33.0
Just for the record,
I compared both object files by running `objdump -d`, and the result is
the same.
The binary differed (`vbindiff`), but I guess this is due to the
increased revision (`make bindeb-pkg`).
without a change (Linus’ current master):
0B50: 00 00 00 00 00 00 00 00 1F 01 00 00 36 00 00 00
6...
^
0B60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0B70: 00 00 00 00 00 00 00 00 29 01 00 00 32 00 00 00
)...2...
^
v2 (ternary operator):
0B50: 00 00 00 00 00 00 00 00 1C 01 00 00 36 00 00 00
6...
0B60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0B70: 00 00 00 00 00 00 00 00 26 01 00 00 32 00 00 00
&...2...
v3 (if-else statement):
0B50: 00 00 00 00 00 00 00 00 1E 01 00 00 36 00 00 00
6...
0B60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0B70: 00 00 00 00 00 00 00 00 28 01 00 00 32 00 00 00
(...2...
Kind regards,
Paul
[PATCH] mm: Remove HARDENED_USERCOPY_FALLBACK
This has served its purpose and is no longer used. All usercopy
violations appear to have been handled by now, any remaining
instances (or new bugs) will cause copies to be rejected.
This isn't a direct revert of commit 2d891fbc3bb6 ("usercopy: Allow
strict enforcement of whitelists"); since usercopy_fallback is
effectively 0, the fallback handling is removed too.
This also removes the usercopy_fallback module parameter on
slab_common.
Link: https://github.com/KSPP/linux/issues/153
Signed-off-by: Stephen Kitt
Suggested-by: Kees Cook
---
arch/powerpc/configs/skiroot_defconfig | 1 -
include/linux/slab.h | 2 --
mm/slab.c | 13 -
mm/slab_common.c | 8
mm/slub.c | 14 --
security/Kconfig | 14 --
6 files changed, 52 deletions(-)
diff --git a/arch/powerpc/configs/skiroot_defconfig
b/arch/powerpc/configs/skiroot_defconfig
index b806a5d3a695..c3ba614c973d 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -275,7 +275,6 @@ CONFIG_NLS_UTF8=y
CONFIG_ENCRYPTED_KEYS=y
CONFIG_SECURITY=y
CONFIG_HARDENED_USERCOPY=y
-# CONFIG_HARDENED_USERCOPY_FALLBACK is not set
CONFIG_HARDENED_USERCOPY_PAGESPAN=y
CONFIG_FORTIFY_SOURCE=y
CONFIG_SECURITY_LOCKDOWN_LSM=y
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 0c97d788762c..5b21515afae0 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -142,8 +142,6 @@ struct mem_cgroup;
void __init kmem_cache_init(void);
bool slab_is_available(void);
-extern bool usercopy_fallback;
-
struct kmem_cache *kmem_cache_create(const char *name, unsigned int size,
unsigned int align, slab_flags_t flags,
void (*ctor)(void *));
diff --git a/mm/slab.c b/mm/slab.c
index d0f725637663..4d826394ffcb 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4207,19 +4207,6 @@ void __check_heap_object(const void *ptr, unsigned long
n, struct page *page,
n <= cachep->useroffset - offset + cachep->usersize)
return;
- /*
-* If the copy is still within the allocated object, produce
-* a warning instead of rejecting the copy. This is intended
-* to be a temporary method to find any missing usercopy
-* whitelists.
-*/
- if (usercopy_fallback &&
- offset <= cachep->object_size &&
- n <= cachep->object_size - offset) {
- usercopy_warn("SLAB object", cachep->name, to_user, offset, n);
- return;
- }
-
usercopy_abort("SLAB object", cachep->name, to_user, offset, n);
}
#endif /* CONFIG_HARDENED_USERCOPY */
diff --git a/mm/slab_common.c b/mm/slab_common.c
index a4a571428c51..925b00c1d4e8 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -37,14 +37,6 @@ LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
struct kmem_cache *kmem_cache;
-#ifdef CONFIG_HARDENED_USERCOPY
-bool usercopy_fallback __ro_after_init =
- IS_ENABLED(CONFIG_HARDENED_USERCOPY_FALLBACK);
-module_param(usercopy_fallback, bool, 0400);
-MODULE_PARM_DESC(usercopy_fallback,
- "WARN instead of reject usercopy whitelist violations");
-#endif
-
static LIST_HEAD(slab_caches_to_rcu_destroy);
static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work);
static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
diff --git a/mm/slub.c b/mm/slub.c
index 3f96e099817a..77f53e76a3c3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4125,7 +4125,6 @@ void __check_heap_object(const void *ptr, unsigned long
n, struct page *page,
{
struct kmem_cache *s;
unsigned int offset;
- size_t object_size;
bool is_kfence = is_kfence_address(ptr);
ptr = kasan_reset_tag(ptr);
@@ -4158,19 +4157,6 @@ void __check_heap_object(const void *ptr, unsigned long
n, struct page *page,
n <= s->useroffset - offset + s->usersize)
return;
- /*
-* If the copy is still within the allocated object, produce
-* a warning instead of rejecting the copy. This is intended
-* to be a temporary method to find any missing usercopy
-* whitelists.
-*/
- object_size = slab_ksize(s);
- if (usercopy_fallback &&
- offset <= object_size && n <= object_size - offset) {
- usercopy_warn("SLUB object", s->name, to_user, offset, n);
- return;
- }
-
usercopy_abort("SLUB object", s->name, to_user, offset, n);
}
#endif /* CONFIG_HARDENED_USERCOPY */
diff --git a/security/Kconfig b/security/Kconfig
index 0ced7fd33e4d..d9698900c9b7 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -163,20 +163,6 @@ config HARDENED_USERCOPY
or are part of the kernel text. This kills entire classes
of heap overflow exploits and similar kernel memory exposures.
-config
